diff --git a/README.md b/README.md new file mode 100644 index 0000000..7c8c1b7 --- /dev/null +++ b/README.md @@ -0,0 +1,205 @@ +# LLM Lab + +Un laboratoire pour tester et comparer différents modèles de langage (LLM) via Ollama. + +## Fonctionnalités + +- **Modèles intégrés** : Support pour Mistral 7B, CodeLlama 13B et Llama2 13B via Ollama +- **Agents spécialisés** : Agents configurés pour différentes tâches (code, documentation, gestion de projet...) +- **Interface graphique de chat** : Interface visuelle complète pour interagir avec les agents et personnaliser les paramètres +- **Moniteur système** : Interface graphique pour surveiller les ressources système, Ollama et GPU +- **Interface CLI** : Interface en ligne de commande simple pour interagir avec les agents + +## Modèles disponibles + +Ce projet prend en charge les modèles suivants : + +- **Mistral 7B** : `mistral:latest` via Ollama - pour des tests rapides et la documentation +- **CodeLlama 13B Python** : `codellama:13b-python` via Ollama - pour le développement et le code +- **Llama2 13B** : `llama2:13b` via Ollama - pour la gestion de connaissances et de projet + +## Agents spécialisés + +- **cursor** : Agent de programmation (CodeLlama) pour Python, JavaScript et développement web +- **obsidian** : Agent de gestion de connaissances (Llama2) pour l'organisation d'informations +- **test** : Agent de test rapide (Mistral) pour vérifier rapidement les fonctionnalités +- **python** : Expert Python (CodeLlama) +- **webdev** : Expert développement web (CodeLlama) +- **projectmanager** : Chef de projet (Llama2) +- **documentaliste** : Spécialiste en documentation (Mistral) + +## Installation + +### Prérequis + +- Python 3.8+ +- [Ollama](https://ollama.ai/) installé et en cours d'exécution sur `localhost:11434` +- Les modèles correspondants installés dans Ollama + +### Installation des modèles Ollama + +```bash +# Installation des modèles +ollama pull mistral:latest +ollama pull codellama:13b-python +ollama pull llama2:13b +``` + +### Configuration de l'environnement + +Utilisez le script de configuration automatique : + +```bash +# Exécuter le script de configuration +./setup_env.sh +``` + +Ce script va : +1. Vérifier et installer les dépendances système nécessaires (venv, tkinter) +2. Créer un nouvel environnement virtuel Python +3. Installer toutes les dépendances requises +4. Configurer les scripts pour une utilisation facile + +### Installation manuelle (alternative) + +Si vous préférez l'installation manuelle : + +```bash +# Créer un environnement virtuel +python3 -m venv llmlab + +# Activer l'environnement virtuel +source llmlab/bin/activate + +# Installer les dépendances +pip install -r requirements.txt + +# Installer tkinter si nécessaire (au niveau du système) +sudo apt install python3-tk +``` + +## Utilisation + +### Utilisation avec le script de lancement + +Le moyen le plus simple d'utiliser LLM Lab est d'utiliser le script de lancement `run.sh` : + +```bash +# Afficher l'aide +./run.sh help + +# Lister les agents disponibles +./run.sh list + +# Lancer l'interface graphique de chat +./run.sh gui + +# Lancer le chat en ligne de commande avec un agent spécifique +./run.sh chat cursor # Agent de programmation +./run.sh chat obsidian # Agent de gestion de connaissances +./run.sh chat test # Agent de test rapide + +# Lancer le moniteur système +./run.sh monitor +``` + +### Utilisation directe + +Si vous préférez utiliser directement les scripts Python après avoir activé l'environnement virtuel : + +```bash +# Activer l'environnement virtuel +source llmlab/bin/activate + +# Lancer l'interface graphique de chat +./chat_gui.py + +# Lister les agents disponibles +./chat.py --list + +# Lancer le chat en ligne de commande avec un agent +./chat.py cursor + +# Lancer le moniteur système +./monitor.py +``` + +## Interface graphique de chat + +L'interface graphique de chat offre de nombreuses fonctionnalités avancées : + +- **Sélection d'agent** : Choisissez parmi tous les agents disponibles +- **Personnalisation des modèles** : Changez le modèle utilisé par un agent +- **Paramètres ajustables** : Modifiez tous les paramètres de génération (température, top-p, etc.) +- **Presets** : Appliquez des configurations prédéfinies (Créatif, Précis, Code, etc.) +- **Sauvegarde et chargement** : Enregistrez et chargez des conversations +- **Exportation** : Exportez vos conversations en markdown, texte ou JSON + +Pour lancer l'interface graphique : + +```bash +./run.sh gui +``` + +## Moniteur système + +Le moniteur système fournit une interface graphique pour surveiller : + +- **Ressources système** : CPU, RAM, disque +- **Serveur Ollama** : État, modèles disponibles, tailles +- **GPU NVIDIA** (si disponible) : Utilisation, mémoire, température, processus +- **Journaux d'activité** : Logs en temps réel + +Pour l'utiliser : + +```bash +./run.sh monitor +``` + +## Structure du projet + +- `core/` : Classes de base et implémentations des modèles + - `base_llm.py` : Classe de base pour tous les modèles LLM + - `factory.py` : Factory pour créer des instances de modèle + - `mistral7b.py` : Implémentation du modèle Mistral 7B + - `codellama13b_python.py` : Implémentation du modèle CodeLlama 13B Python + - `llama2_13b.py` : Implémentation du modèle Llama2 13B +- `agents/` : Configuration des agents spécialisés + - `roles.py` : Définition des différents agents et leurs paramètres +- `utils/` : Outils et utilitaires + - `agent_manager.py` : Gestionnaire pour créer et configurer les agents + - `system_monitor.py` : Moniteur de ressources système + - `chat_ui.py` : Interface graphique de chat +- `tests/` : Tests unitaires et d'intégration +- `examples/` : Exemples d'utilisation +- `logs/` : Logs des résultats de génération (créé automatiquement) +- `chat_history/` : Historique des conversations (créé automatiquement) +- `saved_params/` : Paramètres personnalisés sauvegardés (créé automatiquement) + +## Personnalisation + +### Ajouter un nouvel agent + +Pour ajouter un nouvel agent, modifiez le fichier `agents/roles.py` et ajoutez une nouvelle entrée au dictionnaire `AGENTS` : + +```python +"mon_agent": { + "model": "mistral:latest", # Modèle à utiliser + "system_prompt": ( + "Description du rôle de l'agent..." + ), + "params": { + "temperature": 0.7, + "top_p": 0.9, + # Autres paramètres... + } +} +``` + +### Ajouter un nouveau modèle + +Pour ajouter un nouveau modèle LLM : + +1. Créez une nouvelle classe dans `core/` (par exemple `core/nouveau_modele.py`) +2. Ajoutez le modèle au registre dans `core/factory.py` +3. Mettez à jour la documentation et les tests \ No newline at end of file diff --git a/adaptation_windows_scripts.md b/adaptation_windows_scripts.md new file mode 100644 index 0000000..6fd1e3d --- /dev/null +++ b/adaptation_windows_scripts.md @@ -0,0 +1,409 @@ +# Adaptations spécifiques des scripts Python pour Windows + +Ce document détaille les adaptations nécessaires pour chaque script Python du projet LLM Lab lors de la migration vers Windows. + +## Modifications communes à tous les scripts + +### 1. Gestion des chemins + +Pour tous les scripts, remplacez les chemins absolus par des chemins relatifs: + +```python +# Avant +DATA_DIR = '/home/fgras-ca/llm_lab/data' + +# Après +import os +# Obtenir le chemin absolu du répertoire contenant le script +BASE_DIR = os.path.dirname(os.path.abspath(__file__)) +DATA_DIR = os.path.join(BASE_DIR, 'data') +``` + +### 2. Installation des dépendances Windows + +Ces dépendances sont nécessaires pour Windows: + +```cmd +pip install wmi psutil requests pillow +pip install pywin32 # Pour l'accès aux API Windows +``` + +## Adaptations spécifiques par fichier + +### 1. chat_gui.py + +```python +# Avant de créer la fenêtre principale: +import os +import platform + +# Pour éviter les problèmes d'échelle sur les écrans haute résolution +if platform.system() == 'Windows': + import ctypes + try: + ctypes.windll.shcore.SetProcessDpiAwareness(1) + except: + pass + + # Configuration CUDA pour Ollama + os.environ["CUDA_VISIBLE_DEVICES"] = "0" + os.environ["OMP_NUM_THREADS"] = "8" +``` + +### 2. monitor.py + +```python +def _update_system_info(self): + """Met à jour les informations système""" + # Informations système + self.os_label.config(text=f"{platform.system()} {platform.release()}") + self.cpu_label.config(text=f"{psutil.cpu_count(logical=False)} cœurs ({psutil.cpu_count()} threads)") + + # Détection avancée de la RAM + try: + if platform.system() == "Windows": + # Utiliser WMI pour Windows + import wmi + computer = wmi.WMI() + for os_info in computer.Win32_OperatingSystem(): + total_ram = float(os_info.TotalVisibleMemorySize) / (1024 * 1024) # en GB + else: + # Utiliser psutil pour Linux/Mac + ram = psutil.virtual_memory() + total_ram = ram.total / (1024 * 1024 * 1024) # GB + + self.ram_label.config(text=f"{total_ram:.1f} GB") + except Exception as e: + self._log(f"Erreur lors de la détection de la RAM: {str(e)}") + self.ram_label.config(text="Détection impossible") +``` + +### 3. utils/system_monitor.py + +```python +def _check_gpu_available(self): + """Vérifie si un GPU NVIDIA est disponible""" + try: + if platform.system() == "Windows": + import wmi + computer = wmi.WMI() + # Vérifier les contrôleurs vidéo + for gpu in computer.Win32_VideoController(): + if "NVIDIA" in gpu.Name: + return True + return False + else: + # Pour Linux/Mac, utiliser nvidia-smi + result = subprocess.run(['nvidia-smi'], capture_output=True, text=True) + return result.returncode == 0 + except: + return False + +def _update_gpu_info(self): + """Met à jour les informations GPU""" + if not self.gpu_available: + return + + try: + if platform.system() == "Windows": + # Utiliser WMI pour Windows + import wmi + computer = wmi.WMI() + + # Obtenir le nom du modèle GPU + for gpu in computer.Win32_VideoController(): + if "NVIDIA" in gpu.Name: + model_name = gpu.Name + self.gpu_model_label.config(text=model_name) + break + + # Utiliser nvidia-smi pour les métriques détaillées même sous Windows + result = subprocess.run( + ['nvidia-smi', '--query-gpu=memory.total,memory.used,utilization.gpu,temperature.gpu', + '--format=csv,noheader,nounits'], + capture_output=True, + text=True, + check=True + ) + + if result.returncode == 0: + # Analyser les résultats + gpu_data = result.stdout.strip().split(',') + + if len(gpu_data) >= 4: + # Mémoire totale et utilisée + total_memory = float(gpu_data[0].strip()) + used_memory = float(gpu_data[1].strip()) + memory_percent = (used_memory / total_memory) * 100 if total_memory > 0 else 0 + + self.gpu_memory_label.config(text=f"{used_memory:.0f} MiB / {total_memory:.0f} MiB") + self.gpu_mem_progress["value"] = memory_percent + self.gpu_mem_percent.config(text=f"{memory_percent:.1f}%") + + # Utilisation GPU + gpu_util = float(gpu_data[2].strip()) + self.gpu_compute_progress["value"] = gpu_util + self.gpu_compute_percent.config(text=f"{gpu_util:.1f}%") + + # Température + temp = float(gpu_data[3].strip()) + self.gpu_temp_progress["value"] = temp + self.gpu_temp_label.config(text=f"{temp:.1f}°C") + else: + # Code existant pour Linux/Mac + # ... + except Exception as e: + self._log(f"Erreur de mise à jour GPU: {str(e)}") +``` + +### 4. utils/ollama_api.py + +```python +import os +import platform +import requests +import json + +# Optimisations pour Windows +if platform.system() == "Windows": + os.environ["CUDA_VISIBLE_DEVICES"] = "0" + os.environ["OMP_NUM_THREADS"] = str(os.cpu_count()) + +class OllamaAPI: + def __init__(self, base_url="http://localhost:11434"): + self.base_url = base_url + + # Charger la configuration optimisée si elle existe + config_path = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), + "ollama_config.json") + self.default_params = {} + + if os.path.exists(config_path): + try: + with open(config_path, 'r') as f: + self.default_params = json.load(f) + except: + pass + + def generate(self, model, prompt, params=None): + """Génère une réponse du modèle""" + url = f"{self.base_url}/api/generate" + + # Fusionner les paramètres par défaut avec ceux fournis + request_params = self.default_params.copy() + if params: + request_params.update(params) + + data = { + "model": model, + "prompt": prompt, + **request_params + } + + response = requests.post(url, json=data) + response.raise_for_status() + + return response.json() +``` + +### 5. installer.bat - Script d'installation Windows + +```batch +@echo off +setlocal + +echo Installation de LLM Lab pour Windows... + +REM Vérifier si Python est installé +python --version > nul 2>&1 +if %ERRORLEVEL% NEQ 0 ( + echo Python n'est pas installé. Veuillez installer Python 3.10 ou supérieur. + echo Téléchargez Python depuis https://www.python.org/downloads/ + exit /b 1 +) + +REM Créer l'environnement virtuel +if not exist venv ( + echo Création de l'environnement virtuel... + python -m venv venv +) + +REM Activer l'environnement virtuel +call venv\Scripts\activate + +REM Installer les dépendances +echo Installation des dépendances... +pip install -r requirements.txt +pip install wmi psutil requests pillow pywin32 + +REM Vérifier si CUDA est disponible +where nvidia-smi > nul 2>&1 +if %ERRORLEVEL% EQU 0 ( + echo Détection de CUDA: NVIDIA GPU disponible + nvidia-smi +) else ( + echo Aucun GPU NVIDIA détecté +) + +REM Vérifier si Ollama est installé +curl -s http://localhost:11434/api/tags > nul 2>&1 +if %ERRORLEVEL% EQU 0 ( + echo Ollama est en cours d'exécution +) else ( + echo Ollama n'est pas en cours d'exécution ou n'est pas installé + echo Téléchargez Ollama depuis https://ollama.com/download/windows +) + +REM Créer les dossiers nécessaires +if not exist data mkdir data +if not exist logs mkdir logs +if not exist presets mkdir presets +if not exist history mkdir history + +echo. +echo Installation terminée ! Pour lancer LLM Lab: +echo - Activez l'environnement: venv\Scripts\activate +echo - Lancez l'interface GUI: run.bat gui +echo - Lancez le moniteur: run.bat monitor +echo. + +endlocal +``` + +## Configuration des modèles Ollama + +Pour optimiser les performances des modèles, créez des fichiers Modelfile pour chaque modèle: + +### Modelfile pour modèles Llama 3 (exemple) + +``` +FROM llama3:latest + +# Optimisations pour Windows +PARAMETER temperature 0.7 +PARAMETER num_ctx 8192 +PARAMETER num_gpu 100 +PARAMETER num_thread 8 +PARAMETER num_batch 512 +``` + +Pour appliquer: +```cmd +ollama create llama3-optimized -f Modelfile +``` + +## Monitoring des performances + +Pour un monitoring plus précis sous Windows, ajoutez ces fonctions à `system_monitor.py`: + +```python +def _get_windows_process_info(self, process_name): + """Récupère les informations d'un processus Windows""" + if platform.system() != "Windows": + return None + + import wmi + computer = wmi.WMI() + + processes = [] + for process in computer.Win32_Process(): + if process_name.lower() in process.Name.lower(): + processes.append({ + 'pid': process.ProcessId, + 'name': process.Name, + 'cpu': 0, # À calculer + 'memory': float(process.WorkingSetSize) / (1024 * 1024) # MB + }) + + return processes + +def _get_ollama_performance(self): + """Récupère les performances d'Ollama""" + processes = [] + + if platform.system() == "Windows": + processes = self._get_windows_process_info("ollama") + else: + # Code Linux existant + pass + + return processes +``` + +## Test de la migration + +Créez un script `test_windows.py` pour vérifier que tout fonctionne correctement: + +```python +import os +import platform +import psutil +import tkinter as tk +import requests + +def check_system(): + print(f"Système: {platform.system()} {platform.release()}") + print(f"Python: {platform.python_version()}") + + # Vérifier RAM + ram = psutil.virtual_memory() + print(f"RAM: {ram.total / (1024**3):.1f} GB") + + # Vérifier GPU + try: + import wmi + computer = wmi.WMI() + for gpu in computer.Win32_VideoController(): + print(f"GPU: {gpu.Name}") + except: + print("Erreur lors de la détection du GPU via WMI") + + # Vérifier Ollama + try: + response = requests.get("http://localhost:11434/api/tags") + if response.status_code == 200: + print("Ollama: En ligne") + models = response.json().get("models", []) + print(f"Modèles installés: {len(models)}") + for model in models: + print(f" - {model.get('name')}") + else: + print(f"Ollama: Erreur {response.status_code}") + except: + print("Ollama: Hors ligne") + + # Vérifier Tkinter + try: + root = tk.Tk() + root.title("Test Tkinter") + tk.Label(root, text="Tkinter fonctionne correctement").pack(padx=20, pady=20) + print("Tkinter: OK") + return root + except: + print("Tkinter: Erreur") + return None + +if __name__ == "__main__": + print("=== Test d'installation LLM Lab sur Windows ===") + root = check_system() + if root: + print("\nTout est correctement configuré!") + print("Fermer la fenêtre Tkinter pour terminer le test.") + root.mainloop() + else: + print("\nDes erreurs ont été détectées dans l'installation.") +``` + +## Recommandations spécifiques pour Windows + +1. **Performances optimales**: + - Réglez le plan d'alimentation sur "Hautes performances" + - Désactivez l'économiseur d'écran et la mise en veille pendant l'utilisation + +2. **GPU NVIDIA**: + - Utilisez le Panneau de configuration NVIDIA pour régler les performances sur "Préférer les performances maximales" + - Mettez à jour les pilotes régulièrement + +3. **Antivirus**: + - Ajoutez le dossier LLM_Lab aux exceptions de l'antivirus + - Excluez `ollama.exe` du scan en temps réel \ No newline at end of file diff --git a/agents/__pycache__/roles.cpython-312.pyc b/agents/__pycache__/roles.cpython-312.pyc index 0199bf0..3a45089 100644 Binary files a/agents/__pycache__/roles.cpython-312.pyc and b/agents/__pycache__/roles.cpython-312.pyc differ diff --git a/agents/roles.py b/agents/roles.py index 10e503b..3a4eb59 100644 --- a/agents/roles.py +++ b/agents/roles.py @@ -1,44 +1,129 @@ # agents/roles.py AGENTS = { - "assistant_technique": { + # === Agents spécialisés avec modèles spécifiques === + + # Agent CodeLlama pour Cursor - Spécialisé en programmation + "cursor": { + "model": "codellama:13b-python", # Utilise CodeLlama 13B Python "system_prompt": ( - "Tu es un assistant technique spécialisé en informatique et en support aux utilisateurs. " - "Tu réponds de manière concise, claire et structurée aux questions techniques." + "Tu es Cursor, un assistant de programmation expert. " + "Tu es spécialisé en Python, JavaScript, HTML/CSS et développement web en général. " + "Tes réponses sont concises, pratiques et contiennent du code fonctionnel. " + "Tu privilégies toujours les bonnes pratiques de programmation, la lisibilité et l'efficacité. " + "Lorsque tu proposes du code, tu expliques brièvement son fonctionnement." ), "params": { - "temperature": 0.5, - "top_p": 0.9 + "temperature": 0.2, # Faible température pour du code précis + "top_p": 0.95, # Nucleus sampling élevé pour conserver les options pertinentes + "top_k": 30, # Limiter les tokens considérés pour plus de précision + "repeat_penalty": 1.2, # Pénalité élevée pour éviter les répétitions dans le code + "num_predict": 2048, # Nombre élevé de tokens pour générer des blocs de code complets + "stop": ["```", "```python", "```javascript", "```html", "```css"] # Arrêter à la fin des blocs de code } }, - "juriste": { + + # Agent Llama2 pour Obsidian - Gestion de connaissances + "obsidian": { + "model": "llama2:13b", # Utilise Llama2 13B "system_prompt": ( - "Tu es un juriste expert en droit du travail français. " - "Tes réponses sont précises, sourcées et adaptées au contexte légal." + "Tu es Obsidian, un assistant spécialisé dans la gestion des connaissances et la prise de notes. " + "Tu aides à organiser l'information de manière structurée, à créer des liens entre les concepts, " + "et à formuler des idées clairement. Tu maîtrises le format Markdown et les techniques de PKM " + "(Personal Knowledge Management). Tu fournis des réponses bien structurées et organisées." ), "params": { - "temperature": 0.3, - "top_p": 0.8 + "temperature": 0.7, # Température équilibrée pour la créativité et la cohérence + "top_p": 0.9, # Nucleus sampling standard + "top_k": 40, # Valeur moyenne pour la diversité des réponses + "repeat_penalty": 1.1, # Pénalité standard pour les répétitions + "num_predict": 1024, # Taille modérée pour des explications détaillées + "stop": [] # Pas d'arrêt spécifique } }, - "chercheur": { + + # Agent Mistral pour tests rapides + "test": { + "model": "mistral:latest", # Utilise Mistral 7B pour sa rapidité "system_prompt": ( - "Tu es un chercheur scientifique qui explore des solutions innovantes. " - "Tu analyses les problèmes en profondeur et proposes des pistes pertinentes." + "Tu es un agent de test rapide. Tes réponses sont brèves et directes. " + "Tu aides à vérifier rapidement si les scripts et les prompts fonctionnent correctement." ), "params": { - "temperature": 0.9, - "top_p": 1.0 + "temperature": 0.5, # Température modérée + "top_p": 0.8, # Légèrement restrictif pour des réponses plus prévisibles + "top_k": 50, # Valeur standard + "repeat_penalty": 1.0, # Pas de pénalité particulière + "num_predict": 256, # Réponses courtes pour des tests rapides + "stop": [] # Pas d'arrêt spécifique } }, - "formateur": { + + # === Agents spécialisés par domaine (avec modèle par défaut) === + + # Agent spécialisé en Python + "python": { + "model": "codellama:13b-python", # Utilise CodeLlama par défaut "system_prompt": ( - "Tu es un formateur pédagogique et bienveillant. " - "Tu expliques des concepts de façon claire et progressive, adaptés à des débutants." + "Tu es un expert Python avec une connaissance approfondie de l'écosystème Python. " + "Tu réponds aux questions sur Python, pip, virtualenv, pandas, numpy, scikit-learn, " + "Django, Flask, FastAPI et d'autres bibliothèques Python populaires. " + "Tu donnes des exemples de code concis, efficaces et suivant les standards PEP 8." ), "params": { - "temperature": 0.6, - "top_p": 0.95 + "temperature": 0.3, # Faible température pour du code précis + "top_p": 0.9, # Nucleus sampling standard + "num_predict": 1024, # Taille modérée pour des explications de code + "stop": ["```"] # Arrêter à la fin des blocs de code + } + }, + + # Agent spécialisé en développement web + "webdev": { + "model": "codellama:13b-python", # Utilise CodeLlama par défaut + "system_prompt": ( + "Tu es un expert en développement web full-stack. " + "Tu maîtrises HTML, CSS, JavaScript, React, Vue.js, Node.js, et les API REST. " + "Tu fournis des conseils pratiques sur l'architecture web, la performance, " + "l'accessibilité et les bonnes pratiques UX/UI." + ), + "params": { + "temperature": 0.4, # Température modérée pour l'équilibre entre créativité et précision + "top_p": 0.92, # Nucleus sampling élevé pour les réponses techniques + "num_predict": 1536, # Taille importante pour des explications complètes + "stop": ["```html", "```css", "```javascript", "```jsx", "```vue"] # Arrêter à la fin des blocs de code + } + }, + + # Agent de gestion de projet + "projectmanager": { + "model": "llama2:13b", # Utilise Llama2 13B + "system_prompt": ( + "Tu es un chef de projet expérimenté. Tu aides à planifier, organiser et suivre " + "des projets de développement. Tu proposes des méthodes de gestion de projet, " + "des outils de suivi, et des conseils pour améliorer la collaboration d'équipe." + ), + "params": { + "temperature": 0.6, # Température équilibrée + "top_p": 0.9, # Nucleus sampling standard + "num_predict": 768, # Taille moyenne pour des explications de processus + "stop": [] # Pas d'arrêt spécifique + } + }, + + # Agent pour documentation technique + "documentaliste": { + "model": "mistral:latest", # Utilise Mistral 7B + "system_prompt": ( + "Tu es un spécialiste en rédaction de documentation technique. " + "Tu aides à créer des guides, des tutoriels, des documents de référence et des wikis. " + "Tu sais rendre l'information technique accessible et structurée." + ), + "params": { + "temperature": 0.5, # Température modérée + "top_p": 0.85, # Légèrement restrictif pour cohérence + "num_predict": 512, # Taille moyenne + "stop": [] # Pas d'arrêt spécifique } } } \ No newline at end of file diff --git a/chat.py b/chat.py new file mode 100755 index 0000000..68e638e --- /dev/null +++ b/chat.py @@ -0,0 +1,76 @@ +#!/usr/bin/env python3 +""" +Interface en ligne de commande pour interagir avec les agents LLM +Usage: python chat.py [nom_agent] +""" +import sys +import os +import argparse +from utils.agent_manager import AgentManager + +def main(): + # Créer le parser d'arguments + parser = argparse.ArgumentParser(description="Interface en ligne de commande pour interagir avec les agents LLM") + parser.add_argument("agent", nargs="?", default="test", help="Nom de l'agent à utiliser (défaut: test)") + parser.add_argument("--list", "-l", action="store_true", help="Lister les agents disponibles") + parser.add_argument("--info", "-i", action="store_true", help="Afficher les informations détaillées des agents") + + # Parser les arguments + args = parser.parse_args() + + # Vérifier si le dossier logs existe + os.makedirs("logs", exist_ok=True) + + # Lister les agents si demandé + if args.list: + print("\nAgents disponibles:") + for agent in AgentManager.list_agents(): + print(f"- {agent}") + return + + # Afficher les infos détaillées si demandé + if args.info: + print("\nInformations sur les agents:") + for agent_name, info in AgentManager.list_agents().items(): + print(f"\n=== {agent_name} ===") + print(f"Modèle: {info['model']}") + print(f"Description: {info['description']}") + return + + # Vérifier si l'agent existe + agent_name = args.agent + try: + # Créer l'agent + agent = AgentManager.create(agent_name) + print(f"\nAgent '{agent_name}' initialisé (modèle: {agent.model})") + print("Entrez votre message (ou 'exit' pour quitter)") + + # Boucle de conversation + while True: + print("\n> ", end="") + user_input = input() + + if user_input.lower() in ("exit", "quit", "q", "bye"): + print("Au revoir!") + break + + if not user_input.strip(): + continue + + try: + # Générer la réponse + print("\nGénération en cours...\n") + response = agent.generate(user_input) + + # Afficher la réponse + print(f"\n{response}") + + except Exception as e: + print(f"Erreur: {str(e)}") + + except ValueError as e: + print(f"Erreur: {str(e)}") + print("Utilisez --list pour voir les agents disponibles") + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/chat_gui.py b/chat_gui.py new file mode 100755 index 0000000..6b55115 --- /dev/null +++ b/chat_gui.py @@ -0,0 +1,8 @@ +#!/usr/bin/env python3 +""" +Interface graphique pour le chat avec les modèles LLM +""" +from utils.chat_ui import main + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/chat_history/python_2025-03-25_20-50-30.json b/chat_history/python_2025-03-25_20-50-30.json new file mode 100644 index 0000000..7959019 --- /dev/null +++ b/chat_history/python_2025-03-25_20-50-30.json @@ -0,0 +1,20 @@ +{ + "agent": "python", + "model": "codellama:13b-python", + "date": "2025-03-25 20:50:30", + "params": { + "temperature": 0.3, + "top_p": 0.9, + "num_predict": 1024, + "stop": [ + "```" + ] + }, + "messages": [ + { + "sender": "Utilisateur", + "content": "Présente-toi brièvement et explique tes capacités.", + "timestamp": "2025-03-25T20:50:30.896680" + } + ] +} \ No newline at end of file diff --git a/chat_history/python_2025-03-25_20-55-35.json b/chat_history/python_2025-03-25_20-55-35.json new file mode 100644 index 0000000..65e9c69 --- /dev/null +++ b/chat_history/python_2025-03-25_20-55-35.json @@ -0,0 +1,25 @@ +{ + "agent": "python", + "model": "codellama:13b-python", + "date": "2025-03-25 20:55:35", + "params": { + "temperature": 0.3, + "top_p": 0.9, + "num_predict": 1024, + "stop": [ + "```" + ] + }, + "messages": [ + { + "sender": "Utilisateur", + "content": "Présente-toi brièvement et explique tes capacités.", + "timestamp": "2025-03-25T20:50:30.896680" + }, + { + "sender": "python", + "content": " Si tu ne parles pas le français, tu auras toujours accès aux traductions de la communauté (en cliquant sur le lien \"English Translations\" dans l'onglet \"Info\" à droite).\n\nRéponds au plus vite si tu es intéressé(e) par ce poste. Le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!\n\n### Problèmes de la semaine - [Python Weekly Newsletter](https://mailchi.mp/pythonweekly/issues?label=python%20weekly)\nC'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!\n\n### Problèmes du mois - [HackerRank](https://www.hackerrank.com/domains?filters%5Bsubdomains%5D%5B0%5D=python&badge_type=problem-solving)\nC'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!\n\n### Problèmes du jour - [Python Tricks](https://towardsdatascience.com/python-tricks-and-tips-from-the-websites-top-contestants-395ef2e0f5d1)\nC'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!\n\n### Problèmes d'exercice - [Python Exercises](https://www.programiz.com/python-programming/exercises)\nC'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!", + "timestamp": "2025-03-25T20:55:35.637923" + } + ] +} \ No newline at end of file diff --git a/config_wsl_memoire.md b/config_wsl_memoire.md new file mode 100644 index 0000000..8ea1c67 --- /dev/null +++ b/config_wsl_memoire.md @@ -0,0 +1,102 @@ +# Guide de configuration de la mémoire pour WSL + +Ce guide explique comment allouer plus de mémoire à WSL pour exécuter des modèles LLM de grande taille avec Ollama, et comment revenir aux paramètres par défaut. + +## Pourquoi augmenter la mémoire de WSL ? + +- WSL est limité par défaut (souvent à 50% de la RAM physique) +- Les grands modèles LLM nécessitent plus de mémoire +- Ollama sous WSL est limité par la mémoire disponible dans WSL + +## Vérifier la mémoire actuelle de WSL + +Pour vérifier la mémoire actuellement allouée à WSL: + +```bash +cat /proc/meminfo | grep MemTotal +``` + +## Augmenter la mémoire de WSL à 60 Go + +### Étape 1: Créer ou modifier le fichier .wslconfig + +1. Ouvrez l'Explorateur de fichiers Windows +2. Naviguez vers votre répertoire utilisateur: `C:\Users\VotreNomUtilisateur\` +3. Créez un fichier nommé `.wslconfig` (avec le point au début) +4. Ajoutez les lignes suivantes: + +```ini +[wsl2] +memory=60GB +``` + +Si vous souhaitez également configurer d'autres paramètres: + +```ini +[wsl2] +memory=60GB +processors=8 # Nombre de cœurs CPU à allouer +swap=4GB # Taille du fichier d'échange +``` + +### Étape 2: Redémarrer WSL + +1. Ouvrez PowerShell en tant qu'administrateur +2. Exécutez la commande: + +```powershell +wsl --shutdown +``` + +3. Redémarrez WSL en ouvrant votre terminal Ubuntu ou en exécutant: + +```powershell +wsl +``` + +### Étape 3: Vérifier la nouvelle configuration + +```bash +cat /proc/meminfo | grep MemTotal +``` + +Vous devriez voir une valeur proche de 60 Go (environ 62914560 kB). + +## Revenir aux paramètres par défaut + +### Méthode 1: Modifier le fichier .wslconfig + +1. Modifiez le fichier `C:\Users\VotreNomUtilisateur\.wslconfig` +2. Commentez ou supprimez la ligne `memory=60GB` +3. Redémarrez WSL avec `wsl --shutdown` + +```ini +[wsl2] +# memory=60GB # Commentez cette ligne pour revenir au défaut +``` + +### Méthode 2: Supprimer le fichier .wslconfig + +1. Supprimez ou renommez le fichier `C:\Users\VotreNomUtilisateur\.wslconfig` +2. Redémarrez WSL avec `wsl --shutdown` + +## Points importants à noter + +- La mémoire allouée à WSL n'est utilisée que lorsque WSL est actif +- WSL n'utilisera pas toute la mémoire allouée s'il n'en a pas besoin +- Si vous exécutez des applications Windows gourmandes en RAM, fermez WSL temporairement +- Pour fermer complètement WSL: `wsl --shutdown` dans PowerShell + +## Utilisation optimale + +- Pour les sessions Ollama avec de grands modèles: utilisez le paramètre 60 GB +- Pour le travail régulier sur Windows avec des applications gourmandes en RAM: revenez aux paramètres par défaut +- Si vous n'avez pas besoin de WSL, fermez-le pour libérer les ressources + +## Dépannage + +Si vous rencontrez des problèmes après avoir modifié la configuration: + +1. Assurez-vous que le format du fichier `.wslconfig` est correct (pas d'extension .txt cachée) +2. Vérifiez que WSL a bien été redémarré: `wsl --shutdown` puis relancez-le +3. En cas de problème persistant, supprimez le fichier `.wslconfig` et redémarrez WSL \ No newline at end of file diff --git a/core/__pycache__/base_llm.cpython-312.pyc b/core/__pycache__/base_llm.cpython-312.pyc index 1ca84be..7331393 100644 Binary files a/core/__pycache__/base_llm.cpython-312.pyc and b/core/__pycache__/base_llm.cpython-312.pyc differ diff --git a/core/__pycache__/codellama13b_python.cpython-312.pyc b/core/__pycache__/codellama13b_python.cpython-312.pyc new file mode 100644 index 0000000..2dd688f Binary files /dev/null and b/core/__pycache__/codellama13b_python.cpython-312.pyc differ diff --git a/core/__pycache__/factory.cpython-312.pyc b/core/__pycache__/factory.cpython-312.pyc index 5746852..15cf8b4 100644 Binary files a/core/__pycache__/factory.cpython-312.pyc and b/core/__pycache__/factory.cpython-312.pyc differ diff --git a/core/__pycache__/llama2_13b.cpython-312.pyc b/core/__pycache__/llama2_13b.cpython-312.pyc new file mode 100644 index 0000000..efcff54 Binary files /dev/null and b/core/__pycache__/llama2_13b.cpython-312.pyc differ diff --git a/core/__pycache__/mistral7b.cpython-312.pyc b/core/__pycache__/mistral7b.cpython-312.pyc index f40b360..e7e8d57 100644 Binary files a/core/__pycache__/mistral7b.cpython-312.pyc and b/core/__pycache__/mistral7b.cpython-312.pyc differ diff --git a/core/codellama13b_python.py b/core/codellama13b_python.py new file mode 100644 index 0000000..3c6e833 --- /dev/null +++ b/core/codellama13b_python.py @@ -0,0 +1,37 @@ +from core.base_llm import BaseLLM +import requests + +class CodeLlama13bPython(BaseLLM): + def __init__(self): + # Nom du modèle spécifique + model_name = "codellama:13b-python" + # Moteur utilisé pour l'inférence + engine = "Ollama" + + # Paramètres par défaut spécifiques à CodeLlama13bPython + default_params = { + "temperature": 0.6, # Contrôle la créativité : plus bas pour code + "top_p": 0.95, # Nucleus sampling : sélectionne les tokens jusqu'à une probabilité cumulative + "top_k": 40, # Considère les top_k tokens les plus probables pour chaque étape de génération + "repeat_penalty": 1.2, # Pénalise les répétitions : important pour le code + "num_predict": 1024, # Nombre maximum de tokens à générer dans la réponse - plus grand pour le code + "stop": ["```"], # Arrête sur code block + "seed": None, # Graine pour la reproductibilité + "stream": False, # Si True, la réponse est envoyée en flux (streaming) + "raw": False # Si True, désactive le prompt système automatique + } + + super().__init__(model_name=model_name, engine=engine, base_params=default_params) + + def generate(self, user_prompt): + prompt = self._format_prompt(user_prompt) + payload = self.params.copy() + payload["prompt"] = prompt + + response = requests.post("http://localhost:11434/api/generate", json=payload) + if not response.ok: + raise Exception(f"Erreur API Ollama : {response.status_code} - {response.text}") + + result = response.json().get("response", "") + self._log_result(user_prompt, result) + return result \ No newline at end of file diff --git a/core/factory.py b/core/factory.py index 3731c92..2099c31 100644 --- a/core/factory.py +++ b/core/factory.py @@ -1,21 +1,53 @@ from core.mistral7b import Mistral7B +from core.codellama13b_python import CodeLlama13bPython +from core.llama2_13b import Llama2_13b class LLMFactory: """ Factory pour créer des instances de modèles LLM dynamiquement en fonction d'un identifiant text """ _registry = { - "mistral7b": Mistral7B + "mistral:latest": Mistral7B, + "codellama:13b-python": CodeLlama13bPython, + "llama2:13b": Llama2_13b, + # Aliases pour compatibilité rétroactive + "mistral7b": Mistral7B, + "codellama13b-python": CodeLlama13bPython, + "llama2-13b": Llama2_13b # Ajouter d'autres modèles LLM ici } + # Conversion entre noms Ollama et identifiants internes + _model_aliases = { + "mistral:latest": ["mistral7b", "mistral"], + "codellama:13b-python": ["codellama13b-python", "codellama-python", "codellama"], + "llama2:13b": ["llama2-13b", "llama2", "llama"] + } + @staticmethod def create(model_name: str): """ Crée une instance d'un modèle LLM en fonction de l'identifiant textuel """ model_name = model_name.lower() - if model_name not in LLMFactory._registry: - raise ValueError(f"Modèle LLM non supporté: {model_name}") - return LLMFactory._registry[model_name]() + + # Essayer directement + if model_name in LLMFactory._registry: + return LLMFactory._registry[model_name]() + + # Vérifier les alias + for canonical, aliases in LLMFactory._model_aliases.items(): + if model_name in aliases: + return LLMFactory._registry[canonical]() + + # Si on arrive ici, modèle non supporté + raise ValueError(f"Modèle LLM non supporté: {model_name}") + + @staticmethod + def get_available_models(): + """ + Renvoie la liste des modèles disponibles (noms Ollama) + """ + return [m for m in LLMFactory._registry.keys() + if m not in sum(LLMFactory._model_aliases.values(), [])] # Exclure les alias \ No newline at end of file diff --git a/core/llama2_13b.py b/core/llama2_13b.py new file mode 100644 index 0000000..947c2aa --- /dev/null +++ b/core/llama2_13b.py @@ -0,0 +1,37 @@ +from core.base_llm import BaseLLM +import requests + +class Llama2_13b(BaseLLM): + def __init__(self): + # Nom du modèle spécifique + model_name = "llama2:13b" + # Moteur utilisé pour l'inférence + engine = "Ollama" + + # Paramètres par défaut spécifiques à Llama2 13B + default_params = { + "temperature": 0.75, # Contrôle la créativité : 0 = déterministe, 1 = plus créatif + "top_p": 0.9, # Nucleus sampling : sélectionne les tokens jusqu'à une probabilité cumulative de top_p + "top_k": 40, # Considère les top_k tokens les plus probables pour chaque étape de génération + "repeat_penalty": 1.1, # Pénalise les répétitions : >1 pour réduire les répétitions, 1 pour aucune pénalité + "num_predict": 768, # Nombre maximum de tokens à générer dans la réponse + "stop": [], # Liste de séquences qui arrêteront la génération si rencontrées + "seed": None, # Graine pour la reproductibilité : fixe la graine pour obtenir les mêmes résultats + "stream": False, # Si True, la réponse est envoyée en flux (streaming) + "raw": False # Si True, désactive le prompt système automatique + } + + super().__init__(model_name=model_name, engine=engine, base_params=default_params) + + def generate(self, user_prompt): + prompt = self._format_prompt(user_prompt) + payload = self.params.copy() + payload["prompt"] = prompt + + response = requests.post("http://localhost:11434/api/generate", json=payload) + if not response.ok: + raise Exception(f"Erreur API Ollama : {response.status_code} - {response.text}") + + result = response.json().get("response", "") + self._log_result(user_prompt, result) + return result \ No newline at end of file diff --git a/core/mistral7b.py b/core/mistral7b.py index 9b4fa09..dfa2f5a 100644 --- a/core/mistral7b.py +++ b/core/mistral7b.py @@ -28,7 +28,7 @@ class Mistral7B(BaseLLM): payload = self.params.copy() payload["prompt"] = prompt - response = requests.post("http://217.182.105.173:11434/api/generate", json=payload) + response = requests.post("http://localhost:11434/api/generate", json=payload) if not response.ok: raise Exception(f"Erreur API Ollama : {response.status_code} - {response.text}") diff --git a/examples/agent_demo.py b/examples/agent_demo.py new file mode 100644 index 0000000..41f5d50 --- /dev/null +++ b/examples/agent_demo.py @@ -0,0 +1,92 @@ +""" +Démonstration de l'utilisation des agents spécialisés avec leurs modèles associés +""" +from utils.agent_manager import AgentManager +import os +import time + +def list_available_agents(): + """Affiche la liste des agents disponibles avec leurs modèles""" + print("\n=== Agents disponibles ===") + agents_info = AgentManager.list_agents() + + for agent_name, info in agents_info.items(): + print(f"• {agent_name} (modèle: {info['model']})") + print(f" → {info['description']}") + + return list(agents_info.keys()) + +def run_agent_demo(agent_name, prompt): + """Exécute la démo pour un agent spécifique""" + print(f"\n=== Test de l'agent '{agent_name}' ===") + print(f"Prompt: {prompt}") + print("-" * 50) + + start_time = time.time() + + try: + # Création de l'agent + agent = AgentManager.create(agent_name) + print(f"Agent '{agent_name}' créé avec le modèle '{agent.model}'") + + # Génération de la réponse + print("\nGénération en cours...") + response = agent.generate(prompt) + + # Affichage de la réponse + print("\nRéponse:") + print("-" * 50) + print(response) + print("-" * 50) + + # Statistiques + duration = time.time() - start_time + print(f"\nTemps d'exécution: {duration:.2f} secondes") + print(f"Longueur de la réponse: {len(response)} caractères") + + except Exception as e: + print(f"Erreur lors de l'exécution: {str(e)}") + +if __name__ == "__main__": + os.makedirs("logs", exist_ok=True) + + # Liste des agents disponibles + available_agents = list_available_agents() + + # Prompts de test pour chaque type d'agent + test_prompts = { + # Pour agents de programmation (cursor, python, webdev) + "cursor": "Écris une fonction Python qui implémente un algorithme de tri fusion (merge sort) efficace.", + "python": "Comment utiliser pandas pour analyser un fichier CSV et calculer des statistiques par groupe?", + "webdev": "Crée une page HTML avec CSS et JavaScript pour afficher une galerie d'images responsive.", + + # Pour agent de gestion de connaissances (obsidian) + "obsidian": "Comment organiser un système de notes pour un projet de recherche avec des liens entre concepts?", + + # Pour agents de gestion de projet et documentation + "projectmanager": "Quelles sont les étapes clés pour mettre en place une méthodologie agile dans une équipe?", + "documentaliste": "Comment structurer la documentation d'une API REST?", + + # Pour agent de test + "test": "Vérifie que tu peux générer une réponse courte." + } + + # Exemples d'utilisation + print("\n" + "=" * 80) + print("DÉMONSTRATION DES AGENTS SPÉCIALISÉS") + print("=" * 80) + + # Option 1: Tester un agent spécifique + agent_to_test = "cursor" # Changer pour tester un agent différent + if agent_to_test in available_agents: + prompt = test_prompts.get(agent_to_test, "Présente-toi et explique tes capacités.") + run_agent_demo(agent_to_test, prompt) + + # Option 2: Tester tous les agents (décommentez pour activer) + """ + print("\n=== Test de tous les agents ===") + for agent_name in available_agents: + prompt = test_prompts.get(agent_name, "Présente-toi et explique tes capacités.") + run_agent_demo(agent_name, prompt) + print("\n" + "=" * 80) + """ \ No newline at end of file diff --git a/examples/model_comparison.py b/examples/model_comparison.py new file mode 100644 index 0000000..9e01052 --- /dev/null +++ b/examples/model_comparison.py @@ -0,0 +1,52 @@ +""" +Exemple de comparaison des différents modèles LLM sur un même prompt +""" +from core.factory import LLMFactory +import os + +def compare_models(prompt, models=None): + """Compare les réponses de différents modèles sur un même prompt""" + if models is None: + models = ["mistral7b", "codellama13b-python", "llama2-13b"] + + results = {} + + print(f"Comparaison des modèles sur le prompt:\n{prompt}\n") + print("=" * 80) + + for model_name in models: + print(f"\nTesting {model_name}...") + try: + # Création du modèle via la factory + model = LLMFactory.create(model_name) + + # Génération avec le prompt donné + result = model.generate(prompt) + results[model_name] = result + + # Affichage d'une partie de la réponse + preview = result[:200] + "..." if len(result) > 200 else result + print(f"✓ Réponse ({len(result)} caractères):\n{preview}") + + except Exception as e: + print(f"✗ Erreur: {str(e)}") + + return results + +if __name__ == "__main__": + # Création du dossier examples si nécessaire + os.makedirs("examples", exist_ok=True) + + # Prompts de test pour différents cas d'usage + prompts = { + "génération_texte": "Écris un poème sur l'intelligence artificielle en 4 vers.", + "programmation": "Écris une fonction Python qui calcule la suite de Fibonacci de manière récursive.", + "raisonnement": "Si j'ai 5 pommes et que je donne 2 pommes à Marie, puis que Jean me donne 3 pommes, combien de pommes ai-je maintenant?" + } + + # Exécution des tests + for task, prompt in prompts.items(): + print(f"\n\n{'#' * 80}") + print(f"# TEST: {task}") + print(f"{'#' * 80}") + compare_models(prompt) \ No newline at end of file diff --git a/installation_ollama_disques_separes.md b/installation_ollama_disques_separes.md new file mode 100644 index 0000000..cb9de76 --- /dev/null +++ b/installation_ollama_disques_separes.md @@ -0,0 +1,212 @@ +# Guide d'installation d'Ollama avec modèles sur un disque séparé + +Ce guide vous explique comment installer Ollama sur votre disque système Windows (C:) tout en stockant les modèles volumineux sur un autre disque pour économiser de l'espace. + +## Pourquoi séparer Ollama et ses modèles? + +- Les modèles LLM peuvent occuper plusieurs dizaines de Go +- Le disque système (C:) est souvent limité en espace +- Les SSD secondaires ou disques durs offrent plus d'espace de stockage +- Cette configuration permet d'optimiser l'espace disque tout en gardant de bonnes performances + +## 1. Installation d'Ollama sur le disque principal + +1. Téléchargez Ollama depuis [ollama.com/download/windows](https://ollama.com/download/windows) +2. Exécutez l'installateur avec les options par défaut (C:\Program Files\Ollama) +3. Laissez l'installation se terminer et le service démarrer + +## 2. Arrêter le service Ollama + +Avant de modifier la configuration, arrêtez le service Ollama: + +1. Ouvrez un terminal administrateur (clic droit > Exécuter en tant qu'administrateur) +2. Exécutez la commande: + ```cmd + net stop Ollama + ``` + +## 3. Créer le dossier de destination pour les modèles + +Choisissez un disque avec beaucoup d'espace libre (par exemple D:, E:, etc.): + +```cmd +mkdir D:\OllamaModels +``` + +## 4. Configurer le stockage des modèles + +### Méthode 1: Lien symbolique (recommandée) + +Cette méthode permet à Ollama de continuer à chercher les modèles au même endroit, mais Windows redirige vers le nouveau disque: + +```cmd +rmdir /s /q "C:\Users\%USERNAME%\.ollama\models" +mklink /d "C:\Users\%USERNAME%\.ollama\models" "D:\OllamaModels" +``` + +### Méthode 2: Variable d'environnement OLLAMA_MODELS + +Cette méthode indique à Ollama où trouver les modèles: + +1. Ouvrez le Panneau de configuration > Système > Paramètres système avancés +2. Cliquez sur "Variables d'environnement" +3. Ajoutez une nouvelle variable système: + - Nom: `OLLAMA_MODELS` + - Valeur: `D:\OllamaModels` +4. Cliquez sur OK pour sauvegarder + +## 5. Redémarrer le service Ollama + +Pour appliquer les changements: + +```cmd +net start Ollama +``` + +## 6. Tester la configuration + +1. Vérifiez que le service fonctionne correctement: + ```cmd + curl http://localhost:11434/api/tags + ``` + +2. Téléchargez un petit modèle pour tester: + ```cmd + ollama pull tinyllama + ``` + +3. Vérifiez que le modèle est bien stocké sur le disque secondaire en examinant: + ```cmd + dir D:\OllamaModels + ``` + +## 7. Migrer les modèles existants + +Si vous avez des modèles existants sur un autre disque ou sous WSL, vous pouvez les migrer: + +### Depuis WSL + +```cmd +robocopy \\wsl$\Ubuntu\home\fgras-ca\.ollama\models D:\OllamaModels /E +``` + +### Depuis un autre disque Windows + +```cmd +robocopy E:\CheminVersModeles D:\OllamaModels /E +``` + +## 8. Configuration optimale pour les performances + +Pour optimiser les performances, créez un fichier `ollama_performance.bat`: + +```batch +@echo off +setlocal + +echo Configuration des performances d'Ollama... + +REM Répertoire des modèles +set OLLAMA_MODELS=D:\OllamaModels + +REM Paramètres de performance +set CUDA_VISIBLE_DEVICES=0 +set OMP_NUM_THREADS=8 + +REM Redémarrer le service Ollama +net stop Ollama +timeout /t 2 +net start Ollama + +echo Configuration terminée! +echo Modèles stockés dans: %OLLAMA_MODELS% +echo. +echo Ollama est prêt à utiliser! + +endlocal +``` + +## 9. Intégration avec LLM Lab + +Pour que LLM Lab utilise correctement cette configuration: + +1. Assurez-vous que l'interface de monitoring détecte correctement le nouvel emplacement +2. Créez un fichier `C:\LLM_Lab\ollama_config.json` avec: + +```json +{ + "models_dir": "D:\\OllamaModels", + "gpu_layers": -1, + "num_ctx": 8192, + "num_thread": 12, + "num_batch": 512 +} +``` + +3. Modifiez le fichier `C:\LLM_Lab\utils\ollama_api.py` pour qu'il vérifie l'emplacement des modèles. + +## 10. Vérification de l'espace disque + +Ajoutez cette fonction au moniteur système pour surveiller l'espace disque des modèles: + +```python +def check_models_disk_space(): + """Vérifie l'espace disque pour les modèles Ollama""" + models_dir = "D:\\OllamaModels" # Ajustez selon votre configuration + + if os.path.exists(models_dir): + try: + total, used, free = shutil.disk_usage(models_dir) + total_gb = total / (1024**3) + used_gb = used / (1024**3) + free_gb = free / (1024**3) + + print(f"Disque des modèles: {models_dir}") + print(f"Espace total: {total_gb:.1f} GB") + print(f"Espace utilisé: {used_gb:.1f} GB") + print(f"Espace libre: {free_gb:.1f} GB") + except: + print("Erreur lors de la vérification de l'espace disque") +``` + +## Dépannage + +### Les modèles ne sont pas stockés au bon endroit + +1. Vérifiez que le service Ollama a bien les permissions d'accès au dossier D:\OllamaModels +2. Vérifiez que le lien symbolique a bien été créé avec: + ```cmd + dir /al "C:\Users\%USERNAME%\.ollama" + ``` + +### Erreurs lors du téléchargement des modèles + +1. Arrêtez le service Ollama +2. Vérifiez les logs dans `C:\Users\%USERNAME%\.ollama\logs` +3. Assurez-vous que le disque cible a suffisamment d'espace libre +4. Redémarrez le service + +### Le service Ollama ne démarre pas + +1. Vérifiez les services Windows (services.msc) +2. Consultez les logs d'événements Windows +3. Essayez de démarrer Ollama manuellement: + ```cmd + "C:\Program Files\Ollama\ollama.exe" serve + ``` + +## Maintenance + +### Mise à jour d'Ollama + +Lors des mises à jour d'Ollama, votre configuration de stockage sur disque séparé sera préservée tant que vous ne supprimez pas manuellement le lien symbolique ou la variable d'environnement. + +### Nettoyage des modèles + +Pour libérer de l'espace, vous pouvez supprimer les modèles inutilisés: + +```cmd +ollama rm nom-du-modele +``` + +Cela supprimera correctement le modèle de votre disque secondaire. \ No newline at end of file diff --git a/llmlab/bin/activate b/llmlab/bin/activate index c0da8a2..3e3cc96 100644 --- a/llmlab/bin/activate +++ b/llmlab/bin/activate @@ -39,10 +39,10 @@ deactivate nondestructive if [ "${OSTYPE:-}" = "cygwin" ] || [ "${OSTYPE:-}" = "msys" ] ; then # transform D:\path\to\venv to /d/path/to/venv on MSYS # and to /cygdrive/d/path/to/venv on Cygwin - export VIRTUAL_ENV=$(cygpath /home/fgras-ca/llm_lab-test/llmlab) + export VIRTUAL_ENV=$(cygpath /home/fgras-ca/llm_lab/llmlab) else # use the path as-is - export VIRTUAL_ENV=/home/fgras-ca/llm_lab-test/llmlab + export VIRTUAL_ENV=/home/fgras-ca/llm_lab/llmlab fi _OLD_VIRTUAL_PATH="$PATH" diff --git a/llmlab/bin/activate.csh b/llmlab/bin/activate.csh index 6ce8916..f3766ee 100644 --- a/llmlab/bin/activate.csh +++ b/llmlab/bin/activate.csh @@ -9,7 +9,7 @@ alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PA # Unset irrelevant variables. deactivate nondestructive -setenv VIRTUAL_ENV /home/fgras-ca/llm_lab-test/llmlab +setenv VIRTUAL_ENV /home/fgras-ca/llm_lab/llmlab set _OLD_VIRTUAL_PATH="$PATH" setenv PATH "$VIRTUAL_ENV/"bin":$PATH" diff --git a/llmlab/bin/activate.fish b/llmlab/bin/activate.fish index 4a09b59..4fe98d1 100644 --- a/llmlab/bin/activate.fish +++ b/llmlab/bin/activate.fish @@ -33,7 +33,7 @@ end # Unset irrelevant variables. deactivate nondestructive -set -gx VIRTUAL_ENV /home/fgras-ca/llm_lab-test/llmlab +set -gx VIRTUAL_ENV /home/fgras-ca/llm_lab/llmlab set -gx _OLD_VIRTUAL_PATH $PATH set -gx PATH "$VIRTUAL_ENV/"bin $PATH diff --git a/llmlab/bin/normalizer b/llmlab/bin/normalizer index 31cb1c2..1059c73 100755 --- a/llmlab/bin/normalizer +++ b/llmlab/bin/normalizer @@ -1,4 +1,4 @@ -#!/home/fgras-ca/llm_lab-test/llmlab/bin/python3 +#!/home/fgras-ca/llm_lab/llmlab/bin/python3 # -*- coding: utf-8 -*- import re import sys diff --git a/llmlab/bin/pip b/llmlab/bin/pip index 65e8894..d7bdc80 100755 --- a/llmlab/bin/pip +++ b/llmlab/bin/pip @@ -1,4 +1,4 @@ -#!/home/fgras-ca/llm_lab-test/llmlab/bin/python3 +#!/home/fgras-ca/llm_lab/llmlab/bin/python3 # -*- coding: utf-8 -*- import re import sys diff --git a/llmlab/bin/pip3 b/llmlab/bin/pip3 index 65e8894..d7bdc80 100755 --- a/llmlab/bin/pip3 +++ b/llmlab/bin/pip3 @@ -1,4 +1,4 @@ -#!/home/fgras-ca/llm_lab-test/llmlab/bin/python3 +#!/home/fgras-ca/llm_lab/llmlab/bin/python3 # -*- coding: utf-8 -*- import re import sys diff --git a/llmlab/bin/pip3.12 b/llmlab/bin/pip3.12 index 65e8894..d7bdc80 100755 --- a/llmlab/bin/pip3.12 +++ b/llmlab/bin/pip3.12 @@ -1,4 +1,4 @@ -#!/home/fgras-ca/llm_lab-test/llmlab/bin/python3 +#!/home/fgras-ca/llm_lab/llmlab/bin/python3 # -*- coding: utf-8 -*- import re import sys diff --git a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/LICENSE.txt b/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/LICENSE.txt deleted file mode 100644 index e1f9ad7..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/LICENSE.txt +++ /dev/null @@ -1,44 +0,0 @@ -Zope Public License (ZPL) Version 2.1 - -A copyright notice accompanies this license document that identifies the -copyright holders. - -This license has been certified as open source. It has also been designated as -GPL compatible by the Free Software Foundation (FSF). - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - -1. Redistributions in source code must retain the accompanying copyright -notice, this list of conditions, and the following disclaimer. - -2. Redistributions in binary form must reproduce the accompanying copyright -notice, this list of conditions, and the following disclaimer in the -documentation and/or other materials provided with the distribution. - -3. Names of the copyright holders must not be used to endorse or promote -products derived from this software without prior written permission from the -copyright holders. - -4. The right to distribute this software or to use it for any purpose does not -give you the right to use Servicemarks (sm) or Trademarks (tm) of the -copyright -holders. Use of them is covered by separate agreement with the copyright -holders. - -5. If any files are modified, you must cause the modified files to carry -prominent notices stating that you changed the files and the date of any -change. - -Disclaimer - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY EXPRESSED -OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES -OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO -EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY DIRECT, INDIRECT, -INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR -PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF -LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING -NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, -EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/METADATA deleted file mode 100644 index 2c08685..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/METADATA +++ /dev/null @@ -1,1167 +0,0 @@ -Metadata-Version: 2.1 -Name: DateTime -Version: 5.5 -Summary: This package provides a DateTime data type, as known from Zope. Unless you need to communicate with Zope APIs, you're probably better off using Python's built-in datetime module. -Home-page: https://github.com/zopefoundation/DateTime -Author: Zope Foundation and Contributors -Author-email: zope-dev@zope.org -License: ZPL 2.1 -Classifier: Development Status :: 6 - Mature -Classifier: Environment :: Web Environment -Classifier: Framework :: Zope :: 4 -Classifier: License :: OSI Approved :: Zope Public License -Classifier: Operating System :: OS Independent -Classifier: Programming Language :: Python -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3.7 -Classifier: Programming Language :: Python :: 3.8 -Classifier: Programming Language :: Python :: 3.9 -Classifier: Programming Language :: Python :: 3.10 -Classifier: Programming Language :: Python :: 3.11 -Classifier: Programming Language :: Python :: 3.12 -Classifier: Programming Language :: Python :: Implementation :: CPython -Classifier: Programming Language :: Python :: Implementation :: PyPy -Requires-Python: >=3.7 -License-File: LICENSE.txt -Requires-Dist: zope.interface -Requires-Dist: pytz - -.. image:: https://github.com/zopefoundation/DateTime/workflows/tests/badge.svg - :target: https://github.com/zopefoundation/DateTime/actions?query=workflow%3Atests - :alt: CI status - -.. image:: https://img.shields.io/pypi/v/DateTime.svg - :target: https://pypi.org/project/DateTime/ - :alt: Current version on PyPI - -.. image:: https://img.shields.io/pypi/pyversions/DateTime.svg - :target: https://pypi.org/project/DateTime/ - :alt: Supported Python versions - - -DateTime -======== - -This package provides a DateTime data type, as known from Zope. - -Unless you need to communicate with Zope APIs, you're probably better -off using Python's built-in datetime module. - -For further documentation, please have a look at `src/DateTime/DateTime.txt`. - - -.. contents:: - -The DateTime package -==================== - -Encapsulation of date/time values. - - -Function Timezones() --------------------- - -Returns the list of recognized timezone names: - - >>> from DateTime import Timezones - >>> zones = set(Timezones()) - -Almost all of the standard pytz timezones are included, with the exception -of some commonly-used but ambiguous abbreviations, where historical Zope -usage conflicts with the name used by pytz: - - >>> import pytz - >>> [x for x in pytz.all_timezones if x not in zones] - ['CET', 'EET', 'EST', 'MET', 'MST', 'WET'] - -Class DateTime --------------- - -DateTime objects represent instants in time and provide interfaces for -controlling its representation without affecting the absolute value of -the object. - -DateTime objects may be created from a wide variety of string or -numeric data, or may be computed from other DateTime objects. -DateTimes support the ability to convert their representations to many -major timezones, as well as the ability to create a DateTime object -in the context of a given timezone. - -DateTime objects provide partial numerical behavior: - -* Two date-time objects can be subtracted to obtain a time, in days - between the two. - -* A date-time object and a positive or negative number may be added to - obtain a new date-time object that is the given number of days later - than the input date-time object. - -* A positive or negative number and a date-time object may be added to - obtain a new date-time object that is the given number of days later - than the input date-time object. - -* A positive or negative number may be subtracted from a date-time - object to obtain a new date-time object that is the given number of - days earlier than the input date-time object. - -DateTime objects may be converted to integer, long, or float numbers -of days since January 1, 1901, using the standard int, long, and float -functions (Compatibility Note: int, long and float return the number -of days since 1901 in GMT rather than local machine timezone). -DateTime objects also provide access to their value in a float format -usable with the Python time module, provided that the value of the -object falls in the range of the epoch-based time module. - -A DateTime object should be considered immutable; all conversion and numeric -operations return a new DateTime object rather than modify the current object. - -A DateTime object always maintains its value as an absolute UTC time, -and is represented in the context of some timezone based on the -arguments used to create the object. A DateTime object's methods -return values based on the timezone context. - -Note that in all cases the local machine timezone is used for -representation if no timezone is specified. - -Constructor for DateTime ------------------------- - -DateTime() returns a new date-time object. DateTimes may be created -with from zero to seven arguments: - -* If the function is called with no arguments, then the current date/ - time is returned, represented in the timezone of the local machine. - -* If the function is invoked with a single string argument which is a - recognized timezone name, an object representing the current time is - returned, represented in the specified timezone. - -* If the function is invoked with a single string argument - representing a valid date/time, an object representing that date/ - time will be returned. - - As a general rule, any date-time representation that is recognized - and unambiguous to a resident of North America is acceptable. (The - reason for this qualification is that in North America, a date like: - 2/1/1994 is interpreted as February 1, 1994, while in some parts of - the world, it is interpreted as January 2, 1994.) A date/ time - string consists of two components, a date component and an optional - time component, separated by one or more spaces. If the time - component is omitted, 12:00am is assumed. - - Any recognized timezone name specified as the final element of the - date/time string will be used for computing the date/time value. - (If you create a DateTime with the string, - "Mar 9, 1997 1:45pm US/Pacific", the value will essentially be the - same as if you had captured time.time() at the specified date and - time on a machine in that timezone). If no timezone is passed, then - the timezone configured on the local machine will be used, **except** - that if the date format matches ISO 8601 ('YYYY-MM-DD'), the instance - will use UTC / GMT+0 as the timezone. - - o Returns current date/time, represented in US/Eastern: - - >>> from DateTime import DateTime - >>> e = DateTime('US/Eastern') - >>> e.timezone() - 'US/Eastern' - - o Returns specified time, represented in local machine zone: - - >>> x = DateTime('1997/3/9 1:45pm') - >>> x.parts() # doctest: +ELLIPSIS - (1997, 3, 9, 13, 45, ...) - - o Specified time in local machine zone, verbose format: - - >>> y = DateTime('Mar 9, 1997 13:45:00') - >>> y.parts() # doctest: +ELLIPSIS - (1997, 3, 9, 13, 45, ...) - >>> y == x - True - - o Specified time in UTC via ISO 8601 rule: - - >>> z = DateTime('2014-03-24') - >>> z.parts() # doctest: +ELLIPSIS - (2014, 3, 24, 0, 0, ...) - >>> z.timezone() - 'GMT+0' - - The date component consists of year, month, and day values. The - year value must be a one-, two-, or four-digit integer. If a one- - or two-digit year is used, the year is assumed to be in the - twentieth century. The month may an integer, from 1 to 12, a month - name, or a month abbreviation, where a period may optionally follow - the abbreviation. The day must be an integer from 1 to the number of - days in the month. The year, month, and day values may be separated - by periods, hyphens, forward slashes, or spaces. Extra spaces are - permitted around the delimiters. Year, month, and day values may be - given in any order as long as it is possible to distinguish the - components. If all three components are numbers that are less than - 13, then a month-day-year ordering is assumed. - - The time component consists of hour, minute, and second values - separated by colons. The hour value must be an integer between 0 - and 23 inclusively. The minute value must be an integer between 0 - and 59 inclusively. The second value may be an integer value - between 0 and 59.999 inclusively. The second value or both the - minute and second values may be omitted. The time may be followed - by am or pm in upper or lower case, in which case a 12-hour clock is - assumed. - -* If the DateTime function is invoked with a single numeric argument, - the number is assumed to be either a floating point value such as - that returned by time.time(), or a number of days after January 1, - 1901 00:00:00 UTC. - - A DateTime object is returned that represents either the GMT value - of the time.time() float represented in the local machine's - timezone, or that number of days after January 1, 1901. Note that - the number of days after 1901 need to be expressed from the - viewpoint of the local machine's timezone. A negative argument will - yield a date-time value before 1901. - -* If the function is invoked with two numeric arguments, then the - first is taken to be an integer year and the second argument is - taken to be an offset in days from the beginning of the year, in the - context of the local machine timezone. The date-time value returned - is the given offset number of days from the beginning of the given - year, represented in the timezone of the local machine. The offset - may be positive or negative. Two-digit years are assumed to be in - the twentieth century. - -* If the function is invoked with two arguments, the first a float - representing a number of seconds past the epoch in GMT (such as - those returned by time.time()) and the second a string naming a - recognized timezone, a DateTime with a value of that GMT time will - be returned, represented in the given timezone. - - >>> import time - >>> t = time.time() - - Time t represented as US/Eastern: - - >>> now_east = DateTime(t, 'US/Eastern') - - Time t represented as US/Pacific: - - >>> now_west = DateTime(t, 'US/Pacific') - - Only their representations are different: - - >>> now_east.equalTo(now_west) - True - -* If the function is invoked with three or more numeric arguments, - then the first is taken to be an integer year, the second is taken - to be an integer month, and the third is taken to be an integer day. - If the combination of values is not valid, then a DateTimeError is - raised. One- or two-digit years up to 69 are assumed to be in the - 21st century, whereas values 70-99 are assumed to be 20th century. - The fourth, fifth, and sixth arguments are floating point, positive - or negative offsets in units of hours, minutes, and days, and - default to zero if not given. An optional string may be given as - the final argument to indicate timezone (the effect of this is as if - you had taken the value of time.time() at that time on a machine in - the specified timezone). - -If a string argument passed to the DateTime constructor cannot be -parsed, it will raise SyntaxError. Invalid date, time, or -timezone components will raise a DateTimeError. - -The module function Timezones() will return a list of the timezones -recognized by the DateTime module. Recognition of timezone names is -case-insensitive. - -Instance Methods for DateTime (IDateTime interface) ---------------------------------------------------- - -Conversion and comparison methods -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -* ``timeTime()`` returns the date/time as a floating-point number in - UTC, in the format used by the Python time module. Note that it is - possible to create date /time values with DateTime that have no - meaningful value to the time module, and in such cases a - DateTimeError is raised. A DateTime object's value must generally - be between Jan 1, 1970 (or your local machine epoch) and Jan 2038 to - produce a valid time.time() style value. - - >>> dt = DateTime('Mar 9, 1997 13:45:00 US/Eastern') - >>> dt.timeTime() - 857933100.0 - - >>> DateTime('2040/01/01 UTC').timeTime() - 2208988800.0 - - >>> DateTime('1900/01/01 UTC').timeTime() - -2208988800.0 - -* ``toZone(z)`` returns a DateTime with the value as the current - object, represented in the indicated timezone: - - >>> dt.toZone('UTC') - DateTime('1997/03/09 18:45:00 UTC') - - >>> dt.toZone('UTC').equalTo(dt) - True - -* ``isFuture()`` returns true if this object represents a date/time - later than the time of the call: - - >>> dt.isFuture() - False - >>> DateTime('Jan 1 3000').isFuture() # not time-machine safe! - True - -* ``isPast()`` returns true if this object represents a date/time - earlier than the time of the call: - - >>> dt.isPast() - True - >>> DateTime('Jan 1 3000').isPast() # not time-machine safe! - False - -* ``isCurrentYear()`` returns true if this object represents a - date/time that falls within the current year, in the context of this - object's timezone representation: - - >>> dt.isCurrentYear() - False - >>> DateTime().isCurrentYear() - True - -* ``isCurrentMonth()`` returns true if this object represents a - date/time that falls within the current month, in the context of - this object's timezone representation: - - >>> dt.isCurrentMonth() - False - >>> DateTime().isCurrentMonth() - True - -* ``isCurrentDay()`` returns true if this object represents a - date/time that falls within the current day, in the context of this - object's timezone representation: - - >>> dt.isCurrentDay() - False - >>> DateTime().isCurrentDay() - True - -* ``isCurrentHour()`` returns true if this object represents a - date/time that falls within the current hour, in the context of this - object's timezone representation: - - >>> dt.isCurrentHour() - False - - >>> DateTime().isCurrentHour() - True - -* ``isCurrentMinute()`` returns true if this object represents a - date/time that falls within the current minute, in the context of - this object's timezone representation: - - >>> dt.isCurrentMinute() - False - >>> DateTime().isCurrentMinute() - True - -* ``isLeapYear()`` returns true if the current year (in the context of - the object's timezone) is a leap year: - - >>> dt.isLeapYear() - False - >>> DateTime('Mar 8 2004').isLeapYear() - True - -* ``earliestTime()`` returns a new DateTime object that represents the - earliest possible time (in whole seconds) that still falls within - the current object's day, in the object's timezone context: - - >>> dt.earliestTime() - DateTime('1997/03/09 00:00:00 US/Eastern') - -* ``latestTime()`` return a new DateTime object that represents the - latest possible time (in whole seconds) that still falls within the - current object's day, in the object's timezone context - - >>> dt.latestTime() - DateTime('1997/03/09 23:59:59 US/Eastern') - -Component access -~~~~~~~~~~~~~~~~ - -* ``parts()`` returns a tuple containing the calendar year, month, - day, hour, minute second and timezone of the object - - >>> dt.parts() # doctest: +ELLIPSIS - (1997, 3, 9, 13, 45, ... 'US/Eastern') - -* ``timezone()`` returns the timezone in which the object is represented: - - >>> dt.timezone() in Timezones() - True - -* ``tzoffset()`` returns the timezone offset for the objects timezone: - - >>> dt.tzoffset() - -18000 - -* ``year()`` returns the calendar year of the object: - - >>> dt.year() - 1997 - -* ``month()`` returns the month of the object as an integer: - - >>> dt.month() - 3 - -* ``Month()`` returns the full month name: - - >>> dt.Month() - 'March' - -* ``aMonth()`` returns the abbreviated month name: - - >>> dt.aMonth() - 'Mar' - -* ``pMonth()`` returns the abbreviated (with period) month name: - - >>> dt.pMonth() - 'Mar.' - -* ``day()`` returns the integer day: - - >>> dt.day() - 9 - -* ``Day()`` returns the full name of the day of the week: - - >>> dt.Day() - 'Sunday' - -* ``dayOfYear()`` returns the day of the year, in context of the - timezone representation of the object: - - >>> dt.dayOfYear() - 68 - -* ``aDay()`` returns the abbreviated name of the day of the week: - - >>> dt.aDay() - 'Sun' - -* ``pDay()`` returns the abbreviated (with period) name of the day of - the week: - - >>> dt.pDay() - 'Sun.' - -* ``dow()`` returns the integer day of the week, where Sunday is 0: - - >>> dt.dow() - 0 - -* ``dow_1()`` returns the integer day of the week, where sunday is 1: - - >>> dt.dow_1() - 1 - -* ``h_12()`` returns the 12-hour clock representation of the hour: - - >>> dt.h_12() - 1 - -* ``h_24()`` returns the 24-hour clock representation of the hour: - - >>> dt.h_24() - 13 - -* ``ampm()`` returns the appropriate time modifier (am or pm): - - >>> dt.ampm() - 'pm' - -* ``hour()`` returns the 24-hour clock representation of the hour: - - >>> dt.hour() - 13 - -* ``minute()`` returns the minute: - - >>> dt.minute() - 45 - -* ``second()`` returns the second: - - >>> dt.second() == 0 - True - -* ``millis()`` returns the milliseconds since the epoch in GMT. - - >>> dt.millis() == 857933100000 - True - -strftime() -~~~~~~~~~~ - -See ``tests/test_datetime.py``. - -General formats from previous DateTime -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -* ``Date()`` return the date string for the object: - - >>> dt.Date() - '1997/03/09' - -* ``Time()`` returns the time string for an object to the nearest - second: - - >>> dt.Time() - '13:45:00' - -* ``TimeMinutes()`` returns the time string for an object not showing - seconds: - - >>> dt.TimeMinutes() - '13:45' - -* ``AMPM()`` returns the time string for an object to the nearest second: - - >>> dt.AMPM() - '01:45:00 pm' - -* ``AMPMMinutes()`` returns the time string for an object not showing - seconds: - - >>> dt.AMPMMinutes() - '01:45 pm' - -* ``PreciseTime()`` returns the time string for the object: - - >>> dt.PreciseTime() - '13:45:00.000' - -* ``PreciseAMPM()`` returns the time string for the object: - - >>> dt.PreciseAMPM() - '01:45:00.000 pm' - -* ``yy()`` returns the calendar year as a 2 digit string - - >>> dt.yy() - '97' - -* ``mm()`` returns the month as a 2 digit string - - >>> dt.mm() - '03' - -* ``dd()`` returns the day as a 2 digit string: - - >>> dt.dd() - '09' - -* ``rfc822()`` returns the date in RFC 822 format: - - >>> dt.rfc822() - 'Sun, 09 Mar 1997 13:45:00 -0500' - -New formats -~~~~~~~~~~~ - -* ``fCommon()`` returns a string representing the object's value in - the format: March 9, 1997 1:45 pm: - - >>> dt.fCommon() - 'March 9, 1997 1:45 pm' - -* ``fCommonZ()`` returns a string representing the object's value in - the format: March 9, 1997 1:45 pm US/Eastern: - - >>> dt.fCommonZ() - 'March 9, 1997 1:45 pm US/Eastern' - -* ``aCommon()`` returns a string representing the object's value in - the format: Mar 9, 1997 1:45 pm: - - >>> dt.aCommon() - 'Mar 9, 1997 1:45 pm' - -* ``aCommonZ()`` return a string representing the object's value in - the format: Mar 9, 1997 1:45 pm US/Eastern: - - >>> dt.aCommonZ() - 'Mar 9, 1997 1:45 pm US/Eastern' - -* ``pCommon()`` returns a string representing the object's value in - the format Mar. 9, 1997 1:45 pm: - - >>> dt.pCommon() - 'Mar. 9, 1997 1:45 pm' - -* ``pCommonZ()`` returns a string representing the object's value in - the format: Mar. 9, 1997 1:45 pm US/Eastern: - - >>> dt.pCommonZ() - 'Mar. 9, 1997 1:45 pm US/Eastern' - -* ``ISO()`` returns a string with the date/time in ISO format. Note: - this is not ISO 8601-format! See the ISO8601 and HTML4 methods below - for ISO 8601-compliant output. Dates are output as: YYYY-MM-DD HH:MM:SS - - >>> dt.ISO() - '1997-03-09 13:45:00' - -* ``ISO8601()`` returns the object in ISO 8601-compatible format - containing the date, time with seconds-precision and the time zone - identifier - see http://www.w3.org/TR/NOTE-datetime. Dates are - output as: YYYY-MM-DDTHH:MM:SSTZD (T is a literal character, TZD is - Time Zone Designator, format +HH:MM or -HH:MM). - - The ``HTML4()`` method below offers the same formatting, but - converts to UTC before returning the value and sets the TZD"Z" - - >>> dt.ISO8601() - '1997-03-09T13:45:00-05:00' - - -* ``HTML4()`` returns the object in the format used in the HTML4.0 - specification, one of the standard forms in ISO8601. See - http://www.w3.org/TR/NOTE-datetime. Dates are output as: - YYYY-MM-DDTHH:MM:SSZ (T, Z are literal characters, the time is in - UTC.): - - >>> dt.HTML4() - '1997-03-09T18:45:00Z' - -* ``JulianDay()`` returns the Julian day according to - http://www.tondering.dk/claus/cal/node3.html#sec-calcjd - - >>> dt.JulianDay() - 2450517 - -* ``week()`` returns the week number according to ISO - see http://www.tondering.dk/claus/cal/node6.html#SECTION00670000000000000000 - - >>> dt.week() - 10 - -Deprecated API -~~~~~~~~~~~~~~ - -* DayOfWeek(): see Day() - -* Day_(): see pDay() - -* Mon(): see aMonth() - -* Mon_(): see pMonth - -General Services Provided by DateTime -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -DateTimes can be repr()'ed; the result will be a string indicating how -to make a DateTime object like this: - - >>> repr(dt) - "DateTime('1997/03/09 13:45:00 US/Eastern')" - -When we convert them into a string, we get a nicer string that could -actually be shown to a user: - - >>> str(dt) - '1997/03/09 13:45:00 US/Eastern' - -The hash value of a DateTime is based on the date and time and is -equal for different representations of the DateTime: - - >>> hash(dt) - 3618678 - >>> hash(dt.toZone('UTC')) - 3618678 - -DateTime objects can be compared to other DateTime objects OR floating -point numbers such as the ones which are returned by the Python time -module by using the equalTo method. Using this API, True is returned if the -object represents a date/time equal to the specified DateTime or time module -style time: - - >>> dt.equalTo(dt) - True - >>> dt.equalTo(dt.toZone('UTC')) - True - >>> dt.equalTo(dt.timeTime()) - True - >>> dt.equalTo(DateTime()) - False - -Same goes for inequalities: - - >>> dt.notEqualTo(dt) - False - >>> dt.notEqualTo(dt.toZone('UTC')) - False - >>> dt.notEqualTo(dt.timeTime()) - False - >>> dt.notEqualTo(DateTime()) - True - -Normal equality operations only work with DateTime objects and take the -timezone setting into account: - - >>> dt == dt - True - >>> dt == dt.toZone('UTC') - False - >>> dt == DateTime() - False - - >>> dt != dt - False - >>> dt != dt.toZone('UTC') - True - >>> dt != DateTime() - True - -But the other comparison operations compare the referenced moment in time and -not the representation itself: - - >>> dt > dt - False - >>> DateTime() > dt - True - >>> dt > DateTime().timeTime() - False - >>> DateTime().timeTime() > dt - True - - >>> dt.greaterThan(dt) - False - >>> DateTime().greaterThan(dt) - True - >>> dt.greaterThan(DateTime().timeTime()) - False - - >>> dt >= dt - True - >>> DateTime() >= dt - True - >>> dt >= DateTime().timeTime() - False - >>> DateTime().timeTime() >= dt - True - - >>> dt.greaterThanEqualTo(dt) - True - >>> DateTime().greaterThanEqualTo(dt) - True - >>> dt.greaterThanEqualTo(DateTime().timeTime()) - False - - >>> dt < dt - False - >>> DateTime() < dt - False - >>> dt < DateTime().timeTime() - True - >>> DateTime().timeTime() < dt - False - - >>> dt.lessThan(dt) - False - >>> DateTime().lessThan(dt) - False - >>> dt.lessThan(DateTime().timeTime()) - True - - >>> dt <= dt - True - >>> DateTime() <= dt - False - >>> dt <= DateTime().timeTime() - True - >>> DateTime().timeTime() <= dt - False - - >>> dt.lessThanEqualTo(dt) - True - >>> DateTime().lessThanEqualTo(dt) - False - >>> dt.lessThanEqualTo(DateTime().timeTime()) - True - -Numeric Services Provided by DateTime -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -A DateTime may be added to a number and a number may be added to a -DateTime: - - >>> dt + 5 - DateTime('1997/03/14 13:45:00 US/Eastern') - >>> 5 + dt - DateTime('1997/03/14 13:45:00 US/Eastern') - -Two DateTimes cannot be added: - - >>> from DateTime.interfaces import DateTimeError - >>> try: - ... dt + dt - ... print('fail') - ... except DateTimeError: - ... print('ok') - ok - -Either a DateTime or a number may be subtracted from a DateTime, -however, a DateTime may not be subtracted from a number: - - >>> DateTime('1997/03/10 13:45 US/Eastern') - dt - 1.0 - >>> dt - 1 - DateTime('1997/03/08 13:45:00 US/Eastern') - >>> 1 - dt - Traceback (most recent call last): - ... - TypeError: unsupported operand type(s) for -: 'int' and 'DateTime' - -DateTimes can also be converted to integers (number of seconds since -the epoch) and floats: - - >>> int(dt) - 857933100 - >>> float(dt) - 857933100.0 - - -Changelog -========= - -5.5 (2024-03-21) ----------------- - -- Change pickle format to export the microseconds as an int, to - solve a problem with dates after 2038. - (`#56 `_) - - -5.4 (2023-12-15) ----------------- - -- Fix ``UnknownTimeZoneError`` when unpickling ``DateTime.DateTime().asdatetime()``. - (`#58 `_) - -- Repair equality comparison between DateTime instances and other types. - (`#60 `_) - - -5.3 (2023-11-14) ----------------- - -- Add support for Python 3.12. - -- Add preliminary support for Python 3.13a2. - - -5.2 (2023-07-19) ----------------- - -- Cast int to float in compare methods. -- Fix compare methods between DateTime instances and None. - (`#52 `_) - - -5.1 (2023-03-14) ----------------- - -- Add missing ``python_requires`` to ``setup.py``. - - -5.0 (2023-01-12) ----------------- - -- Drop support for Python 2.7, 3.5, 3.6. - - -4.8 (2022-12-16) ----------------- - -- Fix insidious buildout configuration bug that prevented tests on Python 2.7 - and 3.5, and fix test code that was incompatible with Python 3.5. - (`#44 `_) - -- Add support for Python 3.11. - - -4.7 (2022-09-14) ----------------- - -- Fix rounding problem with `DateTime` addition beyond the year 2038 - (`#41 `_) - - -4.6 (2022-09-10) ----------------- - -- Fix ``__format__`` method for DateTime objects - (`#39 `_) - - -4.5 (2022-07-04) ----------------- - -- Add ``__format__`` method for DateTime objects - (`#35 `_) - - -4.4 (2022-02-11) ----------------- - -- Fix WAT definition - `#31 `_. - -- Add support for Python 3.8, 3.9, and 3.10. - -- Drop support for Python 3.4. - -4.3 (2018-10-05) ----------------- - -- Add support for Python 3.7. - -4.2 (2017-04-26) ----------------- - -- Add support for Python 3.6, drop support for Python 3.3. - -4.1.1 (2016-04-30) ------------------- - -- Support unpickling instances having a numeric timezone like `+0430`. - -4.1 (2016-04-03) ----------------- - -- Add support for Python 3.4 and 3.5. - -- Drop support for Python 2.6 and 3.2. - -4.0.1 (2013-10-15) ------------------- - -- Provide more backward compatible timezones. - [vangheem] - -4.0 (2013-02-23) ----------------- - -- Added support for Python 3.2 and 3.3 in addition to 2.6 and 2.7. - -- Removed unused legacy pytz tests and the DateTimeZone module and renamed - some test internals. - -3.0.3 (2013-01-22) ------------------- - -- Allow timezone argument to be a Unicode string while creating a DateTime - object using two arguments. - -3.0.2 (2012-10-21) ------------------- - -- LP #1045233: Respect date format setting for parsing dates like `11-01-2001`. - -3.0.1 (2012-09-23) ------------------- - -- Add `_dt_reconstructor` function introduced in DateTime 2.12.7 to provide - forward compatibility with pickles that might reference this function. - -3.0 (2011-12-09) ----------------- - -- No changes. - -Backwards compatibility of DateTime 3 -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -DateTime 3 changes its pickle representation. DateTime instances pickled with -former versions of DateTime can be read, but older DateTime versions cannot read -DateTime instances pickled with version 3. - -DateTime 3 changes DateTime to be a new-style class with slots instead of being -an old-style class. - -DateTime 3 tries to preserve microsecond resolution throughout most of its API's -while former versions were often only accurate to millisecond resolution. Due to -the representation of float values in Python versions before Python 2.7 you -shouldn't compare string or float representations of DateTime instances if you -want high accuracy. The same is true for calculated values returned by methods -like `timeTime()`. You get the highest accuracy of comparing DateTime values by -calling its `micros()` methods. DateTime is not particular well suited to be -used in comparing timestamps of file systems - use the time and datetime objects -from the Python standard library instead. - -3.0b3 (2011-10-19) ------------------- - -- Allow comparison of DateTime objects against None. - -3.0b2 (2011-10-19) ------------------- - -- Reverted the single argument `None` special case handling for unpickling and - continue to treat it as meaning `now`. - -3.0b1 (2011-05-07) ------------------- - -- Restored `strftimeFormatter` as a class. - -- Added tests for read-only class attributes and interface. - -3.0a2 (2011-05-07) ------------------- - -- Added back support for reading old DateTime pickles without a `_micros` value. - -- Avoid storing `_t` representing the time as a float in seconds since the - epoch, as we already have `_micros` doing the same as a long. Memory use is - down to about 300 bytes per DateTime instance. - -- Updated exception raising syntax to current style. - -- Avoid storing `_aday`, `_fday`, `_pday`, `_amon`, `_fmon`, `_pmon`, `_pmhour` - and `_pm` in memory for every instance but look them up dynamically based on - `_dayoffset`, `_month` and `_hour`. This saves another 150 bytes of memory - per DateTime instance. - -- Moved various internal parsing related class variables to module constants. - -- No longer provide the `DateError`, `DateTimeError`, `SyntaxError` and - `TimeError` exceptions as class attributes, import them from their canonical - `DateTime.interfaces` location instead. - -- Removed deprecated `_isDST` and `_localzone` class variables. - -- Moved pytz cache from `DateTime._tzinfo` to a module global `_TZINFO`. - -- Make DateTime a new-style class and limit its available attributes via a - slots definition. The pickle size increases to 110 bytes thanks to the - `ccopy_reg\n_reconstructor` stanza. But the memory size drops from 3kb to - 500 bytes for each instance. - -3.0a1 (2011-05-06) ------------------- - -- Reordered some calculations in `_calcIndependentSecondEtc` to preserve more - floating point precision. - -- Optimized the pickled data, by only storing a tuple of `_micros` and time - zone information - this reduces the pickle size from an average of 300 bytes - to just 60 bytes. - -- Optimized un-pickling, by avoiding the creation of an intermediate DateTime - value representing the current time. - -- Removed in-place migration of old DateTime pickles without a `_micros` value. - -- Removed deprecated support for using `DateTime.__cmp__`. - -- Take time zone settings into account when comparing two date times for - (non-) equality. - -- Fixed (possibly unused) _parse_iso8601 function. - -- Removed unused import of legacy DateTimeZone, strftime and re. - Remove trailing whitespace. - -- Removed reference to missing version section from buildout. - -2.12.7 (2012-08-11) -------------------- - -- Added forward compatibility with DateTime 3 pickle format. DateTime - instances constructed under version 3 can be read and unpickled by this - version. The pickled data is converted to the current versions format - (old-style class / no slots). Once converted it will be stored again in the - old format. This should allow for a transparent upgrade/downgrade path - between DateTime 2 and 3. - -2.12.6 (2010-10-17) -------------------- - -- Changed ``testDayOfWeek`` test to be independent of OS locale. - -2.12.5 (2010-07-29) -------------------- - -- Launchpad #143269: Corrected the documentation for year value - behavior when constructing a DateTime object with three numeric - arguments. - -- Launchpad #142521: Removed confusing special case in - DateTime.__str__ where DateTime instances for midnight - (e.g. '2010-07-27 00:00:00 US/Eastern') values would - render only their date and nothing else. - -2.12.4 (2010-07-12) -------------------- - -- Fixed mapping of EDT (was -> 'GMT-0400', now 'GMT-4'). - -2.12.3 (2010-07-09) -------------------- - -- Added EDT timezone support. Addresses bug #599856. - [vangheem] - -2.12.2 (2010-05-05) -------------------- - -- Launchpad #572715: Relaxed pin on pytz, after applying a patch from - Marius Gedminus which fixes the apparent API breakage. - -2.12.1 (2010-04-30) -------------------- - -- Removed an undeclared testing dependency on zope.testing.doctest in favor of - the standard libraries doctest module. - -- Added a maximum version requirement on pytz <= 2010b. Later versions produce - test failures related to timezone changes. - -2.12.0 (2009-03-04) -------------------- - -- Launchpad #290254: Forward-ported fix for '_micros'-less pickles from - the Zope 2.11 branch version. - -2.11.2 (2009-02-02) -------------------- - -- Include *all* pytz zone names, not just "common" ones. - -- Fix one fragile doctest, band-aid another. - -- Fix for launchpad #267545: DateTime(DateTime()) should preserve the - correct hour. - -2.11.1 (2008-08-05) -------------------- - -- DateTime conversion of datetime objects with non-pytz tzinfo. Timezones() - returns a copy of the timezone list (allows tests to run). - -- Merged the slinkp-datetime-200007 branch: fix the DateTime(anotherDateTime) - constructor to preserve timezones. - -2.11.0b1 (2008-01-06) ---------------------- - -- Split off from the Zope2 main source code tree. diff --git a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/RECORD deleted file mode 100644 index 9b4e3cd..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/RECORD +++ /dev/null @@ -1,22 +0,0 @@ -DateTime-5.5.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -DateTime-5.5.dist-info/LICENSE.txt,sha256=PmcdsR32h1FswdtbPWXkqjg-rKPCDOo_r1Og9zNdCjw,2070 -DateTime-5.5.dist-info/METADATA,sha256=W1k0PqPJ6SU6QTJAu40JPtHK8XeQRL0GGEpfVGPjWGI,33735 -DateTime-5.5.dist-info/RECORD,, -DateTime-5.5.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -DateTime-5.5.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92 -DateTime-5.5.dist-info/top_level.txt,sha256=iVdUvuV_RIkkMzsnPGNfwojRWvuonInryaK3hA5Hh0o,9 -DateTime/DateTime.py,sha256=65LbTcnrCSsDPGoGLVkk7NC3H8Kq-PjkC1fQVR33gE8,71364 -DateTime/DateTime.txt,sha256=KZFzxoQItLsar1ZDd2vZN74Y6L4a04H8jXMwqc8KjmY,22487 -DateTime/__init__.py,sha256=trlFzEmNkmUpxZT7krPSVDayDK1bRxToccg3CcCF8wg,714 -DateTime/__pycache__/DateTime.cpython-312.pyc,, -DateTime/__pycache__/__init__.cpython-312.pyc,, -DateTime/__pycache__/interfaces.cpython-312.pyc,, -DateTime/__pycache__/pytz_support.cpython-312.pyc,, -DateTime/interfaces.py,sha256=n47sexf1eQ6YMdYB_60PgHtSzYIj4FND-RmHFiNpm1E,12187 -DateTime/pytz.txt,sha256=9Phns9ESXs9MaOKxXztX6sJ09QczGxsbYoSRSllKUfk,5619 -DateTime/pytz_support.py,sha256=inR1SO0X17fp9C2GsRw99S_MhxKiEt5dOV3-TGsBxDI,11853 -DateTime/tests/__init__.py,sha256=H7Ixo1xp-8BlJ65u14hk5i_TKEmETyi2FmLMD6H-mpo,683 -DateTime/tests/__pycache__/__init__.cpython-312.pyc,, -DateTime/tests/__pycache__/test_datetime.cpython-312.pyc,, -DateTime/tests/julian_testdata.txt,sha256=qxvLvabVB9ayhh5UHBvPhuqW5mRL_lizzbUh6lc3d4I,1397 -DateTime/tests/test_datetime.py,sha256=dsrfAqQpz1od1bOVPvSYfZAlduJpJIpc2F_hdN7WRAU,30385 diff --git a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/WHEEL deleted file mode 100644 index 98c0d20..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.42.0) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/top_level.txt deleted file mode 100644 index 1b8c206..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -DateTime diff --git a/llmlab/lib/python3.12/site-packages/DateTime/DateTime.py b/llmlab/lib/python3.12/site-packages/DateTime/DateTime.py deleted file mode 100644 index fc289e6..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/DateTime.py +++ /dev/null @@ -1,1948 +0,0 @@ -############################################################################## -# -# Copyright (c) 2002 Zope Foundation and Contributors. -# -# This software is subject to the provisions of the Zope Public License, -# Version 2.1 (ZPL). A copy of the ZPL should accompany this distribution. -# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED -# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS -# FOR A PARTICULAR PURPOSE -# -############################################################################## - -import copyreg as copy_reg -import math -import re -from datetime import datetime -from time import altzone -from time import daylight -from time import gmtime -from time import localtime -from time import time -from time import timezone -from time import tzname - -from zope.interface import implementer - -from .interfaces import DateError -from .interfaces import DateTimeError -from .interfaces import IDateTime -from .interfaces import SyntaxError -from .interfaces import TimeError -from .pytz_support import PytzCache - - -basestring = str -long = int -explicit_unicode_type = type(None) - -default_datefmt = None - - -def getDefaultDateFormat(): - global default_datefmt - if default_datefmt is None: - try: - from App.config import getConfiguration - default_datefmt = getConfiguration().datetime_format - return default_datefmt - except Exception: - return 'us' - else: - return default_datefmt - - -# To control rounding errors, we round system time to the nearest -# microsecond. Then delicate calculations can rely on the fact that the -# maximum precision that needs to be preserved is known. -_system_time = time - - -def time(): - return round(_system_time(), 6) - - -# Determine machine epoch -tm = ((0, 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334), - (0, 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335)) -yr, mo, dy, hr, mn, sc = gmtime(0)[:6] -i = int(yr - 1) -to_year = int(i * 365 + i // 4 - i // 100 + i // 400 - 693960.0) -to_month = tm[yr % 4 == 0 and (yr % 100 != 0 or yr % 400 == 0)][mo] -EPOCH = ((to_year + to_month + dy + - (hr / 24.0 + mn / 1440.0 + sc / 86400.0)) * 86400) -jd1901 = 2415385 - -_TZINFO = PytzCache() - -INT_PATTERN = re.compile(r'([0-9]+)') -FLT_PATTERN = re.compile(r':([0-9]+\.[0-9]+)') -NAME_PATTERN = re.compile(r'([a-zA-Z]+)', re.I) -SPACE_CHARS = ' \t\n' -DELIMITERS = '-/.:,+' - -_MONTH_LEN = ((0, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31), - (0, 31, 29, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31)) -_MONTHS = ('', 'January', 'February', 'March', 'April', 'May', 'June', - 'July', 'August', 'September', 'October', 'November', 'December') -_MONTHS_A = ('', 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', - 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec') -_MONTHS_P = ('', 'Jan.', 'Feb.', 'Mar.', 'Apr.', 'May', 'June', - 'July', 'Aug.', 'Sep.', 'Oct.', 'Nov.', 'Dec.') -_MONTHMAP = {'january': 1, 'jan': 1, - 'february': 2, 'feb': 2, - 'march': 3, 'mar': 3, - 'april': 4, 'apr': 4, - 'may': 5, - 'june': 6, 'jun': 6, - 'july': 7, 'jul': 7, - 'august': 8, 'aug': 8, - 'september': 9, 'sep': 9, 'sept': 9, - 'october': 10, 'oct': 10, - 'november': 11, 'nov': 11, - 'december': 12, 'dec': 12} -_DAYS = ('Sunday', 'Monday', 'Tuesday', 'Wednesday', - 'Thursday', 'Friday', 'Saturday') -_DAYS_A = ('Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat') -_DAYS_P = ('Sun.', 'Mon.', 'Tue.', 'Wed.', 'Thu.', 'Fri.', 'Sat.') -_DAYMAP = {'sunday': 1, 'sun': 1, - 'monday': 2, 'mon': 2, - 'tuesday': 3, 'tues': 3, 'tue': 3, - 'wednesday': 4, 'wed': 4, - 'thursday': 5, 'thurs': 5, 'thur': 5, 'thu': 5, - 'friday': 6, 'fri': 6, - 'saturday': 7, 'sat': 7} - -numericTimeZoneMatch = re.compile(r'[+-][0-9][0-9][0-9][0-9]').match -iso8601Match = re.compile(r''' - (?P\d\d\d\d) # four digits year - (?:-? # one optional dash - (?: # followed by: - (?P\d\d\d # three digits year day - (?!\d)) # when there is no fourth digit - | # or: - W # one W - (?P\d\d) # two digits week - (?:-? # one optional dash - (?P\d) # one digit week day - )? # week day is optional - | # or: - (?P\d\d)? # two digits month - (?:-? # one optional dash - (?P\d\d)? # two digits day - )? # after day is optional - ) # - )? # after year is optional - (?:[T ] # one T or one whitespace - (?P\d\d) # two digits hour - (?::? # one optional colon - (?P\d\d)? # two digits minute - (?::? # one optional colon - (?P\d\d)? # two digits second - (?:[.,] # one dot or one comma - (?P\d+) # n digits fraction - )? # after second is optional - )? # after minute is optional - )? # after hour is optional - (?: # timezone: - (?PZ) # one Z - | # or: - (?P[-+]) # one plus or one minus as signal - (?P\d # one digit for hour offset... - (?:\d(?!\d$) # ...or two, if not the last two digits - )?) # second hour offset digit is optional - (?::? # one optional colon - (?P\d\d) # two digits minute offset - )? # after hour offset is optional - )? # timezone is optional - )? # time is optional - (?P.*) # store the extra garbage -''', re.VERBOSE).match - - -def _findLocalTimeZoneName(isDST): - if not daylight: - # Daylight savings does not occur in this time zone. - isDST = 0 - try: - # Get the name of the current time zone depending - # on DST. - _localzone = PytzCache._zmap[tzname[isDST].lower()] - except BaseException: - try: - # Generate a GMT-offset zone name. - if isDST: - localzone = altzone - else: - localzone = timezone - offset = (-localzone / 3600.0) - majorOffset = int(offset) - if majorOffset != 0: - minorOffset = abs(int((offset % majorOffset) * 60.0)) - else: - minorOffset = 0 - m = majorOffset >= 0 and '+' or '' - lz = '%s%0.02d%0.02d' % (m, majorOffset, minorOffset) - _localzone = PytzCache._zmap[('GMT%s' % lz).lower()] - except BaseException: - _localzone = '' - return _localzone - - -_localzone0 = _findLocalTimeZoneName(0) -_localzone1 = _findLocalTimeZoneName(1) -_multipleZones = (_localzone0 != _localzone1) - -# Some utility functions for calculating dates: - - -def _calcSD(t): - # Returns timezone-independent days since epoch and the fractional - # part of the days. - dd = t + EPOCH - 86400.0 - d = dd / 86400.0 - s = d - math.floor(d) - return s, d - - -def _calcDependentSecond(tz, t): - # Calculates the timezone-dependent second (integer part only) - # from the timezone-independent second. - fset = _tzoffset(tz, t) - return fset + long(math.floor(t)) + long(EPOCH) - 86400 - - -def _calcDependentSecond2(yr, mo, dy, hr, mn, sc): - # Calculates the timezone-dependent second (integer part only) - # from the date given. - ss = int(hr) * 3600 + int(mn) * 60 + int(sc) - x = long(_julianday(yr, mo, dy) - jd1901) * 86400 + ss - return x - - -def _calcIndependentSecondEtc(tz, x, ms): - # Derive the timezone-independent second from the timezone - # dependent second. - fsetAtEpoch = _tzoffset(tz, 0.0) - nearTime = x - fsetAtEpoch - long(EPOCH) + 86400 + ms - # nearTime is now within an hour of being correct. - # Recalculate t according to DST. - fset = long(_tzoffset(tz, nearTime)) - d = (x - fset) / 86400.0 + (ms / 86400.0) - t = x - fset - long(EPOCH) + 86400 + ms - micros = (x + 86400 - fset) * 1000000 + \ - long(round(ms * 1000000.0)) - long(EPOCH * 1000000.0) - s = d - math.floor(d) - return (s, d, t, micros) - - -def _calcHMS(x, ms): - # hours, minutes, seconds from integer and float. - hr = x // 3600 - x = x - hr * 3600 - mn = x // 60 - sc = x - mn * 60 + ms - return (hr, mn, sc) - - -def _calcYMDHMS(x, ms): - # x is a timezone-dependent integer of seconds. - # Produces yr,mo,dy,hr,mn,sc. - yr, mo, dy = _calendarday(x // 86400 + jd1901) - x = int(x - (x // 86400) * 86400) - hr = x // 3600 - x = x - hr * 3600 - mn = x // 60 - sc = x - mn * 60 + ms - return (yr, mo, dy, hr, mn, sc) - - -def _julianday(yr, mo, dy): - y, m, d = long(yr), long(mo), long(dy) - if m > 12: - y = y + m // 12 - m = m % 12 - elif m < 1: - m = -m - y = y - m // 12 - 1 - m = 12 - m % 12 - if y > 0: - yr_correct = 0 - else: - yr_correct = 3 - if m < 3: - y, m = y - 1, m + 12 - if y * 10000 + m * 100 + d > 15821014: - b = 2 - y // 100 + y // 400 - else: - b = 0 - return ((1461 * y - yr_correct) // 4 + - 306001 * (m + 1) // 10000 + d + 1720994 + b) - - -def _calendarday(j): - j = long(j) - if (j < 2299160): - b = j + 1525 - else: - a = (4 * j - 7468861) // 146097 - b = j + 1526 + a - a // 4 - c = (20 * b - 2442) // 7305 - d = 1461 * c // 4 - e = 10000 * (b - d) // 306001 - dy = int(b - d - 306001 * e // 10000) - mo = (e < 14) and int(e - 1) or int(e - 13) - yr = (mo > 2) and (c - 4716) or (c - 4715) - return (int(yr), int(mo), int(dy)) - - -def _tzoffset(tz, t): - """Returns the offset in seconds to GMT from a specific timezone (tz) at - a specific time (t). NB! The _tzoffset result is the same same sign as - the time zone, i.e. GMT+2 has a 7200 second offset. This is the opposite - sign of time.timezone which (confusingly) is -7200 for GMT+2.""" - try: - return _TZINFO[tz].info(t)[0] - except Exception: - if numericTimeZoneMatch(tz) is not None: - return int(tz[0:3]) * 3600 + int(tz[0] + tz[3:5]) * 60 - else: - return 0 # ?? - - -def _correctYear(year): - # Y2K patch. - if year >= 0 and year < 100: - # 00-69 means 2000-2069, 70-99 means 1970-1999. - if year < 70: - year = 2000 + year - else: - year = 1900 + year - return year - - -def safegmtime(t): - '''gmtime with a safety zone.''' - try: - return gmtime(t) - except (ValueError, OverflowError): - raise TimeError('The time %f is beyond the range of this Python ' - 'implementation.' % float(t)) - - -def safelocaltime(t): - '''localtime with a safety zone.''' - try: - return localtime(t) - except (ValueError, OverflowError): - raise TimeError('The time %f is beyond the range of this Python ' - 'implementation.' % float(t)) - - -def _tzoffset2rfc822zone(seconds): - """Takes an offset, such as from _tzoffset(), and returns an rfc822 - compliant zone specification. Please note that the result of - _tzoffset() is the negative of what time.localzone and time.altzone is. - """ - return "%+03d%02d" % divmod((seconds // 60), 60) - - -def _tzoffset2iso8601zone(seconds): - """Takes an offset, such as from _tzoffset(), and returns an ISO 8601 - compliant zone specification. Please note that the result of - _tzoffset() is the negative of what time.localzone and time.altzone is. - """ - return "%+03d:%02d" % divmod((seconds // 60), 60) - - -def Timezones(): - """Return the list of recognized timezone names""" - return sorted(list(PytzCache._zmap.values())) - - -class strftimeFormatter: - - def __init__(self, dt, format): - self.dt = dt - self.format = format - - def __call__(self): - return self.dt.strftime(self.format) - - -@implementer(IDateTime) -class DateTime: - """DateTime objects represent instants in time and provide - interfaces for controlling its representation without - affecting the absolute value of the object. - - DateTime objects may be created from a wide variety of string - or numeric data, or may be computed from other DateTime objects. - DateTimes support the ability to convert their representations - to many major timezones, as well as the ability to create a - DateTime object in the context of a given timezone. - - DateTime objects provide partial numerical behavior: - - - Two date-time objects can be subtracted to obtain a time, - in days between the two. - - - A date-time object and a positive or negative number may - be added to obtain a new date-time object that is the given - number of days later than the input date-time object. - - - A positive or negative number and a date-time object may - be added to obtain a new date-time object that is the given - number of days later than the input date-time object. - - - A positive or negative number may be subtracted from a - date-time object to obtain a new date-time object that is - the given number of days earlier than the input date-time - object. - - DateTime objects may be converted to integer, long, or float - numbers of days since January 1, 1901, using the standard int, - long, and float functions (Compatibility Note: int, long and - float return the number of days since 1901 in GMT rather than - local machine timezone). DateTime objects also provide access - to their value in a float format usable with the Python time - module, provided that the value of the object falls in the - range of the epoch-based time module, and as a datetime.datetime - object. - - A DateTime object should be considered immutable; all conversion - and numeric operations return a new DateTime object rather than - modify the current object.""" - - # For security machinery: - __roles__ = None - __allow_access_to_unprotected_subobjects__ = 1 - - # Limit the amount of instance attributes - __slots__ = ( - '_timezone_naive', - '_tz', - '_dayoffset', - '_year', - '_month', - '_day', - '_hour', - '_minute', - '_second', - '_nearsec', - '_d', - '_micros', - 'time', - ) - - def __init__(self, *args, **kw): - """Return a new date-time object""" - try: - return self._parse_args(*args, **kw) - except (DateError, TimeError, DateTimeError): - raise - except Exception: - raise SyntaxError('Unable to parse {}, {}'.format(args, kw)) - - def __getstate__(self): - return (self._micros, - getattr(self, '_timezone_naive', False), - self._tz) - - def __setstate__(self, value): - if isinstance(value, tuple): - micros, tz_naive, tz = value - if isinstance(micros, float): - # BBB: support for pickle where micros was a float - micros = int(micros * 1000000) - self._parse_args(micros / 1000000., tz) - self._micros = micros - self._timezone_naive = tz_naive - else: - for k, v in value.items(): - if k in self.__slots__: - setattr(self, k, v) - # BBB: support for very old DateTime pickles - if '_micros' not in value: - self._micros = long(value['_t'] * 1000000) - if '_timezone_naive' not in value: - self._timezone_naive = False - - def _parse_args(self, *args, **kw): - """Return a new date-time object. - - A DateTime object always maintains its value as an absolute - UTC time, and is represented in the context of some timezone - based on the arguments used to create the object. A DateTime - object's methods return values based on the timezone context. - - Note that in all cases the local machine timezone is used for - representation if no timezone is specified. - - DateTimes may be created with zero to seven arguments. - - - If the function is called with no arguments or with None, - then the current date/time is returned, represented in the - timezone of the local machine. - - - If the function is invoked with a single string argument - which is a recognized timezone name, an object representing - the current time is returned, represented in the specified - timezone. - - - If the function is invoked with a single string argument - representing a valid date/time, an object representing - that date/time will be returned. - - As a general rule, any date-time representation that is - recognized and unambiguous to a resident of North America - is acceptable. The reason for this qualification is that - in North America, a date like: 2/1/1994 is interpreted - as February 1, 1994, while in some parts of the world, - it is interpreted as January 2, 1994. - - A date/time string consists of two components, a date - component and an optional time component, separated by one - or more spaces. If the time component is omitted, 12:00am is - assumed. Any recognized timezone name specified as the final - element of the date/time string will be used for computing - the date/time value. If you create a DateTime with the - string 'Mar 9, 1997 1:45pm US/Pacific', the value will - essentially be the same as if you had captured time.time() - at the specified date and time on a machine in that timezone: - - 
-            e = DateTime('US/Eastern')
-            # returns current date/time, represented in US/Eastern.
-
-            x = DateTime('1997/3/9 1:45pm')
-            # returns specified time, represented in local machine zone.
-
-            y = DateTime('Mar 9, 1997 13:45:00')
-            # y is equal to x
-
- - The date component consists of year, month, and day - values. The year value must be a one-, two-, or - four-digit integer. If a one- or two-digit year is - used, the year is assumed to be in the twentieth - century. The month may be an integer, from 1 to 12, a - month name, or a month abbreviation, where a period may - optionally follow the abbreviation. The day must be an - integer from 1 to the number of days in the month. The - year, month, and day values may be separated by - periods, hyphens, forward slashes, or spaces. Extra - spaces are permitted around the delimiters. Year, - month, and day values may be given in any order as long - as it is possible to distinguish the components. If all - three components are numbers that are less than 13, - then a month-day-year ordering is assumed. - - The time component consists of hour, minute, and second - values separated by colons. The hour value must be an - integer between 0 and 23 inclusively. The minute value - must be an integer between 0 and 59 inclusively. The - second value may be an integer value between 0 and - 59.999 inclusively. The second value or both the minute - and second values may be omitted. The time may be - followed by am or pm in upper or lower case, in which - case a 12-hour clock is assumed. - - New in Zope 2.4: - The DateTime constructor automatically detects and handles - ISO8601 compliant dates (YYYY-MM-DDThh:ss:mmTZD). - - New in Zope 2.9.6: - The existing ISO8601 parser was extended to support almost - the whole ISO8601 specification. New formats includes: - - 
-            y = DateTime('1993-045')
-            # returns the 45th day from 1993, which is 14th February
-
-            w = DateTime('1993-W06-7')
-            # returns the 7th day from the 6th week from 1993, which
-            # is also 14th February
-
- - See http://en.wikipedia.org/wiki/ISO_8601 for full specs. - - Note that the Zope DateTime parser assumes timezone naive ISO - strings to be in UTC rather than local time as specified. - - - If the DateTime function is invoked with a single numeric - argument, the number is assumed to be a floating point value - such as that returned by time.time(). - - A DateTime object is returned that represents the GMT value - of the time.time() float represented in the local machine's - timezone. - - - If the DateTime function is invoked with a single argument - that is a DateTime instance, a copy of the passed object will - be created. - - - New in 2.11: - The DateTime function may now be invoked with a single argument - that is a datetime.datetime instance. DateTimes may be converted - back to datetime.datetime objects with asdatetime(). - DateTime instances may be converted to a timezone naive - datetime.datetime in UTC with utcdatetime(). - - - If the function is invoked with two numeric arguments, then - the first is taken to be an integer year and the second - argument is taken to be an offset in days from the beginning - of the year, in the context of the local machine timezone. - - The date-time value returned is the given offset number of - days from the beginning of the given year, represented in - the timezone of the local machine. The offset may be positive - or negative. - - Two-digit years are assumed to be in the twentieth - century. - - - If the function is invoked with two arguments, the first - a float representing a number of seconds past the epoch - in gmt (such as those returned by time.time()) and the - second a string naming a recognized timezone, a DateTime - with a value of that gmt time will be returned, represented - in the given timezone. - - 
-            import time
-            t = time.time()
-
-            now_east = DateTime(t,'US/Eastern')
-            # Time t represented as US/Eastern
-
-            now_west = DateTime(t,'US/Pacific')
-            # Time t represented as US/Pacific
-
-            # now_east == now_west
-            # only their representations are different
-
- - - If the function is invoked with three or more numeric - arguments, then the first is taken to be an integer - year, the second is taken to be an integer month, and - the third is taken to be an integer day. If the - combination of values is not valid, then a - DateError is raised. Two-digit years are assumed - to be in the twentieth century. The fourth, fifth, and - sixth arguments specify a time in hours, minutes, and - seconds; hours and minutes should be positive integers - and seconds is a positive floating point value, all of - these default to zero if not given. An optional string may - be given as the final argument to indicate timezone (the - effect of this is as if you had taken the value of time.time() - at that time on a machine in the specified timezone). - - New in Zope 2.7: - A new keyword parameter "datefmt" can be passed to the - constructor. If set to "international", the constructor - is forced to treat ambiguous dates as "days before month - before year". This useful if you need to parse non-US - dates in a reliable way - - In any case that a floating point number of seconds is given - or derived, it's rounded to the nearest millisecond. - - If a string argument passed to the DateTime constructor cannot be - parsed, it will raise DateTime.SyntaxError. Invalid date components - will raise a DateError, while invalid time or timezone components - will raise a DateTimeError. - - The module function Timezones() will return a list of the (common) - timezones recognized by the DateTime module. Recognition of - timezone names is case-insensitive. - """ - - datefmt = kw.get('datefmt', getDefaultDateFormat()) - d = t = s = None - ac = len(args) - microsecs = None - - if ac == 10: - # Internal format called only by DateTime - yr, mo, dy, hr, mn, sc, tz, t, d, s = args - elif ac == 11: - # Internal format that includes milliseconds (from the epoch) - yr, mo, dy, hr, mn, sc, tz, t, d, s, millisecs = args - microsecs = millisecs * 1000 - - elif ac == 12: - # Internal format that includes microseconds (from the epoch) and a - # flag indicating whether this was constructed in a timezone naive - # manner - yr, mo, dy, hr, mn, sc, tz, t, d, s, microsecs, tznaive = args - if tznaive is not None: # preserve this information - self._timezone_naive = tznaive - - elif not args or (ac and args[0] is None): - # Current time, to be displayed in local timezone - t = time() - lt = safelocaltime(t) - tz = self.localZone(lt) - ms = (t - math.floor(t)) - s, d = _calcSD(t) - yr, mo, dy, hr, mn, sc = lt[:6] - sc = sc + ms - self._timezone_naive = False - - elif ac == 1: - arg = args[0] - - if arg == '': - raise SyntaxError(arg) - - if isinstance(arg, DateTime): - """Construct a new DateTime instance from a given - DateTime instance. - """ - t = arg.timeTime() - s, d = _calcSD(t) - yr, mo, dy, hr, mn, sc, tz = arg.parts() - - elif isinstance(arg, datetime): - yr, mo, dy, hr, mn, sc, numerictz, tznaive = \ - self._parse_iso8601_preserving_tznaive(arg.isoformat()) - if arg.tzinfo is None: - self._timezone_naive = True - tz = None - else: - self._timezone_naive = False - # if we have a pytz tzinfo, use the `zone` attribute - # as a key - tz = getattr(arg.tzinfo, 'zone', numerictz) - ms = sc - math.floor(sc) - x = _calcDependentSecond2(yr, mo, dy, hr, mn, sc) - - if tz: - try: - zone = _TZINFO[tz] - except DateTimeError: - try: - zone = _TZINFO[numerictz] - except DateTimeError: - raise DateTimeError( - 'Unknown time zone in date: %s' % arg) - tz = zone.tzinfo.zone - else: - tz = self._calcTimezoneName(x, ms) - s, d, t, microsecs = _calcIndependentSecondEtc(tz, x, ms) - - elif (isinstance(arg, basestring) and - arg.lower() in _TZINFO._zidx): - # Current time, to be displayed in specified timezone - t, tz = time(), _TZINFO._zmap[arg.lower()] - ms = (t - math.floor(t)) - # Use integer arithmetic as much as possible. - s, d = _calcSD(t) - x = _calcDependentSecond(tz, t) - yr, mo, dy, hr, mn, sc = _calcYMDHMS(x, ms) - - elif isinstance(arg, basestring): - # Date/time string - iso8601 = iso8601Match(arg.strip()) - fields_iso8601 = iso8601 and iso8601.groupdict() or {} - if fields_iso8601 and not fields_iso8601.get('garbage'): - yr, mo, dy, hr, mn, sc, tz, tznaive = \ - self._parse_iso8601_preserving_tznaive(arg) - self._timezone_naive = tznaive - else: - yr, mo, dy, hr, mn, sc, tz = self._parse(arg, datefmt) - - if not self._validDate(yr, mo, dy): - raise DateError('Invalid date: %s' % arg) - if not self._validTime(hr, mn, int(sc)): - raise TimeError('Invalid time: %s' % arg) - ms = sc - math.floor(sc) - x = _calcDependentSecond2(yr, mo, dy, hr, mn, sc) - - if tz: - try: - tz = _TZINFO._zmap[tz.lower()] - except KeyError: - if numericTimeZoneMatch(tz) is None: - raise DateTimeError( - 'Unknown time zone in date: %s' % arg) - else: - tz = self._calcTimezoneName(x, ms) - s, d, t, microsecs = _calcIndependentSecondEtc(tz, x, ms) - - else: - # Seconds from epoch, gmt - t = arg - lt = safelocaltime(t) - tz = self.localZone(lt) - ms = (t - math.floor(t)) - s, d = _calcSD(t) - yr, mo, dy, hr, mn, sc = lt[:6] - sc = sc + ms - - elif ac == 2: - if isinstance(args[1], basestring): - # Seconds from epoch (gmt) and timezone - t, tz = args - ms = (t - math.floor(t)) - try: - tz = _TZINFO._zmap[tz.lower()] - except KeyError: - if numericTimeZoneMatch(tz) is None: - raise DateTimeError('Unknown time zone: %s' % tz) - # Use integer arithmetic as much as possible. - s, d = _calcSD(t) - x = _calcDependentSecond(tz, t) - yr, mo, dy, hr, mn, sc = _calcYMDHMS(x, ms) - else: - # Year, julian expressed in local zone - t = time() - lt = safelocaltime(t) - tz = self.localZone(lt) - yr, jul = args - yr = _correctYear(yr) - d = (_julianday(yr, 1, 0) - jd1901) + jul - x_float = d * 86400.0 - x_floor = math.floor(x_float) - ms = x_float - x_floor - x = long(x_floor) - yr, mo, dy, hr, mn, sc = _calcYMDHMS(x, ms) - s, d, t, microsecs = _calcIndependentSecondEtc(tz, x, ms) - else: - # Explicit format - yr, mo, dy = args[:3] - hr, mn, sc, tz = 0, 0, 0, 0 - yr = _correctYear(yr) - if not self._validDate(yr, mo, dy): - raise DateError('Invalid date: {}'.format(args)) - args = args[3:] - if args: - hr, args = args[0], args[1:] - if args: - mn, args = args[0], args[1:] - if args: - sc, args = args[0], args[1:] - if args: - tz, args = args[0], args[1:] - if args: - raise DateTimeError('Too many arguments') - if not self._validTime(hr, mn, sc): - raise TimeError('Invalid time: %s' % repr(args)) - - x = _calcDependentSecond2(yr, mo, dy, hr, mn, sc) - ms = sc - math.floor(sc) - if tz: - try: - tz = _TZINFO._zmap[tz.lower()] - except KeyError: - if numericTimeZoneMatch(tz) is None: - raise DateTimeError('Unknown time zone: %s' % tz) - else: - # Get local time zone name - tz = self._calcTimezoneName(x, ms) - s, d, t, microsecs = _calcIndependentSecondEtc(tz, x, ms) - - self._dayoffset = int((_julianday(yr, mo, dy) + 2) % 7) - # Round to nearest microsecond in platform-independent way. You - # cannot rely on C sprintf (Python '%') formatting to round - # consistently; doing it ourselves ensures that all but truly - # horrid C sprintf implementations will yield the same result - # cross-platform, provided the format asks for exactly 6 digits after - # the decimal point. - sc = round(sc, 6) - if sc >= 60.0: # can happen if, e.g., orig sc was 59.9999999 - sc = 59.999999 - self._nearsec = math.floor(sc) - self._year, self._month, self._day = yr, mo, dy - self._hour, self._minute, self._second = hr, mn, sc - self.time, self._d, self._tz = s, d, tz - # self._micros is the time since the epoch - # in long integer microseconds. - if microsecs is None: - microsecs = long(round(t * 1000000.0)) - self._micros = microsecs - - def localZone(self, ltm=None): - '''Returns the time zone on the given date. The time zone - can change according to daylight savings.''' - if not _multipleZones: - return _localzone0 - if ltm is None: - ltm = localtime(time()) - isDST = ltm[8] - lz = isDST and _localzone1 or _localzone0 - return lz - - def _calcTimezoneName(self, x, ms): - # Derive the name of the local time zone at the given - # timezone-dependent second. - if not _multipleZones: - return _localzone0 - fsetAtEpoch = _tzoffset(_localzone0, 0.0) - nearTime = x - fsetAtEpoch - long(EPOCH) + 86400 + ms - # nearTime is within an hour of being correct. - try: - ltm = safelocaltime(nearTime) - except BaseException: - # We are beyond the range of Python's date support. - # Hopefully we can assume that daylight savings schedules - # repeat every 28 years. Calculate the name of the - # time zone using a supported range of years. - yr, mo, dy, hr, mn, sc = _calcYMDHMS(x, 0) - yr = ((yr - 1970) % 28) + 1970 - x = _calcDependentSecond2(yr, mo, dy, hr, mn, sc) - nearTime = x - fsetAtEpoch - long(EPOCH) + 86400 + ms - - # nearTime might still be negative if we are east of Greenwich. - # But we can assume on 1969/12/31 were no timezone changes. - nearTime = max(0, nearTime) - - ltm = safelocaltime(nearTime) - tz = self.localZone(ltm) - return tz - - def _parse(self, st, datefmt=getDefaultDateFormat()): - # Parse date-time components from a string - month = year = tz = tm = None - ValidZones = _TZINFO._zidx - TimeModifiers = ['am', 'pm'] - - # Find timezone first, since it should always be the last - # element, and may contain a slash, confusing the parser. - st = st.strip() - sp = st.split() - tz = sp[-1] - if tz and (tz.lower() in ValidZones): - self._timezone_naive = False - st = ' '.join(sp[:-1]) - else: - self._timezone_naive = True - tz = None # Decide later, since the default time zone - # could depend on the date. - - ints = [] - i = 0 - len_st = len(st) - while i < len_st: - while i < len_st and st[i] in SPACE_CHARS: - i += 1 - if i < len_st and st[i] in DELIMITERS: - d = st[i] - i += 1 - else: - d = '' - while i < len_st and st[i] in SPACE_CHARS: - i += 1 - - # The float pattern needs to look back 1 character, because it - # actually looks for a preceding colon like ':33.33'. This is - # needed to avoid accidentally matching the date part of a - # dot-separated date string such as '1999.12.31'. - if i > 0: - b = i - 1 - else: - b = i - - ts_results = FLT_PATTERN.match(st, b) - if ts_results: - s = ts_results.group(1) - i = i + len(s) - ints.append(float(s)) - continue - - ts_results = INT_PATTERN.match(st, i) - if ts_results: - s = ts_results.group(0) - - ls = len(s) - i = i + ls - if (ls == 4 and d and d in '+-' and - (len(ints) + (not not month) >= 3)): - tz = '{}{}'.format(d, s) - else: - v = int(s) - ints.append(v) - continue - - ts_results = NAME_PATTERN.match(st, i) - if ts_results: - s = ts_results.group(0).lower() - i = i + len(s) - if i < len_st and st[i] == '.': - i += 1 - # Check for month name: - _v = _MONTHMAP.get(s) - if _v is not None: - if month is None: - month = _v - else: - raise SyntaxError(st) - continue - # Check for time modifier: - if s in TimeModifiers: - if tm is None: - tm = s - else: - raise SyntaxError(st) - continue - # Check for and skip day of week: - if s in _DAYMAP: - continue - - raise SyntaxError(st) - - day = None - if ints[-1] > 60 and d not in ('.', ':', '/') and len(ints) > 2: - year = ints[-1] - del ints[-1] - if month: - day = ints[0] - del ints[:1] - else: - if datefmt == "us": - month = ints[0] - day = ints[1] - else: - month = ints[1] - day = ints[0] - del ints[:2] - elif month: - if len(ints) > 1: - if ints[0] > 31: - year = ints[0] - day = ints[1] - else: - year = ints[1] - day = ints[0] - del ints[:2] - elif len(ints) > 2: - if ints[0] > 31: - year = ints[0] - if ints[1] > 12: - day = ints[1] - month = ints[2] - else: - day = ints[2] - month = ints[1] - if ints[1] > 31: - year = ints[1] - if ints[0] > 12 and ints[2] <= 12: - day = ints[0] - month = ints[2] - elif ints[2] > 12 and ints[0] <= 12: - day = ints[2] - month = ints[0] - elif ints[2] > 31: - year = ints[2] - if ints[0] > 12: - day = ints[0] - month = ints[1] - else: - if datefmt == "us": - day = ints[1] - month = ints[0] - else: - day = ints[0] - month = ints[1] - - elif ints[0] <= 12: - month = ints[0] - day = ints[1] - year = ints[2] - del ints[:3] - - if day is None: - # Use today's date. - year, month, day = localtime(time())[:3] - - year = _correctYear(year) - if year < 1000: - raise SyntaxError(st) - - leap = year % 4 == 0 and (year % 100 != 0 or year % 400 == 0) - try: - if not day or day > _MONTH_LEN[leap][month]: - raise DateError(st) - except IndexError: - raise DateError(st) - - tod = 0 - if ints: - i = ints[0] - # Modify hour to reflect am/pm - if tm and (tm == 'pm') and i < 12: - i += 12 - if tm and (tm == 'am') and i == 12: - i = 0 - if i > 24: - raise TimeError(st) - tod = tod + int(i) * 3600 - del ints[0] - if ints: - i = ints[0] - if i > 60: - raise TimeError(st) - tod = tod + int(i) * 60 - del ints[0] - if ints: - i = ints[0] - if i > 60: - raise TimeError(st) - tod = tod + i - del ints[0] - if ints: - raise SyntaxError(st) - - tod_int = int(math.floor(tod)) - ms = tod - tod_int - hr, mn, sc = _calcHMS(tod_int, ms) - if not tz: - # Figure out what time zone it is in the local area - # on the given date. - x = _calcDependentSecond2(year, month, day, hr, mn, sc) - tz = self._calcTimezoneName(x, ms) - - return year, month, day, hr, mn, sc, tz - - # Internal methods - def _validDate(self, y, m, d): - if m < 1 or m > 12 or y < 0 or d < 1 or d > 31: - return 0 - return d <= _MONTH_LEN[ - (y % 4 == 0 and (y % 100 != 0 or y % 400 == 0))][m] - - def _validTime(self, h, m, s): - return h >= 0 and h <= 23 and m >= 0 and m <= 59 and s >= 0 and s < 60 - - def __getattr__(self, name): - if '%' in name: - return strftimeFormatter(self, name) - raise AttributeError(name) - - # Conversion and comparison methods - - def timeTime(self): - """Return the date/time as a floating-point number in UTC, - in the format used by the Python time module. - - Note that it is possible to create date/time values with - DateTime that have no meaningful value to the time module. - """ - return self._micros / 1000000.0 - - def toZone(self, z): - """Return a DateTime with the value as the current - object, represented in the indicated timezone. - """ - t, tz = self._t, _TZINFO._zmap[z.lower()] - micros = self.micros() - tznaive = False # you're performing a timzone change, can't be naive - - try: - # Try to use time module for speed. - yr, mo, dy, hr, mn, sc = safegmtime(t + _tzoffset(tz, t))[:6] - sc = self._second - return self.__class__(yr, mo, dy, hr, mn, sc, tz, t, - self._d, self.time, micros, tznaive) - except Exception: - # gmtime can't perform the calculation in the given range. - # Calculate the difference between the two time zones. - tzdiff = _tzoffset(tz, t) - _tzoffset(self._tz, t) - if tzdiff == 0: - return self - sc = self._second - ms = sc - math.floor(sc) - x = _calcDependentSecond2(self._year, self._month, self._day, - self._hour, self._minute, sc) - x_new = x + tzdiff - yr, mo, dy, hr, mn, sc = _calcYMDHMS(x_new, ms) - return self.__class__(yr, mo, dy, hr, mn, sc, tz, t, - self._d, self.time, micros, tznaive) - - def isFuture(self): - """Return true if this object represents a date/time - later than the time of the call. - """ - return (self._t > time()) - - def isPast(self): - """Return true if this object represents a date/time - earlier than the time of the call. - """ - return (self._t < time()) - - def isCurrentYear(self): - """Return true if this object represents a date/time - that falls within the current year, in the context - of this object's timezone representation. - """ - t = time() - return safegmtime(t + _tzoffset(self._tz, t))[0] == self._year - - def isCurrentMonth(self): - """Return true if this object represents a date/time - that falls within the current month, in the context - of this object's timezone representation. - """ - t = time() - gmt = safegmtime(t + _tzoffset(self._tz, t)) - return gmt[0] == self._year and gmt[1] == self._month - - def isCurrentDay(self): - """Return true if this object represents a date/time - that falls within the current day, in the context - of this object's timezone representation. - """ - t = time() - gmt = safegmtime(t + _tzoffset(self._tz, t)) - return (gmt[0] == self._year and gmt[1] == self._month and - gmt[2] == self._day) - - def isCurrentHour(self): - """Return true if this object represents a date/time - that falls within the current hour, in the context - of this object's timezone representation. - """ - t = time() - gmt = safegmtime(t + _tzoffset(self._tz, t)) - return (gmt[0] == self._year and gmt[1] == self._month and - gmt[2] == self._day and gmt[3] == self._hour) - - def isCurrentMinute(self): - """Return true if this object represents a date/time - that falls within the current minute, in the context - of this object's timezone representation. - """ - t = time() - gmt = safegmtime(t + _tzoffset(self._tz, t)) - return (gmt[0] == self._year and gmt[1] == self._month and - gmt[2] == self._day and gmt[3] == self._hour and - gmt[4] == self._minute) - - def earliestTime(self): - """Return a new DateTime object that represents the earliest - possible time (in whole seconds) that still falls within - the current object's day, in the object's timezone context. - """ - return self.__class__( - self._year, self._month, self._day, 0, 0, 0, self._tz) - - def latestTime(self): - """Return a new DateTime object that represents the latest - possible time (in whole seconds) that still falls within - the current object's day, in the object's timezone context. - """ - return self.__class__( - self._year, self._month, self._day, 23, 59, 59, self._tz) - - def greaterThan(self, t): - """Compare this DateTime object to another DateTime object - OR a floating point number such as that which is returned - by the Python time module. - - Returns true if the object represents a date/time greater - than the specified DateTime or time module style time. - - Revised to give more correct results through comparison of - long integer microseconds. - """ - if t is None: - return True - if isinstance(t, (float, int)): - return self._micros > long(t * 1000000) - try: - return self._micros > t._micros - except AttributeError: - return self._micros > t - - __gt__ = greaterThan - - def greaterThanEqualTo(self, t): - """Compare this DateTime object to another DateTime object - OR a floating point number such as that which is returned - by the Python time module. - - Returns true if the object represents a date/time greater - than or equal to the specified DateTime or time module style - time. - - Revised to give more correct results through comparison of - long integer microseconds. - """ - if t is None: - return True - if isinstance(t, (float, int)): - return self._micros >= long(t * 1000000) - try: - return self._micros >= t._micros - except AttributeError: - return self._micros >= t - - __ge__ = greaterThanEqualTo - - def equalTo(self, t): - """Compare this DateTime object to another DateTime object - OR a floating point number such as that which is returned - by the Python time module. - - Returns true if the object represents a date/time equal to - the specified DateTime or time module style time. - - Revised to give more correct results through comparison of - long integer microseconds. - """ - if t is None: - return False - if isinstance(t, (float, int)): - return self._micros == long(t * 1000000) - try: - return self._micros == t._micros - except AttributeError: - return self._micros == t - - def notEqualTo(self, t): - """Compare this DateTime object to another DateTime object - OR a floating point number such as that which is returned - by the Python time module. - - Returns true if the object represents a date/time not equal - to the specified DateTime or time module style time. - - Revised to give more correct results through comparison of - long integer microseconds. - """ - return not self.equalTo(t) - - def __eq__(self, t): - """Compare this DateTime object to another DateTime object. - Return True if their internal state is the same. Two objects - representing the same time in different timezones are regared as - unequal. Use the equalTo method if you are only interested in them - referring to the same moment in time. - """ - if not isinstance(t, DateTime): - return False - return (self._micros, self._tz) == (t._micros, t._tz) - - def __ne__(self, t): - return not self.__eq__(t) - - def lessThan(self, t): - """Compare this DateTime object to another DateTime object - OR a floating point number such as that which is returned - by the Python time module. - - Returns true if the object represents a date/time less than - the specified DateTime or time module style time. - - Revised to give more correct results through comparison of - long integer microseconds. - """ - if t is None: - return False - if isinstance(t, (float, int)): - return self._micros < long(t * 1000000) - try: - return self._micros < t._micros - except AttributeError: - return self._micros < t - - __lt__ = lessThan - - def lessThanEqualTo(self, t): - """Compare this DateTime object to another DateTime object - OR a floating point number such as that which is returned - by the Python time module. - - Returns true if the object represents a date/time less than - or equal to the specified DateTime or time module style time. - - Revised to give more correct results through comparison of - long integer microseconds. - """ - if t is None: - return False - if isinstance(t, (float, int)): - return self._micros <= long(t * 1000000) - try: - return self._micros <= t._micros - except AttributeError: - return self._micros <= t - - __le__ = lessThanEqualTo - - def isLeapYear(self): - """Return true if the current year (in the context of the - object's timezone) is a leap year. - """ - return (self._year % 4 == 0 and - (self._year % 100 != 0 or self._year % 400 == 0)) - - def dayOfYear(self): - """Return the day of the year, in context of the timezone - representation of the object. - """ - d = int(self._d + (_tzoffset(self._tz, self._t) / 86400.0)) - return int((d + jd1901) - _julianday(self._year, 1, 0)) - - # Component access - def parts(self): - """Return a tuple containing the calendar year, month, - day, hour, minute second and timezone of the object. - """ - return (self._year, self._month, self._day, self._hour, - self._minute, self._second, self._tz) - - def timezone(self): - """Return the timezone in which the object is represented.""" - return self._tz - - def tzoffset(self): - """Return the timezone offset for the objects timezone.""" - return _tzoffset(self._tz, self._t) - - def year(self): - """Return the calendar year of the object.""" - return self._year - - def month(self): - """Return the month of the object as an integer.""" - return self._month - - @property - def _fmon(self): - return _MONTHS[self._month] - - def Month(self): - """Return the full month name.""" - return self._fmon - - @property - def _amon(self): - return _MONTHS_A[self._month] - - def aMonth(self): - """Return the abbreviated month name.""" - return self._amon - - def Mon(self): - """Compatibility: see aMonth.""" - return self._amon - - @property - def _pmon(self): - return _MONTHS_P[self._month] - - def pMonth(self): - """Return the abbreviated (with period) month name.""" - return self._pmon - - def Mon_(self): - """Compatibility: see pMonth.""" - return self._pmon - - def day(self): - """Return the integer day.""" - return self._day - - @property - def _fday(self): - return _DAYS[self._dayoffset] - - def Day(self): - """Return the full name of the day of the week.""" - return self._fday - - def DayOfWeek(self): - """Compatibility: see Day.""" - return self._fday - - @property - def _aday(self): - return _DAYS_A[self._dayoffset] - - def aDay(self): - """Return the abbreviated name of the day of the week.""" - return self._aday - - @property - def _pday(self): - return _DAYS_P[self._dayoffset] - - def pDay(self): - """Return the abbreviated (with period) name of the day of the week.""" - return self._pday - - def Day_(self): - """Compatibility: see pDay.""" - return self._pday - - def dow(self): - """Return the integer day of the week, where Sunday is 0.""" - return self._dayoffset - - def dow_1(self): - """Return the integer day of the week, where Sunday is 1.""" - return self._dayoffset + 1 - - @property - def _pmhour(self): - hr = self._hour - if hr > 12: - return hr - 12 - return hr or 12 - - def h_12(self): - """Return the 12-hour clock representation of the hour.""" - return self._pmhour - - def h_24(self): - """Return the 24-hour clock representation of the hour.""" - return self._hour - - @property - def _pm(self): - hr = self._hour - if hr >= 12: - return 'pm' - return 'am' - - def ampm(self): - """Return the appropriate time modifier (am or pm).""" - return self._pm - - def hour(self): - """Return the 24-hour clock representation of the hour.""" - return self._hour - - def minute(self): - """Return the minute.""" - return self._minute - - def second(self): - """Return the second.""" - return self._second - - def millis(self): - """Return the millisecond since the epoch in GMT.""" - return self._micros // 1000 - - def micros(self): - """Return the microsecond since the epoch in GMT.""" - return self._micros - - def timezoneNaive(self): - """The Python datetime module introduces the idea of distinguishing - between timezone aware and timezone naive datetime values. For lossless - conversion to and from datetime.datetime we record this - information using True / False. DateTime makes no distinction, if we - don't have any information we return None here. - """ - try: - return self._timezone_naive - except AttributeError: - return None - - def strftime(self, format): - """Format the date/time using the *current timezone representation*.""" - x = _calcDependentSecond2(self._year, self._month, self._day, - self._hour, self._minute, self._second) - ltz = self._calcTimezoneName(x, 0) - tzdiff = _tzoffset(ltz, self._t) - _tzoffset(self._tz, self._t) - zself = self + tzdiff / 86400.0 - microseconds = int((zself._second - zself._nearsec) * 1000000) - unicode_format = False - if isinstance(format, explicit_unicode_type): - format = format.encode('utf-8') - unicode_format = True - ds = datetime(zself._year, zself._month, zself._day, zself._hour, - zself._minute, int(zself._nearsec), - microseconds).strftime(format) - if unicode_format: - return ds.decode('utf-8') - return ds - - # General formats from previous DateTime - def Date(self): - """Return the date string for the object.""" - return "%s/%2.2d/%2.2d" % (self._year, self._month, self._day) - - def Time(self): - """Return the time string for an object to the nearest second.""" - return '%2.2d:%2.2d:%2.2d' % (self._hour, self._minute, self._nearsec) - - def TimeMinutes(self): - """Return the time string for an object not showing seconds.""" - return '%2.2d:%2.2d' % (self._hour, self._minute) - - def AMPM(self): - """Return the time string for an object to the nearest second.""" - return '%2.2d:%2.2d:%2.2d %s' % ( - self._pmhour, self._minute, self._nearsec, self._pm) - - def AMPMMinutes(self): - """Return the time string for an object not showing seconds.""" - return '%2.2d:%2.2d %s' % (self._pmhour, self._minute, self._pm) - - def PreciseTime(self): - """Return the time string for the object.""" - return '%2.2d:%2.2d:%06.3f' % (self._hour, self._minute, self._second) - - def PreciseAMPM(self): - """Return the time string for the object.""" - return '%2.2d:%2.2d:%06.3f %s' % ( - self._pmhour, self._minute, self._second, self._pm) - - def yy(self): - """Return calendar year as a 2 digit string.""" - return str(self._year)[-2:] - - def mm(self): - """Return month as a 2 digit string.""" - return '%02d' % self._month - - def dd(self): - """Return day as a 2 digit string.""" - return '%02d' % self._day - - def rfc822(self): - """Return the date in RFC 822 format.""" - tzoffset = _tzoffset2rfc822zone(_tzoffset(self._tz, self._t)) - return '%s, %2.2d %s %d %2.2d:%2.2d:%2.2d %s' % ( - self._aday, self._day, self._amon, self._year, - self._hour, self._minute, self._nearsec, tzoffset) - - # New formats - def fCommon(self): - """Return a string representing the object's value - in the format: March 1, 1997 1:45 pm. - """ - return '%s %s, %4.4d %s:%2.2d %s' % ( - self._fmon, self._day, self._year, self._pmhour, - self._minute, self._pm) - - def fCommonZ(self): - """Return a string representing the object's value - in the format: March 1, 1997 1:45 pm US/Eastern. - """ - return '%s %s, %4.4d %d:%2.2d %s %s' % ( - self._fmon, self._day, self._year, self._pmhour, - self._minute, self._pm, self._tz) - - def aCommon(self): - """Return a string representing the object's value - in the format: Mar 1, 1997 1:45 pm. - """ - return '%s %s, %4.4d %s:%2.2d %s' % ( - self._amon, self._day, self._year, self._pmhour, - self._minute, self._pm) - - def aCommonZ(self): - """Return a string representing the object's value - in the format: Mar 1, 1997 1:45 pm US/Eastern. - """ - return '%s %s, %4.4d %d:%2.2d %s %s' % ( - self._amon, self._day, self._year, self._pmhour, - self._minute, self._pm, self._tz) - - def pCommon(self): - """Return a string representing the object's value - in the format: Mar. 1, 1997 1:45 pm. - """ - return '%s %s, %4.4d %s:%2.2d %s' % ( - self._pmon, self._day, self._year, self._pmhour, - self._minute, self._pm) - - def pCommonZ(self): - """Return a string representing the object's value - in the format: Mar. 1, 1997 1:45 pm US/Eastern. - """ - return '%s %s, %4.4d %d:%2.2d %s %s' % ( - self._pmon, self._day, self._year, self._pmhour, - self._minute, self._pm, self._tz) - - def ISO(self): - """Return the object in ISO standard format. - - Note: this is *not* ISO 8601-format! See the ISO8601 and - HTML4 methods below for ISO 8601-compliant output. - - Dates are output as: YYYY-MM-DD HH:MM:SS - """ - return "%.4d-%.2d-%.2d %.2d:%.2d:%.2d" % ( - self._year, self._month, self._day, - self._hour, self._minute, self._second) - - def ISO8601(self): - """Return the object in ISO 8601-compatible format containing the - date, time with seconds-precision and the time zone identifier. - - See: http://www.w3.org/TR/NOTE-datetime - - Dates are output as: YYYY-MM-DDTHH:MM:SSTZD - T is a literal character. - TZD is Time Zone Designator, format +HH:MM or -HH:MM - - If the instance is timezone naive (it was not specified with a timezone - when it was constructed) then the timezone is omitted. - - The HTML4 method below offers the same formatting, but converts - to UTC before returning the value and sets the TZD "Z". - """ - if self.timezoneNaive(): - return "%0.4d-%0.2d-%0.2dT%0.2d:%0.2d:%0.2d" % ( - self._year, self._month, self._day, - self._hour, self._minute, self._second) - tzoffset = _tzoffset2iso8601zone(_tzoffset(self._tz, self._t)) - return "%0.4d-%0.2d-%0.2dT%0.2d:%0.2d:%0.2d%s" % ( - self._year, self._month, self._day, - self._hour, self._minute, self._second, tzoffset) - - def HTML4(self): - """Return the object in the format used in the HTML4.0 specification, - one of the standard forms in ISO8601. - - See: http://www.w3.org/TR/NOTE-datetime - - Dates are output as: YYYY-MM-DDTHH:MM:SSZ - T, Z are literal characters. - The time is in UTC. - """ - newdate = self.toZone('UTC') - return "%0.4d-%0.2d-%0.2dT%0.2d:%0.2d:%0.2dZ" % ( - newdate._year, newdate._month, newdate._day, - newdate._hour, newdate._minute, newdate._second) - - def asdatetime(self): - """Return a standard library datetime.datetime - """ - tznaive = self.timezoneNaive() - if tznaive: - tzinfo = None - else: - tzinfo = _TZINFO[self._tz].tzinfo - second = int(self._second) - microsec = self.micros() % 1000000 - dt = datetime(self._year, self._month, self._day, self._hour, - self._minute, second, microsec, tzinfo) - return dt - - def utcdatetime(self): - """Convert the time to UTC and return a timezone naive datetime object - """ - utc = self.toZone('UTC') - second = int(utc._second) - microsec = utc.micros() % 1000000 - dt = datetime(utc._year, utc._month, utc._day, utc._hour, - utc._minute, second, microsec) - return dt - - def __add__(self, other): - """A DateTime may be added to a number and a number may be - added to a DateTime; two DateTimes cannot be added. - """ - if hasattr(other, '_t'): - raise DateTimeError('Cannot add two DateTimes') - o = float(other) - tz = self._tz - omicros = round(o * 86400000000) - tmicros = self.micros() + omicros - t = tmicros / 1000000.0 - d = (tmicros + long(EPOCH * 1000000)) / 86400000000.0 - s = d - math.floor(d) - ms = t - math.floor(t) - x = _calcDependentSecond(tz, t) - yr, mo, dy, hr, mn, sc = _calcYMDHMS(x, ms) - return self.__class__(yr, mo, dy, hr, mn, sc, self._tz, - t, d, s, tmicros, self.timezoneNaive()) - - __radd__ = __add__ - - def __sub__(self, other): - """Either a DateTime or a number may be subtracted from a - DateTime, however, a DateTime may not be subtracted from - a number. - """ - if hasattr(other, '_d'): - return (self.micros() - other.micros()) / 86400000000.0 - else: - return self.__add__(-(other)) - - def __repr__(self): - """Convert a DateTime to a string that looks like a Python - expression. - """ - return '{}(\'{}\')'.format(self.__class__.__name__, str(self)) - - def __str__(self): - """Convert a DateTime to a string.""" - y, m, d = self._year, self._month, self._day - h, mn, s, t = self._hour, self._minute, self._second, self._tz - if s == int(s): - # A whole number of seconds -- suppress milliseconds. - return '%4.4d/%2.2d/%2.2d %2.2d:%2.2d:%2.2d %s' % ( - y, m, d, h, mn, s, t) - else: - # s is already rounded to the nearest microsecond, and - # it's not a whole number of seconds. Be sure to print - # 2 digits before the decimal point. - return '%4.4d/%2.2d/%2.2d %2.2d:%2.2d:%06.6f %s' % ( - y, m, d, h, mn, s, t) - - def __format__(self, fmt): - """Render a DateTime in an f-string.""" - if not isinstance(fmt, str): - raise TypeError("must be str, not %s" % type(fmt).__name__) - if len(fmt) != 0: - return self.strftime(fmt) - return str(self) - - def __hash__(self): - """Compute a hash value for a DateTime.""" - return int(((self._year % 100 * 12 + self._month) * 31 + - self._day + self.time) * 100) - - def __int__(self): - """Convert to an integer number of seconds since the epoch (gmt).""" - return int(self.micros() // 1000000) - - def __long__(self): - """Convert to a long-int number of seconds since the epoch (gmt).""" - return long(self.micros() // 1000000) # pragma: PY2 - - def __float__(self): - """Convert to floating-point number of seconds since the epoch (gmt). - """ - return self.micros() / 1000000.0 - - @property - def _t(self): - return self._micros / 1000000.0 - - def _parse_iso8601(self, s): - # preserve the previously implied contract - # who knows where this could be used... - return self._parse_iso8601_preserving_tznaive(s)[:7] - - def _parse_iso8601_preserving_tznaive(self, s): - try: - return self.__parse_iso8601(s) - except IndexError: - raise SyntaxError( - 'Not an ISO 8601 compliant date string: "%s"' % s) - - def __parse_iso8601(self, s): - """Parse an ISO 8601 compliant date. - - See: http://en.wikipedia.org/wiki/ISO_8601 - """ - month = day = week_day = 1 - year = hour = minute = seconds = hour_off = min_off = 0 - tznaive = True - - iso8601 = iso8601Match(s.strip()) - fields = iso8601 and iso8601.groupdict() or {} - if not iso8601 or fields.get('garbage'): - raise IndexError - - if fields['year']: - year = int(fields['year']) - if fields['month']: - month = int(fields['month']) - if fields['day']: - day = int(fields['day']) - - if fields['year_day']: - d = DateTime('%s-01-01' % year) + int(fields['year_day']) - 1 - month = d.month() - day = d.day() - - if fields['week']: - week = int(fields['week']) - if fields['week_day']: - week_day = int(fields['week_day']) - d = DateTime('%s-01-04' % year) - d = d - (d.dow() + 6) % 7 + week * 7 + week_day - 8 - month = d.month() - day = d.day() - - if fields['hour']: - hour = int(fields['hour']) - - if fields['minute']: - minute = int(fields['minute']) - elif fields['fraction']: - minute = 60.0 * float('0.%s' % fields['fraction']) - seconds, minute = math.modf(minute) - minute = int(minute) - seconds = 60.0 * seconds - # Avoid reprocess when handling seconds, bellow - fields['fraction'] = None - - if fields['second']: - seconds = int(fields['second']) - if fields['fraction']: - seconds = seconds + float('0.%s' % fields['fraction']) - elif fields['fraction']: - seconds = 60.0 * float('0.%s' % fields['fraction']) - - if fields['hour_off']: - hour_off = int(fields['hour_off']) - if fields['signal'] == '-': - hour_off *= -1 - - if fields['min_off']: - min_off = int(fields['min_off']) - - if fields['signal'] or fields['Z']: - tznaive = False - else: - tznaive = True - - # Differ from the specification here. To preserve backwards - # compatibility assume a default timezone == UTC. - tz = 'GMT%+03d%02d' % (hour_off, min_off) - - return year, month, day, hour, minute, seconds, tz, tznaive - - def JulianDay(self): - """Return the Julian day. - - See: https://www.tondering.dk/claus/cal/julperiod.php#formula - """ - a = (14 - self._month) // 12 - y = self._year + 4800 - a - m = self._month + (12 * a) - 3 - return (self._day + (153 * m + 2) // 5 + 365 * y + - y // 4 - y // 100 + y // 400 - 32045) - - def week(self): - """Return the week number according to ISO. - - See: https://www.tondering.dk/claus/cal/week.php#weekno - """ - J = self.JulianDay() - d4 = (J + 31741 - (J % 7)) % 146097 % 36524 % 1461 - L = d4 // 1460 - d1 = ((d4 - L) % 365) + L - return d1 // 7 + 1 - - def encode(self, out): - """Encode value for XML-RPC.""" - out.write('') - out.write(self.ISO8601()) - out.write('\n') - - -# Provide the _dt_reconstructor function here, in case something -# accidentally creates a reference to this function - -orig_reconstructor = copy_reg._reconstructor - - -def _dt_reconstructor(cls, base, state): - if cls is DateTime: - return cls(state) - return orig_reconstructor(cls, base, state) diff --git a/llmlab/lib/python3.12/site-packages/DateTime/DateTime.txt b/llmlab/lib/python3.12/site-packages/DateTime/DateTime.txt deleted file mode 100644 index aaa9f8f..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/DateTime.txt +++ /dev/null @@ -1,785 +0,0 @@ -The DateTime package -==================== - -Encapsulation of date/time values. - - -Function Timezones() --------------------- - -Returns the list of recognized timezone names: - - >>> from DateTime import Timezones - >>> zones = set(Timezones()) - -Almost all of the standard pytz timezones are included, with the exception -of some commonly-used but ambiguous abbreviations, where historical Zope -usage conflicts with the name used by pytz: - - >>> import pytz - >>> [x for x in pytz.all_timezones if x not in zones] - ['CET', 'EET', 'EST', 'MET', 'MST', 'WET'] - -Class DateTime --------------- - -DateTime objects represent instants in time and provide interfaces for -controlling its representation without affecting the absolute value of -the object. - -DateTime objects may be created from a wide variety of string or -numeric data, or may be computed from other DateTime objects. -DateTimes support the ability to convert their representations to many -major timezones, as well as the ability to create a DateTime object -in the context of a given timezone. - -DateTime objects provide partial numerical behavior: - -* Two date-time objects can be subtracted to obtain a time, in days - between the two. - -* A date-time object and a positive or negative number may be added to - obtain a new date-time object that is the given number of days later - than the input date-time object. - -* A positive or negative number and a date-time object may be added to - obtain a new date-time object that is the given number of days later - than the input date-time object. - -* A positive or negative number may be subtracted from a date-time - object to obtain a new date-time object that is the given number of - days earlier than the input date-time object. - -DateTime objects may be converted to integer, long, or float numbers -of days since January 1, 1901, using the standard int, long, and float -functions (Compatibility Note: int, long and float return the number -of days since 1901 in GMT rather than local machine timezone). -DateTime objects also provide access to their value in a float format -usable with the Python time module, provided that the value of the -object falls in the range of the epoch-based time module. - -A DateTime object should be considered immutable; all conversion and numeric -operations return a new DateTime object rather than modify the current object. - -A DateTime object always maintains its value as an absolute UTC time, -and is represented in the context of some timezone based on the -arguments used to create the object. A DateTime object's methods -return values based on the timezone context. - -Note that in all cases the local machine timezone is used for -representation if no timezone is specified. - -Constructor for DateTime ------------------------- - -DateTime() returns a new date-time object. DateTimes may be created -with from zero to seven arguments: - -* If the function is called with no arguments, then the current date/ - time is returned, represented in the timezone of the local machine. - -* If the function is invoked with a single string argument which is a - recognized timezone name, an object representing the current time is - returned, represented in the specified timezone. - -* If the function is invoked with a single string argument - representing a valid date/time, an object representing that date/ - time will be returned. - - As a general rule, any date-time representation that is recognized - and unambiguous to a resident of North America is acceptable. (The - reason for this qualification is that in North America, a date like: - 2/1/1994 is interpreted as February 1, 1994, while in some parts of - the world, it is interpreted as January 2, 1994.) A date/ time - string consists of two components, a date component and an optional - time component, separated by one or more spaces. If the time - component is omitted, 12:00am is assumed. - - Any recognized timezone name specified as the final element of the - date/time string will be used for computing the date/time value. - (If you create a DateTime with the string, - "Mar 9, 1997 1:45pm US/Pacific", the value will essentially be the - same as if you had captured time.time() at the specified date and - time on a machine in that timezone). If no timezone is passed, then - the timezone configured on the local machine will be used, **except** - that if the date format matches ISO 8601 ('YYYY-MM-DD'), the instance - will use UTC / GMT+0 as the timezone. - - o Returns current date/time, represented in US/Eastern: - - >>> from DateTime import DateTime - >>> e = DateTime('US/Eastern') - >>> e.timezone() - 'US/Eastern' - - o Returns specified time, represented in local machine zone: - - >>> x = DateTime('1997/3/9 1:45pm') - >>> x.parts() # doctest: +ELLIPSIS - (1997, 3, 9, 13, 45, ...) - - o Specified time in local machine zone, verbose format: - - >>> y = DateTime('Mar 9, 1997 13:45:00') - >>> y.parts() # doctest: +ELLIPSIS - (1997, 3, 9, 13, 45, ...) - >>> y == x - True - - o Specified time in UTC via ISO 8601 rule: - - >>> z = DateTime('2014-03-24') - >>> z.parts() # doctest: +ELLIPSIS - (2014, 3, 24, 0, 0, ...) - >>> z.timezone() - 'GMT+0' - - The date component consists of year, month, and day values. The - year value must be a one-, two-, or four-digit integer. If a one- - or two-digit year is used, the year is assumed to be in the - twentieth century. The month may an integer, from 1 to 12, a month - name, or a month abbreviation, where a period may optionally follow - the abbreviation. The day must be an integer from 1 to the number of - days in the month. The year, month, and day values may be separated - by periods, hyphens, forward slashes, or spaces. Extra spaces are - permitted around the delimiters. Year, month, and day values may be - given in any order as long as it is possible to distinguish the - components. If all three components are numbers that are less than - 13, then a month-day-year ordering is assumed. - - The time component consists of hour, minute, and second values - separated by colons. The hour value must be an integer between 0 - and 23 inclusively. The minute value must be an integer between 0 - and 59 inclusively. The second value may be an integer value - between 0 and 59.999 inclusively. The second value or both the - minute and second values may be omitted. The time may be followed - by am or pm in upper or lower case, in which case a 12-hour clock is - assumed. - -* If the DateTime function is invoked with a single numeric argument, - the number is assumed to be either a floating point value such as - that returned by time.time(), or a number of days after January 1, - 1901 00:00:00 UTC. - - A DateTime object is returned that represents either the GMT value - of the time.time() float represented in the local machine's - timezone, or that number of days after January 1, 1901. Note that - the number of days after 1901 need to be expressed from the - viewpoint of the local machine's timezone. A negative argument will - yield a date-time value before 1901. - -* If the function is invoked with two numeric arguments, then the - first is taken to be an integer year and the second argument is - taken to be an offset in days from the beginning of the year, in the - context of the local machine timezone. The date-time value returned - is the given offset number of days from the beginning of the given - year, represented in the timezone of the local machine. The offset - may be positive or negative. Two-digit years are assumed to be in - the twentieth century. - -* If the function is invoked with two arguments, the first a float - representing a number of seconds past the epoch in GMT (such as - those returned by time.time()) and the second a string naming a - recognized timezone, a DateTime with a value of that GMT time will - be returned, represented in the given timezone. - - >>> import time - >>> t = time.time() - - Time t represented as US/Eastern: - - >>> now_east = DateTime(t, 'US/Eastern') - - Time t represented as US/Pacific: - - >>> now_west = DateTime(t, 'US/Pacific') - - Only their representations are different: - - >>> now_east.equalTo(now_west) - True - -* If the function is invoked with three or more numeric arguments, - then the first is taken to be an integer year, the second is taken - to be an integer month, and the third is taken to be an integer day. - If the combination of values is not valid, then a DateTimeError is - raised. One- or two-digit years up to 69 are assumed to be in the - 21st century, whereas values 70-99 are assumed to be 20th century. - The fourth, fifth, and sixth arguments are floating point, positive - or negative offsets in units of hours, minutes, and days, and - default to zero if not given. An optional string may be given as - the final argument to indicate timezone (the effect of this is as if - you had taken the value of time.time() at that time on a machine in - the specified timezone). - -If a string argument passed to the DateTime constructor cannot be -parsed, it will raise SyntaxError. Invalid date, time, or -timezone components will raise a DateTimeError. - -The module function Timezones() will return a list of the timezones -recognized by the DateTime module. Recognition of timezone names is -case-insensitive. - -Instance Methods for DateTime (IDateTime interface) ---------------------------------------------------- - -Conversion and comparison methods -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -* ``timeTime()`` returns the date/time as a floating-point number in - UTC, in the format used by the Python time module. Note that it is - possible to create date /time values with DateTime that have no - meaningful value to the time module, and in such cases a - DateTimeError is raised. A DateTime object's value must generally - be between Jan 1, 1970 (or your local machine epoch) and Jan 2038 to - produce a valid time.time() style value. - - >>> dt = DateTime('Mar 9, 1997 13:45:00 US/Eastern') - >>> dt.timeTime() - 857933100.0 - - >>> DateTime('2040/01/01 UTC').timeTime() - 2208988800.0 - - >>> DateTime('1900/01/01 UTC').timeTime() - -2208988800.0 - -* ``toZone(z)`` returns a DateTime with the value as the current - object, represented in the indicated timezone: - - >>> dt.toZone('UTC') - DateTime('1997/03/09 18:45:00 UTC') - - >>> dt.toZone('UTC').equalTo(dt) - True - -* ``isFuture()`` returns true if this object represents a date/time - later than the time of the call: - - >>> dt.isFuture() - False - >>> DateTime('Jan 1 3000').isFuture() # not time-machine safe! - True - -* ``isPast()`` returns true if this object represents a date/time - earlier than the time of the call: - - >>> dt.isPast() - True - >>> DateTime('Jan 1 3000').isPast() # not time-machine safe! - False - -* ``isCurrentYear()`` returns true if this object represents a - date/time that falls within the current year, in the context of this - object's timezone representation: - - >>> dt.isCurrentYear() - False - >>> DateTime().isCurrentYear() - True - -* ``isCurrentMonth()`` returns true if this object represents a - date/time that falls within the current month, in the context of - this object's timezone representation: - - >>> dt.isCurrentMonth() - False - >>> DateTime().isCurrentMonth() - True - -* ``isCurrentDay()`` returns true if this object represents a - date/time that falls within the current day, in the context of this - object's timezone representation: - - >>> dt.isCurrentDay() - False - >>> DateTime().isCurrentDay() - True - -* ``isCurrentHour()`` returns true if this object represents a - date/time that falls within the current hour, in the context of this - object's timezone representation: - - >>> dt.isCurrentHour() - False - - >>> DateTime().isCurrentHour() - True - -* ``isCurrentMinute()`` returns true if this object represents a - date/time that falls within the current minute, in the context of - this object's timezone representation: - - >>> dt.isCurrentMinute() - False - >>> DateTime().isCurrentMinute() - True - -* ``isLeapYear()`` returns true if the current year (in the context of - the object's timezone) is a leap year: - - >>> dt.isLeapYear() - False - >>> DateTime('Mar 8 2004').isLeapYear() - True - -* ``earliestTime()`` returns a new DateTime object that represents the - earliest possible time (in whole seconds) that still falls within - the current object's day, in the object's timezone context: - - >>> dt.earliestTime() - DateTime('1997/03/09 00:00:00 US/Eastern') - -* ``latestTime()`` return a new DateTime object that represents the - latest possible time (in whole seconds) that still falls within the - current object's day, in the object's timezone context - - >>> dt.latestTime() - DateTime('1997/03/09 23:59:59 US/Eastern') - -Component access -~~~~~~~~~~~~~~~~ - -* ``parts()`` returns a tuple containing the calendar year, month, - day, hour, minute second and timezone of the object - - >>> dt.parts() # doctest: +ELLIPSIS - (1997, 3, 9, 13, 45, ... 'US/Eastern') - -* ``timezone()`` returns the timezone in which the object is represented: - - >>> dt.timezone() in Timezones() - True - -* ``tzoffset()`` returns the timezone offset for the objects timezone: - - >>> dt.tzoffset() - -18000 - -* ``year()`` returns the calendar year of the object: - - >>> dt.year() - 1997 - -* ``month()`` returns the month of the object as an integer: - - >>> dt.month() - 3 - -* ``Month()`` returns the full month name: - - >>> dt.Month() - 'March' - -* ``aMonth()`` returns the abbreviated month name: - - >>> dt.aMonth() - 'Mar' - -* ``pMonth()`` returns the abbreviated (with period) month name: - - >>> dt.pMonth() - 'Mar.' - -* ``day()`` returns the integer day: - - >>> dt.day() - 9 - -* ``Day()`` returns the full name of the day of the week: - - >>> dt.Day() - 'Sunday' - -* ``dayOfYear()`` returns the day of the year, in context of the - timezone representation of the object: - - >>> dt.dayOfYear() - 68 - -* ``aDay()`` returns the abbreviated name of the day of the week: - - >>> dt.aDay() - 'Sun' - -* ``pDay()`` returns the abbreviated (with period) name of the day of - the week: - - >>> dt.pDay() - 'Sun.' - -* ``dow()`` returns the integer day of the week, where Sunday is 0: - - >>> dt.dow() - 0 - -* ``dow_1()`` returns the integer day of the week, where sunday is 1: - - >>> dt.dow_1() - 1 - -* ``h_12()`` returns the 12-hour clock representation of the hour: - - >>> dt.h_12() - 1 - -* ``h_24()`` returns the 24-hour clock representation of the hour: - - >>> dt.h_24() - 13 - -* ``ampm()`` returns the appropriate time modifier (am or pm): - - >>> dt.ampm() - 'pm' - -* ``hour()`` returns the 24-hour clock representation of the hour: - - >>> dt.hour() - 13 - -* ``minute()`` returns the minute: - - >>> dt.minute() - 45 - -* ``second()`` returns the second: - - >>> dt.second() == 0 - True - -* ``millis()`` returns the milliseconds since the epoch in GMT. - - >>> dt.millis() == 857933100000 - True - -strftime() -~~~~~~~~~~ - -See ``tests/test_datetime.py``. - -General formats from previous DateTime -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -* ``Date()`` return the date string for the object: - - >>> dt.Date() - '1997/03/09' - -* ``Time()`` returns the time string for an object to the nearest - second: - - >>> dt.Time() - '13:45:00' - -* ``TimeMinutes()`` returns the time string for an object not showing - seconds: - - >>> dt.TimeMinutes() - '13:45' - -* ``AMPM()`` returns the time string for an object to the nearest second: - - >>> dt.AMPM() - '01:45:00 pm' - -* ``AMPMMinutes()`` returns the time string for an object not showing - seconds: - - >>> dt.AMPMMinutes() - '01:45 pm' - -* ``PreciseTime()`` returns the time string for the object: - - >>> dt.PreciseTime() - '13:45:00.000' - -* ``PreciseAMPM()`` returns the time string for the object: - - >>> dt.PreciseAMPM() - '01:45:00.000 pm' - -* ``yy()`` returns the calendar year as a 2 digit string - - >>> dt.yy() - '97' - -* ``mm()`` returns the month as a 2 digit string - - >>> dt.mm() - '03' - -* ``dd()`` returns the day as a 2 digit string: - - >>> dt.dd() - '09' - -* ``rfc822()`` returns the date in RFC 822 format: - - >>> dt.rfc822() - 'Sun, 09 Mar 1997 13:45:00 -0500' - -New formats -~~~~~~~~~~~ - -* ``fCommon()`` returns a string representing the object's value in - the format: March 9, 1997 1:45 pm: - - >>> dt.fCommon() - 'March 9, 1997 1:45 pm' - -* ``fCommonZ()`` returns a string representing the object's value in - the format: March 9, 1997 1:45 pm US/Eastern: - - >>> dt.fCommonZ() - 'March 9, 1997 1:45 pm US/Eastern' - -* ``aCommon()`` returns a string representing the object's value in - the format: Mar 9, 1997 1:45 pm: - - >>> dt.aCommon() - 'Mar 9, 1997 1:45 pm' - -* ``aCommonZ()`` return a string representing the object's value in - the format: Mar 9, 1997 1:45 pm US/Eastern: - - >>> dt.aCommonZ() - 'Mar 9, 1997 1:45 pm US/Eastern' - -* ``pCommon()`` returns a string representing the object's value in - the format Mar. 9, 1997 1:45 pm: - - >>> dt.pCommon() - 'Mar. 9, 1997 1:45 pm' - -* ``pCommonZ()`` returns a string representing the object's value in - the format: Mar. 9, 1997 1:45 pm US/Eastern: - - >>> dt.pCommonZ() - 'Mar. 9, 1997 1:45 pm US/Eastern' - -* ``ISO()`` returns a string with the date/time in ISO format. Note: - this is not ISO 8601-format! See the ISO8601 and HTML4 methods below - for ISO 8601-compliant output. Dates are output as: YYYY-MM-DD HH:MM:SS - - >>> dt.ISO() - '1997-03-09 13:45:00' - -* ``ISO8601()`` returns the object in ISO 8601-compatible format - containing the date, time with seconds-precision and the time zone - identifier - see http://www.w3.org/TR/NOTE-datetime. Dates are - output as: YYYY-MM-DDTHH:MM:SSTZD (T is a literal character, TZD is - Time Zone Designator, format +HH:MM or -HH:MM). - - The ``HTML4()`` method below offers the same formatting, but - converts to UTC before returning the value and sets the TZD"Z" - - >>> dt.ISO8601() - '1997-03-09T13:45:00-05:00' - - -* ``HTML4()`` returns the object in the format used in the HTML4.0 - specification, one of the standard forms in ISO8601. See - http://www.w3.org/TR/NOTE-datetime. Dates are output as: - YYYY-MM-DDTHH:MM:SSZ (T, Z are literal characters, the time is in - UTC.): - - >>> dt.HTML4() - '1997-03-09T18:45:00Z' - -* ``JulianDay()`` returns the Julian day according to - http://www.tondering.dk/claus/cal/node3.html#sec-calcjd - - >>> dt.JulianDay() - 2450517 - -* ``week()`` returns the week number according to ISO - see http://www.tondering.dk/claus/cal/node6.html#SECTION00670000000000000000 - - >>> dt.week() - 10 - -Deprecated API -~~~~~~~~~~~~~~ - -* DayOfWeek(): see Day() - -* Day_(): see pDay() - -* Mon(): see aMonth() - -* Mon_(): see pMonth - -General Services Provided by DateTime -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -DateTimes can be repr()'ed; the result will be a string indicating how -to make a DateTime object like this: - - >>> repr(dt) - "DateTime('1997/03/09 13:45:00 US/Eastern')" - -When we convert them into a string, we get a nicer string that could -actually be shown to a user: - - >>> str(dt) - '1997/03/09 13:45:00 US/Eastern' - -The hash value of a DateTime is based on the date and time and is -equal for different representations of the DateTime: - - >>> hash(dt) - 3618678 - >>> hash(dt.toZone('UTC')) - 3618678 - -DateTime objects can be compared to other DateTime objects OR floating -point numbers such as the ones which are returned by the Python time -module by using the equalTo method. Using this API, True is returned if the -object represents a date/time equal to the specified DateTime or time module -style time: - - >>> dt.equalTo(dt) - True - >>> dt.equalTo(dt.toZone('UTC')) - True - >>> dt.equalTo(dt.timeTime()) - True - >>> dt.equalTo(DateTime()) - False - -Same goes for inequalities: - - >>> dt.notEqualTo(dt) - False - >>> dt.notEqualTo(dt.toZone('UTC')) - False - >>> dt.notEqualTo(dt.timeTime()) - False - >>> dt.notEqualTo(DateTime()) - True - -Normal equality operations only work with DateTime objects and take the -timezone setting into account: - - >>> dt == dt - True - >>> dt == dt.toZone('UTC') - False - >>> dt == DateTime() - False - - >>> dt != dt - False - >>> dt != dt.toZone('UTC') - True - >>> dt != DateTime() - True - -But the other comparison operations compare the referenced moment in time and -not the representation itself: - - >>> dt > dt - False - >>> DateTime() > dt - True - >>> dt > DateTime().timeTime() - False - >>> DateTime().timeTime() > dt - True - - >>> dt.greaterThan(dt) - False - >>> DateTime().greaterThan(dt) - True - >>> dt.greaterThan(DateTime().timeTime()) - False - - >>> dt >= dt - True - >>> DateTime() >= dt - True - >>> dt >= DateTime().timeTime() - False - >>> DateTime().timeTime() >= dt - True - - >>> dt.greaterThanEqualTo(dt) - True - >>> DateTime().greaterThanEqualTo(dt) - True - >>> dt.greaterThanEqualTo(DateTime().timeTime()) - False - - >>> dt < dt - False - >>> DateTime() < dt - False - >>> dt < DateTime().timeTime() - True - >>> DateTime().timeTime() < dt - False - - >>> dt.lessThan(dt) - False - >>> DateTime().lessThan(dt) - False - >>> dt.lessThan(DateTime().timeTime()) - True - - >>> dt <= dt - True - >>> DateTime() <= dt - False - >>> dt <= DateTime().timeTime() - True - >>> DateTime().timeTime() <= dt - False - - >>> dt.lessThanEqualTo(dt) - True - >>> DateTime().lessThanEqualTo(dt) - False - >>> dt.lessThanEqualTo(DateTime().timeTime()) - True - -Numeric Services Provided by DateTime -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -A DateTime may be added to a number and a number may be added to a -DateTime: - - >>> dt + 5 - DateTime('1997/03/14 13:45:00 US/Eastern') - >>> 5 + dt - DateTime('1997/03/14 13:45:00 US/Eastern') - -Two DateTimes cannot be added: - - >>> from DateTime.interfaces import DateTimeError - >>> try: - ... dt + dt - ... print('fail') - ... except DateTimeError: - ... print('ok') - ok - -Either a DateTime or a number may be subtracted from a DateTime, -however, a DateTime may not be subtracted from a number: - - >>> DateTime('1997/03/10 13:45 US/Eastern') - dt - 1.0 - >>> dt - 1 - DateTime('1997/03/08 13:45:00 US/Eastern') - >>> 1 - dt - Traceback (most recent call last): - ... - TypeError: unsupported operand type(s) for -: 'int' and 'DateTime' - -DateTimes can also be converted to integers (number of seconds since -the epoch) and floats: - - >>> int(dt) - 857933100 - >>> float(dt) - 857933100.0 diff --git a/llmlab/lib/python3.12/site-packages/DateTime/__init__.py b/llmlab/lib/python3.12/site-packages/DateTime/__init__.py deleted file mode 100644 index 4e2df6d..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/__init__.py +++ /dev/null @@ -1,18 +0,0 @@ -############################################################################## -# -# Copyright (c) 2002 Zope Foundation and Contributors. -# -# This software is subject to the provisions of the Zope Public License, -# Version 2.1 (ZPL). A copy of the ZPL should accompany this distribution. -# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED -# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS -# FOR A PARTICULAR PURPOSE -# -############################################################################## - -from .DateTime import DateTime -from .DateTime import Timezones - - -__all__ = ('DateTime', 'Timezones') diff --git a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/DateTime.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/DateTime.cpython-312.pyc deleted file mode 100644 index 7a38166..0000000 Binary files a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/DateTime.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 5ead2c5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/interfaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/interfaces.cpython-312.pyc deleted file mode 100644 index ae4ccd4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/interfaces.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/pytz_support.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/pytz_support.cpython-312.pyc deleted file mode 100644 index 266111b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/DateTime/__pycache__/pytz_support.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/DateTime/interfaces.py b/llmlab/lib/python3.12/site-packages/DateTime/interfaces.py deleted file mode 100644 index 80e7707..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/interfaces.py +++ /dev/null @@ -1,375 +0,0 @@ -############################################################################## -# -# Copyright (c) 2005 Zope Foundation and Contributors. -# -# This software is subject to the provisions of the Zope Public License, -# Version 2.1 (ZPL). A copy of the ZPL should accompany this distribution. -# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED -# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS -# FOR A PARTICULAR PURPOSE -# -############################################################################## -from zope.interface import Interface - - -class DateTimeError(Exception): - pass - - -class SyntaxError(DateTimeError): - pass - - -class DateError(DateTimeError): - pass - - -class TimeError(DateTimeError): - pass - - -class IDateTime(Interface): - # Conversion and comparison methods - - def localZone(ltm=None): - """Returns the time zone on the given date. The time zone - can change according to daylight savings.""" - - def timeTime(): - """Return the date/time as a floating-point number in UTC, in - the format used by the Python time module. Note that it is - possible to create date/time values with DateTime that have no - meaningful value to the time module.""" - - def toZone(z): - """Return a DateTime with the value as the current object, - represented in the indicated timezone.""" - - def isFuture(): - """Return true if this object represents a date/time later - than the time of the call""" - - def isPast(): - """Return true if this object represents a date/time earlier - than the time of the call""" - - def isCurrentYear(): - """Return true if this object represents a date/time that - falls within the current year, in the context of this - object's timezone representation""" - - def isCurrentMonth(): - """Return true if this object represents a date/time that - falls within the current month, in the context of this - object's timezone representation""" - - def isCurrentDay(): - """Return true if this object represents a date/time that - falls within the current day, in the context of this object's - timezone representation""" - - def isCurrentHour(): - """Return true if this object represents a date/time that - falls within the current hour, in the context of this object's - timezone representation""" - - def isCurrentMinute(): - """Return true if this object represents a date/time that - falls within the current minute, in the context of this - object's timezone representation""" - - def isLeapYear(): - """Return true if the current year (in the context of the - object's timezone) is a leap year""" - - def earliestTime(): - """Return a new DateTime object that represents the earliest - possible time (in whole seconds) that still falls within the - current object's day, in the object's timezone context""" - - def latestTime(): - """Return a new DateTime object that represents the latest - possible time (in whole seconds) that still falls within the - current object's day, in the object's timezone context""" - - def greaterThan(t): - """Compare this DateTime object to another DateTime object OR - a floating point number such as that which is returned by the - Python time module. Returns true if the object represents a - date/time greater than the specified DateTime or time module - style time. Revised to give more correct results through - comparison of long integer milliseconds.""" - - __gt__ = greaterThan - - def greaterThanEqualTo(t): - """Compare this DateTime object to another DateTime object OR - a floating point number such as that which is returned by the - Python time module. Returns true if the object represents a - date/time greater than or equal to the specified DateTime or - time module style time. Revised to give more correct results - through comparison of long integer milliseconds.""" - - __ge__ = greaterThanEqualTo - - def equalTo(t): - """Compare this DateTime object to another DateTime object OR - a floating point number such as that which is returned by the - Python time module. Returns true if the object represents a - date/time equal to the specified DateTime or time module style - time. Revised to give more correct results through comparison - of long integer milliseconds.""" - - __eq__ = equalTo - - def notEqualTo(t): - """Compare this DateTime object to another DateTime object OR - a floating point number such as that which is returned by the - Python time module. Returns true if the object represents a - date/time not equal to the specified DateTime or time module - style time. Revised to give more correct results through - comparison of long integer milliseconds.""" - - __ne__ = notEqualTo - - def lessThan(t): - """Compare this DateTime object to another DateTime object OR - a floating point number such as that which is returned by the - Python time module. Returns true if the object represents a - date/time less than the specified DateTime or time module - style time. Revised to give more correct results through - comparison of long integer milliseconds.""" - - __lt__ = lessThan - - def lessThanEqualTo(t): - """Compare this DateTime object to another DateTime object OR - a floating point number such as that which is returned by the - Python time module. Returns true if the object represents a - date/time less than or equal to the specified DateTime or time - module style time. Revised to give more correct results - through comparison of long integer milliseconds.""" - - __le__ = lessThanEqualTo - - # Component access - - def parts(): - """Return a tuple containing the calendar year, month, day, - hour, minute second and timezone of the object""" - - def timezone(): - """Return the timezone in which the object is represented.""" - - def tzoffset(): - """Return the timezone offset for the objects timezone.""" - - def year(): - """Return the calendar year of the object""" - - def month(): - """Return the month of the object as an integer""" - - def Month(): - """Return the full month name""" - - def aMonth(): - """Return the abbreviated month name.""" - - def Mon(): - """Compatibility: see aMonth""" - - def pMonth(): - """Return the abbreviated (with period) month name.""" - - def Mon_(): - """Compatibility: see pMonth""" - - def day(): - """Return the integer day""" - - def Day(): - """Return the full name of the day of the week""" - - def DayOfWeek(): - """Compatibility: see Day""" - - def dayOfYear(): - """Return the day of the year, in context of the timezone - representation of the object""" - - def aDay(): - """Return the abbreviated name of the day of the week""" - - def pDay(): - """Return the abbreviated (with period) name of the day of the - week""" - - def Day_(): - """Compatibility: see pDay""" - - def dow(): - """Return the integer day of the week, where sunday is 0""" - - def dow_1(): - """Return the integer day of the week, where sunday is 1""" - - def h_12(): - """Return the 12-hour clock representation of the hour""" - - def h_24(): - """Return the 24-hour clock representation of the hour""" - - def ampm(): - """Return the appropriate time modifier (am or pm)""" - - def hour(): - """Return the 24-hour clock representation of the hour""" - - def minute(): - """Return the minute""" - - def second(): - """Return the second""" - - def millis(): - """Return the millisecond since the epoch in GMT.""" - - def strftime(format): - """Format the date/time using the *current timezone representation*.""" - - # General formats from previous DateTime - - def Date(): - """Return the date string for the object.""" - - def Time(): - """Return the time string for an object to the nearest second.""" - - def TimeMinutes(): - """Return the time string for an object not showing seconds.""" - - def AMPM(): - """Return the time string for an object to the nearest second.""" - - def AMPMMinutes(): - """Return the time string for an object not showing seconds.""" - - def PreciseTime(): - """Return the time string for the object.""" - - def PreciseAMPM(): - """Return the time string for the object.""" - - def yy(): - """Return calendar year as a 2 digit string""" - - def mm(): - """Return month as a 2 digit string""" - - def dd(): - """Return day as a 2 digit string""" - - def rfc822(): - """Return the date in RFC 822 format""" - - # New formats - - def fCommon(): - """Return a string representing the object's value in the - format: March 1, 1997 1:45 pm""" - - def fCommonZ(): - """Return a string representing the object's value in the - format: March 1, 1997 1:45 pm US/Eastern""" - - def aCommon(): - """Return a string representing the object's value in the - format: Mar 1, 1997 1:45 pm""" - - def aCommonZ(): - """Return a string representing the object's value in the - format: Mar 1, 1997 1:45 pm US/Eastern""" - - def pCommon(): - """Return a string representing the object's value in the - format: Mar. 1, 1997 1:45 pm""" - - def pCommonZ(): - """Return a string representing the object's value - in the format: Mar. 1, 1997 1:45 pm US/Eastern""" - - def ISO(): - """Return the object in ISO standard format. Note: this is - *not* ISO 8601-format! See the ISO8601 and HTML4 methods below - for ISO 8601-compliant output - - Dates are output as: YYYY-MM-DD HH:MM:SS - """ - - def ISO8601(): - """Return the object in ISO 8601-compatible format containing - the date, time with seconds-precision and the time zone - identifier - see http://www.w3.org/TR/NOTE-datetime - - Dates are output as: YYYY-MM-DDTHH:MM:SSTZD - T is a literal character. - TZD is Time Zone Designator, format +HH:MM or -HH:MM - - The HTML4 method below offers the same formatting, but - converts to UTC before returning the value and sets the TZD"Z" - """ - - def HTML4(): - """Return the object in the format used in the HTML4.0 - specification, one of the standard forms in ISO8601. See - http://www.w3.org/TR/NOTE-datetime - - Dates are output as: YYYY-MM-DDTHH:MM:SSZ - T, Z are literal characters. - The time is in UTC. - """ - - def JulianDay(): - """Return the Julian day according to - https://www.tondering.dk/claus/cal/julperiod.php#formula - """ - - def week(): - """Return the week number according to ISO. - - See https://www.tondering.dk/claus/cal/week.php#weekno - """ - - # Python operator and conversion API - - def __add__(other): - """A DateTime may be added to a number and a number may be - added to a DateTime; two DateTimes cannot be added.""" - - __radd__ = __add__ - - def __sub__(other): - """Either a DateTime or a number may be subtracted from a - DateTime, however, a DateTime may not be subtracted from a - number.""" - - def __repr__(): - """Convert a DateTime to a string that looks like a Python - expression.""" - - def __str__(): - """Convert a DateTime to a string.""" - - def __hash__(): - """Compute a hash value for a DateTime""" - - def __int__(): - """Convert to an integer number of seconds since the epoch (gmt)""" - - def __long__(): - """Convert to a long-int number of seconds since the epoch (gmt)""" - - def __float__(): - """Convert to floating-point number of seconds since the epoch (gmt)""" diff --git a/llmlab/lib/python3.12/site-packages/DateTime/pytz.txt b/llmlab/lib/python3.12/site-packages/DateTime/pytz.txt deleted file mode 100644 index 3a87338..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/pytz.txt +++ /dev/null @@ -1,192 +0,0 @@ -Pytz Support -============ - -Allows the pytz package to be used for time zone information. The -advantage of using pytz is that it has a more complete and up to date -time zone and daylight savings time database. - -Usage ------ -You don't have to do anything special to make it work. - - >>> from DateTime import DateTime, Timezones - >>> d = DateTime('March 11, 2007 US/Eastern') - -Daylight Savings ----------------- -In 2007 daylight savings time in the US was changed. The Energy Policy -Act of 2005 mandates that DST will start on the second Sunday in March -and end on the first Sunday in November. - -In 2007, the start and stop dates are March 11 and November 4, -respectively. These dates are different from previous DST start and -stop dates. In 2006, the dates were the first Sunday in April (April -2, 2006) and the last Sunday in October (October 29, 2006). - -Let's make sure that DateTime can deal with this, since the primary -motivation to use pytz for time zone information is the fact that it -is kept up to date with daylight savings changes. - - >>> DateTime('March 11, 2007 US/Eastern').tzoffset() - -18000 - >>> DateTime('March 12, 2007 US/Eastern').tzoffset() - -14400 - >>> DateTime('November 4, 2007 US/Eastern').tzoffset() - -14400 - >>> DateTime('November 5, 2007 US/Eastern').tzoffset() - -18000 - -Let's compare this to 2006. - - >>> DateTime('April 2, 2006 US/Eastern').tzoffset() - -18000 - >>> DateTime('April 3, 2006 US/Eastern').tzoffset() - -14400 - >>> DateTime('October 29, 2006 US/Eastern').tzoffset() - -14400 - >>> DateTime('October 30, 2006 US/Eastern').tzoffset() - -18000 - -Time Zones ---------- -DateTime can use pytz's large database of time zones. Here are some -examples: - - >>> d = DateTime('Pacific/Kwajalein') - >>> d = DateTime('America/Shiprock') - >>> d = DateTime('Africa/Ouagadougou') - -Of course pytz doesn't know about everything. - - >>> from DateTime.interfaces import SyntaxError - >>> try: - ... d = DateTime('July 21, 1969 Moon/Eastern') - ... print('fail') - ... except SyntaxError: - ... print('ok') - ok - -You can still use zone names that DateTime defines that aren't part of -the pytz database. - - >>> d = DateTime('eet') - >>> d = DateTime('iceland') - -These time zones use DateTimes database. So it's preferable to use the -official time zone name. - -One trickiness is that DateTime supports some zone name -abbreviations. Some of these map to pytz names, so these abbreviations -will give you time zone date from pytz. Notable among abbreviations -that work this way are 'est', 'cst', 'mst', and 'pst'. - -Let's verify that 'est' picks up the 2007 daylight savings time changes. - - >>> DateTime('March 11, 2007 est').tzoffset() - -18000 - >>> DateTime('March 12, 2007 est').tzoffset() - -14400 - >>> DateTime('November 4, 2007 est').tzoffset() - -14400 - >>> DateTime('November 5, 2007 est').tzoffset() - -18000 - -You can get a list of time zones supported by calling the Timezones() function. - - >>> Timezones() #doctest: +ELLIPSIS - ['Africa/Abidjan', 'Africa/Accra', 'Africa/Addis_Ababa', ...] - -Note that you can mess with this list without hurting things. - - >>> t = Timezones() - >>> t.remove('US/Eastern') - >>> d = DateTime('US/Eastern') - - -Internal Components -------------------- - -The following are tests of internal components. - -Cache -~~~~~ - -The DateTime class uses a new time zone cache. - - >>> from DateTime.DateTime import _TZINFO - >>> _TZINFO #doctest: +ELLIPSIS - - -The cache maps time zone names to time zone instances. - - >>> cache = _TZINFO - >>> tz = cache['GMT+730'] - >>> tz = cache['US/Mountain'] - -The cache also must provide a few attributes for use by the DateTime -class. - -The _zlst attribute is a list of supported time zone names. - - >>> cache._zlst #doctest: +ELLIPSIS - ['Africa/Abidjan'... 'Africa/Accra'... 'IDLE'... 'NZST'... 'NZT'...] - -The _zidx attribute is a list of lower-case and possibly abbreviated -time zone names that can be mapped to official zone names. - - >>> 'australia/yancowinna' in cache._zidx - True - >>> 'europe/isle_of_man' in cache._zidx - True - >>> 'gmt+0500' in cache._zidx - True - -Note that there are more items in _zidx than in _zlst since there are -multiple names for some time zones. - - >>> len(cache._zidx) > len(cache._zlst) - True - -Each entry in _zlst should also be present in _zidx in lower case form. - - >>> for name in cache._zlst: - ... if not name.lower() in cache._zidx: - ... print("Error %s not in _zidx" % name.lower()) - -The _zmap attribute maps the names in _zidx to official names in _zlst. - - >>> cache._zmap['africa/abidjan'] - 'Africa/Abidjan' - >>> cache._zmap['gmt+1'] - 'GMT+1' - >>> cache._zmap['gmt+0100'] - 'GMT+1' - >>> cache._zmap['utc'] - 'UTC' - -Let's make sure that _zmap and _zidx agree. - - >>> idx = set(cache._zidx) - >>> keys = set(cache._zmap.keys()) - >>> idx == keys - True - -Timezone objects -~~~~~~~~~~~~~~~~ -The timezone instances have only one public method info(). It returns -a tuple of (offset, is_dst, name). The method takes a timestamp, which -is used to determine dst information. - - >>> t1 = DateTime('November 4, 00:00 2007 US/Mountain').timeTime() - >>> t2 = DateTime('November 4, 02:00 2007 US/Mountain').timeTime() - >>> tz.info(t1) - (-21600, 1, 'MDT') - >>> tz.info(t2) - (-25200, 0, 'MST') - -If you don't pass any arguments to info it provides daylight savings -time information as of today. - - >>> tz.info() in ((-21600, 1, 'MDT'), (-25200, 0, 'MST')) - True - diff --git a/llmlab/lib/python3.12/site-packages/DateTime/pytz_support.py b/llmlab/lib/python3.12/site-packages/DateTime/pytz_support.py deleted file mode 100644 index 4acf324..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/pytz_support.py +++ /dev/null @@ -1,269 +0,0 @@ -############################################################################## -# -# Copyright (c) 2007 Zope Foundation and Contributors. -# -# This software is subject to the provisions of the Zope Public License, -# Version 2.1 (ZPL). A copy of the ZPL should accompany this distribution. -# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED -# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS -# FOR A PARTICULAR PURPOSE -# -############################################################################## - -from datetime import datetime -from datetime import timedelta - -import pytz -import pytz.reference -from pytz.tzinfo import StaticTzInfo -from pytz.tzinfo import memorized_timedelta - -from .interfaces import DateTimeError - - -EPOCH = datetime.fromtimestamp(0, tz=pytz.utc) - -_numeric_timezone_data = { - 'GMT': ('GMT', 0, 1, [], '', [(0, 0, 0)], 'GMT\000'), - 'GMT+0': ('GMT+0', 0, 1, [], '', [(0, 0, 0)], 'GMT+0000\000'), - 'GMT+1': ('GMT+1', 0, 1, [], '', [(3600, 0, 0)], 'GMT+0100\000'), - 'GMT+2': ('GMT+2', 0, 1, [], '', [(7200, 0, 0)], 'GMT+0200\000'), - 'GMT+3': ('GMT+3', 0, 1, [], '', [(10800, 0, 0)], 'GMT+0300\000'), - 'GMT+4': ('GMT+4', 0, 1, [], '', [(14400, 0, 0)], 'GMT+0400\000'), - 'GMT+5': ('GMT+5', 0, 1, [], '', [(18000, 0, 0)], 'GMT+0500\000'), - 'GMT+6': ('GMT+6', 0, 1, [], '', [(21600, 0, 0)], 'GMT+0600\000'), - 'GMT+7': ('GMT+7', 0, 1, [], '', [(25200, 0, 0)], 'GMT+0700\000'), - 'GMT+8': ('GMT+8', 0, 1, [], '', [(28800, 0, 0)], 'GMT+0800\000'), - 'GMT+9': ('GMT+9', 0, 1, [], '', [(32400, 0, 0)], 'GMT+0900\000'), - 'GMT+10': ('GMT+10', 0, 1, [], '', [(36000, 0, 0)], 'GMT+1000\000'), - 'GMT+11': ('GMT+11', 0, 1, [], '', [(39600, 0, 0)], 'GMT+1100\000'), - 'GMT+12': ('GMT+12', 0, 1, [], '', [(43200, 0, 0)], 'GMT+1200\000'), - 'GMT+13': ('GMT+13', 0, 1, [], '', [(46800, 0, 0)], 'GMT+1300\000'), - - 'GMT-1': ('GMT-1', 0, 1, [], '', [(-3600, 0, 0)], 'GMT-0100\000'), - 'GMT-2': ('GMT-2', 0, 1, [], '', [(-7200, 0, 0)], 'GMT-0200\000'), - 'GMT-3': ('GMT-3', 0, 1, [], '', [(-10800, 0, 0)], 'GMT-0300\000'), - 'GMT-4': ('GMT-4', 0, 1, [], '', [(-14400, 0, 0)], 'GMT-0400\000'), - 'GMT-5': ('GMT-5', 0, 1, [], '', [(-18000, 0, 0)], 'GMT-0500\000'), - 'GMT-6': ('GMT-6', 0, 1, [], '', [(-21600, 0, 0)], 'GMT-0600\000'), - 'GMT-7': ('GMT-7', 0, 1, [], '', [(-25200, 0, 0)], 'GMT-0700\000'), - 'GMT-8': ('GMT-8', 0, 1, [], '', [(-28800, 0, 0)], 'GMT-0800\000'), - 'GMT-9': ('GMT-9', 0, 1, [], '', [(-32400, 0, 0)], 'GMT-0900\000'), - 'GMT-10': ('GMT-10', 0, 1, [], '', [(-36000, 0, 0)], 'GMT-1000\000'), - 'GMT-11': ('GMT-11', 0, 1, [], '', [(-39600, 0, 0)], 'GMT-1100\000'), - 'GMT-12': ('GMT-12', 0, 1, [], '', [(-43200, 0, 0)], 'GMT-1200\000'), - - 'GMT+0130': ('GMT+0130', 0, 1, [], '', [(5400, 0, 0)], 'GMT+0130\000'), - 'GMT+0230': ('GMT+0230', 0, 1, [], '', [(9000, 0, 0)], 'GMT+0230\000'), - 'GMT+0330': ('GMT+0330', 0, 1, [], '', [(12600, 0, 0)], 'GMT+0330\000'), - 'GMT+0430': ('GMT+0430', 0, 1, [], '', [(16200, 0, 0)], 'GMT+0430\000'), - 'GMT+0530': ('GMT+0530', 0, 1, [], '', [(19800, 0, 0)], 'GMT+0530\000'), - 'GMT+0630': ('GMT+0630', 0, 1, [], '', [(23400, 0, 0)], 'GMT+0630\000'), - 'GMT+0730': ('GMT+0730', 0, 1, [], '', [(27000, 0, 0)], 'GMT+0730\000'), - 'GMT+0830': ('GMT+0830', 0, 1, [], '', [(30600, 0, 0)], 'GMT+0830\000'), - 'GMT+0930': ('GMT+0930', 0, 1, [], '', [(34200, 0, 0)], 'GMT+0930\000'), - 'GMT+1030': ('GMT+1030', 0, 1, [], '', [(37800, 0, 0)], 'GMT+1030\000'), - 'GMT+1130': ('GMT+1130', 0, 1, [], '', [(41400, 0, 0)], 'GMT+1130\000'), - 'GMT+1230': ('GMT+1230', 0, 1, [], '', [(45000, 0, 0)], 'GMT+1230\000'), - - 'GMT-0130': ('GMT-0130', 0, 1, [], '', [(-5400, 0, 0)], 'GMT-0130\000'), - 'GMT-0230': ('GMT-0230', 0, 1, [], '', [(-9000, 0, 0)], 'GMT-0230\000'), - 'GMT-0330': ('GMT-0330', 0, 1, [], '', [(-12600, 0, 0)], 'GMT-0330\000'), - 'GMT-0430': ('GMT-0430', 0, 1, [], '', [(-16200, 0, 0)], 'GMT-0430\000'), - 'GMT-0530': ('GMT-0530', 0, 1, [], '', [(-19800, 0, 0)], 'GMT-0530\000'), - 'GMT-0630': ('GMT-0630', 0, 1, [], '', [(-23400, 0, 0)], 'GMT-0630\000'), - 'GMT-0730': ('GMT-0730', 0, 1, [], '', [(-27000, 0, 0)], 'GMT-0730\000'), - 'GMT-0830': ('GMT-0830', 0, 1, [], '', [(-30600, 0, 0)], 'GMT-0830\000'), - 'GMT-0930': ('GMT-0930', 0, 1, [], '', [(-34200, 0, 0)], 'GMT-0930\000'), - 'GMT-1030': ('GMT-1030', 0, 1, [], '', [(-37800, 0, 0)], 'GMT-1030\000'), - 'GMT-1130': ('GMT-1130', 0, 1, [], '', [(-41400, 0, 0)], 'GMT-1130\000'), - 'GMT-1230': ('GMT-1230', 0, 1, [], '', [(-45000, 0, 0)], 'GMT-1230\000'), -} - -# These are the timezones not in pytz.common_timezones -_old_zlst = [ - 'AST', 'AT', 'BST', 'BT', 'CCT', - 'CET', 'CST', 'Cuba', 'EADT', 'EAST', - 'EEST', 'EET', 'EST', 'Egypt', 'FST', - 'FWT', 'GB-Eire', 'GMT+0100', 'GMT+0130', 'GMT+0200', - 'GMT+0230', 'GMT+0300', 'GMT+0330', 'GMT+0400', 'GMT+0430', - 'GMT+0500', 'GMT+0530', 'GMT+0600', 'GMT+0630', 'GMT+0700', - 'GMT+0730', 'GMT+0800', 'GMT+0830', 'GMT+0900', 'GMT+0930', - 'GMT+1', 'GMT+1000', 'GMT+1030', 'GMT+1100', 'GMT+1130', - 'GMT+1200', 'GMT+1230', 'GMT+1300', 'GMT-0100', 'GMT-0130', - 'GMT-0200', 'GMT-0300', 'GMT-0400', 'GMT-0500', 'GMT-0600', - 'GMT-0630', 'GMT-0700', 'GMT-0730', 'GMT-0800', 'GMT-0830', - 'GMT-0900', 'GMT-0930', 'GMT-1000', 'GMT-1030', 'GMT-1100', - 'GMT-1130', 'GMT-1200', 'GMT-1230', 'GST', 'Greenwich', - 'Hongkong', 'IDLE', 'IDLW', 'Iceland', 'Iran', - 'Israel', 'JST', 'Jamaica', 'Japan', 'MEST', - 'MET', 'MEWT', 'MST', 'NT', 'NZDT', - 'NZST', 'NZT', 'PST', 'Poland', 'SST', - 'SWT', 'Singapore', 'Turkey', 'UCT', 'UT', - 'Universal', 'WADT', 'WAST', 'WAT', 'WET', - 'ZP4', 'ZP5', 'ZP6', -] - -_old_zmap = { - 'aest': 'GMT+10', 'aedt': 'GMT+11', - 'aus eastern standard time': 'GMT+10', - 'sydney standard time': 'GMT+10', - 'tasmania standard time': 'GMT+10', - 'e. australia standard time': 'GMT+10', - 'aus central standard time': 'GMT+0930', - 'cen. australia standard time': 'GMT+0930', - 'w. australia standard time': 'GMT+8', - - 'central europe standard time': 'GMT+1', - 'eastern standard time': 'US/Eastern', - 'us eastern standard time': 'US/Eastern', - 'central standard time': 'US/Central', - 'mountain standard time': 'US/Mountain', - 'pacific standard time': 'US/Pacific', - 'mst': 'US/Mountain', 'pst': 'US/Pacific', - 'cst': 'US/Central', 'est': 'US/Eastern', - - 'gmt+0000': 'GMT+0', 'gmt+0': 'GMT+0', - - 'gmt+0100': 'GMT+1', 'gmt+0200': 'GMT+2', 'gmt+0300': 'GMT+3', - 'gmt+0400': 'GMT+4', 'gmt+0500': 'GMT+5', 'gmt+0600': 'GMT+6', - 'gmt+0700': 'GMT+7', 'gmt+0800': 'GMT+8', 'gmt+0900': 'GMT+9', - 'gmt+1000': 'GMT+10', 'gmt+1100': 'GMT+11', 'gmt+1200': 'GMT+12', - 'gmt+1300': 'GMT+13', - 'gmt-0100': 'GMT-1', 'gmt-0200': 'GMT-2', 'gmt-0300': 'GMT-3', - 'gmt-0400': 'GMT-4', 'gmt-0500': 'GMT-5', 'gmt-0600': 'GMT-6', - 'gmt-0700': 'GMT-7', 'gmt-0800': 'GMT-8', 'gmt-0900': 'GMT-9', - 'gmt-1000': 'GMT-10', 'gmt-1100': 'GMT-11', 'gmt-1200': 'GMT-12', - - 'gmt+1': 'GMT+1', 'gmt+2': 'GMT+2', 'gmt+3': 'GMT+3', - 'gmt+4': 'GMT+4', 'gmt+5': 'GMT+5', 'gmt+6': 'GMT+6', - 'gmt+7': 'GMT+7', 'gmt+8': 'GMT+8', 'gmt+9': 'GMT+9', - 'gmt+10': 'GMT+10', 'gmt+11': 'GMT+11', 'gmt+12': 'GMT+12', - 'gmt+13': 'GMT+13', - 'gmt-1': 'GMT-1', 'gmt-2': 'GMT-2', 'gmt-3': 'GMT-3', - 'gmt-4': 'GMT-4', 'gmt-5': 'GMT-5', 'gmt-6': 'GMT-6', - 'gmt-7': 'GMT-7', 'gmt-8': 'GMT-8', 'gmt-9': 'GMT-9', - 'gmt-10': 'GMT-10', 'gmt-11': 'GMT-11', 'gmt-12': 'GMT-12', - - 'gmt+130': 'GMT+0130', 'gmt+0130': 'GMT+0130', - 'gmt+230': 'GMT+0230', 'gmt+0230': 'GMT+0230', - 'gmt+330': 'GMT+0330', 'gmt+0330': 'GMT+0330', - 'gmt+430': 'GMT+0430', 'gmt+0430': 'GMT+0430', - 'gmt+530': 'GMT+0530', 'gmt+0530': 'GMT+0530', - 'gmt+630': 'GMT+0630', 'gmt+0630': 'GMT+0630', - 'gmt+730': 'GMT+0730', 'gmt+0730': 'GMT+0730', - 'gmt+830': 'GMT+0830', 'gmt+0830': 'GMT+0830', - 'gmt+930': 'GMT+0930', 'gmt+0930': 'GMT+0930', - 'gmt+1030': 'GMT+1030', - 'gmt+1130': 'GMT+1130', - 'gmt+1230': 'GMT+1230', - - 'gmt-130': 'GMT-0130', 'gmt-0130': 'GMT-0130', - 'gmt-230': 'GMT-0230', 'gmt-0230': 'GMT-0230', - 'gmt-330': 'GMT-0330', 'gmt-0330': 'GMT-0330', - 'gmt-430': 'GMT-0430', 'gmt-0430': 'GMT-0430', - 'gmt-530': 'GMT-0530', 'gmt-0530': 'GMT-0530', - 'gmt-630': 'GMT-0630', 'gmt-0630': 'GMT-0630', - 'gmt-730': 'GMT-0730', 'gmt-0730': 'GMT-0730', - 'gmt-830': 'GMT-0830', 'gmt-0830': 'GMT-0830', - 'gmt-930': 'GMT-0930', 'gmt-0930': 'GMT-0930', - 'gmt-1030': 'GMT-1030', - 'gmt-1130': 'GMT-1130', - 'gmt-1230': 'GMT-1230', - - 'ut': 'Universal', - 'bst': 'GMT+1', 'mest': 'GMT+2', 'sst': 'GMT+2', - 'fst': 'GMT+2', 'wadt': 'GMT+8', 'eadt': 'GMT+11', 'nzdt': 'GMT+13', - 'wet': 'GMT', 'wat': 'GMT+1', 'at': 'GMT-2', 'ast': 'GMT-4', - 'nt': 'GMT-11', 'idlw': 'GMT-12', 'cet': 'GMT+1', 'cest': 'GMT+2', - 'met': 'GMT+1', - 'mewt': 'GMT+1', 'swt': 'GMT+1', 'fwt': 'GMT+1', 'eet': 'GMT+2', - 'eest': 'GMT+3', - 'bt': 'GMT+3', 'zp4': 'GMT+4', 'zp5': 'GMT+5', 'zp6': 'GMT+6', - 'wast': 'GMT+7', 'cct': 'GMT+8', 'jst': 'GMT+9', 'east': 'GMT+10', - 'gst': 'GMT+10', 'nzt': 'GMT+12', 'nzst': 'GMT+12', 'idle': 'GMT+12', - 'ret': 'GMT+4', 'ist': 'GMT+0530', 'edt': 'GMT-4', - -} - - -# some timezone definitions of the "-0400" are not working -# when upgrading -for hour in range(0, 13): - hour = hour - fhour = str(hour) - if len(fhour) == 1: - fhour = '0' + fhour - _old_zmap['-%s00' % fhour] = 'GMT-%i' % hour - _old_zmap['+%s00' % fhour] = 'GMT+%i' % hour - - -def _p(zone): - return _numeric_timezones[zone] - - -def _static_timezone_factory(data): - zone = data[0] - cls = type(zone, (StaticTzInfo,), dict( - __reduce__=lambda _: (_p, (zone, )), - zone=zone, - _utcoffset=memorized_timedelta(data[5][0][0]), - _tzname=data[6][:-1])) # strip the trailing null - return cls() - - -_numeric_timezones = {key: _static_timezone_factory(data) - for key, data in _numeric_timezone_data.items()} - - -class Timezone: - """ - Timezone information returned by PytzCache.__getitem__ - Adapts datetime.tzinfo object to DateTime._timezone interface - """ - - def __init__(self, tzinfo): - self.tzinfo = tzinfo - - def info(self, t=None): - if t is None: - dt = datetime.now(tz=pytz.utc) - else: - # can't use utcfromtimestamp past 2038 - dt = EPOCH + timedelta(0, t) - - # need to normalize tzinfo for the datetime to deal with - # daylight savings time. - normalized_dt = self.tzinfo.normalize(dt.astimezone(self.tzinfo)) - normalized_tzinfo = normalized_dt.tzinfo - - offset = normalized_tzinfo.utcoffset(normalized_dt) - secs = offset.days * 24 * 60 * 60 + offset.seconds - dst = normalized_tzinfo.dst(normalized_dt) - if dst == timedelta(0): - is_dst = 0 - else: - is_dst = 1 - return secs, is_dst, normalized_tzinfo.tzname(normalized_dt) - - -class PytzCache: - """ - Reimplementation of the DateTime._cache class that uses for timezone info - """ - - _zlst = pytz.common_timezones + _old_zlst # used by DateTime.TimeZones - _zmap = {name.lower(): name for name in pytz.all_timezones} - _zmap.update(_old_zmap) # These must take priority - _zidx = _zmap.keys() - - def __getitem__(self, key): - name = self._zmap.get(key.lower(), key) # fallback to key - try: - return Timezone(pytz.timezone(name)) - except pytz.UnknownTimeZoneError: - try: - return Timezone(_numeric_timezones[name]) - except KeyError: - raise DateTimeError('Unrecognized timezone: %s' % key) diff --git a/llmlab/lib/python3.12/site-packages/DateTime/tests/__init__.py b/llmlab/lib/python3.12/site-packages/DateTime/tests/__init__.py deleted file mode 100644 index e67bcb6..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/tests/__init__.py +++ /dev/null @@ -1,15 +0,0 @@ -############################################################################## -# -# Copyright (c) 2003 Zope Foundation and Contributors. -# All Rights Reserved. -# -# This software is subject to the provisions of the Zope Public License, -# Version 2.1 (ZPL). A copy of the ZPL should accompany this distribution. -# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED -# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS -# FOR A PARTICULAR PURPOSE. -# -############################################################################## - -# This file is needed to make this a package. diff --git a/llmlab/lib/python3.12/site-packages/DateTime/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/DateTime/tests/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 708d3b8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/DateTime/tests/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/DateTime/tests/__pycache__/test_datetime.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/DateTime/tests/__pycache__/test_datetime.cpython-312.pyc deleted file mode 100644 index d97318e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/DateTime/tests/__pycache__/test_datetime.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/DateTime/tests/julian_testdata.txt b/llmlab/lib/python3.12/site-packages/DateTime/tests/julian_testdata.txt deleted file mode 100644 index 386c3da..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/tests/julian_testdata.txt +++ /dev/null @@ -1,57 +0,0 @@ -1970-01-01 (1970, 1, 4) -1970-01-02 (1970, 1, 5) -1970-01-30 (1970, 5, 5) -1970-01-31 (1970, 5, 6) -1970-02-01 (1970, 5, 7) -1970-02-02 (1970, 6, 1) -1970-02-28 (1970, 9, 6) -1970-03-01 (1970, 9, 7) -1970-03-30 (1970, 14, 1) -1970-03-31 (1970, 14, 2) -1970-04-01 (1970, 14, 3) -1970-09-30 (1970, 40, 3) -1970-10-01 (1970, 40, 4) -1970-10-02 (1970, 40, 5) -1970-10-03 (1970, 40, 6) -1970-10-04 (1970, 40, 7) -1970-10-05 (1970, 41, 1) -1971-01-02 (1970, 53, 6) -1971-01-03 (1970, 53, 7) -1971-01-04 (1971, 1, 1) -1971-01-05 (1971, 1, 2) -1971-12-31 (1971, 52, 5) -1972-01-01 (1971, 52, 6) -1972-01-02 (1971, 52, 7) -1972-01-03 (1972, 1, 1) -1972-01-04 (1972, 1, 2) -1972-12-30 (1972, 52, 6) -1972-12-31 (1972, 52, 7) -1973-01-01 (1973, 1, 1) -1973-01-02 (1973, 1, 2) -1973-12-29 (1973, 52, 6) -1973-12-30 (1973, 52, 7) -1973-12-31 (1974, 1, 1) -1974-01-01 (1974, 1, 2) -1998-12-30 (1998, 53, 3) -1998-12-31 (1998, 53, 4) -1999-01-01 (1998, 53, 5) -1999-01-02 (1998, 53, 6) -1999-01-03 (1998, 53, 7) -1999-01-04 (1999, 1, 1) -1999-01-05 (1999, 1, 2) -1999-12-30 (1999, 52, 4) -1999-12-31 (1999, 52, 5) -2000-01-01 (1999, 52, 6) -2000-01-02 (1999, 52, 7) -2000-01-03 (2000, 1, 1) -2000-01-04 (2000, 1, 2) -2000-01-05 (2000, 1, 3) -2000-01-06 (2000, 1, 4) -2000-01-07 (2000, 1, 5) -2000-01-08 (2000, 1, 6) -2000-01-09 (2000, 1, 7) -2000-01-10 (2000, 2, 1) -2019-12-28 (2019, 52, 6) -2019-12-29 (2019, 52, 7) -2019-12-30 (2020, 1, 1) -2019-12-31 (2020, 1, 2) diff --git a/llmlab/lib/python3.12/site-packages/DateTime/tests/test_datetime.py b/llmlab/lib/python3.12/site-packages/DateTime/tests/test_datetime.py deleted file mode 100644 index f4c2644..0000000 --- a/llmlab/lib/python3.12/site-packages/DateTime/tests/test_datetime.py +++ /dev/null @@ -1,764 +0,0 @@ -############################################################################## -# -# Copyright (c) 2003 Zope Foundation and Contributors. -# All Rights Reserved. -# -# This software is subject to the provisions of the Zope Public License, -# Version 2.1 (ZPL). A copy of the ZPL should accompany this distribution. -# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED -# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS -# FOR A PARTICULAR PURPOSE. -# -############################################################################## - -import math -import os -import pickle -import platform -import sys -import time -import unittest -from datetime import date -from datetime import datetime -from datetime import timedelta -from datetime import tzinfo - -import pytz - -from DateTime import DateTime -from DateTime.DateTime import _findLocalTimeZoneName - - -try: - __file__ -except NameError: # pragma: no cover - f = sys.argv[0] -else: - f = __file__ - -IS_PYPY = getattr(platform, 'python_implementation', lambda: None)() == 'PyPy' - -DATADIR = os.path.dirname(os.path.abspath(f)) -del f - -ZERO = timedelta(0) - - -class FixedOffset(tzinfo): - """Fixed offset in minutes east from UTC.""" - - def __init__(self, offset, name): - self.__offset = timedelta(minutes=offset) - self.__name = name - - def utcoffset(self, dt): - return self.__offset - - def tzname(self, dt): - return self.__name - - def dst(self, dt): - return ZERO - - -class DateTimeTests(unittest.TestCase): - - def _compare(self, dt1, dt2): - '''Compares the internal representation of dt1 with - the representation in dt2. Allows sub-millisecond variations. - Primarily for testing.''' - self.assertEqual(round(dt1._t, 3), round(dt2._t, 3)) - self.assertEqual(round(dt1._d, 9), round(dt2._d, 9)) - self.assertEqual(round(dt1.time, 9), round(dt2.time, 9)) - self.assertEqual(dt1.millis(), dt2.millis()) - self.assertEqual(dt1._micros, dt2._micros) - - def testBug1203(self): - # 01:59:60 occurred in old DateTime - dt = DateTime(7200, 'GMT') - self.assertTrue(str(dt).find('60') < 0, dt) - - def testDSTInEffect(self): - # Checks GMT offset for a DST date in the US/Eastern time zone - dt = DateTime(2000, 5, 9, 15, 0, 0, 'US/Eastern') - self.assertEqual(dt.toZone('GMT').hour(), 19, - (dt, dt.toZone('GMT'))) - - def testDSTNotInEffect(self): - # Checks GMT offset for a non-DST date in the US/Eastern time zone - dt = DateTime(2000, 11, 9, 15, 0, 0, 'US/Eastern') - self.assertEqual(dt.toZone('GMT').hour(), 20, - (dt, dt.toZone('GMT'))) - - def testAddPrecision(self): - # Precision of serial additions - dt = DateTime() - self.assertEqual(str(dt + 0.10 + 3.14 + 6.76 - 10), str(dt), - dt) - # checks problem reported in - # https://github.com/zopefoundation/DateTime/issues/41 - dt = DateTime(2038, 10, 7, 8, 52, 44.959840, "UTC") - self.assertEqual(str(dt + 0.10 + 3.14 + 6.76 - 10), str(dt), - dt) - - def testConsistentSecondMicroRounding(self): - dt = DateTime(2038, 10, 7, 8, 52, 44.9598398, "UTC") - self.assertEqual(int(dt.second() * 1000000), - dt.micros() % 60000000) - - def testConstructor3(self): - # Constructor from date/time string - dt = DateTime() - dt1s = '%d/%d/%d %d:%d:%f %s' % ( - dt.year(), - dt.month(), - dt.day(), - dt.hour(), - dt.minute(), - dt.second(), - dt.timezone()) - dt1 = DateTime(dt1s) - # Compare representations as it's the - # only way to compare the dates to the same accuracy - self.assertEqual(repr(dt), repr(dt1)) - - def testConstructor4(self): - # Constructor from time float - dt = DateTime() - dt1 = DateTime(float(dt)) - self._compare(dt, dt1) - - def testConstructor5(self): - # Constructor from time float and timezone - dt = DateTime() - dt1 = DateTime(float(dt), dt.timezone()) - self.assertEqual(str(dt), str(dt1), (dt, dt1)) - dt1 = DateTime(float(dt), str(dt.timezone())) - self.assertEqual(str(dt), str(dt1), (dt, dt1)) - - def testConstructor6(self): - # Constructor from year and julian date - # This test must normalize the time zone, or it *will* break when - # DST changes! - dt1 = DateTime(2000, 5.500000578705) - dt = DateTime('2000/1/5 12:00:00.050 pm %s' % dt1.localZone()) - self._compare(dt, dt1) - - def testConstructor7(self): - # Constructor from parts - dt = DateTime() - dt1 = DateTime( - dt.year(), - dt.month(), - dt.day(), - dt.hour(), - dt.minute(), - dt.second(), - dt.timezone()) - # Compare representations as it's the - # only way to compare the dates to the same accuracy - self.assertEqual(repr(dt), repr(dt1)) - - def testDayOfWeek(self): - # Compare to the datetime.date value to make it locale independent - expected = date(2000, 6, 16).strftime('%A') - # strftime() used to always be passed a day of week of 0 - dt = DateTime('2000/6/16') - s = dt.strftime('%A') - self.assertEqual(s, expected, (dt, s)) - - def testOldDate(self): - # Fails when an 1800 date is displayed with negative signs - dt = DateTime('1830/5/6 12:31:46.213 pm') - dt1 = dt.toZone('GMT+6') - self.assertTrue(str(dt1).find('-') < 0, (dt, dt1)) - - def testSubtraction(self): - # Reconstruction of a DateTime from its parts, with subtraction - # this also tests the accuracy of addition and reconstruction - dt = DateTime() - dt1 = dt - 3.141592653 - dt2 = DateTime( - dt.year(), - dt.month(), - dt.day(), - dt.hour(), - dt.minute(), - dt.second()) - dt3 = dt2 - 3.141592653 - self.assertEqual(dt1, dt3, (dt, dt1, dt2, dt3)) - - def testTZ1add(self): - # Time zone manipulation: add to a date - dt = DateTime('1997/3/8 1:45am GMT-4') - dt1 = DateTime('1997/3/9 1:45pm GMT+8') - self.assertTrue((dt + 1.0).equalTo(dt1)) - - def testTZ1sub(self): - # Time zone manipulation: subtract from a date - dt = DateTime('1997/3/8 1:45am GMT-4') - dt1 = DateTime('1997/3/9 1:45pm GMT+8') - self.assertTrue((dt1 - 1.0).equalTo(dt)) - - def testTZ1diff(self): - # Time zone manipulation: diff two dates - dt = DateTime('1997/3/8 1:45am GMT-4') - dt1 = DateTime('1997/3/9 1:45pm GMT+8') - self.assertEqual(dt1 - dt, 1.0, (dt, dt1)) - - def test_compare_methods(self): - # Compare two dates using several methods - dt = DateTime('1997/1/1') - dt1 = DateTime('1997/2/2') - self.assertTrue(dt1.greaterThan(dt)) - self.assertTrue(dt1.greaterThanEqualTo(dt)) - self.assertTrue(dt.lessThan(dt1)) - self.assertTrue(dt.lessThanEqualTo(dt1)) - self.assertTrue(dt.notEqualTo(dt1)) - self.assertFalse(dt.equalTo(dt1)) - # Compare a date to float - dt = DateTime(1.0) - self.assertTrue(dt == DateTime(1.0)) # testing __eq__ - self.assertFalse(dt != DateTime(1.0)) # testing __ne__ - self.assertFalse(dt.greaterThan(1.0)) - self.assertTrue(dt.greaterThanEqualTo(1.0)) - self.assertFalse(dt.lessThan(1.0)) - self.assertTrue(dt.lessThanEqualTo(1.0)) - self.assertFalse(dt.notEqualTo(1.0)) - self.assertTrue(dt.equalTo(1.0)) - # Compare a date to int - dt = DateTime(1) - self.assertEqual(dt, DateTime(1.0)) - self.assertTrue(dt == DateTime(1)) # testing __eq__ - self.assertFalse(dt != DateTime(1)) # testing __ne__ - self.assertFalse(dt.greaterThan(1)) - self.assertTrue(dt.greaterThanEqualTo(1)) - self.assertFalse(dt.lessThan(1)) - self.assertTrue(dt.lessThanEqualTo(1)) - self.assertFalse(dt.notEqualTo(1)) - self.assertTrue(dt.equalTo(1)) - # Compare a date to string; there is no implicit type conversion - # but behavior if consistent as when comparing, for example, an int - # and a string. - dt = DateTime("2023") - self.assertFalse(dt == "2023") # testing __eq__ - self.assertTrue(dt != "2023") # testing __ne__ - self.assertRaises(TypeError, dt.greaterThan, "2023") - self.assertRaises(TypeError, dt.greaterThanEqualTo, "2023") - self.assertRaises(TypeError, dt.lessThan, "2023") - self.assertRaises(TypeError, dt.lessThanEqualTo, "2023") - self.assertTrue(dt.notEqualTo("2023")) - self.assertFalse(dt.equalTo("2023")) - - def test_compare_methods_none(self): - # Compare a date to None - for dt in (DateTime('1997/1/1'), DateTime(0)): - self.assertTrue(dt.greaterThan(None)) - self.assertTrue(dt.greaterThanEqualTo(None)) - self.assertFalse(dt.lessThan(None)) - self.assertFalse(dt.lessThanEqualTo(None)) - self.assertTrue(dt.notEqualTo(None)) - self.assertFalse(dt.equalTo(None)) - - def test_pickle(self): - dt = DateTime() - data = pickle.dumps(dt, 1) - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_with_tz(self): - dt = DateTime('2002/5/2 8:00am GMT+8') - data = pickle.dumps(dt, 1) - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_asdatetime_with_tz(self): - dt = DateTime('2002/5/2 8:00am GMT+8') - data = pickle.dumps(dt.asdatetime(), 1) - new = DateTime(pickle.loads(data)) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_with_numerical_tz(self): - for dt_str in ('2007/01/02 12:34:56.789 +0300', - '2007/01/02 12:34:56.789 +0430', - '2007/01/02 12:34:56.789 -1234'): - dt = DateTime(dt_str) - data = pickle.dumps(dt, 1) - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_with_micros(self): - dt = DateTime('2002/5/2 8:00:14.123 GMT+8') - data = pickle.dumps(dt, 1) - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_old(self): - dt = DateTime('2002/5/2 8:00am GMT+0') - data = ( - '(cDateTime.DateTime\nDateTime\nq\x01Noq\x02}q\x03(U\x05' - '_amonq\x04U\x03Mayq\x05U\x05_adayq\x06U\x03Thuq\x07U\x05_pmonq' - '\x08h\x05U\x05_hourq\tK\x08U\x05_fmonq\nh\x05U\x05_pdayq\x0bU' - '\x04Thu.q\x0cU\x05_fdayq\rU\x08Thursdayq\x0eU\x03_pmq\x0fU\x02amq' - '\x10U\x02_tq\x11GA\xcehy\x00\x00\x00\x00U\x07_minuteq\x12K\x00U' - '\x07_microsq\x13L1020326400000000L\nU\x02_dq\x14G@\xe2\x12j\xaa' - '\xaa\xaa\xabU\x07_secondq\x15G\x00\x00\x00\x00\x00\x00\x00\x00U' - '\x03_tzq\x16U\x05GMT+0q\x17U\x06_monthq\x18K\x05U' - '\x0f_timezone_naiveq\x19I00\nU\x04_dayq\x1aK\x02U\x05_yearq' - '\x1bM\xd2\x07U\x08_nearsecq\x1cG\x00\x00\x00\x00\x00\x00\x00' - '\x00U\x07_pmhourq\x1dK\x08U\n_dayoffsetq\x1eK\x04U\x04timeq' - '\x1fG?\xd5UUUV\x00\x00ub.') - data = data.encode('latin-1') - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_old_without_micros(self): - dt = DateTime('2002/5/2 8:00am GMT+0') - data = ( - '(cDateTime.DateTime\nDateTime\nq\x01Noq\x02}q\x03(U\x05' - '_amonq\x04U\x03Mayq\x05U\x05_adayq\x06U\x03Thuq\x07U\x05_pmonq' - '\x08h\x05U\x05_hourq\tK\x08U\x05_fmonq\nh\x05U\x05_pdayq\x0bU' - '\x04Thu.q\x0cU\x05_fdayq\rU\x08Thursdayq\x0eU\x03_pmq\x0fU' - '\x02amq\x10U\x02_tq\x11GA\xcehy\x00\x00\x00\x00U\x07_minuteq' - '\x12K\x00U\x02_dq\x13G@\xe2\x12j\xaa\xaa\xaa\xabU\x07_secondq' - '\x14G\x00\x00\x00\x00\x00\x00\x00\x00U\x03_tzq\x15U\x05GMT+0q' - '\x16U\x06_monthq\x17K\x05U\x0f_timezone_naiveq\x18I00\nU' - '\x04_dayq\x19K\x02U\x05_yearq\x1aM\xd2\x07U\x08_nearsecq' - '\x1bG\x00\x00\x00\x00\x00\x00\x00\x00U\x07_pmhourq\x1cK\x08U' - '\n_dayoffsetq\x1dK\x04U\x04timeq\x1eG?\xd5UUUV\x00\x00ub.') - data = data.encode('latin-1') - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_dates_after_2038(self): - dt = DateTime('2039/09/02 07:07:6.235027 GMT+1') - data = pickle.dumps(dt, 1) - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def test_pickle_old_with_micros_as_float(self): - dt = DateTime('2002/5/2 8:00am GMT+0') - data = ( - 'ccopy_reg\n_reconstructor\nq\x00(cDateTime.DateTime\nDateTime' - '\nq\x01c__builtin__\nobject\nq\x02Ntq\x03Rq\x04(GA\xcehy\x00\x00' - '\x00\x00I00\nX\x05\x00\x00\x00GMT+0q\x05tq\x06b.') - data = data.encode('latin-1') - new = pickle.loads(data) - for key in DateTime.__slots__: - self.assertEqual(getattr(dt, key), getattr(new, key)) - - def testTZ2(self): - # Time zone manipulation test 2 - dt = DateTime() - dt1 = dt.toZone('GMT') - s = dt.second() - s1 = dt1.second() - self.assertEqual(s, s1, (dt, dt1, s, s1)) - - def testTZDiffDaylight(self): - # Diff dates across daylight savings dates - dt = DateTime('2000/6/8 1:45am US/Eastern') - dt1 = DateTime('2000/12/8 12:45am US/Eastern') - self.assertEqual(dt1 - dt, 183, (dt, dt1, dt1 - dt)) - - def testY10KDate(self): - # Comparison of a Y10K date and a Y2K date - dt = DateTime('10213/09/21') - dt1 = DateTime(2000, 1, 1) - - dsec = (dt.millis() - dt1.millis()) / 1000.0 - ddays = math.floor((dsec / 86400.0) + 0.5) - - self.assertEqual(ddays, 3000000, ddays) - - def test_tzoffset(self): - # Test time-zone given as an offset - - # GMT - dt = DateTime('Tue, 10 Sep 2001 09:41:03 GMT') - self.assertEqual(dt.tzoffset(), 0) - - # Timezone by name, a timezone that hasn't got daylightsaving. - dt = DateTime('Tue, 2 Mar 2001 09:41:03 GMT+3') - self.assertEqual(dt.tzoffset(), 10800) - - # Timezone by name, has daylightsaving but is not in effect. - dt = DateTime('Tue, 21 Jan 2001 09:41:03 PST') - self.assertEqual(dt.tzoffset(), -28800) - - # Timezone by name, with daylightsaving in effect - dt = DateTime('Tue, 24 Aug 2001 09:41:03 PST') - self.assertEqual(dt.tzoffset(), -25200) - - # A negative numerical timezone - dt = DateTime('Tue, 24 Jul 2001 09:41:03 -0400') - self.assertEqual(dt.tzoffset(), -14400) - - # A positive numerical timzone - dt = DateTime('Tue, 6 Dec 1966 01:41:03 +0200') - self.assertEqual(dt.tzoffset(), 7200) - - # A negative numerical timezone with minutes. - dt = DateTime('Tue, 24 Jul 2001 09:41:03 -0637') - self.assertEqual(dt.tzoffset(), -23820) - - # A positive numerical timezone with minutes. - dt = DateTime('Tue, 24 Jul 2001 09:41:03 +0425') - self.assertEqual(dt.tzoffset(), 15900) - - def testISO8601(self): - # ISO8601 reference dates - ref0 = DateTime('2002/5/2 8:00am GMT') - ref1 = DateTime('2002/5/2 8:00am US/Eastern') - ref2 = DateTime('2006/11/6 10:30 GMT') - ref3 = DateTime('2004/06/14 14:30:15 GMT-3') - ref4 = DateTime('2006/01/01 GMT') - - # Basic tests - # Though this is timezone naive and according to specification should - # be interpreted in the local timezone, to preserve backwards - # compatibility with previously expected behaviour. - isoDt = DateTime('2002-05-02T08:00:00') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002-05-02T08:00:00Z') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002-05-02T08:00:00+00:00') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002-05-02T08:00:00-04:00') - self.assertTrue(ref1.equalTo(isoDt)) - isoDt = DateTime('2002-05-02 08:00:00-04:00') - self.assertTrue(ref1.equalTo(isoDt)) - - # Bug 1386: the colon in the timezone offset is optional - isoDt = DateTime('2002-05-02T08:00:00-0400') - self.assertTrue(ref1.equalTo(isoDt)) - - # Bug 2191: date reduced formats - isoDt = DateTime('2006-01-01') - self.assertTrue(ref4.equalTo(isoDt)) - isoDt = DateTime('200601-01') - self.assertTrue(ref4.equalTo(isoDt)) - isoDt = DateTime('20060101') - self.assertTrue(ref4.equalTo(isoDt)) - isoDt = DateTime('2006-01') - self.assertTrue(ref4.equalTo(isoDt)) - isoDt = DateTime('200601') - self.assertTrue(ref4.equalTo(isoDt)) - isoDt = DateTime('2006') - self.assertTrue(ref4.equalTo(isoDt)) - - # Bug 2191: date/time separators are also optional - isoDt = DateTime('20020502T08:00:00') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002-05-02T080000') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('20020502T080000') - self.assertTrue(ref0.equalTo(isoDt)) - - # Bug 2191: timezones with only one digit for hour - isoDt = DateTime('20020502T080000+0') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('20020502 080000-4') - self.assertTrue(ref1.equalTo(isoDt)) - isoDt = DateTime('20020502T080000-400') - self.assertTrue(ref1.equalTo(isoDt)) - isoDt = DateTime('20020502T080000-4:00') - self.assertTrue(ref1.equalTo(isoDt)) - - # Bug 2191: optional seconds/minutes - isoDt = DateTime('2002-05-02T0800') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002-05-02T08') - self.assertTrue(ref0.equalTo(isoDt)) - - # Bug 2191: week format - isoDt = DateTime('2002-W18-4T0800') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002-W184T0800') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002W18-4T0800') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002W184T08') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2004-W25-1T14:30:15-03:00') - self.assertTrue(ref3.equalTo(isoDt)) - isoDt = DateTime('2004-W25T14:30:15-03:00') - self.assertTrue(ref3.equalTo(isoDt)) - - # Bug 2191: day of year format - isoDt = DateTime('2002-122T0800') - self.assertTrue(ref0.equalTo(isoDt)) - isoDt = DateTime('2002122T0800') - self.assertTrue(ref0.equalTo(isoDt)) - - # Bug 2191: hours/minutes fractions - isoDt = DateTime('2006-11-06T10.5') - self.assertTrue(ref2.equalTo(isoDt)) - isoDt = DateTime('2006-11-06T10,5') - self.assertTrue(ref2.equalTo(isoDt)) - isoDt = DateTime('20040614T1430.25-3') - self.assertTrue(ref3.equalTo(isoDt)) - isoDt = DateTime('2004-06-14T1430,25-3') - self.assertTrue(ref3.equalTo(isoDt)) - isoDt = DateTime('2004-06-14T14:30.25-3') - self.assertTrue(ref3.equalTo(isoDt)) - isoDt = DateTime('20040614T14:30,25-3') - self.assertTrue(ref3.equalTo(isoDt)) - - # ISO8601 standard format - iso8601_string = '2002-05-02T08:00:00-04:00' - iso8601DT = DateTime(iso8601_string) - self.assertEqual(iso8601_string, iso8601DT.ISO8601()) - - # ISO format with no timezone - isoDt = DateTime('2006-01-01 00:00:00') - self.assertTrue(ref4.equalTo(isoDt)) - - def testJulianWeek(self): - # Check JulianDayWeek function - fn = os.path.join(DATADIR, 'julian_testdata.txt') - with open(fn) as fd: - lines = fd.readlines() - for line in lines: - d = DateTime(line[:10]) - result_from_mx = tuple(map(int, line[12:-2].split(','))) - self.assertEqual(result_from_mx[1], d.week()) - - def testCopyConstructor(self): - d = DateTime('2004/04/04') - self.assertEqual(DateTime(d), d) - self.assertEqual(str(DateTime(d)), str(d)) - d2 = DateTime('1999/04/12 01:00:00') - self.assertEqual(DateTime(d2), d2) - self.assertEqual(str(DateTime(d2)), str(d2)) - - def testCopyConstructorPreservesTimezone(self): - # test for https://bugs.launchpad.net/zope2/+bug/200007 - # This always worked in the local timezone, so we need at least - # two tests with different zones to be sure at least one of them - # is not local. - d = DateTime('2004/04/04') - self.assertEqual(DateTime(d).timezone(), d.timezone()) - d2 = DateTime('2008/04/25 12:00:00 EST') - self.assertEqual(DateTime(d2).timezone(), d2.timezone()) - self.assertEqual(str(DateTime(d2)), str(d2)) - d3 = DateTime('2008/04/25 12:00:00 PST') - self.assertEqual(DateTime(d3).timezone(), d3.timezone()) - self.assertEqual(str(DateTime(d3)), str(d3)) - - def testRFC822(self): - # rfc822 conversion - dt = DateTime('2002-05-02T08:00:00+00:00') - self.assertEqual(dt.rfc822(), 'Thu, 02 May 2002 08:00:00 +0000') - - dt = DateTime('2002-05-02T08:00:00+02:00') - self.assertEqual(dt.rfc822(), 'Thu, 02 May 2002 08:00:00 +0200') - - dt = DateTime('2002-05-02T08:00:00-02:00') - self.assertEqual(dt.rfc822(), 'Thu, 02 May 2002 08:00:00 -0200') - - # Checking that conversion from local time is working. - dt = DateTime() - dts = dt.rfc822().split(' ') - times = dts[4].split(':') - _isDST = time.localtime(time.time())[8] - if _isDST: - offset = time.altzone - else: - offset = time.timezone - self.assertEqual(dts[0], dt.aDay() + ',') - self.assertEqual(int(dts[1]), dt.day()) - self.assertEqual(dts[2], dt.aMonth()) - self.assertEqual(int(dts[3]), dt.year()) - self.assertEqual(int(times[0]), dt.h_24()) - self.assertEqual(int(times[1]), dt.minute()) - self.assertEqual(int(times[2]), int(dt.second())) - self.assertEqual(dts[5], "%+03d%02d" % divmod((-offset / 60), 60)) - - def testInternationalDateformat(self): - for year in (1990, 2001, 2020): - for month in (1, 12): - for day in (1, 12, 28, 31): - try: - d_us = DateTime("%d/%d/%d" % (year, month, day)) - except Exception: - continue - - d_int = DateTime("%d.%d.%d" % (day, month, year), - datefmt="international") - self.assertEqual(d_us, d_int) - - d_int = DateTime("%d/%d/%d" % (day, month, year), - datefmt="international") - self.assertEqual(d_us, d_int) - - def test_intl_format_hyphen(self): - d_jan = DateTime('2011-01-11 GMT') - d_nov = DateTime('2011-11-01 GMT') - d_us = DateTime('11-01-2011 GMT') - d_int = DateTime('11-01-2011 GMT', datefmt="international") - self.assertNotEqual(d_us, d_int) - self.assertEqual(d_us, d_nov) - self.assertEqual(d_int, d_jan) - - def test_calcTimezoneName(self): - from DateTime.interfaces import TimeError - timezone_dependent_epoch = 2177452800 - try: - DateTime()._calcTimezoneName(timezone_dependent_epoch, 0) - except TimeError: - self.fail('Zope Collector issue #484 (negative time bug): ' - 'TimeError raised') - - def testStrftimeTZhandling(self): - # strftime timezone testing - # This is a test for collector issue #1127 - format = '%Y-%m-%d %H:%M %Z' - dt = DateTime('Wed, 19 Nov 2003 18:32:07 -0215') - dt_string = dt.strftime(format) - dt_local = dt.toZone(_findLocalTimeZoneName(0)) - dt_localstring = dt_local.strftime(format) - self.assertEqual(dt_string, dt_localstring) - - def testStrftimeFarDates(self): - # Checks strftime in dates <= 1900 or >= 2038 - dt = DateTime('1900/01/30') - self.assertEqual(dt.strftime('%d/%m/%Y'), '30/01/1900') - dt = DateTime('2040/01/30') - self.assertEqual(dt.strftime('%d/%m/%Y'), '30/01/2040') - - def testZoneInFarDates(self): - # Checks time zone in dates <= 1900 or >= 2038 - dt1 = DateTime('2040/01/30 14:33 GMT+1') - dt2 = DateTime('2040/01/30 11:33 GMT-2') - self.assertEqual(dt1.strftime('%d/%m/%Y %H:%M'), - dt2.strftime('%d/%m/%Y %H:%M')) - - @unittest.skipIf( - IS_PYPY, - "Using Non-Ascii characters for strftime doesn't work in PyPy" - "https://bitbucket.org/pypy/pypy/issues/2161/pypy3-strftime-does-not-accept-unicode" # noqa: E501 line too long - ) - def testStrftimeStr(self): - dt = DateTime('2002-05-02T08:00:00+00:00') - uchar = b'\xc3\xa0'.decode('utf-8') - ok = dt.strftime('Le %d/%m/%Y a %Hh%M').replace('a', uchar) - ustr = b'Le %d/%m/%Y \xc3\xa0 %Hh%M'.decode('utf-8') - self.assertEqual(dt.strftime(ustr), ok) - - def testTimezoneNaiveHandling(self): - # checks that we assign timezone naivity correctly - dt = DateTime('2007-10-04T08:00:00+00:00') - self.assertFalse(dt.timezoneNaive(), - 'error with naivity handling in __parse_iso8601') - dt = DateTime('2007-10-04T08:00:00Z') - self.assertFalse(dt.timezoneNaive(), - 'error with naivity handling in __parse_iso8601') - dt = DateTime('2007-10-04T08:00:00') - self.assertTrue(dt.timezoneNaive(), - 'error with naivity handling in __parse_iso8601') - dt = DateTime('2007/10/04 15:12:33.487618 GMT+1') - self.assertFalse(dt.timezoneNaive(), - 'error with naivity handling in _parse') - dt = DateTime('2007/10/04 15:12:33.487618') - self.assertTrue(dt.timezoneNaive(), - 'error with naivity handling in _parse') - dt = DateTime() - self.assertFalse(dt.timezoneNaive(), - 'error with naivity for current time') - s = '2007-10-04T08:00:00' - dt = DateTime(s) - self.assertEqual(s, dt.ISO8601()) - s = '2007-10-04T08:00:00+00:00' - dt = DateTime(s) - self.assertEqual(s, dt.ISO8601()) - - def testConversions(self): - sdt0 = datetime.now() # this is a timezone naive datetime - dt0 = DateTime(sdt0) - self.assertTrue(dt0.timezoneNaive(), (sdt0, dt0)) - sdt1 = datetime(2007, 10, 4, 18, 14, 42, 580, pytz.utc) - dt1 = DateTime(sdt1) - self.assertFalse(dt1.timezoneNaive(), (sdt1, dt1)) - - # convert back - sdt2 = dt0.asdatetime() - self.assertEqual(sdt0, sdt2) - sdt3 = dt1.utcdatetime() # this returns a timezone naive datetime - self.assertEqual(sdt1.hour, sdt3.hour) - - dt4 = DateTime('2007-10-04T10:00:00+05:00') - sdt4 = datetime(2007, 10, 4, 5, 0) - self.assertEqual(dt4.utcdatetime(), sdt4) - self.assertEqual(dt4.asdatetime(), sdt4.replace(tzinfo=pytz.utc)) - - dt5 = DateTime('2007-10-23 10:00:00 US/Eastern') - tz = pytz.timezone('US/Eastern') - sdt5 = datetime(2007, 10, 23, 10, 0, tzinfo=tz) - dt6 = DateTime(sdt5) - self.assertEqual(dt5.asdatetime(), sdt5) - self.assertEqual(dt6.asdatetime(), sdt5) - self.assertEqual(dt5, dt6) - self.assertEqual(dt5.asdatetime().tzinfo, tz) - self.assertEqual(dt6.asdatetime().tzinfo, tz) - - def testBasicTZ(self): - # psycopg2 supplies it's own tzinfo instances, with no `zone` attribute - tz = FixedOffset(60, 'GMT+1') - dt1 = datetime(2008, 8, 5, 12, 0, tzinfo=tz) - DT = DateTime(dt1) - dt2 = DT.asdatetime() - offset1 = dt1.tzinfo.utcoffset(dt1) - offset2 = dt2.tzinfo.utcoffset(dt2) - self.assertEqual(offset1, offset2) - - def testEDTTimezone(self): - # should be able to parse EDT timezones: see lp:599856. - dt = DateTime("Mon, 28 Jun 2010 10:12:25 EDT") - self.assertEqual(dt.Day(), 'Monday') - self.assertEqual(dt.day(), 28) - self.assertEqual(dt.Month(), 'June') - self.assertEqual(dt.timezone(), 'GMT-4') - - def testParseISO8601(self): - parsed = DateTime()._parse_iso8601('2010-10-10') - self.assertEqual(parsed, (2010, 10, 10, 0, 0, 0, 'GMT+0000')) - - def test_interface(self): - from DateTime.interfaces import IDateTime - self.assertTrue(IDateTime.providedBy(DateTime())) - - def test_security(self): - dt = DateTime() - self.assertEqual(dt.__roles__, None) - self.assertEqual(dt.__allow_access_to_unprotected_subobjects__, 1) - - def test_format(self): - dt = DateTime(1968, 3, 10, 23, 45, 0, 'Europe/Vienna') - fmt = '%d.%m.%Y %H:%M' - result = dt.strftime(fmt) - unformatted_result = '1968/03/10 23:45:00 Europe/Vienna' - self.assertEqual(result, f'{dt:%d.%m.%Y %H:%M}') - self.assertEqual(unformatted_result, f'{dt}') - self.assertEqual(unformatted_result, f'{dt}') - self.assertEqual(result, f'{dt:{fmt}}') - self.assertEqual(unformatted_result, f'{dt:}') - self.assertEqual(unformatted_result, f'{dt}') - - -def test_suite(): - import doctest - return unittest.TestSuite([ - unittest.defaultTestLoader.loadTestsFromTestCase(DateTimeTests), - doctest.DocFileSuite('DateTime.txt', package='DateTime'), - doctest.DocFileSuite('pytz.txt', package='DateTime'), - ]) diff --git a/llmlab/lib/python3.12/site-packages/__pycache__/example.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/__pycache__/example.cpython-312.pyc new file mode 100644 index 0000000..5b06df6 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/__pycache__/example.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/__pycache__/pynvml.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/__pycache__/pynvml.cpython-312.pyc new file mode 100644 index 0000000..2ec68ed Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/__pycache__/pynvml.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/_distutils_hack/__init__.py b/llmlab/lib/python3.12/site-packages/_distutils_hack/__init__.py deleted file mode 100644 index 94f71b9..0000000 --- a/llmlab/lib/python3.12/site-packages/_distutils_hack/__init__.py +++ /dev/null @@ -1,239 +0,0 @@ -# don't import any costly modules -import os -import sys - -report_url = ( - "https://github.com/pypa/setuptools/issues/new?template=distutils-deprecation.yml" -) - - -def warn_distutils_present(): - if 'distutils' not in sys.modules: - return - import warnings - - warnings.warn( - "Distutils was imported before Setuptools, but importing Setuptools " - "also replaces the `distutils` module in `sys.modules`. This may lead " - "to undesirable behaviors or errors. To avoid these issues, avoid " - "using distutils directly, ensure that setuptools is installed in the " - "traditional way (e.g. not an editable install), and/or make sure " - "that setuptools is always imported before distutils." - ) - - -def clear_distutils(): - if 'distutils' not in sys.modules: - return - import warnings - - warnings.warn( - "Setuptools is replacing distutils. Support for replacing " - "an already imported distutils is deprecated. In the future, " - "this condition will fail. " - f"Register concerns at {report_url}" - ) - mods = [ - name - for name in sys.modules - if name == "distutils" or name.startswith("distutils.") - ] - for name in mods: - del sys.modules[name] - - -def enabled(): - """ - Allow selection of distutils by environment variable. - """ - which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'local') - if which == 'stdlib': - import warnings - - warnings.warn( - "Reliance on distutils from stdlib is deprecated. Users " - "must rely on setuptools to provide the distutils module. " - "Avoid importing distutils or import setuptools first, " - "and avoid setting SETUPTOOLS_USE_DISTUTILS=stdlib. " - f"Register concerns at {report_url}" - ) - return which == 'local' - - -def ensure_local_distutils(): - import importlib - - clear_distutils() - - # With the DistutilsMetaFinder in place, - # perform an import to cause distutils to be - # loaded from setuptools._distutils. Ref #2906. - with shim(): - importlib.import_module('distutils') - - # check that submodules load as expected - core = importlib.import_module('distutils.core') - assert '_distutils' in core.__file__, core.__file__ - assert 'setuptools._distutils.log' not in sys.modules - - -def do_override(): - """ - Ensure that the local copy of distutils is preferred over stdlib. - - See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401 - for more motivation. - """ - if enabled(): - warn_distutils_present() - ensure_local_distutils() - - -class _TrivialRe: - def __init__(self, *patterns) -> None: - self._patterns = patterns - - def match(self, string): - return all(pat in string for pat in self._patterns) - - -class DistutilsMetaFinder: - def find_spec(self, fullname, path, target=None): - # optimization: only consider top level modules and those - # found in the CPython test suite. - if path is not None and not fullname.startswith('test.'): - return None - - method_name = 'spec_for_{fullname}'.format(**locals()) - method = getattr(self, method_name, lambda: None) - return method() - - def spec_for_distutils(self): - if self.is_cpython(): - return None - - import importlib - import importlib.abc - import importlib.util - - try: - mod = importlib.import_module('setuptools._distutils') - except Exception: - # There are a couple of cases where setuptools._distutils - # may not be present: - # - An older Setuptools without a local distutils is - # taking precedence. Ref #2957. - # - Path manipulation during sitecustomize removes - # setuptools from the path but only after the hook - # has been loaded. Ref #2980. - # In either case, fall back to stdlib behavior. - return None - - class DistutilsLoader(importlib.abc.Loader): - def create_module(self, spec): - mod.__name__ = 'distutils' - return mod - - def exec_module(self, module): - pass - - return importlib.util.spec_from_loader( - 'distutils', DistutilsLoader(), origin=mod.__file__ - ) - - @staticmethod - def is_cpython(): - """ - Suppress supplying distutils for CPython (build and tests). - Ref #2965 and #3007. - """ - return os.path.isfile('pybuilddir.txt') - - def spec_for_pip(self): - """ - Ensure stdlib distutils when running under pip. - See pypa/pip#8761 for rationale. - """ - if sys.version_info >= (3, 12) or self.pip_imported_during_build(): - return - clear_distutils() - self.spec_for_distutils = lambda: None - - @classmethod - def pip_imported_during_build(cls): - """ - Detect if pip is being imported in a build script. Ref #2355. - """ - import traceback - - return any( - cls.frame_file_is_setup(frame) for frame, line in traceback.walk_stack(None) - ) - - @staticmethod - def frame_file_is_setup(frame): - """ - Return True if the indicated frame suggests a setup.py file. - """ - # some frames may not have __file__ (#2940) - return frame.f_globals.get('__file__', '').endswith('setup.py') - - def spec_for_sensitive_tests(self): - """ - Ensure stdlib distutils when running select tests under CPython. - - python/cpython#91169 - """ - clear_distutils() - self.spec_for_distutils = lambda: None - - sensitive_tests = ( - [ - 'test.test_distutils', - 'test.test_peg_generator', - 'test.test_importlib', - ] - if sys.version_info < (3, 10) - else [ - 'test.test_distutils', - ] - ) - - -for name in DistutilsMetaFinder.sensitive_tests: - setattr( - DistutilsMetaFinder, - f'spec_for_{name}', - DistutilsMetaFinder.spec_for_sensitive_tests, - ) - - -DISTUTILS_FINDER = DistutilsMetaFinder() - - -def add_shim(): - DISTUTILS_FINDER in sys.meta_path or insert_shim() - - -class shim: - def __enter__(self) -> None: - insert_shim() - - def __exit__(self, exc: object, value: object, tb: object) -> None: - _remove_shim() - - -def insert_shim(): - sys.meta_path.insert(0, DISTUTILS_FINDER) - - -def _remove_shim(): - try: - sys.meta_path.remove(DISTUTILS_FINDER) - except ValueError: - pass - - -if sys.version_info < (3, 12): - # DistutilsMetaFinder can only be disabled in Python < 3.12 (PEP 632) - remove_shim = _remove_shim diff --git a/llmlab/lib/python3.12/site-packages/_distutils_hack/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/_distutils_hack/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index cec68b5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/_distutils_hack/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/_distutils_hack/__pycache__/override.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/_distutils_hack/__pycache__/override.cpython-312.pyc deleted file mode 100644 index 7aacc6b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/_distutils_hack/__pycache__/override.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/_distutils_hack/override.py b/llmlab/lib/python3.12/site-packages/_distutils_hack/override.py deleted file mode 100644 index 2cc433a..0000000 --- a/llmlab/lib/python3.12/site-packages/_distutils_hack/override.py +++ /dev/null @@ -1 +0,0 @@ -__import__('_distutils_hack').do_override() diff --git a/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__init__.cpython-312.pyc index 787db57..ca27102 100644 Binary files a/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__main__.cpython-312.pyc index 14370da..96b411c 100644 Binary files a/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/certifi/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/certifi/__pycache__/core.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/certifi/__pycache__/core.cpython-312.pyc index 4c2836c..12ab774 100644 Binary files a/llmlab/lib/python3.12/site-packages/certifi/__pycache__/core.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/certifi/__pycache__/core.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer-3.4.1.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/charset_normalizer-3.4.1.dist-info/RECORD index da12737..eab09d9 100644 --- a/llmlab/lib/python3.12/site-packages/charset_normalizer-3.4.1.dist-info/RECORD +++ b/llmlab/lib/python3.12/site-packages/charset_normalizer-3.4.1.dist-info/RECORD @@ -1,4 +1,4 @@ -../../../bin/normalizer,sha256=9WdyCIqYgSbUxt46Njhg9YwQf8x-EAzNrJo206alMfY,256 +../../../bin/normalizer,sha256=Cb5yIYYCPtaerk6Pit1w6ACFJ_h4ic57z1TTVY-ghfA,251 charset_normalizer-3.4.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 charset_normalizer-3.4.1.dist-info/LICENSE,sha256=bQ1Bv-FwrGx9wkjJpj4lTQ-0WmDVCoJX0K-SxuJJuIc,1071 charset_normalizer-3.4.1.dist-info/METADATA,sha256=JbyHzhmqZh_ugEn1Y7TY7CDYZA9FoU6BP25hrCNDf50,35313 diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__init__.cpython-312.pyc index eb7981b..fa48ee2 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__main__.cpython-312.pyc index bba09fc..844414f 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/api.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/api.cpython-312.pyc index 6e20f42..47202ab 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/api.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/api.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/cd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/cd.cpython-312.pyc index 93b505f..97db342 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/cd.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/cd.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/constant.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/constant.cpython-312.pyc index 2c0a2ff..6df9d3f 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/constant.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/constant.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/legacy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/legacy.cpython-312.pyc index 0858fc6..94fa87d 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/legacy.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/legacy.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/md.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/md.cpython-312.pyc index 23c88b8..78adceb 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/md.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/md.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/models.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/models.cpython-312.pyc index 5401579..0195f0b 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/models.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/models.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/utils.cpython-312.pyc index eac444b..383bc95 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/utils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/utils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/version.cpython-312.pyc index 8a11146..0826618 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/version.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/__pycache__/version.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc index e7d0d3b..ee0d867 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc index 277ec36..ff9d153 100644 Binary files a/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/distutils-precedence.pth b/llmlab/lib/python3.12/site-packages/distutils-precedence.pth deleted file mode 100644 index 7f009fe..0000000 --- a/llmlab/lib/python3.12/site-packages/distutils-precedence.pth +++ /dev/null @@ -1 +0,0 @@ -import os; var = 'SETUPTOOLS_USE_DISTUTILS'; enabled = os.environ.get(var, 'local') == 'local'; enabled and __import__('_distutils_hack').add_shim(); diff --git a/llmlab/lib/python3.12/site-packages/example.py b/llmlab/lib/python3.12/site-packages/example.py new file mode 100644 index 0000000..60173d5 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/example.py @@ -0,0 +1,169 @@ +################################################################################# +# Copyright (c) 2020, NVIDIA Corporation. All rights reserved. # +# # +# Redistribution and use in source and binary forms, with or without # +# modification, are permitted provided that the following conditions are met: # +# # +# * Redistributions of source code must retain the above copyright notice, # +# this list of conditions and the following disclaimer. # +# * Redistributions in binary form must reproduce the above copyright # +# notice, this list of conditions and the following disclaimer in the # +# documentation and/or other materials provided with the distribution. # +# * Neither the name of the NVIDIA Corporation nor the names of its # +# contributors may be used to endorse or promote products derived from # +# this software without specific prior written permission. # +# # +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" # +# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE # +# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE # +# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE # +# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR # +# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF # +# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS # +# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN # +# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) # +# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF # +# THE POSSIBILITY OF SUCH DAMAGE. # +################################################################################# + +# +# Sample script to demonstrate the usage of NVML API python bindings +# + +# To Run: +# $ python ./example.py + +from pynvml import * + +# +# Helper function +# +def StrVirt(mode): + if mode == NVML_GPU_VIRTUALIZATION_MODE_NONE: + return "None"; + elif mode == NVML_GPU_VIRTUALIZATION_MODE_PASSTHROUGH: + return "Pass-Through"; + elif mode == NVML_GPU_VIRTUALIZATION_MODE_VGPU: + return "VGPU"; + elif mode == NVML_GPU_VIRTUALIZATION_MODE_HOST_VGPU: + return "Host VGPU"; + elif mode == NVML_GPU_VIRTUALIZATION_MODE_HOST_VSGA: + return "Host VSGA"; + else: + return "Unknown"; + +# +# Converts errors into string messages +# +def handleError(err): + if (err.value == NVML_ERROR_NOT_SUPPORTED): + return "N/A" + else: + return err.__str__() + +####### +def deviceQuery(): + + strResult = '' + try: + # + # Initialize NVML + # + nvmlInit() + + strResult += ' ' + str(nvmlSystemGetDriverVersion()) + '\n' + + deviceCount = nvmlDeviceGetCount() + strResult += ' ' + str(deviceCount) + '\n' + + for i in range(0, deviceCount): + handle = nvmlDeviceGetHandleByIndex(i) + + pciInfo = nvmlDeviceGetPciInfo(handle) + + strResult += ' \n' % pciInfo.busId + + strResult += ' ' + nvmlDeviceGetName(handle) + '\n' + + brandNames = {NVML_BRAND_UNKNOWN : "Unknown", + NVML_BRAND_QUADRO : "Quadro", + NVML_BRAND_TESLA : "Tesla", + NVML_BRAND_NVS : "NVS", + NVML_BRAND_GRID : "Grid", + NVML_BRAND_TITAN : "Titan", + NVML_BRAND_GEFORCE : "GeForce", + NVML_BRAND_NVIDIA_VAPPS : "NVIDIA Virtual Applications", + NVML_BRAND_NVIDIA_VPC : "NVIDIA Virtual PC", + NVML_BRAND_NVIDIA_VCS : "NVIDIA Virtual Compute Server", + NVML_BRAND_NVIDIA_VWS : "NVIDIA RTX Virtual Workstation", + NVML_BRAND_NVIDIA_CLOUD_GAMING : "NVIDIA Cloud Gaming", + NVML_BRAND_QUADRO_RTX : "Quadro RTX", + NVML_BRAND_NVIDIA_RTX : "NVIDIA RTX", + NVML_BRAND_NVIDIA : "NVIDIA", + NVML_BRAND_GEFORCE_RTX : "GeForce RTX", + NVML_BRAND_TITAN_RTX : "TITAN RTX", + + } + + try: + # If nvmlDeviceGetBrand() succeeds it is guaranteed to be in the dictionary + brandName = brandNames[nvmlDeviceGetBrand(handle)] + except NVMLError as err: + brandName = handleError(err) + + strResult += ' ' + brandName + '\n' + + try: + serial = nvmlDeviceGetSerial(handle) + except NVMLError as err: + serial = handleError(err) + + strResult += ' ' + serial + '\n' + + try: + uuid = nvmlDeviceGetUUID(handle) + except NVMLError as err: + uuid = handleError(err) + + strResult += ' ' + uuid + '\n' + + strResult += ' \n' + try: + mode = StrVirt(nvmlDeviceGetVirtualizationMode(handle)) + except NVMLError as err: + mode = handleError(err) + strResult += ' ' + mode + '\n' + strResult += ' \n' + + try: + gridLicensableFeatures = nvmlDeviceGetGridLicensableFeatures(handle) + if gridLicensableFeatures.isGridLicenseSupported == 1: + strResult += ' \n' + for i in range(gridLicensableFeatures.licensableFeaturesCount): + if gridLicensableFeatures.gridLicensableFeatures[i].featureState == 0: + if nvmlDeviceGetVirtualizationMode(handle) == NVML_GPU_VIRTUALIZATION_MODE_PASSTHROUGH: + strResult += ' ' + 'NVIDIA Virtual Applications' + '\n' + strResult += ' ' + 'Licensed' + '\n' + else: + strResult += ' ' + gridLicensableFeatures.gridLicensableFeatures[i].productName + '\n' + strResult += ' ' + 'Unlicensed' + '\n' + else: + strResult += ' ' + gridLicensableFeatures.gridLicensableFeatures[i].productName + '\n' + strResult += ' ' + 'Licensed' + '\n' + strResult += ' \n' + except NVMLError as err: + gridLicensableFeatures = handleError(err) + + strResult += ' \n' + + except NVMLError as err: + strResult += 'example.py: ' + err.__str__() + '\n' + + nvmlShutdown() + + return strResult + +# If this is not exectued when module is imported +if __name__ == "__main__": + print(deviceQuery()) + diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/__init__.cpython-312.pyc index 8aa2fc2..548654b 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/codec.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/codec.cpython-312.pyc index ba0b8a9..ee3b40b 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/codec.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/codec.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/compat.cpython-312.pyc index 7b511c4..b6d1d3b 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/compat.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/compat.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/core.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/core.cpython-312.pyc index cbe0b75..47a645c 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/core.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/core.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/idnadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/idnadata.cpython-312.pyc index 651cd8d..a0b105a 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/idnadata.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/idnadata.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/intranges.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/intranges.cpython-312.pyc index 84ae48b..84dc292 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/intranges.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/intranges.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/package_data.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/package_data.cpython-312.pyc index 8c91f25..bccd91f 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/package_data.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/package_data.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/idna/__pycache__/uts46data.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/idna/__pycache__/uts46data.cpython-312.pyc index 286a846..9bee6cc 100644 Binary files a/llmlab/lib/python3.12/site-packages/idna/__pycache__/uts46data.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/idna/__pycache__/uts46data.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/INSTALLER similarity index 100% rename from llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/INSTALLER rename to llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/INSTALLER diff --git a/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/METADATA new file mode 100644 index 0000000..f52e7cd --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/METADATA @@ -0,0 +1,261 @@ +Metadata-Version: 2.2 +Name: nvidia-ml-py +Version: 12.570.86 +Summary: Python Bindings for the NVIDIA Management Library +Home-page: https://forums.developer.nvidia.com +Author: NVIDIA Corporation +Author-email: nvml-bindings@nvidia.com +License: BSD +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: Intended Audience :: System Administrators +Classifier: License :: OSI Approved :: BSD License +Classifier: Operating System :: Microsoft :: Windows +Classifier: Operating System :: POSIX :: Linux +Classifier: Programming Language :: Python +Classifier: Topic :: Software Development :: Libraries :: Python Modules +Classifier: Topic :: System :: Hardware +Classifier: Topic :: System :: Systems Administration +Description-Content-Type: text/markdown +Dynamic: author +Dynamic: author-email +Dynamic: classifier +Dynamic: description +Dynamic: description-content-type +Dynamic: home-page +Dynamic: license +Dynamic: summary + +pyNVML +====== + +Python bindings to the NVIDIA Management Library +------------------------------------------------ + +Provides a Python interface to GPU management and monitoring functions. + +This is a wrapper around the NVML library. +For information about the NVML library, see the NVML developer page +http://developer.nvidia.com/nvidia-management-library-nvml + +Download the latest package from: +http://pypi.python.org/pypi/nvidia-ml-py/ + +Note this file can be run with 'python -m doctest -v README.txt' +although the results are system dependent + +The nvml header file contains function documentation that is relevant +to this wrapper. The header file is distributed with. +https://developer.nvidia.com/gpu-deployment-kit + +The main difference is this library handles allocating structs and +passing pointers to the functions, before returning the desired value. +Non-success return codes are raised as exceptions as described in the +section below. + +REQUIRES +-------- +Python 2.5, or an earlier version with the ctypes module. + +INSTALLATION +------------ + +Pip Installation with python3: +- `python3 -m pip install nvidia-ml-py` + +Manual Installation: +``` +$ tar -xzf nvidia-ml-py-$major-$minor-$patch.tar.gz` +$ cd nvidia-ml-py-$major-$minor-$patch +$ sudo python setup.py install +``` + +USAGE +----- +``` +>>> from pynvml import * +>>> nvmlInit() +>>> print(f"Driver Version: {nvmlSystemGetDriverVersion()}") +Driver Version: 11.515.48 +>>> deviceCount = nvmlDeviceGetCount() +>>> for i in range(deviceCount): +... handle = nvmlDeviceGetHandleByIndex(i) +... print(f"Device {i} : {nvmlDeviceGetName(handle)}") +... +Device 0 : Tesla K40c + +>>> nvmlShutdown() +``` + +FUNCTIONS +--------- +Python methods wrap NVML functions, implemented in a C shared library. +Each function's use is the same with the following exceptions: + +- Instead of returning error codes, failing error codes are raised as Python exceptions. + +``` +>>> try: +... nvmlDeviceGetCount() +... except NVMLError as error: +... print(error) +... +Uninitialized +``` + +- C function output parameters are returned from the corresponding Python function left to right. +``` +nvmlReturn_t nvmlDeviceGetEccMode(nvmlDevice_t device, + nvmlEnableState_t *current, + nvmlEnableState_t *pending); + +>>> nvmlInit() +>>> handle = nvmlDeviceGetHandleByIndex(0) +>>> (current, pending) = nvmlDeviceGetEccMode(handle) +``` +- C structs are converted into Python classes. + +``` +// C Function and typedef struct +nvmlReturn_t DECLDIR nvmlDeviceGetMemoryInfo(nvmlDevice_t device, + nvmlMemory_t *memory); +typedef struct nvmlMemory_st { + unsigned long long total; + unsigned long long free; + unsigned long long used; +} nvmlMemory_t; + + +# Python call to function and accessing members of ctype struct +>>> info = nvmlDeviceGetMemoryInfo(handle) +>>> print(f"Total memory: {info.total}") +Total memory: 5636292608 +>>> print(f"Free memory:, {info.free}") +Free memory: 5578420224 +>>> print(f"Used memory: {info.used}") +Used memory: 57872384 +``` + +- Python handles string buffer creation. + +``` +// C Function that needs character array and length +nvmlReturn_t nvmlSystemGetDriverVersion(char* version, + unsigned int length); + +# Python function handles memory +>>> version = nvmlSystemGetDriverVersion() +>>> print(version) +... 11.520.75 +>>> nvmlShutdown() +``` + +For usage information see the NVML documentation. + +VARIABLES +--------- +All meaningful NVML constants and enums are exposed in Python. + +The NVML_VALUE_NOT_AVAILABLE constant is not used. Instead None is mapped to the field. + +EXCEPTIONS +---------- +Since the C library uses return codes and python prefers exception handling, the +library converts all return codes to various exceptions. The exceptions are generated +automatically via a function at run time instead of being defined manually. + +The list of exceptions can be found in NVMLError base class. + +The example seen above in the FUNCTIONS section: + +``` +>>> try: +... nvmlDeviceGetCount() +... except NVMLError as error: +... print(error) +... +Uninitialized +``` + +Can be more accurately caught like this: + +``` +>>> try: +... nvmlDeviceGetCount() +... except NVMLError_Uninitialized as error: +... print(error) +... +Uninitialized +``` + +The conversion from name to exception is like this for all exceptions: +* `NVML_ERROR_UNINITIALIZED` => `NVMLError_Uninitialized` +* `NVML_ERROR_LIBRARY_NOT_FOUND` => `NVMLError_LibraryNotFound` +* `NVML_ERROR_ALREADY_INITIALIZED` => `NVMLError_AlreadyInitialized` + +RELEASE NOTES +------------- +Version 2.285.0 +- Added new functions for NVML 2.285. See NVML documentation for more information. +- Ported to support Python 3.0 and Python 2.0 syntax. +- Added nvidia_smi.py tool as a sample app. + +Version 3.295.0 +- Added new functions for NVML 3.295. See NVML documentation for more information. +- Updated nvidia_smi.py tool +- Includes additional error handling + +Version 4.304.0 +- Added new functions for NVML 4.304. See NVML documentation for more information. +- Updated nvidia_smi.py tool + +Version 4.304.3 +- Fixing nvmlUnitGetDeviceCount bug + +Version 5.319.0 +- Added new functions for NVML 5.319. See NVML documentation for more information. + +Version 6.340.0 +- Added new functions for NVML 6.340. See NVML documentation for more information. + +Version 7.346.0 +- Added new functions for NVML 7.346. See NVML documentation for more information. + +Version 7.352.0 +- Added new functions for NVML 7.352. See NVML documentation for more information. + +Version 10.418 +- Added new functions for NVML 10.418. See NVML documentation for more information. +- Fixed issues with using the bindings with Python 3.x +- Replaced sample app nvidia_smi.py with example.py + +Version 11.515.48 +- Python3 support added +- Updated API to add function new to NVML, bringing pynvml up to date with NVML +- Added auto-version to handle byte and string conversion automatically for both structs and functions +- Minor bug fixes +- Added README.txt correctly in long_description for pypi.org + +Version 11.520 +- Updated Long Description to be actual markdown +- Added new functions for NVML 11.520 + +Version 11.525 +- Added new functions for NVML 11.525 + +COPYRIGHT +--------- +Copyright (c) 2011-2023, NVIDIA Corporation. All rights reserved. + +LICENSE +------- +Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met: + +- Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer. + +- Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution. + +- Neither the name of the NVIDIA Corporation nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + diff --git a/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/RECORD new file mode 100644 index 0000000..032584b --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/RECORD @@ -0,0 +1,10 @@ +__pycache__/example.cpython-312.pyc,, +__pycache__/pynvml.cpython-312.pyc,, +example.py,sha256=mDXwPVyEDuiKeMApEh53r_M36xuncmzMpFOGA3Q-_Kw,7968 +nvidia_ml_py-12.570.86.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +nvidia_ml_py-12.570.86.dist-info/METADATA,sha256=vY-jfk5MJsbWGy2jmbgdwfPKG4G0FHbspv-av_h5bEE,8718 +nvidia_ml_py-12.570.86.dist-info/RECORD,, +nvidia_ml_py-12.570.86.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +nvidia_ml_py-12.570.86.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91 +nvidia_ml_py-12.570.86.dist-info/top_level.txt,sha256=wLINSA1WKnhsGgKsb_nuj51ZCQrXaN5qhioTL56g98A,15 +pynvml.py,sha256=PCW5qJPhGshkIhIUOOQyUXsxkCVaPeTi30R7LsJb4YE,234473 diff --git a/llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/REQUESTED similarity index 100% rename from llmlab/lib/python3.12/site-packages/DateTime-5.5.dist-info/REQUESTED rename to llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/REQUESTED diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/WHEEL similarity index 65% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/WHEEL rename to llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/WHEEL index edf4ec7..505164b 100644 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/WHEEL +++ b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/WHEEL @@ -1,5 +1,5 @@ Wheel-Version: 1.0 -Generator: setuptools (70.1.1) +Generator: setuptools (75.8.0) Root-Is-Purelib: true Tag: py3-none-any diff --git a/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/top_level.txt new file mode 100644 index 0000000..32cd7dc --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/nvidia_ml_py-12.570.86.dist-info/top_level.txt @@ -0,0 +1,2 @@ +example +pynvml diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/RECORD deleted file mode 100644 index 378f1f6..0000000 --- a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/RECORD +++ /dev/null @@ -1,1005 +0,0 @@ -../../../bin/pip,sha256=ywE05nXg5nnGB7HQzx_iAZSEUjwcfYGI-8g76d7ytJ4,251 -../../../bin/pip3,sha256=ywE05nXg5nnGB7HQzx_iAZSEUjwcfYGI-8g76d7ytJ4,251 -../../../bin/pip3.12,sha256=ywE05nXg5nnGB7HQzx_iAZSEUjwcfYGI-8g76d7ytJ4,251 -pip-24.0.dist-info/AUTHORS.txt,sha256=SwXm4nkwRkmtnO1ZY-dLy7EPeoQNXMNLby5CN3GlNhY,10388 -pip-24.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -pip-24.0.dist-info/LICENSE.txt,sha256=Y0MApmnUmurmWxLGxIySTFGkzfPR_whtw0VtyLyqIQQ,1093 -pip-24.0.dist-info/METADATA,sha256=kNEfJ3_Vho2mee4lfJdlbd5RHIqsfQJSMUB-bOkIOeI,3581 -pip-24.0.dist-info/RECORD,, -pip-24.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip-24.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92 -pip-24.0.dist-info/entry_points.txt,sha256=Fa_c0b-xGFaYxagIruvpJD6qqXmNTA02vAVIkmMj-9o,125 -pip-24.0.dist-info/top_level.txt,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -pip/__init__.py,sha256=oAk1nFpLmUVS5Ln7NxvNoGUn5Vkn6FGQjPaNDf8Q8pk,355 -pip/__main__.py,sha256=WzbhHXTbSE6gBY19mNN9m4s5o_365LOvTYSgqgbdBhE,854 -pip/__pip-runner__.py,sha256=EnrfKmKMzWAdqg_JicLCOP9Y95Ux7zHh4ObvqLtQcjo,1444 -pip/__pycache__/__init__.cpython-312.pyc,, -pip/__pycache__/__main__.cpython-312.pyc,, -pip/__pycache__/__pip-runner__.cpython-312.pyc,, -pip/_internal/__init__.py,sha256=iqZ5-YQsQV08tkUc7L806Reop6tguLFWf70ySF6be0Y,515 -pip/_internal/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/__pycache__/build_env.cpython-312.pyc,, -pip/_internal/__pycache__/cache.cpython-312.pyc,, -pip/_internal/__pycache__/configuration.cpython-312.pyc,, -pip/_internal/__pycache__/exceptions.cpython-312.pyc,, -pip/_internal/__pycache__/main.cpython-312.pyc,, -pip/_internal/__pycache__/pyproject.cpython-312.pyc,, -pip/_internal/__pycache__/self_outdated_check.cpython-312.pyc,, -pip/_internal/__pycache__/wheel_builder.cpython-312.pyc,, -pip/_internal/build_env.py,sha256=1ESpqw0iupS_K7phZK5zshVE5Czy9BtGLFU4W6Enva8,10243 -pip/_internal/cache.py,sha256=uiYD-9F0Bv1C8ZyWE85lpzDmQf7hcUkgL99GmI8I41Q,10370 -pip/_internal/cli/__init__.py,sha256=FkHBgpxxb-_gd6r1FjnNhfMOzAUYyXoXKJ6abijfcFU,132 -pip/_internal/cli/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/cli/__pycache__/autocompletion.cpython-312.pyc,, -pip/_internal/cli/__pycache__/base_command.cpython-312.pyc,, -pip/_internal/cli/__pycache__/cmdoptions.cpython-312.pyc,, -pip/_internal/cli/__pycache__/command_context.cpython-312.pyc,, -pip/_internal/cli/__pycache__/main.cpython-312.pyc,, -pip/_internal/cli/__pycache__/main_parser.cpython-312.pyc,, -pip/_internal/cli/__pycache__/parser.cpython-312.pyc,, -pip/_internal/cli/__pycache__/progress_bars.cpython-312.pyc,, -pip/_internal/cli/__pycache__/req_command.cpython-312.pyc,, -pip/_internal/cli/__pycache__/spinners.cpython-312.pyc,, -pip/_internal/cli/__pycache__/status_codes.cpython-312.pyc,, -pip/_internal/cli/autocompletion.py,sha256=_br_5NgSxSuvPjMF0MLHzS5s6BpSkQAQHKrLK89VauM,6690 -pip/_internal/cli/base_command.py,sha256=iuVWGa2oTq7gBReo0er3Z0tXJ2oqBIC6QjDHcnDhKXY,8733 -pip/_internal/cli/cmdoptions.py,sha256=V8ggG6AtHpHKkH_6tRU0mhJaZTeqtrFpu75ghvMXXJk,30063 -pip/_internal/cli/command_context.py,sha256=RHgIPwtObh5KhMrd3YZTkl8zbVG-6Okml7YbFX4Ehg0,774 -pip/_internal/cli/main.py,sha256=Uzxt_YD1hIvB1AW5mxt6IVcht5G712AtMqdo51UMhmQ,2816 -pip/_internal/cli/main_parser.py,sha256=laDpsuBDl6kyfywp9eMMA9s84jfH2TJJn-vmL0GG90w,4338 -pip/_internal/cli/parser.py,sha256=KW6C3-7-4ErTNB0TfLTKwOdHcd-qefCeGnrOoE2r0RQ,10781 -pip/_internal/cli/progress_bars.py,sha256=So4mPoSjXkXiSHiTzzquH3VVyVD_njXlHJSExYPXAow,1968 -pip/_internal/cli/req_command.py,sha256=c7_XHABnXmD3_qlK9-r37KqdKBAcgmVKvQ2WcTrNLfc,18369 -pip/_internal/cli/spinners.py,sha256=hIJ83GerdFgFCdobIA23Jggetegl_uC4Sp586nzFbPE,5118 -pip/_internal/cli/status_codes.py,sha256=sEFHUaUJbqv8iArL3HAtcztWZmGOFX01hTesSytDEh0,116 -pip/_internal/commands/__init__.py,sha256=5oRO9O3dM2vGuh0bFw4HOVletryrz5HHMmmPWwJrH9U,3882 -pip/_internal/commands/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/commands/__pycache__/cache.cpython-312.pyc,, -pip/_internal/commands/__pycache__/check.cpython-312.pyc,, -pip/_internal/commands/__pycache__/completion.cpython-312.pyc,, -pip/_internal/commands/__pycache__/configuration.cpython-312.pyc,, -pip/_internal/commands/__pycache__/debug.cpython-312.pyc,, -pip/_internal/commands/__pycache__/download.cpython-312.pyc,, -pip/_internal/commands/__pycache__/freeze.cpython-312.pyc,, -pip/_internal/commands/__pycache__/hash.cpython-312.pyc,, -pip/_internal/commands/__pycache__/help.cpython-312.pyc,, -pip/_internal/commands/__pycache__/index.cpython-312.pyc,, -pip/_internal/commands/__pycache__/inspect.cpython-312.pyc,, -pip/_internal/commands/__pycache__/install.cpython-312.pyc,, -pip/_internal/commands/__pycache__/list.cpython-312.pyc,, -pip/_internal/commands/__pycache__/search.cpython-312.pyc,, -pip/_internal/commands/__pycache__/show.cpython-312.pyc,, -pip/_internal/commands/__pycache__/uninstall.cpython-312.pyc,, -pip/_internal/commands/__pycache__/wheel.cpython-312.pyc,, -pip/_internal/commands/cache.py,sha256=xg76_ZFEBC6zoQ3gXLRfMZJft4z2a0RwH4GEFZC6nnU,7944 -pip/_internal/commands/check.py,sha256=Rb13Q28yoLh0j1gpx5SU0jlResNct21eQCRsnaO9xKA,1782 -pip/_internal/commands/completion.py,sha256=HT4lD0bgsflHq2IDgYfiEdp7IGGtE7s6MgI3xn0VQEw,4287 -pip/_internal/commands/configuration.py,sha256=n98enwp6y0b5G6fiRQjaZo43FlJKYve_daMhN-4BRNc,9766 -pip/_internal/commands/debug.py,sha256=63972uUCeMIGOdMMVeIUGrOjTOqTVWplFC82a-hcKyA,6777 -pip/_internal/commands/download.py,sha256=e4hw088zGo26WmJaMIRvCniLlLmoOjqolGyfHjsCkCQ,5335 -pip/_internal/commands/freeze.py,sha256=qrIHS_-c6JPrQ92hMhAv9kkl0bHgFpRLwYJDdbcYr1o,3243 -pip/_internal/commands/hash.py,sha256=EVVOuvGtoPEdFi8SNnmdqlCQrhCxV-kJsdwtdcCnXGQ,1703 -pip/_internal/commands/help.py,sha256=gcc6QDkcgHMOuAn5UxaZwAStsRBrnGSn_yxjS57JIoM,1132 -pip/_internal/commands/index.py,sha256=CNXQer_PeZKSJooURcCFCBEKGfwyNoUWYP_MWczAcOM,4775 -pip/_internal/commands/inspect.py,sha256=2wSPt9yfr3r6g-s2S5L6PvRtaHNVyb4TuodMStJ39cw,3188 -pip/_internal/commands/install.py,sha256=VxDd-BD3a27ApeE2OK34rfBXS6Zo2wtemK9-HCwPqxM,28782 -pip/_internal/commands/list.py,sha256=-QbpPuGDiGN1SdThsk2ml8beBnepliefbGhMAN8tkzU,12547 -pip/_internal/commands/search.py,sha256=sbBZiARRc050QquOKcCvOr2K3XLsoYebLKZGRi__iUI,5697 -pip/_internal/commands/show.py,sha256=t5jia4zcYJRJZy4U_Von7zMl03hJmmcofj6oDNTnj7Y,6419 -pip/_internal/commands/uninstall.py,sha256=OIqO9tqadY8kM4HwhFf1Q62fUIp7v8KDrTRo8yWMz7Y,3886 -pip/_internal/commands/wheel.py,sha256=CSnX8Pmf1oPCnd7j7bn1_f58G9KHNiAblvVJ5zykN-A,6476 -pip/_internal/configuration.py,sha256=XkAiBS0hpzsM-LF0Qu5hvPWO_Bs67-oQKRYFBuMbESs,14006 -pip/_internal/distributions/__init__.py,sha256=Hq6kt6gXBgjNit5hTTWLAzeCNOKoB-N0pGYSqehrli8,858 -pip/_internal/distributions/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/distributions/__pycache__/base.cpython-312.pyc,, -pip/_internal/distributions/__pycache__/installed.cpython-312.pyc,, -pip/_internal/distributions/__pycache__/sdist.cpython-312.pyc,, -pip/_internal/distributions/__pycache__/wheel.cpython-312.pyc,, -pip/_internal/distributions/base.py,sha256=oRSEvnv2ZjBnargamnv2fcJa1n6gUDKaW0g6CWSEpWs,1743 -pip/_internal/distributions/installed.py,sha256=QinHFbWAQ8oE0pbD8MFZWkwlnfU1QYTccA1vnhrlYOU,842 -pip/_internal/distributions/sdist.py,sha256=4K3V0VNMllHbBzCJibjwd_tylUKpmIdu2AQyhplvCQo,6709 -pip/_internal/distributions/wheel.py,sha256=-ma3sOtUQj0AxXCEb6_Fhmjl3nh4k3A0HC2taAb2N-4,1277 -pip/_internal/exceptions.py,sha256=TmF1iNFEneSWaemwlg6a5bpPuq2cMHK7d1-SvjsQHb0,23634 -pip/_internal/index/__init__.py,sha256=vpt-JeTZefh8a-FC22ZeBSXFVbuBcXSGiILhQZJaNpQ,30 -pip/_internal/index/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/index/__pycache__/collector.cpython-312.pyc,, -pip/_internal/index/__pycache__/package_finder.cpython-312.pyc,, -pip/_internal/index/__pycache__/sources.cpython-312.pyc,, -pip/_internal/index/collector.py,sha256=sH0tL_cOoCk6pLLfCSGVjFM4rPEJtllF-VobvAvLSH4,16590 -pip/_internal/index/package_finder.py,sha256=S_nC8gzVIMY6ikWfKoSOzRtoesUqnfNhAPl_BwSOusA,37843 -pip/_internal/index/sources.py,sha256=dJegiR9f86kslaAHcv9-R5L_XBf5Rzm_FkyPteDuPxI,8688 -pip/_internal/locations/__init__.py,sha256=Dh8LJWG8LRlDK4JIj9sfRF96TREzE--N_AIlx7Tqoe4,15365 -pip/_internal/locations/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/locations/__pycache__/_distutils.cpython-312.pyc,, -pip/_internal/locations/__pycache__/_sysconfig.cpython-312.pyc,, -pip/_internal/locations/__pycache__/base.cpython-312.pyc,, -pip/_internal/locations/_distutils.py,sha256=H9ZHK_35rdDV1Qsmi4QeaBULjFT4Mbu6QuoVGkJ6QHI,6009 -pip/_internal/locations/_sysconfig.py,sha256=jyNVtUfMIf0mtyY-Xp1m9yQ8iwECozSVVFmjkN9a2yw,7680 -pip/_internal/locations/base.py,sha256=RQiPi1d4FVM2Bxk04dQhXZ2PqkeljEL2fZZ9SYqIQ78,2556 -pip/_internal/main.py,sha256=r-UnUe8HLo5XFJz8inTcOOTiu_sxNhgHb6VwlGUllOI,340 -pip/_internal/metadata/__init__.py,sha256=9pU3W3s-6HtjFuYhWcLTYVmSaziklPv7k2x8p7X1GmA,4339 -pip/_internal/metadata/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/metadata/__pycache__/_json.cpython-312.pyc,, -pip/_internal/metadata/__pycache__/base.cpython-312.pyc,, -pip/_internal/metadata/__pycache__/pkg_resources.cpython-312.pyc,, -pip/_internal/metadata/_json.py,sha256=Rz5M5ciSNvITwaTQR6NfN8TgKgM5WfTws4D6CFknovE,2627 -pip/_internal/metadata/base.py,sha256=l3Wgku4xlgr8s4p6fS-3qQ4QKOpPbWLRwi5d9omEFG4,25907 -pip/_internal/metadata/importlib/__init__.py,sha256=jUUidoxnHcfITHHaAWG1G2i5fdBYklv_uJcjo2x7VYE,135 -pip/_internal/metadata/importlib/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/metadata/importlib/__pycache__/_compat.cpython-312.pyc,, -pip/_internal/metadata/importlib/__pycache__/_dists.cpython-312.pyc,, -pip/_internal/metadata/importlib/__pycache__/_envs.cpython-312.pyc,, -pip/_internal/metadata/importlib/_compat.py,sha256=GAe_prIfCE4iUylrnr_2dJRlkkBVRUbOidEoID7LPoE,1882 -pip/_internal/metadata/importlib/_dists.py,sha256=UPl1wUujFqiwiltRJ1tMF42WRINO1sSpNNlYQ2mX0mk,8297 -pip/_internal/metadata/importlib/_envs.py,sha256=XTaFIYERP2JF0QUZuPx2ETiugXbPEcZ8q8ZKeht6Lpc,7456 -pip/_internal/metadata/pkg_resources.py,sha256=opjw4IBSqHvie6sXJ_cbT42meygoPEUfNURJuWZY7sk,10035 -pip/_internal/models/__init__.py,sha256=3DHUd_qxpPozfzouoqa9g9ts1Czr5qaHfFxbnxriepM,63 -pip/_internal/models/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/models/__pycache__/candidate.cpython-312.pyc,, -pip/_internal/models/__pycache__/direct_url.cpython-312.pyc,, -pip/_internal/models/__pycache__/format_control.cpython-312.pyc,, -pip/_internal/models/__pycache__/index.cpython-312.pyc,, -pip/_internal/models/__pycache__/installation_report.cpython-312.pyc,, -pip/_internal/models/__pycache__/link.cpython-312.pyc,, -pip/_internal/models/__pycache__/scheme.cpython-312.pyc,, -pip/_internal/models/__pycache__/search_scope.cpython-312.pyc,, -pip/_internal/models/__pycache__/selection_prefs.cpython-312.pyc,, -pip/_internal/models/__pycache__/target_python.cpython-312.pyc,, -pip/_internal/models/__pycache__/wheel.cpython-312.pyc,, -pip/_internal/models/candidate.py,sha256=hEPu8VdGE5qVASv6vLz-R-Rgh5-7LMbai1jgthMCd8M,931 -pip/_internal/models/direct_url.py,sha256=FwouYBKcqckh7B-k2H3HVgRhhFTukFwqiS3kfvtFLSk,6889 -pip/_internal/models/format_control.py,sha256=wtsQqSK9HaUiNxQEuB-C62eVimw6G4_VQFxV9-_KDBE,2486 -pip/_internal/models/index.py,sha256=tYnL8oxGi4aSNWur0mG8DAP7rC6yuha_MwJO8xw0crI,1030 -pip/_internal/models/installation_report.py,sha256=zRVZoaz-2vsrezj_H3hLOhMZCK9c7TbzWgC-jOalD00,2818 -pip/_internal/models/link.py,sha256=XirOAGv1jgMu7vu87kuPbohGj7VHpwVrd2q3KUgVQNg,20777 -pip/_internal/models/scheme.py,sha256=3EFQp_ICu_shH1-TBqhl0QAusKCPDFOlgHFeN4XowWs,738 -pip/_internal/models/search_scope.py,sha256=ASVyyZxiJILw7bTIVVpJx8J293M3Hk5F33ilGn0e80c,4643 -pip/_internal/models/selection_prefs.py,sha256=KZdi66gsR-_RUXUr9uejssk3rmTHrQVJWeNA2sV-VSY,1907 -pip/_internal/models/target_python.py,sha256=34EkorrMuRvRp-bjqHKJ-bOO71m9xdjN2b8WWFEC2HU,4272 -pip/_internal/models/wheel.py,sha256=YqazoIZyma_Q1ejFa1C7NHKQRRWlvWkdK96VRKmDBeI,3600 -pip/_internal/network/__init__.py,sha256=jf6Tt5nV_7zkARBrKojIXItgejvoegVJVKUbhAa5Ioc,50 -pip/_internal/network/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/network/__pycache__/auth.cpython-312.pyc,, -pip/_internal/network/__pycache__/cache.cpython-312.pyc,, -pip/_internal/network/__pycache__/download.cpython-312.pyc,, -pip/_internal/network/__pycache__/lazy_wheel.cpython-312.pyc,, -pip/_internal/network/__pycache__/session.cpython-312.pyc,, -pip/_internal/network/__pycache__/utils.cpython-312.pyc,, -pip/_internal/network/__pycache__/xmlrpc.cpython-312.pyc,, -pip/_internal/network/auth.py,sha256=TC-OcW2KU4W6R1hU4qPgQXvVH54adACpZz6sWq-R9NA,20541 -pip/_internal/network/cache.py,sha256=48A971qCzKNFvkb57uGEk7-0xaqPS0HWj2711QNTxkU,3935 -pip/_internal/network/download.py,sha256=i0Tn55CD5D7XYEFY3TxiYaCf0OaaTQ6SScNgCsSeV14,6086 -pip/_internal/network/lazy_wheel.py,sha256=2PXVduYZPCPZkkQFe1J1GbfHJWeCU--FXonGyIfw9eU,7638 -pip/_internal/network/session.py,sha256=9tqEDD8JiVaFdplOEXJxNo9cjRfBZ6RIa0yQQ_qBNiM,18698 -pip/_internal/network/utils.py,sha256=6A5SrUJEEUHxbGtbscwU2NpCyz-3ztiDlGWHpRRhsJ8,4073 -pip/_internal/network/xmlrpc.py,sha256=sAxzOacJ-N1NXGPvap9jC3zuYWSnnv3GXtgR2-E2APA,1838 -pip/_internal/operations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_internal/operations/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/operations/__pycache__/check.cpython-312.pyc,, -pip/_internal/operations/__pycache__/freeze.cpython-312.pyc,, -pip/_internal/operations/__pycache__/prepare.cpython-312.pyc,, -pip/_internal/operations/build/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_internal/operations/build/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/operations/build/__pycache__/build_tracker.cpython-312.pyc,, -pip/_internal/operations/build/__pycache__/metadata.cpython-312.pyc,, -pip/_internal/operations/build/__pycache__/metadata_editable.cpython-312.pyc,, -pip/_internal/operations/build/__pycache__/metadata_legacy.cpython-312.pyc,, -pip/_internal/operations/build/__pycache__/wheel.cpython-312.pyc,, -pip/_internal/operations/build/__pycache__/wheel_editable.cpython-312.pyc,, -pip/_internal/operations/build/__pycache__/wheel_legacy.cpython-312.pyc,, -pip/_internal/operations/build/build_tracker.py,sha256=z-H5DOknZdBa3dh2Vq6VBMY5qLYIKmlj2p6CGZK5Lc8,4832 -pip/_internal/operations/build/metadata.py,sha256=9S0CUD8U3QqZeXp-Zyt8HxwU90lE4QrnYDgrqZDzBnc,1422 -pip/_internal/operations/build/metadata_editable.py,sha256=VLL7LvntKE8qxdhUdEJhcotFzUsOSI8NNS043xULKew,1474 -pip/_internal/operations/build/metadata_legacy.py,sha256=o-eU21As175hDC7dluM1fJJ_FqokTIShyWpjKaIpHZw,2198 -pip/_internal/operations/build/wheel.py,sha256=sT12FBLAxDC6wyrDorh8kvcZ1jG5qInCRWzzP-UkJiQ,1075 -pip/_internal/operations/build/wheel_editable.py,sha256=yOtoH6zpAkoKYEUtr8FhzrYnkNHQaQBjWQ2HYae1MQg,1417 -pip/_internal/operations/build/wheel_legacy.py,sha256=C9j6rukgQI1n_JeQLoZGuDdfUwzCXShyIdPTp6edbMQ,3064 -pip/_internal/operations/check.py,sha256=fsqA88iGaqftCr2tlP3sSU202CSkoODRtW0O-JU9M4Y,6806 -pip/_internal/operations/freeze.py,sha256=uqoeTAf6HOYVMR2UgAT8N85UZoGEVEoQdan_Ao6SOfk,9816 -pip/_internal/operations/install/__init__.py,sha256=mX7hyD2GNBO2mFGokDQ30r_GXv7Y_PLdtxcUv144e-s,51 -pip/_internal/operations/install/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/operations/install/__pycache__/editable_legacy.cpython-312.pyc,, -pip/_internal/operations/install/__pycache__/wheel.cpython-312.pyc,, -pip/_internal/operations/install/editable_legacy.py,sha256=YeR0KadWXw_ZheC1NtAG1qVIEkOgRGHc23x-YtGW7NU,1282 -pip/_internal/operations/install/wheel.py,sha256=9hGb1c4bRnPIb2FG7CtUSPfPxqprmHQBtwIAlWPNTtE,27311 -pip/_internal/operations/prepare.py,sha256=57Oq87HfunX3Rbqp47FdaJr9cHbAKUm_3gv7WhBAqbE,28128 -pip/_internal/pyproject.py,sha256=4Xszp11xgr126yzG6BbJA0oaQ9WXuhb0jyUb-y_6lPQ,7152 -pip/_internal/req/__init__.py,sha256=TELFgZOof3lhMmaICVWL9U7PlhXo9OufokbMAJ6J2GI,2738 -pip/_internal/req/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/req/__pycache__/constructors.cpython-312.pyc,, -pip/_internal/req/__pycache__/req_file.cpython-312.pyc,, -pip/_internal/req/__pycache__/req_install.cpython-312.pyc,, -pip/_internal/req/__pycache__/req_set.cpython-312.pyc,, -pip/_internal/req/__pycache__/req_uninstall.cpython-312.pyc,, -pip/_internal/req/constructors.py,sha256=8hlY56imEthLORRwmloyKz3YOyXymIaKsNB6P9ewvNI,19018 -pip/_internal/req/req_file.py,sha256=M8ttOZL-PwAj7scPElhW3ZD2hiD9mm_6FJAGIbwAzEI,17790 -pip/_internal/req/req_install.py,sha256=wtOPxkyRSM8comTks8oL1Gp2oyGqbH7JwIDRci2QiPk,35460 -pip/_internal/req/req_set.py,sha256=iMYDUToSgkxFyrP_OrTtPSgw4dwjRyGRDpGooTqeA4Y,4704 -pip/_internal/req/req_uninstall.py,sha256=nmvTQaRCC0iu-5Tw0djlXJhSj6WmqHRvT3qkkEdC35E,24551 -pip/_internal/resolution/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_internal/resolution/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/resolution/__pycache__/base.cpython-312.pyc,, -pip/_internal/resolution/base.py,sha256=qlmh325SBVfvG6Me9gc5Nsh5sdwHBwzHBq6aEXtKsLA,583 -pip/_internal/resolution/legacy/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_internal/resolution/legacy/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/resolution/legacy/__pycache__/resolver.cpython-312.pyc,, -pip/_internal/resolution/legacy/resolver.py,sha256=Xk24jQ62GvLr4Mc7IjN_qiO88qp0BImzVmPIFz9QLOE,24025 -pip/_internal/resolution/resolvelib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_internal/resolution/resolvelib/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/base.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/candidates.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/factory.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/found_candidates.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/provider.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/reporter.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/requirements.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/__pycache__/resolver.cpython-312.pyc,, -pip/_internal/resolution/resolvelib/base.py,sha256=jg5COmHLhmBIKOR-4spdJD3jyULYa1BdsqiBu2YJnJ4,5173 -pip/_internal/resolution/resolvelib/candidates.py,sha256=19Ki91Po-MSxBknGIfOGkaWkFdOznN0W_nKv7jL28L0,21052 -pip/_internal/resolution/resolvelib/factory.py,sha256=vqqk-hjchdhShwWVdeW2_A-5ZblLhE_nC_v3Mhz4Svc,32292 -pip/_internal/resolution/resolvelib/found_candidates.py,sha256=hvL3Hoa9VaYo-qEOZkBi2Iqw251UDxPz-uMHVaWmLpE,5705 -pip/_internal/resolution/resolvelib/provider.py,sha256=4t23ivjruqM6hKBX1KpGiTt-M4HGhRcZnGLV0c01K7U,9824 -pip/_internal/resolution/resolvelib/reporter.py,sha256=YFm9hQvz4DFCbjZeFTQ56hTz3Ac-mDBnHkeNRVvMHLY,3100 -pip/_internal/resolution/resolvelib/requirements.py,sha256=-kJONP0WjDfdTvBAs2vUXPgAnOyNIBEAXY4b72ogtPE,5696 -pip/_internal/resolution/resolvelib/resolver.py,sha256=nLJOsVMEVi2gQUVJoUFKMZAeu2f7GRMjGMvNSWyz0Bc,12592 -pip/_internal/self_outdated_check.py,sha256=saxQLB8UzIFtMScquytG10TOTsYVFJQ_mkW1NY-46wE,8378 -pip/_internal/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_internal/utils/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/utils/__pycache__/_jaraco_text.cpython-312.pyc,, -pip/_internal/utils/__pycache__/_log.cpython-312.pyc,, -pip/_internal/utils/__pycache__/appdirs.cpython-312.pyc,, -pip/_internal/utils/__pycache__/compat.cpython-312.pyc,, -pip/_internal/utils/__pycache__/compatibility_tags.cpython-312.pyc,, -pip/_internal/utils/__pycache__/datetime.cpython-312.pyc,, -pip/_internal/utils/__pycache__/deprecation.cpython-312.pyc,, -pip/_internal/utils/__pycache__/direct_url_helpers.cpython-312.pyc,, -pip/_internal/utils/__pycache__/egg_link.cpython-312.pyc,, -pip/_internal/utils/__pycache__/encoding.cpython-312.pyc,, -pip/_internal/utils/__pycache__/entrypoints.cpython-312.pyc,, -pip/_internal/utils/__pycache__/filesystem.cpython-312.pyc,, -pip/_internal/utils/__pycache__/filetypes.cpython-312.pyc,, -pip/_internal/utils/__pycache__/glibc.cpython-312.pyc,, -pip/_internal/utils/__pycache__/hashes.cpython-312.pyc,, -pip/_internal/utils/__pycache__/logging.cpython-312.pyc,, -pip/_internal/utils/__pycache__/misc.cpython-312.pyc,, -pip/_internal/utils/__pycache__/models.cpython-312.pyc,, -pip/_internal/utils/__pycache__/packaging.cpython-312.pyc,, -pip/_internal/utils/__pycache__/setuptools_build.cpython-312.pyc,, -pip/_internal/utils/__pycache__/subprocess.cpython-312.pyc,, -pip/_internal/utils/__pycache__/temp_dir.cpython-312.pyc,, -pip/_internal/utils/__pycache__/unpacking.cpython-312.pyc,, -pip/_internal/utils/__pycache__/urls.cpython-312.pyc,, -pip/_internal/utils/__pycache__/virtualenv.cpython-312.pyc,, -pip/_internal/utils/__pycache__/wheel.cpython-312.pyc,, -pip/_internal/utils/_jaraco_text.py,sha256=yvDGelTVugRayPaOF2k4ab0Ky4d3uOkAfuOQjASjImY,3351 -pip/_internal/utils/_log.py,sha256=-jHLOE_THaZz5BFcCnoSL9EYAtJ0nXem49s9of4jvKw,1015 -pip/_internal/utils/appdirs.py,sha256=swgcTKOm3daLeXTW6v5BUS2Ti2RvEnGRQYH_yDXklAo,1665 -pip/_internal/utils/compat.py,sha256=ACyBfLgj3_XG-iA5omEDrXqDM0cQKzi8h8HRBInzG6Q,1884 -pip/_internal/utils/compatibility_tags.py,sha256=ydin8QG8BHqYRsPY4OL6cmb44CbqXl1T0xxS97VhHkk,5377 -pip/_internal/utils/datetime.py,sha256=m21Y3wAtQc-ji6Veb6k_M5g6A0ZyFI4egchTdnwh-pQ,242 -pip/_internal/utils/deprecation.py,sha256=NKo8VqLioJ4nnXXGmW4KdasxF90EFHkZaHeX1fT08C8,3627 -pip/_internal/utils/direct_url_helpers.py,sha256=6F1tc2rcKaCZmgfVwsE6ObIe_Pux23mUVYA-2D9wCFc,3206 -pip/_internal/utils/egg_link.py,sha256=0FePZoUYKv4RGQ2t6x7w5Z427wbA_Uo3WZnAkrgsuqo,2463 -pip/_internal/utils/encoding.py,sha256=qqsXDtiwMIjXMEiIVSaOjwH5YmirCaK-dIzb6-XJsL0,1169 -pip/_internal/utils/entrypoints.py,sha256=YlhLTRl2oHBAuqhc-zmL7USS67TPWVHImjeAQHreZTQ,3064 -pip/_internal/utils/filesystem.py,sha256=RhMIXUaNVMGjc3rhsDahWQ4MavvEQDdqXqgq-F6fpw8,5122 -pip/_internal/utils/filetypes.py,sha256=i8XAQ0eFCog26Fw9yV0Yb1ygAqKYB1w9Cz9n0fj8gZU,716 -pip/_internal/utils/glibc.py,sha256=Mesxxgg3BLxheLZx-dSf30b6gKpOgdVXw6W--uHSszQ,3113 -pip/_internal/utils/hashes.py,sha256=MjOigC75z6qoRMkgHiHqot7eqxfwDZSrEflJMPm-bHE,5118 -pip/_internal/utils/logging.py,sha256=fdtuZJ-AKkqwDTANDvGcBEpssL8el7T1jnwk1CnZl3Y,11603 -pip/_internal/utils/misc.py,sha256=fNXwaeeikvnUt4CPMFIL4-IQbZDxxjj4jDpzCi4ZsOw,23623 -pip/_internal/utils/models.py,sha256=5GoYU586SrxURMvDn_jBMJInitviJg4O5-iOU-6I0WY,1193 -pip/_internal/utils/packaging.py,sha256=5Wm6_x7lKrlqVjPI5MBN_RurcRHwVYoQ7Ksrs84de7s,2108 -pip/_internal/utils/setuptools_build.py,sha256=ouXpud-jeS8xPyTPsXJ-m34NPvK5os45otAzdSV_IJE,4435 -pip/_internal/utils/subprocess.py,sha256=zzdimb75jVLE1GU4WlTZ055gczhD7n1y1xTcNc7vNZQ,9207 -pip/_internal/utils/temp_dir.py,sha256=DUAw22uFruQdK43i2L2K53C-CDjRCPeAsBKJpu-rHQ4,9312 -pip/_internal/utils/unpacking.py,sha256=SBb2iV1crb89MDRTEKY86R4A_UOWApTQn9VQVcMDOlE,8821 -pip/_internal/utils/urls.py,sha256=AhaesUGl-9it6uvG6fsFPOr9ynFpGaTMk4t5XTX7Z_Q,1759 -pip/_internal/utils/virtualenv.py,sha256=S6f7csYorRpiD6cvn3jISZYc3I8PJC43H5iMFpRAEDU,3456 -pip/_internal/utils/wheel.py,sha256=i4BwUNHattzN0ixy3HBAF04tZPRh2CcxaT6t86viwkE,4499 -pip/_internal/vcs/__init__.py,sha256=UAqvzpbi0VbZo3Ub6skEeZAw-ooIZR-zX_WpCbxyCoU,596 -pip/_internal/vcs/__pycache__/__init__.cpython-312.pyc,, -pip/_internal/vcs/__pycache__/bazaar.cpython-312.pyc,, -pip/_internal/vcs/__pycache__/git.cpython-312.pyc,, -pip/_internal/vcs/__pycache__/mercurial.cpython-312.pyc,, -pip/_internal/vcs/__pycache__/subversion.cpython-312.pyc,, -pip/_internal/vcs/__pycache__/versioncontrol.cpython-312.pyc,, -pip/_internal/vcs/bazaar.py,sha256=j0oin0fpGRHcCFCxEcpPCQoFEvA-DMLULKdGP8Nv76o,3519 -pip/_internal/vcs/git.py,sha256=CeKBGJnl6uskvvjkAUXrJVxbHJrpS_B_pyfFdjL3CRc,18121 -pip/_internal/vcs/mercurial.py,sha256=oULOhzJ2Uie-06d1omkL-_Gc6meGaUkyogvqG9ZCyPs,5249 -pip/_internal/vcs/subversion.py,sha256=vhZs8L-TNggXqM1bbhl-FpbxE3TrIB6Tgnx8fh3S2HE,11729 -pip/_internal/vcs/versioncontrol.py,sha256=3eIjtOMYvOY5qP6BMYIYDZ375CSuec6kSEB0bOo1cSs,22787 -pip/_internal/wheel_builder.py,sha256=qTTzQV8F6b1jNsFCda1TRQC8J7gK-m7iuRNgKo7Dj68,11801 -pip/_vendor/__init__.py,sha256=U51NPwXdA-wXOiANIQncYjcMp6txgeOL5nHxksJeyas,4993 -pip/_vendor/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/__pycache__/six.cpython-312.pyc,, -pip/_vendor/__pycache__/typing_extensions.cpython-312.pyc,, -pip/_vendor/cachecontrol/__init__.py,sha256=ctHagMhQXuvQDdm4TirZrwDOT5H8oBNAJqzdKI6sovk,676 -pip/_vendor/cachecontrol/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/_cmd.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/adapter.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/cache.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/controller.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/filewrapper.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/heuristics.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/serialize.cpython-312.pyc,, -pip/_vendor/cachecontrol/__pycache__/wrapper.cpython-312.pyc,, -pip/_vendor/cachecontrol/_cmd.py,sha256=iist2EpzJvDVIhMAxXq8iFnTBsiZAd6iplxfmNboNyk,1737 -pip/_vendor/cachecontrol/adapter.py,sha256=_CcWvUP9048qAZjsNqViaHbdcLs9mmFNixVfpO7oebE,6392 -pip/_vendor/cachecontrol/cache.py,sha256=OTQj72tUf8C1uEgczdl3Gc8vkldSzsTITKtDGKMx4z8,1952 -pip/_vendor/cachecontrol/caches/__init__.py,sha256=dtrrroK5BnADR1GWjCZ19aZ0tFsMfvFBtLQQU1sp_ag,303 -pip/_vendor/cachecontrol/caches/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/cachecontrol/caches/__pycache__/file_cache.cpython-312.pyc,, -pip/_vendor/cachecontrol/caches/__pycache__/redis_cache.cpython-312.pyc,, -pip/_vendor/cachecontrol/caches/file_cache.py,sha256=3z8AWKD-vfKeiJqIzLmJyIYtR2yd6Tsh3u1TyLRQoIQ,5352 -pip/_vendor/cachecontrol/caches/redis_cache.py,sha256=9rmqwtYu_ljVkW6_oLqbC7EaX_a8YT_yLuna-eS0dgo,1386 -pip/_vendor/cachecontrol/controller.py,sha256=keCFA3ZaNVaWTwHd6F1zqWhb4vyvNx_UvZuo5iIYMfo,18384 -pip/_vendor/cachecontrol/filewrapper.py,sha256=STttGmIPBvZzt2b51dUOwoWX5crcMCpKZOisM3f5BNc,4292 -pip/_vendor/cachecontrol/heuristics.py,sha256=fdFbk9W8IeLrjteIz_fK4mj2HD_Y7COXF2Uc8TgjT1c,4828 -pip/_vendor/cachecontrol/serialize.py,sha256=0dHeMaDwysVAAnGVlhMOP4tDliohgNK0Jxk_zsOiWxw,7173 -pip/_vendor/cachecontrol/wrapper.py,sha256=hsGc7g8QGQTT-4f8tgz3AM5qwScg6FO0BSdLSRdEvpU,1417 -pip/_vendor/certifi/__init__.py,sha256=L_j-d0kYuA_MzA2_2hraF1ovf6KT6DTquRdV3paQwOk,94 -pip/_vendor/certifi/__main__.py,sha256=1k3Cr95vCxxGRGDljrW3wMdpZdL3Nhf0u1n-k2qdsCY,255 -pip/_vendor/certifi/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/certifi/__pycache__/__main__.cpython-312.pyc,, -pip/_vendor/certifi/__pycache__/core.cpython-312.pyc,, -pip/_vendor/certifi/cacert.pem,sha256=eU0Dn_3yd8BH4m8sfVj4Glhl2KDrcCSg-sEWT-pNJ88,281617 -pip/_vendor/certifi/core.py,sha256=DNTl8b_B6C4vO3Vc9_q2uvwHpNnBQoy5onDC4McImxc,4531 -pip/_vendor/chardet/__init__.py,sha256=57R-HSxj0PWmILMN0GFmUNqEMfrEVSamXyjD-W6_fbs,4797 -pip/_vendor/chardet/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/big5freq.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/big5prober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/chardistribution.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/charsetgroupprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/charsetprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/codingstatemachine.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/codingstatemachinedict.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/cp949prober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/enums.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/escprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/escsm.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/eucjpprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/euckrfreq.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/euckrprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/euctwfreq.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/euctwprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/gb2312freq.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/gb2312prober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/hebrewprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/jisfreq.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/johabfreq.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/johabprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/jpcntx.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/langbulgarianmodel.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/langgreekmodel.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/langhebrewmodel.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/langhungarianmodel.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/langrussianmodel.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/langthaimodel.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/langturkishmodel.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/latin1prober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/macromanprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/mbcharsetprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/mbcsgroupprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/mbcssm.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/resultdict.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/sbcharsetprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/sbcsgroupprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/sjisprober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/universaldetector.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/utf1632prober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/utf8prober.cpython-312.pyc,, -pip/_vendor/chardet/__pycache__/version.cpython-312.pyc,, -pip/_vendor/chardet/big5freq.py,sha256=ltcfP-3PjlNHCoo5e4a7C4z-2DhBTXRfY6jbMbB7P30,31274 -pip/_vendor/chardet/big5prober.py,sha256=lPMfwCX6v2AaPgvFh_cSWZcgLDbWiFCHLZ_p9RQ9uxE,1763 -pip/_vendor/chardet/chardistribution.py,sha256=13B8XUG4oXDuLdXvfbIWwLFeR-ZU21AqTS1zcdON8bU,10032 -pip/_vendor/chardet/charsetgroupprober.py,sha256=UKK3SaIZB2PCdKSIS0gnvMtLR9JJX62M-fZJu3OlWyg,3915 -pip/_vendor/chardet/charsetprober.py,sha256=L3t8_wIOov8em-vZWOcbkdsrwe43N6_gqNh5pH7WPd4,5420 -pip/_vendor/chardet/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_vendor/chardet/cli/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/chardet/cli/__pycache__/chardetect.cpython-312.pyc,, -pip/_vendor/chardet/cli/chardetect.py,sha256=zibMVg5RpKb-ME9_7EYG4ZM2Sf07NHcQzZ12U-rYJho,3242 -pip/_vendor/chardet/codingstatemachine.py,sha256=K7k69sw3jY5DmTXoSJQVsUtFIQKYPQVOSJJhBuGv_yE,3732 -pip/_vendor/chardet/codingstatemachinedict.py,sha256=0GY3Hi2qIZvDrOOJ3AtqppM1RsYxr_66ER4EHjuMiMc,542 -pip/_vendor/chardet/cp949prober.py,sha256=0jKRV7fECuWI16rNnks0ZECKA1iZYCIEaP8A1ZvjUSI,1860 -pip/_vendor/chardet/enums.py,sha256=TzECiZoCKNMqgwU76cPCeKWFBqaWvAdLMev5_bCkhY8,1683 -pip/_vendor/chardet/escprober.py,sha256=Kho48X65xE0scFylIdeJjM2bcbvRvv0h0WUbMWrJD3A,4006 -pip/_vendor/chardet/escsm.py,sha256=AqyXpA2FQFD7k-buBty_7itGEYkhmVa8X09NLRul3QM,12176 -pip/_vendor/chardet/eucjpprober.py,sha256=5KYaM9fsxkRYzw1b5k0fL-j_-ezIw-ij9r97a9MHxLY,3934 -pip/_vendor/chardet/euckrfreq.py,sha256=3mHuRvXfsq_QcQysDQFb8qSudvTiol71C6Ic2w57tKM,13566 -pip/_vendor/chardet/euckrprober.py,sha256=hiFT6wM174GIwRvqDsIcuOc-dDsq2uPKMKbyV8-1Xnc,1753 -pip/_vendor/chardet/euctwfreq.py,sha256=2alILE1Lh5eqiFJZjzRkMQXolNJRHY5oBQd-vmZYFFM,36913 -pip/_vendor/chardet/euctwprober.py,sha256=NxbpNdBtU0VFI0bKfGfDkpP7S2_8_6FlO87dVH0ogws,1753 -pip/_vendor/chardet/gb2312freq.py,sha256=49OrdXzD-HXqwavkqjo8Z7gvs58hONNzDhAyMENNkvY,20735 -pip/_vendor/chardet/gb2312prober.py,sha256=KPEBueaSLSvBpFeINMu0D6TgHcR90e5PaQawifzF4o0,1759 -pip/_vendor/chardet/hebrewprober.py,sha256=96T_Lj_OmW-fK7JrSHojYjyG3fsGgbzkoTNleZ3kfYE,14537 -pip/_vendor/chardet/jisfreq.py,sha256=mm8tfrwqhpOd3wzZKS4NJqkYBQVcDfTM2JiQ5aW932E,25796 -pip/_vendor/chardet/johabfreq.py,sha256=dBpOYG34GRX6SL8k_LbS9rxZPMjLjoMlgZ03Pz5Hmqc,42498 -pip/_vendor/chardet/johabprober.py,sha256=O1Qw9nVzRnun7vZp4UZM7wvJSv9W941mEU9uDMnY3DU,1752 -pip/_vendor/chardet/jpcntx.py,sha256=uhHrYWkLxE_rF5OkHKInm0HUsrjgKHHVQvtt3UcvotA,27055 -pip/_vendor/chardet/langbulgarianmodel.py,sha256=vmbvYFP8SZkSxoBvLkFqKiH1sjma5ihk3PTpdy71Rr4,104562 -pip/_vendor/chardet/langgreekmodel.py,sha256=JfB7bupjjJH2w3X_mYnQr9cJA_7EuITC2cRW13fUjeI,98484 -pip/_vendor/chardet/langhebrewmodel.py,sha256=3HXHaLQPNAGcXnJjkIJfozNZLTvTJmf4W5Awi6zRRKc,98196 -pip/_vendor/chardet/langhungarianmodel.py,sha256=WxbeQIxkv8YtApiNqxQcvj-tMycsoI4Xy-fwkDHpP_Y,101363 -pip/_vendor/chardet/langrussianmodel.py,sha256=s395bTZ87ESTrZCOdgXbEjZ9P1iGPwCl_8xSsac_DLY,128035 -pip/_vendor/chardet/langthaimodel.py,sha256=7bJlQitRpTnVGABmbSznHnJwOHDy3InkTvtFUx13WQI,102774 -pip/_vendor/chardet/langturkishmodel.py,sha256=XY0eGdTIy4eQ9Xg1LVPZacb-UBhHBR-cq0IpPVHowKc,95372 -pip/_vendor/chardet/latin1prober.py,sha256=p15EEmFbmQUwbKLC7lOJVGHEZwcG45ubEZYTGu01J5g,5380 -pip/_vendor/chardet/macromanprober.py,sha256=9anfzmY6TBfUPDyBDOdY07kqmTHpZ1tK0jL-p1JWcOY,6077 -pip/_vendor/chardet/mbcharsetprober.py,sha256=Wr04WNI4F3X_VxEverNG-H25g7u-MDDKlNt-JGj-_uU,3715 -pip/_vendor/chardet/mbcsgroupprober.py,sha256=iRpaNBjV0DNwYPu_z6TiHgRpwYahiM7ztI_4kZ4Uz9A,2131 -pip/_vendor/chardet/mbcssm.py,sha256=hUtPvDYgWDaA2dWdgLsshbwRfm3Q5YRlRogdmeRUNQw,30391 -pip/_vendor/chardet/metadata/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_vendor/chardet/metadata/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/chardet/metadata/__pycache__/languages.cpython-312.pyc,, -pip/_vendor/chardet/metadata/languages.py,sha256=FhvBIdZFxRQ-dTwkb_0madRKgVBCaUMQz9I5xqjE5iQ,13560 -pip/_vendor/chardet/resultdict.py,sha256=ez4FRvN5KaSosJeJ2WzUyKdDdg35HDy_SSLPXKCdt5M,402 -pip/_vendor/chardet/sbcharsetprober.py,sha256=-nd3F90i7GpXLjehLVHqVBE0KlWzGvQUPETLBNn4o6U,6400 -pip/_vendor/chardet/sbcsgroupprober.py,sha256=gcgI0fOfgw_3YTClpbra_MNxwyEyJ3eUXraoLHYb59E,4137 -pip/_vendor/chardet/sjisprober.py,sha256=aqQufMzRw46ZpFlzmYaYeT2-nzmKb-hmcrApppJ862k,4007 -pip/_vendor/chardet/universaldetector.py,sha256=xYBrg4x0dd9WnT8qclfADVD9ondrUNkqPmvte1pa520,14848 -pip/_vendor/chardet/utf1632prober.py,sha256=pw1epGdMj1hDGiCu1AHqqzOEfjX8MVdiW7O1BlT8-eQ,8505 -pip/_vendor/chardet/utf8prober.py,sha256=8m08Ub5490H4jQ6LYXvFysGtgKoKsHUd2zH_i8_TnVw,2812 -pip/_vendor/chardet/version.py,sha256=lGtJcxGM44Qz4Cbk4rbbmrKxnNr1-97U25TameLehZw,244 -pip/_vendor/colorama/__init__.py,sha256=wePQA4U20tKgYARySLEC047ucNX-g8pRLpYBuiHlLb8,266 -pip/_vendor/colorama/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/colorama/__pycache__/ansi.cpython-312.pyc,, -pip/_vendor/colorama/__pycache__/ansitowin32.cpython-312.pyc,, -pip/_vendor/colorama/__pycache__/initialise.cpython-312.pyc,, -pip/_vendor/colorama/__pycache__/win32.cpython-312.pyc,, -pip/_vendor/colorama/__pycache__/winterm.cpython-312.pyc,, -pip/_vendor/colorama/ansi.py,sha256=Top4EeEuaQdBWdteKMEcGOTeKeF19Q-Wo_6_Cj5kOzQ,2522 -pip/_vendor/colorama/ansitowin32.py,sha256=vPNYa3OZbxjbuFyaVo0Tmhmy1FZ1lKMWCnT7odXpItk,11128 -pip/_vendor/colorama/initialise.py,sha256=-hIny86ClXo39ixh5iSCfUIa2f_h_bgKRDW7gqs-KLU,3325 -pip/_vendor/colorama/tests/__init__.py,sha256=MkgPAEzGQd-Rq0w0PZXSX2LadRWhUECcisJY8lSrm4Q,75 -pip/_vendor/colorama/tests/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/colorama/tests/__pycache__/ansi_test.cpython-312.pyc,, -pip/_vendor/colorama/tests/__pycache__/ansitowin32_test.cpython-312.pyc,, -pip/_vendor/colorama/tests/__pycache__/initialise_test.cpython-312.pyc,, -pip/_vendor/colorama/tests/__pycache__/isatty_test.cpython-312.pyc,, -pip/_vendor/colorama/tests/__pycache__/utils.cpython-312.pyc,, -pip/_vendor/colorama/tests/__pycache__/winterm_test.cpython-312.pyc,, -pip/_vendor/colorama/tests/ansi_test.py,sha256=FeViDrUINIZcr505PAxvU4AjXz1asEiALs9GXMhwRaE,2839 -pip/_vendor/colorama/tests/ansitowin32_test.py,sha256=RN7AIhMJ5EqDsYaCjVo-o4u8JzDD4ukJbmevWKS70rY,10678 -pip/_vendor/colorama/tests/initialise_test.py,sha256=BbPy-XfyHwJ6zKozuQOvNvQZzsx9vdb_0bYXn7hsBTc,6741 -pip/_vendor/colorama/tests/isatty_test.py,sha256=Pg26LRpv0yQDB5Ac-sxgVXG7hsA1NYvapFgApZfYzZg,1866 -pip/_vendor/colorama/tests/utils.py,sha256=1IIRylG39z5-dzq09R_ngufxyPZxgldNbrxKxUGwGKE,1079 -pip/_vendor/colorama/tests/winterm_test.py,sha256=qoWFPEjym5gm2RuMwpf3pOis3a5r_PJZFCzK254JL8A,3709 -pip/_vendor/colorama/win32.py,sha256=YQOKwMTwtGBbsY4dL5HYTvwTeP9wIQra5MvPNddpxZs,6181 -pip/_vendor/colorama/winterm.py,sha256=XCQFDHjPi6AHYNdZwy0tA02H-Jh48Jp-HvCjeLeLp3U,7134 -pip/_vendor/distlib/__init__.py,sha256=hJKF7FHoqbmGckncDuEINWo_OYkDNiHODtYXSMcvjcc,625 -pip/_vendor/distlib/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/compat.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/database.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/index.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/locators.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/manifest.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/markers.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/metadata.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/resources.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/scripts.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/util.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/version.cpython-312.pyc,, -pip/_vendor/distlib/__pycache__/wheel.cpython-312.pyc,, -pip/_vendor/distlib/compat.py,sha256=Un-uIBvy02w-D267OG4VEhuddqWgKj9nNkxVltAb75w,41487 -pip/_vendor/distlib/database.py,sha256=0V9Qvs0Vrxa2F_-hLWitIyVyRifJ0pCxyOI-kEOBwsA,51965 -pip/_vendor/distlib/index.py,sha256=lTbw268rRhj8dw1sib3VZ_0EhSGgoJO3FKJzSFMOaeA,20797 -pip/_vendor/distlib/locators.py,sha256=o1r_M86_bRLafSpetmyfX8KRtFu-_Q58abvQrnOSnbA,51767 -pip/_vendor/distlib/manifest.py,sha256=3qfmAmVwxRqU1o23AlfXrQGZzh6g_GGzTAP_Hb9C5zQ,14168 -pip/_vendor/distlib/markers.py,sha256=n3DfOh1yvZ_8EW7atMyoYeZFXjYla0Nz0itQlojCd0A,5268 -pip/_vendor/distlib/metadata.py,sha256=pB9WZ9mBfmQxc9OVIldLS5CjOoQRvKAvUwwQyKwKQtQ,39693 -pip/_vendor/distlib/resources.py,sha256=LwbPksc0A1JMbi6XnuPdMBUn83X7BPuFNWqPGEKI698,10820 -pip/_vendor/distlib/scripts.py,sha256=nQFXN6G7nOWNDUyxirUep-3WOlJhB7McvCs9zOnkGTI,18315 -pip/_vendor/distlib/util.py,sha256=XSznxEi_i3T20UJuaVc0qXHz5ksGUCW1khYlBprN_QE,67530 -pip/_vendor/distlib/version.py,sha256=9pXkduchve_aN7JG6iL9VTYV_kqNSGoc2Dwl8JuySnQ,23747 -pip/_vendor/distlib/wheel.py,sha256=FVQCve8u-L0QYk5-YTZc7s4WmNQdvjRWTK08KXzZVX4,43958 -pip/_vendor/distro/__init__.py,sha256=2fHjF-SfgPvjyNZ1iHh_wjqWdR_Yo5ODHwZC0jLBPhc,981 -pip/_vendor/distro/__main__.py,sha256=bu9d3TifoKciZFcqRBuygV3GSuThnVD_m2IK4cz96Vs,64 -pip/_vendor/distro/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/distro/__pycache__/__main__.cpython-312.pyc,, -pip/_vendor/distro/__pycache__/distro.cpython-312.pyc,, -pip/_vendor/distro/distro.py,sha256=UZO1LjIhtFCMdlbiz39gj3raV-Amf3SBwzGzfApiMHw,49330 -pip/_vendor/idna/__init__.py,sha256=KJQN1eQBr8iIK5SKrJ47lXvxG0BJ7Lm38W4zT0v_8lk,849 -pip/_vendor/idna/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/idna/__pycache__/codec.cpython-312.pyc,, -pip/_vendor/idna/__pycache__/compat.cpython-312.pyc,, -pip/_vendor/idna/__pycache__/core.cpython-312.pyc,, -pip/_vendor/idna/__pycache__/idnadata.cpython-312.pyc,, -pip/_vendor/idna/__pycache__/intranges.cpython-312.pyc,, -pip/_vendor/idna/__pycache__/package_data.cpython-312.pyc,, -pip/_vendor/idna/__pycache__/uts46data.cpython-312.pyc,, -pip/_vendor/idna/codec.py,sha256=6ly5odKfqrytKT9_7UrlGklHnf1DSK2r9C6cSM4sa28,3374 -pip/_vendor/idna/compat.py,sha256=0_sOEUMT4CVw9doD3vyRhX80X19PwqFoUBs7gWsFME4,321 -pip/_vendor/idna/core.py,sha256=1JxchwKzkxBSn7R_oCE12oBu3eVux0VzdxolmIad24M,12950 -pip/_vendor/idna/idnadata.py,sha256=xUjqKqiJV8Ho_XzBpAtv5JFoVPSupK-SUXvtjygUHqw,44375 -pip/_vendor/idna/intranges.py,sha256=YBr4fRYuWH7kTKS2tXlFjM24ZF1Pdvcir-aywniInqg,1881 -pip/_vendor/idna/package_data.py,sha256=C_jHJzmX8PI4xq0jpzmcTMxpb5lDsq4o5VyxQzlVrZE,21 -pip/_vendor/idna/uts46data.py,sha256=zvjZU24s58_uAS850Mcd0NnD0X7_gCMAMjzWNIeUJdc,206539 -pip/_vendor/msgpack/__init__.py,sha256=hyGhlnmcJkxryJBKC3X5FnEph375kQoL_mG8LZUuXgY,1132 -pip/_vendor/msgpack/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/msgpack/__pycache__/exceptions.cpython-312.pyc,, -pip/_vendor/msgpack/__pycache__/ext.cpython-312.pyc,, -pip/_vendor/msgpack/__pycache__/fallback.cpython-312.pyc,, -pip/_vendor/msgpack/exceptions.py,sha256=dCTWei8dpkrMsQDcjQk74ATl9HsIBH0ybt8zOPNqMYc,1081 -pip/_vendor/msgpack/ext.py,sha256=C5MK8JhVYGYFWPvxsORsqZAnvOXefYQ57m1Ym0luW5M,6079 -pip/_vendor/msgpack/fallback.py,sha256=tvNBHyxxFbuVlC8GZShETClJxjLiDMOja4XwwyvNm2g,34544 -pip/_vendor/packaging/__about__.py,sha256=ugASIO2w1oUyH8_COqQ2X_s0rDhjbhQC3yJocD03h2c,661 -pip/_vendor/packaging/__init__.py,sha256=b9Kk5MF7KxhhLgcDmiUWukN-LatWFxPdNug0joPhHSk,497 -pip/_vendor/packaging/__pycache__/__about__.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/_structures.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/markers.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/requirements.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/tags.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/utils.cpython-312.pyc,, -pip/_vendor/packaging/__pycache__/version.cpython-312.pyc,, -pip/_vendor/packaging/_manylinux.py,sha256=XcbiXB-qcjv3bcohp6N98TMpOP4_j3m-iOA8ptK2GWY,11488 -pip/_vendor/packaging/_musllinux.py,sha256=_KGgY_qc7vhMGpoqss25n2hiLCNKRtvz9mCrS7gkqyc,4378 -pip/_vendor/packaging/_structures.py,sha256=q3eVNmbWJGG_S0Dit_S3Ao8qQqz_5PYTXFAKBZe5yr4,1431 -pip/_vendor/packaging/markers.py,sha256=AJBOcY8Oq0kYc570KuuPTkvuqjAlhufaE2c9sCUbm64,8487 -pip/_vendor/packaging/requirements.py,sha256=NtDlPBtojpn1IUC85iMjPNsUmufjpSlwnNA-Xb4m5NA,4676 -pip/_vendor/packaging/specifiers.py,sha256=LRQ0kFsHrl5qfcFNEEJrIFYsnIHQUJXY9fIsakTrrqE,30110 -pip/_vendor/packaging/tags.py,sha256=lmsnGNiJ8C4D_Pf9PbM0qgbZvD9kmB9lpZBQUZa3R_Y,15699 -pip/_vendor/packaging/utils.py,sha256=dJjeat3BS-TYn1RrUFVwufUMasbtzLfYRoy_HXENeFQ,4200 -pip/_vendor/packaging/version.py,sha256=_fLRNrFrxYcHVfyo8vk9j8s6JM8N_xsSxVFr6RJyco8,14665 -pip/_vendor/pkg_resources/__init__.py,sha256=hTAeJCNYb7dJseIDVsYK3mPQep_gphj4tQh-bspX8bg,109364 -pip/_vendor/pkg_resources/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/platformdirs/__init__.py,sha256=SkhEYVyC_HUHC6KX7n4M_6coyRMtEB38QMyOYIAX6Yk,20155 -pip/_vendor/platformdirs/__main__.py,sha256=fVvSiTzr2-RM6IsjWjj4fkaOtDOgDhUWv6sA99do4CQ,1476 -pip/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc,, -pip/_vendor/platformdirs/__pycache__/android.cpython-312.pyc,, -pip/_vendor/platformdirs/__pycache__/api.cpython-312.pyc,, -pip/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc,, -pip/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc,, -pip/_vendor/platformdirs/__pycache__/version.cpython-312.pyc,, -pip/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc,, -pip/_vendor/platformdirs/android.py,sha256=y_EEMKwYl2-bzYBDovksSn8m76on0Lda8eyJksVQE9U,7211 -pip/_vendor/platformdirs/api.py,sha256=jWtX06jAJytYrkJDOqEls97mCkyHRSZkoqUlbMK5Qew,7132 -pip/_vendor/platformdirs/macos.py,sha256=LueVOoVgGWDBwQb8OFwXkVKfVn33CM1Lkwf1-A86tRQ,3678 -pip/_vendor/platformdirs/unix.py,sha256=22JhR8ZY0aLxSVCFnKrc6f1iz6Gv42K24Daj7aTjfSg,8809 -pip/_vendor/platformdirs/version.py,sha256=mavZTQIJIXfdewEaSTn7EWrNfPZWeRofb-74xqW5f2M,160 -pip/_vendor/platformdirs/windows.py,sha256=4TtbPGoWG2PRgI11uquDa7eRk8TcxvnUNuuMGZItnXc,9573 -pip/_vendor/pygments/__init__.py,sha256=6AuDljQtvf89DTNUyWM7k3oUlP_lq70NU-INKKteOBY,2983 -pip/_vendor/pygments/__main__.py,sha256=es8EKMvXj5yToIfQ-pf3Dv5TnIeeM6sME0LW-n4ecHo,353 -pip/_vendor/pygments/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/__main__.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/cmdline.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/console.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/filter.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/formatter.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/lexer.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/modeline.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/plugin.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/regexopt.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/scanner.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/sphinxext.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/style.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/token.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/unistring.cpython-312.pyc,, -pip/_vendor/pygments/__pycache__/util.cpython-312.pyc,, -pip/_vendor/pygments/cmdline.py,sha256=byxYJp9gnjVeyhRlZ3UTMgo_LhkXh1afvN8wJBtAcc8,23685 -pip/_vendor/pygments/console.py,sha256=2wZ5W-U6TudJD1_NLUwjclMpbomFM91lNv11_60sfGY,1697 -pip/_vendor/pygments/filter.py,sha256=j5aLM9a9wSx6eH1oy473oSkJ02hGWNptBlVo4s1g_30,1938 -pip/_vendor/pygments/filters/__init__.py,sha256=h_koYkUFo-FFUxjs564JHUAz7O3yJpVwI6fKN3MYzG0,40386 -pip/_vendor/pygments/filters/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pygments/formatter.py,sha256=J9OL9hXLJKZk7moUgKwpjW9HNf4WlJFg_o_-Z_S_tTY,4178 -pip/_vendor/pygments/formatters/__init__.py,sha256=_xgAcdFKr0QNYwh_i98AU9hvfP3X2wAkhElFcRRF3Uo,5424 -pip/_vendor/pygments/formatters/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/_mapping.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/bbcode.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/groff.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/html.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/img.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/irc.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/latex.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/other.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/pangomarkup.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/rtf.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/svg.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/terminal.cpython-312.pyc,, -pip/_vendor/pygments/formatters/__pycache__/terminal256.cpython-312.pyc,, -pip/_vendor/pygments/formatters/_mapping.py,sha256=1Cw37FuQlNacnxRKmtlPX4nyLoX9_ttko5ZwscNUZZ4,4176 -pip/_vendor/pygments/formatters/bbcode.py,sha256=r1b7wzWTJouADDLh-Z11iRi4iQxD0JKJ1qHl6mOYxsA,3314 -pip/_vendor/pygments/formatters/groff.py,sha256=xy8Zf3tXOo6MWrXh7yPGWx3lVEkg_DhY4CxmsDb0IVo,5094 -pip/_vendor/pygments/formatters/html.py,sha256=PIzAyilNqaTzSSP2slDG2VDLE3qNioWy2rgtSSoviuI,35610 -pip/_vendor/pygments/formatters/img.py,sha256=XKXmg2_XONrR4mtq2jfEU8XCsoln3VSGTw-UYiEokys,21938 -pip/_vendor/pygments/formatters/irc.py,sha256=Ep-m8jd3voFO6Fv57cUGFmz6JVA67IEgyiBOwv0N4a0,4981 -pip/_vendor/pygments/formatters/latex.py,sha256=FGzJ-YqSTE8z_voWPdzvLY5Tq8jE_ygjGjM6dXZJ8-k,19351 -pip/_vendor/pygments/formatters/other.py,sha256=gPxkk5BdAzWTCgbEHg1lpLi-1F6ZPh5A_aotgLXHnzg,5073 -pip/_vendor/pygments/formatters/pangomarkup.py,sha256=6LKnQc8yh49f802bF0sPvbzck4QivMYqqoXAPaYP8uU,2212 -pip/_vendor/pygments/formatters/rtf.py,sha256=aA0v_psW6KZI3N18TKDifxeL6mcF8EDXcPXDWI4vhVQ,5014 -pip/_vendor/pygments/formatters/svg.py,sha256=dQONWypbzfvzGCDtdp3M_NJawScJvM2DiHbx1k-ww7g,7335 -pip/_vendor/pygments/formatters/terminal.py,sha256=FG-rpjRpFmNpiGB4NzIucvxq6sQIXB3HOTo2meTKtrU,4674 -pip/_vendor/pygments/formatters/terminal256.py,sha256=13SJ3D5pFdqZ9zROE6HbWnBDwHvOGE8GlsmqGhprRp4,11753 -pip/_vendor/pygments/lexer.py,sha256=2BpqLlT2ExvOOi7vnjK5nB4Fp-m52ldiPaXMox5uwug,34618 -pip/_vendor/pygments/lexers/__init__.py,sha256=j5KEi5O_VQ5GS59H49l-10gzUOkWKxlwGeVMlGO2MMk,12130 -pip/_vendor/pygments/lexers/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pygments/lexers/__pycache__/_mapping.cpython-312.pyc,, -pip/_vendor/pygments/lexers/__pycache__/python.cpython-312.pyc,, -pip/_vendor/pygments/lexers/_mapping.py,sha256=Hts4r_ZQ8icftGM7gkBPeED5lyVSv4affFgXYE6Ap04,72281 -pip/_vendor/pygments/lexers/python.py,sha256=c7jnmKFU9DLxTJW0UbwXt6Z9FJqbBlVsWA1Qr9xSA_w,53424 -pip/_vendor/pygments/modeline.py,sha256=eF2vO4LpOGoPvIKKkbPfnyut8hT4UiebZPpb-BYGQdI,986 -pip/_vendor/pygments/plugin.py,sha256=j1Fh310RbV2DQ9nvkmkqvlj38gdyuYKllLnGxbc8sJM,2591 -pip/_vendor/pygments/regexopt.py,sha256=jg1ALogcYGU96TQS9isBl6dCrvw5y5--BP_K-uFk_8s,3072 -pip/_vendor/pygments/scanner.py,sha256=b_nu5_f3HCgSdp5S_aNRBQ1MSCm4ZjDwec2OmTRickw,3092 -pip/_vendor/pygments/sphinxext.py,sha256=wBFYm180qea9JKt__UzhRlNRNhczPDFDaqGD21sbuso,6882 -pip/_vendor/pygments/style.py,sha256=C4qyoJrUTkq-OV3iO-8Vz3UtWYpJwSTdh5_vlGCGdNQ,6257 -pip/_vendor/pygments/styles/__init__.py,sha256=he7HjQx7sC0d2kfTVLjUs0J15mtToJM6M1brwIm9--Q,3700 -pip/_vendor/pygments/styles/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pygments/token.py,sha256=seNsmcch9OEHXYirh8Ool7w8xDhfNTbLj5rHAC-gc_o,6184 -pip/_vendor/pygments/unistring.py,sha256=FaUfG14NBJEKLQoY9qj6JYeXrpYcLmKulghdxOGFaOc,63223 -pip/_vendor/pygments/util.py,sha256=AEVY0qonyyEMgv4Do2dINrrqUAwUk2XYSqHM650uzek,10230 -pip/_vendor/pyparsing/__init__.py,sha256=9m1JbE2JTLdBG0Mb6B0lEaZj181Wx5cuPXZpsbHEYgE,9116 -pip/_vendor/pyparsing/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/actions.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/common.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/core.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/exceptions.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/helpers.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/results.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/testing.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/unicode.cpython-312.pyc,, -pip/_vendor/pyparsing/__pycache__/util.cpython-312.pyc,, -pip/_vendor/pyparsing/actions.py,sha256=05uaIPOznJPQ7VgRdmGCmG4sDnUPtwgv5qOYIqbL2UY,6567 -pip/_vendor/pyparsing/common.py,sha256=p-3c83E5-DjlkF35G0O9-kjQRpoejP-2_z0hxZ-eol4,13387 -pip/_vendor/pyparsing/core.py,sha256=yvuRlLpXSF8mgk-QhiW3OVLqD9T0rsj9tbibhRH4Yaw,224445 -pip/_vendor/pyparsing/diagram/__init__.py,sha256=nxmDOoYF9NXuLaGYy01tKFjkNReWJlrGFuJNWEiTo84,24215 -pip/_vendor/pyparsing/diagram/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pyparsing/exceptions.py,sha256=6Jc6W1eDZBzyFu1J0YrcdNFVBC-RINujZmveSnB8Rxw,9523 -pip/_vendor/pyparsing/helpers.py,sha256=BZJHCA8SS0pYio30KGQTc9w2qMOaK4YpZ7hcvHbnTgk,38646 -pip/_vendor/pyparsing/results.py,sha256=9dyqQ-w3MjfmxWbFt8KEPU6IfXeyRdoWp2Og802rUQY,26692 -pip/_vendor/pyparsing/testing.py,sha256=eJncg0p83zm1FTPvM9auNT6oavIvXaibmRFDf1qmwkY,13488 -pip/_vendor/pyparsing/unicode.py,sha256=fAPdsJiARFbkPAih6NkYry0dpj4jPqelGVMlE4wWFW8,10646 -pip/_vendor/pyparsing/util.py,sha256=vTMzTdwSDyV8d_dSgquUTdWgBFoA_W30nfxEJDsshRQ,8670 -pip/_vendor/pyproject_hooks/__init__.py,sha256=kCehmy0UaBa9oVMD7ZIZrnswfnP3LXZ5lvnNJAL5JBM,491 -pip/_vendor/pyproject_hooks/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pyproject_hooks/__pycache__/_compat.cpython-312.pyc,, -pip/_vendor/pyproject_hooks/__pycache__/_impl.cpython-312.pyc,, -pip/_vendor/pyproject_hooks/_compat.py,sha256=by6evrYnqkisiM-MQcvOKs5bgDMzlOSgZqRHNqf04zE,138 -pip/_vendor/pyproject_hooks/_impl.py,sha256=61GJxzQip0IInhuO69ZI5GbNQ82XEDUB_1Gg5_KtUoc,11920 -pip/_vendor/pyproject_hooks/_in_process/__init__.py,sha256=9gQATptbFkelkIy0OfWFEACzqxXJMQDWCH9rBOAZVwQ,546 -pip/_vendor/pyproject_hooks/_in_process/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/pyproject_hooks/_in_process/__pycache__/_in_process.cpython-312.pyc,, -pip/_vendor/pyproject_hooks/_in_process/_in_process.py,sha256=m2b34c917IW5o-Q_6TYIHlsK9lSUlNiyrITTUH_zwew,10927 -pip/_vendor/requests/__init__.py,sha256=owujob4dk45Siy4EYtbCKR6wcFph7E04a_v_OuAacBA,5169 -pip/_vendor/requests/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/__version__.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/_internal_utils.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/adapters.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/api.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/auth.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/certs.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/compat.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/cookies.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/exceptions.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/help.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/hooks.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/models.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/packages.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/sessions.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/status_codes.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/structures.cpython-312.pyc,, -pip/_vendor/requests/__pycache__/utils.cpython-312.pyc,, -pip/_vendor/requests/__version__.py,sha256=ssI3Ezt7PaxgkOW45GhtwPUclo_SO_ygtIm4A74IOfw,435 -pip/_vendor/requests/_internal_utils.py,sha256=nMQymr4hs32TqVo5AbCrmcJEhvPUh7xXlluyqwslLiQ,1495 -pip/_vendor/requests/adapters.py,sha256=idj6cZcId3L5xNNeJ7ieOLtw3awJk5A64xUfetHwq3M,19697 -pip/_vendor/requests/api.py,sha256=q61xcXq4tmiImrvcSVLTbFyCiD2F-L_-hWKGbz4y8vg,6449 -pip/_vendor/requests/auth.py,sha256=h-HLlVx9j8rKV5hfSAycP2ApOSglTz77R0tz7qCbbEE,10187 -pip/_vendor/requests/certs.py,sha256=PVPooB0jP5hkZEULSCwC074532UFbR2Ptgu0I5zwmCs,575 -pip/_vendor/requests/compat.py,sha256=IhK9quyX0RRuWTNcg6d2JGSAOUbM6mym2p_2XjLTwf4,1286 -pip/_vendor/requests/cookies.py,sha256=kD3kNEcCj-mxbtf5fJsSaT86eGoEYpD3X0CSgpzl7BM,18560 -pip/_vendor/requests/exceptions.py,sha256=FA-_kVwBZ2jhXauRctN_ewHVK25b-fj0Azyz1THQ0Kk,3823 -pip/_vendor/requests/help.py,sha256=FnAAklv8MGm_qb2UilDQgS6l0cUttiCFKUjx0zn2XNA,3879 -pip/_vendor/requests/hooks.py,sha256=CiuysiHA39V5UfcCBXFIx83IrDpuwfN9RcTUgv28ftQ,733 -pip/_vendor/requests/models.py,sha256=dDZ-iThotky-Noq9yy97cUEJhr3wnY6mv-xR_ePg_lk,35288 -pip/_vendor/requests/packages.py,sha256=njJmVifY4aSctuW3PP5EFRCxjEwMRDO6J_feG2dKWsI,695 -pip/_vendor/requests/sessions.py,sha256=-LvTzrPtetSTrR3buxu4XhdgMrJFLB1q5D7P--L2Xhw,30373 -pip/_vendor/requests/status_codes.py,sha256=FvHmT5uH-_uimtRz5hH9VCbt7VV-Nei2J9upbej6j8g,4235 -pip/_vendor/requests/structures.py,sha256=-IbmhVz06S-5aPSZuUthZ6-6D9XOjRuTXHOabY041XM,2912 -pip/_vendor/requests/utils.py,sha256=kOPn0qYD6xRTzaxbqTdYiSInBZHl6379AJsyIgzYGLY,33460 -pip/_vendor/resolvelib/__init__.py,sha256=h509TdEcpb5-44JonaU3ex2TM15GVBLjM9CNCPwnTTs,537 -pip/_vendor/resolvelib/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/resolvelib/__pycache__/providers.cpython-312.pyc,, -pip/_vendor/resolvelib/__pycache__/reporters.cpython-312.pyc,, -pip/_vendor/resolvelib/__pycache__/resolvers.cpython-312.pyc,, -pip/_vendor/resolvelib/__pycache__/structs.cpython-312.pyc,, -pip/_vendor/resolvelib/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_vendor/resolvelib/compat/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/resolvelib/compat/__pycache__/collections_abc.cpython-312.pyc,, -pip/_vendor/resolvelib/compat/collections_abc.py,sha256=uy8xUZ-NDEw916tugUXm8HgwCGiMO0f-RcdnpkfXfOs,156 -pip/_vendor/resolvelib/providers.py,sha256=fuuvVrCetu5gsxPB43ERyjfO8aReS3rFQHpDgiItbs4,5871 -pip/_vendor/resolvelib/reporters.py,sha256=TSbRmWzTc26w0ggsV1bxVpeWDB8QNIre6twYl7GIZBE,1601 -pip/_vendor/resolvelib/resolvers.py,sha256=G8rsLZSq64g5VmIq-lB7UcIJ1gjAxIQJmTF4REZleQ0,20511 -pip/_vendor/resolvelib/structs.py,sha256=0_1_XO8z_CLhegP3Vpf9VJ3zJcfLm0NOHRM-i0Ykz3o,4963 -pip/_vendor/rich/__init__.py,sha256=dRxjIL-SbFVY0q3IjSMrfgBTHrm1LZDgLOygVBwiYZc,6090 -pip/_vendor/rich/__main__.py,sha256=TT8sb9PTnsnKhhrGuHkLN0jdN0dtKhtPkEr9CidDbPM,8478 -pip/_vendor/rich/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/__main__.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_cell_widths.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_emoji_codes.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_emoji_replace.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_export_format.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_extension.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_fileno.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_inspect.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_log_render.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_loop.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_null_file.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_palettes.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_pick.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_ratio.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_spinners.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_stack.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_timer.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_win32_console.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_windows.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_windows_renderer.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/_wrap.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/abc.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/align.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/ansi.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/bar.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/box.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/cells.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/color.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/color_triplet.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/columns.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/console.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/constrain.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/containers.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/control.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/default_styles.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/diagnose.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/emoji.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/errors.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/file_proxy.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/filesize.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/highlighter.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/json.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/jupyter.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/layout.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/live.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/live_render.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/logging.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/markup.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/measure.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/padding.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/pager.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/palette.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/panel.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/pretty.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/progress.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/progress_bar.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/prompt.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/protocol.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/region.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/repr.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/rule.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/scope.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/screen.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/segment.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/spinner.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/status.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/style.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/styled.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/syntax.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/table.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/terminal_theme.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/text.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/theme.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/themes.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/traceback.cpython-312.pyc,, -pip/_vendor/rich/__pycache__/tree.cpython-312.pyc,, -pip/_vendor/rich/_cell_widths.py,sha256=2n4EiJi3X9sqIq0O16kUZ_zy6UYMd3xFfChlKfnW1Hc,10096 -pip/_vendor/rich/_emoji_codes.py,sha256=hu1VL9nbVdppJrVoijVshRlcRRe_v3dju3Mmd2sKZdY,140235 -pip/_vendor/rich/_emoji_replace.py,sha256=n-kcetsEUx2ZUmhQrfeMNc-teeGhpuSQ5F8VPBsyvDo,1064 -pip/_vendor/rich/_export_format.py,sha256=qxgV3nKnXQu1hfbnRVswPYy-AwIg1X0LSC47cK5s8jk,2100 -pip/_vendor/rich/_extension.py,sha256=Xt47QacCKwYruzjDi-gOBq724JReDj9Cm9xUi5fr-34,265 -pip/_vendor/rich/_fileno.py,sha256=HWZxP5C2ajMbHryvAQZseflVfQoGzsKOHzKGsLD8ynQ,799 -pip/_vendor/rich/_inspect.py,sha256=oZJGw31e64dwXSCmrDnvZbwVb1ZKhWfU8wI3VWohjJk,9695 -pip/_vendor/rich/_log_render.py,sha256=1ByI0PA1ZpxZY3CGJOK54hjlq4X-Bz_boIjIqCd8Kns,3225 -pip/_vendor/rich/_loop.py,sha256=hV_6CLdoPm0va22Wpw4zKqM0RYsz3TZxXj0PoS-9eDQ,1236 -pip/_vendor/rich/_null_file.py,sha256=tGSXk_v-IZmbj1GAzHit8A3kYIQMiCpVsCFfsC-_KJ4,1387 -pip/_vendor/rich/_palettes.py,sha256=cdev1JQKZ0JvlguV9ipHgznTdnvlIzUFDBb0It2PzjI,7063 -pip/_vendor/rich/_pick.py,sha256=evDt8QN4lF5CiwrUIXlOJCntitBCOsI3ZLPEIAVRLJU,423 -pip/_vendor/rich/_ratio.py,sha256=2lLSliL025Y-YMfdfGbutkQDevhcyDqc-DtUYW9mU70,5472 -pip/_vendor/rich/_spinners.py,sha256=U2r1_g_1zSjsjiUdAESc2iAMc3i4ri_S8PYP6kQ5z1I,19919 -pip/_vendor/rich/_stack.py,sha256=-C8OK7rxn3sIUdVwxZBBpeHhIzX0eI-VM3MemYfaXm0,351 -pip/_vendor/rich/_timer.py,sha256=zelxbT6oPFZnNrwWPpc1ktUeAT-Vc4fuFcRZLQGLtMI,417 -pip/_vendor/rich/_win32_console.py,sha256=P0vxI2fcndym1UU1S37XAzQzQnkyY7YqAKmxm24_gug,22820 -pip/_vendor/rich/_windows.py,sha256=dvNl9TmfPzNVxiKk5WDFihErZ5796g2UC9-KGGyfXmk,1926 -pip/_vendor/rich/_windows_renderer.py,sha256=t74ZL3xuDCP3nmTp9pH1L5LiI2cakJuQRQleHCJerlk,2783 -pip/_vendor/rich/_wrap.py,sha256=xfV_9t0Sg6rzimmrDru8fCVmUlalYAcHLDfrJZnbbwQ,1840 -pip/_vendor/rich/abc.py,sha256=ON-E-ZqSSheZ88VrKX2M3PXpFbGEUUZPMa_Af0l-4f0,890 -pip/_vendor/rich/align.py,sha256=Ji-Yokfkhnfe_xMmr4ISjZB07TJXggBCOYoYa-HDAr8,10368 -pip/_vendor/rich/ansi.py,sha256=iD6532QYqnBm6hADulKjrV8l8kFJ-9fEVooHJHH3hMg,6906 -pip/_vendor/rich/bar.py,sha256=a7UD303BccRCrEhGjfMElpv5RFYIinaAhAuqYqhUvmw,3264 -pip/_vendor/rich/box.py,sha256=FJ6nI3jD7h2XNFU138bJUt2HYmWOlRbltoCEuIAZhew,9842 -pip/_vendor/rich/cells.py,sha256=627ztJs9zOL-38HJ7kXBerR-gT8KBfYC8UzEwMJDYYo,4509 -pip/_vendor/rich/color.py,sha256=9Gh958U3f75WVdLTeC0U9nkGTn2n0wnojKpJ6jQEkIE,18224 -pip/_vendor/rich/color_triplet.py,sha256=3lhQkdJbvWPoLDO-AnYImAWmJvV5dlgYNCVZ97ORaN4,1054 -pip/_vendor/rich/columns.py,sha256=HUX0KcMm9dsKNi11fTbiM_h2iDtl8ySCaVcxlalEzq8,7131 -pip/_vendor/rich/console.py,sha256=pDvkbLkvtZIMIwQx_jkZ-seyNl4zGBLviXoWXte9fwg,99218 -pip/_vendor/rich/constrain.py,sha256=1VIPuC8AgtKWrcncQrjBdYqA3JVWysu6jZo1rrh7c7Q,1288 -pip/_vendor/rich/containers.py,sha256=aKgm5UDHn5Nmui6IJaKdsZhbHClh_X7D-_Wg8Ehrr7s,5497 -pip/_vendor/rich/control.py,sha256=DSkHTUQLorfSERAKE_oTAEUFefZnZp4bQb4q8rHbKws,6630 -pip/_vendor/rich/default_styles.py,sha256=-Fe318kMVI_IwciK5POpThcO0-9DYJ67TZAN6DlmlmM,8082 -pip/_vendor/rich/diagnose.py,sha256=an6uouwhKPAlvQhYpNNpGq9EJysfMIOvvCbO3oSoR24,972 -pip/_vendor/rich/emoji.py,sha256=omTF9asaAnsM4yLY94eR_9dgRRSm1lHUszX20D1yYCQ,2501 -pip/_vendor/rich/errors.py,sha256=5pP3Kc5d4QJ_c0KFsxrfyhjiPVe7J1zOqSFbFAzcV-Y,642 -pip/_vendor/rich/file_proxy.py,sha256=Tl9THMDZ-Pk5Wm8sI1gGg_U5DhusmxD-FZ0fUbcU0W0,1683 -pip/_vendor/rich/filesize.py,sha256=9fTLAPCAwHmBXdRv7KZU194jSgNrRb6Wx7RIoBgqeKY,2508 -pip/_vendor/rich/highlighter.py,sha256=p3C1g4QYzezFKdR7NF9EhPbzQDvdPUhGRgSyGGEmPko,9584 -pip/_vendor/rich/json.py,sha256=EYp9ucj-nDjYDkHCV6Mk1ve8nUOpuFLaW76X50Mis2M,5032 -pip/_vendor/rich/jupyter.py,sha256=QyoKoE_8IdCbrtiSHp9TsTSNyTHY0FO5whE7jOTd9UE,3252 -pip/_vendor/rich/layout.py,sha256=RFYL6HdCFsHf9WRpcvi3w-fpj-8O5dMZ8W96VdKNdbI,14007 -pip/_vendor/rich/live.py,sha256=vZzYvu7fqwlv3Gthl2xiw1Dc_O80VlGcCV0DOHwCyDM,14273 -pip/_vendor/rich/live_render.py,sha256=zElm3PrfSIvjOce28zETHMIUf9pFYSUA5o0AflgUP64,3667 -pip/_vendor/rich/logging.py,sha256=uB-cB-3Q4bmXDLLpbOWkmFviw-Fde39zyMV6tKJ2WHQ,11903 -pip/_vendor/rich/markup.py,sha256=xzF4uAafiEeEYDJYt_vUnJOGoTU8RrH-PH7WcWYXjCg,8198 -pip/_vendor/rich/measure.py,sha256=HmrIJX8sWRTHbgh8MxEay_83VkqNW_70s8aKP5ZcYI8,5305 -pip/_vendor/rich/padding.py,sha256=kTFGsdGe0os7tXLnHKpwTI90CXEvrceeZGCshmJy5zw,4970 -pip/_vendor/rich/pager.py,sha256=SO_ETBFKbg3n_AgOzXm41Sv36YxXAyI3_R-KOY2_uSc,828 -pip/_vendor/rich/palette.py,sha256=lInvR1ODDT2f3UZMfL1grq7dY_pDdKHw4bdUgOGaM4Y,3396 -pip/_vendor/rich/panel.py,sha256=wGMe40J8KCGgQoM0LyjRErmGIkv2bsYA71RCXThD0xE,10574 -pip/_vendor/rich/pretty.py,sha256=eLEYN9xVaMNuA6EJVYm4li7HdOHxCqmVKvnOqJpyFt0,35852 -pip/_vendor/rich/progress.py,sha256=n4KF9vky8_5iYeXcyZPEvzyLplWlDvFLkM5JI0Bs08A,59706 -pip/_vendor/rich/progress_bar.py,sha256=cEoBfkc3lLwqba4XKsUpy4vSQKDh2QQ5J2J94-ACFoo,8165 -pip/_vendor/rich/prompt.py,sha256=x0mW-pIPodJM4ry6grgmmLrl8VZp99kqcmdnBe70YYA,11303 -pip/_vendor/rich/protocol.py,sha256=5hHHDDNHckdk8iWH5zEbi-zuIVSF5hbU2jIo47R7lTE,1391 -pip/_vendor/rich/region.py,sha256=rNT9xZrVZTYIXZC0NYn41CJQwYNbR-KecPOxTgQvB8Y,166 -pip/_vendor/rich/repr.py,sha256=9Z8otOmM-tyxnyTodvXlectP60lwahjGiDTrbrxPSTg,4431 -pip/_vendor/rich/rule.py,sha256=0fNaS_aERa3UMRc3T5WMpN_sumtDxfaor2y3of1ftBk,4602 -pip/_vendor/rich/scope.py,sha256=TMUU8qo17thyqQCPqjDLYpg_UU1k5qVd-WwiJvnJVas,2843 -pip/_vendor/rich/screen.py,sha256=YoeReESUhx74grqb0mSSb9lghhysWmFHYhsbMVQjXO8,1591 -pip/_vendor/rich/segment.py,sha256=XLnJEFvcV3bjaVzMNUJiem3n8lvvI9TJ5PTu-IG2uTg,24247 -pip/_vendor/rich/spinner.py,sha256=15koCmF0DQeD8-k28Lpt6X_zJQUlzEhgo_6A6uy47lc,4339 -pip/_vendor/rich/status.py,sha256=gJsIXIZeSo3urOyxRUjs6VrhX5CZrA0NxIQ-dxhCnwo,4425 -pip/_vendor/rich/style.py,sha256=3hiocH_4N8vwRm3-8yFWzM7tSwjjEven69XqWasSQwM,27073 -pip/_vendor/rich/styled.py,sha256=eZNnzGrI4ki_54pgY3Oj0T-x3lxdXTYh4_ryDB24wBU,1258 -pip/_vendor/rich/syntax.py,sha256=jgDiVCK6cpR0NmBOpZmIu-Ud4eaW7fHvjJZkDbjpcSA,35173 -pip/_vendor/rich/table.py,sha256=-WzesL-VJKsaiDU3uyczpJMHy6VCaSewBYJwx8RudI8,39684 -pip/_vendor/rich/terminal_theme.py,sha256=1j5-ufJfnvlAo5Qsi_ACZiXDmwMXzqgmFByObT9-yJY,3370 -pip/_vendor/rich/text.py,sha256=_8JBlSau0c2z8ENOZMi1hJ7M1ZGY408E4-hXjHyyg1A,45525 -pip/_vendor/rich/theme.py,sha256=belFJogzA0W0HysQabKaHOc3RWH2ko3fQAJhoN-AFdo,3777 -pip/_vendor/rich/themes.py,sha256=0xgTLozfabebYtcJtDdC5QkX5IVUEaviqDUJJh4YVFk,102 -pip/_vendor/rich/traceback.py,sha256=yCLVrCtyoFNENd9mkm2xeG3KmqkTwH9xpFOO7p2Bq0A,29604 -pip/_vendor/rich/tree.py,sha256=BMbUYNjS9uodNPfvtY_odmU09GA5QzcMbQ5cJZhllQI,9169 -pip/_vendor/six.py,sha256=TOOfQi7nFGfMrIvtdr6wX4wyHH8M7aknmuLfo2cBBrM,34549 -pip/_vendor/tenacity/__init__.py,sha256=3kvAL6KClq8GFo2KFhmOzskRKSDQI-ubrlfZ8AQEEI0,20493 -pip/_vendor/tenacity/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/_asyncio.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/_utils.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/after.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/before.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/before_sleep.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/nap.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/retry.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/stop.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/tornadoweb.cpython-312.pyc,, -pip/_vendor/tenacity/__pycache__/wait.cpython-312.pyc,, -pip/_vendor/tenacity/_asyncio.py,sha256=Qi6wgQsGa9MQibYRy3OXqcDQswIZZ00dLOoSUGN-6o8,3551 -pip/_vendor/tenacity/_utils.py,sha256=ubs6a7sxj3JDNRKWCyCU2j5r1CB7rgyONgZzYZq6D_4,2179 -pip/_vendor/tenacity/after.py,sha256=S5NCISScPeIrKwIeXRwdJl3kV9Q4nqZfnNPDx6Hf__g,1682 -pip/_vendor/tenacity/before.py,sha256=dIZE9gmBTffisfwNkK0F1xFwGPV41u5GK70UY4Pi5Kc,1562 -pip/_vendor/tenacity/before_sleep.py,sha256=YmpgN9Y7HGlH97U24vvq_YWb5deaK4_DbiD8ZuFmy-E,2372 -pip/_vendor/tenacity/nap.py,sha256=fRWvnz1aIzbIq9Ap3gAkAZgDH6oo5zxMrU6ZOVByq0I,1383 -pip/_vendor/tenacity/retry.py,sha256=jrzD_mxA5mSTUEdiYB7SHpxltjhPSYZSnSRATb-ggRc,8746 -pip/_vendor/tenacity/stop.py,sha256=YMJs7ZgZfND65PRLqlGB_agpfGXlemx_5Hm4PKnBqpQ,3086 -pip/_vendor/tenacity/tornadoweb.py,sha256=po29_F1Mt8qZpsFjX7EVwAT0ydC_NbVia9gVi7R_wXA,2142 -pip/_vendor/tenacity/wait.py,sha256=3FcBJoCDgym12_dN6xfK8C1gROY0Hn4NSI2u8xv50uE,8024 -pip/_vendor/tomli/__init__.py,sha256=JhUwV66DB1g4Hvt1UQCVMdfCu-IgAV8FXmvDU9onxd4,396 -pip/_vendor/tomli/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/tomli/__pycache__/_parser.cpython-312.pyc,, -pip/_vendor/tomli/__pycache__/_re.cpython-312.pyc,, -pip/_vendor/tomli/__pycache__/_types.cpython-312.pyc,, -pip/_vendor/tomli/_parser.py,sha256=g9-ENaALS-B8dokYpCuzUFalWlog7T-SIYMjLZSWrtM,22633 -pip/_vendor/tomli/_re.py,sha256=dbjg5ChZT23Ka9z9DHOXfdtSpPwUfdgMXnj8NOoly-w,2943 -pip/_vendor/tomli/_types.py,sha256=-GTG2VUqkpxwMqzmVO4F7ybKddIbAnuAHXfmWQcTi3Q,254 -pip/_vendor/truststore/__init__.py,sha256=qzTLSH8PvAkY1fr6QQ2vV-KwE_M83wdXugtpJaP_AbM,403 -pip/_vendor/truststore/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/truststore/__pycache__/_api.cpython-312.pyc,, -pip/_vendor/truststore/__pycache__/_macos.cpython-312.pyc,, -pip/_vendor/truststore/__pycache__/_openssl.cpython-312.pyc,, -pip/_vendor/truststore/__pycache__/_ssl_constants.cpython-312.pyc,, -pip/_vendor/truststore/__pycache__/_windows.cpython-312.pyc,, -pip/_vendor/truststore/_api.py,sha256=xjuEu_rlH4hcdJTROImEyOEqdw-F8t5vO2H2BToY0Ro,9893 -pip/_vendor/truststore/_macos.py,sha256=BjvAKoAjXhdIPuxpY124HJIFswDb0pq8DjynzJOVwqc,17694 -pip/_vendor/truststore/_openssl.py,sha256=LLUZ7ZGaio-i5dpKKjKCSeSufmn6T8pi9lDcFnvSyq0,2324 -pip/_vendor/truststore/_ssl_constants.py,sha256=NUD4fVKdSD02ri7-db0tnO0VqLP9aHuzmStcW7tAl08,1130 -pip/_vendor/truststore/_windows.py,sha256=1x_EhROeJ9QK1sMAjfnZC7awYI8UnBJYL-TjACUYI4A,17468 -pip/_vendor/typing_extensions.py,sha256=EWpcpyQnVmc48E9fSyPGs-vXgHcAk9tQABQIxmMsCGk,111130 -pip/_vendor/urllib3/__init__.py,sha256=iXLcYiJySn0GNbWOOZDDApgBL1JgP44EZ8i1760S8Mc,3333 -pip/_vendor/urllib3/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/_collections.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/_version.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/connection.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/connectionpool.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/exceptions.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/fields.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/filepost.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/poolmanager.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/request.cpython-312.pyc,, -pip/_vendor/urllib3/__pycache__/response.cpython-312.pyc,, -pip/_vendor/urllib3/_collections.py,sha256=Rp1mVyBgc_UlAcp6M3at1skJBXR5J43NawRTvW2g_XY,10811 -pip/_vendor/urllib3/_version.py,sha256=azoM7M7BUADl2kBhMVR6PPf2GhBDI90me1fcnzTwdcw,64 -pip/_vendor/urllib3/connection.py,sha256=92k9td_y4PEiTIjNufCUa1NzMB3J3w0LEdyokYgXnW8,20300 -pip/_vendor/urllib3/connectionpool.py,sha256=ItVDasDnPRPP9R8bNxY7tPBlC724nJ9nlxVgXG_SLbI,39990 -pip/_vendor/urllib3/contrib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_vendor/urllib3/contrib/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/__pycache__/_appengine_environ.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/__pycache__/appengine.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/__pycache__/ntlmpool.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/__pycache__/securetransport.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/__pycache__/socks.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/_appengine_environ.py,sha256=bDbyOEhW2CKLJcQqAKAyrEHN-aklsyHFKq6vF8ZFsmk,957 -pip/_vendor/urllib3/contrib/_securetransport/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_vendor/urllib3/contrib/_securetransport/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/_securetransport/__pycache__/bindings.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/_securetransport/__pycache__/low_level.cpython-312.pyc,, -pip/_vendor/urllib3/contrib/_securetransport/bindings.py,sha256=4Xk64qIkPBt09A5q-RIFUuDhNc9mXilVapm7WnYnzRw,17632 -pip/_vendor/urllib3/contrib/_securetransport/low_level.py,sha256=B2JBB2_NRP02xK6DCa1Pa9IuxrPwxzDzZbixQkb7U9M,13922 -pip/_vendor/urllib3/contrib/appengine.py,sha256=VR68eAVE137lxTgjBDwCna5UiBZTOKa01Aj_-5BaCz4,11036 -pip/_vendor/urllib3/contrib/ntlmpool.py,sha256=NlfkW7WMdW8ziqudopjHoW299og1BTWi0IeIibquFwk,4528 -pip/_vendor/urllib3/contrib/pyopenssl.py,sha256=hDJh4MhyY_p-oKlFcYcQaVQRDv6GMmBGuW9yjxyeejM,17081 -pip/_vendor/urllib3/contrib/securetransport.py,sha256=yhZdmVjY6PI6EeFbp7qYOp6-vp1Rkv2NMuOGaEj7pmc,34448 -pip/_vendor/urllib3/contrib/socks.py,sha256=aRi9eWXo9ZEb95XUxef4Z21CFlnnjbEiAo9HOseoMt4,7097 -pip/_vendor/urllib3/exceptions.py,sha256=0Mnno3KHTNfXRfY7638NufOPkUb6mXOm-Lqj-4x2w8A,8217 -pip/_vendor/urllib3/fields.py,sha256=kvLDCg_JmH1lLjUUEY_FLS8UhY7hBvDPuVETbY8mdrM,8579 -pip/_vendor/urllib3/filepost.py,sha256=5b_qqgRHVlL7uLtdAYBzBh-GHmU5AfJVt_2N0XS3PeY,2440 -pip/_vendor/urllib3/packages/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_vendor/urllib3/packages/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/urllib3/packages/__pycache__/six.cpython-312.pyc,, -pip/_vendor/urllib3/packages/backports/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pip/_vendor/urllib3/packages/backports/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/urllib3/packages/backports/__pycache__/makefile.cpython-312.pyc,, -pip/_vendor/urllib3/packages/backports/__pycache__/weakref_finalize.cpython-312.pyc,, -pip/_vendor/urllib3/packages/backports/makefile.py,sha256=nbzt3i0agPVP07jqqgjhaYjMmuAi_W5E0EywZivVO8E,1417 -pip/_vendor/urllib3/packages/backports/weakref_finalize.py,sha256=tRCal5OAhNSRyb0DhHp-38AtIlCsRP8BxF3NX-6rqIA,5343 -pip/_vendor/urllib3/packages/six.py,sha256=b9LM0wBXv7E7SrbCjAm4wwN-hrH-iNxv18LgWNMMKPo,34665 -pip/_vendor/urllib3/poolmanager.py,sha256=0i8cJgrqupza67IBPZ_u9jXvnSxr5UBlVEiUqdkPtYI,19752 -pip/_vendor/urllib3/request.py,sha256=YTWFNr7QIwh7E1W9dde9LM77v2VWTJ5V78XuTTw7D1A,6691 -pip/_vendor/urllib3/response.py,sha256=fmDJAFkG71uFTn-sVSTh2Iw0WmcXQYqkbRjihvwBjU8,30641 -pip/_vendor/urllib3/util/__init__.py,sha256=JEmSmmqqLyaw8P51gUImZh8Gwg9i1zSe-DoqAitn2nc,1155 -pip/_vendor/urllib3/util/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/connection.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/proxy.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/queue.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/request.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/response.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/retry.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/ssl_.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/ssltransport.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/timeout.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/url.cpython-312.pyc,, -pip/_vendor/urllib3/util/__pycache__/wait.cpython-312.pyc,, -pip/_vendor/urllib3/util/connection.py,sha256=5Lx2B1PW29KxBn2T0xkN1CBgRBa3gGVJBKoQoRogEVk,4901 -pip/_vendor/urllib3/util/proxy.py,sha256=zUvPPCJrp6dOF0N4GAVbOcl6o-4uXKSrGiTkkr5vUS4,1605 -pip/_vendor/urllib3/util/queue.py,sha256=nRgX8_eX-_VkvxoX096QWoz8Ps0QHUAExILCY_7PncM,498 -pip/_vendor/urllib3/util/request.py,sha256=C0OUt2tcU6LRiQJ7YYNP9GvPrSvl7ziIBekQ-5nlBZk,3997 -pip/_vendor/urllib3/util/response.py,sha256=GJpg3Egi9qaJXRwBh5wv-MNuRWan5BIu40oReoxWP28,3510 -pip/_vendor/urllib3/util/retry.py,sha256=6ENvOZ8PBDzh8kgixpql9lIrb2dxH-k7ZmBanJF2Ng4,22050 -pip/_vendor/urllib3/util/ssl_.py,sha256=X4-AqW91aYPhPx6-xbf66yHFQKbqqfC_5Zt4WkLX1Hc,17177 -pip/_vendor/urllib3/util/ssl_match_hostname.py,sha256=Ir4cZVEjmAk8gUAIHWSi7wtOO83UCYABY2xFD1Ql_WA,5758 -pip/_vendor/urllib3/util/ssltransport.py,sha256=NA-u5rMTrDFDFC8QzRKUEKMG0561hOD4qBTr3Z4pv6E,6895 -pip/_vendor/urllib3/util/timeout.py,sha256=cwq4dMk87mJHSBktK1miYJ-85G-3T3RmT20v7SFCpno,10168 -pip/_vendor/urllib3/util/url.py,sha256=lCAE7M5myA8EDdW0sJuyyZhVB9K_j38ljWhHAnFaWoE,14296 -pip/_vendor/urllib3/util/wait.py,sha256=fOX0_faozG2P7iVojQoE1mbydweNyTcm-hXEfFrTtLI,5403 -pip/_vendor/vendor.txt,sha256=4NKk7fQhVsZw0U-0zmm9Q2LgGyaPXacFbnJAaS0Q6EY,493 -pip/_vendor/webencodings/__init__.py,sha256=qOBJIuPy_4ByYH6W_bNgJF-qYQ2DoU-dKsDu5yRWCXg,10579 -pip/_vendor/webencodings/__pycache__/__init__.cpython-312.pyc,, -pip/_vendor/webencodings/__pycache__/labels.cpython-312.pyc,, -pip/_vendor/webencodings/__pycache__/mklabels.cpython-312.pyc,, -pip/_vendor/webencodings/__pycache__/tests.cpython-312.pyc,, -pip/_vendor/webencodings/__pycache__/x_user_defined.cpython-312.pyc,, -pip/_vendor/webencodings/labels.py,sha256=4AO_KxTddqGtrL9ns7kAPjb0CcN6xsCIxbK37HY9r3E,8979 -pip/_vendor/webencodings/mklabels.py,sha256=GYIeywnpaLnP0GSic8LFWgd0UVvO_l1Nc6YoF-87R_4,1305 -pip/_vendor/webencodings/tests.py,sha256=OtGLyjhNY1fvkW1GvLJ_FV9ZoqC9Anyjr7q3kxTbzNs,6563 -pip/_vendor/webencodings/x_user_defined.py,sha256=yOqWSdmpytGfUgh_Z6JYgDNhoc-BAHyyeeT15Fr42tM,4307 -pip/py.typed,sha256=EBVvvPRTn_eIpz5e5QztSCdrMX7Qwd7VP93RSoIlZ2I,286 diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/WHEEL deleted file mode 100644 index 98c0d20..0000000 --- a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.42.0) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/AUTHORS.txt b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/AUTHORS.txt similarity index 93% rename from llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/AUTHORS.txt rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/AUTHORS.txt index 0e63548..f42daec 100644 --- a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/AUTHORS.txt +++ b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/AUTHORS.txt @@ -9,7 +9,9 @@ Adam Chainz Adam Tse Adam Wentz admin +Adolfo Ochagavía Adrien Morison +Agus ahayrapetyan Ahilya AinsworthK @@ -55,6 +57,7 @@ Anthony Sottile Antoine Musso Anton Ovchinnikov Anton Patrushev +Anton Zelenov Antonio Alvarado Hernandez Antony Lee Antti Kaihola @@ -63,8 +66,11 @@ Anudit Nagar Anuj Godase AQNOUCH Mohammed AraHaan +arena +arenasys Arindam Choudhury Armin Ronacher +Arnon Yaari Artem Arun Babu Neelicattu Ashley Manton @@ -100,8 +106,10 @@ Bogdan Opanchuk BorisZZZ Brad Erickson Bradley Ayers +Branch Vincent Brandon L. Reiss Brandt Bucher +Brannon Dorsey Brett Randall Brett Rosen Brian Cristante @@ -117,6 +125,7 @@ burrows Bussonnier Matthias bwoodsend c22 +Caleb Brown Caleb Martinez Calvin Smith Carl Meyer @@ -125,11 +134,14 @@ Carol Willing Carter Thayer Cass Chandrasekhar Atina +Charlie Marsh +charwick Chih-Hsuan Yen Chris Brinker Chris Hunt Chris Jerdonek Chris Kuehl +Chris Markiewicz Chris McDonough Chris Pawley Chris Pryer @@ -140,6 +152,7 @@ Christian Oudard Christoph Reiter Christopher Hunt Christopher Snyder +chrysle cjc7373 Clark Boylan Claudio Jolowicz @@ -157,6 +170,7 @@ Craig Kerstiens Cristian Sorinel Cristina Cristina Muñoz +ctg123 Curtis Doty cytolentino Daan De Meyer @@ -194,6 +208,7 @@ David Evans David Hewitt David Linke David Poggi +David Poznik David Pursehouse David Runge David Tucker @@ -207,11 +222,13 @@ dependabot[bot] derwolfe Desetude Devesh Kumar Singh +devsagul Diego Caraballo Diego Ramirez DiegoCaraballo Dimitri Merejkowsky Dimitri Papadopoulos +Dimitri Papadopoulos Orfanos Dirk Stolle Dmitry Gladkov Dmitry Volodin @@ -224,6 +241,7 @@ Dos Moonen Douglas Thor DrFeathers Dustin Ingram +Dustin Rodrigues Dwayne Bailey Ed Morley Edgar Ramírez @@ -265,6 +283,7 @@ Florian Briand Florian Rathgeber Francesco Francesco Montesano +Fredrik Orderud Frost Ming Gabriel Curio Gabriel de Perthuis @@ -315,6 +334,7 @@ Ian Stapleton Cordasco Ian Wienand Igor Kuzmitshov Igor Sobreira +Ikko Ashimine Ilan Schnell Illia Volochii Ilya Baryshev @@ -353,17 +373,20 @@ Jeff Dairiki Jeff Widman Jelmer Vernooij jenix21 +Jeremy Fleischman Jeremy Stanley Jeremy Zafran Jesse Rittner Jiashuo Li Jim Fisher Jim Garrison +Jinzhe Zeng Jiun Bae Jivan Amara Joe Bylund Joe Michelini John Paton +John Sirois John T. Wodder II John-Scott Atlakson johnthagen @@ -378,21 +401,26 @@ Jorge Niedbalski Joseph Bylund Joseph Long Josh Bronson +Josh Cannon Josh Hansen Josh Schneier Joshua +JoshuaPerdue Juan Luis Cano Rodríguez Juanjo Bazán Judah Rand Julian Berman Julian Gethmann Julien Demoor +July Tikhonov Jussi Kukkonen +Justin van Heek jwg4 Jyrki Pulliainen Kai Chen Kai Mueller Kamal Bin Mustafa +Karolina Surma kasium kaustav haldar keanemind @@ -408,9 +436,11 @@ Kexuan Sun Kit Randel Klaas van Schelven KOLANICH +konstin kpinc Krishna Oza Kumar McMillan +Kuntal Majumder Kurt McKee Kyle Persohn lakshmanaram @@ -428,6 +458,7 @@ lorddavidiii Loren Carvalho Lucas Cimon Ludovic Gasc +Luis Medel Lukas Geiger Lukas Juhrich Luke Macken @@ -441,11 +472,12 @@ Marc Tamlyn Marcus Smith Mariatta Mark Kohler +Mark McLoughlin Mark Williams Markus Hametner Martey Dodoo Martin Fischer -Martin Häcker +Martin Häcker Martin Pavlasek Masaki Masklinn @@ -457,10 +489,12 @@ Matt Bacchi Matt Good Matt Maker Matt Robenolt +Matt Wozniski matthew Matthew Einhorn Matthew Feickert Matthew Gilliard +Matthew Hughes Matthew Iversen Matthew Treinish Matthew Trumbell @@ -495,7 +529,9 @@ Miro Hrončok Monica Baluna montefra Monty Taylor -Muha Ajjan‮ +morotti +mrKazzila +Muha Ajjan Nadav Wexler Nahuel Ambrosini Nate Coraor @@ -559,7 +595,9 @@ Paweł Szramowski Pekka Klärck Peter Gessler Peter Lisák +Peter Shen Peter Waller +Petr Viktorin petr-tik Phaneendra Chiruvella Phil Elson @@ -592,6 +630,8 @@ Quentin Pradet R. David Murray Rafael Caricio Ralf Schmitt +Ran Benita +Randy Döring Razzi Abuissa rdb Reece Dunham @@ -603,6 +643,7 @@ Richard Jones Richard Si Ricky Ng-Adam Rishi +rmorotti RobberPhex Robert Collins Robert McGibbon @@ -624,6 +665,7 @@ Russell Keith-Magee Ryan Shepherd Ryan Wooden ryneeverett +S. Guliaev Sachi King Salvatore Rinchiera sandeepkiran-js @@ -642,8 +684,10 @@ Seth Michael Larson Seth Woodworth Shahar Epstein Shantanu +shenxianpeng shireenrao Shivansh-007 +Shixian Sheng Shlomi Fish Shovan Maity Simeon Visser @@ -655,6 +699,7 @@ snook92 socketubs Sorin Sbarnea Srinivas Nyayapati +Srishti Hegde Stavros Korokithakis Stefan Scherfke Stefano Rivera @@ -675,6 +720,7 @@ Stéphane Klein Sumana Harihareswara Surbhi Sharma Sviatoslav Sydorenko +Sviatoslav Sydorenko (Святослав Сидоренко) Swat009 Sylvain Takayuki SHIMIZUKAWA @@ -741,6 +787,7 @@ Wolfgang Maier Wu Zhenyu XAMES3 Xavier Fernandez +Xianpeng Shen xoviat xtreak YAMAMOTO Takashi @@ -757,4 +804,3 @@ Zvezdan Petkovic Łukasz Langa Роман Донченко Семён Марьясин -‮rekcäH nitraM‮ diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/INSTALLER similarity index 100% rename from llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/INSTALLER rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/INSTALLER diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/LICENSE.txt b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/LICENSE.txt similarity index 100% rename from llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/LICENSE.txt rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/LICENSE.txt diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/METADATA similarity index 89% rename from llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/METADATA rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/METADATA index e5b45bd..3315c06 100644 --- a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/METADATA +++ b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/METADATA @@ -1,6 +1,6 @@ -Metadata-Version: 2.1 +Metadata-Version: 2.2 Name: pip -Version: 24.0 +Version: 25.0.1 Summary: The PyPA recommended tool for installing Python packages. Author-email: The pip developers License: MIT @@ -15,15 +15,15 @@ Classifier: Topic :: Software Development :: Build Tools Classifier: Programming Language :: Python Classifier: Programming Language :: Python :: 3 Classifier: Programming Language :: Python :: 3 :: Only -Classifier: Programming Language :: Python :: 3.7 Classifier: Programming Language :: Python :: 3.8 Classifier: Programming Language :: Python :: 3.9 Classifier: Programming Language :: Python :: 3.10 Classifier: Programming Language :: Python :: 3.11 Classifier: Programming Language :: Python :: 3.12 +Classifier: Programming Language :: Python :: 3.13 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy -Requires-Python: >=3.7 +Requires-Python: >=3.8 Description-Content-Type: text/x-rst License-File: LICENSE.txt License-File: AUTHORS.txt @@ -31,18 +31,20 @@ License-File: AUTHORS.txt pip - The Python Package Installer ================================== -.. image:: https://img.shields.io/pypi/v/pip.svg +.. |pypi-version| image:: https://img.shields.io/pypi/v/pip.svg :target: https://pypi.org/project/pip/ :alt: PyPI -.. image:: https://img.shields.io/pypi/pyversions/pip +.. |python-versions| image:: https://img.shields.io/pypi/pyversions/pip :target: https://pypi.org/project/pip :alt: PyPI - Python Version -.. image:: https://readthedocs.org/projects/pip/badge/?version=latest +.. |docs-badge| image:: https://readthedocs.org/projects/pip/badge/?version=latest :target: https://pip.pypa.io/en/latest :alt: Documentation +|pypi-version| |python-versions| |docs-badge| + pip is the `package installer`_ for Python. You can use pip to install packages from the `Python Package Index`_ and other indexes. Please take a look at our documentation for how to install and use pip: diff --git a/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/RECORD new file mode 100644 index 0000000..7b6cf83 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/RECORD @@ -0,0 +1,854 @@ +../../../bin/pip,sha256=ylmpUKFndjlrNY_dt86VbK0KJESPnxFlWLqpFX3k9ek,246 +../../../bin/pip3,sha256=ylmpUKFndjlrNY_dt86VbK0KJESPnxFlWLqpFX3k9ek,246 +../../../bin/pip3.12,sha256=ylmpUKFndjlrNY_dt86VbK0KJESPnxFlWLqpFX3k9ek,246 +pip-25.0.1.dist-info/AUTHORS.txt,sha256=HqzpBVLfT1lBthqQfiDlVeFkg65hJ7ZQvvWhoq-BAsA,11018 +pip-25.0.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +pip-25.0.1.dist-info/LICENSE.txt,sha256=Y0MApmnUmurmWxLGxIySTFGkzfPR_whtw0VtyLyqIQQ,1093 +pip-25.0.1.dist-info/METADATA,sha256=T6cxjPMPl523zsRcEsu8K0-IoV8S7vv1mmKR0KA6-SY,3677 +pip-25.0.1.dist-info/RECORD,, +pip-25.0.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip-25.0.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91 +pip-25.0.1.dist-info/entry_points.txt,sha256=eeIjuzfnfR2PrhbjnbzFU6MnSS70kZLxwaHHq6M-bD0,87 +pip-25.0.1.dist-info/top_level.txt,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +pip/__init__.py,sha256=aKiv_sTe7UbE7qmtCinJutFjqN0MndZQZ1fKLNwFFLE,357 +pip/__main__.py,sha256=WzbhHXTbSE6gBY19mNN9m4s5o_365LOvTYSgqgbdBhE,854 +pip/__pip-runner__.py,sha256=cPPWuJ6NK_k-GzfvlejLFgwzmYUROmpAR6QC3Q-vkXQ,1450 +pip/__pycache__/__init__.cpython-312.pyc,, +pip/__pycache__/__main__.cpython-312.pyc,, +pip/__pycache__/__pip-runner__.cpython-312.pyc,, +pip/_internal/__init__.py,sha256=MfcoOluDZ8QMCFYal04IqOJ9q6m2V7a0aOsnI-WOxUo,513 +pip/_internal/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/__pycache__/build_env.cpython-312.pyc,, +pip/_internal/__pycache__/cache.cpython-312.pyc,, +pip/_internal/__pycache__/configuration.cpython-312.pyc,, +pip/_internal/__pycache__/exceptions.cpython-312.pyc,, +pip/_internal/__pycache__/main.cpython-312.pyc,, +pip/_internal/__pycache__/pyproject.cpython-312.pyc,, +pip/_internal/__pycache__/self_outdated_check.cpython-312.pyc,, +pip/_internal/__pycache__/wheel_builder.cpython-312.pyc,, +pip/_internal/build_env.py,sha256=Dv4UCClSg4uNaal_hL-trg5-zl3Is9CuIDxkChCkXF4,10700 +pip/_internal/cache.py,sha256=Jb698p5PNigRtpW5o26wQNkkUv4MnQ94mc471wL63A0,10369 +pip/_internal/cli/__init__.py,sha256=FkHBgpxxb-_gd6r1FjnNhfMOzAUYyXoXKJ6abijfcFU,132 +pip/_internal/cli/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/cli/__pycache__/autocompletion.cpython-312.pyc,, +pip/_internal/cli/__pycache__/base_command.cpython-312.pyc,, +pip/_internal/cli/__pycache__/cmdoptions.cpython-312.pyc,, +pip/_internal/cli/__pycache__/command_context.cpython-312.pyc,, +pip/_internal/cli/__pycache__/index_command.cpython-312.pyc,, +pip/_internal/cli/__pycache__/main.cpython-312.pyc,, +pip/_internal/cli/__pycache__/main_parser.cpython-312.pyc,, +pip/_internal/cli/__pycache__/parser.cpython-312.pyc,, +pip/_internal/cli/__pycache__/progress_bars.cpython-312.pyc,, +pip/_internal/cli/__pycache__/req_command.cpython-312.pyc,, +pip/_internal/cli/__pycache__/spinners.cpython-312.pyc,, +pip/_internal/cli/__pycache__/status_codes.cpython-312.pyc,, +pip/_internal/cli/autocompletion.py,sha256=Lli3Mr6aDNu7ZkJJFFvwD2-hFxNI6Avz8OwMyS5TVrs,6865 +pip/_internal/cli/base_command.py,sha256=NZin6KMzW9NSYzKk4Tc8isb_TQYKR4CKd5j9mSm46PI,8625 +pip/_internal/cli/cmdoptions.py,sha256=V3BB22F4_v_RkHaZ5onWnszhbBtjYZvNhbn9M0NO0HI,30116 +pip/_internal/cli/command_context.py,sha256=RHgIPwtObh5KhMrd3YZTkl8zbVG-6Okml7YbFX4Ehg0,774 +pip/_internal/cli/index_command.py,sha256=i_sgNlPmXC5iHUaY-dmmrHKKTgc5O4hWzisr5Al1rr0,5677 +pip/_internal/cli/main.py,sha256=BDZef-bWe9g9Jpr4OVs4dDf-845HJsKw835T7AqEnAc,2817 +pip/_internal/cli/main_parser.py,sha256=laDpsuBDl6kyfywp9eMMA9s84jfH2TJJn-vmL0GG90w,4338 +pip/_internal/cli/parser.py,sha256=VCMtduzECUV87KaHNu-xJ-wLNL82yT3x16V4XBxOAqI,10825 +pip/_internal/cli/progress_bars.py,sha256=9GcgusWtwfqou2zhAQp1XNbQHIDslqyyz9UwLzw7Jgc,2717 +pip/_internal/cli/req_command.py,sha256=DqeFhmUMs6o6Ev8qawAcOoYNdAZsfyKS0MZI5jsJYwQ,12250 +pip/_internal/cli/spinners.py,sha256=hIJ83GerdFgFCdobIA23Jggetegl_uC4Sp586nzFbPE,5118 +pip/_internal/cli/status_codes.py,sha256=sEFHUaUJbqv8iArL3HAtcztWZmGOFX01hTesSytDEh0,116 +pip/_internal/commands/__init__.py,sha256=5oRO9O3dM2vGuh0bFw4HOVletryrz5HHMmmPWwJrH9U,3882 +pip/_internal/commands/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/commands/__pycache__/cache.cpython-312.pyc,, +pip/_internal/commands/__pycache__/check.cpython-312.pyc,, +pip/_internal/commands/__pycache__/completion.cpython-312.pyc,, +pip/_internal/commands/__pycache__/configuration.cpython-312.pyc,, +pip/_internal/commands/__pycache__/debug.cpython-312.pyc,, +pip/_internal/commands/__pycache__/download.cpython-312.pyc,, +pip/_internal/commands/__pycache__/freeze.cpython-312.pyc,, +pip/_internal/commands/__pycache__/hash.cpython-312.pyc,, +pip/_internal/commands/__pycache__/help.cpython-312.pyc,, +pip/_internal/commands/__pycache__/index.cpython-312.pyc,, +pip/_internal/commands/__pycache__/inspect.cpython-312.pyc,, +pip/_internal/commands/__pycache__/install.cpython-312.pyc,, +pip/_internal/commands/__pycache__/list.cpython-312.pyc,, +pip/_internal/commands/__pycache__/search.cpython-312.pyc,, +pip/_internal/commands/__pycache__/show.cpython-312.pyc,, +pip/_internal/commands/__pycache__/uninstall.cpython-312.pyc,, +pip/_internal/commands/__pycache__/wheel.cpython-312.pyc,, +pip/_internal/commands/cache.py,sha256=IOezTicHjGE5sWdBx2nwPVgbjuJHM3s-BZEkpZLemuY,8107 +pip/_internal/commands/check.py,sha256=Hr_4eiMd9cgVDgEvjtIdw915NmL7ROIWW8enkr8slPQ,2268 +pip/_internal/commands/completion.py,sha256=HT4lD0bgsflHq2IDgYfiEdp7IGGtE7s6MgI3xn0VQEw,4287 +pip/_internal/commands/configuration.py,sha256=n98enwp6y0b5G6fiRQjaZo43FlJKYve_daMhN-4BRNc,9766 +pip/_internal/commands/debug.py,sha256=DNDRgE9YsKrbYzU0s3VKi8rHtKF4X13CJ_br_8PUXO0,6797 +pip/_internal/commands/download.py,sha256=0qB0nys6ZEPsog451lDsjL5Bx7Z97t-B80oFZKhpzKM,5273 +pip/_internal/commands/freeze.py,sha256=2Vt72BYTSm9rzue6d8dNzt8idxWK4Db6Hd-anq7GQ80,3203 +pip/_internal/commands/hash.py,sha256=EVVOuvGtoPEdFi8SNnmdqlCQrhCxV-kJsdwtdcCnXGQ,1703 +pip/_internal/commands/help.py,sha256=gcc6QDkcgHMOuAn5UxaZwAStsRBrnGSn_yxjS57JIoM,1132 +pip/_internal/commands/index.py,sha256=RAXxmJwFhVb5S1BYzb5ifX3sn9Na8v2CCVYwSMP8pao,4731 +pip/_internal/commands/inspect.py,sha256=PGrY9TRTRCM3y5Ml8Bdk8DEOXquWRfscr4DRo1LOTPc,3189 +pip/_internal/commands/install.py,sha256=r3yHQUxvxt7gD5j9n6zRDslAvtx9CT_whLuQJcktp6M,29390 +pip/_internal/commands/list.py,sha256=oiIzSjLP6__d7dIS3q0Xb5ywsaOThBWRqMyjjKzkPdM,12769 +pip/_internal/commands/search.py,sha256=fWkUQVx_gm8ebbFAlCgqtxKXT9rNahpJ-BI__3HNZpg,5626 +pip/_internal/commands/show.py,sha256=0YBhCga3PAd81vT3l7UWflktSpB5-aYqQcJxBVPazVM,7857 +pip/_internal/commands/uninstall.py,sha256=7pOR7enK76gimyxQbzxcG1OsyLXL3DvX939xmM8Fvtg,3892 +pip/_internal/commands/wheel.py,sha256=eJRhr_qoNNxWAkkdJCNiQM7CXd4E1_YyQhsqJnBPGGg,6414 +pip/_internal/configuration.py,sha256=-KOok6jh3hFzXMPQFPJ1_EFjBpAsge-RSreQuLHLmzo,14005 +pip/_internal/distributions/__init__.py,sha256=Hq6kt6gXBgjNit5hTTWLAzeCNOKoB-N0pGYSqehrli8,858 +pip/_internal/distributions/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/distributions/__pycache__/base.cpython-312.pyc,, +pip/_internal/distributions/__pycache__/installed.cpython-312.pyc,, +pip/_internal/distributions/__pycache__/sdist.cpython-312.pyc,, +pip/_internal/distributions/__pycache__/wheel.cpython-312.pyc,, +pip/_internal/distributions/base.py,sha256=QeB9qvKXDIjLdPBDE5fMgpfGqMMCr-govnuoQnGuiF8,1783 +pip/_internal/distributions/installed.py,sha256=QinHFbWAQ8oE0pbD8MFZWkwlnfU1QYTccA1vnhrlYOU,842 +pip/_internal/distributions/sdist.py,sha256=PlcP4a6-R6c98XnOM-b6Lkb3rsvh9iG4ok8shaanrzs,6751 +pip/_internal/distributions/wheel.py,sha256=THBYfnv7VVt8mYhMYUtH13S1E7FDwtDyDfmUcl8ai0E,1317 +pip/_internal/exceptions.py,sha256=2_byISIv3kSnI_9T-Esfxrt0LnTRgcUHyxu0twsHjQY,26481 +pip/_internal/index/__init__.py,sha256=vpt-JeTZefh8a-FC22ZeBSXFVbuBcXSGiILhQZJaNpQ,30 +pip/_internal/index/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/index/__pycache__/collector.cpython-312.pyc,, +pip/_internal/index/__pycache__/package_finder.cpython-312.pyc,, +pip/_internal/index/__pycache__/sources.cpython-312.pyc,, +pip/_internal/index/collector.py,sha256=RdPO0JLAlmyBWPAWYHPyRoGjz3GNAeTngCNkbGey_mE,16265 +pip/_internal/index/package_finder.py,sha256=mJHAljlHeHuclyuxtjvBZO6DtovKjsZjF_tCh_wux5E,38076 +pip/_internal/index/sources.py,sha256=lPBLK5Xiy8Q6IQMio26Wl7ocfZOKkgGklIBNyUJ23fI,8632 +pip/_internal/locations/__init__.py,sha256=UaAxeZ_f93FyouuFf4p7SXYF-4WstXuEvd3LbmPCAno,14925 +pip/_internal/locations/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/locations/__pycache__/_distutils.cpython-312.pyc,, +pip/_internal/locations/__pycache__/_sysconfig.cpython-312.pyc,, +pip/_internal/locations/__pycache__/base.cpython-312.pyc,, +pip/_internal/locations/_distutils.py,sha256=x6nyVLj7X11Y4khIdf-mFlxMl2FWadtVEgeb8upc_WI,6013 +pip/_internal/locations/_sysconfig.py,sha256=IGzds60qsFneRogC-oeBaY7bEh3lPt_v47kMJChQXsU,7724 +pip/_internal/locations/base.py,sha256=RQiPi1d4FVM2Bxk04dQhXZ2PqkeljEL2fZZ9SYqIQ78,2556 +pip/_internal/main.py,sha256=r-UnUe8HLo5XFJz8inTcOOTiu_sxNhgHb6VwlGUllOI,340 +pip/_internal/metadata/__init__.py,sha256=CU8jK1TZso7jOLdr0sX9xDjrcs5iy8d7IRK-hvaIO5Y,4337 +pip/_internal/metadata/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/metadata/__pycache__/_json.cpython-312.pyc,, +pip/_internal/metadata/__pycache__/base.cpython-312.pyc,, +pip/_internal/metadata/__pycache__/pkg_resources.cpython-312.pyc,, +pip/_internal/metadata/_json.py,sha256=ezrIYazHCINM2QUk1eA9wEAMj3aeGWeDVgGalgUzKpc,2707 +pip/_internal/metadata/base.py,sha256=ft0K5XNgI4ETqZnRv2-CtvgYiMOMAeGMAzxT-f6VLJA,25298 +pip/_internal/metadata/importlib/__init__.py,sha256=jUUidoxnHcfITHHaAWG1G2i5fdBYklv_uJcjo2x7VYE,135 +pip/_internal/metadata/importlib/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/metadata/importlib/__pycache__/_compat.cpython-312.pyc,, +pip/_internal/metadata/importlib/__pycache__/_dists.cpython-312.pyc,, +pip/_internal/metadata/importlib/__pycache__/_envs.cpython-312.pyc,, +pip/_internal/metadata/importlib/_compat.py,sha256=c6av8sP8BBjAZuFSJow1iWfygUXNM3xRTCn5nqw6B9M,2796 +pip/_internal/metadata/importlib/_dists.py,sha256=ftmYiyfUGUIjnVwt6W-Ijsimy5c28KgmXly5Q5IQ2P4,8279 +pip/_internal/metadata/importlib/_envs.py,sha256=UUB980XSrDWrMpQ1_G45i0r8Hqlg_tg3IPQ63mEqbNc,7431 +pip/_internal/metadata/pkg_resources.py,sha256=U07ETAINSGeSRBfWUG93E4tZZbaW_f7PGzEqZN0hulc,10542 +pip/_internal/models/__init__.py,sha256=3DHUd_qxpPozfzouoqa9g9ts1Czr5qaHfFxbnxriepM,63 +pip/_internal/models/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/models/__pycache__/candidate.cpython-312.pyc,, +pip/_internal/models/__pycache__/direct_url.cpython-312.pyc,, +pip/_internal/models/__pycache__/format_control.cpython-312.pyc,, +pip/_internal/models/__pycache__/index.cpython-312.pyc,, +pip/_internal/models/__pycache__/installation_report.cpython-312.pyc,, +pip/_internal/models/__pycache__/link.cpython-312.pyc,, +pip/_internal/models/__pycache__/scheme.cpython-312.pyc,, +pip/_internal/models/__pycache__/search_scope.cpython-312.pyc,, +pip/_internal/models/__pycache__/selection_prefs.cpython-312.pyc,, +pip/_internal/models/__pycache__/target_python.cpython-312.pyc,, +pip/_internal/models/__pycache__/wheel.cpython-312.pyc,, +pip/_internal/models/candidate.py,sha256=zzgFRuw_kWPjKpGw7LC0ZUMD2CQ2EberUIYs8izjdCA,753 +pip/_internal/models/direct_url.py,sha256=uBtY2HHd3TO9cKQJWh0ThvE5FRr-MWRYChRU4IG9HZE,6578 +pip/_internal/models/format_control.py,sha256=wtsQqSK9HaUiNxQEuB-C62eVimw6G4_VQFxV9-_KDBE,2486 +pip/_internal/models/index.py,sha256=tYnL8oxGi4aSNWur0mG8DAP7rC6yuha_MwJO8xw0crI,1030 +pip/_internal/models/installation_report.py,sha256=zRVZoaz-2vsrezj_H3hLOhMZCK9c7TbzWgC-jOalD00,2818 +pip/_internal/models/link.py,sha256=GQ8hq7x-FDFPv25Nbn2veIM-MlBrGZDGLd7aZeF4Xrg,21448 +pip/_internal/models/scheme.py,sha256=PakmHJM3e8OOWSZFtfz1Az7f1meONJnkGuQxFlt3wBE,575 +pip/_internal/models/search_scope.py,sha256=67NEnsYY84784S-MM7ekQuo9KXLH-7MzFntXjapvAo0,4531 +pip/_internal/models/selection_prefs.py,sha256=qaFfDs3ciqoXPg6xx45N1jPLqccLJw4N0s4P0PyHTQ8,2015 +pip/_internal/models/target_python.py,sha256=2XaH2rZ5ZF-K5wcJbEMGEl7SqrTToDDNkrtQ2v_v_-Q,4271 +pip/_internal/models/wheel.py,sha256=G7dND_s4ebPkEL7RJ1qCY0QhUUWIIK6AnjWgRATF5no,4539 +pip/_internal/network/__init__.py,sha256=jf6Tt5nV_7zkARBrKojIXItgejvoegVJVKUbhAa5Ioc,50 +pip/_internal/network/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/network/__pycache__/auth.cpython-312.pyc,, +pip/_internal/network/__pycache__/cache.cpython-312.pyc,, +pip/_internal/network/__pycache__/download.cpython-312.pyc,, +pip/_internal/network/__pycache__/lazy_wheel.cpython-312.pyc,, +pip/_internal/network/__pycache__/session.cpython-312.pyc,, +pip/_internal/network/__pycache__/utils.cpython-312.pyc,, +pip/_internal/network/__pycache__/xmlrpc.cpython-312.pyc,, +pip/_internal/network/auth.py,sha256=D4gASjUrqoDFlSt6gQ767KAAjv6PUyJU0puDlhXNVRE,20809 +pip/_internal/network/cache.py,sha256=0yGMA3Eet59xBSLtbPAenvI53dl29oUOeqZ2c0QL2Ss,4614 +pip/_internal/network/download.py,sha256=FLOP29dPYECBiAi7eEjvAbNkyzaKNqbyjOT2m8HPW8U,6048 +pip/_internal/network/lazy_wheel.py,sha256=PBdoMoNQQIA84Fhgne38jWF52W4x_KtsHjxgv4dkRKA,7622 +pip/_internal/network/session.py,sha256=msM4es16LmmNEYNkrYyg8fTc7gAHbKFltawfKP27LOI,18771 +pip/_internal/network/utils.py,sha256=Inaxel-NxBu4PQWkjyErdnfewsFCcgHph7dzR1-FboY,4088 +pip/_internal/network/xmlrpc.py,sha256=sAxzOacJ-N1NXGPvap9jC3zuYWSnnv3GXtgR2-E2APA,1838 +pip/_internal/operations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_internal/operations/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/operations/__pycache__/check.cpython-312.pyc,, +pip/_internal/operations/__pycache__/freeze.cpython-312.pyc,, +pip/_internal/operations/__pycache__/prepare.cpython-312.pyc,, +pip/_internal/operations/build/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_internal/operations/build/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/operations/build/__pycache__/build_tracker.cpython-312.pyc,, +pip/_internal/operations/build/__pycache__/metadata.cpython-312.pyc,, +pip/_internal/operations/build/__pycache__/metadata_editable.cpython-312.pyc,, +pip/_internal/operations/build/__pycache__/metadata_legacy.cpython-312.pyc,, +pip/_internal/operations/build/__pycache__/wheel.cpython-312.pyc,, +pip/_internal/operations/build/__pycache__/wheel_editable.cpython-312.pyc,, +pip/_internal/operations/build/__pycache__/wheel_legacy.cpython-312.pyc,, +pip/_internal/operations/build/build_tracker.py,sha256=-ARW_TcjHCOX7D2NUOGntB4Fgc6b4aolsXkAK6BWL7w,4774 +pip/_internal/operations/build/metadata.py,sha256=9S0CUD8U3QqZeXp-Zyt8HxwU90lE4QrnYDgrqZDzBnc,1422 +pip/_internal/operations/build/metadata_editable.py,sha256=xlAwcP9q_8_fmv_3I39w9EZ7SQV9hnJZr9VuTsq2Y68,1510 +pip/_internal/operations/build/metadata_legacy.py,sha256=8i6i1QZX9m_lKPStEFsHKM0MT4a-CD408JOw99daLmo,2190 +pip/_internal/operations/build/wheel.py,sha256=sT12FBLAxDC6wyrDorh8kvcZ1jG5qInCRWzzP-UkJiQ,1075 +pip/_internal/operations/build/wheel_editable.py,sha256=yOtoH6zpAkoKYEUtr8FhzrYnkNHQaQBjWQ2HYae1MQg,1417 +pip/_internal/operations/build/wheel_legacy.py,sha256=K-6kNhmj-1xDF45ny1yheMerF0ui4EoQCLzEoHh6-tc,3045 +pip/_internal/operations/check.py,sha256=L24vRL8VWbyywdoeAhM89WCd8zLTnjIbULlKelUgIec,5912 +pip/_internal/operations/freeze.py,sha256=1_M79jAQKnCxWr-KCCmHuVXOVFGaUJHmoWLfFzgh7K4,9843 +pip/_internal/operations/install/__init__.py,sha256=mX7hyD2GNBO2mFGokDQ30r_GXv7Y_PLdtxcUv144e-s,51 +pip/_internal/operations/install/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/operations/install/__pycache__/editable_legacy.cpython-312.pyc,, +pip/_internal/operations/install/__pycache__/wheel.cpython-312.pyc,, +pip/_internal/operations/install/editable_legacy.py,sha256=PoEsNEPGbIZ2yQphPsmYTKLOCMs4gv5OcCdzW124NcA,1283 +pip/_internal/operations/install/wheel.py,sha256=X5Iz9yUg5LlK5VNQ9g2ikc6dcRu8EPi_SUi5iuEDRgo,27615 +pip/_internal/operations/prepare.py,sha256=joWJwPkuqGscQgVNImLK71e9hRapwKvRCM8HclysmvU,28118 +pip/_internal/pyproject.py,sha256=GLJ6rWRS5_2noKdajohoLyDty57Z7QXhcUAYghmTnWc,7286 +pip/_internal/req/__init__.py,sha256=HxBFtZy_BbCclLgr26waMtpzYdO5T3vxePvpGAXSt5s,2653 +pip/_internal/req/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/req/__pycache__/constructors.cpython-312.pyc,, +pip/_internal/req/__pycache__/req_file.cpython-312.pyc,, +pip/_internal/req/__pycache__/req_install.cpython-312.pyc,, +pip/_internal/req/__pycache__/req_set.cpython-312.pyc,, +pip/_internal/req/__pycache__/req_uninstall.cpython-312.pyc,, +pip/_internal/req/constructors.py,sha256=v1qzCN1mIldwx-nCrPc8JO4lxkm3Fv8M5RWvt8LISjc,18430 +pip/_internal/req/req_file.py,sha256=eys82McgaICOGic2UZRHjD720piKJPwmeSYdXlWwl6w,20234 +pip/_internal/req/req_install.py,sha256=BMptxHYg2uG_b-7HFEULPb3nuw0FMAbuea8zTq2rE7w,35786 +pip/_internal/req/req_set.py,sha256=j3esG0s6SzoVReX9rWn4rpYNtyET_fwxbwJPRimvRxo,2858 +pip/_internal/req/req_uninstall.py,sha256=qzDIxJo-OETWqGais7tSMCDcWbATYABT-Tid3ityF0s,23853 +pip/_internal/resolution/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_internal/resolution/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/resolution/__pycache__/base.cpython-312.pyc,, +pip/_internal/resolution/base.py,sha256=qlmh325SBVfvG6Me9gc5Nsh5sdwHBwzHBq6aEXtKsLA,583 +pip/_internal/resolution/legacy/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_internal/resolution/legacy/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/resolution/legacy/__pycache__/resolver.cpython-312.pyc,, +pip/_internal/resolution/legacy/resolver.py,sha256=3HZiJBRd1FTN6jQpI4qRO8-TbLYeIbUTS6PFvXnXs2w,24068 +pip/_internal/resolution/resolvelib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_internal/resolution/resolvelib/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/base.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/candidates.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/factory.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/found_candidates.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/provider.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/reporter.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/requirements.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/__pycache__/resolver.cpython-312.pyc,, +pip/_internal/resolution/resolvelib/base.py,sha256=DCf669FsqyQY5uqXeePDHQY1e4QO-pBzWH8O0s9-K94,5023 +pip/_internal/resolution/resolvelib/candidates.py,sha256=5UZ1upNnmqsP-nmEZaDYxaBgCoejw_e2WVGmmAvBxXc,20001 +pip/_internal/resolution/resolvelib/factory.py,sha256=MJOLSZJY8_28PPdcutoQ6gjJ_1eBDt6Z1edtfTJyR4E,32659 +pip/_internal/resolution/resolvelib/found_candidates.py,sha256=9hrTyQqFvl9I7Tji79F1AxHv39Qh1rkJ_7deSHSMfQc,6383 +pip/_internal/resolution/resolvelib/provider.py,sha256=bcsFnYvlmtB80cwVdW1fIwgol8ZNr1f1VHyRTkz47SM,9935 +pip/_internal/resolution/resolvelib/reporter.py,sha256=00JtoXEkTlw0-rl_sl54d71avwOsJHt9GGHcrj5Sza0,3168 +pip/_internal/resolution/resolvelib/requirements.py,sha256=7JG4Z72e5Yk4vU0S5ulGvbqTy4FMQGYhY5zQhX9zTtY,8065 +pip/_internal/resolution/resolvelib/resolver.py,sha256=nLJOsVMEVi2gQUVJoUFKMZAeu2f7GRMjGMvNSWyz0Bc,12592 +pip/_internal/self_outdated_check.py,sha256=1PFtttvLAeyCVR3tPoBq2sOlPD0IJ-KSqU6bc1HUk9c,8318 +pip/_internal/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_internal/utils/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/utils/__pycache__/_jaraco_text.cpython-312.pyc,, +pip/_internal/utils/__pycache__/_log.cpython-312.pyc,, +pip/_internal/utils/__pycache__/appdirs.cpython-312.pyc,, +pip/_internal/utils/__pycache__/compat.cpython-312.pyc,, +pip/_internal/utils/__pycache__/compatibility_tags.cpython-312.pyc,, +pip/_internal/utils/__pycache__/datetime.cpython-312.pyc,, +pip/_internal/utils/__pycache__/deprecation.cpython-312.pyc,, +pip/_internal/utils/__pycache__/direct_url_helpers.cpython-312.pyc,, +pip/_internal/utils/__pycache__/egg_link.cpython-312.pyc,, +pip/_internal/utils/__pycache__/entrypoints.cpython-312.pyc,, +pip/_internal/utils/__pycache__/filesystem.cpython-312.pyc,, +pip/_internal/utils/__pycache__/filetypes.cpython-312.pyc,, +pip/_internal/utils/__pycache__/glibc.cpython-312.pyc,, +pip/_internal/utils/__pycache__/hashes.cpython-312.pyc,, +pip/_internal/utils/__pycache__/logging.cpython-312.pyc,, +pip/_internal/utils/__pycache__/misc.cpython-312.pyc,, +pip/_internal/utils/__pycache__/packaging.cpython-312.pyc,, +pip/_internal/utils/__pycache__/retry.cpython-312.pyc,, +pip/_internal/utils/__pycache__/setuptools_build.cpython-312.pyc,, +pip/_internal/utils/__pycache__/subprocess.cpython-312.pyc,, +pip/_internal/utils/__pycache__/temp_dir.cpython-312.pyc,, +pip/_internal/utils/__pycache__/unpacking.cpython-312.pyc,, +pip/_internal/utils/__pycache__/urls.cpython-312.pyc,, +pip/_internal/utils/__pycache__/virtualenv.cpython-312.pyc,, +pip/_internal/utils/__pycache__/wheel.cpython-312.pyc,, +pip/_internal/utils/_jaraco_text.py,sha256=M15uUPIh5NpP1tdUGBxRau6q1ZAEtI8-XyLEETscFfE,3350 +pip/_internal/utils/_log.py,sha256=-jHLOE_THaZz5BFcCnoSL9EYAtJ0nXem49s9of4jvKw,1015 +pip/_internal/utils/appdirs.py,sha256=swgcTKOm3daLeXTW6v5BUS2Ti2RvEnGRQYH_yDXklAo,1665 +pip/_internal/utils/compat.py,sha256=ckkFveBiYQjRWjkNsajt_oWPS57tJvE8XxoC4OIYgCY,2399 +pip/_internal/utils/compatibility_tags.py,sha256=OWq5axHpW-MEEPztGdvgADrgJPAcV9a88Rxm4Z8VBs8,6272 +pip/_internal/utils/datetime.py,sha256=m21Y3wAtQc-ji6Veb6k_M5g6A0ZyFI4egchTdnwh-pQ,242 +pip/_internal/utils/deprecation.py,sha256=k7Qg_UBAaaTdyq82YVARA6D7RmcGTXGv7fnfcgigj4Q,3707 +pip/_internal/utils/direct_url_helpers.py,sha256=r2MRtkVDACv9AGqYODBUC9CjwgtsUU1s68hmgfCJMtA,3196 +pip/_internal/utils/egg_link.py,sha256=0FePZoUYKv4RGQ2t6x7w5Z427wbA_Uo3WZnAkrgsuqo,2463 +pip/_internal/utils/entrypoints.py,sha256=YlhLTRl2oHBAuqhc-zmL7USS67TPWVHImjeAQHreZTQ,3064 +pip/_internal/utils/filesystem.py,sha256=ajvA-q4ocliW9kPp8Yquh-4vssXbu-UKbo5FV9V4X64,4950 +pip/_internal/utils/filetypes.py,sha256=i8XAQ0eFCog26Fw9yV0Yb1ygAqKYB1w9Cz9n0fj8gZU,716 +pip/_internal/utils/glibc.py,sha256=vUkWq_1pJuzcYNcGKLlQmABoUiisK8noYY1yc8Wq4w4,3734 +pip/_internal/utils/hashes.py,sha256=XGGLL0AG8-RhWnyz87xF6MFZ--BKadHU35D47eApCKI,4972 +pip/_internal/utils/logging.py,sha256=ONfbrhaD248akkosK79if97n20EABxwjOxp5dE5RCRY,11845 +pip/_internal/utils/misc.py,sha256=DWnYxBUItjRp7hhxEg4ih6P6YpKrykM86dbi_EcU8SQ,23450 +pip/_internal/utils/packaging.py,sha256=cm-X_0HVHV_jRwUVZh6AuEWqSitzf8EpaJ7Uv2UGu6A,2142 +pip/_internal/utils/retry.py,sha256=mhFbykXjhTnZfgzeuy-vl9c8nECnYn_CMtwNJX2tYzQ,1392 +pip/_internal/utils/setuptools_build.py,sha256=ouXpud-jeS8xPyTPsXJ-m34NPvK5os45otAzdSV_IJE,4435 +pip/_internal/utils/subprocess.py,sha256=EsvqSRiSMHF98T8Txmu6NLU3U--MpTTQjtNgKP0P--M,8988 +pip/_internal/utils/temp_dir.py,sha256=5qOXe8M4JeY6vaFQM867d5zkp1bSwMZ-KT5jymmP0Zg,9310 +pip/_internal/utils/unpacking.py,sha256=_gVdyzTRDMYktpnYljn4OoxrZTtMCf4xknSm4rK0WaA,11967 +pip/_internal/utils/urls.py,sha256=qceSOZb5lbNDrHNsv7_S4L4Ytszja5NwPKUMnZHbYnM,1599 +pip/_internal/utils/virtualenv.py,sha256=S6f7csYorRpiD6cvn3jISZYc3I8PJC43H5iMFpRAEDU,3456 +pip/_internal/utils/wheel.py,sha256=b442jkydFHjXzDy6cMR7MpzWBJ1Q82hR5F33cmcHV3g,4494 +pip/_internal/vcs/__init__.py,sha256=UAqvzpbi0VbZo3Ub6skEeZAw-ooIZR-zX_WpCbxyCoU,596 +pip/_internal/vcs/__pycache__/__init__.cpython-312.pyc,, +pip/_internal/vcs/__pycache__/bazaar.cpython-312.pyc,, +pip/_internal/vcs/__pycache__/git.cpython-312.pyc,, +pip/_internal/vcs/__pycache__/mercurial.cpython-312.pyc,, +pip/_internal/vcs/__pycache__/subversion.cpython-312.pyc,, +pip/_internal/vcs/__pycache__/versioncontrol.cpython-312.pyc,, +pip/_internal/vcs/bazaar.py,sha256=EKStcQaKpNu0NK4p5Q10Oc4xb3DUxFw024XrJy40bFQ,3528 +pip/_internal/vcs/git.py,sha256=3tpc9LQA_J4IVW5r5NvWaaSeDzcmJOrSFZN0J8vIKfU,18177 +pip/_internal/vcs/mercurial.py,sha256=oULOhzJ2Uie-06d1omkL-_Gc6meGaUkyogvqG9ZCyPs,5249 +pip/_internal/vcs/subversion.py,sha256=ddTugHBqHzV3ebKlU5QXHPN4gUqlyXbOx8q8NgXKvs8,11735 +pip/_internal/vcs/versioncontrol.py,sha256=cvf_-hnTAjQLXJ3d17FMNhQfcO1AcKWUF10tfrYyP-c,22440 +pip/_internal/wheel_builder.py,sha256=DL3A8LKeRj_ACp11WS5wSgASgPFqeyAeXJKdXfmaWXU,11799 +pip/_vendor/__init__.py,sha256=JYuAXvClhInxIrA2FTp5p-uuWVL7WV6-vEpTs46-Qh4,4873 +pip/_vendor/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/__pycache__/typing_extensions.cpython-312.pyc,, +pip/_vendor/cachecontrol/__init__.py,sha256=LMC5CBe94ZRL5xhlzwyPDmHXvBD0p7lT4R3Z73D6a_I,677 +pip/_vendor/cachecontrol/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/_cmd.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/adapter.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/cache.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/controller.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/filewrapper.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/heuristics.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/serialize.cpython-312.pyc,, +pip/_vendor/cachecontrol/__pycache__/wrapper.cpython-312.pyc,, +pip/_vendor/cachecontrol/_cmd.py,sha256=iist2EpzJvDVIhMAxXq8iFnTBsiZAd6iplxfmNboNyk,1737 +pip/_vendor/cachecontrol/adapter.py,sha256=febjY4LV87iiCIK3jcl8iH58iaSA7b9WkovsByIDK0Y,6348 +pip/_vendor/cachecontrol/cache.py,sha256=OXwv7Fn2AwnKNiahJHnjtvaKLndvVLv_-zO-ltlV9qI,1953 +pip/_vendor/cachecontrol/caches/__init__.py,sha256=dtrrroK5BnADR1GWjCZ19aZ0tFsMfvFBtLQQU1sp_ag,303 +pip/_vendor/cachecontrol/caches/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/cachecontrol/caches/__pycache__/file_cache.cpython-312.pyc,, +pip/_vendor/cachecontrol/caches/__pycache__/redis_cache.cpython-312.pyc,, +pip/_vendor/cachecontrol/caches/file_cache.py,sha256=b7oMgsRSqPmEsonVJw6uFEYUlFgD6GF8TyacOGG1x3M,5399 +pip/_vendor/cachecontrol/caches/redis_cache.py,sha256=9rmqwtYu_ljVkW6_oLqbC7EaX_a8YT_yLuna-eS0dgo,1386 +pip/_vendor/cachecontrol/controller.py,sha256=glbPj2iZlGqdBg8z09D2DtQOzoOGXnWvy7K2LEyBsEQ,18576 +pip/_vendor/cachecontrol/filewrapper.py,sha256=2ktXNPE0KqnyzF24aOsKCA58HQq1xeC6l2g6_zwjghc,4291 +pip/_vendor/cachecontrol/heuristics.py,sha256=gqMXU8w0gQuEQiSdu3Yg-0vd9kW7nrWKbLca75rheGE,4881 +pip/_vendor/cachecontrol/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/cachecontrol/serialize.py,sha256=HQd2IllQ05HzPkVLMXTF2uX5mjEQjDBkxCqUJUODpZk,5163 +pip/_vendor/cachecontrol/wrapper.py,sha256=hsGc7g8QGQTT-4f8tgz3AM5qwScg6FO0BSdLSRdEvpU,1417 +pip/_vendor/certifi/__init__.py,sha256=p_GYZrjUwPBUhpLlCZoGb0miKBKSqDAyZC5DvIuqbHQ,94 +pip/_vendor/certifi/__main__.py,sha256=1k3Cr95vCxxGRGDljrW3wMdpZdL3Nhf0u1n-k2qdsCY,255 +pip/_vendor/certifi/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/certifi/__pycache__/__main__.cpython-312.pyc,, +pip/_vendor/certifi/__pycache__/core.cpython-312.pyc,, +pip/_vendor/certifi/cacert.pem,sha256=lO3rZukXdPyuk6BWUJFOKQliWaXH6HGh9l1GGrUgG0c,299427 +pip/_vendor/certifi/core.py,sha256=2SRT5rIcQChFDbe37BQa-kULxAgJ8qN6l1jfqTp4HIs,4486 +pip/_vendor/certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/distlib/__init__.py,sha256=dcwgYGYGQqAEawBXPDtIx80DO_3cOmFv8HTc8JMzknQ,625 +pip/_vendor/distlib/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/compat.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/database.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/index.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/locators.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/manifest.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/markers.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/metadata.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/resources.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/scripts.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/util.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/version.cpython-312.pyc,, +pip/_vendor/distlib/__pycache__/wheel.cpython-312.pyc,, +pip/_vendor/distlib/compat.py,sha256=2jRSjRI4o-vlXeTK2BCGIUhkc6e9ZGhSsacRM5oseTw,41467 +pip/_vendor/distlib/database.py,sha256=mHy_LxiXIsIVRb-T0-idBrVLw3Ffij5teHCpbjmJ9YU,51160 +pip/_vendor/distlib/index.py,sha256=lTbw268rRhj8dw1sib3VZ_0EhSGgoJO3FKJzSFMOaeA,20797 +pip/_vendor/distlib/locators.py,sha256=oBeAZpFuPQSY09MgNnLfQGGAXXvVO96BFpZyKMuK4tM,51026 +pip/_vendor/distlib/manifest.py,sha256=3qfmAmVwxRqU1o23AlfXrQGZzh6g_GGzTAP_Hb9C5zQ,14168 +pip/_vendor/distlib/markers.py,sha256=X6sDvkFGcYS8gUW8hfsWuKEKAqhQZAJ7iXOMLxRYjYk,5164 +pip/_vendor/distlib/metadata.py,sha256=zil3sg2EUfLXVigljY2d_03IJt-JSs7nX-73fECMX2s,38724 +pip/_vendor/distlib/resources.py,sha256=LwbPksc0A1JMbi6XnuPdMBUn83X7BPuFNWqPGEKI698,10820 +pip/_vendor/distlib/scripts.py,sha256=BJliaDAZaVB7WAkwokgC3HXwLD2iWiHaVI50H7C6eG8,18608 +pip/_vendor/distlib/t32.exe,sha256=a0GV5kCoWsMutvliiCKmIgV98eRZ33wXoS-XrqvJQVs,97792 +pip/_vendor/distlib/t64-arm.exe,sha256=68TAa32V504xVBnufojh0PcenpR3U4wAqTqf-MZqbPw,182784 +pip/_vendor/distlib/t64.exe,sha256=gaYY8hy4fbkHYTTnA4i26ct8IQZzkBG2pRdy0iyuBrc,108032 +pip/_vendor/distlib/util.py,sha256=vMPGvsS4j9hF6Y9k3Tyom1aaHLb0rFmZAEyzeAdel9w,66682 +pip/_vendor/distlib/version.py,sha256=s5VIs8wBn0fxzGxWM_aA2ZZyx525HcZbMvcTlTyZ3Rg,23727 +pip/_vendor/distlib/w32.exe,sha256=R4csx3-OGM9kL4aPIzQKRo5TfmRSHZo6QWyLhDhNBks,91648 +pip/_vendor/distlib/w64-arm.exe,sha256=xdyYhKj0WDcVUOCb05blQYvzdYIKMbmJn2SZvzkcey4,168448 +pip/_vendor/distlib/w64.exe,sha256=ejGf-rojoBfXseGLpya6bFTFPWRG21X5KvU8J5iU-K0,101888 +pip/_vendor/distlib/wheel.py,sha256=DFIVguEQHCdxnSdAO0dfFsgMcvVZitg7bCOuLwZ7A_s,43979 +pip/_vendor/distro/__init__.py,sha256=2fHjF-SfgPvjyNZ1iHh_wjqWdR_Yo5ODHwZC0jLBPhc,981 +pip/_vendor/distro/__main__.py,sha256=bu9d3TifoKciZFcqRBuygV3GSuThnVD_m2IK4cz96Vs,64 +pip/_vendor/distro/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/distro/__pycache__/__main__.cpython-312.pyc,, +pip/_vendor/distro/__pycache__/distro.cpython-312.pyc,, +pip/_vendor/distro/distro.py,sha256=XqbefacAhDT4zr_trnbA15eY8vdK4GTghgmvUGrEM_4,49430 +pip/_vendor/distro/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/idna/__init__.py,sha256=MPqNDLZbXqGaNdXxAFhiqFPKEQXju2jNQhCey6-5eJM,868 +pip/_vendor/idna/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/idna/__pycache__/codec.cpython-312.pyc,, +pip/_vendor/idna/__pycache__/compat.cpython-312.pyc,, +pip/_vendor/idna/__pycache__/core.cpython-312.pyc,, +pip/_vendor/idna/__pycache__/idnadata.cpython-312.pyc,, +pip/_vendor/idna/__pycache__/intranges.cpython-312.pyc,, +pip/_vendor/idna/__pycache__/package_data.cpython-312.pyc,, +pip/_vendor/idna/__pycache__/uts46data.cpython-312.pyc,, +pip/_vendor/idna/codec.py,sha256=PEew3ItwzjW4hymbasnty2N2OXvNcgHB-JjrBuxHPYY,3422 +pip/_vendor/idna/compat.py,sha256=RzLy6QQCdl9784aFhb2EX9EKGCJjg0P3PilGdeXXcx8,316 +pip/_vendor/idna/core.py,sha256=YJYyAMnwiQEPjVC4-Fqu_p4CJ6yKKuDGmppBNQNQpFs,13239 +pip/_vendor/idna/idnadata.py,sha256=W30GcIGvtOWYwAjZj4ZjuouUutC6ffgNuyjJy7fZ-lo,78306 +pip/_vendor/idna/intranges.py,sha256=amUtkdhYcQG8Zr-CoMM_kVRacxkivC1WgxN1b63KKdU,1898 +pip/_vendor/idna/package_data.py,sha256=q59S3OXsc5VI8j6vSD0sGBMyk6zZ4vWFREE88yCJYKs,21 +pip/_vendor/idna/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/idna/uts46data.py,sha256=rt90K9J40gUSwppDPCrhjgi5AA6pWM65dEGRSf6rIhM,239289 +pip/_vendor/msgpack/__init__.py,sha256=reRaiOtEzSjPnr7TpxjgIvbfln5pV66FhricAs2eC-g,1109 +pip/_vendor/msgpack/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/msgpack/__pycache__/exceptions.cpython-312.pyc,, +pip/_vendor/msgpack/__pycache__/ext.cpython-312.pyc,, +pip/_vendor/msgpack/__pycache__/fallback.cpython-312.pyc,, +pip/_vendor/msgpack/exceptions.py,sha256=dCTWei8dpkrMsQDcjQk74ATl9HsIBH0ybt8zOPNqMYc,1081 +pip/_vendor/msgpack/ext.py,sha256=kteJv03n9tYzd5oo3xYopVTo4vRaAxonBQQJhXohZZo,5726 +pip/_vendor/msgpack/fallback.py,sha256=0g1Pzp0vtmBEmJ5w9F3s_-JMVURP8RS4G1cc5TRaAsI,32390 +pip/_vendor/packaging/__init__.py,sha256=dk4Ta_vmdVJxYHDcfyhvQNw8V3PgSBomKNXqg-D2JDY,494 +pip/_vendor/packaging/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/_parser.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/_structures.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/markers.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/metadata.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/requirements.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/tags.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/utils.cpython-312.pyc,, +pip/_vendor/packaging/__pycache__/version.cpython-312.pyc,, +pip/_vendor/packaging/_elffile.py,sha256=cflAQAkE25tzhYmq_aCi72QfbT_tn891tPzfpbeHOwE,3306 +pip/_vendor/packaging/_manylinux.py,sha256=vl5OCoz4kx80H5rwXKeXWjl9WNISGmr4ZgTpTP9lU9c,9612 +pip/_vendor/packaging/_musllinux.py,sha256=p9ZqNYiOItGee8KcZFeHF_YcdhVwGHdK6r-8lgixvGQ,2694 +pip/_vendor/packaging/_parser.py,sha256=s_TvTvDNK0NrM2QB3VKThdWFM4Nc0P6JnkObkl3MjpM,10236 +pip/_vendor/packaging/_structures.py,sha256=q3eVNmbWJGG_S0Dit_S3Ao8qQqz_5PYTXFAKBZe5yr4,1431 +pip/_vendor/packaging/_tokenizer.py,sha256=J6v5H7Jzvb-g81xp_2QACKwO7LxHQA6ikryMU7zXwN8,5273 +pip/_vendor/packaging/licenses/__init__.py,sha256=A116-FU49_Dz4162M4y1uAiZN4Rgdc83FxNd8EjlfqI,5727 +pip/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc,, +pip/_vendor/packaging/licenses/_spdx.py,sha256=oAm1ztPFwlsmCKe7lAAsv_OIOfS1cWDu9bNBkeu-2ns,48398 +pip/_vendor/packaging/markers.py,sha256=c89TNzB7ZdGYhkovm6PYmqGyHxXlYVaLW591PHUNKD8,10561 +pip/_vendor/packaging/metadata.py,sha256=YJibM7GYe4re8-0a3OlXmGS-XDgTEoO4tlBt2q25Bng,34762 +pip/_vendor/packaging/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/packaging/requirements.py,sha256=gYyRSAdbrIyKDY66ugIDUQjRMvxkH2ALioTmX3tnL6o,2947 +pip/_vendor/packaging/specifiers.py,sha256=hGU6kuCd77bL-msIL6yLCp6MNT75RSMUKZDuju26c8U,40098 +pip/_vendor/packaging/tags.py,sha256=CFqrJzAzc2XNGexerH__T-Y5Iwq7WbsYXsiLERLWxY0,21014 +pip/_vendor/packaging/utils.py,sha256=0F3Hh9OFuRgrhTgGZUl5K22Fv1YP2tZl1z_2gO6kJiA,5050 +pip/_vendor/packaging/version.py,sha256=oiHqzTUv_p12hpjgsLDVcaF5hT7pDaSOViUNMD4GTW0,16688 +pip/_vendor/pkg_resources/__init__.py,sha256=jrhDRbOubP74QuPXxd7U7Po42PH2l-LZ2XfcO7llpZ4,124463 +pip/_vendor/pkg_resources/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/platformdirs/__init__.py,sha256=JueR2cRLkxY7iwik-qNWJCwKOrAlBgVgcZ_IHQzqGLE,22344 +pip/_vendor/platformdirs/__main__.py,sha256=jBJ8zb7Mpx5ebcqF83xrpO94MaeCpNGHVf9cvDN2JLg,1505 +pip/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc,, +pip/_vendor/platformdirs/__pycache__/android.cpython-312.pyc,, +pip/_vendor/platformdirs/__pycache__/api.cpython-312.pyc,, +pip/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc,, +pip/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc,, +pip/_vendor/platformdirs/__pycache__/version.cpython-312.pyc,, +pip/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc,, +pip/_vendor/platformdirs/android.py,sha256=kV5oL3V3DZ6WZKu9yFiQupv18yp_jlSV2ChH1TmPcds,9007 +pip/_vendor/platformdirs/api.py,sha256=2dfUDNbEXeDhDKarqtR5NY7oUikUZ4RZhs3ozstmhBQ,9246 +pip/_vendor/platformdirs/macos.py,sha256=UlbyFZ8Rzu3xndCqQEHrfsYTeHwYdFap1Ioz-yxveT4,6154 +pip/_vendor/platformdirs/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/platformdirs/unix.py,sha256=uRPJWRyQEtv7yOSvU94rUmsblo5XKDLA1SzFg55kbK0,10393 +pip/_vendor/platformdirs/version.py,sha256=oH4KgTfK4AklbTYVcV_yynvJ9JLI3pyvDVay0hRsLCs,411 +pip/_vendor/platformdirs/windows.py,sha256=IFpiohUBwxPtCzlyKwNtxyW4Jk8haa6W8o59mfrDXVo,10125 +pip/_vendor/pygments/__init__.py,sha256=7N1oiaWulw_nCsTY4EEixYLz15pWY5u4uPAFFi-ielU,2983 +pip/_vendor/pygments/__main__.py,sha256=isIhBxLg65nLlXukG4VkMuPfNdd7gFzTZ_R_z3Q8diY,353 +pip/_vendor/pygments/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/__main__.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/cmdline.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/console.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/filter.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/formatter.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/lexer.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/modeline.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/plugin.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/regexopt.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/scanner.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/sphinxext.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/style.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/token.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/unistring.cpython-312.pyc,, +pip/_vendor/pygments/__pycache__/util.cpython-312.pyc,, +pip/_vendor/pygments/cmdline.py,sha256=LIVzmAunlk9sRJJp54O4KRy9GDIN4Wu13v9p9QzfGPM,23656 +pip/_vendor/pygments/console.py,sha256=yhP9UsLAVmWKVQf2446JJewkA7AiXeeTf4Ieg3Oi2fU,1718 +pip/_vendor/pygments/filter.py,sha256=_ADNPCskD8_GmodHi6_LoVgPU3Zh336aBCT5cOeTMs0,1910 +pip/_vendor/pygments/filters/__init__.py,sha256=RdedK2KWKXlKwR7cvkfr3NUj9YiZQgMgilRMFUg2jPA,40392 +pip/_vendor/pygments/filters/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/pygments/formatter.py,sha256=jDWBTndlBH2Z5IYZFVDnP0qn1CaTQjTWt7iAGtCnJEg,4390 +pip/_vendor/pygments/formatters/__init__.py,sha256=8No-NUs8rBTSSBJIv4hSEQt2M0cFB4hwAT0snVc2QGE,5385 +pip/_vendor/pygments/formatters/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/_mapping.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/bbcode.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/groff.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/html.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/img.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/irc.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/latex.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/other.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/pangomarkup.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/rtf.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/svg.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/terminal.cpython-312.pyc,, +pip/_vendor/pygments/formatters/__pycache__/terminal256.cpython-312.pyc,, +pip/_vendor/pygments/formatters/_mapping.py,sha256=1Cw37FuQlNacnxRKmtlPX4nyLoX9_ttko5ZwscNUZZ4,4176 +pip/_vendor/pygments/formatters/bbcode.py,sha256=3JQLI45tcrQ_kRUMjuab6C7Hb0XUsbVWqqbSn9cMjkI,3320 +pip/_vendor/pygments/formatters/groff.py,sha256=M39k0PaSSZRnxWjqBSVPkF0mu1-Vr7bm6RsFvs-CNN4,5106 +pip/_vendor/pygments/formatters/html.py,sha256=SE2jc3YCqbMS3rZW9EAmDlAUhdVxJ52gA4dileEvCGU,35669 +pip/_vendor/pygments/formatters/img.py,sha256=MwA4xWPLOwh6j7Yc6oHzjuqSPt0M1fh5r-5BTIIUfsU,23287 +pip/_vendor/pygments/formatters/irc.py,sha256=dp1Z0l_ObJ5NFh9MhqLGg5ptG5hgJqedT2Vkutt9v0M,4981 +pip/_vendor/pygments/formatters/latex.py,sha256=XMmhOCqUKDBQtG5mGJNAFYxApqaC5puo5cMmPfK3944,19306 +pip/_vendor/pygments/formatters/other.py,sha256=56PMJOliin-rAUdnRM0i1wsV1GdUPd_dvQq0_UPfF9c,5034 +pip/_vendor/pygments/formatters/pangomarkup.py,sha256=y16U00aVYYEFpeCfGXlYBSMacG425CbfoG8oKbKegIg,2218 +pip/_vendor/pygments/formatters/rtf.py,sha256=ZT90dmcKyJboIB0mArhL7IhE467GXRN0G7QAUgG03To,11957 +pip/_vendor/pygments/formatters/svg.py,sha256=KKsiophPupHuxm0So-MsbQEWOT54IAiSF7hZPmxtKXE,7174 +pip/_vendor/pygments/formatters/terminal.py,sha256=AojNG4MlKq2L6IsC_VnXHu4AbHCBn9Otog6u45XvxeI,4674 +pip/_vendor/pygments/formatters/terminal256.py,sha256=kGkNUVo3FpwjytIDS0if79EuUoroAprcWt3igrcIqT0,11753 +pip/_vendor/pygments/lexer.py,sha256=TYHDt___gNW4axTl2zvPZff-VQi8fPaIh5OKRcVSjUM,35349 +pip/_vendor/pygments/lexers/__init__.py,sha256=pIlxyQJuu_syh9lE080cq8ceVbEVcKp0osAFU5fawJU,12115 +pip/_vendor/pygments/lexers/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/pygments/lexers/__pycache__/_mapping.cpython-312.pyc,, +pip/_vendor/pygments/lexers/__pycache__/python.cpython-312.pyc,, +pip/_vendor/pygments/lexers/_mapping.py,sha256=61-h3zr103m01OS5BUq_AfUiL9YI06Ves9ipQ7k4vr4,76097 +pip/_vendor/pygments/lexers/python.py,sha256=2J_YJrPTr_A6fJY_qKiKv0GpgPwHMrlMSeo59qN3fe4,53687 +pip/_vendor/pygments/modeline.py,sha256=gtRYZBS-CKOCDXHhGZqApboHBaZwGH8gznN3O6nuxj4,1005 +pip/_vendor/pygments/plugin.py,sha256=ioeJ3QeoJ-UQhZpY9JL7vbxsTVuwwM7BCu-Jb8nN0AU,1891 +pip/_vendor/pygments/regexopt.py,sha256=Hky4EB13rIXEHQUNkwmCrYqtIlnXDehNR3MztafZ43w,3072 +pip/_vendor/pygments/scanner.py,sha256=NDy3ofK_fHRFK4hIDvxpamG871aewqcsIb6sgTi7Fhk,3092 +pip/_vendor/pygments/sphinxext.py,sha256=iOptJBcqOGPwMEJ2p70PvwpZPIGdvdZ8dxvq6kzxDgA,7981 +pip/_vendor/pygments/style.py,sha256=rSCZWFpg1_DwFMXDU0nEVmAcBHpuQGf9RxvOPPQvKLQ,6420 +pip/_vendor/pygments/styles/__init__.py,sha256=qUk6_1z5KmT8EdJFZYgESmG6P_HJF_2vVrDD7HSCGYY,2042 +pip/_vendor/pygments/styles/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/pygments/styles/__pycache__/_mapping.cpython-312.pyc,, +pip/_vendor/pygments/styles/_mapping.py,sha256=6lovFUE29tz6EsV3XYY4hgozJ7q1JL7cfO3UOlgnS8w,3312 +pip/_vendor/pygments/token.py,sha256=qZwT7LSPy5YBY3JgDjut642CCy7JdQzAfmqD9NmT5j0,6226 +pip/_vendor/pygments/unistring.py,sha256=p5c1i-HhoIhWemy9CUsaN9o39oomYHNxXll0Xfw6tEA,63208 +pip/_vendor/pygments/util.py,sha256=2tj2nS1X9_OpcuSjf8dOET2bDVZhs8cEKd_uT6-Fgg8,10031 +pip/_vendor/pyproject_hooks/__init__.py,sha256=cPB_a9LXz5xvsRbX1o2qyAdjLatZJdQ_Lc5McNX-X7Y,691 +pip/_vendor/pyproject_hooks/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/pyproject_hooks/__pycache__/_impl.cpython-312.pyc,, +pip/_vendor/pyproject_hooks/_impl.py,sha256=jY-raxnmyRyB57ruAitrJRUzEexuAhGTpgMygqx67Z4,14936 +pip/_vendor/pyproject_hooks/_in_process/__init__.py,sha256=MJNPpfIxcO-FghxpBbxkG1rFiQf6HOUbV4U5mq0HFns,557 +pip/_vendor/pyproject_hooks/_in_process/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/pyproject_hooks/_in_process/__pycache__/_in_process.cpython-312.pyc,, +pip/_vendor/pyproject_hooks/_in_process/_in_process.py,sha256=qcXMhmx__MIJq10gGHW3mA4Tl8dy8YzHMccwnNoKlw0,12216 +pip/_vendor/pyproject_hooks/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/requests/__init__.py,sha256=HlB_HzhrzGtfD_aaYUwUh1zWXLZ75_YCLyit75d0Vz8,5057 +pip/_vendor/requests/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/__version__.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/_internal_utils.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/adapters.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/api.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/auth.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/certs.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/compat.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/cookies.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/exceptions.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/help.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/hooks.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/models.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/packages.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/sessions.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/status_codes.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/structures.cpython-312.pyc,, +pip/_vendor/requests/__pycache__/utils.cpython-312.pyc,, +pip/_vendor/requests/__version__.py,sha256=FVfglgZmNQnmYPXpOohDU58F5EUb_-VnSTaAesS187g,435 +pip/_vendor/requests/_internal_utils.py,sha256=nMQymr4hs32TqVo5AbCrmcJEhvPUh7xXlluyqwslLiQ,1495 +pip/_vendor/requests/adapters.py,sha256=J7VeVxKBvawbtlX2DERVo05J9BXTcWYLMHNd1Baa-bk,27607 +pip/_vendor/requests/api.py,sha256=_Zb9Oa7tzVIizTKwFrPjDEY9ejtm_OnSRERnADxGsQs,6449 +pip/_vendor/requests/auth.py,sha256=kF75tqnLctZ9Mf_hm9TZIj4cQWnN5uxRz8oWsx5wmR0,10186 +pip/_vendor/requests/certs.py,sha256=kHDlkK_beuHXeMPc5jta2wgl8gdKeUWt5f2nTDVrvt8,441 +pip/_vendor/requests/compat.py,sha256=Mo9f9xZpefod8Zm-n9_StJcVTmwSukXR2p3IQyyVXvU,1485 +pip/_vendor/requests/cookies.py,sha256=bNi-iqEj4NPZ00-ob-rHvzkvObzN3lEpgw3g6paS3Xw,18590 +pip/_vendor/requests/exceptions.py,sha256=D1wqzYWne1mS2rU43tP9CeN1G7QAy7eqL9o1god6Ejw,4272 +pip/_vendor/requests/help.py,sha256=hRKaf9u0G7fdwrqMHtF3oG16RKktRf6KiwtSq2Fo1_0,3813 +pip/_vendor/requests/hooks.py,sha256=CiuysiHA39V5UfcCBXFIx83IrDpuwfN9RcTUgv28ftQ,733 +pip/_vendor/requests/models.py,sha256=x4K4CmH-lC0l2Kb-iPfMN4dRXxHEcbOaEWBL_i09AwI,35483 +pip/_vendor/requests/packages.py,sha256=_ZQDCJTJ8SP3kVWunSqBsRZNPzj2c1WFVqbdr08pz3U,1057 +pip/_vendor/requests/sessions.py,sha256=ykTI8UWGSltOfH07HKollH7kTBGw4WhiBVaQGmckTw4,30495 +pip/_vendor/requests/status_codes.py,sha256=iJUAeA25baTdw-6PfD0eF4qhpINDJRJI-yaMqxs4LEI,4322 +pip/_vendor/requests/structures.py,sha256=-IbmhVz06S-5aPSZuUthZ6-6D9XOjRuTXHOabY041XM,2912 +pip/_vendor/requests/utils.py,sha256=L79vnFbzJ3SFLKtJwpoWe41Tozi3RlZv94pY1TFIyow,33631 +pip/_vendor/resolvelib/__init__.py,sha256=h509TdEcpb5-44JonaU3ex2TM15GVBLjM9CNCPwnTTs,537 +pip/_vendor/resolvelib/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/resolvelib/__pycache__/providers.cpython-312.pyc,, +pip/_vendor/resolvelib/__pycache__/reporters.cpython-312.pyc,, +pip/_vendor/resolvelib/__pycache__/resolvers.cpython-312.pyc,, +pip/_vendor/resolvelib/__pycache__/structs.cpython-312.pyc,, +pip/_vendor/resolvelib/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/resolvelib/compat/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/resolvelib/compat/__pycache__/collections_abc.cpython-312.pyc,, +pip/_vendor/resolvelib/compat/collections_abc.py,sha256=uy8xUZ-NDEw916tugUXm8HgwCGiMO0f-RcdnpkfXfOs,156 +pip/_vendor/resolvelib/providers.py,sha256=fuuvVrCetu5gsxPB43ERyjfO8aReS3rFQHpDgiItbs4,5871 +pip/_vendor/resolvelib/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/resolvelib/reporters.py,sha256=TSbRmWzTc26w0ggsV1bxVpeWDB8QNIre6twYl7GIZBE,1601 +pip/_vendor/resolvelib/resolvers.py,sha256=G8rsLZSq64g5VmIq-lB7UcIJ1gjAxIQJmTF4REZleQ0,20511 +pip/_vendor/resolvelib/structs.py,sha256=0_1_XO8z_CLhegP3Vpf9VJ3zJcfLm0NOHRM-i0Ykz3o,4963 +pip/_vendor/rich/__init__.py,sha256=dRxjIL-SbFVY0q3IjSMrfgBTHrm1LZDgLOygVBwiYZc,6090 +pip/_vendor/rich/__main__.py,sha256=eO7Cq8JnrgG8zVoeImiAs92q3hXNMIfp0w5lMsO7Q2Y,8477 +pip/_vendor/rich/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/__main__.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_cell_widths.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_emoji_codes.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_emoji_replace.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_export_format.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_extension.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_fileno.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_inspect.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_log_render.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_loop.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_null_file.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_palettes.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_pick.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_ratio.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_spinners.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_stack.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_timer.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_win32_console.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_windows.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_windows_renderer.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/_wrap.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/abc.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/align.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/ansi.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/bar.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/box.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/cells.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/color.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/color_triplet.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/columns.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/console.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/constrain.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/containers.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/control.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/default_styles.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/diagnose.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/emoji.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/errors.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/file_proxy.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/filesize.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/highlighter.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/json.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/jupyter.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/layout.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/live.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/live_render.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/logging.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/markup.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/measure.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/padding.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/pager.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/palette.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/panel.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/pretty.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/progress.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/progress_bar.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/prompt.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/protocol.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/region.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/repr.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/rule.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/scope.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/screen.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/segment.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/spinner.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/status.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/style.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/styled.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/syntax.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/table.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/terminal_theme.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/text.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/theme.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/themes.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/traceback.cpython-312.pyc,, +pip/_vendor/rich/__pycache__/tree.cpython-312.pyc,, +pip/_vendor/rich/_cell_widths.py,sha256=fbmeyetEdHjzE_Vx2l1uK7tnPOhMs2X1lJfO3vsKDpA,10209 +pip/_vendor/rich/_emoji_codes.py,sha256=hu1VL9nbVdppJrVoijVshRlcRRe_v3dju3Mmd2sKZdY,140235 +pip/_vendor/rich/_emoji_replace.py,sha256=n-kcetsEUx2ZUmhQrfeMNc-teeGhpuSQ5F8VPBsyvDo,1064 +pip/_vendor/rich/_export_format.py,sha256=RI08pSrm5tBSzPMvnbTqbD9WIalaOoN5d4M1RTmLq1Y,2128 +pip/_vendor/rich/_extension.py,sha256=Xt47QacCKwYruzjDi-gOBq724JReDj9Cm9xUi5fr-34,265 +pip/_vendor/rich/_fileno.py,sha256=HWZxP5C2ajMbHryvAQZseflVfQoGzsKOHzKGsLD8ynQ,799 +pip/_vendor/rich/_inspect.py,sha256=QM05lEFnFoTaFqpnbx-zBEI6k8oIKrD3cvjEOQNhKig,9655 +pip/_vendor/rich/_log_render.py,sha256=1ByI0PA1ZpxZY3CGJOK54hjlq4X-Bz_boIjIqCd8Kns,3225 +pip/_vendor/rich/_loop.py,sha256=hV_6CLdoPm0va22Wpw4zKqM0RYsz3TZxXj0PoS-9eDQ,1236 +pip/_vendor/rich/_null_file.py,sha256=ADGKp1yt-k70FMKV6tnqCqecB-rSJzp-WQsD7LPL-kg,1394 +pip/_vendor/rich/_palettes.py,sha256=cdev1JQKZ0JvlguV9ipHgznTdnvlIzUFDBb0It2PzjI,7063 +pip/_vendor/rich/_pick.py,sha256=evDt8QN4lF5CiwrUIXlOJCntitBCOsI3ZLPEIAVRLJU,423 +pip/_vendor/rich/_ratio.py,sha256=Zt58apszI6hAAcXPpgdWKpu3c31UBWebOeR4mbyptvU,5471 +pip/_vendor/rich/_spinners.py,sha256=U2r1_g_1zSjsjiUdAESc2iAMc3i4ri_S8PYP6kQ5z1I,19919 +pip/_vendor/rich/_stack.py,sha256=-C8OK7rxn3sIUdVwxZBBpeHhIzX0eI-VM3MemYfaXm0,351 +pip/_vendor/rich/_timer.py,sha256=zelxbT6oPFZnNrwWPpc1ktUeAT-Vc4fuFcRZLQGLtMI,417 +pip/_vendor/rich/_win32_console.py,sha256=BSaDRIMwBLITn_m0mTRLPqME5q-quGdSMuYMpYeYJwc,22755 +pip/_vendor/rich/_windows.py,sha256=aBwaD_S56SbgopIvayVmpk0Y28uwY2C5Bab1wl3Bp-I,1925 +pip/_vendor/rich/_windows_renderer.py,sha256=t74ZL3xuDCP3nmTp9pH1L5LiI2cakJuQRQleHCJerlk,2783 +pip/_vendor/rich/_wrap.py,sha256=FlSsom5EX0LVkA3KWy34yHnCfLtqX-ZIepXKh-70rpc,3404 +pip/_vendor/rich/abc.py,sha256=ON-E-ZqSSheZ88VrKX2M3PXpFbGEUUZPMa_Af0l-4f0,890 +pip/_vendor/rich/align.py,sha256=Rh-3adnDaN1Ao07EjR2PhgE62PGLPgO8SMwJBku1urQ,10469 +pip/_vendor/rich/ansi.py,sha256=Avs1LHbSdcyOvDOdpELZUoULcBiYewY76eNBp6uFBhs,6921 +pip/_vendor/rich/bar.py,sha256=ldbVHOzKJOnflVNuv1xS7g6dLX2E3wMnXkdPbpzJTcs,3263 +pip/_vendor/rich/box.py,sha256=nr5fYIUghB_iUCEq6y0Z3LlCT8gFPDrzN9u2kn7tJl4,10831 +pip/_vendor/rich/cells.py,sha256=KrQkj5-LghCCpJLSNQIyAZjndc4bnEqOEmi5YuZ9UCY,5130 +pip/_vendor/rich/color.py,sha256=3HSULVDj7qQkXUdFWv78JOiSZzfy5y1nkcYhna296V0,18211 +pip/_vendor/rich/color_triplet.py,sha256=3lhQkdJbvWPoLDO-AnYImAWmJvV5dlgYNCVZ97ORaN4,1054 +pip/_vendor/rich/columns.py,sha256=HUX0KcMm9dsKNi11fTbiM_h2iDtl8ySCaVcxlalEzq8,7131 +pip/_vendor/rich/console.py,sha256=nKjrEx_7xy8KGmDVT-BgNII0R5hm1cexhAHDwdwNVqg,100156 +pip/_vendor/rich/constrain.py,sha256=1VIPuC8AgtKWrcncQrjBdYqA3JVWysu6jZo1rrh7c7Q,1288 +pip/_vendor/rich/containers.py,sha256=c_56TxcedGYqDepHBMTuZdUIijitAQgnox-Qde0Z1qo,5502 +pip/_vendor/rich/control.py,sha256=DSkHTUQLorfSERAKE_oTAEUFefZnZp4bQb4q8rHbKws,6630 +pip/_vendor/rich/default_styles.py,sha256=dZxgaSD9VUy7SXQShO33aLYiAWspCr2sCQZFX_JK1j4,8159 +pip/_vendor/rich/diagnose.py,sha256=an6uouwhKPAlvQhYpNNpGq9EJysfMIOvvCbO3oSoR24,972 +pip/_vendor/rich/emoji.py,sha256=omTF9asaAnsM4yLY94eR_9dgRRSm1lHUszX20D1yYCQ,2501 +pip/_vendor/rich/errors.py,sha256=5pP3Kc5d4QJ_c0KFsxrfyhjiPVe7J1zOqSFbFAzcV-Y,642 +pip/_vendor/rich/file_proxy.py,sha256=Tl9THMDZ-Pk5Wm8sI1gGg_U5DhusmxD-FZ0fUbcU0W0,1683 +pip/_vendor/rich/filesize.py,sha256=_iz9lIpRgvW7MNSeCZnLg-HwzbP4GETg543WqD8SFs0,2484 +pip/_vendor/rich/highlighter.py,sha256=G_sn-8DKjM1sEjLG_oc4ovkWmiUpWvj8bXi0yed2LnY,9586 +pip/_vendor/rich/json.py,sha256=vVEoKdawoJRjAFayPwXkMBPLy7RSTs-f44wSQDR2nJ0,5031 +pip/_vendor/rich/jupyter.py,sha256=QyoKoE_8IdCbrtiSHp9TsTSNyTHY0FO5whE7jOTd9UE,3252 +pip/_vendor/rich/layout.py,sha256=ajkSFAtEVv9EFTcFs-w4uZfft7nEXhNzL7ZVdgrT5rI,14004 +pip/_vendor/rich/live.py,sha256=DhzAPEnjTxQuq9_0Y2xh2MUwQcP_aGPkenLfKETslwM,14270 +pip/_vendor/rich/live_render.py,sha256=zJtB471jGziBtEwxc54x12wEQtH4BuQr1SA8v9kU82w,3666 +pip/_vendor/rich/logging.py,sha256=ZgpKMMBY_BuMAI_BYzo-UtXak6t5oH9VK8m9Q2Lm0f4,12458 +pip/_vendor/rich/markup.py,sha256=3euGKP5s41NCQwaSjTnJxus5iZMHjxpIM0W6fCxra38,8451 +pip/_vendor/rich/measure.py,sha256=HmrIJX8sWRTHbgh8MxEay_83VkqNW_70s8aKP5ZcYI8,5305 +pip/_vendor/rich/padding.py,sha256=KVEI3tOwo9sgK1YNSuH__M1_jUWmLZwRVV_KmOtVzyM,4908 +pip/_vendor/rich/pager.py,sha256=SO_ETBFKbg3n_AgOzXm41Sv36YxXAyI3_R-KOY2_uSc,828 +pip/_vendor/rich/palette.py,sha256=lInvR1ODDT2f3UZMfL1grq7dY_pDdKHw4bdUgOGaM4Y,3396 +pip/_vendor/rich/panel.py,sha256=fFRHcviXvWhk3V3zx5Zwmsb_RL9KJ3esD-sU0NYEVyw,11235 +pip/_vendor/rich/pretty.py,sha256=gy3S72u4FRg2ytoo7N1ZDWDIvB4unbzd5iUGdgm-8fc,36391 +pip/_vendor/rich/progress.py,sha256=MtmCjTk5zYU_XtRHxRHTAEHG6hF9PeF7EMWbEPleIC0,60357 +pip/_vendor/rich/progress_bar.py,sha256=mZTPpJUwcfcdgQCTTz3kyY-fc79ddLwtx6Ghhxfo064,8162 +pip/_vendor/rich/prompt.py,sha256=l0RhQU-0UVTV9e08xW1BbIj0Jq2IXyChX4lC0lFNzt4,12447 +pip/_vendor/rich/protocol.py,sha256=5hHHDDNHckdk8iWH5zEbi-zuIVSF5hbU2jIo47R7lTE,1391 +pip/_vendor/rich/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/rich/region.py,sha256=rNT9xZrVZTYIXZC0NYn41CJQwYNbR-KecPOxTgQvB8Y,166 +pip/_vendor/rich/repr.py,sha256=5MZJZmONgC6kud-QW-_m1okXwL2aR6u6y-pUcUCJz28,4431 +pip/_vendor/rich/rule.py,sha256=0fNaS_aERa3UMRc3T5WMpN_sumtDxfaor2y3of1ftBk,4602 +pip/_vendor/rich/scope.py,sha256=TMUU8qo17thyqQCPqjDLYpg_UU1k5qVd-WwiJvnJVas,2843 +pip/_vendor/rich/screen.py,sha256=YoeReESUhx74grqb0mSSb9lghhysWmFHYhsbMVQjXO8,1591 +pip/_vendor/rich/segment.py,sha256=otnKeKGEV-WRlQVosfJVeFDcDxAKHpvJ_hLzSu5lumM,24743 +pip/_vendor/rich/spinner.py,sha256=PT5qgXPG3ZpqRj7n3EZQ6NW56mx3ldZqZCU7gEMyZk4,4364 +pip/_vendor/rich/status.py,sha256=kkPph3YeAZBo-X-4wPp8gTqZyU466NLwZBA4PZTTewo,4424 +pip/_vendor/rich/style.py,sha256=aSoUNbVgfP1PAnduAqgbbl4AMQy668qs2S1FEwr3Oqs,27067 +pip/_vendor/rich/styled.py,sha256=eZNnzGrI4ki_54pgY3Oj0T-x3lxdXTYh4_ryDB24wBU,1258 +pip/_vendor/rich/syntax.py,sha256=qqAnEUZ4K57Po81_5RBxnsuU4KRzSdvDPAhKw8ma_3E,35763 +pip/_vendor/rich/table.py,sha256=yXYUr0YsPpG466N50HCAw2bpb5ZUuuzdc-G66Zk-oTc,40103 +pip/_vendor/rich/terminal_theme.py,sha256=1j5-ufJfnvlAo5Qsi_ACZiXDmwMXzqgmFByObT9-yJY,3370 +pip/_vendor/rich/text.py,sha256=AO7JPCz6-gaN1thVLXMBntEmDPVYFgFNG1oM61_sanU,47552 +pip/_vendor/rich/theme.py,sha256=oNyhXhGagtDlbDye3tVu3esWOWk0vNkuxFw-_unlaK0,3771 +pip/_vendor/rich/themes.py,sha256=0xgTLozfabebYtcJtDdC5QkX5IVUEaviqDUJJh4YVFk,102 +pip/_vendor/rich/traceback.py,sha256=z8UoN7NbTQKW6YDDUVwOh7F8snZf6gYnUWtOrKsLE1w,31797 +pip/_vendor/rich/tree.py,sha256=yWnQ6rAvRGJ3qZGqBrxS2SW2TKBTNrP0SdY8QxOFPuw,9451 +pip/_vendor/tomli/__init__.py,sha256=PhNw_eyLgdn7McJ6nrAN8yIm3dXC75vr1sVGVVwDSpA,314 +pip/_vendor/tomli/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/tomli/__pycache__/_parser.cpython-312.pyc,, +pip/_vendor/tomli/__pycache__/_re.cpython-312.pyc,, +pip/_vendor/tomli/__pycache__/_types.cpython-312.pyc,, +pip/_vendor/tomli/_parser.py,sha256=9w8LG0jB7fwmZZWB0vVXbeejDHcl4ANIJxB2scEnDlA,25591 +pip/_vendor/tomli/_re.py,sha256=sh4sBDRgO94KJZwNIrgdcyV_qQast50YvzOAUGpRDKA,3171 +pip/_vendor/tomli/_types.py,sha256=-GTG2VUqkpxwMqzmVO4F7ybKddIbAnuAHXfmWQcTi3Q,254 +pip/_vendor/tomli/py.typed,sha256=8PjyZ1aVoQpRVvt71muvuq5qE-jTFZkK-GLHkhdebmc,26 +pip/_vendor/truststore/__init__.py,sha256=WIDeyzWm7EVX44g354M25vpRXbeY1lsPH6EmUJUcq4o,1264 +pip/_vendor/truststore/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/truststore/__pycache__/_api.cpython-312.pyc,, +pip/_vendor/truststore/__pycache__/_macos.cpython-312.pyc,, +pip/_vendor/truststore/__pycache__/_openssl.cpython-312.pyc,, +pip/_vendor/truststore/__pycache__/_ssl_constants.cpython-312.pyc,, +pip/_vendor/truststore/__pycache__/_windows.cpython-312.pyc,, +pip/_vendor/truststore/_api.py,sha256=GeXRNTlxPZ3kif4kNoh6JY0oE4QRzTGcgXr6l_X_Gk0,10555 +pip/_vendor/truststore/_macos.py,sha256=nZlLkOmszUE0g6ryRwBVGY5COzPyudcsiJtDWarM5LQ,20503 +pip/_vendor/truststore/_openssl.py,sha256=LLUZ7ZGaio-i5dpKKjKCSeSufmn6T8pi9lDcFnvSyq0,2324 +pip/_vendor/truststore/_ssl_constants.py,sha256=NUD4fVKdSD02ri7-db0tnO0VqLP9aHuzmStcW7tAl08,1130 +pip/_vendor/truststore/_windows.py,sha256=rAHyKYD8M7t-bXfG8VgOVa3TpfhVhbt4rZQlO45YuP8,17993 +pip/_vendor/truststore/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/typing_extensions.py,sha256=78hFl0HpDY-ylHUVCnWdU5nTHxUP2-S-3wEZk6CQmLk,134499 +pip/_vendor/urllib3/__init__.py,sha256=iXLcYiJySn0GNbWOOZDDApgBL1JgP44EZ8i1760S8Mc,3333 +pip/_vendor/urllib3/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/_collections.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/_version.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/connection.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/connectionpool.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/exceptions.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/fields.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/filepost.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/poolmanager.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/request.cpython-312.pyc,, +pip/_vendor/urllib3/__pycache__/response.cpython-312.pyc,, +pip/_vendor/urllib3/_collections.py,sha256=pyASJJhW7wdOpqJj9QJA8FyGRfr8E8uUUhqUvhF0728,11372 +pip/_vendor/urllib3/_version.py,sha256=t9wGB6ooOTXXgiY66K1m6BZS1CJyXHAU8EoWDTe6Shk,64 +pip/_vendor/urllib3/connection.py,sha256=ttIA909BrbTUzwkqEe_TzZVh4JOOj7g61Ysei2mrwGg,20314 +pip/_vendor/urllib3/connectionpool.py,sha256=e2eiAwNbFNCKxj4bwDKNK-w7HIdSz3OmMxU_TIt-evQ,40408 +pip/_vendor/urllib3/contrib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/urllib3/contrib/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/__pycache__/_appengine_environ.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/__pycache__/appengine.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/__pycache__/ntlmpool.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/__pycache__/securetransport.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/__pycache__/socks.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/_appengine_environ.py,sha256=bDbyOEhW2CKLJcQqAKAyrEHN-aklsyHFKq6vF8ZFsmk,957 +pip/_vendor/urllib3/contrib/_securetransport/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/urllib3/contrib/_securetransport/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/_securetransport/__pycache__/bindings.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/_securetransport/__pycache__/low_level.cpython-312.pyc,, +pip/_vendor/urllib3/contrib/_securetransport/bindings.py,sha256=4Xk64qIkPBt09A5q-RIFUuDhNc9mXilVapm7WnYnzRw,17632 +pip/_vendor/urllib3/contrib/_securetransport/low_level.py,sha256=B2JBB2_NRP02xK6DCa1Pa9IuxrPwxzDzZbixQkb7U9M,13922 +pip/_vendor/urllib3/contrib/appengine.py,sha256=VR68eAVE137lxTgjBDwCna5UiBZTOKa01Aj_-5BaCz4,11036 +pip/_vendor/urllib3/contrib/ntlmpool.py,sha256=NlfkW7WMdW8ziqudopjHoW299og1BTWi0IeIibquFwk,4528 +pip/_vendor/urllib3/contrib/pyopenssl.py,sha256=hDJh4MhyY_p-oKlFcYcQaVQRDv6GMmBGuW9yjxyeejM,17081 +pip/_vendor/urllib3/contrib/securetransport.py,sha256=Fef1IIUUFHqpevzXiDPbIGkDKchY2FVKeVeLGR1Qq3g,34446 +pip/_vendor/urllib3/contrib/socks.py,sha256=aRi9eWXo9ZEb95XUxef4Z21CFlnnjbEiAo9HOseoMt4,7097 +pip/_vendor/urllib3/exceptions.py,sha256=0Mnno3KHTNfXRfY7638NufOPkUb6mXOm-Lqj-4x2w8A,8217 +pip/_vendor/urllib3/fields.py,sha256=kvLDCg_JmH1lLjUUEY_FLS8UhY7hBvDPuVETbY8mdrM,8579 +pip/_vendor/urllib3/filepost.py,sha256=5b_qqgRHVlL7uLtdAYBzBh-GHmU5AfJVt_2N0XS3PeY,2440 +pip/_vendor/urllib3/packages/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/urllib3/packages/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/urllib3/packages/__pycache__/six.cpython-312.pyc,, +pip/_vendor/urllib3/packages/backports/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +pip/_vendor/urllib3/packages/backports/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/urllib3/packages/backports/__pycache__/makefile.cpython-312.pyc,, +pip/_vendor/urllib3/packages/backports/__pycache__/weakref_finalize.cpython-312.pyc,, +pip/_vendor/urllib3/packages/backports/makefile.py,sha256=nbzt3i0agPVP07jqqgjhaYjMmuAi_W5E0EywZivVO8E,1417 +pip/_vendor/urllib3/packages/backports/weakref_finalize.py,sha256=tRCal5OAhNSRyb0DhHp-38AtIlCsRP8BxF3NX-6rqIA,5343 +pip/_vendor/urllib3/packages/six.py,sha256=b9LM0wBXv7E7SrbCjAm4wwN-hrH-iNxv18LgWNMMKPo,34665 +pip/_vendor/urllib3/poolmanager.py,sha256=aWyhXRtNO4JUnCSVVqKTKQd8EXTvUm1VN9pgs2bcONo,19990 +pip/_vendor/urllib3/request.py,sha256=YTWFNr7QIwh7E1W9dde9LM77v2VWTJ5V78XuTTw7D1A,6691 +pip/_vendor/urllib3/response.py,sha256=fmDJAFkG71uFTn-sVSTh2Iw0WmcXQYqkbRjihvwBjU8,30641 +pip/_vendor/urllib3/util/__init__.py,sha256=JEmSmmqqLyaw8P51gUImZh8Gwg9i1zSe-DoqAitn2nc,1155 +pip/_vendor/urllib3/util/__pycache__/__init__.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/connection.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/proxy.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/queue.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/request.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/response.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/retry.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/ssl_.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/ssltransport.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/timeout.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/url.cpython-312.pyc,, +pip/_vendor/urllib3/util/__pycache__/wait.cpython-312.pyc,, +pip/_vendor/urllib3/util/connection.py,sha256=5Lx2B1PW29KxBn2T0xkN1CBgRBa3gGVJBKoQoRogEVk,4901 +pip/_vendor/urllib3/util/proxy.py,sha256=zUvPPCJrp6dOF0N4GAVbOcl6o-4uXKSrGiTkkr5vUS4,1605 +pip/_vendor/urllib3/util/queue.py,sha256=nRgX8_eX-_VkvxoX096QWoz8Ps0QHUAExILCY_7PncM,498 +pip/_vendor/urllib3/util/request.py,sha256=C0OUt2tcU6LRiQJ7YYNP9GvPrSvl7ziIBekQ-5nlBZk,3997 +pip/_vendor/urllib3/util/response.py,sha256=GJpg3Egi9qaJXRwBh5wv-MNuRWan5BIu40oReoxWP28,3510 +pip/_vendor/urllib3/util/retry.py,sha256=6ENvOZ8PBDzh8kgixpql9lIrb2dxH-k7ZmBanJF2Ng4,22050 +pip/_vendor/urllib3/util/ssl_.py,sha256=QDuuTxPSCj1rYtZ4xpD7Ux-r20TD50aHyqKyhQ7Bq4A,17460 +pip/_vendor/urllib3/util/ssl_match_hostname.py,sha256=Ir4cZVEjmAk8gUAIHWSi7wtOO83UCYABY2xFD1Ql_WA,5758 +pip/_vendor/urllib3/util/ssltransport.py,sha256=NA-u5rMTrDFDFC8QzRKUEKMG0561hOD4qBTr3Z4pv6E,6895 +pip/_vendor/urllib3/util/timeout.py,sha256=cwq4dMk87mJHSBktK1miYJ-85G-3T3RmT20v7SFCpno,10168 +pip/_vendor/urllib3/util/url.py,sha256=lCAE7M5myA8EDdW0sJuyyZhVB9K_j38ljWhHAnFaWoE,14296 +pip/_vendor/urllib3/util/wait.py,sha256=fOX0_faozG2P7iVojQoE1mbydweNyTcm-hXEfFrTtLI,5403 +pip/_vendor/vendor.txt,sha256=EW-E3cE5XEAtVFzGInikArOMDxGP0DLUWzXpY4RZfFY,333 +pip/py.typed,sha256=EBVvvPRTn_eIpz5e5QztSCdrMX7Qwd7VP93RSoIlZ2I,286 diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/REQUESTED similarity index 100% rename from llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/REQUESTED rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/REQUESTED diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/WHEEL similarity index 65% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/WHEEL rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/WHEEL index 564c672..505164b 100644 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/WHEEL +++ b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/WHEEL @@ -1,5 +1,5 @@ Wheel-Version: 1.0 -Generator: setuptools (70.2.0) +Generator: setuptools (75.8.0) Root-Is-Purelib: true Tag: py3-none-any diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/entry_points.txt b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/entry_points.txt similarity index 69% rename from llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/entry_points.txt rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/entry_points.txt index 26fa361..25fcf7e 100644 --- a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/entry_points.txt +++ b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/entry_points.txt @@ -1,4 +1,3 @@ [console_scripts] pip = pip._internal.cli.main:main pip3 = pip._internal.cli.main:main -pip3.12 = pip._internal.cli.main:main diff --git a/llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/top_level.txt similarity index 100% rename from llmlab/lib/python3.12/site-packages/pip-24.0.dist-info/top_level.txt rename to llmlab/lib/python3.12/site-packages/pip-25.0.1.dist-info/top_level.txt diff --git a/llmlab/lib/python3.12/site-packages/pip/__init__.py b/llmlab/lib/python3.12/site-packages/pip/__init__.py index be0e3ed..d628f93 100644 --- a/llmlab/lib/python3.12/site-packages/pip/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/__init__.py @@ -1,6 +1,6 @@ from typing import List, Optional -__version__ = "24.0" +__version__ = "25.0.1" def main(args: Optional[List[str]] = None) -> int: diff --git a/llmlab/lib/python3.12/site-packages/pip/__pip-runner__.py b/llmlab/lib/python3.12/site-packages/pip/__pip-runner__.py index 49a148a..c633787 100644 --- a/llmlab/lib/python3.12/site-packages/pip/__pip-runner__.py +++ b/llmlab/lib/python3.12/site-packages/pip/__pip-runner__.py @@ -8,8 +8,8 @@ an import statement. import sys -# Copied from setup.py -PYTHON_REQUIRES = (3, 7) +# Copied from pyproject.toml +PYTHON_REQUIRES = (3, 8) def version_str(version): # type: ignore diff --git a/llmlab/lib/python3.12/site-packages/pip/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/__pycache__/__init__.cpython-312.pyc index edf395c..49f18f7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/__pycache__/__main__.cpython-312.pyc index 6baf062..d056b52 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/__pycache__/__pip-runner__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/__pycache__/__pip-runner__.cpython-312.pyc index 21e460b..a3c5a49 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/__pycache__/__pip-runner__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/__pycache__/__pip-runner__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_internal/__init__.py index 96c6b88..1a5b7f8 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/__init__.py @@ -7,7 +7,7 @@ from pip._internal.utils import _log _log.init_logging() -def main(args: (Optional[List[str]]) = None) -> int: +def main(args: Optional[List[str]] = None) -> int: """This is preserved for old console scripts that may still be referencing it. diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/__init__.cpython-312.pyc index 33abeb2..36a8e2a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/build_env.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/build_env.cpython-312.pyc index 8c88800..10b6eb3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/build_env.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/build_env.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/cache.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/cache.cpython-312.pyc index 5edc940..2afb4bb 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/cache.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/cache.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/configuration.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/configuration.cpython-312.pyc index 28ed91c..60b797e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/configuration.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/configuration.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/exceptions.cpython-312.pyc index 1207176..a677a0c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/exceptions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/exceptions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/main.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/main.cpython-312.pyc index be3845c..e4085cc 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/main.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/main.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/pyproject.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/pyproject.cpython-312.pyc index 8bac438..9ecf0ef 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/pyproject.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/pyproject.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/self_outdated_check.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/self_outdated_check.cpython-312.pyc index 58d0354..698a668 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/self_outdated_check.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/self_outdated_check.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/wheel_builder.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/wheel_builder.cpython-312.pyc index 574419d..900190b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/wheel_builder.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/__pycache__/wheel_builder.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/build_env.py b/llmlab/lib/python3.12/site-packages/pip/_internal/build_env.py index 4f704a3..e8d1aca 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/build_env.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/build_env.py @@ -11,14 +11,14 @@ from collections import OrderedDict from types import TracebackType from typing import TYPE_CHECKING, Iterable, List, Optional, Set, Tuple, Type, Union -from pip._vendor.certifi import where -from pip._vendor.packaging.requirements import Requirement from pip._vendor.packaging.version import Version from pip import __file__ as pip_location from pip._internal.cli.spinners import open_spinner from pip._internal.locations import get_platlib, get_purelib, get_scheme from pip._internal.metadata import get_default_environment, get_environment +from pip._internal.utils.logging import VERBOSE +from pip._internal.utils.packaging import get_requirement from pip._internal.utils.subprocess import call_subprocess from pip._internal.utils.temp_dir import TempDirectory, tempdir_kinds @@ -183,7 +183,7 @@ class BuildEnvironment: else get_default_environment() ) for req_str in reqs: - req = Requirement(req_str) + req = get_requirement(req_str) # We're explicitly evaluating with an empty extra value, since build # environments are not provided any mechanism to select specific extras. if req.marker is not None and not req.marker.evaluate({"extra": ""}): @@ -240,8 +240,15 @@ class BuildEnvironment: "--prefix", prefix.path, "--no-warn-script-location", + "--disable-pip-version-check", + # The prefix specified two lines above, thus + # target from config file or env var should be ignored + "--target", + "", ] if logger.getEffectiveLevel() <= logging.DEBUG: + args.append("-vv") + elif logger.getEffectiveLevel() <= VERBOSE: args.append("-v") for format_control in ("no_binary", "only_binary"): formats = getattr(finder.format_control, format_control) @@ -262,21 +269,25 @@ class BuildEnvironment: for link in finder.find_links: args.extend(["--find-links", link]) + if finder.proxy: + args.extend(["--proxy", finder.proxy]) for host in finder.trusted_hosts: args.extend(["--trusted-host", host]) + if finder.custom_cert: + args.extend(["--cert", finder.custom_cert]) + if finder.client_cert: + args.extend(["--client-cert", finder.client_cert]) if finder.allow_all_prereleases: args.append("--pre") if finder.prefer_binary: args.append("--prefer-binary") args.append("--") args.extend(requirements) - extra_environ = {"_PIP_STANDALONE_CERT": where()} with open_spinner(f"Installing {kind}") as spinner: call_subprocess( args, command_desc=f"pip subprocess to install {kind}", spinner=spinner, - extra_environ=extra_environ, ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cache.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cache.py index f45ac23..6b45126 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cache.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cache.py @@ -44,7 +44,7 @@ class Cache: """Get parts of part that must be os.path.joined with cache_dir""" # We want to generate an url to use as our cache key, we don't want to - # just re-use the URL because it might have other items in the fragment + # just reuse the URL because it might have other items in the fragment # and we don't care about those. key_parts = {"url": link.url_without_fragment} if link.hash_name is not None and link.hash is not None: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/__init__.cpython-312.pyc index 53597d8..27c6579 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/autocompletion.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/autocompletion.cpython-312.pyc index 5f477dd..c4ed9b5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/autocompletion.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/autocompletion.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/base_command.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/base_command.cpython-312.pyc index a048cd1..b749a11 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/base_command.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/base_command.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/cmdoptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/cmdoptions.cpython-312.pyc index a6cedde..09aaa0f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/cmdoptions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/cmdoptions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/command_context.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/command_context.cpython-312.pyc index cec8cf3..f35dce0 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/command_context.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/command_context.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/index_command.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/index_command.cpython-312.pyc new file mode 100644 index 0000000..8f7f496 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/index_command.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main.cpython-312.pyc index f48058c..10d20f8 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main_parser.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main_parser.cpython-312.pyc index 9995bde..87c2d2b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main_parser.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/main_parser.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/parser.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/parser.cpython-312.pyc index c2fd77f..25d6970 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/parser.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/parser.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/progress_bars.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/progress_bars.cpython-312.pyc index 174496a..5469426 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/progress_bars.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/progress_bars.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/req_command.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/req_command.cpython-312.pyc index e3d6ad3..ef8b843 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/req_command.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/req_command.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/spinners.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/spinners.cpython-312.pyc index a803e10..f4cf516 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/spinners.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/spinners.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/status_codes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/status_codes.cpython-312.pyc index 1509ef3..6b5b2ee 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/status_codes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/__pycache__/status_codes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/autocompletion.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/autocompletion.py index e5950b9..f3f70ac 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/autocompletion.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/autocompletion.py @@ -17,6 +17,10 @@ def autocomplete() -> None: # Don't complete if user hasn't sourced bash_completion file. if "PIP_AUTO_COMPLETE" not in os.environ: return + # Don't complete if autocompletion environment variables + # are not present + if not os.environ.get("COMP_WORDS") or not os.environ.get("COMP_CWORD"): + return cwords = os.environ["COMP_WORDS"].split()[1:] cword = int(os.environ["COMP_CWORD"]) try: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/base_command.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/base_command.py index db9d5cc..362f84b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/base_command.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/base_command.py @@ -1,6 +1,5 @@ """Base Command class, and related routines""" -import functools import logging import logging.config import optparse @@ -8,8 +7,9 @@ import os import sys import traceback from optparse import Values -from typing import Any, Callable, List, Optional, Tuple +from typing import List, Optional, Tuple +from pip._vendor.rich import reconfigure from pip._vendor.rich import traceback as rich_traceback from pip._internal.cli import cmdoptions @@ -28,8 +28,8 @@ from pip._internal.exceptions import ( InstallationError, NetworkConnectionError, PreviousBuildDirError, - UninstallationError, ) +from pip._internal.utils.deprecation import deprecated from pip._internal.utils.filesystem import check_path_owner from pip._internal.utils.logging import BrokenStdoutLoggingError, setup_logging from pip._internal.utils.misc import get_prog, normalize_path @@ -91,6 +91,63 @@ class Command(CommandContextMixIn): def run(self, options: Values, args: List[str]) -> int: raise NotImplementedError + def _run_wrapper(self, level_number: int, options: Values, args: List[str]) -> int: + def _inner_run() -> int: + try: + return self.run(options, args) + finally: + self.handle_pip_version_check(options) + + if options.debug_mode: + rich_traceback.install(show_locals=True) + return _inner_run() + + try: + status = _inner_run() + assert isinstance(status, int) + return status + except DiagnosticPipError as exc: + logger.error("%s", exc, extra={"rich": True}) + logger.debug("Exception information:", exc_info=True) + + return ERROR + except PreviousBuildDirError as exc: + logger.critical(str(exc)) + logger.debug("Exception information:", exc_info=True) + + return PREVIOUS_BUILD_DIR_ERROR + except ( + InstallationError, + BadCommand, + NetworkConnectionError, + ) as exc: + logger.critical(str(exc)) + logger.debug("Exception information:", exc_info=True) + + return ERROR + except CommandError as exc: + logger.critical("%s", exc) + logger.debug("Exception information:", exc_info=True) + + return ERROR + except BrokenStdoutLoggingError: + # Bypass our logger and write any remaining messages to + # stderr because stdout no longer works. + print("ERROR: Pipe to stdout was broken", file=sys.stderr) + if level_number <= logging.DEBUG: + traceback.print_exc(file=sys.stderr) + + return ERROR + except KeyboardInterrupt: + logger.critical("Operation cancelled by user") + logger.debug("Exception information:", exc_info=True) + + return ERROR + except BaseException: + logger.critical("Exception:", exc_info=True) + + return UNKNOWN_ERROR + def parse_args(self, args: List[str]) -> Tuple[Values, List[str]]: # factored out for testability return self.parser.parse_args(args) @@ -116,6 +173,7 @@ class Command(CommandContextMixIn): # Set verbosity so that it can be used elsewhere. self.verbosity = options.verbose - options.quiet + reconfigure(no_color=options.no_color) level_number = setup_logging( verbosity=self.verbosity, no_color=options.no_color, @@ -171,66 +229,12 @@ class Command(CommandContextMixIn): ) options.cache_dir = None - def intercepts_unhandled_exc( - run_func: Callable[..., int] - ) -> Callable[..., int]: - @functools.wraps(run_func) - def exc_logging_wrapper(*args: Any) -> int: - try: - status = run_func(*args) - assert isinstance(status, int) - return status - except DiagnosticPipError as exc: - logger.error("%s", exc, extra={"rich": True}) - logger.debug("Exception information:", exc_info=True) + if options.no_python_version_warning: + deprecated( + reason="--no-python-version-warning is deprecated.", + replacement="to remove the flag as it's a no-op", + gone_in="25.1", + issue=13154, + ) - return ERROR - except PreviousBuildDirError as exc: - logger.critical(str(exc)) - logger.debug("Exception information:", exc_info=True) - - return PREVIOUS_BUILD_DIR_ERROR - except ( - InstallationError, - UninstallationError, - BadCommand, - NetworkConnectionError, - ) as exc: - logger.critical(str(exc)) - logger.debug("Exception information:", exc_info=True) - - return ERROR - except CommandError as exc: - logger.critical("%s", exc) - logger.debug("Exception information:", exc_info=True) - - return ERROR - except BrokenStdoutLoggingError: - # Bypass our logger and write any remaining messages to - # stderr because stdout no longer works. - print("ERROR: Pipe to stdout was broken", file=sys.stderr) - if level_number <= logging.DEBUG: - traceback.print_exc(file=sys.stderr) - - return ERROR - except KeyboardInterrupt: - logger.critical("Operation cancelled by user") - logger.debug("Exception information:", exc_info=True) - - return ERROR - except BaseException: - logger.critical("Exception:", exc_info=True) - - return UNKNOWN_ERROR - - return exc_logging_wrapper - - try: - if not options.debug_mode: - run = intercepts_unhandled_exc(self.run) - else: - run = self.run - rich_traceback.install(show_locals=True) - return run(options, args) - finally: - self.handle_pip_version_check(options) + return self._run_wrapper(level_number, options, args) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/cmdoptions.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/cmdoptions.py index d643256..eeb7e65 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/cmdoptions.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/cmdoptions.py @@ -226,9 +226,9 @@ progress_bar: Callable[..., Option] = partial( "--progress-bar", dest="progress_bar", type="choice", - choices=["on", "off"], + choices=["on", "off", "raw"], default="on", - help="Specify whether the progress bar should be used [on, off] (default: on)", + help="Specify whether the progress bar should be used [on, off, raw] (default: on)", ) log: Callable[..., Option] = partial( @@ -260,8 +260,8 @@ keyring_provider: Callable[..., Option] = partial( default="auto", help=( "Enable the credential lookup via the keyring library if user input is allowed." - " Specify which mechanism to use [disabled, import, subprocess]." - " (default: disabled)" + " Specify which mechanism to use [auto, disabled, import, subprocess]." + " (default: %default)" ), ) @@ -892,7 +892,7 @@ disable_pip_version_check: Callable[..., Option] = partial( "--disable-pip-version-check", dest="disable_pip_version_check", action="store_true", - default=True, + default=False, help="Don't periodically check PyPI to determine whether a new version " "of pip is available for download. Implied with --no-index.", ) @@ -903,7 +903,7 @@ root_user_action: Callable[..., Option] = partial( dest="root_user_action", default="warn", choices=["warn", "ignore"], - help="Action if pip is run as a root user. By default, a warning message is shown.", + help="Action if pip is run as a root user [warn, ignore] (default: warn)", ) @@ -996,6 +996,7 @@ no_python_version_warning: Callable[..., Option] = partial( # Features that are now always on. A warning is printed if they are used. ALWAYS_ENABLED_FEATURES = [ + "truststore", # always on since 24.2 "no-binary-enable-wheel-cache", # always on since 23.1 ] @@ -1008,7 +1009,6 @@ use_new_feature: Callable[..., Option] = partial( default=[], choices=[ "fast-deps", - "truststore", ] + ALWAYS_ENABLED_FEATURES, help="Enable new functionality, that may be backward incompatible.", @@ -1023,6 +1023,7 @@ use_deprecated_feature: Callable[..., Option] = partial( default=[], choices=[ "legacy-resolver", + "legacy-certs", ], help=("Enable deprecated functionality, that will be removed in the future."), ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/index_command.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/index_command.py new file mode 100644 index 0000000..295108e --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/index_command.py @@ -0,0 +1,171 @@ +""" +Contains command classes which may interact with an index / the network. + +Unlike its sister module, req_command, this module still uses lazy imports +so commands which don't always hit the network (e.g. list w/o --outdated or +--uptodate) don't need waste time importing PipSession and friends. +""" + +import logging +import os +import sys +from optparse import Values +from typing import TYPE_CHECKING, List, Optional + +from pip._vendor import certifi + +from pip._internal.cli.base_command import Command +from pip._internal.cli.command_context import CommandContextMixIn + +if TYPE_CHECKING: + from ssl import SSLContext + + from pip._internal.network.session import PipSession + +logger = logging.getLogger(__name__) + + +def _create_truststore_ssl_context() -> Optional["SSLContext"]: + if sys.version_info < (3, 10): + logger.debug("Disabling truststore because Python version isn't 3.10+") + return None + + try: + import ssl + except ImportError: + logger.warning("Disabling truststore since ssl support is missing") + return None + + try: + from pip._vendor import truststore + except ImportError: + logger.warning("Disabling truststore because platform isn't supported") + return None + + ctx = truststore.SSLContext(ssl.PROTOCOL_TLS_CLIENT) + ctx.load_verify_locations(certifi.where()) + return ctx + + +class SessionCommandMixin(CommandContextMixIn): + """ + A class mixin for command classes needing _build_session(). + """ + + def __init__(self) -> None: + super().__init__() + self._session: Optional[PipSession] = None + + @classmethod + def _get_index_urls(cls, options: Values) -> Optional[List[str]]: + """Return a list of index urls from user-provided options.""" + index_urls = [] + if not getattr(options, "no_index", False): + url = getattr(options, "index_url", None) + if url: + index_urls.append(url) + urls = getattr(options, "extra_index_urls", None) + if urls: + index_urls.extend(urls) + # Return None rather than an empty list + return index_urls or None + + def get_default_session(self, options: Values) -> "PipSession": + """Get a default-managed session.""" + if self._session is None: + self._session = self.enter_context(self._build_session(options)) + # there's no type annotation on requests.Session, so it's + # automatically ContextManager[Any] and self._session becomes Any, + # then https://github.com/python/mypy/issues/7696 kicks in + assert self._session is not None + return self._session + + def _build_session( + self, + options: Values, + retries: Optional[int] = None, + timeout: Optional[int] = None, + ) -> "PipSession": + from pip._internal.network.session import PipSession + + cache_dir = options.cache_dir + assert not cache_dir or os.path.isabs(cache_dir) + + if "legacy-certs" not in options.deprecated_features_enabled: + ssl_context = _create_truststore_ssl_context() + else: + ssl_context = None + + session = PipSession( + cache=os.path.join(cache_dir, "http-v2") if cache_dir else None, + retries=retries if retries is not None else options.retries, + trusted_hosts=options.trusted_hosts, + index_urls=self._get_index_urls(options), + ssl_context=ssl_context, + ) + + # Handle custom ca-bundles from the user + if options.cert: + session.verify = options.cert + + # Handle SSL client certificate + if options.client_cert: + session.cert = options.client_cert + + # Handle timeouts + if options.timeout or timeout: + session.timeout = timeout if timeout is not None else options.timeout + + # Handle configured proxies + if options.proxy: + session.proxies = { + "http": options.proxy, + "https": options.proxy, + } + session.trust_env = False + session.pip_proxy = options.proxy + + # Determine if we can prompt the user for authentication or not + session.auth.prompting = not options.no_input + session.auth.keyring_provider = options.keyring_provider + + return session + + +def _pip_self_version_check(session: "PipSession", options: Values) -> None: + from pip._internal.self_outdated_check import pip_self_version_check as check + + check(session, options) + + +class IndexGroupCommand(Command, SessionCommandMixin): + """ + Abstract base class for commands with the index_group options. + + This also corresponds to the commands that permit the pip version check. + """ + + def handle_pip_version_check(self, options: Values) -> None: + """ + Do the pip version check if not disabled. + + This overrides the default behavior of not doing the check. + """ + # Make sure the index_group options are present. + assert hasattr(options, "no_index") + + if options.disable_pip_version_check or options.no_index: + return + + try: + # Otherwise, check if we're using the latest version of pip available. + session = self._build_session( + options, + retries=0, + timeout=min(5, options.timeout), + ) + with session: + _pip_self_version_check(session, options) + except Exception: + logger.warning("There was an error checking the latest version of pip.") + logger.debug("See below for error", exc_info=True) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/main.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/main.py index 7e061f5..563ac79 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/main.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/main.py @@ -1,5 +1,6 @@ """Primary application entrypoint. """ + import locale import logging import os diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/parser.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/parser.py index ae554b2..bc4aca0 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/parser.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/parser.py @@ -6,7 +6,7 @@ import shutil import sys import textwrap from contextlib import suppress -from typing import Any, Dict, Generator, List, Tuple +from typing import Any, Dict, Generator, List, NoReturn, Optional, Tuple from pip._internal.cli.status_codes import UNKNOWN_ERROR from pip._internal.configuration import Configuration, ConfigurationError @@ -67,7 +67,7 @@ class PrettyHelpFormatter(optparse.IndentedHelpFormatter): msg = "\nUsage: {}\n".format(self.indent_lines(textwrap.dedent(usage), " ")) return msg - def format_description(self, description: str) -> str: + def format_description(self, description: Optional[str]) -> str: # leave full control over description to us if description: if hasattr(self.parser, "main"): @@ -85,7 +85,7 @@ class PrettyHelpFormatter(optparse.IndentedHelpFormatter): else: return "" - def format_epilog(self, epilog: str) -> str: + def format_epilog(self, epilog: Optional[str]) -> str: # leave full control over epilog to us if epilog: return epilog @@ -289,6 +289,6 @@ class ConfigOptionParser(CustomOptionParser): defaults[option.dest] = option.check_value(opt_str, default) return optparse.Values(defaults) - def error(self, msg: str) -> None: + def error(self, msg: str) -> NoReturn: self.print_usage(sys.stderr) self.exit(UNKNOWN_ERROR, f"{msg}\n") diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/progress_bars.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/progress_bars.py index 0ad1403..3d9dde8 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/progress_bars.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/progress_bars.py @@ -1,4 +1,5 @@ import functools +import sys from typing import Callable, Generator, Iterable, Iterator, Optional, Tuple from pip._vendor.rich.progress import ( @@ -14,6 +15,7 @@ from pip._vendor.rich.progress import ( TransferSpeedColumn, ) +from pip._internal.cli.spinners import RateLimiter from pip._internal.utils.logging import get_indentation DownloadProgressRenderer = Callable[[Iterable[bytes]], Iterator[bytes]] @@ -23,7 +25,7 @@ def _rich_progress_bar( iterable: Iterable[bytes], *, bar_type: str, - size: int, + size: Optional[int], ) -> Generator[bytes, None, None]: assert bar_type == "on", "This should only be used in the default mode." @@ -47,7 +49,7 @@ def _rich_progress_bar( TimeRemainingColumn(), ) - progress = Progress(*columns, refresh_per_second=30) + progress = Progress(*columns, refresh_per_second=5) task_id = progress.add_task(" " * (get_indentation() + 2), total=total) with progress: for chunk in iterable: @@ -55,6 +57,28 @@ def _rich_progress_bar( progress.update(task_id, advance=len(chunk)) +def _raw_progress_bar( + iterable: Iterable[bytes], + *, + size: Optional[int], +) -> Generator[bytes, None, None]: + def write_progress(current: int, total: int) -> None: + sys.stdout.write(f"Progress {current} of {total}\n") + sys.stdout.flush() + + current = 0 + total = size or 0 + rate_limiter = RateLimiter(0.25) + + write_progress(current, total) + for chunk in iterable: + current += len(chunk) + if rate_limiter.ready() or current == total: + write_progress(current, total) + rate_limiter.reset() + yield chunk + + def get_download_progress_renderer( *, bar_type: str, size: Optional[int] = None ) -> DownloadProgressRenderer: @@ -64,5 +88,7 @@ def get_download_progress_renderer( """ if bar_type == "on": return functools.partial(_rich_progress_bar, bar_type=bar_type, size=size) + elif bar_type == "raw": + return functools.partial(_raw_progress_bar, size=size) else: return iter # no-op, when passed an iterator diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/req_command.py b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/req_command.py index 6f2f79c..92900f9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/cli/req_command.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/cli/req_command.py @@ -1,21 +1,19 @@ -"""Contains the Command base classes that depend on PipSession. +"""Contains the RequirementCommand base class. -The classes in this module are in a separate module so the commands not -needing download / PackageFinder capability don't unnecessarily import the +This class is in a separate module so the commands that do not always +need PackageFinder capability don't unnecessarily import the PackageFinder machinery and all its vendored dependencies, etc. """ import logging -import os -import sys from functools import partial from optparse import Values -from typing import TYPE_CHECKING, Any, List, Optional, Tuple +from typing import Any, List, Optional, Tuple from pip._internal.cache import WheelCache from pip._internal.cli import cmdoptions -from pip._internal.cli.base_command import Command -from pip._internal.cli.command_context import CommandContextMixIn +from pip._internal.cli.index_command import IndexGroupCommand +from pip._internal.cli.index_command import SessionCommandMixin as SessionCommandMixin from pip._internal.exceptions import CommandError, PreviousBuildDirError from pip._internal.index.collector import LinkCollector from pip._internal.index.package_finder import PackageFinder @@ -33,161 +31,15 @@ from pip._internal.req.constructors import ( from pip._internal.req.req_file import parse_requirements from pip._internal.req.req_install import InstallRequirement from pip._internal.resolution.base import BaseResolver -from pip._internal.self_outdated_check import pip_self_version_check from pip._internal.utils.temp_dir import ( TempDirectory, TempDirectoryTypeRegistry, tempdir_kinds, ) -from pip._internal.utils.virtualenv import running_under_virtualenv - -if TYPE_CHECKING: - from ssl import SSLContext logger = logging.getLogger(__name__) -def _create_truststore_ssl_context() -> Optional["SSLContext"]: - if sys.version_info < (3, 10): - raise CommandError("The truststore feature is only available for Python 3.10+") - - try: - import ssl - except ImportError: - logger.warning("Disabling truststore since ssl support is missing") - return None - - try: - from pip._vendor import truststore - except ImportError as e: - raise CommandError(f"The truststore feature is unavailable: {e}") - - return truststore.SSLContext(ssl.PROTOCOL_TLS_CLIENT) - - -class SessionCommandMixin(CommandContextMixIn): - - """ - A class mixin for command classes needing _build_session(). - """ - - def __init__(self) -> None: - super().__init__() - self._session: Optional[PipSession] = None - - @classmethod - def _get_index_urls(cls, options: Values) -> Optional[List[str]]: - """Return a list of index urls from user-provided options.""" - index_urls = [] - if not getattr(options, "no_index", False): - url = getattr(options, "index_url", None) - if url: - index_urls.append(url) - urls = getattr(options, "extra_index_urls", None) - if urls: - index_urls.extend(urls) - # Return None rather than an empty list - return index_urls or None - - def get_default_session(self, options: Values) -> PipSession: - """Get a default-managed session.""" - if self._session is None: - self._session = self.enter_context(self._build_session(options)) - # there's no type annotation on requests.Session, so it's - # automatically ContextManager[Any] and self._session becomes Any, - # then https://github.com/python/mypy/issues/7696 kicks in - assert self._session is not None - return self._session - - def _build_session( - self, - options: Values, - retries: Optional[int] = None, - timeout: Optional[int] = None, - fallback_to_certifi: bool = False, - ) -> PipSession: - cache_dir = options.cache_dir - assert not cache_dir or os.path.isabs(cache_dir) - - if "truststore" in options.features_enabled: - try: - ssl_context = _create_truststore_ssl_context() - except Exception: - if not fallback_to_certifi: - raise - ssl_context = None - else: - ssl_context = None - - session = PipSession( - cache=os.path.join(cache_dir, "http-v2") if cache_dir else None, - retries=retries if retries is not None else options.retries, - trusted_hosts=options.trusted_hosts, - index_urls=self._get_index_urls(options), - ssl_context=ssl_context, - ) - - # Handle custom ca-bundles from the user - if options.cert: - session.verify = options.cert - - # Handle SSL client certificate - if options.client_cert: - session.cert = options.client_cert - - # Handle timeouts - if options.timeout or timeout: - session.timeout = timeout if timeout is not None else options.timeout - - # Handle configured proxies - if options.proxy: - session.proxies = { - "http": options.proxy, - "https": options.proxy, - } - - # Determine if we can prompt the user for authentication or not - session.auth.prompting = not options.no_input - session.auth.keyring_provider = options.keyring_provider - - return session - - -class IndexGroupCommand(Command, SessionCommandMixin): - - """ - Abstract base class for commands with the index_group options. - - This also corresponds to the commands that permit the pip version check. - """ - - def handle_pip_version_check(self, options: Values) -> None: - """ - Do the pip version check if not disabled. - - This overrides the default behavior of not doing the check. - """ - # Make sure the index_group options are present. - assert hasattr(options, "no_index") - - if options.disable_pip_version_check or options.no_index: - return - - # Otherwise, check if we're using the latest version of pip available. - session = self._build_session( - options, - retries=0, - timeout=min(5, options.timeout), - # This is set to ensure the function does not fail when truststore is - # specified in use-feature but cannot be loaded. This usually raises a - # CommandError and shows a nice user-facing error, but this function is not - # called in that try-except block. - fallback_to_certifi=True, - ) - with session: - pip_self_version_check(session, options) - - KEEPABLE_TEMPDIR_TYPES = [ tempdir_kinds.BUILD_ENV, tempdir_kinds.EPHEM_WHEEL_CACHE, @@ -195,36 +47,6 @@ KEEPABLE_TEMPDIR_TYPES = [ ] -def warn_if_run_as_root() -> None: - """Output a warning for sudo users on Unix. - - In a virtual environment, sudo pip still writes to virtualenv. - On Windows, users may run pip as Administrator without issues. - This warning only applies to Unix root users outside of virtualenv. - """ - if running_under_virtualenv(): - return - if not hasattr(os, "getuid"): - return - # On Windows, there are no "system managed" Python packages. Installing as - # Administrator via pip is the correct way of updating system environments. - # - # We choose sys.platform over utils.compat.WINDOWS here to enable Mypy platform - # checks: https://mypy.readthedocs.io/en/stable/common_issues.html - if sys.platform == "win32" or sys.platform == "cygwin": - return - - if os.getuid() != 0: - return - - logger.warning( - "Running pip as the 'root' user can result in broken permissions and " - "conflicting behaviour with the system package manager. " - "It is recommended to use a virtual environment instead: " - "https://pip.pypa.io/warnings/venv" - ) - - def with_cleanup(func: Any) -> Any: """Decorator for common logic related to managing temporary directories. @@ -438,9 +260,11 @@ class RequirementCommand(IndexGroupCommand): isolated=options.isolated_mode, use_pep517=options.use_pep517, user_supplied=True, - config_settings=parsed_req.options.get("config_settings") - if parsed_req.options - else None, + config_settings=( + parsed_req.options.get("config_settings") + if parsed_req.options + else None + ), ) requirements.append(req_to_add) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/__init__.cpython-312.pyc index f8be968..331bdf8 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/cache.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/cache.cpython-312.pyc index 9d5010c..4e1bac3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/cache.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/cache.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/check.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/check.cpython-312.pyc index 9e58000..c8d8a0d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/check.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/check.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/completion.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/completion.cpython-312.pyc index cc76f21..2a27bc5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/completion.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/completion.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/configuration.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/configuration.cpython-312.pyc index 3e5ae3e..24f0eb0 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/configuration.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/configuration.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/debug.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/debug.cpython-312.pyc index c6d188e..8e749e1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/debug.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/debug.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/download.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/download.cpython-312.pyc index ae62efb..7dd339c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/download.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/download.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/freeze.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/freeze.cpython-312.pyc index d91afa7..6d700f5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/freeze.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/freeze.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/hash.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/hash.cpython-312.pyc index 954996d..d623734 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/hash.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/hash.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/help.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/help.cpython-312.pyc index 744b33e..2487684 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/help.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/help.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/index.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/index.cpython-312.pyc index 9fbf715..95395d6 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/index.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/index.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/inspect.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/inspect.cpython-312.pyc index 6c188b3..1877415 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/inspect.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/inspect.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/install.cpython-312.pyc index d3830a2..2c7633c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/install.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/install.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/list.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/list.cpython-312.pyc index d875968..1a1a594 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/list.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/list.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/search.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/search.cpython-312.pyc index bdd90c8..d61cad7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/search.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/search.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/show.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/show.cpython-312.pyc index 3c03dd8..6059164 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/show.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/show.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/uninstall.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/uninstall.cpython-312.pyc index 727469e..595013d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/uninstall.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/uninstall.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/wheel.cpython-312.pyc index 3774777..53c94d3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/__pycache__/wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/cache.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/cache.py index 3283361..ad65641 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/cache.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/cache.py @@ -8,6 +8,7 @@ from pip._internal.cli.status_codes import ERROR, SUCCESS from pip._internal.exceptions import CommandError, PipError from pip._internal.utils import filesystem from pip._internal.utils.logging import getLogger +from pip._internal.utils.misc import format_size logger = getLogger(__name__) @@ -180,10 +181,12 @@ class CacheCommand(Command): if not files: logger.warning(no_matching_msg) + bytes_removed = 0 for filename in files: + bytes_removed += os.stat(filename).st_size os.unlink(filename) logger.verbose("Removed %s", filename) - logger.info("Files removed: %s", len(files)) + logger.info("Files removed: %s (%s)", len(files), format_size(bytes_removed)) def purge_cache(self, options: Values, args: List[Any]) -> None: if args: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/check.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/check.py index 5efd0a3..f54a16d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/check.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/check.py @@ -4,11 +4,13 @@ from typing import List from pip._internal.cli.base_command import Command from pip._internal.cli.status_codes import ERROR, SUCCESS +from pip._internal.metadata import get_default_environment from pip._internal.operations.check import ( check_package_set, + check_unsupported, create_package_set_from_installed, - warn_legacy_versions_and_specifiers, ) +from pip._internal.utils.compatibility_tags import get_supported from pip._internal.utils.misc import write_output logger = logging.getLogger(__name__) @@ -17,13 +19,19 @@ logger = logging.getLogger(__name__) class CheckCommand(Command): """Verify installed packages have compatible dependencies.""" + ignore_require_venv = True usage = """ %prog [options]""" def run(self, options: Values, args: List[str]) -> int: package_set, parsing_probs = create_package_set_from_installed() - warn_legacy_versions_and_specifiers(package_set) missing, conflicting = check_package_set(package_set) + unsupported = list( + check_unsupported( + get_default_environment().iter_installed_distributions(), + get_supported(), + ) + ) for project_name in missing: version = package_set[project_name].version @@ -46,8 +54,13 @@ class CheckCommand(Command): dep_name, dep_version, ) - - if missing or conflicting or parsing_probs: + for package in unsupported: + write_output( + "%s %s is not supported on this platform", + package.raw_name, + package.version, + ) + if missing or conflicting or parsing_probs or unsupported: return ERROR else: write_output("No broken requirements found.") diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/debug.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/debug.py index 7e5271c..567ca96 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/debug.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/debug.py @@ -1,4 +1,3 @@ -import importlib.resources import locale import logging import os @@ -17,6 +16,7 @@ from pip._internal.cli.cmdoptions import make_target_python from pip._internal.cli.status_codes import SUCCESS from pip._internal.configuration import Configuration from pip._internal.metadata import get_environment +from pip._internal.utils.compat import open_text_resource from pip._internal.utils.logging import indent_log from pip._internal.utils.misc import get_pip_version @@ -35,7 +35,7 @@ def show_sys_implementation() -> None: def create_vendor_txt_map() -> Dict[str, str]: - with importlib.resources.open_text("pip._vendor", "vendor.txt") as f: + with open_text_resource("pip._vendor", "vendor.txt") as f: # Purge non version specifying lines. # Also, remove any space prefix or suffixes (including comments). lines = [ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/download.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/download.py index 54247a7..917bbb9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/download.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/download.py @@ -139,7 +139,6 @@ class DownloadCommand(RequirementCommand): downloaded.append(req.name) preparer.prepare_linked_requirements_more(requirement_set.requirements.values()) - requirement_set.warn_legacy_versions_and_specifiers() if downloaded: write_output("Successfully downloaded %s", " ".join(downloaded)) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/freeze.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/freeze.py index e64cb3d..885fdfe 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/freeze.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/freeze.py @@ -18,7 +18,6 @@ def _dev_pkgs() -> AbstractSet[str]: if _should_suppress_build_backends(): pkgs |= {"setuptools", "distribute", "wheel"} - pkgs |= {"setuptools", "distribute", "wheel", "pkg-resources"} return pkgs @@ -30,6 +29,7 @@ class FreezeCommand(Command): packages are listed in a case-insensitive sorted order. """ + ignore_require_venv = True usage = """ %prog [options]""" log_streams = ("ext://sys.stderr", "ext://sys.stderr") diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/index.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/index.py index f55e9e4..2e2661b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/index.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/index.py @@ -1,8 +1,8 @@ import logging from optparse import Values -from typing import Any, Iterable, List, Optional, Union +from typing import Any, Iterable, List, Optional -from pip._vendor.packaging.version import LegacyVersion, Version +from pip._vendor.packaging.version import Version from pip._internal.cli import cmdoptions from pip._internal.cli.req_command import IndexGroupCommand @@ -115,7 +115,7 @@ class IndexCommand(IndexGroupCommand): ignore_requires_python=options.ignore_requires_python, ) - versions: Iterable[Union[LegacyVersion, Version]] = ( + versions: Iterable[Version] = ( candidate.version for candidate in finder.find_all_candidates(query) ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/inspect.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/inspect.py index 27c8fa3..e810c13 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/inspect.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/inspect.py @@ -7,7 +7,7 @@ from pip._vendor.rich import print_json from pip import __version__ from pip._internal.cli import cmdoptions -from pip._internal.cli.req_command import Command +from pip._internal.cli.base_command import Command from pip._internal.cli.status_codes import SUCCESS from pip._internal.metadata import BaseDistribution, get_environment from pip._internal.utils.compat import stdlib_pkgs diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/install.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/install.py index e944bb9..232a34a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/install.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/install.py @@ -7,14 +7,21 @@ import site from optparse import SUPPRESS_HELP, Values from typing import List, Optional +from pip._vendor.packaging.utils import canonicalize_name from pip._vendor.rich import print_json +# Eagerly import self_outdated_check to avoid crashes. Otherwise, +# this module would be imported *after* pip was replaced, resulting +# in crashes if the new self_outdated_check module was incompatible +# with the rest of pip that's already imported, or allowing a +# wheel to execute arbitrary code on install by replacing +# self_outdated_check. +import pip._internal.self_outdated_check # noqa: F401 from pip._internal.cache import WheelCache from pip._internal.cli import cmdoptions from pip._internal.cli.cmdoptions import make_target_python from pip._internal.cli.req_command import ( RequirementCommand, - warn_if_run_as_root, with_cleanup, ) from pip._internal.cli.status_codes import ERROR, SUCCESS @@ -37,6 +44,7 @@ from pip._internal.utils.misc import ( ensure_dir, get_pip_version, protect_pip_from_modification_on_windows, + warn_if_run_as_root, write_output, ) from pip._internal.utils.temp_dir import TempDirectory @@ -370,6 +378,7 @@ class InstallCommand(RequirementCommand): force_reinstall=options.force_reinstall, upgrade_strategy=upgrade_strategy, use_pep517=options.use_pep517, + py_version_info=options.python_version, ) self.trace_basic_info(finder) @@ -387,9 +396,6 @@ class InstallCommand(RequirementCommand): json.dump(report.to_dict(), f, indent=2, ensure_ascii=False) if options.dry_run: - # In non dry-run mode, the legacy versions and specifiers check - # will be done as part of conflict detection. - requirement_set.warn_legacy_versions_and_specifiers() would_install_items = sorted( (r.metadata["name"], r.metadata["version"]) for r in requirement_set.requirements_to_install @@ -427,8 +433,8 @@ class InstallCommand(RequirementCommand): if build_failures: raise InstallationError( - "Could not build wheels for {}, which is required to " - "install pyproject.toml-based projects".format( + "Failed to build installable wheels for some " + "pyproject.toml based projects ({})".format( ", ".join(r.name for r in build_failures) # type: ignore ) ) @@ -469,17 +475,21 @@ class InstallCommand(RequirementCommand): ) env = get_environment(lib_locations) + # Display a summary of installed packages, with extra care to + # display a package name as it was requested by the user. installed.sort(key=operator.attrgetter("name")) - items = [] - for result in installed: - item = result.name - try: - installed_dist = env.get_distribution(item) - if installed_dist is not None: - item = f"{item}-{installed_dist.version}" - except Exception: - pass - items.append(item) + summary = [] + installed_versions = {} + for distribution in env.iter_all_distributions(): + installed_versions[distribution.canonical_name] = distribution.version + for package in installed: + display_name = package.name + version = installed_versions.get(canonicalize_name(display_name), None) + if version: + text = f"{display_name}-{version}" + else: + text = display_name + summary.append(text) if conflicts is not None: self._warn_about_conflicts( @@ -487,7 +497,7 @@ class InstallCommand(RequirementCommand): resolver_variant=self.determine_resolver_variant(options), ) - installed_desc = " ".join(items) + installed_desc = " ".join(summary) if installed_desc: write_output( "Successfully installed %s", diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/list.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/list.py index 32fb19b..8494370 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/list.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/list.py @@ -4,21 +4,20 @@ from optparse import Values from typing import TYPE_CHECKING, Generator, List, Optional, Sequence, Tuple, cast from pip._vendor.packaging.utils import canonicalize_name +from pip._vendor.packaging.version import Version from pip._internal.cli import cmdoptions -from pip._internal.cli.req_command import IndexGroupCommand +from pip._internal.cli.index_command import IndexGroupCommand from pip._internal.cli.status_codes import SUCCESS from pip._internal.exceptions import CommandError -from pip._internal.index.collector import LinkCollector -from pip._internal.index.package_finder import PackageFinder from pip._internal.metadata import BaseDistribution, get_environment from pip._internal.models.selection_prefs import SelectionPreferences -from pip._internal.network.session import PipSession from pip._internal.utils.compat import stdlib_pkgs from pip._internal.utils.misc import tabulate, write_output if TYPE_CHECKING: - from pip._internal.metadata.base import DistributionVersion + from pip._internal.index.package_finder import PackageFinder + from pip._internal.network.session import PipSession class _DistWithLatestInfo(BaseDistribution): """Give the distribution object a couple of extra fields. @@ -27,14 +26,12 @@ if TYPE_CHECKING: makes the rest of the code much cleaner. """ - latest_version: DistributionVersion + latest_version: Version latest_filetype: str _ProcessedDists = Sequence[_DistWithLatestInfo] -from pip._vendor.packaging.version import parse - logger = logging.getLogger(__name__) @@ -137,12 +134,20 @@ class ListCommand(IndexGroupCommand): self.parser.insert_option_group(0, index_opts) self.parser.insert_option_group(0, self.cmd_opts) + def handle_pip_version_check(self, options: Values) -> None: + if options.outdated or options.uptodate: + super().handle_pip_version_check(options) + def _build_package_finder( - self, options: Values, session: PipSession - ) -> PackageFinder: + self, options: Values, session: "PipSession" + ) -> "PackageFinder": """ Create a package finder appropriate to this list command. """ + # Lazy import the heavy index modules as most list invocations won't need 'em. + from pip._internal.index.collector import LinkCollector + from pip._internal.index.package_finder import PackageFinder + link_collector = LinkCollector.create(session, options=options) # Pass allow_yanked=False to ignore yanked versions. @@ -171,7 +176,7 @@ class ListCommand(IndexGroupCommand): if options.excludes: skip.update(canonicalize_name(n) for n in options.excludes) - packages: "_ProcessedDists" = [ + packages: _ProcessedDists = [ cast("_DistWithLatestInfo", d) for d in get_environment(options.path).iter_installed_distributions( local_only=options.local, @@ -203,7 +208,7 @@ class ListCommand(IndexGroupCommand): return [ dist for dist in self.iter_packages_latest_infos(packages, options) - if parse(str(dist.latest_version)) > parse(str(dist.version)) + if dist.latest_version > dist.version ] def get_uptodate( @@ -212,7 +217,7 @@ class ListCommand(IndexGroupCommand): return [ dist for dist in self.iter_packages_latest_infos(packages, options) - if parse(str(dist.latest_version)) == parse(str(dist.version)) + if dist.latest_version == dist.version ] def get_not_required( @@ -331,7 +336,7 @@ def format_for_columns( for proj in pkgs: # if we're working on the 'outdated' list, separate out the # latest_version and type - row = [proj.raw_name, str(proj.version)] + row = [proj.raw_name, proj.raw_version] if running_outdated: row.append(str(proj.latest_version)) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/search.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/search.py index 03ed925..74b8d65 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/search.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/search.py @@ -5,7 +5,7 @@ import textwrap import xmlrpc.client from collections import OrderedDict from optparse import Values -from typing import TYPE_CHECKING, Dict, List, Optional +from typing import TYPE_CHECKING, Dict, List, Optional, TypedDict from pip._vendor.packaging.version import parse as parse_version @@ -20,7 +20,6 @@ from pip._internal.utils.logging import indent_log from pip._internal.utils.misc import write_output if TYPE_CHECKING: - from typing import TypedDict class TransformedHit(TypedDict): name: str @@ -76,9 +75,8 @@ class SearchCommand(Command, SessionCommandMixin): try: hits = pypi.search({"name": query, "summary": query}, "or") except xmlrpc.client.Fault as fault: - message = "XMLRPC request failed [code: {code}]\n{string}".format( - code=fault.faultCode, - string=fault.faultString, + message = ( + f"XMLRPC request failed [code: {fault.faultCode}]\n{fault.faultString}" ) raise CommandError(message) assert isinstance(hits, list) @@ -91,7 +89,7 @@ def transform_hits(hits: List[Dict[str, str]]) -> List["TransformedHit"]: packages with the list of versions stored inline. This converts the list from pypi into one we can use. """ - packages: Dict[str, "TransformedHit"] = OrderedDict() + packages: Dict[str, TransformedHit] = OrderedDict() for hit in hits: name = hit["name"] summary = hit["summary"] diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/show.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/show.py index 3f10701..b47500c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/show.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/show.py @@ -2,6 +2,7 @@ import logging from optparse import Values from typing import Generator, Iterable, Iterator, List, NamedTuple, Optional +from pip._vendor.packaging.requirements import InvalidRequirement from pip._vendor.packaging.utils import canonicalize_name from pip._internal.cli.base_command import Command @@ -65,6 +66,7 @@ class _PackageInfo(NamedTuple): author: str author_email: str license: str + license_expression: str entry_points: List[str] files: Optional[List[str]] @@ -100,8 +102,19 @@ def search_packages_info(query: List[str]) -> Generator[_PackageInfo, None, None except KeyError: continue - requires = sorted((req.name for req in dist.iter_dependencies()), key=str.lower) - required_by = sorted(_get_requiring_packages(dist), key=str.lower) + try: + requires = sorted( + # Avoid duplicates in requirements (e.g. due to environment markers). + {req.name for req in dist.iter_dependencies()}, + key=str.lower, + ) + except InvalidRequirement: + requires = sorted(dist.iter_raw_dependencies(), key=str.lower) + + try: + required_by = sorted(_get_requiring_packages(dist), key=str.lower) + except InvalidRequirement: + required_by = ["#N/A"] try: entry_points_text = dist.read_text("entry_points.txt") @@ -117,9 +130,25 @@ def search_packages_info(query: List[str]) -> Generator[_PackageInfo, None, None metadata = dist.metadata + project_urls = metadata.get_all("Project-URL", []) + homepage = metadata.get("Home-page", "") + if not homepage: + # It's common that there is a "homepage" Project-URL, but Home-page + # remains unset (especially as PEP 621 doesn't surface the field). + # + # This logic was taken from PyPI's codebase. + for url in project_urls: + url_label, url = url.split(",", maxsplit=1) + normalized_label = ( + url_label.casefold().replace("-", "").replace("_", "").strip() + ) + if normalized_label == "homepage": + homepage = url.strip() + break + yield _PackageInfo( name=dist.raw_name, - version=str(dist.version), + version=dist.raw_version, location=dist.location or "", editable_project_location=dist.editable_project_location, requires=requires, @@ -128,11 +157,12 @@ def search_packages_info(query: List[str]) -> Generator[_PackageInfo, None, None metadata_version=dist.metadata_version or "", classifiers=metadata.get_all("Classifier", []), summary=metadata.get("Summary", ""), - homepage=metadata.get("Home-page", ""), - project_urls=metadata.get_all("Project-URL", []), + homepage=homepage, + project_urls=project_urls, author=metadata.get("Author", ""), author_email=metadata.get("Author-email", ""), license=metadata.get("License", ""), + license_expression=metadata.get("License-Expression", ""), entry_points=entry_points, files=files, ) @@ -152,13 +182,18 @@ def print_results( if i > 0: write_output("---") + metadata_version_tuple = tuple(map(int, dist.metadata_version.split("."))) + write_output("Name: %s", dist.name) write_output("Version: %s", dist.version) write_output("Summary: %s", dist.summary) write_output("Home-page: %s", dist.homepage) write_output("Author: %s", dist.author) write_output("Author-email: %s", dist.author_email) - write_output("License: %s", dist.license) + if metadata_version_tuple >= (2, 4) and dist.license_expression: + write_output("License-Expression: %s", dist.license_expression) + else: + write_output("License: %s", dist.license) write_output("Location: %s", dist.location) if dist.editable_project_location is not None: write_output( diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/uninstall.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/uninstall.py index f198fc3..bc0edea 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/uninstall.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/uninstall.py @@ -6,7 +6,7 @@ from pip._vendor.packaging.utils import canonicalize_name from pip._internal.cli import cmdoptions from pip._internal.cli.base_command import Command -from pip._internal.cli.req_command import SessionCommandMixin, warn_if_run_as_root +from pip._internal.cli.index_command import SessionCommandMixin from pip._internal.cli.status_codes import SUCCESS from pip._internal.exceptions import InstallationError from pip._internal.req import parse_requirements @@ -17,6 +17,7 @@ from pip._internal.req.constructors import ( from pip._internal.utils.misc import ( check_externally_managed, protect_pip_from_modification_on_windows, + warn_if_run_as_root, ) logger = logging.getLogger(__name__) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/wheel.py b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/wheel.py index ed578aa..278719f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/commands/wheel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/commands/wheel.py @@ -154,7 +154,6 @@ class WheelCommand(RequirementCommand): reqs_to_build.append(req) preparer.prepare_linked_requirements_more(requirement_set.requirements.values()) - requirement_set.warn_legacy_versions_and_specifiers() # build wheels build_successes, build_failures = build( diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/configuration.py b/llmlab/lib/python3.12/site-packages/pip/_internal/configuration.py index c25273d..ffeda1d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/configuration.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/configuration.py @@ -330,7 +330,7 @@ class Configuration: This should be treated like items of a dictionary. The order here doesn't affect what gets overridden. That is controlled by OVERRIDE_ORDER. However this does control the order they are - displayed to the user. It's probably most ergononmic to display + displayed to the user. It's probably most ergonomic to display things in the same order as OVERRIDE_ORDER """ # SMELL: Move the conditions out of this function diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/__init__.cpython-312.pyc index 709a5b4..6fa91f1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/base.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/base.cpython-312.pyc index 309639b..28c660c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/base.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/base.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/installed.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/installed.cpython-312.pyc index 188df9e..4a33081 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/installed.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/installed.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/sdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/sdist.cpython-312.pyc index ac663bd..48dcbb2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/sdist.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/sdist.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/wheel.cpython-312.pyc index b593b7d..c93ecdf 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/__pycache__/wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/base.py b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/base.py index 6fb0d7b..6e4d0c9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/base.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/base.py @@ -1,10 +1,12 @@ import abc -from typing import Optional +from typing import TYPE_CHECKING, Optional -from pip._internal.index.package_finder import PackageFinder from pip._internal.metadata.base import BaseDistribution from pip._internal.req import InstallRequirement +if TYPE_CHECKING: + from pip._internal.index.package_finder import PackageFinder + class AbstractDistribution(metaclass=abc.ABCMeta): """A base class for handling installable artifacts. @@ -44,7 +46,7 @@ class AbstractDistribution(metaclass=abc.ABCMeta): @abc.abstractmethod def prepare_distribution_metadata( self, - finder: PackageFinder, + finder: "PackageFinder", build_isolation: bool, check_build_deps: bool, ) -> None: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/sdist.py b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/sdist.py index 15ff42b..28ea5ce 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/sdist.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/sdist.py @@ -1,13 +1,15 @@ import logging -from typing import Iterable, Optional, Set, Tuple +from typing import TYPE_CHECKING, Iterable, Optional, Set, Tuple from pip._internal.build_env import BuildEnvironment from pip._internal.distributions.base import AbstractDistribution from pip._internal.exceptions import InstallationError -from pip._internal.index.package_finder import PackageFinder from pip._internal.metadata import BaseDistribution from pip._internal.utils.subprocess import runner_with_spinner_message +if TYPE_CHECKING: + from pip._internal.index.package_finder import PackageFinder + logger = logging.getLogger(__name__) @@ -29,7 +31,7 @@ class SourceDistribution(AbstractDistribution): def prepare_distribution_metadata( self, - finder: PackageFinder, + finder: "PackageFinder", build_isolation: bool, check_build_deps: bool, ) -> None: @@ -66,7 +68,7 @@ class SourceDistribution(AbstractDistribution): self._raise_missing_reqs(missing) self.req.prepare_metadata() - def _prepare_build_backend(self, finder: PackageFinder) -> None: + def _prepare_build_backend(self, finder: "PackageFinder") -> None: # Isolate in a BuildEnvironment and install the build-time # requirements. pyproject_requires = self.req.pyproject_requires @@ -110,14 +112,14 @@ class SourceDistribution(AbstractDistribution): with backend.subprocess_runner(runner): return backend.get_requires_for_build_editable() - def _install_build_reqs(self, finder: PackageFinder) -> None: + def _install_build_reqs(self, finder: "PackageFinder") -> None: # Install any extra build dependencies that the backend requests. # This must be done in a second pass, as the pyproject.toml # dependencies must be installed before we can call the backend. if ( self.req.editable and self.req.permit_editable_wheels - and self.req.supports_pyproject_editable() + and self.req.supports_pyproject_editable ): build_reqs = self._get_build_requires_editable() else: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/wheel.py b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/wheel.py index eb16e25..bfadd39 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/wheel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/distributions/wheel.py @@ -1,15 +1,17 @@ -from typing import Optional +from typing import TYPE_CHECKING, Optional from pip._vendor.packaging.utils import canonicalize_name from pip._internal.distributions.base import AbstractDistribution -from pip._internal.index.package_finder import PackageFinder from pip._internal.metadata import ( BaseDistribution, FilesystemWheel, get_wheel_distribution, ) +if TYPE_CHECKING: + from pip._internal.index.package_finder import PackageFinder + class WheelDistribution(AbstractDistribution): """Represents a wheel distribution. @@ -33,7 +35,7 @@ class WheelDistribution(AbstractDistribution): def prepare_distribution_metadata( self, - finder: PackageFinder, + finder: "PackageFinder", build_isolation: bool, check_build_deps: bool, ) -> None: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/exceptions.py b/llmlab/lib/python3.12/site-packages/pip/_internal/exceptions.py index 5007a62..45a876a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/exceptions.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/exceptions.py @@ -13,16 +13,18 @@ import pathlib import re import sys from itertools import chain, groupby, repeat -from typing import TYPE_CHECKING, Dict, Iterator, List, Optional, Union +from typing import TYPE_CHECKING, Dict, Iterator, List, Literal, Optional, Union -from pip._vendor.requests.models import Request, Response +from pip._vendor.packaging.requirements import InvalidRequirement +from pip._vendor.packaging.version import InvalidVersion from pip._vendor.rich.console import Console, ConsoleOptions, RenderResult from pip._vendor.rich.markup import escape from pip._vendor.rich.text import Text if TYPE_CHECKING: from hashlib import _Hash - from typing import Literal + + from pip._vendor.requests.models import Request, Response from pip._internal.metadata import BaseDistribution from pip._internal.req.req_install import InstallRequirement @@ -184,10 +186,6 @@ class InstallationError(PipError): """General exception during installation""" -class UninstallationError(PipError): - """General exception during uninstallation""" - - class MissingPyProjectBuildRequires(DiagnosticPipError): """Raised when pyproject.toml has `build-system`, but no `build-system.requires`.""" @@ -294,8 +292,8 @@ class NetworkConnectionError(PipError): def __init__( self, error_msg: str, - response: Optional[Response] = None, - request: Optional[Request] = None, + response: Optional["Response"] = None, + request: Optional["Request"] = None, ) -> None: """ Initialize NetworkConnectionError with `request` and `response` @@ -358,6 +356,17 @@ class MetadataInconsistent(InstallationError): ) +class MetadataInvalid(InstallationError): + """Metadata is invalid.""" + + def __init__(self, ireq: "InstallRequirement", error: str) -> None: + self.ireq = ireq + self.error = error + + def __str__(self) -> str: + return f"Requested {self.ireq} has invalid metadata: {self.error}" + + class InstallationSubprocessError(DiagnosticPipError, InstallationError): """A subprocess call failed.""" @@ -422,7 +431,7 @@ class HashErrors(InstallationError): """Multiple HashError instances rolled into one for reporting""" def __init__(self) -> None: - self.errors: List["HashError"] = [] + self.errors: List[HashError] = [] def append(self, error: "HashError") -> None: self.errors.append(error) @@ -726,3 +735,75 @@ class ExternallyManagedEnvironment(DiagnosticPipError): exc_info = logger.isEnabledFor(VERBOSE) logger.warning("Failed to read %s", config, exc_info=exc_info) return cls(None) + + +class UninstallMissingRecord(DiagnosticPipError): + reference = "uninstall-no-record-file" + + def __init__(self, *, distribution: "BaseDistribution") -> None: + installer = distribution.installer + if not installer or installer == "pip": + dep = f"{distribution.raw_name}=={distribution.version}" + hint = Text.assemble( + "You might be able to recover from this via: ", + (f"pip install --force-reinstall --no-deps {dep}", "green"), + ) + else: + hint = Text( + f"The package was installed by {installer}. " + "You should check if it can uninstall the package." + ) + + super().__init__( + message=Text(f"Cannot uninstall {distribution}"), + context=( + "The package's contents are unknown: " + f"no RECORD file was found for {distribution.raw_name}." + ), + hint_stmt=hint, + ) + + +class LegacyDistutilsInstall(DiagnosticPipError): + reference = "uninstall-distutils-installed-package" + + def __init__(self, *, distribution: "BaseDistribution") -> None: + super().__init__( + message=Text(f"Cannot uninstall {distribution}"), + context=( + "It is a distutils installed project and thus we cannot accurately " + "determine which files belong to it which would lead to only a partial " + "uninstall." + ), + hint_stmt=None, + ) + + +class InvalidInstalledPackage(DiagnosticPipError): + reference = "invalid-installed-package" + + def __init__( + self, + *, + dist: "BaseDistribution", + invalid_exc: Union[InvalidRequirement, InvalidVersion], + ) -> None: + installed_location = dist.installed_location + + if isinstance(invalid_exc, InvalidRequirement): + invalid_type = "requirement" + else: + invalid_type = "version" + + super().__init__( + message=Text( + f"Cannot process installed package {dist} " + + (f"in {installed_location!r} " if installed_location else "") + + f"because it has an invalid {invalid_type}:\n{invalid_exc.args[0]}" + ), + context=( + "Starting with pip 24.1, packages with invalid " + f"{invalid_type}s can not be processed." + ), + hint_stmt="To proceed this package must be uninstalled.", + ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/__init__.cpython-312.pyc index cc1a103..9a0139d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/collector.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/collector.cpython-312.pyc index 7985393..3b2d3e5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/collector.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/collector.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/package_finder.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/package_finder.cpython-312.pyc index c9b27aa..7ad0107 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/package_finder.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/package_finder.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/sources.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/sources.cpython-312.pyc index f03d7e1..a7dc812 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/sources.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/index/__pycache__/sources.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/index/collector.py b/llmlab/lib/python3.12/site-packages/pip/_internal/index/collector.py index 08c8bdd..5f8fdee 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/index/collector.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/index/collector.py @@ -11,10 +11,10 @@ import logging import os import urllib.parse import urllib.request +from dataclasses import dataclass from html.parser import HTMLParser from optparse import Values from typing import ( - TYPE_CHECKING, Callable, Dict, Iterable, @@ -22,6 +22,7 @@ from typing import ( MutableMapping, NamedTuple, Optional, + Protocol, Sequence, Tuple, Union, @@ -42,11 +43,6 @@ from pip._internal.vcs import vcs from .sources import CandidatesFromPage, LinkSource, build_source -if TYPE_CHECKING: - from typing import Protocol -else: - Protocol = object - logger = logging.getLogger(__name__) ResponseHeaders = MutableMapping[str, str] @@ -201,8 +197,7 @@ class CacheablePageContent: class ParseLinks(Protocol): - def __call__(self, page: "IndexContent") -> Iterable[Link]: - ... + def __call__(self, page: "IndexContent") -> Iterable[Link]: ... def with_cached_index_content(fn: ParseLinks) -> ParseLinks: @@ -254,29 +249,22 @@ def parse_links(page: "IndexContent") -> Iterable[Link]: yield link +@dataclass(frozen=True) class IndexContent: - """Represents one response (or page), along with its URL""" + """Represents one response (or page), along with its URL. - def __init__( - self, - content: bytes, - content_type: str, - encoding: Optional[str], - url: str, - cache_link_parsing: bool = True, - ) -> None: - """ - :param encoding: the encoding to decode the given content. - :param url: the URL from which the HTML was downloaded. - :param cache_link_parsing: whether links parsed from this page's url - should be cached. PyPI index urls should - have this set to False, for example. - """ - self.content = content - self.content_type = content_type - self.encoding = encoding - self.url = url - self.cache_link_parsing = cache_link_parsing + :param encoding: the encoding to decode the given content. + :param url: the URL from which the HTML was downloaded. + :param cache_link_parsing: whether links parsed from this page's url + should be cached. PyPI index urls should + have this set to False, for example. + """ + + content: bytes + content_type: str + encoding: Optional[str] + url: str + cache_link_parsing: bool = True def __str__(self) -> str: return redact_auth_from_url(self.url) @@ -400,7 +388,6 @@ class CollectedSources(NamedTuple): class LinkCollector: - """ Responsible for collecting Link objects from all configured locations, making network requests as needed. diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/index/package_finder.py b/llmlab/lib/python3.12/site-packages/pip/_internal/index/package_finder.py index ec9ebc3..85628ee 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/index/package_finder.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/index/package_finder.py @@ -5,12 +5,13 @@ import functools import itertools import logging import re +from dataclasses import dataclass from typing import TYPE_CHECKING, FrozenSet, Iterable, List, Optional, Set, Tuple, Union from pip._vendor.packaging import specifiers from pip._vendor.packaging.tags import Tag from pip._vendor.packaging.utils import canonicalize_name -from pip._vendor.packaging.version import _BaseVersion +from pip._vendor.packaging.version import InvalidVersion, _BaseVersion from pip._vendor.packaging.version import parse as parse_version from pip._internal.exceptions import ( @@ -106,7 +107,6 @@ class LinkType(enum.Enum): class LinkEvaluator: - """ Responsible for evaluating links for a particular project. """ @@ -323,67 +323,44 @@ def filter_unallowed_hashes( return filtered +@dataclass class CandidatePreferences: - """ Encapsulates some of the preferences for filtering and sorting InstallationCandidate objects. """ - def __init__( - self, - prefer_binary: bool = False, - allow_all_prereleases: bool = False, - ) -> None: - """ - :param allow_all_prereleases: Whether to allow all pre-releases. - """ - self.allow_all_prereleases = allow_all_prereleases - self.prefer_binary = prefer_binary + prefer_binary: bool = False + allow_all_prereleases: bool = False +@dataclass(frozen=True) class BestCandidateResult: """A collection of candidates, returned by `PackageFinder.find_best_candidate`. This class is only intended to be instantiated by CandidateEvaluator's `compute_best_candidate()` method. + + :param all_candidates: A sequence of all available candidates found. + :param applicable_candidates: The applicable candidates. + :param best_candidate: The most preferred candidate found, or None + if no applicable candidates were found. """ - def __init__( - self, - candidates: List[InstallationCandidate], - applicable_candidates: List[InstallationCandidate], - best_candidate: Optional[InstallationCandidate], - ) -> None: - """ - :param candidates: A sequence of all available candidates found. - :param applicable_candidates: The applicable candidates. - :param best_candidate: The most preferred candidate found, or None - if no applicable candidates were found. - """ - assert set(applicable_candidates) <= set(candidates) + all_candidates: List[InstallationCandidate] + applicable_candidates: List[InstallationCandidate] + best_candidate: Optional[InstallationCandidate] - if best_candidate is None: - assert not applicable_candidates + def __post_init__(self) -> None: + assert set(self.applicable_candidates) <= set(self.all_candidates) + + if self.best_candidate is None: + assert not self.applicable_candidates else: - assert best_candidate in applicable_candidates - - self._applicable_candidates = applicable_candidates - self._candidates = candidates - - self.best_candidate = best_candidate - - def iter_all(self) -> Iterable[InstallationCandidate]: - """Iterate through all candidates.""" - return iter(self._candidates) - - def iter_applicable(self) -> Iterable[InstallationCandidate]: - """Iterate through the applicable candidates.""" - return iter(self._applicable_candidates) + assert self.best_candidate in self.applicable_candidates class CandidateEvaluator: - """ Responsible for filtering and sorting candidates for installation based on what tags are valid. @@ -461,24 +438,23 @@ class CandidateEvaluator: # Using None infers from the specifier instead. allow_prereleases = self._allow_all_prereleases or None specifier = self._specifier - versions = { - str(v) - for v in specifier.filter( - # We turn the version object into a str here because otherwise - # when we're debundled but setuptools isn't, Python will see - # packaging.version.Version and - # pkg_resources._vendor.packaging.version.Version as different - # types. This way we'll use a str as a common data interchange - # format. If we stop using the pkg_resources provided specifier - # and start using our own, we can drop the cast to str(). - (str(c.version) for c in candidates), + + # We turn the version object into a str here because otherwise + # when we're debundled but setuptools isn't, Python will see + # packaging.version.Version and + # pkg_resources._vendor.packaging.version.Version as different + # types. This way we'll use a str as a common data interchange + # format. If we stop using the pkg_resources provided specifier + # and start using our own, we can drop the cast to str(). + candidates_and_versions = [(c, str(c.version)) for c in candidates] + versions = set( + specifier.filter( + (v for _, v in candidates_and_versions), prereleases=allow_prereleases, ) - } - - # Again, converting version to str to deal with debundling. - applicable_candidates = [c for c in candidates if str(c.version) in versions] + ) + applicable_candidates = [c for c, v in candidates_and_versions if v in versions] filtered_applicable_candidates = filter_unallowed_hashes( candidates=applicable_candidates, hashes=self._hashes, @@ -685,11 +661,29 @@ class PackageFinder: def index_urls(self) -> List[str]: return self.search_scope.index_urls + @property + def proxy(self) -> Optional[str]: + return self._link_collector.session.pip_proxy + @property def trusted_hosts(self) -> Iterable[str]: for host_port in self._link_collector.session.pip_trusted_origins: yield build_netloc(*host_port) + @property + def custom_cert(self) -> Optional[str]: + # session.verify is either a boolean (use default bundle/no SSL + # verification) or a string path to a custom CA bundle to use. We only + # care about the latter. + verify = self._link_collector.session.verify + return verify if isinstance(verify, str) else None + + @property + def client_cert(self) -> Optional[str]: + cert = self._link_collector.session.cert + assert not isinstance(cert, tuple), "pip only supports PEM client certs" + return cert + @property def allow_all_prereleases(self) -> bool: return self._candidate_prefs.allow_all_prereleases @@ -742,6 +736,11 @@ class PackageFinder: return no_eggs + eggs def _log_skipped_link(self, link: Link, result: LinkType, detail: str) -> None: + # This is a hot method so don't waste time hashing links unless we're + # actually going to log 'em. + if not logger.isEnabledFor(logging.DEBUG): + return + entry = (link, result, detail) if entry not in self._logged_links: # Put the link at the end so the reason is more visible and because @@ -761,11 +760,14 @@ class PackageFinder: self._log_skipped_link(link, result, detail) return None - return InstallationCandidate( - name=link_evaluator.project_name, - link=link, - version=detail, - ) + try: + return InstallationCandidate( + name=link_evaluator.project_name, + link=link, + version=detail, + ) + except InvalidVersion: + return None def evaluate_links( self, link_evaluator: LinkEvaluator, links: Iterable[Link] @@ -936,7 +938,7 @@ class PackageFinder: "Could not find a version that satisfies the requirement %s " "(from versions: %s)", req, - _format_versions(best_candidate_result.iter_all()), + _format_versions(best_candidate_result.all_candidates), ) raise DistributionNotFound(f"No matching distribution found for {req}") @@ -970,7 +972,7 @@ class PackageFinder: logger.debug( "Using version %s (newest of versions: %s)", best_candidate.version, - _format_versions(best_candidate_result.iter_applicable()), + _format_versions(best_candidate_result.applicable_candidates), ) return best_candidate @@ -978,7 +980,7 @@ class PackageFinder: logger.debug( "Installed version (%s) is most up-to-date (past versions: %s)", installed_version, - _format_versions(best_candidate_result.iter_applicable()), + _format_versions(best_candidate_result.applicable_candidates), ) raise BestVersionAlreadyInstalled diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/index/sources.py b/llmlab/lib/python3.12/site-packages/pip/_internal/index/sources.py index f4626d7..3dafb30 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/index/sources.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/index/sources.py @@ -6,7 +6,6 @@ from typing import Callable, Dict, Iterable, List, Optional, Tuple from pip._vendor.packaging.utils import ( InvalidSdistFilename, - InvalidVersion, InvalidWheelFilename, canonicalize_name, parse_sdist_filename, @@ -68,10 +67,10 @@ class _FlatDirectoryToUrls: # otherwise not worth considering as a package try: project_filename = parse_wheel_filename(entry.name)[0] - except (InvalidWheelFilename, InvalidVersion): + except InvalidWheelFilename: try: project_filename = parse_sdist_filename(entry.name)[0] - except (InvalidSdistFilename, InvalidVersion): + except InvalidSdistFilename: continue self._project_name_to_urls[project_filename].append(url) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__init__.py index d54bc63..32382be 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__init__.py @@ -336,17 +336,6 @@ def get_scheme( if skip_linux_system_special_case: continue - # On Python 3.7 and earlier, sysconfig does not include sys.abiflags in - # the "pythonX.Y" part of the path, but distutils does. - skip_sysconfig_abiflag_bug = ( - sys.version_info < (3, 8) - and not WINDOWS - and k in ("headers", "platlib", "purelib") - and tuple(_fix_abiflags(old_v.parts)) == new_v.parts - ) - if skip_sysconfig_abiflag_bug: - continue - # MSYS2 MINGW's sysconfig patch does not include the "site-packages" # part of the path. This is incorrect and will be fixed in MSYS. skip_msys2_mingw_bug = ( diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/__init__.cpython-312.pyc index f34a727..f0ca4b2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_distutils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_distutils.cpython-312.pyc index 40a1c5b..9025520 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_distutils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_distutils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_sysconfig.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_sysconfig.cpython-312.pyc index 868259f..04557ff 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_sysconfig.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/_sysconfig.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/base.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/base.cpython-312.pyc index d52c9d9..62532ef 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/base.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/__pycache__/base.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_distutils.py b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_distutils.py index 0e18c6e..3d85625 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_distutils.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_distutils.py @@ -21,7 +21,7 @@ from distutils.cmd import Command as DistutilsCommand from distutils.command.install import SCHEME_KEYS from distutils.command.install import install as distutils_install_command from distutils.sysconfig import get_python_lib -from typing import Dict, List, Optional, Union, cast +from typing import Dict, List, Optional, Union from pip._internal.models.scheme import Scheme from pip._internal.utils.compat import WINDOWS @@ -64,7 +64,7 @@ def distutils_scheme( obj: Optional[DistutilsCommand] = None obj = d.get_command_obj("install", create=True) assert obj is not None - i = cast(distutils_install_command, obj) + i: distutils_install_command = obj # NOTE: setting user or home has the side-effect of creating the home dir # or user base for installations during finalize_options() # ideally, we'd prefer a scheme class that has no side-effects. @@ -78,7 +78,7 @@ def distutils_scheme( i.root = root or i.root i.finalize_options() - scheme = {} + scheme: Dict[str, str] = {} for key in SCHEME_KEYS: scheme[key] = getattr(i, "install_" + key) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_sysconfig.py b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_sysconfig.py index 97aef1f..ca860ea 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_sysconfig.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/locations/_sysconfig.py @@ -192,9 +192,10 @@ def get_scheme( data=paths["data"], ) if root is not None: + converted_keys = {} for key in SCHEME_KEYS: - value = change_root(root, getattr(scheme, key)) - setattr(scheme, key, value) + converted_keys[key] = change_root(root, getattr(scheme, key)) + scheme = Scheme(**converted_keys) return scheme diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__init__.py index aa232b6..1ea1e7f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__init__.py @@ -30,7 +30,7 @@ def _should_use_importlib_metadata() -> bool: """Whether to use the ``importlib.metadata`` or ``pkg_resources`` backend. By default, pip uses ``importlib.metadata`` on Python 3.11+, and - ``pkg_resourcess`` otherwise. This can be overridden by a couple of ways: + ``pkg_resources`` otherwise. This can be overridden by a couple of ways: * If environment variable ``_PIP_USE_IMPORTLIB_METADATA`` is set, it dictates whether ``importlib.metadata`` is used, regardless of Python @@ -71,7 +71,7 @@ def get_default_environment() -> BaseEnvironment: This returns an Environment instance from the chosen backend. The default Environment instance should be built from ``sys.path`` and may use caching - to share instance state accorss calls. + to share instance state across calls. """ return select_backend().Environment.default() diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/__init__.cpython-312.pyc index 284f237..5a676a4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/_json.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/_json.cpython-312.pyc index f924f78..a054835 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/_json.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/_json.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/base.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/base.cpython-312.pyc index 049751e..b18f40e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/base.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/base.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/pkg_resources.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/pkg_resources.cpython-312.pyc index 25ad8c4..833b7fc 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/pkg_resources.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/__pycache__/pkg_resources.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/_json.py b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/_json.py index 27362fc..f3aeab3 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/_json.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/_json.py @@ -2,7 +2,7 @@ from email.header import Header, decode_header, make_header from email.message import Message -from typing import Any, Dict, List, Union +from typing import Any, Dict, List, Union, cast METADATA_FIELDS = [ # Name, Multiple-Use @@ -23,6 +23,8 @@ METADATA_FIELDS = [ ("Maintainer", False), ("Maintainer-email", False), ("License", False), + ("License-Expression", False), + ("License-File", True), ("Classifier", True), ("Requires-Dist", True), ("Requires-Python", False), @@ -77,7 +79,7 @@ def msg_to_json(msg: Message) -> Dict[str, Any]: value = value.split() result[key] = value - payload = msg.get_payload() + payload = cast(str, msg.get_payload()) if payload: result["description"] = payload diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/base.py b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/base.py index 9249124..9eabcdb 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/base.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/base.py @@ -8,7 +8,6 @@ import re import zipfile from typing import ( IO, - TYPE_CHECKING, Any, Collection, Container, @@ -18,6 +17,7 @@ from typing import ( List, NamedTuple, Optional, + Protocol, Tuple, Union, ) @@ -25,7 +25,7 @@ from typing import ( from pip._vendor.packaging.requirements import Requirement from pip._vendor.packaging.specifiers import InvalidSpecifier, SpecifierSet from pip._vendor.packaging.utils import NormalizedName, canonicalize_name -from pip._vendor.packaging.version import LegacyVersion, Version +from pip._vendor.packaging.version import Version from pip._internal.exceptions import NoneMetadataError from pip._internal.locations import site_packages, user_site @@ -41,13 +41,6 @@ from pip._internal.utils.urls import url_to_path from ._json import msg_to_json -if TYPE_CHECKING: - from typing import Protocol -else: - Protocol = object - -DistributionVersion = Union[LegacyVersion, Version] - InfoPath = Union[str, pathlib.PurePath] logger = logging.getLogger(__name__) @@ -145,10 +138,10 @@ class BaseDistribution(Protocol): raise NotImplementedError() def __repr__(self) -> str: - return f"{self.raw_name} {self.version} ({self.location})" + return f"{self.raw_name} {self.raw_version} ({self.location})" def __str__(self) -> str: - return f"{self.raw_name} {self.version}" + return f"{self.raw_name} {self.raw_version}" @property def location(self) -> Optional[str]: @@ -279,7 +272,11 @@ class BaseDistribution(Protocol): raise NotImplementedError() @property - def version(self) -> DistributionVersion: + def version(self) -> Version: + raise NotImplementedError() + + @property + def raw_version(self) -> str: raise NotImplementedError() @property @@ -385,15 +382,7 @@ class BaseDistribution(Protocol): def _metadata_impl(self) -> email.message.Message: raise NotImplementedError() - @functools.lru_cache(maxsize=1) - def _metadata_cached(self) -> email.message.Message: - # When we drop python 3.7 support, move this to the metadata property and use - # functools.cached_property instead of lru_cache. - metadata = self._metadata_impl() - self._add_egg_info_requires(metadata) - return metadata - - @property + @functools.cached_property def metadata(self) -> email.message.Message: """Metadata of distribution parsed from e.g. METADATA or PKG-INFO. @@ -402,7 +391,9 @@ class BaseDistribution(Protocol): :raises NoneMetadataError: If the metadata file is available, but does not contain valid metadata. """ - return self._metadata_cached() + metadata = self._metadata_impl() + self._add_egg_info_requires(metadata) + return metadata @property def metadata_dict(self) -> Dict[str, Any]: @@ -454,24 +445,19 @@ class BaseDistribution(Protocol): """ raise NotImplementedError() - def iter_provided_extras(self) -> Iterable[str]: + def iter_raw_dependencies(self) -> Iterable[str]: + """Raw Requires-Dist metadata.""" + return self.metadata.get_all("Requires-Dist", []) + + def iter_provided_extras(self) -> Iterable[NormalizedName]: """Extras provided by this distribution. For modern .dist-info distributions, this is the collection of "Provides-Extra:" entries in distribution metadata. - The return value of this function is not particularly useful other than - display purposes due to backward compatibility issues and the extra - names being poorly normalized prior to PEP 685. If you want to perform - logic operations on extras, use :func:`is_extra_provided` instead. - """ - raise NotImplementedError() - - def is_extra_provided(self, extra: str) -> bool: - """Check whether an extra is provided by this distribution. - - This is needed mostly for compatibility issues with pkg_resources not - following the extra normalization rules defined in PEP 685. + The return value of this function is expected to be normalised names, + per PEP 685, with the returned value being handled appropriately by + `iter_dependencies`. """ raise NotImplementedError() diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/__init__.cpython-312.pyc index 235a2bf..b790243 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_compat.cpython-312.pyc index 0b6048b..423fe16 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_compat.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_compat.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_dists.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_dists.cpython-312.pyc index 4b8077d..654c712 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_dists.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_dists.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_envs.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_envs.cpython-312.pyc index e26e303..d74bc87 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_envs.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/__pycache__/_envs.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_compat.py b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_compat.py index 593bff2..ec1e815 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_compat.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_compat.py @@ -1,5 +1,8 @@ import importlib.metadata -from typing import Any, Optional, Protocol, cast +import os +from typing import Any, Optional, Protocol, Tuple, cast + +from pip._vendor.packaging.utils import NormalizedName, canonicalize_name class BadMetadata(ValueError): @@ -43,13 +46,40 @@ def get_info_location(d: importlib.metadata.Distribution) -> Optional[BasePath]: return getattr(d, "_path", None) -def get_dist_name(dist: importlib.metadata.Distribution) -> str: - """Get the distribution's project name. +def parse_name_and_version_from_info_directory( + dist: importlib.metadata.Distribution, +) -> Tuple[Optional[str], Optional[str]]: + """Get a name and version from the metadata directory name. + + This is much faster than reading distribution metadata. + """ + info_location = get_info_location(dist) + if info_location is None: + return None, None + + stem, suffix = os.path.splitext(info_location.name) + if suffix == ".dist-info": + name, sep, version = stem.partition("-") + if sep: + return name, version + + if suffix == ".egg-info": + name = stem.split("-", 1)[0] + return name, None + + return None, None + + +def get_dist_canonical_name(dist: importlib.metadata.Distribution) -> NormalizedName: + """Get the distribution's normalized name. The ``name`` attribute is only available in Python 3.10 or later. We are targeting exactly that, but Mypy does not know this. """ + if name := parse_name_and_version_from_info_directory(dist)[0]: + return canonicalize_name(name) + name = cast(Any, dist).name if not isinstance(name, str): raise BadMetadata(dist, reason="invalid metadata entry 'name'") - return name + return canonicalize_name(name) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_dists.py b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_dists.py index 26370fa..d220b61 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_dists.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_dists.py @@ -1,8 +1,8 @@ import email.message import importlib.metadata -import os import pathlib import zipfile +from os import PathLike from typing import ( Collection, Dict, @@ -11,26 +11,32 @@ from typing import ( Mapping, Optional, Sequence, + Union, cast, ) from pip._vendor.packaging.requirements import Requirement from pip._vendor.packaging.utils import NormalizedName, canonicalize_name +from pip._vendor.packaging.version import Version from pip._vendor.packaging.version import parse as parse_version from pip._internal.exceptions import InvalidWheel, UnsupportedWheel from pip._internal.metadata.base import ( BaseDistribution, BaseEntryPoint, - DistributionVersion, InfoPath, Wheel, ) from pip._internal.utils.misc import normalize_path +from pip._internal.utils.packaging import get_requirement from pip._internal.utils.temp_dir import TempDirectory from pip._internal.utils.wheel import parse_wheel, read_wheel_metadata_file -from ._compat import BasePath, get_dist_name +from ._compat import ( + BasePath, + get_dist_canonical_name, + parse_name_and_version_from_info_directory, +) class WheelDistribution(importlib.metadata.Distribution): @@ -91,6 +97,11 @@ class WheelDistribution(importlib.metadata.Distribution): raise UnsupportedWheel(error) return text + def locate_file(self, path: Union[str, "PathLike[str]"]) -> pathlib.Path: + # This method doesn't make sense for our in-memory wheel, but the API + # requires us to define it. + raise NotImplementedError + class Distribution(BaseDistribution): def __init__( @@ -133,8 +144,6 @@ class Distribution(BaseDistribution): dist = WheelDistribution.from_zipfile(zf, name, wheel.location) except zipfile.BadZipFile as e: raise InvalidWheel(wheel.location, name) from e - except UnsupportedWheel as e: - raise UnsupportedWheel(f"{name} has an invalid wheel, {e}") return cls(dist, dist.info_location, pathlib.PurePosixPath(wheel.location)) @property @@ -155,27 +164,20 @@ class Distribution(BaseDistribution): return None return normalize_path(str(self._installed_location)) - def _get_dist_name_from_location(self) -> Optional[str]: - """Try to get the name from the metadata directory name. - - This is much faster than reading metadata. - """ - if self._info_location is None: - return None - stem, suffix = os.path.splitext(self._info_location.name) - if suffix not in (".dist-info", ".egg-info"): - return None - return stem.split("-", 1)[0] - @property def canonical_name(self) -> NormalizedName: - name = self._get_dist_name_from_location() or get_dist_name(self._dist) - return canonicalize_name(name) + return get_dist_canonical_name(self._dist) @property - def version(self) -> DistributionVersion: + def version(self) -> Version: + if version := parse_name_and_version_from_info_directory(self._dist)[1]: + return parse_version(version) return parse_version(self._dist.version) + @property + def raw_version(self) -> str: + return self._dist.version + def is_file(self, path: InfoPath) -> bool: return self._dist.read_text(str(path)) is not None @@ -195,7 +197,7 @@ class Distribution(BaseDistribution): return content def iter_entry_points(self) -> Iterable[BaseEntryPoint]: - # importlib.metadata's EntryPoint structure sasitfies BaseEntryPoint. + # importlib.metadata's EntryPoint structure satisfies BaseEntryPoint. return self._dist.entry_points def _metadata_impl(self) -> email.message.Message: @@ -206,19 +208,18 @@ class Distribution(BaseDistribution): # until upstream can improve the protocol. (python/cpython#94952) return cast(email.message.Message, self._dist.metadata) - def iter_provided_extras(self) -> Iterable[str]: - return self.metadata.get_all("Provides-Extra", []) - - def is_extra_provided(self, extra: str) -> bool: - return any( - canonicalize_name(provided_extra) == canonicalize_name(extra) - for provided_extra in self.metadata.get_all("Provides-Extra", []) - ) + def iter_provided_extras(self) -> Iterable[NormalizedName]: + return [ + canonicalize_name(extra) + for extra in self.metadata.get_all("Provides-Extra", []) + ] def iter_dependencies(self, extras: Collection[str] = ()) -> Iterable[Requirement]: contexts: Sequence[Dict[str, str]] = [{"extra": e} for e in extras] for req_string in self.metadata.get_all("Requires-Dist", []): - req = Requirement(req_string) + # strip() because email.message.Message.get_all() may return a leading \n + # in case a long header was wrapped. + req = get_requirement(req_string.strip()) if not req.marker: yield req elif not extras and req.marker.evaluate({"extra": ""}): diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_envs.py b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_envs.py index 048dc55..4d906fd 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_envs.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/importlib/_envs.py @@ -15,7 +15,7 @@ from pip._internal.models.wheel import Wheel from pip._internal.utils.deprecation import deprecated from pip._internal.utils.filetypes import WHEEL_EXTENSION -from ._compat import BadMetadata, BasePath, get_dist_name, get_info_location +from ._compat import BadMetadata, BasePath, get_dist_canonical_name, get_info_location from ._dists import Distribution logger = logging.getLogger(__name__) @@ -61,14 +61,13 @@ class _DistributionFinder: for dist in importlib.metadata.distributions(path=[location]): info_location = get_info_location(dist) try: - raw_name = get_dist_name(dist) + name = get_dist_canonical_name(dist) except BadMetadata as e: logger.warning("Skipping %s due to %s", info_location, e.reason) continue - normalized_name = canonicalize_name(raw_name) - if normalized_name in self._found_names: + if name in self._found_names: continue - self._found_names.add(normalized_name) + self._found_names.add(name) yield dist, info_location def find(self, location: str) -> Iterator[BaseDistribution]: @@ -150,8 +149,8 @@ class _DistributionFinder: def _emit_egg_deprecation(location: Optional[str]) -> None: deprecated( reason=f"Loading egg at {location} is deprecated.", - replacement="to use pip for package installation.", - gone_in="24.3", + replacement="to use pip for package installation", + gone_in="25.1", issue=12330, ) @@ -181,9 +180,10 @@ class Environment(BaseEnvironment): yield from finder.find_linked(location) def get_distribution(self, name: str) -> Optional[BaseDistribution]: + canonical_name = canonicalize_name(name) matches = ( distribution for distribution in self.iter_all_distributions() - if distribution.canonical_name == canonicalize_name(name) + if distribution.canonical_name == canonical_name ) return next(matches, None) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/pkg_resources.py b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/pkg_resources.py index bb11e5b..4ea84f9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/pkg_resources.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/metadata/pkg_resources.py @@ -3,11 +3,20 @@ import email.parser import logging import os import zipfile -from typing import Collection, Iterable, Iterator, List, Mapping, NamedTuple, Optional +from typing import ( + Collection, + Iterable, + Iterator, + List, + Mapping, + NamedTuple, + Optional, +) from pip._vendor import pkg_resources from pip._vendor.packaging.requirements import Requirement from pip._vendor.packaging.utils import NormalizedName, canonicalize_name +from pip._vendor.packaging.version import Version from pip._vendor.packaging.version import parse as parse_version from pip._internal.exceptions import InvalidWheel, NoneMetadataError, UnsupportedWheel @@ -19,7 +28,6 @@ from .base import ( BaseDistribution, BaseEntryPoint, BaseEnvironment, - DistributionVersion, InfoPath, Wheel, ) @@ -75,6 +83,18 @@ class InMemoryMetadata: class Distribution(BaseDistribution): def __init__(self, dist: pkg_resources.Distribution) -> None: self._dist = dist + # This is populated lazily, to avoid loading metadata for all possible + # distributions eagerly. + self.__extra_mapping: Optional[Mapping[NormalizedName, str]] = None + + @property + def _extra_mapping(self) -> Mapping[NormalizedName, str]: + if self.__extra_mapping is None: + self.__extra_mapping = { + canonicalize_name(extra): extra for extra in self._dist.extras + } + + return self.__extra_mapping @classmethod def from_directory(cls, directory: str) -> BaseDistribution: @@ -168,9 +188,13 @@ class Distribution(BaseDistribution): return canonicalize_name(self._dist.project_name) @property - def version(self) -> DistributionVersion: + def version(self) -> Version: return parse_version(self._dist.version) + @property + def raw_version(self) -> str: + return self._dist.version + def is_file(self, path: InfoPath) -> bool: return self._dist.has_metadata(str(path)) @@ -215,16 +239,15 @@ class Distribution(BaseDistribution): return feed_parser.close() def iter_dependencies(self, extras: Collection[str] = ()) -> Iterable[Requirement]: - if extras: # pkg_resources raises on invalid extras, so we sanitize. - extras = frozenset(pkg_resources.safe_extra(e) for e in extras) - extras = extras.intersection(self._dist.extras) + if extras: + relevant_extras = set(self._extra_mapping) & set( + map(canonicalize_name, extras) + ) + extras = [self._extra_mapping[extra] for extra in relevant_extras] return self._dist.requires(extras) - def iter_provided_extras(self) -> Iterable[str]: - return self._dist.extras - - def is_extra_provided(self, extra: str) -> bool: - return pkg_resources.safe_extra(extra) in self._dist.extras + def iter_provided_extras(self) -> Iterable[NormalizedName]: + return self._extra_mapping.keys() class Environment(BaseEnvironment): diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/__init__.cpython-312.pyc index 622d04b..7c4154e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/candidate.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/candidate.cpython-312.pyc index f238881..962b549 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/candidate.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/candidate.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/direct_url.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/direct_url.cpython-312.pyc index b39ff8e..78725ba 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/direct_url.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/direct_url.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/format_control.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/format_control.cpython-312.pyc index 205713e..d3a17a4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/format_control.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/format_control.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/index.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/index.cpython-312.pyc index 061f8f3..4ce268c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/index.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/index.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/installation_report.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/installation_report.cpython-312.pyc index 5feb93f..1376250 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/installation_report.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/installation_report.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/link.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/link.cpython-312.pyc index d384866..5dbf2b9 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/link.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/link.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/scheme.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/scheme.cpython-312.pyc index d7cd2ff..1aaeecc 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/scheme.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/scheme.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/search_scope.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/search_scope.cpython-312.pyc index deb0222..871498c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/search_scope.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/search_scope.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/selection_prefs.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/selection_prefs.cpython-312.pyc index 2e0336b..3eaf28c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/selection_prefs.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/selection_prefs.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/target_python.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/target_python.cpython-312.pyc index 3e581f5..e50c00f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/target_python.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/target_python.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/wheel.cpython-312.pyc index b1ce54a..7181e86 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/models/__pycache__/wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/candidate.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/candidate.py index 9184a90..f27f283 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/candidate.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/candidate.py @@ -1,30 +1,25 @@ +from dataclasses import dataclass + +from pip._vendor.packaging.version import Version from pip._vendor.packaging.version import parse as parse_version from pip._internal.models.link import Link -from pip._internal.utils.models import KeyBasedCompareMixin -class InstallationCandidate(KeyBasedCompareMixin): +@dataclass(frozen=True) +class InstallationCandidate: """Represents a potential "candidate" for installation.""" __slots__ = ["name", "version", "link"] + name: str + version: Version + link: Link + def __init__(self, name: str, version: str, link: Link) -> None: - self.name = name - self.version = parse_version(version) - self.link = link - - super().__init__( - key=(self.name, self.version, self.link), - defining_class=InstallationCandidate, - ) - - def __repr__(self) -> str: - return "".format( - self.name, - self.version, - self.link, - ) + object.__setattr__(self, "name", name) + object.__setattr__(self, "version", parse_version(version)) + object.__setattr__(self, "link", link) def __str__(self) -> str: return f"{self.name!r} candidate (version {self.version} at {self.link})" diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/direct_url.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/direct_url.py index 0af884b..fc5ec8d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/direct_url.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/direct_url.py @@ -1,8 +1,10 @@ """ PEP 610 """ + import json import re import urllib.parse -from typing import Any, Dict, Iterable, Optional, Type, TypeVar, Union +from dataclasses import dataclass +from typing import Any, ClassVar, Dict, Iterable, Optional, Type, TypeVar, Union __all__ = [ "DirectUrl", @@ -64,18 +66,13 @@ def _filter_none(**kwargs: Any) -> Dict[str, Any]: return {k: v for k, v in kwargs.items() if v is not None} +@dataclass class VcsInfo: - name = "vcs_info" + name: ClassVar = "vcs_info" - def __init__( - self, - vcs: str, - commit_id: str, - requested_revision: Optional[str] = None, - ) -> None: - self.vcs = vcs - self.requested_revision = requested_revision - self.commit_id = commit_id + vcs: str + commit_id: str + requested_revision: Optional[str] = None @classmethod def _from_dict(cls, d: Optional[Dict[str, Any]]) -> Optional["VcsInfo"]: @@ -139,14 +136,11 @@ class ArchiveInfo: return _filter_none(hash=self.hash, hashes=self.hashes) +@dataclass class DirInfo: - name = "dir_info" + name: ClassVar = "dir_info" - def __init__( - self, - editable: bool = False, - ) -> None: - self.editable = editable + editable: bool = False @classmethod def _from_dict(cls, d: Optional[Dict[str, Any]]) -> Optional["DirInfo"]: @@ -161,16 +155,11 @@ class DirInfo: InfoType = Union[ArchiveInfo, DirInfo, VcsInfo] +@dataclass class DirectUrl: - def __init__( - self, - url: str, - info: InfoType, - subdirectory: Optional[str] = None, - ) -> None: - self.url = url - self.info = info - self.subdirectory = subdirectory + url: str + info: InfoType + subdirectory: Optional[str] = None def _remove_auth_from_netloc(self, netloc: str) -> str: if "@" not in netloc: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/link.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/link.py index 73041b8..27ad016 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/link.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/link.py @@ -27,7 +27,6 @@ from pip._internal.utils.misc import ( split_auth_from_netloc, splitext, ) -from pip._internal.utils.models import KeyBasedCompareMixin from pip._internal.utils.urls import path_to_url, url_to_path if TYPE_CHECKING: @@ -171,20 +170,33 @@ def _ensure_quoted_url(url: str) -> str: and without double-quoting other characters. """ # Split the URL into parts according to the general structure - # `scheme://netloc/path;parameters?query#fragment`. - result = urllib.parse.urlparse(url) + # `scheme://netloc/path?query#fragment`. + result = urllib.parse.urlsplit(url) # If the netloc is empty, then the URL refers to a local filesystem path. is_local_path = not result.netloc path = _clean_url_path(result.path, is_local_path=is_local_path) - return urllib.parse.urlunparse(result._replace(path=path)) + return urllib.parse.urlunsplit(result._replace(path=path)) -class Link(KeyBasedCompareMixin): +def _absolute_link_url(base_url: str, url: str) -> str: + """ + A faster implementation of urllib.parse.urljoin with a shortcut + for absolute http/https URLs. + """ + if url.startswith(("https://", "http://")): + return url + else: + return urllib.parse.urljoin(base_url, url) + + +@functools.total_ordering +class Link: """Represents a parsed link from a Package Index's simple URL""" __slots__ = [ "_parsed_url", "_url", + "_path", "_hashes", "comes_from", "requires_python", @@ -241,6 +253,8 @@ class Link(KeyBasedCompareMixin): # Store the url as a private attribute to prevent accidentally # trying to set a new value. self._url = url + # The .path property is hot, so calculate its value ahead of time. + self._path = urllib.parse.unquote(self._parsed_url.path) link_hash = LinkHash.find_hash_url_fragment(url) hashes_from_link = {} if link_hash is None else link_hash.as_dict() @@ -254,8 +268,6 @@ class Link(KeyBasedCompareMixin): self.yanked_reason = yanked_reason self.metadata_file_data = metadata_file_data - super().__init__(key=url, defining_class=Link) - self.cache_link_parsing = cache_link_parsing self.egg_fragment = self._egg_fragment() @@ -272,7 +284,7 @@ class Link(KeyBasedCompareMixin): if file_url is None: return None - url = _ensure_quoted_url(urllib.parse.urljoin(page_url, file_url)) + url = _ensure_quoted_url(_absolute_link_url(page_url, file_url)) pyrequire = file_data.get("requires-python") yanked_reason = file_data.get("yanked") hashes = file_data.get("hashes", {}) @@ -324,7 +336,7 @@ class Link(KeyBasedCompareMixin): if not href: return None - url = _ensure_quoted_url(urllib.parse.urljoin(base_url, href)) + url = _ensure_quoted_url(_absolute_link_url(base_url, href)) pyrequire = anchor_attribs.get("data-requires-python") yanked_reason = anchor_attribs.get("data-yanked") @@ -375,6 +387,19 @@ class Link(KeyBasedCompareMixin): def __repr__(self) -> str: return f"" + def __hash__(self) -> int: + return hash(self.url) + + def __eq__(self, other: Any) -> bool: + if not isinstance(other, Link): + return NotImplemented + return self.url == other.url + + def __lt__(self, other: Any) -> bool: + if not isinstance(other, Link): + return NotImplemented + return self.url < other.url + @property def url(self) -> str: return self._url @@ -410,7 +435,7 @@ class Link(KeyBasedCompareMixin): @property def path(self) -> str: - return urllib.parse.unquote(self._parsed_url.path) + return self._path def splitext(self) -> Tuple[str, str]: return splitext(posixpath.basename(self.path.rstrip("/"))) @@ -441,10 +466,10 @@ class Link(KeyBasedCompareMixin): project_name = match.group(1) if not self._project_name_re.match(project_name): deprecated( - reason=f"{self} contains an egg fragment with a non-PEP 508 name", + reason=f"{self} contains an egg fragment with a non-PEP 508 name.", replacement="to use the req @ url syntax, and remove the egg fragment", - gone_in="25.0", - issue=11617, + gone_in="25.1", + issue=13157, ) return project_name diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/scheme.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/scheme.py index f51190a..06a9a55 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/scheme.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/scheme.py @@ -5,10 +5,12 @@ For a general overview of available schemes and their context, see https://docs.python.org/3/install/index.html#alternate-installation. """ +from dataclasses import dataclass SCHEME_KEYS = ["platlib", "purelib", "headers", "scripts", "data"] +@dataclass(frozen=True) class Scheme: """A Scheme holds paths which are used as the base directories for artifacts associated with a Python package. @@ -16,16 +18,8 @@ class Scheme: __slots__ = SCHEME_KEYS - def __init__( - self, - platlib: str, - purelib: str, - headers: str, - scripts: str, - data: str, - ) -> None: - self.platlib = platlib - self.purelib = purelib - self.headers = headers - self.scripts = scripts - self.data = data + platlib: str + purelib: str + headers: str + scripts: str + data: str diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/search_scope.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/search_scope.py index fe61e81..ee7bc86 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/search_scope.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/search_scope.py @@ -3,6 +3,7 @@ import logging import os import posixpath import urllib.parse +from dataclasses import dataclass from typing import List from pip._vendor.packaging.utils import canonicalize_name @@ -14,14 +15,18 @@ from pip._internal.utils.misc import normalize_path, redact_auth_from_url logger = logging.getLogger(__name__) +@dataclass(frozen=True) class SearchScope: - """ Encapsulates the locations that pip is configured to search. """ __slots__ = ["find_links", "index_urls", "no_index"] + find_links: List[str] + index_urls: List[str] + no_index: bool + @classmethod def create( cls, @@ -64,16 +69,6 @@ class SearchScope: no_index=no_index, ) - def __init__( - self, - find_links: List[str], - index_urls: List[str], - no_index: bool, - ) -> None: - self.find_links = find_links - self.index_urls = index_urls - self.no_index = no_index - def get_formatted_locations(self) -> str: lines = [] redacted_index_urls = [] diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/selection_prefs.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/selection_prefs.py index 977bc4c..e9b50aa 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/selection_prefs.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/selection_prefs.py @@ -3,6 +3,8 @@ from typing import Optional from pip._internal.models.format_control import FormatControl +# TODO: This needs Python 3.10's improved slots support for dataclasses +# to be converted into a dataclass. class SelectionPreferences: """ Encapsulates the candidate selection preferences for downloading diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/target_python.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/target_python.py index 67ea5da..88925a9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/target_python.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/target_python.py @@ -8,7 +8,6 @@ from pip._internal.utils.misc import normalize_version_info class TargetPython: - """ Encapsulates the properties of a Python interpreter one is targeting for a package install, download, etc. diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/models/wheel.py b/llmlab/lib/python3.12/site-packages/pip/_internal/models/wheel.py index a5dc12b..ea85600 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/models/wheel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/models/wheel.py @@ -1,12 +1,18 @@ """Represents a wheel file and provides access to the various parts of the name that have meaning. """ + import re from typing import Dict, Iterable, List from pip._vendor.packaging.tags import Tag +from pip._vendor.packaging.utils import ( + InvalidWheelFilename as PackagingInvalidWheelName, +) +from pip._vendor.packaging.utils import parse_wheel_filename from pip._internal.exceptions import InvalidWheelFilename +from pip._internal.utils.deprecation import deprecated class Wheel: @@ -28,9 +34,29 @@ class Wheel: raise InvalidWheelFilename(f"{filename} is not a valid wheel filename.") self.filename = filename self.name = wheel_info.group("name").replace("_", "-") - # we'll assume "_" means "-" due to wheel naming scheme - # (https://github.com/pypa/pip/issues/1150) - self.version = wheel_info.group("ver").replace("_", "-") + _version = wheel_info.group("ver") + if "_" in _version: + try: + parse_wheel_filename(filename) + except PackagingInvalidWheelName as e: + deprecated( + reason=( + f"Wheel filename {filename!r} is not correctly normalised. " + "Future versions of pip will raise the following error:\n" + f"{e.args[0]}\n\n" + ), + replacement=( + "to rename the wheel to use a correctly normalised " + "name (this may require updating the version in " + "the project metadata)" + ), + gone_in="25.1", + issue=12938, + ) + + _version = _version.replace("_", "-") + + self.version = _version self.build_tag = wheel_info.group("build") self.pyversions = wheel_info.group("pyver").split(".") self.abis = wheel_info.group("abi").split(".") diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/__init__.cpython-312.pyc index c38dffd..dc8267e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/auth.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/auth.cpython-312.pyc index 8258ecf..e34ec15 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/auth.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/auth.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/cache.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/cache.cpython-312.pyc index 910368e..0385a9b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/cache.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/cache.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/download.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/download.cpython-312.pyc index bab49bb..9d99bd3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/download.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/download.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/lazy_wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/lazy_wheel.cpython-312.pyc index 110bb98..4ddba57 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/lazy_wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/lazy_wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/session.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/session.cpython-312.pyc index 75ceece..15b62f7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/session.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/session.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/utils.cpython-312.pyc index 44ccb6b..67321b7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/utils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/utils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/xmlrpc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/xmlrpc.cpython-312.pyc index 7bd5235..93d0f91 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/xmlrpc.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/network/__pycache__/xmlrpc.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/auth.py b/llmlab/lib/python3.12/site-packages/pip/_internal/network/auth.py index 94a82fa..1a2606e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/network/auth.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/network/auth.py @@ -3,6 +3,7 @@ Contains interface (MultiDomainBasicAuth) and associated glue code for providing credentials in the context of network requests. """ + import logging import os import shutil @@ -47,12 +48,12 @@ class KeyRingBaseProvider(ABC): has_keyring: bool @abstractmethod - def get_auth_info(self, url: str, username: Optional[str]) -> Optional[AuthInfo]: - ... + def get_auth_info( + self, url: str, username: Optional[str] + ) -> Optional[AuthInfo]: ... @abstractmethod - def save_auth_info(self, url: str, username: str, password: str) -> None: - ... + def save_auth_info(self, url: str, username: str, password: str) -> None: ... class KeyRingNullProvider(KeyRingBaseProvider): @@ -151,7 +152,7 @@ class KeyRingCliProvider(KeyRingBaseProvider): env["PYTHONIOENCODING"] = "utf-8" subprocess.run( [self.keyring, "set", service_name, username], - input=f"{password}{os.linesep}".encode("utf-8"), + input=f"{password}{os.linesep}".encode(), env=env, check=True, ) @@ -270,6 +271,10 @@ class MultiDomainBasicAuth(AuthBase): try: return self.keyring_provider.get_auth_info(url, username) except Exception as exc: + # Log the full exception (with stacktrace) at debug, so it'll only + # show up when running in verbose mode. + logger.debug("Keyring is skipped due to an exception", exc_info=True) + # Always log a shortened version of the exception. logger.warning( "Keyring is skipped due to an exception: %s", str(exc), diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/cache.py b/llmlab/lib/python3.12/site-packages/pip/_internal/network/cache.py index 4d0fb54..fca04e6 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/network/cache.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/network/cache.py @@ -76,6 +76,18 @@ class SafeFileCache(SeparateBodyBaseCache): with adjacent_tmp_file(path) as f: f.write(data) + # Inherit the read/write permissions of the cache directory + # to enable multi-user cache use-cases. + mode = ( + os.stat(self.directory).st_mode + & 0o666 # select read/write permissions of cache directory + | 0o600 # set owner read/write permissions + ) + # Change permissions only if there is no risk of following a symlink. + if os.chmod in os.supports_fd: + os.chmod(f.fileno(), mode) + elif os.chmod in os.supports_follow_symlinks: + os.chmod(f.name, mode, follow_symlinks=False) replace(f.name, path) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/download.py b/llmlab/lib/python3.12/site-packages/pip/_internal/network/download.py index d1d4354..5c3bce3 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/network/download.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/network/download.py @@ -1,12 +1,13 @@ """Download files with progress indicators. """ + import email.message import logging import mimetypes import os from typing import Iterable, Optional, Tuple -from pip._vendor.requests.models import CONTENT_CHUNK_SIZE, Response +from pip._vendor.requests.models import Response from pip._internal.cli.progress_bars import get_download_progress_renderer from pip._internal.exceptions import NetworkConnectionError @@ -55,12 +56,12 @@ def _prepare_download( show_progress = False elif not total_length: show_progress = True - elif total_length > (40 * 1000): + elif total_length > (512 * 1024): show_progress = True else: show_progress = False - chunks = response_chunks(resp, CONTENT_CHUNK_SIZE) + chunks = response_chunks(resp) if not show_progress: return chunks diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/lazy_wheel.py b/llmlab/lib/python3.12/site-packages/pip/_internal/network/lazy_wheel.py index 82ec50d..03f883c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/network/lazy_wheel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/network/lazy_wheel.py @@ -159,7 +159,7 @@ class LazyZipOverHTTP: try: # For read-only ZIP files, ZipFile only needs # methods read, seek, seekable and tell. - ZipFile(self) # type: ignore + ZipFile(self) except BadZipFile: pass else: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/session.py b/llmlab/lib/python3.12/site-packages/pip/_internal/network/session.py index f17efc5..5e10f8f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/network/session.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/network/session.py @@ -3,6 +3,7 @@ network request configuration and behavior. """ import email.utils +import functools import io import ipaddress import json @@ -106,6 +107,7 @@ def looks_like_ci() -> bool: return any(name in os.environ for name in CI_ENVIRONMENT_VARIABLES) +@functools.lru_cache(maxsize=1) def user_agent() -> str: """ Return a string representing the user agent. @@ -230,7 +232,7 @@ class LocalFSAdapter(BaseAdapter): # to return a better error message: resp.status_code = 404 resp.reason = type(exc).__name__ - resp.raw = io.BytesIO(f"{resp.reason}: {exc}".encode("utf8")) + resp.raw = io.BytesIO(f"{resp.reason}: {exc}".encode()) else: modified = email.utils.formatdate(stats.st_mtime, usegmt=True) content_type = mimetypes.guess_type(pathname)[0] or "text/plain" @@ -337,6 +339,7 @@ class PipSession(requests.Session): # Namespace the attribute with "pip_" just in case to prevent # possible conflicts with the base class. self.pip_trusted_origins: List[Tuple[str, Optional[int]]] = [] + self.pip_proxy = None # Attach our User Agent to the request self.headers["User-Agent"] = user_agent() diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/network/utils.py b/llmlab/lib/python3.12/site-packages/pip/_internal/network/utils.py index 134848a..bba4c26 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/network/utils.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/network/utils.py @@ -1,6 +1,6 @@ from typing import Dict, Generator -from pip._vendor.requests.models import CONTENT_CHUNK_SIZE, Response +from pip._vendor.requests.models import Response from pip._internal.exceptions import NetworkConnectionError @@ -25,6 +25,8 @@ from pip._internal.exceptions import NetworkConnectionError # possible to make this work. HEADERS: Dict[str, str] = {"Accept-Encoding": "identity"} +DOWNLOAD_CHUNK_SIZE = 256 * 1024 + def raise_for_status(resp: Response) -> None: http_error_msg = "" @@ -55,7 +57,7 @@ def raise_for_status(resp: Response) -> None: def response_chunks( - response: Response, chunk_size: int = CONTENT_CHUNK_SIZE + response: Response, chunk_size: int = DOWNLOAD_CHUNK_SIZE ) -> Generator[bytes, None, None]: """Given a requests Response, provide the data chunks.""" try: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/__init__.cpython-312.pyc index 14f1bb1..2474dd1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/check.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/check.cpython-312.pyc index 30bde4d..6064e7b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/check.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/check.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/freeze.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/freeze.cpython-312.pyc index d9551b4..8e395bd 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/freeze.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/freeze.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/prepare.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/prepare.cpython-312.pyc index 3a7ddca..3786f8b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/prepare.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/__pycache__/prepare.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/__init__.cpython-312.pyc index 80a2b23..a0bf5c6 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/build_tracker.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/build_tracker.cpython-312.pyc index 75c34d6..93bdfe6 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/build_tracker.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/build_tracker.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata.cpython-312.pyc index 846a9ca..674396f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_editable.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_editable.cpython-312.pyc index 941e2ac..8e6a2cb 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_editable.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_editable.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_legacy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_legacy.cpython-312.pyc index 545a853..f593b3d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_legacy.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/metadata_legacy.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel.cpython-312.pyc index ae41a2d..8046eef 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_editable.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_editable.cpython-312.pyc index 349c689..bc40f6a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_editable.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_editable.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_legacy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_legacy.cpython-312.pyc index 14f8cd2..6e7a922 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_legacy.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/__pycache__/wheel_legacy.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/build_tracker.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/build_tracker.py index 3791932..0ed8dd2 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/build_tracker.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/build_tracker.py @@ -3,9 +3,8 @@ import hashlib import logging import os from types import TracebackType -from typing import Dict, Generator, Optional, Set, Type, Union +from typing import Dict, Generator, Optional, Type, Union -from pip._internal.models.link import Link from pip._internal.req.req_install import InstallRequirement from pip._internal.utils.temp_dir import TempDirectory @@ -99,7 +98,7 @@ class BuildTracker: except FileNotFoundError: pass else: - message = "{} is already being built: {}".format(req.link, contents) + message = f"{req.link} is already being built: {contents}" raise LookupError(message) # If we're here, req should really not be building already. diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_editable.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_editable.py index 27c69f0..3397ccf 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_editable.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_editable.py @@ -38,4 +38,5 @@ def generate_editable_metadata( except InstallationSubprocessError as error: raise MetadataGenerationFailed(package_details=details) from error + assert distinfo_dir is not None return os.path.join(metadata_dir, distinfo_dir) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_legacy.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_legacy.py index e60988d..c01dd1c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_legacy.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/metadata_legacy.py @@ -27,7 +27,7 @@ def _find_egg_info(directory: str) -> str: if len(filenames) > 1: raise InstallationError( - "More than one .egg-info directory found in {}".format(directory) + f"More than one .egg-info directory found in {directory}" ) return os.path.join(directory, filenames[0]) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/wheel_legacy.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/wheel_legacy.py index c5f0492..3ee2a70 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/wheel_legacy.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/build/wheel_legacy.py @@ -40,16 +40,16 @@ def get_legacy_build_wheel_path( # Sort for determinism. names = sorted(names) if not names: - msg = ("Legacy build of wheel for {!r} created no files.\n").format(name) + msg = f"Legacy build of wheel for {name!r} created no files.\n" msg += format_command_result(command_args, command_output) logger.warning(msg) return None if len(names) > 1: msg = ( - "Legacy build of wheel for {!r} created more than one file.\n" - "Filenames (choosing first): {}\n" - ).format(name, names) + f"Legacy build of wheel for {name!r} created more than one file.\n" + f"Filenames (choosing first): {names}\n" + ) msg += format_command_result(command_args, command_output) logger.warning(msg) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/check.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/check.py index 90c6a58..4b6fbc4 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/check.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/check.py @@ -2,31 +2,44 @@ """ import logging -from typing import Callable, Dict, List, NamedTuple, Optional, Set, Tuple +from contextlib import suppress +from email.parser import Parser +from functools import reduce +from typing import ( + Callable, + Dict, + FrozenSet, + Generator, + Iterable, + List, + NamedTuple, + Optional, + Set, + Tuple, +) from pip._vendor.packaging.requirements import Requirement -from pip._vendor.packaging.specifiers import LegacySpecifier +from pip._vendor.packaging.tags import Tag, parse_tag from pip._vendor.packaging.utils import NormalizedName, canonicalize_name -from pip._vendor.packaging.version import LegacyVersion +from pip._vendor.packaging.version import Version from pip._internal.distributions import make_distribution_for_install_requirement from pip._internal.metadata import get_default_environment -from pip._internal.metadata.base import DistributionVersion +from pip._internal.metadata.base import BaseDistribution from pip._internal.req.req_install import InstallRequirement -from pip._internal.utils.deprecation import deprecated logger = logging.getLogger(__name__) class PackageDetails(NamedTuple): - version: DistributionVersion + version: Version dependencies: List[Requirement] # Shorthands PackageSet = Dict[NormalizedName, PackageDetails] Missing = Tuple[NormalizedName, Requirement] -Conflicting = Tuple[NormalizedName, DistributionVersion, Requirement] +Conflicting = Tuple[NormalizedName, Version, Requirement] MissingDict = Dict[NormalizedName, List[Missing]] ConflictingDict = Dict[NormalizedName, List[Conflicting]] @@ -46,7 +59,7 @@ def create_package_set_from_installed() -> Tuple[PackageSet, bool]: package_set[name] = PackageDetails(dist.version, dependencies) except (OSError, ValueError) as e: # Don't crash on unreadable or broken metadata. - logger.warning("Error parsing requirements for %s: %s", name, e) + logger.warning("Error parsing dependencies of %s: %s", name, e) problems = True return package_set, problems @@ -60,8 +73,6 @@ def check_package_set( package name and returns a boolean. """ - warn_legacy_versions_and_specifiers(package_set) - missing = {} conflicting = {} @@ -118,6 +129,22 @@ def check_install_conflicts(to_install: List[InstallRequirement]) -> ConflictDet ) +def check_unsupported( + packages: Iterable[BaseDistribution], + supported_tags: Iterable[Tag], +) -> Generator[BaseDistribution, None, None]: + for p in packages: + with suppress(FileNotFoundError): + wheel_file = p.read_text("WHEEL") + wheel_tags: FrozenSet[Tag] = reduce( + frozenset.union, + map(parse_tag, Parser().parsestr(wheel_file).get_all("Tag", [])), + frozenset(), + ) + if wheel_tags.isdisjoint(supported_tags): + yield p + + def _simulate_installation_of( to_install: List[InstallRequirement], package_set: PackageSet ) -> Set[NormalizedName]: @@ -152,36 +179,3 @@ def _create_whitelist( break return packages_affected - - -def warn_legacy_versions_and_specifiers(package_set: PackageSet) -> None: - for project_name, package_details in package_set.items(): - if isinstance(package_details.version, LegacyVersion): - deprecated( - reason=( - f"{project_name} {package_details.version} " - f"has a non-standard version number." - ), - replacement=( - f"to upgrade to a newer version of {project_name} " - f"or contact the author to suggest that they " - f"release a version with a conforming version number" - ), - issue=12063, - gone_in="24.1", - ) - for dep in package_details.dependencies: - if any(isinstance(spec, LegacySpecifier) for spec in dep.specifier): - deprecated( - reason=( - f"{project_name} {package_details.version} " - f"has a non-standard dependency specifier {dep}." - ), - replacement=( - f"to upgrade to a newer version of {project_name} " - f"or contact the author to suggest that they " - f"release a version with a conforming dependency specifiers" - ), - issue=12063, - gone_in="24.1", - ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/freeze.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/freeze.py index 3544568..ae5dd37 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/freeze.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/freeze.py @@ -1,10 +1,11 @@ import collections import logging import os +from dataclasses import dataclass, field from typing import Container, Dict, Generator, Iterable, List, NamedTuple, Optional, Set -from pip._vendor.packaging.utils import canonicalize_name -from pip._vendor.packaging.version import Version +from pip._vendor.packaging.utils import NormalizedName, canonicalize_name +from pip._vendor.packaging.version import InvalidVersion from pip._internal.exceptions import BadCommand, InstallationError from pip._internal.metadata import BaseDistribution, get_environment @@ -145,10 +146,13 @@ def freeze( def _format_as_name_version(dist: BaseDistribution) -> str: - dist_version = dist.version - if isinstance(dist_version, Version): + try: + dist_version = dist.version + except InvalidVersion: + # legacy version + return f"{dist.raw_name}==={dist.raw_version}" + else: return f"{dist.raw_name}=={dist_version}" - return f"{dist.raw_name}==={dist_version}" def _get_editable_info(dist: BaseDistribution) -> _EditableInfo: @@ -217,19 +221,16 @@ def _get_editable_info(dist: BaseDistribution) -> _EditableInfo: ) +@dataclass(frozen=True) class FrozenRequirement: - def __init__( - self, - name: str, - req: str, - editable: bool, - comments: Iterable[str] = (), - ) -> None: - self.name = name - self.canonical_name = canonicalize_name(name) - self.req = req - self.editable = editable - self.comments = comments + name: str + req: str + editable: bool + comments: Iterable[str] = field(default_factory=tuple) + + @property + def canonical_name(self) -> NormalizedName: + return canonicalize_name(self.name) @classmethod def from_dist(cls, dist: BaseDistribution) -> "FrozenRequirement": diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/__init__.cpython-312.pyc index a5bedae..a2d13b6 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/editable_legacy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/editable_legacy.cpython-312.pyc index 0f9641f..b1ebb32 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/editable_legacy.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/editable_legacy.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/wheel.cpython-312.pyc index f370369..1addefd 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/__pycache__/wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/editable_legacy.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/editable_legacy.py index bebe24e..9aaa699 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/editable_legacy.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/editable_legacy.py @@ -1,5 +1,6 @@ """Legacy editable installation process, i.e. `setup.py develop`. """ + import logging from typing import Optional, Sequence diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/wheel.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/wheel.py index f67180c..aef42aa 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/wheel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/install/wheel.py @@ -28,6 +28,7 @@ from typing import ( List, NewType, Optional, + Protocol, Sequence, Set, Tuple, @@ -50,7 +51,7 @@ from pip._internal.metadata import ( from pip._internal.models.direct_url import DIRECT_URL_METADATA_NAME, DirectUrl from pip._internal.models.scheme import SCHEME_KEYS, Scheme from pip._internal.utils.filesystem import adjacent_tmp_file, replace -from pip._internal.utils.misc import captured_stdout, ensure_dir, hash_file, partition +from pip._internal.utils.misc import StreamWrapper, ensure_dir, hash_file, partition from pip._internal.utils.unpacking import ( current_umask, is_within_directory, @@ -60,7 +61,6 @@ from pip._internal.utils.unpacking import ( from pip._internal.utils.wheel import parse_wheel if TYPE_CHECKING: - from typing import Protocol class File(Protocol): src_record_path: "RecordPath" @@ -288,17 +288,15 @@ def get_console_script_specs(console: Dict[str, str]) -> List[str]: # the wheel metadata at build time, and so if the wheel is installed with # a *different* version of Python the entry points will be wrong. The # correct fix for this is to enhance the metadata to be able to describe - # such versioned entry points, but that won't happen till Metadata 2.0 is - # available. - # In the meantime, projects using versioned entry points will either have + # such versioned entry points. + # Currently, projects using versioned entry points will either have # incorrect versioned entry points, or they will not be able to distribute # "universal" wheels (i.e., they will need a wheel per Python version). # # Because setuptools and pip are bundled with _ensurepip and virtualenv, - # we need to use universal wheels. So, as a stopgap until Metadata 2.0, we + # we need to use universal wheels. As a workaround, we # override the versioned entry points in the wheel and generate the - # correct ones. This code is purely a short-term measure until Metadata 2.0 - # is available. + # correct ones. # # To add the level of hack in this section of code, in order to support # ensurepip this code will look for an ``ENSUREPIP_OPTIONS`` environment @@ -360,12 +358,6 @@ class ZipBackedFile: return self._zip_file.getinfo(self.src_record_path) def save(self) -> None: - # directory creation is lazy and after file filtering - # to ensure we don't install empty dirs; empty dirs can't be - # uninstalled. - parent_dir = os.path.dirname(self.dest_path) - ensure_dir(parent_dir) - # When we open the output file below, any existing file is truncated # before we start writing the new contents. This is fine in most # cases, but can cause a segfault if pip has loaded a shared @@ -379,9 +371,13 @@ class ZipBackedFile: zipinfo = self._getinfo() - with self._zip_file.open(zipinfo) as f: - with open(self.dest_path, "wb") as dest: - shutil.copyfileobj(f, dest) + # optimization: the file is created by open(), + # skip the decompression when there is 0 bytes to decompress. + with open(self.dest_path, "wb") as dest: + if zipinfo.file_size > 0: + with self._zip_file.open(zipinfo) as f: + blocksize = min(zipinfo.file_size, 1024 * 1024) + shutil.copyfileobj(f, dest, blocksize) if zip_item_is_executable(zipinfo): set_extracted_file_to_default_mode_plus_executable(self.dest_path) @@ -423,7 +419,7 @@ class PipScriptMaker(ScriptMaker): return super().make(specification, options) -def _install_wheel( +def _install_wheel( # noqa: C901, PLR0915 function is too long name: str, wheel_zip: ZipFile, wheel_path: str, @@ -507,9 +503,9 @@ def _install_wheel( _, scheme_key, dest_subpath = normed_path.split(os.path.sep, 2) except ValueError: message = ( - "Unexpected file in {}: {!r}. .data directory contents" - " should be named like: '/'." - ).format(wheel_path, record_path) + f"Unexpected file in {wheel_path}: {record_path!r}. .data directory" + " contents should be named like: '/'." + ) raise InstallationError(message) try: @@ -517,10 +513,11 @@ def _install_wheel( except KeyError: valid_scheme_keys = ", ".join(sorted(scheme_paths)) message = ( - "Unknown scheme key used in {}: {} (for file {!r}). .data" - " directory contents should be in subdirectories named" - " with a valid scheme key ({})" - ).format(wheel_path, scheme_key, record_path, valid_scheme_keys) + f"Unknown scheme key used in {wheel_path}: {scheme_key} " + f"(for file {record_path!r}). .data directory contents " + f"should be in subdirectories named with a valid scheme " + f"key ({valid_scheme_keys})" + ) raise InstallationError(message) dest_path = os.path.join(scheme_path, dest_subpath) @@ -581,7 +578,15 @@ def _install_wheel( script_scheme_files = map(ScriptFile, script_scheme_files) files = chain(files, script_scheme_files) + existing_parents = set() for file in files: + # directory creation is lazy and after file filtering + # to ensure we don't install empty dirs; empty dirs can't be + # uninstalled. + parent_dir = os.path.dirname(file.dest_path) + if parent_dir not in existing_parents: + ensure_dir(parent_dir) + existing_parents.add(parent_dir) file.save() record_installed(file.src_record_path, file.dest_path, file.changed) @@ -604,7 +609,9 @@ def _install_wheel( # Compile all of the pyc files for the installed files if pycompile: - with captured_stdout() as stdout: + with contextlib.redirect_stdout( + StreamWrapper.from_stream(sys.stdout) + ) as stdout: with warnings.catch_warnings(): warnings.filterwarnings("ignore") for path in pyc_source_file_paths(): diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/prepare.py b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/prepare.py index 956717d..e6aa344 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/operations/prepare.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/operations/prepare.py @@ -7,6 +7,7 @@ import mimetypes import os import shutil +from dataclasses import dataclass from pathlib import Path from typing import Dict, Iterable, List, Optional @@ -80,13 +81,14 @@ def unpack_vcs_link(link: Link, location: str, verbosity: int) -> None: vcs_backend.unpack(location, url=hide_url(link.url), verbosity=verbosity) +@dataclass class File: - def __init__(self, path: str, content_type: Optional[str]) -> None: - self.path = path - if content_type is None: - self.content_type = mimetypes.guess_type(path)[0] - else: - self.content_type = content_type + path: str + content_type: Optional[str] = None + + def __post_init__(self) -> None: + if self.content_type is None: + self.content_type = mimetypes.guess_type(self.path)[0] def get_http_url( diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/pyproject.py b/llmlab/lib/python3.12/site-packages/pip/_internal/pyproject.py index 8de36b8..0e8452f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/pyproject.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/pyproject.py @@ -1,16 +1,22 @@ import importlib.util import os +import sys from collections import namedtuple from typing import Any, List, Optional -from pip._vendor import tomli -from pip._vendor.packaging.requirements import InvalidRequirement, Requirement +if sys.version_info >= (3, 11): + import tomllib +else: + from pip._vendor import tomli as tomllib + +from pip._vendor.packaging.requirements import InvalidRequirement from pip._internal.exceptions import ( InstallationError, InvalidPyProjectBuildRequires, MissingPyProjectBuildRequires, ) +from pip._internal.utils.packaging import get_requirement def _is_list_of_str(obj: Any) -> bool: @@ -61,13 +67,13 @@ def load_pyproject_toml( if has_pyproject: with open(pyproject_toml, encoding="utf-8") as f: - pp_toml = tomli.loads(f.read()) + pp_toml = tomllib.loads(f.read()) build_system = pp_toml.get("build-system") else: build_system = None # The following cases must use PEP 517 - # We check for use_pep517 being non-None and falsey because that means + # We check for use_pep517 being non-None and falsy because that means # the user explicitly requested --no-use-pep517. The value 0 as # opposed to False can occur when the value is provided via an # environment variable or config file option (due to the quirk of @@ -151,7 +157,7 @@ def load_pyproject_toml( # Each requirement must be valid as per PEP 508 for requirement in requires: try: - Requirement(requirement) + get_requirement(requirement) except InvalidRequirement as error: raise InvalidPyProjectBuildRequires( package=req_name, diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__init__.py index 16de903..422d851 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__init__.py @@ -1,5 +1,6 @@ import collections import logging +from dataclasses import dataclass from typing import Generator, List, Optional, Sequence, Tuple from pip._internal.utils.logging import indent_log @@ -18,12 +19,9 @@ __all__ = [ logger = logging.getLogger(__name__) +@dataclass(frozen=True) class InstallationResult: - def __init__(self, name: str) -> None: - self.name = name - - def __repr__(self) -> str: - return f"InstallationResult(name={self.name!r})" + name: str def _validate_requirements( diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/__init__.cpython-312.pyc index d4137ce..44e490c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/constructors.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/constructors.cpython-312.pyc index 5b7bd97..e3bf880 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/constructors.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/constructors.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_file.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_file.cpython-312.pyc index f26853f..622f280 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_file.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_file.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_install.cpython-312.pyc index b67b0ea..e3c861b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_install.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_install.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_set.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_set.cpython-312.pyc index 9265fb1..b77944c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_set.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_set.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_uninstall.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_uninstall.cpython-312.pyc index 4d44053..ab4b05c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_uninstall.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/req/__pycache__/req_uninstall.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/constructors.py b/llmlab/lib/python3.12/site-packages/pip/_internal/req/constructors.py index 7e2d0e5..56a964f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/req/constructors.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/req/constructors.py @@ -12,6 +12,7 @@ import copy import logging import os import re +from dataclasses import dataclass from typing import Collection, Dict, List, Optional, Set, Tuple, Union from pip._vendor.packaging.markers import Marker @@ -79,8 +80,8 @@ def _set_requirement_extras(req: Requirement, new_extras: Set[str]) -> Requireme assert ( pre is not None and post is not None ), f"regex group selection for requirement {req} failed, this should never happen" - extras: str = "[%s]" % ",".join(sorted(new_extras)) if new_extras else "" - return Requirement(f"{pre}{extras}{post}") + extras: str = "[{}]".format(",".join(sorted(new_extras)) if new_extras else "") + return get_requirement(f"{pre}{extras}{post}") def parse_editable(editable_req: str) -> Tuple[Optional[str], str, Set[str]]: @@ -132,8 +133,8 @@ def parse_editable(editable_req: str) -> Tuple[Optional[str], str, Set[str]]: package_name = link.egg_fragment if not package_name: raise InstallationError( - "Could not detect requirement name for '{}', please specify one " - "with #egg=your_package_name".format(editable_req) + f"Could not detect requirement name for '{editable_req}', " + "please specify one with #egg=your_package_name" ) return package_name, url, set() @@ -162,7 +163,7 @@ def check_first_requirement_in_file(filename: str) -> None: # If there is a line continuation, drop it, and append the next line. if line.endswith("\\"): line = line[:-2].strip() + next(lines, "") - Requirement(line) + get_requirement(line) return @@ -191,18 +192,12 @@ def deduce_helpful_msg(req: str) -> str: return msg +@dataclass(frozen=True) class RequirementParts: - def __init__( - self, - requirement: Optional[Requirement], - link: Optional[Link], - markers: Optional[Marker], - extras: Set[str], - ): - self.requirement = requirement - self.link = link - self.markers = markers - self.extras = extras + requirement: Optional[Requirement] + link: Optional[Link] + markers: Optional[Marker] + extras: Set[str] def parse_req_from_editable(editable_req: str) -> RequirementParts: @@ -210,9 +205,9 @@ def parse_req_from_editable(editable_req: str) -> RequirementParts: if name is not None: try: - req: Optional[Requirement] = Requirement(name) - except InvalidRequirement: - raise InstallationError(f"Invalid requirement: '{name}'") + req: Optional[Requirement] = get_requirement(name) + except InvalidRequirement as exc: + raise InstallationError(f"Invalid requirement: {name!r}: {exc}") else: req = None @@ -364,8 +359,8 @@ def parse_req_from_line(name: str, line_source: Optional[str]) -> RequirementPar def _parse_req_string(req_as_string: str) -> Requirement: try: - req = get_requirement(req_as_string) - except InvalidRequirement: + return get_requirement(req_as_string) + except InvalidRequirement as exc: if os.path.sep in req_as_string: add_msg = "It looks like a path." add_msg += deduce_helpful_msg(req_as_string) @@ -375,21 +370,10 @@ def parse_req_from_line(name: str, line_source: Optional[str]) -> RequirementPar add_msg = "= is not a valid operator. Did you mean == ?" else: add_msg = "" - msg = with_source(f"Invalid requirement: {req_as_string!r}") + msg = with_source(f"Invalid requirement: {req_as_string!r}: {exc}") if add_msg: msg += f"\nHint: {add_msg}" raise InstallationError(msg) - else: - # Deprecate extras after specifiers: "name>=1.0[extras]" - # This currently works by accident because _strip_extras() parses - # any extras in the end of the string and those are saved in - # RequirementParts - for spec in req.specifier: - spec_str = str(spec) - if spec_str.endswith("]"): - msg = f"Extras after version '{spec_str}'." - raise InstallationError(msg) - return req if req_as_string is not None: req: Optional[Requirement] = _parse_req_string(req_as_string) @@ -445,8 +429,8 @@ def install_req_from_req_string( ) -> InstallRequirement: try: req = get_requirement(req_string) - except InvalidRequirement: - raise InstallationError(f"Invalid requirement: '{req_string}'") + except InvalidRequirement as exc: + raise InstallationError(f"Invalid requirement: {req_string!r}: {exc}") domains_not_allowed = [ PyPI.file_storage_domain, diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_file.py b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_file.py index 1ef3d5e..f6ba70f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_file.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_file.py @@ -2,12 +2,16 @@ Requirements file parsing """ +import codecs +import locale import logging import optparse import os import re import shlex +import sys import urllib.parse +from dataclasses import dataclass from optparse import Values from typing import ( TYPE_CHECKING, @@ -17,6 +21,7 @@ from typing import ( Generator, Iterable, List, + NoReturn, Optional, Tuple, ) @@ -24,17 +29,10 @@ from typing import ( from pip._internal.cli import cmdoptions from pip._internal.exceptions import InstallationError, RequirementsFileParseError from pip._internal.models.search_scope import SearchScope -from pip._internal.network.session import PipSession -from pip._internal.network.utils import raise_for_status -from pip._internal.utils.encoding import auto_decode -from pip._internal.utils.urls import get_url_scheme if TYPE_CHECKING: - # NoReturn introduced in 3.6.2; imported only for type checking to maintain - # pip compatibility with older patch versions of Python 3.6 - from typing import NoReturn - from pip._internal.index.package_finder import PackageFinder + from pip._internal.network.session import PipSession __all__ = ["parse_requirements"] @@ -86,57 +84,71 @@ SUPPORTED_OPTIONS_EDITABLE_REQ_DEST = [ str(o().dest) for o in SUPPORTED_OPTIONS_EDITABLE_REQ ] +# order of BOMS is important: codecs.BOM_UTF16_LE is a prefix of codecs.BOM_UTF32_LE +# so data.startswith(BOM_UTF16_LE) would be true for UTF32_LE data +BOMS: List[Tuple[bytes, str]] = [ + (codecs.BOM_UTF8, "utf-8"), + (codecs.BOM_UTF32, "utf-32"), + (codecs.BOM_UTF32_BE, "utf-32-be"), + (codecs.BOM_UTF32_LE, "utf-32-le"), + (codecs.BOM_UTF16, "utf-16"), + (codecs.BOM_UTF16_BE, "utf-16-be"), + (codecs.BOM_UTF16_LE, "utf-16-le"), +] + +PEP263_ENCODING_RE = re.compile(rb"coding[:=]\s*([-\w.]+)") +DEFAULT_ENCODING = "utf-8" + logger = logging.getLogger(__name__) +@dataclass(frozen=True) class ParsedRequirement: - def __init__( - self, - requirement: str, - is_editable: bool, - comes_from: str, - constraint: bool, - options: Optional[Dict[str, Any]] = None, - line_source: Optional[str] = None, - ) -> None: - self.requirement = requirement - self.is_editable = is_editable - self.comes_from = comes_from - self.options = options - self.constraint = constraint - self.line_source = line_source + # TODO: replace this with slots=True when dropping Python 3.9 support. + __slots__ = ( + "requirement", + "is_editable", + "comes_from", + "constraint", + "options", + "line_source", + ) + + requirement: str + is_editable: bool + comes_from: str + constraint: bool + options: Optional[Dict[str, Any]] + line_source: Optional[str] +@dataclass(frozen=True) class ParsedLine: - def __init__( - self, - filename: str, - lineno: int, - args: str, - opts: Values, - constraint: bool, - ) -> None: - self.filename = filename - self.lineno = lineno - self.opts = opts - self.constraint = constraint + __slots__ = ("filename", "lineno", "args", "opts", "constraint") - if args: - self.is_requirement = True - self.is_editable = False - self.requirement = args - elif opts.editables: - self.is_requirement = True - self.is_editable = True + filename: str + lineno: int + args: str + opts: Values + constraint: bool + + @property + def is_editable(self) -> bool: + return bool(self.opts.editables) + + @property + def requirement(self) -> Optional[str]: + if self.args: + return self.args + elif self.is_editable: # We don't support multiple -e on one line - self.requirement = opts.editables[0] - else: - self.is_requirement = False + return self.opts.editables[0] + return None def parse_requirements( filename: str, - session: PipSession, + session: "PipSession", finder: Optional["PackageFinder"] = None, options: Optional[optparse.Values] = None, constraint: bool = False, @@ -184,7 +196,7 @@ def handle_requirement_line( line.lineno, ) - assert line.is_requirement + assert line.requirement is not None # get the options that apply to requirements if line.is_editable: @@ -213,7 +225,7 @@ def handle_option_line( lineno: int, finder: Optional["PackageFinder"] = None, options: Optional[optparse.Values] = None, - session: Optional[PipSession] = None, + session: Optional["PipSession"] = None, ) -> None: if opts.hashes: logger.warning( @@ -281,7 +293,7 @@ def handle_line( line: ParsedLine, options: Optional[optparse.Values] = None, finder: Optional["PackageFinder"] = None, - session: Optional[PipSession] = None, + session: Optional["PipSession"] = None, ) -> Optional[ParsedRequirement]: """Handle a single parsed requirements line; This can result in creating/yielding requirements, or updating the finder. @@ -306,7 +318,7 @@ def handle_line( affect the finder. """ - if line.is_requirement: + if line.requirement is not None: parsed_req = handle_requirement_line(line, options) return parsed_req else: @@ -324,7 +336,7 @@ def handle_line( class RequirementsFileParser: def __init__( self, - session: PipSession, + session: "PipSession", line_parser: LineParser, ) -> None: self._session = session @@ -334,13 +346,18 @@ class RequirementsFileParser: self, filename: str, constraint: bool ) -> Generator[ParsedLine, None, None]: """Parse a given file, yielding parsed lines.""" - yield from self._parse_and_recurse(filename, constraint) + yield from self._parse_and_recurse( + filename, constraint, [{os.path.abspath(filename): None}] + ) def _parse_and_recurse( - self, filename: str, constraint: bool + self, + filename: str, + constraint: bool, + parsed_files_stack: List[Dict[str, Optional[str]]], ) -> Generator[ParsedLine, None, None]: for line in self._parse_file(filename, constraint): - if not line.is_requirement and ( + if line.requirement is None and ( line.opts.requirements or line.opts.constraints ): # parse a nested requirements file @@ -358,12 +375,30 @@ class RequirementsFileParser: # original file and nested file are paths elif not SCHEME_RE.search(req_path): # do a join so relative paths work - req_path = os.path.join( - os.path.dirname(filename), - req_path, + # and then abspath so that we can identify recursive references + req_path = os.path.abspath( + os.path.join( + os.path.dirname(filename), + req_path, + ) ) - - yield from self._parse_and_recurse(req_path, nested_constraint) + parsed_files = parsed_files_stack[0] + if req_path in parsed_files: + initial_file = parsed_files[req_path] + tail = ( + f" and again in {initial_file}" + if initial_file is not None + else "" + ) + raise RequirementsFileParseError( + f"{req_path} recursively references itself in {filename}{tail}" + ) + # Keeping a track where was each file first included in + new_parsed_files = parsed_files.copy() + new_parsed_files[req_path] = filename + yield from self._parse_and_recurse( + req_path, nested_constraint, [new_parsed_files, *parsed_files_stack] + ) else: yield line @@ -529,7 +564,7 @@ def expand_env_variables(lines_enum: ReqFileLines) -> ReqFileLines: yield line_number, line -def get_file_content(url: str, session: PipSession) -> Tuple[str, str]: +def get_file_content(url: str, session: "PipSession") -> Tuple[str, str]: """Gets the content of a file; it may be a filename, file: URL, or http: URL. Returns (location, content). Content is unicode. Respects # -*- coding: declarations on the retrieved files. @@ -537,10 +572,12 @@ def get_file_content(url: str, session: PipSession) -> Tuple[str, str]: :param url: File path or url. :param session: PipSession instance. """ - scheme = get_url_scheme(url) - + scheme = urllib.parse.urlsplit(url).scheme # Pip has special support for file:// URLs (LocalFSAdapter). if scheme in ["http", "https", "file"]: + # Delay importing heavy network modules until absolutely necessary. + from pip._internal.network.utils import raise_for_status + resp = session.get(url) raise_for_status(resp) return resp.url, resp.text @@ -548,7 +585,39 @@ def get_file_content(url: str, session: PipSession) -> Tuple[str, str]: # Assume this is a bare path. try: with open(url, "rb") as f: - content = auto_decode(f.read()) + raw_content = f.read() except OSError as exc: raise InstallationError(f"Could not open requirements file: {exc}") + + content = _decode_req_file(raw_content, url) + return url, content + + +def _decode_req_file(data: bytes, url: str) -> str: + for bom, encoding in BOMS: + if data.startswith(bom): + return data[len(bom) :].decode(encoding) + + for line in data.split(b"\n")[:2]: + if line[0:1] == b"#": + result = PEP263_ENCODING_RE.search(line) + if result is not None: + encoding = result.groups()[0].decode("ascii") + return data.decode(encoding) + + try: + return data.decode(DEFAULT_ENCODING) + except UnicodeDecodeError: + locale_encoding = locale.getpreferredencoding(False) or sys.getdefaultencoding() + logging.warning( + "unable to decode data from %s with default encoding %s, " + "falling back to encoding from locale: %s. " + "If this is intentional you should specify the encoding with a " + "PEP-263 style comment, e.g. '# -*- coding: %s -*-'", + url, + DEFAULT_ENCODING, + locale_encoding, + locale_encoding, + ) + return data.decode(locale_encoding) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_install.py b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_install.py index a65611c..3262d82 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_install.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_install.py @@ -52,7 +52,7 @@ from pip._internal.utils.misc import ( redact_auth_from_requirement, redact_auth_from_url, ) -from pip._internal.utils.packaging import safe_extra +from pip._internal.utils.packaging import get_requirement from pip._internal.utils.subprocess import runner_with_spinner_message from pip._internal.utils.temp_dir import TempDirectory, tempdir_kinds from pip._internal.utils.unpacking import unpack_file @@ -222,8 +222,9 @@ class InstallRequirement: return s def __repr__(self) -> str: - return "<{} object: {} editable={!r}>".format( - self.__class__.__name__, str(self), self.editable + return ( + f"<{self.__class__.__name__} object: " + f"{str(self)} editable={self.editable!r}>" ) def format_debug(self) -> str: @@ -244,7 +245,7 @@ class InstallRequirement: return None return self.req.name - @functools.lru_cache() # use cached_property in python 3.8+ + @functools.cached_property def supports_pyproject_editable(self) -> bool: if not self.use_pep517: return False @@ -283,12 +284,7 @@ class InstallRequirement: extras_requested = ("",) if self.markers is not None: return any( - self.markers.evaluate({"extra": extra}) - # TODO: Remove these two variants when packaging is upgraded to - # support the marker comparison logic specified in PEP 685. - or self.markers.evaluate({"extra": safe_extra(extra)}) - or self.markers.evaluate({"extra": canonicalize_name(extra)}) - for extra in extras_requested + self.markers.evaluate({"extra": extra}) for extra in extras_requested ) else: return True @@ -400,7 +396,7 @@ class InstallRequirement: else: op = "===" - self.req = Requirement( + self.req = get_requirement( "".join( [ self.metadata["Name"], @@ -426,7 +422,7 @@ class InstallRequirement: metadata_name, self.name, ) - self.req = Requirement(metadata_name) + self.req = get_requirement(metadata_name) def check_if_exists(self, use_user_site: bool) -> None: """Find an installed distribution that satisfies or conflicts @@ -542,7 +538,7 @@ class InstallRequirement: if ( self.editable and self.use_pep517 - and not self.supports_pyproject_editable() + and not self.supports_pyproject_editable and not os.path.isfile(self.setup_py_path) and not os.path.isfile(self.setup_cfg_path) ): @@ -568,7 +564,7 @@ class InstallRequirement: if ( self.editable and self.permit_editable_wheels - and self.supports_pyproject_editable() + and self.supports_pyproject_editable ): self.metadata_directory = generate_editable_metadata( build_env=self.build_env, @@ -829,6 +825,21 @@ class InstallRequirement: ) if self.editable and not self.is_wheel: + deprecated( + reason=( + f"Legacy editable install of {self} (setup.py develop) " + "is deprecated." + ), + replacement=( + "to add a pyproject.toml or enable --use-pep517, " + "and use setuptools >= 64. " + "If the resulting installation is not behaving as expected, " + "try using --config-settings editable_mode=compat. " + "Please consult the setuptools documentation for more information" + ), + gone_in="25.1", + issue=11457, + ) if self.config_settings: logger.warning( "--config-settings ignored for legacy editable install of %s. " @@ -914,7 +925,7 @@ def check_legacy_setup_py_options( reason="--build-option and --global-option are deprecated.", issue=11859, replacement="to use --config-settings", - gone_in="24.2", + gone_in=None, ) logger.warning( "Implying --no-binary=:all: due to the presence of " diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_set.py b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_set.py index bf36114..ec7a6e0 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_set.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_set.py @@ -2,12 +2,9 @@ import logging from collections import OrderedDict from typing import Dict, List -from pip._vendor.packaging.specifiers import LegacySpecifier from pip._vendor.packaging.utils import canonicalize_name -from pip._vendor.packaging.version import LegacyVersion from pip._internal.req.req_install import InstallRequirement -from pip._internal.utils.deprecation import deprecated logger = logging.getLogger(__name__) @@ -83,37 +80,3 @@ class RequirementSet: for install_req in self.all_requirements if not install_req.constraint and not install_req.satisfied_by ] - - def warn_legacy_versions_and_specifiers(self) -> None: - for req in self.requirements_to_install: - version = req.get_dist().version - if isinstance(version, LegacyVersion): - deprecated( - reason=( - f"pip has selected the non standard version {version} " - f"of {req}. In the future this version will be " - f"ignored as it isn't standard compliant." - ), - replacement=( - "set or update constraints to select another version " - "or contact the package author to fix the version number" - ), - issue=12063, - gone_in="24.1", - ) - for dep in req.get_dist().iter_dependencies(): - if any(isinstance(spec, LegacySpecifier) for spec in dep.specifier): - deprecated( - reason=( - f"pip has selected {req} {version} which has non " - f"standard dependency specifier {dep}. " - f"In the future this version of {req} will be " - f"ignored as it isn't standard compliant." - ), - replacement=( - "set or update constraints to select another version " - "or contact the package author to fix the version number" - ), - issue=12063, - gone_in="24.1", - ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_uninstall.py b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_uninstall.py index 707fde1..26df208 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_uninstall.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/req/req_uninstall.py @@ -5,7 +5,7 @@ import sysconfig from importlib.util import cache_from_source from typing import Any, Callable, Dict, Generator, Iterable, List, Optional, Set, Tuple -from pip._internal.exceptions import UninstallationError +from pip._internal.exceptions import LegacyDistutilsInstall, UninstallMissingRecord from pip._internal.locations import get_bin_prefix, get_bin_user from pip._internal.metadata import BaseDistribution from pip._internal.utils.compat import WINDOWS @@ -61,7 +61,7 @@ def uninstallation_paths(dist: BaseDistribution) -> Generator[str, None, None]: UninstallPathSet.add() takes care of the __pycache__ .py[co]. - If RECORD is not found, raises UninstallationError, + If RECORD is not found, raises an error, with possible information from the INSTALLER file. https://packaging.python.org/specifications/recording-installed-packages/ @@ -71,17 +71,7 @@ def uninstallation_paths(dist: BaseDistribution) -> Generator[str, None, None]: entries = dist.iter_declared_entries() if entries is None: - msg = f"Cannot uninstall {dist}, RECORD file not found." - installer = dist.installer - if not installer or installer == "pip": - dep = f"{dist.raw_name}=={dist.version}" - msg += ( - " You might be able to recover from this via: " - f"'pip install --force-reinstall --no-deps {dep}'." - ) - else: - msg += f" Hint: The package was installed by {installer}." - raise UninstallationError(msg) + raise UninstallMissingRecord(distribution=dist) for entry in entries: path = os.path.join(location, entry) @@ -315,7 +305,7 @@ class UninstallPathSet: # Create local cache of normalize_path results. Creating an UninstallPathSet # can result in hundreds/thousands of redundant calls to normalize_path with # the same args, which hurts performance. - self._normalize_path_cached = functools.lru_cache()(normalize_path) + self._normalize_path_cached = functools.lru_cache(normalize_path) def _permitted(self, path: str) -> bool: """ @@ -367,7 +357,7 @@ class UninstallPathSet: ) return - dist_name_version = f"{self._dist.raw_name}-{self._dist.version}" + dist_name_version = f"{self._dist.raw_name}-{self._dist.raw_version}" logger.info("Uninstalling %s:", dist_name_version) with indent_log(): @@ -509,13 +499,7 @@ class UninstallPathSet: paths_to_remove.add(f"{path}.pyo") elif dist.installed_by_distutils: - raise UninstallationError( - "Cannot uninstall {!r}. It is a distutils installed project " - "and thus we cannot accurately determine which files belong " - "to it which would lead to only a partial uninstall.".format( - dist.raw_name, - ) - ) + raise LegacyDistutilsInstall(distribution=dist) elif dist.installed_as_egg: # package installed by easy_install diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/__init__.cpython-312.pyc index 2cf38ba..11a93cf 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/base.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/base.cpython-312.pyc index 50c5735..adb1b33 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/base.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/__pycache__/base.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/__init__.cpython-312.pyc index 66ae3af..113d806 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/resolver.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/resolver.cpython-312.pyc index be4f59b..0f33636 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/resolver.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/__pycache__/resolver.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/resolver.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/resolver.py index 5ddb848..1dd0d70 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/resolver.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/legacy/resolver.py @@ -10,9 +10,6 @@ for sub-dependencies a. "first found, wins" (where the order is breadth first) """ -# The following comment should be removed at some point in the future. -# mypy: strict-optional=False - import logging import sys from collections import defaultdict @@ -52,7 +49,7 @@ from pip._internal.utils.packaging import check_requires_python logger = logging.getLogger(__name__) -DiscoveredDependencies = DefaultDict[str, List[InstallRequirement]] +DiscoveredDependencies = DefaultDict[Optional[str], List[InstallRequirement]] def _check_dist_requires_python( @@ -104,9 +101,8 @@ def _check_dist_requires_python( return raise UnsupportedPythonVersion( - "Package {!r} requires a different Python: {} not in {!r}".format( - dist.raw_name, version, requires_python - ) + f"Package {dist.raw_name!r} requires a different Python: " + f"{version} not in {requires_python!r}" ) @@ -246,9 +242,9 @@ class Resolver(BaseResolver): return [install_req], None try: - existing_req: Optional[ - InstallRequirement - ] = requirement_set.get_requirement(install_req.name) + existing_req: Optional[InstallRequirement] = ( + requirement_set.get_requirement(install_req.name) + ) except KeyError: existing_req = None @@ -263,9 +259,8 @@ class Resolver(BaseResolver): ) if has_conflicting_requirement: raise InstallationError( - "Double requirement given: {} (already in {}, name={!r})".format( - install_req, existing_req, install_req.name - ) + f"Double requirement given: {install_req} " + f"(already in {existing_req}, name={install_req.name!r})" ) # When no existing requirement exists, add the requirement as a @@ -323,6 +318,7 @@ class Resolver(BaseResolver): """ # Don't uninstall the conflict if doing a user install and the # conflict is not a user install. + assert req.satisfied_by is not None if not self.use_user_site or req.satisfied_by.in_usersite: req.should_reinstall = True req.satisfied_by = None @@ -421,6 +417,8 @@ class Resolver(BaseResolver): if self.wheel_cache is None or self.preparer.require_hashes: return + + assert req.link is not None, "_find_requirement_link unexpectedly returned None" cache_entry = self.wheel_cache.get_cache_entry( link=req.link, package_name=req.name, @@ -534,6 +532,7 @@ class Resolver(BaseResolver): with indent_log(): # We add req_to_install before its dependencies, so that we # can refer to it when adding dependencies. + assert req_to_install.name is not None if not requirement_set.has_requirement(req_to_install.name): # 'unnamed' requirements will get added here # 'unnamed' requirements can only come from being directly diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/__init__.cpython-312.pyc index cb03f17..830c0b5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/base.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/base.cpython-312.pyc index 5a1e810..f58c872 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/base.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/base.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/candidates.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/candidates.cpython-312.pyc index 0ffbf83..0325f2f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/candidates.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/candidates.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/factory.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/factory.cpython-312.pyc index 291ff8e..8830c5b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/factory.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/factory.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/found_candidates.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/found_candidates.cpython-312.pyc index c1ec348..9a772c8 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/found_candidates.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/found_candidates.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/provider.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/provider.cpython-312.pyc index 98fe622..4847437 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/provider.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/provider.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/reporter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/reporter.cpython-312.pyc index 0b5b83b..55e3083 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/reporter.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/reporter.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/requirements.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/requirements.cpython-312.pyc index ff3ff98..d9b7591 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/requirements.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/requirements.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/resolver.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/resolver.cpython-312.pyc index 32ca1c1..83a77b5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/resolver.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/__pycache__/resolver.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/base.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/base.py index 9c0ef5c..0f31dc9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/base.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/base.py @@ -1,15 +1,15 @@ -from typing import FrozenSet, Iterable, Optional, Tuple, Union +from dataclasses import dataclass +from typing import FrozenSet, Iterable, Optional, Tuple from pip._vendor.packaging.specifiers import SpecifierSet from pip._vendor.packaging.utils import NormalizedName -from pip._vendor.packaging.version import LegacyVersion, Version +from pip._vendor.packaging.version import Version from pip._internal.models.link import Link, links_equivalent from pip._internal.req.req_install import InstallRequirement from pip._internal.utils.hashes import Hashes CandidateLookup = Tuple[Optional["Candidate"], Optional[InstallRequirement]] -CandidateVersion = Union[LegacyVersion, Version] def format_name(project: NormalizedName, extras: FrozenSet[NormalizedName]) -> str: @@ -19,13 +19,11 @@ def format_name(project: NormalizedName, extras: FrozenSet[NormalizedName]) -> s return f"{project}[{extras_expr}]" +@dataclass(frozen=True) class Constraint: - def __init__( - self, specifier: SpecifierSet, hashes: Hashes, links: FrozenSet[Link] - ) -> None: - self.specifier = specifier - self.hashes = hashes - self.links = links + specifier: SpecifierSet + hashes: Hashes + links: FrozenSet[Link] @classmethod def empty(cls) -> "Constraint": @@ -116,7 +114,7 @@ class Candidate: raise NotImplementedError("Override in subclass") @property - def version(self) -> CandidateVersion: + def version(self) -> Version: raise NotImplementedError("Override in subclass") @property diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/candidates.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/candidates.py index 4125cda..6617644 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/candidates.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/candidates.py @@ -2,13 +2,16 @@ import logging import sys from typing import TYPE_CHECKING, Any, FrozenSet, Iterable, Optional, Tuple, Union, cast +from pip._vendor.packaging.requirements import InvalidRequirement from pip._vendor.packaging.utils import NormalizedName, canonicalize_name from pip._vendor.packaging.version import Version from pip._internal.exceptions import ( HashError, InstallationSubprocessError, + InvalidInstalledPackage, MetadataInconsistent, + MetadataInvalid, ) from pip._internal.metadata import BaseDistribution from pip._internal.models.link import Link, links_equivalent @@ -21,7 +24,7 @@ from pip._internal.req.req_install import InstallRequirement from pip._internal.utils.direct_url_helpers import direct_url_from_link from pip._internal.utils.misc import normalize_version_info -from .base import Candidate, CandidateVersion, Requirement, format_name +from .base import Candidate, Requirement, format_name if TYPE_CHECKING: from .factory import Factory @@ -145,7 +148,7 @@ class _InstallRequirementBackedCandidate(Candidate): ireq: InstallRequirement, factory: "Factory", name: Optional[NormalizedName] = None, - version: Optional[CandidateVersion] = None, + version: Optional[Version] = None, ) -> None: self._link = link self._source_link = source_link @@ -154,6 +157,7 @@ class _InstallRequirementBackedCandidate(Candidate): self._name = name self._version = version self.dist = self._prepare() + self._hash: Optional[int] = None def __str__(self) -> str: return f"{self.name} {self.version}" @@ -162,7 +166,11 @@ class _InstallRequirementBackedCandidate(Candidate): return f"{self.__class__.__name__}({str(self._link)!r})" def __hash__(self) -> int: - return hash((self.__class__, self._link)) + if self._hash is not None: + return self._hash + + self._hash = hash((self.__class__, self._link)) + return self._hash def __eq__(self, other: Any) -> bool: if isinstance(other, self.__class__): @@ -185,16 +193,15 @@ class _InstallRequirementBackedCandidate(Candidate): return self.project_name @property - def version(self) -> CandidateVersion: + def version(self) -> Version: if self._version is None: self._version = self.dist.version return self._version def format_for_error(self) -> str: - return "{} {} (from {})".format( - self.name, - self.version, - self._link.file_path if self._link.is_file else self._link, + return ( + f"{self.name} {self.version} " + f"(from {self._link.file_path if self._link.is_file else self._link})" ) def _prepare_distribution(self) -> BaseDistribution: @@ -216,6 +223,13 @@ class _InstallRequirementBackedCandidate(Candidate): str(self._version), str(dist.version), ) + # check dependencies are valid + # TODO performance: this means we iterate the dependencies at least twice, + # we may want to cache parsed Requires-Dist + try: + list(dist.iter_dependencies(list(dist.iter_provided_extras()))) + except InvalidRequirement as e: + raise MetadataInvalid(self._ireq, str(e)) def _prepare(self) -> BaseDistribution: try: @@ -253,7 +267,7 @@ class LinkCandidate(_InstallRequirementBackedCandidate): template: InstallRequirement, factory: "Factory", name: Optional[NormalizedName] = None, - version: Optional[CandidateVersion] = None, + version: Optional[Version] = None, ) -> None: source_link = link cache_entry = factory.get_wheel_cache_entry(source_link, name) @@ -269,9 +283,9 @@ class LinkCandidate(_InstallRequirementBackedCandidate): # Version may not be present for PEP 508 direct URLs if version is not None: wheel_version = Version(wheel.version) - assert version == wheel_version, "{!r} != {!r} for wheel {}".format( - version, wheel_version, name - ) + assert ( + version == wheel_version + ), f"{version!r} != {wheel_version!r} for wheel {name}" if cache_entry is not None: assert ireq.link.is_wheel @@ -310,7 +324,7 @@ class EditableCandidate(_InstallRequirementBackedCandidate): template: InstallRequirement, factory: "Factory", name: Optional[NormalizedName] = None, - version: Optional[CandidateVersion] = None, + version: Optional[Version] = None, ) -> None: super().__init__( link=link, @@ -353,13 +367,13 @@ class AlreadyInstalledCandidate(Candidate): def __repr__(self) -> str: return f"{self.__class__.__name__}({self.dist!r})" - def __hash__(self) -> int: - return hash((self.__class__, self.name, self.version)) + def __eq__(self, other: object) -> bool: + if not isinstance(other, AlreadyInstalledCandidate): + return NotImplemented + return self.name == other.name and self.version == other.version - def __eq__(self, other: Any) -> bool: - if isinstance(other, self.__class__): - return self.name == other.name and self.version == other.version - return False + def __hash__(self) -> int: + return hash((self.name, self.version)) @property def project_name(self) -> NormalizedName: @@ -370,7 +384,7 @@ class AlreadyInstalledCandidate(Candidate): return self.project_name @property - def version(self) -> CandidateVersion: + def version(self) -> Version: if self._version is None: self._version = self.dist.version return self._version @@ -385,8 +399,12 @@ class AlreadyInstalledCandidate(Candidate): def iter_dependencies(self, with_requires: bool) -> Iterable[Optional[Requirement]]: if not with_requires: return - for r in self.dist.iter_dependencies(): - yield from self._factory.make_requirements_from_spec(str(r), self._ireq) + + try: + for r in self.dist.iter_dependencies(): + yield from self._factory.make_requirements_from_spec(str(r), self._ireq) + except InvalidRequirement as exc: + raise InvalidInstalledPackage(dist=self.dist, invalid_exc=exc) from None def get_install_requirement(self) -> Optional[InstallRequirement]: return None @@ -434,14 +452,6 @@ class ExtrasCandidate(Candidate): """ self.base = base self.extras = frozenset(canonicalize_name(e) for e in extras) - # If any extras are requested in their non-normalized forms, keep track - # of their raw values. This is needed when we look up dependencies - # since PEP 685 has not been implemented for marker-matching, and using - # the non-normalized extra for lookup ensures the user can select a - # non-normalized extra in a package with its non-normalized form. - # TODO: Remove this attribute when packaging is upgraded to support the - # marker comparison logic specified in PEP 685. - self._unnormalized_extras = extras.difference(self.extras) self._comes_from = comes_from if comes_from is not None else self.base._ireq def __str__(self) -> str: @@ -469,7 +479,7 @@ class ExtrasCandidate(Candidate): return format_name(self.base.project_name, self.extras) @property - def version(self) -> CandidateVersion: + def version(self) -> Version: return self.base.version def format_for_error(self) -> str: @@ -489,50 +499,6 @@ class ExtrasCandidate(Candidate): def source_link(self) -> Optional[Link]: return self.base.source_link - def _warn_invalid_extras( - self, - requested: FrozenSet[str], - valid: FrozenSet[str], - ) -> None: - """Emit warnings for invalid extras being requested. - - This emits a warning for each requested extra that is not in the - candidate's ``Provides-Extra`` list. - """ - invalid_extras_to_warn = frozenset( - extra - for extra in requested - if extra not in valid - # If an extra is requested in an unnormalized form, skip warning - # about the normalized form being missing. - and extra in self.extras - ) - if not invalid_extras_to_warn: - return - for extra in sorted(invalid_extras_to_warn): - logger.warning( - "%s %s does not provide the extra '%s'", - self.base.name, - self.version, - extra, - ) - - def _calculate_valid_requested_extras(self) -> FrozenSet[str]: - """Get a list of valid extras requested by this candidate. - - The user (or upstream dependant) may have specified extras that the - candidate doesn't support. Any unsupported extras are dropped, and each - cause a warning to be logged here. - """ - requested_extras = self.extras.union(self._unnormalized_extras) - valid_extras = frozenset( - extra - for extra in requested_extras - if self.base.dist.is_extra_provided(extra) - ) - self._warn_invalid_extras(requested_extras, valid_extras) - return valid_extras - def iter_dependencies(self, with_requires: bool) -> Iterable[Optional[Requirement]]: factory = self.base._factory @@ -542,7 +508,18 @@ class ExtrasCandidate(Candidate): if not with_requires: return - valid_extras = self._calculate_valid_requested_extras() + # The user may have specified extras that the candidate doesn't + # support. We ignore any unsupported extras here. + valid_extras = self.extras.intersection(self.base.dist.iter_provided_extras()) + invalid_extras = self.extras.difference(self.base.dist.iter_provided_extras()) + for extra in sorted(invalid_extras): + logger.warning( + "%s %s does not provide the extra '%s'", + self.base.name, + self.version, + extra, + ) + for r in self.base.dist.iter_dependencies(valid_extras): yield from factory.make_requirements_from_spec( str(r), @@ -584,7 +561,7 @@ class RequiresPythonCandidate(Candidate): return REQUIRES_PYTHON_IDENTIFIER @property - def version(self) -> CandidateVersion: + def version(self) -> Version: return self._version def format_for_error(self) -> str: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/factory.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/factory.py index 4adeb43..6c273eb 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/factory.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/factory.py @@ -3,6 +3,7 @@ import functools import logging from typing import ( TYPE_CHECKING, + Callable, Dict, FrozenSet, Iterable, @@ -11,6 +12,7 @@ from typing import ( Mapping, NamedTuple, Optional, + Protocol, Sequence, Set, Tuple, @@ -21,13 +23,16 @@ from typing import ( from pip._vendor.packaging.requirements import InvalidRequirement from pip._vendor.packaging.specifiers import SpecifierSet from pip._vendor.packaging.utils import NormalizedName, canonicalize_name +from pip._vendor.packaging.version import InvalidVersion, Version from pip._vendor.resolvelib import ResolutionImpossible from pip._internal.cache import CacheEntry, WheelCache from pip._internal.exceptions import ( DistributionNotFound, InstallationError, + InvalidInstalledPackage, MetadataInconsistent, + MetadataInvalid, UnsupportedPythonVersion, UnsupportedWheel, ) @@ -50,7 +55,7 @@ from pip._internal.utils.hashes import Hashes from pip._internal.utils.packaging import get_requirement from pip._internal.utils.virtualenv import running_under_virtualenv -from .base import Candidate, CandidateVersion, Constraint, Requirement +from .base import Candidate, Constraint, Requirement from .candidates import ( AlreadyInstalledCandidate, BaseCandidate, @@ -70,7 +75,6 @@ from .requirements import ( ) if TYPE_CHECKING: - from typing import Protocol class ConflictCause(Protocol): requirement: RequiresPythonRequirement @@ -118,6 +122,7 @@ class Factory: self._extras_candidate_cache: Dict[ Tuple[int, FrozenSet[NormalizedName]], ExtrasCandidate ] = {} + self._supported_tags_cache = get_supported() if not ignore_installed: env = get_default_environment() @@ -177,7 +182,7 @@ class Factory: extras: FrozenSet[str], template: InstallRequirement, name: Optional[NormalizedName], - version: Optional[CandidateVersion], + version: Optional[Version], ) -> Optional[Candidate]: base: Optional[BaseCandidate] = self._make_base_candidate_from_link( link, template, name, version @@ -191,7 +196,7 @@ class Factory: link: Link, template: InstallRequirement, name: Optional[NormalizedName], - version: Optional[CandidateVersion], + version: Optional[Version], ) -> Optional[BaseCandidate]: # TODO: Check already installed candidate, and use it if the link and # editable flag match. @@ -211,7 +216,7 @@ class Factory: name=name, version=version, ) - except MetadataInconsistent as e: + except (MetadataInconsistent, MetadataInvalid) as e: logger.info( "Discarding [blue underline]%s[/]: [yellow]%s[reset]", link, @@ -279,10 +284,15 @@ class Factory: installed_dist = self._installed_dists[name] except KeyError: return None - # Don't use the installed distribution if its version does not fit - # the current dependency graph. - if not specifier.contains(installed_dist.version, prereleases=True): - return None + + try: + # Don't use the installed distribution if its version + # does not fit the current dependency graph. + if not specifier.contains(installed_dist.version, prereleases=True): + return None + except InvalidVersion as e: + raise InvalidInstalledPackage(dist=installed_dist, invalid_exc=e) + candidate = self._make_candidate_from_dist( dist=installed_dist, extras=extras, @@ -299,7 +309,7 @@ class Factory: specifier=specifier, hashes=hashes, ) - icans = list(result.iter_applicable()) + icans = result.applicable_candidates # PEP 592: Yanked releases are ignored unless the specifier # explicitly pins a version (via '==' or '===') that can be @@ -391,6 +401,7 @@ class Factory: incompatibilities: Mapping[str, Iterator[Candidate]], constraint: Constraint, prefers_installed: bool, + is_satisfied_by: Callable[[Requirement, Candidate], bool], ) -> Iterable[Candidate]: # Collect basic lookup information from the requirements. explicit_candidates: Set[Candidate] = set() @@ -456,7 +467,7 @@ class Factory: for c in explicit_candidates if id(c) not in incompat_ids and constraint.is_satisfied_by(c) - and all(req.is_satisfied_by(c) for req in requirements[identifier]) + and all(is_satisfied_by(req, c) for req in requirements[identifier]) ) def _make_requirements_from_install_req( @@ -604,7 +615,7 @@ class Factory: return self._wheel_cache.get_cache_entry( link=link, package_name=name, - supported_tags=get_supported(), + supported_tags=self._supported_tags_cache, ) def get_dist_to_uninstall(self, candidate: Candidate) -> Optional[BaseDistribution]: @@ -668,8 +679,8 @@ class Factory: cands = self._finder.find_all_candidates(req.project_name) skipped_by_requires_python = self._finder.requires_python_skipped_reasons() - versions_set: Set[CandidateVersion] = set() - yanked_versions_set: Set[CandidateVersion] = set() + versions_set: Set[Version] = set() + yanked_versions_set: Set[Version] = set() for c in cands: is_yanked = c.link.is_yanked if c.link else False if is_yanked: @@ -799,7 +810,7 @@ class Factory: + "\n\n" + "To fix this you could try to:\n" + "1. loosen the range of package versions you've specified\n" - + "2. remove package versions to allow pip attempt to solve " + + "2. remove package versions to allow pip to attempt to solve " + "the dependency conflict\n" ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/found_candidates.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/found_candidates.py index 8663097..a1d57e0 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/found_candidates.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/found_candidates.py @@ -9,13 +9,18 @@ something. """ import functools +import logging from collections.abc import Sequence from typing import TYPE_CHECKING, Any, Callable, Iterator, Optional, Set, Tuple from pip._vendor.packaging.version import _BaseVersion +from pip._internal.exceptions import MetadataInvalid + from .base import Candidate +logger = logging.getLogger(__name__) + IndexCandidateInfo = Tuple[_BaseVersion, Callable[[], Optional[Candidate]]] if TYPE_CHECKING: @@ -44,11 +49,25 @@ def _iter_built(infos: Iterator[IndexCandidateInfo]) -> Iterator[Candidate]: for version, func in infos: if version in versions_found: continue - candidate = func() - if candidate is None: - continue - yield candidate - versions_found.add(version) + try: + candidate = func() + except MetadataInvalid as e: + logger.warning( + "Ignoring version %s of %s since it has invalid metadata:\n" + "%s\n" + "Please use pip<24.1 if you need to use this version.", + version, + e.ireq.name, + e, + ) + # Mark version as found to avoid trying other candidates with the same + # version, since they most likely have invalid metadata as well. + versions_found.add(version) + else: + if candidate is None: + continue + yield candidate + versions_found.add(version) def _iter_built_with_prepended( diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/provider.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/provider.py index 315fb9c..fb0dd85 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/provider.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/provider.py @@ -1,5 +1,6 @@ import collections import math +from functools import lru_cache from typing import ( TYPE_CHECKING, Dict, @@ -234,8 +235,10 @@ class PipProvider(_ProviderBase): constraint=constraint, prefers_installed=(not _eligible_for_upgrade(identifier)), incompatibilities=incompatibilities, + is_satisfied_by=self.is_satisfied_by, ) + @lru_cache(maxsize=None) def is_satisfied_by(self, requirement: Requirement, candidate: Candidate) -> bool: return requirement.is_satisfied_by(candidate) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/reporter.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/reporter.py index 12adeff..0594569 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/reporter.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/reporter.py @@ -66,6 +66,7 @@ class PipDebuggingReporter(BaseReporter): def ending_round(self, index: int, state: Any) -> None: logger.info("Reporter.ending_round(%r, state)", index) + logger.debug("Reporter.ending_round(%r, %r)", index, state) def ending(self, state: Any) -> None: logger.info("Reporter.ending(%r)", state) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/requirements.py b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/requirements.py index 4af4a9f..b04f41b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/requirements.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/resolution/resolvelib/requirements.py @@ -1,3 +1,5 @@ +from typing import Any, Optional + from pip._vendor.packaging.specifiers import SpecifierSet from pip._vendor.packaging.utils import NormalizedName, canonicalize_name @@ -17,6 +19,14 @@ class ExplicitRequirement(Requirement): def __repr__(self) -> str: return f"{self.__class__.__name__}({self.candidate!r})" + def __hash__(self) -> int: + return hash(self.candidate) + + def __eq__(self, other: Any) -> bool: + if not isinstance(other, ExplicitRequirement): + return False + return self.candidate == other.candidate + @property def project_name(self) -> NormalizedName: # No need to canonicalize - the candidate did this @@ -41,14 +51,36 @@ class SpecifierRequirement(Requirement): def __init__(self, ireq: InstallRequirement) -> None: assert ireq.link is None, "This is a link, not a specifier" self._ireq = ireq + self._equal_cache: Optional[str] = None + self._hash: Optional[int] = None self._extras = frozenset(canonicalize_name(e) for e in self._ireq.extras) + @property + def _equal(self) -> str: + if self._equal_cache is not None: + return self._equal_cache + + self._equal_cache = str(self._ireq) + return self._equal_cache + def __str__(self) -> str: return str(self._ireq.req) def __repr__(self) -> str: return f"{self.__class__.__name__}({str(self._ireq.req)!r})" + def __eq__(self, other: object) -> bool: + if not isinstance(other, SpecifierRequirement): + return NotImplemented + return self._equal == other._equal + + def __hash__(self) -> int: + if self._hash is not None: + return self._hash + + self._hash = hash(self._equal) + return self._hash + @property def project_name(self) -> NormalizedName: assert self._ireq.req, "Specifier-backed ireq is always PEP 508" @@ -96,14 +128,38 @@ class SpecifierWithoutExtrasRequirement(SpecifierRequirement): def __init__(self, ireq: InstallRequirement) -> None: assert ireq.link is None, "This is a link, not a specifier" self._ireq = install_req_drop_extras(ireq) + self._equal_cache: Optional[str] = None + self._hash: Optional[int] = None self._extras = frozenset(canonicalize_name(e) for e in self._ireq.extras) + @property + def _equal(self) -> str: + if self._equal_cache is not None: + return self._equal_cache + + self._equal_cache = str(self._ireq) + return self._equal_cache + + def __eq__(self, other: object) -> bool: + if not isinstance(other, SpecifierWithoutExtrasRequirement): + return NotImplemented + return self._equal == other._equal + + def __hash__(self) -> int: + if self._hash is not None: + return self._hash + + self._hash = hash(self._equal) + return self._hash + class RequiresPythonRequirement(Requirement): """A requirement representing Requires-Python metadata.""" def __init__(self, specifier: SpecifierSet, match: Candidate) -> None: self.specifier = specifier + self._specifier_string = str(specifier) # for faster __eq__ + self._hash: Optional[int] = None self._candidate = match def __str__(self) -> str: @@ -112,6 +168,21 @@ class RequiresPythonRequirement(Requirement): def __repr__(self) -> str: return f"{self.__class__.__name__}({str(self.specifier)!r})" + def __hash__(self) -> int: + if self._hash is not None: + return self._hash + + self._hash = hash((self._specifier_string, self._candidate)) + return self._hash + + def __eq__(self, other: Any) -> bool: + if not isinstance(other, RequiresPythonRequirement): + return False + return ( + self._specifier_string == other._specifier_string + and self._candidate == other._candidate + ) + @property def project_name(self) -> NormalizedName: return self._candidate.project_name @@ -148,6 +219,14 @@ class UnsatisfiableRequirement(Requirement): def __repr__(self) -> str: return f"{self.__class__.__name__}({str(self._name)!r})" + def __eq__(self, other: object) -> bool: + if not isinstance(other, UnsatisfiableRequirement): + return NotImplemented + return self._name == other._name + + def __hash__(self) -> int: + return hash(self._name) + @property def project_name(self) -> NormalizedName: return self._name diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/self_outdated_check.py b/llmlab/lib/python3.12/site-packages/pip/_internal/self_outdated_check.py index 0f64ae0..2e0e3df 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/self_outdated_check.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/self_outdated_check.py @@ -9,6 +9,7 @@ import sys from dataclasses import dataclass from typing import Any, Callable, Dict, Optional +from pip._vendor.packaging.version import Version from pip._vendor.packaging.version import parse as parse_version from pip._vendor.rich.console import Group from pip._vendor.rich.markup import escape @@ -17,7 +18,6 @@ from pip._vendor.rich.text import Text from pip._internal.index.collector import LinkCollector from pip._internal.index.package_finder import PackageFinder from pip._internal.metadata import get_default_environment -from pip._internal.metadata.base import DistributionVersion from pip._internal.models.selection_prefs import SelectionPreferences from pip._internal.network.session import PipSession from pip._internal.utils.compat import WINDOWS @@ -26,7 +26,11 @@ from pip._internal.utils.entrypoints import ( get_best_invocation_for_this_python, ) from pip._internal.utils.filesystem import adjacent_tmp_file, check_path_owner, replace -from pip._internal.utils.misc import ensure_dir +from pip._internal.utils.misc import ( + ExternallyManagedEnvironment, + check_externally_managed, + ensure_dir, +) _WEEK = datetime.timedelta(days=7) @@ -191,7 +195,7 @@ def _self_version_check_logic( *, state: SelfCheckState, current_time: datetime.datetime, - local_version: DistributionVersion, + local_version: Version, get_remote_version: Callable[[], Optional[str]], ) -> Optional[UpgradePrompt]: remote_version_str = state.get(current_time) @@ -231,18 +235,18 @@ def pip_self_version_check(session: PipSession, options: optparse.Values) -> Non installed_dist = get_default_environment().get_distribution("pip") if not installed_dist: return - try: - upgrade_prompt = _self_version_check_logic( - state=SelfCheckState(cache_dir=options.cache_dir), - current_time=datetime.datetime.now(datetime.timezone.utc), - local_version=installed_dist.version, - get_remote_version=functools.partial( - _get_current_remote_pip_version, session, options - ), - ) - if upgrade_prompt is not None: - logger.warning("%s", upgrade_prompt, extra={"rich": True}) - except Exception: - logger.warning("There was an error checking the latest version of pip.") - logger.debug("See below for error", exc_info=True) + check_externally_managed() + except ExternallyManagedEnvironment: + return + + upgrade_prompt = _self_version_check_logic( + state=SelfCheckState(cache_dir=options.cache_dir), + current_time=datetime.datetime.now(datetime.timezone.utc), + local_version=installed_dist.version, + get_remote_version=functools.partial( + _get_current_remote_pip_version, session, options + ), + ) + if upgrade_prompt is not None: + logger.warning("%s", upgrade_prompt, extra={"rich": True}) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/__init__.cpython-312.pyc index a78919c..f085116 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_jaraco_text.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_jaraco_text.cpython-312.pyc index 52afc27..35ca594 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_jaraco_text.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_jaraco_text.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_log.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_log.cpython-312.pyc index 28d55d3..e21a746 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_log.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/_log.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/appdirs.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/appdirs.cpython-312.pyc index caf17a0..f5c6fba 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/appdirs.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/appdirs.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compat.cpython-312.pyc index 1b42243..36da175 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compat.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compat.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compatibility_tags.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compatibility_tags.cpython-312.pyc index b8883a1..295d884 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compatibility_tags.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/compatibility_tags.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/datetime.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/datetime.cpython-312.pyc index b112a9e..c38142a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/datetime.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/datetime.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/deprecation.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/deprecation.cpython-312.pyc index e159c57..9e3e615 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/deprecation.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/deprecation.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/direct_url_helpers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/direct_url_helpers.cpython-312.pyc index 5dfdd28..48c4d11 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/direct_url_helpers.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/direct_url_helpers.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/egg_link.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/egg_link.cpython-312.pyc index bb1ba5f..782061a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/egg_link.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/egg_link.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/encoding.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/encoding.cpython-312.pyc deleted file mode 100644 index 31fbaaa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/encoding.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/entrypoints.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/entrypoints.cpython-312.pyc index 88c79bb..76f4d4a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/entrypoints.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/entrypoints.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filesystem.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filesystem.cpython-312.pyc index 745662c..5d3a9bd 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filesystem.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filesystem.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filetypes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filetypes.cpython-312.pyc index 5159f66..af3ece1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filetypes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/filetypes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/glibc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/glibc.cpython-312.pyc index 0c812d0..ee1a886 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/glibc.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/glibc.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/hashes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/hashes.cpython-312.pyc index 93dc8f4..c929635 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/hashes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/hashes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/logging.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/logging.cpython-312.pyc index b683860..d4c3168 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/logging.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/logging.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/misc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/misc.cpython-312.pyc index 32e7a50..dbe226b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/misc.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/misc.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/models.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/models.cpython-312.pyc deleted file mode 100644 index c649848..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/models.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/packaging.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/packaging.cpython-312.pyc index e00f80d..e5d5ad4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/packaging.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/packaging.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/retry.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/retry.cpython-312.pyc new file mode 100644 index 0000000..a35ccdd Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/retry.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/setuptools_build.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/setuptools_build.cpython-312.pyc index 6dfe25d..1c266be 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/setuptools_build.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/setuptools_build.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/subprocess.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/subprocess.cpython-312.pyc index 137ed23..83dfb89 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/subprocess.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/subprocess.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/temp_dir.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/temp_dir.cpython-312.pyc index 3f87fee..10082f7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/temp_dir.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/temp_dir.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/unpacking.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/unpacking.cpython-312.pyc index 215413a..4c081e1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/unpacking.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/unpacking.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/urls.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/urls.cpython-312.pyc index 8c57dcf..94cb693 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/urls.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/urls.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/virtualenv.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/virtualenv.cpython-312.pyc index ea338ed..737d816 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/virtualenv.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/virtualenv.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/wheel.cpython-312.pyc index b93039a..86d9b0d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/__pycache__/wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/_jaraco_text.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/_jaraco_text.py index e06947c..6ccf53b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/_jaraco_text.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/_jaraco_text.py @@ -88,7 +88,7 @@ def join_continuation(lines): ['foobarbaz'] Not sure why, but... - The character preceeding the backslash is also elided. + The character preceding the backslash is also elided. >>> list(join_continuation(['goo\\', 'dly'])) ['godly'] diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compat.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compat.py index 3f4d300..d8b54e4 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compat.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compat.py @@ -1,9 +1,11 @@ """Stuff that differs in different Python versions and platform distributions.""" +import importlib.resources import logging import os import sys +from typing import IO __all__ = ["get_path_uid", "stdlib_pkgs", "WINDOWS"] @@ -51,6 +53,20 @@ def get_path_uid(path: str) -> int: return file_uid +# The importlib.resources.open_text function was deprecated in 3.11 with suggested +# replacement we use below. +if sys.version_info < (3, 11): + open_text_resource = importlib.resources.open_text +else: + + def open_text_resource( + package: str, resource: str, encoding: str = "utf-8", errors: str = "strict" + ) -> IO[str]: + return (importlib.resources.files(package) / resource).open( + "r", encoding=encoding, errors=errors + ) + + # packages in the stdlib that may have installation metadata, but should not be # considered 'installed'. this theoretically could be determined based on # dist.location (py27:`sysconfig.get_paths()['stdlib']`, diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compatibility_tags.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compatibility_tags.py index b6ed9a7..2e7b745 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compatibility_tags.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/compatibility_tags.py @@ -12,10 +12,11 @@ from pip._vendor.packaging.tags import ( generic_tags, interpreter_name, interpreter_version, + ios_platforms, mac_platforms, ) -_osx_arch_pat = re.compile(r"(.+)_(\d+)_(\d+)_(.+)") +_apple_arch_pat = re.compile(r"(.+)_(\d+)_(\d+)_(.+)") def version_info_to_nodot(version_info: Tuple[int, ...]) -> str: @@ -24,7 +25,7 @@ def version_info_to_nodot(version_info: Tuple[int, ...]) -> str: def _mac_platforms(arch: str) -> List[str]: - match = _osx_arch_pat.match(arch) + match = _apple_arch_pat.match(arch) if match: name, major, minor, actual_arch = match.groups() mac_version = (int(major), int(minor)) @@ -43,6 +44,26 @@ def _mac_platforms(arch: str) -> List[str]: return arches +def _ios_platforms(arch: str) -> List[str]: + match = _apple_arch_pat.match(arch) + if match: + name, major, minor, actual_multiarch = match.groups() + ios_version = (int(major), int(minor)) + arches = [ + # Since we have always only checked that the platform starts + # with "ios", for backwards-compatibility we extract the + # actual prefix provided by the user in case they provided + # something like "ioscustom_". It may be good to remove + # this as undocumented or deprecate it in the future. + "{}_{}".format(name, arch[len("ios_") :]) + for arch in ios_platforms(ios_version, actual_multiarch) + ] + else: + # arch pattern didn't match (?!) + arches = [arch] + return arches + + def _custom_manylinux_platforms(arch: str) -> List[str]: arches = [arch] arch_prefix, arch_sep, arch_suffix = arch.partition("_") @@ -68,6 +89,8 @@ def _get_custom_platforms(arch: str) -> List[str]: arch_prefix, arch_sep, arch_suffix = arch.partition("_") if arch.startswith("macosx"): arches = _mac_platforms(arch) + elif arch.startswith("ios"): + arches = _ios_platforms(arch) elif arch_prefix in ["manylinux2014", "manylinux2010"]: arches = _custom_manylinux_platforms(arch) else: diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/deprecation.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/deprecation.py index 72bd6f2..0911147 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/deprecation.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/deprecation.py @@ -87,9 +87,11 @@ def deprecated( (reason, f"{DEPRECATION_MSG_PREFIX}{{}}"), ( gone_in, - "pip {} will enforce this behaviour change." - if not is_gone - else "Since pip {}, this is no longer supported.", + ( + "pip {} will enforce this behaviour change." + if not is_gone + else "Since pip {}, this is no longer supported." + ), ), ( replacement, @@ -97,9 +99,11 @@ def deprecated( ), ( feature_flag, - "You can use the flag --use-feature={} to test the upcoming behaviour." - if not is_gone - else None, + ( + "You can use the flag --use-feature={} to test the upcoming behaviour." + if not is_gone + else None + ), ), ( issue, diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/direct_url_helpers.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/direct_url_helpers.py index 0e8e5e1..66020d3 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/direct_url_helpers.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/direct_url_helpers.py @@ -12,8 +12,8 @@ def direct_url_as_pep440_direct_reference(direct_url: DirectUrl, name: str) -> s requirement = name + " @ " fragments = [] if isinstance(direct_url.info, VcsInfo): - requirement += "{}+{}@{}".format( - direct_url.info.vcs, direct_url.url, direct_url.info.commit_id + requirement += ( + f"{direct_url.info.vcs}+{direct_url.url}@{direct_url.info.commit_id}" ) elif isinstance(direct_url.info, ArchiveInfo): requirement += direct_url.url diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/encoding.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/encoding.py deleted file mode 100644 index 008f06a..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/encoding.py +++ /dev/null @@ -1,36 +0,0 @@ -import codecs -import locale -import re -import sys -from typing import List, Tuple - -BOMS: List[Tuple[bytes, str]] = [ - (codecs.BOM_UTF8, "utf-8"), - (codecs.BOM_UTF16, "utf-16"), - (codecs.BOM_UTF16_BE, "utf-16-be"), - (codecs.BOM_UTF16_LE, "utf-16-le"), - (codecs.BOM_UTF32, "utf-32"), - (codecs.BOM_UTF32_BE, "utf-32-be"), - (codecs.BOM_UTF32_LE, "utf-32-le"), -] - -ENCODING_RE = re.compile(rb"coding[:=]\s*([-\w.]+)") - - -def auto_decode(data: bytes) -> str: - """Check a bytes string for a BOM to correctly detect the encoding - - Fallback to locale.getpreferredencoding(False) like open() on Python3""" - for bom, encoding in BOMS: - if data.startswith(bom): - return data[len(bom) :].decode(encoding) - # Lets check the first two lines as in PEP263 - for line in data.split(b"\n")[:2]: - if line[0:1] == b"#" and ENCODING_RE.search(line): - result = ENCODING_RE.search(line) - assert result is not None - encoding = result.groups()[0].decode("ascii") - return data.decode(encoding) - return data.decode( - locale.getpreferredencoding(False) or sys.getdefaultencoding(), - ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/filesystem.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/filesystem.py index 83c2df7..22e356c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/filesystem.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/filesystem.py @@ -7,10 +7,9 @@ from contextlib import contextmanager from tempfile import NamedTemporaryFile from typing import Any, BinaryIO, Generator, List, Union, cast -from pip._vendor.tenacity import retry, stop_after_delay, wait_fixed - from pip._internal.utils.compat import get_path_uid from pip._internal.utils.misc import format_size +from pip._internal.utils.retry import retry def check_path_owner(path: str) -> bool: @@ -65,10 +64,7 @@ def adjacent_tmp_file(path: str, **kwargs: Any) -> Generator[BinaryIO, None, Non os.fsync(result.fileno()) -# Tenacity raises RetryError by default, explicitly raise the original exception -_replace_retry = retry(reraise=True, stop=stop_after_delay(1), wait=wait_fixed(0.25)) - -replace = _replace_retry(os.replace) +replace = retry(stop_after_delay=1, wait=0.25)(os.replace) # test_writable_dir and _test_writable_dir_win are copied from Flit, diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/glibc.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/glibc.py index 81342af..998868f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/glibc.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/glibc.py @@ -40,7 +40,20 @@ def glibc_version_string_ctypes() -> Optional[str]: # manpage says, "If filename is NULL, then the returned handle is for the # main program". This way we can let the linker do the work to figure out # which libc our process is actually using. - process_namespace = ctypes.CDLL(None) + # + # We must also handle the special case where the executable is not a + # dynamically linked executable. This can occur when using musl libc, + # for example. In this situation, dlopen() will error, leading to an + # OSError. Interestingly, at least in the case of musl, there is no + # errno set on the OSError. The single string argument used to construct + # OSError comes from libc itself and is therefore not portable to + # hard code here. In any case, failure to call dlopen() means we + # can't proceed, so we bail on our attempt. + try: + process_namespace = ctypes.CDLL(None) + except OSError: + return None + try: gnu_get_libc_version = process_namespace.gnu_get_libc_version except AttributeError: @@ -50,7 +63,7 @@ def glibc_version_string_ctypes() -> Optional[str]: # Call gnu_get_libc_version, which returns a string like "2.5" gnu_get_libc_version.restype = ctypes.c_char_p - version_str = gnu_get_libc_version() + version_str: str = gnu_get_libc_version() # py2 / py3 compatibility: if not isinstance(version_str, str): version_str = version_str.decode("ascii") diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/hashes.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/hashes.py index 843cffc..535e94f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/hashes.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/hashes.py @@ -1,5 +1,5 @@ import hashlib -from typing import TYPE_CHECKING, BinaryIO, Dict, Iterable, List, Optional +from typing import TYPE_CHECKING, BinaryIO, Dict, Iterable, List, NoReturn, Optional from pip._internal.exceptions import HashMismatch, HashMissing, InstallationError from pip._internal.utils.misc import read_chunks @@ -7,10 +7,6 @@ from pip._internal.utils.misc import read_chunks if TYPE_CHECKING: from hashlib import _Hash - # NoReturn introduced in 3.6.2; imported only for type checking to maintain - # pip compatibility with older patch versions of Python 3.6 - from typing import NoReturn - # The recommended hash algo of the moment. Change this whenever the state of # the art changes; it won't hurt backward compatibility. @@ -37,7 +33,7 @@ class Hashes: if hashes is not None: for alg, keys in hashes.items(): # Make sure values are always sorted (to ease equality checks) - allowed[alg] = sorted(keys) + allowed[alg] = [k.lower() for k in sorted(keys)] self._allowed = allowed def __and__(self, other: "Hashes") -> "Hashes": diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/logging.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/logging.py index 95982df..62035fc 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/logging.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/logging.py @@ -137,12 +137,19 @@ class IndentedRenderable: yield Segment("\n") +class PipConsole(Console): + def on_broken_pipe(self) -> None: + # Reraise the original exception, rich 13.8.0+ exits by default + # instead, preventing our handler from firing. + raise BrokenPipeError() from None + + class RichPipStreamHandler(RichHandler): KEYWORDS: ClassVar[Optional[List[str]]] = [] def __init__(self, stream: Optional[TextIO], no_color: bool) -> None: super().__init__( - console=Console(file=stream, no_color=no_color, soft_wrap=True), + console=PipConsole(file=stream, no_color=no_color, soft_wrap=True), show_time=False, show_level=False, show_path=False, @@ -154,8 +161,8 @@ class RichPipStreamHandler(RichHandler): style: Optional[Style] = None # If we are given a diagnostic error to present, present it with indentation. - assert isinstance(record.args, tuple) if getattr(record, "rich", False): + assert isinstance(record.args, tuple) (rich_renderable,) = record.args assert isinstance( rich_renderable, (ConsoleRenderable, RichCast, str) @@ -212,7 +219,6 @@ class MaxLevelFilter(Filter): class ExcludeLoggerFilter(Filter): - """ A logging Filter that excludes records from a logger (or its children). """ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/misc.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/misc.py index 1ad3f61..44f6a05 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/misc.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/misc.py @@ -1,8 +1,6 @@ -import contextlib import errno import getpass import hashlib -import io import logging import os import posixpath @@ -11,6 +9,7 @@ import stat import sys import sysconfig import urllib.parse +from dataclasses import dataclass from functools import partial from io import StringIO from itertools import filterfalse, tee, zip_longest @@ -20,13 +19,13 @@ from typing import ( Any, BinaryIO, Callable, - ContextManager, - Dict, Generator, Iterable, Iterator, List, + Mapping, Optional, + Sequence, TextIO, Tuple, Type, @@ -37,12 +36,12 @@ from typing import ( from pip._vendor.packaging.requirements import Requirement from pip._vendor.pyproject_hooks import BuildBackendHookCaller -from pip._vendor.tenacity import retry, stop_after_delay, wait_fixed from pip import __version__ from pip._internal.exceptions import CommandError, ExternallyManagedEnvironment from pip._internal.locations import get_major_minor_version from pip._internal.utils.compat import WINDOWS +from pip._internal.utils.retry import retry from pip._internal.utils.virtualenv import running_under_virtualenv __all__ = [ @@ -56,7 +55,6 @@ __all__ = [ "normalize_path", "renames", "get_prog", - "captured_stdout", "ensure_dir", "remove_auth_from_url", "check_externally_managed", @@ -72,6 +70,8 @@ NetlocTuple = Tuple[str, Tuple[Optional[str], Optional[str]]] OnExc = Callable[[FunctionType, Path, BaseException], Any] OnErr = Callable[[FunctionType, Path, ExcInfo], Any] +FILE_CHUNK_SIZE = 1024 * 1024 + def get_pip_version() -> str: pip_pkg_dir = os.path.join(os.path.dirname(__file__), "..", "..") @@ -122,23 +122,15 @@ def get_prog() -> str: # Retry every half second for up to 3 seconds -# Tenacity raises RetryError by default, explicitly raise the original exception -@retry(reraise=True, stop=stop_after_delay(3), wait=wait_fixed(0.5)) +@retry(stop_after_delay=3, wait=0.5) def rmtree( - dir: str, - ignore_errors: bool = False, - onexc: Optional[OnExc] = None, + dir: str, ignore_errors: bool = False, onexc: Optional[OnExc] = None ) -> None: if ignore_errors: onexc = _onerror_ignore if onexc is None: onexc = _onerror_reraise - handler: OnErr = partial( - # `[func, path, Union[ExcInfo, BaseException]] -> Any` is equivalent to - # `Union[([func, path, ExcInfo] -> Any), ([func, path, BaseException] -> Any)]`. - cast(Union[OnExc, OnErr], rmtree_errorhandler), - onexc=onexc, - ) + handler: OnErr = partial(rmtree_errorhandler, onexc=onexc) if sys.version_info >= (3, 12): # See https://docs.python.org/3.12/whatsnew/3.12.html#shutil. shutil.rmtree(dir, onexc=handler) # type: ignore @@ -151,7 +143,7 @@ def _onerror_ignore(*_args: Any) -> None: def _onerror_reraise(*_args: Any) -> None: - raise + raise # noqa: PLE0704 - Bare exception used to reraise existing exception def rmtree_errorhandler( @@ -316,7 +308,7 @@ def is_installable_dir(path: str) -> bool: def read_chunks( - file: BinaryIO, size: int = io.DEFAULT_BUFFER_SIZE + file: BinaryIO, size: int = FILE_CHUNK_SIZE ) -> Generator[bytes, None, None]: """Yield pieces of data from a file-like object until EOF.""" while True: @@ -399,40 +391,6 @@ class StreamWrapper(StringIO): return self.orig_stream.encoding -@contextlib.contextmanager -def captured_output(stream_name: str) -> Generator[StreamWrapper, None, None]: - """Return a context manager used by captured_stdout/stdin/stderr - that temporarily replaces the sys stream *stream_name* with a StringIO. - - Taken from Lib/support/__init__.py in the CPython repo. - """ - orig_stdout = getattr(sys, stream_name) - setattr(sys, stream_name, StreamWrapper.from_stream(orig_stdout)) - try: - yield getattr(sys, stream_name) - finally: - setattr(sys, stream_name, orig_stdout) - - -def captured_stdout() -> ContextManager[StreamWrapper]: - """Capture the output of sys.stdout: - - with captured_stdout() as stdout: - print('hello') - self.assertEqual(stdout.getvalue(), 'hello\n') - - Taken from Lib/support/__init__.py in the CPython repo. - """ - return captured_output("stdout") - - -def captured_stderr() -> ContextManager[StreamWrapper]: - """ - See captured_stdout(). - """ - return captured_output("stderr") - - # Simulates an enum def enum(*sequential: Any, **named: Any) -> Type[Any]: enums = dict(zip(sequential, range(len(sequential))), **named) @@ -580,10 +538,10 @@ def redact_auth_from_requirement(req: Requirement) -> str: return str(req).replace(req.url, redact_auth_from_url(req.url)) +@dataclass(frozen=True) class HiddenText: - def __init__(self, secret: str, redacted: str) -> None: - self.secret = secret - self.redacted = redacted + secret: str + redacted: str def __repr__(self) -> str: return f"" @@ -593,7 +551,7 @@ class HiddenText: # This is useful for testing. def __eq__(self, other: Any) -> bool: - if type(self) != type(other): + if type(self) is not type(other): return False # The string being used for redaction doesn't also have to match, @@ -680,8 +638,7 @@ def pairwise(iterable: Iterable[Any]) -> Iterator[Tuple[Any, Any]]: def partition( - pred: Callable[[T], bool], - iterable: Iterable[T], + pred: Callable[[T], bool], iterable: Iterable[T] ) -> Tuple[Iterable[T], Iterable[T]]: """ Use a predicate to partition entries into false entries and true entries, @@ -711,7 +668,7 @@ class ConfiguredBuildBackendHookCaller(BuildBackendHookCaller): def build_wheel( self, wheel_directory: str, - config_settings: Optional[Dict[str, Union[str, List[str]]]] = None, + config_settings: Optional[Mapping[str, Any]] = None, metadata_directory: Optional[str] = None, ) -> str: cs = self.config_holder.config_settings @@ -722,7 +679,7 @@ class ConfiguredBuildBackendHookCaller(BuildBackendHookCaller): def build_sdist( self, sdist_directory: str, - config_settings: Optional[Dict[str, Union[str, List[str]]]] = None, + config_settings: Optional[Mapping[str, Any]] = None, ) -> str: cs = self.config_holder.config_settings return super().build_sdist(sdist_directory, config_settings=cs) @@ -730,7 +687,7 @@ class ConfiguredBuildBackendHookCaller(BuildBackendHookCaller): def build_editable( self, wheel_directory: str, - config_settings: Optional[Dict[str, Union[str, List[str]]]] = None, + config_settings: Optional[Mapping[str, Any]] = None, metadata_directory: Optional[str] = None, ) -> str: cs = self.config_holder.config_settings @@ -739,27 +696,27 @@ class ConfiguredBuildBackendHookCaller(BuildBackendHookCaller): ) def get_requires_for_build_wheel( - self, config_settings: Optional[Dict[str, Union[str, List[str]]]] = None - ) -> List[str]: + self, config_settings: Optional[Mapping[str, Any]] = None + ) -> Sequence[str]: cs = self.config_holder.config_settings return super().get_requires_for_build_wheel(config_settings=cs) def get_requires_for_build_sdist( - self, config_settings: Optional[Dict[str, Union[str, List[str]]]] = None - ) -> List[str]: + self, config_settings: Optional[Mapping[str, Any]] = None + ) -> Sequence[str]: cs = self.config_holder.config_settings return super().get_requires_for_build_sdist(config_settings=cs) def get_requires_for_build_editable( - self, config_settings: Optional[Dict[str, Union[str, List[str]]]] = None - ) -> List[str]: + self, config_settings: Optional[Mapping[str, Any]] = None + ) -> Sequence[str]: cs = self.config_holder.config_settings return super().get_requires_for_build_editable(config_settings=cs) def prepare_metadata_for_build_wheel( self, metadata_directory: str, - config_settings: Optional[Dict[str, Union[str, List[str]]]] = None, + config_settings: Optional[Mapping[str, Any]] = None, _allow_fallback: bool = True, ) -> str: cs = self.config_holder.config_settings @@ -772,12 +729,45 @@ class ConfiguredBuildBackendHookCaller(BuildBackendHookCaller): def prepare_metadata_for_build_editable( self, metadata_directory: str, - config_settings: Optional[Dict[str, Union[str, List[str]]]] = None, + config_settings: Optional[Mapping[str, Any]] = None, _allow_fallback: bool = True, - ) -> str: + ) -> Optional[str]: cs = self.config_holder.config_settings return super().prepare_metadata_for_build_editable( metadata_directory=metadata_directory, config_settings=cs, _allow_fallback=_allow_fallback, ) + + +def warn_if_run_as_root() -> None: + """Output a warning for sudo users on Unix. + + In a virtual environment, sudo pip still writes to virtualenv. + On Windows, users may run pip as Administrator without issues. + This warning only applies to Unix root users outside of virtualenv. + """ + if running_under_virtualenv(): + return + if not hasattr(os, "getuid"): + return + # On Windows, there are no "system managed" Python packages. Installing as + # Administrator via pip is the correct way of updating system environments. + # + # We choose sys.platform over utils.compat.WINDOWS here to enable Mypy platform + # checks: https://mypy.readthedocs.io/en/stable/common_issues.html + if sys.platform == "win32" or sys.platform == "cygwin": + return + + if os.getuid() != 0: + return + + logger.warning( + "Running pip as the 'root' user can result in broken permissions and " + "conflicting behaviour with the system package manager, possibly " + "rendering your system unusable. " + "It is recommended to use a virtual environment instead: " + "https://pip.pypa.io/warnings/venv. " + "Use the --root-user-action option if you know what you are doing and " + "want to suppress this warning." + ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/models.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/models.py deleted file mode 100644 index b6bb21a..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/models.py +++ /dev/null @@ -1,39 +0,0 @@ -"""Utilities for defining models -""" - -import operator -from typing import Any, Callable, Type - - -class KeyBasedCompareMixin: - """Provides comparison capabilities that is based on a key""" - - __slots__ = ["_compare_key", "_defining_class"] - - def __init__(self, key: Any, defining_class: Type["KeyBasedCompareMixin"]) -> None: - self._compare_key = key - self._defining_class = defining_class - - def __hash__(self) -> int: - return hash(self._compare_key) - - def __lt__(self, other: Any) -> bool: - return self._compare(other, operator.__lt__) - - def __le__(self, other: Any) -> bool: - return self._compare(other, operator.__le__) - - def __gt__(self, other: Any) -> bool: - return self._compare(other, operator.__gt__) - - def __ge__(self, other: Any) -> bool: - return self._compare(other, operator.__ge__) - - def __eq__(self, other: Any) -> bool: - return self._compare(other, operator.__eq__) - - def _compare(self, other: Any, method: Callable[[Any, Any], bool]) -> bool: - if not isinstance(other, self._defining_class): - return NotImplemented - - return method(self._compare_key, other._compare_key) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/packaging.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/packaging.py index b9f6af4..caad70f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/packaging.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/packaging.py @@ -11,6 +11,7 @@ NormalizedExtra = NewType("NormalizedExtra", str) logger = logging.getLogger(__name__) +@functools.lru_cache(maxsize=32) def check_requires_python( requires_python: Optional[str], version_info: Tuple[int, ...] ) -> bool: @@ -34,7 +35,7 @@ def check_requires_python( return python_version in requires_python_specifier -@functools.lru_cache(maxsize=512) +@functools.lru_cache(maxsize=2048) def get_requirement(req_string: str) -> Requirement: """Construct a packaging.Requirement object with caching""" # Parsing requirement strings is expensive, and is also expected to happen diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/retry.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/retry.py new file mode 100644 index 0000000..abfe072 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/retry.py @@ -0,0 +1,42 @@ +import functools +from time import perf_counter, sleep +from typing import Callable, TypeVar + +from pip._vendor.typing_extensions import ParamSpec + +T = TypeVar("T") +P = ParamSpec("P") + + +def retry( + wait: float, stop_after_delay: float +) -> Callable[[Callable[P, T]], Callable[P, T]]: + """Decorator to automatically retry a function on error. + + If the function raises, the function is recalled with the same arguments + until it returns or the time limit is reached. When the time limit is + surpassed, the last exception raised is reraised. + + :param wait: The time to wait after an error before retrying, in seconds. + :param stop_after_delay: The time limit after which retries will cease, + in seconds. + """ + + def wrapper(func: Callable[P, T]) -> Callable[P, T]: + + @functools.wraps(func) + def retry_wrapped(*args: P.args, **kwargs: P.kwargs) -> T: + # The performance counter is monotonic on all platforms we care + # about and has much better resolution than time.monotonic(). + start_time = perf_counter() + while True: + try: + return func(*args, **kwargs) + except Exception: + if perf_counter() - start_time > stop_after_delay: + raise + sleep(wait) + + return retry_wrapped + + return wrapper diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/subprocess.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/subprocess.py index 79580b0..cb2e23f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/subprocess.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/subprocess.py @@ -2,16 +2,7 @@ import logging import os import shlex import subprocess -from typing import ( - TYPE_CHECKING, - Any, - Callable, - Iterable, - List, - Mapping, - Optional, - Union, -) +from typing import Any, Callable, Iterable, List, Literal, Mapping, Optional, Union from pip._vendor.rich.markup import escape @@ -20,12 +11,6 @@ from pip._internal.exceptions import InstallationSubprocessError from pip._internal.utils.logging import VERBOSE, subprocess_logger from pip._internal.utils.misc import HiddenText -if TYPE_CHECKING: - # Literal was introduced in Python 3.8. - # - # TODO: Remove `if TYPE_CHECKING` when dropping support for Python 3.7. - from typing import Literal - CommandArgs = List[Union[str, HiddenText]] diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/temp_dir.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/temp_dir.py index 4eec5f3..06668e8 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/temp_dir.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/temp_dir.py @@ -208,7 +208,7 @@ class TempDirectory: if self.ignore_cleanup_errors: try: - # first try with tenacity; retrying to handle ephemeral errors + # first try with @retry; retrying to handle ephemeral errors rmtree(self._path, ignore_errors=False) except OSError: # last pass ignore/log all errors diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/unpacking.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/unpacking.py index 78b5c13..87a6d19 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/unpacking.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/unpacking.py @@ -5,6 +5,7 @@ import logging import os import shutil import stat +import sys import tarfile import zipfile from typing import Iterable, List, Optional @@ -85,12 +86,16 @@ def is_within_directory(directory: str, target: str) -> bool: return prefix == abs_directory +def _get_default_mode_plus_executable() -> int: + return 0o777 & ~current_umask() | 0o111 + + def set_extracted_file_to_default_mode_plus_executable(path: str) -> None: """ Make file present at path have execute for user/group/world (chmod +x) is no-op on windows per python docs """ - os.chmod(path, (0o777 & ~current_umask() | 0o111)) + os.chmod(path, _get_default_mode_plus_executable()) def zip_item_is_executable(info: ZipInfo) -> bool: @@ -151,8 +156,8 @@ def untar_file(filename: str, location: str) -> None: Untar the file (with path `filename`) to the destination `location`. All files are written based on system defaults and umask (i.e. permissions are not preserved), except that regular file members with any execute - permissions (user, group, or world) have "chmod +x" applied after being - written. Note that for windows, any execute changes using os.chmod are + permissions (user, group, or world) have "chmod +x" applied on top of the + default. Note that for windows, any execute changes using os.chmod are no-ops per the python docs. """ ensure_dir(location) @@ -170,62 +175,137 @@ def untar_file(filename: str, location: str) -> None: filename, ) mode = "r:*" - tar = tarfile.open(filename, mode, encoding="utf-8") + + tar = tarfile.open(filename, mode, encoding="utf-8") # type: ignore try: leading = has_leading_dir([member.name for member in tar.getmembers()]) - for member in tar.getmembers(): - fn = member.name + + # PEP 706 added `tarfile.data_filter`, and made some other changes to + # Python's tarfile module (see below). The features were backported to + # security releases. + try: + data_filter = tarfile.data_filter + except AttributeError: + _untar_without_filter(filename, location, tar, leading) + else: + default_mode_plus_executable = _get_default_mode_plus_executable() + if leading: - fn = split_leading_dir(fn)[1] - path = os.path.join(location, fn) - if not is_within_directory(location, path): - message = ( - "The tar file ({}) has a file ({}) trying to install " - "outside target directory ({})" - ) - raise InstallationError(message.format(filename, path, location)) - if member.isdir(): - ensure_dir(path) - elif member.issym(): + # Strip the leading directory from all files in the archive, + # including hardlink targets (which are relative to the + # unpack location). + for member in tar.getmembers(): + name_lead, name_rest = split_leading_dir(member.name) + member.name = name_rest + if member.islnk(): + lnk_lead, lnk_rest = split_leading_dir(member.linkname) + if lnk_lead == name_lead: + member.linkname = lnk_rest + + def pip_filter(member: tarfile.TarInfo, path: str) -> tarfile.TarInfo: + orig_mode = member.mode try: - tar._extract_member(member, path) - except Exception as exc: - # Some corrupt tar files seem to produce this - # (specifically bad symlinks) - logger.warning( - "In the tar file %s the member %s is invalid: %s", - filename, - member.name, - exc, + try: + member = data_filter(member, location) + except tarfile.LinkOutsideDestinationError: + if sys.version_info[:3] in { + (3, 8, 17), + (3, 9, 17), + (3, 10, 12), + (3, 11, 4), + }: + # The tarfile filter in specific Python versions + # raises LinkOutsideDestinationError on valid input + # (https://github.com/python/cpython/issues/107845) + # Ignore the error there, but do use the + # more lax `tar_filter` + member = tarfile.tar_filter(member, location) + else: + raise + except tarfile.TarError as exc: + message = "Invalid member in the tar file {}: {}" + # Filter error messages mention the member name. + # No need to add it here. + raise InstallationError( + message.format( + filename, + exc, + ) ) - continue - else: - try: - fp = tar.extractfile(member) - except (KeyError, AttributeError) as exc: - # Some corrupt tar files seem to produce this - # (specifically bad symlinks) - logger.warning( - "In the tar file %s the member %s is invalid: %s", - filename, - member.name, - exc, - ) - continue - ensure_dir(os.path.dirname(path)) - assert fp is not None - with open(path, "wb") as destfp: - shutil.copyfileobj(fp, destfp) - fp.close() - # Update the timestamp (useful for cython compiled files) - tar.utime(member, path) - # member have any execute permissions for user/group/world? - if member.mode & 0o111: - set_extracted_file_to_default_mode_plus_executable(path) + if member.isfile() and orig_mode & 0o111: + member.mode = default_mode_plus_executable + else: + # See PEP 706 note above. + # The PEP changed this from `int` to `Optional[int]`, + # where None means "use the default". Mypy doesn't + # know this yet. + member.mode = None # type: ignore [assignment] + return member + + tar.extractall(location, filter=pip_filter) + finally: tar.close() +def _untar_without_filter( + filename: str, + location: str, + tar: tarfile.TarFile, + leading: bool, +) -> None: + """Fallback for Python without tarfile.data_filter""" + for member in tar.getmembers(): + fn = member.name + if leading: + fn = split_leading_dir(fn)[1] + path = os.path.join(location, fn) + if not is_within_directory(location, path): + message = ( + "The tar file ({}) has a file ({}) trying to install " + "outside target directory ({})" + ) + raise InstallationError(message.format(filename, path, location)) + if member.isdir(): + ensure_dir(path) + elif member.issym(): + try: + tar._extract_member(member, path) + except Exception as exc: + # Some corrupt tar files seem to produce this + # (specifically bad symlinks) + logger.warning( + "In the tar file %s the member %s is invalid: %s", + filename, + member.name, + exc, + ) + continue + else: + try: + fp = tar.extractfile(member) + except (KeyError, AttributeError) as exc: + # Some corrupt tar files seem to produce this + # (specifically bad symlinks) + logger.warning( + "In the tar file %s the member %s is invalid: %s", + filename, + member.name, + exc, + ) + continue + ensure_dir(os.path.dirname(path)) + assert fp is not None + with open(path, "wb") as destfp: + shutil.copyfileobj(fp, destfp) + fp.close() + # Update the timestamp (useful for cython compiled files) + tar.utime(member, path) + # member have any execute permissions for user/group/world? + if member.mode & 0o111: + set_extracted_file_to_default_mode_plus_executable(path) + + def unpack_file( filename: str, location: str, diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/urls.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/urls.py index 6ba2e04..9f34f88 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/urls.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/urls.py @@ -2,17 +2,10 @@ import os import string import urllib.parse import urllib.request -from typing import Optional from .compat import WINDOWS -def get_url_scheme(url: str) -> Optional[str]: - if ":" not in url: - return None - return url.split(":", 1)[0].lower() - - def path_to_url(path: str) -> str: """ Convert a path to a file: URL. The path will be made absolute and have diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/wheel.py b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/wheel.py index 3551f8f..f85aee8 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/utils/wheel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/utils/wheel.py @@ -28,7 +28,7 @@ def parse_wheel(wheel_zip: ZipFile, name: str) -> Tuple[str, Message]: metadata = wheel_metadata(wheel_zip, info_dir) version = wheel_version(metadata) except UnsupportedWheel as e: - raise UnsupportedWheel(f"{name} has an invalid wheel, {str(e)}") + raise UnsupportedWheel(f"{name} has an invalid wheel, {e}") check_compatibility(version, name) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/__init__.cpython-312.pyc index 4f79314..e558458 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/bazaar.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/bazaar.cpython-312.pyc index 0d4d437..b9982be 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/bazaar.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/bazaar.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/git.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/git.cpython-312.pyc index 15f798f..29f4ffe 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/git.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/git.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/mercurial.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/mercurial.cpython-312.pyc index 136620a..b54eca2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/mercurial.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/mercurial.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/subversion.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/subversion.cpython-312.pyc index ea1ef6c..2a28177 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/subversion.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/subversion.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/versioncontrol.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/versioncontrol.cpython-312.pyc index 0c9316e..92099bf 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/versioncontrol.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/__pycache__/versioncontrol.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/bazaar.py b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/bazaar.py index 20a17ed..c754b7c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/bazaar.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/bazaar.py @@ -44,13 +44,13 @@ class Bazaar(VersionControl): display_path(dest), ) if verbosity <= 0: - flag = "--quiet" + flags = ["--quiet"] elif verbosity == 1: - flag = "" + flags = [] else: - flag = f"-{'v'*verbosity}" + flags = [f"-{'v'*verbosity}"] cmd_args = make_command( - "checkout", "--lightweight", flag, rev_options.to_args(), url, dest + "checkout", "--lightweight", *flags, rev_options.to_args(), url, dest ) self.run_command(cmd_args) diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/git.py b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/git.py index 8c242cf..0425deb 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/git.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/git.py @@ -4,6 +4,7 @@ import pathlib import re import urllib.parse import urllib.request +from dataclasses import replace from typing import List, Optional, Tuple from pip._internal.exceptions import BadCommand, InstallationError @@ -217,7 +218,7 @@ class Git(VersionControl): if sha is not None: rev_options = rev_options.make_new(sha) - rev_options.branch_name = rev if is_branch else None + rev_options = replace(rev_options, branch_name=(rev if is_branch else None)) return rev_options diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/subversion.py b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/subversion.py index 16d93a6..f359266 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/subversion.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/subversion.py @@ -288,12 +288,12 @@ class Subversion(VersionControl): display_path(dest), ) if verbosity <= 0: - flag = "--quiet" + flags = ["--quiet"] else: - flag = "" + flags = [] cmd_args = make_command( "checkout", - flag, + *flags, self.get_remote_call_options(), rev_options.to_args(), url, diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/versioncontrol.py b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/versioncontrol.py index 46ca279..a413316 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/versioncontrol.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/vcs/versioncontrol.py @@ -5,13 +5,14 @@ import os import shutil import sys import urllib.parse +from dataclasses import dataclass, field from typing import ( - TYPE_CHECKING, Any, Dict, Iterable, Iterator, List, + Literal, Mapping, Optional, Tuple, @@ -37,14 +38,6 @@ from pip._internal.utils.subprocess import ( format_command_args, make_command, ) -from pip._internal.utils.urls import get_url_scheme - -if TYPE_CHECKING: - # Literal was introduced in Python 3.8. - # - # TODO: Remove `if TYPE_CHECKING` when dropping support for Python 3.7. - from typing import Literal - __all__ = ["vcs"] @@ -58,8 +51,8 @@ def is_url(name: str) -> bool: """ Return true if the name looks like a URL. """ - scheme = get_url_scheme(name) - if scheme is None: + scheme = urllib.parse.urlsplit(name).scheme + if not scheme: return False return scheme in ["http", "https", "file", "ftp"] + vcs.all_schemes @@ -121,34 +114,22 @@ class RemoteNotValidError(Exception): self.url = url +@dataclass(frozen=True) class RevOptions: - """ Encapsulates a VCS-specific revision to install, along with any VCS install options. - Instances of this class should be treated as if immutable. + Args: + vc_class: a VersionControl subclass. + rev: the name of the revision to install. + extra_args: a list of extra options. """ - def __init__( - self, - vc_class: Type["VersionControl"], - rev: Optional[str] = None, - extra_args: Optional[CommandArgs] = None, - ) -> None: - """ - Args: - vc_class: a VersionControl subclass. - rev: the name of the revision to install. - extra_args: a list of extra options. - """ - if extra_args is None: - extra_args = [] - - self.extra_args = extra_args - self.rev = rev - self.vc_class = vc_class - self.branch_name: Optional[str] = None + vc_class: Type["VersionControl"] + rev: Optional[str] = None + extra_args: CommandArgs = field(default_factory=list) + branch_name: Optional[str] = None def __repr__(self) -> str: return f"" @@ -362,7 +343,7 @@ class VersionControl: rev: the name of a revision to install. extra_args: a list of extra options. """ - return RevOptions(cls, rev, extra_args=extra_args) + return RevOptions(cls, rev, extra_args=extra_args or []) @classmethod def _is_local_repository(cls, repo: str) -> bool: @@ -660,6 +641,8 @@ class VersionControl: log_failed_cmd=log_failed_cmd, stdout_only=stdout_only, ) + except NotADirectoryError: + raise BadCommand(f"Cannot find command {cls.name!r} - invalid PATH") except FileNotFoundError: # errno.ENOENT = no such file or directory # In other words, the VCS executable isn't available diff --git a/llmlab/lib/python3.12/site-packages/pip/_internal/wheel_builder.py b/llmlab/lib/python3.12/site-packages/pip/_internal/wheel_builder.py index b1debe3..93f8e1f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_internal/wheel_builder.py +++ b/llmlab/lib/python3.12/site-packages/pip/_internal/wheel_builder.py @@ -70,7 +70,7 @@ def _should_build( if req.editable: # we only build PEP 660 editable requirements - return req.supports_pyproject_editable() + return req.supports_pyproject_editable return True diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/__init__.py index c1884ba..561089c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/__init__.py @@ -60,20 +60,15 @@ if DEBUNDLED: # Actually alias all of our vendored dependencies. vendored("cachecontrol") vendored("certifi") - vendored("colorama") vendored("distlib") vendored("distro") - vendored("six") - vendored("six.moves") - vendored("six.moves.urllib") - vendored("six.moves.urllib.parse") vendored("packaging") vendored("packaging.version") vendored("packaging.specifiers") - vendored("pep517") vendored("pkg_resources") vendored("platformdirs") vendored("progress") + vendored("pyproject_hooks") vendored("requests") vendored("requests.exceptions") vendored("requests.packages") @@ -115,7 +110,7 @@ if DEBUNDLED: vendored("rich.style") vendored("rich.text") vendored("rich.traceback") - vendored("tenacity") - vendored("tomli") + if sys.version_info < (3, 11): + vendored("tomli") vendored("truststore") vendored("urllib3") diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/__init__.cpython-312.pyc index a8cd640..f32daa2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/six.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/six.cpython-312.pyc deleted file mode 100644 index 8a57b31..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/six.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/typing_extensions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/typing_extensions.cpython-312.pyc index 0847141..10b0d43 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/typing_extensions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/__pycache__/typing_extensions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__init__.py index 4d20bc9..2191624 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__init__.py @@ -6,9 +6,10 @@ Make it easy to import from cachecontrol without long namespaces. """ + __author__ = "Eric Larson" __email__ = "eric@ionrock.org" -__version__ = "0.13.1" +__version__ = "0.14.1" from pip._vendor.cachecontrol.adapter import CacheControlAdapter from pip._vendor.cachecontrol.controller import CacheController diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/__init__.cpython-312.pyc index 707dbf9..5072706 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/_cmd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/_cmd.cpython-312.pyc index acfa3f8..7cc4998 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/_cmd.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/_cmd.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/adapter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/adapter.cpython-312.pyc index b799e75..958cd2c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/adapter.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/adapter.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/cache.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/cache.cpython-312.pyc index 0d9b5b2..47105bf 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/cache.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/cache.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/controller.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/controller.cpython-312.pyc index 85a3347..0a4ebe2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/controller.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/controller.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/filewrapper.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/filewrapper.cpython-312.pyc index d24ea83..2f99653 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/filewrapper.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/filewrapper.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/heuristics.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/heuristics.cpython-312.pyc index ae06df5..46f0ea5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/heuristics.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/heuristics.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/serialize.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/serialize.cpython-312.pyc index 9ca8ff1..9cc4987 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/serialize.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/serialize.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/wrapper.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/wrapper.cpython-312.pyc index d8e08d7..9ec03e4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/wrapper.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/__pycache__/wrapper.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/adapter.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/adapter.py index 3e83e30..34a9eb8 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/adapter.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/adapter.py @@ -77,7 +77,7 @@ class CacheControlAdapter(HTTPAdapter): return resp - def build_response( + def build_response( # type: ignore[override] self, request: PreparedRequest, response: HTTPResponse, @@ -125,25 +125,25 @@ class CacheControlAdapter(HTTPAdapter): else: # Wrap the response file with a wrapper that will cache the # response when the stream has been consumed. - response._fp = CallbackFileWrapper( # type: ignore[attr-defined] - response._fp, # type: ignore[attr-defined] + response._fp = CallbackFileWrapper( # type: ignore[assignment] + response._fp, # type: ignore[arg-type] functools.partial( self.controller.cache_response, request, response ), ) if response.chunked: - super_update_chunk_length = response._update_chunk_length # type: ignore[attr-defined] + super_update_chunk_length = response._update_chunk_length def _update_chunk_length(self: HTTPResponse) -> None: super_update_chunk_length() if self.chunk_left == 0: - self._fp._close() # type: ignore[attr-defined] + self._fp._close() # type: ignore[union-attr] - response._update_chunk_length = types.MethodType( # type: ignore[attr-defined] + response._update_chunk_length = types.MethodType( # type: ignore[method-assign] _update_chunk_length, response ) - resp: Response = super().build_response(request, response) # type: ignore[no-untyped-call] + resp: Response = super().build_response(request, response) # See if we should invalidate the cache. if request.method in self.invalidating_methods and resp.ok: diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/cache.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/cache.py index 3293b00..91598e9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/cache.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/cache.py @@ -6,6 +6,7 @@ The cache object API for implementing caches. The default is a thread safe in-memory dictionary. """ + from __future__ import annotations from threading import Lock diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/__init__.cpython-312.pyc index cb3e1ed..4e18db2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/file_cache.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/file_cache.cpython-312.pyc index fa5289b..de55550 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/file_cache.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/file_cache.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/redis_cache.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/redis_cache.cpython-312.pyc index 681b1b6..ffe7fde 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/redis_cache.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/__pycache__/redis_cache.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/file_cache.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/file_cache.py index 1fd2801..81d2ef4 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/file_cache.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/caches/file_cache.py @@ -7,6 +7,7 @@ import hashlib import os from textwrap import dedent from typing import IO, TYPE_CHECKING +from pathlib import Path from pip._vendor.cachecontrol.cache import BaseCache, SeparateBodyBaseCache from pip._vendor.cachecontrol.controller import CacheController @@ -63,7 +64,7 @@ class _FileCacheMixin: def __init__( self, - directory: str, + directory: str | Path, forever: bool = False, filemode: int = 0o0600, dirmode: int = 0o0700, @@ -79,7 +80,7 @@ class _FileCacheMixin: """ NOTE: In order to use the FileCache you must have filelock installed. You can install it via pip: - pip install filelock + pip install cachecontrol[filecache] """ ) raise ImportError(notice) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/controller.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/controller.py index 586b9f9..f0ff6e1 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/controller.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/controller.py @@ -5,6 +5,7 @@ """ The httplib2 algorithms ported for use with requests. """ + from __future__ import annotations import calendar @@ -142,6 +143,11 @@ class CacheController: """ Load a cached response, or return None if it's not available. """ + # We do not support caching of partial content: so if the request contains a + # Range header then we don't want to load anything from the cache. + if "Range" in request.headers: + return None + cache_url = request.url assert cache_url is not None cache_data = self.cache.get(cache_url) @@ -480,7 +486,7 @@ class CacheController: cached_response.headers.update( { k: v - for k, v in response.headers.items() # type: ignore[no-untyped-call] + for k, v in response.headers.items() if k.lower() not in excluded_headers } ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/filewrapper.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/filewrapper.py index 2514390..37d2fa5 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/filewrapper.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/filewrapper.py @@ -38,10 +38,10 @@ class CallbackFileWrapper: self.__callback = callback def __getattr__(self, name: str) -> Any: - # The vaguaries of garbage collection means that self.__fp is + # The vagaries of garbage collection means that self.__fp is # not always set. By using __getattribute__ and the private # name[0] allows looking up the attribute value and raising an - # AttributeError when it doesn't exist. This stop thigns from + # AttributeError when it doesn't exist. This stop things from # infinitely recursing calls to getattr in the case where # self.__fp hasn't been set. # diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/heuristics.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/heuristics.py index b9d72ca..b778c4f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/heuristics.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/heuristics.py @@ -68,7 +68,10 @@ class OneDayCache(BaseHeuristic): if "expires" not in response.headers: date = parsedate(response.headers["date"]) - expires = expire_after(timedelta(days=1), date=datetime(*date[:6], tzinfo=timezone.utc)) # type: ignore[misc] + expires = expire_after( + timedelta(days=1), + date=datetime(*date[:6], tzinfo=timezone.utc), # type: ignore[index,misc] + ) headers["expires"] = datetime_to_header(expires) headers["cache-control"] = "public" return headers diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/pkg_resources/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/serialize.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/serialize.py index f9e967c..a49487a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/serialize.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/cachecontrol/serialize.py @@ -32,13 +32,13 @@ class Serializer: # also update the response with a new file handler to be # sure it acts as though it was never read. body = response.read(decode_content=False) - response._fp = io.BytesIO(body) # type: ignore[attr-defined] + response._fp = io.BytesIO(body) # type: ignore[assignment] response.length_remaining = len(body) data = { "response": { "body": body, # Empty bytestring if body is stored separately - "headers": {str(k): str(v) for k, v in response.headers.items()}, # type: ignore[no-untyped-call] + "headers": {str(k): str(v) for k, v in response.headers.items()}, "status": response.status, "version": response.version, "reason": str(response.reason), @@ -72,31 +72,14 @@ class Serializer: if not data: return None - # Determine what version of the serializer the data was serialized - # with - try: - ver, data = data.split(b",", 1) - except ValueError: - ver = b"cc=0" - - # Make sure that our "ver" is actually a version and isn't a false - # positive from a , being in the data stream. - if ver[:3] != b"cc=": - data = ver + data - ver = b"cc=0" - - # Get the version number out of the cc=N - verstr = ver.split(b"=", 1)[-1].decode("ascii") - - # Dispatch to the actual load method for the given version - try: - return getattr(self, f"_loads_v{verstr}")(request, data, body_file) # type: ignore[no-any-return] - - except AttributeError: - # This is a version we don't have a loads function for, so we'll - # just treat it as a miss and return None + # Previous versions of this library supported other serialization + # formats, but these have all been removed. + if not data.startswith(f"cc={self.serde_version},".encode()): return None + data = data[5:] + return self._loads_v4(request, data, body_file) + def prepare_response( self, request: PreparedRequest, @@ -149,49 +132,6 @@ class Serializer: return HTTPResponse(body=body, preload_content=False, **cached["response"]) - def _loads_v0( - self, - request: PreparedRequest, - data: bytes, - body_file: IO[bytes] | None = None, - ) -> None: - # The original legacy cache data. This doesn't contain enough - # information to construct everything we need, so we'll treat this as - # a miss. - return None - - def _loads_v1( - self, - request: PreparedRequest, - data: bytes, - body_file: IO[bytes] | None = None, - ) -> HTTPResponse | None: - # The "v1" pickled cache format. This is no longer supported - # for security reasons, so we treat it as a miss. - return None - - def _loads_v2( - self, - request: PreparedRequest, - data: bytes, - body_file: IO[bytes] | None = None, - ) -> HTTPResponse | None: - # The "v2" compressed base64 cache format. - # This has been removed due to age and poor size/performance - # characteristics, so we treat it as a miss. - return None - - def _loads_v3( - self, - request: PreparedRequest, - data: bytes, - body_file: IO[bytes] | None = None, - ) -> None: - # Due to Python 2 encoding issues, it's impossible to know for sure - # exactly how to load v3 entries, thus we'll treat these as a miss so - # that they get rewritten out as v4 entries. - return None - def _loads_v4( self, request: PreparedRequest, diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__init__.py index 8ce89ce..f61d77f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__init__.py @@ -1,4 +1,4 @@ from .core import contents, where __all__ = ["contents", "where"] -__version__ = "2023.07.22" +__version__ = "2024.08.30" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__init__.cpython-312.pyc index 3390392..1c98edc 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__main__.cpython-312.pyc index d947188..218e1c7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/core.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/core.cpython-312.pyc index 7187454..14c4809 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/core.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/__pycache__/core.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/cacert.pem b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/cacert.pem index 0212369..3c165a1 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/cacert.pem +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/cacert.pem @@ -245,34 +245,6 @@ mJlglFwjz1onl14LBQaTNx47aTbrqZ5hHY8y2o4M1nQ+ewkk2gF3R8Q7zTSMmfXK 4SVhM7JZG+Ju1zdXtg2pEto= -----END CERTIFICATE----- -# Issuer: O=SECOM Trust.net OU=Security Communication RootCA1 -# Subject: O=SECOM Trust.net OU=Security Communication RootCA1 -# Label: "Security Communication Root CA" -# Serial: 0 -# MD5 Fingerprint: f1:bc:63:6a:54:e0:b5:27:f5:cd:e7:1a:e3:4d:6e:4a -# SHA1 Fingerprint: 36:b1:2b:49:f9:81:9e:d7:4c:9e:bc:38:0f:c6:56:8f:5d:ac:b2:f7 -# SHA256 Fingerprint: e7:5e:72:ed:9f:56:0e:ec:6e:b4:80:00:73:a4:3f:c3:ad:19:19:5a:39:22:82:01:78:95:97:4a:99:02:6b:6c ------BEGIN CERTIFICATE----- -MIIDWjCCAkKgAwIBAgIBADANBgkqhkiG9w0BAQUFADBQMQswCQYDVQQGEwJKUDEY -MBYGA1UEChMPU0VDT00gVHJ1c3QubmV0MScwJQYDVQQLEx5TZWN1cml0eSBDb21t -dW5pY2F0aW9uIFJvb3RDQTEwHhcNMDMwOTMwMDQyMDQ5WhcNMjMwOTMwMDQyMDQ5 -WjBQMQswCQYDVQQGEwJKUDEYMBYGA1UEChMPU0VDT00gVHJ1c3QubmV0MScwJQYD -VQQLEx5TZWN1cml0eSBDb21tdW5pY2F0aW9uIFJvb3RDQTEwggEiMA0GCSqGSIb3 -DQEBAQUAA4IBDwAwggEKAoIBAQCzs/5/022x7xZ8V6UMbXaKL0u/ZPtM7orw8yl8 -9f/uKuDp6bpbZCKamm8sOiZpUQWZJtzVHGpxxpp9Hp3dfGzGjGdnSj74cbAZJ6kJ -DKaVv0uMDPpVmDvY6CKhS3E4eayXkmmziX7qIWgGmBSWh9JhNrxtJ1aeV+7AwFb9 -Ms+k2Y7CI9eNqPPYJayX5HA49LY6tJ07lyZDo6G8SVlyTCMwhwFY9k6+HGhWZq/N -QV3Is00qVUarH9oe4kA92819uZKAnDfdDJZkndwi92SL32HeFZRSFaB9UslLqCHJ -xrHty8OVYNEP8Ktw+N/LTX7s1vqr2b1/VPKl6Xn62dZ2JChzAgMBAAGjPzA9MB0G -A1UdDgQWBBSgc0mZaNyFW2XjmygvV5+9M7wHSDALBgNVHQ8EBAMCAQYwDwYDVR0T -AQH/BAUwAwEB/zANBgkqhkiG9w0BAQUFAAOCAQEAaECpqLvkT115swW1F7NgE+vG -kl3g0dNq/vu+m22/xwVtWSDEHPC32oRYAmP6SBbvT6UL90qY8j+eG61Ha2POCEfr -Uj94nK9NrvjVT8+amCoQQTlSxN3Zmw7vkwGusi7KaEIkQmywszo+zenaSMQVy+n5 -Bw+SUEmK3TGXX8npN6o7WWWXlDLJs58+OmJYxUmtYg5xpTKqL8aJdkNAExNnPaJU -JRDL8Try2frbSVa7pv6nQTXD4IhhyYjH3zYQIphZ6rBK+1YWc26sTfcioU+tHXot -RSflMMFe8toTyyVCUZVHA4xsIcx0Qu1T/zOLjw9XARYvz6buyXAiFL39vmwLAw== ------END CERTIFICATE----- - # Issuer: CN=XRamp Global Certification Authority O=XRamp Security Services Inc OU=www.xrampsecurity.com # Subject: CN=XRamp Global Certification Authority O=XRamp Security Services Inc OU=www.xrampsecurity.com # Label: "XRamp Global CA Root" @@ -881,49 +853,6 @@ Mx86OyXShkDOOyyGeMlhLxS67ttVb9+E7gUJTb0o2HLO02JQZR7rkpeDMdmztcpH WD9f -----END CERTIFICATE----- -# Issuer: CN=Autoridad de Certificacion Firmaprofesional CIF A62634068 -# Subject: CN=Autoridad de Certificacion Firmaprofesional CIF A62634068 -# Label: "Autoridad de Certificacion Firmaprofesional CIF A62634068" -# Serial: 6047274297262753887 -# MD5 Fingerprint: 73:3a:74:7a:ec:bb:a3:96:a6:c2:e4:e2:c8:9b:c0:c3 -# SHA1 Fingerprint: ae:c5:fb:3f:c8:e1:bf:c4:e5:4f:03:07:5a:9a:e8:00:b7:f7:b6:fa -# SHA256 Fingerprint: 04:04:80:28:bf:1f:28:64:d4:8f:9a:d4:d8:32:94:36:6a:82:88:56:55:3f:3b:14:30:3f:90:14:7f:5d:40:ef ------BEGIN CERTIFICATE----- -MIIGFDCCA/ygAwIBAgIIU+w77vuySF8wDQYJKoZIhvcNAQEFBQAwUTELMAkGA1UE -BhMCRVMxQjBABgNVBAMMOUF1dG9yaWRhZCBkZSBDZXJ0aWZpY2FjaW9uIEZpcm1h -cHJvZmVzaW9uYWwgQ0lGIEE2MjYzNDA2ODAeFw0wOTA1MjAwODM4MTVaFw0zMDEy -MzEwODM4MTVaMFExCzAJBgNVBAYTAkVTMUIwQAYDVQQDDDlBdXRvcmlkYWQgZGUg -Q2VydGlmaWNhY2lvbiBGaXJtYXByb2Zlc2lvbmFsIENJRiBBNjI2MzQwNjgwggIi -MA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQDKlmuO6vj78aI14H9M2uDDUtd9 -thDIAl6zQyrET2qyyhxdKJp4ERppWVevtSBC5IsP5t9bpgOSL/UR5GLXMnE42QQM -cas9UX4PB99jBVzpv5RvwSmCwLTaUbDBPLutN0pcyvFLNg4kq7/DhHf9qFD0sefG -L9ItWY16Ck6WaVICqjaY7Pz6FIMMNx/Jkjd/14Et5cS54D40/mf0PmbR0/RAz15i -NA9wBj4gGFrO93IbJWyTdBSTo3OxDqqHECNZXyAFGUftaI6SEspd/NYrspI8IM/h -X68gvqB2f3bl7BqGYTM+53u0P6APjqK5am+5hyZvQWyIplD9amML9ZMWGxmPsu2b -m8mQ9QEM3xk9Dz44I8kvjwzRAv4bVdZO0I08r0+k8/6vKtMFnXkIoctXMbScyJCy -Z/QYFpM6/EfY0XiWMR+6KwxfXZmtY4laJCB22N/9q06mIqqdXuYnin1oKaPnirja -EbsXLZmdEyRG98Xi2J+Of8ePdG1asuhy9azuJBCtLxTa/y2aRnFHvkLfuwHb9H/T -KI8xWVvTyQKmtFLKbpf7Q8UIJm+K9Lv9nyiqDdVF8xM6HdjAeI9BZzwelGSuewvF -6NkBiDkal4ZkQdU7hwxu+g/GvUgUvzlN1J5Bto+WHWOWk9mVBngxaJ43BjuAiUVh -OSPHG0SjFeUc+JIwuwIDAQABo4HvMIHsMBIGA1UdEwEB/wQIMAYBAf8CAQEwDgYD -VR0PAQH/BAQDAgEGMB0GA1UdDgQWBBRlzeurNR4APn7VdMActHNHDhpkLzCBpgYD -VR0gBIGeMIGbMIGYBgRVHSAAMIGPMC8GCCsGAQUFBwIBFiNodHRwOi8vd3d3LmZp -cm1hcHJvZmVzaW9uYWwuY29tL2NwczBcBggrBgEFBQcCAjBQHk4AUABhAHMAZQBv -ACAAZABlACAAbABhACAAQgBvAG4AYQBuAG8AdgBhACAANAA3ACAAQgBhAHIAYwBl -AGwAbwBuAGEAIAAwADgAMAAxADcwDQYJKoZIhvcNAQEFBQADggIBABd9oPm03cXF -661LJLWhAqvdpYhKsg9VSytXjDvlMd3+xDLx51tkljYyGOylMnfX40S2wBEqgLk9 -am58m9Ot/MPWo+ZkKXzR4Tgegiv/J2Wv+xYVxC5xhOW1//qkR71kMrv2JYSiJ0L1 -ILDCExARzRAVukKQKtJE4ZYm6zFIEv0q2skGz3QeqUvVhyj5eTSSPi5E6PaPT481 -PyWzOdxjKpBrIF/EUhJOlywqrJ2X3kjyo2bbwtKDlaZmp54lD+kLM5FlClrD2VQS -3a/DTg4fJl4N3LON7NWBcN7STyQF82xO9UxJZo3R/9ILJUFI/lGExkKvgATP0H5k -SeTy36LssUzAKh3ntLFlosS88Zj0qnAHY7S42jtM+kAiMFsRpvAFDsYCA0irhpuF -3dvd6qJ2gHN99ZwExEWN57kci57q13XRcrHedUTnQn3iV2t93Jm8PYMo6oCTjcVM -ZcFwgbg4/EMxsvYDNEeyrPsiBsse3RdHHF9mudMaotoRsaS8I8nkvof/uZS2+F0g -StRf571oe2XyFR7SOqkt6dhrJKyXWERHrVkY8SFlcN7ONGCoQPHzPKTDKCOM/icz -Q0CgFzzr6juwcqajuUpLXhZI9LK8yIySxZ2frHI2vDSANGupi5LAuBft7HZT9SQB -jLMi6Et8Vcad+qMUu2WFbm5PEn4KPJ2V ------END CERTIFICATE----- - # Issuer: CN=Izenpe.com O=IZENPE S.A. # Subject: CN=Izenpe.com O=IZENPE S.A. # Label: "Izenpe.com" @@ -3556,46 +3485,6 @@ DgQWBBQxCpCPtsad0kRLgLWi5h+xEk8blTAKBggqhkjOPQQDAwNoADBlAjEA31SQ +RHUjE7AwWHCFUyqqx0LMV87HOIAl0Qx5v5zli/altP+CAezNIm8BZ/3Hobui3A= -----END CERTIFICATE----- -# Issuer: CN=GLOBALTRUST 2020 O=e-commerce monitoring GmbH -# Subject: CN=GLOBALTRUST 2020 O=e-commerce monitoring GmbH -# Label: "GLOBALTRUST 2020" -# Serial: 109160994242082918454945253 -# MD5 Fingerprint: 8a:c7:6f:cb:6d:e3:cc:a2:f1:7c:83:fa:0e:78:d7:e8 -# SHA1 Fingerprint: d0:67:c1:13:51:01:0c:aa:d0:c7:6a:65:37:31:16:26:4f:53:71:a2 -# SHA256 Fingerprint: 9a:29:6a:51:82:d1:d4:51:a2:e3:7f:43:9b:74:da:af:a2:67:52:33:29:f9:0f:9a:0d:20:07:c3:34:e2:3c:9a ------BEGIN CERTIFICATE----- -MIIFgjCCA2qgAwIBAgILWku9WvtPilv6ZeUwDQYJKoZIhvcNAQELBQAwTTELMAkG -A1UEBhMCQVQxIzAhBgNVBAoTGmUtY29tbWVyY2UgbW9uaXRvcmluZyBHbWJIMRkw -FwYDVQQDExBHTE9CQUxUUlVTVCAyMDIwMB4XDTIwMDIxMDAwMDAwMFoXDTQwMDYx -MDAwMDAwMFowTTELMAkGA1UEBhMCQVQxIzAhBgNVBAoTGmUtY29tbWVyY2UgbW9u -aXRvcmluZyBHbWJIMRkwFwYDVQQDExBHTE9CQUxUUlVTVCAyMDIwMIICIjANBgkq -hkiG9w0BAQEFAAOCAg8AMIICCgKCAgEAri5WrRsc7/aVj6B3GyvTY4+ETUWiD59b -RatZe1E0+eyLinjF3WuvvcTfk0Uev5E4C64OFudBc/jbu9G4UeDLgztzOG53ig9Z -YybNpyrOVPu44sB8R85gfD+yc/LAGbaKkoc1DZAoouQVBGM+uq/ufF7MpotQsjj3 -QWPKzv9pj2gOlTblzLmMCcpL3TGQlsjMH/1WljTbjhzqLL6FLmPdqqmV0/0plRPw -yJiT2S0WR5ARg6I6IqIoV6Lr/sCMKKCmfecqQjuCgGOlYx8ZzHyyZqjC0203b+J+ -BlHZRYQfEs4kUmSFC0iAToexIiIwquuuvuAC4EDosEKAA1GqtH6qRNdDYfOiaxaJ -SaSjpCuKAsR49GiKweR6NrFvG5Ybd0mN1MkGco/PU+PcF4UgStyYJ9ORJitHHmkH -r96i5OTUawuzXnzUJIBHKWk7buis/UDr2O1xcSvy6Fgd60GXIsUf1DnQJ4+H4xj0 -4KlGDfV0OoIu0G4skaMxXDtG6nsEEFZegB31pWXogvziB4xiRfUg3kZwhqG8k9Me -dKZssCz3AwyIDMvUclOGvGBG85hqwvG/Q/lwIHfKN0F5VVJjjVsSn8VoxIidrPIw -q7ejMZdnrY8XD2zHc+0klGvIg5rQmjdJBKuxFshsSUktq6HQjJLyQUp5ISXbY9e2 -nKd+Qmn7OmMCAwEAAaNjMGEwDwYDVR0TAQH/BAUwAwEB/zAOBgNVHQ8BAf8EBAMC -AQYwHQYDVR0OBBYEFNwuH9FhN3nkq9XVsxJxaD1qaJwiMB8GA1UdIwQYMBaAFNwu -H9FhN3nkq9XVsxJxaD1qaJwiMA0GCSqGSIb3DQEBCwUAA4ICAQCR8EICaEDuw2jA -VC/f7GLDw56KoDEoqoOOpFaWEhCGVrqXctJUMHytGdUdaG/7FELYjQ7ztdGl4wJC -XtzoRlgHNQIw4Lx0SsFDKv/bGtCwr2zD/cuz9X9tAy5ZVp0tLTWMstZDFyySCstd -6IwPS3BD0IL/qMy/pJTAvoe9iuOTe8aPmxadJ2W8esVCgmxcB9CpwYhgROmYhRZf -+I/KARDOJcP5YBugxZfD0yyIMaK9MOzQ0MAS8cE54+X1+NZK3TTN+2/BT+MAi1bi -kvcoskJ3ciNnxz8RFbLEAwW+uxF7Cr+obuf/WEPPm2eggAe2HcqtbepBEX4tdJP7 -wry+UUTF72glJ4DjyKDUEuzZpTcdN3y0kcra1LGWge9oXHYQSa9+pTeAsRxSvTOB -TI/53WXZFM2KJVj04sWDpQmQ1GwUY7VA3+vA/MRYfg0UFodUJ25W5HCEuGwyEn6C -MUO+1918oa2u1qsgEu8KwxCMSZY13At1XrFP1U80DhEgB3VDRemjEdqso5nCtnkn -4rnvyOL2NSl6dPrFf4IFYqYK6miyeUcGbvJXqBUzxvd4Sj1Ce2t+/vdG6tHrju+I -aFvowdlxfv1k7/9nR4hYJS8+hge9+6jlgqispdNpQ80xiEmEU5LAsTkbOYMBMMTy -qfrQA71yN2BWHzZ8vTmR9W0Nv3vXkg== ------END CERTIFICATE----- - # Issuer: CN=ANF Secure Server Root CA O=ANF Autoridad de Certificacion OU=ANF CA Raiz # Subject: CN=ANF Secure Server Root CA O=ANF Autoridad de Certificacion OU=ANF CA Raiz # Label: "ANF Secure Server Root CA" @@ -4633,3 +4522,408 @@ o7Ey7Nmj1m+UI/87tyll5gfp77YZ6ufCOB0yiJA8EytuzO+rdwY0d4RPcuSBhPm5 dDTedk+SKlOxJTnbPP/lPqYO5Wue/9vsL3SD3460s6neFE3/MaNFcyT6lSnMEpcE oji2jbDwN/zIIX8/syQbPYtuzE2wFg2WHYMfRsCbvUOZ58SWLs5fyQ== -----END CERTIFICATE----- + +# Issuer: CN=TrustAsia Global Root CA G3 O=TrustAsia Technologies, Inc. +# Subject: CN=TrustAsia Global Root CA G3 O=TrustAsia Technologies, Inc. +# Label: "TrustAsia Global Root CA G3" +# Serial: 576386314500428537169965010905813481816650257167 +# MD5 Fingerprint: 30:42:1b:b7:bb:81:75:35:e4:16:4f:53:d2:94:de:04 +# SHA1 Fingerprint: 63:cf:b6:c1:27:2b:56:e4:88:8e:1c:23:9a:b6:2e:81:47:24:c3:c7 +# SHA256 Fingerprint: e0:d3:22:6a:eb:11:63:c2:e4:8f:f9:be:3b:50:b4:c6:43:1b:e7:bb:1e:ac:c5:c3:6b:5d:5e:c5:09:03:9a:08 +-----BEGIN CERTIFICATE----- +MIIFpTCCA42gAwIBAgIUZPYOZXdhaqs7tOqFhLuxibhxkw8wDQYJKoZIhvcNAQEM +BQAwWjELMAkGA1UEBhMCQ04xJTAjBgNVBAoMHFRydXN0QXNpYSBUZWNobm9sb2dp +ZXMsIEluYy4xJDAiBgNVBAMMG1RydXN0QXNpYSBHbG9iYWwgUm9vdCBDQSBHMzAe +Fw0yMTA1MjAwMjEwMTlaFw00NjA1MTkwMjEwMTlaMFoxCzAJBgNVBAYTAkNOMSUw +IwYDVQQKDBxUcnVzdEFzaWEgVGVjaG5vbG9naWVzLCBJbmMuMSQwIgYDVQQDDBtU +cnVzdEFzaWEgR2xvYmFsIFJvb3QgQ0EgRzMwggIiMA0GCSqGSIb3DQEBAQUAA4IC +DwAwggIKAoICAQDAMYJhkuSUGwoqZdC+BqmHO1ES6nBBruL7dOoKjbmzTNyPtxNS +T1QY4SxzlZHFZjtqz6xjbYdT8PfxObegQ2OwxANdV6nnRM7EoYNl9lA+sX4WuDqK +AtCWHwDNBSHvBm3dIZwZQ0WhxeiAysKtQGIXBsaqvPPW5vxQfmZCHzyLpnl5hkA1 +nyDvP+uLRx+PjsXUjrYsyUQE49RDdT/VP68czH5GX6zfZBCK70bwkPAPLfSIC7Ep +qq+FqklYqL9joDiR5rPmd2jE+SoZhLsO4fWvieylL1AgdB4SQXMeJNnKziyhWTXA +yB1GJ2Faj/lN03J5Zh6fFZAhLf3ti1ZwA0pJPn9pMRJpxx5cynoTi+jm9WAPzJMs +hH/x/Gr8m0ed262IPfN2dTPXS6TIi/n1Q1hPy8gDVI+lhXgEGvNz8teHHUGf59gX +zhqcD0r83ERoVGjiQTz+LISGNzzNPy+i2+f3VANfWdP3kXjHi3dqFuVJhZBFcnAv +kV34PmVACxmZySYgWmjBNb9Pp1Hx2BErW+Canig7CjoKH8GB5S7wprlppYiU5msT +f9FkPz2ccEblooV7WIQn3MSAPmeamseaMQ4w7OYXQJXZRe0Blqq/DPNL0WP3E1jA +uPP6Z92bfW1K/zJMtSU7/xxnD4UiWQWRkUF3gdCFTIcQcf+eQxuulXUtgQIDAQAB +o2MwYTAPBgNVHRMBAf8EBTADAQH/MB8GA1UdIwQYMBaAFEDk5PIj7zjKsK5Xf/Ih +MBY027ySMB0GA1UdDgQWBBRA5OTyI+84yrCuV3/yITAWNNu8kjAOBgNVHQ8BAf8E +BAMCAQYwDQYJKoZIhvcNAQEMBQADggIBACY7UeFNOPMyGLS0XuFlXsSUT9SnYaP4 +wM8zAQLpw6o1D/GUE3d3NZ4tVlFEbuHGLige/9rsR82XRBf34EzC4Xx8MnpmyFq2 +XFNFV1pF1AWZLy4jVe5jaN/TG3inEpQGAHUNcoTpLrxaatXeL1nHo+zSh2bbt1S1 +JKv0Q3jbSwTEb93mPmY+KfJLaHEih6D4sTNjduMNhXJEIlU/HHzp/LgV6FL6qj6j +ITk1dImmasI5+njPtqzn59ZW/yOSLlALqbUHM/Q4X6RJpstlcHboCoWASzY9M/eV +VHUl2qzEc4Jl6VL1XP04lQJqaTDFHApXB64ipCz5xUG3uOyfT0gA+QEEVcys+TIx +xHWVBqB/0Y0n3bOppHKH/lmLmnp0Ft0WpWIp6zqW3IunaFnT63eROfjXy9mPX1on +AX1daBli2MjN9LdyR75bl87yraKZk62Uy5P2EgmVtqvXO9A/EcswFi55gORngS1d +7XB4tmBZrOFdRWOPyN9yaFvqHbgB8X7754qz41SgOAngPN5C8sLtLpvzHzW2Ntjj +gKGLzZlkD8Kqq7HK9W+eQ42EVJmzbsASZthwEPEGNTNDqJwuuhQxzhB/HIbjj9LV ++Hfsm6vxL2PZQl/gZ4FkkfGXL/xuJvYz+NO1+MRiqzFRJQJ6+N1rZdVtTTDIZbpo +FGWsJwt0ivKH +-----END CERTIFICATE----- + +# Issuer: CN=TrustAsia Global Root CA G4 O=TrustAsia Technologies, Inc. +# Subject: CN=TrustAsia Global Root CA G4 O=TrustAsia Technologies, Inc. +# Label: "TrustAsia Global Root CA G4" +# Serial: 451799571007117016466790293371524403291602933463 +# MD5 Fingerprint: 54:dd:b2:d7:5f:d8:3e:ed:7c:e0:0b:2e:cc:ed:eb:eb +# SHA1 Fingerprint: 57:73:a5:61:5d:80:b2:e6:ac:38:82:fc:68:07:31:ac:9f:b5:92:5a +# SHA256 Fingerprint: be:4b:56:cb:50:56:c0:13:6a:52:6d:f4:44:50:8d:aa:36:a0:b5:4f:42:e4:ac:38:f7:2a:f4:70:e4:79:65:4c +-----BEGIN CERTIFICATE----- +MIICVTCCAdygAwIBAgIUTyNkuI6XY57GU4HBdk7LKnQV1tcwCgYIKoZIzj0EAwMw +WjELMAkGA1UEBhMCQ04xJTAjBgNVBAoMHFRydXN0QXNpYSBUZWNobm9sb2dpZXMs +IEluYy4xJDAiBgNVBAMMG1RydXN0QXNpYSBHbG9iYWwgUm9vdCBDQSBHNDAeFw0y +MTA1MjAwMjEwMjJaFw00NjA1MTkwMjEwMjJaMFoxCzAJBgNVBAYTAkNOMSUwIwYD +VQQKDBxUcnVzdEFzaWEgVGVjaG5vbG9naWVzLCBJbmMuMSQwIgYDVQQDDBtUcnVz +dEFzaWEgR2xvYmFsIFJvb3QgQ0EgRzQwdjAQBgcqhkjOPQIBBgUrgQQAIgNiAATx +s8045CVD5d4ZCbuBeaIVXxVjAd7Cq92zphtnS4CDr5nLrBfbK5bKfFJV4hrhPVbw +LxYI+hW8m7tH5j/uqOFMjPXTNvk4XatwmkcN4oFBButJ+bAp3TPsUKV/eSm4IJij +YzBhMA8GA1UdEwEB/wQFMAMBAf8wHwYDVR0jBBgwFoAUpbtKl86zK3+kMd6Xg1mD +pm9xy94wHQYDVR0OBBYEFKW7SpfOsyt/pDHel4NZg6ZvccveMA4GA1UdDwEB/wQE +AwIBBjAKBggqhkjOPQQDAwNnADBkAjBe8usGzEkxn0AAbbd+NvBNEU/zy4k6LHiR +UKNbwMp1JvK/kF0LgoxgKJ/GcJpo5PECMFxYDlZ2z1jD1xCMuo6u47xkdUfFVZDj +/bpV6wfEU6s3qe4hsiFbYI89MvHVI5TWWA== +-----END CERTIFICATE----- + +# Issuer: CN=CommScope Public Trust ECC Root-01 O=CommScope +# Subject: CN=CommScope Public Trust ECC Root-01 O=CommScope +# Label: "CommScope Public Trust ECC Root-01" +# Serial: 385011430473757362783587124273108818652468453534 +# MD5 Fingerprint: 3a:40:a7:fc:03:8c:9c:38:79:2f:3a:a2:6c:b6:0a:16 +# SHA1 Fingerprint: 07:86:c0:d8:dd:8e:c0:80:98:06:98:d0:58:7a:ef:de:a6:cc:a2:5d +# SHA256 Fingerprint: 11:43:7c:da:7b:b4:5e:41:36:5f:45:b3:9a:38:98:6b:0d:e0:0d:ef:34:8e:0c:7b:b0:87:36:33:80:0b:c3:8b +-----BEGIN CERTIFICATE----- +MIICHTCCAaOgAwIBAgIUQ3CCd89NXTTxyq4yLzf39H91oJ4wCgYIKoZIzj0EAwMw +TjELMAkGA1UEBhMCVVMxEjAQBgNVBAoMCUNvbW1TY29wZTErMCkGA1UEAwwiQ29t +bVNjb3BlIFB1YmxpYyBUcnVzdCBFQ0MgUm9vdC0wMTAeFw0yMTA0MjgxNzM1NDNa +Fw00NjA0MjgxNzM1NDJaME4xCzAJBgNVBAYTAlVTMRIwEAYDVQQKDAlDb21tU2Nv +cGUxKzApBgNVBAMMIkNvbW1TY29wZSBQdWJsaWMgVHJ1c3QgRUNDIFJvb3QtMDEw +djAQBgcqhkjOPQIBBgUrgQQAIgNiAARLNumuV16ocNfQj3Rid8NeeqrltqLxeP0C +flfdkXmcbLlSiFS8LwS+uM32ENEp7LXQoMPwiXAZu1FlxUOcw5tjnSCDPgYLpkJE +hRGnSjot6dZoL0hOUysHP029uax3OVejQjBAMA8GA1UdEwEB/wQFMAMBAf8wDgYD +VR0PAQH/BAQDAgEGMB0GA1UdDgQWBBSOB2LAUN3GGQYARnQE9/OufXVNMDAKBggq +hkjOPQQDAwNoADBlAjEAnDPfQeMjqEI2Jpc1XHvr20v4qotzVRVcrHgpD7oh2MSg +2NED3W3ROT3Ek2DS43KyAjB8xX6I01D1HiXo+k515liWpDVfG2XqYZpwI7UNo5uS +Um9poIyNStDuiw7LR47QjRE= +-----END CERTIFICATE----- + +# Issuer: CN=CommScope Public Trust ECC Root-02 O=CommScope +# Subject: CN=CommScope Public Trust ECC Root-02 O=CommScope +# Label: "CommScope Public Trust ECC Root-02" +# Serial: 234015080301808452132356021271193974922492992893 +# MD5 Fingerprint: 59:b0:44:d5:65:4d:b8:5c:55:19:92:02:b6:d1:94:b2 +# SHA1 Fingerprint: 3c:3f:ef:57:0f:fe:65:93:86:9e:a0:fe:b0:f6:ed:8e:d1:13:c7:e5 +# SHA256 Fingerprint: 2f:fb:7f:81:3b:bb:b3:c8:9a:b4:e8:16:2d:0f:16:d7:15:09:a8:30:cc:9d:73:c2:62:e5:14:08:75:d1:ad:4a +-----BEGIN CERTIFICATE----- +MIICHDCCAaOgAwIBAgIUKP2ZYEFHpgE6yhR7H+/5aAiDXX0wCgYIKoZIzj0EAwMw +TjELMAkGA1UEBhMCVVMxEjAQBgNVBAoMCUNvbW1TY29wZTErMCkGA1UEAwwiQ29t +bVNjb3BlIFB1YmxpYyBUcnVzdCBFQ0MgUm9vdC0wMjAeFw0yMTA0MjgxNzQ0NTRa +Fw00NjA0MjgxNzQ0NTNaME4xCzAJBgNVBAYTAlVTMRIwEAYDVQQKDAlDb21tU2Nv +cGUxKzApBgNVBAMMIkNvbW1TY29wZSBQdWJsaWMgVHJ1c3QgRUNDIFJvb3QtMDIw +djAQBgcqhkjOPQIBBgUrgQQAIgNiAAR4MIHoYx7l63FRD/cHB8o5mXxO1Q/MMDAL +j2aTPs+9xYa9+bG3tD60B8jzljHz7aRP+KNOjSkVWLjVb3/ubCK1sK9IRQq9qEmU +v4RDsNuESgMjGWdqb8FuvAY5N9GIIvejQjBAMA8GA1UdEwEB/wQFMAMBAf8wDgYD +VR0PAQH/BAQDAgEGMB0GA1UdDgQWBBTmGHX/72DehKT1RsfeSlXjMjZ59TAKBggq +hkjOPQQDAwNnADBkAjAmc0l6tqvmSfR9Uj/UQQSugEODZXW5hYA4O9Zv5JOGq4/n +ich/m35rChJVYaoR4HkCMHfoMXGsPHED1oQmHhS48zs73u1Z/GtMMH9ZzkXpc2AV +mkzw5l4lIhVtwodZ0LKOag== +-----END CERTIFICATE----- + +# Issuer: CN=CommScope Public Trust RSA Root-01 O=CommScope +# Subject: CN=CommScope Public Trust RSA Root-01 O=CommScope +# Label: "CommScope Public Trust RSA Root-01" +# Serial: 354030733275608256394402989253558293562031411421 +# MD5 Fingerprint: 0e:b4:15:bc:87:63:5d:5d:02:73:d4:26:38:68:73:d8 +# SHA1 Fingerprint: 6d:0a:5f:f7:b4:23:06:b4:85:b3:b7:97:64:fc:ac:75:f5:33:f2:93 +# SHA256 Fingerprint: 02:bd:f9:6e:2a:45:dd:9b:f1:8f:c7:e1:db:df:21:a0:37:9b:a3:c9:c2:61:03:44:cf:d8:d6:06:fe:c1:ed:81 +-----BEGIN CERTIFICATE----- +MIIFbDCCA1SgAwIBAgIUPgNJgXUWdDGOTKvVxZAplsU5EN0wDQYJKoZIhvcNAQEL +BQAwTjELMAkGA1UEBhMCVVMxEjAQBgNVBAoMCUNvbW1TY29wZTErMCkGA1UEAwwi +Q29tbVNjb3BlIFB1YmxpYyBUcnVzdCBSU0EgUm9vdC0wMTAeFw0yMTA0MjgxNjQ1 +NTRaFw00NjA0MjgxNjQ1NTNaME4xCzAJBgNVBAYTAlVTMRIwEAYDVQQKDAlDb21t +U2NvcGUxKzApBgNVBAMMIkNvbW1TY29wZSBQdWJsaWMgVHJ1c3QgUlNBIFJvb3Qt +MDEwggIiMA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQCwSGWjDR1C45FtnYSk +YZYSwu3D2iM0GXb26v1VWvZVAVMP8syMl0+5UMuzAURWlv2bKOx7dAvnQmtVzslh +suitQDy6uUEKBU8bJoWPQ7VAtYXR1HHcg0Hz9kXHgKKEUJdGzqAMxGBWBB0HW0al +DrJLpA6lfO741GIDuZNqihS4cPgugkY4Iw50x2tBt9Apo52AsH53k2NC+zSDO3Oj +WiE260f6GBfZumbCk6SP/F2krfxQapWsvCQz0b2If4b19bJzKo98rwjyGpg/qYFl +P8GMicWWMJoKz/TUyDTtnS+8jTiGU+6Xn6myY5QXjQ/cZip8UlF1y5mO6D1cv547 +KI2DAg+pn3LiLCuz3GaXAEDQpFSOm117RTYm1nJD68/A6g3czhLmfTifBSeolz7p +UcZsBSjBAg/pGG3svZwG1KdJ9FQFa2ww8esD1eo9anbCyxooSU1/ZOD6K9pzg4H/ +kQO9lLvkuI6cMmPNn7togbGEW682v3fuHX/3SZtS7NJ3Wn2RnU3COS3kuoL4b/JO +Hg9O5j9ZpSPcPYeoKFgo0fEbNttPxP/hjFtyjMcmAyejOQoBqsCyMWCDIqFPEgkB +Ea801M/XrmLTBQe0MXXgDW1XT2mH+VepuhX2yFJtocucH+X8eKg1mp9BFM6ltM6U +CBwJrVbl2rZJmkrqYxhTnCwuwwIDAQABo0IwQDAPBgNVHRMBAf8EBTADAQH/MA4G +A1UdDwEB/wQEAwIBBjAdBgNVHQ4EFgQUN12mmnQywsL5x6YVEFm45P3luG0wDQYJ +KoZIhvcNAQELBQADggIBAK+nz97/4L1CjU3lIpbfaOp9TSp90K09FlxD533Ahuh6 +NWPxzIHIxgvoLlI1pKZJkGNRrDSsBTtXAOnTYtPZKdVUvhwQkZyybf5Z/Xn36lbQ +nmhUQo8mUuJM3y+Xpi/SB5io82BdS5pYV4jvguX6r2yBS5KPQJqTRlnLX3gWsWc+ +QgvfKNmwrZggvkN80V4aCRckjXtdlemrwWCrWxhkgPut4AZ9HcpZuPN4KWfGVh2v +trV0KnahP/t1MJ+UXjulYPPLXAziDslg+MkfFoom3ecnf+slpoq9uC02EJqxWE2a +aE9gVOX2RhOOiKy8IUISrcZKiX2bwdgt6ZYD9KJ0DLwAHb/WNyVntHKLr4W96ioD +j8z7PEQkguIBpQtZtjSNMgsSDesnwv1B10A8ckYpwIzqug/xBpMu95yo9GA+o/E4 +Xo4TwbM6l4c/ksp4qRyv0LAbJh6+cOx69TOY6lz/KwsETkPdY34Op054A5U+1C0w +lREQKC6/oAI+/15Z0wUOlV9TRe9rh9VIzRamloPh37MG88EU26fsHItdkJANclHn +YfkUyq+Dj7+vsQpZXdxc1+SWrVtgHdqul7I52Qb1dgAT+GhMIbA1xNxVssnBQVoc +icCMb3SgazNNtQEo/a2tiRc7ppqEvOuM6sRxJKi6KfkIsidWNTJf6jn7MZrVGczw +-----END CERTIFICATE----- + +# Issuer: CN=CommScope Public Trust RSA Root-02 O=CommScope +# Subject: CN=CommScope Public Trust RSA Root-02 O=CommScope +# Label: "CommScope Public Trust RSA Root-02" +# Serial: 480062499834624527752716769107743131258796508494 +# MD5 Fingerprint: e1:29:f9:62:7b:76:e2:96:6d:f3:d4:d7:0f:ae:1f:aa +# SHA1 Fingerprint: ea:b0:e2:52:1b:89:93:4c:11:68:f2:d8:9a:ac:22:4c:a3:8a:57:ae +# SHA256 Fingerprint: ff:e9:43:d7:93:42:4b:4f:7c:44:0c:1c:3d:64:8d:53:63:f3:4b:82:dc:87:aa:7a:9f:11:8f:c5:de:e1:01:f1 +-----BEGIN CERTIFICATE----- +MIIFbDCCA1SgAwIBAgIUVBa/O345lXGN0aoApYYNK496BU4wDQYJKoZIhvcNAQEL +BQAwTjELMAkGA1UEBhMCVVMxEjAQBgNVBAoMCUNvbW1TY29wZTErMCkGA1UEAwwi +Q29tbVNjb3BlIFB1YmxpYyBUcnVzdCBSU0EgUm9vdC0wMjAeFw0yMTA0MjgxNzE2 +NDNaFw00NjA0MjgxNzE2NDJaME4xCzAJBgNVBAYTAlVTMRIwEAYDVQQKDAlDb21t +U2NvcGUxKzApBgNVBAMMIkNvbW1TY29wZSBQdWJsaWMgVHJ1c3QgUlNBIFJvb3Qt +MDIwggIiMA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQDh+g77aAASyE3VrCLE +NQE7xVTlWXZjpX/rwcRqmL0yjReA61260WI9JSMZNRTpf4mnG2I81lDnNJUDMrG0 +kyI9p+Kx7eZ7Ti6Hmw0zdQreqjXnfuU2mKKuJZ6VszKWpCtYHu8//mI0SFHRtI1C +rWDaSWqVcN3SAOLMV2MCe5bdSZdbkk6V0/nLKR8YSvgBKtJjCW4k6YnS5cciTNxz +hkcAqg2Ijq6FfUrpuzNPDlJwnZXjfG2WWy09X6GDRl224yW4fKcZgBzqZUPckXk2 +LHR88mcGyYnJ27/aaL8j7dxrrSiDeS/sOKUNNwFnJ5rpM9kzXzehxfCrPfp4sOcs +n/Y+n2Dg70jpkEUeBVF4GiwSLFworA2iI540jwXmojPOEXcT1A6kHkIfhs1w/tku +FT0du7jyU1fbzMZ0KZwYszZ1OC4PVKH4kh+Jlk+71O6d6Ts2QrUKOyrUZHk2EOH5 +kQMreyBUzQ0ZGshBMjTRsJnhkB4BQDa1t/qp5Xd1pCKBXbCL5CcSD1SIxtuFdOa3 +wNemKfrb3vOTlycEVS8KbzfFPROvCgCpLIscgSjX74Yxqa7ybrjKaixUR9gqiC6v +wQcQeKwRoi9C8DfF8rhW3Q5iLc4tVn5V8qdE9isy9COoR+jUKgF4z2rDN6ieZdIs +5fq6M8EGRPbmz6UNp2YINIos8wIDAQABo0IwQDAPBgNVHRMBAf8EBTADAQH/MA4G +A1UdDwEB/wQEAwIBBjAdBgNVHQ4EFgQUR9DnsSL/nSz12Vdgs7GxcJXvYXowDQYJ +KoZIhvcNAQELBQADggIBAIZpsU0v6Z9PIpNojuQhmaPORVMbc0RTAIFhzTHjCLqB +KCh6krm2qMhDnscTJk3C2OVVnJJdUNjCK9v+5qiXz1I6JMNlZFxHMaNlNRPDk7n3 ++VGXu6TwYofF1gbTl4MgqX67tiHCpQ2EAOHyJxCDut0DgdXdaMNmEMjRdrSzbyme +APnCKfWxkxlSaRosTKCL4BWaMS/TiJVZbuXEs1DIFAhKm4sTg7GkcrI7djNB3Nyq +pgdvHSQSn8h2vS/ZjvQs7rfSOBAkNlEv41xdgSGn2rtO/+YHqP65DSdsu3BaVXoT +6fEqSWnHX4dXTEN5bTpl6TBcQe7rd6VzEojov32u5cSoHw2OHG1QAk8mGEPej1WF +sQs3BWDJVTkSBKEqz3EWnzZRSb9wO55nnPt7eck5HHisd5FUmrh1CoFSl+NmYWvt +PjgelmFV4ZFUjO2MJB+ByRCac5krFk5yAD9UG/iNuovnFNa2RU9g7Jauwy8CTl2d +lklyALKrdVwPaFsdZcJfMw8eD/A7hvWwTruc9+olBdytoptLFwG+Qt81IR2tq670 +v64fG9PiO/yzcnMcmyiQiRM9HcEARwmWmjgb3bHPDcK0RPOWlc4yOo80nOAXx17O +rg3bhzjlP1v9mxnhMUF6cKojawHhRUzNlM47ni3niAIi9G7oyOzWPPO5std3eqx7 +-----END CERTIFICATE----- + +# Issuer: CN=Telekom Security TLS ECC Root 2020 O=Deutsche Telekom Security GmbH +# Subject: CN=Telekom Security TLS ECC Root 2020 O=Deutsche Telekom Security GmbH +# Label: "Telekom Security TLS ECC Root 2020" +# Serial: 72082518505882327255703894282316633856 +# MD5 Fingerprint: c1:ab:fe:6a:10:2c:03:8d:bc:1c:22:32:c0:85:a7:fd +# SHA1 Fingerprint: c0:f8:96:c5:a9:3b:01:06:21:07:da:18:42:48:bc:e9:9d:88:d5:ec +# SHA256 Fingerprint: 57:8a:f4:de:d0:85:3f:4e:59:98:db:4a:ea:f9:cb:ea:8d:94:5f:60:b6:20:a3:8d:1a:3c:13:b2:bc:7b:a8:e1 +-----BEGIN CERTIFICATE----- +MIICQjCCAcmgAwIBAgIQNjqWjMlcsljN0AFdxeVXADAKBggqhkjOPQQDAzBjMQsw +CQYDVQQGEwJERTEnMCUGA1UECgweRGV1dHNjaGUgVGVsZWtvbSBTZWN1cml0eSBH +bWJIMSswKQYDVQQDDCJUZWxla29tIFNlY3VyaXR5IFRMUyBFQ0MgUm9vdCAyMDIw +MB4XDTIwMDgyNTA3NDgyMFoXDTQ1MDgyNTIzNTk1OVowYzELMAkGA1UEBhMCREUx +JzAlBgNVBAoMHkRldXRzY2hlIFRlbGVrb20gU2VjdXJpdHkgR21iSDErMCkGA1UE +AwwiVGVsZWtvbSBTZWN1cml0eSBUTFMgRUNDIFJvb3QgMjAyMDB2MBAGByqGSM49 +AgEGBSuBBAAiA2IABM6//leov9Wq9xCazbzREaK9Z0LMkOsVGJDZos0MKiXrPk/O +tdKPD/M12kOLAoC+b1EkHQ9rK8qfwm9QMuU3ILYg/4gND21Ju9sGpIeQkpT0CdDP +f8iAC8GXs7s1J8nCG6NCMEAwHQYDVR0OBBYEFONyzG6VmUex5rNhTNHLq+O6zd6f +MA8GA1UdEwEB/wQFMAMBAf8wDgYDVR0PAQH/BAQDAgEGMAoGCCqGSM49BAMDA2cA +MGQCMHVSi7ekEE+uShCLsoRbQuHmKjYC2qBuGT8lv9pZMo7k+5Dck2TOrbRBR2Di +z6fLHgIwN0GMZt9Ba9aDAEH9L1r3ULRn0SyocddDypwnJJGDSA3PzfdUga/sf+Rn +27iQ7t0l +-----END CERTIFICATE----- + +# Issuer: CN=Telekom Security TLS RSA Root 2023 O=Deutsche Telekom Security GmbH +# Subject: CN=Telekom Security TLS RSA Root 2023 O=Deutsche Telekom Security GmbH +# Label: "Telekom Security TLS RSA Root 2023" +# Serial: 44676229530606711399881795178081572759 +# MD5 Fingerprint: bf:5b:eb:54:40:cd:48:71:c4:20:8d:7d:de:0a:42:f2 +# SHA1 Fingerprint: 54:d3:ac:b3:bd:57:56:f6:85:9d:ce:e5:c3:21:e2:d4:ad:83:d0:93 +# SHA256 Fingerprint: ef:c6:5c:ad:bb:59:ad:b6:ef:e8:4d:a2:23:11:b3:56:24:b7:1b:3b:1e:a0:da:8b:66:55:17:4e:c8:97:86:46 +-----BEGIN CERTIFICATE----- +MIIFszCCA5ugAwIBAgIQIZxULej27HF3+k7ow3BXlzANBgkqhkiG9w0BAQwFADBj +MQswCQYDVQQGEwJERTEnMCUGA1UECgweRGV1dHNjaGUgVGVsZWtvbSBTZWN1cml0 +eSBHbWJIMSswKQYDVQQDDCJUZWxla29tIFNlY3VyaXR5IFRMUyBSU0EgUm9vdCAy +MDIzMB4XDTIzMDMyODEyMTY0NVoXDTQ4MDMyNzIzNTk1OVowYzELMAkGA1UEBhMC +REUxJzAlBgNVBAoMHkRldXRzY2hlIFRlbGVrb20gU2VjdXJpdHkgR21iSDErMCkG +A1UEAwwiVGVsZWtvbSBTZWN1cml0eSBUTFMgUlNBIFJvb3QgMjAyMzCCAiIwDQYJ +KoZIhvcNAQEBBQADggIPADCCAgoCggIBAO01oYGA88tKaVvC+1GDrib94W7zgRJ9 +cUD/h3VCKSHtgVIs3xLBGYSJwb3FKNXVS2xE1kzbB5ZKVXrKNoIENqil/Cf2SfHV +cp6R+SPWcHu79ZvB7JPPGeplfohwoHP89v+1VmLhc2o0mD6CuKyVU/QBoCcHcqMA +U6DksquDOFczJZSfvkgdmOGjup5czQRxUX11eKvzWarE4GC+j4NSuHUaQTXtvPM6 +Y+mpFEXX5lLRbtLevOP1Czvm4MS9Q2QTps70mDdsipWol8hHD/BeEIvnHRz+sTug +BTNoBUGCwQMrAcjnj02r6LX2zWtEtefdi+zqJbQAIldNsLGyMcEWzv/9FIS3R/qy +8XDe24tsNlikfLMR0cN3f1+2JeANxdKz+bi4d9s3cXFH42AYTyS2dTd4uaNir73J +co4vzLuu2+QVUhkHM/tqty1LkCiCc/4YizWN26cEar7qwU02OxY2kTLvtkCJkUPg +8qKrBC7m8kwOFjQgrIfBLX7JZkcXFBGk8/ehJImr2BrIoVyxo/eMbcgByU/J7MT8 +rFEz0ciD0cmfHdRHNCk+y7AO+oMLKFjlKdw/fKifybYKu6boRhYPluV75Gp6SG12 +mAWl3G0eQh5C2hrgUve1g8Aae3g1LDj1H/1Joy7SWWO/gLCMk3PLNaaZlSJhZQNg ++y+TS/qanIA7AgMBAAGjYzBhMA4GA1UdDwEB/wQEAwIBBjAdBgNVHQ4EFgQUtqeX +gj10hZv3PJ+TmpV5dVKMbUcwDwYDVR0TAQH/BAUwAwEB/zAfBgNVHSMEGDAWgBS2 +p5eCPXSFm/c8n5OalXl1UoxtRzANBgkqhkiG9w0BAQwFAAOCAgEAqMxhpr51nhVQ +pGv7qHBFfLp+sVr8WyP6Cnf4mHGCDG3gXkaqk/QeoMPhk9tLrbKmXauw1GLLXrtm +9S3ul0A8Yute1hTWjOKWi0FpkzXmuZlrYrShF2Y0pmtjxrlO8iLpWA1WQdH6DErw +M807u20hOq6OcrXDSvvpfeWxm4bu4uB9tPcy/SKE8YXJN3nptT+/XOR0so8RYgDd +GGah2XsjX/GO1WfoVNpbOms2b/mBsTNHM3dA+VKq3dSDz4V4mZqTuXNnQkYRIer+ +CqkbGmVps4+uFrb2S1ayLfmlyOw7YqPta9BO1UAJpB+Y1zqlklkg5LB9zVtzaL1t +xKITDmcZuI1CfmwMmm6gJC3VRRvcxAIU/oVbZZfKTpBQCHpCNfnqwmbU+AGuHrS+ +w6jv/naaoqYfRvaE7fzbzsQCzndILIyy7MMAo+wsVRjBfhnu4S/yrYObnqsZ38aK +L4x35bcF7DvB7L6Gs4a8wPfc5+pbrrLMtTWGS9DiP7bY+A4A7l3j941Y/8+LN+lj +X273CXE2whJdV/LItM3z7gLfEdxquVeEHVlNjM7IDiPCtyaaEBRx/pOyiriA8A4Q +ntOoUAw3gi/q4Iqd4Sw5/7W0cwDk90imc6y/st53BIe0o82bNSQ3+pCTE4FCxpgm +dTdmQRCsu/WU48IxK63nI1bMNSWSs1A= +-----END CERTIFICATE----- + +# Issuer: CN=FIRMAPROFESIONAL CA ROOT-A WEB O=Firmaprofesional SA +# Subject: CN=FIRMAPROFESIONAL CA ROOT-A WEB O=Firmaprofesional SA +# Label: "FIRMAPROFESIONAL CA ROOT-A WEB" +# Serial: 65916896770016886708751106294915943533 +# MD5 Fingerprint: 82:b2:ad:45:00:82:b0:66:63:f8:5f:c3:67:4e:ce:a3 +# SHA1 Fingerprint: a8:31:11:74:a6:14:15:0d:ca:77:dd:0e:e4:0c:5d:58:fc:a0:72:a5 +# SHA256 Fingerprint: be:f2:56:da:f2:6e:9c:69:bd:ec:16:02:35:97:98:f3:ca:f7:18:21:a0:3e:01:82:57:c5:3c:65:61:7f:3d:4a +-----BEGIN CERTIFICATE----- +MIICejCCAgCgAwIBAgIQMZch7a+JQn81QYehZ1ZMbTAKBggqhkjOPQQDAzBuMQsw +CQYDVQQGEwJFUzEcMBoGA1UECgwTRmlybWFwcm9mZXNpb25hbCBTQTEYMBYGA1UE +YQwPVkFURVMtQTYyNjM0MDY4MScwJQYDVQQDDB5GSVJNQVBST0ZFU0lPTkFMIENB +IFJPT1QtQSBXRUIwHhcNMjIwNDA2MDkwMTM2WhcNNDcwMzMxMDkwMTM2WjBuMQsw +CQYDVQQGEwJFUzEcMBoGA1UECgwTRmlybWFwcm9mZXNpb25hbCBTQTEYMBYGA1UE +YQwPVkFURVMtQTYyNjM0MDY4MScwJQYDVQQDDB5GSVJNQVBST0ZFU0lPTkFMIENB +IFJPT1QtQSBXRUIwdjAQBgcqhkjOPQIBBgUrgQQAIgNiAARHU+osEaR3xyrq89Zf +e9MEkVz6iMYiuYMQYneEMy3pA4jU4DP37XcsSmDq5G+tbbT4TIqk5B/K6k84Si6C +cyvHZpsKjECcfIr28jlgst7L7Ljkb+qbXbdTkBgyVcUgt5SjYzBhMA8GA1UdEwEB +/wQFMAMBAf8wHwYDVR0jBBgwFoAUk+FDY1w8ndYn81LsF7Kpryz3dvgwHQYDVR0O +BBYEFJPhQ2NcPJ3WJ/NS7Beyqa8s93b4MA4GA1UdDwEB/wQEAwIBBjAKBggqhkjO +PQQDAwNoADBlAjAdfKR7w4l1M+E7qUW/Runpod3JIha3RxEL2Jq68cgLcFBTApFw +hVmpHqTm6iMxoAACMQD94vizrxa5HnPEluPBMBnYfubDl94cT7iJLzPrSA8Z94dG +XSaQpYXFuXqUPoeovQA= +-----END CERTIFICATE----- + +# Issuer: CN=TWCA CYBER Root CA O=TAIWAN-CA OU=Root CA +# Subject: CN=TWCA CYBER Root CA O=TAIWAN-CA OU=Root CA +# Label: "TWCA CYBER Root CA" +# Serial: 85076849864375384482682434040119489222 +# MD5 Fingerprint: 0b:33:a0:97:52:95:d4:a9:fd:bb:db:6e:a3:55:5b:51 +# SHA1 Fingerprint: f6:b1:1c:1a:83:38:e9:7b:db:b3:a8:c8:33:24:e0:2d:9c:7f:26:66 +# SHA256 Fingerprint: 3f:63:bb:28:14:be:17:4e:c8:b6:43:9c:f0:8d:6d:56:f0:b7:c4:05:88:3a:56:48:a3:34:42:4d:6b:3e:c5:58 +-----BEGIN CERTIFICATE----- +MIIFjTCCA3WgAwIBAgIQQAE0jMIAAAAAAAAAATzyxjANBgkqhkiG9w0BAQwFADBQ +MQswCQYDVQQGEwJUVzESMBAGA1UEChMJVEFJV0FOLUNBMRAwDgYDVQQLEwdSb290 +IENBMRswGQYDVQQDExJUV0NBIENZQkVSIFJvb3QgQ0EwHhcNMjIxMTIyMDY1NDI5 +WhcNNDcxMTIyMTU1OTU5WjBQMQswCQYDVQQGEwJUVzESMBAGA1UEChMJVEFJV0FO +LUNBMRAwDgYDVQQLEwdSb290IENBMRswGQYDVQQDExJUV0NBIENZQkVSIFJvb3Qg +Q0EwggIiMA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQDG+Moe2Qkgfh1sTs6P +40czRJzHyWmqOlt47nDSkvgEs1JSHWdyKKHfi12VCv7qze33Kc7wb3+szT3vsxxF +avcokPFhV8UMxKNQXd7UtcsZyoC5dc4pztKFIuwCY8xEMCDa6pFbVuYdHNWdZsc/ +34bKS1PE2Y2yHer43CdTo0fhYcx9tbD47nORxc5zb87uEB8aBs/pJ2DFTxnk684i +JkXXYJndzk834H/nY62wuFm40AZoNWDTNq5xQwTxaWV4fPMf88oon1oglWa0zbfu +j3ikRRjpJi+NmykosaS3Om251Bw4ckVYsV7r8Cibt4LK/c/WMw+f+5eesRycnupf +Xtuq3VTpMCEobY5583WSjCb+3MX2w7DfRFlDo7YDKPYIMKoNM+HvnKkHIuNZW0CP +2oi3aQiotyMuRAlZN1vH4xfyIutuOVLF3lSnmMlLIJXcRolftBL5hSmO68gnFSDA +S9TMfAxsNAwmmyYxpjyn9tnQS6Jk/zuZQXLB4HCX8SS7K8R0IrGsayIyJNN4KsDA +oS/xUgXJP+92ZuJF2A09rZXIx4kmyA+upwMu+8Ff+iDhcK2wZSA3M2Cw1a/XDBzC +kHDXShi8fgGwsOsVHkQGzaRP6AzRwyAQ4VRlnrZR0Bp2a0JaWHY06rc3Ga4udfmW +5cFZ95RXKSWNOkyrTZpB0F8mAwIDAQABo2MwYTAOBgNVHQ8BAf8EBAMCAQYwDwYD +VR0TAQH/BAUwAwEB/zAfBgNVHSMEGDAWgBSdhWEUfMFib5do5E83QOGt4A1WNzAd +BgNVHQ4EFgQUnYVhFHzBYm+XaORPN0DhreANVjcwDQYJKoZIhvcNAQEMBQADggIB +AGSPesRiDrWIzLjHhg6hShbNcAu3p4ULs3a2D6f/CIsLJc+o1IN1KriWiLb73y0t +tGlTITVX1olNc79pj3CjYcya2x6a4CD4bLubIp1dhDGaLIrdaqHXKGnK/nZVekZn +68xDiBaiA9a5F/gZbG0jAn/xX9AKKSM70aoK7akXJlQKTcKlTfjF/biBzysseKNn +TKkHmvPfXvt89YnNdJdhEGoHK4Fa0o635yDRIG4kqIQnoVesqlVYL9zZyvpoBJ7t +RCT5dEA7IzOrg1oYJkK2bVS1FmAwbLGg+LhBoF1JSdJlBTrq/p1hvIbZv97Tujqx +f36SNI7JAG7cmL3c7IAFrQI932XtCwP39xaEBDG6k5TY8hL4iuO/Qq+n1M0RFxbI +Qh0UqEL20kCGoE8jypZFVmAGzbdVAaYBlGX+bgUJurSkquLvWL69J1bY73NxW0Qz +8ppy6rBePm6pUlvscG21h483XjyMnM7k8M4MZ0HMzvaAq07MTFb1wWFZk7Q+ptq4 +NxKfKjLji7gh7MMrZQzvIt6IKTtM1/r+t+FHvpw+PoP7UV31aPcuIYXcv/Fa4nzX +xeSDwWrruoBa3lwtcHb4yOWHh8qgnaHlIhInD0Q9HWzq1MKLL295q39QpsQZp6F6 +t5b5wR9iWqJDB0BeJsas7a5wFsWqynKKTbDPAYsDP27X +-----END CERTIFICATE----- + +# Issuer: CN=SecureSign Root CA12 O=Cybertrust Japan Co., Ltd. +# Subject: CN=SecureSign Root CA12 O=Cybertrust Japan Co., Ltd. +# Label: "SecureSign Root CA12" +# Serial: 587887345431707215246142177076162061960426065942 +# MD5 Fingerprint: c6:89:ca:64:42:9b:62:08:49:0b:1e:7f:e9:07:3d:e8 +# SHA1 Fingerprint: 7a:22:1e:3d:de:1b:06:ac:9e:c8:47:70:16:8e:3c:e5:f7:6b:06:f4 +# SHA256 Fingerprint: 3f:03:4b:b5:70:4d:44:b2:d0:85:45:a0:20:57:de:93:eb:f3:90:5f:ce:72:1a:cb:c7:30:c0:6d:da:ee:90:4e +-----BEGIN CERTIFICATE----- +MIIDcjCCAlqgAwIBAgIUZvnHwa/swlG07VOX5uaCwysckBYwDQYJKoZIhvcNAQEL +BQAwUTELMAkGA1UEBhMCSlAxIzAhBgNVBAoTGkN5YmVydHJ1c3QgSmFwYW4gQ28u +LCBMdGQuMR0wGwYDVQQDExRTZWN1cmVTaWduIFJvb3QgQ0ExMjAeFw0yMDA0MDgw +NTM2NDZaFw00MDA0MDgwNTM2NDZaMFExCzAJBgNVBAYTAkpQMSMwIQYDVQQKExpD +eWJlcnRydXN0IEphcGFuIENvLiwgTHRkLjEdMBsGA1UEAxMUU2VjdXJlU2lnbiBS +b290IENBMTIwggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAwggEKAoIBAQC6OcE3emhF +KxS06+QT61d1I02PJC0W6K6OyX2kVzsqdiUzg2zqMoqUm048luT9Ub+ZyZN+v/mt +p7JIKwccJ/VMvHASd6SFVLX9kHrko+RRWAPNEHl57muTH2SOa2SroxPjcf59q5zd +J1M3s6oYwlkm7Fsf0uZlfO+TvdhYXAvA42VvPMfKWeP+bl+sg779XSVOKik71gur +FzJ4pOE+lEa+Ym6b3kaosRbnhW70CEBFEaCeVESE99g2zvVQR9wsMJvuwPWW0v4J +hscGWa5Pro4RmHvzC1KqYiaqId+OJTN5lxZJjfU+1UefNzFJM3IFTQy2VYzxV4+K +h9GtxRESOaCtAgMBAAGjQjBAMA8GA1UdEwEB/wQFMAMBAf8wDgYDVR0PAQH/BAQD +AgEGMB0GA1UdDgQWBBRXNPN0zwRL1SXm8UC2LEzZLemgrTANBgkqhkiG9w0BAQsF +AAOCAQEAPrvbFxbS8hQBICw4g0utvsqFepq2m2um4fylOqyttCg6r9cBg0krY6Ld +mmQOmFxv3Y67ilQiLUoT865AQ9tPkbeGGuwAtEGBpE/6aouIs3YIcipJQMPTw4WJ +mBClnW8Zt7vPemVV2zfrPIpyMpcemik+rY3moxtt9XUa5rBouVui7mlHJzWhhpmA +8zNL4WukJsPvdFlseqJkth5Ew1DgDzk9qTPxpfPSvWKErI4cqc1avTc7bgoitPQV +55FYxTpE05Uo2cBl6XLK0A+9H7MV2anjpEcJnuDLN/v9vZfVvhgaaaI5gdka9at/ +yOPiZwud9AzqVN/Ssq+xIvEg37xEHA== +-----END CERTIFICATE----- + +# Issuer: CN=SecureSign Root CA14 O=Cybertrust Japan Co., Ltd. +# Subject: CN=SecureSign Root CA14 O=Cybertrust Japan Co., Ltd. +# Label: "SecureSign Root CA14" +# Serial: 575790784512929437950770173562378038616896959179 +# MD5 Fingerprint: 71:0d:72:fa:92:19:65:5e:89:04:ac:16:33:f0:bc:d5 +# SHA1 Fingerprint: dd:50:c0:f7:79:b3:64:2e:74:a2:b8:9d:9f:d3:40:dd:bb:f0:f2:4f +# SHA256 Fingerprint: 4b:00:9c:10:34:49:4f:9a:b5:6b:ba:3b:a1:d6:27:31:fc:4d:20:d8:95:5a:dc:ec:10:a9:25:60:72:61:e3:38 +-----BEGIN CERTIFICATE----- +MIIFcjCCA1qgAwIBAgIUZNtaDCBO6Ncpd8hQJ6JaJ90t8sswDQYJKoZIhvcNAQEM +BQAwUTELMAkGA1UEBhMCSlAxIzAhBgNVBAoTGkN5YmVydHJ1c3QgSmFwYW4gQ28u +LCBMdGQuMR0wGwYDVQQDExRTZWN1cmVTaWduIFJvb3QgQ0ExNDAeFw0yMDA0MDgw +NzA2MTlaFw00NTA0MDgwNzA2MTlaMFExCzAJBgNVBAYTAkpQMSMwIQYDVQQKExpD +eWJlcnRydXN0IEphcGFuIENvLiwgTHRkLjEdMBsGA1UEAxMUU2VjdXJlU2lnbiBS +b290IENBMTQwggIiMA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQDF0nqh1oq/ +FjHQmNE6lPxauG4iwWL3pwon71D2LrGeaBLwbCRjOfHw3xDG3rdSINVSW0KZnvOg +vlIfX8xnbacuUKLBl422+JX1sLrcneC+y9/3OPJH9aaakpUqYllQC6KxNedlsmGy +6pJxaeQp8E+BgQQ8sqVb1MWoWWd7VRxJq3qdwudzTe/NCcLEVxLbAQ4jeQkHO6Lo +/IrPj8BGJJw4J+CDnRugv3gVEOuGTgpa/d/aLIJ+7sr2KeH6caH3iGicnPCNvg9J +kdjqOvn90Ghx2+m1K06Ckm9mH+Dw3EzsytHqunQG+bOEkJTRX45zGRBdAuVwpcAQ +0BB8b8VYSbSwbprafZX1zNoCr7gsfXmPvkPx+SgojQlD+Ajda8iLLCSxjVIHvXib +y8posqTdDEx5YMaZ0ZPxMBoH064iwurO8YQJzOAUbn8/ftKChazcqRZOhaBgy/ac +18izju3Gm5h1DVXoX+WViwKkrkMpKBGk5hIwAUt1ax5mnXkvpXYvHUC0bcl9eQjs +0Wq2XSqypWa9a4X0dFbD9ed1Uigspf9mR6XU/v6eVL9lfgHWMI+lNpyiUBzuOIAB +SMbHdPTGrMNASRZhdCyvjG817XsYAFs2PJxQDcqSMxDxJklt33UkN4Ii1+iW/RVL +ApY+B3KVfqs9TC7XyvDf4Fg/LS8EmjijAQIDAQABo0IwQDAPBgNVHRMBAf8EBTAD +AQH/MA4GA1UdDwEB/wQEAwIBBjAdBgNVHQ4EFgQUBpOjCl4oaTeqYR3r6/wtbyPk +86AwDQYJKoZIhvcNAQEMBQADggIBAJaAcgkGfpzMkwQWu6A6jZJOtxEaCnFxEM0E +rX+lRVAQZk5KQaID2RFPeje5S+LGjzJmdSX7684/AykmjbgWHfYfM25I5uj4V7Ib +ed87hwriZLoAymzvftAj63iP/2SbNDefNWWipAA9EiOWWF3KY4fGoweITedpdopT +zfFP7ELyk+OZpDc8h7hi2/DsHzc/N19DzFGdtfCXwreFamgLRB7lUe6TzktuhsHS +DCRZNhqfLJGP4xjblJUK7ZGqDpncllPjYYPGFrojutzdfhrGe0K22VoF3Jpf1d+4 +2kd92jjbrDnVHmtsKheMYc2xbXIBw8MgAGJoFjHVdqqGuw6qnsb58Nn4DSEC5MUo +FlkRudlpcyqSeLiSV5sI8jrlL5WwWLdrIBRtFO8KvH7YVdiI2i/6GaX7i+B/OfVy +K4XELKzvGUWSTLNhB9xNH27SgRNcmvMSZ4PPmz+Ln52kuaiWA3rF7iDeM9ovnhp6 +dB7h7sxaOgTdsxoEqBRjrLdHEoOabPXm6RUVkRqEGQ6UROcSjiVbgGcZ3GOTEAtl +Lor6CZpO2oYofaphNdgOpygau1LgePhsumywbrmHXumZNTfxPWQrqaA0k89jL9WB +365jJ6UeTo3cKXhZ+PmhIIynJkBugnLNeLLIjzwec+fBH7/PzqUqm9tEZDKgu39c +JRNItX+S +-----END CERTIFICATE----- + +# Issuer: CN=SecureSign Root CA15 O=Cybertrust Japan Co., Ltd. +# Subject: CN=SecureSign Root CA15 O=Cybertrust Japan Co., Ltd. +# Label: "SecureSign Root CA15" +# Serial: 126083514594751269499665114766174399806381178503 +# MD5 Fingerprint: 13:30:fc:c4:62:a6:a9:de:b5:c1:68:af:b5:d2:31:47 +# SHA1 Fingerprint: cb:ba:83:c8:c1:5a:5d:f1:f9:73:6f:ca:d7:ef:28:13:06:4a:07:7d +# SHA256 Fingerprint: e7:78:f0:f0:95:fe:84:37:29:cd:1a:00:82:17:9e:53:14:a9:c2:91:44:28:05:e1:fb:1d:8f:b6:b8:88:6c:3a +-----BEGIN CERTIFICATE----- +MIICIzCCAamgAwIBAgIUFhXHw9hJp75pDIqI7fBw+d23PocwCgYIKoZIzj0EAwMw +UTELMAkGA1UEBhMCSlAxIzAhBgNVBAoTGkN5YmVydHJ1c3QgSmFwYW4gQ28uLCBM +dGQuMR0wGwYDVQQDExRTZWN1cmVTaWduIFJvb3QgQ0ExNTAeFw0yMDA0MDgwODMy +NTZaFw00NTA0MDgwODMyNTZaMFExCzAJBgNVBAYTAkpQMSMwIQYDVQQKExpDeWJl +cnRydXN0IEphcGFuIENvLiwgTHRkLjEdMBsGA1UEAxMUU2VjdXJlU2lnbiBSb290 +IENBMTUwdjAQBgcqhkjOPQIBBgUrgQQAIgNiAAQLUHSNZDKZmbPSYAi4Io5GdCx4 +wCtELW1fHcmuS1Iggz24FG1Th2CeX2yF2wYUleDHKP+dX+Sq8bOLbe1PL0vJSpSR +ZHX+AezB2Ot6lHhWGENfa4HL9rzatAy2KZMIaY+jQjBAMA8GA1UdEwEB/wQFMAMB +Af8wDgYDVR0PAQH/BAQDAgEGMB0GA1UdDgQWBBTrQciu/NWeUUj1vYv0hyCTQSvT +9DAKBggqhkjOPQQDAwNoADBlAjEA2S6Jfl5OpBEHvVnCB96rMjhTKkZEBhd6zlHp +4P9mLQlO4E/0BdGF9jVg3PVys0Z9AjBEmEYagoUeYWmJSwdLZrWeqrqgHkHZAXQ6 +bkU6iYAZezKYVWOr62Nuk22rGwlgMU4= +-----END CERTIFICATE----- diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/core.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/core.py index 5c67600..70e0c3b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/core.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/core.py @@ -5,8 +5,11 @@ certifi.py This module returns the installation location of cacert.pem or its contents. """ import sys +import atexit + +def exit_cacert_ctx() -> None: + _CACERT_CTX.__exit__(None, None, None) # type: ignore[union-attr] -DEBIAN_CA_CERTS_PATH = '/etc/ssl/certs/ca-certificates.crt' if sys.version_info >= (3, 11): @@ -36,6 +39,7 @@ if sys.version_info >= (3, 11): # we will also store that at the global level as well. _CACERT_CTX = as_file(files("pip._vendor.certifi").joinpath("cacert.pem")) _CACERT_PATH = str(_CACERT_CTX.__enter__()) + atexit.register(exit_cacert_ctx) return _CACERT_PATH @@ -71,6 +75,7 @@ elif sys.version_info >= (3, 7): # we will also store that at the global level as well. _CACERT_CTX = get_path("pip._vendor.certifi", "cacert.pem") _CACERT_PATH = str(_CACERT_CTX.__enter__()) + atexit.register(exit_cacert_ctx) return _CACERT_PATH @@ -107,13 +112,3 @@ else: def contents() -> str: return read_text("pip._vendor.certifi", "cacert.pem", encoding="ascii") - - -# Debian: Use system CA certs: -def where() -> str: - return DEBIAN_CA_CERTS_PATH - - -def contents() -> str: - with open(where(), "r", encoding="ascii") as data: - return data.read() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/certifi/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__init__.py deleted file mode 100644 index fe58162..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__init__.py +++ /dev/null @@ -1,115 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import List, Union - -from .charsetgroupprober import CharSetGroupProber -from .charsetprober import CharSetProber -from .enums import InputState -from .resultdict import ResultDict -from .universaldetector import UniversalDetector -from .version import VERSION, __version__ - -__all__ = ["UniversalDetector", "detect", "detect_all", "__version__", "VERSION"] - - -def detect( - byte_str: Union[bytes, bytearray], should_rename_legacy: bool = False -) -> ResultDict: - """ - Detect the encoding of the given byte string. - - :param byte_str: The byte sequence to examine. - :type byte_str: ``bytes`` or ``bytearray`` - :param should_rename_legacy: Should we rename legacy encodings - to their more modern equivalents? - :type should_rename_legacy: ``bool`` - """ - if not isinstance(byte_str, bytearray): - if not isinstance(byte_str, bytes): - raise TypeError( - f"Expected object of type bytes or bytearray, got: {type(byte_str)}" - ) - byte_str = bytearray(byte_str) - detector = UniversalDetector(should_rename_legacy=should_rename_legacy) - detector.feed(byte_str) - return detector.close() - - -def detect_all( - byte_str: Union[bytes, bytearray], - ignore_threshold: bool = False, - should_rename_legacy: bool = False, -) -> List[ResultDict]: - """ - Detect all the possible encodings of the given byte string. - - :param byte_str: The byte sequence to examine. - :type byte_str: ``bytes`` or ``bytearray`` - :param ignore_threshold: Include encodings that are below - ``UniversalDetector.MINIMUM_THRESHOLD`` - in results. - :type ignore_threshold: ``bool`` - :param should_rename_legacy: Should we rename legacy encodings - to their more modern equivalents? - :type should_rename_legacy: ``bool`` - """ - if not isinstance(byte_str, bytearray): - if not isinstance(byte_str, bytes): - raise TypeError( - f"Expected object of type bytes or bytearray, got: {type(byte_str)}" - ) - byte_str = bytearray(byte_str) - - detector = UniversalDetector(should_rename_legacy=should_rename_legacy) - detector.feed(byte_str) - detector.close() - - if detector.input_state == InputState.HIGH_BYTE: - results: List[ResultDict] = [] - probers: List[CharSetProber] = [] - for prober in detector.charset_probers: - if isinstance(prober, CharSetGroupProber): - probers.extend(p for p in prober.probers) - else: - probers.append(prober) - for prober in probers: - if ignore_threshold or prober.get_confidence() > detector.MINIMUM_THRESHOLD: - charset_name = prober.charset_name or "" - lower_charset_name = charset_name.lower() - # Use Windows encoding name instead of ISO-8859 if we saw any - # extra Windows-specific bytes - if lower_charset_name.startswith("iso-8859") and detector.has_win_bytes: - charset_name = detector.ISO_WIN_MAP.get( - lower_charset_name, charset_name - ) - # Rename legacy encodings with superset encodings if asked - if should_rename_legacy: - charset_name = detector.LEGACY_MAP.get( - charset_name.lower(), charset_name - ) - results.append( - { - "encoding": charset_name, - "confidence": prober.get_confidence(), - "language": prober.language, - } - ) - if len(results) > 0: - return sorted(results, key=lambda result: -result["confidence"]) - - return [detector.result] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 065de5c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/big5freq.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/big5freq.cpython-312.pyc deleted file mode 100644 index 26e461a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/big5freq.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/big5prober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/big5prober.cpython-312.pyc deleted file mode 100644 index 7fd4679..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/big5prober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/chardistribution.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/chardistribution.cpython-312.pyc deleted file mode 100644 index 5b5483b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/chardistribution.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/charsetgroupprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/charsetgroupprober.cpython-312.pyc deleted file mode 100644 index 14b5a75..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/charsetgroupprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/charsetprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/charsetprober.cpython-312.pyc deleted file mode 100644 index 78e2728..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/charsetprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/codingstatemachine.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/codingstatemachine.cpython-312.pyc deleted file mode 100644 index 9ebcc00..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/codingstatemachine.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/codingstatemachinedict.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/codingstatemachinedict.cpython-312.pyc deleted file mode 100644 index 2e02feb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/codingstatemachinedict.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/cp949prober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/cp949prober.cpython-312.pyc deleted file mode 100644 index d26ec41..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/cp949prober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/enums.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/enums.cpython-312.pyc deleted file mode 100644 index 65f232a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/enums.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/escprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/escprober.cpython-312.pyc deleted file mode 100644 index 9491ce3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/escprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/escsm.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/escsm.cpython-312.pyc deleted file mode 100644 index 6b72ff2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/escsm.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/eucjpprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/eucjpprober.cpython-312.pyc deleted file mode 100644 index 5dca828..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/eucjpprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euckrfreq.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euckrfreq.cpython-312.pyc deleted file mode 100644 index 5e01aa8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euckrfreq.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euckrprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euckrprober.cpython-312.pyc deleted file mode 100644 index 0467e03..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euckrprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euctwfreq.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euctwfreq.cpython-312.pyc deleted file mode 100644 index 4cd2cb7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euctwfreq.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euctwprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euctwprober.cpython-312.pyc deleted file mode 100644 index 50aa7a8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/euctwprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/gb2312freq.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/gb2312freq.cpython-312.pyc deleted file mode 100644 index 2bc37e2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/gb2312freq.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/gb2312prober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/gb2312prober.cpython-312.pyc deleted file mode 100644 index de9c559..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/gb2312prober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/hebrewprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/hebrewprober.cpython-312.pyc deleted file mode 100644 index 3ca9d28..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/hebrewprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/jisfreq.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/jisfreq.cpython-312.pyc deleted file mode 100644 index 936016b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/jisfreq.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/johabfreq.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/johabfreq.cpython-312.pyc deleted file mode 100644 index f0bde88..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/johabfreq.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/johabprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/johabprober.cpython-312.pyc deleted file mode 100644 index 9213719..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/johabprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/jpcntx.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/jpcntx.cpython-312.pyc deleted file mode 100644 index b68fd65..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/jpcntx.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langbulgarianmodel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langbulgarianmodel.cpython-312.pyc deleted file mode 100644 index c5d4ec8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langbulgarianmodel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langgreekmodel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langgreekmodel.cpython-312.pyc deleted file mode 100644 index c1ba261..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langgreekmodel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langhebrewmodel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langhebrewmodel.cpython-312.pyc deleted file mode 100644 index d4dccda..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langhebrewmodel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langhungarianmodel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langhungarianmodel.cpython-312.pyc deleted file mode 100644 index 299e63e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langhungarianmodel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langrussianmodel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langrussianmodel.cpython-312.pyc deleted file mode 100644 index 38c0c1e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langrussianmodel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langthaimodel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langthaimodel.cpython-312.pyc deleted file mode 100644 index d0253f0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langthaimodel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langturkishmodel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langturkishmodel.cpython-312.pyc deleted file mode 100644 index ff79965..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/langturkishmodel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/latin1prober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/latin1prober.cpython-312.pyc deleted file mode 100644 index 9793fe2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/latin1prober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/macromanprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/macromanprober.cpython-312.pyc deleted file mode 100644 index 4937186..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/macromanprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcharsetprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcharsetprober.cpython-312.pyc deleted file mode 100644 index 594b424..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcharsetprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcsgroupprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcsgroupprober.cpython-312.pyc deleted file mode 100644 index 627a9c8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcsgroupprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcssm.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcssm.cpython-312.pyc deleted file mode 100644 index 71f2e75..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/mbcssm.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/resultdict.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/resultdict.cpython-312.pyc deleted file mode 100644 index 5e44879..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/resultdict.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sbcharsetprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sbcharsetprober.cpython-312.pyc deleted file mode 100644 index d1967f9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sbcharsetprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sbcsgroupprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sbcsgroupprober.cpython-312.pyc deleted file mode 100644 index 31e5b6a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sbcsgroupprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sjisprober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sjisprober.cpython-312.pyc deleted file mode 100644 index 26f5d13..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/sjisprober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/universaldetector.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/universaldetector.cpython-312.pyc deleted file mode 100644 index 7615cd3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/universaldetector.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/utf1632prober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/utf1632prober.cpython-312.pyc deleted file mode 100644 index 333b1f0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/utf1632prober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/utf8prober.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/utf8prober.cpython-312.pyc deleted file mode 100644 index b851bda..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/utf8prober.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/version.cpython-312.pyc deleted file mode 100644 index 9e851fb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/__pycache__/version.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/big5freq.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/big5freq.py deleted file mode 100644 index 87d9f97..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/big5freq.py +++ /dev/null @@ -1,386 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -# Big5 frequency table -# by Taiwan's Mandarin Promotion Council -# -# -# 128 --> 0.42261 -# 256 --> 0.57851 -# 512 --> 0.74851 -# 1024 --> 0.89384 -# 2048 --> 0.97583 -# -# Ideal Distribution Ratio = 0.74851/(1-0.74851) =2.98 -# Random Distribution Ration = 512/(5401-512)=0.105 -# -# Typical Distribution Ratio about 25% of Ideal one, still much higher than RDR - -BIG5_TYPICAL_DISTRIBUTION_RATIO = 0.75 - -# Char to FreqOrder table -BIG5_TABLE_SIZE = 5376 -# fmt: off -BIG5_CHAR_TO_FREQ_ORDER = ( - 1,1801,1506, 255,1431, 198, 9, 82, 6,5008, 177, 202,3681,1256,2821, 110, # 16 -3814, 33,3274, 261, 76, 44,2114, 16,2946,2187,1176, 659,3971, 26,3451,2653, # 32 -1198,3972,3350,4202, 410,2215, 302, 590, 361,1964, 8, 204, 58,4510,5009,1932, # 48 - 63,5010,5011, 317,1614, 75, 222, 159,4203,2417,1480,5012,3555,3091, 224,2822, # 64 -3682, 3, 10,3973,1471, 29,2787,1135,2866,1940, 873, 130,3275,1123, 312,5013, # 80 -4511,2052, 507, 252, 682,5014, 142,1915, 124, 206,2947, 34,3556,3204, 64, 604, # 96 -5015,2501,1977,1978, 155,1991, 645, 641,1606,5016,3452, 337, 72, 406,5017, 80, # 112 - 630, 238,3205,1509, 263, 939,1092,2654, 756,1440,1094,3453, 449, 69,2987, 591, # 128 - 179,2096, 471, 115,2035,1844, 60, 50,2988, 134, 806,1869, 734,2036,3454, 180, # 144 - 995,1607, 156, 537,2907, 688,5018, 319,1305, 779,2145, 514,2379, 298,4512, 359, # 160 -2502, 90,2716,1338, 663, 11, 906,1099,2553, 20,2441, 182, 532,1716,5019, 732, # 176 -1376,4204,1311,1420,3206, 25,2317,1056, 113, 399, 382,1950, 242,3455,2474, 529, # 192 -3276, 475,1447,3683,5020, 117, 21, 656, 810,1297,2300,2334,3557,5021, 126,4205, # 208 - 706, 456, 150, 613,4513, 71,1118,2037,4206, 145,3092, 85, 835, 486,2115,1246, # 224 -1426, 428, 727,1285,1015, 800, 106, 623, 303,1281,5022,2128,2359, 347,3815, 221, # 240 -3558,3135,5023,1956,1153,4207, 83, 296,1199,3093, 192, 624, 93,5024, 822,1898, # 256 -2823,3136, 795,2065, 991,1554,1542,1592, 27, 43,2867, 859, 139,1456, 860,4514, # 272 - 437, 712,3974, 164,2397,3137, 695, 211,3037,2097, 195,3975,1608,3559,3560,3684, # 288 -3976, 234, 811,2989,2098,3977,2233,1441,3561,1615,2380, 668,2077,1638, 305, 228, # 304 -1664,4515, 467, 415,5025, 262,2099,1593, 239, 108, 300, 200,1033, 512,1247,2078, # 320 -5026,5027,2176,3207,3685,2682, 593, 845,1062,3277, 88,1723,2038,3978,1951, 212, # 336 - 266, 152, 149, 468,1899,4208,4516, 77, 187,5028,3038, 37, 5,2990,5029,3979, # 352 -5030,5031, 39,2524,4517,2908,3208,2079, 55, 148, 74,4518, 545, 483,1474,1029, # 368 -1665, 217,1870,1531,3138,1104,2655,4209, 24, 172,3562, 900,3980,3563,3564,4519, # 384 - 32,1408,2824,1312, 329, 487,2360,2251,2717, 784,2683, 4,3039,3351,1427,1789, # 400 - 188, 109, 499,5032,3686,1717,1790, 888,1217,3040,4520,5033,3565,5034,3352,1520, # 416 -3687,3981, 196,1034, 775,5035,5036, 929,1816, 249, 439, 38,5037,1063,5038, 794, # 432 -3982,1435,2301, 46, 178,3278,2066,5039,2381,5040, 214,1709,4521, 804, 35, 707, # 448 - 324,3688,1601,2554, 140, 459,4210,5041,5042,1365, 839, 272, 978,2262,2580,3456, # 464 -2129,1363,3689,1423, 697, 100,3094, 48, 70,1231, 495,3139,2196,5043,1294,5044, # 480 -2080, 462, 586,1042,3279, 853, 256, 988, 185,2382,3457,1698, 434,1084,5045,3458, # 496 - 314,2625,2788,4522,2335,2336, 569,2285, 637,1817,2525, 757,1162,1879,1616,3459, # 512 - 287,1577,2116, 768,4523,1671,2868,3566,2526,1321,3816, 909,2418,5046,4211, 933, # 528 -3817,4212,2053,2361,1222,4524, 765,2419,1322, 786,4525,5047,1920,1462,1677,2909, # 544 -1699,5048,4526,1424,2442,3140,3690,2600,3353,1775,1941,3460,3983,4213, 309,1369, # 560 -1130,2825, 364,2234,1653,1299,3984,3567,3985,3986,2656, 525,1085,3041, 902,2001, # 576 -1475, 964,4527, 421,1845,1415,1057,2286, 940,1364,3141, 376,4528,4529,1381, 7, # 592 -2527, 983,2383, 336,1710,2684,1846, 321,3461, 559,1131,3042,2752,1809,1132,1313, # 608 - 265,1481,1858,5049, 352,1203,2826,3280, 167,1089, 420,2827, 776, 792,1724,3568, # 624 -4214,2443,3281,5050,4215,5051, 446, 229, 333,2753, 901,3818,1200,1557,4530,2657, # 640 -1921, 395,2754,2685,3819,4216,1836, 125, 916,3209,2626,4531,5052,5053,3820,5054, # 656 -5055,5056,4532,3142,3691,1133,2555,1757,3462,1510,2318,1409,3569,5057,2146, 438, # 672 -2601,2910,2384,3354,1068, 958,3043, 461, 311,2869,2686,4217,1916,3210,4218,1979, # 688 - 383, 750,2755,2627,4219, 274, 539, 385,1278,1442,5058,1154,1965, 384, 561, 210, # 704 - 98,1295,2556,3570,5059,1711,2420,1482,3463,3987,2911,1257, 129,5060,3821, 642, # 720 - 523,2789,2790,2658,5061, 141,2235,1333, 68, 176, 441, 876, 907,4220, 603,2602, # 736 - 710, 171,3464, 404, 549, 18,3143,2398,1410,3692,1666,5062,3571,4533,2912,4534, # 752 -5063,2991, 368,5064, 146, 366, 99, 871,3693,1543, 748, 807,1586,1185, 22,2263, # 768 - 379,3822,3211,5065,3212, 505,1942,2628,1992,1382,2319,5066, 380,2362, 218, 702, # 784 -1818,1248,3465,3044,3572,3355,3282,5067,2992,3694, 930,3283,3823,5068, 59,5069, # 800 - 585, 601,4221, 497,3466,1112,1314,4535,1802,5070,1223,1472,2177,5071, 749,1837, # 816 - 690,1900,3824,1773,3988,1476, 429,1043,1791,2236,2117, 917,4222, 447,1086,1629, # 832 -5072, 556,5073,5074,2021,1654, 844,1090, 105, 550, 966,1758,2828,1008,1783, 686, # 848 -1095,5075,2287, 793,1602,5076,3573,2603,4536,4223,2948,2302,4537,3825, 980,2503, # 864 - 544, 353, 527,4538, 908,2687,2913,5077, 381,2629,1943,1348,5078,1341,1252, 560, # 880 -3095,5079,3467,2870,5080,2054, 973, 886,2081, 143,4539,5081,5082, 157,3989, 496, # 896 -4224, 57, 840, 540,2039,4540,4541,3468,2118,1445, 970,2264,1748,1966,2082,4225, # 912 -3144,1234,1776,3284,2829,3695, 773,1206,2130,1066,2040,1326,3990,1738,1725,4226, # 928 - 279,3145, 51,1544,2604, 423,1578,2131,2067, 173,4542,1880,5083,5084,1583, 264, # 944 - 610,3696,4543,2444, 280, 154,5085,5086,5087,1739, 338,1282,3096, 693,2871,1411, # 960 -1074,3826,2445,5088,4544,5089,5090,1240, 952,2399,5091,2914,1538,2688, 685,1483, # 976 -4227,2475,1436, 953,4228,2055,4545, 671,2400, 79,4229,2446,3285, 608, 567,2689, # 992 -3469,4230,4231,1691, 393,1261,1792,2401,5092,4546,5093,5094,5095,5096,1383,1672, # 1008 -3827,3213,1464, 522,1119, 661,1150, 216, 675,4547,3991,1432,3574, 609,4548,2690, # 1024 -2402,5097,5098,5099,4232,3045, 0,5100,2476, 315, 231,2447, 301,3356,4549,2385, # 1040 -5101, 233,4233,3697,1819,4550,4551,5102, 96,1777,1315,2083,5103, 257,5104,1810, # 1056 -3698,2718,1139,1820,4234,2022,1124,2164,2791,1778,2659,5105,3097, 363,1655,3214, # 1072 -5106,2993,5107,5108,5109,3992,1567,3993, 718, 103,3215, 849,1443, 341,3357,2949, # 1088 -1484,5110,1712, 127, 67, 339,4235,2403, 679,1412, 821,5111,5112, 834, 738, 351, # 1104 -2994,2147, 846, 235,1497,1881, 418,1993,3828,2719, 186,1100,2148,2756,3575,1545, # 1120 -1355,2950,2872,1377, 583,3994,4236,2581,2995,5113,1298,3699,1078,2557,3700,2363, # 1136 - 78,3829,3830, 267,1289,2100,2002,1594,4237, 348, 369,1274,2197,2178,1838,4552, # 1152 -1821,2830,3701,2757,2288,2003,4553,2951,2758, 144,3358, 882,4554,3995,2759,3470, # 1168 -4555,2915,5114,4238,1726, 320,5115,3996,3046, 788,2996,5116,2831,1774,1327,2873, # 1184 -3997,2832,5117,1306,4556,2004,1700,3831,3576,2364,2660, 787,2023, 506, 824,3702, # 1200 - 534, 323,4557,1044,3359,2024,1901, 946,3471,5118,1779,1500,1678,5119,1882,4558, # 1216 - 165, 243,4559,3703,2528, 123, 683,4239, 764,4560, 36,3998,1793, 589,2916, 816, # 1232 - 626,1667,3047,2237,1639,1555,1622,3832,3999,5120,4000,2874,1370,1228,1933, 891, # 1248 -2084,2917, 304,4240,5121, 292,2997,2720,3577, 691,2101,4241,1115,4561, 118, 662, # 1264 -5122, 611,1156, 854,2386,1316,2875, 2, 386, 515,2918,5123,5124,3286, 868,2238, # 1280 -1486, 855,2661, 785,2216,3048,5125,1040,3216,3578,5126,3146, 448,5127,1525,5128, # 1296 -2165,4562,5129,3833,5130,4242,2833,3579,3147, 503, 818,4001,3148,1568, 814, 676, # 1312 -1444, 306,1749,5131,3834,1416,1030, 197,1428, 805,2834,1501,4563,5132,5133,5134, # 1328 -1994,5135,4564,5136,5137,2198, 13,2792,3704,2998,3149,1229,1917,5138,3835,2132, # 1344 -5139,4243,4565,2404,3580,5140,2217,1511,1727,1120,5141,5142, 646,3836,2448, 307, # 1360 -5143,5144,1595,3217,5145,5146,5147,3705,1113,1356,4002,1465,2529,2530,5148, 519, # 1376 -5149, 128,2133, 92,2289,1980,5150,4003,1512, 342,3150,2199,5151,2793,2218,1981, # 1392 -3360,4244, 290,1656,1317, 789, 827,2365,5152,3837,4566, 562, 581,4004,5153, 401, # 1408 -4567,2252, 94,4568,5154,1399,2794,5155,1463,2025,4569,3218,1944,5156, 828,1105, # 1424 -4245,1262,1394,5157,4246, 605,4570,5158,1784,2876,5159,2835, 819,2102, 578,2200, # 1440 -2952,5160,1502, 436,3287,4247,3288,2836,4005,2919,3472,3473,5161,2721,2320,5162, # 1456 -5163,2337,2068, 23,4571, 193, 826,3838,2103, 699,1630,4248,3098, 390,1794,1064, # 1472 -3581,5164,1579,3099,3100,1400,5165,4249,1839,1640,2877,5166,4572,4573, 137,4250, # 1488 - 598,3101,1967, 780, 104, 974,2953,5167, 278, 899, 253, 402, 572, 504, 493,1339, # 1504 -5168,4006,1275,4574,2582,2558,5169,3706,3049,3102,2253, 565,1334,2722, 863, 41, # 1520 -5170,5171,4575,5172,1657,2338, 19, 463,2760,4251, 606,5173,2999,3289,1087,2085, # 1536 -1323,2662,3000,5174,1631,1623,1750,4252,2691,5175,2878, 791,2723,2663,2339, 232, # 1552 -2421,5176,3001,1498,5177,2664,2630, 755,1366,3707,3290,3151,2026,1609, 119,1918, # 1568 -3474, 862,1026,4253,5178,4007,3839,4576,4008,4577,2265,1952,2477,5179,1125, 817, # 1584 -4254,4255,4009,1513,1766,2041,1487,4256,3050,3291,2837,3840,3152,5180,5181,1507, # 1600 -5182,2692, 733, 40,1632,1106,2879, 345,4257, 841,2531, 230,4578,3002,1847,3292, # 1616 -3475,5183,1263, 986,3476,5184, 735, 879, 254,1137, 857, 622,1300,1180,1388,1562, # 1632 -4010,4011,2954, 967,2761,2665,1349, 592,2134,1692,3361,3003,1995,4258,1679,4012, # 1648 -1902,2188,5185, 739,3708,2724,1296,1290,5186,4259,2201,2202,1922,1563,2605,2559, # 1664 -1871,2762,3004,5187, 435,5188, 343,1108, 596, 17,1751,4579,2239,3477,3709,5189, # 1680 -4580, 294,3582,2955,1693, 477, 979, 281,2042,3583, 643,2043,3710,2631,2795,2266, # 1696 -1031,2340,2135,2303,3584,4581, 367,1249,2560,5190,3585,5191,4582,1283,3362,2005, # 1712 - 240,1762,3363,4583,4584, 836,1069,3153, 474,5192,2149,2532, 268,3586,5193,3219, # 1728 -1521,1284,5194,1658,1546,4260,5195,3587,3588,5196,4261,3364,2693,1685,4262, 961, # 1744 -1673,2632, 190,2006,2203,3841,4585,4586,5197, 570,2504,3711,1490,5198,4587,2633, # 1760 -3293,1957,4588, 584,1514, 396,1045,1945,5199,4589,1968,2449,5200,5201,4590,4013, # 1776 - 619,5202,3154,3294, 215,2007,2796,2561,3220,4591,3221,4592, 763,4263,3842,4593, # 1792 -5203,5204,1958,1767,2956,3365,3712,1174, 452,1477,4594,3366,3155,5205,2838,1253, # 1808 -2387,2189,1091,2290,4264, 492,5206, 638,1169,1825,2136,1752,4014, 648, 926,1021, # 1824 -1324,4595, 520,4596, 997, 847,1007, 892,4597,3843,2267,1872,3713,2405,1785,4598, # 1840 -1953,2957,3103,3222,1728,4265,2044,3714,4599,2008,1701,3156,1551, 30,2268,4266, # 1856 -5207,2027,4600,3589,5208, 501,5209,4267, 594,3478,2166,1822,3590,3479,3591,3223, # 1872 - 829,2839,4268,5210,1680,3157,1225,4269,5211,3295,4601,4270,3158,2341,5212,4602, # 1888 -4271,5213,4015,4016,5214,1848,2388,2606,3367,5215,4603, 374,4017, 652,4272,4273, # 1904 - 375,1140, 798,5216,5217,5218,2366,4604,2269, 546,1659, 138,3051,2450,4605,5219, # 1920 -2254, 612,1849, 910, 796,3844,1740,1371, 825,3845,3846,5220,2920,2562,5221, 692, # 1936 - 444,3052,2634, 801,4606,4274,5222,1491, 244,1053,3053,4275,4276, 340,5223,4018, # 1952 -1041,3005, 293,1168, 87,1357,5224,1539, 959,5225,2240, 721, 694,4277,3847, 219, # 1968 -1478, 644,1417,3368,2666,1413,1401,1335,1389,4019,5226,5227,3006,2367,3159,1826, # 1984 - 730,1515, 184,2840, 66,4607,5228,1660,2958, 246,3369, 378,1457, 226,3480, 975, # 2000 -4020,2959,1264,3592, 674, 696,5229, 163,5230,1141,2422,2167, 713,3593,3370,4608, # 2016 -4021,5231,5232,1186, 15,5233,1079,1070,5234,1522,3224,3594, 276,1050,2725, 758, # 2032 -1126, 653,2960,3296,5235,2342, 889,3595,4022,3104,3007, 903,1250,4609,4023,3481, # 2048 -3596,1342,1681,1718, 766,3297, 286, 89,2961,3715,5236,1713,5237,2607,3371,3008, # 2064 -5238,2962,2219,3225,2880,5239,4610,2505,2533, 181, 387,1075,4024, 731,2190,3372, # 2080 -5240,3298, 310, 313,3482,2304, 770,4278, 54,3054, 189,4611,3105,3848,4025,5241, # 2096 -1230,1617,1850, 355,3597,4279,4612,3373, 111,4280,3716,1350,3160,3483,3055,4281, # 2112 -2150,3299,3598,5242,2797,4026,4027,3009, 722,2009,5243,1071, 247,1207,2343,2478, # 2128 -1378,4613,2010, 864,1437,1214,4614, 373,3849,1142,2220, 667,4615, 442,2763,2563, # 2144 -3850,4028,1969,4282,3300,1840, 837, 170,1107, 934,1336,1883,5244,5245,2119,4283, # 2160 -2841, 743,1569,5246,4616,4284, 582,2389,1418,3484,5247,1803,5248, 357,1395,1729, # 2176 -3717,3301,2423,1564,2241,5249,3106,3851,1633,4617,1114,2086,4285,1532,5250, 482, # 2192 -2451,4618,5251,5252,1492, 833,1466,5253,2726,3599,1641,2842,5254,1526,1272,3718, # 2208 -4286,1686,1795, 416,2564,1903,1954,1804,5255,3852,2798,3853,1159,2321,5256,2881, # 2224 -4619,1610,1584,3056,2424,2764, 443,3302,1163,3161,5257,5258,4029,5259,4287,2506, # 2240 -3057,4620,4030,3162,2104,1647,3600,2011,1873,4288,5260,4289, 431,3485,5261, 250, # 2256 - 97, 81,4290,5262,1648,1851,1558, 160, 848,5263, 866, 740,1694,5264,2204,2843, # 2272 -3226,4291,4621,3719,1687, 950,2479, 426, 469,3227,3720,3721,4031,5265,5266,1188, # 2288 - 424,1996, 861,3601,4292,3854,2205,2694, 168,1235,3602,4293,5267,2087,1674,4622, # 2304 -3374,3303, 220,2565,1009,5268,3855, 670,3010, 332,1208, 717,5269,5270,3603,2452, # 2320 -4032,3375,5271, 513,5272,1209,2882,3376,3163,4623,1080,5273,5274,5275,5276,2534, # 2336 -3722,3604, 815,1587,4033,4034,5277,3605,3486,3856,1254,4624,1328,3058,1390,4035, # 2352 -1741,4036,3857,4037,5278, 236,3858,2453,3304,5279,5280,3723,3859,1273,3860,4625, # 2368 -5281, 308,5282,4626, 245,4627,1852,2480,1307,2583, 430, 715,2137,2454,5283, 270, # 2384 - 199,2883,4038,5284,3606,2727,1753, 761,1754, 725,1661,1841,4628,3487,3724,5285, # 2400 -5286, 587, 14,3305, 227,2608, 326, 480,2270, 943,2765,3607, 291, 650,1884,5287, # 2416 -1702,1226, 102,1547, 62,3488, 904,4629,3489,1164,4294,5288,5289,1224,1548,2766, # 2432 - 391, 498,1493,5290,1386,1419,5291,2056,1177,4630, 813, 880,1081,2368, 566,1145, # 2448 -4631,2291,1001,1035,2566,2609,2242, 394,1286,5292,5293,2069,5294, 86,1494,1730, # 2464 -4039, 491,1588, 745, 897,2963, 843,3377,4040,2767,2884,3306,1768, 998,2221,2070, # 2480 - 397,1827,1195,1970,3725,3011,3378, 284,5295,3861,2507,2138,2120,1904,5296,4041, # 2496 -2151,4042,4295,1036,3490,1905, 114,2567,4296, 209,1527,5297,5298,2964,2844,2635, # 2512 -2390,2728,3164, 812,2568,5299,3307,5300,1559, 737,1885,3726,1210, 885, 28,2695, # 2528 -3608,3862,5301,4297,1004,1780,4632,5302, 346,1982,2222,2696,4633,3863,1742, 797, # 2544 -1642,4043,1934,1072,1384,2152, 896,4044,3308,3727,3228,2885,3609,5303,2569,1959, # 2560 -4634,2455,1786,5304,5305,5306,4045,4298,1005,1308,3728,4299,2729,4635,4636,1528, # 2576 -2610, 161,1178,4300,1983, 987,4637,1101,4301, 631,4046,1157,3229,2425,1343,1241, # 2592 -1016,2243,2570, 372, 877,2344,2508,1160, 555,1935, 911,4047,5307, 466,1170, 169, # 2608 -1051,2921,2697,3729,2481,3012,1182,2012,2571,1251,2636,5308, 992,2345,3491,1540, # 2624 -2730,1201,2071,2406,1997,2482,5309,4638, 528,1923,2191,1503,1874,1570,2369,3379, # 2640 -3309,5310, 557,1073,5311,1828,3492,2088,2271,3165,3059,3107, 767,3108,2799,4639, # 2656 -1006,4302,4640,2346,1267,2179,3730,3230, 778,4048,3231,2731,1597,2667,5312,4641, # 2672 -5313,3493,5314,5315,5316,3310,2698,1433,3311, 131, 95,1504,4049, 723,4303,3166, # 2688 -1842,3610,2768,2192,4050,2028,2105,3731,5317,3013,4051,1218,5318,3380,3232,4052, # 2704 -4304,2584, 248,1634,3864, 912,5319,2845,3732,3060,3865, 654, 53,5320,3014,5321, # 2720 -1688,4642, 777,3494,1032,4053,1425,5322, 191, 820,2121,2846, 971,4643, 931,3233, # 2736 - 135, 664, 783,3866,1998, 772,2922,1936,4054,3867,4644,2923,3234, 282,2732, 640, # 2752 -1372,3495,1127, 922, 325,3381,5323,5324, 711,2045,5325,5326,4055,2223,2800,1937, # 2768 -4056,3382,2224,2255,3868,2305,5327,4645,3869,1258,3312,4057,3235,2139,2965,4058, # 2784 -4059,5328,2225, 258,3236,4646, 101,1227,5329,3313,1755,5330,1391,3314,5331,2924, # 2800 -2057, 893,5332,5333,5334,1402,4305,2347,5335,5336,3237,3611,5337,5338, 878,1325, # 2816 -1781,2801,4647, 259,1385,2585, 744,1183,2272,4648,5339,4060,2509,5340, 684,1024, # 2832 -4306,5341, 472,3612,3496,1165,3315,4061,4062, 322,2153, 881, 455,1695,1152,1340, # 2848 - 660, 554,2154,4649,1058,4650,4307, 830,1065,3383,4063,4651,1924,5342,1703,1919, # 2864 -5343, 932,2273, 122,5344,4652, 947, 677,5345,3870,2637, 297,1906,1925,2274,4653, # 2880 -2322,3316,5346,5347,4308,5348,4309, 84,4310, 112, 989,5349, 547,1059,4064, 701, # 2896 -3613,1019,5350,4311,5351,3497, 942, 639, 457,2306,2456, 993,2966, 407, 851, 494, # 2912 -4654,3384, 927,5352,1237,5353,2426,3385, 573,4312, 680, 921,2925,1279,1875, 285, # 2928 - 790,1448,1984, 719,2168,5354,5355,4655,4065,4066,1649,5356,1541, 563,5357,1077, # 2944 -5358,3386,3061,3498, 511,3015,4067,4068,3733,4069,1268,2572,3387,3238,4656,4657, # 2960 -5359, 535,1048,1276,1189,2926,2029,3167,1438,1373,2847,2967,1134,2013,5360,4313, # 2976 -1238,2586,3109,1259,5361, 700,5362,2968,3168,3734,4314,5363,4315,1146,1876,1907, # 2992 -4658,2611,4070, 781,2427, 132,1589, 203, 147, 273,2802,2407, 898,1787,2155,4071, # 3008 -4072,5364,3871,2803,5365,5366,4659,4660,5367,3239,5368,1635,3872, 965,5369,1805, # 3024 -2699,1516,3614,1121,1082,1329,3317,4073,1449,3873, 65,1128,2848,2927,2769,1590, # 3040 -3874,5370,5371, 12,2668, 45, 976,2587,3169,4661, 517,2535,1013,1037,3240,5372, # 3056 -3875,2849,5373,3876,5374,3499,5375,2612, 614,1999,2323,3877,3110,2733,2638,5376, # 3072 -2588,4316, 599,1269,5377,1811,3735,5378,2700,3111, 759,1060, 489,1806,3388,3318, # 3088 -1358,5379,5380,2391,1387,1215,2639,2256, 490,5381,5382,4317,1759,2392,2348,5383, # 3104 -4662,3878,1908,4074,2640,1807,3241,4663,3500,3319,2770,2349, 874,5384,5385,3501, # 3120 -3736,1859, 91,2928,3737,3062,3879,4664,5386,3170,4075,2669,5387,3502,1202,1403, # 3136 -3880,2969,2536,1517,2510,4665,3503,2511,5388,4666,5389,2701,1886,1495,1731,4076, # 3152 -2370,4667,5390,2030,5391,5392,4077,2702,1216, 237,2589,4318,2324,4078,3881,4668, # 3168 -4669,2703,3615,3504, 445,4670,5393,5394,5395,5396,2771, 61,4079,3738,1823,4080, # 3184 -5397, 687,2046, 935, 925, 405,2670, 703,1096,1860,2734,4671,4081,1877,1367,2704, # 3200 -3389, 918,2106,1782,2483, 334,3320,1611,1093,4672, 564,3171,3505,3739,3390, 945, # 3216 -2641,2058,4673,5398,1926, 872,4319,5399,3506,2705,3112, 349,4320,3740,4082,4674, # 3232 -3882,4321,3741,2156,4083,4675,4676,4322,4677,2408,2047, 782,4084, 400, 251,4323, # 3248 -1624,5400,5401, 277,3742, 299,1265, 476,1191,3883,2122,4324,4325,1109, 205,5402, # 3264 -2590,1000,2157,3616,1861,5403,5404,5405,4678,5406,4679,2573, 107,2484,2158,4085, # 3280 -3507,3172,5407,1533, 541,1301, 158, 753,4326,2886,3617,5408,1696, 370,1088,4327, # 3296 -4680,3618, 579, 327, 440, 162,2244, 269,1938,1374,3508, 968,3063, 56,1396,3113, # 3312 -2107,3321,3391,5409,1927,2159,4681,3016,5410,3619,5411,5412,3743,4682,2485,5413, # 3328 -2804,5414,1650,4683,5415,2613,5416,5417,4086,2671,3392,1149,3393,4087,3884,4088, # 3344 -5418,1076, 49,5419, 951,3242,3322,3323, 450,2850, 920,5420,1812,2805,2371,4328, # 3360 -1909,1138,2372,3885,3509,5421,3243,4684,1910,1147,1518,2428,4685,3886,5422,4686, # 3376 -2393,2614, 260,1796,3244,5423,5424,3887,3324, 708,5425,3620,1704,5426,3621,1351, # 3392 -1618,3394,3017,1887, 944,4329,3395,4330,3064,3396,4331,5427,3744, 422, 413,1714, # 3408 -3325, 500,2059,2350,4332,2486,5428,1344,1911, 954,5429,1668,5430,5431,4089,2409, # 3424 -4333,3622,3888,4334,5432,2307,1318,2512,3114, 133,3115,2887,4687, 629, 31,2851, # 3440 -2706,3889,4688, 850, 949,4689,4090,2970,1732,2089,4335,1496,1853,5433,4091, 620, # 3456 -3245, 981,1242,3745,3397,1619,3746,1643,3326,2140,2457,1971,1719,3510,2169,5434, # 3472 -3246,5435,5436,3398,1829,5437,1277,4690,1565,2048,5438,1636,3623,3116,5439, 869, # 3488 -2852, 655,3890,3891,3117,4092,3018,3892,1310,3624,4691,5440,5441,5442,1733, 558, # 3504 -4692,3747, 335,1549,3065,1756,4336,3748,1946,3511,1830,1291,1192, 470,2735,2108, # 3520 -2806, 913,1054,4093,5443,1027,5444,3066,4094,4693, 982,2672,3399,3173,3512,3247, # 3536 -3248,1947,2807,5445, 571,4694,5446,1831,5447,3625,2591,1523,2429,5448,2090, 984, # 3552 -4695,3749,1960,5449,3750, 852, 923,2808,3513,3751, 969,1519, 999,2049,2325,1705, # 3568 -5450,3118, 615,1662, 151, 597,4095,2410,2326,1049, 275,4696,3752,4337, 568,3753, # 3584 -3626,2487,4338,3754,5451,2430,2275, 409,3249,5452,1566,2888,3514,1002, 769,2853, # 3600 - 194,2091,3174,3755,2226,3327,4339, 628,1505,5453,5454,1763,2180,3019,4096, 521, # 3616 -1161,2592,1788,2206,2411,4697,4097,1625,4340,4341, 412, 42,3119, 464,5455,2642, # 3632 -4698,3400,1760,1571,2889,3515,2537,1219,2207,3893,2643,2141,2373,4699,4700,3328, # 3648 -1651,3401,3627,5456,5457,3628,2488,3516,5458,3756,5459,5460,2276,2092, 460,5461, # 3664 -4701,5462,3020, 962, 588,3629, 289,3250,2644,1116, 52,5463,3067,1797,5464,5465, # 3680 -5466,1467,5467,1598,1143,3757,4342,1985,1734,1067,4702,1280,3402, 465,4703,1572, # 3696 - 510,5468,1928,2245,1813,1644,3630,5469,4704,3758,5470,5471,2673,1573,1534,5472, # 3712 -5473, 536,1808,1761,3517,3894,3175,2645,5474,5475,5476,4705,3518,2929,1912,2809, # 3728 -5477,3329,1122, 377,3251,5478, 360,5479,5480,4343,1529, 551,5481,2060,3759,1769, # 3744 -2431,5482,2930,4344,3330,3120,2327,2109,2031,4706,1404, 136,1468,1479, 672,1171, # 3760 -3252,2308, 271,3176,5483,2772,5484,2050, 678,2736, 865,1948,4707,5485,2014,4098, # 3776 -2971,5486,2737,2227,1397,3068,3760,4708,4709,1735,2931,3403,3631,5487,3895, 509, # 3792 -2854,2458,2890,3896,5488,5489,3177,3178,4710,4345,2538,4711,2309,1166,1010, 552, # 3808 - 681,1888,5490,5491,2972,2973,4099,1287,1596,1862,3179, 358, 453, 736, 175, 478, # 3824 -1117, 905,1167,1097,5492,1854,1530,5493,1706,5494,2181,3519,2292,3761,3520,3632, # 3840 -4346,2093,4347,5495,3404,1193,2489,4348,1458,2193,2208,1863,1889,1421,3331,2932, # 3856 -3069,2182,3521, 595,2123,5496,4100,5497,5498,4349,1707,2646, 223,3762,1359, 751, # 3872 -3121, 183,3522,5499,2810,3021, 419,2374, 633, 704,3897,2394, 241,5500,5501,5502, # 3888 - 838,3022,3763,2277,2773,2459,3898,1939,2051,4101,1309,3122,2246,1181,5503,1136, # 3904 -2209,3899,2375,1446,4350,2310,4712,5504,5505,4351,1055,2615, 484,3764,5506,4102, # 3920 - 625,4352,2278,3405,1499,4353,4103,5507,4104,4354,3253,2279,2280,3523,5508,5509, # 3936 -2774, 808,2616,3765,3406,4105,4355,3123,2539, 526,3407,3900,4356, 955,5510,1620, # 3952 -4357,2647,2432,5511,1429,3766,1669,1832, 994, 928,5512,3633,1260,5513,5514,5515, # 3968 -1949,2293, 741,2933,1626,4358,2738,2460, 867,1184, 362,3408,1392,5516,5517,4106, # 3984 -4359,1770,1736,3254,2934,4713,4714,1929,2707,1459,1158,5518,3070,3409,2891,1292, # 4000 -1930,2513,2855,3767,1986,1187,2072,2015,2617,4360,5519,2574,2514,2170,3768,2490, # 4016 -3332,5520,3769,4715,5521,5522, 666,1003,3023,1022,3634,4361,5523,4716,1814,2257, # 4032 - 574,3901,1603, 295,1535, 705,3902,4362, 283, 858, 417,5524,5525,3255,4717,4718, # 4048 -3071,1220,1890,1046,2281,2461,4107,1393,1599, 689,2575, 388,4363,5526,2491, 802, # 4064 -5527,2811,3903,2061,1405,2258,5528,4719,3904,2110,1052,1345,3256,1585,5529, 809, # 4080 -5530,5531,5532, 575,2739,3524, 956,1552,1469,1144,2328,5533,2329,1560,2462,3635, # 4096 -3257,4108, 616,2210,4364,3180,2183,2294,5534,1833,5535,3525,4720,5536,1319,3770, # 4112 -3771,1211,3636,1023,3258,1293,2812,5537,5538,5539,3905, 607,2311,3906, 762,2892, # 4128 -1439,4365,1360,4721,1485,3072,5540,4722,1038,4366,1450,2062,2648,4367,1379,4723, # 4144 -2593,5541,5542,4368,1352,1414,2330,2935,1172,5543,5544,3907,3908,4724,1798,1451, # 4160 -5545,5546,5547,5548,2936,4109,4110,2492,2351, 411,4111,4112,3637,3333,3124,4725, # 4176 -1561,2674,1452,4113,1375,5549,5550, 47,2974, 316,5551,1406,1591,2937,3181,5552, # 4192 -1025,2142,3125,3182, 354,2740, 884,2228,4369,2412, 508,3772, 726,3638, 996,2433, # 4208 -3639, 729,5553, 392,2194,1453,4114,4726,3773,5554,5555,2463,3640,2618,1675,2813, # 4224 - 919,2352,2975,2353,1270,4727,4115, 73,5556,5557, 647,5558,3259,2856,2259,1550, # 4240 -1346,3024,5559,1332, 883,3526,5560,5561,5562,5563,3334,2775,5564,1212, 831,1347, # 4256 -4370,4728,2331,3909,1864,3073, 720,3910,4729,4730,3911,5565,4371,5566,5567,4731, # 4272 -5568,5569,1799,4732,3774,2619,4733,3641,1645,2376,4734,5570,2938, 669,2211,2675, # 4288 -2434,5571,2893,5572,5573,1028,3260,5574,4372,2413,5575,2260,1353,5576,5577,4735, # 4304 -3183, 518,5578,4116,5579,4373,1961,5580,2143,4374,5581,5582,3025,2354,2355,3912, # 4320 - 516,1834,1454,4117,2708,4375,4736,2229,2620,1972,1129,3642,5583,2776,5584,2976, # 4336 -1422, 577,1470,3026,1524,3410,5585,5586, 432,4376,3074,3527,5587,2594,1455,2515, # 4352 -2230,1973,1175,5588,1020,2741,4118,3528,4737,5589,2742,5590,1743,1361,3075,3529, # 4368 -2649,4119,4377,4738,2295, 895, 924,4378,2171, 331,2247,3076, 166,1627,3077,1098, # 4384 -5591,1232,2894,2231,3411,4739, 657, 403,1196,2377, 542,3775,3412,1600,4379,3530, # 4400 -5592,4740,2777,3261, 576, 530,1362,4741,4742,2540,2676,3776,4120,5593, 842,3913, # 4416 -5594,2814,2032,1014,4121, 213,2709,3413, 665, 621,4380,5595,3777,2939,2435,5596, # 4432 -2436,3335,3643,3414,4743,4381,2541,4382,4744,3644,1682,4383,3531,1380,5597, 724, # 4448 -2282, 600,1670,5598,1337,1233,4745,3126,2248,5599,1621,4746,5600, 651,4384,5601, # 4464 -1612,4385,2621,5602,2857,5603,2743,2312,3078,5604, 716,2464,3079, 174,1255,2710, # 4480 -4122,3645, 548,1320,1398, 728,4123,1574,5605,1891,1197,3080,4124,5606,3081,3082, # 4496 -3778,3646,3779, 747,5607, 635,4386,4747,5608,5609,5610,4387,5611,5612,4748,5613, # 4512 -3415,4749,2437, 451,5614,3780,2542,2073,4388,2744,4389,4125,5615,1764,4750,5616, # 4528 -4390, 350,4751,2283,2395,2493,5617,4391,4126,2249,1434,4127, 488,4752, 458,4392, # 4544 -4128,3781, 771,1330,2396,3914,2576,3184,2160,2414,1553,2677,3185,4393,5618,2494, # 4560 -2895,2622,1720,2711,4394,3416,4753,5619,2543,4395,5620,3262,4396,2778,5621,2016, # 4576 -2745,5622,1155,1017,3782,3915,5623,3336,2313, 201,1865,4397,1430,5624,4129,5625, # 4592 -5626,5627,5628,5629,4398,1604,5630, 414,1866, 371,2595,4754,4755,3532,2017,3127, # 4608 -4756,1708, 960,4399, 887, 389,2172,1536,1663,1721,5631,2232,4130,2356,2940,1580, # 4624 -5632,5633,1744,4757,2544,4758,4759,5634,4760,5635,2074,5636,4761,3647,3417,2896, # 4640 -4400,5637,4401,2650,3418,2815, 673,2712,2465, 709,3533,4131,3648,4402,5638,1148, # 4656 - 502, 634,5639,5640,1204,4762,3649,1575,4763,2623,3783,5641,3784,3128, 948,3263, # 4672 - 121,1745,3916,1110,5642,4403,3083,2516,3027,4132,3785,1151,1771,3917,1488,4133, # 4688 -1987,5643,2438,3534,5644,5645,2094,5646,4404,3918,1213,1407,2816, 531,2746,2545, # 4704 -3264,1011,1537,4764,2779,4405,3129,1061,5647,3786,3787,1867,2897,5648,2018, 120, # 4720 -4406,4407,2063,3650,3265,2314,3919,2678,3419,1955,4765,4134,5649,3535,1047,2713, # 4736 -1266,5650,1368,4766,2858, 649,3420,3920,2546,2747,1102,2859,2679,5651,5652,2000, # 4752 -5653,1111,3651,2977,5654,2495,3921,3652,2817,1855,3421,3788,5655,5656,3422,2415, # 4768 -2898,3337,3266,3653,5657,2577,5658,3654,2818,4135,1460, 856,5659,3655,5660,2899, # 4784 -2978,5661,2900,3922,5662,4408, 632,2517, 875,3923,1697,3924,2296,5663,5664,4767, # 4800 -3028,1239, 580,4768,4409,5665, 914, 936,2075,1190,4136,1039,2124,5666,5667,5668, # 4816 -5669,3423,1473,5670,1354,4410,3925,4769,2173,3084,4137, 915,3338,4411,4412,3339, # 4832 -1605,1835,5671,2748, 398,3656,4413,3926,4138, 328,1913,2860,4139,3927,1331,4414, # 4848 -3029, 937,4415,5672,3657,4140,4141,3424,2161,4770,3425, 524, 742, 538,3085,1012, # 4864 -5673,5674,3928,2466,5675, 658,1103, 225,3929,5676,5677,4771,5678,4772,5679,3267, # 4880 -1243,5680,4142, 963,2250,4773,5681,2714,3658,3186,5682,5683,2596,2332,5684,4774, # 4896 -5685,5686,5687,3536, 957,3426,2547,2033,1931,2941,2467, 870,2019,3659,1746,2780, # 4912 -2781,2439,2468,5688,3930,5689,3789,3130,3790,3537,3427,3791,5690,1179,3086,5691, # 4928 -3187,2378,4416,3792,2548,3188,3131,2749,4143,5692,3428,1556,2549,2297, 977,2901, # 4944 -2034,4144,1205,3429,5693,1765,3430,3189,2125,1271, 714,1689,4775,3538,5694,2333, # 4960 -3931, 533,4417,3660,2184, 617,5695,2469,3340,3539,2315,5696,5697,3190,5698,5699, # 4976 -3932,1988, 618, 427,2651,3540,3431,5700,5701,1244,1690,5702,2819,4418,4776,5703, # 4992 -3541,4777,5704,2284,1576, 473,3661,4419,3432, 972,5705,3662,5706,3087,5707,5708, # 5008 -4778,4779,5709,3793,4145,4146,5710, 153,4780, 356,5711,1892,2902,4420,2144, 408, # 5024 - 803,2357,5712,3933,5713,4421,1646,2578,2518,4781,4782,3934,5714,3935,4422,5715, # 5040 -2416,3433, 752,5716,5717,1962,3341,2979,5718, 746,3030,2470,4783,4423,3794, 698, # 5056 -4784,1893,4424,3663,2550,4785,3664,3936,5719,3191,3434,5720,1824,1302,4147,2715, # 5072 -3937,1974,4425,5721,4426,3192, 823,1303,1288,1236,2861,3542,4148,3435, 774,3938, # 5088 -5722,1581,4786,1304,2862,3939,4787,5723,2440,2162,1083,3268,4427,4149,4428, 344, # 5104 -1173, 288,2316, 454,1683,5724,5725,1461,4788,4150,2597,5726,5727,4789, 985, 894, # 5120 -5728,3436,3193,5729,1914,2942,3795,1989,5730,2111,1975,5731,4151,5732,2579,1194, # 5136 - 425,5733,4790,3194,1245,3796,4429,5734,5735,2863,5736, 636,4791,1856,3940, 760, # 5152 -1800,5737,4430,2212,1508,4792,4152,1894,1684,2298,5738,5739,4793,4431,4432,2213, # 5168 - 479,5740,5741, 832,5742,4153,2496,5743,2980,2497,3797, 990,3132, 627,1815,2652, # 5184 -4433,1582,4434,2126,2112,3543,4794,5744, 799,4435,3195,5745,4795,2113,1737,3031, # 5200 -1018, 543, 754,4436,3342,1676,4796,4797,4154,4798,1489,5746,3544,5747,2624,2903, # 5216 -4155,5748,5749,2981,5750,5751,5752,5753,3196,4799,4800,2185,1722,5754,3269,3270, # 5232 -1843,3665,1715, 481, 365,1976,1857,5755,5756,1963,2498,4801,5757,2127,3666,3271, # 5248 - 433,1895,2064,2076,5758, 602,2750,5759,5760,5761,5762,5763,3032,1628,3437,5764, # 5264 -3197,4802,4156,2904,4803,2519,5765,2551,2782,5766,5767,5768,3343,4804,2905,5769, # 5280 -4805,5770,2864,4806,4807,1221,2982,4157,2520,5771,5772,5773,1868,1990,5774,5775, # 5296 -5776,1896,5777,5778,4808,1897,4158, 318,5779,2095,4159,4437,5780,5781, 485,5782, # 5312 - 938,3941, 553,2680, 116,5783,3942,3667,5784,3545,2681,2783,3438,3344,2820,5785, # 5328 -3668,2943,4160,1747,2944,2983,5786,5787, 207,5788,4809,5789,4810,2521,5790,3033, # 5344 - 890,3669,3943,5791,1878,3798,3439,5792,2186,2358,3440,1652,5793,5794,5795, 941, # 5360 -2299, 208,3546,4161,2020, 330,4438,3944,2906,2499,3799,4439,4811,5796,5797,5798, # 5376 -) -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/big5prober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/big5prober.py deleted file mode 100644 index ef09c60..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/big5prober.py +++ /dev/null @@ -1,47 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .chardistribution import Big5DistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import BIG5_SM_MODEL - - -class Big5Prober(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(BIG5_SM_MODEL) - self.distribution_analyzer = Big5DistributionAnalysis() - self.reset() - - @property - def charset_name(self) -> str: - return "Big5" - - @property - def language(self) -> str: - return "Chinese" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/chardistribution.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/chardistribution.py deleted file mode 100644 index 176cb99..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/chardistribution.py +++ /dev/null @@ -1,261 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Tuple, Union - -from .big5freq import ( - BIG5_CHAR_TO_FREQ_ORDER, - BIG5_TABLE_SIZE, - BIG5_TYPICAL_DISTRIBUTION_RATIO, -) -from .euckrfreq import ( - EUCKR_CHAR_TO_FREQ_ORDER, - EUCKR_TABLE_SIZE, - EUCKR_TYPICAL_DISTRIBUTION_RATIO, -) -from .euctwfreq import ( - EUCTW_CHAR_TO_FREQ_ORDER, - EUCTW_TABLE_SIZE, - EUCTW_TYPICAL_DISTRIBUTION_RATIO, -) -from .gb2312freq import ( - GB2312_CHAR_TO_FREQ_ORDER, - GB2312_TABLE_SIZE, - GB2312_TYPICAL_DISTRIBUTION_RATIO, -) -from .jisfreq import ( - JIS_CHAR_TO_FREQ_ORDER, - JIS_TABLE_SIZE, - JIS_TYPICAL_DISTRIBUTION_RATIO, -) -from .johabfreq import JOHAB_TO_EUCKR_ORDER_TABLE - - -class CharDistributionAnalysis: - ENOUGH_DATA_THRESHOLD = 1024 - SURE_YES = 0.99 - SURE_NO = 0.01 - MINIMUM_DATA_THRESHOLD = 3 - - def __init__(self) -> None: - # Mapping table to get frequency order from char order (get from - # GetOrder()) - self._char_to_freq_order: Tuple[int, ...] = tuple() - self._table_size = 0 # Size of above table - # This is a constant value which varies from language to language, - # used in calculating confidence. See - # http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html - # for further detail. - self.typical_distribution_ratio = 0.0 - self._done = False - self._total_chars = 0 - self._freq_chars = 0 - self.reset() - - def reset(self) -> None: - """reset analyser, clear any state""" - # If this flag is set to True, detection is done and conclusion has - # been made - self._done = False - self._total_chars = 0 # Total characters encountered - # The number of characters whose frequency order is less than 512 - self._freq_chars = 0 - - def feed(self, char: Union[bytes, bytearray], char_len: int) -> None: - """feed a character with known length""" - if char_len == 2: - # we only care about 2-bytes character in our distribution analysis - order = self.get_order(char) - else: - order = -1 - if order >= 0: - self._total_chars += 1 - # order is valid - if order < self._table_size: - if 512 > self._char_to_freq_order[order]: - self._freq_chars += 1 - - def get_confidence(self) -> float: - """return confidence based on existing data""" - # if we didn't receive any character in our consideration range, - # return negative answer - if self._total_chars <= 0 or self._freq_chars <= self.MINIMUM_DATA_THRESHOLD: - return self.SURE_NO - - if self._total_chars != self._freq_chars: - r = self._freq_chars / ( - (self._total_chars - self._freq_chars) * self.typical_distribution_ratio - ) - if r < self.SURE_YES: - return r - - # normalize confidence (we don't want to be 100% sure) - return self.SURE_YES - - def got_enough_data(self) -> bool: - # It is not necessary to receive all data to draw conclusion. - # For charset detection, certain amount of data is enough - return self._total_chars > self.ENOUGH_DATA_THRESHOLD - - def get_order(self, _: Union[bytes, bytearray]) -> int: - # We do not handle characters based on the original encoding string, - # but convert this encoding string to a number, here called order. - # This allows multiple encodings of a language to share one frequency - # table. - return -1 - - -class EUCTWDistributionAnalysis(CharDistributionAnalysis): - def __init__(self) -> None: - super().__init__() - self._char_to_freq_order = EUCTW_CHAR_TO_FREQ_ORDER - self._table_size = EUCTW_TABLE_SIZE - self.typical_distribution_ratio = EUCTW_TYPICAL_DISTRIBUTION_RATIO - - def get_order(self, byte_str: Union[bytes, bytearray]) -> int: - # for euc-TW encoding, we are interested - # first byte range: 0xc4 -- 0xfe - # second byte range: 0xa1 -- 0xfe - # no validation needed here. State machine has done that - first_char = byte_str[0] - if first_char >= 0xC4: - return 94 * (first_char - 0xC4) + byte_str[1] - 0xA1 - return -1 - - -class EUCKRDistributionAnalysis(CharDistributionAnalysis): - def __init__(self) -> None: - super().__init__() - self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER - self._table_size = EUCKR_TABLE_SIZE - self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO - - def get_order(self, byte_str: Union[bytes, bytearray]) -> int: - # for euc-KR encoding, we are interested - # first byte range: 0xb0 -- 0xfe - # second byte range: 0xa1 -- 0xfe - # no validation needed here. State machine has done that - first_char = byte_str[0] - if first_char >= 0xB0: - return 94 * (first_char - 0xB0) + byte_str[1] - 0xA1 - return -1 - - -class JOHABDistributionAnalysis(CharDistributionAnalysis): - def __init__(self) -> None: - super().__init__() - self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER - self._table_size = EUCKR_TABLE_SIZE - self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO - - def get_order(self, byte_str: Union[bytes, bytearray]) -> int: - first_char = byte_str[0] - if 0x88 <= first_char < 0xD4: - code = first_char * 256 + byte_str[1] - return JOHAB_TO_EUCKR_ORDER_TABLE.get(code, -1) - return -1 - - -class GB2312DistributionAnalysis(CharDistributionAnalysis): - def __init__(self) -> None: - super().__init__() - self._char_to_freq_order = GB2312_CHAR_TO_FREQ_ORDER - self._table_size = GB2312_TABLE_SIZE - self.typical_distribution_ratio = GB2312_TYPICAL_DISTRIBUTION_RATIO - - def get_order(self, byte_str: Union[bytes, bytearray]) -> int: - # for GB2312 encoding, we are interested - # first byte range: 0xb0 -- 0xfe - # second byte range: 0xa1 -- 0xfe - # no validation needed here. State machine has done that - first_char, second_char = byte_str[0], byte_str[1] - if (first_char >= 0xB0) and (second_char >= 0xA1): - return 94 * (first_char - 0xB0) + second_char - 0xA1 - return -1 - - -class Big5DistributionAnalysis(CharDistributionAnalysis): - def __init__(self) -> None: - super().__init__() - self._char_to_freq_order = BIG5_CHAR_TO_FREQ_ORDER - self._table_size = BIG5_TABLE_SIZE - self.typical_distribution_ratio = BIG5_TYPICAL_DISTRIBUTION_RATIO - - def get_order(self, byte_str: Union[bytes, bytearray]) -> int: - # for big5 encoding, we are interested - # first byte range: 0xa4 -- 0xfe - # second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe - # no validation needed here. State machine has done that - first_char, second_char = byte_str[0], byte_str[1] - if first_char >= 0xA4: - if second_char >= 0xA1: - return 157 * (first_char - 0xA4) + second_char - 0xA1 + 63 - return 157 * (first_char - 0xA4) + second_char - 0x40 - return -1 - - -class SJISDistributionAnalysis(CharDistributionAnalysis): - def __init__(self) -> None: - super().__init__() - self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER - self._table_size = JIS_TABLE_SIZE - self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO - - def get_order(self, byte_str: Union[bytes, bytearray]) -> int: - # for sjis encoding, we are interested - # first byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe - # second byte range: 0x40 -- 0x7e, 0x81 -- oxfe - # no validation needed here. State machine has done that - first_char, second_char = byte_str[0], byte_str[1] - if 0x81 <= first_char <= 0x9F: - order = 188 * (first_char - 0x81) - elif 0xE0 <= first_char <= 0xEF: - order = 188 * (first_char - 0xE0 + 31) - else: - return -1 - order = order + second_char - 0x40 - if second_char > 0x7F: - order = -1 - return order - - -class EUCJPDistributionAnalysis(CharDistributionAnalysis): - def __init__(self) -> None: - super().__init__() - self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER - self._table_size = JIS_TABLE_SIZE - self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO - - def get_order(self, byte_str: Union[bytes, bytearray]) -> int: - # for euc-JP encoding, we are interested - # first byte range: 0xa0 -- 0xfe - # second byte range: 0xa1 -- 0xfe - # no validation needed here. State machine has done that - char = byte_str[0] - if char >= 0xA0: - return 94 * (char - 0xA1) + byte_str[1] - 0xA1 - return -1 diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/charsetgroupprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/charsetgroupprober.py deleted file mode 100644 index 6def56b..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/charsetgroupprober.py +++ /dev/null @@ -1,106 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import List, Optional, Union - -from .charsetprober import CharSetProber -from .enums import LanguageFilter, ProbingState - - -class CharSetGroupProber(CharSetProber): - def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None: - super().__init__(lang_filter=lang_filter) - self._active_num = 0 - self.probers: List[CharSetProber] = [] - self._best_guess_prober: Optional[CharSetProber] = None - - def reset(self) -> None: - super().reset() - self._active_num = 0 - for prober in self.probers: - prober.reset() - prober.active = True - self._active_num += 1 - self._best_guess_prober = None - - @property - def charset_name(self) -> Optional[str]: - if not self._best_guess_prober: - self.get_confidence() - if not self._best_guess_prober: - return None - return self._best_guess_prober.charset_name - - @property - def language(self) -> Optional[str]: - if not self._best_guess_prober: - self.get_confidence() - if not self._best_guess_prober: - return None - return self._best_guess_prober.language - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - for prober in self.probers: - if not prober.active: - continue - state = prober.feed(byte_str) - if not state: - continue - if state == ProbingState.FOUND_IT: - self._best_guess_prober = prober - self._state = ProbingState.FOUND_IT - return self.state - if state == ProbingState.NOT_ME: - prober.active = False - self._active_num -= 1 - if self._active_num <= 0: - self._state = ProbingState.NOT_ME - return self.state - return self.state - - def get_confidence(self) -> float: - state = self.state - if state == ProbingState.FOUND_IT: - return 0.99 - if state == ProbingState.NOT_ME: - return 0.01 - best_conf = 0.0 - self._best_guess_prober = None - for prober in self.probers: - if not prober.active: - self.logger.debug("%s not active", prober.charset_name) - continue - conf = prober.get_confidence() - self.logger.debug( - "%s %s confidence = %s", prober.charset_name, prober.language, conf - ) - if best_conf < conf: - best_conf = conf - self._best_guess_prober = prober - if not self._best_guess_prober: - return 0.0 - return best_conf diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/charsetprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/charsetprober.py deleted file mode 100644 index a103ca1..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/charsetprober.py +++ /dev/null @@ -1,147 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -import logging -import re -from typing import Optional, Union - -from .enums import LanguageFilter, ProbingState - -INTERNATIONAL_WORDS_PATTERN = re.compile( - b"[a-zA-Z]*[\x80-\xFF]+[a-zA-Z]*[^a-zA-Z\x80-\xFF]?" -) - - -class CharSetProber: - - SHORTCUT_THRESHOLD = 0.95 - - def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None: - self._state = ProbingState.DETECTING - self.active = True - self.lang_filter = lang_filter - self.logger = logging.getLogger(__name__) - - def reset(self) -> None: - self._state = ProbingState.DETECTING - - @property - def charset_name(self) -> Optional[str]: - return None - - @property - def language(self) -> Optional[str]: - raise NotImplementedError - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - raise NotImplementedError - - @property - def state(self) -> ProbingState: - return self._state - - def get_confidence(self) -> float: - return 0.0 - - @staticmethod - def filter_high_byte_only(buf: Union[bytes, bytearray]) -> bytes: - buf = re.sub(b"([\x00-\x7F])+", b" ", buf) - return buf - - @staticmethod - def filter_international_words(buf: Union[bytes, bytearray]) -> bytearray: - """ - We define three types of bytes: - alphabet: english alphabets [a-zA-Z] - international: international characters [\x80-\xFF] - marker: everything else [^a-zA-Z\x80-\xFF] - The input buffer can be thought to contain a series of words delimited - by markers. This function works to filter all words that contain at - least one international character. All contiguous sequences of markers - are replaced by a single space ascii character. - This filter applies to all scripts which do not use English characters. - """ - filtered = bytearray() - - # This regex expression filters out only words that have at-least one - # international character. The word may include one marker character at - # the end. - words = INTERNATIONAL_WORDS_PATTERN.findall(buf) - - for word in words: - filtered.extend(word[:-1]) - - # If the last character in the word is a marker, replace it with a - # space as markers shouldn't affect our analysis (they are used - # similarly across all languages and may thus have similar - # frequencies). - last_char = word[-1:] - if not last_char.isalpha() and last_char < b"\x80": - last_char = b" " - filtered.extend(last_char) - - return filtered - - @staticmethod - def remove_xml_tags(buf: Union[bytes, bytearray]) -> bytes: - """ - Returns a copy of ``buf`` that retains only the sequences of English - alphabet and high byte characters that are not between <> characters. - This filter can be applied to all scripts which contain both English - characters and extended ASCII characters, but is currently only used by - ``Latin1Prober``. - """ - filtered = bytearray() - in_tag = False - prev = 0 - buf = memoryview(buf).cast("c") - - for curr, buf_char in enumerate(buf): - # Check if we're coming out of or entering an XML tag - - # https://github.com/python/typeshed/issues/8182 - if buf_char == b">": # type: ignore[comparison-overlap] - prev = curr + 1 - in_tag = False - # https://github.com/python/typeshed/issues/8182 - elif buf_char == b"<": # type: ignore[comparison-overlap] - if curr > prev and not in_tag: - # Keep everything after last non-extended-ASCII, - # non-alphabetic character - filtered.extend(buf[prev:curr]) - # Output a space to delimit stretch we kept - filtered.extend(b" ") - in_tag = True - - # If we're not in a tag... - if not in_tag: - # Keep everything after last non-extended-ASCII, non-alphabetic - # character - filtered.extend(buf[prev:]) - - return filtered diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 0d6a421..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__pycache__/chardetect.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__pycache__/chardetect.cpython-312.pyc deleted file mode 100644 index 97311d6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__pycache__/chardetect.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/chardetect.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/chardetect.py deleted file mode 100644 index 43f6e14..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/chardetect.py +++ /dev/null @@ -1,112 +0,0 @@ -""" -Script which takes one or more file paths and reports on their detected -encodings - -Example:: - - % chardetect somefile someotherfile - somefile: windows-1252 with confidence 0.5 - someotherfile: ascii with confidence 1.0 - -If no paths are provided, it takes its input from stdin. - -""" - - -import argparse -import sys -from typing import Iterable, List, Optional - -from .. import __version__ -from ..universaldetector import UniversalDetector - - -def description_of( - lines: Iterable[bytes], - name: str = "stdin", - minimal: bool = False, - should_rename_legacy: bool = False, -) -> Optional[str]: - """ - Return a string describing the probable encoding of a file or - list of strings. - - :param lines: The lines to get the encoding of. - :type lines: Iterable of bytes - :param name: Name of file or collection of lines - :type name: str - :param should_rename_legacy: Should we rename legacy encodings to - their more modern equivalents? - :type should_rename_legacy: ``bool`` - """ - u = UniversalDetector(should_rename_legacy=should_rename_legacy) - for line in lines: - line = bytearray(line) - u.feed(line) - # shortcut out of the loop to save reading further - particularly useful if we read a BOM. - if u.done: - break - u.close() - result = u.result - if minimal: - return result["encoding"] - if result["encoding"]: - return f'{name}: {result["encoding"]} with confidence {result["confidence"]}' - return f"{name}: no result" - - -def main(argv: Optional[List[str]] = None) -> None: - """ - Handles command line arguments and gets things started. - - :param argv: List of arguments, as if specified on the command-line. - If None, ``sys.argv[1:]`` is used instead. - :type argv: list of str - """ - # Get command line arguments - parser = argparse.ArgumentParser( - description=( - "Takes one or more file paths and reports their detected encodings" - ) - ) - parser.add_argument( - "input", - help="File whose encoding we would like to determine. (default: stdin)", - type=argparse.FileType("rb"), - nargs="*", - default=[sys.stdin.buffer], - ) - parser.add_argument( - "--minimal", - help="Print only the encoding to standard output", - action="store_true", - ) - parser.add_argument( - "-l", - "--legacy", - help="Rename legacy encodings to more modern ones.", - action="store_true", - ) - parser.add_argument( - "--version", action="version", version=f"%(prog)s {__version__}" - ) - args = parser.parse_args(argv) - - for f in args.input: - if f.isatty(): - print( - "You are running chardetect interactively. Press " - "CTRL-D twice at the start of a blank line to signal the " - "end of your input. If you want help, run chardetect " - "--help\n", - file=sys.stderr, - ) - print( - description_of( - f, f.name, minimal=args.minimal, should_rename_legacy=args.legacy - ) - ) - - -if __name__ == "__main__": - main() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/codingstatemachine.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/codingstatemachine.py deleted file mode 100644 index 8ed4a87..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/codingstatemachine.py +++ /dev/null @@ -1,90 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -import logging - -from .codingstatemachinedict import CodingStateMachineDict -from .enums import MachineState - - -class CodingStateMachine: - """ - A state machine to verify a byte sequence for a particular encoding. For - each byte the detector receives, it will feed that byte to every active - state machine available, one byte at a time. The state machine changes its - state based on its previous state and the byte it receives. There are 3 - states in a state machine that are of interest to an auto-detector: - - START state: This is the state to start with, or a legal byte sequence - (i.e. a valid code point) for character has been identified. - - ME state: This indicates that the state machine identified a byte sequence - that is specific to the charset it is designed for and that - there is no other possible encoding which can contain this byte - sequence. This will to lead to an immediate positive answer for - the detector. - - ERROR state: This indicates the state machine identified an illegal byte - sequence for that encoding. This will lead to an immediate - negative answer for this encoding. Detector will exclude this - encoding from consideration from here on. - """ - - def __init__(self, sm: CodingStateMachineDict) -> None: - self._model = sm - self._curr_byte_pos = 0 - self._curr_char_len = 0 - self._curr_state = MachineState.START - self.active = True - self.logger = logging.getLogger(__name__) - self.reset() - - def reset(self) -> None: - self._curr_state = MachineState.START - - def next_state(self, c: int) -> int: - # for each byte we get its class - # if it is first byte, we also get byte length - byte_class = self._model["class_table"][c] - if self._curr_state == MachineState.START: - self._curr_byte_pos = 0 - self._curr_char_len = self._model["char_len_table"][byte_class] - # from byte's class and state_table, we get its next state - curr_state = self._curr_state * self._model["class_factor"] + byte_class - self._curr_state = self._model["state_table"][curr_state] - self._curr_byte_pos += 1 - return self._curr_state - - def get_current_charlen(self) -> int: - return self._curr_char_len - - def get_coding_state_machine(self) -> str: - return self._model["name"] - - @property - def language(self) -> str: - return self._model["language"] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/codingstatemachinedict.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/codingstatemachinedict.py deleted file mode 100644 index 7a3c4c7..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/codingstatemachinedict.py +++ /dev/null @@ -1,19 +0,0 @@ -from typing import TYPE_CHECKING, Tuple - -if TYPE_CHECKING: - # TypedDict was introduced in Python 3.8. - # - # TODO: Remove the else block and TYPE_CHECKING check when dropping support - # for Python 3.7. - from typing import TypedDict - - class CodingStateMachineDict(TypedDict, total=False): - class_table: Tuple[int, ...] - class_factor: int - state_table: Tuple[int, ...] - char_len_table: Tuple[int, ...] - name: str - language: str # Optional key - -else: - CodingStateMachineDict = dict diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cp949prober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cp949prober.py deleted file mode 100644 index fa7307e..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cp949prober.py +++ /dev/null @@ -1,49 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .chardistribution import EUCKRDistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import CP949_SM_MODEL - - -class CP949Prober(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(CP949_SM_MODEL) - # NOTE: CP949 is a superset of EUC-KR, so the distribution should be - # not different. - self.distribution_analyzer = EUCKRDistributionAnalysis() - self.reset() - - @property - def charset_name(self) -> str: - return "CP949" - - @property - def language(self) -> str: - return "Korean" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/enums.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/enums.py deleted file mode 100644 index 5e3e198..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/enums.py +++ /dev/null @@ -1,85 +0,0 @@ -""" -All of the Enums that are used throughout the chardet package. - -:author: Dan Blanchard (dan.blanchard@gmail.com) -""" - -from enum import Enum, Flag - - -class InputState: - """ - This enum represents the different states a universal detector can be in. - """ - - PURE_ASCII = 0 - ESC_ASCII = 1 - HIGH_BYTE = 2 - - -class LanguageFilter(Flag): - """ - This enum represents the different language filters we can apply to a - ``UniversalDetector``. - """ - - NONE = 0x00 - CHINESE_SIMPLIFIED = 0x01 - CHINESE_TRADITIONAL = 0x02 - JAPANESE = 0x04 - KOREAN = 0x08 - NON_CJK = 0x10 - ALL = 0x1F - CHINESE = CHINESE_SIMPLIFIED | CHINESE_TRADITIONAL - CJK = CHINESE | JAPANESE | KOREAN - - -class ProbingState(Enum): - """ - This enum represents the different states a prober can be in. - """ - - DETECTING = 0 - FOUND_IT = 1 - NOT_ME = 2 - - -class MachineState: - """ - This enum represents the different states a state machine can be in. - """ - - START = 0 - ERROR = 1 - ITS_ME = 2 - - -class SequenceLikelihood: - """ - This enum represents the likelihood of a character following the previous one. - """ - - NEGATIVE = 0 - UNLIKELY = 1 - LIKELY = 2 - POSITIVE = 3 - - @classmethod - def get_num_categories(cls) -> int: - """:returns: The number of likelihood categories in the enum.""" - return 4 - - -class CharacterCategory: - """ - This enum represents the different categories language models for - ``SingleByteCharsetProber`` put characters into. - - Anything less than CONTROL is considered a letter. - """ - - UNDEFINED = 255 - LINE_BREAK = 254 - SYMBOL = 253 - DIGIT = 252 - CONTROL = 251 diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/escprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/escprober.py deleted file mode 100644 index fd71383..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/escprober.py +++ /dev/null @@ -1,102 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Optional, Union - -from .charsetprober import CharSetProber -from .codingstatemachine import CodingStateMachine -from .enums import LanguageFilter, MachineState, ProbingState -from .escsm import ( - HZ_SM_MODEL, - ISO2022CN_SM_MODEL, - ISO2022JP_SM_MODEL, - ISO2022KR_SM_MODEL, -) - - -class EscCharSetProber(CharSetProber): - """ - This CharSetProber uses a "code scheme" approach for detecting encodings, - whereby easily recognizable escape or shift sequences are relied on to - identify these encodings. - """ - - def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None: - super().__init__(lang_filter=lang_filter) - self.coding_sm = [] - if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED: - self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL)) - self.coding_sm.append(CodingStateMachine(ISO2022CN_SM_MODEL)) - if self.lang_filter & LanguageFilter.JAPANESE: - self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL)) - if self.lang_filter & LanguageFilter.KOREAN: - self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL)) - self.active_sm_count = 0 - self._detected_charset: Optional[str] = None - self._detected_language: Optional[str] = None - self._state = ProbingState.DETECTING - self.reset() - - def reset(self) -> None: - super().reset() - for coding_sm in self.coding_sm: - coding_sm.active = True - coding_sm.reset() - self.active_sm_count = len(self.coding_sm) - self._detected_charset = None - self._detected_language = None - - @property - def charset_name(self) -> Optional[str]: - return self._detected_charset - - @property - def language(self) -> Optional[str]: - return self._detected_language - - def get_confidence(self) -> float: - return 0.99 if self._detected_charset else 0.00 - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - for c in byte_str: - for coding_sm in self.coding_sm: - if not coding_sm.active: - continue - coding_state = coding_sm.next_state(c) - if coding_state == MachineState.ERROR: - coding_sm.active = False - self.active_sm_count -= 1 - if self.active_sm_count <= 0: - self._state = ProbingState.NOT_ME - return self.state - elif coding_state == MachineState.ITS_ME: - self._state = ProbingState.FOUND_IT - self._detected_charset = coding_sm.get_coding_state_machine() - self._detected_language = coding_sm.language - return self.state - - return self.state diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/escsm.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/escsm.py deleted file mode 100644 index 11d4adf..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/escsm.py +++ /dev/null @@ -1,261 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .codingstatemachinedict import CodingStateMachineDict -from .enums import MachineState - -# fmt: off -HZ_CLS = ( - 1, 0, 0, 0, 0, 0, 0, 0, # 00 - 07 - 0, 0, 0, 0, 0, 0, 0, 0, # 08 - 0f - 0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17 - 0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f - 0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27 - 0, 0, 0, 0, 0, 0, 0, 0, # 28 - 2f - 0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37 - 0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f - 0, 0, 0, 0, 0, 0, 0, 0, # 40 - 47 - 0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f - 0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57 - 0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f - 0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67 - 0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f - 0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77 - 0, 0, 0, 4, 0, 5, 2, 0, # 78 - 7f - 1, 1, 1, 1, 1, 1, 1, 1, # 80 - 87 - 1, 1, 1, 1, 1, 1, 1, 1, # 88 - 8f - 1, 1, 1, 1, 1, 1, 1, 1, # 90 - 97 - 1, 1, 1, 1, 1, 1, 1, 1, # 98 - 9f - 1, 1, 1, 1, 1, 1, 1, 1, # a0 - a7 - 1, 1, 1, 1, 1, 1, 1, 1, # a8 - af - 1, 1, 1, 1, 1, 1, 1, 1, # b0 - b7 - 1, 1, 1, 1, 1, 1, 1, 1, # b8 - bf - 1, 1, 1, 1, 1, 1, 1, 1, # c0 - c7 - 1, 1, 1, 1, 1, 1, 1, 1, # c8 - cf - 1, 1, 1, 1, 1, 1, 1, 1, # d0 - d7 - 1, 1, 1, 1, 1, 1, 1, 1, # d8 - df - 1, 1, 1, 1, 1, 1, 1, 1, # e0 - e7 - 1, 1, 1, 1, 1, 1, 1, 1, # e8 - ef - 1, 1, 1, 1, 1, 1, 1, 1, # f0 - f7 - 1, 1, 1, 1, 1, 1, 1, 1, # f8 - ff -) - -HZ_ST = ( -MachineState.START, MachineState.ERROR, 3, MachineState.START, MachineState.START, MachineState.START, MachineState.ERROR, MachineState.ERROR, # 00-07 -MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 08-0f -MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.START, MachineState.START, 4, MachineState.ERROR, # 10-17 - 5, MachineState.ERROR, 6, MachineState.ERROR, 5, 5, 4, MachineState.ERROR, # 18-1f - 4, MachineState.ERROR, 4, 4, 4, MachineState.ERROR, 4, MachineState.ERROR, # 20-27 - 4, MachineState.ITS_ME, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 28-2f -) -# fmt: on - -HZ_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0) - -HZ_SM_MODEL: CodingStateMachineDict = { - "class_table": HZ_CLS, - "class_factor": 6, - "state_table": HZ_ST, - "char_len_table": HZ_CHAR_LEN_TABLE, - "name": "HZ-GB-2312", - "language": "Chinese", -} - -# fmt: off -ISO2022CN_CLS = ( - 2, 0, 0, 0, 0, 0, 0, 0, # 00 - 07 - 0, 0, 0, 0, 0, 0, 0, 0, # 08 - 0f - 0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17 - 0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f - 0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27 - 0, 3, 0, 0, 0, 0, 0, 0, # 28 - 2f - 0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37 - 0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f - 0, 0, 0, 4, 0, 0, 0, 0, # 40 - 47 - 0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f - 0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57 - 0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f - 0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67 - 0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f - 0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77 - 0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f - 2, 2, 2, 2, 2, 2, 2, 2, # 80 - 87 - 2, 2, 2, 2, 2, 2, 2, 2, # 88 - 8f - 2, 2, 2, 2, 2, 2, 2, 2, # 90 - 97 - 2, 2, 2, 2, 2, 2, 2, 2, # 98 - 9f - 2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7 - 2, 2, 2, 2, 2, 2, 2, 2, # a8 - af - 2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7 - 2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf - 2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7 - 2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf - 2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7 - 2, 2, 2, 2, 2, 2, 2, 2, # d8 - df - 2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7 - 2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef - 2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7 - 2, 2, 2, 2, 2, 2, 2, 2, # f8 - ff -) - -ISO2022CN_ST = ( - MachineState.START, 3, MachineState.ERROR, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 00-07 - MachineState.START, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 08-0f - MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 10-17 - MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 4, MachineState.ERROR, # 18-1f - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 20-27 - 5, 6, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 28-2f - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 30-37 - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.START, # 38-3f -) -# fmt: on - -ISO2022CN_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0, 0, 0, 0) - -ISO2022CN_SM_MODEL: CodingStateMachineDict = { - "class_table": ISO2022CN_CLS, - "class_factor": 9, - "state_table": ISO2022CN_ST, - "char_len_table": ISO2022CN_CHAR_LEN_TABLE, - "name": "ISO-2022-CN", - "language": "Chinese", -} - -# fmt: off -ISO2022JP_CLS = ( - 2, 0, 0, 0, 0, 0, 0, 0, # 00 - 07 - 0, 0, 0, 0, 0, 0, 2, 2, # 08 - 0f - 0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17 - 0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f - 0, 0, 0, 0, 7, 0, 0, 0, # 20 - 27 - 3, 0, 0, 0, 0, 0, 0, 0, # 28 - 2f - 0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37 - 0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f - 6, 0, 4, 0, 8, 0, 0, 0, # 40 - 47 - 0, 9, 5, 0, 0, 0, 0, 0, # 48 - 4f - 0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57 - 0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f - 0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67 - 0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f - 0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77 - 0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f - 2, 2, 2, 2, 2, 2, 2, 2, # 80 - 87 - 2, 2, 2, 2, 2, 2, 2, 2, # 88 - 8f - 2, 2, 2, 2, 2, 2, 2, 2, # 90 - 97 - 2, 2, 2, 2, 2, 2, 2, 2, # 98 - 9f - 2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7 - 2, 2, 2, 2, 2, 2, 2, 2, # a8 - af - 2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7 - 2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf - 2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7 - 2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf - 2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7 - 2, 2, 2, 2, 2, 2, 2, 2, # d8 - df - 2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7 - 2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef - 2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7 - 2, 2, 2, 2, 2, 2, 2, 2, # f8 - ff -) - -ISO2022JP_ST = ( - MachineState.START, 3, MachineState.ERROR, MachineState.START, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 00-07 - MachineState.START, MachineState.START, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 08-0f - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 10-17 - MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, # 18-1f - MachineState.ERROR, 5, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 4, MachineState.ERROR, MachineState.ERROR, # 20-27 - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 6, MachineState.ITS_ME, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, # 28-2f - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, # 30-37 - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 38-3f - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ERROR, MachineState.START, MachineState.START, # 40-47 -) -# fmt: on - -ISO2022JP_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0, 0, 0, 0, 0) - -ISO2022JP_SM_MODEL: CodingStateMachineDict = { - "class_table": ISO2022JP_CLS, - "class_factor": 10, - "state_table": ISO2022JP_ST, - "char_len_table": ISO2022JP_CHAR_LEN_TABLE, - "name": "ISO-2022-JP", - "language": "Japanese", -} - -# fmt: off -ISO2022KR_CLS = ( - 2, 0, 0, 0, 0, 0, 0, 0, # 00 - 07 - 0, 0, 0, 0, 0, 0, 0, 0, # 08 - 0f - 0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17 - 0, 0, 0, 1, 0, 0, 0, 0, # 18 - 1f - 0, 0, 0, 0, 3, 0, 0, 0, # 20 - 27 - 0, 4, 0, 0, 0, 0, 0, 0, # 28 - 2f - 0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37 - 0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f - 0, 0, 0, 5, 0, 0, 0, 0, # 40 - 47 - 0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f - 0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57 - 0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f - 0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67 - 0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f - 0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77 - 0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f - 2, 2, 2, 2, 2, 2, 2, 2, # 80 - 87 - 2, 2, 2, 2, 2, 2, 2, 2, # 88 - 8f - 2, 2, 2, 2, 2, 2, 2, 2, # 90 - 97 - 2, 2, 2, 2, 2, 2, 2, 2, # 98 - 9f - 2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7 - 2, 2, 2, 2, 2, 2, 2, 2, # a8 - af - 2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7 - 2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf - 2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7 - 2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf - 2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7 - 2, 2, 2, 2, 2, 2, 2, 2, # d8 - df - 2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7 - 2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef - 2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7 - 2, 2, 2, 2, 2, 2, 2, 2, # f8 - ff -) - -ISO2022KR_ST = ( - MachineState.START, 3, MachineState.ERROR, MachineState.START, MachineState.START, MachineState.START, MachineState.ERROR, MachineState.ERROR, # 00-07 - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ITS_ME, # 08-0f - MachineState.ITS_ME, MachineState.ITS_ME, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 4, MachineState.ERROR, MachineState.ERROR, # 10-17 - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, 5, MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, # 18-1f - MachineState.ERROR, MachineState.ERROR, MachineState.ERROR, MachineState.ITS_ME, MachineState.START, MachineState.START, MachineState.START, MachineState.START, # 20-27 -) -# fmt: on - -ISO2022KR_CHAR_LEN_TABLE = (0, 0, 0, 0, 0, 0) - -ISO2022KR_SM_MODEL: CodingStateMachineDict = { - "class_table": ISO2022KR_CLS, - "class_factor": 6, - "state_table": ISO2022KR_ST, - "char_len_table": ISO2022KR_CHAR_LEN_TABLE, - "name": "ISO-2022-KR", - "language": "Korean", -} diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/eucjpprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/eucjpprober.py deleted file mode 100644 index 39487f4..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/eucjpprober.py +++ /dev/null @@ -1,102 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Union - -from .chardistribution import EUCJPDistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .enums import MachineState, ProbingState -from .jpcntx import EUCJPContextAnalysis -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import EUCJP_SM_MODEL - - -class EUCJPProber(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL) - self.distribution_analyzer = EUCJPDistributionAnalysis() - self.context_analyzer = EUCJPContextAnalysis() - self.reset() - - def reset(self) -> None: - super().reset() - self.context_analyzer.reset() - - @property - def charset_name(self) -> str: - return "EUC-JP" - - @property - def language(self) -> str: - return "Japanese" - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - assert self.coding_sm is not None - assert self.distribution_analyzer is not None - - for i, byte in enumerate(byte_str): - # PY3K: byte_str is a byte array, so byte is an int, not a byte - coding_state = self.coding_sm.next_state(byte) - if coding_state == MachineState.ERROR: - self.logger.debug( - "%s %s prober hit error at byte %s", - self.charset_name, - self.language, - i, - ) - self._state = ProbingState.NOT_ME - break - if coding_state == MachineState.ITS_ME: - self._state = ProbingState.FOUND_IT - break - if coding_state == MachineState.START: - char_len = self.coding_sm.get_current_charlen() - if i == 0: - self._last_char[1] = byte - self.context_analyzer.feed(self._last_char, char_len) - self.distribution_analyzer.feed(self._last_char, char_len) - else: - self.context_analyzer.feed(byte_str[i - 1 : i + 1], char_len) - self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len) - - self._last_char[0] = byte_str[-1] - - if self.state == ProbingState.DETECTING: - if self.context_analyzer.got_enough_data() and ( - self.get_confidence() > self.SHORTCUT_THRESHOLD - ): - self._state = ProbingState.FOUND_IT - - return self.state - - def get_confidence(self) -> float: - assert self.distribution_analyzer is not None - - context_conf = self.context_analyzer.get_confidence() - distrib_conf = self.distribution_analyzer.get_confidence() - return max(context_conf, distrib_conf) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euckrfreq.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euckrfreq.py deleted file mode 100644 index 7dc3b10..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euckrfreq.py +++ /dev/null @@ -1,196 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -# Sampling from about 20M text materials include literature and computer technology - -# 128 --> 0.79 -# 256 --> 0.92 -# 512 --> 0.986 -# 1024 --> 0.99944 -# 2048 --> 0.99999 -# -# Idea Distribution Ratio = 0.98653 / (1-0.98653) = 73.24 -# Random Distribution Ration = 512 / (2350-512) = 0.279. -# -# Typical Distribution Ratio - -EUCKR_TYPICAL_DISTRIBUTION_RATIO = 6.0 - -EUCKR_TABLE_SIZE = 2352 - -# Char to FreqOrder table , -# fmt: off -EUCKR_CHAR_TO_FREQ_ORDER = ( - 13, 130, 120,1396, 481,1719,1720, 328, 609, 212,1721, 707, 400, 299,1722, 87, -1397,1723, 104, 536,1117,1203,1724,1267, 685,1268, 508,1725,1726,1727,1728,1398, -1399,1729,1730,1731, 141, 621, 326,1057, 368,1732, 267, 488, 20,1733,1269,1734, - 945,1400,1735, 47, 904,1270,1736,1737, 773, 248,1738, 409, 313, 786, 429,1739, - 116, 987, 813,1401, 683, 75,1204, 145,1740,1741,1742,1743, 16, 847, 667, 622, - 708,1744,1745,1746, 966, 787, 304, 129,1747, 60, 820, 123, 676,1748,1749,1750, -1751, 617,1752, 626,1753,1754,1755,1756, 653,1757,1758,1759,1760,1761,1762, 856, - 344,1763,1764,1765,1766, 89, 401, 418, 806, 905, 848,1767,1768,1769, 946,1205, - 709,1770,1118,1771, 241,1772,1773,1774,1271,1775, 569,1776, 999,1777,1778,1779, -1780, 337, 751,1058, 28, 628, 254,1781, 177, 906, 270, 349, 891,1079,1782, 19, -1783, 379,1784, 315,1785, 629, 754,1402, 559,1786, 636, 203,1206,1787, 710, 567, -1788, 935, 814,1789,1790,1207, 766, 528,1791,1792,1208,1793,1794,1795,1796,1797, -1403,1798,1799, 533,1059,1404,1405,1156,1406, 936, 884,1080,1800, 351,1801,1802, -1803,1804,1805, 801,1806,1807,1808,1119,1809,1157, 714, 474,1407,1810, 298, 899, - 885,1811,1120, 802,1158,1812, 892,1813,1814,1408, 659,1815,1816,1121,1817,1818, -1819,1820,1821,1822, 319,1823, 594, 545,1824, 815, 937,1209,1825,1826, 573,1409, -1022,1827,1210,1828,1829,1830,1831,1832,1833, 556, 722, 807,1122,1060,1834, 697, -1835, 900, 557, 715,1836,1410, 540,1411, 752,1159, 294, 597,1211, 976, 803, 770, -1412,1837,1838, 39, 794,1413, 358,1839, 371, 925,1840, 453, 661, 788, 531, 723, - 544,1023,1081, 869, 91,1841, 392, 430, 790, 602,1414, 677,1082, 457,1415,1416, -1842,1843, 475, 327,1024,1417, 795, 121,1844, 733, 403,1418,1845,1846,1847, 300, - 119, 711,1212, 627,1848,1272, 207,1849,1850, 796,1213, 382,1851, 519,1852,1083, - 893,1853,1854,1855, 367, 809, 487, 671,1856, 663,1857,1858, 956, 471, 306, 857, -1859,1860,1160,1084,1861,1862,1863,1864,1865,1061,1866,1867,1868,1869,1870,1871, - 282, 96, 574,1872, 502,1085,1873,1214,1874, 907,1875,1876, 827, 977,1419,1420, -1421, 268,1877,1422,1878,1879,1880, 308,1881, 2, 537,1882,1883,1215,1884,1885, - 127, 791,1886,1273,1423,1887, 34, 336, 404, 643,1888, 571, 654, 894, 840,1889, - 0, 886,1274, 122, 575, 260, 908, 938,1890,1275, 410, 316,1891,1892, 100,1893, -1894,1123, 48,1161,1124,1025,1895, 633, 901,1276,1896,1897, 115, 816,1898, 317, -1899, 694,1900, 909, 734,1424, 572, 866,1425, 691, 85, 524,1010, 543, 394, 841, -1901,1902,1903,1026,1904,1905,1906,1907,1908,1909, 30, 451, 651, 988, 310,1910, -1911,1426, 810,1216, 93,1912,1913,1277,1217,1914, 858, 759, 45, 58, 181, 610, - 269,1915,1916, 131,1062, 551, 443,1000, 821,1427, 957, 895,1086,1917,1918, 375, -1919, 359,1920, 687,1921, 822,1922, 293,1923,1924, 40, 662, 118, 692, 29, 939, - 887, 640, 482, 174,1925, 69,1162, 728,1428, 910,1926,1278,1218,1279, 386, 870, - 217, 854,1163, 823,1927,1928,1929,1930, 834,1931, 78,1932, 859,1933,1063,1934, -1935,1936,1937, 438,1164, 208, 595,1938,1939,1940,1941,1219,1125,1942, 280, 888, -1429,1430,1220,1431,1943,1944,1945,1946,1947,1280, 150, 510,1432,1948,1949,1950, -1951,1952,1953,1954,1011,1087,1955,1433,1043,1956, 881,1957, 614, 958,1064,1065, -1221,1958, 638,1001, 860, 967, 896,1434, 989, 492, 553,1281,1165,1959,1282,1002, -1283,1222,1960,1961,1962,1963, 36, 383, 228, 753, 247, 454,1964, 876, 678,1965, -1966,1284, 126, 464, 490, 835, 136, 672, 529, 940,1088,1435, 473,1967,1968, 467, - 50, 390, 227, 587, 279, 378, 598, 792, 968, 240, 151, 160, 849, 882,1126,1285, - 639,1044, 133, 140, 288, 360, 811, 563,1027, 561, 142, 523,1969,1970,1971, 7, - 103, 296, 439, 407, 506, 634, 990,1972,1973,1974,1975, 645,1976,1977,1978,1979, -1980,1981, 236,1982,1436,1983,1984,1089, 192, 828, 618, 518,1166, 333,1127,1985, - 818,1223,1986,1987,1988,1989,1990,1991,1992,1993, 342,1128,1286, 746, 842,1994, -1995, 560, 223,1287, 98, 8, 189, 650, 978,1288,1996,1437,1997, 17, 345, 250, - 423, 277, 234, 512, 226, 97, 289, 42, 167,1998, 201,1999,2000, 843, 836, 824, - 532, 338, 783,1090, 182, 576, 436,1438,1439, 527, 500,2001, 947, 889,2002,2003, -2004,2005, 262, 600, 314, 447,2006, 547,2007, 693, 738,1129,2008, 71,1440, 745, - 619, 688,2009, 829,2010,2011, 147,2012, 33, 948,2013,2014, 74, 224,2015, 61, - 191, 918, 399, 637,2016,1028,1130, 257, 902,2017,2018,2019,2020,2021,2022,2023, -2024,2025,2026, 837,2027,2028,2029,2030, 179, 874, 591, 52, 724, 246,2031,2032, -2033,2034,1167, 969,2035,1289, 630, 605, 911,1091,1168,2036,2037,2038,1441, 912, -2039, 623,2040,2041, 253,1169,1290,2042,1442, 146, 620, 611, 577, 433,2043,1224, - 719,1170, 959, 440, 437, 534, 84, 388, 480,1131, 159, 220, 198, 679,2044,1012, - 819,1066,1443, 113,1225, 194, 318,1003,1029,2045,2046,2047,2048,1067,2049,2050, -2051,2052,2053, 59, 913, 112,2054, 632,2055, 455, 144, 739,1291,2056, 273, 681, - 499,2057, 448,2058,2059, 760,2060,2061, 970, 384, 169, 245,1132,2062,2063, 414, -1444,2064,2065, 41, 235,2066, 157, 252, 877, 568, 919, 789, 580,2067, 725,2068, -2069,1292,2070,2071,1445,2072,1446,2073,2074, 55, 588, 66,1447, 271,1092,2075, -1226,2076, 960,1013, 372,2077,2078,2079,2080,2081,1293,2082,2083,2084,2085, 850, -2086,2087,2088,2089,2090, 186,2091,1068, 180,2092,2093,2094, 109,1227, 522, 606, -2095, 867,1448,1093, 991,1171, 926, 353,1133,2096, 581,2097,2098,2099,1294,1449, -1450,2100, 596,1172,1014,1228,2101,1451,1295,1173,1229,2102,2103,1296,1134,1452, - 949,1135,2104,2105,1094,1453,1454,1455,2106,1095,2107,2108,2109,2110,2111,2112, -2113,2114,2115,2116,2117, 804,2118,2119,1230,1231, 805,1456, 405,1136,2120,2121, -2122,2123,2124, 720, 701,1297, 992,1457, 927,1004,2125,2126,2127,2128,2129,2130, - 22, 417,2131, 303,2132, 385,2133, 971, 520, 513,2134,1174, 73,1096, 231, 274, - 962,1458, 673,2135,1459,2136, 152,1137,2137,2138,2139,2140,1005,1138,1460,1139, -2141,2142,2143,2144, 11, 374, 844,2145, 154,1232, 46,1461,2146, 838, 830, 721, -1233, 106,2147, 90, 428, 462, 578, 566,1175, 352,2148,2149, 538,1234, 124,1298, -2150,1462, 761, 565,2151, 686,2152, 649,2153, 72, 173,2154, 460, 415,2155,1463, -2156,1235, 305,2157,2158,2159,2160,2161,2162, 579,2163,2164,2165,2166,2167, 747, -2168,2169,2170,2171,1464, 669,2172,2173,2174,2175,2176,1465,2177, 23, 530, 285, -2178, 335, 729,2179, 397,2180,2181,2182,1030,2183,2184, 698,2185,2186, 325,2187, -2188, 369,2189, 799,1097,1015, 348,2190,1069, 680,2191, 851,1466,2192,2193, 10, -2194, 613, 424,2195, 979, 108, 449, 589, 27, 172, 81,1031, 80, 774, 281, 350, -1032, 525, 301, 582,1176,2196, 674,1045,2197,2198,1467, 730, 762,2199,2200,2201, -2202,1468,2203, 993,2204,2205, 266,1070, 963,1140,2206,2207,2208, 664,1098, 972, -2209,2210,2211,1177,1469,1470, 871,2212,2213,2214,2215,2216,1471,2217,2218,2219, -2220,2221,2222,2223,2224,2225,2226,2227,1472,1236,2228,2229,2230,2231,2232,2233, -2234,2235,1299,2236,2237, 200,2238, 477, 373,2239,2240, 731, 825, 777,2241,2242, -2243, 521, 486, 548,2244,2245,2246,1473,1300, 53, 549, 137, 875, 76, 158,2247, -1301,1474, 469, 396,1016, 278, 712,2248, 321, 442, 503, 767, 744, 941,1237,1178, -1475,2249, 82, 178,1141,1179, 973,2250,1302,2251, 297,2252,2253, 570,2254,2255, -2256, 18, 450, 206,2257, 290, 292,1142,2258, 511, 162, 99, 346, 164, 735,2259, -1476,1477, 4, 554, 343, 798,1099,2260,1100,2261, 43, 171,1303, 139, 215,2262, -2263, 717, 775,2264,1033, 322, 216,2265, 831,2266, 149,2267,1304,2268,2269, 702, -1238, 135, 845, 347, 309,2270, 484,2271, 878, 655, 238,1006,1478,2272, 67,2273, - 295,2274,2275, 461,2276, 478, 942, 412,2277,1034,2278,2279,2280, 265,2281, 541, -2282,2283,2284,2285,2286, 70, 852,1071,2287,2288,2289,2290, 21, 56, 509, 117, - 432,2291,2292, 331, 980, 552,1101, 148, 284, 105, 393,1180,1239, 755,2293, 187, -2294,1046,1479,2295, 340,2296, 63,1047, 230,2297,2298,1305, 763,1306, 101, 800, - 808, 494,2299,2300,2301, 903,2302, 37,1072, 14, 5,2303, 79, 675,2304, 312, -2305,2306,2307,2308,2309,1480, 6,1307,2310,2311,2312, 1, 470, 35, 24, 229, -2313, 695, 210, 86, 778, 15, 784, 592, 779, 32, 77, 855, 964,2314, 259,2315, - 501, 380,2316,2317, 83, 981, 153, 689,1308,1481,1482,1483,2318,2319, 716,1484, -2320,2321,2322,2323,2324,2325,1485,2326,2327, 128, 57, 68, 261,1048, 211, 170, -1240, 31,2328, 51, 435, 742,2329,2330,2331, 635,2332, 264, 456,2333,2334,2335, - 425,2336,1486, 143, 507, 263, 943,2337, 363, 920,1487, 256,1488,1102, 243, 601, -1489,2338,2339,2340,2341,2342,2343,2344, 861,2345,2346,2347,2348,2349,2350, 395, -2351,1490,1491, 62, 535, 166, 225,2352,2353, 668, 419,1241, 138, 604, 928,2354, -1181,2355,1492,1493,2356,2357,2358,1143,2359, 696,2360, 387, 307,1309, 682, 476, -2361,2362, 332, 12, 222, 156,2363, 232,2364, 641, 276, 656, 517,1494,1495,1035, - 416, 736,1496,2365,1017, 586,2366,2367,2368,1497,2369, 242,2370,2371,2372,1498, -2373, 965, 713,2374,2375,2376,2377, 740, 982,1499, 944,1500,1007,2378,2379,1310, -1501,2380,2381,2382, 785, 329,2383,2384,1502,2385,2386,2387, 932,2388,1503,2389, -2390,2391,2392,1242,2393,2394,2395,2396,2397, 994, 950,2398,2399,2400,2401,1504, -1311,2402,2403,2404,2405,1049, 749,2406,2407, 853, 718,1144,1312,2408,1182,1505, -2409,2410, 255, 516, 479, 564, 550, 214,1506,1507,1313, 413, 239, 444, 339,1145, -1036,1508,1509,1314,1037,1510,1315,2411,1511,2412,2413,2414, 176, 703, 497, 624, - 593, 921, 302,2415, 341, 165,1103,1512,2416,1513,2417,2418,2419, 376,2420, 700, -2421,2422,2423, 258, 768,1316,2424,1183,2425, 995, 608,2426,2427,2428,2429, 221, -2430,2431,2432,2433,2434,2435,2436,2437, 195, 323, 726, 188, 897, 983,1317, 377, - 644,1050, 879,2438, 452,2439,2440,2441,2442,2443,2444, 914,2445,2446,2447,2448, - 915, 489,2449,1514,1184,2450,2451, 515, 64, 427, 495,2452, 583,2453, 483, 485, -1038, 562, 213,1515, 748, 666,2454,2455,2456,2457, 334,2458, 780, 996,1008, 705, -1243,2459,2460,2461,2462,2463, 114,2464, 493,1146, 366, 163,1516, 961,1104,2465, - 291,2466,1318,1105,2467,1517, 365,2468, 355, 951,1244,2469,1319,2470, 631,2471, -2472, 218,1320, 364, 320, 756,1518,1519,1321,1520,1322,2473,2474,2475,2476, 997, -2477,2478,2479,2480, 665,1185,2481, 916,1521,2482,2483,2484, 584, 684,2485,2486, - 797,2487,1051,1186,2488,2489,2490,1522,2491,2492, 370,2493,1039,1187, 65,2494, - 434, 205, 463,1188,2495, 125, 812, 391, 402, 826, 699, 286, 398, 155, 781, 771, - 585,2496, 590, 505,1073,2497, 599, 244, 219, 917,1018, 952, 646,1523,2498,1323, -2499,2500, 49, 984, 354, 741,2501, 625,2502,1324,2503,1019, 190, 357, 757, 491, - 95, 782, 868,2504,2505,2506,2507,2508,2509, 134,1524,1074, 422,1525, 898,2510, - 161,2511,2512,2513,2514, 769,2515,1526,2516,2517, 411,1325,2518, 472,1527,2519, -2520,2521,2522,2523,2524, 985,2525,2526,2527,2528,2529,2530, 764,2531,1245,2532, -2533, 25, 204, 311,2534, 496,2535,1052,2536,2537,2538,2539,2540,2541,2542, 199, - 704, 504, 468, 758, 657,1528, 196, 44, 839,1246, 272, 750,2543, 765, 862,2544, -2545,1326,2546, 132, 615, 933,2547, 732,2548,2549,2550,1189,1529,2551, 283,1247, -1053, 607, 929,2552,2553,2554, 930, 183, 872, 616,1040,1147,2555,1148,1020, 441, - 249,1075,2556,2557,2558, 466, 743,2559,2560,2561, 92, 514, 426, 420, 526,2562, -2563,2564,2565,2566,2567,2568, 185,2569,2570,2571,2572, 776,1530, 658,2573, 362, -2574, 361, 922,1076, 793,2575,2576,2577,2578,2579,2580,1531, 251,2581,2582,2583, -2584,1532, 54, 612, 237,1327,2585,2586, 275, 408, 647, 111,2587,1533,1106, 465, - 3, 458, 9, 38,2588, 107, 110, 890, 209, 26, 737, 498,2589,1534,2590, 431, - 202, 88,1535, 356, 287,1107, 660,1149,2591, 381,1536, 986,1150, 445,1248,1151, - 974,2592,2593, 846,2594, 446, 953, 184,1249,1250, 727,2595, 923, 193, 883,2596, -2597,2598, 102, 324, 539, 817,2599, 421,1041,2600, 832,2601, 94, 175, 197, 406, -2602, 459,2603,2604,2605,2606,2607, 330, 555,2608,2609,2610, 706,1108, 389,2611, -2612,2613,2614, 233,2615, 833, 558, 931, 954,1251,2616,2617,1537, 546,2618,2619, -1009,2620,2621,2622,1538, 690,1328,2623, 955,2624,1539,2625,2626, 772,2627,2628, -2629,2630,2631, 924, 648, 863, 603,2632,2633, 934,1540, 864, 865,2634, 642,1042, - 670,1190,2635,2636,2637,2638, 168,2639, 652, 873, 542,1054,1541,2640,2641,2642, # 512, 256 -) -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euckrprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euckrprober.py deleted file mode 100644 index 1fc5de0..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euckrprober.py +++ /dev/null @@ -1,47 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .chardistribution import EUCKRDistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import EUCKR_SM_MODEL - - -class EUCKRProber(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(EUCKR_SM_MODEL) - self.distribution_analyzer = EUCKRDistributionAnalysis() - self.reset() - - @property - def charset_name(self) -> str: - return "EUC-KR" - - @property - def language(self) -> str: - return "Korean" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euctwfreq.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euctwfreq.py deleted file mode 100644 index 4900ccc..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euctwfreq.py +++ /dev/null @@ -1,388 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -# EUCTW frequency table -# Converted from big5 work -# by Taiwan's Mandarin Promotion Council -# - -# 128 --> 0.42261 -# 256 --> 0.57851 -# 512 --> 0.74851 -# 1024 --> 0.89384 -# 2048 --> 0.97583 -# -# Idea Distribution Ratio = 0.74851/(1-0.74851) =2.98 -# Random Distribution Ration = 512/(5401-512)=0.105 -# -# Typical Distribution Ratio about 25% of Ideal one, still much higher than RDR - -EUCTW_TYPICAL_DISTRIBUTION_RATIO = 0.75 - -# Char to FreqOrder table -EUCTW_TABLE_SIZE = 5376 - -# fmt: off -EUCTW_CHAR_TO_FREQ_ORDER = ( - 1, 1800, 1506, 255, 1431, 198, 9, 82, 6, 7310, 177, 202, 3615, 1256, 2808, 110, # 2742 - 3735, 33, 3241, 261, 76, 44, 2113, 16, 2931, 2184, 1176, 659, 3868, 26, 3404, 2643, # 2758 - 1198, 3869, 3313, 4060, 410, 2211, 302, 590, 361, 1963, 8, 204, 58, 4296, 7311, 1931, # 2774 - 63, 7312, 7313, 317, 1614, 75, 222, 159, 4061, 2412, 1480, 7314, 3500, 3068, 224, 2809, # 2790 - 3616, 3, 10, 3870, 1471, 29, 2774, 1135, 2852, 1939, 873, 130, 3242, 1123, 312, 7315, # 2806 - 4297, 2051, 507, 252, 682, 7316, 142, 1914, 124, 206, 2932, 34, 3501, 3173, 64, 604, # 2822 - 7317, 2494, 1976, 1977, 155, 1990, 645, 641, 1606, 7318, 3405, 337, 72, 406, 7319, 80, # 2838 - 630, 238, 3174, 1509, 263, 939, 1092, 2644, 756, 1440, 1094, 3406, 449, 69, 2969, 591, # 2854 - 179, 2095, 471, 115, 2034, 1843, 60, 50, 2970, 134, 806, 1868, 734, 2035, 3407, 180, # 2870 - 995, 1607, 156, 537, 2893, 688, 7320, 319, 1305, 779, 2144, 514, 2374, 298, 4298, 359, # 2886 - 2495, 90, 2707, 1338, 663, 11, 906, 1099, 2545, 20, 2436, 182, 532, 1716, 7321, 732, # 2902 - 1376, 4062, 1311, 1420, 3175, 25, 2312, 1056, 113, 399, 382, 1949, 242, 3408, 2467, 529, # 2918 - 3243, 475, 1447, 3617, 7322, 117, 21, 656, 810, 1297, 2295, 2329, 3502, 7323, 126, 4063, # 2934 - 706, 456, 150, 613, 4299, 71, 1118, 2036, 4064, 145, 3069, 85, 835, 486, 2114, 1246, # 2950 - 1426, 428, 727, 1285, 1015, 800, 106, 623, 303, 1281, 7324, 2127, 2354, 347, 3736, 221, # 2966 - 3503, 3110, 7325, 1955, 1153, 4065, 83, 296, 1199, 3070, 192, 624, 93, 7326, 822, 1897, # 2982 - 2810, 3111, 795, 2064, 991, 1554, 1542, 1592, 27, 43, 2853, 859, 139, 1456, 860, 4300, # 2998 - 437, 712, 3871, 164, 2392, 3112, 695, 211, 3017, 2096, 195, 3872, 1608, 3504, 3505, 3618, # 3014 - 3873, 234, 811, 2971, 2097, 3874, 2229, 1441, 3506, 1615, 2375, 668, 2076, 1638, 305, 228, # 3030 - 1664, 4301, 467, 415, 7327, 262, 2098, 1593, 239, 108, 300, 200, 1033, 512, 1247, 2077, # 3046 - 7328, 7329, 2173, 3176, 3619, 2673, 593, 845, 1062, 3244, 88, 1723, 2037, 3875, 1950, 212, # 3062 - 266, 152, 149, 468, 1898, 4066, 4302, 77, 187, 7330, 3018, 37, 5, 2972, 7331, 3876, # 3078 - 7332, 7333, 39, 2517, 4303, 2894, 3177, 2078, 55, 148, 74, 4304, 545, 483, 1474, 1029, # 3094 - 1665, 217, 1869, 1531, 3113, 1104, 2645, 4067, 24, 172, 3507, 900, 3877, 3508, 3509, 4305, # 3110 - 32, 1408, 2811, 1312, 329, 487, 2355, 2247, 2708, 784, 2674, 4, 3019, 3314, 1427, 1788, # 3126 - 188, 109, 499, 7334, 3620, 1717, 1789, 888, 1217, 3020, 4306, 7335, 3510, 7336, 3315, 1520, # 3142 - 3621, 3878, 196, 1034, 775, 7337, 7338, 929, 1815, 249, 439, 38, 7339, 1063, 7340, 794, # 3158 - 3879, 1435, 2296, 46, 178, 3245, 2065, 7341, 2376, 7342, 214, 1709, 4307, 804, 35, 707, # 3174 - 324, 3622, 1601, 2546, 140, 459, 4068, 7343, 7344, 1365, 839, 272, 978, 2257, 2572, 3409, # 3190 - 2128, 1363, 3623, 1423, 697, 100, 3071, 48, 70, 1231, 495, 3114, 2193, 7345, 1294, 7346, # 3206 - 2079, 462, 586, 1042, 3246, 853, 256, 988, 185, 2377, 3410, 1698, 434, 1084, 7347, 3411, # 3222 - 314, 2615, 2775, 4308, 2330, 2331, 569, 2280, 637, 1816, 2518, 757, 1162, 1878, 1616, 3412, # 3238 - 287, 1577, 2115, 768, 4309, 1671, 2854, 3511, 2519, 1321, 3737, 909, 2413, 7348, 4069, 933, # 3254 - 3738, 7349, 2052, 2356, 1222, 4310, 765, 2414, 1322, 786, 4311, 7350, 1919, 1462, 1677, 2895, # 3270 - 1699, 7351, 4312, 1424, 2437, 3115, 3624, 2590, 3316, 1774, 1940, 3413, 3880, 4070, 309, 1369, # 3286 - 1130, 2812, 364, 2230, 1653, 1299, 3881, 3512, 3882, 3883, 2646, 525, 1085, 3021, 902, 2000, # 3302 - 1475, 964, 4313, 421, 1844, 1415, 1057, 2281, 940, 1364, 3116, 376, 4314, 4315, 1381, 7, # 3318 - 2520, 983, 2378, 336, 1710, 2675, 1845, 321, 3414, 559, 1131, 3022, 2742, 1808, 1132, 1313, # 3334 - 265, 1481, 1857, 7352, 352, 1203, 2813, 3247, 167, 1089, 420, 2814, 776, 792, 1724, 3513, # 3350 - 4071, 2438, 3248, 7353, 4072, 7354, 446, 229, 333, 2743, 901, 3739, 1200, 1557, 4316, 2647, # 3366 - 1920, 395, 2744, 2676, 3740, 4073, 1835, 125, 916, 3178, 2616, 4317, 7355, 7356, 3741, 7357, # 3382 - 7358, 7359, 4318, 3117, 3625, 1133, 2547, 1757, 3415, 1510, 2313, 1409, 3514, 7360, 2145, 438, # 3398 - 2591, 2896, 2379, 3317, 1068, 958, 3023, 461, 311, 2855, 2677, 4074, 1915, 3179, 4075, 1978, # 3414 - 383, 750, 2745, 2617, 4076, 274, 539, 385, 1278, 1442, 7361, 1154, 1964, 384, 561, 210, # 3430 - 98, 1295, 2548, 3515, 7362, 1711, 2415, 1482, 3416, 3884, 2897, 1257, 129, 7363, 3742, 642, # 3446 - 523, 2776, 2777, 2648, 7364, 141, 2231, 1333, 68, 176, 441, 876, 907, 4077, 603, 2592, # 3462 - 710, 171, 3417, 404, 549, 18, 3118, 2393, 1410, 3626, 1666, 7365, 3516, 4319, 2898, 4320, # 3478 - 7366, 2973, 368, 7367, 146, 366, 99, 871, 3627, 1543, 748, 807, 1586, 1185, 22, 2258, # 3494 - 379, 3743, 3180, 7368, 3181, 505, 1941, 2618, 1991, 1382, 2314, 7369, 380, 2357, 218, 702, # 3510 - 1817, 1248, 3418, 3024, 3517, 3318, 3249, 7370, 2974, 3628, 930, 3250, 3744, 7371, 59, 7372, # 3526 - 585, 601, 4078, 497, 3419, 1112, 1314, 4321, 1801, 7373, 1223, 1472, 2174, 7374, 749, 1836, # 3542 - 690, 1899, 3745, 1772, 3885, 1476, 429, 1043, 1790, 2232, 2116, 917, 4079, 447, 1086, 1629, # 3558 - 7375, 556, 7376, 7377, 2020, 1654, 844, 1090, 105, 550, 966, 1758, 2815, 1008, 1782, 686, # 3574 - 1095, 7378, 2282, 793, 1602, 7379, 3518, 2593, 4322, 4080, 2933, 2297, 4323, 3746, 980, 2496, # 3590 - 544, 353, 527, 4324, 908, 2678, 2899, 7380, 381, 2619, 1942, 1348, 7381, 1341, 1252, 560, # 3606 - 3072, 7382, 3420, 2856, 7383, 2053, 973, 886, 2080, 143, 4325, 7384, 7385, 157, 3886, 496, # 3622 - 4081, 57, 840, 540, 2038, 4326, 4327, 3421, 2117, 1445, 970, 2259, 1748, 1965, 2081, 4082, # 3638 - 3119, 1234, 1775, 3251, 2816, 3629, 773, 1206, 2129, 1066, 2039, 1326, 3887, 1738, 1725, 4083, # 3654 - 279, 3120, 51, 1544, 2594, 423, 1578, 2130, 2066, 173, 4328, 1879, 7386, 7387, 1583, 264, # 3670 - 610, 3630, 4329, 2439, 280, 154, 7388, 7389, 7390, 1739, 338, 1282, 3073, 693, 2857, 1411, # 3686 - 1074, 3747, 2440, 7391, 4330, 7392, 7393, 1240, 952, 2394, 7394, 2900, 1538, 2679, 685, 1483, # 3702 - 4084, 2468, 1436, 953, 4085, 2054, 4331, 671, 2395, 79, 4086, 2441, 3252, 608, 567, 2680, # 3718 - 3422, 4087, 4088, 1691, 393, 1261, 1791, 2396, 7395, 4332, 7396, 7397, 7398, 7399, 1383, 1672, # 3734 - 3748, 3182, 1464, 522, 1119, 661, 1150, 216, 675, 4333, 3888, 1432, 3519, 609, 4334, 2681, # 3750 - 2397, 7400, 7401, 7402, 4089, 3025, 0, 7403, 2469, 315, 231, 2442, 301, 3319, 4335, 2380, # 3766 - 7404, 233, 4090, 3631, 1818, 4336, 4337, 7405, 96, 1776, 1315, 2082, 7406, 257, 7407, 1809, # 3782 - 3632, 2709, 1139, 1819, 4091, 2021, 1124, 2163, 2778, 1777, 2649, 7408, 3074, 363, 1655, 3183, # 3798 - 7409, 2975, 7410, 7411, 7412, 3889, 1567, 3890, 718, 103, 3184, 849, 1443, 341, 3320, 2934, # 3814 - 1484, 7413, 1712, 127, 67, 339, 4092, 2398, 679, 1412, 821, 7414, 7415, 834, 738, 351, # 3830 - 2976, 2146, 846, 235, 1497, 1880, 418, 1992, 3749, 2710, 186, 1100, 2147, 2746, 3520, 1545, # 3846 - 1355, 2935, 2858, 1377, 583, 3891, 4093, 2573, 2977, 7416, 1298, 3633, 1078, 2549, 3634, 2358, # 3862 - 78, 3750, 3751, 267, 1289, 2099, 2001, 1594, 4094, 348, 369, 1274, 2194, 2175, 1837, 4338, # 3878 - 1820, 2817, 3635, 2747, 2283, 2002, 4339, 2936, 2748, 144, 3321, 882, 4340, 3892, 2749, 3423, # 3894 - 4341, 2901, 7417, 4095, 1726, 320, 7418, 3893, 3026, 788, 2978, 7419, 2818, 1773, 1327, 2859, # 3910 - 3894, 2819, 7420, 1306, 4342, 2003, 1700, 3752, 3521, 2359, 2650, 787, 2022, 506, 824, 3636, # 3926 - 534, 323, 4343, 1044, 3322, 2023, 1900, 946, 3424, 7421, 1778, 1500, 1678, 7422, 1881, 4344, # 3942 - 165, 243, 4345, 3637, 2521, 123, 683, 4096, 764, 4346, 36, 3895, 1792, 589, 2902, 816, # 3958 - 626, 1667, 3027, 2233, 1639, 1555, 1622, 3753, 3896, 7423, 3897, 2860, 1370, 1228, 1932, 891, # 3974 - 2083, 2903, 304, 4097, 7424, 292, 2979, 2711, 3522, 691, 2100, 4098, 1115, 4347, 118, 662, # 3990 - 7425, 611, 1156, 854, 2381, 1316, 2861, 2, 386, 515, 2904, 7426, 7427, 3253, 868, 2234, # 4006 - 1486, 855, 2651, 785, 2212, 3028, 7428, 1040, 3185, 3523, 7429, 3121, 448, 7430, 1525, 7431, # 4022 - 2164, 4348, 7432, 3754, 7433, 4099, 2820, 3524, 3122, 503, 818, 3898, 3123, 1568, 814, 676, # 4038 - 1444, 306, 1749, 7434, 3755, 1416, 1030, 197, 1428, 805, 2821, 1501, 4349, 7435, 7436, 7437, # 4054 - 1993, 7438, 4350, 7439, 7440, 2195, 13, 2779, 3638, 2980, 3124, 1229, 1916, 7441, 3756, 2131, # 4070 - 7442, 4100, 4351, 2399, 3525, 7443, 2213, 1511, 1727, 1120, 7444, 7445, 646, 3757, 2443, 307, # 4086 - 7446, 7447, 1595, 3186, 7448, 7449, 7450, 3639, 1113, 1356, 3899, 1465, 2522, 2523, 7451, 519, # 4102 - 7452, 128, 2132, 92, 2284, 1979, 7453, 3900, 1512, 342, 3125, 2196, 7454, 2780, 2214, 1980, # 4118 - 3323, 7455, 290, 1656, 1317, 789, 827, 2360, 7456, 3758, 4352, 562, 581, 3901, 7457, 401, # 4134 - 4353, 2248, 94, 4354, 1399, 2781, 7458, 1463, 2024, 4355, 3187, 1943, 7459, 828, 1105, 4101, # 4150 - 1262, 1394, 7460, 4102, 605, 4356, 7461, 1783, 2862, 7462, 2822, 819, 2101, 578, 2197, 2937, # 4166 - 7463, 1502, 436, 3254, 4103, 3255, 2823, 3902, 2905, 3425, 3426, 7464, 2712, 2315, 7465, 7466, # 4182 - 2332, 2067, 23, 4357, 193, 826, 3759, 2102, 699, 1630, 4104, 3075, 390, 1793, 1064, 3526, # 4198 - 7467, 1579, 3076, 3077, 1400, 7468, 4105, 1838, 1640, 2863, 7469, 4358, 4359, 137, 4106, 598, # 4214 - 3078, 1966, 780, 104, 974, 2938, 7470, 278, 899, 253, 402, 572, 504, 493, 1339, 7471, # 4230 - 3903, 1275, 4360, 2574, 2550, 7472, 3640, 3029, 3079, 2249, 565, 1334, 2713, 863, 41, 7473, # 4246 - 7474, 4361, 7475, 1657, 2333, 19, 463, 2750, 4107, 606, 7476, 2981, 3256, 1087, 2084, 1323, # 4262 - 2652, 2982, 7477, 1631, 1623, 1750, 4108, 2682, 7478, 2864, 791, 2714, 2653, 2334, 232, 2416, # 4278 - 7479, 2983, 1498, 7480, 2654, 2620, 755, 1366, 3641, 3257, 3126, 2025, 1609, 119, 1917, 3427, # 4294 - 862, 1026, 4109, 7481, 3904, 3760, 4362, 3905, 4363, 2260, 1951, 2470, 7482, 1125, 817, 4110, # 4310 - 4111, 3906, 1513, 1766, 2040, 1487, 4112, 3030, 3258, 2824, 3761, 3127, 7483, 7484, 1507, 7485, # 4326 - 2683, 733, 40, 1632, 1106, 2865, 345, 4113, 841, 2524, 230, 4364, 2984, 1846, 3259, 3428, # 4342 - 7486, 1263, 986, 3429, 7487, 735, 879, 254, 1137, 857, 622, 1300, 1180, 1388, 1562, 3907, # 4358 - 3908, 2939, 967, 2751, 2655, 1349, 592, 2133, 1692, 3324, 2985, 1994, 4114, 1679, 3909, 1901, # 4374 - 2185, 7488, 739, 3642, 2715, 1296, 1290, 7489, 4115, 2198, 2199, 1921, 1563, 2595, 2551, 1870, # 4390 - 2752, 2986, 7490, 435, 7491, 343, 1108, 596, 17, 1751, 4365, 2235, 3430, 3643, 7492, 4366, # 4406 - 294, 3527, 2940, 1693, 477, 979, 281, 2041, 3528, 643, 2042, 3644, 2621, 2782, 2261, 1031, # 4422 - 2335, 2134, 2298, 3529, 4367, 367, 1249, 2552, 7493, 3530, 7494, 4368, 1283, 3325, 2004, 240, # 4438 - 1762, 3326, 4369, 4370, 836, 1069, 3128, 474, 7495, 2148, 2525, 268, 3531, 7496, 3188, 1521, # 4454 - 1284, 7497, 1658, 1546, 4116, 7498, 3532, 3533, 7499, 4117, 3327, 2684, 1685, 4118, 961, 1673, # 4470 - 2622, 190, 2005, 2200, 3762, 4371, 4372, 7500, 570, 2497, 3645, 1490, 7501, 4373, 2623, 3260, # 4486 - 1956, 4374, 584, 1514, 396, 1045, 1944, 7502, 4375, 1967, 2444, 7503, 7504, 4376, 3910, 619, # 4502 - 7505, 3129, 3261, 215, 2006, 2783, 2553, 3189, 4377, 3190, 4378, 763, 4119, 3763, 4379, 7506, # 4518 - 7507, 1957, 1767, 2941, 3328, 3646, 1174, 452, 1477, 4380, 3329, 3130, 7508, 2825, 1253, 2382, # 4534 - 2186, 1091, 2285, 4120, 492, 7509, 638, 1169, 1824, 2135, 1752, 3911, 648, 926, 1021, 1324, # 4550 - 4381, 520, 4382, 997, 847, 1007, 892, 4383, 3764, 2262, 1871, 3647, 7510, 2400, 1784, 4384, # 4566 - 1952, 2942, 3080, 3191, 1728, 4121, 2043, 3648, 4385, 2007, 1701, 3131, 1551, 30, 2263, 4122, # 4582 - 7511, 2026, 4386, 3534, 7512, 501, 7513, 4123, 594, 3431, 2165, 1821, 3535, 3432, 3536, 3192, # 4598 - 829, 2826, 4124, 7514, 1680, 3132, 1225, 4125, 7515, 3262, 4387, 4126, 3133, 2336, 7516, 4388, # 4614 - 4127, 7517, 3912, 3913, 7518, 1847, 2383, 2596, 3330, 7519, 4389, 374, 3914, 652, 4128, 4129, # 4630 - 375, 1140, 798, 7520, 7521, 7522, 2361, 4390, 2264, 546, 1659, 138, 3031, 2445, 4391, 7523, # 4646 - 2250, 612, 1848, 910, 796, 3765, 1740, 1371, 825, 3766, 3767, 7524, 2906, 2554, 7525, 692, # 4662 - 444, 3032, 2624, 801, 4392, 4130, 7526, 1491, 244, 1053, 3033, 4131, 4132, 340, 7527, 3915, # 4678 - 1041, 2987, 293, 1168, 87, 1357, 7528, 1539, 959, 7529, 2236, 721, 694, 4133, 3768, 219, # 4694 - 1478, 644, 1417, 3331, 2656, 1413, 1401, 1335, 1389, 3916, 7530, 7531, 2988, 2362, 3134, 1825, # 4710 - 730, 1515, 184, 2827, 66, 4393, 7532, 1660, 2943, 246, 3332, 378, 1457, 226, 3433, 975, # 4726 - 3917, 2944, 1264, 3537, 674, 696, 7533, 163, 7534, 1141, 2417, 2166, 713, 3538, 3333, 4394, # 4742 - 3918, 7535, 7536, 1186, 15, 7537, 1079, 1070, 7538, 1522, 3193, 3539, 276, 1050, 2716, 758, # 4758 - 1126, 653, 2945, 3263, 7539, 2337, 889, 3540, 3919, 3081, 2989, 903, 1250, 4395, 3920, 3434, # 4774 - 3541, 1342, 1681, 1718, 766, 3264, 286, 89, 2946, 3649, 7540, 1713, 7541, 2597, 3334, 2990, # 4790 - 7542, 2947, 2215, 3194, 2866, 7543, 4396, 2498, 2526, 181, 387, 1075, 3921, 731, 2187, 3335, # 4806 - 7544, 3265, 310, 313, 3435, 2299, 770, 4134, 54, 3034, 189, 4397, 3082, 3769, 3922, 7545, # 4822 - 1230, 1617, 1849, 355, 3542, 4135, 4398, 3336, 111, 4136, 3650, 1350, 3135, 3436, 3035, 4137, # 4838 - 2149, 3266, 3543, 7546, 2784, 3923, 3924, 2991, 722, 2008, 7547, 1071, 247, 1207, 2338, 2471, # 4854 - 1378, 4399, 2009, 864, 1437, 1214, 4400, 373, 3770, 1142, 2216, 667, 4401, 442, 2753, 2555, # 4870 - 3771, 3925, 1968, 4138, 3267, 1839, 837, 170, 1107, 934, 1336, 1882, 7548, 7549, 2118, 4139, # 4886 - 2828, 743, 1569, 7550, 4402, 4140, 582, 2384, 1418, 3437, 7551, 1802, 7552, 357, 1395, 1729, # 4902 - 3651, 3268, 2418, 1564, 2237, 7553, 3083, 3772, 1633, 4403, 1114, 2085, 4141, 1532, 7554, 482, # 4918 - 2446, 4404, 7555, 7556, 1492, 833, 1466, 7557, 2717, 3544, 1641, 2829, 7558, 1526, 1272, 3652, # 4934 - 4142, 1686, 1794, 416, 2556, 1902, 1953, 1803, 7559, 3773, 2785, 3774, 1159, 2316, 7560, 2867, # 4950 - 4405, 1610, 1584, 3036, 2419, 2754, 443, 3269, 1163, 3136, 7561, 7562, 3926, 7563, 4143, 2499, # 4966 - 3037, 4406, 3927, 3137, 2103, 1647, 3545, 2010, 1872, 4144, 7564, 4145, 431, 3438, 7565, 250, # 4982 - 97, 81, 4146, 7566, 1648, 1850, 1558, 160, 848, 7567, 866, 740, 1694, 7568, 2201, 2830, # 4998 - 3195, 4147, 4407, 3653, 1687, 950, 2472, 426, 469, 3196, 3654, 3655, 3928, 7569, 7570, 1188, # 5014 - 424, 1995, 861, 3546, 4148, 3775, 2202, 2685, 168, 1235, 3547, 4149, 7571, 2086, 1674, 4408, # 5030 - 3337, 3270, 220, 2557, 1009, 7572, 3776, 670, 2992, 332, 1208, 717, 7573, 7574, 3548, 2447, # 5046 - 3929, 3338, 7575, 513, 7576, 1209, 2868, 3339, 3138, 4409, 1080, 7577, 7578, 7579, 7580, 2527, # 5062 - 3656, 3549, 815, 1587, 3930, 3931, 7581, 3550, 3439, 3777, 1254, 4410, 1328, 3038, 1390, 3932, # 5078 - 1741, 3933, 3778, 3934, 7582, 236, 3779, 2448, 3271, 7583, 7584, 3657, 3780, 1273, 3781, 4411, # 5094 - 7585, 308, 7586, 4412, 245, 4413, 1851, 2473, 1307, 2575, 430, 715, 2136, 2449, 7587, 270, # 5110 - 199, 2869, 3935, 7588, 3551, 2718, 1753, 761, 1754, 725, 1661, 1840, 4414, 3440, 3658, 7589, # 5126 - 7590, 587, 14, 3272, 227, 2598, 326, 480, 2265, 943, 2755, 3552, 291, 650, 1883, 7591, # 5142 - 1702, 1226, 102, 1547, 62, 3441, 904, 4415, 3442, 1164, 4150, 7592, 7593, 1224, 1548, 2756, # 5158 - 391, 498, 1493, 7594, 1386, 1419, 7595, 2055, 1177, 4416, 813, 880, 1081, 2363, 566, 1145, # 5174 - 4417, 2286, 1001, 1035, 2558, 2599, 2238, 394, 1286, 7596, 7597, 2068, 7598, 86, 1494, 1730, # 5190 - 3936, 491, 1588, 745, 897, 2948, 843, 3340, 3937, 2757, 2870, 3273, 1768, 998, 2217, 2069, # 5206 - 397, 1826, 1195, 1969, 3659, 2993, 3341, 284, 7599, 3782, 2500, 2137, 2119, 1903, 7600, 3938, # 5222 - 2150, 3939, 4151, 1036, 3443, 1904, 114, 2559, 4152, 209, 1527, 7601, 7602, 2949, 2831, 2625, # 5238 - 2385, 2719, 3139, 812, 2560, 7603, 3274, 7604, 1559, 737, 1884, 3660, 1210, 885, 28, 2686, # 5254 - 3553, 3783, 7605, 4153, 1004, 1779, 4418, 7606, 346, 1981, 2218, 2687, 4419, 3784, 1742, 797, # 5270 - 1642, 3940, 1933, 1072, 1384, 2151, 896, 3941, 3275, 3661, 3197, 2871, 3554, 7607, 2561, 1958, # 5286 - 4420, 2450, 1785, 7608, 7609, 7610, 3942, 4154, 1005, 1308, 3662, 4155, 2720, 4421, 4422, 1528, # 5302 - 2600, 161, 1178, 4156, 1982, 987, 4423, 1101, 4157, 631, 3943, 1157, 3198, 2420, 1343, 1241, # 5318 - 1016, 2239, 2562, 372, 877, 2339, 2501, 1160, 555, 1934, 911, 3944, 7611, 466, 1170, 169, # 5334 - 1051, 2907, 2688, 3663, 2474, 2994, 1182, 2011, 2563, 1251, 2626, 7612, 992, 2340, 3444, 1540, # 5350 - 2721, 1201, 2070, 2401, 1996, 2475, 7613, 4424, 528, 1922, 2188, 1503, 1873, 1570, 2364, 3342, # 5366 - 3276, 7614, 557, 1073, 7615, 1827, 3445, 2087, 2266, 3140, 3039, 3084, 767, 3085, 2786, 4425, # 5382 - 1006, 4158, 4426, 2341, 1267, 2176, 3664, 3199, 778, 3945, 3200, 2722, 1597, 2657, 7616, 4427, # 5398 - 7617, 3446, 7618, 7619, 7620, 3277, 2689, 1433, 3278, 131, 95, 1504, 3946, 723, 4159, 3141, # 5414 - 1841, 3555, 2758, 2189, 3947, 2027, 2104, 3665, 7621, 2995, 3948, 1218, 7622, 3343, 3201, 3949, # 5430 - 4160, 2576, 248, 1634, 3785, 912, 7623, 2832, 3666, 3040, 3786, 654, 53, 7624, 2996, 7625, # 5446 - 1688, 4428, 777, 3447, 1032, 3950, 1425, 7626, 191, 820, 2120, 2833, 971, 4429, 931, 3202, # 5462 - 135, 664, 783, 3787, 1997, 772, 2908, 1935, 3951, 3788, 4430, 2909, 3203, 282, 2723, 640, # 5478 - 1372, 3448, 1127, 922, 325, 3344, 7627, 7628, 711, 2044, 7629, 7630, 3952, 2219, 2787, 1936, # 5494 - 3953, 3345, 2220, 2251, 3789, 2300, 7631, 4431, 3790, 1258, 3279, 3954, 3204, 2138, 2950, 3955, # 5510 - 3956, 7632, 2221, 258, 3205, 4432, 101, 1227, 7633, 3280, 1755, 7634, 1391, 3281, 7635, 2910, # 5526 - 2056, 893, 7636, 7637, 7638, 1402, 4161, 2342, 7639, 7640, 3206, 3556, 7641, 7642, 878, 1325, # 5542 - 1780, 2788, 4433, 259, 1385, 2577, 744, 1183, 2267, 4434, 7643, 3957, 2502, 7644, 684, 1024, # 5558 - 4162, 7645, 472, 3557, 3449, 1165, 3282, 3958, 3959, 322, 2152, 881, 455, 1695, 1152, 1340, # 5574 - 660, 554, 2153, 4435, 1058, 4436, 4163, 830, 1065, 3346, 3960, 4437, 1923, 7646, 1703, 1918, # 5590 - 7647, 932, 2268, 122, 7648, 4438, 947, 677, 7649, 3791, 2627, 297, 1905, 1924, 2269, 4439, # 5606 - 2317, 3283, 7650, 7651, 4164, 7652, 4165, 84, 4166, 112, 989, 7653, 547, 1059, 3961, 701, # 5622 - 3558, 1019, 7654, 4167, 7655, 3450, 942, 639, 457, 2301, 2451, 993, 2951, 407, 851, 494, # 5638 - 4440, 3347, 927, 7656, 1237, 7657, 2421, 3348, 573, 4168, 680, 921, 2911, 1279, 1874, 285, # 5654 - 790, 1448, 1983, 719, 2167, 7658, 7659, 4441, 3962, 3963, 1649, 7660, 1541, 563, 7661, 1077, # 5670 - 7662, 3349, 3041, 3451, 511, 2997, 3964, 3965, 3667, 3966, 1268, 2564, 3350, 3207, 4442, 4443, # 5686 - 7663, 535, 1048, 1276, 1189, 2912, 2028, 3142, 1438, 1373, 2834, 2952, 1134, 2012, 7664, 4169, # 5702 - 1238, 2578, 3086, 1259, 7665, 700, 7666, 2953, 3143, 3668, 4170, 7667, 4171, 1146, 1875, 1906, # 5718 - 4444, 2601, 3967, 781, 2422, 132, 1589, 203, 147, 273, 2789, 2402, 898, 1786, 2154, 3968, # 5734 - 3969, 7668, 3792, 2790, 7669, 7670, 4445, 4446, 7671, 3208, 7672, 1635, 3793, 965, 7673, 1804, # 5750 - 2690, 1516, 3559, 1121, 1082, 1329, 3284, 3970, 1449, 3794, 65, 1128, 2835, 2913, 2759, 1590, # 5766 - 3795, 7674, 7675, 12, 2658, 45, 976, 2579, 3144, 4447, 517, 2528, 1013, 1037, 3209, 7676, # 5782 - 3796, 2836, 7677, 3797, 7678, 3452, 7679, 2602, 614, 1998, 2318, 3798, 3087, 2724, 2628, 7680, # 5798 - 2580, 4172, 599, 1269, 7681, 1810, 3669, 7682, 2691, 3088, 759, 1060, 489, 1805, 3351, 3285, # 5814 - 1358, 7683, 7684, 2386, 1387, 1215, 2629, 2252, 490, 7685, 7686, 4173, 1759, 2387, 2343, 7687, # 5830 - 4448, 3799, 1907, 3971, 2630, 1806, 3210, 4449, 3453, 3286, 2760, 2344, 874, 7688, 7689, 3454, # 5846 - 3670, 1858, 91, 2914, 3671, 3042, 3800, 4450, 7690, 3145, 3972, 2659, 7691, 3455, 1202, 1403, # 5862 - 3801, 2954, 2529, 1517, 2503, 4451, 3456, 2504, 7692, 4452, 7693, 2692, 1885, 1495, 1731, 3973, # 5878 - 2365, 4453, 7694, 2029, 7695, 7696, 3974, 2693, 1216, 237, 2581, 4174, 2319, 3975, 3802, 4454, # 5894 - 4455, 2694, 3560, 3457, 445, 4456, 7697, 7698, 7699, 7700, 2761, 61, 3976, 3672, 1822, 3977, # 5910 - 7701, 687, 2045, 935, 925, 405, 2660, 703, 1096, 1859, 2725, 4457, 3978, 1876, 1367, 2695, # 5926 - 3352, 918, 2105, 1781, 2476, 334, 3287, 1611, 1093, 4458, 564, 3146, 3458, 3673, 3353, 945, # 5942 - 2631, 2057, 4459, 7702, 1925, 872, 4175, 7703, 3459, 2696, 3089, 349, 4176, 3674, 3979, 4460, # 5958 - 3803, 4177, 3675, 2155, 3980, 4461, 4462, 4178, 4463, 2403, 2046, 782, 3981, 400, 251, 4179, # 5974 - 1624, 7704, 7705, 277, 3676, 299, 1265, 476, 1191, 3804, 2121, 4180, 4181, 1109, 205, 7706, # 5990 - 2582, 1000, 2156, 3561, 1860, 7707, 7708, 7709, 4464, 7710, 4465, 2565, 107, 2477, 2157, 3982, # 6006 - 3460, 3147, 7711, 1533, 541, 1301, 158, 753, 4182, 2872, 3562, 7712, 1696, 370, 1088, 4183, # 6022 - 4466, 3563, 579, 327, 440, 162, 2240, 269, 1937, 1374, 3461, 968, 3043, 56, 1396, 3090, # 6038 - 2106, 3288, 3354, 7713, 1926, 2158, 4467, 2998, 7714, 3564, 7715, 7716, 3677, 4468, 2478, 7717, # 6054 - 2791, 7718, 1650, 4469, 7719, 2603, 7720, 7721, 3983, 2661, 3355, 1149, 3356, 3984, 3805, 3985, # 6070 - 7722, 1076, 49, 7723, 951, 3211, 3289, 3290, 450, 2837, 920, 7724, 1811, 2792, 2366, 4184, # 6086 - 1908, 1138, 2367, 3806, 3462, 7725, 3212, 4470, 1909, 1147, 1518, 2423, 4471, 3807, 7726, 4472, # 6102 - 2388, 2604, 260, 1795, 3213, 7727, 7728, 3808, 3291, 708, 7729, 3565, 1704, 7730, 3566, 1351, # 6118 - 1618, 3357, 2999, 1886, 944, 4185, 3358, 4186, 3044, 3359, 4187, 7731, 3678, 422, 413, 1714, # 6134 - 3292, 500, 2058, 2345, 4188, 2479, 7732, 1344, 1910, 954, 7733, 1668, 7734, 7735, 3986, 2404, # 6150 - 4189, 3567, 3809, 4190, 7736, 2302, 1318, 2505, 3091, 133, 3092, 2873, 4473, 629, 31, 2838, # 6166 - 2697, 3810, 4474, 850, 949, 4475, 3987, 2955, 1732, 2088, 4191, 1496, 1852, 7737, 3988, 620, # 6182 - 3214, 981, 1242, 3679, 3360, 1619, 3680, 1643, 3293, 2139, 2452, 1970, 1719, 3463, 2168, 7738, # 6198 - 3215, 7739, 7740, 3361, 1828, 7741, 1277, 4476, 1565, 2047, 7742, 1636, 3568, 3093, 7743, 869, # 6214 - 2839, 655, 3811, 3812, 3094, 3989, 3000, 3813, 1310, 3569, 4477, 7744, 7745, 7746, 1733, 558, # 6230 - 4478, 3681, 335, 1549, 3045, 1756, 4192, 3682, 1945, 3464, 1829, 1291, 1192, 470, 2726, 2107, # 6246 - 2793, 913, 1054, 3990, 7747, 1027, 7748, 3046, 3991, 4479, 982, 2662, 3362, 3148, 3465, 3216, # 6262 - 3217, 1946, 2794, 7749, 571, 4480, 7750, 1830, 7751, 3570, 2583, 1523, 2424, 7752, 2089, 984, # 6278 - 4481, 3683, 1959, 7753, 3684, 852, 923, 2795, 3466, 3685, 969, 1519, 999, 2048, 2320, 1705, # 6294 - 7754, 3095, 615, 1662, 151, 597, 3992, 2405, 2321, 1049, 275, 4482, 3686, 4193, 568, 3687, # 6310 - 3571, 2480, 4194, 3688, 7755, 2425, 2270, 409, 3218, 7756, 1566, 2874, 3467, 1002, 769, 2840, # 6326 - 194, 2090, 3149, 3689, 2222, 3294, 4195, 628, 1505, 7757, 7758, 1763, 2177, 3001, 3993, 521, # 6342 - 1161, 2584, 1787, 2203, 2406, 4483, 3994, 1625, 4196, 4197, 412, 42, 3096, 464, 7759, 2632, # 6358 - 4484, 3363, 1760, 1571, 2875, 3468, 2530, 1219, 2204, 3814, 2633, 2140, 2368, 4485, 4486, 3295, # 6374 - 1651, 3364, 3572, 7760, 7761, 3573, 2481, 3469, 7762, 3690, 7763, 7764, 2271, 2091, 460, 7765, # 6390 - 4487, 7766, 3002, 962, 588, 3574, 289, 3219, 2634, 1116, 52, 7767, 3047, 1796, 7768, 7769, # 6406 - 7770, 1467, 7771, 1598, 1143, 3691, 4198, 1984, 1734, 1067, 4488, 1280, 3365, 465, 4489, 1572, # 6422 - 510, 7772, 1927, 2241, 1812, 1644, 3575, 7773, 4490, 3692, 7774, 7775, 2663, 1573, 1534, 7776, # 6438 - 7777, 4199, 536, 1807, 1761, 3470, 3815, 3150, 2635, 7778, 7779, 7780, 4491, 3471, 2915, 1911, # 6454 - 2796, 7781, 3296, 1122, 377, 3220, 7782, 360, 7783, 7784, 4200, 1529, 551, 7785, 2059, 3693, # 6470 - 1769, 2426, 7786, 2916, 4201, 3297, 3097, 2322, 2108, 2030, 4492, 1404, 136, 1468, 1479, 672, # 6486 - 1171, 3221, 2303, 271, 3151, 7787, 2762, 7788, 2049, 678, 2727, 865, 1947, 4493, 7789, 2013, # 6502 - 3995, 2956, 7790, 2728, 2223, 1397, 3048, 3694, 4494, 4495, 1735, 2917, 3366, 3576, 7791, 3816, # 6518 - 509, 2841, 2453, 2876, 3817, 7792, 7793, 3152, 3153, 4496, 4202, 2531, 4497, 2304, 1166, 1010, # 6534 - 552, 681, 1887, 7794, 7795, 2957, 2958, 3996, 1287, 1596, 1861, 3154, 358, 453, 736, 175, # 6550 - 478, 1117, 905, 1167, 1097, 7796, 1853, 1530, 7797, 1706, 7798, 2178, 3472, 2287, 3695, 3473, # 6566 - 3577, 4203, 2092, 4204, 7799, 3367, 1193, 2482, 4205, 1458, 2190, 2205, 1862, 1888, 1421, 3298, # 6582 - 2918, 3049, 2179, 3474, 595, 2122, 7800, 3997, 7801, 7802, 4206, 1707, 2636, 223, 3696, 1359, # 6598 - 751, 3098, 183, 3475, 7803, 2797, 3003, 419, 2369, 633, 704, 3818, 2389, 241, 7804, 7805, # 6614 - 7806, 838, 3004, 3697, 2272, 2763, 2454, 3819, 1938, 2050, 3998, 1309, 3099, 2242, 1181, 7807, # 6630 - 1136, 2206, 3820, 2370, 1446, 4207, 2305, 4498, 7808, 7809, 4208, 1055, 2605, 484, 3698, 7810, # 6646 - 3999, 625, 4209, 2273, 3368, 1499, 4210, 4000, 7811, 4001, 4211, 3222, 2274, 2275, 3476, 7812, # 6662 - 7813, 2764, 808, 2606, 3699, 3369, 4002, 4212, 3100, 2532, 526, 3370, 3821, 4213, 955, 7814, # 6678 - 1620, 4214, 2637, 2427, 7815, 1429, 3700, 1669, 1831, 994, 928, 7816, 3578, 1260, 7817, 7818, # 6694 - 7819, 1948, 2288, 741, 2919, 1626, 4215, 2729, 2455, 867, 1184, 362, 3371, 1392, 7820, 7821, # 6710 - 4003, 4216, 1770, 1736, 3223, 2920, 4499, 4500, 1928, 2698, 1459, 1158, 7822, 3050, 3372, 2877, # 6726 - 1292, 1929, 2506, 2842, 3701, 1985, 1187, 2071, 2014, 2607, 4217, 7823, 2566, 2507, 2169, 3702, # 6742 - 2483, 3299, 7824, 3703, 4501, 7825, 7826, 666, 1003, 3005, 1022, 3579, 4218, 7827, 4502, 1813, # 6758 - 2253, 574, 3822, 1603, 295, 1535, 705, 3823, 4219, 283, 858, 417, 7828, 7829, 3224, 4503, # 6774 - 4504, 3051, 1220, 1889, 1046, 2276, 2456, 4004, 1393, 1599, 689, 2567, 388, 4220, 7830, 2484, # 6790 - 802, 7831, 2798, 3824, 2060, 1405, 2254, 7832, 4505, 3825, 2109, 1052, 1345, 3225, 1585, 7833, # 6806 - 809, 7834, 7835, 7836, 575, 2730, 3477, 956, 1552, 1469, 1144, 2323, 7837, 2324, 1560, 2457, # 6822 - 3580, 3226, 4005, 616, 2207, 3155, 2180, 2289, 7838, 1832, 7839, 3478, 4506, 7840, 1319, 3704, # 6838 - 3705, 1211, 3581, 1023, 3227, 1293, 2799, 7841, 7842, 7843, 3826, 607, 2306, 3827, 762, 2878, # 6854 - 1439, 4221, 1360, 7844, 1485, 3052, 7845, 4507, 1038, 4222, 1450, 2061, 2638, 4223, 1379, 4508, # 6870 - 2585, 7846, 7847, 4224, 1352, 1414, 2325, 2921, 1172, 7848, 7849, 3828, 3829, 7850, 1797, 1451, # 6886 - 7851, 7852, 7853, 7854, 2922, 4006, 4007, 2485, 2346, 411, 4008, 4009, 3582, 3300, 3101, 4509, # 6902 - 1561, 2664, 1452, 4010, 1375, 7855, 7856, 47, 2959, 316, 7857, 1406, 1591, 2923, 3156, 7858, # 6918 - 1025, 2141, 3102, 3157, 354, 2731, 884, 2224, 4225, 2407, 508, 3706, 726, 3583, 996, 2428, # 6934 - 3584, 729, 7859, 392, 2191, 1453, 4011, 4510, 3707, 7860, 7861, 2458, 3585, 2608, 1675, 2800, # 6950 - 919, 2347, 2960, 2348, 1270, 4511, 4012, 73, 7862, 7863, 647, 7864, 3228, 2843, 2255, 1550, # 6966 - 1346, 3006, 7865, 1332, 883, 3479, 7866, 7867, 7868, 7869, 3301, 2765, 7870, 1212, 831, 1347, # 6982 - 4226, 4512, 2326, 3830, 1863, 3053, 720, 3831, 4513, 4514, 3832, 7871, 4227, 7872, 7873, 4515, # 6998 - 7874, 7875, 1798, 4516, 3708, 2609, 4517, 3586, 1645, 2371, 7876, 7877, 2924, 669, 2208, 2665, # 7014 - 2429, 7878, 2879, 7879, 7880, 1028, 3229, 7881, 4228, 2408, 7882, 2256, 1353, 7883, 7884, 4518, # 7030 - 3158, 518, 7885, 4013, 7886, 4229, 1960, 7887, 2142, 4230, 7888, 7889, 3007, 2349, 2350, 3833, # 7046 - 516, 1833, 1454, 4014, 2699, 4231, 4519, 2225, 2610, 1971, 1129, 3587, 7890, 2766, 7891, 2961, # 7062 - 1422, 577, 1470, 3008, 1524, 3373, 7892, 7893, 432, 4232, 3054, 3480, 7894, 2586, 1455, 2508, # 7078 - 2226, 1972, 1175, 7895, 1020, 2732, 4015, 3481, 4520, 7896, 2733, 7897, 1743, 1361, 3055, 3482, # 7094 - 2639, 4016, 4233, 4521, 2290, 895, 924, 4234, 2170, 331, 2243, 3056, 166, 1627, 3057, 1098, # 7110 - 7898, 1232, 2880, 2227, 3374, 4522, 657, 403, 1196, 2372, 542, 3709, 3375, 1600, 4235, 3483, # 7126 - 7899, 4523, 2767, 3230, 576, 530, 1362, 7900, 4524, 2533, 2666, 3710, 4017, 7901, 842, 3834, # 7142 - 7902, 2801, 2031, 1014, 4018, 213, 2700, 3376, 665, 621, 4236, 7903, 3711, 2925, 2430, 7904, # 7158 - 2431, 3302, 3588, 3377, 7905, 4237, 2534, 4238, 4525, 3589, 1682, 4239, 3484, 1380, 7906, 724, # 7174 - 2277, 600, 1670, 7907, 1337, 1233, 4526, 3103, 2244, 7908, 1621, 4527, 7909, 651, 4240, 7910, # 7190 - 1612, 4241, 2611, 7911, 2844, 7912, 2734, 2307, 3058, 7913, 716, 2459, 3059, 174, 1255, 2701, # 7206 - 4019, 3590, 548, 1320, 1398, 728, 4020, 1574, 7914, 1890, 1197, 3060, 4021, 7915, 3061, 3062, # 7222 - 3712, 3591, 3713, 747, 7916, 635, 4242, 4528, 7917, 7918, 7919, 4243, 7920, 7921, 4529, 7922, # 7238 - 3378, 4530, 2432, 451, 7923, 3714, 2535, 2072, 4244, 2735, 4245, 4022, 7924, 1764, 4531, 7925, # 7254 - 4246, 350, 7926, 2278, 2390, 2486, 7927, 4247, 4023, 2245, 1434, 4024, 488, 4532, 458, 4248, # 7270 - 4025, 3715, 771, 1330, 2391, 3835, 2568, 3159, 2159, 2409, 1553, 2667, 3160, 4249, 7928, 2487, # 7286 - 2881, 2612, 1720, 2702, 4250, 3379, 4533, 7929, 2536, 4251, 7930, 3231, 4252, 2768, 7931, 2015, # 7302 - 2736, 7932, 1155, 1017, 3716, 3836, 7933, 3303, 2308, 201, 1864, 4253, 1430, 7934, 4026, 7935, # 7318 - 7936, 7937, 7938, 7939, 4254, 1604, 7940, 414, 1865, 371, 2587, 4534, 4535, 3485, 2016, 3104, # 7334 - 4536, 1708, 960, 4255, 887, 389, 2171, 1536, 1663, 1721, 7941, 2228, 4027, 2351, 2926, 1580, # 7350 - 7942, 7943, 7944, 1744, 7945, 2537, 4537, 4538, 7946, 4539, 7947, 2073, 7948, 7949, 3592, 3380, # 7366 - 2882, 4256, 7950, 4257, 2640, 3381, 2802, 673, 2703, 2460, 709, 3486, 4028, 3593, 4258, 7951, # 7382 - 1148, 502, 634, 7952, 7953, 1204, 4540, 3594, 1575, 4541, 2613, 3717, 7954, 3718, 3105, 948, # 7398 - 3232, 121, 1745, 3837, 1110, 7955, 4259, 3063, 2509, 3009, 4029, 3719, 1151, 1771, 3838, 1488, # 7414 - 4030, 1986, 7956, 2433, 3487, 7957, 7958, 2093, 7959, 4260, 3839, 1213, 1407, 2803, 531, 2737, # 7430 - 2538, 3233, 1011, 1537, 7960, 2769, 4261, 3106, 1061, 7961, 3720, 3721, 1866, 2883, 7962, 2017, # 7446 - 120, 4262, 4263, 2062, 3595, 3234, 2309, 3840, 2668, 3382, 1954, 4542, 7963, 7964, 3488, 1047, # 7462 - 2704, 1266, 7965, 1368, 4543, 2845, 649, 3383, 3841, 2539, 2738, 1102, 2846, 2669, 7966, 7967, # 7478 - 1999, 7968, 1111, 3596, 2962, 7969, 2488, 3842, 3597, 2804, 1854, 3384, 3722, 7970, 7971, 3385, # 7494 - 2410, 2884, 3304, 3235, 3598, 7972, 2569, 7973, 3599, 2805, 4031, 1460, 856, 7974, 3600, 7975, # 7510 - 2885, 2963, 7976, 2886, 3843, 7977, 4264, 632, 2510, 875, 3844, 1697, 3845, 2291, 7978, 7979, # 7526 - 4544, 3010, 1239, 580, 4545, 4265, 7980, 914, 936, 2074, 1190, 4032, 1039, 2123, 7981, 7982, # 7542 - 7983, 3386, 1473, 7984, 1354, 4266, 3846, 7985, 2172, 3064, 4033, 915, 3305, 4267, 4268, 3306, # 7558 - 1605, 1834, 7986, 2739, 398, 3601, 4269, 3847, 4034, 328, 1912, 2847, 4035, 3848, 1331, 4270, # 7574 - 3011, 937, 4271, 7987, 3602, 4036, 4037, 3387, 2160, 4546, 3388, 524, 742, 538, 3065, 1012, # 7590 - 7988, 7989, 3849, 2461, 7990, 658, 1103, 225, 3850, 7991, 7992, 4547, 7993, 4548, 7994, 3236, # 7606 - 1243, 7995, 4038, 963, 2246, 4549, 7996, 2705, 3603, 3161, 7997, 7998, 2588, 2327, 7999, 4550, # 7622 - 8000, 8001, 8002, 3489, 3307, 957, 3389, 2540, 2032, 1930, 2927, 2462, 870, 2018, 3604, 1746, # 7638 - 2770, 2771, 2434, 2463, 8003, 3851, 8004, 3723, 3107, 3724, 3490, 3390, 3725, 8005, 1179, 3066, # 7654 - 8006, 3162, 2373, 4272, 3726, 2541, 3163, 3108, 2740, 4039, 8007, 3391, 1556, 2542, 2292, 977, # 7670 - 2887, 2033, 4040, 1205, 3392, 8008, 1765, 3393, 3164, 2124, 1271, 1689, 714, 4551, 3491, 8009, # 7686 - 2328, 3852, 533, 4273, 3605, 2181, 617, 8010, 2464, 3308, 3492, 2310, 8011, 8012, 3165, 8013, # 7702 - 8014, 3853, 1987, 618, 427, 2641, 3493, 3394, 8015, 8016, 1244, 1690, 8017, 2806, 4274, 4552, # 7718 - 8018, 3494, 8019, 8020, 2279, 1576, 473, 3606, 4275, 3395, 972, 8021, 3607, 8022, 3067, 8023, # 7734 - 8024, 4553, 4554, 8025, 3727, 4041, 4042, 8026, 153, 4555, 356, 8027, 1891, 2888, 4276, 2143, # 7750 - 408, 803, 2352, 8028, 3854, 8029, 4277, 1646, 2570, 2511, 4556, 4557, 3855, 8030, 3856, 4278, # 7766 - 8031, 2411, 3396, 752, 8032, 8033, 1961, 2964, 8034, 746, 3012, 2465, 8035, 4279, 3728, 698, # 7782 - 4558, 1892, 4280, 3608, 2543, 4559, 3609, 3857, 8036, 3166, 3397, 8037, 1823, 1302, 4043, 2706, # 7798 - 3858, 1973, 4281, 8038, 4282, 3167, 823, 1303, 1288, 1236, 2848, 3495, 4044, 3398, 774, 3859, # 7814 - 8039, 1581, 4560, 1304, 2849, 3860, 4561, 8040, 2435, 2161, 1083, 3237, 4283, 4045, 4284, 344, # 7830 - 1173, 288, 2311, 454, 1683, 8041, 8042, 1461, 4562, 4046, 2589, 8043, 8044, 4563, 985, 894, # 7846 - 8045, 3399, 3168, 8046, 1913, 2928, 3729, 1988, 8047, 2110, 1974, 8048, 4047, 8049, 2571, 1194, # 7862 - 425, 8050, 4564, 3169, 1245, 3730, 4285, 8051, 8052, 2850, 8053, 636, 4565, 1855, 3861, 760, # 7878 - 1799, 8054, 4286, 2209, 1508, 4566, 4048, 1893, 1684, 2293, 8055, 8056, 8057, 4287, 4288, 2210, # 7894 - 479, 8058, 8059, 832, 8060, 4049, 2489, 8061, 2965, 2490, 3731, 990, 3109, 627, 1814, 2642, # 7910 - 4289, 1582, 4290, 2125, 2111, 3496, 4567, 8062, 799, 4291, 3170, 8063, 4568, 2112, 1737, 3013, # 7926 - 1018, 543, 754, 4292, 3309, 1676, 4569, 4570, 4050, 8064, 1489, 8065, 3497, 8066, 2614, 2889, # 7942 - 4051, 8067, 8068, 2966, 8069, 8070, 8071, 8072, 3171, 4571, 4572, 2182, 1722, 8073, 3238, 3239, # 7958 - 1842, 3610, 1715, 481, 365, 1975, 1856, 8074, 8075, 1962, 2491, 4573, 8076, 2126, 3611, 3240, # 7974 - 433, 1894, 2063, 2075, 8077, 602, 2741, 8078, 8079, 8080, 8081, 8082, 3014, 1628, 3400, 8083, # 7990 - 3172, 4574, 4052, 2890, 4575, 2512, 8084, 2544, 2772, 8085, 8086, 8087, 3310, 4576, 2891, 8088, # 8006 - 4577, 8089, 2851, 4578, 4579, 1221, 2967, 4053, 2513, 8090, 8091, 8092, 1867, 1989, 8093, 8094, # 8022 - 8095, 1895, 8096, 8097, 4580, 1896, 4054, 318, 8098, 2094, 4055, 4293, 8099, 8100, 485, 8101, # 8038 - 938, 3862, 553, 2670, 116, 8102, 3863, 3612, 8103, 3498, 2671, 2773, 3401, 3311, 2807, 8104, # 8054 - 3613, 2929, 4056, 1747, 2930, 2968, 8105, 8106, 207, 8107, 8108, 2672, 4581, 2514, 8109, 3015, # 8070 - 890, 3614, 3864, 8110, 1877, 3732, 3402, 8111, 2183, 2353, 3403, 1652, 8112, 8113, 8114, 941, # 8086 - 2294, 208, 3499, 4057, 2019, 330, 4294, 3865, 2892, 2492, 3733, 4295, 8115, 8116, 8117, 8118, # 8102 -) -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euctwprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euctwprober.py deleted file mode 100644 index a37ab18..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/euctwprober.py +++ /dev/null @@ -1,47 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .chardistribution import EUCTWDistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import EUCTW_SM_MODEL - - -class EUCTWProber(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(EUCTW_SM_MODEL) - self.distribution_analyzer = EUCTWDistributionAnalysis() - self.reset() - - @property - def charset_name(self) -> str: - return "EUC-TW" - - @property - def language(self) -> str: - return "Taiwan" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/gb2312freq.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/gb2312freq.py deleted file mode 100644 index b32bfc7..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/gb2312freq.py +++ /dev/null @@ -1,284 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -# GB2312 most frequently used character table -# -# Char to FreqOrder table , from hz6763 - -# 512 --> 0.79 -- 0.79 -# 1024 --> 0.92 -- 0.13 -# 2048 --> 0.98 -- 0.06 -# 6768 --> 1.00 -- 0.02 -# -# Ideal Distribution Ratio = 0.79135/(1-0.79135) = 3.79 -# Random Distribution Ration = 512 / (3755 - 512) = 0.157 -# -# Typical Distribution Ratio about 25% of Ideal one, still much higher that RDR - -GB2312_TYPICAL_DISTRIBUTION_RATIO = 0.9 - -GB2312_TABLE_SIZE = 3760 - -# fmt: off -GB2312_CHAR_TO_FREQ_ORDER = ( -1671, 749,1443,2364,3924,3807,2330,3921,1704,3463,2691,1511,1515, 572,3191,2205, -2361, 224,2558, 479,1711, 963,3162, 440,4060,1905,2966,2947,3580,2647,3961,3842, -2204, 869,4207, 970,2678,5626,2944,2956,1479,4048, 514,3595, 588,1346,2820,3409, - 249,4088,1746,1873,2047,1774, 581,1813, 358,1174,3590,1014,1561,4844,2245, 670, -1636,3112, 889,1286, 953, 556,2327,3060,1290,3141, 613, 185,3477,1367, 850,3820, -1715,2428,2642,2303,2732,3041,2562,2648,3566,3946,1349, 388,3098,2091,1360,3585, - 152,1687,1539, 738,1559, 59,1232,2925,2267,1388,1249,1741,1679,2960, 151,1566, -1125,1352,4271, 924,4296, 385,3166,4459, 310,1245,2850, 70,3285,2729,3534,3575, -2398,3298,3466,1960,2265, 217,3647, 864,1909,2084,4401,2773,1010,3269,5152, 853, -3051,3121,1244,4251,1895, 364,1499,1540,2313,1180,3655,2268, 562, 715,2417,3061, - 544, 336,3768,2380,1752,4075, 950, 280,2425,4382, 183,2759,3272, 333,4297,2155, -1688,2356,1444,1039,4540, 736,1177,3349,2443,2368,2144,2225, 565, 196,1482,3406, - 927,1335,4147, 692, 878,1311,1653,3911,3622,1378,4200,1840,2969,3149,2126,1816, -2534,1546,2393,2760, 737,2494, 13, 447, 245,2747, 38,2765,2129,2589,1079, 606, - 360, 471,3755,2890, 404, 848, 699,1785,1236, 370,2221,1023,3746,2074,2026,2023, -2388,1581,2119, 812,1141,3091,2536,1519, 804,2053, 406,1596,1090, 784, 548,4414, -1806,2264,2936,1100, 343,4114,5096, 622,3358, 743,3668,1510,1626,5020,3567,2513, -3195,4115,5627,2489,2991, 24,2065,2697,1087,2719, 48,1634, 315, 68, 985,2052, - 198,2239,1347,1107,1439, 597,2366,2172, 871,3307, 919,2487,2790,1867, 236,2570, -1413,3794, 906,3365,3381,1701,1982,1818,1524,2924,1205, 616,2586,2072,2004, 575, - 253,3099, 32,1365,1182, 197,1714,2454,1201, 554,3388,3224,2748, 756,2587, 250, -2567,1507,1517,3529,1922,2761,2337,3416,1961,1677,2452,2238,3153, 615, 911,1506, -1474,2495,1265,1906,2749,3756,3280,2161, 898,2714,1759,3450,2243,2444, 563, 26, -3286,2266,3769,3344,2707,3677, 611,1402, 531,1028,2871,4548,1375, 261,2948, 835, -1190,4134, 353, 840,2684,1900,3082,1435,2109,1207,1674, 329,1872,2781,4055,2686, -2104, 608,3318,2423,2957,2768,1108,3739,3512,3271,3985,2203,1771,3520,1418,2054, -1681,1153, 225,1627,2929, 162,2050,2511,3687,1954, 124,1859,2431,1684,3032,2894, - 585,4805,3969,2869,2704,2088,2032,2095,3656,2635,4362,2209, 256, 518,2042,2105, -3777,3657, 643,2298,1148,1779, 190, 989,3544, 414, 11,2135,2063,2979,1471, 403, -3678, 126, 770,1563, 671,2499,3216,2877, 600,1179, 307,2805,4937,1268,1297,2694, - 252,4032,1448,1494,1331,1394, 127,2256, 222,1647,1035,1481,3056,1915,1048, 873, -3651, 210, 33,1608,2516, 200,1520, 415, 102, 0,3389,1287, 817, 91,3299,2940, - 836,1814, 549,2197,1396,1669,2987,3582,2297,2848,4528,1070, 687, 20,1819, 121, -1552,1364,1461,1968,2617,3540,2824,2083, 177, 948,4938,2291, 110,4549,2066, 648, -3359,1755,2110,2114,4642,4845,1693,3937,3308,1257,1869,2123, 208,1804,3159,2992, -2531,2549,3361,2418,1350,2347,2800,2568,1291,2036,2680, 72, 842,1990, 212,1233, -1154,1586, 75,2027,3410,4900,1823,1337,2710,2676, 728,2810,1522,3026,4995, 157, - 755,1050,4022, 710, 785,1936,2194,2085,1406,2777,2400, 150,1250,4049,1206, 807, -1910, 534, 529,3309,1721,1660, 274, 39,2827, 661,2670,1578, 925,3248,3815,1094, -4278,4901,4252, 41,1150,3747,2572,2227,4501,3658,4902,3813,3357,3617,2884,2258, - 887, 538,4187,3199,1294,2439,3042,2329,2343,2497,1255, 107, 543,1527, 521,3478, -3568, 194,5062, 15, 961,3870,1241,1192,2664, 66,5215,3260,2111,1295,1127,2152, -3805,4135, 901,1164,1976, 398,1278, 530,1460, 748, 904,1054,1966,1426, 53,2909, - 509, 523,2279,1534, 536,1019, 239,1685, 460,2353, 673,1065,2401,3600,4298,2272, -1272,2363, 284,1753,3679,4064,1695, 81, 815,2677,2757,2731,1386, 859, 500,4221, -2190,2566, 757,1006,2519,2068,1166,1455, 337,2654,3203,1863,1682,1914,3025,1252, -1409,1366, 847, 714,2834,2038,3209, 964,2970,1901, 885,2553,1078,1756,3049, 301, -1572,3326, 688,2130,1996,2429,1805,1648,2930,3421,2750,3652,3088, 262,1158,1254, - 389,1641,1812, 526,1719, 923,2073,1073,1902, 468, 489,4625,1140, 857,2375,3070, -3319,2863, 380, 116,1328,2693,1161,2244, 273,1212,1884,2769,3011,1775,1142, 461, -3066,1200,2147,2212, 790, 702,2695,4222,1601,1058, 434,2338,5153,3640, 67,2360, -4099,2502, 618,3472,1329, 416,1132, 830,2782,1807,2653,3211,3510,1662, 192,2124, - 296,3979,1739,1611,3684, 23, 118, 324, 446,1239,1225, 293,2520,3814,3795,2535, -3116, 17,1074, 467,2692,2201, 387,2922, 45,1326,3055,1645,3659,2817, 958, 243, -1903,2320,1339,2825,1784,3289, 356, 576, 865,2315,2381,3377,3916,1088,3122,1713, -1655, 935, 628,4689,1034,1327, 441, 800, 720, 894,1979,2183,1528,5289,2702,1071, -4046,3572,2399,1571,3281, 79, 761,1103, 327, 134, 758,1899,1371,1615, 879, 442, - 215,2605,2579, 173,2048,2485,1057,2975,3317,1097,2253,3801,4263,1403,1650,2946, - 814,4968,3487,1548,2644,1567,1285, 2, 295,2636, 97, 946,3576, 832, 141,4257, -3273, 760,3821,3521,3156,2607, 949,1024,1733,1516,1803,1920,2125,2283,2665,3180, -1501,2064,3560,2171,1592, 803,3518,1416, 732,3897,4258,1363,1362,2458, 119,1427, - 602,1525,2608,1605,1639,3175, 694,3064, 10, 465, 76,2000,4846,4208, 444,3781, -1619,3353,2206,1273,3796, 740,2483, 320,1723,2377,3660,2619,1359,1137,1762,1724, -2345,2842,1850,1862, 912, 821,1866, 612,2625,1735,2573,3369,1093, 844, 89, 937, - 930,1424,3564,2413,2972,1004,3046,3019,2011, 711,3171,1452,4178, 428, 801,1943, - 432, 445,2811, 206,4136,1472, 730, 349, 73, 397,2802,2547, 998,1637,1167, 789, - 396,3217, 154,1218, 716,1120,1780,2819,4826,1931,3334,3762,2139,1215,2627, 552, -3664,3628,3232,1405,2383,3111,1356,2652,3577,3320,3101,1703, 640,1045,1370,1246, -4996, 371,1575,2436,1621,2210, 984,4033,1734,2638, 16,4529, 663,2755,3255,1451, -3917,2257,1253,1955,2234,1263,2951, 214,1229, 617, 485, 359,1831,1969, 473,2310, - 750,2058, 165, 80,2864,2419, 361,4344,2416,2479,1134, 796,3726,1266,2943, 860, -2715, 938, 390,2734,1313,1384, 248, 202, 877,1064,2854, 522,3907, 279,1602, 297, -2357, 395,3740, 137,2075, 944,4089,2584,1267,3802, 62,1533,2285, 178, 176, 780, -2440, 201,3707, 590, 478,1560,4354,2117,1075, 30, 74,4643,4004,1635,1441,2745, - 776,2596, 238,1077,1692,1912,2844, 605, 499,1742,3947, 241,3053, 980,1749, 936, -2640,4511,2582, 515,1543,2162,5322,2892,2993, 890,2148,1924, 665,1827,3581,1032, - 968,3163, 339,1044,1896, 270, 583,1791,1720,4367,1194,3488,3669, 43,2523,1657, - 163,2167, 290,1209,1622,3378, 550, 634,2508,2510, 695,2634,2384,2512,1476,1414, - 220,1469,2341,2138,2852,3183,2900,4939,2865,3502,1211,3680, 854,3227,1299,2976, -3172, 186,2998,1459, 443,1067,3251,1495, 321,1932,3054, 909, 753,1410,1828, 436, -2441,1119,1587,3164,2186,1258, 227, 231,1425,1890,3200,3942, 247, 959, 725,5254, -2741, 577,2158,2079, 929, 120, 174, 838,2813, 591,1115, 417,2024, 40,3240,1536, -1037, 291,4151,2354, 632,1298,2406,2500,3535,1825,1846,3451, 205,1171, 345,4238, - 18,1163, 811, 685,2208,1217, 425,1312,1508,1175,4308,2552,1033, 587,1381,3059, -2984,3482, 340,1316,4023,3972, 792,3176, 519, 777,4690, 918, 933,4130,2981,3741, - 90,3360,2911,2200,5184,4550, 609,3079,2030, 272,3379,2736, 363,3881,1130,1447, - 286, 779, 357,1169,3350,3137,1630,1220,2687,2391, 747,1277,3688,2618,2682,2601, -1156,3196,5290,4034,3102,1689,3596,3128, 874, 219,2783, 798, 508,1843,2461, 269, -1658,1776,1392,1913,2983,3287,2866,2159,2372, 829,4076, 46,4253,2873,1889,1894, - 915,1834,1631,2181,2318, 298, 664,2818,3555,2735, 954,3228,3117, 527,3511,2173, - 681,2712,3033,2247,2346,3467,1652, 155,2164,3382, 113,1994, 450, 899, 494, 994, -1237,2958,1875,2336,1926,3727, 545,1577,1550, 633,3473, 204,1305,3072,2410,1956, -2471, 707,2134, 841,2195,2196,2663,3843,1026,4940, 990,3252,4997, 368,1092, 437, -3212,3258,1933,1829, 675,2977,2893, 412, 943,3723,4644,3294,3283,2230,2373,5154, -2389,2241,2661,2323,1404,2524, 593, 787, 677,3008,1275,2059, 438,2709,2609,2240, -2269,2246,1446, 36,1568,1373,3892,1574,2301,1456,3962, 693,2276,5216,2035,1143, -2720,1919,1797,1811,2763,4137,2597,1830,1699,1488,1198,2090, 424,1694, 312,3634, -3390,4179,3335,2252,1214, 561,1059,3243,2295,2561, 975,5155,2321,2751,3772, 472, -1537,3282,3398,1047,2077,2348,2878,1323,3340,3076, 690,2906, 51, 369, 170,3541, -1060,2187,2688,3670,2541,1083,1683, 928,3918, 459, 109,4427, 599,3744,4286, 143, -2101,2730,2490, 82,1588,3036,2121, 281,1860, 477,4035,1238,2812,3020,2716,3312, -1530,2188,2055,1317, 843, 636,1808,1173,3495, 649, 181,1002, 147,3641,1159,2414, -3750,2289,2795, 813,3123,2610,1136,4368, 5,3391,4541,2174, 420, 429,1728, 754, -1228,2115,2219, 347,2223,2733, 735,1518,3003,2355,3134,1764,3948,3329,1888,2424, -1001,1234,1972,3321,3363,1672,1021,1450,1584, 226, 765, 655,2526,3404,3244,2302, -3665, 731, 594,2184, 319,1576, 621, 658,2656,4299,2099,3864,1279,2071,2598,2739, - 795,3086,3699,3908,1707,2352,2402,1382,3136,2475,1465,4847,3496,3865,1085,3004, -2591,1084, 213,2287,1963,3565,2250, 822, 793,4574,3187,1772,1789,3050, 595,1484, -1959,2770,1080,2650, 456, 422,2996, 940,3322,4328,4345,3092,2742, 965,2784, 739, -4124, 952,1358,2498,2949,2565, 332,2698,2378, 660,2260,2473,4194,3856,2919, 535, -1260,2651,1208,1428,1300,1949,1303,2942, 433,2455,2450,1251,1946, 614,1269, 641, -1306,1810,2737,3078,2912, 564,2365,1419,1415,1497,4460,2367,2185,1379,3005,1307, -3218,2175,1897,3063, 682,1157,4040,4005,1712,1160,1941,1399, 394, 402,2952,1573, -1151,2986,2404, 862, 299,2033,1489,3006, 346, 171,2886,3401,1726,2932, 168,2533, - 47,2507,1030,3735,1145,3370,1395,1318,1579,3609,4560,2857,4116,1457,2529,1965, - 504,1036,2690,2988,2405, 745,5871, 849,2397,2056,3081, 863,2359,3857,2096, 99, -1397,1769,2300,4428,1643,3455,1978,1757,3718,1440, 35,4879,3742,1296,4228,2280, - 160,5063,1599,2013, 166, 520,3479,1646,3345,3012, 490,1937,1545,1264,2182,2505, -1096,1188,1369,1436,2421,1667,2792,2460,1270,2122, 727,3167,2143, 806,1706,1012, -1800,3037, 960,2218,1882, 805, 139,2456,1139,1521, 851,1052,3093,3089, 342,2039, - 744,5097,1468,1502,1585,2087, 223, 939, 326,2140,2577, 892,2481,1623,4077, 982, -3708, 135,2131, 87,2503,3114,2326,1106, 876,1616, 547,2997,2831,2093,3441,4530, -4314, 9,3256,4229,4148, 659,1462,1986,1710,2046,2913,2231,4090,4880,5255,3392, -3274,1368,3689,4645,1477, 705,3384,3635,1068,1529,2941,1458,3782,1509, 100,1656, -2548, 718,2339, 408,1590,2780,3548,1838,4117,3719,1345,3530, 717,3442,2778,3220, -2898,1892,4590,3614,3371,2043,1998,1224,3483, 891, 635, 584,2559,3355, 733,1766, -1729,1172,3789,1891,2307, 781,2982,2271,1957,1580,5773,2633,2005,4195,3097,1535, -3213,1189,1934,5693,3262, 586,3118,1324,1598, 517,1564,2217,1868,1893,4445,3728, -2703,3139,1526,1787,1992,3882,2875,1549,1199,1056,2224,1904,2711,5098,4287, 338, -1993,3129,3489,2689,1809,2815,1997, 957,1855,3898,2550,3275,3057,1105,1319, 627, -1505,1911,1883,3526, 698,3629,3456,1833,1431, 746, 77,1261,2017,2296,1977,1885, - 125,1334,1600, 525,1798,1109,2222,1470,1945, 559,2236,1186,3443,2476,1929,1411, -2411,3135,1777,3372,2621,1841,1613,3229, 668,1430,1839,2643,2916, 195,1989,2671, -2358,1387, 629,3205,2293,5256,4439, 123,1310, 888,1879,4300,3021,3605,1003,1162, -3192,2910,2010, 140,2395,2859, 55,1082,2012,2901, 662, 419,2081,1438, 680,2774, -4654,3912,1620,1731,1625,5035,4065,2328, 512,1344, 802,5443,2163,2311,2537, 524, -3399, 98,1155,2103,1918,2606,3925,2816,1393,2465,1504,3773,2177,3963,1478,4346, - 180,1113,4655,3461,2028,1698, 833,2696,1235,1322,1594,4408,3623,3013,3225,2040, -3022, 541,2881, 607,3632,2029,1665,1219, 639,1385,1686,1099,2803,3231,1938,3188, -2858, 427, 676,2772,1168,2025, 454,3253,2486,3556, 230,1950, 580, 791,1991,1280, -1086,1974,2034, 630, 257,3338,2788,4903,1017, 86,4790, 966,2789,1995,1696,1131, - 259,3095,4188,1308, 179,1463,5257, 289,4107,1248, 42,3413,1725,2288, 896,1947, - 774,4474,4254, 604,3430,4264, 392,2514,2588, 452, 237,1408,3018, 988,4531,1970, -3034,3310, 540,2370,1562,1288,2990, 502,4765,1147, 4,1853,2708, 207, 294,2814, -4078,2902,2509, 684, 34,3105,3532,2551, 644, 709,2801,2344, 573,1727,3573,3557, -2021,1081,3100,4315,2100,3681, 199,2263,1837,2385, 146,3484,1195,2776,3949, 997, -1939,3973,1008,1091,1202,1962,1847,1149,4209,5444,1076, 493, 117,5400,2521, 972, -1490,2934,1796,4542,2374,1512,2933,2657, 413,2888,1135,2762,2314,2156,1355,2369, - 766,2007,2527,2170,3124,2491,2593,2632,4757,2437, 234,3125,3591,1898,1750,1376, -1942,3468,3138, 570,2127,2145,3276,4131, 962, 132,1445,4196, 19, 941,3624,3480, -3366,1973,1374,4461,3431,2629, 283,2415,2275, 808,2887,3620,2112,2563,1353,3610, - 955,1089,3103,1053, 96, 88,4097, 823,3808,1583, 399, 292,4091,3313, 421,1128, - 642,4006, 903,2539,1877,2082, 596, 29,4066,1790, 722,2157, 130, 995,1569, 769, -1485, 464, 513,2213, 288,1923,1101,2453,4316, 133, 486,2445, 50, 625, 487,2207, - 57, 423, 481,2962, 159,3729,1558, 491, 303, 482, 501, 240,2837, 112,3648,2392, -1783, 362, 8,3433,3422, 610,2793,3277,1390,1284,1654, 21,3823, 734, 367, 623, - 193, 287, 374,1009,1483, 816, 476, 313,2255,2340,1262,2150,2899,1146,2581, 782, -2116,1659,2018,1880, 255,3586,3314,1110,2867,2137,2564, 986,2767,5185,2006, 650, - 158, 926, 762, 881,3157,2717,2362,3587, 306,3690,3245,1542,3077,2427,1691,2478, -2118,2985,3490,2438, 539,2305, 983, 129,1754, 355,4201,2386, 827,2923, 104,1773, -2838,2771, 411,2905,3919, 376, 767, 122,1114, 828,2422,1817,3506, 266,3460,1007, -1609,4998, 945,2612,4429,2274, 726,1247,1964,2914,2199,2070,4002,4108, 657,3323, -1422, 579, 455,2764,4737,1222,2895,1670, 824,1223,1487,2525, 558, 861,3080, 598, -2659,2515,1967, 752,2583,2376,2214,4180, 977, 704,2464,4999,2622,4109,1210,2961, - 819,1541, 142,2284, 44, 418, 457,1126,3730,4347,4626,1644,1876,3671,1864, 302, -1063,5694, 624, 723,1984,3745,1314,1676,2488,1610,1449,3558,3569,2166,2098, 409, -1011,2325,3704,2306, 818,1732,1383,1824,1844,3757, 999,2705,3497,1216,1423,2683, -2426,2954,2501,2726,2229,1475,2554,5064,1971,1794,1666,2014,1343, 783, 724, 191, -2434,1354,2220,5065,1763,2752,2472,4152, 131, 175,2885,3434, 92,1466,4920,2616, -3871,3872,3866, 128,1551,1632, 669,1854,3682,4691,4125,1230, 188,2973,3290,1302, -1213, 560,3266, 917, 763,3909,3249,1760, 868,1958, 764,1782,2097, 145,2277,3774, -4462, 64,1491,3062, 971,2132,3606,2442, 221,1226,1617, 218, 323,1185,3207,3147, - 571, 619,1473,1005,1744,2281, 449,1887,2396,3685, 275, 375,3816,1743,3844,3731, - 845,1983,2350,4210,1377, 773, 967,3499,3052,3743,2725,4007,1697,1022,3943,1464, -3264,2855,2722,1952,1029,2839,2467, 84,4383,2215, 820,1391,2015,2448,3672, 377, -1948,2168, 797,2545,3536,2578,2645, 94,2874,1678, 405,1259,3071, 771, 546,1315, - 470,1243,3083, 895,2468, 981, 969,2037, 846,4181, 653,1276,2928, 14,2594, 557, -3007,2474, 156, 902,1338,1740,2574, 537,2518, 973,2282,2216,2433,1928, 138,2903, -1293,2631,1612, 646,3457, 839,2935, 111, 496,2191,2847, 589,3186, 149,3994,2060, -4031,2641,4067,3145,1870, 37,3597,2136,1025,2051,3009,3383,3549,1121,1016,3261, -1301, 251,2446,2599,2153, 872,3246, 637, 334,3705, 831, 884, 921,3065,3140,4092, -2198,1944, 246,2964, 108,2045,1152,1921,2308,1031, 203,3173,4170,1907,3890, 810, -1401,2003,1690, 506, 647,1242,2828,1761,1649,3208,2249,1589,3709,2931,5156,1708, - 498, 666,2613, 834,3817,1231, 184,2851,1124, 883,3197,2261,3710,1765,1553,2658, -1178,2639,2351, 93,1193, 942,2538,2141,4402, 235,1821, 870,1591,2192,1709,1871, -3341,1618,4126,2595,2334, 603, 651, 69, 701, 268,2662,3411,2555,1380,1606, 503, - 448, 254,2371,2646, 574,1187,2309,1770, 322,2235,1292,1801, 305, 566,1133, 229, -2067,2057, 706, 167, 483,2002,2672,3295,1820,3561,3067, 316, 378,2746,3452,1112, - 136,1981, 507,1651,2917,1117, 285,4591, 182,2580,3522,1304, 335,3303,1835,2504, -1795,1792,2248, 674,1018,2106,2449,1857,2292,2845, 976,3047,1781,2600,2727,1389, -1281, 52,3152, 153, 265,3950, 672,3485,3951,4463, 430,1183, 365, 278,2169, 27, -1407,1336,2304, 209,1340,1730,2202,1852,2403,2883, 979,1737,1062, 631,2829,2542, -3876,2592, 825,2086,2226,3048,3625, 352,1417,3724, 542, 991, 431,1351,3938,1861, -2294, 826,1361,2927,3142,3503,1738, 463,2462,2723, 582,1916,1595,2808, 400,3845, -3891,2868,3621,2254, 58,2492,1123, 910,2160,2614,1372,1603,1196,1072,3385,1700, -3267,1980, 696, 480,2430, 920, 799,1570,2920,1951,2041,4047,2540,1321,4223,2469, -3562,2228,1271,2602, 401,2833,3351,2575,5157, 907,2312,1256, 410, 263,3507,1582, - 996, 678,1849,2316,1480, 908,3545,2237, 703,2322, 667,1826,2849,1531,2604,2999, -2407,3146,2151,2630,1786,3711, 469,3542, 497,3899,2409, 858, 837,4446,3393,1274, - 786, 620,1845,2001,3311, 484, 308,3367,1204,1815,3691,2332,1532,2557,1842,2020, -2724,1927,2333,4440, 567, 22,1673,2728,4475,1987,1858,1144,1597, 101,1832,3601, - 12, 974,3783,4391, 951,1412, 1,3720, 453,4608,4041, 528,1041,1027,3230,2628, -1129, 875,1051,3291,1203,2262,1069,2860,2799,2149,2615,3278, 144,1758,3040, 31, - 475,1680, 366,2685,3184, 311,1642,4008,2466,5036,1593,1493,2809, 216,1420,1668, - 233, 304,2128,3284, 232,1429,1768,1040,2008,3407,2740,2967,2543, 242,2133, 778, -1565,2022,2620, 505,2189,2756,1098,2273, 372,1614, 708, 553,2846,2094,2278, 169, -3626,2835,4161, 228,2674,3165, 809,1454,1309, 466,1705,1095, 900,3423, 880,2667, -3751,5258,2317,3109,2571,4317,2766,1503,1342, 866,4447,1118, 63,2076, 314,1881, -1348,1061, 172, 978,3515,1747, 532, 511,3970, 6, 601, 905,2699,3300,1751, 276, -1467,3725,2668, 65,4239,2544,2779,2556,1604, 578,2451,1802, 992,2331,2624,1320, -3446, 713,1513,1013, 103,2786,2447,1661, 886,1702, 916, 654,3574,2031,1556, 751, -2178,2821,2179,1498,1538,2176, 271, 914,2251,2080,1325, 638,1953,2937,3877,2432, -2754, 95,3265,1716, 260,1227,4083, 775, 106,1357,3254, 426,1607, 555,2480, 772, -1985, 244,2546, 474, 495,1046,2611,1851,2061, 71,2089,1675,2590, 742,3758,2843, -3222,1433, 267,2180,2576,2826,2233,2092,3913,2435, 956,1745,3075, 856,2113,1116, - 451, 3,1988,2896,1398, 993,2463,1878,2049,1341,2718,2721,2870,2108, 712,2904, -4363,2753,2324, 277,2872,2349,2649, 384, 987, 435, 691,3000, 922, 164,3939, 652, -1500,1184,4153,2482,3373,2165,4848,2335,3775,3508,3154,2806,2830,1554,2102,1664, -2530,1434,2408, 893,1547,2623,3447,2832,2242,2532,3169,2856,3223,2078, 49,3770, -3469, 462, 318, 656,2259,3250,3069, 679,1629,2758, 344,1138,1104,3120,1836,1283, -3115,2154,1437,4448, 934, 759,1999, 794,2862,1038, 533,2560,1722,2342, 855,2626, -1197,1663,4476,3127, 85,4240,2528, 25,1111,1181,3673, 407,3470,4561,2679,2713, - 768,1925,2841,3986,1544,1165, 932, 373,1240,2146,1930,2673, 721,4766, 354,4333, - 391,2963, 187, 61,3364,1442,1102, 330,1940,1767, 341,3809,4118, 393,2496,2062, -2211, 105, 331, 300, 439, 913,1332, 626, 379,3304,1557, 328, 689,3952, 309,1555, - 931, 317,2517,3027, 325, 569, 686,2107,3084, 60,1042,1333,2794, 264,3177,4014, -1628, 258,3712, 7,4464,1176,1043,1778, 683, 114,1975, 78,1492, 383,1886, 510, - 386, 645,5291,2891,2069,3305,4138,3867,2939,2603,2493,1935,1066,1848,3588,1015, -1282,1289,4609, 697,1453,3044,2666,3611,1856,2412, 54, 719,1330, 568,3778,2459, -1748, 788, 492, 551,1191,1000, 488,3394,3763, 282,1799, 348,2016,1523,3155,2390, -1049, 382,2019,1788,1170, 729,2968,3523, 897,3926,2785,2938,3292, 350,2319,3238, -1718,1717,2655,3453,3143,4465, 161,2889,2980,2009,1421, 56,1908,1640,2387,2232, -1917,1874,2477,4921, 148, 83,3438, 592,4245,2882,1822,1055, 741, 115,1496,1624, - 381,1638,4592,1020, 516,3214, 458, 947,4575,1432, 211,1514,2926,1865,2142, 189, - 852,1221,1400,1486, 882,2299,4036, 351, 28,1122, 700,6479,6480,6481,6482,6483, #last 512 -) -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/gb2312prober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/gb2312prober.py deleted file mode 100644 index d423e73..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/gb2312prober.py +++ /dev/null @@ -1,47 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .chardistribution import GB2312DistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import GB2312_SM_MODEL - - -class GB2312Prober(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(GB2312_SM_MODEL) - self.distribution_analyzer = GB2312DistributionAnalysis() - self.reset() - - @property - def charset_name(self) -> str: - return "GB2312" - - @property - def language(self) -> str: - return "Chinese" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/hebrewprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/hebrewprober.py deleted file mode 100644 index 785d005..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/hebrewprober.py +++ /dev/null @@ -1,316 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Shy Shalom -# Portions created by the Initial Developer are Copyright (C) 2005 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Optional, Union - -from .charsetprober import CharSetProber -from .enums import ProbingState -from .sbcharsetprober import SingleByteCharSetProber - -# This prober doesn't actually recognize a language or a charset. -# It is a helper prober for the use of the Hebrew model probers - -### General ideas of the Hebrew charset recognition ### -# -# Four main charsets exist in Hebrew: -# "ISO-8859-8" - Visual Hebrew -# "windows-1255" - Logical Hebrew -# "ISO-8859-8-I" - Logical Hebrew -# "x-mac-hebrew" - ?? Logical Hebrew ?? -# -# Both "ISO" charsets use a completely identical set of code points, whereas -# "windows-1255" and "x-mac-hebrew" are two different proper supersets of -# these code points. windows-1255 defines additional characters in the range -# 0x80-0x9F as some misc punctuation marks as well as some Hebrew-specific -# diacritics and additional 'Yiddish' ligature letters in the range 0xc0-0xd6. -# x-mac-hebrew defines similar additional code points but with a different -# mapping. -# -# As far as an average Hebrew text with no diacritics is concerned, all four -# charsets are identical with respect to code points. Meaning that for the -# main Hebrew alphabet, all four map the same values to all 27 Hebrew letters -# (including final letters). -# -# The dominant difference between these charsets is their directionality. -# "Visual" directionality means that the text is ordered as if the renderer is -# not aware of a BIDI rendering algorithm. The renderer sees the text and -# draws it from left to right. The text itself when ordered naturally is read -# backwards. A buffer of Visual Hebrew generally looks like so: -# "[last word of first line spelled backwards] [whole line ordered backwards -# and spelled backwards] [first word of first line spelled backwards] -# [end of line] [last word of second line] ... etc' " -# adding punctuation marks, numbers and English text to visual text is -# naturally also "visual" and from left to right. -# -# "Logical" directionality means the text is ordered "naturally" according to -# the order it is read. It is the responsibility of the renderer to display -# the text from right to left. A BIDI algorithm is used to place general -# punctuation marks, numbers and English text in the text. -# -# Texts in x-mac-hebrew are almost impossible to find on the Internet. From -# what little evidence I could find, it seems that its general directionality -# is Logical. -# -# To sum up all of the above, the Hebrew probing mechanism knows about two -# charsets: -# Visual Hebrew - "ISO-8859-8" - backwards text - Words and sentences are -# backwards while line order is natural. For charset recognition purposes -# the line order is unimportant (In fact, for this implementation, even -# word order is unimportant). -# Logical Hebrew - "windows-1255" - normal, naturally ordered text. -# -# "ISO-8859-8-I" is a subset of windows-1255 and doesn't need to be -# specifically identified. -# "x-mac-hebrew" is also identified as windows-1255. A text in x-mac-hebrew -# that contain special punctuation marks or diacritics is displayed with -# some unconverted characters showing as question marks. This problem might -# be corrected using another model prober for x-mac-hebrew. Due to the fact -# that x-mac-hebrew texts are so rare, writing another model prober isn't -# worth the effort and performance hit. -# -#### The Prober #### -# -# The prober is divided between two SBCharSetProbers and a HebrewProber, -# all of which are managed, created, fed data, inquired and deleted by the -# SBCSGroupProber. The two SBCharSetProbers identify that the text is in -# fact some kind of Hebrew, Logical or Visual. The final decision about which -# one is it is made by the HebrewProber by combining final-letter scores -# with the scores of the two SBCharSetProbers to produce a final answer. -# -# The SBCSGroupProber is responsible for stripping the original text of HTML -# tags, English characters, numbers, low-ASCII punctuation characters, spaces -# and new lines. It reduces any sequence of such characters to a single space. -# The buffer fed to each prober in the SBCS group prober is pure text in -# high-ASCII. -# The two SBCharSetProbers (model probers) share the same language model: -# Win1255Model. -# The first SBCharSetProber uses the model normally as any other -# SBCharSetProber does, to recognize windows-1255, upon which this model was -# built. The second SBCharSetProber is told to make the pair-of-letter -# lookup in the language model backwards. This in practice exactly simulates -# a visual Hebrew model using the windows-1255 logical Hebrew model. -# -# The HebrewProber is not using any language model. All it does is look for -# final-letter evidence suggesting the text is either logical Hebrew or visual -# Hebrew. Disjointed from the model probers, the results of the HebrewProber -# alone are meaningless. HebrewProber always returns 0.00 as confidence -# since it never identifies a charset by itself. Instead, the pointer to the -# HebrewProber is passed to the model probers as a helper "Name Prober". -# When the Group prober receives a positive identification from any prober, -# it asks for the name of the charset identified. If the prober queried is a -# Hebrew model prober, the model prober forwards the call to the -# HebrewProber to make the final decision. In the HebrewProber, the -# decision is made according to the final-letters scores maintained and Both -# model probers scores. The answer is returned in the form of the name of the -# charset identified, either "windows-1255" or "ISO-8859-8". - - -class HebrewProber(CharSetProber): - SPACE = 0x20 - # windows-1255 / ISO-8859-8 code points of interest - FINAL_KAF = 0xEA - NORMAL_KAF = 0xEB - FINAL_MEM = 0xED - NORMAL_MEM = 0xEE - FINAL_NUN = 0xEF - NORMAL_NUN = 0xF0 - FINAL_PE = 0xF3 - NORMAL_PE = 0xF4 - FINAL_TSADI = 0xF5 - NORMAL_TSADI = 0xF6 - - # Minimum Visual vs Logical final letter score difference. - # If the difference is below this, don't rely solely on the final letter score - # distance. - MIN_FINAL_CHAR_DISTANCE = 5 - - # Minimum Visual vs Logical model score difference. - # If the difference is below this, don't rely at all on the model score - # distance. - MIN_MODEL_DISTANCE = 0.01 - - VISUAL_HEBREW_NAME = "ISO-8859-8" - LOGICAL_HEBREW_NAME = "windows-1255" - - def __init__(self) -> None: - super().__init__() - self._final_char_logical_score = 0 - self._final_char_visual_score = 0 - self._prev = self.SPACE - self._before_prev = self.SPACE - self._logical_prober: Optional[SingleByteCharSetProber] = None - self._visual_prober: Optional[SingleByteCharSetProber] = None - self.reset() - - def reset(self) -> None: - self._final_char_logical_score = 0 - self._final_char_visual_score = 0 - # The two last characters seen in the previous buffer, - # mPrev and mBeforePrev are initialized to space in order to simulate - # a word delimiter at the beginning of the data - self._prev = self.SPACE - self._before_prev = self.SPACE - # These probers are owned by the group prober. - - def set_model_probers( - self, - logical_prober: SingleByteCharSetProber, - visual_prober: SingleByteCharSetProber, - ) -> None: - self._logical_prober = logical_prober - self._visual_prober = visual_prober - - def is_final(self, c: int) -> bool: - return c in [ - self.FINAL_KAF, - self.FINAL_MEM, - self.FINAL_NUN, - self.FINAL_PE, - self.FINAL_TSADI, - ] - - def is_non_final(self, c: int) -> bool: - # The normal Tsadi is not a good Non-Final letter due to words like - # 'lechotet' (to chat) containing an apostrophe after the tsadi. This - # apostrophe is converted to a space in FilterWithoutEnglishLetters - # causing the Non-Final tsadi to appear at an end of a word even - # though this is not the case in the original text. - # The letters Pe and Kaf rarely display a related behavior of not being - # a good Non-Final letter. Words like 'Pop', 'Winamp' and 'Mubarak' - # for example legally end with a Non-Final Pe or Kaf. However, the - # benefit of these letters as Non-Final letters outweighs the damage - # since these words are quite rare. - return c in [self.NORMAL_KAF, self.NORMAL_MEM, self.NORMAL_NUN, self.NORMAL_PE] - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - # Final letter analysis for logical-visual decision. - # Look for evidence that the received buffer is either logical Hebrew - # or visual Hebrew. - # The following cases are checked: - # 1) A word longer than 1 letter, ending with a final letter. This is - # an indication that the text is laid out "naturally" since the - # final letter really appears at the end. +1 for logical score. - # 2) A word longer than 1 letter, ending with a Non-Final letter. In - # normal Hebrew, words ending with Kaf, Mem, Nun, Pe or Tsadi, - # should not end with the Non-Final form of that letter. Exceptions - # to this rule are mentioned above in isNonFinal(). This is an - # indication that the text is laid out backwards. +1 for visual - # score - # 3) A word longer than 1 letter, starting with a final letter. Final - # letters should not appear at the beginning of a word. This is an - # indication that the text is laid out backwards. +1 for visual - # score. - # - # The visual score and logical score are accumulated throughout the - # text and are finally checked against each other in GetCharSetName(). - # No checking for final letters in the middle of words is done since - # that case is not an indication for either Logical or Visual text. - # - # We automatically filter out all 7-bit characters (replace them with - # spaces) so the word boundary detection works properly. [MAP] - - if self.state == ProbingState.NOT_ME: - # Both model probers say it's not them. No reason to continue. - return ProbingState.NOT_ME - - byte_str = self.filter_high_byte_only(byte_str) - - for cur in byte_str: - if cur == self.SPACE: - # We stand on a space - a word just ended - if self._before_prev != self.SPACE: - # next-to-last char was not a space so self._prev is not a - # 1 letter word - if self.is_final(self._prev): - # case (1) [-2:not space][-1:final letter][cur:space] - self._final_char_logical_score += 1 - elif self.is_non_final(self._prev): - # case (2) [-2:not space][-1:Non-Final letter][ - # cur:space] - self._final_char_visual_score += 1 - else: - # Not standing on a space - if ( - (self._before_prev == self.SPACE) - and (self.is_final(self._prev)) - and (cur != self.SPACE) - ): - # case (3) [-2:space][-1:final letter][cur:not space] - self._final_char_visual_score += 1 - self._before_prev = self._prev - self._prev = cur - - # Forever detecting, till the end or until both model probers return - # ProbingState.NOT_ME (handled above) - return ProbingState.DETECTING - - @property - def charset_name(self) -> str: - assert self._logical_prober is not None - assert self._visual_prober is not None - - # Make the decision: is it Logical or Visual? - # If the final letter score distance is dominant enough, rely on it. - finalsub = self._final_char_logical_score - self._final_char_visual_score - if finalsub >= self.MIN_FINAL_CHAR_DISTANCE: - return self.LOGICAL_HEBREW_NAME - if finalsub <= -self.MIN_FINAL_CHAR_DISTANCE: - return self.VISUAL_HEBREW_NAME - - # It's not dominant enough, try to rely on the model scores instead. - modelsub = ( - self._logical_prober.get_confidence() - self._visual_prober.get_confidence() - ) - if modelsub > self.MIN_MODEL_DISTANCE: - return self.LOGICAL_HEBREW_NAME - if modelsub < -self.MIN_MODEL_DISTANCE: - return self.VISUAL_HEBREW_NAME - - # Still no good, back to final letter distance, maybe it'll save the - # day. - if finalsub < 0.0: - return self.VISUAL_HEBREW_NAME - - # (finalsub > 0 - Logical) or (don't know what to do) default to - # Logical. - return self.LOGICAL_HEBREW_NAME - - @property - def language(self) -> str: - return "Hebrew" - - @property - def state(self) -> ProbingState: - assert self._logical_prober is not None - assert self._visual_prober is not None - - # Remain active as long as any of the model probers are active. - if (self._logical_prober.state == ProbingState.NOT_ME) and ( - self._visual_prober.state == ProbingState.NOT_ME - ): - return ProbingState.NOT_ME - return ProbingState.DETECTING diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/jisfreq.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/jisfreq.py deleted file mode 100644 index 3293576..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/jisfreq.py +++ /dev/null @@ -1,325 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -# Sampling from about 20M text materials include literature and computer technology -# -# Japanese frequency table, applied to both S-JIS and EUC-JP -# They are sorted in order. - -# 128 --> 0.77094 -# 256 --> 0.85710 -# 512 --> 0.92635 -# 1024 --> 0.97130 -# 2048 --> 0.99431 -# -# Ideal Distribution Ratio = 0.92635 / (1-0.92635) = 12.58 -# Random Distribution Ration = 512 / (2965+62+83+86-512) = 0.191 -# -# Typical Distribution Ratio, 25% of IDR - -JIS_TYPICAL_DISTRIBUTION_RATIO = 3.0 - -# Char to FreqOrder table , -JIS_TABLE_SIZE = 4368 - -# fmt: off -JIS_CHAR_TO_FREQ_ORDER = ( - 40, 1, 6, 182, 152, 180, 295,2127, 285, 381,3295,4304,3068,4606,3165,3510, # 16 -3511,1822,2785,4607,1193,2226,5070,4608, 171,2996,1247, 18, 179,5071, 856,1661, # 32 -1262,5072, 619, 127,3431,3512,3230,1899,1700, 232, 228,1294,1298, 284, 283,2041, # 48 -2042,1061,1062, 48, 49, 44, 45, 433, 434,1040,1041, 996, 787,2997,1255,4305, # 64 -2108,4609,1684,1648,5073,5074,5075,5076,5077,5078,3687,5079,4610,5080,3927,3928, # 80 -5081,3296,3432, 290,2285,1471,2187,5082,2580,2825,1303,2140,1739,1445,2691,3375, # 96 -1691,3297,4306,4307,4611, 452,3376,1182,2713,3688,3069,4308,5083,5084,5085,5086, # 112 -5087,5088,5089,5090,5091,5092,5093,5094,5095,5096,5097,5098,5099,5100,5101,5102, # 128 -5103,5104,5105,5106,5107,5108,5109,5110,5111,5112,4097,5113,5114,5115,5116,5117, # 144 -5118,5119,5120,5121,5122,5123,5124,5125,5126,5127,5128,5129,5130,5131,5132,5133, # 160 -5134,5135,5136,5137,5138,5139,5140,5141,5142,5143,5144,5145,5146,5147,5148,5149, # 176 -5150,5151,5152,4612,5153,5154,5155,5156,5157,5158,5159,5160,5161,5162,5163,5164, # 192 -5165,5166,5167,5168,5169,5170,5171,5172,5173,5174,5175,1472, 598, 618, 820,1205, # 208 -1309,1412,1858,1307,1692,5176,5177,5178,5179,5180,5181,5182,1142,1452,1234,1172, # 224 -1875,2043,2149,1793,1382,2973, 925,2404,1067,1241, 960,1377,2935,1491, 919,1217, # 240 -1865,2030,1406,1499,2749,4098,5183,5184,5185,5186,5187,5188,2561,4099,3117,1804, # 256 -2049,3689,4309,3513,1663,5189,3166,3118,3298,1587,1561,3433,5190,3119,1625,2998, # 272 -3299,4613,1766,3690,2786,4614,5191,5192,5193,5194,2161, 26,3377, 2,3929, 20, # 288 -3691, 47,4100, 50, 17, 16, 35, 268, 27, 243, 42, 155, 24, 154, 29, 184, # 304 - 4, 91, 14, 92, 53, 396, 33, 289, 9, 37, 64, 620, 21, 39, 321, 5, # 320 - 12, 11, 52, 13, 3, 208, 138, 0, 7, 60, 526, 141, 151,1069, 181, 275, # 336 -1591, 83, 132,1475, 126, 331, 829, 15, 69, 160, 59, 22, 157, 55,1079, 312, # 352 - 109, 38, 23, 25, 10, 19, 79,5195, 61, 382,1124, 8, 30,5196,5197,5198, # 368 -5199,5200,5201,5202,5203,5204,5205,5206, 89, 62, 74, 34,2416, 112, 139, 196, # 384 - 271, 149, 84, 607, 131, 765, 46, 88, 153, 683, 76, 874, 101, 258, 57, 80, # 400 - 32, 364, 121,1508, 169,1547, 68, 235, 145,2999, 41, 360,3027, 70, 63, 31, # 416 - 43, 259, 262,1383, 99, 533, 194, 66, 93, 846, 217, 192, 56, 106, 58, 565, # 432 - 280, 272, 311, 256, 146, 82, 308, 71, 100, 128, 214, 655, 110, 261, 104,1140, # 448 - 54, 51, 36, 87, 67,3070, 185,2618,2936,2020, 28,1066,2390,2059,5207,5208, # 464 -5209,5210,5211,5212,5213,5214,5215,5216,4615,5217,5218,5219,5220,5221,5222,5223, # 480 -5224,5225,5226,5227,5228,5229,5230,5231,5232,5233,5234,5235,5236,3514,5237,5238, # 496 -5239,5240,5241,5242,5243,5244,2297,2031,4616,4310,3692,5245,3071,5246,3598,5247, # 512 -4617,3231,3515,5248,4101,4311,4618,3808,4312,4102,5249,4103,4104,3599,5250,5251, # 528 -5252,5253,5254,5255,5256,5257,5258,5259,5260,5261,5262,5263,5264,5265,5266,5267, # 544 -5268,5269,5270,5271,5272,5273,5274,5275,5276,5277,5278,5279,5280,5281,5282,5283, # 560 -5284,5285,5286,5287,5288,5289,5290,5291,5292,5293,5294,5295,5296,5297,5298,5299, # 576 -5300,5301,5302,5303,5304,5305,5306,5307,5308,5309,5310,5311,5312,5313,5314,5315, # 592 -5316,5317,5318,5319,5320,5321,5322,5323,5324,5325,5326,5327,5328,5329,5330,5331, # 608 -5332,5333,5334,5335,5336,5337,5338,5339,5340,5341,5342,5343,5344,5345,5346,5347, # 624 -5348,5349,5350,5351,5352,5353,5354,5355,5356,5357,5358,5359,5360,5361,5362,5363, # 640 -5364,5365,5366,5367,5368,5369,5370,5371,5372,5373,5374,5375,5376,5377,5378,5379, # 656 -5380,5381, 363, 642,2787,2878,2788,2789,2316,3232,2317,3434,2011, 165,1942,3930, # 672 -3931,3932,3933,5382,4619,5383,4620,5384,5385,5386,5387,5388,5389,5390,5391,5392, # 688 -5393,5394,5395,5396,5397,5398,5399,5400,5401,5402,5403,5404,5405,5406,5407,5408, # 704 -5409,5410,5411,5412,5413,5414,5415,5416,5417,5418,5419,5420,5421,5422,5423,5424, # 720 -5425,5426,5427,5428,5429,5430,5431,5432,5433,5434,5435,5436,5437,5438,5439,5440, # 736 -5441,5442,5443,5444,5445,5446,5447,5448,5449,5450,5451,5452,5453,5454,5455,5456, # 752 -5457,5458,5459,5460,5461,5462,5463,5464,5465,5466,5467,5468,5469,5470,5471,5472, # 768 -5473,5474,5475,5476,5477,5478,5479,5480,5481,5482,5483,5484,5485,5486,5487,5488, # 784 -5489,5490,5491,5492,5493,5494,5495,5496,5497,5498,5499,5500,5501,5502,5503,5504, # 800 -5505,5506,5507,5508,5509,5510,5511,5512,5513,5514,5515,5516,5517,5518,5519,5520, # 816 -5521,5522,5523,5524,5525,5526,5527,5528,5529,5530,5531,5532,5533,5534,5535,5536, # 832 -5537,5538,5539,5540,5541,5542,5543,5544,5545,5546,5547,5548,5549,5550,5551,5552, # 848 -5553,5554,5555,5556,5557,5558,5559,5560,5561,5562,5563,5564,5565,5566,5567,5568, # 864 -5569,5570,5571,5572,5573,5574,5575,5576,5577,5578,5579,5580,5581,5582,5583,5584, # 880 -5585,5586,5587,5588,5589,5590,5591,5592,5593,5594,5595,5596,5597,5598,5599,5600, # 896 -5601,5602,5603,5604,5605,5606,5607,5608,5609,5610,5611,5612,5613,5614,5615,5616, # 912 -5617,5618,5619,5620,5621,5622,5623,5624,5625,5626,5627,5628,5629,5630,5631,5632, # 928 -5633,5634,5635,5636,5637,5638,5639,5640,5641,5642,5643,5644,5645,5646,5647,5648, # 944 -5649,5650,5651,5652,5653,5654,5655,5656,5657,5658,5659,5660,5661,5662,5663,5664, # 960 -5665,5666,5667,5668,5669,5670,5671,5672,5673,5674,5675,5676,5677,5678,5679,5680, # 976 -5681,5682,5683,5684,5685,5686,5687,5688,5689,5690,5691,5692,5693,5694,5695,5696, # 992 -5697,5698,5699,5700,5701,5702,5703,5704,5705,5706,5707,5708,5709,5710,5711,5712, # 1008 -5713,5714,5715,5716,5717,5718,5719,5720,5721,5722,5723,5724,5725,5726,5727,5728, # 1024 -5729,5730,5731,5732,5733,5734,5735,5736,5737,5738,5739,5740,5741,5742,5743,5744, # 1040 -5745,5746,5747,5748,5749,5750,5751,5752,5753,5754,5755,5756,5757,5758,5759,5760, # 1056 -5761,5762,5763,5764,5765,5766,5767,5768,5769,5770,5771,5772,5773,5774,5775,5776, # 1072 -5777,5778,5779,5780,5781,5782,5783,5784,5785,5786,5787,5788,5789,5790,5791,5792, # 1088 -5793,5794,5795,5796,5797,5798,5799,5800,5801,5802,5803,5804,5805,5806,5807,5808, # 1104 -5809,5810,5811,5812,5813,5814,5815,5816,5817,5818,5819,5820,5821,5822,5823,5824, # 1120 -5825,5826,5827,5828,5829,5830,5831,5832,5833,5834,5835,5836,5837,5838,5839,5840, # 1136 -5841,5842,5843,5844,5845,5846,5847,5848,5849,5850,5851,5852,5853,5854,5855,5856, # 1152 -5857,5858,5859,5860,5861,5862,5863,5864,5865,5866,5867,5868,5869,5870,5871,5872, # 1168 -5873,5874,5875,5876,5877,5878,5879,5880,5881,5882,5883,5884,5885,5886,5887,5888, # 1184 -5889,5890,5891,5892,5893,5894,5895,5896,5897,5898,5899,5900,5901,5902,5903,5904, # 1200 -5905,5906,5907,5908,5909,5910,5911,5912,5913,5914,5915,5916,5917,5918,5919,5920, # 1216 -5921,5922,5923,5924,5925,5926,5927,5928,5929,5930,5931,5932,5933,5934,5935,5936, # 1232 -5937,5938,5939,5940,5941,5942,5943,5944,5945,5946,5947,5948,5949,5950,5951,5952, # 1248 -5953,5954,5955,5956,5957,5958,5959,5960,5961,5962,5963,5964,5965,5966,5967,5968, # 1264 -5969,5970,5971,5972,5973,5974,5975,5976,5977,5978,5979,5980,5981,5982,5983,5984, # 1280 -5985,5986,5987,5988,5989,5990,5991,5992,5993,5994,5995,5996,5997,5998,5999,6000, # 1296 -6001,6002,6003,6004,6005,6006,6007,6008,6009,6010,6011,6012,6013,6014,6015,6016, # 1312 -6017,6018,6019,6020,6021,6022,6023,6024,6025,6026,6027,6028,6029,6030,6031,6032, # 1328 -6033,6034,6035,6036,6037,6038,6039,6040,6041,6042,6043,6044,6045,6046,6047,6048, # 1344 -6049,6050,6051,6052,6053,6054,6055,6056,6057,6058,6059,6060,6061,6062,6063,6064, # 1360 -6065,6066,6067,6068,6069,6070,6071,6072,6073,6074,6075,6076,6077,6078,6079,6080, # 1376 -6081,6082,6083,6084,6085,6086,6087,6088,6089,6090,6091,6092,6093,6094,6095,6096, # 1392 -6097,6098,6099,6100,6101,6102,6103,6104,6105,6106,6107,6108,6109,6110,6111,6112, # 1408 -6113,6114,2044,2060,4621, 997,1235, 473,1186,4622, 920,3378,6115,6116, 379,1108, # 1424 -4313,2657,2735,3934,6117,3809, 636,3233, 573,1026,3693,3435,2974,3300,2298,4105, # 1440 - 854,2937,2463, 393,2581,2417, 539, 752,1280,2750,2480, 140,1161, 440, 708,1569, # 1456 - 665,2497,1746,1291,1523,3000, 164,1603, 847,1331, 537,1997, 486, 508,1693,2418, # 1472 -1970,2227, 878,1220, 299,1030, 969, 652,2751, 624,1137,3301,2619, 65,3302,2045, # 1488 -1761,1859,3120,1930,3694,3516, 663,1767, 852, 835,3695, 269, 767,2826,2339,1305, # 1504 - 896,1150, 770,1616,6118, 506,1502,2075,1012,2519, 775,2520,2975,2340,2938,4314, # 1520 -3028,2086,1224,1943,2286,6119,3072,4315,2240,1273,1987,3935,1557, 175, 597, 985, # 1536 -3517,2419,2521,1416,3029, 585, 938,1931,1007,1052,1932,1685,6120,3379,4316,4623, # 1552 - 804, 599,3121,1333,2128,2539,1159,1554,2032,3810, 687,2033,2904, 952, 675,1467, # 1568 -3436,6121,2241,1096,1786,2440,1543,1924, 980,1813,2228, 781,2692,1879, 728,1918, # 1584 -3696,4624, 548,1950,4625,1809,1088,1356,3303,2522,1944, 502, 972, 373, 513,2827, # 1600 - 586,2377,2391,1003,1976,1631,6122,2464,1084, 648,1776,4626,2141, 324, 962,2012, # 1616 -2177,2076,1384, 742,2178,1448,1173,1810, 222, 102, 301, 445, 125,2420, 662,2498, # 1632 - 277, 200,1476,1165,1068, 224,2562,1378,1446, 450,1880, 659, 791, 582,4627,2939, # 1648 -3936,1516,1274, 555,2099,3697,1020,1389,1526,3380,1762,1723,1787,2229, 412,2114, # 1664 -1900,2392,3518, 512,2597, 427,1925,2341,3122,1653,1686,2465,2499, 697, 330, 273, # 1680 - 380,2162, 951, 832, 780, 991,1301,3073, 965,2270,3519, 668,2523,2636,1286, 535, # 1696 -1407, 518, 671, 957,2658,2378, 267, 611,2197,3030,6123, 248,2299, 967,1799,2356, # 1712 - 850,1418,3437,1876,1256,1480,2828,1718,6124,6125,1755,1664,2405,6126,4628,2879, # 1728 -2829, 499,2179, 676,4629, 557,2329,2214,2090, 325,3234, 464, 811,3001, 992,2342, # 1744 -2481,1232,1469, 303,2242, 466,1070,2163, 603,1777,2091,4630,2752,4631,2714, 322, # 1760 -2659,1964,1768, 481,2188,1463,2330,2857,3600,2092,3031,2421,4632,2318,2070,1849, # 1776 -2598,4633,1302,2254,1668,1701,2422,3811,2905,3032,3123,2046,4106,1763,1694,4634, # 1792 -1604, 943,1724,1454, 917, 868,2215,1169,2940, 552,1145,1800,1228,1823,1955, 316, # 1808 -1080,2510, 361,1807,2830,4107,2660,3381,1346,1423,1134,4108,6127, 541,1263,1229, # 1824 -1148,2540, 545, 465,1833,2880,3438,1901,3074,2482, 816,3937, 713,1788,2500, 122, # 1840 -1575, 195,1451,2501,1111,6128, 859, 374,1225,2243,2483,4317, 390,1033,3439,3075, # 1856 -2524,1687, 266, 793,1440,2599, 946, 779, 802, 507, 897,1081, 528,2189,1292, 711, # 1872 -1866,1725,1167,1640, 753, 398,2661,1053, 246, 348,4318, 137,1024,3440,1600,2077, # 1888 -2129, 825,4319, 698, 238, 521, 187,2300,1157,2423,1641,1605,1464,1610,1097,2541, # 1904 -1260,1436, 759,2255,1814,2150, 705,3235, 409,2563,3304, 561,3033,2005,2564, 726, # 1920 -1956,2343,3698,4109, 949,3812,3813,3520,1669, 653,1379,2525, 881,2198, 632,2256, # 1936 -1027, 778,1074, 733,1957, 514,1481,2466, 554,2180, 702,3938,1606,1017,1398,6129, # 1952 -1380,3521, 921, 993,1313, 594, 449,1489,1617,1166, 768,1426,1360, 495,1794,3601, # 1968 -1177,3602,1170,4320,2344, 476, 425,3167,4635,3168,1424, 401,2662,1171,3382,1998, # 1984 -1089,4110, 477,3169, 474,6130,1909, 596,2831,1842, 494, 693,1051,1028,1207,3076, # 2000 - 606,2115, 727,2790,1473,1115, 743,3522, 630, 805,1532,4321,2021, 366,1057, 838, # 2016 - 684,1114,2142,4322,2050,1492,1892,1808,2271,3814,2424,1971,1447,1373,3305,1090, # 2032 -1536,3939,3523,3306,1455,2199, 336, 369,2331,1035, 584,2393, 902, 718,2600,6131, # 2048 -2753, 463,2151,1149,1611,2467, 715,1308,3124,1268, 343,1413,3236,1517,1347,2663, # 2064 -2093,3940,2022,1131,1553,2100,2941,1427,3441,2942,1323,2484,6132,1980, 872,2368, # 2080 -2441,2943, 320,2369,2116,1082, 679,1933,3941,2791,3815, 625,1143,2023, 422,2200, # 2096 -3816,6133, 730,1695, 356,2257,1626,2301,2858,2637,1627,1778, 937, 883,2906,2693, # 2112 -3002,1769,1086, 400,1063,1325,3307,2792,4111,3077, 456,2345,1046, 747,6134,1524, # 2128 - 884,1094,3383,1474,2164,1059, 974,1688,2181,2258,1047, 345,1665,1187, 358, 875, # 2144 -3170, 305, 660,3524,2190,1334,1135,3171,1540,1649,2542,1527, 927, 968,2793, 885, # 2160 -1972,1850, 482, 500,2638,1218,1109,1085,2543,1654,2034, 876, 78,2287,1482,1277, # 2176 - 861,1675,1083,1779, 724,2754, 454, 397,1132,1612,2332, 893, 672,1237, 257,2259, # 2192 -2370, 135,3384, 337,2244, 547, 352, 340, 709,2485,1400, 788,1138,2511, 540, 772, # 2208 -1682,2260,2272,2544,2013,1843,1902,4636,1999,1562,2288,4637,2201,1403,1533, 407, # 2224 - 576,3308,1254,2071, 978,3385, 170, 136,1201,3125,2664,3172,2394, 213, 912, 873, # 2240 -3603,1713,2202, 699,3604,3699, 813,3442, 493, 531,1054, 468,2907,1483, 304, 281, # 2256 -4112,1726,1252,2094, 339,2319,2130,2639, 756,1563,2944, 748, 571,2976,1588,2425, # 2272 -2715,1851,1460,2426,1528,1392,1973,3237, 288,3309, 685,3386, 296, 892,2716,2216, # 2288 -1570,2245, 722,1747,2217, 905,3238,1103,6135,1893,1441,1965, 251,1805,2371,3700, # 2304 -2601,1919,1078, 75,2182,1509,1592,1270,2640,4638,2152,6136,3310,3817, 524, 706, # 2320 -1075, 292,3818,1756,2602, 317, 98,3173,3605,3525,1844,2218,3819,2502, 814, 567, # 2336 - 385,2908,1534,6137, 534,1642,3239, 797,6138,1670,1529, 953,4323, 188,1071, 538, # 2352 - 178, 729,3240,2109,1226,1374,2000,2357,2977, 731,2468,1116,2014,2051,6139,1261, # 2368 -1593, 803,2859,2736,3443, 556, 682, 823,1541,6140,1369,2289,1706,2794, 845, 462, # 2384 -2603,2665,1361, 387, 162,2358,1740, 739,1770,1720,1304,1401,3241,1049, 627,1571, # 2400 -2427,3526,1877,3942,1852,1500, 431,1910,1503, 677, 297,2795, 286,1433,1038,1198, # 2416 -2290,1133,1596,4113,4639,2469,1510,1484,3943,6141,2442, 108, 712,4640,2372, 866, # 2432 -3701,2755,3242,1348, 834,1945,1408,3527,2395,3243,1811, 824, 994,1179,2110,1548, # 2448 -1453, 790,3003, 690,4324,4325,2832,2909,3820,1860,3821, 225,1748, 310, 346,1780, # 2464 -2470, 821,1993,2717,2796, 828, 877,3528,2860,2471,1702,2165,2910,2486,1789, 453, # 2480 - 359,2291,1676, 73,1164,1461,1127,3311, 421, 604, 314,1037, 589, 116,2487, 737, # 2496 - 837,1180, 111, 244, 735,6142,2261,1861,1362, 986, 523, 418, 581,2666,3822, 103, # 2512 - 855, 503,1414,1867,2488,1091, 657,1597, 979, 605,1316,4641,1021,2443,2078,2001, # 2528 -1209, 96, 587,2166,1032, 260,1072,2153, 173, 94, 226,3244, 819,2006,4642,4114, # 2544 -2203, 231,1744, 782, 97,2667, 786,3387, 887, 391, 442,2219,4326,1425,6143,2694, # 2560 - 633,1544,1202, 483,2015, 592,2052,1958,2472,1655, 419, 129,4327,3444,3312,1714, # 2576 -1257,3078,4328,1518,1098, 865,1310,1019,1885,1512,1734, 469,2444, 148, 773, 436, # 2592 -1815,1868,1128,1055,4329,1245,2756,3445,2154,1934,1039,4643, 579,1238, 932,2320, # 2608 - 353, 205, 801, 115,2428, 944,2321,1881, 399,2565,1211, 678, 766,3944, 335,2101, # 2624 -1459,1781,1402,3945,2737,2131,1010, 844, 981,1326,1013, 550,1816,1545,2620,1335, # 2640 -1008, 371,2881, 936,1419,1613,3529,1456,1395,2273,1834,2604,1317,2738,2503, 416, # 2656 -1643,4330, 806,1126, 229, 591,3946,1314,1981,1576,1837,1666, 347,1790, 977,3313, # 2672 - 764,2861,1853, 688,2429,1920,1462, 77, 595, 415,2002,3034, 798,1192,4115,6144, # 2688 -2978,4331,3035,2695,2582,2072,2566, 430,2430,1727, 842,1396,3947,3702, 613, 377, # 2704 - 278, 236,1417,3388,3314,3174, 757,1869, 107,3530,6145,1194, 623,2262, 207,1253, # 2720 -2167,3446,3948, 492,1117,1935, 536,1838,2757,1246,4332, 696,2095,2406,1393,1572, # 2736 -3175,1782, 583, 190, 253,1390,2230, 830,3126,3389, 934,3245,1703,1749,2979,1870, # 2752 -2545,1656,2204, 869,2346,4116,3176,1817, 496,1764,4644, 942,1504, 404,1903,1122, # 2768 -1580,3606,2945,1022, 515, 372,1735, 955,2431,3036,6146,2797,1110,2302,2798, 617, # 2784 -6147, 441, 762,1771,3447,3607,3608,1904, 840,3037, 86, 939,1385, 572,1370,2445, # 2800 -1336, 114,3703, 898, 294, 203,3315, 703,1583,2274, 429, 961,4333,1854,1951,3390, # 2816 -2373,3704,4334,1318,1381, 966,1911,2322,1006,1155, 309, 989, 458,2718,1795,1372, # 2832 -1203, 252,1689,1363,3177, 517,1936, 168,1490, 562, 193,3823,1042,4117,1835, 551, # 2848 - 470,4645, 395, 489,3448,1871,1465,2583,2641, 417,1493, 279,1295, 511,1236,1119, # 2864 - 72,1231,1982,1812,3004, 871,1564, 984,3449,1667,2696,2096,4646,2347,2833,1673, # 2880 -3609, 695,3246,2668, 807,1183,4647, 890, 388,2333,1801,1457,2911,1765,1477,1031, # 2896 -3316,3317,1278,3391,2799,2292,2526, 163,3450,4335,2669,1404,1802,6148,2323,2407, # 2912 -1584,1728,1494,1824,1269, 298, 909,3318,1034,1632, 375, 776,1683,2061, 291, 210, # 2928 -1123, 809,1249,1002,2642,3038, 206,1011,2132, 144, 975, 882,1565, 342, 667, 754, # 2944 -1442,2143,1299,2303,2062, 447, 626,2205,1221,2739,2912,1144,1214,2206,2584, 760, # 2960 -1715, 614, 950,1281,2670,2621, 810, 577,1287,2546,4648, 242,2168, 250,2643, 691, # 2976 - 123,2644, 647, 313,1029, 689,1357,2946,1650, 216, 771,1339,1306, 808,2063, 549, # 2992 - 913,1371,2913,2914,6149,1466,1092,1174,1196,1311,2605,2396,1783,1796,3079, 406, # 3008 -2671,2117,3949,4649, 487,1825,2220,6150,2915, 448,2348,1073,6151,2397,1707, 130, # 3024 - 900,1598, 329, 176,1959,2527,1620,6152,2275,4336,3319,1983,2191,3705,3610,2155, # 3040 -3706,1912,1513,1614,6153,1988, 646, 392,2304,1589,3320,3039,1826,1239,1352,1340, # 3056 -2916, 505,2567,1709,1437,2408,2547, 906,6154,2672, 384,1458,1594,1100,1329, 710, # 3072 - 423,3531,2064,2231,2622,1989,2673,1087,1882, 333, 841,3005,1296,2882,2379, 580, # 3088 -1937,1827,1293,2585, 601, 574, 249,1772,4118,2079,1120, 645, 901,1176,1690, 795, # 3104 -2207, 478,1434, 516,1190,1530, 761,2080, 930,1264, 355, 435,1552, 644,1791, 987, # 3120 - 220,1364,1163,1121,1538, 306,2169,1327,1222, 546,2645, 218, 241, 610,1704,3321, # 3136 -1984,1839,1966,2528, 451,6155,2586,3707,2568, 907,3178, 254,2947, 186,1845,4650, # 3152 - 745, 432,1757, 428,1633, 888,2246,2221,2489,3611,2118,1258,1265, 956,3127,1784, # 3168 -4337,2490, 319, 510, 119, 457,3612, 274,2035,2007,4651,1409,3128, 970,2758, 590, # 3184 -2800, 661,2247,4652,2008,3950,1420,1549,3080,3322,3951,1651,1375,2111, 485,2491, # 3200 -1429,1156,6156,2548,2183,1495, 831,1840,2529,2446, 501,1657, 307,1894,3247,1341, # 3216 - 666, 899,2156,1539,2549,1559, 886, 349,2208,3081,2305,1736,3824,2170,2759,1014, # 3232 -1913,1386, 542,1397,2948, 490, 368, 716, 362, 159, 282,2569,1129,1658,1288,1750, # 3248 -2674, 276, 649,2016, 751,1496, 658,1818,1284,1862,2209,2087,2512,3451, 622,2834, # 3264 - 376, 117,1060,2053,1208,1721,1101,1443, 247,1250,3179,1792,3952,2760,2398,3953, # 3280 -6157,2144,3708, 446,2432,1151,2570,3452,2447,2761,2835,1210,2448,3082, 424,2222, # 3296 -1251,2449,2119,2836, 504,1581,4338, 602, 817, 857,3825,2349,2306, 357,3826,1470, # 3312 -1883,2883, 255, 958, 929,2917,3248, 302,4653,1050,1271,1751,2307,1952,1430,2697, # 3328 -2719,2359, 354,3180, 777, 158,2036,4339,1659,4340,4654,2308,2949,2248,1146,2232, # 3344 -3532,2720,1696,2623,3827,6158,3129,1550,2698,1485,1297,1428, 637, 931,2721,2145, # 3360 - 914,2550,2587, 81,2450, 612, 827,2646,1242,4655,1118,2884, 472,1855,3181,3533, # 3376 -3534, 569,1353,2699,1244,1758,2588,4119,2009,2762,2171,3709,1312,1531,6159,1152, # 3392 -1938, 134,1830, 471,3710,2276,1112,1535,3323,3453,3535, 982,1337,2950, 488, 826, # 3408 - 674,1058,1628,4120,2017, 522,2399, 211, 568,1367,3454, 350, 293,1872,1139,3249, # 3424 -1399,1946,3006,1300,2360,3324, 588, 736,6160,2606, 744, 669,3536,3828,6161,1358, # 3440 - 199, 723, 848, 933, 851,1939,1505,1514,1338,1618,1831,4656,1634,3613, 443,2740, # 3456 -3829, 717,1947, 491,1914,6162,2551,1542,4121,1025,6163,1099,1223, 198,3040,2722, # 3472 - 370, 410,1905,2589, 998,1248,3182,2380, 519,1449,4122,1710, 947, 928,1153,4341, # 3488 -2277, 344,2624,1511, 615, 105, 161,1212,1076,1960,3130,2054,1926,1175,1906,2473, # 3504 - 414,1873,2801,6164,2309, 315,1319,3325, 318,2018,2146,2157, 963, 631, 223,4342, # 3520 -4343,2675, 479,3711,1197,2625,3712,2676,2361,6165,4344,4123,6166,2451,3183,1886, # 3536 -2184,1674,1330,1711,1635,1506, 799, 219,3250,3083,3954,1677,3713,3326,2081,3614, # 3552 -1652,2073,4657,1147,3041,1752, 643,1961, 147,1974,3955,6167,1716,2037, 918,3007, # 3568 -1994, 120,1537, 118, 609,3184,4345, 740,3455,1219, 332,1615,3830,6168,1621,2980, # 3584 -1582, 783, 212, 553,2350,3714,1349,2433,2082,4124, 889,6169,2310,1275,1410, 973, # 3600 - 166,1320,3456,1797,1215,3185,2885,1846,2590,2763,4658, 629, 822,3008, 763, 940, # 3616 -1990,2862, 439,2409,1566,1240,1622, 926,1282,1907,2764, 654,2210,1607, 327,1130, # 3632 -3956,1678,1623,6170,2434,2192, 686, 608,3831,3715, 903,3957,3042,6171,2741,1522, # 3648 -1915,1105,1555,2552,1359, 323,3251,4346,3457, 738,1354,2553,2311,2334,1828,2003, # 3664 -3832,1753,2351,1227,6172,1887,4125,1478,6173,2410,1874,1712,1847, 520,1204,2607, # 3680 - 264,4659, 836,2677,2102, 600,4660,3833,2278,3084,6174,4347,3615,1342, 640, 532, # 3696 - 543,2608,1888,2400,2591,1009,4348,1497, 341,1737,3616,2723,1394, 529,3252,1321, # 3712 - 983,4661,1515,2120, 971,2592, 924, 287,1662,3186,4349,2700,4350,1519, 908,1948, # 3728 -2452, 156, 796,1629,1486,2223,2055, 694,4126,1259,1036,3392,1213,2249,2742,1889, # 3744 -1230,3958,1015, 910, 408, 559,3617,4662, 746, 725, 935,4663,3959,3009,1289, 563, # 3760 - 867,4664,3960,1567,2981,2038,2626, 988,2263,2381,4351, 143,2374, 704,1895,6175, # 3776 -1188,3716,2088, 673,3085,2362,4352, 484,1608,1921,2765,2918, 215, 904,3618,3537, # 3792 - 894, 509, 976,3043,2701,3961,4353,2837,2982, 498,6176,6177,1102,3538,1332,3393, # 3808 -1487,1636,1637, 233, 245,3962, 383, 650, 995,3044, 460,1520,1206,2352, 749,3327, # 3824 - 530, 700, 389,1438,1560,1773,3963,2264, 719,2951,2724,3834, 870,1832,1644,1000, # 3840 - 839,2474,3717, 197,1630,3394, 365,2886,3964,1285,2133, 734, 922, 818,1106, 732, # 3856 - 480,2083,1774,3458, 923,2279,1350, 221,3086, 85,2233,2234,3835,1585,3010,2147, # 3872 -1387,1705,2382,1619,2475, 133, 239,2802,1991,1016,2084,2383, 411,2838,1113, 651, # 3888 -1985,1160,3328, 990,1863,3087,1048,1276,2647, 265,2627,1599,3253,2056, 150, 638, # 3904 -2019, 656, 853, 326,1479, 680,1439,4354,1001,1759, 413,3459,3395,2492,1431, 459, # 3920 -4355,1125,3329,2265,1953,1450,2065,2863, 849, 351,2678,3131,3254,3255,1104,1577, # 3936 - 227,1351,1645,2453,2193,1421,2887, 812,2121, 634, 95,2435, 201,2312,4665,1646, # 3952 -1671,2743,1601,2554,2702,2648,2280,1315,1366,2089,3132,1573,3718,3965,1729,1189, # 3968 - 328,2679,1077,1940,1136, 558,1283, 964,1195, 621,2074,1199,1743,3460,3619,1896, # 3984 -1916,1890,3836,2952,1154,2112,1064, 862, 378,3011,2066,2113,2803,1568,2839,6178, # 4000 -3088,2919,1941,1660,2004,1992,2194, 142, 707,1590,1708,1624,1922,1023,1836,1233, # 4016 -1004,2313, 789, 741,3620,6179,1609,2411,1200,4127,3719,3720,4666,2057,3721, 593, # 4032 -2840, 367,2920,1878,6180,3461,1521, 628,1168, 692,2211,2649, 300, 720,2067,2571, # 4048 -2953,3396, 959,2504,3966,3539,3462,1977, 701,6181, 954,1043, 800, 681, 183,3722, # 4064 -1803,1730,3540,4128,2103, 815,2314, 174, 467, 230,2454,1093,2134, 755,3541,3397, # 4080 -1141,1162,6182,1738,2039, 270,3256,2513,1005,1647,2185,3837, 858,1679,1897,1719, # 4096 -2954,2324,1806, 402, 670, 167,4129,1498,2158,2104, 750,6183, 915, 189,1680,1551, # 4112 - 455,4356,1501,2455, 405,1095,2955, 338,1586,1266,1819, 570, 641,1324, 237,1556, # 4128 -2650,1388,3723,6184,1368,2384,1343,1978,3089,2436, 879,3724, 792,1191, 758,3012, # 4144 -1411,2135,1322,4357, 240,4667,1848,3725,1574,6185, 420,3045,1546,1391, 714,4358, # 4160 -1967, 941,1864, 863, 664, 426, 560,1731,2680,1785,2864,1949,2363, 403,3330,1415, # 4176 -1279,2136,1697,2335, 204, 721,2097,3838, 90,6186,2085,2505, 191,3967, 124,2148, # 4192 -1376,1798,1178,1107,1898,1405, 860,4359,1243,1272,2375,2983,1558,2456,1638, 113, # 4208 -3621, 578,1923,2609, 880, 386,4130, 784,2186,2266,1422,2956,2172,1722, 497, 263, # 4224 -2514,1267,2412,2610, 177,2703,3542, 774,1927,1344, 616,1432,1595,1018, 172,4360, # 4240 -2325, 911,4361, 438,1468,3622, 794,3968,2024,2173,1681,1829,2957, 945, 895,3090, # 4256 - 575,2212,2476, 475,2401,2681, 785,2744,1745,2293,2555,1975,3133,2865, 394,4668, # 4272 -3839, 635,4131, 639, 202,1507,2195,2766,1345,1435,2572,3726,1908,1184,1181,2457, # 4288 -3727,3134,4362, 843,2611, 437, 916,4669, 234, 769,1884,3046,3047,3623, 833,6187, # 4304 -1639,2250,2402,1355,1185,2010,2047, 999, 525,1732,1290,1488,2612, 948,1578,3728, # 4320 -2413,2477,1216,2725,2159, 334,3840,1328,3624,2921,1525,4132, 564,1056, 891,4363, # 4336 -1444,1698,2385,2251,3729,1365,2281,2235,1717,6188, 864,3841,2515, 444, 527,2767, # 4352 -2922,3625, 544, 461,6189, 566, 209,2437,3398,2098,1065,2068,3331,3626,3257,2137, # 4368 #last 512 -) -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/johabfreq.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/johabfreq.py deleted file mode 100644 index c129699..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/johabfreq.py +++ /dev/null @@ -1,2382 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -# The frequency data itself is the same as euc-kr. -# This is just a mapping table to euc-kr. - -JOHAB_TO_EUCKR_ORDER_TABLE = { - 0x8861: 0, - 0x8862: 1, - 0x8865: 2, - 0x8868: 3, - 0x8869: 4, - 0x886A: 5, - 0x886B: 6, - 0x8871: 7, - 0x8873: 8, - 0x8874: 9, - 0x8875: 10, - 0x8876: 11, - 0x8877: 12, - 0x8878: 13, - 0x8879: 14, - 0x887B: 15, - 0x887C: 16, - 0x887D: 17, - 0x8881: 18, - 0x8882: 19, - 0x8885: 20, - 0x8889: 21, - 0x8891: 22, - 0x8893: 23, - 0x8895: 24, - 0x8896: 25, - 0x8897: 26, - 0x88A1: 27, - 0x88A2: 28, - 0x88A5: 29, - 0x88A9: 30, - 0x88B5: 31, - 0x88B7: 32, - 0x88C1: 33, - 0x88C5: 34, - 0x88C9: 35, - 0x88E1: 36, - 0x88E2: 37, - 0x88E5: 38, - 0x88E8: 39, - 0x88E9: 40, - 0x88EB: 41, - 0x88F1: 42, - 0x88F3: 43, - 0x88F5: 44, - 0x88F6: 45, - 0x88F7: 46, - 0x88F8: 47, - 0x88FB: 48, - 0x88FC: 49, - 0x88FD: 50, - 0x8941: 51, - 0x8945: 52, - 0x8949: 53, - 0x8951: 54, - 0x8953: 55, - 0x8955: 56, - 0x8956: 57, - 0x8957: 58, - 0x8961: 59, - 0x8962: 60, - 0x8963: 61, - 0x8965: 62, - 0x8968: 63, - 0x8969: 64, - 0x8971: 65, - 0x8973: 66, - 0x8975: 67, - 0x8976: 68, - 0x8977: 69, - 0x897B: 70, - 0x8981: 71, - 0x8985: 72, - 0x8989: 73, - 0x8993: 74, - 0x8995: 75, - 0x89A1: 76, - 0x89A2: 77, - 0x89A5: 78, - 0x89A8: 79, - 0x89A9: 80, - 0x89AB: 81, - 0x89AD: 82, - 0x89B0: 83, - 0x89B1: 84, - 0x89B3: 85, - 0x89B5: 86, - 0x89B7: 87, - 0x89B8: 88, - 0x89C1: 89, - 0x89C2: 90, - 0x89C5: 91, - 0x89C9: 92, - 0x89CB: 93, - 0x89D1: 94, - 0x89D3: 95, - 0x89D5: 96, - 0x89D7: 97, - 0x89E1: 98, - 0x89E5: 99, - 0x89E9: 100, - 0x89F3: 101, - 0x89F6: 102, - 0x89F7: 103, - 0x8A41: 104, - 0x8A42: 105, - 0x8A45: 106, - 0x8A49: 107, - 0x8A51: 108, - 0x8A53: 109, - 0x8A55: 110, - 0x8A57: 111, - 0x8A61: 112, - 0x8A65: 113, - 0x8A69: 114, - 0x8A73: 115, - 0x8A75: 116, - 0x8A81: 117, - 0x8A82: 118, - 0x8A85: 119, - 0x8A88: 120, - 0x8A89: 121, - 0x8A8A: 122, - 0x8A8B: 123, - 0x8A90: 124, - 0x8A91: 125, - 0x8A93: 126, - 0x8A95: 127, - 0x8A97: 128, - 0x8A98: 129, - 0x8AA1: 130, - 0x8AA2: 131, - 0x8AA5: 132, - 0x8AA9: 133, - 0x8AB6: 134, - 0x8AB7: 135, - 0x8AC1: 136, - 0x8AD5: 137, - 0x8AE1: 138, - 0x8AE2: 139, - 0x8AE5: 140, - 0x8AE9: 141, - 0x8AF1: 142, - 0x8AF3: 143, - 0x8AF5: 144, - 0x8B41: 145, - 0x8B45: 146, - 0x8B49: 147, - 0x8B61: 148, - 0x8B62: 149, - 0x8B65: 150, - 0x8B68: 151, - 0x8B69: 152, - 0x8B6A: 153, - 0x8B71: 154, - 0x8B73: 155, - 0x8B75: 156, - 0x8B77: 157, - 0x8B81: 158, - 0x8BA1: 159, - 0x8BA2: 160, - 0x8BA5: 161, - 0x8BA8: 162, - 0x8BA9: 163, - 0x8BAB: 164, - 0x8BB1: 165, - 0x8BB3: 166, - 0x8BB5: 167, - 0x8BB7: 168, - 0x8BB8: 169, - 0x8BBC: 170, - 0x8C61: 171, - 0x8C62: 172, - 0x8C63: 173, - 0x8C65: 174, - 0x8C69: 175, - 0x8C6B: 176, - 0x8C71: 177, - 0x8C73: 178, - 0x8C75: 179, - 0x8C76: 180, - 0x8C77: 181, - 0x8C7B: 182, - 0x8C81: 183, - 0x8C82: 184, - 0x8C85: 185, - 0x8C89: 186, - 0x8C91: 187, - 0x8C93: 188, - 0x8C95: 189, - 0x8C96: 190, - 0x8C97: 191, - 0x8CA1: 192, - 0x8CA2: 193, - 0x8CA9: 194, - 0x8CE1: 195, - 0x8CE2: 196, - 0x8CE3: 197, - 0x8CE5: 198, - 0x8CE9: 199, - 0x8CF1: 200, - 0x8CF3: 201, - 0x8CF5: 202, - 0x8CF6: 203, - 0x8CF7: 204, - 0x8D41: 205, - 0x8D42: 206, - 0x8D45: 207, - 0x8D51: 208, - 0x8D55: 209, - 0x8D57: 210, - 0x8D61: 211, - 0x8D65: 212, - 0x8D69: 213, - 0x8D75: 214, - 0x8D76: 215, - 0x8D7B: 216, - 0x8D81: 217, - 0x8DA1: 218, - 0x8DA2: 219, - 0x8DA5: 220, - 0x8DA7: 221, - 0x8DA9: 222, - 0x8DB1: 223, - 0x8DB3: 224, - 0x8DB5: 225, - 0x8DB7: 226, - 0x8DB8: 227, - 0x8DB9: 228, - 0x8DC1: 229, - 0x8DC2: 230, - 0x8DC9: 231, - 0x8DD6: 232, - 0x8DD7: 233, - 0x8DE1: 234, - 0x8DE2: 235, - 0x8DF7: 236, - 0x8E41: 237, - 0x8E45: 238, - 0x8E49: 239, - 0x8E51: 240, - 0x8E53: 241, - 0x8E57: 242, - 0x8E61: 243, - 0x8E81: 244, - 0x8E82: 245, - 0x8E85: 246, - 0x8E89: 247, - 0x8E90: 248, - 0x8E91: 249, - 0x8E93: 250, - 0x8E95: 251, - 0x8E97: 252, - 0x8E98: 253, - 0x8EA1: 254, - 0x8EA9: 255, - 0x8EB6: 256, - 0x8EB7: 257, - 0x8EC1: 258, - 0x8EC2: 259, - 0x8EC5: 260, - 0x8EC9: 261, - 0x8ED1: 262, - 0x8ED3: 263, - 0x8ED6: 264, - 0x8EE1: 265, - 0x8EE5: 266, - 0x8EE9: 267, - 0x8EF1: 268, - 0x8EF3: 269, - 0x8F41: 270, - 0x8F61: 271, - 0x8F62: 272, - 0x8F65: 273, - 0x8F67: 274, - 0x8F69: 275, - 0x8F6B: 276, - 0x8F70: 277, - 0x8F71: 278, - 0x8F73: 279, - 0x8F75: 280, - 0x8F77: 281, - 0x8F7B: 282, - 0x8FA1: 283, - 0x8FA2: 284, - 0x8FA5: 285, - 0x8FA9: 286, - 0x8FB1: 287, - 0x8FB3: 288, - 0x8FB5: 289, - 0x8FB7: 290, - 0x9061: 291, - 0x9062: 292, - 0x9063: 293, - 0x9065: 294, - 0x9068: 295, - 0x9069: 296, - 0x906A: 297, - 0x906B: 298, - 0x9071: 299, - 0x9073: 300, - 0x9075: 301, - 0x9076: 302, - 0x9077: 303, - 0x9078: 304, - 0x9079: 305, - 0x907B: 306, - 0x907D: 307, - 0x9081: 308, - 0x9082: 309, - 0x9085: 310, - 0x9089: 311, - 0x9091: 312, - 0x9093: 313, - 0x9095: 314, - 0x9096: 315, - 0x9097: 316, - 0x90A1: 317, - 0x90A2: 318, - 0x90A5: 319, - 0x90A9: 320, - 0x90B1: 321, - 0x90B7: 322, - 0x90E1: 323, - 0x90E2: 324, - 0x90E4: 325, - 0x90E5: 326, - 0x90E9: 327, - 0x90EB: 328, - 0x90EC: 329, - 0x90F1: 330, - 0x90F3: 331, - 0x90F5: 332, - 0x90F6: 333, - 0x90F7: 334, - 0x90FD: 335, - 0x9141: 336, - 0x9142: 337, - 0x9145: 338, - 0x9149: 339, - 0x9151: 340, - 0x9153: 341, - 0x9155: 342, - 0x9156: 343, - 0x9157: 344, - 0x9161: 345, - 0x9162: 346, - 0x9165: 347, - 0x9169: 348, - 0x9171: 349, - 0x9173: 350, - 0x9176: 351, - 0x9177: 352, - 0x917A: 353, - 0x9181: 354, - 0x9185: 355, - 0x91A1: 356, - 0x91A2: 357, - 0x91A5: 358, - 0x91A9: 359, - 0x91AB: 360, - 0x91B1: 361, - 0x91B3: 362, - 0x91B5: 363, - 0x91B7: 364, - 0x91BC: 365, - 0x91BD: 366, - 0x91C1: 367, - 0x91C5: 368, - 0x91C9: 369, - 0x91D6: 370, - 0x9241: 371, - 0x9245: 372, - 0x9249: 373, - 0x9251: 374, - 0x9253: 375, - 0x9255: 376, - 0x9261: 377, - 0x9262: 378, - 0x9265: 379, - 0x9269: 380, - 0x9273: 381, - 0x9275: 382, - 0x9277: 383, - 0x9281: 384, - 0x9282: 385, - 0x9285: 386, - 0x9288: 387, - 0x9289: 388, - 0x9291: 389, - 0x9293: 390, - 0x9295: 391, - 0x9297: 392, - 0x92A1: 393, - 0x92B6: 394, - 0x92C1: 395, - 0x92E1: 396, - 0x92E5: 397, - 0x92E9: 398, - 0x92F1: 399, - 0x92F3: 400, - 0x9341: 401, - 0x9342: 402, - 0x9349: 403, - 0x9351: 404, - 0x9353: 405, - 0x9357: 406, - 0x9361: 407, - 0x9362: 408, - 0x9365: 409, - 0x9369: 410, - 0x936A: 411, - 0x936B: 412, - 0x9371: 413, - 0x9373: 414, - 0x9375: 415, - 0x9377: 416, - 0x9378: 417, - 0x937C: 418, - 0x9381: 419, - 0x9385: 420, - 0x9389: 421, - 0x93A1: 422, - 0x93A2: 423, - 0x93A5: 424, - 0x93A9: 425, - 0x93AB: 426, - 0x93B1: 427, - 0x93B3: 428, - 0x93B5: 429, - 0x93B7: 430, - 0x93BC: 431, - 0x9461: 432, - 0x9462: 433, - 0x9463: 434, - 0x9465: 435, - 0x9468: 436, - 0x9469: 437, - 0x946A: 438, - 0x946B: 439, - 0x946C: 440, - 0x9470: 441, - 0x9471: 442, - 0x9473: 443, - 0x9475: 444, - 0x9476: 445, - 0x9477: 446, - 0x9478: 447, - 0x9479: 448, - 0x947D: 449, - 0x9481: 450, - 0x9482: 451, - 0x9485: 452, - 0x9489: 453, - 0x9491: 454, - 0x9493: 455, - 0x9495: 456, - 0x9496: 457, - 0x9497: 458, - 0x94A1: 459, - 0x94E1: 460, - 0x94E2: 461, - 0x94E3: 462, - 0x94E5: 463, - 0x94E8: 464, - 0x94E9: 465, - 0x94EB: 466, - 0x94EC: 467, - 0x94F1: 468, - 0x94F3: 469, - 0x94F5: 470, - 0x94F7: 471, - 0x94F9: 472, - 0x94FC: 473, - 0x9541: 474, - 0x9542: 475, - 0x9545: 476, - 0x9549: 477, - 0x9551: 478, - 0x9553: 479, - 0x9555: 480, - 0x9556: 481, - 0x9557: 482, - 0x9561: 483, - 0x9565: 484, - 0x9569: 485, - 0x9576: 486, - 0x9577: 487, - 0x9581: 488, - 0x9585: 489, - 0x95A1: 490, - 0x95A2: 491, - 0x95A5: 492, - 0x95A8: 493, - 0x95A9: 494, - 0x95AB: 495, - 0x95AD: 496, - 0x95B1: 497, - 0x95B3: 498, - 0x95B5: 499, - 0x95B7: 500, - 0x95B9: 501, - 0x95BB: 502, - 0x95C1: 503, - 0x95C5: 504, - 0x95C9: 505, - 0x95E1: 506, - 0x95F6: 507, - 0x9641: 508, - 0x9645: 509, - 0x9649: 510, - 0x9651: 511, - 0x9653: 512, - 0x9655: 513, - 0x9661: 514, - 0x9681: 515, - 0x9682: 516, - 0x9685: 517, - 0x9689: 518, - 0x9691: 519, - 0x9693: 520, - 0x9695: 521, - 0x9697: 522, - 0x96A1: 523, - 0x96B6: 524, - 0x96C1: 525, - 0x96D7: 526, - 0x96E1: 527, - 0x96E5: 528, - 0x96E9: 529, - 0x96F3: 530, - 0x96F5: 531, - 0x96F7: 532, - 0x9741: 533, - 0x9745: 534, - 0x9749: 535, - 0x9751: 536, - 0x9757: 537, - 0x9761: 538, - 0x9762: 539, - 0x9765: 540, - 0x9768: 541, - 0x9769: 542, - 0x976B: 543, - 0x9771: 544, - 0x9773: 545, - 0x9775: 546, - 0x9777: 547, - 0x9781: 548, - 0x97A1: 549, - 0x97A2: 550, - 0x97A5: 551, - 0x97A8: 552, - 0x97A9: 553, - 0x97B1: 554, - 0x97B3: 555, - 0x97B5: 556, - 0x97B6: 557, - 0x97B7: 558, - 0x97B8: 559, - 0x9861: 560, - 0x9862: 561, - 0x9865: 562, - 0x9869: 563, - 0x9871: 564, - 0x9873: 565, - 0x9875: 566, - 0x9876: 567, - 0x9877: 568, - 0x987D: 569, - 0x9881: 570, - 0x9882: 571, - 0x9885: 572, - 0x9889: 573, - 0x9891: 574, - 0x9893: 575, - 0x9895: 576, - 0x9896: 577, - 0x9897: 578, - 0x98E1: 579, - 0x98E2: 580, - 0x98E5: 581, - 0x98E9: 582, - 0x98EB: 583, - 0x98EC: 584, - 0x98F1: 585, - 0x98F3: 586, - 0x98F5: 587, - 0x98F6: 588, - 0x98F7: 589, - 0x98FD: 590, - 0x9941: 591, - 0x9942: 592, - 0x9945: 593, - 0x9949: 594, - 0x9951: 595, - 0x9953: 596, - 0x9955: 597, - 0x9956: 598, - 0x9957: 599, - 0x9961: 600, - 0x9976: 601, - 0x99A1: 602, - 0x99A2: 603, - 0x99A5: 604, - 0x99A9: 605, - 0x99B7: 606, - 0x99C1: 607, - 0x99C9: 608, - 0x99E1: 609, - 0x9A41: 610, - 0x9A45: 611, - 0x9A81: 612, - 0x9A82: 613, - 0x9A85: 614, - 0x9A89: 615, - 0x9A90: 616, - 0x9A91: 617, - 0x9A97: 618, - 0x9AC1: 619, - 0x9AE1: 620, - 0x9AE5: 621, - 0x9AE9: 622, - 0x9AF1: 623, - 0x9AF3: 624, - 0x9AF7: 625, - 0x9B61: 626, - 0x9B62: 627, - 0x9B65: 628, - 0x9B68: 629, - 0x9B69: 630, - 0x9B71: 631, - 0x9B73: 632, - 0x9B75: 633, - 0x9B81: 634, - 0x9B85: 635, - 0x9B89: 636, - 0x9B91: 637, - 0x9B93: 638, - 0x9BA1: 639, - 0x9BA5: 640, - 0x9BA9: 641, - 0x9BB1: 642, - 0x9BB3: 643, - 0x9BB5: 644, - 0x9BB7: 645, - 0x9C61: 646, - 0x9C62: 647, - 0x9C65: 648, - 0x9C69: 649, - 0x9C71: 650, - 0x9C73: 651, - 0x9C75: 652, - 0x9C76: 653, - 0x9C77: 654, - 0x9C78: 655, - 0x9C7C: 656, - 0x9C7D: 657, - 0x9C81: 658, - 0x9C82: 659, - 0x9C85: 660, - 0x9C89: 661, - 0x9C91: 662, - 0x9C93: 663, - 0x9C95: 664, - 0x9C96: 665, - 0x9C97: 666, - 0x9CA1: 667, - 0x9CA2: 668, - 0x9CA5: 669, - 0x9CB5: 670, - 0x9CB7: 671, - 0x9CE1: 672, - 0x9CE2: 673, - 0x9CE5: 674, - 0x9CE9: 675, - 0x9CF1: 676, - 0x9CF3: 677, - 0x9CF5: 678, - 0x9CF6: 679, - 0x9CF7: 680, - 0x9CFD: 681, - 0x9D41: 682, - 0x9D42: 683, - 0x9D45: 684, - 0x9D49: 685, - 0x9D51: 686, - 0x9D53: 687, - 0x9D55: 688, - 0x9D57: 689, - 0x9D61: 690, - 0x9D62: 691, - 0x9D65: 692, - 0x9D69: 693, - 0x9D71: 694, - 0x9D73: 695, - 0x9D75: 696, - 0x9D76: 697, - 0x9D77: 698, - 0x9D81: 699, - 0x9D85: 700, - 0x9D93: 701, - 0x9D95: 702, - 0x9DA1: 703, - 0x9DA2: 704, - 0x9DA5: 705, - 0x9DA9: 706, - 0x9DB1: 707, - 0x9DB3: 708, - 0x9DB5: 709, - 0x9DB7: 710, - 0x9DC1: 711, - 0x9DC5: 712, - 0x9DD7: 713, - 0x9DF6: 714, - 0x9E41: 715, - 0x9E45: 716, - 0x9E49: 717, - 0x9E51: 718, - 0x9E53: 719, - 0x9E55: 720, - 0x9E57: 721, - 0x9E61: 722, - 0x9E65: 723, - 0x9E69: 724, - 0x9E73: 725, - 0x9E75: 726, - 0x9E77: 727, - 0x9E81: 728, - 0x9E82: 729, - 0x9E85: 730, - 0x9E89: 731, - 0x9E91: 732, - 0x9E93: 733, - 0x9E95: 734, - 0x9E97: 735, - 0x9EA1: 736, - 0x9EB6: 737, - 0x9EC1: 738, - 0x9EE1: 739, - 0x9EE2: 740, - 0x9EE5: 741, - 0x9EE9: 742, - 0x9EF1: 743, - 0x9EF5: 744, - 0x9EF7: 745, - 0x9F41: 746, - 0x9F42: 747, - 0x9F45: 748, - 0x9F49: 749, - 0x9F51: 750, - 0x9F53: 751, - 0x9F55: 752, - 0x9F57: 753, - 0x9F61: 754, - 0x9F62: 755, - 0x9F65: 756, - 0x9F69: 757, - 0x9F71: 758, - 0x9F73: 759, - 0x9F75: 760, - 0x9F77: 761, - 0x9F78: 762, - 0x9F7B: 763, - 0x9F7C: 764, - 0x9FA1: 765, - 0x9FA2: 766, - 0x9FA5: 767, - 0x9FA9: 768, - 0x9FB1: 769, - 0x9FB3: 770, - 0x9FB5: 771, - 0x9FB7: 772, - 0xA061: 773, - 0xA062: 774, - 0xA065: 775, - 0xA067: 776, - 0xA068: 777, - 0xA069: 778, - 0xA06A: 779, - 0xA06B: 780, - 0xA071: 781, - 0xA073: 782, - 0xA075: 783, - 0xA077: 784, - 0xA078: 785, - 0xA07B: 786, - 0xA07D: 787, - 0xA081: 788, - 0xA082: 789, - 0xA085: 790, - 0xA089: 791, - 0xA091: 792, - 0xA093: 793, - 0xA095: 794, - 0xA096: 795, - 0xA097: 796, - 0xA098: 797, - 0xA0A1: 798, - 0xA0A2: 799, - 0xA0A9: 800, - 0xA0B7: 801, - 0xA0E1: 802, - 0xA0E2: 803, - 0xA0E5: 804, - 0xA0E9: 805, - 0xA0EB: 806, - 0xA0F1: 807, - 0xA0F3: 808, - 0xA0F5: 809, - 0xA0F7: 810, - 0xA0F8: 811, - 0xA0FD: 812, - 0xA141: 813, - 0xA142: 814, - 0xA145: 815, - 0xA149: 816, - 0xA151: 817, - 0xA153: 818, - 0xA155: 819, - 0xA156: 820, - 0xA157: 821, - 0xA161: 822, - 0xA162: 823, - 0xA165: 824, - 0xA169: 825, - 0xA175: 826, - 0xA176: 827, - 0xA177: 828, - 0xA179: 829, - 0xA181: 830, - 0xA1A1: 831, - 0xA1A2: 832, - 0xA1A4: 833, - 0xA1A5: 834, - 0xA1A9: 835, - 0xA1AB: 836, - 0xA1B1: 837, - 0xA1B3: 838, - 0xA1B5: 839, - 0xA1B7: 840, - 0xA1C1: 841, - 0xA1C5: 842, - 0xA1D6: 843, - 0xA1D7: 844, - 0xA241: 845, - 0xA245: 846, - 0xA249: 847, - 0xA253: 848, - 0xA255: 849, - 0xA257: 850, - 0xA261: 851, - 0xA265: 852, - 0xA269: 853, - 0xA273: 854, - 0xA275: 855, - 0xA281: 856, - 0xA282: 857, - 0xA283: 858, - 0xA285: 859, - 0xA288: 860, - 0xA289: 861, - 0xA28A: 862, - 0xA28B: 863, - 0xA291: 864, - 0xA293: 865, - 0xA295: 866, - 0xA297: 867, - 0xA29B: 868, - 0xA29D: 869, - 0xA2A1: 870, - 0xA2A5: 871, - 0xA2A9: 872, - 0xA2B3: 873, - 0xA2B5: 874, - 0xA2C1: 875, - 0xA2E1: 876, - 0xA2E5: 877, - 0xA2E9: 878, - 0xA341: 879, - 0xA345: 880, - 0xA349: 881, - 0xA351: 882, - 0xA355: 883, - 0xA361: 884, - 0xA365: 885, - 0xA369: 886, - 0xA371: 887, - 0xA375: 888, - 0xA3A1: 889, - 0xA3A2: 890, - 0xA3A5: 891, - 0xA3A8: 892, - 0xA3A9: 893, - 0xA3AB: 894, - 0xA3B1: 895, - 0xA3B3: 896, - 0xA3B5: 897, - 0xA3B6: 898, - 0xA3B7: 899, - 0xA3B9: 900, - 0xA3BB: 901, - 0xA461: 902, - 0xA462: 903, - 0xA463: 904, - 0xA464: 905, - 0xA465: 906, - 0xA468: 907, - 0xA469: 908, - 0xA46A: 909, - 0xA46B: 910, - 0xA46C: 911, - 0xA471: 912, - 0xA473: 913, - 0xA475: 914, - 0xA477: 915, - 0xA47B: 916, - 0xA481: 917, - 0xA482: 918, - 0xA485: 919, - 0xA489: 920, - 0xA491: 921, - 0xA493: 922, - 0xA495: 923, - 0xA496: 924, - 0xA497: 925, - 0xA49B: 926, - 0xA4A1: 927, - 0xA4A2: 928, - 0xA4A5: 929, - 0xA4B3: 930, - 0xA4E1: 931, - 0xA4E2: 932, - 0xA4E5: 933, - 0xA4E8: 934, - 0xA4E9: 935, - 0xA4EB: 936, - 0xA4F1: 937, - 0xA4F3: 938, - 0xA4F5: 939, - 0xA4F7: 940, - 0xA4F8: 941, - 0xA541: 942, - 0xA542: 943, - 0xA545: 944, - 0xA548: 945, - 0xA549: 946, - 0xA551: 947, - 0xA553: 948, - 0xA555: 949, - 0xA556: 950, - 0xA557: 951, - 0xA561: 952, - 0xA562: 953, - 0xA565: 954, - 0xA569: 955, - 0xA573: 956, - 0xA575: 957, - 0xA576: 958, - 0xA577: 959, - 0xA57B: 960, - 0xA581: 961, - 0xA585: 962, - 0xA5A1: 963, - 0xA5A2: 964, - 0xA5A3: 965, - 0xA5A5: 966, - 0xA5A9: 967, - 0xA5B1: 968, - 0xA5B3: 969, - 0xA5B5: 970, - 0xA5B7: 971, - 0xA5C1: 972, - 0xA5C5: 973, - 0xA5D6: 974, - 0xA5E1: 975, - 0xA5F6: 976, - 0xA641: 977, - 0xA642: 978, - 0xA645: 979, - 0xA649: 980, - 0xA651: 981, - 0xA653: 982, - 0xA661: 983, - 0xA665: 984, - 0xA681: 985, - 0xA682: 986, - 0xA685: 987, - 0xA688: 988, - 0xA689: 989, - 0xA68A: 990, - 0xA68B: 991, - 0xA691: 992, - 0xA693: 993, - 0xA695: 994, - 0xA697: 995, - 0xA69B: 996, - 0xA69C: 997, - 0xA6A1: 998, - 0xA6A9: 999, - 0xA6B6: 1000, - 0xA6C1: 1001, - 0xA6E1: 1002, - 0xA6E2: 1003, - 0xA6E5: 1004, - 0xA6E9: 1005, - 0xA6F7: 1006, - 0xA741: 1007, - 0xA745: 1008, - 0xA749: 1009, - 0xA751: 1010, - 0xA755: 1011, - 0xA757: 1012, - 0xA761: 1013, - 0xA762: 1014, - 0xA765: 1015, - 0xA769: 1016, - 0xA771: 1017, - 0xA773: 1018, - 0xA775: 1019, - 0xA7A1: 1020, - 0xA7A2: 1021, - 0xA7A5: 1022, - 0xA7A9: 1023, - 0xA7AB: 1024, - 0xA7B1: 1025, - 0xA7B3: 1026, - 0xA7B5: 1027, - 0xA7B7: 1028, - 0xA7B8: 1029, - 0xA7B9: 1030, - 0xA861: 1031, - 0xA862: 1032, - 0xA865: 1033, - 0xA869: 1034, - 0xA86B: 1035, - 0xA871: 1036, - 0xA873: 1037, - 0xA875: 1038, - 0xA876: 1039, - 0xA877: 1040, - 0xA87D: 1041, - 0xA881: 1042, - 0xA882: 1043, - 0xA885: 1044, - 0xA889: 1045, - 0xA891: 1046, - 0xA893: 1047, - 0xA895: 1048, - 0xA896: 1049, - 0xA897: 1050, - 0xA8A1: 1051, - 0xA8A2: 1052, - 0xA8B1: 1053, - 0xA8E1: 1054, - 0xA8E2: 1055, - 0xA8E5: 1056, - 0xA8E8: 1057, - 0xA8E9: 1058, - 0xA8F1: 1059, - 0xA8F5: 1060, - 0xA8F6: 1061, - 0xA8F7: 1062, - 0xA941: 1063, - 0xA957: 1064, - 0xA961: 1065, - 0xA962: 1066, - 0xA971: 1067, - 0xA973: 1068, - 0xA975: 1069, - 0xA976: 1070, - 0xA977: 1071, - 0xA9A1: 1072, - 0xA9A2: 1073, - 0xA9A5: 1074, - 0xA9A9: 1075, - 0xA9B1: 1076, - 0xA9B3: 1077, - 0xA9B7: 1078, - 0xAA41: 1079, - 0xAA61: 1080, - 0xAA77: 1081, - 0xAA81: 1082, - 0xAA82: 1083, - 0xAA85: 1084, - 0xAA89: 1085, - 0xAA91: 1086, - 0xAA95: 1087, - 0xAA97: 1088, - 0xAB41: 1089, - 0xAB57: 1090, - 0xAB61: 1091, - 0xAB65: 1092, - 0xAB69: 1093, - 0xAB71: 1094, - 0xAB73: 1095, - 0xABA1: 1096, - 0xABA2: 1097, - 0xABA5: 1098, - 0xABA9: 1099, - 0xABB1: 1100, - 0xABB3: 1101, - 0xABB5: 1102, - 0xABB7: 1103, - 0xAC61: 1104, - 0xAC62: 1105, - 0xAC64: 1106, - 0xAC65: 1107, - 0xAC68: 1108, - 0xAC69: 1109, - 0xAC6A: 1110, - 0xAC6B: 1111, - 0xAC71: 1112, - 0xAC73: 1113, - 0xAC75: 1114, - 0xAC76: 1115, - 0xAC77: 1116, - 0xAC7B: 1117, - 0xAC81: 1118, - 0xAC82: 1119, - 0xAC85: 1120, - 0xAC89: 1121, - 0xAC91: 1122, - 0xAC93: 1123, - 0xAC95: 1124, - 0xAC96: 1125, - 0xAC97: 1126, - 0xACA1: 1127, - 0xACA2: 1128, - 0xACA5: 1129, - 0xACA9: 1130, - 0xACB1: 1131, - 0xACB3: 1132, - 0xACB5: 1133, - 0xACB7: 1134, - 0xACC1: 1135, - 0xACC5: 1136, - 0xACC9: 1137, - 0xACD1: 1138, - 0xACD7: 1139, - 0xACE1: 1140, - 0xACE2: 1141, - 0xACE3: 1142, - 0xACE4: 1143, - 0xACE5: 1144, - 0xACE8: 1145, - 0xACE9: 1146, - 0xACEB: 1147, - 0xACEC: 1148, - 0xACF1: 1149, - 0xACF3: 1150, - 0xACF5: 1151, - 0xACF6: 1152, - 0xACF7: 1153, - 0xACFC: 1154, - 0xAD41: 1155, - 0xAD42: 1156, - 0xAD45: 1157, - 0xAD49: 1158, - 0xAD51: 1159, - 0xAD53: 1160, - 0xAD55: 1161, - 0xAD56: 1162, - 0xAD57: 1163, - 0xAD61: 1164, - 0xAD62: 1165, - 0xAD65: 1166, - 0xAD69: 1167, - 0xAD71: 1168, - 0xAD73: 1169, - 0xAD75: 1170, - 0xAD76: 1171, - 0xAD77: 1172, - 0xAD81: 1173, - 0xAD85: 1174, - 0xAD89: 1175, - 0xAD97: 1176, - 0xADA1: 1177, - 0xADA2: 1178, - 0xADA3: 1179, - 0xADA5: 1180, - 0xADA9: 1181, - 0xADAB: 1182, - 0xADB1: 1183, - 0xADB3: 1184, - 0xADB5: 1185, - 0xADB7: 1186, - 0xADBB: 1187, - 0xADC1: 1188, - 0xADC2: 1189, - 0xADC5: 1190, - 0xADC9: 1191, - 0xADD7: 1192, - 0xADE1: 1193, - 0xADE5: 1194, - 0xADE9: 1195, - 0xADF1: 1196, - 0xADF5: 1197, - 0xADF6: 1198, - 0xAE41: 1199, - 0xAE45: 1200, - 0xAE49: 1201, - 0xAE51: 1202, - 0xAE53: 1203, - 0xAE55: 1204, - 0xAE61: 1205, - 0xAE62: 1206, - 0xAE65: 1207, - 0xAE69: 1208, - 0xAE71: 1209, - 0xAE73: 1210, - 0xAE75: 1211, - 0xAE77: 1212, - 0xAE81: 1213, - 0xAE82: 1214, - 0xAE85: 1215, - 0xAE88: 1216, - 0xAE89: 1217, - 0xAE91: 1218, - 0xAE93: 1219, - 0xAE95: 1220, - 0xAE97: 1221, - 0xAE99: 1222, - 0xAE9B: 1223, - 0xAE9C: 1224, - 0xAEA1: 1225, - 0xAEB6: 1226, - 0xAEC1: 1227, - 0xAEC2: 1228, - 0xAEC5: 1229, - 0xAEC9: 1230, - 0xAED1: 1231, - 0xAED7: 1232, - 0xAEE1: 1233, - 0xAEE2: 1234, - 0xAEE5: 1235, - 0xAEE9: 1236, - 0xAEF1: 1237, - 0xAEF3: 1238, - 0xAEF5: 1239, - 0xAEF7: 1240, - 0xAF41: 1241, - 0xAF42: 1242, - 0xAF49: 1243, - 0xAF51: 1244, - 0xAF55: 1245, - 0xAF57: 1246, - 0xAF61: 1247, - 0xAF62: 1248, - 0xAF65: 1249, - 0xAF69: 1250, - 0xAF6A: 1251, - 0xAF71: 1252, - 0xAF73: 1253, - 0xAF75: 1254, - 0xAF77: 1255, - 0xAFA1: 1256, - 0xAFA2: 1257, - 0xAFA5: 1258, - 0xAFA8: 1259, - 0xAFA9: 1260, - 0xAFB0: 1261, - 0xAFB1: 1262, - 0xAFB3: 1263, - 0xAFB5: 1264, - 0xAFB7: 1265, - 0xAFBC: 1266, - 0xB061: 1267, - 0xB062: 1268, - 0xB064: 1269, - 0xB065: 1270, - 0xB069: 1271, - 0xB071: 1272, - 0xB073: 1273, - 0xB076: 1274, - 0xB077: 1275, - 0xB07D: 1276, - 0xB081: 1277, - 0xB082: 1278, - 0xB085: 1279, - 0xB089: 1280, - 0xB091: 1281, - 0xB093: 1282, - 0xB096: 1283, - 0xB097: 1284, - 0xB0B7: 1285, - 0xB0E1: 1286, - 0xB0E2: 1287, - 0xB0E5: 1288, - 0xB0E9: 1289, - 0xB0EB: 1290, - 0xB0F1: 1291, - 0xB0F3: 1292, - 0xB0F6: 1293, - 0xB0F7: 1294, - 0xB141: 1295, - 0xB145: 1296, - 0xB149: 1297, - 0xB185: 1298, - 0xB1A1: 1299, - 0xB1A2: 1300, - 0xB1A5: 1301, - 0xB1A8: 1302, - 0xB1A9: 1303, - 0xB1AB: 1304, - 0xB1B1: 1305, - 0xB1B3: 1306, - 0xB1B7: 1307, - 0xB1C1: 1308, - 0xB1C2: 1309, - 0xB1C5: 1310, - 0xB1D6: 1311, - 0xB1E1: 1312, - 0xB1F6: 1313, - 0xB241: 1314, - 0xB245: 1315, - 0xB249: 1316, - 0xB251: 1317, - 0xB253: 1318, - 0xB261: 1319, - 0xB281: 1320, - 0xB282: 1321, - 0xB285: 1322, - 0xB289: 1323, - 0xB291: 1324, - 0xB293: 1325, - 0xB297: 1326, - 0xB2A1: 1327, - 0xB2B6: 1328, - 0xB2C1: 1329, - 0xB2E1: 1330, - 0xB2E5: 1331, - 0xB357: 1332, - 0xB361: 1333, - 0xB362: 1334, - 0xB365: 1335, - 0xB369: 1336, - 0xB36B: 1337, - 0xB370: 1338, - 0xB371: 1339, - 0xB373: 1340, - 0xB381: 1341, - 0xB385: 1342, - 0xB389: 1343, - 0xB391: 1344, - 0xB3A1: 1345, - 0xB3A2: 1346, - 0xB3A5: 1347, - 0xB3A9: 1348, - 0xB3B1: 1349, - 0xB3B3: 1350, - 0xB3B5: 1351, - 0xB3B7: 1352, - 0xB461: 1353, - 0xB462: 1354, - 0xB465: 1355, - 0xB466: 1356, - 0xB467: 1357, - 0xB469: 1358, - 0xB46A: 1359, - 0xB46B: 1360, - 0xB470: 1361, - 0xB471: 1362, - 0xB473: 1363, - 0xB475: 1364, - 0xB476: 1365, - 0xB477: 1366, - 0xB47B: 1367, - 0xB47C: 1368, - 0xB481: 1369, - 0xB482: 1370, - 0xB485: 1371, - 0xB489: 1372, - 0xB491: 1373, - 0xB493: 1374, - 0xB495: 1375, - 0xB496: 1376, - 0xB497: 1377, - 0xB4A1: 1378, - 0xB4A2: 1379, - 0xB4A5: 1380, - 0xB4A9: 1381, - 0xB4AC: 1382, - 0xB4B1: 1383, - 0xB4B3: 1384, - 0xB4B5: 1385, - 0xB4B7: 1386, - 0xB4BB: 1387, - 0xB4BD: 1388, - 0xB4C1: 1389, - 0xB4C5: 1390, - 0xB4C9: 1391, - 0xB4D3: 1392, - 0xB4E1: 1393, - 0xB4E2: 1394, - 0xB4E5: 1395, - 0xB4E6: 1396, - 0xB4E8: 1397, - 0xB4E9: 1398, - 0xB4EA: 1399, - 0xB4EB: 1400, - 0xB4F1: 1401, - 0xB4F3: 1402, - 0xB4F4: 1403, - 0xB4F5: 1404, - 0xB4F6: 1405, - 0xB4F7: 1406, - 0xB4F8: 1407, - 0xB4FA: 1408, - 0xB4FC: 1409, - 0xB541: 1410, - 0xB542: 1411, - 0xB545: 1412, - 0xB549: 1413, - 0xB551: 1414, - 0xB553: 1415, - 0xB555: 1416, - 0xB557: 1417, - 0xB561: 1418, - 0xB562: 1419, - 0xB563: 1420, - 0xB565: 1421, - 0xB569: 1422, - 0xB56B: 1423, - 0xB56C: 1424, - 0xB571: 1425, - 0xB573: 1426, - 0xB574: 1427, - 0xB575: 1428, - 0xB576: 1429, - 0xB577: 1430, - 0xB57B: 1431, - 0xB57C: 1432, - 0xB57D: 1433, - 0xB581: 1434, - 0xB585: 1435, - 0xB589: 1436, - 0xB591: 1437, - 0xB593: 1438, - 0xB595: 1439, - 0xB596: 1440, - 0xB5A1: 1441, - 0xB5A2: 1442, - 0xB5A5: 1443, - 0xB5A9: 1444, - 0xB5AA: 1445, - 0xB5AB: 1446, - 0xB5AD: 1447, - 0xB5B0: 1448, - 0xB5B1: 1449, - 0xB5B3: 1450, - 0xB5B5: 1451, - 0xB5B7: 1452, - 0xB5B9: 1453, - 0xB5C1: 1454, - 0xB5C2: 1455, - 0xB5C5: 1456, - 0xB5C9: 1457, - 0xB5D1: 1458, - 0xB5D3: 1459, - 0xB5D5: 1460, - 0xB5D6: 1461, - 0xB5D7: 1462, - 0xB5E1: 1463, - 0xB5E2: 1464, - 0xB5E5: 1465, - 0xB5F1: 1466, - 0xB5F5: 1467, - 0xB5F7: 1468, - 0xB641: 1469, - 0xB642: 1470, - 0xB645: 1471, - 0xB649: 1472, - 0xB651: 1473, - 0xB653: 1474, - 0xB655: 1475, - 0xB657: 1476, - 0xB661: 1477, - 0xB662: 1478, - 0xB665: 1479, - 0xB669: 1480, - 0xB671: 1481, - 0xB673: 1482, - 0xB675: 1483, - 0xB677: 1484, - 0xB681: 1485, - 0xB682: 1486, - 0xB685: 1487, - 0xB689: 1488, - 0xB68A: 1489, - 0xB68B: 1490, - 0xB691: 1491, - 0xB693: 1492, - 0xB695: 1493, - 0xB697: 1494, - 0xB6A1: 1495, - 0xB6A2: 1496, - 0xB6A5: 1497, - 0xB6A9: 1498, - 0xB6B1: 1499, - 0xB6B3: 1500, - 0xB6B6: 1501, - 0xB6B7: 1502, - 0xB6C1: 1503, - 0xB6C2: 1504, - 0xB6C5: 1505, - 0xB6C9: 1506, - 0xB6D1: 1507, - 0xB6D3: 1508, - 0xB6D7: 1509, - 0xB6E1: 1510, - 0xB6E2: 1511, - 0xB6E5: 1512, - 0xB6E9: 1513, - 0xB6F1: 1514, - 0xB6F3: 1515, - 0xB6F5: 1516, - 0xB6F7: 1517, - 0xB741: 1518, - 0xB742: 1519, - 0xB745: 1520, - 0xB749: 1521, - 0xB751: 1522, - 0xB753: 1523, - 0xB755: 1524, - 0xB757: 1525, - 0xB759: 1526, - 0xB761: 1527, - 0xB762: 1528, - 0xB765: 1529, - 0xB769: 1530, - 0xB76F: 1531, - 0xB771: 1532, - 0xB773: 1533, - 0xB775: 1534, - 0xB777: 1535, - 0xB778: 1536, - 0xB779: 1537, - 0xB77A: 1538, - 0xB77B: 1539, - 0xB77C: 1540, - 0xB77D: 1541, - 0xB781: 1542, - 0xB785: 1543, - 0xB789: 1544, - 0xB791: 1545, - 0xB795: 1546, - 0xB7A1: 1547, - 0xB7A2: 1548, - 0xB7A5: 1549, - 0xB7A9: 1550, - 0xB7AA: 1551, - 0xB7AB: 1552, - 0xB7B0: 1553, - 0xB7B1: 1554, - 0xB7B3: 1555, - 0xB7B5: 1556, - 0xB7B6: 1557, - 0xB7B7: 1558, - 0xB7B8: 1559, - 0xB7BC: 1560, - 0xB861: 1561, - 0xB862: 1562, - 0xB865: 1563, - 0xB867: 1564, - 0xB868: 1565, - 0xB869: 1566, - 0xB86B: 1567, - 0xB871: 1568, - 0xB873: 1569, - 0xB875: 1570, - 0xB876: 1571, - 0xB877: 1572, - 0xB878: 1573, - 0xB881: 1574, - 0xB882: 1575, - 0xB885: 1576, - 0xB889: 1577, - 0xB891: 1578, - 0xB893: 1579, - 0xB895: 1580, - 0xB896: 1581, - 0xB897: 1582, - 0xB8A1: 1583, - 0xB8A2: 1584, - 0xB8A5: 1585, - 0xB8A7: 1586, - 0xB8A9: 1587, - 0xB8B1: 1588, - 0xB8B7: 1589, - 0xB8C1: 1590, - 0xB8C5: 1591, - 0xB8C9: 1592, - 0xB8E1: 1593, - 0xB8E2: 1594, - 0xB8E5: 1595, - 0xB8E9: 1596, - 0xB8EB: 1597, - 0xB8F1: 1598, - 0xB8F3: 1599, - 0xB8F5: 1600, - 0xB8F7: 1601, - 0xB8F8: 1602, - 0xB941: 1603, - 0xB942: 1604, - 0xB945: 1605, - 0xB949: 1606, - 0xB951: 1607, - 0xB953: 1608, - 0xB955: 1609, - 0xB957: 1610, - 0xB961: 1611, - 0xB965: 1612, - 0xB969: 1613, - 0xB971: 1614, - 0xB973: 1615, - 0xB976: 1616, - 0xB977: 1617, - 0xB981: 1618, - 0xB9A1: 1619, - 0xB9A2: 1620, - 0xB9A5: 1621, - 0xB9A9: 1622, - 0xB9AB: 1623, - 0xB9B1: 1624, - 0xB9B3: 1625, - 0xB9B5: 1626, - 0xB9B7: 1627, - 0xB9B8: 1628, - 0xB9B9: 1629, - 0xB9BD: 1630, - 0xB9C1: 1631, - 0xB9C2: 1632, - 0xB9C9: 1633, - 0xB9D3: 1634, - 0xB9D5: 1635, - 0xB9D7: 1636, - 0xB9E1: 1637, - 0xB9F6: 1638, - 0xB9F7: 1639, - 0xBA41: 1640, - 0xBA45: 1641, - 0xBA49: 1642, - 0xBA51: 1643, - 0xBA53: 1644, - 0xBA55: 1645, - 0xBA57: 1646, - 0xBA61: 1647, - 0xBA62: 1648, - 0xBA65: 1649, - 0xBA77: 1650, - 0xBA81: 1651, - 0xBA82: 1652, - 0xBA85: 1653, - 0xBA89: 1654, - 0xBA8A: 1655, - 0xBA8B: 1656, - 0xBA91: 1657, - 0xBA93: 1658, - 0xBA95: 1659, - 0xBA97: 1660, - 0xBAA1: 1661, - 0xBAB6: 1662, - 0xBAC1: 1663, - 0xBAE1: 1664, - 0xBAE2: 1665, - 0xBAE5: 1666, - 0xBAE9: 1667, - 0xBAF1: 1668, - 0xBAF3: 1669, - 0xBAF5: 1670, - 0xBB41: 1671, - 0xBB45: 1672, - 0xBB49: 1673, - 0xBB51: 1674, - 0xBB61: 1675, - 0xBB62: 1676, - 0xBB65: 1677, - 0xBB69: 1678, - 0xBB71: 1679, - 0xBB73: 1680, - 0xBB75: 1681, - 0xBB77: 1682, - 0xBBA1: 1683, - 0xBBA2: 1684, - 0xBBA5: 1685, - 0xBBA8: 1686, - 0xBBA9: 1687, - 0xBBAB: 1688, - 0xBBB1: 1689, - 0xBBB3: 1690, - 0xBBB5: 1691, - 0xBBB7: 1692, - 0xBBB8: 1693, - 0xBBBB: 1694, - 0xBBBC: 1695, - 0xBC61: 1696, - 0xBC62: 1697, - 0xBC65: 1698, - 0xBC67: 1699, - 0xBC69: 1700, - 0xBC6C: 1701, - 0xBC71: 1702, - 0xBC73: 1703, - 0xBC75: 1704, - 0xBC76: 1705, - 0xBC77: 1706, - 0xBC81: 1707, - 0xBC82: 1708, - 0xBC85: 1709, - 0xBC89: 1710, - 0xBC91: 1711, - 0xBC93: 1712, - 0xBC95: 1713, - 0xBC96: 1714, - 0xBC97: 1715, - 0xBCA1: 1716, - 0xBCA5: 1717, - 0xBCB7: 1718, - 0xBCE1: 1719, - 0xBCE2: 1720, - 0xBCE5: 1721, - 0xBCE9: 1722, - 0xBCF1: 1723, - 0xBCF3: 1724, - 0xBCF5: 1725, - 0xBCF6: 1726, - 0xBCF7: 1727, - 0xBD41: 1728, - 0xBD57: 1729, - 0xBD61: 1730, - 0xBD76: 1731, - 0xBDA1: 1732, - 0xBDA2: 1733, - 0xBDA5: 1734, - 0xBDA9: 1735, - 0xBDB1: 1736, - 0xBDB3: 1737, - 0xBDB5: 1738, - 0xBDB7: 1739, - 0xBDB9: 1740, - 0xBDC1: 1741, - 0xBDC2: 1742, - 0xBDC9: 1743, - 0xBDD6: 1744, - 0xBDE1: 1745, - 0xBDF6: 1746, - 0xBE41: 1747, - 0xBE45: 1748, - 0xBE49: 1749, - 0xBE51: 1750, - 0xBE53: 1751, - 0xBE77: 1752, - 0xBE81: 1753, - 0xBE82: 1754, - 0xBE85: 1755, - 0xBE89: 1756, - 0xBE91: 1757, - 0xBE93: 1758, - 0xBE97: 1759, - 0xBEA1: 1760, - 0xBEB6: 1761, - 0xBEB7: 1762, - 0xBEE1: 1763, - 0xBF41: 1764, - 0xBF61: 1765, - 0xBF71: 1766, - 0xBF75: 1767, - 0xBF77: 1768, - 0xBFA1: 1769, - 0xBFA2: 1770, - 0xBFA5: 1771, - 0xBFA9: 1772, - 0xBFB1: 1773, - 0xBFB3: 1774, - 0xBFB7: 1775, - 0xBFB8: 1776, - 0xBFBD: 1777, - 0xC061: 1778, - 0xC062: 1779, - 0xC065: 1780, - 0xC067: 1781, - 0xC069: 1782, - 0xC071: 1783, - 0xC073: 1784, - 0xC075: 1785, - 0xC076: 1786, - 0xC077: 1787, - 0xC078: 1788, - 0xC081: 1789, - 0xC082: 1790, - 0xC085: 1791, - 0xC089: 1792, - 0xC091: 1793, - 0xC093: 1794, - 0xC095: 1795, - 0xC096: 1796, - 0xC097: 1797, - 0xC0A1: 1798, - 0xC0A5: 1799, - 0xC0A7: 1800, - 0xC0A9: 1801, - 0xC0B1: 1802, - 0xC0B7: 1803, - 0xC0E1: 1804, - 0xC0E2: 1805, - 0xC0E5: 1806, - 0xC0E9: 1807, - 0xC0F1: 1808, - 0xC0F3: 1809, - 0xC0F5: 1810, - 0xC0F6: 1811, - 0xC0F7: 1812, - 0xC141: 1813, - 0xC142: 1814, - 0xC145: 1815, - 0xC149: 1816, - 0xC151: 1817, - 0xC153: 1818, - 0xC155: 1819, - 0xC157: 1820, - 0xC161: 1821, - 0xC165: 1822, - 0xC176: 1823, - 0xC181: 1824, - 0xC185: 1825, - 0xC197: 1826, - 0xC1A1: 1827, - 0xC1A2: 1828, - 0xC1A5: 1829, - 0xC1A9: 1830, - 0xC1B1: 1831, - 0xC1B3: 1832, - 0xC1B5: 1833, - 0xC1B7: 1834, - 0xC1C1: 1835, - 0xC1C5: 1836, - 0xC1C9: 1837, - 0xC1D7: 1838, - 0xC241: 1839, - 0xC245: 1840, - 0xC249: 1841, - 0xC251: 1842, - 0xC253: 1843, - 0xC255: 1844, - 0xC257: 1845, - 0xC261: 1846, - 0xC271: 1847, - 0xC281: 1848, - 0xC282: 1849, - 0xC285: 1850, - 0xC289: 1851, - 0xC291: 1852, - 0xC293: 1853, - 0xC295: 1854, - 0xC297: 1855, - 0xC2A1: 1856, - 0xC2B6: 1857, - 0xC2C1: 1858, - 0xC2C5: 1859, - 0xC2E1: 1860, - 0xC2E5: 1861, - 0xC2E9: 1862, - 0xC2F1: 1863, - 0xC2F3: 1864, - 0xC2F5: 1865, - 0xC2F7: 1866, - 0xC341: 1867, - 0xC345: 1868, - 0xC349: 1869, - 0xC351: 1870, - 0xC357: 1871, - 0xC361: 1872, - 0xC362: 1873, - 0xC365: 1874, - 0xC369: 1875, - 0xC371: 1876, - 0xC373: 1877, - 0xC375: 1878, - 0xC377: 1879, - 0xC3A1: 1880, - 0xC3A2: 1881, - 0xC3A5: 1882, - 0xC3A8: 1883, - 0xC3A9: 1884, - 0xC3AA: 1885, - 0xC3B1: 1886, - 0xC3B3: 1887, - 0xC3B5: 1888, - 0xC3B7: 1889, - 0xC461: 1890, - 0xC462: 1891, - 0xC465: 1892, - 0xC469: 1893, - 0xC471: 1894, - 0xC473: 1895, - 0xC475: 1896, - 0xC477: 1897, - 0xC481: 1898, - 0xC482: 1899, - 0xC485: 1900, - 0xC489: 1901, - 0xC491: 1902, - 0xC493: 1903, - 0xC495: 1904, - 0xC496: 1905, - 0xC497: 1906, - 0xC4A1: 1907, - 0xC4A2: 1908, - 0xC4B7: 1909, - 0xC4E1: 1910, - 0xC4E2: 1911, - 0xC4E5: 1912, - 0xC4E8: 1913, - 0xC4E9: 1914, - 0xC4F1: 1915, - 0xC4F3: 1916, - 0xC4F5: 1917, - 0xC4F6: 1918, - 0xC4F7: 1919, - 0xC541: 1920, - 0xC542: 1921, - 0xC545: 1922, - 0xC549: 1923, - 0xC551: 1924, - 0xC553: 1925, - 0xC555: 1926, - 0xC557: 1927, - 0xC561: 1928, - 0xC565: 1929, - 0xC569: 1930, - 0xC571: 1931, - 0xC573: 1932, - 0xC575: 1933, - 0xC576: 1934, - 0xC577: 1935, - 0xC581: 1936, - 0xC5A1: 1937, - 0xC5A2: 1938, - 0xC5A5: 1939, - 0xC5A9: 1940, - 0xC5B1: 1941, - 0xC5B3: 1942, - 0xC5B5: 1943, - 0xC5B7: 1944, - 0xC5C1: 1945, - 0xC5C2: 1946, - 0xC5C5: 1947, - 0xC5C9: 1948, - 0xC5D1: 1949, - 0xC5D7: 1950, - 0xC5E1: 1951, - 0xC5F7: 1952, - 0xC641: 1953, - 0xC649: 1954, - 0xC661: 1955, - 0xC681: 1956, - 0xC682: 1957, - 0xC685: 1958, - 0xC689: 1959, - 0xC691: 1960, - 0xC693: 1961, - 0xC695: 1962, - 0xC697: 1963, - 0xC6A1: 1964, - 0xC6A5: 1965, - 0xC6A9: 1966, - 0xC6B7: 1967, - 0xC6C1: 1968, - 0xC6D7: 1969, - 0xC6E1: 1970, - 0xC6E2: 1971, - 0xC6E5: 1972, - 0xC6E9: 1973, - 0xC6F1: 1974, - 0xC6F3: 1975, - 0xC6F5: 1976, - 0xC6F7: 1977, - 0xC741: 1978, - 0xC745: 1979, - 0xC749: 1980, - 0xC751: 1981, - 0xC761: 1982, - 0xC762: 1983, - 0xC765: 1984, - 0xC769: 1985, - 0xC771: 1986, - 0xC773: 1987, - 0xC777: 1988, - 0xC7A1: 1989, - 0xC7A2: 1990, - 0xC7A5: 1991, - 0xC7A9: 1992, - 0xC7B1: 1993, - 0xC7B3: 1994, - 0xC7B5: 1995, - 0xC7B7: 1996, - 0xC861: 1997, - 0xC862: 1998, - 0xC865: 1999, - 0xC869: 2000, - 0xC86A: 2001, - 0xC871: 2002, - 0xC873: 2003, - 0xC875: 2004, - 0xC876: 2005, - 0xC877: 2006, - 0xC881: 2007, - 0xC882: 2008, - 0xC885: 2009, - 0xC889: 2010, - 0xC891: 2011, - 0xC893: 2012, - 0xC895: 2013, - 0xC896: 2014, - 0xC897: 2015, - 0xC8A1: 2016, - 0xC8B7: 2017, - 0xC8E1: 2018, - 0xC8E2: 2019, - 0xC8E5: 2020, - 0xC8E9: 2021, - 0xC8EB: 2022, - 0xC8F1: 2023, - 0xC8F3: 2024, - 0xC8F5: 2025, - 0xC8F6: 2026, - 0xC8F7: 2027, - 0xC941: 2028, - 0xC942: 2029, - 0xC945: 2030, - 0xC949: 2031, - 0xC951: 2032, - 0xC953: 2033, - 0xC955: 2034, - 0xC957: 2035, - 0xC961: 2036, - 0xC965: 2037, - 0xC976: 2038, - 0xC981: 2039, - 0xC985: 2040, - 0xC9A1: 2041, - 0xC9A2: 2042, - 0xC9A5: 2043, - 0xC9A9: 2044, - 0xC9B1: 2045, - 0xC9B3: 2046, - 0xC9B5: 2047, - 0xC9B7: 2048, - 0xC9BC: 2049, - 0xC9C1: 2050, - 0xC9C5: 2051, - 0xC9E1: 2052, - 0xCA41: 2053, - 0xCA45: 2054, - 0xCA55: 2055, - 0xCA57: 2056, - 0xCA61: 2057, - 0xCA81: 2058, - 0xCA82: 2059, - 0xCA85: 2060, - 0xCA89: 2061, - 0xCA91: 2062, - 0xCA93: 2063, - 0xCA95: 2064, - 0xCA97: 2065, - 0xCAA1: 2066, - 0xCAB6: 2067, - 0xCAC1: 2068, - 0xCAE1: 2069, - 0xCAE2: 2070, - 0xCAE5: 2071, - 0xCAE9: 2072, - 0xCAF1: 2073, - 0xCAF3: 2074, - 0xCAF7: 2075, - 0xCB41: 2076, - 0xCB45: 2077, - 0xCB49: 2078, - 0xCB51: 2079, - 0xCB57: 2080, - 0xCB61: 2081, - 0xCB62: 2082, - 0xCB65: 2083, - 0xCB68: 2084, - 0xCB69: 2085, - 0xCB6B: 2086, - 0xCB71: 2087, - 0xCB73: 2088, - 0xCB75: 2089, - 0xCB81: 2090, - 0xCB85: 2091, - 0xCB89: 2092, - 0xCB91: 2093, - 0xCB93: 2094, - 0xCBA1: 2095, - 0xCBA2: 2096, - 0xCBA5: 2097, - 0xCBA9: 2098, - 0xCBB1: 2099, - 0xCBB3: 2100, - 0xCBB5: 2101, - 0xCBB7: 2102, - 0xCC61: 2103, - 0xCC62: 2104, - 0xCC63: 2105, - 0xCC65: 2106, - 0xCC69: 2107, - 0xCC6B: 2108, - 0xCC71: 2109, - 0xCC73: 2110, - 0xCC75: 2111, - 0xCC76: 2112, - 0xCC77: 2113, - 0xCC7B: 2114, - 0xCC81: 2115, - 0xCC82: 2116, - 0xCC85: 2117, - 0xCC89: 2118, - 0xCC91: 2119, - 0xCC93: 2120, - 0xCC95: 2121, - 0xCC96: 2122, - 0xCC97: 2123, - 0xCCA1: 2124, - 0xCCA2: 2125, - 0xCCE1: 2126, - 0xCCE2: 2127, - 0xCCE5: 2128, - 0xCCE9: 2129, - 0xCCF1: 2130, - 0xCCF3: 2131, - 0xCCF5: 2132, - 0xCCF6: 2133, - 0xCCF7: 2134, - 0xCD41: 2135, - 0xCD42: 2136, - 0xCD45: 2137, - 0xCD49: 2138, - 0xCD51: 2139, - 0xCD53: 2140, - 0xCD55: 2141, - 0xCD57: 2142, - 0xCD61: 2143, - 0xCD65: 2144, - 0xCD69: 2145, - 0xCD71: 2146, - 0xCD73: 2147, - 0xCD76: 2148, - 0xCD77: 2149, - 0xCD81: 2150, - 0xCD89: 2151, - 0xCD93: 2152, - 0xCD95: 2153, - 0xCDA1: 2154, - 0xCDA2: 2155, - 0xCDA5: 2156, - 0xCDA9: 2157, - 0xCDB1: 2158, - 0xCDB3: 2159, - 0xCDB5: 2160, - 0xCDB7: 2161, - 0xCDC1: 2162, - 0xCDD7: 2163, - 0xCE41: 2164, - 0xCE45: 2165, - 0xCE61: 2166, - 0xCE65: 2167, - 0xCE69: 2168, - 0xCE73: 2169, - 0xCE75: 2170, - 0xCE81: 2171, - 0xCE82: 2172, - 0xCE85: 2173, - 0xCE88: 2174, - 0xCE89: 2175, - 0xCE8B: 2176, - 0xCE91: 2177, - 0xCE93: 2178, - 0xCE95: 2179, - 0xCE97: 2180, - 0xCEA1: 2181, - 0xCEB7: 2182, - 0xCEE1: 2183, - 0xCEE5: 2184, - 0xCEE9: 2185, - 0xCEF1: 2186, - 0xCEF5: 2187, - 0xCF41: 2188, - 0xCF45: 2189, - 0xCF49: 2190, - 0xCF51: 2191, - 0xCF55: 2192, - 0xCF57: 2193, - 0xCF61: 2194, - 0xCF65: 2195, - 0xCF69: 2196, - 0xCF71: 2197, - 0xCF73: 2198, - 0xCF75: 2199, - 0xCFA1: 2200, - 0xCFA2: 2201, - 0xCFA5: 2202, - 0xCFA9: 2203, - 0xCFB1: 2204, - 0xCFB3: 2205, - 0xCFB5: 2206, - 0xCFB7: 2207, - 0xD061: 2208, - 0xD062: 2209, - 0xD065: 2210, - 0xD069: 2211, - 0xD06E: 2212, - 0xD071: 2213, - 0xD073: 2214, - 0xD075: 2215, - 0xD077: 2216, - 0xD081: 2217, - 0xD082: 2218, - 0xD085: 2219, - 0xD089: 2220, - 0xD091: 2221, - 0xD093: 2222, - 0xD095: 2223, - 0xD096: 2224, - 0xD097: 2225, - 0xD0A1: 2226, - 0xD0B7: 2227, - 0xD0E1: 2228, - 0xD0E2: 2229, - 0xD0E5: 2230, - 0xD0E9: 2231, - 0xD0EB: 2232, - 0xD0F1: 2233, - 0xD0F3: 2234, - 0xD0F5: 2235, - 0xD0F7: 2236, - 0xD141: 2237, - 0xD142: 2238, - 0xD145: 2239, - 0xD149: 2240, - 0xD151: 2241, - 0xD153: 2242, - 0xD155: 2243, - 0xD157: 2244, - 0xD161: 2245, - 0xD162: 2246, - 0xD165: 2247, - 0xD169: 2248, - 0xD171: 2249, - 0xD173: 2250, - 0xD175: 2251, - 0xD176: 2252, - 0xD177: 2253, - 0xD181: 2254, - 0xD185: 2255, - 0xD189: 2256, - 0xD193: 2257, - 0xD1A1: 2258, - 0xD1A2: 2259, - 0xD1A5: 2260, - 0xD1A9: 2261, - 0xD1AE: 2262, - 0xD1B1: 2263, - 0xD1B3: 2264, - 0xD1B5: 2265, - 0xD1B7: 2266, - 0xD1BB: 2267, - 0xD1C1: 2268, - 0xD1C2: 2269, - 0xD1C5: 2270, - 0xD1C9: 2271, - 0xD1D5: 2272, - 0xD1D7: 2273, - 0xD1E1: 2274, - 0xD1E2: 2275, - 0xD1E5: 2276, - 0xD1F5: 2277, - 0xD1F7: 2278, - 0xD241: 2279, - 0xD242: 2280, - 0xD245: 2281, - 0xD249: 2282, - 0xD253: 2283, - 0xD255: 2284, - 0xD257: 2285, - 0xD261: 2286, - 0xD265: 2287, - 0xD269: 2288, - 0xD273: 2289, - 0xD275: 2290, - 0xD281: 2291, - 0xD282: 2292, - 0xD285: 2293, - 0xD289: 2294, - 0xD28E: 2295, - 0xD291: 2296, - 0xD295: 2297, - 0xD297: 2298, - 0xD2A1: 2299, - 0xD2A5: 2300, - 0xD2A9: 2301, - 0xD2B1: 2302, - 0xD2B7: 2303, - 0xD2C1: 2304, - 0xD2C2: 2305, - 0xD2C5: 2306, - 0xD2C9: 2307, - 0xD2D7: 2308, - 0xD2E1: 2309, - 0xD2E2: 2310, - 0xD2E5: 2311, - 0xD2E9: 2312, - 0xD2F1: 2313, - 0xD2F3: 2314, - 0xD2F5: 2315, - 0xD2F7: 2316, - 0xD341: 2317, - 0xD342: 2318, - 0xD345: 2319, - 0xD349: 2320, - 0xD351: 2321, - 0xD355: 2322, - 0xD357: 2323, - 0xD361: 2324, - 0xD362: 2325, - 0xD365: 2326, - 0xD367: 2327, - 0xD368: 2328, - 0xD369: 2329, - 0xD36A: 2330, - 0xD371: 2331, - 0xD373: 2332, - 0xD375: 2333, - 0xD377: 2334, - 0xD37B: 2335, - 0xD381: 2336, - 0xD385: 2337, - 0xD389: 2338, - 0xD391: 2339, - 0xD393: 2340, - 0xD397: 2341, - 0xD3A1: 2342, - 0xD3A2: 2343, - 0xD3A5: 2344, - 0xD3A9: 2345, - 0xD3B1: 2346, - 0xD3B3: 2347, - 0xD3B5: 2348, - 0xD3B7: 2349, -} diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/johabprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/johabprober.py deleted file mode 100644 index d7364ba..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/johabprober.py +++ /dev/null @@ -1,47 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .chardistribution import JOHABDistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import JOHAB_SM_MODEL - - -class JOHABProber(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(JOHAB_SM_MODEL) - self.distribution_analyzer = JOHABDistributionAnalysis() - self.reset() - - @property - def charset_name(self) -> str: - return "Johab" - - @property - def language(self) -> str: - return "Korean" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/jpcntx.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/jpcntx.py deleted file mode 100644 index 2f53bdd..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/jpcntx.py +++ /dev/null @@ -1,238 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Communicator client code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import List, Tuple, Union - -# This is hiragana 2-char sequence table, the number in each cell represents its frequency category -# fmt: off -jp2_char_context = ( - (0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1), - (2, 4, 0, 4, 0, 3, 0, 4, 0, 3, 4, 4, 4, 2, 4, 3, 3, 4, 3, 2, 3, 3, 4, 2, 3, 3, 3, 2, 4, 1, 4, 3, 3, 1, 5, 4, 3, 4, 3, 4, 3, 5, 3, 0, 3, 5, 4, 2, 0, 3, 1, 0, 3, 3, 0, 3, 3, 0, 1, 1, 0, 4, 3, 0, 3, 3, 0, 4, 0, 2, 0, 3, 5, 5, 5, 5, 4, 0, 4, 1, 0, 3, 4), - (0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2), - (0, 4, 0, 5, 0, 5, 0, 4, 0, 4, 5, 4, 4, 3, 5, 3, 5, 1, 5, 3, 4, 3, 4, 4, 3, 4, 3, 3, 4, 3, 5, 4, 4, 3, 5, 5, 3, 5, 5, 5, 3, 5, 5, 3, 4, 5, 5, 3, 1, 3, 2, 0, 3, 4, 0, 4, 2, 0, 4, 2, 1, 5, 3, 2, 3, 5, 0, 4, 0, 2, 0, 5, 4, 4, 5, 4, 5, 0, 4, 0, 0, 4, 4), - (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), - (0, 3, 0, 4, 0, 3, 0, 3, 0, 4, 5, 4, 3, 3, 3, 3, 4, 3, 5, 4, 4, 3, 5, 4, 4, 3, 4, 3, 4, 4, 4, 4, 5, 3, 4, 4, 3, 4, 5, 5, 4, 5, 5, 1, 4, 5, 4, 3, 0, 3, 3, 1, 3, 3, 0, 4, 4, 0, 3, 3, 1, 5, 3, 3, 3, 5, 0, 4, 0, 3, 0, 4, 4, 3, 4, 3, 3, 0, 4, 1, 1, 3, 4), - (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), - (0, 4, 0, 3, 0, 3, 0, 4, 0, 3, 4, 4, 3, 2, 2, 1, 2, 1, 3, 1, 3, 3, 3, 3, 3, 4, 3, 1, 3, 3, 5, 3, 3, 0, 4, 3, 0, 5, 4, 3, 3, 5, 4, 4, 3, 4, 4, 5, 0, 1, 2, 0, 1, 2, 0, 2, 2, 0, 1, 0, 0, 5, 2, 2, 1, 4, 0, 3, 0, 1, 0, 4, 4, 3, 5, 4, 3, 0, 2, 1, 0, 4, 3), - (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), - (0, 3, 0, 5, 0, 4, 0, 2, 1, 4, 4, 2, 4, 1, 4, 2, 4, 2, 4, 3, 3, 3, 4, 3, 3, 3, 3, 1, 4, 2, 3, 3, 3, 1, 4, 4, 1, 1, 1, 4, 3, 3, 2, 0, 2, 4, 3, 2, 0, 3, 3, 0, 3, 1, 1, 0, 0, 0, 3, 3, 0, 4, 2, 2, 3, 4, 0, 4, 0, 3, 0, 4, 4, 5, 3, 4, 4, 0, 3, 0, 0, 1, 4), - (1, 4, 0, 4, 0, 4, 0, 4, 0, 3, 5, 4, 4, 3, 4, 3, 5, 4, 3, 3, 4, 3, 5, 4, 4, 4, 4, 3, 4, 2, 4, 3, 3, 1, 5, 4, 3, 2, 4, 5, 4, 5, 5, 4, 4, 5, 4, 4, 0, 3, 2, 2, 3, 3, 0, 4, 3, 1, 3, 2, 1, 4, 3, 3, 4, 5, 0, 3, 0, 2, 0, 4, 5, 5, 4, 5, 4, 0, 4, 0, 0, 5, 4), - (0, 5, 0, 5, 0, 4, 0, 3, 0, 4, 4, 3, 4, 3, 3, 3, 4, 0, 4, 4, 4, 3, 4, 3, 4, 3, 3, 1, 4, 2, 4, 3, 4, 0, 5, 4, 1, 4, 5, 4, 4, 5, 3, 2, 4, 3, 4, 3, 2, 4, 1, 3, 3, 3, 2, 3, 2, 0, 4, 3, 3, 4, 3, 3, 3, 4, 0, 4, 0, 3, 0, 4, 5, 4, 4, 4, 3, 0, 4, 1, 0, 1, 3), - (0, 3, 1, 4, 0, 3, 0, 2, 0, 3, 4, 4, 3, 1, 4, 2, 3, 3, 4, 3, 4, 3, 4, 3, 4, 4, 3, 2, 3, 1, 5, 4, 4, 1, 4, 4, 3, 5, 4, 4, 3, 5, 5, 4, 3, 4, 4, 3, 1, 2, 3, 1, 2, 2, 0, 3, 2, 0, 3, 1, 0, 5, 3, 3, 3, 4, 3, 3, 3, 3, 4, 4, 4, 4, 5, 4, 2, 0, 3, 3, 2, 4, 3), - (0, 2, 0, 3, 0, 1, 0, 1, 0, 0, 3, 2, 0, 0, 2, 0, 1, 0, 2, 1, 3, 3, 3, 1, 2, 3, 1, 0, 1, 0, 4, 2, 1, 1, 3, 3, 0, 4, 3, 3, 1, 4, 3, 3, 0, 3, 3, 2, 0, 0, 0, 0, 1, 0, 0, 2, 0, 0, 0, 0, 0, 4, 1, 0, 2, 3, 2, 2, 2, 1, 3, 3, 3, 4, 4, 3, 2, 0, 3, 1, 0, 3, 3), - (0, 4, 0, 4, 0, 3, 0, 3, 0, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 3, 4, 2, 4, 3, 4, 3, 3, 2, 4, 3, 4, 5, 4, 1, 4, 5, 3, 5, 4, 5, 3, 5, 4, 0, 3, 5, 5, 3, 1, 3, 3, 2, 2, 3, 0, 3, 4, 1, 3, 3, 2, 4, 3, 3, 3, 4, 0, 4, 0, 3, 0, 4, 5, 4, 4, 5, 3, 0, 4, 1, 0, 3, 4), - (0, 2, 0, 3, 0, 3, 0, 0, 0, 2, 2, 2, 1, 0, 1, 0, 0, 0, 3, 0, 3, 0, 3, 0, 1, 3, 1, 0, 3, 1, 3, 3, 3, 1, 3, 3, 3, 0, 1, 3, 1, 3, 4, 0, 0, 3, 1, 1, 0, 3, 2, 0, 0, 0, 0, 1, 3, 0, 1, 0, 0, 3, 3, 2, 0, 3, 0, 0, 0, 0, 0, 3, 4, 3, 4, 3, 3, 0, 3, 0, 0, 2, 3), - (2, 3, 0, 3, 0, 2, 0, 1, 0, 3, 3, 4, 3, 1, 3, 1, 1, 1, 3, 1, 4, 3, 4, 3, 3, 3, 0, 0, 3, 1, 5, 4, 3, 1, 4, 3, 2, 5, 5, 4, 4, 4, 4, 3, 3, 4, 4, 4, 0, 2, 1, 1, 3, 2, 0, 1, 2, 0, 0, 1, 0, 4, 1, 3, 3, 3, 0, 3, 0, 1, 0, 4, 4, 4, 5, 5, 3, 0, 2, 0, 0, 4, 4), - (0, 2, 0, 1, 0, 3, 1, 3, 0, 2, 3, 3, 3, 0, 3, 1, 0, 0, 3, 0, 3, 2, 3, 1, 3, 2, 1, 1, 0, 0, 4, 2, 1, 0, 2, 3, 1, 4, 3, 2, 0, 4, 4, 3, 1, 3, 1, 3, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 4, 1, 1, 1, 2, 0, 3, 0, 0, 0, 3, 4, 2, 4, 3, 2, 0, 1, 0, 0, 3, 3), - (0, 1, 0, 4, 0, 5, 0, 4, 0, 2, 4, 4, 2, 3, 3, 2, 3, 3, 5, 3, 3, 3, 4, 3, 4, 2, 3, 0, 4, 3, 3, 3, 4, 1, 4, 3, 2, 1, 5, 5, 3, 4, 5, 1, 3, 5, 4, 2, 0, 3, 3, 0, 1, 3, 0, 4, 2, 0, 1, 3, 1, 4, 3, 3, 3, 3, 0, 3, 0, 1, 0, 3, 4, 4, 4, 5, 5, 0, 3, 0, 1, 4, 5), - (0, 2, 0, 3, 0, 3, 0, 0, 0, 2, 3, 1, 3, 0, 4, 0, 1, 1, 3, 0, 3, 4, 3, 2, 3, 1, 0, 3, 3, 2, 3, 1, 3, 0, 2, 3, 0, 2, 1, 4, 1, 2, 2, 0, 0, 3, 3, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 2, 2, 0, 3, 2, 1, 3, 3, 0, 2, 0, 2, 0, 0, 3, 3, 1, 2, 4, 0, 3, 0, 2, 2, 3), - (2, 4, 0, 5, 0, 4, 0, 4, 0, 2, 4, 4, 4, 3, 4, 3, 3, 3, 1, 2, 4, 3, 4, 3, 4, 4, 5, 0, 3, 3, 3, 3, 2, 0, 4, 3, 1, 4, 3, 4, 1, 4, 4, 3, 3, 4, 4, 3, 1, 2, 3, 0, 4, 2, 0, 4, 1, 0, 3, 3, 0, 4, 3, 3, 3, 4, 0, 4, 0, 2, 0, 3, 5, 3, 4, 5, 2, 0, 3, 0, 0, 4, 5), - (0, 3, 0, 4, 0, 1, 0, 1, 0, 1, 3, 2, 2, 1, 3, 0, 3, 0, 2, 0, 2, 0, 3, 0, 2, 0, 0, 0, 1, 0, 1, 1, 0, 0, 3, 1, 0, 0, 0, 4, 0, 3, 1, 0, 2, 1, 3, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 4, 2, 2, 3, 1, 0, 3, 0, 0, 0, 1, 4, 4, 4, 3, 0, 0, 4, 0, 0, 1, 4), - (1, 4, 1, 5, 0, 3, 0, 3, 0, 4, 5, 4, 4, 3, 5, 3, 3, 4, 4, 3, 4, 1, 3, 3, 3, 3, 2, 1, 4, 1, 5, 4, 3, 1, 4, 4, 3, 5, 4, 4, 3, 5, 4, 3, 3, 4, 4, 4, 0, 3, 3, 1, 2, 3, 0, 3, 1, 0, 3, 3, 0, 5, 4, 4, 4, 4, 4, 4, 3, 3, 5, 4, 4, 3, 3, 5, 4, 0, 3, 2, 0, 4, 4), - (0, 2, 0, 3, 0, 1, 0, 0, 0, 1, 3, 3, 3, 2, 4, 1, 3, 0, 3, 1, 3, 0, 2, 2, 1, 1, 0, 0, 2, 0, 4, 3, 1, 0, 4, 3, 0, 4, 4, 4, 1, 4, 3, 1, 1, 3, 3, 1, 0, 2, 0, 0, 1, 3, 0, 0, 0, 0, 2, 0, 0, 4, 3, 2, 4, 3, 5, 4, 3, 3, 3, 4, 3, 3, 4, 3, 3, 0, 2, 1, 0, 3, 3), - (0, 2, 0, 4, 0, 3, 0, 2, 0, 2, 5, 5, 3, 4, 4, 4, 4, 1, 4, 3, 3, 0, 4, 3, 4, 3, 1, 3, 3, 2, 4, 3, 0, 3, 4, 3, 0, 3, 4, 4, 2, 4, 4, 0, 4, 5, 3, 3, 2, 2, 1, 1, 1, 2, 0, 1, 5, 0, 3, 3, 2, 4, 3, 3, 3, 4, 0, 3, 0, 2, 0, 4, 4, 3, 5, 5, 0, 0, 3, 0, 2, 3, 3), - (0, 3, 0, 4, 0, 3, 0, 1, 0, 3, 4, 3, 3, 1, 3, 3, 3, 0, 3, 1, 3, 0, 4, 3, 3, 1, 1, 0, 3, 0, 3, 3, 0, 0, 4, 4, 0, 1, 5, 4, 3, 3, 5, 0, 3, 3, 4, 3, 0, 2, 0, 1, 1, 1, 0, 1, 3, 0, 1, 2, 1, 3, 3, 2, 3, 3, 0, 3, 0, 1, 0, 1, 3, 3, 4, 4, 1, 0, 1, 2, 2, 1, 3), - (0, 1, 0, 4, 0, 4, 0, 3, 0, 1, 3, 3, 3, 2, 3, 1, 1, 0, 3, 0, 3, 3, 4, 3, 2, 4, 2, 0, 1, 0, 4, 3, 2, 0, 4, 3, 0, 5, 3, 3, 2, 4, 4, 4, 3, 3, 3, 4, 0, 1, 3, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 4, 2, 3, 3, 3, 0, 3, 0, 0, 0, 4, 4, 4, 5, 3, 2, 0, 3, 3, 0, 3, 5), - (0, 2, 0, 3, 0, 0, 0, 3, 0, 1, 3, 0, 2, 0, 0, 0, 1, 0, 3, 1, 1, 3, 3, 0, 0, 3, 0, 0, 3, 0, 2, 3, 1, 0, 3, 1, 0, 3, 3, 2, 0, 4, 2, 2, 0, 2, 0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 1, 2, 0, 1, 0, 1, 0, 0, 0, 1, 3, 1, 2, 0, 0, 0, 1, 0, 0, 1, 4), - (0, 3, 0, 3, 0, 5, 0, 1, 0, 2, 4, 3, 1, 3, 3, 2, 1, 1, 5, 2, 1, 0, 5, 1, 2, 0, 0, 0, 3, 3, 2, 2, 3, 2, 4, 3, 0, 0, 3, 3, 1, 3, 3, 0, 2, 5, 3, 4, 0, 3, 3, 0, 1, 2, 0, 2, 2, 0, 3, 2, 0, 2, 2, 3, 3, 3, 0, 2, 0, 1, 0, 3, 4, 4, 2, 5, 4, 0, 3, 0, 0, 3, 5), - (0, 3, 0, 3, 0, 3, 0, 1, 0, 3, 3, 3, 3, 0, 3, 0, 2, 0, 2, 1, 1, 0, 2, 0, 1, 0, 0, 0, 2, 1, 0, 0, 1, 0, 3, 2, 0, 0, 3, 3, 1, 2, 3, 1, 0, 3, 3, 0, 0, 1, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 2, 3, 1, 2, 3, 0, 3, 0, 1, 0, 3, 2, 1, 0, 4, 3, 0, 1, 1, 0, 3, 3), - (0, 4, 0, 5, 0, 3, 0, 3, 0, 4, 5, 5, 4, 3, 5, 3, 4, 3, 5, 3, 3, 2, 5, 3, 4, 4, 4, 3, 4, 3, 4, 5, 5, 3, 4, 4, 3, 4, 4, 5, 4, 4, 4, 3, 4, 5, 5, 4, 2, 3, 4, 2, 3, 4, 0, 3, 3, 1, 4, 3, 2, 4, 3, 3, 5, 5, 0, 3, 0, 3, 0, 5, 5, 5, 5, 4, 4, 0, 4, 0, 1, 4, 4), - (0, 4, 0, 4, 0, 3, 0, 3, 0, 3, 5, 4, 4, 2, 3, 2, 5, 1, 3, 2, 5, 1, 4, 2, 3, 2, 3, 3, 4, 3, 3, 3, 3, 2, 5, 4, 1, 3, 3, 5, 3, 4, 4, 0, 4, 4, 3, 1, 1, 3, 1, 0, 2, 3, 0, 2, 3, 0, 3, 0, 0, 4, 3, 1, 3, 4, 0, 3, 0, 2, 0, 4, 4, 4, 3, 4, 5, 0, 4, 0, 0, 3, 4), - (0, 3, 0, 3, 0, 3, 1, 2, 0, 3, 4, 4, 3, 3, 3, 0, 2, 2, 4, 3, 3, 1, 3, 3, 3, 1, 1, 0, 3, 1, 4, 3, 2, 3, 4, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 4, 4, 3, 1, 3, 3, 1, 3, 3, 0, 4, 1, 0, 2, 2, 1, 4, 3, 2, 3, 3, 5, 4, 3, 3, 5, 4, 4, 3, 3, 0, 4, 0, 3, 2, 2, 4, 4), - (0, 2, 0, 1, 0, 0, 0, 0, 0, 1, 2, 1, 3, 0, 0, 0, 0, 0, 2, 0, 1, 2, 1, 0, 0, 1, 0, 0, 0, 0, 3, 0, 0, 1, 0, 1, 1, 3, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 2, 2, 0, 3, 4, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1), - (0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 4, 0, 4, 1, 4, 0, 3, 0, 4, 0, 3, 0, 4, 0, 3, 0, 3, 0, 4, 1, 5, 1, 4, 0, 0, 3, 0, 5, 0, 5, 2, 0, 1, 0, 0, 0, 2, 1, 4, 0, 1, 3, 0, 0, 3, 0, 0, 3, 1, 1, 4, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0), - (1, 4, 0, 5, 0, 3, 0, 2, 0, 3, 5, 4, 4, 3, 4, 3, 5, 3, 4, 3, 3, 0, 4, 3, 3, 3, 3, 3, 3, 2, 4, 4, 3, 1, 3, 4, 4, 5, 4, 4, 3, 4, 4, 1, 3, 5, 4, 3, 3, 3, 1, 2, 2, 3, 3, 1, 3, 1, 3, 3, 3, 5, 3, 3, 4, 5, 0, 3, 0, 3, 0, 3, 4, 3, 4, 4, 3, 0, 3, 0, 2, 4, 3), - (0, 1, 0, 4, 0, 0, 0, 0, 0, 1, 4, 0, 4, 1, 4, 2, 4, 0, 3, 0, 1, 0, 1, 0, 0, 0, 0, 0, 2, 0, 3, 1, 1, 1, 0, 3, 0, 0, 0, 1, 2, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 3, 0, 0, 0, 0, 3, 2, 0, 2, 2, 0, 1, 0, 0, 0, 2, 3, 2, 3, 3, 0, 0, 0, 0, 2, 1, 0), - (0, 5, 1, 5, 0, 3, 0, 3, 0, 5, 4, 4, 5, 1, 5, 3, 3, 0, 4, 3, 4, 3, 5, 3, 4, 3, 3, 2, 4, 3, 4, 3, 3, 0, 3, 3, 1, 4, 4, 3, 4, 4, 4, 3, 4, 5, 5, 3, 2, 3, 1, 1, 3, 3, 1, 3, 1, 1, 3, 3, 2, 4, 5, 3, 3, 5, 0, 4, 0, 3, 0, 4, 4, 3, 5, 3, 3, 0, 3, 4, 0, 4, 3), - (0, 5, 0, 5, 0, 3, 0, 2, 0, 4, 4, 3, 5, 2, 4, 3, 3, 3, 4, 4, 4, 3, 5, 3, 5, 3, 3, 1, 4, 0, 4, 3, 3, 0, 3, 3, 0, 4, 4, 4, 4, 5, 4, 3, 3, 5, 5, 3, 2, 3, 1, 2, 3, 2, 0, 1, 0, 0, 3, 2, 2, 4, 4, 3, 1, 5, 0, 4, 0, 3, 0, 4, 3, 1, 3, 2, 1, 0, 3, 3, 0, 3, 3), - (0, 4, 0, 5, 0, 5, 0, 4, 0, 4, 5, 5, 5, 3, 4, 3, 3, 2, 5, 4, 4, 3, 5, 3, 5, 3, 4, 0, 4, 3, 4, 4, 3, 2, 4, 4, 3, 4, 5, 4, 4, 5, 5, 0, 3, 5, 5, 4, 1, 3, 3, 2, 3, 3, 1, 3, 1, 0, 4, 3, 1, 4, 4, 3, 4, 5, 0, 4, 0, 2, 0, 4, 3, 4, 4, 3, 3, 0, 4, 0, 0, 5, 5), - (0, 4, 0, 4, 0, 5, 0, 1, 1, 3, 3, 4, 4, 3, 4, 1, 3, 0, 5, 1, 3, 0, 3, 1, 3, 1, 1, 0, 3, 0, 3, 3, 4, 0, 4, 3, 0, 4, 4, 4, 3, 4, 4, 0, 3, 5, 4, 1, 0, 3, 0, 0, 2, 3, 0, 3, 1, 0, 3, 1, 0, 3, 2, 1, 3, 5, 0, 3, 0, 1, 0, 3, 2, 3, 3, 4, 4, 0, 2, 2, 0, 4, 4), - (2, 4, 0, 5, 0, 4, 0, 3, 0, 4, 5, 5, 4, 3, 5, 3, 5, 3, 5, 3, 5, 2, 5, 3, 4, 3, 3, 4, 3, 4, 5, 3, 2, 1, 5, 4, 3, 2, 3, 4, 5, 3, 4, 1, 2, 5, 4, 3, 0, 3, 3, 0, 3, 2, 0, 2, 3, 0, 4, 1, 0, 3, 4, 3, 3, 5, 0, 3, 0, 1, 0, 4, 5, 5, 5, 4, 3, 0, 4, 2, 0, 3, 5), - (0, 5, 0, 4, 0, 4, 0, 2, 0, 5, 4, 3, 4, 3, 4, 3, 3, 3, 4, 3, 4, 2, 5, 3, 5, 3, 4, 1, 4, 3, 4, 4, 4, 0, 3, 5, 0, 4, 4, 4, 4, 5, 3, 1, 3, 4, 5, 3, 3, 3, 3, 3, 3, 3, 0, 2, 2, 0, 3, 3, 2, 4, 3, 3, 3, 5, 3, 4, 1, 3, 3, 5, 3, 2, 0, 0, 0, 0, 4, 3, 1, 3, 3), - (0, 1, 0, 3, 0, 3, 0, 1, 0, 1, 3, 3, 3, 2, 3, 3, 3, 0, 3, 0, 0, 0, 3, 1, 3, 0, 0, 0, 2, 2, 2, 3, 0, 0, 3, 2, 0, 1, 2, 4, 1, 3, 3, 0, 0, 3, 3, 3, 0, 1, 0, 0, 2, 1, 0, 0, 3, 0, 3, 1, 0, 3, 0, 0, 1, 3, 0, 2, 0, 1, 0, 3, 3, 1, 3, 3, 0, 0, 1, 1, 0, 3, 3), - (0, 2, 0, 3, 0, 2, 1, 4, 0, 2, 2, 3, 1, 1, 3, 1, 1, 0, 2, 0, 3, 1, 2, 3, 1, 3, 0, 0, 1, 0, 4, 3, 2, 3, 3, 3, 1, 4, 2, 3, 3, 3, 3, 1, 0, 3, 1, 4, 0, 1, 1, 0, 1, 2, 0, 1, 1, 0, 1, 1, 0, 3, 1, 3, 2, 2, 0, 1, 0, 0, 0, 2, 3, 3, 3, 1, 0, 0, 0, 0, 0, 2, 3), - (0, 5, 0, 4, 0, 5, 0, 2, 0, 4, 5, 5, 3, 3, 4, 3, 3, 1, 5, 4, 4, 2, 4, 4, 4, 3, 4, 2, 4, 3, 5, 5, 4, 3, 3, 4, 3, 3, 5, 5, 4, 5, 5, 1, 3, 4, 5, 3, 1, 4, 3, 1, 3, 3, 0, 3, 3, 1, 4, 3, 1, 4, 5, 3, 3, 5, 0, 4, 0, 3, 0, 5, 3, 3, 1, 4, 3, 0, 4, 0, 1, 5, 3), - (0, 5, 0, 5, 0, 4, 0, 2, 0, 4, 4, 3, 4, 3, 3, 3, 3, 3, 5, 4, 4, 4, 4, 4, 4, 5, 3, 3, 5, 2, 4, 4, 4, 3, 4, 4, 3, 3, 4, 4, 5, 5, 3, 3, 4, 3, 4, 3, 3, 4, 3, 3, 3, 3, 1, 2, 2, 1, 4, 3, 3, 5, 4, 4, 3, 4, 0, 4, 0, 3, 0, 4, 4, 4, 4, 4, 1, 0, 4, 2, 0, 2, 4), - (0, 4, 0, 4, 0, 3, 0, 1, 0, 3, 5, 2, 3, 0, 3, 0, 2, 1, 4, 2, 3, 3, 4, 1, 4, 3, 3, 2, 4, 1, 3, 3, 3, 0, 3, 3, 0, 0, 3, 3, 3, 5, 3, 3, 3, 3, 3, 2, 0, 2, 0, 0, 2, 0, 0, 2, 0, 0, 1, 0, 0, 3, 1, 2, 2, 3, 0, 3, 0, 2, 0, 4, 4, 3, 3, 4, 1, 0, 3, 0, 0, 2, 4), - (0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 2, 0, 0, 0, 0, 0, 1, 0, 2, 0, 1, 0, 0, 0, 0, 0, 3, 1, 3, 0, 3, 2, 0, 0, 0, 1, 0, 3, 2, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 4, 0, 2, 0, 0, 0, 0, 0, 0, 2), - (0, 2, 1, 3, 0, 2, 0, 2, 0, 3, 3, 3, 3, 1, 3, 1, 3, 3, 3, 3, 3, 3, 4, 2, 2, 1, 2, 1, 4, 0, 4, 3, 1, 3, 3, 3, 2, 4, 3, 5, 4, 3, 3, 3, 3, 3, 3, 3, 0, 1, 3, 0, 2, 0, 0, 1, 0, 0, 1, 0, 0, 4, 2, 0, 2, 3, 0, 3, 3, 0, 3, 3, 4, 2, 3, 1, 4, 0, 1, 2, 0, 2, 3), - (0, 3, 0, 3, 0, 1, 0, 3, 0, 2, 3, 3, 3, 0, 3, 1, 2, 0, 3, 3, 2, 3, 3, 2, 3, 2, 3, 1, 3, 0, 4, 3, 2, 0, 3, 3, 1, 4, 3, 3, 2, 3, 4, 3, 1, 3, 3, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 4, 1, 1, 0, 3, 0, 3, 1, 0, 2, 3, 3, 3, 3, 3, 1, 0, 0, 2, 0, 3, 3), - (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 2, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 3, 0, 3, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 2, 0, 2, 3, 0, 0, 0, 0, 0, 0, 0, 0, 3), - (0, 2, 0, 3, 1, 3, 0, 3, 0, 2, 3, 3, 3, 1, 3, 1, 3, 1, 3, 1, 3, 3, 3, 1, 3, 0, 2, 3, 1, 1, 4, 3, 3, 2, 3, 3, 1, 2, 2, 4, 1, 3, 3, 0, 1, 4, 2, 3, 0, 1, 3, 0, 3, 0, 0, 1, 3, 0, 2, 0, 0, 3, 3, 2, 1, 3, 0, 3, 0, 2, 0, 3, 4, 4, 4, 3, 1, 0, 3, 0, 0, 3, 3), - (0, 2, 0, 1, 0, 2, 0, 0, 0, 1, 3, 2, 2, 1, 3, 0, 1, 1, 3, 0, 3, 2, 3, 1, 2, 0, 2, 0, 1, 1, 3, 3, 3, 0, 3, 3, 1, 1, 2, 3, 2, 3, 3, 1, 2, 3, 2, 0, 0, 1, 0, 0, 0, 0, 0, 0, 3, 0, 1, 0, 0, 2, 1, 2, 1, 3, 0, 3, 0, 0, 0, 3, 4, 4, 4, 3, 2, 0, 2, 0, 0, 2, 4), - (0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 3, 1, 0, 0, 0, 0, 0, 0, 0, 3), - (0, 3, 0, 3, 0, 2, 0, 3, 0, 3, 3, 3, 2, 3, 2, 2, 2, 0, 3, 1, 3, 3, 3, 2, 3, 3, 0, 0, 3, 0, 3, 2, 2, 0, 2, 3, 1, 4, 3, 4, 3, 3, 2, 3, 1, 5, 4, 4, 0, 3, 1, 2, 1, 3, 0, 3, 1, 1, 2, 0, 2, 3, 1, 3, 1, 3, 0, 3, 0, 1, 0, 3, 3, 4, 4, 2, 1, 0, 2, 1, 0, 2, 4), - (0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 4, 2, 5, 1, 4, 0, 2, 0, 2, 1, 3, 1, 4, 0, 2, 1, 0, 0, 2, 1, 4, 1, 1, 0, 3, 3, 0, 5, 1, 3, 2, 3, 3, 1, 0, 3, 2, 3, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 4, 0, 1, 0, 3, 0, 2, 0, 1, 0, 3, 3, 3, 4, 3, 3, 0, 0, 0, 0, 2, 3), - (0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 2, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 1, 0, 0, 1, 0, 0, 0, 0, 0, 3), - (0, 1, 0, 3, 0, 4, 0, 3, 0, 2, 4, 3, 1, 0, 3, 2, 2, 1, 3, 1, 2, 2, 3, 1, 1, 1, 2, 1, 3, 0, 1, 2, 0, 1, 3, 2, 1, 3, 0, 5, 5, 1, 0, 0, 1, 3, 2, 1, 0, 3, 0, 0, 1, 0, 0, 0, 0, 0, 3, 4, 0, 1, 1, 1, 3, 2, 0, 2, 0, 1, 0, 2, 3, 3, 1, 2, 3, 0, 1, 0, 1, 0, 4), - (0, 0, 0, 1, 0, 3, 0, 3, 0, 2, 2, 1, 0, 0, 4, 0, 3, 0, 3, 1, 3, 0, 3, 0, 3, 0, 1, 0, 3, 0, 3, 1, 3, 0, 3, 3, 0, 0, 1, 2, 1, 1, 1, 0, 1, 2, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 1, 2, 0, 0, 2, 0, 0, 0, 0, 2, 3, 3, 3, 3, 0, 0, 0, 0, 1, 4), - (0, 0, 0, 3, 0, 3, 0, 0, 0, 0, 3, 1, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 0, 2, 0, 2, 3, 0, 0, 2, 2, 3, 1, 2, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 2, 0, 0, 0, 0, 2, 3), - (2, 4, 0, 5, 0, 5, 0, 4, 0, 3, 4, 3, 3, 3, 4, 3, 3, 3, 4, 3, 4, 4, 5, 4, 5, 5, 5, 2, 3, 0, 5, 5, 4, 1, 5, 4, 3, 1, 5, 4, 3, 4, 4, 3, 3, 4, 3, 3, 0, 3, 2, 0, 2, 3, 0, 3, 0, 0, 3, 3, 0, 5, 3, 2, 3, 3, 0, 3, 0, 3, 0, 3, 4, 5, 4, 5, 3, 0, 4, 3, 0, 3, 4), - (0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 3, 4, 3, 2, 3, 2, 3, 0, 4, 3, 3, 3, 3, 3, 3, 3, 3, 0, 3, 2, 4, 3, 3, 1, 3, 4, 3, 4, 4, 4, 3, 4, 4, 3, 2, 4, 4, 1, 0, 2, 0, 0, 1, 1, 0, 2, 0, 0, 3, 1, 0, 5, 3, 2, 1, 3, 0, 3, 0, 1, 2, 4, 3, 2, 4, 3, 3, 0, 3, 2, 0, 4, 4), - (0, 3, 0, 3, 0, 1, 0, 0, 0, 1, 4, 3, 3, 2, 3, 1, 3, 1, 4, 2, 3, 2, 4, 2, 3, 4, 3, 0, 2, 2, 3, 3, 3, 0, 3, 3, 3, 0, 3, 4, 1, 3, 3, 0, 3, 4, 3, 3, 0, 1, 1, 0, 1, 0, 0, 0, 4, 0, 3, 0, 0, 3, 1, 2, 1, 3, 0, 4, 0, 1, 0, 4, 3, 3, 4, 3, 3, 0, 2, 0, 0, 3, 3), - (0, 3, 0, 4, 0, 1, 0, 3, 0, 3, 4, 3, 3, 0, 3, 3, 3, 1, 3, 1, 3, 3, 4, 3, 3, 3, 0, 0, 3, 1, 5, 3, 3, 1, 3, 3, 2, 5, 4, 3, 3, 4, 5, 3, 2, 5, 3, 4, 0, 1, 0, 0, 0, 0, 0, 2, 0, 0, 1, 1, 0, 4, 2, 2, 1, 3, 0, 3, 0, 2, 0, 4, 4, 3, 5, 3, 2, 0, 1, 1, 0, 3, 4), - (0, 5, 0, 4, 0, 5, 0, 2, 0, 4, 4, 3, 3, 2, 3, 3, 3, 1, 4, 3, 4, 1, 5, 3, 4, 3, 4, 0, 4, 2, 4, 3, 4, 1, 5, 4, 0, 4, 4, 4, 4, 5, 4, 1, 3, 5, 4, 2, 1, 4, 1, 1, 3, 2, 0, 3, 1, 0, 3, 2, 1, 4, 3, 3, 3, 4, 0, 4, 0, 3, 0, 4, 4, 4, 3, 3, 3, 0, 4, 2, 0, 3, 4), - (1, 4, 0, 4, 0, 3, 0, 1, 0, 3, 3, 3, 1, 1, 3, 3, 2, 2, 3, 3, 1, 0, 3, 2, 2, 1, 2, 0, 3, 1, 2, 1, 2, 0, 3, 2, 0, 2, 2, 3, 3, 4, 3, 0, 3, 3, 1, 2, 0, 1, 1, 3, 1, 2, 0, 0, 3, 0, 1, 1, 0, 3, 2, 2, 3, 3, 0, 3, 0, 0, 0, 2, 3, 3, 4, 3, 3, 0, 1, 0, 0, 1, 4), - (0, 4, 0, 4, 0, 4, 0, 0, 0, 3, 4, 4, 3, 1, 4, 2, 3, 2, 3, 3, 3, 1, 4, 3, 4, 0, 3, 0, 4, 2, 3, 3, 2, 2, 5, 4, 2, 1, 3, 4, 3, 4, 3, 1, 3, 3, 4, 2, 0, 2, 1, 0, 3, 3, 0, 0, 2, 0, 3, 1, 0, 4, 4, 3, 4, 3, 0, 4, 0, 1, 0, 2, 4, 4, 4, 4, 4, 0, 3, 2, 0, 3, 3), - (0, 0, 0, 1, 0, 4, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 2, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 2), - (0, 2, 0, 3, 0, 4, 0, 4, 0, 1, 3, 3, 3, 0, 4, 0, 2, 1, 2, 1, 1, 1, 2, 0, 3, 1, 1, 0, 1, 0, 3, 1, 0, 0, 3, 3, 2, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 2, 0, 2, 2, 0, 3, 1, 0, 0, 1, 0, 1, 1, 0, 1, 2, 0, 3, 0, 0, 0, 0, 1, 0, 0, 3, 3, 4, 3, 1, 0, 1, 0, 3, 0, 2), - (0, 0, 0, 3, 0, 5, 0, 0, 0, 0, 1, 0, 2, 0, 3, 1, 0, 1, 3, 0, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 4, 0, 0, 0, 2, 3, 0, 1, 4, 1, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 3, 0, 0, 0, 0, 0, 3), - (0, 2, 0, 5, 0, 5, 0, 1, 0, 2, 4, 3, 3, 2, 5, 1, 3, 2, 3, 3, 3, 0, 4, 1, 2, 0, 3, 0, 4, 0, 2, 2, 1, 1, 5, 3, 0, 0, 1, 4, 2, 3, 2, 0, 3, 3, 3, 2, 0, 2, 4, 1, 1, 2, 0, 1, 1, 0, 3, 1, 0, 1, 3, 1, 2, 3, 0, 2, 0, 0, 0, 1, 3, 5, 4, 4, 4, 0, 3, 0, 0, 1, 3), - (0, 4, 0, 5, 0, 4, 0, 4, 0, 4, 5, 4, 3, 3, 4, 3, 3, 3, 4, 3, 4, 4, 5, 3, 4, 5, 4, 2, 4, 2, 3, 4, 3, 1, 4, 4, 1, 3, 5, 4, 4, 5, 5, 4, 4, 5, 5, 5, 2, 3, 3, 1, 4, 3, 1, 3, 3, 0, 3, 3, 1, 4, 3, 4, 4, 4, 0, 3, 0, 4, 0, 3, 3, 4, 4, 5, 0, 0, 4, 3, 0, 4, 5), - (0, 4, 0, 4, 0, 3, 0, 3, 0, 3, 4, 4, 4, 3, 3, 2, 4, 3, 4, 3, 4, 3, 5, 3, 4, 3, 2, 1, 4, 2, 4, 4, 3, 1, 3, 4, 2, 4, 5, 5, 3, 4, 5, 4, 1, 5, 4, 3, 0, 3, 2, 2, 3, 2, 1, 3, 1, 0, 3, 3, 3, 5, 3, 3, 3, 5, 4, 4, 2, 3, 3, 4, 3, 3, 3, 2, 1, 0, 3, 2, 1, 4, 3), - (0, 4, 0, 5, 0, 4, 0, 3, 0, 3, 5, 5, 3, 2, 4, 3, 4, 0, 5, 4, 4, 1, 4, 4, 4, 3, 3, 3, 4, 3, 5, 5, 2, 3, 3, 4, 1, 2, 5, 5, 3, 5, 5, 2, 3, 5, 5, 4, 0, 3, 2, 0, 3, 3, 1, 1, 5, 1, 4, 1, 0, 4, 3, 2, 3, 5, 0, 4, 0, 3, 0, 5, 4, 3, 4, 3, 0, 0, 4, 1, 0, 4, 4), - (1, 3, 0, 4, 0, 2, 0, 2, 0, 2, 5, 5, 3, 3, 3, 3, 3, 0, 4, 2, 3, 4, 4, 4, 3, 4, 0, 0, 3, 4, 5, 4, 3, 3, 3, 3, 2, 5, 5, 4, 5, 5, 5, 4, 3, 5, 5, 5, 1, 3, 1, 0, 1, 0, 0, 3, 2, 0, 4, 2, 0, 5, 2, 3, 2, 4, 1, 3, 0, 3, 0, 4, 5, 4, 5, 4, 3, 0, 4, 2, 0, 5, 4), - (0, 3, 0, 4, 0, 5, 0, 3, 0, 3, 4, 4, 3, 2, 3, 2, 3, 3, 3, 3, 3, 2, 4, 3, 3, 2, 2, 0, 3, 3, 3, 3, 3, 1, 3, 3, 3, 0, 4, 4, 3, 4, 4, 1, 1, 4, 4, 2, 0, 3, 1, 0, 1, 1, 0, 4, 1, 0, 2, 3, 1, 3, 3, 1, 3, 4, 0, 3, 0, 1, 0, 3, 1, 3, 0, 0, 1, 0, 2, 0, 0, 4, 4), - (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), - (0, 3, 0, 3, 0, 2, 0, 3, 0, 1, 5, 4, 3, 3, 3, 1, 4, 2, 1, 2, 3, 4, 4, 2, 4, 4, 5, 0, 3, 1, 4, 3, 4, 0, 4, 3, 3, 3, 2, 3, 2, 5, 3, 4, 3, 2, 2, 3, 0, 0, 3, 0, 2, 1, 0, 1, 2, 0, 0, 0, 0, 2, 1, 1, 3, 1, 0, 2, 0, 4, 0, 3, 4, 4, 4, 5, 2, 0, 2, 0, 0, 1, 3), - (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 4, 2, 1, 1, 0, 1, 0, 3, 2, 0, 0, 3, 1, 1, 1, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 1, 0, 0, 0, 2, 0, 0, 0, 1, 4, 0, 4, 2, 1, 0, 0, 0, 0, 0, 1), - (0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 3, 1, 0, 0, 0, 2, 0, 2, 1, 0, 0, 1, 2, 1, 0, 1, 1, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 3, 1, 0, 0, 0, 0, 0, 1, 0, 0, 2, 1, 0, 0, 0, 0, 0, 0, 0, 0, 2), - (0, 4, 0, 4, 0, 4, 0, 3, 0, 4, 4, 3, 4, 2, 4, 3, 2, 0, 4, 4, 4, 3, 5, 3, 5, 3, 3, 2, 4, 2, 4, 3, 4, 3, 1, 4, 0, 2, 3, 4, 4, 4, 3, 3, 3, 4, 4, 4, 3, 4, 1, 3, 4, 3, 2, 1, 2, 1, 3, 3, 3, 4, 4, 3, 3, 5, 0, 4, 0, 3, 0, 4, 3, 3, 3, 2, 1, 0, 3, 0, 0, 3, 3), - (0, 4, 0, 3, 0, 3, 0, 3, 0, 3, 5, 5, 3, 3, 3, 3, 4, 3, 4, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 4, 3, 5, 3, 3, 1, 3, 2, 4, 5, 5, 5, 5, 4, 3, 4, 5, 5, 3, 2, 2, 3, 3, 3, 3, 2, 3, 3, 1, 2, 3, 2, 4, 3, 3, 3, 4, 0, 4, 0, 2, 0, 4, 3, 2, 2, 1, 2, 0, 3, 0, 0, 4, 1), -) -# fmt: on - - -class JapaneseContextAnalysis: - NUM_OF_CATEGORY = 6 - DONT_KNOW = -1 - ENOUGH_REL_THRESHOLD = 100 - MAX_REL_THRESHOLD = 1000 - MINIMUM_DATA_THRESHOLD = 4 - - def __init__(self) -> None: - self._total_rel = 0 - self._rel_sample: List[int] = [] - self._need_to_skip_char_num = 0 - self._last_char_order = -1 - self._done = False - self.reset() - - def reset(self) -> None: - self._total_rel = 0 # total sequence received - # category counters, each integer counts sequence in its category - self._rel_sample = [0] * self.NUM_OF_CATEGORY - # if last byte in current buffer is not the last byte of a character, - # we need to know how many bytes to skip in next buffer - self._need_to_skip_char_num = 0 - self._last_char_order = -1 # The order of previous char - # If this flag is set to True, detection is done and conclusion has - # been made - self._done = False - - def feed(self, byte_str: Union[bytes, bytearray], num_bytes: int) -> None: - if self._done: - return - - # The buffer we got is byte oriented, and a character may span in more than one - # buffers. In case the last one or two byte in last buffer is not - # complete, we record how many byte needed to complete that character - # and skip these bytes here. We can choose to record those bytes as - # well and analyse the character once it is complete, but since a - # character will not make much difference, by simply skipping - # this character will simply our logic and improve performance. - i = self._need_to_skip_char_num - while i < num_bytes: - order, char_len = self.get_order(byte_str[i : i + 2]) - i += char_len - if i > num_bytes: - self._need_to_skip_char_num = i - num_bytes - self._last_char_order = -1 - else: - if (order != -1) and (self._last_char_order != -1): - self._total_rel += 1 - if self._total_rel > self.MAX_REL_THRESHOLD: - self._done = True - break - self._rel_sample[ - jp2_char_context[self._last_char_order][order] - ] += 1 - self._last_char_order = order - - def got_enough_data(self) -> bool: - return self._total_rel > self.ENOUGH_REL_THRESHOLD - - def get_confidence(self) -> float: - # This is just one way to calculate confidence. It works well for me. - if self._total_rel > self.MINIMUM_DATA_THRESHOLD: - return (self._total_rel - self._rel_sample[0]) / self._total_rel - return self.DONT_KNOW - - def get_order(self, _: Union[bytes, bytearray]) -> Tuple[int, int]: - return -1, 1 - - -class SJISContextAnalysis(JapaneseContextAnalysis): - def __init__(self) -> None: - super().__init__() - self._charset_name = "SHIFT_JIS" - - @property - def charset_name(self) -> str: - return self._charset_name - - def get_order(self, byte_str: Union[bytes, bytearray]) -> Tuple[int, int]: - if not byte_str: - return -1, 1 - # find out current char's byte length - first_char = byte_str[0] - if (0x81 <= first_char <= 0x9F) or (0xE0 <= first_char <= 0xFC): - char_len = 2 - if (first_char == 0x87) or (0xFA <= first_char <= 0xFC): - self._charset_name = "CP932" - else: - char_len = 1 - - # return its order if it is hiragana - if len(byte_str) > 1: - second_char = byte_str[1] - if (first_char == 202) and (0x9F <= second_char <= 0xF1): - return second_char - 0x9F, char_len - - return -1, char_len - - -class EUCJPContextAnalysis(JapaneseContextAnalysis): - def get_order(self, byte_str: Union[bytes, bytearray]) -> Tuple[int, int]: - if not byte_str: - return -1, 1 - # find out current char's byte length - first_char = byte_str[0] - if (first_char == 0x8E) or (0xA1 <= first_char <= 0xFE): - char_len = 2 - elif first_char == 0x8F: - char_len = 3 - else: - char_len = 1 - - # return its order if it is hiragana - if len(byte_str) > 1: - second_char = byte_str[1] - if (first_char == 0xA4) and (0xA1 <= second_char <= 0xF3): - return second_char - 0xA1, char_len - - return -1, char_len diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langbulgarianmodel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langbulgarianmodel.py deleted file mode 100644 index 9946682..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langbulgarianmodel.py +++ /dev/null @@ -1,4649 +0,0 @@ -from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel - -# 3: Positive -# 2: Likely -# 1: Unlikely -# 0: Negative - -BULGARIAN_LANG_MODEL = { - 63: { # 'e' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 1, # 'б' - 9: 1, # 'в' - 20: 1, # 'г' - 11: 1, # 'д' - 3: 1, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 0, # 'и' - 26: 1, # 'й' - 12: 1, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 1, # 'о' - 13: 1, # 'п' - 7: 1, # 'р' - 8: 1, # 'с' - 5: 1, # 'т' - 19: 0, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 45: { # '\xad' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 0, # 'Л' - 38: 1, # 'М' - 36: 0, # 'Н' - 41: 1, # 'О' - 30: 1, # 'П' - 39: 1, # 'Р' - 28: 1, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 1, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 0, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 0, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 0, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 31: { # 'А' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 1, # 'А' - 32: 1, # 'Б' - 35: 2, # 'В' - 43: 1, # 'Г' - 37: 2, # 'Д' - 44: 2, # 'Е' - 55: 1, # 'Ж' - 47: 2, # 'З' - 40: 1, # 'И' - 59: 1, # 'Й' - 33: 1, # 'К' - 46: 2, # 'Л' - 38: 1, # 'М' - 36: 2, # 'Н' - 41: 1, # 'О' - 30: 2, # 'П' - 39: 2, # 'Р' - 28: 2, # 'С' - 34: 2, # 'Т' - 51: 1, # 'У' - 48: 2, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 2, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 1, # 'Я' - 1: 1, # 'а' - 18: 2, # 'б' - 9: 2, # 'в' - 20: 2, # 'г' - 11: 2, # 'д' - 3: 1, # 'е' - 23: 1, # 'ж' - 15: 2, # 'з' - 2: 0, # 'и' - 26: 2, # 'й' - 12: 2, # 'к' - 10: 3, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 0, # 'о' - 13: 2, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 2, # 'т' - 19: 1, # 'у' - 29: 2, # 'ф' - 25: 1, # 'х' - 22: 1, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 32: { # 'Б' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 2, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 2, # 'Д' - 44: 1, # 'Е' - 55: 1, # 'Ж' - 47: 2, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 2, # 'Н' - 41: 2, # 'О' - 30: 1, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 2, # 'Т' - 51: 1, # 'У' - 48: 2, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 0, # 'Ш' - 57: 1, # 'Щ' - 61: 2, # 'Ъ' - 60: 1, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 2, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 2, # 'р' - 8: 1, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 2, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 35: { # 'В' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 2, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 1, # 'П' - 39: 2, # 'Р' - 28: 2, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 2, # 'Ф' - 49: 0, # 'Х' - 53: 1, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 2, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 2, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 2, # 'н' - 4: 2, # 'о' - 13: 1, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 2, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 2, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 43: { # 'Г' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 2, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 0, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 0, # 'П' - 39: 1, # 'Р' - 28: 1, # 'С' - 34: 0, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 1, # 'Щ' - 61: 1, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 1, # 'б' - 9: 1, # 'в' - 20: 0, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 2, # 'о' - 13: 0, # 'п' - 7: 2, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 1, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 37: { # 'Д' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 2, # 'В' - 43: 1, # 'Г' - 37: 2, # 'Д' - 44: 2, # 'Е' - 55: 2, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 2, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 2, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 3, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 2, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 2, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 44: { # 'Е' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 1, # 'Б' - 35: 2, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 1, # 'Ж' - 47: 1, # 'З' - 40: 1, # 'И' - 59: 1, # 'Й' - 33: 2, # 'К' - 46: 2, # 'Л' - 38: 1, # 'М' - 36: 2, # 'Н' - 41: 2, # 'О' - 30: 1, # 'П' - 39: 2, # 'Р' - 28: 2, # 'С' - 34: 2, # 'Т' - 51: 1, # 'У' - 48: 2, # 'Ф' - 49: 1, # 'Х' - 53: 2, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 1, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 1, # 'Я' - 1: 0, # 'а' - 18: 1, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 2, # 'д' - 3: 0, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 0, # 'и' - 26: 1, # 'й' - 12: 2, # 'к' - 10: 2, # 'л' - 14: 2, # 'м' - 6: 2, # 'н' - 4: 0, # 'о' - 13: 1, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 1, # 'т' - 19: 1, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 55: { # 'Ж' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 0, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 1, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 1, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 2, # 'о' - 13: 1, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 47: { # 'З' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 2, # 'Н' - 41: 1, # 'О' - 30: 1, # 'П' - 39: 1, # 'Р' - 28: 1, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 0, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 0, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 2, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 1, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 1, # 'о' - 13: 0, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 40: { # 'И' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 1, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 2, # 'Е' - 55: 1, # 'Ж' - 47: 2, # 'З' - 40: 1, # 'И' - 59: 1, # 'Й' - 33: 2, # 'К' - 46: 2, # 'Л' - 38: 2, # 'М' - 36: 2, # 'Н' - 41: 1, # 'О' - 30: 1, # 'П' - 39: 2, # 'Р' - 28: 2, # 'С' - 34: 2, # 'Т' - 51: 0, # 'У' - 48: 1, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 1, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 2, # 'Я' - 1: 1, # 'а' - 18: 1, # 'б' - 9: 3, # 'в' - 20: 2, # 'г' - 11: 1, # 'д' - 3: 1, # 'е' - 23: 0, # 'ж' - 15: 3, # 'з' - 2: 0, # 'и' - 26: 1, # 'й' - 12: 1, # 'к' - 10: 2, # 'л' - 14: 2, # 'м' - 6: 2, # 'н' - 4: 0, # 'о' - 13: 1, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 2, # 'т' - 19: 0, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 1, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 59: { # 'Й' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 1, # 'С' - 34: 1, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 1, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 1, # 'Я' - 1: 0, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 1, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 0, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 2, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 33: { # 'К' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 0, # 'М' - 36: 2, # 'Н' - 41: 2, # 'О' - 30: 2, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 1, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 2, # 'е' - 23: 1, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 2, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 3, # 'р' - 8: 1, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 46: { # 'Л' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 2, # 'Г' - 37: 1, # 'Д' - 44: 2, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 0, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 1, # 'П' - 39: 0, # 'Р' - 28: 1, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 0, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 1, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 1, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 2, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 38: { # 'М' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 2, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 1, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 1, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 0, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 2, # 'л' - 14: 0, # 'м' - 6: 2, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 36: { # 'Н' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 2, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 2, # 'Д' - 44: 2, # 'Е' - 55: 1, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 1, # 'Й' - 33: 2, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 1, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 2, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 1, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 0, # 'с' - 5: 1, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 2, # 'ю' - 16: 2, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 41: { # 'О' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 1, # 'Б' - 35: 2, # 'В' - 43: 1, # 'Г' - 37: 2, # 'Д' - 44: 1, # 'Е' - 55: 1, # 'Ж' - 47: 1, # 'З' - 40: 1, # 'И' - 59: 1, # 'Й' - 33: 2, # 'К' - 46: 2, # 'Л' - 38: 2, # 'М' - 36: 2, # 'Н' - 41: 2, # 'О' - 30: 1, # 'П' - 39: 2, # 'Р' - 28: 2, # 'С' - 34: 2, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 1, # 'Х' - 53: 0, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 1, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 1, # 'Я' - 1: 1, # 'а' - 18: 2, # 'б' - 9: 2, # 'в' - 20: 2, # 'г' - 11: 1, # 'д' - 3: 1, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 0, # 'и' - 26: 1, # 'й' - 12: 2, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 0, # 'о' - 13: 2, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 3, # 'т' - 19: 1, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 1, # 'ц' - 21: 2, # 'ч' - 27: 0, # 'ш' - 24: 2, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 30: { # 'П' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 2, # 'П' - 39: 2, # 'Р' - 28: 2, # 'С' - 34: 1, # 'Т' - 51: 2, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 2, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 3, # 'л' - 14: 0, # 'м' - 6: 1, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 3, # 'р' - 8: 1, # 'с' - 5: 1, # 'т' - 19: 2, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 39: { # 'Р' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 2, # 'Г' - 37: 2, # 'Д' - 44: 2, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 0, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 2, # 'П' - 39: 1, # 'Р' - 28: 1, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 1, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 1, # 'с' - 5: 0, # 'т' - 19: 3, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 28: { # 'С' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 3, # 'А' - 32: 2, # 'Б' - 35: 2, # 'В' - 43: 1, # 'Г' - 37: 2, # 'Д' - 44: 2, # 'Е' - 55: 1, # 'Ж' - 47: 1, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 2, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 2, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 2, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 1, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 2, # 'к' - 10: 3, # 'л' - 14: 2, # 'м' - 6: 1, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 2, # 'р' - 8: 0, # 'с' - 5: 3, # 'т' - 19: 2, # 'у' - 29: 2, # 'ф' - 25: 1, # 'х' - 22: 1, # 'ц' - 21: 1, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 34: { # 'Т' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 2, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 2, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 2, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 2, # 'О' - 30: 1, # 'П' - 39: 2, # 'Р' - 28: 2, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 1, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 1, # 'Ъ' - 60: 0, # 'Ю' - 56: 1, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 1, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 1, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 3, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 2, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 51: { # 'У' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 1, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 2, # 'Е' - 55: 1, # 'Ж' - 47: 1, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 0, # 'О' - 30: 1, # 'П' - 39: 1, # 'Р' - 28: 1, # 'С' - 34: 2, # 'Т' - 51: 0, # 'У' - 48: 1, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 1, # 'а' - 18: 1, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 1, # 'д' - 3: 2, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 2, # 'и' - 26: 1, # 'й' - 12: 2, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 2, # 'н' - 4: 2, # 'о' - 13: 1, # 'п' - 7: 1, # 'р' - 8: 2, # 'с' - 5: 1, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 2, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 48: { # 'Ф' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 0, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 2, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 1, # 'Т' - 51: 1, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 2, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 2, # 'о' - 13: 0, # 'п' - 7: 2, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 49: { # 'Х' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 0, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 1, # 'П' - 39: 1, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 1, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 1, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 0, # 'н' - 4: 2, # 'о' - 13: 0, # 'п' - 7: 2, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 53: { # 'Ц' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 0, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 2, # 'И' - 59: 0, # 'Й' - 33: 2, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 1, # 'Р' - 28: 2, # 'С' - 34: 0, # 'Т' - 51: 1, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 2, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 1, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 1, # 'о' - 13: 0, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 50: { # 'Ч' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 2, # 'А' - 32: 1, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 0, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 1, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 1, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 2, # 'о' - 13: 0, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 1, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 54: { # 'Ш' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 1, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 1, # 'Н' - 41: 1, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 1, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 2, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 2, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 2, # 'о' - 13: 1, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 1, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 57: { # 'Щ' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 1, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 1, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 1, # 'о' - 13: 0, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 1, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 61: { # 'Ъ' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 1, # 'Д' - 44: 0, # 'Е' - 55: 1, # 'Ж' - 47: 1, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 2, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 0, # 'О' - 30: 1, # 'П' - 39: 2, # 'Р' - 28: 1, # 'С' - 34: 1, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 1, # 'Х' - 53: 1, # 'Ц' - 50: 1, # 'Ч' - 54: 1, # 'Ш' - 57: 1, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 0, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 0, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 1, # 'л' - 14: 0, # 'м' - 6: 1, # 'н' - 4: 0, # 'о' - 13: 0, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 60: { # 'Ю' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 1, # 'Б' - 35: 0, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 0, # 'Е' - 55: 1, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 0, # 'М' - 36: 1, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 1, # 'Р' - 28: 1, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 1, # 'б' - 9: 1, # 'в' - 20: 2, # 'г' - 11: 1, # 'д' - 3: 0, # 'е' - 23: 2, # 'ж' - 15: 1, # 'з' - 2: 1, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 0, # 'о' - 13: 1, # 'п' - 7: 1, # 'р' - 8: 1, # 'с' - 5: 1, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 56: { # 'Я' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 1, # 'Б' - 35: 1, # 'В' - 43: 1, # 'Г' - 37: 1, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 1, # 'Л' - 38: 1, # 'М' - 36: 1, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 1, # 'С' - 34: 2, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 1, # 'б' - 9: 1, # 'в' - 20: 1, # 'г' - 11: 1, # 'д' - 3: 0, # 'е' - 23: 0, # 'ж' - 15: 1, # 'з' - 2: 1, # 'и' - 26: 1, # 'й' - 12: 1, # 'к' - 10: 1, # 'л' - 14: 2, # 'м' - 6: 2, # 'н' - 4: 0, # 'о' - 13: 2, # 'п' - 7: 1, # 'р' - 8: 1, # 'с' - 5: 1, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 1: { # 'а' - 63: 1, # 'e' - 45: 1, # '\xad' - 31: 1, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 1, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 1, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 3, # 'ж' - 15: 3, # 'з' - 2: 3, # 'и' - 26: 3, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 2, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 3, # 'ф' - 25: 3, # 'х' - 22: 3, # 'ц' - 21: 3, # 'ч' - 27: 3, # 'ш' - 24: 3, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 18: { # 'б' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 3, # 'в' - 20: 1, # 'г' - 11: 2, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 3, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 1, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 0, # 'т' - 19: 3, # 'у' - 29: 0, # 'ф' - 25: 2, # 'х' - 22: 1, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 3, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 9: { # 'в' - 63: 1, # 'e' - 45: 1, # '\xad' - 31: 0, # 'А' - 32: 1, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 0, # 'в' - 20: 2, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 3, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 2, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 3, # 'ч' - 27: 2, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 20: { # 'г' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 2, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 3, # 'л' - 14: 1, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 1, # 'п' - 7: 3, # 'р' - 8: 2, # 'с' - 5: 2, # 'т' - 19: 3, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 11: { # 'д' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 2, # 'б' - 9: 3, # 'в' - 20: 2, # 'г' - 11: 2, # 'д' - 3: 3, # 'е' - 23: 3, # 'ж' - 15: 2, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 1, # 'т' - 19: 3, # 'у' - 29: 1, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 3: { # 'е' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 2, # 'е' - 23: 3, # 'ж' - 15: 3, # 'з' - 2: 2, # 'и' - 26: 3, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 2, # 'у' - 29: 3, # 'ф' - 25: 3, # 'х' - 22: 3, # 'ц' - 21: 3, # 'ч' - 27: 3, # 'ш' - 24: 3, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 23: { # 'ж' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 2, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 3, # 'н' - 4: 2, # 'о' - 13: 1, # 'п' - 7: 1, # 'р' - 8: 1, # 'с' - 5: 1, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 1, # 'ц' - 21: 1, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 15: { # 'з' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 1, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 2, # 'ш' - 24: 1, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 2, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 2: { # 'и' - 63: 1, # 'e' - 45: 1, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 1, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 1, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 1, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 1, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 3, # 'ж' - 15: 3, # 'з' - 2: 3, # 'и' - 26: 3, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 2, # 'у' - 29: 3, # 'ф' - 25: 3, # 'х' - 22: 3, # 'ц' - 21: 3, # 'ч' - 27: 3, # 'ш' - 24: 3, # 'щ' - 17: 2, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 26: { # 'й' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 1, # 'а' - 18: 2, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 2, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 2, # 'з' - 2: 1, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 2, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 2, # 'о' - 13: 1, # 'п' - 7: 2, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 1, # 'у' - 29: 2, # 'ф' - 25: 1, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 12: { # 'к' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 1, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 1, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 3, # 'в' - 20: 2, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 2, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 3, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 1, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 3, # 'ц' - 21: 2, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 10: { # 'л' - 63: 1, # 'e' - 45: 1, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 1, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 2, # 'д' - 3: 3, # 'е' - 23: 3, # 'ж' - 15: 2, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 1, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 2, # 'п' - 7: 2, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 2, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 2, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 2, # 'ь' - 42: 3, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 14: { # 'м' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 1, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 1, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 2, # 'к' - 10: 3, # 'л' - 14: 1, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 1, # 'т' - 19: 3, # 'у' - 29: 2, # 'ф' - 25: 1, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 2, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 6: { # 'н' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 1, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 2, # 'б' - 9: 2, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 2, # 'ж' - 15: 2, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 1, # 'п' - 7: 2, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 3, # 'ф' - 25: 2, # 'х' - 22: 3, # 'ц' - 21: 3, # 'ч' - 27: 2, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 2, # 'ь' - 42: 2, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 4: { # 'о' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 2, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 3, # 'ж' - 15: 3, # 'з' - 2: 3, # 'и' - 26: 3, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 2, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 2, # 'у' - 29: 3, # 'ф' - 25: 3, # 'х' - 22: 3, # 'ц' - 21: 3, # 'ч' - 27: 3, # 'ш' - 24: 3, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 13: { # 'п' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 1, # 'й' - 12: 2, # 'к' - 10: 3, # 'л' - 14: 1, # 'м' - 6: 2, # 'н' - 4: 3, # 'о' - 13: 1, # 'п' - 7: 3, # 'р' - 8: 2, # 'с' - 5: 2, # 'т' - 19: 3, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 2, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 7: { # 'р' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 3, # 'е' - 23: 3, # 'ж' - 15: 2, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 2, # 'п' - 7: 1, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 2, # 'ф' - 25: 3, # 'х' - 22: 3, # 'ц' - 21: 2, # 'ч' - 27: 3, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 1, # 'ь' - 42: 2, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 8: { # 'с' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 2, # 'б' - 9: 3, # 'в' - 20: 2, # 'г' - 11: 2, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 1, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 2, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 2, # 'ш' - 24: 0, # 'щ' - 17: 3, # 'ъ' - 52: 2, # 'ь' - 42: 2, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 5: { # 'т' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 2, # 'г' - 11: 2, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 2, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 3, # 'у' - 29: 1, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 2, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 3, # 'ъ' - 52: 2, # 'ь' - 42: 2, # 'ю' - 16: 3, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 19: { # 'у' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 2, # 'е' - 23: 3, # 'ж' - 15: 3, # 'з' - 2: 2, # 'и' - 26: 2, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 2, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 1, # 'у' - 29: 2, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 3, # 'ч' - 27: 3, # 'ш' - 24: 2, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 29: { # 'ф' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 1, # 'в' - 20: 1, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 2, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 2, # 'т' - 19: 2, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 2, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 25: { # 'х' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 3, # 'в' - 20: 0, # 'г' - 11: 1, # 'д' - 3: 2, # 'е' - 23: 0, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 2, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 1, # 'п' - 7: 3, # 'р' - 8: 1, # 'с' - 5: 2, # 'т' - 19: 3, # 'у' - 29: 0, # 'ф' - 25: 1, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 22: { # 'ц' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 2, # 'в' - 20: 1, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 1, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 2, # 'к' - 10: 1, # 'л' - 14: 1, # 'м' - 6: 1, # 'н' - 4: 2, # 'о' - 13: 1, # 'п' - 7: 1, # 'р' - 8: 1, # 'с' - 5: 1, # 'т' - 19: 2, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 1, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 0, # 'ю' - 16: 2, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 21: { # 'ч' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 1, # 'б' - 9: 3, # 'в' - 20: 1, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 1, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 2, # 'л' - 14: 2, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 2, # 'р' - 8: 0, # 'с' - 5: 2, # 'т' - 19: 3, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 1, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 27: { # 'ш' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 2, # 'в' - 20: 0, # 'г' - 11: 1, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 3, # 'к' - 10: 2, # 'л' - 14: 1, # 'м' - 6: 3, # 'н' - 4: 2, # 'о' - 13: 2, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 1, # 'т' - 19: 2, # 'у' - 29: 1, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 1, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 2, # 'ъ' - 52: 1, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 24: { # 'щ' - 63: 1, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 3, # 'а' - 18: 0, # 'б' - 9: 1, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 3, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 3, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 2, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 1, # 'р' - 8: 0, # 'с' - 5: 2, # 'т' - 19: 3, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 1, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 2, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 17: { # 'ъ' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 1, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 3, # 'г' - 11: 3, # 'д' - 3: 2, # 'е' - 23: 3, # 'ж' - 15: 3, # 'з' - 2: 1, # 'и' - 26: 2, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 3, # 'о' - 13: 3, # 'п' - 7: 3, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 1, # 'у' - 29: 1, # 'ф' - 25: 2, # 'х' - 22: 2, # 'ц' - 21: 3, # 'ч' - 27: 2, # 'ш' - 24: 3, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 2, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 52: { # 'ь' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 1, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 0, # 'и' - 26: 0, # 'й' - 12: 1, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 1, # 'н' - 4: 3, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 0, # 'с' - 5: 1, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 1, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 1, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 42: { # 'ю' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 1, # 'а' - 18: 2, # 'б' - 9: 1, # 'в' - 20: 2, # 'г' - 11: 2, # 'д' - 3: 1, # 'е' - 23: 2, # 'ж' - 15: 2, # 'з' - 2: 1, # 'и' - 26: 1, # 'й' - 12: 2, # 'к' - 10: 2, # 'л' - 14: 2, # 'м' - 6: 2, # 'н' - 4: 1, # 'о' - 13: 1, # 'п' - 7: 2, # 'р' - 8: 2, # 'с' - 5: 2, # 'т' - 19: 1, # 'у' - 29: 1, # 'ф' - 25: 1, # 'х' - 22: 2, # 'ц' - 21: 3, # 'ч' - 27: 1, # 'ш' - 24: 1, # 'щ' - 17: 1, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 16: { # 'я' - 63: 0, # 'e' - 45: 1, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 3, # 'б' - 9: 3, # 'в' - 20: 2, # 'г' - 11: 3, # 'д' - 3: 2, # 'е' - 23: 1, # 'ж' - 15: 2, # 'з' - 2: 1, # 'и' - 26: 2, # 'й' - 12: 3, # 'к' - 10: 3, # 'л' - 14: 3, # 'м' - 6: 3, # 'н' - 4: 1, # 'о' - 13: 2, # 'п' - 7: 2, # 'р' - 8: 3, # 'с' - 5: 3, # 'т' - 19: 1, # 'у' - 29: 1, # 'ф' - 25: 3, # 'х' - 22: 2, # 'ц' - 21: 1, # 'ч' - 27: 1, # 'ш' - 24: 2, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 1, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 58: { # 'є' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 0, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 0, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 0, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, - 62: { # '№' - 63: 0, # 'e' - 45: 0, # '\xad' - 31: 0, # 'А' - 32: 0, # 'Б' - 35: 0, # 'В' - 43: 0, # 'Г' - 37: 0, # 'Д' - 44: 0, # 'Е' - 55: 0, # 'Ж' - 47: 0, # 'З' - 40: 0, # 'И' - 59: 0, # 'Й' - 33: 0, # 'К' - 46: 0, # 'Л' - 38: 0, # 'М' - 36: 0, # 'Н' - 41: 0, # 'О' - 30: 0, # 'П' - 39: 0, # 'Р' - 28: 0, # 'С' - 34: 0, # 'Т' - 51: 0, # 'У' - 48: 0, # 'Ф' - 49: 0, # 'Х' - 53: 0, # 'Ц' - 50: 0, # 'Ч' - 54: 0, # 'Ш' - 57: 0, # 'Щ' - 61: 0, # 'Ъ' - 60: 0, # 'Ю' - 56: 0, # 'Я' - 1: 0, # 'а' - 18: 0, # 'б' - 9: 0, # 'в' - 20: 0, # 'г' - 11: 0, # 'д' - 3: 0, # 'е' - 23: 0, # 'ж' - 15: 0, # 'з' - 2: 0, # 'и' - 26: 0, # 'й' - 12: 0, # 'к' - 10: 0, # 'л' - 14: 0, # 'м' - 6: 0, # 'н' - 4: 0, # 'о' - 13: 0, # 'п' - 7: 0, # 'р' - 8: 0, # 'с' - 5: 0, # 'т' - 19: 0, # 'у' - 29: 0, # 'ф' - 25: 0, # 'х' - 22: 0, # 'ц' - 21: 0, # 'ч' - 27: 0, # 'ш' - 24: 0, # 'щ' - 17: 0, # 'ъ' - 52: 0, # 'ь' - 42: 0, # 'ю' - 16: 0, # 'я' - 58: 0, # 'є' - 62: 0, # '№' - }, -} - -# 255: Undefined characters that did not exist in training text -# 254: Carriage/Return -# 253: symbol (punctuation) that does not belong to word -# 252: 0 - 9 -# 251: Control characters - -# Character Mapping Table(s): -ISO_8859_5_BULGARIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 77, # 'A' - 66: 90, # 'B' - 67: 99, # 'C' - 68: 100, # 'D' - 69: 72, # 'E' - 70: 109, # 'F' - 71: 107, # 'G' - 72: 101, # 'H' - 73: 79, # 'I' - 74: 185, # 'J' - 75: 81, # 'K' - 76: 102, # 'L' - 77: 76, # 'M' - 78: 94, # 'N' - 79: 82, # 'O' - 80: 110, # 'P' - 81: 186, # 'Q' - 82: 108, # 'R' - 83: 91, # 'S' - 84: 74, # 'T' - 85: 119, # 'U' - 86: 84, # 'V' - 87: 96, # 'W' - 88: 111, # 'X' - 89: 187, # 'Y' - 90: 115, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 65, # 'a' - 98: 69, # 'b' - 99: 70, # 'c' - 100: 66, # 'd' - 101: 63, # 'e' - 102: 68, # 'f' - 103: 112, # 'g' - 104: 103, # 'h' - 105: 92, # 'i' - 106: 194, # 'j' - 107: 104, # 'k' - 108: 95, # 'l' - 109: 86, # 'm' - 110: 87, # 'n' - 111: 71, # 'o' - 112: 116, # 'p' - 113: 195, # 'q' - 114: 85, # 'r' - 115: 93, # 's' - 116: 97, # 't' - 117: 113, # 'u' - 118: 196, # 'v' - 119: 197, # 'w' - 120: 198, # 'x' - 121: 199, # 'y' - 122: 200, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 194, # '\x80' - 129: 195, # '\x81' - 130: 196, # '\x82' - 131: 197, # '\x83' - 132: 198, # '\x84' - 133: 199, # '\x85' - 134: 200, # '\x86' - 135: 201, # '\x87' - 136: 202, # '\x88' - 137: 203, # '\x89' - 138: 204, # '\x8a' - 139: 205, # '\x8b' - 140: 206, # '\x8c' - 141: 207, # '\x8d' - 142: 208, # '\x8e' - 143: 209, # '\x8f' - 144: 210, # '\x90' - 145: 211, # '\x91' - 146: 212, # '\x92' - 147: 213, # '\x93' - 148: 214, # '\x94' - 149: 215, # '\x95' - 150: 216, # '\x96' - 151: 217, # '\x97' - 152: 218, # '\x98' - 153: 219, # '\x99' - 154: 220, # '\x9a' - 155: 221, # '\x9b' - 156: 222, # '\x9c' - 157: 223, # '\x9d' - 158: 224, # '\x9e' - 159: 225, # '\x9f' - 160: 81, # '\xa0' - 161: 226, # 'Ё' - 162: 227, # 'Ђ' - 163: 228, # 'Ѓ' - 164: 229, # 'Є' - 165: 230, # 'Ѕ' - 166: 105, # 'І' - 167: 231, # 'Ї' - 168: 232, # 'Ј' - 169: 233, # 'Љ' - 170: 234, # 'Њ' - 171: 235, # 'Ћ' - 172: 236, # 'Ќ' - 173: 45, # '\xad' - 174: 237, # 'Ў' - 175: 238, # 'Џ' - 176: 31, # 'А' - 177: 32, # 'Б' - 178: 35, # 'В' - 179: 43, # 'Г' - 180: 37, # 'Д' - 181: 44, # 'Е' - 182: 55, # 'Ж' - 183: 47, # 'З' - 184: 40, # 'И' - 185: 59, # 'Й' - 186: 33, # 'К' - 187: 46, # 'Л' - 188: 38, # 'М' - 189: 36, # 'Н' - 190: 41, # 'О' - 191: 30, # 'П' - 192: 39, # 'Р' - 193: 28, # 'С' - 194: 34, # 'Т' - 195: 51, # 'У' - 196: 48, # 'Ф' - 197: 49, # 'Х' - 198: 53, # 'Ц' - 199: 50, # 'Ч' - 200: 54, # 'Ш' - 201: 57, # 'Щ' - 202: 61, # 'Ъ' - 203: 239, # 'Ы' - 204: 67, # 'Ь' - 205: 240, # 'Э' - 206: 60, # 'Ю' - 207: 56, # 'Я' - 208: 1, # 'а' - 209: 18, # 'б' - 210: 9, # 'в' - 211: 20, # 'г' - 212: 11, # 'д' - 213: 3, # 'е' - 214: 23, # 'ж' - 215: 15, # 'з' - 216: 2, # 'и' - 217: 26, # 'й' - 218: 12, # 'к' - 219: 10, # 'л' - 220: 14, # 'м' - 221: 6, # 'н' - 222: 4, # 'о' - 223: 13, # 'п' - 224: 7, # 'р' - 225: 8, # 'с' - 226: 5, # 'т' - 227: 19, # 'у' - 228: 29, # 'ф' - 229: 25, # 'х' - 230: 22, # 'ц' - 231: 21, # 'ч' - 232: 27, # 'ш' - 233: 24, # 'щ' - 234: 17, # 'ъ' - 235: 75, # 'ы' - 236: 52, # 'ь' - 237: 241, # 'э' - 238: 42, # 'ю' - 239: 16, # 'я' - 240: 62, # '№' - 241: 242, # 'ё' - 242: 243, # 'ђ' - 243: 244, # 'ѓ' - 244: 58, # 'є' - 245: 245, # 'ѕ' - 246: 98, # 'і' - 247: 246, # 'ї' - 248: 247, # 'ј' - 249: 248, # 'љ' - 250: 249, # 'њ' - 251: 250, # 'ћ' - 252: 251, # 'ќ' - 253: 91, # '§' - 254: 252, # 'ў' - 255: 253, # 'џ' -} - -ISO_8859_5_BULGARIAN_MODEL = SingleByteCharSetModel( - charset_name="ISO-8859-5", - language="Bulgarian", - char_to_order_map=ISO_8859_5_BULGARIAN_CHAR_TO_ORDER, - language_model=BULGARIAN_LANG_MODEL, - typical_positive_ratio=0.969392, - keep_ascii_letters=False, - alphabet="АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯабвгдежзийклмнопрстуфхцчшщъьюя", -) - -WINDOWS_1251_BULGARIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 77, # 'A' - 66: 90, # 'B' - 67: 99, # 'C' - 68: 100, # 'D' - 69: 72, # 'E' - 70: 109, # 'F' - 71: 107, # 'G' - 72: 101, # 'H' - 73: 79, # 'I' - 74: 185, # 'J' - 75: 81, # 'K' - 76: 102, # 'L' - 77: 76, # 'M' - 78: 94, # 'N' - 79: 82, # 'O' - 80: 110, # 'P' - 81: 186, # 'Q' - 82: 108, # 'R' - 83: 91, # 'S' - 84: 74, # 'T' - 85: 119, # 'U' - 86: 84, # 'V' - 87: 96, # 'W' - 88: 111, # 'X' - 89: 187, # 'Y' - 90: 115, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 65, # 'a' - 98: 69, # 'b' - 99: 70, # 'c' - 100: 66, # 'd' - 101: 63, # 'e' - 102: 68, # 'f' - 103: 112, # 'g' - 104: 103, # 'h' - 105: 92, # 'i' - 106: 194, # 'j' - 107: 104, # 'k' - 108: 95, # 'l' - 109: 86, # 'm' - 110: 87, # 'n' - 111: 71, # 'o' - 112: 116, # 'p' - 113: 195, # 'q' - 114: 85, # 'r' - 115: 93, # 's' - 116: 97, # 't' - 117: 113, # 'u' - 118: 196, # 'v' - 119: 197, # 'w' - 120: 198, # 'x' - 121: 199, # 'y' - 122: 200, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 206, # 'Ђ' - 129: 207, # 'Ѓ' - 130: 208, # '‚' - 131: 209, # 'ѓ' - 132: 210, # '„' - 133: 211, # '…' - 134: 212, # '†' - 135: 213, # '‡' - 136: 120, # '€' - 137: 214, # '‰' - 138: 215, # 'Љ' - 139: 216, # '‹' - 140: 217, # 'Њ' - 141: 218, # 'Ќ' - 142: 219, # 'Ћ' - 143: 220, # 'Џ' - 144: 221, # 'ђ' - 145: 78, # '‘' - 146: 64, # '’' - 147: 83, # '“' - 148: 121, # '”' - 149: 98, # '•' - 150: 117, # '–' - 151: 105, # '—' - 152: 222, # None - 153: 223, # '™' - 154: 224, # 'љ' - 155: 225, # '›' - 156: 226, # 'њ' - 157: 227, # 'ќ' - 158: 228, # 'ћ' - 159: 229, # 'џ' - 160: 88, # '\xa0' - 161: 230, # 'Ў' - 162: 231, # 'ў' - 163: 232, # 'Ј' - 164: 233, # '¤' - 165: 122, # 'Ґ' - 166: 89, # '¦' - 167: 106, # '§' - 168: 234, # 'Ё' - 169: 235, # '©' - 170: 236, # 'Є' - 171: 237, # '«' - 172: 238, # '¬' - 173: 45, # '\xad' - 174: 239, # '®' - 175: 240, # 'Ї' - 176: 73, # '°' - 177: 80, # '±' - 178: 118, # 'І' - 179: 114, # 'і' - 180: 241, # 'ґ' - 181: 242, # 'µ' - 182: 243, # '¶' - 183: 244, # '·' - 184: 245, # 'ё' - 185: 62, # '№' - 186: 58, # 'є' - 187: 246, # '»' - 188: 247, # 'ј' - 189: 248, # 'Ѕ' - 190: 249, # 'ѕ' - 191: 250, # 'ї' - 192: 31, # 'А' - 193: 32, # 'Б' - 194: 35, # 'В' - 195: 43, # 'Г' - 196: 37, # 'Д' - 197: 44, # 'Е' - 198: 55, # 'Ж' - 199: 47, # 'З' - 200: 40, # 'И' - 201: 59, # 'Й' - 202: 33, # 'К' - 203: 46, # 'Л' - 204: 38, # 'М' - 205: 36, # 'Н' - 206: 41, # 'О' - 207: 30, # 'П' - 208: 39, # 'Р' - 209: 28, # 'С' - 210: 34, # 'Т' - 211: 51, # 'У' - 212: 48, # 'Ф' - 213: 49, # 'Х' - 214: 53, # 'Ц' - 215: 50, # 'Ч' - 216: 54, # 'Ш' - 217: 57, # 'Щ' - 218: 61, # 'Ъ' - 219: 251, # 'Ы' - 220: 67, # 'Ь' - 221: 252, # 'Э' - 222: 60, # 'Ю' - 223: 56, # 'Я' - 224: 1, # 'а' - 225: 18, # 'б' - 226: 9, # 'в' - 227: 20, # 'г' - 228: 11, # 'д' - 229: 3, # 'е' - 230: 23, # 'ж' - 231: 15, # 'з' - 232: 2, # 'и' - 233: 26, # 'й' - 234: 12, # 'к' - 235: 10, # 'л' - 236: 14, # 'м' - 237: 6, # 'н' - 238: 4, # 'о' - 239: 13, # 'п' - 240: 7, # 'р' - 241: 8, # 'с' - 242: 5, # 'т' - 243: 19, # 'у' - 244: 29, # 'ф' - 245: 25, # 'х' - 246: 22, # 'ц' - 247: 21, # 'ч' - 248: 27, # 'ш' - 249: 24, # 'щ' - 250: 17, # 'ъ' - 251: 75, # 'ы' - 252: 52, # 'ь' - 253: 253, # 'э' - 254: 42, # 'ю' - 255: 16, # 'я' -} - -WINDOWS_1251_BULGARIAN_MODEL = SingleByteCharSetModel( - charset_name="windows-1251", - language="Bulgarian", - char_to_order_map=WINDOWS_1251_BULGARIAN_CHAR_TO_ORDER, - language_model=BULGARIAN_LANG_MODEL, - typical_positive_ratio=0.969392, - keep_ascii_letters=False, - alphabet="АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯабвгдежзийклмнопрстуфхцчшщъьюя", -) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langgreekmodel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langgreekmodel.py deleted file mode 100644 index cfb8639..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langgreekmodel.py +++ /dev/null @@ -1,4397 +0,0 @@ -from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel - -# 3: Positive -# 2: Likely -# 1: Unlikely -# 0: Negative - -GREEK_LANG_MODEL = { - 60: { # 'e' - 60: 2, # 'e' - 55: 1, # 'o' - 58: 2, # 't' - 36: 1, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 1, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 55: { # 'o' - 60: 0, # 'e' - 55: 2, # 'o' - 58: 2, # 't' - 36: 1, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 1, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 1, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 58: { # 't' - 60: 2, # 'e' - 55: 1, # 'o' - 58: 1, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 1, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 36: { # '·' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 61: { # 'Ά' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 1, # 'γ' - 21: 2, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 1, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 46: { # 'Έ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 2, # 'β' - 20: 2, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 2, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 0, # 'ο' - 9: 2, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 1, # 'σ' - 2: 2, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 3, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 54: { # 'Ό' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 2, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 2, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 2, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 2, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 31: { # 'Α' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 2, # 'Β' - 43: 2, # 'Γ' - 41: 1, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 2, # 'Θ' - 47: 2, # 'Ι' - 44: 2, # 'Κ' - 53: 2, # 'Λ' - 38: 2, # 'Μ' - 49: 2, # 'Ν' - 59: 1, # 'Ξ' - 39: 0, # 'Ο' - 35: 2, # 'Π' - 48: 2, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 2, # 'Υ' - 56: 2, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 2, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 1, # 'θ' - 5: 0, # 'ι' - 11: 2, # 'κ' - 16: 3, # 'λ' - 10: 2, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 0, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 2, # 'ς' - 7: 2, # 'σ' - 2: 0, # 'τ' - 12: 3, # 'υ' - 28: 2, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 2, # 'ύ' - 27: 0, # 'ώ' - }, - 51: { # 'Β' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 1, # 'Ε' - 40: 1, # 'Η' - 52: 0, # 'Θ' - 47: 1, # 'Ι' - 44: 0, # 'Κ' - 53: 1, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 2, # 'ή' - 15: 0, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 43: { # 'Γ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 1, # 'Α' - 51: 0, # 'Β' - 43: 2, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 1, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 1, # 'Κ' - 53: 1, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 1, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 2, # 'Υ' - 56: 0, # 'Φ' - 50: 1, # 'Χ' - 57: 2, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 2, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 41: { # 'Δ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 2, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 2, # 'ή' - 15: 2, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 2, # 'ω' - 19: 1, # 'ό' - 26: 2, # 'ύ' - 27: 2, # 'ώ' - }, - 34: { # 'Ε' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 2, # 'Γ' - 41: 2, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 2, # 'Κ' - 53: 2, # 'Λ' - 38: 2, # 'Μ' - 49: 2, # 'Ν' - 59: 1, # 'Ξ' - 39: 0, # 'Ο' - 35: 2, # 'Π' - 48: 2, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 2, # 'Υ' - 56: 0, # 'Φ' - 50: 2, # 'Χ' - 57: 2, # 'Ω' - 17: 3, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 3, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 3, # 'γ' - 21: 2, # 'δ' - 3: 1, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 1, # 'θ' - 5: 2, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 2, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 0, # 'ο' - 9: 3, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 2, # 'σ' - 2: 2, # 'τ' - 12: 2, # 'υ' - 28: 2, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 1, # 'ύ' - 27: 0, # 'ώ' - }, - 40: { # 'Η' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 1, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 2, # 'Θ' - 47: 0, # 'Ι' - 44: 2, # 'Κ' - 53: 0, # 'Λ' - 38: 2, # 'Μ' - 49: 2, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 2, # 'Π' - 48: 2, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 1, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 1, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 1, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 52: { # 'Θ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 1, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 1, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 2, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 2, # 'ύ' - 27: 0, # 'ώ' - }, - 47: { # 'Ι' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 1, # 'Β' - 43: 1, # 'Γ' - 41: 2, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 2, # 'Κ' - 53: 2, # 'Λ' - 38: 2, # 'Μ' - 49: 2, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 0, # 'Υ' - 56: 2, # 'Φ' - 50: 0, # 'Χ' - 57: 2, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 2, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 1, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 2, # 'σ' - 2: 1, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 1, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 44: { # 'Κ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 1, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 1, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 0, # 'Σ' - 33: 1, # 'Τ' - 45: 2, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 1, # 'Ω' - 17: 3, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 2, # 'ό' - 26: 2, # 'ύ' - 27: 2, # 'ώ' - }, - 53: { # 'Λ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 2, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 2, # 'Σ' - 33: 0, # 'Τ' - 45: 2, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 2, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 0, # 'ή' - 15: 2, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 1, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 2, # 'ό' - 26: 2, # 'ύ' - 27: 0, # 'ώ' - }, - 38: { # 'Μ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 2, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 2, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 2, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 2, # 'ή' - 15: 2, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 3, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 2, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 49: { # 'Ν' - 60: 2, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 2, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 2, # 'Ω' - 17: 0, # 'ά' - 18: 2, # 'έ' - 22: 0, # 'ή' - 15: 2, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 1, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 1, # 'ω' - 19: 2, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 59: { # 'Ξ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 1, # 'Ε' - 40: 1, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 1, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 2, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 39: { # 'Ο' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 1, # 'Β' - 43: 2, # 'Γ' - 41: 2, # 'Δ' - 34: 2, # 'Ε' - 40: 1, # 'Η' - 52: 2, # 'Θ' - 47: 2, # 'Ι' - 44: 2, # 'Κ' - 53: 2, # 'Λ' - 38: 2, # 'Μ' - 49: 2, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 2, # 'Π' - 48: 2, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 2, # 'Υ' - 56: 2, # 'Φ' - 50: 2, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 2, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 2, # 'κ' - 16: 2, # 'λ' - 10: 2, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 2, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 2, # 'τ' - 12: 2, # 'υ' - 28: 1, # 'φ' - 23: 1, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 2, # 'ύ' - 27: 0, # 'ώ' - }, - 35: { # 'Π' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 2, # 'Λ' - 38: 1, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 0, # 'Σ' - 33: 1, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 1, # 'Χ' - 57: 2, # 'Ω' - 17: 2, # 'ά' - 18: 1, # 'έ' - 22: 1, # 'ή' - 15: 2, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 2, # 'χ' - 42: 0, # 'ψ' - 24: 2, # 'ω' - 19: 2, # 'ό' - 26: 0, # 'ύ' - 27: 3, # 'ώ' - }, - 48: { # 'Ρ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 1, # 'Γ' - 41: 1, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 2, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 0, # 'Σ' - 33: 1, # 'Τ' - 45: 1, # 'Υ' - 56: 0, # 'Φ' - 50: 1, # 'Χ' - 57: 1, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 2, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 1, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 3, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 2, # 'ω' - 19: 0, # 'ό' - 26: 2, # 'ύ' - 27: 0, # 'ώ' - }, - 37: { # 'Σ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 1, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 2, # 'Κ' - 53: 0, # 'Λ' - 38: 2, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 2, # 'Υ' - 56: 0, # 'Φ' - 50: 2, # 'Χ' - 57: 2, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 2, # 'ή' - 15: 2, # 'ί' - 1: 2, # 'α' - 29: 2, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 2, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 2, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 0, # 'φ' - 23: 2, # 'χ' - 42: 0, # 'ψ' - 24: 2, # 'ω' - 19: 0, # 'ό' - 26: 2, # 'ύ' - 27: 2, # 'ώ' - }, - 33: { # 'Τ' - 60: 0, # 'e' - 55: 1, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 2, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 2, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 0, # 'Σ' - 33: 1, # 'Τ' - 45: 1, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 2, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 0, # 'ή' - 15: 2, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 2, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 2, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 2, # 'ό' - 26: 2, # 'ύ' - 27: 3, # 'ώ' - }, - 45: { # 'Υ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 2, # 'Γ' - 41: 0, # 'Δ' - 34: 1, # 'Ε' - 40: 2, # 'Η' - 52: 2, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 1, # 'Λ' - 38: 2, # 'Μ' - 49: 2, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 2, # 'Π' - 48: 1, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 1, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 3, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 56: { # 'Φ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 1, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 1, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 2, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 2, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 1, # 'ύ' - 27: 1, # 'ώ' - }, - 50: { # 'Χ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 1, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 2, # 'Ε' - 40: 2, # 'Η' - 52: 0, # 'Θ' - 47: 2, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 1, # 'Ν' - 59: 0, # 'Ξ' - 39: 1, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 1, # 'Χ' - 57: 1, # 'Ω' - 17: 2, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 2, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 2, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 2, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 57: { # 'Ω' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 1, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 1, # 'Λ' - 38: 0, # 'Μ' - 49: 2, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 2, # 'Ρ' - 37: 2, # 'Σ' - 33: 2, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 2, # 'ρ' - 14: 2, # 'ς' - 7: 2, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 1, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 17: { # 'ά' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 3, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 3, # 'ε' - 32: 3, # 'ζ' - 13: 0, # 'η' - 25: 3, # 'θ' - 5: 2, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 0, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 3, # 'φ' - 23: 3, # 'χ' - 42: 3, # 'ψ' - 24: 2, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 18: { # 'έ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 3, # 'α' - 29: 2, # 'β' - 20: 3, # 'γ' - 21: 2, # 'δ' - 3: 3, # 'ε' - 32: 2, # 'ζ' - 13: 0, # 'η' - 25: 3, # 'θ' - 5: 0, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 3, # 'φ' - 23: 3, # 'χ' - 42: 3, # 'ψ' - 24: 2, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 22: { # 'ή' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 1, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 3, # 'θ' - 5: 0, # 'ι' - 11: 3, # 'κ' - 16: 2, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 0, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 15: { # 'ί' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 3, # 'α' - 29: 2, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 3, # 'ε' - 32: 3, # 'ζ' - 13: 3, # 'η' - 25: 3, # 'θ' - 5: 0, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 1, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 3, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 1: { # 'α' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 2, # 'έ' - 22: 0, # 'ή' - 15: 3, # 'ί' - 1: 0, # 'α' - 29: 3, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 2, # 'ε' - 32: 3, # 'ζ' - 13: 1, # 'η' - 25: 3, # 'θ' - 5: 3, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 2, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 3, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 0, # 'ω' - 19: 2, # 'ό' - 26: 2, # 'ύ' - 27: 0, # 'ώ' - }, - 29: { # 'β' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 2, # 'έ' - 22: 3, # 'ή' - 15: 2, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 2, # 'γ' - 21: 2, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 3, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 2, # 'ω' - 19: 2, # 'ό' - 26: 2, # 'ύ' - 27: 2, # 'ώ' - }, - 20: { # 'γ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 3, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 3, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 2, # 'ύ' - 27: 3, # 'ώ' - }, - 21: { # 'δ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 3, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 3: { # 'ε' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 3, # 'ί' - 1: 2, # 'α' - 29: 3, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 2, # 'ε' - 32: 2, # 'ζ' - 13: 0, # 'η' - 25: 3, # 'θ' - 5: 3, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 2, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 3, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 3, # 'ω' - 19: 2, # 'ό' - 26: 3, # 'ύ' - 27: 2, # 'ώ' - }, - 32: { # 'ζ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 2, # 'ή' - 15: 2, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 1, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 2, # 'ό' - 26: 0, # 'ύ' - 27: 2, # 'ώ' - }, - 13: { # 'η' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 3, # 'γ' - 21: 2, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 3, # 'θ' - 5: 0, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 0, # 'ο' - 9: 2, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 25: { # 'θ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 2, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 1, # 'λ' - 10: 3, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 3, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 5: { # 'ι' - 60: 0, # 'e' - 55: 1, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 1, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 0, # 'ί' - 1: 3, # 'α' - 29: 3, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 3, # 'ε' - 32: 2, # 'ζ' - 13: 3, # 'η' - 25: 3, # 'θ' - 5: 0, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 0, # 'ύ' - 27: 3, # 'ώ' - }, - 11: { # 'κ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 3, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 2, # 'θ' - 5: 3, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 2, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 2, # 'φ' - 23: 2, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 16: { # 'λ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 1, # 'β' - 20: 2, # 'γ' - 21: 1, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 2, # 'θ' - 5: 3, # 'ι' - 11: 2, # 'κ' - 16: 3, # 'λ' - 10: 2, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 2, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 10: { # 'μ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 1, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 3, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 2, # 'υ' - 28: 3, # 'φ' - 23: 0, # 'χ' - 42: 2, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 2, # 'ύ' - 27: 2, # 'ώ' - }, - 6: { # 'ν' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 3, # 'δ' - 3: 3, # 'ε' - 32: 2, # 'ζ' - 13: 3, # 'η' - 25: 3, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 1, # 'λ' - 10: 0, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 30: { # 'ξ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 2, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 3, # 'τ' - 12: 2, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 2, # 'ό' - 26: 3, # 'ύ' - 27: 1, # 'ώ' - }, - 4: { # 'ο' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 2, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 2, # 'α' - 29: 3, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 3, # 'θ' - 5: 3, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 2, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 3, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 2, # 'ω' - 19: 1, # 'ό' - 26: 3, # 'ύ' - 27: 2, # 'ώ' - }, - 9: { # 'π' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 3, # 'λ' - 10: 0, # 'μ' - 6: 2, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 2, # 'ς' - 7: 0, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 0, # 'φ' - 23: 2, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 2, # 'ύ' - 27: 3, # 'ώ' - }, - 8: { # 'ρ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 2, # 'β' - 20: 3, # 'γ' - 21: 2, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 3, # 'θ' - 5: 3, # 'ι' - 11: 3, # 'κ' - 16: 1, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 3, # 'ο' - 9: 2, # 'π' - 8: 2, # 'ρ' - 14: 0, # 'ς' - 7: 2, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 3, # 'φ' - 23: 3, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 14: { # 'ς' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 2, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 0, # 'θ' - 5: 0, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 0, # 'τ' - 12: 0, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 7: { # 'σ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 3, # 'β' - 20: 0, # 'γ' - 21: 2, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 3, # 'θ' - 5: 3, # 'ι' - 11: 3, # 'κ' - 16: 2, # 'λ' - 10: 3, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 3, # 'φ' - 23: 3, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 2, # 'ώ' - }, - 2: { # 'τ' - 60: 0, # 'e' - 55: 2, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 2, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 3, # 'ι' - 11: 2, # 'κ' - 16: 2, # 'λ' - 10: 3, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 2, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 12: { # 'υ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 3, # 'ή' - 15: 2, # 'ί' - 1: 3, # 'α' - 29: 2, # 'β' - 20: 3, # 'γ' - 21: 2, # 'δ' - 3: 2, # 'ε' - 32: 2, # 'ζ' - 13: 2, # 'η' - 25: 3, # 'θ' - 5: 2, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 3, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 2, # 'ω' - 19: 2, # 'ό' - 26: 0, # 'ύ' - 27: 2, # 'ώ' - }, - 28: { # 'φ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 3, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 2, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 0, # 'μ' - 6: 1, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 1, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 2, # 'ύ' - 27: 2, # 'ώ' - }, - 23: { # 'χ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 3, # 'ά' - 18: 2, # 'έ' - 22: 3, # 'ή' - 15: 3, # 'ί' - 1: 3, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 2, # 'θ' - 5: 3, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 2, # 'μ' - 6: 3, # 'ν' - 30: 0, # 'ξ' - 4: 3, # 'ο' - 9: 0, # 'π' - 8: 3, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 3, # 'τ' - 12: 3, # 'υ' - 28: 0, # 'φ' - 23: 2, # 'χ' - 42: 0, # 'ψ' - 24: 3, # 'ω' - 19: 3, # 'ό' - 26: 3, # 'ύ' - 27: 3, # 'ώ' - }, - 42: { # 'ψ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 2, # 'ά' - 18: 2, # 'έ' - 22: 1, # 'ή' - 15: 2, # 'ί' - 1: 2, # 'α' - 29: 0, # 'β' - 20: 0, # 'γ' - 21: 0, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 3, # 'η' - 25: 0, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 0, # 'λ' - 10: 0, # 'μ' - 6: 0, # 'ν' - 30: 0, # 'ξ' - 4: 2, # 'ο' - 9: 0, # 'π' - 8: 0, # 'ρ' - 14: 0, # 'ς' - 7: 0, # 'σ' - 2: 2, # 'τ' - 12: 1, # 'υ' - 28: 0, # 'φ' - 23: 0, # 'χ' - 42: 0, # 'ψ' - 24: 2, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 24: { # 'ω' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 1, # 'ά' - 18: 0, # 'έ' - 22: 2, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 2, # 'β' - 20: 3, # 'γ' - 21: 2, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 0, # 'η' - 25: 3, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 0, # 'ξ' - 4: 0, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 2, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 19: { # 'ό' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 3, # 'β' - 20: 3, # 'γ' - 21: 3, # 'δ' - 3: 1, # 'ε' - 32: 2, # 'ζ' - 13: 2, # 'η' - 25: 2, # 'θ' - 5: 2, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 1, # 'ξ' - 4: 2, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 3, # 'χ' - 42: 2, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 26: { # 'ύ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 2, # 'α' - 29: 2, # 'β' - 20: 2, # 'γ' - 21: 1, # 'δ' - 3: 3, # 'ε' - 32: 0, # 'ζ' - 13: 2, # 'η' - 25: 3, # 'θ' - 5: 0, # 'ι' - 11: 3, # 'κ' - 16: 3, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 2, # 'ξ' - 4: 3, # 'ο' - 9: 3, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 2, # 'φ' - 23: 2, # 'χ' - 42: 2, # 'ψ' - 24: 2, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, - 27: { # 'ώ' - 60: 0, # 'e' - 55: 0, # 'o' - 58: 0, # 't' - 36: 0, # '·' - 61: 0, # 'Ά' - 46: 0, # 'Έ' - 54: 0, # 'Ό' - 31: 0, # 'Α' - 51: 0, # 'Β' - 43: 0, # 'Γ' - 41: 0, # 'Δ' - 34: 0, # 'Ε' - 40: 0, # 'Η' - 52: 0, # 'Θ' - 47: 0, # 'Ι' - 44: 0, # 'Κ' - 53: 0, # 'Λ' - 38: 0, # 'Μ' - 49: 0, # 'Ν' - 59: 0, # 'Ξ' - 39: 0, # 'Ο' - 35: 0, # 'Π' - 48: 0, # 'Ρ' - 37: 0, # 'Σ' - 33: 0, # 'Τ' - 45: 0, # 'Υ' - 56: 0, # 'Φ' - 50: 0, # 'Χ' - 57: 0, # 'Ω' - 17: 0, # 'ά' - 18: 0, # 'έ' - 22: 0, # 'ή' - 15: 0, # 'ί' - 1: 0, # 'α' - 29: 1, # 'β' - 20: 0, # 'γ' - 21: 3, # 'δ' - 3: 0, # 'ε' - 32: 0, # 'ζ' - 13: 1, # 'η' - 25: 2, # 'θ' - 5: 2, # 'ι' - 11: 0, # 'κ' - 16: 2, # 'λ' - 10: 3, # 'μ' - 6: 3, # 'ν' - 30: 1, # 'ξ' - 4: 0, # 'ο' - 9: 2, # 'π' - 8: 3, # 'ρ' - 14: 3, # 'ς' - 7: 3, # 'σ' - 2: 3, # 'τ' - 12: 0, # 'υ' - 28: 1, # 'φ' - 23: 1, # 'χ' - 42: 0, # 'ψ' - 24: 0, # 'ω' - 19: 0, # 'ό' - 26: 0, # 'ύ' - 27: 0, # 'ώ' - }, -} - -# 255: Undefined characters that did not exist in training text -# 254: Carriage/Return -# 253: symbol (punctuation) that does not belong to word -# 252: 0 - 9 -# 251: Control characters - -# Character Mapping Table(s): -WINDOWS_1253_GREEK_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 82, # 'A' - 66: 100, # 'B' - 67: 104, # 'C' - 68: 94, # 'D' - 69: 98, # 'E' - 70: 101, # 'F' - 71: 116, # 'G' - 72: 102, # 'H' - 73: 111, # 'I' - 74: 187, # 'J' - 75: 117, # 'K' - 76: 92, # 'L' - 77: 88, # 'M' - 78: 113, # 'N' - 79: 85, # 'O' - 80: 79, # 'P' - 81: 118, # 'Q' - 82: 105, # 'R' - 83: 83, # 'S' - 84: 67, # 'T' - 85: 114, # 'U' - 86: 119, # 'V' - 87: 95, # 'W' - 88: 99, # 'X' - 89: 109, # 'Y' - 90: 188, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 72, # 'a' - 98: 70, # 'b' - 99: 80, # 'c' - 100: 81, # 'd' - 101: 60, # 'e' - 102: 96, # 'f' - 103: 93, # 'g' - 104: 89, # 'h' - 105: 68, # 'i' - 106: 120, # 'j' - 107: 97, # 'k' - 108: 77, # 'l' - 109: 86, # 'm' - 110: 69, # 'n' - 111: 55, # 'o' - 112: 78, # 'p' - 113: 115, # 'q' - 114: 65, # 'r' - 115: 66, # 's' - 116: 58, # 't' - 117: 76, # 'u' - 118: 106, # 'v' - 119: 103, # 'w' - 120: 87, # 'x' - 121: 107, # 'y' - 122: 112, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 255, # '€' - 129: 255, # None - 130: 255, # '‚' - 131: 255, # 'ƒ' - 132: 255, # '„' - 133: 255, # '…' - 134: 255, # '†' - 135: 255, # '‡' - 136: 255, # None - 137: 255, # '‰' - 138: 255, # None - 139: 255, # '‹' - 140: 255, # None - 141: 255, # None - 142: 255, # None - 143: 255, # None - 144: 255, # None - 145: 255, # '‘' - 146: 255, # '’' - 147: 255, # '“' - 148: 255, # '”' - 149: 255, # '•' - 150: 255, # '–' - 151: 255, # '—' - 152: 255, # None - 153: 255, # '™' - 154: 255, # None - 155: 255, # '›' - 156: 255, # None - 157: 255, # None - 158: 255, # None - 159: 255, # None - 160: 253, # '\xa0' - 161: 233, # '΅' - 162: 61, # 'Ά' - 163: 253, # '£' - 164: 253, # '¤' - 165: 253, # '¥' - 166: 253, # '¦' - 167: 253, # '§' - 168: 253, # '¨' - 169: 253, # '©' - 170: 253, # None - 171: 253, # '«' - 172: 253, # '¬' - 173: 74, # '\xad' - 174: 253, # '®' - 175: 253, # '―' - 176: 253, # '°' - 177: 253, # '±' - 178: 253, # '²' - 179: 253, # '³' - 180: 247, # '΄' - 181: 253, # 'µ' - 182: 253, # '¶' - 183: 36, # '·' - 184: 46, # 'Έ' - 185: 71, # 'Ή' - 186: 73, # 'Ί' - 187: 253, # '»' - 188: 54, # 'Ό' - 189: 253, # '½' - 190: 108, # 'Ύ' - 191: 123, # 'Ώ' - 192: 110, # 'ΐ' - 193: 31, # 'Α' - 194: 51, # 'Β' - 195: 43, # 'Γ' - 196: 41, # 'Δ' - 197: 34, # 'Ε' - 198: 91, # 'Ζ' - 199: 40, # 'Η' - 200: 52, # 'Θ' - 201: 47, # 'Ι' - 202: 44, # 'Κ' - 203: 53, # 'Λ' - 204: 38, # 'Μ' - 205: 49, # 'Ν' - 206: 59, # 'Ξ' - 207: 39, # 'Ο' - 208: 35, # 'Π' - 209: 48, # 'Ρ' - 210: 250, # None - 211: 37, # 'Σ' - 212: 33, # 'Τ' - 213: 45, # 'Υ' - 214: 56, # 'Φ' - 215: 50, # 'Χ' - 216: 84, # 'Ψ' - 217: 57, # 'Ω' - 218: 120, # 'Ϊ' - 219: 121, # 'Ϋ' - 220: 17, # 'ά' - 221: 18, # 'έ' - 222: 22, # 'ή' - 223: 15, # 'ί' - 224: 124, # 'ΰ' - 225: 1, # 'α' - 226: 29, # 'β' - 227: 20, # 'γ' - 228: 21, # 'δ' - 229: 3, # 'ε' - 230: 32, # 'ζ' - 231: 13, # 'η' - 232: 25, # 'θ' - 233: 5, # 'ι' - 234: 11, # 'κ' - 235: 16, # 'λ' - 236: 10, # 'μ' - 237: 6, # 'ν' - 238: 30, # 'ξ' - 239: 4, # 'ο' - 240: 9, # 'π' - 241: 8, # 'ρ' - 242: 14, # 'ς' - 243: 7, # 'σ' - 244: 2, # 'τ' - 245: 12, # 'υ' - 246: 28, # 'φ' - 247: 23, # 'χ' - 248: 42, # 'ψ' - 249: 24, # 'ω' - 250: 64, # 'ϊ' - 251: 75, # 'ϋ' - 252: 19, # 'ό' - 253: 26, # 'ύ' - 254: 27, # 'ώ' - 255: 253, # None -} - -WINDOWS_1253_GREEK_MODEL = SingleByteCharSetModel( - charset_name="windows-1253", - language="Greek", - char_to_order_map=WINDOWS_1253_GREEK_CHAR_TO_ORDER, - language_model=GREEK_LANG_MODEL, - typical_positive_ratio=0.982851, - keep_ascii_letters=False, - alphabet="ΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩάέήίαβγδεζηθικλμνξοπρςστυφχψωόύώ", -) - -ISO_8859_7_GREEK_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 82, # 'A' - 66: 100, # 'B' - 67: 104, # 'C' - 68: 94, # 'D' - 69: 98, # 'E' - 70: 101, # 'F' - 71: 116, # 'G' - 72: 102, # 'H' - 73: 111, # 'I' - 74: 187, # 'J' - 75: 117, # 'K' - 76: 92, # 'L' - 77: 88, # 'M' - 78: 113, # 'N' - 79: 85, # 'O' - 80: 79, # 'P' - 81: 118, # 'Q' - 82: 105, # 'R' - 83: 83, # 'S' - 84: 67, # 'T' - 85: 114, # 'U' - 86: 119, # 'V' - 87: 95, # 'W' - 88: 99, # 'X' - 89: 109, # 'Y' - 90: 188, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 72, # 'a' - 98: 70, # 'b' - 99: 80, # 'c' - 100: 81, # 'd' - 101: 60, # 'e' - 102: 96, # 'f' - 103: 93, # 'g' - 104: 89, # 'h' - 105: 68, # 'i' - 106: 120, # 'j' - 107: 97, # 'k' - 108: 77, # 'l' - 109: 86, # 'm' - 110: 69, # 'n' - 111: 55, # 'o' - 112: 78, # 'p' - 113: 115, # 'q' - 114: 65, # 'r' - 115: 66, # 's' - 116: 58, # 't' - 117: 76, # 'u' - 118: 106, # 'v' - 119: 103, # 'w' - 120: 87, # 'x' - 121: 107, # 'y' - 122: 112, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 255, # '\x80' - 129: 255, # '\x81' - 130: 255, # '\x82' - 131: 255, # '\x83' - 132: 255, # '\x84' - 133: 255, # '\x85' - 134: 255, # '\x86' - 135: 255, # '\x87' - 136: 255, # '\x88' - 137: 255, # '\x89' - 138: 255, # '\x8a' - 139: 255, # '\x8b' - 140: 255, # '\x8c' - 141: 255, # '\x8d' - 142: 255, # '\x8e' - 143: 255, # '\x8f' - 144: 255, # '\x90' - 145: 255, # '\x91' - 146: 255, # '\x92' - 147: 255, # '\x93' - 148: 255, # '\x94' - 149: 255, # '\x95' - 150: 255, # '\x96' - 151: 255, # '\x97' - 152: 255, # '\x98' - 153: 255, # '\x99' - 154: 255, # '\x9a' - 155: 255, # '\x9b' - 156: 255, # '\x9c' - 157: 255, # '\x9d' - 158: 255, # '\x9e' - 159: 255, # '\x9f' - 160: 253, # '\xa0' - 161: 233, # '‘' - 162: 90, # '’' - 163: 253, # '£' - 164: 253, # '€' - 165: 253, # '₯' - 166: 253, # '¦' - 167: 253, # '§' - 168: 253, # '¨' - 169: 253, # '©' - 170: 253, # 'ͺ' - 171: 253, # '«' - 172: 253, # '¬' - 173: 74, # '\xad' - 174: 253, # None - 175: 253, # '―' - 176: 253, # '°' - 177: 253, # '±' - 178: 253, # '²' - 179: 253, # '³' - 180: 247, # '΄' - 181: 248, # '΅' - 182: 61, # 'Ά' - 183: 36, # '·' - 184: 46, # 'Έ' - 185: 71, # 'Ή' - 186: 73, # 'Ί' - 187: 253, # '»' - 188: 54, # 'Ό' - 189: 253, # '½' - 190: 108, # 'Ύ' - 191: 123, # 'Ώ' - 192: 110, # 'ΐ' - 193: 31, # 'Α' - 194: 51, # 'Β' - 195: 43, # 'Γ' - 196: 41, # 'Δ' - 197: 34, # 'Ε' - 198: 91, # 'Ζ' - 199: 40, # 'Η' - 200: 52, # 'Θ' - 201: 47, # 'Ι' - 202: 44, # 'Κ' - 203: 53, # 'Λ' - 204: 38, # 'Μ' - 205: 49, # 'Ν' - 206: 59, # 'Ξ' - 207: 39, # 'Ο' - 208: 35, # 'Π' - 209: 48, # 'Ρ' - 210: 250, # None - 211: 37, # 'Σ' - 212: 33, # 'Τ' - 213: 45, # 'Υ' - 214: 56, # 'Φ' - 215: 50, # 'Χ' - 216: 84, # 'Ψ' - 217: 57, # 'Ω' - 218: 120, # 'Ϊ' - 219: 121, # 'Ϋ' - 220: 17, # 'ά' - 221: 18, # 'έ' - 222: 22, # 'ή' - 223: 15, # 'ί' - 224: 124, # 'ΰ' - 225: 1, # 'α' - 226: 29, # 'β' - 227: 20, # 'γ' - 228: 21, # 'δ' - 229: 3, # 'ε' - 230: 32, # 'ζ' - 231: 13, # 'η' - 232: 25, # 'θ' - 233: 5, # 'ι' - 234: 11, # 'κ' - 235: 16, # 'λ' - 236: 10, # 'μ' - 237: 6, # 'ν' - 238: 30, # 'ξ' - 239: 4, # 'ο' - 240: 9, # 'π' - 241: 8, # 'ρ' - 242: 14, # 'ς' - 243: 7, # 'σ' - 244: 2, # 'τ' - 245: 12, # 'υ' - 246: 28, # 'φ' - 247: 23, # 'χ' - 248: 42, # 'ψ' - 249: 24, # 'ω' - 250: 64, # 'ϊ' - 251: 75, # 'ϋ' - 252: 19, # 'ό' - 253: 26, # 'ύ' - 254: 27, # 'ώ' - 255: 253, # None -} - -ISO_8859_7_GREEK_MODEL = SingleByteCharSetModel( - charset_name="ISO-8859-7", - language="Greek", - char_to_order_map=ISO_8859_7_GREEK_CHAR_TO_ORDER, - language_model=GREEK_LANG_MODEL, - typical_positive_ratio=0.982851, - keep_ascii_letters=False, - alphabet="ΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩάέήίαβγδεζηθικλμνξοπρςστυφχψωόύώ", -) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langhebrewmodel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langhebrewmodel.py deleted file mode 100644 index 56d2975..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langhebrewmodel.py +++ /dev/null @@ -1,4380 +0,0 @@ -from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel - -# 3: Positive -# 2: Likely -# 1: Unlikely -# 0: Negative - -HEBREW_LANG_MODEL = { - 50: { # 'a' - 50: 0, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 2, # 'l' - 54: 2, # 'n' - 49: 0, # 'o' - 51: 2, # 'r' - 43: 1, # 's' - 44: 2, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 1, # 'ק' - 7: 0, # 'ר' - 10: 1, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 60: { # 'c' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 0, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 0, # 'n' - 49: 1, # 'o' - 51: 1, # 'r' - 43: 1, # 's' - 44: 2, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 61: { # 'd' - 50: 1, # 'a' - 60: 0, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 1, # 'n' - 49: 2, # 'o' - 51: 1, # 'r' - 43: 1, # 's' - 44: 0, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 1, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 42: { # 'e' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 2, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 2, # 'l' - 54: 2, # 'n' - 49: 1, # 'o' - 51: 2, # 'r' - 43: 2, # 's' - 44: 2, # 't' - 63: 1, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 1, # '–' - 52: 2, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 53: { # 'i' - 50: 1, # 'a' - 60: 2, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 0, # 'i' - 56: 1, # 'l' - 54: 2, # 'n' - 49: 2, # 'o' - 51: 1, # 'r' - 43: 2, # 's' - 44: 2, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 56: { # 'l' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 2, # 'e' - 53: 2, # 'i' - 56: 2, # 'l' - 54: 1, # 'n' - 49: 1, # 'o' - 51: 0, # 'r' - 43: 1, # 's' - 44: 1, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 54: { # 'n' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 1, # 'n' - 49: 1, # 'o' - 51: 0, # 'r' - 43: 1, # 's' - 44: 2, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 2, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 49: { # 'o' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 2, # 'n' - 49: 1, # 'o' - 51: 2, # 'r' - 43: 1, # 's' - 44: 1, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 51: { # 'r' - 50: 2, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 2, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 1, # 'n' - 49: 2, # 'o' - 51: 1, # 'r' - 43: 1, # 's' - 44: 1, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 2, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 43: { # 's' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 0, # 'd' - 42: 2, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 1, # 'n' - 49: 1, # 'o' - 51: 1, # 'r' - 43: 1, # 's' - 44: 2, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 2, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 44: { # 't' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 0, # 'd' - 42: 2, # 'e' - 53: 2, # 'i' - 56: 1, # 'l' - 54: 0, # 'n' - 49: 1, # 'o' - 51: 1, # 'r' - 43: 1, # 's' - 44: 1, # 't' - 63: 1, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 2, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 63: { # 'u' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 1, # 'n' - 49: 0, # 'o' - 51: 1, # 'r' - 43: 2, # 's' - 44: 1, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 34: { # '\xa0' - 50: 1, # 'a' - 60: 0, # 'c' - 61: 1, # 'd' - 42: 0, # 'e' - 53: 1, # 'i' - 56: 0, # 'l' - 54: 1, # 'n' - 49: 1, # 'o' - 51: 0, # 'r' - 43: 1, # 's' - 44: 1, # 't' - 63: 0, # 'u' - 34: 2, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 1, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 1, # 'ח' - 22: 1, # 'ט' - 1: 2, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 2, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 1, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 55: { # '´' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 1, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 2, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 1, # 'ן' - 12: 1, # 'נ' - 19: 1, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 48: { # '¼' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 1, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 39: { # '½' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 57: { # '¾' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 30: { # 'ְ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 1, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 1, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 2, # 'ב' - 20: 2, # 'ג' - 16: 2, # 'ד' - 3: 2, # 'ה' - 2: 2, # 'ו' - 24: 2, # 'ז' - 14: 2, # 'ח' - 22: 2, # 'ט' - 1: 2, # 'י' - 25: 2, # 'ך' - 15: 2, # 'כ' - 4: 2, # 'ל' - 11: 1, # 'ם' - 6: 2, # 'מ' - 23: 0, # 'ן' - 12: 2, # 'נ' - 19: 2, # 'ס' - 13: 2, # 'ע' - 26: 0, # 'ף' - 18: 2, # 'פ' - 27: 0, # 'ץ' - 21: 2, # 'צ' - 17: 2, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 59: { # 'ֱ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 1, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 1, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 2, # 'ל' - 11: 0, # 'ם' - 6: 2, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 41: { # 'ֲ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 2, # 'ב' - 20: 1, # 'ג' - 16: 2, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 1, # 'ח' - 22: 1, # 'ט' - 1: 1, # 'י' - 25: 1, # 'ך' - 15: 1, # 'כ' - 4: 2, # 'ל' - 11: 0, # 'ם' - 6: 2, # 'מ' - 23: 0, # 'ן' - 12: 2, # 'נ' - 19: 1, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 2, # 'צ' - 17: 1, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 33: { # 'ִ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 1, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 1, # 'ִ' - 37: 0, # 'ֵ' - 36: 1, # 'ֶ' - 31: 0, # 'ַ' - 29: 1, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 1, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 2, # 'ב' - 20: 2, # 'ג' - 16: 2, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 2, # 'ז' - 14: 1, # 'ח' - 22: 1, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 2, # 'כ' - 4: 2, # 'ל' - 11: 2, # 'ם' - 6: 2, # 'מ' - 23: 2, # 'ן' - 12: 2, # 'נ' - 19: 2, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 2, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 2, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 37: { # 'ֵ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 1, # 'ֶ' - 31: 1, # 'ַ' - 29: 1, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 2, # 'ב' - 20: 1, # 'ג' - 16: 2, # 'ד' - 3: 2, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 2, # 'ח' - 22: 1, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 1, # 'כ' - 4: 2, # 'ל' - 11: 2, # 'ם' - 6: 1, # 'מ' - 23: 2, # 'ן' - 12: 2, # 'נ' - 19: 1, # 'ס' - 13: 2, # 'ע' - 26: 1, # 'ף' - 18: 1, # 'פ' - 27: 1, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 36: { # 'ֶ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 1, # 'ֶ' - 31: 1, # 'ַ' - 29: 1, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 2, # 'ב' - 20: 1, # 'ג' - 16: 2, # 'ד' - 3: 2, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 2, # 'ח' - 22: 1, # 'ט' - 1: 2, # 'י' - 25: 2, # 'ך' - 15: 1, # 'כ' - 4: 2, # 'ל' - 11: 2, # 'ם' - 6: 2, # 'מ' - 23: 2, # 'ן' - 12: 2, # 'נ' - 19: 2, # 'ס' - 13: 1, # 'ע' - 26: 1, # 'ף' - 18: 1, # 'פ' - 27: 2, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 31: { # 'ַ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 1, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 1, # 'ֶ' - 31: 0, # 'ַ' - 29: 2, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 2, # 'ב' - 20: 2, # 'ג' - 16: 2, # 'ד' - 3: 2, # 'ה' - 2: 1, # 'ו' - 24: 2, # 'ז' - 14: 2, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 2, # 'כ' - 4: 2, # 'ל' - 11: 2, # 'ם' - 6: 2, # 'מ' - 23: 2, # 'ן' - 12: 2, # 'נ' - 19: 2, # 'ס' - 13: 2, # 'ע' - 26: 2, # 'ף' - 18: 2, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 2, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 29: { # 'ָ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 1, # 'ַ' - 29: 2, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 1, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 2, # 'ב' - 20: 2, # 'ג' - 16: 2, # 'ד' - 3: 3, # 'ה' - 2: 2, # 'ו' - 24: 2, # 'ז' - 14: 2, # 'ח' - 22: 1, # 'ט' - 1: 2, # 'י' - 25: 2, # 'ך' - 15: 2, # 'כ' - 4: 2, # 'ל' - 11: 2, # 'ם' - 6: 2, # 'מ' - 23: 2, # 'ן' - 12: 2, # 'נ' - 19: 1, # 'ס' - 13: 2, # 'ע' - 26: 1, # 'ף' - 18: 2, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 2, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 35: { # 'ֹ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 1, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 2, # 'ב' - 20: 1, # 'ג' - 16: 2, # 'ד' - 3: 2, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 1, # 'ח' - 22: 1, # 'ט' - 1: 1, # 'י' - 25: 1, # 'ך' - 15: 2, # 'כ' - 4: 2, # 'ל' - 11: 2, # 'ם' - 6: 2, # 'מ' - 23: 2, # 'ן' - 12: 2, # 'נ' - 19: 2, # 'ס' - 13: 2, # 'ע' - 26: 1, # 'ף' - 18: 2, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 2, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 62: { # 'ֻ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 1, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 1, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 2, # 'ל' - 11: 1, # 'ם' - 6: 1, # 'מ' - 23: 1, # 'ן' - 12: 1, # 'נ' - 19: 1, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 28: { # 'ּ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 3, # 'ְ' - 59: 0, # 'ֱ' - 41: 1, # 'ֲ' - 33: 3, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 3, # 'ַ' - 29: 3, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 0, # 'ּ' - 38: 2, # 'ׁ' - 45: 1, # 'ׂ' - 9: 2, # 'א' - 8: 2, # 'ב' - 20: 1, # 'ג' - 16: 2, # 'ד' - 3: 1, # 'ה' - 2: 2, # 'ו' - 24: 1, # 'ז' - 14: 1, # 'ח' - 22: 1, # 'ט' - 1: 2, # 'י' - 25: 2, # 'ך' - 15: 2, # 'כ' - 4: 2, # 'ל' - 11: 1, # 'ם' - 6: 2, # 'מ' - 23: 1, # 'ן' - 12: 2, # 'נ' - 19: 1, # 'ס' - 13: 2, # 'ע' - 26: 1, # 'ף' - 18: 1, # 'פ' - 27: 1, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 2, # 'ר' - 10: 2, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 38: { # 'ׁ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 2, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 45: { # 'ׂ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 1, # 'ֵ' - 36: 2, # 'ֶ' - 31: 1, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 1, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 2, # 'ו' - 24: 0, # 'ז' - 14: 1, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 1, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 0, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 1, # 'ר' - 10: 0, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 9: { # 'א' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 1, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 2, # 'ֱ' - 41: 2, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 3, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 2, # 'ע' - 26: 3, # 'ף' - 18: 3, # 'פ' - 27: 1, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 8: { # 'ב' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 1, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 3, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 2, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 1, # 'ף' - 18: 3, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 1, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 20: { # 'ג' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 2, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 1, # 'ִ' - 37: 1, # 'ֵ' - 36: 1, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 0, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 3, # 'ב' - 20: 2, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 2, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 1, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 2, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 2, # 'פ' - 27: 1, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 16: { # 'ד' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 1, # 'ז' - 14: 2, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 2, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 2, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 0, # 'ץ' - 21: 2, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 3: { # 'ה' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 1, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 1, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 1, # 'ְ' - 59: 1, # 'ֱ' - 41: 2, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 3, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 0, # 'ף' - 18: 3, # 'פ' - 27: 1, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 1, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 2: { # 'ו' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 1, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 1, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 1, # 'ֵ' - 36: 1, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 3, # 'ֹ' - 62: 0, # 'ֻ' - 28: 3, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 3, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 3, # 'ף' - 18: 3, # 'פ' - 27: 3, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 1, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 24: { # 'ז' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 1, # 'ֲ' - 33: 1, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 2, # 'ב' - 20: 2, # 'ג' - 16: 2, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 2, # 'ז' - 14: 2, # 'ח' - 22: 1, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 2, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 2, # 'נ' - 19: 1, # 'ס' - 13: 2, # 'ע' - 26: 1, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 2, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 1, # 'ש' - 5: 2, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 14: { # 'ח' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 1, # 'ֱ' - 41: 2, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 3, # 'ב' - 20: 2, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 2, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 2, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 1, # 'ע' - 26: 2, # 'ף' - 18: 2, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 22: { # 'ט' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 1, # 'ֵ' - 36: 1, # 'ֶ' - 31: 2, # 'ַ' - 29: 1, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 1, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 1, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 2, # 'ז' - 14: 3, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 2, # 'כ' - 4: 3, # 'ל' - 11: 2, # 'ם' - 6: 2, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 2, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 2, # 'ק' - 7: 3, # 'ר' - 10: 2, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 1: { # 'י' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 1, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 1, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 3, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 3, # 'ף' - 18: 3, # 'פ' - 27: 3, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 1, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 25: { # 'ך' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 2, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 1, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 1, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 1, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 15: { # 'כ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 3, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 2, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 3, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 2, # 'ע' - 26: 3, # 'ף' - 18: 3, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 2, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 4: { # 'ל' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 3, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 3, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 1, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 11: { # 'ם' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 1, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 1, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 0, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 1, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 6: { # 'מ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 0, # 'ף' - 18: 3, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 23: { # 'ן' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 1, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 1, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 0, # 'ז' - 14: 1, # 'ח' - 22: 1, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 1, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 1, # 'ס' - 13: 1, # 'ע' - 26: 1, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 1, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 1, # 'ת' - 32: 1, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 12: { # 'נ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 19: { # 'ס' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 1, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 1, # 'ָ' - 35: 1, # 'ֹ' - 62: 2, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 1, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 2, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 2, # 'ס' - 13: 3, # 'ע' - 26: 3, # 'ף' - 18: 3, # 'פ' - 27: 0, # 'ץ' - 21: 2, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 1, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 13: { # 'ע' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 1, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 1, # 'ְ' - 59: 1, # 'ֱ' - 41: 2, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 1, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 2, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 2, # 'ע' - 26: 1, # 'ף' - 18: 2, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 26: { # 'ף' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 1, # 'ו' - 24: 0, # 'ז' - 14: 1, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 1, # 'ס' - 13: 0, # 'ע' - 26: 1, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 1, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 18: { # 'פ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 1, # 'ֵ' - 36: 2, # 'ֶ' - 31: 1, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 2, # 'ב' - 20: 3, # 'ג' - 16: 2, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 2, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 2, # 'ם' - 6: 2, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 2, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 27: { # 'ץ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 1, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 1, # 'ר' - 10: 0, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 21: { # 'צ' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 1, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 2, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 1, # 'ז' - 14: 3, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 1, # 'כ' - 4: 3, # 'ל' - 11: 2, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 1, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 2, # 'ץ' - 21: 2, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 0, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 17: { # 'ק' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 1, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 1, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 2, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 2, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 1, # 'ך' - 15: 1, # 'כ' - 4: 3, # 'ל' - 11: 2, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 2, # 'ץ' - 21: 3, # 'צ' - 17: 2, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 7: { # 'ר' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 2, # '´' - 48: 1, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 1, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 2, # 'ֹ' - 62: 1, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 3, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 3, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 3, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 3, # 'ץ' - 21: 3, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 10: { # 'ש' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 1, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 1, # 'ִ' - 37: 1, # 'ֵ' - 36: 1, # 'ֶ' - 31: 1, # 'ַ' - 29: 1, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 3, # 'ׁ' - 45: 2, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 3, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 2, # 'ז' - 14: 3, # 'ח' - 22: 3, # 'ט' - 1: 3, # 'י' - 25: 3, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 2, # 'ן' - 12: 3, # 'נ' - 19: 2, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 1, # '…' - }, - 5: { # 'ת' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 1, # '\xa0' - 55: 0, # '´' - 48: 1, # '¼' - 39: 1, # '½' - 57: 0, # '¾' - 30: 2, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 2, # 'ִ' - 37: 2, # 'ֵ' - 36: 2, # 'ֶ' - 31: 2, # 'ַ' - 29: 2, # 'ָ' - 35: 1, # 'ֹ' - 62: 1, # 'ֻ' - 28: 2, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 3, # 'א' - 8: 3, # 'ב' - 20: 3, # 'ג' - 16: 2, # 'ד' - 3: 3, # 'ה' - 2: 3, # 'ו' - 24: 2, # 'ז' - 14: 3, # 'ח' - 22: 2, # 'ט' - 1: 3, # 'י' - 25: 2, # 'ך' - 15: 3, # 'כ' - 4: 3, # 'ל' - 11: 3, # 'ם' - 6: 3, # 'מ' - 23: 3, # 'ן' - 12: 3, # 'נ' - 19: 2, # 'ס' - 13: 3, # 'ע' - 26: 2, # 'ף' - 18: 3, # 'פ' - 27: 1, # 'ץ' - 21: 2, # 'צ' - 17: 3, # 'ק' - 7: 3, # 'ר' - 10: 3, # 'ש' - 5: 3, # 'ת' - 32: 1, # '–' - 52: 1, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, - 32: { # '–' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 1, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 1, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 0, # 'ז' - 14: 1, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 1, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 1, # 'צ' - 17: 0, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 52: { # '’' - 50: 1, # 'a' - 60: 0, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 1, # 'r' - 43: 2, # 's' - 44: 2, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 1, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 47: { # '“' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 1, # 'l' - 54: 1, # 'n' - 49: 1, # 'o' - 51: 1, # 'r' - 43: 1, # 's' - 44: 1, # 't' - 63: 1, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 2, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 1, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 1, # 'ח' - 22: 1, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 1, # 'ס' - 13: 1, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 1, # 'צ' - 17: 1, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 46: { # '”' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 1, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 1, # 'ב' - 20: 1, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 1, # 'צ' - 17: 0, # 'ק' - 7: 1, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 0, # '†' - 40: 0, # '…' - }, - 58: { # '†' - 50: 0, # 'a' - 60: 0, # 'c' - 61: 0, # 'd' - 42: 0, # 'e' - 53: 0, # 'i' - 56: 0, # 'l' - 54: 0, # 'n' - 49: 0, # 'o' - 51: 0, # 'r' - 43: 0, # 's' - 44: 0, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 0, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 0, # 'ה' - 2: 0, # 'ו' - 24: 0, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 0, # 'י' - 25: 0, # 'ך' - 15: 0, # 'כ' - 4: 0, # 'ל' - 11: 0, # 'ם' - 6: 0, # 'מ' - 23: 0, # 'ן' - 12: 0, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 0, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 0, # 'ר' - 10: 0, # 'ש' - 5: 0, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 0, # '”' - 58: 2, # '†' - 40: 0, # '…' - }, - 40: { # '…' - 50: 1, # 'a' - 60: 1, # 'c' - 61: 1, # 'd' - 42: 1, # 'e' - 53: 1, # 'i' - 56: 0, # 'l' - 54: 1, # 'n' - 49: 0, # 'o' - 51: 1, # 'r' - 43: 1, # 's' - 44: 1, # 't' - 63: 0, # 'u' - 34: 0, # '\xa0' - 55: 0, # '´' - 48: 0, # '¼' - 39: 0, # '½' - 57: 0, # '¾' - 30: 0, # 'ְ' - 59: 0, # 'ֱ' - 41: 0, # 'ֲ' - 33: 0, # 'ִ' - 37: 0, # 'ֵ' - 36: 0, # 'ֶ' - 31: 0, # 'ַ' - 29: 0, # 'ָ' - 35: 0, # 'ֹ' - 62: 0, # 'ֻ' - 28: 0, # 'ּ' - 38: 0, # 'ׁ' - 45: 0, # 'ׂ' - 9: 1, # 'א' - 8: 0, # 'ב' - 20: 0, # 'ג' - 16: 0, # 'ד' - 3: 1, # 'ה' - 2: 1, # 'ו' - 24: 1, # 'ז' - 14: 0, # 'ח' - 22: 0, # 'ט' - 1: 1, # 'י' - 25: 0, # 'ך' - 15: 1, # 'כ' - 4: 1, # 'ל' - 11: 0, # 'ם' - 6: 1, # 'מ' - 23: 0, # 'ן' - 12: 1, # 'נ' - 19: 0, # 'ס' - 13: 0, # 'ע' - 26: 0, # 'ף' - 18: 1, # 'פ' - 27: 0, # 'ץ' - 21: 0, # 'צ' - 17: 0, # 'ק' - 7: 1, # 'ר' - 10: 1, # 'ש' - 5: 1, # 'ת' - 32: 0, # '–' - 52: 0, # '’' - 47: 0, # '“' - 46: 1, # '”' - 58: 0, # '†' - 40: 2, # '…' - }, -} - -# 255: Undefined characters that did not exist in training text -# 254: Carriage/Return -# 253: symbol (punctuation) that does not belong to word -# 252: 0 - 9 -# 251: Control characters - -# Character Mapping Table(s): -WINDOWS_1255_HEBREW_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 69, # 'A' - 66: 91, # 'B' - 67: 79, # 'C' - 68: 80, # 'D' - 69: 92, # 'E' - 70: 89, # 'F' - 71: 97, # 'G' - 72: 90, # 'H' - 73: 68, # 'I' - 74: 111, # 'J' - 75: 112, # 'K' - 76: 82, # 'L' - 77: 73, # 'M' - 78: 95, # 'N' - 79: 85, # 'O' - 80: 78, # 'P' - 81: 121, # 'Q' - 82: 86, # 'R' - 83: 71, # 'S' - 84: 67, # 'T' - 85: 102, # 'U' - 86: 107, # 'V' - 87: 84, # 'W' - 88: 114, # 'X' - 89: 103, # 'Y' - 90: 115, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 50, # 'a' - 98: 74, # 'b' - 99: 60, # 'c' - 100: 61, # 'd' - 101: 42, # 'e' - 102: 76, # 'f' - 103: 70, # 'g' - 104: 64, # 'h' - 105: 53, # 'i' - 106: 105, # 'j' - 107: 93, # 'k' - 108: 56, # 'l' - 109: 65, # 'm' - 110: 54, # 'n' - 111: 49, # 'o' - 112: 66, # 'p' - 113: 110, # 'q' - 114: 51, # 'r' - 115: 43, # 's' - 116: 44, # 't' - 117: 63, # 'u' - 118: 81, # 'v' - 119: 77, # 'w' - 120: 98, # 'x' - 121: 75, # 'y' - 122: 108, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 124, # '€' - 129: 202, # None - 130: 203, # '‚' - 131: 204, # 'ƒ' - 132: 205, # '„' - 133: 40, # '…' - 134: 58, # '†' - 135: 206, # '‡' - 136: 207, # 'ˆ' - 137: 208, # '‰' - 138: 209, # None - 139: 210, # '‹' - 140: 211, # None - 141: 212, # None - 142: 213, # None - 143: 214, # None - 144: 215, # None - 145: 83, # '‘' - 146: 52, # '’' - 147: 47, # '“' - 148: 46, # '”' - 149: 72, # '•' - 150: 32, # '–' - 151: 94, # '—' - 152: 216, # '˜' - 153: 113, # '™' - 154: 217, # None - 155: 109, # '›' - 156: 218, # None - 157: 219, # None - 158: 220, # None - 159: 221, # None - 160: 34, # '\xa0' - 161: 116, # '¡' - 162: 222, # '¢' - 163: 118, # '£' - 164: 100, # '₪' - 165: 223, # '¥' - 166: 224, # '¦' - 167: 117, # '§' - 168: 119, # '¨' - 169: 104, # '©' - 170: 125, # '×' - 171: 225, # '«' - 172: 226, # '¬' - 173: 87, # '\xad' - 174: 99, # '®' - 175: 227, # '¯' - 176: 106, # '°' - 177: 122, # '±' - 178: 123, # '²' - 179: 228, # '³' - 180: 55, # '´' - 181: 229, # 'µ' - 182: 230, # '¶' - 183: 101, # '·' - 184: 231, # '¸' - 185: 232, # '¹' - 186: 120, # '÷' - 187: 233, # '»' - 188: 48, # '¼' - 189: 39, # '½' - 190: 57, # '¾' - 191: 234, # '¿' - 192: 30, # 'ְ' - 193: 59, # 'ֱ' - 194: 41, # 'ֲ' - 195: 88, # 'ֳ' - 196: 33, # 'ִ' - 197: 37, # 'ֵ' - 198: 36, # 'ֶ' - 199: 31, # 'ַ' - 200: 29, # 'ָ' - 201: 35, # 'ֹ' - 202: 235, # None - 203: 62, # 'ֻ' - 204: 28, # 'ּ' - 205: 236, # 'ֽ' - 206: 126, # '־' - 207: 237, # 'ֿ' - 208: 238, # '׀' - 209: 38, # 'ׁ' - 210: 45, # 'ׂ' - 211: 239, # '׃' - 212: 240, # 'װ' - 213: 241, # 'ױ' - 214: 242, # 'ײ' - 215: 243, # '׳' - 216: 127, # '״' - 217: 244, # None - 218: 245, # None - 219: 246, # None - 220: 247, # None - 221: 248, # None - 222: 249, # None - 223: 250, # None - 224: 9, # 'א' - 225: 8, # 'ב' - 226: 20, # 'ג' - 227: 16, # 'ד' - 228: 3, # 'ה' - 229: 2, # 'ו' - 230: 24, # 'ז' - 231: 14, # 'ח' - 232: 22, # 'ט' - 233: 1, # 'י' - 234: 25, # 'ך' - 235: 15, # 'כ' - 236: 4, # 'ל' - 237: 11, # 'ם' - 238: 6, # 'מ' - 239: 23, # 'ן' - 240: 12, # 'נ' - 241: 19, # 'ס' - 242: 13, # 'ע' - 243: 26, # 'ף' - 244: 18, # 'פ' - 245: 27, # 'ץ' - 246: 21, # 'צ' - 247: 17, # 'ק' - 248: 7, # 'ר' - 249: 10, # 'ש' - 250: 5, # 'ת' - 251: 251, # None - 252: 252, # None - 253: 128, # '\u200e' - 254: 96, # '\u200f' - 255: 253, # None -} - -WINDOWS_1255_HEBREW_MODEL = SingleByteCharSetModel( - charset_name="windows-1255", - language="Hebrew", - char_to_order_map=WINDOWS_1255_HEBREW_CHAR_TO_ORDER, - language_model=HEBREW_LANG_MODEL, - typical_positive_ratio=0.984004, - keep_ascii_letters=False, - alphabet="אבגדהוזחטיךכלםמןנסעףפץצקרשתװױײ", -) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langhungarianmodel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langhungarianmodel.py deleted file mode 100644 index 09a0d32..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langhungarianmodel.py +++ /dev/null @@ -1,4649 +0,0 @@ -from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel - -# 3: Positive -# 2: Likely -# 1: Unlikely -# 0: Negative - -HUNGARIAN_LANG_MODEL = { - 28: { # 'A' - 28: 0, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 2, # 'D' - 32: 1, # 'E' - 50: 1, # 'F' - 49: 2, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 2, # 'K' - 41: 2, # 'L' - 34: 1, # 'M' - 35: 2, # 'N' - 47: 1, # 'O' - 46: 2, # 'P' - 43: 2, # 'R' - 33: 2, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 2, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 2, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 1, # 'i' - 22: 1, # 'j' - 7: 2, # 'k' - 6: 2, # 'l' - 13: 2, # 'm' - 4: 2, # 'n' - 8: 0, # 'o' - 23: 2, # 'p' - 10: 2, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 1, # 'u' - 19: 1, # 'v' - 62: 1, # 'x' - 16: 0, # 'y' - 11: 3, # 'z' - 51: 1, # 'Á' - 44: 0, # 'É' - 61: 1, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 40: { # 'B' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 0, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 3, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 2, # 'i' - 22: 1, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 3, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 54: { # 'C' - 28: 1, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 1, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 0, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 2, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 0, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 1, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 1, # 'h' - 9: 1, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 3, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 1, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 45: { # 'D' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 0, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 0, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 3, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 1, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 1, # 'o' - 23: 0, # 'p' - 10: 2, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 2, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 1, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 0, # 'ű' - }, - 32: { # 'E' - 28: 1, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 1, # 'E' - 50: 1, # 'F' - 49: 2, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 2, # 'K' - 41: 2, # 'L' - 34: 2, # 'M' - 35: 2, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 2, # 'R' - 33: 2, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 1, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 2, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 3, # 'g' - 20: 1, # 'h' - 9: 1, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 2, # 'l' - 13: 2, # 'm' - 4: 2, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 2, # 's' - 3: 1, # 't' - 21: 2, # 'u' - 19: 1, # 'v' - 62: 1, # 'x' - 16: 0, # 'y' - 11: 3, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 0, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 0, # 'Ú' - 63: 1, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 1, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 50: { # 'F' - 28: 1, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 1, # 'E' - 50: 1, # 'F' - 49: 0, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 0, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 0, # 'V' - 55: 1, # 'Y' - 52: 0, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 1, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 2, # 'i' - 22: 1, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 2, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 0, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 0, # 'Ú' - 63: 1, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 2, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 49: { # 'G' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 2, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 1, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 2, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 2, # 'y' - 11: 0, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 0, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 0, # 'ű' - }, - 38: { # 'H' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 0, # 'D' - 32: 1, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 1, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 1, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 1, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 0, # 'V' - 55: 1, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 2, # 'i' - 22: 1, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 0, # 'n' - 8: 3, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 2, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 2, # 'Á' - 44: 2, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 1, # 'é' - 30: 2, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 39: { # 'I' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 1, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 2, # 'K' - 41: 2, # 'L' - 34: 1, # 'M' - 35: 2, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 2, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 2, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 2, # 'd' - 1: 0, # 'e' - 27: 1, # 'f' - 12: 2, # 'g' - 20: 1, # 'h' - 9: 0, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 2, # 'l' - 13: 2, # 'm' - 4: 1, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 2, # 's' - 3: 2, # 't' - 21: 0, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 0, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 53: { # 'J' - 28: 2, # 'A' - 40: 0, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 1, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 1, # 'o' - 23: 0, # 'p' - 10: 0, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 2, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 0, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 1, # 'é' - 30: 0, # 'í' - 25: 2, # 'ó' - 24: 2, # 'ö' - 31: 1, # 'ú' - 29: 0, # 'ü' - 42: 1, # 'ő' - 56: 0, # 'ű' - }, - 36: { # 'K' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 0, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 0, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 1, # 'f' - 12: 0, # 'g' - 20: 1, # 'h' - 9: 3, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 2, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 2, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 2, # 'ö' - 31: 1, # 'ú' - 29: 2, # 'ü' - 42: 1, # 'ő' - 56: 0, # 'ű' - }, - 41: { # 'L' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 2, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 3, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 2, # 'i' - 22: 1, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 0, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 2, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 2, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 0, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 34: { # 'M' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 0, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 3, # 'a' - 18: 0, # 'b' - 26: 1, # 'c' - 17: 0, # 'd' - 1: 3, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 3, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 3, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 2, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 2, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 1, # 'ű' - }, - 35: { # 'N' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 2, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 2, # 'Y' - 52: 1, # 'Z' - 2: 3, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 3, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 2, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 0, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 2, # 'y' - 11: 0, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 1, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 1, # 'ő' - 56: 0, # 'ű' - }, - 47: { # 'O' - 28: 1, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 1, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 2, # 'K' - 41: 2, # 'L' - 34: 2, # 'M' - 35: 2, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 2, # 'R' - 33: 2, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 1, # 'i' - 22: 1, # 'j' - 7: 2, # 'k' - 6: 2, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 1, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 1, # 's' - 3: 2, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 1, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 0, # 'Í' - 58: 1, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 46: { # 'P' - 28: 1, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 1, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 0, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 2, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 1, # 'f' - 12: 0, # 'g' - 20: 1, # 'h' - 9: 2, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 2, # 'r' - 5: 1, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 2, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 0, # 'Ú' - 63: 1, # 'Ü' - 14: 3, # 'á' - 15: 2, # 'é' - 30: 0, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 0, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 0, # 'ű' - }, - 43: { # 'R' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 2, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 1, # 'h' - 9: 2, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 0, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 2, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 2, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 2, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 33: { # 'S' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 2, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 3, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 1, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 1, # 'h' - 9: 2, # 'i' - 22: 0, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 1, # 'p' - 10: 0, # 'r' - 5: 0, # 's' - 3: 1, # 't' - 21: 1, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 3, # 'z' - 51: 2, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 37: { # 'T' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 1, # 'P' - 43: 2, # 'R' - 33: 1, # 'S' - 37: 2, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 2, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 1, # 'h' - 9: 2, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 0, # 't' - 21: 2, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 1, # 'z' - 51: 2, # 'Á' - 44: 2, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 2, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 57: { # 'U' - 28: 1, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 1, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 2, # 'S' - 37: 1, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 1, # 'e' - 27: 0, # 'f' - 12: 2, # 'g' - 20: 0, # 'h' - 9: 0, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 1, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 48: { # 'V' - 28: 2, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 0, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 2, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 2, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 2, # 'o' - 23: 0, # 'p' - 10: 0, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 2, # 'Á' - 44: 2, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 0, # 'Ú' - 63: 1, # 'Ü' - 14: 2, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 0, # 'ó' - 24: 1, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 55: { # 'Y' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 1, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 2, # 'Z' - 2: 1, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 1, # 'd' - 1: 1, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 0, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 8: 1, # 'o' - 23: 1, # 'p' - 10: 0, # 'r' - 5: 0, # 's' - 3: 0, # 't' - 21: 0, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 1, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 52: { # 'Z' - 28: 2, # 'A' - 40: 1, # 'B' - 54: 0, # 'C' - 45: 1, # 'D' - 32: 2, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 2, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 2, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 2, # 'S' - 37: 1, # 'T' - 57: 1, # 'U' - 48: 1, # 'V' - 55: 1, # 'Y' - 52: 1, # 'Z' - 2: 1, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 1, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 1, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 8: 1, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 2, # 's' - 3: 0, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 2, # 'Á' - 44: 1, # 'É' - 61: 1, # 'Í' - 58: 1, # 'Ó' - 59: 1, # 'Ö' - 60: 1, # 'Ú' - 63: 1, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 2: { # 'a' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 3, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 2, # 'e' - 27: 2, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 3, # 'i' - 22: 3, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 2, # 'o' - 23: 3, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 1, # 'x' - 16: 2, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 18: { # 'b' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 3, # 'i' - 22: 2, # 'j' - 7: 2, # 'k' - 6: 2, # 'l' - 13: 1, # 'm' - 4: 2, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 3, # 'r' - 5: 2, # 's' - 3: 1, # 't' - 21: 3, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 3, # 'ó' - 24: 2, # 'ö' - 31: 2, # 'ú' - 29: 2, # 'ü' - 42: 2, # 'ő' - 56: 1, # 'ű' - }, - 26: { # 'c' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 1, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 1, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 2, # 'a' - 18: 1, # 'b' - 26: 2, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 3, # 'h' - 9: 3, # 'i' - 22: 1, # 'j' - 7: 2, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 3, # 's' - 3: 2, # 't' - 21: 2, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 2, # 'á' - 15: 2, # 'é' - 30: 2, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 17: { # 'd' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 2, # 'b' - 26: 1, # 'c' - 17: 2, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 3, # 'j' - 7: 2, # 'k' - 6: 1, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 2, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 3, # 'í' - 25: 3, # 'ó' - 24: 3, # 'ö' - 31: 2, # 'ú' - 29: 2, # 'ü' - 42: 2, # 'ő' - 56: 1, # 'ű' - }, - 1: { # 'e' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 2, # 'a' - 18: 3, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 2, # 'e' - 27: 3, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 3, # 'i' - 22: 3, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 2, # 'o' - 23: 3, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 2, # 'u' - 19: 3, # 'v' - 62: 2, # 'x' - 16: 2, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 27: { # 'f' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 2, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 3, # 'i' - 22: 2, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 3, # 'o' - 23: 0, # 'p' - 10: 3, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 2, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 0, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 3, # 'ö' - 31: 1, # 'ú' - 29: 2, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 12: { # 'g' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 2, # 'c' - 17: 2, # 'd' - 1: 3, # 'e' - 27: 2, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 3, # 'i' - 22: 3, # 'j' - 7: 2, # 'k' - 6: 3, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 3, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 3, # 'ó' - 24: 2, # 'ö' - 31: 2, # 'ú' - 29: 2, # 'ü' - 42: 2, # 'ő' - 56: 1, # 'ű' - }, - 20: { # 'h' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 0, # 'd' - 1: 3, # 'e' - 27: 0, # 'f' - 12: 1, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 3, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 2, # 's' - 3: 1, # 't' - 21: 3, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 2, # 'y' - 11: 0, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 3, # 'í' - 25: 2, # 'ó' - 24: 2, # 'ö' - 31: 2, # 'ú' - 29: 1, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 9: { # 'i' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 3, # 'e' - 27: 3, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 2, # 'i' - 22: 2, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 2, # 'o' - 23: 2, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 1, # 'x' - 16: 1, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 3, # 'ó' - 24: 1, # 'ö' - 31: 2, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 1, # 'ű' - }, - 22: { # 'j' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 2, # 'b' - 26: 1, # 'c' - 17: 3, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 2, # 'h' - 9: 1, # 'i' - 22: 2, # 'j' - 7: 2, # 'k' - 6: 2, # 'l' - 13: 1, # 'm' - 4: 2, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 2, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 1, # 'í' - 25: 3, # 'ó' - 24: 3, # 'ö' - 31: 3, # 'ú' - 29: 2, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 7: { # 'k' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 2, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 2, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 1, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 2, # 'v' - 62: 0, # 'x' - 16: 2, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 3, # 'í' - 25: 2, # 'ó' - 24: 3, # 'ö' - 31: 1, # 'ú' - 29: 3, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 6: { # 'l' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 1, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 1, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 2, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 3, # 'e' - 27: 3, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 3, # 'i' - 22: 3, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 2, # 'p' - 10: 2, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 3, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 3, # 'í' - 25: 3, # 'ó' - 24: 3, # 'ö' - 31: 2, # 'ú' - 29: 2, # 'ü' - 42: 3, # 'ő' - 56: 1, # 'ű' - }, - 13: { # 'm' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 2, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 2, # 'j' - 7: 1, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 8: 3, # 'o' - 23: 3, # 'p' - 10: 2, # 'r' - 5: 2, # 's' - 3: 2, # 't' - 21: 3, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 2, # 'ó' - 24: 2, # 'ö' - 31: 2, # 'ú' - 29: 2, # 'ü' - 42: 1, # 'ő' - 56: 2, # 'ű' - }, - 4: { # 'n' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 3, # 'e' - 27: 2, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 3, # 'i' - 22: 2, # 'j' - 7: 3, # 'k' - 6: 2, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 2, # 'p' - 10: 2, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 2, # 'v' - 62: 1, # 'x' - 16: 3, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 2, # 'ó' - 24: 3, # 'ö' - 31: 2, # 'ú' - 29: 3, # 'ü' - 42: 2, # 'ő' - 56: 1, # 'ű' - }, - 8: { # 'o' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 1, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 2, # 'a' - 18: 3, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 2, # 'e' - 27: 2, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 2, # 'i' - 22: 2, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 1, # 'o' - 23: 3, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 2, # 'u' - 19: 3, # 'v' - 62: 1, # 'x' - 16: 1, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 23: { # 'p' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 1, # 'b' - 26: 2, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 2, # 'j' - 7: 2, # 'k' - 6: 3, # 'l' - 13: 1, # 'm' - 4: 2, # 'n' - 8: 3, # 'o' - 23: 3, # 'p' - 10: 3, # 'r' - 5: 2, # 's' - 3: 2, # 't' - 21: 3, # 'u' - 19: 2, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 2, # 'ó' - 24: 2, # 'ö' - 31: 1, # 'ú' - 29: 2, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 10: { # 'r' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 3, # 'e' - 27: 2, # 'f' - 12: 3, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 3, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 2, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 1, # 'x' - 16: 2, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 3, # 'ó' - 24: 3, # 'ö' - 31: 3, # 'ú' - 29: 3, # 'ü' - 42: 2, # 'ő' - 56: 2, # 'ű' - }, - 5: { # 's' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 2, # 'c' - 17: 2, # 'd' - 1: 3, # 'e' - 27: 2, # 'f' - 12: 2, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 1, # 'j' - 7: 3, # 'k' - 6: 2, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 2, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 2, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 3, # 'í' - 25: 3, # 'ó' - 24: 3, # 'ö' - 31: 3, # 'ú' - 29: 3, # 'ü' - 42: 2, # 'ő' - 56: 1, # 'ű' - }, - 3: { # 't' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 3, # 'b' - 26: 2, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 2, # 'f' - 12: 1, # 'g' - 20: 3, # 'h' - 9: 3, # 'i' - 22: 3, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 3, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 3, # 'ó' - 24: 3, # 'ö' - 31: 3, # 'ú' - 29: 3, # 'ü' - 42: 3, # 'ő' - 56: 2, # 'ű' - }, - 21: { # 'u' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 2, # 'b' - 26: 2, # 'c' - 17: 3, # 'd' - 1: 2, # 'e' - 27: 1, # 'f' - 12: 3, # 'g' - 20: 2, # 'h' - 9: 2, # 'i' - 22: 2, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 1, # 'o' - 23: 2, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 1, # 'u' - 19: 3, # 'v' - 62: 1, # 'x' - 16: 1, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 2, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 0, # 'ö' - 31: 1, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 19: { # 'v' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 2, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 3, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 1, # 'r' - 5: 2, # 's' - 3: 2, # 't' - 21: 2, # 'u' - 19: 2, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 2, # 'ó' - 24: 2, # 'ö' - 31: 1, # 'ú' - 29: 2, # 'ü' - 42: 1, # 'ő' - 56: 1, # 'ű' - }, - 62: { # 'x' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 0, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 1, # 'i' - 22: 0, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 1, # 'o' - 23: 1, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 1, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 1, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 16: { # 'y' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 2, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 3, # 'e' - 27: 2, # 'f' - 12: 2, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 2, # 'j' - 7: 2, # 'k' - 6: 2, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 2, # 'p' - 10: 2, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 2, # 'í' - 25: 2, # 'ó' - 24: 3, # 'ö' - 31: 2, # 'ú' - 29: 2, # 'ü' - 42: 1, # 'ő' - 56: 2, # 'ű' - }, - 11: { # 'z' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 3, # 'a' - 18: 2, # 'b' - 26: 1, # 'c' - 17: 3, # 'd' - 1: 3, # 'e' - 27: 1, # 'f' - 12: 2, # 'g' - 20: 2, # 'h' - 9: 3, # 'i' - 22: 1, # 'j' - 7: 3, # 'k' - 6: 2, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 3, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 3, # 'u' - 19: 2, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 3, # 'á' - 15: 3, # 'é' - 30: 3, # 'í' - 25: 3, # 'ó' - 24: 3, # 'ö' - 31: 2, # 'ú' - 29: 3, # 'ü' - 42: 2, # 'ő' - 56: 1, # 'ű' - }, - 51: { # 'Á' - 28: 0, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 0, # 'E' - 50: 1, # 'F' - 49: 2, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 2, # 'L' - 34: 1, # 'M' - 35: 2, # 'N' - 47: 0, # 'O' - 46: 1, # 'P' - 43: 2, # 'R' - 33: 2, # 'S' - 37: 1, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 0, # 'e' - 27: 0, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 0, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 2, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 1, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 44: { # 'É' - 28: 0, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 1, # 'E' - 50: 0, # 'F' - 49: 2, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 2, # 'L' - 34: 1, # 'M' - 35: 2, # 'N' - 47: 0, # 'O' - 46: 1, # 'P' - 43: 2, # 'R' - 33: 2, # 'S' - 37: 2, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 0, # 'e' - 27: 0, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 0, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 2, # 'l' - 13: 1, # 'm' - 4: 2, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 3, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 0, # 'Á' - 44: 1, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 61: { # 'Í' - 28: 0, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 0, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 1, # 'J' - 36: 0, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 0, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 0, # 'e' - 27: 0, # 'f' - 12: 2, # 'g' - 20: 0, # 'h' - 9: 0, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 1, # 'm' - 4: 0, # 'n' - 8: 0, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 0, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 58: { # 'Ó' - 28: 1, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 0, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 1, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 2, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 0, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 0, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 2, # 'h' - 9: 0, # 'i' - 22: 0, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 0, # 't' - 21: 0, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 1, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 59: { # 'Ö' - 28: 0, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 0, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 0, # 'O' - 46: 1, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 0, # 'b' - 26: 1, # 'c' - 17: 1, # 'd' - 1: 0, # 'e' - 27: 0, # 'f' - 12: 0, # 'g' - 20: 0, # 'h' - 9: 0, # 'i' - 22: 0, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 8: 0, # 'o' - 23: 0, # 'p' - 10: 2, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 60: { # 'Ú' - 28: 0, # 'A' - 40: 1, # 'B' - 54: 1, # 'C' - 45: 1, # 'D' - 32: 0, # 'E' - 50: 1, # 'F' - 49: 1, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 0, # 'b' - 26: 0, # 'c' - 17: 0, # 'd' - 1: 0, # 'e' - 27: 0, # 'f' - 12: 2, # 'g' - 20: 0, # 'h' - 9: 0, # 'i' - 22: 2, # 'j' - 7: 0, # 'k' - 6: 0, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 8: 0, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 0, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 0, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 63: { # 'Ü' - 28: 0, # 'A' - 40: 1, # 'B' - 54: 0, # 'C' - 45: 1, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 1, # 'G' - 38: 1, # 'H' - 39: 0, # 'I' - 53: 1, # 'J' - 36: 1, # 'K' - 41: 1, # 'L' - 34: 1, # 'M' - 35: 1, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 1, # 'R' - 33: 1, # 'S' - 37: 1, # 'T' - 57: 0, # 'U' - 48: 1, # 'V' - 55: 0, # 'Y' - 52: 1, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 0, # 'c' - 17: 1, # 'd' - 1: 0, # 'e' - 27: 0, # 'f' - 12: 1, # 'g' - 20: 0, # 'h' - 9: 0, # 'i' - 22: 0, # 'j' - 7: 0, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 8: 0, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 1, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 14: { # 'á' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 3, # 'b' - 26: 3, # 'c' - 17: 3, # 'd' - 1: 1, # 'e' - 27: 2, # 'f' - 12: 3, # 'g' - 20: 2, # 'h' - 9: 2, # 'i' - 22: 3, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 1, # 'o' - 23: 2, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 2, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 1, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 2, # 'é' - 30: 1, # 'í' - 25: 0, # 'ó' - 24: 1, # 'ö' - 31: 0, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 15: { # 'é' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 3, # 'b' - 26: 2, # 'c' - 17: 3, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 3, # 'g' - 20: 3, # 'h' - 9: 2, # 'i' - 22: 2, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 1, # 'o' - 23: 3, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 0, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 30: { # 'í' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 0, # 'a' - 18: 1, # 'b' - 26: 2, # 'c' - 17: 1, # 'd' - 1: 0, # 'e' - 27: 1, # 'f' - 12: 3, # 'g' - 20: 0, # 'h' - 9: 0, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 2, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 3, # 'r' - 5: 2, # 's' - 3: 3, # 't' - 21: 0, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 25: { # 'ó' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 2, # 'a' - 18: 3, # 'b' - 26: 2, # 'c' - 17: 3, # 'd' - 1: 1, # 'e' - 27: 2, # 'f' - 12: 2, # 'g' - 20: 2, # 'h' - 9: 2, # 'i' - 22: 2, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 8: 1, # 'o' - 23: 2, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 1, # 'u' - 19: 2, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 0, # 'ó' - 24: 1, # 'ö' - 31: 1, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 24: { # 'ö' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 0, # 'a' - 18: 3, # 'b' - 26: 1, # 'c' - 17: 2, # 'd' - 1: 0, # 'e' - 27: 1, # 'f' - 12: 2, # 'g' - 20: 1, # 'h' - 9: 0, # 'i' - 22: 1, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 8: 0, # 'o' - 23: 2, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 3, # 't' - 21: 0, # 'u' - 19: 3, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 3, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 31: { # 'ú' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 1, # 'b' - 26: 2, # 'c' - 17: 1, # 'd' - 1: 1, # 'e' - 27: 2, # 'f' - 12: 3, # 'g' - 20: 1, # 'h' - 9: 1, # 'i' - 22: 3, # 'j' - 7: 1, # 'k' - 6: 3, # 'l' - 13: 1, # 'm' - 4: 2, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 3, # 'r' - 5: 3, # 's' - 3: 2, # 't' - 21: 1, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 1, # 'á' - 15: 1, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 29: { # 'ü' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 1, # 'b' - 26: 1, # 'c' - 17: 2, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 3, # 'g' - 20: 2, # 'h' - 9: 1, # 'i' - 22: 1, # 'j' - 7: 3, # 'k' - 6: 3, # 'l' - 13: 1, # 'm' - 4: 3, # 'n' - 8: 0, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 2, # 's' - 3: 2, # 't' - 21: 0, # 'u' - 19: 2, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 1, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 42: { # 'ő' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 2, # 'b' - 26: 1, # 'c' - 17: 2, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 1, # 'i' - 22: 1, # 'j' - 7: 2, # 'k' - 6: 3, # 'l' - 13: 1, # 'm' - 4: 2, # 'n' - 8: 1, # 'o' - 23: 1, # 'p' - 10: 2, # 'r' - 5: 2, # 's' - 3: 2, # 't' - 21: 1, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 1, # 'é' - 30: 1, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 1, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, - 56: { # 'ű' - 28: 0, # 'A' - 40: 0, # 'B' - 54: 0, # 'C' - 45: 0, # 'D' - 32: 0, # 'E' - 50: 0, # 'F' - 49: 0, # 'G' - 38: 0, # 'H' - 39: 0, # 'I' - 53: 0, # 'J' - 36: 0, # 'K' - 41: 0, # 'L' - 34: 0, # 'M' - 35: 0, # 'N' - 47: 0, # 'O' - 46: 0, # 'P' - 43: 0, # 'R' - 33: 0, # 'S' - 37: 0, # 'T' - 57: 0, # 'U' - 48: 0, # 'V' - 55: 0, # 'Y' - 52: 0, # 'Z' - 2: 1, # 'a' - 18: 1, # 'b' - 26: 0, # 'c' - 17: 1, # 'd' - 1: 1, # 'e' - 27: 1, # 'f' - 12: 1, # 'g' - 20: 1, # 'h' - 9: 1, # 'i' - 22: 1, # 'j' - 7: 1, # 'k' - 6: 1, # 'l' - 13: 0, # 'm' - 4: 2, # 'n' - 8: 0, # 'o' - 23: 0, # 'p' - 10: 1, # 'r' - 5: 1, # 's' - 3: 1, # 't' - 21: 0, # 'u' - 19: 1, # 'v' - 62: 0, # 'x' - 16: 0, # 'y' - 11: 2, # 'z' - 51: 0, # 'Á' - 44: 0, # 'É' - 61: 0, # 'Í' - 58: 0, # 'Ó' - 59: 0, # 'Ö' - 60: 0, # 'Ú' - 63: 0, # 'Ü' - 14: 0, # 'á' - 15: 0, # 'é' - 30: 0, # 'í' - 25: 0, # 'ó' - 24: 0, # 'ö' - 31: 0, # 'ú' - 29: 0, # 'ü' - 42: 0, # 'ő' - 56: 0, # 'ű' - }, -} - -# 255: Undefined characters that did not exist in training text -# 254: Carriage/Return -# 253: symbol (punctuation) that does not belong to word -# 252: 0 - 9 -# 251: Control characters - -# Character Mapping Table(s): -WINDOWS_1250_HUNGARIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 28, # 'A' - 66: 40, # 'B' - 67: 54, # 'C' - 68: 45, # 'D' - 69: 32, # 'E' - 70: 50, # 'F' - 71: 49, # 'G' - 72: 38, # 'H' - 73: 39, # 'I' - 74: 53, # 'J' - 75: 36, # 'K' - 76: 41, # 'L' - 77: 34, # 'M' - 78: 35, # 'N' - 79: 47, # 'O' - 80: 46, # 'P' - 81: 72, # 'Q' - 82: 43, # 'R' - 83: 33, # 'S' - 84: 37, # 'T' - 85: 57, # 'U' - 86: 48, # 'V' - 87: 64, # 'W' - 88: 68, # 'X' - 89: 55, # 'Y' - 90: 52, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 2, # 'a' - 98: 18, # 'b' - 99: 26, # 'c' - 100: 17, # 'd' - 101: 1, # 'e' - 102: 27, # 'f' - 103: 12, # 'g' - 104: 20, # 'h' - 105: 9, # 'i' - 106: 22, # 'j' - 107: 7, # 'k' - 108: 6, # 'l' - 109: 13, # 'm' - 110: 4, # 'n' - 111: 8, # 'o' - 112: 23, # 'p' - 113: 67, # 'q' - 114: 10, # 'r' - 115: 5, # 's' - 116: 3, # 't' - 117: 21, # 'u' - 118: 19, # 'v' - 119: 65, # 'w' - 120: 62, # 'x' - 121: 16, # 'y' - 122: 11, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 161, # '€' - 129: 162, # None - 130: 163, # '‚' - 131: 164, # None - 132: 165, # '„' - 133: 166, # '…' - 134: 167, # '†' - 135: 168, # '‡' - 136: 169, # None - 137: 170, # '‰' - 138: 171, # 'Š' - 139: 172, # '‹' - 140: 173, # 'Ś' - 141: 174, # 'Ť' - 142: 175, # 'Ž' - 143: 176, # 'Ź' - 144: 177, # None - 145: 178, # '‘' - 146: 179, # '’' - 147: 180, # '“' - 148: 78, # '”' - 149: 181, # '•' - 150: 69, # '–' - 151: 182, # '—' - 152: 183, # None - 153: 184, # '™' - 154: 185, # 'š' - 155: 186, # '›' - 156: 187, # 'ś' - 157: 188, # 'ť' - 158: 189, # 'ž' - 159: 190, # 'ź' - 160: 191, # '\xa0' - 161: 192, # 'ˇ' - 162: 193, # '˘' - 163: 194, # 'Ł' - 164: 195, # '¤' - 165: 196, # 'Ą' - 166: 197, # '¦' - 167: 76, # '§' - 168: 198, # '¨' - 169: 199, # '©' - 170: 200, # 'Ş' - 171: 201, # '«' - 172: 202, # '¬' - 173: 203, # '\xad' - 174: 204, # '®' - 175: 205, # 'Ż' - 176: 81, # '°' - 177: 206, # '±' - 178: 207, # '˛' - 179: 208, # 'ł' - 180: 209, # '´' - 181: 210, # 'µ' - 182: 211, # '¶' - 183: 212, # '·' - 184: 213, # '¸' - 185: 214, # 'ą' - 186: 215, # 'ş' - 187: 216, # '»' - 188: 217, # 'Ľ' - 189: 218, # '˝' - 190: 219, # 'ľ' - 191: 220, # 'ż' - 192: 221, # 'Ŕ' - 193: 51, # 'Á' - 194: 83, # 'Â' - 195: 222, # 'Ă' - 196: 80, # 'Ä' - 197: 223, # 'Ĺ' - 198: 224, # 'Ć' - 199: 225, # 'Ç' - 200: 226, # 'Č' - 201: 44, # 'É' - 202: 227, # 'Ę' - 203: 228, # 'Ë' - 204: 229, # 'Ě' - 205: 61, # 'Í' - 206: 230, # 'Î' - 207: 231, # 'Ď' - 208: 232, # 'Đ' - 209: 233, # 'Ń' - 210: 234, # 'Ň' - 211: 58, # 'Ó' - 212: 235, # 'Ô' - 213: 66, # 'Ő' - 214: 59, # 'Ö' - 215: 236, # '×' - 216: 237, # 'Ř' - 217: 238, # 'Ů' - 218: 60, # 'Ú' - 219: 70, # 'Ű' - 220: 63, # 'Ü' - 221: 239, # 'Ý' - 222: 240, # 'Ţ' - 223: 241, # 'ß' - 224: 84, # 'ŕ' - 225: 14, # 'á' - 226: 75, # 'â' - 227: 242, # 'ă' - 228: 71, # 'ä' - 229: 82, # 'ĺ' - 230: 243, # 'ć' - 231: 73, # 'ç' - 232: 244, # 'č' - 233: 15, # 'é' - 234: 85, # 'ę' - 235: 79, # 'ë' - 236: 86, # 'ě' - 237: 30, # 'í' - 238: 77, # 'î' - 239: 87, # 'ď' - 240: 245, # 'đ' - 241: 246, # 'ń' - 242: 247, # 'ň' - 243: 25, # 'ó' - 244: 74, # 'ô' - 245: 42, # 'ő' - 246: 24, # 'ö' - 247: 248, # '÷' - 248: 249, # 'ř' - 249: 250, # 'ů' - 250: 31, # 'ú' - 251: 56, # 'ű' - 252: 29, # 'ü' - 253: 251, # 'ý' - 254: 252, # 'ţ' - 255: 253, # '˙' -} - -WINDOWS_1250_HUNGARIAN_MODEL = SingleByteCharSetModel( - charset_name="windows-1250", - language="Hungarian", - char_to_order_map=WINDOWS_1250_HUNGARIAN_CHAR_TO_ORDER, - language_model=HUNGARIAN_LANG_MODEL, - typical_positive_ratio=0.947368, - keep_ascii_letters=True, - alphabet="ABCDEFGHIJKLMNOPRSTUVZabcdefghijklmnoprstuvzÁÉÍÓÖÚÜáéíóöúüŐőŰű", -) - -ISO_8859_2_HUNGARIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 28, # 'A' - 66: 40, # 'B' - 67: 54, # 'C' - 68: 45, # 'D' - 69: 32, # 'E' - 70: 50, # 'F' - 71: 49, # 'G' - 72: 38, # 'H' - 73: 39, # 'I' - 74: 53, # 'J' - 75: 36, # 'K' - 76: 41, # 'L' - 77: 34, # 'M' - 78: 35, # 'N' - 79: 47, # 'O' - 80: 46, # 'P' - 81: 71, # 'Q' - 82: 43, # 'R' - 83: 33, # 'S' - 84: 37, # 'T' - 85: 57, # 'U' - 86: 48, # 'V' - 87: 64, # 'W' - 88: 68, # 'X' - 89: 55, # 'Y' - 90: 52, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 2, # 'a' - 98: 18, # 'b' - 99: 26, # 'c' - 100: 17, # 'd' - 101: 1, # 'e' - 102: 27, # 'f' - 103: 12, # 'g' - 104: 20, # 'h' - 105: 9, # 'i' - 106: 22, # 'j' - 107: 7, # 'k' - 108: 6, # 'l' - 109: 13, # 'm' - 110: 4, # 'n' - 111: 8, # 'o' - 112: 23, # 'p' - 113: 67, # 'q' - 114: 10, # 'r' - 115: 5, # 's' - 116: 3, # 't' - 117: 21, # 'u' - 118: 19, # 'v' - 119: 65, # 'w' - 120: 62, # 'x' - 121: 16, # 'y' - 122: 11, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 159, # '\x80' - 129: 160, # '\x81' - 130: 161, # '\x82' - 131: 162, # '\x83' - 132: 163, # '\x84' - 133: 164, # '\x85' - 134: 165, # '\x86' - 135: 166, # '\x87' - 136: 167, # '\x88' - 137: 168, # '\x89' - 138: 169, # '\x8a' - 139: 170, # '\x8b' - 140: 171, # '\x8c' - 141: 172, # '\x8d' - 142: 173, # '\x8e' - 143: 174, # '\x8f' - 144: 175, # '\x90' - 145: 176, # '\x91' - 146: 177, # '\x92' - 147: 178, # '\x93' - 148: 179, # '\x94' - 149: 180, # '\x95' - 150: 181, # '\x96' - 151: 182, # '\x97' - 152: 183, # '\x98' - 153: 184, # '\x99' - 154: 185, # '\x9a' - 155: 186, # '\x9b' - 156: 187, # '\x9c' - 157: 188, # '\x9d' - 158: 189, # '\x9e' - 159: 190, # '\x9f' - 160: 191, # '\xa0' - 161: 192, # 'Ą' - 162: 193, # '˘' - 163: 194, # 'Ł' - 164: 195, # '¤' - 165: 196, # 'Ľ' - 166: 197, # 'Ś' - 167: 75, # '§' - 168: 198, # '¨' - 169: 199, # 'Š' - 170: 200, # 'Ş' - 171: 201, # 'Ť' - 172: 202, # 'Ź' - 173: 203, # '\xad' - 174: 204, # 'Ž' - 175: 205, # 'Ż' - 176: 79, # '°' - 177: 206, # 'ą' - 178: 207, # '˛' - 179: 208, # 'ł' - 180: 209, # '´' - 181: 210, # 'ľ' - 182: 211, # 'ś' - 183: 212, # 'ˇ' - 184: 213, # '¸' - 185: 214, # 'š' - 186: 215, # 'ş' - 187: 216, # 'ť' - 188: 217, # 'ź' - 189: 218, # '˝' - 190: 219, # 'ž' - 191: 220, # 'ż' - 192: 221, # 'Ŕ' - 193: 51, # 'Á' - 194: 81, # 'Â' - 195: 222, # 'Ă' - 196: 78, # 'Ä' - 197: 223, # 'Ĺ' - 198: 224, # 'Ć' - 199: 225, # 'Ç' - 200: 226, # 'Č' - 201: 44, # 'É' - 202: 227, # 'Ę' - 203: 228, # 'Ë' - 204: 229, # 'Ě' - 205: 61, # 'Í' - 206: 230, # 'Î' - 207: 231, # 'Ď' - 208: 232, # 'Đ' - 209: 233, # 'Ń' - 210: 234, # 'Ň' - 211: 58, # 'Ó' - 212: 235, # 'Ô' - 213: 66, # 'Ő' - 214: 59, # 'Ö' - 215: 236, # '×' - 216: 237, # 'Ř' - 217: 238, # 'Ů' - 218: 60, # 'Ú' - 219: 69, # 'Ű' - 220: 63, # 'Ü' - 221: 239, # 'Ý' - 222: 240, # 'Ţ' - 223: 241, # 'ß' - 224: 82, # 'ŕ' - 225: 14, # 'á' - 226: 74, # 'â' - 227: 242, # 'ă' - 228: 70, # 'ä' - 229: 80, # 'ĺ' - 230: 243, # 'ć' - 231: 72, # 'ç' - 232: 244, # 'č' - 233: 15, # 'é' - 234: 83, # 'ę' - 235: 77, # 'ë' - 236: 84, # 'ě' - 237: 30, # 'í' - 238: 76, # 'î' - 239: 85, # 'ď' - 240: 245, # 'đ' - 241: 246, # 'ń' - 242: 247, # 'ň' - 243: 25, # 'ó' - 244: 73, # 'ô' - 245: 42, # 'ő' - 246: 24, # 'ö' - 247: 248, # '÷' - 248: 249, # 'ř' - 249: 250, # 'ů' - 250: 31, # 'ú' - 251: 56, # 'ű' - 252: 29, # 'ü' - 253: 251, # 'ý' - 254: 252, # 'ţ' - 255: 253, # '˙' -} - -ISO_8859_2_HUNGARIAN_MODEL = SingleByteCharSetModel( - charset_name="ISO-8859-2", - language="Hungarian", - char_to_order_map=ISO_8859_2_HUNGARIAN_CHAR_TO_ORDER, - language_model=HUNGARIAN_LANG_MODEL, - typical_positive_ratio=0.947368, - keep_ascii_letters=True, - alphabet="ABCDEFGHIJKLMNOPRSTUVZabcdefghijklmnoprstuvzÁÉÍÓÖÚÜáéíóöúüŐőŰű", -) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langrussianmodel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langrussianmodel.py deleted file mode 100644 index 39a5388..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langrussianmodel.py +++ /dev/null @@ -1,5725 +0,0 @@ -from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel - -# 3: Positive -# 2: Likely -# 1: Unlikely -# 0: Negative - -RUSSIAN_LANG_MODEL = { - 37: { # 'А' - 37: 0, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 1, # 'Ж' - 51: 1, # 'З' - 42: 1, # 'И' - 60: 1, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 2, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 1, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 1, # 'Ч' - 57: 1, # 'Ш' - 63: 1, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 1, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 0, # 'е' - 24: 1, # 'ж' - 20: 1, # 'з' - 4: 0, # 'и' - 23: 1, # 'й' - 11: 2, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 2, # 'н' - 1: 0, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 2, # 'у' - 39: 2, # 'ф' - 26: 2, # 'х' - 28: 0, # 'ц' - 22: 1, # 'ч' - 25: 2, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 44: { # 'Б' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 1, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 2, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 2, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 33: { # 'В' - 37: 2, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 1, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 2, # 'а' - 21: 1, # 'б' - 10: 1, # 'в' - 19: 1, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 2, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 2, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 3, # 'с' - 6: 2, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 1, # 'ц' - 22: 2, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 1, # 'ъ' - 18: 3, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 0, # 'ю' - 16: 1, # 'я' - }, - 46: { # 'Г' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 1, # 'в' - 19: 0, # 'г' - 13: 2, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 1, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 1, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 41: { # 'Д' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 2, # 'Е' - 56: 1, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 1, # 'Ц' - 50: 1, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 3, # 'а' - 21: 0, # 'б' - 10: 2, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 3, # 'ж' - 20: 1, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 1, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 48: { # 'Е' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 1, # 'Ж' - 51: 1, # 'З' - 42: 1, # 'И' - 60: 1, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 2, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 2, # 'Р' - 32: 2, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 1, # 'Ч' - 57: 1, # 'Ш' - 63: 1, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 0, # 'а' - 21: 0, # 'б' - 10: 2, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 2, # 'е' - 24: 1, # 'ж' - 20: 1, # 'з' - 4: 0, # 'и' - 23: 2, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 1, # 'н' - 1: 0, # 'о' - 15: 1, # 'п' - 9: 1, # 'р' - 7: 3, # 'с' - 6: 0, # 'т' - 14: 0, # 'у' - 39: 1, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 2, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 56: { # 'Ж' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 1, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 1, # 'б' - 10: 0, # 'в' - 19: 1, # 'г' - 13: 1, # 'д' - 2: 2, # 'е' - 24: 1, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 1, # 'м' - 5: 0, # 'н' - 1: 2, # 'о' - 15: 0, # 'п' - 9: 1, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 2, # 'ю' - 16: 0, # 'я' - }, - 51: { # 'З' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 2, # 'в' - 19: 0, # 'г' - 13: 2, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 1, # 'л' - 12: 1, # 'м' - 5: 2, # 'н' - 1: 2, # 'о' - 15: 0, # 'п' - 9: 1, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 1, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 1, # 'я' - }, - 42: { # 'И' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 2, # 'Е' - 56: 1, # 'Ж' - 51: 1, # 'З' - 42: 1, # 'И' - 60: 1, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 2, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 1, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 1, # 'Ч' - 57: 0, # 'Ш' - 63: 1, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 1, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 2, # 'з' - 4: 1, # 'и' - 23: 0, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 2, # 'н' - 1: 1, # 'о' - 15: 1, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 1, # 'у' - 39: 1, # 'ф' - 26: 2, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 60: { # 'Й' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 1, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 1, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 0, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 2, # 'о' - 15: 0, # 'п' - 9: 0, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 0, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 36: { # 'К' - 37: 2, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 1, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 1, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 2, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 1, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 0, # 'б' - 10: 1, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 2, # 'л' - 12: 0, # 'м' - 5: 1, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 49: { # 'Л' - 37: 2, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 1, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 1, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 0, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 0, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 1, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 0, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 1, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 1, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 1, # 'л' - 12: 0, # 'м' - 5: 1, # 'н' - 1: 2, # 'о' - 15: 0, # 'п' - 9: 0, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 2, # 'ю' - 16: 1, # 'я' - }, - 38: { # 'М' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 1, # 'Ф' - 55: 1, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 0, # 'Ь' - 47: 1, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 3, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 1, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 1, # 'л' - 12: 1, # 'м' - 5: 2, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 1, # 'р' - 7: 1, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 3, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 31: { # 'Н' - 37: 2, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 1, # 'З' - 42: 2, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 1, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 1, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 1, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 3, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 1, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 3, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 2, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 34: { # 'О' - 37: 0, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 2, # 'Д' - 48: 1, # 'Е' - 56: 1, # 'Ж' - 51: 1, # 'З' - 42: 1, # 'И' - 60: 1, # 'Й' - 36: 1, # 'К' - 49: 2, # 'Л' - 38: 1, # 'М' - 31: 2, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 2, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 1, # 'Ф' - 55: 1, # 'Х' - 58: 0, # 'Ц' - 50: 1, # 'Ч' - 57: 1, # 'Ш' - 63: 1, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 1, # 'а' - 21: 2, # 'б' - 10: 1, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 0, # 'е' - 24: 1, # 'ж' - 20: 1, # 'з' - 4: 0, # 'и' - 23: 1, # 'й' - 11: 2, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 3, # 'н' - 1: 0, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 1, # 'у' - 39: 1, # 'ф' - 26: 2, # 'х' - 28: 1, # 'ц' - 22: 2, # 'ч' - 25: 2, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 35: { # 'П' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 1, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 2, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 1, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 2, # 'л' - 12: 0, # 'м' - 5: 1, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 3, # 'р' - 7: 1, # 'с' - 6: 1, # 'т' - 14: 2, # 'у' - 39: 1, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 2, # 'ь' - 30: 1, # 'э' - 27: 0, # 'ю' - 16: 2, # 'я' - }, - 45: { # 'Р' - 37: 2, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 2, # 'Е' - 56: 1, # 'Ж' - 51: 0, # 'З' - 42: 2, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 2, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 1, # 'Ч' - 57: 1, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 1, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 3, # 'а' - 21: 0, # 'б' - 10: 1, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 1, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 1, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 2, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 2, # 'я' - }, - 32: { # 'С' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 2, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 1, # 'Ч' - 57: 1, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 1, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 2, # 'а' - 21: 1, # 'б' - 10: 2, # 'в' - 19: 1, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 1, # 'ж' - 20: 1, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 2, # 'н' - 1: 2, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 1, # 'с' - 6: 3, # 'т' - 14: 2, # 'у' - 39: 1, # 'ф' - 26: 1, # 'х' - 28: 1, # 'ц' - 22: 1, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 1, # 'ъ' - 18: 1, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 40: { # 'Т' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 2, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 1, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 1, # 'Ь' - 47: 1, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 2, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 1, # 'к' - 8: 1, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 1, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 3, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 52: { # 'У' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 1, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 1, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 1, # 'Х' - 58: 0, # 'Ц' - 50: 1, # 'Ч' - 57: 1, # 'Ш' - 63: 1, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 1, # 'Ю' - 43: 0, # 'Я' - 3: 1, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 1, # 'г' - 13: 2, # 'д' - 2: 1, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 2, # 'и' - 23: 1, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 1, # 'н' - 1: 2, # 'о' - 15: 1, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 0, # 'у' - 39: 1, # 'ф' - 26: 1, # 'х' - 28: 1, # 'ц' - 22: 2, # 'ч' - 25: 1, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 53: { # 'Ф' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 1, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 2, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 2, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 0, # 'с' - 6: 1, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 55: { # 'Х' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 2, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 0, # 'н' - 1: 2, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 1, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 1, # 'ь' - 30: 1, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 58: { # 'Ц' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 1, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 1, # 'а' - 21: 0, # 'б' - 10: 1, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 0, # 'о' - 15: 0, # 'п' - 9: 0, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 1, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 50: { # 'Ч' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 1, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 1, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 1, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 1, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 1, # 'о' - 15: 0, # 'п' - 9: 1, # 'р' - 7: 0, # 'с' - 6: 3, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 1, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 57: { # 'Ш' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 1, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 0, # 'б' - 10: 1, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 1, # 'и' - 23: 0, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 1, # 'н' - 1: 2, # 'о' - 15: 2, # 'п' - 9: 1, # 'р' - 7: 0, # 'с' - 6: 2, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 63: { # 'Щ' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 1, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 1, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 1, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 1, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 1, # 'о' - 15: 0, # 'п' - 9: 0, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 1, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 62: { # 'Ы' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 1, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 1, # 'Х' - 58: 1, # 'Ц' - 50: 0, # 'Ч' - 57: 1, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 0, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 0, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 0, # 'о' - 15: 0, # 'п' - 9: 0, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 0, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 61: { # 'Ь' - 37: 0, # 'А' - 44: 1, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 1, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 0, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 1, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 1, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 1, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 1, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 0, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 0, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 0, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 0, # 'о' - 15: 0, # 'п' - 9: 0, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 0, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 47: { # 'Э' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 0, # 'Г' - 41: 1, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 1, # 'Й' - 36: 1, # 'К' - 49: 1, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 1, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 1, # 'а' - 21: 1, # 'б' - 10: 2, # 'в' - 19: 1, # 'г' - 13: 2, # 'д' - 2: 0, # 'е' - 24: 1, # 'ж' - 20: 0, # 'з' - 4: 0, # 'и' - 23: 2, # 'й' - 11: 2, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 2, # 'н' - 1: 0, # 'о' - 15: 1, # 'п' - 9: 2, # 'р' - 7: 1, # 'с' - 6: 3, # 'т' - 14: 1, # 'у' - 39: 1, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 59: { # 'Ю' - 37: 1, # 'А' - 44: 1, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 1, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 0, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 1, # 'Ч' - 57: 0, # 'Ш' - 63: 1, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 1, # 'б' - 10: 0, # 'в' - 19: 1, # 'г' - 13: 1, # 'д' - 2: 0, # 'е' - 24: 1, # 'ж' - 20: 0, # 'з' - 4: 0, # 'и' - 23: 0, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 2, # 'н' - 1: 0, # 'о' - 15: 1, # 'п' - 9: 1, # 'р' - 7: 1, # 'с' - 6: 0, # 'т' - 14: 0, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 43: { # 'Я' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 1, # 'В' - 46: 1, # 'Г' - 41: 0, # 'Д' - 48: 1, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 1, # 'С' - 40: 1, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 1, # 'Х' - 58: 0, # 'Ц' - 50: 1, # 'Ч' - 57: 0, # 'Ш' - 63: 1, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 1, # 'Ю' - 43: 1, # 'Я' - 3: 0, # 'а' - 21: 1, # 'б' - 10: 1, # 'в' - 19: 1, # 'г' - 13: 1, # 'д' - 2: 0, # 'е' - 24: 0, # 'ж' - 20: 1, # 'з' - 4: 0, # 'и' - 23: 1, # 'й' - 11: 1, # 'к' - 8: 1, # 'л' - 12: 1, # 'м' - 5: 2, # 'н' - 1: 0, # 'о' - 15: 1, # 'п' - 9: 1, # 'р' - 7: 1, # 'с' - 6: 0, # 'т' - 14: 0, # 'у' - 39: 0, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 3: { # 'а' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 1, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 3, # 'б' - 10: 3, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 3, # 'з' - 4: 3, # 'и' - 23: 3, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 2, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 3, # 'х' - 28: 3, # 'ц' - 22: 3, # 'ч' - 25: 3, # 'ш' - 29: 3, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 2, # 'э' - 27: 3, # 'ю' - 16: 3, # 'я' - }, - 21: { # 'б' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 1, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 1, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 1, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 1, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 0, # 'ф' - 26: 2, # 'х' - 28: 1, # 'ц' - 22: 1, # 'ч' - 25: 2, # 'ш' - 29: 3, # 'щ' - 54: 2, # 'ъ' - 18: 3, # 'ы' - 17: 2, # 'ь' - 30: 1, # 'э' - 27: 2, # 'ю' - 16: 3, # 'я' - }, - 10: { # 'в' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 2, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 1, # 'ж' - 20: 3, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 1, # 'ф' - 26: 2, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 3, # 'ш' - 29: 2, # 'щ' - 54: 2, # 'ъ' - 18: 3, # 'ы' - 17: 3, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 3, # 'я' - }, - 19: { # 'г' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 2, # 'в' - 19: 1, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 1, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 3, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 1, # 'ф' - 26: 1, # 'х' - 28: 1, # 'ц' - 22: 2, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 1, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 13: { # 'д' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 3, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 1, # 'ф' - 26: 2, # 'х' - 28: 3, # 'ц' - 22: 2, # 'ч' - 25: 2, # 'ш' - 29: 1, # 'щ' - 54: 2, # 'ъ' - 18: 3, # 'ы' - 17: 3, # 'ь' - 30: 1, # 'э' - 27: 2, # 'ю' - 16: 3, # 'я' - }, - 2: { # 'е' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 3, # 'б' - 10: 3, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 3, # 'з' - 4: 2, # 'и' - 23: 3, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 2, # 'у' - 39: 2, # 'ф' - 26: 3, # 'х' - 28: 3, # 'ц' - 22: 3, # 'ч' - 25: 3, # 'ш' - 29: 3, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 2, # 'ю' - 16: 3, # 'я' - }, - 24: { # 'ж' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 1, # 'в' - 19: 2, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 1, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 3, # 'н' - 1: 2, # 'о' - 15: 1, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 1, # 'т' - 14: 3, # 'у' - 39: 1, # 'ф' - 26: 0, # 'х' - 28: 1, # 'ц' - 22: 2, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 2, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 20: { # 'з' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 3, # 'б' - 10: 3, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 3, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 1, # 'ц' - 22: 2, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 2, # 'ъ' - 18: 3, # 'ы' - 17: 2, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 3, # 'я' - }, - 4: { # 'и' - 37: 1, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 3, # 'б' - 10: 3, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 3, # 'з' - 4: 3, # 'и' - 23: 3, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 2, # 'у' - 39: 2, # 'ф' - 26: 3, # 'х' - 28: 3, # 'ц' - 22: 3, # 'ч' - 25: 3, # 'ш' - 29: 3, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 2, # 'э' - 27: 3, # 'ю' - 16: 3, # 'я' - }, - 23: { # 'й' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 1, # 'а' - 21: 1, # 'б' - 10: 1, # 'в' - 19: 2, # 'г' - 13: 3, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 2, # 'з' - 4: 1, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 2, # 'о' - 15: 1, # 'п' - 9: 2, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 1, # 'у' - 39: 2, # 'ф' - 26: 1, # 'х' - 28: 2, # 'ц' - 22: 3, # 'ч' - 25: 2, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 2, # 'я' - }, - 11: { # 'к' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 3, # 'в' - 19: 1, # 'г' - 13: 1, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 3, # 'л' - 12: 1, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 1, # 'ф' - 26: 2, # 'х' - 28: 2, # 'ц' - 22: 1, # 'ч' - 25: 2, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 1, # 'ы' - 17: 1, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 8: { # 'л' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 3, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 2, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 1, # 'р' - 7: 3, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 2, # 'х' - 28: 1, # 'ц' - 22: 3, # 'ч' - 25: 2, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 3, # 'ы' - 17: 3, # 'ь' - 30: 1, # 'э' - 27: 3, # 'ю' - 16: 3, # 'я' - }, - 12: { # 'м' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 2, # 'г' - 13: 1, # 'д' - 2: 3, # 'е' - 24: 1, # 'ж' - 20: 1, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 3, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 2, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 1, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 3, # 'ы' - 17: 2, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 3, # 'я' - }, - 5: { # 'н' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 1, # 'п' - 9: 2, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 2, # 'х' - 28: 3, # 'ц' - 22: 3, # 'ч' - 25: 2, # 'ш' - 29: 2, # 'щ' - 54: 1, # 'ъ' - 18: 3, # 'ы' - 17: 3, # 'ь' - 30: 1, # 'э' - 27: 3, # 'ю' - 16: 3, # 'я' - }, - 1: { # 'о' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 3, # 'б' - 10: 3, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 3, # 'з' - 4: 3, # 'и' - 23: 3, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 2, # 'у' - 39: 2, # 'ф' - 26: 3, # 'х' - 28: 2, # 'ц' - 22: 3, # 'ч' - 25: 3, # 'ш' - 29: 3, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 2, # 'э' - 27: 3, # 'ю' - 16: 3, # 'я' - }, - 15: { # 'п' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 3, # 'л' - 12: 1, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 3, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 1, # 'ф' - 26: 0, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 1, # 'ш' - 29: 1, # 'щ' - 54: 0, # 'ъ' - 18: 3, # 'ы' - 17: 2, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 3, # 'я' - }, - 9: { # 'р' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 3, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 2, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 2, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 3, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 3, # 'ш' - 29: 2, # 'щ' - 54: 0, # 'ъ' - 18: 3, # 'ы' - 17: 3, # 'ь' - 30: 2, # 'э' - 27: 2, # 'ю' - 16: 3, # 'я' - }, - 7: { # 'с' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 1, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 3, # 'в' - 19: 2, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 3, # 'х' - 28: 2, # 'ц' - 22: 3, # 'ч' - 25: 2, # 'ш' - 29: 1, # 'щ' - 54: 2, # 'ъ' - 18: 3, # 'ы' - 17: 3, # 'ь' - 30: 2, # 'э' - 27: 3, # 'ю' - 16: 3, # 'я' - }, - 6: { # 'т' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 2, # 'б' - 10: 3, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 1, # 'ж' - 20: 1, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 2, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 2, # 'ш' - 29: 2, # 'щ' - 54: 2, # 'ъ' - 18: 3, # 'ы' - 17: 3, # 'ь' - 30: 2, # 'э' - 27: 2, # 'ю' - 16: 3, # 'я' - }, - 14: { # 'у' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 3, # 'б' - 10: 3, # 'в' - 19: 3, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 3, # 'з' - 4: 2, # 'и' - 23: 2, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 2, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 1, # 'у' - 39: 2, # 'ф' - 26: 3, # 'х' - 28: 2, # 'ц' - 22: 3, # 'ч' - 25: 3, # 'ш' - 29: 3, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 2, # 'э' - 27: 3, # 'ю' - 16: 2, # 'я' - }, - 39: { # 'ф' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 0, # 'в' - 19: 1, # 'г' - 13: 0, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 1, # 'н' - 1: 3, # 'о' - 15: 1, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 2, # 'у' - 39: 2, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 1, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 2, # 'ы' - 17: 1, # 'ь' - 30: 2, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 26: { # 'х' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 0, # 'б' - 10: 3, # 'в' - 19: 1, # 'г' - 13: 1, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 1, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 1, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 1, # 'п' - 9: 3, # 'р' - 7: 2, # 'с' - 6: 2, # 'т' - 14: 2, # 'у' - 39: 1, # 'ф' - 26: 1, # 'х' - 28: 1, # 'ц' - 22: 1, # 'ч' - 25: 2, # 'ш' - 29: 0, # 'щ' - 54: 1, # 'ъ' - 18: 0, # 'ы' - 17: 1, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 28: { # 'ц' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 2, # 'в' - 19: 1, # 'г' - 13: 1, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 1, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 2, # 'к' - 8: 1, # 'л' - 12: 1, # 'м' - 5: 1, # 'н' - 1: 3, # 'о' - 15: 0, # 'п' - 9: 1, # 'р' - 7: 0, # 'с' - 6: 1, # 'т' - 14: 3, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 1, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 3, # 'ы' - 17: 1, # 'ь' - 30: 0, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 22: { # 'ч' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 1, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 3, # 'е' - 24: 1, # 'ж' - 20: 0, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 2, # 'л' - 12: 1, # 'м' - 5: 3, # 'н' - 1: 2, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 1, # 'с' - 6: 3, # 'т' - 14: 3, # 'у' - 39: 1, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 1, # 'ч' - 25: 2, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 3, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 25: { # 'ш' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 1, # 'б' - 10: 2, # 'в' - 19: 1, # 'г' - 13: 0, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 2, # 'м' - 5: 3, # 'н' - 1: 3, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 1, # 'с' - 6: 2, # 'т' - 14: 3, # 'у' - 39: 2, # 'ф' - 26: 1, # 'х' - 28: 1, # 'ц' - 22: 1, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 3, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 0, # 'я' - }, - 29: { # 'щ' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 3, # 'а' - 21: 0, # 'б' - 10: 1, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 3, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 3, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 1, # 'м' - 5: 2, # 'н' - 1: 1, # 'о' - 15: 0, # 'п' - 9: 2, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 2, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 2, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 0, # 'я' - }, - 54: { # 'ъ' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 0, # 'б' - 10: 0, # 'в' - 19: 0, # 'г' - 13: 0, # 'д' - 2: 2, # 'е' - 24: 0, # 'ж' - 20: 0, # 'з' - 4: 0, # 'и' - 23: 0, # 'й' - 11: 0, # 'к' - 8: 0, # 'л' - 12: 0, # 'м' - 5: 0, # 'н' - 1: 0, # 'о' - 15: 0, # 'п' - 9: 0, # 'р' - 7: 0, # 'с' - 6: 0, # 'т' - 14: 0, # 'у' - 39: 0, # 'ф' - 26: 0, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 0, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 1, # 'ю' - 16: 2, # 'я' - }, - 18: { # 'ы' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 3, # 'б' - 10: 3, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 2, # 'и' - 23: 3, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 1, # 'о' - 15: 3, # 'п' - 9: 3, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 1, # 'у' - 39: 0, # 'ф' - 26: 3, # 'х' - 28: 2, # 'ц' - 22: 3, # 'ч' - 25: 3, # 'ш' - 29: 2, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 0, # 'ю' - 16: 2, # 'я' - }, - 17: { # 'ь' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 2, # 'б' - 10: 2, # 'в' - 19: 2, # 'г' - 13: 2, # 'д' - 2: 3, # 'е' - 24: 1, # 'ж' - 20: 3, # 'з' - 4: 2, # 'и' - 23: 0, # 'й' - 11: 3, # 'к' - 8: 0, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 2, # 'о' - 15: 2, # 'п' - 9: 1, # 'р' - 7: 3, # 'с' - 6: 2, # 'т' - 14: 0, # 'у' - 39: 2, # 'ф' - 26: 1, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 3, # 'ш' - 29: 2, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 3, # 'ю' - 16: 3, # 'я' - }, - 30: { # 'э' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 1, # 'М' - 31: 1, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 1, # 'Р' - 32: 1, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 1, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 1, # 'б' - 10: 1, # 'в' - 19: 1, # 'г' - 13: 2, # 'д' - 2: 1, # 'е' - 24: 0, # 'ж' - 20: 1, # 'з' - 4: 0, # 'и' - 23: 2, # 'й' - 11: 2, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 2, # 'н' - 1: 0, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 2, # 'с' - 6: 3, # 'т' - 14: 1, # 'у' - 39: 2, # 'ф' - 26: 1, # 'х' - 28: 0, # 'ц' - 22: 0, # 'ч' - 25: 1, # 'ш' - 29: 0, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 1, # 'ю' - 16: 1, # 'я' - }, - 27: { # 'ю' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 2, # 'а' - 21: 3, # 'б' - 10: 1, # 'в' - 19: 2, # 'г' - 13: 3, # 'д' - 2: 1, # 'е' - 24: 2, # 'ж' - 20: 2, # 'з' - 4: 1, # 'и' - 23: 1, # 'й' - 11: 2, # 'к' - 8: 2, # 'л' - 12: 2, # 'м' - 5: 2, # 'н' - 1: 1, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 0, # 'у' - 39: 1, # 'ф' - 26: 2, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 2, # 'ш' - 29: 3, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 1, # 'э' - 27: 2, # 'ю' - 16: 1, # 'я' - }, - 16: { # 'я' - 37: 0, # 'А' - 44: 0, # 'Б' - 33: 0, # 'В' - 46: 0, # 'Г' - 41: 0, # 'Д' - 48: 0, # 'Е' - 56: 0, # 'Ж' - 51: 0, # 'З' - 42: 0, # 'И' - 60: 0, # 'Й' - 36: 0, # 'К' - 49: 0, # 'Л' - 38: 0, # 'М' - 31: 0, # 'Н' - 34: 0, # 'О' - 35: 0, # 'П' - 45: 0, # 'Р' - 32: 0, # 'С' - 40: 0, # 'Т' - 52: 0, # 'У' - 53: 0, # 'Ф' - 55: 0, # 'Х' - 58: 0, # 'Ц' - 50: 0, # 'Ч' - 57: 0, # 'Ш' - 63: 0, # 'Щ' - 62: 0, # 'Ы' - 61: 0, # 'Ь' - 47: 0, # 'Э' - 59: 0, # 'Ю' - 43: 0, # 'Я' - 3: 0, # 'а' - 21: 2, # 'б' - 10: 3, # 'в' - 19: 2, # 'г' - 13: 3, # 'д' - 2: 3, # 'е' - 24: 3, # 'ж' - 20: 3, # 'з' - 4: 2, # 'и' - 23: 2, # 'й' - 11: 3, # 'к' - 8: 3, # 'л' - 12: 3, # 'м' - 5: 3, # 'н' - 1: 0, # 'о' - 15: 2, # 'п' - 9: 2, # 'р' - 7: 3, # 'с' - 6: 3, # 'т' - 14: 1, # 'у' - 39: 1, # 'ф' - 26: 3, # 'х' - 28: 2, # 'ц' - 22: 2, # 'ч' - 25: 2, # 'ш' - 29: 3, # 'щ' - 54: 0, # 'ъ' - 18: 0, # 'ы' - 17: 0, # 'ь' - 30: 0, # 'э' - 27: 2, # 'ю' - 16: 2, # 'я' - }, -} - -# 255: Undefined characters that did not exist in training text -# 254: Carriage/Return -# 253: symbol (punctuation) that does not belong to word -# 252: 0 - 9 -# 251: Control characters - -# Character Mapping Table(s): -IBM866_RUSSIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 142, # 'A' - 66: 143, # 'B' - 67: 144, # 'C' - 68: 145, # 'D' - 69: 146, # 'E' - 70: 147, # 'F' - 71: 148, # 'G' - 72: 149, # 'H' - 73: 150, # 'I' - 74: 151, # 'J' - 75: 152, # 'K' - 76: 74, # 'L' - 77: 153, # 'M' - 78: 75, # 'N' - 79: 154, # 'O' - 80: 155, # 'P' - 81: 156, # 'Q' - 82: 157, # 'R' - 83: 158, # 'S' - 84: 159, # 'T' - 85: 160, # 'U' - 86: 161, # 'V' - 87: 162, # 'W' - 88: 163, # 'X' - 89: 164, # 'Y' - 90: 165, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 71, # 'a' - 98: 172, # 'b' - 99: 66, # 'c' - 100: 173, # 'd' - 101: 65, # 'e' - 102: 174, # 'f' - 103: 76, # 'g' - 104: 175, # 'h' - 105: 64, # 'i' - 106: 176, # 'j' - 107: 177, # 'k' - 108: 77, # 'l' - 109: 72, # 'm' - 110: 178, # 'n' - 111: 69, # 'o' - 112: 67, # 'p' - 113: 179, # 'q' - 114: 78, # 'r' - 115: 73, # 's' - 116: 180, # 't' - 117: 181, # 'u' - 118: 79, # 'v' - 119: 182, # 'w' - 120: 183, # 'x' - 121: 184, # 'y' - 122: 185, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 37, # 'А' - 129: 44, # 'Б' - 130: 33, # 'В' - 131: 46, # 'Г' - 132: 41, # 'Д' - 133: 48, # 'Е' - 134: 56, # 'Ж' - 135: 51, # 'З' - 136: 42, # 'И' - 137: 60, # 'Й' - 138: 36, # 'К' - 139: 49, # 'Л' - 140: 38, # 'М' - 141: 31, # 'Н' - 142: 34, # 'О' - 143: 35, # 'П' - 144: 45, # 'Р' - 145: 32, # 'С' - 146: 40, # 'Т' - 147: 52, # 'У' - 148: 53, # 'Ф' - 149: 55, # 'Х' - 150: 58, # 'Ц' - 151: 50, # 'Ч' - 152: 57, # 'Ш' - 153: 63, # 'Щ' - 154: 70, # 'Ъ' - 155: 62, # 'Ы' - 156: 61, # 'Ь' - 157: 47, # 'Э' - 158: 59, # 'Ю' - 159: 43, # 'Я' - 160: 3, # 'а' - 161: 21, # 'б' - 162: 10, # 'в' - 163: 19, # 'г' - 164: 13, # 'д' - 165: 2, # 'е' - 166: 24, # 'ж' - 167: 20, # 'з' - 168: 4, # 'и' - 169: 23, # 'й' - 170: 11, # 'к' - 171: 8, # 'л' - 172: 12, # 'м' - 173: 5, # 'н' - 174: 1, # 'о' - 175: 15, # 'п' - 176: 191, # '░' - 177: 192, # '▒' - 178: 193, # '▓' - 179: 194, # '│' - 180: 195, # '┤' - 181: 196, # '╡' - 182: 197, # '╢' - 183: 198, # '╖' - 184: 199, # '╕' - 185: 200, # '╣' - 186: 201, # '║' - 187: 202, # '╗' - 188: 203, # '╝' - 189: 204, # '╜' - 190: 205, # '╛' - 191: 206, # '┐' - 192: 207, # '└' - 193: 208, # '┴' - 194: 209, # '┬' - 195: 210, # '├' - 196: 211, # '─' - 197: 212, # '┼' - 198: 213, # '╞' - 199: 214, # '╟' - 200: 215, # '╚' - 201: 216, # '╔' - 202: 217, # '╩' - 203: 218, # '╦' - 204: 219, # '╠' - 205: 220, # '═' - 206: 221, # '╬' - 207: 222, # '╧' - 208: 223, # '╨' - 209: 224, # '╤' - 210: 225, # '╥' - 211: 226, # '╙' - 212: 227, # '╘' - 213: 228, # '╒' - 214: 229, # '╓' - 215: 230, # '╫' - 216: 231, # '╪' - 217: 232, # '┘' - 218: 233, # '┌' - 219: 234, # '█' - 220: 235, # '▄' - 221: 236, # '▌' - 222: 237, # '▐' - 223: 238, # '▀' - 224: 9, # 'р' - 225: 7, # 'с' - 226: 6, # 'т' - 227: 14, # 'у' - 228: 39, # 'ф' - 229: 26, # 'х' - 230: 28, # 'ц' - 231: 22, # 'ч' - 232: 25, # 'ш' - 233: 29, # 'щ' - 234: 54, # 'ъ' - 235: 18, # 'ы' - 236: 17, # 'ь' - 237: 30, # 'э' - 238: 27, # 'ю' - 239: 16, # 'я' - 240: 239, # 'Ё' - 241: 68, # 'ё' - 242: 240, # 'Є' - 243: 241, # 'є' - 244: 242, # 'Ї' - 245: 243, # 'ї' - 246: 244, # 'Ў' - 247: 245, # 'ў' - 248: 246, # '°' - 249: 247, # '∙' - 250: 248, # '·' - 251: 249, # '√' - 252: 250, # '№' - 253: 251, # '¤' - 254: 252, # '■' - 255: 255, # '\xa0' -} - -IBM866_RUSSIAN_MODEL = SingleByteCharSetModel( - charset_name="IBM866", - language="Russian", - char_to_order_map=IBM866_RUSSIAN_CHAR_TO_ORDER, - language_model=RUSSIAN_LANG_MODEL, - typical_positive_ratio=0.976601, - keep_ascii_letters=False, - alphabet="ЁАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюяё", -) - -WINDOWS_1251_RUSSIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 142, # 'A' - 66: 143, # 'B' - 67: 144, # 'C' - 68: 145, # 'D' - 69: 146, # 'E' - 70: 147, # 'F' - 71: 148, # 'G' - 72: 149, # 'H' - 73: 150, # 'I' - 74: 151, # 'J' - 75: 152, # 'K' - 76: 74, # 'L' - 77: 153, # 'M' - 78: 75, # 'N' - 79: 154, # 'O' - 80: 155, # 'P' - 81: 156, # 'Q' - 82: 157, # 'R' - 83: 158, # 'S' - 84: 159, # 'T' - 85: 160, # 'U' - 86: 161, # 'V' - 87: 162, # 'W' - 88: 163, # 'X' - 89: 164, # 'Y' - 90: 165, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 71, # 'a' - 98: 172, # 'b' - 99: 66, # 'c' - 100: 173, # 'd' - 101: 65, # 'e' - 102: 174, # 'f' - 103: 76, # 'g' - 104: 175, # 'h' - 105: 64, # 'i' - 106: 176, # 'j' - 107: 177, # 'k' - 108: 77, # 'l' - 109: 72, # 'm' - 110: 178, # 'n' - 111: 69, # 'o' - 112: 67, # 'p' - 113: 179, # 'q' - 114: 78, # 'r' - 115: 73, # 's' - 116: 180, # 't' - 117: 181, # 'u' - 118: 79, # 'v' - 119: 182, # 'w' - 120: 183, # 'x' - 121: 184, # 'y' - 122: 185, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 191, # 'Ђ' - 129: 192, # 'Ѓ' - 130: 193, # '‚' - 131: 194, # 'ѓ' - 132: 195, # '„' - 133: 196, # '…' - 134: 197, # '†' - 135: 198, # '‡' - 136: 199, # '€' - 137: 200, # '‰' - 138: 201, # 'Љ' - 139: 202, # '‹' - 140: 203, # 'Њ' - 141: 204, # 'Ќ' - 142: 205, # 'Ћ' - 143: 206, # 'Џ' - 144: 207, # 'ђ' - 145: 208, # '‘' - 146: 209, # '’' - 147: 210, # '“' - 148: 211, # '”' - 149: 212, # '•' - 150: 213, # '–' - 151: 214, # '—' - 152: 215, # None - 153: 216, # '™' - 154: 217, # 'љ' - 155: 218, # '›' - 156: 219, # 'њ' - 157: 220, # 'ќ' - 158: 221, # 'ћ' - 159: 222, # 'џ' - 160: 223, # '\xa0' - 161: 224, # 'Ў' - 162: 225, # 'ў' - 163: 226, # 'Ј' - 164: 227, # '¤' - 165: 228, # 'Ґ' - 166: 229, # '¦' - 167: 230, # '§' - 168: 231, # 'Ё' - 169: 232, # '©' - 170: 233, # 'Є' - 171: 234, # '«' - 172: 235, # '¬' - 173: 236, # '\xad' - 174: 237, # '®' - 175: 238, # 'Ї' - 176: 239, # '°' - 177: 240, # '±' - 178: 241, # 'І' - 179: 242, # 'і' - 180: 243, # 'ґ' - 181: 244, # 'µ' - 182: 245, # '¶' - 183: 246, # '·' - 184: 68, # 'ё' - 185: 247, # '№' - 186: 248, # 'є' - 187: 249, # '»' - 188: 250, # 'ј' - 189: 251, # 'Ѕ' - 190: 252, # 'ѕ' - 191: 253, # 'ї' - 192: 37, # 'А' - 193: 44, # 'Б' - 194: 33, # 'В' - 195: 46, # 'Г' - 196: 41, # 'Д' - 197: 48, # 'Е' - 198: 56, # 'Ж' - 199: 51, # 'З' - 200: 42, # 'И' - 201: 60, # 'Й' - 202: 36, # 'К' - 203: 49, # 'Л' - 204: 38, # 'М' - 205: 31, # 'Н' - 206: 34, # 'О' - 207: 35, # 'П' - 208: 45, # 'Р' - 209: 32, # 'С' - 210: 40, # 'Т' - 211: 52, # 'У' - 212: 53, # 'Ф' - 213: 55, # 'Х' - 214: 58, # 'Ц' - 215: 50, # 'Ч' - 216: 57, # 'Ш' - 217: 63, # 'Щ' - 218: 70, # 'Ъ' - 219: 62, # 'Ы' - 220: 61, # 'Ь' - 221: 47, # 'Э' - 222: 59, # 'Ю' - 223: 43, # 'Я' - 224: 3, # 'а' - 225: 21, # 'б' - 226: 10, # 'в' - 227: 19, # 'г' - 228: 13, # 'д' - 229: 2, # 'е' - 230: 24, # 'ж' - 231: 20, # 'з' - 232: 4, # 'и' - 233: 23, # 'й' - 234: 11, # 'к' - 235: 8, # 'л' - 236: 12, # 'м' - 237: 5, # 'н' - 238: 1, # 'о' - 239: 15, # 'п' - 240: 9, # 'р' - 241: 7, # 'с' - 242: 6, # 'т' - 243: 14, # 'у' - 244: 39, # 'ф' - 245: 26, # 'х' - 246: 28, # 'ц' - 247: 22, # 'ч' - 248: 25, # 'ш' - 249: 29, # 'щ' - 250: 54, # 'ъ' - 251: 18, # 'ы' - 252: 17, # 'ь' - 253: 30, # 'э' - 254: 27, # 'ю' - 255: 16, # 'я' -} - -WINDOWS_1251_RUSSIAN_MODEL = SingleByteCharSetModel( - charset_name="windows-1251", - language="Russian", - char_to_order_map=WINDOWS_1251_RUSSIAN_CHAR_TO_ORDER, - language_model=RUSSIAN_LANG_MODEL, - typical_positive_ratio=0.976601, - keep_ascii_letters=False, - alphabet="ЁАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюяё", -) - -IBM855_RUSSIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 142, # 'A' - 66: 143, # 'B' - 67: 144, # 'C' - 68: 145, # 'D' - 69: 146, # 'E' - 70: 147, # 'F' - 71: 148, # 'G' - 72: 149, # 'H' - 73: 150, # 'I' - 74: 151, # 'J' - 75: 152, # 'K' - 76: 74, # 'L' - 77: 153, # 'M' - 78: 75, # 'N' - 79: 154, # 'O' - 80: 155, # 'P' - 81: 156, # 'Q' - 82: 157, # 'R' - 83: 158, # 'S' - 84: 159, # 'T' - 85: 160, # 'U' - 86: 161, # 'V' - 87: 162, # 'W' - 88: 163, # 'X' - 89: 164, # 'Y' - 90: 165, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 71, # 'a' - 98: 172, # 'b' - 99: 66, # 'c' - 100: 173, # 'd' - 101: 65, # 'e' - 102: 174, # 'f' - 103: 76, # 'g' - 104: 175, # 'h' - 105: 64, # 'i' - 106: 176, # 'j' - 107: 177, # 'k' - 108: 77, # 'l' - 109: 72, # 'm' - 110: 178, # 'n' - 111: 69, # 'o' - 112: 67, # 'p' - 113: 179, # 'q' - 114: 78, # 'r' - 115: 73, # 's' - 116: 180, # 't' - 117: 181, # 'u' - 118: 79, # 'v' - 119: 182, # 'w' - 120: 183, # 'x' - 121: 184, # 'y' - 122: 185, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 191, # 'ђ' - 129: 192, # 'Ђ' - 130: 193, # 'ѓ' - 131: 194, # 'Ѓ' - 132: 68, # 'ё' - 133: 195, # 'Ё' - 134: 196, # 'є' - 135: 197, # 'Є' - 136: 198, # 'ѕ' - 137: 199, # 'Ѕ' - 138: 200, # 'і' - 139: 201, # 'І' - 140: 202, # 'ї' - 141: 203, # 'Ї' - 142: 204, # 'ј' - 143: 205, # 'Ј' - 144: 206, # 'љ' - 145: 207, # 'Љ' - 146: 208, # 'њ' - 147: 209, # 'Њ' - 148: 210, # 'ћ' - 149: 211, # 'Ћ' - 150: 212, # 'ќ' - 151: 213, # 'Ќ' - 152: 214, # 'ў' - 153: 215, # 'Ў' - 154: 216, # 'џ' - 155: 217, # 'Џ' - 156: 27, # 'ю' - 157: 59, # 'Ю' - 158: 54, # 'ъ' - 159: 70, # 'Ъ' - 160: 3, # 'а' - 161: 37, # 'А' - 162: 21, # 'б' - 163: 44, # 'Б' - 164: 28, # 'ц' - 165: 58, # 'Ц' - 166: 13, # 'д' - 167: 41, # 'Д' - 168: 2, # 'е' - 169: 48, # 'Е' - 170: 39, # 'ф' - 171: 53, # 'Ф' - 172: 19, # 'г' - 173: 46, # 'Г' - 174: 218, # '«' - 175: 219, # '»' - 176: 220, # '░' - 177: 221, # '▒' - 178: 222, # '▓' - 179: 223, # '│' - 180: 224, # '┤' - 181: 26, # 'х' - 182: 55, # 'Х' - 183: 4, # 'и' - 184: 42, # 'И' - 185: 225, # '╣' - 186: 226, # '║' - 187: 227, # '╗' - 188: 228, # '╝' - 189: 23, # 'й' - 190: 60, # 'Й' - 191: 229, # '┐' - 192: 230, # '└' - 193: 231, # '┴' - 194: 232, # '┬' - 195: 233, # '├' - 196: 234, # '─' - 197: 235, # '┼' - 198: 11, # 'к' - 199: 36, # 'К' - 200: 236, # '╚' - 201: 237, # '╔' - 202: 238, # '╩' - 203: 239, # '╦' - 204: 240, # '╠' - 205: 241, # '═' - 206: 242, # '╬' - 207: 243, # '¤' - 208: 8, # 'л' - 209: 49, # 'Л' - 210: 12, # 'м' - 211: 38, # 'М' - 212: 5, # 'н' - 213: 31, # 'Н' - 214: 1, # 'о' - 215: 34, # 'О' - 216: 15, # 'п' - 217: 244, # '┘' - 218: 245, # '┌' - 219: 246, # '█' - 220: 247, # '▄' - 221: 35, # 'П' - 222: 16, # 'я' - 223: 248, # '▀' - 224: 43, # 'Я' - 225: 9, # 'р' - 226: 45, # 'Р' - 227: 7, # 'с' - 228: 32, # 'С' - 229: 6, # 'т' - 230: 40, # 'Т' - 231: 14, # 'у' - 232: 52, # 'У' - 233: 24, # 'ж' - 234: 56, # 'Ж' - 235: 10, # 'в' - 236: 33, # 'В' - 237: 17, # 'ь' - 238: 61, # 'Ь' - 239: 249, # '№' - 240: 250, # '\xad' - 241: 18, # 'ы' - 242: 62, # 'Ы' - 243: 20, # 'з' - 244: 51, # 'З' - 245: 25, # 'ш' - 246: 57, # 'Ш' - 247: 30, # 'э' - 248: 47, # 'Э' - 249: 29, # 'щ' - 250: 63, # 'Щ' - 251: 22, # 'ч' - 252: 50, # 'Ч' - 253: 251, # '§' - 254: 252, # '■' - 255: 255, # '\xa0' -} - -IBM855_RUSSIAN_MODEL = SingleByteCharSetModel( - charset_name="IBM855", - language="Russian", - char_to_order_map=IBM855_RUSSIAN_CHAR_TO_ORDER, - language_model=RUSSIAN_LANG_MODEL, - typical_positive_ratio=0.976601, - keep_ascii_letters=False, - alphabet="ЁАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюяё", -) - -KOI8_R_RUSSIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 142, # 'A' - 66: 143, # 'B' - 67: 144, # 'C' - 68: 145, # 'D' - 69: 146, # 'E' - 70: 147, # 'F' - 71: 148, # 'G' - 72: 149, # 'H' - 73: 150, # 'I' - 74: 151, # 'J' - 75: 152, # 'K' - 76: 74, # 'L' - 77: 153, # 'M' - 78: 75, # 'N' - 79: 154, # 'O' - 80: 155, # 'P' - 81: 156, # 'Q' - 82: 157, # 'R' - 83: 158, # 'S' - 84: 159, # 'T' - 85: 160, # 'U' - 86: 161, # 'V' - 87: 162, # 'W' - 88: 163, # 'X' - 89: 164, # 'Y' - 90: 165, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 71, # 'a' - 98: 172, # 'b' - 99: 66, # 'c' - 100: 173, # 'd' - 101: 65, # 'e' - 102: 174, # 'f' - 103: 76, # 'g' - 104: 175, # 'h' - 105: 64, # 'i' - 106: 176, # 'j' - 107: 177, # 'k' - 108: 77, # 'l' - 109: 72, # 'm' - 110: 178, # 'n' - 111: 69, # 'o' - 112: 67, # 'p' - 113: 179, # 'q' - 114: 78, # 'r' - 115: 73, # 's' - 116: 180, # 't' - 117: 181, # 'u' - 118: 79, # 'v' - 119: 182, # 'w' - 120: 183, # 'x' - 121: 184, # 'y' - 122: 185, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 191, # '─' - 129: 192, # '│' - 130: 193, # '┌' - 131: 194, # '┐' - 132: 195, # '└' - 133: 196, # '┘' - 134: 197, # '├' - 135: 198, # '┤' - 136: 199, # '┬' - 137: 200, # '┴' - 138: 201, # '┼' - 139: 202, # '▀' - 140: 203, # '▄' - 141: 204, # '█' - 142: 205, # '▌' - 143: 206, # '▐' - 144: 207, # '░' - 145: 208, # '▒' - 146: 209, # '▓' - 147: 210, # '⌠' - 148: 211, # '■' - 149: 212, # '∙' - 150: 213, # '√' - 151: 214, # '≈' - 152: 215, # '≤' - 153: 216, # '≥' - 154: 217, # '\xa0' - 155: 218, # '⌡' - 156: 219, # '°' - 157: 220, # '²' - 158: 221, # '·' - 159: 222, # '÷' - 160: 223, # '═' - 161: 224, # '║' - 162: 225, # '╒' - 163: 68, # 'ё' - 164: 226, # '╓' - 165: 227, # '╔' - 166: 228, # '╕' - 167: 229, # '╖' - 168: 230, # '╗' - 169: 231, # '╘' - 170: 232, # '╙' - 171: 233, # '╚' - 172: 234, # '╛' - 173: 235, # '╜' - 174: 236, # '╝' - 175: 237, # '╞' - 176: 238, # '╟' - 177: 239, # '╠' - 178: 240, # '╡' - 179: 241, # 'Ё' - 180: 242, # '╢' - 181: 243, # '╣' - 182: 244, # '╤' - 183: 245, # '╥' - 184: 246, # '╦' - 185: 247, # '╧' - 186: 248, # '╨' - 187: 249, # '╩' - 188: 250, # '╪' - 189: 251, # '╫' - 190: 252, # '╬' - 191: 253, # '©' - 192: 27, # 'ю' - 193: 3, # 'а' - 194: 21, # 'б' - 195: 28, # 'ц' - 196: 13, # 'д' - 197: 2, # 'е' - 198: 39, # 'ф' - 199: 19, # 'г' - 200: 26, # 'х' - 201: 4, # 'и' - 202: 23, # 'й' - 203: 11, # 'к' - 204: 8, # 'л' - 205: 12, # 'м' - 206: 5, # 'н' - 207: 1, # 'о' - 208: 15, # 'п' - 209: 16, # 'я' - 210: 9, # 'р' - 211: 7, # 'с' - 212: 6, # 'т' - 213: 14, # 'у' - 214: 24, # 'ж' - 215: 10, # 'в' - 216: 17, # 'ь' - 217: 18, # 'ы' - 218: 20, # 'з' - 219: 25, # 'ш' - 220: 30, # 'э' - 221: 29, # 'щ' - 222: 22, # 'ч' - 223: 54, # 'ъ' - 224: 59, # 'Ю' - 225: 37, # 'А' - 226: 44, # 'Б' - 227: 58, # 'Ц' - 228: 41, # 'Д' - 229: 48, # 'Е' - 230: 53, # 'Ф' - 231: 46, # 'Г' - 232: 55, # 'Х' - 233: 42, # 'И' - 234: 60, # 'Й' - 235: 36, # 'К' - 236: 49, # 'Л' - 237: 38, # 'М' - 238: 31, # 'Н' - 239: 34, # 'О' - 240: 35, # 'П' - 241: 43, # 'Я' - 242: 45, # 'Р' - 243: 32, # 'С' - 244: 40, # 'Т' - 245: 52, # 'У' - 246: 56, # 'Ж' - 247: 33, # 'В' - 248: 61, # 'Ь' - 249: 62, # 'Ы' - 250: 51, # 'З' - 251: 57, # 'Ш' - 252: 47, # 'Э' - 253: 63, # 'Щ' - 254: 50, # 'Ч' - 255: 70, # 'Ъ' -} - -KOI8_R_RUSSIAN_MODEL = SingleByteCharSetModel( - charset_name="KOI8-R", - language="Russian", - char_to_order_map=KOI8_R_RUSSIAN_CHAR_TO_ORDER, - language_model=RUSSIAN_LANG_MODEL, - typical_positive_ratio=0.976601, - keep_ascii_letters=False, - alphabet="ЁАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюяё", -) - -MACCYRILLIC_RUSSIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 142, # 'A' - 66: 143, # 'B' - 67: 144, # 'C' - 68: 145, # 'D' - 69: 146, # 'E' - 70: 147, # 'F' - 71: 148, # 'G' - 72: 149, # 'H' - 73: 150, # 'I' - 74: 151, # 'J' - 75: 152, # 'K' - 76: 74, # 'L' - 77: 153, # 'M' - 78: 75, # 'N' - 79: 154, # 'O' - 80: 155, # 'P' - 81: 156, # 'Q' - 82: 157, # 'R' - 83: 158, # 'S' - 84: 159, # 'T' - 85: 160, # 'U' - 86: 161, # 'V' - 87: 162, # 'W' - 88: 163, # 'X' - 89: 164, # 'Y' - 90: 165, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 71, # 'a' - 98: 172, # 'b' - 99: 66, # 'c' - 100: 173, # 'd' - 101: 65, # 'e' - 102: 174, # 'f' - 103: 76, # 'g' - 104: 175, # 'h' - 105: 64, # 'i' - 106: 176, # 'j' - 107: 177, # 'k' - 108: 77, # 'l' - 109: 72, # 'm' - 110: 178, # 'n' - 111: 69, # 'o' - 112: 67, # 'p' - 113: 179, # 'q' - 114: 78, # 'r' - 115: 73, # 's' - 116: 180, # 't' - 117: 181, # 'u' - 118: 79, # 'v' - 119: 182, # 'w' - 120: 183, # 'x' - 121: 184, # 'y' - 122: 185, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 37, # 'А' - 129: 44, # 'Б' - 130: 33, # 'В' - 131: 46, # 'Г' - 132: 41, # 'Д' - 133: 48, # 'Е' - 134: 56, # 'Ж' - 135: 51, # 'З' - 136: 42, # 'И' - 137: 60, # 'Й' - 138: 36, # 'К' - 139: 49, # 'Л' - 140: 38, # 'М' - 141: 31, # 'Н' - 142: 34, # 'О' - 143: 35, # 'П' - 144: 45, # 'Р' - 145: 32, # 'С' - 146: 40, # 'Т' - 147: 52, # 'У' - 148: 53, # 'Ф' - 149: 55, # 'Х' - 150: 58, # 'Ц' - 151: 50, # 'Ч' - 152: 57, # 'Ш' - 153: 63, # 'Щ' - 154: 70, # 'Ъ' - 155: 62, # 'Ы' - 156: 61, # 'Ь' - 157: 47, # 'Э' - 158: 59, # 'Ю' - 159: 43, # 'Я' - 160: 191, # '†' - 161: 192, # '°' - 162: 193, # 'Ґ' - 163: 194, # '£' - 164: 195, # '§' - 165: 196, # '•' - 166: 197, # '¶' - 167: 198, # 'І' - 168: 199, # '®' - 169: 200, # '©' - 170: 201, # '™' - 171: 202, # 'Ђ' - 172: 203, # 'ђ' - 173: 204, # '≠' - 174: 205, # 'Ѓ' - 175: 206, # 'ѓ' - 176: 207, # '∞' - 177: 208, # '±' - 178: 209, # '≤' - 179: 210, # '≥' - 180: 211, # 'і' - 181: 212, # 'µ' - 182: 213, # 'ґ' - 183: 214, # 'Ј' - 184: 215, # 'Є' - 185: 216, # 'є' - 186: 217, # 'Ї' - 187: 218, # 'ї' - 188: 219, # 'Љ' - 189: 220, # 'љ' - 190: 221, # 'Њ' - 191: 222, # 'њ' - 192: 223, # 'ј' - 193: 224, # 'Ѕ' - 194: 225, # '¬' - 195: 226, # '√' - 196: 227, # 'ƒ' - 197: 228, # '≈' - 198: 229, # '∆' - 199: 230, # '«' - 200: 231, # '»' - 201: 232, # '…' - 202: 233, # '\xa0' - 203: 234, # 'Ћ' - 204: 235, # 'ћ' - 205: 236, # 'Ќ' - 206: 237, # 'ќ' - 207: 238, # 'ѕ' - 208: 239, # '–' - 209: 240, # '—' - 210: 241, # '“' - 211: 242, # '”' - 212: 243, # '‘' - 213: 244, # '’' - 214: 245, # '÷' - 215: 246, # '„' - 216: 247, # 'Ў' - 217: 248, # 'ў' - 218: 249, # 'Џ' - 219: 250, # 'џ' - 220: 251, # '№' - 221: 252, # 'Ё' - 222: 68, # 'ё' - 223: 16, # 'я' - 224: 3, # 'а' - 225: 21, # 'б' - 226: 10, # 'в' - 227: 19, # 'г' - 228: 13, # 'д' - 229: 2, # 'е' - 230: 24, # 'ж' - 231: 20, # 'з' - 232: 4, # 'и' - 233: 23, # 'й' - 234: 11, # 'к' - 235: 8, # 'л' - 236: 12, # 'м' - 237: 5, # 'н' - 238: 1, # 'о' - 239: 15, # 'п' - 240: 9, # 'р' - 241: 7, # 'с' - 242: 6, # 'т' - 243: 14, # 'у' - 244: 39, # 'ф' - 245: 26, # 'х' - 246: 28, # 'ц' - 247: 22, # 'ч' - 248: 25, # 'ш' - 249: 29, # 'щ' - 250: 54, # 'ъ' - 251: 18, # 'ы' - 252: 17, # 'ь' - 253: 30, # 'э' - 254: 27, # 'ю' - 255: 255, # '€' -} - -MACCYRILLIC_RUSSIAN_MODEL = SingleByteCharSetModel( - charset_name="MacCyrillic", - language="Russian", - char_to_order_map=MACCYRILLIC_RUSSIAN_CHAR_TO_ORDER, - language_model=RUSSIAN_LANG_MODEL, - typical_positive_ratio=0.976601, - keep_ascii_letters=False, - alphabet="ЁАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюяё", -) - -ISO_8859_5_RUSSIAN_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 142, # 'A' - 66: 143, # 'B' - 67: 144, # 'C' - 68: 145, # 'D' - 69: 146, # 'E' - 70: 147, # 'F' - 71: 148, # 'G' - 72: 149, # 'H' - 73: 150, # 'I' - 74: 151, # 'J' - 75: 152, # 'K' - 76: 74, # 'L' - 77: 153, # 'M' - 78: 75, # 'N' - 79: 154, # 'O' - 80: 155, # 'P' - 81: 156, # 'Q' - 82: 157, # 'R' - 83: 158, # 'S' - 84: 159, # 'T' - 85: 160, # 'U' - 86: 161, # 'V' - 87: 162, # 'W' - 88: 163, # 'X' - 89: 164, # 'Y' - 90: 165, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 71, # 'a' - 98: 172, # 'b' - 99: 66, # 'c' - 100: 173, # 'd' - 101: 65, # 'e' - 102: 174, # 'f' - 103: 76, # 'g' - 104: 175, # 'h' - 105: 64, # 'i' - 106: 176, # 'j' - 107: 177, # 'k' - 108: 77, # 'l' - 109: 72, # 'm' - 110: 178, # 'n' - 111: 69, # 'o' - 112: 67, # 'p' - 113: 179, # 'q' - 114: 78, # 'r' - 115: 73, # 's' - 116: 180, # 't' - 117: 181, # 'u' - 118: 79, # 'v' - 119: 182, # 'w' - 120: 183, # 'x' - 121: 184, # 'y' - 122: 185, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 191, # '\x80' - 129: 192, # '\x81' - 130: 193, # '\x82' - 131: 194, # '\x83' - 132: 195, # '\x84' - 133: 196, # '\x85' - 134: 197, # '\x86' - 135: 198, # '\x87' - 136: 199, # '\x88' - 137: 200, # '\x89' - 138: 201, # '\x8a' - 139: 202, # '\x8b' - 140: 203, # '\x8c' - 141: 204, # '\x8d' - 142: 205, # '\x8e' - 143: 206, # '\x8f' - 144: 207, # '\x90' - 145: 208, # '\x91' - 146: 209, # '\x92' - 147: 210, # '\x93' - 148: 211, # '\x94' - 149: 212, # '\x95' - 150: 213, # '\x96' - 151: 214, # '\x97' - 152: 215, # '\x98' - 153: 216, # '\x99' - 154: 217, # '\x9a' - 155: 218, # '\x9b' - 156: 219, # '\x9c' - 157: 220, # '\x9d' - 158: 221, # '\x9e' - 159: 222, # '\x9f' - 160: 223, # '\xa0' - 161: 224, # 'Ё' - 162: 225, # 'Ђ' - 163: 226, # 'Ѓ' - 164: 227, # 'Є' - 165: 228, # 'Ѕ' - 166: 229, # 'І' - 167: 230, # 'Ї' - 168: 231, # 'Ј' - 169: 232, # 'Љ' - 170: 233, # 'Њ' - 171: 234, # 'Ћ' - 172: 235, # 'Ќ' - 173: 236, # '\xad' - 174: 237, # 'Ў' - 175: 238, # 'Џ' - 176: 37, # 'А' - 177: 44, # 'Б' - 178: 33, # 'В' - 179: 46, # 'Г' - 180: 41, # 'Д' - 181: 48, # 'Е' - 182: 56, # 'Ж' - 183: 51, # 'З' - 184: 42, # 'И' - 185: 60, # 'Й' - 186: 36, # 'К' - 187: 49, # 'Л' - 188: 38, # 'М' - 189: 31, # 'Н' - 190: 34, # 'О' - 191: 35, # 'П' - 192: 45, # 'Р' - 193: 32, # 'С' - 194: 40, # 'Т' - 195: 52, # 'У' - 196: 53, # 'Ф' - 197: 55, # 'Х' - 198: 58, # 'Ц' - 199: 50, # 'Ч' - 200: 57, # 'Ш' - 201: 63, # 'Щ' - 202: 70, # 'Ъ' - 203: 62, # 'Ы' - 204: 61, # 'Ь' - 205: 47, # 'Э' - 206: 59, # 'Ю' - 207: 43, # 'Я' - 208: 3, # 'а' - 209: 21, # 'б' - 210: 10, # 'в' - 211: 19, # 'г' - 212: 13, # 'д' - 213: 2, # 'е' - 214: 24, # 'ж' - 215: 20, # 'з' - 216: 4, # 'и' - 217: 23, # 'й' - 218: 11, # 'к' - 219: 8, # 'л' - 220: 12, # 'м' - 221: 5, # 'н' - 222: 1, # 'о' - 223: 15, # 'п' - 224: 9, # 'р' - 225: 7, # 'с' - 226: 6, # 'т' - 227: 14, # 'у' - 228: 39, # 'ф' - 229: 26, # 'х' - 230: 28, # 'ц' - 231: 22, # 'ч' - 232: 25, # 'ш' - 233: 29, # 'щ' - 234: 54, # 'ъ' - 235: 18, # 'ы' - 236: 17, # 'ь' - 237: 30, # 'э' - 238: 27, # 'ю' - 239: 16, # 'я' - 240: 239, # '№' - 241: 68, # 'ё' - 242: 240, # 'ђ' - 243: 241, # 'ѓ' - 244: 242, # 'є' - 245: 243, # 'ѕ' - 246: 244, # 'і' - 247: 245, # 'ї' - 248: 246, # 'ј' - 249: 247, # 'љ' - 250: 248, # 'њ' - 251: 249, # 'ћ' - 252: 250, # 'ќ' - 253: 251, # '§' - 254: 252, # 'ў' - 255: 255, # 'џ' -} - -ISO_8859_5_RUSSIAN_MODEL = SingleByteCharSetModel( - charset_name="ISO-8859-5", - language="Russian", - char_to_order_map=ISO_8859_5_RUSSIAN_CHAR_TO_ORDER, - language_model=RUSSIAN_LANG_MODEL, - typical_positive_ratio=0.976601, - keep_ascii_letters=False, - alphabet="ЁАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюяё", -) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langthaimodel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langthaimodel.py deleted file mode 100644 index 489cad9..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langthaimodel.py +++ /dev/null @@ -1,4380 +0,0 @@ -from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel - -# 3: Positive -# 2: Likely -# 1: Unlikely -# 0: Negative - -THAI_LANG_MODEL = { - 5: { # 'ก' - 5: 2, # 'ก' - 30: 2, # 'ข' - 24: 2, # 'ค' - 8: 2, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 3, # 'ฎ' - 57: 2, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 2, # 'ณ' - 20: 2, # 'ด' - 19: 3, # 'ต' - 44: 0, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 1, # 'บ' - 25: 2, # 'ป' - 39: 1, # 'ผ' - 62: 1, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 2, # 'ม' - 16: 1, # 'ย' - 2: 3, # 'ร' - 61: 2, # 'ฤ' - 15: 3, # 'ล' - 12: 3, # 'ว' - 42: 2, # 'ศ' - 46: 3, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 3, # 'อ' - 63: 1, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 3, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 0, # 'ึ' - 27: 2, # 'ื' - 32: 2, # 'ุ' - 35: 1, # 'ู' - 11: 2, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 1, # 'ใ' - 33: 2, # 'ไ' - 50: 1, # 'ๆ' - 37: 3, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 30: { # 'ข' - 5: 1, # 'ก' - 30: 0, # 'ข' - 24: 1, # 'ค' - 8: 1, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 2, # 'ณ' - 20: 0, # 'ด' - 19: 2, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 1, # 'บ' - 25: 1, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 2, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 1, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 2, # 'ี' - 40: 3, # 'ึ' - 27: 1, # 'ื' - 32: 1, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 1, # '็' - 6: 2, # '่' - 7: 3, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 24: { # 'ค' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 2, # 'ค' - 8: 2, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 2, # 'ณ' - 20: 2, # 'ด' - 19: 2, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 0, # 'บ' - 25: 1, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 2, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 3, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 2, # 'า' - 36: 3, # 'ำ' - 23: 3, # 'ิ' - 13: 2, # 'ี' - 40: 0, # 'ึ' - 27: 3, # 'ื' - 32: 3, # 'ุ' - 35: 2, # 'ู' - 11: 1, # 'เ' - 28: 0, # 'แ' - 41: 3, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 1, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 3, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 8: { # 'ง' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 3, # 'ค' - 8: 2, # 'ง' - 26: 2, # 'จ' - 52: 1, # 'ฉ' - 34: 2, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 3, # 'ท' - 48: 1, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 2, # 'ผ' - 62: 1, # 'ฝ' - 31: 2, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 2, # 'ม' - 16: 1, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 2, # 'ว' - 42: 2, # 'ศ' - 46: 1, # 'ษ' - 18: 3, # 'ส' - 21: 3, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 1, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 2, # 'ิ' - 13: 1, # 'ี' - 40: 0, # 'ึ' - 27: 1, # 'ื' - 32: 1, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 3, # 'ๆ' - 37: 0, # '็' - 6: 2, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 26: { # 'จ' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 0, # 'ค' - 8: 2, # 'ง' - 26: 3, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 1, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 1, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 1, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 1, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 3, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 3, # 'ำ' - 23: 2, # 'ิ' - 13: 1, # 'ี' - 40: 3, # 'ึ' - 27: 1, # 'ื' - 32: 3, # 'ุ' - 35: 2, # 'ู' - 11: 1, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 2, # '่' - 7: 2, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 52: { # 'ฉ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 3, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 3, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 1, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 1, # 'ะ' - 10: 1, # 'ั' - 1: 1, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 1, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 1, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 34: { # 'ช' - 5: 1, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 1, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 1, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 1, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 2, # 'ั' - 1: 3, # 'า' - 36: 1, # 'ำ' - 23: 3, # 'ิ' - 13: 2, # 'ี' - 40: 0, # 'ึ' - 27: 3, # 'ื' - 32: 3, # 'ุ' - 35: 1, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 1, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 51: { # 'ซ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 1, # 'ั' - 1: 1, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 2, # 'ี' - 40: 3, # 'ึ' - 27: 2, # 'ื' - 32: 1, # 'ุ' - 35: 1, # 'ู' - 11: 1, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 1, # '็' - 6: 1, # '่' - 7: 2, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 47: { # 'ญ' - 5: 1, # 'ก' - 30: 1, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 3, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 1, # 'บ' - 25: 1, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 2, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 1, # 'ะ' - 10: 2, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 1, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 1, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 0, # 'ไ' - 50: 1, # 'ๆ' - 37: 0, # '็' - 6: 2, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 58: { # 'ฎ' - 5: 2, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 1, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 2, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 57: { # 'ฏ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 3, # 'ิ' - 13: 1, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 49: { # 'ฐ' - 5: 1, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 2, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 53: { # 'ฑ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 2, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 3, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 55: { # 'ฒ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 43: { # 'ณ' - 5: 1, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 3, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 3, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 1, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 3, # 'ะ' - 10: 0, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 2, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 1, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 3, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 20: { # 'ด' - 5: 2, # 'ก' - 30: 2, # 'ข' - 24: 2, # 'ค' - 8: 3, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 1, # 'บ' - 25: 1, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 2, # 'ม' - 16: 3, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 3, # 'ั' - 1: 2, # 'า' - 36: 2, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 1, # 'ึ' - 27: 2, # 'ื' - 32: 3, # 'ุ' - 35: 2, # 'ู' - 11: 2, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 2, # 'ๆ' - 37: 2, # '็' - 6: 1, # '่' - 7: 3, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 19: { # 'ต' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 1, # 'ค' - 8: 0, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 1, # 'ต' - 44: 2, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 1, # 'บ' - 25: 1, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 2, # 'ภ' - 9: 1, # 'ม' - 16: 1, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 3, # 'ส' - 21: 0, # 'ห' - 4: 3, # 'อ' - 63: 1, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 2, # 'ำ' - 23: 3, # 'ิ' - 13: 2, # 'ี' - 40: 1, # 'ึ' - 27: 1, # 'ื' - 32: 3, # 'ุ' - 35: 2, # 'ู' - 11: 1, # 'เ' - 28: 1, # 'แ' - 41: 1, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 2, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 44: { # 'ถ' - 5: 1, # 'ก' - 30: 0, # 'ข' - 24: 1, # 'ค' - 8: 0, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 2, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 2, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 2, # 'ิ' - 13: 1, # 'ี' - 40: 3, # 'ึ' - 27: 2, # 'ื' - 32: 2, # 'ุ' - 35: 3, # 'ู' - 11: 1, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 2, # '่' - 7: 3, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 14: { # 'ท' - 5: 1, # 'ก' - 30: 1, # 'ข' - 24: 3, # 'ค' - 8: 1, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 3, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 2, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 3, # 'ย' - 2: 3, # 'ร' - 61: 1, # 'ฤ' - 15: 1, # 'ล' - 12: 2, # 'ว' - 42: 3, # 'ศ' - 46: 1, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 3, # 'ำ' - 23: 2, # 'ิ' - 13: 3, # 'ี' - 40: 2, # 'ึ' - 27: 1, # 'ื' - 32: 3, # 'ุ' - 35: 1, # 'ู' - 11: 0, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 1, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 48: { # 'ธ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 1, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 2, # 'า' - 36: 0, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 2, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 3, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 3: { # 'น' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 3, # 'ค' - 8: 1, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 1, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 2, # 'ถ' - 14: 3, # 'ท' - 48: 3, # 'ธ' - 3: 2, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 2, # 'ผ' - 62: 0, # 'ฝ' - 31: 2, # 'พ' - 54: 1, # 'ฟ' - 45: 1, # 'ภ' - 9: 2, # 'ม' - 16: 2, # 'ย' - 2: 2, # 'ร' - 61: 1, # 'ฤ' - 15: 2, # 'ล' - 12: 3, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 3, # 'อ' - 63: 1, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 3, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 3, # 'ึ' - 27: 3, # 'ื' - 32: 3, # 'ุ' - 35: 2, # 'ู' - 11: 3, # 'เ' - 28: 2, # 'แ' - 41: 3, # 'โ' - 29: 3, # 'ใ' - 33: 3, # 'ไ' - 50: 2, # 'ๆ' - 37: 1, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 17: { # 'บ' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 2, # 'ค' - 8: 1, # 'ง' - 26: 1, # 'จ' - 52: 1, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 3, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 2, # 'ป' - 39: 2, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 1, # 'ฟ' - 45: 1, # 'ภ' - 9: 1, # 'ม' - 16: 0, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 3, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 2, # 'อ' - 63: 1, # 'ฯ' - 22: 0, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 2, # 'ำ' - 23: 2, # 'ิ' - 13: 2, # 'ี' - 40: 0, # 'ึ' - 27: 2, # 'ื' - 32: 3, # 'ุ' - 35: 2, # 'ู' - 11: 2, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 0, # 'ๆ' - 37: 1, # '็' - 6: 2, # '่' - 7: 2, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 25: { # 'ป' - 5: 2, # 'ก' - 30: 0, # 'ข' - 24: 1, # 'ค' - 8: 0, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 1, # 'ฎ' - 57: 3, # 'ฏ' - 49: 1, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 1, # 'ต' - 44: 1, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 0, # 'บ' - 25: 1, # 'ป' - 39: 1, # 'ผ' - 62: 1, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 0, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 1, # 'ษ' - 18: 2, # 'ส' - 21: 1, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 1, # 'ะ' - 10: 3, # 'ั' - 1: 1, # 'า' - 36: 0, # 'ำ' - 23: 2, # 'ิ' - 13: 3, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 1, # 'ุ' - 35: 0, # 'ู' - 11: 1, # 'เ' - 28: 2, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 2, # 'ไ' - 50: 0, # 'ๆ' - 37: 3, # '็' - 6: 1, # '่' - 7: 2, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 39: { # 'ผ' - 5: 1, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 1, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 2, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 1, # 'ะ' - 10: 1, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 2, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 1, # 'ื' - 32: 0, # 'ุ' - 35: 3, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 1, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 62: { # 'ฝ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 1, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 1, # 'ี' - 40: 2, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 2, # '่' - 7: 1, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 31: { # 'พ' - 5: 1, # 'ก' - 30: 1, # 'ข' - 24: 1, # 'ค' - 8: 1, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 1, # 'ณ' - 20: 1, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 2, # 'ท' - 48: 1, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 0, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 2, # 'ย' - 2: 3, # 'ร' - 61: 2, # 'ฤ' - 15: 2, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 1, # 'ห' - 4: 2, # 'อ' - 63: 1, # 'ฯ' - 22: 0, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 3, # 'ิ' - 13: 2, # 'ี' - 40: 1, # 'ึ' - 27: 3, # 'ื' - 32: 1, # 'ุ' - 35: 2, # 'ู' - 11: 1, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 1, # '็' - 6: 0, # '่' - 7: 1, # '้' - 38: 3, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 54: { # 'ฟ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 2, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 2, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 1, # 'ี' - 40: 0, # 'ึ' - 27: 1, # 'ื' - 32: 1, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 2, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 45: { # 'ภ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 1, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 3, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 2, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 9: { # 'ม' - 5: 2, # 'ก' - 30: 2, # 'ข' - 24: 2, # 'ค' - 8: 2, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 1, # 'ณ' - 20: 2, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 1, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 3, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 2, # 'ม' - 16: 1, # 'ย' - 2: 2, # 'ร' - 61: 2, # 'ฤ' - 15: 2, # 'ล' - 12: 2, # 'ว' - 42: 1, # 'ศ' - 46: 1, # 'ษ' - 18: 3, # 'ส' - 21: 3, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 1, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 0, # 'ึ' - 27: 3, # 'ื' - 32: 3, # 'ุ' - 35: 3, # 'ู' - 11: 2, # 'เ' - 28: 2, # 'แ' - 41: 2, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 1, # 'ๆ' - 37: 1, # '็' - 6: 3, # '่' - 7: 2, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 16: { # 'ย' - 5: 3, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 3, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 2, # 'ช' - 51: 0, # 'ซ' - 47: 2, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 1, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 1, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 2, # 'ม' - 16: 0, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 3, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 1, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 2, # 'ิ' - 13: 3, # 'ี' - 40: 1, # 'ึ' - 27: 2, # 'ื' - 32: 2, # 'ุ' - 35: 3, # 'ู' - 11: 2, # 'เ' - 28: 1, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 2, # 'ๆ' - 37: 1, # '็' - 6: 3, # '่' - 7: 2, # '้' - 38: 3, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 2: { # 'ร' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 2, # 'ค' - 8: 3, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 2, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 3, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 3, # 'ณ' - 20: 2, # 'ด' - 19: 2, # 'ต' - 44: 3, # 'ถ' - 14: 3, # 'ท' - 48: 1, # 'ธ' - 3: 2, # 'น' - 17: 2, # 'บ' - 25: 3, # 'ป' - 39: 2, # 'ผ' - 62: 1, # 'ฝ' - 31: 2, # 'พ' - 54: 1, # 'ฟ' - 45: 1, # 'ภ' - 9: 3, # 'ม' - 16: 2, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 3, # 'ว' - 42: 2, # 'ศ' - 46: 2, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 3, # 'อ' - 63: 1, # 'ฯ' - 22: 3, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 2, # 'ึ' - 27: 3, # 'ื' - 32: 3, # 'ุ' - 35: 3, # 'ู' - 11: 3, # 'เ' - 28: 3, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 3, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 3, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 61: { # 'ฤ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 2, # 'ต' - 44: 0, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 2, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 15: { # 'ล' - 5: 2, # 'ก' - 30: 3, # 'ข' - 24: 1, # 'ค' - 8: 3, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 1, # 'ม' - 16: 3, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 1, # 'ห' - 4: 3, # 'อ' - 63: 2, # 'ฯ' - 22: 3, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 2, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 2, # 'ึ' - 27: 3, # 'ื' - 32: 2, # 'ุ' - 35: 3, # 'ู' - 11: 2, # 'เ' - 28: 1, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 2, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 12: { # 'ว' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 1, # 'ค' - 8: 3, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 1, # 'ณ' - 20: 2, # 'ด' - 19: 1, # 'ต' - 44: 1, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 1, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 1, # 'ฟ' - 45: 0, # 'ภ' - 9: 3, # 'ม' - 16: 3, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 3, # 'ิ' - 13: 2, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 2, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 1, # 'ใ' - 33: 2, # 'ไ' - 50: 1, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 42: { # 'ศ' - 5: 1, # 'ก' - 30: 0, # 'ข' - 24: 1, # 'ค' - 8: 0, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 1, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 2, # 'ว' - 42: 1, # 'ศ' - 46: 2, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 2, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 2, # 'ิ' - 13: 0, # 'ี' - 40: 3, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 2, # 'ู' - 11: 0, # 'เ' - 28: 1, # 'แ' - 41: 0, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 46: { # 'ษ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 2, # 'ฎ' - 57: 1, # 'ฏ' - 49: 2, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 3, # 'ณ' - 20: 0, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 1, # 'ม' - 16: 2, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 2, # 'ะ' - 10: 2, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 1, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 1, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 18: { # 'ส' - 5: 2, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 2, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 3, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 1, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 2, # 'ภ' - 9: 3, # 'ม' - 16: 1, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 2, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 3, # 'ำ' - 23: 3, # 'ิ' - 13: 3, # 'ี' - 40: 2, # 'ึ' - 27: 3, # 'ื' - 32: 3, # 'ุ' - 35: 3, # 'ู' - 11: 2, # 'เ' - 28: 0, # 'แ' - 41: 1, # 'โ' - 29: 0, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 1, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 21: { # 'ห' - 5: 3, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 1, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 2, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 3, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 0, # 'บ' - 25: 1, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 3, # 'ม' - 16: 2, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 1, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 0, # 'ำ' - 23: 1, # 'ิ' - 13: 1, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 1, # 'ุ' - 35: 1, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 3, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 4: { # 'อ' - 5: 3, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 3, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 1, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 1, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 1, # 'ฟ' - 45: 1, # 'ภ' - 9: 3, # 'ม' - 16: 3, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 2, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 2, # 'ะ' - 10: 3, # 'ั' - 1: 3, # 'า' - 36: 2, # 'ำ' - 23: 2, # 'ิ' - 13: 3, # 'ี' - 40: 0, # 'ึ' - 27: 3, # 'ื' - 32: 3, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 1, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 1, # 'ๆ' - 37: 1, # '็' - 6: 2, # '่' - 7: 2, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 63: { # 'ฯ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 22: { # 'ะ' - 5: 3, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 1, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 3, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 1, # 'ถ' - 14: 3, # 'ท' - 48: 1, # 'ธ' - 3: 2, # 'น' - 17: 3, # 'บ' - 25: 2, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 2, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 3, # 'ม' - 16: 2, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 3, # 'ส' - 21: 3, # 'ห' - 4: 2, # 'อ' - 63: 1, # 'ฯ' - 22: 1, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 10: { # 'ั' - 5: 3, # 'ก' - 30: 0, # 'ข' - 24: 1, # 'ค' - 8: 3, # 'ง' - 26: 3, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 3, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 2, # 'ฐ' - 53: 0, # 'ฑ' - 55: 3, # 'ฒ' - 43: 3, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 0, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 1, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 2, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 3, # 'ม' - 16: 3, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 3, # 'ว' - 42: 2, # 'ศ' - 46: 0, # 'ษ' - 18: 3, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 1: { # 'า' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 3, # 'ค' - 8: 3, # 'ง' - 26: 3, # 'จ' - 52: 0, # 'ฉ' - 34: 3, # 'ช' - 51: 1, # 'ซ' - 47: 2, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 3, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 1, # 'ถ' - 14: 3, # 'ท' - 48: 2, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 2, # 'ป' - 39: 1, # 'ผ' - 62: 1, # 'ฝ' - 31: 3, # 'พ' - 54: 1, # 'ฟ' - 45: 1, # 'ภ' - 9: 3, # 'ม' - 16: 3, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 3, # 'ว' - 42: 2, # 'ศ' - 46: 3, # 'ษ' - 18: 3, # 'ส' - 21: 3, # 'ห' - 4: 2, # 'อ' - 63: 1, # 'ฯ' - 22: 3, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 1, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 36: { # 'ำ' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 3, # 'ค' - 8: 2, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 1, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 1, # 'ต' - 44: 1, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 1, # 'บ' - 25: 1, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 1, # 'ม' - 16: 0, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 3, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 23: { # 'ิ' - 5: 3, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 3, # 'ง' - 26: 3, # 'จ' - 52: 0, # 'ฉ' - 34: 3, # 'ช' - 51: 0, # 'ซ' - 47: 2, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 1, # 'ถ' - 14: 3, # 'ท' - 48: 3, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 2, # 'ป' - 39: 2, # 'ผ' - 62: 0, # 'ฝ' - 31: 3, # 'พ' - 54: 1, # 'ฟ' - 45: 2, # 'ภ' - 9: 3, # 'ม' - 16: 2, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 3, # 'ว' - 42: 3, # 'ศ' - 46: 2, # 'ษ' - 18: 2, # 'ส' - 21: 3, # 'ห' - 4: 1, # 'อ' - 63: 1, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 1, # 'แ' - 41: 1, # 'โ' - 29: 1, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 2, # '้' - 38: 2, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 13: { # 'ี' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 2, # 'ค' - 8: 0, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 1, # 'ผ' - 62: 0, # 'ฝ' - 31: 2, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 3, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 2, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 1, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 2, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 1, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 40: { # 'ึ' - 5: 3, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 3, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 1, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 27: { # 'ื' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 3, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 32: { # 'ุ' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 3, # 'ค' - 8: 3, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 2, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 1, # 'ฒ' - 43: 3, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 1, # 'ธ' - 3: 2, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 2, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 1, # 'ภ' - 9: 3, # 'ม' - 16: 1, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 1, # 'ว' - 42: 1, # 'ศ' - 46: 2, # 'ษ' - 18: 1, # 'ส' - 21: 1, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 1, # 'เ' - 28: 0, # 'แ' - 41: 1, # 'โ' - 29: 0, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 2, # '้' - 38: 1, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 35: { # 'ู' - 5: 3, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 2, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 2, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 1, # 'ณ' - 20: 2, # 'ด' - 19: 2, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 2, # 'น' - 17: 0, # 'บ' - 25: 3, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 0, # 'ย' - 2: 1, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 1, # 'เ' - 28: 1, # 'แ' - 41: 1, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 3, # '่' - 7: 3, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 11: { # 'เ' - 5: 3, # 'ก' - 30: 3, # 'ข' - 24: 3, # 'ค' - 8: 2, # 'ง' - 26: 3, # 'จ' - 52: 3, # 'ฉ' - 34: 3, # 'ช' - 51: 2, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 1, # 'ณ' - 20: 3, # 'ด' - 19: 3, # 'ต' - 44: 1, # 'ถ' - 14: 3, # 'ท' - 48: 1, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 3, # 'ป' - 39: 2, # 'ผ' - 62: 1, # 'ฝ' - 31: 3, # 'พ' - 54: 1, # 'ฟ' - 45: 3, # 'ภ' - 9: 3, # 'ม' - 16: 2, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 3, # 'ว' - 42: 2, # 'ศ' - 46: 0, # 'ษ' - 18: 3, # 'ส' - 21: 3, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 28: { # 'แ' - 5: 3, # 'ก' - 30: 2, # 'ข' - 24: 2, # 'ค' - 8: 1, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 3, # 'ต' - 44: 2, # 'ถ' - 14: 3, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 2, # 'ป' - 39: 3, # 'ผ' - 62: 0, # 'ฝ' - 31: 2, # 'พ' - 54: 2, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 2, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 3, # 'ส' - 21: 3, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 41: { # 'โ' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 0, # 'ง' - 26: 1, # 'จ' - 52: 1, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 2, # 'ต' - 44: 0, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 1, # 'บ' - 25: 3, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 1, # 'ฟ' - 45: 1, # 'ภ' - 9: 1, # 'ม' - 16: 2, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 3, # 'ล' - 12: 0, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 0, # 'ห' - 4: 2, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 29: { # 'ใ' - 5: 2, # 'ก' - 30: 0, # 'ข' - 24: 1, # 'ค' - 8: 0, # 'ง' - 26: 3, # 'จ' - 52: 0, # 'ฉ' - 34: 3, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 1, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 3, # 'ส' - 21: 3, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 33: { # 'ไ' - 5: 1, # 'ก' - 30: 2, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 3, # 'ด' - 19: 1, # 'ต' - 44: 0, # 'ถ' - 14: 3, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 1, # 'บ' - 25: 3, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 2, # 'ฟ' - 45: 0, # 'ภ' - 9: 3, # 'ม' - 16: 0, # 'ย' - 2: 3, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 3, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 2, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 50: { # 'ๆ' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 37: { # '็' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 2, # 'ง' - 26: 3, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 1, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 2, # 'ต' - 44: 0, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 3, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 1, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 2, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 0, # 'ห' - 4: 1, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 1, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 6: { # '่' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 3, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 1, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 1, # 'ธ' - 3: 3, # 'น' - 17: 1, # 'บ' - 25: 2, # 'ป' - 39: 2, # 'ผ' - 62: 1, # 'ฝ' - 31: 1, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 3, # 'ม' - 16: 3, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 2, # 'ล' - 12: 3, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 1, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 1, # 'ะ' - 10: 0, # 'ั' - 1: 3, # 'า' - 36: 2, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 3, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 1, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 7: { # '้' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 2, # 'ค' - 8: 3, # 'ง' - 26: 2, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 1, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 1, # 'ด' - 19: 2, # 'ต' - 44: 1, # 'ถ' - 14: 2, # 'ท' - 48: 0, # 'ธ' - 3: 3, # 'น' - 17: 2, # 'บ' - 25: 2, # 'ป' - 39: 2, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 1, # 'ฟ' - 45: 0, # 'ภ' - 9: 3, # 'ม' - 16: 2, # 'ย' - 2: 2, # 'ร' - 61: 0, # 'ฤ' - 15: 1, # 'ล' - 12: 3, # 'ว' - 42: 1, # 'ศ' - 46: 0, # 'ษ' - 18: 2, # 'ส' - 21: 2, # 'ห' - 4: 3, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 3, # 'า' - 36: 2, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 2, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 2, # 'ใ' - 33: 2, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 38: { # '์' - 5: 2, # 'ก' - 30: 1, # 'ข' - 24: 1, # 'ค' - 8: 0, # 'ง' - 26: 1, # 'จ' - 52: 0, # 'ฉ' - 34: 1, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 2, # 'ด' - 19: 1, # 'ต' - 44: 1, # 'ถ' - 14: 1, # 'ท' - 48: 0, # 'ธ' - 3: 1, # 'น' - 17: 1, # 'บ' - 25: 1, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 1, # 'พ' - 54: 1, # 'ฟ' - 45: 0, # 'ภ' - 9: 2, # 'ม' - 16: 0, # 'ย' - 2: 1, # 'ร' - 61: 1, # 'ฤ' - 15: 1, # 'ล' - 12: 1, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 1, # 'ส' - 21: 1, # 'ห' - 4: 2, # 'อ' - 63: 1, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 2, # 'เ' - 28: 2, # 'แ' - 41: 1, # 'โ' - 29: 1, # 'ใ' - 33: 1, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 0, # '๑' - 59: 0, # '๒' - 60: 0, # '๕' - }, - 56: { # '๑' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 2, # '๑' - 59: 1, # '๒' - 60: 1, # '๕' - }, - 59: { # '๒' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 1, # '๑' - 59: 1, # '๒' - 60: 3, # '๕' - }, - 60: { # '๕' - 5: 0, # 'ก' - 30: 0, # 'ข' - 24: 0, # 'ค' - 8: 0, # 'ง' - 26: 0, # 'จ' - 52: 0, # 'ฉ' - 34: 0, # 'ช' - 51: 0, # 'ซ' - 47: 0, # 'ญ' - 58: 0, # 'ฎ' - 57: 0, # 'ฏ' - 49: 0, # 'ฐ' - 53: 0, # 'ฑ' - 55: 0, # 'ฒ' - 43: 0, # 'ณ' - 20: 0, # 'ด' - 19: 0, # 'ต' - 44: 0, # 'ถ' - 14: 0, # 'ท' - 48: 0, # 'ธ' - 3: 0, # 'น' - 17: 0, # 'บ' - 25: 0, # 'ป' - 39: 0, # 'ผ' - 62: 0, # 'ฝ' - 31: 0, # 'พ' - 54: 0, # 'ฟ' - 45: 0, # 'ภ' - 9: 0, # 'ม' - 16: 0, # 'ย' - 2: 0, # 'ร' - 61: 0, # 'ฤ' - 15: 0, # 'ล' - 12: 0, # 'ว' - 42: 0, # 'ศ' - 46: 0, # 'ษ' - 18: 0, # 'ส' - 21: 0, # 'ห' - 4: 0, # 'อ' - 63: 0, # 'ฯ' - 22: 0, # 'ะ' - 10: 0, # 'ั' - 1: 0, # 'า' - 36: 0, # 'ำ' - 23: 0, # 'ิ' - 13: 0, # 'ี' - 40: 0, # 'ึ' - 27: 0, # 'ื' - 32: 0, # 'ุ' - 35: 0, # 'ู' - 11: 0, # 'เ' - 28: 0, # 'แ' - 41: 0, # 'โ' - 29: 0, # 'ใ' - 33: 0, # 'ไ' - 50: 0, # 'ๆ' - 37: 0, # '็' - 6: 0, # '่' - 7: 0, # '้' - 38: 0, # '์' - 56: 2, # '๑' - 59: 1, # '๒' - 60: 0, # '๕' - }, -} - -# 255: Undefined characters that did not exist in training text -# 254: Carriage/Return -# 253: symbol (punctuation) that does not belong to word -# 252: 0 - 9 -# 251: Control characters - -# Character Mapping Table(s): -TIS_620_THAI_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 254, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 254, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 253, # ' ' - 33: 253, # '!' - 34: 253, # '"' - 35: 253, # '#' - 36: 253, # '$' - 37: 253, # '%' - 38: 253, # '&' - 39: 253, # "'" - 40: 253, # '(' - 41: 253, # ')' - 42: 253, # '*' - 43: 253, # '+' - 44: 253, # ',' - 45: 253, # '-' - 46: 253, # '.' - 47: 253, # '/' - 48: 252, # '0' - 49: 252, # '1' - 50: 252, # '2' - 51: 252, # '3' - 52: 252, # '4' - 53: 252, # '5' - 54: 252, # '6' - 55: 252, # '7' - 56: 252, # '8' - 57: 252, # '9' - 58: 253, # ':' - 59: 253, # ';' - 60: 253, # '<' - 61: 253, # '=' - 62: 253, # '>' - 63: 253, # '?' - 64: 253, # '@' - 65: 182, # 'A' - 66: 106, # 'B' - 67: 107, # 'C' - 68: 100, # 'D' - 69: 183, # 'E' - 70: 184, # 'F' - 71: 185, # 'G' - 72: 101, # 'H' - 73: 94, # 'I' - 74: 186, # 'J' - 75: 187, # 'K' - 76: 108, # 'L' - 77: 109, # 'M' - 78: 110, # 'N' - 79: 111, # 'O' - 80: 188, # 'P' - 81: 189, # 'Q' - 82: 190, # 'R' - 83: 89, # 'S' - 84: 95, # 'T' - 85: 112, # 'U' - 86: 113, # 'V' - 87: 191, # 'W' - 88: 192, # 'X' - 89: 193, # 'Y' - 90: 194, # 'Z' - 91: 253, # '[' - 92: 253, # '\\' - 93: 253, # ']' - 94: 253, # '^' - 95: 253, # '_' - 96: 253, # '`' - 97: 64, # 'a' - 98: 72, # 'b' - 99: 73, # 'c' - 100: 114, # 'd' - 101: 74, # 'e' - 102: 115, # 'f' - 103: 116, # 'g' - 104: 102, # 'h' - 105: 81, # 'i' - 106: 201, # 'j' - 107: 117, # 'k' - 108: 90, # 'l' - 109: 103, # 'm' - 110: 78, # 'n' - 111: 82, # 'o' - 112: 96, # 'p' - 113: 202, # 'q' - 114: 91, # 'r' - 115: 79, # 's' - 116: 84, # 't' - 117: 104, # 'u' - 118: 105, # 'v' - 119: 97, # 'w' - 120: 98, # 'x' - 121: 92, # 'y' - 122: 203, # 'z' - 123: 253, # '{' - 124: 253, # '|' - 125: 253, # '}' - 126: 253, # '~' - 127: 253, # '\x7f' - 128: 209, # '\x80' - 129: 210, # '\x81' - 130: 211, # '\x82' - 131: 212, # '\x83' - 132: 213, # '\x84' - 133: 88, # '\x85' - 134: 214, # '\x86' - 135: 215, # '\x87' - 136: 216, # '\x88' - 137: 217, # '\x89' - 138: 218, # '\x8a' - 139: 219, # '\x8b' - 140: 220, # '\x8c' - 141: 118, # '\x8d' - 142: 221, # '\x8e' - 143: 222, # '\x8f' - 144: 223, # '\x90' - 145: 224, # '\x91' - 146: 99, # '\x92' - 147: 85, # '\x93' - 148: 83, # '\x94' - 149: 225, # '\x95' - 150: 226, # '\x96' - 151: 227, # '\x97' - 152: 228, # '\x98' - 153: 229, # '\x99' - 154: 230, # '\x9a' - 155: 231, # '\x9b' - 156: 232, # '\x9c' - 157: 233, # '\x9d' - 158: 234, # '\x9e' - 159: 235, # '\x9f' - 160: 236, # None - 161: 5, # 'ก' - 162: 30, # 'ข' - 163: 237, # 'ฃ' - 164: 24, # 'ค' - 165: 238, # 'ฅ' - 166: 75, # 'ฆ' - 167: 8, # 'ง' - 168: 26, # 'จ' - 169: 52, # 'ฉ' - 170: 34, # 'ช' - 171: 51, # 'ซ' - 172: 119, # 'ฌ' - 173: 47, # 'ญ' - 174: 58, # 'ฎ' - 175: 57, # 'ฏ' - 176: 49, # 'ฐ' - 177: 53, # 'ฑ' - 178: 55, # 'ฒ' - 179: 43, # 'ณ' - 180: 20, # 'ด' - 181: 19, # 'ต' - 182: 44, # 'ถ' - 183: 14, # 'ท' - 184: 48, # 'ธ' - 185: 3, # 'น' - 186: 17, # 'บ' - 187: 25, # 'ป' - 188: 39, # 'ผ' - 189: 62, # 'ฝ' - 190: 31, # 'พ' - 191: 54, # 'ฟ' - 192: 45, # 'ภ' - 193: 9, # 'ม' - 194: 16, # 'ย' - 195: 2, # 'ร' - 196: 61, # 'ฤ' - 197: 15, # 'ล' - 198: 239, # 'ฦ' - 199: 12, # 'ว' - 200: 42, # 'ศ' - 201: 46, # 'ษ' - 202: 18, # 'ส' - 203: 21, # 'ห' - 204: 76, # 'ฬ' - 205: 4, # 'อ' - 206: 66, # 'ฮ' - 207: 63, # 'ฯ' - 208: 22, # 'ะ' - 209: 10, # 'ั' - 210: 1, # 'า' - 211: 36, # 'ำ' - 212: 23, # 'ิ' - 213: 13, # 'ี' - 214: 40, # 'ึ' - 215: 27, # 'ื' - 216: 32, # 'ุ' - 217: 35, # 'ู' - 218: 86, # 'ฺ' - 219: 240, # None - 220: 241, # None - 221: 242, # None - 222: 243, # None - 223: 244, # '฿' - 224: 11, # 'เ' - 225: 28, # 'แ' - 226: 41, # 'โ' - 227: 29, # 'ใ' - 228: 33, # 'ไ' - 229: 245, # 'ๅ' - 230: 50, # 'ๆ' - 231: 37, # '็' - 232: 6, # '่' - 233: 7, # '้' - 234: 67, # '๊' - 235: 77, # '๋' - 236: 38, # '์' - 237: 93, # 'ํ' - 238: 246, # '๎' - 239: 247, # '๏' - 240: 68, # '๐' - 241: 56, # '๑' - 242: 59, # '๒' - 243: 65, # '๓' - 244: 69, # '๔' - 245: 60, # '๕' - 246: 70, # '๖' - 247: 80, # '๗' - 248: 71, # '๘' - 249: 87, # '๙' - 250: 248, # '๚' - 251: 249, # '๛' - 252: 250, # None - 253: 251, # None - 254: 252, # None - 255: 253, # None -} - -TIS_620_THAI_MODEL = SingleByteCharSetModel( - charset_name="TIS-620", - language="Thai", - char_to_order_map=TIS_620_THAI_CHAR_TO_ORDER, - language_model=THAI_LANG_MODEL, - typical_positive_ratio=0.926386, - keep_ascii_letters=False, - alphabet="กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลฦวศษสหฬอฮฯะัาำิีึืฺุู฿เแโใไๅๆ็่้๊๋์ํ๎๏๐๑๒๓๔๕๖๗๘๙๚๛", -) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langturkishmodel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langturkishmodel.py deleted file mode 100644 index 291857c..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/langturkishmodel.py +++ /dev/null @@ -1,4380 +0,0 @@ -from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel - -# 3: Positive -# 2: Likely -# 1: Unlikely -# 0: Negative - -TURKISH_LANG_MODEL = { - 23: { # 'A' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 1, # 'h' - 3: 1, # 'i' - 24: 0, # 'j' - 10: 2, # 'k' - 5: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 1, # 'r' - 8: 1, # 's' - 9: 1, # 't' - 14: 1, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 0, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 37: { # 'B' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 2, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 1, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 1, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 0, # 'ı' - 40: 1, # 'Ş' - 19: 1, # 'ş' - }, - 47: { # 'C' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 1, # 'L' - 20: 0, # 'M' - 46: 1, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 1, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 2, # 'j' - 10: 1, # 'k' - 5: 2, # 'l' - 13: 2, # 'm' - 4: 2, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 2, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 1, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 39: { # 'D' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 1, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 1, # 'l' - 13: 3, # 'm' - 4: 0, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 1, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 0, # 'İ' - 6: 1, # 'ı' - 40: 1, # 'Ş' - 19: 0, # 'ş' - }, - 29: { # 'E' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 1, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 0, # 'h' - 3: 1, # 'i' - 24: 1, # 'j' - 10: 0, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 1, # 's' - 9: 1, # 't' - 14: 1, # 'u' - 32: 1, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 52: { # 'F' - 23: 0, # 'A' - 37: 1, # 'B' - 47: 1, # 'C' - 39: 1, # 'D' - 29: 1, # 'E' - 52: 2, # 'F' - 36: 0, # 'G' - 45: 2, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 1, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 1, # 'b' - 28: 1, # 'c' - 12: 1, # 'd' - 2: 0, # 'e' - 18: 1, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 2, # 'i' - 24: 1, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 1, # 'm' - 4: 2, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 2, # 'r' - 8: 1, # 's' - 9: 1, # 't' - 14: 1, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 1, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 1, # 'Ö' - 55: 2, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 2, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 2, # 'ş' - }, - 36: { # 'G' - 23: 1, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 2, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 2, # 'N' - 42: 1, # 'O' - 48: 1, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 1, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 1, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 0, # 'r' - 8: 1, # 's' - 9: 1, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 2, # 'Ö' - 55: 0, # 'Ü' - 59: 1, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 2, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 45: { # 'H' - 23: 0, # 'A' - 37: 1, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 2, # 'G' - 45: 1, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 1, # 'L' - 20: 0, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 2, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 2, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 15: 1, # 'o' - 26: 1, # 'p' - 7: 1, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 2, # 'ğ' - 41: 1, # 'İ' - 6: 0, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 53: { # 'I' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 2, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 0, # 'ı' - 40: 1, # 'Ş' - 19: 1, # 'ş' - }, - 60: { # 'J' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 1, # 'd' - 2: 0, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 1, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 1, # 's' - 9: 0, # 't' - 14: 0, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 0, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 16: { # 'K' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 3, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 1, # 'e' - 18: 3, # 'f' - 27: 3, # 'g' - 25: 3, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 0, # 'u' - 32: 3, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 2, # 'ü' - 30: 0, # 'ğ' - 41: 1, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 49: { # 'L' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 2, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 2, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 0, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 2, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 2, # 'n' - 15: 1, # 'o' - 26: 1, # 'p' - 7: 1, # 'r' - 8: 1, # 's' - 9: 1, # 't' - 14: 0, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 2, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 1, # 'ü' - 30: 1, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 20: { # 'M' - 23: 1, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 1, # 'h' - 3: 2, # 'i' - 24: 2, # 'j' - 10: 2, # 'k' - 5: 2, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 3, # 'r' - 8: 0, # 's' - 9: 2, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 3, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 46: { # 'N' - 23: 0, # 'A' - 37: 1, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 1, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 2, # 'j' - 10: 1, # 'k' - 5: 1, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 1, # 'o' - 26: 1, # 'p' - 7: 1, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 1, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 1, # 'İ' - 6: 2, # 'ı' - 40: 1, # 'Ş' - 19: 1, # 'ş' - }, - 42: { # 'O' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 0, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 1, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 0, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 2, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 2, # 'İ' - 6: 1, # 'ı' - 40: 1, # 'Ş' - 19: 1, # 'ş' - }, - 48: { # 'P' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 2, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 1, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 15: 2, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 2, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 2, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 2, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 0, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 44: { # 'R' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 1, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 2, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 1, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 1, # 'ü' - 30: 1, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 1, # 'Ş' - 19: 1, # 'ş' - }, - 35: { # 'S' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 1, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 1, # 'l' - 13: 2, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 1, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 2, # 'Ç' - 50: 2, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 3, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 31: { # 'T' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 0, # 'c' - 12: 1, # 'd' - 2: 3, # 'e' - 18: 2, # 'f' - 27: 2, # 'g' - 25: 0, # 'h' - 3: 1, # 'i' - 24: 1, # 'j' - 10: 2, # 'k' - 5: 2, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 2, # 'p' - 7: 2, # 'r' - 8: 0, # 's' - 9: 2, # 't' - 14: 2, # 'u' - 32: 1, # 'v' - 57: 1, # 'w' - 58: 1, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 51: { # 'U' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 1, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 1, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 1, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 1, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 2, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 1, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 38: { # 'V' - 23: 1, # 'A' - 37: 1, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 1, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 2, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 15: 2, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 1, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 1, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 1, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 3, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 62: { # 'W' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 0, # 'd' - 2: 0, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 0, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 0, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 0, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 43: { # 'Y' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 0, # 'G' - 45: 1, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 2, # 'N' - 42: 0, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 1, # 'j' - 10: 1, # 'k' - 5: 1, # 'l' - 13: 3, # 'm' - 4: 0, # 'n' - 15: 2, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 2, # 'Ö' - 55: 1, # 'Ü' - 59: 1, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 0, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 56: { # 'Z' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 2, # 'Z' - 1: 2, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 2, # 'i' - 24: 1, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 1, # 'r' - 8: 1, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 1, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 1: { # 'a' - 23: 3, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 3, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 1, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 3, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 2, # 'Z' - 1: 2, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 2, # 'e' - 18: 3, # 'f' - 27: 3, # 'g' - 25: 3, # 'h' - 3: 3, # 'i' - 24: 3, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 3, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 3, # 'v' - 57: 2, # 'w' - 58: 0, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 1, # 'î' - 34: 1, # 'ö' - 17: 3, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 21: { # 'b' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 3, # 'g' - 25: 1, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 3, # 'p' - 7: 1, # 'r' - 8: 2, # 's' - 9: 2, # 't' - 14: 2, # 'u' - 32: 1, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 28: { # 'c' - 23: 0, # 'A' - 37: 1, # 'B' - 47: 1, # 'C' - 39: 1, # 'D' - 29: 2, # 'E' - 52: 0, # 'F' - 36: 2, # 'G' - 45: 2, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 2, # 'T' - 51: 2, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 3, # 'Y' - 56: 0, # 'Z' - 1: 1, # 'a' - 21: 1, # 'b' - 28: 2, # 'c' - 12: 2, # 'd' - 2: 1, # 'e' - 18: 1, # 'f' - 27: 2, # 'g' - 25: 2, # 'h' - 3: 3, # 'i' - 24: 1, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 15: 2, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 1, # 'u' - 32: 0, # 'v' - 57: 1, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 1, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 1, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 1, # 'î' - 34: 2, # 'ö' - 17: 2, # 'ü' - 30: 2, # 'ğ' - 41: 1, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 2, # 'ş' - }, - 12: { # 'd' - 23: 1, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 2, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 1, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 1, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 1, # 'f' - 27: 3, # 'g' - 25: 3, # 'h' - 3: 2, # 'i' - 24: 3, # 'j' - 10: 2, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 2, # 's' - 9: 2, # 't' - 14: 3, # 'u' - 32: 1, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 3, # 'y' - 22: 1, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 2: { # 'e' - 23: 2, # 'A' - 37: 0, # 'B' - 47: 2, # 'C' - 39: 0, # 'D' - 29: 3, # 'E' - 52: 1, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 1, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 1, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 1, # 'R' - 35: 0, # 'S' - 31: 3, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 2, # 'e' - 18: 3, # 'f' - 27: 3, # 'g' - 25: 3, # 'h' - 3: 3, # 'i' - 24: 3, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 3, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 3, # 'v' - 57: 2, # 'w' - 58: 0, # 'x' - 11: 3, # 'y' - 22: 1, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 3, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 18: { # 'f' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 2, # 'f' - 27: 1, # 'g' - 25: 1, # 'h' - 3: 1, # 'i' - 24: 1, # 'j' - 10: 1, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 2, # 'p' - 7: 1, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 1, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 1, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 1, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 27: { # 'g' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 1, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 1, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 2, # 'g' - 25: 1, # 'h' - 3: 2, # 'i' - 24: 3, # 'j' - 10: 2, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 2, # 'r' - 8: 2, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 1, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 1, # 'y' - 22: 0, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 25: { # 'h' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 2, # 'h' - 3: 2, # 'i' - 24: 3, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 1, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 2, # 't' - 14: 3, # 'u' - 32: 2, # 'v' - 57: 1, # 'w' - 58: 0, # 'x' - 11: 1, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 3: { # 'i' - 23: 2, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 0, # 'N' - 42: 1, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 1, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 2, # 'f' - 27: 3, # 'g' - 25: 1, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 3, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 2, # 'v' - 57: 1, # 'w' - 58: 1, # 'x' - 11: 3, # 'y' - 22: 1, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 1, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 3, # 'ü' - 30: 0, # 'ğ' - 41: 1, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 24: { # 'j' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 2, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 1, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 2, # 'f' - 27: 1, # 'g' - 25: 1, # 'h' - 3: 2, # 'i' - 24: 1, # 'j' - 10: 2, # 'k' - 5: 2, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 2, # 'r' - 8: 3, # 's' - 9: 2, # 't' - 14: 3, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 2, # 'x' - 11: 1, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 10: { # 'k' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 3, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 3, # 'e' - 18: 1, # 'f' - 27: 2, # 'g' - 25: 2, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 2, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 3, # 'p' - 7: 2, # 'r' - 8: 2, # 's' - 9: 2, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 3, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 3, # 'ü' - 30: 1, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 5: { # 'l' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 3, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 1, # 'e' - 18: 3, # 'f' - 27: 3, # 'g' - 25: 2, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 1, # 'l' - 13: 1, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 2, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 2, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 13: { # 'm' - 23: 1, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 3, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 3, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 2, # 'e' - 18: 3, # 'f' - 27: 3, # 'g' - 25: 3, # 'h' - 3: 3, # 'i' - 24: 3, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 2, # 'u' - 32: 2, # 'v' - 57: 1, # 'w' - 58: 0, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 3, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 4: { # 'n' - 23: 1, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 2, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 1, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 1, # 'f' - 27: 2, # 'g' - 25: 3, # 'h' - 3: 2, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 3, # 'p' - 7: 2, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 2, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 2, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 1, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 15: { # 'o' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 2, # 'L' - 20: 0, # 'M' - 46: 2, # 'N' - 42: 1, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 1, # 'i' - 24: 2, # 'j' - 10: 1, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 2, # 'o' - 26: 0, # 'p' - 7: 1, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 2, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 2, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 3, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 2, # 'ğ' - 41: 2, # 'İ' - 6: 3, # 'ı' - 40: 2, # 'Ş' - 19: 2, # 'ş' - }, - 26: { # 'p' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 1, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 1, # 'h' - 3: 2, # 'i' - 24: 3, # 'j' - 10: 1, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 0, # 'o' - 26: 2, # 'p' - 7: 2, # 'r' - 8: 1, # 's' - 9: 1, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 1, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 3, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 7: { # 'r' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 1, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 2, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 1, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 2, # 'g' - 25: 3, # 'h' - 3: 2, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 3, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 8: { # 's' - 23: 1, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 1, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 2, # 'g' - 25: 2, # 'h' - 3: 2, # 'i' - 24: 3, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 3, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 2, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 2, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 9: { # 't' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 2, # 'f' - 27: 2, # 'g' - 25: 2, # 'h' - 3: 2, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 3, # 'v' - 57: 0, # 'w' - 58: 2, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 3, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 2, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 14: { # 'u' - 23: 3, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 3, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 2, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 3, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 2, # 'Z' - 1: 2, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 2, # 'e' - 18: 2, # 'f' - 27: 3, # 'g' - 25: 3, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 3, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 2, # 'v' - 57: 2, # 'w' - 58: 0, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 3, # 'ü' - 30: 1, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 32: { # 'v' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 1, # 'j' - 10: 1, # 'k' - 5: 3, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 1, # 'r' - 8: 2, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 1, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 1, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 57: { # 'w' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 1, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 1, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 1, # 's' - 9: 0, # 't' - 14: 1, # 'u' - 32: 0, # 'v' - 57: 2, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 0, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 58: { # 'x' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 1, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 1, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 2, # 'i' - 24: 2, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 2, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 1, # 'r' - 8: 2, # 's' - 9: 1, # 't' - 14: 0, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 11: { # 'y' - 23: 1, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 2, # 'g' - 25: 2, # 'h' - 3: 2, # 'i' - 24: 1, # 'j' - 10: 2, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 2, # 'r' - 8: 1, # 's' - 9: 2, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 1, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 3, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 2, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 22: { # 'z' - 23: 2, # 'A' - 37: 2, # 'B' - 47: 1, # 'C' - 39: 2, # 'D' - 29: 3, # 'E' - 52: 1, # 'F' - 36: 2, # 'G' - 45: 2, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 2, # 'N' - 42: 2, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 3, # 'T' - 51: 2, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 1, # 'Z' - 1: 1, # 'a' - 21: 2, # 'b' - 28: 1, # 'c' - 12: 2, # 'd' - 2: 2, # 'e' - 18: 3, # 'f' - 27: 2, # 'g' - 25: 2, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 15: 2, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 0, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 3, # 'y' - 22: 2, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 2, # 'Ü' - 59: 1, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 2, # 'ö' - 17: 2, # 'ü' - 30: 2, # 'ğ' - 41: 1, # 'İ' - 6: 3, # 'ı' - 40: 1, # 'Ş' - 19: 2, # 'ş' - }, - 63: { # '·' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 0, # 'd' - 2: 1, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 0, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 54: { # 'Ç' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 1, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 1, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 1, # 'b' - 28: 0, # 'c' - 12: 1, # 'd' - 2: 0, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 0, # 'h' - 3: 3, # 'i' - 24: 0, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 2, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 2, # 'r' - 8: 0, # 's' - 9: 1, # 't' - 14: 0, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 2, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 50: { # 'Ö' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 1, # 'D' - 29: 2, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 2, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 1, # 'N' - 42: 2, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 2, # 'b' - 28: 1, # 'c' - 12: 2, # 'd' - 2: 0, # 'e' - 18: 1, # 'f' - 27: 1, # 'g' - 25: 1, # 'h' - 3: 2, # 'i' - 24: 0, # 'j' - 10: 2, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 3, # 'n' - 15: 2, # 'o' - 26: 2, # 'p' - 7: 3, # 'r' - 8: 1, # 's' - 9: 2, # 't' - 14: 0, # 'u' - 32: 1, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 2, # 'ö' - 17: 2, # 'ü' - 30: 1, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 55: { # 'Ü' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 1, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 1, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 1, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 1, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 1, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 1, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 0, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 59: { # 'â' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 1, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 2, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 0, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 2, # 'm' - 4: 0, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 2, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 1, # 'ı' - 40: 1, # 'Ş' - 19: 0, # 'ş' - }, - 33: { # 'ç' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 3, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 0, # 'Z' - 1: 0, # 'a' - 21: 3, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 0, # 'e' - 18: 2, # 'f' - 27: 1, # 'g' - 25: 3, # 'h' - 3: 3, # 'i' - 24: 0, # 'j' - 10: 3, # 'k' - 5: 0, # 'l' - 13: 0, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 3, # 'r' - 8: 2, # 's' - 9: 3, # 't' - 14: 0, # 'u' - 32: 2, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 1, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 61: { # 'î' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 0, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 0, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 2, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 1, # 'j' - 10: 0, # 'k' - 5: 0, # 'l' - 13: 1, # 'm' - 4: 1, # 'n' - 15: 0, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 1, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 1, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 1, # 'î' - 34: 0, # 'ö' - 17: 0, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 1, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 34: { # 'ö' - 23: 0, # 'A' - 37: 1, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 1, # 'G' - 45: 1, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 1, # 'L' - 20: 0, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 2, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 1, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 2, # 'c' - 12: 1, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 2, # 'g' - 25: 2, # 'h' - 3: 1, # 'i' - 24: 2, # 'j' - 10: 1, # 'k' - 5: 2, # 'l' - 13: 3, # 'm' - 4: 2, # 'n' - 15: 2, # 'o' - 26: 0, # 'p' - 7: 0, # 'r' - 8: 3, # 's' - 9: 1, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 1, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 2, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 2, # 'ö' - 17: 0, # 'ü' - 30: 2, # 'ğ' - 41: 1, # 'İ' - 6: 1, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 17: { # 'ü' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 0, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 1, # 'J' - 16: 1, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 0, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 0, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 0, # 'c' - 12: 1, # 'd' - 2: 3, # 'e' - 18: 1, # 'f' - 27: 2, # 'g' - 25: 0, # 'h' - 3: 1, # 'i' - 24: 1, # 'j' - 10: 2, # 'k' - 5: 3, # 'l' - 13: 2, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 2, # 'p' - 7: 2, # 'r' - 8: 3, # 's' - 9: 2, # 't' - 14: 3, # 'u' - 32: 1, # 'v' - 57: 1, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 2, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 30: { # 'ğ' - 23: 0, # 'A' - 37: 2, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 1, # 'G' - 45: 0, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 1, # 'M' - 46: 2, # 'N' - 42: 2, # 'O' - 48: 1, # 'P' - 44: 1, # 'R' - 35: 0, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 2, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 0, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 2, # 'e' - 18: 0, # 'f' - 27: 0, # 'g' - 25: 0, # 'h' - 3: 0, # 'i' - 24: 3, # 'j' - 10: 1, # 'k' - 5: 2, # 'l' - 13: 3, # 'm' - 4: 0, # 'n' - 15: 1, # 'o' - 26: 0, # 'p' - 7: 1, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 2, # 'Ç' - 50: 2, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 0, # 'î' - 34: 2, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 2, # 'İ' - 6: 2, # 'ı' - 40: 2, # 'Ş' - 19: 1, # 'ş' - }, - 41: { # 'İ' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 1, # 'D' - 29: 1, # 'E' - 52: 0, # 'F' - 36: 2, # 'G' - 45: 2, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 2, # 'P' - 44: 0, # 'R' - 35: 1, # 'S' - 31: 1, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 0, # 'Z' - 1: 1, # 'a' - 21: 2, # 'b' - 28: 1, # 'c' - 12: 2, # 'd' - 2: 1, # 'e' - 18: 0, # 'f' - 27: 3, # 'g' - 25: 2, # 'h' - 3: 2, # 'i' - 24: 2, # 'j' - 10: 2, # 'k' - 5: 0, # 'l' - 13: 1, # 'm' - 4: 3, # 'n' - 15: 1, # 'o' - 26: 1, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 2, # 't' - 14: 0, # 'u' - 32: 0, # 'v' - 57: 1, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 1, # 'Ü' - 59: 1, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 1, # 'ö' - 17: 1, # 'ü' - 30: 2, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 1, # 'ş' - }, - 6: { # 'ı' - 23: 2, # 'A' - 37: 0, # 'B' - 47: 0, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 2, # 'J' - 16: 3, # 'K' - 49: 0, # 'L' - 20: 3, # 'M' - 46: 1, # 'N' - 42: 0, # 'O' - 48: 0, # 'P' - 44: 0, # 'R' - 35: 0, # 'S' - 31: 2, # 'T' - 51: 0, # 'U' - 38: 0, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 1, # 'Z' - 1: 3, # 'a' - 21: 2, # 'b' - 28: 1, # 'c' - 12: 3, # 'd' - 2: 3, # 'e' - 18: 3, # 'f' - 27: 3, # 'g' - 25: 2, # 'h' - 3: 3, # 'i' - 24: 3, # 'j' - 10: 3, # 'k' - 5: 3, # 'l' - 13: 3, # 'm' - 4: 3, # 'n' - 15: 0, # 'o' - 26: 3, # 'p' - 7: 3, # 'r' - 8: 3, # 's' - 9: 3, # 't' - 14: 3, # 'u' - 32: 3, # 'v' - 57: 1, # 'w' - 58: 1, # 'x' - 11: 3, # 'y' - 22: 0, # 'z' - 63: 1, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 2, # 'ç' - 61: 0, # 'î' - 34: 0, # 'ö' - 17: 3, # 'ü' - 30: 0, # 'ğ' - 41: 0, # 'İ' - 6: 3, # 'ı' - 40: 0, # 'Ş' - 19: 0, # 'ş' - }, - 40: { # 'Ş' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 1, # 'D' - 29: 1, # 'E' - 52: 0, # 'F' - 36: 1, # 'G' - 45: 2, # 'H' - 53: 1, # 'I' - 60: 0, # 'J' - 16: 0, # 'K' - 49: 0, # 'L' - 20: 2, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 2, # 'P' - 44: 2, # 'R' - 35: 1, # 'S' - 31: 1, # 'T' - 51: 0, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 2, # 'Y' - 56: 1, # 'Z' - 1: 0, # 'a' - 21: 2, # 'b' - 28: 0, # 'c' - 12: 2, # 'd' - 2: 0, # 'e' - 18: 3, # 'f' - 27: 0, # 'g' - 25: 2, # 'h' - 3: 3, # 'i' - 24: 2, # 'j' - 10: 1, # 'k' - 5: 0, # 'l' - 13: 1, # 'm' - 4: 3, # 'n' - 15: 2, # 'o' - 26: 0, # 'p' - 7: 3, # 'r' - 8: 2, # 's' - 9: 2, # 't' - 14: 1, # 'u' - 32: 3, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 2, # 'y' - 22: 0, # 'z' - 63: 0, # '·' - 54: 0, # 'Ç' - 50: 0, # 'Ö' - 55: 1, # 'Ü' - 59: 0, # 'â' - 33: 0, # 'ç' - 61: 0, # 'î' - 34: 2, # 'ö' - 17: 1, # 'ü' - 30: 2, # 'ğ' - 41: 0, # 'İ' - 6: 2, # 'ı' - 40: 1, # 'Ş' - 19: 2, # 'ş' - }, - 19: { # 'ş' - 23: 0, # 'A' - 37: 0, # 'B' - 47: 1, # 'C' - 39: 0, # 'D' - 29: 0, # 'E' - 52: 2, # 'F' - 36: 1, # 'G' - 45: 0, # 'H' - 53: 0, # 'I' - 60: 0, # 'J' - 16: 3, # 'K' - 49: 2, # 'L' - 20: 0, # 'M' - 46: 1, # 'N' - 42: 1, # 'O' - 48: 1, # 'P' - 44: 1, # 'R' - 35: 1, # 'S' - 31: 0, # 'T' - 51: 1, # 'U' - 38: 1, # 'V' - 62: 0, # 'W' - 43: 1, # 'Y' - 56: 0, # 'Z' - 1: 3, # 'a' - 21: 1, # 'b' - 28: 2, # 'c' - 12: 0, # 'd' - 2: 3, # 'e' - 18: 0, # 'f' - 27: 2, # 'g' - 25: 1, # 'h' - 3: 1, # 'i' - 24: 0, # 'j' - 10: 2, # 'k' - 5: 2, # 'l' - 13: 3, # 'm' - 4: 0, # 'n' - 15: 0, # 'o' - 26: 1, # 'p' - 7: 3, # 'r' - 8: 0, # 's' - 9: 0, # 't' - 14: 3, # 'u' - 32: 0, # 'v' - 57: 0, # 'w' - 58: 0, # 'x' - 11: 0, # 'y' - 22: 2, # 'z' - 63: 0, # '·' - 54: 1, # 'Ç' - 50: 2, # 'Ö' - 55: 0, # 'Ü' - 59: 0, # 'â' - 33: 1, # 'ç' - 61: 1, # 'î' - 34: 2, # 'ö' - 17: 0, # 'ü' - 30: 1, # 'ğ' - 41: 1, # 'İ' - 6: 1, # 'ı' - 40: 1, # 'Ş' - 19: 1, # 'ş' - }, -} - -# 255: Undefined characters that did not exist in training text -# 254: Carriage/Return -# 253: symbol (punctuation) that does not belong to word -# 252: 0 - 9 -# 251: Control characters - -# Character Mapping Table(s): -ISO_8859_9_TURKISH_CHAR_TO_ORDER = { - 0: 255, # '\x00' - 1: 255, # '\x01' - 2: 255, # '\x02' - 3: 255, # '\x03' - 4: 255, # '\x04' - 5: 255, # '\x05' - 6: 255, # '\x06' - 7: 255, # '\x07' - 8: 255, # '\x08' - 9: 255, # '\t' - 10: 255, # '\n' - 11: 255, # '\x0b' - 12: 255, # '\x0c' - 13: 255, # '\r' - 14: 255, # '\x0e' - 15: 255, # '\x0f' - 16: 255, # '\x10' - 17: 255, # '\x11' - 18: 255, # '\x12' - 19: 255, # '\x13' - 20: 255, # '\x14' - 21: 255, # '\x15' - 22: 255, # '\x16' - 23: 255, # '\x17' - 24: 255, # '\x18' - 25: 255, # '\x19' - 26: 255, # '\x1a' - 27: 255, # '\x1b' - 28: 255, # '\x1c' - 29: 255, # '\x1d' - 30: 255, # '\x1e' - 31: 255, # '\x1f' - 32: 255, # ' ' - 33: 255, # '!' - 34: 255, # '"' - 35: 255, # '#' - 36: 255, # '$' - 37: 255, # '%' - 38: 255, # '&' - 39: 255, # "'" - 40: 255, # '(' - 41: 255, # ')' - 42: 255, # '*' - 43: 255, # '+' - 44: 255, # ',' - 45: 255, # '-' - 46: 255, # '.' - 47: 255, # '/' - 48: 255, # '0' - 49: 255, # '1' - 50: 255, # '2' - 51: 255, # '3' - 52: 255, # '4' - 53: 255, # '5' - 54: 255, # '6' - 55: 255, # '7' - 56: 255, # '8' - 57: 255, # '9' - 58: 255, # ':' - 59: 255, # ';' - 60: 255, # '<' - 61: 255, # '=' - 62: 255, # '>' - 63: 255, # '?' - 64: 255, # '@' - 65: 23, # 'A' - 66: 37, # 'B' - 67: 47, # 'C' - 68: 39, # 'D' - 69: 29, # 'E' - 70: 52, # 'F' - 71: 36, # 'G' - 72: 45, # 'H' - 73: 53, # 'I' - 74: 60, # 'J' - 75: 16, # 'K' - 76: 49, # 'L' - 77: 20, # 'M' - 78: 46, # 'N' - 79: 42, # 'O' - 80: 48, # 'P' - 81: 69, # 'Q' - 82: 44, # 'R' - 83: 35, # 'S' - 84: 31, # 'T' - 85: 51, # 'U' - 86: 38, # 'V' - 87: 62, # 'W' - 88: 65, # 'X' - 89: 43, # 'Y' - 90: 56, # 'Z' - 91: 255, # '[' - 92: 255, # '\\' - 93: 255, # ']' - 94: 255, # '^' - 95: 255, # '_' - 96: 255, # '`' - 97: 1, # 'a' - 98: 21, # 'b' - 99: 28, # 'c' - 100: 12, # 'd' - 101: 2, # 'e' - 102: 18, # 'f' - 103: 27, # 'g' - 104: 25, # 'h' - 105: 3, # 'i' - 106: 24, # 'j' - 107: 10, # 'k' - 108: 5, # 'l' - 109: 13, # 'm' - 110: 4, # 'n' - 111: 15, # 'o' - 112: 26, # 'p' - 113: 64, # 'q' - 114: 7, # 'r' - 115: 8, # 's' - 116: 9, # 't' - 117: 14, # 'u' - 118: 32, # 'v' - 119: 57, # 'w' - 120: 58, # 'x' - 121: 11, # 'y' - 122: 22, # 'z' - 123: 255, # '{' - 124: 255, # '|' - 125: 255, # '}' - 126: 255, # '~' - 127: 255, # '\x7f' - 128: 180, # '\x80' - 129: 179, # '\x81' - 130: 178, # '\x82' - 131: 177, # '\x83' - 132: 176, # '\x84' - 133: 175, # '\x85' - 134: 174, # '\x86' - 135: 173, # '\x87' - 136: 172, # '\x88' - 137: 171, # '\x89' - 138: 170, # '\x8a' - 139: 169, # '\x8b' - 140: 168, # '\x8c' - 141: 167, # '\x8d' - 142: 166, # '\x8e' - 143: 165, # '\x8f' - 144: 164, # '\x90' - 145: 163, # '\x91' - 146: 162, # '\x92' - 147: 161, # '\x93' - 148: 160, # '\x94' - 149: 159, # '\x95' - 150: 101, # '\x96' - 151: 158, # '\x97' - 152: 157, # '\x98' - 153: 156, # '\x99' - 154: 155, # '\x9a' - 155: 154, # '\x9b' - 156: 153, # '\x9c' - 157: 152, # '\x9d' - 158: 151, # '\x9e' - 159: 106, # '\x9f' - 160: 150, # '\xa0' - 161: 149, # '¡' - 162: 148, # '¢' - 163: 147, # '£' - 164: 146, # '¤' - 165: 145, # '¥' - 166: 144, # '¦' - 167: 100, # '§' - 168: 143, # '¨' - 169: 142, # '©' - 170: 141, # 'ª' - 171: 140, # '«' - 172: 139, # '¬' - 173: 138, # '\xad' - 174: 137, # '®' - 175: 136, # '¯' - 176: 94, # '°' - 177: 80, # '±' - 178: 93, # '²' - 179: 135, # '³' - 180: 105, # '´' - 181: 134, # 'µ' - 182: 133, # '¶' - 183: 63, # '·' - 184: 132, # '¸' - 185: 131, # '¹' - 186: 130, # 'º' - 187: 129, # '»' - 188: 128, # '¼' - 189: 127, # '½' - 190: 126, # '¾' - 191: 125, # '¿' - 192: 124, # 'À' - 193: 104, # 'Á' - 194: 73, # 'Â' - 195: 99, # 'Ã' - 196: 79, # 'Ä' - 197: 85, # 'Å' - 198: 123, # 'Æ' - 199: 54, # 'Ç' - 200: 122, # 'È' - 201: 98, # 'É' - 202: 92, # 'Ê' - 203: 121, # 'Ë' - 204: 120, # 'Ì' - 205: 91, # 'Í' - 206: 103, # 'Î' - 207: 119, # 'Ï' - 208: 68, # 'Ğ' - 209: 118, # 'Ñ' - 210: 117, # 'Ò' - 211: 97, # 'Ó' - 212: 116, # 'Ô' - 213: 115, # 'Õ' - 214: 50, # 'Ö' - 215: 90, # '×' - 216: 114, # 'Ø' - 217: 113, # 'Ù' - 218: 112, # 'Ú' - 219: 111, # 'Û' - 220: 55, # 'Ü' - 221: 41, # 'İ' - 222: 40, # 'Ş' - 223: 86, # 'ß' - 224: 89, # 'à' - 225: 70, # 'á' - 226: 59, # 'â' - 227: 78, # 'ã' - 228: 71, # 'ä' - 229: 82, # 'å' - 230: 88, # 'æ' - 231: 33, # 'ç' - 232: 77, # 'è' - 233: 66, # 'é' - 234: 84, # 'ê' - 235: 83, # 'ë' - 236: 110, # 'ì' - 237: 75, # 'í' - 238: 61, # 'î' - 239: 96, # 'ï' - 240: 30, # 'ğ' - 241: 67, # 'ñ' - 242: 109, # 'ò' - 243: 74, # 'ó' - 244: 87, # 'ô' - 245: 102, # 'õ' - 246: 34, # 'ö' - 247: 95, # '÷' - 248: 81, # 'ø' - 249: 108, # 'ù' - 250: 76, # 'ú' - 251: 72, # 'û' - 252: 17, # 'ü' - 253: 6, # 'ı' - 254: 19, # 'ş' - 255: 107, # 'ÿ' -} - -ISO_8859_9_TURKISH_MODEL = SingleByteCharSetModel( - charset_name="ISO-8859-9", - language="Turkish", - char_to_order_map=ISO_8859_9_TURKISH_CHAR_TO_ORDER, - language_model=TURKISH_LANG_MODEL, - typical_positive_ratio=0.97029, - keep_ascii_letters=True, - alphabet="ABCDEFGHIJKLMNOPRSTUVYZabcdefghijklmnoprstuvyzÂÇÎÖÛÜâçîöûüĞğİıŞş", -) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/latin1prober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/latin1prober.py deleted file mode 100644 index 59a01d9..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/latin1prober.py +++ /dev/null @@ -1,147 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import List, Union - -from .charsetprober import CharSetProber -from .enums import ProbingState - -FREQ_CAT_NUM = 4 - -UDF = 0 # undefined -OTH = 1 # other -ASC = 2 # ascii capital letter -ASS = 3 # ascii small letter -ACV = 4 # accent capital vowel -ACO = 5 # accent capital other -ASV = 6 # accent small vowel -ASO = 7 # accent small other -CLASS_NUM = 8 # total classes - -# fmt: off -Latin1_CharToClass = ( - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 00 - 07 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 08 - 0F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 10 - 17 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 18 - 1F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 20 - 27 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 28 - 2F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 30 - 37 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 38 - 3F - OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 40 - 47 - ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 48 - 4F - ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 50 - 57 - ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH, # 58 - 5F - OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 60 - 67 - ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 68 - 6F - ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 70 - 77 - ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH, # 78 - 7F - OTH, UDF, OTH, ASO, OTH, OTH, OTH, OTH, # 80 - 87 - OTH, OTH, ACO, OTH, ACO, UDF, ACO, UDF, # 88 - 8F - UDF, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 90 - 97 - OTH, OTH, ASO, OTH, ASO, UDF, ASO, ACO, # 98 - 9F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # A0 - A7 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # A8 - AF - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # B0 - B7 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # B8 - BF - ACV, ACV, ACV, ACV, ACV, ACV, ACO, ACO, # C0 - C7 - ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV, # C8 - CF - ACO, ACO, ACV, ACV, ACV, ACV, ACV, OTH, # D0 - D7 - ACV, ACV, ACV, ACV, ACV, ACO, ACO, ACO, # D8 - DF - ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASO, # E0 - E7 - ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV, # E8 - EF - ASO, ASO, ASV, ASV, ASV, ASV, ASV, OTH, # F0 - F7 - ASV, ASV, ASV, ASV, ASV, ASO, ASO, ASO, # F8 - FF -) - -# 0 : illegal -# 1 : very unlikely -# 2 : normal -# 3 : very likely -Latin1ClassModel = ( -# UDF OTH ASC ASS ACV ACO ASV ASO - 0, 0, 0, 0, 0, 0, 0, 0, # UDF - 0, 3, 3, 3, 3, 3, 3, 3, # OTH - 0, 3, 3, 3, 3, 3, 3, 3, # ASC - 0, 3, 3, 3, 1, 1, 3, 3, # ASS - 0, 3, 3, 3, 1, 2, 1, 2, # ACV - 0, 3, 3, 3, 3, 3, 3, 3, # ACO - 0, 3, 1, 3, 1, 1, 1, 3, # ASV - 0, 3, 1, 3, 1, 1, 3, 3, # ASO -) -# fmt: on - - -class Latin1Prober(CharSetProber): - def __init__(self) -> None: - super().__init__() - self._last_char_class = OTH - self._freq_counter: List[int] = [] - self.reset() - - def reset(self) -> None: - self._last_char_class = OTH - self._freq_counter = [0] * FREQ_CAT_NUM - super().reset() - - @property - def charset_name(self) -> str: - return "ISO-8859-1" - - @property - def language(self) -> str: - return "" - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - byte_str = self.remove_xml_tags(byte_str) - for c in byte_str: - char_class = Latin1_CharToClass[c] - freq = Latin1ClassModel[(self._last_char_class * CLASS_NUM) + char_class] - if freq == 0: - self._state = ProbingState.NOT_ME - break - self._freq_counter[freq] += 1 - self._last_char_class = char_class - - return self.state - - def get_confidence(self) -> float: - if self.state == ProbingState.NOT_ME: - return 0.01 - - total = sum(self._freq_counter) - confidence = ( - 0.0 - if total < 0.01 - else (self._freq_counter[3] - self._freq_counter[1] * 20.0) / total - ) - confidence = max(confidence, 0.0) - # lower the confidence of latin1 so that other more accurate - # detector can take priority. - confidence *= 0.73 - return confidence diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/macromanprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/macromanprober.py deleted file mode 100644 index 1425d10..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/macromanprober.py +++ /dev/null @@ -1,162 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# This code was modified from latin1prober.py by Rob Speer . -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Rob Speer - adapt to MacRoman encoding -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import List, Union - -from .charsetprober import CharSetProber -from .enums import ProbingState - -FREQ_CAT_NUM = 4 - -UDF = 0 # undefined -OTH = 1 # other -ASC = 2 # ascii capital letter -ASS = 3 # ascii small letter -ACV = 4 # accent capital vowel -ACO = 5 # accent capital other -ASV = 6 # accent small vowel -ASO = 7 # accent small other -ODD = 8 # character that is unlikely to appear -CLASS_NUM = 9 # total classes - -# The change from Latin1 is that we explicitly look for extended characters -# that are infrequently-occurring symbols, and consider them to always be -# improbable. This should let MacRoman get out of the way of more likely -# encodings in most situations. - -# fmt: off -MacRoman_CharToClass = ( - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 00 - 07 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 08 - 0F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 10 - 17 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 18 - 1F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 20 - 27 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 28 - 2F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 30 - 37 - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 38 - 3F - OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 40 - 47 - ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 48 - 4F - ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 50 - 57 - ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH, # 58 - 5F - OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 60 - 67 - ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 68 - 6F - ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 70 - 77 - ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH, # 78 - 7F - ACV, ACV, ACO, ACV, ACO, ACV, ACV, ASV, # 80 - 87 - ASV, ASV, ASV, ASV, ASV, ASO, ASV, ASV, # 88 - 8F - ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASV, # 90 - 97 - ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV, # 98 - 9F - OTH, OTH, OTH, OTH, OTH, OTH, OTH, ASO, # A0 - A7 - OTH, OTH, ODD, ODD, OTH, OTH, ACV, ACV, # A8 - AF - OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # B0 - B7 - OTH, OTH, OTH, OTH, OTH, OTH, ASV, ASV, # B8 - BF - OTH, OTH, ODD, OTH, ODD, OTH, OTH, OTH, # C0 - C7 - OTH, OTH, OTH, ACV, ACV, ACV, ACV, ASV, # C8 - CF - OTH, OTH, OTH, OTH, OTH, OTH, OTH, ODD, # D0 - D7 - ASV, ACV, ODD, OTH, OTH, OTH, OTH, OTH, # D8 - DF - OTH, OTH, OTH, OTH, OTH, ACV, ACV, ACV, # E0 - E7 - ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV, # E8 - EF - ODD, ACV, ACV, ACV, ACV, ASV, ODD, ODD, # F0 - F7 - ODD, ODD, ODD, ODD, ODD, ODD, ODD, ODD, # F8 - FF -) - -# 0 : illegal -# 1 : very unlikely -# 2 : normal -# 3 : very likely -MacRomanClassModel = ( -# UDF OTH ASC ASS ACV ACO ASV ASO ODD - 0, 0, 0, 0, 0, 0, 0, 0, 0, # UDF - 0, 3, 3, 3, 3, 3, 3, 3, 1, # OTH - 0, 3, 3, 3, 3, 3, 3, 3, 1, # ASC - 0, 3, 3, 3, 1, 1, 3, 3, 1, # ASS - 0, 3, 3, 3, 1, 2, 1, 2, 1, # ACV - 0, 3, 3, 3, 3, 3, 3, 3, 1, # ACO - 0, 3, 1, 3, 1, 1, 1, 3, 1, # ASV - 0, 3, 1, 3, 1, 1, 3, 3, 1, # ASO - 0, 1, 1, 1, 1, 1, 1, 1, 1, # ODD -) -# fmt: on - - -class MacRomanProber(CharSetProber): - def __init__(self) -> None: - super().__init__() - self._last_char_class = OTH - self._freq_counter: List[int] = [] - self.reset() - - def reset(self) -> None: - self._last_char_class = OTH - self._freq_counter = [0] * FREQ_CAT_NUM - - # express the prior that MacRoman is a somewhat rare encoding; - # this can be done by starting out in a slightly improbable state - # that must be overcome - self._freq_counter[2] = 10 - - super().reset() - - @property - def charset_name(self) -> str: - return "MacRoman" - - @property - def language(self) -> str: - return "" - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - byte_str = self.remove_xml_tags(byte_str) - for c in byte_str: - char_class = MacRoman_CharToClass[c] - freq = MacRomanClassModel[(self._last_char_class * CLASS_NUM) + char_class] - if freq == 0: - self._state = ProbingState.NOT_ME - break - self._freq_counter[freq] += 1 - self._last_char_class = char_class - - return self.state - - def get_confidence(self) -> float: - if self.state == ProbingState.NOT_ME: - return 0.01 - - total = sum(self._freq_counter) - confidence = ( - 0.0 - if total < 0.01 - else (self._freq_counter[3] - self._freq_counter[1] * 20.0) / total - ) - confidence = max(confidence, 0.0) - # lower the confidence of MacRoman so that other more accurate - # detector can take priority. - confidence *= 0.73 - return confidence diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcharsetprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcharsetprober.py deleted file mode 100644 index 666307e..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcharsetprober.py +++ /dev/null @@ -1,95 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# Proofpoint, Inc. -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Optional, Union - -from .chardistribution import CharDistributionAnalysis -from .charsetprober import CharSetProber -from .codingstatemachine import CodingStateMachine -from .enums import LanguageFilter, MachineState, ProbingState - - -class MultiByteCharSetProber(CharSetProber): - """ - MultiByteCharSetProber - """ - - def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None: - super().__init__(lang_filter=lang_filter) - self.distribution_analyzer: Optional[CharDistributionAnalysis] = None - self.coding_sm: Optional[CodingStateMachine] = None - self._last_char = bytearray(b"\0\0") - - def reset(self) -> None: - super().reset() - if self.coding_sm: - self.coding_sm.reset() - if self.distribution_analyzer: - self.distribution_analyzer.reset() - self._last_char = bytearray(b"\0\0") - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - assert self.coding_sm is not None - assert self.distribution_analyzer is not None - - for i, byte in enumerate(byte_str): - coding_state = self.coding_sm.next_state(byte) - if coding_state == MachineState.ERROR: - self.logger.debug( - "%s %s prober hit error at byte %s", - self.charset_name, - self.language, - i, - ) - self._state = ProbingState.NOT_ME - break - if coding_state == MachineState.ITS_ME: - self._state = ProbingState.FOUND_IT - break - if coding_state == MachineState.START: - char_len = self.coding_sm.get_current_charlen() - if i == 0: - self._last_char[1] = byte - self.distribution_analyzer.feed(self._last_char, char_len) - else: - self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len) - - self._last_char[0] = byte_str[-1] - - if self.state == ProbingState.DETECTING: - if self.distribution_analyzer.got_enough_data() and ( - self.get_confidence() > self.SHORTCUT_THRESHOLD - ): - self._state = ProbingState.FOUND_IT - - return self.state - - def get_confidence(self) -> float: - assert self.distribution_analyzer is not None - return self.distribution_analyzer.get_confidence() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcsgroupprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcsgroupprober.py deleted file mode 100644 index 6cb9cc7..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcsgroupprober.py +++ /dev/null @@ -1,57 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# Proofpoint, Inc. -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .big5prober import Big5Prober -from .charsetgroupprober import CharSetGroupProber -from .cp949prober import CP949Prober -from .enums import LanguageFilter -from .eucjpprober import EUCJPProber -from .euckrprober import EUCKRProber -from .euctwprober import EUCTWProber -from .gb2312prober import GB2312Prober -from .johabprober import JOHABProber -from .sjisprober import SJISProber -from .utf8prober import UTF8Prober - - -class MBCSGroupProber(CharSetGroupProber): - def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None: - super().__init__(lang_filter=lang_filter) - self.probers = [ - UTF8Prober(), - SJISProber(), - EUCJPProber(), - GB2312Prober(), - EUCKRProber(), - CP949Prober(), - Big5Prober(), - EUCTWProber(), - JOHABProber(), - ] - self.reset() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcssm.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcssm.py deleted file mode 100644 index 7bbe97e..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/mbcssm.py +++ /dev/null @@ -1,661 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .codingstatemachinedict import CodingStateMachineDict -from .enums import MachineState - -# BIG5 - -# fmt: off -BIG5_CLS = ( - 1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07 #allow 0x00 as legal value - 1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f - 1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17 - 1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f - 1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27 - 1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f - 1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37 - 1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f - 2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47 - 2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f - 2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57 - 2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f - 2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67 - 2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f - 2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77 - 2, 2, 2, 2, 2, 2, 2, 1, # 78 - 7f - 4, 4, 4, 4, 4, 4, 4, 4, # 80 - 87 - 4, 4, 4, 4, 4, 4, 4, 4, # 88 - 8f - 4, 4, 4, 4, 4, 4, 4, 4, # 90 - 97 - 4, 4, 4, 4, 4, 4, 4, 4, # 98 - 9f - 4, 3, 3, 3, 3, 3, 3, 3, # a0 - a7 - 3, 3, 3, 3, 3, 3, 3, 3, # a8 - af - 3, 3, 3, 3, 3, 3, 3, 3, # b0 - b7 - 3, 3, 3, 3, 3, 3, 3, 3, # b8 - bf - 3, 3, 3, 3, 3, 3, 3, 3, # c0 - c7 - 3, 3, 3, 3, 3, 3, 3, 3, # c8 - cf - 3, 3, 3, 3, 3, 3, 3, 3, # d0 - d7 - 3, 3, 3, 3, 3, 3, 3, 3, # d8 - df - 3, 3, 3, 3, 3, 3, 3, 3, # e0 - e7 - 3, 3, 3, 3, 3, 3, 3, 3, # e8 - ef - 3, 3, 3, 3, 3, 3, 3, 3, # f0 - f7 - 3, 3, 3, 3, 3, 3, 3, 0 # f8 - ff -) - -BIG5_ST = ( - MachineState.ERROR,MachineState.START,MachineState.START, 3,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#00-07 - MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,#08-0f - MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START#10-17 -) -# fmt: on - -BIG5_CHAR_LEN_TABLE = (0, 1, 1, 2, 0) - -BIG5_SM_MODEL: CodingStateMachineDict = { - "class_table": BIG5_CLS, - "class_factor": 5, - "state_table": BIG5_ST, - "char_len_table": BIG5_CHAR_LEN_TABLE, - "name": "Big5", -} - -# CP949 -# fmt: off -CP949_CLS = ( - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, # 00 - 0f - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, # 10 - 1f - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, # 20 - 2f - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, # 30 - 3f - 1, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, # 40 - 4f - 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 1, 1, 1, 1, 1, # 50 - 5f - 1, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, # 60 - 6f - 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 1, 1, 1, 1, 1, # 70 - 7f - 0, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, # 80 - 8f - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, # 90 - 9f - 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, # a0 - af - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, # b0 - bf - 7, 7, 7, 7, 7, 7, 9, 2, 2, 3, 2, 2, 2, 2, 2, 2, # c0 - cf - 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, # d0 - df - 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, # e0 - ef - 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, # f0 - ff -) - -CP949_ST = ( -#cls= 0 1 2 3 4 5 6 7 8 9 # previous state = - MachineState.ERROR,MachineState.START, 3,MachineState.ERROR,MachineState.START,MachineState.START, 4, 5,MachineState.ERROR, 6, # MachineState.START - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, # MachineState.ERROR - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME, # MachineState.ITS_ME - MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START, # 3 - MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START, # 4 - MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START, # 5 - MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START, # 6 -) -# fmt: on - -CP949_CHAR_LEN_TABLE = (0, 1, 2, 0, 1, 1, 2, 2, 0, 2) - -CP949_SM_MODEL: CodingStateMachineDict = { - "class_table": CP949_CLS, - "class_factor": 10, - "state_table": CP949_ST, - "char_len_table": CP949_CHAR_LEN_TABLE, - "name": "CP949", -} - -# EUC-JP -# fmt: off -EUCJP_CLS = ( - 4, 4, 4, 4, 4, 4, 4, 4, # 00 - 07 - 4, 4, 4, 4, 4, 4, 5, 5, # 08 - 0f - 4, 4, 4, 4, 4, 4, 4, 4, # 10 - 17 - 4, 4, 4, 5, 4, 4, 4, 4, # 18 - 1f - 4, 4, 4, 4, 4, 4, 4, 4, # 20 - 27 - 4, 4, 4, 4, 4, 4, 4, 4, # 28 - 2f - 4, 4, 4, 4, 4, 4, 4, 4, # 30 - 37 - 4, 4, 4, 4, 4, 4, 4, 4, # 38 - 3f - 4, 4, 4, 4, 4, 4, 4, 4, # 40 - 47 - 4, 4, 4, 4, 4, 4, 4, 4, # 48 - 4f - 4, 4, 4, 4, 4, 4, 4, 4, # 50 - 57 - 4, 4, 4, 4, 4, 4, 4, 4, # 58 - 5f - 4, 4, 4, 4, 4, 4, 4, 4, # 60 - 67 - 4, 4, 4, 4, 4, 4, 4, 4, # 68 - 6f - 4, 4, 4, 4, 4, 4, 4, 4, # 70 - 77 - 4, 4, 4, 4, 4, 4, 4, 4, # 78 - 7f - 5, 5, 5, 5, 5, 5, 5, 5, # 80 - 87 - 5, 5, 5, 5, 5, 5, 1, 3, # 88 - 8f - 5, 5, 5, 5, 5, 5, 5, 5, # 90 - 97 - 5, 5, 5, 5, 5, 5, 5, 5, # 98 - 9f - 5, 2, 2, 2, 2, 2, 2, 2, # a0 - a7 - 2, 2, 2, 2, 2, 2, 2, 2, # a8 - af - 2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7 - 2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf - 2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7 - 2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf - 2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7 - 2, 2, 2, 2, 2, 2, 2, 2, # d8 - df - 0, 0, 0, 0, 0, 0, 0, 0, # e0 - e7 - 0, 0, 0, 0, 0, 0, 0, 0, # e8 - ef - 0, 0, 0, 0, 0, 0, 0, 0, # f0 - f7 - 0, 0, 0, 0, 0, 0, 0, 5 # f8 - ff -) - -EUCJP_ST = ( - 3, 4, 3, 5,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#00-07 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,#08-0f - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.START,MachineState.ERROR,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#10-17 - MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 3,MachineState.ERROR,#18-1f - 3,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START#20-27 -) -# fmt: on - -EUCJP_CHAR_LEN_TABLE = (2, 2, 2, 3, 1, 0) - -EUCJP_SM_MODEL: CodingStateMachineDict = { - "class_table": EUCJP_CLS, - "class_factor": 6, - "state_table": EUCJP_ST, - "char_len_table": EUCJP_CHAR_LEN_TABLE, - "name": "EUC-JP", -} - -# EUC-KR -# fmt: off -EUCKR_CLS = ( - 1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07 - 1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f - 1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17 - 1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f - 1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27 - 1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f - 1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37 - 1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f - 1, 1, 1, 1, 1, 1, 1, 1, # 40 - 47 - 1, 1, 1, 1, 1, 1, 1, 1, # 48 - 4f - 1, 1, 1, 1, 1, 1, 1, 1, # 50 - 57 - 1, 1, 1, 1, 1, 1, 1, 1, # 58 - 5f - 1, 1, 1, 1, 1, 1, 1, 1, # 60 - 67 - 1, 1, 1, 1, 1, 1, 1, 1, # 68 - 6f - 1, 1, 1, 1, 1, 1, 1, 1, # 70 - 77 - 1, 1, 1, 1, 1, 1, 1, 1, # 78 - 7f - 0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87 - 0, 0, 0, 0, 0, 0, 0, 0, # 88 - 8f - 0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97 - 0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f - 0, 2, 2, 2, 2, 2, 2, 2, # a0 - a7 - 2, 2, 2, 2, 2, 3, 3, 3, # a8 - af - 2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7 - 2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf - 2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7 - 2, 3, 2, 2, 2, 2, 2, 2, # c8 - cf - 2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7 - 2, 2, 2, 2, 2, 2, 2, 2, # d8 - df - 2, 2, 2, 2, 2, 2, 2, 2, # e0 - e7 - 2, 2, 2, 2, 2, 2, 2, 2, # e8 - ef - 2, 2, 2, 2, 2, 2, 2, 2, # f0 - f7 - 2, 2, 2, 2, 2, 2, 2, 0 # f8 - ff -) - -EUCKR_ST = ( - MachineState.ERROR,MachineState.START, 3,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#00-07 - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START #08-0f -) -# fmt: on - -EUCKR_CHAR_LEN_TABLE = (0, 1, 2, 0) - -EUCKR_SM_MODEL: CodingStateMachineDict = { - "class_table": EUCKR_CLS, - "class_factor": 4, - "state_table": EUCKR_ST, - "char_len_table": EUCKR_CHAR_LEN_TABLE, - "name": "EUC-KR", -} - -# JOHAB -# fmt: off -JOHAB_CLS = ( - 4,4,4,4,4,4,4,4, # 00 - 07 - 4,4,4,4,4,4,0,0, # 08 - 0f - 4,4,4,4,4,4,4,4, # 10 - 17 - 4,4,4,0,4,4,4,4, # 18 - 1f - 4,4,4,4,4,4,4,4, # 20 - 27 - 4,4,4,4,4,4,4,4, # 28 - 2f - 4,3,3,3,3,3,3,3, # 30 - 37 - 3,3,3,3,3,3,3,3, # 38 - 3f - 3,1,1,1,1,1,1,1, # 40 - 47 - 1,1,1,1,1,1,1,1, # 48 - 4f - 1,1,1,1,1,1,1,1, # 50 - 57 - 1,1,1,1,1,1,1,1, # 58 - 5f - 1,1,1,1,1,1,1,1, # 60 - 67 - 1,1,1,1,1,1,1,1, # 68 - 6f - 1,1,1,1,1,1,1,1, # 70 - 77 - 1,1,1,1,1,1,1,2, # 78 - 7f - 6,6,6,6,8,8,8,8, # 80 - 87 - 8,8,8,8,8,8,8,8, # 88 - 8f - 8,7,7,7,7,7,7,7, # 90 - 97 - 7,7,7,7,7,7,7,7, # 98 - 9f - 7,7,7,7,7,7,7,7, # a0 - a7 - 7,7,7,7,7,7,7,7, # a8 - af - 7,7,7,7,7,7,7,7, # b0 - b7 - 7,7,7,7,7,7,7,7, # b8 - bf - 7,7,7,7,7,7,7,7, # c0 - c7 - 7,7,7,7,7,7,7,7, # c8 - cf - 7,7,7,7,5,5,5,5, # d0 - d7 - 5,9,9,9,9,9,9,5, # d8 - df - 9,9,9,9,9,9,9,9, # e0 - e7 - 9,9,9,9,9,9,9,9, # e8 - ef - 9,9,9,9,9,9,9,9, # f0 - f7 - 9,9,5,5,5,5,5,0 # f8 - ff -) - -JOHAB_ST = ( -# cls = 0 1 2 3 4 5 6 7 8 9 - MachineState.ERROR ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.ERROR ,MachineState.ERROR ,3 ,3 ,4 , # MachineState.START - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME, # MachineState.ITS_ME - MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR ,MachineState.ERROR , # MachineState.ERROR - MachineState.ERROR ,MachineState.START ,MachineState.START ,MachineState.ERROR ,MachineState.ERROR ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.START ,MachineState.START , # 3 - MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START ,MachineState.ERROR ,MachineState.START , # 4 -) -# fmt: on - -JOHAB_CHAR_LEN_TABLE = (0, 1, 1, 1, 1, 0, 0, 2, 2, 2) - -JOHAB_SM_MODEL: CodingStateMachineDict = { - "class_table": JOHAB_CLS, - "class_factor": 10, - "state_table": JOHAB_ST, - "char_len_table": JOHAB_CHAR_LEN_TABLE, - "name": "Johab", -} - -# EUC-TW -# fmt: off -EUCTW_CLS = ( - 2, 2, 2, 2, 2, 2, 2, 2, # 00 - 07 - 2, 2, 2, 2, 2, 2, 0, 0, # 08 - 0f - 2, 2, 2, 2, 2, 2, 2, 2, # 10 - 17 - 2, 2, 2, 0, 2, 2, 2, 2, # 18 - 1f - 2, 2, 2, 2, 2, 2, 2, 2, # 20 - 27 - 2, 2, 2, 2, 2, 2, 2, 2, # 28 - 2f - 2, 2, 2, 2, 2, 2, 2, 2, # 30 - 37 - 2, 2, 2, 2, 2, 2, 2, 2, # 38 - 3f - 2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47 - 2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f - 2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57 - 2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f - 2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67 - 2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f - 2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77 - 2, 2, 2, 2, 2, 2, 2, 2, # 78 - 7f - 0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87 - 0, 0, 0, 0, 0, 0, 6, 0, # 88 - 8f - 0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97 - 0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f - 0, 3, 4, 4, 4, 4, 4, 4, # a0 - a7 - 5, 5, 1, 1, 1, 1, 1, 1, # a8 - af - 1, 1, 1, 1, 1, 1, 1, 1, # b0 - b7 - 1, 1, 1, 1, 1, 1, 1, 1, # b8 - bf - 1, 1, 3, 1, 3, 3, 3, 3, # c0 - c7 - 3, 3, 3, 3, 3, 3, 3, 3, # c8 - cf - 3, 3, 3, 3, 3, 3, 3, 3, # d0 - d7 - 3, 3, 3, 3, 3, 3, 3, 3, # d8 - df - 3, 3, 3, 3, 3, 3, 3, 3, # e0 - e7 - 3, 3, 3, 3, 3, 3, 3, 3, # e8 - ef - 3, 3, 3, 3, 3, 3, 3, 3, # f0 - f7 - 3, 3, 3, 3, 3, 3, 3, 0 # f8 - ff -) - -EUCTW_ST = ( - MachineState.ERROR,MachineState.ERROR,MachineState.START, 3, 3, 3, 4,MachineState.ERROR,#00-07 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,#08-0f - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.START,MachineState.ERROR,#10-17 - MachineState.START,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#18-1f - 5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.ERROR,MachineState.START,MachineState.START,#20-27 - MachineState.START,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START #28-2f -) -# fmt: on - -EUCTW_CHAR_LEN_TABLE = (0, 0, 1, 2, 2, 2, 3) - -EUCTW_SM_MODEL: CodingStateMachineDict = { - "class_table": EUCTW_CLS, - "class_factor": 7, - "state_table": EUCTW_ST, - "char_len_table": EUCTW_CHAR_LEN_TABLE, - "name": "x-euc-tw", -} - -# GB2312 -# fmt: off -GB2312_CLS = ( - 1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07 - 1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f - 1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17 - 1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f - 1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27 - 1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f - 3, 3, 3, 3, 3, 3, 3, 3, # 30 - 37 - 3, 3, 1, 1, 1, 1, 1, 1, # 38 - 3f - 2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47 - 2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f - 2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57 - 2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f - 2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67 - 2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f - 2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77 - 2, 2, 2, 2, 2, 2, 2, 4, # 78 - 7f - 5, 6, 6, 6, 6, 6, 6, 6, # 80 - 87 - 6, 6, 6, 6, 6, 6, 6, 6, # 88 - 8f - 6, 6, 6, 6, 6, 6, 6, 6, # 90 - 97 - 6, 6, 6, 6, 6, 6, 6, 6, # 98 - 9f - 6, 6, 6, 6, 6, 6, 6, 6, # a0 - a7 - 6, 6, 6, 6, 6, 6, 6, 6, # a8 - af - 6, 6, 6, 6, 6, 6, 6, 6, # b0 - b7 - 6, 6, 6, 6, 6, 6, 6, 6, # b8 - bf - 6, 6, 6, 6, 6, 6, 6, 6, # c0 - c7 - 6, 6, 6, 6, 6, 6, 6, 6, # c8 - cf - 6, 6, 6, 6, 6, 6, 6, 6, # d0 - d7 - 6, 6, 6, 6, 6, 6, 6, 6, # d8 - df - 6, 6, 6, 6, 6, 6, 6, 6, # e0 - e7 - 6, 6, 6, 6, 6, 6, 6, 6, # e8 - ef - 6, 6, 6, 6, 6, 6, 6, 6, # f0 - f7 - 6, 6, 6, 6, 6, 6, 6, 0 # f8 - ff -) - -GB2312_ST = ( - MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START, 3,MachineState.ERROR,#00-07 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,#08-0f - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.START,#10-17 - 4,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#18-1f - MachineState.ERROR,MachineState.ERROR, 5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,#20-27 - MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.START #28-2f -) -# fmt: on - -# To be accurate, the length of class 6 can be either 2 or 4. -# But it is not necessary to discriminate between the two since -# it is used for frequency analysis only, and we are validating -# each code range there as well. So it is safe to set it to be -# 2 here. -GB2312_CHAR_LEN_TABLE = (0, 1, 1, 1, 1, 1, 2) - -GB2312_SM_MODEL: CodingStateMachineDict = { - "class_table": GB2312_CLS, - "class_factor": 7, - "state_table": GB2312_ST, - "char_len_table": GB2312_CHAR_LEN_TABLE, - "name": "GB2312", -} - -# Shift_JIS -# fmt: off -SJIS_CLS = ( - 1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07 - 1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f - 1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17 - 1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f - 1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27 - 1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f - 1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37 - 1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f - 2, 2, 2, 2, 2, 2, 2, 2, # 40 - 47 - 2, 2, 2, 2, 2, 2, 2, 2, # 48 - 4f - 2, 2, 2, 2, 2, 2, 2, 2, # 50 - 57 - 2, 2, 2, 2, 2, 2, 2, 2, # 58 - 5f - 2, 2, 2, 2, 2, 2, 2, 2, # 60 - 67 - 2, 2, 2, 2, 2, 2, 2, 2, # 68 - 6f - 2, 2, 2, 2, 2, 2, 2, 2, # 70 - 77 - 2, 2, 2, 2, 2, 2, 2, 1, # 78 - 7f - 3, 3, 3, 3, 3, 2, 2, 3, # 80 - 87 - 3, 3, 3, 3, 3, 3, 3, 3, # 88 - 8f - 3, 3, 3, 3, 3, 3, 3, 3, # 90 - 97 - 3, 3, 3, 3, 3, 3, 3, 3, # 98 - 9f - #0xa0 is illegal in sjis encoding, but some pages does - #contain such byte. We need to be more error forgiven. - 2, 2, 2, 2, 2, 2, 2, 2, # a0 - a7 - 2, 2, 2, 2, 2, 2, 2, 2, # a8 - af - 2, 2, 2, 2, 2, 2, 2, 2, # b0 - b7 - 2, 2, 2, 2, 2, 2, 2, 2, # b8 - bf - 2, 2, 2, 2, 2, 2, 2, 2, # c0 - c7 - 2, 2, 2, 2, 2, 2, 2, 2, # c8 - cf - 2, 2, 2, 2, 2, 2, 2, 2, # d0 - d7 - 2, 2, 2, 2, 2, 2, 2, 2, # d8 - df - 3, 3, 3, 3, 3, 3, 3, 3, # e0 - e7 - 3, 3, 3, 3, 3, 4, 4, 4, # e8 - ef - 3, 3, 3, 3, 3, 3, 3, 3, # f0 - f7 - 3, 3, 3, 3, 3, 0, 0, 0, # f8 - ff -) - -SJIS_ST = ( - MachineState.ERROR,MachineState.START,MachineState.START, 3,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#00-07 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,#08-0f - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START #10-17 -) -# fmt: on - -SJIS_CHAR_LEN_TABLE = (0, 1, 1, 2, 0, 0) - -SJIS_SM_MODEL: CodingStateMachineDict = { - "class_table": SJIS_CLS, - "class_factor": 6, - "state_table": SJIS_ST, - "char_len_table": SJIS_CHAR_LEN_TABLE, - "name": "Shift_JIS", -} - -# UCS2-BE -# fmt: off -UCS2BE_CLS = ( - 0, 0, 0, 0, 0, 0, 0, 0, # 00 - 07 - 0, 0, 1, 0, 0, 2, 0, 0, # 08 - 0f - 0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17 - 0, 0, 0, 3, 0, 0, 0, 0, # 18 - 1f - 0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27 - 0, 3, 3, 3, 3, 3, 0, 0, # 28 - 2f - 0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37 - 0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f - 0, 0, 0, 0, 0, 0, 0, 0, # 40 - 47 - 0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f - 0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57 - 0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f - 0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67 - 0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f - 0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77 - 0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f - 0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87 - 0, 0, 0, 0, 0, 0, 0, 0, # 88 - 8f - 0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97 - 0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f - 0, 0, 0, 0, 0, 0, 0, 0, # a0 - a7 - 0, 0, 0, 0, 0, 0, 0, 0, # a8 - af - 0, 0, 0, 0, 0, 0, 0, 0, # b0 - b7 - 0, 0, 0, 0, 0, 0, 0, 0, # b8 - bf - 0, 0, 0, 0, 0, 0, 0, 0, # c0 - c7 - 0, 0, 0, 0, 0, 0, 0, 0, # c8 - cf - 0, 0, 0, 0, 0, 0, 0, 0, # d0 - d7 - 0, 0, 0, 0, 0, 0, 0, 0, # d8 - df - 0, 0, 0, 0, 0, 0, 0, 0, # e0 - e7 - 0, 0, 0, 0, 0, 0, 0, 0, # e8 - ef - 0, 0, 0, 0, 0, 0, 0, 0, # f0 - f7 - 0, 0, 0, 0, 0, 0, 4, 5 # f8 - ff -) - -UCS2BE_ST = ( - 5, 7, 7,MachineState.ERROR, 4, 3,MachineState.ERROR,MachineState.ERROR,#00-07 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,#08-0f - MachineState.ITS_ME,MachineState.ITS_ME, 6, 6, 6, 6,MachineState.ERROR,MachineState.ERROR,#10-17 - 6, 6, 6, 6, 6,MachineState.ITS_ME, 6, 6,#18-1f - 6, 6, 6, 6, 5, 7, 7,MachineState.ERROR,#20-27 - 5, 8, 6, 6,MachineState.ERROR, 6, 6, 6,#28-2f - 6, 6, 6, 6,MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START #30-37 -) -# fmt: on - -UCS2BE_CHAR_LEN_TABLE = (2, 2, 2, 0, 2, 2) - -UCS2BE_SM_MODEL: CodingStateMachineDict = { - "class_table": UCS2BE_CLS, - "class_factor": 6, - "state_table": UCS2BE_ST, - "char_len_table": UCS2BE_CHAR_LEN_TABLE, - "name": "UTF-16BE", -} - -# UCS2-LE -# fmt: off -UCS2LE_CLS = ( - 0, 0, 0, 0, 0, 0, 0, 0, # 00 - 07 - 0, 0, 1, 0, 0, 2, 0, 0, # 08 - 0f - 0, 0, 0, 0, 0, 0, 0, 0, # 10 - 17 - 0, 0, 0, 3, 0, 0, 0, 0, # 18 - 1f - 0, 0, 0, 0, 0, 0, 0, 0, # 20 - 27 - 0, 3, 3, 3, 3, 3, 0, 0, # 28 - 2f - 0, 0, 0, 0, 0, 0, 0, 0, # 30 - 37 - 0, 0, 0, 0, 0, 0, 0, 0, # 38 - 3f - 0, 0, 0, 0, 0, 0, 0, 0, # 40 - 47 - 0, 0, 0, 0, 0, 0, 0, 0, # 48 - 4f - 0, 0, 0, 0, 0, 0, 0, 0, # 50 - 57 - 0, 0, 0, 0, 0, 0, 0, 0, # 58 - 5f - 0, 0, 0, 0, 0, 0, 0, 0, # 60 - 67 - 0, 0, 0, 0, 0, 0, 0, 0, # 68 - 6f - 0, 0, 0, 0, 0, 0, 0, 0, # 70 - 77 - 0, 0, 0, 0, 0, 0, 0, 0, # 78 - 7f - 0, 0, 0, 0, 0, 0, 0, 0, # 80 - 87 - 0, 0, 0, 0, 0, 0, 0, 0, # 88 - 8f - 0, 0, 0, 0, 0, 0, 0, 0, # 90 - 97 - 0, 0, 0, 0, 0, 0, 0, 0, # 98 - 9f - 0, 0, 0, 0, 0, 0, 0, 0, # a0 - a7 - 0, 0, 0, 0, 0, 0, 0, 0, # a8 - af - 0, 0, 0, 0, 0, 0, 0, 0, # b0 - b7 - 0, 0, 0, 0, 0, 0, 0, 0, # b8 - bf - 0, 0, 0, 0, 0, 0, 0, 0, # c0 - c7 - 0, 0, 0, 0, 0, 0, 0, 0, # c8 - cf - 0, 0, 0, 0, 0, 0, 0, 0, # d0 - d7 - 0, 0, 0, 0, 0, 0, 0, 0, # d8 - df - 0, 0, 0, 0, 0, 0, 0, 0, # e0 - e7 - 0, 0, 0, 0, 0, 0, 0, 0, # e8 - ef - 0, 0, 0, 0, 0, 0, 0, 0, # f0 - f7 - 0, 0, 0, 0, 0, 0, 4, 5 # f8 - ff -) - -UCS2LE_ST = ( - 6, 6, 7, 6, 4, 3,MachineState.ERROR,MachineState.ERROR,#00-07 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,#08-0f - MachineState.ITS_ME,MachineState.ITS_ME, 5, 5, 5,MachineState.ERROR,MachineState.ITS_ME,MachineState.ERROR,#10-17 - 5, 5, 5,MachineState.ERROR, 5,MachineState.ERROR, 6, 6,#18-1f - 7, 6, 8, 8, 5, 5, 5,MachineState.ERROR,#20-27 - 5, 5, 5,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 5, 5,#28-2f - 5, 5, 5,MachineState.ERROR, 5,MachineState.ERROR,MachineState.START,MachineState.START #30-37 -) -# fmt: on - -UCS2LE_CHAR_LEN_TABLE = (2, 2, 2, 2, 2, 2) - -UCS2LE_SM_MODEL: CodingStateMachineDict = { - "class_table": UCS2LE_CLS, - "class_factor": 6, - "state_table": UCS2LE_ST, - "char_len_table": UCS2LE_CHAR_LEN_TABLE, - "name": "UTF-16LE", -} - -# UTF-8 -# fmt: off -UTF8_CLS = ( - 1, 1, 1, 1, 1, 1, 1, 1, # 00 - 07 #allow 0x00 as a legal value - 1, 1, 1, 1, 1, 1, 0, 0, # 08 - 0f - 1, 1, 1, 1, 1, 1, 1, 1, # 10 - 17 - 1, 1, 1, 0, 1, 1, 1, 1, # 18 - 1f - 1, 1, 1, 1, 1, 1, 1, 1, # 20 - 27 - 1, 1, 1, 1, 1, 1, 1, 1, # 28 - 2f - 1, 1, 1, 1, 1, 1, 1, 1, # 30 - 37 - 1, 1, 1, 1, 1, 1, 1, 1, # 38 - 3f - 1, 1, 1, 1, 1, 1, 1, 1, # 40 - 47 - 1, 1, 1, 1, 1, 1, 1, 1, # 48 - 4f - 1, 1, 1, 1, 1, 1, 1, 1, # 50 - 57 - 1, 1, 1, 1, 1, 1, 1, 1, # 58 - 5f - 1, 1, 1, 1, 1, 1, 1, 1, # 60 - 67 - 1, 1, 1, 1, 1, 1, 1, 1, # 68 - 6f - 1, 1, 1, 1, 1, 1, 1, 1, # 70 - 77 - 1, 1, 1, 1, 1, 1, 1, 1, # 78 - 7f - 2, 2, 2, 2, 3, 3, 3, 3, # 80 - 87 - 4, 4, 4, 4, 4, 4, 4, 4, # 88 - 8f - 4, 4, 4, 4, 4, 4, 4, 4, # 90 - 97 - 4, 4, 4, 4, 4, 4, 4, 4, # 98 - 9f - 5, 5, 5, 5, 5, 5, 5, 5, # a0 - a7 - 5, 5, 5, 5, 5, 5, 5, 5, # a8 - af - 5, 5, 5, 5, 5, 5, 5, 5, # b0 - b7 - 5, 5, 5, 5, 5, 5, 5, 5, # b8 - bf - 0, 0, 6, 6, 6, 6, 6, 6, # c0 - c7 - 6, 6, 6, 6, 6, 6, 6, 6, # c8 - cf - 6, 6, 6, 6, 6, 6, 6, 6, # d0 - d7 - 6, 6, 6, 6, 6, 6, 6, 6, # d8 - df - 7, 8, 8, 8, 8, 8, 8, 8, # e0 - e7 - 8, 8, 8, 8, 8, 9, 8, 8, # e8 - ef - 10, 11, 11, 11, 11, 11, 11, 11, # f0 - f7 - 12, 13, 13, 13, 14, 15, 0, 0 # f8 - ff -) - -UTF8_ST = ( - MachineState.ERROR,MachineState.START,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 12, 10,#00-07 - 9, 11, 8, 7, 6, 5, 4, 3,#08-0f - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#10-17 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#18-1f - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,#20-27 - MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,MachineState.ITS_ME,#28-2f - MachineState.ERROR,MachineState.ERROR, 5, 5, 5, 5,MachineState.ERROR,MachineState.ERROR,#30-37 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#38-3f - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 5, 5, 5,MachineState.ERROR,MachineState.ERROR,#40-47 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#48-4f - MachineState.ERROR,MachineState.ERROR, 7, 7, 7, 7,MachineState.ERROR,MachineState.ERROR,#50-57 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#58-5f - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 7, 7,MachineState.ERROR,MachineState.ERROR,#60-67 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#68-6f - MachineState.ERROR,MachineState.ERROR, 9, 9, 9, 9,MachineState.ERROR,MachineState.ERROR,#70-77 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#78-7f - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 9,MachineState.ERROR,MachineState.ERROR,#80-87 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#88-8f - MachineState.ERROR,MachineState.ERROR, 12, 12, 12, 12,MachineState.ERROR,MachineState.ERROR,#90-97 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#98-9f - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR, 12,MachineState.ERROR,MachineState.ERROR,#a0-a7 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#a8-af - MachineState.ERROR,MachineState.ERROR, 12, 12, 12,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#b0-b7 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,#b8-bf - MachineState.ERROR,MachineState.ERROR,MachineState.START,MachineState.START,MachineState.START,MachineState.START,MachineState.ERROR,MachineState.ERROR,#c0-c7 - MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR,MachineState.ERROR #c8-cf -) -# fmt: on - -UTF8_CHAR_LEN_TABLE = (0, 1, 0, 0, 0, 0, 2, 3, 3, 3, 4, 4, 5, 5, 6, 6) - -UTF8_SM_MODEL: CodingStateMachineDict = { - "class_table": UTF8_CLS, - "class_factor": 16, - "state_table": UTF8_ST, - "char_len_table": UTF8_CHAR_LEN_TABLE, - "name": "UTF-8", -} diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 9b5773c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__pycache__/languages.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__pycache__/languages.cpython-312.pyc deleted file mode 100644 index 6b914b2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/__pycache__/languages.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/languages.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/languages.py deleted file mode 100644 index eb40c5f..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/metadata/languages.py +++ /dev/null @@ -1,352 +0,0 @@ -""" -Metadata about languages used by our model training code for our -SingleByteCharSetProbers. Could be used for other things in the future. - -This code is based on the language metadata from the uchardet project. -""" - -from string import ascii_letters -from typing import List, Optional - -# TODO: Add Ukrainian (KOI8-U) - - -class Language: - """Metadata about a language useful for training models - - :ivar name: The human name for the language, in English. - :type name: str - :ivar iso_code: 2-letter ISO 639-1 if possible, 3-letter ISO code otherwise, - or use another catalog as a last resort. - :type iso_code: str - :ivar use_ascii: Whether or not ASCII letters should be included in trained - models. - :type use_ascii: bool - :ivar charsets: The charsets we want to support and create data for. - :type charsets: list of str - :ivar alphabet: The characters in the language's alphabet. If `use_ascii` is - `True`, you only need to add those not in the ASCII set. - :type alphabet: str - :ivar wiki_start_pages: The Wikipedia pages to start from if we're crawling - Wikipedia for training data. - :type wiki_start_pages: list of str - """ - - def __init__( - self, - name: Optional[str] = None, - iso_code: Optional[str] = None, - use_ascii: bool = True, - charsets: Optional[List[str]] = None, - alphabet: Optional[str] = None, - wiki_start_pages: Optional[List[str]] = None, - ) -> None: - super().__init__() - self.name = name - self.iso_code = iso_code - self.use_ascii = use_ascii - self.charsets = charsets - if self.use_ascii: - if alphabet: - alphabet += ascii_letters - else: - alphabet = ascii_letters - elif not alphabet: - raise ValueError("Must supply alphabet if use_ascii is False") - self.alphabet = "".join(sorted(set(alphabet))) if alphabet else None - self.wiki_start_pages = wiki_start_pages - - def __repr__(self) -> str: - param_str = ", ".join( - f"{k}={v!r}" for k, v in self.__dict__.items() if not k.startswith("_") - ) - return f"{self.__class__.__name__}({param_str})" - - -LANGUAGES = { - "Arabic": Language( - name="Arabic", - iso_code="ar", - use_ascii=False, - # We only support encodings that use isolated - # forms, because the current recommendation is - # that the rendering system handles presentation - # forms. This means we purposefully skip IBM864. - charsets=["ISO-8859-6", "WINDOWS-1256", "CP720", "CP864"], - alphabet="ءآأؤإئابةتثجحخدذرزسشصضطظعغػؼؽؾؿـفقكلمنهوىيًٌٍَُِّ", - wiki_start_pages=["الصفحة_الرئيسية"], - ), - "Belarusian": Language( - name="Belarusian", - iso_code="be", - use_ascii=False, - charsets=["ISO-8859-5", "WINDOWS-1251", "IBM866", "MacCyrillic"], - alphabet="АБВГДЕЁЖЗІЙКЛМНОПРСТУЎФХЦЧШЫЬЭЮЯабвгдеёжзійклмнопрстуўфхцчшыьэюяʼ", - wiki_start_pages=["Галоўная_старонка"], - ), - "Bulgarian": Language( - name="Bulgarian", - iso_code="bg", - use_ascii=False, - charsets=["ISO-8859-5", "WINDOWS-1251", "IBM855"], - alphabet="АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯабвгдежзийклмнопрстуфхцчшщъьюя", - wiki_start_pages=["Начална_страница"], - ), - "Czech": Language( - name="Czech", - iso_code="cz", - use_ascii=True, - charsets=["ISO-8859-2", "WINDOWS-1250"], - alphabet="áčďéěíňóřšťúůýžÁČĎÉĚÍŇÓŘŠŤÚŮÝŽ", - wiki_start_pages=["Hlavní_strana"], - ), - "Danish": Language( - name="Danish", - iso_code="da", - use_ascii=True, - charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"], - alphabet="æøåÆØÅ", - wiki_start_pages=["Forside"], - ), - "German": Language( - name="German", - iso_code="de", - use_ascii=True, - charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"], - alphabet="äöüßẞÄÖÜ", - wiki_start_pages=["Wikipedia:Hauptseite"], - ), - "Greek": Language( - name="Greek", - iso_code="el", - use_ascii=False, - charsets=["ISO-8859-7", "WINDOWS-1253"], - alphabet="αβγδεζηθικλμνξοπρσςτυφχψωάέήίόύώΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΣΤΥΦΧΨΩΆΈΉΊΌΎΏ", - wiki_start_pages=["Πύλη:Κύρια"], - ), - "English": Language( - name="English", - iso_code="en", - use_ascii=True, - charsets=["ISO-8859-1", "WINDOWS-1252", "MacRoman"], - wiki_start_pages=["Main_Page"], - ), - "Esperanto": Language( - name="Esperanto", - iso_code="eo", - # Q, W, X, and Y not used at all - use_ascii=False, - charsets=["ISO-8859-3"], - alphabet="abcĉdefgĝhĥijĵklmnoprsŝtuŭvzABCĈDEFGĜHĤIJĴKLMNOPRSŜTUŬVZ", - wiki_start_pages=["Vikipedio:Ĉefpaĝo"], - ), - "Spanish": Language( - name="Spanish", - iso_code="es", - use_ascii=True, - charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"], - alphabet="ñáéíóúüÑÁÉÍÓÚÜ", - wiki_start_pages=["Wikipedia:Portada"], - ), - "Estonian": Language( - name="Estonian", - iso_code="et", - use_ascii=False, - charsets=["ISO-8859-4", "ISO-8859-13", "WINDOWS-1257"], - # C, F, Š, Q, W, X, Y, Z, Ž are only for - # loanwords - alphabet="ABDEGHIJKLMNOPRSTUVÕÄÖÜabdeghijklmnoprstuvõäöü", - wiki_start_pages=["Esileht"], - ), - "Finnish": Language( - name="Finnish", - iso_code="fi", - use_ascii=True, - charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"], - alphabet="ÅÄÖŠŽåäöšž", - wiki_start_pages=["Wikipedia:Etusivu"], - ), - "French": Language( - name="French", - iso_code="fr", - use_ascii=True, - charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"], - alphabet="œàâçèéîïùûêŒÀÂÇÈÉÎÏÙÛÊ", - wiki_start_pages=["Wikipédia:Accueil_principal", "Bœuf (animal)"], - ), - "Hebrew": Language( - name="Hebrew", - iso_code="he", - use_ascii=False, - charsets=["ISO-8859-8", "WINDOWS-1255"], - alphabet="אבגדהוזחטיךכלםמןנסעףפץצקרשתװױײ", - wiki_start_pages=["עמוד_ראשי"], - ), - "Croatian": Language( - name="Croatian", - iso_code="hr", - # Q, W, X, Y are only used for foreign words. - use_ascii=False, - charsets=["ISO-8859-2", "WINDOWS-1250"], - alphabet="abcčćdđefghijklmnoprsštuvzžABCČĆDĐEFGHIJKLMNOPRSŠTUVZŽ", - wiki_start_pages=["Glavna_stranica"], - ), - "Hungarian": Language( - name="Hungarian", - iso_code="hu", - # Q, W, X, Y are only used for foreign words. - use_ascii=False, - charsets=["ISO-8859-2", "WINDOWS-1250"], - alphabet="abcdefghijklmnoprstuvzáéíóöőúüűABCDEFGHIJKLMNOPRSTUVZÁÉÍÓÖŐÚÜŰ", - wiki_start_pages=["Kezdőlap"], - ), - "Italian": Language( - name="Italian", - iso_code="it", - use_ascii=True, - charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"], - alphabet="ÀÈÉÌÒÓÙàèéìòóù", - wiki_start_pages=["Pagina_principale"], - ), - "Lithuanian": Language( - name="Lithuanian", - iso_code="lt", - use_ascii=False, - charsets=["ISO-8859-13", "WINDOWS-1257", "ISO-8859-4"], - # Q, W, and X not used at all - alphabet="AĄBCČDEĘĖFGHIĮYJKLMNOPRSŠTUŲŪVZŽaąbcčdeęėfghiįyjklmnoprsštuųūvzž", - wiki_start_pages=["Pagrindinis_puslapis"], - ), - "Latvian": Language( - name="Latvian", - iso_code="lv", - use_ascii=False, - charsets=["ISO-8859-13", "WINDOWS-1257", "ISO-8859-4"], - # Q, W, X, Y are only for loanwords - alphabet="AĀBCČDEĒFGĢHIĪJKĶLĻMNŅOPRSŠTUŪVZŽaābcčdeēfgģhiījkķlļmnņoprsštuūvzž", - wiki_start_pages=["Sākumlapa"], - ), - "Macedonian": Language( - name="Macedonian", - iso_code="mk", - use_ascii=False, - charsets=["ISO-8859-5", "WINDOWS-1251", "MacCyrillic", "IBM855"], - alphabet="АБВГДЃЕЖЗЅИЈКЛЉМНЊОПРСТЌУФХЦЧЏШабвгдѓежзѕијклљмнњопрстќуфхцчџш", - wiki_start_pages=["Главна_страница"], - ), - "Dutch": Language( - name="Dutch", - iso_code="nl", - use_ascii=True, - charsets=["ISO-8859-1", "WINDOWS-1252", "MacRoman"], - wiki_start_pages=["Hoofdpagina"], - ), - "Polish": Language( - name="Polish", - iso_code="pl", - # Q and X are only used for foreign words. - use_ascii=False, - charsets=["ISO-8859-2", "WINDOWS-1250"], - alphabet="AĄBCĆDEĘFGHIJKLŁMNŃOÓPRSŚTUWYZŹŻaąbcćdeęfghijklłmnńoóprsśtuwyzźż", - wiki_start_pages=["Wikipedia:Strona_główna"], - ), - "Portuguese": Language( - name="Portuguese", - iso_code="pt", - use_ascii=True, - charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"], - alphabet="ÁÂÃÀÇÉÊÍÓÔÕÚáâãàçéêíóôõú", - wiki_start_pages=["Wikipédia:Página_principal"], - ), - "Romanian": Language( - name="Romanian", - iso_code="ro", - use_ascii=True, - charsets=["ISO-8859-2", "WINDOWS-1250"], - alphabet="ăâîșțĂÂÎȘȚ", - wiki_start_pages=["Pagina_principală"], - ), - "Russian": Language( - name="Russian", - iso_code="ru", - use_ascii=False, - charsets=[ - "ISO-8859-5", - "WINDOWS-1251", - "KOI8-R", - "MacCyrillic", - "IBM866", - "IBM855", - ], - alphabet="абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ", - wiki_start_pages=["Заглавная_страница"], - ), - "Slovak": Language( - name="Slovak", - iso_code="sk", - use_ascii=True, - charsets=["ISO-8859-2", "WINDOWS-1250"], - alphabet="áäčďéíĺľňóôŕšťúýžÁÄČĎÉÍĹĽŇÓÔŔŠŤÚÝŽ", - wiki_start_pages=["Hlavná_stránka"], - ), - "Slovene": Language( - name="Slovene", - iso_code="sl", - # Q, W, X, Y are only used for foreign words. - use_ascii=False, - charsets=["ISO-8859-2", "WINDOWS-1250"], - alphabet="abcčdefghijklmnoprsštuvzžABCČDEFGHIJKLMNOPRSŠTUVZŽ", - wiki_start_pages=["Glavna_stran"], - ), - # Serbian can be written in both Latin and Cyrillic, but there's no - # simple way to get the Latin alphabet pages from Wikipedia through - # the API, so for now we just support Cyrillic. - "Serbian": Language( - name="Serbian", - iso_code="sr", - alphabet="АБВГДЂЕЖЗИЈКЛЉМНЊОПРСТЋУФХЦЧЏШабвгдђежзијклљмнњопрстћуфхцчџш", - charsets=["ISO-8859-5", "WINDOWS-1251", "MacCyrillic", "IBM855"], - wiki_start_pages=["Главна_страна"], - ), - "Thai": Language( - name="Thai", - iso_code="th", - use_ascii=False, - charsets=["ISO-8859-11", "TIS-620", "CP874"], - alphabet="กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลฦวศษสหฬอฮฯะัาำิีึืฺุู฿เแโใไๅๆ็่้๊๋์ํ๎๏๐๑๒๓๔๕๖๗๘๙๚๛", - wiki_start_pages=["หน้าหลัก"], - ), - "Turkish": Language( - name="Turkish", - iso_code="tr", - # Q, W, and X are not used by Turkish - use_ascii=False, - charsets=["ISO-8859-3", "ISO-8859-9", "WINDOWS-1254"], - alphabet="abcçdefgğhıijklmnoöprsştuüvyzâîûABCÇDEFGĞHIİJKLMNOÖPRSŞTUÜVYZÂÎÛ", - wiki_start_pages=["Ana_Sayfa"], - ), - "Vietnamese": Language( - name="Vietnamese", - iso_code="vi", - use_ascii=False, - # Windows-1258 is the only common 8-bit - # Vietnamese encoding supported by Python. - # From Wikipedia: - # For systems that lack support for Unicode, - # dozens of 8-bit Vietnamese code pages are - # available.[1] The most common are VISCII - # (TCVN 5712:1993), VPS, and Windows-1258.[3] - # Where ASCII is required, such as when - # ensuring readability in plain text e-mail, - # Vietnamese letters are often encoded - # according to Vietnamese Quoted-Readable - # (VIQR) or VSCII Mnemonic (VSCII-MNEM),[4] - # though usage of either variable-width - # scheme has declined dramatically following - # the adoption of Unicode on the World Wide - # Web. - charsets=["WINDOWS-1258"], - alphabet="aăâbcdđeêghiklmnoôơpqrstuưvxyAĂÂBCDĐEÊGHIKLMNOÔƠPQRSTUƯVXY", - wiki_start_pages=["Chữ_Quốc_ngữ"], - ), -} diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/resultdict.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/resultdict.py deleted file mode 100644 index 7d36e64..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/resultdict.py +++ /dev/null @@ -1,16 +0,0 @@ -from typing import TYPE_CHECKING, Optional - -if TYPE_CHECKING: - # TypedDict was introduced in Python 3.8. - # - # TODO: Remove the else block and TYPE_CHECKING check when dropping support - # for Python 3.7. - from typing import TypedDict - - class ResultDict(TypedDict): - encoding: Optional[str] - confidence: float - language: Optional[str] - -else: - ResultDict = dict diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sbcharsetprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sbcharsetprober.py deleted file mode 100644 index 0ffbcdd..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sbcharsetprober.py +++ /dev/null @@ -1,162 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Dict, List, NamedTuple, Optional, Union - -from .charsetprober import CharSetProber -from .enums import CharacterCategory, ProbingState, SequenceLikelihood - - -class SingleByteCharSetModel(NamedTuple): - charset_name: str - language: str - char_to_order_map: Dict[int, int] - language_model: Dict[int, Dict[int, int]] - typical_positive_ratio: float - keep_ascii_letters: bool - alphabet: str - - -class SingleByteCharSetProber(CharSetProber): - SAMPLE_SIZE = 64 - SB_ENOUGH_REL_THRESHOLD = 1024 # 0.25 * SAMPLE_SIZE^2 - POSITIVE_SHORTCUT_THRESHOLD = 0.95 - NEGATIVE_SHORTCUT_THRESHOLD = 0.05 - - def __init__( - self, - model: SingleByteCharSetModel, - is_reversed: bool = False, - name_prober: Optional[CharSetProber] = None, - ) -> None: - super().__init__() - self._model = model - # TRUE if we need to reverse every pair in the model lookup - self._reversed = is_reversed - # Optional auxiliary prober for name decision - self._name_prober = name_prober - self._last_order = 255 - self._seq_counters: List[int] = [] - self._total_seqs = 0 - self._total_char = 0 - self._control_char = 0 - self._freq_char = 0 - self.reset() - - def reset(self) -> None: - super().reset() - # char order of last character - self._last_order = 255 - self._seq_counters = [0] * SequenceLikelihood.get_num_categories() - self._total_seqs = 0 - self._total_char = 0 - self._control_char = 0 - # characters that fall in our sampling range - self._freq_char = 0 - - @property - def charset_name(self) -> Optional[str]: - if self._name_prober: - return self._name_prober.charset_name - return self._model.charset_name - - @property - def language(self) -> Optional[str]: - if self._name_prober: - return self._name_prober.language - return self._model.language - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - # TODO: Make filter_international_words keep things in self.alphabet - if not self._model.keep_ascii_letters: - byte_str = self.filter_international_words(byte_str) - else: - byte_str = self.remove_xml_tags(byte_str) - if not byte_str: - return self.state - char_to_order_map = self._model.char_to_order_map - language_model = self._model.language_model - for char in byte_str: - order = char_to_order_map.get(char, CharacterCategory.UNDEFINED) - # XXX: This was SYMBOL_CAT_ORDER before, with a value of 250, but - # CharacterCategory.SYMBOL is actually 253, so we use CONTROL - # to make it closer to the original intent. The only difference - # is whether or not we count digits and control characters for - # _total_char purposes. - if order < CharacterCategory.CONTROL: - self._total_char += 1 - if order < self.SAMPLE_SIZE: - self._freq_char += 1 - if self._last_order < self.SAMPLE_SIZE: - self._total_seqs += 1 - if not self._reversed: - lm_cat = language_model[self._last_order][order] - else: - lm_cat = language_model[order][self._last_order] - self._seq_counters[lm_cat] += 1 - self._last_order = order - - charset_name = self._model.charset_name - if self.state == ProbingState.DETECTING: - if self._total_seqs > self.SB_ENOUGH_REL_THRESHOLD: - confidence = self.get_confidence() - if confidence > self.POSITIVE_SHORTCUT_THRESHOLD: - self.logger.debug( - "%s confidence = %s, we have a winner", charset_name, confidence - ) - self._state = ProbingState.FOUND_IT - elif confidence < self.NEGATIVE_SHORTCUT_THRESHOLD: - self.logger.debug( - "%s confidence = %s, below negative shortcut threshold %s", - charset_name, - confidence, - self.NEGATIVE_SHORTCUT_THRESHOLD, - ) - self._state = ProbingState.NOT_ME - - return self.state - - def get_confidence(self) -> float: - r = 0.01 - if self._total_seqs > 0: - r = ( - ( - self._seq_counters[SequenceLikelihood.POSITIVE] - + 0.25 * self._seq_counters[SequenceLikelihood.LIKELY] - ) - / self._total_seqs - / self._model.typical_positive_ratio - ) - # The more control characters (proportionnaly to the size - # of the text), the less confident we become in the current - # charset. - r = r * (self._total_char - self._control_char) / self._total_char - r = r * self._freq_char / self._total_char - if r >= 1.0: - r = 0.99 - return r diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sbcsgroupprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sbcsgroupprober.py deleted file mode 100644 index 890ae84..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sbcsgroupprober.py +++ /dev/null @@ -1,88 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from .charsetgroupprober import CharSetGroupProber -from .hebrewprober import HebrewProber -from .langbulgarianmodel import ISO_8859_5_BULGARIAN_MODEL, WINDOWS_1251_BULGARIAN_MODEL -from .langgreekmodel import ISO_8859_7_GREEK_MODEL, WINDOWS_1253_GREEK_MODEL -from .langhebrewmodel import WINDOWS_1255_HEBREW_MODEL - -# from .langhungarianmodel import (ISO_8859_2_HUNGARIAN_MODEL, -# WINDOWS_1250_HUNGARIAN_MODEL) -from .langrussianmodel import ( - IBM855_RUSSIAN_MODEL, - IBM866_RUSSIAN_MODEL, - ISO_8859_5_RUSSIAN_MODEL, - KOI8_R_RUSSIAN_MODEL, - MACCYRILLIC_RUSSIAN_MODEL, - WINDOWS_1251_RUSSIAN_MODEL, -) -from .langthaimodel import TIS_620_THAI_MODEL -from .langturkishmodel import ISO_8859_9_TURKISH_MODEL -from .sbcharsetprober import SingleByteCharSetProber - - -class SBCSGroupProber(CharSetGroupProber): - def __init__(self) -> None: - super().__init__() - hebrew_prober = HebrewProber() - logical_hebrew_prober = SingleByteCharSetProber( - WINDOWS_1255_HEBREW_MODEL, is_reversed=False, name_prober=hebrew_prober - ) - # TODO: See if using ISO-8859-8 Hebrew model works better here, since - # it's actually the visual one - visual_hebrew_prober = SingleByteCharSetProber( - WINDOWS_1255_HEBREW_MODEL, is_reversed=True, name_prober=hebrew_prober - ) - hebrew_prober.set_model_probers(logical_hebrew_prober, visual_hebrew_prober) - # TODO: ORDER MATTERS HERE. I changed the order vs what was in master - # and several tests failed that did not before. Some thought - # should be put into the ordering, and we should consider making - # order not matter here, because that is very counter-intuitive. - self.probers = [ - SingleByteCharSetProber(WINDOWS_1251_RUSSIAN_MODEL), - SingleByteCharSetProber(KOI8_R_RUSSIAN_MODEL), - SingleByteCharSetProber(ISO_8859_5_RUSSIAN_MODEL), - SingleByteCharSetProber(MACCYRILLIC_RUSSIAN_MODEL), - SingleByteCharSetProber(IBM866_RUSSIAN_MODEL), - SingleByteCharSetProber(IBM855_RUSSIAN_MODEL), - SingleByteCharSetProber(ISO_8859_7_GREEK_MODEL), - SingleByteCharSetProber(WINDOWS_1253_GREEK_MODEL), - SingleByteCharSetProber(ISO_8859_5_BULGARIAN_MODEL), - SingleByteCharSetProber(WINDOWS_1251_BULGARIAN_MODEL), - # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250) - # after we retrain model. - # SingleByteCharSetProber(ISO_8859_2_HUNGARIAN_MODEL), - # SingleByteCharSetProber(WINDOWS_1250_HUNGARIAN_MODEL), - SingleByteCharSetProber(TIS_620_THAI_MODEL), - SingleByteCharSetProber(ISO_8859_9_TURKISH_MODEL), - hebrew_prober, - logical_hebrew_prober, - visual_hebrew_prober, - ] - self.reset() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sjisprober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sjisprober.py deleted file mode 100644 index 91df077..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/sjisprober.py +++ /dev/null @@ -1,105 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Union - -from .chardistribution import SJISDistributionAnalysis -from .codingstatemachine import CodingStateMachine -from .enums import MachineState, ProbingState -from .jpcntx import SJISContextAnalysis -from .mbcharsetprober import MultiByteCharSetProber -from .mbcssm import SJIS_SM_MODEL - - -class SJISProber(MultiByteCharSetProber): - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(SJIS_SM_MODEL) - self.distribution_analyzer = SJISDistributionAnalysis() - self.context_analyzer = SJISContextAnalysis() - self.reset() - - def reset(self) -> None: - super().reset() - self.context_analyzer.reset() - - @property - def charset_name(self) -> str: - return self.context_analyzer.charset_name - - @property - def language(self) -> str: - return "Japanese" - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - assert self.coding_sm is not None - assert self.distribution_analyzer is not None - - for i, byte in enumerate(byte_str): - coding_state = self.coding_sm.next_state(byte) - if coding_state == MachineState.ERROR: - self.logger.debug( - "%s %s prober hit error at byte %s", - self.charset_name, - self.language, - i, - ) - self._state = ProbingState.NOT_ME - break - if coding_state == MachineState.ITS_ME: - self._state = ProbingState.FOUND_IT - break - if coding_state == MachineState.START: - char_len = self.coding_sm.get_current_charlen() - if i == 0: - self._last_char[1] = byte - self.context_analyzer.feed( - self._last_char[2 - char_len :], char_len - ) - self.distribution_analyzer.feed(self._last_char, char_len) - else: - self.context_analyzer.feed( - byte_str[i + 1 - char_len : i + 3 - char_len], char_len - ) - self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len) - - self._last_char[0] = byte_str[-1] - - if self.state == ProbingState.DETECTING: - if self.context_analyzer.got_enough_data() and ( - self.get_confidence() > self.SHORTCUT_THRESHOLD - ): - self._state = ProbingState.FOUND_IT - - return self.state - - def get_confidence(self) -> float: - assert self.distribution_analyzer is not None - - context_conf = self.context_analyzer.get_confidence() - distrib_conf = self.distribution_analyzer.get_confidence() - return max(context_conf, distrib_conf) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/universaldetector.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/universaldetector.py deleted file mode 100644 index 30c441d..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/universaldetector.py +++ /dev/null @@ -1,362 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is Mozilla Universal charset detector code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 2001 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# Shy Shalom - original C code -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### -""" -Module containing the UniversalDetector detector class, which is the primary -class a user of ``chardet`` should use. - -:author: Mark Pilgrim (initial port to Python) -:author: Shy Shalom (original C code) -:author: Dan Blanchard (major refactoring for 3.0) -:author: Ian Cordasco -""" - - -import codecs -import logging -import re -from typing import List, Optional, Union - -from .charsetgroupprober import CharSetGroupProber -from .charsetprober import CharSetProber -from .enums import InputState, LanguageFilter, ProbingState -from .escprober import EscCharSetProber -from .latin1prober import Latin1Prober -from .macromanprober import MacRomanProber -from .mbcsgroupprober import MBCSGroupProber -from .resultdict import ResultDict -from .sbcsgroupprober import SBCSGroupProber -from .utf1632prober import UTF1632Prober - - -class UniversalDetector: - """ - The ``UniversalDetector`` class underlies the ``chardet.detect`` function - and coordinates all of the different charset probers. - - To get a ``dict`` containing an encoding and its confidence, you can simply - run: - - .. code:: - - u = UniversalDetector() - u.feed(some_bytes) - u.close() - detected = u.result - - """ - - MINIMUM_THRESHOLD = 0.20 - HIGH_BYTE_DETECTOR = re.compile(b"[\x80-\xFF]") - ESC_DETECTOR = re.compile(b"(\033|~{)") - WIN_BYTE_DETECTOR = re.compile(b"[\x80-\x9F]") - ISO_WIN_MAP = { - "iso-8859-1": "Windows-1252", - "iso-8859-2": "Windows-1250", - "iso-8859-5": "Windows-1251", - "iso-8859-6": "Windows-1256", - "iso-8859-7": "Windows-1253", - "iso-8859-8": "Windows-1255", - "iso-8859-9": "Windows-1254", - "iso-8859-13": "Windows-1257", - } - # Based on https://encoding.spec.whatwg.org/#names-and-labels - # but altered to match Python names for encodings and remove mappings - # that break tests. - LEGACY_MAP = { - "ascii": "Windows-1252", - "iso-8859-1": "Windows-1252", - "tis-620": "ISO-8859-11", - "iso-8859-9": "Windows-1254", - "gb2312": "GB18030", - "euc-kr": "CP949", - "utf-16le": "UTF-16", - } - - def __init__( - self, - lang_filter: LanguageFilter = LanguageFilter.ALL, - should_rename_legacy: bool = False, - ) -> None: - self._esc_charset_prober: Optional[EscCharSetProber] = None - self._utf1632_prober: Optional[UTF1632Prober] = None - self._charset_probers: List[CharSetProber] = [] - self.result: ResultDict = { - "encoding": None, - "confidence": 0.0, - "language": None, - } - self.done = False - self._got_data = False - self._input_state = InputState.PURE_ASCII - self._last_char = b"" - self.lang_filter = lang_filter - self.logger = logging.getLogger(__name__) - self._has_win_bytes = False - self.should_rename_legacy = should_rename_legacy - self.reset() - - @property - def input_state(self) -> int: - return self._input_state - - @property - def has_win_bytes(self) -> bool: - return self._has_win_bytes - - @property - def charset_probers(self) -> List[CharSetProber]: - return self._charset_probers - - def reset(self) -> None: - """ - Reset the UniversalDetector and all of its probers back to their - initial states. This is called by ``__init__``, so you only need to - call this directly in between analyses of different documents. - """ - self.result = {"encoding": None, "confidence": 0.0, "language": None} - self.done = False - self._got_data = False - self._has_win_bytes = False - self._input_state = InputState.PURE_ASCII - self._last_char = b"" - if self._esc_charset_prober: - self._esc_charset_prober.reset() - if self._utf1632_prober: - self._utf1632_prober.reset() - for prober in self._charset_probers: - prober.reset() - - def feed(self, byte_str: Union[bytes, bytearray]) -> None: - """ - Takes a chunk of a document and feeds it through all of the relevant - charset probers. - - After calling ``feed``, you can check the value of the ``done`` - attribute to see if you need to continue feeding the - ``UniversalDetector`` more data, or if it has made a prediction - (in the ``result`` attribute). - - .. note:: - You should always call ``close`` when you're done feeding in your - document if ``done`` is not already ``True``. - """ - if self.done: - return - - if not byte_str: - return - - if not isinstance(byte_str, bytearray): - byte_str = bytearray(byte_str) - - # First check for known BOMs, since these are guaranteed to be correct - if not self._got_data: - # If the data starts with BOM, we know it is UTF - if byte_str.startswith(codecs.BOM_UTF8): - # EF BB BF UTF-8 with BOM - self.result = { - "encoding": "UTF-8-SIG", - "confidence": 1.0, - "language": "", - } - elif byte_str.startswith((codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE)): - # FF FE 00 00 UTF-32, little-endian BOM - # 00 00 FE FF UTF-32, big-endian BOM - self.result = {"encoding": "UTF-32", "confidence": 1.0, "language": ""} - elif byte_str.startswith(b"\xFE\xFF\x00\x00"): - # FE FF 00 00 UCS-4, unusual octet order BOM (3412) - self.result = { - # TODO: This encoding is not supported by Python. Should remove? - "encoding": "X-ISO-10646-UCS-4-3412", - "confidence": 1.0, - "language": "", - } - elif byte_str.startswith(b"\x00\x00\xFF\xFE"): - # 00 00 FF FE UCS-4, unusual octet order BOM (2143) - self.result = { - # TODO: This encoding is not supported by Python. Should remove? - "encoding": "X-ISO-10646-UCS-4-2143", - "confidence": 1.0, - "language": "", - } - elif byte_str.startswith((codecs.BOM_LE, codecs.BOM_BE)): - # FF FE UTF-16, little endian BOM - # FE FF UTF-16, big endian BOM - self.result = {"encoding": "UTF-16", "confidence": 1.0, "language": ""} - - self._got_data = True - if self.result["encoding"] is not None: - self.done = True - return - - # If none of those matched and we've only see ASCII so far, check - # for high bytes and escape sequences - if self._input_state == InputState.PURE_ASCII: - if self.HIGH_BYTE_DETECTOR.search(byte_str): - self._input_state = InputState.HIGH_BYTE - elif ( - self._input_state == InputState.PURE_ASCII - and self.ESC_DETECTOR.search(self._last_char + byte_str) - ): - self._input_state = InputState.ESC_ASCII - - self._last_char = byte_str[-1:] - - # next we will look to see if it is appears to be either a UTF-16 or - # UTF-32 encoding - if not self._utf1632_prober: - self._utf1632_prober = UTF1632Prober() - - if self._utf1632_prober.state == ProbingState.DETECTING: - if self._utf1632_prober.feed(byte_str) == ProbingState.FOUND_IT: - self.result = { - "encoding": self._utf1632_prober.charset_name, - "confidence": self._utf1632_prober.get_confidence(), - "language": "", - } - self.done = True - return - - # If we've seen escape sequences, use the EscCharSetProber, which - # uses a simple state machine to check for known escape sequences in - # HZ and ISO-2022 encodings, since those are the only encodings that - # use such sequences. - if self._input_state == InputState.ESC_ASCII: - if not self._esc_charset_prober: - self._esc_charset_prober = EscCharSetProber(self.lang_filter) - if self._esc_charset_prober.feed(byte_str) == ProbingState.FOUND_IT: - self.result = { - "encoding": self._esc_charset_prober.charset_name, - "confidence": self._esc_charset_prober.get_confidence(), - "language": self._esc_charset_prober.language, - } - self.done = True - # If we've seen high bytes (i.e., those with values greater than 127), - # we need to do more complicated checks using all our multi-byte and - # single-byte probers that are left. The single-byte probers - # use character bigram distributions to determine the encoding, whereas - # the multi-byte probers use a combination of character unigram and - # bigram distributions. - elif self._input_state == InputState.HIGH_BYTE: - if not self._charset_probers: - self._charset_probers = [MBCSGroupProber(self.lang_filter)] - # If we're checking non-CJK encodings, use single-byte prober - if self.lang_filter & LanguageFilter.NON_CJK: - self._charset_probers.append(SBCSGroupProber()) - self._charset_probers.append(Latin1Prober()) - self._charset_probers.append(MacRomanProber()) - for prober in self._charset_probers: - if prober.feed(byte_str) == ProbingState.FOUND_IT: - self.result = { - "encoding": prober.charset_name, - "confidence": prober.get_confidence(), - "language": prober.language, - } - self.done = True - break - if self.WIN_BYTE_DETECTOR.search(byte_str): - self._has_win_bytes = True - - def close(self) -> ResultDict: - """ - Stop analyzing the current document and come up with a final - prediction. - - :returns: The ``result`` attribute, a ``dict`` with the keys - `encoding`, `confidence`, and `language`. - """ - # Don't bother with checks if we're already done - if self.done: - return self.result - self.done = True - - if not self._got_data: - self.logger.debug("no data received!") - - # Default to ASCII if it is all we've seen so far - elif self._input_state == InputState.PURE_ASCII: - self.result = {"encoding": "ascii", "confidence": 1.0, "language": ""} - - # If we have seen non-ASCII, return the best that met MINIMUM_THRESHOLD - elif self._input_state == InputState.HIGH_BYTE: - prober_confidence = None - max_prober_confidence = 0.0 - max_prober = None - for prober in self._charset_probers: - if not prober: - continue - prober_confidence = prober.get_confidence() - if prober_confidence > max_prober_confidence: - max_prober_confidence = prober_confidence - max_prober = prober - if max_prober and (max_prober_confidence > self.MINIMUM_THRESHOLD): - charset_name = max_prober.charset_name - assert charset_name is not None - lower_charset_name = charset_name.lower() - confidence = max_prober.get_confidence() - # Use Windows encoding name instead of ISO-8859 if we saw any - # extra Windows-specific bytes - if lower_charset_name.startswith("iso-8859"): - if self._has_win_bytes: - charset_name = self.ISO_WIN_MAP.get( - lower_charset_name, charset_name - ) - # Rename legacy encodings with superset encodings if asked - if self.should_rename_legacy: - charset_name = self.LEGACY_MAP.get( - (charset_name or "").lower(), charset_name - ) - self.result = { - "encoding": charset_name, - "confidence": confidence, - "language": max_prober.language, - } - - # Log all prober confidences if none met MINIMUM_THRESHOLD - if self.logger.getEffectiveLevel() <= logging.DEBUG: - if self.result["encoding"] is None: - self.logger.debug("no probers hit minimum threshold") - for group_prober in self._charset_probers: - if not group_prober: - continue - if isinstance(group_prober, CharSetGroupProber): - for prober in group_prober.probers: - self.logger.debug( - "%s %s confidence = %s", - prober.charset_name, - prober.language, - prober.get_confidence(), - ) - else: - self.logger.debug( - "%s %s confidence = %s", - group_prober.charset_name, - group_prober.language, - group_prober.get_confidence(), - ) - return self.result diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/utf1632prober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/utf1632prober.py deleted file mode 100644 index 6bdec63..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/utf1632prober.py +++ /dev/null @@ -1,225 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# -# Contributor(s): -# Jason Zavaglia -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### -from typing import List, Union - -from .charsetprober import CharSetProber -from .enums import ProbingState - - -class UTF1632Prober(CharSetProber): - """ - This class simply looks for occurrences of zero bytes, and infers - whether the file is UTF16 or UTF32 (low-endian or big-endian) - For instance, files looking like ( \0 \0 \0 [nonzero] )+ - have a good probability to be UTF32BE. Files looking like ( \0 [nonzero] )+ - may be guessed to be UTF16BE, and inversely for little-endian varieties. - """ - - # how many logical characters to scan before feeling confident of prediction - MIN_CHARS_FOR_DETECTION = 20 - # a fixed constant ratio of expected zeros or non-zeros in modulo-position. - EXPECTED_RATIO = 0.94 - - def __init__(self) -> None: - super().__init__() - self.position = 0 - self.zeros_at_mod = [0] * 4 - self.nonzeros_at_mod = [0] * 4 - self._state = ProbingState.DETECTING - self.quad = [0, 0, 0, 0] - self.invalid_utf16be = False - self.invalid_utf16le = False - self.invalid_utf32be = False - self.invalid_utf32le = False - self.first_half_surrogate_pair_detected_16be = False - self.first_half_surrogate_pair_detected_16le = False - self.reset() - - def reset(self) -> None: - super().reset() - self.position = 0 - self.zeros_at_mod = [0] * 4 - self.nonzeros_at_mod = [0] * 4 - self._state = ProbingState.DETECTING - self.invalid_utf16be = False - self.invalid_utf16le = False - self.invalid_utf32be = False - self.invalid_utf32le = False - self.first_half_surrogate_pair_detected_16be = False - self.first_half_surrogate_pair_detected_16le = False - self.quad = [0, 0, 0, 0] - - @property - def charset_name(self) -> str: - if self.is_likely_utf32be(): - return "utf-32be" - if self.is_likely_utf32le(): - return "utf-32le" - if self.is_likely_utf16be(): - return "utf-16be" - if self.is_likely_utf16le(): - return "utf-16le" - # default to something valid - return "utf-16" - - @property - def language(self) -> str: - return "" - - def approx_32bit_chars(self) -> float: - return max(1.0, self.position / 4.0) - - def approx_16bit_chars(self) -> float: - return max(1.0, self.position / 2.0) - - def is_likely_utf32be(self) -> bool: - approx_chars = self.approx_32bit_chars() - return approx_chars >= self.MIN_CHARS_FOR_DETECTION and ( - self.zeros_at_mod[0] / approx_chars > self.EXPECTED_RATIO - and self.zeros_at_mod[1] / approx_chars > self.EXPECTED_RATIO - and self.zeros_at_mod[2] / approx_chars > self.EXPECTED_RATIO - and self.nonzeros_at_mod[3] / approx_chars > self.EXPECTED_RATIO - and not self.invalid_utf32be - ) - - def is_likely_utf32le(self) -> bool: - approx_chars = self.approx_32bit_chars() - return approx_chars >= self.MIN_CHARS_FOR_DETECTION and ( - self.nonzeros_at_mod[0] / approx_chars > self.EXPECTED_RATIO - and self.zeros_at_mod[1] / approx_chars > self.EXPECTED_RATIO - and self.zeros_at_mod[2] / approx_chars > self.EXPECTED_RATIO - and self.zeros_at_mod[3] / approx_chars > self.EXPECTED_RATIO - and not self.invalid_utf32le - ) - - def is_likely_utf16be(self) -> bool: - approx_chars = self.approx_16bit_chars() - return approx_chars >= self.MIN_CHARS_FOR_DETECTION and ( - (self.nonzeros_at_mod[1] + self.nonzeros_at_mod[3]) / approx_chars - > self.EXPECTED_RATIO - and (self.zeros_at_mod[0] + self.zeros_at_mod[2]) / approx_chars - > self.EXPECTED_RATIO - and not self.invalid_utf16be - ) - - def is_likely_utf16le(self) -> bool: - approx_chars = self.approx_16bit_chars() - return approx_chars >= self.MIN_CHARS_FOR_DETECTION and ( - (self.nonzeros_at_mod[0] + self.nonzeros_at_mod[2]) / approx_chars - > self.EXPECTED_RATIO - and (self.zeros_at_mod[1] + self.zeros_at_mod[3]) / approx_chars - > self.EXPECTED_RATIO - and not self.invalid_utf16le - ) - - def validate_utf32_characters(self, quad: List[int]) -> None: - """ - Validate if the quad of bytes is valid UTF-32. - - UTF-32 is valid in the range 0x00000000 - 0x0010FFFF - excluding 0x0000D800 - 0x0000DFFF - - https://en.wikipedia.org/wiki/UTF-32 - """ - if ( - quad[0] != 0 - or quad[1] > 0x10 - or (quad[0] == 0 and quad[1] == 0 and 0xD8 <= quad[2] <= 0xDF) - ): - self.invalid_utf32be = True - if ( - quad[3] != 0 - or quad[2] > 0x10 - or (quad[3] == 0 and quad[2] == 0 and 0xD8 <= quad[1] <= 0xDF) - ): - self.invalid_utf32le = True - - def validate_utf16_characters(self, pair: List[int]) -> None: - """ - Validate if the pair of bytes is valid UTF-16. - - UTF-16 is valid in the range 0x0000 - 0xFFFF excluding 0xD800 - 0xFFFF - with an exception for surrogate pairs, which must be in the range - 0xD800-0xDBFF followed by 0xDC00-0xDFFF - - https://en.wikipedia.org/wiki/UTF-16 - """ - if not self.first_half_surrogate_pair_detected_16be: - if 0xD8 <= pair[0] <= 0xDB: - self.first_half_surrogate_pair_detected_16be = True - elif 0xDC <= pair[0] <= 0xDF: - self.invalid_utf16be = True - else: - if 0xDC <= pair[0] <= 0xDF: - self.first_half_surrogate_pair_detected_16be = False - else: - self.invalid_utf16be = True - - if not self.first_half_surrogate_pair_detected_16le: - if 0xD8 <= pair[1] <= 0xDB: - self.first_half_surrogate_pair_detected_16le = True - elif 0xDC <= pair[1] <= 0xDF: - self.invalid_utf16le = True - else: - if 0xDC <= pair[1] <= 0xDF: - self.first_half_surrogate_pair_detected_16le = False - else: - self.invalid_utf16le = True - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - for c in byte_str: - mod4 = self.position % 4 - self.quad[mod4] = c - if mod4 == 3: - self.validate_utf32_characters(self.quad) - self.validate_utf16_characters(self.quad[0:2]) - self.validate_utf16_characters(self.quad[2:4]) - if c == 0: - self.zeros_at_mod[mod4] += 1 - else: - self.nonzeros_at_mod[mod4] += 1 - self.position += 1 - return self.state - - @property - def state(self) -> ProbingState: - if self._state in {ProbingState.NOT_ME, ProbingState.FOUND_IT}: - # terminal, decided states - return self._state - if self.get_confidence() > 0.80: - self._state = ProbingState.FOUND_IT - elif self.position > 4 * 1024: - # if we get to 4kb into the file, and we can't conclude it's UTF, - # let's give up - self._state = ProbingState.NOT_ME - return self._state - - def get_confidence(self) -> float: - return ( - 0.85 - if ( - self.is_likely_utf16le() - or self.is_likely_utf16be() - or self.is_likely_utf32le() - or self.is_likely_utf32be() - ) - else 0.00 - ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/utf8prober.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/utf8prober.py deleted file mode 100644 index d96354d..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/utf8prober.py +++ /dev/null @@ -1,82 +0,0 @@ -######################## BEGIN LICENSE BLOCK ######################## -# The Original Code is mozilla.org code. -# -# The Initial Developer of the Original Code is -# Netscape Communications Corporation. -# Portions created by the Initial Developer are Copyright (C) 1998 -# the Initial Developer. All Rights Reserved. -# -# Contributor(s): -# Mark Pilgrim - port to Python -# -# This library is free software; you can redistribute it and/or -# modify it under the terms of the GNU Lesser General Public -# License as published by the Free Software Foundation; either -# version 2.1 of the License, or (at your option) any later version. -# -# This library is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public -# License along with this library; if not, write to the Free Software -# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA -# 02110-1301 USA -######################### END LICENSE BLOCK ######################### - -from typing import Union - -from .charsetprober import CharSetProber -from .codingstatemachine import CodingStateMachine -from .enums import MachineState, ProbingState -from .mbcssm import UTF8_SM_MODEL - - -class UTF8Prober(CharSetProber): - ONE_CHAR_PROB = 0.5 - - def __init__(self) -> None: - super().__init__() - self.coding_sm = CodingStateMachine(UTF8_SM_MODEL) - self._num_mb_chars = 0 - self.reset() - - def reset(self) -> None: - super().reset() - self.coding_sm.reset() - self._num_mb_chars = 0 - - @property - def charset_name(self) -> str: - return "utf-8" - - @property - def language(self) -> str: - return "" - - def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: - for c in byte_str: - coding_state = self.coding_sm.next_state(c) - if coding_state == MachineState.ERROR: - self._state = ProbingState.NOT_ME - break - if coding_state == MachineState.ITS_ME: - self._state = ProbingState.FOUND_IT - break - if coding_state == MachineState.START: - if self.coding_sm.get_current_charlen() >= 2: - self._num_mb_chars += 1 - - if self.state == ProbingState.DETECTING: - if self.get_confidence() > self.SHORTCUT_THRESHOLD: - self._state = ProbingState.FOUND_IT - - return self.state - - def get_confidence(self) -> float: - unlike = 0.99 - if self._num_mb_chars < 6: - unlike *= self.ONE_CHAR_PROB**self._num_mb_chars - return 1.0 - unlike - return unlike diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/version.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/version.py deleted file mode 100644 index c5e9d85..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/version.py +++ /dev/null @@ -1,9 +0,0 @@ -""" -This module exists only to simplify retrieving the version number of chardet -from within setuptools and from chardet subpackages. - -:author: Dan Blanchard (dan.blanchard@gmail.com) -""" - -__version__ = "5.1.0" -VERSION = __version__.split(".") diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__init__.py deleted file mode 100644 index 383101c..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -from .initialise import init, deinit, reinit, colorama_text, just_fix_windows_console -from .ansi import Fore, Back, Style, Cursor -from .ansitowin32 import AnsiToWin32 - -__version__ = '0.4.6' - diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 7a72ee5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/ansi.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/ansi.cpython-312.pyc deleted file mode 100644 index 1d031d3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/ansi.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/ansitowin32.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/ansitowin32.cpython-312.pyc deleted file mode 100644 index 67ad425..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/ansitowin32.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/initialise.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/initialise.cpython-312.pyc deleted file mode 100644 index 31014bc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/initialise.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/win32.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/win32.cpython-312.pyc deleted file mode 100644 index 555d17d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/win32.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/winterm.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/winterm.cpython-312.pyc deleted file mode 100644 index 76c8e2d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/__pycache__/winterm.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/ansi.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/ansi.py deleted file mode 100644 index 11ec695..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/ansi.py +++ /dev/null @@ -1,102 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -''' -This module generates ANSI character codes to printing colors to terminals. -See: http://en.wikipedia.org/wiki/ANSI_escape_code -''' - -CSI = '\033[' -OSC = '\033]' -BEL = '\a' - - -def code_to_chars(code): - return CSI + str(code) + 'm' - -def set_title(title): - return OSC + '2;' + title + BEL - -def clear_screen(mode=2): - return CSI + str(mode) + 'J' - -def clear_line(mode=2): - return CSI + str(mode) + 'K' - - -class AnsiCodes(object): - def __init__(self): - # the subclasses declare class attributes which are numbers. - # Upon instantiation we define instance attributes, which are the same - # as the class attributes but wrapped with the ANSI escape sequence - for name in dir(self): - if not name.startswith('_'): - value = getattr(self, name) - setattr(self, name, code_to_chars(value)) - - -class AnsiCursor(object): - def UP(self, n=1): - return CSI + str(n) + 'A' - def DOWN(self, n=1): - return CSI + str(n) + 'B' - def FORWARD(self, n=1): - return CSI + str(n) + 'C' - def BACK(self, n=1): - return CSI + str(n) + 'D' - def POS(self, x=1, y=1): - return CSI + str(y) + ';' + str(x) + 'H' - - -class AnsiFore(AnsiCodes): - BLACK = 30 - RED = 31 - GREEN = 32 - YELLOW = 33 - BLUE = 34 - MAGENTA = 35 - CYAN = 36 - WHITE = 37 - RESET = 39 - - # These are fairly well supported, but not part of the standard. - LIGHTBLACK_EX = 90 - LIGHTRED_EX = 91 - LIGHTGREEN_EX = 92 - LIGHTYELLOW_EX = 93 - LIGHTBLUE_EX = 94 - LIGHTMAGENTA_EX = 95 - LIGHTCYAN_EX = 96 - LIGHTWHITE_EX = 97 - - -class AnsiBack(AnsiCodes): - BLACK = 40 - RED = 41 - GREEN = 42 - YELLOW = 43 - BLUE = 44 - MAGENTA = 45 - CYAN = 46 - WHITE = 47 - RESET = 49 - - # These are fairly well supported, but not part of the standard. - LIGHTBLACK_EX = 100 - LIGHTRED_EX = 101 - LIGHTGREEN_EX = 102 - LIGHTYELLOW_EX = 103 - LIGHTBLUE_EX = 104 - LIGHTMAGENTA_EX = 105 - LIGHTCYAN_EX = 106 - LIGHTWHITE_EX = 107 - - -class AnsiStyle(AnsiCodes): - BRIGHT = 1 - DIM = 2 - NORMAL = 22 - RESET_ALL = 0 - -Fore = AnsiFore() -Back = AnsiBack() -Style = AnsiStyle() -Cursor = AnsiCursor() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/ansitowin32.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/ansitowin32.py deleted file mode 100644 index abf209e..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/ansitowin32.py +++ /dev/null @@ -1,277 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -import re -import sys -import os - -from .ansi import AnsiFore, AnsiBack, AnsiStyle, Style, BEL -from .winterm import enable_vt_processing, WinTerm, WinColor, WinStyle -from .win32 import windll, winapi_test - - -winterm = None -if windll is not None: - winterm = WinTerm() - - -class StreamWrapper(object): - ''' - Wraps a stream (such as stdout), acting as a transparent proxy for all - attribute access apart from method 'write()', which is delegated to our - Converter instance. - ''' - def __init__(self, wrapped, converter): - # double-underscore everything to prevent clashes with names of - # attributes on the wrapped stream object. - self.__wrapped = wrapped - self.__convertor = converter - - def __getattr__(self, name): - return getattr(self.__wrapped, name) - - def __enter__(self, *args, **kwargs): - # special method lookup bypasses __getattr__/__getattribute__, see - # https://stackoverflow.com/questions/12632894/why-doesnt-getattr-work-with-exit - # thus, contextlib magic methods are not proxied via __getattr__ - return self.__wrapped.__enter__(*args, **kwargs) - - def __exit__(self, *args, **kwargs): - return self.__wrapped.__exit__(*args, **kwargs) - - def __setstate__(self, state): - self.__dict__ = state - - def __getstate__(self): - return self.__dict__ - - def write(self, text): - self.__convertor.write(text) - - def isatty(self): - stream = self.__wrapped - if 'PYCHARM_HOSTED' in os.environ: - if stream is not None and (stream is sys.__stdout__ or stream is sys.__stderr__): - return True - try: - stream_isatty = stream.isatty - except AttributeError: - return False - else: - return stream_isatty() - - @property - def closed(self): - stream = self.__wrapped - try: - return stream.closed - # AttributeError in the case that the stream doesn't support being closed - # ValueError for the case that the stream has already been detached when atexit runs - except (AttributeError, ValueError): - return True - - -class AnsiToWin32(object): - ''' - Implements a 'write()' method which, on Windows, will strip ANSI character - sequences from the text, and if outputting to a tty, will convert them into - win32 function calls. - ''' - ANSI_CSI_RE = re.compile('\001?\033\\[((?:\\d|;)*)([a-zA-Z])\002?') # Control Sequence Introducer - ANSI_OSC_RE = re.compile('\001?\033\\]([^\a]*)(\a)\002?') # Operating System Command - - def __init__(self, wrapped, convert=None, strip=None, autoreset=False): - # The wrapped stream (normally sys.stdout or sys.stderr) - self.wrapped = wrapped - - # should we reset colors to defaults after every .write() - self.autoreset = autoreset - - # create the proxy wrapping our output stream - self.stream = StreamWrapper(wrapped, self) - - on_windows = os.name == 'nt' - # We test if the WinAPI works, because even if we are on Windows - # we may be using a terminal that doesn't support the WinAPI - # (e.g. Cygwin Terminal). In this case it's up to the terminal - # to support the ANSI codes. - conversion_supported = on_windows and winapi_test() - try: - fd = wrapped.fileno() - except Exception: - fd = -1 - system_has_native_ansi = not on_windows or enable_vt_processing(fd) - have_tty = not self.stream.closed and self.stream.isatty() - need_conversion = conversion_supported and not system_has_native_ansi - - # should we strip ANSI sequences from our output? - if strip is None: - strip = need_conversion or not have_tty - self.strip = strip - - # should we should convert ANSI sequences into win32 calls? - if convert is None: - convert = need_conversion and have_tty - self.convert = convert - - # dict of ansi codes to win32 functions and parameters - self.win32_calls = self.get_win32_calls() - - # are we wrapping stderr? - self.on_stderr = self.wrapped is sys.stderr - - def should_wrap(self): - ''' - True if this class is actually needed. If false, then the output - stream will not be affected, nor will win32 calls be issued, so - wrapping stdout is not actually required. This will generally be - False on non-Windows platforms, unless optional functionality like - autoreset has been requested using kwargs to init() - ''' - return self.convert or self.strip or self.autoreset - - def get_win32_calls(self): - if self.convert and winterm: - return { - AnsiStyle.RESET_ALL: (winterm.reset_all, ), - AnsiStyle.BRIGHT: (winterm.style, WinStyle.BRIGHT), - AnsiStyle.DIM: (winterm.style, WinStyle.NORMAL), - AnsiStyle.NORMAL: (winterm.style, WinStyle.NORMAL), - AnsiFore.BLACK: (winterm.fore, WinColor.BLACK), - AnsiFore.RED: (winterm.fore, WinColor.RED), - AnsiFore.GREEN: (winterm.fore, WinColor.GREEN), - AnsiFore.YELLOW: (winterm.fore, WinColor.YELLOW), - AnsiFore.BLUE: (winterm.fore, WinColor.BLUE), - AnsiFore.MAGENTA: (winterm.fore, WinColor.MAGENTA), - AnsiFore.CYAN: (winterm.fore, WinColor.CYAN), - AnsiFore.WHITE: (winterm.fore, WinColor.GREY), - AnsiFore.RESET: (winterm.fore, ), - AnsiFore.LIGHTBLACK_EX: (winterm.fore, WinColor.BLACK, True), - AnsiFore.LIGHTRED_EX: (winterm.fore, WinColor.RED, True), - AnsiFore.LIGHTGREEN_EX: (winterm.fore, WinColor.GREEN, True), - AnsiFore.LIGHTYELLOW_EX: (winterm.fore, WinColor.YELLOW, True), - AnsiFore.LIGHTBLUE_EX: (winterm.fore, WinColor.BLUE, True), - AnsiFore.LIGHTMAGENTA_EX: (winterm.fore, WinColor.MAGENTA, True), - AnsiFore.LIGHTCYAN_EX: (winterm.fore, WinColor.CYAN, True), - AnsiFore.LIGHTWHITE_EX: (winterm.fore, WinColor.GREY, True), - AnsiBack.BLACK: (winterm.back, WinColor.BLACK), - AnsiBack.RED: (winterm.back, WinColor.RED), - AnsiBack.GREEN: (winterm.back, WinColor.GREEN), - AnsiBack.YELLOW: (winterm.back, WinColor.YELLOW), - AnsiBack.BLUE: (winterm.back, WinColor.BLUE), - AnsiBack.MAGENTA: (winterm.back, WinColor.MAGENTA), - AnsiBack.CYAN: (winterm.back, WinColor.CYAN), - AnsiBack.WHITE: (winterm.back, WinColor.GREY), - AnsiBack.RESET: (winterm.back, ), - AnsiBack.LIGHTBLACK_EX: (winterm.back, WinColor.BLACK, True), - AnsiBack.LIGHTRED_EX: (winterm.back, WinColor.RED, True), - AnsiBack.LIGHTGREEN_EX: (winterm.back, WinColor.GREEN, True), - AnsiBack.LIGHTYELLOW_EX: (winterm.back, WinColor.YELLOW, True), - AnsiBack.LIGHTBLUE_EX: (winterm.back, WinColor.BLUE, True), - AnsiBack.LIGHTMAGENTA_EX: (winterm.back, WinColor.MAGENTA, True), - AnsiBack.LIGHTCYAN_EX: (winterm.back, WinColor.CYAN, True), - AnsiBack.LIGHTWHITE_EX: (winterm.back, WinColor.GREY, True), - } - return dict() - - def write(self, text): - if self.strip or self.convert: - self.write_and_convert(text) - else: - self.wrapped.write(text) - self.wrapped.flush() - if self.autoreset: - self.reset_all() - - - def reset_all(self): - if self.convert: - self.call_win32('m', (0,)) - elif not self.strip and not self.stream.closed: - self.wrapped.write(Style.RESET_ALL) - - - def write_and_convert(self, text): - ''' - Write the given text to our wrapped stream, stripping any ANSI - sequences from the text, and optionally converting them into win32 - calls. - ''' - cursor = 0 - text = self.convert_osc(text) - for match in self.ANSI_CSI_RE.finditer(text): - start, end = match.span() - self.write_plain_text(text, cursor, start) - self.convert_ansi(*match.groups()) - cursor = end - self.write_plain_text(text, cursor, len(text)) - - - def write_plain_text(self, text, start, end): - if start < end: - self.wrapped.write(text[start:end]) - self.wrapped.flush() - - - def convert_ansi(self, paramstring, command): - if self.convert: - params = self.extract_params(command, paramstring) - self.call_win32(command, params) - - - def extract_params(self, command, paramstring): - if command in 'Hf': - params = tuple(int(p) if len(p) != 0 else 1 for p in paramstring.split(';')) - while len(params) < 2: - # defaults: - params = params + (1,) - else: - params = tuple(int(p) for p in paramstring.split(';') if len(p) != 0) - if len(params) == 0: - # defaults: - if command in 'JKm': - params = (0,) - elif command in 'ABCD': - params = (1,) - - return params - - - def call_win32(self, command, params): - if command == 'm': - for param in params: - if param in self.win32_calls: - func_args = self.win32_calls[param] - func = func_args[0] - args = func_args[1:] - kwargs = dict(on_stderr=self.on_stderr) - func(*args, **kwargs) - elif command in 'J': - winterm.erase_screen(params[0], on_stderr=self.on_stderr) - elif command in 'K': - winterm.erase_line(params[0], on_stderr=self.on_stderr) - elif command in 'Hf': # cursor position - absolute - winterm.set_cursor_position(params, on_stderr=self.on_stderr) - elif command in 'ABCD': # cursor position - relative - n = params[0] - # A - up, B - down, C - forward, D - back - x, y = {'A': (0, -n), 'B': (0, n), 'C': (n, 0), 'D': (-n, 0)}[command] - winterm.cursor_adjust(x, y, on_stderr=self.on_stderr) - - - def convert_osc(self, text): - for match in self.ANSI_OSC_RE.finditer(text): - start, end = match.span() - text = text[:start] + text[end:] - paramstring, command = match.groups() - if command == BEL: - if paramstring.count(";") == 1: - params = paramstring.split(";") - # 0 - change title and icon (we will only change title) - # 1 - change icon (we don't support this) - # 2 - change title - if params[0] in '02': - winterm.set_title(params[1]) - return text - - - def flush(self): - self.wrapped.flush() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/initialise.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/initialise.py deleted file mode 100644 index d5fd4b7..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/initialise.py +++ /dev/null @@ -1,121 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -import atexit -import contextlib -import sys - -from .ansitowin32 import AnsiToWin32 - - -def _wipe_internal_state_for_tests(): - global orig_stdout, orig_stderr - orig_stdout = None - orig_stderr = None - - global wrapped_stdout, wrapped_stderr - wrapped_stdout = None - wrapped_stderr = None - - global atexit_done - atexit_done = False - - global fixed_windows_console - fixed_windows_console = False - - try: - # no-op if it wasn't registered - atexit.unregister(reset_all) - except AttributeError: - # python 2: no atexit.unregister. Oh well, we did our best. - pass - - -def reset_all(): - if AnsiToWin32 is not None: # Issue #74: objects might become None at exit - AnsiToWin32(orig_stdout).reset_all() - - -def init(autoreset=False, convert=None, strip=None, wrap=True): - - if not wrap and any([autoreset, convert, strip]): - raise ValueError('wrap=False conflicts with any other arg=True') - - global wrapped_stdout, wrapped_stderr - global orig_stdout, orig_stderr - - orig_stdout = sys.stdout - orig_stderr = sys.stderr - - if sys.stdout is None: - wrapped_stdout = None - else: - sys.stdout = wrapped_stdout = \ - wrap_stream(orig_stdout, convert, strip, autoreset, wrap) - if sys.stderr is None: - wrapped_stderr = None - else: - sys.stderr = wrapped_stderr = \ - wrap_stream(orig_stderr, convert, strip, autoreset, wrap) - - global atexit_done - if not atexit_done: - atexit.register(reset_all) - atexit_done = True - - -def deinit(): - if orig_stdout is not None: - sys.stdout = orig_stdout - if orig_stderr is not None: - sys.stderr = orig_stderr - - -def just_fix_windows_console(): - global fixed_windows_console - - if sys.platform != "win32": - return - if fixed_windows_console: - return - if wrapped_stdout is not None or wrapped_stderr is not None: - # Someone already ran init() and it did stuff, so we won't second-guess them - return - - # On newer versions of Windows, AnsiToWin32.__init__ will implicitly enable the - # native ANSI support in the console as a side-effect. We only need to actually - # replace sys.stdout/stderr if we're in the old-style conversion mode. - new_stdout = AnsiToWin32(sys.stdout, convert=None, strip=None, autoreset=False) - if new_stdout.convert: - sys.stdout = new_stdout - new_stderr = AnsiToWin32(sys.stderr, convert=None, strip=None, autoreset=False) - if new_stderr.convert: - sys.stderr = new_stderr - - fixed_windows_console = True - -@contextlib.contextmanager -def colorama_text(*args, **kwargs): - init(*args, **kwargs) - try: - yield - finally: - deinit() - - -def reinit(): - if wrapped_stdout is not None: - sys.stdout = wrapped_stdout - if wrapped_stderr is not None: - sys.stderr = wrapped_stderr - - -def wrap_stream(stream, convert, strip, autoreset, wrap): - if wrap: - wrapper = AnsiToWin32(stream, - convert=convert, strip=strip, autoreset=autoreset) - if wrapper.should_wrap(): - stream = wrapper.stream - return stream - - -# Use this for initial setup as well, to reduce code duplication -_wipe_internal_state_for_tests() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__init__.py deleted file mode 100644 index 8c5661e..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__init__.py +++ /dev/null @@ -1 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 4fcd12a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/ansi_test.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/ansi_test.cpython-312.pyc deleted file mode 100644 index 6f9d989..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/ansi_test.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/ansitowin32_test.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/ansitowin32_test.cpython-312.pyc deleted file mode 100644 index b5eef96..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/ansitowin32_test.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/initialise_test.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/initialise_test.cpython-312.pyc deleted file mode 100644 index 4ce6e5a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/initialise_test.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/isatty_test.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/isatty_test.cpython-312.pyc deleted file mode 100644 index 88bc735..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/isatty_test.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/utils.cpython-312.pyc deleted file mode 100644 index ab820db..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/utils.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/winterm_test.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/winterm_test.cpython-312.pyc deleted file mode 100644 index 14de2ae..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/__pycache__/winterm_test.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/ansi_test.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/ansi_test.py deleted file mode 100644 index 0a20c80..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/ansi_test.py +++ /dev/null @@ -1,76 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -import sys -from unittest import TestCase, main - -from ..ansi import Back, Fore, Style -from ..ansitowin32 import AnsiToWin32 - -stdout_orig = sys.stdout -stderr_orig = sys.stderr - - -class AnsiTest(TestCase): - - def setUp(self): - # sanity check: stdout should be a file or StringIO object. - # It will only be AnsiToWin32 if init() has previously wrapped it - self.assertNotEqual(type(sys.stdout), AnsiToWin32) - self.assertNotEqual(type(sys.stderr), AnsiToWin32) - - def tearDown(self): - sys.stdout = stdout_orig - sys.stderr = stderr_orig - - - def testForeAttributes(self): - self.assertEqual(Fore.BLACK, '\033[30m') - self.assertEqual(Fore.RED, '\033[31m') - self.assertEqual(Fore.GREEN, '\033[32m') - self.assertEqual(Fore.YELLOW, '\033[33m') - self.assertEqual(Fore.BLUE, '\033[34m') - self.assertEqual(Fore.MAGENTA, '\033[35m') - self.assertEqual(Fore.CYAN, '\033[36m') - self.assertEqual(Fore.WHITE, '\033[37m') - self.assertEqual(Fore.RESET, '\033[39m') - - # Check the light, extended versions. - self.assertEqual(Fore.LIGHTBLACK_EX, '\033[90m') - self.assertEqual(Fore.LIGHTRED_EX, '\033[91m') - self.assertEqual(Fore.LIGHTGREEN_EX, '\033[92m') - self.assertEqual(Fore.LIGHTYELLOW_EX, '\033[93m') - self.assertEqual(Fore.LIGHTBLUE_EX, '\033[94m') - self.assertEqual(Fore.LIGHTMAGENTA_EX, '\033[95m') - self.assertEqual(Fore.LIGHTCYAN_EX, '\033[96m') - self.assertEqual(Fore.LIGHTWHITE_EX, '\033[97m') - - - def testBackAttributes(self): - self.assertEqual(Back.BLACK, '\033[40m') - self.assertEqual(Back.RED, '\033[41m') - self.assertEqual(Back.GREEN, '\033[42m') - self.assertEqual(Back.YELLOW, '\033[43m') - self.assertEqual(Back.BLUE, '\033[44m') - self.assertEqual(Back.MAGENTA, '\033[45m') - self.assertEqual(Back.CYAN, '\033[46m') - self.assertEqual(Back.WHITE, '\033[47m') - self.assertEqual(Back.RESET, '\033[49m') - - # Check the light, extended versions. - self.assertEqual(Back.LIGHTBLACK_EX, '\033[100m') - self.assertEqual(Back.LIGHTRED_EX, '\033[101m') - self.assertEqual(Back.LIGHTGREEN_EX, '\033[102m') - self.assertEqual(Back.LIGHTYELLOW_EX, '\033[103m') - self.assertEqual(Back.LIGHTBLUE_EX, '\033[104m') - self.assertEqual(Back.LIGHTMAGENTA_EX, '\033[105m') - self.assertEqual(Back.LIGHTCYAN_EX, '\033[106m') - self.assertEqual(Back.LIGHTWHITE_EX, '\033[107m') - - - def testStyleAttributes(self): - self.assertEqual(Style.DIM, '\033[2m') - self.assertEqual(Style.NORMAL, '\033[22m') - self.assertEqual(Style.BRIGHT, '\033[1m') - - -if __name__ == '__main__': - main() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/ansitowin32_test.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/ansitowin32_test.py deleted file mode 100644 index 91ca551..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/ansitowin32_test.py +++ /dev/null @@ -1,294 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -from io import StringIO, TextIOWrapper -from unittest import TestCase, main -try: - from contextlib import ExitStack -except ImportError: - # python 2 - from contextlib2 import ExitStack - -try: - from unittest.mock import MagicMock, Mock, patch -except ImportError: - from mock import MagicMock, Mock, patch - -from ..ansitowin32 import AnsiToWin32, StreamWrapper -from ..win32 import ENABLE_VIRTUAL_TERMINAL_PROCESSING -from .utils import osname - - -class StreamWrapperTest(TestCase): - - def testIsAProxy(self): - mockStream = Mock() - wrapper = StreamWrapper(mockStream, None) - self.assertTrue( wrapper.random_attr is mockStream.random_attr ) - - def testDelegatesWrite(self): - mockStream = Mock() - mockConverter = Mock() - wrapper = StreamWrapper(mockStream, mockConverter) - wrapper.write('hello') - self.assertTrue(mockConverter.write.call_args, (('hello',), {})) - - def testDelegatesContext(self): - mockConverter = Mock() - s = StringIO() - with StreamWrapper(s, mockConverter) as fp: - fp.write(u'hello') - self.assertTrue(s.closed) - - def testProxyNoContextManager(self): - mockStream = MagicMock() - mockStream.__enter__.side_effect = AttributeError() - mockConverter = Mock() - with self.assertRaises(AttributeError) as excinfo: - with StreamWrapper(mockStream, mockConverter) as wrapper: - wrapper.write('hello') - - def test_closed_shouldnt_raise_on_closed_stream(self): - stream = StringIO() - stream.close() - wrapper = StreamWrapper(stream, None) - self.assertEqual(wrapper.closed, True) - - def test_closed_shouldnt_raise_on_detached_stream(self): - stream = TextIOWrapper(StringIO()) - stream.detach() - wrapper = StreamWrapper(stream, None) - self.assertEqual(wrapper.closed, True) - -class AnsiToWin32Test(TestCase): - - def testInit(self): - mockStdout = Mock() - auto = Mock() - stream = AnsiToWin32(mockStdout, autoreset=auto) - self.assertEqual(stream.wrapped, mockStdout) - self.assertEqual(stream.autoreset, auto) - - @patch('colorama.ansitowin32.winterm', None) - @patch('colorama.ansitowin32.winapi_test', lambda *_: True) - def testStripIsTrueOnWindows(self): - with osname('nt'): - mockStdout = Mock() - stream = AnsiToWin32(mockStdout) - self.assertTrue(stream.strip) - - def testStripIsFalseOffWindows(self): - with osname('posix'): - mockStdout = Mock(closed=False) - stream = AnsiToWin32(mockStdout) - self.assertFalse(stream.strip) - - def testWriteStripsAnsi(self): - mockStdout = Mock() - stream = AnsiToWin32(mockStdout) - stream.wrapped = Mock() - stream.write_and_convert = Mock() - stream.strip = True - - stream.write('abc') - - self.assertFalse(stream.wrapped.write.called) - self.assertEqual(stream.write_and_convert.call_args, (('abc',), {})) - - def testWriteDoesNotStripAnsi(self): - mockStdout = Mock() - stream = AnsiToWin32(mockStdout) - stream.wrapped = Mock() - stream.write_and_convert = Mock() - stream.strip = False - stream.convert = False - - stream.write('abc') - - self.assertFalse(stream.write_and_convert.called) - self.assertEqual(stream.wrapped.write.call_args, (('abc',), {})) - - def assert_autoresets(self, convert, autoreset=True): - stream = AnsiToWin32(Mock()) - stream.convert = convert - stream.reset_all = Mock() - stream.autoreset = autoreset - stream.winterm = Mock() - - stream.write('abc') - - self.assertEqual(stream.reset_all.called, autoreset) - - def testWriteAutoresets(self): - self.assert_autoresets(convert=True) - self.assert_autoresets(convert=False) - self.assert_autoresets(convert=True, autoreset=False) - self.assert_autoresets(convert=False, autoreset=False) - - def testWriteAndConvertWritesPlainText(self): - stream = AnsiToWin32(Mock()) - stream.write_and_convert( 'abc' ) - self.assertEqual( stream.wrapped.write.call_args, (('abc',), {}) ) - - def testWriteAndConvertStripsAllValidAnsi(self): - stream = AnsiToWin32(Mock()) - stream.call_win32 = Mock() - data = [ - 'abc\033[mdef', - 'abc\033[0mdef', - 'abc\033[2mdef', - 'abc\033[02mdef', - 'abc\033[002mdef', - 'abc\033[40mdef', - 'abc\033[040mdef', - 'abc\033[0;1mdef', - 'abc\033[40;50mdef', - 'abc\033[50;30;40mdef', - 'abc\033[Adef', - 'abc\033[0Gdef', - 'abc\033[1;20;128Hdef', - ] - for datum in data: - stream.wrapped.write.reset_mock() - stream.write_and_convert( datum ) - self.assertEqual( - [args[0] for args in stream.wrapped.write.call_args_list], - [ ('abc',), ('def',) ] - ) - - def testWriteAndConvertSkipsEmptySnippets(self): - stream = AnsiToWin32(Mock()) - stream.call_win32 = Mock() - stream.write_and_convert( '\033[40m\033[41m' ) - self.assertFalse( stream.wrapped.write.called ) - - def testWriteAndConvertCallsWin32WithParamsAndCommand(self): - stream = AnsiToWin32(Mock()) - stream.convert = True - stream.call_win32 = Mock() - stream.extract_params = Mock(return_value='params') - data = { - 'abc\033[adef': ('a', 'params'), - 'abc\033[;;bdef': ('b', 'params'), - 'abc\033[0cdef': ('c', 'params'), - 'abc\033[;;0;;Gdef': ('G', 'params'), - 'abc\033[1;20;128Hdef': ('H', 'params'), - } - for datum, expected in data.items(): - stream.call_win32.reset_mock() - stream.write_and_convert( datum ) - self.assertEqual( stream.call_win32.call_args[0], expected ) - - def test_reset_all_shouldnt_raise_on_closed_orig_stdout(self): - stream = StringIO() - converter = AnsiToWin32(stream) - stream.close() - - converter.reset_all() - - def test_wrap_shouldnt_raise_on_closed_orig_stdout(self): - stream = StringIO() - stream.close() - with \ - patch("colorama.ansitowin32.os.name", "nt"), \ - patch("colorama.ansitowin32.winapi_test", lambda: True): - converter = AnsiToWin32(stream) - self.assertTrue(converter.strip) - self.assertFalse(converter.convert) - - def test_wrap_shouldnt_raise_on_missing_closed_attr(self): - with \ - patch("colorama.ansitowin32.os.name", "nt"), \ - patch("colorama.ansitowin32.winapi_test", lambda: True): - converter = AnsiToWin32(object()) - self.assertTrue(converter.strip) - self.assertFalse(converter.convert) - - def testExtractParams(self): - stream = AnsiToWin32(Mock()) - data = { - '': (0,), - ';;': (0,), - '2': (2,), - ';;002;;': (2,), - '0;1': (0, 1), - ';;003;;456;;': (3, 456), - '11;22;33;44;55': (11, 22, 33, 44, 55), - } - for datum, expected in data.items(): - self.assertEqual(stream.extract_params('m', datum), expected) - - def testCallWin32UsesLookup(self): - listener = Mock() - stream = AnsiToWin32(listener) - stream.win32_calls = { - 1: (lambda *_, **__: listener(11),), - 2: (lambda *_, **__: listener(22),), - 3: (lambda *_, **__: listener(33),), - } - stream.call_win32('m', (3, 1, 99, 2)) - self.assertEqual( - [a[0][0] for a in listener.call_args_list], - [33, 11, 22] ) - - def test_osc_codes(self): - mockStdout = Mock() - stream = AnsiToWin32(mockStdout, convert=True) - with patch('colorama.ansitowin32.winterm') as winterm: - data = [ - '\033]0\x07', # missing arguments - '\033]0;foo\x08', # wrong OSC command - '\033]0;colorama_test_title\x07', # should work - '\033]1;colorama_test_title\x07', # wrong set command - '\033]2;colorama_test_title\x07', # should work - '\033]' + ';' * 64 + '\x08', # see issue #247 - ] - for code in data: - stream.write(code) - self.assertEqual(winterm.set_title.call_count, 2) - - def test_native_windows_ansi(self): - with ExitStack() as stack: - def p(a, b): - stack.enter_context(patch(a, b, create=True)) - # Pretend to be on Windows - p("colorama.ansitowin32.os.name", "nt") - p("colorama.ansitowin32.winapi_test", lambda: True) - p("colorama.win32.winapi_test", lambda: True) - p("colorama.winterm.win32.windll", "non-None") - p("colorama.winterm.get_osfhandle", lambda _: 1234) - - # Pretend that our mock stream has native ANSI support - p( - "colorama.winterm.win32.GetConsoleMode", - lambda _: ENABLE_VIRTUAL_TERMINAL_PROCESSING, - ) - SetConsoleMode = Mock() - p("colorama.winterm.win32.SetConsoleMode", SetConsoleMode) - - stdout = Mock() - stdout.closed = False - stdout.isatty.return_value = True - stdout.fileno.return_value = 1 - - # Our fake console says it has native vt support, so AnsiToWin32 should - # enable that support and do nothing else. - stream = AnsiToWin32(stdout) - SetConsoleMode.assert_called_with(1234, ENABLE_VIRTUAL_TERMINAL_PROCESSING) - self.assertFalse(stream.strip) - self.assertFalse(stream.convert) - self.assertFalse(stream.should_wrap()) - - # Now let's pretend we're on an old Windows console, that doesn't have - # native ANSI support. - p("colorama.winterm.win32.GetConsoleMode", lambda _: 0) - SetConsoleMode = Mock() - p("colorama.winterm.win32.SetConsoleMode", SetConsoleMode) - - stream = AnsiToWin32(stdout) - SetConsoleMode.assert_called_with(1234, ENABLE_VIRTUAL_TERMINAL_PROCESSING) - self.assertTrue(stream.strip) - self.assertTrue(stream.convert) - self.assertTrue(stream.should_wrap()) - - -if __name__ == '__main__': - main() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/initialise_test.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/initialise_test.py deleted file mode 100644 index 89f9b07..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/initialise_test.py +++ /dev/null @@ -1,189 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -import sys -from unittest import TestCase, main, skipUnless - -try: - from unittest.mock import patch, Mock -except ImportError: - from mock import patch, Mock - -from ..ansitowin32 import StreamWrapper -from ..initialise import init, just_fix_windows_console, _wipe_internal_state_for_tests -from .utils import osname, replace_by - -orig_stdout = sys.stdout -orig_stderr = sys.stderr - - -class InitTest(TestCase): - - @skipUnless(sys.stdout.isatty(), "sys.stdout is not a tty") - def setUp(self): - # sanity check - self.assertNotWrapped() - - def tearDown(self): - _wipe_internal_state_for_tests() - sys.stdout = orig_stdout - sys.stderr = orig_stderr - - def assertWrapped(self): - self.assertIsNot(sys.stdout, orig_stdout, 'stdout should be wrapped') - self.assertIsNot(sys.stderr, orig_stderr, 'stderr should be wrapped') - self.assertTrue(isinstance(sys.stdout, StreamWrapper), - 'bad stdout wrapper') - self.assertTrue(isinstance(sys.stderr, StreamWrapper), - 'bad stderr wrapper') - - def assertNotWrapped(self): - self.assertIs(sys.stdout, orig_stdout, 'stdout should not be wrapped') - self.assertIs(sys.stderr, orig_stderr, 'stderr should not be wrapped') - - @patch('colorama.initialise.reset_all') - @patch('colorama.ansitowin32.winapi_test', lambda *_: True) - @patch('colorama.ansitowin32.enable_vt_processing', lambda *_: False) - def testInitWrapsOnWindows(self, _): - with osname("nt"): - init() - self.assertWrapped() - - @patch('colorama.initialise.reset_all') - @patch('colorama.ansitowin32.winapi_test', lambda *_: False) - def testInitDoesntWrapOnEmulatedWindows(self, _): - with osname("nt"): - init() - self.assertNotWrapped() - - def testInitDoesntWrapOnNonWindows(self): - with osname("posix"): - init() - self.assertNotWrapped() - - def testInitDoesntWrapIfNone(self): - with replace_by(None): - init() - # We can't use assertNotWrapped here because replace_by(None) - # changes stdout/stderr already. - self.assertIsNone(sys.stdout) - self.assertIsNone(sys.stderr) - - def testInitAutoresetOnWrapsOnAllPlatforms(self): - with osname("posix"): - init(autoreset=True) - self.assertWrapped() - - def testInitWrapOffDoesntWrapOnWindows(self): - with osname("nt"): - init(wrap=False) - self.assertNotWrapped() - - def testInitWrapOffIncompatibleWithAutoresetOn(self): - self.assertRaises(ValueError, lambda: init(autoreset=True, wrap=False)) - - @patch('colorama.win32.SetConsoleTextAttribute') - @patch('colorama.initialise.AnsiToWin32') - def testAutoResetPassedOn(self, mockATW32, _): - with osname("nt"): - init(autoreset=True) - self.assertEqual(len(mockATW32.call_args_list), 2) - self.assertEqual(mockATW32.call_args_list[1][1]['autoreset'], True) - self.assertEqual(mockATW32.call_args_list[0][1]['autoreset'], True) - - @patch('colorama.initialise.AnsiToWin32') - def testAutoResetChangeable(self, mockATW32): - with osname("nt"): - init() - - init(autoreset=True) - self.assertEqual(len(mockATW32.call_args_list), 4) - self.assertEqual(mockATW32.call_args_list[2][1]['autoreset'], True) - self.assertEqual(mockATW32.call_args_list[3][1]['autoreset'], True) - - init() - self.assertEqual(len(mockATW32.call_args_list), 6) - self.assertEqual( - mockATW32.call_args_list[4][1]['autoreset'], False) - self.assertEqual( - mockATW32.call_args_list[5][1]['autoreset'], False) - - - @patch('colorama.initialise.atexit.register') - def testAtexitRegisteredOnlyOnce(self, mockRegister): - init() - self.assertTrue(mockRegister.called) - mockRegister.reset_mock() - init() - self.assertFalse(mockRegister.called) - - -class JustFixWindowsConsoleTest(TestCase): - def _reset(self): - _wipe_internal_state_for_tests() - sys.stdout = orig_stdout - sys.stderr = orig_stderr - - def tearDown(self): - self._reset() - - @patch("colorama.ansitowin32.winapi_test", lambda: True) - def testJustFixWindowsConsole(self): - if sys.platform != "win32": - # just_fix_windows_console should be a no-op - just_fix_windows_console() - self.assertIs(sys.stdout, orig_stdout) - self.assertIs(sys.stderr, orig_stderr) - else: - def fake_std(): - # Emulate stdout=not a tty, stderr=tty - # to check that we handle both cases correctly - stdout = Mock() - stdout.closed = False - stdout.isatty.return_value = False - stdout.fileno.return_value = 1 - sys.stdout = stdout - - stderr = Mock() - stderr.closed = False - stderr.isatty.return_value = True - stderr.fileno.return_value = 2 - sys.stderr = stderr - - for native_ansi in [False, True]: - with patch( - 'colorama.ansitowin32.enable_vt_processing', - lambda *_: native_ansi - ): - self._reset() - fake_std() - - # Regular single-call test - prev_stdout = sys.stdout - prev_stderr = sys.stderr - just_fix_windows_console() - self.assertIs(sys.stdout, prev_stdout) - if native_ansi: - self.assertIs(sys.stderr, prev_stderr) - else: - self.assertIsNot(sys.stderr, prev_stderr) - - # second call without resetting is always a no-op - prev_stdout = sys.stdout - prev_stderr = sys.stderr - just_fix_windows_console() - self.assertIs(sys.stdout, prev_stdout) - self.assertIs(sys.stderr, prev_stderr) - - self._reset() - fake_std() - - # If init() runs first, just_fix_windows_console should be a no-op - init() - prev_stdout = sys.stdout - prev_stderr = sys.stderr - just_fix_windows_console() - self.assertIs(prev_stdout, sys.stdout) - self.assertIs(prev_stderr, sys.stderr) - - -if __name__ == '__main__': - main() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/isatty_test.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/isatty_test.py deleted file mode 100644 index 0f84e4b..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/isatty_test.py +++ /dev/null @@ -1,57 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -import sys -from unittest import TestCase, main - -from ..ansitowin32 import StreamWrapper, AnsiToWin32 -from .utils import pycharm, replace_by, replace_original_by, StreamTTY, StreamNonTTY - - -def is_a_tty(stream): - return StreamWrapper(stream, None).isatty() - -class IsattyTest(TestCase): - - def test_TTY(self): - tty = StreamTTY() - self.assertTrue(is_a_tty(tty)) - with pycharm(): - self.assertTrue(is_a_tty(tty)) - - def test_nonTTY(self): - non_tty = StreamNonTTY() - self.assertFalse(is_a_tty(non_tty)) - with pycharm(): - self.assertFalse(is_a_tty(non_tty)) - - def test_withPycharm(self): - with pycharm(): - self.assertTrue(is_a_tty(sys.stderr)) - self.assertTrue(is_a_tty(sys.stdout)) - - def test_withPycharmTTYOverride(self): - tty = StreamTTY() - with pycharm(), replace_by(tty): - self.assertTrue(is_a_tty(tty)) - - def test_withPycharmNonTTYOverride(self): - non_tty = StreamNonTTY() - with pycharm(), replace_by(non_tty): - self.assertFalse(is_a_tty(non_tty)) - - def test_withPycharmNoneOverride(self): - with pycharm(): - with replace_by(None), replace_original_by(None): - self.assertFalse(is_a_tty(None)) - self.assertFalse(is_a_tty(StreamNonTTY())) - self.assertTrue(is_a_tty(StreamTTY())) - - def test_withPycharmStreamWrapped(self): - with pycharm(): - self.assertTrue(AnsiToWin32(StreamTTY()).stream.isatty()) - self.assertFalse(AnsiToWin32(StreamNonTTY()).stream.isatty()) - self.assertTrue(AnsiToWin32(sys.stdout).stream.isatty()) - self.assertTrue(AnsiToWin32(sys.stderr).stream.isatty()) - - -if __name__ == '__main__': - main() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/utils.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/utils.py deleted file mode 100644 index 472fafb..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/utils.py +++ /dev/null @@ -1,49 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -from contextlib import contextmanager -from io import StringIO -import sys -import os - - -class StreamTTY(StringIO): - def isatty(self): - return True - -class StreamNonTTY(StringIO): - def isatty(self): - return False - -@contextmanager -def osname(name): - orig = os.name - os.name = name - yield - os.name = orig - -@contextmanager -def replace_by(stream): - orig_stdout = sys.stdout - orig_stderr = sys.stderr - sys.stdout = stream - sys.stderr = stream - yield - sys.stdout = orig_stdout - sys.stderr = orig_stderr - -@contextmanager -def replace_original_by(stream): - orig_stdout = sys.__stdout__ - orig_stderr = sys.__stderr__ - sys.__stdout__ = stream - sys.__stderr__ = stream - yield - sys.__stdout__ = orig_stdout - sys.__stderr__ = orig_stderr - -@contextmanager -def pycharm(): - os.environ["PYCHARM_HOSTED"] = "1" - non_tty = StreamNonTTY() - with replace_by(non_tty), replace_original_by(non_tty): - yield - del os.environ["PYCHARM_HOSTED"] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/winterm_test.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/winterm_test.py deleted file mode 100644 index d0955f9..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/tests/winterm_test.py +++ /dev/null @@ -1,131 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -import sys -from unittest import TestCase, main, skipUnless - -try: - from unittest.mock import Mock, patch -except ImportError: - from mock import Mock, patch - -from ..winterm import WinColor, WinStyle, WinTerm - - -class WinTermTest(TestCase): - - @patch('colorama.winterm.win32') - def testInit(self, mockWin32): - mockAttr = Mock() - mockAttr.wAttributes = 7 + 6 * 16 + 8 - mockWin32.GetConsoleScreenBufferInfo.return_value = mockAttr - term = WinTerm() - self.assertEqual(term._fore, 7) - self.assertEqual(term._back, 6) - self.assertEqual(term._style, 8) - - @skipUnless(sys.platform.startswith("win"), "requires Windows") - def testGetAttrs(self): - term = WinTerm() - - term._fore = 0 - term._back = 0 - term._style = 0 - self.assertEqual(term.get_attrs(), 0) - - term._fore = WinColor.YELLOW - self.assertEqual(term.get_attrs(), WinColor.YELLOW) - - term._back = WinColor.MAGENTA - self.assertEqual( - term.get_attrs(), - WinColor.YELLOW + WinColor.MAGENTA * 16) - - term._style = WinStyle.BRIGHT - self.assertEqual( - term.get_attrs(), - WinColor.YELLOW + WinColor.MAGENTA * 16 + WinStyle.BRIGHT) - - @patch('colorama.winterm.win32') - def testResetAll(self, mockWin32): - mockAttr = Mock() - mockAttr.wAttributes = 1 + 2 * 16 + 8 - mockWin32.GetConsoleScreenBufferInfo.return_value = mockAttr - term = WinTerm() - - term.set_console = Mock() - term._fore = -1 - term._back = -1 - term._style = -1 - - term.reset_all() - - self.assertEqual(term._fore, 1) - self.assertEqual(term._back, 2) - self.assertEqual(term._style, 8) - self.assertEqual(term.set_console.called, True) - - @skipUnless(sys.platform.startswith("win"), "requires Windows") - def testFore(self): - term = WinTerm() - term.set_console = Mock() - term._fore = 0 - - term.fore(5) - - self.assertEqual(term._fore, 5) - self.assertEqual(term.set_console.called, True) - - @skipUnless(sys.platform.startswith("win"), "requires Windows") - def testBack(self): - term = WinTerm() - term.set_console = Mock() - term._back = 0 - - term.back(5) - - self.assertEqual(term._back, 5) - self.assertEqual(term.set_console.called, True) - - @skipUnless(sys.platform.startswith("win"), "requires Windows") - def testStyle(self): - term = WinTerm() - term.set_console = Mock() - term._style = 0 - - term.style(22) - - self.assertEqual(term._style, 22) - self.assertEqual(term.set_console.called, True) - - @patch('colorama.winterm.win32') - def testSetConsole(self, mockWin32): - mockAttr = Mock() - mockAttr.wAttributes = 0 - mockWin32.GetConsoleScreenBufferInfo.return_value = mockAttr - term = WinTerm() - term.windll = Mock() - - term.set_console() - - self.assertEqual( - mockWin32.SetConsoleTextAttribute.call_args, - ((mockWin32.STDOUT, term.get_attrs()), {}) - ) - - @patch('colorama.winterm.win32') - def testSetConsoleOnStderr(self, mockWin32): - mockAttr = Mock() - mockAttr.wAttributes = 0 - mockWin32.GetConsoleScreenBufferInfo.return_value = mockAttr - term = WinTerm() - term.windll = Mock() - - term.set_console(on_stderr=True) - - self.assertEqual( - mockWin32.SetConsoleTextAttribute.call_args, - ((mockWin32.STDERR, term.get_attrs()), {}) - ) - - -if __name__ == '__main__': - main() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/win32.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/win32.py deleted file mode 100644 index 841b0e2..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/win32.py +++ /dev/null @@ -1,180 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. - -# from winbase.h -STDOUT = -11 -STDERR = -12 - -ENABLE_VIRTUAL_TERMINAL_PROCESSING = 0x0004 - -try: - import ctypes - from ctypes import LibraryLoader - windll = LibraryLoader(ctypes.WinDLL) - from ctypes import wintypes -except (AttributeError, ImportError): - windll = None - SetConsoleTextAttribute = lambda *_: None - winapi_test = lambda *_: None -else: - from ctypes import byref, Structure, c_char, POINTER - - COORD = wintypes._COORD - - class CONSOLE_SCREEN_BUFFER_INFO(Structure): - """struct in wincon.h.""" - _fields_ = [ - ("dwSize", COORD), - ("dwCursorPosition", COORD), - ("wAttributes", wintypes.WORD), - ("srWindow", wintypes.SMALL_RECT), - ("dwMaximumWindowSize", COORD), - ] - def __str__(self): - return '(%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d)' % ( - self.dwSize.Y, self.dwSize.X - , self.dwCursorPosition.Y, self.dwCursorPosition.X - , self.wAttributes - , self.srWindow.Top, self.srWindow.Left, self.srWindow.Bottom, self.srWindow.Right - , self.dwMaximumWindowSize.Y, self.dwMaximumWindowSize.X - ) - - _GetStdHandle = windll.kernel32.GetStdHandle - _GetStdHandle.argtypes = [ - wintypes.DWORD, - ] - _GetStdHandle.restype = wintypes.HANDLE - - _GetConsoleScreenBufferInfo = windll.kernel32.GetConsoleScreenBufferInfo - _GetConsoleScreenBufferInfo.argtypes = [ - wintypes.HANDLE, - POINTER(CONSOLE_SCREEN_BUFFER_INFO), - ] - _GetConsoleScreenBufferInfo.restype = wintypes.BOOL - - _SetConsoleTextAttribute = windll.kernel32.SetConsoleTextAttribute - _SetConsoleTextAttribute.argtypes = [ - wintypes.HANDLE, - wintypes.WORD, - ] - _SetConsoleTextAttribute.restype = wintypes.BOOL - - _SetConsoleCursorPosition = windll.kernel32.SetConsoleCursorPosition - _SetConsoleCursorPosition.argtypes = [ - wintypes.HANDLE, - COORD, - ] - _SetConsoleCursorPosition.restype = wintypes.BOOL - - _FillConsoleOutputCharacterA = windll.kernel32.FillConsoleOutputCharacterA - _FillConsoleOutputCharacterA.argtypes = [ - wintypes.HANDLE, - c_char, - wintypes.DWORD, - COORD, - POINTER(wintypes.DWORD), - ] - _FillConsoleOutputCharacterA.restype = wintypes.BOOL - - _FillConsoleOutputAttribute = windll.kernel32.FillConsoleOutputAttribute - _FillConsoleOutputAttribute.argtypes = [ - wintypes.HANDLE, - wintypes.WORD, - wintypes.DWORD, - COORD, - POINTER(wintypes.DWORD), - ] - _FillConsoleOutputAttribute.restype = wintypes.BOOL - - _SetConsoleTitleW = windll.kernel32.SetConsoleTitleW - _SetConsoleTitleW.argtypes = [ - wintypes.LPCWSTR - ] - _SetConsoleTitleW.restype = wintypes.BOOL - - _GetConsoleMode = windll.kernel32.GetConsoleMode - _GetConsoleMode.argtypes = [ - wintypes.HANDLE, - POINTER(wintypes.DWORD) - ] - _GetConsoleMode.restype = wintypes.BOOL - - _SetConsoleMode = windll.kernel32.SetConsoleMode - _SetConsoleMode.argtypes = [ - wintypes.HANDLE, - wintypes.DWORD - ] - _SetConsoleMode.restype = wintypes.BOOL - - def _winapi_test(handle): - csbi = CONSOLE_SCREEN_BUFFER_INFO() - success = _GetConsoleScreenBufferInfo( - handle, byref(csbi)) - return bool(success) - - def winapi_test(): - return any(_winapi_test(h) for h in - (_GetStdHandle(STDOUT), _GetStdHandle(STDERR))) - - def GetConsoleScreenBufferInfo(stream_id=STDOUT): - handle = _GetStdHandle(stream_id) - csbi = CONSOLE_SCREEN_BUFFER_INFO() - success = _GetConsoleScreenBufferInfo( - handle, byref(csbi)) - return csbi - - def SetConsoleTextAttribute(stream_id, attrs): - handle = _GetStdHandle(stream_id) - return _SetConsoleTextAttribute(handle, attrs) - - def SetConsoleCursorPosition(stream_id, position, adjust=True): - position = COORD(*position) - # If the position is out of range, do nothing. - if position.Y <= 0 or position.X <= 0: - return - # Adjust for Windows' SetConsoleCursorPosition: - # 1. being 0-based, while ANSI is 1-based. - # 2. expecting (x,y), while ANSI uses (y,x). - adjusted_position = COORD(position.Y - 1, position.X - 1) - if adjust: - # Adjust for viewport's scroll position - sr = GetConsoleScreenBufferInfo(STDOUT).srWindow - adjusted_position.Y += sr.Top - adjusted_position.X += sr.Left - # Resume normal processing - handle = _GetStdHandle(stream_id) - return _SetConsoleCursorPosition(handle, adjusted_position) - - def FillConsoleOutputCharacter(stream_id, char, length, start): - handle = _GetStdHandle(stream_id) - char = c_char(char.encode()) - length = wintypes.DWORD(length) - num_written = wintypes.DWORD(0) - # Note that this is hard-coded for ANSI (vs wide) bytes. - success = _FillConsoleOutputCharacterA( - handle, char, length, start, byref(num_written)) - return num_written.value - - def FillConsoleOutputAttribute(stream_id, attr, length, start): - ''' FillConsoleOutputAttribute( hConsole, csbi.wAttributes, dwConSize, coordScreen, &cCharsWritten )''' - handle = _GetStdHandle(stream_id) - attribute = wintypes.WORD(attr) - length = wintypes.DWORD(length) - num_written = wintypes.DWORD(0) - # Note that this is hard-coded for ANSI (vs wide) bytes. - return _FillConsoleOutputAttribute( - handle, attribute, length, start, byref(num_written)) - - def SetConsoleTitle(title): - return _SetConsoleTitleW(title) - - def GetConsoleMode(handle): - mode = wintypes.DWORD() - success = _GetConsoleMode(handle, byref(mode)) - if not success: - raise ctypes.WinError() - return mode.value - - def SetConsoleMode(handle, mode): - success = _SetConsoleMode(handle, mode) - if not success: - raise ctypes.WinError() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/winterm.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/winterm.py deleted file mode 100644 index aad867e..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/colorama/winterm.py +++ /dev/null @@ -1,195 +0,0 @@ -# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. -try: - from msvcrt import get_osfhandle -except ImportError: - def get_osfhandle(_): - raise OSError("This isn't windows!") - - -from . import win32 - -# from wincon.h -class WinColor(object): - BLACK = 0 - BLUE = 1 - GREEN = 2 - CYAN = 3 - RED = 4 - MAGENTA = 5 - YELLOW = 6 - GREY = 7 - -# from wincon.h -class WinStyle(object): - NORMAL = 0x00 # dim text, dim background - BRIGHT = 0x08 # bright text, dim background - BRIGHT_BACKGROUND = 0x80 # dim text, bright background - -class WinTerm(object): - - def __init__(self): - self._default = win32.GetConsoleScreenBufferInfo(win32.STDOUT).wAttributes - self.set_attrs(self._default) - self._default_fore = self._fore - self._default_back = self._back - self._default_style = self._style - # In order to emulate LIGHT_EX in windows, we borrow the BRIGHT style. - # So that LIGHT_EX colors and BRIGHT style do not clobber each other, - # we track them separately, since LIGHT_EX is overwritten by Fore/Back - # and BRIGHT is overwritten by Style codes. - self._light = 0 - - def get_attrs(self): - return self._fore + self._back * 16 + (self._style | self._light) - - def set_attrs(self, value): - self._fore = value & 7 - self._back = (value >> 4) & 7 - self._style = value & (WinStyle.BRIGHT | WinStyle.BRIGHT_BACKGROUND) - - def reset_all(self, on_stderr=None): - self.set_attrs(self._default) - self.set_console(attrs=self._default) - self._light = 0 - - def fore(self, fore=None, light=False, on_stderr=False): - if fore is None: - fore = self._default_fore - self._fore = fore - # Emulate LIGHT_EX with BRIGHT Style - if light: - self._light |= WinStyle.BRIGHT - else: - self._light &= ~WinStyle.BRIGHT - self.set_console(on_stderr=on_stderr) - - def back(self, back=None, light=False, on_stderr=False): - if back is None: - back = self._default_back - self._back = back - # Emulate LIGHT_EX with BRIGHT_BACKGROUND Style - if light: - self._light |= WinStyle.BRIGHT_BACKGROUND - else: - self._light &= ~WinStyle.BRIGHT_BACKGROUND - self.set_console(on_stderr=on_stderr) - - def style(self, style=None, on_stderr=False): - if style is None: - style = self._default_style - self._style = style - self.set_console(on_stderr=on_stderr) - - def set_console(self, attrs=None, on_stderr=False): - if attrs is None: - attrs = self.get_attrs() - handle = win32.STDOUT - if on_stderr: - handle = win32.STDERR - win32.SetConsoleTextAttribute(handle, attrs) - - def get_position(self, handle): - position = win32.GetConsoleScreenBufferInfo(handle).dwCursorPosition - # Because Windows coordinates are 0-based, - # and win32.SetConsoleCursorPosition expects 1-based. - position.X += 1 - position.Y += 1 - return position - - def set_cursor_position(self, position=None, on_stderr=False): - if position is None: - # I'm not currently tracking the position, so there is no default. - # position = self.get_position() - return - handle = win32.STDOUT - if on_stderr: - handle = win32.STDERR - win32.SetConsoleCursorPosition(handle, position) - - def cursor_adjust(self, x, y, on_stderr=False): - handle = win32.STDOUT - if on_stderr: - handle = win32.STDERR - position = self.get_position(handle) - adjusted_position = (position.Y + y, position.X + x) - win32.SetConsoleCursorPosition(handle, adjusted_position, adjust=False) - - def erase_screen(self, mode=0, on_stderr=False): - # 0 should clear from the cursor to the end of the screen. - # 1 should clear from the cursor to the beginning of the screen. - # 2 should clear the entire screen, and move cursor to (1,1) - handle = win32.STDOUT - if on_stderr: - handle = win32.STDERR - csbi = win32.GetConsoleScreenBufferInfo(handle) - # get the number of character cells in the current buffer - cells_in_screen = csbi.dwSize.X * csbi.dwSize.Y - # get number of character cells before current cursor position - cells_before_cursor = csbi.dwSize.X * csbi.dwCursorPosition.Y + csbi.dwCursorPosition.X - if mode == 0: - from_coord = csbi.dwCursorPosition - cells_to_erase = cells_in_screen - cells_before_cursor - elif mode == 1: - from_coord = win32.COORD(0, 0) - cells_to_erase = cells_before_cursor - elif mode == 2: - from_coord = win32.COORD(0, 0) - cells_to_erase = cells_in_screen - else: - # invalid mode - return - # fill the entire screen with blanks - win32.FillConsoleOutputCharacter(handle, ' ', cells_to_erase, from_coord) - # now set the buffer's attributes accordingly - win32.FillConsoleOutputAttribute(handle, self.get_attrs(), cells_to_erase, from_coord) - if mode == 2: - # put the cursor where needed - win32.SetConsoleCursorPosition(handle, (1, 1)) - - def erase_line(self, mode=0, on_stderr=False): - # 0 should clear from the cursor to the end of the line. - # 1 should clear from the cursor to the beginning of the line. - # 2 should clear the entire line. - handle = win32.STDOUT - if on_stderr: - handle = win32.STDERR - csbi = win32.GetConsoleScreenBufferInfo(handle) - if mode == 0: - from_coord = csbi.dwCursorPosition - cells_to_erase = csbi.dwSize.X - csbi.dwCursorPosition.X - elif mode == 1: - from_coord = win32.COORD(0, csbi.dwCursorPosition.Y) - cells_to_erase = csbi.dwCursorPosition.X - elif mode == 2: - from_coord = win32.COORD(0, csbi.dwCursorPosition.Y) - cells_to_erase = csbi.dwSize.X - else: - # invalid mode - return - # fill the entire screen with blanks - win32.FillConsoleOutputCharacter(handle, ' ', cells_to_erase, from_coord) - # now set the buffer's attributes accordingly - win32.FillConsoleOutputAttribute(handle, self.get_attrs(), cells_to_erase, from_coord) - - def set_title(self, title): - win32.SetConsoleTitle(title) - - -def enable_vt_processing(fd): - if win32.windll is None or not win32.winapi_test(): - return False - - try: - handle = get_osfhandle(fd) - mode = win32.GetConsoleMode(handle) - win32.SetConsoleMode( - handle, - mode | win32.ENABLE_VIRTUAL_TERMINAL_PROCESSING, - ) - - mode = win32.GetConsoleMode(handle) - if mode & win32.ENABLE_VIRTUAL_TERMINAL_PROCESSING: - return True - # Can get TypeError in testsuite where 'fd' is a Mock() - except (OSError, TypeError): - return False diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__init__.py index e999438..bf0d6c6 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__init__.py @@ -6,7 +6,7 @@ # import logging -__version__ = '0.3.8' +__version__ = '0.3.9' class DistlibException(Exception): diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/__init__.cpython-312.pyc index c10daae..a6b8942 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/compat.cpython-312.pyc index 3adad8b..9dc5389 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/compat.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/compat.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/database.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/database.cpython-312.pyc index 25cecd3..5726526 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/database.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/database.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/index.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/index.cpython-312.pyc index 72bf091..d3b2fbc 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/index.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/index.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/locators.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/locators.cpython-312.pyc index 18ff207..91fd84e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/locators.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/locators.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/manifest.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/manifest.cpython-312.pyc index 7bdb03f..6dea4ed 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/manifest.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/manifest.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/markers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/markers.cpython-312.pyc index c13f05b..55b14a5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/markers.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/markers.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/metadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/metadata.cpython-312.pyc index bdcaafd..29bde54 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/metadata.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/metadata.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/resources.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/resources.cpython-312.pyc index ce42a75..3967102 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/resources.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/resources.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/scripts.cpython-312.pyc index 17b2610..dcd9b73 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/scripts.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/scripts.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/util.cpython-312.pyc index 3359dc2..266af60 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/util.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/util.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/version.cpython-312.pyc index b407331..9b72935 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/version.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/version.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/wheel.cpython-312.pyc index f763c3a..1a892eb 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/wheel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/__pycache__/wheel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/compat.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/compat.py index e93dc27..ca561dd 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/compat.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/compat.py @@ -217,8 +217,7 @@ except ImportError: # pragma: no cover # Additionally check that `file` is not a directory, as on Windows # directories pass the os.access check. def _access_check(fn, mode): - return (os.path.exists(fn) and os.access(fn, mode) - and not os.path.isdir(fn)) + return (os.path.exists(fn) and os.access(fn, mode) and not os.path.isdir(fn)) # If we're given a path with a directory part, look it up directly rather # than referring to PATH directories. This includes checking relative to the diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/database.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/database.py index eb3765f..c0f896a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/database.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/database.py @@ -20,14 +20,12 @@ import zipimport from . import DistlibException, resources from .compat import StringIO from .version import get_scheme, UnsupportedVersionError -from .metadata import (Metadata, METADATA_FILENAME, WHEEL_METADATA_FILENAME, - LEGACY_METADATA_FILENAME) -from .util import (parse_requirement, cached_property, parse_name_and_version, - read_exports, write_exports, CSVReader, CSVWriter) +from .metadata import (Metadata, METADATA_FILENAME, WHEEL_METADATA_FILENAME, LEGACY_METADATA_FILENAME) +from .util import (parse_requirement, cached_property, parse_name_and_version, read_exports, write_exports, CSVReader, + CSVWriter) __all__ = [ - 'Distribution', 'BaseInstalledDistribution', 'InstalledDistribution', - 'EggInfoDistribution', 'DistributionPath' + 'Distribution', 'BaseInstalledDistribution', 'InstalledDistribution', 'EggInfoDistribution', 'DistributionPath' ] logger = logging.getLogger(__name__) @@ -35,8 +33,7 @@ logger = logging.getLogger(__name__) EXPORTS_FILENAME = 'pydist-exports.json' COMMANDS_FILENAME = 'pydist-commands.json' -DIST_FILES = ('INSTALLER', METADATA_FILENAME, 'RECORD', 'REQUESTED', - 'RESOURCES', EXPORTS_FILENAME, 'SHARED') +DIST_FILES = ('INSTALLER', METADATA_FILENAME, 'RECORD', 'REQUESTED', 'RESOURCES', EXPORTS_FILENAME, 'SHARED') DISTINFO_EXT = '.dist-info' @@ -134,13 +131,9 @@ class DistributionPath(object): continue try: if self._include_dist and entry.endswith(DISTINFO_EXT): - possible_filenames = [ - METADATA_FILENAME, WHEEL_METADATA_FILENAME, - LEGACY_METADATA_FILENAME - ] + possible_filenames = [METADATA_FILENAME, WHEEL_METADATA_FILENAME, LEGACY_METADATA_FILENAME] for metadata_filename in possible_filenames: - metadata_path = posixpath.join( - entry, metadata_filename) + metadata_path = posixpath.join(entry, metadata_filename) pydist = finder.find(metadata_path) if pydist: break @@ -148,15 +141,11 @@ class DistributionPath(object): continue with contextlib.closing(pydist.as_stream()) as stream: - metadata = Metadata(fileobj=stream, - scheme='legacy') + metadata = Metadata(fileobj=stream, scheme='legacy') logger.debug('Found %s', r.path) seen.add(r.path) - yield new_dist_class(r.path, - metadata=metadata, - env=self) - elif self._include_egg and entry.endswith( - ('.egg-info', '.egg')): + yield new_dist_class(r.path, metadata=metadata, env=self) + elif self._include_egg and entry.endswith(('.egg-info', '.egg')): logger.debug('Found %s', r.path) seen.add(r.path) yield old_dist_class(r.path, self) @@ -274,8 +263,7 @@ class DistributionPath(object): try: matcher = self._scheme.matcher('%s (%s)' % (name, version)) except ValueError: - raise DistlibException('invalid name or version: %r, %r' % - (name, version)) + raise DistlibException('invalid name or version: %r, %r' % (name, version)) for dist in self.get_distributions(): # We hit a problem on Travis where enum34 was installed and doesn't @@ -390,10 +378,8 @@ class Distribution(object): def _get_requirements(self, req_attr): md = self.metadata reqts = getattr(md, req_attr) - logger.debug('%s: got requirements %r from metadata: %r', self.name, - req_attr, reqts) - return set( - md.get_requirements(reqts, extras=self.extras, env=self.context)) + logger.debug('%s: got requirements %r from metadata: %r', self.name, req_attr, reqts) + return set(md.get_requirements(reqts, extras=self.extras, env=self.context)) @property def run_requires(self): @@ -469,8 +455,7 @@ class Distribution(object): if type(other) is not type(self): result = False else: - result = (self.name == other.name and self.version == other.version - and self.source_url == other.source_url) + result = (self.name == other.name and self.version == other.version and self.source_url == other.source_url) return result def __hash__(self): @@ -561,8 +546,7 @@ class InstalledDistribution(BaseInstalledDistribution): if r is None: r = finder.find(LEGACY_METADATA_FILENAME) if r is None: - raise ValueError('no %s found in %s' % - (METADATA_FILENAME, path)) + raise ValueError('no %s found in %s' % (METADATA_FILENAME, path)) with contextlib.closing(r.as_stream()) as stream: metadata = Metadata(fileobj=stream, scheme='legacy') @@ -580,8 +564,7 @@ class InstalledDistribution(BaseInstalledDistribution): self.modules = data.splitlines() def __repr__(self): - return '' % ( - self.name, self.version, self.path) + return '' % (self.name, self.version, self.path) def __str__(self): return "%s %s" % (self.name, self.version) @@ -703,8 +686,7 @@ class InstalledDistribution(BaseInstalledDistribution): size = '%d' % os.path.getsize(path) with open(path, 'rb') as fp: hash_value = self.get_hash(fp.read()) - if path.startswith(base) or (base_under_prefix - and path.startswith(prefix)): + if path.startswith(base) or (base_under_prefix and path.startswith(prefix)): path = os.path.relpath(path, base) writer.writerow((path, hash_value, size)) @@ -746,8 +728,7 @@ class InstalledDistribution(BaseInstalledDistribution): with open(path, 'rb') as f: actual_hash = self.get_hash(f.read(), hasher) if actual_hash != hash_value: - mismatches.append( - (path, 'hash', hash_value, actual_hash)) + mismatches.append((path, 'hash', hash_value, actual_hash)) return mismatches @cached_property @@ -829,9 +810,8 @@ class InstalledDistribution(BaseInstalledDistribution): # it's an absolute path? distinfo_dirname, path = path.split(os.sep)[-2:] if distinfo_dirname != self.path.split(os.sep)[-1]: - raise DistlibException( - 'dist-info file %r does not belong to the %r %s ' - 'distribution' % (path, self.name, self.version)) + raise DistlibException('dist-info file %r does not belong to the %r %s ' + 'distribution' % (path, self.name, self.version)) # The file must be relative if path not in DIST_FILES: @@ -857,8 +837,7 @@ class InstalledDistribution(BaseInstalledDistribution): yield path def __eq__(self, other): - return (isinstance(other, InstalledDistribution) - and self.path == other.path) + return (isinstance(other, InstalledDistribution) and self.path == other.path) # See http://docs.python.org/reference/datamodel#object.__hash__ __hash__ = object.__hash__ @@ -911,8 +890,7 @@ class EggInfoDistribution(BaseInstalledDistribution): if not line: # pragma: no cover continue if line.startswith('['): # pragma: no cover - logger.warning( - 'Unexpected line: quitting requirement scan: %r', line) + logger.warning('Unexpected line: quitting requirement scan: %r', line) break r = parse_requirement(line) if not r: # pragma: no cover @@ -954,13 +932,11 @@ class EggInfoDistribution(BaseInstalledDistribution): else: # FIXME handle the case where zipfile is not available zipf = zipimport.zipimporter(path) - fileobj = StringIO( - zipf.get_data('EGG-INFO/PKG-INFO').decode('utf8')) + fileobj = StringIO(zipf.get_data('EGG-INFO/PKG-INFO').decode('utf8')) metadata = Metadata(fileobj=fileobj, scheme='legacy') try: data = zipf.get_data('EGG-INFO/requires.txt') - tl_data = zipf.get_data('EGG-INFO/top_level.txt').decode( - 'utf-8') + tl_data = zipf.get_data('EGG-INFO/top_level.txt').decode('utf-8') requires = parse_requires_data(data.decode('utf-8')) except IOError: requires = None @@ -990,8 +966,7 @@ class EggInfoDistribution(BaseInstalledDistribution): return metadata def __repr__(self): - return '' % (self.name, self.version, - self.path) + return '' % (self.name, self.version, self.path) def __str__(self): return "%s %s" % (self.name, self.version) @@ -1083,8 +1058,7 @@ class EggInfoDistribution(BaseInstalledDistribution): yield line def __eq__(self, other): - return (isinstance(other, EggInfoDistribution) - and self.path == other.path) + return (isinstance(other, EggInfoDistribution) and self.path == other.path) # See http://docs.python.org/reference/datamodel#object.__hash__ __hash__ = object.__hash__ @@ -1184,8 +1158,7 @@ class DependencyGraph(object): disconnected.append(dist) for other, label in adjs: if label is not None: - f.write('"%s" -> "%s" [label="%s"]\n' % - (dist.name, other.name, label)) + f.write('"%s" -> "%s" [label="%s"]\n' % (dist.name, other.name, label)) else: f.write('"%s" -> "%s"\n' % (dist.name, other.name)) if not skip_disconnected and len(disconnected) > 0: @@ -1225,8 +1198,7 @@ class DependencyGraph(object): # Remove from the adjacency list of others for k, v in alist.items(): alist[k] = [(d, r) for d, r in v if d not in to_remove] - logger.debug('Moving to result: %s', - ['%s (%s)' % (d.name, d.version) for d in to_remove]) + logger.debug('Moving to result: %s', ['%s (%s)' % (d.name, d.version) for d in to_remove]) result.extend(to_remove) return result, list(alist.keys()) @@ -1261,15 +1233,13 @@ def make_graph(dists, scheme='default'): # now make the edges for dist in dists: - requires = (dist.run_requires | dist.meta_requires - | dist.build_requires | dist.dev_requires) + requires = (dist.run_requires | dist.meta_requires | dist.build_requires | dist.dev_requires) for req in requires: try: matcher = scheme.matcher(req) except UnsupportedVersionError: # XXX compat-mode if cannot read the version - logger.warning('could not read version %r - using name only', - req) + logger.warning('could not read version %r - using name only', req) name = req.split()[0] matcher = scheme.matcher(name) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/locators.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/locators.py index f9f0788..222c1bf 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/locators.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/locators.py @@ -19,15 +19,12 @@ except ImportError: # pragma: no cover import zlib from . import DistlibException -from .compat import (urljoin, urlparse, urlunparse, url2pathname, pathname2url, - queue, quote, unescape, build_opener, - HTTPRedirectHandler as BaseRedirectHandler, text_type, - Request, HTTPError, URLError) +from .compat import (urljoin, urlparse, urlunparse, url2pathname, pathname2url, queue, quote, unescape, build_opener, + HTTPRedirectHandler as BaseRedirectHandler, text_type, Request, HTTPError, URLError) from .database import Distribution, DistributionPath, make_dist from .metadata import Metadata, MetadataInvalidError -from .util import (cached_property, ensure_slash, split_filename, get_project_data, - parse_requirement, parse_name_and_version, ServerProxy, - normalize_name) +from .util import (cached_property, ensure_slash, split_filename, get_project_data, parse_requirement, + parse_name_and_version, ServerProxy, normalize_name) from .version import get_scheme, UnsupportedVersionError from .wheel import Wheel, is_compatible @@ -58,6 +55,7 @@ class RedirectHandler(BaseRedirectHandler): """ A class to work around a bug in some Python 3.2.x releases. """ + # There's a bug in the base version for some 3.2.x # (e.g. 3.2.2 on Ubuntu Oneiric). If a Location header # returns e.g. /abc, it bails because it says the scheme '' @@ -80,8 +78,7 @@ class RedirectHandler(BaseRedirectHandler): headers.replace_header(key, newurl) else: headers[key] = newurl - return BaseRedirectHandler.http_error_302(self, req, fp, code, msg, - headers) + return BaseRedirectHandler.http_error_302(self, req, fp, code, msg, headers) http_error_301 = http_error_303 = http_error_307 = http_error_302 @@ -92,7 +89,7 @@ class Locator(object): """ source_extensions = ('.tar.gz', '.tar.bz2', '.tar', '.zip', '.tgz', '.tbz') binary_extensions = ('.egg', '.exe', '.whl') - excluded_extensions = ('.pdf',) + excluded_extensions = ('.pdf', ) # A list of tags indicating which wheels you want to match. The default # value of None matches against the tags compatible with the running @@ -100,7 +97,7 @@ class Locator(object): # instance to a list of tuples (pyver, abi, arch) which you want to match. wheel_tags = None - downloadable_extensions = source_extensions + ('.whl',) + downloadable_extensions = source_extensions + ('.whl', ) def __init__(self, scheme='default'): """ @@ -200,8 +197,7 @@ class Locator(object): is_downloadable = basename.endswith(self.downloadable_extensions) if is_wheel: compatible = is_compatible(Wheel(basename), self.wheel_tags) - return (t.scheme == 'https', 'pypi.org' in t.netloc, - is_downloadable, is_wheel, compatible, basename) + return (t.scheme == 'https', 'pypi.org' in t.netloc, is_downloadable, is_wheel, compatible, basename) def prefer_url(self, url1, url2): """ @@ -239,14 +235,14 @@ class Locator(object): If it is, a dictionary is returned with keys "name", "version", "filename" and "url"; otherwise, None is returned. """ + def same_project(name1, name2): return normalize_name(name1) == normalize_name(name2) result = None scheme, netloc, path, params, query, frag = urlparse(url) if frag.lower().startswith('egg='): # pragma: no cover - logger.debug('%s: version hint in fragment: %r', - project_name, frag) + logger.debug('%s: version hint in fragment: %r', project_name, frag) m = HASHER_HASH.match(frag) if m: algo, digest = m.groups() @@ -270,10 +266,8 @@ class Locator(object): 'name': wheel.name, 'version': wheel.version, 'filename': wheel.filename, - 'url': urlunparse((scheme, netloc, origpath, - params, query, '')), - 'python-version': ', '.join( - ['.'.join(list(v[2:])) for v in wheel.pyver]), + 'url': urlunparse((scheme, netloc, origpath, params, query, '')), + 'python-version': ', '.join(['.'.join(list(v[2:])) for v in wheel.pyver]), } except Exception: # pragma: no cover logger.warning('invalid path for wheel: %s', path) @@ -294,8 +288,7 @@ class Locator(object): 'name': name, 'version': version, 'filename': filename, - 'url': urlunparse((scheme, netloc, origpath, - params, query, '')), + 'url': urlunparse((scheme, netloc, origpath, params, query, '')), } if pyver: # pragma: no cover result['python-version'] = pyver @@ -371,7 +364,7 @@ class Locator(object): self.matcher = matcher = scheme.matcher(r.requirement) logger.debug('matcher: %s (%s)', matcher, type(matcher).__name__) versions = self.get_project(r.name) - if len(versions) > 2: # urls and digests keys are present + if len(versions) > 2: # urls and digests keys are present # sometimes, versions are invalid slist = [] vcls = matcher.version_class @@ -412,6 +405,7 @@ class PyPIRPCLocator(Locator): This locator uses XML-RPC to locate distributions. It therefore cannot be used with simple mirrors (that only mirror file content). """ + def __init__(self, url, **kwargs): """ Initialise an instance. @@ -461,6 +455,7 @@ class PyPIJSONLocator(Locator): This locator uses PyPI's JSON interface. It's very limited in functionality and probably not worth using. """ + def __init__(self, url, **kwargs): super(PyPIJSONLocator, self).__init__(**kwargs) self.base_url = ensure_slash(url) @@ -498,7 +493,7 @@ class PyPIJSONLocator(Locator): # Now get other releases for version, infos in d['releases'].items(): if version == md.version: - continue # already done + continue # already done omd = Metadata(scheme=self.scheme) omd.name = md.name omd.version = version @@ -511,6 +506,8 @@ class PyPIJSONLocator(Locator): odist.digests[url] = self._get_digest(info) result['urls'].setdefault(version, set()).add(url) result['digests'][url] = self._get_digest(info) + + # for info in urls: # md.source_url = info['url'] # dist.digest = self._get_digest(info) @@ -534,7 +531,8 @@ class Page(object): # or immediately followed by a "rel" attribute. The attribute values can be # declared with double quotes, single quotes or no quotes - which leads to # the length of the expression. - _href = re.compile(""" + _href = re.compile( + """ (rel\\s*=\\s*(?:"(?P[^"]*)"|'(?P[^']*)'|(?P[^>\\s\n]*))\\s+)? href\\s*=\\s*(?:"(?P[^"]*)"|'(?P[^']*)'|(?P[^>\\s\n]*)) (\\s+rel\\s*=\\s*(?:"(?P[^"]*)"|'(?P[^']*)'|(?P[^>\\s\n]*)))? @@ -561,17 +559,16 @@ href\\s*=\\s*(?:"(?P[^"]*)"|'(?P[^']*)'|(?P[^>\\s\n]*)) about their "rel" attribute, for determining which ones to treat as downloads and which ones to queue for further scraping. """ + def clean(url): "Tidy up an URL." scheme, netloc, path, params, query, frag = urlparse(url) - return urlunparse((scheme, netloc, quote(path), - params, query, frag)) + return urlunparse((scheme, netloc, quote(path), params, query, frag)) result = set() for match in self._href.finditer(self.data): d = match.groupdict('') - rel = (d['rel1'] or d['rel2'] or d['rel3'] or - d['rel4'] or d['rel5'] or d['rel6']) + rel = (d['rel1'] or d['rel2'] or d['rel3'] or d['rel4'] or d['rel5'] or d['rel6']) url = d['url1'] or d['url2'] or d['url3'] url = urljoin(self.base_url, url) url = unescape(url) @@ -645,7 +642,7 @@ class SimpleScrapingLocator(Locator): # Note that you need two loops, since you can't say which # thread will get each sentinel for t in self._threads: - self._to_fetch.put(None) # sentinel + self._to_fetch.put(None) # sentinel for t in self._threads: t.join() self._threads = [] @@ -693,7 +690,7 @@ class SimpleScrapingLocator(Locator): info = self.convert_url_to_download_info(url, self.project_name) logger.debug('process_download: %s -> %s', url, info) if info: - with self._lock: # needed because self.result is shared + with self._lock: # needed because self.result is shared self._update_version_data(self.result, info) return info @@ -703,8 +700,7 @@ class SimpleScrapingLocator(Locator): particular "rel" attribute should be queued for scraping. """ scheme, netloc, path, _, _, _ = urlparse(link) - if path.endswith(self.source_extensions + self.binary_extensions + - self.excluded_extensions): + if path.endswith(self.source_extensions + self.binary_extensions + self.excluded_extensions): result = False elif self.skip_externals and not link.startswith(self.base_url): result = False @@ -722,8 +718,7 @@ class SimpleScrapingLocator(Locator): result = False else: result = True - logger.debug('should_queue: %s (%s) from %s -> %s', link, rel, - referrer, result) + logger.debug('should_queue: %s (%s) from %s -> %s', link, rel, referrer, result) return result def _fetch(self): @@ -738,14 +733,13 @@ class SimpleScrapingLocator(Locator): try: if url: page = self.get_page(url) - if page is None: # e.g. after an error + if page is None: # e.g. after an error continue for link, rel in page.links: if link not in self._seen: try: self._seen.add(link) - if (not self._process_download(link) and - self._should_queue(link, url, rel)): + if (not self._process_download(link) and self._should_queue(link, url, rel)): logger.debug('Queueing %s from %s', link, url) self._to_fetch.put(link) except MetadataInvalidError: # e.g. invalid versions @@ -793,7 +787,7 @@ class SimpleScrapingLocator(Locator): data = resp.read() encoding = headers.get('Content-Encoding') if encoding: - decoder = self.decoders[encoding] # fail if not found + decoder = self.decoders[encoding] # fail if not found data = decoder(data) encoding = 'utf-8' m = CHARSET.search(content_type) @@ -802,7 +796,7 @@ class SimpleScrapingLocator(Locator): try: data = data.decode(encoding) except UnicodeError: # pragma: no cover - data = data.decode('latin-1') # fallback + data = data.decode('latin-1') # fallback result = Page(data, final_url) self._page_cache[final_url] = result except HTTPError as e: @@ -815,7 +809,7 @@ class SimpleScrapingLocator(Locator): except Exception as e: # pragma: no cover logger.exception('Fetch failed: %s: %s', url, e) finally: - self._page_cache[url] = result # even if None (failure) + self._page_cache[url] = result # even if None (failure) return result _distname_re = re.compile(']*>([^<]+)<') @@ -869,9 +863,7 @@ class DirectoryLocator(Locator): for fn in files: if self.should_include(fn, root): fn = os.path.join(root, fn) - url = urlunparse(('file', '', - pathname2url(os.path.abspath(fn)), - '', '', '')) + url = urlunparse(('file', '', pathname2url(os.path.abspath(fn)), '', '', '')) info = self.convert_url_to_download_info(url, name) if info: self._update_version_data(result, info) @@ -888,9 +880,7 @@ class DirectoryLocator(Locator): for fn in files: if self.should_include(fn, root): fn = os.path.join(root, fn) - url = urlunparse(('file', '', - pathname2url(os.path.abspath(fn)), - '', '', '')) + url = urlunparse(('file', '', pathname2url(os.path.abspath(fn)), '', '', '')) info = self.convert_url_to_download_info(url, None) if info: result.add(info['name']) @@ -906,6 +896,7 @@ class JSONLocator(Locator): require archive downloads before dependencies can be determined! As you might imagine, that can be slow. """ + def get_distribution_names(self): """ Return all the distribution names known to this locator. @@ -922,9 +913,9 @@ class JSONLocator(Locator): # We don't store summary in project metadata as it makes # the data bigger for no benefit during dependency # resolution - dist = make_dist(data['name'], info['version'], - summary=data.get('summary', - 'Placeholder for summary'), + dist = make_dist(data['name'], + info['version'], + summary=data.get('summary', 'Placeholder for summary'), scheme=self.scheme) md = dist.metadata md.source_url = info['url'] @@ -943,6 +934,7 @@ class DistPathLocator(Locator): This locator finds installed distributions in a path. It can be useful for adding to an :class:`AggregatingLocator`. """ + def __init__(self, distpath, **kwargs): """ Initialise an instance. @@ -960,8 +952,12 @@ class DistPathLocator(Locator): else: result = { dist.version: dist, - 'urls': {dist.version: set([dist.source_url])}, - 'digests': {dist.version: set([None])} + 'urls': { + dist.version: set([dist.source_url]) + }, + 'digests': { + dist.version: set([None]) + } } return result @@ -970,6 +966,7 @@ class AggregatingLocator(Locator): """ This class allows you to chain and/or merge a list of locators. """ + def __init__(self, *locators, **kwargs): """ Initialise an instance. @@ -1058,10 +1055,9 @@ class AggregatingLocator(Locator): # We use a legacy scheme simply because most of the dists on PyPI use legacy # versions which don't conform to PEP 440. default_locator = AggregatingLocator( - # JSONLocator(), # don't use as PEP 426 is withdrawn - SimpleScrapingLocator('https://pypi.org/simple/', - timeout=3.0), - scheme='legacy') + # JSONLocator(), # don't use as PEP 426 is withdrawn + SimpleScrapingLocator('https://pypi.org/simple/', timeout=3.0), + scheme='legacy') locate = default_locator.locate @@ -1137,7 +1133,7 @@ class DependencyFinder(object): :return: A set of distribution which can fulfill the requirement. """ matcher = self.get_matcher(reqt) - name = matcher.key # case-insensitive + name = matcher.key # case-insensitive result = set() provided = self.provided if name in provided: @@ -1179,8 +1175,7 @@ class DependencyFinder(object): unmatched.add(s) if unmatched: # can't replace other with provider - problems.add(('cantreplace', provider, other, - frozenset(unmatched))) + problems.add(('cantreplace', provider, other, frozenset(unmatched))) result = False else: # can replace other with provider @@ -1233,8 +1228,7 @@ class DependencyFinder(object): dist = odist = requirement logger.debug('passed %s as requirement', odist) else: - dist = odist = self.locator.locate(requirement, - prereleases=prereleases) + dist = odist = self.locator.locate(requirement, prereleases=prereleases) if dist is None: raise DistlibException('Unable to locate %r' % requirement) logger.debug('located %s', odist) @@ -1244,7 +1238,7 @@ class DependencyFinder(object): install_dists = set([odist]) while todo: dist = todo.pop() - name = dist.key # case-insensitive + name = dist.key # case-insensitive if name not in self.dists_by_name: self.add_distribution(dist) else: @@ -1281,8 +1275,7 @@ class DependencyFinder(object): providers.add(provider) if r in ireqts and dist in install_dists: install_dists.add(provider) - logger.debug('Adding %s to install_dists', - provider.name_and_version) + logger.debug('Adding %s to install_dists', provider.name_and_version) for p in providers: name = p.key if name not in self.dists_by_name: @@ -1297,7 +1290,6 @@ class DependencyFinder(object): for dist in dists: dist.build_time_dependency = dist not in install_dists if dist.build_time_dependency: - logger.debug('%s is a build-time dependency only.', - dist.name_and_version) + logger.debug('%s is a build-time dependency only.', dist.name_and_version) logger.debug('find done for %s', odist) return dists, problems diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/markers.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/markers.py index 1514d46..3f5632b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/markers.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/markers.py @@ -23,8 +23,7 @@ from .version import LegacyVersion as LV __all__ = ['interpret'] -_VERSION_PATTERN = re.compile( - r'((\d+(\.\d+)*\w*)|\'(\d+(\.\d+)*\w*)\'|\"(\d+(\.\d+)*\w*)\")') +_VERSION_PATTERN = re.compile(r'((\d+(\.\d+)*\w*)|\'(\d+(\.\d+)*\w*)\'|\"(\d+(\.\d+)*\w*)\")') _VERSION_MARKERS = {'python_version', 'python_full_version'} @@ -82,13 +81,12 @@ class Evaluator(object): elhs = expr['lhs'] erhs = expr['rhs'] if _is_literal(expr['lhs']) and _is_literal(expr['rhs']): - raise SyntaxError('invalid comparison: %s %s %s' % - (elhs, op, erhs)) + raise SyntaxError('invalid comparison: %s %s %s' % (elhs, op, erhs)) lhs = self.evaluate(elhs, context) rhs = self.evaluate(erhs, context) - if ((_is_version_marker(elhs) or _is_version_marker(erhs)) - and op in ('<', '<=', '>', '>=', '===', '==', '!=', '~=')): + if ((_is_version_marker(elhs) or _is_version_marker(erhs)) and + op in ('<', '<=', '>', '>=', '===', '==', '!=', '~=')): lhs = LV(lhs) rhs = LV(rhs) elif _is_version_marker(elhs) and op in ('in', 'not in'): @@ -111,8 +109,7 @@ def default_context(): return version if hasattr(sys, 'implementation'): - implementation_version = format_full_version( - sys.implementation.version) + implementation_version = format_full_version(sys.implementation.version) implementation_name = sys.implementation.name else: implementation_version = '0' @@ -156,11 +153,9 @@ def interpret(marker, execution_context=None): try: expr, rest = parse_marker(marker) except Exception as e: - raise SyntaxError('Unable to interpret marker syntax: %s: %s' % - (marker, e)) + raise SyntaxError('Unable to interpret marker syntax: %s: %s' % (marker, e)) if rest and rest[0] != '#': - raise SyntaxError('unexpected trailing data in marker: %s: %s' % - (marker, rest)) + raise SyntaxError('unexpected trailing data in marker: %s: %s' % (marker, rest)) context = dict(DEFAULT_CONTEXT) if execution_context: context.update(execution_context) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/metadata.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/metadata.py index 7189aee..ce9a34b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/metadata.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/metadata.py @@ -15,7 +15,6 @@ import json import logging import re - from . import DistlibException, __version__ from .compat import StringIO, string_types, text_type from .markers import interpret @@ -40,6 +39,7 @@ class MetadataUnrecognizedVersionError(DistlibException): class MetadataInvalidError(DistlibException): """A metadata value is invalid""" + # public API of this module __all__ = ['Metadata', 'PKG_INFO_ENCODING', 'PKG_INFO_PREFERRED_VERSION'] @@ -52,53 +52,38 @@ PKG_INFO_PREFERRED_VERSION = '1.1' _LINE_PREFIX_1_2 = re.compile('\n \\|') _LINE_PREFIX_PRE_1_2 = re.compile('\n ') -_241_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', - 'Summary', 'Description', - 'Keywords', 'Home-page', 'Author', 'Author-email', - 'License') +_241_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Summary', 'Description', 'Keywords', 'Home-page', + 'Author', 'Author-email', 'License') -_314_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', - 'Supported-Platform', 'Summary', 'Description', - 'Keywords', 'Home-page', 'Author', 'Author-email', - 'License', 'Classifier', 'Download-URL', 'Obsoletes', +_314_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Supported-Platform', 'Summary', 'Description', + 'Keywords', 'Home-page', 'Author', 'Author-email', 'License', 'Classifier', 'Download-URL', 'Obsoletes', 'Provides', 'Requires') -_314_MARKERS = ('Obsoletes', 'Provides', 'Requires', 'Classifier', - 'Download-URL') +_314_MARKERS = ('Obsoletes', 'Provides', 'Requires', 'Classifier', 'Download-URL') -_345_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', - 'Supported-Platform', 'Summary', 'Description', - 'Keywords', 'Home-page', 'Author', 'Author-email', - 'Maintainer', 'Maintainer-email', 'License', - 'Classifier', 'Download-URL', 'Obsoletes-Dist', - 'Project-URL', 'Provides-Dist', 'Requires-Dist', +_345_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Supported-Platform', 'Summary', 'Description', + 'Keywords', 'Home-page', 'Author', 'Author-email', 'Maintainer', 'Maintainer-email', 'License', + 'Classifier', 'Download-URL', 'Obsoletes-Dist', 'Project-URL', 'Provides-Dist', 'Requires-Dist', 'Requires-Python', 'Requires-External') -_345_MARKERS = ('Provides-Dist', 'Requires-Dist', 'Requires-Python', - 'Obsoletes-Dist', 'Requires-External', 'Maintainer', - 'Maintainer-email', 'Project-URL') +_345_MARKERS = ('Provides-Dist', 'Requires-Dist', 'Requires-Python', 'Obsoletes-Dist', 'Requires-External', + 'Maintainer', 'Maintainer-email', 'Project-URL') -_426_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', - 'Supported-Platform', 'Summary', 'Description', - 'Keywords', 'Home-page', 'Author', 'Author-email', - 'Maintainer', 'Maintainer-email', 'License', - 'Classifier', 'Download-URL', 'Obsoletes-Dist', - 'Project-URL', 'Provides-Dist', 'Requires-Dist', - 'Requires-Python', 'Requires-External', 'Private-Version', - 'Obsoleted-By', 'Setup-Requires-Dist', 'Extension', - 'Provides-Extra') +_426_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Supported-Platform', 'Summary', 'Description', + 'Keywords', 'Home-page', 'Author', 'Author-email', 'Maintainer', 'Maintainer-email', 'License', + 'Classifier', 'Download-URL', 'Obsoletes-Dist', 'Project-URL', 'Provides-Dist', 'Requires-Dist', + 'Requires-Python', 'Requires-External', 'Private-Version', 'Obsoleted-By', 'Setup-Requires-Dist', + 'Extension', 'Provides-Extra') -_426_MARKERS = ('Private-Version', 'Provides-Extra', 'Obsoleted-By', - 'Setup-Requires-Dist', 'Extension') +_426_MARKERS = ('Private-Version', 'Provides-Extra', 'Obsoleted-By', 'Setup-Requires-Dist', 'Extension') # See issue #106: Sometimes 'Requires' and 'Provides' occur wrongly in # the metadata. Include them in the tuple literal below to allow them # (for now). # Ditto for Obsoletes - see issue #140. -_566_FIELDS = _426_FIELDS + ('Description-Content-Type', - 'Requires', 'Provides', 'Obsoletes') +_566_FIELDS = _426_FIELDS + ('Description-Content-Type', 'Requires', 'Provides', 'Obsoletes') -_566_MARKERS = ('Description-Content-Type',) +_566_MARKERS = ('Description-Content-Type', ) _643_MARKERS = ('Dynamic', 'License-File') @@ -135,6 +120,7 @@ def _version2fieldlist(version): def _best_version(fields): """Detect the best version depending on the fields used.""" + def _has_marker(keys, markers): return any(marker in keys for marker in markers) @@ -163,12 +149,12 @@ def _best_version(fields): possible_versions.remove('2.2') logger.debug('Removed 2.2 due to %s', key) # if key not in _426_FIELDS and '2.0' in possible_versions: - # possible_versions.remove('2.0') - # logger.debug('Removed 2.0 due to %s', key) + # possible_versions.remove('2.0') + # logger.debug('Removed 2.0 due to %s', key) # possible_version contains qualified versions if len(possible_versions) == 1: - return possible_versions[0] # found ! + return possible_versions[0] # found ! elif len(possible_versions) == 0: logger.debug('Out of options - unknown metadata set: %s', fields) raise MetadataConflictError('Unknown metadata set') @@ -199,28 +185,25 @@ def _best_version(fields): if is_2_1: return '2.1' # if is_2_2: - # return '2.2' + # return '2.2' return '2.2' + # This follows the rules about transforming keys as described in # https://www.python.org/dev/peps/pep-0566/#id17 -_ATTR2FIELD = { - name.lower().replace("-", "_"): name for name in _ALL_FIELDS -} +_ATTR2FIELD = {name.lower().replace("-", "_"): name for name in _ALL_FIELDS} _FIELD2ATTR = {field: attr for attr, field in _ATTR2FIELD.items()} _PREDICATE_FIELDS = ('Requires-Dist', 'Obsoletes-Dist', 'Provides-Dist') -_VERSIONS_FIELDS = ('Requires-Python',) -_VERSION_FIELDS = ('Version',) -_LISTFIELDS = ('Platform', 'Classifier', 'Obsoletes', - 'Requires', 'Provides', 'Obsoletes-Dist', - 'Provides-Dist', 'Requires-Dist', 'Requires-External', - 'Project-URL', 'Supported-Platform', 'Setup-Requires-Dist', +_VERSIONS_FIELDS = ('Requires-Python', ) +_VERSION_FIELDS = ('Version', ) +_LISTFIELDS = ('Platform', 'Classifier', 'Obsoletes', 'Requires', 'Provides', 'Obsoletes-Dist', 'Provides-Dist', + 'Requires-Dist', 'Requires-External', 'Project-URL', 'Supported-Platform', 'Setup-Requires-Dist', 'Provides-Extra', 'Extension', 'License-File') -_LISTTUPLEFIELDS = ('Project-URL',) +_LISTTUPLEFIELDS = ('Project-URL', ) -_ELEMENTSFIELD = ('Keywords',) +_ELEMENTSFIELD = ('Keywords', ) _UNICODEFIELDS = ('Author', 'Maintainer', 'Summary', 'Description') @@ -252,10 +235,10 @@ class LegacyMetadata(object): - *mapping* is a dict-like object - *scheme* is a version scheme name """ + # TODO document the mapping API and UNKNOWN default key - def __init__(self, path=None, fileobj=None, mapping=None, - scheme='default'): + def __init__(self, path=None, fileobj=None, mapping=None, scheme='default'): if [path, fileobj, mapping].count(None) < 2: raise TypeError('path, fileobj and mapping are exclusive') self._fields = {} @@ -290,8 +273,7 @@ class LegacyMetadata(object): raise KeyError(name) def __contains__(self, name): - return (name in self._fields or - self._convert_name(name) in self._fields) + return (name in self._fields or self._convert_name(name) in self._fields) def _convert_name(self, name): if name in _ALL_FIELDS: @@ -319,12 +301,12 @@ class LegacyMetadata(object): # Public API # -# dependencies = property(_get_dependencies, _set_dependencies) - def get_fullname(self, filesafe=False): - """Return the distribution name with version. + """ + Return the distribution name with version. - If filesafe is true, return a filename-escaped form.""" + If filesafe is true, return a filename-escaped form. + """ return _get_name_and_version(self['Name'], self['Version'], filesafe) def is_field(self, name): @@ -415,6 +397,7 @@ class LegacyMetadata(object): Keys that don't match a metadata field or that have an empty value are dropped. """ + def _set(key, value): if key in _ATTR2FIELD and value: self.set(self._convert_name(key), value) @@ -437,14 +420,12 @@ class LegacyMetadata(object): """Control then set a metadata field.""" name = self._convert_name(name) - if ((name in _ELEMENTSFIELD or name == 'Platform') and - not isinstance(value, (list, tuple))): + if ((name in _ELEMENTSFIELD or name == 'Platform') and not isinstance(value, (list, tuple))): if isinstance(value, string_types): value = [v.strip() for v in value.split(',')] else: value = [] - elif (name in _LISTFIELDS and - not isinstance(value, (list, tuple))): + elif (name in _LISTFIELDS and not isinstance(value, (list, tuple))): if isinstance(value, string_types): value = [value] else: @@ -458,18 +439,14 @@ class LegacyMetadata(object): for v in value: # check that the values are valid if not scheme.is_valid_matcher(v.split(';')[0]): - logger.warning( - "'%s': '%s' is not valid (field '%s')", - project_name, v, name) + logger.warning("'%s': '%s' is not valid (field '%s')", project_name, v, name) # FIXME this rejects UNKNOWN, is that right? elif name in _VERSIONS_FIELDS and value is not None: if not scheme.is_valid_constraint_list(value): - logger.warning("'%s': '%s' is not a valid version (field '%s')", - project_name, value, name) + logger.warning("'%s': '%s' is not a valid version (field '%s')", project_name, value, name) elif name in _VERSION_FIELDS and value is not None: if not scheme.is_valid_version(value): - logger.warning("'%s': '%s' is not a valid version (field '%s')", - project_name, value, name) + logger.warning("'%s': '%s' is not a valid version (field '%s')", project_name, value, name) if name in _UNICODEFIELDS: if name == 'Description': @@ -539,10 +516,8 @@ class LegacyMetadata(object): return True for fields, controller in ((_PREDICATE_FIELDS, are_valid_constraints), - (_VERSIONS_FIELDS, - scheme.is_valid_constraint_list), - (_VERSION_FIELDS, - scheme.is_valid_version)): + (_VERSIONS_FIELDS, scheme.is_valid_constraint_list), (_VERSION_FIELDS, + scheme.is_valid_version)): for field in fields: value = self.get(field, None) if value is not None and not controller(value): @@ -598,8 +573,7 @@ class LegacyMetadata(object): return [(key, self[key]) for key in self.keys()] def __repr__(self): - return '<%s %s %s>' % (self.__class__.__name__, self.name, - self.version) + return '<%s %s %s>' % (self.__class__.__name__, self.name, self.version) METADATA_FILENAME = 'pydist.json' @@ -631,7 +605,7 @@ class Metadata(object): MANDATORY_KEYS = { 'name': (), 'version': (), - 'summary': ('legacy',), + 'summary': ('legacy', ), } INDEX_KEYS = ('name version license summary description author ' @@ -644,22 +618,21 @@ class Metadata(object): SYNTAX_VALIDATORS = { 'metadata_version': (METADATA_VERSION_MATCHER, ()), - 'name': (NAME_MATCHER, ('legacy',)), - 'version': (VERSION_MATCHER, ('legacy',)), - 'summary': (SUMMARY_MATCHER, ('legacy',)), - 'dynamic': (FIELDNAME_MATCHER, ('legacy',)), + 'name': (NAME_MATCHER, ('legacy', )), + 'version': (VERSION_MATCHER, ('legacy', )), + 'summary': (SUMMARY_MATCHER, ('legacy', )), + 'dynamic': (FIELDNAME_MATCHER, ('legacy', )), } __slots__ = ('_legacy', '_data', 'scheme') - def __init__(self, path=None, fileobj=None, mapping=None, - scheme='default'): + def __init__(self, path=None, fileobj=None, mapping=None, scheme='default'): if [path, fileobj, mapping].count(None) < 2: raise TypeError('path, fileobj and mapping are exclusive') self._legacy = None self._data = None self.scheme = scheme - #import pdb; pdb.set_trace() + # import pdb; pdb.set_trace() if mapping is not None: try: self._validate_mapping(mapping, scheme) @@ -693,8 +666,7 @@ class Metadata(object): # The ValueError comes from the json.load - if that # succeeds and we get a validation error, we want # that to propagate - self._legacy = LegacyMetadata(fileobj=StringIO(data), - scheme=scheme) + self._legacy = LegacyMetadata(fileobj=StringIO(data), scheme=scheme) self.validate() common_keys = set(('name', 'version', 'license', 'keywords', 'summary')) @@ -732,8 +704,7 @@ class Metadata(object): result = self._legacy.get(lk) else: value = None if maker is None else maker() - if key not in ('commands', 'exports', 'modules', 'namespaces', - 'classifiers'): + if key not in ('commands', 'exports', 'modules', 'namespaces', 'classifiers'): result = self._data.get(key, value) else: # special cases for PEP 459 @@ -770,8 +741,7 @@ class Metadata(object): m = pattern.match(value) if not m: raise MetadataInvalidError("'%s' is an invalid value for " - "the '%s' property" % (value, - key)) + "the '%s' property" % (value, key)) def __setattr__(self, key, value): self._validate_value(key, value) @@ -783,8 +753,7 @@ class Metadata(object): if lk is None: raise NotImplementedError self._legacy[lk] = value - elif key not in ('commands', 'exports', 'modules', 'namespaces', - 'classifiers'): + elif key not in ('commands', 'exports', 'modules', 'namespaces', 'classifiers'): self._data[key] = value else: # special cases for PEP 459 @@ -872,8 +841,7 @@ class Metadata(object): # A recursive call, but it should terminate since 'test' # has been removed from the extras reqts = self._data.get('%s_requires' % key, []) - result.extend(self.get_requirements(reqts, extras=extras, - env=env)) + result.extend(self.get_requirements(reqts, extras=extras, env=env)) return result @property @@ -914,8 +882,7 @@ class Metadata(object): if self._legacy: missing, warnings = self._legacy.check(True) if missing or warnings: - logger.warning('Metadata: missing: %s, warnings: %s', - missing, warnings) + logger.warning('Metadata: missing: %s, warnings: %s', missing, warnings) else: self._validate_mapping(self._data, self.scheme) @@ -932,9 +899,8 @@ class Metadata(object): 'metadata_version': self.METADATA_VERSION, 'generator': self.GENERATOR, } - lmd = self._legacy.todict(True) # skip missing ones - for k in ('name', 'version', 'license', 'summary', 'description', - 'classifier'): + lmd = self._legacy.todict(True) # skip missing ones + for k in ('name', 'version', 'license', 'summary', 'description', 'classifier'): if k in lmd: if k == 'classifier': nk = 'classifiers' @@ -945,14 +911,13 @@ class Metadata(object): if kw == ['']: kw = [] result['keywords'] = kw - keys = (('requires_dist', 'run_requires'), - ('setup_requires_dist', 'build_requires')) + keys = (('requires_dist', 'run_requires'), ('setup_requires_dist', 'build_requires')) for ok, nk in keys: if ok in lmd and lmd[ok]: result[nk] = [{'requires': lmd[ok]}] result['provides'] = self.provides - author = {} - maintainer = {} + # author = {} + # maintainer = {} return result LEGACY_MAPPING = { @@ -969,6 +934,7 @@ class Metadata(object): } def _to_legacy(self): + def process_entries(entries): reqts = set() for e in entries: @@ -1037,12 +1003,10 @@ class Metadata(object): else: d = self._data if fileobj: - json.dump(d, fileobj, ensure_ascii=True, indent=2, - sort_keys=True) + json.dump(d, fileobj, ensure_ascii=True, indent=2, sort_keys=True) else: with codecs.open(path, 'w', 'utf-8') as f: - json.dump(d, f, ensure_ascii=True, indent=2, - sort_keys=True) + json.dump(d, f, ensure_ascii=True, indent=2, sort_keys=True) def add_requirements(self, requirements): if self._legacy: @@ -1055,7 +1019,7 @@ class Metadata(object): always = entry break if always is None: - always = { 'requires': requirements } + always = {'requires': requirements} run_requires.insert(0, always) else: rset = set(always['requires']) | set(requirements) @@ -1064,5 +1028,4 @@ class Metadata(object): def __repr__(self): name = self.name or '(no name)' version = self.version or 'no version' - return '<%s %s %s (%s)>' % (self.__class__.__name__, - self.metadata_version, name, version) + return '<%s %s %s (%s)>' % (self.__class__.__name__, self.metadata_version, name, version) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/scripts.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/scripts.py index cfa45d2..b1fc705 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/scripts.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/scripts.py @@ -15,8 +15,7 @@ from zipfile import ZipInfo from .compat import sysconfig, detect_encoding, ZipFile from .resources import finder -from .util import (FileOperator, get_export_entry, convert_path, - get_executable, get_platform, in_venv) +from .util import (FileOperator, get_export_entry, convert_path, get_executable, get_platform, in_venv) logger = logging.getLogger(__name__) @@ -49,6 +48,25 @@ if __name__ == '__main__': sys.exit(%(func)s()) ''' +# Pre-fetch the contents of all executable wrapper stubs. +# This is to address https://github.com/pypa/pip/issues/12666. +# When updating pip, we rename the old pip in place before installing the +# new version. If we try to fetch a wrapper *after* that rename, the finder +# machinery will be confused as the package is no longer available at the +# location where it was imported from. So we load everything into memory in +# advance. + +if os.name == 'nt' or (os.name == 'java' and os._name == 'nt'): + # Issue 31: don't hardcode an absolute package name, but + # determine it relative to the current package + DISTLIB_PACKAGE = __name__.rsplit('.', 1)[0] + + WRAPPERS = { + r.name: r.bytes + for r in finder(DISTLIB_PACKAGE).iterator("") + if r.name.endswith(".exe") + } + def enquote_executable(executable): if ' ' in executable: @@ -79,25 +97,18 @@ class ScriptMaker(object): executable = None # for shebangs - def __init__(self, - source_dir, - target_dir, - add_launchers=True, - dry_run=False, - fileop=None): + def __init__(self, source_dir, target_dir, add_launchers=True, dry_run=False, fileop=None): self.source_dir = source_dir self.target_dir = target_dir self.add_launchers = add_launchers self.force = False self.clobber = False # It only makes sense to set mode bits on POSIX. - self.set_mode = (os.name == 'posix') or (os.name == 'java' - and os._name == 'posix') + self.set_mode = (os.name == 'posix') or (os.name == 'java' and os._name == 'posix') self.variants = set(('', 'X.Y')) self._fileop = fileop or FileOperator(dry_run) - self._is_nt = os.name == 'nt' or (os.name == 'java' - and os._name == 'nt') + self._is_nt = os.name == 'nt' or (os.name == 'java' and os._name == 'nt') self.version_info = sys.version_info def _get_alternate_executable(self, executable, options): @@ -146,6 +157,12 @@ class ScriptMaker(object): """ if os.name != 'posix': simple_shebang = True + elif getattr(sys, "cross_compiling", False): + # In a cross-compiling environment, the shebang will likely be a + # script; this *must* be invoked with the "safe" version of the + # shebang, or else using os.exec() to run the entry script will + # fail, raising "OSError 8 [Errno 8] Exec format error". + simple_shebang = False else: # Add 3 for '#!' prefix and newline suffix. shebang_length = len(executable) + len(post_interp) + 3 @@ -153,15 +170,14 @@ class ScriptMaker(object): max_shebang_length = 512 else: max_shebang_length = 127 - simple_shebang = ((b' ' not in executable) - and (shebang_length <= max_shebang_length)) + simple_shebang = ((b' ' not in executable) and (shebang_length <= max_shebang_length)) if simple_shebang: result = b'#!' + executable + post_interp + b'\n' else: result = b'#!/bin/sh\n' result += b"'''exec' " + executable + post_interp + b' "$0" "$@"\n' - result += b"' '''" + result += b"' '''\n" return result def _get_shebang(self, encoding, post_interp=b'', options=None): @@ -172,21 +188,17 @@ class ScriptMaker(object): elif not sysconfig.is_python_build(): executable = get_executable() elif in_venv(): # pragma: no cover - executable = os.path.join( - sysconfig.get_path('scripts'), - 'python%s' % sysconfig.get_config_var('EXE')) + executable = os.path.join(sysconfig.get_path('scripts'), 'python%s' % sysconfig.get_config_var('EXE')) else: # pragma: no cover if os.name == 'nt': # for Python builds from source on Windows, no Python executables with # a version suffix are created, so we use python.exe - executable = os.path.join( - sysconfig.get_config_var('BINDIR'), - 'python%s' % (sysconfig.get_config_var('EXE'))) + executable = os.path.join(sysconfig.get_config_var('BINDIR'), + 'python%s' % (sysconfig.get_config_var('EXE'))) else: executable = os.path.join( sysconfig.get_config_var('BINDIR'), - 'python%s%s' % (sysconfig.get_config_var('VERSION'), - sysconfig.get_config_var('EXE'))) + 'python%s%s' % (sysconfig.get_config_var('VERSION'), sysconfig.get_config_var('EXE'))) if options: executable = self._get_alternate_executable(executable, options) @@ -210,8 +222,8 @@ class ScriptMaker(object): # check that the shebang is decodable using utf-8. executable = executable.encode('utf-8') # in case of IronPython, play safe and enable frames support - if (sys.platform == 'cli' and '-X:Frames' not in post_interp - and '-X:FullFrames' not in post_interp): # pragma: no cover + if (sys.platform == 'cli' and '-X:Frames' not in post_interp and + '-X:FullFrames' not in post_interp): # pragma: no cover post_interp += b' -X:Frames' shebang = self._build_shebang(executable, post_interp) # Python parser starts to read a script using UTF-8 until @@ -222,8 +234,7 @@ class ScriptMaker(object): try: shebang.decode('utf-8') except UnicodeDecodeError: # pragma: no cover - raise ValueError('The shebang (%r) is not decodable from utf-8' % - shebang) + raise ValueError('The shebang (%r) is not decodable from utf-8' % shebang) # If the script is encoded to a custom encoding (use a # #coding:xxx cookie), the shebang has to be decodable from # the script encoding too. @@ -232,15 +243,12 @@ class ScriptMaker(object): shebang.decode(encoding) except UnicodeDecodeError: # pragma: no cover raise ValueError('The shebang (%r) is not decodable ' - 'from the script encoding (%r)' % - (shebang, encoding)) + 'from the script encoding (%r)' % (shebang, encoding)) return shebang def _get_script_text(self, entry): return self.script_template % dict( - module=entry.prefix, - import_name=entry.suffix.split('.')[0], - func=entry.suffix) + module=entry.prefix, import_name=entry.suffix.split('.')[0], func=entry.suffix) manifest = _DEFAULT_MANIFEST @@ -250,9 +258,6 @@ class ScriptMaker(object): def _write_script(self, names, shebang, script_bytes, filenames, ext): use_launcher = self.add_launchers and self._is_nt - linesep = os.linesep.encode('utf-8') - if not shebang.endswith(linesep): - shebang += linesep if not use_launcher: script_bytes = shebang + script_bytes else: # pragma: no cover @@ -265,8 +270,7 @@ class ScriptMaker(object): source_date_epoch = os.environ.get('SOURCE_DATE_EPOCH') if source_date_epoch: date_time = time.gmtime(int(source_date_epoch))[:6] - zinfo = ZipInfo(filename='__main__.py', - date_time=date_time) + zinfo = ZipInfo(filename='__main__.py', date_time=date_time) zf.writestr(zinfo, script_bytes) else: zf.writestr('__main__.py', script_bytes) @@ -297,8 +301,7 @@ class ScriptMaker(object): except Exception: pass # still in use - ignore error else: - if self._is_nt and not outname.endswith( - '.' + ext): # pragma: no cover + if self._is_nt and not outname.endswith('.' + ext): # pragma: no cover outname = '%s.%s' % (outname, ext) if os.path.exists(outname) and not self.clobber: logger.warning('Skipping existing file %s', outname) @@ -317,9 +320,7 @@ class ScriptMaker(object): if 'X' in self.variants: result.add('%s%s' % (name, self.version_info[0])) if 'X.Y' in self.variants: - result.add('%s%s%s.%s' % - (name, self.variant_separator, self.version_info[0], - self.version_info[1])) + result.add('%s%s%s.%s' % (name, self.variant_separator, self.version_info[0], self.version_info[1])) return result def _make_script(self, entry, filenames, options=None): @@ -374,8 +375,7 @@ class ScriptMaker(object): self._fileop.set_executable_mode([outname]) filenames.append(outname) else: - logger.info('copying and adjusting %s -> %s', script, - self.target_dir) + logger.info('copying and adjusting %s -> %s', script, self.target_dir) if not self._fileop.dry_run: encoding, lines = detect_encoding(f.readline) f.seek(0) @@ -397,8 +397,7 @@ class ScriptMaker(object): def dry_run(self, value): self._fileop.dry_run = value - if os.name == 'nt' or (os.name == 'java' - and os._name == 'nt'): # pragma: no cover + if os.name == 'nt' or (os.name == 'java' and os._name == 'nt'): # pragma: no cover # Executable launcher support. # Launchers are from https://bitbucket.org/vinay.sajip/simple_launcher/ @@ -409,15 +408,11 @@ class ScriptMaker(object): bits = '32' platform_suffix = '-arm' if get_platform() == 'win-arm64' else '' name = '%s%s%s.exe' % (kind, bits, platform_suffix) - # Issue 31: don't hardcode an absolute package name, but - # determine it relative to the current package - distlib_package = __name__.rsplit('.', 1)[0] - resource = finder(distlib_package).find(name) - if not resource: + if name not in WRAPPERS: msg = ('Unable to find resource %s in package %s' % - (name, distlib_package)) + (name, DISTLIB_PACKAGE)) raise ValueError(msg) - return resource.bytes + return WRAPPERS[name] # Public API follows diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t32.exe b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t32.exe new file mode 100644 index 0000000..52154f0 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t32.exe differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t64-arm.exe b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t64-arm.exe new file mode 100644 index 0000000..e1ab8f8 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t64-arm.exe differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t64.exe b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t64.exe new file mode 100644 index 0000000..e8bebdb Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/t64.exe differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/util.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/util.py index ba58858..0d5bd7a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/util.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/util.py @@ -31,11 +31,9 @@ except ImportError: # pragma: no cover import time from . import DistlibException -from .compat import (string_types, text_type, shutil, raw_input, StringIO, - cache_from_source, urlopen, urljoin, httplib, xmlrpclib, - HTTPHandler, BaseConfigurator, valid_ident, - Container, configparser, URLError, ZipFile, fsdecode, - unquote, urlparse) +from .compat import (string_types, text_type, shutil, raw_input, StringIO, cache_from_source, urlopen, urljoin, httplib, + xmlrpclib, HTTPHandler, BaseConfigurator, valid_ident, Container, configparser, URLError, ZipFile, + fsdecode, unquote, urlparse) logger = logging.getLogger(__name__) @@ -88,8 +86,7 @@ def parse_marker(marker_string): else: m = STRING_CHUNK.match(remaining) if not m: - raise SyntaxError('error in string literal: %s' % - remaining) + raise SyntaxError('error in string literal: %s' % remaining) parts.append(m.groups()[0]) remaining = remaining[m.end():] else: @@ -210,8 +207,7 @@ def parse_requirement(req): ver_remaining = ver_remaining[m.end():] m = VERSION_IDENTIFIER.match(ver_remaining) if not m: - raise SyntaxError('invalid version: %s' % - ver_remaining) + raise SyntaxError('invalid version: %s' % ver_remaining) v = m.groups()[0] versions.append((op, v)) ver_remaining = ver_remaining[m.end():] @@ -224,8 +220,7 @@ def parse_requirement(req): break m = COMPARE_OP.match(ver_remaining) if not m: - raise SyntaxError('invalid constraint: %s' % - ver_remaining) + raise SyntaxError('invalid constraint: %s' % ver_remaining) if not versions: versions = None return versions, ver_remaining @@ -235,8 +230,7 @@ def parse_requirement(req): else: i = remaining.find(')', 1) if i < 0: - raise SyntaxError('unterminated parenthesis: %s' % - remaining) + raise SyntaxError('unterminated parenthesis: %s' % remaining) s = remaining[1:i] remaining = remaining[i + 1:].lstrip() # As a special diversion from PEP 508, allow a version number @@ -267,14 +261,8 @@ def parse_requirement(req): if not versions: rs = distname else: - rs = '%s %s' % (distname, ', '.join( - ['%s %s' % con for con in versions])) - return Container(name=distname, - extras=extras, - constraints=versions, - marker=mark_expr, - url=uri, - requirement=rs) + rs = '%s %s' % (distname, ', '.join(['%s %s' % con for con in versions])) + return Container(name=distname, extras=extras, constraints=versions, marker=mark_expr, url=uri, requirement=rs) def get_resources_dests(resources_root, rules): @@ -524,8 +512,7 @@ class FileOperator(object): second will have the same "age". """ if not os.path.exists(source): - raise DistlibException("file '%r' does not exist" % - os.path.abspath(source)) + raise DistlibException("file '%r' does not exist" % os.path.abspath(source)) if not os.path.exists(target): return True @@ -601,12 +588,7 @@ class FileOperator(object): if self.record: self.dirs_created.add(path) - def byte_compile(self, - path, - optimize=False, - force=False, - prefix=None, - hashed_invalidation=False): + def byte_compile(self, path, optimize=False, force=False, prefix=None, hashed_invalidation=False): dpath = cache_from_source(path, not optimize) logger.info('Byte-compiling %s to %s', path, dpath) if not self.dry_run: @@ -617,12 +599,11 @@ class FileOperator(object): assert path.startswith(prefix) diagpath = path[len(prefix):] compile_kwargs = {} - if hashed_invalidation and hasattr(py_compile, - 'PycInvalidationMode'): - compile_kwargs[ - 'invalidation_mode'] = py_compile.PycInvalidationMode.CHECKED_HASH - py_compile.compile(path, dpath, diagpath, True, - **compile_kwargs) # raise error + if hashed_invalidation and hasattr(py_compile, 'PycInvalidationMode'): + if not isinstance(hashed_invalidation, py_compile.PycInvalidationMode): + hashed_invalidation = py_compile.PycInvalidationMode.CHECKED_HASH + compile_kwargs['invalidation_mode'] = hashed_invalidation + py_compile.compile(path, dpath, diagpath, True, **compile_kwargs) # raise error self.record_as_written(dpath) return dpath @@ -716,16 +697,14 @@ class ExportEntry(object): return resolve(self.prefix, self.suffix) def __repr__(self): # pragma: no cover - return '' % (self.name, self.prefix, - self.suffix, self.flags) + return '' % (self.name, self.prefix, self.suffix, self.flags) def __eq__(self, other): if not isinstance(other, ExportEntry): result = False else: - result = (self.name == other.name and self.prefix == other.prefix - and self.suffix == other.suffix - and self.flags == other.flags) + result = (self.name == other.name and self.prefix == other.prefix and self.suffix == other.suffix and + self.flags == other.flags) return result __hash__ = object.__hash__ @@ -810,7 +789,7 @@ def get_cache_base(suffix=None): return os.path.join(result, suffix) -def path_to_cache_dir(path): +def path_to_cache_dir(path, use_abspath=True): """ Convert an absolute path to a directory name for use in a cache. @@ -820,7 +799,7 @@ def path_to_cache_dir(path): #. Any occurrence of ``os.sep`` is replaced with ``'--'``. #. ``'.cache'`` is appended. """ - d, p = os.path.splitdrive(os.path.abspath(path)) + d, p = os.path.splitdrive(os.path.abspath(path) if use_abspath else path) if d: d = d.replace(':', '---') p = p.replace(os.sep, '--') @@ -865,9 +844,8 @@ def is_string_sequence(seq): return result -PROJECT_NAME_AND_VERSION = re.compile( - '([a-z0-9_]+([.-][a-z_][a-z0-9_]*)*)-' - '([a-z0-9_.+-]+)', re.I) +PROJECT_NAME_AND_VERSION = re.compile('([a-z0-9_]+([.-][a-z_][a-z0-9_]*)*)-' + '([a-z0-9_.+-]+)', re.I) PYTHON_VERSION = re.compile(r'-py(\d\.?\d?)') @@ -1003,11 +981,11 @@ class Cache(object): logger.warning('Directory \'%s\' is not private', base) self.base = os.path.abspath(os.path.normpath(base)) - def prefix_to_dir(self, prefix): + def prefix_to_dir(self, prefix, use_abspath=True): """ Converts a resource prefix to a directory name in the cache. """ - return path_to_cache_dir(prefix) + return path_to_cache_dir(prefix, use_abspath=use_abspath) def clear(self): """ @@ -1092,8 +1070,7 @@ class EventMixin(object): logger.exception('Exception during event publication') value = None result.append(value) - logger.debug('publish %s: args = %s, kwargs = %s, result = %s', event, - args, kwargs, result) + logger.debug('publish %s: args = %s, kwargs = %s, result = %s', event, args, kwargs, result) return result @@ -1145,8 +1122,7 @@ class Sequencer(object): raise ValueError('%r not a successor of %r' % (succ, pred)) def is_step(self, step): - return (step in self._preds or step in self._succs - or step in self._nodes) + return (step in self._preds or step in self._succs or step in self._nodes) def get_steps(self, final): if not self.is_step(final): @@ -1242,8 +1218,7 @@ class Sequencer(object): # Unarchiving functionality for zip, tar, tgz, tbz, whl # -ARCHIVE_EXTENSIONS = ('.tar.gz', '.tar.bz2', '.tar', '.zip', '.tgz', '.tbz', - '.whl') +ARCHIVE_EXTENSIONS = ('.tar.gz', '.tar.bz2', '.tar', '.zip', '.tgz', '.tbz', '.whl') def unarchive(archive_filename, dest_dir, format=None, check=True): @@ -1474,8 +1449,7 @@ def _iglob(path_glob): if ssl: - from .compat import (HTTPSHandler as BaseHTTPSHandler, match_hostname, - CertificateError) + from .compat import (HTTPSHandler as BaseHTTPSHandler, match_hostname, CertificateError) # # HTTPSConnection which verifies certificates/matches domains @@ -1487,8 +1461,7 @@ if ssl: # noinspection PyPropertyAccess def connect(self): - sock = socket.create_connection((self.host, self.port), - self.timeout) + sock = socket.create_connection((self.host, self.port), self.timeout) if getattr(self, '_tunnel_host', False): self.sock = sock self._tunnel() @@ -1543,9 +1516,8 @@ if ssl: return self.do_open(self._conn_maker, req) except URLError as e: if 'certificate verify failed' in str(e.reason): - raise CertificateError( - 'Unable to verify server certificate ' - 'for %s' % req.host) + raise CertificateError('Unable to verify server certificate ' + 'for %s' % req.host) else: raise @@ -1561,9 +1533,8 @@ if ssl: class HTTPSOnlyHandler(HTTPSHandler, HTTPHandler): def http_open(self, req): - raise URLError( - 'Unexpected HTTP request on what should be a secure ' - 'connection: %s' % req) + raise URLError('Unexpected HTTP request on what should be a secure ' + 'connection: %s' % req) # @@ -1598,8 +1569,7 @@ if ssl: kwargs['timeout'] = self.timeout if not self._connection or host != self._connection[0]: self._extra_headers = eh - self._connection = host, httplib.HTTPSConnection( - h, None, **kwargs) + self._connection = host, httplib.HTTPSConnection(h, None, **kwargs) return self._connection[1] @@ -1789,10 +1759,7 @@ class SubprocessMixin(object): stream.close() def run_command(self, cmd, **kwargs): - p = subprocess.Popen(cmd, - stdout=subprocess.PIPE, - stderr=subprocess.PIPE, - **kwargs) + p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, **kwargs) t1 = threading.Thread(target=self.reader, args=(p.stdout, 'stdout')) t1.start() t2 = threading.Thread(target=self.reader, args=(p.stderr, 'stderr')) @@ -1847,10 +1814,7 @@ class PyPIRCFile(object): if 'distutils' in sections: # let's get the list of servers index_servers = config.get('distutils', 'index-servers') - _servers = [ - server.strip() for server in index_servers.split('\n') - if server.strip() != '' - ] + _servers = [server.strip() for server in index_servers.split('\n') if server.strip() != ''] if _servers == []: # nothing set, let's try to get the default pypi if 'pypi' in sections: @@ -1861,9 +1825,7 @@ class PyPIRCFile(object): result['username'] = config.get(server, 'username') # optional params - for key, default in (('repository', - self.DEFAULT_REPOSITORY), - ('realm', self.DEFAULT_REALM), + for key, default in (('repository', self.DEFAULT_REPOSITORY), ('realm', self.DEFAULT_REALM), ('password', None)): if config.has_option(server, key): result[key] = config.get(server, key) @@ -1873,11 +1835,9 @@ class PyPIRCFile(object): # work around people having "repository" for the "pypi" # section of their config set to the HTTP (rather than # HTTPS) URL - if (server == 'pypi' and repository - in (self.DEFAULT_REPOSITORY, 'pypi')): + if (server == 'pypi' and repository in (self.DEFAULT_REPOSITORY, 'pypi')): result['repository'] = self.DEFAULT_REPOSITORY - elif (result['server'] != repository - and result['repository'] != repository): + elif (result['server'] != repository and result['repository'] != repository): result = {} elif 'server-login' in sections: # old format @@ -2003,8 +1963,7 @@ def get_host_platform(): from distutils import sysconfig except ImportError: import sysconfig - osname, release, machine = _osx_support.get_platform_osx( - sysconfig.get_config_vars(), osname, release, machine) + osname, release, machine = _osx_support.get_platform_osx(sysconfig.get_config_vars(), osname, release, machine) return '%s-%s-%s' % (osname, release, machine) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/version.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/version.py index 14171ac..d70a96e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/version.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/version.py @@ -619,8 +619,7 @@ class LegacyVersion(Version): def is_prerelease(self): result = False for x in self._parts: - if (isinstance(x, string_types) and x.startswith('*') and - x < '*final'): + if (isinstance(x, string_types) and x.startswith('*') and x < '*final'): result = True break return result diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w32.exe b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w32.exe new file mode 100644 index 0000000..4ee2d3a Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w32.exe differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w64-arm.exe b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w64-arm.exe new file mode 100644 index 0000000..951d581 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w64-arm.exe differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w64.exe b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w64.exe new file mode 100644 index 0000000..5763076 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/w64.exe differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/wheel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/wheel.py index 4a5a30e..62ab10f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/wheel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distlib/wheel.py @@ -25,9 +25,8 @@ from . import __version__, DistlibException from .compat import sysconfig, ZipFile, fsdecode, text_type, filter from .database import InstalledDistribution from .metadata import Metadata, WHEEL_METADATA_FILENAME, LEGACY_METADATA_FILENAME -from .util import (FileOperator, convert_path, CSVReader, CSVWriter, Cache, - cached_property, get_cache_base, read_exports, tempdir, - get_platform) +from .util import (FileOperator, convert_path, CSVReader, CSVWriter, Cache, cached_property, get_cache_base, + read_exports, tempdir, get_platform) from .version import NormalizedVersion, UnsupportedVersionError logger = logging.getLogger(__name__) @@ -88,8 +87,7 @@ FILENAME_RE = re.compile( \.whl$ ''', re.IGNORECASE | re.VERBOSE) -NAME_VERSION_RE = re.compile( - r''' +NAME_VERSION_RE = re.compile(r''' (?P[^-]+) -(?P\d+[^-]*) (-(?P\d+[^-]*))?$ @@ -235,8 +233,7 @@ class Wheel(object): arch = '.'.join(self.arch) # replace - with _ as a local version separator version = self.version.replace('-', '_') - return '%s-%s%s-%s-%s-%s.whl' % (self.name, version, buildver, pyver, - abi, arch) + return '%s-%s%s-%s-%s-%s.whl' % (self.name, version, buildver, pyver, abi, arch) @property def exists(self): @@ -334,8 +331,7 @@ class Wheel(object): try: hasher = getattr(hashlib, hash_kind) except AttributeError: - raise DistlibException('Unsupported hash algorithm: %r' % - hash_kind) + raise DistlibException('Unsupported hash algorithm: %r' % hash_kind) result = hasher(data).digest() result = base64.urlsafe_b64encode(result).rstrip(b'=').decode('ascii') return hash_kind, result @@ -513,7 +509,7 @@ class Wheel(object): installed, and the headers, scripts, data and dist-info metadata are not written. If kwarg ``bytecode_hashed_invalidation`` is True, written bytecode will try to use file-hash based invalidation (PEP-552) on - supported interpreter versions (CPython 2.7+). + supported interpreter versions (CPython 3.7+). The return value is a :class:`InstalledDistribution` instance unless ``options.lib_only`` is True, in which case the return value is ``None``. @@ -522,8 +518,7 @@ class Wheel(object): dry_run = maker.dry_run warner = kwargs.get('warner') lib_only = kwargs.get('lib_only', False) - bc_hashed_invalidation = kwargs.get('bytecode_hashed_invalidation', - False) + bc_hashed_invalidation = kwargs.get('bytecode_hashed_invalidation', False) pathname = os.path.join(self.dirname, self.filename) name_ver = '%s-%s' % (self.name, self.version) @@ -602,8 +597,7 @@ class Wheel(object): if lib_only and u_arcname.startswith((info_pfx, data_pfx)): logger.debug('lib_only: skipping %s', u_arcname) continue - is_script = (u_arcname.startswith(script_pfx) - and not u_arcname.endswith('.exe')) + is_script = (u_arcname.startswith(script_pfx) and not u_arcname.endswith('.exe')) if u_arcname.startswith(data_pfx): _, where, rp = u_arcname.split('/', 2) @@ -622,8 +616,7 @@ class Wheel(object): # So ... manually preserve permission bits as given in zinfo if os.name == 'posix': # just set the normal permission bits - os.chmod(outfile, - (zinfo.external_attr >> 16) & 0x1FF) + os.chmod(outfile, (zinfo.external_attr >> 16) & 0x1FF) outfiles.append(outfile) # Double check the digest of the written file if not dry_run and row[1]: @@ -636,15 +629,12 @@ class Wheel(object): '%s' % outfile) if bc and outfile.endswith('.py'): try: - pyc = fileop.byte_compile( - outfile, - hashed_invalidation=bc_hashed_invalidation) + pyc = fileop.byte_compile(outfile, hashed_invalidation=bc_hashed_invalidation) outfiles.append(pyc) except Exception: # Don't give up if byte-compilation fails, # but log it and perhaps warn the user - logger.warning('Byte-compilation failed', - exc_info=True) + logger.warning('Byte-compilation failed', exc_info=True) else: fn = os.path.basename(convert_path(arcname)) workname = os.path.join(workdir, fn) @@ -732,8 +722,7 @@ class Wheel(object): outfiles.append(p) # Write RECORD - dist.write_installed_files(outfiles, paths['prefix'], - dry_run) + dist.write_installed_files(outfiles, paths['prefix'], dry_run) return dist except Exception: # pragma: no cover logger.exception('installation failed.') @@ -746,8 +735,7 @@ class Wheel(object): global cache if cache is None: # Use native string to avoid issues on 2.x: see Python #20140. - base = os.path.join(get_cache_base(), str('dylib-cache'), - '%s.%s' % sys.version_info[:2]) + base = os.path.join(get_cache_base(), str('dylib-cache'), '%s.%s' % sys.version_info[:2]) cache = Cache(base) return cache @@ -764,7 +752,7 @@ class Wheel(object): wf = wrapper(bf) extensions = json.load(wf) cache = self._get_dylib_cache() - prefix = cache.prefix_to_dir(pathname) + prefix = cache.prefix_to_dir(self.filename, use_abspath=False) cache_base = os.path.join(cache.base, prefix) if not os.path.isdir(cache_base): os.makedirs(cache_base) @@ -774,8 +762,7 @@ class Wheel(object): extract = True else: file_time = os.stat(dest).st_mtime - file_time = datetime.datetime.fromtimestamp( - file_time) + file_time = datetime.datetime.fromtimestamp(file_time) info = zf.getinfo(relpath) wheel_time = datetime.datetime(*info.date_time) extract = wheel_time > file_time @@ -924,12 +911,10 @@ class Wheel(object): else: parts = [int(s) for s in version[i + 1:].split('.')] parts[-1] += 1 - updated = '%s+%s' % (version[:i], '.'.join( - str(i) for i in parts)) + updated = '%s+%s' % (version[:i], '.'.join(str(i) for i in parts)) except UnsupportedVersionError: - logger.debug( - 'Cannot update non-compliant (PEP-440) ' - 'version %r', version) + logger.debug('Cannot update non-compliant (PEP-440) ' + 'version %r', version) if updated: md = Metadata(path=path) md.version = updated @@ -971,14 +956,11 @@ class Wheel(object): update_version(current_version, path) # Decide where the new wheel goes. if dest_dir is None: - fd, newpath = tempfile.mkstemp(suffix='.whl', - prefix='wheel-update-', - dir=workdir) + fd, newpath = tempfile.mkstemp(suffix='.whl', prefix='wheel-update-', dir=workdir) os.close(fd) else: if not os.path.isdir(dest_dir): - raise DistlibException('Not a directory: %r' % - dest_dir) + raise DistlibException('Not a directory: %r' % dest_dir) newpath = os.path.join(dest_dir, self.filename) archive_paths = list(path_map.items()) distinfo = os.path.join(workdir, info_dir) @@ -1005,11 +987,20 @@ def compatible_tags(): """ Return (pyver, abi, arch) tuples compatible with this Python. """ - versions = [VER_SUFFIX] - major = VER_SUFFIX[0] - for minor in range(sys.version_info[1] - 1, -1, -1): - versions.append(''.join([major, str(minor)])) + class _Version: + def __init__(self, major, minor): + self.major = major + self.major_minor = (major, minor) + self.string = ''.join((str(major), str(minor))) + def __str__(self): + return self.string + + + versions = [ + _Version(sys.version_info.major, minor_version) + for minor_version in range(sys.version_info.minor, -1, -1) + ] abis = [] for suffix in _get_suffixes(): if suffix.startswith('.abi'): @@ -1045,35 +1036,45 @@ def compatible_tags(): minor -= 1 # Most specific - our Python version, ABI and arch - for abi in abis: - for arch in arches: - result.append((''.join((IMP_PREFIX, versions[0])), abi, arch)) - # manylinux - if abi != 'none' and sys.platform.startswith('linux'): - arch = arch.replace('linux_', '') - parts = _get_glibc_version() - if len(parts) == 2: - if parts >= (2, 5): - result.append((''.join((IMP_PREFIX, versions[0])), abi, - 'manylinux1_%s' % arch)) - if parts >= (2, 12): - result.append((''.join((IMP_PREFIX, versions[0])), abi, - 'manylinux2010_%s' % arch)) - if parts >= (2, 17): - result.append((''.join((IMP_PREFIX, versions[0])), abi, - 'manylinux2014_%s' % arch)) - result.append( - (''.join((IMP_PREFIX, versions[0])), abi, - 'manylinux_%s_%s_%s' % (parts[0], parts[1], arch))) + for i, version_object in enumerate(versions): + version = str(version_object) + add_abis = [] + + if i == 0: + add_abis = abis + + if IMP_PREFIX == 'cp' and version_object.major_minor >= (3, 2): + limited_api_abi = 'abi' + str(version_object.major) + if limited_api_abi not in add_abis: + add_abis.append(limited_api_abi) + + for abi in add_abis: + for arch in arches: + result.append((''.join((IMP_PREFIX, version)), abi, arch)) + # manylinux + if abi != 'none' and sys.platform.startswith('linux'): + arch = arch.replace('linux_', '') + parts = _get_glibc_version() + if len(parts) == 2: + if parts >= (2, 5): + result.append((''.join((IMP_PREFIX, version)), abi, 'manylinux1_%s' % arch)) + if parts >= (2, 12): + result.append((''.join((IMP_PREFIX, version)), abi, 'manylinux2010_%s' % arch)) + if parts >= (2, 17): + result.append((''.join((IMP_PREFIX, version)), abi, 'manylinux2014_%s' % arch)) + result.append((''.join( + (IMP_PREFIX, version)), abi, 'manylinux_%s_%s_%s' % (parts[0], parts[1], arch))) # where no ABI / arch dependency, but IMP_PREFIX dependency - for i, version in enumerate(versions): + for i, version_object in enumerate(versions): + version = str(version_object) result.append((''.join((IMP_PREFIX, version)), 'none', 'any')) if i == 0: result.append((''.join((IMP_PREFIX, version[0])), 'none', 'any')) # no IMP_PREFIX, ABI or arch dependency - for i, version in enumerate(versions): + for i, version_object in enumerate(versions): + version = str(version_object) result.append((''.join(('py', version)), 'none', 'any')) if i == 0: result.append((''.join(('py', version[0])), 'none', 'any')) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__init__.cpython-312.pyc index b5cdc89..70816ce 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__main__.cpython-312.pyc index 1f99fb4..2c0054f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/distro.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/distro.cpython-312.pyc index 96678fa..14098a8 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/distro.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/__pycache__/distro.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/distro.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/distro.py index 89e1868..78ccdfa 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/distro.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/distro.py @@ -1,5 +1,5 @@ #!/usr/bin/env python -# Copyright 2015,2016,2017 Nir Cohen +# Copyright 2015-2021 Nir Cohen # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. @@ -55,7 +55,7 @@ except ImportError: # Python 3.7 TypedDict = dict -__version__ = "1.8.0" +__version__ = "1.9.0" class VersionDict(TypedDict): @@ -125,6 +125,7 @@ _DISTRO_RELEASE_BASENAME_PATTERN = re.compile(r"(\w+)[-_](release|version)$") # Base file names to be looked up for if _UNIXCONFDIR is not readable. _DISTRO_RELEASE_BASENAMES = [ "SuSE-release", + "altlinux-release", "arch-release", "base-release", "centos-release", @@ -151,6 +152,8 @@ _DISTRO_RELEASE_IGNORE_BASENAMES = ( "system-release", "plesk-release", "iredmail-release", + "board-release", + "ec2_version", ) @@ -243,6 +246,7 @@ def id() -> str: "rocky" Rocky Linux "aix" AIX "guix" Guix System + "altlinux" ALT Linux ============== ========================================= If you have a need to get distros for reliable IDs added into this set, @@ -991,10 +995,10 @@ class LinuxDistribution: For details, see :func:`distro.info`. """ - return dict( + return InfoDict( id=self.id(), version=self.version(pretty, best), - version_parts=dict( + version_parts=VersionDict( major=self.major_version(best), minor=self.minor_version(best), build_number=self.build_number(best), diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/distro/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/distro/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__init__.py index a40eeaf..cfdc030 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__init__.py @@ -1,4 +1,3 @@ -from .package_data import __version__ from .core import ( IDNABidiError, IDNAError, @@ -20,8 +19,10 @@ from .core import ( valid_string_length, ) from .intranges import intranges_contain +from .package_data import __version__ __all__ = [ + "__version__", "IDNABidiError", "IDNAError", "InvalidCodepoint", diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/__init__.cpython-312.pyc index 0e4a91b..439460b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/codec.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/codec.cpython-312.pyc index 5799912..c2108d8 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/codec.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/codec.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/compat.cpython-312.pyc index 64a202d..34846ee 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/compat.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/compat.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/core.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/core.cpython-312.pyc index d36326f..bce683b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/core.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/core.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/idnadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/idnadata.cpython-312.pyc index 9fe5d74..d5f1d08 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/idnadata.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/idnadata.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/intranges.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/intranges.cpython-312.pyc index 0cb29ef..409c355 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/intranges.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/intranges.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/package_data.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/package_data.cpython-312.pyc index a5bced9..af95914 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/package_data.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/package_data.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/uts46data.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/uts46data.cpython-312.pyc index b889dda..cbc639f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/uts46data.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/__pycache__/uts46data.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/codec.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/codec.py index 1ca9ba6..913abfd 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/codec.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/codec.py @@ -1,49 +1,51 @@ -from .core import encode, decode, alabel, ulabel, IDNAError import codecs import re -from typing import Tuple, Optional +from typing import Any, Optional, Tuple + +from .core import IDNAError, alabel, decode, encode, ulabel + +_unicode_dots_re = re.compile("[\u002e\u3002\uff0e\uff61]") -_unicode_dots_re = re.compile('[\u002e\u3002\uff0e\uff61]') class Codec(codecs.Codec): - - def encode(self, data: str, errors: str = 'strict') -> Tuple[bytes, int]: - if errors != 'strict': - raise IDNAError('Unsupported error handling \"{}\"'.format(errors)) + def encode(self, data: str, errors: str = "strict") -> Tuple[bytes, int]: + if errors != "strict": + raise IDNAError('Unsupported error handling "{}"'.format(errors)) if not data: return b"", 0 return encode(data), len(data) - def decode(self, data: bytes, errors: str = 'strict') -> Tuple[str, int]: - if errors != 'strict': - raise IDNAError('Unsupported error handling \"{}\"'.format(errors)) - - if not data: - return '', 0 - - return decode(data), len(data) - -class IncrementalEncoder(codecs.BufferedIncrementalEncoder): - def _buffer_encode(self, data: str, errors: str, final: bool) -> Tuple[str, int]: # type: ignore - if errors != 'strict': - raise IDNAError('Unsupported error handling \"{}\"'.format(errors)) + def decode(self, data: bytes, errors: str = "strict") -> Tuple[str, int]: + if errors != "strict": + raise IDNAError('Unsupported error handling "{}"'.format(errors)) if not data: return "", 0 + return decode(data), len(data) + + +class IncrementalEncoder(codecs.BufferedIncrementalEncoder): + def _buffer_encode(self, data: str, errors: str, final: bool) -> Tuple[bytes, int]: + if errors != "strict": + raise IDNAError('Unsupported error handling "{}"'.format(errors)) + + if not data: + return b"", 0 + labels = _unicode_dots_re.split(data) - trailing_dot = '' + trailing_dot = b"" if labels: if not labels[-1]: - trailing_dot = '.' + trailing_dot = b"." del labels[-1] elif not final: # Keep potentially unfinished label until the next call del labels[-1] if labels: - trailing_dot = '.' + trailing_dot = b"." result = [] size = 0 @@ -54,29 +56,33 @@ class IncrementalEncoder(codecs.BufferedIncrementalEncoder): size += len(label) # Join with U+002E - result_str = '.'.join(result) + trailing_dot # type: ignore + result_bytes = b".".join(result) + trailing_dot size += len(trailing_dot) - return result_str, size + return result_bytes, size + class IncrementalDecoder(codecs.BufferedIncrementalDecoder): - def _buffer_decode(self, data: str, errors: str, final: bool) -> Tuple[str, int]: # type: ignore - if errors != 'strict': - raise IDNAError('Unsupported error handling \"{}\"'.format(errors)) + def _buffer_decode(self, data: Any, errors: str, final: bool) -> Tuple[str, int]: + if errors != "strict": + raise IDNAError('Unsupported error handling "{}"'.format(errors)) if not data: - return ('', 0) + return ("", 0) + + if not isinstance(data, str): + data = str(data, "ascii") labels = _unicode_dots_re.split(data) - trailing_dot = '' + trailing_dot = "" if labels: if not labels[-1]: - trailing_dot = '.' + trailing_dot = "." del labels[-1] elif not final: # Keep potentially unfinished label until the next call del labels[-1] if labels: - trailing_dot = '.' + trailing_dot = "." result = [] size = 0 @@ -86,7 +92,7 @@ class IncrementalDecoder(codecs.BufferedIncrementalDecoder): size += 1 size += len(label) - result_str = '.'.join(result) + trailing_dot + result_str = ".".join(result) + trailing_dot size += len(trailing_dot) return (result_str, size) @@ -99,14 +105,18 @@ class StreamReader(Codec, codecs.StreamReader): pass -def getregentry() -> codecs.CodecInfo: - # Compatibility as a search_function for codecs.register() +def search_function(name: str) -> Optional[codecs.CodecInfo]: + if name != "idna2008": + return None return codecs.CodecInfo( - name='idna', - encode=Codec().encode, # type: ignore - decode=Codec().decode, # type: ignore + name=name, + encode=Codec().encode, + decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) + + +codecs.register(search_function) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/compat.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/compat.py index 786e6bd..1df9f2a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/compat.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/compat.py @@ -1,13 +1,15 @@ -from .core import * -from .codec import * from typing import Any, Union +from .core import decode, encode + + def ToASCII(label: str) -> bytes: return encode(label) + def ToUnicode(label: Union[bytes, bytearray]) -> str: return decode(label) -def nameprep(s: Any) -> None: - raise NotImplementedError('IDNA 2008 does not utilise nameprep protocol') +def nameprep(s: Any) -> None: + raise NotImplementedError("IDNA 2008 does not utilise nameprep protocol") diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/core.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/core.py index 4f30037..9115f12 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/core.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/core.py @@ -1,31 +1,37 @@ -from . import idnadata import bisect -import unicodedata import re -from typing import Union, Optional +import unicodedata +from typing import Optional, Union + +from . import idnadata from .intranges import intranges_contain _virama_combining_class = 9 -_alabel_prefix = b'xn--' -_unicode_dots_re = re.compile('[\u002e\u3002\uff0e\uff61]') +_alabel_prefix = b"xn--" +_unicode_dots_re = re.compile("[\u002e\u3002\uff0e\uff61]") + class IDNAError(UnicodeError): - """ Base exception for all IDNA-encoding related problems """ + """Base exception for all IDNA-encoding related problems""" + pass class IDNABidiError(IDNAError): - """ Exception when bidirectional requirements are not satisfied """ + """Exception when bidirectional requirements are not satisfied""" + pass class InvalidCodepoint(IDNAError): - """ Exception when a disallowed or unallocated codepoint is used """ + """Exception when a disallowed or unallocated codepoint is used""" + pass class InvalidCodepointContext(IDNAError): - """ Exception when the codepoint is not valid in the context it is used """ + """Exception when the codepoint is not valid in the context it is used""" + pass @@ -33,17 +39,20 @@ def _combining_class(cp: int) -> int: v = unicodedata.combining(chr(cp)) if v == 0: if not unicodedata.name(chr(cp)): - raise ValueError('Unknown character in unicodedata') + raise ValueError("Unknown character in unicodedata") return v + def _is_script(cp: str, script: str) -> bool: return intranges_contain(ord(cp), idnadata.scripts[script]) + def _punycode(s: str) -> bytes: - return s.encode('punycode') + return s.encode("punycode") + def _unot(s: int) -> str: - return 'U+{:04X}'.format(s) + return "U+{:04X}".format(s) def valid_label_length(label: Union[bytes, str]) -> bool: @@ -61,158 +70,170 @@ def valid_string_length(label: Union[bytes, str], trailing_dot: bool) -> bool: def check_bidi(label: str, check_ltr: bool = False) -> bool: # Bidi rules should only be applied if string contains RTL characters bidi_label = False - for (idx, cp) in enumerate(label, 1): + for idx, cp in enumerate(label, 1): direction = unicodedata.bidirectional(cp) - if direction == '': + if direction == "": # String likely comes from a newer version of Unicode - raise IDNABidiError('Unknown directionality in label {} at position {}'.format(repr(label), idx)) - if direction in ['R', 'AL', 'AN']: + raise IDNABidiError("Unknown directionality in label {} at position {}".format(repr(label), idx)) + if direction in ["R", "AL", "AN"]: bidi_label = True if not bidi_label and not check_ltr: return True # Bidi rule 1 direction = unicodedata.bidirectional(label[0]) - if direction in ['R', 'AL']: + if direction in ["R", "AL"]: rtl = True - elif direction == 'L': + elif direction == "L": rtl = False else: - raise IDNABidiError('First codepoint in label {} must be directionality L, R or AL'.format(repr(label))) + raise IDNABidiError("First codepoint in label {} must be directionality L, R or AL".format(repr(label))) valid_ending = False - number_type = None # type: Optional[str] - for (idx, cp) in enumerate(label, 1): + number_type: Optional[str] = None + for idx, cp in enumerate(label, 1): direction = unicodedata.bidirectional(cp) if rtl: # Bidi rule 2 - if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']: - raise IDNABidiError('Invalid direction for codepoint at position {} in a right-to-left label'.format(idx)) + if direction not in [ + "R", + "AL", + "AN", + "EN", + "ES", + "CS", + "ET", + "ON", + "BN", + "NSM", + ]: + raise IDNABidiError("Invalid direction for codepoint at position {} in a right-to-left label".format(idx)) # Bidi rule 3 - if direction in ['R', 'AL', 'EN', 'AN']: + if direction in ["R", "AL", "EN", "AN"]: valid_ending = True - elif direction != 'NSM': + elif direction != "NSM": valid_ending = False # Bidi rule 4 - if direction in ['AN', 'EN']: + if direction in ["AN", "EN"]: if not number_type: number_type = direction else: if number_type != direction: - raise IDNABidiError('Can not mix numeral types in a right-to-left label') + raise IDNABidiError("Can not mix numeral types in a right-to-left label") else: # Bidi rule 5 - if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']: - raise IDNABidiError('Invalid direction for codepoint at position {} in a left-to-right label'.format(idx)) + if direction not in ["L", "EN", "ES", "CS", "ET", "ON", "BN", "NSM"]: + raise IDNABidiError("Invalid direction for codepoint at position {} in a left-to-right label".format(idx)) # Bidi rule 6 - if direction in ['L', 'EN']: + if direction in ["L", "EN"]: valid_ending = True - elif direction != 'NSM': + elif direction != "NSM": valid_ending = False if not valid_ending: - raise IDNABidiError('Label ends with illegal codepoint directionality') + raise IDNABidiError("Label ends with illegal codepoint directionality") return True def check_initial_combiner(label: str) -> bool: - if unicodedata.category(label[0])[0] == 'M': - raise IDNAError('Label begins with an illegal combining character') + if unicodedata.category(label[0])[0] == "M": + raise IDNAError("Label begins with an illegal combining character") return True def check_hyphen_ok(label: str) -> bool: - if label[2:4] == '--': - raise IDNAError('Label has disallowed hyphens in 3rd and 4th position') - if label[0] == '-' or label[-1] == '-': - raise IDNAError('Label must not start or end with a hyphen') + if label[2:4] == "--": + raise IDNAError("Label has disallowed hyphens in 3rd and 4th position") + if label[0] == "-" or label[-1] == "-": + raise IDNAError("Label must not start or end with a hyphen") return True def check_nfc(label: str) -> None: - if unicodedata.normalize('NFC', label) != label: - raise IDNAError('Label must be in Normalization Form C') + if unicodedata.normalize("NFC", label) != label: + raise IDNAError("Label must be in Normalization Form C") def valid_contextj(label: str, pos: int) -> bool: cp_value = ord(label[pos]) - if cp_value == 0x200c: - + if cp_value == 0x200C: if pos > 0: if _combining_class(ord(label[pos - 1])) == _virama_combining_class: return True ok = False - for i in range(pos-1, -1, -1): + for i in range(pos - 1, -1, -1): joining_type = idnadata.joining_types.get(ord(label[i])) - if joining_type == ord('T'): + if joining_type == ord("T"): continue - if joining_type in [ord('L'), ord('D')]: + elif joining_type in [ord("L"), ord("D")]: ok = True break + else: + break if not ok: return False ok = False - for i in range(pos+1, len(label)): + for i in range(pos + 1, len(label)): joining_type = idnadata.joining_types.get(ord(label[i])) - if joining_type == ord('T'): + if joining_type == ord("T"): continue - if joining_type in [ord('R'), ord('D')]: + elif joining_type in [ord("R"), ord("D")]: ok = True break + else: + break return ok - if cp_value == 0x200d: - + if cp_value == 0x200D: if pos > 0: if _combining_class(ord(label[pos - 1])) == _virama_combining_class: return True return False else: - return False def valid_contexto(label: str, pos: int, exception: bool = False) -> bool: cp_value = ord(label[pos]) - if cp_value == 0x00b7: - if 0 < pos < len(label)-1: - if ord(label[pos - 1]) == 0x006c and ord(label[pos + 1]) == 0x006c: + if cp_value == 0x00B7: + if 0 < pos < len(label) - 1: + if ord(label[pos - 1]) == 0x006C and ord(label[pos + 1]) == 0x006C: return True return False elif cp_value == 0x0375: - if pos < len(label)-1 and len(label) > 1: - return _is_script(label[pos + 1], 'Greek') + if pos < len(label) - 1 and len(label) > 1: + return _is_script(label[pos + 1], "Greek") return False - elif cp_value == 0x05f3 or cp_value == 0x05f4: + elif cp_value == 0x05F3 or cp_value == 0x05F4: if pos > 0: - return _is_script(label[pos - 1], 'Hebrew') + return _is_script(label[pos - 1], "Hebrew") return False - elif cp_value == 0x30fb: + elif cp_value == 0x30FB: for cp in label: - if cp == '\u30fb': + if cp == "\u30fb": continue - if _is_script(cp, 'Hiragana') or _is_script(cp, 'Katakana') or _is_script(cp, 'Han'): + if _is_script(cp, "Hiragana") or _is_script(cp, "Katakana") or _is_script(cp, "Han"): return True return False elif 0x660 <= cp_value <= 0x669: for cp in label: - if 0x6f0 <= ord(cp) <= 0x06f9: + if 0x6F0 <= ord(cp) <= 0x06F9: return False return True - elif 0x6f0 <= cp_value <= 0x6f9: + elif 0x6F0 <= cp_value <= 0x6F9: for cp in label: if 0x660 <= ord(cp) <= 0x0669: return False @@ -223,55 +244,58 @@ def valid_contexto(label: str, pos: int, exception: bool = False) -> bool: def check_label(label: Union[str, bytes, bytearray]) -> None: if isinstance(label, (bytes, bytearray)): - label = label.decode('utf-8') + label = label.decode("utf-8") if len(label) == 0: - raise IDNAError('Empty Label') + raise IDNAError("Empty Label") check_nfc(label) check_hyphen_ok(label) check_initial_combiner(label) - for (pos, cp) in enumerate(label): + for pos, cp in enumerate(label): cp_value = ord(cp) - if intranges_contain(cp_value, idnadata.codepoint_classes['PVALID']): + if intranges_contain(cp_value, idnadata.codepoint_classes["PVALID"]): continue - elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTJ']): + elif intranges_contain(cp_value, idnadata.codepoint_classes["CONTEXTJ"]): try: if not valid_contextj(label, pos): - raise InvalidCodepointContext('Joiner {} not allowed at position {} in {}'.format( - _unot(cp_value), pos+1, repr(label))) + raise InvalidCodepointContext( + "Joiner {} not allowed at position {} in {}".format(_unot(cp_value), pos + 1, repr(label)) + ) except ValueError: - raise IDNAError('Unknown codepoint adjacent to joiner {} at position {} in {}'.format( - _unot(cp_value), pos+1, repr(label))) - elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTO']): + raise IDNAError( + "Unknown codepoint adjacent to joiner {} at position {} in {}".format( + _unot(cp_value), pos + 1, repr(label) + ) + ) + elif intranges_contain(cp_value, idnadata.codepoint_classes["CONTEXTO"]): if not valid_contexto(label, pos): - raise InvalidCodepointContext('Codepoint {} not allowed at position {} in {}'.format(_unot(cp_value), pos+1, repr(label))) + raise InvalidCodepointContext( + "Codepoint {} not allowed at position {} in {}".format(_unot(cp_value), pos + 1, repr(label)) + ) else: - raise InvalidCodepoint('Codepoint {} at position {} of {} not allowed'.format(_unot(cp_value), pos+1, repr(label))) + raise InvalidCodepoint( + "Codepoint {} at position {} of {} not allowed".format(_unot(cp_value), pos + 1, repr(label)) + ) check_bidi(label) def alabel(label: str) -> bytes: try: - label_bytes = label.encode('ascii') + label_bytes = label.encode("ascii") ulabel(label_bytes) if not valid_label_length(label_bytes): - raise IDNAError('Label too long') + raise IDNAError("Label too long") return label_bytes except UnicodeEncodeError: pass - if not label: - raise IDNAError('No Input') - - label = str(label) check_label(label) - label_bytes = _punycode(label) - label_bytes = _alabel_prefix + label_bytes + label_bytes = _alabel_prefix + _punycode(label) if not valid_label_length(label_bytes): - raise IDNAError('Label too long') + raise IDNAError("Label too long") return label_bytes @@ -279,7 +303,7 @@ def alabel(label: str) -> bytes: def ulabel(label: Union[str, bytes, bytearray]) -> str: if not isinstance(label, (bytes, bytearray)): try: - label_bytes = label.encode('ascii') + label_bytes = label.encode("ascii") except UnicodeEncodeError: check_label(label) return label @@ -288,19 +312,19 @@ def ulabel(label: Union[str, bytes, bytearray]) -> str: label_bytes = label_bytes.lower() if label_bytes.startswith(_alabel_prefix): - label_bytes = label_bytes[len(_alabel_prefix):] + label_bytes = label_bytes[len(_alabel_prefix) :] if not label_bytes: - raise IDNAError('Malformed A-label, no Punycode eligible content found') - if label_bytes.decode('ascii')[-1] == '-': - raise IDNAError('A-label must not end with a hyphen') + raise IDNAError("Malformed A-label, no Punycode eligible content found") + if label_bytes.decode("ascii")[-1] == "-": + raise IDNAError("A-label must not end with a hyphen") else: check_label(label_bytes) - return label_bytes.decode('ascii') + return label_bytes.decode("ascii") try: - label = label_bytes.decode('punycode') + label = label_bytes.decode("punycode") except UnicodeError: - raise IDNAError('Invalid A-label') + raise IDNAError("Invalid A-label") check_label(label) return label @@ -308,52 +332,60 @@ def ulabel(label: Union[str, bytes, bytearray]) -> str: def uts46_remap(domain: str, std3_rules: bool = True, transitional: bool = False) -> str: """Re-map the characters in the string according to UTS46 processing.""" from .uts46data import uts46data - output = '' + + output = "" for pos, char in enumerate(domain): code_point = ord(char) try: - uts46row = uts46data[code_point if code_point < 256 else - bisect.bisect_left(uts46data, (code_point, 'Z')) - 1] + uts46row = uts46data[code_point if code_point < 256 else bisect.bisect_left(uts46data, (code_point, "Z")) - 1] status = uts46row[1] - replacement = None # type: Optional[str] + replacement: Optional[str] = None if len(uts46row) == 3: - replacement = uts46row[2] # type: ignore - if (status == 'V' or - (status == 'D' and not transitional) or - (status == '3' and not std3_rules and replacement is None)): + replacement = uts46row[2] + if ( + status == "V" + or (status == "D" and not transitional) + or (status == "3" and not std3_rules and replacement is None) + ): output += char - elif replacement is not None and (status == 'M' or - (status == '3' and not std3_rules) or - (status == 'D' and transitional)): + elif replacement is not None and ( + status == "M" or (status == "3" and not std3_rules) or (status == "D" and transitional) + ): output += replacement - elif status != 'I': + elif status != "I": raise IndexError() except IndexError: raise InvalidCodepoint( - 'Codepoint {} not allowed at position {} in {}'.format( - _unot(code_point), pos + 1, repr(domain))) + "Codepoint {} not allowed at position {} in {}".format(_unot(code_point), pos + 1, repr(domain)) + ) - return unicodedata.normalize('NFC', output) + return unicodedata.normalize("NFC", output) -def encode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False, transitional: bool = False) -> bytes: - if isinstance(s, (bytes, bytearray)): +def encode( + s: Union[str, bytes, bytearray], + strict: bool = False, + uts46: bool = False, + std3_rules: bool = False, + transitional: bool = False, +) -> bytes: + if not isinstance(s, str): try: - s = s.decode('ascii') + s = str(s, "ascii") except UnicodeDecodeError: - raise IDNAError('should pass a unicode string to the function rather than a byte string.') + raise IDNAError("should pass a unicode string to the function rather than a byte string.") if uts46: s = uts46_remap(s, std3_rules, transitional) trailing_dot = False result = [] if strict: - labels = s.split('.') + labels = s.split(".") else: labels = _unicode_dots_re.split(s) - if not labels or labels == ['']: - raise IDNAError('Empty domain') - if labels[-1] == '': + if not labels or labels == [""]: + raise IDNAError("Empty domain") + if labels[-1] == "": del labels[-1] trailing_dot = True for label in labels: @@ -361,21 +393,26 @@ def encode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = if s: result.append(s) else: - raise IDNAError('Empty label') + raise IDNAError("Empty label") if trailing_dot: - result.append(b'') - s = b'.'.join(result) + result.append(b"") + s = b".".join(result) if not valid_string_length(s, trailing_dot): - raise IDNAError('Domain too long') + raise IDNAError("Domain too long") return s -def decode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False) -> str: +def decode( + s: Union[str, bytes, bytearray], + strict: bool = False, + uts46: bool = False, + std3_rules: bool = False, +) -> str: try: - if isinstance(s, (bytes, bytearray)): - s = s.decode('ascii') + if not isinstance(s, str): + s = str(s, "ascii") except UnicodeDecodeError: - raise IDNAError('Invalid ASCII in A-label') + raise IDNAError("Invalid ASCII in A-label") if uts46: s = uts46_remap(s, std3_rules, False) trailing_dot = False @@ -383,9 +420,9 @@ def decode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = if not strict: labels = _unicode_dots_re.split(s) else: - labels = s.split('.') - if not labels or labels == ['']: - raise IDNAError('Empty domain') + labels = s.split(".") + if not labels or labels == [""]: + raise IDNAError("Empty domain") if not labels[-1]: del labels[-1] trailing_dot = True @@ -394,7 +431,7 @@ def decode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = if s: result.append(s) else: - raise IDNAError('Empty label') + raise IDNAError("Empty label") if trailing_dot: - result.append('') - return '.'.join(result) + result.append("") + return ".".join(result) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/idnadata.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/idnadata.py index 67db462..4be6004 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/idnadata.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/idnadata.py @@ -1,115 +1,290 @@ # This file is automatically generated by tools/idna-data -__version__ = '15.0.0' +__version__ = "15.1.0" scripts = { - 'Greek': ( + "Greek": ( 0x37000000374, 0x37500000378, - 0x37a0000037e, - 0x37f00000380, + 0x37A0000037E, + 0x37F00000380, 0x38400000385, 0x38600000387, - 0x3880000038b, - 0x38c0000038d, - 0x38e000003a2, - 0x3a3000003e2, - 0x3f000000400, - 0x1d2600001d2b, - 0x1d5d00001d62, - 0x1d6600001d6b, - 0x1dbf00001dc0, - 0x1f0000001f16, - 0x1f1800001f1e, - 0x1f2000001f46, - 0x1f4800001f4e, - 0x1f5000001f58, - 0x1f5900001f5a, - 0x1f5b00001f5c, - 0x1f5d00001f5e, - 0x1f5f00001f7e, - 0x1f8000001fb5, - 0x1fb600001fc5, - 0x1fc600001fd4, - 0x1fd600001fdc, - 0x1fdd00001ff0, - 0x1ff200001ff5, - 0x1ff600001fff, + 0x3880000038B, + 0x38C0000038D, + 0x38E000003A2, + 0x3A3000003E2, + 0x3F000000400, + 0x1D2600001D2B, + 0x1D5D00001D62, + 0x1D6600001D6B, + 0x1DBF00001DC0, + 0x1F0000001F16, + 0x1F1800001F1E, + 0x1F2000001F46, + 0x1F4800001F4E, + 0x1F5000001F58, + 0x1F5900001F5A, + 0x1F5B00001F5C, + 0x1F5D00001F5E, + 0x1F5F00001F7E, + 0x1F8000001FB5, + 0x1FB600001FC5, + 0x1FC600001FD4, + 0x1FD600001FDC, + 0x1FDD00001FF0, + 0x1FF200001FF5, + 0x1FF600001FFF, 0x212600002127, - 0xab650000ab66, - 0x101400001018f, - 0x101a0000101a1, - 0x1d2000001d246, + 0xAB650000AB66, + 0x101400001018F, + 0x101A0000101A1, + 0x1D2000001D246, ), - 'Han': ( - 0x2e8000002e9a, - 0x2e9b00002ef4, - 0x2f0000002fd6, + "Han": ( + 0x2E8000002E9A, + 0x2E9B00002EF4, + 0x2F0000002FD6, 0x300500003006, 0x300700003008, - 0x30210000302a, - 0x30380000303c, - 0x340000004dc0, - 0x4e000000a000, - 0xf9000000fa6e, - 0xfa700000fada, - 0x16fe200016fe4, - 0x16ff000016ff2, - 0x200000002a6e0, - 0x2a7000002b73a, - 0x2b7400002b81e, - 0x2b8200002cea2, - 0x2ceb00002ebe1, - 0x2f8000002fa1e, - 0x300000003134b, - 0x31350000323b0, + 0x30210000302A, + 0x30380000303C, + 0x340000004DC0, + 0x4E000000A000, + 0xF9000000FA6E, + 0xFA700000FADA, + 0x16FE200016FE4, + 0x16FF000016FF2, + 0x200000002A6E0, + 0x2A7000002B73A, + 0x2B7400002B81E, + 0x2B8200002CEA2, + 0x2CEB00002EBE1, + 0x2EBF00002EE5E, + 0x2F8000002FA1E, + 0x300000003134B, + 0x31350000323B0, ), - 'Hebrew': ( - 0x591000005c8, - 0x5d0000005eb, - 0x5ef000005f5, - 0xfb1d0000fb37, - 0xfb380000fb3d, - 0xfb3e0000fb3f, - 0xfb400000fb42, - 0xfb430000fb45, - 0xfb460000fb50, + "Hebrew": ( + 0x591000005C8, + 0x5D0000005EB, + 0x5EF000005F5, + 0xFB1D0000FB37, + 0xFB380000FB3D, + 0xFB3E0000FB3F, + 0xFB400000FB42, + 0xFB430000FB45, + 0xFB460000FB50, ), - 'Hiragana': ( + "Hiragana": ( 0x304100003097, - 0x309d000030a0, - 0x1b0010001b120, - 0x1b1320001b133, - 0x1b1500001b153, - 0x1f2000001f201, + 0x309D000030A0, + 0x1B0010001B120, + 0x1B1320001B133, + 0x1B1500001B153, + 0x1F2000001F201, ), - 'Katakana': ( - 0x30a1000030fb, - 0x30fd00003100, - 0x31f000003200, - 0x32d0000032ff, + "Katakana": ( + 0x30A1000030FB, + 0x30FD00003100, + 0x31F000003200, + 0x32D0000032FF, 0x330000003358, - 0xff660000ff70, - 0xff710000ff9e, - 0x1aff00001aff4, - 0x1aff50001affc, - 0x1affd0001afff, - 0x1b0000001b001, - 0x1b1200001b123, - 0x1b1550001b156, - 0x1b1640001b168, + 0xFF660000FF70, + 0xFF710000FF9E, + 0x1AFF00001AFF4, + 0x1AFF50001AFFC, + 0x1AFFD0001AFFF, + 0x1B0000001B001, + 0x1B1200001B123, + 0x1B1550001B156, + 0x1B1640001B168, ), } joining_types = { - 0x600: 85, - 0x601: 85, - 0x602: 85, - 0x603: 85, - 0x604: 85, - 0x605: 85, - 0x608: 85, - 0x60b: 85, + 0xAD: 84, + 0x300: 84, + 0x301: 84, + 0x302: 84, + 0x303: 84, + 0x304: 84, + 0x305: 84, + 0x306: 84, + 0x307: 84, + 0x308: 84, + 0x309: 84, + 0x30A: 84, + 0x30B: 84, + 0x30C: 84, + 0x30D: 84, + 0x30E: 84, + 0x30F: 84, + 0x310: 84, + 0x311: 84, + 0x312: 84, + 0x313: 84, + 0x314: 84, + 0x315: 84, + 0x316: 84, + 0x317: 84, + 0x318: 84, + 0x319: 84, + 0x31A: 84, + 0x31B: 84, + 0x31C: 84, + 0x31D: 84, + 0x31E: 84, + 0x31F: 84, + 0x320: 84, + 0x321: 84, + 0x322: 84, + 0x323: 84, + 0x324: 84, + 0x325: 84, + 0x326: 84, + 0x327: 84, + 0x328: 84, + 0x329: 84, + 0x32A: 84, + 0x32B: 84, + 0x32C: 84, + 0x32D: 84, + 0x32E: 84, + 0x32F: 84, + 0x330: 84, + 0x331: 84, + 0x332: 84, + 0x333: 84, + 0x334: 84, + 0x335: 84, + 0x336: 84, + 0x337: 84, + 0x338: 84, + 0x339: 84, + 0x33A: 84, + 0x33B: 84, + 0x33C: 84, + 0x33D: 84, + 0x33E: 84, + 0x33F: 84, + 0x340: 84, + 0x341: 84, + 0x342: 84, + 0x343: 84, + 0x344: 84, + 0x345: 84, + 0x346: 84, + 0x347: 84, + 0x348: 84, + 0x349: 84, + 0x34A: 84, + 0x34B: 84, + 0x34C: 84, + 0x34D: 84, + 0x34E: 84, + 0x34F: 84, + 0x350: 84, + 0x351: 84, + 0x352: 84, + 0x353: 84, + 0x354: 84, + 0x355: 84, + 0x356: 84, + 0x357: 84, + 0x358: 84, + 0x359: 84, + 0x35A: 84, + 0x35B: 84, + 0x35C: 84, + 0x35D: 84, + 0x35E: 84, + 0x35F: 84, + 0x360: 84, + 0x361: 84, + 0x362: 84, + 0x363: 84, + 0x364: 84, + 0x365: 84, + 0x366: 84, + 0x367: 84, + 0x368: 84, + 0x369: 84, + 0x36A: 84, + 0x36B: 84, + 0x36C: 84, + 0x36D: 84, + 0x36E: 84, + 0x36F: 84, + 0x483: 84, + 0x484: 84, + 0x485: 84, + 0x486: 84, + 0x487: 84, + 0x488: 84, + 0x489: 84, + 0x591: 84, + 0x592: 84, + 0x593: 84, + 0x594: 84, + 0x595: 84, + 0x596: 84, + 0x597: 84, + 0x598: 84, + 0x599: 84, + 0x59A: 84, + 0x59B: 84, + 0x59C: 84, + 0x59D: 84, + 0x59E: 84, + 0x59F: 84, + 0x5A0: 84, + 0x5A1: 84, + 0x5A2: 84, + 0x5A3: 84, + 0x5A4: 84, + 0x5A5: 84, + 0x5A6: 84, + 0x5A7: 84, + 0x5A8: 84, + 0x5A9: 84, + 0x5AA: 84, + 0x5AB: 84, + 0x5AC: 84, + 0x5AD: 84, + 0x5AE: 84, + 0x5AF: 84, + 0x5B0: 84, + 0x5B1: 84, + 0x5B2: 84, + 0x5B3: 84, + 0x5B4: 84, + 0x5B5: 84, + 0x5B6: 84, + 0x5B7: 84, + 0x5B8: 84, + 0x5B9: 84, + 0x5BA: 84, + 0x5BB: 84, + 0x5BC: 84, + 0x5BD: 84, + 0x5BF: 84, + 0x5C1: 84, + 0x5C2: 84, + 0x5C4: 84, + 0x5C5: 84, + 0x5C7: 84, + 0x610: 84, + 0x611: 84, + 0x612: 84, + 0x613: 84, + 0x614: 84, + 0x615: 84, + 0x616: 84, + 0x617: 84, + 0x618: 84, + 0x619: 84, + 0x61A: 84, + 0x61C: 84, 0x620: 68, - 0x621: 85, 0x622: 82, 0x623: 82, 0x624: 82, @@ -118,12 +293,12 @@ joining_types = { 0x627: 82, 0x628: 68, 0x629: 82, - 0x62a: 68, - 0x62b: 68, - 0x62c: 68, - 0x62d: 68, - 0x62e: 68, - 0x62f: 82, + 0x62A: 68, + 0x62B: 68, + 0x62C: 68, + 0x62D: 68, + 0x62E: 68, + 0x62F: 82, 0x630: 82, 0x631: 82, 0x632: 82, @@ -134,12 +309,12 @@ joining_types = { 0x637: 68, 0x638: 68, 0x639: 68, - 0x63a: 68, - 0x63b: 68, - 0x63c: 68, - 0x63d: 68, - 0x63e: 68, - 0x63f: 68, + 0x63A: 68, + 0x63B: 68, + 0x63C: 68, + 0x63D: 68, + 0x63E: 68, + 0x63F: 68, 0x640: 67, 0x641: 68, 0x642: 68, @@ -150,24 +325,45 @@ joining_types = { 0x647: 68, 0x648: 82, 0x649: 68, - 0x64a: 68, - 0x66e: 68, - 0x66f: 68, + 0x64A: 68, + 0x64B: 84, + 0x64C: 84, + 0x64D: 84, + 0x64E: 84, + 0x64F: 84, + 0x650: 84, + 0x651: 84, + 0x652: 84, + 0x653: 84, + 0x654: 84, + 0x655: 84, + 0x656: 84, + 0x657: 84, + 0x658: 84, + 0x659: 84, + 0x65A: 84, + 0x65B: 84, + 0x65C: 84, + 0x65D: 84, + 0x65E: 84, + 0x65F: 84, + 0x66E: 68, + 0x66F: 68, + 0x670: 84, 0x671: 82, 0x672: 82, 0x673: 82, - 0x674: 85, 0x675: 82, 0x676: 82, 0x677: 82, 0x678: 68, 0x679: 68, - 0x67a: 68, - 0x67b: 68, - 0x67c: 68, - 0x67d: 68, - 0x67e: 68, - 0x67f: 68, + 0x67A: 68, + 0x67B: 68, + 0x67C: 68, + 0x67D: 68, + 0x67E: 68, + 0x67F: 68, 0x680: 68, 0x681: 68, 0x682: 68, @@ -178,12 +374,12 @@ joining_types = { 0x687: 68, 0x688: 82, 0x689: 82, - 0x68a: 82, - 0x68b: 82, - 0x68c: 82, - 0x68d: 82, - 0x68e: 82, - 0x68f: 82, + 0x68A: 82, + 0x68B: 82, + 0x68C: 82, + 0x68D: 82, + 0x68E: 82, + 0x68F: 82, 0x690: 82, 0x691: 82, 0x692: 82, @@ -194,74 +390,93 @@ joining_types = { 0x697: 82, 0x698: 82, 0x699: 82, - 0x69a: 68, - 0x69b: 68, - 0x69c: 68, - 0x69d: 68, - 0x69e: 68, - 0x69f: 68, - 0x6a0: 68, - 0x6a1: 68, - 0x6a2: 68, - 0x6a3: 68, - 0x6a4: 68, - 0x6a5: 68, - 0x6a6: 68, - 0x6a7: 68, - 0x6a8: 68, - 0x6a9: 68, - 0x6aa: 68, - 0x6ab: 68, - 0x6ac: 68, - 0x6ad: 68, - 0x6ae: 68, - 0x6af: 68, - 0x6b0: 68, - 0x6b1: 68, - 0x6b2: 68, - 0x6b3: 68, - 0x6b4: 68, - 0x6b5: 68, - 0x6b6: 68, - 0x6b7: 68, - 0x6b8: 68, - 0x6b9: 68, - 0x6ba: 68, - 0x6bb: 68, - 0x6bc: 68, - 0x6bd: 68, - 0x6be: 68, - 0x6bf: 68, - 0x6c0: 82, - 0x6c1: 68, - 0x6c2: 68, - 0x6c3: 82, - 0x6c4: 82, - 0x6c5: 82, - 0x6c6: 82, - 0x6c7: 82, - 0x6c8: 82, - 0x6c9: 82, - 0x6ca: 82, - 0x6cb: 82, - 0x6cc: 68, - 0x6cd: 82, - 0x6ce: 68, - 0x6cf: 82, - 0x6d0: 68, - 0x6d1: 68, - 0x6d2: 82, - 0x6d3: 82, - 0x6d5: 82, - 0x6dd: 85, - 0x6ee: 82, - 0x6ef: 82, - 0x6fa: 68, - 0x6fb: 68, - 0x6fc: 68, - 0x6ff: 68, - 0x70f: 84, + 0x69A: 68, + 0x69B: 68, + 0x69C: 68, + 0x69D: 68, + 0x69E: 68, + 0x69F: 68, + 0x6A0: 68, + 0x6A1: 68, + 0x6A2: 68, + 0x6A3: 68, + 0x6A4: 68, + 0x6A5: 68, + 0x6A6: 68, + 0x6A7: 68, + 0x6A8: 68, + 0x6A9: 68, + 0x6AA: 68, + 0x6AB: 68, + 0x6AC: 68, + 0x6AD: 68, + 0x6AE: 68, + 0x6AF: 68, + 0x6B0: 68, + 0x6B1: 68, + 0x6B2: 68, + 0x6B3: 68, + 0x6B4: 68, + 0x6B5: 68, + 0x6B6: 68, + 0x6B7: 68, + 0x6B8: 68, + 0x6B9: 68, + 0x6BA: 68, + 0x6BB: 68, + 0x6BC: 68, + 0x6BD: 68, + 0x6BE: 68, + 0x6BF: 68, + 0x6C0: 82, + 0x6C1: 68, + 0x6C2: 68, + 0x6C3: 82, + 0x6C4: 82, + 0x6C5: 82, + 0x6C6: 82, + 0x6C7: 82, + 0x6C8: 82, + 0x6C9: 82, + 0x6CA: 82, + 0x6CB: 82, + 0x6CC: 68, + 0x6CD: 82, + 0x6CE: 68, + 0x6CF: 82, + 0x6D0: 68, + 0x6D1: 68, + 0x6D2: 82, + 0x6D3: 82, + 0x6D5: 82, + 0x6D6: 84, + 0x6D7: 84, + 0x6D8: 84, + 0x6D9: 84, + 0x6DA: 84, + 0x6DB: 84, + 0x6DC: 84, + 0x6DF: 84, + 0x6E0: 84, + 0x6E1: 84, + 0x6E2: 84, + 0x6E3: 84, + 0x6E4: 84, + 0x6E7: 84, + 0x6E8: 84, + 0x6EA: 84, + 0x6EB: 84, + 0x6EC: 84, + 0x6ED: 84, + 0x6EE: 82, + 0x6EF: 82, + 0x6FA: 68, + 0x6FB: 68, + 0x6FC: 68, + 0x6FF: 68, + 0x70F: 84, 0x710: 82, + 0x711: 84, 0x712: 68, 0x713: 68, 0x714: 68, @@ -270,12 +485,12 @@ joining_types = { 0x717: 82, 0x718: 82, 0x719: 82, - 0x71a: 68, - 0x71b: 68, - 0x71c: 68, - 0x71d: 68, - 0x71e: 82, - 0x71f: 68, + 0x71A: 68, + 0x71B: 68, + 0x71C: 68, + 0x71D: 68, + 0x71E: 82, + 0x71F: 68, 0x720: 68, 0x721: 68, 0x722: 68, @@ -286,15 +501,42 @@ joining_types = { 0x727: 68, 0x728: 82, 0x729: 68, - 0x72a: 82, - 0x72b: 68, - 0x72c: 82, - 0x72d: 68, - 0x72e: 68, - 0x72f: 82, - 0x74d: 82, - 0x74e: 68, - 0x74f: 68, + 0x72A: 82, + 0x72B: 68, + 0x72C: 82, + 0x72D: 68, + 0x72E: 68, + 0x72F: 82, + 0x730: 84, + 0x731: 84, + 0x732: 84, + 0x733: 84, + 0x734: 84, + 0x735: 84, + 0x736: 84, + 0x737: 84, + 0x738: 84, + 0x739: 84, + 0x73A: 84, + 0x73B: 84, + 0x73C: 84, + 0x73D: 84, + 0x73E: 84, + 0x73F: 84, + 0x740: 84, + 0x741: 84, + 0x742: 84, + 0x743: 84, + 0x744: 84, + 0x745: 84, + 0x746: 84, + 0x747: 84, + 0x748: 84, + 0x749: 84, + 0x74A: 84, + 0x74D: 82, + 0x74E: 68, + 0x74F: 68, 0x750: 68, 0x751: 68, 0x752: 68, @@ -305,12 +547,12 @@ joining_types = { 0x757: 68, 0x758: 68, 0x759: 82, - 0x75a: 82, - 0x75b: 82, - 0x75c: 68, - 0x75d: 68, - 0x75e: 68, - 0x75f: 68, + 0x75A: 82, + 0x75B: 82, + 0x75C: 68, + 0x75D: 68, + 0x75E: 68, + 0x75F: 68, 0x760: 68, 0x761: 68, 0x762: 68, @@ -321,12 +563,12 @@ joining_types = { 0x767: 68, 0x768: 68, 0x769: 68, - 0x76a: 68, - 0x76b: 82, - 0x76c: 82, - 0x76d: 68, - 0x76e: 68, - 0x76f: 68, + 0x76A: 68, + 0x76B: 82, + 0x76C: 82, + 0x76D: 68, + 0x76E: 68, + 0x76F: 68, 0x770: 68, 0x771: 82, 0x772: 68, @@ -337,46 +579,88 @@ joining_types = { 0x777: 68, 0x778: 82, 0x779: 82, - 0x77a: 68, - 0x77b: 68, - 0x77c: 68, - 0x77d: 68, - 0x77e: 68, - 0x77f: 68, - 0x7ca: 68, - 0x7cb: 68, - 0x7cc: 68, - 0x7cd: 68, - 0x7ce: 68, - 0x7cf: 68, - 0x7d0: 68, - 0x7d1: 68, - 0x7d2: 68, - 0x7d3: 68, - 0x7d4: 68, - 0x7d5: 68, - 0x7d6: 68, - 0x7d7: 68, - 0x7d8: 68, - 0x7d9: 68, - 0x7da: 68, - 0x7db: 68, - 0x7dc: 68, - 0x7dd: 68, - 0x7de: 68, - 0x7df: 68, - 0x7e0: 68, - 0x7e1: 68, - 0x7e2: 68, - 0x7e3: 68, - 0x7e4: 68, - 0x7e5: 68, - 0x7e6: 68, - 0x7e7: 68, - 0x7e8: 68, - 0x7e9: 68, - 0x7ea: 68, - 0x7fa: 67, + 0x77A: 68, + 0x77B: 68, + 0x77C: 68, + 0x77D: 68, + 0x77E: 68, + 0x77F: 68, + 0x7A6: 84, + 0x7A7: 84, + 0x7A8: 84, + 0x7A9: 84, + 0x7AA: 84, + 0x7AB: 84, + 0x7AC: 84, + 0x7AD: 84, + 0x7AE: 84, + 0x7AF: 84, + 0x7B0: 84, + 0x7CA: 68, + 0x7CB: 68, + 0x7CC: 68, + 0x7CD: 68, + 0x7CE: 68, + 0x7CF: 68, + 0x7D0: 68, + 0x7D1: 68, + 0x7D2: 68, + 0x7D3: 68, + 0x7D4: 68, + 0x7D5: 68, + 0x7D6: 68, + 0x7D7: 68, + 0x7D8: 68, + 0x7D9: 68, + 0x7DA: 68, + 0x7DB: 68, + 0x7DC: 68, + 0x7DD: 68, + 0x7DE: 68, + 0x7DF: 68, + 0x7E0: 68, + 0x7E1: 68, + 0x7E2: 68, + 0x7E3: 68, + 0x7E4: 68, + 0x7E5: 68, + 0x7E6: 68, + 0x7E7: 68, + 0x7E8: 68, + 0x7E9: 68, + 0x7EA: 68, + 0x7EB: 84, + 0x7EC: 84, + 0x7ED: 84, + 0x7EE: 84, + 0x7EF: 84, + 0x7F0: 84, + 0x7F1: 84, + 0x7F2: 84, + 0x7F3: 84, + 0x7FA: 67, + 0x7FD: 84, + 0x816: 84, + 0x817: 84, + 0x818: 84, + 0x819: 84, + 0x81B: 84, + 0x81C: 84, + 0x81D: 84, + 0x81E: 84, + 0x81F: 84, + 0x820: 84, + 0x821: 84, + 0x822: 84, + 0x823: 84, + 0x825: 84, + 0x826: 84, + 0x827: 84, + 0x829: 84, + 0x82A: 84, + 0x82B: 84, + 0x82C: 84, + 0x82D: 84, 0x840: 82, 0x841: 68, 0x842: 68, @@ -387,12 +671,12 @@ joining_types = { 0x847: 82, 0x848: 68, 0x849: 82, - 0x84a: 68, - 0x84b: 68, - 0x84c: 68, - 0x84d: 68, - 0x84e: 68, - 0x84f: 68, + 0x84A: 68, + 0x84B: 68, + 0x84C: 68, + 0x84D: 68, + 0x84E: 68, + 0x84F: 68, 0x850: 68, 0x851: 68, 0x852: 68, @@ -402,17 +686,18 @@ joining_types = { 0x856: 82, 0x857: 82, 0x858: 82, + 0x859: 84, + 0x85A: 84, + 0x85B: 84, 0x860: 68, - 0x861: 85, 0x862: 68, 0x863: 68, 0x864: 68, 0x865: 68, - 0x866: 85, 0x867: 82, 0x868: 68, 0x869: 82, - 0x86a: 82, + 0x86A: 82, 0x870: 82, 0x871: 82, 0x872: 82, @@ -423,12 +708,12 @@ joining_types = { 0x877: 82, 0x878: 82, 0x879: 82, - 0x87a: 82, - 0x87b: 82, - 0x87c: 82, - 0x87d: 82, - 0x87e: 82, - 0x87f: 82, + 0x87A: 82, + 0x87B: 82, + 0x87C: 82, + 0x87D: 82, + 0x87E: 82, + 0x87F: 82, 0x880: 82, 0x881: 82, 0x882: 82, @@ -436,62 +721,411 @@ joining_types = { 0x884: 67, 0x885: 67, 0x886: 68, - 0x887: 85, - 0x888: 85, 0x889: 68, - 0x88a: 68, - 0x88b: 68, - 0x88c: 68, - 0x88d: 68, - 0x88e: 82, - 0x890: 85, - 0x891: 85, - 0x8a0: 68, - 0x8a1: 68, - 0x8a2: 68, - 0x8a3: 68, - 0x8a4: 68, - 0x8a5: 68, - 0x8a6: 68, - 0x8a7: 68, - 0x8a8: 68, - 0x8a9: 68, - 0x8aa: 82, - 0x8ab: 82, - 0x8ac: 82, - 0x8ad: 85, - 0x8ae: 82, - 0x8af: 68, - 0x8b0: 68, - 0x8b1: 82, - 0x8b2: 82, - 0x8b3: 68, - 0x8b4: 68, - 0x8b5: 68, - 0x8b6: 68, - 0x8b7: 68, - 0x8b8: 68, - 0x8b9: 82, - 0x8ba: 68, - 0x8bb: 68, - 0x8bc: 68, - 0x8bd: 68, - 0x8be: 68, - 0x8bf: 68, - 0x8c0: 68, - 0x8c1: 68, - 0x8c2: 68, - 0x8c3: 68, - 0x8c4: 68, - 0x8c5: 68, - 0x8c6: 68, - 0x8c7: 68, - 0x8c8: 68, - 0x8e2: 85, - 0x1806: 85, + 0x88A: 68, + 0x88B: 68, + 0x88C: 68, + 0x88D: 68, + 0x88E: 82, + 0x898: 84, + 0x899: 84, + 0x89A: 84, + 0x89B: 84, + 0x89C: 84, + 0x89D: 84, + 0x89E: 84, + 0x89F: 84, + 0x8A0: 68, + 0x8A1: 68, + 0x8A2: 68, + 0x8A3: 68, + 0x8A4: 68, + 0x8A5: 68, + 0x8A6: 68, + 0x8A7: 68, + 0x8A8: 68, + 0x8A9: 68, + 0x8AA: 82, + 0x8AB: 82, + 0x8AC: 82, + 0x8AE: 82, + 0x8AF: 68, + 0x8B0: 68, + 0x8B1: 82, + 0x8B2: 82, + 0x8B3: 68, + 0x8B4: 68, + 0x8B5: 68, + 0x8B6: 68, + 0x8B7: 68, + 0x8B8: 68, + 0x8B9: 82, + 0x8BA: 68, + 0x8BB: 68, + 0x8BC: 68, + 0x8BD: 68, + 0x8BE: 68, + 0x8BF: 68, + 0x8C0: 68, + 0x8C1: 68, + 0x8C2: 68, + 0x8C3: 68, + 0x8C4: 68, + 0x8C5: 68, + 0x8C6: 68, + 0x8C7: 68, + 0x8C8: 68, + 0x8CA: 84, + 0x8CB: 84, + 0x8CC: 84, + 0x8CD: 84, + 0x8CE: 84, + 0x8CF: 84, + 0x8D0: 84, + 0x8D1: 84, + 0x8D2: 84, + 0x8D3: 84, + 0x8D4: 84, + 0x8D5: 84, + 0x8D6: 84, + 0x8D7: 84, + 0x8D8: 84, + 0x8D9: 84, + 0x8DA: 84, + 0x8DB: 84, + 0x8DC: 84, + 0x8DD: 84, + 0x8DE: 84, + 0x8DF: 84, + 0x8E0: 84, + 0x8E1: 84, + 0x8E3: 84, + 0x8E4: 84, + 0x8E5: 84, + 0x8E6: 84, + 0x8E7: 84, + 0x8E8: 84, + 0x8E9: 84, + 0x8EA: 84, + 0x8EB: 84, + 0x8EC: 84, + 0x8ED: 84, + 0x8EE: 84, + 0x8EF: 84, + 0x8F0: 84, + 0x8F1: 84, + 0x8F2: 84, + 0x8F3: 84, + 0x8F4: 84, + 0x8F5: 84, + 0x8F6: 84, + 0x8F7: 84, + 0x8F8: 84, + 0x8F9: 84, + 0x8FA: 84, + 0x8FB: 84, + 0x8FC: 84, + 0x8FD: 84, + 0x8FE: 84, + 0x8FF: 84, + 0x900: 84, + 0x901: 84, + 0x902: 84, + 0x93A: 84, + 0x93C: 84, + 0x941: 84, + 0x942: 84, + 0x943: 84, + 0x944: 84, + 0x945: 84, + 0x946: 84, + 0x947: 84, + 0x948: 84, + 0x94D: 84, + 0x951: 84, + 0x952: 84, + 0x953: 84, + 0x954: 84, + 0x955: 84, + 0x956: 84, + 0x957: 84, + 0x962: 84, + 0x963: 84, + 0x981: 84, + 0x9BC: 84, + 0x9C1: 84, + 0x9C2: 84, + 0x9C3: 84, + 0x9C4: 84, + 0x9CD: 84, + 0x9E2: 84, + 0x9E3: 84, + 0x9FE: 84, + 0xA01: 84, + 0xA02: 84, + 0xA3C: 84, + 0xA41: 84, + 0xA42: 84, + 0xA47: 84, + 0xA48: 84, + 0xA4B: 84, + 0xA4C: 84, + 0xA4D: 84, + 0xA51: 84, + 0xA70: 84, + 0xA71: 84, + 0xA75: 84, + 0xA81: 84, + 0xA82: 84, + 0xABC: 84, + 0xAC1: 84, + 0xAC2: 84, + 0xAC3: 84, + 0xAC4: 84, + 0xAC5: 84, + 0xAC7: 84, + 0xAC8: 84, + 0xACD: 84, + 0xAE2: 84, + 0xAE3: 84, + 0xAFA: 84, + 0xAFB: 84, + 0xAFC: 84, + 0xAFD: 84, + 0xAFE: 84, + 0xAFF: 84, + 0xB01: 84, + 0xB3C: 84, + 0xB3F: 84, + 0xB41: 84, + 0xB42: 84, + 0xB43: 84, + 0xB44: 84, + 0xB4D: 84, + 0xB55: 84, + 0xB56: 84, + 0xB62: 84, + 0xB63: 84, + 0xB82: 84, + 0xBC0: 84, + 0xBCD: 84, + 0xC00: 84, + 0xC04: 84, + 0xC3C: 84, + 0xC3E: 84, + 0xC3F: 84, + 0xC40: 84, + 0xC46: 84, + 0xC47: 84, + 0xC48: 84, + 0xC4A: 84, + 0xC4B: 84, + 0xC4C: 84, + 0xC4D: 84, + 0xC55: 84, + 0xC56: 84, + 0xC62: 84, + 0xC63: 84, + 0xC81: 84, + 0xCBC: 84, + 0xCBF: 84, + 0xCC6: 84, + 0xCCC: 84, + 0xCCD: 84, + 0xCE2: 84, + 0xCE3: 84, + 0xD00: 84, + 0xD01: 84, + 0xD3B: 84, + 0xD3C: 84, + 0xD41: 84, + 0xD42: 84, + 0xD43: 84, + 0xD44: 84, + 0xD4D: 84, + 0xD62: 84, + 0xD63: 84, + 0xD81: 84, + 0xDCA: 84, + 0xDD2: 84, + 0xDD3: 84, + 0xDD4: 84, + 0xDD6: 84, + 0xE31: 84, + 0xE34: 84, + 0xE35: 84, + 0xE36: 84, + 0xE37: 84, + 0xE38: 84, + 0xE39: 84, + 0xE3A: 84, + 0xE47: 84, + 0xE48: 84, + 0xE49: 84, + 0xE4A: 84, + 0xE4B: 84, + 0xE4C: 84, + 0xE4D: 84, + 0xE4E: 84, + 0xEB1: 84, + 0xEB4: 84, + 0xEB5: 84, + 0xEB6: 84, + 0xEB7: 84, + 0xEB8: 84, + 0xEB9: 84, + 0xEBA: 84, + 0xEBB: 84, + 0xEBC: 84, + 0xEC8: 84, + 0xEC9: 84, + 0xECA: 84, + 0xECB: 84, + 0xECC: 84, + 0xECD: 84, + 0xECE: 84, + 0xF18: 84, + 0xF19: 84, + 0xF35: 84, + 0xF37: 84, + 0xF39: 84, + 0xF71: 84, + 0xF72: 84, + 0xF73: 84, + 0xF74: 84, + 0xF75: 84, + 0xF76: 84, + 0xF77: 84, + 0xF78: 84, + 0xF79: 84, + 0xF7A: 84, + 0xF7B: 84, + 0xF7C: 84, + 0xF7D: 84, + 0xF7E: 84, + 0xF80: 84, + 0xF81: 84, + 0xF82: 84, + 0xF83: 84, + 0xF84: 84, + 0xF86: 84, + 0xF87: 84, + 0xF8D: 84, + 0xF8E: 84, + 0xF8F: 84, + 0xF90: 84, + 0xF91: 84, + 0xF92: 84, + 0xF93: 84, + 0xF94: 84, + 0xF95: 84, + 0xF96: 84, + 0xF97: 84, + 0xF99: 84, + 0xF9A: 84, + 0xF9B: 84, + 0xF9C: 84, + 0xF9D: 84, + 0xF9E: 84, + 0xF9F: 84, + 0xFA0: 84, + 0xFA1: 84, + 0xFA2: 84, + 0xFA3: 84, + 0xFA4: 84, + 0xFA5: 84, + 0xFA6: 84, + 0xFA7: 84, + 0xFA8: 84, + 0xFA9: 84, + 0xFAA: 84, + 0xFAB: 84, + 0xFAC: 84, + 0xFAD: 84, + 0xFAE: 84, + 0xFAF: 84, + 0xFB0: 84, + 0xFB1: 84, + 0xFB2: 84, + 0xFB3: 84, + 0xFB4: 84, + 0xFB5: 84, + 0xFB6: 84, + 0xFB7: 84, + 0xFB8: 84, + 0xFB9: 84, + 0xFBA: 84, + 0xFBB: 84, + 0xFBC: 84, + 0xFC6: 84, + 0x102D: 84, + 0x102E: 84, + 0x102F: 84, + 0x1030: 84, + 0x1032: 84, + 0x1033: 84, + 0x1034: 84, + 0x1035: 84, + 0x1036: 84, + 0x1037: 84, + 0x1039: 84, + 0x103A: 84, + 0x103D: 84, + 0x103E: 84, + 0x1058: 84, + 0x1059: 84, + 0x105E: 84, + 0x105F: 84, + 0x1060: 84, + 0x1071: 84, + 0x1072: 84, + 0x1073: 84, + 0x1074: 84, + 0x1082: 84, + 0x1085: 84, + 0x1086: 84, + 0x108D: 84, + 0x109D: 84, + 0x135D: 84, + 0x135E: 84, + 0x135F: 84, + 0x1712: 84, + 0x1713: 84, + 0x1714: 84, + 0x1732: 84, + 0x1733: 84, + 0x1752: 84, + 0x1753: 84, + 0x1772: 84, + 0x1773: 84, + 0x17B4: 84, + 0x17B5: 84, + 0x17B7: 84, + 0x17B8: 84, + 0x17B9: 84, + 0x17BA: 84, + 0x17BB: 84, + 0x17BC: 84, + 0x17BD: 84, + 0x17C6: 84, + 0x17C9: 84, + 0x17CA: 84, + 0x17CB: 84, + 0x17CC: 84, + 0x17CD: 84, + 0x17CE: 84, + 0x17CF: 84, + 0x17D0: 84, + 0x17D1: 84, + 0x17D2: 84, + 0x17D3: 84, + 0x17DD: 84, 0x1807: 68, - 0x180a: 67, - 0x180e: 85, + 0x180A: 67, + 0x180B: 84, + 0x180C: 84, + 0x180D: 84, + 0x180F: 84, 0x1820: 68, 0x1821: 68, 0x1822: 68, @@ -502,12 +1136,12 @@ joining_types = { 0x1827: 68, 0x1828: 68, 0x1829: 68, - 0x182a: 68, - 0x182b: 68, - 0x182c: 68, - 0x182d: 68, - 0x182e: 68, - 0x182f: 68, + 0x182A: 68, + 0x182B: 68, + 0x182C: 68, + 0x182D: 68, + 0x182E: 68, + 0x182F: 68, 0x1830: 68, 0x1831: 68, 0x1832: 68, @@ -518,12 +1152,12 @@ joining_types = { 0x1837: 68, 0x1838: 68, 0x1839: 68, - 0x183a: 68, - 0x183b: 68, - 0x183c: 68, - 0x183d: 68, - 0x183e: 68, - 0x183f: 68, + 0x183A: 68, + 0x183B: 68, + 0x183C: 68, + 0x183D: 68, + 0x183E: 68, + 0x183F: 68, 0x1840: 68, 0x1841: 68, 0x1842: 68, @@ -534,12 +1168,12 @@ joining_types = { 0x1847: 68, 0x1848: 68, 0x1849: 68, - 0x184a: 68, - 0x184b: 68, - 0x184c: 68, - 0x184d: 68, - 0x184e: 68, - 0x184f: 68, + 0x184A: 68, + 0x184B: 68, + 0x184C: 68, + 0x184D: 68, + 0x184E: 68, + 0x184F: 68, 0x1850: 68, 0x1851: 68, 0x1852: 68, @@ -550,12 +1184,12 @@ joining_types = { 0x1857: 68, 0x1858: 68, 0x1859: 68, - 0x185a: 68, - 0x185b: 68, - 0x185c: 68, - 0x185d: 68, - 0x185e: 68, - 0x185f: 68, + 0x185A: 68, + 0x185B: 68, + 0x185C: 68, + 0x185D: 68, + 0x185E: 68, + 0x185F: 68, 0x1860: 68, 0x1861: 68, 0x1862: 68, @@ -566,12 +1200,12 @@ joining_types = { 0x1867: 68, 0x1868: 68, 0x1869: 68, - 0x186a: 68, - 0x186b: 68, - 0x186c: 68, - 0x186d: 68, - 0x186e: 68, - 0x186f: 68, + 0x186A: 68, + 0x186B: 68, + 0x186C: 68, + 0x186D: 68, + 0x186E: 68, + 0x186F: 68, 0x1870: 68, 0x1871: 68, 0x1872: 68, @@ -581,22 +1215,17 @@ joining_types = { 0x1876: 68, 0x1877: 68, 0x1878: 68, - 0x1880: 85, - 0x1881: 85, - 0x1882: 85, - 0x1883: 85, - 0x1884: 85, 0x1885: 84, 0x1886: 84, 0x1887: 68, 0x1888: 68, 0x1889: 68, - 0x188a: 68, - 0x188b: 68, - 0x188c: 68, - 0x188d: 68, - 0x188e: 68, - 0x188f: 68, + 0x188A: 68, + 0x188B: 68, + 0x188C: 68, + 0x188D: 68, + 0x188E: 68, + 0x188F: 68, 0x1890: 68, 0x1891: 68, 0x1892: 68, @@ -607,1545 +1236,3008 @@ joining_types = { 0x1897: 68, 0x1898: 68, 0x1899: 68, - 0x189a: 68, - 0x189b: 68, - 0x189c: 68, - 0x189d: 68, - 0x189e: 68, - 0x189f: 68, - 0x18a0: 68, - 0x18a1: 68, - 0x18a2: 68, - 0x18a3: 68, - 0x18a4: 68, - 0x18a5: 68, - 0x18a6: 68, - 0x18a7: 68, - 0x18a8: 68, - 0x18aa: 68, - 0x200c: 85, - 0x200d: 67, - 0x202f: 85, - 0x2066: 85, - 0x2067: 85, - 0x2068: 85, - 0x2069: 85, - 0xa840: 68, - 0xa841: 68, - 0xa842: 68, - 0xa843: 68, - 0xa844: 68, - 0xa845: 68, - 0xa846: 68, - 0xa847: 68, - 0xa848: 68, - 0xa849: 68, - 0xa84a: 68, - 0xa84b: 68, - 0xa84c: 68, - 0xa84d: 68, - 0xa84e: 68, - 0xa84f: 68, - 0xa850: 68, - 0xa851: 68, - 0xa852: 68, - 0xa853: 68, - 0xa854: 68, - 0xa855: 68, - 0xa856: 68, - 0xa857: 68, - 0xa858: 68, - 0xa859: 68, - 0xa85a: 68, - 0xa85b: 68, - 0xa85c: 68, - 0xa85d: 68, - 0xa85e: 68, - 0xa85f: 68, - 0xa860: 68, - 0xa861: 68, - 0xa862: 68, - 0xa863: 68, - 0xa864: 68, - 0xa865: 68, - 0xa866: 68, - 0xa867: 68, - 0xa868: 68, - 0xa869: 68, - 0xa86a: 68, - 0xa86b: 68, - 0xa86c: 68, - 0xa86d: 68, - 0xa86e: 68, - 0xa86f: 68, - 0xa870: 68, - 0xa871: 68, - 0xa872: 76, - 0xa873: 85, - 0x10ac0: 68, - 0x10ac1: 68, - 0x10ac2: 68, - 0x10ac3: 68, - 0x10ac4: 68, - 0x10ac5: 82, - 0x10ac6: 85, - 0x10ac7: 82, - 0x10ac8: 85, - 0x10ac9: 82, - 0x10aca: 82, - 0x10acb: 85, - 0x10acc: 85, - 0x10acd: 76, - 0x10ace: 82, - 0x10acf: 82, - 0x10ad0: 82, - 0x10ad1: 82, - 0x10ad2: 82, - 0x10ad3: 68, - 0x10ad4: 68, - 0x10ad5: 68, - 0x10ad6: 68, - 0x10ad7: 76, - 0x10ad8: 68, - 0x10ad9: 68, - 0x10ada: 68, - 0x10adb: 68, - 0x10adc: 68, - 0x10add: 82, - 0x10ade: 68, - 0x10adf: 68, - 0x10ae0: 68, - 0x10ae1: 82, - 0x10ae2: 85, - 0x10ae3: 85, - 0x10ae4: 82, - 0x10aeb: 68, - 0x10aec: 68, - 0x10aed: 68, - 0x10aee: 68, - 0x10aef: 82, - 0x10b80: 68, - 0x10b81: 82, - 0x10b82: 68, - 0x10b83: 82, - 0x10b84: 82, - 0x10b85: 82, - 0x10b86: 68, - 0x10b87: 68, - 0x10b88: 68, - 0x10b89: 82, - 0x10b8a: 68, - 0x10b8b: 68, - 0x10b8c: 82, - 0x10b8d: 68, - 0x10b8e: 82, - 0x10b8f: 82, - 0x10b90: 68, - 0x10b91: 82, - 0x10ba9: 82, - 0x10baa: 82, - 0x10bab: 82, - 0x10bac: 82, - 0x10bad: 68, - 0x10bae: 68, - 0x10baf: 85, - 0x10d00: 76, - 0x10d01: 68, - 0x10d02: 68, - 0x10d03: 68, - 0x10d04: 68, - 0x10d05: 68, - 0x10d06: 68, - 0x10d07: 68, - 0x10d08: 68, - 0x10d09: 68, - 0x10d0a: 68, - 0x10d0b: 68, - 0x10d0c: 68, - 0x10d0d: 68, - 0x10d0e: 68, - 0x10d0f: 68, - 0x10d10: 68, - 0x10d11: 68, - 0x10d12: 68, - 0x10d13: 68, - 0x10d14: 68, - 0x10d15: 68, - 0x10d16: 68, - 0x10d17: 68, - 0x10d18: 68, - 0x10d19: 68, - 0x10d1a: 68, - 0x10d1b: 68, - 0x10d1c: 68, - 0x10d1d: 68, - 0x10d1e: 68, - 0x10d1f: 68, - 0x10d20: 68, - 0x10d21: 68, - 0x10d22: 82, - 0x10d23: 68, - 0x10f30: 68, - 0x10f31: 68, - 0x10f32: 68, - 0x10f33: 82, - 0x10f34: 68, - 0x10f35: 68, - 0x10f36: 68, - 0x10f37: 68, - 0x10f38: 68, - 0x10f39: 68, - 0x10f3a: 68, - 0x10f3b: 68, - 0x10f3c: 68, - 0x10f3d: 68, - 0x10f3e: 68, - 0x10f3f: 68, - 0x10f40: 68, - 0x10f41: 68, - 0x10f42: 68, - 0x10f43: 68, - 0x10f44: 68, - 0x10f45: 85, - 0x10f51: 68, - 0x10f52: 68, - 0x10f53: 68, - 0x10f54: 82, - 0x10f70: 68, - 0x10f71: 68, - 0x10f72: 68, - 0x10f73: 68, - 0x10f74: 82, - 0x10f75: 82, - 0x10f76: 68, - 0x10f77: 68, - 0x10f78: 68, - 0x10f79: 68, - 0x10f7a: 68, - 0x10f7b: 68, - 0x10f7c: 68, - 0x10f7d: 68, - 0x10f7e: 68, - 0x10f7f: 68, - 0x10f80: 68, - 0x10f81: 68, - 0x10fb0: 68, - 0x10fb1: 85, - 0x10fb2: 68, - 0x10fb3: 68, - 0x10fb4: 82, - 0x10fb5: 82, - 0x10fb6: 82, - 0x10fb7: 85, - 0x10fb8: 68, - 0x10fb9: 82, - 0x10fba: 82, - 0x10fbb: 68, - 0x10fbc: 68, - 0x10fbd: 82, - 0x10fbe: 68, - 0x10fbf: 68, - 0x10fc0: 85, - 0x10fc1: 68, - 0x10fc2: 82, - 0x10fc3: 82, - 0x10fc4: 68, - 0x10fc5: 85, - 0x10fc6: 85, - 0x10fc7: 85, - 0x10fc8: 85, - 0x10fc9: 82, - 0x10fca: 68, - 0x10fcb: 76, - 0x110bd: 85, - 0x110cd: 85, - 0x1e900: 68, - 0x1e901: 68, - 0x1e902: 68, - 0x1e903: 68, - 0x1e904: 68, - 0x1e905: 68, - 0x1e906: 68, - 0x1e907: 68, - 0x1e908: 68, - 0x1e909: 68, - 0x1e90a: 68, - 0x1e90b: 68, - 0x1e90c: 68, - 0x1e90d: 68, - 0x1e90e: 68, - 0x1e90f: 68, - 0x1e910: 68, - 0x1e911: 68, - 0x1e912: 68, - 0x1e913: 68, - 0x1e914: 68, - 0x1e915: 68, - 0x1e916: 68, - 0x1e917: 68, - 0x1e918: 68, - 0x1e919: 68, - 0x1e91a: 68, - 0x1e91b: 68, - 0x1e91c: 68, - 0x1e91d: 68, - 0x1e91e: 68, - 0x1e91f: 68, - 0x1e920: 68, - 0x1e921: 68, - 0x1e922: 68, - 0x1e923: 68, - 0x1e924: 68, - 0x1e925: 68, - 0x1e926: 68, - 0x1e927: 68, - 0x1e928: 68, - 0x1e929: 68, - 0x1e92a: 68, - 0x1e92b: 68, - 0x1e92c: 68, - 0x1e92d: 68, - 0x1e92e: 68, - 0x1e92f: 68, - 0x1e930: 68, - 0x1e931: 68, - 0x1e932: 68, - 0x1e933: 68, - 0x1e934: 68, - 0x1e935: 68, - 0x1e936: 68, - 0x1e937: 68, - 0x1e938: 68, - 0x1e939: 68, - 0x1e93a: 68, - 0x1e93b: 68, - 0x1e93c: 68, - 0x1e93d: 68, - 0x1e93e: 68, - 0x1e93f: 68, - 0x1e940: 68, - 0x1e941: 68, - 0x1e942: 68, - 0x1e943: 68, - 0x1e94b: 84, + 0x189A: 68, + 0x189B: 68, + 0x189C: 68, + 0x189D: 68, + 0x189E: 68, + 0x189F: 68, + 0x18A0: 68, + 0x18A1: 68, + 0x18A2: 68, + 0x18A3: 68, + 0x18A4: 68, + 0x18A5: 68, + 0x18A6: 68, + 0x18A7: 68, + 0x18A8: 68, + 0x18A9: 84, + 0x18AA: 68, + 0x1920: 84, + 0x1921: 84, + 0x1922: 84, + 0x1927: 84, + 0x1928: 84, + 0x1932: 84, + 0x1939: 84, + 0x193A: 84, + 0x193B: 84, + 0x1A17: 84, + 0x1A18: 84, + 0x1A1B: 84, + 0x1A56: 84, + 0x1A58: 84, + 0x1A59: 84, + 0x1A5A: 84, + 0x1A5B: 84, + 0x1A5C: 84, + 0x1A5D: 84, + 0x1A5E: 84, + 0x1A60: 84, + 0x1A62: 84, + 0x1A65: 84, + 0x1A66: 84, + 0x1A67: 84, + 0x1A68: 84, + 0x1A69: 84, + 0x1A6A: 84, + 0x1A6B: 84, + 0x1A6C: 84, + 0x1A73: 84, + 0x1A74: 84, + 0x1A75: 84, + 0x1A76: 84, + 0x1A77: 84, + 0x1A78: 84, + 0x1A79: 84, + 0x1A7A: 84, + 0x1A7B: 84, + 0x1A7C: 84, + 0x1A7F: 84, + 0x1AB0: 84, + 0x1AB1: 84, + 0x1AB2: 84, + 0x1AB3: 84, + 0x1AB4: 84, + 0x1AB5: 84, + 0x1AB6: 84, + 0x1AB7: 84, + 0x1AB8: 84, + 0x1AB9: 84, + 0x1ABA: 84, + 0x1ABB: 84, + 0x1ABC: 84, + 0x1ABD: 84, + 0x1ABE: 84, + 0x1ABF: 84, + 0x1AC0: 84, + 0x1AC1: 84, + 0x1AC2: 84, + 0x1AC3: 84, + 0x1AC4: 84, + 0x1AC5: 84, + 0x1AC6: 84, + 0x1AC7: 84, + 0x1AC8: 84, + 0x1AC9: 84, + 0x1ACA: 84, + 0x1ACB: 84, + 0x1ACC: 84, + 0x1ACD: 84, + 0x1ACE: 84, + 0x1B00: 84, + 0x1B01: 84, + 0x1B02: 84, + 0x1B03: 84, + 0x1B34: 84, + 0x1B36: 84, + 0x1B37: 84, + 0x1B38: 84, + 0x1B39: 84, + 0x1B3A: 84, + 0x1B3C: 84, + 0x1B42: 84, + 0x1B6B: 84, + 0x1B6C: 84, + 0x1B6D: 84, + 0x1B6E: 84, + 0x1B6F: 84, + 0x1B70: 84, + 0x1B71: 84, + 0x1B72: 84, + 0x1B73: 84, + 0x1B80: 84, + 0x1B81: 84, + 0x1BA2: 84, + 0x1BA3: 84, + 0x1BA4: 84, + 0x1BA5: 84, + 0x1BA8: 84, + 0x1BA9: 84, + 0x1BAB: 84, + 0x1BAC: 84, + 0x1BAD: 84, + 0x1BE6: 84, + 0x1BE8: 84, + 0x1BE9: 84, + 0x1BED: 84, + 0x1BEF: 84, + 0x1BF0: 84, + 0x1BF1: 84, + 0x1C2C: 84, + 0x1C2D: 84, + 0x1C2E: 84, + 0x1C2F: 84, + 0x1C30: 84, + 0x1C31: 84, + 0x1C32: 84, + 0x1C33: 84, + 0x1C36: 84, + 0x1C37: 84, + 0x1CD0: 84, + 0x1CD1: 84, + 0x1CD2: 84, + 0x1CD4: 84, + 0x1CD5: 84, + 0x1CD6: 84, + 0x1CD7: 84, + 0x1CD8: 84, + 0x1CD9: 84, + 0x1CDA: 84, + 0x1CDB: 84, + 0x1CDC: 84, + 0x1CDD: 84, + 0x1CDE: 84, + 0x1CDF: 84, + 0x1CE0: 84, + 0x1CE2: 84, + 0x1CE3: 84, + 0x1CE4: 84, + 0x1CE5: 84, + 0x1CE6: 84, + 0x1CE7: 84, + 0x1CE8: 84, + 0x1CED: 84, + 0x1CF4: 84, + 0x1CF8: 84, + 0x1CF9: 84, + 0x1DC0: 84, + 0x1DC1: 84, + 0x1DC2: 84, + 0x1DC3: 84, + 0x1DC4: 84, + 0x1DC5: 84, + 0x1DC6: 84, + 0x1DC7: 84, + 0x1DC8: 84, + 0x1DC9: 84, + 0x1DCA: 84, + 0x1DCB: 84, + 0x1DCC: 84, + 0x1DCD: 84, + 0x1DCE: 84, + 0x1DCF: 84, + 0x1DD0: 84, + 0x1DD1: 84, + 0x1DD2: 84, + 0x1DD3: 84, + 0x1DD4: 84, + 0x1DD5: 84, + 0x1DD6: 84, + 0x1DD7: 84, + 0x1DD8: 84, + 0x1DD9: 84, + 0x1DDA: 84, + 0x1DDB: 84, + 0x1DDC: 84, + 0x1DDD: 84, + 0x1DDE: 84, + 0x1DDF: 84, + 0x1DE0: 84, + 0x1DE1: 84, + 0x1DE2: 84, + 0x1DE3: 84, + 0x1DE4: 84, + 0x1DE5: 84, + 0x1DE6: 84, + 0x1DE7: 84, + 0x1DE8: 84, + 0x1DE9: 84, + 0x1DEA: 84, + 0x1DEB: 84, + 0x1DEC: 84, + 0x1DED: 84, + 0x1DEE: 84, + 0x1DEF: 84, + 0x1DF0: 84, + 0x1DF1: 84, + 0x1DF2: 84, + 0x1DF3: 84, + 0x1DF4: 84, + 0x1DF5: 84, + 0x1DF6: 84, + 0x1DF7: 84, + 0x1DF8: 84, + 0x1DF9: 84, + 0x1DFA: 84, + 0x1DFB: 84, + 0x1DFC: 84, + 0x1DFD: 84, + 0x1DFE: 84, + 0x1DFF: 84, + 0x200B: 84, + 0x200D: 67, + 0x200E: 84, + 0x200F: 84, + 0x202A: 84, + 0x202B: 84, + 0x202C: 84, + 0x202D: 84, + 0x202E: 84, + 0x2060: 84, + 0x2061: 84, + 0x2062: 84, + 0x2063: 84, + 0x2064: 84, + 0x206A: 84, + 0x206B: 84, + 0x206C: 84, + 0x206D: 84, + 0x206E: 84, + 0x206F: 84, + 0x20D0: 84, + 0x20D1: 84, + 0x20D2: 84, + 0x20D3: 84, + 0x20D4: 84, + 0x20D5: 84, + 0x20D6: 84, + 0x20D7: 84, + 0x20D8: 84, + 0x20D9: 84, + 0x20DA: 84, + 0x20DB: 84, + 0x20DC: 84, + 0x20DD: 84, + 0x20DE: 84, + 0x20DF: 84, + 0x20E0: 84, + 0x20E1: 84, + 0x20E2: 84, + 0x20E3: 84, + 0x20E4: 84, + 0x20E5: 84, + 0x20E6: 84, + 0x20E7: 84, + 0x20E8: 84, + 0x20E9: 84, + 0x20EA: 84, + 0x20EB: 84, + 0x20EC: 84, + 0x20ED: 84, + 0x20EE: 84, + 0x20EF: 84, + 0x20F0: 84, + 0x2CEF: 84, + 0x2CF0: 84, + 0x2CF1: 84, + 0x2D7F: 84, + 0x2DE0: 84, + 0x2DE1: 84, + 0x2DE2: 84, + 0x2DE3: 84, + 0x2DE4: 84, + 0x2DE5: 84, + 0x2DE6: 84, + 0x2DE7: 84, + 0x2DE8: 84, + 0x2DE9: 84, + 0x2DEA: 84, + 0x2DEB: 84, + 0x2DEC: 84, + 0x2DED: 84, + 0x2DEE: 84, + 0x2DEF: 84, + 0x2DF0: 84, + 0x2DF1: 84, + 0x2DF2: 84, + 0x2DF3: 84, + 0x2DF4: 84, + 0x2DF5: 84, + 0x2DF6: 84, + 0x2DF7: 84, + 0x2DF8: 84, + 0x2DF9: 84, + 0x2DFA: 84, + 0x2DFB: 84, + 0x2DFC: 84, + 0x2DFD: 84, + 0x2DFE: 84, + 0x2DFF: 84, + 0x302A: 84, + 0x302B: 84, + 0x302C: 84, + 0x302D: 84, + 0x3099: 84, + 0x309A: 84, + 0xA66F: 84, + 0xA670: 84, + 0xA671: 84, + 0xA672: 84, + 0xA674: 84, + 0xA675: 84, + 0xA676: 84, + 0xA677: 84, + 0xA678: 84, + 0xA679: 84, + 0xA67A: 84, + 0xA67B: 84, + 0xA67C: 84, + 0xA67D: 84, + 0xA69E: 84, + 0xA69F: 84, + 0xA6F0: 84, + 0xA6F1: 84, + 0xA802: 84, + 0xA806: 84, + 0xA80B: 84, + 0xA825: 84, + 0xA826: 84, + 0xA82C: 84, + 0xA840: 68, + 0xA841: 68, + 0xA842: 68, + 0xA843: 68, + 0xA844: 68, + 0xA845: 68, + 0xA846: 68, + 0xA847: 68, + 0xA848: 68, + 0xA849: 68, + 0xA84A: 68, + 0xA84B: 68, + 0xA84C: 68, + 0xA84D: 68, + 0xA84E: 68, + 0xA84F: 68, + 0xA850: 68, + 0xA851: 68, + 0xA852: 68, + 0xA853: 68, + 0xA854: 68, + 0xA855: 68, + 0xA856: 68, + 0xA857: 68, + 0xA858: 68, + 0xA859: 68, + 0xA85A: 68, + 0xA85B: 68, + 0xA85C: 68, + 0xA85D: 68, + 0xA85E: 68, + 0xA85F: 68, + 0xA860: 68, + 0xA861: 68, + 0xA862: 68, + 0xA863: 68, + 0xA864: 68, + 0xA865: 68, + 0xA866: 68, + 0xA867: 68, + 0xA868: 68, + 0xA869: 68, + 0xA86A: 68, + 0xA86B: 68, + 0xA86C: 68, + 0xA86D: 68, + 0xA86E: 68, + 0xA86F: 68, + 0xA870: 68, + 0xA871: 68, + 0xA872: 76, + 0xA8C4: 84, + 0xA8C5: 84, + 0xA8E0: 84, + 0xA8E1: 84, + 0xA8E2: 84, + 0xA8E3: 84, + 0xA8E4: 84, + 0xA8E5: 84, + 0xA8E6: 84, + 0xA8E7: 84, + 0xA8E8: 84, + 0xA8E9: 84, + 0xA8EA: 84, + 0xA8EB: 84, + 0xA8EC: 84, + 0xA8ED: 84, + 0xA8EE: 84, + 0xA8EF: 84, + 0xA8F0: 84, + 0xA8F1: 84, + 0xA8FF: 84, + 0xA926: 84, + 0xA927: 84, + 0xA928: 84, + 0xA929: 84, + 0xA92A: 84, + 0xA92B: 84, + 0xA92C: 84, + 0xA92D: 84, + 0xA947: 84, + 0xA948: 84, + 0xA949: 84, + 0xA94A: 84, + 0xA94B: 84, + 0xA94C: 84, + 0xA94D: 84, + 0xA94E: 84, + 0xA94F: 84, + 0xA950: 84, + 0xA951: 84, + 0xA980: 84, + 0xA981: 84, + 0xA982: 84, + 0xA9B3: 84, + 0xA9B6: 84, + 0xA9B7: 84, + 0xA9B8: 84, + 0xA9B9: 84, + 0xA9BC: 84, + 0xA9BD: 84, + 0xA9E5: 84, + 0xAA29: 84, + 0xAA2A: 84, + 0xAA2B: 84, + 0xAA2C: 84, + 0xAA2D: 84, + 0xAA2E: 84, + 0xAA31: 84, + 0xAA32: 84, + 0xAA35: 84, + 0xAA36: 84, + 0xAA43: 84, + 0xAA4C: 84, + 0xAA7C: 84, + 0xAAB0: 84, + 0xAAB2: 84, + 0xAAB3: 84, + 0xAAB4: 84, + 0xAAB7: 84, + 0xAAB8: 84, + 0xAABE: 84, + 0xAABF: 84, + 0xAAC1: 84, + 0xAAEC: 84, + 0xAAED: 84, + 0xAAF6: 84, + 0xABE5: 84, + 0xABE8: 84, + 0xABED: 84, + 0xFB1E: 84, + 0xFE00: 84, + 0xFE01: 84, + 0xFE02: 84, + 0xFE03: 84, + 0xFE04: 84, + 0xFE05: 84, + 0xFE06: 84, + 0xFE07: 84, + 0xFE08: 84, + 0xFE09: 84, + 0xFE0A: 84, + 0xFE0B: 84, + 0xFE0C: 84, + 0xFE0D: 84, + 0xFE0E: 84, + 0xFE0F: 84, + 0xFE20: 84, + 0xFE21: 84, + 0xFE22: 84, + 0xFE23: 84, + 0xFE24: 84, + 0xFE25: 84, + 0xFE26: 84, + 0xFE27: 84, + 0xFE28: 84, + 0xFE29: 84, + 0xFE2A: 84, + 0xFE2B: 84, + 0xFE2C: 84, + 0xFE2D: 84, + 0xFE2E: 84, + 0xFE2F: 84, + 0xFEFF: 84, + 0xFFF9: 84, + 0xFFFA: 84, + 0xFFFB: 84, + 0x101FD: 84, + 0x102E0: 84, + 0x10376: 84, + 0x10377: 84, + 0x10378: 84, + 0x10379: 84, + 0x1037A: 84, + 0x10A01: 84, + 0x10A02: 84, + 0x10A03: 84, + 0x10A05: 84, + 0x10A06: 84, + 0x10A0C: 84, + 0x10A0D: 84, + 0x10A0E: 84, + 0x10A0F: 84, + 0x10A38: 84, + 0x10A39: 84, + 0x10A3A: 84, + 0x10A3F: 84, + 0x10AC0: 68, + 0x10AC1: 68, + 0x10AC2: 68, + 0x10AC3: 68, + 0x10AC4: 68, + 0x10AC5: 82, + 0x10AC7: 82, + 0x10AC9: 82, + 0x10ACA: 82, + 0x10ACD: 76, + 0x10ACE: 82, + 0x10ACF: 82, + 0x10AD0: 82, + 0x10AD1: 82, + 0x10AD2: 82, + 0x10AD3: 68, + 0x10AD4: 68, + 0x10AD5: 68, + 0x10AD6: 68, + 0x10AD7: 76, + 0x10AD8: 68, + 0x10AD9: 68, + 0x10ADA: 68, + 0x10ADB: 68, + 0x10ADC: 68, + 0x10ADD: 82, + 0x10ADE: 68, + 0x10ADF: 68, + 0x10AE0: 68, + 0x10AE1: 82, + 0x10AE4: 82, + 0x10AE5: 84, + 0x10AE6: 84, + 0x10AEB: 68, + 0x10AEC: 68, + 0x10AED: 68, + 0x10AEE: 68, + 0x10AEF: 82, + 0x10B80: 68, + 0x10B81: 82, + 0x10B82: 68, + 0x10B83: 82, + 0x10B84: 82, + 0x10B85: 82, + 0x10B86: 68, + 0x10B87: 68, + 0x10B88: 68, + 0x10B89: 82, + 0x10B8A: 68, + 0x10B8B: 68, + 0x10B8C: 82, + 0x10B8D: 68, + 0x10B8E: 82, + 0x10B8F: 82, + 0x10B90: 68, + 0x10B91: 82, + 0x10BA9: 82, + 0x10BAA: 82, + 0x10BAB: 82, + 0x10BAC: 82, + 0x10BAD: 68, + 0x10BAE: 68, + 0x10D00: 76, + 0x10D01: 68, + 0x10D02: 68, + 0x10D03: 68, + 0x10D04: 68, + 0x10D05: 68, + 0x10D06: 68, + 0x10D07: 68, + 0x10D08: 68, + 0x10D09: 68, + 0x10D0A: 68, + 0x10D0B: 68, + 0x10D0C: 68, + 0x10D0D: 68, + 0x10D0E: 68, + 0x10D0F: 68, + 0x10D10: 68, + 0x10D11: 68, + 0x10D12: 68, + 0x10D13: 68, + 0x10D14: 68, + 0x10D15: 68, + 0x10D16: 68, + 0x10D17: 68, + 0x10D18: 68, + 0x10D19: 68, + 0x10D1A: 68, + 0x10D1B: 68, + 0x10D1C: 68, + 0x10D1D: 68, + 0x10D1E: 68, + 0x10D1F: 68, + 0x10D20: 68, + 0x10D21: 68, + 0x10D22: 82, + 0x10D23: 68, + 0x10D24: 84, + 0x10D25: 84, + 0x10D26: 84, + 0x10D27: 84, + 0x10EAB: 84, + 0x10EAC: 84, + 0x10EFD: 84, + 0x10EFE: 84, + 0x10EFF: 84, + 0x10F30: 68, + 0x10F31: 68, + 0x10F32: 68, + 0x10F33: 82, + 0x10F34: 68, + 0x10F35: 68, + 0x10F36: 68, + 0x10F37: 68, + 0x10F38: 68, + 0x10F39: 68, + 0x10F3A: 68, + 0x10F3B: 68, + 0x10F3C: 68, + 0x10F3D: 68, + 0x10F3E: 68, + 0x10F3F: 68, + 0x10F40: 68, + 0x10F41: 68, + 0x10F42: 68, + 0x10F43: 68, + 0x10F44: 68, + 0x10F46: 84, + 0x10F47: 84, + 0x10F48: 84, + 0x10F49: 84, + 0x10F4A: 84, + 0x10F4B: 84, + 0x10F4C: 84, + 0x10F4D: 84, + 0x10F4E: 84, + 0x10F4F: 84, + 0x10F50: 84, + 0x10F51: 68, + 0x10F52: 68, + 0x10F53: 68, + 0x10F54: 82, + 0x10F70: 68, + 0x10F71: 68, + 0x10F72: 68, + 0x10F73: 68, + 0x10F74: 82, + 0x10F75: 82, + 0x10F76: 68, + 0x10F77: 68, + 0x10F78: 68, + 0x10F79: 68, + 0x10F7A: 68, + 0x10F7B: 68, + 0x10F7C: 68, + 0x10F7D: 68, + 0x10F7E: 68, + 0x10F7F: 68, + 0x10F80: 68, + 0x10F81: 68, + 0x10F82: 84, + 0x10F83: 84, + 0x10F84: 84, + 0x10F85: 84, + 0x10FB0: 68, + 0x10FB2: 68, + 0x10FB3: 68, + 0x10FB4: 82, + 0x10FB5: 82, + 0x10FB6: 82, + 0x10FB8: 68, + 0x10FB9: 82, + 0x10FBA: 82, + 0x10FBB: 68, + 0x10FBC: 68, + 0x10FBD: 82, + 0x10FBE: 68, + 0x10FBF: 68, + 0x10FC1: 68, + 0x10FC2: 82, + 0x10FC3: 82, + 0x10FC4: 68, + 0x10FC9: 82, + 0x10FCA: 68, + 0x10FCB: 76, + 0x11001: 84, + 0x11038: 84, + 0x11039: 84, + 0x1103A: 84, + 0x1103B: 84, + 0x1103C: 84, + 0x1103D: 84, + 0x1103E: 84, + 0x1103F: 84, + 0x11040: 84, + 0x11041: 84, + 0x11042: 84, + 0x11043: 84, + 0x11044: 84, + 0x11045: 84, + 0x11046: 84, + 0x11070: 84, + 0x11073: 84, + 0x11074: 84, + 0x1107F: 84, + 0x11080: 84, + 0x11081: 84, + 0x110B3: 84, + 0x110B4: 84, + 0x110B5: 84, + 0x110B6: 84, + 0x110B9: 84, + 0x110BA: 84, + 0x110C2: 84, + 0x11100: 84, + 0x11101: 84, + 0x11102: 84, + 0x11127: 84, + 0x11128: 84, + 0x11129: 84, + 0x1112A: 84, + 0x1112B: 84, + 0x1112D: 84, + 0x1112E: 84, + 0x1112F: 84, + 0x11130: 84, + 0x11131: 84, + 0x11132: 84, + 0x11133: 84, + 0x11134: 84, + 0x11173: 84, + 0x11180: 84, + 0x11181: 84, + 0x111B6: 84, + 0x111B7: 84, + 0x111B8: 84, + 0x111B9: 84, + 0x111BA: 84, + 0x111BB: 84, + 0x111BC: 84, + 0x111BD: 84, + 0x111BE: 84, + 0x111C9: 84, + 0x111CA: 84, + 0x111CB: 84, + 0x111CC: 84, + 0x111CF: 84, + 0x1122F: 84, + 0x11230: 84, + 0x11231: 84, + 0x11234: 84, + 0x11236: 84, + 0x11237: 84, + 0x1123E: 84, + 0x11241: 84, + 0x112DF: 84, + 0x112E3: 84, + 0x112E4: 84, + 0x112E5: 84, + 0x112E6: 84, + 0x112E7: 84, + 0x112E8: 84, + 0x112E9: 84, + 0x112EA: 84, + 0x11300: 84, + 0x11301: 84, + 0x1133B: 84, + 0x1133C: 84, + 0x11340: 84, + 0x11366: 84, + 0x11367: 84, + 0x11368: 84, + 0x11369: 84, + 0x1136A: 84, + 0x1136B: 84, + 0x1136C: 84, + 0x11370: 84, + 0x11371: 84, + 0x11372: 84, + 0x11373: 84, + 0x11374: 84, + 0x11438: 84, + 0x11439: 84, + 0x1143A: 84, + 0x1143B: 84, + 0x1143C: 84, + 0x1143D: 84, + 0x1143E: 84, + 0x1143F: 84, + 0x11442: 84, + 0x11443: 84, + 0x11444: 84, + 0x11446: 84, + 0x1145E: 84, + 0x114B3: 84, + 0x114B4: 84, + 0x114B5: 84, + 0x114B6: 84, + 0x114B7: 84, + 0x114B8: 84, + 0x114BA: 84, + 0x114BF: 84, + 0x114C0: 84, + 0x114C2: 84, + 0x114C3: 84, + 0x115B2: 84, + 0x115B3: 84, + 0x115B4: 84, + 0x115B5: 84, + 0x115BC: 84, + 0x115BD: 84, + 0x115BF: 84, + 0x115C0: 84, + 0x115DC: 84, + 0x115DD: 84, + 0x11633: 84, + 0x11634: 84, + 0x11635: 84, + 0x11636: 84, + 0x11637: 84, + 0x11638: 84, + 0x11639: 84, + 0x1163A: 84, + 0x1163D: 84, + 0x1163F: 84, + 0x11640: 84, + 0x116AB: 84, + 0x116AD: 84, + 0x116B0: 84, + 0x116B1: 84, + 0x116B2: 84, + 0x116B3: 84, + 0x116B4: 84, + 0x116B5: 84, + 0x116B7: 84, + 0x1171D: 84, + 0x1171E: 84, + 0x1171F: 84, + 0x11722: 84, + 0x11723: 84, + 0x11724: 84, + 0x11725: 84, + 0x11727: 84, + 0x11728: 84, + 0x11729: 84, + 0x1172A: 84, + 0x1172B: 84, + 0x1182F: 84, + 0x11830: 84, + 0x11831: 84, + 0x11832: 84, + 0x11833: 84, + 0x11834: 84, + 0x11835: 84, + 0x11836: 84, + 0x11837: 84, + 0x11839: 84, + 0x1183A: 84, + 0x1193B: 84, + 0x1193C: 84, + 0x1193E: 84, + 0x11943: 84, + 0x119D4: 84, + 0x119D5: 84, + 0x119D6: 84, + 0x119D7: 84, + 0x119DA: 84, + 0x119DB: 84, + 0x119E0: 84, + 0x11A01: 84, + 0x11A02: 84, + 0x11A03: 84, + 0x11A04: 84, + 0x11A05: 84, + 0x11A06: 84, + 0x11A07: 84, + 0x11A08: 84, + 0x11A09: 84, + 0x11A0A: 84, + 0x11A33: 84, + 0x11A34: 84, + 0x11A35: 84, + 0x11A36: 84, + 0x11A37: 84, + 0x11A38: 84, + 0x11A3B: 84, + 0x11A3C: 84, + 0x11A3D: 84, + 0x11A3E: 84, + 0x11A47: 84, + 0x11A51: 84, + 0x11A52: 84, + 0x11A53: 84, + 0x11A54: 84, + 0x11A55: 84, + 0x11A56: 84, + 0x11A59: 84, + 0x11A5A: 84, + 0x11A5B: 84, + 0x11A8A: 84, + 0x11A8B: 84, + 0x11A8C: 84, + 0x11A8D: 84, + 0x11A8E: 84, + 0x11A8F: 84, + 0x11A90: 84, + 0x11A91: 84, + 0x11A92: 84, + 0x11A93: 84, + 0x11A94: 84, + 0x11A95: 84, + 0x11A96: 84, + 0x11A98: 84, + 0x11A99: 84, + 0x11C30: 84, + 0x11C31: 84, + 0x11C32: 84, + 0x11C33: 84, + 0x11C34: 84, + 0x11C35: 84, + 0x11C36: 84, + 0x11C38: 84, + 0x11C39: 84, + 0x11C3A: 84, + 0x11C3B: 84, + 0x11C3C: 84, + 0x11C3D: 84, + 0x11C3F: 84, + 0x11C92: 84, + 0x11C93: 84, + 0x11C94: 84, + 0x11C95: 84, + 0x11C96: 84, + 0x11C97: 84, + 0x11C98: 84, + 0x11C99: 84, + 0x11C9A: 84, + 0x11C9B: 84, + 0x11C9C: 84, + 0x11C9D: 84, + 0x11C9E: 84, + 0x11C9F: 84, + 0x11CA0: 84, + 0x11CA1: 84, + 0x11CA2: 84, + 0x11CA3: 84, + 0x11CA4: 84, + 0x11CA5: 84, + 0x11CA6: 84, + 0x11CA7: 84, + 0x11CAA: 84, + 0x11CAB: 84, + 0x11CAC: 84, + 0x11CAD: 84, + 0x11CAE: 84, + 0x11CAF: 84, + 0x11CB0: 84, + 0x11CB2: 84, + 0x11CB3: 84, + 0x11CB5: 84, + 0x11CB6: 84, + 0x11D31: 84, + 0x11D32: 84, + 0x11D33: 84, + 0x11D34: 84, + 0x11D35: 84, + 0x11D36: 84, + 0x11D3A: 84, + 0x11D3C: 84, + 0x11D3D: 84, + 0x11D3F: 84, + 0x11D40: 84, + 0x11D41: 84, + 0x11D42: 84, + 0x11D43: 84, + 0x11D44: 84, + 0x11D45: 84, + 0x11D47: 84, + 0x11D90: 84, + 0x11D91: 84, + 0x11D95: 84, + 0x11D97: 84, + 0x11EF3: 84, + 0x11EF4: 84, + 0x11F00: 84, + 0x11F01: 84, + 0x11F36: 84, + 0x11F37: 84, + 0x11F38: 84, + 0x11F39: 84, + 0x11F3A: 84, + 0x11F40: 84, + 0x11F42: 84, + 0x13430: 84, + 0x13431: 84, + 0x13432: 84, + 0x13433: 84, + 0x13434: 84, + 0x13435: 84, + 0x13436: 84, + 0x13437: 84, + 0x13438: 84, + 0x13439: 84, + 0x1343A: 84, + 0x1343B: 84, + 0x1343C: 84, + 0x1343D: 84, + 0x1343E: 84, + 0x1343F: 84, + 0x13440: 84, + 0x13447: 84, + 0x13448: 84, + 0x13449: 84, + 0x1344A: 84, + 0x1344B: 84, + 0x1344C: 84, + 0x1344D: 84, + 0x1344E: 84, + 0x1344F: 84, + 0x13450: 84, + 0x13451: 84, + 0x13452: 84, + 0x13453: 84, + 0x13454: 84, + 0x13455: 84, + 0x16AF0: 84, + 0x16AF1: 84, + 0x16AF2: 84, + 0x16AF3: 84, + 0x16AF4: 84, + 0x16B30: 84, + 0x16B31: 84, + 0x16B32: 84, + 0x16B33: 84, + 0x16B34: 84, + 0x16B35: 84, + 0x16B36: 84, + 0x16F4F: 84, + 0x16F8F: 84, + 0x16F90: 84, + 0x16F91: 84, + 0x16F92: 84, + 0x16FE4: 84, + 0x1BC9D: 84, + 0x1BC9E: 84, + 0x1BCA0: 84, + 0x1BCA1: 84, + 0x1BCA2: 84, + 0x1BCA3: 84, + 0x1CF00: 84, + 0x1CF01: 84, + 0x1CF02: 84, + 0x1CF03: 84, + 0x1CF04: 84, + 0x1CF05: 84, + 0x1CF06: 84, + 0x1CF07: 84, + 0x1CF08: 84, + 0x1CF09: 84, + 0x1CF0A: 84, + 0x1CF0B: 84, + 0x1CF0C: 84, + 0x1CF0D: 84, + 0x1CF0E: 84, + 0x1CF0F: 84, + 0x1CF10: 84, + 0x1CF11: 84, + 0x1CF12: 84, + 0x1CF13: 84, + 0x1CF14: 84, + 0x1CF15: 84, + 0x1CF16: 84, + 0x1CF17: 84, + 0x1CF18: 84, + 0x1CF19: 84, + 0x1CF1A: 84, + 0x1CF1B: 84, + 0x1CF1C: 84, + 0x1CF1D: 84, + 0x1CF1E: 84, + 0x1CF1F: 84, + 0x1CF20: 84, + 0x1CF21: 84, + 0x1CF22: 84, + 0x1CF23: 84, + 0x1CF24: 84, + 0x1CF25: 84, + 0x1CF26: 84, + 0x1CF27: 84, + 0x1CF28: 84, + 0x1CF29: 84, + 0x1CF2A: 84, + 0x1CF2B: 84, + 0x1CF2C: 84, + 0x1CF2D: 84, + 0x1CF30: 84, + 0x1CF31: 84, + 0x1CF32: 84, + 0x1CF33: 84, + 0x1CF34: 84, + 0x1CF35: 84, + 0x1CF36: 84, + 0x1CF37: 84, + 0x1CF38: 84, + 0x1CF39: 84, + 0x1CF3A: 84, + 0x1CF3B: 84, + 0x1CF3C: 84, + 0x1CF3D: 84, + 0x1CF3E: 84, + 0x1CF3F: 84, + 0x1CF40: 84, + 0x1CF41: 84, + 0x1CF42: 84, + 0x1CF43: 84, + 0x1CF44: 84, + 0x1CF45: 84, + 0x1CF46: 84, + 0x1D167: 84, + 0x1D168: 84, + 0x1D169: 84, + 0x1D173: 84, + 0x1D174: 84, + 0x1D175: 84, + 0x1D176: 84, + 0x1D177: 84, + 0x1D178: 84, + 0x1D179: 84, + 0x1D17A: 84, + 0x1D17B: 84, + 0x1D17C: 84, + 0x1D17D: 84, + 0x1D17E: 84, + 0x1D17F: 84, + 0x1D180: 84, + 0x1D181: 84, + 0x1D182: 84, + 0x1D185: 84, + 0x1D186: 84, + 0x1D187: 84, + 0x1D188: 84, + 0x1D189: 84, + 0x1D18A: 84, + 0x1D18B: 84, + 0x1D1AA: 84, + 0x1D1AB: 84, + 0x1D1AC: 84, + 0x1D1AD: 84, + 0x1D242: 84, + 0x1D243: 84, + 0x1D244: 84, + 0x1DA00: 84, + 0x1DA01: 84, + 0x1DA02: 84, + 0x1DA03: 84, + 0x1DA04: 84, + 0x1DA05: 84, + 0x1DA06: 84, + 0x1DA07: 84, + 0x1DA08: 84, + 0x1DA09: 84, + 0x1DA0A: 84, + 0x1DA0B: 84, + 0x1DA0C: 84, + 0x1DA0D: 84, + 0x1DA0E: 84, + 0x1DA0F: 84, + 0x1DA10: 84, + 0x1DA11: 84, + 0x1DA12: 84, + 0x1DA13: 84, + 0x1DA14: 84, + 0x1DA15: 84, + 0x1DA16: 84, + 0x1DA17: 84, + 0x1DA18: 84, + 0x1DA19: 84, + 0x1DA1A: 84, + 0x1DA1B: 84, + 0x1DA1C: 84, + 0x1DA1D: 84, + 0x1DA1E: 84, + 0x1DA1F: 84, + 0x1DA20: 84, + 0x1DA21: 84, + 0x1DA22: 84, + 0x1DA23: 84, + 0x1DA24: 84, + 0x1DA25: 84, + 0x1DA26: 84, + 0x1DA27: 84, + 0x1DA28: 84, + 0x1DA29: 84, + 0x1DA2A: 84, + 0x1DA2B: 84, + 0x1DA2C: 84, + 0x1DA2D: 84, + 0x1DA2E: 84, + 0x1DA2F: 84, + 0x1DA30: 84, + 0x1DA31: 84, + 0x1DA32: 84, + 0x1DA33: 84, + 0x1DA34: 84, + 0x1DA35: 84, + 0x1DA36: 84, + 0x1DA3B: 84, + 0x1DA3C: 84, + 0x1DA3D: 84, + 0x1DA3E: 84, + 0x1DA3F: 84, + 0x1DA40: 84, + 0x1DA41: 84, + 0x1DA42: 84, + 0x1DA43: 84, + 0x1DA44: 84, + 0x1DA45: 84, + 0x1DA46: 84, + 0x1DA47: 84, + 0x1DA48: 84, + 0x1DA49: 84, + 0x1DA4A: 84, + 0x1DA4B: 84, + 0x1DA4C: 84, + 0x1DA4D: 84, + 0x1DA4E: 84, + 0x1DA4F: 84, + 0x1DA50: 84, + 0x1DA51: 84, + 0x1DA52: 84, + 0x1DA53: 84, + 0x1DA54: 84, + 0x1DA55: 84, + 0x1DA56: 84, + 0x1DA57: 84, + 0x1DA58: 84, + 0x1DA59: 84, + 0x1DA5A: 84, + 0x1DA5B: 84, + 0x1DA5C: 84, + 0x1DA5D: 84, + 0x1DA5E: 84, + 0x1DA5F: 84, + 0x1DA60: 84, + 0x1DA61: 84, + 0x1DA62: 84, + 0x1DA63: 84, + 0x1DA64: 84, + 0x1DA65: 84, + 0x1DA66: 84, + 0x1DA67: 84, + 0x1DA68: 84, + 0x1DA69: 84, + 0x1DA6A: 84, + 0x1DA6B: 84, + 0x1DA6C: 84, + 0x1DA75: 84, + 0x1DA84: 84, + 0x1DA9B: 84, + 0x1DA9C: 84, + 0x1DA9D: 84, + 0x1DA9E: 84, + 0x1DA9F: 84, + 0x1DAA1: 84, + 0x1DAA2: 84, + 0x1DAA3: 84, + 0x1DAA4: 84, + 0x1DAA5: 84, + 0x1DAA6: 84, + 0x1DAA7: 84, + 0x1DAA8: 84, + 0x1DAA9: 84, + 0x1DAAA: 84, + 0x1DAAB: 84, + 0x1DAAC: 84, + 0x1DAAD: 84, + 0x1DAAE: 84, + 0x1DAAF: 84, + 0x1E000: 84, + 0x1E001: 84, + 0x1E002: 84, + 0x1E003: 84, + 0x1E004: 84, + 0x1E005: 84, + 0x1E006: 84, + 0x1E008: 84, + 0x1E009: 84, + 0x1E00A: 84, + 0x1E00B: 84, + 0x1E00C: 84, + 0x1E00D: 84, + 0x1E00E: 84, + 0x1E00F: 84, + 0x1E010: 84, + 0x1E011: 84, + 0x1E012: 84, + 0x1E013: 84, + 0x1E014: 84, + 0x1E015: 84, + 0x1E016: 84, + 0x1E017: 84, + 0x1E018: 84, + 0x1E01B: 84, + 0x1E01C: 84, + 0x1E01D: 84, + 0x1E01E: 84, + 0x1E01F: 84, + 0x1E020: 84, + 0x1E021: 84, + 0x1E023: 84, + 0x1E024: 84, + 0x1E026: 84, + 0x1E027: 84, + 0x1E028: 84, + 0x1E029: 84, + 0x1E02A: 84, + 0x1E08F: 84, + 0x1E130: 84, + 0x1E131: 84, + 0x1E132: 84, + 0x1E133: 84, + 0x1E134: 84, + 0x1E135: 84, + 0x1E136: 84, + 0x1E2AE: 84, + 0x1E2EC: 84, + 0x1E2ED: 84, + 0x1E2EE: 84, + 0x1E2EF: 84, + 0x1E4EC: 84, + 0x1E4ED: 84, + 0x1E4EE: 84, + 0x1E4EF: 84, + 0x1E8D0: 84, + 0x1E8D1: 84, + 0x1E8D2: 84, + 0x1E8D3: 84, + 0x1E8D4: 84, + 0x1E8D5: 84, + 0x1E8D6: 84, + 0x1E900: 68, + 0x1E901: 68, + 0x1E902: 68, + 0x1E903: 68, + 0x1E904: 68, + 0x1E905: 68, + 0x1E906: 68, + 0x1E907: 68, + 0x1E908: 68, + 0x1E909: 68, + 0x1E90A: 68, + 0x1E90B: 68, + 0x1E90C: 68, + 0x1E90D: 68, + 0x1E90E: 68, + 0x1E90F: 68, + 0x1E910: 68, + 0x1E911: 68, + 0x1E912: 68, + 0x1E913: 68, + 0x1E914: 68, + 0x1E915: 68, + 0x1E916: 68, + 0x1E917: 68, + 0x1E918: 68, + 0x1E919: 68, + 0x1E91A: 68, + 0x1E91B: 68, + 0x1E91C: 68, + 0x1E91D: 68, + 0x1E91E: 68, + 0x1E91F: 68, + 0x1E920: 68, + 0x1E921: 68, + 0x1E922: 68, + 0x1E923: 68, + 0x1E924: 68, + 0x1E925: 68, + 0x1E926: 68, + 0x1E927: 68, + 0x1E928: 68, + 0x1E929: 68, + 0x1E92A: 68, + 0x1E92B: 68, + 0x1E92C: 68, + 0x1E92D: 68, + 0x1E92E: 68, + 0x1E92F: 68, + 0x1E930: 68, + 0x1E931: 68, + 0x1E932: 68, + 0x1E933: 68, + 0x1E934: 68, + 0x1E935: 68, + 0x1E936: 68, + 0x1E937: 68, + 0x1E938: 68, + 0x1E939: 68, + 0x1E93A: 68, + 0x1E93B: 68, + 0x1E93C: 68, + 0x1E93D: 68, + 0x1E93E: 68, + 0x1E93F: 68, + 0x1E940: 68, + 0x1E941: 68, + 0x1E942: 68, + 0x1E943: 68, + 0x1E944: 84, + 0x1E945: 84, + 0x1E946: 84, + 0x1E947: 84, + 0x1E948: 84, + 0x1E949: 84, + 0x1E94A: 84, + 0x1E94B: 84, + 0xE0001: 84, + 0xE0020: 84, + 0xE0021: 84, + 0xE0022: 84, + 0xE0023: 84, + 0xE0024: 84, + 0xE0025: 84, + 0xE0026: 84, + 0xE0027: 84, + 0xE0028: 84, + 0xE0029: 84, + 0xE002A: 84, + 0xE002B: 84, + 0xE002C: 84, + 0xE002D: 84, + 0xE002E: 84, + 0xE002F: 84, + 0xE0030: 84, + 0xE0031: 84, + 0xE0032: 84, + 0xE0033: 84, + 0xE0034: 84, + 0xE0035: 84, + 0xE0036: 84, + 0xE0037: 84, + 0xE0038: 84, + 0xE0039: 84, + 0xE003A: 84, + 0xE003B: 84, + 0xE003C: 84, + 0xE003D: 84, + 0xE003E: 84, + 0xE003F: 84, + 0xE0040: 84, + 0xE0041: 84, + 0xE0042: 84, + 0xE0043: 84, + 0xE0044: 84, + 0xE0045: 84, + 0xE0046: 84, + 0xE0047: 84, + 0xE0048: 84, + 0xE0049: 84, + 0xE004A: 84, + 0xE004B: 84, + 0xE004C: 84, + 0xE004D: 84, + 0xE004E: 84, + 0xE004F: 84, + 0xE0050: 84, + 0xE0051: 84, + 0xE0052: 84, + 0xE0053: 84, + 0xE0054: 84, + 0xE0055: 84, + 0xE0056: 84, + 0xE0057: 84, + 0xE0058: 84, + 0xE0059: 84, + 0xE005A: 84, + 0xE005B: 84, + 0xE005C: 84, + 0xE005D: 84, + 0xE005E: 84, + 0xE005F: 84, + 0xE0060: 84, + 0xE0061: 84, + 0xE0062: 84, + 0xE0063: 84, + 0xE0064: 84, + 0xE0065: 84, + 0xE0066: 84, + 0xE0067: 84, + 0xE0068: 84, + 0xE0069: 84, + 0xE006A: 84, + 0xE006B: 84, + 0xE006C: 84, + 0xE006D: 84, + 0xE006E: 84, + 0xE006F: 84, + 0xE0070: 84, + 0xE0071: 84, + 0xE0072: 84, + 0xE0073: 84, + 0xE0074: 84, + 0xE0075: 84, + 0xE0076: 84, + 0xE0077: 84, + 0xE0078: 84, + 0xE0079: 84, + 0xE007A: 84, + 0xE007B: 84, + 0xE007C: 84, + 0xE007D: 84, + 0xE007E: 84, + 0xE007F: 84, + 0xE0100: 84, + 0xE0101: 84, + 0xE0102: 84, + 0xE0103: 84, + 0xE0104: 84, + 0xE0105: 84, + 0xE0106: 84, + 0xE0107: 84, + 0xE0108: 84, + 0xE0109: 84, + 0xE010A: 84, + 0xE010B: 84, + 0xE010C: 84, + 0xE010D: 84, + 0xE010E: 84, + 0xE010F: 84, + 0xE0110: 84, + 0xE0111: 84, + 0xE0112: 84, + 0xE0113: 84, + 0xE0114: 84, + 0xE0115: 84, + 0xE0116: 84, + 0xE0117: 84, + 0xE0118: 84, + 0xE0119: 84, + 0xE011A: 84, + 0xE011B: 84, + 0xE011C: 84, + 0xE011D: 84, + 0xE011E: 84, + 0xE011F: 84, + 0xE0120: 84, + 0xE0121: 84, + 0xE0122: 84, + 0xE0123: 84, + 0xE0124: 84, + 0xE0125: 84, + 0xE0126: 84, + 0xE0127: 84, + 0xE0128: 84, + 0xE0129: 84, + 0xE012A: 84, + 0xE012B: 84, + 0xE012C: 84, + 0xE012D: 84, + 0xE012E: 84, + 0xE012F: 84, + 0xE0130: 84, + 0xE0131: 84, + 0xE0132: 84, + 0xE0133: 84, + 0xE0134: 84, + 0xE0135: 84, + 0xE0136: 84, + 0xE0137: 84, + 0xE0138: 84, + 0xE0139: 84, + 0xE013A: 84, + 0xE013B: 84, + 0xE013C: 84, + 0xE013D: 84, + 0xE013E: 84, + 0xE013F: 84, + 0xE0140: 84, + 0xE0141: 84, + 0xE0142: 84, + 0xE0143: 84, + 0xE0144: 84, + 0xE0145: 84, + 0xE0146: 84, + 0xE0147: 84, + 0xE0148: 84, + 0xE0149: 84, + 0xE014A: 84, + 0xE014B: 84, + 0xE014C: 84, + 0xE014D: 84, + 0xE014E: 84, + 0xE014F: 84, + 0xE0150: 84, + 0xE0151: 84, + 0xE0152: 84, + 0xE0153: 84, + 0xE0154: 84, + 0xE0155: 84, + 0xE0156: 84, + 0xE0157: 84, + 0xE0158: 84, + 0xE0159: 84, + 0xE015A: 84, + 0xE015B: 84, + 0xE015C: 84, + 0xE015D: 84, + 0xE015E: 84, + 0xE015F: 84, + 0xE0160: 84, + 0xE0161: 84, + 0xE0162: 84, + 0xE0163: 84, + 0xE0164: 84, + 0xE0165: 84, + 0xE0166: 84, + 0xE0167: 84, + 0xE0168: 84, + 0xE0169: 84, + 0xE016A: 84, + 0xE016B: 84, + 0xE016C: 84, + 0xE016D: 84, + 0xE016E: 84, + 0xE016F: 84, + 0xE0170: 84, + 0xE0171: 84, + 0xE0172: 84, + 0xE0173: 84, + 0xE0174: 84, + 0xE0175: 84, + 0xE0176: 84, + 0xE0177: 84, + 0xE0178: 84, + 0xE0179: 84, + 0xE017A: 84, + 0xE017B: 84, + 0xE017C: 84, + 0xE017D: 84, + 0xE017E: 84, + 0xE017F: 84, + 0xE0180: 84, + 0xE0181: 84, + 0xE0182: 84, + 0xE0183: 84, + 0xE0184: 84, + 0xE0185: 84, + 0xE0186: 84, + 0xE0187: 84, + 0xE0188: 84, + 0xE0189: 84, + 0xE018A: 84, + 0xE018B: 84, + 0xE018C: 84, + 0xE018D: 84, + 0xE018E: 84, + 0xE018F: 84, + 0xE0190: 84, + 0xE0191: 84, + 0xE0192: 84, + 0xE0193: 84, + 0xE0194: 84, + 0xE0195: 84, + 0xE0196: 84, + 0xE0197: 84, + 0xE0198: 84, + 0xE0199: 84, + 0xE019A: 84, + 0xE019B: 84, + 0xE019C: 84, + 0xE019D: 84, + 0xE019E: 84, + 0xE019F: 84, + 0xE01A0: 84, + 0xE01A1: 84, + 0xE01A2: 84, + 0xE01A3: 84, + 0xE01A4: 84, + 0xE01A5: 84, + 0xE01A6: 84, + 0xE01A7: 84, + 0xE01A8: 84, + 0xE01A9: 84, + 0xE01AA: 84, + 0xE01AB: 84, + 0xE01AC: 84, + 0xE01AD: 84, + 0xE01AE: 84, + 0xE01AF: 84, + 0xE01B0: 84, + 0xE01B1: 84, + 0xE01B2: 84, + 0xE01B3: 84, + 0xE01B4: 84, + 0xE01B5: 84, + 0xE01B6: 84, + 0xE01B7: 84, + 0xE01B8: 84, + 0xE01B9: 84, + 0xE01BA: 84, + 0xE01BB: 84, + 0xE01BC: 84, + 0xE01BD: 84, + 0xE01BE: 84, + 0xE01BF: 84, + 0xE01C0: 84, + 0xE01C1: 84, + 0xE01C2: 84, + 0xE01C3: 84, + 0xE01C4: 84, + 0xE01C5: 84, + 0xE01C6: 84, + 0xE01C7: 84, + 0xE01C8: 84, + 0xE01C9: 84, + 0xE01CA: 84, + 0xE01CB: 84, + 0xE01CC: 84, + 0xE01CD: 84, + 0xE01CE: 84, + 0xE01CF: 84, + 0xE01D0: 84, + 0xE01D1: 84, + 0xE01D2: 84, + 0xE01D3: 84, + 0xE01D4: 84, + 0xE01D5: 84, + 0xE01D6: 84, + 0xE01D7: 84, + 0xE01D8: 84, + 0xE01D9: 84, + 0xE01DA: 84, + 0xE01DB: 84, + 0xE01DC: 84, + 0xE01DD: 84, + 0xE01DE: 84, + 0xE01DF: 84, + 0xE01E0: 84, + 0xE01E1: 84, + 0xE01E2: 84, + 0xE01E3: 84, + 0xE01E4: 84, + 0xE01E5: 84, + 0xE01E6: 84, + 0xE01E7: 84, + 0xE01E8: 84, + 0xE01E9: 84, + 0xE01EA: 84, + 0xE01EB: 84, + 0xE01EC: 84, + 0xE01ED: 84, + 0xE01EE: 84, + 0xE01EF: 84, } codepoint_classes = { - 'PVALID': ( - 0x2d0000002e, - 0x300000003a, - 0x610000007b, - 0xdf000000f7, - 0xf800000100, + "PVALID": ( + 0x2D0000002E, + 0x300000003A, + 0x610000007B, + 0xDF000000F7, + 0xF800000100, 0x10100000102, 0x10300000104, 0x10500000106, 0x10700000108, - 0x1090000010a, - 0x10b0000010c, - 0x10d0000010e, - 0x10f00000110, + 0x1090000010A, + 0x10B0000010C, + 0x10D0000010E, + 0x10F00000110, 0x11100000112, 0x11300000114, 0x11500000116, 0x11700000118, - 0x1190000011a, - 0x11b0000011c, - 0x11d0000011e, - 0x11f00000120, + 0x1190000011A, + 0x11B0000011C, + 0x11D0000011E, + 0x11F00000120, 0x12100000122, 0x12300000124, 0x12500000126, 0x12700000128, - 0x1290000012a, - 0x12b0000012c, - 0x12d0000012e, - 0x12f00000130, + 0x1290000012A, + 0x12B0000012C, + 0x12D0000012E, + 0x12F00000130, 0x13100000132, 0x13500000136, 0x13700000139, - 0x13a0000013b, - 0x13c0000013d, - 0x13e0000013f, + 0x13A0000013B, + 0x13C0000013D, + 0x13E0000013F, 0x14200000143, 0x14400000145, 0x14600000147, 0x14800000149, - 0x14b0000014c, - 0x14d0000014e, - 0x14f00000150, + 0x14B0000014C, + 0x14D0000014E, + 0x14F00000150, 0x15100000152, 0x15300000154, 0x15500000156, 0x15700000158, - 0x1590000015a, - 0x15b0000015c, - 0x15d0000015e, - 0x15f00000160, + 0x1590000015A, + 0x15B0000015C, + 0x15D0000015E, + 0x15F00000160, 0x16100000162, 0x16300000164, 0x16500000166, 0x16700000168, - 0x1690000016a, - 0x16b0000016c, - 0x16d0000016e, - 0x16f00000170, + 0x1690000016A, + 0x16B0000016C, + 0x16D0000016E, + 0x16F00000170, 0x17100000172, 0x17300000174, 0x17500000176, 0x17700000178, - 0x17a0000017b, - 0x17c0000017d, - 0x17e0000017f, + 0x17A0000017B, + 0x17C0000017D, + 0x17E0000017F, 0x18000000181, 0x18300000184, 0x18500000186, 0x18800000189, - 0x18c0000018e, + 0x18C0000018E, 0x19200000193, 0x19500000196, - 0x1990000019c, - 0x19e0000019f, - 0x1a1000001a2, - 0x1a3000001a4, - 0x1a5000001a6, - 0x1a8000001a9, - 0x1aa000001ac, - 0x1ad000001ae, - 0x1b0000001b1, - 0x1b4000001b5, - 0x1b6000001b7, - 0x1b9000001bc, - 0x1bd000001c4, - 0x1ce000001cf, - 0x1d0000001d1, - 0x1d2000001d3, - 0x1d4000001d5, - 0x1d6000001d7, - 0x1d8000001d9, - 0x1da000001db, - 0x1dc000001de, - 0x1df000001e0, - 0x1e1000001e2, - 0x1e3000001e4, - 0x1e5000001e6, - 0x1e7000001e8, - 0x1e9000001ea, - 0x1eb000001ec, - 0x1ed000001ee, - 0x1ef000001f1, - 0x1f5000001f6, - 0x1f9000001fa, - 0x1fb000001fc, - 0x1fd000001fe, - 0x1ff00000200, + 0x1990000019C, + 0x19E0000019F, + 0x1A1000001A2, + 0x1A3000001A4, + 0x1A5000001A6, + 0x1A8000001A9, + 0x1AA000001AC, + 0x1AD000001AE, + 0x1B0000001B1, + 0x1B4000001B5, + 0x1B6000001B7, + 0x1B9000001BC, + 0x1BD000001C4, + 0x1CE000001CF, + 0x1D0000001D1, + 0x1D2000001D3, + 0x1D4000001D5, + 0x1D6000001D7, + 0x1D8000001D9, + 0x1DA000001DB, + 0x1DC000001DE, + 0x1DF000001E0, + 0x1E1000001E2, + 0x1E3000001E4, + 0x1E5000001E6, + 0x1E7000001E8, + 0x1E9000001EA, + 0x1EB000001EC, + 0x1ED000001EE, + 0x1EF000001F1, + 0x1F5000001F6, + 0x1F9000001FA, + 0x1FB000001FC, + 0x1FD000001FE, + 0x1FF00000200, 0x20100000202, 0x20300000204, 0x20500000206, 0x20700000208, - 0x2090000020a, - 0x20b0000020c, - 0x20d0000020e, - 0x20f00000210, + 0x2090000020A, + 0x20B0000020C, + 0x20D0000020E, + 0x20F00000210, 0x21100000212, 0x21300000214, 0x21500000216, 0x21700000218, - 0x2190000021a, - 0x21b0000021c, - 0x21d0000021e, - 0x21f00000220, + 0x2190000021A, + 0x21B0000021C, + 0x21D0000021E, + 0x21F00000220, 0x22100000222, 0x22300000224, 0x22500000226, 0x22700000228, - 0x2290000022a, - 0x22b0000022c, - 0x22d0000022e, - 0x22f00000230, + 0x2290000022A, + 0x22B0000022C, + 0x22D0000022E, + 0x22F00000230, 0x23100000232, - 0x2330000023a, - 0x23c0000023d, - 0x23f00000241, + 0x2330000023A, + 0x23C0000023D, + 0x23F00000241, 0x24200000243, 0x24700000248, - 0x2490000024a, - 0x24b0000024c, - 0x24d0000024e, - 0x24f000002b0, - 0x2b9000002c2, - 0x2c6000002d2, - 0x2ec000002ed, - 0x2ee000002ef, + 0x2490000024A, + 0x24B0000024C, + 0x24D0000024E, + 0x24F000002B0, + 0x2B9000002C2, + 0x2C6000002D2, + 0x2EC000002ED, + 0x2EE000002EF, 0x30000000340, 0x34200000343, - 0x3460000034f, + 0x3460000034F, 0x35000000370, 0x37100000372, 0x37300000374, 0x37700000378, - 0x37b0000037e, + 0x37B0000037E, 0x39000000391, - 0x3ac000003cf, - 0x3d7000003d8, - 0x3d9000003da, - 0x3db000003dc, - 0x3dd000003de, - 0x3df000003e0, - 0x3e1000003e2, - 0x3e3000003e4, - 0x3e5000003e6, - 0x3e7000003e8, - 0x3e9000003ea, - 0x3eb000003ec, - 0x3ed000003ee, - 0x3ef000003f0, - 0x3f3000003f4, - 0x3f8000003f9, - 0x3fb000003fd, + 0x3AC000003CF, + 0x3D7000003D8, + 0x3D9000003DA, + 0x3DB000003DC, + 0x3DD000003DE, + 0x3DF000003E0, + 0x3E1000003E2, + 0x3E3000003E4, + 0x3E5000003E6, + 0x3E7000003E8, + 0x3E9000003EA, + 0x3EB000003EC, + 0x3ED000003EE, + 0x3EF000003F0, + 0x3F3000003F4, + 0x3F8000003F9, + 0x3FB000003FD, 0x43000000460, 0x46100000462, 0x46300000464, 0x46500000466, 0x46700000468, - 0x4690000046a, - 0x46b0000046c, - 0x46d0000046e, - 0x46f00000470, + 0x4690000046A, + 0x46B0000046C, + 0x46D0000046E, + 0x46F00000470, 0x47100000472, 0x47300000474, 0x47500000476, 0x47700000478, - 0x4790000047a, - 0x47b0000047c, - 0x47d0000047e, - 0x47f00000480, + 0x4790000047A, + 0x47B0000047C, + 0x47D0000047E, + 0x47F00000480, 0x48100000482, 0x48300000488, - 0x48b0000048c, - 0x48d0000048e, - 0x48f00000490, + 0x48B0000048C, + 0x48D0000048E, + 0x48F00000490, 0x49100000492, 0x49300000494, 0x49500000496, 0x49700000498, - 0x4990000049a, - 0x49b0000049c, - 0x49d0000049e, - 0x49f000004a0, - 0x4a1000004a2, - 0x4a3000004a4, - 0x4a5000004a6, - 0x4a7000004a8, - 0x4a9000004aa, - 0x4ab000004ac, - 0x4ad000004ae, - 0x4af000004b0, - 0x4b1000004b2, - 0x4b3000004b4, - 0x4b5000004b6, - 0x4b7000004b8, - 0x4b9000004ba, - 0x4bb000004bc, - 0x4bd000004be, - 0x4bf000004c0, - 0x4c2000004c3, - 0x4c4000004c5, - 0x4c6000004c7, - 0x4c8000004c9, - 0x4ca000004cb, - 0x4cc000004cd, - 0x4ce000004d0, - 0x4d1000004d2, - 0x4d3000004d4, - 0x4d5000004d6, - 0x4d7000004d8, - 0x4d9000004da, - 0x4db000004dc, - 0x4dd000004de, - 0x4df000004e0, - 0x4e1000004e2, - 0x4e3000004e4, - 0x4e5000004e6, - 0x4e7000004e8, - 0x4e9000004ea, - 0x4eb000004ec, - 0x4ed000004ee, - 0x4ef000004f0, - 0x4f1000004f2, - 0x4f3000004f4, - 0x4f5000004f6, - 0x4f7000004f8, - 0x4f9000004fa, - 0x4fb000004fc, - 0x4fd000004fe, - 0x4ff00000500, + 0x4990000049A, + 0x49B0000049C, + 0x49D0000049E, + 0x49F000004A0, + 0x4A1000004A2, + 0x4A3000004A4, + 0x4A5000004A6, + 0x4A7000004A8, + 0x4A9000004AA, + 0x4AB000004AC, + 0x4AD000004AE, + 0x4AF000004B0, + 0x4B1000004B2, + 0x4B3000004B4, + 0x4B5000004B6, + 0x4B7000004B8, + 0x4B9000004BA, + 0x4BB000004BC, + 0x4BD000004BE, + 0x4BF000004C0, + 0x4C2000004C3, + 0x4C4000004C5, + 0x4C6000004C7, + 0x4C8000004C9, + 0x4CA000004CB, + 0x4CC000004CD, + 0x4CE000004D0, + 0x4D1000004D2, + 0x4D3000004D4, + 0x4D5000004D6, + 0x4D7000004D8, + 0x4D9000004DA, + 0x4DB000004DC, + 0x4DD000004DE, + 0x4DF000004E0, + 0x4E1000004E2, + 0x4E3000004E4, + 0x4E5000004E6, + 0x4E7000004E8, + 0x4E9000004EA, + 0x4EB000004EC, + 0x4ED000004EE, + 0x4EF000004F0, + 0x4F1000004F2, + 0x4F3000004F4, + 0x4F5000004F6, + 0x4F7000004F8, + 0x4F9000004FA, + 0x4FB000004FC, + 0x4FD000004FE, + 0x4FF00000500, 0x50100000502, 0x50300000504, 0x50500000506, 0x50700000508, - 0x5090000050a, - 0x50b0000050c, - 0x50d0000050e, - 0x50f00000510, + 0x5090000050A, + 0x50B0000050C, + 0x50D0000050E, + 0x50F00000510, 0x51100000512, 0x51300000514, 0x51500000516, 0x51700000518, - 0x5190000051a, - 0x51b0000051c, - 0x51d0000051e, - 0x51f00000520, + 0x5190000051A, + 0x51B0000051C, + 0x51D0000051E, + 0x51F00000520, 0x52100000522, 0x52300000524, 0x52500000526, 0x52700000528, - 0x5290000052a, - 0x52b0000052c, - 0x52d0000052e, - 0x52f00000530, - 0x5590000055a, + 0x5290000052A, + 0x52B0000052C, + 0x52D0000052E, + 0x52F00000530, + 0x5590000055A, 0x56000000587, 0x58800000589, - 0x591000005be, - 0x5bf000005c0, - 0x5c1000005c3, - 0x5c4000005c6, - 0x5c7000005c8, - 0x5d0000005eb, - 0x5ef000005f3, - 0x6100000061b, + 0x591000005BE, + 0x5BF000005C0, + 0x5C1000005C3, + 0x5C4000005C6, + 0x5C7000005C8, + 0x5D0000005EB, + 0x5EF000005F3, + 0x6100000061B, 0x62000000640, 0x64100000660, - 0x66e00000675, - 0x679000006d4, - 0x6d5000006dd, - 0x6df000006e9, - 0x6ea000006f0, - 0x6fa00000700, - 0x7100000074b, - 0x74d000007b2, - 0x7c0000007f6, - 0x7fd000007fe, - 0x8000000082e, - 0x8400000085c, - 0x8600000086b, + 0x66E00000675, + 0x679000006D4, + 0x6D5000006DD, + 0x6DF000006E9, + 0x6EA000006F0, + 0x6FA00000700, + 0x7100000074B, + 0x74D000007B2, + 0x7C0000007F6, + 0x7FD000007FE, + 0x8000000082E, + 0x8400000085C, + 0x8600000086B, 0x87000000888, - 0x8890000088f, - 0x898000008e2, - 0x8e300000958, + 0x8890000088F, + 0x898000008E2, + 0x8E300000958, 0x96000000964, 0x96600000970, 0x97100000984, - 0x9850000098d, - 0x98f00000991, - 0x993000009a9, - 0x9aa000009b1, - 0x9b2000009b3, - 0x9b6000009ba, - 0x9bc000009c5, - 0x9c7000009c9, - 0x9cb000009cf, - 0x9d7000009d8, - 0x9e0000009e4, - 0x9e6000009f2, - 0x9fc000009fd, - 0x9fe000009ff, - 0xa0100000a04, - 0xa0500000a0b, - 0xa0f00000a11, - 0xa1300000a29, - 0xa2a00000a31, - 0xa3200000a33, - 0xa3500000a36, - 0xa3800000a3a, - 0xa3c00000a3d, - 0xa3e00000a43, - 0xa4700000a49, - 0xa4b00000a4e, - 0xa5100000a52, - 0xa5c00000a5d, - 0xa6600000a76, - 0xa8100000a84, - 0xa8500000a8e, - 0xa8f00000a92, - 0xa9300000aa9, - 0xaaa00000ab1, - 0xab200000ab4, - 0xab500000aba, - 0xabc00000ac6, - 0xac700000aca, - 0xacb00000ace, - 0xad000000ad1, - 0xae000000ae4, - 0xae600000af0, - 0xaf900000b00, - 0xb0100000b04, - 0xb0500000b0d, - 0xb0f00000b11, - 0xb1300000b29, - 0xb2a00000b31, - 0xb3200000b34, - 0xb3500000b3a, - 0xb3c00000b45, - 0xb4700000b49, - 0xb4b00000b4e, - 0xb5500000b58, - 0xb5f00000b64, - 0xb6600000b70, - 0xb7100000b72, - 0xb8200000b84, - 0xb8500000b8b, - 0xb8e00000b91, - 0xb9200000b96, - 0xb9900000b9b, - 0xb9c00000b9d, - 0xb9e00000ba0, - 0xba300000ba5, - 0xba800000bab, - 0xbae00000bba, - 0xbbe00000bc3, - 0xbc600000bc9, - 0xbca00000bce, - 0xbd000000bd1, - 0xbd700000bd8, - 0xbe600000bf0, - 0xc0000000c0d, - 0xc0e00000c11, - 0xc1200000c29, - 0xc2a00000c3a, - 0xc3c00000c45, - 0xc4600000c49, - 0xc4a00000c4e, - 0xc5500000c57, - 0xc5800000c5b, - 0xc5d00000c5e, - 0xc6000000c64, - 0xc6600000c70, - 0xc8000000c84, - 0xc8500000c8d, - 0xc8e00000c91, - 0xc9200000ca9, - 0xcaa00000cb4, - 0xcb500000cba, - 0xcbc00000cc5, - 0xcc600000cc9, - 0xcca00000cce, - 0xcd500000cd7, - 0xcdd00000cdf, - 0xce000000ce4, - 0xce600000cf0, - 0xcf100000cf4, - 0xd0000000d0d, - 0xd0e00000d11, - 0xd1200000d45, - 0xd4600000d49, - 0xd4a00000d4f, - 0xd5400000d58, - 0xd5f00000d64, - 0xd6600000d70, - 0xd7a00000d80, - 0xd8100000d84, - 0xd8500000d97, - 0xd9a00000db2, - 0xdb300000dbc, - 0xdbd00000dbe, - 0xdc000000dc7, - 0xdca00000dcb, - 0xdcf00000dd5, - 0xdd600000dd7, - 0xdd800000de0, - 0xde600000df0, - 0xdf200000df4, - 0xe0100000e33, - 0xe3400000e3b, - 0xe4000000e4f, - 0xe5000000e5a, - 0xe8100000e83, - 0xe8400000e85, - 0xe8600000e8b, - 0xe8c00000ea4, - 0xea500000ea6, - 0xea700000eb3, - 0xeb400000ebe, - 0xec000000ec5, - 0xec600000ec7, - 0xec800000ecf, - 0xed000000eda, - 0xede00000ee0, - 0xf0000000f01, - 0xf0b00000f0c, - 0xf1800000f1a, - 0xf2000000f2a, - 0xf3500000f36, - 0xf3700000f38, - 0xf3900000f3a, - 0xf3e00000f43, - 0xf4400000f48, - 0xf4900000f4d, - 0xf4e00000f52, - 0xf5300000f57, - 0xf5800000f5c, - 0xf5d00000f69, - 0xf6a00000f6d, - 0xf7100000f73, - 0xf7400000f75, - 0xf7a00000f81, - 0xf8200000f85, - 0xf8600000f93, - 0xf9400000f98, - 0xf9900000f9d, - 0xf9e00000fa2, - 0xfa300000fa7, - 0xfa800000fac, - 0xfad00000fb9, - 0xfba00000fbd, - 0xfc600000fc7, - 0x10000000104a, - 0x10500000109e, - 0x10d0000010fb, - 0x10fd00001100, + 0x9850000098D, + 0x98F00000991, + 0x993000009A9, + 0x9AA000009B1, + 0x9B2000009B3, + 0x9B6000009BA, + 0x9BC000009C5, + 0x9C7000009C9, + 0x9CB000009CF, + 0x9D7000009D8, + 0x9E0000009E4, + 0x9E6000009F2, + 0x9FC000009FD, + 0x9FE000009FF, + 0xA0100000A04, + 0xA0500000A0B, + 0xA0F00000A11, + 0xA1300000A29, + 0xA2A00000A31, + 0xA3200000A33, + 0xA3500000A36, + 0xA3800000A3A, + 0xA3C00000A3D, + 0xA3E00000A43, + 0xA4700000A49, + 0xA4B00000A4E, + 0xA5100000A52, + 0xA5C00000A5D, + 0xA6600000A76, + 0xA8100000A84, + 0xA8500000A8E, + 0xA8F00000A92, + 0xA9300000AA9, + 0xAAA00000AB1, + 0xAB200000AB4, + 0xAB500000ABA, + 0xABC00000AC6, + 0xAC700000ACA, + 0xACB00000ACE, + 0xAD000000AD1, + 0xAE000000AE4, + 0xAE600000AF0, + 0xAF900000B00, + 0xB0100000B04, + 0xB0500000B0D, + 0xB0F00000B11, + 0xB1300000B29, + 0xB2A00000B31, + 0xB3200000B34, + 0xB3500000B3A, + 0xB3C00000B45, + 0xB4700000B49, + 0xB4B00000B4E, + 0xB5500000B58, + 0xB5F00000B64, + 0xB6600000B70, + 0xB7100000B72, + 0xB8200000B84, + 0xB8500000B8B, + 0xB8E00000B91, + 0xB9200000B96, + 0xB9900000B9B, + 0xB9C00000B9D, + 0xB9E00000BA0, + 0xBA300000BA5, + 0xBA800000BAB, + 0xBAE00000BBA, + 0xBBE00000BC3, + 0xBC600000BC9, + 0xBCA00000BCE, + 0xBD000000BD1, + 0xBD700000BD8, + 0xBE600000BF0, + 0xC0000000C0D, + 0xC0E00000C11, + 0xC1200000C29, + 0xC2A00000C3A, + 0xC3C00000C45, + 0xC4600000C49, + 0xC4A00000C4E, + 0xC5500000C57, + 0xC5800000C5B, + 0xC5D00000C5E, + 0xC6000000C64, + 0xC6600000C70, + 0xC8000000C84, + 0xC8500000C8D, + 0xC8E00000C91, + 0xC9200000CA9, + 0xCAA00000CB4, + 0xCB500000CBA, + 0xCBC00000CC5, + 0xCC600000CC9, + 0xCCA00000CCE, + 0xCD500000CD7, + 0xCDD00000CDF, + 0xCE000000CE4, + 0xCE600000CF0, + 0xCF100000CF4, + 0xD0000000D0D, + 0xD0E00000D11, + 0xD1200000D45, + 0xD4600000D49, + 0xD4A00000D4F, + 0xD5400000D58, + 0xD5F00000D64, + 0xD6600000D70, + 0xD7A00000D80, + 0xD8100000D84, + 0xD8500000D97, + 0xD9A00000DB2, + 0xDB300000DBC, + 0xDBD00000DBE, + 0xDC000000DC7, + 0xDCA00000DCB, + 0xDCF00000DD5, + 0xDD600000DD7, + 0xDD800000DE0, + 0xDE600000DF0, + 0xDF200000DF4, + 0xE0100000E33, + 0xE3400000E3B, + 0xE4000000E4F, + 0xE5000000E5A, + 0xE8100000E83, + 0xE8400000E85, + 0xE8600000E8B, + 0xE8C00000EA4, + 0xEA500000EA6, + 0xEA700000EB3, + 0xEB400000EBE, + 0xEC000000EC5, + 0xEC600000EC7, + 0xEC800000ECF, + 0xED000000EDA, + 0xEDE00000EE0, + 0xF0000000F01, + 0xF0B00000F0C, + 0xF1800000F1A, + 0xF2000000F2A, + 0xF3500000F36, + 0xF3700000F38, + 0xF3900000F3A, + 0xF3E00000F43, + 0xF4400000F48, + 0xF4900000F4D, + 0xF4E00000F52, + 0xF5300000F57, + 0xF5800000F5C, + 0xF5D00000F69, + 0xF6A00000F6D, + 0xF7100000F73, + 0xF7400000F75, + 0xF7A00000F81, + 0xF8200000F85, + 0xF8600000F93, + 0xF9400000F98, + 0xF9900000F9D, + 0xF9E00000FA2, + 0xFA300000FA7, + 0xFA800000FAC, + 0xFAD00000FB9, + 0xFBA00000FBD, + 0xFC600000FC7, + 0x10000000104A, + 0x10500000109E, + 0x10D0000010FB, + 0x10FD00001100, 0x120000001249, - 0x124a0000124e, + 0x124A0000124E, 0x125000001257, 0x125800001259, - 0x125a0000125e, + 0x125A0000125E, 0x126000001289, - 0x128a0000128e, - 0x1290000012b1, - 0x12b2000012b6, - 0x12b8000012bf, - 0x12c0000012c1, - 0x12c2000012c6, - 0x12c8000012d7, - 0x12d800001311, + 0x128A0000128E, + 0x1290000012B1, + 0x12B2000012B6, + 0x12B8000012BF, + 0x12C0000012C1, + 0x12C2000012C6, + 0x12C8000012D7, + 0x12D800001311, 0x131200001316, - 0x13180000135b, - 0x135d00001360, + 0x13180000135B, + 0x135D00001360, 0x138000001390, - 0x13a0000013f6, - 0x14010000166d, - 0x166f00001680, - 0x16810000169b, - 0x16a0000016eb, - 0x16f1000016f9, + 0x13A0000013F6, + 0x14010000166D, + 0x166F00001680, + 0x16810000169B, + 0x16A0000016EB, + 0x16F1000016F9, 0x170000001716, - 0x171f00001735, + 0x171F00001735, 0x174000001754, - 0x17600000176d, - 0x176e00001771, + 0x17600000176D, + 0x176E00001771, 0x177200001774, - 0x1780000017b4, - 0x17b6000017d4, - 0x17d7000017d8, - 0x17dc000017de, - 0x17e0000017ea, - 0x18100000181a, + 0x1780000017B4, + 0x17B6000017D4, + 0x17D7000017D8, + 0x17DC000017DE, + 0x17E0000017EA, + 0x18100000181A, 0x182000001879, - 0x1880000018ab, - 0x18b0000018f6, - 0x19000000191f, - 0x19200000192c, - 0x19300000193c, - 0x19460000196e, + 0x1880000018AB, + 0x18B0000018F6, + 0x19000000191F, + 0x19200000192C, + 0x19300000193C, + 0x19460000196E, 0x197000001975, - 0x1980000019ac, - 0x19b0000019ca, - 0x19d0000019da, - 0x1a0000001a1c, - 0x1a2000001a5f, - 0x1a6000001a7d, - 0x1a7f00001a8a, - 0x1a9000001a9a, - 0x1aa700001aa8, - 0x1ab000001abe, - 0x1abf00001acf, - 0x1b0000001b4d, - 0x1b5000001b5a, - 0x1b6b00001b74, - 0x1b8000001bf4, - 0x1c0000001c38, - 0x1c4000001c4a, - 0x1c4d00001c7e, - 0x1cd000001cd3, - 0x1cd400001cfb, - 0x1d0000001d2c, - 0x1d2f00001d30, - 0x1d3b00001d3c, - 0x1d4e00001d4f, - 0x1d6b00001d78, - 0x1d7900001d9b, - 0x1dc000001e00, - 0x1e0100001e02, - 0x1e0300001e04, - 0x1e0500001e06, - 0x1e0700001e08, - 0x1e0900001e0a, - 0x1e0b00001e0c, - 0x1e0d00001e0e, - 0x1e0f00001e10, - 0x1e1100001e12, - 0x1e1300001e14, - 0x1e1500001e16, - 0x1e1700001e18, - 0x1e1900001e1a, - 0x1e1b00001e1c, - 0x1e1d00001e1e, - 0x1e1f00001e20, - 0x1e2100001e22, - 0x1e2300001e24, - 0x1e2500001e26, - 0x1e2700001e28, - 0x1e2900001e2a, - 0x1e2b00001e2c, - 0x1e2d00001e2e, - 0x1e2f00001e30, - 0x1e3100001e32, - 0x1e3300001e34, - 0x1e3500001e36, - 0x1e3700001e38, - 0x1e3900001e3a, - 0x1e3b00001e3c, - 0x1e3d00001e3e, - 0x1e3f00001e40, - 0x1e4100001e42, - 0x1e4300001e44, - 0x1e4500001e46, - 0x1e4700001e48, - 0x1e4900001e4a, - 0x1e4b00001e4c, - 0x1e4d00001e4e, - 0x1e4f00001e50, - 0x1e5100001e52, - 0x1e5300001e54, - 0x1e5500001e56, - 0x1e5700001e58, - 0x1e5900001e5a, - 0x1e5b00001e5c, - 0x1e5d00001e5e, - 0x1e5f00001e60, - 0x1e6100001e62, - 0x1e6300001e64, - 0x1e6500001e66, - 0x1e6700001e68, - 0x1e6900001e6a, - 0x1e6b00001e6c, - 0x1e6d00001e6e, - 0x1e6f00001e70, - 0x1e7100001e72, - 0x1e7300001e74, - 0x1e7500001e76, - 0x1e7700001e78, - 0x1e7900001e7a, - 0x1e7b00001e7c, - 0x1e7d00001e7e, - 0x1e7f00001e80, - 0x1e8100001e82, - 0x1e8300001e84, - 0x1e8500001e86, - 0x1e8700001e88, - 0x1e8900001e8a, - 0x1e8b00001e8c, - 0x1e8d00001e8e, - 0x1e8f00001e90, - 0x1e9100001e92, - 0x1e9300001e94, - 0x1e9500001e9a, - 0x1e9c00001e9e, - 0x1e9f00001ea0, - 0x1ea100001ea2, - 0x1ea300001ea4, - 0x1ea500001ea6, - 0x1ea700001ea8, - 0x1ea900001eaa, - 0x1eab00001eac, - 0x1ead00001eae, - 0x1eaf00001eb0, - 0x1eb100001eb2, - 0x1eb300001eb4, - 0x1eb500001eb6, - 0x1eb700001eb8, - 0x1eb900001eba, - 0x1ebb00001ebc, - 0x1ebd00001ebe, - 0x1ebf00001ec0, - 0x1ec100001ec2, - 0x1ec300001ec4, - 0x1ec500001ec6, - 0x1ec700001ec8, - 0x1ec900001eca, - 0x1ecb00001ecc, - 0x1ecd00001ece, - 0x1ecf00001ed0, - 0x1ed100001ed2, - 0x1ed300001ed4, - 0x1ed500001ed6, - 0x1ed700001ed8, - 0x1ed900001eda, - 0x1edb00001edc, - 0x1edd00001ede, - 0x1edf00001ee0, - 0x1ee100001ee2, - 0x1ee300001ee4, - 0x1ee500001ee6, - 0x1ee700001ee8, - 0x1ee900001eea, - 0x1eeb00001eec, - 0x1eed00001eee, - 0x1eef00001ef0, - 0x1ef100001ef2, - 0x1ef300001ef4, - 0x1ef500001ef6, - 0x1ef700001ef8, - 0x1ef900001efa, - 0x1efb00001efc, - 0x1efd00001efe, - 0x1eff00001f08, - 0x1f1000001f16, - 0x1f2000001f28, - 0x1f3000001f38, - 0x1f4000001f46, - 0x1f5000001f58, - 0x1f6000001f68, - 0x1f7000001f71, - 0x1f7200001f73, - 0x1f7400001f75, - 0x1f7600001f77, - 0x1f7800001f79, - 0x1f7a00001f7b, - 0x1f7c00001f7d, - 0x1fb000001fb2, - 0x1fb600001fb7, - 0x1fc600001fc7, - 0x1fd000001fd3, - 0x1fd600001fd8, - 0x1fe000001fe3, - 0x1fe400001fe8, - 0x1ff600001ff7, - 0x214e0000214f, + 0x1980000019AC, + 0x19B0000019CA, + 0x19D0000019DA, + 0x1A0000001A1C, + 0x1A2000001A5F, + 0x1A6000001A7D, + 0x1A7F00001A8A, + 0x1A9000001A9A, + 0x1AA700001AA8, + 0x1AB000001ABE, + 0x1ABF00001ACF, + 0x1B0000001B4D, + 0x1B5000001B5A, + 0x1B6B00001B74, + 0x1B8000001BF4, + 0x1C0000001C38, + 0x1C4000001C4A, + 0x1C4D00001C7E, + 0x1CD000001CD3, + 0x1CD400001CFB, + 0x1D0000001D2C, + 0x1D2F00001D30, + 0x1D3B00001D3C, + 0x1D4E00001D4F, + 0x1D6B00001D78, + 0x1D7900001D9B, + 0x1DC000001E00, + 0x1E0100001E02, + 0x1E0300001E04, + 0x1E0500001E06, + 0x1E0700001E08, + 0x1E0900001E0A, + 0x1E0B00001E0C, + 0x1E0D00001E0E, + 0x1E0F00001E10, + 0x1E1100001E12, + 0x1E1300001E14, + 0x1E1500001E16, + 0x1E1700001E18, + 0x1E1900001E1A, + 0x1E1B00001E1C, + 0x1E1D00001E1E, + 0x1E1F00001E20, + 0x1E2100001E22, + 0x1E2300001E24, + 0x1E2500001E26, + 0x1E2700001E28, + 0x1E2900001E2A, + 0x1E2B00001E2C, + 0x1E2D00001E2E, + 0x1E2F00001E30, + 0x1E3100001E32, + 0x1E3300001E34, + 0x1E3500001E36, + 0x1E3700001E38, + 0x1E3900001E3A, + 0x1E3B00001E3C, + 0x1E3D00001E3E, + 0x1E3F00001E40, + 0x1E4100001E42, + 0x1E4300001E44, + 0x1E4500001E46, + 0x1E4700001E48, + 0x1E4900001E4A, + 0x1E4B00001E4C, + 0x1E4D00001E4E, + 0x1E4F00001E50, + 0x1E5100001E52, + 0x1E5300001E54, + 0x1E5500001E56, + 0x1E5700001E58, + 0x1E5900001E5A, + 0x1E5B00001E5C, + 0x1E5D00001E5E, + 0x1E5F00001E60, + 0x1E6100001E62, + 0x1E6300001E64, + 0x1E6500001E66, + 0x1E6700001E68, + 0x1E6900001E6A, + 0x1E6B00001E6C, + 0x1E6D00001E6E, + 0x1E6F00001E70, + 0x1E7100001E72, + 0x1E7300001E74, + 0x1E7500001E76, + 0x1E7700001E78, + 0x1E7900001E7A, + 0x1E7B00001E7C, + 0x1E7D00001E7E, + 0x1E7F00001E80, + 0x1E8100001E82, + 0x1E8300001E84, + 0x1E8500001E86, + 0x1E8700001E88, + 0x1E8900001E8A, + 0x1E8B00001E8C, + 0x1E8D00001E8E, + 0x1E8F00001E90, + 0x1E9100001E92, + 0x1E9300001E94, + 0x1E9500001E9A, + 0x1E9C00001E9E, + 0x1E9F00001EA0, + 0x1EA100001EA2, + 0x1EA300001EA4, + 0x1EA500001EA6, + 0x1EA700001EA8, + 0x1EA900001EAA, + 0x1EAB00001EAC, + 0x1EAD00001EAE, + 0x1EAF00001EB0, + 0x1EB100001EB2, + 0x1EB300001EB4, + 0x1EB500001EB6, + 0x1EB700001EB8, + 0x1EB900001EBA, + 0x1EBB00001EBC, + 0x1EBD00001EBE, + 0x1EBF00001EC0, + 0x1EC100001EC2, + 0x1EC300001EC4, + 0x1EC500001EC6, + 0x1EC700001EC8, + 0x1EC900001ECA, + 0x1ECB00001ECC, + 0x1ECD00001ECE, + 0x1ECF00001ED0, + 0x1ED100001ED2, + 0x1ED300001ED4, + 0x1ED500001ED6, + 0x1ED700001ED8, + 0x1ED900001EDA, + 0x1EDB00001EDC, + 0x1EDD00001EDE, + 0x1EDF00001EE0, + 0x1EE100001EE2, + 0x1EE300001EE4, + 0x1EE500001EE6, + 0x1EE700001EE8, + 0x1EE900001EEA, + 0x1EEB00001EEC, + 0x1EED00001EEE, + 0x1EEF00001EF0, + 0x1EF100001EF2, + 0x1EF300001EF4, + 0x1EF500001EF6, + 0x1EF700001EF8, + 0x1EF900001EFA, + 0x1EFB00001EFC, + 0x1EFD00001EFE, + 0x1EFF00001F08, + 0x1F1000001F16, + 0x1F2000001F28, + 0x1F3000001F38, + 0x1F4000001F46, + 0x1F5000001F58, + 0x1F6000001F68, + 0x1F7000001F71, + 0x1F7200001F73, + 0x1F7400001F75, + 0x1F7600001F77, + 0x1F7800001F79, + 0x1F7A00001F7B, + 0x1F7C00001F7D, + 0x1FB000001FB2, + 0x1FB600001FB7, + 0x1FC600001FC7, + 0x1FD000001FD3, + 0x1FD600001FD8, + 0x1FE000001FE3, + 0x1FE400001FE8, + 0x1FF600001FF7, + 0x214E0000214F, 0x218400002185, - 0x2c3000002c60, - 0x2c6100002c62, - 0x2c6500002c67, - 0x2c6800002c69, - 0x2c6a00002c6b, - 0x2c6c00002c6d, - 0x2c7100002c72, - 0x2c7300002c75, - 0x2c7600002c7c, - 0x2c8100002c82, - 0x2c8300002c84, - 0x2c8500002c86, - 0x2c8700002c88, - 0x2c8900002c8a, - 0x2c8b00002c8c, - 0x2c8d00002c8e, - 0x2c8f00002c90, - 0x2c9100002c92, - 0x2c9300002c94, - 0x2c9500002c96, - 0x2c9700002c98, - 0x2c9900002c9a, - 0x2c9b00002c9c, - 0x2c9d00002c9e, - 0x2c9f00002ca0, - 0x2ca100002ca2, - 0x2ca300002ca4, - 0x2ca500002ca6, - 0x2ca700002ca8, - 0x2ca900002caa, - 0x2cab00002cac, - 0x2cad00002cae, - 0x2caf00002cb0, - 0x2cb100002cb2, - 0x2cb300002cb4, - 0x2cb500002cb6, - 0x2cb700002cb8, - 0x2cb900002cba, - 0x2cbb00002cbc, - 0x2cbd00002cbe, - 0x2cbf00002cc0, - 0x2cc100002cc2, - 0x2cc300002cc4, - 0x2cc500002cc6, - 0x2cc700002cc8, - 0x2cc900002cca, - 0x2ccb00002ccc, - 0x2ccd00002cce, - 0x2ccf00002cd0, - 0x2cd100002cd2, - 0x2cd300002cd4, - 0x2cd500002cd6, - 0x2cd700002cd8, - 0x2cd900002cda, - 0x2cdb00002cdc, - 0x2cdd00002cde, - 0x2cdf00002ce0, - 0x2ce100002ce2, - 0x2ce300002ce5, - 0x2cec00002ced, - 0x2cee00002cf2, - 0x2cf300002cf4, - 0x2d0000002d26, - 0x2d2700002d28, - 0x2d2d00002d2e, - 0x2d3000002d68, - 0x2d7f00002d97, - 0x2da000002da7, - 0x2da800002daf, - 0x2db000002db7, - 0x2db800002dbf, - 0x2dc000002dc7, - 0x2dc800002dcf, - 0x2dd000002dd7, - 0x2dd800002ddf, - 0x2de000002e00, - 0x2e2f00002e30, + 0x2C3000002C60, + 0x2C6100002C62, + 0x2C6500002C67, + 0x2C6800002C69, + 0x2C6A00002C6B, + 0x2C6C00002C6D, + 0x2C7100002C72, + 0x2C7300002C75, + 0x2C7600002C7C, + 0x2C8100002C82, + 0x2C8300002C84, + 0x2C8500002C86, + 0x2C8700002C88, + 0x2C8900002C8A, + 0x2C8B00002C8C, + 0x2C8D00002C8E, + 0x2C8F00002C90, + 0x2C9100002C92, + 0x2C9300002C94, + 0x2C9500002C96, + 0x2C9700002C98, + 0x2C9900002C9A, + 0x2C9B00002C9C, + 0x2C9D00002C9E, + 0x2C9F00002CA0, + 0x2CA100002CA2, + 0x2CA300002CA4, + 0x2CA500002CA6, + 0x2CA700002CA8, + 0x2CA900002CAA, + 0x2CAB00002CAC, + 0x2CAD00002CAE, + 0x2CAF00002CB0, + 0x2CB100002CB2, + 0x2CB300002CB4, + 0x2CB500002CB6, + 0x2CB700002CB8, + 0x2CB900002CBA, + 0x2CBB00002CBC, + 0x2CBD00002CBE, + 0x2CBF00002CC0, + 0x2CC100002CC2, + 0x2CC300002CC4, + 0x2CC500002CC6, + 0x2CC700002CC8, + 0x2CC900002CCA, + 0x2CCB00002CCC, + 0x2CCD00002CCE, + 0x2CCF00002CD0, + 0x2CD100002CD2, + 0x2CD300002CD4, + 0x2CD500002CD6, + 0x2CD700002CD8, + 0x2CD900002CDA, + 0x2CDB00002CDC, + 0x2CDD00002CDE, + 0x2CDF00002CE0, + 0x2CE100002CE2, + 0x2CE300002CE5, + 0x2CEC00002CED, + 0x2CEE00002CF2, + 0x2CF300002CF4, + 0x2D0000002D26, + 0x2D2700002D28, + 0x2D2D00002D2E, + 0x2D3000002D68, + 0x2D7F00002D97, + 0x2DA000002DA7, + 0x2DA800002DAF, + 0x2DB000002DB7, + 0x2DB800002DBF, + 0x2DC000002DC7, + 0x2DC800002DCF, + 0x2DD000002DD7, + 0x2DD800002DDF, + 0x2DE000002E00, + 0x2E2F00002E30, 0x300500003008, - 0x302a0000302e, - 0x303c0000303d, + 0x302A0000302E, + 0x303C0000303D, 0x304100003097, - 0x30990000309b, - 0x309d0000309f, - 0x30a1000030fb, - 0x30fc000030ff, + 0x30990000309B, + 0x309D0000309F, + 0x30A1000030FB, + 0x30FC000030FF, 0x310500003130, - 0x31a0000031c0, - 0x31f000003200, - 0x340000004dc0, - 0x4e000000a48d, - 0xa4d00000a4fe, - 0xa5000000a60d, - 0xa6100000a62c, - 0xa6410000a642, - 0xa6430000a644, - 0xa6450000a646, - 0xa6470000a648, - 0xa6490000a64a, - 0xa64b0000a64c, - 0xa64d0000a64e, - 0xa64f0000a650, - 0xa6510000a652, - 0xa6530000a654, - 0xa6550000a656, - 0xa6570000a658, - 0xa6590000a65a, - 0xa65b0000a65c, - 0xa65d0000a65e, - 0xa65f0000a660, - 0xa6610000a662, - 0xa6630000a664, - 0xa6650000a666, - 0xa6670000a668, - 0xa6690000a66a, - 0xa66b0000a66c, - 0xa66d0000a670, - 0xa6740000a67e, - 0xa67f0000a680, - 0xa6810000a682, - 0xa6830000a684, - 0xa6850000a686, - 0xa6870000a688, - 0xa6890000a68a, - 0xa68b0000a68c, - 0xa68d0000a68e, - 0xa68f0000a690, - 0xa6910000a692, - 0xa6930000a694, - 0xa6950000a696, - 0xa6970000a698, - 0xa6990000a69a, - 0xa69b0000a69c, - 0xa69e0000a6e6, - 0xa6f00000a6f2, - 0xa7170000a720, - 0xa7230000a724, - 0xa7250000a726, - 0xa7270000a728, - 0xa7290000a72a, - 0xa72b0000a72c, - 0xa72d0000a72e, - 0xa72f0000a732, - 0xa7330000a734, - 0xa7350000a736, - 0xa7370000a738, - 0xa7390000a73a, - 0xa73b0000a73c, - 0xa73d0000a73e, - 0xa73f0000a740, - 0xa7410000a742, - 0xa7430000a744, - 0xa7450000a746, - 0xa7470000a748, - 0xa7490000a74a, - 0xa74b0000a74c, - 0xa74d0000a74e, - 0xa74f0000a750, - 0xa7510000a752, - 0xa7530000a754, - 0xa7550000a756, - 0xa7570000a758, - 0xa7590000a75a, - 0xa75b0000a75c, - 0xa75d0000a75e, - 0xa75f0000a760, - 0xa7610000a762, - 0xa7630000a764, - 0xa7650000a766, - 0xa7670000a768, - 0xa7690000a76a, - 0xa76b0000a76c, - 0xa76d0000a76e, - 0xa76f0000a770, - 0xa7710000a779, - 0xa77a0000a77b, - 0xa77c0000a77d, - 0xa77f0000a780, - 0xa7810000a782, - 0xa7830000a784, - 0xa7850000a786, - 0xa7870000a789, - 0xa78c0000a78d, - 0xa78e0000a790, - 0xa7910000a792, - 0xa7930000a796, - 0xa7970000a798, - 0xa7990000a79a, - 0xa79b0000a79c, - 0xa79d0000a79e, - 0xa79f0000a7a0, - 0xa7a10000a7a2, - 0xa7a30000a7a4, - 0xa7a50000a7a6, - 0xa7a70000a7a8, - 0xa7a90000a7aa, - 0xa7af0000a7b0, - 0xa7b50000a7b6, - 0xa7b70000a7b8, - 0xa7b90000a7ba, - 0xa7bb0000a7bc, - 0xa7bd0000a7be, - 0xa7bf0000a7c0, - 0xa7c10000a7c2, - 0xa7c30000a7c4, - 0xa7c80000a7c9, - 0xa7ca0000a7cb, - 0xa7d10000a7d2, - 0xa7d30000a7d4, - 0xa7d50000a7d6, - 0xa7d70000a7d8, - 0xa7d90000a7da, - 0xa7f20000a7f5, - 0xa7f60000a7f8, - 0xa7fa0000a828, - 0xa82c0000a82d, - 0xa8400000a874, - 0xa8800000a8c6, - 0xa8d00000a8da, - 0xa8e00000a8f8, - 0xa8fb0000a8fc, - 0xa8fd0000a92e, - 0xa9300000a954, - 0xa9800000a9c1, - 0xa9cf0000a9da, - 0xa9e00000a9ff, - 0xaa000000aa37, - 0xaa400000aa4e, - 0xaa500000aa5a, - 0xaa600000aa77, - 0xaa7a0000aac3, - 0xaadb0000aade, - 0xaae00000aaf0, - 0xaaf20000aaf7, - 0xab010000ab07, - 0xab090000ab0f, - 0xab110000ab17, - 0xab200000ab27, - 0xab280000ab2f, - 0xab300000ab5b, - 0xab600000ab69, - 0xabc00000abeb, - 0xabec0000abee, - 0xabf00000abfa, - 0xac000000d7a4, - 0xfa0e0000fa10, - 0xfa110000fa12, - 0xfa130000fa15, - 0xfa1f0000fa20, - 0xfa210000fa22, - 0xfa230000fa25, - 0xfa270000fa2a, - 0xfb1e0000fb1f, - 0xfe200000fe30, - 0xfe730000fe74, - 0x100000001000c, - 0x1000d00010027, - 0x100280001003b, - 0x1003c0001003e, - 0x1003f0001004e, - 0x100500001005e, - 0x10080000100fb, - 0x101fd000101fe, - 0x102800001029d, - 0x102a0000102d1, - 0x102e0000102e1, + 0x31A0000031C0, + 0x31F000003200, + 0x340000004DC0, + 0x4E000000A48D, + 0xA4D00000A4FE, + 0xA5000000A60D, + 0xA6100000A62C, + 0xA6410000A642, + 0xA6430000A644, + 0xA6450000A646, + 0xA6470000A648, + 0xA6490000A64A, + 0xA64B0000A64C, + 0xA64D0000A64E, + 0xA64F0000A650, + 0xA6510000A652, + 0xA6530000A654, + 0xA6550000A656, + 0xA6570000A658, + 0xA6590000A65A, + 0xA65B0000A65C, + 0xA65D0000A65E, + 0xA65F0000A660, + 0xA6610000A662, + 0xA6630000A664, + 0xA6650000A666, + 0xA6670000A668, + 0xA6690000A66A, + 0xA66B0000A66C, + 0xA66D0000A670, + 0xA6740000A67E, + 0xA67F0000A680, + 0xA6810000A682, + 0xA6830000A684, + 0xA6850000A686, + 0xA6870000A688, + 0xA6890000A68A, + 0xA68B0000A68C, + 0xA68D0000A68E, + 0xA68F0000A690, + 0xA6910000A692, + 0xA6930000A694, + 0xA6950000A696, + 0xA6970000A698, + 0xA6990000A69A, + 0xA69B0000A69C, + 0xA69E0000A6E6, + 0xA6F00000A6F2, + 0xA7170000A720, + 0xA7230000A724, + 0xA7250000A726, + 0xA7270000A728, + 0xA7290000A72A, + 0xA72B0000A72C, + 0xA72D0000A72E, + 0xA72F0000A732, + 0xA7330000A734, + 0xA7350000A736, + 0xA7370000A738, + 0xA7390000A73A, + 0xA73B0000A73C, + 0xA73D0000A73E, + 0xA73F0000A740, + 0xA7410000A742, + 0xA7430000A744, + 0xA7450000A746, + 0xA7470000A748, + 0xA7490000A74A, + 0xA74B0000A74C, + 0xA74D0000A74E, + 0xA74F0000A750, + 0xA7510000A752, + 0xA7530000A754, + 0xA7550000A756, + 0xA7570000A758, + 0xA7590000A75A, + 0xA75B0000A75C, + 0xA75D0000A75E, + 0xA75F0000A760, + 0xA7610000A762, + 0xA7630000A764, + 0xA7650000A766, + 0xA7670000A768, + 0xA7690000A76A, + 0xA76B0000A76C, + 0xA76D0000A76E, + 0xA76F0000A770, + 0xA7710000A779, + 0xA77A0000A77B, + 0xA77C0000A77D, + 0xA77F0000A780, + 0xA7810000A782, + 0xA7830000A784, + 0xA7850000A786, + 0xA7870000A789, + 0xA78C0000A78D, + 0xA78E0000A790, + 0xA7910000A792, + 0xA7930000A796, + 0xA7970000A798, + 0xA7990000A79A, + 0xA79B0000A79C, + 0xA79D0000A79E, + 0xA79F0000A7A0, + 0xA7A10000A7A2, + 0xA7A30000A7A4, + 0xA7A50000A7A6, + 0xA7A70000A7A8, + 0xA7A90000A7AA, + 0xA7AF0000A7B0, + 0xA7B50000A7B6, + 0xA7B70000A7B8, + 0xA7B90000A7BA, + 0xA7BB0000A7BC, + 0xA7BD0000A7BE, + 0xA7BF0000A7C0, + 0xA7C10000A7C2, + 0xA7C30000A7C4, + 0xA7C80000A7C9, + 0xA7CA0000A7CB, + 0xA7D10000A7D2, + 0xA7D30000A7D4, + 0xA7D50000A7D6, + 0xA7D70000A7D8, + 0xA7D90000A7DA, + 0xA7F60000A7F8, + 0xA7FA0000A828, + 0xA82C0000A82D, + 0xA8400000A874, + 0xA8800000A8C6, + 0xA8D00000A8DA, + 0xA8E00000A8F8, + 0xA8FB0000A8FC, + 0xA8FD0000A92E, + 0xA9300000A954, + 0xA9800000A9C1, + 0xA9CF0000A9DA, + 0xA9E00000A9FF, + 0xAA000000AA37, + 0xAA400000AA4E, + 0xAA500000AA5A, + 0xAA600000AA77, + 0xAA7A0000AAC3, + 0xAADB0000AADE, + 0xAAE00000AAF0, + 0xAAF20000AAF7, + 0xAB010000AB07, + 0xAB090000AB0F, + 0xAB110000AB17, + 0xAB200000AB27, + 0xAB280000AB2F, + 0xAB300000AB5B, + 0xAB600000AB69, + 0xABC00000ABEB, + 0xABEC0000ABEE, + 0xABF00000ABFA, + 0xAC000000D7A4, + 0xFA0E0000FA10, + 0xFA110000FA12, + 0xFA130000FA15, + 0xFA1F0000FA20, + 0xFA210000FA22, + 0xFA230000FA25, + 0xFA270000FA2A, + 0xFB1E0000FB1F, + 0xFE200000FE30, + 0xFE730000FE74, + 0x100000001000C, + 0x1000D00010027, + 0x100280001003B, + 0x1003C0001003E, + 0x1003F0001004E, + 0x100500001005E, + 0x10080000100FB, + 0x101FD000101FE, + 0x102800001029D, + 0x102A0000102D1, + 0x102E0000102E1, 0x1030000010320, - 0x1032d00010341, - 0x103420001034a, - 0x103500001037b, - 0x103800001039e, - 0x103a0000103c4, - 0x103c8000103d0, - 0x104280001049e, - 0x104a0000104aa, - 0x104d8000104fc, + 0x1032D00010341, + 0x103420001034A, + 0x103500001037B, + 0x103800001039E, + 0x103A0000103C4, + 0x103C8000103D0, + 0x104280001049E, + 0x104A0000104AA, + 0x104D8000104FC, 0x1050000010528, 0x1053000010564, - 0x10597000105a2, - 0x105a3000105b2, - 0x105b3000105ba, - 0x105bb000105bd, + 0x10597000105A2, + 0x105A3000105B2, + 0x105B3000105BA, + 0x105BB000105BD, 0x1060000010737, 0x1074000010756, 0x1076000010768, - 0x1078000010786, - 0x10787000107b1, - 0x107b2000107bb, + 0x1078000010781, 0x1080000010806, 0x1080800010809, - 0x1080a00010836, + 0x1080A00010836, 0x1083700010839, - 0x1083c0001083d, - 0x1083f00010856, + 0x1083C0001083D, + 0x1083F00010856, 0x1086000010877, - 0x108800001089f, - 0x108e0000108f3, - 0x108f4000108f6, + 0x108800001089F, + 0x108E0000108F3, + 0x108F4000108F6, 0x1090000010916, - 0x109200001093a, - 0x10980000109b8, - 0x109be000109c0, - 0x10a0000010a04, - 0x10a0500010a07, - 0x10a0c00010a14, - 0x10a1500010a18, - 0x10a1900010a36, - 0x10a3800010a3b, - 0x10a3f00010a40, - 0x10a6000010a7d, - 0x10a8000010a9d, - 0x10ac000010ac8, - 0x10ac900010ae7, - 0x10b0000010b36, - 0x10b4000010b56, - 0x10b6000010b73, - 0x10b8000010b92, - 0x10c0000010c49, - 0x10cc000010cf3, - 0x10d0000010d28, - 0x10d3000010d3a, - 0x10e8000010eaa, - 0x10eab00010ead, - 0x10eb000010eb2, - 0x10efd00010f1d, - 0x10f2700010f28, - 0x10f3000010f51, - 0x10f7000010f86, - 0x10fb000010fc5, - 0x10fe000010ff7, + 0x109200001093A, + 0x10980000109B8, + 0x109BE000109C0, + 0x10A0000010A04, + 0x10A0500010A07, + 0x10A0C00010A14, + 0x10A1500010A18, + 0x10A1900010A36, + 0x10A3800010A3B, + 0x10A3F00010A40, + 0x10A6000010A7D, + 0x10A8000010A9D, + 0x10AC000010AC8, + 0x10AC900010AE7, + 0x10B0000010B36, + 0x10B4000010B56, + 0x10B6000010B73, + 0x10B8000010B92, + 0x10C0000010C49, + 0x10CC000010CF3, + 0x10D0000010D28, + 0x10D3000010D3A, + 0x10E8000010EAA, + 0x10EAB00010EAD, + 0x10EB000010EB2, + 0x10EFD00010F1D, + 0x10F2700010F28, + 0x10F3000010F51, + 0x10F7000010F86, + 0x10FB000010FC5, + 0x10FE000010FF7, 0x1100000011047, 0x1106600011076, - 0x1107f000110bb, - 0x110c2000110c3, - 0x110d0000110e9, - 0x110f0000110fa, + 0x1107F000110BB, + 0x110C2000110C3, + 0x110D0000110E9, + 0x110F0000110FA, 0x1110000011135, 0x1113600011140, 0x1114400011148, 0x1115000011174, 0x1117600011177, - 0x11180000111c5, - 0x111c9000111cd, - 0x111ce000111db, - 0x111dc000111dd, + 0x11180000111C5, + 0x111C9000111CD, + 0x111CE000111DB, + 0x111DC000111DD, 0x1120000011212, 0x1121300011238, - 0x1123e00011242, + 0x1123E00011242, 0x1128000011287, 0x1128800011289, - 0x1128a0001128e, - 0x1128f0001129e, - 0x1129f000112a9, - 0x112b0000112eb, - 0x112f0000112fa, + 0x1128A0001128E, + 0x1128F0001129E, + 0x1129F000112A9, + 0x112B0000112EB, + 0x112F0000112FA, 0x1130000011304, - 0x113050001130d, - 0x1130f00011311, + 0x113050001130D, + 0x1130F00011311, 0x1131300011329, - 0x1132a00011331, + 0x1132A00011331, 0x1133200011334, - 0x113350001133a, - 0x1133b00011345, + 0x113350001133A, + 0x1133B00011345, 0x1134700011349, - 0x1134b0001134e, + 0x1134B0001134E, 0x1135000011351, 0x1135700011358, - 0x1135d00011364, - 0x113660001136d, + 0x1135D00011364, + 0x113660001136D, 0x1137000011375, - 0x114000001144b, - 0x114500001145a, - 0x1145e00011462, - 0x11480000114c6, - 0x114c7000114c8, - 0x114d0000114da, - 0x11580000115b6, - 0x115b8000115c1, - 0x115d8000115de, + 0x114000001144B, + 0x114500001145A, + 0x1145E00011462, + 0x11480000114C6, + 0x114C7000114C8, + 0x114D0000114DA, + 0x11580000115B6, + 0x115B8000115C1, + 0x115D8000115DE, 0x1160000011641, 0x1164400011645, - 0x116500001165a, - 0x11680000116b9, - 0x116c0000116ca, - 0x117000001171b, - 0x1171d0001172c, - 0x117300001173a, + 0x116500001165A, + 0x11680000116B9, + 0x116C0000116CA, + 0x117000001171B, + 0x1171D0001172C, + 0x117300001173A, 0x1174000011747, - 0x118000001183b, - 0x118c0000118ea, - 0x118ff00011907, - 0x119090001190a, - 0x1190c00011914, + 0x118000001183B, + 0x118C0000118EA, + 0x118FF00011907, + 0x119090001190A, + 0x1190C00011914, 0x1191500011917, 0x1191800011936, 0x1193700011939, - 0x1193b00011944, - 0x119500001195a, - 0x119a0000119a8, - 0x119aa000119d8, - 0x119da000119e2, - 0x119e3000119e5, - 0x11a0000011a3f, - 0x11a4700011a48, - 0x11a5000011a9a, - 0x11a9d00011a9e, - 0x11ab000011af9, - 0x11c0000011c09, - 0x11c0a00011c37, - 0x11c3800011c41, - 0x11c5000011c5a, - 0x11c7200011c90, - 0x11c9200011ca8, - 0x11ca900011cb7, - 0x11d0000011d07, - 0x11d0800011d0a, - 0x11d0b00011d37, - 0x11d3a00011d3b, - 0x11d3c00011d3e, - 0x11d3f00011d48, - 0x11d5000011d5a, - 0x11d6000011d66, - 0x11d6700011d69, - 0x11d6a00011d8f, - 0x11d9000011d92, - 0x11d9300011d99, - 0x11da000011daa, - 0x11ee000011ef7, - 0x11f0000011f11, - 0x11f1200011f3b, - 0x11f3e00011f43, - 0x11f5000011f5a, - 0x11fb000011fb1, - 0x120000001239a, + 0x1193B00011944, + 0x119500001195A, + 0x119A0000119A8, + 0x119AA000119D8, + 0x119DA000119E2, + 0x119E3000119E5, + 0x11A0000011A3F, + 0x11A4700011A48, + 0x11A5000011A9A, + 0x11A9D00011A9E, + 0x11AB000011AF9, + 0x11C0000011C09, + 0x11C0A00011C37, + 0x11C3800011C41, + 0x11C5000011C5A, + 0x11C7200011C90, + 0x11C9200011CA8, + 0x11CA900011CB7, + 0x11D0000011D07, + 0x11D0800011D0A, + 0x11D0B00011D37, + 0x11D3A00011D3B, + 0x11D3C00011D3E, + 0x11D3F00011D48, + 0x11D5000011D5A, + 0x11D6000011D66, + 0x11D6700011D69, + 0x11D6A00011D8F, + 0x11D9000011D92, + 0x11D9300011D99, + 0x11DA000011DAA, + 0x11EE000011EF7, + 0x11F0000011F11, + 0x11F1200011F3B, + 0x11F3E00011F43, + 0x11F5000011F5A, + 0x11FB000011FB1, + 0x120000001239A, 0x1248000012544, - 0x12f9000012ff1, + 0x12F9000012FF1, 0x1300000013430, 0x1344000013456, 0x1440000014647, - 0x1680000016a39, - 0x16a4000016a5f, - 0x16a6000016a6a, - 0x16a7000016abf, - 0x16ac000016aca, - 0x16ad000016aee, - 0x16af000016af5, - 0x16b0000016b37, - 0x16b4000016b44, - 0x16b5000016b5a, - 0x16b6300016b78, - 0x16b7d00016b90, - 0x16e6000016e80, - 0x16f0000016f4b, - 0x16f4f00016f88, - 0x16f8f00016fa0, - 0x16fe000016fe2, - 0x16fe300016fe5, - 0x16ff000016ff2, - 0x17000000187f8, - 0x1880000018cd6, - 0x18d0000018d09, - 0x1aff00001aff4, - 0x1aff50001affc, - 0x1affd0001afff, - 0x1b0000001b123, - 0x1b1320001b133, - 0x1b1500001b153, - 0x1b1550001b156, - 0x1b1640001b168, - 0x1b1700001b2fc, - 0x1bc000001bc6b, - 0x1bc700001bc7d, - 0x1bc800001bc89, - 0x1bc900001bc9a, - 0x1bc9d0001bc9f, - 0x1cf000001cf2e, - 0x1cf300001cf47, - 0x1da000001da37, - 0x1da3b0001da6d, - 0x1da750001da76, - 0x1da840001da85, - 0x1da9b0001daa0, - 0x1daa10001dab0, - 0x1df000001df1f, - 0x1df250001df2b, - 0x1e0000001e007, - 0x1e0080001e019, - 0x1e01b0001e022, - 0x1e0230001e025, - 0x1e0260001e02b, - 0x1e0300001e06e, - 0x1e08f0001e090, - 0x1e1000001e12d, - 0x1e1300001e13e, - 0x1e1400001e14a, - 0x1e14e0001e14f, - 0x1e2900001e2af, - 0x1e2c00001e2fa, - 0x1e4d00001e4fa, - 0x1e7e00001e7e7, - 0x1e7e80001e7ec, - 0x1e7ed0001e7ef, - 0x1e7f00001e7ff, - 0x1e8000001e8c5, - 0x1e8d00001e8d7, - 0x1e9220001e94c, - 0x1e9500001e95a, - 0x200000002a6e0, - 0x2a7000002b73a, - 0x2b7400002b81e, - 0x2b8200002cea2, - 0x2ceb00002ebe1, - 0x300000003134b, - 0x31350000323b0, + 0x1680000016A39, + 0x16A4000016A5F, + 0x16A6000016A6A, + 0x16A7000016ABF, + 0x16AC000016ACA, + 0x16AD000016AEE, + 0x16AF000016AF5, + 0x16B0000016B37, + 0x16B4000016B44, + 0x16B5000016B5A, + 0x16B6300016B78, + 0x16B7D00016B90, + 0x16E6000016E80, + 0x16F0000016F4B, + 0x16F4F00016F88, + 0x16F8F00016FA0, + 0x16FE000016FE2, + 0x16FE300016FE5, + 0x16FF000016FF2, + 0x17000000187F8, + 0x1880000018CD6, + 0x18D0000018D09, + 0x1AFF00001AFF4, + 0x1AFF50001AFFC, + 0x1AFFD0001AFFF, + 0x1B0000001B123, + 0x1B1320001B133, + 0x1B1500001B153, + 0x1B1550001B156, + 0x1B1640001B168, + 0x1B1700001B2FC, + 0x1BC000001BC6B, + 0x1BC700001BC7D, + 0x1BC800001BC89, + 0x1BC900001BC9A, + 0x1BC9D0001BC9F, + 0x1CF000001CF2E, + 0x1CF300001CF47, + 0x1DA000001DA37, + 0x1DA3B0001DA6D, + 0x1DA750001DA76, + 0x1DA840001DA85, + 0x1DA9B0001DAA0, + 0x1DAA10001DAB0, + 0x1DF000001DF1F, + 0x1DF250001DF2B, + 0x1E0000001E007, + 0x1E0080001E019, + 0x1E01B0001E022, + 0x1E0230001E025, + 0x1E0260001E02B, + 0x1E08F0001E090, + 0x1E1000001E12D, + 0x1E1300001E13E, + 0x1E1400001E14A, + 0x1E14E0001E14F, + 0x1E2900001E2AF, + 0x1E2C00001E2FA, + 0x1E4D00001E4FA, + 0x1E7E00001E7E7, + 0x1E7E80001E7EC, + 0x1E7ED0001E7EF, + 0x1E7F00001E7FF, + 0x1E8000001E8C5, + 0x1E8D00001E8D7, + 0x1E9220001E94C, + 0x1E9500001E95A, + 0x200000002A6E0, + 0x2A7000002B73A, + 0x2B7400002B81E, + 0x2B8200002CEA2, + 0x2CEB00002EBE1, + 0x2EBF00002EE5E, + 0x300000003134B, + 0x31350000323B0, ), - 'CONTEXTJ': ( - 0x200c0000200e, - ), - 'CONTEXTO': ( - 0xb7000000b8, + "CONTEXTJ": (0x200C0000200E,), + "CONTEXTO": ( + 0xB7000000B8, 0x37500000376, - 0x5f3000005f5, - 0x6600000066a, - 0x6f0000006fa, - 0x30fb000030fc, + 0x5F3000005F5, + 0x6600000066A, + 0x6F0000006FA, + 0x30FB000030FC, ), } diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/intranges.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/intranges.py index 6a43b04..7bfaa8d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/intranges.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/intranges.py @@ -8,6 +8,7 @@ in the original list?" in time O(log(# runs)). import bisect from typing import List, Tuple + def intranges_from_list(list_: List[int]) -> Tuple[int, ...]: """Represent a list of integers as a sequence of ranges: ((start_0, end_0), (start_1, end_1), ...), such that the original @@ -20,18 +21,20 @@ def intranges_from_list(list_: List[int]) -> Tuple[int, ...]: ranges = [] last_write = -1 for i in range(len(sorted_list)): - if i+1 < len(sorted_list): - if sorted_list[i] == sorted_list[i+1]-1: + if i + 1 < len(sorted_list): + if sorted_list[i] == sorted_list[i + 1] - 1: continue - current_range = sorted_list[last_write+1:i+1] + current_range = sorted_list[last_write + 1 : i + 1] ranges.append(_encode_range(current_range[0], current_range[-1] + 1)) last_write = i return tuple(ranges) + def _encode_range(start: int, end: int) -> int: return (start << 32) | end + def _decode_range(r: int) -> Tuple[int, int]: return (r >> 32), (r & ((1 << 32) - 1)) @@ -43,7 +46,7 @@ def intranges_contain(int_: int, ranges: Tuple[int, ...]) -> bool: # we could be immediately ahead of a tuple (start, end) # with start < int_ <= end if pos > 0: - left, right = _decode_range(ranges[pos-1]) + left, right = _decode_range(ranges[pos - 1]) if left <= int_ < right: return True # or we could be immediately behind a tuple (int_, end) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/package_data.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/package_data.py index 8501893..514ff7e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/package_data.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/package_data.py @@ -1,2 +1 @@ -__version__ = '3.4' - +__version__ = "3.10" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/idna/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/uts46data.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/uts46data.py index 186796c..eb89432 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/uts46data.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/idna/uts46data.py @@ -3,8517 +3,8598 @@ from typing import List, Tuple, Union - """IDNA Mapping Table from UTS46.""" -__version__ = '15.0.0' +__version__ = "15.1.0" + + def _seg_0() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x0, '3'), - (0x1, '3'), - (0x2, '3'), - (0x3, '3'), - (0x4, '3'), - (0x5, '3'), - (0x6, '3'), - (0x7, '3'), - (0x8, '3'), - (0x9, '3'), - (0xA, '3'), - (0xB, '3'), - (0xC, '3'), - (0xD, '3'), - (0xE, '3'), - (0xF, '3'), - (0x10, '3'), - (0x11, '3'), - (0x12, '3'), - (0x13, '3'), - (0x14, '3'), - (0x15, '3'), - (0x16, '3'), - (0x17, '3'), - (0x18, '3'), - (0x19, '3'), - (0x1A, '3'), - (0x1B, '3'), - (0x1C, '3'), - (0x1D, '3'), - (0x1E, '3'), - (0x1F, '3'), - (0x20, '3'), - (0x21, '3'), - (0x22, '3'), - (0x23, '3'), - (0x24, '3'), - (0x25, '3'), - (0x26, '3'), - (0x27, '3'), - (0x28, '3'), - (0x29, '3'), - (0x2A, '3'), - (0x2B, '3'), - (0x2C, '3'), - (0x2D, 'V'), - (0x2E, 'V'), - (0x2F, '3'), - (0x30, 'V'), - (0x31, 'V'), - (0x32, 'V'), - (0x33, 'V'), - (0x34, 'V'), - (0x35, 'V'), - (0x36, 'V'), - (0x37, 'V'), - (0x38, 'V'), - (0x39, 'V'), - (0x3A, '3'), - (0x3B, '3'), - (0x3C, '3'), - (0x3D, '3'), - (0x3E, '3'), - (0x3F, '3'), - (0x40, '3'), - (0x41, 'M', 'a'), - (0x42, 'M', 'b'), - (0x43, 'M', 'c'), - (0x44, 'M', 'd'), - (0x45, 'M', 'e'), - (0x46, 'M', 'f'), - (0x47, 'M', 'g'), - (0x48, 'M', 'h'), - (0x49, 'M', 'i'), - (0x4A, 'M', 'j'), - (0x4B, 'M', 'k'), - (0x4C, 'M', 'l'), - (0x4D, 'M', 'm'), - (0x4E, 'M', 'n'), - (0x4F, 'M', 'o'), - (0x50, 'M', 'p'), - (0x51, 'M', 'q'), - (0x52, 'M', 'r'), - (0x53, 'M', 's'), - (0x54, 'M', 't'), - (0x55, 'M', 'u'), - (0x56, 'M', 'v'), - (0x57, 'M', 'w'), - (0x58, 'M', 'x'), - (0x59, 'M', 'y'), - (0x5A, 'M', 'z'), - (0x5B, '3'), - (0x5C, '3'), - (0x5D, '3'), - (0x5E, '3'), - (0x5F, '3'), - (0x60, '3'), - (0x61, 'V'), - (0x62, 'V'), - (0x63, 'V'), + (0x0, "3"), + (0x1, "3"), + (0x2, "3"), + (0x3, "3"), + (0x4, "3"), + (0x5, "3"), + (0x6, "3"), + (0x7, "3"), + (0x8, "3"), + (0x9, "3"), + (0xA, "3"), + (0xB, "3"), + (0xC, "3"), + (0xD, "3"), + (0xE, "3"), + (0xF, "3"), + (0x10, "3"), + (0x11, "3"), + (0x12, "3"), + (0x13, "3"), + (0x14, "3"), + (0x15, "3"), + (0x16, "3"), + (0x17, "3"), + (0x18, "3"), + (0x19, "3"), + (0x1A, "3"), + (0x1B, "3"), + (0x1C, "3"), + (0x1D, "3"), + (0x1E, "3"), + (0x1F, "3"), + (0x20, "3"), + (0x21, "3"), + (0x22, "3"), + (0x23, "3"), + (0x24, "3"), + (0x25, "3"), + (0x26, "3"), + (0x27, "3"), + (0x28, "3"), + (0x29, "3"), + (0x2A, "3"), + (0x2B, "3"), + (0x2C, "3"), + (0x2D, "V"), + (0x2E, "V"), + (0x2F, "3"), + (0x30, "V"), + (0x31, "V"), + (0x32, "V"), + (0x33, "V"), + (0x34, "V"), + (0x35, "V"), + (0x36, "V"), + (0x37, "V"), + (0x38, "V"), + (0x39, "V"), + (0x3A, "3"), + (0x3B, "3"), + (0x3C, "3"), + (0x3D, "3"), + (0x3E, "3"), + (0x3F, "3"), + (0x40, "3"), + (0x41, "M", "a"), + (0x42, "M", "b"), + (0x43, "M", "c"), + (0x44, "M", "d"), + (0x45, "M", "e"), + (0x46, "M", "f"), + (0x47, "M", "g"), + (0x48, "M", "h"), + (0x49, "M", "i"), + (0x4A, "M", "j"), + (0x4B, "M", "k"), + (0x4C, "M", "l"), + (0x4D, "M", "m"), + (0x4E, "M", "n"), + (0x4F, "M", "o"), + (0x50, "M", "p"), + (0x51, "M", "q"), + (0x52, "M", "r"), + (0x53, "M", "s"), + (0x54, "M", "t"), + (0x55, "M", "u"), + (0x56, "M", "v"), + (0x57, "M", "w"), + (0x58, "M", "x"), + (0x59, "M", "y"), + (0x5A, "M", "z"), + (0x5B, "3"), + (0x5C, "3"), + (0x5D, "3"), + (0x5E, "3"), + (0x5F, "3"), + (0x60, "3"), + (0x61, "V"), + (0x62, "V"), + (0x63, "V"), ] + def _seg_1() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x64, 'V'), - (0x65, 'V'), - (0x66, 'V'), - (0x67, 'V'), - (0x68, 'V'), - (0x69, 'V'), - (0x6A, 'V'), - (0x6B, 'V'), - (0x6C, 'V'), - (0x6D, 'V'), - (0x6E, 'V'), - (0x6F, 'V'), - (0x70, 'V'), - (0x71, 'V'), - (0x72, 'V'), - (0x73, 'V'), - (0x74, 'V'), - (0x75, 'V'), - (0x76, 'V'), - (0x77, 'V'), - (0x78, 'V'), - (0x79, 'V'), - (0x7A, 'V'), - (0x7B, '3'), - (0x7C, '3'), - (0x7D, '3'), - (0x7E, '3'), - (0x7F, '3'), - (0x80, 'X'), - (0x81, 'X'), - (0x82, 'X'), - (0x83, 'X'), - (0x84, 'X'), - (0x85, 'X'), - (0x86, 'X'), - (0x87, 'X'), - (0x88, 'X'), - (0x89, 'X'), - (0x8A, 'X'), - (0x8B, 'X'), - (0x8C, 'X'), - (0x8D, 'X'), - (0x8E, 'X'), - (0x8F, 'X'), - (0x90, 'X'), - (0x91, 'X'), - (0x92, 'X'), - (0x93, 'X'), - (0x94, 'X'), - (0x95, 'X'), - (0x96, 'X'), - (0x97, 'X'), - (0x98, 'X'), - (0x99, 'X'), - (0x9A, 'X'), - (0x9B, 'X'), - (0x9C, 'X'), - (0x9D, 'X'), - (0x9E, 'X'), - (0x9F, 'X'), - (0xA0, '3', ' '), - (0xA1, 'V'), - (0xA2, 'V'), - (0xA3, 'V'), - (0xA4, 'V'), - (0xA5, 'V'), - (0xA6, 'V'), - (0xA7, 'V'), - (0xA8, '3', ' ̈'), - (0xA9, 'V'), - (0xAA, 'M', 'a'), - (0xAB, 'V'), - (0xAC, 'V'), - (0xAD, 'I'), - (0xAE, 'V'), - (0xAF, '3', ' ̄'), - (0xB0, 'V'), - (0xB1, 'V'), - (0xB2, 'M', '2'), - (0xB3, 'M', '3'), - (0xB4, '3', ' ́'), - (0xB5, 'M', 'μ'), - (0xB6, 'V'), - (0xB7, 'V'), - (0xB8, '3', ' ̧'), - (0xB9, 'M', '1'), - (0xBA, 'M', 'o'), - (0xBB, 'V'), - (0xBC, 'M', '1⁄4'), - (0xBD, 'M', '1⁄2'), - (0xBE, 'M', '3⁄4'), - (0xBF, 'V'), - (0xC0, 'M', 'à'), - (0xC1, 'M', 'á'), - (0xC2, 'M', 'â'), - (0xC3, 'M', 'ã'), - (0xC4, 'M', 'ä'), - (0xC5, 'M', 'å'), - (0xC6, 'M', 'æ'), - (0xC7, 'M', 'ç'), + (0x64, "V"), + (0x65, "V"), + (0x66, "V"), + (0x67, "V"), + (0x68, "V"), + (0x69, "V"), + (0x6A, "V"), + (0x6B, "V"), + (0x6C, "V"), + (0x6D, "V"), + (0x6E, "V"), + (0x6F, "V"), + (0x70, "V"), + (0x71, "V"), + (0x72, "V"), + (0x73, "V"), + (0x74, "V"), + (0x75, "V"), + (0x76, "V"), + (0x77, "V"), + (0x78, "V"), + (0x79, "V"), + (0x7A, "V"), + (0x7B, "3"), + (0x7C, "3"), + (0x7D, "3"), + (0x7E, "3"), + (0x7F, "3"), + (0x80, "X"), + (0x81, "X"), + (0x82, "X"), + (0x83, "X"), + (0x84, "X"), + (0x85, "X"), + (0x86, "X"), + (0x87, "X"), + (0x88, "X"), + (0x89, "X"), + (0x8A, "X"), + (0x8B, "X"), + (0x8C, "X"), + (0x8D, "X"), + (0x8E, "X"), + (0x8F, "X"), + (0x90, "X"), + (0x91, "X"), + (0x92, "X"), + (0x93, "X"), + (0x94, "X"), + (0x95, "X"), + (0x96, "X"), + (0x97, "X"), + (0x98, "X"), + (0x99, "X"), + (0x9A, "X"), + (0x9B, "X"), + (0x9C, "X"), + (0x9D, "X"), + (0x9E, "X"), + (0x9F, "X"), + (0xA0, "3", " "), + (0xA1, "V"), + (0xA2, "V"), + (0xA3, "V"), + (0xA4, "V"), + (0xA5, "V"), + (0xA6, "V"), + (0xA7, "V"), + (0xA8, "3", " ̈"), + (0xA9, "V"), + (0xAA, "M", "a"), + (0xAB, "V"), + (0xAC, "V"), + (0xAD, "I"), + (0xAE, "V"), + (0xAF, "3", " ̄"), + (0xB0, "V"), + (0xB1, "V"), + (0xB2, "M", "2"), + (0xB3, "M", "3"), + (0xB4, "3", " ́"), + (0xB5, "M", "μ"), + (0xB6, "V"), + (0xB7, "V"), + (0xB8, "3", " ̧"), + (0xB9, "M", "1"), + (0xBA, "M", "o"), + (0xBB, "V"), + (0xBC, "M", "1⁄4"), + (0xBD, "M", "1⁄2"), + (0xBE, "M", "3⁄4"), + (0xBF, "V"), + (0xC0, "M", "à"), + (0xC1, "M", "á"), + (0xC2, "M", "â"), + (0xC3, "M", "ã"), + (0xC4, "M", "ä"), + (0xC5, "M", "å"), + (0xC6, "M", "æ"), + (0xC7, "M", "ç"), ] + def _seg_2() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xC8, 'M', 'è'), - (0xC9, 'M', 'é'), - (0xCA, 'M', 'ê'), - (0xCB, 'M', 'ë'), - (0xCC, 'M', 'ì'), - (0xCD, 'M', 'í'), - (0xCE, 'M', 'î'), - (0xCF, 'M', 'ï'), - (0xD0, 'M', 'ð'), - (0xD1, 'M', 'ñ'), - (0xD2, 'M', 'ò'), - (0xD3, 'M', 'ó'), - (0xD4, 'M', 'ô'), - (0xD5, 'M', 'õ'), - (0xD6, 'M', 'ö'), - (0xD7, 'V'), - (0xD8, 'M', 'ø'), - (0xD9, 'M', 'ù'), - (0xDA, 'M', 'ú'), - (0xDB, 'M', 'û'), - (0xDC, 'M', 'ü'), - (0xDD, 'M', 'ý'), - (0xDE, 'M', 'þ'), - (0xDF, 'D', 'ss'), - (0xE0, 'V'), - (0xE1, 'V'), - (0xE2, 'V'), - (0xE3, 'V'), - (0xE4, 'V'), - (0xE5, 'V'), - (0xE6, 'V'), - (0xE7, 'V'), - (0xE8, 'V'), - (0xE9, 'V'), - (0xEA, 'V'), - (0xEB, 'V'), - (0xEC, 'V'), - (0xED, 'V'), - (0xEE, 'V'), - (0xEF, 'V'), - (0xF0, 'V'), - (0xF1, 'V'), - (0xF2, 'V'), - (0xF3, 'V'), - (0xF4, 'V'), - (0xF5, 'V'), - (0xF6, 'V'), - (0xF7, 'V'), - (0xF8, 'V'), - (0xF9, 'V'), - (0xFA, 'V'), - (0xFB, 'V'), - (0xFC, 'V'), - (0xFD, 'V'), - (0xFE, 'V'), - (0xFF, 'V'), - (0x100, 'M', 'ā'), - (0x101, 'V'), - (0x102, 'M', 'ă'), - (0x103, 'V'), - (0x104, 'M', 'ą'), - (0x105, 'V'), - (0x106, 'M', 'ć'), - (0x107, 'V'), - (0x108, 'M', 'ĉ'), - (0x109, 'V'), - (0x10A, 'M', 'ċ'), - (0x10B, 'V'), - (0x10C, 'M', 'č'), - (0x10D, 'V'), - (0x10E, 'M', 'ď'), - (0x10F, 'V'), - (0x110, 'M', 'đ'), - (0x111, 'V'), - (0x112, 'M', 'ē'), - (0x113, 'V'), - (0x114, 'M', 'ĕ'), - (0x115, 'V'), - (0x116, 'M', 'ė'), - (0x117, 'V'), - (0x118, 'M', 'ę'), - (0x119, 'V'), - (0x11A, 'M', 'ě'), - (0x11B, 'V'), - (0x11C, 'M', 'ĝ'), - (0x11D, 'V'), - (0x11E, 'M', 'ğ'), - (0x11F, 'V'), - (0x120, 'M', 'ġ'), - (0x121, 'V'), - (0x122, 'M', 'ģ'), - (0x123, 'V'), - (0x124, 'M', 'ĥ'), - (0x125, 'V'), - (0x126, 'M', 'ħ'), - (0x127, 'V'), - (0x128, 'M', 'ĩ'), - (0x129, 'V'), - (0x12A, 'M', 'ī'), - (0x12B, 'V'), + (0xC8, "M", "è"), + (0xC9, "M", "é"), + (0xCA, "M", "ê"), + (0xCB, "M", "ë"), + (0xCC, "M", "ì"), + (0xCD, "M", "í"), + (0xCE, "M", "î"), + (0xCF, "M", "ï"), + (0xD0, "M", "ð"), + (0xD1, "M", "ñ"), + (0xD2, "M", "ò"), + (0xD3, "M", "ó"), + (0xD4, "M", "ô"), + (0xD5, "M", "õ"), + (0xD6, "M", "ö"), + (0xD7, "V"), + (0xD8, "M", "ø"), + (0xD9, "M", "ù"), + (0xDA, "M", "ú"), + (0xDB, "M", "û"), + (0xDC, "M", "ü"), + (0xDD, "M", "ý"), + (0xDE, "M", "þ"), + (0xDF, "D", "ss"), + (0xE0, "V"), + (0xE1, "V"), + (0xE2, "V"), + (0xE3, "V"), + (0xE4, "V"), + (0xE5, "V"), + (0xE6, "V"), + (0xE7, "V"), + (0xE8, "V"), + (0xE9, "V"), + (0xEA, "V"), + (0xEB, "V"), + (0xEC, "V"), + (0xED, "V"), + (0xEE, "V"), + (0xEF, "V"), + (0xF0, "V"), + (0xF1, "V"), + (0xF2, "V"), + (0xF3, "V"), + (0xF4, "V"), + (0xF5, "V"), + (0xF6, "V"), + (0xF7, "V"), + (0xF8, "V"), + (0xF9, "V"), + (0xFA, "V"), + (0xFB, "V"), + (0xFC, "V"), + (0xFD, "V"), + (0xFE, "V"), + (0xFF, "V"), + (0x100, "M", "ā"), + (0x101, "V"), + (0x102, "M", "ă"), + (0x103, "V"), + (0x104, "M", "ą"), + (0x105, "V"), + (0x106, "M", "ć"), + (0x107, "V"), + (0x108, "M", "ĉ"), + (0x109, "V"), + (0x10A, "M", "ċ"), + (0x10B, "V"), + (0x10C, "M", "č"), + (0x10D, "V"), + (0x10E, "M", "ď"), + (0x10F, "V"), + (0x110, "M", "đ"), + (0x111, "V"), + (0x112, "M", "ē"), + (0x113, "V"), + (0x114, "M", "ĕ"), + (0x115, "V"), + (0x116, "M", "ė"), + (0x117, "V"), + (0x118, "M", "ę"), + (0x119, "V"), + (0x11A, "M", "ě"), + (0x11B, "V"), + (0x11C, "M", "ĝ"), + (0x11D, "V"), + (0x11E, "M", "ğ"), + (0x11F, "V"), + (0x120, "M", "ġ"), + (0x121, "V"), + (0x122, "M", "ģ"), + (0x123, "V"), + (0x124, "M", "ĥ"), + (0x125, "V"), + (0x126, "M", "ħ"), + (0x127, "V"), + (0x128, "M", "ĩ"), + (0x129, "V"), + (0x12A, "M", "ī"), + (0x12B, "V"), ] + def _seg_3() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x12C, 'M', 'ĭ'), - (0x12D, 'V'), - (0x12E, 'M', 'į'), - (0x12F, 'V'), - (0x130, 'M', 'i̇'), - (0x131, 'V'), - (0x132, 'M', 'ij'), - (0x134, 'M', 'ĵ'), - (0x135, 'V'), - (0x136, 'M', 'ķ'), - (0x137, 'V'), - (0x139, 'M', 'ĺ'), - (0x13A, 'V'), - (0x13B, 'M', 'ļ'), - (0x13C, 'V'), - (0x13D, 'M', 'ľ'), - (0x13E, 'V'), - (0x13F, 'M', 'l·'), - (0x141, 'M', 'ł'), - (0x142, 'V'), - (0x143, 'M', 'ń'), - (0x144, 'V'), - (0x145, 'M', 'ņ'), - (0x146, 'V'), - (0x147, 'M', 'ň'), - (0x148, 'V'), - (0x149, 'M', 'ʼn'), - (0x14A, 'M', 'ŋ'), - (0x14B, 'V'), - (0x14C, 'M', 'ō'), - (0x14D, 'V'), - (0x14E, 'M', 'ŏ'), - (0x14F, 'V'), - (0x150, 'M', 'ő'), - (0x151, 'V'), - (0x152, 'M', 'œ'), - (0x153, 'V'), - (0x154, 'M', 'ŕ'), - (0x155, 'V'), - (0x156, 'M', 'ŗ'), - (0x157, 'V'), - (0x158, 'M', 'ř'), - (0x159, 'V'), - (0x15A, 'M', 'ś'), - (0x15B, 'V'), - (0x15C, 'M', 'ŝ'), - (0x15D, 'V'), - (0x15E, 'M', 'ş'), - (0x15F, 'V'), - (0x160, 'M', 'š'), - (0x161, 'V'), - (0x162, 'M', 'ţ'), - (0x163, 'V'), - (0x164, 'M', 'ť'), - (0x165, 'V'), - (0x166, 'M', 'ŧ'), - (0x167, 'V'), - (0x168, 'M', 'ũ'), - (0x169, 'V'), - (0x16A, 'M', 'ū'), - (0x16B, 'V'), - (0x16C, 'M', 'ŭ'), - (0x16D, 'V'), - (0x16E, 'M', 'ů'), - (0x16F, 'V'), - (0x170, 'M', 'ű'), - (0x171, 'V'), - (0x172, 'M', 'ų'), - (0x173, 'V'), - (0x174, 'M', 'ŵ'), - (0x175, 'V'), - (0x176, 'M', 'ŷ'), - (0x177, 'V'), - (0x178, 'M', 'ÿ'), - (0x179, 'M', 'ź'), - (0x17A, 'V'), - (0x17B, 'M', 'ż'), - (0x17C, 'V'), - (0x17D, 'M', 'ž'), - (0x17E, 'V'), - (0x17F, 'M', 's'), - (0x180, 'V'), - (0x181, 'M', 'ɓ'), - (0x182, 'M', 'ƃ'), - (0x183, 'V'), - (0x184, 'M', 'ƅ'), - (0x185, 'V'), - (0x186, 'M', 'ɔ'), - (0x187, 'M', 'ƈ'), - (0x188, 'V'), - (0x189, 'M', 'ɖ'), - (0x18A, 'M', 'ɗ'), - (0x18B, 'M', 'ƌ'), - (0x18C, 'V'), - (0x18E, 'M', 'ǝ'), - (0x18F, 'M', 'ə'), - (0x190, 'M', 'ɛ'), - (0x191, 'M', 'ƒ'), - (0x192, 'V'), - (0x193, 'M', 'ɠ'), + (0x12C, "M", "ĭ"), + (0x12D, "V"), + (0x12E, "M", "į"), + (0x12F, "V"), + (0x130, "M", "i̇"), + (0x131, "V"), + (0x132, "M", "ij"), + (0x134, "M", "ĵ"), + (0x135, "V"), + (0x136, "M", "ķ"), + (0x137, "V"), + (0x139, "M", "ĺ"), + (0x13A, "V"), + (0x13B, "M", "ļ"), + (0x13C, "V"), + (0x13D, "M", "ľ"), + (0x13E, "V"), + (0x13F, "M", "l·"), + (0x141, "M", "ł"), + (0x142, "V"), + (0x143, "M", "ń"), + (0x144, "V"), + (0x145, "M", "ņ"), + (0x146, "V"), + (0x147, "M", "ň"), + (0x148, "V"), + (0x149, "M", "ʼn"), + (0x14A, "M", "ŋ"), + (0x14B, "V"), + (0x14C, "M", "ō"), + (0x14D, "V"), + (0x14E, "M", "ŏ"), + (0x14F, "V"), + (0x150, "M", "ő"), + (0x151, "V"), + (0x152, "M", "œ"), + (0x153, "V"), + (0x154, "M", "ŕ"), + (0x155, "V"), + (0x156, "M", "ŗ"), + (0x157, "V"), + (0x158, "M", "ř"), + (0x159, "V"), + (0x15A, "M", "ś"), + (0x15B, "V"), + (0x15C, "M", "ŝ"), + (0x15D, "V"), + (0x15E, "M", "ş"), + (0x15F, "V"), + (0x160, "M", "š"), + (0x161, "V"), + (0x162, "M", "ţ"), + (0x163, "V"), + (0x164, "M", "ť"), + (0x165, "V"), + (0x166, "M", "ŧ"), + (0x167, "V"), + (0x168, "M", "ũ"), + (0x169, "V"), + (0x16A, "M", "ū"), + (0x16B, "V"), + (0x16C, "M", "ŭ"), + (0x16D, "V"), + (0x16E, "M", "ů"), + (0x16F, "V"), + (0x170, "M", "ű"), + (0x171, "V"), + (0x172, "M", "ų"), + (0x173, "V"), + (0x174, "M", "ŵ"), + (0x175, "V"), + (0x176, "M", "ŷ"), + (0x177, "V"), + (0x178, "M", "ÿ"), + (0x179, "M", "ź"), + (0x17A, "V"), + (0x17B, "M", "ż"), + (0x17C, "V"), + (0x17D, "M", "ž"), + (0x17E, "V"), + (0x17F, "M", "s"), + (0x180, "V"), + (0x181, "M", "ɓ"), + (0x182, "M", "ƃ"), + (0x183, "V"), + (0x184, "M", "ƅ"), + (0x185, "V"), + (0x186, "M", "ɔ"), + (0x187, "M", "ƈ"), + (0x188, "V"), + (0x189, "M", "ɖ"), + (0x18A, "M", "ɗ"), + (0x18B, "M", "ƌ"), + (0x18C, "V"), + (0x18E, "M", "ǝ"), + (0x18F, "M", "ə"), + (0x190, "M", "ɛ"), + (0x191, "M", "ƒ"), + (0x192, "V"), + (0x193, "M", "ɠ"), ] + def _seg_4() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x194, 'M', 'ɣ'), - (0x195, 'V'), - (0x196, 'M', 'ɩ'), - (0x197, 'M', 'ɨ'), - (0x198, 'M', 'ƙ'), - (0x199, 'V'), - (0x19C, 'M', 'ɯ'), - (0x19D, 'M', 'ɲ'), - (0x19E, 'V'), - (0x19F, 'M', 'ɵ'), - (0x1A0, 'M', 'ơ'), - (0x1A1, 'V'), - (0x1A2, 'M', 'ƣ'), - (0x1A3, 'V'), - (0x1A4, 'M', 'ƥ'), - (0x1A5, 'V'), - (0x1A6, 'M', 'ʀ'), - (0x1A7, 'M', 'ƨ'), - (0x1A8, 'V'), - (0x1A9, 'M', 'ʃ'), - (0x1AA, 'V'), - (0x1AC, 'M', 'ƭ'), - (0x1AD, 'V'), - (0x1AE, 'M', 'ʈ'), - (0x1AF, 'M', 'ư'), - (0x1B0, 'V'), - (0x1B1, 'M', 'ʊ'), - (0x1B2, 'M', 'ʋ'), - (0x1B3, 'M', 'ƴ'), - (0x1B4, 'V'), - (0x1B5, 'M', 'ƶ'), - (0x1B6, 'V'), - (0x1B7, 'M', 'ʒ'), - (0x1B8, 'M', 'ƹ'), - (0x1B9, 'V'), - (0x1BC, 'M', 'ƽ'), - (0x1BD, 'V'), - (0x1C4, 'M', 'dž'), - (0x1C7, 'M', 'lj'), - (0x1CA, 'M', 'nj'), - (0x1CD, 'M', 'ǎ'), - (0x1CE, 'V'), - (0x1CF, 'M', 'ǐ'), - (0x1D0, 'V'), - (0x1D1, 'M', 'ǒ'), - (0x1D2, 'V'), - (0x1D3, 'M', 'ǔ'), - (0x1D4, 'V'), - (0x1D5, 'M', 'ǖ'), - (0x1D6, 'V'), - (0x1D7, 'M', 'ǘ'), - (0x1D8, 'V'), - (0x1D9, 'M', 'ǚ'), - (0x1DA, 'V'), - (0x1DB, 'M', 'ǜ'), - (0x1DC, 'V'), - (0x1DE, 'M', 'ǟ'), - (0x1DF, 'V'), - (0x1E0, 'M', 'ǡ'), - (0x1E1, 'V'), - (0x1E2, 'M', 'ǣ'), - (0x1E3, 'V'), - (0x1E4, 'M', 'ǥ'), - (0x1E5, 'V'), - (0x1E6, 'M', 'ǧ'), - (0x1E7, 'V'), - (0x1E8, 'M', 'ǩ'), - (0x1E9, 'V'), - (0x1EA, 'M', 'ǫ'), - (0x1EB, 'V'), - (0x1EC, 'M', 'ǭ'), - (0x1ED, 'V'), - (0x1EE, 'M', 'ǯ'), - (0x1EF, 'V'), - (0x1F1, 'M', 'dz'), - (0x1F4, 'M', 'ǵ'), - (0x1F5, 'V'), - (0x1F6, 'M', 'ƕ'), - (0x1F7, 'M', 'ƿ'), - (0x1F8, 'M', 'ǹ'), - (0x1F9, 'V'), - (0x1FA, 'M', 'ǻ'), - (0x1FB, 'V'), - (0x1FC, 'M', 'ǽ'), - (0x1FD, 'V'), - (0x1FE, 'M', 'ǿ'), - (0x1FF, 'V'), - (0x200, 'M', 'ȁ'), - (0x201, 'V'), - (0x202, 'M', 'ȃ'), - (0x203, 'V'), - (0x204, 'M', 'ȅ'), - (0x205, 'V'), - (0x206, 'M', 'ȇ'), - (0x207, 'V'), - (0x208, 'M', 'ȉ'), - (0x209, 'V'), - (0x20A, 'M', 'ȋ'), - (0x20B, 'V'), - (0x20C, 'M', 'ȍ'), + (0x194, "M", "ɣ"), + (0x195, "V"), + (0x196, "M", "ɩ"), + (0x197, "M", "ɨ"), + (0x198, "M", "ƙ"), + (0x199, "V"), + (0x19C, "M", "ɯ"), + (0x19D, "M", "ɲ"), + (0x19E, "V"), + (0x19F, "M", "ɵ"), + (0x1A0, "M", "ơ"), + (0x1A1, "V"), + (0x1A2, "M", "ƣ"), + (0x1A3, "V"), + (0x1A4, "M", "ƥ"), + (0x1A5, "V"), + (0x1A6, "M", "ʀ"), + (0x1A7, "M", "ƨ"), + (0x1A8, "V"), + (0x1A9, "M", "ʃ"), + (0x1AA, "V"), + (0x1AC, "M", "ƭ"), + (0x1AD, "V"), + (0x1AE, "M", "ʈ"), + (0x1AF, "M", "ư"), + (0x1B0, "V"), + (0x1B1, "M", "ʊ"), + (0x1B2, "M", "ʋ"), + (0x1B3, "M", "ƴ"), + (0x1B4, "V"), + (0x1B5, "M", "ƶ"), + (0x1B6, "V"), + (0x1B7, "M", "ʒ"), + (0x1B8, "M", "ƹ"), + (0x1B9, "V"), + (0x1BC, "M", "ƽ"), + (0x1BD, "V"), + (0x1C4, "M", "dž"), + (0x1C7, "M", "lj"), + (0x1CA, "M", "nj"), + (0x1CD, "M", "ǎ"), + (0x1CE, "V"), + (0x1CF, "M", "ǐ"), + (0x1D0, "V"), + (0x1D1, "M", "ǒ"), + (0x1D2, "V"), + (0x1D3, "M", "ǔ"), + (0x1D4, "V"), + (0x1D5, "M", "ǖ"), + (0x1D6, "V"), + (0x1D7, "M", "ǘ"), + (0x1D8, "V"), + (0x1D9, "M", "ǚ"), + (0x1DA, "V"), + (0x1DB, "M", "ǜ"), + (0x1DC, "V"), + (0x1DE, "M", "ǟ"), + (0x1DF, "V"), + (0x1E0, "M", "ǡ"), + (0x1E1, "V"), + (0x1E2, "M", "ǣ"), + (0x1E3, "V"), + (0x1E4, "M", "ǥ"), + (0x1E5, "V"), + (0x1E6, "M", "ǧ"), + (0x1E7, "V"), + (0x1E8, "M", "ǩ"), + (0x1E9, "V"), + (0x1EA, "M", "ǫ"), + (0x1EB, "V"), + (0x1EC, "M", "ǭ"), + (0x1ED, "V"), + (0x1EE, "M", "ǯ"), + (0x1EF, "V"), + (0x1F1, "M", "dz"), + (0x1F4, "M", "ǵ"), + (0x1F5, "V"), + (0x1F6, "M", "ƕ"), + (0x1F7, "M", "ƿ"), + (0x1F8, "M", "ǹ"), + (0x1F9, "V"), + (0x1FA, "M", "ǻ"), + (0x1FB, "V"), + (0x1FC, "M", "ǽ"), + (0x1FD, "V"), + (0x1FE, "M", "ǿ"), + (0x1FF, "V"), + (0x200, "M", "ȁ"), + (0x201, "V"), + (0x202, "M", "ȃ"), + (0x203, "V"), + (0x204, "M", "ȅ"), + (0x205, "V"), + (0x206, "M", "ȇ"), + (0x207, "V"), + (0x208, "M", "ȉ"), + (0x209, "V"), + (0x20A, "M", "ȋ"), + (0x20B, "V"), + (0x20C, "M", "ȍ"), ] + def _seg_5() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x20D, 'V'), - (0x20E, 'M', 'ȏ'), - (0x20F, 'V'), - (0x210, 'M', 'ȑ'), - (0x211, 'V'), - (0x212, 'M', 'ȓ'), - (0x213, 'V'), - (0x214, 'M', 'ȕ'), - (0x215, 'V'), - (0x216, 'M', 'ȗ'), - (0x217, 'V'), - (0x218, 'M', 'ș'), - (0x219, 'V'), - (0x21A, 'M', 'ț'), - (0x21B, 'V'), - (0x21C, 'M', 'ȝ'), - (0x21D, 'V'), - (0x21E, 'M', 'ȟ'), - (0x21F, 'V'), - (0x220, 'M', 'ƞ'), - (0x221, 'V'), - (0x222, 'M', 'ȣ'), - (0x223, 'V'), - (0x224, 'M', 'ȥ'), - (0x225, 'V'), - (0x226, 'M', 'ȧ'), - (0x227, 'V'), - (0x228, 'M', 'ȩ'), - (0x229, 'V'), - (0x22A, 'M', 'ȫ'), - (0x22B, 'V'), - (0x22C, 'M', 'ȭ'), - (0x22D, 'V'), - (0x22E, 'M', 'ȯ'), - (0x22F, 'V'), - (0x230, 'M', 'ȱ'), - (0x231, 'V'), - (0x232, 'M', 'ȳ'), - (0x233, 'V'), - (0x23A, 'M', 'ⱥ'), - (0x23B, 'M', 'ȼ'), - (0x23C, 'V'), - (0x23D, 'M', 'ƚ'), - (0x23E, 'M', 'ⱦ'), - (0x23F, 'V'), - (0x241, 'M', 'ɂ'), - (0x242, 'V'), - (0x243, 'M', 'ƀ'), - (0x244, 'M', 'ʉ'), - (0x245, 'M', 'ʌ'), - (0x246, 'M', 'ɇ'), - (0x247, 'V'), - (0x248, 'M', 'ɉ'), - (0x249, 'V'), - (0x24A, 'M', 'ɋ'), - (0x24B, 'V'), - (0x24C, 'M', 'ɍ'), - (0x24D, 'V'), - (0x24E, 'M', 'ɏ'), - (0x24F, 'V'), - (0x2B0, 'M', 'h'), - (0x2B1, 'M', 'ɦ'), - (0x2B2, 'M', 'j'), - (0x2B3, 'M', 'r'), - (0x2B4, 'M', 'ɹ'), - (0x2B5, 'M', 'ɻ'), - (0x2B6, 'M', 'ʁ'), - (0x2B7, 'M', 'w'), - (0x2B8, 'M', 'y'), - (0x2B9, 'V'), - (0x2D8, '3', ' ̆'), - (0x2D9, '3', ' ̇'), - (0x2DA, '3', ' ̊'), - (0x2DB, '3', ' ̨'), - (0x2DC, '3', ' ̃'), - (0x2DD, '3', ' ̋'), - (0x2DE, 'V'), - (0x2E0, 'M', 'ɣ'), - (0x2E1, 'M', 'l'), - (0x2E2, 'M', 's'), - (0x2E3, 'M', 'x'), - (0x2E4, 'M', 'ʕ'), - (0x2E5, 'V'), - (0x340, 'M', '̀'), - (0x341, 'M', '́'), - (0x342, 'V'), - (0x343, 'M', '̓'), - (0x344, 'M', '̈́'), - (0x345, 'M', 'ι'), - (0x346, 'V'), - (0x34F, 'I'), - (0x350, 'V'), - (0x370, 'M', 'ͱ'), - (0x371, 'V'), - (0x372, 'M', 'ͳ'), - (0x373, 'V'), - (0x374, 'M', 'ʹ'), - (0x375, 'V'), - (0x376, 'M', 'ͷ'), - (0x377, 'V'), + (0x20D, "V"), + (0x20E, "M", "ȏ"), + (0x20F, "V"), + (0x210, "M", "ȑ"), + (0x211, "V"), + (0x212, "M", "ȓ"), + (0x213, "V"), + (0x214, "M", "ȕ"), + (0x215, "V"), + (0x216, "M", "ȗ"), + (0x217, "V"), + (0x218, "M", "ș"), + (0x219, "V"), + (0x21A, "M", "ț"), + (0x21B, "V"), + (0x21C, "M", "ȝ"), + (0x21D, "V"), + (0x21E, "M", "ȟ"), + (0x21F, "V"), + (0x220, "M", "ƞ"), + (0x221, "V"), + (0x222, "M", "ȣ"), + (0x223, "V"), + (0x224, "M", "ȥ"), + (0x225, "V"), + (0x226, "M", "ȧ"), + (0x227, "V"), + (0x228, "M", "ȩ"), + (0x229, "V"), + (0x22A, "M", "ȫ"), + (0x22B, "V"), + (0x22C, "M", "ȭ"), + (0x22D, "V"), + (0x22E, "M", "ȯ"), + (0x22F, "V"), + (0x230, "M", "ȱ"), + (0x231, "V"), + (0x232, "M", "ȳ"), + (0x233, "V"), + (0x23A, "M", "ⱥ"), + (0x23B, "M", "ȼ"), + (0x23C, "V"), + (0x23D, "M", "ƚ"), + (0x23E, "M", "ⱦ"), + (0x23F, "V"), + (0x241, "M", "ɂ"), + (0x242, "V"), + (0x243, "M", "ƀ"), + (0x244, "M", "ʉ"), + (0x245, "M", "ʌ"), + (0x246, "M", "ɇ"), + (0x247, "V"), + (0x248, "M", "ɉ"), + (0x249, "V"), + (0x24A, "M", "ɋ"), + (0x24B, "V"), + (0x24C, "M", "ɍ"), + (0x24D, "V"), + (0x24E, "M", "ɏ"), + (0x24F, "V"), + (0x2B0, "M", "h"), + (0x2B1, "M", "ɦ"), + (0x2B2, "M", "j"), + (0x2B3, "M", "r"), + (0x2B4, "M", "ɹ"), + (0x2B5, "M", "ɻ"), + (0x2B6, "M", "ʁ"), + (0x2B7, "M", "w"), + (0x2B8, "M", "y"), + (0x2B9, "V"), + (0x2D8, "3", " ̆"), + (0x2D9, "3", " ̇"), + (0x2DA, "3", " ̊"), + (0x2DB, "3", " ̨"), + (0x2DC, "3", " ̃"), + (0x2DD, "3", " ̋"), + (0x2DE, "V"), + (0x2E0, "M", "ɣ"), + (0x2E1, "M", "l"), + (0x2E2, "M", "s"), + (0x2E3, "M", "x"), + (0x2E4, "M", "ʕ"), + (0x2E5, "V"), + (0x340, "M", "̀"), + (0x341, "M", "́"), + (0x342, "V"), + (0x343, "M", "̓"), + (0x344, "M", "̈́"), + (0x345, "M", "ι"), + (0x346, "V"), + (0x34F, "I"), + (0x350, "V"), + (0x370, "M", "ͱ"), + (0x371, "V"), + (0x372, "M", "ͳ"), + (0x373, "V"), + (0x374, "M", "ʹ"), + (0x375, "V"), + (0x376, "M", "ͷ"), + (0x377, "V"), ] + def _seg_6() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x378, 'X'), - (0x37A, '3', ' ι'), - (0x37B, 'V'), - (0x37E, '3', ';'), - (0x37F, 'M', 'ϳ'), - (0x380, 'X'), - (0x384, '3', ' ́'), - (0x385, '3', ' ̈́'), - (0x386, 'M', 'ά'), - (0x387, 'M', '·'), - (0x388, 'M', 'έ'), - (0x389, 'M', 'ή'), - (0x38A, 'M', 'ί'), - (0x38B, 'X'), - (0x38C, 'M', 'ό'), - (0x38D, 'X'), - (0x38E, 'M', 'ύ'), - (0x38F, 'M', 'ώ'), - (0x390, 'V'), - (0x391, 'M', 'α'), - (0x392, 'M', 'β'), - (0x393, 'M', 'γ'), - (0x394, 'M', 'δ'), - (0x395, 'M', 'ε'), - (0x396, 'M', 'ζ'), - (0x397, 'M', 'η'), - (0x398, 'M', 'θ'), - (0x399, 'M', 'ι'), - (0x39A, 'M', 'κ'), - (0x39B, 'M', 'λ'), - (0x39C, 'M', 'μ'), - (0x39D, 'M', 'ν'), - (0x39E, 'M', 'ξ'), - (0x39F, 'M', 'ο'), - (0x3A0, 'M', 'π'), - (0x3A1, 'M', 'ρ'), - (0x3A2, 'X'), - (0x3A3, 'M', 'σ'), - (0x3A4, 'M', 'τ'), - (0x3A5, 'M', 'υ'), - (0x3A6, 'M', 'φ'), - (0x3A7, 'M', 'χ'), - (0x3A8, 'M', 'ψ'), - (0x3A9, 'M', 'ω'), - (0x3AA, 'M', 'ϊ'), - (0x3AB, 'M', 'ϋ'), - (0x3AC, 'V'), - (0x3C2, 'D', 'σ'), - (0x3C3, 'V'), - (0x3CF, 'M', 'ϗ'), - (0x3D0, 'M', 'β'), - (0x3D1, 'M', 'θ'), - (0x3D2, 'M', 'υ'), - (0x3D3, 'M', 'ύ'), - (0x3D4, 'M', 'ϋ'), - (0x3D5, 'M', 'φ'), - (0x3D6, 'M', 'π'), - (0x3D7, 'V'), - (0x3D8, 'M', 'ϙ'), - (0x3D9, 'V'), - (0x3DA, 'M', 'ϛ'), - (0x3DB, 'V'), - (0x3DC, 'M', 'ϝ'), - (0x3DD, 'V'), - (0x3DE, 'M', 'ϟ'), - (0x3DF, 'V'), - (0x3E0, 'M', 'ϡ'), - (0x3E1, 'V'), - (0x3E2, 'M', 'ϣ'), - (0x3E3, 'V'), - (0x3E4, 'M', 'ϥ'), - (0x3E5, 'V'), - (0x3E6, 'M', 'ϧ'), - (0x3E7, 'V'), - (0x3E8, 'M', 'ϩ'), - (0x3E9, 'V'), - (0x3EA, 'M', 'ϫ'), - (0x3EB, 'V'), - (0x3EC, 'M', 'ϭ'), - (0x3ED, 'V'), - (0x3EE, 'M', 'ϯ'), - (0x3EF, 'V'), - (0x3F0, 'M', 'κ'), - (0x3F1, 'M', 'ρ'), - (0x3F2, 'M', 'σ'), - (0x3F3, 'V'), - (0x3F4, 'M', 'θ'), - (0x3F5, 'M', 'ε'), - (0x3F6, 'V'), - (0x3F7, 'M', 'ϸ'), - (0x3F8, 'V'), - (0x3F9, 'M', 'σ'), - (0x3FA, 'M', 'ϻ'), - (0x3FB, 'V'), - (0x3FD, 'M', 'ͻ'), - (0x3FE, 'M', 'ͼ'), - (0x3FF, 'M', 'ͽ'), - (0x400, 'M', 'ѐ'), - (0x401, 'M', 'ё'), - (0x402, 'M', 'ђ'), + (0x378, "X"), + (0x37A, "3", " ι"), + (0x37B, "V"), + (0x37E, "3", ";"), + (0x37F, "M", "ϳ"), + (0x380, "X"), + (0x384, "3", " ́"), + (0x385, "3", " ̈́"), + (0x386, "M", "ά"), + (0x387, "M", "·"), + (0x388, "M", "έ"), + (0x389, "M", "ή"), + (0x38A, "M", "ί"), + (0x38B, "X"), + (0x38C, "M", "ό"), + (0x38D, "X"), + (0x38E, "M", "ύ"), + (0x38F, "M", "ώ"), + (0x390, "V"), + (0x391, "M", "α"), + (0x392, "M", "β"), + (0x393, "M", "γ"), + (0x394, "M", "δ"), + (0x395, "M", "ε"), + (0x396, "M", "ζ"), + (0x397, "M", "η"), + (0x398, "M", "θ"), + (0x399, "M", "ι"), + (0x39A, "M", "κ"), + (0x39B, "M", "λ"), + (0x39C, "M", "μ"), + (0x39D, "M", "ν"), + (0x39E, "M", "ξ"), + (0x39F, "M", "ο"), + (0x3A0, "M", "π"), + (0x3A1, "M", "ρ"), + (0x3A2, "X"), + (0x3A3, "M", "σ"), + (0x3A4, "M", "τ"), + (0x3A5, "M", "υ"), + (0x3A6, "M", "φ"), + (0x3A7, "M", "χ"), + (0x3A8, "M", "ψ"), + (0x3A9, "M", "ω"), + (0x3AA, "M", "ϊ"), + (0x3AB, "M", "ϋ"), + (0x3AC, "V"), + (0x3C2, "D", "σ"), + (0x3C3, "V"), + (0x3CF, "M", "ϗ"), + (0x3D0, "M", "β"), + (0x3D1, "M", "θ"), + (0x3D2, "M", "υ"), + (0x3D3, "M", "ύ"), + (0x3D4, "M", "ϋ"), + (0x3D5, "M", "φ"), + (0x3D6, "M", "π"), + (0x3D7, "V"), + (0x3D8, "M", "ϙ"), + (0x3D9, "V"), + (0x3DA, "M", "ϛ"), + (0x3DB, "V"), + (0x3DC, "M", "ϝ"), + (0x3DD, "V"), + (0x3DE, "M", "ϟ"), + (0x3DF, "V"), + (0x3E0, "M", "ϡ"), + (0x3E1, "V"), + (0x3E2, "M", "ϣ"), + (0x3E3, "V"), + (0x3E4, "M", "ϥ"), + (0x3E5, "V"), + (0x3E6, "M", "ϧ"), + (0x3E7, "V"), + (0x3E8, "M", "ϩ"), + (0x3E9, "V"), + (0x3EA, "M", "ϫ"), + (0x3EB, "V"), + (0x3EC, "M", "ϭ"), + (0x3ED, "V"), + (0x3EE, "M", "ϯ"), + (0x3EF, "V"), + (0x3F0, "M", "κ"), + (0x3F1, "M", "ρ"), + (0x3F2, "M", "σ"), + (0x3F3, "V"), + (0x3F4, "M", "θ"), + (0x3F5, "M", "ε"), + (0x3F6, "V"), + (0x3F7, "M", "ϸ"), + (0x3F8, "V"), + (0x3F9, "M", "σ"), + (0x3FA, "M", "ϻ"), + (0x3FB, "V"), + (0x3FD, "M", "ͻ"), + (0x3FE, "M", "ͼ"), + (0x3FF, "M", "ͽ"), + (0x400, "M", "ѐ"), + (0x401, "M", "ё"), + (0x402, "M", "ђ"), ] + def _seg_7() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x403, 'M', 'ѓ'), - (0x404, 'M', 'є'), - (0x405, 'M', 'ѕ'), - (0x406, 'M', 'і'), - (0x407, 'M', 'ї'), - (0x408, 'M', 'ј'), - (0x409, 'M', 'љ'), - (0x40A, 'M', 'њ'), - (0x40B, 'M', 'ћ'), - (0x40C, 'M', 'ќ'), - (0x40D, 'M', 'ѝ'), - (0x40E, 'M', 'ў'), - (0x40F, 'M', 'џ'), - (0x410, 'M', 'а'), - (0x411, 'M', 'б'), - (0x412, 'M', 'в'), - (0x413, 'M', 'г'), - (0x414, 'M', 'д'), - (0x415, 'M', 'е'), - (0x416, 'M', 'ж'), - (0x417, 'M', 'з'), - (0x418, 'M', 'и'), - (0x419, 'M', 'й'), - (0x41A, 'M', 'к'), - (0x41B, 'M', 'л'), - (0x41C, 'M', 'м'), - (0x41D, 'M', 'н'), - (0x41E, 'M', 'о'), - (0x41F, 'M', 'п'), - (0x420, 'M', 'р'), - (0x421, 'M', 'с'), - (0x422, 'M', 'т'), - (0x423, 'M', 'у'), - (0x424, 'M', 'ф'), - (0x425, 'M', 'х'), - (0x426, 'M', 'ц'), - (0x427, 'M', 'ч'), - (0x428, 'M', 'ш'), - (0x429, 'M', 'щ'), - (0x42A, 'M', 'ъ'), - (0x42B, 'M', 'ы'), - (0x42C, 'M', 'ь'), - (0x42D, 'M', 'э'), - (0x42E, 'M', 'ю'), - (0x42F, 'M', 'я'), - (0x430, 'V'), - (0x460, 'M', 'ѡ'), - (0x461, 'V'), - (0x462, 'M', 'ѣ'), - (0x463, 'V'), - (0x464, 'M', 'ѥ'), - (0x465, 'V'), - (0x466, 'M', 'ѧ'), - (0x467, 'V'), - (0x468, 'M', 'ѩ'), - (0x469, 'V'), - (0x46A, 'M', 'ѫ'), - (0x46B, 'V'), - (0x46C, 'M', 'ѭ'), - (0x46D, 'V'), - (0x46E, 'M', 'ѯ'), - (0x46F, 'V'), - (0x470, 'M', 'ѱ'), - (0x471, 'V'), - (0x472, 'M', 'ѳ'), - (0x473, 'V'), - (0x474, 'M', 'ѵ'), - (0x475, 'V'), - (0x476, 'M', 'ѷ'), - (0x477, 'V'), - (0x478, 'M', 'ѹ'), - (0x479, 'V'), - (0x47A, 'M', 'ѻ'), - (0x47B, 'V'), - (0x47C, 'M', 'ѽ'), - (0x47D, 'V'), - (0x47E, 'M', 'ѿ'), - (0x47F, 'V'), - (0x480, 'M', 'ҁ'), - (0x481, 'V'), - (0x48A, 'M', 'ҋ'), - (0x48B, 'V'), - (0x48C, 'M', 'ҍ'), - (0x48D, 'V'), - (0x48E, 'M', 'ҏ'), - (0x48F, 'V'), - (0x490, 'M', 'ґ'), - (0x491, 'V'), - (0x492, 'M', 'ғ'), - (0x493, 'V'), - (0x494, 'M', 'ҕ'), - (0x495, 'V'), - (0x496, 'M', 'җ'), - (0x497, 'V'), - (0x498, 'M', 'ҙ'), - (0x499, 'V'), - (0x49A, 'M', 'қ'), - (0x49B, 'V'), - (0x49C, 'M', 'ҝ'), - (0x49D, 'V'), + (0x403, "M", "ѓ"), + (0x404, "M", "є"), + (0x405, "M", "ѕ"), + (0x406, "M", "і"), + (0x407, "M", "ї"), + (0x408, "M", "ј"), + (0x409, "M", "љ"), + (0x40A, "M", "њ"), + (0x40B, "M", "ћ"), + (0x40C, "M", "ќ"), + (0x40D, "M", "ѝ"), + (0x40E, "M", "ў"), + (0x40F, "M", "џ"), + (0x410, "M", "а"), + (0x411, "M", "б"), + (0x412, "M", "в"), + (0x413, "M", "г"), + (0x414, "M", "д"), + (0x415, "M", "е"), + (0x416, "M", "ж"), + (0x417, "M", "з"), + (0x418, "M", "и"), + (0x419, "M", "й"), + (0x41A, "M", "к"), + (0x41B, "M", "л"), + (0x41C, "M", "м"), + (0x41D, "M", "н"), + (0x41E, "M", "о"), + (0x41F, "M", "п"), + (0x420, "M", "р"), + (0x421, "M", "с"), + (0x422, "M", "т"), + (0x423, "M", "у"), + (0x424, "M", "ф"), + (0x425, "M", "х"), + (0x426, "M", "ц"), + (0x427, "M", "ч"), + (0x428, "M", "ш"), + (0x429, "M", "щ"), + (0x42A, "M", "ъ"), + (0x42B, "M", "ы"), + (0x42C, "M", "ь"), + (0x42D, "M", "э"), + (0x42E, "M", "ю"), + (0x42F, "M", "я"), + (0x430, "V"), + (0x460, "M", "ѡ"), + (0x461, "V"), + (0x462, "M", "ѣ"), + (0x463, "V"), + (0x464, "M", "ѥ"), + (0x465, "V"), + (0x466, "M", "ѧ"), + (0x467, "V"), + (0x468, "M", "ѩ"), + (0x469, "V"), + (0x46A, "M", "ѫ"), + (0x46B, "V"), + (0x46C, "M", "ѭ"), + (0x46D, "V"), + (0x46E, "M", "ѯ"), + (0x46F, "V"), + (0x470, "M", "ѱ"), + (0x471, "V"), + (0x472, "M", "ѳ"), + (0x473, "V"), + (0x474, "M", "ѵ"), + (0x475, "V"), + (0x476, "M", "ѷ"), + (0x477, "V"), + (0x478, "M", "ѹ"), + (0x479, "V"), + (0x47A, "M", "ѻ"), + (0x47B, "V"), + (0x47C, "M", "ѽ"), + (0x47D, "V"), + (0x47E, "M", "ѿ"), + (0x47F, "V"), + (0x480, "M", "ҁ"), + (0x481, "V"), + (0x48A, "M", "ҋ"), + (0x48B, "V"), + (0x48C, "M", "ҍ"), + (0x48D, "V"), + (0x48E, "M", "ҏ"), + (0x48F, "V"), + (0x490, "M", "ґ"), + (0x491, "V"), + (0x492, "M", "ғ"), + (0x493, "V"), + (0x494, "M", "ҕ"), + (0x495, "V"), + (0x496, "M", "җ"), + (0x497, "V"), + (0x498, "M", "ҙ"), + (0x499, "V"), + (0x49A, "M", "қ"), + (0x49B, "V"), + (0x49C, "M", "ҝ"), + (0x49D, "V"), ] + def _seg_8() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x49E, 'M', 'ҟ'), - (0x49F, 'V'), - (0x4A0, 'M', 'ҡ'), - (0x4A1, 'V'), - (0x4A2, 'M', 'ң'), - (0x4A3, 'V'), - (0x4A4, 'M', 'ҥ'), - (0x4A5, 'V'), - (0x4A6, 'M', 'ҧ'), - (0x4A7, 'V'), - (0x4A8, 'M', 'ҩ'), - (0x4A9, 'V'), - (0x4AA, 'M', 'ҫ'), - (0x4AB, 'V'), - (0x4AC, 'M', 'ҭ'), - (0x4AD, 'V'), - (0x4AE, 'M', 'ү'), - (0x4AF, 'V'), - (0x4B0, 'M', 'ұ'), - (0x4B1, 'V'), - (0x4B2, 'M', 'ҳ'), - (0x4B3, 'V'), - (0x4B4, 'M', 'ҵ'), - (0x4B5, 'V'), - (0x4B6, 'M', 'ҷ'), - (0x4B7, 'V'), - (0x4B8, 'M', 'ҹ'), - (0x4B9, 'V'), - (0x4BA, 'M', 'һ'), - (0x4BB, 'V'), - (0x4BC, 'M', 'ҽ'), - (0x4BD, 'V'), - (0x4BE, 'M', 'ҿ'), - (0x4BF, 'V'), - (0x4C0, 'X'), - (0x4C1, 'M', 'ӂ'), - (0x4C2, 'V'), - (0x4C3, 'M', 'ӄ'), - (0x4C4, 'V'), - (0x4C5, 'M', 'ӆ'), - (0x4C6, 'V'), - (0x4C7, 'M', 'ӈ'), - (0x4C8, 'V'), - (0x4C9, 'M', 'ӊ'), - (0x4CA, 'V'), - (0x4CB, 'M', 'ӌ'), - (0x4CC, 'V'), - (0x4CD, 'M', 'ӎ'), - (0x4CE, 'V'), - (0x4D0, 'M', 'ӑ'), - (0x4D1, 'V'), - (0x4D2, 'M', 'ӓ'), - (0x4D3, 'V'), - (0x4D4, 'M', 'ӕ'), - (0x4D5, 'V'), - (0x4D6, 'M', 'ӗ'), - (0x4D7, 'V'), - (0x4D8, 'M', 'ә'), - (0x4D9, 'V'), - (0x4DA, 'M', 'ӛ'), - (0x4DB, 'V'), - (0x4DC, 'M', 'ӝ'), - (0x4DD, 'V'), - (0x4DE, 'M', 'ӟ'), - (0x4DF, 'V'), - (0x4E0, 'M', 'ӡ'), - (0x4E1, 'V'), - (0x4E2, 'M', 'ӣ'), - (0x4E3, 'V'), - (0x4E4, 'M', 'ӥ'), - (0x4E5, 'V'), - (0x4E6, 'M', 'ӧ'), - (0x4E7, 'V'), - (0x4E8, 'M', 'ө'), - (0x4E9, 'V'), - (0x4EA, 'M', 'ӫ'), - (0x4EB, 'V'), - (0x4EC, 'M', 'ӭ'), - (0x4ED, 'V'), - (0x4EE, 'M', 'ӯ'), - (0x4EF, 'V'), - (0x4F0, 'M', 'ӱ'), - (0x4F1, 'V'), - (0x4F2, 'M', 'ӳ'), - (0x4F3, 'V'), - (0x4F4, 'M', 'ӵ'), - (0x4F5, 'V'), - (0x4F6, 'M', 'ӷ'), - (0x4F7, 'V'), - (0x4F8, 'M', 'ӹ'), - (0x4F9, 'V'), - (0x4FA, 'M', 'ӻ'), - (0x4FB, 'V'), - (0x4FC, 'M', 'ӽ'), - (0x4FD, 'V'), - (0x4FE, 'M', 'ӿ'), - (0x4FF, 'V'), - (0x500, 'M', 'ԁ'), - (0x501, 'V'), - (0x502, 'M', 'ԃ'), + (0x49E, "M", "ҟ"), + (0x49F, "V"), + (0x4A0, "M", "ҡ"), + (0x4A1, "V"), + (0x4A2, "M", "ң"), + (0x4A3, "V"), + (0x4A4, "M", "ҥ"), + (0x4A5, "V"), + (0x4A6, "M", "ҧ"), + (0x4A7, "V"), + (0x4A8, "M", "ҩ"), + (0x4A9, "V"), + (0x4AA, "M", "ҫ"), + (0x4AB, "V"), + (0x4AC, "M", "ҭ"), + (0x4AD, "V"), + (0x4AE, "M", "ү"), + (0x4AF, "V"), + (0x4B0, "M", "ұ"), + (0x4B1, "V"), + (0x4B2, "M", "ҳ"), + (0x4B3, "V"), + (0x4B4, "M", "ҵ"), + (0x4B5, "V"), + (0x4B6, "M", "ҷ"), + (0x4B7, "V"), + (0x4B8, "M", "ҹ"), + (0x4B9, "V"), + (0x4BA, "M", "һ"), + (0x4BB, "V"), + (0x4BC, "M", "ҽ"), + (0x4BD, "V"), + (0x4BE, "M", "ҿ"), + (0x4BF, "V"), + (0x4C0, "X"), + (0x4C1, "M", "ӂ"), + (0x4C2, "V"), + (0x4C3, "M", "ӄ"), + (0x4C4, "V"), + (0x4C5, "M", "ӆ"), + (0x4C6, "V"), + (0x4C7, "M", "ӈ"), + (0x4C8, "V"), + (0x4C9, "M", "ӊ"), + (0x4CA, "V"), + (0x4CB, "M", "ӌ"), + (0x4CC, "V"), + (0x4CD, "M", "ӎ"), + (0x4CE, "V"), + (0x4D0, "M", "ӑ"), + (0x4D1, "V"), + (0x4D2, "M", "ӓ"), + (0x4D3, "V"), + (0x4D4, "M", "ӕ"), + (0x4D5, "V"), + (0x4D6, "M", "ӗ"), + (0x4D7, "V"), + (0x4D8, "M", "ә"), + (0x4D9, "V"), + (0x4DA, "M", "ӛ"), + (0x4DB, "V"), + (0x4DC, "M", "ӝ"), + (0x4DD, "V"), + (0x4DE, "M", "ӟ"), + (0x4DF, "V"), + (0x4E0, "M", "ӡ"), + (0x4E1, "V"), + (0x4E2, "M", "ӣ"), + (0x4E3, "V"), + (0x4E4, "M", "ӥ"), + (0x4E5, "V"), + (0x4E6, "M", "ӧ"), + (0x4E7, "V"), + (0x4E8, "M", "ө"), + (0x4E9, "V"), + (0x4EA, "M", "ӫ"), + (0x4EB, "V"), + (0x4EC, "M", "ӭ"), + (0x4ED, "V"), + (0x4EE, "M", "ӯ"), + (0x4EF, "V"), + (0x4F0, "M", "ӱ"), + (0x4F1, "V"), + (0x4F2, "M", "ӳ"), + (0x4F3, "V"), + (0x4F4, "M", "ӵ"), + (0x4F5, "V"), + (0x4F6, "M", "ӷ"), + (0x4F7, "V"), + (0x4F8, "M", "ӹ"), + (0x4F9, "V"), + (0x4FA, "M", "ӻ"), + (0x4FB, "V"), + (0x4FC, "M", "ӽ"), + (0x4FD, "V"), + (0x4FE, "M", "ӿ"), + (0x4FF, "V"), + (0x500, "M", "ԁ"), + (0x501, "V"), + (0x502, "M", "ԃ"), ] + def _seg_9() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x503, 'V'), - (0x504, 'M', 'ԅ'), - (0x505, 'V'), - (0x506, 'M', 'ԇ'), - (0x507, 'V'), - (0x508, 'M', 'ԉ'), - (0x509, 'V'), - (0x50A, 'M', 'ԋ'), - (0x50B, 'V'), - (0x50C, 'M', 'ԍ'), - (0x50D, 'V'), - (0x50E, 'M', 'ԏ'), - (0x50F, 'V'), - (0x510, 'M', 'ԑ'), - (0x511, 'V'), - (0x512, 'M', 'ԓ'), - (0x513, 'V'), - (0x514, 'M', 'ԕ'), - (0x515, 'V'), - (0x516, 'M', 'ԗ'), - (0x517, 'V'), - (0x518, 'M', 'ԙ'), - (0x519, 'V'), - (0x51A, 'M', 'ԛ'), - (0x51B, 'V'), - (0x51C, 'M', 'ԝ'), - (0x51D, 'V'), - (0x51E, 'M', 'ԟ'), - (0x51F, 'V'), - (0x520, 'M', 'ԡ'), - (0x521, 'V'), - (0x522, 'M', 'ԣ'), - (0x523, 'V'), - (0x524, 'M', 'ԥ'), - (0x525, 'V'), - (0x526, 'M', 'ԧ'), - (0x527, 'V'), - (0x528, 'M', 'ԩ'), - (0x529, 'V'), - (0x52A, 'M', 'ԫ'), - (0x52B, 'V'), - (0x52C, 'M', 'ԭ'), - (0x52D, 'V'), - (0x52E, 'M', 'ԯ'), - (0x52F, 'V'), - (0x530, 'X'), - (0x531, 'M', 'ա'), - (0x532, 'M', 'բ'), - (0x533, 'M', 'գ'), - (0x534, 'M', 'դ'), - (0x535, 'M', 'ե'), - (0x536, 'M', 'զ'), - (0x537, 'M', 'է'), - (0x538, 'M', 'ը'), - (0x539, 'M', 'թ'), - (0x53A, 'M', 'ժ'), - (0x53B, 'M', 'ի'), - (0x53C, 'M', 'լ'), - (0x53D, 'M', 'խ'), - (0x53E, 'M', 'ծ'), - (0x53F, 'M', 'կ'), - (0x540, 'M', 'հ'), - (0x541, 'M', 'ձ'), - (0x542, 'M', 'ղ'), - (0x543, 'M', 'ճ'), - (0x544, 'M', 'մ'), - (0x545, 'M', 'յ'), - (0x546, 'M', 'ն'), - (0x547, 'M', 'շ'), - (0x548, 'M', 'ո'), - (0x549, 'M', 'չ'), - (0x54A, 'M', 'պ'), - (0x54B, 'M', 'ջ'), - (0x54C, 'M', 'ռ'), - (0x54D, 'M', 'ս'), - (0x54E, 'M', 'վ'), - (0x54F, 'M', 'տ'), - (0x550, 'M', 'ր'), - (0x551, 'M', 'ց'), - (0x552, 'M', 'ւ'), - (0x553, 'M', 'փ'), - (0x554, 'M', 'ք'), - (0x555, 'M', 'օ'), - (0x556, 'M', 'ֆ'), - (0x557, 'X'), - (0x559, 'V'), - (0x587, 'M', 'եւ'), - (0x588, 'V'), - (0x58B, 'X'), - (0x58D, 'V'), - (0x590, 'X'), - (0x591, 'V'), - (0x5C8, 'X'), - (0x5D0, 'V'), - (0x5EB, 'X'), - (0x5EF, 'V'), - (0x5F5, 'X'), - (0x606, 'V'), - (0x61C, 'X'), - (0x61D, 'V'), + (0x503, "V"), + (0x504, "M", "ԅ"), + (0x505, "V"), + (0x506, "M", "ԇ"), + (0x507, "V"), + (0x508, "M", "ԉ"), + (0x509, "V"), + (0x50A, "M", "ԋ"), + (0x50B, "V"), + (0x50C, "M", "ԍ"), + (0x50D, "V"), + (0x50E, "M", "ԏ"), + (0x50F, "V"), + (0x510, "M", "ԑ"), + (0x511, "V"), + (0x512, "M", "ԓ"), + (0x513, "V"), + (0x514, "M", "ԕ"), + (0x515, "V"), + (0x516, "M", "ԗ"), + (0x517, "V"), + (0x518, "M", "ԙ"), + (0x519, "V"), + (0x51A, "M", "ԛ"), + (0x51B, "V"), + (0x51C, "M", "ԝ"), + (0x51D, "V"), + (0x51E, "M", "ԟ"), + (0x51F, "V"), + (0x520, "M", "ԡ"), + (0x521, "V"), + (0x522, "M", "ԣ"), + (0x523, "V"), + (0x524, "M", "ԥ"), + (0x525, "V"), + (0x526, "M", "ԧ"), + (0x527, "V"), + (0x528, "M", "ԩ"), + (0x529, "V"), + (0x52A, "M", "ԫ"), + (0x52B, "V"), + (0x52C, "M", "ԭ"), + (0x52D, "V"), + (0x52E, "M", "ԯ"), + (0x52F, "V"), + (0x530, "X"), + (0x531, "M", "ա"), + (0x532, "M", "բ"), + (0x533, "M", "գ"), + (0x534, "M", "դ"), + (0x535, "M", "ե"), + (0x536, "M", "զ"), + (0x537, "M", "է"), + (0x538, "M", "ը"), + (0x539, "M", "թ"), + (0x53A, "M", "ժ"), + (0x53B, "M", "ի"), + (0x53C, "M", "լ"), + (0x53D, "M", "խ"), + (0x53E, "M", "ծ"), + (0x53F, "M", "կ"), + (0x540, "M", "հ"), + (0x541, "M", "ձ"), + (0x542, "M", "ղ"), + (0x543, "M", "ճ"), + (0x544, "M", "մ"), + (0x545, "M", "յ"), + (0x546, "M", "ն"), + (0x547, "M", "շ"), + (0x548, "M", "ո"), + (0x549, "M", "չ"), + (0x54A, "M", "պ"), + (0x54B, "M", "ջ"), + (0x54C, "M", "ռ"), + (0x54D, "M", "ս"), + (0x54E, "M", "վ"), + (0x54F, "M", "տ"), + (0x550, "M", "ր"), + (0x551, "M", "ց"), + (0x552, "M", "ւ"), + (0x553, "M", "փ"), + (0x554, "M", "ք"), + (0x555, "M", "օ"), + (0x556, "M", "ֆ"), + (0x557, "X"), + (0x559, "V"), + (0x587, "M", "եւ"), + (0x588, "V"), + (0x58B, "X"), + (0x58D, "V"), + (0x590, "X"), + (0x591, "V"), + (0x5C8, "X"), + (0x5D0, "V"), + (0x5EB, "X"), + (0x5EF, "V"), + (0x5F5, "X"), + (0x606, "V"), + (0x61C, "X"), + (0x61D, "V"), ] + def _seg_10() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x675, 'M', 'اٴ'), - (0x676, 'M', 'وٴ'), - (0x677, 'M', 'ۇٴ'), - (0x678, 'M', 'يٴ'), - (0x679, 'V'), - (0x6DD, 'X'), - (0x6DE, 'V'), - (0x70E, 'X'), - (0x710, 'V'), - (0x74B, 'X'), - (0x74D, 'V'), - (0x7B2, 'X'), - (0x7C0, 'V'), - (0x7FB, 'X'), - (0x7FD, 'V'), - (0x82E, 'X'), - (0x830, 'V'), - (0x83F, 'X'), - (0x840, 'V'), - (0x85C, 'X'), - (0x85E, 'V'), - (0x85F, 'X'), - (0x860, 'V'), - (0x86B, 'X'), - (0x870, 'V'), - (0x88F, 'X'), - (0x898, 'V'), - (0x8E2, 'X'), - (0x8E3, 'V'), - (0x958, 'M', 'क़'), - (0x959, 'M', 'ख़'), - (0x95A, 'M', 'ग़'), - (0x95B, 'M', 'ज़'), - (0x95C, 'M', 'ड़'), - (0x95D, 'M', 'ढ़'), - (0x95E, 'M', 'फ़'), - (0x95F, 'M', 'य़'), - (0x960, 'V'), - (0x984, 'X'), - (0x985, 'V'), - (0x98D, 'X'), - (0x98F, 'V'), - (0x991, 'X'), - (0x993, 'V'), - (0x9A9, 'X'), - (0x9AA, 'V'), - (0x9B1, 'X'), - (0x9B2, 'V'), - (0x9B3, 'X'), - (0x9B6, 'V'), - (0x9BA, 'X'), - (0x9BC, 'V'), - (0x9C5, 'X'), - (0x9C7, 'V'), - (0x9C9, 'X'), - (0x9CB, 'V'), - (0x9CF, 'X'), - (0x9D7, 'V'), - (0x9D8, 'X'), - (0x9DC, 'M', 'ড়'), - (0x9DD, 'M', 'ঢ়'), - (0x9DE, 'X'), - (0x9DF, 'M', 'য়'), - (0x9E0, 'V'), - (0x9E4, 'X'), - (0x9E6, 'V'), - (0x9FF, 'X'), - (0xA01, 'V'), - (0xA04, 'X'), - (0xA05, 'V'), - (0xA0B, 'X'), - (0xA0F, 'V'), - (0xA11, 'X'), - (0xA13, 'V'), - (0xA29, 'X'), - (0xA2A, 'V'), - (0xA31, 'X'), - (0xA32, 'V'), - (0xA33, 'M', 'ਲ਼'), - (0xA34, 'X'), - (0xA35, 'V'), - (0xA36, 'M', 'ਸ਼'), - (0xA37, 'X'), - (0xA38, 'V'), - (0xA3A, 'X'), - (0xA3C, 'V'), - (0xA3D, 'X'), - (0xA3E, 'V'), - (0xA43, 'X'), - (0xA47, 'V'), - (0xA49, 'X'), - (0xA4B, 'V'), - (0xA4E, 'X'), - (0xA51, 'V'), - (0xA52, 'X'), - (0xA59, 'M', 'ਖ਼'), - (0xA5A, 'M', 'ਗ਼'), - (0xA5B, 'M', 'ਜ਼'), - (0xA5C, 'V'), - (0xA5D, 'X'), + (0x675, "M", "اٴ"), + (0x676, "M", "وٴ"), + (0x677, "M", "ۇٴ"), + (0x678, "M", "يٴ"), + (0x679, "V"), + (0x6DD, "X"), + (0x6DE, "V"), + (0x70E, "X"), + (0x710, "V"), + (0x74B, "X"), + (0x74D, "V"), + (0x7B2, "X"), + (0x7C0, "V"), + (0x7FB, "X"), + (0x7FD, "V"), + (0x82E, "X"), + (0x830, "V"), + (0x83F, "X"), + (0x840, "V"), + (0x85C, "X"), + (0x85E, "V"), + (0x85F, "X"), + (0x860, "V"), + (0x86B, "X"), + (0x870, "V"), + (0x88F, "X"), + (0x898, "V"), + (0x8E2, "X"), + (0x8E3, "V"), + (0x958, "M", "क़"), + (0x959, "M", "ख़"), + (0x95A, "M", "ग़"), + (0x95B, "M", "ज़"), + (0x95C, "M", "ड़"), + (0x95D, "M", "ढ़"), + (0x95E, "M", "फ़"), + (0x95F, "M", "य़"), + (0x960, "V"), + (0x984, "X"), + (0x985, "V"), + (0x98D, "X"), + (0x98F, "V"), + (0x991, "X"), + (0x993, "V"), + (0x9A9, "X"), + (0x9AA, "V"), + (0x9B1, "X"), + (0x9B2, "V"), + (0x9B3, "X"), + (0x9B6, "V"), + (0x9BA, "X"), + (0x9BC, "V"), + (0x9C5, "X"), + (0x9C7, "V"), + (0x9C9, "X"), + (0x9CB, "V"), + (0x9CF, "X"), + (0x9D7, "V"), + (0x9D8, "X"), + (0x9DC, "M", "ড়"), + (0x9DD, "M", "ঢ়"), + (0x9DE, "X"), + (0x9DF, "M", "য়"), + (0x9E0, "V"), + (0x9E4, "X"), + (0x9E6, "V"), + (0x9FF, "X"), + (0xA01, "V"), + (0xA04, "X"), + (0xA05, "V"), + (0xA0B, "X"), + (0xA0F, "V"), + (0xA11, "X"), + (0xA13, "V"), + (0xA29, "X"), + (0xA2A, "V"), + (0xA31, "X"), + (0xA32, "V"), + (0xA33, "M", "ਲ਼"), + (0xA34, "X"), + (0xA35, "V"), + (0xA36, "M", "ਸ਼"), + (0xA37, "X"), + (0xA38, "V"), + (0xA3A, "X"), + (0xA3C, "V"), + (0xA3D, "X"), + (0xA3E, "V"), + (0xA43, "X"), + (0xA47, "V"), + (0xA49, "X"), + (0xA4B, "V"), + (0xA4E, "X"), + (0xA51, "V"), + (0xA52, "X"), + (0xA59, "M", "ਖ਼"), + (0xA5A, "M", "ਗ਼"), + (0xA5B, "M", "ਜ਼"), + (0xA5C, "V"), + (0xA5D, "X"), ] + def _seg_11() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xA5E, 'M', 'ਫ਼'), - (0xA5F, 'X'), - (0xA66, 'V'), - (0xA77, 'X'), - (0xA81, 'V'), - (0xA84, 'X'), - (0xA85, 'V'), - (0xA8E, 'X'), - (0xA8F, 'V'), - (0xA92, 'X'), - (0xA93, 'V'), - (0xAA9, 'X'), - (0xAAA, 'V'), - (0xAB1, 'X'), - (0xAB2, 'V'), - (0xAB4, 'X'), - (0xAB5, 'V'), - (0xABA, 'X'), - (0xABC, 'V'), - (0xAC6, 'X'), - (0xAC7, 'V'), - (0xACA, 'X'), - (0xACB, 'V'), - (0xACE, 'X'), - (0xAD0, 'V'), - (0xAD1, 'X'), - (0xAE0, 'V'), - (0xAE4, 'X'), - (0xAE6, 'V'), - (0xAF2, 'X'), - (0xAF9, 'V'), - (0xB00, 'X'), - (0xB01, 'V'), - (0xB04, 'X'), - (0xB05, 'V'), - (0xB0D, 'X'), - (0xB0F, 'V'), - (0xB11, 'X'), - (0xB13, 'V'), - (0xB29, 'X'), - (0xB2A, 'V'), - (0xB31, 'X'), - (0xB32, 'V'), - (0xB34, 'X'), - (0xB35, 'V'), - (0xB3A, 'X'), - (0xB3C, 'V'), - (0xB45, 'X'), - (0xB47, 'V'), - (0xB49, 'X'), - (0xB4B, 'V'), - (0xB4E, 'X'), - (0xB55, 'V'), - (0xB58, 'X'), - (0xB5C, 'M', 'ଡ଼'), - (0xB5D, 'M', 'ଢ଼'), - (0xB5E, 'X'), - (0xB5F, 'V'), - (0xB64, 'X'), - (0xB66, 'V'), - (0xB78, 'X'), - (0xB82, 'V'), - (0xB84, 'X'), - (0xB85, 'V'), - (0xB8B, 'X'), - (0xB8E, 'V'), - (0xB91, 'X'), - (0xB92, 'V'), - (0xB96, 'X'), - (0xB99, 'V'), - (0xB9B, 'X'), - (0xB9C, 'V'), - (0xB9D, 'X'), - (0xB9E, 'V'), - (0xBA0, 'X'), - (0xBA3, 'V'), - (0xBA5, 'X'), - (0xBA8, 'V'), - (0xBAB, 'X'), - (0xBAE, 'V'), - (0xBBA, 'X'), - (0xBBE, 'V'), - (0xBC3, 'X'), - (0xBC6, 'V'), - (0xBC9, 'X'), - (0xBCA, 'V'), - (0xBCE, 'X'), - (0xBD0, 'V'), - (0xBD1, 'X'), - (0xBD7, 'V'), - (0xBD8, 'X'), - (0xBE6, 'V'), - (0xBFB, 'X'), - (0xC00, 'V'), - (0xC0D, 'X'), - (0xC0E, 'V'), - (0xC11, 'X'), - (0xC12, 'V'), - (0xC29, 'X'), - (0xC2A, 'V'), + (0xA5E, "M", "ਫ਼"), + (0xA5F, "X"), + (0xA66, "V"), + (0xA77, "X"), + (0xA81, "V"), + (0xA84, "X"), + (0xA85, "V"), + (0xA8E, "X"), + (0xA8F, "V"), + (0xA92, "X"), + (0xA93, "V"), + (0xAA9, "X"), + (0xAAA, "V"), + (0xAB1, "X"), + (0xAB2, "V"), + (0xAB4, "X"), + (0xAB5, "V"), + (0xABA, "X"), + (0xABC, "V"), + (0xAC6, "X"), + (0xAC7, "V"), + (0xACA, "X"), + (0xACB, "V"), + (0xACE, "X"), + (0xAD0, "V"), + (0xAD1, "X"), + (0xAE0, "V"), + (0xAE4, "X"), + (0xAE6, "V"), + (0xAF2, "X"), + (0xAF9, "V"), + (0xB00, "X"), + (0xB01, "V"), + (0xB04, "X"), + (0xB05, "V"), + (0xB0D, "X"), + (0xB0F, "V"), + (0xB11, "X"), + (0xB13, "V"), + (0xB29, "X"), + (0xB2A, "V"), + (0xB31, "X"), + (0xB32, "V"), + (0xB34, "X"), + (0xB35, "V"), + (0xB3A, "X"), + (0xB3C, "V"), + (0xB45, "X"), + (0xB47, "V"), + (0xB49, "X"), + (0xB4B, "V"), + (0xB4E, "X"), + (0xB55, "V"), + (0xB58, "X"), + (0xB5C, "M", "ଡ଼"), + (0xB5D, "M", "ଢ଼"), + (0xB5E, "X"), + (0xB5F, "V"), + (0xB64, "X"), + (0xB66, "V"), + (0xB78, "X"), + (0xB82, "V"), + (0xB84, "X"), + (0xB85, "V"), + (0xB8B, "X"), + (0xB8E, "V"), + (0xB91, "X"), + (0xB92, "V"), + (0xB96, "X"), + (0xB99, "V"), + (0xB9B, "X"), + (0xB9C, "V"), + (0xB9D, "X"), + (0xB9E, "V"), + (0xBA0, "X"), + (0xBA3, "V"), + (0xBA5, "X"), + (0xBA8, "V"), + (0xBAB, "X"), + (0xBAE, "V"), + (0xBBA, "X"), + (0xBBE, "V"), + (0xBC3, "X"), + (0xBC6, "V"), + (0xBC9, "X"), + (0xBCA, "V"), + (0xBCE, "X"), + (0xBD0, "V"), + (0xBD1, "X"), + (0xBD7, "V"), + (0xBD8, "X"), + (0xBE6, "V"), + (0xBFB, "X"), + (0xC00, "V"), + (0xC0D, "X"), + (0xC0E, "V"), + (0xC11, "X"), + (0xC12, "V"), + (0xC29, "X"), + (0xC2A, "V"), ] + def _seg_12() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xC3A, 'X'), - (0xC3C, 'V'), - (0xC45, 'X'), - (0xC46, 'V'), - (0xC49, 'X'), - (0xC4A, 'V'), - (0xC4E, 'X'), - (0xC55, 'V'), - (0xC57, 'X'), - (0xC58, 'V'), - (0xC5B, 'X'), - (0xC5D, 'V'), - (0xC5E, 'X'), - (0xC60, 'V'), - (0xC64, 'X'), - (0xC66, 'V'), - (0xC70, 'X'), - (0xC77, 'V'), - (0xC8D, 'X'), - (0xC8E, 'V'), - (0xC91, 'X'), - (0xC92, 'V'), - (0xCA9, 'X'), - (0xCAA, 'V'), - (0xCB4, 'X'), - (0xCB5, 'V'), - (0xCBA, 'X'), - (0xCBC, 'V'), - (0xCC5, 'X'), - (0xCC6, 'V'), - (0xCC9, 'X'), - (0xCCA, 'V'), - (0xCCE, 'X'), - (0xCD5, 'V'), - (0xCD7, 'X'), - (0xCDD, 'V'), - (0xCDF, 'X'), - (0xCE0, 'V'), - (0xCE4, 'X'), - (0xCE6, 'V'), - (0xCF0, 'X'), - (0xCF1, 'V'), - (0xCF4, 'X'), - (0xD00, 'V'), - (0xD0D, 'X'), - (0xD0E, 'V'), - (0xD11, 'X'), - (0xD12, 'V'), - (0xD45, 'X'), - (0xD46, 'V'), - (0xD49, 'X'), - (0xD4A, 'V'), - (0xD50, 'X'), - (0xD54, 'V'), - (0xD64, 'X'), - (0xD66, 'V'), - (0xD80, 'X'), - (0xD81, 'V'), - (0xD84, 'X'), - (0xD85, 'V'), - (0xD97, 'X'), - (0xD9A, 'V'), - (0xDB2, 'X'), - (0xDB3, 'V'), - (0xDBC, 'X'), - (0xDBD, 'V'), - (0xDBE, 'X'), - (0xDC0, 'V'), - (0xDC7, 'X'), - (0xDCA, 'V'), - (0xDCB, 'X'), - (0xDCF, 'V'), - (0xDD5, 'X'), - (0xDD6, 'V'), - (0xDD7, 'X'), - (0xDD8, 'V'), - (0xDE0, 'X'), - (0xDE6, 'V'), - (0xDF0, 'X'), - (0xDF2, 'V'), - (0xDF5, 'X'), - (0xE01, 'V'), - (0xE33, 'M', 'ํา'), - (0xE34, 'V'), - (0xE3B, 'X'), - (0xE3F, 'V'), - (0xE5C, 'X'), - (0xE81, 'V'), - (0xE83, 'X'), - (0xE84, 'V'), - (0xE85, 'X'), - (0xE86, 'V'), - (0xE8B, 'X'), - (0xE8C, 'V'), - (0xEA4, 'X'), - (0xEA5, 'V'), - (0xEA6, 'X'), - (0xEA7, 'V'), - (0xEB3, 'M', 'ໍາ'), - (0xEB4, 'V'), + (0xC3A, "X"), + (0xC3C, "V"), + (0xC45, "X"), + (0xC46, "V"), + (0xC49, "X"), + (0xC4A, "V"), + (0xC4E, "X"), + (0xC55, "V"), + (0xC57, "X"), + (0xC58, "V"), + (0xC5B, "X"), + (0xC5D, "V"), + (0xC5E, "X"), + (0xC60, "V"), + (0xC64, "X"), + (0xC66, "V"), + (0xC70, "X"), + (0xC77, "V"), + (0xC8D, "X"), + (0xC8E, "V"), + (0xC91, "X"), + (0xC92, "V"), + (0xCA9, "X"), + (0xCAA, "V"), + (0xCB4, "X"), + (0xCB5, "V"), + (0xCBA, "X"), + (0xCBC, "V"), + (0xCC5, "X"), + (0xCC6, "V"), + (0xCC9, "X"), + (0xCCA, "V"), + (0xCCE, "X"), + (0xCD5, "V"), + (0xCD7, "X"), + (0xCDD, "V"), + (0xCDF, "X"), + (0xCE0, "V"), + (0xCE4, "X"), + (0xCE6, "V"), + (0xCF0, "X"), + (0xCF1, "V"), + (0xCF4, "X"), + (0xD00, "V"), + (0xD0D, "X"), + (0xD0E, "V"), + (0xD11, "X"), + (0xD12, "V"), + (0xD45, "X"), + (0xD46, "V"), + (0xD49, "X"), + (0xD4A, "V"), + (0xD50, "X"), + (0xD54, "V"), + (0xD64, "X"), + (0xD66, "V"), + (0xD80, "X"), + (0xD81, "V"), + (0xD84, "X"), + (0xD85, "V"), + (0xD97, "X"), + (0xD9A, "V"), + (0xDB2, "X"), + (0xDB3, "V"), + (0xDBC, "X"), + (0xDBD, "V"), + (0xDBE, "X"), + (0xDC0, "V"), + (0xDC7, "X"), + (0xDCA, "V"), + (0xDCB, "X"), + (0xDCF, "V"), + (0xDD5, "X"), + (0xDD6, "V"), + (0xDD7, "X"), + (0xDD8, "V"), + (0xDE0, "X"), + (0xDE6, "V"), + (0xDF0, "X"), + (0xDF2, "V"), + (0xDF5, "X"), + (0xE01, "V"), + (0xE33, "M", "ํา"), + (0xE34, "V"), + (0xE3B, "X"), + (0xE3F, "V"), + (0xE5C, "X"), + (0xE81, "V"), + (0xE83, "X"), + (0xE84, "V"), + (0xE85, "X"), + (0xE86, "V"), + (0xE8B, "X"), + (0xE8C, "V"), + (0xEA4, "X"), + (0xEA5, "V"), + (0xEA6, "X"), + (0xEA7, "V"), + (0xEB3, "M", "ໍາ"), + (0xEB4, "V"), ] + def _seg_13() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xEBE, 'X'), - (0xEC0, 'V'), - (0xEC5, 'X'), - (0xEC6, 'V'), - (0xEC7, 'X'), - (0xEC8, 'V'), - (0xECF, 'X'), - (0xED0, 'V'), - (0xEDA, 'X'), - (0xEDC, 'M', 'ຫນ'), - (0xEDD, 'M', 'ຫມ'), - (0xEDE, 'V'), - (0xEE0, 'X'), - (0xF00, 'V'), - (0xF0C, 'M', '་'), - (0xF0D, 'V'), - (0xF43, 'M', 'གྷ'), - (0xF44, 'V'), - (0xF48, 'X'), - (0xF49, 'V'), - (0xF4D, 'M', 'ཌྷ'), - (0xF4E, 'V'), - (0xF52, 'M', 'དྷ'), - (0xF53, 'V'), - (0xF57, 'M', 'བྷ'), - (0xF58, 'V'), - (0xF5C, 'M', 'ཛྷ'), - (0xF5D, 'V'), - (0xF69, 'M', 'ཀྵ'), - (0xF6A, 'V'), - (0xF6D, 'X'), - (0xF71, 'V'), - (0xF73, 'M', 'ཱི'), - (0xF74, 'V'), - (0xF75, 'M', 'ཱུ'), - (0xF76, 'M', 'ྲྀ'), - (0xF77, 'M', 'ྲཱྀ'), - (0xF78, 'M', 'ླྀ'), - (0xF79, 'M', 'ླཱྀ'), - (0xF7A, 'V'), - (0xF81, 'M', 'ཱྀ'), - (0xF82, 'V'), - (0xF93, 'M', 'ྒྷ'), - (0xF94, 'V'), - (0xF98, 'X'), - (0xF99, 'V'), - (0xF9D, 'M', 'ྜྷ'), - (0xF9E, 'V'), - (0xFA2, 'M', 'ྡྷ'), - (0xFA3, 'V'), - (0xFA7, 'M', 'ྦྷ'), - (0xFA8, 'V'), - (0xFAC, 'M', 'ྫྷ'), - (0xFAD, 'V'), - (0xFB9, 'M', 'ྐྵ'), - (0xFBA, 'V'), - (0xFBD, 'X'), - (0xFBE, 'V'), - (0xFCD, 'X'), - (0xFCE, 'V'), - (0xFDB, 'X'), - (0x1000, 'V'), - (0x10A0, 'X'), - (0x10C7, 'M', 'ⴧ'), - (0x10C8, 'X'), - (0x10CD, 'M', 'ⴭ'), - (0x10CE, 'X'), - (0x10D0, 'V'), - (0x10FC, 'M', 'ნ'), - (0x10FD, 'V'), - (0x115F, 'X'), - (0x1161, 'V'), - (0x1249, 'X'), - (0x124A, 'V'), - (0x124E, 'X'), - (0x1250, 'V'), - (0x1257, 'X'), - (0x1258, 'V'), - (0x1259, 'X'), - (0x125A, 'V'), - (0x125E, 'X'), - (0x1260, 'V'), - (0x1289, 'X'), - (0x128A, 'V'), - (0x128E, 'X'), - (0x1290, 'V'), - (0x12B1, 'X'), - (0x12B2, 'V'), - (0x12B6, 'X'), - (0x12B8, 'V'), - (0x12BF, 'X'), - (0x12C0, 'V'), - (0x12C1, 'X'), - (0x12C2, 'V'), - (0x12C6, 'X'), - (0x12C8, 'V'), - (0x12D7, 'X'), - (0x12D8, 'V'), - (0x1311, 'X'), - (0x1312, 'V'), + (0xEBE, "X"), + (0xEC0, "V"), + (0xEC5, "X"), + (0xEC6, "V"), + (0xEC7, "X"), + (0xEC8, "V"), + (0xECF, "X"), + (0xED0, "V"), + (0xEDA, "X"), + (0xEDC, "M", "ຫນ"), + (0xEDD, "M", "ຫມ"), + (0xEDE, "V"), + (0xEE0, "X"), + (0xF00, "V"), + (0xF0C, "M", "་"), + (0xF0D, "V"), + (0xF43, "M", "གྷ"), + (0xF44, "V"), + (0xF48, "X"), + (0xF49, "V"), + (0xF4D, "M", "ཌྷ"), + (0xF4E, "V"), + (0xF52, "M", "དྷ"), + (0xF53, "V"), + (0xF57, "M", "བྷ"), + (0xF58, "V"), + (0xF5C, "M", "ཛྷ"), + (0xF5D, "V"), + (0xF69, "M", "ཀྵ"), + (0xF6A, "V"), + (0xF6D, "X"), + (0xF71, "V"), + (0xF73, "M", "ཱི"), + (0xF74, "V"), + (0xF75, "M", "ཱུ"), + (0xF76, "M", "ྲྀ"), + (0xF77, "M", "ྲཱྀ"), + (0xF78, "M", "ླྀ"), + (0xF79, "M", "ླཱྀ"), + (0xF7A, "V"), + (0xF81, "M", "ཱྀ"), + (0xF82, "V"), + (0xF93, "M", "ྒྷ"), + (0xF94, "V"), + (0xF98, "X"), + (0xF99, "V"), + (0xF9D, "M", "ྜྷ"), + (0xF9E, "V"), + (0xFA2, "M", "ྡྷ"), + (0xFA3, "V"), + (0xFA7, "M", "ྦྷ"), + (0xFA8, "V"), + (0xFAC, "M", "ྫྷ"), + (0xFAD, "V"), + (0xFB9, "M", "ྐྵ"), + (0xFBA, "V"), + (0xFBD, "X"), + (0xFBE, "V"), + (0xFCD, "X"), + (0xFCE, "V"), + (0xFDB, "X"), + (0x1000, "V"), + (0x10A0, "X"), + (0x10C7, "M", "ⴧ"), + (0x10C8, "X"), + (0x10CD, "M", "ⴭ"), + (0x10CE, "X"), + (0x10D0, "V"), + (0x10FC, "M", "ნ"), + (0x10FD, "V"), + (0x115F, "X"), + (0x1161, "V"), + (0x1249, "X"), + (0x124A, "V"), + (0x124E, "X"), + (0x1250, "V"), + (0x1257, "X"), + (0x1258, "V"), + (0x1259, "X"), + (0x125A, "V"), + (0x125E, "X"), + (0x1260, "V"), + (0x1289, "X"), + (0x128A, "V"), + (0x128E, "X"), + (0x1290, "V"), + (0x12B1, "X"), + (0x12B2, "V"), + (0x12B6, "X"), + (0x12B8, "V"), + (0x12BF, "X"), + (0x12C0, "V"), + (0x12C1, "X"), + (0x12C2, "V"), + (0x12C6, "X"), + (0x12C8, "V"), + (0x12D7, "X"), + (0x12D8, "V"), + (0x1311, "X"), + (0x1312, "V"), ] + def _seg_14() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1316, 'X'), - (0x1318, 'V'), - (0x135B, 'X'), - (0x135D, 'V'), - (0x137D, 'X'), - (0x1380, 'V'), - (0x139A, 'X'), - (0x13A0, 'V'), - (0x13F6, 'X'), - (0x13F8, 'M', 'Ᏸ'), - (0x13F9, 'M', 'Ᏹ'), - (0x13FA, 'M', 'Ᏺ'), - (0x13FB, 'M', 'Ᏻ'), - (0x13FC, 'M', 'Ᏼ'), - (0x13FD, 'M', 'Ᏽ'), - (0x13FE, 'X'), - (0x1400, 'V'), - (0x1680, 'X'), - (0x1681, 'V'), - (0x169D, 'X'), - (0x16A0, 'V'), - (0x16F9, 'X'), - (0x1700, 'V'), - (0x1716, 'X'), - (0x171F, 'V'), - (0x1737, 'X'), - (0x1740, 'V'), - (0x1754, 'X'), - (0x1760, 'V'), - (0x176D, 'X'), - (0x176E, 'V'), - (0x1771, 'X'), - (0x1772, 'V'), - (0x1774, 'X'), - (0x1780, 'V'), - (0x17B4, 'X'), - (0x17B6, 'V'), - (0x17DE, 'X'), - (0x17E0, 'V'), - (0x17EA, 'X'), - (0x17F0, 'V'), - (0x17FA, 'X'), - (0x1800, 'V'), - (0x1806, 'X'), - (0x1807, 'V'), - (0x180B, 'I'), - (0x180E, 'X'), - (0x180F, 'I'), - (0x1810, 'V'), - (0x181A, 'X'), - (0x1820, 'V'), - (0x1879, 'X'), - (0x1880, 'V'), - (0x18AB, 'X'), - (0x18B0, 'V'), - (0x18F6, 'X'), - (0x1900, 'V'), - (0x191F, 'X'), - (0x1920, 'V'), - (0x192C, 'X'), - (0x1930, 'V'), - (0x193C, 'X'), - (0x1940, 'V'), - (0x1941, 'X'), - (0x1944, 'V'), - (0x196E, 'X'), - (0x1970, 'V'), - (0x1975, 'X'), - (0x1980, 'V'), - (0x19AC, 'X'), - (0x19B0, 'V'), - (0x19CA, 'X'), - (0x19D0, 'V'), - (0x19DB, 'X'), - (0x19DE, 'V'), - (0x1A1C, 'X'), - (0x1A1E, 'V'), - (0x1A5F, 'X'), - (0x1A60, 'V'), - (0x1A7D, 'X'), - (0x1A7F, 'V'), - (0x1A8A, 'X'), - (0x1A90, 'V'), - (0x1A9A, 'X'), - (0x1AA0, 'V'), - (0x1AAE, 'X'), - (0x1AB0, 'V'), - (0x1ACF, 'X'), - (0x1B00, 'V'), - (0x1B4D, 'X'), - (0x1B50, 'V'), - (0x1B7F, 'X'), - (0x1B80, 'V'), - (0x1BF4, 'X'), - (0x1BFC, 'V'), - (0x1C38, 'X'), - (0x1C3B, 'V'), - (0x1C4A, 'X'), - (0x1C4D, 'V'), - (0x1C80, 'M', 'в'), + (0x1316, "X"), + (0x1318, "V"), + (0x135B, "X"), + (0x135D, "V"), + (0x137D, "X"), + (0x1380, "V"), + (0x139A, "X"), + (0x13A0, "V"), + (0x13F6, "X"), + (0x13F8, "M", "Ᏸ"), + (0x13F9, "M", "Ᏹ"), + (0x13FA, "M", "Ᏺ"), + (0x13FB, "M", "Ᏻ"), + (0x13FC, "M", "Ᏼ"), + (0x13FD, "M", "Ᏽ"), + (0x13FE, "X"), + (0x1400, "V"), + (0x1680, "X"), + (0x1681, "V"), + (0x169D, "X"), + (0x16A0, "V"), + (0x16F9, "X"), + (0x1700, "V"), + (0x1716, "X"), + (0x171F, "V"), + (0x1737, "X"), + (0x1740, "V"), + (0x1754, "X"), + (0x1760, "V"), + (0x176D, "X"), + (0x176E, "V"), + (0x1771, "X"), + (0x1772, "V"), + (0x1774, "X"), + (0x1780, "V"), + (0x17B4, "X"), + (0x17B6, "V"), + (0x17DE, "X"), + (0x17E0, "V"), + (0x17EA, "X"), + (0x17F0, "V"), + (0x17FA, "X"), + (0x1800, "V"), + (0x1806, "X"), + (0x1807, "V"), + (0x180B, "I"), + (0x180E, "X"), + (0x180F, "I"), + (0x1810, "V"), + (0x181A, "X"), + (0x1820, "V"), + (0x1879, "X"), + (0x1880, "V"), + (0x18AB, "X"), + (0x18B0, "V"), + (0x18F6, "X"), + (0x1900, "V"), + (0x191F, "X"), + (0x1920, "V"), + (0x192C, "X"), + (0x1930, "V"), + (0x193C, "X"), + (0x1940, "V"), + (0x1941, "X"), + (0x1944, "V"), + (0x196E, "X"), + (0x1970, "V"), + (0x1975, "X"), + (0x1980, "V"), + (0x19AC, "X"), + (0x19B0, "V"), + (0x19CA, "X"), + (0x19D0, "V"), + (0x19DB, "X"), + (0x19DE, "V"), + (0x1A1C, "X"), + (0x1A1E, "V"), + (0x1A5F, "X"), + (0x1A60, "V"), + (0x1A7D, "X"), + (0x1A7F, "V"), + (0x1A8A, "X"), + (0x1A90, "V"), + (0x1A9A, "X"), + (0x1AA0, "V"), + (0x1AAE, "X"), + (0x1AB0, "V"), + (0x1ACF, "X"), + (0x1B00, "V"), + (0x1B4D, "X"), + (0x1B50, "V"), + (0x1B7F, "X"), + (0x1B80, "V"), + (0x1BF4, "X"), + (0x1BFC, "V"), + (0x1C38, "X"), + (0x1C3B, "V"), + (0x1C4A, "X"), + (0x1C4D, "V"), + (0x1C80, "M", "в"), ] + def _seg_15() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1C81, 'M', 'д'), - (0x1C82, 'M', 'о'), - (0x1C83, 'M', 'с'), - (0x1C84, 'M', 'т'), - (0x1C86, 'M', 'ъ'), - (0x1C87, 'M', 'ѣ'), - (0x1C88, 'M', 'ꙋ'), - (0x1C89, 'X'), - (0x1C90, 'M', 'ა'), - (0x1C91, 'M', 'ბ'), - (0x1C92, 'M', 'გ'), - (0x1C93, 'M', 'დ'), - (0x1C94, 'M', 'ე'), - (0x1C95, 'M', 'ვ'), - (0x1C96, 'M', 'ზ'), - (0x1C97, 'M', 'თ'), - (0x1C98, 'M', 'ი'), - (0x1C99, 'M', 'კ'), - (0x1C9A, 'M', 'ლ'), - (0x1C9B, 'M', 'მ'), - (0x1C9C, 'M', 'ნ'), - (0x1C9D, 'M', 'ო'), - (0x1C9E, 'M', 'პ'), - (0x1C9F, 'M', 'ჟ'), - (0x1CA0, 'M', 'რ'), - (0x1CA1, 'M', 'ს'), - (0x1CA2, 'M', 'ტ'), - (0x1CA3, 'M', 'უ'), - (0x1CA4, 'M', 'ფ'), - (0x1CA5, 'M', 'ქ'), - (0x1CA6, 'M', 'ღ'), - (0x1CA7, 'M', 'ყ'), - (0x1CA8, 'M', 'შ'), - (0x1CA9, 'M', 'ჩ'), - (0x1CAA, 'M', 'ც'), - (0x1CAB, 'M', 'ძ'), - (0x1CAC, 'M', 'წ'), - (0x1CAD, 'M', 'ჭ'), - (0x1CAE, 'M', 'ხ'), - (0x1CAF, 'M', 'ჯ'), - (0x1CB0, 'M', 'ჰ'), - (0x1CB1, 'M', 'ჱ'), - (0x1CB2, 'M', 'ჲ'), - (0x1CB3, 'M', 'ჳ'), - (0x1CB4, 'M', 'ჴ'), - (0x1CB5, 'M', 'ჵ'), - (0x1CB6, 'M', 'ჶ'), - (0x1CB7, 'M', 'ჷ'), - (0x1CB8, 'M', 'ჸ'), - (0x1CB9, 'M', 'ჹ'), - (0x1CBA, 'M', 'ჺ'), - (0x1CBB, 'X'), - (0x1CBD, 'M', 'ჽ'), - (0x1CBE, 'M', 'ჾ'), - (0x1CBF, 'M', 'ჿ'), - (0x1CC0, 'V'), - (0x1CC8, 'X'), - (0x1CD0, 'V'), - (0x1CFB, 'X'), - (0x1D00, 'V'), - (0x1D2C, 'M', 'a'), - (0x1D2D, 'M', 'æ'), - (0x1D2E, 'M', 'b'), - (0x1D2F, 'V'), - (0x1D30, 'M', 'd'), - (0x1D31, 'M', 'e'), - (0x1D32, 'M', 'ǝ'), - (0x1D33, 'M', 'g'), - (0x1D34, 'M', 'h'), - (0x1D35, 'M', 'i'), - (0x1D36, 'M', 'j'), - (0x1D37, 'M', 'k'), - (0x1D38, 'M', 'l'), - (0x1D39, 'M', 'm'), - (0x1D3A, 'M', 'n'), - (0x1D3B, 'V'), - (0x1D3C, 'M', 'o'), - (0x1D3D, 'M', 'ȣ'), - (0x1D3E, 'M', 'p'), - (0x1D3F, 'M', 'r'), - (0x1D40, 'M', 't'), - (0x1D41, 'M', 'u'), - (0x1D42, 'M', 'w'), - (0x1D43, 'M', 'a'), - (0x1D44, 'M', 'ɐ'), - (0x1D45, 'M', 'ɑ'), - (0x1D46, 'M', 'ᴂ'), - (0x1D47, 'M', 'b'), - (0x1D48, 'M', 'd'), - (0x1D49, 'M', 'e'), - (0x1D4A, 'M', 'ə'), - (0x1D4B, 'M', 'ɛ'), - (0x1D4C, 'M', 'ɜ'), - (0x1D4D, 'M', 'g'), - (0x1D4E, 'V'), - (0x1D4F, 'M', 'k'), - (0x1D50, 'M', 'm'), - (0x1D51, 'M', 'ŋ'), - (0x1D52, 'M', 'o'), - (0x1D53, 'M', 'ɔ'), + (0x1C81, "M", "д"), + (0x1C82, "M", "о"), + (0x1C83, "M", "с"), + (0x1C84, "M", "т"), + (0x1C86, "M", "ъ"), + (0x1C87, "M", "ѣ"), + (0x1C88, "M", "ꙋ"), + (0x1C89, "X"), + (0x1C90, "M", "ა"), + (0x1C91, "M", "ბ"), + (0x1C92, "M", "გ"), + (0x1C93, "M", "დ"), + (0x1C94, "M", "ე"), + (0x1C95, "M", "ვ"), + (0x1C96, "M", "ზ"), + (0x1C97, "M", "თ"), + (0x1C98, "M", "ი"), + (0x1C99, "M", "კ"), + (0x1C9A, "M", "ლ"), + (0x1C9B, "M", "მ"), + (0x1C9C, "M", "ნ"), + (0x1C9D, "M", "ო"), + (0x1C9E, "M", "პ"), + (0x1C9F, "M", "ჟ"), + (0x1CA0, "M", "რ"), + (0x1CA1, "M", "ს"), + (0x1CA2, "M", "ტ"), + (0x1CA3, "M", "უ"), + (0x1CA4, "M", "ფ"), + (0x1CA5, "M", "ქ"), + (0x1CA6, "M", "ღ"), + (0x1CA7, "M", "ყ"), + (0x1CA8, "M", "შ"), + (0x1CA9, "M", "ჩ"), + (0x1CAA, "M", "ც"), + (0x1CAB, "M", "ძ"), + (0x1CAC, "M", "წ"), + (0x1CAD, "M", "ჭ"), + (0x1CAE, "M", "ხ"), + (0x1CAF, "M", "ჯ"), + (0x1CB0, "M", "ჰ"), + (0x1CB1, "M", "ჱ"), + (0x1CB2, "M", "ჲ"), + (0x1CB3, "M", "ჳ"), + (0x1CB4, "M", "ჴ"), + (0x1CB5, "M", "ჵ"), + (0x1CB6, "M", "ჶ"), + (0x1CB7, "M", "ჷ"), + (0x1CB8, "M", "ჸ"), + (0x1CB9, "M", "ჹ"), + (0x1CBA, "M", "ჺ"), + (0x1CBB, "X"), + (0x1CBD, "M", "ჽ"), + (0x1CBE, "M", "ჾ"), + (0x1CBF, "M", "ჿ"), + (0x1CC0, "V"), + (0x1CC8, "X"), + (0x1CD0, "V"), + (0x1CFB, "X"), + (0x1D00, "V"), + (0x1D2C, "M", "a"), + (0x1D2D, "M", "æ"), + (0x1D2E, "M", "b"), + (0x1D2F, "V"), + (0x1D30, "M", "d"), + (0x1D31, "M", "e"), + (0x1D32, "M", "ǝ"), + (0x1D33, "M", "g"), + (0x1D34, "M", "h"), + (0x1D35, "M", "i"), + (0x1D36, "M", "j"), + (0x1D37, "M", "k"), + (0x1D38, "M", "l"), + (0x1D39, "M", "m"), + (0x1D3A, "M", "n"), + (0x1D3B, "V"), + (0x1D3C, "M", "o"), + (0x1D3D, "M", "ȣ"), + (0x1D3E, "M", "p"), + (0x1D3F, "M", "r"), + (0x1D40, "M", "t"), + (0x1D41, "M", "u"), + (0x1D42, "M", "w"), + (0x1D43, "M", "a"), + (0x1D44, "M", "ɐ"), + (0x1D45, "M", "ɑ"), + (0x1D46, "M", "ᴂ"), + (0x1D47, "M", "b"), + (0x1D48, "M", "d"), + (0x1D49, "M", "e"), + (0x1D4A, "M", "ə"), + (0x1D4B, "M", "ɛ"), + (0x1D4C, "M", "ɜ"), + (0x1D4D, "M", "g"), + (0x1D4E, "V"), + (0x1D4F, "M", "k"), + (0x1D50, "M", "m"), + (0x1D51, "M", "ŋ"), + (0x1D52, "M", "o"), + (0x1D53, "M", "ɔ"), ] + def _seg_16() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D54, 'M', 'ᴖ'), - (0x1D55, 'M', 'ᴗ'), - (0x1D56, 'M', 'p'), - (0x1D57, 'M', 't'), - (0x1D58, 'M', 'u'), - (0x1D59, 'M', 'ᴝ'), - (0x1D5A, 'M', 'ɯ'), - (0x1D5B, 'M', 'v'), - (0x1D5C, 'M', 'ᴥ'), - (0x1D5D, 'M', 'β'), - (0x1D5E, 'M', 'γ'), - (0x1D5F, 'M', 'δ'), - (0x1D60, 'M', 'φ'), - (0x1D61, 'M', 'χ'), - (0x1D62, 'M', 'i'), - (0x1D63, 'M', 'r'), - (0x1D64, 'M', 'u'), - (0x1D65, 'M', 'v'), - (0x1D66, 'M', 'β'), - (0x1D67, 'M', 'γ'), - (0x1D68, 'M', 'ρ'), - (0x1D69, 'M', 'φ'), - (0x1D6A, 'M', 'χ'), - (0x1D6B, 'V'), - (0x1D78, 'M', 'н'), - (0x1D79, 'V'), - (0x1D9B, 'M', 'ɒ'), - (0x1D9C, 'M', 'c'), - (0x1D9D, 'M', 'ɕ'), - (0x1D9E, 'M', 'ð'), - (0x1D9F, 'M', 'ɜ'), - (0x1DA0, 'M', 'f'), - (0x1DA1, 'M', 'ɟ'), - (0x1DA2, 'M', 'ɡ'), - (0x1DA3, 'M', 'ɥ'), - (0x1DA4, 'M', 'ɨ'), - (0x1DA5, 'M', 'ɩ'), - (0x1DA6, 'M', 'ɪ'), - (0x1DA7, 'M', 'ᵻ'), - (0x1DA8, 'M', 'ʝ'), - (0x1DA9, 'M', 'ɭ'), - (0x1DAA, 'M', 'ᶅ'), - (0x1DAB, 'M', 'ʟ'), - (0x1DAC, 'M', 'ɱ'), - (0x1DAD, 'M', 'ɰ'), - (0x1DAE, 'M', 'ɲ'), - (0x1DAF, 'M', 'ɳ'), - (0x1DB0, 'M', 'ɴ'), - (0x1DB1, 'M', 'ɵ'), - (0x1DB2, 'M', 'ɸ'), - (0x1DB3, 'M', 'ʂ'), - (0x1DB4, 'M', 'ʃ'), - (0x1DB5, 'M', 'ƫ'), - (0x1DB6, 'M', 'ʉ'), - (0x1DB7, 'M', 'ʊ'), - (0x1DB8, 'M', 'ᴜ'), - (0x1DB9, 'M', 'ʋ'), - (0x1DBA, 'M', 'ʌ'), - (0x1DBB, 'M', 'z'), - (0x1DBC, 'M', 'ʐ'), - (0x1DBD, 'M', 'ʑ'), - (0x1DBE, 'M', 'ʒ'), - (0x1DBF, 'M', 'θ'), - (0x1DC0, 'V'), - (0x1E00, 'M', 'ḁ'), - (0x1E01, 'V'), - (0x1E02, 'M', 'ḃ'), - (0x1E03, 'V'), - (0x1E04, 'M', 'ḅ'), - (0x1E05, 'V'), - (0x1E06, 'M', 'ḇ'), - (0x1E07, 'V'), - (0x1E08, 'M', 'ḉ'), - (0x1E09, 'V'), - (0x1E0A, 'M', 'ḋ'), - (0x1E0B, 'V'), - (0x1E0C, 'M', 'ḍ'), - (0x1E0D, 'V'), - (0x1E0E, 'M', 'ḏ'), - (0x1E0F, 'V'), - (0x1E10, 'M', 'ḑ'), - (0x1E11, 'V'), - (0x1E12, 'M', 'ḓ'), - (0x1E13, 'V'), - (0x1E14, 'M', 'ḕ'), - (0x1E15, 'V'), - (0x1E16, 'M', 'ḗ'), - (0x1E17, 'V'), - (0x1E18, 'M', 'ḙ'), - (0x1E19, 'V'), - (0x1E1A, 'M', 'ḛ'), - (0x1E1B, 'V'), - (0x1E1C, 'M', 'ḝ'), - (0x1E1D, 'V'), - (0x1E1E, 'M', 'ḟ'), - (0x1E1F, 'V'), - (0x1E20, 'M', 'ḡ'), - (0x1E21, 'V'), - (0x1E22, 'M', 'ḣ'), - (0x1E23, 'V'), + (0x1D54, "M", "ᴖ"), + (0x1D55, "M", "ᴗ"), + (0x1D56, "M", "p"), + (0x1D57, "M", "t"), + (0x1D58, "M", "u"), + (0x1D59, "M", "ᴝ"), + (0x1D5A, "M", "ɯ"), + (0x1D5B, "M", "v"), + (0x1D5C, "M", "ᴥ"), + (0x1D5D, "M", "β"), + (0x1D5E, "M", "γ"), + (0x1D5F, "M", "δ"), + (0x1D60, "M", "φ"), + (0x1D61, "M", "χ"), + (0x1D62, "M", "i"), + (0x1D63, "M", "r"), + (0x1D64, "M", "u"), + (0x1D65, "M", "v"), + (0x1D66, "M", "β"), + (0x1D67, "M", "γ"), + (0x1D68, "M", "ρ"), + (0x1D69, "M", "φ"), + (0x1D6A, "M", "χ"), + (0x1D6B, "V"), + (0x1D78, "M", "н"), + (0x1D79, "V"), + (0x1D9B, "M", "ɒ"), + (0x1D9C, "M", "c"), + (0x1D9D, "M", "ɕ"), + (0x1D9E, "M", "ð"), + (0x1D9F, "M", "ɜ"), + (0x1DA0, "M", "f"), + (0x1DA1, "M", "ɟ"), + (0x1DA2, "M", "ɡ"), + (0x1DA3, "M", "ɥ"), + (0x1DA4, "M", "ɨ"), + (0x1DA5, "M", "ɩ"), + (0x1DA6, "M", "ɪ"), + (0x1DA7, "M", "ᵻ"), + (0x1DA8, "M", "ʝ"), + (0x1DA9, "M", "ɭ"), + (0x1DAA, "M", "ᶅ"), + (0x1DAB, "M", "ʟ"), + (0x1DAC, "M", "ɱ"), + (0x1DAD, "M", "ɰ"), + (0x1DAE, "M", "ɲ"), + (0x1DAF, "M", "ɳ"), + (0x1DB0, "M", "ɴ"), + (0x1DB1, "M", "ɵ"), + (0x1DB2, "M", "ɸ"), + (0x1DB3, "M", "ʂ"), + (0x1DB4, "M", "ʃ"), + (0x1DB5, "M", "ƫ"), + (0x1DB6, "M", "ʉ"), + (0x1DB7, "M", "ʊ"), + (0x1DB8, "M", "ᴜ"), + (0x1DB9, "M", "ʋ"), + (0x1DBA, "M", "ʌ"), + (0x1DBB, "M", "z"), + (0x1DBC, "M", "ʐ"), + (0x1DBD, "M", "ʑ"), + (0x1DBE, "M", "ʒ"), + (0x1DBF, "M", "θ"), + (0x1DC0, "V"), + (0x1E00, "M", "ḁ"), + (0x1E01, "V"), + (0x1E02, "M", "ḃ"), + (0x1E03, "V"), + (0x1E04, "M", "ḅ"), + (0x1E05, "V"), + (0x1E06, "M", "ḇ"), + (0x1E07, "V"), + (0x1E08, "M", "ḉ"), + (0x1E09, "V"), + (0x1E0A, "M", "ḋ"), + (0x1E0B, "V"), + (0x1E0C, "M", "ḍ"), + (0x1E0D, "V"), + (0x1E0E, "M", "ḏ"), + (0x1E0F, "V"), + (0x1E10, "M", "ḑ"), + (0x1E11, "V"), + (0x1E12, "M", "ḓ"), + (0x1E13, "V"), + (0x1E14, "M", "ḕ"), + (0x1E15, "V"), + (0x1E16, "M", "ḗ"), + (0x1E17, "V"), + (0x1E18, "M", "ḙ"), + (0x1E19, "V"), + (0x1E1A, "M", "ḛ"), + (0x1E1B, "V"), + (0x1E1C, "M", "ḝ"), + (0x1E1D, "V"), + (0x1E1E, "M", "ḟ"), + (0x1E1F, "V"), + (0x1E20, "M", "ḡ"), + (0x1E21, "V"), + (0x1E22, "M", "ḣ"), + (0x1E23, "V"), ] + def _seg_17() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1E24, 'M', 'ḥ'), - (0x1E25, 'V'), - (0x1E26, 'M', 'ḧ'), - (0x1E27, 'V'), - (0x1E28, 'M', 'ḩ'), - (0x1E29, 'V'), - (0x1E2A, 'M', 'ḫ'), - (0x1E2B, 'V'), - (0x1E2C, 'M', 'ḭ'), - (0x1E2D, 'V'), - (0x1E2E, 'M', 'ḯ'), - (0x1E2F, 'V'), - (0x1E30, 'M', 'ḱ'), - (0x1E31, 'V'), - (0x1E32, 'M', 'ḳ'), - (0x1E33, 'V'), - (0x1E34, 'M', 'ḵ'), - (0x1E35, 'V'), - (0x1E36, 'M', 'ḷ'), - (0x1E37, 'V'), - (0x1E38, 'M', 'ḹ'), - (0x1E39, 'V'), - (0x1E3A, 'M', 'ḻ'), - (0x1E3B, 'V'), - (0x1E3C, 'M', 'ḽ'), - (0x1E3D, 'V'), - (0x1E3E, 'M', 'ḿ'), - (0x1E3F, 'V'), - (0x1E40, 'M', 'ṁ'), - (0x1E41, 'V'), - (0x1E42, 'M', 'ṃ'), - (0x1E43, 'V'), - (0x1E44, 'M', 'ṅ'), - (0x1E45, 'V'), - (0x1E46, 'M', 'ṇ'), - (0x1E47, 'V'), - (0x1E48, 'M', 'ṉ'), - (0x1E49, 'V'), - (0x1E4A, 'M', 'ṋ'), - (0x1E4B, 'V'), - (0x1E4C, 'M', 'ṍ'), - (0x1E4D, 'V'), - (0x1E4E, 'M', 'ṏ'), - (0x1E4F, 'V'), - (0x1E50, 'M', 'ṑ'), - (0x1E51, 'V'), - (0x1E52, 'M', 'ṓ'), - (0x1E53, 'V'), - (0x1E54, 'M', 'ṕ'), - (0x1E55, 'V'), - (0x1E56, 'M', 'ṗ'), - (0x1E57, 'V'), - (0x1E58, 'M', 'ṙ'), - (0x1E59, 'V'), - (0x1E5A, 'M', 'ṛ'), - (0x1E5B, 'V'), - (0x1E5C, 'M', 'ṝ'), - (0x1E5D, 'V'), - (0x1E5E, 'M', 'ṟ'), - (0x1E5F, 'V'), - (0x1E60, 'M', 'ṡ'), - (0x1E61, 'V'), - (0x1E62, 'M', 'ṣ'), - (0x1E63, 'V'), - (0x1E64, 'M', 'ṥ'), - (0x1E65, 'V'), - (0x1E66, 'M', 'ṧ'), - (0x1E67, 'V'), - (0x1E68, 'M', 'ṩ'), - (0x1E69, 'V'), - (0x1E6A, 'M', 'ṫ'), - (0x1E6B, 'V'), - (0x1E6C, 'M', 'ṭ'), - (0x1E6D, 'V'), - (0x1E6E, 'M', 'ṯ'), - (0x1E6F, 'V'), - (0x1E70, 'M', 'ṱ'), - (0x1E71, 'V'), - (0x1E72, 'M', 'ṳ'), - (0x1E73, 'V'), - (0x1E74, 'M', 'ṵ'), - (0x1E75, 'V'), - (0x1E76, 'M', 'ṷ'), - (0x1E77, 'V'), - (0x1E78, 'M', 'ṹ'), - (0x1E79, 'V'), - (0x1E7A, 'M', 'ṻ'), - (0x1E7B, 'V'), - (0x1E7C, 'M', 'ṽ'), - (0x1E7D, 'V'), - (0x1E7E, 'M', 'ṿ'), - (0x1E7F, 'V'), - (0x1E80, 'M', 'ẁ'), - (0x1E81, 'V'), - (0x1E82, 'M', 'ẃ'), - (0x1E83, 'V'), - (0x1E84, 'M', 'ẅ'), - (0x1E85, 'V'), - (0x1E86, 'M', 'ẇ'), - (0x1E87, 'V'), + (0x1E24, "M", "ḥ"), + (0x1E25, "V"), + (0x1E26, "M", "ḧ"), + (0x1E27, "V"), + (0x1E28, "M", "ḩ"), + (0x1E29, "V"), + (0x1E2A, "M", "ḫ"), + (0x1E2B, "V"), + (0x1E2C, "M", "ḭ"), + (0x1E2D, "V"), + (0x1E2E, "M", "ḯ"), + (0x1E2F, "V"), + (0x1E30, "M", "ḱ"), + (0x1E31, "V"), + (0x1E32, "M", "ḳ"), + (0x1E33, "V"), + (0x1E34, "M", "ḵ"), + (0x1E35, "V"), + (0x1E36, "M", "ḷ"), + (0x1E37, "V"), + (0x1E38, "M", "ḹ"), + (0x1E39, "V"), + (0x1E3A, "M", "ḻ"), + (0x1E3B, "V"), + (0x1E3C, "M", "ḽ"), + (0x1E3D, "V"), + (0x1E3E, "M", "ḿ"), + (0x1E3F, "V"), + (0x1E40, "M", "ṁ"), + (0x1E41, "V"), + (0x1E42, "M", "ṃ"), + (0x1E43, "V"), + (0x1E44, "M", "ṅ"), + (0x1E45, "V"), + (0x1E46, "M", "ṇ"), + (0x1E47, "V"), + (0x1E48, "M", "ṉ"), + (0x1E49, "V"), + (0x1E4A, "M", "ṋ"), + (0x1E4B, "V"), + (0x1E4C, "M", "ṍ"), + (0x1E4D, "V"), + (0x1E4E, "M", "ṏ"), + (0x1E4F, "V"), + (0x1E50, "M", "ṑ"), + (0x1E51, "V"), + (0x1E52, "M", "ṓ"), + (0x1E53, "V"), + (0x1E54, "M", "ṕ"), + (0x1E55, "V"), + (0x1E56, "M", "ṗ"), + (0x1E57, "V"), + (0x1E58, "M", "ṙ"), + (0x1E59, "V"), + (0x1E5A, "M", "ṛ"), + (0x1E5B, "V"), + (0x1E5C, "M", "ṝ"), + (0x1E5D, "V"), + (0x1E5E, "M", "ṟ"), + (0x1E5F, "V"), + (0x1E60, "M", "ṡ"), + (0x1E61, "V"), + (0x1E62, "M", "ṣ"), + (0x1E63, "V"), + (0x1E64, "M", "ṥ"), + (0x1E65, "V"), + (0x1E66, "M", "ṧ"), + (0x1E67, "V"), + (0x1E68, "M", "ṩ"), + (0x1E69, "V"), + (0x1E6A, "M", "ṫ"), + (0x1E6B, "V"), + (0x1E6C, "M", "ṭ"), + (0x1E6D, "V"), + (0x1E6E, "M", "ṯ"), + (0x1E6F, "V"), + (0x1E70, "M", "ṱ"), + (0x1E71, "V"), + (0x1E72, "M", "ṳ"), + (0x1E73, "V"), + (0x1E74, "M", "ṵ"), + (0x1E75, "V"), + (0x1E76, "M", "ṷ"), + (0x1E77, "V"), + (0x1E78, "M", "ṹ"), + (0x1E79, "V"), + (0x1E7A, "M", "ṻ"), + (0x1E7B, "V"), + (0x1E7C, "M", "ṽ"), + (0x1E7D, "V"), + (0x1E7E, "M", "ṿ"), + (0x1E7F, "V"), + (0x1E80, "M", "ẁ"), + (0x1E81, "V"), + (0x1E82, "M", "ẃ"), + (0x1E83, "V"), + (0x1E84, "M", "ẅ"), + (0x1E85, "V"), + (0x1E86, "M", "ẇ"), + (0x1E87, "V"), ] + def _seg_18() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1E88, 'M', 'ẉ'), - (0x1E89, 'V'), - (0x1E8A, 'M', 'ẋ'), - (0x1E8B, 'V'), - (0x1E8C, 'M', 'ẍ'), - (0x1E8D, 'V'), - (0x1E8E, 'M', 'ẏ'), - (0x1E8F, 'V'), - (0x1E90, 'M', 'ẑ'), - (0x1E91, 'V'), - (0x1E92, 'M', 'ẓ'), - (0x1E93, 'V'), - (0x1E94, 'M', 'ẕ'), - (0x1E95, 'V'), - (0x1E9A, 'M', 'aʾ'), - (0x1E9B, 'M', 'ṡ'), - (0x1E9C, 'V'), - (0x1E9E, 'M', 'ss'), - (0x1E9F, 'V'), - (0x1EA0, 'M', 'ạ'), - (0x1EA1, 'V'), - (0x1EA2, 'M', 'ả'), - (0x1EA3, 'V'), - (0x1EA4, 'M', 'ấ'), - (0x1EA5, 'V'), - (0x1EA6, 'M', 'ầ'), - (0x1EA7, 'V'), - (0x1EA8, 'M', 'ẩ'), - (0x1EA9, 'V'), - (0x1EAA, 'M', 'ẫ'), - (0x1EAB, 'V'), - (0x1EAC, 'M', 'ậ'), - (0x1EAD, 'V'), - (0x1EAE, 'M', 'ắ'), - (0x1EAF, 'V'), - (0x1EB0, 'M', 'ằ'), - (0x1EB1, 'V'), - (0x1EB2, 'M', 'ẳ'), - (0x1EB3, 'V'), - (0x1EB4, 'M', 'ẵ'), - (0x1EB5, 'V'), - (0x1EB6, 'M', 'ặ'), - (0x1EB7, 'V'), - (0x1EB8, 'M', 'ẹ'), - (0x1EB9, 'V'), - (0x1EBA, 'M', 'ẻ'), - (0x1EBB, 'V'), - (0x1EBC, 'M', 'ẽ'), - (0x1EBD, 'V'), - (0x1EBE, 'M', 'ế'), - (0x1EBF, 'V'), - (0x1EC0, 'M', 'ề'), - (0x1EC1, 'V'), - (0x1EC2, 'M', 'ể'), - (0x1EC3, 'V'), - (0x1EC4, 'M', 'ễ'), - (0x1EC5, 'V'), - (0x1EC6, 'M', 'ệ'), - (0x1EC7, 'V'), - (0x1EC8, 'M', 'ỉ'), - (0x1EC9, 'V'), - (0x1ECA, 'M', 'ị'), - (0x1ECB, 'V'), - (0x1ECC, 'M', 'ọ'), - (0x1ECD, 'V'), - (0x1ECE, 'M', 'ỏ'), - (0x1ECF, 'V'), - (0x1ED0, 'M', 'ố'), - (0x1ED1, 'V'), - (0x1ED2, 'M', 'ồ'), - (0x1ED3, 'V'), - (0x1ED4, 'M', 'ổ'), - (0x1ED5, 'V'), - (0x1ED6, 'M', 'ỗ'), - (0x1ED7, 'V'), - (0x1ED8, 'M', 'ộ'), - (0x1ED9, 'V'), - (0x1EDA, 'M', 'ớ'), - (0x1EDB, 'V'), - (0x1EDC, 'M', 'ờ'), - (0x1EDD, 'V'), - (0x1EDE, 'M', 'ở'), - (0x1EDF, 'V'), - (0x1EE0, 'M', 'ỡ'), - (0x1EE1, 'V'), - (0x1EE2, 'M', 'ợ'), - (0x1EE3, 'V'), - (0x1EE4, 'M', 'ụ'), - (0x1EE5, 'V'), - (0x1EE6, 'M', 'ủ'), - (0x1EE7, 'V'), - (0x1EE8, 'M', 'ứ'), - (0x1EE9, 'V'), - (0x1EEA, 'M', 'ừ'), - (0x1EEB, 'V'), - (0x1EEC, 'M', 'ử'), - (0x1EED, 'V'), - (0x1EEE, 'M', 'ữ'), - (0x1EEF, 'V'), - (0x1EF0, 'M', 'ự'), + (0x1E88, "M", "ẉ"), + (0x1E89, "V"), + (0x1E8A, "M", "ẋ"), + (0x1E8B, "V"), + (0x1E8C, "M", "ẍ"), + (0x1E8D, "V"), + (0x1E8E, "M", "ẏ"), + (0x1E8F, "V"), + (0x1E90, "M", "ẑ"), + (0x1E91, "V"), + (0x1E92, "M", "ẓ"), + (0x1E93, "V"), + (0x1E94, "M", "ẕ"), + (0x1E95, "V"), + (0x1E9A, "M", "aʾ"), + (0x1E9B, "M", "ṡ"), + (0x1E9C, "V"), + (0x1E9E, "M", "ß"), + (0x1E9F, "V"), + (0x1EA0, "M", "ạ"), + (0x1EA1, "V"), + (0x1EA2, "M", "ả"), + (0x1EA3, "V"), + (0x1EA4, "M", "ấ"), + (0x1EA5, "V"), + (0x1EA6, "M", "ầ"), + (0x1EA7, "V"), + (0x1EA8, "M", "ẩ"), + (0x1EA9, "V"), + (0x1EAA, "M", "ẫ"), + (0x1EAB, "V"), + (0x1EAC, "M", "ậ"), + (0x1EAD, "V"), + (0x1EAE, "M", "ắ"), + (0x1EAF, "V"), + (0x1EB0, "M", "ằ"), + (0x1EB1, "V"), + (0x1EB2, "M", "ẳ"), + (0x1EB3, "V"), + (0x1EB4, "M", "ẵ"), + (0x1EB5, "V"), + (0x1EB6, "M", "ặ"), + (0x1EB7, "V"), + (0x1EB8, "M", "ẹ"), + (0x1EB9, "V"), + (0x1EBA, "M", "ẻ"), + (0x1EBB, "V"), + (0x1EBC, "M", "ẽ"), + (0x1EBD, "V"), + (0x1EBE, "M", "ế"), + (0x1EBF, "V"), + (0x1EC0, "M", "ề"), + (0x1EC1, "V"), + (0x1EC2, "M", "ể"), + (0x1EC3, "V"), + (0x1EC4, "M", "ễ"), + (0x1EC5, "V"), + (0x1EC6, "M", "ệ"), + (0x1EC7, "V"), + (0x1EC8, "M", "ỉ"), + (0x1EC9, "V"), + (0x1ECA, "M", "ị"), + (0x1ECB, "V"), + (0x1ECC, "M", "ọ"), + (0x1ECD, "V"), + (0x1ECE, "M", "ỏ"), + (0x1ECF, "V"), + (0x1ED0, "M", "ố"), + (0x1ED1, "V"), + (0x1ED2, "M", "ồ"), + (0x1ED3, "V"), + (0x1ED4, "M", "ổ"), + (0x1ED5, "V"), + (0x1ED6, "M", "ỗ"), + (0x1ED7, "V"), + (0x1ED8, "M", "ộ"), + (0x1ED9, "V"), + (0x1EDA, "M", "ớ"), + (0x1EDB, "V"), + (0x1EDC, "M", "ờ"), + (0x1EDD, "V"), + (0x1EDE, "M", "ở"), + (0x1EDF, "V"), + (0x1EE0, "M", "ỡ"), + (0x1EE1, "V"), + (0x1EE2, "M", "ợ"), + (0x1EE3, "V"), + (0x1EE4, "M", "ụ"), + (0x1EE5, "V"), + (0x1EE6, "M", "ủ"), + (0x1EE7, "V"), + (0x1EE8, "M", "ứ"), + (0x1EE9, "V"), + (0x1EEA, "M", "ừ"), + (0x1EEB, "V"), + (0x1EEC, "M", "ử"), + (0x1EED, "V"), + (0x1EEE, "M", "ữ"), + (0x1EEF, "V"), + (0x1EF0, "M", "ự"), ] + def _seg_19() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1EF1, 'V'), - (0x1EF2, 'M', 'ỳ'), - (0x1EF3, 'V'), - (0x1EF4, 'M', 'ỵ'), - (0x1EF5, 'V'), - (0x1EF6, 'M', 'ỷ'), - (0x1EF7, 'V'), - (0x1EF8, 'M', 'ỹ'), - (0x1EF9, 'V'), - (0x1EFA, 'M', 'ỻ'), - (0x1EFB, 'V'), - (0x1EFC, 'M', 'ỽ'), - (0x1EFD, 'V'), - (0x1EFE, 'M', 'ỿ'), - (0x1EFF, 'V'), - (0x1F08, 'M', 'ἀ'), - (0x1F09, 'M', 'ἁ'), - (0x1F0A, 'M', 'ἂ'), - (0x1F0B, 'M', 'ἃ'), - (0x1F0C, 'M', 'ἄ'), - (0x1F0D, 'M', 'ἅ'), - (0x1F0E, 'M', 'ἆ'), - (0x1F0F, 'M', 'ἇ'), - (0x1F10, 'V'), - (0x1F16, 'X'), - (0x1F18, 'M', 'ἐ'), - (0x1F19, 'M', 'ἑ'), - (0x1F1A, 'M', 'ἒ'), - (0x1F1B, 'M', 'ἓ'), - (0x1F1C, 'M', 'ἔ'), - (0x1F1D, 'M', 'ἕ'), - (0x1F1E, 'X'), - (0x1F20, 'V'), - (0x1F28, 'M', 'ἠ'), - (0x1F29, 'M', 'ἡ'), - (0x1F2A, 'M', 'ἢ'), - (0x1F2B, 'M', 'ἣ'), - (0x1F2C, 'M', 'ἤ'), - (0x1F2D, 'M', 'ἥ'), - (0x1F2E, 'M', 'ἦ'), - (0x1F2F, 'M', 'ἧ'), - (0x1F30, 'V'), - (0x1F38, 'M', 'ἰ'), - (0x1F39, 'M', 'ἱ'), - (0x1F3A, 'M', 'ἲ'), - (0x1F3B, 'M', 'ἳ'), - (0x1F3C, 'M', 'ἴ'), - (0x1F3D, 'M', 'ἵ'), - (0x1F3E, 'M', 'ἶ'), - (0x1F3F, 'M', 'ἷ'), - (0x1F40, 'V'), - (0x1F46, 'X'), - (0x1F48, 'M', 'ὀ'), - (0x1F49, 'M', 'ὁ'), - (0x1F4A, 'M', 'ὂ'), - (0x1F4B, 'M', 'ὃ'), - (0x1F4C, 'M', 'ὄ'), - (0x1F4D, 'M', 'ὅ'), - (0x1F4E, 'X'), - (0x1F50, 'V'), - (0x1F58, 'X'), - (0x1F59, 'M', 'ὑ'), - (0x1F5A, 'X'), - (0x1F5B, 'M', 'ὓ'), - (0x1F5C, 'X'), - (0x1F5D, 'M', 'ὕ'), - (0x1F5E, 'X'), - (0x1F5F, 'M', 'ὗ'), - (0x1F60, 'V'), - (0x1F68, 'M', 'ὠ'), - (0x1F69, 'M', 'ὡ'), - (0x1F6A, 'M', 'ὢ'), - (0x1F6B, 'M', 'ὣ'), - (0x1F6C, 'M', 'ὤ'), - (0x1F6D, 'M', 'ὥ'), - (0x1F6E, 'M', 'ὦ'), - (0x1F6F, 'M', 'ὧ'), - (0x1F70, 'V'), - (0x1F71, 'M', 'ά'), - (0x1F72, 'V'), - (0x1F73, 'M', 'έ'), - (0x1F74, 'V'), - (0x1F75, 'M', 'ή'), - (0x1F76, 'V'), - (0x1F77, 'M', 'ί'), - (0x1F78, 'V'), - (0x1F79, 'M', 'ό'), - (0x1F7A, 'V'), - (0x1F7B, 'M', 'ύ'), - (0x1F7C, 'V'), - (0x1F7D, 'M', 'ώ'), - (0x1F7E, 'X'), - (0x1F80, 'M', 'ἀι'), - (0x1F81, 'M', 'ἁι'), - (0x1F82, 'M', 'ἂι'), - (0x1F83, 'M', 'ἃι'), - (0x1F84, 'M', 'ἄι'), - (0x1F85, 'M', 'ἅι'), - (0x1F86, 'M', 'ἆι'), - (0x1F87, 'M', 'ἇι'), + (0x1EF1, "V"), + (0x1EF2, "M", "ỳ"), + (0x1EF3, "V"), + (0x1EF4, "M", "ỵ"), + (0x1EF5, "V"), + (0x1EF6, "M", "ỷ"), + (0x1EF7, "V"), + (0x1EF8, "M", "ỹ"), + (0x1EF9, "V"), + (0x1EFA, "M", "ỻ"), + (0x1EFB, "V"), + (0x1EFC, "M", "ỽ"), + (0x1EFD, "V"), + (0x1EFE, "M", "ỿ"), + (0x1EFF, "V"), + (0x1F08, "M", "ἀ"), + (0x1F09, "M", "ἁ"), + (0x1F0A, "M", "ἂ"), + (0x1F0B, "M", "ἃ"), + (0x1F0C, "M", "ἄ"), + (0x1F0D, "M", "ἅ"), + (0x1F0E, "M", "ἆ"), + (0x1F0F, "M", "ἇ"), + (0x1F10, "V"), + (0x1F16, "X"), + (0x1F18, "M", "ἐ"), + (0x1F19, "M", "ἑ"), + (0x1F1A, "M", "ἒ"), + (0x1F1B, "M", "ἓ"), + (0x1F1C, "M", "ἔ"), + (0x1F1D, "M", "ἕ"), + (0x1F1E, "X"), + (0x1F20, "V"), + (0x1F28, "M", "ἠ"), + (0x1F29, "M", "ἡ"), + (0x1F2A, "M", "ἢ"), + (0x1F2B, "M", "ἣ"), + (0x1F2C, "M", "ἤ"), + (0x1F2D, "M", "ἥ"), + (0x1F2E, "M", "ἦ"), + (0x1F2F, "M", "ἧ"), + (0x1F30, "V"), + (0x1F38, "M", "ἰ"), + (0x1F39, "M", "ἱ"), + (0x1F3A, "M", "ἲ"), + (0x1F3B, "M", "ἳ"), + (0x1F3C, "M", "ἴ"), + (0x1F3D, "M", "ἵ"), + (0x1F3E, "M", "ἶ"), + (0x1F3F, "M", "ἷ"), + (0x1F40, "V"), + (0x1F46, "X"), + (0x1F48, "M", "ὀ"), + (0x1F49, "M", "ὁ"), + (0x1F4A, "M", "ὂ"), + (0x1F4B, "M", "ὃ"), + (0x1F4C, "M", "ὄ"), + (0x1F4D, "M", "ὅ"), + (0x1F4E, "X"), + (0x1F50, "V"), + (0x1F58, "X"), + (0x1F59, "M", "ὑ"), + (0x1F5A, "X"), + (0x1F5B, "M", "ὓ"), + (0x1F5C, "X"), + (0x1F5D, "M", "ὕ"), + (0x1F5E, "X"), + (0x1F5F, "M", "ὗ"), + (0x1F60, "V"), + (0x1F68, "M", "ὠ"), + (0x1F69, "M", "ὡ"), + (0x1F6A, "M", "ὢ"), + (0x1F6B, "M", "ὣ"), + (0x1F6C, "M", "ὤ"), + (0x1F6D, "M", "ὥ"), + (0x1F6E, "M", "ὦ"), + (0x1F6F, "M", "ὧ"), + (0x1F70, "V"), + (0x1F71, "M", "ά"), + (0x1F72, "V"), + (0x1F73, "M", "έ"), + (0x1F74, "V"), + (0x1F75, "M", "ή"), + (0x1F76, "V"), + (0x1F77, "M", "ί"), + (0x1F78, "V"), + (0x1F79, "M", "ό"), + (0x1F7A, "V"), + (0x1F7B, "M", "ύ"), + (0x1F7C, "V"), + (0x1F7D, "M", "ώ"), + (0x1F7E, "X"), + (0x1F80, "M", "ἀι"), + (0x1F81, "M", "ἁι"), + (0x1F82, "M", "ἂι"), + (0x1F83, "M", "ἃι"), + (0x1F84, "M", "ἄι"), + (0x1F85, "M", "ἅι"), + (0x1F86, "M", "ἆι"), + (0x1F87, "M", "ἇι"), ] + def _seg_20() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1F88, 'M', 'ἀι'), - (0x1F89, 'M', 'ἁι'), - (0x1F8A, 'M', 'ἂι'), - (0x1F8B, 'M', 'ἃι'), - (0x1F8C, 'M', 'ἄι'), - (0x1F8D, 'M', 'ἅι'), - (0x1F8E, 'M', 'ἆι'), - (0x1F8F, 'M', 'ἇι'), - (0x1F90, 'M', 'ἠι'), - (0x1F91, 'M', 'ἡι'), - (0x1F92, 'M', 'ἢι'), - (0x1F93, 'M', 'ἣι'), - (0x1F94, 'M', 'ἤι'), - (0x1F95, 'M', 'ἥι'), - (0x1F96, 'M', 'ἦι'), - (0x1F97, 'M', 'ἧι'), - (0x1F98, 'M', 'ἠι'), - (0x1F99, 'M', 'ἡι'), - (0x1F9A, 'M', 'ἢι'), - (0x1F9B, 'M', 'ἣι'), - (0x1F9C, 'M', 'ἤι'), - (0x1F9D, 'M', 'ἥι'), - (0x1F9E, 'M', 'ἦι'), - (0x1F9F, 'M', 'ἧι'), - (0x1FA0, 'M', 'ὠι'), - (0x1FA1, 'M', 'ὡι'), - (0x1FA2, 'M', 'ὢι'), - (0x1FA3, 'M', 'ὣι'), - (0x1FA4, 'M', 'ὤι'), - (0x1FA5, 'M', 'ὥι'), - (0x1FA6, 'M', 'ὦι'), - (0x1FA7, 'M', 'ὧι'), - (0x1FA8, 'M', 'ὠι'), - (0x1FA9, 'M', 'ὡι'), - (0x1FAA, 'M', 'ὢι'), - (0x1FAB, 'M', 'ὣι'), - (0x1FAC, 'M', 'ὤι'), - (0x1FAD, 'M', 'ὥι'), - (0x1FAE, 'M', 'ὦι'), - (0x1FAF, 'M', 'ὧι'), - (0x1FB0, 'V'), - (0x1FB2, 'M', 'ὰι'), - (0x1FB3, 'M', 'αι'), - (0x1FB4, 'M', 'άι'), - (0x1FB5, 'X'), - (0x1FB6, 'V'), - (0x1FB7, 'M', 'ᾶι'), - (0x1FB8, 'M', 'ᾰ'), - (0x1FB9, 'M', 'ᾱ'), - (0x1FBA, 'M', 'ὰ'), - (0x1FBB, 'M', 'ά'), - (0x1FBC, 'M', 'αι'), - (0x1FBD, '3', ' ̓'), - (0x1FBE, 'M', 'ι'), - (0x1FBF, '3', ' ̓'), - (0x1FC0, '3', ' ͂'), - (0x1FC1, '3', ' ̈͂'), - (0x1FC2, 'M', 'ὴι'), - (0x1FC3, 'M', 'ηι'), - (0x1FC4, 'M', 'ήι'), - (0x1FC5, 'X'), - (0x1FC6, 'V'), - (0x1FC7, 'M', 'ῆι'), - (0x1FC8, 'M', 'ὲ'), - (0x1FC9, 'M', 'έ'), - (0x1FCA, 'M', 'ὴ'), - (0x1FCB, 'M', 'ή'), - (0x1FCC, 'M', 'ηι'), - (0x1FCD, '3', ' ̓̀'), - (0x1FCE, '3', ' ̓́'), - (0x1FCF, '3', ' ̓͂'), - (0x1FD0, 'V'), - (0x1FD3, 'M', 'ΐ'), - (0x1FD4, 'X'), - (0x1FD6, 'V'), - (0x1FD8, 'M', 'ῐ'), - (0x1FD9, 'M', 'ῑ'), - (0x1FDA, 'M', 'ὶ'), - (0x1FDB, 'M', 'ί'), - (0x1FDC, 'X'), - (0x1FDD, '3', ' ̔̀'), - (0x1FDE, '3', ' ̔́'), - (0x1FDF, '3', ' ̔͂'), - (0x1FE0, 'V'), - (0x1FE3, 'M', 'ΰ'), - (0x1FE4, 'V'), - (0x1FE8, 'M', 'ῠ'), - (0x1FE9, 'M', 'ῡ'), - (0x1FEA, 'M', 'ὺ'), - (0x1FEB, 'M', 'ύ'), - (0x1FEC, 'M', 'ῥ'), - (0x1FED, '3', ' ̈̀'), - (0x1FEE, '3', ' ̈́'), - (0x1FEF, '3', '`'), - (0x1FF0, 'X'), - (0x1FF2, 'M', 'ὼι'), - (0x1FF3, 'M', 'ωι'), - (0x1FF4, 'M', 'ώι'), - (0x1FF5, 'X'), - (0x1FF6, 'V'), + (0x1F88, "M", "ἀι"), + (0x1F89, "M", "ἁι"), + (0x1F8A, "M", "ἂι"), + (0x1F8B, "M", "ἃι"), + (0x1F8C, "M", "ἄι"), + (0x1F8D, "M", "ἅι"), + (0x1F8E, "M", "ἆι"), + (0x1F8F, "M", "ἇι"), + (0x1F90, "M", "ἠι"), + (0x1F91, "M", "ἡι"), + (0x1F92, "M", "ἢι"), + (0x1F93, "M", "ἣι"), + (0x1F94, "M", "ἤι"), + (0x1F95, "M", "ἥι"), + (0x1F96, "M", "ἦι"), + (0x1F97, "M", "ἧι"), + (0x1F98, "M", "ἠι"), + (0x1F99, "M", "ἡι"), + (0x1F9A, "M", "ἢι"), + (0x1F9B, "M", "ἣι"), + (0x1F9C, "M", "ἤι"), + (0x1F9D, "M", "ἥι"), + (0x1F9E, "M", "ἦι"), + (0x1F9F, "M", "ἧι"), + (0x1FA0, "M", "ὠι"), + (0x1FA1, "M", "ὡι"), + (0x1FA2, "M", "ὢι"), + (0x1FA3, "M", "ὣι"), + (0x1FA4, "M", "ὤι"), + (0x1FA5, "M", "ὥι"), + (0x1FA6, "M", "ὦι"), + (0x1FA7, "M", "ὧι"), + (0x1FA8, "M", "ὠι"), + (0x1FA9, "M", "ὡι"), + (0x1FAA, "M", "ὢι"), + (0x1FAB, "M", "ὣι"), + (0x1FAC, "M", "ὤι"), + (0x1FAD, "M", "ὥι"), + (0x1FAE, "M", "ὦι"), + (0x1FAF, "M", "ὧι"), + (0x1FB0, "V"), + (0x1FB2, "M", "ὰι"), + (0x1FB3, "M", "αι"), + (0x1FB4, "M", "άι"), + (0x1FB5, "X"), + (0x1FB6, "V"), + (0x1FB7, "M", "ᾶι"), + (0x1FB8, "M", "ᾰ"), + (0x1FB9, "M", "ᾱ"), + (0x1FBA, "M", "ὰ"), + (0x1FBB, "M", "ά"), + (0x1FBC, "M", "αι"), + (0x1FBD, "3", " ̓"), + (0x1FBE, "M", "ι"), + (0x1FBF, "3", " ̓"), + (0x1FC0, "3", " ͂"), + (0x1FC1, "3", " ̈͂"), + (0x1FC2, "M", "ὴι"), + (0x1FC3, "M", "ηι"), + (0x1FC4, "M", "ήι"), + (0x1FC5, "X"), + (0x1FC6, "V"), + (0x1FC7, "M", "ῆι"), + (0x1FC8, "M", "ὲ"), + (0x1FC9, "M", "έ"), + (0x1FCA, "M", "ὴ"), + (0x1FCB, "M", "ή"), + (0x1FCC, "M", "ηι"), + (0x1FCD, "3", " ̓̀"), + (0x1FCE, "3", " ̓́"), + (0x1FCF, "3", " ̓͂"), + (0x1FD0, "V"), + (0x1FD3, "M", "ΐ"), + (0x1FD4, "X"), + (0x1FD6, "V"), + (0x1FD8, "M", "ῐ"), + (0x1FD9, "M", "ῑ"), + (0x1FDA, "M", "ὶ"), + (0x1FDB, "M", "ί"), + (0x1FDC, "X"), + (0x1FDD, "3", " ̔̀"), + (0x1FDE, "3", " ̔́"), + (0x1FDF, "3", " ̔͂"), + (0x1FE0, "V"), + (0x1FE3, "M", "ΰ"), + (0x1FE4, "V"), + (0x1FE8, "M", "ῠ"), + (0x1FE9, "M", "ῡ"), + (0x1FEA, "M", "ὺ"), + (0x1FEB, "M", "ύ"), + (0x1FEC, "M", "ῥ"), + (0x1FED, "3", " ̈̀"), + (0x1FEE, "3", " ̈́"), + (0x1FEF, "3", "`"), + (0x1FF0, "X"), + (0x1FF2, "M", "ὼι"), + (0x1FF3, "M", "ωι"), + (0x1FF4, "M", "ώι"), + (0x1FF5, "X"), + (0x1FF6, "V"), ] + def _seg_21() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1FF7, 'M', 'ῶι'), - (0x1FF8, 'M', 'ὸ'), - (0x1FF9, 'M', 'ό'), - (0x1FFA, 'M', 'ὼ'), - (0x1FFB, 'M', 'ώ'), - (0x1FFC, 'M', 'ωι'), - (0x1FFD, '3', ' ́'), - (0x1FFE, '3', ' ̔'), - (0x1FFF, 'X'), - (0x2000, '3', ' '), - (0x200B, 'I'), - (0x200C, 'D', ''), - (0x200E, 'X'), - (0x2010, 'V'), - (0x2011, 'M', '‐'), - (0x2012, 'V'), - (0x2017, '3', ' ̳'), - (0x2018, 'V'), - (0x2024, 'X'), - (0x2027, 'V'), - (0x2028, 'X'), - (0x202F, '3', ' '), - (0x2030, 'V'), - (0x2033, 'M', '′′'), - (0x2034, 'M', '′′′'), - (0x2035, 'V'), - (0x2036, 'M', '‵‵'), - (0x2037, 'M', '‵‵‵'), - (0x2038, 'V'), - (0x203C, '3', '!!'), - (0x203D, 'V'), - (0x203E, '3', ' ̅'), - (0x203F, 'V'), - (0x2047, '3', '??'), - (0x2048, '3', '?!'), - (0x2049, '3', '!?'), - (0x204A, 'V'), - (0x2057, 'M', '′′′′'), - (0x2058, 'V'), - (0x205F, '3', ' '), - (0x2060, 'I'), - (0x2061, 'X'), - (0x2064, 'I'), - (0x2065, 'X'), - (0x2070, 'M', '0'), - (0x2071, 'M', 'i'), - (0x2072, 'X'), - (0x2074, 'M', '4'), - (0x2075, 'M', '5'), - (0x2076, 'M', '6'), - (0x2077, 'M', '7'), - (0x2078, 'M', '8'), - (0x2079, 'M', '9'), - (0x207A, '3', '+'), - (0x207B, 'M', '−'), - (0x207C, '3', '='), - (0x207D, '3', '('), - (0x207E, '3', ')'), - (0x207F, 'M', 'n'), - (0x2080, 'M', '0'), - (0x2081, 'M', '1'), - (0x2082, 'M', '2'), - (0x2083, 'M', '3'), - (0x2084, 'M', '4'), - (0x2085, 'M', '5'), - (0x2086, 'M', '6'), - (0x2087, 'M', '7'), - (0x2088, 'M', '8'), - (0x2089, 'M', '9'), - (0x208A, '3', '+'), - (0x208B, 'M', '−'), - (0x208C, '3', '='), - (0x208D, '3', '('), - (0x208E, '3', ')'), - (0x208F, 'X'), - (0x2090, 'M', 'a'), - (0x2091, 'M', 'e'), - (0x2092, 'M', 'o'), - (0x2093, 'M', 'x'), - (0x2094, 'M', 'ə'), - (0x2095, 'M', 'h'), - (0x2096, 'M', 'k'), - (0x2097, 'M', 'l'), - (0x2098, 'M', 'm'), - (0x2099, 'M', 'n'), - (0x209A, 'M', 'p'), - (0x209B, 'M', 's'), - (0x209C, 'M', 't'), - (0x209D, 'X'), - (0x20A0, 'V'), - (0x20A8, 'M', 'rs'), - (0x20A9, 'V'), - (0x20C1, 'X'), - (0x20D0, 'V'), - (0x20F1, 'X'), - (0x2100, '3', 'a/c'), - (0x2101, '3', 'a/s'), - (0x2102, 'M', 'c'), - (0x2103, 'M', '°c'), - (0x2104, 'V'), + (0x1FF7, "M", "ῶι"), + (0x1FF8, "M", "ὸ"), + (0x1FF9, "M", "ό"), + (0x1FFA, "M", "ὼ"), + (0x1FFB, "M", "ώ"), + (0x1FFC, "M", "ωι"), + (0x1FFD, "3", " ́"), + (0x1FFE, "3", " ̔"), + (0x1FFF, "X"), + (0x2000, "3", " "), + (0x200B, "I"), + (0x200C, "D", ""), + (0x200E, "X"), + (0x2010, "V"), + (0x2011, "M", "‐"), + (0x2012, "V"), + (0x2017, "3", " ̳"), + (0x2018, "V"), + (0x2024, "X"), + (0x2027, "V"), + (0x2028, "X"), + (0x202F, "3", " "), + (0x2030, "V"), + (0x2033, "M", "′′"), + (0x2034, "M", "′′′"), + (0x2035, "V"), + (0x2036, "M", "‵‵"), + (0x2037, "M", "‵‵‵"), + (0x2038, "V"), + (0x203C, "3", "!!"), + (0x203D, "V"), + (0x203E, "3", " ̅"), + (0x203F, "V"), + (0x2047, "3", "??"), + (0x2048, "3", "?!"), + (0x2049, "3", "!?"), + (0x204A, "V"), + (0x2057, "M", "′′′′"), + (0x2058, "V"), + (0x205F, "3", " "), + (0x2060, "I"), + (0x2061, "X"), + (0x2064, "I"), + (0x2065, "X"), + (0x2070, "M", "0"), + (0x2071, "M", "i"), + (0x2072, "X"), + (0x2074, "M", "4"), + (0x2075, "M", "5"), + (0x2076, "M", "6"), + (0x2077, "M", "7"), + (0x2078, "M", "8"), + (0x2079, "M", "9"), + (0x207A, "3", "+"), + (0x207B, "M", "−"), + (0x207C, "3", "="), + (0x207D, "3", "("), + (0x207E, "3", ")"), + (0x207F, "M", "n"), + (0x2080, "M", "0"), + (0x2081, "M", "1"), + (0x2082, "M", "2"), + (0x2083, "M", "3"), + (0x2084, "M", "4"), + (0x2085, "M", "5"), + (0x2086, "M", "6"), + (0x2087, "M", "7"), + (0x2088, "M", "8"), + (0x2089, "M", "9"), + (0x208A, "3", "+"), + (0x208B, "M", "−"), + (0x208C, "3", "="), + (0x208D, "3", "("), + (0x208E, "3", ")"), + (0x208F, "X"), + (0x2090, "M", "a"), + (0x2091, "M", "e"), + (0x2092, "M", "o"), + (0x2093, "M", "x"), + (0x2094, "M", "ə"), + (0x2095, "M", "h"), + (0x2096, "M", "k"), + (0x2097, "M", "l"), + (0x2098, "M", "m"), + (0x2099, "M", "n"), + (0x209A, "M", "p"), + (0x209B, "M", "s"), + (0x209C, "M", "t"), + (0x209D, "X"), + (0x20A0, "V"), + (0x20A8, "M", "rs"), + (0x20A9, "V"), + (0x20C1, "X"), + (0x20D0, "V"), + (0x20F1, "X"), + (0x2100, "3", "a/c"), + (0x2101, "3", "a/s"), + (0x2102, "M", "c"), + (0x2103, "M", "°c"), + (0x2104, "V"), ] + def _seg_22() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2105, '3', 'c/o'), - (0x2106, '3', 'c/u'), - (0x2107, 'M', 'ɛ'), - (0x2108, 'V'), - (0x2109, 'M', '°f'), - (0x210A, 'M', 'g'), - (0x210B, 'M', 'h'), - (0x210F, 'M', 'ħ'), - (0x2110, 'M', 'i'), - (0x2112, 'M', 'l'), - (0x2114, 'V'), - (0x2115, 'M', 'n'), - (0x2116, 'M', 'no'), - (0x2117, 'V'), - (0x2119, 'M', 'p'), - (0x211A, 'M', 'q'), - (0x211B, 'M', 'r'), - (0x211E, 'V'), - (0x2120, 'M', 'sm'), - (0x2121, 'M', 'tel'), - (0x2122, 'M', 'tm'), - (0x2123, 'V'), - (0x2124, 'M', 'z'), - (0x2125, 'V'), - (0x2126, 'M', 'ω'), - (0x2127, 'V'), - (0x2128, 'M', 'z'), - (0x2129, 'V'), - (0x212A, 'M', 'k'), - (0x212B, 'M', 'å'), - (0x212C, 'M', 'b'), - (0x212D, 'M', 'c'), - (0x212E, 'V'), - (0x212F, 'M', 'e'), - (0x2131, 'M', 'f'), - (0x2132, 'X'), - (0x2133, 'M', 'm'), - (0x2134, 'M', 'o'), - (0x2135, 'M', 'א'), - (0x2136, 'M', 'ב'), - (0x2137, 'M', 'ג'), - (0x2138, 'M', 'ד'), - (0x2139, 'M', 'i'), - (0x213A, 'V'), - (0x213B, 'M', 'fax'), - (0x213C, 'M', 'π'), - (0x213D, 'M', 'γ'), - (0x213F, 'M', 'π'), - (0x2140, 'M', '∑'), - (0x2141, 'V'), - (0x2145, 'M', 'd'), - (0x2147, 'M', 'e'), - (0x2148, 'M', 'i'), - (0x2149, 'M', 'j'), - (0x214A, 'V'), - (0x2150, 'M', '1⁄7'), - (0x2151, 'M', '1⁄9'), - (0x2152, 'M', '1⁄10'), - (0x2153, 'M', '1⁄3'), - (0x2154, 'M', '2⁄3'), - (0x2155, 'M', '1⁄5'), - (0x2156, 'M', '2⁄5'), - (0x2157, 'M', '3⁄5'), - (0x2158, 'M', '4⁄5'), - (0x2159, 'M', '1⁄6'), - (0x215A, 'M', '5⁄6'), - (0x215B, 'M', '1⁄8'), - (0x215C, 'M', '3⁄8'), - (0x215D, 'M', '5⁄8'), - (0x215E, 'M', '7⁄8'), - (0x215F, 'M', '1⁄'), - (0x2160, 'M', 'i'), - (0x2161, 'M', 'ii'), - (0x2162, 'M', 'iii'), - (0x2163, 'M', 'iv'), - (0x2164, 'M', 'v'), - (0x2165, 'M', 'vi'), - (0x2166, 'M', 'vii'), - (0x2167, 'M', 'viii'), - (0x2168, 'M', 'ix'), - (0x2169, 'M', 'x'), - (0x216A, 'M', 'xi'), - (0x216B, 'M', 'xii'), - (0x216C, 'M', 'l'), - (0x216D, 'M', 'c'), - (0x216E, 'M', 'd'), - (0x216F, 'M', 'm'), - (0x2170, 'M', 'i'), - (0x2171, 'M', 'ii'), - (0x2172, 'M', 'iii'), - (0x2173, 'M', 'iv'), - (0x2174, 'M', 'v'), - (0x2175, 'M', 'vi'), - (0x2176, 'M', 'vii'), - (0x2177, 'M', 'viii'), - (0x2178, 'M', 'ix'), - (0x2179, 'M', 'x'), - (0x217A, 'M', 'xi'), - (0x217B, 'M', 'xii'), - (0x217C, 'M', 'l'), + (0x2105, "3", "c/o"), + (0x2106, "3", "c/u"), + (0x2107, "M", "ɛ"), + (0x2108, "V"), + (0x2109, "M", "°f"), + (0x210A, "M", "g"), + (0x210B, "M", "h"), + (0x210F, "M", "ħ"), + (0x2110, "M", "i"), + (0x2112, "M", "l"), + (0x2114, "V"), + (0x2115, "M", "n"), + (0x2116, "M", "no"), + (0x2117, "V"), + (0x2119, "M", "p"), + (0x211A, "M", "q"), + (0x211B, "M", "r"), + (0x211E, "V"), + (0x2120, "M", "sm"), + (0x2121, "M", "tel"), + (0x2122, "M", "tm"), + (0x2123, "V"), + (0x2124, "M", "z"), + (0x2125, "V"), + (0x2126, "M", "ω"), + (0x2127, "V"), + (0x2128, "M", "z"), + (0x2129, "V"), + (0x212A, "M", "k"), + (0x212B, "M", "å"), + (0x212C, "M", "b"), + (0x212D, "M", "c"), + (0x212E, "V"), + (0x212F, "M", "e"), + (0x2131, "M", "f"), + (0x2132, "X"), + (0x2133, "M", "m"), + (0x2134, "M", "o"), + (0x2135, "M", "א"), + (0x2136, "M", "ב"), + (0x2137, "M", "ג"), + (0x2138, "M", "ד"), + (0x2139, "M", "i"), + (0x213A, "V"), + (0x213B, "M", "fax"), + (0x213C, "M", "π"), + (0x213D, "M", "γ"), + (0x213F, "M", "π"), + (0x2140, "M", "∑"), + (0x2141, "V"), + (0x2145, "M", "d"), + (0x2147, "M", "e"), + (0x2148, "M", "i"), + (0x2149, "M", "j"), + (0x214A, "V"), + (0x2150, "M", "1⁄7"), + (0x2151, "M", "1⁄9"), + (0x2152, "M", "1⁄10"), + (0x2153, "M", "1⁄3"), + (0x2154, "M", "2⁄3"), + (0x2155, "M", "1⁄5"), + (0x2156, "M", "2⁄5"), + (0x2157, "M", "3⁄5"), + (0x2158, "M", "4⁄5"), + (0x2159, "M", "1⁄6"), + (0x215A, "M", "5⁄6"), + (0x215B, "M", "1⁄8"), + (0x215C, "M", "3⁄8"), + (0x215D, "M", "5⁄8"), + (0x215E, "M", "7⁄8"), + (0x215F, "M", "1⁄"), + (0x2160, "M", "i"), + (0x2161, "M", "ii"), + (0x2162, "M", "iii"), + (0x2163, "M", "iv"), + (0x2164, "M", "v"), + (0x2165, "M", "vi"), + (0x2166, "M", "vii"), + (0x2167, "M", "viii"), + (0x2168, "M", "ix"), + (0x2169, "M", "x"), + (0x216A, "M", "xi"), + (0x216B, "M", "xii"), + (0x216C, "M", "l"), + (0x216D, "M", "c"), + (0x216E, "M", "d"), + (0x216F, "M", "m"), + (0x2170, "M", "i"), + (0x2171, "M", "ii"), + (0x2172, "M", "iii"), + (0x2173, "M", "iv"), + (0x2174, "M", "v"), + (0x2175, "M", "vi"), + (0x2176, "M", "vii"), + (0x2177, "M", "viii"), + (0x2178, "M", "ix"), + (0x2179, "M", "x"), + (0x217A, "M", "xi"), + (0x217B, "M", "xii"), + (0x217C, "M", "l"), ] + def _seg_23() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x217D, 'M', 'c'), - (0x217E, 'M', 'd'), - (0x217F, 'M', 'm'), - (0x2180, 'V'), - (0x2183, 'X'), - (0x2184, 'V'), - (0x2189, 'M', '0⁄3'), - (0x218A, 'V'), - (0x218C, 'X'), - (0x2190, 'V'), - (0x222C, 'M', '∫∫'), - (0x222D, 'M', '∫∫∫'), - (0x222E, 'V'), - (0x222F, 'M', '∮∮'), - (0x2230, 'M', '∮∮∮'), - (0x2231, 'V'), - (0x2260, '3'), - (0x2261, 'V'), - (0x226E, '3'), - (0x2270, 'V'), - (0x2329, 'M', '〈'), - (0x232A, 'M', '〉'), - (0x232B, 'V'), - (0x2427, 'X'), - (0x2440, 'V'), - (0x244B, 'X'), - (0x2460, 'M', '1'), - (0x2461, 'M', '2'), - (0x2462, 'M', '3'), - (0x2463, 'M', '4'), - (0x2464, 'M', '5'), - (0x2465, 'M', '6'), - (0x2466, 'M', '7'), - (0x2467, 'M', '8'), - (0x2468, 'M', '9'), - (0x2469, 'M', '10'), - (0x246A, 'M', '11'), - (0x246B, 'M', '12'), - (0x246C, 'M', '13'), - (0x246D, 'M', '14'), - (0x246E, 'M', '15'), - (0x246F, 'M', '16'), - (0x2470, 'M', '17'), - (0x2471, 'M', '18'), - (0x2472, 'M', '19'), - (0x2473, 'M', '20'), - (0x2474, '3', '(1)'), - (0x2475, '3', '(2)'), - (0x2476, '3', '(3)'), - (0x2477, '3', '(4)'), - (0x2478, '3', '(5)'), - (0x2479, '3', '(6)'), - (0x247A, '3', '(7)'), - (0x247B, '3', '(8)'), - (0x247C, '3', '(9)'), - (0x247D, '3', '(10)'), - (0x247E, '3', '(11)'), - (0x247F, '3', '(12)'), - (0x2480, '3', '(13)'), - (0x2481, '3', '(14)'), - (0x2482, '3', '(15)'), - (0x2483, '3', '(16)'), - (0x2484, '3', '(17)'), - (0x2485, '3', '(18)'), - (0x2486, '3', '(19)'), - (0x2487, '3', '(20)'), - (0x2488, 'X'), - (0x249C, '3', '(a)'), - (0x249D, '3', '(b)'), - (0x249E, '3', '(c)'), - (0x249F, '3', '(d)'), - (0x24A0, '3', '(e)'), - (0x24A1, '3', '(f)'), - (0x24A2, '3', '(g)'), - (0x24A3, '3', '(h)'), - (0x24A4, '3', '(i)'), - (0x24A5, '3', '(j)'), - (0x24A6, '3', '(k)'), - (0x24A7, '3', '(l)'), - (0x24A8, '3', '(m)'), - (0x24A9, '3', '(n)'), - (0x24AA, '3', '(o)'), - (0x24AB, '3', '(p)'), - (0x24AC, '3', '(q)'), - (0x24AD, '3', '(r)'), - (0x24AE, '3', '(s)'), - (0x24AF, '3', '(t)'), - (0x24B0, '3', '(u)'), - (0x24B1, '3', '(v)'), - (0x24B2, '3', '(w)'), - (0x24B3, '3', '(x)'), - (0x24B4, '3', '(y)'), - (0x24B5, '3', '(z)'), - (0x24B6, 'M', 'a'), - (0x24B7, 'M', 'b'), - (0x24B8, 'M', 'c'), - (0x24B9, 'M', 'd'), - (0x24BA, 'M', 'e'), - (0x24BB, 'M', 'f'), - (0x24BC, 'M', 'g'), + (0x217D, "M", "c"), + (0x217E, "M", "d"), + (0x217F, "M", "m"), + (0x2180, "V"), + (0x2183, "X"), + (0x2184, "V"), + (0x2189, "M", "0⁄3"), + (0x218A, "V"), + (0x218C, "X"), + (0x2190, "V"), + (0x222C, "M", "∫∫"), + (0x222D, "M", "∫∫∫"), + (0x222E, "V"), + (0x222F, "M", "∮∮"), + (0x2230, "M", "∮∮∮"), + (0x2231, "V"), + (0x2329, "M", "〈"), + (0x232A, "M", "〉"), + (0x232B, "V"), + (0x2427, "X"), + (0x2440, "V"), + (0x244B, "X"), + (0x2460, "M", "1"), + (0x2461, "M", "2"), + (0x2462, "M", "3"), + (0x2463, "M", "4"), + (0x2464, "M", "5"), + (0x2465, "M", "6"), + (0x2466, "M", "7"), + (0x2467, "M", "8"), + (0x2468, "M", "9"), + (0x2469, "M", "10"), + (0x246A, "M", "11"), + (0x246B, "M", "12"), + (0x246C, "M", "13"), + (0x246D, "M", "14"), + (0x246E, "M", "15"), + (0x246F, "M", "16"), + (0x2470, "M", "17"), + (0x2471, "M", "18"), + (0x2472, "M", "19"), + (0x2473, "M", "20"), + (0x2474, "3", "(1)"), + (0x2475, "3", "(2)"), + (0x2476, "3", "(3)"), + (0x2477, "3", "(4)"), + (0x2478, "3", "(5)"), + (0x2479, "3", "(6)"), + (0x247A, "3", "(7)"), + (0x247B, "3", "(8)"), + (0x247C, "3", "(9)"), + (0x247D, "3", "(10)"), + (0x247E, "3", "(11)"), + (0x247F, "3", "(12)"), + (0x2480, "3", "(13)"), + (0x2481, "3", "(14)"), + (0x2482, "3", "(15)"), + (0x2483, "3", "(16)"), + (0x2484, "3", "(17)"), + (0x2485, "3", "(18)"), + (0x2486, "3", "(19)"), + (0x2487, "3", "(20)"), + (0x2488, "X"), + (0x249C, "3", "(a)"), + (0x249D, "3", "(b)"), + (0x249E, "3", "(c)"), + (0x249F, "3", "(d)"), + (0x24A0, "3", "(e)"), + (0x24A1, "3", "(f)"), + (0x24A2, "3", "(g)"), + (0x24A3, "3", "(h)"), + (0x24A4, "3", "(i)"), + (0x24A5, "3", "(j)"), + (0x24A6, "3", "(k)"), + (0x24A7, "3", "(l)"), + (0x24A8, "3", "(m)"), + (0x24A9, "3", "(n)"), + (0x24AA, "3", "(o)"), + (0x24AB, "3", "(p)"), + (0x24AC, "3", "(q)"), + (0x24AD, "3", "(r)"), + (0x24AE, "3", "(s)"), + (0x24AF, "3", "(t)"), + (0x24B0, "3", "(u)"), + (0x24B1, "3", "(v)"), + (0x24B2, "3", "(w)"), + (0x24B3, "3", "(x)"), + (0x24B4, "3", "(y)"), + (0x24B5, "3", "(z)"), + (0x24B6, "M", "a"), + (0x24B7, "M", "b"), + (0x24B8, "M", "c"), + (0x24B9, "M", "d"), + (0x24BA, "M", "e"), + (0x24BB, "M", "f"), + (0x24BC, "M", "g"), + (0x24BD, "M", "h"), + (0x24BE, "M", "i"), + (0x24BF, "M", "j"), + (0x24C0, "M", "k"), ] + def _seg_24() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x24BD, 'M', 'h'), - (0x24BE, 'M', 'i'), - (0x24BF, 'M', 'j'), - (0x24C0, 'M', 'k'), - (0x24C1, 'M', 'l'), - (0x24C2, 'M', 'm'), - (0x24C3, 'M', 'n'), - (0x24C4, 'M', 'o'), - (0x24C5, 'M', 'p'), - (0x24C6, 'M', 'q'), - (0x24C7, 'M', 'r'), - (0x24C8, 'M', 's'), - (0x24C9, 'M', 't'), - (0x24CA, 'M', 'u'), - (0x24CB, 'M', 'v'), - (0x24CC, 'M', 'w'), - (0x24CD, 'M', 'x'), - (0x24CE, 'M', 'y'), - (0x24CF, 'M', 'z'), - (0x24D0, 'M', 'a'), - (0x24D1, 'M', 'b'), - (0x24D2, 'M', 'c'), - (0x24D3, 'M', 'd'), - (0x24D4, 'M', 'e'), - (0x24D5, 'M', 'f'), - (0x24D6, 'M', 'g'), - (0x24D7, 'M', 'h'), - (0x24D8, 'M', 'i'), - (0x24D9, 'M', 'j'), - (0x24DA, 'M', 'k'), - (0x24DB, 'M', 'l'), - (0x24DC, 'M', 'm'), - (0x24DD, 'M', 'n'), - (0x24DE, 'M', 'o'), - (0x24DF, 'M', 'p'), - (0x24E0, 'M', 'q'), - (0x24E1, 'M', 'r'), - (0x24E2, 'M', 's'), - (0x24E3, 'M', 't'), - (0x24E4, 'M', 'u'), - (0x24E5, 'M', 'v'), - (0x24E6, 'M', 'w'), - (0x24E7, 'M', 'x'), - (0x24E8, 'M', 'y'), - (0x24E9, 'M', 'z'), - (0x24EA, 'M', '0'), - (0x24EB, 'V'), - (0x2A0C, 'M', '∫∫∫∫'), - (0x2A0D, 'V'), - (0x2A74, '3', '::='), - (0x2A75, '3', '=='), - (0x2A76, '3', '==='), - (0x2A77, 'V'), - (0x2ADC, 'M', '⫝̸'), - (0x2ADD, 'V'), - (0x2B74, 'X'), - (0x2B76, 'V'), - (0x2B96, 'X'), - (0x2B97, 'V'), - (0x2C00, 'M', 'ⰰ'), - (0x2C01, 'M', 'ⰱ'), - (0x2C02, 'M', 'ⰲ'), - (0x2C03, 'M', 'ⰳ'), - (0x2C04, 'M', 'ⰴ'), - (0x2C05, 'M', 'ⰵ'), - (0x2C06, 'M', 'ⰶ'), - (0x2C07, 'M', 'ⰷ'), - (0x2C08, 'M', 'ⰸ'), - (0x2C09, 'M', 'ⰹ'), - (0x2C0A, 'M', 'ⰺ'), - (0x2C0B, 'M', 'ⰻ'), - (0x2C0C, 'M', 'ⰼ'), - (0x2C0D, 'M', 'ⰽ'), - (0x2C0E, 'M', 'ⰾ'), - (0x2C0F, 'M', 'ⰿ'), - (0x2C10, 'M', 'ⱀ'), - (0x2C11, 'M', 'ⱁ'), - (0x2C12, 'M', 'ⱂ'), - (0x2C13, 'M', 'ⱃ'), - (0x2C14, 'M', 'ⱄ'), - (0x2C15, 'M', 'ⱅ'), - (0x2C16, 'M', 'ⱆ'), - (0x2C17, 'M', 'ⱇ'), - (0x2C18, 'M', 'ⱈ'), - (0x2C19, 'M', 'ⱉ'), - (0x2C1A, 'M', 'ⱊ'), - (0x2C1B, 'M', 'ⱋ'), - (0x2C1C, 'M', 'ⱌ'), - (0x2C1D, 'M', 'ⱍ'), - (0x2C1E, 'M', 'ⱎ'), - (0x2C1F, 'M', 'ⱏ'), - (0x2C20, 'M', 'ⱐ'), - (0x2C21, 'M', 'ⱑ'), - (0x2C22, 'M', 'ⱒ'), - (0x2C23, 'M', 'ⱓ'), - (0x2C24, 'M', 'ⱔ'), - (0x2C25, 'M', 'ⱕ'), - (0x2C26, 'M', 'ⱖ'), - (0x2C27, 'M', 'ⱗ'), - (0x2C28, 'M', 'ⱘ'), + (0x24C1, "M", "l"), + (0x24C2, "M", "m"), + (0x24C3, "M", "n"), + (0x24C4, "M", "o"), + (0x24C5, "M", "p"), + (0x24C6, "M", "q"), + (0x24C7, "M", "r"), + (0x24C8, "M", "s"), + (0x24C9, "M", "t"), + (0x24CA, "M", "u"), + (0x24CB, "M", "v"), + (0x24CC, "M", "w"), + (0x24CD, "M", "x"), + (0x24CE, "M", "y"), + (0x24CF, "M", "z"), + (0x24D0, "M", "a"), + (0x24D1, "M", "b"), + (0x24D2, "M", "c"), + (0x24D3, "M", "d"), + (0x24D4, "M", "e"), + (0x24D5, "M", "f"), + (0x24D6, "M", "g"), + (0x24D7, "M", "h"), + (0x24D8, "M", "i"), + (0x24D9, "M", "j"), + (0x24DA, "M", "k"), + (0x24DB, "M", "l"), + (0x24DC, "M", "m"), + (0x24DD, "M", "n"), + (0x24DE, "M", "o"), + (0x24DF, "M", "p"), + (0x24E0, "M", "q"), + (0x24E1, "M", "r"), + (0x24E2, "M", "s"), + (0x24E3, "M", "t"), + (0x24E4, "M", "u"), + (0x24E5, "M", "v"), + (0x24E6, "M", "w"), + (0x24E7, "M", "x"), + (0x24E8, "M", "y"), + (0x24E9, "M", "z"), + (0x24EA, "M", "0"), + (0x24EB, "V"), + (0x2A0C, "M", "∫∫∫∫"), + (0x2A0D, "V"), + (0x2A74, "3", "::="), + (0x2A75, "3", "=="), + (0x2A76, "3", "==="), + (0x2A77, "V"), + (0x2ADC, "M", "⫝̸"), + (0x2ADD, "V"), + (0x2B74, "X"), + (0x2B76, "V"), + (0x2B96, "X"), + (0x2B97, "V"), + (0x2C00, "M", "ⰰ"), + (0x2C01, "M", "ⰱ"), + (0x2C02, "M", "ⰲ"), + (0x2C03, "M", "ⰳ"), + (0x2C04, "M", "ⰴ"), + (0x2C05, "M", "ⰵ"), + (0x2C06, "M", "ⰶ"), + (0x2C07, "M", "ⰷ"), + (0x2C08, "M", "ⰸ"), + (0x2C09, "M", "ⰹ"), + (0x2C0A, "M", "ⰺ"), + (0x2C0B, "M", "ⰻ"), + (0x2C0C, "M", "ⰼ"), + (0x2C0D, "M", "ⰽ"), + (0x2C0E, "M", "ⰾ"), + (0x2C0F, "M", "ⰿ"), + (0x2C10, "M", "ⱀ"), + (0x2C11, "M", "ⱁ"), + (0x2C12, "M", "ⱂ"), + (0x2C13, "M", "ⱃ"), + (0x2C14, "M", "ⱄ"), + (0x2C15, "M", "ⱅ"), + (0x2C16, "M", "ⱆ"), + (0x2C17, "M", "ⱇ"), + (0x2C18, "M", "ⱈ"), + (0x2C19, "M", "ⱉ"), + (0x2C1A, "M", "ⱊ"), + (0x2C1B, "M", "ⱋ"), + (0x2C1C, "M", "ⱌ"), + (0x2C1D, "M", "ⱍ"), + (0x2C1E, "M", "ⱎ"), + (0x2C1F, "M", "ⱏ"), + (0x2C20, "M", "ⱐ"), + (0x2C21, "M", "ⱑ"), + (0x2C22, "M", "ⱒ"), + (0x2C23, "M", "ⱓ"), + (0x2C24, "M", "ⱔ"), + (0x2C25, "M", "ⱕ"), + (0x2C26, "M", "ⱖ"), + (0x2C27, "M", "ⱗ"), + (0x2C28, "M", "ⱘ"), + (0x2C29, "M", "ⱙ"), + (0x2C2A, "M", "ⱚ"), + (0x2C2B, "M", "ⱛ"), + (0x2C2C, "M", "ⱜ"), ] + def _seg_25() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2C29, 'M', 'ⱙ'), - (0x2C2A, 'M', 'ⱚ'), - (0x2C2B, 'M', 'ⱛ'), - (0x2C2C, 'M', 'ⱜ'), - (0x2C2D, 'M', 'ⱝ'), - (0x2C2E, 'M', 'ⱞ'), - (0x2C2F, 'M', 'ⱟ'), - (0x2C30, 'V'), - (0x2C60, 'M', 'ⱡ'), - (0x2C61, 'V'), - (0x2C62, 'M', 'ɫ'), - (0x2C63, 'M', 'ᵽ'), - (0x2C64, 'M', 'ɽ'), - (0x2C65, 'V'), - (0x2C67, 'M', 'ⱨ'), - (0x2C68, 'V'), - (0x2C69, 'M', 'ⱪ'), - (0x2C6A, 'V'), - (0x2C6B, 'M', 'ⱬ'), - (0x2C6C, 'V'), - (0x2C6D, 'M', 'ɑ'), - (0x2C6E, 'M', 'ɱ'), - (0x2C6F, 'M', 'ɐ'), - (0x2C70, 'M', 'ɒ'), - (0x2C71, 'V'), - (0x2C72, 'M', 'ⱳ'), - (0x2C73, 'V'), - (0x2C75, 'M', 'ⱶ'), - (0x2C76, 'V'), - (0x2C7C, 'M', 'j'), - (0x2C7D, 'M', 'v'), - (0x2C7E, 'M', 'ȿ'), - (0x2C7F, 'M', 'ɀ'), - (0x2C80, 'M', 'ⲁ'), - (0x2C81, 'V'), - (0x2C82, 'M', 'ⲃ'), - (0x2C83, 'V'), - (0x2C84, 'M', 'ⲅ'), - (0x2C85, 'V'), - (0x2C86, 'M', 'ⲇ'), - (0x2C87, 'V'), - (0x2C88, 'M', 'ⲉ'), - (0x2C89, 'V'), - (0x2C8A, 'M', 'ⲋ'), - (0x2C8B, 'V'), - (0x2C8C, 'M', 'ⲍ'), - (0x2C8D, 'V'), - (0x2C8E, 'M', 'ⲏ'), - (0x2C8F, 'V'), - (0x2C90, 'M', 'ⲑ'), - (0x2C91, 'V'), - (0x2C92, 'M', 'ⲓ'), - (0x2C93, 'V'), - (0x2C94, 'M', 'ⲕ'), - (0x2C95, 'V'), - (0x2C96, 'M', 'ⲗ'), - (0x2C97, 'V'), - (0x2C98, 'M', 'ⲙ'), - (0x2C99, 'V'), - (0x2C9A, 'M', 'ⲛ'), - (0x2C9B, 'V'), - (0x2C9C, 'M', 'ⲝ'), - (0x2C9D, 'V'), - (0x2C9E, 'M', 'ⲟ'), - (0x2C9F, 'V'), - (0x2CA0, 'M', 'ⲡ'), - (0x2CA1, 'V'), - (0x2CA2, 'M', 'ⲣ'), - (0x2CA3, 'V'), - (0x2CA4, 'M', 'ⲥ'), - (0x2CA5, 'V'), - (0x2CA6, 'M', 'ⲧ'), - (0x2CA7, 'V'), - (0x2CA8, 'M', 'ⲩ'), - (0x2CA9, 'V'), - (0x2CAA, 'M', 'ⲫ'), - (0x2CAB, 'V'), - (0x2CAC, 'M', 'ⲭ'), - (0x2CAD, 'V'), - (0x2CAE, 'M', 'ⲯ'), - (0x2CAF, 'V'), - (0x2CB0, 'M', 'ⲱ'), - (0x2CB1, 'V'), - (0x2CB2, 'M', 'ⲳ'), - (0x2CB3, 'V'), - (0x2CB4, 'M', 'ⲵ'), - (0x2CB5, 'V'), - (0x2CB6, 'M', 'ⲷ'), - (0x2CB7, 'V'), - (0x2CB8, 'M', 'ⲹ'), - (0x2CB9, 'V'), - (0x2CBA, 'M', 'ⲻ'), - (0x2CBB, 'V'), - (0x2CBC, 'M', 'ⲽ'), - (0x2CBD, 'V'), - (0x2CBE, 'M', 'ⲿ'), - (0x2CBF, 'V'), - (0x2CC0, 'M', 'ⳁ'), - (0x2CC1, 'V'), - (0x2CC2, 'M', 'ⳃ'), + (0x2C2D, "M", "ⱝ"), + (0x2C2E, "M", "ⱞ"), + (0x2C2F, "M", "ⱟ"), + (0x2C30, "V"), + (0x2C60, "M", "ⱡ"), + (0x2C61, "V"), + (0x2C62, "M", "ɫ"), + (0x2C63, "M", "ᵽ"), + (0x2C64, "M", "ɽ"), + (0x2C65, "V"), + (0x2C67, "M", "ⱨ"), + (0x2C68, "V"), + (0x2C69, "M", "ⱪ"), + (0x2C6A, "V"), + (0x2C6B, "M", "ⱬ"), + (0x2C6C, "V"), + (0x2C6D, "M", "ɑ"), + (0x2C6E, "M", "ɱ"), + (0x2C6F, "M", "ɐ"), + (0x2C70, "M", "ɒ"), + (0x2C71, "V"), + (0x2C72, "M", "ⱳ"), + (0x2C73, "V"), + (0x2C75, "M", "ⱶ"), + (0x2C76, "V"), + (0x2C7C, "M", "j"), + (0x2C7D, "M", "v"), + (0x2C7E, "M", "ȿ"), + (0x2C7F, "M", "ɀ"), + (0x2C80, "M", "ⲁ"), + (0x2C81, "V"), + (0x2C82, "M", "ⲃ"), + (0x2C83, "V"), + (0x2C84, "M", "ⲅ"), + (0x2C85, "V"), + (0x2C86, "M", "ⲇ"), + (0x2C87, "V"), + (0x2C88, "M", "ⲉ"), + (0x2C89, "V"), + (0x2C8A, "M", "ⲋ"), + (0x2C8B, "V"), + (0x2C8C, "M", "ⲍ"), + (0x2C8D, "V"), + (0x2C8E, "M", "ⲏ"), + (0x2C8F, "V"), + (0x2C90, "M", "ⲑ"), + (0x2C91, "V"), + (0x2C92, "M", "ⲓ"), + (0x2C93, "V"), + (0x2C94, "M", "ⲕ"), + (0x2C95, "V"), + (0x2C96, "M", "ⲗ"), + (0x2C97, "V"), + (0x2C98, "M", "ⲙ"), + (0x2C99, "V"), + (0x2C9A, "M", "ⲛ"), + (0x2C9B, "V"), + (0x2C9C, "M", "ⲝ"), + (0x2C9D, "V"), + (0x2C9E, "M", "ⲟ"), + (0x2C9F, "V"), + (0x2CA0, "M", "ⲡ"), + (0x2CA1, "V"), + (0x2CA2, "M", "ⲣ"), + (0x2CA3, "V"), + (0x2CA4, "M", "ⲥ"), + (0x2CA5, "V"), + (0x2CA6, "M", "ⲧ"), + (0x2CA7, "V"), + (0x2CA8, "M", "ⲩ"), + (0x2CA9, "V"), + (0x2CAA, "M", "ⲫ"), + (0x2CAB, "V"), + (0x2CAC, "M", "ⲭ"), + (0x2CAD, "V"), + (0x2CAE, "M", "ⲯ"), + (0x2CAF, "V"), + (0x2CB0, "M", "ⲱ"), + (0x2CB1, "V"), + (0x2CB2, "M", "ⲳ"), + (0x2CB3, "V"), + (0x2CB4, "M", "ⲵ"), + (0x2CB5, "V"), + (0x2CB6, "M", "ⲷ"), + (0x2CB7, "V"), + (0x2CB8, "M", "ⲹ"), + (0x2CB9, "V"), + (0x2CBA, "M", "ⲻ"), + (0x2CBB, "V"), + (0x2CBC, "M", "ⲽ"), + (0x2CBD, "V"), + (0x2CBE, "M", "ⲿ"), + (0x2CBF, "V"), + (0x2CC0, "M", "ⳁ"), + (0x2CC1, "V"), + (0x2CC2, "M", "ⳃ"), + (0x2CC3, "V"), + (0x2CC4, "M", "ⳅ"), + (0x2CC5, "V"), + (0x2CC6, "M", "ⳇ"), ] + def _seg_26() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2CC3, 'V'), - (0x2CC4, 'M', 'ⳅ'), - (0x2CC5, 'V'), - (0x2CC6, 'M', 'ⳇ'), - (0x2CC7, 'V'), - (0x2CC8, 'M', 'ⳉ'), - (0x2CC9, 'V'), - (0x2CCA, 'M', 'ⳋ'), - (0x2CCB, 'V'), - (0x2CCC, 'M', 'ⳍ'), - (0x2CCD, 'V'), - (0x2CCE, 'M', 'ⳏ'), - (0x2CCF, 'V'), - (0x2CD0, 'M', 'ⳑ'), - (0x2CD1, 'V'), - (0x2CD2, 'M', 'ⳓ'), - (0x2CD3, 'V'), - (0x2CD4, 'M', 'ⳕ'), - (0x2CD5, 'V'), - (0x2CD6, 'M', 'ⳗ'), - (0x2CD7, 'V'), - (0x2CD8, 'M', 'ⳙ'), - (0x2CD9, 'V'), - (0x2CDA, 'M', 'ⳛ'), - (0x2CDB, 'V'), - (0x2CDC, 'M', 'ⳝ'), - (0x2CDD, 'V'), - (0x2CDE, 'M', 'ⳟ'), - (0x2CDF, 'V'), - (0x2CE0, 'M', 'ⳡ'), - (0x2CE1, 'V'), - (0x2CE2, 'M', 'ⳣ'), - (0x2CE3, 'V'), - (0x2CEB, 'M', 'ⳬ'), - (0x2CEC, 'V'), - (0x2CED, 'M', 'ⳮ'), - (0x2CEE, 'V'), - (0x2CF2, 'M', 'ⳳ'), - (0x2CF3, 'V'), - (0x2CF4, 'X'), - (0x2CF9, 'V'), - (0x2D26, 'X'), - (0x2D27, 'V'), - (0x2D28, 'X'), - (0x2D2D, 'V'), - (0x2D2E, 'X'), - (0x2D30, 'V'), - (0x2D68, 'X'), - (0x2D6F, 'M', 'ⵡ'), - (0x2D70, 'V'), - (0x2D71, 'X'), - (0x2D7F, 'V'), - (0x2D97, 'X'), - (0x2DA0, 'V'), - (0x2DA7, 'X'), - (0x2DA8, 'V'), - (0x2DAF, 'X'), - (0x2DB0, 'V'), - (0x2DB7, 'X'), - (0x2DB8, 'V'), - (0x2DBF, 'X'), - (0x2DC0, 'V'), - (0x2DC7, 'X'), - (0x2DC8, 'V'), - (0x2DCF, 'X'), - (0x2DD0, 'V'), - (0x2DD7, 'X'), - (0x2DD8, 'V'), - (0x2DDF, 'X'), - (0x2DE0, 'V'), - (0x2E5E, 'X'), - (0x2E80, 'V'), - (0x2E9A, 'X'), - (0x2E9B, 'V'), - (0x2E9F, 'M', '母'), - (0x2EA0, 'V'), - (0x2EF3, 'M', '龟'), - (0x2EF4, 'X'), - (0x2F00, 'M', '一'), - (0x2F01, 'M', '丨'), - (0x2F02, 'M', '丶'), - (0x2F03, 'M', '丿'), - (0x2F04, 'M', '乙'), - (0x2F05, 'M', '亅'), - (0x2F06, 'M', '二'), - (0x2F07, 'M', '亠'), - (0x2F08, 'M', '人'), - (0x2F09, 'M', '儿'), - (0x2F0A, 'M', '入'), - (0x2F0B, 'M', '八'), - (0x2F0C, 'M', '冂'), - (0x2F0D, 'M', '冖'), - (0x2F0E, 'M', '冫'), - (0x2F0F, 'M', '几'), - (0x2F10, 'M', '凵'), - (0x2F11, 'M', '刀'), - (0x2F12, 'M', '力'), - (0x2F13, 'M', '勹'), - (0x2F14, 'M', '匕'), - (0x2F15, 'M', '匚'), + (0x2CC7, "V"), + (0x2CC8, "M", "ⳉ"), + (0x2CC9, "V"), + (0x2CCA, "M", "ⳋ"), + (0x2CCB, "V"), + (0x2CCC, "M", "ⳍ"), + (0x2CCD, "V"), + (0x2CCE, "M", "ⳏ"), + (0x2CCF, "V"), + (0x2CD0, "M", "ⳑ"), + (0x2CD1, "V"), + (0x2CD2, "M", "ⳓ"), + (0x2CD3, "V"), + (0x2CD4, "M", "ⳕ"), + (0x2CD5, "V"), + (0x2CD6, "M", "ⳗ"), + (0x2CD7, "V"), + (0x2CD8, "M", "ⳙ"), + (0x2CD9, "V"), + (0x2CDA, "M", "ⳛ"), + (0x2CDB, "V"), + (0x2CDC, "M", "ⳝ"), + (0x2CDD, "V"), + (0x2CDE, "M", "ⳟ"), + (0x2CDF, "V"), + (0x2CE0, "M", "ⳡ"), + (0x2CE1, "V"), + (0x2CE2, "M", "ⳣ"), + (0x2CE3, "V"), + (0x2CEB, "M", "ⳬ"), + (0x2CEC, "V"), + (0x2CED, "M", "ⳮ"), + (0x2CEE, "V"), + (0x2CF2, "M", "ⳳ"), + (0x2CF3, "V"), + (0x2CF4, "X"), + (0x2CF9, "V"), + (0x2D26, "X"), + (0x2D27, "V"), + (0x2D28, "X"), + (0x2D2D, "V"), + (0x2D2E, "X"), + (0x2D30, "V"), + (0x2D68, "X"), + (0x2D6F, "M", "ⵡ"), + (0x2D70, "V"), + (0x2D71, "X"), + (0x2D7F, "V"), + (0x2D97, "X"), + (0x2DA0, "V"), + (0x2DA7, "X"), + (0x2DA8, "V"), + (0x2DAF, "X"), + (0x2DB0, "V"), + (0x2DB7, "X"), + (0x2DB8, "V"), + (0x2DBF, "X"), + (0x2DC0, "V"), + (0x2DC7, "X"), + (0x2DC8, "V"), + (0x2DCF, "X"), + (0x2DD0, "V"), + (0x2DD7, "X"), + (0x2DD8, "V"), + (0x2DDF, "X"), + (0x2DE0, "V"), + (0x2E5E, "X"), + (0x2E80, "V"), + (0x2E9A, "X"), + (0x2E9B, "V"), + (0x2E9F, "M", "母"), + (0x2EA0, "V"), + (0x2EF3, "M", "龟"), + (0x2EF4, "X"), + (0x2F00, "M", "一"), + (0x2F01, "M", "丨"), + (0x2F02, "M", "丶"), + (0x2F03, "M", "丿"), + (0x2F04, "M", "乙"), + (0x2F05, "M", "亅"), + (0x2F06, "M", "二"), + (0x2F07, "M", "亠"), + (0x2F08, "M", "人"), + (0x2F09, "M", "儿"), + (0x2F0A, "M", "入"), + (0x2F0B, "M", "八"), + (0x2F0C, "M", "冂"), + (0x2F0D, "M", "冖"), + (0x2F0E, "M", "冫"), + (0x2F0F, "M", "几"), + (0x2F10, "M", "凵"), + (0x2F11, "M", "刀"), + (0x2F12, "M", "力"), + (0x2F13, "M", "勹"), + (0x2F14, "M", "匕"), + (0x2F15, "M", "匚"), + (0x2F16, "M", "匸"), + (0x2F17, "M", "十"), + (0x2F18, "M", "卜"), + (0x2F19, "M", "卩"), ] + def _seg_27() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2F16, 'M', '匸'), - (0x2F17, 'M', '十'), - (0x2F18, 'M', '卜'), - (0x2F19, 'M', '卩'), - (0x2F1A, 'M', '厂'), - (0x2F1B, 'M', '厶'), - (0x2F1C, 'M', '又'), - (0x2F1D, 'M', '口'), - (0x2F1E, 'M', '囗'), - (0x2F1F, 'M', '土'), - (0x2F20, 'M', '士'), - (0x2F21, 'M', '夂'), - (0x2F22, 'M', '夊'), - (0x2F23, 'M', '夕'), - (0x2F24, 'M', '大'), - (0x2F25, 'M', '女'), - (0x2F26, 'M', '子'), - (0x2F27, 'M', '宀'), - (0x2F28, 'M', '寸'), - (0x2F29, 'M', '小'), - (0x2F2A, 'M', '尢'), - (0x2F2B, 'M', '尸'), - (0x2F2C, 'M', '屮'), - (0x2F2D, 'M', '山'), - (0x2F2E, 'M', '巛'), - (0x2F2F, 'M', '工'), - (0x2F30, 'M', '己'), - (0x2F31, 'M', '巾'), - (0x2F32, 'M', '干'), - (0x2F33, 'M', '幺'), - (0x2F34, 'M', '广'), - (0x2F35, 'M', '廴'), - (0x2F36, 'M', '廾'), - (0x2F37, 'M', '弋'), - (0x2F38, 'M', '弓'), - (0x2F39, 'M', '彐'), - (0x2F3A, 'M', '彡'), - (0x2F3B, 'M', '彳'), - (0x2F3C, 'M', '心'), - (0x2F3D, 'M', '戈'), - (0x2F3E, 'M', '戶'), - (0x2F3F, 'M', '手'), - (0x2F40, 'M', '支'), - (0x2F41, 'M', '攴'), - (0x2F42, 'M', '文'), - (0x2F43, 'M', '斗'), - (0x2F44, 'M', '斤'), - (0x2F45, 'M', '方'), - (0x2F46, 'M', '无'), - (0x2F47, 'M', '日'), - (0x2F48, 'M', '曰'), - (0x2F49, 'M', '月'), - (0x2F4A, 'M', '木'), - (0x2F4B, 'M', '欠'), - (0x2F4C, 'M', '止'), - (0x2F4D, 'M', '歹'), - (0x2F4E, 'M', '殳'), - (0x2F4F, 'M', '毋'), - (0x2F50, 'M', '比'), - (0x2F51, 'M', '毛'), - (0x2F52, 'M', '氏'), - (0x2F53, 'M', '气'), - (0x2F54, 'M', '水'), - (0x2F55, 'M', '火'), - (0x2F56, 'M', '爪'), - (0x2F57, 'M', '父'), - (0x2F58, 'M', '爻'), - (0x2F59, 'M', '爿'), - (0x2F5A, 'M', '片'), - (0x2F5B, 'M', '牙'), - (0x2F5C, 'M', '牛'), - (0x2F5D, 'M', '犬'), - (0x2F5E, 'M', '玄'), - (0x2F5F, 'M', '玉'), - (0x2F60, 'M', '瓜'), - (0x2F61, 'M', '瓦'), - (0x2F62, 'M', '甘'), - (0x2F63, 'M', '生'), - (0x2F64, 'M', '用'), - (0x2F65, 'M', '田'), - (0x2F66, 'M', '疋'), - (0x2F67, 'M', '疒'), - (0x2F68, 'M', '癶'), - (0x2F69, 'M', '白'), - (0x2F6A, 'M', '皮'), - (0x2F6B, 'M', '皿'), - (0x2F6C, 'M', '目'), - (0x2F6D, 'M', '矛'), - (0x2F6E, 'M', '矢'), - (0x2F6F, 'M', '石'), - (0x2F70, 'M', '示'), - (0x2F71, 'M', '禸'), - (0x2F72, 'M', '禾'), - (0x2F73, 'M', '穴'), - (0x2F74, 'M', '立'), - (0x2F75, 'M', '竹'), - (0x2F76, 'M', '米'), - (0x2F77, 'M', '糸'), - (0x2F78, 'M', '缶'), - (0x2F79, 'M', '网'), + (0x2F1A, "M", "厂"), + (0x2F1B, "M", "厶"), + (0x2F1C, "M", "又"), + (0x2F1D, "M", "口"), + (0x2F1E, "M", "囗"), + (0x2F1F, "M", "土"), + (0x2F20, "M", "士"), + (0x2F21, "M", "夂"), + (0x2F22, "M", "夊"), + (0x2F23, "M", "夕"), + (0x2F24, "M", "大"), + (0x2F25, "M", "女"), + (0x2F26, "M", "子"), + (0x2F27, "M", "宀"), + (0x2F28, "M", "寸"), + (0x2F29, "M", "小"), + (0x2F2A, "M", "尢"), + (0x2F2B, "M", "尸"), + (0x2F2C, "M", "屮"), + (0x2F2D, "M", "山"), + (0x2F2E, "M", "巛"), + (0x2F2F, "M", "工"), + (0x2F30, "M", "己"), + (0x2F31, "M", "巾"), + (0x2F32, "M", "干"), + (0x2F33, "M", "幺"), + (0x2F34, "M", "广"), + (0x2F35, "M", "廴"), + (0x2F36, "M", "廾"), + (0x2F37, "M", "弋"), + (0x2F38, "M", "弓"), + (0x2F39, "M", "彐"), + (0x2F3A, "M", "彡"), + (0x2F3B, "M", "彳"), + (0x2F3C, "M", "心"), + (0x2F3D, "M", "戈"), + (0x2F3E, "M", "戶"), + (0x2F3F, "M", "手"), + (0x2F40, "M", "支"), + (0x2F41, "M", "攴"), + (0x2F42, "M", "文"), + (0x2F43, "M", "斗"), + (0x2F44, "M", "斤"), + (0x2F45, "M", "方"), + (0x2F46, "M", "无"), + (0x2F47, "M", "日"), + (0x2F48, "M", "曰"), + (0x2F49, "M", "月"), + (0x2F4A, "M", "木"), + (0x2F4B, "M", "欠"), + (0x2F4C, "M", "止"), + (0x2F4D, "M", "歹"), + (0x2F4E, "M", "殳"), + (0x2F4F, "M", "毋"), + (0x2F50, "M", "比"), + (0x2F51, "M", "毛"), + (0x2F52, "M", "氏"), + (0x2F53, "M", "气"), + (0x2F54, "M", "水"), + (0x2F55, "M", "火"), + (0x2F56, "M", "爪"), + (0x2F57, "M", "父"), + (0x2F58, "M", "爻"), + (0x2F59, "M", "爿"), + (0x2F5A, "M", "片"), + (0x2F5B, "M", "牙"), + (0x2F5C, "M", "牛"), + (0x2F5D, "M", "犬"), + (0x2F5E, "M", "玄"), + (0x2F5F, "M", "玉"), + (0x2F60, "M", "瓜"), + (0x2F61, "M", "瓦"), + (0x2F62, "M", "甘"), + (0x2F63, "M", "生"), + (0x2F64, "M", "用"), + (0x2F65, "M", "田"), + (0x2F66, "M", "疋"), + (0x2F67, "M", "疒"), + (0x2F68, "M", "癶"), + (0x2F69, "M", "白"), + (0x2F6A, "M", "皮"), + (0x2F6B, "M", "皿"), + (0x2F6C, "M", "目"), + (0x2F6D, "M", "矛"), + (0x2F6E, "M", "矢"), + (0x2F6F, "M", "石"), + (0x2F70, "M", "示"), + (0x2F71, "M", "禸"), + (0x2F72, "M", "禾"), + (0x2F73, "M", "穴"), + (0x2F74, "M", "立"), + (0x2F75, "M", "竹"), + (0x2F76, "M", "米"), + (0x2F77, "M", "糸"), + (0x2F78, "M", "缶"), + (0x2F79, "M", "网"), + (0x2F7A, "M", "羊"), + (0x2F7B, "M", "羽"), + (0x2F7C, "M", "老"), + (0x2F7D, "M", "而"), ] + def _seg_28() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2F7A, 'M', '羊'), - (0x2F7B, 'M', '羽'), - (0x2F7C, 'M', '老'), - (0x2F7D, 'M', '而'), - (0x2F7E, 'M', '耒'), - (0x2F7F, 'M', '耳'), - (0x2F80, 'M', '聿'), - (0x2F81, 'M', '肉'), - (0x2F82, 'M', '臣'), - (0x2F83, 'M', '自'), - (0x2F84, 'M', '至'), - (0x2F85, 'M', '臼'), - (0x2F86, 'M', '舌'), - (0x2F87, 'M', '舛'), - (0x2F88, 'M', '舟'), - (0x2F89, 'M', '艮'), - (0x2F8A, 'M', '色'), - (0x2F8B, 'M', '艸'), - (0x2F8C, 'M', '虍'), - (0x2F8D, 'M', '虫'), - (0x2F8E, 'M', '血'), - (0x2F8F, 'M', '行'), - (0x2F90, 'M', '衣'), - (0x2F91, 'M', '襾'), - (0x2F92, 'M', '見'), - (0x2F93, 'M', '角'), - (0x2F94, 'M', '言'), - (0x2F95, 'M', '谷'), - (0x2F96, 'M', '豆'), - (0x2F97, 'M', '豕'), - (0x2F98, 'M', '豸'), - (0x2F99, 'M', '貝'), - (0x2F9A, 'M', '赤'), - (0x2F9B, 'M', '走'), - (0x2F9C, 'M', '足'), - (0x2F9D, 'M', '身'), - (0x2F9E, 'M', '車'), - (0x2F9F, 'M', '辛'), - (0x2FA0, 'M', '辰'), - (0x2FA1, 'M', '辵'), - (0x2FA2, 'M', '邑'), - (0x2FA3, 'M', '酉'), - (0x2FA4, 'M', '釆'), - (0x2FA5, 'M', '里'), - (0x2FA6, 'M', '金'), - (0x2FA7, 'M', '長'), - (0x2FA8, 'M', '門'), - (0x2FA9, 'M', '阜'), - (0x2FAA, 'M', '隶'), - (0x2FAB, 'M', '隹'), - (0x2FAC, 'M', '雨'), - (0x2FAD, 'M', '靑'), - (0x2FAE, 'M', '非'), - (0x2FAF, 'M', '面'), - (0x2FB0, 'M', '革'), - (0x2FB1, 'M', '韋'), - (0x2FB2, 'M', '韭'), - (0x2FB3, 'M', '音'), - (0x2FB4, 'M', '頁'), - (0x2FB5, 'M', '風'), - (0x2FB6, 'M', '飛'), - (0x2FB7, 'M', '食'), - (0x2FB8, 'M', '首'), - (0x2FB9, 'M', '香'), - (0x2FBA, 'M', '馬'), - (0x2FBB, 'M', '骨'), - (0x2FBC, 'M', '高'), - (0x2FBD, 'M', '髟'), - (0x2FBE, 'M', '鬥'), - (0x2FBF, 'M', '鬯'), - (0x2FC0, 'M', '鬲'), - (0x2FC1, 'M', '鬼'), - (0x2FC2, 'M', '魚'), - (0x2FC3, 'M', '鳥'), - (0x2FC4, 'M', '鹵'), - (0x2FC5, 'M', '鹿'), - (0x2FC6, 'M', '麥'), - (0x2FC7, 'M', '麻'), - (0x2FC8, 'M', '黃'), - (0x2FC9, 'M', '黍'), - (0x2FCA, 'M', '黑'), - (0x2FCB, 'M', '黹'), - (0x2FCC, 'M', '黽'), - (0x2FCD, 'M', '鼎'), - (0x2FCE, 'M', '鼓'), - (0x2FCF, 'M', '鼠'), - (0x2FD0, 'M', '鼻'), - (0x2FD1, 'M', '齊'), - (0x2FD2, 'M', '齒'), - (0x2FD3, 'M', '龍'), - (0x2FD4, 'M', '龜'), - (0x2FD5, 'M', '龠'), - (0x2FD6, 'X'), - (0x3000, '3', ' '), - (0x3001, 'V'), - (0x3002, 'M', '.'), - (0x3003, 'V'), - (0x3036, 'M', '〒'), - (0x3037, 'V'), - (0x3038, 'M', '十'), + (0x2F7E, "M", "耒"), + (0x2F7F, "M", "耳"), + (0x2F80, "M", "聿"), + (0x2F81, "M", "肉"), + (0x2F82, "M", "臣"), + (0x2F83, "M", "自"), + (0x2F84, "M", "至"), + (0x2F85, "M", "臼"), + (0x2F86, "M", "舌"), + (0x2F87, "M", "舛"), + (0x2F88, "M", "舟"), + (0x2F89, "M", "艮"), + (0x2F8A, "M", "色"), + (0x2F8B, "M", "艸"), + (0x2F8C, "M", "虍"), + (0x2F8D, "M", "虫"), + (0x2F8E, "M", "血"), + (0x2F8F, "M", "行"), + (0x2F90, "M", "衣"), + (0x2F91, "M", "襾"), + (0x2F92, "M", "見"), + (0x2F93, "M", "角"), + (0x2F94, "M", "言"), + (0x2F95, "M", "谷"), + (0x2F96, "M", "豆"), + (0x2F97, "M", "豕"), + (0x2F98, "M", "豸"), + (0x2F99, "M", "貝"), + (0x2F9A, "M", "赤"), + (0x2F9B, "M", "走"), + (0x2F9C, "M", "足"), + (0x2F9D, "M", "身"), + (0x2F9E, "M", "車"), + (0x2F9F, "M", "辛"), + (0x2FA0, "M", "辰"), + (0x2FA1, "M", "辵"), + (0x2FA2, "M", "邑"), + (0x2FA3, "M", "酉"), + (0x2FA4, "M", "釆"), + (0x2FA5, "M", "里"), + (0x2FA6, "M", "金"), + (0x2FA7, "M", "長"), + (0x2FA8, "M", "門"), + (0x2FA9, "M", "阜"), + (0x2FAA, "M", "隶"), + (0x2FAB, "M", "隹"), + (0x2FAC, "M", "雨"), + (0x2FAD, "M", "靑"), + (0x2FAE, "M", "非"), + (0x2FAF, "M", "面"), + (0x2FB0, "M", "革"), + (0x2FB1, "M", "韋"), + (0x2FB2, "M", "韭"), + (0x2FB3, "M", "音"), + (0x2FB4, "M", "頁"), + (0x2FB5, "M", "風"), + (0x2FB6, "M", "飛"), + (0x2FB7, "M", "食"), + (0x2FB8, "M", "首"), + (0x2FB9, "M", "香"), + (0x2FBA, "M", "馬"), + (0x2FBB, "M", "骨"), + (0x2FBC, "M", "高"), + (0x2FBD, "M", "髟"), + (0x2FBE, "M", "鬥"), + (0x2FBF, "M", "鬯"), + (0x2FC0, "M", "鬲"), + (0x2FC1, "M", "鬼"), + (0x2FC2, "M", "魚"), + (0x2FC3, "M", "鳥"), + (0x2FC4, "M", "鹵"), + (0x2FC5, "M", "鹿"), + (0x2FC6, "M", "麥"), + (0x2FC7, "M", "麻"), + (0x2FC8, "M", "黃"), + (0x2FC9, "M", "黍"), + (0x2FCA, "M", "黑"), + (0x2FCB, "M", "黹"), + (0x2FCC, "M", "黽"), + (0x2FCD, "M", "鼎"), + (0x2FCE, "M", "鼓"), + (0x2FCF, "M", "鼠"), + (0x2FD0, "M", "鼻"), + (0x2FD1, "M", "齊"), + (0x2FD2, "M", "齒"), + (0x2FD3, "M", "龍"), + (0x2FD4, "M", "龜"), + (0x2FD5, "M", "龠"), + (0x2FD6, "X"), + (0x3000, "3", " "), + (0x3001, "V"), + (0x3002, "M", "."), + (0x3003, "V"), + (0x3036, "M", "〒"), + (0x3037, "V"), + (0x3038, "M", "十"), + (0x3039, "M", "卄"), + (0x303A, "M", "卅"), + (0x303B, "V"), + (0x3040, "X"), ] + def _seg_29() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x3039, 'M', '卄'), - (0x303A, 'M', '卅'), - (0x303B, 'V'), - (0x3040, 'X'), - (0x3041, 'V'), - (0x3097, 'X'), - (0x3099, 'V'), - (0x309B, '3', ' ゙'), - (0x309C, '3', ' ゚'), - (0x309D, 'V'), - (0x309F, 'M', 'より'), - (0x30A0, 'V'), - (0x30FF, 'M', 'コト'), - (0x3100, 'X'), - (0x3105, 'V'), - (0x3130, 'X'), - (0x3131, 'M', 'ᄀ'), - (0x3132, 'M', 'ᄁ'), - (0x3133, 'M', 'ᆪ'), - (0x3134, 'M', 'ᄂ'), - (0x3135, 'M', 'ᆬ'), - (0x3136, 'M', 'ᆭ'), - (0x3137, 'M', 'ᄃ'), - (0x3138, 'M', 'ᄄ'), - (0x3139, 'M', 'ᄅ'), - (0x313A, 'M', 'ᆰ'), - (0x313B, 'M', 'ᆱ'), - (0x313C, 'M', 'ᆲ'), - (0x313D, 'M', 'ᆳ'), - (0x313E, 'M', 'ᆴ'), - (0x313F, 'M', 'ᆵ'), - (0x3140, 'M', 'ᄚ'), - (0x3141, 'M', 'ᄆ'), - (0x3142, 'M', 'ᄇ'), - (0x3143, 'M', 'ᄈ'), - (0x3144, 'M', 'ᄡ'), - (0x3145, 'M', 'ᄉ'), - (0x3146, 'M', 'ᄊ'), - (0x3147, 'M', 'ᄋ'), - (0x3148, 'M', 'ᄌ'), - (0x3149, 'M', 'ᄍ'), - (0x314A, 'M', 'ᄎ'), - (0x314B, 'M', 'ᄏ'), - (0x314C, 'M', 'ᄐ'), - (0x314D, 'M', 'ᄑ'), - (0x314E, 'M', 'ᄒ'), - (0x314F, 'M', 'ᅡ'), - (0x3150, 'M', 'ᅢ'), - (0x3151, 'M', 'ᅣ'), - (0x3152, 'M', 'ᅤ'), - (0x3153, 'M', 'ᅥ'), - (0x3154, 'M', 'ᅦ'), - (0x3155, 'M', 'ᅧ'), - (0x3156, 'M', 'ᅨ'), - (0x3157, 'M', 'ᅩ'), - (0x3158, 'M', 'ᅪ'), - (0x3159, 'M', 'ᅫ'), - (0x315A, 'M', 'ᅬ'), - (0x315B, 'M', 'ᅭ'), - (0x315C, 'M', 'ᅮ'), - (0x315D, 'M', 'ᅯ'), - (0x315E, 'M', 'ᅰ'), - (0x315F, 'M', 'ᅱ'), - (0x3160, 'M', 'ᅲ'), - (0x3161, 'M', 'ᅳ'), - (0x3162, 'M', 'ᅴ'), - (0x3163, 'M', 'ᅵ'), - (0x3164, 'X'), - (0x3165, 'M', 'ᄔ'), - (0x3166, 'M', 'ᄕ'), - (0x3167, 'M', 'ᇇ'), - (0x3168, 'M', 'ᇈ'), - (0x3169, 'M', 'ᇌ'), - (0x316A, 'M', 'ᇎ'), - (0x316B, 'M', 'ᇓ'), - (0x316C, 'M', 'ᇗ'), - (0x316D, 'M', 'ᇙ'), - (0x316E, 'M', 'ᄜ'), - (0x316F, 'M', 'ᇝ'), - (0x3170, 'M', 'ᇟ'), - (0x3171, 'M', 'ᄝ'), - (0x3172, 'M', 'ᄞ'), - (0x3173, 'M', 'ᄠ'), - (0x3174, 'M', 'ᄢ'), - (0x3175, 'M', 'ᄣ'), - (0x3176, 'M', 'ᄧ'), - (0x3177, 'M', 'ᄩ'), - (0x3178, 'M', 'ᄫ'), - (0x3179, 'M', 'ᄬ'), - (0x317A, 'M', 'ᄭ'), - (0x317B, 'M', 'ᄮ'), - (0x317C, 'M', 'ᄯ'), - (0x317D, 'M', 'ᄲ'), - (0x317E, 'M', 'ᄶ'), - (0x317F, 'M', 'ᅀ'), - (0x3180, 'M', 'ᅇ'), - (0x3181, 'M', 'ᅌ'), - (0x3182, 'M', 'ᇱ'), - (0x3183, 'M', 'ᇲ'), - (0x3184, 'M', 'ᅗ'), + (0x3041, "V"), + (0x3097, "X"), + (0x3099, "V"), + (0x309B, "3", " ゙"), + (0x309C, "3", " ゚"), + (0x309D, "V"), + (0x309F, "M", "より"), + (0x30A0, "V"), + (0x30FF, "M", "コト"), + (0x3100, "X"), + (0x3105, "V"), + (0x3130, "X"), + (0x3131, "M", "ᄀ"), + (0x3132, "M", "ᄁ"), + (0x3133, "M", "ᆪ"), + (0x3134, "M", "ᄂ"), + (0x3135, "M", "ᆬ"), + (0x3136, "M", "ᆭ"), + (0x3137, "M", "ᄃ"), + (0x3138, "M", "ᄄ"), + (0x3139, "M", "ᄅ"), + (0x313A, "M", "ᆰ"), + (0x313B, "M", "ᆱ"), + (0x313C, "M", "ᆲ"), + (0x313D, "M", "ᆳ"), + (0x313E, "M", "ᆴ"), + (0x313F, "M", "ᆵ"), + (0x3140, "M", "ᄚ"), + (0x3141, "M", "ᄆ"), + (0x3142, "M", "ᄇ"), + (0x3143, "M", "ᄈ"), + (0x3144, "M", "ᄡ"), + (0x3145, "M", "ᄉ"), + (0x3146, "M", "ᄊ"), + (0x3147, "M", "ᄋ"), + (0x3148, "M", "ᄌ"), + (0x3149, "M", "ᄍ"), + (0x314A, "M", "ᄎ"), + (0x314B, "M", "ᄏ"), + (0x314C, "M", "ᄐ"), + (0x314D, "M", "ᄑ"), + (0x314E, "M", "ᄒ"), + (0x314F, "M", "ᅡ"), + (0x3150, "M", "ᅢ"), + (0x3151, "M", "ᅣ"), + (0x3152, "M", "ᅤ"), + (0x3153, "M", "ᅥ"), + (0x3154, "M", "ᅦ"), + (0x3155, "M", "ᅧ"), + (0x3156, "M", "ᅨ"), + (0x3157, "M", "ᅩ"), + (0x3158, "M", "ᅪ"), + (0x3159, "M", "ᅫ"), + (0x315A, "M", "ᅬ"), + (0x315B, "M", "ᅭ"), + (0x315C, "M", "ᅮ"), + (0x315D, "M", "ᅯ"), + (0x315E, "M", "ᅰ"), + (0x315F, "M", "ᅱ"), + (0x3160, "M", "ᅲ"), + (0x3161, "M", "ᅳ"), + (0x3162, "M", "ᅴ"), + (0x3163, "M", "ᅵ"), + (0x3164, "X"), + (0x3165, "M", "ᄔ"), + (0x3166, "M", "ᄕ"), + (0x3167, "M", "ᇇ"), + (0x3168, "M", "ᇈ"), + (0x3169, "M", "ᇌ"), + (0x316A, "M", "ᇎ"), + (0x316B, "M", "ᇓ"), + (0x316C, "M", "ᇗ"), + (0x316D, "M", "ᇙ"), + (0x316E, "M", "ᄜ"), + (0x316F, "M", "ᇝ"), + (0x3170, "M", "ᇟ"), + (0x3171, "M", "ᄝ"), + (0x3172, "M", "ᄞ"), + (0x3173, "M", "ᄠ"), + (0x3174, "M", "ᄢ"), + (0x3175, "M", "ᄣ"), + (0x3176, "M", "ᄧ"), + (0x3177, "M", "ᄩ"), + (0x3178, "M", "ᄫ"), + (0x3179, "M", "ᄬ"), + (0x317A, "M", "ᄭ"), + (0x317B, "M", "ᄮ"), + (0x317C, "M", "ᄯ"), + (0x317D, "M", "ᄲ"), + (0x317E, "M", "ᄶ"), + (0x317F, "M", "ᅀ"), + (0x3180, "M", "ᅇ"), + (0x3181, "M", "ᅌ"), + (0x3182, "M", "ᇱ"), + (0x3183, "M", "ᇲ"), + (0x3184, "M", "ᅗ"), + (0x3185, "M", "ᅘ"), + (0x3186, "M", "ᅙ"), + (0x3187, "M", "ᆄ"), + (0x3188, "M", "ᆅ"), ] + def _seg_30() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x3185, 'M', 'ᅘ'), - (0x3186, 'M', 'ᅙ'), - (0x3187, 'M', 'ᆄ'), - (0x3188, 'M', 'ᆅ'), - (0x3189, 'M', 'ᆈ'), - (0x318A, 'M', 'ᆑ'), - (0x318B, 'M', 'ᆒ'), - (0x318C, 'M', 'ᆔ'), - (0x318D, 'M', 'ᆞ'), - (0x318E, 'M', 'ᆡ'), - (0x318F, 'X'), - (0x3190, 'V'), - (0x3192, 'M', '一'), - (0x3193, 'M', '二'), - (0x3194, 'M', '三'), - (0x3195, 'M', '四'), - (0x3196, 'M', '上'), - (0x3197, 'M', '中'), - (0x3198, 'M', '下'), - (0x3199, 'M', '甲'), - (0x319A, 'M', '乙'), - (0x319B, 'M', '丙'), - (0x319C, 'M', '丁'), - (0x319D, 'M', '天'), - (0x319E, 'M', '地'), - (0x319F, 'M', '人'), - (0x31A0, 'V'), - (0x31E4, 'X'), - (0x31F0, 'V'), - (0x3200, '3', '(ᄀ)'), - (0x3201, '3', '(ᄂ)'), - (0x3202, '3', '(ᄃ)'), - (0x3203, '3', '(ᄅ)'), - (0x3204, '3', '(ᄆ)'), - (0x3205, '3', '(ᄇ)'), - (0x3206, '3', '(ᄉ)'), - (0x3207, '3', '(ᄋ)'), - (0x3208, '3', '(ᄌ)'), - (0x3209, '3', '(ᄎ)'), - (0x320A, '3', '(ᄏ)'), - (0x320B, '3', '(ᄐ)'), - (0x320C, '3', '(ᄑ)'), - (0x320D, '3', '(ᄒ)'), - (0x320E, '3', '(가)'), - (0x320F, '3', '(나)'), - (0x3210, '3', '(다)'), - (0x3211, '3', '(라)'), - (0x3212, '3', '(마)'), - (0x3213, '3', '(바)'), - (0x3214, '3', '(사)'), - (0x3215, '3', '(아)'), - (0x3216, '3', '(자)'), - (0x3217, '3', '(차)'), - (0x3218, '3', '(카)'), - (0x3219, '3', '(타)'), - (0x321A, '3', '(파)'), - (0x321B, '3', '(하)'), - (0x321C, '3', '(주)'), - (0x321D, '3', '(오전)'), - (0x321E, '3', '(오후)'), - (0x321F, 'X'), - (0x3220, '3', '(一)'), - (0x3221, '3', '(二)'), - (0x3222, '3', '(三)'), - (0x3223, '3', '(四)'), - (0x3224, '3', '(五)'), - (0x3225, '3', '(六)'), - (0x3226, '3', '(七)'), - (0x3227, '3', '(八)'), - (0x3228, '3', '(九)'), - (0x3229, '3', '(十)'), - (0x322A, '3', '(月)'), - (0x322B, '3', '(火)'), - (0x322C, '3', '(水)'), - (0x322D, '3', '(木)'), - (0x322E, '3', '(金)'), - (0x322F, '3', '(土)'), - (0x3230, '3', '(日)'), - (0x3231, '3', '(株)'), - (0x3232, '3', '(有)'), - (0x3233, '3', '(社)'), - (0x3234, '3', '(名)'), - (0x3235, '3', '(特)'), - (0x3236, '3', '(財)'), - (0x3237, '3', '(祝)'), - (0x3238, '3', '(労)'), - (0x3239, '3', '(代)'), - (0x323A, '3', '(呼)'), - (0x323B, '3', '(学)'), - (0x323C, '3', '(監)'), - (0x323D, '3', '(企)'), - (0x323E, '3', '(資)'), - (0x323F, '3', '(協)'), - (0x3240, '3', '(祭)'), - (0x3241, '3', '(休)'), - (0x3242, '3', '(自)'), - (0x3243, '3', '(至)'), - (0x3244, 'M', '問'), - (0x3245, 'M', '幼'), - (0x3246, 'M', '文'), + (0x3189, "M", "ᆈ"), + (0x318A, "M", "ᆑ"), + (0x318B, "M", "ᆒ"), + (0x318C, "M", "ᆔ"), + (0x318D, "M", "ᆞ"), + (0x318E, "M", "ᆡ"), + (0x318F, "X"), + (0x3190, "V"), + (0x3192, "M", "一"), + (0x3193, "M", "二"), + (0x3194, "M", "三"), + (0x3195, "M", "四"), + (0x3196, "M", "上"), + (0x3197, "M", "中"), + (0x3198, "M", "下"), + (0x3199, "M", "甲"), + (0x319A, "M", "乙"), + (0x319B, "M", "丙"), + (0x319C, "M", "丁"), + (0x319D, "M", "天"), + (0x319E, "M", "地"), + (0x319F, "M", "人"), + (0x31A0, "V"), + (0x31E4, "X"), + (0x31F0, "V"), + (0x3200, "3", "(ᄀ)"), + (0x3201, "3", "(ᄂ)"), + (0x3202, "3", "(ᄃ)"), + (0x3203, "3", "(ᄅ)"), + (0x3204, "3", "(ᄆ)"), + (0x3205, "3", "(ᄇ)"), + (0x3206, "3", "(ᄉ)"), + (0x3207, "3", "(ᄋ)"), + (0x3208, "3", "(ᄌ)"), + (0x3209, "3", "(ᄎ)"), + (0x320A, "3", "(ᄏ)"), + (0x320B, "3", "(ᄐ)"), + (0x320C, "3", "(ᄑ)"), + (0x320D, "3", "(ᄒ)"), + (0x320E, "3", "(가)"), + (0x320F, "3", "(나)"), + (0x3210, "3", "(다)"), + (0x3211, "3", "(라)"), + (0x3212, "3", "(마)"), + (0x3213, "3", "(바)"), + (0x3214, "3", "(사)"), + (0x3215, "3", "(아)"), + (0x3216, "3", "(자)"), + (0x3217, "3", "(차)"), + (0x3218, "3", "(카)"), + (0x3219, "3", "(타)"), + (0x321A, "3", "(파)"), + (0x321B, "3", "(하)"), + (0x321C, "3", "(주)"), + (0x321D, "3", "(오전)"), + (0x321E, "3", "(오후)"), + (0x321F, "X"), + (0x3220, "3", "(一)"), + (0x3221, "3", "(二)"), + (0x3222, "3", "(三)"), + (0x3223, "3", "(四)"), + (0x3224, "3", "(五)"), + (0x3225, "3", "(六)"), + (0x3226, "3", "(七)"), + (0x3227, "3", "(八)"), + (0x3228, "3", "(九)"), + (0x3229, "3", "(十)"), + (0x322A, "3", "(月)"), + (0x322B, "3", "(火)"), + (0x322C, "3", "(水)"), + (0x322D, "3", "(木)"), + (0x322E, "3", "(金)"), + (0x322F, "3", "(土)"), + (0x3230, "3", "(日)"), + (0x3231, "3", "(株)"), + (0x3232, "3", "(有)"), + (0x3233, "3", "(社)"), + (0x3234, "3", "(名)"), + (0x3235, "3", "(特)"), + (0x3236, "3", "(財)"), + (0x3237, "3", "(祝)"), + (0x3238, "3", "(労)"), + (0x3239, "3", "(代)"), + (0x323A, "3", "(呼)"), + (0x323B, "3", "(学)"), + (0x323C, "3", "(監)"), + (0x323D, "3", "(企)"), + (0x323E, "3", "(資)"), + (0x323F, "3", "(協)"), + (0x3240, "3", "(祭)"), + (0x3241, "3", "(休)"), + (0x3242, "3", "(自)"), + (0x3243, "3", "(至)"), + (0x3244, "M", "問"), + (0x3245, "M", "幼"), + (0x3246, "M", "文"), + (0x3247, "M", "箏"), + (0x3248, "V"), + (0x3250, "M", "pte"), + (0x3251, "M", "21"), ] + def _seg_31() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x3247, 'M', '箏'), - (0x3248, 'V'), - (0x3250, 'M', 'pte'), - (0x3251, 'M', '21'), - (0x3252, 'M', '22'), - (0x3253, 'M', '23'), - (0x3254, 'M', '24'), - (0x3255, 'M', '25'), - (0x3256, 'M', '26'), - (0x3257, 'M', '27'), - (0x3258, 'M', '28'), - (0x3259, 'M', '29'), - (0x325A, 'M', '30'), - (0x325B, 'M', '31'), - (0x325C, 'M', '32'), - (0x325D, 'M', '33'), - (0x325E, 'M', '34'), - (0x325F, 'M', '35'), - (0x3260, 'M', 'ᄀ'), - (0x3261, 'M', 'ᄂ'), - (0x3262, 'M', 'ᄃ'), - (0x3263, 'M', 'ᄅ'), - (0x3264, 'M', 'ᄆ'), - (0x3265, 'M', 'ᄇ'), - (0x3266, 'M', 'ᄉ'), - (0x3267, 'M', 'ᄋ'), - (0x3268, 'M', 'ᄌ'), - (0x3269, 'M', 'ᄎ'), - (0x326A, 'M', 'ᄏ'), - (0x326B, 'M', 'ᄐ'), - (0x326C, 'M', 'ᄑ'), - (0x326D, 'M', 'ᄒ'), - (0x326E, 'M', '가'), - (0x326F, 'M', '나'), - (0x3270, 'M', '다'), - (0x3271, 'M', '라'), - (0x3272, 'M', '마'), - (0x3273, 'M', '바'), - (0x3274, 'M', '사'), - (0x3275, 'M', '아'), - (0x3276, 'M', '자'), - (0x3277, 'M', '차'), - (0x3278, 'M', '카'), - (0x3279, 'M', '타'), - (0x327A, 'M', '파'), - (0x327B, 'M', '하'), - (0x327C, 'M', '참고'), - (0x327D, 'M', '주의'), - (0x327E, 'M', '우'), - (0x327F, 'V'), - (0x3280, 'M', '一'), - (0x3281, 'M', '二'), - (0x3282, 'M', '三'), - (0x3283, 'M', '四'), - (0x3284, 'M', '五'), - (0x3285, 'M', '六'), - (0x3286, 'M', '七'), - (0x3287, 'M', '八'), - (0x3288, 'M', '九'), - (0x3289, 'M', '十'), - (0x328A, 'M', '月'), - (0x328B, 'M', '火'), - (0x328C, 'M', '水'), - (0x328D, 'M', '木'), - (0x328E, 'M', '金'), - (0x328F, 'M', '土'), - (0x3290, 'M', '日'), - (0x3291, 'M', '株'), - (0x3292, 'M', '有'), - (0x3293, 'M', '社'), - (0x3294, 'M', '名'), - (0x3295, 'M', '特'), - (0x3296, 'M', '財'), - (0x3297, 'M', '祝'), - (0x3298, 'M', '労'), - (0x3299, 'M', '秘'), - (0x329A, 'M', '男'), - (0x329B, 'M', '女'), - (0x329C, 'M', '適'), - (0x329D, 'M', '優'), - (0x329E, 'M', '印'), - (0x329F, 'M', '注'), - (0x32A0, 'M', '項'), - (0x32A1, 'M', '休'), - (0x32A2, 'M', '写'), - (0x32A3, 'M', '正'), - (0x32A4, 'M', '上'), - (0x32A5, 'M', '中'), - (0x32A6, 'M', '下'), - (0x32A7, 'M', '左'), - (0x32A8, 'M', '右'), - (0x32A9, 'M', '医'), - (0x32AA, 'M', '宗'), - (0x32AB, 'M', '学'), - (0x32AC, 'M', '監'), - (0x32AD, 'M', '企'), - (0x32AE, 'M', '資'), - (0x32AF, 'M', '協'), - (0x32B0, 'M', '夜'), - (0x32B1, 'M', '36'), + (0x3252, "M", "22"), + (0x3253, "M", "23"), + (0x3254, "M", "24"), + (0x3255, "M", "25"), + (0x3256, "M", "26"), + (0x3257, "M", "27"), + (0x3258, "M", "28"), + (0x3259, "M", "29"), + (0x325A, "M", "30"), + (0x325B, "M", "31"), + (0x325C, "M", "32"), + (0x325D, "M", "33"), + (0x325E, "M", "34"), + (0x325F, "M", "35"), + (0x3260, "M", "ᄀ"), + (0x3261, "M", "ᄂ"), + (0x3262, "M", "ᄃ"), + (0x3263, "M", "ᄅ"), + (0x3264, "M", "ᄆ"), + (0x3265, "M", "ᄇ"), + (0x3266, "M", "ᄉ"), + (0x3267, "M", "ᄋ"), + (0x3268, "M", "ᄌ"), + (0x3269, "M", "ᄎ"), + (0x326A, "M", "ᄏ"), + (0x326B, "M", "ᄐ"), + (0x326C, "M", "ᄑ"), + (0x326D, "M", "ᄒ"), + (0x326E, "M", "가"), + (0x326F, "M", "나"), + (0x3270, "M", "다"), + (0x3271, "M", "라"), + (0x3272, "M", "마"), + (0x3273, "M", "바"), + (0x3274, "M", "사"), + (0x3275, "M", "아"), + (0x3276, "M", "자"), + (0x3277, "M", "차"), + (0x3278, "M", "카"), + (0x3279, "M", "타"), + (0x327A, "M", "파"), + (0x327B, "M", "하"), + (0x327C, "M", "참고"), + (0x327D, "M", "주의"), + (0x327E, "M", "우"), + (0x327F, "V"), + (0x3280, "M", "一"), + (0x3281, "M", "二"), + (0x3282, "M", "三"), + (0x3283, "M", "四"), + (0x3284, "M", "五"), + (0x3285, "M", "六"), + (0x3286, "M", "七"), + (0x3287, "M", "八"), + (0x3288, "M", "九"), + (0x3289, "M", "十"), + (0x328A, "M", "月"), + (0x328B, "M", "火"), + (0x328C, "M", "水"), + (0x328D, "M", "木"), + (0x328E, "M", "金"), + (0x328F, "M", "土"), + (0x3290, "M", "日"), + (0x3291, "M", "株"), + (0x3292, "M", "有"), + (0x3293, "M", "社"), + (0x3294, "M", "名"), + (0x3295, "M", "特"), + (0x3296, "M", "財"), + (0x3297, "M", "祝"), + (0x3298, "M", "労"), + (0x3299, "M", "秘"), + (0x329A, "M", "男"), + (0x329B, "M", "女"), + (0x329C, "M", "適"), + (0x329D, "M", "優"), + (0x329E, "M", "印"), + (0x329F, "M", "注"), + (0x32A0, "M", "項"), + (0x32A1, "M", "休"), + (0x32A2, "M", "写"), + (0x32A3, "M", "正"), + (0x32A4, "M", "上"), + (0x32A5, "M", "中"), + (0x32A6, "M", "下"), + (0x32A7, "M", "左"), + (0x32A8, "M", "右"), + (0x32A9, "M", "医"), + (0x32AA, "M", "宗"), + (0x32AB, "M", "学"), + (0x32AC, "M", "監"), + (0x32AD, "M", "企"), + (0x32AE, "M", "資"), + (0x32AF, "M", "協"), + (0x32B0, "M", "夜"), + (0x32B1, "M", "36"), + (0x32B2, "M", "37"), + (0x32B3, "M", "38"), + (0x32B4, "M", "39"), + (0x32B5, "M", "40"), ] + def _seg_32() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x32B2, 'M', '37'), - (0x32B3, 'M', '38'), - (0x32B4, 'M', '39'), - (0x32B5, 'M', '40'), - (0x32B6, 'M', '41'), - (0x32B7, 'M', '42'), - (0x32B8, 'M', '43'), - (0x32B9, 'M', '44'), - (0x32BA, 'M', '45'), - (0x32BB, 'M', '46'), - (0x32BC, 'M', '47'), - (0x32BD, 'M', '48'), - (0x32BE, 'M', '49'), - (0x32BF, 'M', '50'), - (0x32C0, 'M', '1月'), - (0x32C1, 'M', '2月'), - (0x32C2, 'M', '3月'), - (0x32C3, 'M', '4月'), - (0x32C4, 'M', '5月'), - (0x32C5, 'M', '6月'), - (0x32C6, 'M', '7月'), - (0x32C7, 'M', '8月'), - (0x32C8, 'M', '9月'), - (0x32C9, 'M', '10月'), - (0x32CA, 'M', '11月'), - (0x32CB, 'M', '12月'), - (0x32CC, 'M', 'hg'), - (0x32CD, 'M', 'erg'), - (0x32CE, 'M', 'ev'), - (0x32CF, 'M', 'ltd'), - (0x32D0, 'M', 'ア'), - (0x32D1, 'M', 'イ'), - (0x32D2, 'M', 'ウ'), - (0x32D3, 'M', 'エ'), - (0x32D4, 'M', 'オ'), - (0x32D5, 'M', 'カ'), - (0x32D6, 'M', 'キ'), - (0x32D7, 'M', 'ク'), - (0x32D8, 'M', 'ケ'), - (0x32D9, 'M', 'コ'), - (0x32DA, 'M', 'サ'), - (0x32DB, 'M', 'シ'), - (0x32DC, 'M', 'ス'), - (0x32DD, 'M', 'セ'), - (0x32DE, 'M', 'ソ'), - (0x32DF, 'M', 'タ'), - (0x32E0, 'M', 'チ'), - (0x32E1, 'M', 'ツ'), - (0x32E2, 'M', 'テ'), - (0x32E3, 'M', 'ト'), - (0x32E4, 'M', 'ナ'), - (0x32E5, 'M', 'ニ'), - (0x32E6, 'M', 'ヌ'), - (0x32E7, 'M', 'ネ'), - (0x32E8, 'M', 'ノ'), - (0x32E9, 'M', 'ハ'), - (0x32EA, 'M', 'ヒ'), - (0x32EB, 'M', 'フ'), - (0x32EC, 'M', 'ヘ'), - (0x32ED, 'M', 'ホ'), - (0x32EE, 'M', 'マ'), - (0x32EF, 'M', 'ミ'), - (0x32F0, 'M', 'ム'), - (0x32F1, 'M', 'メ'), - (0x32F2, 'M', 'モ'), - (0x32F3, 'M', 'ヤ'), - (0x32F4, 'M', 'ユ'), - (0x32F5, 'M', 'ヨ'), - (0x32F6, 'M', 'ラ'), - (0x32F7, 'M', 'リ'), - (0x32F8, 'M', 'ル'), - (0x32F9, 'M', 'レ'), - (0x32FA, 'M', 'ロ'), - (0x32FB, 'M', 'ワ'), - (0x32FC, 'M', 'ヰ'), - (0x32FD, 'M', 'ヱ'), - (0x32FE, 'M', 'ヲ'), - (0x32FF, 'M', '令和'), - (0x3300, 'M', 'アパート'), - (0x3301, 'M', 'アルファ'), - (0x3302, 'M', 'アンペア'), - (0x3303, 'M', 'アール'), - (0x3304, 'M', 'イニング'), - (0x3305, 'M', 'インチ'), - (0x3306, 'M', 'ウォン'), - (0x3307, 'M', 'エスクード'), - (0x3308, 'M', 'エーカー'), - (0x3309, 'M', 'オンス'), - (0x330A, 'M', 'オーム'), - (0x330B, 'M', 'カイリ'), - (0x330C, 'M', 'カラット'), - (0x330D, 'M', 'カロリー'), - (0x330E, 'M', 'ガロン'), - (0x330F, 'M', 'ガンマ'), - (0x3310, 'M', 'ギガ'), - (0x3311, 'M', 'ギニー'), - (0x3312, 'M', 'キュリー'), - (0x3313, 'M', 'ギルダー'), - (0x3314, 'M', 'キロ'), - (0x3315, 'M', 'キログラム'), + (0x32B6, "M", "41"), + (0x32B7, "M", "42"), + (0x32B8, "M", "43"), + (0x32B9, "M", "44"), + (0x32BA, "M", "45"), + (0x32BB, "M", "46"), + (0x32BC, "M", "47"), + (0x32BD, "M", "48"), + (0x32BE, "M", "49"), + (0x32BF, "M", "50"), + (0x32C0, "M", "1月"), + (0x32C1, "M", "2月"), + (0x32C2, "M", "3月"), + (0x32C3, "M", "4月"), + (0x32C4, "M", "5月"), + (0x32C5, "M", "6月"), + (0x32C6, "M", "7月"), + (0x32C7, "M", "8月"), + (0x32C8, "M", "9月"), + (0x32C9, "M", "10月"), + (0x32CA, "M", "11月"), + (0x32CB, "M", "12月"), + (0x32CC, "M", "hg"), + (0x32CD, "M", "erg"), + (0x32CE, "M", "ev"), + (0x32CF, "M", "ltd"), + (0x32D0, "M", "ア"), + (0x32D1, "M", "イ"), + (0x32D2, "M", "ウ"), + (0x32D3, "M", "エ"), + (0x32D4, "M", "オ"), + (0x32D5, "M", "カ"), + (0x32D6, "M", "キ"), + (0x32D7, "M", "ク"), + (0x32D8, "M", "ケ"), + (0x32D9, "M", "コ"), + (0x32DA, "M", "サ"), + (0x32DB, "M", "シ"), + (0x32DC, "M", "ス"), + (0x32DD, "M", "セ"), + (0x32DE, "M", "ソ"), + (0x32DF, "M", "タ"), + (0x32E0, "M", "チ"), + (0x32E1, "M", "ツ"), + (0x32E2, "M", "テ"), + (0x32E3, "M", "ト"), + (0x32E4, "M", "ナ"), + (0x32E5, "M", "ニ"), + (0x32E6, "M", "ヌ"), + (0x32E7, "M", "ネ"), + (0x32E8, "M", "ノ"), + (0x32E9, "M", "ハ"), + (0x32EA, "M", "ヒ"), + (0x32EB, "M", "フ"), + (0x32EC, "M", "ヘ"), + (0x32ED, "M", "ホ"), + (0x32EE, "M", "マ"), + (0x32EF, "M", "ミ"), + (0x32F0, "M", "ム"), + (0x32F1, "M", "メ"), + (0x32F2, "M", "モ"), + (0x32F3, "M", "ヤ"), + (0x32F4, "M", "ユ"), + (0x32F5, "M", "ヨ"), + (0x32F6, "M", "ラ"), + (0x32F7, "M", "リ"), + (0x32F8, "M", "ル"), + (0x32F9, "M", "レ"), + (0x32FA, "M", "ロ"), + (0x32FB, "M", "ワ"), + (0x32FC, "M", "ヰ"), + (0x32FD, "M", "ヱ"), + (0x32FE, "M", "ヲ"), + (0x32FF, "M", "令和"), + (0x3300, "M", "アパート"), + (0x3301, "M", "アルファ"), + (0x3302, "M", "アンペア"), + (0x3303, "M", "アール"), + (0x3304, "M", "イニング"), + (0x3305, "M", "インチ"), + (0x3306, "M", "ウォン"), + (0x3307, "M", "エスクード"), + (0x3308, "M", "エーカー"), + (0x3309, "M", "オンス"), + (0x330A, "M", "オーム"), + (0x330B, "M", "カイリ"), + (0x330C, "M", "カラット"), + (0x330D, "M", "カロリー"), + (0x330E, "M", "ガロン"), + (0x330F, "M", "ガンマ"), + (0x3310, "M", "ギガ"), + (0x3311, "M", "ギニー"), + (0x3312, "M", "キュリー"), + (0x3313, "M", "ギルダー"), + (0x3314, "M", "キロ"), + (0x3315, "M", "キログラム"), + (0x3316, "M", "キロメートル"), + (0x3317, "M", "キロワット"), + (0x3318, "M", "グラム"), + (0x3319, "M", "グラムトン"), ] + def _seg_33() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x3316, 'M', 'キロメートル'), - (0x3317, 'M', 'キロワット'), - (0x3318, 'M', 'グラム'), - (0x3319, 'M', 'グラムトン'), - (0x331A, 'M', 'クルゼイロ'), - (0x331B, 'M', 'クローネ'), - (0x331C, 'M', 'ケース'), - (0x331D, 'M', 'コルナ'), - (0x331E, 'M', 'コーポ'), - (0x331F, 'M', 'サイクル'), - (0x3320, 'M', 'サンチーム'), - (0x3321, 'M', 'シリング'), - (0x3322, 'M', 'センチ'), - (0x3323, 'M', 'セント'), - (0x3324, 'M', 'ダース'), - (0x3325, 'M', 'デシ'), - (0x3326, 'M', 'ドル'), - (0x3327, 'M', 'トン'), - (0x3328, 'M', 'ナノ'), - (0x3329, 'M', 'ノット'), - (0x332A, 'M', 'ハイツ'), - (0x332B, 'M', 'パーセント'), - (0x332C, 'M', 'パーツ'), - (0x332D, 'M', 'バーレル'), - (0x332E, 'M', 'ピアストル'), - (0x332F, 'M', 'ピクル'), - (0x3330, 'M', 'ピコ'), - (0x3331, 'M', 'ビル'), - (0x3332, 'M', 'ファラッド'), - (0x3333, 'M', 'フィート'), - (0x3334, 'M', 'ブッシェル'), - (0x3335, 'M', 'フラン'), - (0x3336, 'M', 'ヘクタール'), - (0x3337, 'M', 'ペソ'), - (0x3338, 'M', 'ペニヒ'), - (0x3339, 'M', 'ヘルツ'), - (0x333A, 'M', 'ペンス'), - (0x333B, 'M', 'ページ'), - (0x333C, 'M', 'ベータ'), - (0x333D, 'M', 'ポイント'), - (0x333E, 'M', 'ボルト'), - (0x333F, 'M', 'ホン'), - (0x3340, 'M', 'ポンド'), - (0x3341, 'M', 'ホール'), - (0x3342, 'M', 'ホーン'), - (0x3343, 'M', 'マイクロ'), - (0x3344, 'M', 'マイル'), - (0x3345, 'M', 'マッハ'), - (0x3346, 'M', 'マルク'), - (0x3347, 'M', 'マンション'), - (0x3348, 'M', 'ミクロン'), - (0x3349, 'M', 'ミリ'), - (0x334A, 'M', 'ミリバール'), - (0x334B, 'M', 'メガ'), - (0x334C, 'M', 'メガトン'), - (0x334D, 'M', 'メートル'), - (0x334E, 'M', 'ヤード'), - (0x334F, 'M', 'ヤール'), - (0x3350, 'M', 'ユアン'), - (0x3351, 'M', 'リットル'), - (0x3352, 'M', 'リラ'), - (0x3353, 'M', 'ルピー'), - (0x3354, 'M', 'ルーブル'), - (0x3355, 'M', 'レム'), - (0x3356, 'M', 'レントゲン'), - (0x3357, 'M', 'ワット'), - (0x3358, 'M', '0点'), - (0x3359, 'M', '1点'), - (0x335A, 'M', '2点'), - (0x335B, 'M', '3点'), - (0x335C, 'M', '4点'), - (0x335D, 'M', '5点'), - (0x335E, 'M', '6点'), - (0x335F, 'M', '7点'), - (0x3360, 'M', '8点'), - (0x3361, 'M', '9点'), - (0x3362, 'M', '10点'), - (0x3363, 'M', '11点'), - (0x3364, 'M', '12点'), - (0x3365, 'M', '13点'), - (0x3366, 'M', '14点'), - (0x3367, 'M', '15点'), - (0x3368, 'M', '16点'), - (0x3369, 'M', '17点'), - (0x336A, 'M', '18点'), - (0x336B, 'M', '19点'), - (0x336C, 'M', '20点'), - (0x336D, 'M', '21点'), - (0x336E, 'M', '22点'), - (0x336F, 'M', '23点'), - (0x3370, 'M', '24点'), - (0x3371, 'M', 'hpa'), - (0x3372, 'M', 'da'), - (0x3373, 'M', 'au'), - (0x3374, 'M', 'bar'), - (0x3375, 'M', 'ov'), - (0x3376, 'M', 'pc'), - (0x3377, 'M', 'dm'), - (0x3378, 'M', 'dm2'), - (0x3379, 'M', 'dm3'), + (0x331A, "M", "クルゼイロ"), + (0x331B, "M", "クローネ"), + (0x331C, "M", "ケース"), + (0x331D, "M", "コルナ"), + (0x331E, "M", "コーポ"), + (0x331F, "M", "サイクル"), + (0x3320, "M", "サンチーム"), + (0x3321, "M", "シリング"), + (0x3322, "M", "センチ"), + (0x3323, "M", "セント"), + (0x3324, "M", "ダース"), + (0x3325, "M", "デシ"), + (0x3326, "M", "ドル"), + (0x3327, "M", "トン"), + (0x3328, "M", "ナノ"), + (0x3329, "M", "ノット"), + (0x332A, "M", "ハイツ"), + (0x332B, "M", "パーセント"), + (0x332C, "M", "パーツ"), + (0x332D, "M", "バーレル"), + (0x332E, "M", "ピアストル"), + (0x332F, "M", "ピクル"), + (0x3330, "M", "ピコ"), + (0x3331, "M", "ビル"), + (0x3332, "M", "ファラッド"), + (0x3333, "M", "フィート"), + (0x3334, "M", "ブッシェル"), + (0x3335, "M", "フラン"), + (0x3336, "M", "ヘクタール"), + (0x3337, "M", "ペソ"), + (0x3338, "M", "ペニヒ"), + (0x3339, "M", "ヘルツ"), + (0x333A, "M", "ペンス"), + (0x333B, "M", "ページ"), + (0x333C, "M", "ベータ"), + (0x333D, "M", "ポイント"), + (0x333E, "M", "ボルト"), + (0x333F, "M", "ホン"), + (0x3340, "M", "ポンド"), + (0x3341, "M", "ホール"), + (0x3342, "M", "ホーン"), + (0x3343, "M", "マイクロ"), + (0x3344, "M", "マイル"), + (0x3345, "M", "マッハ"), + (0x3346, "M", "マルク"), + (0x3347, "M", "マンション"), + (0x3348, "M", "ミクロン"), + (0x3349, "M", "ミリ"), + (0x334A, "M", "ミリバール"), + (0x334B, "M", "メガ"), + (0x334C, "M", "メガトン"), + (0x334D, "M", "メートル"), + (0x334E, "M", "ヤード"), + (0x334F, "M", "ヤール"), + (0x3350, "M", "ユアン"), + (0x3351, "M", "リットル"), + (0x3352, "M", "リラ"), + (0x3353, "M", "ルピー"), + (0x3354, "M", "ルーブル"), + (0x3355, "M", "レム"), + (0x3356, "M", "レントゲン"), + (0x3357, "M", "ワット"), + (0x3358, "M", "0点"), + (0x3359, "M", "1点"), + (0x335A, "M", "2点"), + (0x335B, "M", "3点"), + (0x335C, "M", "4点"), + (0x335D, "M", "5点"), + (0x335E, "M", "6点"), + (0x335F, "M", "7点"), + (0x3360, "M", "8点"), + (0x3361, "M", "9点"), + (0x3362, "M", "10点"), + (0x3363, "M", "11点"), + (0x3364, "M", "12点"), + (0x3365, "M", "13点"), + (0x3366, "M", "14点"), + (0x3367, "M", "15点"), + (0x3368, "M", "16点"), + (0x3369, "M", "17点"), + (0x336A, "M", "18点"), + (0x336B, "M", "19点"), + (0x336C, "M", "20点"), + (0x336D, "M", "21点"), + (0x336E, "M", "22点"), + (0x336F, "M", "23点"), + (0x3370, "M", "24点"), + (0x3371, "M", "hpa"), + (0x3372, "M", "da"), + (0x3373, "M", "au"), + (0x3374, "M", "bar"), + (0x3375, "M", "ov"), + (0x3376, "M", "pc"), + (0x3377, "M", "dm"), + (0x3378, "M", "dm2"), + (0x3379, "M", "dm3"), + (0x337A, "M", "iu"), + (0x337B, "M", "平成"), + (0x337C, "M", "昭和"), + (0x337D, "M", "大正"), ] + def _seg_34() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x337A, 'M', 'iu'), - (0x337B, 'M', '平成'), - (0x337C, 'M', '昭和'), - (0x337D, 'M', '大正'), - (0x337E, 'M', '明治'), - (0x337F, 'M', '株式会社'), - (0x3380, 'M', 'pa'), - (0x3381, 'M', 'na'), - (0x3382, 'M', 'μa'), - (0x3383, 'M', 'ma'), - (0x3384, 'M', 'ka'), - (0x3385, 'M', 'kb'), - (0x3386, 'M', 'mb'), - (0x3387, 'M', 'gb'), - (0x3388, 'M', 'cal'), - (0x3389, 'M', 'kcal'), - (0x338A, 'M', 'pf'), - (0x338B, 'M', 'nf'), - (0x338C, 'M', 'μf'), - (0x338D, 'M', 'μg'), - (0x338E, 'M', 'mg'), - (0x338F, 'M', 'kg'), - (0x3390, 'M', 'hz'), - (0x3391, 'M', 'khz'), - (0x3392, 'M', 'mhz'), - (0x3393, 'M', 'ghz'), - (0x3394, 'M', 'thz'), - (0x3395, 'M', 'μl'), - (0x3396, 'M', 'ml'), - (0x3397, 'M', 'dl'), - (0x3398, 'M', 'kl'), - (0x3399, 'M', 'fm'), - (0x339A, 'M', 'nm'), - (0x339B, 'M', 'μm'), - (0x339C, 'M', 'mm'), - (0x339D, 'M', 'cm'), - (0x339E, 'M', 'km'), - (0x339F, 'M', 'mm2'), - (0x33A0, 'M', 'cm2'), - (0x33A1, 'M', 'm2'), - (0x33A2, 'M', 'km2'), - (0x33A3, 'M', 'mm3'), - (0x33A4, 'M', 'cm3'), - (0x33A5, 'M', 'm3'), - (0x33A6, 'M', 'km3'), - (0x33A7, 'M', 'm∕s'), - (0x33A8, 'M', 'm∕s2'), - (0x33A9, 'M', 'pa'), - (0x33AA, 'M', 'kpa'), - (0x33AB, 'M', 'mpa'), - (0x33AC, 'M', 'gpa'), - (0x33AD, 'M', 'rad'), - (0x33AE, 'M', 'rad∕s'), - (0x33AF, 'M', 'rad∕s2'), - (0x33B0, 'M', 'ps'), - (0x33B1, 'M', 'ns'), - (0x33B2, 'M', 'μs'), - (0x33B3, 'M', 'ms'), - (0x33B4, 'M', 'pv'), - (0x33B5, 'M', 'nv'), - (0x33B6, 'M', 'μv'), - (0x33B7, 'M', 'mv'), - (0x33B8, 'M', 'kv'), - (0x33B9, 'M', 'mv'), - (0x33BA, 'M', 'pw'), - (0x33BB, 'M', 'nw'), - (0x33BC, 'M', 'μw'), - (0x33BD, 'M', 'mw'), - (0x33BE, 'M', 'kw'), - (0x33BF, 'M', 'mw'), - (0x33C0, 'M', 'kω'), - (0x33C1, 'M', 'mω'), - (0x33C2, 'X'), - (0x33C3, 'M', 'bq'), - (0x33C4, 'M', 'cc'), - (0x33C5, 'M', 'cd'), - (0x33C6, 'M', 'c∕kg'), - (0x33C7, 'X'), - (0x33C8, 'M', 'db'), - (0x33C9, 'M', 'gy'), - (0x33CA, 'M', 'ha'), - (0x33CB, 'M', 'hp'), - (0x33CC, 'M', 'in'), - (0x33CD, 'M', 'kk'), - (0x33CE, 'M', 'km'), - (0x33CF, 'M', 'kt'), - (0x33D0, 'M', 'lm'), - (0x33D1, 'M', 'ln'), - (0x33D2, 'M', 'log'), - (0x33D3, 'M', 'lx'), - (0x33D4, 'M', 'mb'), - (0x33D5, 'M', 'mil'), - (0x33D6, 'M', 'mol'), - (0x33D7, 'M', 'ph'), - (0x33D8, 'X'), - (0x33D9, 'M', 'ppm'), - (0x33DA, 'M', 'pr'), - (0x33DB, 'M', 'sr'), - (0x33DC, 'M', 'sv'), - (0x33DD, 'M', 'wb'), + (0x337E, "M", "明治"), + (0x337F, "M", "株式会社"), + (0x3380, "M", "pa"), + (0x3381, "M", "na"), + (0x3382, "M", "μa"), + (0x3383, "M", "ma"), + (0x3384, "M", "ka"), + (0x3385, "M", "kb"), + (0x3386, "M", "mb"), + (0x3387, "M", "gb"), + (0x3388, "M", "cal"), + (0x3389, "M", "kcal"), + (0x338A, "M", "pf"), + (0x338B, "M", "nf"), + (0x338C, "M", "μf"), + (0x338D, "M", "μg"), + (0x338E, "M", "mg"), + (0x338F, "M", "kg"), + (0x3390, "M", "hz"), + (0x3391, "M", "khz"), + (0x3392, "M", "mhz"), + (0x3393, "M", "ghz"), + (0x3394, "M", "thz"), + (0x3395, "M", "μl"), + (0x3396, "M", "ml"), + (0x3397, "M", "dl"), + (0x3398, "M", "kl"), + (0x3399, "M", "fm"), + (0x339A, "M", "nm"), + (0x339B, "M", "μm"), + (0x339C, "M", "mm"), + (0x339D, "M", "cm"), + (0x339E, "M", "km"), + (0x339F, "M", "mm2"), + (0x33A0, "M", "cm2"), + (0x33A1, "M", "m2"), + (0x33A2, "M", "km2"), + (0x33A3, "M", "mm3"), + (0x33A4, "M", "cm3"), + (0x33A5, "M", "m3"), + (0x33A6, "M", "km3"), + (0x33A7, "M", "m∕s"), + (0x33A8, "M", "m∕s2"), + (0x33A9, "M", "pa"), + (0x33AA, "M", "kpa"), + (0x33AB, "M", "mpa"), + (0x33AC, "M", "gpa"), + (0x33AD, "M", "rad"), + (0x33AE, "M", "rad∕s"), + (0x33AF, "M", "rad∕s2"), + (0x33B0, "M", "ps"), + (0x33B1, "M", "ns"), + (0x33B2, "M", "μs"), + (0x33B3, "M", "ms"), + (0x33B4, "M", "pv"), + (0x33B5, "M", "nv"), + (0x33B6, "M", "μv"), + (0x33B7, "M", "mv"), + (0x33B8, "M", "kv"), + (0x33B9, "M", "mv"), + (0x33BA, "M", "pw"), + (0x33BB, "M", "nw"), + (0x33BC, "M", "μw"), + (0x33BD, "M", "mw"), + (0x33BE, "M", "kw"), + (0x33BF, "M", "mw"), + (0x33C0, "M", "kω"), + (0x33C1, "M", "mω"), + (0x33C2, "X"), + (0x33C3, "M", "bq"), + (0x33C4, "M", "cc"), + (0x33C5, "M", "cd"), + (0x33C6, "M", "c∕kg"), + (0x33C7, "X"), + (0x33C8, "M", "db"), + (0x33C9, "M", "gy"), + (0x33CA, "M", "ha"), + (0x33CB, "M", "hp"), + (0x33CC, "M", "in"), + (0x33CD, "M", "kk"), + (0x33CE, "M", "km"), + (0x33CF, "M", "kt"), + (0x33D0, "M", "lm"), + (0x33D1, "M", "ln"), + (0x33D2, "M", "log"), + (0x33D3, "M", "lx"), + (0x33D4, "M", "mb"), + (0x33D5, "M", "mil"), + (0x33D6, "M", "mol"), + (0x33D7, "M", "ph"), + (0x33D8, "X"), + (0x33D9, "M", "ppm"), + (0x33DA, "M", "pr"), + (0x33DB, "M", "sr"), + (0x33DC, "M", "sv"), + (0x33DD, "M", "wb"), + (0x33DE, "M", "v∕m"), + (0x33DF, "M", "a∕m"), + (0x33E0, "M", "1日"), + (0x33E1, "M", "2日"), ] + def _seg_35() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x33DE, 'M', 'v∕m'), - (0x33DF, 'M', 'a∕m'), - (0x33E0, 'M', '1日'), - (0x33E1, 'M', '2日'), - (0x33E2, 'M', '3日'), - (0x33E3, 'M', '4日'), - (0x33E4, 'M', '5日'), - (0x33E5, 'M', '6日'), - (0x33E6, 'M', '7日'), - (0x33E7, 'M', '8日'), - (0x33E8, 'M', '9日'), - (0x33E9, 'M', '10日'), - (0x33EA, 'M', '11日'), - (0x33EB, 'M', '12日'), - (0x33EC, 'M', '13日'), - (0x33ED, 'M', '14日'), - (0x33EE, 'M', '15日'), - (0x33EF, 'M', '16日'), - (0x33F0, 'M', '17日'), - (0x33F1, 'M', '18日'), - (0x33F2, 'M', '19日'), - (0x33F3, 'M', '20日'), - (0x33F4, 'M', '21日'), - (0x33F5, 'M', '22日'), - (0x33F6, 'M', '23日'), - (0x33F7, 'M', '24日'), - (0x33F8, 'M', '25日'), - (0x33F9, 'M', '26日'), - (0x33FA, 'M', '27日'), - (0x33FB, 'M', '28日'), - (0x33FC, 'M', '29日'), - (0x33FD, 'M', '30日'), - (0x33FE, 'M', '31日'), - (0x33FF, 'M', 'gal'), - (0x3400, 'V'), - (0xA48D, 'X'), - (0xA490, 'V'), - (0xA4C7, 'X'), - (0xA4D0, 'V'), - (0xA62C, 'X'), - (0xA640, 'M', 'ꙁ'), - (0xA641, 'V'), - (0xA642, 'M', 'ꙃ'), - (0xA643, 'V'), - (0xA644, 'M', 'ꙅ'), - (0xA645, 'V'), - (0xA646, 'M', 'ꙇ'), - (0xA647, 'V'), - (0xA648, 'M', 'ꙉ'), - (0xA649, 'V'), - (0xA64A, 'M', 'ꙋ'), - (0xA64B, 'V'), - (0xA64C, 'M', 'ꙍ'), - (0xA64D, 'V'), - (0xA64E, 'M', 'ꙏ'), - (0xA64F, 'V'), - (0xA650, 'M', 'ꙑ'), - (0xA651, 'V'), - (0xA652, 'M', 'ꙓ'), - (0xA653, 'V'), - (0xA654, 'M', 'ꙕ'), - (0xA655, 'V'), - (0xA656, 'M', 'ꙗ'), - (0xA657, 'V'), - (0xA658, 'M', 'ꙙ'), - (0xA659, 'V'), - (0xA65A, 'M', 'ꙛ'), - (0xA65B, 'V'), - (0xA65C, 'M', 'ꙝ'), - (0xA65D, 'V'), - (0xA65E, 'M', 'ꙟ'), - (0xA65F, 'V'), - (0xA660, 'M', 'ꙡ'), - (0xA661, 'V'), - (0xA662, 'M', 'ꙣ'), - (0xA663, 'V'), - (0xA664, 'M', 'ꙥ'), - (0xA665, 'V'), - (0xA666, 'M', 'ꙧ'), - (0xA667, 'V'), - (0xA668, 'M', 'ꙩ'), - (0xA669, 'V'), - (0xA66A, 'M', 'ꙫ'), - (0xA66B, 'V'), - (0xA66C, 'M', 'ꙭ'), - (0xA66D, 'V'), - (0xA680, 'M', 'ꚁ'), - (0xA681, 'V'), - (0xA682, 'M', 'ꚃ'), - (0xA683, 'V'), - (0xA684, 'M', 'ꚅ'), - (0xA685, 'V'), - (0xA686, 'M', 'ꚇ'), - (0xA687, 'V'), - (0xA688, 'M', 'ꚉ'), - (0xA689, 'V'), - (0xA68A, 'M', 'ꚋ'), - (0xA68B, 'V'), - (0xA68C, 'M', 'ꚍ'), - (0xA68D, 'V'), + (0x33E2, "M", "3日"), + (0x33E3, "M", "4日"), + (0x33E4, "M", "5日"), + (0x33E5, "M", "6日"), + (0x33E6, "M", "7日"), + (0x33E7, "M", "8日"), + (0x33E8, "M", "9日"), + (0x33E9, "M", "10日"), + (0x33EA, "M", "11日"), + (0x33EB, "M", "12日"), + (0x33EC, "M", "13日"), + (0x33ED, "M", "14日"), + (0x33EE, "M", "15日"), + (0x33EF, "M", "16日"), + (0x33F0, "M", "17日"), + (0x33F1, "M", "18日"), + (0x33F2, "M", "19日"), + (0x33F3, "M", "20日"), + (0x33F4, "M", "21日"), + (0x33F5, "M", "22日"), + (0x33F6, "M", "23日"), + (0x33F7, "M", "24日"), + (0x33F8, "M", "25日"), + (0x33F9, "M", "26日"), + (0x33FA, "M", "27日"), + (0x33FB, "M", "28日"), + (0x33FC, "M", "29日"), + (0x33FD, "M", "30日"), + (0x33FE, "M", "31日"), + (0x33FF, "M", "gal"), + (0x3400, "V"), + (0xA48D, "X"), + (0xA490, "V"), + (0xA4C7, "X"), + (0xA4D0, "V"), + (0xA62C, "X"), + (0xA640, "M", "ꙁ"), + (0xA641, "V"), + (0xA642, "M", "ꙃ"), + (0xA643, "V"), + (0xA644, "M", "ꙅ"), + (0xA645, "V"), + (0xA646, "M", "ꙇ"), + (0xA647, "V"), + (0xA648, "M", "ꙉ"), + (0xA649, "V"), + (0xA64A, "M", "ꙋ"), + (0xA64B, "V"), + (0xA64C, "M", "ꙍ"), + (0xA64D, "V"), + (0xA64E, "M", "ꙏ"), + (0xA64F, "V"), + (0xA650, "M", "ꙑ"), + (0xA651, "V"), + (0xA652, "M", "ꙓ"), + (0xA653, "V"), + (0xA654, "M", "ꙕ"), + (0xA655, "V"), + (0xA656, "M", "ꙗ"), + (0xA657, "V"), + (0xA658, "M", "ꙙ"), + (0xA659, "V"), + (0xA65A, "M", "ꙛ"), + (0xA65B, "V"), + (0xA65C, "M", "ꙝ"), + (0xA65D, "V"), + (0xA65E, "M", "ꙟ"), + (0xA65F, "V"), + (0xA660, "M", "ꙡ"), + (0xA661, "V"), + (0xA662, "M", "ꙣ"), + (0xA663, "V"), + (0xA664, "M", "ꙥ"), + (0xA665, "V"), + (0xA666, "M", "ꙧ"), + (0xA667, "V"), + (0xA668, "M", "ꙩ"), + (0xA669, "V"), + (0xA66A, "M", "ꙫ"), + (0xA66B, "V"), + (0xA66C, "M", "ꙭ"), + (0xA66D, "V"), + (0xA680, "M", "ꚁ"), + (0xA681, "V"), + (0xA682, "M", "ꚃ"), + (0xA683, "V"), + (0xA684, "M", "ꚅ"), + (0xA685, "V"), + (0xA686, "M", "ꚇ"), + (0xA687, "V"), + (0xA688, "M", "ꚉ"), + (0xA689, "V"), + (0xA68A, "M", "ꚋ"), + (0xA68B, "V"), + (0xA68C, "M", "ꚍ"), + (0xA68D, "V"), + (0xA68E, "M", "ꚏ"), + (0xA68F, "V"), + (0xA690, "M", "ꚑ"), + (0xA691, "V"), ] + def _seg_36() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xA68E, 'M', 'ꚏ'), - (0xA68F, 'V'), - (0xA690, 'M', 'ꚑ'), - (0xA691, 'V'), - (0xA692, 'M', 'ꚓ'), - (0xA693, 'V'), - (0xA694, 'M', 'ꚕ'), - (0xA695, 'V'), - (0xA696, 'M', 'ꚗ'), - (0xA697, 'V'), - (0xA698, 'M', 'ꚙ'), - (0xA699, 'V'), - (0xA69A, 'M', 'ꚛ'), - (0xA69B, 'V'), - (0xA69C, 'M', 'ъ'), - (0xA69D, 'M', 'ь'), - (0xA69E, 'V'), - (0xA6F8, 'X'), - (0xA700, 'V'), - (0xA722, 'M', 'ꜣ'), - (0xA723, 'V'), - (0xA724, 'M', 'ꜥ'), - (0xA725, 'V'), - (0xA726, 'M', 'ꜧ'), - (0xA727, 'V'), - (0xA728, 'M', 'ꜩ'), - (0xA729, 'V'), - (0xA72A, 'M', 'ꜫ'), - (0xA72B, 'V'), - (0xA72C, 'M', 'ꜭ'), - (0xA72D, 'V'), - (0xA72E, 'M', 'ꜯ'), - (0xA72F, 'V'), - (0xA732, 'M', 'ꜳ'), - (0xA733, 'V'), - (0xA734, 'M', 'ꜵ'), - (0xA735, 'V'), - (0xA736, 'M', 'ꜷ'), - (0xA737, 'V'), - (0xA738, 'M', 'ꜹ'), - (0xA739, 'V'), - (0xA73A, 'M', 'ꜻ'), - (0xA73B, 'V'), - (0xA73C, 'M', 'ꜽ'), - (0xA73D, 'V'), - (0xA73E, 'M', 'ꜿ'), - (0xA73F, 'V'), - (0xA740, 'M', 'ꝁ'), - (0xA741, 'V'), - (0xA742, 'M', 'ꝃ'), - (0xA743, 'V'), - (0xA744, 'M', 'ꝅ'), - (0xA745, 'V'), - (0xA746, 'M', 'ꝇ'), - (0xA747, 'V'), - (0xA748, 'M', 'ꝉ'), - (0xA749, 'V'), - (0xA74A, 'M', 'ꝋ'), - (0xA74B, 'V'), - (0xA74C, 'M', 'ꝍ'), - (0xA74D, 'V'), - (0xA74E, 'M', 'ꝏ'), - (0xA74F, 'V'), - (0xA750, 'M', 'ꝑ'), - (0xA751, 'V'), - (0xA752, 'M', 'ꝓ'), - (0xA753, 'V'), - (0xA754, 'M', 'ꝕ'), - (0xA755, 'V'), - (0xA756, 'M', 'ꝗ'), - (0xA757, 'V'), - (0xA758, 'M', 'ꝙ'), - (0xA759, 'V'), - (0xA75A, 'M', 'ꝛ'), - (0xA75B, 'V'), - (0xA75C, 'M', 'ꝝ'), - (0xA75D, 'V'), - (0xA75E, 'M', 'ꝟ'), - (0xA75F, 'V'), - (0xA760, 'M', 'ꝡ'), - (0xA761, 'V'), - (0xA762, 'M', 'ꝣ'), - (0xA763, 'V'), - (0xA764, 'M', 'ꝥ'), - (0xA765, 'V'), - (0xA766, 'M', 'ꝧ'), - (0xA767, 'V'), - (0xA768, 'M', 'ꝩ'), - (0xA769, 'V'), - (0xA76A, 'M', 'ꝫ'), - (0xA76B, 'V'), - (0xA76C, 'M', 'ꝭ'), - (0xA76D, 'V'), - (0xA76E, 'M', 'ꝯ'), - (0xA76F, 'V'), - (0xA770, 'M', 'ꝯ'), - (0xA771, 'V'), - (0xA779, 'M', 'ꝺ'), - (0xA77A, 'V'), - (0xA77B, 'M', 'ꝼ'), + (0xA692, "M", "ꚓ"), + (0xA693, "V"), + (0xA694, "M", "ꚕ"), + (0xA695, "V"), + (0xA696, "M", "ꚗ"), + (0xA697, "V"), + (0xA698, "M", "ꚙ"), + (0xA699, "V"), + (0xA69A, "M", "ꚛ"), + (0xA69B, "V"), + (0xA69C, "M", "ъ"), + (0xA69D, "M", "ь"), + (0xA69E, "V"), + (0xA6F8, "X"), + (0xA700, "V"), + (0xA722, "M", "ꜣ"), + (0xA723, "V"), + (0xA724, "M", "ꜥ"), + (0xA725, "V"), + (0xA726, "M", "ꜧ"), + (0xA727, "V"), + (0xA728, "M", "ꜩ"), + (0xA729, "V"), + (0xA72A, "M", "ꜫ"), + (0xA72B, "V"), + (0xA72C, "M", "ꜭ"), + (0xA72D, "V"), + (0xA72E, "M", "ꜯ"), + (0xA72F, "V"), + (0xA732, "M", "ꜳ"), + (0xA733, "V"), + (0xA734, "M", "ꜵ"), + (0xA735, "V"), + (0xA736, "M", "ꜷ"), + (0xA737, "V"), + (0xA738, "M", "ꜹ"), + (0xA739, "V"), + (0xA73A, "M", "ꜻ"), + (0xA73B, "V"), + (0xA73C, "M", "ꜽ"), + (0xA73D, "V"), + (0xA73E, "M", "ꜿ"), + (0xA73F, "V"), + (0xA740, "M", "ꝁ"), + (0xA741, "V"), + (0xA742, "M", "ꝃ"), + (0xA743, "V"), + (0xA744, "M", "ꝅ"), + (0xA745, "V"), + (0xA746, "M", "ꝇ"), + (0xA747, "V"), + (0xA748, "M", "ꝉ"), + (0xA749, "V"), + (0xA74A, "M", "ꝋ"), + (0xA74B, "V"), + (0xA74C, "M", "ꝍ"), + (0xA74D, "V"), + (0xA74E, "M", "ꝏ"), + (0xA74F, "V"), + (0xA750, "M", "ꝑ"), + (0xA751, "V"), + (0xA752, "M", "ꝓ"), + (0xA753, "V"), + (0xA754, "M", "ꝕ"), + (0xA755, "V"), + (0xA756, "M", "ꝗ"), + (0xA757, "V"), + (0xA758, "M", "ꝙ"), + (0xA759, "V"), + (0xA75A, "M", "ꝛ"), + (0xA75B, "V"), + (0xA75C, "M", "ꝝ"), + (0xA75D, "V"), + (0xA75E, "M", "ꝟ"), + (0xA75F, "V"), + (0xA760, "M", "ꝡ"), + (0xA761, "V"), + (0xA762, "M", "ꝣ"), + (0xA763, "V"), + (0xA764, "M", "ꝥ"), + (0xA765, "V"), + (0xA766, "M", "ꝧ"), + (0xA767, "V"), + (0xA768, "M", "ꝩ"), + (0xA769, "V"), + (0xA76A, "M", "ꝫ"), + (0xA76B, "V"), + (0xA76C, "M", "ꝭ"), + (0xA76D, "V"), + (0xA76E, "M", "ꝯ"), + (0xA76F, "V"), + (0xA770, "M", "ꝯ"), + (0xA771, "V"), + (0xA779, "M", "ꝺ"), + (0xA77A, "V"), + (0xA77B, "M", "ꝼ"), + (0xA77C, "V"), + (0xA77D, "M", "ᵹ"), + (0xA77E, "M", "ꝿ"), + (0xA77F, "V"), ] + def _seg_37() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xA77C, 'V'), - (0xA77D, 'M', 'ᵹ'), - (0xA77E, 'M', 'ꝿ'), - (0xA77F, 'V'), - (0xA780, 'M', 'ꞁ'), - (0xA781, 'V'), - (0xA782, 'M', 'ꞃ'), - (0xA783, 'V'), - (0xA784, 'M', 'ꞅ'), - (0xA785, 'V'), - (0xA786, 'M', 'ꞇ'), - (0xA787, 'V'), - (0xA78B, 'M', 'ꞌ'), - (0xA78C, 'V'), - (0xA78D, 'M', 'ɥ'), - (0xA78E, 'V'), - (0xA790, 'M', 'ꞑ'), - (0xA791, 'V'), - (0xA792, 'M', 'ꞓ'), - (0xA793, 'V'), - (0xA796, 'M', 'ꞗ'), - (0xA797, 'V'), - (0xA798, 'M', 'ꞙ'), - (0xA799, 'V'), - (0xA79A, 'M', 'ꞛ'), - (0xA79B, 'V'), - (0xA79C, 'M', 'ꞝ'), - (0xA79D, 'V'), - (0xA79E, 'M', 'ꞟ'), - (0xA79F, 'V'), - (0xA7A0, 'M', 'ꞡ'), - (0xA7A1, 'V'), - (0xA7A2, 'M', 'ꞣ'), - (0xA7A3, 'V'), - (0xA7A4, 'M', 'ꞥ'), - (0xA7A5, 'V'), - (0xA7A6, 'M', 'ꞧ'), - (0xA7A7, 'V'), - (0xA7A8, 'M', 'ꞩ'), - (0xA7A9, 'V'), - (0xA7AA, 'M', 'ɦ'), - (0xA7AB, 'M', 'ɜ'), - (0xA7AC, 'M', 'ɡ'), - (0xA7AD, 'M', 'ɬ'), - (0xA7AE, 'M', 'ɪ'), - (0xA7AF, 'V'), - (0xA7B0, 'M', 'ʞ'), - (0xA7B1, 'M', 'ʇ'), - (0xA7B2, 'M', 'ʝ'), - (0xA7B3, 'M', 'ꭓ'), - (0xA7B4, 'M', 'ꞵ'), - (0xA7B5, 'V'), - (0xA7B6, 'M', 'ꞷ'), - (0xA7B7, 'V'), - (0xA7B8, 'M', 'ꞹ'), - (0xA7B9, 'V'), - (0xA7BA, 'M', 'ꞻ'), - (0xA7BB, 'V'), - (0xA7BC, 'M', 'ꞽ'), - (0xA7BD, 'V'), - (0xA7BE, 'M', 'ꞿ'), - (0xA7BF, 'V'), - (0xA7C0, 'M', 'ꟁ'), - (0xA7C1, 'V'), - (0xA7C2, 'M', 'ꟃ'), - (0xA7C3, 'V'), - (0xA7C4, 'M', 'ꞔ'), - (0xA7C5, 'M', 'ʂ'), - (0xA7C6, 'M', 'ᶎ'), - (0xA7C7, 'M', 'ꟈ'), - (0xA7C8, 'V'), - (0xA7C9, 'M', 'ꟊ'), - (0xA7CA, 'V'), - (0xA7CB, 'X'), - (0xA7D0, 'M', 'ꟑ'), - (0xA7D1, 'V'), - (0xA7D2, 'X'), - (0xA7D3, 'V'), - (0xA7D4, 'X'), - (0xA7D5, 'V'), - (0xA7D6, 'M', 'ꟗ'), - (0xA7D7, 'V'), - (0xA7D8, 'M', 'ꟙ'), - (0xA7D9, 'V'), - (0xA7DA, 'X'), - (0xA7F2, 'M', 'c'), - (0xA7F3, 'M', 'f'), - (0xA7F4, 'M', 'q'), - (0xA7F5, 'M', 'ꟶ'), - (0xA7F6, 'V'), - (0xA7F8, 'M', 'ħ'), - (0xA7F9, 'M', 'œ'), - (0xA7FA, 'V'), - (0xA82D, 'X'), - (0xA830, 'V'), - (0xA83A, 'X'), - (0xA840, 'V'), - (0xA878, 'X'), - (0xA880, 'V'), - (0xA8C6, 'X'), + (0xA780, "M", "ꞁ"), + (0xA781, "V"), + (0xA782, "M", "ꞃ"), + (0xA783, "V"), + (0xA784, "M", "ꞅ"), + (0xA785, "V"), + (0xA786, "M", "ꞇ"), + (0xA787, "V"), + (0xA78B, "M", "ꞌ"), + (0xA78C, "V"), + (0xA78D, "M", "ɥ"), + (0xA78E, "V"), + (0xA790, "M", "ꞑ"), + (0xA791, "V"), + (0xA792, "M", "ꞓ"), + (0xA793, "V"), + (0xA796, "M", "ꞗ"), + (0xA797, "V"), + (0xA798, "M", "ꞙ"), + (0xA799, "V"), + (0xA79A, "M", "ꞛ"), + (0xA79B, "V"), + (0xA79C, "M", "ꞝ"), + (0xA79D, "V"), + (0xA79E, "M", "ꞟ"), + (0xA79F, "V"), + (0xA7A0, "M", "ꞡ"), + (0xA7A1, "V"), + (0xA7A2, "M", "ꞣ"), + (0xA7A3, "V"), + (0xA7A4, "M", "ꞥ"), + (0xA7A5, "V"), + (0xA7A6, "M", "ꞧ"), + (0xA7A7, "V"), + (0xA7A8, "M", "ꞩ"), + (0xA7A9, "V"), + (0xA7AA, "M", "ɦ"), + (0xA7AB, "M", "ɜ"), + (0xA7AC, "M", "ɡ"), + (0xA7AD, "M", "ɬ"), + (0xA7AE, "M", "ɪ"), + (0xA7AF, "V"), + (0xA7B0, "M", "ʞ"), + (0xA7B1, "M", "ʇ"), + (0xA7B2, "M", "ʝ"), + (0xA7B3, "M", "ꭓ"), + (0xA7B4, "M", "ꞵ"), + (0xA7B5, "V"), + (0xA7B6, "M", "ꞷ"), + (0xA7B7, "V"), + (0xA7B8, "M", "ꞹ"), + (0xA7B9, "V"), + (0xA7BA, "M", "ꞻ"), + (0xA7BB, "V"), + (0xA7BC, "M", "ꞽ"), + (0xA7BD, "V"), + (0xA7BE, "M", "ꞿ"), + (0xA7BF, "V"), + (0xA7C0, "M", "ꟁ"), + (0xA7C1, "V"), + (0xA7C2, "M", "ꟃ"), + (0xA7C3, "V"), + (0xA7C4, "M", "ꞔ"), + (0xA7C5, "M", "ʂ"), + (0xA7C6, "M", "ᶎ"), + (0xA7C7, "M", "ꟈ"), + (0xA7C8, "V"), + (0xA7C9, "M", "ꟊ"), + (0xA7CA, "V"), + (0xA7CB, "X"), + (0xA7D0, "M", "ꟑ"), + (0xA7D1, "V"), + (0xA7D2, "X"), + (0xA7D3, "V"), + (0xA7D4, "X"), + (0xA7D5, "V"), + (0xA7D6, "M", "ꟗ"), + (0xA7D7, "V"), + (0xA7D8, "M", "ꟙ"), + (0xA7D9, "V"), + (0xA7DA, "X"), + (0xA7F2, "M", "c"), + (0xA7F3, "M", "f"), + (0xA7F4, "M", "q"), + (0xA7F5, "M", "ꟶ"), + (0xA7F6, "V"), + (0xA7F8, "M", "ħ"), + (0xA7F9, "M", "œ"), + (0xA7FA, "V"), + (0xA82D, "X"), + (0xA830, "V"), + (0xA83A, "X"), + (0xA840, "V"), + (0xA878, "X"), + (0xA880, "V"), + (0xA8C6, "X"), + (0xA8CE, "V"), + (0xA8DA, "X"), + (0xA8E0, "V"), + (0xA954, "X"), ] + def _seg_38() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xA8CE, 'V'), - (0xA8DA, 'X'), - (0xA8E0, 'V'), - (0xA954, 'X'), - (0xA95F, 'V'), - (0xA97D, 'X'), - (0xA980, 'V'), - (0xA9CE, 'X'), - (0xA9CF, 'V'), - (0xA9DA, 'X'), - (0xA9DE, 'V'), - (0xA9FF, 'X'), - (0xAA00, 'V'), - (0xAA37, 'X'), - (0xAA40, 'V'), - (0xAA4E, 'X'), - (0xAA50, 'V'), - (0xAA5A, 'X'), - (0xAA5C, 'V'), - (0xAAC3, 'X'), - (0xAADB, 'V'), - (0xAAF7, 'X'), - (0xAB01, 'V'), - (0xAB07, 'X'), - (0xAB09, 'V'), - (0xAB0F, 'X'), - (0xAB11, 'V'), - (0xAB17, 'X'), - (0xAB20, 'V'), - (0xAB27, 'X'), - (0xAB28, 'V'), - (0xAB2F, 'X'), - (0xAB30, 'V'), - (0xAB5C, 'M', 'ꜧ'), - (0xAB5D, 'M', 'ꬷ'), - (0xAB5E, 'M', 'ɫ'), - (0xAB5F, 'M', 'ꭒ'), - (0xAB60, 'V'), - (0xAB69, 'M', 'ʍ'), - (0xAB6A, 'V'), - (0xAB6C, 'X'), - (0xAB70, 'M', 'Ꭰ'), - (0xAB71, 'M', 'Ꭱ'), - (0xAB72, 'M', 'Ꭲ'), - (0xAB73, 'M', 'Ꭳ'), - (0xAB74, 'M', 'Ꭴ'), - (0xAB75, 'M', 'Ꭵ'), - (0xAB76, 'M', 'Ꭶ'), - (0xAB77, 'M', 'Ꭷ'), - (0xAB78, 'M', 'Ꭸ'), - (0xAB79, 'M', 'Ꭹ'), - (0xAB7A, 'M', 'Ꭺ'), - (0xAB7B, 'M', 'Ꭻ'), - (0xAB7C, 'M', 'Ꭼ'), - (0xAB7D, 'M', 'Ꭽ'), - (0xAB7E, 'M', 'Ꭾ'), - (0xAB7F, 'M', 'Ꭿ'), - (0xAB80, 'M', 'Ꮀ'), - (0xAB81, 'M', 'Ꮁ'), - (0xAB82, 'M', 'Ꮂ'), - (0xAB83, 'M', 'Ꮃ'), - (0xAB84, 'M', 'Ꮄ'), - (0xAB85, 'M', 'Ꮅ'), - (0xAB86, 'M', 'Ꮆ'), - (0xAB87, 'M', 'Ꮇ'), - (0xAB88, 'M', 'Ꮈ'), - (0xAB89, 'M', 'Ꮉ'), - (0xAB8A, 'M', 'Ꮊ'), - (0xAB8B, 'M', 'Ꮋ'), - (0xAB8C, 'M', 'Ꮌ'), - (0xAB8D, 'M', 'Ꮍ'), - (0xAB8E, 'M', 'Ꮎ'), - (0xAB8F, 'M', 'Ꮏ'), - (0xAB90, 'M', 'Ꮐ'), - (0xAB91, 'M', 'Ꮑ'), - (0xAB92, 'M', 'Ꮒ'), - (0xAB93, 'M', 'Ꮓ'), - (0xAB94, 'M', 'Ꮔ'), - (0xAB95, 'M', 'Ꮕ'), - (0xAB96, 'M', 'Ꮖ'), - (0xAB97, 'M', 'Ꮗ'), - (0xAB98, 'M', 'Ꮘ'), - (0xAB99, 'M', 'Ꮙ'), - (0xAB9A, 'M', 'Ꮚ'), - (0xAB9B, 'M', 'Ꮛ'), - (0xAB9C, 'M', 'Ꮜ'), - (0xAB9D, 'M', 'Ꮝ'), - (0xAB9E, 'M', 'Ꮞ'), - (0xAB9F, 'M', 'Ꮟ'), - (0xABA0, 'M', 'Ꮠ'), - (0xABA1, 'M', 'Ꮡ'), - (0xABA2, 'M', 'Ꮢ'), - (0xABA3, 'M', 'Ꮣ'), - (0xABA4, 'M', 'Ꮤ'), - (0xABA5, 'M', 'Ꮥ'), - (0xABA6, 'M', 'Ꮦ'), - (0xABA7, 'M', 'Ꮧ'), - (0xABA8, 'M', 'Ꮨ'), - (0xABA9, 'M', 'Ꮩ'), - (0xABAA, 'M', 'Ꮪ'), + (0xA95F, "V"), + (0xA97D, "X"), + (0xA980, "V"), + (0xA9CE, "X"), + (0xA9CF, "V"), + (0xA9DA, "X"), + (0xA9DE, "V"), + (0xA9FF, "X"), + (0xAA00, "V"), + (0xAA37, "X"), + (0xAA40, "V"), + (0xAA4E, "X"), + (0xAA50, "V"), + (0xAA5A, "X"), + (0xAA5C, "V"), + (0xAAC3, "X"), + (0xAADB, "V"), + (0xAAF7, "X"), + (0xAB01, "V"), + (0xAB07, "X"), + (0xAB09, "V"), + (0xAB0F, "X"), + (0xAB11, "V"), + (0xAB17, "X"), + (0xAB20, "V"), + (0xAB27, "X"), + (0xAB28, "V"), + (0xAB2F, "X"), + (0xAB30, "V"), + (0xAB5C, "M", "ꜧ"), + (0xAB5D, "M", "ꬷ"), + (0xAB5E, "M", "ɫ"), + (0xAB5F, "M", "ꭒ"), + (0xAB60, "V"), + (0xAB69, "M", "ʍ"), + (0xAB6A, "V"), + (0xAB6C, "X"), + (0xAB70, "M", "Ꭰ"), + (0xAB71, "M", "Ꭱ"), + (0xAB72, "M", "Ꭲ"), + (0xAB73, "M", "Ꭳ"), + (0xAB74, "M", "Ꭴ"), + (0xAB75, "M", "Ꭵ"), + (0xAB76, "M", "Ꭶ"), + (0xAB77, "M", "Ꭷ"), + (0xAB78, "M", "Ꭸ"), + (0xAB79, "M", "Ꭹ"), + (0xAB7A, "M", "Ꭺ"), + (0xAB7B, "M", "Ꭻ"), + (0xAB7C, "M", "Ꭼ"), + (0xAB7D, "M", "Ꭽ"), + (0xAB7E, "M", "Ꭾ"), + (0xAB7F, "M", "Ꭿ"), + (0xAB80, "M", "Ꮀ"), + (0xAB81, "M", "Ꮁ"), + (0xAB82, "M", "Ꮂ"), + (0xAB83, "M", "Ꮃ"), + (0xAB84, "M", "Ꮄ"), + (0xAB85, "M", "Ꮅ"), + (0xAB86, "M", "Ꮆ"), + (0xAB87, "M", "Ꮇ"), + (0xAB88, "M", "Ꮈ"), + (0xAB89, "M", "Ꮉ"), + (0xAB8A, "M", "Ꮊ"), + (0xAB8B, "M", "Ꮋ"), + (0xAB8C, "M", "Ꮌ"), + (0xAB8D, "M", "Ꮍ"), + (0xAB8E, "M", "Ꮎ"), + (0xAB8F, "M", "Ꮏ"), + (0xAB90, "M", "Ꮐ"), + (0xAB91, "M", "Ꮑ"), + (0xAB92, "M", "Ꮒ"), + (0xAB93, "M", "Ꮓ"), + (0xAB94, "M", "Ꮔ"), + (0xAB95, "M", "Ꮕ"), + (0xAB96, "M", "Ꮖ"), + (0xAB97, "M", "Ꮗ"), + (0xAB98, "M", "Ꮘ"), + (0xAB99, "M", "Ꮙ"), + (0xAB9A, "M", "Ꮚ"), + (0xAB9B, "M", "Ꮛ"), + (0xAB9C, "M", "Ꮜ"), + (0xAB9D, "M", "Ꮝ"), + (0xAB9E, "M", "Ꮞ"), + (0xAB9F, "M", "Ꮟ"), + (0xABA0, "M", "Ꮠ"), + (0xABA1, "M", "Ꮡ"), + (0xABA2, "M", "Ꮢ"), + (0xABA3, "M", "Ꮣ"), + (0xABA4, "M", "Ꮤ"), + (0xABA5, "M", "Ꮥ"), + (0xABA6, "M", "Ꮦ"), + (0xABA7, "M", "Ꮧ"), + (0xABA8, "M", "Ꮨ"), + (0xABA9, "M", "Ꮩ"), + (0xABAA, "M", "Ꮪ"), + (0xABAB, "M", "Ꮫ"), + (0xABAC, "M", "Ꮬ"), + (0xABAD, "M", "Ꮭ"), + (0xABAE, "M", "Ꮮ"), ] + def _seg_39() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xABAB, 'M', 'Ꮫ'), - (0xABAC, 'M', 'Ꮬ'), - (0xABAD, 'M', 'Ꮭ'), - (0xABAE, 'M', 'Ꮮ'), - (0xABAF, 'M', 'Ꮯ'), - (0xABB0, 'M', 'Ꮰ'), - (0xABB1, 'M', 'Ꮱ'), - (0xABB2, 'M', 'Ꮲ'), - (0xABB3, 'M', 'Ꮳ'), - (0xABB4, 'M', 'Ꮴ'), - (0xABB5, 'M', 'Ꮵ'), - (0xABB6, 'M', 'Ꮶ'), - (0xABB7, 'M', 'Ꮷ'), - (0xABB8, 'M', 'Ꮸ'), - (0xABB9, 'M', 'Ꮹ'), - (0xABBA, 'M', 'Ꮺ'), - (0xABBB, 'M', 'Ꮻ'), - (0xABBC, 'M', 'Ꮼ'), - (0xABBD, 'M', 'Ꮽ'), - (0xABBE, 'M', 'Ꮾ'), - (0xABBF, 'M', 'Ꮿ'), - (0xABC0, 'V'), - (0xABEE, 'X'), - (0xABF0, 'V'), - (0xABFA, 'X'), - (0xAC00, 'V'), - (0xD7A4, 'X'), - (0xD7B0, 'V'), - (0xD7C7, 'X'), - (0xD7CB, 'V'), - (0xD7FC, 'X'), - (0xF900, 'M', '豈'), - (0xF901, 'M', '更'), - (0xF902, 'M', '車'), - (0xF903, 'M', '賈'), - (0xF904, 'M', '滑'), - (0xF905, 'M', '串'), - (0xF906, 'M', '句'), - (0xF907, 'M', '龜'), - (0xF909, 'M', '契'), - (0xF90A, 'M', '金'), - (0xF90B, 'M', '喇'), - (0xF90C, 'M', '奈'), - (0xF90D, 'M', '懶'), - (0xF90E, 'M', '癩'), - (0xF90F, 'M', '羅'), - (0xF910, 'M', '蘿'), - (0xF911, 'M', '螺'), - (0xF912, 'M', '裸'), - (0xF913, 'M', '邏'), - (0xF914, 'M', '樂'), - (0xF915, 'M', '洛'), - (0xF916, 'M', '烙'), - (0xF917, 'M', '珞'), - (0xF918, 'M', '落'), - (0xF919, 'M', '酪'), - (0xF91A, 'M', '駱'), - (0xF91B, 'M', '亂'), - (0xF91C, 'M', '卵'), - (0xF91D, 'M', '欄'), - (0xF91E, 'M', '爛'), - (0xF91F, 'M', '蘭'), - (0xF920, 'M', '鸞'), - (0xF921, 'M', '嵐'), - (0xF922, 'M', '濫'), - (0xF923, 'M', '藍'), - (0xF924, 'M', '襤'), - (0xF925, 'M', '拉'), - (0xF926, 'M', '臘'), - (0xF927, 'M', '蠟'), - (0xF928, 'M', '廊'), - (0xF929, 'M', '朗'), - (0xF92A, 'M', '浪'), - (0xF92B, 'M', '狼'), - (0xF92C, 'M', '郎'), - (0xF92D, 'M', '來'), - (0xF92E, 'M', '冷'), - (0xF92F, 'M', '勞'), - (0xF930, 'M', '擄'), - (0xF931, 'M', '櫓'), - (0xF932, 'M', '爐'), - (0xF933, 'M', '盧'), - (0xF934, 'M', '老'), - (0xF935, 'M', '蘆'), - (0xF936, 'M', '虜'), - (0xF937, 'M', '路'), - (0xF938, 'M', '露'), - (0xF939, 'M', '魯'), - (0xF93A, 'M', '鷺'), - (0xF93B, 'M', '碌'), - (0xF93C, 'M', '祿'), - (0xF93D, 'M', '綠'), - (0xF93E, 'M', '菉'), - (0xF93F, 'M', '錄'), - (0xF940, 'M', '鹿'), - (0xF941, 'M', '論'), - (0xF942, 'M', '壟'), - (0xF943, 'M', '弄'), - (0xF944, 'M', '籠'), - (0xF945, 'M', '聾'), + (0xABAF, "M", "Ꮯ"), + (0xABB0, "M", "Ꮰ"), + (0xABB1, "M", "Ꮱ"), + (0xABB2, "M", "Ꮲ"), + (0xABB3, "M", "Ꮳ"), + (0xABB4, "M", "Ꮴ"), + (0xABB5, "M", "Ꮵ"), + (0xABB6, "M", "Ꮶ"), + (0xABB7, "M", "Ꮷ"), + (0xABB8, "M", "Ꮸ"), + (0xABB9, "M", "Ꮹ"), + (0xABBA, "M", "Ꮺ"), + (0xABBB, "M", "Ꮻ"), + (0xABBC, "M", "Ꮼ"), + (0xABBD, "M", "Ꮽ"), + (0xABBE, "M", "Ꮾ"), + (0xABBF, "M", "Ꮿ"), + (0xABC0, "V"), + (0xABEE, "X"), + (0xABF0, "V"), + (0xABFA, "X"), + (0xAC00, "V"), + (0xD7A4, "X"), + (0xD7B0, "V"), + (0xD7C7, "X"), + (0xD7CB, "V"), + (0xD7FC, "X"), + (0xF900, "M", "豈"), + (0xF901, "M", "更"), + (0xF902, "M", "車"), + (0xF903, "M", "賈"), + (0xF904, "M", "滑"), + (0xF905, "M", "串"), + (0xF906, "M", "句"), + (0xF907, "M", "龜"), + (0xF909, "M", "契"), + (0xF90A, "M", "金"), + (0xF90B, "M", "喇"), + (0xF90C, "M", "奈"), + (0xF90D, "M", "懶"), + (0xF90E, "M", "癩"), + (0xF90F, "M", "羅"), + (0xF910, "M", "蘿"), + (0xF911, "M", "螺"), + (0xF912, "M", "裸"), + (0xF913, "M", "邏"), + (0xF914, "M", "樂"), + (0xF915, "M", "洛"), + (0xF916, "M", "烙"), + (0xF917, "M", "珞"), + (0xF918, "M", "落"), + (0xF919, "M", "酪"), + (0xF91A, "M", "駱"), + (0xF91B, "M", "亂"), + (0xF91C, "M", "卵"), + (0xF91D, "M", "欄"), + (0xF91E, "M", "爛"), + (0xF91F, "M", "蘭"), + (0xF920, "M", "鸞"), + (0xF921, "M", "嵐"), + (0xF922, "M", "濫"), + (0xF923, "M", "藍"), + (0xF924, "M", "襤"), + (0xF925, "M", "拉"), + (0xF926, "M", "臘"), + (0xF927, "M", "蠟"), + (0xF928, "M", "廊"), + (0xF929, "M", "朗"), + (0xF92A, "M", "浪"), + (0xF92B, "M", "狼"), + (0xF92C, "M", "郎"), + (0xF92D, "M", "來"), + (0xF92E, "M", "冷"), + (0xF92F, "M", "勞"), + (0xF930, "M", "擄"), + (0xF931, "M", "櫓"), + (0xF932, "M", "爐"), + (0xF933, "M", "盧"), + (0xF934, "M", "老"), + (0xF935, "M", "蘆"), + (0xF936, "M", "虜"), + (0xF937, "M", "路"), + (0xF938, "M", "露"), + (0xF939, "M", "魯"), + (0xF93A, "M", "鷺"), + (0xF93B, "M", "碌"), + (0xF93C, "M", "祿"), + (0xF93D, "M", "綠"), + (0xF93E, "M", "菉"), + (0xF93F, "M", "錄"), + (0xF940, "M", "鹿"), + (0xF941, "M", "論"), + (0xF942, "M", "壟"), + (0xF943, "M", "弄"), + (0xF944, "M", "籠"), + (0xF945, "M", "聾"), + (0xF946, "M", "牢"), + (0xF947, "M", "磊"), + (0xF948, "M", "賂"), + (0xF949, "M", "雷"), ] + def _seg_40() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xF946, 'M', '牢'), - (0xF947, 'M', '磊'), - (0xF948, 'M', '賂'), - (0xF949, 'M', '雷'), - (0xF94A, 'M', '壘'), - (0xF94B, 'M', '屢'), - (0xF94C, 'M', '樓'), - (0xF94D, 'M', '淚'), - (0xF94E, 'M', '漏'), - (0xF94F, 'M', '累'), - (0xF950, 'M', '縷'), - (0xF951, 'M', '陋'), - (0xF952, 'M', '勒'), - (0xF953, 'M', '肋'), - (0xF954, 'M', '凜'), - (0xF955, 'M', '凌'), - (0xF956, 'M', '稜'), - (0xF957, 'M', '綾'), - (0xF958, 'M', '菱'), - (0xF959, 'M', '陵'), - (0xF95A, 'M', '讀'), - (0xF95B, 'M', '拏'), - (0xF95C, 'M', '樂'), - (0xF95D, 'M', '諾'), - (0xF95E, 'M', '丹'), - (0xF95F, 'M', '寧'), - (0xF960, 'M', '怒'), - (0xF961, 'M', '率'), - (0xF962, 'M', '異'), - (0xF963, 'M', '北'), - (0xF964, 'M', '磻'), - (0xF965, 'M', '便'), - (0xF966, 'M', '復'), - (0xF967, 'M', '不'), - (0xF968, 'M', '泌'), - (0xF969, 'M', '數'), - (0xF96A, 'M', '索'), - (0xF96B, 'M', '參'), - (0xF96C, 'M', '塞'), - (0xF96D, 'M', '省'), - (0xF96E, 'M', '葉'), - (0xF96F, 'M', '說'), - (0xF970, 'M', '殺'), - (0xF971, 'M', '辰'), - (0xF972, 'M', '沈'), - (0xF973, 'M', '拾'), - (0xF974, 'M', '若'), - (0xF975, 'M', '掠'), - (0xF976, 'M', '略'), - (0xF977, 'M', '亮'), - (0xF978, 'M', '兩'), - (0xF979, 'M', '凉'), - (0xF97A, 'M', '梁'), - (0xF97B, 'M', '糧'), - (0xF97C, 'M', '良'), - (0xF97D, 'M', '諒'), - (0xF97E, 'M', '量'), - (0xF97F, 'M', '勵'), - (0xF980, 'M', '呂'), - (0xF981, 'M', '女'), - (0xF982, 'M', '廬'), - (0xF983, 'M', '旅'), - (0xF984, 'M', '濾'), - (0xF985, 'M', '礪'), - (0xF986, 'M', '閭'), - (0xF987, 'M', '驪'), - (0xF988, 'M', '麗'), - (0xF989, 'M', '黎'), - (0xF98A, 'M', '力'), - (0xF98B, 'M', '曆'), - (0xF98C, 'M', '歷'), - (0xF98D, 'M', '轢'), - (0xF98E, 'M', '年'), - (0xF98F, 'M', '憐'), - (0xF990, 'M', '戀'), - (0xF991, 'M', '撚'), - (0xF992, 'M', '漣'), - (0xF993, 'M', '煉'), - (0xF994, 'M', '璉'), - (0xF995, 'M', '秊'), - (0xF996, 'M', '練'), - (0xF997, 'M', '聯'), - (0xF998, 'M', '輦'), - (0xF999, 'M', '蓮'), - (0xF99A, 'M', '連'), - (0xF99B, 'M', '鍊'), - (0xF99C, 'M', '列'), - (0xF99D, 'M', '劣'), - (0xF99E, 'M', '咽'), - (0xF99F, 'M', '烈'), - (0xF9A0, 'M', '裂'), - (0xF9A1, 'M', '說'), - (0xF9A2, 'M', '廉'), - (0xF9A3, 'M', '念'), - (0xF9A4, 'M', '捻'), - (0xF9A5, 'M', '殮'), - (0xF9A6, 'M', '簾'), - (0xF9A7, 'M', '獵'), - (0xF9A8, 'M', '令'), - (0xF9A9, 'M', '囹'), + (0xF94A, "M", "壘"), + (0xF94B, "M", "屢"), + (0xF94C, "M", "樓"), + (0xF94D, "M", "淚"), + (0xF94E, "M", "漏"), + (0xF94F, "M", "累"), + (0xF950, "M", "縷"), + (0xF951, "M", "陋"), + (0xF952, "M", "勒"), + (0xF953, "M", "肋"), + (0xF954, "M", "凜"), + (0xF955, "M", "凌"), + (0xF956, "M", "稜"), + (0xF957, "M", "綾"), + (0xF958, "M", "菱"), + (0xF959, "M", "陵"), + (0xF95A, "M", "讀"), + (0xF95B, "M", "拏"), + (0xF95C, "M", "樂"), + (0xF95D, "M", "諾"), + (0xF95E, "M", "丹"), + (0xF95F, "M", "寧"), + (0xF960, "M", "怒"), + (0xF961, "M", "率"), + (0xF962, "M", "異"), + (0xF963, "M", "北"), + (0xF964, "M", "磻"), + (0xF965, "M", "便"), + (0xF966, "M", "復"), + (0xF967, "M", "不"), + (0xF968, "M", "泌"), + (0xF969, "M", "數"), + (0xF96A, "M", "索"), + (0xF96B, "M", "參"), + (0xF96C, "M", "塞"), + (0xF96D, "M", "省"), + (0xF96E, "M", "葉"), + (0xF96F, "M", "說"), + (0xF970, "M", "殺"), + (0xF971, "M", "辰"), + (0xF972, "M", "沈"), + (0xF973, "M", "拾"), + (0xF974, "M", "若"), + (0xF975, "M", "掠"), + (0xF976, "M", "略"), + (0xF977, "M", "亮"), + (0xF978, "M", "兩"), + (0xF979, "M", "凉"), + (0xF97A, "M", "梁"), + (0xF97B, "M", "糧"), + (0xF97C, "M", "良"), + (0xF97D, "M", "諒"), + (0xF97E, "M", "量"), + (0xF97F, "M", "勵"), + (0xF980, "M", "呂"), + (0xF981, "M", "女"), + (0xF982, "M", "廬"), + (0xF983, "M", "旅"), + (0xF984, "M", "濾"), + (0xF985, "M", "礪"), + (0xF986, "M", "閭"), + (0xF987, "M", "驪"), + (0xF988, "M", "麗"), + (0xF989, "M", "黎"), + (0xF98A, "M", "力"), + (0xF98B, "M", "曆"), + (0xF98C, "M", "歷"), + (0xF98D, "M", "轢"), + (0xF98E, "M", "年"), + (0xF98F, "M", "憐"), + (0xF990, "M", "戀"), + (0xF991, "M", "撚"), + (0xF992, "M", "漣"), + (0xF993, "M", "煉"), + (0xF994, "M", "璉"), + (0xF995, "M", "秊"), + (0xF996, "M", "練"), + (0xF997, "M", "聯"), + (0xF998, "M", "輦"), + (0xF999, "M", "蓮"), + (0xF99A, "M", "連"), + (0xF99B, "M", "鍊"), + (0xF99C, "M", "列"), + (0xF99D, "M", "劣"), + (0xF99E, "M", "咽"), + (0xF99F, "M", "烈"), + (0xF9A0, "M", "裂"), + (0xF9A1, "M", "說"), + (0xF9A2, "M", "廉"), + (0xF9A3, "M", "念"), + (0xF9A4, "M", "捻"), + (0xF9A5, "M", "殮"), + (0xF9A6, "M", "簾"), + (0xF9A7, "M", "獵"), + (0xF9A8, "M", "令"), + (0xF9A9, "M", "囹"), + (0xF9AA, "M", "寧"), + (0xF9AB, "M", "嶺"), + (0xF9AC, "M", "怜"), + (0xF9AD, "M", "玲"), ] + def _seg_41() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xF9AA, 'M', '寧'), - (0xF9AB, 'M', '嶺'), - (0xF9AC, 'M', '怜'), - (0xF9AD, 'M', '玲'), - (0xF9AE, 'M', '瑩'), - (0xF9AF, 'M', '羚'), - (0xF9B0, 'M', '聆'), - (0xF9B1, 'M', '鈴'), - (0xF9B2, 'M', '零'), - (0xF9B3, 'M', '靈'), - (0xF9B4, 'M', '領'), - (0xF9B5, 'M', '例'), - (0xF9B6, 'M', '禮'), - (0xF9B7, 'M', '醴'), - (0xF9B8, 'M', '隸'), - (0xF9B9, 'M', '惡'), - (0xF9BA, 'M', '了'), - (0xF9BB, 'M', '僚'), - (0xF9BC, 'M', '寮'), - (0xF9BD, 'M', '尿'), - (0xF9BE, 'M', '料'), - (0xF9BF, 'M', '樂'), - (0xF9C0, 'M', '燎'), - (0xF9C1, 'M', '療'), - (0xF9C2, 'M', '蓼'), - (0xF9C3, 'M', '遼'), - (0xF9C4, 'M', '龍'), - (0xF9C5, 'M', '暈'), - (0xF9C6, 'M', '阮'), - (0xF9C7, 'M', '劉'), - (0xF9C8, 'M', '杻'), - (0xF9C9, 'M', '柳'), - (0xF9CA, 'M', '流'), - (0xF9CB, 'M', '溜'), - (0xF9CC, 'M', '琉'), - (0xF9CD, 'M', '留'), - (0xF9CE, 'M', '硫'), - (0xF9CF, 'M', '紐'), - (0xF9D0, 'M', '類'), - (0xF9D1, 'M', '六'), - (0xF9D2, 'M', '戮'), - (0xF9D3, 'M', '陸'), - (0xF9D4, 'M', '倫'), - (0xF9D5, 'M', '崙'), - (0xF9D6, 'M', '淪'), - (0xF9D7, 'M', '輪'), - (0xF9D8, 'M', '律'), - (0xF9D9, 'M', '慄'), - (0xF9DA, 'M', '栗'), - (0xF9DB, 'M', '率'), - (0xF9DC, 'M', '隆'), - (0xF9DD, 'M', '利'), - (0xF9DE, 'M', '吏'), - (0xF9DF, 'M', '履'), - (0xF9E0, 'M', '易'), - (0xF9E1, 'M', '李'), - (0xF9E2, 'M', '梨'), - (0xF9E3, 'M', '泥'), - (0xF9E4, 'M', '理'), - (0xF9E5, 'M', '痢'), - (0xF9E6, 'M', '罹'), - (0xF9E7, 'M', '裏'), - (0xF9E8, 'M', '裡'), - (0xF9E9, 'M', '里'), - (0xF9EA, 'M', '離'), - (0xF9EB, 'M', '匿'), - (0xF9EC, 'M', '溺'), - (0xF9ED, 'M', '吝'), - (0xF9EE, 'M', '燐'), - (0xF9EF, 'M', '璘'), - (0xF9F0, 'M', '藺'), - (0xF9F1, 'M', '隣'), - (0xF9F2, 'M', '鱗'), - (0xF9F3, 'M', '麟'), - (0xF9F4, 'M', '林'), - (0xF9F5, 'M', '淋'), - (0xF9F6, 'M', '臨'), - (0xF9F7, 'M', '立'), - (0xF9F8, 'M', '笠'), - (0xF9F9, 'M', '粒'), - (0xF9FA, 'M', '狀'), - (0xF9FB, 'M', '炙'), - (0xF9FC, 'M', '識'), - (0xF9FD, 'M', '什'), - (0xF9FE, 'M', '茶'), - (0xF9FF, 'M', '刺'), - (0xFA00, 'M', '切'), - (0xFA01, 'M', '度'), - (0xFA02, 'M', '拓'), - (0xFA03, 'M', '糖'), - (0xFA04, 'M', '宅'), - (0xFA05, 'M', '洞'), - (0xFA06, 'M', '暴'), - (0xFA07, 'M', '輻'), - (0xFA08, 'M', '行'), - (0xFA09, 'M', '降'), - (0xFA0A, 'M', '見'), - (0xFA0B, 'M', '廓'), - (0xFA0C, 'M', '兀'), - (0xFA0D, 'M', '嗀'), + (0xF9AE, "M", "瑩"), + (0xF9AF, "M", "羚"), + (0xF9B0, "M", "聆"), + (0xF9B1, "M", "鈴"), + (0xF9B2, "M", "零"), + (0xF9B3, "M", "靈"), + (0xF9B4, "M", "領"), + (0xF9B5, "M", "例"), + (0xF9B6, "M", "禮"), + (0xF9B7, "M", "醴"), + (0xF9B8, "M", "隸"), + (0xF9B9, "M", "惡"), + (0xF9BA, "M", "了"), + (0xF9BB, "M", "僚"), + (0xF9BC, "M", "寮"), + (0xF9BD, "M", "尿"), + (0xF9BE, "M", "料"), + (0xF9BF, "M", "樂"), + (0xF9C0, "M", "燎"), + (0xF9C1, "M", "療"), + (0xF9C2, "M", "蓼"), + (0xF9C3, "M", "遼"), + (0xF9C4, "M", "龍"), + (0xF9C5, "M", "暈"), + (0xF9C6, "M", "阮"), + (0xF9C7, "M", "劉"), + (0xF9C8, "M", "杻"), + (0xF9C9, "M", "柳"), + (0xF9CA, "M", "流"), + (0xF9CB, "M", "溜"), + (0xF9CC, "M", "琉"), + (0xF9CD, "M", "留"), + (0xF9CE, "M", "硫"), + (0xF9CF, "M", "紐"), + (0xF9D0, "M", "類"), + (0xF9D1, "M", "六"), + (0xF9D2, "M", "戮"), + (0xF9D3, "M", "陸"), + (0xF9D4, "M", "倫"), + (0xF9D5, "M", "崙"), + (0xF9D6, "M", "淪"), + (0xF9D7, "M", "輪"), + (0xF9D8, "M", "律"), + (0xF9D9, "M", "慄"), + (0xF9DA, "M", "栗"), + (0xF9DB, "M", "率"), + (0xF9DC, "M", "隆"), + (0xF9DD, "M", "利"), + (0xF9DE, "M", "吏"), + (0xF9DF, "M", "履"), + (0xF9E0, "M", "易"), + (0xF9E1, "M", "李"), + (0xF9E2, "M", "梨"), + (0xF9E3, "M", "泥"), + (0xF9E4, "M", "理"), + (0xF9E5, "M", "痢"), + (0xF9E6, "M", "罹"), + (0xF9E7, "M", "裏"), + (0xF9E8, "M", "裡"), + (0xF9E9, "M", "里"), + (0xF9EA, "M", "離"), + (0xF9EB, "M", "匿"), + (0xF9EC, "M", "溺"), + (0xF9ED, "M", "吝"), + (0xF9EE, "M", "燐"), + (0xF9EF, "M", "璘"), + (0xF9F0, "M", "藺"), + (0xF9F1, "M", "隣"), + (0xF9F2, "M", "鱗"), + (0xF9F3, "M", "麟"), + (0xF9F4, "M", "林"), + (0xF9F5, "M", "淋"), + (0xF9F6, "M", "臨"), + (0xF9F7, "M", "立"), + (0xF9F8, "M", "笠"), + (0xF9F9, "M", "粒"), + (0xF9FA, "M", "狀"), + (0xF9FB, "M", "炙"), + (0xF9FC, "M", "識"), + (0xF9FD, "M", "什"), + (0xF9FE, "M", "茶"), + (0xF9FF, "M", "刺"), + (0xFA00, "M", "切"), + (0xFA01, "M", "度"), + (0xFA02, "M", "拓"), + (0xFA03, "M", "糖"), + (0xFA04, "M", "宅"), + (0xFA05, "M", "洞"), + (0xFA06, "M", "暴"), + (0xFA07, "M", "輻"), + (0xFA08, "M", "行"), + (0xFA09, "M", "降"), + (0xFA0A, "M", "見"), + (0xFA0B, "M", "廓"), + (0xFA0C, "M", "兀"), + (0xFA0D, "M", "嗀"), + (0xFA0E, "V"), + (0xFA10, "M", "塚"), + (0xFA11, "V"), + (0xFA12, "M", "晴"), ] + def _seg_42() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFA0E, 'V'), - (0xFA10, 'M', '塚'), - (0xFA11, 'V'), - (0xFA12, 'M', '晴'), - (0xFA13, 'V'), - (0xFA15, 'M', '凞'), - (0xFA16, 'M', '猪'), - (0xFA17, 'M', '益'), - (0xFA18, 'M', '礼'), - (0xFA19, 'M', '神'), - (0xFA1A, 'M', '祥'), - (0xFA1B, 'M', '福'), - (0xFA1C, 'M', '靖'), - (0xFA1D, 'M', '精'), - (0xFA1E, 'M', '羽'), - (0xFA1F, 'V'), - (0xFA20, 'M', '蘒'), - (0xFA21, 'V'), - (0xFA22, 'M', '諸'), - (0xFA23, 'V'), - (0xFA25, 'M', '逸'), - (0xFA26, 'M', '都'), - (0xFA27, 'V'), - (0xFA2A, 'M', '飯'), - (0xFA2B, 'M', '飼'), - (0xFA2C, 'M', '館'), - (0xFA2D, 'M', '鶴'), - (0xFA2E, 'M', '郞'), - (0xFA2F, 'M', '隷'), - (0xFA30, 'M', '侮'), - (0xFA31, 'M', '僧'), - (0xFA32, 'M', '免'), - (0xFA33, 'M', '勉'), - (0xFA34, 'M', '勤'), - (0xFA35, 'M', '卑'), - (0xFA36, 'M', '喝'), - (0xFA37, 'M', '嘆'), - (0xFA38, 'M', '器'), - (0xFA39, 'M', '塀'), - (0xFA3A, 'M', '墨'), - (0xFA3B, 'M', '層'), - (0xFA3C, 'M', '屮'), - (0xFA3D, 'M', '悔'), - (0xFA3E, 'M', '慨'), - (0xFA3F, 'M', '憎'), - (0xFA40, 'M', '懲'), - (0xFA41, 'M', '敏'), - (0xFA42, 'M', '既'), - (0xFA43, 'M', '暑'), - (0xFA44, 'M', '梅'), - (0xFA45, 'M', '海'), - (0xFA46, 'M', '渚'), - (0xFA47, 'M', '漢'), - (0xFA48, 'M', '煮'), - (0xFA49, 'M', '爫'), - (0xFA4A, 'M', '琢'), - (0xFA4B, 'M', '碑'), - (0xFA4C, 'M', '社'), - (0xFA4D, 'M', '祉'), - (0xFA4E, 'M', '祈'), - (0xFA4F, 'M', '祐'), - (0xFA50, 'M', '祖'), - (0xFA51, 'M', '祝'), - (0xFA52, 'M', '禍'), - (0xFA53, 'M', '禎'), - (0xFA54, 'M', '穀'), - (0xFA55, 'M', '突'), - (0xFA56, 'M', '節'), - (0xFA57, 'M', '練'), - (0xFA58, 'M', '縉'), - (0xFA59, 'M', '繁'), - (0xFA5A, 'M', '署'), - (0xFA5B, 'M', '者'), - (0xFA5C, 'M', '臭'), - (0xFA5D, 'M', '艹'), - (0xFA5F, 'M', '著'), - (0xFA60, 'M', '褐'), - (0xFA61, 'M', '視'), - (0xFA62, 'M', '謁'), - (0xFA63, 'M', '謹'), - (0xFA64, 'M', '賓'), - (0xFA65, 'M', '贈'), - (0xFA66, 'M', '辶'), - (0xFA67, 'M', '逸'), - (0xFA68, 'M', '難'), - (0xFA69, 'M', '響'), - (0xFA6A, 'M', '頻'), - (0xFA6B, 'M', '恵'), - (0xFA6C, 'M', '𤋮'), - (0xFA6D, 'M', '舘'), - (0xFA6E, 'X'), - (0xFA70, 'M', '並'), - (0xFA71, 'M', '况'), - (0xFA72, 'M', '全'), - (0xFA73, 'M', '侀'), - (0xFA74, 'M', '充'), - (0xFA75, 'M', '冀'), - (0xFA76, 'M', '勇'), - (0xFA77, 'M', '勺'), - (0xFA78, 'M', '喝'), + (0xFA13, "V"), + (0xFA15, "M", "凞"), + (0xFA16, "M", "猪"), + (0xFA17, "M", "益"), + (0xFA18, "M", "礼"), + (0xFA19, "M", "神"), + (0xFA1A, "M", "祥"), + (0xFA1B, "M", "福"), + (0xFA1C, "M", "靖"), + (0xFA1D, "M", "精"), + (0xFA1E, "M", "羽"), + (0xFA1F, "V"), + (0xFA20, "M", "蘒"), + (0xFA21, "V"), + (0xFA22, "M", "諸"), + (0xFA23, "V"), + (0xFA25, "M", "逸"), + (0xFA26, "M", "都"), + (0xFA27, "V"), + (0xFA2A, "M", "飯"), + (0xFA2B, "M", "飼"), + (0xFA2C, "M", "館"), + (0xFA2D, "M", "鶴"), + (0xFA2E, "M", "郞"), + (0xFA2F, "M", "隷"), + (0xFA30, "M", "侮"), + (0xFA31, "M", "僧"), + (0xFA32, "M", "免"), + (0xFA33, "M", "勉"), + (0xFA34, "M", "勤"), + (0xFA35, "M", "卑"), + (0xFA36, "M", "喝"), + (0xFA37, "M", "嘆"), + (0xFA38, "M", "器"), + (0xFA39, "M", "塀"), + (0xFA3A, "M", "墨"), + (0xFA3B, "M", "層"), + (0xFA3C, "M", "屮"), + (0xFA3D, "M", "悔"), + (0xFA3E, "M", "慨"), + (0xFA3F, "M", "憎"), + (0xFA40, "M", "懲"), + (0xFA41, "M", "敏"), + (0xFA42, "M", "既"), + (0xFA43, "M", "暑"), + (0xFA44, "M", "梅"), + (0xFA45, "M", "海"), + (0xFA46, "M", "渚"), + (0xFA47, "M", "漢"), + (0xFA48, "M", "煮"), + (0xFA49, "M", "爫"), + (0xFA4A, "M", "琢"), + (0xFA4B, "M", "碑"), + (0xFA4C, "M", "社"), + (0xFA4D, "M", "祉"), + (0xFA4E, "M", "祈"), + (0xFA4F, "M", "祐"), + (0xFA50, "M", "祖"), + (0xFA51, "M", "祝"), + (0xFA52, "M", "禍"), + (0xFA53, "M", "禎"), + (0xFA54, "M", "穀"), + (0xFA55, "M", "突"), + (0xFA56, "M", "節"), + (0xFA57, "M", "練"), + (0xFA58, "M", "縉"), + (0xFA59, "M", "繁"), + (0xFA5A, "M", "署"), + (0xFA5B, "M", "者"), + (0xFA5C, "M", "臭"), + (0xFA5D, "M", "艹"), + (0xFA5F, "M", "著"), + (0xFA60, "M", "褐"), + (0xFA61, "M", "視"), + (0xFA62, "M", "謁"), + (0xFA63, "M", "謹"), + (0xFA64, "M", "賓"), + (0xFA65, "M", "贈"), + (0xFA66, "M", "辶"), + (0xFA67, "M", "逸"), + (0xFA68, "M", "難"), + (0xFA69, "M", "響"), + (0xFA6A, "M", "頻"), + (0xFA6B, "M", "恵"), + (0xFA6C, "M", "𤋮"), + (0xFA6D, "M", "舘"), + (0xFA6E, "X"), + (0xFA70, "M", "並"), + (0xFA71, "M", "况"), + (0xFA72, "M", "全"), + (0xFA73, "M", "侀"), + (0xFA74, "M", "充"), + (0xFA75, "M", "冀"), + (0xFA76, "M", "勇"), + (0xFA77, "M", "勺"), + (0xFA78, "M", "喝"), + (0xFA79, "M", "啕"), + (0xFA7A, "M", "喙"), + (0xFA7B, "M", "嗢"), + (0xFA7C, "M", "塚"), ] + def _seg_43() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFA79, 'M', '啕'), - (0xFA7A, 'M', '喙'), - (0xFA7B, 'M', '嗢'), - (0xFA7C, 'M', '塚'), - (0xFA7D, 'M', '墳'), - (0xFA7E, 'M', '奄'), - (0xFA7F, 'M', '奔'), - (0xFA80, 'M', '婢'), - (0xFA81, 'M', '嬨'), - (0xFA82, 'M', '廒'), - (0xFA83, 'M', '廙'), - (0xFA84, 'M', '彩'), - (0xFA85, 'M', '徭'), - (0xFA86, 'M', '惘'), - (0xFA87, 'M', '慎'), - (0xFA88, 'M', '愈'), - (0xFA89, 'M', '憎'), - (0xFA8A, 'M', '慠'), - (0xFA8B, 'M', '懲'), - (0xFA8C, 'M', '戴'), - (0xFA8D, 'M', '揄'), - (0xFA8E, 'M', '搜'), - (0xFA8F, 'M', '摒'), - (0xFA90, 'M', '敖'), - (0xFA91, 'M', '晴'), - (0xFA92, 'M', '朗'), - (0xFA93, 'M', '望'), - (0xFA94, 'M', '杖'), - (0xFA95, 'M', '歹'), - (0xFA96, 'M', '殺'), - (0xFA97, 'M', '流'), - (0xFA98, 'M', '滛'), - (0xFA99, 'M', '滋'), - (0xFA9A, 'M', '漢'), - (0xFA9B, 'M', '瀞'), - (0xFA9C, 'M', '煮'), - (0xFA9D, 'M', '瞧'), - (0xFA9E, 'M', '爵'), - (0xFA9F, 'M', '犯'), - (0xFAA0, 'M', '猪'), - (0xFAA1, 'M', '瑱'), - (0xFAA2, 'M', '甆'), - (0xFAA3, 'M', '画'), - (0xFAA4, 'M', '瘝'), - (0xFAA5, 'M', '瘟'), - (0xFAA6, 'M', '益'), - (0xFAA7, 'M', '盛'), - (0xFAA8, 'M', '直'), - (0xFAA9, 'M', '睊'), - (0xFAAA, 'M', '着'), - (0xFAAB, 'M', '磌'), - (0xFAAC, 'M', '窱'), - (0xFAAD, 'M', '節'), - (0xFAAE, 'M', '类'), - (0xFAAF, 'M', '絛'), - (0xFAB0, 'M', '練'), - (0xFAB1, 'M', '缾'), - (0xFAB2, 'M', '者'), - (0xFAB3, 'M', '荒'), - (0xFAB4, 'M', '華'), - (0xFAB5, 'M', '蝹'), - (0xFAB6, 'M', '襁'), - (0xFAB7, 'M', '覆'), - (0xFAB8, 'M', '視'), - (0xFAB9, 'M', '調'), - (0xFABA, 'M', '諸'), - (0xFABB, 'M', '請'), - (0xFABC, 'M', '謁'), - (0xFABD, 'M', '諾'), - (0xFABE, 'M', '諭'), - (0xFABF, 'M', '謹'), - (0xFAC0, 'M', '變'), - (0xFAC1, 'M', '贈'), - (0xFAC2, 'M', '輸'), - (0xFAC3, 'M', '遲'), - (0xFAC4, 'M', '醙'), - (0xFAC5, 'M', '鉶'), - (0xFAC6, 'M', '陼'), - (0xFAC7, 'M', '難'), - (0xFAC8, 'M', '靖'), - (0xFAC9, 'M', '韛'), - (0xFACA, 'M', '響'), - (0xFACB, 'M', '頋'), - (0xFACC, 'M', '頻'), - (0xFACD, 'M', '鬒'), - (0xFACE, 'M', '龜'), - (0xFACF, 'M', '𢡊'), - (0xFAD0, 'M', '𢡄'), - (0xFAD1, 'M', '𣏕'), - (0xFAD2, 'M', '㮝'), - (0xFAD3, 'M', '䀘'), - (0xFAD4, 'M', '䀹'), - (0xFAD5, 'M', '𥉉'), - (0xFAD6, 'M', '𥳐'), - (0xFAD7, 'M', '𧻓'), - (0xFAD8, 'M', '齃'), - (0xFAD9, 'M', '龎'), - (0xFADA, 'X'), - (0xFB00, 'M', 'ff'), - (0xFB01, 'M', 'fi'), + (0xFA7D, "M", "墳"), + (0xFA7E, "M", "奄"), + (0xFA7F, "M", "奔"), + (0xFA80, "M", "婢"), + (0xFA81, "M", "嬨"), + (0xFA82, "M", "廒"), + (0xFA83, "M", "廙"), + (0xFA84, "M", "彩"), + (0xFA85, "M", "徭"), + (0xFA86, "M", "惘"), + (0xFA87, "M", "慎"), + (0xFA88, "M", "愈"), + (0xFA89, "M", "憎"), + (0xFA8A, "M", "慠"), + (0xFA8B, "M", "懲"), + (0xFA8C, "M", "戴"), + (0xFA8D, "M", "揄"), + (0xFA8E, "M", "搜"), + (0xFA8F, "M", "摒"), + (0xFA90, "M", "敖"), + (0xFA91, "M", "晴"), + (0xFA92, "M", "朗"), + (0xFA93, "M", "望"), + (0xFA94, "M", "杖"), + (0xFA95, "M", "歹"), + (0xFA96, "M", "殺"), + (0xFA97, "M", "流"), + (0xFA98, "M", "滛"), + (0xFA99, "M", "滋"), + (0xFA9A, "M", "漢"), + (0xFA9B, "M", "瀞"), + (0xFA9C, "M", "煮"), + (0xFA9D, "M", "瞧"), + (0xFA9E, "M", "爵"), + (0xFA9F, "M", "犯"), + (0xFAA0, "M", "猪"), + (0xFAA1, "M", "瑱"), + (0xFAA2, "M", "甆"), + (0xFAA3, "M", "画"), + (0xFAA4, "M", "瘝"), + (0xFAA5, "M", "瘟"), + (0xFAA6, "M", "益"), + (0xFAA7, "M", "盛"), + (0xFAA8, "M", "直"), + (0xFAA9, "M", "睊"), + (0xFAAA, "M", "着"), + (0xFAAB, "M", "磌"), + (0xFAAC, "M", "窱"), + (0xFAAD, "M", "節"), + (0xFAAE, "M", "类"), + (0xFAAF, "M", "絛"), + (0xFAB0, "M", "練"), + (0xFAB1, "M", "缾"), + (0xFAB2, "M", "者"), + (0xFAB3, "M", "荒"), + (0xFAB4, "M", "華"), + (0xFAB5, "M", "蝹"), + (0xFAB6, "M", "襁"), + (0xFAB7, "M", "覆"), + (0xFAB8, "M", "視"), + (0xFAB9, "M", "調"), + (0xFABA, "M", "諸"), + (0xFABB, "M", "請"), + (0xFABC, "M", "謁"), + (0xFABD, "M", "諾"), + (0xFABE, "M", "諭"), + (0xFABF, "M", "謹"), + (0xFAC0, "M", "變"), + (0xFAC1, "M", "贈"), + (0xFAC2, "M", "輸"), + (0xFAC3, "M", "遲"), + (0xFAC4, "M", "醙"), + (0xFAC5, "M", "鉶"), + (0xFAC6, "M", "陼"), + (0xFAC7, "M", "難"), + (0xFAC8, "M", "靖"), + (0xFAC9, "M", "韛"), + (0xFACA, "M", "響"), + (0xFACB, "M", "頋"), + (0xFACC, "M", "頻"), + (0xFACD, "M", "鬒"), + (0xFACE, "M", "龜"), + (0xFACF, "M", "𢡊"), + (0xFAD0, "M", "𢡄"), + (0xFAD1, "M", "𣏕"), + (0xFAD2, "M", "㮝"), + (0xFAD3, "M", "䀘"), + (0xFAD4, "M", "䀹"), + (0xFAD5, "M", "𥉉"), + (0xFAD6, "M", "𥳐"), + (0xFAD7, "M", "𧻓"), + (0xFAD8, "M", "齃"), + (0xFAD9, "M", "龎"), + (0xFADA, "X"), + (0xFB00, "M", "ff"), + (0xFB01, "M", "fi"), + (0xFB02, "M", "fl"), + (0xFB03, "M", "ffi"), + (0xFB04, "M", "ffl"), + (0xFB05, "M", "st"), ] + def _seg_44() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFB02, 'M', 'fl'), - (0xFB03, 'M', 'ffi'), - (0xFB04, 'M', 'ffl'), - (0xFB05, 'M', 'st'), - (0xFB07, 'X'), - (0xFB13, 'M', 'մն'), - (0xFB14, 'M', 'մե'), - (0xFB15, 'M', 'մի'), - (0xFB16, 'M', 'վն'), - (0xFB17, 'M', 'մխ'), - (0xFB18, 'X'), - (0xFB1D, 'M', 'יִ'), - (0xFB1E, 'V'), - (0xFB1F, 'M', 'ײַ'), - (0xFB20, 'M', 'ע'), - (0xFB21, 'M', 'א'), - (0xFB22, 'M', 'ד'), - (0xFB23, 'M', 'ה'), - (0xFB24, 'M', 'כ'), - (0xFB25, 'M', 'ל'), - (0xFB26, 'M', 'ם'), - (0xFB27, 'M', 'ר'), - (0xFB28, 'M', 'ת'), - (0xFB29, '3', '+'), - (0xFB2A, 'M', 'שׁ'), - (0xFB2B, 'M', 'שׂ'), - (0xFB2C, 'M', 'שּׁ'), - (0xFB2D, 'M', 'שּׂ'), - (0xFB2E, 'M', 'אַ'), - (0xFB2F, 'M', 'אָ'), - (0xFB30, 'M', 'אּ'), - (0xFB31, 'M', 'בּ'), - (0xFB32, 'M', 'גּ'), - (0xFB33, 'M', 'דּ'), - (0xFB34, 'M', 'הּ'), - (0xFB35, 'M', 'וּ'), - (0xFB36, 'M', 'זּ'), - (0xFB37, 'X'), - (0xFB38, 'M', 'טּ'), - (0xFB39, 'M', 'יּ'), - (0xFB3A, 'M', 'ךּ'), - (0xFB3B, 'M', 'כּ'), - (0xFB3C, 'M', 'לּ'), - (0xFB3D, 'X'), - (0xFB3E, 'M', 'מּ'), - (0xFB3F, 'X'), - (0xFB40, 'M', 'נּ'), - (0xFB41, 'M', 'סּ'), - (0xFB42, 'X'), - (0xFB43, 'M', 'ףּ'), - (0xFB44, 'M', 'פּ'), - (0xFB45, 'X'), - (0xFB46, 'M', 'צּ'), - (0xFB47, 'M', 'קּ'), - (0xFB48, 'M', 'רּ'), - (0xFB49, 'M', 'שּ'), - (0xFB4A, 'M', 'תּ'), - (0xFB4B, 'M', 'וֹ'), - (0xFB4C, 'M', 'בֿ'), - (0xFB4D, 'M', 'כֿ'), - (0xFB4E, 'M', 'פֿ'), - (0xFB4F, 'M', 'אל'), - (0xFB50, 'M', 'ٱ'), - (0xFB52, 'M', 'ٻ'), - (0xFB56, 'M', 'پ'), - (0xFB5A, 'M', 'ڀ'), - (0xFB5E, 'M', 'ٺ'), - (0xFB62, 'M', 'ٿ'), - (0xFB66, 'M', 'ٹ'), - (0xFB6A, 'M', 'ڤ'), - (0xFB6E, 'M', 'ڦ'), - (0xFB72, 'M', 'ڄ'), - (0xFB76, 'M', 'ڃ'), - (0xFB7A, 'M', 'چ'), - (0xFB7E, 'M', 'ڇ'), - (0xFB82, 'M', 'ڍ'), - (0xFB84, 'M', 'ڌ'), - (0xFB86, 'M', 'ڎ'), - (0xFB88, 'M', 'ڈ'), - (0xFB8A, 'M', 'ژ'), - (0xFB8C, 'M', 'ڑ'), - (0xFB8E, 'M', 'ک'), - (0xFB92, 'M', 'گ'), - (0xFB96, 'M', 'ڳ'), - (0xFB9A, 'M', 'ڱ'), - (0xFB9E, 'M', 'ں'), - (0xFBA0, 'M', 'ڻ'), - (0xFBA4, 'M', 'ۀ'), - (0xFBA6, 'M', 'ہ'), - (0xFBAA, 'M', 'ھ'), - (0xFBAE, 'M', 'ے'), - (0xFBB0, 'M', 'ۓ'), - (0xFBB2, 'V'), - (0xFBC3, 'X'), - (0xFBD3, 'M', 'ڭ'), - (0xFBD7, 'M', 'ۇ'), - (0xFBD9, 'M', 'ۆ'), - (0xFBDB, 'M', 'ۈ'), - (0xFBDD, 'M', 'ۇٴ'), - (0xFBDE, 'M', 'ۋ'), + (0xFB07, "X"), + (0xFB13, "M", "մն"), + (0xFB14, "M", "մե"), + (0xFB15, "M", "մի"), + (0xFB16, "M", "վն"), + (0xFB17, "M", "մխ"), + (0xFB18, "X"), + (0xFB1D, "M", "יִ"), + (0xFB1E, "V"), + (0xFB1F, "M", "ײַ"), + (0xFB20, "M", "ע"), + (0xFB21, "M", "א"), + (0xFB22, "M", "ד"), + (0xFB23, "M", "ה"), + (0xFB24, "M", "כ"), + (0xFB25, "M", "ל"), + (0xFB26, "M", "ם"), + (0xFB27, "M", "ר"), + (0xFB28, "M", "ת"), + (0xFB29, "3", "+"), + (0xFB2A, "M", "שׁ"), + (0xFB2B, "M", "שׂ"), + (0xFB2C, "M", "שּׁ"), + (0xFB2D, "M", "שּׂ"), + (0xFB2E, "M", "אַ"), + (0xFB2F, "M", "אָ"), + (0xFB30, "M", "אּ"), + (0xFB31, "M", "בּ"), + (0xFB32, "M", "גּ"), + (0xFB33, "M", "דּ"), + (0xFB34, "M", "הּ"), + (0xFB35, "M", "וּ"), + (0xFB36, "M", "זּ"), + (0xFB37, "X"), + (0xFB38, "M", "טּ"), + (0xFB39, "M", "יּ"), + (0xFB3A, "M", "ךּ"), + (0xFB3B, "M", "כּ"), + (0xFB3C, "M", "לּ"), + (0xFB3D, "X"), + (0xFB3E, "M", "מּ"), + (0xFB3F, "X"), + (0xFB40, "M", "נּ"), + (0xFB41, "M", "סּ"), + (0xFB42, "X"), + (0xFB43, "M", "ףּ"), + (0xFB44, "M", "פּ"), + (0xFB45, "X"), + (0xFB46, "M", "צּ"), + (0xFB47, "M", "קּ"), + (0xFB48, "M", "רּ"), + (0xFB49, "M", "שּ"), + (0xFB4A, "M", "תּ"), + (0xFB4B, "M", "וֹ"), + (0xFB4C, "M", "בֿ"), + (0xFB4D, "M", "כֿ"), + (0xFB4E, "M", "פֿ"), + (0xFB4F, "M", "אל"), + (0xFB50, "M", "ٱ"), + (0xFB52, "M", "ٻ"), + (0xFB56, "M", "پ"), + (0xFB5A, "M", "ڀ"), + (0xFB5E, "M", "ٺ"), + (0xFB62, "M", "ٿ"), + (0xFB66, "M", "ٹ"), + (0xFB6A, "M", "ڤ"), + (0xFB6E, "M", "ڦ"), + (0xFB72, "M", "ڄ"), + (0xFB76, "M", "ڃ"), + (0xFB7A, "M", "چ"), + (0xFB7E, "M", "ڇ"), + (0xFB82, "M", "ڍ"), + (0xFB84, "M", "ڌ"), + (0xFB86, "M", "ڎ"), + (0xFB88, "M", "ڈ"), + (0xFB8A, "M", "ژ"), + (0xFB8C, "M", "ڑ"), + (0xFB8E, "M", "ک"), + (0xFB92, "M", "گ"), + (0xFB96, "M", "ڳ"), + (0xFB9A, "M", "ڱ"), + (0xFB9E, "M", "ں"), + (0xFBA0, "M", "ڻ"), + (0xFBA4, "M", "ۀ"), + (0xFBA6, "M", "ہ"), + (0xFBAA, "M", "ھ"), + (0xFBAE, "M", "ے"), + (0xFBB0, "M", "ۓ"), + (0xFBB2, "V"), + (0xFBC3, "X"), + (0xFBD3, "M", "ڭ"), + (0xFBD7, "M", "ۇ"), + (0xFBD9, "M", "ۆ"), + (0xFBDB, "M", "ۈ"), + (0xFBDD, "M", "ۇٴ"), + (0xFBDE, "M", "ۋ"), + (0xFBE0, "M", "ۅ"), + (0xFBE2, "M", "ۉ"), + (0xFBE4, "M", "ې"), + (0xFBE8, "M", "ى"), ] + def _seg_45() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFBE0, 'M', 'ۅ'), - (0xFBE2, 'M', 'ۉ'), - (0xFBE4, 'M', 'ې'), - (0xFBE8, 'M', 'ى'), - (0xFBEA, 'M', 'ئا'), - (0xFBEC, 'M', 'ئە'), - (0xFBEE, 'M', 'ئو'), - (0xFBF0, 'M', 'ئۇ'), - (0xFBF2, 'M', 'ئۆ'), - (0xFBF4, 'M', 'ئۈ'), - (0xFBF6, 'M', 'ئې'), - (0xFBF9, 'M', 'ئى'), - (0xFBFC, 'M', 'ی'), - (0xFC00, 'M', 'ئج'), - (0xFC01, 'M', 'ئح'), - (0xFC02, 'M', 'ئم'), - (0xFC03, 'M', 'ئى'), - (0xFC04, 'M', 'ئي'), - (0xFC05, 'M', 'بج'), - (0xFC06, 'M', 'بح'), - (0xFC07, 'M', 'بخ'), - (0xFC08, 'M', 'بم'), - (0xFC09, 'M', 'بى'), - (0xFC0A, 'M', 'بي'), - (0xFC0B, 'M', 'تج'), - (0xFC0C, 'M', 'تح'), - (0xFC0D, 'M', 'تخ'), - (0xFC0E, 'M', 'تم'), - (0xFC0F, 'M', 'تى'), - (0xFC10, 'M', 'تي'), - (0xFC11, 'M', 'ثج'), - (0xFC12, 'M', 'ثم'), - (0xFC13, 'M', 'ثى'), - (0xFC14, 'M', 'ثي'), - (0xFC15, 'M', 'جح'), - (0xFC16, 'M', 'جم'), - (0xFC17, 'M', 'حج'), - (0xFC18, 'M', 'حم'), - (0xFC19, 'M', 'خج'), - (0xFC1A, 'M', 'خح'), - (0xFC1B, 'M', 'خم'), - (0xFC1C, 'M', 'سج'), - (0xFC1D, 'M', 'سح'), - (0xFC1E, 'M', 'سخ'), - (0xFC1F, 'M', 'سم'), - (0xFC20, 'M', 'صح'), - (0xFC21, 'M', 'صم'), - (0xFC22, 'M', 'ضج'), - (0xFC23, 'M', 'ضح'), - (0xFC24, 'M', 'ضخ'), - (0xFC25, 'M', 'ضم'), - (0xFC26, 'M', 'طح'), - (0xFC27, 'M', 'طم'), - (0xFC28, 'M', 'ظم'), - (0xFC29, 'M', 'عج'), - (0xFC2A, 'M', 'عم'), - (0xFC2B, 'M', 'غج'), - (0xFC2C, 'M', 'غم'), - (0xFC2D, 'M', 'فج'), - (0xFC2E, 'M', 'فح'), - (0xFC2F, 'M', 'فخ'), - (0xFC30, 'M', 'فم'), - (0xFC31, 'M', 'فى'), - (0xFC32, 'M', 'في'), - (0xFC33, 'M', 'قح'), - (0xFC34, 'M', 'قم'), - (0xFC35, 'M', 'قى'), - (0xFC36, 'M', 'قي'), - (0xFC37, 'M', 'كا'), - (0xFC38, 'M', 'كج'), - (0xFC39, 'M', 'كح'), - (0xFC3A, 'M', 'كخ'), - (0xFC3B, 'M', 'كل'), - (0xFC3C, 'M', 'كم'), - (0xFC3D, 'M', 'كى'), - (0xFC3E, 'M', 'كي'), - (0xFC3F, 'M', 'لج'), - (0xFC40, 'M', 'لح'), - (0xFC41, 'M', 'لخ'), - (0xFC42, 'M', 'لم'), - (0xFC43, 'M', 'لى'), - (0xFC44, 'M', 'لي'), - (0xFC45, 'M', 'مج'), - (0xFC46, 'M', 'مح'), - (0xFC47, 'M', 'مخ'), - (0xFC48, 'M', 'مم'), - (0xFC49, 'M', 'مى'), - (0xFC4A, 'M', 'مي'), - (0xFC4B, 'M', 'نج'), - (0xFC4C, 'M', 'نح'), - (0xFC4D, 'M', 'نخ'), - (0xFC4E, 'M', 'نم'), - (0xFC4F, 'M', 'نى'), - (0xFC50, 'M', 'ني'), - (0xFC51, 'M', 'هج'), - (0xFC52, 'M', 'هم'), - (0xFC53, 'M', 'هى'), - (0xFC54, 'M', 'هي'), - (0xFC55, 'M', 'يج'), - (0xFC56, 'M', 'يح'), + (0xFBEA, "M", "ئا"), + (0xFBEC, "M", "ئە"), + (0xFBEE, "M", "ئو"), + (0xFBF0, "M", "ئۇ"), + (0xFBF2, "M", "ئۆ"), + (0xFBF4, "M", "ئۈ"), + (0xFBF6, "M", "ئې"), + (0xFBF9, "M", "ئى"), + (0xFBFC, "M", "ی"), + (0xFC00, "M", "ئج"), + (0xFC01, "M", "ئح"), + (0xFC02, "M", "ئم"), + (0xFC03, "M", "ئى"), + (0xFC04, "M", "ئي"), + (0xFC05, "M", "بج"), + (0xFC06, "M", "بح"), + (0xFC07, "M", "بخ"), + (0xFC08, "M", "بم"), + (0xFC09, "M", "بى"), + (0xFC0A, "M", "بي"), + (0xFC0B, "M", "تج"), + (0xFC0C, "M", "تح"), + (0xFC0D, "M", "تخ"), + (0xFC0E, "M", "تم"), + (0xFC0F, "M", "تى"), + (0xFC10, "M", "تي"), + (0xFC11, "M", "ثج"), + (0xFC12, "M", "ثم"), + (0xFC13, "M", "ثى"), + (0xFC14, "M", "ثي"), + (0xFC15, "M", "جح"), + (0xFC16, "M", "جم"), + (0xFC17, "M", "حج"), + (0xFC18, "M", "حم"), + (0xFC19, "M", "خج"), + (0xFC1A, "M", "خح"), + (0xFC1B, "M", "خم"), + (0xFC1C, "M", "سج"), + (0xFC1D, "M", "سح"), + (0xFC1E, "M", "سخ"), + (0xFC1F, "M", "سم"), + (0xFC20, "M", "صح"), + (0xFC21, "M", "صم"), + (0xFC22, "M", "ضج"), + (0xFC23, "M", "ضح"), + (0xFC24, "M", "ضخ"), + (0xFC25, "M", "ضم"), + (0xFC26, "M", "طح"), + (0xFC27, "M", "طم"), + (0xFC28, "M", "ظم"), + (0xFC29, "M", "عج"), + (0xFC2A, "M", "عم"), + (0xFC2B, "M", "غج"), + (0xFC2C, "M", "غم"), + (0xFC2D, "M", "فج"), + (0xFC2E, "M", "فح"), + (0xFC2F, "M", "فخ"), + (0xFC30, "M", "فم"), + (0xFC31, "M", "فى"), + (0xFC32, "M", "في"), + (0xFC33, "M", "قح"), + (0xFC34, "M", "قم"), + (0xFC35, "M", "قى"), + (0xFC36, "M", "قي"), + (0xFC37, "M", "كا"), + (0xFC38, "M", "كج"), + (0xFC39, "M", "كح"), + (0xFC3A, "M", "كخ"), + (0xFC3B, "M", "كل"), + (0xFC3C, "M", "كم"), + (0xFC3D, "M", "كى"), + (0xFC3E, "M", "كي"), + (0xFC3F, "M", "لج"), + (0xFC40, "M", "لح"), + (0xFC41, "M", "لخ"), + (0xFC42, "M", "لم"), + (0xFC43, "M", "لى"), + (0xFC44, "M", "لي"), + (0xFC45, "M", "مج"), + (0xFC46, "M", "مح"), + (0xFC47, "M", "مخ"), + (0xFC48, "M", "مم"), + (0xFC49, "M", "مى"), + (0xFC4A, "M", "مي"), + (0xFC4B, "M", "نج"), + (0xFC4C, "M", "نح"), + (0xFC4D, "M", "نخ"), + (0xFC4E, "M", "نم"), + (0xFC4F, "M", "نى"), + (0xFC50, "M", "ني"), + (0xFC51, "M", "هج"), + (0xFC52, "M", "هم"), + (0xFC53, "M", "هى"), + (0xFC54, "M", "هي"), + (0xFC55, "M", "يج"), + (0xFC56, "M", "يح"), + (0xFC57, "M", "يخ"), + (0xFC58, "M", "يم"), + (0xFC59, "M", "يى"), + (0xFC5A, "M", "يي"), ] + def _seg_46() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFC57, 'M', 'يخ'), - (0xFC58, 'M', 'يم'), - (0xFC59, 'M', 'يى'), - (0xFC5A, 'M', 'يي'), - (0xFC5B, 'M', 'ذٰ'), - (0xFC5C, 'M', 'رٰ'), - (0xFC5D, 'M', 'ىٰ'), - (0xFC5E, '3', ' ٌّ'), - (0xFC5F, '3', ' ٍّ'), - (0xFC60, '3', ' َّ'), - (0xFC61, '3', ' ُّ'), - (0xFC62, '3', ' ِّ'), - (0xFC63, '3', ' ّٰ'), - (0xFC64, 'M', 'ئر'), - (0xFC65, 'M', 'ئز'), - (0xFC66, 'M', 'ئم'), - (0xFC67, 'M', 'ئن'), - (0xFC68, 'M', 'ئى'), - (0xFC69, 'M', 'ئي'), - (0xFC6A, 'M', 'بر'), - (0xFC6B, 'M', 'بز'), - (0xFC6C, 'M', 'بم'), - (0xFC6D, 'M', 'بن'), - (0xFC6E, 'M', 'بى'), - (0xFC6F, 'M', 'بي'), - (0xFC70, 'M', 'تر'), - (0xFC71, 'M', 'تز'), - (0xFC72, 'M', 'تم'), - (0xFC73, 'M', 'تن'), - (0xFC74, 'M', 'تى'), - (0xFC75, 'M', 'تي'), - (0xFC76, 'M', 'ثر'), - (0xFC77, 'M', 'ثز'), - (0xFC78, 'M', 'ثم'), - (0xFC79, 'M', 'ثن'), - (0xFC7A, 'M', 'ثى'), - (0xFC7B, 'M', 'ثي'), - (0xFC7C, 'M', 'فى'), - (0xFC7D, 'M', 'في'), - (0xFC7E, 'M', 'قى'), - (0xFC7F, 'M', 'قي'), - (0xFC80, 'M', 'كا'), - (0xFC81, 'M', 'كل'), - (0xFC82, 'M', 'كم'), - (0xFC83, 'M', 'كى'), - (0xFC84, 'M', 'كي'), - (0xFC85, 'M', 'لم'), - (0xFC86, 'M', 'لى'), - (0xFC87, 'M', 'لي'), - (0xFC88, 'M', 'ما'), - (0xFC89, 'M', 'مم'), - (0xFC8A, 'M', 'نر'), - (0xFC8B, 'M', 'نز'), - (0xFC8C, 'M', 'نم'), - (0xFC8D, 'M', 'نن'), - (0xFC8E, 'M', 'نى'), - (0xFC8F, 'M', 'ني'), - (0xFC90, 'M', 'ىٰ'), - (0xFC91, 'M', 'ير'), - (0xFC92, 'M', 'يز'), - (0xFC93, 'M', 'يم'), - (0xFC94, 'M', 'ين'), - (0xFC95, 'M', 'يى'), - (0xFC96, 'M', 'يي'), - (0xFC97, 'M', 'ئج'), - (0xFC98, 'M', 'ئح'), - (0xFC99, 'M', 'ئخ'), - (0xFC9A, 'M', 'ئم'), - (0xFC9B, 'M', 'ئه'), - (0xFC9C, 'M', 'بج'), - (0xFC9D, 'M', 'بح'), - (0xFC9E, 'M', 'بخ'), - (0xFC9F, 'M', 'بم'), - (0xFCA0, 'M', 'به'), - (0xFCA1, 'M', 'تج'), - (0xFCA2, 'M', 'تح'), - (0xFCA3, 'M', 'تخ'), - (0xFCA4, 'M', 'تم'), - (0xFCA5, 'M', 'ته'), - (0xFCA6, 'M', 'ثم'), - (0xFCA7, 'M', 'جح'), - (0xFCA8, 'M', 'جم'), - (0xFCA9, 'M', 'حج'), - (0xFCAA, 'M', 'حم'), - (0xFCAB, 'M', 'خج'), - (0xFCAC, 'M', 'خم'), - (0xFCAD, 'M', 'سج'), - (0xFCAE, 'M', 'سح'), - (0xFCAF, 'M', 'سخ'), - (0xFCB0, 'M', 'سم'), - (0xFCB1, 'M', 'صح'), - (0xFCB2, 'M', 'صخ'), - (0xFCB3, 'M', 'صم'), - (0xFCB4, 'M', 'ضج'), - (0xFCB5, 'M', 'ضح'), - (0xFCB6, 'M', 'ضخ'), - (0xFCB7, 'M', 'ضم'), - (0xFCB8, 'M', 'طح'), - (0xFCB9, 'M', 'ظم'), - (0xFCBA, 'M', 'عج'), + (0xFC5B, "M", "ذٰ"), + (0xFC5C, "M", "رٰ"), + (0xFC5D, "M", "ىٰ"), + (0xFC5E, "3", " ٌّ"), + (0xFC5F, "3", " ٍّ"), + (0xFC60, "3", " َّ"), + (0xFC61, "3", " ُّ"), + (0xFC62, "3", " ِّ"), + (0xFC63, "3", " ّٰ"), + (0xFC64, "M", "ئر"), + (0xFC65, "M", "ئز"), + (0xFC66, "M", "ئم"), + (0xFC67, "M", "ئن"), + (0xFC68, "M", "ئى"), + (0xFC69, "M", "ئي"), + (0xFC6A, "M", "بر"), + (0xFC6B, "M", "بز"), + (0xFC6C, "M", "بم"), + (0xFC6D, "M", "بن"), + (0xFC6E, "M", "بى"), + (0xFC6F, "M", "بي"), + (0xFC70, "M", "تر"), + (0xFC71, "M", "تز"), + (0xFC72, "M", "تم"), + (0xFC73, "M", "تن"), + (0xFC74, "M", "تى"), + (0xFC75, "M", "تي"), + (0xFC76, "M", "ثر"), + (0xFC77, "M", "ثز"), + (0xFC78, "M", "ثم"), + (0xFC79, "M", "ثن"), + (0xFC7A, "M", "ثى"), + (0xFC7B, "M", "ثي"), + (0xFC7C, "M", "فى"), + (0xFC7D, "M", "في"), + (0xFC7E, "M", "قى"), + (0xFC7F, "M", "قي"), + (0xFC80, "M", "كا"), + (0xFC81, "M", "كل"), + (0xFC82, "M", "كم"), + (0xFC83, "M", "كى"), + (0xFC84, "M", "كي"), + (0xFC85, "M", "لم"), + (0xFC86, "M", "لى"), + (0xFC87, "M", "لي"), + (0xFC88, "M", "ما"), + (0xFC89, "M", "مم"), + (0xFC8A, "M", "نر"), + (0xFC8B, "M", "نز"), + (0xFC8C, "M", "نم"), + (0xFC8D, "M", "نن"), + (0xFC8E, "M", "نى"), + (0xFC8F, "M", "ني"), + (0xFC90, "M", "ىٰ"), + (0xFC91, "M", "ير"), + (0xFC92, "M", "يز"), + (0xFC93, "M", "يم"), + (0xFC94, "M", "ين"), + (0xFC95, "M", "يى"), + (0xFC96, "M", "يي"), + (0xFC97, "M", "ئج"), + (0xFC98, "M", "ئح"), + (0xFC99, "M", "ئخ"), + (0xFC9A, "M", "ئم"), + (0xFC9B, "M", "ئه"), + (0xFC9C, "M", "بج"), + (0xFC9D, "M", "بح"), + (0xFC9E, "M", "بخ"), + (0xFC9F, "M", "بم"), + (0xFCA0, "M", "به"), + (0xFCA1, "M", "تج"), + (0xFCA2, "M", "تح"), + (0xFCA3, "M", "تخ"), + (0xFCA4, "M", "تم"), + (0xFCA5, "M", "ته"), + (0xFCA6, "M", "ثم"), + (0xFCA7, "M", "جح"), + (0xFCA8, "M", "جم"), + (0xFCA9, "M", "حج"), + (0xFCAA, "M", "حم"), + (0xFCAB, "M", "خج"), + (0xFCAC, "M", "خم"), + (0xFCAD, "M", "سج"), + (0xFCAE, "M", "سح"), + (0xFCAF, "M", "سخ"), + (0xFCB0, "M", "سم"), + (0xFCB1, "M", "صح"), + (0xFCB2, "M", "صخ"), + (0xFCB3, "M", "صم"), + (0xFCB4, "M", "ضج"), + (0xFCB5, "M", "ضح"), + (0xFCB6, "M", "ضخ"), + (0xFCB7, "M", "ضم"), + (0xFCB8, "M", "طح"), + (0xFCB9, "M", "ظم"), + (0xFCBA, "M", "عج"), + (0xFCBB, "M", "عم"), + (0xFCBC, "M", "غج"), + (0xFCBD, "M", "غم"), + (0xFCBE, "M", "فج"), ] + def _seg_47() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFCBB, 'M', 'عم'), - (0xFCBC, 'M', 'غج'), - (0xFCBD, 'M', 'غم'), - (0xFCBE, 'M', 'فج'), - (0xFCBF, 'M', 'فح'), - (0xFCC0, 'M', 'فخ'), - (0xFCC1, 'M', 'فم'), - (0xFCC2, 'M', 'قح'), - (0xFCC3, 'M', 'قم'), - (0xFCC4, 'M', 'كج'), - (0xFCC5, 'M', 'كح'), - (0xFCC6, 'M', 'كخ'), - (0xFCC7, 'M', 'كل'), - (0xFCC8, 'M', 'كم'), - (0xFCC9, 'M', 'لج'), - (0xFCCA, 'M', 'لح'), - (0xFCCB, 'M', 'لخ'), - (0xFCCC, 'M', 'لم'), - (0xFCCD, 'M', 'له'), - (0xFCCE, 'M', 'مج'), - (0xFCCF, 'M', 'مح'), - (0xFCD0, 'M', 'مخ'), - (0xFCD1, 'M', 'مم'), - (0xFCD2, 'M', 'نج'), - (0xFCD3, 'M', 'نح'), - (0xFCD4, 'M', 'نخ'), - (0xFCD5, 'M', 'نم'), - (0xFCD6, 'M', 'نه'), - (0xFCD7, 'M', 'هج'), - (0xFCD8, 'M', 'هم'), - (0xFCD9, 'M', 'هٰ'), - (0xFCDA, 'M', 'يج'), - (0xFCDB, 'M', 'يح'), - (0xFCDC, 'M', 'يخ'), - (0xFCDD, 'M', 'يم'), - (0xFCDE, 'M', 'يه'), - (0xFCDF, 'M', 'ئم'), - (0xFCE0, 'M', 'ئه'), - (0xFCE1, 'M', 'بم'), - (0xFCE2, 'M', 'به'), - (0xFCE3, 'M', 'تم'), - (0xFCE4, 'M', 'ته'), - (0xFCE5, 'M', 'ثم'), - (0xFCE6, 'M', 'ثه'), - (0xFCE7, 'M', 'سم'), - (0xFCE8, 'M', 'سه'), - (0xFCE9, 'M', 'شم'), - (0xFCEA, 'M', 'شه'), - (0xFCEB, 'M', 'كل'), - (0xFCEC, 'M', 'كم'), - (0xFCED, 'M', 'لم'), - (0xFCEE, 'M', 'نم'), - (0xFCEF, 'M', 'نه'), - (0xFCF0, 'M', 'يم'), - (0xFCF1, 'M', 'يه'), - (0xFCF2, 'M', 'ـَّ'), - (0xFCF3, 'M', 'ـُّ'), - (0xFCF4, 'M', 'ـِّ'), - (0xFCF5, 'M', 'طى'), - (0xFCF6, 'M', 'طي'), - (0xFCF7, 'M', 'عى'), - (0xFCF8, 'M', 'عي'), - (0xFCF9, 'M', 'غى'), - (0xFCFA, 'M', 'غي'), - (0xFCFB, 'M', 'سى'), - (0xFCFC, 'M', 'سي'), - (0xFCFD, 'M', 'شى'), - (0xFCFE, 'M', 'شي'), - (0xFCFF, 'M', 'حى'), - (0xFD00, 'M', 'حي'), - (0xFD01, 'M', 'جى'), - (0xFD02, 'M', 'جي'), - (0xFD03, 'M', 'خى'), - (0xFD04, 'M', 'خي'), - (0xFD05, 'M', 'صى'), - (0xFD06, 'M', 'صي'), - (0xFD07, 'M', 'ضى'), - (0xFD08, 'M', 'ضي'), - (0xFD09, 'M', 'شج'), - (0xFD0A, 'M', 'شح'), - (0xFD0B, 'M', 'شخ'), - (0xFD0C, 'M', 'شم'), - (0xFD0D, 'M', 'شر'), - (0xFD0E, 'M', 'سر'), - (0xFD0F, 'M', 'صر'), - (0xFD10, 'M', 'ضر'), - (0xFD11, 'M', 'طى'), - (0xFD12, 'M', 'طي'), - (0xFD13, 'M', 'عى'), - (0xFD14, 'M', 'عي'), - (0xFD15, 'M', 'غى'), - (0xFD16, 'M', 'غي'), - (0xFD17, 'M', 'سى'), - (0xFD18, 'M', 'سي'), - (0xFD19, 'M', 'شى'), - (0xFD1A, 'M', 'شي'), - (0xFD1B, 'M', 'حى'), - (0xFD1C, 'M', 'حي'), - (0xFD1D, 'M', 'جى'), - (0xFD1E, 'M', 'جي'), + (0xFCBF, "M", "فح"), + (0xFCC0, "M", "فخ"), + (0xFCC1, "M", "فم"), + (0xFCC2, "M", "قح"), + (0xFCC3, "M", "قم"), + (0xFCC4, "M", "كج"), + (0xFCC5, "M", "كح"), + (0xFCC6, "M", "كخ"), + (0xFCC7, "M", "كل"), + (0xFCC8, "M", "كم"), + (0xFCC9, "M", "لج"), + (0xFCCA, "M", "لح"), + (0xFCCB, "M", "لخ"), + (0xFCCC, "M", "لم"), + (0xFCCD, "M", "له"), + (0xFCCE, "M", "مج"), + (0xFCCF, "M", "مح"), + (0xFCD0, "M", "مخ"), + (0xFCD1, "M", "مم"), + (0xFCD2, "M", "نج"), + (0xFCD3, "M", "نح"), + (0xFCD4, "M", "نخ"), + (0xFCD5, "M", "نم"), + (0xFCD6, "M", "نه"), + (0xFCD7, "M", "هج"), + (0xFCD8, "M", "هم"), + (0xFCD9, "M", "هٰ"), + (0xFCDA, "M", "يج"), + (0xFCDB, "M", "يح"), + (0xFCDC, "M", "يخ"), + (0xFCDD, "M", "يم"), + (0xFCDE, "M", "يه"), + (0xFCDF, "M", "ئم"), + (0xFCE0, "M", "ئه"), + (0xFCE1, "M", "بم"), + (0xFCE2, "M", "به"), + (0xFCE3, "M", "تم"), + (0xFCE4, "M", "ته"), + (0xFCE5, "M", "ثم"), + (0xFCE6, "M", "ثه"), + (0xFCE7, "M", "سم"), + (0xFCE8, "M", "سه"), + (0xFCE9, "M", "شم"), + (0xFCEA, "M", "شه"), + (0xFCEB, "M", "كل"), + (0xFCEC, "M", "كم"), + (0xFCED, "M", "لم"), + (0xFCEE, "M", "نم"), + (0xFCEF, "M", "نه"), + (0xFCF0, "M", "يم"), + (0xFCF1, "M", "يه"), + (0xFCF2, "M", "ـَّ"), + (0xFCF3, "M", "ـُّ"), + (0xFCF4, "M", "ـِّ"), + (0xFCF5, "M", "طى"), + (0xFCF6, "M", "طي"), + (0xFCF7, "M", "عى"), + (0xFCF8, "M", "عي"), + (0xFCF9, "M", "غى"), + (0xFCFA, "M", "غي"), + (0xFCFB, "M", "سى"), + (0xFCFC, "M", "سي"), + (0xFCFD, "M", "شى"), + (0xFCFE, "M", "شي"), + (0xFCFF, "M", "حى"), + (0xFD00, "M", "حي"), + (0xFD01, "M", "جى"), + (0xFD02, "M", "جي"), + (0xFD03, "M", "خى"), + (0xFD04, "M", "خي"), + (0xFD05, "M", "صى"), + (0xFD06, "M", "صي"), + (0xFD07, "M", "ضى"), + (0xFD08, "M", "ضي"), + (0xFD09, "M", "شج"), + (0xFD0A, "M", "شح"), + (0xFD0B, "M", "شخ"), + (0xFD0C, "M", "شم"), + (0xFD0D, "M", "شر"), + (0xFD0E, "M", "سر"), + (0xFD0F, "M", "صر"), + (0xFD10, "M", "ضر"), + (0xFD11, "M", "طى"), + (0xFD12, "M", "طي"), + (0xFD13, "M", "عى"), + (0xFD14, "M", "عي"), + (0xFD15, "M", "غى"), + (0xFD16, "M", "غي"), + (0xFD17, "M", "سى"), + (0xFD18, "M", "سي"), + (0xFD19, "M", "شى"), + (0xFD1A, "M", "شي"), + (0xFD1B, "M", "حى"), + (0xFD1C, "M", "حي"), + (0xFD1D, "M", "جى"), + (0xFD1E, "M", "جي"), + (0xFD1F, "M", "خى"), + (0xFD20, "M", "خي"), + (0xFD21, "M", "صى"), + (0xFD22, "M", "صي"), ] + def _seg_48() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFD1F, 'M', 'خى'), - (0xFD20, 'M', 'خي'), - (0xFD21, 'M', 'صى'), - (0xFD22, 'M', 'صي'), - (0xFD23, 'M', 'ضى'), - (0xFD24, 'M', 'ضي'), - (0xFD25, 'M', 'شج'), - (0xFD26, 'M', 'شح'), - (0xFD27, 'M', 'شخ'), - (0xFD28, 'M', 'شم'), - (0xFD29, 'M', 'شر'), - (0xFD2A, 'M', 'سر'), - (0xFD2B, 'M', 'صر'), - (0xFD2C, 'M', 'ضر'), - (0xFD2D, 'M', 'شج'), - (0xFD2E, 'M', 'شح'), - (0xFD2F, 'M', 'شخ'), - (0xFD30, 'M', 'شم'), - (0xFD31, 'M', 'سه'), - (0xFD32, 'M', 'شه'), - (0xFD33, 'M', 'طم'), - (0xFD34, 'M', 'سج'), - (0xFD35, 'M', 'سح'), - (0xFD36, 'M', 'سخ'), - (0xFD37, 'M', 'شج'), - (0xFD38, 'M', 'شح'), - (0xFD39, 'M', 'شخ'), - (0xFD3A, 'M', 'طم'), - (0xFD3B, 'M', 'ظم'), - (0xFD3C, 'M', 'اً'), - (0xFD3E, 'V'), - (0xFD50, 'M', 'تجم'), - (0xFD51, 'M', 'تحج'), - (0xFD53, 'M', 'تحم'), - (0xFD54, 'M', 'تخم'), - (0xFD55, 'M', 'تمج'), - (0xFD56, 'M', 'تمح'), - (0xFD57, 'M', 'تمخ'), - (0xFD58, 'M', 'جمح'), - (0xFD5A, 'M', 'حمي'), - (0xFD5B, 'M', 'حمى'), - (0xFD5C, 'M', 'سحج'), - (0xFD5D, 'M', 'سجح'), - (0xFD5E, 'M', 'سجى'), - (0xFD5F, 'M', 'سمح'), - (0xFD61, 'M', 'سمج'), - (0xFD62, 'M', 'سمم'), - (0xFD64, 'M', 'صحح'), - (0xFD66, 'M', 'صمم'), - (0xFD67, 'M', 'شحم'), - (0xFD69, 'M', 'شجي'), - (0xFD6A, 'M', 'شمخ'), - (0xFD6C, 'M', 'شمم'), - (0xFD6E, 'M', 'ضحى'), - (0xFD6F, 'M', 'ضخم'), - (0xFD71, 'M', 'طمح'), - (0xFD73, 'M', 'طمم'), - (0xFD74, 'M', 'طمي'), - (0xFD75, 'M', 'عجم'), - (0xFD76, 'M', 'عمم'), - (0xFD78, 'M', 'عمى'), - (0xFD79, 'M', 'غمم'), - (0xFD7A, 'M', 'غمي'), - (0xFD7B, 'M', 'غمى'), - (0xFD7C, 'M', 'فخم'), - (0xFD7E, 'M', 'قمح'), - (0xFD7F, 'M', 'قمم'), - (0xFD80, 'M', 'لحم'), - (0xFD81, 'M', 'لحي'), - (0xFD82, 'M', 'لحى'), - (0xFD83, 'M', 'لجج'), - (0xFD85, 'M', 'لخم'), - (0xFD87, 'M', 'لمح'), - (0xFD89, 'M', 'محج'), - (0xFD8A, 'M', 'محم'), - (0xFD8B, 'M', 'محي'), - (0xFD8C, 'M', 'مجح'), - (0xFD8D, 'M', 'مجم'), - (0xFD8E, 'M', 'مخج'), - (0xFD8F, 'M', 'مخم'), - (0xFD90, 'X'), - (0xFD92, 'M', 'مجخ'), - (0xFD93, 'M', 'همج'), - (0xFD94, 'M', 'همم'), - (0xFD95, 'M', 'نحم'), - (0xFD96, 'M', 'نحى'), - (0xFD97, 'M', 'نجم'), - (0xFD99, 'M', 'نجى'), - (0xFD9A, 'M', 'نمي'), - (0xFD9B, 'M', 'نمى'), - (0xFD9C, 'M', 'يمم'), - (0xFD9E, 'M', 'بخي'), - (0xFD9F, 'M', 'تجي'), - (0xFDA0, 'M', 'تجى'), - (0xFDA1, 'M', 'تخي'), - (0xFDA2, 'M', 'تخى'), - (0xFDA3, 'M', 'تمي'), - (0xFDA4, 'M', 'تمى'), - (0xFDA5, 'M', 'جمي'), - (0xFDA6, 'M', 'جحى'), + (0xFD23, "M", "ضى"), + (0xFD24, "M", "ضي"), + (0xFD25, "M", "شج"), + (0xFD26, "M", "شح"), + (0xFD27, "M", "شخ"), + (0xFD28, "M", "شم"), + (0xFD29, "M", "شر"), + (0xFD2A, "M", "سر"), + (0xFD2B, "M", "صر"), + (0xFD2C, "M", "ضر"), + (0xFD2D, "M", "شج"), + (0xFD2E, "M", "شح"), + (0xFD2F, "M", "شخ"), + (0xFD30, "M", "شم"), + (0xFD31, "M", "سه"), + (0xFD32, "M", "شه"), + (0xFD33, "M", "طم"), + (0xFD34, "M", "سج"), + (0xFD35, "M", "سح"), + (0xFD36, "M", "سخ"), + (0xFD37, "M", "شج"), + (0xFD38, "M", "شح"), + (0xFD39, "M", "شخ"), + (0xFD3A, "M", "طم"), + (0xFD3B, "M", "ظم"), + (0xFD3C, "M", "اً"), + (0xFD3E, "V"), + (0xFD50, "M", "تجم"), + (0xFD51, "M", "تحج"), + (0xFD53, "M", "تحم"), + (0xFD54, "M", "تخم"), + (0xFD55, "M", "تمج"), + (0xFD56, "M", "تمح"), + (0xFD57, "M", "تمخ"), + (0xFD58, "M", "جمح"), + (0xFD5A, "M", "حمي"), + (0xFD5B, "M", "حمى"), + (0xFD5C, "M", "سحج"), + (0xFD5D, "M", "سجح"), + (0xFD5E, "M", "سجى"), + (0xFD5F, "M", "سمح"), + (0xFD61, "M", "سمج"), + (0xFD62, "M", "سمم"), + (0xFD64, "M", "صحح"), + (0xFD66, "M", "صمم"), + (0xFD67, "M", "شحم"), + (0xFD69, "M", "شجي"), + (0xFD6A, "M", "شمخ"), + (0xFD6C, "M", "شمم"), + (0xFD6E, "M", "ضحى"), + (0xFD6F, "M", "ضخم"), + (0xFD71, "M", "طمح"), + (0xFD73, "M", "طمم"), + (0xFD74, "M", "طمي"), + (0xFD75, "M", "عجم"), + (0xFD76, "M", "عمم"), + (0xFD78, "M", "عمى"), + (0xFD79, "M", "غمم"), + (0xFD7A, "M", "غمي"), + (0xFD7B, "M", "غمى"), + (0xFD7C, "M", "فخم"), + (0xFD7E, "M", "قمح"), + (0xFD7F, "M", "قمم"), + (0xFD80, "M", "لحم"), + (0xFD81, "M", "لحي"), + (0xFD82, "M", "لحى"), + (0xFD83, "M", "لجج"), + (0xFD85, "M", "لخم"), + (0xFD87, "M", "لمح"), + (0xFD89, "M", "محج"), + (0xFD8A, "M", "محم"), + (0xFD8B, "M", "محي"), + (0xFD8C, "M", "مجح"), + (0xFD8D, "M", "مجم"), + (0xFD8E, "M", "مخج"), + (0xFD8F, "M", "مخم"), + (0xFD90, "X"), + (0xFD92, "M", "مجخ"), + (0xFD93, "M", "همج"), + (0xFD94, "M", "همم"), + (0xFD95, "M", "نحم"), + (0xFD96, "M", "نحى"), + (0xFD97, "M", "نجم"), + (0xFD99, "M", "نجى"), + (0xFD9A, "M", "نمي"), + (0xFD9B, "M", "نمى"), + (0xFD9C, "M", "يمم"), + (0xFD9E, "M", "بخي"), + (0xFD9F, "M", "تجي"), + (0xFDA0, "M", "تجى"), + (0xFDA1, "M", "تخي"), + (0xFDA2, "M", "تخى"), + (0xFDA3, "M", "تمي"), + (0xFDA4, "M", "تمى"), + (0xFDA5, "M", "جمي"), + (0xFDA6, "M", "جحى"), + (0xFDA7, "M", "جمى"), + (0xFDA8, "M", "سخى"), + (0xFDA9, "M", "صحي"), + (0xFDAA, "M", "شحي"), ] + def _seg_49() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFDA7, 'M', 'جمى'), - (0xFDA8, 'M', 'سخى'), - (0xFDA9, 'M', 'صحي'), - (0xFDAA, 'M', 'شحي'), - (0xFDAB, 'M', 'ضحي'), - (0xFDAC, 'M', 'لجي'), - (0xFDAD, 'M', 'لمي'), - (0xFDAE, 'M', 'يحي'), - (0xFDAF, 'M', 'يجي'), - (0xFDB0, 'M', 'يمي'), - (0xFDB1, 'M', 'ممي'), - (0xFDB2, 'M', 'قمي'), - (0xFDB3, 'M', 'نحي'), - (0xFDB4, 'M', 'قمح'), - (0xFDB5, 'M', 'لحم'), - (0xFDB6, 'M', 'عمي'), - (0xFDB7, 'M', 'كمي'), - (0xFDB8, 'M', 'نجح'), - (0xFDB9, 'M', 'مخي'), - (0xFDBA, 'M', 'لجم'), - (0xFDBB, 'M', 'كمم'), - (0xFDBC, 'M', 'لجم'), - (0xFDBD, 'M', 'نجح'), - (0xFDBE, 'M', 'جحي'), - (0xFDBF, 'M', 'حجي'), - (0xFDC0, 'M', 'مجي'), - (0xFDC1, 'M', 'فمي'), - (0xFDC2, 'M', 'بحي'), - (0xFDC3, 'M', 'كمم'), - (0xFDC4, 'M', 'عجم'), - (0xFDC5, 'M', 'صمم'), - (0xFDC6, 'M', 'سخي'), - (0xFDC7, 'M', 'نجي'), - (0xFDC8, 'X'), - (0xFDCF, 'V'), - (0xFDD0, 'X'), - (0xFDF0, 'M', 'صلے'), - (0xFDF1, 'M', 'قلے'), - (0xFDF2, 'M', 'الله'), - (0xFDF3, 'M', 'اكبر'), - (0xFDF4, 'M', 'محمد'), - (0xFDF5, 'M', 'صلعم'), - (0xFDF6, 'M', 'رسول'), - (0xFDF7, 'M', 'عليه'), - (0xFDF8, 'M', 'وسلم'), - (0xFDF9, 'M', 'صلى'), - (0xFDFA, '3', 'صلى الله عليه وسلم'), - (0xFDFB, '3', 'جل جلاله'), - (0xFDFC, 'M', 'ریال'), - (0xFDFD, 'V'), - (0xFE00, 'I'), - (0xFE10, '3', ','), - (0xFE11, 'M', '、'), - (0xFE12, 'X'), - (0xFE13, '3', ':'), - (0xFE14, '3', ';'), - (0xFE15, '3', '!'), - (0xFE16, '3', '?'), - (0xFE17, 'M', '〖'), - (0xFE18, 'M', '〗'), - (0xFE19, 'X'), - (0xFE20, 'V'), - (0xFE30, 'X'), - (0xFE31, 'M', '—'), - (0xFE32, 'M', '–'), - (0xFE33, '3', '_'), - (0xFE35, '3', '('), - (0xFE36, '3', ')'), - (0xFE37, '3', '{'), - (0xFE38, '3', '}'), - (0xFE39, 'M', '〔'), - (0xFE3A, 'M', '〕'), - (0xFE3B, 'M', '【'), - (0xFE3C, 'M', '】'), - (0xFE3D, 'M', '《'), - (0xFE3E, 'M', '》'), - (0xFE3F, 'M', '〈'), - (0xFE40, 'M', '〉'), - (0xFE41, 'M', '「'), - (0xFE42, 'M', '」'), - (0xFE43, 'M', '『'), - (0xFE44, 'M', '』'), - (0xFE45, 'V'), - (0xFE47, '3', '['), - (0xFE48, '3', ']'), - (0xFE49, '3', ' ̅'), - (0xFE4D, '3', '_'), - (0xFE50, '3', ','), - (0xFE51, 'M', '、'), - (0xFE52, 'X'), - (0xFE54, '3', ';'), - (0xFE55, '3', ':'), - (0xFE56, '3', '?'), - (0xFE57, '3', '!'), - (0xFE58, 'M', '—'), - (0xFE59, '3', '('), - (0xFE5A, '3', ')'), - (0xFE5B, '3', '{'), - (0xFE5C, '3', '}'), - (0xFE5D, 'M', '〔'), + (0xFDAB, "M", "ضحي"), + (0xFDAC, "M", "لجي"), + (0xFDAD, "M", "لمي"), + (0xFDAE, "M", "يحي"), + (0xFDAF, "M", "يجي"), + (0xFDB0, "M", "يمي"), + (0xFDB1, "M", "ممي"), + (0xFDB2, "M", "قمي"), + (0xFDB3, "M", "نحي"), + (0xFDB4, "M", "قمح"), + (0xFDB5, "M", "لحم"), + (0xFDB6, "M", "عمي"), + (0xFDB7, "M", "كمي"), + (0xFDB8, "M", "نجح"), + (0xFDB9, "M", "مخي"), + (0xFDBA, "M", "لجم"), + (0xFDBB, "M", "كمم"), + (0xFDBC, "M", "لجم"), + (0xFDBD, "M", "نجح"), + (0xFDBE, "M", "جحي"), + (0xFDBF, "M", "حجي"), + (0xFDC0, "M", "مجي"), + (0xFDC1, "M", "فمي"), + (0xFDC2, "M", "بحي"), + (0xFDC3, "M", "كمم"), + (0xFDC4, "M", "عجم"), + (0xFDC5, "M", "صمم"), + (0xFDC6, "M", "سخي"), + (0xFDC7, "M", "نجي"), + (0xFDC8, "X"), + (0xFDCF, "V"), + (0xFDD0, "X"), + (0xFDF0, "M", "صلے"), + (0xFDF1, "M", "قلے"), + (0xFDF2, "M", "الله"), + (0xFDF3, "M", "اكبر"), + (0xFDF4, "M", "محمد"), + (0xFDF5, "M", "صلعم"), + (0xFDF6, "M", "رسول"), + (0xFDF7, "M", "عليه"), + (0xFDF8, "M", "وسلم"), + (0xFDF9, "M", "صلى"), + (0xFDFA, "3", "صلى الله عليه وسلم"), + (0xFDFB, "3", "جل جلاله"), + (0xFDFC, "M", "ریال"), + (0xFDFD, "V"), + (0xFE00, "I"), + (0xFE10, "3", ","), + (0xFE11, "M", "、"), + (0xFE12, "X"), + (0xFE13, "3", ":"), + (0xFE14, "3", ";"), + (0xFE15, "3", "!"), + (0xFE16, "3", "?"), + (0xFE17, "M", "〖"), + (0xFE18, "M", "〗"), + (0xFE19, "X"), + (0xFE20, "V"), + (0xFE30, "X"), + (0xFE31, "M", "—"), + (0xFE32, "M", "–"), + (0xFE33, "3", "_"), + (0xFE35, "3", "("), + (0xFE36, "3", ")"), + (0xFE37, "3", "{"), + (0xFE38, "3", "}"), + (0xFE39, "M", "〔"), + (0xFE3A, "M", "〕"), + (0xFE3B, "M", "【"), + (0xFE3C, "M", "】"), + (0xFE3D, "M", "《"), + (0xFE3E, "M", "》"), + (0xFE3F, "M", "〈"), + (0xFE40, "M", "〉"), + (0xFE41, "M", "「"), + (0xFE42, "M", "」"), + (0xFE43, "M", "『"), + (0xFE44, "M", "』"), + (0xFE45, "V"), + (0xFE47, "3", "["), + (0xFE48, "3", "]"), + (0xFE49, "3", " ̅"), + (0xFE4D, "3", "_"), + (0xFE50, "3", ","), + (0xFE51, "M", "、"), + (0xFE52, "X"), + (0xFE54, "3", ";"), + (0xFE55, "3", ":"), + (0xFE56, "3", "?"), + (0xFE57, "3", "!"), + (0xFE58, "M", "—"), + (0xFE59, "3", "("), + (0xFE5A, "3", ")"), + (0xFE5B, "3", "{"), + (0xFE5C, "3", "}"), + (0xFE5D, "M", "〔"), + (0xFE5E, "M", "〕"), + (0xFE5F, "3", "#"), + (0xFE60, "3", "&"), + (0xFE61, "3", "*"), ] + def _seg_50() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFE5E, 'M', '〕'), - (0xFE5F, '3', '#'), - (0xFE60, '3', '&'), - (0xFE61, '3', '*'), - (0xFE62, '3', '+'), - (0xFE63, 'M', '-'), - (0xFE64, '3', '<'), - (0xFE65, '3', '>'), - (0xFE66, '3', '='), - (0xFE67, 'X'), - (0xFE68, '3', '\\'), - (0xFE69, '3', '$'), - (0xFE6A, '3', '%'), - (0xFE6B, '3', '@'), - (0xFE6C, 'X'), - (0xFE70, '3', ' ً'), - (0xFE71, 'M', 'ـً'), - (0xFE72, '3', ' ٌ'), - (0xFE73, 'V'), - (0xFE74, '3', ' ٍ'), - (0xFE75, 'X'), - (0xFE76, '3', ' َ'), - (0xFE77, 'M', 'ـَ'), - (0xFE78, '3', ' ُ'), - (0xFE79, 'M', 'ـُ'), - (0xFE7A, '3', ' ِ'), - (0xFE7B, 'M', 'ـِ'), - (0xFE7C, '3', ' ّ'), - (0xFE7D, 'M', 'ـّ'), - (0xFE7E, '3', ' ْ'), - (0xFE7F, 'M', 'ـْ'), - (0xFE80, 'M', 'ء'), - (0xFE81, 'M', 'آ'), - (0xFE83, 'M', 'أ'), - (0xFE85, 'M', 'ؤ'), - (0xFE87, 'M', 'إ'), - (0xFE89, 'M', 'ئ'), - (0xFE8D, 'M', 'ا'), - (0xFE8F, 'M', 'ب'), - (0xFE93, 'M', 'ة'), - (0xFE95, 'M', 'ت'), - (0xFE99, 'M', 'ث'), - (0xFE9D, 'M', 'ج'), - (0xFEA1, 'M', 'ح'), - (0xFEA5, 'M', 'خ'), - (0xFEA9, 'M', 'د'), - (0xFEAB, 'M', 'ذ'), - (0xFEAD, 'M', 'ر'), - (0xFEAF, 'M', 'ز'), - (0xFEB1, 'M', 'س'), - (0xFEB5, 'M', 'ش'), - (0xFEB9, 'M', 'ص'), - (0xFEBD, 'M', 'ض'), - (0xFEC1, 'M', 'ط'), - (0xFEC5, 'M', 'ظ'), - (0xFEC9, 'M', 'ع'), - (0xFECD, 'M', 'غ'), - (0xFED1, 'M', 'ف'), - (0xFED5, 'M', 'ق'), - (0xFED9, 'M', 'ك'), - (0xFEDD, 'M', 'ل'), - (0xFEE1, 'M', 'م'), - (0xFEE5, 'M', 'ن'), - (0xFEE9, 'M', 'ه'), - (0xFEED, 'M', 'و'), - (0xFEEF, 'M', 'ى'), - (0xFEF1, 'M', 'ي'), - (0xFEF5, 'M', 'لآ'), - (0xFEF7, 'M', 'لأ'), - (0xFEF9, 'M', 'لإ'), - (0xFEFB, 'M', 'لا'), - (0xFEFD, 'X'), - (0xFEFF, 'I'), - (0xFF00, 'X'), - (0xFF01, '3', '!'), - (0xFF02, '3', '"'), - (0xFF03, '3', '#'), - (0xFF04, '3', '$'), - (0xFF05, '3', '%'), - (0xFF06, '3', '&'), - (0xFF07, '3', '\''), - (0xFF08, '3', '('), - (0xFF09, '3', ')'), - (0xFF0A, '3', '*'), - (0xFF0B, '3', '+'), - (0xFF0C, '3', ','), - (0xFF0D, 'M', '-'), - (0xFF0E, 'M', '.'), - (0xFF0F, '3', '/'), - (0xFF10, 'M', '0'), - (0xFF11, 'M', '1'), - (0xFF12, 'M', '2'), - (0xFF13, 'M', '3'), - (0xFF14, 'M', '4'), - (0xFF15, 'M', '5'), - (0xFF16, 'M', '6'), - (0xFF17, 'M', '7'), - (0xFF18, 'M', '8'), - (0xFF19, 'M', '9'), - (0xFF1A, '3', ':'), + (0xFE62, "3", "+"), + (0xFE63, "M", "-"), + (0xFE64, "3", "<"), + (0xFE65, "3", ">"), + (0xFE66, "3", "="), + (0xFE67, "X"), + (0xFE68, "3", "\\"), + (0xFE69, "3", "$"), + (0xFE6A, "3", "%"), + (0xFE6B, "3", "@"), + (0xFE6C, "X"), + (0xFE70, "3", " ً"), + (0xFE71, "M", "ـً"), + (0xFE72, "3", " ٌ"), + (0xFE73, "V"), + (0xFE74, "3", " ٍ"), + (0xFE75, "X"), + (0xFE76, "3", " َ"), + (0xFE77, "M", "ـَ"), + (0xFE78, "3", " ُ"), + (0xFE79, "M", "ـُ"), + (0xFE7A, "3", " ِ"), + (0xFE7B, "M", "ـِ"), + (0xFE7C, "3", " ّ"), + (0xFE7D, "M", "ـّ"), + (0xFE7E, "3", " ْ"), + (0xFE7F, "M", "ـْ"), + (0xFE80, "M", "ء"), + (0xFE81, "M", "آ"), + (0xFE83, "M", "أ"), + (0xFE85, "M", "ؤ"), + (0xFE87, "M", "إ"), + (0xFE89, "M", "ئ"), + (0xFE8D, "M", "ا"), + (0xFE8F, "M", "ب"), + (0xFE93, "M", "ة"), + (0xFE95, "M", "ت"), + (0xFE99, "M", "ث"), + (0xFE9D, "M", "ج"), + (0xFEA1, "M", "ح"), + (0xFEA5, "M", "خ"), + (0xFEA9, "M", "د"), + (0xFEAB, "M", "ذ"), + (0xFEAD, "M", "ر"), + (0xFEAF, "M", "ز"), + (0xFEB1, "M", "س"), + (0xFEB5, "M", "ش"), + (0xFEB9, "M", "ص"), + (0xFEBD, "M", "ض"), + (0xFEC1, "M", "ط"), + (0xFEC5, "M", "ظ"), + (0xFEC9, "M", "ع"), + (0xFECD, "M", "غ"), + (0xFED1, "M", "ف"), + (0xFED5, "M", "ق"), + (0xFED9, "M", "ك"), + (0xFEDD, "M", "ل"), + (0xFEE1, "M", "م"), + (0xFEE5, "M", "ن"), + (0xFEE9, "M", "ه"), + (0xFEED, "M", "و"), + (0xFEEF, "M", "ى"), + (0xFEF1, "M", "ي"), + (0xFEF5, "M", "لآ"), + (0xFEF7, "M", "لأ"), + (0xFEF9, "M", "لإ"), + (0xFEFB, "M", "لا"), + (0xFEFD, "X"), + (0xFEFF, "I"), + (0xFF00, "X"), + (0xFF01, "3", "!"), + (0xFF02, "3", '"'), + (0xFF03, "3", "#"), + (0xFF04, "3", "$"), + (0xFF05, "3", "%"), + (0xFF06, "3", "&"), + (0xFF07, "3", "'"), + (0xFF08, "3", "("), + (0xFF09, "3", ")"), + (0xFF0A, "3", "*"), + (0xFF0B, "3", "+"), + (0xFF0C, "3", ","), + (0xFF0D, "M", "-"), + (0xFF0E, "M", "."), + (0xFF0F, "3", "/"), + (0xFF10, "M", "0"), + (0xFF11, "M", "1"), + (0xFF12, "M", "2"), + (0xFF13, "M", "3"), + (0xFF14, "M", "4"), + (0xFF15, "M", "5"), + (0xFF16, "M", "6"), + (0xFF17, "M", "7"), + (0xFF18, "M", "8"), + (0xFF19, "M", "9"), + (0xFF1A, "3", ":"), + (0xFF1B, "3", ";"), + (0xFF1C, "3", "<"), + (0xFF1D, "3", "="), + (0xFF1E, "3", ">"), ] + def _seg_51() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFF1B, '3', ';'), - (0xFF1C, '3', '<'), - (0xFF1D, '3', '='), - (0xFF1E, '3', '>'), - (0xFF1F, '3', '?'), - (0xFF20, '3', '@'), - (0xFF21, 'M', 'a'), - (0xFF22, 'M', 'b'), - (0xFF23, 'M', 'c'), - (0xFF24, 'M', 'd'), - (0xFF25, 'M', 'e'), - (0xFF26, 'M', 'f'), - (0xFF27, 'M', 'g'), - (0xFF28, 'M', 'h'), - (0xFF29, 'M', 'i'), - (0xFF2A, 'M', 'j'), - (0xFF2B, 'M', 'k'), - (0xFF2C, 'M', 'l'), - (0xFF2D, 'M', 'm'), - (0xFF2E, 'M', 'n'), - (0xFF2F, 'M', 'o'), - (0xFF30, 'M', 'p'), - (0xFF31, 'M', 'q'), - (0xFF32, 'M', 'r'), - (0xFF33, 'M', 's'), - (0xFF34, 'M', 't'), - (0xFF35, 'M', 'u'), - (0xFF36, 'M', 'v'), - (0xFF37, 'M', 'w'), - (0xFF38, 'M', 'x'), - (0xFF39, 'M', 'y'), - (0xFF3A, 'M', 'z'), - (0xFF3B, '3', '['), - (0xFF3C, '3', '\\'), - (0xFF3D, '3', ']'), - (0xFF3E, '3', '^'), - (0xFF3F, '3', '_'), - (0xFF40, '3', '`'), - (0xFF41, 'M', 'a'), - (0xFF42, 'M', 'b'), - (0xFF43, 'M', 'c'), - (0xFF44, 'M', 'd'), - (0xFF45, 'M', 'e'), - (0xFF46, 'M', 'f'), - (0xFF47, 'M', 'g'), - (0xFF48, 'M', 'h'), - (0xFF49, 'M', 'i'), - (0xFF4A, 'M', 'j'), - (0xFF4B, 'M', 'k'), - (0xFF4C, 'M', 'l'), - (0xFF4D, 'M', 'm'), - (0xFF4E, 'M', 'n'), - (0xFF4F, 'M', 'o'), - (0xFF50, 'M', 'p'), - (0xFF51, 'M', 'q'), - (0xFF52, 'M', 'r'), - (0xFF53, 'M', 's'), - (0xFF54, 'M', 't'), - (0xFF55, 'M', 'u'), - (0xFF56, 'M', 'v'), - (0xFF57, 'M', 'w'), - (0xFF58, 'M', 'x'), - (0xFF59, 'M', 'y'), - (0xFF5A, 'M', 'z'), - (0xFF5B, '3', '{'), - (0xFF5C, '3', '|'), - (0xFF5D, '3', '}'), - (0xFF5E, '3', '~'), - (0xFF5F, 'M', '⦅'), - (0xFF60, 'M', '⦆'), - (0xFF61, 'M', '.'), - (0xFF62, 'M', '「'), - (0xFF63, 'M', '」'), - (0xFF64, 'M', '、'), - (0xFF65, 'M', '・'), - (0xFF66, 'M', 'ヲ'), - (0xFF67, 'M', 'ァ'), - (0xFF68, 'M', 'ィ'), - (0xFF69, 'M', 'ゥ'), - (0xFF6A, 'M', 'ェ'), - (0xFF6B, 'M', 'ォ'), - (0xFF6C, 'M', 'ャ'), - (0xFF6D, 'M', 'ュ'), - (0xFF6E, 'M', 'ョ'), - (0xFF6F, 'M', 'ッ'), - (0xFF70, 'M', 'ー'), - (0xFF71, 'M', 'ア'), - (0xFF72, 'M', 'イ'), - (0xFF73, 'M', 'ウ'), - (0xFF74, 'M', 'エ'), - (0xFF75, 'M', 'オ'), - (0xFF76, 'M', 'カ'), - (0xFF77, 'M', 'キ'), - (0xFF78, 'M', 'ク'), - (0xFF79, 'M', 'ケ'), - (0xFF7A, 'M', 'コ'), - (0xFF7B, 'M', 'サ'), - (0xFF7C, 'M', 'シ'), - (0xFF7D, 'M', 'ス'), - (0xFF7E, 'M', 'セ'), + (0xFF1F, "3", "?"), + (0xFF20, "3", "@"), + (0xFF21, "M", "a"), + (0xFF22, "M", "b"), + (0xFF23, "M", "c"), + (0xFF24, "M", "d"), + (0xFF25, "M", "e"), + (0xFF26, "M", "f"), + (0xFF27, "M", "g"), + (0xFF28, "M", "h"), + (0xFF29, "M", "i"), + (0xFF2A, "M", "j"), + (0xFF2B, "M", "k"), + (0xFF2C, "M", "l"), + (0xFF2D, "M", "m"), + (0xFF2E, "M", "n"), + (0xFF2F, "M", "o"), + (0xFF30, "M", "p"), + (0xFF31, "M", "q"), + (0xFF32, "M", "r"), + (0xFF33, "M", "s"), + (0xFF34, "M", "t"), + (0xFF35, "M", "u"), + (0xFF36, "M", "v"), + (0xFF37, "M", "w"), + (0xFF38, "M", "x"), + (0xFF39, "M", "y"), + (0xFF3A, "M", "z"), + (0xFF3B, "3", "["), + (0xFF3C, "3", "\\"), + (0xFF3D, "3", "]"), + (0xFF3E, "3", "^"), + (0xFF3F, "3", "_"), + (0xFF40, "3", "`"), + (0xFF41, "M", "a"), + (0xFF42, "M", "b"), + (0xFF43, "M", "c"), + (0xFF44, "M", "d"), + (0xFF45, "M", "e"), + (0xFF46, "M", "f"), + (0xFF47, "M", "g"), + (0xFF48, "M", "h"), + (0xFF49, "M", "i"), + (0xFF4A, "M", "j"), + (0xFF4B, "M", "k"), + (0xFF4C, "M", "l"), + (0xFF4D, "M", "m"), + (0xFF4E, "M", "n"), + (0xFF4F, "M", "o"), + (0xFF50, "M", "p"), + (0xFF51, "M", "q"), + (0xFF52, "M", "r"), + (0xFF53, "M", "s"), + (0xFF54, "M", "t"), + (0xFF55, "M", "u"), + (0xFF56, "M", "v"), + (0xFF57, "M", "w"), + (0xFF58, "M", "x"), + (0xFF59, "M", "y"), + (0xFF5A, "M", "z"), + (0xFF5B, "3", "{"), + (0xFF5C, "3", "|"), + (0xFF5D, "3", "}"), + (0xFF5E, "3", "~"), + (0xFF5F, "M", "⦅"), + (0xFF60, "M", "⦆"), + (0xFF61, "M", "."), + (0xFF62, "M", "「"), + (0xFF63, "M", "」"), + (0xFF64, "M", "、"), + (0xFF65, "M", "・"), + (0xFF66, "M", "ヲ"), + (0xFF67, "M", "ァ"), + (0xFF68, "M", "ィ"), + (0xFF69, "M", "ゥ"), + (0xFF6A, "M", "ェ"), + (0xFF6B, "M", "ォ"), + (0xFF6C, "M", "ャ"), + (0xFF6D, "M", "ュ"), + (0xFF6E, "M", "ョ"), + (0xFF6F, "M", "ッ"), + (0xFF70, "M", "ー"), + (0xFF71, "M", "ア"), + (0xFF72, "M", "イ"), + (0xFF73, "M", "ウ"), + (0xFF74, "M", "エ"), + (0xFF75, "M", "オ"), + (0xFF76, "M", "カ"), + (0xFF77, "M", "キ"), + (0xFF78, "M", "ク"), + (0xFF79, "M", "ケ"), + (0xFF7A, "M", "コ"), + (0xFF7B, "M", "サ"), + (0xFF7C, "M", "シ"), + (0xFF7D, "M", "ス"), + (0xFF7E, "M", "セ"), + (0xFF7F, "M", "ソ"), + (0xFF80, "M", "タ"), + (0xFF81, "M", "チ"), + (0xFF82, "M", "ツ"), ] + def _seg_52() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFF7F, 'M', 'ソ'), - (0xFF80, 'M', 'タ'), - (0xFF81, 'M', 'チ'), - (0xFF82, 'M', 'ツ'), - (0xFF83, 'M', 'テ'), - (0xFF84, 'M', 'ト'), - (0xFF85, 'M', 'ナ'), - (0xFF86, 'M', 'ニ'), - (0xFF87, 'M', 'ヌ'), - (0xFF88, 'M', 'ネ'), - (0xFF89, 'M', 'ノ'), - (0xFF8A, 'M', 'ハ'), - (0xFF8B, 'M', 'ヒ'), - (0xFF8C, 'M', 'フ'), - (0xFF8D, 'M', 'ヘ'), - (0xFF8E, 'M', 'ホ'), - (0xFF8F, 'M', 'マ'), - (0xFF90, 'M', 'ミ'), - (0xFF91, 'M', 'ム'), - (0xFF92, 'M', 'メ'), - (0xFF93, 'M', 'モ'), - (0xFF94, 'M', 'ヤ'), - (0xFF95, 'M', 'ユ'), - (0xFF96, 'M', 'ヨ'), - (0xFF97, 'M', 'ラ'), - (0xFF98, 'M', 'リ'), - (0xFF99, 'M', 'ル'), - (0xFF9A, 'M', 'レ'), - (0xFF9B, 'M', 'ロ'), - (0xFF9C, 'M', 'ワ'), - (0xFF9D, 'M', 'ン'), - (0xFF9E, 'M', '゙'), - (0xFF9F, 'M', '゚'), - (0xFFA0, 'X'), - (0xFFA1, 'M', 'ᄀ'), - (0xFFA2, 'M', 'ᄁ'), - (0xFFA3, 'M', 'ᆪ'), - (0xFFA4, 'M', 'ᄂ'), - (0xFFA5, 'M', 'ᆬ'), - (0xFFA6, 'M', 'ᆭ'), - (0xFFA7, 'M', 'ᄃ'), - (0xFFA8, 'M', 'ᄄ'), - (0xFFA9, 'M', 'ᄅ'), - (0xFFAA, 'M', 'ᆰ'), - (0xFFAB, 'M', 'ᆱ'), - (0xFFAC, 'M', 'ᆲ'), - (0xFFAD, 'M', 'ᆳ'), - (0xFFAE, 'M', 'ᆴ'), - (0xFFAF, 'M', 'ᆵ'), - (0xFFB0, 'M', 'ᄚ'), - (0xFFB1, 'M', 'ᄆ'), - (0xFFB2, 'M', 'ᄇ'), - (0xFFB3, 'M', 'ᄈ'), - (0xFFB4, 'M', 'ᄡ'), - (0xFFB5, 'M', 'ᄉ'), - (0xFFB6, 'M', 'ᄊ'), - (0xFFB7, 'M', 'ᄋ'), - (0xFFB8, 'M', 'ᄌ'), - (0xFFB9, 'M', 'ᄍ'), - (0xFFBA, 'M', 'ᄎ'), - (0xFFBB, 'M', 'ᄏ'), - (0xFFBC, 'M', 'ᄐ'), - (0xFFBD, 'M', 'ᄑ'), - (0xFFBE, 'M', 'ᄒ'), - (0xFFBF, 'X'), - (0xFFC2, 'M', 'ᅡ'), - (0xFFC3, 'M', 'ᅢ'), - (0xFFC4, 'M', 'ᅣ'), - (0xFFC5, 'M', 'ᅤ'), - (0xFFC6, 'M', 'ᅥ'), - (0xFFC7, 'M', 'ᅦ'), - (0xFFC8, 'X'), - (0xFFCA, 'M', 'ᅧ'), - (0xFFCB, 'M', 'ᅨ'), - (0xFFCC, 'M', 'ᅩ'), - (0xFFCD, 'M', 'ᅪ'), - (0xFFCE, 'M', 'ᅫ'), - (0xFFCF, 'M', 'ᅬ'), - (0xFFD0, 'X'), - (0xFFD2, 'M', 'ᅭ'), - (0xFFD3, 'M', 'ᅮ'), - (0xFFD4, 'M', 'ᅯ'), - (0xFFD5, 'M', 'ᅰ'), - (0xFFD6, 'M', 'ᅱ'), - (0xFFD7, 'M', 'ᅲ'), - (0xFFD8, 'X'), - (0xFFDA, 'M', 'ᅳ'), - (0xFFDB, 'M', 'ᅴ'), - (0xFFDC, 'M', 'ᅵ'), - (0xFFDD, 'X'), - (0xFFE0, 'M', '¢'), - (0xFFE1, 'M', '£'), - (0xFFE2, 'M', '¬'), - (0xFFE3, '3', ' ̄'), - (0xFFE4, 'M', '¦'), - (0xFFE5, 'M', '¥'), - (0xFFE6, 'M', '₩'), - (0xFFE7, 'X'), - (0xFFE8, 'M', '│'), - (0xFFE9, 'M', '←'), + (0xFF83, "M", "テ"), + (0xFF84, "M", "ト"), + (0xFF85, "M", "ナ"), + (0xFF86, "M", "ニ"), + (0xFF87, "M", "ヌ"), + (0xFF88, "M", "ネ"), + (0xFF89, "M", "ノ"), + (0xFF8A, "M", "ハ"), + (0xFF8B, "M", "ヒ"), + (0xFF8C, "M", "フ"), + (0xFF8D, "M", "ヘ"), + (0xFF8E, "M", "ホ"), + (0xFF8F, "M", "マ"), + (0xFF90, "M", "ミ"), + (0xFF91, "M", "ム"), + (0xFF92, "M", "メ"), + (0xFF93, "M", "モ"), + (0xFF94, "M", "ヤ"), + (0xFF95, "M", "ユ"), + (0xFF96, "M", "ヨ"), + (0xFF97, "M", "ラ"), + (0xFF98, "M", "リ"), + (0xFF99, "M", "ル"), + (0xFF9A, "M", "レ"), + (0xFF9B, "M", "ロ"), + (0xFF9C, "M", "ワ"), + (0xFF9D, "M", "ン"), + (0xFF9E, "M", "゙"), + (0xFF9F, "M", "゚"), + (0xFFA0, "X"), + (0xFFA1, "M", "ᄀ"), + (0xFFA2, "M", "ᄁ"), + (0xFFA3, "M", "ᆪ"), + (0xFFA4, "M", "ᄂ"), + (0xFFA5, "M", "ᆬ"), + (0xFFA6, "M", "ᆭ"), + (0xFFA7, "M", "ᄃ"), + (0xFFA8, "M", "ᄄ"), + (0xFFA9, "M", "ᄅ"), + (0xFFAA, "M", "ᆰ"), + (0xFFAB, "M", "ᆱ"), + (0xFFAC, "M", "ᆲ"), + (0xFFAD, "M", "ᆳ"), + (0xFFAE, "M", "ᆴ"), + (0xFFAF, "M", "ᆵ"), + (0xFFB0, "M", "ᄚ"), + (0xFFB1, "M", "ᄆ"), + (0xFFB2, "M", "ᄇ"), + (0xFFB3, "M", "ᄈ"), + (0xFFB4, "M", "ᄡ"), + (0xFFB5, "M", "ᄉ"), + (0xFFB6, "M", "ᄊ"), + (0xFFB7, "M", "ᄋ"), + (0xFFB8, "M", "ᄌ"), + (0xFFB9, "M", "ᄍ"), + (0xFFBA, "M", "ᄎ"), + (0xFFBB, "M", "ᄏ"), + (0xFFBC, "M", "ᄐ"), + (0xFFBD, "M", "ᄑ"), + (0xFFBE, "M", "ᄒ"), + (0xFFBF, "X"), + (0xFFC2, "M", "ᅡ"), + (0xFFC3, "M", "ᅢ"), + (0xFFC4, "M", "ᅣ"), + (0xFFC5, "M", "ᅤ"), + (0xFFC6, "M", "ᅥ"), + (0xFFC7, "M", "ᅦ"), + (0xFFC8, "X"), + (0xFFCA, "M", "ᅧ"), + (0xFFCB, "M", "ᅨ"), + (0xFFCC, "M", "ᅩ"), + (0xFFCD, "M", "ᅪ"), + (0xFFCE, "M", "ᅫ"), + (0xFFCF, "M", "ᅬ"), + (0xFFD0, "X"), + (0xFFD2, "M", "ᅭ"), + (0xFFD3, "M", "ᅮ"), + (0xFFD4, "M", "ᅯ"), + (0xFFD5, "M", "ᅰ"), + (0xFFD6, "M", "ᅱ"), + (0xFFD7, "M", "ᅲ"), + (0xFFD8, "X"), + (0xFFDA, "M", "ᅳ"), + (0xFFDB, "M", "ᅴ"), + (0xFFDC, "M", "ᅵ"), + (0xFFDD, "X"), + (0xFFE0, "M", "¢"), + (0xFFE1, "M", "£"), + (0xFFE2, "M", "¬"), + (0xFFE3, "3", " ̄"), + (0xFFE4, "M", "¦"), + (0xFFE5, "M", "¥"), + (0xFFE6, "M", "₩"), + (0xFFE7, "X"), + (0xFFE8, "M", "│"), + (0xFFE9, "M", "←"), + (0xFFEA, "M", "↑"), + (0xFFEB, "M", "→"), + (0xFFEC, "M", "↓"), + (0xFFED, "M", "■"), ] + def _seg_53() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0xFFEA, 'M', '↑'), - (0xFFEB, 'M', '→'), - (0xFFEC, 'M', '↓'), - (0xFFED, 'M', '■'), - (0xFFEE, 'M', '○'), - (0xFFEF, 'X'), - (0x10000, 'V'), - (0x1000C, 'X'), - (0x1000D, 'V'), - (0x10027, 'X'), - (0x10028, 'V'), - (0x1003B, 'X'), - (0x1003C, 'V'), - (0x1003E, 'X'), - (0x1003F, 'V'), - (0x1004E, 'X'), - (0x10050, 'V'), - (0x1005E, 'X'), - (0x10080, 'V'), - (0x100FB, 'X'), - (0x10100, 'V'), - (0x10103, 'X'), - (0x10107, 'V'), - (0x10134, 'X'), - (0x10137, 'V'), - (0x1018F, 'X'), - (0x10190, 'V'), - (0x1019D, 'X'), - (0x101A0, 'V'), - (0x101A1, 'X'), - (0x101D0, 'V'), - (0x101FE, 'X'), - (0x10280, 'V'), - (0x1029D, 'X'), - (0x102A0, 'V'), - (0x102D1, 'X'), - (0x102E0, 'V'), - (0x102FC, 'X'), - (0x10300, 'V'), - (0x10324, 'X'), - (0x1032D, 'V'), - (0x1034B, 'X'), - (0x10350, 'V'), - (0x1037B, 'X'), - (0x10380, 'V'), - (0x1039E, 'X'), - (0x1039F, 'V'), - (0x103C4, 'X'), - (0x103C8, 'V'), - (0x103D6, 'X'), - (0x10400, 'M', '𐐨'), - (0x10401, 'M', '𐐩'), - (0x10402, 'M', '𐐪'), - (0x10403, 'M', '𐐫'), - (0x10404, 'M', '𐐬'), - (0x10405, 'M', '𐐭'), - (0x10406, 'M', '𐐮'), - (0x10407, 'M', '𐐯'), - (0x10408, 'M', '𐐰'), - (0x10409, 'M', '𐐱'), - (0x1040A, 'M', '𐐲'), - (0x1040B, 'M', '𐐳'), - (0x1040C, 'M', '𐐴'), - (0x1040D, 'M', '𐐵'), - (0x1040E, 'M', '𐐶'), - (0x1040F, 'M', '𐐷'), - (0x10410, 'M', '𐐸'), - (0x10411, 'M', '𐐹'), - (0x10412, 'M', '𐐺'), - (0x10413, 'M', '𐐻'), - (0x10414, 'M', '𐐼'), - (0x10415, 'M', '𐐽'), - (0x10416, 'M', '𐐾'), - (0x10417, 'M', '𐐿'), - (0x10418, 'M', '𐑀'), - (0x10419, 'M', '𐑁'), - (0x1041A, 'M', '𐑂'), - (0x1041B, 'M', '𐑃'), - (0x1041C, 'M', '𐑄'), - (0x1041D, 'M', '𐑅'), - (0x1041E, 'M', '𐑆'), - (0x1041F, 'M', '𐑇'), - (0x10420, 'M', '𐑈'), - (0x10421, 'M', '𐑉'), - (0x10422, 'M', '𐑊'), - (0x10423, 'M', '𐑋'), - (0x10424, 'M', '𐑌'), - (0x10425, 'M', '𐑍'), - (0x10426, 'M', '𐑎'), - (0x10427, 'M', '𐑏'), - (0x10428, 'V'), - (0x1049E, 'X'), - (0x104A0, 'V'), - (0x104AA, 'X'), - (0x104B0, 'M', '𐓘'), - (0x104B1, 'M', '𐓙'), - (0x104B2, 'M', '𐓚'), - (0x104B3, 'M', '𐓛'), - (0x104B4, 'M', '𐓜'), - (0x104B5, 'M', '𐓝'), + (0xFFEE, "M", "○"), + (0xFFEF, "X"), + (0x10000, "V"), + (0x1000C, "X"), + (0x1000D, "V"), + (0x10027, "X"), + (0x10028, "V"), + (0x1003B, "X"), + (0x1003C, "V"), + (0x1003E, "X"), + (0x1003F, "V"), + (0x1004E, "X"), + (0x10050, "V"), + (0x1005E, "X"), + (0x10080, "V"), + (0x100FB, "X"), + (0x10100, "V"), + (0x10103, "X"), + (0x10107, "V"), + (0x10134, "X"), + (0x10137, "V"), + (0x1018F, "X"), + (0x10190, "V"), + (0x1019D, "X"), + (0x101A0, "V"), + (0x101A1, "X"), + (0x101D0, "V"), + (0x101FE, "X"), + (0x10280, "V"), + (0x1029D, "X"), + (0x102A0, "V"), + (0x102D1, "X"), + (0x102E0, "V"), + (0x102FC, "X"), + (0x10300, "V"), + (0x10324, "X"), + (0x1032D, "V"), + (0x1034B, "X"), + (0x10350, "V"), + (0x1037B, "X"), + (0x10380, "V"), + (0x1039E, "X"), + (0x1039F, "V"), + (0x103C4, "X"), + (0x103C8, "V"), + (0x103D6, "X"), + (0x10400, "M", "𐐨"), + (0x10401, "M", "𐐩"), + (0x10402, "M", "𐐪"), + (0x10403, "M", "𐐫"), + (0x10404, "M", "𐐬"), + (0x10405, "M", "𐐭"), + (0x10406, "M", "𐐮"), + (0x10407, "M", "𐐯"), + (0x10408, "M", "𐐰"), + (0x10409, "M", "𐐱"), + (0x1040A, "M", "𐐲"), + (0x1040B, "M", "𐐳"), + (0x1040C, "M", "𐐴"), + (0x1040D, "M", "𐐵"), + (0x1040E, "M", "𐐶"), + (0x1040F, "M", "𐐷"), + (0x10410, "M", "𐐸"), + (0x10411, "M", "𐐹"), + (0x10412, "M", "𐐺"), + (0x10413, "M", "𐐻"), + (0x10414, "M", "𐐼"), + (0x10415, "M", "𐐽"), + (0x10416, "M", "𐐾"), + (0x10417, "M", "𐐿"), + (0x10418, "M", "𐑀"), + (0x10419, "M", "𐑁"), + (0x1041A, "M", "𐑂"), + (0x1041B, "M", "𐑃"), + (0x1041C, "M", "𐑄"), + (0x1041D, "M", "𐑅"), + (0x1041E, "M", "𐑆"), + (0x1041F, "M", "𐑇"), + (0x10420, "M", "𐑈"), + (0x10421, "M", "𐑉"), + (0x10422, "M", "𐑊"), + (0x10423, "M", "𐑋"), + (0x10424, "M", "𐑌"), + (0x10425, "M", "𐑍"), + (0x10426, "M", "𐑎"), + (0x10427, "M", "𐑏"), + (0x10428, "V"), + (0x1049E, "X"), + (0x104A0, "V"), + (0x104AA, "X"), + (0x104B0, "M", "𐓘"), + (0x104B1, "M", "𐓙"), + (0x104B2, "M", "𐓚"), + (0x104B3, "M", "𐓛"), + (0x104B4, "M", "𐓜"), + (0x104B5, "M", "𐓝"), + (0x104B6, "M", "𐓞"), + (0x104B7, "M", "𐓟"), + (0x104B8, "M", "𐓠"), + (0x104B9, "M", "𐓡"), ] + def _seg_54() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x104B6, 'M', '𐓞'), - (0x104B7, 'M', '𐓟'), - (0x104B8, 'M', '𐓠'), - (0x104B9, 'M', '𐓡'), - (0x104BA, 'M', '𐓢'), - (0x104BB, 'M', '𐓣'), - (0x104BC, 'M', '𐓤'), - (0x104BD, 'M', '𐓥'), - (0x104BE, 'M', '𐓦'), - (0x104BF, 'M', '𐓧'), - (0x104C0, 'M', '𐓨'), - (0x104C1, 'M', '𐓩'), - (0x104C2, 'M', '𐓪'), - (0x104C3, 'M', '𐓫'), - (0x104C4, 'M', '𐓬'), - (0x104C5, 'M', '𐓭'), - (0x104C6, 'M', '𐓮'), - (0x104C7, 'M', '𐓯'), - (0x104C8, 'M', '𐓰'), - (0x104C9, 'M', '𐓱'), - (0x104CA, 'M', '𐓲'), - (0x104CB, 'M', '𐓳'), - (0x104CC, 'M', '𐓴'), - (0x104CD, 'M', '𐓵'), - (0x104CE, 'M', '𐓶'), - (0x104CF, 'M', '𐓷'), - (0x104D0, 'M', '𐓸'), - (0x104D1, 'M', '𐓹'), - (0x104D2, 'M', '𐓺'), - (0x104D3, 'M', '𐓻'), - (0x104D4, 'X'), - (0x104D8, 'V'), - (0x104FC, 'X'), - (0x10500, 'V'), - (0x10528, 'X'), - (0x10530, 'V'), - (0x10564, 'X'), - (0x1056F, 'V'), - (0x10570, 'M', '𐖗'), - (0x10571, 'M', '𐖘'), - (0x10572, 'M', '𐖙'), - (0x10573, 'M', '𐖚'), - (0x10574, 'M', '𐖛'), - (0x10575, 'M', '𐖜'), - (0x10576, 'M', '𐖝'), - (0x10577, 'M', '𐖞'), - (0x10578, 'M', '𐖟'), - (0x10579, 'M', '𐖠'), - (0x1057A, 'M', '𐖡'), - (0x1057B, 'X'), - (0x1057C, 'M', '𐖣'), - (0x1057D, 'M', '𐖤'), - (0x1057E, 'M', '𐖥'), - (0x1057F, 'M', '𐖦'), - (0x10580, 'M', '𐖧'), - (0x10581, 'M', '𐖨'), - (0x10582, 'M', '𐖩'), - (0x10583, 'M', '𐖪'), - (0x10584, 'M', '𐖫'), - (0x10585, 'M', '𐖬'), - (0x10586, 'M', '𐖭'), - (0x10587, 'M', '𐖮'), - (0x10588, 'M', '𐖯'), - (0x10589, 'M', '𐖰'), - (0x1058A, 'M', '𐖱'), - (0x1058B, 'X'), - (0x1058C, 'M', '𐖳'), - (0x1058D, 'M', '𐖴'), - (0x1058E, 'M', '𐖵'), - (0x1058F, 'M', '𐖶'), - (0x10590, 'M', '𐖷'), - (0x10591, 'M', '𐖸'), - (0x10592, 'M', '𐖹'), - (0x10593, 'X'), - (0x10594, 'M', '𐖻'), - (0x10595, 'M', '𐖼'), - (0x10596, 'X'), - (0x10597, 'V'), - (0x105A2, 'X'), - (0x105A3, 'V'), - (0x105B2, 'X'), - (0x105B3, 'V'), - (0x105BA, 'X'), - (0x105BB, 'V'), - (0x105BD, 'X'), - (0x10600, 'V'), - (0x10737, 'X'), - (0x10740, 'V'), - (0x10756, 'X'), - (0x10760, 'V'), - (0x10768, 'X'), - (0x10780, 'V'), - (0x10781, 'M', 'ː'), - (0x10782, 'M', 'ˑ'), - (0x10783, 'M', 'æ'), - (0x10784, 'M', 'ʙ'), - (0x10785, 'M', 'ɓ'), - (0x10786, 'X'), - (0x10787, 'M', 'ʣ'), - (0x10788, 'M', 'ꭦ'), + (0x104BA, "M", "𐓢"), + (0x104BB, "M", "𐓣"), + (0x104BC, "M", "𐓤"), + (0x104BD, "M", "𐓥"), + (0x104BE, "M", "𐓦"), + (0x104BF, "M", "𐓧"), + (0x104C0, "M", "𐓨"), + (0x104C1, "M", "𐓩"), + (0x104C2, "M", "𐓪"), + (0x104C3, "M", "𐓫"), + (0x104C4, "M", "𐓬"), + (0x104C5, "M", "𐓭"), + (0x104C6, "M", "𐓮"), + (0x104C7, "M", "𐓯"), + (0x104C8, "M", "𐓰"), + (0x104C9, "M", "𐓱"), + (0x104CA, "M", "𐓲"), + (0x104CB, "M", "𐓳"), + (0x104CC, "M", "𐓴"), + (0x104CD, "M", "𐓵"), + (0x104CE, "M", "𐓶"), + (0x104CF, "M", "𐓷"), + (0x104D0, "M", "𐓸"), + (0x104D1, "M", "𐓹"), + (0x104D2, "M", "𐓺"), + (0x104D3, "M", "𐓻"), + (0x104D4, "X"), + (0x104D8, "V"), + (0x104FC, "X"), + (0x10500, "V"), + (0x10528, "X"), + (0x10530, "V"), + (0x10564, "X"), + (0x1056F, "V"), + (0x10570, "M", "𐖗"), + (0x10571, "M", "𐖘"), + (0x10572, "M", "𐖙"), + (0x10573, "M", "𐖚"), + (0x10574, "M", "𐖛"), + (0x10575, "M", "𐖜"), + (0x10576, "M", "𐖝"), + (0x10577, "M", "𐖞"), + (0x10578, "M", "𐖟"), + (0x10579, "M", "𐖠"), + (0x1057A, "M", "𐖡"), + (0x1057B, "X"), + (0x1057C, "M", "𐖣"), + (0x1057D, "M", "𐖤"), + (0x1057E, "M", "𐖥"), + (0x1057F, "M", "𐖦"), + (0x10580, "M", "𐖧"), + (0x10581, "M", "𐖨"), + (0x10582, "M", "𐖩"), + (0x10583, "M", "𐖪"), + (0x10584, "M", "𐖫"), + (0x10585, "M", "𐖬"), + (0x10586, "M", "𐖭"), + (0x10587, "M", "𐖮"), + (0x10588, "M", "𐖯"), + (0x10589, "M", "𐖰"), + (0x1058A, "M", "𐖱"), + (0x1058B, "X"), + (0x1058C, "M", "𐖳"), + (0x1058D, "M", "𐖴"), + (0x1058E, "M", "𐖵"), + (0x1058F, "M", "𐖶"), + (0x10590, "M", "𐖷"), + (0x10591, "M", "𐖸"), + (0x10592, "M", "𐖹"), + (0x10593, "X"), + (0x10594, "M", "𐖻"), + (0x10595, "M", "𐖼"), + (0x10596, "X"), + (0x10597, "V"), + (0x105A2, "X"), + (0x105A3, "V"), + (0x105B2, "X"), + (0x105B3, "V"), + (0x105BA, "X"), + (0x105BB, "V"), + (0x105BD, "X"), + (0x10600, "V"), + (0x10737, "X"), + (0x10740, "V"), + (0x10756, "X"), + (0x10760, "V"), + (0x10768, "X"), + (0x10780, "V"), + (0x10781, "M", "ː"), + (0x10782, "M", "ˑ"), + (0x10783, "M", "æ"), + (0x10784, "M", "ʙ"), + (0x10785, "M", "ɓ"), + (0x10786, "X"), + (0x10787, "M", "ʣ"), + (0x10788, "M", "ꭦ"), + (0x10789, "M", "ʥ"), + (0x1078A, "M", "ʤ"), + (0x1078B, "M", "ɖ"), + (0x1078C, "M", "ɗ"), ] + def _seg_55() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x10789, 'M', 'ʥ'), - (0x1078A, 'M', 'ʤ'), - (0x1078B, 'M', 'ɖ'), - (0x1078C, 'M', 'ɗ'), - (0x1078D, 'M', 'ᶑ'), - (0x1078E, 'M', 'ɘ'), - (0x1078F, 'M', 'ɞ'), - (0x10790, 'M', 'ʩ'), - (0x10791, 'M', 'ɤ'), - (0x10792, 'M', 'ɢ'), - (0x10793, 'M', 'ɠ'), - (0x10794, 'M', 'ʛ'), - (0x10795, 'M', 'ħ'), - (0x10796, 'M', 'ʜ'), - (0x10797, 'M', 'ɧ'), - (0x10798, 'M', 'ʄ'), - (0x10799, 'M', 'ʪ'), - (0x1079A, 'M', 'ʫ'), - (0x1079B, 'M', 'ɬ'), - (0x1079C, 'M', '𝼄'), - (0x1079D, 'M', 'ꞎ'), - (0x1079E, 'M', 'ɮ'), - (0x1079F, 'M', '𝼅'), - (0x107A0, 'M', 'ʎ'), - (0x107A1, 'M', '𝼆'), - (0x107A2, 'M', 'ø'), - (0x107A3, 'M', 'ɶ'), - (0x107A4, 'M', 'ɷ'), - (0x107A5, 'M', 'q'), - (0x107A6, 'M', 'ɺ'), - (0x107A7, 'M', '𝼈'), - (0x107A8, 'M', 'ɽ'), - (0x107A9, 'M', 'ɾ'), - (0x107AA, 'M', 'ʀ'), - (0x107AB, 'M', 'ʨ'), - (0x107AC, 'M', 'ʦ'), - (0x107AD, 'M', 'ꭧ'), - (0x107AE, 'M', 'ʧ'), - (0x107AF, 'M', 'ʈ'), - (0x107B0, 'M', 'ⱱ'), - (0x107B1, 'X'), - (0x107B2, 'M', 'ʏ'), - (0x107B3, 'M', 'ʡ'), - (0x107B4, 'M', 'ʢ'), - (0x107B5, 'M', 'ʘ'), - (0x107B6, 'M', 'ǀ'), - (0x107B7, 'M', 'ǁ'), - (0x107B8, 'M', 'ǂ'), - (0x107B9, 'M', '𝼊'), - (0x107BA, 'M', '𝼞'), - (0x107BB, 'X'), - (0x10800, 'V'), - (0x10806, 'X'), - (0x10808, 'V'), - (0x10809, 'X'), - (0x1080A, 'V'), - (0x10836, 'X'), - (0x10837, 'V'), - (0x10839, 'X'), - (0x1083C, 'V'), - (0x1083D, 'X'), - (0x1083F, 'V'), - (0x10856, 'X'), - (0x10857, 'V'), - (0x1089F, 'X'), - (0x108A7, 'V'), - (0x108B0, 'X'), - (0x108E0, 'V'), - (0x108F3, 'X'), - (0x108F4, 'V'), - (0x108F6, 'X'), - (0x108FB, 'V'), - (0x1091C, 'X'), - (0x1091F, 'V'), - (0x1093A, 'X'), - (0x1093F, 'V'), - (0x10940, 'X'), - (0x10980, 'V'), - (0x109B8, 'X'), - (0x109BC, 'V'), - (0x109D0, 'X'), - (0x109D2, 'V'), - (0x10A04, 'X'), - (0x10A05, 'V'), - (0x10A07, 'X'), - (0x10A0C, 'V'), - (0x10A14, 'X'), - (0x10A15, 'V'), - (0x10A18, 'X'), - (0x10A19, 'V'), - (0x10A36, 'X'), - (0x10A38, 'V'), - (0x10A3B, 'X'), - (0x10A3F, 'V'), - (0x10A49, 'X'), - (0x10A50, 'V'), - (0x10A59, 'X'), - (0x10A60, 'V'), - (0x10AA0, 'X'), - (0x10AC0, 'V'), + (0x1078D, "M", "ᶑ"), + (0x1078E, "M", "ɘ"), + (0x1078F, "M", "ɞ"), + (0x10790, "M", "ʩ"), + (0x10791, "M", "ɤ"), + (0x10792, "M", "ɢ"), + (0x10793, "M", "ɠ"), + (0x10794, "M", "ʛ"), + (0x10795, "M", "ħ"), + (0x10796, "M", "ʜ"), + (0x10797, "M", "ɧ"), + (0x10798, "M", "ʄ"), + (0x10799, "M", "ʪ"), + (0x1079A, "M", "ʫ"), + (0x1079B, "M", "ɬ"), + (0x1079C, "M", "𝼄"), + (0x1079D, "M", "ꞎ"), + (0x1079E, "M", "ɮ"), + (0x1079F, "M", "𝼅"), + (0x107A0, "M", "ʎ"), + (0x107A1, "M", "𝼆"), + (0x107A2, "M", "ø"), + (0x107A3, "M", "ɶ"), + (0x107A4, "M", "ɷ"), + (0x107A5, "M", "q"), + (0x107A6, "M", "ɺ"), + (0x107A7, "M", "𝼈"), + (0x107A8, "M", "ɽ"), + (0x107A9, "M", "ɾ"), + (0x107AA, "M", "ʀ"), + (0x107AB, "M", "ʨ"), + (0x107AC, "M", "ʦ"), + (0x107AD, "M", "ꭧ"), + (0x107AE, "M", "ʧ"), + (0x107AF, "M", "ʈ"), + (0x107B0, "M", "ⱱ"), + (0x107B1, "X"), + (0x107B2, "M", "ʏ"), + (0x107B3, "M", "ʡ"), + (0x107B4, "M", "ʢ"), + (0x107B5, "M", "ʘ"), + (0x107B6, "M", "ǀ"), + (0x107B7, "M", "ǁ"), + (0x107B8, "M", "ǂ"), + (0x107B9, "M", "𝼊"), + (0x107BA, "M", "𝼞"), + (0x107BB, "X"), + (0x10800, "V"), + (0x10806, "X"), + (0x10808, "V"), + (0x10809, "X"), + (0x1080A, "V"), + (0x10836, "X"), + (0x10837, "V"), + (0x10839, "X"), + (0x1083C, "V"), + (0x1083D, "X"), + (0x1083F, "V"), + (0x10856, "X"), + (0x10857, "V"), + (0x1089F, "X"), + (0x108A7, "V"), + (0x108B0, "X"), + (0x108E0, "V"), + (0x108F3, "X"), + (0x108F4, "V"), + (0x108F6, "X"), + (0x108FB, "V"), + (0x1091C, "X"), + (0x1091F, "V"), + (0x1093A, "X"), + (0x1093F, "V"), + (0x10940, "X"), + (0x10980, "V"), + (0x109B8, "X"), + (0x109BC, "V"), + (0x109D0, "X"), + (0x109D2, "V"), + (0x10A04, "X"), + (0x10A05, "V"), + (0x10A07, "X"), + (0x10A0C, "V"), + (0x10A14, "X"), + (0x10A15, "V"), + (0x10A18, "X"), + (0x10A19, "V"), + (0x10A36, "X"), + (0x10A38, "V"), + (0x10A3B, "X"), + (0x10A3F, "V"), + (0x10A49, "X"), + (0x10A50, "V"), + (0x10A59, "X"), + (0x10A60, "V"), + (0x10AA0, "X"), + (0x10AC0, "V"), + (0x10AE7, "X"), + (0x10AEB, "V"), + (0x10AF7, "X"), + (0x10B00, "V"), ] + def _seg_56() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x10AE7, 'X'), - (0x10AEB, 'V'), - (0x10AF7, 'X'), - (0x10B00, 'V'), - (0x10B36, 'X'), - (0x10B39, 'V'), - (0x10B56, 'X'), - (0x10B58, 'V'), - (0x10B73, 'X'), - (0x10B78, 'V'), - (0x10B92, 'X'), - (0x10B99, 'V'), - (0x10B9D, 'X'), - (0x10BA9, 'V'), - (0x10BB0, 'X'), - (0x10C00, 'V'), - (0x10C49, 'X'), - (0x10C80, 'M', '𐳀'), - (0x10C81, 'M', '𐳁'), - (0x10C82, 'M', '𐳂'), - (0x10C83, 'M', '𐳃'), - (0x10C84, 'M', '𐳄'), - (0x10C85, 'M', '𐳅'), - (0x10C86, 'M', '𐳆'), - (0x10C87, 'M', '𐳇'), - (0x10C88, 'M', '𐳈'), - (0x10C89, 'M', '𐳉'), - (0x10C8A, 'M', '𐳊'), - (0x10C8B, 'M', '𐳋'), - (0x10C8C, 'M', '𐳌'), - (0x10C8D, 'M', '𐳍'), - (0x10C8E, 'M', '𐳎'), - (0x10C8F, 'M', '𐳏'), - (0x10C90, 'M', '𐳐'), - (0x10C91, 'M', '𐳑'), - (0x10C92, 'M', '𐳒'), - (0x10C93, 'M', '𐳓'), - (0x10C94, 'M', '𐳔'), - (0x10C95, 'M', '𐳕'), - (0x10C96, 'M', '𐳖'), - (0x10C97, 'M', '𐳗'), - (0x10C98, 'M', '𐳘'), - (0x10C99, 'M', '𐳙'), - (0x10C9A, 'M', '𐳚'), - (0x10C9B, 'M', '𐳛'), - (0x10C9C, 'M', '𐳜'), - (0x10C9D, 'M', '𐳝'), - (0x10C9E, 'M', '𐳞'), - (0x10C9F, 'M', '𐳟'), - (0x10CA0, 'M', '𐳠'), - (0x10CA1, 'M', '𐳡'), - (0x10CA2, 'M', '𐳢'), - (0x10CA3, 'M', '𐳣'), - (0x10CA4, 'M', '𐳤'), - (0x10CA5, 'M', '𐳥'), - (0x10CA6, 'M', '𐳦'), - (0x10CA7, 'M', '𐳧'), - (0x10CA8, 'M', '𐳨'), - (0x10CA9, 'M', '𐳩'), - (0x10CAA, 'M', '𐳪'), - (0x10CAB, 'M', '𐳫'), - (0x10CAC, 'M', '𐳬'), - (0x10CAD, 'M', '𐳭'), - (0x10CAE, 'M', '𐳮'), - (0x10CAF, 'M', '𐳯'), - (0x10CB0, 'M', '𐳰'), - (0x10CB1, 'M', '𐳱'), - (0x10CB2, 'M', '𐳲'), - (0x10CB3, 'X'), - (0x10CC0, 'V'), - (0x10CF3, 'X'), - (0x10CFA, 'V'), - (0x10D28, 'X'), - (0x10D30, 'V'), - (0x10D3A, 'X'), - (0x10E60, 'V'), - (0x10E7F, 'X'), - (0x10E80, 'V'), - (0x10EAA, 'X'), - (0x10EAB, 'V'), - (0x10EAE, 'X'), - (0x10EB0, 'V'), - (0x10EB2, 'X'), - (0x10EFD, 'V'), - (0x10F28, 'X'), - (0x10F30, 'V'), - (0x10F5A, 'X'), - (0x10F70, 'V'), - (0x10F8A, 'X'), - (0x10FB0, 'V'), - (0x10FCC, 'X'), - (0x10FE0, 'V'), - (0x10FF7, 'X'), - (0x11000, 'V'), - (0x1104E, 'X'), - (0x11052, 'V'), - (0x11076, 'X'), - (0x1107F, 'V'), - (0x110BD, 'X'), - (0x110BE, 'V'), + (0x10B36, "X"), + (0x10B39, "V"), + (0x10B56, "X"), + (0x10B58, "V"), + (0x10B73, "X"), + (0x10B78, "V"), + (0x10B92, "X"), + (0x10B99, "V"), + (0x10B9D, "X"), + (0x10BA9, "V"), + (0x10BB0, "X"), + (0x10C00, "V"), + (0x10C49, "X"), + (0x10C80, "M", "𐳀"), + (0x10C81, "M", "𐳁"), + (0x10C82, "M", "𐳂"), + (0x10C83, "M", "𐳃"), + (0x10C84, "M", "𐳄"), + (0x10C85, "M", "𐳅"), + (0x10C86, "M", "𐳆"), + (0x10C87, "M", "𐳇"), + (0x10C88, "M", "𐳈"), + (0x10C89, "M", "𐳉"), + (0x10C8A, "M", "𐳊"), + (0x10C8B, "M", "𐳋"), + (0x10C8C, "M", "𐳌"), + (0x10C8D, "M", "𐳍"), + (0x10C8E, "M", "𐳎"), + (0x10C8F, "M", "𐳏"), + (0x10C90, "M", "𐳐"), + (0x10C91, "M", "𐳑"), + (0x10C92, "M", "𐳒"), + (0x10C93, "M", "𐳓"), + (0x10C94, "M", "𐳔"), + (0x10C95, "M", "𐳕"), + (0x10C96, "M", "𐳖"), + (0x10C97, "M", "𐳗"), + (0x10C98, "M", "𐳘"), + (0x10C99, "M", "𐳙"), + (0x10C9A, "M", "𐳚"), + (0x10C9B, "M", "𐳛"), + (0x10C9C, "M", "𐳜"), + (0x10C9D, "M", "𐳝"), + (0x10C9E, "M", "𐳞"), + (0x10C9F, "M", "𐳟"), + (0x10CA0, "M", "𐳠"), + (0x10CA1, "M", "𐳡"), + (0x10CA2, "M", "𐳢"), + (0x10CA3, "M", "𐳣"), + (0x10CA4, "M", "𐳤"), + (0x10CA5, "M", "𐳥"), + (0x10CA6, "M", "𐳦"), + (0x10CA7, "M", "𐳧"), + (0x10CA8, "M", "𐳨"), + (0x10CA9, "M", "𐳩"), + (0x10CAA, "M", "𐳪"), + (0x10CAB, "M", "𐳫"), + (0x10CAC, "M", "𐳬"), + (0x10CAD, "M", "𐳭"), + (0x10CAE, "M", "𐳮"), + (0x10CAF, "M", "𐳯"), + (0x10CB0, "M", "𐳰"), + (0x10CB1, "M", "𐳱"), + (0x10CB2, "M", "𐳲"), + (0x10CB3, "X"), + (0x10CC0, "V"), + (0x10CF3, "X"), + (0x10CFA, "V"), + (0x10D28, "X"), + (0x10D30, "V"), + (0x10D3A, "X"), + (0x10E60, "V"), + (0x10E7F, "X"), + (0x10E80, "V"), + (0x10EAA, "X"), + (0x10EAB, "V"), + (0x10EAE, "X"), + (0x10EB0, "V"), + (0x10EB2, "X"), + (0x10EFD, "V"), + (0x10F28, "X"), + (0x10F30, "V"), + (0x10F5A, "X"), + (0x10F70, "V"), + (0x10F8A, "X"), + (0x10FB0, "V"), + (0x10FCC, "X"), + (0x10FE0, "V"), + (0x10FF7, "X"), + (0x11000, "V"), + (0x1104E, "X"), + (0x11052, "V"), + (0x11076, "X"), + (0x1107F, "V"), + (0x110BD, "X"), + (0x110BE, "V"), + (0x110C3, "X"), + (0x110D0, "V"), + (0x110E9, "X"), + (0x110F0, "V"), ] + def _seg_57() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x110C3, 'X'), - (0x110D0, 'V'), - (0x110E9, 'X'), - (0x110F0, 'V'), - (0x110FA, 'X'), - (0x11100, 'V'), - (0x11135, 'X'), - (0x11136, 'V'), - (0x11148, 'X'), - (0x11150, 'V'), - (0x11177, 'X'), - (0x11180, 'V'), - (0x111E0, 'X'), - (0x111E1, 'V'), - (0x111F5, 'X'), - (0x11200, 'V'), - (0x11212, 'X'), - (0x11213, 'V'), - (0x11242, 'X'), - (0x11280, 'V'), - (0x11287, 'X'), - (0x11288, 'V'), - (0x11289, 'X'), - (0x1128A, 'V'), - (0x1128E, 'X'), - (0x1128F, 'V'), - (0x1129E, 'X'), - (0x1129F, 'V'), - (0x112AA, 'X'), - (0x112B0, 'V'), - (0x112EB, 'X'), - (0x112F0, 'V'), - (0x112FA, 'X'), - (0x11300, 'V'), - (0x11304, 'X'), - (0x11305, 'V'), - (0x1130D, 'X'), - (0x1130F, 'V'), - (0x11311, 'X'), - (0x11313, 'V'), - (0x11329, 'X'), - (0x1132A, 'V'), - (0x11331, 'X'), - (0x11332, 'V'), - (0x11334, 'X'), - (0x11335, 'V'), - (0x1133A, 'X'), - (0x1133B, 'V'), - (0x11345, 'X'), - (0x11347, 'V'), - (0x11349, 'X'), - (0x1134B, 'V'), - (0x1134E, 'X'), - (0x11350, 'V'), - (0x11351, 'X'), - (0x11357, 'V'), - (0x11358, 'X'), - (0x1135D, 'V'), - (0x11364, 'X'), - (0x11366, 'V'), - (0x1136D, 'X'), - (0x11370, 'V'), - (0x11375, 'X'), - (0x11400, 'V'), - (0x1145C, 'X'), - (0x1145D, 'V'), - (0x11462, 'X'), - (0x11480, 'V'), - (0x114C8, 'X'), - (0x114D0, 'V'), - (0x114DA, 'X'), - (0x11580, 'V'), - (0x115B6, 'X'), - (0x115B8, 'V'), - (0x115DE, 'X'), - (0x11600, 'V'), - (0x11645, 'X'), - (0x11650, 'V'), - (0x1165A, 'X'), - (0x11660, 'V'), - (0x1166D, 'X'), - (0x11680, 'V'), - (0x116BA, 'X'), - (0x116C0, 'V'), - (0x116CA, 'X'), - (0x11700, 'V'), - (0x1171B, 'X'), - (0x1171D, 'V'), - (0x1172C, 'X'), - (0x11730, 'V'), - (0x11747, 'X'), - (0x11800, 'V'), - (0x1183C, 'X'), - (0x118A0, 'M', '𑣀'), - (0x118A1, 'M', '𑣁'), - (0x118A2, 'M', '𑣂'), - (0x118A3, 'M', '𑣃'), - (0x118A4, 'M', '𑣄'), - (0x118A5, 'M', '𑣅'), - (0x118A6, 'M', '𑣆'), + (0x110FA, "X"), + (0x11100, "V"), + (0x11135, "X"), + (0x11136, "V"), + (0x11148, "X"), + (0x11150, "V"), + (0x11177, "X"), + (0x11180, "V"), + (0x111E0, "X"), + (0x111E1, "V"), + (0x111F5, "X"), + (0x11200, "V"), + (0x11212, "X"), + (0x11213, "V"), + (0x11242, "X"), + (0x11280, "V"), + (0x11287, "X"), + (0x11288, "V"), + (0x11289, "X"), + (0x1128A, "V"), + (0x1128E, "X"), + (0x1128F, "V"), + (0x1129E, "X"), + (0x1129F, "V"), + (0x112AA, "X"), + (0x112B0, "V"), + (0x112EB, "X"), + (0x112F0, "V"), + (0x112FA, "X"), + (0x11300, "V"), + (0x11304, "X"), + (0x11305, "V"), + (0x1130D, "X"), + (0x1130F, "V"), + (0x11311, "X"), + (0x11313, "V"), + (0x11329, "X"), + (0x1132A, "V"), + (0x11331, "X"), + (0x11332, "V"), + (0x11334, "X"), + (0x11335, "V"), + (0x1133A, "X"), + (0x1133B, "V"), + (0x11345, "X"), + (0x11347, "V"), + (0x11349, "X"), + (0x1134B, "V"), + (0x1134E, "X"), + (0x11350, "V"), + (0x11351, "X"), + (0x11357, "V"), + (0x11358, "X"), + (0x1135D, "V"), + (0x11364, "X"), + (0x11366, "V"), + (0x1136D, "X"), + (0x11370, "V"), + (0x11375, "X"), + (0x11400, "V"), + (0x1145C, "X"), + (0x1145D, "V"), + (0x11462, "X"), + (0x11480, "V"), + (0x114C8, "X"), + (0x114D0, "V"), + (0x114DA, "X"), + (0x11580, "V"), + (0x115B6, "X"), + (0x115B8, "V"), + (0x115DE, "X"), + (0x11600, "V"), + (0x11645, "X"), + (0x11650, "V"), + (0x1165A, "X"), + (0x11660, "V"), + (0x1166D, "X"), + (0x11680, "V"), + (0x116BA, "X"), + (0x116C0, "V"), + (0x116CA, "X"), + (0x11700, "V"), + (0x1171B, "X"), + (0x1171D, "V"), + (0x1172C, "X"), + (0x11730, "V"), + (0x11747, "X"), + (0x11800, "V"), + (0x1183C, "X"), + (0x118A0, "M", "𑣀"), + (0x118A1, "M", "𑣁"), + (0x118A2, "M", "𑣂"), + (0x118A3, "M", "𑣃"), + (0x118A4, "M", "𑣄"), + (0x118A5, "M", "𑣅"), + (0x118A6, "M", "𑣆"), + (0x118A7, "M", "𑣇"), + (0x118A8, "M", "𑣈"), + (0x118A9, "M", "𑣉"), + (0x118AA, "M", "𑣊"), ] + def _seg_58() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x118A7, 'M', '𑣇'), - (0x118A8, 'M', '𑣈'), - (0x118A9, 'M', '𑣉'), - (0x118AA, 'M', '𑣊'), - (0x118AB, 'M', '𑣋'), - (0x118AC, 'M', '𑣌'), - (0x118AD, 'M', '𑣍'), - (0x118AE, 'M', '𑣎'), - (0x118AF, 'M', '𑣏'), - (0x118B0, 'M', '𑣐'), - (0x118B1, 'M', '𑣑'), - (0x118B2, 'M', '𑣒'), - (0x118B3, 'M', '𑣓'), - (0x118B4, 'M', '𑣔'), - (0x118B5, 'M', '𑣕'), - (0x118B6, 'M', '𑣖'), - (0x118B7, 'M', '𑣗'), - (0x118B8, 'M', '𑣘'), - (0x118B9, 'M', '𑣙'), - (0x118BA, 'M', '𑣚'), - (0x118BB, 'M', '𑣛'), - (0x118BC, 'M', '𑣜'), - (0x118BD, 'M', '𑣝'), - (0x118BE, 'M', '𑣞'), - (0x118BF, 'M', '𑣟'), - (0x118C0, 'V'), - (0x118F3, 'X'), - (0x118FF, 'V'), - (0x11907, 'X'), - (0x11909, 'V'), - (0x1190A, 'X'), - (0x1190C, 'V'), - (0x11914, 'X'), - (0x11915, 'V'), - (0x11917, 'X'), - (0x11918, 'V'), - (0x11936, 'X'), - (0x11937, 'V'), - (0x11939, 'X'), - (0x1193B, 'V'), - (0x11947, 'X'), - (0x11950, 'V'), - (0x1195A, 'X'), - (0x119A0, 'V'), - (0x119A8, 'X'), - (0x119AA, 'V'), - (0x119D8, 'X'), - (0x119DA, 'V'), - (0x119E5, 'X'), - (0x11A00, 'V'), - (0x11A48, 'X'), - (0x11A50, 'V'), - (0x11AA3, 'X'), - (0x11AB0, 'V'), - (0x11AF9, 'X'), - (0x11B00, 'V'), - (0x11B0A, 'X'), - (0x11C00, 'V'), - (0x11C09, 'X'), - (0x11C0A, 'V'), - (0x11C37, 'X'), - (0x11C38, 'V'), - (0x11C46, 'X'), - (0x11C50, 'V'), - (0x11C6D, 'X'), - (0x11C70, 'V'), - (0x11C90, 'X'), - (0x11C92, 'V'), - (0x11CA8, 'X'), - (0x11CA9, 'V'), - (0x11CB7, 'X'), - (0x11D00, 'V'), - (0x11D07, 'X'), - (0x11D08, 'V'), - (0x11D0A, 'X'), - (0x11D0B, 'V'), - (0x11D37, 'X'), - (0x11D3A, 'V'), - (0x11D3B, 'X'), - (0x11D3C, 'V'), - (0x11D3E, 'X'), - (0x11D3F, 'V'), - (0x11D48, 'X'), - (0x11D50, 'V'), - (0x11D5A, 'X'), - (0x11D60, 'V'), - (0x11D66, 'X'), - (0x11D67, 'V'), - (0x11D69, 'X'), - (0x11D6A, 'V'), - (0x11D8F, 'X'), - (0x11D90, 'V'), - (0x11D92, 'X'), - (0x11D93, 'V'), - (0x11D99, 'X'), - (0x11DA0, 'V'), - (0x11DAA, 'X'), - (0x11EE0, 'V'), - (0x11EF9, 'X'), - (0x11F00, 'V'), + (0x118AB, "M", "𑣋"), + (0x118AC, "M", "𑣌"), + (0x118AD, "M", "𑣍"), + (0x118AE, "M", "𑣎"), + (0x118AF, "M", "𑣏"), + (0x118B0, "M", "𑣐"), + (0x118B1, "M", "𑣑"), + (0x118B2, "M", "𑣒"), + (0x118B3, "M", "𑣓"), + (0x118B4, "M", "𑣔"), + (0x118B5, "M", "𑣕"), + (0x118B6, "M", "𑣖"), + (0x118B7, "M", "𑣗"), + (0x118B8, "M", "𑣘"), + (0x118B9, "M", "𑣙"), + (0x118BA, "M", "𑣚"), + (0x118BB, "M", "𑣛"), + (0x118BC, "M", "𑣜"), + (0x118BD, "M", "𑣝"), + (0x118BE, "M", "𑣞"), + (0x118BF, "M", "𑣟"), + (0x118C0, "V"), + (0x118F3, "X"), + (0x118FF, "V"), + (0x11907, "X"), + (0x11909, "V"), + (0x1190A, "X"), + (0x1190C, "V"), + (0x11914, "X"), + (0x11915, "V"), + (0x11917, "X"), + (0x11918, "V"), + (0x11936, "X"), + (0x11937, "V"), + (0x11939, "X"), + (0x1193B, "V"), + (0x11947, "X"), + (0x11950, "V"), + (0x1195A, "X"), + (0x119A0, "V"), + (0x119A8, "X"), + (0x119AA, "V"), + (0x119D8, "X"), + (0x119DA, "V"), + (0x119E5, "X"), + (0x11A00, "V"), + (0x11A48, "X"), + (0x11A50, "V"), + (0x11AA3, "X"), + (0x11AB0, "V"), + (0x11AF9, "X"), + (0x11B00, "V"), + (0x11B0A, "X"), + (0x11C00, "V"), + (0x11C09, "X"), + (0x11C0A, "V"), + (0x11C37, "X"), + (0x11C38, "V"), + (0x11C46, "X"), + (0x11C50, "V"), + (0x11C6D, "X"), + (0x11C70, "V"), + (0x11C90, "X"), + (0x11C92, "V"), + (0x11CA8, "X"), + (0x11CA9, "V"), + (0x11CB7, "X"), + (0x11D00, "V"), + (0x11D07, "X"), + (0x11D08, "V"), + (0x11D0A, "X"), + (0x11D0B, "V"), + (0x11D37, "X"), + (0x11D3A, "V"), + (0x11D3B, "X"), + (0x11D3C, "V"), + (0x11D3E, "X"), + (0x11D3F, "V"), + (0x11D48, "X"), + (0x11D50, "V"), + (0x11D5A, "X"), + (0x11D60, "V"), + (0x11D66, "X"), + (0x11D67, "V"), + (0x11D69, "X"), + (0x11D6A, "V"), + (0x11D8F, "X"), + (0x11D90, "V"), + (0x11D92, "X"), + (0x11D93, "V"), + (0x11D99, "X"), + (0x11DA0, "V"), + (0x11DAA, "X"), + (0x11EE0, "V"), + (0x11EF9, "X"), + (0x11F00, "V"), + (0x11F11, "X"), + (0x11F12, "V"), + (0x11F3B, "X"), + (0x11F3E, "V"), ] + def _seg_59() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x11F11, 'X'), - (0x11F12, 'V'), - (0x11F3B, 'X'), - (0x11F3E, 'V'), - (0x11F5A, 'X'), - (0x11FB0, 'V'), - (0x11FB1, 'X'), - (0x11FC0, 'V'), - (0x11FF2, 'X'), - (0x11FFF, 'V'), - (0x1239A, 'X'), - (0x12400, 'V'), - (0x1246F, 'X'), - (0x12470, 'V'), - (0x12475, 'X'), - (0x12480, 'V'), - (0x12544, 'X'), - (0x12F90, 'V'), - (0x12FF3, 'X'), - (0x13000, 'V'), - (0x13430, 'X'), - (0x13440, 'V'), - (0x13456, 'X'), - (0x14400, 'V'), - (0x14647, 'X'), - (0x16800, 'V'), - (0x16A39, 'X'), - (0x16A40, 'V'), - (0x16A5F, 'X'), - (0x16A60, 'V'), - (0x16A6A, 'X'), - (0x16A6E, 'V'), - (0x16ABF, 'X'), - (0x16AC0, 'V'), - (0x16ACA, 'X'), - (0x16AD0, 'V'), - (0x16AEE, 'X'), - (0x16AF0, 'V'), - (0x16AF6, 'X'), - (0x16B00, 'V'), - (0x16B46, 'X'), - (0x16B50, 'V'), - (0x16B5A, 'X'), - (0x16B5B, 'V'), - (0x16B62, 'X'), - (0x16B63, 'V'), - (0x16B78, 'X'), - (0x16B7D, 'V'), - (0x16B90, 'X'), - (0x16E40, 'M', '𖹠'), - (0x16E41, 'M', '𖹡'), - (0x16E42, 'M', '𖹢'), - (0x16E43, 'M', '𖹣'), - (0x16E44, 'M', '𖹤'), - (0x16E45, 'M', '𖹥'), - (0x16E46, 'M', '𖹦'), - (0x16E47, 'M', '𖹧'), - (0x16E48, 'M', '𖹨'), - (0x16E49, 'M', '𖹩'), - (0x16E4A, 'M', '𖹪'), - (0x16E4B, 'M', '𖹫'), - (0x16E4C, 'M', '𖹬'), - (0x16E4D, 'M', '𖹭'), - (0x16E4E, 'M', '𖹮'), - (0x16E4F, 'M', '𖹯'), - (0x16E50, 'M', '𖹰'), - (0x16E51, 'M', '𖹱'), - (0x16E52, 'M', '𖹲'), - (0x16E53, 'M', '𖹳'), - (0x16E54, 'M', '𖹴'), - (0x16E55, 'M', '𖹵'), - (0x16E56, 'M', '𖹶'), - (0x16E57, 'M', '𖹷'), - (0x16E58, 'M', '𖹸'), - (0x16E59, 'M', '𖹹'), - (0x16E5A, 'M', '𖹺'), - (0x16E5B, 'M', '𖹻'), - (0x16E5C, 'M', '𖹼'), - (0x16E5D, 'M', '𖹽'), - (0x16E5E, 'M', '𖹾'), - (0x16E5F, 'M', '𖹿'), - (0x16E60, 'V'), - (0x16E9B, 'X'), - (0x16F00, 'V'), - (0x16F4B, 'X'), - (0x16F4F, 'V'), - (0x16F88, 'X'), - (0x16F8F, 'V'), - (0x16FA0, 'X'), - (0x16FE0, 'V'), - (0x16FE5, 'X'), - (0x16FF0, 'V'), - (0x16FF2, 'X'), - (0x17000, 'V'), - (0x187F8, 'X'), - (0x18800, 'V'), - (0x18CD6, 'X'), - (0x18D00, 'V'), - (0x18D09, 'X'), - (0x1AFF0, 'V'), + (0x11F5A, "X"), + (0x11FB0, "V"), + (0x11FB1, "X"), + (0x11FC0, "V"), + (0x11FF2, "X"), + (0x11FFF, "V"), + (0x1239A, "X"), + (0x12400, "V"), + (0x1246F, "X"), + (0x12470, "V"), + (0x12475, "X"), + (0x12480, "V"), + (0x12544, "X"), + (0x12F90, "V"), + (0x12FF3, "X"), + (0x13000, "V"), + (0x13430, "X"), + (0x13440, "V"), + (0x13456, "X"), + (0x14400, "V"), + (0x14647, "X"), + (0x16800, "V"), + (0x16A39, "X"), + (0x16A40, "V"), + (0x16A5F, "X"), + (0x16A60, "V"), + (0x16A6A, "X"), + (0x16A6E, "V"), + (0x16ABF, "X"), + (0x16AC0, "V"), + (0x16ACA, "X"), + (0x16AD0, "V"), + (0x16AEE, "X"), + (0x16AF0, "V"), + (0x16AF6, "X"), + (0x16B00, "V"), + (0x16B46, "X"), + (0x16B50, "V"), + (0x16B5A, "X"), + (0x16B5B, "V"), + (0x16B62, "X"), + (0x16B63, "V"), + (0x16B78, "X"), + (0x16B7D, "V"), + (0x16B90, "X"), + (0x16E40, "M", "𖹠"), + (0x16E41, "M", "𖹡"), + (0x16E42, "M", "𖹢"), + (0x16E43, "M", "𖹣"), + (0x16E44, "M", "𖹤"), + (0x16E45, "M", "𖹥"), + (0x16E46, "M", "𖹦"), + (0x16E47, "M", "𖹧"), + (0x16E48, "M", "𖹨"), + (0x16E49, "M", "𖹩"), + (0x16E4A, "M", "𖹪"), + (0x16E4B, "M", "𖹫"), + (0x16E4C, "M", "𖹬"), + (0x16E4D, "M", "𖹭"), + (0x16E4E, "M", "𖹮"), + (0x16E4F, "M", "𖹯"), + (0x16E50, "M", "𖹰"), + (0x16E51, "M", "𖹱"), + (0x16E52, "M", "𖹲"), + (0x16E53, "M", "𖹳"), + (0x16E54, "M", "𖹴"), + (0x16E55, "M", "𖹵"), + (0x16E56, "M", "𖹶"), + (0x16E57, "M", "𖹷"), + (0x16E58, "M", "𖹸"), + (0x16E59, "M", "𖹹"), + (0x16E5A, "M", "𖹺"), + (0x16E5B, "M", "𖹻"), + (0x16E5C, "M", "𖹼"), + (0x16E5D, "M", "𖹽"), + (0x16E5E, "M", "𖹾"), + (0x16E5F, "M", "𖹿"), + (0x16E60, "V"), + (0x16E9B, "X"), + (0x16F00, "V"), + (0x16F4B, "X"), + (0x16F4F, "V"), + (0x16F88, "X"), + (0x16F8F, "V"), + (0x16FA0, "X"), + (0x16FE0, "V"), + (0x16FE5, "X"), + (0x16FF0, "V"), + (0x16FF2, "X"), + (0x17000, "V"), + (0x187F8, "X"), + (0x18800, "V"), + (0x18CD6, "X"), + (0x18D00, "V"), + (0x18D09, "X"), + (0x1AFF0, "V"), + (0x1AFF4, "X"), + (0x1AFF5, "V"), + (0x1AFFC, "X"), + (0x1AFFD, "V"), ] + def _seg_60() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1AFF4, 'X'), - (0x1AFF5, 'V'), - (0x1AFFC, 'X'), - (0x1AFFD, 'V'), - (0x1AFFF, 'X'), - (0x1B000, 'V'), - (0x1B123, 'X'), - (0x1B132, 'V'), - (0x1B133, 'X'), - (0x1B150, 'V'), - (0x1B153, 'X'), - (0x1B155, 'V'), - (0x1B156, 'X'), - (0x1B164, 'V'), - (0x1B168, 'X'), - (0x1B170, 'V'), - (0x1B2FC, 'X'), - (0x1BC00, 'V'), - (0x1BC6B, 'X'), - (0x1BC70, 'V'), - (0x1BC7D, 'X'), - (0x1BC80, 'V'), - (0x1BC89, 'X'), - (0x1BC90, 'V'), - (0x1BC9A, 'X'), - (0x1BC9C, 'V'), - (0x1BCA0, 'I'), - (0x1BCA4, 'X'), - (0x1CF00, 'V'), - (0x1CF2E, 'X'), - (0x1CF30, 'V'), - (0x1CF47, 'X'), - (0x1CF50, 'V'), - (0x1CFC4, 'X'), - (0x1D000, 'V'), - (0x1D0F6, 'X'), - (0x1D100, 'V'), - (0x1D127, 'X'), - (0x1D129, 'V'), - (0x1D15E, 'M', '𝅗𝅥'), - (0x1D15F, 'M', '𝅘𝅥'), - (0x1D160, 'M', '𝅘𝅥𝅮'), - (0x1D161, 'M', '𝅘𝅥𝅯'), - (0x1D162, 'M', '𝅘𝅥𝅰'), - (0x1D163, 'M', '𝅘𝅥𝅱'), - (0x1D164, 'M', '𝅘𝅥𝅲'), - (0x1D165, 'V'), - (0x1D173, 'X'), - (0x1D17B, 'V'), - (0x1D1BB, 'M', '𝆹𝅥'), - (0x1D1BC, 'M', '𝆺𝅥'), - (0x1D1BD, 'M', '𝆹𝅥𝅮'), - (0x1D1BE, 'M', '𝆺𝅥𝅮'), - (0x1D1BF, 'M', '𝆹𝅥𝅯'), - (0x1D1C0, 'M', '𝆺𝅥𝅯'), - (0x1D1C1, 'V'), - (0x1D1EB, 'X'), - (0x1D200, 'V'), - (0x1D246, 'X'), - (0x1D2C0, 'V'), - (0x1D2D4, 'X'), - (0x1D2E0, 'V'), - (0x1D2F4, 'X'), - (0x1D300, 'V'), - (0x1D357, 'X'), - (0x1D360, 'V'), - (0x1D379, 'X'), - (0x1D400, 'M', 'a'), - (0x1D401, 'M', 'b'), - (0x1D402, 'M', 'c'), - (0x1D403, 'M', 'd'), - (0x1D404, 'M', 'e'), - (0x1D405, 'M', 'f'), - (0x1D406, 'M', 'g'), - (0x1D407, 'M', 'h'), - (0x1D408, 'M', 'i'), - (0x1D409, 'M', 'j'), - (0x1D40A, 'M', 'k'), - (0x1D40B, 'M', 'l'), - (0x1D40C, 'M', 'm'), - (0x1D40D, 'M', 'n'), - (0x1D40E, 'M', 'o'), - (0x1D40F, 'M', 'p'), - (0x1D410, 'M', 'q'), - (0x1D411, 'M', 'r'), - (0x1D412, 'M', 's'), - (0x1D413, 'M', 't'), - (0x1D414, 'M', 'u'), - (0x1D415, 'M', 'v'), - (0x1D416, 'M', 'w'), - (0x1D417, 'M', 'x'), - (0x1D418, 'M', 'y'), - (0x1D419, 'M', 'z'), - (0x1D41A, 'M', 'a'), - (0x1D41B, 'M', 'b'), - (0x1D41C, 'M', 'c'), - (0x1D41D, 'M', 'd'), - (0x1D41E, 'M', 'e'), - (0x1D41F, 'M', 'f'), - (0x1D420, 'M', 'g'), + (0x1AFFF, "X"), + (0x1B000, "V"), + (0x1B123, "X"), + (0x1B132, "V"), + (0x1B133, "X"), + (0x1B150, "V"), + (0x1B153, "X"), + (0x1B155, "V"), + (0x1B156, "X"), + (0x1B164, "V"), + (0x1B168, "X"), + (0x1B170, "V"), + (0x1B2FC, "X"), + (0x1BC00, "V"), + (0x1BC6B, "X"), + (0x1BC70, "V"), + (0x1BC7D, "X"), + (0x1BC80, "V"), + (0x1BC89, "X"), + (0x1BC90, "V"), + (0x1BC9A, "X"), + (0x1BC9C, "V"), + (0x1BCA0, "I"), + (0x1BCA4, "X"), + (0x1CF00, "V"), + (0x1CF2E, "X"), + (0x1CF30, "V"), + (0x1CF47, "X"), + (0x1CF50, "V"), + (0x1CFC4, "X"), + (0x1D000, "V"), + (0x1D0F6, "X"), + (0x1D100, "V"), + (0x1D127, "X"), + (0x1D129, "V"), + (0x1D15E, "M", "𝅗𝅥"), + (0x1D15F, "M", "𝅘𝅥"), + (0x1D160, "M", "𝅘𝅥𝅮"), + (0x1D161, "M", "𝅘𝅥𝅯"), + (0x1D162, "M", "𝅘𝅥𝅰"), + (0x1D163, "M", "𝅘𝅥𝅱"), + (0x1D164, "M", "𝅘𝅥𝅲"), + (0x1D165, "V"), + (0x1D173, "X"), + (0x1D17B, "V"), + (0x1D1BB, "M", "𝆹𝅥"), + (0x1D1BC, "M", "𝆺𝅥"), + (0x1D1BD, "M", "𝆹𝅥𝅮"), + (0x1D1BE, "M", "𝆺𝅥𝅮"), + (0x1D1BF, "M", "𝆹𝅥𝅯"), + (0x1D1C0, "M", "𝆺𝅥𝅯"), + (0x1D1C1, "V"), + (0x1D1EB, "X"), + (0x1D200, "V"), + (0x1D246, "X"), + (0x1D2C0, "V"), + (0x1D2D4, "X"), + (0x1D2E0, "V"), + (0x1D2F4, "X"), + (0x1D300, "V"), + (0x1D357, "X"), + (0x1D360, "V"), + (0x1D379, "X"), + (0x1D400, "M", "a"), + (0x1D401, "M", "b"), + (0x1D402, "M", "c"), + (0x1D403, "M", "d"), + (0x1D404, "M", "e"), + (0x1D405, "M", "f"), + (0x1D406, "M", "g"), + (0x1D407, "M", "h"), + (0x1D408, "M", "i"), + (0x1D409, "M", "j"), + (0x1D40A, "M", "k"), + (0x1D40B, "M", "l"), + (0x1D40C, "M", "m"), + (0x1D40D, "M", "n"), + (0x1D40E, "M", "o"), + (0x1D40F, "M", "p"), + (0x1D410, "M", "q"), + (0x1D411, "M", "r"), + (0x1D412, "M", "s"), + (0x1D413, "M", "t"), + (0x1D414, "M", "u"), + (0x1D415, "M", "v"), + (0x1D416, "M", "w"), + (0x1D417, "M", "x"), + (0x1D418, "M", "y"), + (0x1D419, "M", "z"), + (0x1D41A, "M", "a"), + (0x1D41B, "M", "b"), + (0x1D41C, "M", "c"), + (0x1D41D, "M", "d"), + (0x1D41E, "M", "e"), + (0x1D41F, "M", "f"), + (0x1D420, "M", "g"), + (0x1D421, "M", "h"), + (0x1D422, "M", "i"), + (0x1D423, "M", "j"), + (0x1D424, "M", "k"), ] + def _seg_61() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D421, 'M', 'h'), - (0x1D422, 'M', 'i'), - (0x1D423, 'M', 'j'), - (0x1D424, 'M', 'k'), - (0x1D425, 'M', 'l'), - (0x1D426, 'M', 'm'), - (0x1D427, 'M', 'n'), - (0x1D428, 'M', 'o'), - (0x1D429, 'M', 'p'), - (0x1D42A, 'M', 'q'), - (0x1D42B, 'M', 'r'), - (0x1D42C, 'M', 's'), - (0x1D42D, 'M', 't'), - (0x1D42E, 'M', 'u'), - (0x1D42F, 'M', 'v'), - (0x1D430, 'M', 'w'), - (0x1D431, 'M', 'x'), - (0x1D432, 'M', 'y'), - (0x1D433, 'M', 'z'), - (0x1D434, 'M', 'a'), - (0x1D435, 'M', 'b'), - (0x1D436, 'M', 'c'), - (0x1D437, 'M', 'd'), - (0x1D438, 'M', 'e'), - (0x1D439, 'M', 'f'), - (0x1D43A, 'M', 'g'), - (0x1D43B, 'M', 'h'), - (0x1D43C, 'M', 'i'), - (0x1D43D, 'M', 'j'), - (0x1D43E, 'M', 'k'), - (0x1D43F, 'M', 'l'), - (0x1D440, 'M', 'm'), - (0x1D441, 'M', 'n'), - (0x1D442, 'M', 'o'), - (0x1D443, 'M', 'p'), - (0x1D444, 'M', 'q'), - (0x1D445, 'M', 'r'), - (0x1D446, 'M', 's'), - (0x1D447, 'M', 't'), - (0x1D448, 'M', 'u'), - (0x1D449, 'M', 'v'), - (0x1D44A, 'M', 'w'), - (0x1D44B, 'M', 'x'), - (0x1D44C, 'M', 'y'), - (0x1D44D, 'M', 'z'), - (0x1D44E, 'M', 'a'), - (0x1D44F, 'M', 'b'), - (0x1D450, 'M', 'c'), - (0x1D451, 'M', 'd'), - (0x1D452, 'M', 'e'), - (0x1D453, 'M', 'f'), - (0x1D454, 'M', 'g'), - (0x1D455, 'X'), - (0x1D456, 'M', 'i'), - (0x1D457, 'M', 'j'), - (0x1D458, 'M', 'k'), - (0x1D459, 'M', 'l'), - (0x1D45A, 'M', 'm'), - (0x1D45B, 'M', 'n'), - (0x1D45C, 'M', 'o'), - (0x1D45D, 'M', 'p'), - (0x1D45E, 'M', 'q'), - (0x1D45F, 'M', 'r'), - (0x1D460, 'M', 's'), - (0x1D461, 'M', 't'), - (0x1D462, 'M', 'u'), - (0x1D463, 'M', 'v'), - (0x1D464, 'M', 'w'), - (0x1D465, 'M', 'x'), - (0x1D466, 'M', 'y'), - (0x1D467, 'M', 'z'), - (0x1D468, 'M', 'a'), - (0x1D469, 'M', 'b'), - (0x1D46A, 'M', 'c'), - (0x1D46B, 'M', 'd'), - (0x1D46C, 'M', 'e'), - (0x1D46D, 'M', 'f'), - (0x1D46E, 'M', 'g'), - (0x1D46F, 'M', 'h'), - (0x1D470, 'M', 'i'), - (0x1D471, 'M', 'j'), - (0x1D472, 'M', 'k'), - (0x1D473, 'M', 'l'), - (0x1D474, 'M', 'm'), - (0x1D475, 'M', 'n'), - (0x1D476, 'M', 'o'), - (0x1D477, 'M', 'p'), - (0x1D478, 'M', 'q'), - (0x1D479, 'M', 'r'), - (0x1D47A, 'M', 's'), - (0x1D47B, 'M', 't'), - (0x1D47C, 'M', 'u'), - (0x1D47D, 'M', 'v'), - (0x1D47E, 'M', 'w'), - (0x1D47F, 'M', 'x'), - (0x1D480, 'M', 'y'), - (0x1D481, 'M', 'z'), - (0x1D482, 'M', 'a'), - (0x1D483, 'M', 'b'), - (0x1D484, 'M', 'c'), + (0x1D425, "M", "l"), + (0x1D426, "M", "m"), + (0x1D427, "M", "n"), + (0x1D428, "M", "o"), + (0x1D429, "M", "p"), + (0x1D42A, "M", "q"), + (0x1D42B, "M", "r"), + (0x1D42C, "M", "s"), + (0x1D42D, "M", "t"), + (0x1D42E, "M", "u"), + (0x1D42F, "M", "v"), + (0x1D430, "M", "w"), + (0x1D431, "M", "x"), + (0x1D432, "M", "y"), + (0x1D433, "M", "z"), + (0x1D434, "M", "a"), + (0x1D435, "M", "b"), + (0x1D436, "M", "c"), + (0x1D437, "M", "d"), + (0x1D438, "M", "e"), + (0x1D439, "M", "f"), + (0x1D43A, "M", "g"), + (0x1D43B, "M", "h"), + (0x1D43C, "M", "i"), + (0x1D43D, "M", "j"), + (0x1D43E, "M", "k"), + (0x1D43F, "M", "l"), + (0x1D440, "M", "m"), + (0x1D441, "M", "n"), + (0x1D442, "M", "o"), + (0x1D443, "M", "p"), + (0x1D444, "M", "q"), + (0x1D445, "M", "r"), + (0x1D446, "M", "s"), + (0x1D447, "M", "t"), + (0x1D448, "M", "u"), + (0x1D449, "M", "v"), + (0x1D44A, "M", "w"), + (0x1D44B, "M", "x"), + (0x1D44C, "M", "y"), + (0x1D44D, "M", "z"), + (0x1D44E, "M", "a"), + (0x1D44F, "M", "b"), + (0x1D450, "M", "c"), + (0x1D451, "M", "d"), + (0x1D452, "M", "e"), + (0x1D453, "M", "f"), + (0x1D454, "M", "g"), + (0x1D455, "X"), + (0x1D456, "M", "i"), + (0x1D457, "M", "j"), + (0x1D458, "M", "k"), + (0x1D459, "M", "l"), + (0x1D45A, "M", "m"), + (0x1D45B, "M", "n"), + (0x1D45C, "M", "o"), + (0x1D45D, "M", "p"), + (0x1D45E, "M", "q"), + (0x1D45F, "M", "r"), + (0x1D460, "M", "s"), + (0x1D461, "M", "t"), + (0x1D462, "M", "u"), + (0x1D463, "M", "v"), + (0x1D464, "M", "w"), + (0x1D465, "M", "x"), + (0x1D466, "M", "y"), + (0x1D467, "M", "z"), + (0x1D468, "M", "a"), + (0x1D469, "M", "b"), + (0x1D46A, "M", "c"), + (0x1D46B, "M", "d"), + (0x1D46C, "M", "e"), + (0x1D46D, "M", "f"), + (0x1D46E, "M", "g"), + (0x1D46F, "M", "h"), + (0x1D470, "M", "i"), + (0x1D471, "M", "j"), + (0x1D472, "M", "k"), + (0x1D473, "M", "l"), + (0x1D474, "M", "m"), + (0x1D475, "M", "n"), + (0x1D476, "M", "o"), + (0x1D477, "M", "p"), + (0x1D478, "M", "q"), + (0x1D479, "M", "r"), + (0x1D47A, "M", "s"), + (0x1D47B, "M", "t"), + (0x1D47C, "M", "u"), + (0x1D47D, "M", "v"), + (0x1D47E, "M", "w"), + (0x1D47F, "M", "x"), + (0x1D480, "M", "y"), + (0x1D481, "M", "z"), + (0x1D482, "M", "a"), + (0x1D483, "M", "b"), + (0x1D484, "M", "c"), + (0x1D485, "M", "d"), + (0x1D486, "M", "e"), + (0x1D487, "M", "f"), + (0x1D488, "M", "g"), ] + def _seg_62() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D485, 'M', 'd'), - (0x1D486, 'M', 'e'), - (0x1D487, 'M', 'f'), - (0x1D488, 'M', 'g'), - (0x1D489, 'M', 'h'), - (0x1D48A, 'M', 'i'), - (0x1D48B, 'M', 'j'), - (0x1D48C, 'M', 'k'), - (0x1D48D, 'M', 'l'), - (0x1D48E, 'M', 'm'), - (0x1D48F, 'M', 'n'), - (0x1D490, 'M', 'o'), - (0x1D491, 'M', 'p'), - (0x1D492, 'M', 'q'), - (0x1D493, 'M', 'r'), - (0x1D494, 'M', 's'), - (0x1D495, 'M', 't'), - (0x1D496, 'M', 'u'), - (0x1D497, 'M', 'v'), - (0x1D498, 'M', 'w'), - (0x1D499, 'M', 'x'), - (0x1D49A, 'M', 'y'), - (0x1D49B, 'M', 'z'), - (0x1D49C, 'M', 'a'), - (0x1D49D, 'X'), - (0x1D49E, 'M', 'c'), - (0x1D49F, 'M', 'd'), - (0x1D4A0, 'X'), - (0x1D4A2, 'M', 'g'), - (0x1D4A3, 'X'), - (0x1D4A5, 'M', 'j'), - (0x1D4A6, 'M', 'k'), - (0x1D4A7, 'X'), - (0x1D4A9, 'M', 'n'), - (0x1D4AA, 'M', 'o'), - (0x1D4AB, 'M', 'p'), - (0x1D4AC, 'M', 'q'), - (0x1D4AD, 'X'), - (0x1D4AE, 'M', 's'), - (0x1D4AF, 'M', 't'), - (0x1D4B0, 'M', 'u'), - (0x1D4B1, 'M', 'v'), - (0x1D4B2, 'M', 'w'), - (0x1D4B3, 'M', 'x'), - (0x1D4B4, 'M', 'y'), - (0x1D4B5, 'M', 'z'), - (0x1D4B6, 'M', 'a'), - (0x1D4B7, 'M', 'b'), - (0x1D4B8, 'M', 'c'), - (0x1D4B9, 'M', 'd'), - (0x1D4BA, 'X'), - (0x1D4BB, 'M', 'f'), - (0x1D4BC, 'X'), - (0x1D4BD, 'M', 'h'), - (0x1D4BE, 'M', 'i'), - (0x1D4BF, 'M', 'j'), - (0x1D4C0, 'M', 'k'), - (0x1D4C1, 'M', 'l'), - (0x1D4C2, 'M', 'm'), - (0x1D4C3, 'M', 'n'), - (0x1D4C4, 'X'), - (0x1D4C5, 'M', 'p'), - (0x1D4C6, 'M', 'q'), - (0x1D4C7, 'M', 'r'), - (0x1D4C8, 'M', 's'), - (0x1D4C9, 'M', 't'), - (0x1D4CA, 'M', 'u'), - (0x1D4CB, 'M', 'v'), - (0x1D4CC, 'M', 'w'), - (0x1D4CD, 'M', 'x'), - (0x1D4CE, 'M', 'y'), - (0x1D4CF, 'M', 'z'), - (0x1D4D0, 'M', 'a'), - (0x1D4D1, 'M', 'b'), - (0x1D4D2, 'M', 'c'), - (0x1D4D3, 'M', 'd'), - (0x1D4D4, 'M', 'e'), - (0x1D4D5, 'M', 'f'), - (0x1D4D6, 'M', 'g'), - (0x1D4D7, 'M', 'h'), - (0x1D4D8, 'M', 'i'), - (0x1D4D9, 'M', 'j'), - (0x1D4DA, 'M', 'k'), - (0x1D4DB, 'M', 'l'), - (0x1D4DC, 'M', 'm'), - (0x1D4DD, 'M', 'n'), - (0x1D4DE, 'M', 'o'), - (0x1D4DF, 'M', 'p'), - (0x1D4E0, 'M', 'q'), - (0x1D4E1, 'M', 'r'), - (0x1D4E2, 'M', 's'), - (0x1D4E3, 'M', 't'), - (0x1D4E4, 'M', 'u'), - (0x1D4E5, 'M', 'v'), - (0x1D4E6, 'M', 'w'), - (0x1D4E7, 'M', 'x'), - (0x1D4E8, 'M', 'y'), - (0x1D4E9, 'M', 'z'), - (0x1D4EA, 'M', 'a'), - (0x1D4EB, 'M', 'b'), + (0x1D489, "M", "h"), + (0x1D48A, "M", "i"), + (0x1D48B, "M", "j"), + (0x1D48C, "M", "k"), + (0x1D48D, "M", "l"), + (0x1D48E, "M", "m"), + (0x1D48F, "M", "n"), + (0x1D490, "M", "o"), + (0x1D491, "M", "p"), + (0x1D492, "M", "q"), + (0x1D493, "M", "r"), + (0x1D494, "M", "s"), + (0x1D495, "M", "t"), + (0x1D496, "M", "u"), + (0x1D497, "M", "v"), + (0x1D498, "M", "w"), + (0x1D499, "M", "x"), + (0x1D49A, "M", "y"), + (0x1D49B, "M", "z"), + (0x1D49C, "M", "a"), + (0x1D49D, "X"), + (0x1D49E, "M", "c"), + (0x1D49F, "M", "d"), + (0x1D4A0, "X"), + (0x1D4A2, "M", "g"), + (0x1D4A3, "X"), + (0x1D4A5, "M", "j"), + (0x1D4A6, "M", "k"), + (0x1D4A7, "X"), + (0x1D4A9, "M", "n"), + (0x1D4AA, "M", "o"), + (0x1D4AB, "M", "p"), + (0x1D4AC, "M", "q"), + (0x1D4AD, "X"), + (0x1D4AE, "M", "s"), + (0x1D4AF, "M", "t"), + (0x1D4B0, "M", "u"), + (0x1D4B1, "M", "v"), + (0x1D4B2, "M", "w"), + (0x1D4B3, "M", "x"), + (0x1D4B4, "M", "y"), + (0x1D4B5, "M", "z"), + (0x1D4B6, "M", "a"), + (0x1D4B7, "M", "b"), + (0x1D4B8, "M", "c"), + (0x1D4B9, "M", "d"), + (0x1D4BA, "X"), + (0x1D4BB, "M", "f"), + (0x1D4BC, "X"), + (0x1D4BD, "M", "h"), + (0x1D4BE, "M", "i"), + (0x1D4BF, "M", "j"), + (0x1D4C0, "M", "k"), + (0x1D4C1, "M", "l"), + (0x1D4C2, "M", "m"), + (0x1D4C3, "M", "n"), + (0x1D4C4, "X"), + (0x1D4C5, "M", "p"), + (0x1D4C6, "M", "q"), + (0x1D4C7, "M", "r"), + (0x1D4C8, "M", "s"), + (0x1D4C9, "M", "t"), + (0x1D4CA, "M", "u"), + (0x1D4CB, "M", "v"), + (0x1D4CC, "M", "w"), + (0x1D4CD, "M", "x"), + (0x1D4CE, "M", "y"), + (0x1D4CF, "M", "z"), + (0x1D4D0, "M", "a"), + (0x1D4D1, "M", "b"), + (0x1D4D2, "M", "c"), + (0x1D4D3, "M", "d"), + (0x1D4D4, "M", "e"), + (0x1D4D5, "M", "f"), + (0x1D4D6, "M", "g"), + (0x1D4D7, "M", "h"), + (0x1D4D8, "M", "i"), + (0x1D4D9, "M", "j"), + (0x1D4DA, "M", "k"), + (0x1D4DB, "M", "l"), + (0x1D4DC, "M", "m"), + (0x1D4DD, "M", "n"), + (0x1D4DE, "M", "o"), + (0x1D4DF, "M", "p"), + (0x1D4E0, "M", "q"), + (0x1D4E1, "M", "r"), + (0x1D4E2, "M", "s"), + (0x1D4E3, "M", "t"), + (0x1D4E4, "M", "u"), + (0x1D4E5, "M", "v"), + (0x1D4E6, "M", "w"), + (0x1D4E7, "M", "x"), + (0x1D4E8, "M", "y"), + (0x1D4E9, "M", "z"), + (0x1D4EA, "M", "a"), + (0x1D4EB, "M", "b"), + (0x1D4EC, "M", "c"), + (0x1D4ED, "M", "d"), + (0x1D4EE, "M", "e"), + (0x1D4EF, "M", "f"), ] + def _seg_63() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D4EC, 'M', 'c'), - (0x1D4ED, 'M', 'd'), - (0x1D4EE, 'M', 'e'), - (0x1D4EF, 'M', 'f'), - (0x1D4F0, 'M', 'g'), - (0x1D4F1, 'M', 'h'), - (0x1D4F2, 'M', 'i'), - (0x1D4F3, 'M', 'j'), - (0x1D4F4, 'M', 'k'), - (0x1D4F5, 'M', 'l'), - (0x1D4F6, 'M', 'm'), - (0x1D4F7, 'M', 'n'), - (0x1D4F8, 'M', 'o'), - (0x1D4F9, 'M', 'p'), - (0x1D4FA, 'M', 'q'), - (0x1D4FB, 'M', 'r'), - (0x1D4FC, 'M', 's'), - (0x1D4FD, 'M', 't'), - (0x1D4FE, 'M', 'u'), - (0x1D4FF, 'M', 'v'), - (0x1D500, 'M', 'w'), - (0x1D501, 'M', 'x'), - (0x1D502, 'M', 'y'), - (0x1D503, 'M', 'z'), - (0x1D504, 'M', 'a'), - (0x1D505, 'M', 'b'), - (0x1D506, 'X'), - (0x1D507, 'M', 'd'), - (0x1D508, 'M', 'e'), - (0x1D509, 'M', 'f'), - (0x1D50A, 'M', 'g'), - (0x1D50B, 'X'), - (0x1D50D, 'M', 'j'), - (0x1D50E, 'M', 'k'), - (0x1D50F, 'M', 'l'), - (0x1D510, 'M', 'm'), - (0x1D511, 'M', 'n'), - (0x1D512, 'M', 'o'), - (0x1D513, 'M', 'p'), - (0x1D514, 'M', 'q'), - (0x1D515, 'X'), - (0x1D516, 'M', 's'), - (0x1D517, 'M', 't'), - (0x1D518, 'M', 'u'), - (0x1D519, 'M', 'v'), - (0x1D51A, 'M', 'w'), - (0x1D51B, 'M', 'x'), - (0x1D51C, 'M', 'y'), - (0x1D51D, 'X'), - (0x1D51E, 'M', 'a'), - (0x1D51F, 'M', 'b'), - (0x1D520, 'M', 'c'), - (0x1D521, 'M', 'd'), - (0x1D522, 'M', 'e'), - (0x1D523, 'M', 'f'), - (0x1D524, 'M', 'g'), - (0x1D525, 'M', 'h'), - (0x1D526, 'M', 'i'), - (0x1D527, 'M', 'j'), - (0x1D528, 'M', 'k'), - (0x1D529, 'M', 'l'), - (0x1D52A, 'M', 'm'), - (0x1D52B, 'M', 'n'), - (0x1D52C, 'M', 'o'), - (0x1D52D, 'M', 'p'), - (0x1D52E, 'M', 'q'), - (0x1D52F, 'M', 'r'), - (0x1D530, 'M', 's'), - (0x1D531, 'M', 't'), - (0x1D532, 'M', 'u'), - (0x1D533, 'M', 'v'), - (0x1D534, 'M', 'w'), - (0x1D535, 'M', 'x'), - (0x1D536, 'M', 'y'), - (0x1D537, 'M', 'z'), - (0x1D538, 'M', 'a'), - (0x1D539, 'M', 'b'), - (0x1D53A, 'X'), - (0x1D53B, 'M', 'd'), - (0x1D53C, 'M', 'e'), - (0x1D53D, 'M', 'f'), - (0x1D53E, 'M', 'g'), - (0x1D53F, 'X'), - (0x1D540, 'M', 'i'), - (0x1D541, 'M', 'j'), - (0x1D542, 'M', 'k'), - (0x1D543, 'M', 'l'), - (0x1D544, 'M', 'm'), - (0x1D545, 'X'), - (0x1D546, 'M', 'o'), - (0x1D547, 'X'), - (0x1D54A, 'M', 's'), - (0x1D54B, 'M', 't'), - (0x1D54C, 'M', 'u'), - (0x1D54D, 'M', 'v'), - (0x1D54E, 'M', 'w'), - (0x1D54F, 'M', 'x'), - (0x1D550, 'M', 'y'), - (0x1D551, 'X'), - (0x1D552, 'M', 'a'), + (0x1D4F0, "M", "g"), + (0x1D4F1, "M", "h"), + (0x1D4F2, "M", "i"), + (0x1D4F3, "M", "j"), + (0x1D4F4, "M", "k"), + (0x1D4F5, "M", "l"), + (0x1D4F6, "M", "m"), + (0x1D4F7, "M", "n"), + (0x1D4F8, "M", "o"), + (0x1D4F9, "M", "p"), + (0x1D4FA, "M", "q"), + (0x1D4FB, "M", "r"), + (0x1D4FC, "M", "s"), + (0x1D4FD, "M", "t"), + (0x1D4FE, "M", "u"), + (0x1D4FF, "M", "v"), + (0x1D500, "M", "w"), + (0x1D501, "M", "x"), + (0x1D502, "M", "y"), + (0x1D503, "M", "z"), + (0x1D504, "M", "a"), + (0x1D505, "M", "b"), + (0x1D506, "X"), + (0x1D507, "M", "d"), + (0x1D508, "M", "e"), + (0x1D509, "M", "f"), + (0x1D50A, "M", "g"), + (0x1D50B, "X"), + (0x1D50D, "M", "j"), + (0x1D50E, "M", "k"), + (0x1D50F, "M", "l"), + (0x1D510, "M", "m"), + (0x1D511, "M", "n"), + (0x1D512, "M", "o"), + (0x1D513, "M", "p"), + (0x1D514, "M", "q"), + (0x1D515, "X"), + (0x1D516, "M", "s"), + (0x1D517, "M", "t"), + (0x1D518, "M", "u"), + (0x1D519, "M", "v"), + (0x1D51A, "M", "w"), + (0x1D51B, "M", "x"), + (0x1D51C, "M", "y"), + (0x1D51D, "X"), + (0x1D51E, "M", "a"), + (0x1D51F, "M", "b"), + (0x1D520, "M", "c"), + (0x1D521, "M", "d"), + (0x1D522, "M", "e"), + (0x1D523, "M", "f"), + (0x1D524, "M", "g"), + (0x1D525, "M", "h"), + (0x1D526, "M", "i"), + (0x1D527, "M", "j"), + (0x1D528, "M", "k"), + (0x1D529, "M", "l"), + (0x1D52A, "M", "m"), + (0x1D52B, "M", "n"), + (0x1D52C, "M", "o"), + (0x1D52D, "M", "p"), + (0x1D52E, "M", "q"), + (0x1D52F, "M", "r"), + (0x1D530, "M", "s"), + (0x1D531, "M", "t"), + (0x1D532, "M", "u"), + (0x1D533, "M", "v"), + (0x1D534, "M", "w"), + (0x1D535, "M", "x"), + (0x1D536, "M", "y"), + (0x1D537, "M", "z"), + (0x1D538, "M", "a"), + (0x1D539, "M", "b"), + (0x1D53A, "X"), + (0x1D53B, "M", "d"), + (0x1D53C, "M", "e"), + (0x1D53D, "M", "f"), + (0x1D53E, "M", "g"), + (0x1D53F, "X"), + (0x1D540, "M", "i"), + (0x1D541, "M", "j"), + (0x1D542, "M", "k"), + (0x1D543, "M", "l"), + (0x1D544, "M", "m"), + (0x1D545, "X"), + (0x1D546, "M", "o"), + (0x1D547, "X"), + (0x1D54A, "M", "s"), + (0x1D54B, "M", "t"), + (0x1D54C, "M", "u"), + (0x1D54D, "M", "v"), + (0x1D54E, "M", "w"), + (0x1D54F, "M", "x"), + (0x1D550, "M", "y"), + (0x1D551, "X"), + (0x1D552, "M", "a"), + (0x1D553, "M", "b"), + (0x1D554, "M", "c"), + (0x1D555, "M", "d"), + (0x1D556, "M", "e"), ] + def _seg_64() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D553, 'M', 'b'), - (0x1D554, 'M', 'c'), - (0x1D555, 'M', 'd'), - (0x1D556, 'M', 'e'), - (0x1D557, 'M', 'f'), - (0x1D558, 'M', 'g'), - (0x1D559, 'M', 'h'), - (0x1D55A, 'M', 'i'), - (0x1D55B, 'M', 'j'), - (0x1D55C, 'M', 'k'), - (0x1D55D, 'M', 'l'), - (0x1D55E, 'M', 'm'), - (0x1D55F, 'M', 'n'), - (0x1D560, 'M', 'o'), - (0x1D561, 'M', 'p'), - (0x1D562, 'M', 'q'), - (0x1D563, 'M', 'r'), - (0x1D564, 'M', 's'), - (0x1D565, 'M', 't'), - (0x1D566, 'M', 'u'), - (0x1D567, 'M', 'v'), - (0x1D568, 'M', 'w'), - (0x1D569, 'M', 'x'), - (0x1D56A, 'M', 'y'), - (0x1D56B, 'M', 'z'), - (0x1D56C, 'M', 'a'), - (0x1D56D, 'M', 'b'), - (0x1D56E, 'M', 'c'), - (0x1D56F, 'M', 'd'), - (0x1D570, 'M', 'e'), - (0x1D571, 'M', 'f'), - (0x1D572, 'M', 'g'), - (0x1D573, 'M', 'h'), - (0x1D574, 'M', 'i'), - (0x1D575, 'M', 'j'), - (0x1D576, 'M', 'k'), - (0x1D577, 'M', 'l'), - (0x1D578, 'M', 'm'), - (0x1D579, 'M', 'n'), - (0x1D57A, 'M', 'o'), - (0x1D57B, 'M', 'p'), - (0x1D57C, 'M', 'q'), - (0x1D57D, 'M', 'r'), - (0x1D57E, 'M', 's'), - (0x1D57F, 'M', 't'), - (0x1D580, 'M', 'u'), - (0x1D581, 'M', 'v'), - (0x1D582, 'M', 'w'), - (0x1D583, 'M', 'x'), - (0x1D584, 'M', 'y'), - (0x1D585, 'M', 'z'), - (0x1D586, 'M', 'a'), - (0x1D587, 'M', 'b'), - (0x1D588, 'M', 'c'), - (0x1D589, 'M', 'd'), - (0x1D58A, 'M', 'e'), - (0x1D58B, 'M', 'f'), - (0x1D58C, 'M', 'g'), - (0x1D58D, 'M', 'h'), - (0x1D58E, 'M', 'i'), - (0x1D58F, 'M', 'j'), - (0x1D590, 'M', 'k'), - (0x1D591, 'M', 'l'), - (0x1D592, 'M', 'm'), - (0x1D593, 'M', 'n'), - (0x1D594, 'M', 'o'), - (0x1D595, 'M', 'p'), - (0x1D596, 'M', 'q'), - (0x1D597, 'M', 'r'), - (0x1D598, 'M', 's'), - (0x1D599, 'M', 't'), - (0x1D59A, 'M', 'u'), - (0x1D59B, 'M', 'v'), - (0x1D59C, 'M', 'w'), - (0x1D59D, 'M', 'x'), - (0x1D59E, 'M', 'y'), - (0x1D59F, 'M', 'z'), - (0x1D5A0, 'M', 'a'), - (0x1D5A1, 'M', 'b'), - (0x1D5A2, 'M', 'c'), - (0x1D5A3, 'M', 'd'), - (0x1D5A4, 'M', 'e'), - (0x1D5A5, 'M', 'f'), - (0x1D5A6, 'M', 'g'), - (0x1D5A7, 'M', 'h'), - (0x1D5A8, 'M', 'i'), - (0x1D5A9, 'M', 'j'), - (0x1D5AA, 'M', 'k'), - (0x1D5AB, 'M', 'l'), - (0x1D5AC, 'M', 'm'), - (0x1D5AD, 'M', 'n'), - (0x1D5AE, 'M', 'o'), - (0x1D5AF, 'M', 'p'), - (0x1D5B0, 'M', 'q'), - (0x1D5B1, 'M', 'r'), - (0x1D5B2, 'M', 's'), - (0x1D5B3, 'M', 't'), - (0x1D5B4, 'M', 'u'), - (0x1D5B5, 'M', 'v'), - (0x1D5B6, 'M', 'w'), + (0x1D557, "M", "f"), + (0x1D558, "M", "g"), + (0x1D559, "M", "h"), + (0x1D55A, "M", "i"), + (0x1D55B, "M", "j"), + (0x1D55C, "M", "k"), + (0x1D55D, "M", "l"), + (0x1D55E, "M", "m"), + (0x1D55F, "M", "n"), + (0x1D560, "M", "o"), + (0x1D561, "M", "p"), + (0x1D562, "M", "q"), + (0x1D563, "M", "r"), + (0x1D564, "M", "s"), + (0x1D565, "M", "t"), + (0x1D566, "M", "u"), + (0x1D567, "M", "v"), + (0x1D568, "M", "w"), + (0x1D569, "M", "x"), + (0x1D56A, "M", "y"), + (0x1D56B, "M", "z"), + (0x1D56C, "M", "a"), + (0x1D56D, "M", "b"), + (0x1D56E, "M", "c"), + (0x1D56F, "M", "d"), + (0x1D570, "M", "e"), + (0x1D571, "M", "f"), + (0x1D572, "M", "g"), + (0x1D573, "M", "h"), + (0x1D574, "M", "i"), + (0x1D575, "M", "j"), + (0x1D576, "M", "k"), + (0x1D577, "M", "l"), + (0x1D578, "M", "m"), + (0x1D579, "M", "n"), + (0x1D57A, "M", "o"), + (0x1D57B, "M", "p"), + (0x1D57C, "M", "q"), + (0x1D57D, "M", "r"), + (0x1D57E, "M", "s"), + (0x1D57F, "M", "t"), + (0x1D580, "M", "u"), + (0x1D581, "M", "v"), + (0x1D582, "M", "w"), + (0x1D583, "M", "x"), + (0x1D584, "M", "y"), + (0x1D585, "M", "z"), + (0x1D586, "M", "a"), + (0x1D587, "M", "b"), + (0x1D588, "M", "c"), + (0x1D589, "M", "d"), + (0x1D58A, "M", "e"), + (0x1D58B, "M", "f"), + (0x1D58C, "M", "g"), + (0x1D58D, "M", "h"), + (0x1D58E, "M", "i"), + (0x1D58F, "M", "j"), + (0x1D590, "M", "k"), + (0x1D591, "M", "l"), + (0x1D592, "M", "m"), + (0x1D593, "M", "n"), + (0x1D594, "M", "o"), + (0x1D595, "M", "p"), + (0x1D596, "M", "q"), + (0x1D597, "M", "r"), + (0x1D598, "M", "s"), + (0x1D599, "M", "t"), + (0x1D59A, "M", "u"), + (0x1D59B, "M", "v"), + (0x1D59C, "M", "w"), + (0x1D59D, "M", "x"), + (0x1D59E, "M", "y"), + (0x1D59F, "M", "z"), + (0x1D5A0, "M", "a"), + (0x1D5A1, "M", "b"), + (0x1D5A2, "M", "c"), + (0x1D5A3, "M", "d"), + (0x1D5A4, "M", "e"), + (0x1D5A5, "M", "f"), + (0x1D5A6, "M", "g"), + (0x1D5A7, "M", "h"), + (0x1D5A8, "M", "i"), + (0x1D5A9, "M", "j"), + (0x1D5AA, "M", "k"), + (0x1D5AB, "M", "l"), + (0x1D5AC, "M", "m"), + (0x1D5AD, "M", "n"), + (0x1D5AE, "M", "o"), + (0x1D5AF, "M", "p"), + (0x1D5B0, "M", "q"), + (0x1D5B1, "M", "r"), + (0x1D5B2, "M", "s"), + (0x1D5B3, "M", "t"), + (0x1D5B4, "M", "u"), + (0x1D5B5, "M", "v"), + (0x1D5B6, "M", "w"), + (0x1D5B7, "M", "x"), + (0x1D5B8, "M", "y"), + (0x1D5B9, "M", "z"), + (0x1D5BA, "M", "a"), ] + def _seg_65() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D5B7, 'M', 'x'), - (0x1D5B8, 'M', 'y'), - (0x1D5B9, 'M', 'z'), - (0x1D5BA, 'M', 'a'), - (0x1D5BB, 'M', 'b'), - (0x1D5BC, 'M', 'c'), - (0x1D5BD, 'M', 'd'), - (0x1D5BE, 'M', 'e'), - (0x1D5BF, 'M', 'f'), - (0x1D5C0, 'M', 'g'), - (0x1D5C1, 'M', 'h'), - (0x1D5C2, 'M', 'i'), - (0x1D5C3, 'M', 'j'), - (0x1D5C4, 'M', 'k'), - (0x1D5C5, 'M', 'l'), - (0x1D5C6, 'M', 'm'), - (0x1D5C7, 'M', 'n'), - (0x1D5C8, 'M', 'o'), - (0x1D5C9, 'M', 'p'), - (0x1D5CA, 'M', 'q'), - (0x1D5CB, 'M', 'r'), - (0x1D5CC, 'M', 's'), - (0x1D5CD, 'M', 't'), - (0x1D5CE, 'M', 'u'), - (0x1D5CF, 'M', 'v'), - (0x1D5D0, 'M', 'w'), - (0x1D5D1, 'M', 'x'), - (0x1D5D2, 'M', 'y'), - (0x1D5D3, 'M', 'z'), - (0x1D5D4, 'M', 'a'), - (0x1D5D5, 'M', 'b'), - (0x1D5D6, 'M', 'c'), - (0x1D5D7, 'M', 'd'), - (0x1D5D8, 'M', 'e'), - (0x1D5D9, 'M', 'f'), - (0x1D5DA, 'M', 'g'), - (0x1D5DB, 'M', 'h'), - (0x1D5DC, 'M', 'i'), - (0x1D5DD, 'M', 'j'), - (0x1D5DE, 'M', 'k'), - (0x1D5DF, 'M', 'l'), - (0x1D5E0, 'M', 'm'), - (0x1D5E1, 'M', 'n'), - (0x1D5E2, 'M', 'o'), - (0x1D5E3, 'M', 'p'), - (0x1D5E4, 'M', 'q'), - (0x1D5E5, 'M', 'r'), - (0x1D5E6, 'M', 's'), - (0x1D5E7, 'M', 't'), - (0x1D5E8, 'M', 'u'), - (0x1D5E9, 'M', 'v'), - (0x1D5EA, 'M', 'w'), - (0x1D5EB, 'M', 'x'), - (0x1D5EC, 'M', 'y'), - (0x1D5ED, 'M', 'z'), - (0x1D5EE, 'M', 'a'), - (0x1D5EF, 'M', 'b'), - (0x1D5F0, 'M', 'c'), - (0x1D5F1, 'M', 'd'), - (0x1D5F2, 'M', 'e'), - (0x1D5F3, 'M', 'f'), - (0x1D5F4, 'M', 'g'), - (0x1D5F5, 'M', 'h'), - (0x1D5F6, 'M', 'i'), - (0x1D5F7, 'M', 'j'), - (0x1D5F8, 'M', 'k'), - (0x1D5F9, 'M', 'l'), - (0x1D5FA, 'M', 'm'), - (0x1D5FB, 'M', 'n'), - (0x1D5FC, 'M', 'o'), - (0x1D5FD, 'M', 'p'), - (0x1D5FE, 'M', 'q'), - (0x1D5FF, 'M', 'r'), - (0x1D600, 'M', 's'), - (0x1D601, 'M', 't'), - (0x1D602, 'M', 'u'), - (0x1D603, 'M', 'v'), - (0x1D604, 'M', 'w'), - (0x1D605, 'M', 'x'), - (0x1D606, 'M', 'y'), - (0x1D607, 'M', 'z'), - (0x1D608, 'M', 'a'), - (0x1D609, 'M', 'b'), - (0x1D60A, 'M', 'c'), - (0x1D60B, 'M', 'd'), - (0x1D60C, 'M', 'e'), - (0x1D60D, 'M', 'f'), - (0x1D60E, 'M', 'g'), - (0x1D60F, 'M', 'h'), - (0x1D610, 'M', 'i'), - (0x1D611, 'M', 'j'), - (0x1D612, 'M', 'k'), - (0x1D613, 'M', 'l'), - (0x1D614, 'M', 'm'), - (0x1D615, 'M', 'n'), - (0x1D616, 'M', 'o'), - (0x1D617, 'M', 'p'), - (0x1D618, 'M', 'q'), - (0x1D619, 'M', 'r'), - (0x1D61A, 'M', 's'), + (0x1D5BB, "M", "b"), + (0x1D5BC, "M", "c"), + (0x1D5BD, "M", "d"), + (0x1D5BE, "M", "e"), + (0x1D5BF, "M", "f"), + (0x1D5C0, "M", "g"), + (0x1D5C1, "M", "h"), + (0x1D5C2, "M", "i"), + (0x1D5C3, "M", "j"), + (0x1D5C4, "M", "k"), + (0x1D5C5, "M", "l"), + (0x1D5C6, "M", "m"), + (0x1D5C7, "M", "n"), + (0x1D5C8, "M", "o"), + (0x1D5C9, "M", "p"), + (0x1D5CA, "M", "q"), + (0x1D5CB, "M", "r"), + (0x1D5CC, "M", "s"), + (0x1D5CD, "M", "t"), + (0x1D5CE, "M", "u"), + (0x1D5CF, "M", "v"), + (0x1D5D0, "M", "w"), + (0x1D5D1, "M", "x"), + (0x1D5D2, "M", "y"), + (0x1D5D3, "M", "z"), + (0x1D5D4, "M", "a"), + (0x1D5D5, "M", "b"), + (0x1D5D6, "M", "c"), + (0x1D5D7, "M", "d"), + (0x1D5D8, "M", "e"), + (0x1D5D9, "M", "f"), + (0x1D5DA, "M", "g"), + (0x1D5DB, "M", "h"), + (0x1D5DC, "M", "i"), + (0x1D5DD, "M", "j"), + (0x1D5DE, "M", "k"), + (0x1D5DF, "M", "l"), + (0x1D5E0, "M", "m"), + (0x1D5E1, "M", "n"), + (0x1D5E2, "M", "o"), + (0x1D5E3, "M", "p"), + (0x1D5E4, "M", "q"), + (0x1D5E5, "M", "r"), + (0x1D5E6, "M", "s"), + (0x1D5E7, "M", "t"), + (0x1D5E8, "M", "u"), + (0x1D5E9, "M", "v"), + (0x1D5EA, "M", "w"), + (0x1D5EB, "M", "x"), + (0x1D5EC, "M", "y"), + (0x1D5ED, "M", "z"), + (0x1D5EE, "M", "a"), + (0x1D5EF, "M", "b"), + (0x1D5F0, "M", "c"), + (0x1D5F1, "M", "d"), + (0x1D5F2, "M", "e"), + (0x1D5F3, "M", "f"), + (0x1D5F4, "M", "g"), + (0x1D5F5, "M", "h"), + (0x1D5F6, "M", "i"), + (0x1D5F7, "M", "j"), + (0x1D5F8, "M", "k"), + (0x1D5F9, "M", "l"), + (0x1D5FA, "M", "m"), + (0x1D5FB, "M", "n"), + (0x1D5FC, "M", "o"), + (0x1D5FD, "M", "p"), + (0x1D5FE, "M", "q"), + (0x1D5FF, "M", "r"), + (0x1D600, "M", "s"), + (0x1D601, "M", "t"), + (0x1D602, "M", "u"), + (0x1D603, "M", "v"), + (0x1D604, "M", "w"), + (0x1D605, "M", "x"), + (0x1D606, "M", "y"), + (0x1D607, "M", "z"), + (0x1D608, "M", "a"), + (0x1D609, "M", "b"), + (0x1D60A, "M", "c"), + (0x1D60B, "M", "d"), + (0x1D60C, "M", "e"), + (0x1D60D, "M", "f"), + (0x1D60E, "M", "g"), + (0x1D60F, "M", "h"), + (0x1D610, "M", "i"), + (0x1D611, "M", "j"), + (0x1D612, "M", "k"), + (0x1D613, "M", "l"), + (0x1D614, "M", "m"), + (0x1D615, "M", "n"), + (0x1D616, "M", "o"), + (0x1D617, "M", "p"), + (0x1D618, "M", "q"), + (0x1D619, "M", "r"), + (0x1D61A, "M", "s"), + (0x1D61B, "M", "t"), + (0x1D61C, "M", "u"), + (0x1D61D, "M", "v"), + (0x1D61E, "M", "w"), ] + def _seg_66() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D61B, 'M', 't'), - (0x1D61C, 'M', 'u'), - (0x1D61D, 'M', 'v'), - (0x1D61E, 'M', 'w'), - (0x1D61F, 'M', 'x'), - (0x1D620, 'M', 'y'), - (0x1D621, 'M', 'z'), - (0x1D622, 'M', 'a'), - (0x1D623, 'M', 'b'), - (0x1D624, 'M', 'c'), - (0x1D625, 'M', 'd'), - (0x1D626, 'M', 'e'), - (0x1D627, 'M', 'f'), - (0x1D628, 'M', 'g'), - (0x1D629, 'M', 'h'), - (0x1D62A, 'M', 'i'), - (0x1D62B, 'M', 'j'), - (0x1D62C, 'M', 'k'), - (0x1D62D, 'M', 'l'), - (0x1D62E, 'M', 'm'), - (0x1D62F, 'M', 'n'), - (0x1D630, 'M', 'o'), - (0x1D631, 'M', 'p'), - (0x1D632, 'M', 'q'), - (0x1D633, 'M', 'r'), - (0x1D634, 'M', 's'), - (0x1D635, 'M', 't'), - (0x1D636, 'M', 'u'), - (0x1D637, 'M', 'v'), - (0x1D638, 'M', 'w'), - (0x1D639, 'M', 'x'), - (0x1D63A, 'M', 'y'), - (0x1D63B, 'M', 'z'), - (0x1D63C, 'M', 'a'), - (0x1D63D, 'M', 'b'), - (0x1D63E, 'M', 'c'), - (0x1D63F, 'M', 'd'), - (0x1D640, 'M', 'e'), - (0x1D641, 'M', 'f'), - (0x1D642, 'M', 'g'), - (0x1D643, 'M', 'h'), - (0x1D644, 'M', 'i'), - (0x1D645, 'M', 'j'), - (0x1D646, 'M', 'k'), - (0x1D647, 'M', 'l'), - (0x1D648, 'M', 'm'), - (0x1D649, 'M', 'n'), - (0x1D64A, 'M', 'o'), - (0x1D64B, 'M', 'p'), - (0x1D64C, 'M', 'q'), - (0x1D64D, 'M', 'r'), - (0x1D64E, 'M', 's'), - (0x1D64F, 'M', 't'), - (0x1D650, 'M', 'u'), - (0x1D651, 'M', 'v'), - (0x1D652, 'M', 'w'), - (0x1D653, 'M', 'x'), - (0x1D654, 'M', 'y'), - (0x1D655, 'M', 'z'), - (0x1D656, 'M', 'a'), - (0x1D657, 'M', 'b'), - (0x1D658, 'M', 'c'), - (0x1D659, 'M', 'd'), - (0x1D65A, 'M', 'e'), - (0x1D65B, 'M', 'f'), - (0x1D65C, 'M', 'g'), - (0x1D65D, 'M', 'h'), - (0x1D65E, 'M', 'i'), - (0x1D65F, 'M', 'j'), - (0x1D660, 'M', 'k'), - (0x1D661, 'M', 'l'), - (0x1D662, 'M', 'm'), - (0x1D663, 'M', 'n'), - (0x1D664, 'M', 'o'), - (0x1D665, 'M', 'p'), - (0x1D666, 'M', 'q'), - (0x1D667, 'M', 'r'), - (0x1D668, 'M', 's'), - (0x1D669, 'M', 't'), - (0x1D66A, 'M', 'u'), - (0x1D66B, 'M', 'v'), - (0x1D66C, 'M', 'w'), - (0x1D66D, 'M', 'x'), - (0x1D66E, 'M', 'y'), - (0x1D66F, 'M', 'z'), - (0x1D670, 'M', 'a'), - (0x1D671, 'M', 'b'), - (0x1D672, 'M', 'c'), - (0x1D673, 'M', 'd'), - (0x1D674, 'M', 'e'), - (0x1D675, 'M', 'f'), - (0x1D676, 'M', 'g'), - (0x1D677, 'M', 'h'), - (0x1D678, 'M', 'i'), - (0x1D679, 'M', 'j'), - (0x1D67A, 'M', 'k'), - (0x1D67B, 'M', 'l'), - (0x1D67C, 'M', 'm'), - (0x1D67D, 'M', 'n'), - (0x1D67E, 'M', 'o'), + (0x1D61F, "M", "x"), + (0x1D620, "M", "y"), + (0x1D621, "M", "z"), + (0x1D622, "M", "a"), + (0x1D623, "M", "b"), + (0x1D624, "M", "c"), + (0x1D625, "M", "d"), + (0x1D626, "M", "e"), + (0x1D627, "M", "f"), + (0x1D628, "M", "g"), + (0x1D629, "M", "h"), + (0x1D62A, "M", "i"), + (0x1D62B, "M", "j"), + (0x1D62C, "M", "k"), + (0x1D62D, "M", "l"), + (0x1D62E, "M", "m"), + (0x1D62F, "M", "n"), + (0x1D630, "M", "o"), + (0x1D631, "M", "p"), + (0x1D632, "M", "q"), + (0x1D633, "M", "r"), + (0x1D634, "M", "s"), + (0x1D635, "M", "t"), + (0x1D636, "M", "u"), + (0x1D637, "M", "v"), + (0x1D638, "M", "w"), + (0x1D639, "M", "x"), + (0x1D63A, "M", "y"), + (0x1D63B, "M", "z"), + (0x1D63C, "M", "a"), + (0x1D63D, "M", "b"), + (0x1D63E, "M", "c"), + (0x1D63F, "M", "d"), + (0x1D640, "M", "e"), + (0x1D641, "M", "f"), + (0x1D642, "M", "g"), + (0x1D643, "M", "h"), + (0x1D644, "M", "i"), + (0x1D645, "M", "j"), + (0x1D646, "M", "k"), + (0x1D647, "M", "l"), + (0x1D648, "M", "m"), + (0x1D649, "M", "n"), + (0x1D64A, "M", "o"), + (0x1D64B, "M", "p"), + (0x1D64C, "M", "q"), + (0x1D64D, "M", "r"), + (0x1D64E, "M", "s"), + (0x1D64F, "M", "t"), + (0x1D650, "M", "u"), + (0x1D651, "M", "v"), + (0x1D652, "M", "w"), + (0x1D653, "M", "x"), + (0x1D654, "M", "y"), + (0x1D655, "M", "z"), + (0x1D656, "M", "a"), + (0x1D657, "M", "b"), + (0x1D658, "M", "c"), + (0x1D659, "M", "d"), + (0x1D65A, "M", "e"), + (0x1D65B, "M", "f"), + (0x1D65C, "M", "g"), + (0x1D65D, "M", "h"), + (0x1D65E, "M", "i"), + (0x1D65F, "M", "j"), + (0x1D660, "M", "k"), + (0x1D661, "M", "l"), + (0x1D662, "M", "m"), + (0x1D663, "M", "n"), + (0x1D664, "M", "o"), + (0x1D665, "M", "p"), + (0x1D666, "M", "q"), + (0x1D667, "M", "r"), + (0x1D668, "M", "s"), + (0x1D669, "M", "t"), + (0x1D66A, "M", "u"), + (0x1D66B, "M", "v"), + (0x1D66C, "M", "w"), + (0x1D66D, "M", "x"), + (0x1D66E, "M", "y"), + (0x1D66F, "M", "z"), + (0x1D670, "M", "a"), + (0x1D671, "M", "b"), + (0x1D672, "M", "c"), + (0x1D673, "M", "d"), + (0x1D674, "M", "e"), + (0x1D675, "M", "f"), + (0x1D676, "M", "g"), + (0x1D677, "M", "h"), + (0x1D678, "M", "i"), + (0x1D679, "M", "j"), + (0x1D67A, "M", "k"), + (0x1D67B, "M", "l"), + (0x1D67C, "M", "m"), + (0x1D67D, "M", "n"), + (0x1D67E, "M", "o"), + (0x1D67F, "M", "p"), + (0x1D680, "M", "q"), + (0x1D681, "M", "r"), + (0x1D682, "M", "s"), ] + def _seg_67() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D67F, 'M', 'p'), - (0x1D680, 'M', 'q'), - (0x1D681, 'M', 'r'), - (0x1D682, 'M', 's'), - (0x1D683, 'M', 't'), - (0x1D684, 'M', 'u'), - (0x1D685, 'M', 'v'), - (0x1D686, 'M', 'w'), - (0x1D687, 'M', 'x'), - (0x1D688, 'M', 'y'), - (0x1D689, 'M', 'z'), - (0x1D68A, 'M', 'a'), - (0x1D68B, 'M', 'b'), - (0x1D68C, 'M', 'c'), - (0x1D68D, 'M', 'd'), - (0x1D68E, 'M', 'e'), - (0x1D68F, 'M', 'f'), - (0x1D690, 'M', 'g'), - (0x1D691, 'M', 'h'), - (0x1D692, 'M', 'i'), - (0x1D693, 'M', 'j'), - (0x1D694, 'M', 'k'), - (0x1D695, 'M', 'l'), - (0x1D696, 'M', 'm'), - (0x1D697, 'M', 'n'), - (0x1D698, 'M', 'o'), - (0x1D699, 'M', 'p'), - (0x1D69A, 'M', 'q'), - (0x1D69B, 'M', 'r'), - (0x1D69C, 'M', 's'), - (0x1D69D, 'M', 't'), - (0x1D69E, 'M', 'u'), - (0x1D69F, 'M', 'v'), - (0x1D6A0, 'M', 'w'), - (0x1D6A1, 'M', 'x'), - (0x1D6A2, 'M', 'y'), - (0x1D6A3, 'M', 'z'), - (0x1D6A4, 'M', 'ı'), - (0x1D6A5, 'M', 'ȷ'), - (0x1D6A6, 'X'), - (0x1D6A8, 'M', 'α'), - (0x1D6A9, 'M', 'β'), - (0x1D6AA, 'M', 'γ'), - (0x1D6AB, 'M', 'δ'), - (0x1D6AC, 'M', 'ε'), - (0x1D6AD, 'M', 'ζ'), - (0x1D6AE, 'M', 'η'), - (0x1D6AF, 'M', 'θ'), - (0x1D6B0, 'M', 'ι'), - (0x1D6B1, 'M', 'κ'), - (0x1D6B2, 'M', 'λ'), - (0x1D6B3, 'M', 'μ'), - (0x1D6B4, 'M', 'ν'), - (0x1D6B5, 'M', 'ξ'), - (0x1D6B6, 'M', 'ο'), - (0x1D6B7, 'M', 'π'), - (0x1D6B8, 'M', 'ρ'), - (0x1D6B9, 'M', 'θ'), - (0x1D6BA, 'M', 'σ'), - (0x1D6BB, 'M', 'τ'), - (0x1D6BC, 'M', 'υ'), - (0x1D6BD, 'M', 'φ'), - (0x1D6BE, 'M', 'χ'), - (0x1D6BF, 'M', 'ψ'), - (0x1D6C0, 'M', 'ω'), - (0x1D6C1, 'M', '∇'), - (0x1D6C2, 'M', 'α'), - (0x1D6C3, 'M', 'β'), - (0x1D6C4, 'M', 'γ'), - (0x1D6C5, 'M', 'δ'), - (0x1D6C6, 'M', 'ε'), - (0x1D6C7, 'M', 'ζ'), - (0x1D6C8, 'M', 'η'), - (0x1D6C9, 'M', 'θ'), - (0x1D6CA, 'M', 'ι'), - (0x1D6CB, 'M', 'κ'), - (0x1D6CC, 'M', 'λ'), - (0x1D6CD, 'M', 'μ'), - (0x1D6CE, 'M', 'ν'), - (0x1D6CF, 'M', 'ξ'), - (0x1D6D0, 'M', 'ο'), - (0x1D6D1, 'M', 'π'), - (0x1D6D2, 'M', 'ρ'), - (0x1D6D3, 'M', 'σ'), - (0x1D6D5, 'M', 'τ'), - (0x1D6D6, 'M', 'υ'), - (0x1D6D7, 'M', 'φ'), - (0x1D6D8, 'M', 'χ'), - (0x1D6D9, 'M', 'ψ'), - (0x1D6DA, 'M', 'ω'), - (0x1D6DB, 'M', '∂'), - (0x1D6DC, 'M', 'ε'), - (0x1D6DD, 'M', 'θ'), - (0x1D6DE, 'M', 'κ'), - (0x1D6DF, 'M', 'φ'), - (0x1D6E0, 'M', 'ρ'), - (0x1D6E1, 'M', 'π'), - (0x1D6E2, 'M', 'α'), - (0x1D6E3, 'M', 'β'), - (0x1D6E4, 'M', 'γ'), + (0x1D683, "M", "t"), + (0x1D684, "M", "u"), + (0x1D685, "M", "v"), + (0x1D686, "M", "w"), + (0x1D687, "M", "x"), + (0x1D688, "M", "y"), + (0x1D689, "M", "z"), + (0x1D68A, "M", "a"), + (0x1D68B, "M", "b"), + (0x1D68C, "M", "c"), + (0x1D68D, "M", "d"), + (0x1D68E, "M", "e"), + (0x1D68F, "M", "f"), + (0x1D690, "M", "g"), + (0x1D691, "M", "h"), + (0x1D692, "M", "i"), + (0x1D693, "M", "j"), + (0x1D694, "M", "k"), + (0x1D695, "M", "l"), + (0x1D696, "M", "m"), + (0x1D697, "M", "n"), + (0x1D698, "M", "o"), + (0x1D699, "M", "p"), + (0x1D69A, "M", "q"), + (0x1D69B, "M", "r"), + (0x1D69C, "M", "s"), + (0x1D69D, "M", "t"), + (0x1D69E, "M", "u"), + (0x1D69F, "M", "v"), + (0x1D6A0, "M", "w"), + (0x1D6A1, "M", "x"), + (0x1D6A2, "M", "y"), + (0x1D6A3, "M", "z"), + (0x1D6A4, "M", "ı"), + (0x1D6A5, "M", "ȷ"), + (0x1D6A6, "X"), + (0x1D6A8, "M", "α"), + (0x1D6A9, "M", "β"), + (0x1D6AA, "M", "γ"), + (0x1D6AB, "M", "δ"), + (0x1D6AC, "M", "ε"), + (0x1D6AD, "M", "ζ"), + (0x1D6AE, "M", "η"), + (0x1D6AF, "M", "θ"), + (0x1D6B0, "M", "ι"), + (0x1D6B1, "M", "κ"), + (0x1D6B2, "M", "λ"), + (0x1D6B3, "M", "μ"), + (0x1D6B4, "M", "ν"), + (0x1D6B5, "M", "ξ"), + (0x1D6B6, "M", "ο"), + (0x1D6B7, "M", "π"), + (0x1D6B8, "M", "ρ"), + (0x1D6B9, "M", "θ"), + (0x1D6BA, "M", "σ"), + (0x1D6BB, "M", "τ"), + (0x1D6BC, "M", "υ"), + (0x1D6BD, "M", "φ"), + (0x1D6BE, "M", "χ"), + (0x1D6BF, "M", "ψ"), + (0x1D6C0, "M", "ω"), + (0x1D6C1, "M", "∇"), + (0x1D6C2, "M", "α"), + (0x1D6C3, "M", "β"), + (0x1D6C4, "M", "γ"), + (0x1D6C5, "M", "δ"), + (0x1D6C6, "M", "ε"), + (0x1D6C7, "M", "ζ"), + (0x1D6C8, "M", "η"), + (0x1D6C9, "M", "θ"), + (0x1D6CA, "M", "ι"), + (0x1D6CB, "M", "κ"), + (0x1D6CC, "M", "λ"), + (0x1D6CD, "M", "μ"), + (0x1D6CE, "M", "ν"), + (0x1D6CF, "M", "ξ"), + (0x1D6D0, "M", "ο"), + (0x1D6D1, "M", "π"), + (0x1D6D2, "M", "ρ"), + (0x1D6D3, "M", "σ"), + (0x1D6D5, "M", "τ"), + (0x1D6D6, "M", "υ"), + (0x1D6D7, "M", "φ"), + (0x1D6D8, "M", "χ"), + (0x1D6D9, "M", "ψ"), + (0x1D6DA, "M", "ω"), + (0x1D6DB, "M", "∂"), + (0x1D6DC, "M", "ε"), + (0x1D6DD, "M", "θ"), + (0x1D6DE, "M", "κ"), + (0x1D6DF, "M", "φ"), + (0x1D6E0, "M", "ρ"), + (0x1D6E1, "M", "π"), + (0x1D6E2, "M", "α"), + (0x1D6E3, "M", "β"), + (0x1D6E4, "M", "γ"), + (0x1D6E5, "M", "δ"), + (0x1D6E6, "M", "ε"), + (0x1D6E7, "M", "ζ"), + (0x1D6E8, "M", "η"), ] + def _seg_68() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D6E5, 'M', 'δ'), - (0x1D6E6, 'M', 'ε'), - (0x1D6E7, 'M', 'ζ'), - (0x1D6E8, 'M', 'η'), - (0x1D6E9, 'M', 'θ'), - (0x1D6EA, 'M', 'ι'), - (0x1D6EB, 'M', 'κ'), - (0x1D6EC, 'M', 'λ'), - (0x1D6ED, 'M', 'μ'), - (0x1D6EE, 'M', 'ν'), - (0x1D6EF, 'M', 'ξ'), - (0x1D6F0, 'M', 'ο'), - (0x1D6F1, 'M', 'π'), - (0x1D6F2, 'M', 'ρ'), - (0x1D6F3, 'M', 'θ'), - (0x1D6F4, 'M', 'σ'), - (0x1D6F5, 'M', 'τ'), - (0x1D6F6, 'M', 'υ'), - (0x1D6F7, 'M', 'φ'), - (0x1D6F8, 'M', 'χ'), - (0x1D6F9, 'M', 'ψ'), - (0x1D6FA, 'M', 'ω'), - (0x1D6FB, 'M', '∇'), - (0x1D6FC, 'M', 'α'), - (0x1D6FD, 'M', 'β'), - (0x1D6FE, 'M', 'γ'), - (0x1D6FF, 'M', 'δ'), - (0x1D700, 'M', 'ε'), - (0x1D701, 'M', 'ζ'), - (0x1D702, 'M', 'η'), - (0x1D703, 'M', 'θ'), - (0x1D704, 'M', 'ι'), - (0x1D705, 'M', 'κ'), - (0x1D706, 'M', 'λ'), - (0x1D707, 'M', 'μ'), - (0x1D708, 'M', 'ν'), - (0x1D709, 'M', 'ξ'), - (0x1D70A, 'M', 'ο'), - (0x1D70B, 'M', 'π'), - (0x1D70C, 'M', 'ρ'), - (0x1D70D, 'M', 'σ'), - (0x1D70F, 'M', 'τ'), - (0x1D710, 'M', 'υ'), - (0x1D711, 'M', 'φ'), - (0x1D712, 'M', 'χ'), - (0x1D713, 'M', 'ψ'), - (0x1D714, 'M', 'ω'), - (0x1D715, 'M', '∂'), - (0x1D716, 'M', 'ε'), - (0x1D717, 'M', 'θ'), - (0x1D718, 'M', 'κ'), - (0x1D719, 'M', 'φ'), - (0x1D71A, 'M', 'ρ'), - (0x1D71B, 'M', 'π'), - (0x1D71C, 'M', 'α'), - (0x1D71D, 'M', 'β'), - (0x1D71E, 'M', 'γ'), - (0x1D71F, 'M', 'δ'), - (0x1D720, 'M', 'ε'), - (0x1D721, 'M', 'ζ'), - (0x1D722, 'M', 'η'), - (0x1D723, 'M', 'θ'), - (0x1D724, 'M', 'ι'), - (0x1D725, 'M', 'κ'), - (0x1D726, 'M', 'λ'), - (0x1D727, 'M', 'μ'), - (0x1D728, 'M', 'ν'), - (0x1D729, 'M', 'ξ'), - (0x1D72A, 'M', 'ο'), - (0x1D72B, 'M', 'π'), - (0x1D72C, 'M', 'ρ'), - (0x1D72D, 'M', 'θ'), - (0x1D72E, 'M', 'σ'), - (0x1D72F, 'M', 'τ'), - (0x1D730, 'M', 'υ'), - (0x1D731, 'M', 'φ'), - (0x1D732, 'M', 'χ'), - (0x1D733, 'M', 'ψ'), - (0x1D734, 'M', 'ω'), - (0x1D735, 'M', '∇'), - (0x1D736, 'M', 'α'), - (0x1D737, 'M', 'β'), - (0x1D738, 'M', 'γ'), - (0x1D739, 'M', 'δ'), - (0x1D73A, 'M', 'ε'), - (0x1D73B, 'M', 'ζ'), - (0x1D73C, 'M', 'η'), - (0x1D73D, 'M', 'θ'), - (0x1D73E, 'M', 'ι'), - (0x1D73F, 'M', 'κ'), - (0x1D740, 'M', 'λ'), - (0x1D741, 'M', 'μ'), - (0x1D742, 'M', 'ν'), - (0x1D743, 'M', 'ξ'), - (0x1D744, 'M', 'ο'), - (0x1D745, 'M', 'π'), - (0x1D746, 'M', 'ρ'), - (0x1D747, 'M', 'σ'), - (0x1D749, 'M', 'τ'), - (0x1D74A, 'M', 'υ'), + (0x1D6E9, "M", "θ"), + (0x1D6EA, "M", "ι"), + (0x1D6EB, "M", "κ"), + (0x1D6EC, "M", "λ"), + (0x1D6ED, "M", "μ"), + (0x1D6EE, "M", "ν"), + (0x1D6EF, "M", "ξ"), + (0x1D6F0, "M", "ο"), + (0x1D6F1, "M", "π"), + (0x1D6F2, "M", "ρ"), + (0x1D6F3, "M", "θ"), + (0x1D6F4, "M", "σ"), + (0x1D6F5, "M", "τ"), + (0x1D6F6, "M", "υ"), + (0x1D6F7, "M", "φ"), + (0x1D6F8, "M", "χ"), + (0x1D6F9, "M", "ψ"), + (0x1D6FA, "M", "ω"), + (0x1D6FB, "M", "∇"), + (0x1D6FC, "M", "α"), + (0x1D6FD, "M", "β"), + (0x1D6FE, "M", "γ"), + (0x1D6FF, "M", "δ"), + (0x1D700, "M", "ε"), + (0x1D701, "M", "ζ"), + (0x1D702, "M", "η"), + (0x1D703, "M", "θ"), + (0x1D704, "M", "ι"), + (0x1D705, "M", "κ"), + (0x1D706, "M", "λ"), + (0x1D707, "M", "μ"), + (0x1D708, "M", "ν"), + (0x1D709, "M", "ξ"), + (0x1D70A, "M", "ο"), + (0x1D70B, "M", "π"), + (0x1D70C, "M", "ρ"), + (0x1D70D, "M", "σ"), + (0x1D70F, "M", "τ"), + (0x1D710, "M", "υ"), + (0x1D711, "M", "φ"), + (0x1D712, "M", "χ"), + (0x1D713, "M", "ψ"), + (0x1D714, "M", "ω"), + (0x1D715, "M", "∂"), + (0x1D716, "M", "ε"), + (0x1D717, "M", "θ"), + (0x1D718, "M", "κ"), + (0x1D719, "M", "φ"), + (0x1D71A, "M", "ρ"), + (0x1D71B, "M", "π"), + (0x1D71C, "M", "α"), + (0x1D71D, "M", "β"), + (0x1D71E, "M", "γ"), + (0x1D71F, "M", "δ"), + (0x1D720, "M", "ε"), + (0x1D721, "M", "ζ"), + (0x1D722, "M", "η"), + (0x1D723, "M", "θ"), + (0x1D724, "M", "ι"), + (0x1D725, "M", "κ"), + (0x1D726, "M", "λ"), + (0x1D727, "M", "μ"), + (0x1D728, "M", "ν"), + (0x1D729, "M", "ξ"), + (0x1D72A, "M", "ο"), + (0x1D72B, "M", "π"), + (0x1D72C, "M", "ρ"), + (0x1D72D, "M", "θ"), + (0x1D72E, "M", "σ"), + (0x1D72F, "M", "τ"), + (0x1D730, "M", "υ"), + (0x1D731, "M", "φ"), + (0x1D732, "M", "χ"), + (0x1D733, "M", "ψ"), + (0x1D734, "M", "ω"), + (0x1D735, "M", "∇"), + (0x1D736, "M", "α"), + (0x1D737, "M", "β"), + (0x1D738, "M", "γ"), + (0x1D739, "M", "δ"), + (0x1D73A, "M", "ε"), + (0x1D73B, "M", "ζ"), + (0x1D73C, "M", "η"), + (0x1D73D, "M", "θ"), + (0x1D73E, "M", "ι"), + (0x1D73F, "M", "κ"), + (0x1D740, "M", "λ"), + (0x1D741, "M", "μ"), + (0x1D742, "M", "ν"), + (0x1D743, "M", "ξ"), + (0x1D744, "M", "ο"), + (0x1D745, "M", "π"), + (0x1D746, "M", "ρ"), + (0x1D747, "M", "σ"), + (0x1D749, "M", "τ"), + (0x1D74A, "M", "υ"), + (0x1D74B, "M", "φ"), + (0x1D74C, "M", "χ"), + (0x1D74D, "M", "ψ"), + (0x1D74E, "M", "ω"), ] + def _seg_69() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D74B, 'M', 'φ'), - (0x1D74C, 'M', 'χ'), - (0x1D74D, 'M', 'ψ'), - (0x1D74E, 'M', 'ω'), - (0x1D74F, 'M', '∂'), - (0x1D750, 'M', 'ε'), - (0x1D751, 'M', 'θ'), - (0x1D752, 'M', 'κ'), - (0x1D753, 'M', 'φ'), - (0x1D754, 'M', 'ρ'), - (0x1D755, 'M', 'π'), - (0x1D756, 'M', 'α'), - (0x1D757, 'M', 'β'), - (0x1D758, 'M', 'γ'), - (0x1D759, 'M', 'δ'), - (0x1D75A, 'M', 'ε'), - (0x1D75B, 'M', 'ζ'), - (0x1D75C, 'M', 'η'), - (0x1D75D, 'M', 'θ'), - (0x1D75E, 'M', 'ι'), - (0x1D75F, 'M', 'κ'), - (0x1D760, 'M', 'λ'), - (0x1D761, 'M', 'μ'), - (0x1D762, 'M', 'ν'), - (0x1D763, 'M', 'ξ'), - (0x1D764, 'M', 'ο'), - (0x1D765, 'M', 'π'), - (0x1D766, 'M', 'ρ'), - (0x1D767, 'M', 'θ'), - (0x1D768, 'M', 'σ'), - (0x1D769, 'M', 'τ'), - (0x1D76A, 'M', 'υ'), - (0x1D76B, 'M', 'φ'), - (0x1D76C, 'M', 'χ'), - (0x1D76D, 'M', 'ψ'), - (0x1D76E, 'M', 'ω'), - (0x1D76F, 'M', '∇'), - (0x1D770, 'M', 'α'), - (0x1D771, 'M', 'β'), - (0x1D772, 'M', 'γ'), - (0x1D773, 'M', 'δ'), - (0x1D774, 'M', 'ε'), - (0x1D775, 'M', 'ζ'), - (0x1D776, 'M', 'η'), - (0x1D777, 'M', 'θ'), - (0x1D778, 'M', 'ι'), - (0x1D779, 'M', 'κ'), - (0x1D77A, 'M', 'λ'), - (0x1D77B, 'M', 'μ'), - (0x1D77C, 'M', 'ν'), - (0x1D77D, 'M', 'ξ'), - (0x1D77E, 'M', 'ο'), - (0x1D77F, 'M', 'π'), - (0x1D780, 'M', 'ρ'), - (0x1D781, 'M', 'σ'), - (0x1D783, 'M', 'τ'), - (0x1D784, 'M', 'υ'), - (0x1D785, 'M', 'φ'), - (0x1D786, 'M', 'χ'), - (0x1D787, 'M', 'ψ'), - (0x1D788, 'M', 'ω'), - (0x1D789, 'M', '∂'), - (0x1D78A, 'M', 'ε'), - (0x1D78B, 'M', 'θ'), - (0x1D78C, 'M', 'κ'), - (0x1D78D, 'M', 'φ'), - (0x1D78E, 'M', 'ρ'), - (0x1D78F, 'M', 'π'), - (0x1D790, 'M', 'α'), - (0x1D791, 'M', 'β'), - (0x1D792, 'M', 'γ'), - (0x1D793, 'M', 'δ'), - (0x1D794, 'M', 'ε'), - (0x1D795, 'M', 'ζ'), - (0x1D796, 'M', 'η'), - (0x1D797, 'M', 'θ'), - (0x1D798, 'M', 'ι'), - (0x1D799, 'M', 'κ'), - (0x1D79A, 'M', 'λ'), - (0x1D79B, 'M', 'μ'), - (0x1D79C, 'M', 'ν'), - (0x1D79D, 'M', 'ξ'), - (0x1D79E, 'M', 'ο'), - (0x1D79F, 'M', 'π'), - (0x1D7A0, 'M', 'ρ'), - (0x1D7A1, 'M', 'θ'), - (0x1D7A2, 'M', 'σ'), - (0x1D7A3, 'M', 'τ'), - (0x1D7A4, 'M', 'υ'), - (0x1D7A5, 'M', 'φ'), - (0x1D7A6, 'M', 'χ'), - (0x1D7A7, 'M', 'ψ'), - (0x1D7A8, 'M', 'ω'), - (0x1D7A9, 'M', '∇'), - (0x1D7AA, 'M', 'α'), - (0x1D7AB, 'M', 'β'), - (0x1D7AC, 'M', 'γ'), - (0x1D7AD, 'M', 'δ'), - (0x1D7AE, 'M', 'ε'), - (0x1D7AF, 'M', 'ζ'), + (0x1D74F, "M", "∂"), + (0x1D750, "M", "ε"), + (0x1D751, "M", "θ"), + (0x1D752, "M", "κ"), + (0x1D753, "M", "φ"), + (0x1D754, "M", "ρ"), + (0x1D755, "M", "π"), + (0x1D756, "M", "α"), + (0x1D757, "M", "β"), + (0x1D758, "M", "γ"), + (0x1D759, "M", "δ"), + (0x1D75A, "M", "ε"), + (0x1D75B, "M", "ζ"), + (0x1D75C, "M", "η"), + (0x1D75D, "M", "θ"), + (0x1D75E, "M", "ι"), + (0x1D75F, "M", "κ"), + (0x1D760, "M", "λ"), + (0x1D761, "M", "μ"), + (0x1D762, "M", "ν"), + (0x1D763, "M", "ξ"), + (0x1D764, "M", "ο"), + (0x1D765, "M", "π"), + (0x1D766, "M", "ρ"), + (0x1D767, "M", "θ"), + (0x1D768, "M", "σ"), + (0x1D769, "M", "τ"), + (0x1D76A, "M", "υ"), + (0x1D76B, "M", "φ"), + (0x1D76C, "M", "χ"), + (0x1D76D, "M", "ψ"), + (0x1D76E, "M", "ω"), + (0x1D76F, "M", "∇"), + (0x1D770, "M", "α"), + (0x1D771, "M", "β"), + (0x1D772, "M", "γ"), + (0x1D773, "M", "δ"), + (0x1D774, "M", "ε"), + (0x1D775, "M", "ζ"), + (0x1D776, "M", "η"), + (0x1D777, "M", "θ"), + (0x1D778, "M", "ι"), + (0x1D779, "M", "κ"), + (0x1D77A, "M", "λ"), + (0x1D77B, "M", "μ"), + (0x1D77C, "M", "ν"), + (0x1D77D, "M", "ξ"), + (0x1D77E, "M", "ο"), + (0x1D77F, "M", "π"), + (0x1D780, "M", "ρ"), + (0x1D781, "M", "σ"), + (0x1D783, "M", "τ"), + (0x1D784, "M", "υ"), + (0x1D785, "M", "φ"), + (0x1D786, "M", "χ"), + (0x1D787, "M", "ψ"), + (0x1D788, "M", "ω"), + (0x1D789, "M", "∂"), + (0x1D78A, "M", "ε"), + (0x1D78B, "M", "θ"), + (0x1D78C, "M", "κ"), + (0x1D78D, "M", "φ"), + (0x1D78E, "M", "ρ"), + (0x1D78F, "M", "π"), + (0x1D790, "M", "α"), + (0x1D791, "M", "β"), + (0x1D792, "M", "γ"), + (0x1D793, "M", "δ"), + (0x1D794, "M", "ε"), + (0x1D795, "M", "ζ"), + (0x1D796, "M", "η"), + (0x1D797, "M", "θ"), + (0x1D798, "M", "ι"), + (0x1D799, "M", "κ"), + (0x1D79A, "M", "λ"), + (0x1D79B, "M", "μ"), + (0x1D79C, "M", "ν"), + (0x1D79D, "M", "ξ"), + (0x1D79E, "M", "ο"), + (0x1D79F, "M", "π"), + (0x1D7A0, "M", "ρ"), + (0x1D7A1, "M", "θ"), + (0x1D7A2, "M", "σ"), + (0x1D7A3, "M", "τ"), + (0x1D7A4, "M", "υ"), + (0x1D7A5, "M", "φ"), + (0x1D7A6, "M", "χ"), + (0x1D7A7, "M", "ψ"), + (0x1D7A8, "M", "ω"), + (0x1D7A9, "M", "∇"), + (0x1D7AA, "M", "α"), + (0x1D7AB, "M", "β"), + (0x1D7AC, "M", "γ"), + (0x1D7AD, "M", "δ"), + (0x1D7AE, "M", "ε"), + (0x1D7AF, "M", "ζ"), + (0x1D7B0, "M", "η"), + (0x1D7B1, "M", "θ"), + (0x1D7B2, "M", "ι"), + (0x1D7B3, "M", "κ"), ] + def _seg_70() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1D7B0, 'M', 'η'), - (0x1D7B1, 'M', 'θ'), - (0x1D7B2, 'M', 'ι'), - (0x1D7B3, 'M', 'κ'), - (0x1D7B4, 'M', 'λ'), - (0x1D7B5, 'M', 'μ'), - (0x1D7B6, 'M', 'ν'), - (0x1D7B7, 'M', 'ξ'), - (0x1D7B8, 'M', 'ο'), - (0x1D7B9, 'M', 'π'), - (0x1D7BA, 'M', 'ρ'), - (0x1D7BB, 'M', 'σ'), - (0x1D7BD, 'M', 'τ'), - (0x1D7BE, 'M', 'υ'), - (0x1D7BF, 'M', 'φ'), - (0x1D7C0, 'M', 'χ'), - (0x1D7C1, 'M', 'ψ'), - (0x1D7C2, 'M', 'ω'), - (0x1D7C3, 'M', '∂'), - (0x1D7C4, 'M', 'ε'), - (0x1D7C5, 'M', 'θ'), - (0x1D7C6, 'M', 'κ'), - (0x1D7C7, 'M', 'φ'), - (0x1D7C8, 'M', 'ρ'), - (0x1D7C9, 'M', 'π'), - (0x1D7CA, 'M', 'ϝ'), - (0x1D7CC, 'X'), - (0x1D7CE, 'M', '0'), - (0x1D7CF, 'M', '1'), - (0x1D7D0, 'M', '2'), - (0x1D7D1, 'M', '3'), - (0x1D7D2, 'M', '4'), - (0x1D7D3, 'M', '5'), - (0x1D7D4, 'M', '6'), - (0x1D7D5, 'M', '7'), - (0x1D7D6, 'M', '8'), - (0x1D7D7, 'M', '9'), - (0x1D7D8, 'M', '0'), - (0x1D7D9, 'M', '1'), - (0x1D7DA, 'M', '2'), - (0x1D7DB, 'M', '3'), - (0x1D7DC, 'M', '4'), - (0x1D7DD, 'M', '5'), - (0x1D7DE, 'M', '6'), - (0x1D7DF, 'M', '7'), - (0x1D7E0, 'M', '8'), - (0x1D7E1, 'M', '9'), - (0x1D7E2, 'M', '0'), - (0x1D7E3, 'M', '1'), - (0x1D7E4, 'M', '2'), - (0x1D7E5, 'M', '3'), - (0x1D7E6, 'M', '4'), - (0x1D7E7, 'M', '5'), - (0x1D7E8, 'M', '6'), - (0x1D7E9, 'M', '7'), - (0x1D7EA, 'M', '8'), - (0x1D7EB, 'M', '9'), - (0x1D7EC, 'M', '0'), - (0x1D7ED, 'M', '1'), - (0x1D7EE, 'M', '2'), - (0x1D7EF, 'M', '3'), - (0x1D7F0, 'M', '4'), - (0x1D7F1, 'M', '5'), - (0x1D7F2, 'M', '6'), - (0x1D7F3, 'M', '7'), - (0x1D7F4, 'M', '8'), - (0x1D7F5, 'M', '9'), - (0x1D7F6, 'M', '0'), - (0x1D7F7, 'M', '1'), - (0x1D7F8, 'M', '2'), - (0x1D7F9, 'M', '3'), - (0x1D7FA, 'M', '4'), - (0x1D7FB, 'M', '5'), - (0x1D7FC, 'M', '6'), - (0x1D7FD, 'M', '7'), - (0x1D7FE, 'M', '8'), - (0x1D7FF, 'M', '9'), - (0x1D800, 'V'), - (0x1DA8C, 'X'), - (0x1DA9B, 'V'), - (0x1DAA0, 'X'), - (0x1DAA1, 'V'), - (0x1DAB0, 'X'), - (0x1DF00, 'V'), - (0x1DF1F, 'X'), - (0x1DF25, 'V'), - (0x1DF2B, 'X'), - (0x1E000, 'V'), - (0x1E007, 'X'), - (0x1E008, 'V'), - (0x1E019, 'X'), - (0x1E01B, 'V'), - (0x1E022, 'X'), - (0x1E023, 'V'), - (0x1E025, 'X'), - (0x1E026, 'V'), - (0x1E02B, 'X'), - (0x1E030, 'M', 'а'), - (0x1E031, 'M', 'б'), - (0x1E032, 'M', 'в'), + (0x1D7B4, "M", "λ"), + (0x1D7B5, "M", "μ"), + (0x1D7B6, "M", "ν"), + (0x1D7B7, "M", "ξ"), + (0x1D7B8, "M", "ο"), + (0x1D7B9, "M", "π"), + (0x1D7BA, "M", "ρ"), + (0x1D7BB, "M", "σ"), + (0x1D7BD, "M", "τ"), + (0x1D7BE, "M", "υ"), + (0x1D7BF, "M", "φ"), + (0x1D7C0, "M", "χ"), + (0x1D7C1, "M", "ψ"), + (0x1D7C2, "M", "ω"), + (0x1D7C3, "M", "∂"), + (0x1D7C4, "M", "ε"), + (0x1D7C5, "M", "θ"), + (0x1D7C6, "M", "κ"), + (0x1D7C7, "M", "φ"), + (0x1D7C8, "M", "ρ"), + (0x1D7C9, "M", "π"), + (0x1D7CA, "M", "ϝ"), + (0x1D7CC, "X"), + (0x1D7CE, "M", "0"), + (0x1D7CF, "M", "1"), + (0x1D7D0, "M", "2"), + (0x1D7D1, "M", "3"), + (0x1D7D2, "M", "4"), + (0x1D7D3, "M", "5"), + (0x1D7D4, "M", "6"), + (0x1D7D5, "M", "7"), + (0x1D7D6, "M", "8"), + (0x1D7D7, "M", "9"), + (0x1D7D8, "M", "0"), + (0x1D7D9, "M", "1"), + (0x1D7DA, "M", "2"), + (0x1D7DB, "M", "3"), + (0x1D7DC, "M", "4"), + (0x1D7DD, "M", "5"), + (0x1D7DE, "M", "6"), + (0x1D7DF, "M", "7"), + (0x1D7E0, "M", "8"), + (0x1D7E1, "M", "9"), + (0x1D7E2, "M", "0"), + (0x1D7E3, "M", "1"), + (0x1D7E4, "M", "2"), + (0x1D7E5, "M", "3"), + (0x1D7E6, "M", "4"), + (0x1D7E7, "M", "5"), + (0x1D7E8, "M", "6"), + (0x1D7E9, "M", "7"), + (0x1D7EA, "M", "8"), + (0x1D7EB, "M", "9"), + (0x1D7EC, "M", "0"), + (0x1D7ED, "M", "1"), + (0x1D7EE, "M", "2"), + (0x1D7EF, "M", "3"), + (0x1D7F0, "M", "4"), + (0x1D7F1, "M", "5"), + (0x1D7F2, "M", "6"), + (0x1D7F3, "M", "7"), + (0x1D7F4, "M", "8"), + (0x1D7F5, "M", "9"), + (0x1D7F6, "M", "0"), + (0x1D7F7, "M", "1"), + (0x1D7F8, "M", "2"), + (0x1D7F9, "M", "3"), + (0x1D7FA, "M", "4"), + (0x1D7FB, "M", "5"), + (0x1D7FC, "M", "6"), + (0x1D7FD, "M", "7"), + (0x1D7FE, "M", "8"), + (0x1D7FF, "M", "9"), + (0x1D800, "V"), + (0x1DA8C, "X"), + (0x1DA9B, "V"), + (0x1DAA0, "X"), + (0x1DAA1, "V"), + (0x1DAB0, "X"), + (0x1DF00, "V"), + (0x1DF1F, "X"), + (0x1DF25, "V"), + (0x1DF2B, "X"), + (0x1E000, "V"), + (0x1E007, "X"), + (0x1E008, "V"), + (0x1E019, "X"), + (0x1E01B, "V"), + (0x1E022, "X"), + (0x1E023, "V"), + (0x1E025, "X"), + (0x1E026, "V"), + (0x1E02B, "X"), + (0x1E030, "M", "а"), + (0x1E031, "M", "б"), + (0x1E032, "M", "в"), + (0x1E033, "M", "г"), + (0x1E034, "M", "д"), + (0x1E035, "M", "е"), + (0x1E036, "M", "ж"), ] + def _seg_71() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1E033, 'M', 'г'), - (0x1E034, 'M', 'д'), - (0x1E035, 'M', 'е'), - (0x1E036, 'M', 'ж'), - (0x1E037, 'M', 'з'), - (0x1E038, 'M', 'и'), - (0x1E039, 'M', 'к'), - (0x1E03A, 'M', 'л'), - (0x1E03B, 'M', 'м'), - (0x1E03C, 'M', 'о'), - (0x1E03D, 'M', 'п'), - (0x1E03E, 'M', 'р'), - (0x1E03F, 'M', 'с'), - (0x1E040, 'M', 'т'), - (0x1E041, 'M', 'у'), - (0x1E042, 'M', 'ф'), - (0x1E043, 'M', 'х'), - (0x1E044, 'M', 'ц'), - (0x1E045, 'M', 'ч'), - (0x1E046, 'M', 'ш'), - (0x1E047, 'M', 'ы'), - (0x1E048, 'M', 'э'), - (0x1E049, 'M', 'ю'), - (0x1E04A, 'M', 'ꚉ'), - (0x1E04B, 'M', 'ә'), - (0x1E04C, 'M', 'і'), - (0x1E04D, 'M', 'ј'), - (0x1E04E, 'M', 'ө'), - (0x1E04F, 'M', 'ү'), - (0x1E050, 'M', 'ӏ'), - (0x1E051, 'M', 'а'), - (0x1E052, 'M', 'б'), - (0x1E053, 'M', 'в'), - (0x1E054, 'M', 'г'), - (0x1E055, 'M', 'д'), - (0x1E056, 'M', 'е'), - (0x1E057, 'M', 'ж'), - (0x1E058, 'M', 'з'), - (0x1E059, 'M', 'и'), - (0x1E05A, 'M', 'к'), - (0x1E05B, 'M', 'л'), - (0x1E05C, 'M', 'о'), - (0x1E05D, 'M', 'п'), - (0x1E05E, 'M', 'с'), - (0x1E05F, 'M', 'у'), - (0x1E060, 'M', 'ф'), - (0x1E061, 'M', 'х'), - (0x1E062, 'M', 'ц'), - (0x1E063, 'M', 'ч'), - (0x1E064, 'M', 'ш'), - (0x1E065, 'M', 'ъ'), - (0x1E066, 'M', 'ы'), - (0x1E067, 'M', 'ґ'), - (0x1E068, 'M', 'і'), - (0x1E069, 'M', 'ѕ'), - (0x1E06A, 'M', 'џ'), - (0x1E06B, 'M', 'ҫ'), - (0x1E06C, 'M', 'ꙑ'), - (0x1E06D, 'M', 'ұ'), - (0x1E06E, 'X'), - (0x1E08F, 'V'), - (0x1E090, 'X'), - (0x1E100, 'V'), - (0x1E12D, 'X'), - (0x1E130, 'V'), - (0x1E13E, 'X'), - (0x1E140, 'V'), - (0x1E14A, 'X'), - (0x1E14E, 'V'), - (0x1E150, 'X'), - (0x1E290, 'V'), - (0x1E2AF, 'X'), - (0x1E2C0, 'V'), - (0x1E2FA, 'X'), - (0x1E2FF, 'V'), - (0x1E300, 'X'), - (0x1E4D0, 'V'), - (0x1E4FA, 'X'), - (0x1E7E0, 'V'), - (0x1E7E7, 'X'), - (0x1E7E8, 'V'), - (0x1E7EC, 'X'), - (0x1E7ED, 'V'), - (0x1E7EF, 'X'), - (0x1E7F0, 'V'), - (0x1E7FF, 'X'), - (0x1E800, 'V'), - (0x1E8C5, 'X'), - (0x1E8C7, 'V'), - (0x1E8D7, 'X'), - (0x1E900, 'M', '𞤢'), - (0x1E901, 'M', '𞤣'), - (0x1E902, 'M', '𞤤'), - (0x1E903, 'M', '𞤥'), - (0x1E904, 'M', '𞤦'), - (0x1E905, 'M', '𞤧'), - (0x1E906, 'M', '𞤨'), - (0x1E907, 'M', '𞤩'), - (0x1E908, 'M', '𞤪'), - (0x1E909, 'M', '𞤫'), + (0x1E037, "M", "з"), + (0x1E038, "M", "и"), + (0x1E039, "M", "к"), + (0x1E03A, "M", "л"), + (0x1E03B, "M", "м"), + (0x1E03C, "M", "о"), + (0x1E03D, "M", "п"), + (0x1E03E, "M", "р"), + (0x1E03F, "M", "с"), + (0x1E040, "M", "т"), + (0x1E041, "M", "у"), + (0x1E042, "M", "ф"), + (0x1E043, "M", "х"), + (0x1E044, "M", "ц"), + (0x1E045, "M", "ч"), + (0x1E046, "M", "ш"), + (0x1E047, "M", "ы"), + (0x1E048, "M", "э"), + (0x1E049, "M", "ю"), + (0x1E04A, "M", "ꚉ"), + (0x1E04B, "M", "ә"), + (0x1E04C, "M", "і"), + (0x1E04D, "M", "ј"), + (0x1E04E, "M", "ө"), + (0x1E04F, "M", "ү"), + (0x1E050, "M", "ӏ"), + (0x1E051, "M", "а"), + (0x1E052, "M", "б"), + (0x1E053, "M", "в"), + (0x1E054, "M", "г"), + (0x1E055, "M", "д"), + (0x1E056, "M", "е"), + (0x1E057, "M", "ж"), + (0x1E058, "M", "з"), + (0x1E059, "M", "и"), + (0x1E05A, "M", "к"), + (0x1E05B, "M", "л"), + (0x1E05C, "M", "о"), + (0x1E05D, "M", "п"), + (0x1E05E, "M", "с"), + (0x1E05F, "M", "у"), + (0x1E060, "M", "ф"), + (0x1E061, "M", "х"), + (0x1E062, "M", "ц"), + (0x1E063, "M", "ч"), + (0x1E064, "M", "ш"), + (0x1E065, "M", "ъ"), + (0x1E066, "M", "ы"), + (0x1E067, "M", "ґ"), + (0x1E068, "M", "і"), + (0x1E069, "M", "ѕ"), + (0x1E06A, "M", "џ"), + (0x1E06B, "M", "ҫ"), + (0x1E06C, "M", "ꙑ"), + (0x1E06D, "M", "ұ"), + (0x1E06E, "X"), + (0x1E08F, "V"), + (0x1E090, "X"), + (0x1E100, "V"), + (0x1E12D, "X"), + (0x1E130, "V"), + (0x1E13E, "X"), + (0x1E140, "V"), + (0x1E14A, "X"), + (0x1E14E, "V"), + (0x1E150, "X"), + (0x1E290, "V"), + (0x1E2AF, "X"), + (0x1E2C0, "V"), + (0x1E2FA, "X"), + (0x1E2FF, "V"), + (0x1E300, "X"), + (0x1E4D0, "V"), + (0x1E4FA, "X"), + (0x1E7E0, "V"), + (0x1E7E7, "X"), + (0x1E7E8, "V"), + (0x1E7EC, "X"), + (0x1E7ED, "V"), + (0x1E7EF, "X"), + (0x1E7F0, "V"), + (0x1E7FF, "X"), + (0x1E800, "V"), + (0x1E8C5, "X"), + (0x1E8C7, "V"), + (0x1E8D7, "X"), + (0x1E900, "M", "𞤢"), + (0x1E901, "M", "𞤣"), + (0x1E902, "M", "𞤤"), + (0x1E903, "M", "𞤥"), + (0x1E904, "M", "𞤦"), + (0x1E905, "M", "𞤧"), + (0x1E906, "M", "𞤨"), + (0x1E907, "M", "𞤩"), + (0x1E908, "M", "𞤪"), + (0x1E909, "M", "𞤫"), + (0x1E90A, "M", "𞤬"), + (0x1E90B, "M", "𞤭"), + (0x1E90C, "M", "𞤮"), + (0x1E90D, "M", "𞤯"), ] + def _seg_72() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1E90A, 'M', '𞤬'), - (0x1E90B, 'M', '𞤭'), - (0x1E90C, 'M', '𞤮'), - (0x1E90D, 'M', '𞤯'), - (0x1E90E, 'M', '𞤰'), - (0x1E90F, 'M', '𞤱'), - (0x1E910, 'M', '𞤲'), - (0x1E911, 'M', '𞤳'), - (0x1E912, 'M', '𞤴'), - (0x1E913, 'M', '𞤵'), - (0x1E914, 'M', '𞤶'), - (0x1E915, 'M', '𞤷'), - (0x1E916, 'M', '𞤸'), - (0x1E917, 'M', '𞤹'), - (0x1E918, 'M', '𞤺'), - (0x1E919, 'M', '𞤻'), - (0x1E91A, 'M', '𞤼'), - (0x1E91B, 'M', '𞤽'), - (0x1E91C, 'M', '𞤾'), - (0x1E91D, 'M', '𞤿'), - (0x1E91E, 'M', '𞥀'), - (0x1E91F, 'M', '𞥁'), - (0x1E920, 'M', '𞥂'), - (0x1E921, 'M', '𞥃'), - (0x1E922, 'V'), - (0x1E94C, 'X'), - (0x1E950, 'V'), - (0x1E95A, 'X'), - (0x1E95E, 'V'), - (0x1E960, 'X'), - (0x1EC71, 'V'), - (0x1ECB5, 'X'), - (0x1ED01, 'V'), - (0x1ED3E, 'X'), - (0x1EE00, 'M', 'ا'), - (0x1EE01, 'M', 'ب'), - (0x1EE02, 'M', 'ج'), - (0x1EE03, 'M', 'د'), - (0x1EE04, 'X'), - (0x1EE05, 'M', 'و'), - (0x1EE06, 'M', 'ز'), - (0x1EE07, 'M', 'ح'), - (0x1EE08, 'M', 'ط'), - (0x1EE09, 'M', 'ي'), - (0x1EE0A, 'M', 'ك'), - (0x1EE0B, 'M', 'ل'), - (0x1EE0C, 'M', 'م'), - (0x1EE0D, 'M', 'ن'), - (0x1EE0E, 'M', 'س'), - (0x1EE0F, 'M', 'ع'), - (0x1EE10, 'M', 'ف'), - (0x1EE11, 'M', 'ص'), - (0x1EE12, 'M', 'ق'), - (0x1EE13, 'M', 'ر'), - (0x1EE14, 'M', 'ش'), - (0x1EE15, 'M', 'ت'), - (0x1EE16, 'M', 'ث'), - (0x1EE17, 'M', 'خ'), - (0x1EE18, 'M', 'ذ'), - (0x1EE19, 'M', 'ض'), - (0x1EE1A, 'M', 'ظ'), - (0x1EE1B, 'M', 'غ'), - (0x1EE1C, 'M', 'ٮ'), - (0x1EE1D, 'M', 'ں'), - (0x1EE1E, 'M', 'ڡ'), - (0x1EE1F, 'M', 'ٯ'), - (0x1EE20, 'X'), - (0x1EE21, 'M', 'ب'), - (0x1EE22, 'M', 'ج'), - (0x1EE23, 'X'), - (0x1EE24, 'M', 'ه'), - (0x1EE25, 'X'), - (0x1EE27, 'M', 'ح'), - (0x1EE28, 'X'), - (0x1EE29, 'M', 'ي'), - (0x1EE2A, 'M', 'ك'), - (0x1EE2B, 'M', 'ل'), - (0x1EE2C, 'M', 'م'), - (0x1EE2D, 'M', 'ن'), - (0x1EE2E, 'M', 'س'), - (0x1EE2F, 'M', 'ع'), - (0x1EE30, 'M', 'ف'), - (0x1EE31, 'M', 'ص'), - (0x1EE32, 'M', 'ق'), - (0x1EE33, 'X'), - (0x1EE34, 'M', 'ش'), - (0x1EE35, 'M', 'ت'), - (0x1EE36, 'M', 'ث'), - (0x1EE37, 'M', 'خ'), - (0x1EE38, 'X'), - (0x1EE39, 'M', 'ض'), - (0x1EE3A, 'X'), - (0x1EE3B, 'M', 'غ'), - (0x1EE3C, 'X'), - (0x1EE42, 'M', 'ج'), - (0x1EE43, 'X'), - (0x1EE47, 'M', 'ح'), - (0x1EE48, 'X'), - (0x1EE49, 'M', 'ي'), - (0x1EE4A, 'X'), + (0x1E90E, "M", "𞤰"), + (0x1E90F, "M", "𞤱"), + (0x1E910, "M", "𞤲"), + (0x1E911, "M", "𞤳"), + (0x1E912, "M", "𞤴"), + (0x1E913, "M", "𞤵"), + (0x1E914, "M", "𞤶"), + (0x1E915, "M", "𞤷"), + (0x1E916, "M", "𞤸"), + (0x1E917, "M", "𞤹"), + (0x1E918, "M", "𞤺"), + (0x1E919, "M", "𞤻"), + (0x1E91A, "M", "𞤼"), + (0x1E91B, "M", "𞤽"), + (0x1E91C, "M", "𞤾"), + (0x1E91D, "M", "𞤿"), + (0x1E91E, "M", "𞥀"), + (0x1E91F, "M", "𞥁"), + (0x1E920, "M", "𞥂"), + (0x1E921, "M", "𞥃"), + (0x1E922, "V"), + (0x1E94C, "X"), + (0x1E950, "V"), + (0x1E95A, "X"), + (0x1E95E, "V"), + (0x1E960, "X"), + (0x1EC71, "V"), + (0x1ECB5, "X"), + (0x1ED01, "V"), + (0x1ED3E, "X"), + (0x1EE00, "M", "ا"), + (0x1EE01, "M", "ب"), + (0x1EE02, "M", "ج"), + (0x1EE03, "M", "د"), + (0x1EE04, "X"), + (0x1EE05, "M", "و"), + (0x1EE06, "M", "ز"), + (0x1EE07, "M", "ح"), + (0x1EE08, "M", "ط"), + (0x1EE09, "M", "ي"), + (0x1EE0A, "M", "ك"), + (0x1EE0B, "M", "ل"), + (0x1EE0C, "M", "م"), + (0x1EE0D, "M", "ن"), + (0x1EE0E, "M", "س"), + (0x1EE0F, "M", "ع"), + (0x1EE10, "M", "ف"), + (0x1EE11, "M", "ص"), + (0x1EE12, "M", "ق"), + (0x1EE13, "M", "ر"), + (0x1EE14, "M", "ش"), + (0x1EE15, "M", "ت"), + (0x1EE16, "M", "ث"), + (0x1EE17, "M", "خ"), + (0x1EE18, "M", "ذ"), + (0x1EE19, "M", "ض"), + (0x1EE1A, "M", "ظ"), + (0x1EE1B, "M", "غ"), + (0x1EE1C, "M", "ٮ"), + (0x1EE1D, "M", "ں"), + (0x1EE1E, "M", "ڡ"), + (0x1EE1F, "M", "ٯ"), + (0x1EE20, "X"), + (0x1EE21, "M", "ب"), + (0x1EE22, "M", "ج"), + (0x1EE23, "X"), + (0x1EE24, "M", "ه"), + (0x1EE25, "X"), + (0x1EE27, "M", "ح"), + (0x1EE28, "X"), + (0x1EE29, "M", "ي"), + (0x1EE2A, "M", "ك"), + (0x1EE2B, "M", "ل"), + (0x1EE2C, "M", "م"), + (0x1EE2D, "M", "ن"), + (0x1EE2E, "M", "س"), + (0x1EE2F, "M", "ع"), + (0x1EE30, "M", "ف"), + (0x1EE31, "M", "ص"), + (0x1EE32, "M", "ق"), + (0x1EE33, "X"), + (0x1EE34, "M", "ش"), + (0x1EE35, "M", "ت"), + (0x1EE36, "M", "ث"), + (0x1EE37, "M", "خ"), + (0x1EE38, "X"), + (0x1EE39, "M", "ض"), + (0x1EE3A, "X"), + (0x1EE3B, "M", "غ"), + (0x1EE3C, "X"), + (0x1EE42, "M", "ج"), + (0x1EE43, "X"), + (0x1EE47, "M", "ح"), + (0x1EE48, "X"), + (0x1EE49, "M", "ي"), + (0x1EE4A, "X"), + (0x1EE4B, "M", "ل"), + (0x1EE4C, "X"), + (0x1EE4D, "M", "ن"), + (0x1EE4E, "M", "س"), ] + def _seg_73() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1EE4B, 'M', 'ل'), - (0x1EE4C, 'X'), - (0x1EE4D, 'M', 'ن'), - (0x1EE4E, 'M', 'س'), - (0x1EE4F, 'M', 'ع'), - (0x1EE50, 'X'), - (0x1EE51, 'M', 'ص'), - (0x1EE52, 'M', 'ق'), - (0x1EE53, 'X'), - (0x1EE54, 'M', 'ش'), - (0x1EE55, 'X'), - (0x1EE57, 'M', 'خ'), - (0x1EE58, 'X'), - (0x1EE59, 'M', 'ض'), - (0x1EE5A, 'X'), - (0x1EE5B, 'M', 'غ'), - (0x1EE5C, 'X'), - (0x1EE5D, 'M', 'ں'), - (0x1EE5E, 'X'), - (0x1EE5F, 'M', 'ٯ'), - (0x1EE60, 'X'), - (0x1EE61, 'M', 'ب'), - (0x1EE62, 'M', 'ج'), - (0x1EE63, 'X'), - (0x1EE64, 'M', 'ه'), - (0x1EE65, 'X'), - (0x1EE67, 'M', 'ح'), - (0x1EE68, 'M', 'ط'), - (0x1EE69, 'M', 'ي'), - (0x1EE6A, 'M', 'ك'), - (0x1EE6B, 'X'), - (0x1EE6C, 'M', 'م'), - (0x1EE6D, 'M', 'ن'), - (0x1EE6E, 'M', 'س'), - (0x1EE6F, 'M', 'ع'), - (0x1EE70, 'M', 'ف'), - (0x1EE71, 'M', 'ص'), - (0x1EE72, 'M', 'ق'), - (0x1EE73, 'X'), - (0x1EE74, 'M', 'ش'), - (0x1EE75, 'M', 'ت'), - (0x1EE76, 'M', 'ث'), - (0x1EE77, 'M', 'خ'), - (0x1EE78, 'X'), - (0x1EE79, 'M', 'ض'), - (0x1EE7A, 'M', 'ظ'), - (0x1EE7B, 'M', 'غ'), - (0x1EE7C, 'M', 'ٮ'), - (0x1EE7D, 'X'), - (0x1EE7E, 'M', 'ڡ'), - (0x1EE7F, 'X'), - (0x1EE80, 'M', 'ا'), - (0x1EE81, 'M', 'ب'), - (0x1EE82, 'M', 'ج'), - (0x1EE83, 'M', 'د'), - (0x1EE84, 'M', 'ه'), - (0x1EE85, 'M', 'و'), - (0x1EE86, 'M', 'ز'), - (0x1EE87, 'M', 'ح'), - (0x1EE88, 'M', 'ط'), - (0x1EE89, 'M', 'ي'), - (0x1EE8A, 'X'), - (0x1EE8B, 'M', 'ل'), - (0x1EE8C, 'M', 'م'), - (0x1EE8D, 'M', 'ن'), - (0x1EE8E, 'M', 'س'), - (0x1EE8F, 'M', 'ع'), - (0x1EE90, 'M', 'ف'), - (0x1EE91, 'M', 'ص'), - (0x1EE92, 'M', 'ق'), - (0x1EE93, 'M', 'ر'), - (0x1EE94, 'M', 'ش'), - (0x1EE95, 'M', 'ت'), - (0x1EE96, 'M', 'ث'), - (0x1EE97, 'M', 'خ'), - (0x1EE98, 'M', 'ذ'), - (0x1EE99, 'M', 'ض'), - (0x1EE9A, 'M', 'ظ'), - (0x1EE9B, 'M', 'غ'), - (0x1EE9C, 'X'), - (0x1EEA1, 'M', 'ب'), - (0x1EEA2, 'M', 'ج'), - (0x1EEA3, 'M', 'د'), - (0x1EEA4, 'X'), - (0x1EEA5, 'M', 'و'), - (0x1EEA6, 'M', 'ز'), - (0x1EEA7, 'M', 'ح'), - (0x1EEA8, 'M', 'ط'), - (0x1EEA9, 'M', 'ي'), - (0x1EEAA, 'X'), - (0x1EEAB, 'M', 'ل'), - (0x1EEAC, 'M', 'م'), - (0x1EEAD, 'M', 'ن'), - (0x1EEAE, 'M', 'س'), - (0x1EEAF, 'M', 'ع'), - (0x1EEB0, 'M', 'ف'), - (0x1EEB1, 'M', 'ص'), - (0x1EEB2, 'M', 'ق'), - (0x1EEB3, 'M', 'ر'), - (0x1EEB4, 'M', 'ش'), + (0x1EE4F, "M", "ع"), + (0x1EE50, "X"), + (0x1EE51, "M", "ص"), + (0x1EE52, "M", "ق"), + (0x1EE53, "X"), + (0x1EE54, "M", "ش"), + (0x1EE55, "X"), + (0x1EE57, "M", "خ"), + (0x1EE58, "X"), + (0x1EE59, "M", "ض"), + (0x1EE5A, "X"), + (0x1EE5B, "M", "غ"), + (0x1EE5C, "X"), + (0x1EE5D, "M", "ں"), + (0x1EE5E, "X"), + (0x1EE5F, "M", "ٯ"), + (0x1EE60, "X"), + (0x1EE61, "M", "ب"), + (0x1EE62, "M", "ج"), + (0x1EE63, "X"), + (0x1EE64, "M", "ه"), + (0x1EE65, "X"), + (0x1EE67, "M", "ح"), + (0x1EE68, "M", "ط"), + (0x1EE69, "M", "ي"), + (0x1EE6A, "M", "ك"), + (0x1EE6B, "X"), + (0x1EE6C, "M", "م"), + (0x1EE6D, "M", "ن"), + (0x1EE6E, "M", "س"), + (0x1EE6F, "M", "ع"), + (0x1EE70, "M", "ف"), + (0x1EE71, "M", "ص"), + (0x1EE72, "M", "ق"), + (0x1EE73, "X"), + (0x1EE74, "M", "ش"), + (0x1EE75, "M", "ت"), + (0x1EE76, "M", "ث"), + (0x1EE77, "M", "خ"), + (0x1EE78, "X"), + (0x1EE79, "M", "ض"), + (0x1EE7A, "M", "ظ"), + (0x1EE7B, "M", "غ"), + (0x1EE7C, "M", "ٮ"), + (0x1EE7D, "X"), + (0x1EE7E, "M", "ڡ"), + (0x1EE7F, "X"), + (0x1EE80, "M", "ا"), + (0x1EE81, "M", "ب"), + (0x1EE82, "M", "ج"), + (0x1EE83, "M", "د"), + (0x1EE84, "M", "ه"), + (0x1EE85, "M", "و"), + (0x1EE86, "M", "ز"), + (0x1EE87, "M", "ح"), + (0x1EE88, "M", "ط"), + (0x1EE89, "M", "ي"), + (0x1EE8A, "X"), + (0x1EE8B, "M", "ل"), + (0x1EE8C, "M", "م"), + (0x1EE8D, "M", "ن"), + (0x1EE8E, "M", "س"), + (0x1EE8F, "M", "ع"), + (0x1EE90, "M", "ف"), + (0x1EE91, "M", "ص"), + (0x1EE92, "M", "ق"), + (0x1EE93, "M", "ر"), + (0x1EE94, "M", "ش"), + (0x1EE95, "M", "ت"), + (0x1EE96, "M", "ث"), + (0x1EE97, "M", "خ"), + (0x1EE98, "M", "ذ"), + (0x1EE99, "M", "ض"), + (0x1EE9A, "M", "ظ"), + (0x1EE9B, "M", "غ"), + (0x1EE9C, "X"), + (0x1EEA1, "M", "ب"), + (0x1EEA2, "M", "ج"), + (0x1EEA3, "M", "د"), + (0x1EEA4, "X"), + (0x1EEA5, "M", "و"), + (0x1EEA6, "M", "ز"), + (0x1EEA7, "M", "ح"), + (0x1EEA8, "M", "ط"), + (0x1EEA9, "M", "ي"), + (0x1EEAA, "X"), + (0x1EEAB, "M", "ل"), + (0x1EEAC, "M", "م"), + (0x1EEAD, "M", "ن"), + (0x1EEAE, "M", "س"), + (0x1EEAF, "M", "ع"), + (0x1EEB0, "M", "ف"), + (0x1EEB1, "M", "ص"), + (0x1EEB2, "M", "ق"), + (0x1EEB3, "M", "ر"), + (0x1EEB4, "M", "ش"), + (0x1EEB5, "M", "ت"), + (0x1EEB6, "M", "ث"), + (0x1EEB7, "M", "خ"), + (0x1EEB8, "M", "ذ"), ] + def _seg_74() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1EEB5, 'M', 'ت'), - (0x1EEB6, 'M', 'ث'), - (0x1EEB7, 'M', 'خ'), - (0x1EEB8, 'M', 'ذ'), - (0x1EEB9, 'M', 'ض'), - (0x1EEBA, 'M', 'ظ'), - (0x1EEBB, 'M', 'غ'), - (0x1EEBC, 'X'), - (0x1EEF0, 'V'), - (0x1EEF2, 'X'), - (0x1F000, 'V'), - (0x1F02C, 'X'), - (0x1F030, 'V'), - (0x1F094, 'X'), - (0x1F0A0, 'V'), - (0x1F0AF, 'X'), - (0x1F0B1, 'V'), - (0x1F0C0, 'X'), - (0x1F0C1, 'V'), - (0x1F0D0, 'X'), - (0x1F0D1, 'V'), - (0x1F0F6, 'X'), - (0x1F101, '3', '0,'), - (0x1F102, '3', '1,'), - (0x1F103, '3', '2,'), - (0x1F104, '3', '3,'), - (0x1F105, '3', '4,'), - (0x1F106, '3', '5,'), - (0x1F107, '3', '6,'), - (0x1F108, '3', '7,'), - (0x1F109, '3', '8,'), - (0x1F10A, '3', '9,'), - (0x1F10B, 'V'), - (0x1F110, '3', '(a)'), - (0x1F111, '3', '(b)'), - (0x1F112, '3', '(c)'), - (0x1F113, '3', '(d)'), - (0x1F114, '3', '(e)'), - (0x1F115, '3', '(f)'), - (0x1F116, '3', '(g)'), - (0x1F117, '3', '(h)'), - (0x1F118, '3', '(i)'), - (0x1F119, '3', '(j)'), - (0x1F11A, '3', '(k)'), - (0x1F11B, '3', '(l)'), - (0x1F11C, '3', '(m)'), - (0x1F11D, '3', '(n)'), - (0x1F11E, '3', '(o)'), - (0x1F11F, '3', '(p)'), - (0x1F120, '3', '(q)'), - (0x1F121, '3', '(r)'), - (0x1F122, '3', '(s)'), - (0x1F123, '3', '(t)'), - (0x1F124, '3', '(u)'), - (0x1F125, '3', '(v)'), - (0x1F126, '3', '(w)'), - (0x1F127, '3', '(x)'), - (0x1F128, '3', '(y)'), - (0x1F129, '3', '(z)'), - (0x1F12A, 'M', '〔s〕'), - (0x1F12B, 'M', 'c'), - (0x1F12C, 'M', 'r'), - (0x1F12D, 'M', 'cd'), - (0x1F12E, 'M', 'wz'), - (0x1F12F, 'V'), - (0x1F130, 'M', 'a'), - (0x1F131, 'M', 'b'), - (0x1F132, 'M', 'c'), - (0x1F133, 'M', 'd'), - (0x1F134, 'M', 'e'), - (0x1F135, 'M', 'f'), - (0x1F136, 'M', 'g'), - (0x1F137, 'M', 'h'), - (0x1F138, 'M', 'i'), - (0x1F139, 'M', 'j'), - (0x1F13A, 'M', 'k'), - (0x1F13B, 'M', 'l'), - (0x1F13C, 'M', 'm'), - (0x1F13D, 'M', 'n'), - (0x1F13E, 'M', 'o'), - (0x1F13F, 'M', 'p'), - (0x1F140, 'M', 'q'), - (0x1F141, 'M', 'r'), - (0x1F142, 'M', 's'), - (0x1F143, 'M', 't'), - (0x1F144, 'M', 'u'), - (0x1F145, 'M', 'v'), - (0x1F146, 'M', 'w'), - (0x1F147, 'M', 'x'), - (0x1F148, 'M', 'y'), - (0x1F149, 'M', 'z'), - (0x1F14A, 'M', 'hv'), - (0x1F14B, 'M', 'mv'), - (0x1F14C, 'M', 'sd'), - (0x1F14D, 'M', 'ss'), - (0x1F14E, 'M', 'ppv'), - (0x1F14F, 'M', 'wc'), - (0x1F150, 'V'), - (0x1F16A, 'M', 'mc'), - (0x1F16B, 'M', 'md'), + (0x1EEB9, "M", "ض"), + (0x1EEBA, "M", "ظ"), + (0x1EEBB, "M", "غ"), + (0x1EEBC, "X"), + (0x1EEF0, "V"), + (0x1EEF2, "X"), + (0x1F000, "V"), + (0x1F02C, "X"), + (0x1F030, "V"), + (0x1F094, "X"), + (0x1F0A0, "V"), + (0x1F0AF, "X"), + (0x1F0B1, "V"), + (0x1F0C0, "X"), + (0x1F0C1, "V"), + (0x1F0D0, "X"), + (0x1F0D1, "V"), + (0x1F0F6, "X"), + (0x1F101, "3", "0,"), + (0x1F102, "3", "1,"), + (0x1F103, "3", "2,"), + (0x1F104, "3", "3,"), + (0x1F105, "3", "4,"), + (0x1F106, "3", "5,"), + (0x1F107, "3", "6,"), + (0x1F108, "3", "7,"), + (0x1F109, "3", "8,"), + (0x1F10A, "3", "9,"), + (0x1F10B, "V"), + (0x1F110, "3", "(a)"), + (0x1F111, "3", "(b)"), + (0x1F112, "3", "(c)"), + (0x1F113, "3", "(d)"), + (0x1F114, "3", "(e)"), + (0x1F115, "3", "(f)"), + (0x1F116, "3", "(g)"), + (0x1F117, "3", "(h)"), + (0x1F118, "3", "(i)"), + (0x1F119, "3", "(j)"), + (0x1F11A, "3", "(k)"), + (0x1F11B, "3", "(l)"), + (0x1F11C, "3", "(m)"), + (0x1F11D, "3", "(n)"), + (0x1F11E, "3", "(o)"), + (0x1F11F, "3", "(p)"), + (0x1F120, "3", "(q)"), + (0x1F121, "3", "(r)"), + (0x1F122, "3", "(s)"), + (0x1F123, "3", "(t)"), + (0x1F124, "3", "(u)"), + (0x1F125, "3", "(v)"), + (0x1F126, "3", "(w)"), + (0x1F127, "3", "(x)"), + (0x1F128, "3", "(y)"), + (0x1F129, "3", "(z)"), + (0x1F12A, "M", "〔s〕"), + (0x1F12B, "M", "c"), + (0x1F12C, "M", "r"), + (0x1F12D, "M", "cd"), + (0x1F12E, "M", "wz"), + (0x1F12F, "V"), + (0x1F130, "M", "a"), + (0x1F131, "M", "b"), + (0x1F132, "M", "c"), + (0x1F133, "M", "d"), + (0x1F134, "M", "e"), + (0x1F135, "M", "f"), + (0x1F136, "M", "g"), + (0x1F137, "M", "h"), + (0x1F138, "M", "i"), + (0x1F139, "M", "j"), + (0x1F13A, "M", "k"), + (0x1F13B, "M", "l"), + (0x1F13C, "M", "m"), + (0x1F13D, "M", "n"), + (0x1F13E, "M", "o"), + (0x1F13F, "M", "p"), + (0x1F140, "M", "q"), + (0x1F141, "M", "r"), + (0x1F142, "M", "s"), + (0x1F143, "M", "t"), + (0x1F144, "M", "u"), + (0x1F145, "M", "v"), + (0x1F146, "M", "w"), + (0x1F147, "M", "x"), + (0x1F148, "M", "y"), + (0x1F149, "M", "z"), + (0x1F14A, "M", "hv"), + (0x1F14B, "M", "mv"), + (0x1F14C, "M", "sd"), + (0x1F14D, "M", "ss"), + (0x1F14E, "M", "ppv"), + (0x1F14F, "M", "wc"), + (0x1F150, "V"), + (0x1F16A, "M", "mc"), + (0x1F16B, "M", "md"), + (0x1F16C, "M", "mr"), + (0x1F16D, "V"), + (0x1F190, "M", "dj"), + (0x1F191, "V"), ] + def _seg_75() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1F16C, 'M', 'mr'), - (0x1F16D, 'V'), - (0x1F190, 'M', 'dj'), - (0x1F191, 'V'), - (0x1F1AE, 'X'), - (0x1F1E6, 'V'), - (0x1F200, 'M', 'ほか'), - (0x1F201, 'M', 'ココ'), - (0x1F202, 'M', 'サ'), - (0x1F203, 'X'), - (0x1F210, 'M', '手'), - (0x1F211, 'M', '字'), - (0x1F212, 'M', '双'), - (0x1F213, 'M', 'デ'), - (0x1F214, 'M', '二'), - (0x1F215, 'M', '多'), - (0x1F216, 'M', '解'), - (0x1F217, 'M', '天'), - (0x1F218, 'M', '交'), - (0x1F219, 'M', '映'), - (0x1F21A, 'M', '無'), - (0x1F21B, 'M', '料'), - (0x1F21C, 'M', '前'), - (0x1F21D, 'M', '後'), - (0x1F21E, 'M', '再'), - (0x1F21F, 'M', '新'), - (0x1F220, 'M', '初'), - (0x1F221, 'M', '終'), - (0x1F222, 'M', '生'), - (0x1F223, 'M', '販'), - (0x1F224, 'M', '声'), - (0x1F225, 'M', '吹'), - (0x1F226, 'M', '演'), - (0x1F227, 'M', '投'), - (0x1F228, 'M', '捕'), - (0x1F229, 'M', '一'), - (0x1F22A, 'M', '三'), - (0x1F22B, 'M', '遊'), - (0x1F22C, 'M', '左'), - (0x1F22D, 'M', '中'), - (0x1F22E, 'M', '右'), - (0x1F22F, 'M', '指'), - (0x1F230, 'M', '走'), - (0x1F231, 'M', '打'), - (0x1F232, 'M', '禁'), - (0x1F233, 'M', '空'), - (0x1F234, 'M', '合'), - (0x1F235, 'M', '満'), - (0x1F236, 'M', '有'), - (0x1F237, 'M', '月'), - (0x1F238, 'M', '申'), - (0x1F239, 'M', '割'), - (0x1F23A, 'M', '営'), - (0x1F23B, 'M', '配'), - (0x1F23C, 'X'), - (0x1F240, 'M', '〔本〕'), - (0x1F241, 'M', '〔三〕'), - (0x1F242, 'M', '〔二〕'), - (0x1F243, 'M', '〔安〕'), - (0x1F244, 'M', '〔点〕'), - (0x1F245, 'M', '〔打〕'), - (0x1F246, 'M', '〔盗〕'), - (0x1F247, 'M', '〔勝〕'), - (0x1F248, 'M', '〔敗〕'), - (0x1F249, 'X'), - (0x1F250, 'M', '得'), - (0x1F251, 'M', '可'), - (0x1F252, 'X'), - (0x1F260, 'V'), - (0x1F266, 'X'), - (0x1F300, 'V'), - (0x1F6D8, 'X'), - (0x1F6DC, 'V'), - (0x1F6ED, 'X'), - (0x1F6F0, 'V'), - (0x1F6FD, 'X'), - (0x1F700, 'V'), - (0x1F777, 'X'), - (0x1F77B, 'V'), - (0x1F7DA, 'X'), - (0x1F7E0, 'V'), - (0x1F7EC, 'X'), - (0x1F7F0, 'V'), - (0x1F7F1, 'X'), - (0x1F800, 'V'), - (0x1F80C, 'X'), - (0x1F810, 'V'), - (0x1F848, 'X'), - (0x1F850, 'V'), - (0x1F85A, 'X'), - (0x1F860, 'V'), - (0x1F888, 'X'), - (0x1F890, 'V'), - (0x1F8AE, 'X'), - (0x1F8B0, 'V'), - (0x1F8B2, 'X'), - (0x1F900, 'V'), - (0x1FA54, 'X'), - (0x1FA60, 'V'), - (0x1FA6E, 'X'), + (0x1F1AE, "X"), + (0x1F1E6, "V"), + (0x1F200, "M", "ほか"), + (0x1F201, "M", "ココ"), + (0x1F202, "M", "サ"), + (0x1F203, "X"), + (0x1F210, "M", "手"), + (0x1F211, "M", "字"), + (0x1F212, "M", "双"), + (0x1F213, "M", "デ"), + (0x1F214, "M", "二"), + (0x1F215, "M", "多"), + (0x1F216, "M", "解"), + (0x1F217, "M", "天"), + (0x1F218, "M", "交"), + (0x1F219, "M", "映"), + (0x1F21A, "M", "無"), + (0x1F21B, "M", "料"), + (0x1F21C, "M", "前"), + (0x1F21D, "M", "後"), + (0x1F21E, "M", "再"), + (0x1F21F, "M", "新"), + (0x1F220, "M", "初"), + (0x1F221, "M", "終"), + (0x1F222, "M", "生"), + (0x1F223, "M", "販"), + (0x1F224, "M", "声"), + (0x1F225, "M", "吹"), + (0x1F226, "M", "演"), + (0x1F227, "M", "投"), + (0x1F228, "M", "捕"), + (0x1F229, "M", "一"), + (0x1F22A, "M", "三"), + (0x1F22B, "M", "遊"), + (0x1F22C, "M", "左"), + (0x1F22D, "M", "中"), + (0x1F22E, "M", "右"), + (0x1F22F, "M", "指"), + (0x1F230, "M", "走"), + (0x1F231, "M", "打"), + (0x1F232, "M", "禁"), + (0x1F233, "M", "空"), + (0x1F234, "M", "合"), + (0x1F235, "M", "満"), + (0x1F236, "M", "有"), + (0x1F237, "M", "月"), + (0x1F238, "M", "申"), + (0x1F239, "M", "割"), + (0x1F23A, "M", "営"), + (0x1F23B, "M", "配"), + (0x1F23C, "X"), + (0x1F240, "M", "〔本〕"), + (0x1F241, "M", "〔三〕"), + (0x1F242, "M", "〔二〕"), + (0x1F243, "M", "〔安〕"), + (0x1F244, "M", "〔点〕"), + (0x1F245, "M", "〔打〕"), + (0x1F246, "M", "〔盗〕"), + (0x1F247, "M", "〔勝〕"), + (0x1F248, "M", "〔敗〕"), + (0x1F249, "X"), + (0x1F250, "M", "得"), + (0x1F251, "M", "可"), + (0x1F252, "X"), + (0x1F260, "V"), + (0x1F266, "X"), + (0x1F300, "V"), + (0x1F6D8, "X"), + (0x1F6DC, "V"), + (0x1F6ED, "X"), + (0x1F6F0, "V"), + (0x1F6FD, "X"), + (0x1F700, "V"), + (0x1F777, "X"), + (0x1F77B, "V"), + (0x1F7DA, "X"), + (0x1F7E0, "V"), + (0x1F7EC, "X"), + (0x1F7F0, "V"), + (0x1F7F1, "X"), + (0x1F800, "V"), + (0x1F80C, "X"), + (0x1F810, "V"), + (0x1F848, "X"), + (0x1F850, "V"), + (0x1F85A, "X"), + (0x1F860, "V"), + (0x1F888, "X"), + (0x1F890, "V"), + (0x1F8AE, "X"), + (0x1F8B0, "V"), + (0x1F8B2, "X"), + (0x1F900, "V"), + (0x1FA54, "X"), + (0x1FA60, "V"), + (0x1FA6E, "X"), + (0x1FA70, "V"), + (0x1FA7D, "X"), + (0x1FA80, "V"), + (0x1FA89, "X"), ] + def _seg_76() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x1FA70, 'V'), - (0x1FA7D, 'X'), - (0x1FA80, 'V'), - (0x1FA89, 'X'), - (0x1FA90, 'V'), - (0x1FABE, 'X'), - (0x1FABF, 'V'), - (0x1FAC6, 'X'), - (0x1FACE, 'V'), - (0x1FADC, 'X'), - (0x1FAE0, 'V'), - (0x1FAE9, 'X'), - (0x1FAF0, 'V'), - (0x1FAF9, 'X'), - (0x1FB00, 'V'), - (0x1FB93, 'X'), - (0x1FB94, 'V'), - (0x1FBCB, 'X'), - (0x1FBF0, 'M', '0'), - (0x1FBF1, 'M', '1'), - (0x1FBF2, 'M', '2'), - (0x1FBF3, 'M', '3'), - (0x1FBF4, 'M', '4'), - (0x1FBF5, 'M', '5'), - (0x1FBF6, 'M', '6'), - (0x1FBF7, 'M', '7'), - (0x1FBF8, 'M', '8'), - (0x1FBF9, 'M', '9'), - (0x1FBFA, 'X'), - (0x20000, 'V'), - (0x2A6E0, 'X'), - (0x2A700, 'V'), - (0x2B73A, 'X'), - (0x2B740, 'V'), - (0x2B81E, 'X'), - (0x2B820, 'V'), - (0x2CEA2, 'X'), - (0x2CEB0, 'V'), - (0x2EBE1, 'X'), - (0x2F800, 'M', '丽'), - (0x2F801, 'M', '丸'), - (0x2F802, 'M', '乁'), - (0x2F803, 'M', '𠄢'), - (0x2F804, 'M', '你'), - (0x2F805, 'M', '侮'), - (0x2F806, 'M', '侻'), - (0x2F807, 'M', '倂'), - (0x2F808, 'M', '偺'), - (0x2F809, 'M', '備'), - (0x2F80A, 'M', '僧'), - (0x2F80B, 'M', '像'), - (0x2F80C, 'M', '㒞'), - (0x2F80D, 'M', '𠘺'), - (0x2F80E, 'M', '免'), - (0x2F80F, 'M', '兔'), - (0x2F810, 'M', '兤'), - (0x2F811, 'M', '具'), - (0x2F812, 'M', '𠔜'), - (0x2F813, 'M', '㒹'), - (0x2F814, 'M', '內'), - (0x2F815, 'M', '再'), - (0x2F816, 'M', '𠕋'), - (0x2F817, 'M', '冗'), - (0x2F818, 'M', '冤'), - (0x2F819, 'M', '仌'), - (0x2F81A, 'M', '冬'), - (0x2F81B, 'M', '况'), - (0x2F81C, 'M', '𩇟'), - (0x2F81D, 'M', '凵'), - (0x2F81E, 'M', '刃'), - (0x2F81F, 'M', '㓟'), - (0x2F820, 'M', '刻'), - (0x2F821, 'M', '剆'), - (0x2F822, 'M', '割'), - (0x2F823, 'M', '剷'), - (0x2F824, 'M', '㔕'), - (0x2F825, 'M', '勇'), - (0x2F826, 'M', '勉'), - (0x2F827, 'M', '勤'), - (0x2F828, 'M', '勺'), - (0x2F829, 'M', '包'), - (0x2F82A, 'M', '匆'), - (0x2F82B, 'M', '北'), - (0x2F82C, 'M', '卉'), - (0x2F82D, 'M', '卑'), - (0x2F82E, 'M', '博'), - (0x2F82F, 'M', '即'), - (0x2F830, 'M', '卽'), - (0x2F831, 'M', '卿'), - (0x2F834, 'M', '𠨬'), - (0x2F835, 'M', '灰'), - (0x2F836, 'M', '及'), - (0x2F837, 'M', '叟'), - (0x2F838, 'M', '𠭣'), - (0x2F839, 'M', '叫'), - (0x2F83A, 'M', '叱'), - (0x2F83B, 'M', '吆'), - (0x2F83C, 'M', '咞'), - (0x2F83D, 'M', '吸'), - (0x2F83E, 'M', '呈'), + (0x1FA90, "V"), + (0x1FABE, "X"), + (0x1FABF, "V"), + (0x1FAC6, "X"), + (0x1FACE, "V"), + (0x1FADC, "X"), + (0x1FAE0, "V"), + (0x1FAE9, "X"), + (0x1FAF0, "V"), + (0x1FAF9, "X"), + (0x1FB00, "V"), + (0x1FB93, "X"), + (0x1FB94, "V"), + (0x1FBCB, "X"), + (0x1FBF0, "M", "0"), + (0x1FBF1, "M", "1"), + (0x1FBF2, "M", "2"), + (0x1FBF3, "M", "3"), + (0x1FBF4, "M", "4"), + (0x1FBF5, "M", "5"), + (0x1FBF6, "M", "6"), + (0x1FBF7, "M", "7"), + (0x1FBF8, "M", "8"), + (0x1FBF9, "M", "9"), + (0x1FBFA, "X"), + (0x20000, "V"), + (0x2A6E0, "X"), + (0x2A700, "V"), + (0x2B73A, "X"), + (0x2B740, "V"), + (0x2B81E, "X"), + (0x2B820, "V"), + (0x2CEA2, "X"), + (0x2CEB0, "V"), + (0x2EBE1, "X"), + (0x2EBF0, "V"), + (0x2EE5E, "X"), + (0x2F800, "M", "丽"), + (0x2F801, "M", "丸"), + (0x2F802, "M", "乁"), + (0x2F803, "M", "𠄢"), + (0x2F804, "M", "你"), + (0x2F805, "M", "侮"), + (0x2F806, "M", "侻"), + (0x2F807, "M", "倂"), + (0x2F808, "M", "偺"), + (0x2F809, "M", "備"), + (0x2F80A, "M", "僧"), + (0x2F80B, "M", "像"), + (0x2F80C, "M", "㒞"), + (0x2F80D, "M", "𠘺"), + (0x2F80E, "M", "免"), + (0x2F80F, "M", "兔"), + (0x2F810, "M", "兤"), + (0x2F811, "M", "具"), + (0x2F812, "M", "𠔜"), + (0x2F813, "M", "㒹"), + (0x2F814, "M", "內"), + (0x2F815, "M", "再"), + (0x2F816, "M", "𠕋"), + (0x2F817, "M", "冗"), + (0x2F818, "M", "冤"), + (0x2F819, "M", "仌"), + (0x2F81A, "M", "冬"), + (0x2F81B, "M", "况"), + (0x2F81C, "M", "𩇟"), + (0x2F81D, "M", "凵"), + (0x2F81E, "M", "刃"), + (0x2F81F, "M", "㓟"), + (0x2F820, "M", "刻"), + (0x2F821, "M", "剆"), + (0x2F822, "M", "割"), + (0x2F823, "M", "剷"), + (0x2F824, "M", "㔕"), + (0x2F825, "M", "勇"), + (0x2F826, "M", "勉"), + (0x2F827, "M", "勤"), + (0x2F828, "M", "勺"), + (0x2F829, "M", "包"), + (0x2F82A, "M", "匆"), + (0x2F82B, "M", "北"), + (0x2F82C, "M", "卉"), + (0x2F82D, "M", "卑"), + (0x2F82E, "M", "博"), + (0x2F82F, "M", "即"), + (0x2F830, "M", "卽"), + (0x2F831, "M", "卿"), + (0x2F834, "M", "𠨬"), + (0x2F835, "M", "灰"), + (0x2F836, "M", "及"), + (0x2F837, "M", "叟"), + (0x2F838, "M", "𠭣"), + (0x2F839, "M", "叫"), + (0x2F83A, "M", "叱"), + (0x2F83B, "M", "吆"), + (0x2F83C, "M", "咞"), + (0x2F83D, "M", "吸"), + (0x2F83E, "M", "呈"), + (0x2F83F, "M", "周"), + (0x2F840, "M", "咢"), ] + def _seg_77() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2F83F, 'M', '周'), - (0x2F840, 'M', '咢'), - (0x2F841, 'M', '哶'), - (0x2F842, 'M', '唐'), - (0x2F843, 'M', '啓'), - (0x2F844, 'M', '啣'), - (0x2F845, 'M', '善'), - (0x2F847, 'M', '喙'), - (0x2F848, 'M', '喫'), - (0x2F849, 'M', '喳'), - (0x2F84A, 'M', '嗂'), - (0x2F84B, 'M', '圖'), - (0x2F84C, 'M', '嘆'), - (0x2F84D, 'M', '圗'), - (0x2F84E, 'M', '噑'), - (0x2F84F, 'M', '噴'), - (0x2F850, 'M', '切'), - (0x2F851, 'M', '壮'), - (0x2F852, 'M', '城'), - (0x2F853, 'M', '埴'), - (0x2F854, 'M', '堍'), - (0x2F855, 'M', '型'), - (0x2F856, 'M', '堲'), - (0x2F857, 'M', '報'), - (0x2F858, 'M', '墬'), - (0x2F859, 'M', '𡓤'), - (0x2F85A, 'M', '売'), - (0x2F85B, 'M', '壷'), - (0x2F85C, 'M', '夆'), - (0x2F85D, 'M', '多'), - (0x2F85E, 'M', '夢'), - (0x2F85F, 'M', '奢'), - (0x2F860, 'M', '𡚨'), - (0x2F861, 'M', '𡛪'), - (0x2F862, 'M', '姬'), - (0x2F863, 'M', '娛'), - (0x2F864, 'M', '娧'), - (0x2F865, 'M', '姘'), - (0x2F866, 'M', '婦'), - (0x2F867, 'M', '㛮'), - (0x2F868, 'X'), - (0x2F869, 'M', '嬈'), - (0x2F86A, 'M', '嬾'), - (0x2F86C, 'M', '𡧈'), - (0x2F86D, 'M', '寃'), - (0x2F86E, 'M', '寘'), - (0x2F86F, 'M', '寧'), - (0x2F870, 'M', '寳'), - (0x2F871, 'M', '𡬘'), - (0x2F872, 'M', '寿'), - (0x2F873, 'M', '将'), - (0x2F874, 'X'), - (0x2F875, 'M', '尢'), - (0x2F876, 'M', '㞁'), - (0x2F877, 'M', '屠'), - (0x2F878, 'M', '屮'), - (0x2F879, 'M', '峀'), - (0x2F87A, 'M', '岍'), - (0x2F87B, 'M', '𡷤'), - (0x2F87C, 'M', '嵃'), - (0x2F87D, 'M', '𡷦'), - (0x2F87E, 'M', '嵮'), - (0x2F87F, 'M', '嵫'), - (0x2F880, 'M', '嵼'), - (0x2F881, 'M', '巡'), - (0x2F882, 'M', '巢'), - (0x2F883, 'M', '㠯'), - (0x2F884, 'M', '巽'), - (0x2F885, 'M', '帨'), - (0x2F886, 'M', '帽'), - (0x2F887, 'M', '幩'), - (0x2F888, 'M', '㡢'), - (0x2F889, 'M', '𢆃'), - (0x2F88A, 'M', '㡼'), - (0x2F88B, 'M', '庰'), - (0x2F88C, 'M', '庳'), - (0x2F88D, 'M', '庶'), - (0x2F88E, 'M', '廊'), - (0x2F88F, 'M', '𪎒'), - (0x2F890, 'M', '廾'), - (0x2F891, 'M', '𢌱'), - (0x2F893, 'M', '舁'), - (0x2F894, 'M', '弢'), - (0x2F896, 'M', '㣇'), - (0x2F897, 'M', '𣊸'), - (0x2F898, 'M', '𦇚'), - (0x2F899, 'M', '形'), - (0x2F89A, 'M', '彫'), - (0x2F89B, 'M', '㣣'), - (0x2F89C, 'M', '徚'), - (0x2F89D, 'M', '忍'), - (0x2F89E, 'M', '志'), - (0x2F89F, 'M', '忹'), - (0x2F8A0, 'M', '悁'), - (0x2F8A1, 'M', '㤺'), - (0x2F8A2, 'M', '㤜'), - (0x2F8A3, 'M', '悔'), - (0x2F8A4, 'M', '𢛔'), - (0x2F8A5, 'M', '惇'), - (0x2F8A6, 'M', '慈'), + (0x2F841, "M", "哶"), + (0x2F842, "M", "唐"), + (0x2F843, "M", "啓"), + (0x2F844, "M", "啣"), + (0x2F845, "M", "善"), + (0x2F847, "M", "喙"), + (0x2F848, "M", "喫"), + (0x2F849, "M", "喳"), + (0x2F84A, "M", "嗂"), + (0x2F84B, "M", "圖"), + (0x2F84C, "M", "嘆"), + (0x2F84D, "M", "圗"), + (0x2F84E, "M", "噑"), + (0x2F84F, "M", "噴"), + (0x2F850, "M", "切"), + (0x2F851, "M", "壮"), + (0x2F852, "M", "城"), + (0x2F853, "M", "埴"), + (0x2F854, "M", "堍"), + (0x2F855, "M", "型"), + (0x2F856, "M", "堲"), + (0x2F857, "M", "報"), + (0x2F858, "M", "墬"), + (0x2F859, "M", "𡓤"), + (0x2F85A, "M", "売"), + (0x2F85B, "M", "壷"), + (0x2F85C, "M", "夆"), + (0x2F85D, "M", "多"), + (0x2F85E, "M", "夢"), + (0x2F85F, "M", "奢"), + (0x2F860, "M", "𡚨"), + (0x2F861, "M", "𡛪"), + (0x2F862, "M", "姬"), + (0x2F863, "M", "娛"), + (0x2F864, "M", "娧"), + (0x2F865, "M", "姘"), + (0x2F866, "M", "婦"), + (0x2F867, "M", "㛮"), + (0x2F868, "X"), + (0x2F869, "M", "嬈"), + (0x2F86A, "M", "嬾"), + (0x2F86C, "M", "𡧈"), + (0x2F86D, "M", "寃"), + (0x2F86E, "M", "寘"), + (0x2F86F, "M", "寧"), + (0x2F870, "M", "寳"), + (0x2F871, "M", "𡬘"), + (0x2F872, "M", "寿"), + (0x2F873, "M", "将"), + (0x2F874, "X"), + (0x2F875, "M", "尢"), + (0x2F876, "M", "㞁"), + (0x2F877, "M", "屠"), + (0x2F878, "M", "屮"), + (0x2F879, "M", "峀"), + (0x2F87A, "M", "岍"), + (0x2F87B, "M", "𡷤"), + (0x2F87C, "M", "嵃"), + (0x2F87D, "M", "𡷦"), + (0x2F87E, "M", "嵮"), + (0x2F87F, "M", "嵫"), + (0x2F880, "M", "嵼"), + (0x2F881, "M", "巡"), + (0x2F882, "M", "巢"), + (0x2F883, "M", "㠯"), + (0x2F884, "M", "巽"), + (0x2F885, "M", "帨"), + (0x2F886, "M", "帽"), + (0x2F887, "M", "幩"), + (0x2F888, "M", "㡢"), + (0x2F889, "M", "𢆃"), + (0x2F88A, "M", "㡼"), + (0x2F88B, "M", "庰"), + (0x2F88C, "M", "庳"), + (0x2F88D, "M", "庶"), + (0x2F88E, "M", "廊"), + (0x2F88F, "M", "𪎒"), + (0x2F890, "M", "廾"), + (0x2F891, "M", "𢌱"), + (0x2F893, "M", "舁"), + (0x2F894, "M", "弢"), + (0x2F896, "M", "㣇"), + (0x2F897, "M", "𣊸"), + (0x2F898, "M", "𦇚"), + (0x2F899, "M", "形"), + (0x2F89A, "M", "彫"), + (0x2F89B, "M", "㣣"), + (0x2F89C, "M", "徚"), + (0x2F89D, "M", "忍"), + (0x2F89E, "M", "志"), + (0x2F89F, "M", "忹"), + (0x2F8A0, "M", "悁"), + (0x2F8A1, "M", "㤺"), + (0x2F8A2, "M", "㤜"), + (0x2F8A3, "M", "悔"), + (0x2F8A4, "M", "𢛔"), + (0x2F8A5, "M", "惇"), + (0x2F8A6, "M", "慈"), + (0x2F8A7, "M", "慌"), + (0x2F8A8, "M", "慎"), ] + def _seg_78() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2F8A7, 'M', '慌'), - (0x2F8A8, 'M', '慎'), - (0x2F8A9, 'M', '慌'), - (0x2F8AA, 'M', '慺'), - (0x2F8AB, 'M', '憎'), - (0x2F8AC, 'M', '憲'), - (0x2F8AD, 'M', '憤'), - (0x2F8AE, 'M', '憯'), - (0x2F8AF, 'M', '懞'), - (0x2F8B0, 'M', '懲'), - (0x2F8B1, 'M', '懶'), - (0x2F8B2, 'M', '成'), - (0x2F8B3, 'M', '戛'), - (0x2F8B4, 'M', '扝'), - (0x2F8B5, 'M', '抱'), - (0x2F8B6, 'M', '拔'), - (0x2F8B7, 'M', '捐'), - (0x2F8B8, 'M', '𢬌'), - (0x2F8B9, 'M', '挽'), - (0x2F8BA, 'M', '拼'), - (0x2F8BB, 'M', '捨'), - (0x2F8BC, 'M', '掃'), - (0x2F8BD, 'M', '揤'), - (0x2F8BE, 'M', '𢯱'), - (0x2F8BF, 'M', '搢'), - (0x2F8C0, 'M', '揅'), - (0x2F8C1, 'M', '掩'), - (0x2F8C2, 'M', '㨮'), - (0x2F8C3, 'M', '摩'), - (0x2F8C4, 'M', '摾'), - (0x2F8C5, 'M', '撝'), - (0x2F8C6, 'M', '摷'), - (0x2F8C7, 'M', '㩬'), - (0x2F8C8, 'M', '敏'), - (0x2F8C9, 'M', '敬'), - (0x2F8CA, 'M', '𣀊'), - (0x2F8CB, 'M', '旣'), - (0x2F8CC, 'M', '書'), - (0x2F8CD, 'M', '晉'), - (0x2F8CE, 'M', '㬙'), - (0x2F8CF, 'M', '暑'), - (0x2F8D0, 'M', '㬈'), - (0x2F8D1, 'M', '㫤'), - (0x2F8D2, 'M', '冒'), - (0x2F8D3, 'M', '冕'), - (0x2F8D4, 'M', '最'), - (0x2F8D5, 'M', '暜'), - (0x2F8D6, 'M', '肭'), - (0x2F8D7, 'M', '䏙'), - (0x2F8D8, 'M', '朗'), - (0x2F8D9, 'M', '望'), - (0x2F8DA, 'M', '朡'), - (0x2F8DB, 'M', '杞'), - (0x2F8DC, 'M', '杓'), - (0x2F8DD, 'M', '𣏃'), - (0x2F8DE, 'M', '㭉'), - (0x2F8DF, 'M', '柺'), - (0x2F8E0, 'M', '枅'), - (0x2F8E1, 'M', '桒'), - (0x2F8E2, 'M', '梅'), - (0x2F8E3, 'M', '𣑭'), - (0x2F8E4, 'M', '梎'), - (0x2F8E5, 'M', '栟'), - (0x2F8E6, 'M', '椔'), - (0x2F8E7, 'M', '㮝'), - (0x2F8E8, 'M', '楂'), - (0x2F8E9, 'M', '榣'), - (0x2F8EA, 'M', '槪'), - (0x2F8EB, 'M', '檨'), - (0x2F8EC, 'M', '𣚣'), - (0x2F8ED, 'M', '櫛'), - (0x2F8EE, 'M', '㰘'), - (0x2F8EF, 'M', '次'), - (0x2F8F0, 'M', '𣢧'), - (0x2F8F1, 'M', '歔'), - (0x2F8F2, 'M', '㱎'), - (0x2F8F3, 'M', '歲'), - (0x2F8F4, 'M', '殟'), - (0x2F8F5, 'M', '殺'), - (0x2F8F6, 'M', '殻'), - (0x2F8F7, 'M', '𣪍'), - (0x2F8F8, 'M', '𡴋'), - (0x2F8F9, 'M', '𣫺'), - (0x2F8FA, 'M', '汎'), - (0x2F8FB, 'M', '𣲼'), - (0x2F8FC, 'M', '沿'), - (0x2F8FD, 'M', '泍'), - (0x2F8FE, 'M', '汧'), - (0x2F8FF, 'M', '洖'), - (0x2F900, 'M', '派'), - (0x2F901, 'M', '海'), - (0x2F902, 'M', '流'), - (0x2F903, 'M', '浩'), - (0x2F904, 'M', '浸'), - (0x2F905, 'M', '涅'), - (0x2F906, 'M', '𣴞'), - (0x2F907, 'M', '洴'), - (0x2F908, 'M', '港'), - (0x2F909, 'M', '湮'), - (0x2F90A, 'M', '㴳'), + (0x2F8A9, "M", "慌"), + (0x2F8AA, "M", "慺"), + (0x2F8AB, "M", "憎"), + (0x2F8AC, "M", "憲"), + (0x2F8AD, "M", "憤"), + (0x2F8AE, "M", "憯"), + (0x2F8AF, "M", "懞"), + (0x2F8B0, "M", "懲"), + (0x2F8B1, "M", "懶"), + (0x2F8B2, "M", "成"), + (0x2F8B3, "M", "戛"), + (0x2F8B4, "M", "扝"), + (0x2F8B5, "M", "抱"), + (0x2F8B6, "M", "拔"), + (0x2F8B7, "M", "捐"), + (0x2F8B8, "M", "𢬌"), + (0x2F8B9, "M", "挽"), + (0x2F8BA, "M", "拼"), + (0x2F8BB, "M", "捨"), + (0x2F8BC, "M", "掃"), + (0x2F8BD, "M", "揤"), + (0x2F8BE, "M", "𢯱"), + (0x2F8BF, "M", "搢"), + (0x2F8C0, "M", "揅"), + (0x2F8C1, "M", "掩"), + (0x2F8C2, "M", "㨮"), + (0x2F8C3, "M", "摩"), + (0x2F8C4, "M", "摾"), + (0x2F8C5, "M", "撝"), + (0x2F8C6, "M", "摷"), + (0x2F8C7, "M", "㩬"), + (0x2F8C8, "M", "敏"), + (0x2F8C9, "M", "敬"), + (0x2F8CA, "M", "𣀊"), + (0x2F8CB, "M", "旣"), + (0x2F8CC, "M", "書"), + (0x2F8CD, "M", "晉"), + (0x2F8CE, "M", "㬙"), + (0x2F8CF, "M", "暑"), + (0x2F8D0, "M", "㬈"), + (0x2F8D1, "M", "㫤"), + (0x2F8D2, "M", "冒"), + (0x2F8D3, "M", "冕"), + (0x2F8D4, "M", "最"), + (0x2F8D5, "M", "暜"), + (0x2F8D6, "M", "肭"), + (0x2F8D7, "M", "䏙"), + (0x2F8D8, "M", "朗"), + (0x2F8D9, "M", "望"), + (0x2F8DA, "M", "朡"), + (0x2F8DB, "M", "杞"), + (0x2F8DC, "M", "杓"), + (0x2F8DD, "M", "𣏃"), + (0x2F8DE, "M", "㭉"), + (0x2F8DF, "M", "柺"), + (0x2F8E0, "M", "枅"), + (0x2F8E1, "M", "桒"), + (0x2F8E2, "M", "梅"), + (0x2F8E3, "M", "𣑭"), + (0x2F8E4, "M", "梎"), + (0x2F8E5, "M", "栟"), + (0x2F8E6, "M", "椔"), + (0x2F8E7, "M", "㮝"), + (0x2F8E8, "M", "楂"), + (0x2F8E9, "M", "榣"), + (0x2F8EA, "M", "槪"), + (0x2F8EB, "M", "檨"), + (0x2F8EC, "M", "𣚣"), + (0x2F8ED, "M", "櫛"), + (0x2F8EE, "M", "㰘"), + (0x2F8EF, "M", "次"), + (0x2F8F0, "M", "𣢧"), + (0x2F8F1, "M", "歔"), + (0x2F8F2, "M", "㱎"), + (0x2F8F3, "M", "歲"), + (0x2F8F4, "M", "殟"), + (0x2F8F5, "M", "殺"), + (0x2F8F6, "M", "殻"), + (0x2F8F7, "M", "𣪍"), + (0x2F8F8, "M", "𡴋"), + (0x2F8F9, "M", "𣫺"), + (0x2F8FA, "M", "汎"), + (0x2F8FB, "M", "𣲼"), + (0x2F8FC, "M", "沿"), + (0x2F8FD, "M", "泍"), + (0x2F8FE, "M", "汧"), + (0x2F8FF, "M", "洖"), + (0x2F900, "M", "派"), + (0x2F901, "M", "海"), + (0x2F902, "M", "流"), + (0x2F903, "M", "浩"), + (0x2F904, "M", "浸"), + (0x2F905, "M", "涅"), + (0x2F906, "M", "𣴞"), + (0x2F907, "M", "洴"), + (0x2F908, "M", "港"), + (0x2F909, "M", "湮"), + (0x2F90A, "M", "㴳"), + (0x2F90B, "M", "滋"), + (0x2F90C, "M", "滇"), ] + def _seg_79() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2F90B, 'M', '滋'), - (0x2F90C, 'M', '滇'), - (0x2F90D, 'M', '𣻑'), - (0x2F90E, 'M', '淹'), - (0x2F90F, 'M', '潮'), - (0x2F910, 'M', '𣽞'), - (0x2F911, 'M', '𣾎'), - (0x2F912, 'M', '濆'), - (0x2F913, 'M', '瀹'), - (0x2F914, 'M', '瀞'), - (0x2F915, 'M', '瀛'), - (0x2F916, 'M', '㶖'), - (0x2F917, 'M', '灊'), - (0x2F918, 'M', '災'), - (0x2F919, 'M', '灷'), - (0x2F91A, 'M', '炭'), - (0x2F91B, 'M', '𠔥'), - (0x2F91C, 'M', '煅'), - (0x2F91D, 'M', '𤉣'), - (0x2F91E, 'M', '熜'), - (0x2F91F, 'X'), - (0x2F920, 'M', '爨'), - (0x2F921, 'M', '爵'), - (0x2F922, 'M', '牐'), - (0x2F923, 'M', '𤘈'), - (0x2F924, 'M', '犀'), - (0x2F925, 'M', '犕'), - (0x2F926, 'M', '𤜵'), - (0x2F927, 'M', '𤠔'), - (0x2F928, 'M', '獺'), - (0x2F929, 'M', '王'), - (0x2F92A, 'M', '㺬'), - (0x2F92B, 'M', '玥'), - (0x2F92C, 'M', '㺸'), - (0x2F92E, 'M', '瑇'), - (0x2F92F, 'M', '瑜'), - (0x2F930, 'M', '瑱'), - (0x2F931, 'M', '璅'), - (0x2F932, 'M', '瓊'), - (0x2F933, 'M', '㼛'), - (0x2F934, 'M', '甤'), - (0x2F935, 'M', '𤰶'), - (0x2F936, 'M', '甾'), - (0x2F937, 'M', '𤲒'), - (0x2F938, 'M', '異'), - (0x2F939, 'M', '𢆟'), - (0x2F93A, 'M', '瘐'), - (0x2F93B, 'M', '𤾡'), - (0x2F93C, 'M', '𤾸'), - (0x2F93D, 'M', '𥁄'), - (0x2F93E, 'M', '㿼'), - (0x2F93F, 'M', '䀈'), - (0x2F940, 'M', '直'), - (0x2F941, 'M', '𥃳'), - (0x2F942, 'M', '𥃲'), - (0x2F943, 'M', '𥄙'), - (0x2F944, 'M', '𥄳'), - (0x2F945, 'M', '眞'), - (0x2F946, 'M', '真'), - (0x2F948, 'M', '睊'), - (0x2F949, 'M', '䀹'), - (0x2F94A, 'M', '瞋'), - (0x2F94B, 'M', '䁆'), - (0x2F94C, 'M', '䂖'), - (0x2F94D, 'M', '𥐝'), - (0x2F94E, 'M', '硎'), - (0x2F94F, 'M', '碌'), - (0x2F950, 'M', '磌'), - (0x2F951, 'M', '䃣'), - (0x2F952, 'M', '𥘦'), - (0x2F953, 'M', '祖'), - (0x2F954, 'M', '𥚚'), - (0x2F955, 'M', '𥛅'), - (0x2F956, 'M', '福'), - (0x2F957, 'M', '秫'), - (0x2F958, 'M', '䄯'), - (0x2F959, 'M', '穀'), - (0x2F95A, 'M', '穊'), - (0x2F95B, 'M', '穏'), - (0x2F95C, 'M', '𥥼'), - (0x2F95D, 'M', '𥪧'), - (0x2F95F, 'X'), - (0x2F960, 'M', '䈂'), - (0x2F961, 'M', '𥮫'), - (0x2F962, 'M', '篆'), - (0x2F963, 'M', '築'), - (0x2F964, 'M', '䈧'), - (0x2F965, 'M', '𥲀'), - (0x2F966, 'M', '糒'), - (0x2F967, 'M', '䊠'), - (0x2F968, 'M', '糨'), - (0x2F969, 'M', '糣'), - (0x2F96A, 'M', '紀'), - (0x2F96B, 'M', '𥾆'), - (0x2F96C, 'M', '絣'), - (0x2F96D, 'M', '䌁'), - (0x2F96E, 'M', '緇'), - (0x2F96F, 'M', '縂'), - (0x2F970, 'M', '繅'), - (0x2F971, 'M', '䌴'), + (0x2F90D, "M", "𣻑"), + (0x2F90E, "M", "淹"), + (0x2F90F, "M", "潮"), + (0x2F910, "M", "𣽞"), + (0x2F911, "M", "𣾎"), + (0x2F912, "M", "濆"), + (0x2F913, "M", "瀹"), + (0x2F914, "M", "瀞"), + (0x2F915, "M", "瀛"), + (0x2F916, "M", "㶖"), + (0x2F917, "M", "灊"), + (0x2F918, "M", "災"), + (0x2F919, "M", "灷"), + (0x2F91A, "M", "炭"), + (0x2F91B, "M", "𠔥"), + (0x2F91C, "M", "煅"), + (0x2F91D, "M", "𤉣"), + (0x2F91E, "M", "熜"), + (0x2F91F, "X"), + (0x2F920, "M", "爨"), + (0x2F921, "M", "爵"), + (0x2F922, "M", "牐"), + (0x2F923, "M", "𤘈"), + (0x2F924, "M", "犀"), + (0x2F925, "M", "犕"), + (0x2F926, "M", "𤜵"), + (0x2F927, "M", "𤠔"), + (0x2F928, "M", "獺"), + (0x2F929, "M", "王"), + (0x2F92A, "M", "㺬"), + (0x2F92B, "M", "玥"), + (0x2F92C, "M", "㺸"), + (0x2F92E, "M", "瑇"), + (0x2F92F, "M", "瑜"), + (0x2F930, "M", "瑱"), + (0x2F931, "M", "璅"), + (0x2F932, "M", "瓊"), + (0x2F933, "M", "㼛"), + (0x2F934, "M", "甤"), + (0x2F935, "M", "𤰶"), + (0x2F936, "M", "甾"), + (0x2F937, "M", "𤲒"), + (0x2F938, "M", "異"), + (0x2F939, "M", "𢆟"), + (0x2F93A, "M", "瘐"), + (0x2F93B, "M", "𤾡"), + (0x2F93C, "M", "𤾸"), + (0x2F93D, "M", "𥁄"), + (0x2F93E, "M", "㿼"), + (0x2F93F, "M", "䀈"), + (0x2F940, "M", "直"), + (0x2F941, "M", "𥃳"), + (0x2F942, "M", "𥃲"), + (0x2F943, "M", "𥄙"), + (0x2F944, "M", "𥄳"), + (0x2F945, "M", "眞"), + (0x2F946, "M", "真"), + (0x2F948, "M", "睊"), + (0x2F949, "M", "䀹"), + (0x2F94A, "M", "瞋"), + (0x2F94B, "M", "䁆"), + (0x2F94C, "M", "䂖"), + (0x2F94D, "M", "𥐝"), + (0x2F94E, "M", "硎"), + (0x2F94F, "M", "碌"), + (0x2F950, "M", "磌"), + (0x2F951, "M", "䃣"), + (0x2F952, "M", "𥘦"), + (0x2F953, "M", "祖"), + (0x2F954, "M", "𥚚"), + (0x2F955, "M", "𥛅"), + (0x2F956, "M", "福"), + (0x2F957, "M", "秫"), + (0x2F958, "M", "䄯"), + (0x2F959, "M", "穀"), + (0x2F95A, "M", "穊"), + (0x2F95B, "M", "穏"), + (0x2F95C, "M", "𥥼"), + (0x2F95D, "M", "𥪧"), + (0x2F95F, "X"), + (0x2F960, "M", "䈂"), + (0x2F961, "M", "𥮫"), + (0x2F962, "M", "篆"), + (0x2F963, "M", "築"), + (0x2F964, "M", "䈧"), + (0x2F965, "M", "𥲀"), + (0x2F966, "M", "糒"), + (0x2F967, "M", "䊠"), + (0x2F968, "M", "糨"), + (0x2F969, "M", "糣"), + (0x2F96A, "M", "紀"), + (0x2F96B, "M", "𥾆"), + (0x2F96C, "M", "絣"), + (0x2F96D, "M", "䌁"), + (0x2F96E, "M", "緇"), + (0x2F96F, "M", "縂"), + (0x2F970, "M", "繅"), + (0x2F971, "M", "䌴"), + (0x2F972, "M", "𦈨"), + (0x2F973, "M", "𦉇"), ] + def _seg_80() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2F972, 'M', '𦈨'), - (0x2F973, 'M', '𦉇'), - (0x2F974, 'M', '䍙'), - (0x2F975, 'M', '𦋙'), - (0x2F976, 'M', '罺'), - (0x2F977, 'M', '𦌾'), - (0x2F978, 'M', '羕'), - (0x2F979, 'M', '翺'), - (0x2F97A, 'M', '者'), - (0x2F97B, 'M', '𦓚'), - (0x2F97C, 'M', '𦔣'), - (0x2F97D, 'M', '聠'), - (0x2F97E, 'M', '𦖨'), - (0x2F97F, 'M', '聰'), - (0x2F980, 'M', '𣍟'), - (0x2F981, 'M', '䏕'), - (0x2F982, 'M', '育'), - (0x2F983, 'M', '脃'), - (0x2F984, 'M', '䐋'), - (0x2F985, 'M', '脾'), - (0x2F986, 'M', '媵'), - (0x2F987, 'M', '𦞧'), - (0x2F988, 'M', '𦞵'), - (0x2F989, 'M', '𣎓'), - (0x2F98A, 'M', '𣎜'), - (0x2F98B, 'M', '舁'), - (0x2F98C, 'M', '舄'), - (0x2F98D, 'M', '辞'), - (0x2F98E, 'M', '䑫'), - (0x2F98F, 'M', '芑'), - (0x2F990, 'M', '芋'), - (0x2F991, 'M', '芝'), - (0x2F992, 'M', '劳'), - (0x2F993, 'M', '花'), - (0x2F994, 'M', '芳'), - (0x2F995, 'M', '芽'), - (0x2F996, 'M', '苦'), - (0x2F997, 'M', '𦬼'), - (0x2F998, 'M', '若'), - (0x2F999, 'M', '茝'), - (0x2F99A, 'M', '荣'), - (0x2F99B, 'M', '莭'), - (0x2F99C, 'M', '茣'), - (0x2F99D, 'M', '莽'), - (0x2F99E, 'M', '菧'), - (0x2F99F, 'M', '著'), - (0x2F9A0, 'M', '荓'), - (0x2F9A1, 'M', '菊'), - (0x2F9A2, 'M', '菌'), - (0x2F9A3, 'M', '菜'), - (0x2F9A4, 'M', '𦰶'), - (0x2F9A5, 'M', '𦵫'), - (0x2F9A6, 'M', '𦳕'), - (0x2F9A7, 'M', '䔫'), - (0x2F9A8, 'M', '蓱'), - (0x2F9A9, 'M', '蓳'), - (0x2F9AA, 'M', '蔖'), - (0x2F9AB, 'M', '𧏊'), - (0x2F9AC, 'M', '蕤'), - (0x2F9AD, 'M', '𦼬'), - (0x2F9AE, 'M', '䕝'), - (0x2F9AF, 'M', '䕡'), - (0x2F9B0, 'M', '𦾱'), - (0x2F9B1, 'M', '𧃒'), - (0x2F9B2, 'M', '䕫'), - (0x2F9B3, 'M', '虐'), - (0x2F9B4, 'M', '虜'), - (0x2F9B5, 'M', '虧'), - (0x2F9B6, 'M', '虩'), - (0x2F9B7, 'M', '蚩'), - (0x2F9B8, 'M', '蚈'), - (0x2F9B9, 'M', '蜎'), - (0x2F9BA, 'M', '蛢'), - (0x2F9BB, 'M', '蝹'), - (0x2F9BC, 'M', '蜨'), - (0x2F9BD, 'M', '蝫'), - (0x2F9BE, 'M', '螆'), - (0x2F9BF, 'X'), - (0x2F9C0, 'M', '蟡'), - (0x2F9C1, 'M', '蠁'), - (0x2F9C2, 'M', '䗹'), - (0x2F9C3, 'M', '衠'), - (0x2F9C4, 'M', '衣'), - (0x2F9C5, 'M', '𧙧'), - (0x2F9C6, 'M', '裗'), - (0x2F9C7, 'M', '裞'), - (0x2F9C8, 'M', '䘵'), - (0x2F9C9, 'M', '裺'), - (0x2F9CA, 'M', '㒻'), - (0x2F9CB, 'M', '𧢮'), - (0x2F9CC, 'M', '𧥦'), - (0x2F9CD, 'M', '䚾'), - (0x2F9CE, 'M', '䛇'), - (0x2F9CF, 'M', '誠'), - (0x2F9D0, 'M', '諭'), - (0x2F9D1, 'M', '變'), - (0x2F9D2, 'M', '豕'), - (0x2F9D3, 'M', '𧲨'), - (0x2F9D4, 'M', '貫'), - (0x2F9D5, 'M', '賁'), + (0x2F974, "M", "䍙"), + (0x2F975, "M", "𦋙"), + (0x2F976, "M", "罺"), + (0x2F977, "M", "𦌾"), + (0x2F978, "M", "羕"), + (0x2F979, "M", "翺"), + (0x2F97A, "M", "者"), + (0x2F97B, "M", "𦓚"), + (0x2F97C, "M", "𦔣"), + (0x2F97D, "M", "聠"), + (0x2F97E, "M", "𦖨"), + (0x2F97F, "M", "聰"), + (0x2F980, "M", "𣍟"), + (0x2F981, "M", "䏕"), + (0x2F982, "M", "育"), + (0x2F983, "M", "脃"), + (0x2F984, "M", "䐋"), + (0x2F985, "M", "脾"), + (0x2F986, "M", "媵"), + (0x2F987, "M", "𦞧"), + (0x2F988, "M", "𦞵"), + (0x2F989, "M", "𣎓"), + (0x2F98A, "M", "𣎜"), + (0x2F98B, "M", "舁"), + (0x2F98C, "M", "舄"), + (0x2F98D, "M", "辞"), + (0x2F98E, "M", "䑫"), + (0x2F98F, "M", "芑"), + (0x2F990, "M", "芋"), + (0x2F991, "M", "芝"), + (0x2F992, "M", "劳"), + (0x2F993, "M", "花"), + (0x2F994, "M", "芳"), + (0x2F995, "M", "芽"), + (0x2F996, "M", "苦"), + (0x2F997, "M", "𦬼"), + (0x2F998, "M", "若"), + (0x2F999, "M", "茝"), + (0x2F99A, "M", "荣"), + (0x2F99B, "M", "莭"), + (0x2F99C, "M", "茣"), + (0x2F99D, "M", "莽"), + (0x2F99E, "M", "菧"), + (0x2F99F, "M", "著"), + (0x2F9A0, "M", "荓"), + (0x2F9A1, "M", "菊"), + (0x2F9A2, "M", "菌"), + (0x2F9A3, "M", "菜"), + (0x2F9A4, "M", "𦰶"), + (0x2F9A5, "M", "𦵫"), + (0x2F9A6, "M", "𦳕"), + (0x2F9A7, "M", "䔫"), + (0x2F9A8, "M", "蓱"), + (0x2F9A9, "M", "蓳"), + (0x2F9AA, "M", "蔖"), + (0x2F9AB, "M", "𧏊"), + (0x2F9AC, "M", "蕤"), + (0x2F9AD, "M", "𦼬"), + (0x2F9AE, "M", "䕝"), + (0x2F9AF, "M", "䕡"), + (0x2F9B0, "M", "𦾱"), + (0x2F9B1, "M", "𧃒"), + (0x2F9B2, "M", "䕫"), + (0x2F9B3, "M", "虐"), + (0x2F9B4, "M", "虜"), + (0x2F9B5, "M", "虧"), + (0x2F9B6, "M", "虩"), + (0x2F9B7, "M", "蚩"), + (0x2F9B8, "M", "蚈"), + (0x2F9B9, "M", "蜎"), + (0x2F9BA, "M", "蛢"), + (0x2F9BB, "M", "蝹"), + (0x2F9BC, "M", "蜨"), + (0x2F9BD, "M", "蝫"), + (0x2F9BE, "M", "螆"), + (0x2F9BF, "X"), + (0x2F9C0, "M", "蟡"), + (0x2F9C1, "M", "蠁"), + (0x2F9C2, "M", "䗹"), + (0x2F9C3, "M", "衠"), + (0x2F9C4, "M", "衣"), + (0x2F9C5, "M", "𧙧"), + (0x2F9C6, "M", "裗"), + (0x2F9C7, "M", "裞"), + (0x2F9C8, "M", "䘵"), + (0x2F9C9, "M", "裺"), + (0x2F9CA, "M", "㒻"), + (0x2F9CB, "M", "𧢮"), + (0x2F9CC, "M", "𧥦"), + (0x2F9CD, "M", "䚾"), + (0x2F9CE, "M", "䛇"), + (0x2F9CF, "M", "誠"), + (0x2F9D0, "M", "諭"), + (0x2F9D1, "M", "變"), + (0x2F9D2, "M", "豕"), + (0x2F9D3, "M", "𧲨"), + (0x2F9D4, "M", "貫"), + (0x2F9D5, "M", "賁"), + (0x2F9D6, "M", "贛"), + (0x2F9D7, "M", "起"), ] + def _seg_81() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]: return [ - (0x2F9D6, 'M', '贛'), - (0x2F9D7, 'M', '起'), - (0x2F9D8, 'M', '𧼯'), - (0x2F9D9, 'M', '𠠄'), - (0x2F9DA, 'M', '跋'), - (0x2F9DB, 'M', '趼'), - (0x2F9DC, 'M', '跰'), - (0x2F9DD, 'M', '𠣞'), - (0x2F9DE, 'M', '軔'), - (0x2F9DF, 'M', '輸'), - (0x2F9E0, 'M', '𨗒'), - (0x2F9E1, 'M', '𨗭'), - (0x2F9E2, 'M', '邔'), - (0x2F9E3, 'M', '郱'), - (0x2F9E4, 'M', '鄑'), - (0x2F9E5, 'M', '𨜮'), - (0x2F9E6, 'M', '鄛'), - (0x2F9E7, 'M', '鈸'), - (0x2F9E8, 'M', '鋗'), - (0x2F9E9, 'M', '鋘'), - (0x2F9EA, 'M', '鉼'), - (0x2F9EB, 'M', '鏹'), - (0x2F9EC, 'M', '鐕'), - (0x2F9ED, 'M', '𨯺'), - (0x2F9EE, 'M', '開'), - (0x2F9EF, 'M', '䦕'), - (0x2F9F0, 'M', '閷'), - (0x2F9F1, 'M', '𨵷'), - (0x2F9F2, 'M', '䧦'), - (0x2F9F3, 'M', '雃'), - (0x2F9F4, 'M', '嶲'), - (0x2F9F5, 'M', '霣'), - (0x2F9F6, 'M', '𩅅'), - (0x2F9F7, 'M', '𩈚'), - (0x2F9F8, 'M', '䩮'), - (0x2F9F9, 'M', '䩶'), - (0x2F9FA, 'M', '韠'), - (0x2F9FB, 'M', '𩐊'), - (0x2F9FC, 'M', '䪲'), - (0x2F9FD, 'M', '𩒖'), - (0x2F9FE, 'M', '頋'), - (0x2FA00, 'M', '頩'), - (0x2FA01, 'M', '𩖶'), - (0x2FA02, 'M', '飢'), - (0x2FA03, 'M', '䬳'), - (0x2FA04, 'M', '餩'), - (0x2FA05, 'M', '馧'), - (0x2FA06, 'M', '駂'), - (0x2FA07, 'M', '駾'), - (0x2FA08, 'M', '䯎'), - (0x2FA09, 'M', '𩬰'), - (0x2FA0A, 'M', '鬒'), - (0x2FA0B, 'M', '鱀'), - (0x2FA0C, 'M', '鳽'), - (0x2FA0D, 'M', '䳎'), - (0x2FA0E, 'M', '䳭'), - (0x2FA0F, 'M', '鵧'), - (0x2FA10, 'M', '𪃎'), - (0x2FA11, 'M', '䳸'), - (0x2FA12, 'M', '𪄅'), - (0x2FA13, 'M', '𪈎'), - (0x2FA14, 'M', '𪊑'), - (0x2FA15, 'M', '麻'), - (0x2FA16, 'M', '䵖'), - (0x2FA17, 'M', '黹'), - (0x2FA18, 'M', '黾'), - (0x2FA19, 'M', '鼅'), - (0x2FA1A, 'M', '鼏'), - (0x2FA1B, 'M', '鼖'), - (0x2FA1C, 'M', '鼻'), - (0x2FA1D, 'M', '𪘀'), - (0x2FA1E, 'X'), - (0x30000, 'V'), - (0x3134B, 'X'), - (0x31350, 'V'), - (0x323B0, 'X'), - (0xE0100, 'I'), - (0xE01F0, 'X'), + (0x2F9D8, "M", "𧼯"), + (0x2F9D9, "M", "𠠄"), + (0x2F9DA, "M", "跋"), + (0x2F9DB, "M", "趼"), + (0x2F9DC, "M", "跰"), + (0x2F9DD, "M", "𠣞"), + (0x2F9DE, "M", "軔"), + (0x2F9DF, "M", "輸"), + (0x2F9E0, "M", "𨗒"), + (0x2F9E1, "M", "𨗭"), + (0x2F9E2, "M", "邔"), + (0x2F9E3, "M", "郱"), + (0x2F9E4, "M", "鄑"), + (0x2F9E5, "M", "𨜮"), + (0x2F9E6, "M", "鄛"), + (0x2F9E7, "M", "鈸"), + (0x2F9E8, "M", "鋗"), + (0x2F9E9, "M", "鋘"), + (0x2F9EA, "M", "鉼"), + (0x2F9EB, "M", "鏹"), + (0x2F9EC, "M", "鐕"), + (0x2F9ED, "M", "𨯺"), + (0x2F9EE, "M", "開"), + (0x2F9EF, "M", "䦕"), + (0x2F9F0, "M", "閷"), + (0x2F9F1, "M", "𨵷"), + (0x2F9F2, "M", "䧦"), + (0x2F9F3, "M", "雃"), + (0x2F9F4, "M", "嶲"), + (0x2F9F5, "M", "霣"), + (0x2F9F6, "M", "𩅅"), + (0x2F9F7, "M", "𩈚"), + (0x2F9F8, "M", "䩮"), + (0x2F9F9, "M", "䩶"), + (0x2F9FA, "M", "韠"), + (0x2F9FB, "M", "𩐊"), + (0x2F9FC, "M", "䪲"), + (0x2F9FD, "M", "𩒖"), + (0x2F9FE, "M", "頋"), + (0x2FA00, "M", "頩"), + (0x2FA01, "M", "𩖶"), + (0x2FA02, "M", "飢"), + (0x2FA03, "M", "䬳"), + (0x2FA04, "M", "餩"), + (0x2FA05, "M", "馧"), + (0x2FA06, "M", "駂"), + (0x2FA07, "M", "駾"), + (0x2FA08, "M", "䯎"), + (0x2FA09, "M", "𩬰"), + (0x2FA0A, "M", "鬒"), + (0x2FA0B, "M", "鱀"), + (0x2FA0C, "M", "鳽"), + (0x2FA0D, "M", "䳎"), + (0x2FA0E, "M", "䳭"), + (0x2FA0F, "M", "鵧"), + (0x2FA10, "M", "𪃎"), + (0x2FA11, "M", "䳸"), + (0x2FA12, "M", "𪄅"), + (0x2FA13, "M", "𪈎"), + (0x2FA14, "M", "𪊑"), + (0x2FA15, "M", "麻"), + (0x2FA16, "M", "䵖"), + (0x2FA17, "M", "黹"), + (0x2FA18, "M", "黾"), + (0x2FA19, "M", "鼅"), + (0x2FA1A, "M", "鼏"), + (0x2FA1B, "M", "鼖"), + (0x2FA1C, "M", "鼻"), + (0x2FA1D, "M", "𪘀"), + (0x2FA1E, "X"), + (0x30000, "V"), + (0x3134B, "X"), + (0x31350, "V"), + (0x323B0, "X"), + (0xE0100, "I"), + (0xE01F0, "X"), ] + uts46data = tuple( _seg_0() + _seg_1() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__init__.py index 1300b86..b615105 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__init__.py @@ -1,22 +1,20 @@ -# coding: utf-8 -from .exceptions import * +# ruff: noqa: F401 +import os + +from .exceptions import * # noqa: F403 from .ext import ExtType, Timestamp -import os -import sys +version = (1, 1, 0) +__version__ = "1.1.0" -version = (1, 0, 5) -__version__ = "1.0.5" - - -if os.environ.get("MSGPACK_PUREPYTHON") or sys.version_info[0] == 2: - from .fallback import Packer, unpackb, Unpacker +if os.environ.get("MSGPACK_PUREPYTHON"): + from .fallback import Packer, Unpacker, unpackb else: try: - from ._cmsgpack import Packer, unpackb, Unpacker + from ._cmsgpack import Packer, Unpacker, unpackb except ImportError: - from .fallback import Packer, unpackb, Unpacker + from .fallback import Packer, Unpacker, unpackb def pack(o, stream, **kwargs): diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/__init__.cpython-312.pyc index 9011a48..0e6081e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/exceptions.cpython-312.pyc index 560bbb5..69e7251 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/exceptions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/exceptions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/ext.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/ext.cpython-312.pyc index ef75b1f..3916263 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/ext.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/ext.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/fallback.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/fallback.cpython-312.pyc index 27b7b3b..83ce20a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/fallback.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/__pycache__/fallback.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/ext.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/ext.py index 23e0d6b..9694819 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/ext.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/ext.py @@ -1,21 +1,6 @@ -# coding: utf-8 -from collections import namedtuple import datetime -import sys import struct - - -PY2 = sys.version_info[0] == 2 - -if PY2: - int_types = (int, long) - _utc = None -else: - int_types = int - try: - _utc = datetime.timezone.utc - except AttributeError: - _utc = datetime.timezone(datetime.timedelta(0)) +from collections import namedtuple class ExtType(namedtuple("ExtType", "code data")): @@ -28,14 +13,15 @@ class ExtType(namedtuple("ExtType", "code data")): raise TypeError("data must be bytes") if not 0 <= code <= 127: raise ValueError("code must be 0~127") - return super(ExtType, cls).__new__(cls, code, data) + return super().__new__(cls, code, data) -class Timestamp(object): +class Timestamp: """Timestamp represents the Timestamp extension type in msgpack. - When built with Cython, msgpack uses C methods to pack and unpack `Timestamp`. When using pure-Python - msgpack, :func:`to_bytes` and :func:`from_bytes` are used to pack and unpack `Timestamp`. + When built with Cython, msgpack uses C methods to pack and unpack `Timestamp`. + When using pure-Python msgpack, :func:`to_bytes` and :func:`from_bytes` are used to pack and + unpack `Timestamp`. This class is immutable: Do not override seconds and nanoseconds. """ @@ -53,31 +39,25 @@ class Timestamp(object): Number of nanoseconds to add to `seconds` to get fractional time. Maximum is 999_999_999. Default is 0. - Note: Negative times (before the UNIX epoch) are represented as negative seconds + positive ns. + Note: Negative times (before the UNIX epoch) are represented as neg. seconds + pos. ns. """ - if not isinstance(seconds, int_types): + if not isinstance(seconds, int): raise TypeError("seconds must be an integer") - if not isinstance(nanoseconds, int_types): + if not isinstance(nanoseconds, int): raise TypeError("nanoseconds must be an integer") if not (0 <= nanoseconds < 10**9): - raise ValueError( - "nanoseconds must be a non-negative integer less than 999999999." - ) + raise ValueError("nanoseconds must be a non-negative integer less than 999999999.") self.seconds = seconds self.nanoseconds = nanoseconds def __repr__(self): """String representation of Timestamp.""" - return "Timestamp(seconds={0}, nanoseconds={1})".format( - self.seconds, self.nanoseconds - ) + return f"Timestamp(seconds={self.seconds}, nanoseconds={self.nanoseconds})" def __eq__(self, other): """Check for equality with another Timestamp object""" if type(other) is self.__class__: - return ( - self.seconds == other.seconds and self.nanoseconds == other.nanoseconds - ) + return self.seconds == other.seconds and self.nanoseconds == other.nanoseconds return False def __ne__(self, other): @@ -140,7 +120,7 @@ class Timestamp(object): """Create a Timestamp from posix timestamp in seconds. :param unix_float: Posix timestamp in seconds. - :type unix_float: int or float. + :type unix_float: int or float """ seconds = int(unix_sec // 1) nanoseconds = int((unix_sec % 1) * 10**9) @@ -174,20 +154,17 @@ class Timestamp(object): def to_datetime(self): """Get the timestamp as a UTC datetime. - Python 2 is not supported. - - :rtype: datetime. + :rtype: `datetime.datetime` """ - return datetime.datetime.fromtimestamp(0, _utc) + datetime.timedelta( - seconds=self.to_unix() + utc = datetime.timezone.utc + return datetime.datetime.fromtimestamp(0, utc) + datetime.timedelta( + seconds=self.seconds, microseconds=self.nanoseconds // 1000 ) @staticmethod def from_datetime(dt): """Create a Timestamp from datetime with tzinfo. - Python 2 is not supported. - :rtype: Timestamp """ - return Timestamp.from_unix(dt.timestamp()) + return Timestamp(seconds=int(dt.timestamp()), nanoseconds=dt.microsecond * 1000) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/fallback.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/fallback.py index e8cebc1..b02e47c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/fallback.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/msgpack/fallback.py @@ -1,60 +1,22 @@ """Fallback pure Python implementation of msgpack""" -from datetime import datetime as _DateTime -import sys + import struct - - -PY2 = sys.version_info[0] == 2 -if PY2: - int_types = (int, long) - - def dict_iteritems(d): - return d.iteritems() - -else: - int_types = int - unicode = str - xrange = range - - def dict_iteritems(d): - return d.items() - - -if sys.version_info < (3, 5): - # Ugly hack... - RecursionError = RuntimeError - - def _is_recursionerror(e): - return ( - len(e.args) == 1 - and isinstance(e.args[0], str) - and e.args[0].startswith("maximum recursion depth exceeded") - ) - -else: - - def _is_recursionerror(e): - return True - +import sys +from datetime import datetime as _DateTime if hasattr(sys, "pypy_version_info"): - # StringIO is slow on PyPy, StringIO is faster. However: PyPy's own - # StringBuilder is fastest. from __pypy__ import newlist_hint + from __pypy__.builders import BytesBuilder - try: - from __pypy__.builders import BytesBuilder as StringBuilder - except ImportError: - from __pypy__.builders import StringBuilder - USING_STRINGBUILDER = True + _USING_STRINGBUILDER = True - class StringIO(object): + class BytesIO: def __init__(self, s=b""): if s: - self.builder = StringBuilder(len(s)) + self.builder = BytesBuilder(len(s)) self.builder.append(s) else: - self.builder = StringBuilder() + self.builder = BytesBuilder() def write(self, s): if isinstance(s, memoryview): @@ -67,17 +29,17 @@ if hasattr(sys, "pypy_version_info"): return self.builder.build() else: - USING_STRINGBUILDER = False - from io import BytesIO as StringIO + from io import BytesIO - newlist_hint = lambda size: [] + _USING_STRINGBUILDER = False + + def newlist_hint(size): + return [] -from .exceptions import BufferFull, OutOfData, ExtraData, FormatError, StackError - +from .exceptions import BufferFull, ExtraData, FormatError, OutOfData, StackError from .ext import ExtType, Timestamp - EX_SKIP = 0 EX_CONSTRUCT = 1 EX_READ_ARRAY_HEADER = 2 @@ -125,24 +87,13 @@ def unpackb(packed, **kwargs): ret = unpacker._unpack() except OutOfData: raise ValueError("Unpack failed: incomplete input") - except RecursionError as e: - if _is_recursionerror(e): - raise StackError - raise + except RecursionError: + raise StackError if unpacker._got_extradata(): raise ExtraData(ret, unpacker._get_extradata()) return ret -if sys.version_info < (2, 7, 6): - - def _unpack_from(f, b, o=0): - """Explicit type cast for legacy struct.unpack_from""" - return struct.unpack_from(f, bytes(b), o) - -else: - _unpack_from = struct.unpack_from - _NO_FORMAT_USED = "" _MSGPACK_HEADERS = { 0xC4: (1, _NO_FORMAT_USED, TYPE_BIN), @@ -176,14 +127,14 @@ _MSGPACK_HEADERS = { } -class Unpacker(object): +class Unpacker: """Streaming unpacker. Arguments: :param file_like: File-like object having `.read(n)` method. - If specified, unpacker reads serialized data from it and :meth:`feed()` is not usable. + If specified, unpacker reads serialized data from it and `.feed()` is not usable. :param int read_size: Used as `file_like.read(read_size)`. (default: `min(16*1024, max_buffer_size)`) @@ -202,17 +153,17 @@ class Unpacker(object): 0 - Timestamp 1 - float (Seconds from the EPOCH) 2 - int (Nanoseconds from the EPOCH) - 3 - datetime.datetime (UTC). Python 2 is not supported. + 3 - datetime.datetime (UTC). :param bool strict_map_key: If true (default), only str or bytes are accepted for map (dict) keys. - :param callable object_hook: + :param object_hook: When specified, it should be callable. Unpacker calls it with a dict argument after unpacking msgpack map. (See also simplejson) - :param callable object_pairs_hook: + :param object_pairs_hook: When specified, it should be callable. Unpacker calls it with a list of key-value pairs after unpacking msgpack map. (See also simplejson) @@ -275,6 +226,7 @@ class Unpacker(object): def __init__( self, file_like=None, + *, read_size=0, use_list=True, raw=False, @@ -359,9 +311,7 @@ class Unpacker(object): if object_pairs_hook is not None and not callable(object_pairs_hook): raise TypeError("`object_pairs_hook` is not callable") if object_hook is not None and object_pairs_hook is not None: - raise TypeError( - "object_pairs_hook and object_hook are mutually " "exclusive" - ) + raise TypeError("object_pairs_hook and object_hook are mutually exclusive") if not callable(ext_hook): raise TypeError("`ext_hook` is not callable") @@ -379,6 +329,7 @@ class Unpacker(object): # Use extend here: INPLACE_ADD += doesn't reliably typecast memoryview in jython self._buffer.extend(view) + view.release() def _consume(self): """Gets rid of the used parts of the buffer.""" @@ -453,20 +404,18 @@ class Unpacker(object): n = b & 0b00011111 typ = TYPE_RAW if n > self._max_str_len: - raise ValueError("%s exceeds max_str_len(%s)" % (n, self._max_str_len)) + raise ValueError(f"{n} exceeds max_str_len({self._max_str_len})") obj = self._read(n) elif b & 0b11110000 == 0b10010000: n = b & 0b00001111 typ = TYPE_ARRAY if n > self._max_array_len: - raise ValueError( - "%s exceeds max_array_len(%s)" % (n, self._max_array_len) - ) + raise ValueError(f"{n} exceeds max_array_len({self._max_array_len})") elif b & 0b11110000 == 0b10000000: n = b & 0b00001111 typ = TYPE_MAP if n > self._max_map_len: - raise ValueError("%s exceeds max_map_len(%s)" % (n, self._max_map_len)) + raise ValueError(f"{n} exceeds max_map_len({self._max_map_len})") elif b == 0xC0: obj = None elif b == 0xC2: @@ -477,65 +426,61 @@ class Unpacker(object): size, fmt, typ = _MSGPACK_HEADERS[b] self._reserve(size) if len(fmt) > 0: - n = _unpack_from(fmt, self._buffer, self._buff_i)[0] + n = struct.unpack_from(fmt, self._buffer, self._buff_i)[0] else: n = self._buffer[self._buff_i] self._buff_i += size if n > self._max_bin_len: - raise ValueError("%s exceeds max_bin_len(%s)" % (n, self._max_bin_len)) + raise ValueError(f"{n} exceeds max_bin_len({self._max_bin_len})") obj = self._read(n) elif 0xC7 <= b <= 0xC9: size, fmt, typ = _MSGPACK_HEADERS[b] self._reserve(size) - L, n = _unpack_from(fmt, self._buffer, self._buff_i) + L, n = struct.unpack_from(fmt, self._buffer, self._buff_i) self._buff_i += size if L > self._max_ext_len: - raise ValueError("%s exceeds max_ext_len(%s)" % (L, self._max_ext_len)) + raise ValueError(f"{L} exceeds max_ext_len({self._max_ext_len})") obj = self._read(L) elif 0xCA <= b <= 0xD3: size, fmt = _MSGPACK_HEADERS[b] self._reserve(size) if len(fmt) > 0: - obj = _unpack_from(fmt, self._buffer, self._buff_i)[0] + obj = struct.unpack_from(fmt, self._buffer, self._buff_i)[0] else: obj = self._buffer[self._buff_i] self._buff_i += size elif 0xD4 <= b <= 0xD8: size, fmt, typ = _MSGPACK_HEADERS[b] if self._max_ext_len < size: - raise ValueError( - "%s exceeds max_ext_len(%s)" % (size, self._max_ext_len) - ) + raise ValueError(f"{size} exceeds max_ext_len({self._max_ext_len})") self._reserve(size + 1) - n, obj = _unpack_from(fmt, self._buffer, self._buff_i) + n, obj = struct.unpack_from(fmt, self._buffer, self._buff_i) self._buff_i += size + 1 elif 0xD9 <= b <= 0xDB: size, fmt, typ = _MSGPACK_HEADERS[b] self._reserve(size) if len(fmt) > 0: - (n,) = _unpack_from(fmt, self._buffer, self._buff_i) + (n,) = struct.unpack_from(fmt, self._buffer, self._buff_i) else: n = self._buffer[self._buff_i] self._buff_i += size if n > self._max_str_len: - raise ValueError("%s exceeds max_str_len(%s)" % (n, self._max_str_len)) + raise ValueError(f"{n} exceeds max_str_len({self._max_str_len})") obj = self._read(n) elif 0xDC <= b <= 0xDD: size, fmt, typ = _MSGPACK_HEADERS[b] self._reserve(size) - (n,) = _unpack_from(fmt, self._buffer, self._buff_i) + (n,) = struct.unpack_from(fmt, self._buffer, self._buff_i) self._buff_i += size if n > self._max_array_len: - raise ValueError( - "%s exceeds max_array_len(%s)" % (n, self._max_array_len) - ) + raise ValueError(f"{n} exceeds max_array_len({self._max_array_len})") elif 0xDE <= b <= 0xDF: size, fmt, typ = _MSGPACK_HEADERS[b] self._reserve(size) - (n,) = _unpack_from(fmt, self._buffer, self._buff_i) + (n,) = struct.unpack_from(fmt, self._buffer, self._buff_i) self._buff_i += size if n > self._max_map_len: - raise ValueError("%s exceeds max_map_len(%s)" % (n, self._max_map_len)) + raise ValueError(f"{n} exceeds max_map_len({self._max_map_len})") else: raise FormatError("Unknown header: 0x%x" % b) return typ, n, obj @@ -554,12 +499,12 @@ class Unpacker(object): # TODO should we eliminate the recursion? if typ == TYPE_ARRAY: if execute == EX_SKIP: - for i in xrange(n): + for i in range(n): # TODO check whether we need to call `list_hook` self._unpack(EX_SKIP) return ret = newlist_hint(n) - for i in xrange(n): + for i in range(n): ret.append(self._unpack(EX_CONSTRUCT)) if self._list_hook is not None: ret = self._list_hook(ret) @@ -567,25 +512,22 @@ class Unpacker(object): return ret if self._use_list else tuple(ret) if typ == TYPE_MAP: if execute == EX_SKIP: - for i in xrange(n): + for i in range(n): # TODO check whether we need to call hooks self._unpack(EX_SKIP) self._unpack(EX_SKIP) return if self._object_pairs_hook is not None: ret = self._object_pairs_hook( - (self._unpack(EX_CONSTRUCT), self._unpack(EX_CONSTRUCT)) - for _ in xrange(n) + (self._unpack(EX_CONSTRUCT), self._unpack(EX_CONSTRUCT)) for _ in range(n) ) else: ret = {} - for _ in xrange(n): + for _ in range(n): key = self._unpack(EX_CONSTRUCT) - if self._strict_map_key and type(key) not in (unicode, bytes): - raise ValueError( - "%s is not allowed for map key" % str(type(key)) - ) - if not PY2 and type(key) is str: + if self._strict_map_key and type(key) not in (str, bytes): + raise ValueError("%s is not allowed for map key" % str(type(key))) + if isinstance(key, str): key = sys.intern(key) ret[key] = self._unpack(EX_CONSTRUCT) if self._object_hook is not None: @@ -659,7 +601,7 @@ class Unpacker(object): return self._stream_offset -class Packer(object): +class Packer: """ MessagePack Packer @@ -671,7 +613,8 @@ class Packer(object): Packer's constructor has some keyword arguments: - :param callable default: + :param default: + When specified, it should be callable. Convert user type to builtin type that Packer supports. See also simplejson's document. @@ -698,38 +641,18 @@ class Packer(object): If set to true, datetime with tzinfo is packed into Timestamp type. Note that the tzinfo is stripped in the timestamp. You can get UTC datetime with `timestamp=3` option of the Unpacker. - (Python 2 is not supported). :param str unicode_errors: The error handler for encoding unicode. (default: 'strict') DO NOT USE THIS!! This option is kept for very specific usage. - Example of streaming deserialize from file-like object:: - - unpacker = Unpacker(file_like) - for o in unpacker: - process(o) - - Example of streaming deserialize from socket:: - - unpacker = Unpacker() - while True: - buf = sock.recv(1024**2) - if not buf: - break - unpacker.feed(buf) - for o in unpacker: - process(o) - - Raises ``ExtraData`` when *packed* contains extra bytes. - Raises ``OutOfData`` when *packed* is incomplete. - Raises ``FormatError`` when *packed* is not valid msgpack. - Raises ``StackError`` when *packed* contains too nested. - Other exceptions can be raised during unpacking. + :param int buf_size: + Internal buffer size. This option is used only for C implementation. """ def __init__( self, + *, default=None, use_single_float=False, autoreset=True, @@ -737,19 +660,17 @@ class Packer(object): strict_types=False, datetime=False, unicode_errors=None, + buf_size=None, ): self._strict_types = strict_types self._use_float = use_single_float self._autoreset = autoreset self._use_bin_type = use_bin_type - self._buffer = StringIO() - if PY2 and datetime: - raise ValueError("datetime is not supported in Python 2") + self._buffer = BytesIO() self._datetime = bool(datetime) self._unicode_errors = unicode_errors or "strict" - if default is not None: - if not callable(default): - raise TypeError("default must be callable") + if default is not None and not callable(default): + raise TypeError("default must be callable") self._default = default def _pack( @@ -774,7 +695,7 @@ class Packer(object): if obj: return self._buffer.write(b"\xc3") return self._buffer.write(b"\xc2") - if check(obj, int_types): + if check(obj, int): if 0 <= obj < 0x80: return self._buffer.write(struct.pack("B", obj)) if -0x20 <= obj < 0: @@ -806,7 +727,7 @@ class Packer(object): raise ValueError("%s is too large" % type(obj).__name__) self._pack_bin_header(n) return self._buffer.write(obj) - if check(obj, unicode): + if check(obj, str): obj = obj.encode("utf-8", self._unicode_errors) n = len(obj) if n >= 2**32: @@ -855,13 +776,11 @@ class Packer(object): if check(obj, list_types): n = len(obj) self._pack_array_header(n) - for i in xrange(n): + for i in range(n): self._pack(obj[i], nest_limit - 1) return if check(obj, dict): - return self._pack_map_pairs( - len(obj), dict_iteritems(obj), nest_limit - 1 - ) + return self._pack_map_pairs(len(obj), obj.items(), nest_limit - 1) if self._datetime and check(obj, _DateTime) and obj.tzinfo is not None: obj = Timestamp.from_datetime(obj) @@ -874,26 +793,26 @@ class Packer(object): continue if self._datetime and check(obj, _DateTime): - raise ValueError("Cannot serialize %r where tzinfo=None" % (obj,)) + raise ValueError(f"Cannot serialize {obj!r} where tzinfo=None") - raise TypeError("Cannot serialize %r" % (obj,)) + raise TypeError(f"Cannot serialize {obj!r}") def pack(self, obj): try: self._pack(obj) except: - self._buffer = StringIO() # force reset + self._buffer = BytesIO() # force reset raise if self._autoreset: ret = self._buffer.getvalue() - self._buffer = StringIO() + self._buffer = BytesIO() return ret def pack_map_pairs(self, pairs): self._pack_map_pairs(len(pairs), pairs) if self._autoreset: ret = self._buffer.getvalue() - self._buffer = StringIO() + self._buffer = BytesIO() return ret def pack_array_header(self, n): @@ -902,7 +821,7 @@ class Packer(object): self._pack_array_header(n) if self._autoreset: ret = self._buffer.getvalue() - self._buffer = StringIO() + self._buffer = BytesIO() return ret def pack_map_header(self, n): @@ -911,7 +830,7 @@ class Packer(object): self._pack_map_header(n) if self._autoreset: ret = self._buffer.getvalue() - self._buffer = StringIO() + self._buffer = BytesIO() return ret def pack_ext_type(self, typecode, data): @@ -963,7 +882,7 @@ class Packer(object): def _pack_map_pairs(self, n, pairs, nest_limit=DEFAULT_RECURSE_LIMIT): self._pack_map_header(n) - for (k, v) in pairs: + for k, v in pairs: self._pack(k, nest_limit - 1) self._pack(v, nest_limit - 1) @@ -1000,11 +919,11 @@ class Packer(object): This method is useful only when autoreset=False. """ - self._buffer = StringIO() + self._buffer = BytesIO() def getbuffer(self): """Return view of internal buffer.""" - if USING_STRINGBUILDER or PY2: + if _USING_STRINGBUILDER: return memoryview(self.bytes()) else: return self._buffer.getbuffer() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__about__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__about__.py deleted file mode 100644 index 3551bc2..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__about__.py +++ /dev/null @@ -1,26 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. - -__all__ = [ - "__title__", - "__summary__", - "__uri__", - "__version__", - "__author__", - "__email__", - "__license__", - "__copyright__", -] - -__title__ = "packaging" -__summary__ = "Core utilities for Python packages" -__uri__ = "https://github.com/pypa/packaging" - -__version__ = "21.3" - -__author__ = "Donald Stufft and individual contributors" -__email__ = "donald@stufft.io" - -__license__ = "BSD-2-Clause or Apache-2.0" -__copyright__ = "2014-2019 %s" % __author__ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__init__.py index 3c50c5d..d79f73c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__init__.py @@ -2,24 +2,14 @@ # 2.0, and the BSD License. See the LICENSE file in the root of this repository # for complete details. -from .__about__ import ( - __author__, - __copyright__, - __email__, - __license__, - __summary__, - __title__, - __uri__, - __version__, -) +__title__ = "packaging" +__summary__ = "Core utilities for Python packages" +__uri__ = "https://github.com/pypa/packaging" -__all__ = [ - "__title__", - "__summary__", - "__uri__", - "__version__", - "__author__", - "__email__", - "__license__", - "__copyright__", -] +__version__ = "24.2" + +__author__ = "Donald Stufft and individual contributors" +__email__ = "donald@stufft.io" + +__license__ = "BSD-2-Clause or Apache-2.0" +__copyright__ = f"2014 {__author__}" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/__about__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/__about__.cpython-312.pyc deleted file mode 100644 index 82a6ade..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/__about__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/__init__.cpython-312.pyc index 2f0561b..44e055f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc similarity index 93% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc index 09b1c73..56bbe5f 100644 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc index 6fb6cc0..f5476d3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc index 36234d1..0c0f502 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_parser.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_parser.cpython-312.pyc similarity index 98% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_parser.cpython-312.pyc rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_parser.cpython-312.pyc index ac6d802..97074ac 100644 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_parser.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_parser.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_structures.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_structures.cpython-312.pyc index bfef476..ff0ff0c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_structures.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_structures.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc similarity index 97% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc index a697062..38aad07 100644 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/markers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/markers.cpython-312.pyc index 37429a8..4163b13 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/markers.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/markers.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/metadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/metadata.cpython-312.pyc similarity index 97% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/metadata.cpython-312.pyc rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/metadata.cpython-312.pyc index 4f3437d..431feb5 100644 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/metadata.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/metadata.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/requirements.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/requirements.cpython-312.pyc index d25477b..c91c3c1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/requirements.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/requirements.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc index 48a5145..8a81d99 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/tags.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/tags.cpython-312.pyc index d9a127a..9614da3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/tags.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/tags.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/utils.cpython-312.pyc index 8a18258..006a7e7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/utils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/utils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/version.cpython-312.pyc index b40e3d6..9fac172 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/version.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/__pycache__/version.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_elffile.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_elffile.py similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_elffile.py rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_elffile.py diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_manylinux.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_manylinux.py index 4c379aa..61339a6 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_manylinux.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_manylinux.py @@ -1,122 +1,72 @@ +from __future__ import annotations + import collections +import contextlib import functools import os import re -import struct import sys import warnings -from typing import IO, Dict, Iterator, NamedTuple, Optional, Tuple +from typing import Generator, Iterator, NamedTuple, Sequence + +from ._elffile import EIClass, EIData, ELFFile, EMachine + +EF_ARM_ABIMASK = 0xFF000000 +EF_ARM_ABI_VER5 = 0x05000000 +EF_ARM_ABI_FLOAT_HARD = 0x00000400 -# Python does not provide platform information at sufficient granularity to -# identify the architecture of the running executable in some cases, so we -# determine it dynamically by reading the information from the running -# process. This only applies on Linux, which uses the ELF format. -class _ELFFileHeader: - # https://en.wikipedia.org/wiki/Executable_and_Linkable_Format#File_header - class _InvalidELFFileHeader(ValueError): - """ - An invalid ELF file header was found. - """ - - ELF_MAGIC_NUMBER = 0x7F454C46 - ELFCLASS32 = 1 - ELFCLASS64 = 2 - ELFDATA2LSB = 1 - ELFDATA2MSB = 2 - EM_386 = 3 - EM_S390 = 22 - EM_ARM = 40 - EM_X86_64 = 62 - EF_ARM_ABIMASK = 0xFF000000 - EF_ARM_ABI_VER5 = 0x05000000 - EF_ARM_ABI_FLOAT_HARD = 0x00000400 - - def __init__(self, file: IO[bytes]) -> None: - def unpack(fmt: str) -> int: - try: - data = file.read(struct.calcsize(fmt)) - result: Tuple[int, ...] = struct.unpack(fmt, data) - except struct.error: - raise _ELFFileHeader._InvalidELFFileHeader() - return result[0] - - self.e_ident_magic = unpack(">I") - if self.e_ident_magic != self.ELF_MAGIC_NUMBER: - raise _ELFFileHeader._InvalidELFFileHeader() - self.e_ident_class = unpack("B") - if self.e_ident_class not in {self.ELFCLASS32, self.ELFCLASS64}: - raise _ELFFileHeader._InvalidELFFileHeader() - self.e_ident_data = unpack("B") - if self.e_ident_data not in {self.ELFDATA2LSB, self.ELFDATA2MSB}: - raise _ELFFileHeader._InvalidELFFileHeader() - self.e_ident_version = unpack("B") - self.e_ident_osabi = unpack("B") - self.e_ident_abiversion = unpack("B") - self.e_ident_pad = file.read(7) - format_h = "H" - format_i = "I" - format_q = "Q" - format_p = format_i if self.e_ident_class == self.ELFCLASS32 else format_q - self.e_type = unpack(format_h) - self.e_machine = unpack(format_h) - self.e_version = unpack(format_i) - self.e_entry = unpack(format_p) - self.e_phoff = unpack(format_p) - self.e_shoff = unpack(format_p) - self.e_flags = unpack(format_i) - self.e_ehsize = unpack(format_h) - self.e_phentsize = unpack(format_h) - self.e_phnum = unpack(format_h) - self.e_shentsize = unpack(format_h) - self.e_shnum = unpack(format_h) - self.e_shstrndx = unpack(format_h) - - -def _get_elf_header() -> Optional[_ELFFileHeader]: +# `os.PathLike` not a generic type until Python 3.9, so sticking with `str` +# as the type for `path` until then. +@contextlib.contextmanager +def _parse_elf(path: str) -> Generator[ELFFile | None, None, None]: try: - with open(sys.executable, "rb") as f: - elf_header = _ELFFileHeader(f) - except (OSError, TypeError, _ELFFileHeader._InvalidELFFileHeader): - return None - return elf_header + with open(path, "rb") as f: + yield ELFFile(f) + except (OSError, TypeError, ValueError): + yield None -def _is_linux_armhf() -> bool: +def _is_linux_armhf(executable: str) -> bool: # hard-float ABI can be detected from the ELF header of the running # process # https://static.docs.arm.com/ihi0044/g/aaelf32.pdf - elf_header = _get_elf_header() - if elf_header is None: - return False - result = elf_header.e_ident_class == elf_header.ELFCLASS32 - result &= elf_header.e_ident_data == elf_header.ELFDATA2LSB - result &= elf_header.e_machine == elf_header.EM_ARM - result &= ( - elf_header.e_flags & elf_header.EF_ARM_ABIMASK - ) == elf_header.EF_ARM_ABI_VER5 - result &= ( - elf_header.e_flags & elf_header.EF_ARM_ABI_FLOAT_HARD - ) == elf_header.EF_ARM_ABI_FLOAT_HARD - return result + with _parse_elf(executable) as f: + return ( + f is not None + and f.capacity == EIClass.C32 + and f.encoding == EIData.Lsb + and f.machine == EMachine.Arm + and f.flags & EF_ARM_ABIMASK == EF_ARM_ABI_VER5 + and f.flags & EF_ARM_ABI_FLOAT_HARD == EF_ARM_ABI_FLOAT_HARD + ) -def _is_linux_i686() -> bool: - elf_header = _get_elf_header() - if elf_header is None: - return False - result = elf_header.e_ident_class == elf_header.ELFCLASS32 - result &= elf_header.e_ident_data == elf_header.ELFDATA2LSB - result &= elf_header.e_machine == elf_header.EM_386 - return result +def _is_linux_i686(executable: str) -> bool: + with _parse_elf(executable) as f: + return ( + f is not None + and f.capacity == EIClass.C32 + and f.encoding == EIData.Lsb + and f.machine == EMachine.I386 + ) -def _have_compatible_abi(arch: str) -> bool: - if arch == "armv7l": - return _is_linux_armhf() - if arch == "i686": - return _is_linux_i686() - return arch in {"x86_64", "aarch64", "ppc64", "ppc64le", "s390x"} +def _have_compatible_abi(executable: str, archs: Sequence[str]) -> bool: + if "armv7l" in archs: + return _is_linux_armhf(executable) + if "i686" in archs: + return _is_linux_i686(executable) + allowed_archs = { + "x86_64", + "aarch64", + "ppc64", + "ppc64le", + "s390x", + "loongarch64", + "riscv64", + } + return any(arch in allowed_archs for arch in archs) # If glibc ever changes its major version, we need to know what the last @@ -124,7 +74,7 @@ def _have_compatible_abi(arch: str) -> bool: # For now, guess what the highest minor version might be, assume it will # be 50 for testing. Once this actually happens, update the dictionary # with the actual value. -_LAST_GLIBC_MINOR: Dict[int, int] = collections.defaultdict(lambda: 50) +_LAST_GLIBC_MINOR: dict[int, int] = collections.defaultdict(lambda: 50) class _GLibCVersion(NamedTuple): @@ -132,7 +82,7 @@ class _GLibCVersion(NamedTuple): minor: int -def _glibc_version_string_confstr() -> Optional[str]: +def _glibc_version_string_confstr() -> str | None: """ Primary implementation of glibc_version_string using os.confstr. """ @@ -141,17 +91,17 @@ def _glibc_version_string_confstr() -> Optional[str]: # platform module. # https://github.com/python/cpython/blob/fcf1d003bf4f0100c/Lib/platform.py#L175-L183 try: - # os.confstr("CS_GNU_LIBC_VERSION") returns a string like "glibc 2.17". - version_string = os.confstr("CS_GNU_LIBC_VERSION") + # Should be a string like "glibc 2.17". + version_string: str | None = os.confstr("CS_GNU_LIBC_VERSION") assert version_string is not None - _, version = version_string.split() + _, version = version_string.rsplit() except (AssertionError, AttributeError, OSError, ValueError): # os.confstr() or CS_GNU_LIBC_VERSION not available (or a bad value)... return None return version -def _glibc_version_string_ctypes() -> Optional[str]: +def _glibc_version_string_ctypes() -> str | None: """ Fallback implementation of glibc_version_string using ctypes. """ @@ -195,12 +145,12 @@ def _glibc_version_string_ctypes() -> Optional[str]: return version_str -def _glibc_version_string() -> Optional[str]: +def _glibc_version_string() -> str | None: """Returns glibc version string, or None if not using glibc.""" return _glibc_version_string_confstr() or _glibc_version_string_ctypes() -def _parse_glibc_version(version_str: str) -> Tuple[int, int]: +def _parse_glibc_version(version_str: str) -> tuple[int, int]: """Parse glibc version. We use a regexp instead of str.split because we want to discard any @@ -211,16 +161,17 @@ def _parse_glibc_version(version_str: str) -> Tuple[int, int]: m = re.match(r"(?P[0-9]+)\.(?P[0-9]+)", version_str) if not m: warnings.warn( - "Expected glibc version with 2 components major.minor," - " got: %s" % version_str, + f"Expected glibc version with 2 components major.minor," + f" got: {version_str}", RuntimeWarning, + stacklevel=2, ) return -1, -1 return int(m.group("major")), int(m.group("minor")) -@functools.lru_cache() -def _get_glibc_version() -> Tuple[int, int]: +@functools.lru_cache +def _get_glibc_version() -> tuple[int, int]: version_str = _glibc_version_string() if version_str is None: return (-1, -1) @@ -228,13 +179,13 @@ def _get_glibc_version() -> Tuple[int, int]: # From PEP 513, PEP 600 -def _is_compatible(name: str, arch: str, version: _GLibCVersion) -> bool: +def _is_compatible(arch: str, version: _GLibCVersion) -> bool: sys_glibc = _get_glibc_version() if sys_glibc < version: return False # Check for presence of _manylinux module. try: - import _manylinux # noqa + import _manylinux except ImportError: return True if hasattr(_manylinux, "manylinux_compatible"): @@ -264,12 +215,22 @@ _LEGACY_MANYLINUX_MAP = { } -def platform_tags(linux: str, arch: str) -> Iterator[str]: - if not _have_compatible_abi(arch): +def platform_tags(archs: Sequence[str]) -> Iterator[str]: + """Generate manylinux tags compatible to the current platform. + + :param archs: Sequence of compatible architectures. + The first one shall be the closest to the actual architecture and be the part of + platform tag after the ``linux_`` prefix, e.g. ``x86_64``. + The ``linux_`` prefix is assumed as a prerequisite for the current platform to + be manylinux-compatible. + + :returns: An iterator of compatible manylinux tags. + """ + if not _have_compatible_abi(sys.executable, archs): return # Oldest glibc to be supported regardless of architecture is (2, 17). too_old_glibc2 = _GLibCVersion(2, 16) - if arch in {"x86_64", "i686"}: + if set(archs) & {"x86_64", "i686"}: # On x86/i686 also oldest glibc to be supported is (2, 5). too_old_glibc2 = _GLibCVersion(2, 4) current_glibc = _GLibCVersion(*_get_glibc_version()) @@ -283,19 +244,20 @@ def platform_tags(linux: str, arch: str) -> Iterator[str]: for glibc_major in range(current_glibc.major - 1, 1, -1): glibc_minor = _LAST_GLIBC_MINOR[glibc_major] glibc_max_list.append(_GLibCVersion(glibc_major, glibc_minor)) - for glibc_max in glibc_max_list: - if glibc_max.major == too_old_glibc2.major: - min_minor = too_old_glibc2.minor - else: - # For other glibc major versions oldest supported is (x, 0). - min_minor = -1 - for glibc_minor in range(glibc_max.minor, min_minor, -1): - glibc_version = _GLibCVersion(glibc_max.major, glibc_minor) - tag = "manylinux_{}_{}".format(*glibc_version) - if _is_compatible(tag, arch, glibc_version): - yield linux.replace("linux", tag) - # Handle the legacy manylinux1, manylinux2010, manylinux2014 tags. - if glibc_version in _LEGACY_MANYLINUX_MAP: - legacy_tag = _LEGACY_MANYLINUX_MAP[glibc_version] - if _is_compatible(legacy_tag, arch, glibc_version): - yield linux.replace("linux", legacy_tag) + for arch in archs: + for glibc_max in glibc_max_list: + if glibc_max.major == too_old_glibc2.major: + min_minor = too_old_glibc2.minor + else: + # For other glibc major versions oldest supported is (x, 0). + min_minor = -1 + for glibc_minor in range(glibc_max.minor, min_minor, -1): + glibc_version = _GLibCVersion(glibc_max.major, glibc_minor) + tag = "manylinux_{}_{}".format(*glibc_version) + if _is_compatible(arch, glibc_version): + yield f"{tag}_{arch}" + # Handle the legacy manylinux1, manylinux2010, manylinux2014 tags. + if glibc_version in _LEGACY_MANYLINUX_MAP: + legacy_tag = _LEGACY_MANYLINUX_MAP[glibc_version] + if _is_compatible(arch, glibc_version): + yield f"{legacy_tag}_{arch}" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_musllinux.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_musllinux.py index 8ac3059..d2bf30b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_musllinux.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_musllinux.py @@ -4,68 +4,15 @@ This module implements logic to detect if the currently running Python is linked against musl, and what musl version is used. """ -import contextlib +from __future__ import annotations + import functools -import operator -import os import re -import struct import subprocess import sys -from typing import IO, Iterator, NamedTuple, Optional, Tuple +from typing import Iterator, NamedTuple, Sequence - -def _read_unpacked(f: IO[bytes], fmt: str) -> Tuple[int, ...]: - return struct.unpack(fmt, f.read(struct.calcsize(fmt))) - - -def _parse_ld_musl_from_elf(f: IO[bytes]) -> Optional[str]: - """Detect musl libc location by parsing the Python executable. - - Based on: https://gist.github.com/lyssdod/f51579ae8d93c8657a5564aefc2ffbca - ELF header: https://refspecs.linuxfoundation.org/elf/gabi4+/ch4.eheader.html - """ - f.seek(0) - try: - ident = _read_unpacked(f, "16B") - except struct.error: - return None - if ident[:4] != tuple(b"\x7fELF"): # Invalid magic, not ELF. - return None - f.seek(struct.calcsize("HHI"), 1) # Skip file type, machine, and version. - - try: - # e_fmt: Format for program header. - # p_fmt: Format for section header. - # p_idx: Indexes to find p_type, p_offset, and p_filesz. - e_fmt, p_fmt, p_idx = { - 1: ("IIIIHHH", "IIIIIIII", (0, 1, 4)), # 32-bit. - 2: ("QQQIHHH", "IIQQQQQQ", (0, 2, 5)), # 64-bit. - }[ident[4]] - except KeyError: - return None - else: - p_get = operator.itemgetter(*p_idx) - - # Find the interpreter section and return its content. - try: - _, e_phoff, _, _, _, e_phentsize, e_phnum = _read_unpacked(f, e_fmt) - except struct.error: - return None - for i in range(e_phnum + 1): - f.seek(e_phoff + e_phentsize * i) - try: - p_type, p_offset, p_filesz = p_get(_read_unpacked(f, p_fmt)) - except struct.error: - return None - if p_type != 3: # Not PT_INTERP. - continue - f.seek(p_offset) - interpreter = os.fsdecode(f.read(p_filesz)).strip("\0") - if "musl" not in interpreter: - return None - return interpreter - return None +from ._elffile import ELFFile class _MuslVersion(NamedTuple): @@ -73,7 +20,7 @@ class _MuslVersion(NamedTuple): minor: int -def _parse_musl_version(output: str) -> Optional[_MuslVersion]: +def _parse_musl_version(output: str) -> _MuslVersion | None: lines = [n for n in (n.strip() for n in output.splitlines()) if n] if len(lines) < 2 or lines[0][:4] != "musl": return None @@ -83,8 +30,8 @@ def _parse_musl_version(output: str) -> Optional[_MuslVersion]: return _MuslVersion(major=int(m.group(1)), minor=int(m.group(2))) -@functools.lru_cache() -def _get_musl_version(executable: str) -> Optional[_MuslVersion]: +@functools.lru_cache +def _get_musl_version(executable: str) -> _MuslVersion | None: """Detect currently-running musl runtime version. This is done by checking the specified executable's dynamic linking @@ -95,32 +42,34 @@ def _get_musl_version(executable: str) -> Optional[_MuslVersion]: Version 1.2.2 Dynamic Program Loader """ - with contextlib.ExitStack() as stack: - try: - f = stack.enter_context(open(executable, "rb")) - except OSError: - return None - ld = _parse_ld_musl_from_elf(f) - if not ld: + try: + with open(executable, "rb") as f: + ld = ELFFile(f).interpreter + except (OSError, TypeError, ValueError): return None - proc = subprocess.run([ld], stderr=subprocess.PIPE, universal_newlines=True) + if ld is None or "musl" not in ld: + return None + proc = subprocess.run([ld], stderr=subprocess.PIPE, text=True) return _parse_musl_version(proc.stderr) -def platform_tags(arch: str) -> Iterator[str]: +def platform_tags(archs: Sequence[str]) -> Iterator[str]: """Generate musllinux tags compatible to the current platform. - :param arch: Should be the part of platform tag after the ``linux_`` - prefix, e.g. ``x86_64``. The ``linux_`` prefix is assumed as a - prerequisite for the current platform to be musllinux-compatible. + :param archs: Sequence of compatible architectures. + The first one shall be the closest to the actual architecture and be the part of + platform tag after the ``linux_`` prefix, e.g. ``x86_64``. + The ``linux_`` prefix is assumed as a prerequisite for the current platform to + be musllinux-compatible. :returns: An iterator of compatible musllinux tags. """ sys_musl = _get_musl_version(sys.executable) if sys_musl is None: # Python not dynamically linked against musl. return - for minor in range(sys_musl.minor, -1, -1): - yield f"musllinux_{sys_musl.major}_{minor}_{arch}" + for arch in archs: + for minor in range(sys_musl.minor, -1, -1): + yield f"musllinux_{sys_musl.major}_{minor}_{arch}" if __name__ == "__main__": # pragma: no cover diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_parser.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_parser.py similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_parser.py rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_parser.py diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_tokenizer.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_tokenizer.py similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_tokenizer.py rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/_tokenizer.py diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__init__.py similarity index 98% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__init__.py rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__init__.py index 569156d..71a1a77 100644 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__init__.py @@ -34,7 +34,7 @@ from __future__ import annotations import re from typing import NewType, cast -from packaging.licenses._spdx import EXCEPTIONS, LICENSES +from pip._vendor.packaging.licenses._spdx import EXCEPTIONS, LICENSES __all__ = [ "NormalizedLicenseExpression", diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc similarity index 77% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc index 148f441..6e2918f 100644 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc similarity index 99% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc index a5c9760..aa78651 100644 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/_spdx.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/_spdx.py similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/licenses/_spdx.py rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/licenses/_spdx.py diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/markers.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/markers.py index 540e7a4..fb7f49c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/markers.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/markers.py @@ -2,31 +2,25 @@ # 2.0, and the BSD License. See the LICENSE file in the root of this repository # for complete details. +from __future__ import annotations + import operator import os import platform import sys -from typing import Any, Callable, Dict, List, Optional, Tuple, Union - -from pip._vendor.pyparsing import ( # noqa: N817 - Forward, - Group, - Literal as L, - ParseException, - ParseResults, - QuotedString, - ZeroOrMore, - stringEnd, - stringStart, -) +from typing import Any, Callable, TypedDict, cast +from ._parser import MarkerAtom, MarkerList, Op, Value, Variable +from ._parser import parse_marker as _parse_marker +from ._tokenizer import ParserSyntaxError from .specifiers import InvalidSpecifier, Specifier +from .utils import canonicalize_name __all__ = [ "InvalidMarker", + "Marker", "UndefinedComparison", "UndefinedEnvironmentName", - "Marker", "default_environment", ] @@ -52,103 +46,97 @@ class UndefinedEnvironmentName(ValueError): """ -class Node: - def __init__(self, value: Any) -> None: - self.value = value +class Environment(TypedDict): + implementation_name: str + """The implementation's identifier, e.g. ``'cpython'``.""" - def __str__(self) -> str: - return str(self.value) + implementation_version: str + """ + The implementation's version, e.g. ``'3.13.0a2'`` for CPython 3.13.0a2, or + ``'7.3.13'`` for PyPy3.10 v7.3.13. + """ - def __repr__(self) -> str: - return f"<{self.__class__.__name__}('{self}')>" + os_name: str + """ + The value of :py:data:`os.name`. The name of the operating system dependent module + imported, e.g. ``'posix'``. + """ - def serialize(self) -> str: - raise NotImplementedError + platform_machine: str + """ + Returns the machine type, e.g. ``'i386'``. + + An empty string if the value cannot be determined. + """ + + platform_release: str + """ + The system's release, e.g. ``'2.2.0'`` or ``'NT'``. + + An empty string if the value cannot be determined. + """ + + platform_system: str + """ + The system/OS name, e.g. ``'Linux'``, ``'Windows'`` or ``'Java'``. + + An empty string if the value cannot be determined. + """ + + platform_version: str + """ + The system's release version, e.g. ``'#3 on degas'``. + + An empty string if the value cannot be determined. + """ + + python_full_version: str + """ + The Python version as string ``'major.minor.patchlevel'``. + + Note that unlike the Python :py:data:`sys.version`, this value will always include + the patchlevel (it defaults to 0). + """ + + platform_python_implementation: str + """ + A string identifying the Python implementation, e.g. ``'CPython'``. + """ + + python_version: str + """The Python version as string ``'major.minor'``.""" + + sys_platform: str + """ + This string contains a platform identifier that can be used to append + platform-specific components to :py:data:`sys.path`, for instance. + + For Unix systems, except on Linux and AIX, this is the lowercased OS name as + returned by ``uname -s`` with the first part of the version as returned by + ``uname -r`` appended, e.g. ``'sunos5'`` or ``'freebsd8'``, at the time when Python + was built. + """ -class Variable(Node): - def serialize(self) -> str: - return str(self) - - -class Value(Node): - def serialize(self) -> str: - return f'"{self}"' - - -class Op(Node): - def serialize(self) -> str: - return str(self) - - -VARIABLE = ( - L("implementation_version") - | L("platform_python_implementation") - | L("implementation_name") - | L("python_full_version") - | L("platform_release") - | L("platform_version") - | L("platform_machine") - | L("platform_system") - | L("python_version") - | L("sys_platform") - | L("os_name") - | L("os.name") # PEP-345 - | L("sys.platform") # PEP-345 - | L("platform.version") # PEP-345 - | L("platform.machine") # PEP-345 - | L("platform.python_implementation") # PEP-345 - | L("python_implementation") # undocumented setuptools legacy - | L("extra") # PEP-508 -) -ALIASES = { - "os.name": "os_name", - "sys.platform": "sys_platform", - "platform.version": "platform_version", - "platform.machine": "platform_machine", - "platform.python_implementation": "platform_python_implementation", - "python_implementation": "platform_python_implementation", -} -VARIABLE.setParseAction(lambda s, l, t: Variable(ALIASES.get(t[0], t[0]))) - -VERSION_CMP = ( - L("===") | L("==") | L(">=") | L("<=") | L("!=") | L("~=") | L(">") | L("<") -) - -MARKER_OP = VERSION_CMP | L("not in") | L("in") -MARKER_OP.setParseAction(lambda s, l, t: Op(t[0])) - -MARKER_VALUE = QuotedString("'") | QuotedString('"') -MARKER_VALUE.setParseAction(lambda s, l, t: Value(t[0])) - -BOOLOP = L("and") | L("or") - -MARKER_VAR = VARIABLE | MARKER_VALUE - -MARKER_ITEM = Group(MARKER_VAR + MARKER_OP + MARKER_VAR) -MARKER_ITEM.setParseAction(lambda s, l, t: tuple(t[0])) - -LPAREN = L("(").suppress() -RPAREN = L(")").suppress() - -MARKER_EXPR = Forward() -MARKER_ATOM = MARKER_ITEM | Group(LPAREN + MARKER_EXPR + RPAREN) -MARKER_EXPR << MARKER_ATOM + ZeroOrMore(BOOLOP + MARKER_EXPR) - -MARKER = stringStart + MARKER_EXPR + stringEnd - - -def _coerce_parse_result(results: Union[ParseResults, List[Any]]) -> List[Any]: - if isinstance(results, ParseResults): - return [_coerce_parse_result(i) for i in results] - else: - return results +def _normalize_extra_values(results: Any) -> Any: + """ + Normalize extra values. + """ + if isinstance(results[0], tuple): + lhs, op, rhs = results[0] + if isinstance(lhs, Variable) and lhs.value == "extra": + normalized_extra = canonicalize_name(rhs.value) + rhs = Value(normalized_extra) + elif isinstance(rhs, Variable) and rhs.value == "extra": + normalized_extra = canonicalize_name(lhs.value) + lhs = Value(normalized_extra) + results[0] = lhs, op, rhs + return results def _format_marker( - marker: Union[List[str], Tuple[Node, ...], str], first: Optional[bool] = True + marker: list[str] | MarkerAtom | str, first: bool | None = True ) -> str: - assert isinstance(marker, (list, tuple, str)) # Sometimes we have a structure like [[...]] which is a single item list @@ -174,7 +162,7 @@ def _format_marker( return marker -_operators: Dict[str, Operator] = { +_operators: dict[str, Operator] = { "in": lambda lhs, rhs: lhs in rhs, "not in": lambda lhs, rhs: lhs not in rhs, "<": operator.lt, @@ -192,35 +180,29 @@ def _eval_op(lhs: str, op: Op, rhs: str) -> bool: except InvalidSpecifier: pass else: - return spec.contains(lhs) + return spec.contains(lhs, prereleases=True) - oper: Optional[Operator] = _operators.get(op.serialize()) + oper: Operator | None = _operators.get(op.serialize()) if oper is None: raise UndefinedComparison(f"Undefined {op!r} on {lhs!r} and {rhs!r}.") return oper(lhs, rhs) -class Undefined: - pass +def _normalize(*values: str, key: str) -> tuple[str, ...]: + # PEP 685 – Comparison of extra names for optional distribution dependencies + # https://peps.python.org/pep-0685/ + # > When comparing extra names, tools MUST normalize the names being + # > compared using the semantics outlined in PEP 503 for names + if key == "extra": + return tuple(canonicalize_name(v) for v in values) + + # other environment markers don't have such standards + return values -_undefined = Undefined() - - -def _get_env(environment: Dict[str, str], name: str) -> str: - value: Union[str, Undefined] = environment.get(name, _undefined) - - if isinstance(value, Undefined): - raise UndefinedEnvironmentName( - f"{name!r} does not exist in evaluation environment." - ) - - return value - - -def _evaluate_markers(markers: List[Any], environment: Dict[str, str]) -> bool: - groups: List[List[bool]] = [[]] +def _evaluate_markers(markers: MarkerList, environment: dict[str, str]) -> bool: + groups: list[list[bool]] = [[]] for marker in markers: assert isinstance(marker, (list, tuple, str)) @@ -231,12 +213,15 @@ def _evaluate_markers(markers: List[Any], environment: Dict[str, str]) -> bool: lhs, op, rhs = marker if isinstance(lhs, Variable): - lhs_value = _get_env(environment, lhs.value) + environment_key = lhs.value + lhs_value = environment[environment_key] rhs_value = rhs.value else: lhs_value = lhs.value - rhs_value = _get_env(environment, rhs.value) + environment_key = rhs.value + rhs_value = environment[environment_key] + lhs_value, rhs_value = _normalize(lhs_value, rhs_value, key=environment_key) groups[-1].append(_eval_op(lhs_value, op, rhs_value)) else: assert marker in ["and", "or"] @@ -246,15 +231,15 @@ def _evaluate_markers(markers: List[Any], environment: Dict[str, str]) -> bool: return any(all(item) for item in groups) -def format_full_version(info: "sys._version_info") -> str: - version = "{0.major}.{0.minor}.{0.micro}".format(info) +def format_full_version(info: sys._version_info) -> str: + version = f"{info.major}.{info.minor}.{info.micro}" kind = info.releaselevel if kind != "final": version += kind[0] + str(info.serial) return version -def default_environment() -> Dict[str, str]: +def default_environment() -> Environment: iver = format_full_version(sys.implementation.version) implementation_name = sys.implementation.name return { @@ -274,13 +259,29 @@ def default_environment() -> Dict[str, str]: class Marker: def __init__(self, marker: str) -> None: + # Note: We create a Marker object without calling this constructor in + # packaging.requirements.Requirement. If any additional logic is + # added here, make sure to mirror/adapt Requirement. try: - self._markers = _coerce_parse_result(MARKER.parseString(marker)) - except ParseException as e: - raise InvalidMarker( - f"Invalid marker: {marker!r}, parse error at " - f"{marker[e.loc : e.loc + 8]!r}" - ) + self._markers = _normalize_extra_values(_parse_marker(marker)) + # The attribute `_markers` can be described in terms of a recursive type: + # MarkerList = List[Union[Tuple[Node, ...], str, MarkerList]] + # + # For example, the following expression: + # python_version > "3.6" or (python_version == "3.6" and os_name == "unix") + # + # is parsed into: + # [ + # (, ')>, ), + # 'and', + # [ + # (, , ), + # 'or', + # (, , ) + # ] + # ] + except ParserSyntaxError as e: + raise InvalidMarker(str(e)) from e def __str__(self) -> str: return _format_marker(self._markers) @@ -288,7 +289,16 @@ class Marker: def __repr__(self) -> str: return f"" - def evaluate(self, environment: Optional[Dict[str, str]] = None) -> bool: + def __hash__(self) -> int: + return hash((self.__class__.__name__, str(self))) + + def __eq__(self, other: Any) -> bool: + if not isinstance(other, Marker): + return NotImplemented + + return str(self) == str(other) + + def evaluate(self, environment: dict[str, str] | None = None) -> bool: """Evaluate a marker. Return the boolean from evaluating the given marker against the @@ -297,8 +307,25 @@ class Marker: The environment is determined from the current Python process. """ - current_environment = default_environment() + current_environment = cast("dict[str, str]", default_environment()) + current_environment["extra"] = "" if environment is not None: current_environment.update(environment) + # The API used to allow setting extra to None. We need to handle this + # case for backwards compatibility. + if current_environment["extra"] is None: + current_environment["extra"] = "" - return _evaluate_markers(self._markers, current_environment) + return _evaluate_markers( + self._markers, _repair_python_full_version(current_environment) + ) + + +def _repair_python_full_version(env: dict[str, str]) -> dict[str, str]: + """ + Work around platform.python_version() returning something that is not PEP 440 + compliant for non-tagged Python builds. + """ + if env["python_full_version"].endswith("+"): + env["python_full_version"] += "local" + return env diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/metadata.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/metadata.py similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/metadata.py rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/metadata.py diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/requirements.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/requirements.py index 1eab7dd..4e068c9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/requirements.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/requirements.py @@ -1,27 +1,15 @@ # This file is dual licensed under the terms of the Apache License, Version # 2.0, and the BSD License. See the LICENSE file in the root of this repository # for complete details. +from __future__ import annotations -import re -import string -import urllib.parse -from typing import List, Optional as TOptional, Set +from typing import Any, Iterator -from pip._vendor.pyparsing import ( # noqa - Combine, - Literal as L, - Optional, - ParseException, - Regex, - Word, - ZeroOrMore, - originalTextFor, - stringEnd, - stringStart, -) - -from .markers import MARKER_EXPR, Marker -from .specifiers import LegacySpecifier, Specifier, SpecifierSet +from ._parser import parse_requirement as _parse_requirement +from ._tokenizer import ParserSyntaxError +from .markers import Marker, _normalize_extra_values +from .specifiers import SpecifierSet +from .utils import canonicalize_name class InvalidRequirement(ValueError): @@ -30,60 +18,6 @@ class InvalidRequirement(ValueError): """ -ALPHANUM = Word(string.ascii_letters + string.digits) - -LBRACKET = L("[").suppress() -RBRACKET = L("]").suppress() -LPAREN = L("(").suppress() -RPAREN = L(")").suppress() -COMMA = L(",").suppress() -SEMICOLON = L(";").suppress() -AT = L("@").suppress() - -PUNCTUATION = Word("-_.") -IDENTIFIER_END = ALPHANUM | (ZeroOrMore(PUNCTUATION) + ALPHANUM) -IDENTIFIER = Combine(ALPHANUM + ZeroOrMore(IDENTIFIER_END)) - -NAME = IDENTIFIER("name") -EXTRA = IDENTIFIER - -URI = Regex(r"[^ ]+")("url") -URL = AT + URI - -EXTRAS_LIST = EXTRA + ZeroOrMore(COMMA + EXTRA) -EXTRAS = (LBRACKET + Optional(EXTRAS_LIST) + RBRACKET)("extras") - -VERSION_PEP440 = Regex(Specifier._regex_str, re.VERBOSE | re.IGNORECASE) -VERSION_LEGACY = Regex(LegacySpecifier._regex_str, re.VERBOSE | re.IGNORECASE) - -VERSION_ONE = VERSION_PEP440 ^ VERSION_LEGACY -VERSION_MANY = Combine( - VERSION_ONE + ZeroOrMore(COMMA + VERSION_ONE), joinString=",", adjacent=False -)("_raw_spec") -_VERSION_SPEC = Optional((LPAREN + VERSION_MANY + RPAREN) | VERSION_MANY) -_VERSION_SPEC.setParseAction(lambda s, l, t: t._raw_spec or "") - -VERSION_SPEC = originalTextFor(_VERSION_SPEC)("specifier") -VERSION_SPEC.setParseAction(lambda s, l, t: t[1]) - -MARKER_EXPR = originalTextFor(MARKER_EXPR())("marker") -MARKER_EXPR.setParseAction( - lambda s, l, t: Marker(s[t._original_start : t._original_end]) -) -MARKER_SEPARATOR = SEMICOLON -MARKER = MARKER_SEPARATOR + MARKER_EXPR - -VERSION_AND_MARKER = VERSION_SPEC + Optional(MARKER) -URL_AND_MARKER = URL + Optional(MARKER) - -NAMED_REQUIREMENT = NAME + Optional(EXTRAS) + (URL_AND_MARKER | VERSION_AND_MARKER) - -REQUIREMENT = stringStart + NAMED_REQUIREMENT + stringEnd -# pyparsing isn't thread safe during initialization, so we do it eagerly, see -# issue #104 -REQUIREMENT.parseString("x[]") - - class Requirement: """Parse a requirement. @@ -99,48 +33,59 @@ class Requirement: def __init__(self, requirement_string: str) -> None: try: - req = REQUIREMENT.parseString(requirement_string) - except ParseException as e: - raise InvalidRequirement( - f'Parse error at "{ requirement_string[e.loc : e.loc + 8]!r}": {e.msg}' - ) + parsed = _parse_requirement(requirement_string) + except ParserSyntaxError as e: + raise InvalidRequirement(str(e)) from e - self.name: str = req.name - if req.url: - parsed_url = urllib.parse.urlparse(req.url) - if parsed_url.scheme == "file": - if urllib.parse.urlunparse(parsed_url) != req.url: - raise InvalidRequirement("Invalid URL given") - elif not (parsed_url.scheme and parsed_url.netloc) or ( - not parsed_url.scheme and not parsed_url.netloc - ): - raise InvalidRequirement(f"Invalid URL: {req.url}") - self.url: TOptional[str] = req.url - else: - self.url = None - self.extras: Set[str] = set(req.extras.asList() if req.extras else []) - self.specifier: SpecifierSet = SpecifierSet(req.specifier) - self.marker: TOptional[Marker] = req.marker if req.marker else None + self.name: str = parsed.name + self.url: str | None = parsed.url or None + self.extras: set[str] = set(parsed.extras or []) + self.specifier: SpecifierSet = SpecifierSet(parsed.specifier) + self.marker: Marker | None = None + if parsed.marker is not None: + self.marker = Marker.__new__(Marker) + self.marker._markers = _normalize_extra_values(parsed.marker) - def __str__(self) -> str: - parts: List[str] = [self.name] + def _iter_parts(self, name: str) -> Iterator[str]: + yield name if self.extras: formatted_extras = ",".join(sorted(self.extras)) - parts.append(f"[{formatted_extras}]") + yield f"[{formatted_extras}]" if self.specifier: - parts.append(str(self.specifier)) + yield str(self.specifier) if self.url: - parts.append(f"@ {self.url}") + yield f"@ {self.url}" if self.marker: - parts.append(" ") + yield " " if self.marker: - parts.append(f"; {self.marker}") + yield f"; {self.marker}" - return "".join(parts) + def __str__(self) -> str: + return "".join(self._iter_parts(self.name)) def __repr__(self) -> str: return f"" + + def __hash__(self) -> int: + return hash( + ( + self.__class__.__name__, + *self._iter_parts(canonicalize_name(self.name)), + ) + ) + + def __eq__(self, other: Any) -> bool: + if not isinstance(other, Requirement): + return NotImplemented + + return ( + canonicalize_name(self.name) == canonicalize_name(other.name) + and self.extras == other.extras + and self.specifier == other.specifier + and self.url == other.url + and self.marker == other.marker + ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/specifiers.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/specifiers.py index 0e218a6..f18016e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/specifiers.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/specifiers.py @@ -1,38 +1,43 @@ # This file is dual licensed under the terms of the Apache License, Version # 2.0, and the BSD License. See the LICENSE file in the root of this repository # for complete details. +""" +.. testsetup:: + + from pip._vendor.packaging.specifiers import Specifier, SpecifierSet, InvalidSpecifier + from pip._vendor.packaging.version import Version +""" + +from __future__ import annotations import abc -import functools import itertools import re -import warnings -from typing import ( - Callable, - Dict, - Iterable, - Iterator, - List, - Optional, - Pattern, - Set, - Tuple, - TypeVar, - Union, -) +from typing import Callable, Iterable, Iterator, TypeVar, Union from .utils import canonicalize_version -from .version import LegacyVersion, Version, parse +from .version import Version -ParsedVersion = Union[Version, LegacyVersion] -UnparsedVersion = Union[Version, LegacyVersion, str] -VersionTypeVar = TypeVar("VersionTypeVar", bound=UnparsedVersion) -CallableOperator = Callable[[ParsedVersion, str], bool] +UnparsedVersion = Union[Version, str] +UnparsedVersionVar = TypeVar("UnparsedVersionVar", bound=UnparsedVersion) +CallableOperator = Callable[[Version, str], bool] + + +def _coerce_version(version: UnparsedVersion) -> Version: + if not isinstance(version, Version): + version = Version(version) + return version class InvalidSpecifier(ValueError): """ - An invalid specifier was found, users should refer to PEP 440. + Raised when attempting to create a :class:`Specifier` with a specifier + string that is invalid. + + >>> Specifier("lolwat") + Traceback (most recent call last): + ... + packaging.specifiers.InvalidSpecifier: Invalid specifier: 'lolwat' """ @@ -40,266 +45,71 @@ class BaseSpecifier(metaclass=abc.ABCMeta): @abc.abstractmethod def __str__(self) -> str: """ - Returns the str representation of this Specifier like object. This + Returns the str representation of this Specifier-like object. This should be representative of the Specifier itself. """ @abc.abstractmethod def __hash__(self) -> int: """ - Returns a hash value for this Specifier like object. + Returns a hash value for this Specifier-like object. """ @abc.abstractmethod def __eq__(self, other: object) -> bool: """ - Returns a boolean representing whether or not the two Specifier like + Returns a boolean representing whether or not the two Specifier-like objects are equal. + + :param other: The other object to check against. """ - @abc.abstractproperty - def prereleases(self) -> Optional[bool]: - """ - Returns whether or not pre-releases as a whole are allowed by this - specifier. + @property + @abc.abstractmethod + def prereleases(self) -> bool | None: + """Whether or not pre-releases as a whole are allowed. + + This can be set to either ``True`` or ``False`` to explicitly enable or disable + prereleases or it can be set to ``None`` (the default) to use default semantics. """ @prereleases.setter def prereleases(self, value: bool) -> None: - """ - Sets whether or not pre-releases as a whole are allowed by this - specifier. + """Setter for :attr:`prereleases`. + + :param value: The value to set. """ @abc.abstractmethod - def contains(self, item: str, prereleases: Optional[bool] = None) -> bool: + def contains(self, item: str, prereleases: bool | None = None) -> bool: """ Determines if the given item is contained within this specifier. """ @abc.abstractmethod def filter( - self, iterable: Iterable[VersionTypeVar], prereleases: Optional[bool] = None - ) -> Iterable[VersionTypeVar]: + self, iterable: Iterable[UnparsedVersionVar], prereleases: bool | None = None + ) -> Iterator[UnparsedVersionVar]: """ Takes an iterable of items and filters them so that only items which are contained within this specifier are allowed in it. """ -class _IndividualSpecifier(BaseSpecifier): +class Specifier(BaseSpecifier): + """This class abstracts handling of version specifiers. - _operators: Dict[str, str] = {} - _regex: Pattern[str] + .. tip:: - def __init__(self, spec: str = "", prereleases: Optional[bool] = None) -> None: - match = self._regex.search(spec) - if not match: - raise InvalidSpecifier(f"Invalid specifier: '{spec}'") + It is generally not required to instantiate this manually. You should instead + prefer to work with :class:`SpecifierSet` instead, which can parse + comma-separated version specifiers (which is what package metadata contains). + """ - self._spec: Tuple[str, str] = ( - match.group("operator").strip(), - match.group("version").strip(), - ) - - # Store whether or not this Specifier should accept prereleases - self._prereleases = prereleases - - def __repr__(self) -> str: - pre = ( - f", prereleases={self.prereleases!r}" - if self._prereleases is not None - else "" - ) - - return f"<{self.__class__.__name__}({str(self)!r}{pre})>" - - def __str__(self) -> str: - return "{}{}".format(*self._spec) - - @property - def _canonical_spec(self) -> Tuple[str, str]: - return self._spec[0], canonicalize_version(self._spec[1]) - - def __hash__(self) -> int: - return hash(self._canonical_spec) - - def __eq__(self, other: object) -> bool: - if isinstance(other, str): - try: - other = self.__class__(str(other)) - except InvalidSpecifier: - return NotImplemented - elif not isinstance(other, self.__class__): - return NotImplemented - - return self._canonical_spec == other._canonical_spec - - def _get_operator(self, op: str) -> CallableOperator: - operator_callable: CallableOperator = getattr( - self, f"_compare_{self._operators[op]}" - ) - return operator_callable - - def _coerce_version(self, version: UnparsedVersion) -> ParsedVersion: - if not isinstance(version, (LegacyVersion, Version)): - version = parse(version) - return version - - @property - def operator(self) -> str: - return self._spec[0] - - @property - def version(self) -> str: - return self._spec[1] - - @property - def prereleases(self) -> Optional[bool]: - return self._prereleases - - @prereleases.setter - def prereleases(self, value: bool) -> None: - self._prereleases = value - - def __contains__(self, item: str) -> bool: - return self.contains(item) - - def contains( - self, item: UnparsedVersion, prereleases: Optional[bool] = None - ) -> bool: - - # Determine if prereleases are to be allowed or not. - if prereleases is None: - prereleases = self.prereleases - - # Normalize item to a Version or LegacyVersion, this allows us to have - # a shortcut for ``"2.0" in Specifier(">=2") - normalized_item = self._coerce_version(item) - - # Determine if we should be supporting prereleases in this specifier - # or not, if we do not support prereleases than we can short circuit - # logic if this version is a prereleases. - if normalized_item.is_prerelease and not prereleases: - return False - - # Actually do the comparison to determine if this item is contained - # within this Specifier or not. - operator_callable: CallableOperator = self._get_operator(self.operator) - return operator_callable(normalized_item, self.version) - - def filter( - self, iterable: Iterable[VersionTypeVar], prereleases: Optional[bool] = None - ) -> Iterable[VersionTypeVar]: - - yielded = False - found_prereleases = [] - - kw = {"prereleases": prereleases if prereleases is not None else True} - - # Attempt to iterate over all the values in the iterable and if any of - # them match, yield them. - for version in iterable: - parsed_version = self._coerce_version(version) - - if self.contains(parsed_version, **kw): - # If our version is a prerelease, and we were not set to allow - # prereleases, then we'll store it for later in case nothing - # else matches this specifier. - if parsed_version.is_prerelease and not ( - prereleases or self.prereleases - ): - found_prereleases.append(version) - # Either this is not a prerelease, or we should have been - # accepting prereleases from the beginning. - else: - yielded = True - yield version - - # Now that we've iterated over everything, determine if we've yielded - # any values, and if we have not and we have any prereleases stored up - # then we will go ahead and yield the prereleases. - if not yielded and found_prereleases: - for version in found_prereleases: - yield version - - -class LegacySpecifier(_IndividualSpecifier): - - _regex_str = r""" - (?P(==|!=|<=|>=|<|>)) - \s* - (?P - [^,;\s)]* # Since this is a "legacy" specifier, and the version - # string can be just about anything, we match everything - # except for whitespace, a semi-colon for marker support, - # a closing paren since versions can be enclosed in - # them, and a comma since it's a version separator. - ) - """ - - _regex = re.compile(r"^\s*" + _regex_str + r"\s*$", re.VERBOSE | re.IGNORECASE) - - _operators = { - "==": "equal", - "!=": "not_equal", - "<=": "less_than_equal", - ">=": "greater_than_equal", - "<": "less_than", - ">": "greater_than", - } - - def __init__(self, spec: str = "", prereleases: Optional[bool] = None) -> None: - super().__init__(spec, prereleases) - - warnings.warn( - "Creating a LegacyVersion has been deprecated and will be " - "removed in the next major release", - DeprecationWarning, - ) - - def _coerce_version(self, version: UnparsedVersion) -> LegacyVersion: - if not isinstance(version, LegacyVersion): - version = LegacyVersion(str(version)) - return version - - def _compare_equal(self, prospective: LegacyVersion, spec: str) -> bool: - return prospective == self._coerce_version(spec) - - def _compare_not_equal(self, prospective: LegacyVersion, spec: str) -> bool: - return prospective != self._coerce_version(spec) - - def _compare_less_than_equal(self, prospective: LegacyVersion, spec: str) -> bool: - return prospective <= self._coerce_version(spec) - - def _compare_greater_than_equal( - self, prospective: LegacyVersion, spec: str - ) -> bool: - return prospective >= self._coerce_version(spec) - - def _compare_less_than(self, prospective: LegacyVersion, spec: str) -> bool: - return prospective < self._coerce_version(spec) - - def _compare_greater_than(self, prospective: LegacyVersion, spec: str) -> bool: - return prospective > self._coerce_version(spec) - - -def _require_version_compare( - fn: Callable[["Specifier", ParsedVersion, str], bool] -) -> Callable[["Specifier", ParsedVersion, str], bool]: - @functools.wraps(fn) - def wrapped(self: "Specifier", prospective: ParsedVersion, spec: str) -> bool: - if not isinstance(prospective, Version): - return False - return fn(self, prospective, spec) - - return wrapped - - -class Specifier(_IndividualSpecifier): - - _regex_str = r""" + _operator_regex_str = r""" (?P(~=|==|!=|<=|>=|<|>|===)) + """ + _version_regex_str = r""" (?P (?: # The identity operators allow for an escape hatch that will @@ -309,8 +119,10 @@ class Specifier(_IndividualSpecifier): # but included entirely as an escape hatch. (?<====) # Only match for the identity operator \s* - [^\s]* # We just match everything, except for whitespace - # since we are only testing for strict identity. + [^\s;)]* # The arbitrary version can be just about anything, + # we match everything except for whitespace, a + # semi-colon for marker support, and a closing paren + # since versions can be enclosed in them. ) | (?: @@ -323,23 +135,23 @@ class Specifier(_IndividualSpecifier): v? (?:[0-9]+!)? # epoch [0-9]+(?:\.[0-9]+)* # release - (?: # pre release - [-_\.]? - (a|b|c|rc|alpha|beta|pre|preview) - [-_\.]? - [0-9]* - )? - (?: # post release - (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*) - )? - # You cannot use a wild card and a dev or local version - # together so group them with a | and make them optional. + # You cannot use a wild card and a pre-release, post-release, a dev or + # local version together so group them with a | and make them optional. (?: + \.\* # Wild card syntax of .* + | + (?: # pre release + [-_\.]? + (alpha|beta|preview|pre|a|b|c|rc) + [-_\.]? + [0-9]* + )? + (?: # post release + (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*) + )? (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release (?:\+[a-z0-9]+(?:[-_\.][a-z0-9]+)*)? # local - | - \.\* # Wild card syntax of .* )? ) | @@ -354,7 +166,7 @@ class Specifier(_IndividualSpecifier): [0-9]+(?:\.[0-9]+)+ # release (We have a + instead of a *) (?: # pre release [-_\.]? - (a|b|c|rc|alpha|beta|pre|preview) + (alpha|beta|preview|pre|a|b|c|rc) [-_\.]? [0-9]* )? @@ -379,7 +191,7 @@ class Specifier(_IndividualSpecifier): [0-9]+(?:\.[0-9]+)* # release (?: # pre release [-_\.]? - (a|b|c|rc|alpha|beta|pre|preview) + (alpha|beta|preview|pre|a|b|c|rc) [-_\.]? [0-9]* )? @@ -391,7 +203,10 @@ class Specifier(_IndividualSpecifier): ) """ - _regex = re.compile(r"^\s*" + _regex_str + r"\s*$", re.VERBOSE | re.IGNORECASE) + _regex = re.compile( + r"^\s*" + _operator_regex_str + _version_regex_str + r"\s*$", + re.VERBOSE | re.IGNORECASE, + ) _operators = { "~=": "compatible", @@ -404,9 +219,153 @@ class Specifier(_IndividualSpecifier): "===": "arbitrary", } - @_require_version_compare - def _compare_compatible(self, prospective: ParsedVersion, spec: str) -> bool: + def __init__(self, spec: str = "", prereleases: bool | None = None) -> None: + """Initialize a Specifier instance. + :param spec: + The string representation of a specifier which will be parsed and + normalized before use. + :param prereleases: + This tells the specifier if it should accept prerelease versions if + applicable or not. The default of ``None`` will autodetect it from the + given specifiers. + :raises InvalidSpecifier: + If the given specifier is invalid (i.e. bad syntax). + """ + match = self._regex.search(spec) + if not match: + raise InvalidSpecifier(f"Invalid specifier: {spec!r}") + + self._spec: tuple[str, str] = ( + match.group("operator").strip(), + match.group("version").strip(), + ) + + # Store whether or not this Specifier should accept prereleases + self._prereleases = prereleases + + # https://github.com/python/mypy/pull/13475#pullrequestreview-1079784515 + @property # type: ignore[override] + def prereleases(self) -> bool: + # If there is an explicit prereleases set for this, then we'll just + # blindly use that. + if self._prereleases is not None: + return self._prereleases + + # Look at all of our specifiers and determine if they are inclusive + # operators, and if they are if they are including an explicit + # prerelease. + operator, version = self._spec + if operator in ["==", ">=", "<=", "~=", "===", ">", "<"]: + # The == specifier can include a trailing .*, if it does we + # want to remove before parsing. + if operator == "==" and version.endswith(".*"): + version = version[:-2] + + # Parse the version, and if it is a pre-release than this + # specifier allows pre-releases. + if Version(version).is_prerelease: + return True + + return False + + @prereleases.setter + def prereleases(self, value: bool) -> None: + self._prereleases = value + + @property + def operator(self) -> str: + """The operator of this specifier. + + >>> Specifier("==1.2.3").operator + '==' + """ + return self._spec[0] + + @property + def version(self) -> str: + """The version of this specifier. + + >>> Specifier("==1.2.3").version + '1.2.3' + """ + return self._spec[1] + + def __repr__(self) -> str: + """A representation of the Specifier that shows all internal state. + + >>> Specifier('>=1.0.0') + =1.0.0')> + >>> Specifier('>=1.0.0', prereleases=False) + =1.0.0', prereleases=False)> + >>> Specifier('>=1.0.0', prereleases=True) + =1.0.0', prereleases=True)> + """ + pre = ( + f", prereleases={self.prereleases!r}" + if self._prereleases is not None + else "" + ) + + return f"<{self.__class__.__name__}({str(self)!r}{pre})>" + + def __str__(self) -> str: + """A string representation of the Specifier that can be round-tripped. + + >>> str(Specifier('>=1.0.0')) + '>=1.0.0' + >>> str(Specifier('>=1.0.0', prereleases=False)) + '>=1.0.0' + """ + return "{}{}".format(*self._spec) + + @property + def _canonical_spec(self) -> tuple[str, str]: + canonical_version = canonicalize_version( + self._spec[1], + strip_trailing_zero=(self._spec[0] != "~="), + ) + return self._spec[0], canonical_version + + def __hash__(self) -> int: + return hash(self._canonical_spec) + + def __eq__(self, other: object) -> bool: + """Whether or not the two Specifier-like objects are equal. + + :param other: The other object to check against. + + The value of :attr:`prereleases` is ignored. + + >>> Specifier("==1.2.3") == Specifier("== 1.2.3.0") + True + >>> (Specifier("==1.2.3", prereleases=False) == + ... Specifier("==1.2.3", prereleases=True)) + True + >>> Specifier("==1.2.3") == "==1.2.3" + True + >>> Specifier("==1.2.3") == Specifier("==1.2.4") + False + >>> Specifier("==1.2.3") == Specifier("~=1.2.3") + False + """ + if isinstance(other, str): + try: + other = self.__class__(str(other)) + except InvalidSpecifier: + return NotImplemented + elif not isinstance(other, self.__class__): + return NotImplemented + + return self._canonical_spec == other._canonical_spec + + def _get_operator(self, op: str) -> CallableOperator: + operator_callable: CallableOperator = getattr( + self, f"_compare_{self._operators[op]}" + ) + return operator_callable + + def _compare_compatible(self, prospective: Version, spec: str) -> bool: # Compatible releases have an equivalent combination of >= and ==. That # is that ~=2.2 is equivalent to >=2.2,==2.*. This allows us to # implement this in terms of the other specifiers instead of @@ -415,7 +374,7 @@ class Specifier(_IndividualSpecifier): # We want everything but the last item in the version, but we want to # ignore suffix segments. - prefix = ".".join( + prefix = _version_join( list(itertools.takewhile(_is_not_suffix, _version_split(spec)))[:-1] ) @@ -426,34 +385,34 @@ class Specifier(_IndividualSpecifier): prospective, prefix ) - @_require_version_compare - def _compare_equal(self, prospective: ParsedVersion, spec: str) -> bool: - + def _compare_equal(self, prospective: Version, spec: str) -> bool: # We need special logic to handle prefix matching if spec.endswith(".*"): # In the case of prefix matching we want to ignore local segment. - prospective = Version(prospective.public) - # Split the spec out by dots, and pretend that there is an implicit - # dot in between a release segment and a pre-release segment. - split_spec = _version_split(spec[:-2]) # Remove the trailing .* + normalized_prospective = canonicalize_version( + prospective.public, strip_trailing_zero=False + ) + # Get the normalized version string ignoring the trailing .* + normalized_spec = canonicalize_version(spec[:-2], strip_trailing_zero=False) + # Split the spec out by bangs and dots, and pretend that there is + # an implicit dot in between a release segment and a pre-release segment. + split_spec = _version_split(normalized_spec) - # Split the prospective version out by dots, and pretend that there - # is an implicit dot in between a release segment and a pre-release - # segment. - split_prospective = _version_split(str(prospective)) + # Split the prospective version out by bangs and dots, and pretend + # that there is an implicit dot in between a release segment and + # a pre-release segment. + split_prospective = _version_split(normalized_prospective) + + # 0-pad the prospective version before shortening it to get the correct + # shortened version. + padded_prospective, _ = _pad_version(split_prospective, split_spec) # Shorten the prospective version to be the same length as the spec # so that we can determine if the specifier is a prefix of the # prospective version or not. - shortened_prospective = split_prospective[: len(split_spec)] + shortened_prospective = padded_prospective[: len(split_spec)] - # Pad out our two sides with zeros so that they both equal the same - # length. - padded_spec, padded_prospective = _pad_version( - split_spec, shortened_prospective - ) - - return padded_prospective == padded_spec + return shortened_prospective == split_spec else: # Convert our spec string into a Version spec_version = Version(spec) @@ -466,31 +425,22 @@ class Specifier(_IndividualSpecifier): return prospective == spec_version - @_require_version_compare - def _compare_not_equal(self, prospective: ParsedVersion, spec: str) -> bool: + def _compare_not_equal(self, prospective: Version, spec: str) -> bool: return not self._compare_equal(prospective, spec) - @_require_version_compare - def _compare_less_than_equal(self, prospective: ParsedVersion, spec: str) -> bool: - + def _compare_less_than_equal(self, prospective: Version, spec: str) -> bool: # NB: Local version identifiers are NOT permitted in the version # specifier, so local version labels can be universally removed from # the prospective version. return Version(prospective.public) <= Version(spec) - @_require_version_compare - def _compare_greater_than_equal( - self, prospective: ParsedVersion, spec: str - ) -> bool: - + def _compare_greater_than_equal(self, prospective: Version, spec: str) -> bool: # NB: Local version identifiers are NOT permitted in the version # specifier, so local version labels can be universally removed from # the prospective version. return Version(prospective.public) >= Version(spec) - @_require_version_compare - def _compare_less_than(self, prospective: ParsedVersion, spec_str: str) -> bool: - + def _compare_less_than(self, prospective: Version, spec_str: str) -> bool: # Convert our spec to a Version instance, since we'll want to work with # it as a version. spec = Version(spec_str) @@ -514,9 +464,7 @@ class Specifier(_IndividualSpecifier): # version in the spec. return True - @_require_version_compare - def _compare_greater_than(self, prospective: ParsedVersion, spec_str: str) -> bool: - + def _compare_greater_than(self, prospective: Version, spec_str: str) -> bool: # Convert our spec to a Version instance, since we'll want to work with # it as a version. spec = Version(spec_str) @@ -549,42 +497,150 @@ class Specifier(_IndividualSpecifier): def _compare_arbitrary(self, prospective: Version, spec: str) -> bool: return str(prospective).lower() == str(spec).lower() - @property - def prereleases(self) -> bool: + def __contains__(self, item: str | Version) -> bool: + """Return whether or not the item is contained in this specifier. - # If there is an explicit prereleases set for this, then we'll just - # blindly use that. - if self._prereleases is not None: - return self._prereleases + :param item: The item to check for. - # Look at all of our specifiers and determine if they are inclusive - # operators, and if they are if they are including an explicit - # prerelease. - operator, version = self._spec - if operator in ["==", ">=", "<=", "~=", "==="]: - # The == specifier can include a trailing .*, if it does we - # want to remove before parsing. - if operator == "==" and version.endswith(".*"): - version = version[:-2] + This is used for the ``in`` operator and behaves the same as + :meth:`contains` with no ``prereleases`` argument passed. - # Parse the version, and if it is a pre-release than this - # specifier allows pre-releases. - if parse(version).is_prerelease: - return True + >>> "1.2.3" in Specifier(">=1.2.3") + True + >>> Version("1.2.3") in Specifier(">=1.2.3") + True + >>> "1.0.0" in Specifier(">=1.2.3") + False + >>> "1.3.0a1" in Specifier(">=1.2.3") + False + >>> "1.3.0a1" in Specifier(">=1.2.3", prereleases=True) + True + """ + return self.contains(item) - return False + def contains(self, item: UnparsedVersion, prereleases: bool | None = None) -> bool: + """Return whether or not the item is contained in this specifier. - @prereleases.setter - def prereleases(self, value: bool) -> None: - self._prereleases = value + :param item: + The item to check for, which can be a version string or a + :class:`Version` instance. + :param prereleases: + Whether or not to match prereleases with this Specifier. If set to + ``None`` (the default), it uses :attr:`prereleases` to determine + whether or not prereleases are allowed. + + >>> Specifier(">=1.2.3").contains("1.2.3") + True + >>> Specifier(">=1.2.3").contains(Version("1.2.3")) + True + >>> Specifier(">=1.2.3").contains("1.0.0") + False + >>> Specifier(">=1.2.3").contains("1.3.0a1") + False + >>> Specifier(">=1.2.3", prereleases=True).contains("1.3.0a1") + True + >>> Specifier(">=1.2.3").contains("1.3.0a1", prereleases=True) + True + """ + + # Determine if prereleases are to be allowed or not. + if prereleases is None: + prereleases = self.prereleases + + # Normalize item to a Version, this allows us to have a shortcut for + # "2.0" in Specifier(">=2") + normalized_item = _coerce_version(item) + + # Determine if we should be supporting prereleases in this specifier + # or not, if we do not support prereleases than we can short circuit + # logic if this version is a prereleases. + if normalized_item.is_prerelease and not prereleases: + return False + + # Actually do the comparison to determine if this item is contained + # within this Specifier or not. + operator_callable: CallableOperator = self._get_operator(self.operator) + return operator_callable(normalized_item, self.version) + + def filter( + self, iterable: Iterable[UnparsedVersionVar], prereleases: bool | None = None + ) -> Iterator[UnparsedVersionVar]: + """Filter items in the given iterable, that match the specifier. + + :param iterable: + An iterable that can contain version strings and :class:`Version` instances. + The items in the iterable will be filtered according to the specifier. + :param prereleases: + Whether or not to allow prereleases in the returned iterator. If set to + ``None`` (the default), it will be intelligently decide whether to allow + prereleases or not (based on the :attr:`prereleases` attribute, and + whether the only versions matching are prereleases). + + This method is smarter than just ``filter(Specifier().contains, [...])`` + because it implements the rule from :pep:`440` that a prerelease item + SHOULD be accepted if no other versions match the given specifier. + + >>> list(Specifier(">=1.2.3").filter(["1.2", "1.3", "1.5a1"])) + ['1.3'] + >>> list(Specifier(">=1.2.3").filter(["1.2", "1.2.3", "1.3", Version("1.4")])) + ['1.2.3', '1.3', ] + >>> list(Specifier(">=1.2.3").filter(["1.2", "1.5a1"])) + ['1.5a1'] + >>> list(Specifier(">=1.2.3").filter(["1.3", "1.5a1"], prereleases=True)) + ['1.3', '1.5a1'] + >>> list(Specifier(">=1.2.3", prereleases=True).filter(["1.3", "1.5a1"])) + ['1.3', '1.5a1'] + """ + + yielded = False + found_prereleases = [] + + kw = {"prereleases": prereleases if prereleases is not None else True} + + # Attempt to iterate over all the values in the iterable and if any of + # them match, yield them. + for version in iterable: + parsed_version = _coerce_version(version) + + if self.contains(parsed_version, **kw): + # If our version is a prerelease, and we were not set to allow + # prereleases, then we'll store it for later in case nothing + # else matches this specifier. + if parsed_version.is_prerelease and not ( + prereleases or self.prereleases + ): + found_prereleases.append(version) + # Either this is not a prerelease, or we should have been + # accepting prereleases from the beginning. + else: + yielded = True + yield version + + # Now that we've iterated over everything, determine if we've yielded + # any values, and if we have not and we have any prereleases stored up + # then we will go ahead and yield the prereleases. + if not yielded and found_prereleases: + for version in found_prereleases: + yield version _prefix_regex = re.compile(r"^([0-9]+)((?:a|b|c|rc)[0-9]+)$") -def _version_split(version: str) -> List[str]: - result: List[str] = [] - for item in version.split("."): +def _version_split(version: str) -> list[str]: + """Split version into components. + + The split components are intended for version comparison. The logic does + not attempt to retain the original version string, so joining the + components back with :func:`_version_join` may not produce the original + version string. + """ + result: list[str] = [] + + epoch, _, rest = version.rpartition("!") + result.append(epoch or "0") + + for item in rest.split("."): match = _prefix_regex.search(item) if match: result.extend(match.groups()) @@ -593,13 +649,24 @@ def _version_split(version: str) -> List[str]: return result +def _version_join(components: list[str]) -> str: + """Join split version components into a version string. + + This function assumes the input came from :func:`_version_split`, where the + first component must be the epoch (either empty or numeric), and all other + components numeric. + """ + epoch, *rest = components + return f"{epoch}!{'.'.join(rest)}" + + def _is_not_suffix(segment: str) -> bool: return not any( segment.startswith(prefix) for prefix in ("dev", "a", "b", "rc", "post") ) -def _pad_version(left: List[str], right: List[str]) -> Tuple[List[str], List[str]]: +def _pad_version(left: list[str], right: list[str]) -> tuple[list[str], list[str]]: left_split, right_split = [], [] # Get the release segment of our versions @@ -614,35 +681,91 @@ def _pad_version(left: List[str], right: List[str]) -> Tuple[List[str], List[str left_split.insert(1, ["0"] * max(0, len(right_split[0]) - len(left_split[0]))) right_split.insert(1, ["0"] * max(0, len(left_split[0]) - len(right_split[0]))) - return (list(itertools.chain(*left_split)), list(itertools.chain(*right_split))) + return ( + list(itertools.chain.from_iterable(left_split)), + list(itertools.chain.from_iterable(right_split)), + ) class SpecifierSet(BaseSpecifier): + """This class abstracts handling of a set of version specifiers. + + It can be passed a single specifier (``>=3.0``), a comma-separated list of + specifiers (``>=3.0,!=3.1``), or no specifier at all. + """ + def __init__( - self, specifiers: str = "", prereleases: Optional[bool] = None + self, + specifiers: str | Iterable[Specifier] = "", + prereleases: bool | None = None, ) -> None: + """Initialize a SpecifierSet instance. - # Split on , to break each individual specifier into it's own item, and - # strip each item to remove leading/trailing whitespace. - split_specifiers = [s.strip() for s in specifiers.split(",") if s.strip()] + :param specifiers: + The string representation of a specifier or a comma-separated list of + specifiers which will be parsed and normalized before use. + May also be an iterable of ``Specifier`` instances, which will be used + as is. + :param prereleases: + This tells the SpecifierSet if it should accept prerelease versions if + applicable or not. The default of ``None`` will autodetect it from the + given specifiers. - # Parsed each individual specifier, attempting first to make it a - # Specifier and falling back to a LegacySpecifier. - parsed: Set[_IndividualSpecifier] = set() - for specifier in split_specifiers: - try: - parsed.add(Specifier(specifier)) - except InvalidSpecifier: - parsed.add(LegacySpecifier(specifier)) + :raises InvalidSpecifier: + If the given ``specifiers`` are not parseable than this exception will be + raised. + """ - # Turn our parsed specifiers into a frozen set and save them for later. - self._specs = frozenset(parsed) + if isinstance(specifiers, str): + # Split on `,` to break each individual specifier into its own item, and + # strip each item to remove leading/trailing whitespace. + split_specifiers = [s.strip() for s in specifiers.split(",") if s.strip()] + + # Make each individual specifier a Specifier and save in a frozen set + # for later. + self._specs = frozenset(map(Specifier, split_specifiers)) + else: + # Save the supplied specifiers in a frozen set. + self._specs = frozenset(specifiers) # Store our prereleases value so we can use it later to determine if # we accept prereleases or not. self._prereleases = prereleases + @property + def prereleases(self) -> bool | None: + # If we have been given an explicit prerelease modifier, then we'll + # pass that through here. + if self._prereleases is not None: + return self._prereleases + + # If we don't have any specifiers, and we don't have a forced value, + # then we'll just return None since we don't know if this should have + # pre-releases or not. + if not self._specs: + return None + + # Otherwise we'll see if any of the given specifiers accept + # prereleases, if any of them do we'll return True, otherwise False. + return any(s.prereleases for s in self._specs) + + @prereleases.setter + def prereleases(self, value: bool) -> None: + self._prereleases = value + def __repr__(self) -> str: + """A representation of the specifier set that shows all internal state. + + Note that the ordering of the individual specifiers within the set may not + match the input string. + + >>> SpecifierSet('>=1.0.0,!=2.0.0') + =1.0.0')> + >>> SpecifierSet('>=1.0.0,!=2.0.0', prereleases=False) + =1.0.0', prereleases=False)> + >>> SpecifierSet('>=1.0.0,!=2.0.0', prereleases=True) + =1.0.0', prereleases=True)> + """ pre = ( f", prereleases={self.prereleases!r}" if self._prereleases is not None @@ -652,12 +775,31 @@ class SpecifierSet(BaseSpecifier): return f"" def __str__(self) -> str: + """A string representation of the specifier set that can be round-tripped. + + Note that the ordering of the individual specifiers within the set may not + match the input string. + + >>> str(SpecifierSet(">=1.0.0,!=1.0.1")) + '!=1.0.1,>=1.0.0' + >>> str(SpecifierSet(">=1.0.0,!=1.0.1", prereleases=False)) + '!=1.0.1,>=1.0.0' + """ return ",".join(sorted(str(s) for s in self._specs)) def __hash__(self) -> int: return hash(self._specs) - def __and__(self, other: Union["SpecifierSet", str]) -> "SpecifierSet": + def __and__(self, other: SpecifierSet | str) -> SpecifierSet: + """Return a SpecifierSet which is a combination of the two sets. + + :param other: The other object to combine with. + + >>> SpecifierSet(">=1.0.0,!=1.0.1") & '<=2.0.0,!=2.0.1' + =1.0.0')> + >>> SpecifierSet(">=1.0.0,!=1.0.1") & SpecifierSet('<=2.0.0,!=2.0.1') + =1.0.0')> + """ if isinstance(other, str): other = SpecifierSet(other) elif not isinstance(other, SpecifierSet): @@ -681,7 +823,25 @@ class SpecifierSet(BaseSpecifier): return specifier def __eq__(self, other: object) -> bool: - if isinstance(other, (str, _IndividualSpecifier)): + """Whether or not the two SpecifierSet-like objects are equal. + + :param other: The other object to check against. + + The value of :attr:`prereleases` is ignored. + + >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0,!=1.0.1") + True + >>> (SpecifierSet(">=1.0.0,!=1.0.1", prereleases=False) == + ... SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True)) + True + >>> SpecifierSet(">=1.0.0,!=1.0.1") == ">=1.0.0,!=1.0.1" + True + >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0") + False + >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0,!=1.0.2") + False + """ + if isinstance(other, (str, Specifier)): other = SpecifierSet(str(other)) elif not isinstance(other, SpecifierSet): return NotImplemented @@ -689,43 +849,72 @@ class SpecifierSet(BaseSpecifier): return self._specs == other._specs def __len__(self) -> int: + """Returns the number of specifiers in this specifier set.""" return len(self._specs) - def __iter__(self) -> Iterator[_IndividualSpecifier]: + def __iter__(self) -> Iterator[Specifier]: + """ + Returns an iterator over all the underlying :class:`Specifier` instances + in this specifier set. + + >>> sorted(SpecifierSet(">=1.0.0,!=1.0.1"), key=str) + [, =1.0.0')>] + """ return iter(self._specs) - @property - def prereleases(self) -> Optional[bool]: - - # If we have been given an explicit prerelease modifier, then we'll - # pass that through here. - if self._prereleases is not None: - return self._prereleases - - # If we don't have any specifiers, and we don't have a forced value, - # then we'll just return None since we don't know if this should have - # pre-releases or not. - if not self._specs: - return None - - # Otherwise we'll see if any of the given specifiers accept - # prereleases, if any of them do we'll return True, otherwise False. - return any(s.prereleases for s in self._specs) - - @prereleases.setter - def prereleases(self, value: bool) -> None: - self._prereleases = value - def __contains__(self, item: UnparsedVersion) -> bool: + """Return whether or not the item is contained in this specifier. + + :param item: The item to check for. + + This is used for the ``in`` operator and behaves the same as + :meth:`contains` with no ``prereleases`` argument passed. + + >>> "1.2.3" in SpecifierSet(">=1.0.0,!=1.0.1") + True + >>> Version("1.2.3") in SpecifierSet(">=1.0.0,!=1.0.1") + True + >>> "1.0.1" in SpecifierSet(">=1.0.0,!=1.0.1") + False + >>> "1.3.0a1" in SpecifierSet(">=1.0.0,!=1.0.1") + False + >>> "1.3.0a1" in SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True) + True + """ return self.contains(item) def contains( - self, item: UnparsedVersion, prereleases: Optional[bool] = None + self, + item: UnparsedVersion, + prereleases: bool | None = None, + installed: bool | None = None, ) -> bool: + """Return whether or not the item is contained in this SpecifierSet. - # Ensure that our item is a Version or LegacyVersion instance. - if not isinstance(item, (LegacyVersion, Version)): - item = parse(item) + :param item: + The item to check for, which can be a version string or a + :class:`Version` instance. + :param prereleases: + Whether or not to match prereleases with this SpecifierSet. If set to + ``None`` (the default), it uses :attr:`prereleases` to determine + whether or not prereleases are allowed. + + >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.2.3") + True + >>> SpecifierSet(">=1.0.0,!=1.0.1").contains(Version("1.2.3")) + True + >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.0.1") + False + >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.3.0a1") + False + >>> SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True).contains("1.3.0a1") + True + >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.3.0a1", prereleases=True) + True + """ + # Ensure that our item is a Version instance. + if not isinstance(item, Version): + item = Version(item) # Determine if we're forcing a prerelease or not, if we're not forcing # one for this particular filter call, then we'll use whatever the @@ -742,6 +931,9 @@ class SpecifierSet(BaseSpecifier): if not prereleases and item.is_prerelease: return False + if installed and item.is_prerelease: + item = Version(item.base_version) + # We simply dispatch to the underlying specs here to make sure that the # given version is contained within all of them. # Note: This use of all() here means that an empty set of specifiers @@ -749,9 +941,46 @@ class SpecifierSet(BaseSpecifier): return all(s.contains(item, prereleases=prereleases) for s in self._specs) def filter( - self, iterable: Iterable[VersionTypeVar], prereleases: Optional[bool] = None - ) -> Iterable[VersionTypeVar]: + self, iterable: Iterable[UnparsedVersionVar], prereleases: bool | None = None + ) -> Iterator[UnparsedVersionVar]: + """Filter items in the given iterable, that match the specifiers in this set. + :param iterable: + An iterable that can contain version strings and :class:`Version` instances. + The items in the iterable will be filtered according to the specifier. + :param prereleases: + Whether or not to allow prereleases in the returned iterator. If set to + ``None`` (the default), it will be intelligently decide whether to allow + prereleases or not (based on the :attr:`prereleases` attribute, and + whether the only versions matching are prereleases). + + This method is smarter than just ``filter(SpecifierSet(...).contains, [...])`` + because it implements the rule from :pep:`440` that a prerelease item + SHOULD be accepted if no other versions match the given specifier. + + >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.3", "1.5a1"])) + ['1.3'] + >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.3", Version("1.4")])) + ['1.3', ] + >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.5a1"])) + [] + >>> list(SpecifierSet(">=1.2.3").filter(["1.3", "1.5a1"], prereleases=True)) + ['1.3', '1.5a1'] + >>> list(SpecifierSet(">=1.2.3", prereleases=True).filter(["1.3", "1.5a1"])) + ['1.3', '1.5a1'] + + An "empty" SpecifierSet will filter items based on the presence of prerelease + versions in the set. + + >>> list(SpecifierSet("").filter(["1.3", "1.5a1"])) + ['1.3'] + >>> list(SpecifierSet("").filter(["1.5a1"])) + ['1.5a1'] + >>> list(SpecifierSet("", prereleases=True).filter(["1.3", "1.5a1"])) + ['1.3', '1.5a1'] + >>> list(SpecifierSet("").filter(["1.3", "1.5a1"], prereleases=True)) + ['1.3', '1.5a1'] + """ # Determine if we're forcing a prerelease or not, if we're not forcing # one for this particular filter call, then we'll use whatever the # SpecifierSet thinks for whether or not we should support prereleases. @@ -764,27 +993,16 @@ class SpecifierSet(BaseSpecifier): if self._specs: for spec in self._specs: iterable = spec.filter(iterable, prereleases=bool(prereleases)) - return iterable + return iter(iterable) # If we do not have any specifiers, then we need to have a rough filter # which will filter out any pre-releases, unless there are no final - # releases, and which will filter out LegacyVersion in general. + # releases. else: - filtered: List[VersionTypeVar] = [] - found_prereleases: List[VersionTypeVar] = [] - - item: UnparsedVersion - parsed_version: Union[Version, LegacyVersion] + filtered: list[UnparsedVersionVar] = [] + found_prereleases: list[UnparsedVersionVar] = [] for item in iterable: - # Ensure that we some kind of Version class for this item. - if not isinstance(item, (LegacyVersion, Version)): - parsed_version = parse(item) - else: - parsed_version = item - - # Filter out any item which is parsed as a LegacyVersion - if isinstance(parsed_version, LegacyVersion): - continue + parsed_version = _coerce_version(item) # Store any item which is a pre-release for later unless we've # already found a final version or we are accepting prereleases @@ -797,6 +1015,6 @@ class SpecifierSet(BaseSpecifier): # If we've found no items except for pre-releases, then we'll go # ahead and use the pre-releases if not filtered and found_prereleases and prereleases is None: - return found_prereleases + return iter(found_prereleases) - return filtered + return iter(filtered) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/tags.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/tags.py index 9a3d25a..f590340 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/tags.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/tags.py @@ -2,21 +2,21 @@ # 2.0, and the BSD License. See the LICENSE file in the root of this repository # for complete details. +from __future__ import annotations + import logging import platform +import re +import struct +import subprocess import sys import sysconfig from importlib.machinery import EXTENSION_SUFFIXES from typing import ( - Dict, - FrozenSet, Iterable, Iterator, - List, - Optional, Sequence, Tuple, - Union, cast, ) @@ -25,9 +25,9 @@ from . import _manylinux, _musllinux logger = logging.getLogger(__name__) PythonVersion = Sequence[int] -MacVersion = Tuple[int, int] +AppleVersion = Tuple[int, int] -INTERPRETER_SHORT_NAMES: Dict[str, str] = { +INTERPRETER_SHORT_NAMES: dict[str, str] = { "python": "py", # Generic. "cpython": "cp", "pypy": "pp", @@ -36,7 +36,7 @@ INTERPRETER_SHORT_NAMES: Dict[str, str] = { } -_32_BIT_INTERPRETER = sys.maxsize <= 2 ** 32 +_32_BIT_INTERPRETER = struct.calcsize("P") == 4 class Tag: @@ -47,7 +47,7 @@ class Tag: is also supported. """ - __slots__ = ["_interpreter", "_abi", "_platform", "_hash"] + __slots__ = ["_abi", "_hash", "_interpreter", "_platform"] def __init__(self, interpreter: str, abi: str, platform: str) -> None: self._interpreter = interpreter.lower() @@ -93,7 +93,7 @@ class Tag: return f"<{self} @ {id(self)}>" -def parse_tag(tag: str) -> FrozenSet[Tag]: +def parse_tag(tag: str) -> frozenset[Tag]: """ Parses the provided tag (e.g. `py3-none-any`) into a frozenset of Tag instances. @@ -109,8 +109,8 @@ def parse_tag(tag: str) -> FrozenSet[Tag]: return frozenset(tags) -def _get_config_var(name: str, warn: bool = False) -> Union[int, str, None]: - value = sysconfig.get_config_var(name) +def _get_config_var(name: str, warn: bool = False) -> int | str | None: + value: int | str | None = sysconfig.get_config_var(name) if value is None and warn: logger.debug( "Config variable '%s' is unset, Python ABI tag may be incorrect", name @@ -119,23 +119,40 @@ def _get_config_var(name: str, warn: bool = False) -> Union[int, str, None]: def _normalize_string(string: str) -> str: - return string.replace(".", "_").replace("-", "_") + return string.replace(".", "_").replace("-", "_").replace(" ", "_") -def _abi3_applies(python_version: PythonVersion) -> bool: +def _is_threaded_cpython(abis: list[str]) -> bool: + """ + Determine if the ABI corresponds to a threaded (`--disable-gil`) build. + + The threaded builds are indicated by a "t" in the abiflags. + """ + if len(abis) == 0: + return False + # expect e.g., cp313 + m = re.match(r"cp\d+(.*)", abis[0]) + if not m: + return False + abiflags = m.group(1) + return "t" in abiflags + + +def _abi3_applies(python_version: PythonVersion, threading: bool) -> bool: """ Determine if the Python version supports abi3. - PEP 384 was first implemented in Python 3.2. + PEP 384 was first implemented in Python 3.2. The threaded (`--disable-gil`) + builds do not support abi3. """ - return len(python_version) > 1 and tuple(python_version) >= (3, 2) + return len(python_version) > 1 and tuple(python_version) >= (3, 2) and not threading -def _cpython_abis(py_version: PythonVersion, warn: bool = False) -> List[str]: +def _cpython_abis(py_version: PythonVersion, warn: bool = False) -> list[str]: py_version = tuple(py_version) # To allow for version comparison. abis = [] version = _version_nodot(py_version[:2]) - debug = pymalloc = ucs4 = "" + threading = debug = pymalloc = ucs4 = "" with_debug = _get_config_var("Py_DEBUG", warn) has_refcount = hasattr(sys, "gettotalrefcount") # Windows doesn't set Py_DEBUG, so checking for support of debug-compiled @@ -144,6 +161,8 @@ def _cpython_abis(py_version: PythonVersion, warn: bool = False) -> List[str]: has_ext = "_d.pyd" in EXTENSION_SUFFIXES if with_debug or (with_debug is None and (has_refcount or has_ext)): debug = "d" + if py_version >= (3, 13) and _get_config_var("Py_GIL_DISABLED", warn): + threading = "t" if py_version < (3, 8): with_pymalloc = _get_config_var("WITH_PYMALLOC", warn) if with_pymalloc or with_pymalloc is None: @@ -157,20 +176,15 @@ def _cpython_abis(py_version: PythonVersion, warn: bool = False) -> List[str]: elif debug: # Debug builds can also load "normal" extension modules. # We can also assume no UCS-4 or pymalloc requirement. - abis.append(f"cp{version}") - abis.insert( - 0, - "cp{version}{debug}{pymalloc}{ucs4}".format( - version=version, debug=debug, pymalloc=pymalloc, ucs4=ucs4 - ), - ) + abis.append(f"cp{version}{threading}") + abis.insert(0, f"cp{version}{threading}{debug}{pymalloc}{ucs4}") return abis def cpython_tags( - python_version: Optional[PythonVersion] = None, - abis: Optional[Iterable[str]] = None, - platforms: Optional[Iterable[str]] = None, + python_version: PythonVersion | None = None, + abis: Iterable[str] | None = None, + platforms: Iterable[str] | None = None, *, warn: bool = False, ) -> Iterator[Tag]: @@ -211,29 +225,66 @@ def cpython_tags( for abi in abis: for platform_ in platforms: yield Tag(interpreter, abi, platform_) - if _abi3_applies(python_version): + + threading = _is_threaded_cpython(abis) + use_abi3 = _abi3_applies(python_version, threading) + if use_abi3: yield from (Tag(interpreter, "abi3", platform_) for platform_ in platforms) yield from (Tag(interpreter, "none", platform_) for platform_ in platforms) - if _abi3_applies(python_version): + if use_abi3: for minor_version in range(python_version[1] - 1, 1, -1): for platform_ in platforms: - interpreter = "cp{version}".format( - version=_version_nodot((python_version[0], minor_version)) - ) + version = _version_nodot((python_version[0], minor_version)) + interpreter = f"cp{version}" yield Tag(interpreter, "abi3", platform_) -def _generic_abi() -> Iterator[str]: - abi = sysconfig.get_config_var("SOABI") - if abi: - yield _normalize_string(abi) +def _generic_abi() -> list[str]: + """ + Return the ABI tag based on EXT_SUFFIX. + """ + # The following are examples of `EXT_SUFFIX`. + # We want to keep the parts which are related to the ABI and remove the + # parts which are related to the platform: + # - linux: '.cpython-310-x86_64-linux-gnu.so' => cp310 + # - mac: '.cpython-310-darwin.so' => cp310 + # - win: '.cp310-win_amd64.pyd' => cp310 + # - win: '.pyd' => cp37 (uses _cpython_abis()) + # - pypy: '.pypy38-pp73-x86_64-linux-gnu.so' => pypy38_pp73 + # - graalpy: '.graalpy-38-native-x86_64-darwin.dylib' + # => graalpy_38_native + + ext_suffix = _get_config_var("EXT_SUFFIX", warn=True) + if not isinstance(ext_suffix, str) or ext_suffix[0] != ".": + raise SystemError("invalid sysconfig.get_config_var('EXT_SUFFIX')") + parts = ext_suffix.split(".") + if len(parts) < 3: + # CPython3.7 and earlier uses ".pyd" on Windows. + return _cpython_abis(sys.version_info[:2]) + soabi = parts[1] + if soabi.startswith("cpython"): + # non-windows + abi = "cp" + soabi.split("-")[1] + elif soabi.startswith("cp"): + # windows + abi = soabi.split("-")[0] + elif soabi.startswith("pypy"): + abi = "-".join(soabi.split("-")[:2]) + elif soabi.startswith("graalpy"): + abi = "-".join(soabi.split("-")[:3]) + elif soabi: + # pyston, ironpython, others? + abi = soabi + else: + return [] + return [_normalize_string(abi)] def generic_tags( - interpreter: Optional[str] = None, - abis: Optional[Iterable[str]] = None, - platforms: Optional[Iterable[str]] = None, + interpreter: str | None = None, + abis: Iterable[str] | None = None, + platforms: Iterable[str] | None = None, *, warn: bool = False, ) -> Iterator[Tag]: @@ -251,8 +302,9 @@ def generic_tags( interpreter = "".join([interp_name, interp_version]) if abis is None: abis = _generic_abi() + else: + abis = list(abis) platforms = list(platforms or platform_tags()) - abis = list(abis) if "none" not in abis: abis.append("none") for abi in abis: @@ -276,9 +328,9 @@ def _py_interpreter_range(py_version: PythonVersion) -> Iterator[str]: def compatible_tags( - python_version: Optional[PythonVersion] = None, - interpreter: Optional[str] = None, - platforms: Optional[Iterable[str]] = None, + python_version: PythonVersion | None = None, + interpreter: str | None = None, + platforms: Iterable[str] | None = None, ) -> Iterator[Tag]: """ Yields the sequence of tags that are compatible with a specific version of Python. @@ -310,7 +362,7 @@ def _mac_arch(arch: str, is_32bit: bool = _32_BIT_INTERPRETER) -> str: return "i386" -def _mac_binary_formats(version: MacVersion, cpu_arch: str) -> List[str]: +def _mac_binary_formats(version: AppleVersion, cpu_arch: str) -> list[str]: formats = [cpu_arch] if cpu_arch == "x86_64": if version < (10, 4): @@ -343,7 +395,7 @@ def _mac_binary_formats(version: MacVersion, cpu_arch: str) -> List[str]: def mac_platforms( - version: Optional[MacVersion] = None, arch: Optional[str] = None + version: AppleVersion | None = None, arch: str | None = None ) -> Iterator[str]: """ Yields the platform tags for a macOS system. @@ -355,7 +407,23 @@ def mac_platforms( """ version_str, _, cpu_arch = platform.mac_ver() if version is None: - version = cast("MacVersion", tuple(map(int, version_str.split(".")[:2]))) + version = cast("AppleVersion", tuple(map(int, version_str.split(".")[:2]))) + if version == (10, 16): + # When built against an older macOS SDK, Python will report macOS 10.16 + # instead of the real version. + version_str = subprocess.run( + [ + sys.executable, + "-sS", + "-c", + "import platform; print(platform.mac_ver()[0])", + ], + check=True, + env={"SYSTEM_VERSION_COMPAT": "0"}, + stdout=subprocess.PIPE, + text=True, + ).stdout + version = cast("AppleVersion", tuple(map(int, version_str.split(".")[:2]))) else: version = version if arch is None: @@ -366,24 +434,22 @@ def mac_platforms( if (10, 0) <= version and version < (11, 0): # Prior to Mac OS 11, each yearly release of Mac OS bumped the # "minor" version number. The major version was always 10. + major_version = 10 for minor_version in range(version[1], -1, -1): - compat_version = 10, minor_version + compat_version = major_version, minor_version binary_formats = _mac_binary_formats(compat_version, arch) for binary_format in binary_formats: - yield "macosx_{major}_{minor}_{binary_format}".format( - major=10, minor=minor_version, binary_format=binary_format - ) + yield f"macosx_{major_version}_{minor_version}_{binary_format}" if version >= (11, 0): # Starting with Mac OS 11, each yearly release bumps the major version # number. The minor versions are now the midyear updates. + minor_version = 0 for major_version in range(version[0], 10, -1): - compat_version = major_version, 0 + compat_version = major_version, minor_version binary_formats = _mac_binary_formats(compat_version, arch) for binary_format in binary_formats: - yield "macosx_{major}_{minor}_{binary_format}".format( - major=major_version, minor=0, binary_format=binary_format - ) + yield f"macosx_{major_version}_{minor_version}_{binary_format}" if version >= (11, 0): # Mac OS 11 on x86_64 is compatible with binaries from previous releases. @@ -393,38 +459,94 @@ def mac_platforms( # However, the "universal2" binary format can have a # macOS version earlier than 11.0 when the x86_64 part of the binary supports # that version of macOS. + major_version = 10 if arch == "x86_64": for minor_version in range(16, 3, -1): - compat_version = 10, minor_version + compat_version = major_version, minor_version binary_formats = _mac_binary_formats(compat_version, arch) for binary_format in binary_formats: - yield "macosx_{major}_{minor}_{binary_format}".format( - major=compat_version[0], - minor=compat_version[1], - binary_format=binary_format, - ) + yield f"macosx_{major_version}_{minor_version}_{binary_format}" else: for minor_version in range(16, 3, -1): - compat_version = 10, minor_version + compat_version = major_version, minor_version binary_format = "universal2" - yield "macosx_{major}_{minor}_{binary_format}".format( - major=compat_version[0], - minor=compat_version[1], - binary_format=binary_format, - ) + yield f"macosx_{major_version}_{minor_version}_{binary_format}" + + +def ios_platforms( + version: AppleVersion | None = None, multiarch: str | None = None +) -> Iterator[str]: + """ + Yields the platform tags for an iOS system. + + :param version: A two-item tuple specifying the iOS version to generate + platform tags for. Defaults to the current iOS version. + :param multiarch: The CPU architecture+ABI to generate platform tags for - + (the value used by `sys.implementation._multiarch` e.g., + `arm64_iphoneos` or `x84_64_iphonesimulator`). Defaults to the current + multiarch value. + """ + if version is None: + # if iOS is the current platform, ios_ver *must* be defined. However, + # it won't exist for CPython versions before 3.13, which causes a mypy + # error. + _, release, _, _ = platform.ios_ver() # type: ignore[attr-defined, unused-ignore] + version = cast("AppleVersion", tuple(map(int, release.split(".")[:2]))) + + if multiarch is None: + multiarch = sys.implementation._multiarch + multiarch = multiarch.replace("-", "_") + + ios_platform_template = "ios_{major}_{minor}_{multiarch}" + + # Consider any iOS major.minor version from the version requested, down to + # 12.0. 12.0 is the first iOS version that is known to have enough features + # to support CPython. Consider every possible minor release up to X.9. There + # highest the minor has ever gone is 8 (14.8 and 15.8) but having some extra + # candidates that won't ever match doesn't really hurt, and it saves us from + # having to keep an explicit list of known iOS versions in the code. Return + # the results descending order of version number. + + # If the requested major version is less than 12, there won't be any matches. + if version[0] < 12: + return + + # Consider the actual X.Y version that was requested. + yield ios_platform_template.format( + major=version[0], minor=version[1], multiarch=multiarch + ) + + # Consider every minor version from X.0 to the minor version prior to the + # version requested by the platform. + for minor in range(version[1] - 1, -1, -1): + yield ios_platform_template.format( + major=version[0], minor=minor, multiarch=multiarch + ) + + for major in range(version[0] - 1, 11, -1): + for minor in range(9, -1, -1): + yield ios_platform_template.format( + major=major, minor=minor, multiarch=multiarch + ) def _linux_platforms(is_32bit: bool = _32_BIT_INTERPRETER) -> Iterator[str]: linux = _normalize_string(sysconfig.get_platform()) + if not linux.startswith("linux_"): + # we should never be here, just yield the sysconfig one and return + yield linux + return if is_32bit: if linux == "linux_x86_64": linux = "linux_i686" elif linux == "linux_aarch64": - linux = "linux_armv7l" + linux = "linux_armv8l" _, arch = linux.split("_", 1) - yield from _manylinux.platform_tags(linux, arch) - yield from _musllinux.platform_tags(arch) - yield linux + archs = {"armv8l": ["armv8l", "armv7l"]}.get(arch, [arch]) + yield from _manylinux.platform_tags(archs) + yield from _musllinux.platform_tags(archs) + for arch in archs: + yield f"linux_{arch}" def _generic_platforms() -> Iterator[str]: @@ -437,6 +559,8 @@ def platform_tags() -> Iterator[str]: """ if platform.system() == "Darwin": return mac_platforms() + elif platform.system() == "iOS": + return ios_platforms() elif platform.system() == "Linux": return _linux_platforms() else: @@ -446,6 +570,9 @@ def platform_tags() -> Iterator[str]: def interpreter_name() -> str: """ Returns the name of the running interpreter. + + Some implementations have a reserved, two-letter abbreviation which will + be returned when appropriate. """ name = sys.implementation.name return INTERPRETER_SHORT_NAMES.get(name) or name @@ -482,6 +609,9 @@ def sys_tags(*, warn: bool = False) -> Iterator[Tag]: yield from generic_tags() if interp_name == "pp": - yield from compatible_tags(interpreter="pp3") + interp = "pp3" + elif interp_name == "cp": + interp = "cp" + interpreter_version(warn=warn) else: - yield from compatible_tags() + interp = None + yield from compatible_tags(interpreter=interp) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/utils.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/utils.py index bab11b8..2345095 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/utils.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/utils.py @@ -2,16 +2,25 @@ # 2.0, and the BSD License. See the LICENSE file in the root of this repository # for complete details. +from __future__ import annotations + +import functools import re -from typing import FrozenSet, NewType, Tuple, Union, cast +from typing import NewType, Tuple, Union, cast from .tags import Tag, parse_tag -from .version import InvalidVersion, Version +from .version import InvalidVersion, Version, _TrimmedRelease BuildTag = Union[Tuple[()], Tuple[int, str]] NormalizedName = NewType("NormalizedName", str) +class InvalidName(ValueError): + """ + An invalid distribution name; users should refer to the packaging user guide. + """ + + class InvalidWheelFilename(ValueError): """ An invalid wheel filename was found, users should refer to PEP 427. @@ -24,88 +33,99 @@ class InvalidSdistFilename(ValueError): """ +# Core metadata spec for `Name` +_validate_regex = re.compile( + r"^([A-Z0-9]|[A-Z0-9][A-Z0-9._-]*[A-Z0-9])$", re.IGNORECASE +) _canonicalize_regex = re.compile(r"[-_.]+") +_normalized_regex = re.compile(r"^([a-z0-9]|[a-z0-9]([a-z0-9-](?!--))*[a-z0-9])$") # PEP 427: The build number must start with a digit. _build_tag_regex = re.compile(r"(\d+)(.*)") -def canonicalize_name(name: str) -> NormalizedName: +def canonicalize_name(name: str, *, validate: bool = False) -> NormalizedName: + if validate and not _validate_regex.match(name): + raise InvalidName(f"name is invalid: {name!r}") # This is taken from PEP 503. value = _canonicalize_regex.sub("-", name).lower() return cast(NormalizedName, value) -def canonicalize_version(version: Union[Version, str]) -> str: +def is_normalized_name(name: str) -> bool: + return _normalized_regex.match(name) is not None + + +@functools.singledispatch +def canonicalize_version( + version: Version | str, *, strip_trailing_zero: bool = True +) -> str: """ - This is very similar to Version.__str__, but has one subtle difference - with the way it handles the release segment. + Return a canonical form of a version as a string. + + >>> canonicalize_version('1.0.1') + '1.0.1' + + Per PEP 625, versions may have multiple canonical forms, differing + only by trailing zeros. + + >>> canonicalize_version('1.0.0') + '1' + >>> canonicalize_version('1.0.0', strip_trailing_zero=False) + '1.0.0' + + Invalid versions are returned unaltered. + + >>> canonicalize_version('foo bar baz') + 'foo bar baz' """ - if isinstance(version, str): - try: - parsed = Version(version) - except InvalidVersion: - # Legacy versions cannot be normalized - return version - else: - parsed = version + return str(_TrimmedRelease(str(version)) if strip_trailing_zero else version) - parts = [] - # Epoch - if parsed.epoch != 0: - parts.append(f"{parsed.epoch}!") - - # Release segment - # NB: This strips trailing '.0's to normalize - parts.append(re.sub(r"(\.0)+$", "", ".".join(str(x) for x in parsed.release))) - - # Pre-release - if parsed.pre is not None: - parts.append("".join(str(x) for x in parsed.pre)) - - # Post-release - if parsed.post is not None: - parts.append(f".post{parsed.post}") - - # Development release - if parsed.dev is not None: - parts.append(f".dev{parsed.dev}") - - # Local version segment - if parsed.local is not None: - parts.append(f"+{parsed.local}") - - return "".join(parts) +@canonicalize_version.register +def _(version: str, *, strip_trailing_zero: bool = True) -> str: + try: + parsed = Version(version) + except InvalidVersion: + # Legacy versions cannot be normalized + return version + return canonicalize_version(parsed, strip_trailing_zero=strip_trailing_zero) def parse_wheel_filename( filename: str, -) -> Tuple[NormalizedName, Version, BuildTag, FrozenSet[Tag]]: +) -> tuple[NormalizedName, Version, BuildTag, frozenset[Tag]]: if not filename.endswith(".whl"): raise InvalidWheelFilename( - f"Invalid wheel filename (extension must be '.whl'): {filename}" + f"Invalid wheel filename (extension must be '.whl'): {filename!r}" ) filename = filename[:-4] dashes = filename.count("-") if dashes not in (4, 5): raise InvalidWheelFilename( - f"Invalid wheel filename (wrong number of parts): {filename}" + f"Invalid wheel filename (wrong number of parts): {filename!r}" ) parts = filename.split("-", dashes - 2) name_part = parts[0] - # See PEP 427 for the rules on escaping the project name + # See PEP 427 for the rules on escaping the project name. if "__" in name_part or re.match(r"^[\w\d._]*$", name_part, re.UNICODE) is None: - raise InvalidWheelFilename(f"Invalid project name: {filename}") + raise InvalidWheelFilename(f"Invalid project name: {filename!r}") name = canonicalize_name(name_part) - version = Version(parts[1]) + + try: + version = Version(parts[1]) + except InvalidVersion as e: + raise InvalidWheelFilename( + f"Invalid wheel filename (invalid version): {filename!r}" + ) from e + if dashes == 5: build_part = parts[2] build_match = _build_tag_regex.match(build_part) if build_match is None: raise InvalidWheelFilename( - f"Invalid build number: {build_part} in '{filename}'" + f"Invalid build number: {build_part} in {filename!r}" ) build = cast(BuildTag, (int(build_match.group(1)), build_match.group(2))) else: @@ -114,7 +134,7 @@ def parse_wheel_filename( return (name, version, build, tags) -def parse_sdist_filename(filename: str) -> Tuple[NormalizedName, Version]: +def parse_sdist_filename(filename: str) -> tuple[NormalizedName, Version]: if filename.endswith(".tar.gz"): file_stem = filename[: -len(".tar.gz")] elif filename.endswith(".zip"): @@ -122,15 +142,22 @@ def parse_sdist_filename(filename: str) -> Tuple[NormalizedName, Version]: else: raise InvalidSdistFilename( f"Invalid sdist filename (extension must be '.tar.gz' or '.zip'):" - f" {filename}" + f" {filename!r}" ) # We are requiring a PEP 440 version, which cannot contain dashes, # so we split on the last dash. name_part, sep, version_part = file_stem.rpartition("-") if not sep: - raise InvalidSdistFilename(f"Invalid sdist filename: {filename}") + raise InvalidSdistFilename(f"Invalid sdist filename: {filename!r}") name = canonicalize_name(name_part) - version = Version(version_part) + + try: + version = Version(version_part) + except InvalidVersion as e: + raise InvalidSdistFilename( + f"Invalid sdist filename (invalid version): {filename!r}" + ) from e + return (name, version) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/version.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/version.py index de9a09a..21f44ca 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/version.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/packaging/version.py @@ -1,64 +1,73 @@ # This file is dual licensed under the terms of the Apache License, Version # 2.0, and the BSD License. See the LICENSE file in the root of this repository # for complete details. +""" +.. testsetup:: + + from pip._vendor.packaging.version import parse, Version +""" + +from __future__ import annotations -import collections import itertools import re -import warnings -from typing import Callable, Iterator, List, Optional, SupportsInt, Tuple, Union +from typing import Any, Callable, NamedTuple, SupportsInt, Tuple, Union from ._structures import Infinity, InfinityType, NegativeInfinity, NegativeInfinityType -__all__ = ["parse", "Version", "LegacyVersion", "InvalidVersion", "VERSION_PATTERN"] +__all__ = ["VERSION_PATTERN", "InvalidVersion", "Version", "parse"] -InfiniteTypes = Union[InfinityType, NegativeInfinityType] -PrePostDevType = Union[InfiniteTypes, Tuple[str, int]] -SubLocalType = Union[InfiniteTypes, int, str] -LocalType = Union[ +LocalType = Tuple[Union[int, str], ...] + +CmpPrePostDevType = Union[InfinityType, NegativeInfinityType, Tuple[str, int]] +CmpLocalType = Union[ NegativeInfinityType, - Tuple[ - Union[ - SubLocalType, - Tuple[SubLocalType, str], - Tuple[NegativeInfinityType, SubLocalType], - ], - ..., - ], + Tuple[Union[Tuple[int, str], Tuple[NegativeInfinityType, Union[int, str]]], ...], ] CmpKey = Tuple[ - int, Tuple[int, ...], PrePostDevType, PrePostDevType, PrePostDevType, LocalType + int, + Tuple[int, ...], + CmpPrePostDevType, + CmpPrePostDevType, + CmpPrePostDevType, + CmpLocalType, ] -LegacyCmpKey = Tuple[int, Tuple[str, ...]] -VersionComparisonMethod = Callable[ - [Union[CmpKey, LegacyCmpKey], Union[CmpKey, LegacyCmpKey]], bool -] - -_Version = collections.namedtuple( - "_Version", ["epoch", "release", "dev", "pre", "post", "local"] -) +VersionComparisonMethod = Callable[[CmpKey, CmpKey], bool] -def parse(version: str) -> Union["LegacyVersion", "Version"]: +class _Version(NamedTuple): + epoch: int + release: tuple[int, ...] + dev: tuple[str, int] | None + pre: tuple[str, int] | None + post: tuple[str, int] | None + local: LocalType | None + + +def parse(version: str) -> Version: + """Parse the given version string. + + >>> parse('1.0.dev1') + + + :param version: The version string to parse. + :raises InvalidVersion: When the version string is not a valid version. """ - Parse the given version string and return either a :class:`Version` object - or a :class:`LegacyVersion` object depending on if the given version is - a valid PEP 440 version or a legacy version. - """ - try: - return Version(version) - except InvalidVersion: - return LegacyVersion(version) + return Version(version) class InvalidVersion(ValueError): - """ - An invalid version was found, users should refer to PEP 440. + """Raised when a version string is not a valid version. + + >>> Version("invalid") + Traceback (most recent call last): + ... + packaging.version.InvalidVersion: Invalid version: 'invalid' """ class _BaseVersion: - _key: Union[CmpKey, LegacyCmpKey] + _key: tuple[Any, ...] def __hash__(self) -> int: return hash(self._key) @@ -66,13 +75,13 @@ class _BaseVersion: # Please keep the duplicated `isinstance` check # in the six comparisons hereunder # unless you find a way to avoid adding overhead function calls. - def __lt__(self, other: "_BaseVersion") -> bool: + def __lt__(self, other: _BaseVersion) -> bool: if not isinstance(other, _BaseVersion): return NotImplemented return self._key < other._key - def __le__(self, other: "_BaseVersion") -> bool: + def __le__(self, other: _BaseVersion) -> bool: if not isinstance(other, _BaseVersion): return NotImplemented @@ -84,13 +93,13 @@ class _BaseVersion: return self._key == other._key - def __ge__(self, other: "_BaseVersion") -> bool: + def __ge__(self, other: _BaseVersion) -> bool: if not isinstance(other, _BaseVersion): return NotImplemented return self._key >= other._key - def __gt__(self, other: "_BaseVersion") -> bool: + def __gt__(self, other: _BaseVersion) -> bool: if not isinstance(other, _BaseVersion): return NotImplemented @@ -103,133 +112,16 @@ class _BaseVersion: return self._key != other._key -class LegacyVersion(_BaseVersion): - def __init__(self, version: str) -> None: - self._version = str(version) - self._key = _legacy_cmpkey(self._version) - - warnings.warn( - "Creating a LegacyVersion has been deprecated and will be " - "removed in the next major release", - DeprecationWarning, - ) - - def __str__(self) -> str: - return self._version - - def __repr__(self) -> str: - return f"" - - @property - def public(self) -> str: - return self._version - - @property - def base_version(self) -> str: - return self._version - - @property - def epoch(self) -> int: - return -1 - - @property - def release(self) -> None: - return None - - @property - def pre(self) -> None: - return None - - @property - def post(self) -> None: - return None - - @property - def dev(self) -> None: - return None - - @property - def local(self) -> None: - return None - - @property - def is_prerelease(self) -> bool: - return False - - @property - def is_postrelease(self) -> bool: - return False - - @property - def is_devrelease(self) -> bool: - return False - - -_legacy_version_component_re = re.compile(r"(\d+ | [a-z]+ | \.| -)", re.VERBOSE) - -_legacy_version_replacement_map = { - "pre": "c", - "preview": "c", - "-": "final-", - "rc": "c", - "dev": "@", -} - - -def _parse_version_parts(s: str) -> Iterator[str]: - for part in _legacy_version_component_re.split(s): - part = _legacy_version_replacement_map.get(part, part) - - if not part or part == ".": - continue - - if part[:1] in "0123456789": - # pad for numeric comparison - yield part.zfill(8) - else: - yield "*" + part - - # ensure that alpha/beta/candidate are before final - yield "*final" - - -def _legacy_cmpkey(version: str) -> LegacyCmpKey: - - # We hardcode an epoch of -1 here. A PEP 440 version can only have a epoch - # greater than or equal to 0. This will effectively put the LegacyVersion, - # which uses the defacto standard originally implemented by setuptools, - # as before all PEP 440 versions. - epoch = -1 - - # This scheme is taken from pkg_resources.parse_version setuptools prior to - # it's adoption of the packaging library. - parts: List[str] = [] - for part in _parse_version_parts(version.lower()): - if part.startswith("*"): - # remove "-" before a prerelease tag - if part < "*final": - while parts and parts[-1] == "*final-": - parts.pop() - - # remove trailing zeros from each series of numeric parts - while parts and parts[-1] == "00000000": - parts.pop() - - parts.append(part) - - return epoch, tuple(parts) - - # Deliberately not anchored to the start and end of the string, to make it # easier for 3rd party code to reuse -VERSION_PATTERN = r""" +_VERSION_PATTERN = r""" v? (?: (?:(?P[0-9]+)!)? # epoch (?P[0-9]+(?:\.[0-9]+)*) # release segment (?P
                                          # pre-release
             [-_\.]?
-            (?P(a|b|c|rc|alpha|beta|pre|preview))
+            (?Palpha|a|beta|b|preview|pre|c|rc)
             [-_\.]?
             (?P[0-9]+)?
         )?
@@ -253,17 +145,61 @@ VERSION_PATTERN = r"""
     (?:\+(?P[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
 """
 
+VERSION_PATTERN = _VERSION_PATTERN
+"""
+A string containing the regular expression used to match a valid version.
+
+The pattern is not anchored at either end, and is intended for embedding in larger
+expressions (for example, matching a version number as part of a file name). The
+regular expression should be compiled with the ``re.VERBOSE`` and ``re.IGNORECASE``
+flags set.
+
+:meta hide-value:
+"""
+
 
 class Version(_BaseVersion):
+    """This class abstracts handling of a project's versions.
+
+    A :class:`Version` instance is comparison aware and can be compared and
+    sorted using the standard Python interfaces.
+
+    >>> v1 = Version("1.0a5")
+    >>> v2 = Version("1.0")
+    >>> v1
+    
+    >>> v2
+    
+    >>> v1 < v2
+    True
+    >>> v1 == v2
+    False
+    >>> v1 > v2
+    False
+    >>> v1 >= v2
+    False
+    >>> v1 <= v2
+    True
+    """
 
     _regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE)
+    _key: CmpKey
 
     def __init__(self, version: str) -> None:
+        """Initialize a Version object.
+
+        :param version:
+            The string representation of a version which will be parsed and normalized
+            before use.
+        :raises InvalidVersion:
+            If the ``version`` does not conform to PEP 440 in any way then this
+            exception will be raised.
+        """
 
         # Validate the version and parse it into pieces
         match = self._regex.search(version)
         if not match:
-            raise InvalidVersion(f"Invalid version: '{version}'")
+            raise InvalidVersion(f"Invalid version: {version!r}")
 
         # Store the parsed out pieces of the version
         self._version = _Version(
@@ -288,9 +224,19 @@ class Version(_BaseVersion):
         )
 
     def __repr__(self) -> str:
+        """A representation of the Version that shows all internal state.
+
+        >>> Version('1.0.0')
+        
+        """
         return f""
 
     def __str__(self) -> str:
+        """A string representation of the version that can be round-tripped.
+
+        >>> str(Version("1.0a5"))
+        '1.0a5'
+        """
         parts = []
 
         # Epoch
@@ -320,29 +266,77 @@ class Version(_BaseVersion):
 
     @property
     def epoch(self) -> int:
-        _epoch: int = self._version.epoch
-        return _epoch
+        """The epoch of the version.
+
+        >>> Version("2.0.0").epoch
+        0
+        >>> Version("1!2.0.0").epoch
+        1
+        """
+        return self._version.epoch
 
     @property
-    def release(self) -> Tuple[int, ...]:
-        _release: Tuple[int, ...] = self._version.release
-        return _release
+    def release(self) -> tuple[int, ...]:
+        """The components of the "release" segment of the version.
+
+        >>> Version("1.2.3").release
+        (1, 2, 3)
+        >>> Version("2.0.0").release
+        (2, 0, 0)
+        >>> Version("1!2.0.0.post0").release
+        (2, 0, 0)
+
+        Includes trailing zeroes but not the epoch or any pre-release / development /
+        post-release suffixes.
+        """
+        return self._version.release
 
     @property
-    def pre(self) -> Optional[Tuple[str, int]]:
-        _pre: Optional[Tuple[str, int]] = self._version.pre
-        return _pre
+    def pre(self) -> tuple[str, int] | None:
+        """The pre-release segment of the version.
+
+        >>> print(Version("1.2.3").pre)
+        None
+        >>> Version("1.2.3a1").pre
+        ('a', 1)
+        >>> Version("1.2.3b1").pre
+        ('b', 1)
+        >>> Version("1.2.3rc1").pre
+        ('rc', 1)
+        """
+        return self._version.pre
 
     @property
-    def post(self) -> Optional[int]:
+    def post(self) -> int | None:
+        """The post-release number of the version.
+
+        >>> print(Version("1.2.3").post)
+        None
+        >>> Version("1.2.3.post1").post
+        1
+        """
         return self._version.post[1] if self._version.post else None
 
     @property
-    def dev(self) -> Optional[int]:
+    def dev(self) -> int | None:
+        """The development number of the version.
+
+        >>> print(Version("1.2.3").dev)
+        None
+        >>> Version("1.2.3.dev1").dev
+        1
+        """
         return self._version.dev[1] if self._version.dev else None
 
     @property
-    def local(self) -> Optional[str]:
+    def local(self) -> str | None:
+        """The local version segment of the version.
+
+        >>> print(Version("1.2.3").local)
+        None
+        >>> Version("1.2.3+abc").local
+        'abc'
+        """
         if self._version.local:
             return ".".join(str(x) for x in self._version.local)
         else:
@@ -350,10 +344,31 @@ class Version(_BaseVersion):
 
     @property
     def public(self) -> str:
+        """The public portion of the version.
+
+        >>> Version("1.2.3").public
+        '1.2.3'
+        >>> Version("1.2.3+abc").public
+        '1.2.3'
+        >>> Version("1!1.2.3dev1+abc").public
+        '1!1.2.3.dev1'
+        """
         return str(self).split("+", 1)[0]
 
     @property
     def base_version(self) -> str:
+        """The "base version" of the version.
+
+        >>> Version("1.2.3").base_version
+        '1.2.3'
+        >>> Version("1.2.3+abc").base_version
+        '1.2.3'
+        >>> Version("1!1.2.3dev1+abc").base_version
+        '1!1.2.3'
+
+        The "base version" is the public version of the project without any pre or post
+        release markers.
+        """
         parts = []
 
         # Epoch
@@ -367,33 +382,95 @@ class Version(_BaseVersion):
 
     @property
     def is_prerelease(self) -> bool:
+        """Whether this version is a pre-release.
+
+        >>> Version("1.2.3").is_prerelease
+        False
+        >>> Version("1.2.3a1").is_prerelease
+        True
+        >>> Version("1.2.3b1").is_prerelease
+        True
+        >>> Version("1.2.3rc1").is_prerelease
+        True
+        >>> Version("1.2.3dev1").is_prerelease
+        True
+        """
         return self.dev is not None or self.pre is not None
 
     @property
     def is_postrelease(self) -> bool:
+        """Whether this version is a post-release.
+
+        >>> Version("1.2.3").is_postrelease
+        False
+        >>> Version("1.2.3.post1").is_postrelease
+        True
+        """
         return self.post is not None
 
     @property
     def is_devrelease(self) -> bool:
+        """Whether this version is a development release.
+
+        >>> Version("1.2.3").is_devrelease
+        False
+        >>> Version("1.2.3.dev1").is_devrelease
+        True
+        """
         return self.dev is not None
 
     @property
     def major(self) -> int:
+        """The first item of :attr:`release` or ``0`` if unavailable.
+
+        >>> Version("1.2.3").major
+        1
+        """
         return self.release[0] if len(self.release) >= 1 else 0
 
     @property
     def minor(self) -> int:
+        """The second item of :attr:`release` or ``0`` if unavailable.
+
+        >>> Version("1.2.3").minor
+        2
+        >>> Version("1").minor
+        0
+        """
         return self.release[1] if len(self.release) >= 2 else 0
 
     @property
     def micro(self) -> int:
+        """The third item of :attr:`release` or ``0`` if unavailable.
+
+        >>> Version("1.2.3").micro
+        3
+        >>> Version("1").micro
+        0
+        """
         return self.release[2] if len(self.release) >= 3 else 0
 
 
-def _parse_letter_version(
-    letter: str, number: Union[str, bytes, SupportsInt]
-) -> Optional[Tuple[str, int]]:
+class _TrimmedRelease(Version):
+    @property
+    def release(self) -> tuple[int, ...]:
+        """
+        Release segment without any trailing zeros.
 
+        >>> _TrimmedRelease('1.0.0').release
+        (1,)
+        >>> _TrimmedRelease('0.0').release
+        (0,)
+        """
+        rel = super().release
+        nonzeros = (index for index, val in enumerate(rel) if val)
+        last_nonzero = max(nonzeros, default=0)
+        return rel[: last_nonzero + 1]
+
+
+def _parse_letter_version(
+    letter: str | None, number: str | bytes | SupportsInt | None
+) -> tuple[str, int] | None:
     if letter:
         # We consider there to be an implicit 0 in a pre-release if there is
         # not a numeral associated with it.
@@ -416,7 +493,9 @@ def _parse_letter_version(
             letter = "post"
 
         return letter, int(number)
-    if not letter and number:
+
+    assert not letter
+    if number:
         # We assume if we are given a number, but we are not given a letter
         # then this is using the implicit post release syntax (e.g. 1.0-1)
         letter = "post"
@@ -429,7 +508,7 @@ def _parse_letter_version(
 _local_version_separators = re.compile(r"[\._-]")
 
 
-def _parse_local_version(local: str) -> Optional[LocalType]:
+def _parse_local_version(local: str | None) -> LocalType | None:
     """
     Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
     """
@@ -443,13 +522,12 @@ def _parse_local_version(local: str) -> Optional[LocalType]:
 
 def _cmpkey(
     epoch: int,
-    release: Tuple[int, ...],
-    pre: Optional[Tuple[str, int]],
-    post: Optional[Tuple[str, int]],
-    dev: Optional[Tuple[str, int]],
-    local: Optional[Tuple[SubLocalType]],
+    release: tuple[int, ...],
+    pre: tuple[str, int] | None,
+    post: tuple[str, int] | None,
+    dev: tuple[str, int] | None,
+    local: LocalType | None,
 ) -> CmpKey:
-
     # When we compare a release version, we want to compare it with all of the
     # trailing zeros removed. So we'll use a reverse the list, drop all the now
     # leading zeros until we come to something non zero, then take the rest
@@ -464,7 +542,7 @@ def _cmpkey(
     # if there is not a pre or a post segment. If we have one of those then
     # the normal sorting rules will handle this case correctly.
     if pre is None and post is None and dev is not None:
-        _pre: PrePostDevType = NegativeInfinity
+        _pre: CmpPrePostDevType = NegativeInfinity
     # Versions without a pre-release (except as noted above) should sort after
     # those with one.
     elif pre is None:
@@ -474,21 +552,21 @@ def _cmpkey(
 
     # Versions without a post segment should sort before those with one.
     if post is None:
-        _post: PrePostDevType = NegativeInfinity
+        _post: CmpPrePostDevType = NegativeInfinity
 
     else:
         _post = post
 
     # Versions without a development segment should sort after those with one.
     if dev is None:
-        _dev: PrePostDevType = Infinity
+        _dev: CmpPrePostDevType = Infinity
 
     else:
         _dev = dev
 
     if local is None:
         # Versions without a local segment should sort before those with one.
-        _local: LocalType = NegativeInfinity
+        _local: CmpLocalType = NegativeInfinity
     else:
         # Versions with a local segment need that segment parsed to implement
         # the sorting rules in PEP440.
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__init__.py
index ad27940..57ce7f1 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__init__.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__init__.py
@@ -1,3 +1,6 @@
+# TODO: Add Generic type annotations to initialized collections.
+# For now we'd simply use implicit Any/Unknown which would add redundant annotations
+# mypy: disable-error-code="var-annotated"
 """
 Package resource API
 --------------------
@@ -17,12 +20,36 @@ This module is deprecated. Users are directed to :mod:`importlib.resources`,
 :mod:`importlib.metadata` and :pypi:`packaging` instead.
 """
 
+from __future__ import annotations
+
 import sys
+
+if sys.version_info < (3, 8):  # noqa: UP036 # Check for unsupported versions
+    raise RuntimeError("Python 3.8 or later is required")
+
 import os
 import io
 import time
 import re
 import types
+from typing import (
+    Any,
+    Literal,
+    Dict,
+    Iterator,
+    Mapping,
+    MutableSequence,
+    NamedTuple,
+    NoReturn,
+    Tuple,
+    Union,
+    TYPE_CHECKING,
+    Protocol,
+    Callable,
+    Iterable,
+    TypeVar,
+    overload,
+)
 import zipfile
 import zipimport
 import warnings
@@ -41,21 +68,16 @@ import inspect
 import ntpath
 import posixpath
 import importlib
+import importlib.abc
+import importlib.machinery
 from pkgutil import get_importer
 
-try:
-    import _imp
-except ImportError:
-    # Python 3.2 compatibility
-    import imp as _imp
-
-try:
-    FileExistsError
-except NameError:
-    FileExistsError = OSError
+import _imp
 
 # capture these to bypass sandboxing
 from os import utime
+from os import open as os_open
+from os.path import isdir, split
 
 try:
     from os import mkdir, rename, unlink
@@ -65,64 +87,59 @@ except ImportError:
     # no write support, probably under GAE
     WRITE_SUPPORT = False
 
-from os import open as os_open
-from os.path import isdir, split
-
-try:
-    import importlib.machinery as importlib_machinery
-
-    # access attribute to force import under delayed import mechanisms.
-    importlib_machinery.__name__
-except ImportError:
-    importlib_machinery = None
-
 from pip._internal.utils._jaraco_text import (
     yield_lines,
     drop_comment,
     join_continuation,
 )
+from pip._vendor.packaging import markers as _packaging_markers
+from pip._vendor.packaging import requirements as _packaging_requirements
+from pip._vendor.packaging import utils as _packaging_utils
+from pip._vendor.packaging import version as _packaging_version
+from pip._vendor.platformdirs import user_cache_dir as _user_cache_dir
 
-from pip._vendor import platformdirs
-from pip._vendor import packaging
-
-__import__('pip._vendor.packaging.version')
-__import__('pip._vendor.packaging.specifiers')
-__import__('pip._vendor.packaging.requirements')
-__import__('pip._vendor.packaging.markers')
-__import__('pip._vendor.packaging.utils')
-
-if sys.version_info < (3, 5):
-    raise RuntimeError("Python 3.5 or later is required")
-
-# declare some globals that will be defined later to
-# satisfy the linters.
-require = None
-working_set = None
-add_activation_listener = None
-resources_stream = None
-cleanup_resources = None
-resource_dir = None
-resource_stream = None
-set_extraction_path = None
-resource_isdir = None
-resource_string = None
-iter_entry_points = None
-resource_listdir = None
-resource_filename = None
-resource_exists = None
-_distribution_finders = None
-_namespace_handlers = None
-_namespace_packages = None
+if TYPE_CHECKING:
+    from _typeshed import BytesPath, StrPath, StrOrBytesPath
+    from pip._vendor.typing_extensions import Self
 
 
-warnings.warn(
-    "pkg_resources is deprecated as an API. "
-    "See https://setuptools.pypa.io/en/latest/pkg_resources.html",
-    DeprecationWarning,
-    stacklevel=2
+# Patch: Remove deprecation warning from vendored pkg_resources.
+# Setting PYTHONWARNINGS=error to verify builds produce no warnings
+# causes immediate exceptions.
+# See https://github.com/pypa/pip/issues/12243
+
+
+_T = TypeVar("_T")
+_DistributionT = TypeVar("_DistributionT", bound="Distribution")
+# Type aliases
+_NestedStr = Union[str, Iterable[Union[str, Iterable["_NestedStr"]]]]
+_InstallerTypeT = Callable[["Requirement"], "_DistributionT"]
+_InstallerType = Callable[["Requirement"], Union["Distribution", None]]
+_PkgReqType = Union[str, "Requirement"]
+_EPDistType = Union["Distribution", _PkgReqType]
+_MetadataType = Union["IResourceProvider", None]
+_ResolvedEntryPoint = Any  # Can be any attribute in the module
+_ResourceStream = Any  # TODO / Incomplete: A readable file-like object
+# Any object works, but let's indicate we expect something like a module (optionally has __loader__ or __file__)
+_ModuleLike = Union[object, types.ModuleType]
+# Any: Should be _ModuleLike but we end up with issues where _ModuleLike doesn't have _ZipLoaderModule's __loader__
+_ProviderFactoryType = Callable[[Any], "IResourceProvider"]
+_DistFinderType = Callable[[_T, str, bool], Iterable["Distribution"]]
+_NSHandlerType = Callable[[_T, str, str, types.ModuleType], Union[str, None]]
+_AdapterT = TypeVar(
+    "_AdapterT", _DistFinderType[Any], _ProviderFactoryType, _NSHandlerType[Any]
 )
 
 
+# Use _typeshed.importlib.LoaderProtocol once available https://github.com/python/typeshed/pull/11890
+class _LoaderProtocol(Protocol):
+    def load_module(self, fullname: str, /) -> types.ModuleType: ...
+
+
+class _ZipLoaderModule(Protocol):
+    __loader__: zipimport.zipimporter
+
+
 _PEP440_FALLBACK = re.compile(r"^v?(?P(?:[0-9]+!)?[0-9]+(?:\.[0-9]+)*)", re.I)
 
 
@@ -133,18 +150,18 @@ class PEP440Warning(RuntimeWarning):
     """
 
 
-parse_version = packaging.version.Version
+parse_version = _packaging_version.Version
 
 
-_state_vars = {}
+_state_vars: dict[str, str] = {}
 
 
-def _declare_state(vartype, **kw):
-    globals().update(kw)
-    _state_vars.update(dict.fromkeys(kw, vartype))
+def _declare_state(vartype: str, varname: str, initial_value: _T) -> _T:
+    _state_vars[varname] = vartype
+    return initial_value
 
 
-def __getstate__():
+def __getstate__() -> dict[str, Any]:
     state = {}
     g = globals()
     for k, v in _state_vars.items():
@@ -152,7 +169,7 @@ def __getstate__():
     return state
 
 
-def __setstate__(state):
+def __setstate__(state: dict[str, Any]) -> dict[str, Any]:
     g = globals()
     for k, v in state.items():
         g['_sset_' + _state_vars[k]](k, g[k], v)
@@ -307,17 +324,17 @@ class VersionConflict(ResolutionError):
     _template = "{self.dist} is installed but {self.req} is required"
 
     @property
-    def dist(self):
+    def dist(self) -> Distribution:
         return self.args[0]
 
     @property
-    def req(self):
+    def req(self) -> Requirement:
         return self.args[1]
 
     def report(self):
         return self._template.format(**locals())
 
-    def with_context(self, required_by):
+    def with_context(self, required_by: set[Distribution | str]):
         """
         If required_by is non-empty, return a version of self that is a
         ContextualVersionConflict.
@@ -337,7 +354,7 @@ class ContextualVersionConflict(VersionConflict):
     _template = VersionConflict._template + ' by {self.required_by}'
 
     @property
-    def required_by(self):
+    def required_by(self) -> set[str]:
         return self.args[2]
 
 
@@ -350,11 +367,11 @@ class DistributionNotFound(ResolutionError):
     )
 
     @property
-    def req(self):
+    def req(self) -> Requirement:
         return self.args[0]
 
     @property
-    def requirers(self):
+    def requirers(self) -> set[str] | None:
         return self.args[1]
 
     @property
@@ -374,7 +391,7 @@ class UnknownExtra(ResolutionError):
     """Distribution doesn't have an "extra feature" of the given name"""
 
 
-_provider_factories = {}
+_provider_factories: dict[type[_ModuleLike], _ProviderFactoryType] = {}
 
 PY_MAJOR = '{}.{}'.format(*sys.version_info)
 EGG_DIST = 3
@@ -384,7 +401,9 @@ CHECKOUT_DIST = 0
 DEVELOP_DIST = -1
 
 
-def register_loader_type(loader_type, provider_factory):
+def register_loader_type(
+    loader_type: type[_ModuleLike], provider_factory: _ProviderFactoryType
+):
     """Register `provider_factory` to make providers for `loader_type`
 
     `loader_type` is the type or class of a PEP 302 ``module.__loader__``,
@@ -394,7 +413,11 @@ def register_loader_type(loader_type, provider_factory):
     _provider_factories[loader_type] = provider_factory
 
 
-def get_provider(moduleOrReq):
+@overload
+def get_provider(moduleOrReq: str) -> IResourceProvider: ...
+@overload
+def get_provider(moduleOrReq: Requirement) -> Distribution: ...
+def get_provider(moduleOrReq: str | Requirement) -> IResourceProvider | Distribution:
     """Return an IResourceProvider for the named module or requirement"""
     if isinstance(moduleOrReq, Requirement):
         return working_set.find(moduleOrReq) or require(str(moduleOrReq))[0]
@@ -407,20 +430,18 @@ def get_provider(moduleOrReq):
     return _find_adapter(_provider_factories, loader)(module)
 
 
-def _macos_vers(_cache=[]):
-    if not _cache:
-        version = platform.mac_ver()[0]
-        # fallback for MacPorts
-        if version == '':
-            plist = '/System/Library/CoreServices/SystemVersion.plist'
-            if os.path.exists(plist):
-                if hasattr(plistlib, 'readPlist'):
-                    plist_content = plistlib.readPlist(plist)
-                    if 'ProductVersion' in plist_content:
-                        version = plist_content['ProductVersion']
-
-        _cache.append(version.split('.'))
-    return _cache[0]
+@functools.lru_cache(maxsize=None)
+def _macos_vers():
+    version = platform.mac_ver()[0]
+    # fallback for MacPorts
+    if version == '':
+        plist = '/System/Library/CoreServices/SystemVersion.plist'
+        if os.path.exists(plist):
+            with open(plist, 'rb') as fh:
+                plist_content = plistlib.load(fh)
+            if 'ProductVersion' in plist_content:
+                version = plist_content['ProductVersion']
+    return version.split('.')
 
 
 def _macos_arch(machine):
@@ -458,7 +479,7 @@ darwinVersionString = re.compile(r"darwin-(\d+)\.(\d+)\.(\d+)-(.*)")
 get_platform = get_build_platform
 
 
-def compatible_platforms(provided, required):
+def compatible_platforms(provided: str | None, required: str | None):
     """Can code for the `provided` platform run on the `required` platform?
 
     Returns true if either platform is ``None``, or the platforms are equal.
@@ -507,102 +528,106 @@ def compatible_platforms(provided, required):
     return False
 
 
-def run_script(dist_spec, script_name):
-    """Locate distribution `dist_spec` and run its `script_name` script"""
-    ns = sys._getframe(1).f_globals
-    name = ns['__name__']
-    ns.clear()
-    ns['__name__'] = name
-    require(dist_spec)[0].run_script(script_name, ns)
-
-
-# backward compatibility
-run_main = run_script
-
-
-def get_distribution(dist):
+@overload
+def get_distribution(dist: _DistributionT) -> _DistributionT: ...
+@overload
+def get_distribution(dist: _PkgReqType) -> Distribution: ...
+def get_distribution(dist: Distribution | _PkgReqType) -> Distribution:
     """Return a current distribution object for a Requirement or string"""
     if isinstance(dist, str):
         dist = Requirement.parse(dist)
     if isinstance(dist, Requirement):
-        dist = get_provider(dist)
+        # Bad type narrowing, dist has to be a Requirement here, so get_provider has to return Distribution
+        dist = get_provider(dist)  # type: ignore[assignment]
     if not isinstance(dist, Distribution):
-        raise TypeError("Expected string, Requirement, or Distribution", dist)
+        raise TypeError("Expected str, Requirement, or Distribution", dist)
     return dist
 
 
-def load_entry_point(dist, group, name):
+def load_entry_point(dist: _EPDistType, group: str, name: str) -> _ResolvedEntryPoint:
     """Return `name` entry point of `group` for `dist` or raise ImportError"""
     return get_distribution(dist).load_entry_point(group, name)
 
 
-def get_entry_map(dist, group=None):
+@overload
+def get_entry_map(
+    dist: _EPDistType, group: None = None
+) -> dict[str, dict[str, EntryPoint]]: ...
+@overload
+def get_entry_map(dist: _EPDistType, group: str) -> dict[str, EntryPoint]: ...
+def get_entry_map(dist: _EPDistType, group: str | None = None):
     """Return the entry point map for `group`, or the full entry map"""
     return get_distribution(dist).get_entry_map(group)
 
 
-def get_entry_info(dist, group, name):
+def get_entry_info(dist: _EPDistType, group: str, name: str):
     """Return the EntryPoint object for `group`+`name`, or ``None``"""
     return get_distribution(dist).get_entry_info(group, name)
 
 
-class IMetadataProvider:
-    def has_metadata(name):
+class IMetadataProvider(Protocol):
+    def has_metadata(self, name: str) -> bool:
         """Does the package's distribution contain the named metadata?"""
 
-    def get_metadata(name):
+    def get_metadata(self, name: str) -> str:
         """The named metadata resource as a string"""
 
-    def get_metadata_lines(name):
+    def get_metadata_lines(self, name: str) -> Iterator[str]:
         """Yield named metadata resource as list of non-blank non-comment lines
 
         Leading and trailing whitespace is stripped from each line, and lines
         with ``#`` as the first non-blank character are omitted."""
 
-    def metadata_isdir(name):
+    def metadata_isdir(self, name: str) -> bool:
         """Is the named metadata a directory?  (like ``os.path.isdir()``)"""
 
-    def metadata_listdir(name):
+    def metadata_listdir(self, name: str) -> list[str]:
         """List of metadata names in the directory (like ``os.listdir()``)"""
 
-    def run_script(script_name, namespace):
+    def run_script(self, script_name: str, namespace: dict[str, Any]) -> None:
         """Execute the named script in the supplied namespace dictionary"""
 
 
-class IResourceProvider(IMetadataProvider):
+class IResourceProvider(IMetadataProvider, Protocol):
     """An object that provides access to package resources"""
 
-    def get_resource_filename(manager, resource_name):
+    def get_resource_filename(
+        self, manager: ResourceManager, resource_name: str
+    ) -> str:
         """Return a true filesystem path for `resource_name`
 
-        `manager` must be an ``IResourceManager``"""
+        `manager` must be a ``ResourceManager``"""
 
-    def get_resource_stream(manager, resource_name):
+    def get_resource_stream(
+        self, manager: ResourceManager, resource_name: str
+    ) -> _ResourceStream:
         """Return a readable file-like object for `resource_name`
 
-        `manager` must be an ``IResourceManager``"""
+        `manager` must be a ``ResourceManager``"""
 
-    def get_resource_string(manager, resource_name):
-        """Return a string containing the contents of `resource_name`
+    def get_resource_string(
+        self, manager: ResourceManager, resource_name: str
+    ) -> bytes:
+        """Return the contents of `resource_name` as :obj:`bytes`
 
-        `manager` must be an ``IResourceManager``"""
+        `manager` must be a ``ResourceManager``"""
 
-    def has_resource(resource_name):
+    def has_resource(self, resource_name: str) -> bool:
         """Does the package contain the named resource?"""
 
-    def resource_isdir(resource_name):
+    def resource_isdir(self, resource_name: str) -> bool:
         """Is the named resource a directory?  (like ``os.path.isdir()``)"""
 
-    def resource_listdir(resource_name):
+    def resource_listdir(self, resource_name: str) -> list[str]:
         """List of resource names in the directory (like ``os.listdir()``)"""
 
 
 class WorkingSet:
     """A collection of active distributions on sys.path (or a similar list)"""
 
-    def __init__(self, entries=None):
+    def __init__(self, entries: Iterable[str] | None = None):
         """Create working set from list of path entries (default=sys.path)"""
-        self.entries = []
+        self.entries: list[str] = []
         self.entry_keys = {}
         self.by_key = {}
         self.normalized_to_canonical_keys = {}
@@ -656,7 +681,7 @@ class WorkingSet:
         sys.path[:] = ws.entries
         return ws
 
-    def add_entry(self, entry):
+    def add_entry(self, entry: str):
         """Add a path item to ``.entries``, finding any distributions on it
 
         ``find_distributions(entry, True)`` is used to find distributions
@@ -671,11 +696,11 @@ class WorkingSet:
         for dist in find_distributions(entry, True):
             self.add(dist, entry, False)
 
-    def __contains__(self, dist):
+    def __contains__(self, dist: Distribution) -> bool:
         """True if `dist` is the active distribution for its project"""
         return self.by_key.get(dist.key) == dist
 
-    def find(self, req):
+    def find(self, req: Requirement) -> Distribution | None:
         """Find a distribution matching requirement `req`
 
         If there is an active distribution for the requested project, this
@@ -699,7 +724,7 @@ class WorkingSet:
             raise VersionConflict(dist, req)
         return dist
 
-    def iter_entry_points(self, group, name=None):
+    def iter_entry_points(self, group: str, name: str | None = None):
         """Yield entry point objects from `group` matching `name`
 
         If `name` is None, yields all entry points in `group` from all
@@ -713,7 +738,7 @@ class WorkingSet:
             if name is None or name == entry.name
         )
 
-    def run_script(self, requires, script_name):
+    def run_script(self, requires: str, script_name: str):
         """Locate distribution for `requires` and run `script_name` script"""
         ns = sys._getframe(1).f_globals
         name = ns['__name__']
@@ -721,13 +746,13 @@ class WorkingSet:
         ns['__name__'] = name
         self.require(requires)[0].run_script(script_name, ns)
 
-    def __iter__(self):
+    def __iter__(self) -> Iterator[Distribution]:
         """Yield distributions for non-duplicate projects in the working set
 
         The yield order is the order in which the items' path entries were
         added to the working set.
         """
-        seen = {}
+        seen = set()
         for item in self.entries:
             if item not in self.entry_keys:
                 # workaround a cache issue
@@ -735,10 +760,16 @@ class WorkingSet:
 
             for key in self.entry_keys[item]:
                 if key not in seen:
-                    seen[key] = 1
+                    seen.add(key)
                     yield self.by_key[key]
 
-    def add(self, dist, entry=None, insert=True, replace=False):
+    def add(
+        self,
+        dist: Distribution,
+        entry: str | None = None,
+        insert: bool = True,
+        replace: bool = False,
+    ):
         """Add `dist` to working set, associated with `entry`
 
         If `entry` is unspecified, it defaults to the ``.location`` of `dist`.
@@ -762,7 +793,7 @@ class WorkingSet:
             return
 
         self.by_key[dist.key] = dist
-        normalized_name = packaging.utils.canonicalize_name(dist.key)
+        normalized_name = _packaging_utils.canonicalize_name(dist.key)
         self.normalized_to_canonical_keys[normalized_name] = dist.key
         if dist.key not in keys:
             keys.append(dist.key)
@@ -770,14 +801,42 @@ class WorkingSet:
             keys2.append(dist.key)
         self._added_new(dist)
 
+    @overload
     def resolve(
         self,
-        requirements,
-        env=None,
-        installer=None,
-        replace_conflicting=False,
-        extras=None,
-    ):
+        requirements: Iterable[Requirement],
+        env: Environment | None,
+        installer: _InstallerTypeT[_DistributionT],
+        replace_conflicting: bool = False,
+        extras: tuple[str, ...] | None = None,
+    ) -> list[_DistributionT]: ...
+    @overload
+    def resolve(
+        self,
+        requirements: Iterable[Requirement],
+        env: Environment | None = None,
+        *,
+        installer: _InstallerTypeT[_DistributionT],
+        replace_conflicting: bool = False,
+        extras: tuple[str, ...] | None = None,
+    ) -> list[_DistributionT]: ...
+    @overload
+    def resolve(
+        self,
+        requirements: Iterable[Requirement],
+        env: Environment | None = None,
+        installer: _InstallerType | None = None,
+        replace_conflicting: bool = False,
+        extras: tuple[str, ...] | None = None,
+    ) -> list[Distribution]: ...
+    def resolve(
+        self,
+        requirements: Iterable[Requirement],
+        env: Environment | None = None,
+        installer: _InstallerType | None | _InstallerTypeT[_DistributionT] = None,
+        replace_conflicting: bool = False,
+        extras: tuple[str, ...] | None = None,
+    ) -> list[Distribution] | list[_DistributionT]:
         """List all distributions needed to (recursively) meet `requirements`
 
         `requirements` must be a sequence of ``Requirement`` objects.  `env`,
@@ -805,7 +864,7 @@ class WorkingSet:
         # set up the stack
         requirements = list(requirements)[::-1]
         # set of processed requirements
-        processed = {}
+        processed = set()
         # key -> dist
         best = {}
         to_activate = []
@@ -839,14 +898,14 @@ class WorkingSet:
                 required_by[new_requirement].add(req.project_name)
                 req_extras[new_requirement] = req.extras
 
-            processed[req] = True
+            processed.add(req)
 
         # return list of distros to activate
         return to_activate
 
     def _resolve_dist(
         self, req, best, replace_conflicting, env, installer, required_by, to_activate
-    ):
+    ) -> Distribution:
         dist = best.get(req.key)
         if dist is None:
             # Find the best distribution and add it to the map
@@ -875,7 +934,41 @@ class WorkingSet:
             raise VersionConflict(dist, req).with_context(dependent_req)
         return dist
 
-    def find_plugins(self, plugin_env, full_env=None, installer=None, fallback=True):
+    @overload
+    def find_plugins(
+        self,
+        plugin_env: Environment,
+        full_env: Environment | None,
+        installer: _InstallerTypeT[_DistributionT],
+        fallback: bool = True,
+    ) -> tuple[list[_DistributionT], dict[Distribution, Exception]]: ...
+    @overload
+    def find_plugins(
+        self,
+        plugin_env: Environment,
+        full_env: Environment | None = None,
+        *,
+        installer: _InstallerTypeT[_DistributionT],
+        fallback: bool = True,
+    ) -> tuple[list[_DistributionT], dict[Distribution, Exception]]: ...
+    @overload
+    def find_plugins(
+        self,
+        plugin_env: Environment,
+        full_env: Environment | None = None,
+        installer: _InstallerType | None = None,
+        fallback: bool = True,
+    ) -> tuple[list[Distribution], dict[Distribution, Exception]]: ...
+    def find_plugins(
+        self,
+        plugin_env: Environment,
+        full_env: Environment | None = None,
+        installer: _InstallerType | None | _InstallerTypeT[_DistributionT] = None,
+        fallback: bool = True,
+    ) -> tuple[
+        list[Distribution] | list[_DistributionT],
+        dict[Distribution, Exception],
+    ]:
         """Find all activatable distributions in `plugin_env`
 
         Example usage::
@@ -914,8 +1007,8 @@ class WorkingSet:
         # scan project names in alphabetic order
         plugin_projects.sort()
 
-        error_info = {}
-        distributions = {}
+        error_info: dict[Distribution, Exception] = {}
+        distributions: dict[Distribution, Exception | None] = {}
 
         if full_env is None:
             env = Environment(self.entries)
@@ -951,12 +1044,12 @@ class WorkingSet:
                     # success, no need to try any more versions of this project
                     break
 
-        distributions = list(distributions)
-        distributions.sort()
+        sorted_distributions = list(distributions)
+        sorted_distributions.sort()
 
-        return distributions, error_info
+        return sorted_distributions, error_info
 
-    def require(self, *requirements):
+    def require(self, *requirements: _NestedStr):
         """Ensure that distributions matching `requirements` are activated
 
         `requirements` must be a string or a (possibly-nested) sequence
@@ -972,7 +1065,9 @@ class WorkingSet:
 
         return needed
 
-    def subscribe(self, callback, existing=True):
+    def subscribe(
+        self, callback: Callable[[Distribution], object], existing: bool = True
+    ):
         """Invoke `callback` for all distributions
 
         If `existing=True` (default),
@@ -1008,12 +1103,12 @@ class WorkingSet:
         self.callbacks = callbacks[:]
 
 
-class _ReqExtras(dict):
+class _ReqExtras(Dict["Requirement", Tuple[str, ...]]):
     """
     Map each requirement to the extras that demanded it.
     """
 
-    def markers_pass(self, req, extras=None):
+    def markers_pass(self, req: Requirement, extras: tuple[str, ...] | None = None):
         """
         Evaluate markers for req against each extra that
         demanded it.
@@ -1032,7 +1127,10 @@ class Environment:
     """Searchable snapshot of distributions on a search path"""
 
     def __init__(
-        self, search_path=None, platform=get_supported_platform(), python=PY_MAJOR
+        self,
+        search_path: Iterable[str] | None = None,
+        platform: str | None = get_supported_platform(),
+        python: str | None = PY_MAJOR,
     ):
         """Snapshot distributions available on a search path
 
@@ -1055,7 +1153,7 @@ class Environment:
         self.python = python
         self.scan(search_path)
 
-    def can_add(self, dist):
+    def can_add(self, dist: Distribution):
         """Is distribution `dist` acceptable for this environment?
 
         The distribution must match the platform and python version
@@ -1069,11 +1167,11 @@ class Environment:
         )
         return py_compat and compatible_platforms(dist.platform, self.platform)
 
-    def remove(self, dist):
+    def remove(self, dist: Distribution):
         """Remove `dist` from the environment"""
         self._distmap[dist.key].remove(dist)
 
-    def scan(self, search_path=None):
+    def scan(self, search_path: Iterable[str] | None = None):
         """Scan `search_path` for distributions usable in this environment
 
         Any distributions found are added to the environment.
@@ -1088,7 +1186,7 @@ class Environment:
             for dist in find_distributions(item):
                 self.add(dist)
 
-    def __getitem__(self, project_name):
+    def __getitem__(self, project_name: str) -> list[Distribution]:
         """Return a newest-to-oldest list of distributions for `project_name`
 
         Uses case-insensitive `project_name` comparison, assuming all the
@@ -1099,7 +1197,7 @@ class Environment:
         distribution_key = project_name.lower()
         return self._distmap.get(distribution_key, [])
 
-    def add(self, dist):
+    def add(self, dist: Distribution):
         """Add `dist` if we ``can_add()`` it and it has not already been added"""
         if self.can_add(dist) and dist.has_version():
             dists = self._distmap.setdefault(dist.key, [])
@@ -1107,7 +1205,29 @@ class Environment:
                 dists.append(dist)
                 dists.sort(key=operator.attrgetter('hashcmp'), reverse=True)
 
-    def best_match(self, req, working_set, installer=None, replace_conflicting=False):
+    @overload
+    def best_match(
+        self,
+        req: Requirement,
+        working_set: WorkingSet,
+        installer: _InstallerTypeT[_DistributionT],
+        replace_conflicting: bool = False,
+    ) -> _DistributionT: ...
+    @overload
+    def best_match(
+        self,
+        req: Requirement,
+        working_set: WorkingSet,
+        installer: _InstallerType | None = None,
+        replace_conflicting: bool = False,
+    ) -> Distribution | None: ...
+    def best_match(
+        self,
+        req: Requirement,
+        working_set: WorkingSet,
+        installer: _InstallerType | None | _InstallerTypeT[_DistributionT] = None,
+        replace_conflicting: bool = False,
+    ) -> Distribution | None:
         """Find distribution best matching `req` and usable on `working_set`
 
         This calls the ``find(req)`` method of the `working_set` to see if a
@@ -1134,7 +1254,32 @@ class Environment:
         # try to download/install
         return self.obtain(req, installer)
 
-    def obtain(self, requirement, installer=None):
+    @overload
+    def obtain(
+        self,
+        requirement: Requirement,
+        installer: _InstallerTypeT[_DistributionT],
+    ) -> _DistributionT: ...
+    @overload
+    def obtain(
+        self,
+        requirement: Requirement,
+        installer: Callable[[Requirement], None] | None = None,
+    ) -> None: ...
+    @overload
+    def obtain(
+        self,
+        requirement: Requirement,
+        installer: _InstallerType | None = None,
+    ) -> Distribution | None: ...
+    def obtain(
+        self,
+        requirement: Requirement,
+        installer: Callable[[Requirement], None]
+        | _InstallerType
+        | None
+        | _InstallerTypeT[_DistributionT] = None,
+    ) -> Distribution | None:
         """Obtain a distribution matching `requirement` (e.g. via download)
 
         Obtain a distro that matches requirement (e.g. via download).  In the
@@ -1143,16 +1288,15 @@ class Environment:
         None is returned instead.  This method is a hook that allows subclasses
         to attempt other ways of obtaining a distribution before falling back
         to the `installer` argument."""
-        if installer is not None:
-            return installer(requirement)
+        return installer(requirement) if installer else None
 
-    def __iter__(self):
+    def __iter__(self) -> Iterator[str]:
         """Yield the unique project names of the available distributions"""
         for key in self._distmap.keys():
             if self[key]:
                 yield key
 
-    def __iadd__(self, other):
+    def __iadd__(self, other: Distribution | Environment):
         """In-place addition of a distribution or environment"""
         if isinstance(other, Distribution):
             self.add(other)
@@ -1164,7 +1308,7 @@ class Environment:
             raise TypeError("Can't add %r to environment" % (other,))
         return self
 
-    def __add__(self, other):
+    def __add__(self, other: Distribution | Environment):
         """Add an environment or distribution to an environment"""
         new = self.__class__([], platform=None, python=None)
         for env in self, other:
@@ -1191,46 +1335,54 @@ class ExtractionError(RuntimeError):
         The exception instance that caused extraction to fail
     """
 
+    manager: ResourceManager
+    cache_path: str
+    original_error: BaseException | None
+
 
 class ResourceManager:
     """Manage resource extraction and packages"""
 
-    extraction_path = None
+    extraction_path: str | None = None
 
     def __init__(self):
         self.cached_files = {}
 
-    def resource_exists(self, package_or_requirement, resource_name):
+    def resource_exists(self, package_or_requirement: _PkgReqType, resource_name: str):
         """Does the named resource exist?"""
         return get_provider(package_or_requirement).has_resource(resource_name)
 
-    def resource_isdir(self, package_or_requirement, resource_name):
+    def resource_isdir(self, package_or_requirement: _PkgReqType, resource_name: str):
         """Is the named resource an existing directory?"""
         return get_provider(package_or_requirement).resource_isdir(resource_name)
 
-    def resource_filename(self, package_or_requirement, resource_name):
+    def resource_filename(
+        self, package_or_requirement: _PkgReqType, resource_name: str
+    ):
         """Return a true filesystem path for specified resource"""
         return get_provider(package_or_requirement).get_resource_filename(
             self, resource_name
         )
 
-    def resource_stream(self, package_or_requirement, resource_name):
+    def resource_stream(self, package_or_requirement: _PkgReqType, resource_name: str):
         """Return a readable file-like object for specified resource"""
         return get_provider(package_or_requirement).get_resource_stream(
             self, resource_name
         )
 
-    def resource_string(self, package_or_requirement, resource_name):
-        """Return specified resource as a string"""
+    def resource_string(
+        self, package_or_requirement: _PkgReqType, resource_name: str
+    ) -> bytes:
+        """Return specified resource as :obj:`bytes`"""
         return get_provider(package_or_requirement).get_resource_string(
             self, resource_name
         )
 
-    def resource_listdir(self, package_or_requirement, resource_name):
+    def resource_listdir(self, package_or_requirement: _PkgReqType, resource_name: str):
         """List the contents of the named resource directory"""
         return get_provider(package_or_requirement).resource_listdir(resource_name)
 
-    def extraction_error(self):
+    def extraction_error(self) -> NoReturn:
         """Give an error message for problems extracting file(s)"""
 
         old_exc = sys.exc_info()[1]
@@ -1260,7 +1412,7 @@ class ResourceManager:
         err.original_error = old_exc
         raise err
 
-    def get_cache_path(self, archive_name, names=()):
+    def get_cache_path(self, archive_name: str, names: Iterable[StrPath] = ()):
         """Return absolute location in cache for `archive_name` and `names`
 
         The parent directory of the resulting path will be created if it does
@@ -1282,7 +1434,7 @@ class ResourceManager:
 
         self._warn_unsafe_extraction_path(extract_path)
 
-        self.cached_files[target_path] = 1
+        self.cached_files[target_path] = True
         return target_path
 
     @staticmethod
@@ -1312,7 +1464,7 @@ class ResourceManager:
             ).format(**locals())
             warnings.warn(msg, UserWarning)
 
-    def postprocess(self, tempname, filename):
+    def postprocess(self, tempname: StrOrBytesPath, filename: StrOrBytesPath):
         """Perform any platform-specific postprocessing of `tempname`
 
         This is where Mac header rewrites should be done; other platforms don't
@@ -1332,7 +1484,7 @@ class ResourceManager:
             mode = ((os.stat(tempname).st_mode) | 0o555) & 0o7777
             os.chmod(tempname, mode)
 
-    def set_extraction_path(self, path):
+    def set_extraction_path(self, path: str):
         """Set the base path where resources will be extracted to, if needed.
 
         If you do not call this routine before any extractions take place, the
@@ -1356,7 +1508,7 @@ class ResourceManager:
 
         self.extraction_path = path
 
-    def cleanup_resources(self, force=False):
+    def cleanup_resources(self, force: bool = False) -> list[str]:
         """
         Delete all extracted resource files and directories, returning a list
         of the file and directory names that could not be successfully removed.
@@ -1368,20 +1520,19 @@ class ResourceManager:
         directory used for extractions.
         """
         # XXX
+        return []
 
 
-def get_default_cache():
+def get_default_cache() -> str:
     """
     Return the ``PYTHON_EGG_CACHE`` environment variable
     or a platform-relevant user cache dir for an app
     named "Python-Eggs".
     """
-    return os.environ.get('PYTHON_EGG_CACHE') or platformdirs.user_cache_dir(
-        appname='Python-Eggs'
-    )
+    return os.environ.get('PYTHON_EGG_CACHE') or _user_cache_dir(appname='Python-Eggs')
 
 
-def safe_name(name):
+def safe_name(name: str):
     """Convert an arbitrary string to a standard distribution name
 
     Any runs of non-alphanumeric/. characters are replaced with a single '-'.
@@ -1389,14 +1540,14 @@ def safe_name(name):
     return re.sub('[^A-Za-z0-9.]+', '-', name)
 
 
-def safe_version(version):
+def safe_version(version: str):
     """
     Convert an arbitrary string to a standard version string
     """
     try:
         # normalize the version
-        return str(packaging.version.Version(version))
-    except packaging.version.InvalidVersion:
+        return str(_packaging_version.Version(version))
+    except _packaging_version.InvalidVersion:
         version = version.replace(' ', '.')
         return re.sub('[^A-Za-z0-9.]+', '-', version)
 
@@ -1418,7 +1569,7 @@ def _forgiving_version(version):
     match = _PEP440_FALLBACK.search(version)
     if match:
         safe = match["safe"]
-        rest = version[len(safe):]
+        rest = version[len(safe) :]
     else:
         safe = "0"
         rest = version
@@ -1433,7 +1584,7 @@ def _safe_segment(segment):
     return re.sub(r'\.[^A-Za-z0-9]+', '.', segment).strip(".-")
 
 
-def safe_extra(extra):
+def safe_extra(extra: str):
     """Convert an arbitrary string to a standard 'extra' name
 
     Any runs of non-alphanumeric characters are replaced with a single '_',
@@ -1442,7 +1593,7 @@ def safe_extra(extra):
     return re.sub('[^A-Za-z0-9.-]+', '_', extra).lower()
 
 
-def to_filename(name):
+def to_filename(name: str):
     """Convert a project or version name to its filename-escaped form
 
     Any '-' characters are currently replaced with '_'.
@@ -1450,7 +1601,7 @@ def to_filename(name):
     return name.replace('-', '_')
 
 
-def invalid_marker(text):
+def invalid_marker(text: str):
     """
     Validate text as a PEP 508 environment marker; return an exception
     if invalid or False otherwise.
@@ -1464,7 +1615,7 @@ def invalid_marker(text):
     return False
 
 
-def evaluate_marker(text, extra=None):
+def evaluate_marker(text: str, extra: str | None = None) -> bool:
     """
     Evaluate a PEP 508 environment marker.
     Return a boolean indicating the marker result in this environment.
@@ -1473,46 +1624,48 @@ def evaluate_marker(text, extra=None):
     This implementation uses the 'pyparsing' module.
     """
     try:
-        marker = packaging.markers.Marker(text)
+        marker = _packaging_markers.Marker(text)
         return marker.evaluate()
-    except packaging.markers.InvalidMarker as e:
+    except _packaging_markers.InvalidMarker as e:
         raise SyntaxError(e) from e
 
 
 class NullProvider:
     """Try to implement resources and metadata for arbitrary PEP 302 loaders"""
 
-    egg_name = None
-    egg_info = None
-    loader = None
+    egg_name: str | None = None
+    egg_info: str | None = None
+    loader: _LoaderProtocol | None = None
 
-    def __init__(self, module):
+    def __init__(self, module: _ModuleLike):
         self.loader = getattr(module, '__loader__', None)
         self.module_path = os.path.dirname(getattr(module, '__file__', ''))
 
-    def get_resource_filename(self, manager, resource_name):
+    def get_resource_filename(self, manager: ResourceManager, resource_name: str):
         return self._fn(self.module_path, resource_name)
 
-    def get_resource_stream(self, manager, resource_name):
+    def get_resource_stream(self, manager: ResourceManager, resource_name: str):
         return io.BytesIO(self.get_resource_string(manager, resource_name))
 
-    def get_resource_string(self, manager, resource_name):
+    def get_resource_string(
+        self, manager: ResourceManager, resource_name: str
+    ) -> bytes:
         return self._get(self._fn(self.module_path, resource_name))
 
-    def has_resource(self, resource_name):
+    def has_resource(self, resource_name: str):
         return self._has(self._fn(self.module_path, resource_name))
 
     def _get_metadata_path(self, name):
         return self._fn(self.egg_info, name)
 
-    def has_metadata(self, name):
+    def has_metadata(self, name: str) -> bool:
         if not self.egg_info:
-            return self.egg_info
+            return False
 
         path = self._get_metadata_path(name)
         return self._has(path)
 
-    def get_metadata(self, name):
+    def get_metadata(self, name: str):
         if not self.egg_info:
             return ""
         path = self._get_metadata_path(name)
@@ -1525,24 +1678,24 @@ class NullProvider:
             exc.reason += ' in {} file at path: {}'.format(name, path)
             raise
 
-    def get_metadata_lines(self, name):
+    def get_metadata_lines(self, name: str) -> Iterator[str]:
         return yield_lines(self.get_metadata(name))
 
-    def resource_isdir(self, resource_name):
+    def resource_isdir(self, resource_name: str):
         return self._isdir(self._fn(self.module_path, resource_name))
 
-    def metadata_isdir(self, name):
-        return self.egg_info and self._isdir(self._fn(self.egg_info, name))
+    def metadata_isdir(self, name: str) -> bool:
+        return bool(self.egg_info and self._isdir(self._fn(self.egg_info, name)))
 
-    def resource_listdir(self, resource_name):
+    def resource_listdir(self, resource_name: str):
         return self._listdir(self._fn(self.module_path, resource_name))
 
-    def metadata_listdir(self, name):
+    def metadata_listdir(self, name: str) -> list[str]:
         if self.egg_info:
             return self._listdir(self._fn(self.egg_info, name))
         return []
 
-    def run_script(self, script_name, namespace):
+    def run_script(self, script_name: str, namespace: dict[str, Any]):
         script = 'scripts/' + script_name
         if not self.has_metadata(script):
             raise ResolutionError(
@@ -1550,13 +1703,13 @@ class NullProvider:
                     **locals()
                 ),
             )
+
         script_text = self.get_metadata(script).replace('\r\n', '\n')
         script_text = script_text.replace('\r', '\n')
         script_filename = self._fn(self.egg_info, script)
         namespace['__file__'] = script_filename
         if os.path.exists(script_filename):
-            with open(script_filename) as fid:
-                source = fid.read()
+            source = _read_utf8_with_fallback(script_filename)
             code = compile(source, script_filename, 'exec')
             exec(code, namespace, namespace)
         else:
@@ -1571,22 +1724,26 @@ class NullProvider:
             script_code = compile(script_text, script_filename, 'exec')
             exec(script_code, namespace, namespace)
 
-    def _has(self, path):
+    def _has(self, path) -> bool:
         raise NotImplementedError(
             "Can't perform this operation for unregistered loader type"
         )
 
-    def _isdir(self, path):
+    def _isdir(self, path) -> bool:
         raise NotImplementedError(
             "Can't perform this operation for unregistered loader type"
         )
 
-    def _listdir(self, path):
+    def _listdir(self, path) -> list[str]:
         raise NotImplementedError(
             "Can't perform this operation for unregistered loader type"
         )
 
-    def _fn(self, base, resource_name):
+    def _fn(self, base: str | None, resource_name: str):
+        if base is None:
+            raise TypeError(
+                "`base` parameter in `_fn` is `None`. Either override this method or check the parameter first."
+            )
         self._validate_resource_path(resource_name)
         if resource_name:
             return os.path.join(base, *resource_name.split('/'))
@@ -1649,6 +1806,7 @@ is not allowed.
             os.path.pardir in path.split(posixpath.sep)
             or posixpath.isabs(path)
             or ntpath.isabs(path)
+            or path.startswith("\\")
         )
         if not invalid:
             return
@@ -1656,7 +1814,7 @@ is not allowed.
         msg = "Use of .. or absolute path in a resource path is not allowed."
 
         # Aggressively disallow Windows absolute paths
-        if ntpath.isabs(path) and not posixpath.isabs(path):
+        if (path.startswith("\\") or ntpath.isabs(path)) and not posixpath.isabs(path):
             raise ValueError(msg)
 
         # for compatibility, warn; in future
@@ -1666,9 +1824,10 @@ is not allowed.
             DeprecationWarning,
         )
 
-    def _get(self, path):
-        if hasattr(self.loader, 'get_data'):
-            return self.loader.get_data(path)
+    def _get(self, path) -> bytes:
+        if hasattr(self.loader, 'get_data') and self.loader:
+            # Already checked get_data exists
+            return self.loader.get_data(path)  # type: ignore[attr-defined]
         raise NotImplementedError(
             "Can't perform this operation for loaders without 'get_data()'"
         )
@@ -1691,7 +1850,7 @@ def _parents(path):
 class EggProvider(NullProvider):
     """Provider based on a virtual filesystem"""
 
-    def __init__(self, module):
+    def __init__(self, module: _ModuleLike):
         super().__init__(module)
         self._setup_prefix()
 
@@ -1702,7 +1861,7 @@ class EggProvider(NullProvider):
         egg = next(eggs, None)
         egg and self._set_egg(egg)
 
-    def _set_egg(self, path):
+    def _set_egg(self, path: str):
         self.egg_name = os.path.basename(path)
         self.egg_info = os.path.join(path, 'EGG-INFO')
         self.egg_root = path
@@ -1711,19 +1870,19 @@ class EggProvider(NullProvider):
 class DefaultProvider(EggProvider):
     """Provides access to package resources in the filesystem"""
 
-    def _has(self, path):
+    def _has(self, path) -> bool:
         return os.path.exists(path)
 
-    def _isdir(self, path):
+    def _isdir(self, path) -> bool:
         return os.path.isdir(path)
 
     def _listdir(self, path):
         return os.listdir(path)
 
-    def get_resource_stream(self, manager, resource_name):
+    def get_resource_stream(self, manager: object, resource_name: str):
         return open(self._fn(self.module_path, resource_name), 'rb')
 
-    def _get(self, path):
+    def _get(self, path) -> bytes:
         with open(path, 'rb') as stream:
             return stream.read()
 
@@ -1734,7 +1893,7 @@ class DefaultProvider(EggProvider):
             'SourcelessFileLoader',
         )
         for name in loader_names:
-            loader_cls = getattr(importlib_machinery, name, type(None))
+            loader_cls = getattr(importlib.machinery, name, type(None))
             register_loader_type(loader_cls, cls)
 
 
@@ -1744,12 +1903,13 @@ DefaultProvider._register()
 class EmptyProvider(NullProvider):
     """Provider that returns nothing for all requests"""
 
-    module_path = None
+    # A special case, we don't want all Providers inheriting from NullProvider to have a potentially None module_path
+    module_path: str | None = None  # type: ignore[assignment]
 
     _isdir = _has = lambda self, path: False
 
-    def _get(self, path):
-        return ''
+    def _get(self, path) -> bytes:
+        return b''
 
     def _listdir(self, path):
         return []
@@ -1761,13 +1921,14 @@ class EmptyProvider(NullProvider):
 empty_provider = EmptyProvider()
 
 
-class ZipManifests(dict):
+class ZipManifests(Dict[str, "MemoizedZipManifests.manifest_mod"]):
     """
     zip manifest builder
     """
 
+    # `path` could be `StrPath | IO[bytes]` but that violates the LSP for `MemoizedZipManifests.load`
     @classmethod
-    def build(cls, path):
+    def build(cls, path: str):
         """
         Build a dictionary similar to the zipimport directory
         caches, except instead of tuples, store ZipInfo objects.
@@ -1793,9 +1954,11 @@ class MemoizedZipManifests(ZipManifests):
     Memoized zipfile manifests.
     """
 
-    manifest_mod = collections.namedtuple('manifest_mod', 'manifest mtime')
+    class manifest_mod(NamedTuple):
+        manifest: dict[str, zipfile.ZipInfo]
+        mtime: float
 
-    def load(self, path):
+    def load(self, path: str) -> dict[str, zipfile.ZipInfo]:  # type: ignore[override] # ZipManifests.load is a classmethod
         """
         Load a manifest at path or return a suitable manifest already loaded.
         """
@@ -1812,10 +1975,12 @@ class MemoizedZipManifests(ZipManifests):
 class ZipProvider(EggProvider):
     """Resource support for zips and eggs"""
 
-    eagers = None
+    eagers: list[str] | None = None
     _zip_manifests = MemoizedZipManifests()
+    # ZipProvider's loader should always be a zipimporter or equivalent
+    loader: zipimport.zipimporter
 
-    def __init__(self, module):
+    def __init__(self, module: _ZipLoaderModule):
         super().__init__(module)
         self.zip_pre = self.loader.archive + os.sep
 
@@ -1841,7 +2006,7 @@ class ZipProvider(EggProvider):
     def zipinfo(self):
         return self._zip_manifests.load(self.loader.archive)
 
-    def get_resource_filename(self, manager, resource_name):
+    def get_resource_filename(self, manager: ResourceManager, resource_name: str):
         if not self.egg_name:
             raise NotImplementedError(
                 "resource_filename() only supported for .egg, not .zip"
@@ -1864,7 +2029,7 @@ class ZipProvider(EggProvider):
         return timestamp, size
 
     # FIXME: 'ZipProvider._extract_resource' is too complex (12)
-    def _extract_resource(self, manager, zip_path):  # noqa: C901
+    def _extract_resource(self, manager: ResourceManager, zip_path) -> str:  # noqa: C901
         if zip_path in self._index():
             for name in self._index()[zip_path]:
                 last = self._extract_resource(manager, os.path.join(zip_path, name))
@@ -1874,10 +2039,14 @@ class ZipProvider(EggProvider):
         timestamp, size = self._get_date_and_size(self.zipinfo[zip_path])
 
         if not WRITE_SUPPORT:
-            raise IOError(
-                '"os.rename" and "os.unlink" are not supported ' 'on this platform'
+            raise OSError(
+                '"os.rename" and "os.unlink" are not supported on this platform'
             )
         try:
+            if not self.egg_name:
+                raise OSError(
+                    '"egg_name" is empty. This likely means no egg could be found from the "module_path".'
+                )
             real_path = manager.get_cache_path(self.egg_name, self._parts(zip_path))
 
             if self._is_current(real_path, zip_path):
@@ -1895,7 +2064,7 @@ class ZipProvider(EggProvider):
             try:
                 rename(tmpnam, real_path)
 
-            except os.error:
+            except OSError:
                 if os.path.isfile(real_path):
                     if self._is_current(real_path, zip_path):
                         # the file became current since it was checked above,
@@ -1908,7 +2077,7 @@ class ZipProvider(EggProvider):
                         return real_path
                 raise
 
-        except os.error:
+        except OSError:
             # report a user-friendly error
             manager.extraction_error()
 
@@ -1956,20 +2125,20 @@ class ZipProvider(EggProvider):
             self._dirindex = ind
             return ind
 
-    def _has(self, fspath):
+    def _has(self, fspath) -> bool:
         zip_path = self._zipinfo_name(fspath)
         return zip_path in self.zipinfo or zip_path in self._index()
 
-    def _isdir(self, fspath):
+    def _isdir(self, fspath) -> bool:
         return self._zipinfo_name(fspath) in self._index()
 
     def _listdir(self, fspath):
         return list(self._index().get(self._zipinfo_name(fspath), ()))
 
-    def _eager_to_zip(self, resource_name):
+    def _eager_to_zip(self, resource_name: str):
         return self._zipinfo_name(self._fn(self.egg_root, resource_name))
 
-    def _resource_to_zip(self, resource_name):
+    def _resource_to_zip(self, resource_name: str):
         return self._zipinfo_name(self._fn(self.module_path, resource_name))
 
 
@@ -1988,20 +2157,20 @@ class FileMetadata(EmptyProvider):
     the provided location.
     """
 
-    def __init__(self, path):
+    def __init__(self, path: StrPath):
         self.path = path
 
     def _get_metadata_path(self, name):
         return self.path
 
-    def has_metadata(self, name):
+    def has_metadata(self, name: str) -> bool:
         return name == 'PKG-INFO' and os.path.isfile(self.path)
 
-    def get_metadata(self, name):
+    def get_metadata(self, name: str):
         if name != 'PKG-INFO':
             raise KeyError("No metadata except PKG-INFO is available")
 
-        with io.open(self.path, encoding='utf-8', errors="replace") as f:
+        with open(self.path, encoding='utf-8', errors="replace") as f:
             metadata = f.read()
         self._warn_on_replacement(metadata)
         return metadata
@@ -2013,7 +2182,7 @@ class FileMetadata(EmptyProvider):
             msg = tmpl.format(**locals())
             warnings.warn(msg)
 
-    def get_metadata_lines(self, name):
+    def get_metadata_lines(self, name: str) -> Iterator[str]:
         return yield_lines(self.get_metadata(name))
 
 
@@ -2037,7 +2206,7 @@ class PathMetadata(DefaultProvider):
         dist = Distribution.from_filename(egg_path, metadata=metadata)
     """
 
-    def __init__(self, path, egg_info):
+    def __init__(self, path: str, egg_info: str):
         self.module_path = path
         self.egg_info = egg_info
 
@@ -2045,7 +2214,7 @@ class PathMetadata(DefaultProvider):
 class EggMetadata(ZipProvider):
     """Metadata provider for .egg files"""
 
-    def __init__(self, importer):
+    def __init__(self, importer: zipimport.zipimporter):
         """Create a metadata provider from a zipimporter"""
 
         self.zip_pre = importer.archive + os.sep
@@ -2057,10 +2226,12 @@ class EggMetadata(ZipProvider):
         self._setup_prefix()
 
 
-_declare_state('dict', _distribution_finders={})
+_distribution_finders: dict[type, _DistFinderType[Any]] = _declare_state(
+    'dict', '_distribution_finders', {}
+)
 
 
-def register_finder(importer_type, distribution_finder):
+def register_finder(importer_type: type[_T], distribution_finder: _DistFinderType[_T]):
     """Register `distribution_finder` to find distributions in sys.path items
 
     `importer_type` is the type or class of a PEP 302 "Importer" (sys.path item
@@ -2070,14 +2241,16 @@ def register_finder(importer_type, distribution_finder):
     _distribution_finders[importer_type] = distribution_finder
 
 
-def find_distributions(path_item, only=False):
+def find_distributions(path_item: str, only: bool = False):
     """Yield distributions accessible via `path_item`"""
     importer = get_importer(path_item)
     finder = _find_adapter(_distribution_finders, importer)
     return finder(importer, path_item, only)
 
 
-def find_eggs_in_zip(importer, path_item, only=False):
+def find_eggs_in_zip(
+    importer: zipimport.zipimporter, path_item: str, only: bool = False
+) -> Iterator[Distribution]:
     """
     Find eggs in zip files; possibly multiple nested eggs.
     """
@@ -2095,8 +2268,7 @@ def find_eggs_in_zip(importer, path_item, only=False):
         if _is_egg_path(subitem):
             subpath = os.path.join(path_item, subitem)
             dists = find_eggs_in_zip(zipimport.zipimporter(subpath), subpath)
-            for dist in dists:
-                yield dist
+            yield from dists
         elif subitem.lower().endswith(('.dist-info', '.egg-info')):
             subpath = os.path.join(path_item, subitem)
             submeta = EggMetadata(zipimport.zipimporter(subpath))
@@ -2107,14 +2279,16 @@ def find_eggs_in_zip(importer, path_item, only=False):
 register_finder(zipimport.zipimporter, find_eggs_in_zip)
 
 
-def find_nothing(importer, path_item, only=False):
+def find_nothing(
+    importer: object | None, path_item: str | None, only: bool | None = False
+):
     return ()
 
 
 register_finder(object, find_nothing)
 
 
-def find_on_path(importer, path_item, only=False):
+def find_on_path(importer: object | None, path_item, only=False):
     """Yield distributions accessible on a sys.path directory"""
     path_item = _normalize_cached(path_item)
 
@@ -2131,8 +2305,7 @@ def find_on_path(importer, path_item, only=False):
     for entry in sorted(entries):
         fullpath = os.path.join(path_item, entry)
         factory = dist_factory(path_item, entry, only)
-        for dist in factory(fullpath):
-            yield dist
+        yield from factory(fullpath)
 
 
 def dist_factory(path_item, entry, only):
@@ -2170,7 +2343,7 @@ class NoDists:
         return iter(())
 
 
-def safe_listdir(path):
+def safe_listdir(path: StrOrBytesPath):
     """
     Attempt to list contents of path, but suppress some exceptions.
     """
@@ -2186,13 +2359,13 @@ def safe_listdir(path):
     return ()
 
 
-def distributions_from_metadata(path):
+def distributions_from_metadata(path: str):
     root = os.path.dirname(path)
     if os.path.isdir(path):
         if len(os.listdir(path)) == 0:
             # empty metadata dir; skip
             return
-        metadata = PathMetadata(root, path)
+        metadata: _MetadataType = PathMetadata(root, path)
     else:
         metadata = FileMetadata(path)
     entry = os.path.basename(path)
@@ -2208,11 +2381,10 @@ def non_empty_lines(path):
     """
     Yield non-empty lines from file at path
     """
-    with open(path) as f:
-        for line in f:
-            line = line.strip()
-            if line:
-                yield line
+    for line in _read_utf8_with_fallback(path).splitlines():
+        line = line.strip()
+        if line:
+            yield line
 
 
 def resolve_egg_link(path):
@@ -2231,13 +2403,19 @@ def resolve_egg_link(path):
 if hasattr(pkgutil, 'ImpImporter'):
     register_finder(pkgutil.ImpImporter, find_on_path)
 
-register_finder(importlib_machinery.FileFinder, find_on_path)
+register_finder(importlib.machinery.FileFinder, find_on_path)
 
-_declare_state('dict', _namespace_handlers={})
-_declare_state('dict', _namespace_packages={})
+_namespace_handlers: dict[type, _NSHandlerType[Any]] = _declare_state(
+    'dict', '_namespace_handlers', {}
+)
+_namespace_packages: dict[str | None, list[str]] = _declare_state(
+    'dict', '_namespace_packages', {}
+)
 
 
-def register_namespace_handler(importer_type, namespace_handler):
+def register_namespace_handler(
+    importer_type: type[_T], namespace_handler: _NSHandlerType[_T]
+):
     """Register `namespace_handler` to declare namespace packages
 
     `importer_type` is the type or class of a PEP 302 "Importer" (sys.path item
@@ -2292,7 +2470,7 @@ def _handle_ns(packageName, path_item):
     return subpath
 
 
-def _rebuild_mod_path(orig_path, package_name, module):
+def _rebuild_mod_path(orig_path, package_name, module: types.ModuleType):
     """
     Rebuild module.__path__ ensuring that all entries are ordered
     corresponding to their sys.path order
@@ -2326,7 +2504,7 @@ def _rebuild_mod_path(orig_path, package_name, module):
         module.__path__ = new_path
 
 
-def declare_namespace(packageName):
+def declare_namespace(packageName: str):
     """Declare that package 'packageName' is a namespace package"""
 
     msg = (
@@ -2343,7 +2521,7 @@ def declare_namespace(packageName):
         if packageName in _namespace_packages:
             return
 
-        path = sys.path
+        path: MutableSequence[str] = sys.path
         parent, _, _ = packageName.rpartition('.')
 
         if parent:
@@ -2369,7 +2547,7 @@ def declare_namespace(packageName):
         _imp.release_lock()
 
 
-def fixup_namespace_packages(path_item, parent=None):
+def fixup_namespace_packages(path_item: str, parent: str | None = None):
     """Ensure that previously-declared namespace packages include path_item"""
     _imp.acquire_lock()
     try:
@@ -2381,7 +2559,12 @@ def fixup_namespace_packages(path_item, parent=None):
         _imp.release_lock()
 
 
-def file_ns_handler(importer, path_item, packageName, module):
+def file_ns_handler(
+    importer: object,
+    path_item: StrPath,
+    packageName: str,
+    module: types.ModuleType,
+):
     """Compute an ns-package subpath for a filesystem or zipfile importer"""
 
     subpath = os.path.join(path_item, packageName.split('.')[-1])
@@ -2398,22 +2581,31 @@ if hasattr(pkgutil, 'ImpImporter'):
     register_namespace_handler(pkgutil.ImpImporter, file_ns_handler)
 
 register_namespace_handler(zipimport.zipimporter, file_ns_handler)
-register_namespace_handler(importlib_machinery.FileFinder, file_ns_handler)
+register_namespace_handler(importlib.machinery.FileFinder, file_ns_handler)
 
 
-def null_ns_handler(importer, path_item, packageName, module):
+def null_ns_handler(
+    importer: object,
+    path_item: str | None,
+    packageName: str | None,
+    module: _ModuleLike | None,
+):
     return None
 
 
 register_namespace_handler(object, null_ns_handler)
 
 
-def normalize_path(filename):
+@overload
+def normalize_path(filename: StrPath) -> str: ...
+@overload
+def normalize_path(filename: BytesPath) -> bytes: ...
+def normalize_path(filename: StrOrBytesPath):
     """Normalize a file/dir name for comparison purposes"""
     return os.path.normcase(os.path.realpath(os.path.normpath(_cygwin_patch(filename))))
 
 
-def _cygwin_patch(filename):  # pragma: nocover
+def _cygwin_patch(filename: StrOrBytesPath):  # pragma: nocover
     """
     Contrary to POSIX 2008, on Cygwin, getcwd (3) contains
     symlink components. Using
@@ -2424,12 +2616,19 @@ def _cygwin_patch(filename):  # pragma: nocover
     return os.path.abspath(filename) if sys.platform == 'cygwin' else filename
 
 
-def _normalize_cached(filename, _cache={}):
-    try:
-        return _cache[filename]
-    except KeyError:
-        _cache[filename] = result = normalize_path(filename)
-        return result
+if TYPE_CHECKING:
+    # https://github.com/python/mypy/issues/16261
+    # https://github.com/python/typeshed/issues/6347
+    @overload
+    def _normalize_cached(filename: StrPath) -> str: ...
+    @overload
+    def _normalize_cached(filename: BytesPath) -> bytes: ...
+    def _normalize_cached(filename: StrOrBytesPath) -> str | bytes: ...
+else:
+
+    @functools.lru_cache(maxsize=None)
+    def _normalize_cached(filename):
+        return normalize_path(filename)
 
 
 def _is_egg_path(path):
@@ -2482,7 +2681,14 @@ EGG_NAME = re.compile(
 class EntryPoint:
     """Object representing an advertised importable object"""
 
-    def __init__(self, name, module_name, attrs=(), extras=(), dist=None):
+    def __init__(
+        self,
+        name: str,
+        module_name: str,
+        attrs: Iterable[str] = (),
+        extras: Iterable[str] = (),
+        dist: Distribution | None = None,
+    ):
         if not MODULE(module_name):
             raise ValueError("Invalid module name", module_name)
         self.name = name
@@ -2502,7 +2708,26 @@ class EntryPoint:
     def __repr__(self):
         return "EntryPoint.parse(%r)" % str(self)
 
-    def load(self, require=True, *args, **kwargs):
+    @overload
+    def load(
+        self,
+        require: Literal[True] = True,
+        env: Environment | None = None,
+        installer: _InstallerType | None = None,
+    ) -> _ResolvedEntryPoint: ...
+    @overload
+    def load(
+        self,
+        require: Literal[False],
+        *args: Any,
+        **kwargs: Any,
+    ) -> _ResolvedEntryPoint: ...
+    def load(
+        self,
+        require: bool = True,
+        *args: Environment | _InstallerType | None,
+        **kwargs: Environment | _InstallerType | None,
+    ) -> _ResolvedEntryPoint:
         """
         Require packages for this EntryPoint, then resolve it.
         """
@@ -2514,10 +2739,12 @@ class EntryPoint:
                 stacklevel=2,
             )
         if require:
-            self.require(*args, **kwargs)
+            # We could pass `env` and `installer` directly,
+            # but keeping `*args` and `**kwargs` for backwards compatibility
+            self.require(*args, **kwargs)  # type: ignore
         return self.resolve()
 
-    def resolve(self):
+    def resolve(self) -> _ResolvedEntryPoint:
         """
         Resolve the entry point from its module and attrs.
         """
@@ -2527,9 +2754,14 @@ class EntryPoint:
         except AttributeError as exc:
             raise ImportError(str(exc)) from exc
 
-    def require(self, env=None, installer=None):
-        if self.extras and not self.dist:
-            raise UnknownExtra("Can't require() without a distribution", self)
+    def require(
+        self,
+        env: Environment | None = None,
+        installer: _InstallerType | None = None,
+    ):
+        if not self.dist:
+            error_cls = UnknownExtra if self.extras else AttributeError
+            raise error_cls("Can't require() without a distribution", self)
 
         # Get the requirements for this entry point with all its extras and
         # then resolve them. We have to pass `extras` along when resolving so
@@ -2550,7 +2782,7 @@ class EntryPoint:
     )
 
     @classmethod
-    def parse(cls, src, dist=None):
+    def parse(cls, src: str, dist: Distribution | None = None):
         """Parse a single entry point from string `src`
 
         Entry point syntax follows the form::
@@ -2575,15 +2807,20 @@ class EntryPoint:
             return ()
         req = Requirement.parse('x' + extras_spec)
         if req.specs:
-            raise ValueError()
+            raise ValueError
         return req.extras
 
     @classmethod
-    def parse_group(cls, group, lines, dist=None):
+    def parse_group(
+        cls,
+        group: str,
+        lines: _NestedStr,
+        dist: Distribution | None = None,
+    ):
         """Parse an entry point group"""
         if not MODULE(group):
             raise ValueError("Invalid group name", group)
-        this = {}
+        this: dict[str, Self] = {}
         for line in yield_lines(lines):
             ep = cls.parse(line, dist)
             if ep.name in this:
@@ -2592,14 +2829,19 @@ class EntryPoint:
         return this
 
     @classmethod
-    def parse_map(cls, data, dist=None):
+    def parse_map(
+        cls,
+        data: str | Iterable[str] | dict[str, str | Iterable[str]],
+        dist: Distribution | None = None,
+    ):
         """Parse a map of entry point groups"""
+        _data: Iterable[tuple[str | None, str | Iterable[str]]]
         if isinstance(data, dict):
-            data = data.items()
+            _data = data.items()
         else:
-            data = split_sections(data)
-        maps = {}
-        for group, lines in data:
+            _data = split_sections(data)
+        maps: dict[str, dict[str, Self]] = {}
+        for group, lines in _data:
             if group is None:
                 if not lines:
                     continue
@@ -2633,13 +2875,13 @@ class Distribution:
 
     def __init__(
         self,
-        location=None,
-        metadata=None,
-        project_name=None,
-        version=None,
-        py_version=PY_MAJOR,
-        platform=None,
-        precedence=EGG_DIST,
+        location: str | None = None,
+        metadata: _MetadataType = None,
+        project_name: str | None = None,
+        version: str | None = None,
+        py_version: str | None = PY_MAJOR,
+        platform: str | None = None,
+        precedence: int = EGG_DIST,
     ):
         self.project_name = safe_name(project_name or 'Unknown')
         if version is not None:
@@ -2651,7 +2893,13 @@ class Distribution:
         self._provider = metadata or empty_provider
 
     @classmethod
-    def from_location(cls, location, basename, metadata=None, **kw):
+    def from_location(
+        cls,
+        location: str,
+        basename: StrPath,
+        metadata: _MetadataType = None,
+        **kw: int,  # We could set `precedence` explicitly, but keeping this as `**kw` for full backwards and subclassing compatibility
+    ) -> Distribution:
         project_name, version, py_version, platform = [None] * 4
         basename, ext = os.path.splitext(basename)
         if ext.lower() in _distributionImpl:
@@ -2689,25 +2937,25 @@ class Distribution:
     def __hash__(self):
         return hash(self.hashcmp)
 
-    def __lt__(self, other):
+    def __lt__(self, other: Distribution):
         return self.hashcmp < other.hashcmp
 
-    def __le__(self, other):
+    def __le__(self, other: Distribution):
         return self.hashcmp <= other.hashcmp
 
-    def __gt__(self, other):
+    def __gt__(self, other: Distribution):
         return self.hashcmp > other.hashcmp
 
-    def __ge__(self, other):
+    def __ge__(self, other: Distribution):
         return self.hashcmp >= other.hashcmp
 
-    def __eq__(self, other):
+    def __eq__(self, other: object):
         if not isinstance(other, self.__class__):
             # It's not a Distribution, so they are not equal
             return False
         return self.hashcmp == other.hashcmp
 
-    def __ne__(self, other):
+    def __ne__(self, other: object):
         return not self == other
 
     # These properties have to be lazy so that we don't have to load any
@@ -2727,12 +2975,12 @@ class Distribution:
         if not hasattr(self, "_parsed_version"):
             try:
                 self._parsed_version = parse_version(self.version)
-            except packaging.version.InvalidVersion as ex:
+            except _packaging_version.InvalidVersion as ex:
                 info = f"(package: {self.project_name})"
                 if hasattr(ex, "add_note"):
                     ex.add_note(info)  # PEP 678
                     raise
-                raise packaging.version.InvalidVersion(f"{str(ex)} {info}") from None
+                raise _packaging_version.InvalidVersion(f"{str(ex)} {info}") from None
 
         return self._parsed_version
 
@@ -2740,7 +2988,7 @@ class Distribution:
     def _forgiving_parsed_version(self):
         try:
             return self.parsed_version
-        except packaging.version.InvalidVersion as ex:
+        except _packaging_version.InvalidVersion as ex:
             self._parsed_version = parse_version(_forgiving_version(self.version))
 
             notes = "\n".join(getattr(ex, "__notes__", []))  # PEP 678
@@ -2790,14 +3038,14 @@ class Distribution:
         return self.__dep_map
 
     @staticmethod
-    def _filter_extras(dm):
+    def _filter_extras(dm: dict[str | None, list[Requirement]]):
         """
         Given a mapping of extras to dependencies, strip off
         environment markers and filter out any dependencies
         not matching the markers.
         """
         for extra in list(filter(None, dm)):
-            new_extra = extra
+            new_extra: str | None = extra
             reqs = dm.pop(extra)
             new_extra, _, marker = extra.partition(':')
             fails_marker = marker and (
@@ -2817,10 +3065,10 @@ class Distribution:
                 dm.setdefault(extra, []).extend(parse_requirements(reqs))
         return dm
 
-    def requires(self, extras=()):
+    def requires(self, extras: Iterable[str] = ()):
         """List of Requirements needed for this distro if `extras` are used"""
         dm = self._dep_map
-        deps = []
+        deps: list[Requirement] = []
         deps.extend(dm.get(None, ()))
         for ext in extras:
             try:
@@ -2850,21 +3098,18 @@ class Distribution:
 
     def _get_metadata(self, name):
         if self.has_metadata(name):
-            for line in self.get_metadata_lines(name):
-                yield line
+            yield from self.get_metadata_lines(name)
 
     def _get_version(self):
         lines = self._get_metadata(self.PKG_INFO)
-        version = _version_from_file(lines)
+        return _version_from_file(lines)
 
-        return version
-
-    def activate(self, path=None, replace=False):
+    def activate(self, path: list[str] | None = None, replace: bool = False):
         """Ensure distribution is importable on `path` (default=sys.path)"""
         if path is None:
             path = sys.path
         self.insert_on(path, replace=replace)
-        if path is sys.path:
+        if path is sys.path and self.location is not None:
             fixup_namespace_packages(self.location)
             for pkg in self._get_metadata('namespace_packages.txt'):
                 if pkg in sys.modules:
@@ -2904,50 +3149,62 @@ class Distribution:
 
     def __dir__(self):
         return list(
-            set(super(Distribution, self).__dir__())
+            set(super().__dir__())
             | set(attr for attr in self._provider.__dir__() if not attr.startswith('_'))
         )
 
     @classmethod
-    def from_filename(cls, filename, metadata=None, **kw):
+    def from_filename(
+        cls,
+        filename: StrPath,
+        metadata: _MetadataType = None,
+        **kw: int,  # We could set `precedence` explicitly, but keeping this as `**kw` for full backwards and subclassing compatibility
+    ):
         return cls.from_location(
             _normalize_cached(filename), os.path.basename(filename), metadata, **kw
         )
 
     def as_requirement(self):
         """Return a ``Requirement`` that matches this distribution exactly"""
-        if isinstance(self.parsed_version, packaging.version.Version):
+        if isinstance(self.parsed_version, _packaging_version.Version):
             spec = "%s==%s" % (self.project_name, self.parsed_version)
         else:
             spec = "%s===%s" % (self.project_name, self.parsed_version)
 
         return Requirement.parse(spec)
 
-    def load_entry_point(self, group, name):
+    def load_entry_point(self, group: str, name: str) -> _ResolvedEntryPoint:
         """Return the `name` entry point of `group` or raise ImportError"""
         ep = self.get_entry_info(group, name)
         if ep is None:
             raise ImportError("Entry point %r not found" % ((group, name),))
         return ep.load()
 
-    def get_entry_map(self, group=None):
+    @overload
+    def get_entry_map(self, group: None = None) -> dict[str, dict[str, EntryPoint]]: ...
+    @overload
+    def get_entry_map(self, group: str) -> dict[str, EntryPoint]: ...
+    def get_entry_map(self, group: str | None = None):
         """Return the entry point map for `group`, or the full entry map"""
-        try:
-            ep_map = self._ep_map
-        except AttributeError:
-            ep_map = self._ep_map = EntryPoint.parse_map(
+        if not hasattr(self, "_ep_map"):
+            self._ep_map = EntryPoint.parse_map(
                 self._get_metadata('entry_points.txt'), self
             )
         if group is not None:
-            return ep_map.get(group, {})
-        return ep_map
+            return self._ep_map.get(group, {})
+        return self._ep_map
 
-    def get_entry_info(self, group, name):
+    def get_entry_info(self, group: str, name: str):
         """Return the EntryPoint object for `group`+`name`, or ``None``"""
         return self.get_entry_map(group).get(name)
 
     # FIXME: 'Distribution.insert_on' is too complex (13)
-    def insert_on(self, path, loc=None, replace=False):  # noqa: C901
+    def insert_on(  # noqa: C901
+        self,
+        path: list[str],
+        loc=None,
+        replace: bool = False,
+    ):
         """Ensure self.location is on path
 
         If replace=False (default):
@@ -3052,13 +3309,14 @@ class Distribution:
             return False
         return True
 
-    def clone(self, **kw):
+    def clone(self, **kw: str | int | IResourceProvider | None):
         """Copy this distribution, substituting in any changed keyword args"""
         names = 'project_name version py_version platform location precedence'
         for attr in names.split():
             kw.setdefault(attr, getattr(self, attr, None))
         kw.setdefault('metadata', self._provider)
-        return self.__class__(**kw)
+        # Unsafely unpacking. But keeping **kw for backwards and subclassing compatibility
+        return self.__class__(**kw)  # type:ignore[arg-type]
 
     @property
     def extras(self):
@@ -3111,11 +3369,11 @@ class DistInfoDistribution(Distribution):
             self.__dep_map = self._compute_dependencies()
             return self.__dep_map
 
-    def _compute_dependencies(self):
+    def _compute_dependencies(self) -> dict[str | None, list[Requirement]]:
         """Recompute this distribution's dependencies."""
-        dm = self.__dep_map = {None: []}
+        self.__dep_map: dict[str | None, list[Requirement]] = {None: []}
 
-        reqs = []
+        reqs: list[Requirement] = []
         # Including any condition expressions
         for req in self._parsed_pkg_info.get_all('Requires-Dist') or []:
             reqs.extend(parse_requirements(req))
@@ -3126,13 +3384,15 @@ class DistInfoDistribution(Distribution):
                     yield req
 
         common = types.MappingProxyType(dict.fromkeys(reqs_for_extra(None)))
-        dm[None].extend(common)
+        self.__dep_map[None].extend(common)
 
         for extra in self._parsed_pkg_info.get_all('Provides-Extra') or []:
             s_extra = safe_extra(extra.strip())
-            dm[s_extra] = [r for r in reqs_for_extra(extra) if r not in common]
+            self.__dep_map[s_extra] = [
+                r for r in reqs_for_extra(extra) if r not in common
+            ]
 
-        return dm
+        return self.__dep_map
 
 
 _distributionImpl = {
@@ -3155,7 +3415,7 @@ def issue_warning(*args, **kw):
     warnings.warn(stacklevel=level + 1, *args, **kw)
 
 
-def parse_requirements(strs):
+def parse_requirements(strs: _NestedStr):
     """
     Yield ``Requirement`` objects for each specification in `strs`.
 
@@ -3164,19 +3424,20 @@ def parse_requirements(strs):
     return map(Requirement, join_continuation(map(drop_comment, yield_lines(strs))))
 
 
-class RequirementParseError(packaging.requirements.InvalidRequirement):
+class RequirementParseError(_packaging_requirements.InvalidRequirement):
     "Compatibility wrapper for InvalidRequirement"
 
 
-class Requirement(packaging.requirements.Requirement):
-    def __init__(self, requirement_string):
+class Requirement(_packaging_requirements.Requirement):
+    def __init__(self, requirement_string: str):
         """DO NOT CALL THIS UNDOCUMENTED METHOD; use Requirement.parse()!"""
-        super(Requirement, self).__init__(requirement_string)
+        super().__init__(requirement_string)
         self.unsafe_name = self.name
         project_name = safe_name(self.name)
         self.project_name, self.key = project_name, project_name.lower()
         self.specs = [(spec.operator, spec.version) for spec in self.specifier]
-        self.extras = tuple(map(safe_extra, self.extras))
+        # packaging.requirements.Requirement uses a set for its extras. We use a variable-length tuple
+        self.extras: tuple[str] = tuple(map(safe_extra, self.extras))
         self.hashCmp = (
             self.key,
             self.url,
@@ -3186,13 +3447,13 @@ class Requirement(packaging.requirements.Requirement):
         )
         self.__hash = hash(self.hashCmp)
 
-    def __eq__(self, other):
+    def __eq__(self, other: object):
         return isinstance(other, Requirement) and self.hashCmp == other.hashCmp
 
     def __ne__(self, other):
         return not self == other
 
-    def __contains__(self, item):
+    def __contains__(self, item: Distribution | str | tuple[str, ...]) -> bool:
         if isinstance(item, Distribution):
             if item.key != self.key:
                 return False
@@ -3211,7 +3472,7 @@ class Requirement(packaging.requirements.Requirement):
         return "Requirement.parse(%r)" % str(self)
 
     @staticmethod
-    def parse(s):
+    def parse(s: str | Iterable[str]):
         (req,) = parse_requirements(s)
         return req
 
@@ -3226,15 +3487,18 @@ def _always_object(classes):
     return classes
 
 
-def _find_adapter(registry, ob):
+def _find_adapter(registry: Mapping[type, _AdapterT], ob: object) -> _AdapterT:
     """Return an adapter factory for `ob` from `registry`"""
     types = _always_object(inspect.getmro(getattr(ob, '__class__', type(ob))))
     for t in types:
         if t in registry:
             return registry[t]
+    # _find_adapter would previously return None, and immediately be called.
+    # So we're raising a TypeError to keep backward compatibility if anyone depended on that behaviour.
+    raise TypeError(f"Could not find adapter for {registry} and {ob}")
 
 
-def ensure_directory(path):
+def ensure_directory(path: StrOrBytesPath):
     """Ensure that the parent directory of `path` exists"""
     dirname = os.path.dirname(path)
     os.makedirs(dirname, exist_ok=True)
@@ -3243,7 +3507,7 @@ def ensure_directory(path):
 def _bypass_ensure_directory(path):
     """Sandbox-bypassing version of ensure_directory()"""
     if not WRITE_SUPPORT:
-        raise IOError('"os.mkdir" not supported on this platform.')
+        raise OSError('"os.mkdir" not supported on this platform.')
     dirname, filename = split(path)
     if dirname and filename and not isdir(dirname):
         _bypass_ensure_directory(dirname)
@@ -3253,7 +3517,7 @@ def _bypass_ensure_directory(path):
             pass
 
 
-def split_sections(s):
+def split_sections(s: _NestedStr) -> Iterator[tuple[str | None, list[str]]]:
     """Split a string or iterable thereof into (section, content) pairs
 
     Each ``section`` is a stripped version of the section header ("[section]")
@@ -3297,6 +3561,47 @@ def _mkstemp(*args, **kw):
 warnings.filterwarnings("ignore", category=PEP440Warning, append=True)
 
 
+class PkgResourcesDeprecationWarning(Warning):
+    """
+    Base class for warning about deprecations in ``pkg_resources``
+
+    This class is not derived from ``DeprecationWarning``, and as such is
+    visible by default.
+    """
+
+
+# Ported from ``setuptools`` to avoid introducing an import inter-dependency:
+_LOCALE_ENCODING = "locale" if sys.version_info >= (3, 10) else None
+
+
+def _read_utf8_with_fallback(file: str, fallback_encoding=_LOCALE_ENCODING) -> str:
+    """See setuptools.unicode_utils._read_utf8_with_fallback"""
+    try:
+        with open(file, "r", encoding="utf-8") as f:
+            return f.read()
+    except UnicodeDecodeError:  # pragma: no cover
+        msg = f"""\
+        ********************************************************************************
+        `encoding="utf-8"` fails with {file!r}, trying `encoding={fallback_encoding!r}`.
+
+        This fallback behaviour is considered **deprecated** and future versions of
+        `setuptools/pkg_resources` may not implement it.
+
+        Please encode {file!r} with "utf-8" to ensure future builds will succeed.
+
+        If this file was produced by `setuptools` itself, cleaning up the cached files
+        and re-building/re-installing the package with a newer version of `setuptools`
+        (e.g. by updating `build-system.requires` in its `pyproject.toml`)
+        might solve the problem.
+        ********************************************************************************
+        """
+        # TODO: Add a deadline?
+        #       See comment in setuptools.unicode_utils._Utf8EncodingNeeded
+        warnings.warn(msg, PkgResourcesDeprecationWarning, stacklevel=2)
+        with open(file, "r", encoding=fallback_encoding) as f:
+            return f.read()
+
+
 # from jaraco.functools 1.3
 def _call_aside(f, *args, **kwargs):
     f(*args, **kwargs)
@@ -3315,15 +3620,6 @@ def _initialize(g=globals()):
     )
 
 
-class PkgResourcesDeprecationWarning(Warning):
-    """
-    Base class for warning about deprecations in ``pkg_resources``
-
-    This class is not derived from ``DeprecationWarning``, and as such is
-    visible by default.
-    """
-
-
 @_call_aside
 def _initialize_master_working_set():
     """
@@ -3337,8 +3633,7 @@ def _initialize_master_working_set():
     Invocation by other packages is unsupported and done
     at their own risk.
     """
-    working_set = WorkingSet._build_master()
-    _declare_state('object', working_set=working_set)
+    working_set = _declare_state('object', 'working_set', WorkingSet._build_master())
 
     require = working_set.require
     iter_entry_points = working_set.iter_entry_points
@@ -3359,3 +3654,23 @@ def _initialize_master_working_set():
     # match order
     list(map(working_set.add_entry, sys.path))
     globals().update(locals())
+
+
+if TYPE_CHECKING:
+    # All of these are set by the @_call_aside methods above
+    __resource_manager = ResourceManager()  # Won't exist at runtime
+    resource_exists = __resource_manager.resource_exists
+    resource_isdir = __resource_manager.resource_isdir
+    resource_filename = __resource_manager.resource_filename
+    resource_stream = __resource_manager.resource_stream
+    resource_string = __resource_manager.resource_string
+    resource_listdir = __resource_manager.resource_listdir
+    set_extraction_path = __resource_manager.set_extraction_path
+    cleanup_resources = __resource_manager.cleanup_resources
+
+    working_set = WorkingSet()
+    require = working_set.require
+    iter_entry_points = working_set.iter_entry_points
+    add_activation_listener = working_set.subscribe
+    run_script = working_set.run_script
+    run_main = run_script
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__pycache__/__init__.cpython-312.pyc
index 15eeb38..e34597e 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pkg_resources/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__init__.py
index 5ebf595..edc21fa 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__init__.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__init__.py
@@ -1,7 +1,10 @@
 """
-Utilities for determining application-specific dirs. See  for details and
-usage.
+Utilities for determining application-specific dirs.
+
+See  for details and usage.
+
 """
+
 from __future__ import annotations
 
 import os
@@ -14,36 +17,36 @@ from .version import __version_tuple__ as __version_info__
 
 if TYPE_CHECKING:
     from pathlib import Path
+    from typing import Literal
 
-    if sys.version_info >= (3, 8):  # pragma: no cover (py38+)
-        from typing import Literal
-    else:  # pragma: no cover (py38+)
-        from pip._vendor.typing_extensions import Literal
+if sys.platform == "win32":
+    from pip._vendor.platformdirs.windows import Windows as _Result
+elif sys.platform == "darwin":
+    from pip._vendor.platformdirs.macos import MacOS as _Result
+else:
+    from pip._vendor.platformdirs.unix import Unix as _Result
 
 
 def _set_platform_dir_class() -> type[PlatformDirsABC]:
-    if sys.platform == "win32":
-        from pip._vendor.platformdirs.windows import Windows as Result
-    elif sys.platform == "darwin":
-        from pip._vendor.platformdirs.macos import MacOS as Result
-    else:
-        from pip._vendor.platformdirs.unix import Unix as Result
-
     if os.getenv("ANDROID_DATA") == "/data" and os.getenv("ANDROID_ROOT") == "/system":
         if os.getenv("SHELL") or os.getenv("PREFIX"):
-            return Result
+            return _Result
 
-        from pip._vendor.platformdirs.android import _android_folder
+        from pip._vendor.platformdirs.android import _android_folder  # noqa: PLC0415
 
         if _android_folder() is not None:
-            from pip._vendor.platformdirs.android import Android
+            from pip._vendor.platformdirs.android import Android  # noqa: PLC0415
 
-            return Android  # return to avoid redefinition of result
+            return Android  # return to avoid redefinition of a result
 
-    return Result
+    return _Result
 
 
-PlatformDirs = _set_platform_dir_class()  #: Currently active platform
+if TYPE_CHECKING:
+    # Work around mypy issue: https://github.com/python/mypy/issues/10962
+    PlatformDirs = _Result
+else:
+    PlatformDirs = _set_platform_dir_class()  #: Currently active platform
 AppDirs = PlatformDirs  #: Backwards compatibility with appdirs
 
 
@@ -264,6 +267,11 @@ def user_music_dir() -> str:
     return PlatformDirs().user_music_dir
 
 
+def user_desktop_dir() -> str:
+    """:returns: desktop directory tied to the user"""
+    return PlatformDirs().user_desktop_dir
+
+
 def user_runtime_dir(
     appname: str | None = None,
     appauthor: str | None | Literal[False] = None,
@@ -288,6 +296,30 @@ def user_runtime_dir(
     ).user_runtime_dir
 
 
+def site_runtime_dir(
+    appname: str | None = None,
+    appauthor: str | None | Literal[False] = None,
+    version: str | None = None,
+    opinion: bool = True,  # noqa: FBT001, FBT002
+    ensure_exists: bool = False,  # noqa: FBT001, FBT002
+) -> str:
+    """
+    :param appname: See `appname `.
+    :param appauthor: See `appauthor `.
+    :param version: See `version `.
+    :param opinion: See `opinion `.
+    :param ensure_exists: See `ensure_exists `.
+    :returns: runtime directory shared by users
+    """
+    return PlatformDirs(
+        appname=appname,
+        appauthor=appauthor,
+        version=version,
+        opinion=opinion,
+        ensure_exists=ensure_exists,
+    ).site_runtime_dir
+
+
 def user_data_path(
     appname: str | None = None,
     appauthor: str | None | Literal[False] = None,
@@ -481,7 +513,7 @@ def user_log_path(
 
 
 def user_documents_path() -> Path:
-    """:returns: documents path tied to the user"""
+    """:returns: documents a path tied to the user"""
     return PlatformDirs().user_documents_path
 
 
@@ -505,6 +537,11 @@ def user_music_path() -> Path:
     return PlatformDirs().user_music_path
 
 
+def user_desktop_path() -> Path:
+    """:returns: desktop path tied to the user"""
+    return PlatformDirs().user_desktop_path
+
+
 def user_runtime_path(
     appname: str | None = None,
     appauthor: str | None | Literal[False] = None,
@@ -529,38 +566,66 @@ def user_runtime_path(
     ).user_runtime_path
 
 
+def site_runtime_path(
+    appname: str | None = None,
+    appauthor: str | None | Literal[False] = None,
+    version: str | None = None,
+    opinion: bool = True,  # noqa: FBT001, FBT002
+    ensure_exists: bool = False,  # noqa: FBT001, FBT002
+) -> Path:
+    """
+    :param appname: See `appname `.
+    :param appauthor: See `appauthor `.
+    :param version: See `version `.
+    :param opinion: See `opinion `.
+    :param ensure_exists: See `ensure_exists `.
+    :returns: runtime path shared by users
+    """
+    return PlatformDirs(
+        appname=appname,
+        appauthor=appauthor,
+        version=version,
+        opinion=opinion,
+        ensure_exists=ensure_exists,
+    ).site_runtime_path
+
+
 __all__ = [
+    "AppDirs",
+    "PlatformDirs",
+    "PlatformDirsABC",
     "__version__",
     "__version_info__",
-    "PlatformDirs",
-    "AppDirs",
-    "PlatformDirsABC",
-    "user_data_dir",
-    "user_config_dir",
-    "user_cache_dir",
-    "user_state_dir",
-    "user_log_dir",
-    "user_documents_dir",
-    "user_downloads_dir",
-    "user_pictures_dir",
-    "user_videos_dir",
-    "user_music_dir",
-    "user_runtime_dir",
-    "site_data_dir",
-    "site_config_dir",
     "site_cache_dir",
-    "user_data_path",
-    "user_config_path",
-    "user_cache_path",
-    "user_state_path",
-    "user_log_path",
-    "user_documents_path",
-    "user_downloads_path",
-    "user_pictures_path",
-    "user_videos_path",
-    "user_music_path",
-    "user_runtime_path",
-    "site_data_path",
-    "site_config_path",
     "site_cache_path",
+    "site_config_dir",
+    "site_config_path",
+    "site_data_dir",
+    "site_data_path",
+    "site_runtime_dir",
+    "site_runtime_path",
+    "user_cache_dir",
+    "user_cache_path",
+    "user_config_dir",
+    "user_config_path",
+    "user_data_dir",
+    "user_data_path",
+    "user_desktop_dir",
+    "user_desktop_path",
+    "user_documents_dir",
+    "user_documents_path",
+    "user_downloads_dir",
+    "user_downloads_path",
+    "user_log_dir",
+    "user_log_path",
+    "user_music_dir",
+    "user_music_path",
+    "user_pictures_dir",
+    "user_pictures_path",
+    "user_runtime_dir",
+    "user_runtime_path",
+    "user_state_dir",
+    "user_state_path",
+    "user_videos_dir",
+    "user_videos_path",
 ]
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__main__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__main__.py
index 6a0d6dd..fa8a677 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__main__.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__main__.py
@@ -1,4 +1,5 @@
 """Main entry point."""
+
 from __future__ import annotations
 
 from pip._vendor.platformdirs import PlatformDirs, __version__
@@ -18,11 +19,12 @@ PROPS = (
     "site_data_dir",
     "site_config_dir",
     "site_cache_dir",
+    "site_runtime_dir",
 )
 
 
 def main() -> None:
-    """Run main entry point."""
+    """Run the main entry point."""
     app_name = "MyApp"
     app_author = "MyCompany"
 
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc
index 0ab1f59..d4c261d 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc
index 80ac5f4..6f12dd0 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/android.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/android.cpython-312.pyc
index b2393c8..88d00fb 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/android.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/android.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/api.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/api.cpython-312.pyc
index dfbd736..935a3b2 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/api.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/api.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc
index 7a0fdbc..89c9c8f 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc
index 7f5690e..f04ef88 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/version.cpython-312.pyc
index 435f749..84ee157 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/version.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/version.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc
index f2bfd43..659198b 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/android.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/android.py
index 76527dd..7004a85 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/android.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/android.py
@@ -1,21 +1,23 @@
 """Android."""
+
 from __future__ import annotations
 
 import os
 import re
 import sys
 from functools import lru_cache
-from typing import cast
+from typing import TYPE_CHECKING, cast
 
 from .api import PlatformDirsABC
 
 
 class Android(PlatformDirsABC):
     """
-    Follows the guidance `from here `_. Makes use of the
-    `appname `,
-    `version `,
-    `ensure_exists `.
+    Follows the guidance `from here `_.
+
+    Makes use of the `appname `, `version
+    `, `ensure_exists `.
+
     """
 
     @property
@@ -43,7 +45,7 @@ class Android(PlatformDirsABC):
 
     @property
     def user_cache_dir(self) -> str:
-        """:return: cache directory tied to the user, e.g. e.g. ``/data/user///cache/``"""
+        """:return: cache directory tied to the user, e.g.,``/data/user///cache/``"""
         return self._append_app_name_and_version(cast(str, _android_folder()), "cache")
 
     @property
@@ -92,6 +94,11 @@ class Android(PlatformDirsABC):
         """:return: music directory tied to the user e.g. ``/storage/emulated/0/Music``"""
         return _android_music_folder()
 
+    @property
+    def user_desktop_dir(self) -> str:
+        """:return: desktop directory tied to the user e.g. ``/storage/emulated/0/Desktop``"""
+        return "/storage/emulated/0/Desktop"
+
     @property
     def user_runtime_dir(self) -> str:
         """
@@ -103,18 +110,40 @@ class Android(PlatformDirsABC):
             path = os.path.join(path, "tmp")  # noqa: PTH118
         return path
 
+    @property
+    def site_runtime_dir(self) -> str:
+        """:return: runtime directory shared by users, same as `user_runtime_dir`"""
+        return self.user_runtime_dir
+
 
 @lru_cache(maxsize=1)
-def _android_folder() -> str | None:
+def _android_folder() -> str | None:  # noqa: C901
     """:return: base folder for the Android OS or None if it cannot be found"""
-    try:
-        # First try to get path to android app via pyjnius
-        from jnius import autoclass
+    result: str | None = None
+    # type checker isn't happy with our "import android", just don't do this when type checking see
+    # https://stackoverflow.com/a/61394121
+    if not TYPE_CHECKING:
+        try:
+            # First try to get a path to android app using python4android (if available)...
+            from android import mActivity  # noqa: PLC0415
 
-        context = autoclass("android.content.Context")
-        result: str | None = context.getFilesDir().getParentFile().getAbsolutePath()
-    except Exception:  # noqa: BLE001
-        # if fails find an android folder looking path on the sys.path
+            context = cast("android.content.Context", mActivity.getApplicationContext())  # noqa: F821
+            result = context.getFilesDir().getParentFile().getAbsolutePath()
+        except Exception:  # noqa: BLE001
+            result = None
+    if result is None:
+        try:
+            # ...and fall back to using plain pyjnius, if python4android isn't available or doesn't deliver any useful
+            # result...
+            from jnius import autoclass  # noqa: PLC0415
+
+            context = autoclass("android.content.Context")
+            result = context.getFilesDir().getParentFile().getAbsolutePath()
+        except Exception:  # noqa: BLE001
+            result = None
+    if result is None:
+        # and if that fails, too, find an android folder looking at path on the sys.path
+        # warning: only works for apps installed under /data, not adopted storage etc.
         pattern = re.compile(r"/data/(data|user/\d+)/(.+)/files")
         for path in sys.path:
             if pattern.match(path):
@@ -122,6 +151,16 @@ def _android_folder() -> str | None:
                 break
         else:
             result = None
+    if result is None:
+        # one last try: find an android folder looking at path on the sys.path taking adopted storage paths into
+        # account
+        pattern = re.compile(r"/mnt/expand/[a-fA-F0-9-]{36}/(data|user/\d+)/(.+)/files")
+        for path in sys.path:
+            if pattern.match(path):
+                result = path.split("/files")[0]
+                break
+        else:
+            result = None
     return result
 
 
@@ -130,7 +169,7 @@ def _android_documents_folder() -> str:
     """:return: documents folder for the Android OS"""
     # Get directories with pyjnius
     try:
-        from jnius import autoclass
+        from jnius import autoclass  # noqa: PLC0415
 
         context = autoclass("android.content.Context")
         environment = autoclass("android.os.Environment")
@@ -146,7 +185,7 @@ def _android_downloads_folder() -> str:
     """:return: downloads folder for the Android OS"""
     # Get directories with pyjnius
     try:
-        from jnius import autoclass
+        from jnius import autoclass  # noqa: PLC0415
 
         context = autoclass("android.content.Context")
         environment = autoclass("android.os.Environment")
@@ -162,7 +201,7 @@ def _android_pictures_folder() -> str:
     """:return: pictures folder for the Android OS"""
     # Get directories with pyjnius
     try:
-        from jnius import autoclass
+        from jnius import autoclass  # noqa: PLC0415
 
         context = autoclass("android.content.Context")
         environment = autoclass("android.os.Environment")
@@ -178,7 +217,7 @@ def _android_videos_folder() -> str:
     """:return: videos folder for the Android OS"""
     # Get directories with pyjnius
     try:
-        from jnius import autoclass
+        from jnius import autoclass  # noqa: PLC0415
 
         context = autoclass("android.content.Context")
         environment = autoclass("android.os.Environment")
@@ -194,7 +233,7 @@ def _android_music_folder() -> str:
     """:return: music folder for the Android OS"""
     # Get directories with pyjnius
     try:
-        from jnius import autoclass
+        from jnius import autoclass  # noqa: PLC0415
 
         context = autoclass("android.content.Context")
         environment = autoclass("android.os.Environment")
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/api.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/api.py
index d64ebb9..18d660e 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/api.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/api.py
@@ -1,4 +1,5 @@
 """Base API."""
+
 from __future__ import annotations
 
 import os
@@ -7,18 +8,13 @@ from pathlib import Path
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    import sys
-
-    if sys.version_info >= (3, 8):  # pragma: no cover (py38+)
-        from typing import Literal
-    else:  # pragma: no cover (py38+)
-        from pip._vendor.typing_extensions import Literal
+    from typing import Iterator, Literal
 
 
-class PlatformDirsABC(ABC):
+class PlatformDirsABC(ABC):  # noqa: PLR0904
     """Abstract base class for platform directories."""
 
-    def __init__(  # noqa: PLR0913
+    def __init__(  # noqa: PLR0913, PLR0917
         self,
         appname: str | None = None,
         appauthor: str | None | Literal[False] = None,
@@ -38,34 +34,47 @@ class PlatformDirsABC(ABC):
         :param multipath: See `multipath`.
         :param opinion: See `opinion`.
         :param ensure_exists: See `ensure_exists`.
+
         """
         self.appname = appname  #: The name of application.
         self.appauthor = appauthor
         """
-        The name of the app author or distributing body for this application. Typically, it is the owning company name.
-        Defaults to `appname`. You may pass ``False`` to disable it.
+        The name of the app author or distributing body for this application.
+
+        Typically, it is the owning company name. Defaults to `appname`. You may pass ``False`` to disable it.
+
         """
         self.version = version
         """
-        An optional version path element to append to the path. You might want to use this if you want multiple versions
-        of your app to be able to run independently. If used, this would typically be ``.``.
+        An optional version path element to append to the path.
+
+        You might want to use this if you want multiple versions of your app to be able to run independently. If used,
+        this would typically be ``.``.
+
         """
         self.roaming = roaming
         """
-        Whether to use the roaming appdata directory on Windows. That means that for users on a Windows network setup
-        for roaming profiles, this user data will be synced on login (see
-        `here `_).
+        Whether to use the roaming appdata directory on Windows.
+
+        That means that for users on a Windows network setup for roaming profiles, this user data will be synced on
+        login (see
+        `here `_).
+
         """
         self.multipath = multipath
         """
-        An optional parameter only applicable to Unix/Linux which indicates that the entire list of data dirs should be
-        returned. By default, the first item would only be returned.
+        An optional parameter which indicates that the entire list of data dirs should be returned.
+
+        By default, the first item would only be returned.
+
         """
         self.opinion = opinion  #: A flag to indicating to use opinionated values.
         self.ensure_exists = ensure_exists
         """
         Optionally create the directory (and any missing parents) upon access if it does not exist.
+
         By default, no directories are created.
+
         """
 
     def _append_app_name_and_version(self, *base: str) -> str:
@@ -82,6 +91,12 @@ class PlatformDirsABC(ABC):
         if self.ensure_exists:
             Path(path).mkdir(parents=True, exist_ok=True)
 
+    def _first_item_as_path_if_multipath(self, directory: str) -> Path:
+        if self.multipath:
+            # If multipath is True, the first path is returned.
+            directory = directory.split(os.pathsep)[0]
+        return Path(directory)
+
     @property
     @abstractmethod
     def user_data_dir(self) -> str:
@@ -147,11 +162,21 @@ class PlatformDirsABC(ABC):
     def user_music_dir(self) -> str:
         """:return: music directory tied to the user"""
 
+    @property
+    @abstractmethod
+    def user_desktop_dir(self) -> str:
+        """:return: desktop directory tied to the user"""
+
     @property
     @abstractmethod
     def user_runtime_dir(self) -> str:
         """:return: runtime directory tied to the user"""
 
+    @property
+    @abstractmethod
+    def site_runtime_dir(self) -> str:
+        """:return: runtime directory shared by users"""
+
     @property
     def user_data_path(self) -> Path:
         """:return: data path tied to the user"""
@@ -194,7 +219,7 @@ class PlatformDirsABC(ABC):
 
     @property
     def user_documents_path(self) -> Path:
-        """:return: documents path tied to the user"""
+        """:return: documents a path tied to the user"""
         return Path(self.user_documents_dir)
 
     @property
@@ -217,7 +242,57 @@ class PlatformDirsABC(ABC):
         """:return: music path tied to the user"""
         return Path(self.user_music_dir)
 
+    @property
+    def user_desktop_path(self) -> Path:
+        """:return: desktop path tied to the user"""
+        return Path(self.user_desktop_dir)
+
     @property
     def user_runtime_path(self) -> Path:
         """:return: runtime path tied to the user"""
         return Path(self.user_runtime_dir)
+
+    @property
+    def site_runtime_path(self) -> Path:
+        """:return: runtime path shared by users"""
+        return Path(self.site_runtime_dir)
+
+    def iter_config_dirs(self) -> Iterator[str]:
+        """:yield: all user and site configuration directories."""
+        yield self.user_config_dir
+        yield self.site_config_dir
+
+    def iter_data_dirs(self) -> Iterator[str]:
+        """:yield: all user and site data directories."""
+        yield self.user_data_dir
+        yield self.site_data_dir
+
+    def iter_cache_dirs(self) -> Iterator[str]:
+        """:yield: all user and site cache directories."""
+        yield self.user_cache_dir
+        yield self.site_cache_dir
+
+    def iter_runtime_dirs(self) -> Iterator[str]:
+        """:yield: all user and site runtime directories."""
+        yield self.user_runtime_dir
+        yield self.site_runtime_dir
+
+    def iter_config_paths(self) -> Iterator[Path]:
+        """:yield: all user and site configuration paths."""
+        for path in self.iter_config_dirs():
+            yield Path(path)
+
+    def iter_data_paths(self) -> Iterator[Path]:
+        """:yield: all user and site data paths."""
+        for path in self.iter_data_dirs():
+            yield Path(path)
+
+    def iter_cache_paths(self) -> Iterator[Path]:
+        """:yield: all user and site cache paths."""
+        for path in self.iter_cache_dirs():
+            yield Path(path)
+
+    def iter_runtime_paths(self) -> Iterator[Path]:
+        """:yield: all user and site runtime paths."""
+        for path in self.iter_runtime_dirs():
+            yield Path(path)
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/macos.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/macos.py
index a753e2a..e4b0391 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/macos.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/macos.py
@@ -1,18 +1,27 @@
 """macOS."""
+
 from __future__ import annotations
 
 import os.path
+import sys
+from typing import TYPE_CHECKING
 
 from .api import PlatformDirsABC
 
+if TYPE_CHECKING:
+    from pathlib import Path
+
 
 class MacOS(PlatformDirsABC):
     """
-    Platform directories for the macOS operating system. Follows the guidance from `Apple documentation
-    `_.
+    Platform directories for the macOS operating system.
+
+    Follows the guidance from
+    `Apple documentation `_.
     Makes use of the `appname `,
     `version `,
     `ensure_exists `.
+
     """
 
     @property
@@ -22,8 +31,25 @@ class MacOS(PlatformDirsABC):
 
     @property
     def site_data_dir(self) -> str:
-        """:return: data directory shared by users, e.g. ``/Library/Application Support/$appname/$version``"""
-        return self._append_app_name_and_version("/Library/Application Support")
+        """
+        :return: data directory shared by users, e.g. ``/Library/Application Support/$appname/$version``.
+          If we're using a Python binary managed by `Homebrew `_, the directory
+          will be under the Homebrew prefix, e.g. ``/opt/homebrew/share/$appname/$version``.
+          If `multipath ` is enabled, and we're in Homebrew,
+          the response is a multi-path string separated by ":", e.g.
+          ``/opt/homebrew/share/$appname/$version:/Library/Application Support/$appname/$version``
+        """
+        is_homebrew = sys.prefix.startswith("/opt/homebrew")
+        path_list = [self._append_app_name_and_version("/opt/homebrew/share")] if is_homebrew else []
+        path_list.append(self._append_app_name_and_version("/Library/Application Support"))
+        if self.multipath:
+            return os.pathsep.join(path_list)
+        return path_list[0]
+
+    @property
+    def site_data_path(self) -> Path:
+        """:return: data path shared by users. Only return the first item, even if ``multipath`` is set to ``True``"""
+        return self._first_item_as_path_if_multipath(self.site_data_dir)
 
     @property
     def user_config_dir(self) -> str:
@@ -42,8 +68,25 @@ class MacOS(PlatformDirsABC):
 
     @property
     def site_cache_dir(self) -> str:
-        """:return: cache directory shared by users, e.g. ``/Library/Caches/$appname/$version``"""
-        return self._append_app_name_and_version("/Library/Caches")
+        """
+        :return: cache directory shared by users, e.g. ``/Library/Caches/$appname/$version``.
+          If we're using a Python binary managed by `Homebrew `_, the directory
+          will be under the Homebrew prefix, e.g. ``/opt/homebrew/var/cache/$appname/$version``.
+          If `multipath ` is enabled, and we're in Homebrew,
+          the response is a multi-path string separated by ":", e.g.
+          ``/opt/homebrew/var/cache/$appname/$version:/Library/Caches/$appname/$version``
+        """
+        is_homebrew = sys.prefix.startswith("/opt/homebrew")
+        path_list = [self._append_app_name_and_version("/opt/homebrew/var/cache")] if is_homebrew else []
+        path_list.append(self._append_app_name_and_version("/Library/Caches"))
+        if self.multipath:
+            return os.pathsep.join(path_list)
+        return path_list[0]
+
+    @property
+    def site_cache_path(self) -> Path:
+        """:return: cache path shared by users. Only return the first item, even if ``multipath`` is set to ``True``"""
+        return self._first_item_as_path_if_multipath(self.site_cache_dir)
 
     @property
     def user_state_dir(self) -> str:
@@ -80,11 +123,21 @@ class MacOS(PlatformDirsABC):
         """:return: music directory tied to the user, e.g. ``~/Music``"""
         return os.path.expanduser("~/Music")  # noqa: PTH111
 
+    @property
+    def user_desktop_dir(self) -> str:
+        """:return: desktop directory tied to the user, e.g. ``~/Desktop``"""
+        return os.path.expanduser("~/Desktop")  # noqa: PTH111
+
     @property
     def user_runtime_dir(self) -> str:
         """:return: runtime directory tied to the user, e.g. ``~/Library/Caches/TemporaryItems/$appname/$version``"""
         return self._append_app_name_and_version(os.path.expanduser("~/Library/Caches/TemporaryItems"))  # noqa: PTH111
 
+    @property
+    def site_runtime_dir(self) -> str:
+        """:return: runtime directory shared by users, same as `user_runtime_dir`"""
+        return self.user_runtime_dir
+
 
 __all__ = [
     "MacOS",
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/py.typed
similarity index 100%
rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/py.typed
rename to llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/py.typed
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/unix.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/unix.py
index 468b0ab..f1942e9 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/unix.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/unix.py
@@ -1,16 +1,18 @@
 """Unix."""
+
 from __future__ import annotations
 
 import os
 import sys
 from configparser import ConfigParser
 from pathlib import Path
+from typing import Iterator, NoReturn
 
 from .api import PlatformDirsABC
 
 if sys.platform == "win32":
 
-    def getuid() -> int:
+    def getuid() -> NoReturn:
         msg = "should only be used on Unix"
         raise RuntimeError(msg)
 
@@ -18,17 +20,17 @@ else:
     from os import getuid
 
 
-class Unix(PlatformDirsABC):
+class Unix(PlatformDirsABC):  # noqa: PLR0904
     """
-    On Unix/Linux, we follow the
-    `XDG Basedir Spec `_. The spec allows
-    overriding directories with environment variables. The examples show are the default values, alongside the name of
-    the environment variable that overrides them. Makes use of the
-    `appname `,
-    `version `,
-    `multipath `,
-    `opinion `,
-    `ensure_exists `.
+    On Unix/Linux, we follow the `XDG Basedir Spec `_.
+
+    The spec allows overriding directories with environment variables. The examples shown are the default values,
+    alongside the name of the environment variable that overrides them. Makes use of the `appname
+    `, `version `, `multipath
+    `, `opinion `, `ensure_exists
+    `.
+
     """
 
     @property
@@ -43,24 +45,24 @@ class Unix(PlatformDirsABC):
         return self._append_app_name_and_version(path)
 
     @property
-    def site_data_dir(self) -> str:
-        """
-        :return: data directories shared by users (if `multipath ` is
-         enabled and ``XDG_DATA_DIR`` is set and a multi path the response is also a multi path separated by the OS
-         path separator), e.g. ``/usr/local/share/$appname/$version`` or ``/usr/share/$appname/$version``
-        """
-        # XDG default for $XDG_DATA_DIRS; only first, if multipath is False
+    def _site_data_dirs(self) -> list[str]:
         path = os.environ.get("XDG_DATA_DIRS", "")
         if not path.strip():
             path = f"/usr/local/share{os.pathsep}/usr/share"
-        return self._with_multi_path(path)
+        return [self._append_app_name_and_version(p) for p in path.split(os.pathsep)]
 
-    def _with_multi_path(self, path: str) -> str:
-        path_list = path.split(os.pathsep)
+    @property
+    def site_data_dir(self) -> str:
+        """
+        :return: data directories shared by users (if `multipath ` is
+         enabled and ``XDG_DATA_DIRS`` is set and a multi path the response is also a multi path separated by the
+         OS path separator), e.g. ``/usr/local/share/$appname/$version`` or ``/usr/share/$appname/$version``
+        """
+        # XDG default for $XDG_DATA_DIRS; only first, if multipath is False
+        dirs = self._site_data_dirs
         if not self.multipath:
-            path_list = path_list[0:1]
-        path_list = [self._append_app_name_and_version(os.path.expanduser(p)) for p in path_list]  # noqa: PTH111
-        return os.pathsep.join(path_list)
+            return dirs[0]
+        return os.pathsep.join(dirs)
 
     @property
     def user_config_dir(self) -> str:
@@ -74,17 +76,24 @@ class Unix(PlatformDirsABC):
         return self._append_app_name_and_version(path)
 
     @property
-    def site_config_dir(self) -> str:
-        """
-        :return: config directories shared by users (if `multipath `
-         is enabled and ``XDG_DATA_DIR`` is set and a multi path the response is also a multi path separated by the OS
-         path separator), e.g. ``/etc/xdg/$appname/$version``
-        """
-        # XDG default for $XDG_CONFIG_DIRS only first, if multipath is False
+    def _site_config_dirs(self) -> list[str]:
         path = os.environ.get("XDG_CONFIG_DIRS", "")
         if not path.strip():
             path = "/etc/xdg"
-        return self._with_multi_path(path)
+        return [self._append_app_name_and_version(p) for p in path.split(os.pathsep)]
+
+    @property
+    def site_config_dir(self) -> str:
+        """
+        :return: config directories shared by users (if `multipath `
+         is enabled and ``XDG_CONFIG_DIRS`` is set and a multi path the response is also a multi path separated by
+         the OS path separator), e.g. ``/etc/xdg/$appname/$version``
+        """
+        # XDG default for $XDG_CONFIG_DIRS only first, if multipath is False
+        dirs = self._site_config_dirs
+        if not self.multipath:
+            return dirs[0]
+        return os.pathsep.join(dirs)
 
     @property
     def user_cache_dir(self) -> str:
@@ -99,8 +108,8 @@ class Unix(PlatformDirsABC):
 
     @property
     def site_cache_dir(self) -> str:
-        """:return: cache directory shared by users, e.g. ``/var/tmp/$appname/$version``"""
-        return self._append_app_name_and_version("/var/tmp")  # noqa: S108
+        """:return: cache directory shared by users, e.g. ``/var/cache/$appname/$version``"""
+        return self._append_app_name_and_version("/var/cache")
 
     @property
     def user_state_dir(self) -> str:
@@ -119,6 +128,7 @@ class Unix(PlatformDirsABC):
         path = self.user_state_dir
         if self.opinion:
             path = os.path.join(path, "log")  # noqa: PTH118
+            self._optionally_create_directory(path)
         return path
 
     @property
@@ -146,6 +156,11 @@ class Unix(PlatformDirsABC):
         """:return: music directory tied to the user, e.g. ``~/Music``"""
         return _get_user_media_dir("XDG_MUSIC_DIR", "~/Music")
 
+    @property
+    def user_desktop_dir(self) -> str:
+        """:return: desktop directory tied to the user, e.g. ``~/Desktop``"""
+        return _get_user_media_dir("XDG_DESKTOP_DIR", "~/Desktop")
+
     @property
     def user_runtime_dir(self) -> str:
         """
@@ -166,26 +181,52 @@ class Unix(PlatformDirsABC):
                 path = f"/run/user/{getuid()}"
         return self._append_app_name_and_version(path)
 
+    @property
+    def site_runtime_dir(self) -> str:
+        """
+        :return: runtime directory shared by users, e.g. ``/run/$appname/$version`` or \
+        ``$XDG_RUNTIME_DIR/$appname/$version``.
+
+        Note that this behaves almost exactly like `user_runtime_dir` if ``$XDG_RUNTIME_DIR`` is set, but will
+        fall back to paths associated to the root user instead of a regular logged-in user if it's not set.
+
+        If you wish to ensure that a logged-in root user path is returned e.g. ``/run/user/0``, use `user_runtime_dir`
+        instead.
+
+        For FreeBSD/OpenBSD/NetBSD, it would return ``/var/run/$appname/$version`` if ``$XDG_RUNTIME_DIR`` is not set.
+        """
+        path = os.environ.get("XDG_RUNTIME_DIR", "")
+        if not path.strip():
+            if sys.platform.startswith(("freebsd", "openbsd", "netbsd")):
+                path = "/var/run"
+            else:
+                path = "/run"
+        return self._append_app_name_and_version(path)
+
     @property
     def site_data_path(self) -> Path:
-        """:return: data path shared by users. Only return first item, even if ``multipath`` is set to ``True``"""
+        """:return: data path shared by users. Only return the first item, even if ``multipath`` is set to ``True``"""
         return self._first_item_as_path_if_multipath(self.site_data_dir)
 
     @property
     def site_config_path(self) -> Path:
-        """:return: config path shared by the users. Only return first item, even if ``multipath`` is set to ``True``"""
+        """:return: config path shared by the users, returns the first item, even if ``multipath`` is set to ``True``"""
         return self._first_item_as_path_if_multipath(self.site_config_dir)
 
     @property
     def site_cache_path(self) -> Path:
-        """:return: cache path shared by users. Only return first item, even if ``multipath`` is set to ``True``"""
+        """:return: cache path shared by users. Only return the first item, even if ``multipath`` is set to ``True``"""
         return self._first_item_as_path_if_multipath(self.site_cache_dir)
 
-    def _first_item_as_path_if_multipath(self, directory: str) -> Path:
-        if self.multipath:
-            # If multipath is True, the first path is returned.
-            directory = directory.split(os.pathsep)[0]
-        return Path(directory)
+    def iter_config_dirs(self) -> Iterator[str]:
+        """:yield: all user and site configuration directories."""
+        yield self.user_config_dir
+        yield from self._site_config_dirs
+
+    def iter_data_dirs(self) -> Iterator[str]:
+        """:yield: all user and site data directories."""
+        yield self.user_data_dir
+        yield from self._site_data_dirs
 
 
 def _get_user_media_dir(env_var: str, fallback_tilde_path: str) -> str:
@@ -199,7 +240,12 @@ def _get_user_media_dir(env_var: str, fallback_tilde_path: str) -> str:
 
 
 def _get_user_dirs_folder(key: str) -> str | None:
-    """Return directory from user-dirs.dirs config file. See https://freedesktop.org/wiki/Software/xdg-user-dirs/."""
+    """
+    Return directory from user-dirs.dirs config file.
+
+    See https://freedesktop.org/wiki/Software/xdg-user-dirs/.
+
+    """
     user_dirs_config_path = Path(Unix().user_config_dir) / "user-dirs.dirs"
     if user_dirs_config_path.exists():
         parser = ConfigParser()
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/version.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/version.py
index dc8c44c..afb4924 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/version.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/version.py
@@ -1,4 +1,16 @@
 # file generated by setuptools_scm
 # don't change, don't track in version control
-__version__ = version = '3.8.1'
-__version_tuple__ = version_tuple = (3, 8, 1)
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple, Union
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '4.3.6'
+__version_tuple__ = version_tuple = (4, 3, 6)
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/windows.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/windows.py
index b52c9c6..d7bc960 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/windows.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/platformdirs/windows.py
@@ -1,7 +1,7 @@
 """Windows."""
+
 from __future__ import annotations
 
-import ctypes
 import os
 import sys
 from functools import lru_cache
@@ -15,15 +15,13 @@ if TYPE_CHECKING:
 
 class Windows(PlatformDirsABC):
     """
-    `MSDN on where to store app data files
-    `_.
-    Makes use of the
-    `appname `,
-    `appauthor `,
-    `version `,
-    `roaming `,
-    `opinion `,
-    `ensure_exists `.
+    `MSDN on where to store app data files `_.
+
+    Makes use of the `appname `, `appauthor
+    `, `version `, `roaming
+    `, `opinion `, `ensure_exists
+    `.
+
     """
 
     @property
@@ -122,6 +120,11 @@ class Windows(PlatformDirsABC):
         """:return: music directory tied to the user e.g. ``%USERPROFILE%\\Music``"""
         return os.path.normpath(get_win_folder("CSIDL_MYMUSIC"))
 
+    @property
+    def user_desktop_dir(self) -> str:
+        """:return: desktop directory tied to the user, e.g. ``%USERPROFILE%\\Desktop``"""
+        return os.path.normpath(get_win_folder("CSIDL_DESKTOPDIRECTORY"))
+
     @property
     def user_runtime_dir(self) -> str:
         """
@@ -131,6 +134,11 @@ class Windows(PlatformDirsABC):
         path = os.path.normpath(os.path.join(get_win_folder("CSIDL_LOCAL_APPDATA"), "Temp"))  # noqa: PTH118
         return self._append_parts(path)
 
+    @property
+    def site_runtime_dir(self) -> str:
+        """:return: runtime directory shared by users, same as `user_runtime_dir`"""
+        return self.user_runtime_dir
+
 
 def get_win_folder_from_env_vars(csidl_name: str) -> str:
     """Get folder from environment variables."""
@@ -154,7 +162,7 @@ def get_win_folder_from_env_vars(csidl_name: str) -> str:
 
 
 def get_win_folder_if_csidl_name_not_env_var(csidl_name: str) -> str | None:
-    """Get folder for a CSIDL name that does not exist as an environment variable."""
+    """Get a folder for a CSIDL name that does not exist as an environment variable."""
     if csidl_name == "CSIDL_PERSONAL":
         return os.path.join(os.path.normpath(os.environ["USERPROFILE"]), "Documents")  # noqa: PTH118
 
@@ -178,6 +186,7 @@ def get_win_folder_from_registry(csidl_name: str) -> str:
 
     This is a fallback technique at best. I'm not sure if using the registry for these guarantees us the correct answer
     for all CSIDL_* names.
+
     """
     shell_folder_name = {
         "CSIDL_APPDATA": "AppData",
@@ -194,7 +203,7 @@ def get_win_folder_from_registry(csidl_name: str) -> str:
         raise ValueError(msg)
     if sys.platform != "win32":  # only needed for mypy type checker to know that this code runs only on Windows
         raise NotImplementedError
-    import winreg
+    import winreg  # noqa: PLC0415
 
     key = winreg.OpenKey(winreg.HKEY_CURRENT_USER, r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders")
     directory, _ = winreg.QueryValueEx(key, shell_folder_name)
@@ -207,6 +216,8 @@ def get_win_folder_via_ctypes(csidl_name: str) -> str:
     # Use 'CSIDL_PROFILE' (40) and append the default folder 'Downloads' instead.
     # https://learn.microsoft.com/en-us/windows/win32/shell/knownfolderid
 
+    import ctypes  # noqa: PLC0415
+
     csidl_const = {
         "CSIDL_APPDATA": 26,
         "CSIDL_COMMON_APPDATA": 35,
@@ -216,6 +227,7 @@ def get_win_folder_via_ctypes(csidl_name: str) -> str:
         "CSIDL_MYVIDEO": 14,
         "CSIDL_MYMUSIC": 13,
         "CSIDL_DOWNLOADS": 40,
+        "CSIDL_DESKTOPDIRECTORY": 16,
     }.get(csidl_name)
     if csidl_const is None:
         msg = f"Unknown CSIDL name: {csidl_name}"
@@ -225,7 +237,7 @@ def get_win_folder_via_ctypes(csidl_name: str) -> str:
     windll = getattr(ctypes, "windll")  # noqa: B009 # using getattr to avoid false positive with mypy type checker
     windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf)
 
-    # Downgrade to short path name if it has highbit chars.
+    # Downgrade to short path name if it has high-bit chars.
     if any(ord(c) > 255 for c in buf):  # noqa: PLR2004
         buf2 = ctypes.create_unicode_buffer(1024)
         if windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024):
@@ -238,10 +250,15 @@ def get_win_folder_via_ctypes(csidl_name: str) -> str:
 
 
 def _pick_get_win_folder() -> Callable[[str], str]:
-    if hasattr(ctypes, "windll"):
-        return get_win_folder_via_ctypes
     try:
-        import winreg  # noqa: F401
+        import ctypes  # noqa: PLC0415
+    except ImportError:
+        pass
+    else:
+        if hasattr(ctypes, "windll"):
+            return get_win_folder_via_ctypes
+    try:
+        import winreg  # noqa: PLC0415, F401
     except ImportError:
         return get_win_folder_from_env_vars
     else:
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__init__.py
index 39c84aa..60ae9bb 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__init__.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__init__.py
@@ -21,12 +21,12 @@
     .. _Pygments master branch:
        https://github.com/pygments/pygments/archive/master.zip#egg=Pygments-dev
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 from io import StringIO, BytesIO
 
-__version__ = '2.15.1'
+__version__ = '2.18.0'
 __docformat__ = 'restructuredtext'
 
 __all__ = ['lex', 'format', 'highlight']
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__main__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__main__.py
index 2f7f8cb..dcc6e5a 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__main__.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__main__.py
@@ -4,7 +4,7 @@
 
     Main entry point for ``python -m pygments``.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__init__.cpython-312.pyc
index 50111b5..a05b89b 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__main__.cpython-312.pyc
index 0c4e3d7..d58c8ca 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/__main__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/cmdline.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/cmdline.cpython-312.pyc
index 48702ed..5937b76 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/cmdline.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/cmdline.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/console.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/console.cpython-312.pyc
index b2b0b73..c2dffbc 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/console.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/console.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/filter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/filter.cpython-312.pyc
index 6f38e06..55953a5 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/filter.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/filter.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/formatter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/formatter.cpython-312.pyc
index f7e431a..ff72da4 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/formatter.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/formatter.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/lexer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/lexer.cpython-312.pyc
index 095e88f..6daf4a9 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/lexer.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/lexer.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/modeline.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/modeline.cpython-312.pyc
index b8c02ec..beb08e4 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/modeline.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/modeline.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/plugin.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/plugin.cpython-312.pyc
index 3e91b3e..2ad0ab0 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/plugin.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/plugin.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/regexopt.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/regexopt.cpython-312.pyc
index 4a11192..1e59bf5 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/regexopt.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/regexopt.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/scanner.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/scanner.cpython-312.pyc
index 26c3094..c89fe4f 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/scanner.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/scanner.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/sphinxext.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/sphinxext.cpython-312.pyc
index 3d2aa14..d95fb2f 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/sphinxext.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/sphinxext.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/style.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/style.cpython-312.pyc
index 69b1bb0..1128164 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/style.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/style.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/token.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/token.cpython-312.pyc
index b136f84..3bda93b 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/token.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/token.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/unistring.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/unistring.cpython-312.pyc
index aded0d7..3d0c04c 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/unistring.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/unistring.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/util.cpython-312.pyc
index 3d5735e..61db035 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/util.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/__pycache__/util.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/cmdline.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/cmdline.py
index eec1775..0a7072e 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/cmdline.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/cmdline.py
@@ -4,7 +4,7 @@
 
     Command line interface.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -68,19 +68,19 @@ def _print_help(what, name):
     try:
         if what == 'lexer':
             cls = get_lexer_by_name(name)
-            print("Help on the %s lexer:" % cls.name)
+            print(f"Help on the {cls.name} lexer:")
             print(dedent(cls.__doc__))
         elif what == 'formatter':
             cls = find_formatter_class(name)
-            print("Help on the %s formatter:" % cls.name)
+            print(f"Help on the {cls.name} formatter:")
             print(dedent(cls.__doc__))
         elif what == 'filter':
             cls = find_filter_class(name)
-            print("Help on the %s filter:" % name)
+            print(f"Help on the {name} filter:")
             print(dedent(cls.__doc__))
         return 0
     except (AttributeError, ValueError):
-        print("%s not found!" % what, file=sys.stderr)
+        print(f"{what} not found!", file=sys.stderr)
         return 1
 
 
@@ -97,7 +97,7 @@ def _print_list(what):
             info.append(tup)
         info.sort()
         for i in info:
-            print(('* %s\n    %s %s') % i)
+            print(('* {}\n    {} {}').format(*i))
 
     elif what == 'formatter':
         print()
@@ -112,7 +112,7 @@ def _print_list(what):
             info.append(tup)
         info.sort()
         for i in info:
-            print(('* %s\n    %s %s') % i)
+            print(('* {}\n    {} {}').format(*i))
 
     elif what == 'filter':
         print()
@@ -122,7 +122,7 @@ def _print_list(what):
         for name in get_all_filters():
             cls = find_filter_class(name)
             print("* " + name + ':')
-            print("    %s" % docstring_headline(cls))
+            print(f"    {docstring_headline(cls)}")
 
     elif what == 'style':
         print()
@@ -132,7 +132,7 @@ def _print_list(what):
         for name in get_all_styles():
             cls = get_style_by_name(name)
             print("* " + name + ':')
-            print("    %s" % docstring_headline(cls))
+            print(f"    {docstring_headline(cls)}")
 
 
 def _print_list_as_json(requested_items):
@@ -185,8 +185,8 @@ def main_inner(parser, argns):
         return 0
 
     if argns.V:
-        print('Pygments version %s, (c) 2006-2023 by Georg Brandl, Matthäus '
-              'Chajdas and contributors.' % __version__)
+        print(f'Pygments version {__version__}, (c) 2006-2024 by Georg Brandl, Matthäus '
+              'Chajdas and contributors.')
         return 0
 
     def is_only_option(opt):
@@ -469,11 +469,11 @@ def main_inner(parser, argns):
         outfile = UnclosingTextIOWrapper(outfile, encoding=fmter.encoding)
         fmter.encoding = None
         try:
-            import pip._vendor.colorama.initialise as colorama_initialise
+            import colorama.initialise
         except ImportError:
             pass
         else:
-            outfile = colorama_initialise.wrap_stream(
+            outfile = colorama.initialise.wrap_stream(
                 outfile, convert=None, strip=None, autoreset=False, wrap=True)
 
     # When using the LaTeX formatter and the option `escapeinside` is
@@ -659,7 +659,7 @@ def main(args=sys.argv):
         msg = info[-1].strip()
         if len(info) >= 3:
             # extract relevant file and position info
-            msg += '\n   (f%s)' % info[-2].split('\n')[0].strip()[1:]
+            msg += '\n   (f{})'.format(info[-2].split('\n')[0].strip()[1:])
         print(file=sys.stderr)
         print('*** Error while highlighting:', file=sys.stderr)
         print(msg, file=sys.stderr)
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/console.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/console.py
index deb4937..4c1a062 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/console.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/console.py
@@ -4,7 +4,7 @@
 
     Format colored console output.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -27,12 +27,12 @@ light_colors = ["brightblack", "brightred", "brightgreen", "brightyellow", "brig
                 "brightmagenta", "brightcyan", "white"]
 
 x = 30
-for d, l in zip(dark_colors, light_colors):
-    codes[d] = esc + "%im" % x
-    codes[l] = esc + "%im" % (60 + x)
+for dark, light in zip(dark_colors, light_colors):
+    codes[dark] = esc + "%im" % x
+    codes[light] = esc + "%im" % (60 + x)
     x += 1
 
-del d, l, x
+del dark, light, x
 
 codes["white"] = codes["bold"]
 
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filter.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filter.py
index dafa08d..aa6f760 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filter.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filter.py
@@ -4,7 +4,7 @@
 
     Module that implements the default filter.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -62,8 +62,7 @@ class FunctionFilter(Filter):
 
     def __init__(self, **options):
         if not hasattr(self, 'function'):
-            raise TypeError('%r used without bound function' %
-                            self.__class__.__name__)
+            raise TypeError(f'{self.__class__.__name__!r} used without bound function')
         Filter.__init__(self, **options)
 
     def filter(self, lexer, stream):
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__init__.py
index 5aa9ecb..9255ca2 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__init__.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__init__.py
@@ -5,7 +5,7 @@
     Module containing filter lookup functions and default
     filters.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -39,7 +39,7 @@ def get_filter_by_name(filtername, **options):
     if cls:
         return cls(**options)
     else:
-        raise ClassNotFound('filter %r not found' % filtername)
+        raise ClassNotFound(f'filter {filtername!r} not found')
 
 
 def get_all_filters():
@@ -79,9 +79,9 @@ class CodeTagFilter(Filter):
         Filter.__init__(self, **options)
         tags = get_list_opt(options, 'codetags',
                             ['XXX', 'TODO', 'FIXME', 'BUG', 'NOTE'])
-        self.tag_re = re.compile(r'\b(%s)\b' % '|'.join([
+        self.tag_re = re.compile(r'\b({})\b'.format('|'.join([
             re.escape(tag) for tag in tags if tag
-        ]))
+        ])))
 
     def filter(self, lexer, stream):
         regex = self.tag_re
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__pycache__/__init__.cpython-312.pyc
index 6bbc50c..b34ce3b 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/filters/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatter.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatter.py
index 3ca4892..d266603 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatter.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatter.py
@@ -4,7 +4,7 @@
 
     Base formatter class.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -122,3 +122,8 @@ class Formatter:
             # wrap the outfile in a StreamWriter
             outfile = codecs.lookup(self.encoding)[3](outfile)
         return self.format_unencoded(tokensource, outfile)
+
+    # Allow writing Formatter[str] or Formatter[bytes]. That's equivalent to
+    # Formatter. This helps when using third-party type stubs from typeshed.
+    def __class_getitem__(cls, name):
+        return cls
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__init__.py
index 39db842..f19e993 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__init__.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__init__.py
@@ -4,7 +4,7 @@
 
     Pygments formatters.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -77,7 +77,7 @@ def get_formatter_by_name(_alias, **options):
     """
     cls = find_formatter_class(_alias)
     if cls is None:
-        raise ClassNotFound("no formatter found for name %r" % _alias)
+        raise ClassNotFound(f"no formatter found for name {_alias!r}")
     return cls(**options)
 
 
@@ -103,17 +103,16 @@ def load_formatter_from_file(filename, formattername="CustomFormatter", **option
             exec(f.read(), custom_namespace)
         # Retrieve the class `formattername` from that namespace
         if formattername not in custom_namespace:
-            raise ClassNotFound('no valid %s class found in %s' %
-                                (formattername, filename))
+            raise ClassNotFound(f'no valid {formattername} class found in {filename}')
         formatter_class = custom_namespace[formattername]
         # And finally instantiate it with the options
         return formatter_class(**options)
     except OSError as err:
-        raise ClassNotFound('cannot read %s: %s' % (filename, err))
+        raise ClassNotFound(f'cannot read {filename}: {err}')
     except ClassNotFound:
         raise
     except Exception as err:
-        raise ClassNotFound('error when loading custom formatter: %s' % err)
+        raise ClassNotFound(f'error when loading custom formatter: {err}')
 
 
 def get_formatter_for_filename(fn, **options):
@@ -131,11 +130,11 @@ def get_formatter_for_filename(fn, **options):
                 if name not in _formatter_cache:
                     _load_formatters(modname)
                 return _formatter_cache[name](**options)
-    for cls in find_plugin_formatters():
+    for _name, cls in find_plugin_formatters():
         for filename in cls.filenames:
             if _fn_matches(fn, filename):
                 return cls(**options)
-    raise ClassNotFound("no formatter found for file name %r" % fn)
+    raise ClassNotFound(f"no formatter found for file name {fn!r}")
 
 
 class _automodule(types.ModuleType):
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/__init__.cpython-312.pyc
index 5c4262f..99a6874 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/_mapping.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/_mapping.cpython-312.pyc
index 99225bc..71718b9 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/_mapping.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/_mapping.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/bbcode.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/bbcode.cpython-312.pyc
index d6848b3..6afff51 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/bbcode.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/bbcode.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/groff.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/groff.cpython-312.pyc
index 8aac973..6908ead 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/groff.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/groff.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/html.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/html.cpython-312.pyc
index 82fd68e..ada67e4 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/html.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/html.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/img.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/img.cpython-312.pyc
index c2d0774..d459704 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/img.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/img.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/irc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/irc.cpython-312.pyc
index 31ce7f7..20aaa4b 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/irc.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/irc.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/latex.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/latex.cpython-312.pyc
index 9d3b3f5..b6c912e 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/latex.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/latex.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/other.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/other.cpython-312.pyc
index 31265aa..b00a262 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/other.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/other.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/pangomarkup.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/pangomarkup.cpython-312.pyc
index 59c823d..d385898 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/pangomarkup.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/pangomarkup.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/rtf.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/rtf.cpython-312.pyc
index 42e8375..1c3b00a 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/rtf.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/rtf.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/svg.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/svg.cpython-312.pyc
index 81fee0a..3ab9d74 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/svg.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/svg.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal.cpython-312.pyc
index 50ff34c..0df3c6c 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal256.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal256.cpython-312.pyc
index 628fd69..d3d8167 100644
Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal256.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/__pycache__/terminal256.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/bbcode.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/bbcode.py
index c4db8f4..5a05bd9 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/bbcode.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/bbcode.py
@@ -4,7 +4,7 @@
 
     BBcode formatter.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -60,7 +60,7 @@ class BBCodeFormatter(Formatter):
         for ttype, ndef in self.style:
             start = end = ''
             if ndef['color']:
-                start += '[color=#%s]' % ndef['color']
+                start += '[color=#{}]'.format(ndef['color'])
                 end = '[/color]' + end
             if ndef['bold']:
                 start += '[b]'
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/groff.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/groff.py
index 30a528e..5c8a958 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/groff.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/groff.py
@@ -4,7 +4,7 @@
 
     Formatter for groff output.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -63,7 +63,7 @@ class GroffFormatter(Formatter):
         for ttype, ndef in self.style:
             start = end = ''
             if ndef['color']:
-                start += '\\m[%s]' % ndef['color']
+                start += '\\m[{}]'.format(ndef['color'])
                 end = '\\m[]' + end
             if ndef['bold']:
                 start += bold
@@ -72,7 +72,7 @@ class GroffFormatter(Formatter):
                 start += italic
                 end = regular + end
             if ndef['bgcolor']:
-                start += '\\M[%s]' % ndef['bgcolor']
+                start += '\\M[{}]'.format(ndef['bgcolor'])
                 end = '\\M[]' + end
 
             self.styles[ttype] = start, end
diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/html.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/html.py
index 931d7c3..7aa938f 100644
--- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/html.py
+++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/html.py
@@ -4,7 +4,7 @@
 
     Formatter for HTML output.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -62,7 +62,7 @@ def _get_ttype_class(ttype):
 CSSFILE_TEMPLATE = '''\
 /*
 generated by Pygments 
-Copyright 2006-2023 by the Pygments team.
+Copyright 2006-2024 by the Pygments team.
 Licensed under the BSD license, see LICENSE for details.
 */
 %(styledefs)s
@@ -73,7 +73,7 @@ DOC_HEADER = '''\
    "http://www.w3.org/TR/html4/strict.dtd">
 
 
@@ -323,6 +323,7 @@ class HtmlFormatter(Formatter):
         If set to the path of a ctags file, wrap names in anchor tags that
         link to their definitions. `lineanchors` should be used, and the
         tags file should specify line numbers (see the `-n` option to ctags).
+        The tags file is assumed to be encoded in UTF-8.
 
         .. versionadded:: 1.6
 
@@ -487,7 +488,7 @@ class HtmlFormatter(Formatter):
             name = self._get_css_class(ttype)
             style = ''
             if ndef['color']:
-                style += 'color: %s; ' % webify(ndef['color'])
+                style += 'color: {}; '.format(webify(ndef['color']))
             if ndef['bold']:
                 style += 'font-weight: bold; '
             if ndef['italic']:
@@ -495,9 +496,9 @@ class HtmlFormatter(Formatter):
             if ndef['underline']:
                 style += 'text-decoration: underline; '
             if ndef['bgcolor']:
-                style += 'background-color: %s; ' % webify(ndef['bgcolor'])
+                style += 'background-color: {}; '.format(webify(ndef['bgcolor']))
             if ndef['border']:
-                style += 'border: 1px solid %s; ' % webify(ndef['border'])
+                style += 'border: 1px solid {}; '.format(webify(ndef['border']))
             if style:
                 t2c[ttype] = name
                 # save len(ttype) to enable ordering the styles by
@@ -529,7 +530,7 @@ class HtmlFormatter(Formatter):
         styles.sort()
 
         lines = [
-            '%s { %s } /* %s */' % (prefix(cls), style, repr(ttype)[6:])
+            f'{prefix(cls)} {{ {style} }} /* {repr(ttype)[6:]} */'
             for (level, ttype, cls, style) in styles
         ]
 
@@ -547,24 +548,24 @@ class HtmlFormatter(Formatter):
             if Text in self.ttype2class:
                 text_style = ' ' + self.class2style[self.ttype2class[Text]][0]
             lines.insert(
-                0, '%s{ background: %s;%s }' % (
+                0, '{}{{ background: {};{} }}'.format(
                     prefix(''), bg_color, text_style
                 )
             )
         if hl_color is not None:
             lines.insert(
-                0, '%s { background-color: %s }' % (prefix('hll'), hl_color)
+                0, '{} {{ background-color: {} }}'.format(prefix('hll'), hl_color)
             )
 
         return lines
 
     def get_linenos_style_defs(self):
         lines = [
-            'pre { %s }' % self._pre_style,
-            'td.linenos .normal { %s }' % self._linenos_style,
-            'span.linenos { %s }' % self._linenos_style,
-            'td.linenos .special { %s }' % self._linenos_special_style,
-            'span.linenos.special { %s }' % self._linenos_special_style,
+            f'pre {{ {self._pre_style} }}',
+            f'td.linenos .normal {{ {self._linenos_style} }}',
+            f'span.linenos {{ {self._linenos_style} }}',
+            f'td.linenos .special {{ {self._linenos_special_style} }}',
+            f'span.linenos.special {{ {self._linenos_special_style} }}',
         ]
 
         return lines
@@ -593,17 +594,15 @@ class HtmlFormatter(Formatter):
 
     @property
     def _linenos_style(self):
-        return 'color: %s; background-color: %s; padding-left: 5px; padding-right: 5px;' % (
-            self.style.line_number_color,
-            self.style.line_number_background_color
-        )
+        color = self.style.line_number_color
+        background_color = self.style.line_number_background_color
+        return f'color: {color}; background-color: {background_color}; padding-left: 5px; padding-right: 5px;'
 
     @property
     def _linenos_special_style(self):
-        return 'color: %s; background-color: %s; padding-left: 5px; padding-right: 5px;' % (
-            self.style.line_number_special_color,
-            self.style.line_number_special_background_color
-        )
+        color = self.style.line_number_special_color
+        background_color = self.style.line_number_special_background_color
+        return f'color: {color}; background-color: {background_color}; padding-left: 5px; padding-right: 5px;'
 
     def _decodeifneeded(self, value):
         if isinstance(value, bytes):
@@ -684,9 +683,9 @@ class HtmlFormatter(Formatter):
 
             if nocls:
                 if special_line:
-                    style = ' style="%s"' % self._linenos_special_style
+                    style = f' style="{self._linenos_special_style}"'
                 else:
-                    style = ' style="%s"' % self._linenos_style
+                    style = f' style="{self._linenos_style}"'
             else:
                 if special_line:
                     style = ' class="special"'
@@ -694,7 +693,7 @@ class HtmlFormatter(Formatter):
                     style = ' class="normal"'
 
             if style:
-                line = '%s' % (style, line)
+                line = f'{line}'
 
             lines.append(line)
 
@@ -743,9 +742,9 @@ class HtmlFormatter(Formatter):
 
             if nocls:
                 if special_line:
-                    style = ' style="%s"' % self._linenos_special_style
+                    style = f' style="{self._linenos_special_style}"'
                 else:
-                    style = ' style="%s"' % self._linenos_style
+                    style = f' style="{self._linenos_style}"'
             else:
                 if special_line:
                     style = ' class="linenos special"'
@@ -753,7 +752,7 @@ class HtmlFormatter(Formatter):
                     style = ' class="linenos"'
 
             if style:
-                linenos = '%s' % (style, line)
+                linenos = f'{line}'
             else:
                 linenos = line
 
@@ -790,13 +789,13 @@ class HtmlFormatter(Formatter):
         style = []
         if (self.noclasses and not self.nobackground and
                 self.style.background_color is not None):
-            style.append('background: %s' % (self.style.background_color,))
+            style.append(f'background: {self.style.background_color}')
         if self.cssstyles:
             style.append(self.cssstyles)
         style = '; '.join(style)
 
-        yield 0, ('')
+        yield 0, ('')
         yield from inner
         yield 0, '\n'
 
@@ -813,7 +812,7 @@ class HtmlFormatter(Formatter):
 
         # the empty span here is to keep leading empty lines from being
         # ignored by HTML parsers
-        yield 0, ('')
+        yield 0, ('')
         yield from inner
         yield 0, '
' @@ -842,18 +841,18 @@ class HtmlFormatter(Formatter): try: cspan = self.span_element_openers[ttype] except KeyError: - title = ' title="%s"' % '.'.join(ttype) if self.debug_token_types else '' + title = ' title="{}"'.format('.'.join(ttype)) if self.debug_token_types else '' if nocls: css_style = self._get_css_inline_styles(ttype) if css_style: css_style = self.class2style[css_style][0] - cspan = '' % (css_style, title) + cspan = f'' else: cspan = '' else: css_class = self._get_css_classes(ttype) if css_class: - cspan = '' % (css_class, title) + cspan = f'' else: cspan = '' self.span_element_openers[ttype] = cspan @@ -908,7 +907,7 @@ class HtmlFormatter(Formatter): def _lookup_ctag(self, token): entry = ctags.TagEntry() if self._ctags.find(entry, token.encode(), 0): - return entry['file'], entry['lineNumber'] + return entry['file'].decode(), entry['lineNumber'] else: return None, None @@ -926,11 +925,10 @@ class HtmlFormatter(Formatter): if self.noclasses: style = '' if self.style.highlight_color is not None: - style = (' style="background-color: %s"' % - (self.style.highlight_color,)) - yield 1, '%s' % (style, value) + style = (f' style="background-color: {self.style.highlight_color}"') + yield 1, f'{value}' else: - yield 1, '%s' % value + yield 1, f'{value}' else: yield 1, value diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/img.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/img.py index a338c15..7542cfa 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/img.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/img.py @@ -4,10 +4,9 @@ Formatter for Pixmap output. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ - import os import sys @@ -68,6 +67,15 @@ class FontManager: self.font_size = font_size self.fonts = {} self.encoding = None + self.variable = False + if hasattr(font_name, 'read') or os.path.isfile(font_name): + font = ImageFont.truetype(font_name, self.font_size) + self.variable = True + for style in STYLES: + self.fonts[style] = font + + return + if sys.platform.startswith('win'): if not font_name: self.font_name = DEFAULT_FONT_NAME_WIN @@ -82,7 +90,7 @@ class FontManager: self._create_nix() def _get_nix_font_path(self, name, style): - proc = subprocess.Popen(['fc-list', "%s:style=%s" % (name, style), 'file'], + proc = subprocess.Popen(['fc-list', f"{name}:style={style}", 'file'], stdout=subprocess.PIPE, stderr=None) stdout, _ = proc.communicate() if proc.returncode == 0: @@ -102,8 +110,7 @@ class FontManager: self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size) break else: - raise FontNotFound('No usable fonts named: "%s"' % - self.font_name) + raise FontNotFound(f'No usable fonts named: "{self.font_name}"') for style in ('ITALIC', 'BOLD', 'BOLDITALIC'): for stylename in STYLES[style]: path = self._get_nix_font_path(self.font_name, stylename) @@ -134,8 +141,7 @@ class FontManager: self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size) break else: - raise FontNotFound('No usable fonts named: "%s"' % - self.font_name) + raise FontNotFound(f'No usable fonts named: "{self.font_name}"') for style in ('ITALIC', 'BOLD', 'BOLDITALIC'): for stylename in STYLES[style]: path = self._get_mac_font_path(font_map, self.font_name, stylename) @@ -152,15 +158,14 @@ class FontManager: for suffix in ('', ' (TrueType)'): for style in styles: try: - valname = '%s%s%s' % (basename, style and ' '+style, suffix) + valname = '{}{}{}'.format(basename, style and ' '+style, suffix) val, _ = _winreg.QueryValueEx(key, valname) return val except OSError: continue else: if fail: - raise FontNotFound('Font %s (%s) not found in registry' % - (basename, styles[0])) + raise FontNotFound(f'Font {basename} ({styles[0]}) not found in registry') return None def _create_win(self): @@ -223,14 +228,43 @@ class FontManager: Get the font based on bold and italic flags. """ if bold and oblique: + if self.variable: + return self.get_style('BOLDITALIC') + return self.fonts['BOLDITALIC'] elif bold: + if self.variable: + return self.get_style('BOLD') + return self.fonts['BOLD'] elif oblique: + if self.variable: + return self.get_style('ITALIC') + return self.fonts['ITALIC'] else: + if self.variable: + return self.get_style('NORMAL') + return self.fonts['NORMAL'] + def get_style(self, style): + """ + Get the specified style of the font if it is a variable font. + If not found, return the normal font. + """ + font = self.fonts[style] + for style_name in STYLES[style]: + try: + font.set_variation_by_name(style_name) + return font + except ValueError: + pass + except OSError: + return font + + return font + class ImageFormatter(Formatter): """ @@ -258,6 +292,8 @@ class ImageFormatter(Formatter): The font name to be used as the base font from which others, such as bold and italic fonts will be generated. This really should be a monospace font to look sane. + If a filename or a file-like object is specified, the user must + provide different styles of the font. Default: "Courier New" on Windows, "Menlo" on Mac OS, and "DejaVu Sans Mono" on \\*nix @@ -594,7 +630,11 @@ class ImageFormatter(Formatter): fill=self.hl_color) for pos, value, font, text_fg, text_bg in self.drawables: if text_bg: - text_size = draw.textsize(text=value, font=font) + # see deprecations https://pillow.readthedocs.io/en/stable/releasenotes/9.2.0.html#font-size-and-offset-methods + if hasattr(draw, 'textsize'): + text_size = draw.textsize(text=value, font=font) + else: + text_size = font.getbbox(value)[2:] draw.rectangle([pos[0], pos[1], pos[0] + text_size[0], pos[1] + text_size[1]], fill=text_bg) draw.text(pos, value, font=font, fill=text_fg) im.save(outfile, self.image_format.upper()) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/irc.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/irc.py index 2144d43..468c287 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/irc.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/irc.py @@ -4,7 +4,7 @@ Formatter for IRC output - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/latex.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/latex.py index ca539b4..0ec9089 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/latex.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/latex.py @@ -4,7 +4,7 @@ Formatter for LaTeX fancyvrb output. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -23,21 +23,21 @@ def escape_tex(text, commandprefix): return text.replace('\\', '\x00'). \ replace('{', '\x01'). \ replace('}', '\x02'). \ - replace('\x00', r'\%sZbs{}' % commandprefix). \ - replace('\x01', r'\%sZob{}' % commandprefix). \ - replace('\x02', r'\%sZcb{}' % commandprefix). \ - replace('^', r'\%sZca{}' % commandprefix). \ - replace('_', r'\%sZus{}' % commandprefix). \ - replace('&', r'\%sZam{}' % commandprefix). \ - replace('<', r'\%sZlt{}' % commandprefix). \ - replace('>', r'\%sZgt{}' % commandprefix). \ - replace('#', r'\%sZsh{}' % commandprefix). \ - replace('%', r'\%sZpc{}' % commandprefix). \ - replace('$', r'\%sZdl{}' % commandprefix). \ - replace('-', r'\%sZhy{}' % commandprefix). \ - replace("'", r'\%sZsq{}' % commandprefix). \ - replace('"', r'\%sZdq{}' % commandprefix). \ - replace('~', r'\%sZti{}' % commandprefix) + replace('\x00', rf'\{commandprefix}Zbs{{}}'). \ + replace('\x01', rf'\{commandprefix}Zob{{}}'). \ + replace('\x02', rf'\{commandprefix}Zcb{{}}'). \ + replace('^', rf'\{commandprefix}Zca{{}}'). \ + replace('_', rf'\{commandprefix}Zus{{}}'). \ + replace('&', rf'\{commandprefix}Zam{{}}'). \ + replace('<', rf'\{commandprefix}Zlt{{}}'). \ + replace('>', rf'\{commandprefix}Zgt{{}}'). \ + replace('#', rf'\{commandprefix}Zsh{{}}'). \ + replace('%', rf'\{commandprefix}Zpc{{}}'). \ + replace('$', rf'\{commandprefix}Zdl{{}}'). \ + replace('-', rf'\{commandprefix}Zhy{{}}'). \ + replace("'", rf'\{commandprefix}Zsq{{}}'). \ + replace('"', rf'\{commandprefix}Zdq{{}}'). \ + replace('~', rf'\{commandprefix}Zti{{}}') DOC_TEMPLATE = r''' @@ -304,17 +304,14 @@ class LatexFormatter(Formatter): if ndef['mono']: cmndef += r'\let\$$@ff=\textsf' if ndef['color']: - cmndef += (r'\def\$$@tc##1{\textcolor[rgb]{%s}{##1}}' % - rgbcolor(ndef['color'])) + cmndef += (r'\def\$$@tc##1{{\textcolor[rgb]{{{}}}{{##1}}}}'.format(rgbcolor(ndef['color']))) if ndef['border']: - cmndef += (r'\def\$$@bc##1{{\setlength{\fboxsep}{\string -\fboxrule}' - r'\fcolorbox[rgb]{%s}{%s}{\strut ##1}}}' % - (rgbcolor(ndef['border']), + cmndef += (r'\def\$$@bc##1{{{{\setlength{{\fboxsep}}{{\string -\fboxrule}}' + r'\fcolorbox[rgb]{{{}}}{{{}}}{{\strut ##1}}}}}}'.format(rgbcolor(ndef['border']), rgbcolor(ndef['bgcolor']))) elif ndef['bgcolor']: - cmndef += (r'\def\$$@bc##1{{\setlength{\fboxsep}{0pt}' - r'\colorbox[rgb]{%s}{\strut ##1}}}' % - rgbcolor(ndef['bgcolor'])) + cmndef += (r'\def\$$@bc##1{{{{\setlength{{\fboxsep}}{{0pt}}' + r'\colorbox[rgb]{{{}}}{{\strut ##1}}}}}}'.format(rgbcolor(ndef['bgcolor']))) if cmndef == '': continue cmndef = cmndef.replace('$$', cp) @@ -329,7 +326,7 @@ class LatexFormatter(Formatter): cp = self.commandprefix styles = [] for name, definition in self.cmd2def.items(): - styles.append(r'\@namedef{%s@tok@%s}{%s}' % (cp, name, definition)) + styles.append(rf'\@namedef{{{cp}@tok@{name}}}{{{definition}}}') return STYLE_TEMPLATE % {'cp': self.commandprefix, 'styles': '\n'.join(styles)} @@ -410,10 +407,10 @@ class LatexFormatter(Formatter): spl = value.split('\n') for line in spl[:-1]: if line: - outfile.write("\\%s{%s}{%s}" % (cp, styleval, line)) + outfile.write(f"\\{cp}{{{styleval}}}{{{line}}}") outfile.write('\n') if spl[-1]: - outfile.write("\\%s{%s}{%s}" % (cp, styleval, spl[-1])) + outfile.write(f"\\{cp}{{{styleval}}}{{{spl[-1]}}}") else: outfile.write(value) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/other.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/other.py index 990ead4..de8d9dc 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/other.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/other.py @@ -4,7 +4,7 @@ Other formatters: NullFormatter, RawTokenFormatter. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -74,8 +74,7 @@ class RawTokenFormatter(Formatter): try: colorize(self.error_color, '') except KeyError: - raise ValueError("Invalid color %r specified" % - self.error_color) + raise ValueError(f"Invalid color {self.error_color!r} specified") def format(self, tokensource, outfile): try: @@ -147,7 +146,7 @@ class TestcaseFormatter(Formatter): outbuf = [] for ttype, value in tokensource: rawbuf.append(value) - outbuf.append('%s(%s, %r),\n' % (indentation, ttype, value)) + outbuf.append(f'{indentation}({ttype}, {value!r}),\n') before = TESTCASE_BEFORE % (''.join(rawbuf),) during = ''.join(outbuf) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/pangomarkup.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/pangomarkup.py index 6bb325d..dfed53a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/pangomarkup.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/pangomarkup.py @@ -4,7 +4,7 @@ Formatter for Pango markup output. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -45,7 +45,7 @@ class PangoMarkupFormatter(Formatter): start = '' end = '' if style['color']: - start += '' % style['color'] + start += ''.format(style['color']) end = '' + end if style['bold']: start += '' diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/rtf.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/rtf.py index 125189c..eca2a41 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/rtf.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/rtf.py @@ -4,12 +4,14 @@ A formatter that generates RTF files. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ +from collections import OrderedDict from pip._vendor.pygments.formatter import Formatter -from pip._vendor.pygments.util import get_int_opt, surrogatepair +from pip._vendor.pygments.style import _ansimap +from pip._vendor.pygments.util import get_bool_opt, get_int_opt, get_list_opt, surrogatepair __all__ = ['RtfFormatter'] @@ -42,6 +44,59 @@ class RtfFormatter(Formatter): default is 24 half-points, giving a size 12 font. .. versionadded:: 2.0 + + `linenos` + Turn on line numbering (default: ``False``). + + .. versionadded:: 2.18 + + `lineno_fontsize` + Font size for line numbers. Size is specified in half points + (default: `fontsize`). + + .. versionadded:: 2.18 + + `lineno_padding` + Number of spaces between the (inline) line numbers and the + source code (default: ``2``). + + .. versionadded:: 2.18 + + `linenostart` + The line number for the first line (default: ``1``). + + .. versionadded:: 2.18 + + `linenostep` + If set to a number n > 1, only every nth line number is printed. + + .. versionadded:: 2.18 + + `lineno_color` + Color for line numbers specified as a hex triplet, e.g. ``'5e5e5e'``. + Defaults to the style's line number color if it is a hex triplet, + otherwise ansi bright black. + + .. versionadded:: 2.18 + + `hl_lines` + Specify a list of lines to be highlighted, as line numbers separated by + spaces, e.g. ``'3 7 8'``. The line numbers are relative to the input + (i.e. the first line is line 1) unless `hl_linenostart` is set. + + .. versionadded:: 2.18 + + `hl_color` + Color for highlighting the lines specified in `hl_lines`, specified as + a hex triplet (default: style's `highlight_color`). + + .. versionadded:: 2.18 + + `hl_linenostart` + If set to ``True`` line numbers in `hl_lines` are specified + relative to `linenostart` (default ``False``). + + .. versionadded:: 2.18 """ name = 'RTF' aliases = ['rtf'] @@ -62,6 +117,40 @@ class RtfFormatter(Formatter): Formatter.__init__(self, **options) self.fontface = options.get('fontface') or '' self.fontsize = get_int_opt(options, 'fontsize', 0) + self.linenos = get_bool_opt(options, 'linenos', False) + self.lineno_fontsize = get_int_opt(options, 'lineno_fontsize', + self.fontsize) + self.lineno_padding = get_int_opt(options, 'lineno_padding', 2) + self.linenostart = abs(get_int_opt(options, 'linenostart', 1)) + self.linenostep = abs(get_int_opt(options, 'linenostep', 1)) + self.hl_linenostart = get_bool_opt(options, 'hl_linenostart', False) + + self.hl_color = options.get('hl_color', '') + if not self.hl_color: + self.hl_color = self.style.highlight_color + + self.hl_lines = [] + for lineno in get_list_opt(options, 'hl_lines', []): + try: + lineno = int(lineno) + if self.hl_linenostart: + lineno = lineno - self.linenostart + 1 + self.hl_lines.append(lineno) + except ValueError: + pass + + self.lineno_color = options.get('lineno_color', '') + if not self.lineno_color: + if self.style.line_number_color == 'inherit': + # style color is the css value 'inherit' + # default to ansi bright-black + self.lineno_color = _ansimap['ansibrightblack'] + else: + # style color is assumed to be a hex triplet as other + # colors in pygments/style.py + self.lineno_color = self.style.line_number_color + + self.color_mapping = self._create_color_mapping() def _escape(self, text): return text.replace('\\', '\\\\') \ @@ -90,43 +179,145 @@ class RtfFormatter(Formatter): # Force surrogate pairs buf.append('{\\u%d}{\\u%d}' % surrogatepair(cn)) - return ''.join(buf).replace('\n', '\\par\n') + return ''.join(buf).replace('\n', '\\par') - def format_unencoded(self, tokensource, outfile): - # rtf 1.8 header - outfile.write('{\\rtf1\\ansi\\uc0\\deff0' - '{\\fonttbl{\\f0\\fmodern\\fprq1\\fcharset0%s;}}' - '{\\colortbl;' % (self.fontface and - ' ' + self._escape(self.fontface) or - '')) + @staticmethod + def hex_to_rtf_color(hex_color): + if hex_color[0] == "#": + hex_color = hex_color[1:] - # convert colors and save them in a mapping to access them later. - color_mapping = {} + return '\\red%d\\green%d\\blue%d;' % ( + int(hex_color[0:2], 16), + int(hex_color[2:4], 16), + int(hex_color[4:6], 16) + ) + + def _split_tokens_on_newlines(self, tokensource): + """ + Split tokens containing newline characters into multiple token + each representing a line of the input file. Needed for numbering + lines of e.g. multiline comments. + """ + for ttype, value in tokensource: + if value == '\n': + yield (ttype, value) + elif "\n" in value: + lines = value.split("\n") + for line in lines[:-1]: + yield (ttype, line+"\n") + if lines[-1]: + yield (ttype, lines[-1]) + else: + yield (ttype, value) + + def _create_color_mapping(self): + """ + Create a mapping of style hex colors to index/offset in + the RTF color table. + """ + color_mapping = OrderedDict() offset = 1 + + if self.linenos: + color_mapping[self.lineno_color] = offset + offset += 1 + + if self.hl_lines: + color_mapping[self.hl_color] = offset + offset += 1 + for _, style in self.style: for color in style['color'], style['bgcolor'], style['border']: if color and color not in color_mapping: color_mapping[color] = offset - outfile.write('\\red%d\\green%d\\blue%d;' % ( - int(color[0:2], 16), - int(color[2:4], 16), - int(color[4:6], 16) - )) offset += 1 - outfile.write('}\\f0 ') + + return color_mapping + + @property + def _lineno_template(self): + if self.lineno_fontsize != self.fontsize: + return '{{\\fs{} \\cf{} %s{}}}'.format(self.lineno_fontsize, + self.color_mapping[self.lineno_color], + " " * self.lineno_padding) + + return '{{\\cf{} %s{}}}'.format(self.color_mapping[self.lineno_color], + " " * self.lineno_padding) + + @property + def _hl_open_str(self): + return rf'{{\highlight{self.color_mapping[self.hl_color]} ' + + @property + def _rtf_header(self): + lines = [] + # rtf 1.8 header + lines.append('{\\rtf1\\ansi\\uc0\\deff0' + '{\\fonttbl{\\f0\\fmodern\\fprq1\\fcharset0%s;}}' + % (self.fontface and ' ' + + self._escape(self.fontface) or '')) + + # color table + lines.append('{\\colortbl;') + for color, _ in self.color_mapping.items(): + lines.append(self.hex_to_rtf_color(color)) + lines.append('}') + + # font and fontsize + lines.append('\\f0\\sa0') if self.fontsize: - outfile.write('\\fs%d' % self.fontsize) + lines.append('\\fs%d' % self.fontsize) + + # ensure Libre Office Writer imports and renders consecutive + # space characters the same width, needed for line numbering. + # https://bugs.documentfoundation.org/show_bug.cgi?id=144050 + lines.append('\\dntblnsbdb') + + return lines + + def format_unencoded(self, tokensource, outfile): + for line in self._rtf_header: + outfile.write(line + "\n") + + tokensource = self._split_tokens_on_newlines(tokensource) + + # first pass of tokens to count lines, needed for line numbering + if self.linenos: + line_count = 0 + tokens = [] # for copying the token source generator + for ttype, value in tokensource: + tokens.append((ttype, value)) + if value.endswith("\n"): + line_count += 1 + + # width of line number strings (for padding with spaces) + linenos_width = len(str(line_count+self.linenostart-1)) + + tokensource = tokens # highlight stream + lineno = 1 + start_new_line = True for ttype, value in tokensource: + if start_new_line and lineno in self.hl_lines: + outfile.write(self._hl_open_str) + + if start_new_line and self.linenos: + if (lineno-self.linenostart+1)%self.linenostep == 0: + current_lineno = lineno + self.linenostart - 1 + lineno_str = str(current_lineno).rjust(linenos_width) + else: + lineno_str = "".rjust(linenos_width) + outfile.write(self._lineno_template % lineno_str) + while not self.style.styles_token(ttype) and ttype.parent: ttype = ttype.parent style = self.style.style_for_token(ttype) buf = [] if style['bgcolor']: - buf.append('\\cb%d' % color_mapping[style['bgcolor']]) + buf.append('\\cb%d' % self.color_mapping[style['bgcolor']]) if style['color']: - buf.append('\\cf%d' % color_mapping[style['color']]) + buf.append('\\cf%d' % self.color_mapping[style['color']]) if style['bold']: buf.append('\\b') if style['italic']: @@ -135,12 +326,24 @@ class RtfFormatter(Formatter): buf.append('\\ul') if style['border']: buf.append('\\chbrdr\\chcfpat%d' % - color_mapping[style['border']]) + self.color_mapping[style['border']]) start = ''.join(buf) if start: - outfile.write('{%s ' % start) + outfile.write(f'{{{start} ') outfile.write(self._escape_text(value)) if start: outfile.write('}') + start_new_line = False - outfile.write('}') + # complete line of input + if value.endswith("\n"): + # close line highlighting + if lineno in self.hl_lines: + outfile.write('}') + # newline in RTF file after closing } + outfile.write("\n") + + start_new_line = True + lineno += 1 + + outfile.write('}\n') diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/svg.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/svg.py index a8727ed..d3e018f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/svg.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/svg.py @@ -4,7 +4,7 @@ Formatter for SVG output. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -60,11 +60,11 @@ class SvgFormatter(Formatter): `linenostep` If set to a number n > 1, only every nth line number is printed. - + `linenowidth` Maximum width devoted to line numbers (default: ``3*ystep``, sufficient - for up to 4-digit line numbers. Increase width for longer code blocks). - + for up to 4-digit line numbers. Increase width for longer code blocks). + `xoffset` Starting offset in X direction, defaults to ``0``. @@ -97,10 +97,11 @@ class SvgFormatter(Formatter): self.fontsize = options.get('fontsize', '14px') self.xoffset = get_int_opt(options, 'xoffset', 0) fs = self.fontsize.strip() - if fs.endswith('px'): fs = fs[:-2].strip() + if fs.endswith('px'): + fs = fs[:-2].strip() try: int_fs = int(fs) - except: + except ValueError: int_fs = 20 self.yoffset = get_int_opt(options, 'yoffset', int_fs) self.ystep = get_int_opt(options, 'ystep', int_fs + 5) @@ -122,30 +123,27 @@ class SvgFormatter(Formatter): y = self.yoffset if not self.nowrap: if self.encoding: - outfile.write('\n' % - self.encoding) + outfile.write(f'\n') else: outfile.write('\n') outfile.write('\n') outfile.write('\n') - outfile.write('\n' % - (self.fontfamily, self.fontsize)) - - counter = self.linenostart + outfile.write(f'\n') + + counter = self.linenostart counter_step = self.linenostep counter_style = self._get_style(Comment) line_x = x - + if self.linenos: if counter % counter_step == 0: - outfile.write('%s' % - (x+self.linenowidth,y,counter_style,counter)) + outfile.write(f'{counter}') line_x += self.linenowidth + self.ystep counter += 1 - outfile.write('' % (line_x, y)) + outfile.write(f'') for ttype, value in tokensource: style = self._get_style(ttype) tspan = style and '' or '' @@ -159,11 +157,10 @@ class SvgFormatter(Formatter): y += self.ystep outfile.write('\n') if self.linenos and counter % counter_step == 0: - outfile.write('%s' % - (x+self.linenowidth,y,counter_style,counter)) - + outfile.write(f'{counter}') + counter += 1 - outfile.write('' % (line_x,y)) + outfile.write(f'') outfile.write(tspan + parts[-1] + tspanend) outfile.write('') diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal.py index abb8770..51b902d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal.py @@ -4,7 +4,7 @@ Formatter for terminal output with ANSI sequences. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal256.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal256.py index 0cfe5d1..5f25405 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal256.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/formatters/terminal256.py @@ -10,7 +10,7 @@ Formatter version 1. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexer.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexer.py index eb2c1b4..1348be5 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexer.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexer.py @@ -4,7 +4,7 @@ Base lexer classes. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -67,10 +67,17 @@ class Lexer(metaclass=LexerMeta): :no-value: .. autoattribute:: priority - Lexers included in Pygments should have an additional attribute: + Lexers included in Pygments should have two additional attributes: .. autoattribute:: url :no-value: + .. autoattribute:: version_added + :no-value: + + Lexers included in Pygments may have additional attributes: + + .. autoattribute:: _example + :no-value: You can pass options to the constructor. The basic options recognized by all lexers and processed by the base `Lexer` class are: @@ -125,9 +132,16 @@ class Lexer(metaclass=LexerMeta): priority = 0 #: URL of the language specification/definition. Used in the Pygments - #: documentation. + #: documentation. Set to an empty string to disable. url = None + #: Version of Pygments in which the lexer was added. + version_added = None + + #: Example file name. Relative to the ``tests/examplefiles`` directory. + #: This is used by the documentation generator to show an example. + _example = None + def __init__(self, **options): """ This constructor takes arbitrary options as keyword arguments. @@ -160,10 +174,9 @@ class Lexer(metaclass=LexerMeta): def __repr__(self): if self.options: - return '' % (self.__class__.__name__, - self.options) + return f'' else: - return '' % self.__class__.__name__ + return f'' def add_filter(self, filter_, **options): """ @@ -190,26 +203,17 @@ class Lexer(metaclass=LexerMeta): it's the same as if the return values was ``0.0``. """ - def get_tokens(self, text, unfiltered=False): - """ - This method is the basic interface of a lexer. It is called by - the `highlight()` function. It must process the text and return an - iterable of ``(tokentype, value)`` pairs from `text`. + def _preprocess_lexer_input(self, text): + """Apply preprocessing such as decoding the input, removing BOM and normalizing newlines.""" - Normally, you don't need to override this method. The default - implementation processes the options recognized by all lexers - (`stripnl`, `stripall` and so on), and then yields all tokens - from `get_tokens_unprocessed()`, with the ``index`` dropped. - - If `unfiltered` is set to `True`, the filtering mechanism is - bypassed even if filters are defined. - """ if not isinstance(text, str): if self.encoding == 'guess': text, _ = guess_decode(text) elif self.encoding == 'chardet': try: - from pip._vendor import chardet + # pip vendoring note: this code is not reachable by pip, + # removed import of chardet to make it clear. + raise ImportError('chardet is not vendored by pip') except ImportError as e: raise ImportError('To enable chardet encoding guessing, ' 'please install the chardet library ' @@ -246,6 +250,24 @@ class Lexer(metaclass=LexerMeta): if self.ensurenl and not text.endswith('\n'): text += '\n' + return text + + def get_tokens(self, text, unfiltered=False): + """ + This method is the basic interface of a lexer. It is called by + the `highlight()` function. It must process the text and return an + iterable of ``(tokentype, value)`` pairs from `text`. + + Normally, you don't need to override this method. The default + implementation processes the options recognized by all lexers + (`stripnl`, `stripall` and so on), and then yields all tokens + from `get_tokens_unprocessed()`, with the ``index`` dropped. + + If `unfiltered` is set to `True`, the filtering mechanism is + bypassed even if filters are defined. + """ + text = self._preprocess_lexer_input(text) + def streamer(): for _, t, v in self.get_tokens_unprocessed(text): yield t, v @@ -490,7 +512,7 @@ class RegexLexerMeta(LexerMeta): def _process_token(cls, token): """Preprocess the token component of a token definition.""" assert type(token) is _TokenType or callable(token), \ - 'token type must be simple type or callable, not %r' % (token,) + f'token type must be simple type or callable, not {token!r}' return token def _process_new_state(cls, new_state, unprocessed, processed): @@ -506,14 +528,14 @@ class RegexLexerMeta(LexerMeta): elif new_state[:5] == '#pop:': return -int(new_state[5:]) else: - assert False, 'unknown new state %r' % new_state + assert False, f'unknown new state {new_state!r}' elif isinstance(new_state, combined): # combine a new state from existing ones tmp_state = '_tmp_%d' % cls._tmpname cls._tmpname += 1 itokens = [] for istate in new_state: - assert istate != new_state, 'circular state ref %r' % istate + assert istate != new_state, f'circular state ref {istate!r}' itokens.extend(cls._process_state(unprocessed, processed, istate)) processed[tmp_state] = itokens @@ -526,12 +548,12 @@ class RegexLexerMeta(LexerMeta): 'unknown new state ' + istate return new_state else: - assert False, 'unknown new state def %r' % new_state + assert False, f'unknown new state def {new_state!r}' def _process_state(cls, unprocessed, processed, state): """Preprocess a single state definition.""" - assert type(state) is str, "wrong state name %r" % state - assert state[0] != '#', "invalid state name %r" % state + assert isinstance(state, str), f"wrong state name {state!r}" + assert state[0] != '#', f"invalid state name {state!r}" if state in processed: return processed[state] tokens = processed[state] = [] @@ -539,7 +561,7 @@ class RegexLexerMeta(LexerMeta): for tdef in unprocessed[state]: if isinstance(tdef, include): # it's a state reference - assert tdef != state, "circular state reference %r" % state + assert tdef != state, f"circular state reference {state!r}" tokens.extend(cls._process_state(unprocessed, processed, str(tdef))) continue @@ -553,13 +575,12 @@ class RegexLexerMeta(LexerMeta): tokens.append((re.compile('').match, None, new_state)) continue - assert type(tdef) is tuple, "wrong rule def %r" % tdef + assert type(tdef) is tuple, f"wrong rule def {tdef!r}" try: rex = cls._process_regex(tdef[0], rflags, state) except Exception as err: - raise ValueError("uncompilable regex %r in state %r of %r: %s" % - (tdef[0], state, cls, err)) from err + raise ValueError(f"uncompilable regex {tdef[0]!r} in state {state!r} of {cls!r}: {err}") from err token = cls._process_token(tdef[1]) @@ -720,7 +741,7 @@ class RegexLexer(Lexer, metaclass=RegexLexerMeta): elif new_state == '#push': statestack.append(statestack[-1]) else: - assert False, "wrong state def: %r" % new_state + assert False, f"wrong state def: {new_state!r}" statetokens = tokendefs[statestack[-1]] break else: @@ -752,8 +773,7 @@ class LexerContext: self.stack = stack or ['root'] def __repr__(self): - return 'LexerContext(%r, %r, %r)' % ( - self.text, self.pos, self.stack) + return f'LexerContext({self.text!r}, {self.pos!r}, {self.stack!r})' class ExtendedRegexLexer(RegexLexer): @@ -808,7 +828,7 @@ class ExtendedRegexLexer(RegexLexer): elif new_state == '#push': ctx.stack.append(ctx.stack[-1]) else: - assert False, "wrong state def: %r" % new_state + assert False, f"wrong state def: {new_state!r}" statetokens = tokendefs[ctx.stack[-1]] break else: diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__init__.py index d97c3e3..ac88645 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__init__.py @@ -4,7 +4,7 @@ Pygments lexers. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -22,6 +22,7 @@ from pip._vendor.pygments.util import ClassNotFound, guess_decode COMPAT = { 'Python3Lexer': 'PythonLexer', 'Python3TracebackLexer': 'PythonTracebackLexer', + 'LeanLexer': 'Lean3Lexer', } __all__ = ['get_lexer_by_name', 'get_lexer_for_filename', 'find_lexer_class', @@ -92,7 +93,7 @@ def find_lexer_class_by_name(_alias): .. versionadded:: 2.2 """ if not _alias: - raise ClassNotFound('no lexer for alias %r found' % _alias) + raise ClassNotFound(f'no lexer for alias {_alias!r} found') # lookup builtin lexers for module_name, name, aliases, _, _ in LEXERS.values(): if _alias.lower() in aliases: @@ -103,7 +104,7 @@ def find_lexer_class_by_name(_alias): for cls in find_plugin_lexers(): if _alias.lower() in cls.aliases: return cls - raise ClassNotFound('no lexer for alias %r found' % _alias) + raise ClassNotFound(f'no lexer for alias {_alias!r} found') def get_lexer_by_name(_alias, **options): @@ -116,7 +117,7 @@ def get_lexer_by_name(_alias, **options): found. """ if not _alias: - raise ClassNotFound('no lexer for alias %r found' % _alias) + raise ClassNotFound(f'no lexer for alias {_alias!r} found') # lookup builtin lexers for module_name, name, aliases, _, _ in LEXERS.values(): @@ -128,7 +129,7 @@ def get_lexer_by_name(_alias, **options): for cls in find_plugin_lexers(): if _alias.lower() in cls.aliases: return cls(**options) - raise ClassNotFound('no lexer for alias %r found' % _alias) + raise ClassNotFound(f'no lexer for alias {_alias!r} found') def load_lexer_from_file(filename, lexername="CustomLexer", **options): @@ -153,17 +154,16 @@ def load_lexer_from_file(filename, lexername="CustomLexer", **options): exec(f.read(), custom_namespace) # Retrieve the class `lexername` from that namespace if lexername not in custom_namespace: - raise ClassNotFound('no valid %s class found in %s' % - (lexername, filename)) + raise ClassNotFound(f'no valid {lexername} class found in {filename}') lexer_class = custom_namespace[lexername] # And finally instantiate it with the options return lexer_class(**options) except OSError as err: - raise ClassNotFound('cannot read %s: %s' % (filename, err)) + raise ClassNotFound(f'cannot read {filename}: {err}') except ClassNotFound: raise except Exception as err: - raise ClassNotFound('error when loading custom lexer: %s' % err) + raise ClassNotFound(f'error when loading custom lexer: {err}') def find_lexer_class_for_filename(_fn, code=None): @@ -224,7 +224,7 @@ def get_lexer_for_filename(_fn, code=None, **options): """ res = find_lexer_class_for_filename(_fn, code) if not res: - raise ClassNotFound('no lexer for filename %r found' % _fn) + raise ClassNotFound(f'no lexer for filename {_fn!r} found') return res(**options) @@ -244,7 +244,7 @@ def get_lexer_for_mimetype(_mime, **options): for cls in find_plugin_lexers(): if _mime in cls.mimetypes: return cls(**options) - raise ClassNotFound('no lexer for mimetype %r found' % _mime) + raise ClassNotFound(f'no lexer for mimetype {_mime!r} found') def _iter_lexerclasses(plugins=True): @@ -279,7 +279,7 @@ def guess_lexer_for_filename(_fn, _text, **options): matching_lexers.add(lexer) primary[lexer] = False if not matching_lexers: - raise ClassNotFound('no lexer for filename %r found' % fn) + raise ClassNotFound(f'no lexer for filename {fn!r} found') if len(matching_lexers) == 1: return matching_lexers.pop()(**options) result = [] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/__init__.cpython-312.pyc index 381d037..bd7c46d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/_mapping.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/_mapping.cpython-312.pyc index dd250d5..f36497d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/_mapping.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/_mapping.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/python.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/python.cpython-312.pyc index c30a53c..dd39306 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/python.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/__pycache__/python.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/_mapping.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/_mapping.py index de6a015..f3e5c46 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/_mapping.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/_mapping.py @@ -31,7 +31,8 @@ LEXERS = { 'ArduinoLexer': ('pip._vendor.pygments.lexers.c_like', 'Arduino', ('arduino',), ('*.ino',), ('text/x-arduino',)), 'ArrowLexer': ('pip._vendor.pygments.lexers.arrow', 'Arrow', ('arrow',), ('*.arw',), ()), 'ArturoLexer': ('pip._vendor.pygments.lexers.arturo', 'Arturo', ('arturo', 'art'), ('*.art',), ()), - 'AscLexer': ('pip._vendor.pygments.lexers.asc', 'ASCII armored', ('asc', 'pem'), ('*.asc', '*.pem', 'id_dsa', 'id_ecdsa', 'id_ecdsa_sk', 'id_ed25519', 'id_ed25519_sk', 'id_rsa'), ('application/pgp-keys', 'application/pgp-encrypted', 'application/pgp-signature')), + 'AscLexer': ('pip._vendor.pygments.lexers.asc', 'ASCII armored', ('asc', 'pem'), ('*.asc', '*.pem', 'id_dsa', 'id_ecdsa', 'id_ecdsa_sk', 'id_ed25519', 'id_ed25519_sk', 'id_rsa'), ('application/pgp-keys', 'application/pgp-encrypted', 'application/pgp-signature', 'application/pem-certificate-chain')), + 'Asn1Lexer': ('pip._vendor.pygments.lexers.asn1', 'ASN.1', ('asn1',), ('*.asn1',), ()), 'AspectJLexer': ('pip._vendor.pygments.lexers.jvm', 'AspectJ', ('aspectj',), ('*.aj',), ('text/x-aspectj',)), 'AsymptoteLexer': ('pip._vendor.pygments.lexers.graphics', 'Asymptote', ('asymptote', 'asy'), ('*.asy',), ('text/x-asymptote',)), 'AugeasLexer': ('pip._vendor.pygments.lexers.configs', 'Augeas', ('augeas',), ('*.aug',), ()), @@ -41,10 +42,11 @@ LEXERS = { 'BBCBasicLexer': ('pip._vendor.pygments.lexers.basic', 'BBC Basic', ('bbcbasic',), ('*.bbc',), ()), 'BBCodeLexer': ('pip._vendor.pygments.lexers.markup', 'BBCode', ('bbcode',), (), ('text/x-bbcode',)), 'BCLexer': ('pip._vendor.pygments.lexers.algebra', 'BC', ('bc',), ('*.bc',), ()), + 'BQNLexer': ('pip._vendor.pygments.lexers.bqn', 'BQN', ('bqn',), ('*.bqn',), ()), 'BSTLexer': ('pip._vendor.pygments.lexers.bibtex', 'BST', ('bst', 'bst-pybtex'), ('*.bst',), ()), 'BareLexer': ('pip._vendor.pygments.lexers.bare', 'BARE', ('bare',), ('*.bare',), ()), 'BaseMakefileLexer': ('pip._vendor.pygments.lexers.make', 'Base Makefile', ('basemake',), (), ()), - 'BashLexer': ('pip._vendor.pygments.lexers.shell', 'Bash', ('bash', 'sh', 'ksh', 'zsh', 'shell'), ('*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass', '*.exheres-0', '*.exlib', '*.zsh', '.bashrc', 'bashrc', '.bash_*', 'bash_*', 'zshrc', '.zshrc', '.kshrc', 'kshrc', 'PKGBUILD'), ('application/x-sh', 'application/x-shellscript', 'text/x-shellscript')), + 'BashLexer': ('pip._vendor.pygments.lexers.shell', 'Bash', ('bash', 'sh', 'ksh', 'zsh', 'shell', 'openrc'), ('*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass', '*.exheres-0', '*.exlib', '*.zsh', '.bashrc', 'bashrc', '.bash_*', 'bash_*', 'zshrc', '.zshrc', '.kshrc', 'kshrc', 'PKGBUILD'), ('application/x-sh', 'application/x-shellscript', 'text/x-shellscript')), 'BashSessionLexer': ('pip._vendor.pygments.lexers.shell', 'Bash Session', ('console', 'shell-session'), ('*.sh-session', '*.shell-session'), ('application/x-shell-session', 'application/x-sh-session')), 'BatchLexer': ('pip._vendor.pygments.lexers.shell', 'Batchfile', ('batch', 'bat', 'dosbatch', 'winbatch'), ('*.bat', '*.cmd'), ('application/x-dos-batch',)), 'BddLexer': ('pip._vendor.pygments.lexers.bdd', 'Bdd', ('bdd',), ('*.feature',), ('text/x-bdd',)), @@ -53,6 +55,7 @@ LEXERS = { 'BibTeXLexer': ('pip._vendor.pygments.lexers.bibtex', 'BibTeX', ('bibtex', 'bib'), ('*.bib',), ('text/x-bibtex',)), 'BlitzBasicLexer': ('pip._vendor.pygments.lexers.basic', 'BlitzBasic', ('blitzbasic', 'b3d', 'bplus'), ('*.bb', '*.decls'), ('text/x-bb',)), 'BlitzMaxLexer': ('pip._vendor.pygments.lexers.basic', 'BlitzMax', ('blitzmax', 'bmax'), ('*.bmx',), ('text/x-bmx',)), + 'BlueprintLexer': ('pip._vendor.pygments.lexers.blueprint', 'Blueprint', ('blueprint',), ('*.blp',), ('text/x-blueprint',)), 'BnfLexer': ('pip._vendor.pygments.lexers.grammar_notation', 'BNF', ('bnf',), ('*.bnf',), ('text/x-bnf',)), 'BoaLexer': ('pip._vendor.pygments.lexers.boa', 'Boa', ('boa',), ('*.boa',), ()), 'BooLexer': ('pip._vendor.pygments.lexers.dotnet', 'Boo', ('boo',), ('*.boo',), ('text/x-boo',)), @@ -125,10 +128,12 @@ LEXERS = { 'DaxLexer': ('pip._vendor.pygments.lexers.dax', 'Dax', ('dax',), ('*.dax',), ()), 'DebianControlLexer': ('pip._vendor.pygments.lexers.installers', 'Debian Control file', ('debcontrol', 'control'), ('control',), ()), 'DelphiLexer': ('pip._vendor.pygments.lexers.pascal', 'Delphi', ('delphi', 'pas', 'pascal', 'objectpascal'), ('*.pas', '*.dpr'), ('text/x-pascal',)), + 'DesktopLexer': ('pip._vendor.pygments.lexers.configs', 'Desktop file', ('desktop',), ('*.desktop',), ('application/x-desktop',)), 'DevicetreeLexer': ('pip._vendor.pygments.lexers.devicetree', 'Devicetree', ('devicetree', 'dts'), ('*.dts', '*.dtsi'), ('text/x-c',)), 'DgLexer': ('pip._vendor.pygments.lexers.python', 'dg', ('dg',), ('*.dg',), ('text/x-dg',)), 'DiffLexer': ('pip._vendor.pygments.lexers.diff', 'Diff', ('diff', 'udiff'), ('*.diff', '*.patch'), ('text/x-diff', 'text/x-patch')), 'DjangoLexer': ('pip._vendor.pygments.lexers.templates', 'Django/Jinja', ('django', 'jinja'), (), ('application/x-django-templating', 'application/x-jinja')), + 'DnsZoneLexer': ('pip._vendor.pygments.lexers.dns', 'Zone', ('zone',), ('*.zone',), ('text/dns',)), 'DockerLexer': ('pip._vendor.pygments.lexers.configs', 'Docker', ('docker', 'dockerfile'), ('Dockerfile', '*.docker'), ('text/x-dockerfile-config',)), 'DtdLexer': ('pip._vendor.pygments.lexers.html', 'DTD', ('dtd',), ('*.dtd',), ('application/xml-dtd',)), 'DuelLexer': ('pip._vendor.pygments.lexers.webmisc', 'Duel', ('duel', 'jbst', 'jsonml+bst'), ('*.duel', '*.jbst'), ('text/x-duel', 'text/x-jbst')), @@ -190,6 +195,7 @@ LEXERS = { 'GoodDataCLLexer': ('pip._vendor.pygments.lexers.business', 'GoodData-CL', ('gooddata-cl',), ('*.gdc',), ('text/x-gooddata-cl',)), 'GosuLexer': ('pip._vendor.pygments.lexers.jvm', 'Gosu', ('gosu',), ('*.gs', '*.gsx', '*.gsp', '*.vark'), ('text/x-gosu',)), 'GosuTemplateLexer': ('pip._vendor.pygments.lexers.jvm', 'Gosu Template', ('gst',), ('*.gst',), ('text/x-gosu-template',)), + 'GraphQLLexer': ('pip._vendor.pygments.lexers.graphql', 'GraphQL', ('graphql',), ('*.graphql',), ()), 'GraphvizLexer': ('pip._vendor.pygments.lexers.graphviz', 'Graphviz', ('graphviz', 'dot'), ('*.gv', '*.dot'), ('text/x-graphviz', 'text/vnd.graphviz')), 'GroffLexer': ('pip._vendor.pygments.lexers.markup', 'Groff', ('groff', 'nroff', 'man'), ('*.[1-9]', '*.man', '*.1p', '*.3pm'), ('application/x-troff', 'text/troff')), 'GroovyLexer': ('pip._vendor.pygments.lexers.jvm', 'Groovy', ('groovy',), ('*.groovy', '*.gradle'), ('text/x-groovy',)), @@ -210,8 +216,8 @@ LEXERS = { 'HtmlSmartyLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Smarty', ('html+smarty',), (), ('text/html+smarty',)), 'HttpLexer': ('pip._vendor.pygments.lexers.textfmts', 'HTTP', ('http',), (), ()), 'HxmlLexer': ('pip._vendor.pygments.lexers.haxe', 'Hxml', ('haxeml', 'hxml'), ('*.hxml',), ()), - 'HyLexer': ('pip._vendor.pygments.lexers.lisp', 'Hy', ('hylang',), ('*.hy',), ('text/x-hy', 'application/x-hy')), - 'HybrisLexer': ('pip._vendor.pygments.lexers.scripting', 'Hybris', ('hybris', 'hy'), ('*.hy', '*.hyb'), ('text/x-hybris', 'application/x-hybris')), + 'HyLexer': ('pip._vendor.pygments.lexers.lisp', 'Hy', ('hylang', 'hy'), ('*.hy',), ('text/x-hy', 'application/x-hy')), + 'HybrisLexer': ('pip._vendor.pygments.lexers.scripting', 'Hybris', ('hybris',), ('*.hyb',), ('text/x-hybris', 'application/x-hybris')), 'IDLLexer': ('pip._vendor.pygments.lexers.idl', 'IDL', ('idl',), ('*.pro',), ('text/idl',)), 'IconLexer': ('pip._vendor.pygments.lexers.unicon', 'Icon', ('icon',), ('*.icon', '*.ICON'), ()), 'IdrisLexer': ('pip._vendor.pygments.lexers.haskell', 'Idris', ('idris', 'idr'), ('*.idr',), ('text/x-idris',)), @@ -219,7 +225,7 @@ LEXERS = { 'Inform6Lexer': ('pip._vendor.pygments.lexers.int_fiction', 'Inform 6', ('inform6', 'i6'), ('*.inf',), ()), 'Inform6TemplateLexer': ('pip._vendor.pygments.lexers.int_fiction', 'Inform 6 template', ('i6t',), ('*.i6t',), ()), 'Inform7Lexer': ('pip._vendor.pygments.lexers.int_fiction', 'Inform 7', ('inform7', 'i7'), ('*.ni', '*.i7x'), ()), - 'IniLexer': ('pip._vendor.pygments.lexers.configs', 'INI', ('ini', 'cfg', 'dosini'), ('*.ini', '*.cfg', '*.inf', '.editorconfig', '*.service', '*.socket', '*.device', '*.mount', '*.automount', '*.swap', '*.target', '*.path', '*.timer', '*.slice', '*.scope'), ('text/x-ini', 'text/inf')), + 'IniLexer': ('pip._vendor.pygments.lexers.configs', 'INI', ('ini', 'cfg', 'dosini'), ('*.ini', '*.cfg', '*.inf', '.editorconfig'), ('text/x-ini', 'text/inf')), 'IoLexer': ('pip._vendor.pygments.lexers.iolang', 'Io', ('io',), ('*.io',), ('text/x-iosrc',)), 'IokeLexer': ('pip._vendor.pygments.lexers.jvm', 'Ioke', ('ioke', 'ik'), ('*.ik',), ('text/x-iokesrc',)), 'IrcLogsLexer': ('pip._vendor.pygments.lexers.textfmts', 'IRC logs', ('irc',), ('*.weechatlog',), ('text/x-irclog',)), @@ -228,6 +234,7 @@ LEXERS = { 'JMESPathLexer': ('pip._vendor.pygments.lexers.jmespath', 'JMESPath', ('jmespath', 'jp'), ('*.jp',), ()), 'JSLTLexer': ('pip._vendor.pygments.lexers.jslt', 'JSLT', ('jslt',), ('*.jslt',), ('text/x-jslt',)), 'JagsLexer': ('pip._vendor.pygments.lexers.modeling', 'JAGS', ('jags',), ('*.jag', '*.bug'), ()), + 'JanetLexer': ('pip._vendor.pygments.lexers.lisp', 'Janet', ('janet',), ('*.janet', '*.jdn'), ('text/x-janet', 'application/x-janet')), 'JasminLexer': ('pip._vendor.pygments.lexers.jvm', 'Jasmin', ('jasmin', 'jasminxt'), ('*.j',), ()), 'JavaLexer': ('pip._vendor.pygments.lexers.jvm', 'Java', ('java',), ('*.java',), ('text/x-java',)), 'JavascriptDjangoLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Django/Jinja', ('javascript+django', 'js+django', 'javascript+jinja', 'js+jinja'), ('*.js.j2', '*.js.jinja2'), ('application/x-javascript+django', 'application/x-javascript+jinja', 'text/x-javascript+django', 'text/x-javascript+jinja', 'text/javascript+django', 'text/javascript+jinja')), @@ -241,9 +248,10 @@ LEXERS = { 'JsgfLexer': ('pip._vendor.pygments.lexers.grammar_notation', 'JSGF', ('jsgf',), ('*.jsgf',), ('application/jsgf', 'application/x-jsgf', 'text/jsgf')), 'JsonBareObjectLexer': ('pip._vendor.pygments.lexers.data', 'JSONBareObject', (), (), ()), 'JsonLdLexer': ('pip._vendor.pygments.lexers.data', 'JSON-LD', ('jsonld', 'json-ld'), ('*.jsonld',), ('application/ld+json',)), - 'JsonLexer': ('pip._vendor.pygments.lexers.data', 'JSON', ('json', 'json-object'), ('*.json', 'Pipfile.lock'), ('application/json', 'application/json-object')), + 'JsonLexer': ('pip._vendor.pygments.lexers.data', 'JSON', ('json', 'json-object'), ('*.json', '*.jsonl', '*.ndjson', 'Pipfile.lock'), ('application/json', 'application/json-object', 'application/x-ndjson', 'application/jsonl', 'application/json-seq')), 'JsonnetLexer': ('pip._vendor.pygments.lexers.jsonnet', 'Jsonnet', ('jsonnet',), ('*.jsonnet', '*.libsonnet'), ()), 'JspLexer': ('pip._vendor.pygments.lexers.templates', 'Java Server Page', ('jsp',), ('*.jsp',), ('application/x-jsp',)), + 'JsxLexer': ('pip._vendor.pygments.lexers.jsx', 'JSX', ('jsx', 'react'), ('*.jsx', '*.react'), ('text/jsx', 'text/typescript-jsx')), 'JuliaConsoleLexer': ('pip._vendor.pygments.lexers.julia', 'Julia console', ('jlcon', 'julia-repl'), (), ()), 'JuliaLexer': ('pip._vendor.pygments.lexers.julia', 'Julia', ('julia', 'jl'), ('*.jl',), ('text/x-julia', 'application/x-julia')), 'JuttleLexer': ('pip._vendor.pygments.lexers.javascript', 'Juttle', ('juttle',), ('*.juttle',), ('application/juttle', 'application/x-juttle', 'text/x-juttle', 'text/juttle')), @@ -254,13 +262,17 @@ LEXERS = { 'KokaLexer': ('pip._vendor.pygments.lexers.haskell', 'Koka', ('koka',), ('*.kk', '*.kki'), ('text/x-koka',)), 'KotlinLexer': ('pip._vendor.pygments.lexers.jvm', 'Kotlin', ('kotlin',), ('*.kt', '*.kts'), ('text/x-kotlin',)), 'KuinLexer': ('pip._vendor.pygments.lexers.kuin', 'Kuin', ('kuin',), ('*.kn',), ()), + 'KustoLexer': ('pip._vendor.pygments.lexers.kusto', 'Kusto', ('kql', 'kusto'), ('*.kql', '*.kusto', '.csl'), ()), 'LSLLexer': ('pip._vendor.pygments.lexers.scripting', 'LSL', ('lsl',), ('*.lsl',), ('text/x-lsl',)), 'LassoCssLexer': ('pip._vendor.pygments.lexers.templates', 'CSS+Lasso', ('css+lasso',), (), ('text/css+lasso',)), 'LassoHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Lasso', ('html+lasso',), (), ('text/html+lasso', 'application/x-httpd-lasso', 'application/x-httpd-lasso[89]')), 'LassoJavascriptLexer': ('pip._vendor.pygments.lexers.templates', 'JavaScript+Lasso', ('javascript+lasso', 'js+lasso'), (), ('application/x-javascript+lasso', 'text/x-javascript+lasso', 'text/javascript+lasso')), 'LassoLexer': ('pip._vendor.pygments.lexers.javascript', 'Lasso', ('lasso', 'lassoscript'), ('*.lasso', '*.lasso[89]'), ('text/x-lasso',)), 'LassoXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Lasso', ('xml+lasso',), (), ('application/xml+lasso',)), - 'LeanLexer': ('pip._vendor.pygments.lexers.theorem', 'Lean', ('lean',), ('*.lean',), ('text/x-lean',)), + 'LdaprcLexer': ('pip._vendor.pygments.lexers.ldap', 'LDAP configuration file', ('ldapconf', 'ldaprc'), ('.ldaprc', 'ldaprc', 'ldap.conf'), ('text/x-ldapconf',)), + 'LdifLexer': ('pip._vendor.pygments.lexers.ldap', 'LDIF', ('ldif',), ('*.ldif',), ('text/x-ldif',)), + 'Lean3Lexer': ('pip._vendor.pygments.lexers.lean', 'Lean', ('lean', 'lean3'), ('*.lean',), ('text/x-lean', 'text/x-lean3')), + 'Lean4Lexer': ('pip._vendor.pygments.lexers.lean', 'Lean4', ('lean4',), ('*.lean',), ('text/x-lean4',)), 'LessCssLexer': ('pip._vendor.pygments.lexers.css', 'LessCss', ('less',), ('*.less',), ('text/x-less-css',)), 'LighttpdConfLexer': ('pip._vendor.pygments.lexers.configs', 'Lighttpd configuration file', ('lighttpd', 'lighty'), ('lighttpd.conf',), ('text/x-lighttpd-conf',)), 'LilyPondLexer': ('pip._vendor.pygments.lexers.lilypond', 'LilyPond', ('lilypond',), ('*.ly',), ()), @@ -277,6 +289,7 @@ LEXERS = { 'LogosLexer': ('pip._vendor.pygments.lexers.objective', 'Logos', ('logos',), ('*.x', '*.xi', '*.xm', '*.xmi'), ('text/x-logos',)), 'LogtalkLexer': ('pip._vendor.pygments.lexers.prolog', 'Logtalk', ('logtalk',), ('*.lgt', '*.logtalk'), ('text/x-logtalk',)), 'LuaLexer': ('pip._vendor.pygments.lexers.scripting', 'Lua', ('lua',), ('*.lua', '*.wlua'), ('text/x-lua', 'application/x-lua')), + 'LuauLexer': ('pip._vendor.pygments.lexers.scripting', 'Luau', ('luau',), ('*.luau',), ()), 'MCFunctionLexer': ('pip._vendor.pygments.lexers.minecraft', 'MCFunction', ('mcfunction', 'mcf'), ('*.mcfunction',), ('text/mcfunction',)), 'MCSchemaLexer': ('pip._vendor.pygments.lexers.minecraft', 'MCSchema', ('mcschema',), ('*.mcschema',), ('text/mcschema',)), 'MIMELexer': ('pip._vendor.pygments.lexers.mime', 'MIME', ('mime',), (), ('multipart/mixed', 'multipart/related', 'multipart/alternative')), @@ -304,6 +317,7 @@ LEXERS = { 'ModelicaLexer': ('pip._vendor.pygments.lexers.modeling', 'Modelica', ('modelica',), ('*.mo',), ('text/x-modelica',)), 'Modula2Lexer': ('pip._vendor.pygments.lexers.modula2', 'Modula-2', ('modula2', 'm2'), ('*.def', '*.mod'), ('text/x-modula2',)), 'MoinWikiLexer': ('pip._vendor.pygments.lexers.markup', 'MoinMoin/Trac Wiki markup', ('trac-wiki', 'moin'), (), ('text/x-trac-wiki',)), + 'MojoLexer': ('pip._vendor.pygments.lexers.mojo', 'Mojo', ('mojo', '🔥'), ('*.mojo', '*.🔥'), ('text/x-mojo', 'application/x-mojo')), 'MonkeyLexer': ('pip._vendor.pygments.lexers.basic', 'Monkey', ('monkey',), ('*.monkey',), ('text/x-monkey',)), 'MonteLexer': ('pip._vendor.pygments.lexers.monte', 'Monte', ('monte',), ('*.mt',), ()), 'MoonScriptLexer': ('pip._vendor.pygments.lexers.scripting', 'MoonScript', ('moonscript', 'moon'), ('*.moon',), ('text/x-moonscript', 'application/x-moonscript')), @@ -351,6 +365,8 @@ LEXERS = { 'OocLexer': ('pip._vendor.pygments.lexers.ooc', 'Ooc', ('ooc',), ('*.ooc',), ('text/x-ooc',)), 'OpaLexer': ('pip._vendor.pygments.lexers.ml', 'Opa', ('opa',), ('*.opa',), ('text/x-opa',)), 'OpenEdgeLexer': ('pip._vendor.pygments.lexers.business', 'OpenEdge ABL', ('openedge', 'abl', 'progress'), ('*.p', '*.cls'), ('text/x-openedge', 'application/x-openedge')), + 'OpenScadLexer': ('pip._vendor.pygments.lexers.openscad', 'OpenSCAD', ('openscad',), ('*.scad',), ('application/x-openscad',)), + 'OrgLexer': ('pip._vendor.pygments.lexers.markup', 'Org Mode', ('org', 'orgmode', 'org-mode'), ('*.org',), ('text/org',)), 'OutputLexer': ('pip._vendor.pygments.lexers.special', 'Text output', ('output',), (), ()), 'PacmanConfLexer': ('pip._vendor.pygments.lexers.configs', 'PacmanConf', ('pacmanconf',), ('pacman.conf',), ()), 'PanLexer': ('pip._vendor.pygments.lexers.dsls', 'Pan', ('pan',), ('*.pan',), ()), @@ -379,16 +395,19 @@ LEXERS = { 'ProcfileLexer': ('pip._vendor.pygments.lexers.procfile', 'Procfile', ('procfile',), ('Procfile',), ()), 'PrologLexer': ('pip._vendor.pygments.lexers.prolog', 'Prolog', ('prolog',), ('*.ecl', '*.prolog', '*.pro', '*.pl'), ('text/x-prolog',)), 'PromQLLexer': ('pip._vendor.pygments.lexers.promql', 'PromQL', ('promql',), ('*.promql',), ()), + 'PromelaLexer': ('pip._vendor.pygments.lexers.c_like', 'Promela', ('promela',), ('*.pml', '*.prom', '*.prm', '*.promela', '*.pr', '*.pm'), ('text/x-promela',)), 'PropertiesLexer': ('pip._vendor.pygments.lexers.configs', 'Properties', ('properties', 'jproperties'), ('*.properties',), ('text/x-java-properties',)), 'ProtoBufLexer': ('pip._vendor.pygments.lexers.dsls', 'Protocol Buffer', ('protobuf', 'proto'), ('*.proto',), ()), + 'PrqlLexer': ('pip._vendor.pygments.lexers.prql', 'PRQL', ('prql',), ('*.prql',), ('application/prql', 'application/x-prql')), 'PsyshConsoleLexer': ('pip._vendor.pygments.lexers.php', 'PsySH console session for PHP', ('psysh',), (), ()), + 'PtxLexer': ('pip._vendor.pygments.lexers.ptx', 'PTX', ('ptx',), ('*.ptx',), ('text/x-ptx',)), 'PugLexer': ('pip._vendor.pygments.lexers.html', 'Pug', ('pug', 'jade'), ('*.pug', '*.jade'), ('text/x-pug', 'text/x-jade')), 'PuppetLexer': ('pip._vendor.pygments.lexers.dsls', 'Puppet', ('puppet',), ('*.pp',), ()), 'PyPyLogLexer': ('pip._vendor.pygments.lexers.console', 'PyPy Log', ('pypylog', 'pypy'), ('*.pypylog',), ('application/x-pypylog',)), 'Python2Lexer': ('pip._vendor.pygments.lexers.python', 'Python 2.x', ('python2', 'py2'), (), ('text/x-python2', 'application/x-python2')), 'Python2TracebackLexer': ('pip._vendor.pygments.lexers.python', 'Python 2.x Traceback', ('py2tb',), ('*.py2tb',), ('text/x-python2-traceback',)), - 'PythonConsoleLexer': ('pip._vendor.pygments.lexers.python', 'Python console session', ('pycon',), (), ('text/x-python-doctest',)), - 'PythonLexer': ('pip._vendor.pygments.lexers.python', 'Python', ('python', 'py', 'sage', 'python3', 'py3'), ('*.py', '*.pyw', '*.pyi', '*.jy', '*.sage', '*.sc', 'SConstruct', 'SConscript', '*.bzl', 'BUCK', 'BUILD', 'BUILD.bazel', 'WORKSPACE', '*.tac'), ('text/x-python', 'application/x-python', 'text/x-python3', 'application/x-python3')), + 'PythonConsoleLexer': ('pip._vendor.pygments.lexers.python', 'Python console session', ('pycon', 'python-console'), (), ('text/x-python-doctest',)), + 'PythonLexer': ('pip._vendor.pygments.lexers.python', 'Python', ('python', 'py', 'sage', 'python3', 'py3', 'bazel', 'starlark'), ('*.py', '*.pyw', '*.pyi', '*.jy', '*.sage', '*.sc', 'SConstruct', 'SConscript', '*.bzl', 'BUCK', 'BUILD', 'BUILD.bazel', 'WORKSPACE', '*.tac'), ('text/x-python', 'application/x-python', 'text/x-python3', 'application/x-python3')), 'PythonTracebackLexer': ('pip._vendor.pygments.lexers.python', 'Python Traceback', ('pytb', 'py3tb'), ('*.pytb', '*.py3tb'), ('text/x-python-traceback', 'text/x-python3-traceback')), 'PythonUL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'Python+UL4', ('py+ul4',), ('*.pyul4',), ()), 'QBasicLexer': ('pip._vendor.pygments.lexers.basic', 'QBasic', ('qbasic', 'basic'), ('*.BAS', '*.bas'), ('text/basic',)), @@ -460,6 +479,7 @@ LEXERS = { 'SnobolLexer': ('pip._vendor.pygments.lexers.snobol', 'Snobol', ('snobol',), ('*.snobol',), ('text/x-snobol',)), 'SnowballLexer': ('pip._vendor.pygments.lexers.dsls', 'Snowball', ('snowball',), ('*.sbl',), ()), 'SolidityLexer': ('pip._vendor.pygments.lexers.solidity', 'Solidity', ('solidity',), ('*.sol',), ()), + 'SoongLexer': ('pip._vendor.pygments.lexers.soong', 'Soong', ('androidbp', 'bp', 'soong'), ('Android.bp',), ()), 'SophiaLexer': ('pip._vendor.pygments.lexers.sophia', 'Sophia', ('sophia',), ('*.aes',), ()), 'SourcePawnLexer': ('pip._vendor.pygments.lexers.pawn', 'SourcePawn', ('sp',), ('*.sp',), ('text/x-sourcepawn',)), 'SourcesListLexer': ('pip._vendor.pygments.lexers.installers', 'Debian Sourcelist', ('debsources', 'sourceslist', 'sources.list'), ('sources.list',), ()), @@ -477,9 +497,11 @@ LEXERS = { 'SwiftLexer': ('pip._vendor.pygments.lexers.objective', 'Swift', ('swift',), ('*.swift',), ('text/x-swift',)), 'SwigLexer': ('pip._vendor.pygments.lexers.c_like', 'SWIG', ('swig',), ('*.swg', '*.i'), ('text/swig',)), 'SystemVerilogLexer': ('pip._vendor.pygments.lexers.hdl', 'systemverilog', ('systemverilog', 'sv'), ('*.sv', '*.svh'), ('text/x-systemverilog',)), + 'SystemdLexer': ('pip._vendor.pygments.lexers.configs', 'Systemd', ('systemd',), ('*.service', '*.socket', '*.device', '*.mount', '*.automount', '*.swap', '*.target', '*.path', '*.timer', '*.slice', '*.scope'), ()), 'TAPLexer': ('pip._vendor.pygments.lexers.testing', 'TAP', ('tap',), ('*.tap',), ()), 'TNTLexer': ('pip._vendor.pygments.lexers.tnt', 'Typographic Number Theory', ('tnt',), ('*.tnt',), ()), - 'TOMLLexer': ('pip._vendor.pygments.lexers.configs', 'TOML', ('toml',), ('*.toml', 'Pipfile', 'poetry.lock'), ()), + 'TOMLLexer': ('pip._vendor.pygments.lexers.configs', 'TOML', ('toml',), ('*.toml', 'Pipfile', 'poetry.lock'), ('application/toml',)), + 'TactLexer': ('pip._vendor.pygments.lexers.tact', 'Tact', ('tact',), ('*.tact',), ()), 'Tads3Lexer': ('pip._vendor.pygments.lexers.int_fiction', 'TADS 3', ('tads3',), ('*.t',), ()), 'TalLexer': ('pip._vendor.pygments.lexers.tal', 'Tal', ('tal', 'uxntal'), ('*.tal',), ('text/x-uxntal',)), 'TasmLexer': ('pip._vendor.pygments.lexers.asm', 'TASM', ('tasm',), ('*.asm', '*.ASM', '*.tasm'), ('text/x-tasm',)), @@ -498,6 +520,7 @@ LEXERS = { 'ThriftLexer': ('pip._vendor.pygments.lexers.dsls', 'Thrift', ('thrift',), ('*.thrift',), ('application/x-thrift',)), 'TiddlyWiki5Lexer': ('pip._vendor.pygments.lexers.markup', 'tiddler', ('tid',), ('*.tid',), ('text/vnd.tiddlywiki',)), 'TlbLexer': ('pip._vendor.pygments.lexers.tlb', 'Tl-b', ('tlb',), ('*.tlb',), ()), + 'TlsLexer': ('pip._vendor.pygments.lexers.tls', 'TLS Presentation Language', ('tls',), (), ()), 'TodotxtLexer': ('pip._vendor.pygments.lexers.textfmts', 'Todotxt', ('todotxt',), ('todo.txt', '*.todotxt'), ('text/x-todo',)), 'TransactSqlLexer': ('pip._vendor.pygments.lexers.sql', 'Transact-SQL', ('tsql', 't-sql'), ('*.sql',), ('text/x-tsql',)), 'TreetopLexer': ('pip._vendor.pygments.lexers.parsers', 'Treetop', ('treetop',), ('*.treetop', '*.tt'), ()), @@ -508,11 +531,13 @@ LEXERS = { 'TypoScriptCssDataLexer': ('pip._vendor.pygments.lexers.typoscript', 'TypoScriptCssData', ('typoscriptcssdata',), (), ()), 'TypoScriptHtmlDataLexer': ('pip._vendor.pygments.lexers.typoscript', 'TypoScriptHtmlData', ('typoscripthtmldata',), (), ()), 'TypoScriptLexer': ('pip._vendor.pygments.lexers.typoscript', 'TypoScript', ('typoscript',), ('*.typoscript',), ('text/x-typoscript',)), + 'TypstLexer': ('pip._vendor.pygments.lexers.typst', 'Typst', ('typst',), ('*.typ',), ('text/x-typst',)), 'UL4Lexer': ('pip._vendor.pygments.lexers.ul4', 'UL4', ('ul4',), ('*.ul4',), ()), 'UcodeLexer': ('pip._vendor.pygments.lexers.unicon', 'ucode', ('ucode',), ('*.u', '*.u1', '*.u2'), ()), 'UniconLexer': ('pip._vendor.pygments.lexers.unicon', 'Unicon', ('unicon',), ('*.icn',), ('text/unicon',)), 'UnixConfigLexer': ('pip._vendor.pygments.lexers.configs', 'Unix/Linux config files', ('unixconfig', 'linuxconfig'), (), ()), 'UrbiscriptLexer': ('pip._vendor.pygments.lexers.urbi', 'UrbiScript', ('urbiscript',), ('*.u',), ('application/x-urbiscript',)), + 'UrlEncodedLexer': ('pip._vendor.pygments.lexers.html', 'urlencoded', ('urlencoded',), (), ('application/x-www-form-urlencoded',)), 'UsdLexer': ('pip._vendor.pygments.lexers.usd', 'USD', ('usd', 'usda'), ('*.usd', '*.usda'), ()), 'VBScriptLexer': ('pip._vendor.pygments.lexers.basic', 'VBScript', ('vbscript',), ('*.vbs', '*.VBS'), ()), 'VCLLexer': ('pip._vendor.pygments.lexers.varnish', 'VCL', ('vcl',), ('*.vcl',), ('text/x-vclsrc',)), @@ -521,13 +546,17 @@ LEXERS = { 'VGLLexer': ('pip._vendor.pygments.lexers.dsls', 'VGL', ('vgl',), ('*.rpf',), ()), 'ValaLexer': ('pip._vendor.pygments.lexers.c_like', 'Vala', ('vala', 'vapi'), ('*.vala', '*.vapi'), ('text/x-vala',)), 'VbNetAspxLexer': ('pip._vendor.pygments.lexers.dotnet', 'aspx-vb', ('aspx-vb',), ('*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd'), ()), - 'VbNetLexer': ('pip._vendor.pygments.lexers.dotnet', 'VB.net', ('vb.net', 'vbnet', 'lobas', 'oobas', 'sobas'), ('*.vb', '*.bas'), ('text/x-vbnet', 'text/x-vba')), + 'VbNetLexer': ('pip._vendor.pygments.lexers.dotnet', 'VB.net', ('vb.net', 'vbnet', 'lobas', 'oobas', 'sobas', 'visual-basic', 'visualbasic'), ('*.vb', '*.bas'), ('text/x-vbnet', 'text/x-vba')), 'VelocityHtmlLexer': ('pip._vendor.pygments.lexers.templates', 'HTML+Velocity', ('html+velocity',), (), ('text/html+velocity',)), 'VelocityLexer': ('pip._vendor.pygments.lexers.templates', 'Velocity', ('velocity',), ('*.vm', '*.fhtml'), ()), 'VelocityXmlLexer': ('pip._vendor.pygments.lexers.templates', 'XML+Velocity', ('xml+velocity',), (), ('application/xml+velocity',)), + 'VerifpalLexer': ('pip._vendor.pygments.lexers.verifpal', 'Verifpal', ('verifpal',), ('*.vp',), ('text/x-verifpal',)), 'VerilogLexer': ('pip._vendor.pygments.lexers.hdl', 'verilog', ('verilog', 'v'), ('*.v',), ('text/x-verilog',)), 'VhdlLexer': ('pip._vendor.pygments.lexers.hdl', 'vhdl', ('vhdl',), ('*.vhdl', '*.vhd'), ('text/x-vhdl',)), 'VimLexer': ('pip._vendor.pygments.lexers.textedit', 'VimL', ('vim',), ('*.vim', '.vimrc', '.exrc', '.gvimrc', '_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc'), ('text/x-vim',)), + 'VisualPrologGrammarLexer': ('pip._vendor.pygments.lexers.vip', 'Visual Prolog Grammar', ('visualprologgrammar',), ('*.vipgrm',), ()), + 'VisualPrologLexer': ('pip._vendor.pygments.lexers.vip', 'Visual Prolog', ('visualprolog',), ('*.pro', '*.cl', '*.i', '*.pack', '*.ph'), ()), + 'VyperLexer': ('pip._vendor.pygments.lexers.vyper', 'Vyper', ('vyper',), ('*.vy',), ()), 'WDiffLexer': ('pip._vendor.pygments.lexers.diff', 'WDiff', ('wdiff',), ('*.wdiff',), ()), 'WatLexer': ('pip._vendor.pygments.lexers.webassembly', 'WebAssembly', ('wast', 'wat'), ('*.wat', '*.wast'), ()), 'WebIDLLexer': ('pip._vendor.pygments.lexers.webidl', 'Web IDL', ('webidl',), ('*.webidl',), ()), @@ -552,6 +581,7 @@ LEXERS = { 'YamlJinjaLexer': ('pip._vendor.pygments.lexers.templates', 'YAML+Jinja', ('yaml+jinja', 'salt', 'sls'), ('*.sls', '*.yaml.j2', '*.yml.j2', '*.yaml.jinja2', '*.yml.jinja2'), ('text/x-yaml+jinja', 'text/x-sls')), 'YamlLexer': ('pip._vendor.pygments.lexers.data', 'YAML', ('yaml',), ('*.yaml', '*.yml'), ('text/x-yaml',)), 'YangLexer': ('pip._vendor.pygments.lexers.yang', 'YANG', ('yang',), ('*.yang',), ('application/yang',)), + 'YaraLexer': ('pip._vendor.pygments.lexers.yara', 'YARA', ('yara', 'yar'), ('*.yar',), ('text/x-yara',)), 'ZeekLexer': ('pip._vendor.pygments.lexers.dsls', 'Zeek', ('zeek', 'bro'), ('*.zeek', '*.bro'), ()), 'ZephirLexer': ('pip._vendor.pygments.lexers.php', 'Zephir', ('zephir',), ('*.zep',), ()), 'ZigLexer': ('pip._vendor.pygments.lexers.zig', 'Zig', ('zig',), ('*.zig',), ('text/zig',)), diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/python.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/python.py index e9bf2d3..b2d07f2 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/python.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/lexers/python.py @@ -4,15 +4,14 @@ Lexers for Python and related languages. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ -import re import keyword -from pip._vendor.pygments.lexer import DelegatingLexer, Lexer, RegexLexer, include, \ - bygroups, using, default, words, combined, do_insertions, this, line_re +from pip._vendor.pygments.lexer import DelegatingLexer, RegexLexer, include, \ + bygroups, using, default, words, combined, this from pip._vendor.pygments.util import get_bool_opt, shebang_matches from pip._vendor.pygments.token import Text, Comment, Operator, Keyword, Name, String, \ Number, Punctuation, Generic, Other, Error, Whitespace @@ -27,16 +26,14 @@ class PythonLexer(RegexLexer): """ For Python source code (version 3.x). - .. versionadded:: 0.10 - .. versionchanged:: 2.5 This is now the default ``PythonLexer``. It is still available as the alias ``Python3Lexer``. """ name = 'Python' - url = 'http://www.python.org' - aliases = ['python', 'py', 'sage', 'python3', 'py3'] + url = 'https://www.python.org' + aliases = ['python', 'py', 'sage', 'python3', 'py3', 'bazel', 'starlark'] filenames = [ '*.py', '*.pyw', @@ -61,8 +58,9 @@ class PythonLexer(RegexLexer): ] mimetypes = ['text/x-python', 'application/x-python', 'text/x-python3', 'application/x-python3'] + version_added = '0.10' - uni_name = "[%s][%s]*" % (uni.xid_start, uni.xid_continue) + uni_name = f"[{uni.xid_start}][{uni.xid_continue}]*" def innerstring_rules(ttype): return [ @@ -224,7 +222,8 @@ class PythonLexer(RegexLexer): r'(match|case)\b' # a possible keyword r'(?![ \t]*(?:' # not followed by... r'[:,;=^&|@~)\]}]|(?:' + # characters and keywords that mean this isn't - r'|'.join(keyword.kwlist) + r')\b))', # pattern matching + # pattern matching (but None/True/False is ok) + r'|'.join(k for k in keyword.kwlist if k[0].islower()) + r')\b))', bygroups(Text, Keyword), 'soft-keywords-inner'), ], 'soft-keywords-inner': [ @@ -425,10 +424,11 @@ class Python2Lexer(RegexLexer): """ name = 'Python 2.x' - url = 'http://www.python.org' + url = 'https://www.python.org' aliases = ['python2', 'py2'] filenames = [] # now taken over by PythonLexer (3.x) mimetypes = ['text/x-python2', 'application/x-python2'] + version_added = '' def innerstring_rules(ttype): return [ @@ -637,7 +637,7 @@ class Python2Lexer(RegexLexer): class _PythonConsoleLexerBase(RegexLexer): name = 'Python console session' - aliases = ['pycon'] + aliases = ['pycon', 'python-console'] mimetypes = ['text/x-python-doctest'] """Auxiliary lexer for `PythonConsoleLexer`. @@ -696,8 +696,10 @@ class PythonConsoleLexer(DelegatingLexer): """ name = 'Python console session' - aliases = ['pycon'] + aliases = ['pycon', 'python-console'] mimetypes = ['text/x-python-doctest'] + url = 'https://python.org' + version_added = '' def __init__(self, **options): python3 = get_bool_opt(options, 'python3', True) @@ -721,8 +723,6 @@ class PythonTracebackLexer(RegexLexer): """ For Python 3.x tracebacks, with support for chained exceptions. - .. versionadded:: 1.0 - .. versionchanged:: 2.5 This is now the default ``PythonTracebackLexer``. It is still available as the alias ``Python3TracebackLexer``. @@ -732,6 +732,8 @@ class PythonTracebackLexer(RegexLexer): aliases = ['pytb', 'py3tb'] filenames = ['*.pytb', '*.py3tb'] mimetypes = ['text/x-python-traceback', 'text/x-python3-traceback'] + url = 'https://python.org' + version_added = '1.0' tokens = { 'root': [ @@ -778,8 +780,6 @@ class Python2TracebackLexer(RegexLexer): """ For Python tracebacks. - .. versionadded:: 0.7 - .. versionchanged:: 2.5 This class has been renamed from ``PythonTracebackLexer``. ``PythonTracebackLexer`` now refers to the Python 3 variant. @@ -789,6 +789,8 @@ class Python2TracebackLexer(RegexLexer): aliases = ['py2tb'] filenames = ['*.py2tb'] mimetypes = ['text/x-python2-traceback'] + url = 'https://python.org' + version_added = '0.7' tokens = { 'root': [ @@ -825,15 +827,14 @@ class Python2TracebackLexer(RegexLexer): class CythonLexer(RegexLexer): """ For Pyrex and Cython source code. - - .. versionadded:: 1.1 """ name = 'Cython' - url = 'http://cython.org' + url = 'https://cython.org' aliases = ['cython', 'pyx', 'pyrex'] filenames = ['*.pyx', '*.pxd', '*.pxi'] mimetypes = ['text/x-cython', 'application/x-cython'] + version_added = '1.1' tokens = { 'root': [ @@ -1007,13 +1008,13 @@ class DgLexer(RegexLexer): Lexer for dg, a functional and object-oriented programming language running on the CPython 3 VM. - - .. versionadded:: 1.6 """ name = 'dg' aliases = ['dg'] filenames = ['*.dg'] mimetypes = ['text/x-dg'] + url = 'http://pyos.github.io/dg' + version_added = '1.6' tokens = { 'root': [ @@ -1104,13 +1105,12 @@ class DgLexer(RegexLexer): class NumPyLexer(PythonLexer): """ A Python lexer recognizing Numerical Python builtins. - - .. versionadded:: 0.10 """ name = 'NumPy' url = 'https://numpy.org/' aliases = ['numpy'] + version_added = '0.10' # override the mimetypes to not inherit them from python mimetypes = [] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/modeline.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/modeline.py index 7b6f6a3..e4d9fe1 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/modeline.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/modeline.py @@ -4,7 +4,7 @@ A simple modeline parser (based on pymodeline). - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -19,7 +19,7 @@ modeline_re = re.compile(r''' ''', re.VERBOSE) -def get_filetype_from_line(l): +def get_filetype_from_line(l): # noqa: E741 m = modeline_re.search(l) if m: return m.group(1) @@ -30,8 +30,8 @@ def get_filetype_from_buffer(buf, max_lines=5): Scan the buffer for modelines and return filetype if one is found. """ lines = buf.splitlines() - for l in lines[-1:-max_lines-1:-1]: - ret = get_filetype_from_line(l) + for line in lines[-1:-max_lines-1:-1]: + ret = get_filetype_from_line(line) if ret: return ret for i in range(max_lines, -1, -1): diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/plugin.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/plugin.py index 7b722d5..2e462f2 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/plugin.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/plugin.py @@ -2,12 +2,7 @@ pygments.plugin ~~~~~~~~~~~~~~~ - Pygments plugin interface. By default, this tries to use - ``importlib.metadata``, which is in the Python standard - library since Python 3.8, or its ``importlib_metadata`` - backport for earlier versions of Python. It falls back on - ``pkg_resources`` if not found. Finally, if ``pkg_resources`` - is not found either, no plugins are loaded at all. + Pygments plugin interface. lexer plugins:: @@ -34,9 +29,10 @@ yourfilter = yourfilter:YourFilter - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ +from importlib.metadata import entry_points LEXER_ENTRY_POINT = 'pygments.lexers' FORMATTER_ENTRY_POINT = 'pygments.formatters' @@ -45,18 +41,6 @@ FILTER_ENTRY_POINT = 'pygments.filters' def iter_entry_points(group_name): - try: - from importlib.metadata import entry_points - except ImportError: - try: - from importlib_metadata import entry_points - except ImportError: - try: - from pip._vendor.pkg_resources import iter_entry_points - except (ImportError, OSError): - return [] - else: - return iter_entry_points(group_name) groups = entry_points() if hasattr(groups, 'select'): # New interface in Python 3.10 and newer versions of the diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/regexopt.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/regexopt.py index 45223ec..c44eedb 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/regexopt.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/regexopt.py @@ -5,7 +5,7 @@ An algorithm that generates optimized regexes for matching long lists of literal strings. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/scanner.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/scanner.py index 32a2f30..112da34 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/scanner.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/scanner.py @@ -11,7 +11,7 @@ Have a look at the `DelphiLexer` to get an idea of how to use this scanner. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ import re diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/sphinxext.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/sphinxext.py index 2c7facd..34077a2 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/sphinxext.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/sphinxext.py @@ -5,7 +5,7 @@ Sphinx extension to generate automatic documentation of lexers, formatters and filters. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -33,6 +33,8 @@ LEXERDOC = ''' %s + %s + ''' FMTERDOC = ''' @@ -119,11 +121,11 @@ class PygmentsDoc(Directive): def write_row(*columns): """Format a table row""" out = [] - for l, c in zip(column_lengths, columns): - if c: - out.append(c.ljust(l)) + for length, col in zip(column_lengths, columns): + if col: + out.append(col.ljust(length)) else: - out.append(' '*l) + out.append(' '*length) return ' '.join(out) @@ -147,6 +149,10 @@ class PygmentsDoc(Directive): def document_lexers(self): from pip._vendor.pygments.lexers._mapping import LEXERS + from pip._vendor import pygments + import inspect + import pathlib + out = [] modules = {} moduledocstrings = {} @@ -156,16 +162,40 @@ class PygmentsDoc(Directive): self.filenames.add(mod.__file__) cls = getattr(mod, classname) if not cls.__doc__: - print("Warning: %s does not have a docstring." % classname) + print(f"Warning: {classname} does not have a docstring.") docstring = cls.__doc__ if isinstance(docstring, bytes): docstring = docstring.decode('utf8') + + example_file = getattr(cls, '_example', None) + if example_file: + p = pathlib.Path(inspect.getabsfile(pygments)).parent.parent /\ + 'tests' / 'examplefiles' / example_file + content = p.read_text(encoding='utf-8') + if not content: + raise Exception( + f"Empty example file '{example_file}' for lexer " + f"{classname}") + + if data[2]: + lexer_name = data[2][0] + docstring += '\n\n .. admonition:: Example\n' + docstring += f'\n .. code-block:: {lexer_name}\n\n' + for line in content.splitlines(): + docstring += f' {line}\n' + + if cls.version_added: + version_line = f'.. versionadded:: {cls.version_added}' + else: + version_line = '' + modules.setdefault(module, []).append(( classname, ', '.join(data[2]) or 'None', ', '.join(data[3]).replace('*', '\\*').replace('_', '\\') or 'None', ', '.join(data[4]) or 'None', - docstring)) + docstring, + version_line)) if module not in moduledocstrings: moddoc = mod.__doc__ if isinstance(moddoc, bytes): @@ -174,7 +204,7 @@ class PygmentsDoc(Directive): for module, lexers in sorted(modules.items(), key=lambda x: x[0]): if moduledocstrings[module] is None: - raise Exception("Missing docstring for %s" % (module,)) + raise Exception(f"Missing docstring for {module}") heading = moduledocstrings[module].splitlines()[4].strip().rstrip('.') out.append(MODULEDOC % (module, heading, '-'*len(heading))) for data in lexers: diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/style.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/style.py index edc1962..076e63f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/style.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/style.py @@ -4,7 +4,7 @@ Basic style object. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -76,7 +76,7 @@ class StyleMeta(type): return '' elif text.startswith('var') or text.startswith('calc'): return text - assert False, "wrong color format %r" % text + assert False, f"wrong color format {text!r}" _styles = obj._styles = {} @@ -190,6 +190,12 @@ class Style(metaclass=StyleMeta): #: Style definitions for individual token types. styles = {} + #: user-friendly style name (used when selecting the style, so this + # should be all-lowercase, no spaces, hyphens) + name = 'unnamed' + + aliases = [] + # Attribute for lexers defined within Pygments. If set # to True, the style is not shown in the style gallery # on the website. This is intended for language-specific diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__init__.py index 7401cf5..712f6e6 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__init__.py @@ -4,65 +4,21 @@ Contains built-in styles. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ from pip._vendor.pygments.plugin import find_plugin_styles from pip._vendor.pygments.util import ClassNotFound +from pip._vendor.pygments.styles._mapping import STYLES #: A dictionary of built-in styles, mapping style names to #: ``'submodule::classname'`` strings. -STYLE_MAP = { - 'default': 'default::DefaultStyle', - 'emacs': 'emacs::EmacsStyle', - 'friendly': 'friendly::FriendlyStyle', - 'friendly_grayscale': 'friendly_grayscale::FriendlyGrayscaleStyle', - 'colorful': 'colorful::ColorfulStyle', - 'autumn': 'autumn::AutumnStyle', - 'murphy': 'murphy::MurphyStyle', - 'manni': 'manni::ManniStyle', - 'material': 'material::MaterialStyle', - 'monokai': 'monokai::MonokaiStyle', - 'perldoc': 'perldoc::PerldocStyle', - 'pastie': 'pastie::PastieStyle', - 'borland': 'borland::BorlandStyle', - 'trac': 'trac::TracStyle', - 'native': 'native::NativeStyle', - 'fruity': 'fruity::FruityStyle', - 'bw': 'bw::BlackWhiteStyle', - 'vim': 'vim::VimStyle', - 'vs': 'vs::VisualStudioStyle', - 'tango': 'tango::TangoStyle', - 'rrt': 'rrt::RrtStyle', - 'xcode': 'xcode::XcodeStyle', - 'igor': 'igor::IgorStyle', - 'paraiso-light': 'paraiso_light::ParaisoLightStyle', - 'paraiso-dark': 'paraiso_dark::ParaisoDarkStyle', - 'lovelace': 'lovelace::LovelaceStyle', - 'algol': 'algol::AlgolStyle', - 'algol_nu': 'algol_nu::Algol_NuStyle', - 'arduino': 'arduino::ArduinoStyle', - 'rainbow_dash': 'rainbow_dash::RainbowDashStyle', - 'abap': 'abap::AbapStyle', - 'solarized-dark': 'solarized::SolarizedDarkStyle', - 'solarized-light': 'solarized::SolarizedLightStyle', - 'sas': 'sas::SasStyle', - 'staroffice' : 'staroffice::StarofficeStyle', - 'stata': 'stata_light::StataLightStyle', - 'stata-light': 'stata_light::StataLightStyle', - 'stata-dark': 'stata_dark::StataDarkStyle', - 'inkpot': 'inkpot::InkPotStyle', - 'zenburn': 'zenburn::ZenburnStyle', - 'gruvbox-dark': 'gruvbox::GruvboxDarkStyle', - 'gruvbox-light': 'gruvbox::GruvboxLightStyle', - 'dracula': 'dracula::DraculaStyle', - 'one-dark': 'onedark::OneDarkStyle', - 'lilypond' : 'lilypond::LilyPondStyle', - 'nord': 'nord::NordStyle', - 'nord-darker': 'nord::NordDarkerStyle', - 'github-dark': 'gh_dark::GhDarkStyle' -} +#: This list is deprecated. Use `pygments.styles.STYLES` instead +STYLE_MAP = {v[1]: v[0].split('.')[-1] + '::' + k for k, v in STYLES.items()} + +#: Internal reverse mapping to make `get_style_by_name` more efficient +_STYLE_NAME_TO_MODULE_MAP = {v[1]: (v[0], k) for k, v in STYLES.items()} def get_style_by_name(name): @@ -73,8 +29,8 @@ def get_style_by_name(name): Will raise :exc:`pygments.util.ClassNotFound` if no style of that name is found. """ - if name in STYLE_MAP: - mod, cls = STYLE_MAP[name].split('::') + if name in _STYLE_NAME_TO_MODULE_MAP: + mod, cls = _STYLE_NAME_TO_MODULE_MAP[name] builtin = "yes" else: for found_name, style in find_plugin_styles(): @@ -82,22 +38,24 @@ def get_style_by_name(name): return style # perhaps it got dropped into our styles package builtin = "" - mod = name + mod = 'pygments.styles.' + name cls = name.title() + "Style" try: - mod = __import__('pygments.styles.' + mod, None, None, [cls]) + mod = __import__(mod, None, None, [cls]) except ImportError: - raise ClassNotFound("Could not find style module %r" % mod + - (builtin and ", though it should be builtin") + ".") + raise ClassNotFound(f"Could not find style module {mod!r}" + + (builtin and ", though it should be builtin") + + ".") try: return getattr(mod, cls) except AttributeError: - raise ClassNotFound("Could not find style class %r in style module." % cls) + raise ClassNotFound(f"Could not find style class {cls!r} in style module.") def get_all_styles(): """Return a generator for all styles by name, both builtin and plugin.""" - yield from STYLE_MAP + for v in STYLES.values(): + yield v[1] for name, _ in find_plugin_styles(): yield name diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__pycache__/__init__.cpython-312.pyc index 8baa958..ec6c1e7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__pycache__/_mapping.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__pycache__/_mapping.cpython-312.pyc new file mode 100644 index 0000000..2252405 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/__pycache__/_mapping.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/_mapping.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/_mapping.py new file mode 100644 index 0000000..49a7fae --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/styles/_mapping.py @@ -0,0 +1,54 @@ +# Automatically generated by scripts/gen_mapfiles.py. +# DO NOT EDIT BY HAND; run `tox -e mapfiles` instead. + +STYLES = { + 'AbapStyle': ('pygments.styles.abap', 'abap', ()), + 'AlgolStyle': ('pygments.styles.algol', 'algol', ()), + 'Algol_NuStyle': ('pygments.styles.algol_nu', 'algol_nu', ()), + 'ArduinoStyle': ('pygments.styles.arduino', 'arduino', ()), + 'AutumnStyle': ('pygments.styles.autumn', 'autumn', ()), + 'BlackWhiteStyle': ('pygments.styles.bw', 'bw', ()), + 'BorlandStyle': ('pygments.styles.borland', 'borland', ()), + 'CoffeeStyle': ('pygments.styles.coffee', 'coffee', ()), + 'ColorfulStyle': ('pygments.styles.colorful', 'colorful', ()), + 'DefaultStyle': ('pygments.styles.default', 'default', ()), + 'DraculaStyle': ('pygments.styles.dracula', 'dracula', ()), + 'EmacsStyle': ('pygments.styles.emacs', 'emacs', ()), + 'FriendlyGrayscaleStyle': ('pygments.styles.friendly_grayscale', 'friendly_grayscale', ()), + 'FriendlyStyle': ('pygments.styles.friendly', 'friendly', ()), + 'FruityStyle': ('pygments.styles.fruity', 'fruity', ()), + 'GhDarkStyle': ('pygments.styles.gh_dark', 'github-dark', ()), + 'GruvboxDarkStyle': ('pygments.styles.gruvbox', 'gruvbox-dark', ()), + 'GruvboxLightStyle': ('pygments.styles.gruvbox', 'gruvbox-light', ()), + 'IgorStyle': ('pygments.styles.igor', 'igor', ()), + 'InkPotStyle': ('pygments.styles.inkpot', 'inkpot', ()), + 'LightbulbStyle': ('pygments.styles.lightbulb', 'lightbulb', ()), + 'LilyPondStyle': ('pygments.styles.lilypond', 'lilypond', ()), + 'LovelaceStyle': ('pygments.styles.lovelace', 'lovelace', ()), + 'ManniStyle': ('pygments.styles.manni', 'manni', ()), + 'MaterialStyle': ('pygments.styles.material', 'material', ()), + 'MonokaiStyle': ('pygments.styles.monokai', 'monokai', ()), + 'MurphyStyle': ('pygments.styles.murphy', 'murphy', ()), + 'NativeStyle': ('pygments.styles.native', 'native', ()), + 'NordDarkerStyle': ('pygments.styles.nord', 'nord-darker', ()), + 'NordStyle': ('pygments.styles.nord', 'nord', ()), + 'OneDarkStyle': ('pygments.styles.onedark', 'one-dark', ()), + 'ParaisoDarkStyle': ('pygments.styles.paraiso_dark', 'paraiso-dark', ()), + 'ParaisoLightStyle': ('pygments.styles.paraiso_light', 'paraiso-light', ()), + 'PastieStyle': ('pygments.styles.pastie', 'pastie', ()), + 'PerldocStyle': ('pygments.styles.perldoc', 'perldoc', ()), + 'RainbowDashStyle': ('pygments.styles.rainbow_dash', 'rainbow_dash', ()), + 'RrtStyle': ('pygments.styles.rrt', 'rrt', ()), + 'SasStyle': ('pygments.styles.sas', 'sas', ()), + 'SolarizedDarkStyle': ('pygments.styles.solarized', 'solarized-dark', ()), + 'SolarizedLightStyle': ('pygments.styles.solarized', 'solarized-light', ()), + 'StarofficeStyle': ('pygments.styles.staroffice', 'staroffice', ()), + 'StataDarkStyle': ('pygments.styles.stata_dark', 'stata-dark', ()), + 'StataLightStyle': ('pygments.styles.stata_light', 'stata-light', ()), + 'TangoStyle': ('pygments.styles.tango', 'tango', ()), + 'TracStyle': ('pygments.styles.trac', 'trac', ()), + 'VimStyle': ('pygments.styles.vim', 'vim', ()), + 'VisualStudioStyle': ('pygments.styles.vs', 'vs', ()), + 'XcodeStyle': ('pygments.styles.xcode', 'xcode', ()), + 'ZenburnStyle': ('pygments.styles.zenburn', 'zenburn', ()), +} diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/token.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/token.py index 7395cb6..f78018a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/token.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/token.py @@ -4,7 +4,7 @@ Basic token types and the standard tokens. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -209,5 +209,6 @@ STANDARD_TYPES = { Generic.Prompt: 'gp', Generic.Strong: 'gs', Generic.Subheading: 'gu', + Generic.EmphStrong: 'ges', Generic.Traceback: 'gt', } diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/unistring.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/unistring.py index 39f6bae..e2c3523 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/unistring.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/unistring.py @@ -7,7 +7,7 @@ Inspired by chartypes_create.py from the MoinMoin project. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -104,7 +104,7 @@ def _handle_runs(char_list): # pragma: no cover if a == b: yield a else: - yield '%s-%s' % (a, b) + yield f'{a}-{b}' if __name__ == '__main__': # pragma: no cover @@ -141,13 +141,13 @@ if __name__ == '__main__': # pragma: no cover for cat in sorted(categories): val = ''.join(_handle_runs(categories[cat])) - fp.write('%s = %a\n\n' % (cat, val)) + fp.write(f'{cat} = {val!a}\n\n') cats = sorted(categories) cats.remove('xid_start') cats.remove('xid_continue') - fp.write('cats = %r\n\n' % cats) + fp.write(f'cats = {cats!r}\n\n') - fp.write('# Generated from unidata %s\n\n' % (unicodedata.unidata_version,)) + fp.write(f'# Generated from unidata {unicodedata.unidata_version}\n\n') fp.write(footer) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/util.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/util.py index 941fdb9..83cf104 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/util.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pygments/util.py @@ -4,7 +4,7 @@ Utility functions. - :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -46,8 +46,7 @@ def get_choice_opt(options, optname, allowed, default=None, normcase=False): if normcase: string = string.lower() if string not in allowed: - raise OptionError('Value for option %s must be one of %s' % - (optname, ', '.join(map(str, allowed)))) + raise OptionError('Value for option {} must be one of {}'.format(optname, ', '.join(map(str, allowed)))) return string @@ -69,17 +68,15 @@ def get_bool_opt(options, optname, default=None): elif isinstance(string, int): return bool(string) elif not isinstance(string, str): - raise OptionError('Invalid type %r for option %s; use ' - '1/0, yes/no, true/false, on/off' % ( - string, optname)) + raise OptionError(f'Invalid type {string!r} for option {optname}; use ' + '1/0, yes/no, true/false, on/off') elif string.lower() in ('1', 'yes', 'true', 'on'): return True elif string.lower() in ('0', 'no', 'false', 'off'): return False else: - raise OptionError('Invalid value %r for option %s; use ' - '1/0, yes/no, true/false, on/off' % ( - string, optname)) + raise OptionError(f'Invalid value {string!r} for option {optname}; use ' + '1/0, yes/no, true/false, on/off') def get_int_opt(options, optname, default=None): @@ -88,13 +85,11 @@ def get_int_opt(options, optname, default=None): try: return int(string) except TypeError: - raise OptionError('Invalid type %r for option %s; you ' - 'must give an integer value' % ( - string, optname)) + raise OptionError(f'Invalid type {string!r} for option {optname}; you ' + 'must give an integer value') except ValueError: - raise OptionError('Invalid value %r for option %s; you ' - 'must give an integer value' % ( - string, optname)) + raise OptionError(f'Invalid value {string!r} for option {optname}; you ' + 'must give an integer value') def get_list_opt(options, optname, default=None): """ @@ -108,9 +103,8 @@ def get_list_opt(options, optname, default=None): elif isinstance(val, (list, tuple)): return list(val) else: - raise OptionError('Invalid type %r for option %s; you ' - 'must give a list value' % ( - val, optname)) + raise OptionError(f'Invalid type {val!r} for option {optname}; you ' + 'must give a list value') def docstring_headline(obj): @@ -181,7 +175,7 @@ def shebang_matches(text, regex): if x and not x.startswith('-')][-1] except IndexError: return False - regex = re.compile(r'^%s(\.(exe|cmd|bat|bin))?$' % regex, re.IGNORECASE) + regex = re.compile(rf'^{regex}(\.(exe|cmd|bat|bin))?$', re.IGNORECASE) if regex.search(found) is not None: return True return False diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__init__.py deleted file mode 100644 index 88bc10a..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__init__.py +++ /dev/null @@ -1,322 +0,0 @@ -# module pyparsing.py -# -# Copyright (c) 2003-2022 Paul T. McGuire -# -# Permission is hereby granted, free of charge, to any person obtaining -# a copy of this software and associated documentation files (the -# "Software"), to deal in the Software without restriction, including -# without limitation the rights to use, copy, modify, merge, publish, -# distribute, sublicense, and/or sell copies of the Software, and to -# permit persons to whom the Software is furnished to do so, subject to -# the following conditions: -# -# The above copyright notice and this permission notice shall be -# included in all copies or substantial portions of the Software. -# -# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, -# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF -# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. -# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY -# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, -# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE -# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. -# - -__doc__ = """ -pyparsing module - Classes and methods to define and execute parsing grammars -============================================================================= - -The pyparsing module is an alternative approach to creating and -executing simple grammars, vs. the traditional lex/yacc approach, or the -use of regular expressions. With pyparsing, you don't need to learn -a new syntax for defining grammars or matching expressions - the parsing -module provides a library of classes that you use to construct the -grammar directly in Python. - -Here is a program to parse "Hello, World!" (or any greeting of the form -``", !"``), built up using :class:`Word`, -:class:`Literal`, and :class:`And` elements -(the :meth:`'+'` operators create :class:`And` expressions, -and the strings are auto-converted to :class:`Literal` expressions):: - - from pip._vendor.pyparsing import Word, alphas - - # define grammar of a greeting - greet = Word(alphas) + "," + Word(alphas) + "!" - - hello = "Hello, World!" - print(hello, "->", greet.parse_string(hello)) - -The program outputs the following:: - - Hello, World! -> ['Hello', ',', 'World', '!'] - -The Python representation of the grammar is quite readable, owing to the -self-explanatory class names, and the use of :class:`'+'`, -:class:`'|'`, :class:`'^'` and :class:`'&'` operators. - -The :class:`ParseResults` object returned from -:class:`ParserElement.parse_string` can be -accessed as a nested list, a dictionary, or an object with named -attributes. - -The pyparsing module handles some of the problems that are typically -vexing when writing text parsers: - - - extra or missing whitespace (the above program will also handle - "Hello,World!", "Hello , World !", etc.) - - quoted strings - - embedded comments - - -Getting Started - ------------------ -Visit the classes :class:`ParserElement` and :class:`ParseResults` to -see the base classes that most other pyparsing -classes inherit from. Use the docstrings for examples of how to: - - - construct literal match expressions from :class:`Literal` and - :class:`CaselessLiteral` classes - - construct character word-group expressions using the :class:`Word` - class - - see how to create repetitive expressions using :class:`ZeroOrMore` - and :class:`OneOrMore` classes - - use :class:`'+'`, :class:`'|'`, :class:`'^'`, - and :class:`'&'` operators to combine simple expressions into - more complex ones - - associate names with your parsed results using - :class:`ParserElement.set_results_name` - - access the parsed data, which is returned as a :class:`ParseResults` - object - - find some helpful expression short-cuts like :class:`DelimitedList` - and :class:`one_of` - - find more useful common expressions in the :class:`pyparsing_common` - namespace class -""" -from typing import NamedTuple - - -class version_info(NamedTuple): - major: int - minor: int - micro: int - releaselevel: str - serial: int - - @property - def __version__(self): - return ( - f"{self.major}.{self.minor}.{self.micro}" - + ( - f"{'r' if self.releaselevel[0] == 'c' else ''}{self.releaselevel[0]}{self.serial}", - "", - )[self.releaselevel == "final"] - ) - - def __str__(self): - return f"{__name__} {self.__version__} / {__version_time__}" - - def __repr__(self): - return f"{__name__}.{type(self).__name__}({', '.join('{}={!r}'.format(*nv) for nv in zip(self._fields, self))})" - - -__version_info__ = version_info(3, 1, 0, "final", 1) -__version_time__ = "18 Jun 2023 14:05 UTC" -__version__ = __version_info__.__version__ -__versionTime__ = __version_time__ -__author__ = "Paul McGuire " - -from .util import * -from .exceptions import * -from .actions import * -from .core import __diag__, __compat__ -from .results import * -from .core import * # type: ignore[misc, assignment] -from .core import _builtin_exprs as core_builtin_exprs -from .helpers import * # type: ignore[misc, assignment] -from .helpers import _builtin_exprs as helper_builtin_exprs - -from .unicode import unicode_set, UnicodeRangeList, pyparsing_unicode as unicode -from .testing import pyparsing_test as testing -from .common import ( - pyparsing_common as common, - _builtin_exprs as common_builtin_exprs, -) - -# define backward compat synonyms -if "pyparsing_unicode" not in globals(): - pyparsing_unicode = unicode # type: ignore[misc] -if "pyparsing_common" not in globals(): - pyparsing_common = common # type: ignore[misc] -if "pyparsing_test" not in globals(): - pyparsing_test = testing # type: ignore[misc] - -core_builtin_exprs += common_builtin_exprs + helper_builtin_exprs - - -__all__ = [ - "__version__", - "__version_time__", - "__author__", - "__compat__", - "__diag__", - "And", - "AtLineStart", - "AtStringStart", - "CaselessKeyword", - "CaselessLiteral", - "CharsNotIn", - "CloseMatch", - "Combine", - "DelimitedList", - "Dict", - "Each", - "Empty", - "FollowedBy", - "Forward", - "GoToColumn", - "Group", - "IndentedBlock", - "Keyword", - "LineEnd", - "LineStart", - "Literal", - "Located", - "PrecededBy", - "MatchFirst", - "NoMatch", - "NotAny", - "OneOrMore", - "OnlyOnce", - "OpAssoc", - "Opt", - "Optional", - "Or", - "ParseBaseException", - "ParseElementEnhance", - "ParseException", - "ParseExpression", - "ParseFatalException", - "ParseResults", - "ParseSyntaxException", - "ParserElement", - "PositionToken", - "QuotedString", - "RecursiveGrammarException", - "Regex", - "SkipTo", - "StringEnd", - "StringStart", - "Suppress", - "Token", - "TokenConverter", - "White", - "Word", - "WordEnd", - "WordStart", - "ZeroOrMore", - "Char", - "alphanums", - "alphas", - "alphas8bit", - "any_close_tag", - "any_open_tag", - "autoname_elements", - "c_style_comment", - "col", - "common_html_entity", - "condition_as_parse_action", - "counted_array", - "cpp_style_comment", - "dbl_quoted_string", - "dbl_slash_comment", - "delimited_list", - "dict_of", - "empty", - "hexnums", - "html_comment", - "identchars", - "identbodychars", - "infix_notation", - "java_style_comment", - "line", - "line_end", - "line_start", - "lineno", - "make_html_tags", - "make_xml_tags", - "match_only_at_col", - "match_previous_expr", - "match_previous_literal", - "nested_expr", - "null_debug_action", - "nums", - "one_of", - "original_text_for", - "printables", - "punc8bit", - "pyparsing_common", - "pyparsing_test", - "pyparsing_unicode", - "python_style_comment", - "quoted_string", - "remove_quotes", - "replace_with", - "replace_html_entity", - "rest_of_line", - "sgl_quoted_string", - "srange", - "string_end", - "string_start", - "token_map", - "trace_parse_action", - "ungroup", - "unicode_set", - "unicode_string", - "with_attribute", - "with_class", - # pre-PEP8 compatibility names - "__versionTime__", - "anyCloseTag", - "anyOpenTag", - "cStyleComment", - "commonHTMLEntity", - "conditionAsParseAction", - "countedArray", - "cppStyleComment", - "dblQuotedString", - "dblSlashComment", - "delimitedList", - "dictOf", - "htmlComment", - "indentedBlock", - "infixNotation", - "javaStyleComment", - "lineEnd", - "lineStart", - "locatedExpr", - "makeHTMLTags", - "makeXMLTags", - "matchOnlyAtCol", - "matchPreviousExpr", - "matchPreviousLiteral", - "nestedExpr", - "nullDebugAction", - "oneOf", - "opAssoc", - "originalTextFor", - "pythonStyleComment", - "quotedString", - "removeQuotes", - "replaceHTMLEntity", - "replaceWith", - "restOfLine", - "sglQuotedString", - "stringEnd", - "stringStart", - "tokenMap", - "traceParseAction", - "unicodeString", - "withAttribute", - "withClass", -] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 479b8b4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/actions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/actions.cpython-312.pyc deleted file mode 100644 index 957467d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/actions.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/common.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/common.cpython-312.pyc deleted file mode 100644 index d10deef..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/common.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/core.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/core.cpython-312.pyc deleted file mode 100644 index 32490c1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/core.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/exceptions.cpython-312.pyc deleted file mode 100644 index 3d9c68a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/exceptions.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/helpers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/helpers.cpython-312.pyc deleted file mode 100644 index 76ada75..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/helpers.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/results.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/results.cpython-312.pyc deleted file mode 100644 index dfe5e03..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/results.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/testing.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/testing.cpython-312.pyc deleted file mode 100644 index cfbdd81..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/testing.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/unicode.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/unicode.cpython-312.pyc deleted file mode 100644 index badb3a4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/unicode.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/util.cpython-312.pyc deleted file mode 100644 index ed566ca..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/__pycache__/util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/actions.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/actions.py deleted file mode 100644 index ca6e4c6..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/actions.py +++ /dev/null @@ -1,217 +0,0 @@ -# actions.py - -from .exceptions import ParseException -from .util import col, replaced_by_pep8 - - -class OnlyOnce: - """ - Wrapper for parse actions, to ensure they are only called once. - """ - - def __init__(self, method_call): - from .core import _trim_arity - - self.callable = _trim_arity(method_call) - self.called = False - - def __call__(self, s, l, t): - if not self.called: - results = self.callable(s, l, t) - self.called = True - return results - raise ParseException(s, l, "OnlyOnce obj called multiple times w/out reset") - - def reset(self): - """ - Allow the associated parse action to be called once more. - """ - - self.called = False - - -def match_only_at_col(n): - """ - Helper method for defining parse actions that require matching at - a specific column in the input text. - """ - - def verify_col(strg, locn, toks): - if col(locn, strg) != n: - raise ParseException(strg, locn, f"matched token not at column {n}") - - return verify_col - - -def replace_with(repl_str): - """ - Helper method for common parse actions that simply return - a literal value. Especially useful when used with - :class:`transform_string` (). - - Example:: - - num = Word(nums).set_parse_action(lambda toks: int(toks[0])) - na = one_of("N/A NA").set_parse_action(replace_with(math.nan)) - term = na | num - - term[1, ...].parse_string("324 234 N/A 234") # -> [324, 234, nan, 234] - """ - return lambda s, l, t: [repl_str] - - -def remove_quotes(s, l, t): - """ - Helper parse action for removing quotation marks from parsed - quoted strings. - - Example:: - - # by default, quotation marks are included in parsed results - quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"] - - # use remove_quotes to strip quotation marks from parsed results - quoted_string.set_parse_action(remove_quotes) - quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"] - """ - return t[0][1:-1] - - -def with_attribute(*args, **attr_dict): - """ - Helper to create a validating parse action to be used with start - tags created with :class:`make_xml_tags` or - :class:`make_html_tags`. Use ``with_attribute`` to qualify - a starting tag with a required attribute value, to avoid false - matches on common tags such as ```` or ``
``. - - Call ``with_attribute`` with a series of attribute names and - values. Specify the list of filter attributes names and values as: - - - keyword arguments, as in ``(align="right")``, or - - as an explicit dict with ``**`` operator, when an attribute - name is also a Python reserved word, as in ``**{"class":"Customer", "align":"right"}`` - - a list of name-value tuples, as in ``(("ns1:class", "Customer"), ("ns2:align", "right"))`` - - For attribute names with a namespace prefix, you must use the second - form. Attribute names are matched insensitive to upper/lower case. - - If just testing for ``class`` (with or without a namespace), use - :class:`with_class`. - - To verify that the attribute exists, but without specifying a value, - pass ``with_attribute.ANY_VALUE`` as the value. - - Example:: - - html = ''' -
- Some text -
1 4 0 1 0
-
1,3 2,3 1,1
-
this has no type
-
- - ''' - div,div_end = make_html_tags("div") - - # only match div tag having a type attribute with value "grid" - div_grid = div().set_parse_action(with_attribute(type="grid")) - grid_expr = div_grid + SkipTo(div | div_end)("body") - for grid_header in grid_expr.search_string(html): - print(grid_header.body) - - # construct a match with any div tag having a type attribute, regardless of the value - div_any_type = div().set_parse_action(with_attribute(type=with_attribute.ANY_VALUE)) - div_expr = div_any_type + SkipTo(div | div_end)("body") - for div_header in div_expr.search_string(html): - print(div_header.body) - - prints:: - - 1 4 0 1 0 - - 1 4 0 1 0 - 1,3 2,3 1,1 - """ - if args: - attrs = args[:] - else: - attrs = attr_dict.items() - attrs = [(k, v) for k, v in attrs] - - def pa(s, l, tokens): - for attrName, attrValue in attrs: - if attrName not in tokens: - raise ParseException(s, l, "no matching attribute " + attrName) - if attrValue != with_attribute.ANY_VALUE and tokens[attrName] != attrValue: - raise ParseException( - s, - l, - f"attribute {attrName!r} has value {tokens[attrName]!r}, must be {attrValue!r}", - ) - - return pa - - -with_attribute.ANY_VALUE = object() # type: ignore [attr-defined] - - -def with_class(classname, namespace=""): - """ - Simplified version of :class:`with_attribute` when - matching on a div class - made difficult because ``class`` is - a reserved word in Python. - - Example:: - - html = ''' -
- Some text -
1 4 0 1 0
-
1,3 2,3 1,1
-
this <div> has no class
-
- - ''' - div,div_end = make_html_tags("div") - div_grid = div().set_parse_action(with_class("grid")) - - grid_expr = div_grid + SkipTo(div | div_end)("body") - for grid_header in grid_expr.search_string(html): - print(grid_header.body) - - div_any_type = div().set_parse_action(with_class(withAttribute.ANY_VALUE)) - div_expr = div_any_type + SkipTo(div | div_end)("body") - for div_header in div_expr.search_string(html): - print(div_header.body) - - prints:: - - 1 4 0 1 0 - - 1 4 0 1 0 - 1,3 2,3 1,1 - """ - classattr = f"{namespace}:class" if namespace else "class" - return with_attribute(**{classattr: classname}) - - -# pre-PEP8 compatibility symbols -# fmt: off -@replaced_by_pep8(replace_with) -def replaceWith(): ... - -@replaced_by_pep8(remove_quotes) -def removeQuotes(): ... - -@replaced_by_pep8(with_attribute) -def withAttribute(): ... - -@replaced_by_pep8(with_class) -def withClass(): ... - -@replaced_by_pep8(match_only_at_col) -def matchOnlyAtCol(): ... - -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/common.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/common.py deleted file mode 100644 index 7a666b2..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/common.py +++ /dev/null @@ -1,432 +0,0 @@ -# common.py -from .core import * -from .helpers import DelimitedList, any_open_tag, any_close_tag -from datetime import datetime - - -# some other useful expressions - using lower-case class name since we are really using this as a namespace -class pyparsing_common: - """Here are some common low-level expressions that may be useful in - jump-starting parser development: - - - numeric forms (:class:`integers`, :class:`reals`, - :class:`scientific notation`) - - common :class:`programming identifiers` - - network addresses (:class:`MAC`, - :class:`IPv4`, :class:`IPv6`) - - ISO8601 :class:`dates` and - :class:`datetime` - - :class:`UUID` - - :class:`comma-separated list` - - :class:`url` - - Parse actions: - - - :class:`convert_to_integer` - - :class:`convert_to_float` - - :class:`convert_to_date` - - :class:`convert_to_datetime` - - :class:`strip_html_tags` - - :class:`upcase_tokens` - - :class:`downcase_tokens` - - Example:: - - pyparsing_common.number.run_tests(''' - # any int or real number, returned as the appropriate type - 100 - -100 - +100 - 3.14159 - 6.02e23 - 1e-12 - ''') - - pyparsing_common.fnumber.run_tests(''' - # any int or real number, returned as float - 100 - -100 - +100 - 3.14159 - 6.02e23 - 1e-12 - ''') - - pyparsing_common.hex_integer.run_tests(''' - # hex numbers - 100 - FF - ''') - - pyparsing_common.fraction.run_tests(''' - # fractions - 1/2 - -3/4 - ''') - - pyparsing_common.mixed_integer.run_tests(''' - # mixed fractions - 1 - 1/2 - -3/4 - 1-3/4 - ''') - - import uuid - pyparsing_common.uuid.set_parse_action(token_map(uuid.UUID)) - pyparsing_common.uuid.run_tests(''' - # uuid - 12345678-1234-5678-1234-567812345678 - ''') - - prints:: - - # any int or real number, returned as the appropriate type - 100 - [100] - - -100 - [-100] - - +100 - [100] - - 3.14159 - [3.14159] - - 6.02e23 - [6.02e+23] - - 1e-12 - [1e-12] - - # any int or real number, returned as float - 100 - [100.0] - - -100 - [-100.0] - - +100 - [100.0] - - 3.14159 - [3.14159] - - 6.02e23 - [6.02e+23] - - 1e-12 - [1e-12] - - # hex numbers - 100 - [256] - - FF - [255] - - # fractions - 1/2 - [0.5] - - -3/4 - [-0.75] - - # mixed fractions - 1 - [1] - - 1/2 - [0.5] - - -3/4 - [-0.75] - - 1-3/4 - [1.75] - - # uuid - 12345678-1234-5678-1234-567812345678 - [UUID('12345678-1234-5678-1234-567812345678')] - """ - - convert_to_integer = token_map(int) - """ - Parse action for converting parsed integers to Python int - """ - - convert_to_float = token_map(float) - """ - Parse action for converting parsed numbers to Python float - """ - - integer = Word(nums).set_name("integer").set_parse_action(convert_to_integer) - """expression that parses an unsigned integer, returns an int""" - - hex_integer = ( - Word(hexnums).set_name("hex integer").set_parse_action(token_map(int, 16)) - ) - """expression that parses a hexadecimal integer, returns an int""" - - signed_integer = ( - Regex(r"[+-]?\d+") - .set_name("signed integer") - .set_parse_action(convert_to_integer) - ) - """expression that parses an integer with optional leading sign, returns an int""" - - fraction = ( - signed_integer().set_parse_action(convert_to_float) - + "/" - + signed_integer().set_parse_action(convert_to_float) - ).set_name("fraction") - """fractional expression of an integer divided by an integer, returns a float""" - fraction.add_parse_action(lambda tt: tt[0] / tt[-1]) - - mixed_integer = ( - fraction | signed_integer + Opt(Opt("-").suppress() + fraction) - ).set_name("fraction or mixed integer-fraction") - """mixed integer of the form 'integer - fraction', with optional leading integer, returns float""" - mixed_integer.add_parse_action(sum) - - real = ( - Regex(r"[+-]?(?:\d+\.\d*|\.\d+)") - .set_name("real number") - .set_parse_action(convert_to_float) - ) - """expression that parses a floating point number and returns a float""" - - sci_real = ( - Regex(r"[+-]?(?:\d+(?:[eE][+-]?\d+)|(?:\d+\.\d*|\.\d+)(?:[eE][+-]?\d+)?)") - .set_name("real number with scientific notation") - .set_parse_action(convert_to_float) - ) - """expression that parses a floating point number with optional - scientific notation and returns a float""" - - # streamlining this expression makes the docs nicer-looking - number = (sci_real | real | signed_integer).setName("number").streamline() - """any numeric expression, returns the corresponding Python type""" - - fnumber = ( - Regex(r"[+-]?\d+\.?\d*([eE][+-]?\d+)?") - .set_name("fnumber") - .set_parse_action(convert_to_float) - ) - """any int or real number, returned as float""" - - identifier = Word(identchars, identbodychars).set_name("identifier") - """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')""" - - ipv4_address = Regex( - r"(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}" - ).set_name("IPv4 address") - "IPv4 address (``0.0.0.0 - 255.255.255.255``)" - - _ipv6_part = Regex(r"[0-9a-fA-F]{1,4}").set_name("hex_integer") - _full_ipv6_address = (_ipv6_part + (":" + _ipv6_part) * 7).set_name( - "full IPv6 address" - ) - _short_ipv6_address = ( - Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) - + "::" - + Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) - ).set_name("short IPv6 address") - _short_ipv6_address.add_condition( - lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8 - ) - _mixed_ipv6_address = ("::ffff:" + ipv4_address).set_name("mixed IPv6 address") - ipv6_address = Combine( - (_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).set_name( - "IPv6 address" - ) - ).set_name("IPv6 address") - "IPv6 address (long, short, or mixed form)" - - mac_address = Regex( - r"[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}" - ).set_name("MAC address") - "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)" - - @staticmethod - def convert_to_date(fmt: str = "%Y-%m-%d"): - """ - Helper to create a parse action for converting parsed date string to Python datetime.date - - Params - - - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%d"``) - - Example:: - - date_expr = pyparsing_common.iso8601_date.copy() - date_expr.set_parse_action(pyparsing_common.convert_to_date()) - print(date_expr.parse_string("1999-12-31")) - - prints:: - - [datetime.date(1999, 12, 31)] - """ - - def cvt_fn(ss, ll, tt): - try: - return datetime.strptime(tt[0], fmt).date() - except ValueError as ve: - raise ParseException(ss, ll, str(ve)) - - return cvt_fn - - @staticmethod - def convert_to_datetime(fmt: str = "%Y-%m-%dT%H:%M:%S.%f"): - """Helper to create a parse action for converting parsed - datetime string to Python datetime.datetime - - Params - - - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%dT%H:%M:%S.%f"``) - - Example:: - - dt_expr = pyparsing_common.iso8601_datetime.copy() - dt_expr.set_parse_action(pyparsing_common.convert_to_datetime()) - print(dt_expr.parse_string("1999-12-31T23:59:59.999")) - - prints:: - - [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)] - """ - - def cvt_fn(s, l, t): - try: - return datetime.strptime(t[0], fmt) - except ValueError as ve: - raise ParseException(s, l, str(ve)) - - return cvt_fn - - iso8601_date = Regex( - r"(?P\d{4})(?:-(?P\d\d)(?:-(?P\d\d))?)?" - ).set_name("ISO8601 date") - "ISO8601 date (``yyyy-mm-dd``)" - - iso8601_datetime = Regex( - r"(?P\d{4})-(?P\d\d)-(?P\d\d)[T ](?P\d\d):(?P\d\d)(:(?P\d\d(\.\d*)?)?)?(?PZ|[+-]\d\d:?\d\d)?" - ).set_name("ISO8601 datetime") - "ISO8601 datetime (``yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)``) - trailing seconds, milliseconds, and timezone optional; accepts separating ``'T'`` or ``' '``" - - uuid = Regex(r"[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}").set_name("UUID") - "UUID (``xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx``)" - - _html_stripper = any_open_tag.suppress() | any_close_tag.suppress() - - @staticmethod - def strip_html_tags(s: str, l: int, tokens: ParseResults): - """Parse action to remove HTML tags from web page HTML source - - Example:: - - # strip HTML links from normal text - text = 'More info at the pyparsing wiki page' - td, td_end = make_html_tags("TD") - table_text = td + SkipTo(td_end).set_parse_action(pyparsing_common.strip_html_tags)("body") + td_end - print(table_text.parse_string(text).body) - - Prints:: - - More info at the pyparsing wiki page - """ - return pyparsing_common._html_stripper.transform_string(tokens[0]) - - _commasepitem = ( - Combine( - OneOrMore( - ~Literal(",") - + ~LineEnd() - + Word(printables, exclude_chars=",") - + Opt(White(" \t") + ~FollowedBy(LineEnd() | ",")) - ) - ) - .streamline() - .set_name("commaItem") - ) - comma_separated_list = DelimitedList( - Opt(quoted_string.copy() | _commasepitem, default="") - ).set_name("comma separated list") - """Predefined expression of 1 or more printable words or quoted strings, separated by commas.""" - - upcase_tokens = staticmethod(token_map(lambda t: t.upper())) - """Parse action to convert tokens to upper case.""" - - downcase_tokens = staticmethod(token_map(lambda t: t.lower())) - """Parse action to convert tokens to lower case.""" - - # fmt: off - url = Regex( - # https://mathiasbynens.be/demo/url-regex - # https://gist.github.com/dperini/729294 - r"(?P" + - # protocol identifier (optional) - # short syntax // still required - r"(?:(?:(?Phttps?|ftp):)?\/\/)" + - # user:pass BasicAuth (optional) - r"(?:(?P\S+(?::\S*)?)@)?" + - r"(?P" + - # IP address exclusion - # private & local networks - r"(?!(?:10|127)(?:\.\d{1,3}){3})" + - r"(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})" + - r"(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})" + - # IP address dotted notation octets - # excludes loopback network 0.0.0.0 - # excludes reserved space >= 224.0.0.0 - # excludes network & broadcast addresses - # (first & last IP address of each class) - r"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])" + - r"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}" + - r"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))" + - r"|" + - # host & domain names, may end with dot - # can be replaced by a shortest alternative - # (?![-_])(?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+ - r"(?:" + - r"(?:" + - r"[a-z0-9\u00a1-\uffff]" + - r"[a-z0-9\u00a1-\uffff_-]{0,62}" + - r")?" + - r"[a-z0-9\u00a1-\uffff]\." + - r")+" + - # TLD identifier name, may end with dot - r"(?:[a-z\u00a1-\uffff]{2,}\.?)" + - r")" + - # port number (optional) - r"(:(?P\d{2,5}))?" + - # resource path (optional) - r"(?P\/[^?# ]*)?" + - # query string (optional) - r"(\?(?P[^#]*))?" + - # fragment (optional) - r"(#(?P\S*))?" + - r")" - ).set_name("url") - """URL (http/https/ftp scheme)""" - # fmt: on - - # pre-PEP8 compatibility names - convertToInteger = convert_to_integer - """Deprecated - use :class:`convert_to_integer`""" - convertToFloat = convert_to_float - """Deprecated - use :class:`convert_to_float`""" - convertToDate = convert_to_date - """Deprecated - use :class:`convert_to_date`""" - convertToDatetime = convert_to_datetime - """Deprecated - use :class:`convert_to_datetime`""" - stripHTMLTags = strip_html_tags - """Deprecated - use :class:`strip_html_tags`""" - upcaseTokens = upcase_tokens - """Deprecated - use :class:`upcase_tokens`""" - downcaseTokens = downcase_tokens - """Deprecated - use :class:`downcase_tokens`""" - - -_builtin_exprs = [ - v for v in vars(pyparsing_common).values() if isinstance(v, ParserElement) -] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/core.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/core.py deleted file mode 100644 index 8d5a856..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/core.py +++ /dev/null @@ -1,6115 +0,0 @@ -# -# core.py -# - -from collections import deque -import os -import typing -from typing import ( - Any, - Callable, - Generator, - List, - NamedTuple, - Sequence, - Set, - TextIO, - Tuple, - Union, - cast, -) -from abc import ABC, abstractmethod -from enum import Enum -import string -import copy -import warnings -import re -import sys -from collections.abc import Iterable -import traceback -import types -from operator import itemgetter -from functools import wraps -from threading import RLock -from pathlib import Path - -from .util import ( - _FifoCache, - _UnboundedCache, - __config_flags, - _collapse_string_to_ranges, - _escape_regex_range_chars, - _bslash, - _flatten, - LRUMemo as _LRUMemo, - UnboundedMemo as _UnboundedMemo, - replaced_by_pep8, -) -from .exceptions import * -from .actions import * -from .results import ParseResults, _ParseResultsWithOffset -from .unicode import pyparsing_unicode - -_MAX_INT = sys.maxsize -str_type: Tuple[type, ...] = (str, bytes) - -# -# Copyright (c) 2003-2022 Paul T. McGuire -# -# Permission is hereby granted, free of charge, to any person obtaining -# a copy of this software and associated documentation files (the -# "Software"), to deal in the Software without restriction, including -# without limitation the rights to use, copy, modify, merge, publish, -# distribute, sublicense, and/or sell copies of the Software, and to -# permit persons to whom the Software is furnished to do so, subject to -# the following conditions: -# -# The above copyright notice and this permission notice shall be -# included in all copies or substantial portions of the Software. -# -# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, -# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF -# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. -# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY -# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, -# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE -# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. -# - - -if sys.version_info >= (3, 8): - from functools import cached_property -else: - - class cached_property: - def __init__(self, func): - self._func = func - - def __get__(self, instance, owner=None): - ret = instance.__dict__[self._func.__name__] = self._func(instance) - return ret - - -class __compat__(__config_flags): - """ - A cross-version compatibility configuration for pyparsing features that will be - released in a future version. By setting values in this configuration to True, - those features can be enabled in prior versions for compatibility development - and testing. - - - ``collect_all_And_tokens`` - flag to enable fix for Issue #63 that fixes erroneous grouping - of results names when an :class:`And` expression is nested within an :class:`Or` or :class:`MatchFirst`; - maintained for compatibility, but setting to ``False`` no longer restores pre-2.3.1 - behavior - """ - - _type_desc = "compatibility" - - collect_all_And_tokens = True - - _all_names = [__ for __ in locals() if not __.startswith("_")] - _fixed_names = """ - collect_all_And_tokens - """.split() - - -class __diag__(__config_flags): - _type_desc = "diagnostic" - - warn_multiple_tokens_in_named_alternation = False - warn_ungrouped_named_tokens_in_collection = False - warn_name_set_on_empty_Forward = False - warn_on_parse_using_empty_Forward = False - warn_on_assignment_to_Forward = False - warn_on_multiple_string_args_to_oneof = False - warn_on_match_first_with_lshift_operator = False - enable_debug_on_named_expressions = False - - _all_names = [__ for __ in locals() if not __.startswith("_")] - _warning_names = [name for name in _all_names if name.startswith("warn")] - _debug_names = [name for name in _all_names if name.startswith("enable_debug")] - - @classmethod - def enable_all_warnings(cls) -> None: - for name in cls._warning_names: - cls.enable(name) - - -class Diagnostics(Enum): - """ - Diagnostic configuration (all default to disabled) - - - ``warn_multiple_tokens_in_named_alternation`` - flag to enable warnings when a results - name is defined on a :class:`MatchFirst` or :class:`Or` expression with one or more :class:`And` subexpressions - - ``warn_ungrouped_named_tokens_in_collection`` - flag to enable warnings when a results - name is defined on a containing expression with ungrouped subexpressions that also - have results names - - ``warn_name_set_on_empty_Forward`` - flag to enable warnings when a :class:`Forward` is defined - with a results name, but has no contents defined - - ``warn_on_parse_using_empty_Forward`` - flag to enable warnings when a :class:`Forward` is - defined in a grammar but has never had an expression attached to it - - ``warn_on_assignment_to_Forward`` - flag to enable warnings when a :class:`Forward` is defined - but is overwritten by assigning using ``'='`` instead of ``'<<='`` or ``'<<'`` - - ``warn_on_multiple_string_args_to_oneof`` - flag to enable warnings when :class:`one_of` is - incorrectly called with multiple str arguments - - ``enable_debug_on_named_expressions`` - flag to auto-enable debug on all subsequent - calls to :class:`ParserElement.set_name` - - Diagnostics are enabled/disabled by calling :class:`enable_diag` and :class:`disable_diag`. - All warnings can be enabled by calling :class:`enable_all_warnings`. - """ - - warn_multiple_tokens_in_named_alternation = 0 - warn_ungrouped_named_tokens_in_collection = 1 - warn_name_set_on_empty_Forward = 2 - warn_on_parse_using_empty_Forward = 3 - warn_on_assignment_to_Forward = 4 - warn_on_multiple_string_args_to_oneof = 5 - warn_on_match_first_with_lshift_operator = 6 - enable_debug_on_named_expressions = 7 - - -def enable_diag(diag_enum: Diagnostics) -> None: - """ - Enable a global pyparsing diagnostic flag (see :class:`Diagnostics`). - """ - __diag__.enable(diag_enum.name) - - -def disable_diag(diag_enum: Diagnostics) -> None: - """ - Disable a global pyparsing diagnostic flag (see :class:`Diagnostics`). - """ - __diag__.disable(diag_enum.name) - - -def enable_all_warnings() -> None: - """ - Enable all global pyparsing diagnostic warnings (see :class:`Diagnostics`). - """ - __diag__.enable_all_warnings() - - -# hide abstract class -del __config_flags - - -def _should_enable_warnings( - cmd_line_warn_options: typing.Iterable[str], warn_env_var: typing.Optional[str] -) -> bool: - enable = bool(warn_env_var) - for warn_opt in cmd_line_warn_options: - w_action, w_message, w_category, w_module, w_line = (warn_opt + "::::").split( - ":" - )[:5] - if not w_action.lower().startswith("i") and ( - not (w_message or w_category or w_module) or w_module == "pyparsing" - ): - enable = True - elif w_action.lower().startswith("i") and w_module in ("pyparsing", ""): - enable = False - return enable - - -if _should_enable_warnings( - sys.warnoptions, os.environ.get("PYPARSINGENABLEALLWARNINGS") -): - enable_all_warnings() - - -# build list of single arg builtins, that can be used as parse actions -_single_arg_builtins = { - sum, - len, - sorted, - reversed, - list, - tuple, - set, - any, - all, - min, - max, -} - -_generatorType = types.GeneratorType -ParseImplReturnType = Tuple[int, Any] -PostParseReturnType = Union[ParseResults, Sequence[ParseResults]] -ParseAction = Union[ - Callable[[], Any], - Callable[[ParseResults], Any], - Callable[[int, ParseResults], Any], - Callable[[str, int, ParseResults], Any], -] -ParseCondition = Union[ - Callable[[], bool], - Callable[[ParseResults], bool], - Callable[[int, ParseResults], bool], - Callable[[str, int, ParseResults], bool], -] -ParseFailAction = Callable[[str, int, "ParserElement", Exception], None] -DebugStartAction = Callable[[str, int, "ParserElement", bool], None] -DebugSuccessAction = Callable[ - [str, int, int, "ParserElement", ParseResults, bool], None -] -DebugExceptionAction = Callable[[str, int, "ParserElement", Exception, bool], None] - - -alphas = string.ascii_uppercase + string.ascii_lowercase -identchars = pyparsing_unicode.Latin1.identchars -identbodychars = pyparsing_unicode.Latin1.identbodychars -nums = "0123456789" -hexnums = nums + "ABCDEFabcdef" -alphanums = alphas + nums -printables = "".join([c for c in string.printable if c not in string.whitespace]) - -_trim_arity_call_line: traceback.StackSummary = None # type: ignore[assignment] - - -def _trim_arity(func, max_limit=3): - """decorator to trim function calls to match the arity of the target""" - global _trim_arity_call_line - - if func in _single_arg_builtins: - return lambda s, l, t: func(t) - - limit = 0 - found_arity = False - - # synthesize what would be returned by traceback.extract_stack at the call to - # user's parse action 'func', so that we don't incur call penalty at parse time - - # fmt: off - LINE_DIFF = 7 - # IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND - # THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!! - _trim_arity_call_line = (_trim_arity_call_line or traceback.extract_stack(limit=2)[-1]) - pa_call_line_synth = (_trim_arity_call_line[0], _trim_arity_call_line[1] + LINE_DIFF) - - def wrapper(*args): - nonlocal found_arity, limit - while 1: - try: - ret = func(*args[limit:]) - found_arity = True - return ret - except TypeError as te: - # re-raise TypeErrors if they did not come from our arity testing - if found_arity: - raise - else: - tb = te.__traceback__ - frames = traceback.extract_tb(tb, limit=2) - frame_summary = frames[-1] - trim_arity_type_error = ( - [frame_summary[:2]][-1][:2] == pa_call_line_synth - ) - del tb - - if trim_arity_type_error: - if limit < max_limit: - limit += 1 - continue - - raise - # fmt: on - - # copy func name to wrapper for sensible debug output - # (can't use functools.wraps, since that messes with function signature) - func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) - wrapper.__name__ = func_name - wrapper.__doc__ = func.__doc__ - - return wrapper - - -def condition_as_parse_action( - fn: ParseCondition, message: typing.Optional[str] = None, fatal: bool = False -) -> ParseAction: - """ - Function to convert a simple predicate function that returns ``True`` or ``False`` - into a parse action. Can be used in places when a parse action is required - and :class:`ParserElement.add_condition` cannot be used (such as when adding a condition - to an operator level in :class:`infix_notation`). - - Optional keyword arguments: - - - ``message`` - define a custom message to be used in the raised exception - - ``fatal`` - if True, will raise :class:`ParseFatalException` to stop parsing immediately; - otherwise will raise :class:`ParseException` - - """ - msg = message if message is not None else "failed user-defined condition" - exc_type = ParseFatalException if fatal else ParseException - fn = _trim_arity(fn) - - @wraps(fn) - def pa(s, l, t): - if not bool(fn(s, l, t)): - raise exc_type(s, l, msg) - - return pa - - -def _default_start_debug_action( - instring: str, loc: int, expr: "ParserElement", cache_hit: bool = False -): - cache_hit_str = "*" if cache_hit else "" - print( - ( - f"{cache_hit_str}Match {expr} at loc {loc}({lineno(loc, instring)},{col(loc, instring)})\n" - f" {line(loc, instring)}\n" - f" {' ' * (col(loc, instring) - 1)}^" - ) - ) - - -def _default_success_debug_action( - instring: str, - startloc: int, - endloc: int, - expr: "ParserElement", - toks: ParseResults, - cache_hit: bool = False, -): - cache_hit_str = "*" if cache_hit else "" - print(f"{cache_hit_str}Matched {expr} -> {toks.as_list()}") - - -def _default_exception_debug_action( - instring: str, - loc: int, - expr: "ParserElement", - exc: Exception, - cache_hit: bool = False, -): - cache_hit_str = "*" if cache_hit else "" - print(f"{cache_hit_str}Match {expr} failed, {type(exc).__name__} raised: {exc}") - - -def null_debug_action(*args): - """'Do-nothing' debug action, to suppress debugging output during parsing.""" - - -class ParserElement(ABC): - """Abstract base level parser element class.""" - - DEFAULT_WHITE_CHARS: str = " \n\t\r" - verbose_stacktrace: bool = False - _literalStringClass: type = None # type: ignore[assignment] - - @staticmethod - def set_default_whitespace_chars(chars: str) -> None: - r""" - Overrides the default whitespace chars - - Example:: - - # default whitespace chars are space, and newline - Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl'] - - # change to just treat newline as significant - ParserElement.set_default_whitespace_chars(" \t") - Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def'] - """ - ParserElement.DEFAULT_WHITE_CHARS = chars - - # update whitespace all parse expressions defined in this module - for expr in _builtin_exprs: - if expr.copyDefaultWhiteChars: - expr.whiteChars = set(chars) - - @staticmethod - def inline_literals_using(cls: type) -> None: - """ - Set class to be used for inclusion of string literals into a parser. - - Example:: - - # default literal class used is Literal - integer = Word(nums) - date_str = integer("year") + '/' + integer("month") + '/' + integer("day") - - date_str.parse_string("1999/12/31") # -> ['1999', '/', '12', '/', '31'] - - - # change to Suppress - ParserElement.inline_literals_using(Suppress) - date_str = integer("year") + '/' + integer("month") + '/' + integer("day") - - date_str.parse_string("1999/12/31") # -> ['1999', '12', '31'] - """ - ParserElement._literalStringClass = cls - - @classmethod - def using_each(cls, seq, **class_kwargs): - """ - Yields a sequence of class(obj, **class_kwargs) for obj in seq. - - Example:: - - LPAR, RPAR, LBRACE, RBRACE, SEMI = Suppress.using_each("(){};") - - """ - yield from (cls(obj, **class_kwargs) for obj in seq) - - class DebugActions(NamedTuple): - debug_try: typing.Optional[DebugStartAction] - debug_match: typing.Optional[DebugSuccessAction] - debug_fail: typing.Optional[DebugExceptionAction] - - def __init__(self, savelist: bool = False): - self.parseAction: List[ParseAction] = list() - self.failAction: typing.Optional[ParseFailAction] = None - self.customName: str = None # type: ignore[assignment] - self._defaultName: typing.Optional[str] = None - self.resultsName: str = None # type: ignore[assignment] - self.saveAsList = savelist - self.skipWhitespace = True - self.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) - self.copyDefaultWhiteChars = True - # used when checking for left-recursion - self.mayReturnEmpty = False - self.keepTabs = False - self.ignoreExprs: List["ParserElement"] = list() - self.debug = False - self.streamlined = False - # optimize exception handling for subclasses that don't advance parse index - self.mayIndexError = True - self.errmsg = "" - # mark results names as modal (report only last) or cumulative (list all) - self.modalResults = True - # custom debug actions - self.debugActions = self.DebugActions(None, None, None) - # avoid redundant calls to preParse - self.callPreparse = True - self.callDuringTry = False - self.suppress_warnings_: List[Diagnostics] = [] - - def suppress_warning(self, warning_type: Diagnostics) -> "ParserElement": - """ - Suppress warnings emitted for a particular diagnostic on this expression. - - Example:: - - base = pp.Forward() - base.suppress_warning(Diagnostics.warn_on_parse_using_empty_Forward) - - # statement would normally raise a warning, but is now suppressed - print(base.parse_string("x")) - - """ - self.suppress_warnings_.append(warning_type) - return self - - def visit_all(self): - """General-purpose method to yield all expressions and sub-expressions - in a grammar. Typically just for internal use. - """ - to_visit = deque([self]) - seen = set() - while to_visit: - cur = to_visit.popleft() - - # guard against looping forever through recursive grammars - if cur in seen: - continue - seen.add(cur) - - to_visit.extend(cur.recurse()) - yield cur - - def copy(self) -> "ParserElement": - """ - Make a copy of this :class:`ParserElement`. Useful for defining - different parse actions for the same parsing pattern, using copies of - the original parse element. - - Example:: - - integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) - integerK = integer.copy().add_parse_action(lambda toks: toks[0] * 1024) + Suppress("K") - integerM = integer.copy().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") - - print((integerK | integerM | integer)[1, ...].parse_string("5K 100 640K 256M")) - - prints:: - - [5120, 100, 655360, 268435456] - - Equivalent form of ``expr.copy()`` is just ``expr()``:: - - integerM = integer().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") - """ - cpy = copy.copy(self) - cpy.parseAction = self.parseAction[:] - cpy.ignoreExprs = self.ignoreExprs[:] - if self.copyDefaultWhiteChars: - cpy.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) - return cpy - - def set_results_name( - self, name: str, list_all_matches: bool = False, *, listAllMatches: bool = False - ) -> "ParserElement": - """ - Define name for referencing matching tokens as a nested attribute - of the returned parse results. - - Normally, results names are assigned as you would assign keys in a dict: - any existing value is overwritten by later values. If it is necessary to - keep all values captured for a particular results name, call ``set_results_name`` - with ``list_all_matches`` = True. - - NOTE: ``set_results_name`` returns a *copy* of the original :class:`ParserElement` object; - this is so that the client can define a basic element, such as an - integer, and reference it in multiple places with different names. - - You can also set results names using the abbreviated syntax, - ``expr("name")`` in place of ``expr.set_results_name("name")`` - - see :class:`__call__`. If ``list_all_matches`` is required, use - ``expr("name*")``. - - Example:: - - date_str = (integer.set_results_name("year") + '/' - + integer.set_results_name("month") + '/' - + integer.set_results_name("day")) - - # equivalent form: - date_str = integer("year") + '/' + integer("month") + '/' + integer("day") - """ - listAllMatches = listAllMatches or list_all_matches - return self._setResultsName(name, listAllMatches) - - def _setResultsName(self, name, listAllMatches=False): - if name is None: - return self - newself = self.copy() - if name.endswith("*"): - name = name[:-1] - listAllMatches = True - newself.resultsName = name - newself.modalResults = not listAllMatches - return newself - - def set_break(self, break_flag: bool = True) -> "ParserElement": - """ - Method to invoke the Python pdb debugger when this element is - about to be parsed. Set ``break_flag`` to ``True`` to enable, ``False`` to - disable. - """ - if break_flag: - _parseMethod = self._parse - - def breaker(instring, loc, doActions=True, callPreParse=True): - import pdb - - # this call to pdb.set_trace() is intentional, not a checkin error - pdb.set_trace() - return _parseMethod(instring, loc, doActions, callPreParse) - - breaker._originalParseMethod = _parseMethod # type: ignore [attr-defined] - self._parse = breaker # type: ignore [assignment] - else: - if hasattr(self._parse, "_originalParseMethod"): - self._parse = self._parse._originalParseMethod # type: ignore [attr-defined, assignment] - return self - - def set_parse_action(self, *fns: ParseAction, **kwargs) -> "ParserElement": - """ - Define one or more actions to perform when successfully matching parse element definition. - - Parse actions can be called to perform data conversions, do extra validation, - update external data structures, or enhance or replace the parsed tokens. - Each parse action ``fn`` is a callable method with 0-3 arguments, called as - ``fn(s, loc, toks)`` , ``fn(loc, toks)`` , ``fn(toks)`` , or just ``fn()`` , where: - - - ``s`` = the original string being parsed (see note below) - - ``loc`` = the location of the matching substring - - ``toks`` = a list of the matched tokens, packaged as a :class:`ParseResults` object - - The parsed tokens are passed to the parse action as ParseResults. They can be - modified in place using list-style append, extend, and pop operations to update - the parsed list elements; and with dictionary-style item set and del operations - to add, update, or remove any named results. If the tokens are modified in place, - it is not necessary to return them with a return statement. - - Parse actions can also completely replace the given tokens, with another ``ParseResults`` - object, or with some entirely different object (common for parse actions that perform data - conversions). A convenient way to build a new parse result is to define the values - using a dict, and then create the return value using :class:`ParseResults.from_dict`. - - If None is passed as the ``fn`` parse action, all previously added parse actions for this - expression are cleared. - - Optional keyword arguments: - - - ``call_during_try`` = (default= ``False``) indicate if parse action should be run during - lookaheads and alternate testing. For parse actions that have side effects, it is - important to only call the parse action once it is determined that it is being - called as part of a successful parse. For parse actions that perform additional - validation, then call_during_try should be passed as True, so that the validation - code is included in the preliminary "try" parses. - - Note: the default parsing behavior is to expand tabs in the input string - before starting the parsing process. See :class:`parse_string` for more - information on parsing strings containing ```` s, and suggested - methods to maintain a consistent view of the parsed string, the parse - location, and line and column positions within the parsed string. - - Example:: - - # parse dates in the form YYYY/MM/DD - - # use parse action to convert toks from str to int at parse time - def convert_to_int(toks): - return int(toks[0]) - - # use a parse action to verify that the date is a valid date - def is_valid_date(instring, loc, toks): - from datetime import date - year, month, day = toks[::2] - try: - date(year, month, day) - except ValueError: - raise ParseException(instring, loc, "invalid date given") - - integer = Word(nums) - date_str = integer + '/' + integer + '/' + integer - - # add parse actions - integer.set_parse_action(convert_to_int) - date_str.set_parse_action(is_valid_date) - - # note that integer fields are now ints, not strings - date_str.run_tests(''' - # successful parse - note that integer fields were converted to ints - 1999/12/31 - - # fail - invalid date - 1999/13/31 - ''') - """ - if list(fns) == [None]: - self.parseAction = [] - else: - if not all(callable(fn) for fn in fns): - raise TypeError("parse actions must be callable") - self.parseAction = [_trim_arity(fn) for fn in fns] - self.callDuringTry = kwargs.get( - "call_during_try", kwargs.get("callDuringTry", False) - ) - return self - - def add_parse_action(self, *fns: ParseAction, **kwargs) -> "ParserElement": - """ - Add one or more parse actions to expression's list of parse actions. See :class:`set_parse_action`. - - See examples in :class:`copy`. - """ - self.parseAction += [_trim_arity(fn) for fn in fns] - self.callDuringTry = self.callDuringTry or kwargs.get( - "call_during_try", kwargs.get("callDuringTry", False) - ) - return self - - def add_condition(self, *fns: ParseCondition, **kwargs) -> "ParserElement": - """Add a boolean predicate function to expression's list of parse actions. See - :class:`set_parse_action` for function call signatures. Unlike ``set_parse_action``, - functions passed to ``add_condition`` need to return boolean success/fail of the condition. - - Optional keyword arguments: - - - ``message`` = define a custom message to be used in the raised exception - - ``fatal`` = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise - ParseException - - ``call_during_try`` = boolean to indicate if this method should be called during internal tryParse calls, - default=False - - Example:: - - integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) - year_int = integer.copy() - year_int.add_condition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later") - date_str = year_int + '/' + integer + '/' + integer - - result = date_str.parse_string("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), - (line:1, col:1) - """ - for fn in fns: - self.parseAction.append( - condition_as_parse_action( - fn, - message=str(kwargs.get("message")), - fatal=bool(kwargs.get("fatal", False)), - ) - ) - - self.callDuringTry = self.callDuringTry or kwargs.get( - "call_during_try", kwargs.get("callDuringTry", False) - ) - return self - - def set_fail_action(self, fn: ParseFailAction) -> "ParserElement": - """ - Define action to perform if parsing fails at this expression. - Fail acton fn is a callable function that takes the arguments - ``fn(s, loc, expr, err)`` where: - - - ``s`` = string being parsed - - ``loc`` = location where expression match was attempted and failed - - ``expr`` = the parse expression that failed - - ``err`` = the exception thrown - - The function returns no value. It may throw :class:`ParseFatalException` - if it is desired to stop parsing immediately.""" - self.failAction = fn - return self - - def _skipIgnorables(self, instring: str, loc: int) -> int: - if not self.ignoreExprs: - return loc - exprsFound = True - ignore_expr_fns = [e._parse for e in self.ignoreExprs] - while exprsFound: - exprsFound = False - for ignore_fn in ignore_expr_fns: - try: - while 1: - loc, dummy = ignore_fn(instring, loc) - exprsFound = True - except ParseException: - pass - return loc - - def preParse(self, instring: str, loc: int) -> int: - if self.ignoreExprs: - loc = self._skipIgnorables(instring, loc) - - if self.skipWhitespace: - instrlen = len(instring) - white_chars = self.whiteChars - while loc < instrlen and instring[loc] in white_chars: - loc += 1 - - return loc - - def parseImpl(self, instring, loc, doActions=True): - return loc, [] - - def postParse(self, instring, loc, tokenlist): - return tokenlist - - # @profile - def _parseNoCache( - self, instring, loc, doActions=True, callPreParse=True - ) -> Tuple[int, ParseResults]: - TRY, MATCH, FAIL = 0, 1, 2 - debugging = self.debug # and doActions) - len_instring = len(instring) - - if debugging or self.failAction: - # print("Match {} at loc {}({}, {})".format(self, loc, lineno(loc, instring), col(loc, instring))) - try: - if callPreParse and self.callPreparse: - pre_loc = self.preParse(instring, loc) - else: - pre_loc = loc - tokens_start = pre_loc - if self.debugActions.debug_try: - self.debugActions.debug_try(instring, tokens_start, self, False) - if self.mayIndexError or pre_loc >= len_instring: - try: - loc, tokens = self.parseImpl(instring, pre_loc, doActions) - except IndexError: - raise ParseException(instring, len_instring, self.errmsg, self) - else: - loc, tokens = self.parseImpl(instring, pre_loc, doActions) - except Exception as err: - # print("Exception raised:", err) - if self.debugActions.debug_fail: - self.debugActions.debug_fail( - instring, tokens_start, self, err, False - ) - if self.failAction: - self.failAction(instring, tokens_start, self, err) - raise - else: - if callPreParse and self.callPreparse: - pre_loc = self.preParse(instring, loc) - else: - pre_loc = loc - tokens_start = pre_loc - if self.mayIndexError or pre_loc >= len_instring: - try: - loc, tokens = self.parseImpl(instring, pre_loc, doActions) - except IndexError: - raise ParseException(instring, len_instring, self.errmsg, self) - else: - loc, tokens = self.parseImpl(instring, pre_loc, doActions) - - tokens = self.postParse(instring, loc, tokens) - - ret_tokens = ParseResults( - tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults - ) - if self.parseAction and (doActions or self.callDuringTry): - if debugging: - try: - for fn in self.parseAction: - try: - tokens = fn(instring, tokens_start, ret_tokens) # type: ignore [call-arg, arg-type] - except IndexError as parse_action_exc: - exc = ParseException("exception raised in parse action") - raise exc from parse_action_exc - - if tokens is not None and tokens is not ret_tokens: - ret_tokens = ParseResults( - tokens, - self.resultsName, - asList=self.saveAsList - and isinstance(tokens, (ParseResults, list)), - modal=self.modalResults, - ) - except Exception as err: - # print "Exception raised in user parse action:", err - if self.debugActions.debug_fail: - self.debugActions.debug_fail( - instring, tokens_start, self, err, False - ) - raise - else: - for fn in self.parseAction: - try: - tokens = fn(instring, tokens_start, ret_tokens) # type: ignore [call-arg, arg-type] - except IndexError as parse_action_exc: - exc = ParseException("exception raised in parse action") - raise exc from parse_action_exc - - if tokens is not None and tokens is not ret_tokens: - ret_tokens = ParseResults( - tokens, - self.resultsName, - asList=self.saveAsList - and isinstance(tokens, (ParseResults, list)), - modal=self.modalResults, - ) - if debugging: - # print("Matched", self, "->", ret_tokens.as_list()) - if self.debugActions.debug_match: - self.debugActions.debug_match( - instring, tokens_start, loc, self, ret_tokens, False - ) - - return loc, ret_tokens - - def try_parse( - self, - instring: str, - loc: int, - *, - raise_fatal: bool = False, - do_actions: bool = False, - ) -> int: - try: - return self._parse(instring, loc, doActions=do_actions)[0] - except ParseFatalException: - if raise_fatal: - raise - raise ParseException(instring, loc, self.errmsg, self) - - def can_parse_next(self, instring: str, loc: int, do_actions: bool = False) -> bool: - try: - self.try_parse(instring, loc, do_actions=do_actions) - except (ParseException, IndexError): - return False - else: - return True - - # cache for left-recursion in Forward references - recursion_lock = RLock() - recursion_memos: typing.Dict[ - Tuple[int, "Forward", bool], Tuple[int, Union[ParseResults, Exception]] - ] = {} - - class _CacheType(dict): - """ - class to help type checking - """ - - not_in_cache: bool - - def get(self, *args): - ... - - def set(self, *args): - ... - - # argument cache for optimizing repeated calls when backtracking through recursive expressions - packrat_cache = ( - _CacheType() - ) # set later by enable_packrat(); this is here so that reset_cache() doesn't fail - packrat_cache_lock = RLock() - packrat_cache_stats = [0, 0] - - # this method gets repeatedly called during backtracking with the same arguments - - # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression - def _parseCache( - self, instring, loc, doActions=True, callPreParse=True - ) -> Tuple[int, ParseResults]: - HIT, MISS = 0, 1 - TRY, MATCH, FAIL = 0, 1, 2 - lookup = (self, instring, loc, callPreParse, doActions) - with ParserElement.packrat_cache_lock: - cache = ParserElement.packrat_cache - value = cache.get(lookup) - if value is cache.not_in_cache: - ParserElement.packrat_cache_stats[MISS] += 1 - try: - value = self._parseNoCache(instring, loc, doActions, callPreParse) - except ParseBaseException as pe: - # cache a copy of the exception, without the traceback - cache.set(lookup, pe.__class__(*pe.args)) - raise - else: - cache.set(lookup, (value[0], value[1].copy(), loc)) - return value - else: - ParserElement.packrat_cache_stats[HIT] += 1 - if self.debug and self.debugActions.debug_try: - try: - self.debugActions.debug_try(instring, loc, self, cache_hit=True) # type: ignore [call-arg] - except TypeError: - pass - if isinstance(value, Exception): - if self.debug and self.debugActions.debug_fail: - try: - self.debugActions.debug_fail( - instring, loc, self, value, cache_hit=True # type: ignore [call-arg] - ) - except TypeError: - pass - raise value - - value = cast(Tuple[int, ParseResults, int], value) - loc_, result, endloc = value[0], value[1].copy(), value[2] - if self.debug and self.debugActions.debug_match: - try: - self.debugActions.debug_match( - instring, loc_, endloc, self, result, cache_hit=True # type: ignore [call-arg] - ) - except TypeError: - pass - - return loc_, result - - _parse = _parseNoCache - - @staticmethod - def reset_cache() -> None: - ParserElement.packrat_cache.clear() - ParserElement.packrat_cache_stats[:] = [0] * len( - ParserElement.packrat_cache_stats - ) - ParserElement.recursion_memos.clear() - - _packratEnabled = False - _left_recursion_enabled = False - - @staticmethod - def disable_memoization() -> None: - """ - Disables active Packrat or Left Recursion parsing and their memoization - - This method also works if neither Packrat nor Left Recursion are enabled. - This makes it safe to call before activating Packrat nor Left Recursion - to clear any previous settings. - """ - ParserElement.reset_cache() - ParserElement._left_recursion_enabled = False - ParserElement._packratEnabled = False - ParserElement._parse = ParserElement._parseNoCache - - @staticmethod - def enable_left_recursion( - cache_size_limit: typing.Optional[int] = None, *, force=False - ) -> None: - """ - Enables "bounded recursion" parsing, which allows for both direct and indirect - left-recursion. During parsing, left-recursive :class:`Forward` elements are - repeatedly matched with a fixed recursion depth that is gradually increased - until finding the longest match. - - Example:: - - from pip._vendor import pyparsing as pp - pp.ParserElement.enable_left_recursion() - - E = pp.Forward("E") - num = pp.Word(pp.nums) - # match `num`, or `num '+' num`, or `num '+' num '+' num`, ... - E <<= E + '+' - num | num - - print(E.parse_string("1+2+3")) - - Recursion search naturally memoizes matches of ``Forward`` elements and may - thus skip reevaluation of parse actions during backtracking. This may break - programs with parse actions which rely on strict ordering of side-effects. - - Parameters: - - - ``cache_size_limit`` - (default=``None``) - memoize at most this many - ``Forward`` elements during matching; if ``None`` (the default), - memoize all ``Forward`` elements. - - Bounded Recursion parsing works similar but not identical to Packrat parsing, - thus the two cannot be used together. Use ``force=True`` to disable any - previous, conflicting settings. - """ - if force: - ParserElement.disable_memoization() - elif ParserElement._packratEnabled: - raise RuntimeError("Packrat and Bounded Recursion are not compatible") - if cache_size_limit is None: - ParserElement.recursion_memos = _UnboundedMemo() # type: ignore[assignment] - elif cache_size_limit > 0: - ParserElement.recursion_memos = _LRUMemo(capacity=cache_size_limit) # type: ignore[assignment] - else: - raise NotImplementedError("Memo size of %s" % cache_size_limit) - ParserElement._left_recursion_enabled = True - - @staticmethod - def enable_packrat(cache_size_limit: int = 128, *, force: bool = False) -> None: - """ - Enables "packrat" parsing, which adds memoizing to the parsing logic. - Repeated parse attempts at the same string location (which happens - often in many complex grammars) can immediately return a cached value, - instead of re-executing parsing/validating code. Memoizing is done of - both valid results and parsing exceptions. - - Parameters: - - - ``cache_size_limit`` - (default= ``128``) - if an integer value is provided - will limit the size of the packrat cache; if None is passed, then - the cache size will be unbounded; if 0 is passed, the cache will - be effectively disabled. - - This speedup may break existing programs that use parse actions that - have side-effects. For this reason, packrat parsing is disabled when - you first import pyparsing. To activate the packrat feature, your - program must call the class method :class:`ParserElement.enable_packrat`. - For best results, call ``enable_packrat()`` immediately after - importing pyparsing. - - Example:: - - from pip._vendor import pyparsing - pyparsing.ParserElement.enable_packrat() - - Packrat parsing works similar but not identical to Bounded Recursion parsing, - thus the two cannot be used together. Use ``force=True`` to disable any - previous, conflicting settings. - """ - if force: - ParserElement.disable_memoization() - elif ParserElement._left_recursion_enabled: - raise RuntimeError("Packrat and Bounded Recursion are not compatible") - if not ParserElement._packratEnabled: - ParserElement._packratEnabled = True - if cache_size_limit is None: - ParserElement.packrat_cache = _UnboundedCache() - else: - ParserElement.packrat_cache = _FifoCache(cache_size_limit) # type: ignore[assignment] - ParserElement._parse = ParserElement._parseCache - - def parse_string( - self, instring: str, parse_all: bool = False, *, parseAll: bool = False - ) -> ParseResults: - """ - Parse a string with respect to the parser definition. This function is intended as the primary interface to the - client code. - - :param instring: The input string to be parsed. - :param parse_all: If set, the entire input string must match the grammar. - :param parseAll: retained for pre-PEP8 compatibility, will be removed in a future release. - :raises ParseException: Raised if ``parse_all`` is set and the input string does not match the whole grammar. - :returns: the parsed data as a :class:`ParseResults` object, which may be accessed as a `list`, a `dict`, or - an object with attributes if the given parser includes results names. - - If the input string is required to match the entire grammar, ``parse_all`` flag must be set to ``True``. This - is also equivalent to ending the grammar with :class:`StringEnd`\\ (). - - To report proper column numbers, ``parse_string`` operates on a copy of the input string where all tabs are - converted to spaces (8 spaces per tab, as per the default in ``string.expandtabs``). If the input string - contains tabs and the grammar uses parse actions that use the ``loc`` argument to index into the string - being parsed, one can ensure a consistent view of the input string by doing one of the following: - - - calling ``parse_with_tabs`` on your grammar before calling ``parse_string`` (see :class:`parse_with_tabs`), - - define your parse action using the full ``(s,loc,toks)`` signature, and reference the input string using the - parse action's ``s`` argument, or - - explicitly expand the tabs in your input string before calling ``parse_string``. - - Examples: - - By default, partial matches are OK. - - >>> res = Word('a').parse_string('aaaaabaaa') - >>> print(res) - ['aaaaa'] - - The parsing behavior varies by the inheriting class of this abstract class. Please refer to the children - directly to see more examples. - - It raises an exception if parse_all flag is set and instring does not match the whole grammar. - - >>> res = Word('a').parse_string('aaaaabaaa', parse_all=True) - Traceback (most recent call last): - ... - pyparsing.ParseException: Expected end of text, found 'b' (at char 5), (line:1, col:6) - """ - parseAll = parse_all or parseAll - - ParserElement.reset_cache() - if not self.streamlined: - self.streamline() - for e in self.ignoreExprs: - e.streamline() - if not self.keepTabs: - instring = instring.expandtabs() - try: - loc, tokens = self._parse(instring, 0) - if parseAll: - loc = self.preParse(instring, loc) - se = Empty() + StringEnd() - se._parse(instring, loc) - except ParseBaseException as exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clearing out pyparsing internal stack trace - raise exc.with_traceback(None) - else: - return tokens - - def scan_string( - self, - instring: str, - max_matches: int = _MAX_INT, - overlap: bool = False, - *, - debug: bool = False, - maxMatches: int = _MAX_INT, - ) -> Generator[Tuple[ParseResults, int, int], None, None]: - """ - Scan the input string for expression matches. Each match will return the - matching tokens, start location, and end location. May be called with optional - ``max_matches`` argument, to clip scanning after 'n' matches are found. If - ``overlap`` is specified, then overlapping matches will be reported. - - Note that the start and end locations are reported relative to the string - being parsed. See :class:`parse_string` for more information on parsing - strings with embedded tabs. - - Example:: - - source = "sldjf123lsdjjkf345sldkjf879lkjsfd987" - print(source) - for tokens, start, end in Word(alphas).scan_string(source): - print(' '*start + '^'*(end-start)) - print(' '*start + tokens[0]) - - prints:: - - sldjf123lsdjjkf345sldkjf879lkjsfd987 - ^^^^^ - sldjf - ^^^^^^^ - lsdjjkf - ^^^^^^ - sldkjf - ^^^^^^ - lkjsfd - """ - maxMatches = min(maxMatches, max_matches) - if not self.streamlined: - self.streamline() - for e in self.ignoreExprs: - e.streamline() - - if not self.keepTabs: - instring = str(instring).expandtabs() - instrlen = len(instring) - loc = 0 - preparseFn = self.preParse - parseFn = self._parse - ParserElement.resetCache() - matches = 0 - try: - while loc <= instrlen and matches < maxMatches: - try: - preloc: int = preparseFn(instring, loc) - nextLoc: int - tokens: ParseResults - nextLoc, tokens = parseFn(instring, preloc, callPreParse=False) - except ParseException: - loc = preloc + 1 - else: - if nextLoc > loc: - matches += 1 - if debug: - print( - { - "tokens": tokens.asList(), - "start": preloc, - "end": nextLoc, - } - ) - yield tokens, preloc, nextLoc - if overlap: - nextloc = preparseFn(instring, loc) - if nextloc > loc: - loc = nextLoc - else: - loc += 1 - else: - loc = nextLoc - else: - loc = preloc + 1 - except ParseBaseException as exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc.with_traceback(None) - - def transform_string(self, instring: str, *, debug: bool = False) -> str: - """ - Extension to :class:`scan_string`, to modify matching text with modified tokens that may - be returned from a parse action. To use ``transform_string``, define a grammar and - attach a parse action to it that modifies the returned token list. - Invoking ``transform_string()`` on a target string will then scan for matches, - and replace the matched text patterns according to the logic in the parse - action. ``transform_string()`` returns the resulting transformed string. - - Example:: - - wd = Word(alphas) - wd.set_parse_action(lambda toks: toks[0].title()) - - print(wd.transform_string("now is the winter of our discontent made glorious summer by this sun of york.")) - - prints:: - - Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York. - """ - out: List[str] = [] - lastE = 0 - # force preservation of s, to minimize unwanted transformation of string, and to - # keep string locs straight between transform_string and scan_string - self.keepTabs = True - try: - for t, s, e in self.scan_string(instring, debug=debug): - out.append(instring[lastE:s]) - if t: - if isinstance(t, ParseResults): - out += t.as_list() - elif isinstance(t, Iterable) and not isinstance(t, str_type): - out.extend(t) - else: - out.append(t) - lastE = e - out.append(instring[lastE:]) - out = [o for o in out if o] - return "".join([str(s) for s in _flatten(out)]) - except ParseBaseException as exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc.with_traceback(None) - - def search_string( - self, - instring: str, - max_matches: int = _MAX_INT, - *, - debug: bool = False, - maxMatches: int = _MAX_INT, - ) -> ParseResults: - """ - Another extension to :class:`scan_string`, simplifying the access to the tokens found - to match the given parse expression. May be called with optional - ``max_matches`` argument, to clip searching after 'n' matches are found. - - Example:: - - # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters - cap_word = Word(alphas.upper(), alphas.lower()) - - print(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity")) - - # the sum() builtin can be used to merge results into a single ParseResults object - print(sum(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity"))) - - prints:: - - [['More'], ['Iron'], ['Lead'], ['Gold'], ['I'], ['Electricity']] - ['More', 'Iron', 'Lead', 'Gold', 'I', 'Electricity'] - """ - maxMatches = min(maxMatches, max_matches) - try: - return ParseResults( - [t for t, s, e in self.scan_string(instring, maxMatches, debug=debug)] - ) - except ParseBaseException as exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc.with_traceback(None) - - def split( - self, - instring: str, - maxsplit: int = _MAX_INT, - include_separators: bool = False, - *, - includeSeparators=False, - ) -> Generator[str, None, None]: - """ - Generator method to split a string using the given expression as a separator. - May be called with optional ``maxsplit`` argument, to limit the number of splits; - and the optional ``include_separators`` argument (default= ``False``), if the separating - matching text should be included in the split results. - - Example:: - - punc = one_of(list(".,;:/-!?")) - print(list(punc.split("This, this?, this sentence, is badly punctuated!"))) - - prints:: - - ['This', ' this', '', ' this sentence', ' is badly punctuated', ''] - """ - includeSeparators = includeSeparators or include_separators - last = 0 - for t, s, e in self.scan_string(instring, max_matches=maxsplit): - yield instring[last:s] - if includeSeparators: - yield t[0] - last = e - yield instring[last:] - - def __add__(self, other) -> "ParserElement": - """ - Implementation of ``+`` operator - returns :class:`And`. Adding strings to a :class:`ParserElement` - converts them to :class:`Literal`\\ s by default. - - Example:: - - greet = Word(alphas) + "," + Word(alphas) + "!" - hello = "Hello, World!" - print(hello, "->", greet.parse_string(hello)) - - prints:: - - Hello, World! -> ['Hello', ',', 'World', '!'] - - ``...`` may be used as a parse expression as a short form of :class:`SkipTo`:: - - Literal('start') + ... + Literal('end') - - is equivalent to:: - - Literal('start') + SkipTo('end')("_skipped*") + Literal('end') - - Note that the skipped text is returned with '_skipped' as a results name, - and to support having multiple skips in the same parser, the value returned is - a list of all skipped text. - """ - if other is Ellipsis: - return _PendingSkip(self) - - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return And([self, other]) - - def __radd__(self, other) -> "ParserElement": - """ - Implementation of ``+`` operator when left operand is not a :class:`ParserElement` - """ - if other is Ellipsis: - return SkipTo(self)("_skipped*") + self - - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return other + self - - def __sub__(self, other) -> "ParserElement": - """ - Implementation of ``-`` operator, returns :class:`And` with error stop - """ - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return self + And._ErrorStop() + other - - def __rsub__(self, other) -> "ParserElement": - """ - Implementation of ``-`` operator when left operand is not a :class:`ParserElement` - """ - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return other - self - - def __mul__(self, other) -> "ParserElement": - """ - Implementation of ``*`` operator, allows use of ``expr * 3`` in place of - ``expr + expr + expr``. Expressions may also be multiplied by a 2-integer - tuple, similar to ``{min, max}`` multipliers in regular expressions. Tuples - may also include ``None`` as in: - - - ``expr*(n, None)`` or ``expr*(n, )`` is equivalent - to ``expr*n + ZeroOrMore(expr)`` - (read as "at least n instances of ``expr``") - - ``expr*(None, n)`` is equivalent to ``expr*(0, n)`` - (read as "0 to n instances of ``expr``") - - ``expr*(None, None)`` is equivalent to ``ZeroOrMore(expr)`` - - ``expr*(1, None)`` is equivalent to ``OneOrMore(expr)`` - - Note that ``expr*(None, n)`` does not raise an exception if - more than n exprs exist in the input stream; that is, - ``expr*(None, n)`` does not enforce a maximum number of expr - occurrences. If this behavior is desired, then write - ``expr*(None, n) + ~expr`` - """ - if other is Ellipsis: - other = (0, None) - elif isinstance(other, tuple) and other[:1] == (Ellipsis,): - other = ((0,) + other[1:] + (None,))[:2] - - if isinstance(other, int): - minElements, optElements = other, 0 - elif isinstance(other, tuple): - other = tuple(o if o is not Ellipsis else None for o in other) - other = (other + (None, None))[:2] - if other[0] is None: - other = (0, other[1]) - if isinstance(other[0], int) and other[1] is None: - if other[0] == 0: - return ZeroOrMore(self) - if other[0] == 1: - return OneOrMore(self) - else: - return self * other[0] + ZeroOrMore(self) - elif isinstance(other[0], int) and isinstance(other[1], int): - minElements, optElements = other - optElements -= minElements - else: - return NotImplemented - else: - return NotImplemented - - if minElements < 0: - raise ValueError("cannot multiply ParserElement by negative value") - if optElements < 0: - raise ValueError( - "second tuple value must be greater or equal to first tuple value" - ) - if minElements == optElements == 0: - return And([]) - - if optElements: - - def makeOptionalList(n): - if n > 1: - return Opt(self + makeOptionalList(n - 1)) - else: - return Opt(self) - - if minElements: - if minElements == 1: - ret = self + makeOptionalList(optElements) - else: - ret = And([self] * minElements) + makeOptionalList(optElements) - else: - ret = makeOptionalList(optElements) - else: - if minElements == 1: - ret = self - else: - ret = And([self] * minElements) - return ret - - def __rmul__(self, other) -> "ParserElement": - return self.__mul__(other) - - def __or__(self, other) -> "ParserElement": - """ - Implementation of ``|`` operator - returns :class:`MatchFirst` - """ - if other is Ellipsis: - return _PendingSkip(self, must_skip=True) - - if isinstance(other, str_type): - # `expr | ""` is equivalent to `Opt(expr)` - if other == "": - return Opt(self) - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return MatchFirst([self, other]) - - def __ror__(self, other) -> "ParserElement": - """ - Implementation of ``|`` operator when left operand is not a :class:`ParserElement` - """ - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return other | self - - def __xor__(self, other) -> "ParserElement": - """ - Implementation of ``^`` operator - returns :class:`Or` - """ - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return Or([self, other]) - - def __rxor__(self, other) -> "ParserElement": - """ - Implementation of ``^`` operator when left operand is not a :class:`ParserElement` - """ - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return other ^ self - - def __and__(self, other) -> "ParserElement": - """ - Implementation of ``&`` operator - returns :class:`Each` - """ - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return Each([self, other]) - - def __rand__(self, other) -> "ParserElement": - """ - Implementation of ``&`` operator when left operand is not a :class:`ParserElement` - """ - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return other & self - - def __invert__(self) -> "ParserElement": - """ - Implementation of ``~`` operator - returns :class:`NotAny` - """ - return NotAny(self) - - # disable __iter__ to override legacy use of sequential access to __getitem__ to - # iterate over a sequence - __iter__ = None - - def __getitem__(self, key): - """ - use ``[]`` indexing notation as a short form for expression repetition: - - - ``expr[n]`` is equivalent to ``expr*n`` - - ``expr[m, n]`` is equivalent to ``expr*(m, n)`` - - ``expr[n, ...]`` or ``expr[n,]`` is equivalent - to ``expr*n + ZeroOrMore(expr)`` - (read as "at least n instances of ``expr``") - - ``expr[..., n]`` is equivalent to ``expr*(0, n)`` - (read as "0 to n instances of ``expr``") - - ``expr[...]`` and ``expr[0, ...]`` are equivalent to ``ZeroOrMore(expr)`` - - ``expr[1, ...]`` is equivalent to ``OneOrMore(expr)`` - - ``None`` may be used in place of ``...``. - - Note that ``expr[..., n]`` and ``expr[m, n]`` do not raise an exception - if more than ``n`` ``expr``\\ s exist in the input stream. If this behavior is - desired, then write ``expr[..., n] + ~expr``. - - For repetition with a stop_on expression, use slice notation: - - - ``expr[...: end_expr]`` and ``expr[0, ...: end_expr]`` are equivalent to ``ZeroOrMore(expr, stop_on=end_expr)`` - - ``expr[1, ...: end_expr]`` is equivalent to ``OneOrMore(expr, stop_on=end_expr)`` - - """ - - stop_on_defined = False - stop_on = NoMatch() - if isinstance(key, slice): - key, stop_on = key.start, key.stop - if key is None: - key = ... - stop_on_defined = True - elif isinstance(key, tuple) and isinstance(key[-1], slice): - key, stop_on = (key[0], key[1].start), key[1].stop - stop_on_defined = True - - # convert single arg keys to tuples - if isinstance(key, str_type): - key = (key,) - try: - iter(key) - except TypeError: - key = (key, key) - - if len(key) > 2: - raise TypeError( - f"only 1 or 2 index arguments supported ({key[:5]}{f'... [{len(key)}]' if len(key) > 5 else ''})" - ) - - # clip to 2 elements - ret = self * tuple(key[:2]) - ret = typing.cast(_MultipleMatch, ret) - - if stop_on_defined: - ret.stopOn(stop_on) - - return ret - - def __call__(self, name: typing.Optional[str] = None) -> "ParserElement": - """ - Shortcut for :class:`set_results_name`, with ``list_all_matches=False``. - - If ``name`` is given with a trailing ``'*'`` character, then ``list_all_matches`` will be - passed as ``True``. - - If ``name`` is omitted, same as calling :class:`copy`. - - Example:: - - # these are equivalent - userdata = Word(alphas).set_results_name("name") + Word(nums + "-").set_results_name("socsecno") - userdata = Word(alphas)("name") + Word(nums + "-")("socsecno") - """ - if name is not None: - return self._setResultsName(name) - else: - return self.copy() - - def suppress(self) -> "ParserElement": - """ - Suppresses the output of this :class:`ParserElement`; useful to keep punctuation from - cluttering up returned output. - """ - return Suppress(self) - - def ignore_whitespace(self, recursive: bool = True) -> "ParserElement": - """ - Enables the skipping of whitespace before matching the characters in the - :class:`ParserElement`'s defined pattern. - - :param recursive: If ``True`` (the default), also enable whitespace skipping in child elements (if any) - """ - self.skipWhitespace = True - return self - - def leave_whitespace(self, recursive: bool = True) -> "ParserElement": - """ - Disables the skipping of whitespace before matching the characters in the - :class:`ParserElement`'s defined pattern. This is normally only used internally by - the pyparsing module, but may be needed in some whitespace-sensitive grammars. - - :param recursive: If true (the default), also disable whitespace skipping in child elements (if any) - """ - self.skipWhitespace = False - return self - - def set_whitespace_chars( - self, chars: Union[Set[str], str], copy_defaults: bool = False - ) -> "ParserElement": - """ - Overrides the default whitespace chars - """ - self.skipWhitespace = True - self.whiteChars = set(chars) - self.copyDefaultWhiteChars = copy_defaults - return self - - def parse_with_tabs(self) -> "ParserElement": - """ - Overrides default behavior to expand ```` s to spaces before parsing the input string. - Must be called before ``parse_string`` when the input grammar contains elements that - match ```` characters. - """ - self.keepTabs = True - return self - - def ignore(self, other: "ParserElement") -> "ParserElement": - """ - Define expression to be ignored (e.g., comments) while doing pattern - matching; may be called repeatedly, to define multiple comment or other - ignorable patterns. - - Example:: - - patt = Word(alphas)[1, ...] - patt.parse_string('ablaj /* comment */ lskjd') - # -> ['ablaj'] - - patt.ignore(c_style_comment) - patt.parse_string('ablaj /* comment */ lskjd') - # -> ['ablaj', 'lskjd'] - """ - import typing - - if isinstance(other, str_type): - other = Suppress(other) - - if isinstance(other, Suppress): - if other not in self.ignoreExprs: - self.ignoreExprs.append(other) - else: - self.ignoreExprs.append(Suppress(other.copy())) - return self - - def set_debug_actions( - self, - start_action: DebugStartAction, - success_action: DebugSuccessAction, - exception_action: DebugExceptionAction, - ) -> "ParserElement": - """ - Customize display of debugging messages while doing pattern matching: - - - ``start_action`` - method to be called when an expression is about to be parsed; - should have the signature ``fn(input_string: str, location: int, expression: ParserElement, cache_hit: bool)`` - - - ``success_action`` - method to be called when an expression has successfully parsed; - should have the signature ``fn(input_string: str, start_location: int, end_location: int, expression: ParserELement, parsed_tokens: ParseResults, cache_hit: bool)`` - - - ``exception_action`` - method to be called when expression fails to parse; - should have the signature ``fn(input_string: str, location: int, expression: ParserElement, exception: Exception, cache_hit: bool)`` - """ - self.debugActions = self.DebugActions( - start_action or _default_start_debug_action, # type: ignore[truthy-function] - success_action or _default_success_debug_action, # type: ignore[truthy-function] - exception_action or _default_exception_debug_action, # type: ignore[truthy-function] - ) - self.debug = True - return self - - def set_debug(self, flag: bool = True, recurse: bool = False) -> "ParserElement": - """ - Enable display of debugging messages while doing pattern matching. - Set ``flag`` to ``True`` to enable, ``False`` to disable. - Set ``recurse`` to ``True`` to set the debug flag on this expression and all sub-expressions. - - Example:: - - wd = Word(alphas).set_name("alphaword") - integer = Word(nums).set_name("numword") - term = wd | integer - - # turn on debugging for wd - wd.set_debug() - - term[1, ...].parse_string("abc 123 xyz 890") - - prints:: - - Match alphaword at loc 0(1,1) - Matched alphaword -> ['abc'] - Match alphaword at loc 3(1,4) - Exception raised:Expected alphaword (at char 4), (line:1, col:5) - Match alphaword at loc 7(1,8) - Matched alphaword -> ['xyz'] - Match alphaword at loc 11(1,12) - Exception raised:Expected alphaword (at char 12), (line:1, col:13) - Match alphaword at loc 15(1,16) - Exception raised:Expected alphaword (at char 15), (line:1, col:16) - - The output shown is that produced by the default debug actions - custom debug actions can be - specified using :class:`set_debug_actions`. Prior to attempting - to match the ``wd`` expression, the debugging message ``"Match at loc (,)"`` - is shown. Then if the parse succeeds, a ``"Matched"`` message is shown, or an ``"Exception raised"`` - message is shown. Also note the use of :class:`set_name` to assign a human-readable name to the expression, - which makes debugging and exception messages easier to understand - for instance, the default - name created for the :class:`Word` expression without calling ``set_name`` is ``"W:(A-Za-z)"``. - """ - if recurse: - for expr in self.visit_all(): - expr.set_debug(flag, recurse=False) - return self - - if flag: - self.set_debug_actions( - _default_start_debug_action, - _default_success_debug_action, - _default_exception_debug_action, - ) - else: - self.debug = False - return self - - @property - def default_name(self) -> str: - if self._defaultName is None: - self._defaultName = self._generateDefaultName() - return self._defaultName - - @abstractmethod - def _generateDefaultName(self) -> str: - """ - Child classes must define this method, which defines how the ``default_name`` is set. - """ - - def set_name(self, name: str) -> "ParserElement": - """ - Define name for this expression, makes debugging and exception messages clearer. - - Example:: - - Word(nums).parse_string("ABC") # -> Exception: Expected W:(0-9) (at char 0), (line:1, col:1) - Word(nums).set_name("integer").parse_string("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1) - """ - self.customName = name - self.errmsg = "Expected " + self.name - if __diag__.enable_debug_on_named_expressions: - self.set_debug() - return self - - @property - def name(self) -> str: - # This will use a user-defined name if available, but otherwise defaults back to the auto-generated name - return self.customName if self.customName is not None else self.default_name - - def __str__(self) -> str: - return self.name - - def __repr__(self) -> str: - return str(self) - - def streamline(self) -> "ParserElement": - self.streamlined = True - self._defaultName = None - return self - - def recurse(self) -> List["ParserElement"]: - return [] - - def _checkRecursion(self, parseElementList): - subRecCheckList = parseElementList[:] + [self] - for e in self.recurse(): - e._checkRecursion(subRecCheckList) - - def validate(self, validateTrace=None) -> None: - """ - Check defined expressions for valid structure, check for infinite recursive definitions. - """ - warnings.warn( - "ParserElement.validate() is deprecated, and should not be used to check for left recursion", - DeprecationWarning, - stacklevel=2, - ) - self._checkRecursion([]) - - def parse_file( - self, - file_or_filename: Union[str, Path, TextIO], - encoding: str = "utf-8", - parse_all: bool = False, - *, - parseAll: bool = False, - ) -> ParseResults: - """ - Execute the parse expression on the given file or filename. - If a filename is specified (instead of a file object), - the entire file is opened, read, and closed before parsing. - """ - parseAll = parseAll or parse_all - try: - file_or_filename = typing.cast(TextIO, file_or_filename) - file_contents = file_or_filename.read() - except AttributeError: - file_or_filename = typing.cast(str, file_or_filename) - with open(file_or_filename, "r", encoding=encoding) as f: - file_contents = f.read() - try: - return self.parse_string(file_contents, parseAll) - except ParseBaseException as exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc.with_traceback(None) - - def __eq__(self, other): - if self is other: - return True - elif isinstance(other, str_type): - return self.matches(other, parse_all=True) - elif isinstance(other, ParserElement): - return vars(self) == vars(other) - return False - - def __hash__(self): - return id(self) - - def matches( - self, test_string: str, parse_all: bool = True, *, parseAll: bool = True - ) -> bool: - """ - Method for quick testing of a parser against a test string. Good for simple - inline microtests of sub expressions while building up larger parser. - - Parameters: - - - ``test_string`` - to test against this expression for a match - - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests - - Example:: - - expr = Word(nums) - assert expr.matches("100") - """ - parseAll = parseAll and parse_all - try: - self.parse_string(str(test_string), parse_all=parseAll) - return True - except ParseBaseException: - return False - - def run_tests( - self, - tests: Union[str, List[str]], - parse_all: bool = True, - comment: typing.Optional[Union["ParserElement", str]] = "#", - full_dump: bool = True, - print_results: bool = True, - failure_tests: bool = False, - post_parse: typing.Optional[Callable[[str, ParseResults], str]] = None, - file: typing.Optional[TextIO] = None, - with_line_numbers: bool = False, - *, - parseAll: bool = True, - fullDump: bool = True, - printResults: bool = True, - failureTests: bool = False, - postParse: typing.Optional[Callable[[str, ParseResults], str]] = None, - ) -> Tuple[bool, List[Tuple[str, Union[ParseResults, Exception]]]]: - """ - Execute the parse expression on a series of test strings, showing each - test, the parsed results or where the parse failed. Quick and easy way to - run a parse expression against a list of sample strings. - - Parameters: - - - ``tests`` - a list of separate test strings, or a multiline string of test strings - - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests - - ``comment`` - (default= ``'#'``) - expression for indicating embedded comments in the test - string; pass None to disable comment filtering - - ``full_dump`` - (default= ``True``) - dump results as list followed by results names in nested outline; - if False, only dump nested list - - ``print_results`` - (default= ``True``) prints test output to stdout - - ``failure_tests`` - (default= ``False``) indicates if these tests are expected to fail parsing - - ``post_parse`` - (default= ``None``) optional callback for successful parse results; called as - `fn(test_string, parse_results)` and returns a string to be added to the test output - - ``file`` - (default= ``None``) optional file-like object to which test output will be written; - if None, will default to ``sys.stdout`` - - ``with_line_numbers`` - default= ``False``) show test strings with line and column numbers - - Returns: a (success, results) tuple, where success indicates that all tests succeeded - (or failed if ``failure_tests`` is True), and the results contain a list of lines of each - test's output - - Example:: - - number_expr = pyparsing_common.number.copy() - - result = number_expr.run_tests(''' - # unsigned integer - 100 - # negative integer - -100 - # float with scientific notation - 6.02e23 - # integer with scientific notation - 1e-12 - ''') - print("Success" if result[0] else "Failed!") - - result = number_expr.run_tests(''' - # stray character - 100Z - # missing leading digit before '.' - -.100 - # too many '.' - 3.14.159 - ''', failure_tests=True) - print("Success" if result[0] else "Failed!") - - prints:: - - # unsigned integer - 100 - [100] - - # negative integer - -100 - [-100] - - # float with scientific notation - 6.02e23 - [6.02e+23] - - # integer with scientific notation - 1e-12 - [1e-12] - - Success - - # stray character - 100Z - ^ - FAIL: Expected end of text (at char 3), (line:1, col:4) - - # missing leading digit before '.' - -.100 - ^ - FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1) - - # too many '.' - 3.14.159 - ^ - FAIL: Expected end of text (at char 4), (line:1, col:5) - - Success - - Each test string must be on a single line. If you want to test a string that spans multiple - lines, create a test like this:: - - expr.run_tests(r"this is a test\\n of strings that spans \\n 3 lines") - - (Note that this is a raw string literal, you must include the leading ``'r'``.) - """ - from .testing import pyparsing_test - - parseAll = parseAll and parse_all - fullDump = fullDump and full_dump - printResults = printResults and print_results - failureTests = failureTests or failure_tests - postParse = postParse or post_parse - if isinstance(tests, str_type): - tests = typing.cast(str, tests) - line_strip = type(tests).strip - tests = [line_strip(test_line) for test_line in tests.rstrip().splitlines()] - comment_specified = comment is not None - if comment_specified: - if isinstance(comment, str_type): - comment = typing.cast(str, comment) - comment = Literal(comment) - comment = typing.cast(ParserElement, comment) - if file is None: - file = sys.stdout - print_ = file.write - - result: Union[ParseResults, Exception] - allResults: List[Tuple[str, Union[ParseResults, Exception]]] = [] - comments: List[str] = [] - success = True - NL = Literal(r"\n").add_parse_action(replace_with("\n")).ignore(quoted_string) - BOM = "\ufeff" - for t in tests: - if comment_specified and comment.matches(t, False) or comments and not t: - comments.append( - pyparsing_test.with_line_numbers(t) if with_line_numbers else t - ) - continue - if not t: - continue - out = [ - "\n" + "\n".join(comments) if comments else "", - pyparsing_test.with_line_numbers(t) if with_line_numbers else t, - ] - comments = [] - try: - # convert newline marks to actual newlines, and strip leading BOM if present - t = NL.transform_string(t.lstrip(BOM)) - result = self.parse_string(t, parse_all=parseAll) - except ParseBaseException as pe: - fatal = "(FATAL)" if isinstance(pe, ParseFatalException) else "" - out.append(pe.explain()) - out.append("FAIL: " + str(pe)) - if ParserElement.verbose_stacktrace: - out.extend(traceback.format_tb(pe.__traceback__)) - success = success and failureTests - result = pe - except Exception as exc: - out.append(f"FAIL-EXCEPTION: {type(exc).__name__}: {exc}") - if ParserElement.verbose_stacktrace: - out.extend(traceback.format_tb(exc.__traceback__)) - success = success and failureTests - result = exc - else: - success = success and not failureTests - if postParse is not None: - try: - pp_value = postParse(t, result) - if pp_value is not None: - if isinstance(pp_value, ParseResults): - out.append(pp_value.dump()) - else: - out.append(str(pp_value)) - else: - out.append(result.dump()) - except Exception as e: - out.append(result.dump(full=fullDump)) - out.append( - f"{postParse.__name__} failed: {type(e).__name__}: {e}" - ) - else: - out.append(result.dump(full=fullDump)) - out.append("") - - if printResults: - print_("\n".join(out)) - - allResults.append((t, result)) - - return success, allResults - - def create_diagram( - self, - output_html: Union[TextIO, Path, str], - vertical: int = 3, - show_results_names: bool = False, - show_groups: bool = False, - embed: bool = False, - **kwargs, - ) -> None: - """ - Create a railroad diagram for the parser. - - Parameters: - - - ``output_html`` (str or file-like object) - output target for generated - diagram HTML - - ``vertical`` (int) - threshold for formatting multiple alternatives vertically - instead of horizontally (default=3) - - ``show_results_names`` - bool flag whether diagram should show annotations for - defined results names - - ``show_groups`` - bool flag whether groups should be highlighted with an unlabeled surrounding box - - ``embed`` - bool flag whether generated HTML should omit , , and tags to embed - the resulting HTML in an enclosing HTML source - - ``head`` - str containing additional HTML to insert into the section of the generated code; - can be used to insert custom CSS styling - - ``body`` - str containing additional HTML to insert at the beginning of the section of the - generated code - - Additional diagram-formatting keyword arguments can also be included; - see railroad.Diagram class. - """ - - try: - from .diagram import to_railroad, railroad_to_html - except ImportError as ie: - raise Exception( - "must ``pip install pyparsing[diagrams]`` to generate parser railroad diagrams" - ) from ie - - self.streamline() - - railroad = to_railroad( - self, - vertical=vertical, - show_results_names=show_results_names, - show_groups=show_groups, - diagram_kwargs=kwargs, - ) - if isinstance(output_html, (str, Path)): - with open(output_html, "w", encoding="utf-8") as diag_file: - diag_file.write(railroad_to_html(railroad, embed=embed, **kwargs)) - else: - # we were passed a file-like object, just write to it - output_html.write(railroad_to_html(railroad, embed=embed, **kwargs)) - - # Compatibility synonyms - # fmt: off - @staticmethod - @replaced_by_pep8(inline_literals_using) - def inlineLiteralsUsing(): ... - - @staticmethod - @replaced_by_pep8(set_default_whitespace_chars) - def setDefaultWhitespaceChars(): ... - - @replaced_by_pep8(set_results_name) - def setResultsName(self): ... - - @replaced_by_pep8(set_break) - def setBreak(self): ... - - @replaced_by_pep8(set_parse_action) - def setParseAction(self): ... - - @replaced_by_pep8(add_parse_action) - def addParseAction(self): ... - - @replaced_by_pep8(add_condition) - def addCondition(self): ... - - @replaced_by_pep8(set_fail_action) - def setFailAction(self): ... - - @replaced_by_pep8(try_parse) - def tryParse(self): ... - - @staticmethod - @replaced_by_pep8(enable_left_recursion) - def enableLeftRecursion(): ... - - @staticmethod - @replaced_by_pep8(enable_packrat) - def enablePackrat(): ... - - @replaced_by_pep8(parse_string) - def parseString(self): ... - - @replaced_by_pep8(scan_string) - def scanString(self): ... - - @replaced_by_pep8(transform_string) - def transformString(self): ... - - @replaced_by_pep8(search_string) - def searchString(self): ... - - @replaced_by_pep8(ignore_whitespace) - def ignoreWhitespace(self): ... - - @replaced_by_pep8(leave_whitespace) - def leaveWhitespace(self): ... - - @replaced_by_pep8(set_whitespace_chars) - def setWhitespaceChars(self): ... - - @replaced_by_pep8(parse_with_tabs) - def parseWithTabs(self): ... - - @replaced_by_pep8(set_debug_actions) - def setDebugActions(self): ... - - @replaced_by_pep8(set_debug) - def setDebug(self): ... - - @replaced_by_pep8(set_name) - def setName(self): ... - - @replaced_by_pep8(parse_file) - def parseFile(self): ... - - @replaced_by_pep8(run_tests) - def runTests(self): ... - - canParseNext = can_parse_next - resetCache = reset_cache - defaultName = default_name - # fmt: on - - -class _PendingSkip(ParserElement): - # internal placeholder class to hold a place were '...' is added to a parser element, - # once another ParserElement is added, this placeholder will be replaced with a SkipTo - def __init__(self, expr: ParserElement, must_skip: bool = False): - super().__init__() - self.anchor = expr - self.must_skip = must_skip - - def _generateDefaultName(self) -> str: - return str(self.anchor + Empty()).replace("Empty", "...") - - def __add__(self, other) -> "ParserElement": - skipper = SkipTo(other).set_name("...")("_skipped*") - if self.must_skip: - - def must_skip(t): - if not t._skipped or t._skipped.as_list() == [""]: - del t[0] - t.pop("_skipped", None) - - def show_skip(t): - if t._skipped.as_list()[-1:] == [""]: - t.pop("_skipped") - t["_skipped"] = "missing <" + repr(self.anchor) + ">" - - return ( - self.anchor + skipper().add_parse_action(must_skip) - | skipper().add_parse_action(show_skip) - ) + other - - return self.anchor + skipper + other - - def __repr__(self): - return self.defaultName - - def parseImpl(self, *args): - raise Exception( - "use of `...` expression without following SkipTo target expression" - ) - - -class Token(ParserElement): - """Abstract :class:`ParserElement` subclass, for defining atomic - matching patterns. - """ - - def __init__(self): - super().__init__(savelist=False) - - def _generateDefaultName(self) -> str: - return type(self).__name__ - - -class NoMatch(Token): - """ - A token that will never match. - """ - - def __init__(self): - super().__init__() - self.mayReturnEmpty = True - self.mayIndexError = False - self.errmsg = "Unmatchable token" - - def parseImpl(self, instring, loc, doActions=True): - raise ParseException(instring, loc, self.errmsg, self) - - -class Literal(Token): - """ - Token to exactly match a specified string. - - Example:: - - Literal('blah').parse_string('blah') # -> ['blah'] - Literal('blah').parse_string('blahfooblah') # -> ['blah'] - Literal('blah').parse_string('bla') # -> Exception: Expected "blah" - - For case-insensitive matching, use :class:`CaselessLiteral`. - - For keyword matching (force word break before and after the matched string), - use :class:`Keyword` or :class:`CaselessKeyword`. - """ - - def __new__(cls, match_string: str = "", *, matchString: str = ""): - # Performance tuning: select a subclass with optimized parseImpl - if cls is Literal: - match_string = matchString or match_string - if not match_string: - return super().__new__(Empty) - if len(match_string) == 1: - return super().__new__(_SingleCharLiteral) - - # Default behavior - return super().__new__(cls) - - # Needed to make copy.copy() work correctly if we customize __new__ - def __getnewargs__(self): - return (self.match,) - - def __init__(self, match_string: str = "", *, matchString: str = ""): - super().__init__() - match_string = matchString or match_string - self.match = match_string - self.matchLen = len(match_string) - self.firstMatchChar = match_string[:1] - self.errmsg = "Expected " + self.name - self.mayReturnEmpty = False - self.mayIndexError = False - - def _generateDefaultName(self) -> str: - return repr(self.match) - - def parseImpl(self, instring, loc, doActions=True): - if instring[loc] == self.firstMatchChar and instring.startswith( - self.match, loc - ): - return loc + self.matchLen, self.match - raise ParseException(instring, loc, self.errmsg, self) - - -class Empty(Literal): - """ - An empty token, will always match. - """ - - def __init__(self, match_string="", *, matchString=""): - super().__init__("") - self.mayReturnEmpty = True - self.mayIndexError = False - - def _generateDefaultName(self) -> str: - return "Empty" - - def parseImpl(self, instring, loc, doActions=True): - return loc, [] - - -class _SingleCharLiteral(Literal): - def parseImpl(self, instring, loc, doActions=True): - if instring[loc] == self.firstMatchChar: - return loc + 1, self.match - raise ParseException(instring, loc, self.errmsg, self) - - -ParserElement._literalStringClass = Literal - - -class Keyword(Token): - """ - Token to exactly match a specified string as a keyword, that is, - it must be immediately preceded and followed by whitespace or - non-keyword characters. Compare with :class:`Literal`: - - - ``Literal("if")`` will match the leading ``'if'`` in - ``'ifAndOnlyIf'``. - - ``Keyword("if")`` will not; it will only match the leading - ``'if'`` in ``'if x=1'``, or ``'if(y==2)'`` - - Accepts two optional constructor arguments in addition to the - keyword string: - - - ``ident_chars`` is a string of characters that would be valid - identifier characters, defaulting to all alphanumerics + "_" and - "$" - - ``caseless`` allows case-insensitive matching, default is ``False``. - - Example:: - - Keyword("start").parse_string("start") # -> ['start'] - Keyword("start").parse_string("starting") # -> Exception - - For case-insensitive matching, use :class:`CaselessKeyword`. - """ - - DEFAULT_KEYWORD_CHARS = alphanums + "_$" - - def __init__( - self, - match_string: str = "", - ident_chars: typing.Optional[str] = None, - caseless: bool = False, - *, - matchString: str = "", - identChars: typing.Optional[str] = None, - ): - super().__init__() - identChars = identChars or ident_chars - if identChars is None: - identChars = Keyword.DEFAULT_KEYWORD_CHARS - match_string = matchString or match_string - self.match = match_string - self.matchLen = len(match_string) - try: - self.firstMatchChar = match_string[0] - except IndexError: - raise ValueError("null string passed to Keyword; use Empty() instead") - self.errmsg = f"Expected {type(self).__name__} {self.name}" - self.mayReturnEmpty = False - self.mayIndexError = False - self.caseless = caseless - if caseless: - self.caselessmatch = match_string.upper() - identChars = identChars.upper() - self.identChars = set(identChars) - - def _generateDefaultName(self) -> str: - return repr(self.match) - - def parseImpl(self, instring, loc, doActions=True): - errmsg = self.errmsg - errloc = loc - if self.caseless: - if instring[loc : loc + self.matchLen].upper() == self.caselessmatch: - if loc == 0 or instring[loc - 1].upper() not in self.identChars: - if ( - loc >= len(instring) - self.matchLen - or instring[loc + self.matchLen].upper() not in self.identChars - ): - return loc + self.matchLen, self.match - else: - # followed by keyword char - errmsg += ", was immediately followed by keyword character" - errloc = loc + self.matchLen - else: - # preceded by keyword char - errmsg += ", keyword was immediately preceded by keyword character" - errloc = loc - 1 - # else no match just raise plain exception - - else: - if ( - instring[loc] == self.firstMatchChar - and self.matchLen == 1 - or instring.startswith(self.match, loc) - ): - if loc == 0 or instring[loc - 1] not in self.identChars: - if ( - loc >= len(instring) - self.matchLen - or instring[loc + self.matchLen] not in self.identChars - ): - return loc + self.matchLen, self.match - else: - # followed by keyword char - errmsg += ( - ", keyword was immediately followed by keyword character" - ) - errloc = loc + self.matchLen - else: - # preceded by keyword char - errmsg += ", keyword was immediately preceded by keyword character" - errloc = loc - 1 - # else no match just raise plain exception - - raise ParseException(instring, errloc, errmsg, self) - - @staticmethod - def set_default_keyword_chars(chars) -> None: - """ - Overrides the default characters used by :class:`Keyword` expressions. - """ - Keyword.DEFAULT_KEYWORD_CHARS = chars - - setDefaultKeywordChars = set_default_keyword_chars - - -class CaselessLiteral(Literal): - """ - Token to match a specified string, ignoring case of letters. - Note: the matched results will always be in the case of the given - match string, NOT the case of the input text. - - Example:: - - CaselessLiteral("CMD")[1, ...].parse_string("cmd CMD Cmd10") - # -> ['CMD', 'CMD', 'CMD'] - - (Contrast with example for :class:`CaselessKeyword`.) - """ - - def __init__(self, match_string: str = "", *, matchString: str = ""): - match_string = matchString or match_string - super().__init__(match_string.upper()) - # Preserve the defining literal. - self.returnString = match_string - self.errmsg = "Expected " + self.name - - def parseImpl(self, instring, loc, doActions=True): - if instring[loc : loc + self.matchLen].upper() == self.match: - return loc + self.matchLen, self.returnString - raise ParseException(instring, loc, self.errmsg, self) - - -class CaselessKeyword(Keyword): - """ - Caseless version of :class:`Keyword`. - - Example:: - - CaselessKeyword("CMD")[1, ...].parse_string("cmd CMD Cmd10") - # -> ['CMD', 'CMD'] - - (Contrast with example for :class:`CaselessLiteral`.) - """ - - def __init__( - self, - match_string: str = "", - ident_chars: typing.Optional[str] = None, - *, - matchString: str = "", - identChars: typing.Optional[str] = None, - ): - identChars = identChars or ident_chars - match_string = matchString or match_string - super().__init__(match_string, identChars, caseless=True) - - -class CloseMatch(Token): - """A variation on :class:`Literal` which matches "close" matches, - that is, strings with at most 'n' mismatching characters. - :class:`CloseMatch` takes parameters: - - - ``match_string`` - string to be matched - - ``caseless`` - a boolean indicating whether to ignore casing when comparing characters - - ``max_mismatches`` - (``default=1``) maximum number of - mismatches allowed to count as a match - - The results from a successful parse will contain the matched text - from the input string and the following named results: - - - ``mismatches`` - a list of the positions within the - match_string where mismatches were found - - ``original`` - the original match_string used to compare - against the input string - - If ``mismatches`` is an empty list, then the match was an exact - match. - - Example:: - - patt = CloseMatch("ATCATCGAATGGA") - patt.parse_string("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']}) - patt.parse_string("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1) - - # exact match - patt.parse_string("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']}) - - # close match allowing up to 2 mismatches - patt = CloseMatch("ATCATCGAATGGA", max_mismatches=2) - patt.parse_string("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']}) - """ - - def __init__( - self, - match_string: str, - max_mismatches: typing.Optional[int] = None, - *, - maxMismatches: int = 1, - caseless=False, - ): - maxMismatches = max_mismatches if max_mismatches is not None else maxMismatches - super().__init__() - self.match_string = match_string - self.maxMismatches = maxMismatches - self.errmsg = f"Expected {self.match_string!r} (with up to {self.maxMismatches} mismatches)" - self.caseless = caseless - self.mayIndexError = False - self.mayReturnEmpty = False - - def _generateDefaultName(self) -> str: - return f"{type(self).__name__}:{self.match_string!r}" - - def parseImpl(self, instring, loc, doActions=True): - start = loc - instrlen = len(instring) - maxloc = start + len(self.match_string) - - if maxloc <= instrlen: - match_string = self.match_string - match_stringloc = 0 - mismatches = [] - maxMismatches = self.maxMismatches - - for match_stringloc, s_m in enumerate( - zip(instring[loc:maxloc], match_string) - ): - src, mat = s_m - if self.caseless: - src, mat = src.lower(), mat.lower() - - if src != mat: - mismatches.append(match_stringloc) - if len(mismatches) > maxMismatches: - break - else: - loc = start + match_stringloc + 1 - results = ParseResults([instring[start:loc]]) - results["original"] = match_string - results["mismatches"] = mismatches - return loc, results - - raise ParseException(instring, loc, self.errmsg, self) - - -class Word(Token): - """Token for matching words composed of allowed character sets. - - Parameters: - - - ``init_chars`` - string of all characters that should be used to - match as a word; "ABC" will match "AAA", "ABAB", "CBAC", etc.; - if ``body_chars`` is also specified, then this is the string of - initial characters - - ``body_chars`` - string of characters that - can be used for matching after a matched initial character as - given in ``init_chars``; if omitted, same as the initial characters - (default=``None``) - - ``min`` - minimum number of characters to match (default=1) - - ``max`` - maximum number of characters to match (default=0) - - ``exact`` - exact number of characters to match (default=0) - - ``as_keyword`` - match as a keyword (default=``False``) - - ``exclude_chars`` - characters that might be - found in the input ``body_chars`` string but which should not be - accepted for matching ;useful to define a word of all - printables except for one or two characters, for instance - (default=``None``) - - :class:`srange` is useful for defining custom character set strings - for defining :class:`Word` expressions, using range notation from - regular expression character sets. - - A common mistake is to use :class:`Word` to match a specific literal - string, as in ``Word("Address")``. Remember that :class:`Word` - uses the string argument to define *sets* of matchable characters. - This expression would match "Add", "AAA", "dAred", or any other word - made up of the characters 'A', 'd', 'r', 'e', and 's'. To match an - exact literal string, use :class:`Literal` or :class:`Keyword`. - - pyparsing includes helper strings for building Words: - - - :class:`alphas` - - :class:`nums` - - :class:`alphanums` - - :class:`hexnums` - - :class:`alphas8bit` (alphabetic characters in ASCII range 128-255 - - accented, tilded, umlauted, etc.) - - :class:`punc8bit` (non-alphabetic characters in ASCII range - 128-255 - currency, symbols, superscripts, diacriticals, etc.) - - :class:`printables` (any non-whitespace character) - - ``alphas``, ``nums``, and ``printables`` are also defined in several - Unicode sets - see :class:`pyparsing_unicode``. - - Example:: - - # a word composed of digits - integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9")) - - # a word with a leading capital, and zero or more lowercase - capital_word = Word(alphas.upper(), alphas.lower()) - - # hostnames are alphanumeric, with leading alpha, and '-' - hostname = Word(alphas, alphanums + '-') - - # roman numeral (not a strict parser, accepts invalid mix of characters) - roman = Word("IVXLCDM") - - # any string of non-whitespace characters, except for ',' - csv_value = Word(printables, exclude_chars=",") - """ - - def __init__( - self, - init_chars: str = "", - body_chars: typing.Optional[str] = None, - min: int = 1, - max: int = 0, - exact: int = 0, - as_keyword: bool = False, - exclude_chars: typing.Optional[str] = None, - *, - initChars: typing.Optional[str] = None, - bodyChars: typing.Optional[str] = None, - asKeyword: bool = False, - excludeChars: typing.Optional[str] = None, - ): - initChars = initChars or init_chars - bodyChars = bodyChars or body_chars - asKeyword = asKeyword or as_keyword - excludeChars = excludeChars or exclude_chars - super().__init__() - if not initChars: - raise ValueError( - f"invalid {type(self).__name__}, initChars cannot be empty string" - ) - - initChars_set = set(initChars) - if excludeChars: - excludeChars_set = set(excludeChars) - initChars_set -= excludeChars_set - if bodyChars: - bodyChars = "".join(set(bodyChars) - excludeChars_set) - self.initChars = initChars_set - self.initCharsOrig = "".join(sorted(initChars_set)) - - if bodyChars: - self.bodyChars = set(bodyChars) - self.bodyCharsOrig = "".join(sorted(bodyChars)) - else: - self.bodyChars = initChars_set - self.bodyCharsOrig = self.initCharsOrig - - self.maxSpecified = max > 0 - - if min < 1: - raise ValueError( - "cannot specify a minimum length < 1; use Opt(Word()) if zero-length word is permitted" - ) - - if self.maxSpecified and min > max: - raise ValueError( - f"invalid args, if min and max both specified min must be <= max (min={min}, max={max})" - ) - - self.minLen = min - - if max > 0: - self.maxLen = max - else: - self.maxLen = _MAX_INT - - if exact > 0: - min = max = exact - self.maxLen = exact - self.minLen = exact - - self.errmsg = "Expected " + self.name - self.mayIndexError = False - self.asKeyword = asKeyword - if self.asKeyword: - self.errmsg += " as a keyword" - - # see if we can make a regex for this Word - if " " not in (self.initChars | self.bodyChars): - if len(self.initChars) == 1: - re_leading_fragment = re.escape(self.initCharsOrig) - else: - re_leading_fragment = f"[{_collapse_string_to_ranges(self.initChars)}]" - - if self.bodyChars == self.initChars: - if max == 0: - repeat = "+" - elif max == 1: - repeat = "" - else: - if self.minLen != self.maxLen: - repeat = f"{{{self.minLen},{'' if self.maxLen == _MAX_INT else self.maxLen}}}" - else: - repeat = f"{{{self.minLen}}}" - self.reString = f"{re_leading_fragment}{repeat}" - else: - if max == 1: - re_body_fragment = "" - repeat = "" - else: - re_body_fragment = f"[{_collapse_string_to_ranges(self.bodyChars)}]" - if max == 0: - repeat = "*" - elif max == 2: - repeat = "?" if min <= 1 else "" - else: - if min != max: - repeat = f"{{{min - 1 if min > 0 else 0},{max - 1}}}" - else: - repeat = f"{{{min - 1 if min > 0 else 0}}}" - - self.reString = ( - f"{re_leading_fragment}" f"{re_body_fragment}" f"{repeat}" - ) - - if self.asKeyword: - self.reString = rf"\b{self.reString}\b" - - try: - self.re = re.compile(self.reString) - except re.error: - self.re = None # type: ignore[assignment] - else: - self.re_match = self.re.match - self.parseImpl = self.parseImpl_regex # type: ignore[assignment] - - def _generateDefaultName(self) -> str: - def charsAsStr(s): - max_repr_len = 16 - s = _collapse_string_to_ranges(s, re_escape=False) - if len(s) > max_repr_len: - return s[: max_repr_len - 3] + "..." - else: - return s - - if self.initChars != self.bodyChars: - base = f"W:({charsAsStr(self.initChars)}, {charsAsStr(self.bodyChars)})" - else: - base = f"W:({charsAsStr(self.initChars)})" - - # add length specification - if self.minLen > 1 or self.maxLen != _MAX_INT: - if self.minLen == self.maxLen: - if self.minLen == 1: - return base[2:] - else: - return base + f"{{{self.minLen}}}" - elif self.maxLen == _MAX_INT: - return base + f"{{{self.minLen},...}}" - else: - return base + f"{{{self.minLen},{self.maxLen}}}" - return base - - def parseImpl(self, instring, loc, doActions=True): - if instring[loc] not in self.initChars: - raise ParseException(instring, loc, self.errmsg, self) - - start = loc - loc += 1 - instrlen = len(instring) - bodychars = self.bodyChars - maxloc = start + self.maxLen - maxloc = min(maxloc, instrlen) - while loc < maxloc and instring[loc] in bodychars: - loc += 1 - - throwException = False - if loc - start < self.minLen: - throwException = True - elif self.maxSpecified and loc < instrlen and instring[loc] in bodychars: - throwException = True - elif self.asKeyword: - if ( - start > 0 - and instring[start - 1] in bodychars - or loc < instrlen - and instring[loc] in bodychars - ): - throwException = True - - if throwException: - raise ParseException(instring, loc, self.errmsg, self) - - return loc, instring[start:loc] - - def parseImpl_regex(self, instring, loc, doActions=True): - result = self.re_match(instring, loc) - if not result: - raise ParseException(instring, loc, self.errmsg, self) - - loc = result.end() - return loc, result.group() - - -class Char(Word): - """A short-cut class for defining :class:`Word` ``(characters, exact=1)``, - when defining a match of any single character in a string of - characters. - """ - - def __init__( - self, - charset: str, - as_keyword: bool = False, - exclude_chars: typing.Optional[str] = None, - *, - asKeyword: bool = False, - excludeChars: typing.Optional[str] = None, - ): - asKeyword = asKeyword or as_keyword - excludeChars = excludeChars or exclude_chars - super().__init__( - charset, exact=1, as_keyword=asKeyword, exclude_chars=excludeChars - ) - - -class Regex(Token): - r"""Token for matching strings that match a given regular - expression. Defined with string specifying the regular expression in - a form recognized by the stdlib Python `re module `_. - If the given regex contains named groups (defined using ``(?P...)``), - these will be preserved as named :class:`ParseResults`. - - If instead of the Python stdlib ``re`` module you wish to use a different RE module - (such as the ``regex`` module), you can do so by building your ``Regex`` object with - a compiled RE that was compiled using ``regex``. - - Example:: - - realnum = Regex(r"[+-]?\d+\.\d*") - # ref: https://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression - roman = Regex(r"M{0,4}(CM|CD|D?{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})") - - # named fields in a regex will be returned as named results - date = Regex(r'(?P\d{4})-(?P\d\d?)-(?P\d\d?)') - - # the Regex class will accept re's compiled using the regex module - import regex - parser = pp.Regex(regex.compile(r'[0-9]')) - """ - - def __init__( - self, - pattern: Any, - flags: Union[re.RegexFlag, int] = 0, - as_group_list: bool = False, - as_match: bool = False, - *, - asGroupList: bool = False, - asMatch: bool = False, - ): - """The parameters ``pattern`` and ``flags`` are passed - to the ``re.compile()`` function as-is. See the Python - `re module `_ module for an - explanation of the acceptable patterns and flags. - """ - super().__init__() - asGroupList = asGroupList or as_group_list - asMatch = asMatch or as_match - - if isinstance(pattern, str_type): - if not pattern: - raise ValueError("null string passed to Regex; use Empty() instead") - - self._re = None - self.reString = self.pattern = pattern - self.flags = flags - - elif hasattr(pattern, "pattern") and hasattr(pattern, "match"): - self._re = pattern - self.pattern = self.reString = pattern.pattern - self.flags = flags - - else: - raise TypeError( - "Regex may only be constructed with a string or a compiled RE object" - ) - - self.errmsg = "Expected " + self.name - self.mayIndexError = False - self.asGroupList = asGroupList - self.asMatch = asMatch - if self.asGroupList: - self.parseImpl = self.parseImplAsGroupList # type: ignore [assignment] - if self.asMatch: - self.parseImpl = self.parseImplAsMatch # type: ignore [assignment] - - @cached_property - def re(self): - if self._re: - return self._re - else: - try: - return re.compile(self.pattern, self.flags) - except re.error: - raise ValueError(f"invalid pattern ({self.pattern!r}) passed to Regex") - - @cached_property - def re_match(self): - return self.re.match - - @cached_property - def mayReturnEmpty(self): - return self.re_match("") is not None - - def _generateDefaultName(self) -> str: - return "Re:({})".format(repr(self.pattern).replace("\\\\", "\\")) - - def parseImpl(self, instring, loc, doActions=True): - result = self.re_match(instring, loc) - if not result: - raise ParseException(instring, loc, self.errmsg, self) - - loc = result.end() - ret = ParseResults(result.group()) - d = result.groupdict() - if d: - for k, v in d.items(): - ret[k] = v - return loc, ret - - def parseImplAsGroupList(self, instring, loc, doActions=True): - result = self.re_match(instring, loc) - if not result: - raise ParseException(instring, loc, self.errmsg, self) - - loc = result.end() - ret = result.groups() - return loc, ret - - def parseImplAsMatch(self, instring, loc, doActions=True): - result = self.re_match(instring, loc) - if not result: - raise ParseException(instring, loc, self.errmsg, self) - - loc = result.end() - ret = result - return loc, ret - - def sub(self, repl: str) -> ParserElement: - r""" - Return :class:`Regex` with an attached parse action to transform the parsed - result as if called using `re.sub(expr, repl, string) `_. - - Example:: - - make_html = Regex(r"(\w+):(.*?):").sub(r"<\1>\2") - print(make_html.transform_string("h1:main title:")) - # prints "

main title

" - """ - if self.asGroupList: - raise TypeError("cannot use sub() with Regex(as_group_list=True)") - - if self.asMatch and callable(repl): - raise TypeError( - "cannot use sub() with a callable with Regex(as_match=True)" - ) - - if self.asMatch: - - def pa(tokens): - return tokens[0].expand(repl) - - else: - - def pa(tokens): - return self.re.sub(repl, tokens[0]) - - return self.add_parse_action(pa) - - -class QuotedString(Token): - r""" - Token for matching strings that are delimited by quoting characters. - - Defined with the following parameters: - - - ``quote_char`` - string of one or more characters defining the - quote delimiting string - - ``esc_char`` - character to re_escape quotes, typically backslash - (default= ``None``) - - ``esc_quote`` - special quote sequence to re_escape an embedded quote - string (such as SQL's ``""`` to re_escape an embedded ``"``) - (default= ``None``) - - ``multiline`` - boolean indicating whether quotes can span - multiple lines (default= ``False``) - - ``unquote_results`` - boolean indicating whether the matched text - should be unquoted (default= ``True``) - - ``end_quote_char`` - string of one or more characters defining the - end of the quote delimited string (default= ``None`` => same as - quote_char) - - ``convert_whitespace_escapes`` - convert escaped whitespace - (``'\t'``, ``'\n'``, etc.) to actual whitespace - (default= ``True``) - - Example:: - - qs = QuotedString('"') - print(qs.search_string('lsjdf "This is the quote" sldjf')) - complex_qs = QuotedString('{{', end_quote_char='}}') - print(complex_qs.search_string('lsjdf {{This is the "quote"}} sldjf')) - sql_qs = QuotedString('"', esc_quote='""') - print(sql_qs.search_string('lsjdf "This is the quote with ""embedded"" quotes" sldjf')) - - prints:: - - [['This is the quote']] - [['This is the "quote"']] - [['This is the quote with "embedded" quotes']] - """ - ws_map = dict(((r"\t", "\t"), (r"\n", "\n"), (r"\f", "\f"), (r"\r", "\r"))) - - def __init__( - self, - quote_char: str = "", - esc_char: typing.Optional[str] = None, - esc_quote: typing.Optional[str] = None, - multiline: bool = False, - unquote_results: bool = True, - end_quote_char: typing.Optional[str] = None, - convert_whitespace_escapes: bool = True, - *, - quoteChar: str = "", - escChar: typing.Optional[str] = None, - escQuote: typing.Optional[str] = None, - unquoteResults: bool = True, - endQuoteChar: typing.Optional[str] = None, - convertWhitespaceEscapes: bool = True, - ): - super().__init__() - escChar = escChar or esc_char - escQuote = escQuote or esc_quote - unquoteResults = unquoteResults and unquote_results - endQuoteChar = endQuoteChar or end_quote_char - convertWhitespaceEscapes = ( - convertWhitespaceEscapes and convert_whitespace_escapes - ) - quote_char = quoteChar or quote_char - - # remove white space from quote chars - wont work anyway - quote_char = quote_char.strip() - if not quote_char: - raise ValueError("quote_char cannot be the empty string") - - if endQuoteChar is None: - endQuoteChar = quote_char - else: - endQuoteChar = endQuoteChar.strip() - if not endQuoteChar: - raise ValueError("end_quote_char cannot be the empty string") - - self.quoteChar: str = quote_char - self.quoteCharLen: int = len(quote_char) - self.firstQuoteChar: str = quote_char[0] - self.endQuoteChar: str = endQuoteChar - self.endQuoteCharLen: int = len(endQuoteChar) - self.escChar: str = escChar or "" - self.escQuote: str = escQuote or "" - self.unquoteResults: bool = unquoteResults - self.convertWhitespaceEscapes: bool = convertWhitespaceEscapes - self.multiline = multiline - - sep = "" - inner_pattern = "" - - if escQuote: - inner_pattern += rf"{sep}(?:{re.escape(escQuote)})" - sep = "|" - - if escChar: - inner_pattern += rf"{sep}(?:{re.escape(escChar)}.)" - sep = "|" - self.escCharReplacePattern = re.escape(escChar) + "(.)" - - if len(self.endQuoteChar) > 1: - inner_pattern += ( - f"{sep}(?:" - + "|".join( - f"(?:{re.escape(self.endQuoteChar[:i])}(?!{re.escape(self.endQuoteChar[i:])}))" - for i in range(len(self.endQuoteChar) - 1, 0, -1) - ) - + ")" - ) - sep = "|" - - self.flags = re.RegexFlag(0) - - if multiline: - self.flags = re.MULTILINE | re.DOTALL - inner_pattern += ( - rf"{sep}(?:[^{_escape_regex_range_chars(self.endQuoteChar[0])}" - rf"{(_escape_regex_range_chars(escChar) if escChar is not None else '')}])" - ) - else: - inner_pattern += ( - rf"{sep}(?:[^{_escape_regex_range_chars(self.endQuoteChar[0])}\n\r" - rf"{(_escape_regex_range_chars(escChar) if escChar is not None else '')}])" - ) - - self.pattern = "".join( - [ - re.escape(self.quoteChar), - "(?:", - inner_pattern, - ")*", - re.escape(self.endQuoteChar), - ] - ) - - if self.unquoteResults: - if self.convertWhitespaceEscapes: - self.unquote_scan_re = re.compile( - rf"({'|'.join(re.escape(k) for k in self.ws_map)})|({re.escape(self.escChar)}.)|(\n|.)", - flags=self.flags, - ) - else: - self.unquote_scan_re = re.compile( - rf"({re.escape(self.escChar)}.)|(\n|.)", flags=self.flags - ) - - try: - self.re = re.compile(self.pattern, self.flags) - self.reString = self.pattern - self.re_match = self.re.match - except re.error: - raise ValueError(f"invalid pattern {self.pattern!r} passed to Regex") - - self.errmsg = "Expected " + self.name - self.mayIndexError = False - self.mayReturnEmpty = True - - def _generateDefaultName(self) -> str: - if self.quoteChar == self.endQuoteChar and isinstance(self.quoteChar, str_type): - return f"string enclosed in {self.quoteChar!r}" - - return f"quoted string, starting with {self.quoteChar} ending with {self.endQuoteChar}" - - def parseImpl(self, instring, loc, doActions=True): - result = ( - instring[loc] == self.firstQuoteChar - and self.re_match(instring, loc) - or None - ) - if not result: - raise ParseException(instring, loc, self.errmsg, self) - - loc = result.end() - ret = result.group() - - if self.unquoteResults: - # strip off quotes - ret = ret[self.quoteCharLen : -self.endQuoteCharLen] - - if isinstance(ret, str_type): - if self.convertWhitespaceEscapes: - ret = "".join( - self.ws_map[match.group(1)] - if match.group(1) - else match.group(2)[-1] - if match.group(2) - else match.group(3) - for match in self.unquote_scan_re.finditer(ret) - ) - else: - ret = "".join( - match.group(1)[-1] if match.group(1) else match.group(2) - for match in self.unquote_scan_re.finditer(ret) - ) - - # replace escaped quotes - if self.escQuote: - ret = ret.replace(self.escQuote, self.endQuoteChar) - - return loc, ret - - -class CharsNotIn(Token): - """Token for matching words composed of characters *not* in a given - set (will include whitespace in matched characters if not listed in - the provided exclusion set - see example). Defined with string - containing all disallowed characters, and an optional minimum, - maximum, and/or exact length. The default value for ``min`` is - 1 (a minimum value < 1 is not valid); the default values for - ``max`` and ``exact`` are 0, meaning no maximum or exact - length restriction. - - Example:: - - # define a comma-separated-value as anything that is not a ',' - csv_value = CharsNotIn(',') - print(DelimitedList(csv_value).parse_string("dkls,lsdkjf,s12 34,@!#,213")) - - prints:: - - ['dkls', 'lsdkjf', 's12 34', '@!#', '213'] - """ - - def __init__( - self, - not_chars: str = "", - min: int = 1, - max: int = 0, - exact: int = 0, - *, - notChars: str = "", - ): - super().__init__() - self.skipWhitespace = False - self.notChars = not_chars or notChars - self.notCharsSet = set(self.notChars) - - if min < 1: - raise ValueError( - "cannot specify a minimum length < 1; use " - "Opt(CharsNotIn()) if zero-length char group is permitted" - ) - - self.minLen = min - - if max > 0: - self.maxLen = max - else: - self.maxLen = _MAX_INT - - if exact > 0: - self.maxLen = exact - self.minLen = exact - - self.errmsg = "Expected " + self.name - self.mayReturnEmpty = self.minLen == 0 - self.mayIndexError = False - - def _generateDefaultName(self) -> str: - not_chars_str = _collapse_string_to_ranges(self.notChars) - if len(not_chars_str) > 16: - return f"!W:({self.notChars[: 16 - 3]}...)" - else: - return f"!W:({self.notChars})" - - def parseImpl(self, instring, loc, doActions=True): - notchars = self.notCharsSet - if instring[loc] in notchars: - raise ParseException(instring, loc, self.errmsg, self) - - start = loc - loc += 1 - maxlen = min(start + self.maxLen, len(instring)) - while loc < maxlen and instring[loc] not in notchars: - loc += 1 - - if loc - start < self.minLen: - raise ParseException(instring, loc, self.errmsg, self) - - return loc, instring[start:loc] - - -class White(Token): - """Special matching class for matching whitespace. Normally, - whitespace is ignored by pyparsing grammars. This class is included - when some whitespace structures are significant. Define with - a string containing the whitespace characters to be matched; default - is ``" \\t\\r\\n"``. Also takes optional ``min``, - ``max``, and ``exact`` arguments, as defined for the - :class:`Word` class. - """ - - whiteStrs = { - " ": "", - "\t": "", - "\n": "", - "\r": "", - "\f": "", - "\u00A0": "", - "\u1680": "", - "\u180E": "", - "\u2000": "", - "\u2001": "", - "\u2002": "", - "\u2003": "", - "\u2004": "", - "\u2005": "", - "\u2006": "", - "\u2007": "", - "\u2008": "", - "\u2009": "", - "\u200A": "", - "\u200B": "", - "\u202F": "", - "\u205F": "", - "\u3000": "", - } - - def __init__(self, ws: str = " \t\r\n", min: int = 1, max: int = 0, exact: int = 0): - super().__init__() - self.matchWhite = ws - self.set_whitespace_chars( - "".join(c for c in self.whiteStrs if c not in self.matchWhite), - copy_defaults=True, - ) - # self.leave_whitespace() - self.mayReturnEmpty = True - self.errmsg = "Expected " + self.name - - self.minLen = min - - if max > 0: - self.maxLen = max - else: - self.maxLen = _MAX_INT - - if exact > 0: - self.maxLen = exact - self.minLen = exact - - def _generateDefaultName(self) -> str: - return "".join(White.whiteStrs[c] for c in self.matchWhite) - - def parseImpl(self, instring, loc, doActions=True): - if instring[loc] not in self.matchWhite: - raise ParseException(instring, loc, self.errmsg, self) - start = loc - loc += 1 - maxloc = start + self.maxLen - maxloc = min(maxloc, len(instring)) - while loc < maxloc and instring[loc] in self.matchWhite: - loc += 1 - - if loc - start < self.minLen: - raise ParseException(instring, loc, self.errmsg, self) - - return loc, instring[start:loc] - - -class PositionToken(Token): - def __init__(self): - super().__init__() - self.mayReturnEmpty = True - self.mayIndexError = False - - -class GoToColumn(PositionToken): - """Token to advance to a specific column of input text; useful for - tabular report scraping. - """ - - def __init__(self, colno: int): - super().__init__() - self.col = colno - - def preParse(self, instring: str, loc: int) -> int: - if col(loc, instring) != self.col: - instrlen = len(instring) - if self.ignoreExprs: - loc = self._skipIgnorables(instring, loc) - while ( - loc < instrlen - and instring[loc].isspace() - and col(loc, instring) != self.col - ): - loc += 1 - return loc - - def parseImpl(self, instring, loc, doActions=True): - thiscol = col(loc, instring) - if thiscol > self.col: - raise ParseException(instring, loc, "Text not in expected column", self) - newloc = loc + self.col - thiscol - ret = instring[loc:newloc] - return newloc, ret - - -class LineStart(PositionToken): - r"""Matches if current position is at the beginning of a line within - the parse string - - Example:: - - test = '''\ - AAA this line - AAA and this line - AAA but not this one - B AAA and definitely not this one - ''' - - for t in (LineStart() + 'AAA' + rest_of_line).search_string(test): - print(t) - - prints:: - - ['AAA', ' this line'] - ['AAA', ' and this line'] - - """ - - def __init__(self): - super().__init__() - self.leave_whitespace() - self.orig_whiteChars = set() | self.whiteChars - self.whiteChars.discard("\n") - self.skipper = Empty().set_whitespace_chars(self.whiteChars) - self.errmsg = "Expected start of line" - - def preParse(self, instring: str, loc: int) -> int: - if loc == 0: - return loc - else: - ret = self.skipper.preParse(instring, loc) - if "\n" in self.orig_whiteChars: - while instring[ret : ret + 1] == "\n": - ret = self.skipper.preParse(instring, ret + 1) - return ret - - def parseImpl(self, instring, loc, doActions=True): - if col(loc, instring) == 1: - return loc, [] - raise ParseException(instring, loc, self.errmsg, self) - - -class LineEnd(PositionToken): - """Matches if current position is at the end of a line within the - parse string - """ - - def __init__(self): - super().__init__() - self.whiteChars.discard("\n") - self.set_whitespace_chars(self.whiteChars, copy_defaults=False) - self.errmsg = "Expected end of line" - - def parseImpl(self, instring, loc, doActions=True): - if loc < len(instring): - if instring[loc] == "\n": - return loc + 1, "\n" - else: - raise ParseException(instring, loc, self.errmsg, self) - elif loc == len(instring): - return loc + 1, [] - else: - raise ParseException(instring, loc, self.errmsg, self) - - -class StringStart(PositionToken): - """Matches if current position is at the beginning of the parse - string - """ - - def __init__(self): - super().__init__() - self.errmsg = "Expected start of text" - - def parseImpl(self, instring, loc, doActions=True): - if loc != 0: - # see if entire string up to here is just whitespace and ignoreables - if loc != self.preParse(instring, 0): - raise ParseException(instring, loc, self.errmsg, self) - return loc, [] - - -class StringEnd(PositionToken): - """ - Matches if current position is at the end of the parse string - """ - - def __init__(self): - super().__init__() - self.errmsg = "Expected end of text" - - def parseImpl(self, instring, loc, doActions=True): - if loc < len(instring): - raise ParseException(instring, loc, self.errmsg, self) - elif loc == len(instring): - return loc + 1, [] - elif loc > len(instring): - return loc, [] - else: - raise ParseException(instring, loc, self.errmsg, self) - - -class WordStart(PositionToken): - """Matches if the current position is at the beginning of a - :class:`Word`, and is not preceded by any character in a given - set of ``word_chars`` (default= ``printables``). To emulate the - ``\b`` behavior of regular expressions, use - ``WordStart(alphanums)``. ``WordStart`` will also match at - the beginning of the string being parsed, or at the beginning of - a line. - """ - - def __init__(self, word_chars: str = printables, *, wordChars: str = printables): - wordChars = word_chars if wordChars == printables else wordChars - super().__init__() - self.wordChars = set(wordChars) - self.errmsg = "Not at the start of a word" - - def parseImpl(self, instring, loc, doActions=True): - if loc != 0: - if ( - instring[loc - 1] in self.wordChars - or instring[loc] not in self.wordChars - ): - raise ParseException(instring, loc, self.errmsg, self) - return loc, [] - - -class WordEnd(PositionToken): - """Matches if the current position is at the end of a :class:`Word`, - and is not followed by any character in a given set of ``word_chars`` - (default= ``printables``). To emulate the ``\b`` behavior of - regular expressions, use ``WordEnd(alphanums)``. ``WordEnd`` - will also match at the end of the string being parsed, or at the end - of a line. - """ - - def __init__(self, word_chars: str = printables, *, wordChars: str = printables): - wordChars = word_chars if wordChars == printables else wordChars - super().__init__() - self.wordChars = set(wordChars) - self.skipWhitespace = False - self.errmsg = "Not at the end of a word" - - def parseImpl(self, instring, loc, doActions=True): - instrlen = len(instring) - if instrlen > 0 and loc < instrlen: - if ( - instring[loc] in self.wordChars - or instring[loc - 1] not in self.wordChars - ): - raise ParseException(instring, loc, self.errmsg, self) - return loc, [] - - -class ParseExpression(ParserElement): - """Abstract subclass of ParserElement, for combining and - post-processing parsed tokens. - """ - - def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): - super().__init__(savelist) - self.exprs: List[ParserElement] - if isinstance(exprs, _generatorType): - exprs = list(exprs) - - if isinstance(exprs, str_type): - self.exprs = [self._literalStringClass(exprs)] - elif isinstance(exprs, ParserElement): - self.exprs = [exprs] - elif isinstance(exprs, Iterable): - exprs = list(exprs) - # if sequence of strings provided, wrap with Literal - if any(isinstance(expr, str_type) for expr in exprs): - exprs = ( - self._literalStringClass(e) if isinstance(e, str_type) else e - for e in exprs - ) - self.exprs = list(exprs) - else: - try: - self.exprs = list(exprs) - except TypeError: - self.exprs = [exprs] - self.callPreparse = False - - def recurse(self) -> List[ParserElement]: - return self.exprs[:] - - def append(self, other) -> ParserElement: - self.exprs.append(other) - self._defaultName = None - return self - - def leave_whitespace(self, recursive: bool = True) -> ParserElement: - """ - Extends ``leave_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on - all contained expressions. - """ - super().leave_whitespace(recursive) - - if recursive: - self.exprs = [e.copy() for e in self.exprs] - for e in self.exprs: - e.leave_whitespace(recursive) - return self - - def ignore_whitespace(self, recursive: bool = True) -> ParserElement: - """ - Extends ``ignore_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on - all contained expressions. - """ - super().ignore_whitespace(recursive) - if recursive: - self.exprs = [e.copy() for e in self.exprs] - for e in self.exprs: - e.ignore_whitespace(recursive) - return self - - def ignore(self, other) -> ParserElement: - if isinstance(other, Suppress): - if other not in self.ignoreExprs: - super().ignore(other) - for e in self.exprs: - e.ignore(self.ignoreExprs[-1]) - else: - super().ignore(other) - for e in self.exprs: - e.ignore(self.ignoreExprs[-1]) - return self - - def _generateDefaultName(self) -> str: - return f"{self.__class__.__name__}:({str(self.exprs)})" - - def streamline(self) -> ParserElement: - if self.streamlined: - return self - - super().streamline() - - for e in self.exprs: - e.streamline() - - # collapse nested :class:`And`'s of the form ``And(And(And(a, b), c), d)`` to ``And(a, b, c, d)`` - # but only if there are no parse actions or resultsNames on the nested And's - # (likewise for :class:`Or`'s and :class:`MatchFirst`'s) - if len(self.exprs) == 2: - other = self.exprs[0] - if ( - isinstance(other, self.__class__) - and not other.parseAction - and other.resultsName is None - and not other.debug - ): - self.exprs = other.exprs[:] + [self.exprs[1]] - self._defaultName = None - self.mayReturnEmpty |= other.mayReturnEmpty - self.mayIndexError |= other.mayIndexError - - other = self.exprs[-1] - if ( - isinstance(other, self.__class__) - and not other.parseAction - and other.resultsName is None - and not other.debug - ): - self.exprs = self.exprs[:-1] + other.exprs[:] - self._defaultName = None - self.mayReturnEmpty |= other.mayReturnEmpty - self.mayIndexError |= other.mayIndexError - - self.errmsg = "Expected " + str(self) - - return self - - def validate(self, validateTrace=None) -> None: - warnings.warn( - "ParserElement.validate() is deprecated, and should not be used to check for left recursion", - DeprecationWarning, - stacklevel=2, - ) - tmp = (validateTrace if validateTrace is not None else [])[:] + [self] - for e in self.exprs: - e.validate(tmp) - self._checkRecursion([]) - - def copy(self) -> ParserElement: - ret = super().copy() - ret = typing.cast(ParseExpression, ret) - ret.exprs = [e.copy() for e in self.exprs] - return ret - - def _setResultsName(self, name, listAllMatches=False): - if ( - __diag__.warn_ungrouped_named_tokens_in_collection - and Diagnostics.warn_ungrouped_named_tokens_in_collection - not in self.suppress_warnings_ - ): - for e in self.exprs: - if ( - isinstance(e, ParserElement) - and e.resultsName - and Diagnostics.warn_ungrouped_named_tokens_in_collection - not in e.suppress_warnings_ - ): - warnings.warn( - "{}: setting results name {!r} on {} expression " - "collides with {!r} on contained expression".format( - "warn_ungrouped_named_tokens_in_collection", - name, - type(self).__name__, - e.resultsName, - ), - stacklevel=3, - ) - - return super()._setResultsName(name, listAllMatches) - - # Compatibility synonyms - # fmt: off - @replaced_by_pep8(leave_whitespace) - def leaveWhitespace(self): ... - - @replaced_by_pep8(ignore_whitespace) - def ignoreWhitespace(self): ... - # fmt: on - - -class And(ParseExpression): - """ - Requires all given :class:`ParseExpression` s to be found in the given order. - Expressions may be separated by whitespace. - May be constructed using the ``'+'`` operator. - May also be constructed using the ``'-'`` operator, which will - suppress backtracking. - - Example:: - - integer = Word(nums) - name_expr = Word(alphas)[1, ...] - - expr = And([integer("id"), name_expr("name"), integer("age")]) - # more easily written as: - expr = integer("id") + name_expr("name") + integer("age") - """ - - class _ErrorStop(Empty): - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) - self.leave_whitespace() - - def _generateDefaultName(self) -> str: - return "-" - - def __init__( - self, exprs_arg: typing.Iterable[ParserElement], savelist: bool = True - ): - exprs: List[ParserElement] = list(exprs_arg) - if exprs and Ellipsis in exprs: - tmp = [] - for i, expr in enumerate(exprs): - if expr is Ellipsis: - if i < len(exprs) - 1: - skipto_arg: ParserElement = typing.cast( - ParseExpression, (Empty() + exprs[i + 1]) - ).exprs[-1] - tmp.append(SkipTo(skipto_arg)("_skipped*")) - else: - raise Exception( - "cannot construct And with sequence ending in ..." - ) - else: - tmp.append(expr) - exprs[:] = tmp - super().__init__(exprs, savelist) - if self.exprs: - self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) - if not isinstance(self.exprs[0], White): - self.set_whitespace_chars( - self.exprs[0].whiteChars, - copy_defaults=self.exprs[0].copyDefaultWhiteChars, - ) - self.skipWhitespace = self.exprs[0].skipWhitespace - else: - self.skipWhitespace = False - else: - self.mayReturnEmpty = True - self.callPreparse = True - - def streamline(self) -> ParserElement: - # collapse any _PendingSkip's - if self.exprs: - if any( - isinstance(e, ParseExpression) - and e.exprs - and isinstance(e.exprs[-1], _PendingSkip) - for e in self.exprs[:-1] - ): - deleted_expr_marker = NoMatch() - for i, e in enumerate(self.exprs[:-1]): - if e is deleted_expr_marker: - continue - if ( - isinstance(e, ParseExpression) - and e.exprs - and isinstance(e.exprs[-1], _PendingSkip) - ): - e.exprs[-1] = e.exprs[-1] + self.exprs[i + 1] - self.exprs[i + 1] = deleted_expr_marker - self.exprs = [e for e in self.exprs if e is not deleted_expr_marker] - - super().streamline() - - # link any IndentedBlocks to the prior expression - prev: ParserElement - cur: ParserElement - for prev, cur in zip(self.exprs, self.exprs[1:]): - # traverse cur or any first embedded expr of cur looking for an IndentedBlock - # (but watch out for recursive grammar) - seen = set() - while True: - if id(cur) in seen: - break - seen.add(id(cur)) - if isinstance(cur, IndentedBlock): - prev.add_parse_action( - lambda s, l, t, cur_=cur: setattr( - cur_, "parent_anchor", col(l, s) - ) - ) - break - subs = cur.recurse() - next_first = next(iter(subs), None) - if next_first is None: - break - cur = typing.cast(ParserElement, next_first) - - self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) - return self - - def parseImpl(self, instring, loc, doActions=True): - # pass False as callPreParse arg to _parse for first element, since we already - # pre-parsed the string as part of our And pre-parsing - loc, resultlist = self.exprs[0]._parse( - instring, loc, doActions, callPreParse=False - ) - errorStop = False - for e in self.exprs[1:]: - # if isinstance(e, And._ErrorStop): - if type(e) is And._ErrorStop: - errorStop = True - continue - if errorStop: - try: - loc, exprtokens = e._parse(instring, loc, doActions) - except ParseSyntaxException: - raise - except ParseBaseException as pe: - pe.__traceback__ = None - raise ParseSyntaxException._from_exception(pe) - except IndexError: - raise ParseSyntaxException( - instring, len(instring), self.errmsg, self - ) - else: - loc, exprtokens = e._parse(instring, loc, doActions) - resultlist += exprtokens - return loc, resultlist - - def __iadd__(self, other): - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return self.append(other) # And([self, other]) - - def _checkRecursion(self, parseElementList): - subRecCheckList = parseElementList[:] + [self] - for e in self.exprs: - e._checkRecursion(subRecCheckList) - if not e.mayReturnEmpty: - break - - def _generateDefaultName(self) -> str: - inner = " ".join(str(e) for e in self.exprs) - # strip off redundant inner {}'s - while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": - inner = inner[1:-1] - return "{" + inner + "}" - - -class Or(ParseExpression): - """Requires that at least one :class:`ParseExpression` is found. If - two expressions match, the expression that matches the longest - string will be used. May be constructed using the ``'^'`` - operator. - - Example:: - - # construct Or using '^' operator - - number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums)) - print(number.search_string("123 3.1416 789")) - - prints:: - - [['123'], ['3.1416'], ['789']] - """ - - def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): - super().__init__(exprs, savelist) - if self.exprs: - self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) - self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) - else: - self.mayReturnEmpty = True - - def streamline(self) -> ParserElement: - super().streamline() - if self.exprs: - self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) - self.saveAsList = any(e.saveAsList for e in self.exprs) - self.skipWhitespace = all( - e.skipWhitespace and not isinstance(e, White) for e in self.exprs - ) - else: - self.saveAsList = False - return self - - def parseImpl(self, instring, loc, doActions=True): - maxExcLoc = -1 - maxException = None - matches = [] - fatals = [] - if all(e.callPreparse for e in self.exprs): - loc = self.preParse(instring, loc) - for e in self.exprs: - try: - loc2 = e.try_parse(instring, loc, raise_fatal=True) - except ParseFatalException as pfe: - pfe.__traceback__ = None - pfe.parser_element = e - fatals.append(pfe) - maxException = None - maxExcLoc = -1 - except ParseException as err: - if not fatals: - err.__traceback__ = None - if err.loc > maxExcLoc: - maxException = err - maxExcLoc = err.loc - except IndexError: - if len(instring) > maxExcLoc: - maxException = ParseException( - instring, len(instring), e.errmsg, self - ) - maxExcLoc = len(instring) - else: - # save match among all matches, to retry longest to shortest - matches.append((loc2, e)) - - if matches: - # re-evaluate all matches in descending order of length of match, in case attached actions - # might change whether or how much they match of the input. - matches.sort(key=itemgetter(0), reverse=True) - - if not doActions: - # no further conditions or parse actions to change the selection of - # alternative, so the first match will be the best match - best_expr = matches[0][1] - return best_expr._parse(instring, loc, doActions) - - longest = -1, None - for loc1, expr1 in matches: - if loc1 <= longest[0]: - # already have a longer match than this one will deliver, we are done - return longest - - try: - loc2, toks = expr1._parse(instring, loc, doActions) - except ParseException as err: - err.__traceback__ = None - if err.loc > maxExcLoc: - maxException = err - maxExcLoc = err.loc - else: - if loc2 >= loc1: - return loc2, toks - # didn't match as much as before - elif loc2 > longest[0]: - longest = loc2, toks - - if longest != (-1, None): - return longest - - if fatals: - if len(fatals) > 1: - fatals.sort(key=lambda e: -e.loc) - if fatals[0].loc == fatals[1].loc: - fatals.sort(key=lambda e: (-e.loc, -len(str(e.parser_element)))) - max_fatal = fatals[0] - raise max_fatal - - if maxException is not None: - # infer from this check that all alternatives failed at the current position - # so emit this collective error message instead of any single error message - if maxExcLoc == loc: - maxException.msg = self.errmsg - raise maxException - else: - raise ParseException( - instring, loc, "no defined alternatives to match", self - ) - - def __ixor__(self, other): - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return self.append(other) # Or([self, other]) - - def _generateDefaultName(self) -> str: - return "{" + " ^ ".join(str(e) for e in self.exprs) + "}" - - def _setResultsName(self, name, listAllMatches=False): - if ( - __diag__.warn_multiple_tokens_in_named_alternation - and Diagnostics.warn_multiple_tokens_in_named_alternation - not in self.suppress_warnings_ - ): - if any( - isinstance(e, And) - and Diagnostics.warn_multiple_tokens_in_named_alternation - not in e.suppress_warnings_ - for e in self.exprs - ): - warnings.warn( - "{}: setting results name {!r} on {} expression " - "will return a list of all parsed tokens in an And alternative, " - "in prior versions only the first token was returned; enclose " - "contained argument in Group".format( - "warn_multiple_tokens_in_named_alternation", - name, - type(self).__name__, - ), - stacklevel=3, - ) - - return super()._setResultsName(name, listAllMatches) - - -class MatchFirst(ParseExpression): - """Requires that at least one :class:`ParseExpression` is found. If - more than one expression matches, the first one listed is the one that will - match. May be constructed using the ``'|'`` operator. - - Example:: - - # construct MatchFirst using '|' operator - - # watch the order of expressions to match - number = Word(nums) | Combine(Word(nums) + '.' + Word(nums)) - print(number.search_string("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']] - - # put more selective expression first - number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums) - print(number.search_string("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']] - """ - - def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): - super().__init__(exprs, savelist) - if self.exprs: - self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) - self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) - else: - self.mayReturnEmpty = True - - def streamline(self) -> ParserElement: - if self.streamlined: - return self - - super().streamline() - if self.exprs: - self.saveAsList = any(e.saveAsList for e in self.exprs) - self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) - self.skipWhitespace = all( - e.skipWhitespace and not isinstance(e, White) for e in self.exprs - ) - else: - self.saveAsList = False - self.mayReturnEmpty = True - return self - - def parseImpl(self, instring, loc, doActions=True): - maxExcLoc = -1 - maxException = None - - for e in self.exprs: - try: - return e._parse( - instring, - loc, - doActions, - ) - except ParseFatalException as pfe: - pfe.__traceback__ = None - pfe.parser_element = e - raise - except ParseException as err: - if err.loc > maxExcLoc: - maxException = err - maxExcLoc = err.loc - except IndexError: - if len(instring) > maxExcLoc: - maxException = ParseException( - instring, len(instring), e.errmsg, self - ) - maxExcLoc = len(instring) - - if maxException is not None: - # infer from this check that all alternatives failed at the current position - # so emit this collective error message instead of any individual error message - if maxExcLoc == loc: - maxException.msg = self.errmsg - raise maxException - else: - raise ParseException( - instring, loc, "no defined alternatives to match", self - ) - - def __ior__(self, other): - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return self.append(other) # MatchFirst([self, other]) - - def _generateDefaultName(self) -> str: - return "{" + " | ".join(str(e) for e in self.exprs) + "}" - - def _setResultsName(self, name, listAllMatches=False): - if ( - __diag__.warn_multiple_tokens_in_named_alternation - and Diagnostics.warn_multiple_tokens_in_named_alternation - not in self.suppress_warnings_ - ): - if any( - isinstance(e, And) - and Diagnostics.warn_multiple_tokens_in_named_alternation - not in e.suppress_warnings_ - for e in self.exprs - ): - warnings.warn( - "{}: setting results name {!r} on {} expression " - "will return a list of all parsed tokens in an And alternative, " - "in prior versions only the first token was returned; enclose " - "contained argument in Group".format( - "warn_multiple_tokens_in_named_alternation", - name, - type(self).__name__, - ), - stacklevel=3, - ) - - return super()._setResultsName(name, listAllMatches) - - -class Each(ParseExpression): - """Requires all given :class:`ParseExpression` s to be found, but in - any order. Expressions may be separated by whitespace. - - May be constructed using the ``'&'`` operator. - - Example:: - - color = one_of("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN") - shape_type = one_of("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON") - integer = Word(nums) - shape_attr = "shape:" + shape_type("shape") - posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn") - color_attr = "color:" + color("color") - size_attr = "size:" + integer("size") - - # use Each (using operator '&') to accept attributes in any order - # (shape and posn are required, color and size are optional) - shape_spec = shape_attr & posn_attr & Opt(color_attr) & Opt(size_attr) - - shape_spec.run_tests(''' - shape: SQUARE color: BLACK posn: 100, 120 - shape: CIRCLE size: 50 color: BLUE posn: 50,80 - color:GREEN size:20 shape:TRIANGLE posn:20,40 - ''' - ) - - prints:: - - shape: SQUARE color: BLACK posn: 100, 120 - ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']] - - color: BLACK - - posn: ['100', ',', '120'] - - x: 100 - - y: 120 - - shape: SQUARE - - - shape: CIRCLE size: 50 color: BLUE posn: 50,80 - ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']] - - color: BLUE - - posn: ['50', ',', '80'] - - x: 50 - - y: 80 - - shape: CIRCLE - - size: 50 - - - color: GREEN size: 20 shape: TRIANGLE posn: 20,40 - ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']] - - color: GREEN - - posn: ['20', ',', '40'] - - x: 20 - - y: 40 - - shape: TRIANGLE - - size: 20 - """ - - def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = True): - super().__init__(exprs, savelist) - if self.exprs: - self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) - else: - self.mayReturnEmpty = True - self.skipWhitespace = True - self.initExprGroups = True - self.saveAsList = True - - def __iand__(self, other): - if isinstance(other, str_type): - other = self._literalStringClass(other) - if not isinstance(other, ParserElement): - return NotImplemented - return self.append(other) # Each([self, other]) - - def streamline(self) -> ParserElement: - super().streamline() - if self.exprs: - self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) - else: - self.mayReturnEmpty = True - return self - - def parseImpl(self, instring, loc, doActions=True): - if self.initExprGroups: - self.opt1map = dict( - (id(e.expr), e) for e in self.exprs if isinstance(e, Opt) - ) - opt1 = [e.expr for e in self.exprs if isinstance(e, Opt)] - opt2 = [ - e - for e in self.exprs - if e.mayReturnEmpty and not isinstance(e, (Opt, Regex, ZeroOrMore)) - ] - self.optionals = opt1 + opt2 - self.multioptionals = [ - e.expr.set_results_name(e.resultsName, list_all_matches=True) - for e in self.exprs - if isinstance(e, _MultipleMatch) - ] - self.multirequired = [ - e.expr.set_results_name(e.resultsName, list_all_matches=True) - for e in self.exprs - if isinstance(e, OneOrMore) - ] - self.required = [ - e for e in self.exprs if not isinstance(e, (Opt, ZeroOrMore, OneOrMore)) - ] - self.required += self.multirequired - self.initExprGroups = False - - tmpLoc = loc - tmpReqd = self.required[:] - tmpOpt = self.optionals[:] - multis = self.multioptionals[:] - matchOrder = [] - - keepMatching = True - failed = [] - fatals = [] - while keepMatching: - tmpExprs = tmpReqd + tmpOpt + multis - failed.clear() - fatals.clear() - for e in tmpExprs: - try: - tmpLoc = e.try_parse(instring, tmpLoc, raise_fatal=True) - except ParseFatalException as pfe: - pfe.__traceback__ = None - pfe.parser_element = e - fatals.append(pfe) - failed.append(e) - except ParseException: - failed.append(e) - else: - matchOrder.append(self.opt1map.get(id(e), e)) - if e in tmpReqd: - tmpReqd.remove(e) - elif e in tmpOpt: - tmpOpt.remove(e) - if len(failed) == len(tmpExprs): - keepMatching = False - - # look for any ParseFatalExceptions - if fatals: - if len(fatals) > 1: - fatals.sort(key=lambda e: -e.loc) - if fatals[0].loc == fatals[1].loc: - fatals.sort(key=lambda e: (-e.loc, -len(str(e.parser_element)))) - max_fatal = fatals[0] - raise max_fatal - - if tmpReqd: - missing = ", ".join([str(e) for e in tmpReqd]) - raise ParseException( - instring, - loc, - f"Missing one or more required elements ({missing})", - ) - - # add any unmatched Opts, in case they have default values defined - matchOrder += [e for e in self.exprs if isinstance(e, Opt) and e.expr in tmpOpt] - - total_results = ParseResults([]) - for e in matchOrder: - loc, results = e._parse(instring, loc, doActions) - total_results += results - - return loc, total_results - - def _generateDefaultName(self) -> str: - return "{" + " & ".join(str(e) for e in self.exprs) + "}" - - -class ParseElementEnhance(ParserElement): - """Abstract subclass of :class:`ParserElement`, for combining and - post-processing parsed tokens. - """ - - def __init__(self, expr: Union[ParserElement, str], savelist: bool = False): - super().__init__(savelist) - if isinstance(expr, str_type): - expr_str = typing.cast(str, expr) - if issubclass(self._literalStringClass, Token): - expr = self._literalStringClass(expr_str) # type: ignore[call-arg] - elif issubclass(type(self), self._literalStringClass): - expr = Literal(expr_str) - else: - expr = self._literalStringClass(Literal(expr_str)) # type: ignore[assignment, call-arg] - expr = typing.cast(ParserElement, expr) - self.expr = expr - if expr is not None: - self.mayIndexError = expr.mayIndexError - self.mayReturnEmpty = expr.mayReturnEmpty - self.set_whitespace_chars( - expr.whiteChars, copy_defaults=expr.copyDefaultWhiteChars - ) - self.skipWhitespace = expr.skipWhitespace - self.saveAsList = expr.saveAsList - self.callPreparse = expr.callPreparse - self.ignoreExprs.extend(expr.ignoreExprs) - - def recurse(self) -> List[ParserElement]: - return [self.expr] if self.expr is not None else [] - - def parseImpl(self, instring, loc, doActions=True): - if self.expr is not None: - try: - return self.expr._parse(instring, loc, doActions, callPreParse=False) - except ParseBaseException as pbe: - pbe.msg = self.errmsg - raise - else: - raise ParseException(instring, loc, "No expression defined", self) - - def leave_whitespace(self, recursive: bool = True) -> ParserElement: - super().leave_whitespace(recursive) - - if recursive: - if self.expr is not None: - self.expr = self.expr.copy() - self.expr.leave_whitespace(recursive) - return self - - def ignore_whitespace(self, recursive: bool = True) -> ParserElement: - super().ignore_whitespace(recursive) - - if recursive: - if self.expr is not None: - self.expr = self.expr.copy() - self.expr.ignore_whitespace(recursive) - return self - - def ignore(self, other) -> ParserElement: - if isinstance(other, Suppress): - if other not in self.ignoreExprs: - super().ignore(other) - if self.expr is not None: - self.expr.ignore(self.ignoreExprs[-1]) - else: - super().ignore(other) - if self.expr is not None: - self.expr.ignore(self.ignoreExprs[-1]) - return self - - def streamline(self) -> ParserElement: - super().streamline() - if self.expr is not None: - self.expr.streamline() - return self - - def _checkRecursion(self, parseElementList): - if self in parseElementList: - raise RecursiveGrammarException(parseElementList + [self]) - subRecCheckList = parseElementList[:] + [self] - if self.expr is not None: - self.expr._checkRecursion(subRecCheckList) - - def validate(self, validateTrace=None) -> None: - warnings.warn( - "ParserElement.validate() is deprecated, and should not be used to check for left recursion", - DeprecationWarning, - stacklevel=2, - ) - if validateTrace is None: - validateTrace = [] - tmp = validateTrace[:] + [self] - if self.expr is not None: - self.expr.validate(tmp) - self._checkRecursion([]) - - def _generateDefaultName(self) -> str: - return f"{self.__class__.__name__}:({str(self.expr)})" - - # Compatibility synonyms - # fmt: off - @replaced_by_pep8(leave_whitespace) - def leaveWhitespace(self): ... - - @replaced_by_pep8(ignore_whitespace) - def ignoreWhitespace(self): ... - # fmt: on - - -class IndentedBlock(ParseElementEnhance): - """ - Expression to match one or more expressions at a given indentation level. - Useful for parsing text where structure is implied by indentation (like Python source code). - """ - - class _Indent(Empty): - def __init__(self, ref_col: int): - super().__init__() - self.errmsg = f"expected indent at column {ref_col}" - self.add_condition(lambda s, l, t: col(l, s) == ref_col) - - class _IndentGreater(Empty): - def __init__(self, ref_col: int): - super().__init__() - self.errmsg = f"expected indent at column greater than {ref_col}" - self.add_condition(lambda s, l, t: col(l, s) > ref_col) - - def __init__( - self, expr: ParserElement, *, recursive: bool = False, grouped: bool = True - ): - super().__init__(expr, savelist=True) - # if recursive: - # raise NotImplementedError("IndentedBlock with recursive is not implemented") - self._recursive = recursive - self._grouped = grouped - self.parent_anchor = 1 - - def parseImpl(self, instring, loc, doActions=True): - # advance parse position to non-whitespace by using an Empty() - # this should be the column to be used for all subsequent indented lines - anchor_loc = Empty().preParse(instring, loc) - - # see if self.expr matches at the current location - if not it will raise an exception - # and no further work is necessary - self.expr.try_parse(instring, anchor_loc, do_actions=doActions) - - indent_col = col(anchor_loc, instring) - peer_detect_expr = self._Indent(indent_col) - - inner_expr = Empty() + peer_detect_expr + self.expr - if self._recursive: - sub_indent = self._IndentGreater(indent_col) - nested_block = IndentedBlock( - self.expr, recursive=self._recursive, grouped=self._grouped - ) - nested_block.set_debug(self.debug) - nested_block.parent_anchor = indent_col - inner_expr += Opt(sub_indent + nested_block) - - inner_expr.set_name(f"inner {hex(id(inner_expr))[-4:].upper()}@{indent_col}") - block = OneOrMore(inner_expr) - - trailing_undent = self._Indent(self.parent_anchor) | StringEnd() - - if self._grouped: - wrapper = Group - else: - wrapper = lambda expr: expr - return (wrapper(block) + Optional(trailing_undent)).parseImpl( - instring, anchor_loc, doActions - ) - - -class AtStringStart(ParseElementEnhance): - """Matches if expression matches at the beginning of the parse - string:: - - AtStringStart(Word(nums)).parse_string("123") - # prints ["123"] - - AtStringStart(Word(nums)).parse_string(" 123") - # raises ParseException - """ - - def __init__(self, expr: Union[ParserElement, str]): - super().__init__(expr) - self.callPreparse = False - - def parseImpl(self, instring, loc, doActions=True): - if loc != 0: - raise ParseException(instring, loc, "not found at string start") - return super().parseImpl(instring, loc, doActions) - - -class AtLineStart(ParseElementEnhance): - r"""Matches if an expression matches at the beginning of a line within - the parse string - - Example:: - - test = '''\ - AAA this line - AAA and this line - AAA but not this one - B AAA and definitely not this one - ''' - - for t in (AtLineStart('AAA') + rest_of_line).search_string(test): - print(t) - - prints:: - - ['AAA', ' this line'] - ['AAA', ' and this line'] - - """ - - def __init__(self, expr: Union[ParserElement, str]): - super().__init__(expr) - self.callPreparse = False - - def parseImpl(self, instring, loc, doActions=True): - if col(loc, instring) != 1: - raise ParseException(instring, loc, "not found at line start") - return super().parseImpl(instring, loc, doActions) - - -class FollowedBy(ParseElementEnhance): - """Lookahead matching of the given parse expression. - ``FollowedBy`` does *not* advance the parsing position within - the input string, it only verifies that the specified parse - expression matches at the current position. ``FollowedBy`` - always returns a null token list. If any results names are defined - in the lookahead expression, those *will* be returned for access by - name. - - Example:: - - # use FollowedBy to match a label only if it is followed by a ':' - data_word = Word(alphas) - label = data_word + FollowedBy(':') - attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) - - attr_expr[1, ...].parse_string("shape: SQUARE color: BLACK posn: upper left").pprint() - - prints:: - - [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']] - """ - - def __init__(self, expr: Union[ParserElement, str]): - super().__init__(expr) - self.mayReturnEmpty = True - - def parseImpl(self, instring, loc, doActions=True): - # by using self._expr.parse and deleting the contents of the returned ParseResults list - # we keep any named results that were defined in the FollowedBy expression - _, ret = self.expr._parse(instring, loc, doActions=doActions) - del ret[:] - - return loc, ret - - -class PrecededBy(ParseElementEnhance): - """Lookbehind matching of the given parse expression. - ``PrecededBy`` does not advance the parsing position within the - input string, it only verifies that the specified parse expression - matches prior to the current position. ``PrecededBy`` always - returns a null token list, but if a results name is defined on the - given expression, it is returned. - - Parameters: - - - ``expr`` - expression that must match prior to the current parse - location - - ``retreat`` - (default= ``None``) - (int) maximum number of characters - to lookbehind prior to the current parse location - - If the lookbehind expression is a string, :class:`Literal`, - :class:`Keyword`, or a :class:`Word` or :class:`CharsNotIn` - with a specified exact or maximum length, then the retreat - parameter is not required. Otherwise, retreat must be specified to - give a maximum number of characters to look back from - the current parse position for a lookbehind match. - - Example:: - - # VB-style variable names with type prefixes - int_var = PrecededBy("#") + pyparsing_common.identifier - str_var = PrecededBy("$") + pyparsing_common.identifier - - """ - - def __init__( - self, expr: Union[ParserElement, str], retreat: typing.Optional[int] = None - ): - super().__init__(expr) - self.expr = self.expr().leave_whitespace() - self.mayReturnEmpty = True - self.mayIndexError = False - self.exact = False - if isinstance(expr, str_type): - expr = typing.cast(str, expr) - retreat = len(expr) - self.exact = True - elif isinstance(expr, (Literal, Keyword)): - retreat = expr.matchLen - self.exact = True - elif isinstance(expr, (Word, CharsNotIn)) and expr.maxLen != _MAX_INT: - retreat = expr.maxLen - self.exact = True - elif isinstance(expr, PositionToken): - retreat = 0 - self.exact = True - self.retreat = retreat - self.errmsg = "not preceded by " + str(expr) - self.skipWhitespace = False - self.parseAction.append(lambda s, l, t: t.__delitem__(slice(None, None))) - - def parseImpl(self, instring, loc=0, doActions=True): - if self.exact: - if loc < self.retreat: - raise ParseException(instring, loc, self.errmsg) - start = loc - self.retreat - _, ret = self.expr._parse(instring, start) - else: - # retreat specified a maximum lookbehind window, iterate - test_expr = self.expr + StringEnd() - instring_slice = instring[max(0, loc - self.retreat) : loc] - last_expr = ParseException(instring, loc, self.errmsg) - for offset in range(1, min(loc, self.retreat + 1) + 1): - try: - # print('trying', offset, instring_slice, repr(instring_slice[loc - offset:])) - _, ret = test_expr._parse( - instring_slice, len(instring_slice) - offset - ) - except ParseBaseException as pbe: - last_expr = pbe - else: - break - else: - raise last_expr - return loc, ret - - -class Located(ParseElementEnhance): - """ - Decorates a returned token with its starting and ending - locations in the input string. - - This helper adds the following results names: - - - ``locn_start`` - location where matched expression begins - - ``locn_end`` - location where matched expression ends - - ``value`` - the actual parsed results - - Be careful if the input text contains ```` characters, you - may want to call :class:`ParserElement.parse_with_tabs` - - Example:: - - wd = Word(alphas) - for match in Located(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): - print(match) - - prints:: - - [0, ['ljsdf'], 5] - [8, ['lksdjjf'], 15] - [18, ['lkkjj'], 23] - - """ - - def parseImpl(self, instring, loc, doActions=True): - start = loc - loc, tokens = self.expr._parse(instring, start, doActions, callPreParse=False) - ret_tokens = ParseResults([start, tokens, loc]) - ret_tokens["locn_start"] = start - ret_tokens["value"] = tokens - ret_tokens["locn_end"] = loc - if self.resultsName: - # must return as a list, so that the name will be attached to the complete group - return loc, [ret_tokens] - else: - return loc, ret_tokens - - -class NotAny(ParseElementEnhance): - """ - Lookahead to disallow matching with the given parse expression. - ``NotAny`` does *not* advance the parsing position within the - input string, it only verifies that the specified parse expression - does *not* match at the current position. Also, ``NotAny`` does - *not* skip over leading whitespace. ``NotAny`` always returns - a null token list. May be constructed using the ``'~'`` operator. - - Example:: - - AND, OR, NOT = map(CaselessKeyword, "AND OR NOT".split()) - - # take care not to mistake keywords for identifiers - ident = ~(AND | OR | NOT) + Word(alphas) - boolean_term = Opt(NOT) + ident - - # very crude boolean expression - to support parenthesis groups and - # operation hierarchy, use infix_notation - boolean_expr = boolean_term + ((AND | OR) + boolean_term)[...] - - # integers that are followed by "." are actually floats - integer = Word(nums) + ~Char(".") - """ - - def __init__(self, expr: Union[ParserElement, str]): - super().__init__(expr) - # do NOT use self.leave_whitespace(), don't want to propagate to exprs - # self.leave_whitespace() - self.skipWhitespace = False - - self.mayReturnEmpty = True - self.errmsg = "Found unwanted token, " + str(self.expr) - - def parseImpl(self, instring, loc, doActions=True): - if self.expr.can_parse_next(instring, loc, do_actions=doActions): - raise ParseException(instring, loc, self.errmsg, self) - return loc, [] - - def _generateDefaultName(self) -> str: - return "~{" + str(self.expr) + "}" - - -class _MultipleMatch(ParseElementEnhance): - def __init__( - self, - expr: Union[str, ParserElement], - stop_on: typing.Optional[Union[ParserElement, str]] = None, - *, - stopOn: typing.Optional[Union[ParserElement, str]] = None, - ): - super().__init__(expr) - stopOn = stopOn or stop_on - self.saveAsList = True - ender = stopOn - if isinstance(ender, str_type): - ender = self._literalStringClass(ender) - self.stopOn(ender) - - def stopOn(self, ender) -> ParserElement: - if isinstance(ender, str_type): - ender = self._literalStringClass(ender) - self.not_ender = ~ender if ender is not None else None - return self - - def parseImpl(self, instring, loc, doActions=True): - self_expr_parse = self.expr._parse - self_skip_ignorables = self._skipIgnorables - check_ender = self.not_ender is not None - if check_ender: - try_not_ender = self.not_ender.try_parse - - # must be at least one (but first see if we are the stopOn sentinel; - # if so, fail) - if check_ender: - try_not_ender(instring, loc) - loc, tokens = self_expr_parse(instring, loc, doActions) - try: - hasIgnoreExprs = not not self.ignoreExprs - while 1: - if check_ender: - try_not_ender(instring, loc) - if hasIgnoreExprs: - preloc = self_skip_ignorables(instring, loc) - else: - preloc = loc - loc, tmptokens = self_expr_parse(instring, preloc, doActions) - tokens += tmptokens - except (ParseException, IndexError): - pass - - return loc, tokens - - def _setResultsName(self, name, listAllMatches=False): - if ( - __diag__.warn_ungrouped_named_tokens_in_collection - and Diagnostics.warn_ungrouped_named_tokens_in_collection - not in self.suppress_warnings_ - ): - for e in [self.expr] + self.expr.recurse(): - if ( - isinstance(e, ParserElement) - and e.resultsName - and Diagnostics.warn_ungrouped_named_tokens_in_collection - not in e.suppress_warnings_ - ): - warnings.warn( - "{}: setting results name {!r} on {} expression " - "collides with {!r} on contained expression".format( - "warn_ungrouped_named_tokens_in_collection", - name, - type(self).__name__, - e.resultsName, - ), - stacklevel=3, - ) - - return super()._setResultsName(name, listAllMatches) - - -class OneOrMore(_MultipleMatch): - """ - Repetition of one or more of the given expression. - - Parameters: - - - ``expr`` - expression that must match one or more times - - ``stop_on`` - (default= ``None``) - expression for a terminating sentinel - (only required if the sentinel would ordinarily match the repetition - expression) - - Example:: - - data_word = Word(alphas) - label = data_word + FollowedBy(':') - attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).set_parse_action(' '.join)) - - text = "shape: SQUARE posn: upper left color: BLACK" - attr_expr[1, ...].parse_string(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']] - - # use stop_on attribute for OneOrMore to avoid reading label string as part of the data - attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) - OneOrMore(attr_expr).parse_string(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']] - - # could also be written as - (attr_expr * (1,)).parse_string(text).pprint() - """ - - def _generateDefaultName(self) -> str: - return "{" + str(self.expr) + "}..." - - -class ZeroOrMore(_MultipleMatch): - """ - Optional repetition of zero or more of the given expression. - - Parameters: - - - ``expr`` - expression that must match zero or more times - - ``stop_on`` - expression for a terminating sentinel - (only required if the sentinel would ordinarily match the repetition - expression) - (default= ``None``) - - Example: similar to :class:`OneOrMore` - """ - - def __init__( - self, - expr: Union[str, ParserElement], - stop_on: typing.Optional[Union[ParserElement, str]] = None, - *, - stopOn: typing.Optional[Union[ParserElement, str]] = None, - ): - super().__init__(expr, stopOn=stopOn or stop_on) - self.mayReturnEmpty = True - - def parseImpl(self, instring, loc, doActions=True): - try: - return super().parseImpl(instring, loc, doActions) - except (ParseException, IndexError): - return loc, ParseResults([], name=self.resultsName) - - def _generateDefaultName(self) -> str: - return "[" + str(self.expr) + "]..." - - -class DelimitedList(ParseElementEnhance): - def __init__( - self, - expr: Union[str, ParserElement], - delim: Union[str, ParserElement] = ",", - combine: bool = False, - min: typing.Optional[int] = None, - max: typing.Optional[int] = None, - *, - allow_trailing_delim: bool = False, - ): - """Helper to define a delimited list of expressions - the delimiter - defaults to ','. By default, the list elements and delimiters can - have intervening whitespace, and comments, but this can be - overridden by passing ``combine=True`` in the constructor. If - ``combine`` is set to ``True``, the matching tokens are - returned as a single token string, with the delimiters included; - otherwise, the matching tokens are returned as a list of tokens, - with the delimiters suppressed. - - If ``allow_trailing_delim`` is set to True, then the list may end with - a delimiter. - - Example:: - - DelimitedList(Word(alphas)).parse_string("aa,bb,cc") # -> ['aa', 'bb', 'cc'] - DelimitedList(Word(hexnums), delim=':', combine=True).parse_string("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE'] - """ - if isinstance(expr, str_type): - expr = ParserElement._literalStringClass(expr) - expr = typing.cast(ParserElement, expr) - - if min is not None: - if min < 1: - raise ValueError("min must be greater than 0") - if max is not None: - if min is not None and max < min: - raise ValueError("max must be greater than, or equal to min") - - self.content = expr - self.raw_delim = str(delim) - self.delim = delim - self.combine = combine - if not combine: - self.delim = Suppress(delim) - self.min = min or 1 - self.max = max - self.allow_trailing_delim = allow_trailing_delim - - delim_list_expr = self.content + (self.delim + self.content) * ( - self.min - 1, - None if self.max is None else self.max - 1, - ) - if self.allow_trailing_delim: - delim_list_expr += Opt(self.delim) - - if self.combine: - delim_list_expr = Combine(delim_list_expr) - - super().__init__(delim_list_expr, savelist=True) - - def _generateDefaultName(self) -> str: - return "{0} [{1} {0}]...".format(self.content.streamline(), self.raw_delim) - - -class _NullToken: - def __bool__(self): - return False - - def __str__(self): - return "" - - -class Opt(ParseElementEnhance): - """ - Optional matching of the given expression. - - Parameters: - - - ``expr`` - expression that must match zero or more times - - ``default`` (optional) - value to be returned if the optional expression is not found. - - Example:: - - # US postal code can be a 5-digit zip, plus optional 4-digit qualifier - zip = Combine(Word(nums, exact=5) + Opt('-' + Word(nums, exact=4))) - zip.run_tests(''' - # traditional ZIP code - 12345 - - # ZIP+4 form - 12101-0001 - - # invalid ZIP - 98765- - ''') - - prints:: - - # traditional ZIP code - 12345 - ['12345'] - - # ZIP+4 form - 12101-0001 - ['12101-0001'] - - # invalid ZIP - 98765- - ^ - FAIL: Expected end of text (at char 5), (line:1, col:6) - """ - - __optionalNotMatched = _NullToken() - - def __init__( - self, expr: Union[ParserElement, str], default: Any = __optionalNotMatched - ): - super().__init__(expr, savelist=False) - self.saveAsList = self.expr.saveAsList - self.defaultValue = default - self.mayReturnEmpty = True - - def parseImpl(self, instring, loc, doActions=True): - self_expr = self.expr - try: - loc, tokens = self_expr._parse(instring, loc, doActions, callPreParse=False) - except (ParseException, IndexError): - default_value = self.defaultValue - if default_value is not self.__optionalNotMatched: - if self_expr.resultsName: - tokens = ParseResults([default_value]) - tokens[self_expr.resultsName] = default_value - else: - tokens = [default_value] - else: - tokens = [] - return loc, tokens - - def _generateDefaultName(self) -> str: - inner = str(self.expr) - # strip off redundant inner {}'s - while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": - inner = inner[1:-1] - return "[" + inner + "]" - - -Optional = Opt - - -class SkipTo(ParseElementEnhance): - """ - Token for skipping over all undefined text until the matched - expression is found. - - Parameters: - - - ``expr`` - target expression marking the end of the data to be skipped - - ``include`` - if ``True``, the target expression is also parsed - (the skipped text and target expression are returned as a 2-element - list) (default= ``False``). - - ``ignore`` - (default= ``None``) used to define grammars (typically quoted strings and - comments) that might contain false matches to the target expression - - ``fail_on`` - (default= ``None``) define expressions that are not allowed to be - included in the skipped test; if found before the target expression is found, - the :class:`SkipTo` is not a match - - Example:: - - report = ''' - Outstanding Issues Report - 1 Jan 2000 - - # | Severity | Description | Days Open - -----+----------+-------------------------------------------+----------- - 101 | Critical | Intermittent system crash | 6 - 94 | Cosmetic | Spelling error on Login ('log|n') | 14 - 79 | Minor | System slow when running too many reports | 47 - ''' - integer = Word(nums) - SEP = Suppress('|') - # use SkipTo to simply match everything up until the next SEP - # - ignore quoted strings, so that a '|' character inside a quoted string does not match - # - parse action will call token.strip() for each matched token, i.e., the description body - string_data = SkipTo(SEP, ignore=quoted_string) - string_data.set_parse_action(token_map(str.strip)) - ticket_expr = (integer("issue_num") + SEP - + string_data("sev") + SEP - + string_data("desc") + SEP - + integer("days_open")) - - for tkt in ticket_expr.search_string(report): - print tkt.dump() - - prints:: - - ['101', 'Critical', 'Intermittent system crash', '6'] - - days_open: '6' - - desc: 'Intermittent system crash' - - issue_num: '101' - - sev: 'Critical' - ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14'] - - days_open: '14' - - desc: "Spelling error on Login ('log|n')" - - issue_num: '94' - - sev: 'Cosmetic' - ['79', 'Minor', 'System slow when running too many reports', '47'] - - days_open: '47' - - desc: 'System slow when running too many reports' - - issue_num: '79' - - sev: 'Minor' - """ - - def __init__( - self, - other: Union[ParserElement, str], - include: bool = False, - ignore: typing.Optional[Union[ParserElement, str]] = None, - fail_on: typing.Optional[Union[ParserElement, str]] = None, - *, - failOn: typing.Optional[Union[ParserElement, str]] = None, - ): - super().__init__(other) - failOn = failOn or fail_on - if ignore is not None: - self.ignore(ignore) - self.mayReturnEmpty = True - self.mayIndexError = False - self.includeMatch = include - self.saveAsList = False - if isinstance(failOn, str_type): - self.failOn = self._literalStringClass(failOn) - else: - self.failOn = failOn - self.errmsg = "No match found for " + str(self.expr) - - def parseImpl(self, instring, loc, doActions=True): - startloc = loc - instrlen = len(instring) - self_expr_parse = self.expr._parse - self_failOn_canParseNext = ( - self.failOn.canParseNext if self.failOn is not None else None - ) - self_preParse = self.preParse if self.callPreparse else None - - tmploc = loc - while tmploc <= instrlen: - if self_failOn_canParseNext is not None: - # break if failOn expression matches - if self_failOn_canParseNext(instring, tmploc): - break - - if self_preParse is not None: - # skip grammar-ignored expressions - tmploc = self_preParse(instring, tmploc) - - try: - self_expr_parse(instring, tmploc, doActions=False, callPreParse=False) - except (ParseException, IndexError): - # no match, advance loc in string - tmploc += 1 - else: - # matched skipto expr, done - break - - else: - # ran off the end of the input string without matching skipto expr, fail - raise ParseException(instring, loc, self.errmsg, self) - - # build up return values - loc = tmploc - skiptext = instring[startloc:loc] - skipresult = ParseResults(skiptext) - - if self.includeMatch: - loc, mat = self_expr_parse(instring, loc, doActions, callPreParse=False) - skipresult += mat - - return loc, skipresult - - -class Forward(ParseElementEnhance): - """ - Forward declaration of an expression to be defined later - - used for recursive grammars, such as algebraic infix notation. - When the expression is known, it is assigned to the ``Forward`` - variable using the ``'<<'`` operator. - - Note: take care when assigning to ``Forward`` not to overlook - precedence of operators. - - Specifically, ``'|'`` has a lower precedence than ``'<<'``, so that:: - - fwd_expr << a | b | c - - will actually be evaluated as:: - - (fwd_expr << a) | b | c - - thereby leaving b and c out as parseable alternatives. It is recommended that you - explicitly group the values inserted into the ``Forward``:: - - fwd_expr << (a | b | c) - - Converting to use the ``'<<='`` operator instead will avoid this problem. - - See :class:`ParseResults.pprint` for an example of a recursive - parser created using ``Forward``. - """ - - def __init__(self, other: typing.Optional[Union[ParserElement, str]] = None): - self.caller_frame = traceback.extract_stack(limit=2)[0] - super().__init__(other, savelist=False) # type: ignore[arg-type] - self.lshift_line = None - - def __lshift__(self, other) -> "Forward": - if hasattr(self, "caller_frame"): - del self.caller_frame - if isinstance(other, str_type): - other = self._literalStringClass(other) - - if not isinstance(other, ParserElement): - return NotImplemented - - self.expr = other - self.streamlined = other.streamlined - self.mayIndexError = self.expr.mayIndexError - self.mayReturnEmpty = self.expr.mayReturnEmpty - self.set_whitespace_chars( - self.expr.whiteChars, copy_defaults=self.expr.copyDefaultWhiteChars - ) - self.skipWhitespace = self.expr.skipWhitespace - self.saveAsList = self.expr.saveAsList - self.ignoreExprs.extend(self.expr.ignoreExprs) - self.lshift_line = traceback.extract_stack(limit=2)[-2] # type: ignore[assignment] - return self - - def __ilshift__(self, other) -> "Forward": - if not isinstance(other, ParserElement): - return NotImplemented - - return self << other - - def __or__(self, other) -> "ParserElement": - caller_line = traceback.extract_stack(limit=2)[-2] - if ( - __diag__.warn_on_match_first_with_lshift_operator - and caller_line == self.lshift_line - and Diagnostics.warn_on_match_first_with_lshift_operator - not in self.suppress_warnings_ - ): - warnings.warn( - "using '<<' operator with '|' is probably an error, use '<<='", - stacklevel=2, - ) - ret = super().__or__(other) - return ret - - def __del__(self): - # see if we are getting dropped because of '=' reassignment of var instead of '<<=' or '<<' - if ( - self.expr is None - and __diag__.warn_on_assignment_to_Forward - and Diagnostics.warn_on_assignment_to_Forward not in self.suppress_warnings_ - ): - warnings.warn_explicit( - "Forward defined here but no expression attached later using '<<=' or '<<'", - UserWarning, - filename=self.caller_frame.filename, - lineno=self.caller_frame.lineno, - ) - - def parseImpl(self, instring, loc, doActions=True): - if ( - self.expr is None - and __diag__.warn_on_parse_using_empty_Forward - and Diagnostics.warn_on_parse_using_empty_Forward - not in self.suppress_warnings_ - ): - # walk stack until parse_string, scan_string, search_string, or transform_string is found - parse_fns = ( - "parse_string", - "scan_string", - "search_string", - "transform_string", - ) - tb = traceback.extract_stack(limit=200) - for i, frm in enumerate(reversed(tb), start=1): - if frm.name in parse_fns: - stacklevel = i + 1 - break - else: - stacklevel = 2 - warnings.warn( - "Forward expression was never assigned a value, will not parse any input", - stacklevel=stacklevel, - ) - if not ParserElement._left_recursion_enabled: - return super().parseImpl(instring, loc, doActions) - # ## Bounded Recursion algorithm ## - # Recursion only needs to be processed at ``Forward`` elements, since they are - # the only ones that can actually refer to themselves. The general idea is - # to handle recursion stepwise: We start at no recursion, then recurse once, - # recurse twice, ..., until more recursion offers no benefit (we hit the bound). - # - # The "trick" here is that each ``Forward`` gets evaluated in two contexts - # - to *match* a specific recursion level, and - # - to *search* the bounded recursion level - # and the two run concurrently. The *search* must *match* each recursion level - # to find the best possible match. This is handled by a memo table, which - # provides the previous match to the next level match attempt. - # - # See also "Left Recursion in Parsing Expression Grammars", Medeiros et al. - # - # There is a complication since we not only *parse* but also *transform* via - # actions: We do not want to run the actions too often while expanding. Thus, - # we expand using `doActions=False` and only run `doActions=True` if the next - # recursion level is acceptable. - with ParserElement.recursion_lock: - memo = ParserElement.recursion_memos - try: - # we are parsing at a specific recursion expansion - use it as-is - prev_loc, prev_result = memo[loc, self, doActions] - if isinstance(prev_result, Exception): - raise prev_result - return prev_loc, prev_result.copy() - except KeyError: - act_key = (loc, self, True) - peek_key = (loc, self, False) - # we are searching for the best recursion expansion - keep on improving - # both `doActions` cases must be tracked separately here! - prev_loc, prev_peek = memo[peek_key] = ( - loc - 1, - ParseException( - instring, loc, "Forward recursion without base case", self - ), - ) - if doActions: - memo[act_key] = memo[peek_key] - while True: - try: - new_loc, new_peek = super().parseImpl(instring, loc, False) - except ParseException: - # we failed before getting any match – do not hide the error - if isinstance(prev_peek, Exception): - raise - new_loc, new_peek = prev_loc, prev_peek - # the match did not get better: we are done - if new_loc <= prev_loc: - if doActions: - # replace the match for doActions=False as well, - # in case the action did backtrack - prev_loc, prev_result = memo[peek_key] = memo[act_key] - del memo[peek_key], memo[act_key] - return prev_loc, prev_result.copy() - del memo[peek_key] - return prev_loc, prev_peek.copy() - # the match did get better: see if we can improve further - else: - if doActions: - try: - memo[act_key] = super().parseImpl(instring, loc, True) - except ParseException as e: - memo[peek_key] = memo[act_key] = (new_loc, e) - raise - prev_loc, prev_peek = memo[peek_key] = new_loc, new_peek - - def leave_whitespace(self, recursive: bool = True) -> ParserElement: - self.skipWhitespace = False - return self - - def ignore_whitespace(self, recursive: bool = True) -> ParserElement: - self.skipWhitespace = True - return self - - def streamline(self) -> ParserElement: - if not self.streamlined: - self.streamlined = True - if self.expr is not None: - self.expr.streamline() - return self - - def validate(self, validateTrace=None) -> None: - warnings.warn( - "ParserElement.validate() is deprecated, and should not be used to check for left recursion", - DeprecationWarning, - stacklevel=2, - ) - if validateTrace is None: - validateTrace = [] - - if self not in validateTrace: - tmp = validateTrace[:] + [self] - if self.expr is not None: - self.expr.validate(tmp) - self._checkRecursion([]) - - def _generateDefaultName(self) -> str: - # Avoid infinite recursion by setting a temporary _defaultName - self._defaultName = ": ..." - - # Use the string representation of main expression. - retString = "..." - try: - if self.expr is not None: - retString = str(self.expr)[:1000] - else: - retString = "None" - finally: - return self.__class__.__name__ + ": " + retString - - def copy(self) -> ParserElement: - if self.expr is not None: - return super().copy() - else: - ret = Forward() - ret <<= self - return ret - - def _setResultsName(self, name, list_all_matches=False): - if ( - __diag__.warn_name_set_on_empty_Forward - and Diagnostics.warn_name_set_on_empty_Forward - not in self.suppress_warnings_ - ): - if self.expr is None: - warnings.warn( - "{}: setting results name {!r} on {} expression " - "that has no contained expression".format( - "warn_name_set_on_empty_Forward", name, type(self).__name__ - ), - stacklevel=3, - ) - - return super()._setResultsName(name, list_all_matches) - - # Compatibility synonyms - # fmt: off - @replaced_by_pep8(leave_whitespace) - def leaveWhitespace(self): ... - - @replaced_by_pep8(ignore_whitespace) - def ignoreWhitespace(self): ... - # fmt: on - - -class TokenConverter(ParseElementEnhance): - """ - Abstract subclass of :class:`ParseExpression`, for converting parsed results. - """ - - def __init__(self, expr: Union[ParserElement, str], savelist=False): - super().__init__(expr) # , savelist) - self.saveAsList = False - - -class Combine(TokenConverter): - """Converter to concatenate all matching tokens to a single string. - By default, the matching patterns must also be contiguous in the - input string; this can be disabled by specifying - ``'adjacent=False'`` in the constructor. - - Example:: - - real = Word(nums) + '.' + Word(nums) - print(real.parse_string('3.1416')) # -> ['3', '.', '1416'] - # will also erroneously match the following - print(real.parse_string('3. 1416')) # -> ['3', '.', '1416'] - - real = Combine(Word(nums) + '.' + Word(nums)) - print(real.parse_string('3.1416')) # -> ['3.1416'] - # no match when there are internal spaces - print(real.parse_string('3. 1416')) # -> Exception: Expected W:(0123...) - """ - - def __init__( - self, - expr: ParserElement, - join_string: str = "", - adjacent: bool = True, - *, - joinString: typing.Optional[str] = None, - ): - super().__init__(expr) - joinString = joinString if joinString is not None else join_string - # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself - if adjacent: - self.leave_whitespace() - self.adjacent = adjacent - self.skipWhitespace = True - self.joinString = joinString - self.callPreparse = True - - def ignore(self, other) -> ParserElement: - if self.adjacent: - ParserElement.ignore(self, other) - else: - super().ignore(other) - return self - - def postParse(self, instring, loc, tokenlist): - retToks = tokenlist.copy() - del retToks[:] - retToks += ParseResults( - ["".join(tokenlist._asStringList(self.joinString))], modal=self.modalResults - ) - - if self.resultsName and retToks.haskeys(): - return [retToks] - else: - return retToks - - -class Group(TokenConverter): - """Converter to return the matched tokens as a list - useful for - returning tokens of :class:`ZeroOrMore` and :class:`OneOrMore` expressions. - - The optional ``aslist`` argument when set to True will return the - parsed tokens as a Python list instead of a pyparsing ParseResults. - - Example:: - - ident = Word(alphas) - num = Word(nums) - term = ident | num - func = ident + Opt(DelimitedList(term)) - print(func.parse_string("fn a, b, 100")) - # -> ['fn', 'a', 'b', '100'] - - func = ident + Group(Opt(DelimitedList(term))) - print(func.parse_string("fn a, b, 100")) - # -> ['fn', ['a', 'b', '100']] - """ - - def __init__(self, expr: ParserElement, aslist: bool = False): - super().__init__(expr) - self.saveAsList = True - self._asPythonList = aslist - - def postParse(self, instring, loc, tokenlist): - if self._asPythonList: - return ParseResults.List( - tokenlist.asList() - if isinstance(tokenlist, ParseResults) - else list(tokenlist) - ) - else: - return [tokenlist] - - -class Dict(TokenConverter): - """Converter to return a repetitive expression as a list, but also - as a dictionary. Each element can also be referenced using the first - token in the expression as its key. Useful for tabular report - scraping when the first column can be used as a item key. - - The optional ``asdict`` argument when set to True will return the - parsed tokens as a Python dict instead of a pyparsing ParseResults. - - Example:: - - data_word = Word(alphas) - label = data_word + FollowedBy(':') - - text = "shape: SQUARE posn: upper left color: light blue texture: burlap" - attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) - - # print attributes as plain groups - print(attr_expr[1, ...].parse_string(text).dump()) - - # instead of OneOrMore(expr), parse using Dict(Group(expr)[1, ...]) - Dict will auto-assign names - result = Dict(Group(attr_expr)[1, ...]).parse_string(text) - print(result.dump()) - - # access named fields as dict entries, or output as dict - print(result['shape']) - print(result.as_dict()) - - prints:: - - ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap'] - [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] - - color: 'light blue' - - posn: 'upper left' - - shape: 'SQUARE' - - texture: 'burlap' - SQUARE - {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'} - - See more examples at :class:`ParseResults` of accessing fields by results name. - """ - - def __init__(self, expr: ParserElement, asdict: bool = False): - super().__init__(expr) - self.saveAsList = True - self._asPythonDict = asdict - - def postParse(self, instring, loc, tokenlist): - for i, tok in enumerate(tokenlist): - if len(tok) == 0: - continue - - ikey = tok[0] - if isinstance(ikey, int): - ikey = str(ikey).strip() - - if len(tok) == 1: - tokenlist[ikey] = _ParseResultsWithOffset("", i) - - elif len(tok) == 2 and not isinstance(tok[1], ParseResults): - tokenlist[ikey] = _ParseResultsWithOffset(tok[1], i) - - else: - try: - dictvalue = tok.copy() # ParseResults(i) - except Exception: - exc = TypeError( - "could not extract dict values from parsed results" - " - Dict expression must contain Grouped expressions" - ) - raise exc from None - - del dictvalue[0] - - if len(dictvalue) != 1 or ( - isinstance(dictvalue, ParseResults) and dictvalue.haskeys() - ): - tokenlist[ikey] = _ParseResultsWithOffset(dictvalue, i) - else: - tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0], i) - - if self._asPythonDict: - return [tokenlist.as_dict()] if self.resultsName else tokenlist.as_dict() - else: - return [tokenlist] if self.resultsName else tokenlist - - -class Suppress(TokenConverter): - """Converter for ignoring the results of a parsed expression. - - Example:: - - source = "a, b, c,d" - wd = Word(alphas) - wd_list1 = wd + (',' + wd)[...] - print(wd_list1.parse_string(source)) - - # often, delimiters that are useful during parsing are just in the - # way afterward - use Suppress to keep them out of the parsed output - wd_list2 = wd + (Suppress(',') + wd)[...] - print(wd_list2.parse_string(source)) - - # Skipped text (using '...') can be suppressed as well - source = "lead in START relevant text END trailing text" - start_marker = Keyword("START") - end_marker = Keyword("END") - find_body = Suppress(...) + start_marker + ... + end_marker - print(find_body.parse_string(source) - - prints:: - - ['a', ',', 'b', ',', 'c', ',', 'd'] - ['a', 'b', 'c', 'd'] - ['START', 'relevant text ', 'END'] - - (See also :class:`DelimitedList`.) - """ - - def __init__(self, expr: Union[ParserElement, str], savelist: bool = False): - if expr is ...: - expr = _PendingSkip(NoMatch()) - super().__init__(expr) - - def __add__(self, other) -> "ParserElement": - if isinstance(self.expr, _PendingSkip): - return Suppress(SkipTo(other)) + other - else: - return super().__add__(other) - - def __sub__(self, other) -> "ParserElement": - if isinstance(self.expr, _PendingSkip): - return Suppress(SkipTo(other)) - other - else: - return super().__sub__(other) - - def postParse(self, instring, loc, tokenlist): - return [] - - def suppress(self) -> ParserElement: - return self - - -def trace_parse_action(f: ParseAction) -> ParseAction: - """Decorator for debugging parse actions. - - When the parse action is called, this decorator will print - ``">> entering method-name(line:, , )"``. - When the parse action completes, the decorator will print - ``"<<"`` followed by the returned value, or any exception that the parse action raised. - - Example:: - - wd = Word(alphas) - - @trace_parse_action - def remove_duplicate_chars(tokens): - return ''.join(sorted(set(''.join(tokens)))) - - wds = wd[1, ...].set_parse_action(remove_duplicate_chars) - print(wds.parse_string("slkdjs sld sldd sdlf sdljf")) - - prints:: - - >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {})) - < 3: - thisFunc = paArgs[0].__class__.__name__ + "." + thisFunc - sys.stderr.write(f">>entering {thisFunc}(line: {line(l, s)!r}, {l}, {t!r})\n") - try: - ret = f(*paArgs) - except Exception as exc: - sys.stderr.write(f"< str: - r"""Helper to easily define string ranges for use in :class:`Word` - construction. Borrows syntax from regexp ``'[]'`` string range - definitions:: - - srange("[0-9]") -> "0123456789" - srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" - srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" - - The input string must be enclosed in []'s, and the returned string - is the expanded character set joined into a single string. The - values enclosed in the []'s may be: - - - a single character - - an escaped character with a leading backslash (such as ``\-`` - or ``\]``) - - an escaped hex character with a leading ``'\x'`` - (``\x21``, which is a ``'!'`` character) (``\0x##`` - is also supported for backwards compatibility) - - an escaped octal character with a leading ``'\0'`` - (``\041``, which is a ``'!'`` character) - - a range of any of the above, separated by a dash (``'a-z'``, - etc.) - - any combination of the above (``'aeiouy'``, - ``'a-zA-Z0-9_$'``, etc.) - """ - _expanded = ( - lambda p: p - if not isinstance(p, ParseResults) - else "".join(chr(c) for c in range(ord(p[0]), ord(p[1]) + 1)) - ) - try: - return "".join(_expanded(part) for part in _reBracketExpr.parse_string(s).body) - except Exception as e: - return "" - - -def token_map(func, *args) -> ParseAction: - """Helper to define a parse action by mapping a function to all - elements of a :class:`ParseResults` list. If any additional args are passed, - they are forwarded to the given function as additional arguments - after the token, as in - ``hex_integer = Word(hexnums).set_parse_action(token_map(int, 16))``, - which will convert the parsed data to an integer using base 16. - - Example (compare the last to example in :class:`ParserElement.transform_string`:: - - hex_ints = Word(hexnums)[1, ...].set_parse_action(token_map(int, 16)) - hex_ints.run_tests(''' - 00 11 22 aa FF 0a 0d 1a - ''') - - upperword = Word(alphas).set_parse_action(token_map(str.upper)) - upperword[1, ...].run_tests(''' - my kingdom for a horse - ''') - - wd = Word(alphas).set_parse_action(token_map(str.title)) - wd[1, ...].set_parse_action(' '.join).run_tests(''' - now is the winter of our discontent made glorious summer by this sun of york - ''') - - prints:: - - 00 11 22 aa FF 0a 0d 1a - [0, 17, 34, 170, 255, 10, 13, 26] - - my kingdom for a horse - ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE'] - - now is the winter of our discontent made glorious summer by this sun of york - ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York'] - """ - - def pa(s, l, t): - return [func(tokn, *args) for tokn in t] - - func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) - pa.__name__ = func_name - - return pa - - -def autoname_elements() -> None: - """ - Utility to simplify mass-naming of parser elements, for - generating railroad diagram with named subdiagrams. - """ - calling_frame = sys._getframe().f_back - if calling_frame is None: - return - calling_frame = typing.cast(types.FrameType, calling_frame) - for name, var in calling_frame.f_locals.items(): - if isinstance(var, ParserElement) and not var.customName: - var.set_name(name) - - -dbl_quoted_string = Combine( - Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"' -).set_name("string enclosed in double quotes") - -sgl_quoted_string = Combine( - Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'" -).set_name("string enclosed in single quotes") - -quoted_string = Combine( - (Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"').set_name( - "double quoted string" - ) - | (Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").set_name( - "single quoted string" - ) -).set_name("quoted string using single or double quotes") - -python_quoted_string = Combine( - (Regex(r'"""(?:[^"\\]|""(?!")|"(?!"")|\\.)*', flags=re.MULTILINE) + '"""').set_name( - "multiline double quoted string" - ) - ^ ( - Regex(r"'''(?:[^'\\]|''(?!')|'(?!'')|\\.)*", flags=re.MULTILINE) + "'''" - ).set_name("multiline single quoted string") - ^ (Regex(r'"(?:[^"\n\r\\]|(?:\\")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"').set_name( - "double quoted string" - ) - ^ (Regex(r"'(?:[^'\n\r\\]|(?:\\')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").set_name( - "single quoted string" - ) -).set_name("Python quoted string") - -unicode_string = Combine("u" + quoted_string.copy()).set_name("unicode string literal") - - -alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") -punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") - -# build list of built-in expressions, for future reference if a global default value -# gets updated -_builtin_exprs: List[ParserElement] = [ - v for v in vars().values() if isinstance(v, ParserElement) -] - -# backward compatibility names -# fmt: off -sglQuotedString = sgl_quoted_string -dblQuotedString = dbl_quoted_string -quotedString = quoted_string -unicodeString = unicode_string -lineStart = line_start -lineEnd = line_end -stringStart = string_start -stringEnd = string_end - -@replaced_by_pep8(null_debug_action) -def nullDebugAction(): ... - -@replaced_by_pep8(trace_parse_action) -def traceParseAction(): ... - -@replaced_by_pep8(condition_as_parse_action) -def conditionAsParseAction(): ... - -@replaced_by_pep8(token_map) -def tokenMap(): ... -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/diagram/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/diagram/__init__.py deleted file mode 100644 index 83f9018..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/diagram/__init__.py +++ /dev/null @@ -1,656 +0,0 @@ -# mypy: ignore-errors -import railroad -from pip._vendor import pyparsing -import typing -from typing import ( - List, - NamedTuple, - Generic, - TypeVar, - Dict, - Callable, - Set, - Iterable, -) -from jinja2 import Template -from io import StringIO -import inspect - - -jinja2_template_source = """\ -{% if not embed %} - - - -{% endif %} - {% if not head %} - - {% else %} - {{ head | safe }} - {% endif %} -{% if not embed %} - - -{% endif %} -{{ body | safe }} -{% for diagram in diagrams %} -
-

{{ diagram.title }}

-
{{ diagram.text }}
-
- {{ diagram.svg }} -
-
-{% endfor %} -{% if not embed %} - - -{% endif %} -""" - -template = Template(jinja2_template_source) - -# Note: ideally this would be a dataclass, but we're supporting Python 3.5+ so we can't do this yet -NamedDiagram = NamedTuple( - "NamedDiagram", - [("name", str), ("diagram", typing.Optional[railroad.DiagramItem]), ("index", int)], -) -""" -A simple structure for associating a name with a railroad diagram -""" - -T = TypeVar("T") - - -class EachItem(railroad.Group): - """ - Custom railroad item to compose a: - - Group containing a - - OneOrMore containing a - - Choice of the elements in the Each - with the group label indicating that all must be matched - """ - - all_label = "[ALL]" - - def __init__(self, *items): - choice_item = railroad.Choice(len(items) - 1, *items) - one_or_more_item = railroad.OneOrMore(item=choice_item) - super().__init__(one_or_more_item, label=self.all_label) - - -class AnnotatedItem(railroad.Group): - """ - Simple subclass of Group that creates an annotation label - """ - - def __init__(self, label: str, item): - super().__init__(item=item, label="[{}]".format(label) if label else label) - - -class EditablePartial(Generic[T]): - """ - Acts like a functools.partial, but can be edited. In other words, it represents a type that hasn't yet been - constructed. - """ - - # We need this here because the railroad constructors actually transform the data, so can't be called until the - # entire tree is assembled - - def __init__(self, func: Callable[..., T], args: list, kwargs: dict): - self.func = func - self.args = args - self.kwargs = kwargs - - @classmethod - def from_call(cls, func: Callable[..., T], *args, **kwargs) -> "EditablePartial[T]": - """ - If you call this function in the same way that you would call the constructor, it will store the arguments - as you expect. For example EditablePartial.from_call(Fraction, 1, 3)() == Fraction(1, 3) - """ - return EditablePartial(func=func, args=list(args), kwargs=kwargs) - - @property - def name(self): - return self.kwargs["name"] - - def __call__(self) -> T: - """ - Evaluate the partial and return the result - """ - args = self.args.copy() - kwargs = self.kwargs.copy() - - # This is a helpful hack to allow you to specify varargs parameters (e.g. *args) as keyword args (e.g. - # args=['list', 'of', 'things']) - arg_spec = inspect.getfullargspec(self.func) - if arg_spec.varargs in self.kwargs: - args += kwargs.pop(arg_spec.varargs) - - return self.func(*args, **kwargs) - - -def railroad_to_html(diagrams: List[NamedDiagram], embed=False, **kwargs) -> str: - """ - Given a list of NamedDiagram, produce a single HTML string that visualises those diagrams - :params kwargs: kwargs to be passed in to the template - """ - data = [] - for diagram in diagrams: - if diagram.diagram is None: - continue - io = StringIO() - try: - css = kwargs.get('css') - diagram.diagram.writeStandalone(io.write, css=css) - except AttributeError: - diagram.diagram.writeSvg(io.write) - title = diagram.name - if diagram.index == 0: - title += " (root)" - data.append({"title": title, "text": "", "svg": io.getvalue()}) - - return template.render(diagrams=data, embed=embed, **kwargs) - - -def resolve_partial(partial: "EditablePartial[T]") -> T: - """ - Recursively resolves a collection of Partials into whatever type they are - """ - if isinstance(partial, EditablePartial): - partial.args = resolve_partial(partial.args) - partial.kwargs = resolve_partial(partial.kwargs) - return partial() - elif isinstance(partial, list): - return [resolve_partial(x) for x in partial] - elif isinstance(partial, dict): - return {key: resolve_partial(x) for key, x in partial.items()} - else: - return partial - - -def to_railroad( - element: pyparsing.ParserElement, - diagram_kwargs: typing.Optional[dict] = None, - vertical: int = 3, - show_results_names: bool = False, - show_groups: bool = False, -) -> List[NamedDiagram]: - """ - Convert a pyparsing element tree into a list of diagrams. This is the recommended entrypoint to diagram - creation if you want to access the Railroad tree before it is converted to HTML - :param element: base element of the parser being diagrammed - :param diagram_kwargs: kwargs to pass to the Diagram() constructor - :param vertical: (optional) - int - limit at which number of alternatives should be - shown vertically instead of horizontally - :param show_results_names - bool to indicate whether results name annotations should be - included in the diagram - :param show_groups - bool to indicate whether groups should be highlighted with an unlabeled - surrounding box - """ - # Convert the whole tree underneath the root - lookup = ConverterState(diagram_kwargs=diagram_kwargs or {}) - _to_diagram_element( - element, - lookup=lookup, - parent=None, - vertical=vertical, - show_results_names=show_results_names, - show_groups=show_groups, - ) - - root_id = id(element) - # Convert the root if it hasn't been already - if root_id in lookup: - if not element.customName: - lookup[root_id].name = "" - lookup[root_id].mark_for_extraction(root_id, lookup, force=True) - - # Now that we're finished, we can convert from intermediate structures into Railroad elements - diags = list(lookup.diagrams.values()) - if len(diags) > 1: - # collapse out duplicate diags with the same name - seen = set() - deduped_diags = [] - for d in diags: - # don't extract SkipTo elements, they are uninformative as subdiagrams - if d.name == "...": - continue - if d.name is not None and d.name not in seen: - seen.add(d.name) - deduped_diags.append(d) - resolved = [resolve_partial(partial) for partial in deduped_diags] - else: - # special case - if just one diagram, always display it, even if - # it has no name - resolved = [resolve_partial(partial) for partial in diags] - return sorted(resolved, key=lambda diag: diag.index) - - -def _should_vertical( - specification: int, exprs: Iterable[pyparsing.ParserElement] -) -> bool: - """ - Returns true if we should return a vertical list of elements - """ - if specification is None: - return False - else: - return len(_visible_exprs(exprs)) >= specification - - -class ElementState: - """ - State recorded for an individual pyparsing Element - """ - - # Note: this should be a dataclass, but we have to support Python 3.5 - def __init__( - self, - element: pyparsing.ParserElement, - converted: EditablePartial, - parent: EditablePartial, - number: int, - name: str = None, - parent_index: typing.Optional[int] = None, - ): - #: The pyparsing element that this represents - self.element: pyparsing.ParserElement = element - #: The name of the element - self.name: typing.Optional[str] = name - #: The output Railroad element in an unconverted state - self.converted: EditablePartial = converted - #: The parent Railroad element, which we store so that we can extract this if it's duplicated - self.parent: EditablePartial = parent - #: The order in which we found this element, used for sorting diagrams if this is extracted into a diagram - self.number: int = number - #: The index of this inside its parent - self.parent_index: typing.Optional[int] = parent_index - #: If true, we should extract this out into a subdiagram - self.extract: bool = False - #: If true, all of this element's children have been filled out - self.complete: bool = False - - def mark_for_extraction( - self, el_id: int, state: "ConverterState", name: str = None, force: bool = False - ): - """ - Called when this instance has been seen twice, and thus should eventually be extracted into a sub-diagram - :param el_id: id of the element - :param state: element/diagram state tracker - :param name: name to use for this element's text - :param force: If true, force extraction now, regardless of the state of this. Only useful for extracting the - root element when we know we're finished - """ - self.extract = True - - # Set the name - if not self.name: - if name: - # Allow forcing a custom name - self.name = name - elif self.element.customName: - self.name = self.element.customName - else: - self.name = "" - - # Just because this is marked for extraction doesn't mean we can do it yet. We may have to wait for children - # to be added - # Also, if this is just a string literal etc, don't bother extracting it - if force or (self.complete and _worth_extracting(self.element)): - state.extract_into_diagram(el_id) - - -class ConverterState: - """ - Stores some state that persists between recursions into the element tree - """ - - def __init__(self, diagram_kwargs: typing.Optional[dict] = None): - #: A dictionary mapping ParserElements to state relating to them - self._element_diagram_states: Dict[int, ElementState] = {} - #: A dictionary mapping ParserElement IDs to subdiagrams generated from them - self.diagrams: Dict[int, EditablePartial[NamedDiagram]] = {} - #: The index of the next unnamed element - self.unnamed_index: int = 1 - #: The index of the next element. This is used for sorting - self.index: int = 0 - #: Shared kwargs that are used to customize the construction of diagrams - self.diagram_kwargs: dict = diagram_kwargs or {} - self.extracted_diagram_names: Set[str] = set() - - def __setitem__(self, key: int, value: ElementState): - self._element_diagram_states[key] = value - - def __getitem__(self, key: int) -> ElementState: - return self._element_diagram_states[key] - - def __delitem__(self, key: int): - del self._element_diagram_states[key] - - def __contains__(self, key: int): - return key in self._element_diagram_states - - def generate_unnamed(self) -> int: - """ - Generate a number used in the name of an otherwise unnamed diagram - """ - self.unnamed_index += 1 - return self.unnamed_index - - def generate_index(self) -> int: - """ - Generate a number used to index a diagram - """ - self.index += 1 - return self.index - - def extract_into_diagram(self, el_id: int): - """ - Used when we encounter the same token twice in the same tree. When this - happens, we replace all instances of that token with a terminal, and - create a new subdiagram for the token - """ - position = self[el_id] - - # Replace the original definition of this element with a regular block - if position.parent: - ret = EditablePartial.from_call(railroad.NonTerminal, text=position.name) - if "item" in position.parent.kwargs: - position.parent.kwargs["item"] = ret - elif "items" in position.parent.kwargs: - position.parent.kwargs["items"][position.parent_index] = ret - - # If the element we're extracting is a group, skip to its content but keep the title - if position.converted.func == railroad.Group: - content = position.converted.kwargs["item"] - else: - content = position.converted - - self.diagrams[el_id] = EditablePartial.from_call( - NamedDiagram, - name=position.name, - diagram=EditablePartial.from_call( - railroad.Diagram, content, **self.diagram_kwargs - ), - index=position.number, - ) - - del self[el_id] - - -def _worth_extracting(element: pyparsing.ParserElement) -> bool: - """ - Returns true if this element is worth having its own sub-diagram. Simply, if any of its children - themselves have children, then its complex enough to extract - """ - children = element.recurse() - return any(child.recurse() for child in children) - - -def _apply_diagram_item_enhancements(fn): - """ - decorator to ensure enhancements to a diagram item (such as results name annotations) - get applied on return from _to_diagram_element (we do this since there are several - returns in _to_diagram_element) - """ - - def _inner( - element: pyparsing.ParserElement, - parent: typing.Optional[EditablePartial], - lookup: ConverterState = None, - vertical: int = None, - index: int = 0, - name_hint: str = None, - show_results_names: bool = False, - show_groups: bool = False, - ) -> typing.Optional[EditablePartial]: - ret = fn( - element, - parent, - lookup, - vertical, - index, - name_hint, - show_results_names, - show_groups, - ) - - # apply annotation for results name, if present - if show_results_names and ret is not None: - element_results_name = element.resultsName - if element_results_name: - # add "*" to indicate if this is a "list all results" name - element_results_name += "" if element.modalResults else "*" - ret = EditablePartial.from_call( - railroad.Group, item=ret, label=element_results_name - ) - - return ret - - return _inner - - -def _visible_exprs(exprs: Iterable[pyparsing.ParserElement]): - non_diagramming_exprs = ( - pyparsing.ParseElementEnhance, - pyparsing.PositionToken, - pyparsing.And._ErrorStop, - ) - return [ - e - for e in exprs - if not (e.customName or e.resultsName or isinstance(e, non_diagramming_exprs)) - ] - - -@_apply_diagram_item_enhancements -def _to_diagram_element( - element: pyparsing.ParserElement, - parent: typing.Optional[EditablePartial], - lookup: ConverterState = None, - vertical: int = None, - index: int = 0, - name_hint: str = None, - show_results_names: bool = False, - show_groups: bool = False, -) -> typing.Optional[EditablePartial]: - """ - Recursively converts a PyParsing Element to a railroad Element - :param lookup: The shared converter state that keeps track of useful things - :param index: The index of this element within the parent - :param parent: The parent of this element in the output tree - :param vertical: Controls at what point we make a list of elements vertical. If this is an integer (the default), - it sets the threshold of the number of items before we go vertical. If True, always go vertical, if False, never - do so - :param name_hint: If provided, this will override the generated name - :param show_results_names: bool flag indicating whether to add annotations for results names - :returns: The converted version of the input element, but as a Partial that hasn't yet been constructed - :param show_groups: bool flag indicating whether to show groups using bounding box - """ - exprs = element.recurse() - name = name_hint or element.customName or element.__class__.__name__ - - # Python's id() is used to provide a unique identifier for elements - el_id = id(element) - - element_results_name = element.resultsName - - # Here we basically bypass processing certain wrapper elements if they contribute nothing to the diagram - if not element.customName: - if isinstance( - element, - ( - # pyparsing.TokenConverter, - # pyparsing.Forward, - pyparsing.Located, - ), - ): - # However, if this element has a useful custom name, and its child does not, we can pass it on to the child - if exprs: - if not exprs[0].customName: - propagated_name = name - else: - propagated_name = None - - return _to_diagram_element( - element.expr, - parent=parent, - lookup=lookup, - vertical=vertical, - index=index, - name_hint=propagated_name, - show_results_names=show_results_names, - show_groups=show_groups, - ) - - # If the element isn't worth extracting, we always treat it as the first time we say it - if _worth_extracting(element): - if el_id in lookup: - # If we've seen this element exactly once before, we are only just now finding out that it's a duplicate, - # so we have to extract it into a new diagram. - looked_up = lookup[el_id] - looked_up.mark_for_extraction(el_id, lookup, name=name_hint) - ret = EditablePartial.from_call(railroad.NonTerminal, text=looked_up.name) - return ret - - elif el_id in lookup.diagrams: - # If we have seen the element at least twice before, and have already extracted it into a subdiagram, we - # just put in a marker element that refers to the sub-diagram - ret = EditablePartial.from_call( - railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"] - ) - return ret - - # Recursively convert child elements - # Here we find the most relevant Railroad element for matching pyparsing Element - # We use ``items=[]`` here to hold the place for where the child elements will go once created - if isinstance(element, pyparsing.And): - # detect And's created with ``expr*N`` notation - for these use a OneOrMore with a repeat - # (all will have the same name, and resultsName) - if not exprs: - return None - if len(set((e.name, e.resultsName) for e in exprs)) == 1: - ret = EditablePartial.from_call( - railroad.OneOrMore, item="", repeat=str(len(exprs)) - ) - elif _should_vertical(vertical, exprs): - ret = EditablePartial.from_call(railroad.Stack, items=[]) - else: - ret = EditablePartial.from_call(railroad.Sequence, items=[]) - elif isinstance(element, (pyparsing.Or, pyparsing.MatchFirst)): - if not exprs: - return None - if _should_vertical(vertical, exprs): - ret = EditablePartial.from_call(railroad.Choice, 0, items=[]) - else: - ret = EditablePartial.from_call(railroad.HorizontalChoice, items=[]) - elif isinstance(element, pyparsing.Each): - if not exprs: - return None - ret = EditablePartial.from_call(EachItem, items=[]) - elif isinstance(element, pyparsing.NotAny): - ret = EditablePartial.from_call(AnnotatedItem, label="NOT", item="") - elif isinstance(element, pyparsing.FollowedBy): - ret = EditablePartial.from_call(AnnotatedItem, label="LOOKAHEAD", item="") - elif isinstance(element, pyparsing.PrecededBy): - ret = EditablePartial.from_call(AnnotatedItem, label="LOOKBEHIND", item="") - elif isinstance(element, pyparsing.Group): - if show_groups: - ret = EditablePartial.from_call(AnnotatedItem, label="", item="") - else: - ret = EditablePartial.from_call(railroad.Group, label="", item="") - elif isinstance(element, pyparsing.TokenConverter): - label = type(element).__name__.lower() - if label == "tokenconverter": - ret = EditablePartial.from_call(railroad.Sequence, items=[]) - else: - ret = EditablePartial.from_call(AnnotatedItem, label=label, item="") - elif isinstance(element, pyparsing.Opt): - ret = EditablePartial.from_call(railroad.Optional, item="") - elif isinstance(element, pyparsing.OneOrMore): - ret = EditablePartial.from_call(railroad.OneOrMore, item="") - elif isinstance(element, pyparsing.ZeroOrMore): - ret = EditablePartial.from_call(railroad.ZeroOrMore, item="") - elif isinstance(element, pyparsing.Group): - ret = EditablePartial.from_call( - railroad.Group, item=None, label=element_results_name - ) - elif isinstance(element, pyparsing.Empty) and not element.customName: - # Skip unnamed "Empty" elements - ret = None - elif isinstance(element, pyparsing.ParseElementEnhance): - ret = EditablePartial.from_call(railroad.Sequence, items=[]) - elif len(exprs) > 0 and not element_results_name: - ret = EditablePartial.from_call(railroad.Group, item="", label=name) - elif len(exprs) > 0: - ret = EditablePartial.from_call(railroad.Sequence, items=[]) - else: - terminal = EditablePartial.from_call(railroad.Terminal, element.defaultName) - ret = terminal - - if ret is None: - return - - # Indicate this element's position in the tree so we can extract it if necessary - lookup[el_id] = ElementState( - element=element, - converted=ret, - parent=parent, - parent_index=index, - number=lookup.generate_index(), - ) - if element.customName: - lookup[el_id].mark_for_extraction(el_id, lookup, element.customName) - - i = 0 - for expr in exprs: - # Add a placeholder index in case we have to extract the child before we even add it to the parent - if "items" in ret.kwargs: - ret.kwargs["items"].insert(i, None) - - item = _to_diagram_element( - expr, - parent=ret, - lookup=lookup, - vertical=vertical, - index=i, - show_results_names=show_results_names, - show_groups=show_groups, - ) - - # Some elements don't need to be shown in the diagram - if item is not None: - if "item" in ret.kwargs: - ret.kwargs["item"] = item - elif "items" in ret.kwargs: - # If we've already extracted the child, don't touch this index, since it's occupied by a nonterminal - ret.kwargs["items"][i] = item - i += 1 - elif "items" in ret.kwargs: - # If we're supposed to skip this element, remove it from the parent - del ret.kwargs["items"][i] - - # If all this items children are none, skip this item - if ret and ( - ("items" in ret.kwargs and len(ret.kwargs["items"]) == 0) - or ("item" in ret.kwargs and ret.kwargs["item"] is None) - ): - ret = EditablePartial.from_call(railroad.Terminal, name) - - # Mark this element as "complete", ie it has all of its children - if el_id in lookup: - lookup[el_id].complete = True - - if el_id in lookup and lookup[el_id].extract and lookup[el_id].complete: - lookup.extract_into_diagram(el_id) - if ret is not None: - ret = EditablePartial.from_call( - railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"] - ) - - return ret diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/diagram/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/diagram/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 5b5d9c3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/diagram/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/exceptions.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/exceptions.py deleted file mode 100644 index 12219f1..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/exceptions.py +++ /dev/null @@ -1,299 +0,0 @@ -# exceptions.py - -import re -import sys -import typing - -from .util import ( - col, - line, - lineno, - _collapse_string_to_ranges, - replaced_by_pep8, -) -from .unicode import pyparsing_unicode as ppu - - -class ExceptionWordUnicode(ppu.Latin1, ppu.LatinA, ppu.LatinB, ppu.Greek, ppu.Cyrillic): - pass - - -_extract_alphanums = _collapse_string_to_ranges(ExceptionWordUnicode.alphanums) -_exception_word_extractor = re.compile("([" + _extract_alphanums + "]{1,16})|.") - - -class ParseBaseException(Exception): - """base exception class for all parsing runtime exceptions""" - - loc: int - msg: str - pstr: str - parser_element: typing.Any # "ParserElement" - args: typing.Tuple[str, int, typing.Optional[str]] - - __slots__ = ( - "loc", - "msg", - "pstr", - "parser_element", - "args", - ) - - # Performance tuning: we construct a *lot* of these, so keep this - # constructor as small and fast as possible - def __init__( - self, - pstr: str, - loc: int = 0, - msg: typing.Optional[str] = None, - elem=None, - ): - self.loc = loc - if msg is None: - self.msg = pstr - self.pstr = "" - else: - self.msg = msg - self.pstr = pstr - self.parser_element = elem - self.args = (pstr, loc, msg) - - @staticmethod - def explain_exception(exc, depth=16): - """ - Method to take an exception and translate the Python internal traceback into a list - of the pyparsing expressions that caused the exception to be raised. - - Parameters: - - - exc - exception raised during parsing (need not be a ParseException, in support - of Python exceptions that might be raised in a parse action) - - depth (default=16) - number of levels back in the stack trace to list expression - and function names; if None, the full stack trace names will be listed; if 0, only - the failing input line, marker, and exception string will be shown - - Returns a multi-line string listing the ParserElements and/or function names in the - exception's stack trace. - """ - import inspect - from .core import ParserElement - - if depth is None: - depth = sys.getrecursionlimit() - ret = [] - if isinstance(exc, ParseBaseException): - ret.append(exc.line) - ret.append(" " * (exc.column - 1) + "^") - ret.append(f"{type(exc).__name__}: {exc}") - - if depth > 0: - callers = inspect.getinnerframes(exc.__traceback__, context=depth) - seen = set() - for i, ff in enumerate(callers[-depth:]): - frm = ff[0] - - f_self = frm.f_locals.get("self", None) - if isinstance(f_self, ParserElement): - if not frm.f_code.co_name.startswith( - ("parseImpl", "_parseNoCache") - ): - continue - if id(f_self) in seen: - continue - seen.add(id(f_self)) - - self_type = type(f_self) - ret.append( - f"{self_type.__module__}.{self_type.__name__} - {f_self}" - ) - - elif f_self is not None: - self_type = type(f_self) - ret.append(f"{self_type.__module__}.{self_type.__name__}") - - else: - code = frm.f_code - if code.co_name in ("wrapper", ""): - continue - - ret.append(code.co_name) - - depth -= 1 - if not depth: - break - - return "\n".join(ret) - - @classmethod - def _from_exception(cls, pe): - """ - internal factory method to simplify creating one type of ParseException - from another - avoids having __init__ signature conflicts among subclasses - """ - return cls(pe.pstr, pe.loc, pe.msg, pe.parser_element) - - @property - def line(self) -> str: - """ - Return the line of text where the exception occurred. - """ - return line(self.loc, self.pstr) - - @property - def lineno(self) -> int: - """ - Return the 1-based line number of text where the exception occurred. - """ - return lineno(self.loc, self.pstr) - - @property - def col(self) -> int: - """ - Return the 1-based column on the line of text where the exception occurred. - """ - return col(self.loc, self.pstr) - - @property - def column(self) -> int: - """ - Return the 1-based column on the line of text where the exception occurred. - """ - return col(self.loc, self.pstr) - - # pre-PEP8 compatibility - @property - def parserElement(self): - return self.parser_element - - @parserElement.setter - def parserElement(self, elem): - self.parser_element = elem - - def __str__(self) -> str: - if self.pstr: - if self.loc >= len(self.pstr): - foundstr = ", found end of text" - else: - # pull out next word at error location - found_match = _exception_word_extractor.match(self.pstr, self.loc) - if found_match is not None: - found = found_match.group(0) - else: - found = self.pstr[self.loc : self.loc + 1] - foundstr = (", found %r" % found).replace(r"\\", "\\") - else: - foundstr = "" - return f"{self.msg}{foundstr} (at char {self.loc}), (line:{self.lineno}, col:{self.column})" - - def __repr__(self): - return str(self) - - def mark_input_line( - self, marker_string: typing.Optional[str] = None, *, markerString: str = ">!<" - ) -> str: - """ - Extracts the exception line from the input string, and marks - the location of the exception with a special symbol. - """ - markerString = marker_string if marker_string is not None else markerString - line_str = self.line - line_column = self.column - 1 - if markerString: - line_str = "".join( - (line_str[:line_column], markerString, line_str[line_column:]) - ) - return line_str.strip() - - def explain(self, depth=16) -> str: - """ - Method to translate the Python internal traceback into a list - of the pyparsing expressions that caused the exception to be raised. - - Parameters: - - - depth (default=16) - number of levels back in the stack trace to list expression - and function names; if None, the full stack trace names will be listed; if 0, only - the failing input line, marker, and exception string will be shown - - Returns a multi-line string listing the ParserElements and/or function names in the - exception's stack trace. - - Example:: - - expr = pp.Word(pp.nums) * 3 - try: - expr.parse_string("123 456 A789") - except pp.ParseException as pe: - print(pe.explain(depth=0)) - - prints:: - - 123 456 A789 - ^ - ParseException: Expected W:(0-9), found 'A' (at char 8), (line:1, col:9) - - Note: the diagnostic output will include string representations of the expressions - that failed to parse. These representations will be more helpful if you use `set_name` to - give identifiable names to your expressions. Otherwise they will use the default string - forms, which may be cryptic to read. - - Note: pyparsing's default truncation of exception tracebacks may also truncate the - stack of expressions that are displayed in the ``explain`` output. To get the full listing - of parser expressions, you may have to set ``ParserElement.verbose_stacktrace = True`` - """ - return self.explain_exception(self, depth) - - # fmt: off - @replaced_by_pep8(mark_input_line) - def markInputline(self): ... - # fmt: on - - -class ParseException(ParseBaseException): - """ - Exception thrown when a parse expression doesn't match the input string - - Example:: - - try: - Word(nums).set_name("integer").parse_string("ABC") - except ParseException as pe: - print(pe) - print("column: {}".format(pe.column)) - - prints:: - - Expected integer (at char 0), (line:1, col:1) - column: 1 - - """ - - -class ParseFatalException(ParseBaseException): - """ - User-throwable exception thrown when inconsistent parse content - is found; stops all parsing immediately - """ - - -class ParseSyntaxException(ParseFatalException): - """ - Just like :class:`ParseFatalException`, but thrown internally - when an :class:`ErrorStop` ('-' operator) indicates - that parsing is to stop immediately because an unbacktrackable - syntax error has been found. - """ - - -class RecursiveGrammarException(Exception): - """ - Exception thrown by :class:`ParserElement.validate` if the - grammar could be left-recursive; parser may need to enable - left recursion using :class:`ParserElement.enable_left_recursion` - """ - - def __init__(self, parseElementList): - self.parseElementTrace = parseElementList - - def __str__(self) -> str: - return f"RecursiveGrammarException: {self.parseElementTrace}" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/helpers.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/helpers.py deleted file mode 100644 index 018f0d6..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/helpers.py +++ /dev/null @@ -1,1100 +0,0 @@ -# helpers.py -import html.entities -import re -import sys -import typing - -from . import __diag__ -from .core import * -from .util import ( - _bslash, - _flatten, - _escape_regex_range_chars, - replaced_by_pep8, -) - - -# -# global helpers -# -def counted_array( - expr: ParserElement, - int_expr: typing.Optional[ParserElement] = None, - *, - intExpr: typing.Optional[ParserElement] = None, -) -> ParserElement: - """Helper to define a counted list of expressions. - - This helper defines a pattern of the form:: - - integer expr expr expr... - - where the leading integer tells how many expr expressions follow. - The matched tokens returns the array of expr tokens as a list - the - leading count token is suppressed. - - If ``int_expr`` is specified, it should be a pyparsing expression - that produces an integer value. - - Example:: - - counted_array(Word(alphas)).parse_string('2 ab cd ef') # -> ['ab', 'cd'] - - # in this parser, the leading integer value is given in binary, - # '10' indicating that 2 values are in the array - binary_constant = Word('01').set_parse_action(lambda t: int(t[0], 2)) - counted_array(Word(alphas), int_expr=binary_constant).parse_string('10 ab cd ef') # -> ['ab', 'cd'] - - # if other fields must be parsed after the count but before the - # list items, give the fields results names and they will - # be preserved in the returned ParseResults: - count_with_metadata = integer + Word(alphas)("type") - typed_array = counted_array(Word(alphanums), int_expr=count_with_metadata)("items") - result = typed_array.parse_string("3 bool True True False") - print(result.dump()) - - # prints - # ['True', 'True', 'False'] - # - items: ['True', 'True', 'False'] - # - type: 'bool' - """ - intExpr = intExpr or int_expr - array_expr = Forward() - - def count_field_parse_action(s, l, t): - nonlocal array_expr - n = t[0] - array_expr <<= (expr * n) if n else Empty() - # clear list contents, but keep any named results - del t[:] - - if intExpr is None: - intExpr = Word(nums).set_parse_action(lambda t: int(t[0])) - else: - intExpr = intExpr.copy() - intExpr.set_name("arrayLen") - intExpr.add_parse_action(count_field_parse_action, call_during_try=True) - return (intExpr + array_expr).set_name("(len) " + str(expr) + "...") - - -def match_previous_literal(expr: ParserElement) -> ParserElement: - """Helper to define an expression that is indirectly defined from - the tokens matched in a previous expression, that is, it looks for - a 'repeat' of a previous expression. For example:: - - first = Word(nums) - second = match_previous_literal(first) - match_expr = first + ":" + second - - will match ``"1:1"``, but not ``"1:2"``. Because this - matches a previous literal, will also match the leading - ``"1:1"`` in ``"1:10"``. If this is not desired, use - :class:`match_previous_expr`. Do *not* use with packrat parsing - enabled. - """ - rep = Forward() - - def copy_token_to_repeater(s, l, t): - if t: - if len(t) == 1: - rep << t[0] - else: - # flatten t tokens - tflat = _flatten(t.as_list()) - rep << And(Literal(tt) for tt in tflat) - else: - rep << Empty() - - expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) - rep.set_name("(prev) " + str(expr)) - return rep - - -def match_previous_expr(expr: ParserElement) -> ParserElement: - """Helper to define an expression that is indirectly defined from - the tokens matched in a previous expression, that is, it looks for - a 'repeat' of a previous expression. For example:: - - first = Word(nums) - second = match_previous_expr(first) - match_expr = first + ":" + second - - will match ``"1:1"``, but not ``"1:2"``. Because this - matches by expressions, will *not* match the leading ``"1:1"`` - in ``"1:10"``; the expressions are evaluated first, and then - compared, so ``"1"`` is compared with ``"10"``. Do *not* use - with packrat parsing enabled. - """ - rep = Forward() - e2 = expr.copy() - rep <<= e2 - - def copy_token_to_repeater(s, l, t): - matchTokens = _flatten(t.as_list()) - - def must_match_these_tokens(s, l, t): - theseTokens = _flatten(t.as_list()) - if theseTokens != matchTokens: - raise ParseException( - s, l, f"Expected {matchTokens}, found{theseTokens}" - ) - - rep.set_parse_action(must_match_these_tokens, callDuringTry=True) - - expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) - rep.set_name("(prev) " + str(expr)) - return rep - - -def one_of( - strs: Union[typing.Iterable[str], str], - caseless: bool = False, - use_regex: bool = True, - as_keyword: bool = False, - *, - useRegex: bool = True, - asKeyword: bool = False, -) -> ParserElement: - """Helper to quickly define a set of alternative :class:`Literal` s, - and makes sure to do longest-first testing when there is a conflict, - regardless of the input order, but returns - a :class:`MatchFirst` for best performance. - - Parameters: - - - ``strs`` - a string of space-delimited literals, or a collection of - string literals - - ``caseless`` - treat all literals as caseless - (default= ``False``) - - ``use_regex`` - as an optimization, will - generate a :class:`Regex` object; otherwise, will generate - a :class:`MatchFirst` object (if ``caseless=True`` or ``as_keyword=True``, or if - creating a :class:`Regex` raises an exception) - (default= ``True``) - - ``as_keyword`` - enforce :class:`Keyword`-style matching on the - generated expressions - (default= ``False``) - - ``asKeyword`` and ``useRegex`` are retained for pre-PEP8 compatibility, - but will be removed in a future release - - Example:: - - comp_oper = one_of("< = > <= >= !=") - var = Word(alphas) - number = Word(nums) - term = var | number - comparison_expr = term + comp_oper + term - print(comparison_expr.search_string("B = 12 AA=23 B<=AA AA>12")) - - prints:: - - [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']] - """ - asKeyword = asKeyword or as_keyword - useRegex = useRegex and use_regex - - if ( - isinstance(caseless, str_type) - and __diag__.warn_on_multiple_string_args_to_oneof - ): - warnings.warn( - "More than one string argument passed to one_of, pass" - " choices as a list or space-delimited string", - stacklevel=2, - ) - - if caseless: - isequal = lambda a, b: a.upper() == b.upper() - masks = lambda a, b: b.upper().startswith(a.upper()) - parseElementClass = CaselessKeyword if asKeyword else CaselessLiteral - else: - isequal = lambda a, b: a == b - masks = lambda a, b: b.startswith(a) - parseElementClass = Keyword if asKeyword else Literal - - symbols: List[str] = [] - if isinstance(strs, str_type): - strs = typing.cast(str, strs) - symbols = strs.split() - elif isinstance(strs, Iterable): - symbols = list(strs) - else: - raise TypeError("Invalid argument to one_of, expected string or iterable") - if not symbols: - return NoMatch() - - # reorder given symbols to take care to avoid masking longer choices with shorter ones - # (but only if the given symbols are not just single characters) - if any(len(sym) > 1 for sym in symbols): - i = 0 - while i < len(symbols) - 1: - cur = symbols[i] - for j, other in enumerate(symbols[i + 1 :]): - if isequal(other, cur): - del symbols[i + j + 1] - break - elif masks(cur, other): - del symbols[i + j + 1] - symbols.insert(i, other) - break - else: - i += 1 - - if useRegex: - re_flags: int = re.IGNORECASE if caseless else 0 - - try: - if all(len(sym) == 1 for sym in symbols): - # symbols are just single characters, create range regex pattern - patt = f"[{''.join(_escape_regex_range_chars(sym) for sym in symbols)}]" - else: - patt = "|".join(re.escape(sym) for sym in symbols) - - # wrap with \b word break markers if defining as keywords - if asKeyword: - patt = rf"\b(?:{patt})\b" - - ret = Regex(patt, flags=re_flags).set_name(" | ".join(symbols)) - - if caseless: - # add parse action to return symbols as specified, not in random - # casing as found in input string - symbol_map = {sym.lower(): sym for sym in symbols} - ret.add_parse_action(lambda s, l, t: symbol_map[t[0].lower()]) - - return ret - - except re.error: - warnings.warn( - "Exception creating Regex for one_of, building MatchFirst", stacklevel=2 - ) - - # last resort, just use MatchFirst - return MatchFirst(parseElementClass(sym) for sym in symbols).set_name( - " | ".join(symbols) - ) - - -def dict_of(key: ParserElement, value: ParserElement) -> ParserElement: - """Helper to easily and clearly define a dictionary by specifying - the respective patterns for the key and value. Takes care of - defining the :class:`Dict`, :class:`ZeroOrMore`, and - :class:`Group` tokens in the proper order. The key pattern - can include delimiting markers or punctuation, as long as they are - suppressed, thereby leaving the significant key text. The value - pattern can include named results, so that the :class:`Dict` results - can include named token fields. - - Example:: - - text = "shape: SQUARE posn: upper left color: light blue texture: burlap" - attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) - print(attr_expr[1, ...].parse_string(text).dump()) - - attr_label = label - attr_value = Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join) - - # similar to Dict, but simpler call format - result = dict_of(attr_label, attr_value).parse_string(text) - print(result.dump()) - print(result['shape']) - print(result.shape) # object attribute access works too - print(result.as_dict()) - - prints:: - - [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] - - color: 'light blue' - - posn: 'upper left' - - shape: 'SQUARE' - - texture: 'burlap' - SQUARE - SQUARE - {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'} - """ - return Dict(OneOrMore(Group(key + value))) - - -def original_text_for( - expr: ParserElement, as_string: bool = True, *, asString: bool = True -) -> ParserElement: - """Helper to return the original, untokenized text for a given - expression. Useful to restore the parsed fields of an HTML start - tag into the raw tag text itself, or to revert separate tokens with - intervening whitespace back to the original matching input text. By - default, returns a string containing the original parsed text. - - If the optional ``as_string`` argument is passed as - ``False``, then the return value is - a :class:`ParseResults` containing any results names that - were originally matched, and a single token containing the original - matched text from the input string. So if the expression passed to - :class:`original_text_for` contains expressions with defined - results names, you must set ``as_string`` to ``False`` if you - want to preserve those results name values. - - The ``asString`` pre-PEP8 argument is retained for compatibility, - but will be removed in a future release. - - Example:: - - src = "this is test bold text normal text " - for tag in ("b", "i"): - opener, closer = make_html_tags(tag) - patt = original_text_for(opener + ... + closer) - print(patt.search_string(src)[0]) - - prints:: - - [' bold text '] - ['text'] - """ - asString = asString and as_string - - locMarker = Empty().set_parse_action(lambda s, loc, t: loc) - endlocMarker = locMarker.copy() - endlocMarker.callPreparse = False - matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end") - if asString: - extractText = lambda s, l, t: s[t._original_start : t._original_end] - else: - - def extractText(s, l, t): - t[:] = [s[t.pop("_original_start") : t.pop("_original_end")]] - - matchExpr.set_parse_action(extractText) - matchExpr.ignoreExprs = expr.ignoreExprs - matchExpr.suppress_warning(Diagnostics.warn_ungrouped_named_tokens_in_collection) - return matchExpr - - -def ungroup(expr: ParserElement) -> ParserElement: - """Helper to undo pyparsing's default grouping of And expressions, - even if all but one are non-empty. - """ - return TokenConverter(expr).add_parse_action(lambda t: t[0]) - - -def locatedExpr(expr: ParserElement) -> ParserElement: - """ - (DEPRECATED - future code should use the :class:`Located` class) - Helper to decorate a returned token with its starting and ending - locations in the input string. - - This helper adds the following results names: - - - ``locn_start`` - location where matched expression begins - - ``locn_end`` - location where matched expression ends - - ``value`` - the actual parsed results - - Be careful if the input text contains ```` characters, you - may want to call :class:`ParserElement.parse_with_tabs` - - Example:: - - wd = Word(alphas) - for match in locatedExpr(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): - print(match) - - prints:: - - [[0, 'ljsdf', 5]] - [[8, 'lksdjjf', 15]] - [[18, 'lkkjj', 23]] - """ - locator = Empty().set_parse_action(lambda ss, ll, tt: ll) - return Group( - locator("locn_start") - + expr("value") - + locator.copy().leaveWhitespace()("locn_end") - ) - - -def nested_expr( - opener: Union[str, ParserElement] = "(", - closer: Union[str, ParserElement] = ")", - content: typing.Optional[ParserElement] = None, - ignore_expr: ParserElement = quoted_string(), - *, - ignoreExpr: ParserElement = quoted_string(), -) -> ParserElement: - """Helper method for defining nested lists enclosed in opening and - closing delimiters (``"("`` and ``")"`` are the default). - - Parameters: - - - ``opener`` - opening character for a nested list - (default= ``"("``); can also be a pyparsing expression - - ``closer`` - closing character for a nested list - (default= ``")"``); can also be a pyparsing expression - - ``content`` - expression for items within the nested lists - (default= ``None``) - - ``ignore_expr`` - expression for ignoring opening and closing delimiters - (default= :class:`quoted_string`) - - ``ignoreExpr`` - this pre-PEP8 argument is retained for compatibility - but will be removed in a future release - - If an expression is not provided for the content argument, the - nested expression will capture all whitespace-delimited content - between delimiters as a list of separate values. - - Use the ``ignore_expr`` argument to define expressions that may - contain opening or closing characters that should not be treated as - opening or closing characters for nesting, such as quoted_string or - a comment expression. Specify multiple expressions using an - :class:`Or` or :class:`MatchFirst`. The default is - :class:`quoted_string`, but if no expressions are to be ignored, then - pass ``None`` for this argument. - - Example:: - - data_type = one_of("void int short long char float double") - decl_data_type = Combine(data_type + Opt(Word('*'))) - ident = Word(alphas+'_', alphanums+'_') - number = pyparsing_common.number - arg = Group(decl_data_type + ident) - LPAR, RPAR = map(Suppress, "()") - - code_body = nested_expr('{', '}', ignore_expr=(quoted_string | c_style_comment)) - - c_function = (decl_data_type("type") - + ident("name") - + LPAR + Opt(DelimitedList(arg), [])("args") + RPAR - + code_body("body")) - c_function.ignore(c_style_comment) - - source_code = ''' - int is_odd(int x) { - return (x%2); - } - - int dec_to_hex(char hchar) { - if (hchar >= '0' && hchar <= '9') { - return (ord(hchar)-ord('0')); - } else { - return (10+ord(hchar)-ord('A')); - } - } - ''' - for func in c_function.search_string(source_code): - print("%(name)s (%(type)s) args: %(args)s" % func) - - - prints:: - - is_odd (int) args: [['int', 'x']] - dec_to_hex (int) args: [['char', 'hchar']] - """ - if ignoreExpr != ignore_expr: - ignoreExpr = ignore_expr if ignoreExpr == quoted_string() else ignoreExpr - if opener == closer: - raise ValueError("opening and closing strings cannot be the same") - if content is None: - if isinstance(opener, str_type) and isinstance(closer, str_type): - opener = typing.cast(str, opener) - closer = typing.cast(str, closer) - if len(opener) == 1 and len(closer) == 1: - if ignoreExpr is not None: - content = Combine( - OneOrMore( - ~ignoreExpr - + CharsNotIn( - opener + closer + ParserElement.DEFAULT_WHITE_CHARS, - exact=1, - ) - ) - ).set_parse_action(lambda t: t[0].strip()) - else: - content = empty.copy() + CharsNotIn( - opener + closer + ParserElement.DEFAULT_WHITE_CHARS - ).set_parse_action(lambda t: t[0].strip()) - else: - if ignoreExpr is not None: - content = Combine( - OneOrMore( - ~ignoreExpr - + ~Literal(opener) - + ~Literal(closer) - + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) - ) - ).set_parse_action(lambda t: t[0].strip()) - else: - content = Combine( - OneOrMore( - ~Literal(opener) - + ~Literal(closer) - + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) - ) - ).set_parse_action(lambda t: t[0].strip()) - else: - raise ValueError( - "opening and closing arguments must be strings if no content expression is given" - ) - ret = Forward() - if ignoreExpr is not None: - ret <<= Group( - Suppress(opener) + ZeroOrMore(ignoreExpr | ret | content) + Suppress(closer) - ) - else: - ret <<= Group(Suppress(opener) + ZeroOrMore(ret | content) + Suppress(closer)) - ret.set_name("nested %s%s expression" % (opener, closer)) - return ret - - -def _makeTags(tagStr, xml, suppress_LT=Suppress("<"), suppress_GT=Suppress(">")): - """Internal helper to construct opening and closing tag expressions, given a tag name""" - if isinstance(tagStr, str_type): - resname = tagStr - tagStr = Keyword(tagStr, caseless=not xml) - else: - resname = tagStr.name - - tagAttrName = Word(alphas, alphanums + "_-:") - if xml: - tagAttrValue = dbl_quoted_string.copy().set_parse_action(remove_quotes) - openTag = ( - suppress_LT - + tagStr("tag") - + Dict(ZeroOrMore(Group(tagAttrName + Suppress("=") + tagAttrValue))) - + Opt("/", default=[False])("empty").set_parse_action( - lambda s, l, t: t[0] == "/" - ) - + suppress_GT - ) - else: - tagAttrValue = quoted_string.copy().set_parse_action(remove_quotes) | Word( - printables, exclude_chars=">" - ) - openTag = ( - suppress_LT - + tagStr("tag") - + Dict( - ZeroOrMore( - Group( - tagAttrName.set_parse_action(lambda t: t[0].lower()) - + Opt(Suppress("=") + tagAttrValue) - ) - ) - ) - + Opt("/", default=[False])("empty").set_parse_action( - lambda s, l, t: t[0] == "/" - ) - + suppress_GT - ) - closeTag = Combine(Literal("", adjacent=False) - - openTag.set_name("<%s>" % resname) - # add start results name in parse action now that ungrouped names are not reported at two levels - openTag.add_parse_action( - lambda t: t.__setitem__( - "start" + "".join(resname.replace(":", " ").title().split()), t.copy() - ) - ) - closeTag = closeTag( - "end" + "".join(resname.replace(":", " ").title().split()) - ).set_name("" % resname) - openTag.tag = resname - closeTag.tag = resname - openTag.tag_body = SkipTo(closeTag()) - return openTag, closeTag - - -def make_html_tags( - tag_str: Union[str, ParserElement] -) -> Tuple[ParserElement, ParserElement]: - """Helper to construct opening and closing tag expressions for HTML, - given a tag name. Matches tags in either upper or lower case, - attributes with namespaces and with quoted or unquoted values. - - Example:: - - text = 'More info at the pyparsing wiki page' - # make_html_tags returns pyparsing expressions for the opening and - # closing tags as a 2-tuple - a, a_end = make_html_tags("A") - link_expr = a + SkipTo(a_end)("link_text") + a_end - - for link in link_expr.search_string(text): - # attributes in the tag (like "href" shown here) are - # also accessible as named results - print(link.link_text, '->', link.href) - - prints:: - - pyparsing -> https://github.com/pyparsing/pyparsing/wiki - """ - return _makeTags(tag_str, False) - - -def make_xml_tags( - tag_str: Union[str, ParserElement] -) -> Tuple[ParserElement, ParserElement]: - """Helper to construct opening and closing tag expressions for XML, - given a tag name. Matches tags only in the given upper/lower case. - - Example: similar to :class:`make_html_tags` - """ - return _makeTags(tag_str, True) - - -any_open_tag: ParserElement -any_close_tag: ParserElement -any_open_tag, any_close_tag = make_html_tags( - Word(alphas, alphanums + "_:").set_name("any tag") -) - -_htmlEntityMap = {k.rstrip(";"): v for k, v in html.entities.html5.items()} -common_html_entity = Regex("&(?P" + "|".join(_htmlEntityMap) + ");").set_name( - "common HTML entity" -) - - -def replace_html_entity(s, l, t): - """Helper parser action to replace common HTML entities with their special characters""" - return _htmlEntityMap.get(t.entity) - - -class OpAssoc(Enum): - """Enumeration of operator associativity - - used in constructing InfixNotationOperatorSpec for :class:`infix_notation`""" - - LEFT = 1 - RIGHT = 2 - - -InfixNotationOperatorArgType = Union[ - ParserElement, str, Tuple[Union[ParserElement, str], Union[ParserElement, str]] -] -InfixNotationOperatorSpec = Union[ - Tuple[ - InfixNotationOperatorArgType, - int, - OpAssoc, - typing.Optional[ParseAction], - ], - Tuple[ - InfixNotationOperatorArgType, - int, - OpAssoc, - ], -] - - -def infix_notation( - base_expr: ParserElement, - op_list: List[InfixNotationOperatorSpec], - lpar: Union[str, ParserElement] = Suppress("("), - rpar: Union[str, ParserElement] = Suppress(")"), -) -> ParserElement: - """Helper method for constructing grammars of expressions made up of - operators working in a precedence hierarchy. Operators may be unary - or binary, left- or right-associative. Parse actions can also be - attached to operator expressions. The generated parser will also - recognize the use of parentheses to override operator precedences - (see example below). - - Note: if you define a deep operator list, you may see performance - issues when using infix_notation. See - :class:`ParserElement.enable_packrat` for a mechanism to potentially - improve your parser performance. - - Parameters: - - - ``base_expr`` - expression representing the most basic operand to - be used in the expression - - ``op_list`` - list of tuples, one for each operator precedence level - in the expression grammar; each tuple is of the form ``(op_expr, - num_operands, right_left_assoc, (optional)parse_action)``, where: - - - ``op_expr`` is the pyparsing expression for the operator; may also - be a string, which will be converted to a Literal; if ``num_operands`` - is 3, ``op_expr`` is a tuple of two expressions, for the two - operators separating the 3 terms - - ``num_operands`` is the number of terms for this operator (must be 1, - 2, or 3) - - ``right_left_assoc`` is the indicator whether the operator is right - or left associative, using the pyparsing-defined constants - ``OpAssoc.RIGHT`` and ``OpAssoc.LEFT``. - - ``parse_action`` is the parse action to be associated with - expressions matching this operator expression (the parse action - tuple member may be omitted); if the parse action is passed - a tuple or list of functions, this is equivalent to calling - ``set_parse_action(*fn)`` - (:class:`ParserElement.set_parse_action`) - - ``lpar`` - expression for matching left-parentheses; if passed as a - str, then will be parsed as ``Suppress(lpar)``. If lpar is passed as - an expression (such as ``Literal('(')``), then it will be kept in - the parsed results, and grouped with them. (default= ``Suppress('(')``) - - ``rpar`` - expression for matching right-parentheses; if passed as a - str, then will be parsed as ``Suppress(rpar)``. If rpar is passed as - an expression (such as ``Literal(')')``), then it will be kept in - the parsed results, and grouped with them. (default= ``Suppress(')')``) - - Example:: - - # simple example of four-function arithmetic with ints and - # variable names - integer = pyparsing_common.signed_integer - varname = pyparsing_common.identifier - - arith_expr = infix_notation(integer | varname, - [ - ('-', 1, OpAssoc.RIGHT), - (one_of('* /'), 2, OpAssoc.LEFT), - (one_of('+ -'), 2, OpAssoc.LEFT), - ]) - - arith_expr.run_tests(''' - 5+3*6 - (5+3)*6 - -2--11 - ''', full_dump=False) - - prints:: - - 5+3*6 - [[5, '+', [3, '*', 6]]] - - (5+3)*6 - [[[5, '+', 3], '*', 6]] - - (5+x)*y - [[[5, '+', 'x'], '*', 'y']] - - -2--11 - [[['-', 2], '-', ['-', 11]]] - """ - - # captive version of FollowedBy that does not do parse actions or capture results names - class _FB(FollowedBy): - def parseImpl(self, instring, loc, doActions=True): - self.expr.try_parse(instring, loc) - return loc, [] - - _FB.__name__ = "FollowedBy>" - - ret = Forward() - if isinstance(lpar, str): - lpar = Suppress(lpar) - if isinstance(rpar, str): - rpar = Suppress(rpar) - - # if lpar and rpar are not suppressed, wrap in group - if not (isinstance(rpar, Suppress) and isinstance(rpar, Suppress)): - lastExpr = base_expr | Group(lpar + ret + rpar) - else: - lastExpr = base_expr | (lpar + ret + rpar) - - arity: int - rightLeftAssoc: opAssoc - pa: typing.Optional[ParseAction] - opExpr1: ParserElement - opExpr2: ParserElement - for i, operDef in enumerate(op_list): - opExpr, arity, rightLeftAssoc, pa = (operDef + (None,))[:4] # type: ignore[assignment] - if isinstance(opExpr, str_type): - opExpr = ParserElement._literalStringClass(opExpr) - opExpr = typing.cast(ParserElement, opExpr) - if arity == 3: - if not isinstance(opExpr, (tuple, list)) or len(opExpr) != 2: - raise ValueError( - "if numterms=3, opExpr must be a tuple or list of two expressions" - ) - opExpr1, opExpr2 = opExpr - term_name = f"{opExpr1}{opExpr2} term" - else: - term_name = f"{opExpr} term" - - if not 1 <= arity <= 3: - raise ValueError("operator must be unary (1), binary (2), or ternary (3)") - - if rightLeftAssoc not in (OpAssoc.LEFT, OpAssoc.RIGHT): - raise ValueError("operator must indicate right or left associativity") - - thisExpr: ParserElement = Forward().set_name(term_name) - thisExpr = typing.cast(Forward, thisExpr) - if rightLeftAssoc is OpAssoc.LEFT: - if arity == 1: - matchExpr = _FB(lastExpr + opExpr) + Group(lastExpr + opExpr[1, ...]) - elif arity == 2: - if opExpr is not None: - matchExpr = _FB(lastExpr + opExpr + lastExpr) + Group( - lastExpr + (opExpr + lastExpr)[1, ...] - ) - else: - matchExpr = _FB(lastExpr + lastExpr) + Group(lastExpr[2, ...]) - elif arity == 3: - matchExpr = _FB( - lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr - ) + Group(lastExpr + OneOrMore(opExpr1 + lastExpr + opExpr2 + lastExpr)) - elif rightLeftAssoc is OpAssoc.RIGHT: - if arity == 1: - # try to avoid LR with this extra test - if not isinstance(opExpr, Opt): - opExpr = Opt(opExpr) - matchExpr = _FB(opExpr.expr + thisExpr) + Group(opExpr + thisExpr) - elif arity == 2: - if opExpr is not None: - matchExpr = _FB(lastExpr + opExpr + thisExpr) + Group( - lastExpr + (opExpr + thisExpr)[1, ...] - ) - else: - matchExpr = _FB(lastExpr + thisExpr) + Group( - lastExpr + thisExpr[1, ...] - ) - elif arity == 3: - matchExpr = _FB( - lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr - ) + Group(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) - if pa: - if isinstance(pa, (tuple, list)): - matchExpr.set_parse_action(*pa) - else: - matchExpr.set_parse_action(pa) - thisExpr <<= (matchExpr | lastExpr).setName(term_name) - lastExpr = thisExpr - ret <<= lastExpr - return ret - - -def indentedBlock(blockStatementExpr, indentStack, indent=True, backup_stacks=[]): - """ - (DEPRECATED - use :class:`IndentedBlock` class instead) - Helper method for defining space-delimited indentation blocks, - such as those used to define block statements in Python source code. - - Parameters: - - - ``blockStatementExpr`` - expression defining syntax of statement that - is repeated within the indented block - - ``indentStack`` - list created by caller to manage indentation stack - (multiple ``statementWithIndentedBlock`` expressions within a single - grammar should share a common ``indentStack``) - - ``indent`` - boolean indicating whether block must be indented beyond - the current level; set to ``False`` for block of left-most statements - (default= ``True``) - - A valid block must contain at least one ``blockStatement``. - - (Note that indentedBlock uses internal parse actions which make it - incompatible with packrat parsing.) - - Example:: - - data = ''' - def A(z): - A1 - B = 100 - G = A2 - A2 - A3 - B - def BB(a,b,c): - BB1 - def BBA(): - bba1 - bba2 - bba3 - C - D - def spam(x,y): - def eggs(z): - pass - ''' - - - indentStack = [1] - stmt = Forward() - - identifier = Word(alphas, alphanums) - funcDecl = ("def" + identifier + Group("(" + Opt(delimitedList(identifier)) + ")") + ":") - func_body = indentedBlock(stmt, indentStack) - funcDef = Group(funcDecl + func_body) - - rvalue = Forward() - funcCall = Group(identifier + "(" + Opt(delimitedList(rvalue)) + ")") - rvalue << (funcCall | identifier | Word(nums)) - assignment = Group(identifier + "=" + rvalue) - stmt << (funcDef | assignment | identifier) - - module_body = stmt[1, ...] - - parseTree = module_body.parseString(data) - parseTree.pprint() - - prints:: - - [['def', - 'A', - ['(', 'z', ')'], - ':', - [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]], - 'B', - ['def', - 'BB', - ['(', 'a', 'b', 'c', ')'], - ':', - [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]], - 'C', - 'D', - ['def', - 'spam', - ['(', 'x', 'y', ')'], - ':', - [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]] - """ - backup_stacks.append(indentStack[:]) - - def reset_stack(): - indentStack[:] = backup_stacks[-1] - - def checkPeerIndent(s, l, t): - if l >= len(s): - return - curCol = col(l, s) - if curCol != indentStack[-1]: - if curCol > indentStack[-1]: - raise ParseException(s, l, "illegal nesting") - raise ParseException(s, l, "not a peer entry") - - def checkSubIndent(s, l, t): - curCol = col(l, s) - if curCol > indentStack[-1]: - indentStack.append(curCol) - else: - raise ParseException(s, l, "not a subentry") - - def checkUnindent(s, l, t): - if l >= len(s): - return - curCol = col(l, s) - if not (indentStack and curCol in indentStack): - raise ParseException(s, l, "not an unindent") - if curCol < indentStack[-1]: - indentStack.pop() - - NL = OneOrMore(LineEnd().set_whitespace_chars("\t ").suppress()) - INDENT = (Empty() + Empty().set_parse_action(checkSubIndent)).set_name("INDENT") - PEER = Empty().set_parse_action(checkPeerIndent).set_name("") - UNDENT = Empty().set_parse_action(checkUnindent).set_name("UNINDENT") - if indent: - smExpr = Group( - Opt(NL) - + INDENT - + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) - + UNDENT - ) - else: - smExpr = Group( - Opt(NL) - + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) - + Opt(UNDENT) - ) - - # add a parse action to remove backup_stack from list of backups - smExpr.add_parse_action( - lambda: backup_stacks.pop(-1) and None if backup_stacks else None - ) - smExpr.set_fail_action(lambda a, b, c, d: reset_stack()) - blockStatementExpr.ignore(_bslash + LineEnd()) - return smExpr.set_name("indented block") - - -# it's easy to get these comment structures wrong - they're very common, so may as well make them available -c_style_comment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + "*/").set_name( - "C style comment" -) -"Comment of the form ``/* ... */``" - -html_comment = Regex(r"").set_name("HTML comment") -"Comment of the form ````" - -rest_of_line = Regex(r".*").leave_whitespace().set_name("rest of line") -dbl_slash_comment = Regex(r"//(?:\\\n|[^\n])*").set_name("// comment") -"Comment of the form ``// ... (to end of line)``" - -cpp_style_comment = Combine( - Regex(r"/\*(?:[^*]|\*(?!/))*") + "*/" | dbl_slash_comment -).set_name("C++ style comment") -"Comment of either form :class:`c_style_comment` or :class:`dbl_slash_comment`" - -java_style_comment = cpp_style_comment -"Same as :class:`cpp_style_comment`" - -python_style_comment = Regex(r"#.*").set_name("Python style comment") -"Comment of the form ``# ... (to end of line)``" - - -# build list of built-in expressions, for future reference if a global default value -# gets updated -_builtin_exprs: List[ParserElement] = [ - v for v in vars().values() if isinstance(v, ParserElement) -] - - -# compatibility function, superseded by DelimitedList class -def delimited_list( - expr: Union[str, ParserElement], - delim: Union[str, ParserElement] = ",", - combine: bool = False, - min: typing.Optional[int] = None, - max: typing.Optional[int] = None, - *, - allow_trailing_delim: bool = False, -) -> ParserElement: - """(DEPRECATED - use :class:`DelimitedList` class)""" - return DelimitedList( - expr, delim, combine, min, max, allow_trailing_delim=allow_trailing_delim - ) - - -# pre-PEP8 compatible names -# fmt: off -opAssoc = OpAssoc -anyOpenTag = any_open_tag -anyCloseTag = any_close_tag -commonHTMLEntity = common_html_entity -cStyleComment = c_style_comment -htmlComment = html_comment -restOfLine = rest_of_line -dblSlashComment = dbl_slash_comment -cppStyleComment = cpp_style_comment -javaStyleComment = java_style_comment -pythonStyleComment = python_style_comment - -@replaced_by_pep8(DelimitedList) -def delimitedList(): ... - -@replaced_by_pep8(DelimitedList) -def delimited_list(): ... - -@replaced_by_pep8(counted_array) -def countedArray(): ... - -@replaced_by_pep8(match_previous_literal) -def matchPreviousLiteral(): ... - -@replaced_by_pep8(match_previous_expr) -def matchPreviousExpr(): ... - -@replaced_by_pep8(one_of) -def oneOf(): ... - -@replaced_by_pep8(dict_of) -def dictOf(): ... - -@replaced_by_pep8(original_text_for) -def originalTextFor(): ... - -@replaced_by_pep8(nested_expr) -def nestedExpr(): ... - -@replaced_by_pep8(make_html_tags) -def makeHTMLTags(): ... - -@replaced_by_pep8(make_xml_tags) -def makeXMLTags(): ... - -@replaced_by_pep8(replace_html_entity) -def replaceHTMLEntity(): ... - -@replaced_by_pep8(infix_notation) -def infixNotation(): ... -# fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/results.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/results.py deleted file mode 100644 index 0313049..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/results.py +++ /dev/null @@ -1,796 +0,0 @@ -# results.py -from collections.abc import ( - MutableMapping, - Mapping, - MutableSequence, - Iterator, - Sequence, - Container, -) -import pprint -from typing import Tuple, Any, Dict, Set, List - -str_type: Tuple[type, ...] = (str, bytes) -_generator_type = type((_ for _ in ())) - - -class _ParseResultsWithOffset: - tup: Tuple["ParseResults", int] - __slots__ = ["tup"] - - def __init__(self, p1: "ParseResults", p2: int): - self.tup: Tuple[ParseResults, int] = (p1, p2) - - def __getitem__(self, i): - return self.tup[i] - - def __getstate__(self): - return self.tup - - def __setstate__(self, *args): - self.tup = args[0] - - -class ParseResults: - """Structured parse results, to provide multiple means of access to - the parsed data: - - - as a list (``len(results)``) - - by list index (``results[0], results[1]``, etc.) - - by attribute (``results.`` - see :class:`ParserElement.set_results_name`) - - Example:: - - integer = Word(nums) - date_str = (integer.set_results_name("year") + '/' - + integer.set_results_name("month") + '/' - + integer.set_results_name("day")) - # equivalent form: - # date_str = (integer("year") + '/' - # + integer("month") + '/' - # + integer("day")) - - # parse_string returns a ParseResults object - result = date_str.parse_string("1999/12/31") - - def test(s, fn=repr): - print(f"{s} -> {fn(eval(s))}") - test("list(result)") - test("result[0]") - test("result['month']") - test("result.day") - test("'month' in result") - test("'minutes' in result") - test("result.dump()", str) - - prints:: - - list(result) -> ['1999', '/', '12', '/', '31'] - result[0] -> '1999' - result['month'] -> '12' - result.day -> '31' - 'month' in result -> True - 'minutes' in result -> False - result.dump() -> ['1999', '/', '12', '/', '31'] - - day: '31' - - month: '12' - - year: '1999' - """ - - _null_values: Tuple[Any, ...] = (None, [], ()) - - _name: str - _parent: "ParseResults" - _all_names: Set[str] - _modal: bool - _toklist: List[Any] - _tokdict: Dict[str, Any] - - __slots__ = ( - "_name", - "_parent", - "_all_names", - "_modal", - "_toklist", - "_tokdict", - ) - - class List(list): - """ - Simple wrapper class to distinguish parsed list results that should be preserved - as actual Python lists, instead of being converted to :class:`ParseResults`:: - - LBRACK, RBRACK = map(pp.Suppress, "[]") - element = pp.Forward() - item = ppc.integer - element_list = LBRACK + pp.DelimitedList(element) + RBRACK - - # add parse actions to convert from ParseResults to actual Python collection types - def as_python_list(t): - return pp.ParseResults.List(t.as_list()) - element_list.add_parse_action(as_python_list) - - element <<= item | element_list - - element.run_tests(''' - 100 - [2,3,4] - [[2, 1],3,4] - [(2, 1),3,4] - (2,3,4) - ''', post_parse=lambda s, r: (r[0], type(r[0]))) - - prints:: - - 100 - (100, ) - - [2,3,4] - ([2, 3, 4], ) - - [[2, 1],3,4] - ([[2, 1], 3, 4], ) - - (Used internally by :class:`Group` when `aslist=True`.) - """ - - def __new__(cls, contained=None): - if contained is None: - contained = [] - - if not isinstance(contained, list): - raise TypeError( - f"{cls.__name__} may only be constructed with a list, not {type(contained).__name__}" - ) - - return list.__new__(cls) - - def __new__(cls, toklist=None, name=None, **kwargs): - if isinstance(toklist, ParseResults): - return toklist - self = object.__new__(cls) - self._name = None - self._parent = None - self._all_names = set() - - if toklist is None: - self._toklist = [] - elif isinstance(toklist, (list, _generator_type)): - self._toklist = ( - [toklist[:]] - if isinstance(toklist, ParseResults.List) - else list(toklist) - ) - else: - self._toklist = [toklist] - self._tokdict = dict() - return self - - # Performance tuning: we construct a *lot* of these, so keep this - # constructor as small and fast as possible - def __init__( - self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance - ): - self._tokdict: Dict[str, _ParseResultsWithOffset] - self._modal = modal - if name is not None and name != "": - if isinstance(name, int): - name = str(name) - if not modal: - self._all_names = {name} - self._name = name - if toklist not in self._null_values: - if isinstance(toklist, (str_type, type)): - toklist = [toklist] - if asList: - if isinstance(toklist, ParseResults): - self[name] = _ParseResultsWithOffset( - ParseResults(toklist._toklist), 0 - ) - else: - self[name] = _ParseResultsWithOffset( - ParseResults(toklist[0]), 0 - ) - self[name]._name = name - else: - try: - self[name] = toklist[0] - except (KeyError, TypeError, IndexError): - if toklist is not self: - self[name] = toklist - else: - self._name = name - - def __getitem__(self, i): - if isinstance(i, (int, slice)): - return self._toklist[i] - else: - if i not in self._all_names: - return self._tokdict[i][-1][0] - else: - return ParseResults([v[0] for v in self._tokdict[i]]) - - def __setitem__(self, k, v, isinstance=isinstance): - if isinstance(v, _ParseResultsWithOffset): - self._tokdict[k] = self._tokdict.get(k, list()) + [v] - sub = v[0] - elif isinstance(k, (int, slice)): - self._toklist[k] = v - sub = v - else: - self._tokdict[k] = self._tokdict.get(k, list()) + [ - _ParseResultsWithOffset(v, 0) - ] - sub = v - if isinstance(sub, ParseResults): - sub._parent = self - - def __delitem__(self, i): - if isinstance(i, (int, slice)): - mylen = len(self._toklist) - del self._toklist[i] - - # convert int to slice - if isinstance(i, int): - if i < 0: - i += mylen - i = slice(i, i + 1) - # get removed indices - removed = list(range(*i.indices(mylen))) - removed.reverse() - # fixup indices in token dictionary - for name, occurrences in self._tokdict.items(): - for j in removed: - for k, (value, position) in enumerate(occurrences): - occurrences[k] = _ParseResultsWithOffset( - value, position - (position > j) - ) - else: - del self._tokdict[i] - - def __contains__(self, k) -> bool: - return k in self._tokdict - - def __len__(self) -> int: - return len(self._toklist) - - def __bool__(self) -> bool: - return not not (self._toklist or self._tokdict) - - def __iter__(self) -> Iterator: - return iter(self._toklist) - - def __reversed__(self) -> Iterator: - return iter(self._toklist[::-1]) - - def keys(self): - return iter(self._tokdict) - - def values(self): - return (self[k] for k in self.keys()) - - def items(self): - return ((k, self[k]) for k in self.keys()) - - def haskeys(self) -> bool: - """ - Since ``keys()`` returns an iterator, this method is helpful in bypassing - code that looks for the existence of any defined results names.""" - return not not self._tokdict - - def pop(self, *args, **kwargs): - """ - Removes and returns item at specified index (default= ``last``). - Supports both ``list`` and ``dict`` semantics for ``pop()``. If - passed no argument or an integer argument, it will use ``list`` - semantics and pop tokens from the list of parsed tokens. If passed - a non-integer argument (most likely a string), it will use ``dict`` - semantics and pop the corresponding value from any defined results - names. A second default return value argument is supported, just as in - ``dict.pop()``. - - Example:: - - numlist = Word(nums)[...] - print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] - - def remove_first(tokens): - tokens.pop(0) - numlist.add_parse_action(remove_first) - print(numlist.parse_string("0 123 321")) # -> ['123', '321'] - - label = Word(alphas) - patt = label("LABEL") + Word(nums)[1, ...] - print(patt.parse_string("AAB 123 321").dump()) - - # Use pop() in a parse action to remove named result (note that corresponding value is not - # removed from list form of results) - def remove_LABEL(tokens): - tokens.pop("LABEL") - return tokens - patt.add_parse_action(remove_LABEL) - print(patt.parse_string("AAB 123 321").dump()) - - prints:: - - ['AAB', '123', '321'] - - LABEL: 'AAB' - - ['AAB', '123', '321'] - """ - if not args: - args = [-1] - for k, v in kwargs.items(): - if k == "default": - args = (args[0], v) - else: - raise TypeError(f"pop() got an unexpected keyword argument {k!r}") - if isinstance(args[0], int) or len(args) == 1 or args[0] in self: - index = args[0] - ret = self[index] - del self[index] - return ret - else: - defaultvalue = args[1] - return defaultvalue - - def get(self, key, default_value=None): - """ - Returns named result matching the given key, or if there is no - such name, then returns the given ``default_value`` or ``None`` if no - ``default_value`` is specified. - - Similar to ``dict.get()``. - - Example:: - - integer = Word(nums) - date_str = integer("year") + '/' + integer("month") + '/' + integer("day") - - result = date_str.parse_string("1999/12/31") - print(result.get("year")) # -> '1999' - print(result.get("hour", "not specified")) # -> 'not specified' - print(result.get("hour")) # -> None - """ - if key in self: - return self[key] - else: - return default_value - - def insert(self, index, ins_string): - """ - Inserts new element at location index in the list of parsed tokens. - - Similar to ``list.insert()``. - - Example:: - - numlist = Word(nums)[...] - print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] - - # use a parse action to insert the parse location in the front of the parsed results - def insert_locn(locn, tokens): - tokens.insert(0, locn) - numlist.add_parse_action(insert_locn) - print(numlist.parse_string("0 123 321")) # -> [0, '0', '123', '321'] - """ - self._toklist.insert(index, ins_string) - # fixup indices in token dictionary - for name, occurrences in self._tokdict.items(): - for k, (value, position) in enumerate(occurrences): - occurrences[k] = _ParseResultsWithOffset( - value, position + (position > index) - ) - - def append(self, item): - """ - Add single element to end of ``ParseResults`` list of elements. - - Example:: - - numlist = Word(nums)[...] - print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] - - # use a parse action to compute the sum of the parsed integers, and add it to the end - def append_sum(tokens): - tokens.append(sum(map(int, tokens))) - numlist.add_parse_action(append_sum) - print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321', 444] - """ - self._toklist.append(item) - - def extend(self, itemseq): - """ - Add sequence of elements to end of ``ParseResults`` list of elements. - - Example:: - - patt = Word(alphas)[1, ...] - - # use a parse action to append the reverse of the matched strings, to make a palindrome - def make_palindrome(tokens): - tokens.extend(reversed([t[::-1] for t in tokens])) - return ''.join(tokens) - patt.add_parse_action(make_palindrome) - print(patt.parse_string("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl' - """ - if isinstance(itemseq, ParseResults): - self.__iadd__(itemseq) - else: - self._toklist.extend(itemseq) - - def clear(self): - """ - Clear all elements and results names. - """ - del self._toklist[:] - self._tokdict.clear() - - def __getattr__(self, name): - try: - return self[name] - except KeyError: - if name.startswith("__"): - raise AttributeError(name) - return "" - - def __add__(self, other: "ParseResults") -> "ParseResults": - ret = self.copy() - ret += other - return ret - - def __iadd__(self, other: "ParseResults") -> "ParseResults": - if not other: - return self - - if other._tokdict: - offset = len(self._toklist) - addoffset = lambda a: offset if a < 0 else a + offset - otheritems = other._tokdict.items() - otherdictitems = [ - (k, _ParseResultsWithOffset(v[0], addoffset(v[1]))) - for k, vlist in otheritems - for v in vlist - ] - for k, v in otherdictitems: - self[k] = v - if isinstance(v[0], ParseResults): - v[0]._parent = self - - self._toklist += other._toklist - self._all_names |= other._all_names - return self - - def __radd__(self, other) -> "ParseResults": - if isinstance(other, int) and other == 0: - # useful for merging many ParseResults using sum() builtin - return self.copy() - else: - # this may raise a TypeError - so be it - return other + self - - def __repr__(self) -> str: - return f"{type(self).__name__}({self._toklist!r}, {self.as_dict()})" - - def __str__(self) -> str: - return ( - "[" - + ", ".join( - [ - str(i) if isinstance(i, ParseResults) else repr(i) - for i in self._toklist - ] - ) - + "]" - ) - - def _asStringList(self, sep=""): - out = [] - for item in self._toklist: - if out and sep: - out.append(sep) - if isinstance(item, ParseResults): - out += item._asStringList() - else: - out.append(str(item)) - return out - - def as_list(self) -> list: - """ - Returns the parse results as a nested list of matching tokens, all converted to strings. - - Example:: - - patt = Word(alphas)[1, ...] - result = patt.parse_string("sldkj lsdkj sldkj") - # even though the result prints in string-like form, it is actually a pyparsing ParseResults - print(type(result), result) # -> ['sldkj', 'lsdkj', 'sldkj'] - - # Use as_list() to create an actual list - result_list = result.as_list() - print(type(result_list), result_list) # -> ['sldkj', 'lsdkj', 'sldkj'] - """ - return [ - res.as_list() if isinstance(res, ParseResults) else res - for res in self._toklist - ] - - def as_dict(self) -> dict: - """ - Returns the named parse results as a nested dictionary. - - Example:: - - integer = Word(nums) - date_str = integer("year") + '/' + integer("month") + '/' + integer("day") - - result = date_str.parse_string('12/31/1999') - print(type(result), repr(result)) # -> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]}) - - result_dict = result.as_dict() - print(type(result_dict), repr(result_dict)) # -> {'day': '1999', 'year': '12', 'month': '31'} - - # even though a ParseResults supports dict-like access, sometime you just need to have a dict - import json - print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable - print(json.dumps(result.as_dict())) # -> {"month": "31", "day": "1999", "year": "12"} - """ - - def to_item(obj): - if isinstance(obj, ParseResults): - return obj.as_dict() if obj.haskeys() else [to_item(v) for v in obj] - else: - return obj - - return dict((k, to_item(v)) for k, v in self.items()) - - def copy(self) -> "ParseResults": - """ - Returns a new shallow copy of a :class:`ParseResults` object. `ParseResults` - items contained within the source are shared with the copy. Use - :class:`ParseResults.deepcopy()` to create a copy with its own separate - content values. - """ - ret = ParseResults(self._toklist) - ret._tokdict = self._tokdict.copy() - ret._parent = self._parent - ret._all_names |= self._all_names - ret._name = self._name - return ret - - def deepcopy(self) -> "ParseResults": - """ - Returns a new deep copy of a :class:`ParseResults` object. - """ - ret = self.copy() - # replace values with copies if they are of known mutable types - for i, obj in enumerate(self._toklist): - if isinstance(obj, ParseResults): - self._toklist[i] = obj.deepcopy() - elif isinstance(obj, (str, bytes)): - pass - elif isinstance(obj, MutableMapping): - self._toklist[i] = dest = type(obj)() - for k, v in obj.items(): - dest[k] = v.deepcopy() if isinstance(v, ParseResults) else v - elif isinstance(obj, Container): - self._toklist[i] = type(obj)( - v.deepcopy() if isinstance(v, ParseResults) else v for v in obj - ) - return ret - - def get_name(self): - r""" - Returns the results name for this token expression. Useful when several - different expressions might match at a particular location. - - Example:: - - integer = Word(nums) - ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d") - house_number_expr = Suppress('#') + Word(nums, alphanums) - user_data = (Group(house_number_expr)("house_number") - | Group(ssn_expr)("ssn") - | Group(integer)("age")) - user_info = user_data[1, ...] - - result = user_info.parse_string("22 111-22-3333 #221B") - for item in result: - print(item.get_name(), ':', item[0]) - - prints:: - - age : 22 - ssn : 111-22-3333 - house_number : 221B - """ - if self._name: - return self._name - elif self._parent: - par: "ParseResults" = self._parent - parent_tokdict_items = par._tokdict.items() - return next( - ( - k - for k, vlist in parent_tokdict_items - for v, loc in vlist - if v is self - ), - None, - ) - elif ( - len(self) == 1 - and len(self._tokdict) == 1 - and next(iter(self._tokdict.values()))[0][1] in (0, -1) - ): - return next(iter(self._tokdict.keys())) - else: - return None - - def dump(self, indent="", full=True, include_list=True, _depth=0) -> str: - """ - Diagnostic method for listing out the contents of - a :class:`ParseResults`. Accepts an optional ``indent`` argument so - that this string can be embedded in a nested display of other data. - - Example:: - - integer = Word(nums) - date_str = integer("year") + '/' + integer("month") + '/' + integer("day") - - result = date_str.parse_string('1999/12/31') - print(result.dump()) - - prints:: - - ['1999', '/', '12', '/', '31'] - - day: '31' - - month: '12' - - year: '1999' - """ - out = [] - NL = "\n" - out.append(indent + str(self.as_list()) if include_list else "") - - if full: - if self.haskeys(): - items = sorted((str(k), v) for k, v in self.items()) - for k, v in items: - if out: - out.append(NL) - out.append(f"{indent}{(' ' * _depth)}- {k}: ") - if isinstance(v, ParseResults): - if v: - out.append( - v.dump( - indent=indent, - full=full, - include_list=include_list, - _depth=_depth + 1, - ) - ) - else: - out.append(str(v)) - else: - out.append(repr(v)) - if any(isinstance(vv, ParseResults) for vv in self): - v = self - for i, vv in enumerate(v): - if isinstance(vv, ParseResults): - out.append( - "\n{}{}[{}]:\n{}{}{}".format( - indent, - (" " * (_depth)), - i, - indent, - (" " * (_depth + 1)), - vv.dump( - indent=indent, - full=full, - include_list=include_list, - _depth=_depth + 1, - ), - ) - ) - else: - out.append( - "\n%s%s[%d]:\n%s%s%s" - % ( - indent, - (" " * (_depth)), - i, - indent, - (" " * (_depth + 1)), - str(vv), - ) - ) - - return "".join(out) - - def pprint(self, *args, **kwargs): - """ - Pretty-printer for parsed results as a list, using the - `pprint `_ module. - Accepts additional positional or keyword args as defined for - `pprint.pprint `_ . - - Example:: - - ident = Word(alphas, alphanums) - num = Word(nums) - func = Forward() - term = ident | num | Group('(' + func + ')') - func <<= ident + Group(Optional(DelimitedList(term))) - result = func.parse_string("fna a,b,(fnb c,d,200),100") - result.pprint(width=40) - - prints:: - - ['fna', - ['a', - 'b', - ['(', 'fnb', ['c', 'd', '200'], ')'], - '100']] - """ - pprint.pprint(self.as_list(), *args, **kwargs) - - # add support for pickle protocol - def __getstate__(self): - return ( - self._toklist, - ( - self._tokdict.copy(), - None, - self._all_names, - self._name, - ), - ) - - def __setstate__(self, state): - self._toklist, (self._tokdict, par, inAccumNames, self._name) = state - self._all_names = set(inAccumNames) - self._parent = None - - def __getnewargs__(self): - return self._toklist, self._name - - def __dir__(self): - return dir(type(self)) + list(self.keys()) - - @classmethod - def from_dict(cls, other, name=None) -> "ParseResults": - """ - Helper classmethod to construct a ``ParseResults`` from a ``dict``, preserving the - name-value relations as results names. If an optional ``name`` argument is - given, a nested ``ParseResults`` will be returned. - """ - - def is_iterable(obj): - try: - iter(obj) - except Exception: - return False - # str's are iterable, but in pyparsing, we don't want to iterate over them - else: - return not isinstance(obj, str_type) - - ret = cls([]) - for k, v in other.items(): - if isinstance(v, Mapping): - ret += cls.from_dict(v, name=k) - else: - ret += cls([v], name=k, asList=is_iterable(v)) - if name is not None: - ret = cls([ret], name=name) - return ret - - asList = as_list - """Deprecated - use :class:`as_list`""" - asDict = as_dict - """Deprecated - use :class:`as_dict`""" - getName = get_name - """Deprecated - use :class:`get_name`""" - - -MutableMapping.register(ParseResults) -MutableSequence.register(ParseResults) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/testing.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/testing.py deleted file mode 100644 index 6a254c1..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/testing.py +++ /dev/null @@ -1,331 +0,0 @@ -# testing.py - -from contextlib import contextmanager -import typing - -from .core import ( - ParserElement, - ParseException, - Keyword, - __diag__, - __compat__, -) - - -class pyparsing_test: - """ - namespace class for classes useful in writing unit tests - """ - - class reset_pyparsing_context: - """ - Context manager to be used when writing unit tests that modify pyparsing config values: - - packrat parsing - - bounded recursion parsing - - default whitespace characters. - - default keyword characters - - literal string auto-conversion class - - __diag__ settings - - Example:: - - with reset_pyparsing_context(): - # test that literals used to construct a grammar are automatically suppressed - ParserElement.inlineLiteralsUsing(Suppress) - - term = Word(alphas) | Word(nums) - group = Group('(' + term[...] + ')') - - # assert that the '()' characters are not included in the parsed tokens - self.assertParseAndCheckList(group, "(abc 123 def)", ['abc', '123', 'def']) - - # after exiting context manager, literals are converted to Literal expressions again - """ - - def __init__(self): - self._save_context = {} - - def save(self): - self._save_context["default_whitespace"] = ParserElement.DEFAULT_WHITE_CHARS - self._save_context["default_keyword_chars"] = Keyword.DEFAULT_KEYWORD_CHARS - - self._save_context[ - "literal_string_class" - ] = ParserElement._literalStringClass - - self._save_context["verbose_stacktrace"] = ParserElement.verbose_stacktrace - - self._save_context["packrat_enabled"] = ParserElement._packratEnabled - if ParserElement._packratEnabled: - self._save_context[ - "packrat_cache_size" - ] = ParserElement.packrat_cache.size - else: - self._save_context["packrat_cache_size"] = None - self._save_context["packrat_parse"] = ParserElement._parse - self._save_context[ - "recursion_enabled" - ] = ParserElement._left_recursion_enabled - - self._save_context["__diag__"] = { - name: getattr(__diag__, name) for name in __diag__._all_names - } - - self._save_context["__compat__"] = { - "collect_all_And_tokens": __compat__.collect_all_And_tokens - } - - return self - - def restore(self): - # reset pyparsing global state - if ( - ParserElement.DEFAULT_WHITE_CHARS - != self._save_context["default_whitespace"] - ): - ParserElement.set_default_whitespace_chars( - self._save_context["default_whitespace"] - ) - - ParserElement.verbose_stacktrace = self._save_context["verbose_stacktrace"] - - Keyword.DEFAULT_KEYWORD_CHARS = self._save_context["default_keyword_chars"] - ParserElement.inlineLiteralsUsing( - self._save_context["literal_string_class"] - ) - - for name, value in self._save_context["__diag__"].items(): - (__diag__.enable if value else __diag__.disable)(name) - - ParserElement._packratEnabled = False - if self._save_context["packrat_enabled"]: - ParserElement.enable_packrat(self._save_context["packrat_cache_size"]) - else: - ParserElement._parse = self._save_context["packrat_parse"] - ParserElement._left_recursion_enabled = self._save_context[ - "recursion_enabled" - ] - - __compat__.collect_all_And_tokens = self._save_context["__compat__"] - - return self - - def copy(self): - ret = type(self)() - ret._save_context.update(self._save_context) - return ret - - def __enter__(self): - return self.save() - - def __exit__(self, *args): - self.restore() - - class TestParseResultsAsserts: - """ - A mixin class to add parse results assertion methods to normal unittest.TestCase classes. - """ - - def assertParseResultsEquals( - self, result, expected_list=None, expected_dict=None, msg=None - ): - """ - Unit test assertion to compare a :class:`ParseResults` object with an optional ``expected_list``, - and compare any defined results names with an optional ``expected_dict``. - """ - if expected_list is not None: - self.assertEqual(expected_list, result.as_list(), msg=msg) - if expected_dict is not None: - self.assertEqual(expected_dict, result.as_dict(), msg=msg) - - def assertParseAndCheckList( - self, expr, test_string, expected_list, msg=None, verbose=True - ): - """ - Convenience wrapper assert to test a parser element and input string, and assert that - the resulting ``ParseResults.asList()`` is equal to the ``expected_list``. - """ - result = expr.parse_string(test_string, parse_all=True) - if verbose: - print(result.dump()) - else: - print(result.as_list()) - self.assertParseResultsEquals(result, expected_list=expected_list, msg=msg) - - def assertParseAndCheckDict( - self, expr, test_string, expected_dict, msg=None, verbose=True - ): - """ - Convenience wrapper assert to test a parser element and input string, and assert that - the resulting ``ParseResults.asDict()`` is equal to the ``expected_dict``. - """ - result = expr.parse_string(test_string, parseAll=True) - if verbose: - print(result.dump()) - else: - print(result.as_list()) - self.assertParseResultsEquals(result, expected_dict=expected_dict, msg=msg) - - def assertRunTestResults( - self, run_tests_report, expected_parse_results=None, msg=None - ): - """ - Unit test assertion to evaluate output of ``ParserElement.runTests()``. If a list of - list-dict tuples is given as the ``expected_parse_results`` argument, then these are zipped - with the report tuples returned by ``runTests`` and evaluated using ``assertParseResultsEquals``. - Finally, asserts that the overall ``runTests()`` success value is ``True``. - - :param run_tests_report: tuple(bool, [tuple(str, ParseResults or Exception)]) returned from runTests - :param expected_parse_results (optional): [tuple(str, list, dict, Exception)] - """ - run_test_success, run_test_results = run_tests_report - - if expected_parse_results is not None: - merged = [ - (*rpt, expected) - for rpt, expected in zip(run_test_results, expected_parse_results) - ] - for test_string, result, expected in merged: - # expected should be a tuple containing a list and/or a dict or an exception, - # and optional failure message string - # an empty tuple will skip any result validation - fail_msg = next( - (exp for exp in expected if isinstance(exp, str)), None - ) - expected_exception = next( - ( - exp - for exp in expected - if isinstance(exp, type) and issubclass(exp, Exception) - ), - None, - ) - if expected_exception is not None: - with self.assertRaises( - expected_exception=expected_exception, msg=fail_msg or msg - ): - if isinstance(result, Exception): - raise result - else: - expected_list = next( - (exp for exp in expected if isinstance(exp, list)), None - ) - expected_dict = next( - (exp for exp in expected if isinstance(exp, dict)), None - ) - if (expected_list, expected_dict) != (None, None): - self.assertParseResultsEquals( - result, - expected_list=expected_list, - expected_dict=expected_dict, - msg=fail_msg or msg, - ) - else: - # warning here maybe? - print(f"no validation for {test_string!r}") - - # do this last, in case some specific test results can be reported instead - self.assertTrue( - run_test_success, msg=msg if msg is not None else "failed runTests" - ) - - @contextmanager - def assertRaisesParseException(self, exc_type=ParseException, msg=None): - with self.assertRaises(exc_type, msg=msg): - yield - - @staticmethod - def with_line_numbers( - s: str, - start_line: typing.Optional[int] = None, - end_line: typing.Optional[int] = None, - expand_tabs: bool = True, - eol_mark: str = "|", - mark_spaces: typing.Optional[str] = None, - mark_control: typing.Optional[str] = None, - ) -> str: - """ - Helpful method for debugging a parser - prints a string with line and column numbers. - (Line and column numbers are 1-based.) - - :param s: tuple(bool, str - string to be printed with line and column numbers - :param start_line: int - (optional) starting line number in s to print (default=1) - :param end_line: int - (optional) ending line number in s to print (default=len(s)) - :param expand_tabs: bool - (optional) expand tabs to spaces, to match the pyparsing default - :param eol_mark: str - (optional) string to mark the end of lines, helps visualize trailing spaces (default="|") - :param mark_spaces: str - (optional) special character to display in place of spaces - :param mark_control: str - (optional) convert non-printing control characters to a placeholding - character; valid values: - - "unicode" - replaces control chars with Unicode symbols, such as "␍" and "␊" - - any single character string - replace control characters with given string - - None (default) - string is displayed as-is - - :return: str - input string with leading line numbers and column number headers - """ - if expand_tabs: - s = s.expandtabs() - if mark_control is not None: - mark_control = typing.cast(str, mark_control) - if mark_control == "unicode": - transtable_map = { - c: u for c, u in zip(range(0, 33), range(0x2400, 0x2433)) - } - transtable_map[127] = 0x2421 - tbl = str.maketrans(transtable_map) - eol_mark = "" - else: - ord_mark_control = ord(mark_control) - tbl = str.maketrans( - {c: ord_mark_control for c in list(range(0, 32)) + [127]} - ) - s = s.translate(tbl) - if mark_spaces is not None and mark_spaces != " ": - if mark_spaces == "unicode": - tbl = str.maketrans({9: 0x2409, 32: 0x2423}) - s = s.translate(tbl) - else: - s = s.replace(" ", mark_spaces) - if start_line is None: - start_line = 1 - if end_line is None: - end_line = len(s) - end_line = min(end_line, len(s)) - start_line = min(max(1, start_line), end_line) - - if mark_control != "unicode": - s_lines = s.splitlines()[start_line - 1 : end_line] - else: - s_lines = [line + "␊" for line in s.split("␊")[start_line - 1 : end_line]] - if not s_lines: - return "" - - lineno_width = len(str(end_line)) - max_line_len = max(len(line) for line in s_lines) - lead = " " * (lineno_width + 1) - if max_line_len >= 99: - header0 = ( - lead - + "".join( - f"{' ' * 99}{(i + 1) % 100}" - for i in range(max(max_line_len // 100, 1)) - ) - + "\n" - ) - else: - header0 = "" - header1 = ( - header0 - + lead - + "".join(f" {(i + 1) % 10}" for i in range(-(-max_line_len // 10))) - + "\n" - ) - header2 = lead + "1234567890" * (-(-max_line_len // 10)) + "\n" - return ( - header1 - + header2 - + "\n".join( - f"{i:{lineno_width}d}:{line}{eol_mark}" - for i, line in enumerate(s_lines, start=start_line) - ) - + "\n" - ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/unicode.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/unicode.py deleted file mode 100644 index ec0b3a4..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/unicode.py +++ /dev/null @@ -1,361 +0,0 @@ -# unicode.py - -import sys -from itertools import filterfalse -from typing import List, Tuple, Union - - -class _lazyclassproperty: - def __init__(self, fn): - self.fn = fn - self.__doc__ = fn.__doc__ - self.__name__ = fn.__name__ - - def __get__(self, obj, cls): - if cls is None: - cls = type(obj) - if not hasattr(cls, "_intern") or any( - cls._intern is getattr(superclass, "_intern", []) - for superclass in cls.__mro__[1:] - ): - cls._intern = {} - attrname = self.fn.__name__ - if attrname not in cls._intern: - cls._intern[attrname] = self.fn(cls) - return cls._intern[attrname] - - -UnicodeRangeList = List[Union[Tuple[int, int], Tuple[int]]] - - -class unicode_set: - """ - A set of Unicode characters, for language-specific strings for - ``alphas``, ``nums``, ``alphanums``, and ``printables``. - A unicode_set is defined by a list of ranges in the Unicode character - set, in a class attribute ``_ranges``. Ranges can be specified using - 2-tuples or a 1-tuple, such as:: - - _ranges = [ - (0x0020, 0x007e), - (0x00a0, 0x00ff), - (0x0100,), - ] - - Ranges are left- and right-inclusive. A 1-tuple of (x,) is treated as (x, x). - - A unicode set can also be defined using multiple inheritance of other unicode sets:: - - class CJK(Chinese, Japanese, Korean): - pass - """ - - _ranges: UnicodeRangeList = [] - - @_lazyclassproperty - def _chars_for_ranges(cls): - ret = [] - for cc in cls.__mro__: - if cc is unicode_set: - break - for rr in getattr(cc, "_ranges", ()): - ret.extend(range(rr[0], rr[-1] + 1)) - return [chr(c) for c in sorted(set(ret))] - - @_lazyclassproperty - def printables(cls): - """all non-whitespace characters in this range""" - return "".join(filterfalse(str.isspace, cls._chars_for_ranges)) - - @_lazyclassproperty - def alphas(cls): - """all alphabetic characters in this range""" - return "".join(filter(str.isalpha, cls._chars_for_ranges)) - - @_lazyclassproperty - def nums(cls): - """all numeric digit characters in this range""" - return "".join(filter(str.isdigit, cls._chars_for_ranges)) - - @_lazyclassproperty - def alphanums(cls): - """all alphanumeric characters in this range""" - return cls.alphas + cls.nums - - @_lazyclassproperty - def identchars(cls): - """all characters in this range that are valid identifier characters, plus underscore '_'""" - return "".join( - sorted( - set( - "".join(filter(str.isidentifier, cls._chars_for_ranges)) - + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzªµº" - + "ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ" - + "_" - ) - ) - ) - - @_lazyclassproperty - def identbodychars(cls): - """ - all characters in this range that are valid identifier body characters, - plus the digits 0-9, and · (Unicode MIDDLE DOT) - """ - return "".join( - sorted( - set( - cls.identchars - + "0123456789·" - + "".join( - [c for c in cls._chars_for_ranges if ("_" + c).isidentifier()] - ) - ) - ) - ) - - @_lazyclassproperty - def identifier(cls): - """ - a pyparsing Word expression for an identifier using this range's definitions for - identchars and identbodychars - """ - from pip._vendor.pyparsing import Word - - return Word(cls.identchars, cls.identbodychars) - - -class pyparsing_unicode(unicode_set): - """ - A namespace class for defining common language unicode_sets. - """ - - # fmt: off - - # define ranges in language character sets - _ranges: UnicodeRangeList = [ - (0x0020, sys.maxunicode), - ] - - class BasicMultilingualPlane(unicode_set): - """Unicode set for the Basic Multilingual Plane""" - _ranges: UnicodeRangeList = [ - (0x0020, 0xFFFF), - ] - - class Latin1(unicode_set): - """Unicode set for Latin-1 Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0020, 0x007E), - (0x00A0, 0x00FF), - ] - - class LatinA(unicode_set): - """Unicode set for Latin-A Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0100, 0x017F), - ] - - class LatinB(unicode_set): - """Unicode set for Latin-B Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0180, 0x024F), - ] - - class Greek(unicode_set): - """Unicode set for Greek Unicode Character Ranges""" - _ranges: UnicodeRangeList = [ - (0x0342, 0x0345), - (0x0370, 0x0377), - (0x037A, 0x037F), - (0x0384, 0x038A), - (0x038C,), - (0x038E, 0x03A1), - (0x03A3, 0x03E1), - (0x03F0, 0x03FF), - (0x1D26, 0x1D2A), - (0x1D5E,), - (0x1D60,), - (0x1D66, 0x1D6A), - (0x1F00, 0x1F15), - (0x1F18, 0x1F1D), - (0x1F20, 0x1F45), - (0x1F48, 0x1F4D), - (0x1F50, 0x1F57), - (0x1F59,), - (0x1F5B,), - (0x1F5D,), - (0x1F5F, 0x1F7D), - (0x1F80, 0x1FB4), - (0x1FB6, 0x1FC4), - (0x1FC6, 0x1FD3), - (0x1FD6, 0x1FDB), - (0x1FDD, 0x1FEF), - (0x1FF2, 0x1FF4), - (0x1FF6, 0x1FFE), - (0x2129,), - (0x2719, 0x271A), - (0xAB65,), - (0x10140, 0x1018D), - (0x101A0,), - (0x1D200, 0x1D245), - (0x1F7A1, 0x1F7A7), - ] - - class Cyrillic(unicode_set): - """Unicode set for Cyrillic Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0400, 0x052F), - (0x1C80, 0x1C88), - (0x1D2B,), - (0x1D78,), - (0x2DE0, 0x2DFF), - (0xA640, 0xA672), - (0xA674, 0xA69F), - (0xFE2E, 0xFE2F), - ] - - class Chinese(unicode_set): - """Unicode set for Chinese Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x2E80, 0x2E99), - (0x2E9B, 0x2EF3), - (0x31C0, 0x31E3), - (0x3400, 0x4DB5), - (0x4E00, 0x9FEF), - (0xA700, 0xA707), - (0xF900, 0xFA6D), - (0xFA70, 0xFAD9), - (0x16FE2, 0x16FE3), - (0x1F210, 0x1F212), - (0x1F214, 0x1F23B), - (0x1F240, 0x1F248), - (0x20000, 0x2A6D6), - (0x2A700, 0x2B734), - (0x2B740, 0x2B81D), - (0x2B820, 0x2CEA1), - (0x2CEB0, 0x2EBE0), - (0x2F800, 0x2FA1D), - ] - - class Japanese(unicode_set): - """Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana ranges""" - - class Kanji(unicode_set): - "Unicode set for Kanji Unicode Character Range" - _ranges: UnicodeRangeList = [ - (0x4E00, 0x9FBF), - (0x3000, 0x303F), - ] - - class Hiragana(unicode_set): - """Unicode set for Hiragana Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x3041, 0x3096), - (0x3099, 0x30A0), - (0x30FC,), - (0xFF70,), - (0x1B001,), - (0x1B150, 0x1B152), - (0x1F200,), - ] - - class Katakana(unicode_set): - """Unicode set for Katakana Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x3099, 0x309C), - (0x30A0, 0x30FF), - (0x31F0, 0x31FF), - (0x32D0, 0x32FE), - (0xFF65, 0xFF9F), - (0x1B000,), - (0x1B164, 0x1B167), - (0x1F201, 0x1F202), - (0x1F213,), - ] - - 漢字 = Kanji - カタカナ = Katakana - ひらがな = Hiragana - - _ranges = ( - Kanji._ranges - + Hiragana._ranges - + Katakana._ranges - ) - - class Hangul(unicode_set): - """Unicode set for Hangul (Korean) Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x1100, 0x11FF), - (0x302E, 0x302F), - (0x3131, 0x318E), - (0x3200, 0x321C), - (0x3260, 0x327B), - (0x327E,), - (0xA960, 0xA97C), - (0xAC00, 0xD7A3), - (0xD7B0, 0xD7C6), - (0xD7CB, 0xD7FB), - (0xFFA0, 0xFFBE), - (0xFFC2, 0xFFC7), - (0xFFCA, 0xFFCF), - (0xFFD2, 0xFFD7), - (0xFFDA, 0xFFDC), - ] - - Korean = Hangul - - class CJK(Chinese, Japanese, Hangul): - """Unicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character Range""" - - class Thai(unicode_set): - """Unicode set for Thai Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0E01, 0x0E3A), - (0x0E3F, 0x0E5B) - ] - - class Arabic(unicode_set): - """Unicode set for Arabic Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0600, 0x061B), - (0x061E, 0x06FF), - (0x0700, 0x077F), - ] - - class Hebrew(unicode_set): - """Unicode set for Hebrew Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0591, 0x05C7), - (0x05D0, 0x05EA), - (0x05EF, 0x05F4), - (0xFB1D, 0xFB36), - (0xFB38, 0xFB3C), - (0xFB3E,), - (0xFB40, 0xFB41), - (0xFB43, 0xFB44), - (0xFB46, 0xFB4F), - ] - - class Devanagari(unicode_set): - """Unicode set for Devanagari Unicode Character Range""" - _ranges: UnicodeRangeList = [ - (0x0900, 0x097F), - (0xA8E0, 0xA8FF) - ] - - BMP = BasicMultilingualPlane - - # add language identifiers using language Unicode - العربية = Arabic - 中文 = Chinese - кириллица = Cyrillic - Ελληνικά = Greek - עִברִית = Hebrew - 日本語 = Japanese - 한국어 = Korean - ไทย = Thai - देवनागरी = Devanagari - - # fmt: on diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/util.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/util.py deleted file mode 100644 index d8d3f41..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyparsing/util.py +++ /dev/null @@ -1,284 +0,0 @@ -# util.py -import inspect -import warnings -import types -import collections -import itertools -from functools import lru_cache, wraps -from typing import Callable, List, Union, Iterable, TypeVar, cast - -_bslash = chr(92) -C = TypeVar("C", bound=Callable) - - -class __config_flags: - """Internal class for defining compatibility and debugging flags""" - - _all_names: List[str] = [] - _fixed_names: List[str] = [] - _type_desc = "configuration" - - @classmethod - def _set(cls, dname, value): - if dname in cls._fixed_names: - warnings.warn( - f"{cls.__name__}.{dname} {cls._type_desc} is {str(getattr(cls, dname)).upper()}" - f" and cannot be overridden", - stacklevel=3, - ) - return - if dname in cls._all_names: - setattr(cls, dname, value) - else: - raise ValueError(f"no such {cls._type_desc} {dname!r}") - - enable = classmethod(lambda cls, name: cls._set(name, True)) - disable = classmethod(lambda cls, name: cls._set(name, False)) - - -@lru_cache(maxsize=128) -def col(loc: int, strg: str) -> int: - """ - Returns current column within a string, counting newlines as line separators. - The first column is number 1. - - Note: the default parsing behavior is to expand tabs in the input string - before starting the parsing process. See - :class:`ParserElement.parse_string` for more - information on parsing strings containing ```` s, and suggested - methods to maintain a consistent view of the parsed string, the parse - location, and line and column positions within the parsed string. - """ - s = strg - return 1 if 0 < loc < len(s) and s[loc - 1] == "\n" else loc - s.rfind("\n", 0, loc) - - -@lru_cache(maxsize=128) -def lineno(loc: int, strg: str) -> int: - """Returns current line number within a string, counting newlines as line separators. - The first line is number 1. - - Note - the default parsing behavior is to expand tabs in the input string - before starting the parsing process. See :class:`ParserElement.parse_string` - for more information on parsing strings containing ```` s, and - suggested methods to maintain a consistent view of the parsed string, the - parse location, and line and column positions within the parsed string. - """ - return strg.count("\n", 0, loc) + 1 - - -@lru_cache(maxsize=128) -def line(loc: int, strg: str) -> str: - """ - Returns the line of text containing loc within a string, counting newlines as line separators. - """ - last_cr = strg.rfind("\n", 0, loc) - next_cr = strg.find("\n", loc) - return strg[last_cr + 1 : next_cr] if next_cr >= 0 else strg[last_cr + 1 :] - - -class _UnboundedCache: - def __init__(self): - cache = {} - cache_get = cache.get - self.not_in_cache = not_in_cache = object() - - def get(_, key): - return cache_get(key, not_in_cache) - - def set_(_, key, value): - cache[key] = value - - def clear(_): - cache.clear() - - self.size = None - self.get = types.MethodType(get, self) - self.set = types.MethodType(set_, self) - self.clear = types.MethodType(clear, self) - - -class _FifoCache: - def __init__(self, size): - self.not_in_cache = not_in_cache = object() - cache = {} - keyring = [object()] * size - cache_get = cache.get - cache_pop = cache.pop - keyiter = itertools.cycle(range(size)) - - def get(_, key): - return cache_get(key, not_in_cache) - - def set_(_, key, value): - cache[key] = value - i = next(keyiter) - cache_pop(keyring[i], None) - keyring[i] = key - - def clear(_): - cache.clear() - keyring[:] = [object()] * size - - self.size = size - self.get = types.MethodType(get, self) - self.set = types.MethodType(set_, self) - self.clear = types.MethodType(clear, self) - - -class LRUMemo: - """ - A memoizing mapping that retains `capacity` deleted items - - The memo tracks retained items by their access order; once `capacity` items - are retained, the least recently used item is discarded. - """ - - def __init__(self, capacity): - self._capacity = capacity - self._active = {} - self._memory = collections.OrderedDict() - - def __getitem__(self, key): - try: - return self._active[key] - except KeyError: - self._memory.move_to_end(key) - return self._memory[key] - - def __setitem__(self, key, value): - self._memory.pop(key, None) - self._active[key] = value - - def __delitem__(self, key): - try: - value = self._active.pop(key) - except KeyError: - pass - else: - while len(self._memory) >= self._capacity: - self._memory.popitem(last=False) - self._memory[key] = value - - def clear(self): - self._active.clear() - self._memory.clear() - - -class UnboundedMemo(dict): - """ - A memoizing mapping that retains all deleted items - """ - - def __delitem__(self, key): - pass - - -def _escape_regex_range_chars(s: str) -> str: - # escape these chars: ^-[] - for c in r"\^-[]": - s = s.replace(c, _bslash + c) - s = s.replace("\n", r"\n") - s = s.replace("\t", r"\t") - return str(s) - - -def _collapse_string_to_ranges( - s: Union[str, Iterable[str]], re_escape: bool = True -) -> str: - def is_consecutive(c): - c_int = ord(c) - is_consecutive.prev, prev = c_int, is_consecutive.prev - if c_int - prev > 1: - is_consecutive.value = next(is_consecutive.counter) - return is_consecutive.value - - is_consecutive.prev = 0 # type: ignore [attr-defined] - is_consecutive.counter = itertools.count() # type: ignore [attr-defined] - is_consecutive.value = -1 # type: ignore [attr-defined] - - def escape_re_range_char(c): - return "\\" + c if c in r"\^-][" else c - - def no_escape_re_range_char(c): - return c - - if not re_escape: - escape_re_range_char = no_escape_re_range_char - - ret = [] - s = "".join(sorted(set(s))) - if len(s) > 3: - for _, chars in itertools.groupby(s, key=is_consecutive): - first = last = next(chars) - last = collections.deque( - itertools.chain(iter([last]), chars), maxlen=1 - ).pop() - if first == last: - ret.append(escape_re_range_char(first)) - else: - sep = "" if ord(last) == ord(first) + 1 else "-" - ret.append( - f"{escape_re_range_char(first)}{sep}{escape_re_range_char(last)}" - ) - else: - ret = [escape_re_range_char(c) for c in s] - - return "".join(ret) - - -def _flatten(ll: list) -> list: - ret = [] - for i in ll: - if isinstance(i, list): - ret.extend(_flatten(i)) - else: - ret.append(i) - return ret - - -def _make_synonym_function(compat_name: str, fn: C) -> C: - # In a future version, uncomment the code in the internal _inner() functions - # to begin emitting DeprecationWarnings. - - # Unwrap staticmethod/classmethod - fn = getattr(fn, "__func__", fn) - - # (Presence of 'self' arg in signature is used by explain_exception() methods, so we take - # some extra steps to add it if present in decorated function.) - if "self" == list(inspect.signature(fn).parameters)[0]: - - @wraps(fn) - def _inner(self, *args, **kwargs): - # warnings.warn( - # f"Deprecated - use {fn.__name__}", DeprecationWarning, stacklevel=3 - # ) - return fn(self, *args, **kwargs) - - else: - - @wraps(fn) - def _inner(*args, **kwargs): - # warnings.warn( - # f"Deprecated - use {fn.__name__}", DeprecationWarning, stacklevel=3 - # ) - return fn(*args, **kwargs) - - _inner.__doc__ = f"""Deprecated - use :class:`{fn.__name__}`""" - _inner.__name__ = compat_name - _inner.__annotations__ = fn.__annotations__ - if isinstance(fn, types.FunctionType): - _inner.__kwdefaults__ = fn.__kwdefaults__ - elif isinstance(fn, type) and hasattr(fn, "__init__"): - _inner.__kwdefaults__ = fn.__init__.__kwdefaults__ - else: - _inner.__kwdefaults__ = None - _inner.__qualname__ = fn.__qualname__ - return cast(C, _inner) - - -def replaced_by_pep8(fn: C) -> Callable[[Callable], C]: - """ - Decorator for pre-PEP8 compatibility synonyms, to link them to the new function. - """ - return lambda other: _make_synonym_function(other.__name__, fn) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__init__.py index ddfcf7f..746b89f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__init__.py @@ -1,8 +1,9 @@ """Wrappers to call pyproject.toml-based build backend hooks. """ +from typing import TYPE_CHECKING + from ._impl import ( - BackendInvalid, BackendUnavailable, BuildBackendHookCaller, HookMissing, @@ -11,13 +12,20 @@ from ._impl import ( quiet_subprocess_runner, ) -__version__ = '1.0.0' +__version__ = "1.2.0" __all__ = [ - 'BackendUnavailable', - 'BackendInvalid', - 'HookMissing', - 'UnsupportedOperation', - 'default_subprocess_runner', - 'quiet_subprocess_runner', - 'BuildBackendHookCaller', + "BackendUnavailable", + "BackendInvalid", + "HookMissing", + "UnsupportedOperation", + "default_subprocess_runner", + "quiet_subprocess_runner", + "BuildBackendHookCaller", ] + +BackendInvalid = BackendUnavailable # Deprecated alias, previously a separate exception + +if TYPE_CHECKING: + from ._impl import SubprocessRunner + + __all__ += ["SubprocessRunner"] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/__init__.cpython-312.pyc index 56f8dc8..1c46e49 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/_compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/_compat.cpython-312.pyc deleted file mode 100644 index 446b5b4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/_compat.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/_impl.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/_impl.cpython-312.pyc index 1104783..c003e1f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/_impl.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/__pycache__/_impl.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_compat.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_compat.py deleted file mode 100644 index 95e509c..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_compat.py +++ /dev/null @@ -1,8 +0,0 @@ -__all__ = ("tomllib",) - -import sys - -if sys.version_info >= (3, 11): - import tomllib -else: - from pip._vendor import tomli as tomllib diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_impl.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_impl.py index 37b0e65..d1e9d7b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_impl.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_impl.py @@ -6,48 +6,72 @@ from contextlib import contextmanager from os.path import abspath from os.path import join as pjoin from subprocess import STDOUT, check_call, check_output +from typing import TYPE_CHECKING, Any, Iterator, Mapping, Optional, Sequence from ._in_process import _in_proc_script_path +if TYPE_CHECKING: + from typing import Protocol -def write_json(obj, path, **kwargs): - with open(path, 'w', encoding='utf-8') as f: + class SubprocessRunner(Protocol): + """A protocol for the subprocess runner.""" + + def __call__( + self, + cmd: Sequence[str], + cwd: Optional[str] = None, + extra_environ: Optional[Mapping[str, str]] = None, + ) -> None: + ... + + +def write_json(obj: Mapping[str, Any], path: str, **kwargs) -> None: + with open(path, "w", encoding="utf-8") as f: json.dump(obj, f, **kwargs) -def read_json(path): - with open(path, encoding='utf-8') as f: +def read_json(path: str) -> Mapping[str, Any]: + with open(path, encoding="utf-8") as f: return json.load(f) class BackendUnavailable(Exception): """Will be raised if the backend cannot be imported in the hook process.""" - def __init__(self, traceback): - self.traceback = traceback - -class BackendInvalid(Exception): - """Will be raised if the backend is invalid.""" - def __init__(self, backend_name, backend_path, message): - super().__init__(message) + def __init__( + self, + traceback: str, + message: Optional[str] = None, + backend_name: Optional[str] = None, + backend_path: Optional[Sequence[str]] = None, + ) -> None: + # Preserving arg order for the sake of API backward compatibility. self.backend_name = backend_name self.backend_path = backend_path + self.traceback = traceback + super().__init__(message or "Error while importing backend") class HookMissing(Exception): """Will be raised on missing hooks (if a fallback can't be used).""" - def __init__(self, hook_name): + + def __init__(self, hook_name: str) -> None: super().__init__(hook_name) self.hook_name = hook_name class UnsupportedOperation(Exception): """May be raised by build_sdist if the backend indicates that it can't.""" - def __init__(self, traceback): + + def __init__(self, traceback: str) -> None: self.traceback = traceback -def default_subprocess_runner(cmd, cwd=None, extra_environ=None): +def default_subprocess_runner( + cmd: Sequence[str], + cwd: Optional[str] = None, + extra_environ: Optional[Mapping[str, str]] = None, +) -> None: """The default method of calling the wrapper subprocess. This uses :func:`subprocess.check_call` under the hood. @@ -59,7 +83,11 @@ def default_subprocess_runner(cmd, cwd=None, extra_environ=None): check_call(cmd, cwd=cwd, env=env) -def quiet_subprocess_runner(cmd, cwd=None, extra_environ=None): +def quiet_subprocess_runner( + cmd: Sequence[str], + cwd: Optional[str] = None, + extra_environ: Optional[Mapping[str, str]] = None, +) -> None: """Call the subprocess while suppressing output. This uses :func:`subprocess.check_output` under the hood. @@ -71,7 +99,7 @@ def quiet_subprocess_runner(cmd, cwd=None, extra_environ=None): check_output(cmd, cwd=cwd, env=env, stderr=STDOUT) -def norm_and_check(source_tree, requested): +def norm_and_check(source_tree: str, requested: str) -> str: """Normalise and check a backend path. Ensure that the requested backend path is specified as a relative path, @@ -96,17 +124,16 @@ def norm_and_check(source_tree, requested): class BuildBackendHookCaller: - """A wrapper to call the build backend hooks for a source directory. - """ + """A wrapper to call the build backend hooks for a source directory.""" def __init__( - self, - source_dir, - build_backend, - backend_path=None, - runner=None, - python_executable=None, - ): + self, + source_dir: str, + build_backend: str, + backend_path: Optional[Sequence[str]] = None, + runner: Optional["SubprocessRunner"] = None, + python_executable: Optional[str] = None, + ) -> None: """ :param source_dir: The source directory to invoke the build backend for :param build_backend: The build backend spec @@ -121,9 +148,7 @@ class BuildBackendHookCaller: self.source_dir = abspath(source_dir) self.build_backend = build_backend if backend_path: - backend_path = [ - norm_and_check(self.source_dir, p) for p in backend_path - ] + backend_path = [norm_and_check(self.source_dir, p) for p in backend_path] self.backend_path = backend_path self._subprocess_runner = runner if not python_executable: @@ -131,10 +156,12 @@ class BuildBackendHookCaller: self.python_executable = python_executable @contextmanager - def subprocess_runner(self, runner): + def subprocess_runner(self, runner: "SubprocessRunner") -> Iterator[None]: """A context manager for temporarily overriding the default :ref:`subprocess runner `. + :param runner: The new subprocess runner to use within the context. + .. code-block:: python hook_caller = BuildBackendHookCaller(...) @@ -148,33 +175,44 @@ class BuildBackendHookCaller: finally: self._subprocess_runner = prev - def _supported_features(self): + def _supported_features(self) -> Sequence[str]: """Return the list of optional features supported by the backend.""" - return self._call_hook('_supported_features', {}) + return self._call_hook("_supported_features", {}) - def get_requires_for_build_wheel(self, config_settings=None): + def get_requires_for_build_wheel( + self, + config_settings: Optional[Mapping[str, Any]] = None, + ) -> Sequence[str]: """Get additional dependencies required for building a wheel. + :param config_settings: The configuration settings for the build backend :returns: A list of :pep:`dependency specifiers <508>`. - :rtype: list[str] .. admonition:: Fallback If the build backend does not defined a hook with this name, an empty list will be returned. """ - return self._call_hook('get_requires_for_build_wheel', { - 'config_settings': config_settings - }) + return self._call_hook( + "get_requires_for_build_wheel", {"config_settings": config_settings} + ) def prepare_metadata_for_build_wheel( - self, metadata_directory, config_settings=None, - _allow_fallback=True): + self, + metadata_directory: str, + config_settings: Optional[Mapping[str, Any]] = None, + _allow_fallback: bool = True, + ) -> str: """Prepare a ``*.dist-info`` folder with metadata for this project. + :param metadata_directory: The directory to write the metadata to + :param config_settings: The configuration settings for the build backend + :param _allow_fallback: + Whether to allow the fallback to building a wheel and extracting + the metadata from it. Should be passed as a keyword argument only. + :returns: Name of the newly created subfolder within ``metadata_directory``, containing the metadata. - :rtype: str .. admonition:: Fallback @@ -183,17 +221,26 @@ class BuildBackendHookCaller: wheel via the ``build_wheel`` hook and the dist-info extracted from that will be returned. """ - return self._call_hook('prepare_metadata_for_build_wheel', { - 'metadata_directory': abspath(metadata_directory), - 'config_settings': config_settings, - '_allow_fallback': _allow_fallback, - }) + return self._call_hook( + "prepare_metadata_for_build_wheel", + { + "metadata_directory": abspath(metadata_directory), + "config_settings": config_settings, + "_allow_fallback": _allow_fallback, + }, + ) def build_wheel( - self, wheel_directory, config_settings=None, - metadata_directory=None): + self, + wheel_directory: str, + config_settings: Optional[Mapping[str, Any]] = None, + metadata_directory: Optional[str] = None, + ) -> str: """Build a wheel from this project. + :param wheel_directory: The directory to write the wheel to + :param config_settings: The configuration settings for the build backend + :param metadata_directory: The directory to reuse existing metadata from :returns: The name of the newly created wheel within ``wheel_directory``. @@ -206,35 +253,48 @@ class BuildBackendHookCaller: """ if metadata_directory is not None: metadata_directory = abspath(metadata_directory) - return self._call_hook('build_wheel', { - 'wheel_directory': abspath(wheel_directory), - 'config_settings': config_settings, - 'metadata_directory': metadata_directory, - }) + return self._call_hook( + "build_wheel", + { + "wheel_directory": abspath(wheel_directory), + "config_settings": config_settings, + "metadata_directory": metadata_directory, + }, + ) - def get_requires_for_build_editable(self, config_settings=None): + def get_requires_for_build_editable( + self, + config_settings: Optional[Mapping[str, Any]] = None, + ) -> Sequence[str]: """Get additional dependencies required for building an editable wheel. + :param config_settings: The configuration settings for the build backend :returns: A list of :pep:`dependency specifiers <508>`. - :rtype: list[str] .. admonition:: Fallback If the build backend does not defined a hook with this name, an empty list will be returned. """ - return self._call_hook('get_requires_for_build_editable', { - 'config_settings': config_settings - }) + return self._call_hook( + "get_requires_for_build_editable", {"config_settings": config_settings} + ) def prepare_metadata_for_build_editable( - self, metadata_directory, config_settings=None, - _allow_fallback=True): + self, + metadata_directory: str, + config_settings: Optional[Mapping[str, Any]] = None, + _allow_fallback: bool = True, + ) -> Optional[str]: """Prepare a ``*.dist-info`` folder with metadata for this project. + :param metadata_directory: The directory to write the metadata to + :param config_settings: The configuration settings for the build backend + :param _allow_fallback: + Whether to allow the fallback to building a wheel and extracting + the metadata from it. Should be passed as a keyword argument only. :returns: Name of the newly created subfolder within ``metadata_directory``, containing the metadata. - :rtype: str .. admonition:: Fallback @@ -243,17 +303,26 @@ class BuildBackendHookCaller: wheel via the ``build_editable`` hook and the dist-info extracted from that will be returned. """ - return self._call_hook('prepare_metadata_for_build_editable', { - 'metadata_directory': abspath(metadata_directory), - 'config_settings': config_settings, - '_allow_fallback': _allow_fallback, - }) + return self._call_hook( + "prepare_metadata_for_build_editable", + { + "metadata_directory": abspath(metadata_directory), + "config_settings": config_settings, + "_allow_fallback": _allow_fallback, + }, + ) def build_editable( - self, wheel_directory, config_settings=None, - metadata_directory=None): + self, + wheel_directory: str, + config_settings: Optional[Mapping[str, Any]] = None, + metadata_directory: Optional[str] = None, + ) -> str: """Build an editable wheel from this project. + :param wheel_directory: The directory to write the wheel to + :param config_settings: The configuration settings for the build backend + :param metadata_directory: The directory to reuse existing metadata from :returns: The name of the newly created wheel within ``wheel_directory``. @@ -267,43 +336,55 @@ class BuildBackendHookCaller: """ if metadata_directory is not None: metadata_directory = abspath(metadata_directory) - return self._call_hook('build_editable', { - 'wheel_directory': abspath(wheel_directory), - 'config_settings': config_settings, - 'metadata_directory': metadata_directory, - }) + return self._call_hook( + "build_editable", + { + "wheel_directory": abspath(wheel_directory), + "config_settings": config_settings, + "metadata_directory": metadata_directory, + }, + ) - def get_requires_for_build_sdist(self, config_settings=None): + def get_requires_for_build_sdist( + self, + config_settings: Optional[Mapping[str, Any]] = None, + ) -> Sequence[str]: """Get additional dependencies required for building an sdist. :returns: A list of :pep:`dependency specifiers <508>`. - :rtype: list[str] """ - return self._call_hook('get_requires_for_build_sdist', { - 'config_settings': config_settings - }) + return self._call_hook( + "get_requires_for_build_sdist", {"config_settings": config_settings} + ) - def build_sdist(self, sdist_directory, config_settings=None): + def build_sdist( + self, + sdist_directory: str, + config_settings: Optional[Mapping[str, Any]] = None, + ) -> str: """Build an sdist from this project. :returns: The name of the newly created sdist within ``wheel_directory``. """ - return self._call_hook('build_sdist', { - 'sdist_directory': abspath(sdist_directory), - 'config_settings': config_settings, - }) + return self._call_hook( + "build_sdist", + { + "sdist_directory": abspath(sdist_directory), + "config_settings": config_settings, + }, + ) - def _call_hook(self, hook_name, kwargs): - extra_environ = {'PEP517_BUILD_BACKEND': self.build_backend} + def _call_hook(self, hook_name: str, kwargs: Mapping[str, Any]) -> Any: + extra_environ = {"_PYPROJECT_HOOKS_BUILD_BACKEND": self.build_backend} if self.backend_path: backend_path = os.pathsep.join(self.backend_path) - extra_environ['PEP517_BACKEND_PATH'] = backend_path + extra_environ["_PYPROJECT_HOOKS_BACKEND_PATH"] = backend_path with tempfile.TemporaryDirectory() as td: - hook_input = {'kwargs': kwargs} - write_json(hook_input, pjoin(td, 'input.json'), indent=2) + hook_input = {"kwargs": kwargs} + write_json(hook_input, pjoin(td, "input.json"), indent=2) # Run the hook in a subprocess with _in_proc_script_path() as script: @@ -311,20 +392,19 @@ class BuildBackendHookCaller: self._subprocess_runner( [python, abspath(str(script)), hook_name, td], cwd=self.source_dir, - extra_environ=extra_environ + extra_environ=extra_environ, ) - data = read_json(pjoin(td, 'output.json')) - if data.get('unsupported'): - raise UnsupportedOperation(data.get('traceback', '')) - if data.get('no_backend'): - raise BackendUnavailable(data.get('traceback', '')) - if data.get('backend_invalid'): - raise BackendInvalid( + data = read_json(pjoin(td, "output.json")) + if data.get("unsupported"): + raise UnsupportedOperation(data.get("traceback", "")) + if data.get("no_backend"): + raise BackendUnavailable( + data.get("traceback", ""), + message=data.get("backend_error", ""), backend_name=self.build_backend, backend_path=self.backend_path, - message=data.get('backend_error', '') ) - if data.get('hook_missing'): - raise HookMissing(data.get('missing_hook_name') or hook_name) - return data['return_val'] + if data.get("hook_missing"): + raise HookMissing(data.get("missing_hook_name") or hook_name) + return data["return_val"] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__init__.py index 917fa06..906d0ba 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__init__.py @@ -11,8 +11,11 @@ try: except AttributeError: # Python 3.8 compatibility def _in_proc_script_path(): - return resources.path(__package__, '_in_process.py') + return resources.path(__package__, "_in_process.py") + else: + def _in_proc_script_path(): return resources.as_file( - resources.files(__package__).joinpath('_in_process.py')) + resources.files(__package__).joinpath("_in_process.py") + ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/__init__.cpython-312.pyc index 71cd4d0..1f9ff19 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/_in_process.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/_in_process.cpython-312.pyc index 514d9a8..8529149 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/_in_process.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/__pycache__/_in_process.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py index ee511ff..d689bab 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py @@ -3,8 +3,8 @@ It expects: - Command line args: hook_name, control_dir - Environment variables: - PEP517_BUILD_BACKEND=entry.point:spec - PEP517_BACKEND_PATH=paths (separated with os.pathsep) + _PYPROJECT_HOOKS_BUILD_BACKEND=entry.point:spec + _PYPROJECT_HOOKS_BACKEND_PATH=paths (separated with os.pathsep) - control_dir/input.json: - {"kwargs": {...}} @@ -21,6 +21,7 @@ import sys import traceback from glob import glob from importlib import import_module +from importlib.machinery import PathFinder from os.path import join as pjoin # This file is run as a script, and `import wrappers` is not zip-safe, so we @@ -28,69 +29,93 @@ from os.path import join as pjoin def write_json(obj, path, **kwargs): - with open(path, 'w', encoding='utf-8') as f: + with open(path, "w", encoding="utf-8") as f: json.dump(obj, f, **kwargs) def read_json(path): - with open(path, encoding='utf-8') as f: + with open(path, encoding="utf-8") as f: return json.load(f) class BackendUnavailable(Exception): """Raised if we cannot import the backend""" - def __init__(self, traceback): - self.traceback = traceback - -class BackendInvalid(Exception): - """Raised if the backend is invalid""" - def __init__(self, message): + def __init__(self, message, traceback=None): + super().__init__(message) self.message = message + self.traceback = traceback class HookMissing(Exception): """Raised if a hook is missing and we are not executing the fallback""" + def __init__(self, hook_name=None): super().__init__(hook_name) self.hook_name = hook_name -def contained_in(filename, directory): - """Test if a file is located within the given directory.""" - filename = os.path.normcase(os.path.abspath(filename)) - directory = os.path.normcase(os.path.abspath(directory)) - return os.path.commonprefix([filename, directory]) == directory - - def _build_backend(): """Find and load the build backend""" - # Add in-tree backend directories to the front of sys.path. - backend_path = os.environ.get('PEP517_BACKEND_PATH') - if backend_path: - extra_pathitems = backend_path.split(os.pathsep) - sys.path[:0] = extra_pathitems + backend_path = os.environ.get("_PYPROJECT_HOOKS_BACKEND_PATH") + ep = os.environ["_PYPROJECT_HOOKS_BUILD_BACKEND"] + mod_path, _, obj_path = ep.partition(":") + + if backend_path: + # Ensure in-tree backend directories have the highest priority when importing. + extra_pathitems = backend_path.split(os.pathsep) + sys.meta_path.insert(0, _BackendPathFinder(extra_pathitems, mod_path)) - ep = os.environ['PEP517_BUILD_BACKEND'] - mod_path, _, obj_path = ep.partition(':') try: obj = import_module(mod_path) except ImportError: - raise BackendUnavailable(traceback.format_exc()) - - if backend_path: - if not any( - contained_in(obj.__file__, path) - for path in extra_pathitems - ): - raise BackendInvalid("Backend was not loaded from backend-path") + msg = f"Cannot import {mod_path!r}" + raise BackendUnavailable(msg, traceback.format_exc()) if obj_path: - for path_part in obj_path.split('.'): + for path_part in obj_path.split("."): obj = getattr(obj, path_part) return obj +class _BackendPathFinder: + """Implements the MetaPathFinder interface to locate modules in ``backend-path``. + + Since the environment provided by the frontend can contain all sorts of + MetaPathFinders, the only way to ensure the backend is loaded from the + right place is to prepend our own. + """ + + def __init__(self, backend_path, backend_module): + self.backend_path = backend_path + self.backend_module = backend_module + self.backend_parent, _, _ = backend_module.partition(".") + + def find_spec(self, fullname, _path, _target=None): + if "." in fullname: + # Rely on importlib to find nested modules based on parent's path + return None + + # Ignore other items in _path or sys.path and use backend_path instead: + spec = PathFinder.find_spec(fullname, path=self.backend_path) + if spec is None and fullname == self.backend_parent: + # According to the spec, the backend MUST be loaded from backend-path. + # Therefore, we can halt the import machinery and raise a clean error. + msg = f"Cannot find module {self.backend_module!r} in {self.backend_path!r}" + raise BackendUnavailable(msg) + + return spec + + if sys.version_info >= (3, 8): + + def find_distributions(self, context=None): + # Delayed import: Python 3.7 does not contain importlib.metadata + from importlib.metadata import DistributionFinder, MetadataPathFinder + + context = DistributionFinder.Context(path=self.backend_path) + return MetadataPathFinder.find_distributions(context=context) + + def _supported_features(): """Return the list of options features supported by the backend. @@ -133,7 +158,8 @@ def get_requires_for_build_editable(config_settings): def prepare_metadata_for_build_wheel( - metadata_directory, config_settings, _allow_fallback): + metadata_directory, config_settings, _allow_fallback +): """Invoke optional prepare_metadata_for_build_wheel Implements a fallback by building a wheel if the hook isn't defined, @@ -150,12 +176,14 @@ def prepare_metadata_for_build_wheel( # fallback to build_wheel outside the try block to avoid exception chaining # which can be confusing to users and is not relevant whl_basename = backend.build_wheel(metadata_directory, config_settings) - return _get_wheel_metadata_from_wheel(whl_basename, metadata_directory, - config_settings) + return _get_wheel_metadata_from_wheel( + whl_basename, metadata_directory, config_settings + ) def prepare_metadata_for_build_editable( - metadata_directory, config_settings, _allow_fallback): + metadata_directory, config_settings, _allow_fallback +): """Invoke optional prepare_metadata_for_build_editable Implements a fallback by building an editable wheel if the hook isn't @@ -171,24 +199,24 @@ def prepare_metadata_for_build_editable( try: build_hook = backend.build_editable except AttributeError: - raise HookMissing(hook_name='build_editable') + raise HookMissing(hook_name="build_editable") else: whl_basename = build_hook(metadata_directory, config_settings) - return _get_wheel_metadata_from_wheel(whl_basename, - metadata_directory, - config_settings) + return _get_wheel_metadata_from_wheel( + whl_basename, metadata_directory, config_settings + ) else: return hook(metadata_directory, config_settings) -WHEEL_BUILT_MARKER = 'PEP517_ALREADY_BUILT_WHEEL' +WHEEL_BUILT_MARKER = "PYPROJECT_HOOKS_ALREADY_BUILT_WHEEL" def _dist_info_files(whl_zip): """Identify the .dist-info folder inside a wheel ZipFile.""" res = [] for path in whl_zip.namelist(): - m = re.match(r'[^/\\]+-[^/\\]+\.dist-info/', path) + m = re.match(r"[^/\\]+-[^/\\]+\.dist-info/", path) if m: res.append(path) if res: @@ -196,40 +224,41 @@ def _dist_info_files(whl_zip): raise Exception("No .dist-info folder found in wheel") -def _get_wheel_metadata_from_wheel( - whl_basename, metadata_directory, config_settings): +def _get_wheel_metadata_from_wheel(whl_basename, metadata_directory, config_settings): """Extract the metadata from a wheel. Fallback for when the build backend does not define the 'get_wheel_metadata' hook. """ from zipfile import ZipFile - with open(os.path.join(metadata_directory, WHEEL_BUILT_MARKER), 'wb'): + + with open(os.path.join(metadata_directory, WHEEL_BUILT_MARKER), "wb"): pass # Touch marker file whl_file = os.path.join(metadata_directory, whl_basename) with ZipFile(whl_file) as zipf: dist_info = _dist_info_files(zipf) zipf.extractall(path=metadata_directory, members=dist_info) - return dist_info[0].split('/')[0] + return dist_info[0].split("/")[0] def _find_already_built_wheel(metadata_directory): - """Check for a wheel already built during the get_wheel_metadata hook. - """ + """Check for a wheel already built during the get_wheel_metadata hook.""" if not metadata_directory: return None metadata_parent = os.path.dirname(metadata_directory) if not os.path.isfile(pjoin(metadata_parent, WHEEL_BUILT_MARKER)): return None - whl_files = glob(os.path.join(metadata_parent, '*.whl')) + whl_files = glob(os.path.join(metadata_parent, "*.whl")) if not whl_files: - print('Found wheel built marker, but no .whl files') + print("Found wheel built marker, but no .whl files") return None if len(whl_files) > 1: - print('Found multiple .whl files; unspecified behaviour. ' - 'Will call build_wheel.') + print( + "Found multiple .whl files; unspecified behaviour. " + "Will call build_wheel." + ) return None # Exactly one .whl file @@ -248,8 +277,9 @@ def build_wheel(wheel_directory, config_settings, metadata_directory=None): shutil.copy2(prebuilt_whl, wheel_directory) return os.path.basename(prebuilt_whl) - return _build_backend().build_wheel(wheel_directory, config_settings, - metadata_directory) + return _build_backend().build_wheel( + wheel_directory, config_settings, metadata_directory + ) def build_editable(wheel_directory, config_settings, metadata_directory=None): @@ -293,6 +323,7 @@ class _DummyException(Exception): class GotUnsupportedOperation(Exception): """For internal use when backend raises UnsupportedOperation""" + def __init__(self, traceback): self.traceback = traceback @@ -302,20 +333,20 @@ def build_sdist(sdist_directory, config_settings): backend = _build_backend() try: return backend.build_sdist(sdist_directory, config_settings) - except getattr(backend, 'UnsupportedOperation', _DummyException): + except getattr(backend, "UnsupportedOperation", _DummyException): raise GotUnsupportedOperation(traceback.format_exc()) HOOK_NAMES = { - 'get_requires_for_build_wheel', - 'prepare_metadata_for_build_wheel', - 'build_wheel', - 'get_requires_for_build_editable', - 'prepare_metadata_for_build_editable', - 'build_editable', - 'get_requires_for_build_sdist', - 'build_sdist', - '_supported_features', + "get_requires_for_build_wheel", + "prepare_metadata_for_build_wheel", + "build_wheel", + "get_requires_for_build_editable", + "prepare_metadata_for_build_editable", + "build_editable", + "get_requires_for_build_sdist", + "build_sdist", + "_supported_features", } @@ -326,28 +357,33 @@ def main(): control_dir = sys.argv[2] if hook_name not in HOOK_NAMES: sys.exit("Unknown hook: %s" % hook_name) + + # Remove the parent directory from sys.path to avoid polluting the backend + # import namespace with this directory. + here = os.path.dirname(__file__) + if here in sys.path: + sys.path.remove(here) + hook = globals()[hook_name] - hook_input = read_json(pjoin(control_dir, 'input.json')) + hook_input = read_json(pjoin(control_dir, "input.json")) - json_out = {'unsupported': False, 'return_val': None} + json_out = {"unsupported": False, "return_val": None} try: - json_out['return_val'] = hook(**hook_input['kwargs']) + json_out["return_val"] = hook(**hook_input["kwargs"]) except BackendUnavailable as e: - json_out['no_backend'] = True - json_out['traceback'] = e.traceback - except BackendInvalid as e: - json_out['backend_invalid'] = True - json_out['backend_error'] = e.message + json_out["no_backend"] = True + json_out["traceback"] = e.traceback + json_out["backend_error"] = e.message except GotUnsupportedOperation as e: - json_out['unsupported'] = True - json_out['traceback'] = e.traceback + json_out["unsupported"] = True + json_out["traceback"] = e.traceback except HookMissing as e: - json_out['hook_missing'] = True - json_out['missing_hook_name'] = e.hook_name or hook_name + json_out["hook_missing"] = True + json_out["missing_hook_name"] = e.hook_name or hook_name - write_json(json_out, pjoin(control_dir, 'output.json'), indent=2) + write_json(json_out, pjoin(control_dir, "output.json"), indent=2) -if __name__ == '__main__': +if __name__ == "__main__": main() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__init__.py index 10ff67f..04230fc 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__init__.py @@ -45,11 +45,7 @@ from pip._vendor import urllib3 from .exceptions import RequestsDependencyWarning charset_normalizer_version = None - -try: - from pip._vendor.chardet import __version__ as chardet_version -except ImportError: - chardet_version = None +chardet_version = None def check_compatibility(urllib3_version, chardet_version, charset_normalizer_version): @@ -80,7 +76,8 @@ def check_compatibility(urllib3_version, chardet_version, charset_normalizer_ver # charset_normalizer >= 2.0.0 < 4.0.0 assert (2, 0, 0) <= (major, minor, patch) < (4, 0, 0) else: - raise Exception("You need either charset_normalizer or chardet installed") + # pip does not need or use character detection + pass def _check_cryptography(cryptography_version): diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__init__.cpython-312.pyc index 442707b..81f7b09 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__version__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__version__.cpython-312.pyc index 06b7f16..36d3032 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__version__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/__version__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/_internal_utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/_internal_utils.cpython-312.pyc index b211861..c3cb6fd 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/_internal_utils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/_internal_utils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/adapters.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/adapters.cpython-312.pyc index cf56f27..d2ee0df 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/adapters.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/adapters.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/api.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/api.cpython-312.pyc index 1b9ecee..5a174fb 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/api.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/api.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/auth.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/auth.cpython-312.pyc index b70dbdf..124bd27 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/auth.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/auth.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/certs.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/certs.cpython-312.pyc index 104e11f..b551297 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/certs.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/certs.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/compat.cpython-312.pyc index 71dfd5c..6269c6b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/compat.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/compat.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/cookies.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/cookies.cpython-312.pyc index 685d5f8..f8a01c1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/cookies.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/cookies.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/exceptions.cpython-312.pyc index fb4080f..8e1fc0b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/exceptions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/exceptions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/help.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/help.cpython-312.pyc index 919c40b..7eda60b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/help.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/help.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/hooks.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/hooks.cpython-312.pyc index a5e9fd5..f62c8b6 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/hooks.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/hooks.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/models.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/models.cpython-312.pyc index 6150322..846399e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/models.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/models.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/packages.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/packages.cpython-312.pyc index 02ee0bf..ad43e49 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/packages.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/packages.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/sessions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/sessions.cpython-312.pyc index 4eeb98f..c984e02 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/sessions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/sessions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/status_codes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/status_codes.cpython-312.pyc index 1b20cad..8e1fdde 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/status_codes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/status_codes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/structures.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/structures.cpython-312.pyc index 61835f0..8af607f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/structures.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/structures.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/utils.cpython-312.pyc index e066155..2f286e0 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/utils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__pycache__/utils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__version__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__version__.py index 5063c3f..2c105ac 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__version__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/__version__.py @@ -5,10 +5,10 @@ __title__ = "requests" __description__ = "Python HTTP for Humans." __url__ = "https://requests.readthedocs.io" -__version__ = "2.31.0" -__build__ = 0x023100 +__version__ = "2.32.3" +__build__ = 0x023203 __author__ = "Kenneth Reitz" __author_email__ = "me@kennethreitz.org" -__license__ = "Apache 2.0" +__license__ = "Apache-2.0" __copyright__ = "Copyright Kenneth Reitz" __cake__ = "\u2728 \U0001f370 \u2728" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/adapters.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/adapters.py index 10c1767..7030777 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/adapters.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/adapters.py @@ -8,6 +8,8 @@ and maintain connections. import os.path import socket # noqa: F401 +import typing +import warnings from pip._vendor.urllib3.exceptions import ClosedPoolError, ConnectTimeoutError from pip._vendor.urllib3.exceptions import HTTPError as _HTTPError @@ -25,6 +27,7 @@ from pip._vendor.urllib3.poolmanager import PoolManager, proxy_from_url from pip._vendor.urllib3.util import Timeout as TimeoutSauce from pip._vendor.urllib3.util import parse_url from pip._vendor.urllib3.util.retry import Retry +from pip._vendor.urllib3.util.ssl_ import create_urllib3_context from .auth import _basic_auth_str from .compat import basestring, urlparse @@ -61,12 +64,76 @@ except ImportError: raise InvalidSchema("Missing dependencies for SOCKS support.") +if typing.TYPE_CHECKING: + from .models import PreparedRequest + + DEFAULT_POOLBLOCK = False DEFAULT_POOLSIZE = 10 DEFAULT_RETRIES = 0 DEFAULT_POOL_TIMEOUT = None +try: + import ssl # noqa: F401 + + _preloaded_ssl_context = create_urllib3_context() + _preloaded_ssl_context.load_verify_locations( + extract_zipped_paths(DEFAULT_CA_BUNDLE_PATH) + ) +except ImportError: + # Bypass default SSLContext creation when Python + # interpreter isn't built with the ssl module. + _preloaded_ssl_context = None + + +def _urllib3_request_context( + request: "PreparedRequest", + verify: "bool | str | None", + client_cert: "typing.Tuple[str, str] | str | None", + poolmanager: "PoolManager", +) -> "(typing.Dict[str, typing.Any], typing.Dict[str, typing.Any])": + host_params = {} + pool_kwargs = {} + parsed_request_url = urlparse(request.url) + scheme = parsed_request_url.scheme.lower() + port = parsed_request_url.port + + # Determine if we have and should use our default SSLContext + # to optimize performance on standard requests. + poolmanager_kwargs = getattr(poolmanager, "connection_pool_kw", {}) + has_poolmanager_ssl_context = poolmanager_kwargs.get("ssl_context") + should_use_default_ssl_context = ( + _preloaded_ssl_context is not None and not has_poolmanager_ssl_context + ) + + cert_reqs = "CERT_REQUIRED" + if verify is False: + cert_reqs = "CERT_NONE" + elif verify is True and should_use_default_ssl_context: + pool_kwargs["ssl_context"] = _preloaded_ssl_context + elif isinstance(verify, str): + if not os.path.isdir(verify): + pool_kwargs["ca_certs"] = verify + else: + pool_kwargs["ca_cert_dir"] = verify + pool_kwargs["cert_reqs"] = cert_reqs + if client_cert is not None: + if isinstance(client_cert, tuple) and len(client_cert) == 2: + pool_kwargs["cert_file"] = client_cert[0] + pool_kwargs["key_file"] = client_cert[1] + else: + # According to our docs, we allow users to specify just the client + # cert path + pool_kwargs["cert_file"] = client_cert + host_params = { + "scheme": scheme, + "host": parsed_request_url.hostname, + "port": port, + } + return host_params, pool_kwargs + + class BaseAdapter: """The Base Transport Adapter""" @@ -247,28 +314,26 @@ class HTTPAdapter(BaseAdapter): :param cert: The SSL certificate to verify. """ if url.lower().startswith("https") and verify: - - cert_loc = None - - # Allow self-specified cert location. - if verify is not True: - cert_loc = verify - - if not cert_loc: - cert_loc = extract_zipped_paths(DEFAULT_CA_BUNDLE_PATH) - - if not cert_loc or not os.path.exists(cert_loc): - raise OSError( - f"Could not find a suitable TLS CA certificate bundle, " - f"invalid path: {cert_loc}" - ) - conn.cert_reqs = "CERT_REQUIRED" - if not os.path.isdir(cert_loc): - conn.ca_certs = cert_loc - else: - conn.ca_cert_dir = cert_loc + # Only load the CA certificates if 'verify' is a string indicating the CA bundle to use. + # Otherwise, if verify is a boolean, we don't load anything since + # the connection will be using a context with the default certificates already loaded, + # and this avoids a call to the slow load_verify_locations() + if verify is not True: + # `verify` must be a str with a path then + cert_loc = verify + + if not os.path.exists(cert_loc): + raise OSError( + f"Could not find a suitable TLS CA certificate bundle, " + f"invalid path: {cert_loc}" + ) + + if not os.path.isdir(cert_loc): + conn.ca_certs = cert_loc + else: + conn.ca_cert_dir = cert_loc else: conn.cert_reqs = "CERT_NONE" conn.ca_certs = None @@ -328,8 +393,110 @@ class HTTPAdapter(BaseAdapter): return response + def build_connection_pool_key_attributes(self, request, verify, cert=None): + """Build the PoolKey attributes used by urllib3 to return a connection. + + This looks at the PreparedRequest, the user-specified verify value, + and the value of the cert parameter to determine what PoolKey values + to use to select a connection from a given urllib3 Connection Pool. + + The SSL related pool key arguments are not consistently set. As of + this writing, use the following to determine what keys may be in that + dictionary: + + * If ``verify`` is ``True``, ``"ssl_context"`` will be set and will be the + default Requests SSL Context + * If ``verify`` is ``False``, ``"ssl_context"`` will not be set but + ``"cert_reqs"`` will be set + * If ``verify`` is a string, (i.e., it is a user-specified trust bundle) + ``"ca_certs"`` will be set if the string is not a directory recognized + by :py:func:`os.path.isdir`, otherwise ``"ca_certs_dir"`` will be + set. + * If ``"cert"`` is specified, ``"cert_file"`` will always be set. If + ``"cert"`` is a tuple with a second item, ``"key_file"`` will also + be present + + To override these settings, one may subclass this class, call this + method and use the above logic to change parameters as desired. For + example, if one wishes to use a custom :py:class:`ssl.SSLContext` one + must both set ``"ssl_context"`` and based on what else they require, + alter the other keys to ensure the desired behaviour. + + :param request: + The PreparedReqest being sent over the connection. + :type request: + :class:`~requests.models.PreparedRequest` + :param verify: + Either a boolean, in which case it controls whether + we verify the server's TLS certificate, or a string, in which case it + must be a path to a CA bundle to use. + :param cert: + (optional) Any user-provided SSL certificate for client + authentication (a.k.a., mTLS). This may be a string (i.e., just + the path to a file which holds both certificate and key) or a + tuple of length 2 with the certificate file path and key file + path. + :returns: + A tuple of two dictionaries. The first is the "host parameters" + portion of the Pool Key including scheme, hostname, and port. The + second is a dictionary of SSLContext related parameters. + """ + return _urllib3_request_context(request, verify, cert, self.poolmanager) + + def get_connection_with_tls_context(self, request, verify, proxies=None, cert=None): + """Returns a urllib3 connection for the given request and TLS settings. + This should not be called from user code, and is only exposed for use + when subclassing the :class:`HTTPAdapter `. + + :param request: + The :class:`PreparedRequest ` object to be sent + over the connection. + :param verify: + Either a boolean, in which case it controls whether we verify the + server's TLS certificate, or a string, in which case it must be a + path to a CA bundle to use. + :param proxies: + (optional) The proxies dictionary to apply to the request. + :param cert: + (optional) Any user-provided SSL certificate to be used for client + authentication (a.k.a., mTLS). + :rtype: + urllib3.ConnectionPool + """ + proxy = select_proxy(request.url, proxies) + try: + host_params, pool_kwargs = self.build_connection_pool_key_attributes( + request, + verify, + cert, + ) + except ValueError as e: + raise InvalidURL(e, request=request) + if proxy: + proxy = prepend_scheme_if_needed(proxy, "http") + proxy_url = parse_url(proxy) + if not proxy_url.host: + raise InvalidProxyURL( + "Please check proxy URL. It is malformed " + "and could be missing the host." + ) + proxy_manager = self.proxy_manager_for(proxy) + conn = proxy_manager.connection_from_host( + **host_params, pool_kwargs=pool_kwargs + ) + else: + # Only scheme should be lower case + conn = self.poolmanager.connection_from_host( + **host_params, pool_kwargs=pool_kwargs + ) + + return conn + def get_connection(self, url, proxies=None): - """Returns a urllib3 connection for the given URL. This should not be + """DEPRECATED: Users should move to `get_connection_with_tls_context` + for all subclasses of HTTPAdapter using Requests>=2.32.2. + + Returns a urllib3 connection for the given URL. This should not be called from user code, and is only exposed for use when subclassing the :class:`HTTPAdapter `. @@ -337,6 +504,15 @@ class HTTPAdapter(BaseAdapter): :param proxies: (optional) A Requests-style dictionary of proxies used on this request. :rtype: urllib3.ConnectionPool """ + warnings.warn( + ( + "`get_connection` has been deprecated in favor of " + "`get_connection_with_tls_context`. Custom HTTPAdapter subclasses " + "will need to migrate for Requests>=2.32.2. Please see " + "https://github.com/psf/requests/pull/6710 for more details." + ), + DeprecationWarning, + ) proxy = select_proxy(url, proxies) if proxy: @@ -391,6 +567,9 @@ class HTTPAdapter(BaseAdapter): using_socks_proxy = proxy_scheme.startswith("socks") url = request.path_url + if url.startswith("//"): # Don't confuse urllib3 + url = f"/{url.lstrip('/')}" + if is_proxied_http_request and not using_socks_proxy: url = urldefragauth(request.url) @@ -451,7 +630,9 @@ class HTTPAdapter(BaseAdapter): """ try: - conn = self.get_connection(request.url, proxies) + conn = self.get_connection_with_tls_context( + request, verify, proxies=proxies, cert=cert + ) except LocationValueError as e: raise InvalidURL(e, request=request) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/api.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/api.py index cd0b3ee..5960744 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/api.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/api.py @@ -25,7 +25,7 @@ def request(method, url, **kwargs): :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload. ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')`` - or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string + or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content_type'`` is a string defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers to add for the file. :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/auth.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/auth.py index 9733686..4a7ce6d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/auth.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/auth.py @@ -258,7 +258,6 @@ class HTTPDigestAuth(AuthBase): s_auth = r.headers.get("www-authenticate", "") if "digest" in s_auth.lower() and self._thread_local.num_401_calls < 2: - self._thread_local.num_401_calls += 1 pat = re.compile(r"digest ", flags=re.IGNORECASE) self._thread_local.chal = parse_dict_header(pat.sub("", s_auth, count=1)) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/certs.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/certs.py index 38696a1..2743144 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/certs.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/certs.py @@ -11,14 +11,7 @@ If you are packaging Requests, e.g., for a Linux distribution or a managed environment, you can change the definition of where() to return a separately packaged CA bundle. """ - -import os - -if "_PIP_STANDALONE_CERT" not in os.environ: - from pip._vendor.certifi import where -else: - def where(): - return os.environ["_PIP_STANDALONE_CERT"] +from pip._vendor.certifi import where if __name__ == "__main__": print(where()) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/compat.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/compat.py index 9ab2bb4..7081da7 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/compat.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/compat.py @@ -7,10 +7,21 @@ between Python 2 and Python 3. It remains for backwards compatibility until the next major version. """ -from pip._vendor import chardet - import sys +# ------------------- +# Character Detection +# ------------------- + + +def _resolve_char_detection(): + """Find supported character detection libraries.""" + chardet = None + return chardet + + +chardet = _resolve_char_detection() + # ------- # Pythons # ------- diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/cookies.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/cookies.py index bf54ab2..f69d0cd 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/cookies.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/cookies.py @@ -2,7 +2,7 @@ requests.cookies ~~~~~~~~~~~~~~~~ -Compatibility code to be able to use `cookielib.CookieJar` with requests. +Compatibility code to be able to use `http.cookiejar.CookieJar` with requests. requests.utils imports from here, so be careful with imports. """ @@ -23,7 +23,7 @@ except ImportError: class MockRequest: """Wraps a `requests.Request` to mimic a `urllib2.Request`. - The code in `cookielib.CookieJar` expects this interface in order to correctly + The code in `http.cookiejar.CookieJar` expects this interface in order to correctly manage cookie policies, i.e., determine whether a cookie can be set, given the domains of the request and the cookie. @@ -76,7 +76,7 @@ class MockRequest: return self._r.headers.get(name, self._new_headers.get(name, default)) def add_header(self, key, val): - """cookielib has no legitimate use for this method; add it back if you find one.""" + """cookiejar has no legitimate use for this method; add it back if you find one.""" raise NotImplementedError( "Cookie headers should be added with add_unredirected_header()" ) @@ -104,11 +104,11 @@ class MockResponse: """Wraps a `httplib.HTTPMessage` to mimic a `urllib.addinfourl`. ...what? Basically, expose the parsed HTTP headers from the server response - the way `cookielib` expects to see them. + the way `http.cookiejar` expects to see them. """ def __init__(self, headers): - """Make a MockResponse for `cookielib` to read. + """Make a MockResponse for `cookiejar` to read. :param headers: a httplib.HTTPMessage or analogous carrying the headers """ @@ -124,7 +124,7 @@ class MockResponse: def extract_cookies_to_jar(jar, request, response): """Extract the cookies from the response into a CookieJar. - :param jar: cookielib.CookieJar (not necessarily a RequestsCookieJar) + :param jar: http.cookiejar.CookieJar (not necessarily a RequestsCookieJar) :param request: our own requests.Request object :param response: urllib3.HTTPResponse object """ @@ -174,7 +174,7 @@ class CookieConflictError(RuntimeError): class RequestsCookieJar(cookielib.CookieJar, MutableMapping): - """Compatibility class; is a cookielib.CookieJar, but exposes a dict + """Compatibility class; is a http.cookiejar.CookieJar, but exposes a dict interface. This is the CookieJar we create by default for requests and sessions that @@ -341,7 +341,7 @@ class RequestsCookieJar(cookielib.CookieJar, MutableMapping): self.set(name, value) def __delitem__(self, name): - """Deletes a cookie given a name. Wraps ``cookielib.CookieJar``'s + """Deletes a cookie given a name. Wraps ``http.cookiejar.CookieJar``'s ``remove_cookie_by_name()``. """ remove_cookie_by_name(self, name) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/exceptions.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/exceptions.py index 168d073..7f3660f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/exceptions.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/exceptions.py @@ -41,6 +41,16 @@ class JSONDecodeError(InvalidJSONError, CompatJSONDecodeError): CompatJSONDecodeError.__init__(self, *args) InvalidJSONError.__init__(self, *self.args, **kwargs) + def __reduce__(self): + """ + The __reduce__ method called when pickling the object must + be the one from the JSONDecodeError (be it json/simplejson) + as it expects all the arguments for instantiation, not just + one like the IOError, and the MRO would by default call the + __reduce__ method from the IOError due to the inheritance order. + """ + return CompatJSONDecodeError.__reduce__(self) + class HTTPError(RequestException): """An HTTP error occurred.""" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/help.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/help.py index 2d292c2..ddbb615 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/help.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/help.py @@ -11,11 +11,7 @@ from pip._vendor import urllib3 from . import __version__ as requests_version charset_normalizer = None - -try: - from pip._vendor import chardet -except ImportError: - chardet = None +chardet = None try: from pip._vendor.urllib3.contrib import pyopenssl diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/models.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/models.py index 76e6f19..85a008c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/models.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/models.py @@ -170,7 +170,7 @@ class RequestEncodingMixin: ) ) - for (k, v) in files: + for k, v in files: # support for explicit filename ft = None fh = None @@ -268,7 +268,6 @@ class Request(RequestHooksMixin): hooks=None, json=None, ): - # Default empty dicts for dict params. data = [] if data is None else data files = [] if files is None else files @@ -277,7 +276,7 @@ class Request(RequestHooksMixin): hooks = {} if hooks is None else hooks self.hooks = default_hooks() - for (k, v) in list(hooks.items()): + for k, v in list(hooks.items()): self.register_hook(event=k, hook=v) self.method = method @@ -790,7 +789,12 @@ class Response: @property def apparent_encoding(self): """The apparent encoding, provided by the charset_normalizer or chardet libraries.""" - return chardet.detect(self.content)["encoding"] + if chardet is not None: + return chardet.detect(self.content)["encoding"] + else: + # If no character detection library is available, we'll fall back + # to a standard Python utf-8 str. + return "utf-8" def iter_content(self, chunk_size=1, decode_unicode=False): """Iterates over the response data. When stream=True is set on the @@ -865,7 +869,6 @@ class Response: for chunk in self.iter_content( chunk_size=chunk_size, decode_unicode=decode_unicode ): - if pending is not None: chunk = pending + chunk diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/packages.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/packages.py index 9582fa7..200c382 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/packages.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/packages.py @@ -1,9 +1,11 @@ import sys +from .compat import chardet + # This code exists for backwards compatibility reasons. # I don't like it either. Just look the other way. :) -for package in ('urllib3', 'idna', 'chardet'): +for package in ("urllib3", "idna"): vendored_package = "pip._vendor." + package locals()[package] = __import__(vendored_package) # This traversal is apparently necessary such that the identities are @@ -13,4 +15,11 @@ for package in ('urllib3', 'idna', 'chardet'): unprefixed_mod = mod[len("pip._vendor."):] sys.modules['pip._vendor.requests.packages.' + unprefixed_mod] = sys.modules[mod] -# Kinda cool, though, right? +if chardet is not None: + target = chardet.__name__ + for mod in list(sys.modules): + if mod == target or mod.startswith(f"{target}."): + imported_mod = sys.modules[mod] + sys.modules[f"requests.packages.{mod}"] = imported_mod + mod = mod.replace(target, "chardet") + sys.modules[f"requests.packages.{mod}"] = imported_mod diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/sessions.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/sessions.py index dbcf2a7..b387bc3 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/sessions.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/sessions.py @@ -262,7 +262,6 @@ class SessionRedirectMixin: if yield_requests: yield req else: - resp = self.send( req, stream=stream, @@ -326,7 +325,7 @@ class SessionRedirectMixin: # urllib3 handles proxy authorization for us in the standard adapter. # Avoid appending this to TLS tunneled requests where it may be leaked. - if not scheme.startswith('https') and username and password: + if not scheme.startswith("https") and username and password: headers["Proxy-Authorization"] = _basic_auth_str(username, password) return new_proxies @@ -389,7 +388,6 @@ class Session(SessionRedirectMixin): ] def __init__(self): - #: A case-insensitive dictionary of headers to be sent on each #: :class:`Request ` sent from this #: :class:`Session `. @@ -545,6 +543,8 @@ class Session(SessionRedirectMixin): :type allow_redirects: bool :param proxies: (optional) Dictionary mapping protocol or protocol and hostname to the URL of the proxy. + :param hooks: (optional) Dictionary mapping hook name to one event or + list of events, event must be callable. :param stream: (optional) whether to immediately download the response content. Defaults to ``False``. :param verify: (optional) Either a boolean, in which case it controls whether we verify @@ -711,7 +711,6 @@ class Session(SessionRedirectMixin): # Persist cookies if r.history: - # If the hooks create history then we want those cookies too for resp in r.history: extract_cookies_to_jar(self.cookies, resp.request, resp.raw) @@ -759,7 +758,7 @@ class Session(SessionRedirectMixin): # Set environment's proxies. no_proxy = proxies.get("no_proxy") if proxies is not None else None env_proxies = get_environ_proxies(url, no_proxy=no_proxy) - for (k, v) in env_proxies.items(): + for k, v in env_proxies.items(): proxies.setdefault(k, v) # Look for requests environment configuration @@ -785,8 +784,7 @@ class Session(SessionRedirectMixin): :rtype: requests.adapters.BaseAdapter """ - for (prefix, adapter) in self.adapters.items(): - + for prefix, adapter in self.adapters.items(): if url.lower().startswith(prefix.lower()): return adapter diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/status_codes.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/status_codes.py index 4bd072b..c7945a2 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/status_codes.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/status_codes.py @@ -24,7 +24,7 @@ _codes = { # Informational. 100: ("continue",), 101: ("switching_protocols",), - 102: ("processing",), + 102: ("processing", "early-hints"), 103: ("checkpoint",), 122: ("uri_too_long", "request_uri_too_long"), 200: ("ok", "okay", "all_ok", "all_okay", "all_good", "\\o/", "✓"), @@ -65,8 +65,8 @@ _codes = { 410: ("gone",), 411: ("length_required",), 412: ("precondition_failed", "precondition"), - 413: ("request_entity_too_large",), - 414: ("request_uri_too_large",), + 413: ("request_entity_too_large", "content_too_large"), + 414: ("request_uri_too_large", "uri_too_long"), 415: ("unsupported_media_type", "unsupported_media", "media_type"), 416: ( "requested_range_not_satisfiable", @@ -76,10 +76,10 @@ _codes = { 417: ("expectation_failed",), 418: ("im_a_teapot", "teapot", "i_am_a_teapot"), 421: ("misdirected_request",), - 422: ("unprocessable_entity", "unprocessable"), + 422: ("unprocessable_entity", "unprocessable", "unprocessable_content"), 423: ("locked",), 424: ("failed_dependency", "dependency"), - 425: ("unordered_collection", "unordered"), + 425: ("unordered_collection", "unordered", "too_early"), 426: ("upgrade_required", "upgrade"), 428: ("precondition_required", "precondition"), 429: ("too_many_requests", "too_many"), diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/utils.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/utils.py index 36607ed..a35ce47 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/utils.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/requests/utils.py @@ -97,6 +97,8 @@ if sys.platform == "win32": # '' string by the localhost entry and the corresponding # canonical entry. proxyOverride = proxyOverride.split(";") + # filter out empty strings to avoid re.match return true in the following code. + proxyOverride = filter(None, proxyOverride) # now check if we match one of the registry values. for test in proxyOverride: if test == "": @@ -134,6 +136,9 @@ def super_len(o): total_length = None current_position = 0 + if isinstance(o, str): + o = o.encode("utf-8") + if hasattr(o, "__len__"): total_length = len(o) @@ -466,11 +471,7 @@ def dict_from_cookiejar(cj): :rtype: dict """ - cookie_dict = {} - - for cookie in cj: - cookie_dict[cookie.name] = cookie.value - + cookie_dict = {cookie.name: cookie.value for cookie in cj} return cookie_dict @@ -767,6 +768,7 @@ def should_bypass_proxies(url, no_proxy): :rtype: bool """ + # Prioritize lowercase environment variables over uppercase # to keep a consistent behaviour with other http projects (curl, wget). def get_proxy(key): @@ -862,7 +864,7 @@ def select_proxy(url, proxies): def resolve_proxies(request, proxies, trust_env=True): """This method takes proxy information from a request and configuration input to resolve a mapping of target proxies. This will consider settings - such a NO_PROXY to strip proxy configurations. + such as NO_PROXY to strip proxy configurations. :param request: Request or PreparedRequest :param proxies: A dictionary of schemes or schemes and hosts to proxy URLs @@ -1054,7 +1056,7 @@ def _validate_header_part(header, header_part, header_validator_index): if not validator.match(header_part): header_kind = "name" if header_validator_index == 0 else "value" raise InvalidHeader( - f"Invalid leading whitespace, reserved character(s), or return" + f"Invalid leading whitespace, reserved character(s), or return " f"character(s) in header {header_kind}: {header_part!r}" ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/__init__.cpython-312.pyc index a260b20..8f4d95e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/providers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/providers.cpython-312.pyc index 075de45..3144db3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/providers.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/providers.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/reporters.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/reporters.cpython-312.pyc index 4423e6a..2815bd4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/reporters.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/reporters.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/resolvers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/resolvers.cpython-312.pyc index b11541f..4fce406 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/resolvers.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/resolvers.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/structs.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/structs.cpython-312.pyc index 93b1a18..f0bc9ff 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/structs.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/__pycache__/structs.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/__init__.cpython-312.pyc index d8d1604..da1ea9c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/collections_abc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/collections_abc.cpython-312.pyc index 1690c61..751e5f3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/collections_abc.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/compat/__pycache__/collections_abc.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/resolvelib/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__main__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__main__.py index 270629f..efb7fb7 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__main__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__main__.py @@ -207,7 +207,6 @@ Supports much of the *markdown* __syntax__! if __name__ == "__main__": # pragma: no cover - console = Console( file=io.StringIO(), force_terminal=True, diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__init__.cpython-312.pyc index 8faa310..3d3c95a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__main__.cpython-312.pyc index d9b23c2..f43a420 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__main__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_cell_widths.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_cell_widths.cpython-312.pyc index a2aaec6..a15ae4c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_cell_widths.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_cell_widths.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_codes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_codes.cpython-312.pyc index 330dcb0..c509814 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_codes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_codes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_replace.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_replace.cpython-312.pyc index 34d8688..73c5ba2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_replace.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_emoji_replace.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_export_format.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_export_format.cpython-312.pyc index be2f327..ba27679 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_export_format.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_export_format.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_extension.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_extension.cpython-312.pyc index 2579dd1..9e2bf0b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_extension.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_extension.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_fileno.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_fileno.cpython-312.pyc index 7b09b4f..0e4cd61 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_fileno.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_fileno.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_inspect.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_inspect.cpython-312.pyc index 2f5bb89..f6e2bc4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_inspect.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_inspect.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_log_render.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_log_render.cpython-312.pyc index 3bb7cde..71e8392 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_log_render.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_log_render.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_loop.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_loop.cpython-312.pyc index 5391c77..7d16f84 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_loop.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_loop.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_null_file.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_null_file.cpython-312.pyc index 0f01b5d..b7709b0 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_null_file.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_null_file.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_palettes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_palettes.cpython-312.pyc index cf13e18..04aa4a5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_palettes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_palettes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_pick.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_pick.cpython-312.pyc index 77423a0..8564c1b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_pick.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_pick.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_ratio.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_ratio.cpython-312.pyc index f2ee730..c64241d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_ratio.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_ratio.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_spinners.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_spinners.cpython-312.pyc index 131254e..5a26554 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_spinners.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_spinners.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_stack.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_stack.cpython-312.pyc index 1a4d99d..4a4fc8c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_stack.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_stack.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_timer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_timer.cpython-312.pyc index e3f29e2..b522e81 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_timer.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_timer.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_win32_console.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_win32_console.cpython-312.pyc index 6525187..9a534b1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_win32_console.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_win32_console.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows.cpython-312.pyc index 305210a..b4ad4f7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows_renderer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows_renderer.cpython-312.pyc index 5d63845..29dd221 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows_renderer.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_windows_renderer.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_wrap.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_wrap.cpython-312.pyc index 56422e4..6642658 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_wrap.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/_wrap.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/abc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/abc.cpython-312.pyc index 9ec0a36..e4fd55a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/abc.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/abc.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/align.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/align.cpython-312.pyc index 887937a..797eba7 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/align.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/align.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/ansi.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/ansi.cpython-312.pyc index 7076d54..c119525 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/ansi.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/ansi.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/bar.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/bar.cpython-312.pyc index 067e8be..c311b1e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/bar.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/bar.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/box.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/box.cpython-312.pyc index dbbcd16..4df28f9 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/box.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/box.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/cells.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/cells.cpython-312.pyc index bc9783f..740b9ac 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/cells.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/cells.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color.cpython-312.pyc index 71bf3f3..12b24bc 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color_triplet.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color_triplet.cpython-312.pyc index 0bb1426..b7afa2a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color_triplet.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/color_triplet.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/columns.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/columns.cpython-312.pyc index f989c7a..4852061 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/columns.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/columns.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/console.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/console.cpython-312.pyc index 92bdbcc..08e7d1e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/console.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/console.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/constrain.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/constrain.cpython-312.pyc index 1e6d0cb..0e7bd8c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/constrain.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/constrain.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/containers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/containers.cpython-312.pyc index 333a292..a3b3569 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/containers.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/containers.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/control.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/control.cpython-312.pyc index 5ec3a9d..a01f1c5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/control.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/control.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/default_styles.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/default_styles.cpython-312.pyc index af6e5e0..e9b4670 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/default_styles.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/default_styles.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/diagnose.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/diagnose.cpython-312.pyc index 43419f2..d85bf77 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/diagnose.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/diagnose.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/emoji.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/emoji.cpython-312.pyc index 4fa1573..e11d3cb 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/emoji.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/emoji.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/errors.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/errors.cpython-312.pyc index df6f859..176a26c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/errors.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/errors.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/file_proxy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/file_proxy.cpython-312.pyc index 667aa95..86733fe 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/file_proxy.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/file_proxy.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/filesize.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/filesize.cpython-312.pyc index a9339bf..363f928 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/filesize.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/filesize.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/highlighter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/highlighter.cpython-312.pyc index a3631fd..0230d34 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/highlighter.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/highlighter.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/json.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/json.cpython-312.pyc index b3b7160..00f3f0f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/json.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/json.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/jupyter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/jupyter.cpython-312.pyc index 45b9067..7875103 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/jupyter.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/jupyter.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/layout.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/layout.cpython-312.pyc index f107288..591ed53 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/layout.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/layout.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live.cpython-312.pyc index f90cc9e..9805bd0 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live_render.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live_render.cpython-312.pyc index 5813b1b..9f655c5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live_render.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/live_render.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/logging.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/logging.cpython-312.pyc index 04a6720..9458ad5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/logging.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/logging.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/markup.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/markup.cpython-312.pyc index 3487a81..7b0d14c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/markup.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/markup.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/measure.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/measure.cpython-312.pyc index 3943387..8c3738e 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/measure.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/measure.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/padding.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/padding.cpython-312.pyc index 91528ec..457d837 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/padding.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/padding.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pager.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pager.cpython-312.pyc index 5ebf257..28dd191 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pager.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pager.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/palette.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/palette.cpython-312.pyc index 22a3b62..c226c7f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/palette.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/palette.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/panel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/panel.cpython-312.pyc index 5241b4f..36d8f74 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/panel.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/panel.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pretty.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pretty.cpython-312.pyc index d4d3393..ceda78f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pretty.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/pretty.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress.cpython-312.pyc index 4e0e176..3e33c87 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress_bar.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress_bar.cpython-312.pyc index af6064c..767d45a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress_bar.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/progress_bar.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/prompt.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/prompt.cpython-312.pyc index fee94ea..d2fcc5c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/prompt.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/prompt.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/protocol.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/protocol.cpython-312.pyc index 1483147..7eead83 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/protocol.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/protocol.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/region.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/region.cpython-312.pyc index deed9a9..9991ef4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/region.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/region.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/repr.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/repr.cpython-312.pyc index f77095d..297e84c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/repr.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/repr.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/rule.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/rule.cpython-312.pyc index d4a96e1..18413d0 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/rule.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/rule.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/scope.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/scope.cpython-312.pyc index 60c30cb..c5342a3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/scope.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/scope.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/screen.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/screen.cpython-312.pyc index c05a915..e6ebe89 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/screen.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/screen.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/segment.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/segment.cpython-312.pyc index adbccdc..399ea49 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/segment.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/segment.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/spinner.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/spinner.cpython-312.pyc index 05094fc..d277b85 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/spinner.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/spinner.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/status.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/status.cpython-312.pyc index 670b427..a67fdff 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/status.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/status.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/style.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/style.cpython-312.pyc index 1a94000..ff89467 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/style.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/style.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/styled.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/styled.cpython-312.pyc index fa73367..4ee31d4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/styled.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/styled.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/syntax.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/syntax.cpython-312.pyc index 501eace..cd155f4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/syntax.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/syntax.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/table.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/table.cpython-312.pyc index dd4b126..ae3f8f9 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/table.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/table.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/terminal_theme.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/terminal_theme.cpython-312.pyc index 326bbe8..41f1895 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/terminal_theme.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/terminal_theme.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/text.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/text.cpython-312.pyc index 1cbd463..490b35c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/text.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/text.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/theme.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/theme.cpython-312.pyc index e6067d6..52bea98 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/theme.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/theme.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/themes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/themes.cpython-312.pyc index 3eb570e..78b92a4 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/themes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/themes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/traceback.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/traceback.cpython-312.pyc index f55cec0..38b463c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/traceback.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/traceback.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/tree.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/tree.cpython-312.pyc index f3f06f7..ce45601 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/tree.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/__pycache__/tree.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_cell_widths.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_cell_widths.py index 36286df..608ae3a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_cell_widths.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_cell_widths.py @@ -4,6 +4,7 @@ CELL_WIDTHS = [ (0, 0, 0), (1, 31, -1), (127, 159, -1), + (173, 173, 0), (768, 879, 0), (1155, 1161, 0), (1425, 1469, 0), @@ -11,13 +12,16 @@ CELL_WIDTHS = [ (1473, 1474, 0), (1476, 1477, 0), (1479, 1479, 0), + (1536, 1541, 0), (1552, 1562, 0), + (1564, 1564, 0), (1611, 1631, 0), (1648, 1648, 0), - (1750, 1756, 0), + (1750, 1757, 0), (1759, 1764, 0), (1767, 1768, 0), (1770, 1773, 0), + (1807, 1807, 0), (1809, 1809, 0), (1840, 1866, 0), (1958, 1968, 0), @@ -28,149 +32,137 @@ CELL_WIDTHS = [ (2085, 2087, 0), (2089, 2093, 0), (2137, 2139, 0), - (2259, 2273, 0), - (2275, 2306, 0), - (2362, 2362, 0), - (2364, 2364, 0), - (2369, 2376, 0), - (2381, 2381, 0), + (2192, 2193, 0), + (2200, 2207, 0), + (2250, 2307, 0), + (2362, 2364, 0), + (2366, 2383, 0), (2385, 2391, 0), (2402, 2403, 0), - (2433, 2433, 0), + (2433, 2435, 0), (2492, 2492, 0), - (2497, 2500, 0), - (2509, 2509, 0), + (2494, 2500, 0), + (2503, 2504, 0), + (2507, 2509, 0), + (2519, 2519, 0), (2530, 2531, 0), (2558, 2558, 0), - (2561, 2562, 0), + (2561, 2563, 0), (2620, 2620, 0), - (2625, 2626, 0), + (2622, 2626, 0), (2631, 2632, 0), (2635, 2637, 0), (2641, 2641, 0), (2672, 2673, 0), (2677, 2677, 0), - (2689, 2690, 0), + (2689, 2691, 0), (2748, 2748, 0), - (2753, 2757, 0), - (2759, 2760, 0), - (2765, 2765, 0), + (2750, 2757, 0), + (2759, 2761, 0), + (2763, 2765, 0), (2786, 2787, 0), (2810, 2815, 0), - (2817, 2817, 0), + (2817, 2819, 0), (2876, 2876, 0), - (2879, 2879, 0), - (2881, 2884, 0), - (2893, 2893, 0), - (2901, 2902, 0), + (2878, 2884, 0), + (2887, 2888, 0), + (2891, 2893, 0), + (2901, 2903, 0), (2914, 2915, 0), (2946, 2946, 0), - (3008, 3008, 0), - (3021, 3021, 0), - (3072, 3072, 0), - (3076, 3076, 0), - (3134, 3136, 0), + (3006, 3010, 0), + (3014, 3016, 0), + (3018, 3021, 0), + (3031, 3031, 0), + (3072, 3076, 0), + (3132, 3132, 0), + (3134, 3140, 0), (3142, 3144, 0), (3146, 3149, 0), (3157, 3158, 0), (3170, 3171, 0), - (3201, 3201, 0), + (3201, 3203, 0), (3260, 3260, 0), - (3263, 3263, 0), - (3270, 3270, 0), - (3276, 3277, 0), + (3262, 3268, 0), + (3270, 3272, 0), + (3274, 3277, 0), + (3285, 3286, 0), (3298, 3299, 0), - (3328, 3329, 0), + (3315, 3315, 0), + (3328, 3331, 0), (3387, 3388, 0), - (3393, 3396, 0), - (3405, 3405, 0), + (3390, 3396, 0), + (3398, 3400, 0), + (3402, 3405, 0), + (3415, 3415, 0), (3426, 3427, 0), - (3457, 3457, 0), + (3457, 3459, 0), (3530, 3530, 0), - (3538, 3540, 0), + (3535, 3540, 0), (3542, 3542, 0), + (3544, 3551, 0), + (3570, 3571, 0), (3633, 3633, 0), (3636, 3642, 0), (3655, 3662, 0), (3761, 3761, 0), (3764, 3772, 0), - (3784, 3789, 0), + (3784, 3790, 0), (3864, 3865, 0), (3893, 3893, 0), (3895, 3895, 0), (3897, 3897, 0), - (3953, 3966, 0), - (3968, 3972, 0), + (3902, 3903, 0), + (3953, 3972, 0), (3974, 3975, 0), (3981, 3991, 0), (3993, 4028, 0), (4038, 4038, 0), - (4141, 4144, 0), - (4146, 4151, 0), - (4153, 4154, 0), - (4157, 4158, 0), - (4184, 4185, 0), + (4139, 4158, 0), + (4182, 4185, 0), (4190, 4192, 0), + (4194, 4196, 0), + (4199, 4205, 0), (4209, 4212, 0), - (4226, 4226, 0), - (4229, 4230, 0), - (4237, 4237, 0), - (4253, 4253, 0), + (4226, 4237, 0), + (4239, 4239, 0), + (4250, 4253, 0), (4352, 4447, 2), + (4448, 4607, 0), (4957, 4959, 0), - (5906, 5908, 0), + (5906, 5909, 0), (5938, 5940, 0), (5970, 5971, 0), (6002, 6003, 0), - (6068, 6069, 0), - (6071, 6077, 0), - (6086, 6086, 0), - (6089, 6099, 0), + (6068, 6099, 0), (6109, 6109, 0), - (6155, 6157, 0), + (6155, 6159, 0), (6277, 6278, 0), (6313, 6313, 0), - (6432, 6434, 0), - (6439, 6440, 0), - (6450, 6450, 0), - (6457, 6459, 0), - (6679, 6680, 0), - (6683, 6683, 0), - (6742, 6742, 0), - (6744, 6750, 0), - (6752, 6752, 0), - (6754, 6754, 0), - (6757, 6764, 0), - (6771, 6780, 0), + (6432, 6443, 0), + (6448, 6459, 0), + (6679, 6683, 0), + (6741, 6750, 0), + (6752, 6780, 0), (6783, 6783, 0), - (6832, 6848, 0), - (6912, 6915, 0), - (6964, 6964, 0), - (6966, 6970, 0), - (6972, 6972, 0), - (6978, 6978, 0), + (6832, 6862, 0), + (6912, 6916, 0), + (6964, 6980, 0), (7019, 7027, 0), - (7040, 7041, 0), - (7074, 7077, 0), - (7080, 7081, 0), - (7083, 7085, 0), - (7142, 7142, 0), - (7144, 7145, 0), - (7149, 7149, 0), - (7151, 7153, 0), - (7212, 7219, 0), - (7222, 7223, 0), + (7040, 7042, 0), + (7073, 7085, 0), + (7142, 7155, 0), + (7204, 7223, 0), (7376, 7378, 0), - (7380, 7392, 0), - (7394, 7400, 0), + (7380, 7400, 0), (7405, 7405, 0), (7412, 7412, 0), - (7416, 7417, 0), - (7616, 7673, 0), - (7675, 7679, 0), + (7415, 7417, 0), + (7616, 7679, 0), (8203, 8207, 0), (8232, 8238, 0), - (8288, 8291, 0), + (8288, 8292, 0), + (8294, 8303, 0), (8400, 8432, 0), (8986, 8987, 2), (9001, 9002, 2), @@ -212,17 +204,16 @@ CELL_WIDTHS = [ (11904, 11929, 2), (11931, 12019, 2), (12032, 12245, 2), - (12272, 12283, 2), - (12288, 12329, 2), - (12330, 12333, 0), - (12334, 12350, 2), + (12272, 12329, 2), + (12330, 12335, 0), + (12336, 12350, 2), (12353, 12438, 2), (12441, 12442, 0), (12443, 12543, 2), (12549, 12591, 2), (12593, 12686, 2), (12688, 12771, 2), - (12784, 12830, 2), + (12783, 12830, 2), (12832, 12871, 2), (12880, 19903, 2), (19968, 42124, 2), @@ -234,36 +225,33 @@ CELL_WIDTHS = [ (43010, 43010, 0), (43014, 43014, 0), (43019, 43019, 0), - (43045, 43046, 0), + (43043, 43047, 0), (43052, 43052, 0), - (43204, 43205, 0), + (43136, 43137, 0), + (43188, 43205, 0), (43232, 43249, 0), (43263, 43263, 0), (43302, 43309, 0), - (43335, 43345, 0), + (43335, 43347, 0), (43360, 43388, 2), - (43392, 43394, 0), - (43443, 43443, 0), - (43446, 43449, 0), - (43452, 43453, 0), + (43392, 43395, 0), + (43443, 43456, 0), (43493, 43493, 0), - (43561, 43566, 0), - (43569, 43570, 0), - (43573, 43574, 0), + (43561, 43574, 0), (43587, 43587, 0), - (43596, 43596, 0), - (43644, 43644, 0), + (43596, 43597, 0), + (43643, 43645, 0), (43696, 43696, 0), (43698, 43700, 0), (43703, 43704, 0), (43710, 43711, 0), (43713, 43713, 0), - (43756, 43757, 0), - (43766, 43766, 0), - (44005, 44005, 0), - (44008, 44008, 0), - (44013, 44013, 0), + (43755, 43759, 0), + (43765, 43766, 0), + (44003, 44010, 0), + (44012, 44013, 0), (44032, 55203, 2), + (55216, 55295, 0), (63744, 64255, 2), (64286, 64286, 0), (65024, 65039, 0), @@ -272,8 +260,10 @@ CELL_WIDTHS = [ (65072, 65106, 2), (65108, 65126, 2), (65128, 65131, 2), + (65279, 65279, 0), (65281, 65376, 2), (65504, 65510, 2), + (65529, 65531, 0), (66045, 66045, 0), (66272, 66272, 0), (66422, 66426, 0), @@ -285,102 +275,108 @@ CELL_WIDTHS = [ (68325, 68326, 0), (68900, 68903, 0), (69291, 69292, 0), + (69373, 69375, 0), (69446, 69456, 0), - (69633, 69633, 0), + (69506, 69509, 0), + (69632, 69634, 0), (69688, 69702, 0), - (69759, 69761, 0), - (69811, 69814, 0), - (69817, 69818, 0), + (69744, 69744, 0), + (69747, 69748, 0), + (69759, 69762, 0), + (69808, 69818, 0), + (69821, 69821, 0), + (69826, 69826, 0), + (69837, 69837, 0), (69888, 69890, 0), - (69927, 69931, 0), - (69933, 69940, 0), + (69927, 69940, 0), + (69957, 69958, 0), (70003, 70003, 0), - (70016, 70017, 0), - (70070, 70078, 0), + (70016, 70018, 0), + (70067, 70080, 0), (70089, 70092, 0), - (70095, 70095, 0), - (70191, 70193, 0), - (70196, 70196, 0), - (70198, 70199, 0), + (70094, 70095, 0), + (70188, 70199, 0), (70206, 70206, 0), - (70367, 70367, 0), - (70371, 70378, 0), - (70400, 70401, 0), + (70209, 70209, 0), + (70367, 70378, 0), + (70400, 70403, 0), (70459, 70460, 0), - (70464, 70464, 0), + (70462, 70468, 0), + (70471, 70472, 0), + (70475, 70477, 0), + (70487, 70487, 0), + (70498, 70499, 0), (70502, 70508, 0), (70512, 70516, 0), - (70712, 70719, 0), - (70722, 70724, 0), - (70726, 70726, 0), + (70709, 70726, 0), (70750, 70750, 0), - (70835, 70840, 0), - (70842, 70842, 0), - (70847, 70848, 0), - (70850, 70851, 0), - (71090, 71093, 0), - (71100, 71101, 0), - (71103, 71104, 0), + (70832, 70851, 0), + (71087, 71093, 0), + (71096, 71104, 0), (71132, 71133, 0), - (71219, 71226, 0), - (71229, 71229, 0), - (71231, 71232, 0), - (71339, 71339, 0), - (71341, 71341, 0), - (71344, 71349, 0), - (71351, 71351, 0), - (71453, 71455, 0), - (71458, 71461, 0), - (71463, 71467, 0), - (71727, 71735, 0), - (71737, 71738, 0), - (71995, 71996, 0), - (71998, 71998, 0), - (72003, 72003, 0), - (72148, 72151, 0), - (72154, 72155, 0), - (72160, 72160, 0), + (71216, 71232, 0), + (71339, 71351, 0), + (71453, 71467, 0), + (71724, 71738, 0), + (71984, 71989, 0), + (71991, 71992, 0), + (71995, 71998, 0), + (72000, 72000, 0), + (72002, 72003, 0), + (72145, 72151, 0), + (72154, 72160, 0), + (72164, 72164, 0), (72193, 72202, 0), - (72243, 72248, 0), + (72243, 72249, 0), (72251, 72254, 0), (72263, 72263, 0), - (72273, 72278, 0), - (72281, 72283, 0), - (72330, 72342, 0), - (72344, 72345, 0), - (72752, 72758, 0), - (72760, 72765, 0), - (72767, 72767, 0), + (72273, 72283, 0), + (72330, 72345, 0), + (72751, 72758, 0), + (72760, 72767, 0), (72850, 72871, 0), - (72874, 72880, 0), - (72882, 72883, 0), - (72885, 72886, 0), + (72873, 72886, 0), (73009, 73014, 0), (73018, 73018, 0), (73020, 73021, 0), (73023, 73029, 0), (73031, 73031, 0), + (73098, 73102, 0), (73104, 73105, 0), - (73109, 73109, 0), - (73111, 73111, 0), - (73459, 73460, 0), + (73107, 73111, 0), + (73459, 73462, 0), + (73472, 73473, 0), + (73475, 73475, 0), + (73524, 73530, 0), + (73534, 73538, 0), + (78896, 78912, 0), + (78919, 78933, 0), (92912, 92916, 0), (92976, 92982, 0), (94031, 94031, 0), + (94033, 94087, 0), (94095, 94098, 0), (94176, 94179, 2), (94180, 94180, 0), - (94192, 94193, 2), + (94192, 94193, 0), (94208, 100343, 2), (100352, 101589, 2), (101632, 101640, 2), - (110592, 110878, 2), + (110576, 110579, 2), + (110581, 110587, 2), + (110589, 110590, 2), + (110592, 110882, 2), + (110898, 110898, 2), (110928, 110930, 2), + (110933, 110933, 2), (110948, 110951, 2), (110960, 111355, 2), (113821, 113822, 0), - (119143, 119145, 0), - (119163, 119170, 0), + (113824, 113827, 0), + (118528, 118573, 0), + (118576, 118598, 0), + (119141, 119145, 0), + (119149, 119170, 0), (119173, 119179, 0), (119210, 119213, 0), (119362, 119364, 0), @@ -395,8 +391,11 @@ CELL_WIDTHS = [ (122907, 122913, 0), (122915, 122916, 0), (122918, 122922, 0), + (123023, 123023, 0), (123184, 123190, 0), + (123566, 123566, 0), (123628, 123631, 0), + (124140, 124143, 0), (125136, 125142, 0), (125252, 125258, 0), (126980, 126980, 2), @@ -416,7 +415,9 @@ CELL_WIDTHS = [ (127951, 127955, 2), (127968, 127984, 2), (127988, 127988, 2), - (127992, 128062, 2), + (127992, 127994, 2), + (127995, 127999, 0), + (128000, 128062, 2), (128064, 128064, 2), (128066, 128252, 2), (128255, 128317, 2), @@ -430,22 +431,24 @@ CELL_WIDTHS = [ (128716, 128716, 2), (128720, 128722, 2), (128725, 128727, 2), + (128732, 128735, 2), (128747, 128748, 2), (128756, 128764, 2), (128992, 129003, 2), + (129008, 129008, 2), (129292, 129338, 2), (129340, 129349, 2), - (129351, 129400, 2), - (129402, 129483, 2), - (129485, 129535, 2), - (129648, 129652, 2), - (129656, 129658, 2), - (129664, 129670, 2), - (129680, 129704, 2), - (129712, 129718, 2), - (129728, 129730, 2), - (129744, 129750, 2), + (129351, 129535, 2), + (129648, 129660, 2), + (129664, 129672, 2), + (129680, 129725, 2), + (129727, 129733, 2), + (129742, 129755, 2), + (129760, 129768, 2), + (129776, 129784, 2), (131072, 196605, 2), (196608, 262141, 2), + (917505, 917505, 0), + (917536, 917631, 0), (917760, 917999, 0), ] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_export_format.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_export_format.py index 094d2dc..e7527e5 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_export_format.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_export_format.py @@ -1,5 +1,6 @@ CONSOLE_HTML_FORMAT = """\ + - - 
{code}
+ 
{code}
""" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_inspect.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_inspect.py index 30446ce..e87698d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_inspect.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_inspect.py @@ -1,5 +1,3 @@ -from __future__ import absolute_import - import inspect from inspect import cleandoc, getdoc, getfile, isclass, ismodule, signature from typing import Any, Collection, Iterable, Optional, Tuple, Type, Union diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_null_file.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_null_file.py index b659673..6ae05d3 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_null_file.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_null_file.py @@ -46,7 +46,7 @@ class NullFile(IO[str]): return iter([""]) def __enter__(self) -> IO[str]: - pass + return self def __exit__( self, diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_ratio.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_ratio.py index e8a3a67..95267b0 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_ratio.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_ratio.py @@ -151,7 +151,6 @@ if __name__ == "__main__": @dataclass class E: - size: Optional[int] = None ratio: int = 1 minimum_size: int = 1 diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_win32_console.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_win32_console.py index 81b1082..2eba1b9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_win32_console.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_win32_console.py @@ -2,6 +2,7 @@ The API that this module wraps is documented at https://docs.microsoft.com/en-us/windows/console/console-functions """ + import ctypes import sys from typing import Any @@ -380,7 +381,7 @@ class LegacyWindowsTerm: WindowsCoordinates: The current cursor position. """ coord: COORD = GetConsoleScreenBufferInfo(self._handle).dwCursorPosition - return WindowsCoordinates(row=cast(int, coord.Y), col=cast(int, coord.X)) + return WindowsCoordinates(row=coord.Y, col=coord.X) @property def screen_size(self) -> WindowsCoordinates: @@ -390,9 +391,7 @@ class LegacyWindowsTerm: WindowsCoordinates: The width and height of the screen as WindowsCoordinates. """ screen_size: COORD = GetConsoleScreenBufferInfo(self._handle).dwSize - return WindowsCoordinates( - row=cast(int, screen_size.Y), col=cast(int, screen_size.X) - ) + return WindowsCoordinates(row=screen_size.Y, col=screen_size.X) def write_text(self, text: str) -> None: """Write text directly to the terminal without any modification of styles diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_windows.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_windows.py index 10fc0d7..7520a9f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_windows.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_windows.py @@ -30,7 +30,6 @@ try: ) except (AttributeError, ImportError, ValueError): - # Fallback if we can't load the Windows DLL def get_windows_console_features() -> WindowsConsoleFeatures: features = WindowsConsoleFeatures() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_wrap.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_wrap.py index c45f193..2e94ff6 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_wrap.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/_wrap.py @@ -1,5 +1,7 @@ +from __future__ import annotations + import re -from typing import Iterable, List, Tuple +from typing import Iterable from ._loop import loop_last from .cells import cell_len, chop_cells @@ -7,7 +9,11 @@ from .cells import cell_len, chop_cells re_word = re.compile(r"\s*\S+\s*") -def words(text: str) -> Iterable[Tuple[int, int, str]]: +def words(text: str) -> Iterable[tuple[int, int, str]]: + """Yields each word from the text as a tuple + containing (start_index, end_index, word). A "word" in this context may + include the actual word and any whitespace to the right. + """ position = 0 word_match = re_word.match(text, position) while word_match is not None: @@ -17,35 +23,59 @@ def words(text: str) -> Iterable[Tuple[int, int, str]]: word_match = re_word.match(text, end) -def divide_line(text: str, width: int, fold: bool = True) -> List[int]: - divides: List[int] = [] - append = divides.append - line_position = 0 +def divide_line(text: str, width: int, fold: bool = True) -> list[int]: + """Given a string of text, and a width (measured in cells), return a list + of cell offsets which the string should be split at in order for it to fit + within the given width. + + Args: + text: The text to examine. + width: The available cell width. + fold: If True, words longer than `width` will be folded onto a new line. + + Returns: + A list of indices to break the line at. + """ + break_positions: list[int] = [] # offsets to insert the breaks at + append = break_positions.append + cell_offset = 0 _cell_len = cell_len + for start, _end, word in words(text): word_length = _cell_len(word.rstrip()) - if line_position + word_length > width: + remaining_space = width - cell_offset + word_fits_remaining_space = remaining_space >= word_length + + if word_fits_remaining_space: + # Simplest case - the word fits within the remaining width for this line. + cell_offset += _cell_len(word) + else: + # Not enough space remaining for this word on the current line. if word_length > width: + # The word doesn't fit on any line, so we can't simply + # place it on the next line... if fold: - chopped_words = chop_cells(word, max_size=width, position=0) - for last, line in loop_last(chopped_words): + # Fold the word across multiple lines. + folded_word = chop_cells(word, width=width) + for last, line in loop_last(folded_word): if start: append(start) - if last: - line_position = _cell_len(line) + cell_offset = _cell_len(line) else: start += len(line) else: + # Folding isn't allowed, so crop the word. if start: append(start) - line_position = _cell_len(word) - elif line_position and start: + cell_offset = _cell_len(word) + elif cell_offset and start: + # The word doesn't fit within the remaining space on the current + # line, but it *can* fit on to the next (empty) line. append(start) - line_position = _cell_len(word) - else: - line_position += _cell_len(word) - return divides + cell_offset = _cell_len(word) + + return break_positions if __name__ == "__main__": # pragma: no cover @@ -53,4 +83,11 @@ if __name__ == "__main__": # pragma: no cover console = Console(width=10) console.print("12345 abcdefghijklmnopqrstuvwyxzABCDEFGHIJKLMNOPQRSTUVWXYZ 12345") - print(chop_cells("abcdefghijklmnopqrstuvwxyz", 10, position=2)) + print(chop_cells("abcdefghijklmnopqrstuvwxyz", 10)) + + console = Console(width=20) + console.rule() + console.print("TextualはPythonの高速アプリケーション開発フレームワークです") + + console.rule() + console.print("アプリケーションは1670万色を使用でき") diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/align.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/align.py index c310b66..330dcc5 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/align.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/align.py @@ -27,7 +27,7 @@ class Align(JupyterMixin): renderable (RenderableType): A console renderable. align (AlignMethod): One of "left", "center", or "right"" style (StyleType, optional): An optional style to apply to the background. - vertical (Optional[VerticalAlginMethod], optional): Optional vertical align, one of "top", "middle", or "bottom". Defaults to None. + vertical (Optional[VerticalAlignMethod], optional): Optional vertical align, one of "top", "middle", or "bottom". Defaults to None. pad (bool, optional): Pad the right with spaces. Defaults to True. width (int, optional): Restrict contents to given width, or None to use default width. Defaults to None. height (int, optional): Set height of align renderable, or None to fit to contents. Defaults to None. @@ -240,6 +240,7 @@ class VerticalCenter(JupyterMixin): Args: renderable (RenderableType): A renderable object. + style (StyleType, optional): An optional style to apply to the background. Defaults to None. """ def __init__( diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/ansi.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/ansi.py index 66365e6..7de86ce 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/ansi.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/ansi.py @@ -9,6 +9,7 @@ from .text import Text re_ansi = re.compile( r""" +(?:\x1b[0-?])| (?:\x1b\](.*?)\x1b\\)| (?:\x1b([(@-Z\\-_]|\[[0-?]*[ -/]*[@-~])) """, diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/bar.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/bar.py index ed86a55..022284b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/bar.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/bar.py @@ -48,7 +48,6 @@ class Bar(JupyterMixin): def __rich_console__( self, console: Console, options: ConsoleOptions ) -> RenderResult: - width = min( self.width if self.width is not None else options.max_width, options.max_width, diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/box.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/box.py index 97d2a94..0511a9e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/box.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/box.py @@ -188,260 +188,224 @@ class Box: return "".join(parts) +# fmt: off ASCII: Box = Box( - """\ -+--+ -| || -|-+| -| || -|-+| -|-+| -| || -+--+ -""", + "+--+\n" + "| ||\n" + "|-+|\n" + "| ||\n" + "|-+|\n" + "|-+|\n" + "| ||\n" + "+--+\n", ascii=True, ) ASCII2: Box = Box( - """\ -+-++ -| || -+-++ -| || -+-++ -+-++ -| || -+-++ -""", + "+-++\n" + "| ||\n" + "+-++\n" + "| ||\n" + "+-++\n" + "+-++\n" + "| ||\n" + "+-++\n", ascii=True, ) ASCII_DOUBLE_HEAD: Box = Box( - """\ -+-++ -| || -+=++ -| || -+-++ -+-++ -| || -+-++ -""", + "+-++\n" + "| ||\n" + "+=++\n" + "| ||\n" + "+-++\n" + "+-++\n" + "| ||\n" + "+-++\n", ascii=True, ) SQUARE: Box = Box( - """\ -┌─┬┐ -│ ││ -├─┼┤ -│ ││ -├─┼┤ -├─┼┤ -│ ││ -└─┴┘ -""" + "┌─┬┐\n" + "│ ││\n" + "├─┼┤\n" + "│ ││\n" + "├─┼┤\n" + "├─┼┤\n" + "│ ││\n" + "└─┴┘\n" ) SQUARE_DOUBLE_HEAD: Box = Box( - """\ -┌─┬┐ -│ ││ -╞═╪╡ -│ ││ -├─┼┤ -├─┼┤ -│ ││ -└─┴┘ -""" + "┌─┬┐\n" + "│ ││\n" + "╞═╪╡\n" + "│ ││\n" + "├─┼┤\n" + "├─┼┤\n" + "│ ││\n" + "└─┴┘\n" ) MINIMAL: Box = Box( - """\ - ╷ - │ -╶─┼╴ - │ -╶─┼╴ -╶─┼╴ - │ - ╵ -""" + " ╷ \n" + " │ \n" + "╶─┼╴\n" + " │ \n" + "╶─┼╴\n" + "╶─┼╴\n" + " │ \n" + " ╵ \n" ) MINIMAL_HEAVY_HEAD: Box = Box( - """\ - ╷ - │ -╺━┿╸ - │ -╶─┼╴ -╶─┼╴ - │ - ╵ -""" + " ╷ \n" + " │ \n" + "╺━┿╸\n" + " │ \n" + "╶─┼╴\n" + "╶─┼╴\n" + " │ \n" + " ╵ \n" ) MINIMAL_DOUBLE_HEAD: Box = Box( - """\ - ╷ - │ - ═╪ - │ - ─┼ - ─┼ - │ - ╵ -""" + " ╷ \n" + " │ \n" + " ═╪ \n" + " │ \n" + " ─┼ \n" + " ─┼ \n" + " │ \n" + " ╵ \n" ) SIMPLE: Box = Box( - """\ - - - ── - - - ── - - -""" + " \n" + " \n" + " ── \n" + " \n" + " \n" + " ── \n" + " \n" + " \n" ) SIMPLE_HEAD: Box = Box( - """\ - - - ── - - - - - -""" + " \n" + " \n" + " ── \n" + " \n" + " \n" + " \n" + " \n" + " \n" ) SIMPLE_HEAVY: Box = Box( - """\ - - - ━━ - - - ━━ - - -""" + " \n" + " \n" + " ━━ \n" + " \n" + " \n" + " ━━ \n" + " \n" + " \n" ) HORIZONTALS: Box = Box( - """\ - ── - - ── - - ── - ── - - ── -""" + " ── \n" + " \n" + " ── \n" + " \n" + " ── \n" + " ── \n" + " \n" + " ── \n" ) ROUNDED: Box = Box( - """\ -╭─┬╮ -│ ││ -├─┼┤ -│ ││ -├─┼┤ -├─┼┤ -│ ││ -╰─┴╯ -""" + "╭─┬╮\n" + "│ ││\n" + "├─┼┤\n" + "│ ││\n" + "├─┼┤\n" + "├─┼┤\n" + "│ ││\n" + "╰─┴╯\n" ) HEAVY: Box = Box( - """\ -┏━┳┓ -┃ ┃┃ -┣━╋┫ -┃ ┃┃ -┣━╋┫ -┣━╋┫ -┃ ┃┃ -┗━┻┛ -""" + "┏━┳┓\n" + "┃ ┃┃\n" + "┣━╋┫\n" + "┃ ┃┃\n" + "┣━╋┫\n" + "┣━╋┫\n" + "┃ ┃┃\n" + "┗━┻┛\n" ) HEAVY_EDGE: Box = Box( - """\ -┏━┯┓ -┃ │┃ -┠─┼┨ -┃ │┃ -┠─┼┨ -┠─┼┨ -┃ │┃ -┗━┷┛ -""" + "┏━┯┓\n" + "┃ │┃\n" + "┠─┼┨\n" + "┃ │┃\n" + "┠─┼┨\n" + "┠─┼┨\n" + "┃ │┃\n" + "┗━┷┛\n" ) HEAVY_HEAD: Box = Box( - """\ -┏━┳┓ -┃ ┃┃ -┡━╇┩ -│ ││ -├─┼┤ -├─┼┤ -│ ││ -└─┴┘ -""" + "┏━┳┓\n" + "┃ ┃┃\n" + "┡━╇┩\n" + "│ ││\n" + "├─┼┤\n" + "├─┼┤\n" + "│ ││\n" + "└─┴┘\n" ) DOUBLE: Box = Box( - """\ -╔═╦╗ -║ ║║ -╠═╬╣ -║ ║║ -╠═╬╣ -╠═╬╣ -║ ║║ -╚═╩╝ -""" + "╔═╦╗\n" + "║ ║║\n" + "╠═╬╣\n" + "║ ║║\n" + "╠═╬╣\n" + "╠═╬╣\n" + "║ ║║\n" + "╚═╩╝\n" ) DOUBLE_EDGE: Box = Box( - """\ -╔═╤╗ -║ │║ -╟─┼╢ -║ │║ -╟─┼╢ -╟─┼╢ -║ │║ -╚═╧╝ -""" + "╔═╤╗\n" + "║ │║\n" + "╟─┼╢\n" + "║ │║\n" + "╟─┼╢\n" + "╟─┼╢\n" + "║ │║\n" + "╚═╧╝\n" ) MARKDOWN: Box = Box( - """\ - -| || -|-|| -| || -|-|| -|-|| -| || - -""", + " \n" + "| ||\n" + "|-||\n" + "| ||\n" + "|-||\n" + "|-||\n" + "| ||\n" + " \n", ascii=True, ) +# fmt: on # Map Boxes that don't render with raster fonts on to equivalent that do LEGACY_WINDOWS_SUBSTITUTIONS = { @@ -464,7 +428,6 @@ PLAIN_HEADED_SUBSTITUTIONS = { if __name__ == "__main__": # pragma: no cover - from pip._vendor.rich.columns import Columns from pip._vendor.rich.panel import Panel diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/cells.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/cells.py index 9354f9e..a854622 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/cells.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/cells.py @@ -1,11 +1,33 @@ -import re +from __future__ import annotations + from functools import lru_cache -from typing import Callable, List +from typing import Callable from ._cell_widths import CELL_WIDTHS -# Regex to match sequence of the most common character ranges -_is_single_cell_widths = re.compile("^[\u0020-\u006f\u00a0\u02ff\u0370-\u0482]*$").match +# Ranges of unicode ordinals that produce a 1-cell wide character +# This is non-exhaustive, but covers most common Western characters +_SINGLE_CELL_UNICODE_RANGES: list[tuple[int, int]] = [ + (0x20, 0x7E), # Latin (excluding non-printable) + (0xA0, 0xAC), + (0xAE, 0x002FF), + (0x00370, 0x00482), # Greek / Cyrillic + (0x02500, 0x025FC), # Box drawing, box elements, geometric shapes + (0x02800, 0x028FF), # Braille +] + +# A set of characters that are a single cell wide +_SINGLE_CELLS = frozenset( + [ + character + for _start, _end in _SINGLE_CELL_UNICODE_RANGES + for character in map(chr, range(_start, _end + 1)) + ] +) + +# When called with a string this will return True if all +# characters are single-cell, otherwise False +_is_single_cell_widths: Callable[[str], bool] = _SINGLE_CELLS.issuperset @lru_cache(4096) @@ -21,9 +43,9 @@ def cached_cell_len(text: str) -> int: Returns: int: Get the number of cells required to display text. """ - _get_size = get_character_cell_size - total_size = sum(_get_size(character) for character in text) - return total_size + if _is_single_cell_widths(text): + return len(text) + return sum(map(get_character_cell_size, text)) def cell_len(text: str, _cell_len: Callable[[str], int] = cached_cell_len) -> int: @@ -37,9 +59,9 @@ def cell_len(text: str, _cell_len: Callable[[str], int] = cached_cell_len) -> in """ if len(text) < 512: return _cell_len(text) - _get_size = get_character_cell_size - total_size = sum(_get_size(character) for character in text) - return total_size + if _is_single_cell_widths(text): + return len(text) + return sum(map(get_character_cell_size, text)) @lru_cache(maxsize=4096) @@ -52,20 +74,7 @@ def get_character_cell_size(character: str) -> int: Returns: int: Number of cells (0, 1 or 2) occupied by that character. """ - return _get_codepoint_cell_size(ord(character)) - - -@lru_cache(maxsize=4096) -def _get_codepoint_cell_size(codepoint: int) -> int: - """Get the cell size of a character. - - Args: - codepoint (int): Codepoint of a character. - - Returns: - int: Number of cells (0, 1 or 2) occupied by that character. - """ - + codepoint = ord(character) _table = CELL_WIDTHS lower_bound = 0 upper_bound = len(_table) - 1 @@ -119,33 +128,44 @@ def set_cell_size(text: str, total: int) -> str: start = pos -# TODO: This is inefficient -# TODO: This might not work with CWJ type characters -def chop_cells(text: str, max_size: int, position: int = 0) -> List[str]: - """Break text in to equal (cell) length strings, returning the characters in reverse - order""" - _get_character_cell_size = get_character_cell_size - characters = [ - (character, _get_character_cell_size(character)) for character in text - ] - total_size = position - lines: List[List[str]] = [[]] - append = lines[-1].append +def chop_cells( + text: str, + width: int, +) -> list[str]: + """Split text into lines such that each line fits within the available (cell) width. - for character, size in reversed(characters): - if total_size + size > max_size: - lines.append([character]) - append = lines[-1].append - total_size = size + Args: + text: The text to fold such that it fits in the given width. + width: The width available (number of cells). + + Returns: + A list of strings such that each string in the list has cell width + less than or equal to the available width. + """ + _get_character_cell_size = get_character_cell_size + lines: list[list[str]] = [[]] + + append_new_line = lines.append + append_to_last_line = lines[-1].append + + total_width = 0 + + for character in text: + cell_width = _get_character_cell_size(character) + char_doesnt_fit = total_width + cell_width > width + + if char_doesnt_fit: + append_new_line([character]) + append_to_last_line = lines[-1].append + total_width = cell_width else: - total_size += size - append(character) + append_to_last_line(character) + total_width += cell_width return ["".join(line) for line in lines] if __name__ == "__main__": # pragma: no cover - print(get_character_cell_size("😽")) for line in chop_cells("""这是对亚洲语言支持的测试。面对模棱两可的想法，拒绝猜测的诱惑。""", 8): print(line) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/color.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/color.py index dfe4559..e2c23a6 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/color.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/color.py @@ -1,5 +1,5 @@ -import platform import re +import sys from colorsys import rgb_to_hls from enum import IntEnum from functools import lru_cache @@ -15,7 +15,7 @@ if TYPE_CHECKING: # pragma: no cover from .text import Text -WINDOWS = platform.system() == "Windows" +WINDOWS = sys.platform == "win32" class ColorSystem(IntEnum): @@ -592,7 +592,6 @@ def blend_rgb( if __name__ == "__main__": # pragma: no cover - from .console import Console from .table import Table from .text import Text diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/console.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/console.py index e559cbb..5728845 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/console.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/console.py @@ -1,6 +1,5 @@ import inspect import os -import platform import sys import threading import zlib @@ -76,7 +75,7 @@ if TYPE_CHECKING: JUPYTER_DEFAULT_COLUMNS = 115 JUPYTER_DEFAULT_LINES = 100 -WINDOWS = platform.system() == "Windows" +WINDOWS = sys.platform == "win32" HighlighterType = Callable[[Union[str, "Text"]], "Text"] JustifyMethod = Literal["default", "left", "center", "right", "full"] @@ -90,15 +89,15 @@ class NoChange: NO_CHANGE = NoChange() try: - _STDIN_FILENO = sys.__stdin__.fileno() + _STDIN_FILENO = sys.__stdin__.fileno() # type: ignore[union-attr] except Exception: _STDIN_FILENO = 0 try: - _STDOUT_FILENO = sys.__stdout__.fileno() + _STDOUT_FILENO = sys.__stdout__.fileno() # type: ignore[union-attr] except Exception: _STDOUT_FILENO = 1 try: - _STDERR_FILENO = sys.__stderr__.fileno() + _STDERR_FILENO = sys.__stderr__.fileno() # type: ignore[union-attr] except Exception: _STDERR_FILENO = 2 @@ -278,6 +277,7 @@ class ConsoleRenderable(Protocol): # A type that may be rendered by Console. RenderableType = Union[ConsoleRenderable, RichCast, str] +"""A string or any object that may be rendered by Rich.""" # The result of calling a __rich_console__ method. RenderResult = Iterable[Union[RenderableType, Segment]] @@ -1005,19 +1005,14 @@ class Console: width: Optional[int] = None height: Optional[int] = None - if WINDOWS: # pragma: no cover + streams = _STD_STREAMS_OUTPUT if WINDOWS else _STD_STREAMS + for file_descriptor in streams: try: - width, height = os.get_terminal_size() + width, height = os.get_terminal_size(file_descriptor) except (AttributeError, ValueError, OSError): # Probably not a terminal pass - else: - for file_descriptor in _STD_STREAMS: - try: - width, height = os.get_terminal_size(file_descriptor) - except (AttributeError, ValueError, OSError): - pass - else: - break + else: + break columns = self._environ.get("COLUMNS") if columns is not None and columns.isdigit(): @@ -1308,7 +1303,7 @@ class Console: renderable = rich_cast(renderable) if hasattr(renderable, "__rich_console__") and not isclass(renderable): - render_iterable = renderable.__rich_console__(self, _options) # type: ignore[union-attr] + render_iterable = renderable.__rich_console__(self, _options) elif isinstance(renderable, str): text_renderable = self.render_str( renderable, highlight=_options.highlight, markup=_options.markup @@ -1385,9 +1380,14 @@ class Console: extra_lines = render_options.height - len(lines) if extra_lines > 0: pad_line = [ - [Segment(" " * render_options.max_width, style), Segment("\n")] - if new_lines - else [Segment(" " * render_options.max_width, style)] + ( + [ + Segment(" " * render_options.max_width, style), + Segment("\n"), + ] + if new_lines + else [Segment(" " * render_options.max_width, style)] + ) ] lines.extend(pad_line * extra_lines) @@ -1436,9 +1436,11 @@ class Console: rich_text.overflow = overflow else: rich_text = Text( - _emoji_replace(text, default_variant=self._emoji_variant) - if emoji_enabled - else text, + ( + _emoji_replace(text, default_variant=self._emoji_variant) + if emoji_enabled + else text + ), justify=justify, overflow=overflow, style=style, @@ -1535,7 +1537,11 @@ class Console: if isinstance(renderable, str): append_text( self.render_str( - renderable, emoji=emoji, markup=markup, highlighter=_highlighter + renderable, + emoji=emoji, + markup=markup, + highlight=highlight, + highlighter=_highlighter, ) ) elif isinstance(renderable, Text): @@ -1925,7 +1931,6 @@ class Console: end (str, optional): String to write at end of print data. Defaults to "\\\\n". style (Union[str, Style], optional): A style to apply to output. Defaults to None. justify (str, optional): One of "left", "right", "center", or "full". Defaults to ``None``. - overflow (str, optional): Overflow method: "crop", "fold", or "ellipsis". Defaults to None. emoji (Optional[bool], optional): Enable emoji code, or ``None`` to use console default. Defaults to None. markup (Optional[bool], optional): Enable markup, or ``None`` to use console default. Defaults to None. highlight (Optional[bool], optional): Enable automatic highlighting, or ``None`` to use console default. Defaults to None. @@ -1986,6 +1991,20 @@ class Console: ): buffer_extend(line) + def on_broken_pipe(self) -> None: + """This function is called when a `BrokenPipeError` is raised. + + This can occur when piping Textual output in Linux and macOS. + The default implementation is to exit the app, but you could implement + this method in a subclass to change the behavior. + + See https://docs.python.org/3/library/signal.html#note-on-sigpipe for details. + """ + self.quiet = True + devnull = os.open(os.devnull, os.O_WRONLY) + os.dup2(devnull, sys.stdout.fileno()) + raise SystemExit(1) + def _check_buffer(self) -> None: """Check if the buffer may be rendered. Render it if it can (e.g. Console.quiet is False) Rendering is supported on Windows, Unix and Jupyter environments. For @@ -1995,8 +2014,17 @@ class Console: if self.quiet: del self._buffer[:] return + + try: + self._write_buffer() + except BrokenPipeError: + self.on_broken_pipe() + + def _write_buffer(self) -> None: + """Write the buffer to the output file.""" + with self._lock: - if self.record: + if self.record and not self._buffer_index: with self._record_buffer_lock: self._record_buffer.extend(self._buffer[:]) @@ -2166,7 +2194,7 @@ class Console: """ text = self.export_text(clear=clear, styles=styles) - with open(path, "wt", encoding="utf-8") as write_file: + with open(path, "w", encoding="utf-8") as write_file: write_file.write(text) def export_html( @@ -2272,7 +2300,7 @@ class Console: code_format=code_format, inline_styles=inline_styles, ) - with open(path, "wt", encoding="utf-8") as write_file: + with open(path, "w", encoding="utf-8") as write_file: write_file.write(html) def export_svg( @@ -2561,7 +2589,7 @@ class Console: font_aspect_ratio=font_aspect_ratio, unique_id=unique_id, ) - with open(path, "wt", encoding="utf-8") as write_file: + with open(path, "w", encoding="utf-8") as write_file: write_file.write(svg) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/containers.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/containers.py index e29cf36..901ff8b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/containers.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/containers.py @@ -1,13 +1,13 @@ from itertools import zip_longest from typing import ( - Iterator, + TYPE_CHECKING, Iterable, + Iterator, List, Optional, + TypeVar, Union, overload, - TypeVar, - TYPE_CHECKING, ) if TYPE_CHECKING: @@ -119,7 +119,7 @@ class Lines: Args: console (Console): Console instance. - width (int): Number of characters per line. + width (int): Number of cells available per line. justify (str, optional): Default justify method for text: "left", "center", "full" or "right". Defaults to "left". overflow (str, optional): Default overflow for text: "crop", "fold", or "ellipsis". Defaults to "fold". diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/default_styles.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/default_styles.py index dca3719..6c0d732 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/default_styles.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/default_styles.py @@ -54,7 +54,7 @@ DEFAULT_STYLES: Dict[str, Style] = { "logging.level.notset": Style(dim=True), "logging.level.debug": Style(color="green"), "logging.level.info": Style(color="blue"), - "logging.level.warning": Style(color="red"), + "logging.level.warning": Style(color="yellow"), "logging.level.error": Style(color="red", bold=True), "logging.level.critical": Style(color="red", bold=True, reverse=True), "log.level": Style.null(), @@ -120,6 +120,7 @@ DEFAULT_STYLES: Dict[str, Style] = { "traceback.exc_type": Style(color="bright_red", bold=True), "traceback.exc_value": Style.null(), "traceback.offset": Style(color="bright_red", bold=True), + "traceback.error_range": Style(underline=True, bold=True, dim=False), "bar.back": Style(color="grey23"), "bar.complete": Style(color="rgb(249,38,114)"), "bar.finished": Style(color="rgb(114,156,31)"), diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/filesize.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/filesize.py index 99f118e..83bc911 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/filesize.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/filesize.py @@ -1,4 +1,3 @@ -# coding: utf-8 """Functions for reporting filesizes. Borrowed from https://github.com/PyFilesystem/pyfilesystem2 The functions declared in this module should cover the different @@ -27,7 +26,7 @@ def _to_str( if size == 1: return "1 byte" elif size < base: - return "{:,} bytes".format(size) + return f"{size:,} bytes" for i, suffix in enumerate(suffixes, 2): # noqa: B007 unit = base**i diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/highlighter.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/highlighter.py index c264679..e4c462e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/highlighter.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/highlighter.py @@ -98,7 +98,7 @@ class ReprHighlighter(RegexHighlighter): r"(?P(?\B(/[-\w._+]+)*\/)(?P[-\w._+]*)?", r"(?b?'''.*?(?(file|https|http|ws|wss)://[-0-9a-zA-Z$_+!`(),.?/;:&=%#]*)", + r"(?P(file|https|http|ws|wss)://[-0-9a-zA-Z$_+!`(),.?/;:&=%#~@]*)", ), ] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/json.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/json.py index ea94493..4087c79 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/json.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/json.py @@ -103,7 +103,6 @@ class JSON: if __name__ == "__main__": - import argparse import sys diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/layout.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/layout.py index 849356e..a6f1a31 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/layout.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/layout.py @@ -227,7 +227,6 @@ class Layout: from pip._vendor.rich.tree import Tree def summary(layout: "Layout") -> Table: - icon = layout.splitter.get_tree_icon() table = Table.grid(padding=(0, 1, 0, 0)) @@ -403,7 +402,7 @@ class Layout: self._render_map = render_map layout_lines: List[List[Segment]] = [[] for _ in range(height)] _islice = islice - for (region, lines) in render_map.values(): + for region, lines in render_map.values(): _x, y, _layout_width, layout_height = region for row, line in zip( _islice(layout_lines, y, y + layout_height), lines diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live.py index 3ebbbc4..8738cf0 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live.py @@ -37,7 +37,7 @@ class Live(JupyterMixin, RenderHook): Args: renderable (RenderableType, optional): The renderable to live display. Defaults to displaying nothing. - console (Console, optional): Optional Console instance. Default will an internal Console instance writing to stdout. + console (Console, optional): Optional Console instance. Defaults to an internal Console instance writing to stdout. screen (bool, optional): Enable alternate screen mode. Defaults to False. auto_refresh (bool, optional): Enable auto refresh. If disabled, you will need to call `refresh()` or `update()` with refresh flag. Defaults to True refresh_per_second (float, optional): Number of times per second to refresh the live display. Defaults to 4. @@ -362,7 +362,7 @@ if __name__ == "__main__": # pragma: no cover table.add_column("Destination Currency") table.add_column("Exchange Rate") - for ((source, dest), exchange_rate) in exchange_rate_dict.items(): + for (source, dest), exchange_rate in exchange_rate_dict.items(): table.add_row( source, dest, diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live_render.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live_render.py index b90fbf7..e20745d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live_render.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/live_render.py @@ -82,7 +82,6 @@ class LiveRender: def __rich_console__( self, console: Console, options: ConsoleOptions ) -> RenderResult: - renderable = self.renderable style = console.get_style(self.style) lines = console.render_lines(renderable, options, style=style, pad=False) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/logging.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/logging.py index 91368dd..ff8d5d9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/logging.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/logging.py @@ -36,11 +36,13 @@ class RichHandler(Handler): markup (bool, optional): Enable console markup in log messages. Defaults to False. rich_tracebacks (bool, optional): Enable rich tracebacks with syntax highlighting and formatting. Defaults to False. tracebacks_width (Optional[int], optional): Number of characters used to render tracebacks, or None for full width. Defaults to None. + tracebacks_code_width (int, optional): Number of code characters used to render tracebacks, or None for full width. Defaults to 88. tracebacks_extra_lines (int, optional): Additional lines of code to render tracebacks, or None for full width. Defaults to None. tracebacks_theme (str, optional): Override pygments theme used in traceback. tracebacks_word_wrap (bool, optional): Enable word wrapping of long tracebacks lines. Defaults to True. tracebacks_show_locals (bool, optional): Enable display of locals in tracebacks. Defaults to False. tracebacks_suppress (Sequence[Union[str, ModuleType]]): Optional sequence of modules or paths to exclude from traceback. + tracebacks_max_frames (int, optional): Optional maximum number of frames returned by traceback. locals_max_length (int, optional): Maximum length of containers before abbreviating, or None for no abbreviation. Defaults to 10. locals_max_string (int, optional): Maximum length of string before truncating, or None to disable. Defaults to 80. @@ -74,11 +76,13 @@ class RichHandler(Handler): markup: bool = False, rich_tracebacks: bool = False, tracebacks_width: Optional[int] = None, + tracebacks_code_width: int = 88, tracebacks_extra_lines: int = 3, tracebacks_theme: Optional[str] = None, tracebacks_word_wrap: bool = True, tracebacks_show_locals: bool = False, tracebacks_suppress: Iterable[Union[str, ModuleType]] = (), + tracebacks_max_frames: int = 100, locals_max_length: int = 10, locals_max_string: int = 80, log_time_format: Union[str, FormatTimeCallable] = "[%x %X]", @@ -104,6 +108,8 @@ class RichHandler(Handler): self.tracebacks_word_wrap = tracebacks_word_wrap self.tracebacks_show_locals = tracebacks_show_locals self.tracebacks_suppress = tracebacks_suppress + self.tracebacks_max_frames = tracebacks_max_frames + self.tracebacks_code_width = tracebacks_code_width self.locals_max_length = locals_max_length self.locals_max_string = locals_max_string self.keywords = keywords @@ -140,6 +146,7 @@ class RichHandler(Handler): exc_value, exc_traceback, width=self.tracebacks_width, + code_width=self.tracebacks_code_width, extra_lines=self.tracebacks_extra_lines, theme=self.tracebacks_theme, word_wrap=self.tracebacks_word_wrap, @@ -147,6 +154,7 @@ class RichHandler(Handler): locals_max_length=self.locals_max_length, locals_max_string=self.locals_max_string, suppress=self.tracebacks_suppress, + max_frames=self.tracebacks_max_frames, ) message = record.getMessage() if self.formatter: diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/markup.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/markup.py index fd80d8c..f617187 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/markup.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/markup.py @@ -64,6 +64,9 @@ def escape( return f"{backslashes}{backslashes}\\{text}" markup = _escape(escape_backslashes, markup) + if markup.endswith("\\") and not markup.endswith("\\\\"): + return markup + "\\" + return markup @@ -110,7 +113,10 @@ def render( Args: markup (str): A string containing console markup. + style: (Union[str, Style]): The style to use. emoji (bool, optional): Also render emoji code. Defaults to True. + emoji_variant (str, optional): Optional emoji variant, either "text" or "emoji". Defaults to None. + Raises: MarkupError: If there is a syntax error in the markup. @@ -226,7 +232,6 @@ def render( if __name__ == "__main__": # pragma: no cover - MARKUP = [ "[red]Hello World[/red]", "[magenta]Hello [b]World[/b]", diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/padding.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/padding.py index 1b2204f..0161cd1 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/padding.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/padding.py @@ -1,4 +1,4 @@ -from typing import cast, List, Optional, Tuple, TYPE_CHECKING, Union +from typing import TYPE_CHECKING, List, Optional, Tuple, Union if TYPE_CHECKING: from .console import ( @@ -7,11 +7,11 @@ if TYPE_CHECKING: RenderableType, RenderResult, ) + from .jupyter import JupyterMixin from .measure import Measurement -from .style import Style from .segment import Segment - +from .style import Style PaddingDimensions = Union[int, Tuple[int], Tuple[int, int], Tuple[int, int, int, int]] @@ -66,10 +66,10 @@ class Padding(JupyterMixin): _pad = pad[0] return (_pad, _pad, _pad, _pad) if len(pad) == 2: - pad_top, pad_right = cast(Tuple[int, int], pad) + pad_top, pad_right = pad return (pad_top, pad_right, pad_top, pad_right) if len(pad) == 4: - top, right, bottom, left = cast(Tuple[int, int, int, int], pad) + top, right, bottom, left = pad return (top, right, bottom, left) raise ValueError(f"1, 2 or 4 integers required for padding; {len(pad)} given") diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/panel.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/panel.py index d522d80..8cfa6f4 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/panel.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/panel.py @@ -22,11 +22,13 @@ class Panel(JupyterMixin): Args: renderable (RenderableType): A console renderable object. - box (Box, optional): A Box instance that defines the look of the border (see :ref:`appendix_box`. - Defaults to box.ROUNDED. + box (Box, optional): A Box instance that defines the look of the border (see :ref:`appendix_box`. Defaults to box.ROUNDED. + title (Optional[TextType], optional): Optional title displayed in panel header. Defaults to None. + title_align (AlignMethod, optional): Alignment of title. Defaults to "center". + subtitle (Optional[TextType], optional): Optional subtitle displayed in panel footer. Defaults to None. + subtitle_align (AlignMethod, optional): Alignment of subtitle. Defaults to "center". safe_box (bool, optional): Disable box characters that don't display on windows legacy terminal with *raster* fonts. Defaults to True. - expand (bool, optional): If True the panel will stretch to fill the console - width, otherwise it will be sized to fit the contents. Defaults to True. + expand (bool, optional): If True the panel will stretch to fill the console width, otherwise it will be sized to fit the contents. Defaults to True. style (str, optional): The style of the panel (border and contents). Defaults to "none". border_style (str, optional): The style of the border. Defaults to "none". width (Optional[int], optional): Optional width of panel. Defaults to None to auto-detect. @@ -82,7 +84,9 @@ class Panel(JupyterMixin): style: StyleType = "none", border_style: StyleType = "none", width: Optional[int] = None, + height: Optional[int] = None, padding: PaddingDimensions = (0, 1), + highlight: bool = False, ) -> "Panel": """An alternative constructor that sets expand=False.""" return cls( @@ -96,7 +100,9 @@ class Panel(JupyterMixin): style=style, border_style=border_style, width=width, + height=height, padding=padding, + highlight=highlight, expand=False, ) @@ -140,7 +146,8 @@ class Panel(JupyterMixin): Padding(self.renderable, _padding) if any(_padding) else self.renderable ) style = console.get_style(self.style) - border_style = style + console.get_style(self.border_style) + partial_border_style = console.get_style(self.border_style) + border_style = style + partial_border_style width = ( options.max_width if self.width is None @@ -168,6 +175,9 @@ class Panel(JupyterMixin): text = text.copy() text.truncate(width) excess_space = width - cell_len(text.plain) + if text.style: + text.stylize(console.get_style(text.style)) + if excess_space: if align == "left": return Text.assemble( @@ -196,7 +206,7 @@ class Panel(JupyterMixin): title_text = self._title if title_text is not None: - title_text.stylize_before(border_style) + title_text.stylize_before(partial_border_style) child_width = ( width - 2 @@ -245,7 +255,7 @@ class Panel(JupyterMixin): subtitle_text = self._subtitle if subtitle_text is not None: - subtitle_text.stylize_before(border_style) + subtitle_text.stylize_before(partial_border_style) if subtitle_text is None or width <= 4: yield Segment(box.get_bottom([width - 2]), border_style) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/pretty.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/pretty.py index 2bd9eb0..c4a274f 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/pretty.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/pretty.py @@ -3,6 +3,7 @@ import collections import dataclasses import inspect import os +import reprlib import sys from array import array from collections import Counter, UserDict, UserList, defaultdict, deque @@ -15,6 +16,7 @@ from typing import ( Any, Callable, DefaultDict, + Deque, Dict, Iterable, List, @@ -77,7 +79,10 @@ def _is_dataclass_repr(obj: object) -> bool: # Digging in to a lot of internals here # Catching all exceptions in case something is missing on a non CPython implementation try: - return obj.__repr__.__code__.co_filename == dataclasses.__file__ + return obj.__repr__.__code__.co_filename in ( + dataclasses.__file__, + reprlib.__file__, + ) except Exception: # pragma: no coverage return False @@ -130,17 +135,19 @@ def _ipy_display_hook( if _safe_isinstance(value, ConsoleRenderable): console.line() console.print( - value - if _safe_isinstance(value, RichRenderable) - else Pretty( - value, - overflow=overflow, - indent_guides=indent_guides, - max_length=max_length, - max_string=max_string, - max_depth=max_depth, - expand_all=expand_all, - margin=12, + ( + value + if _safe_isinstance(value, RichRenderable) + else Pretty( + value, + overflow=overflow, + indent_guides=indent_guides, + max_length=max_length, + max_string=max_string, + max_depth=max_depth, + expand_all=expand_all, + margin=12, + ) ), crop=crop, new_line_start=True, @@ -196,23 +203,28 @@ def install( assert console is not None builtins._ = None # type: ignore[attr-defined] console.print( - value - if _safe_isinstance(value, RichRenderable) - else Pretty( - value, - overflow=overflow, - indent_guides=indent_guides, - max_length=max_length, - max_string=max_string, - max_depth=max_depth, - expand_all=expand_all, + ( + value + if _safe_isinstance(value, RichRenderable) + else Pretty( + value, + overflow=overflow, + indent_guides=indent_guides, + max_length=max_length, + max_string=max_string, + max_depth=max_depth, + expand_all=expand_all, + ) ), crop=crop, ) builtins._ = value # type: ignore[attr-defined] - if "get_ipython" in globals(): + try: ip = get_ipython() # type: ignore[name-defined] + except NameError: + sys.displayhook = display_hook + else: from IPython.core.formatters import BaseFormatter class RichFormatter(BaseFormatter): # type: ignore[misc] @@ -236,8 +248,6 @@ def install( # replace plain text formatter with rich formatter rich_formatter = RichFormatter() ip.display_formatter.formatters["text/plain"] = rich_formatter - else: - sys.displayhook = display_hook class Pretty(JupyterMixin): @@ -352,6 +362,16 @@ def _get_braces_for_defaultdict(_object: DefaultDict[Any, Any]) -> Tuple[str, st ) +def _get_braces_for_deque(_object: Deque[Any]) -> Tuple[str, str, str]: + if _object.maxlen is None: + return ("deque([", "])", "deque()") + return ( + "deque([", + f"], maxlen={_object.maxlen})", + f"deque(maxlen={_object.maxlen})", + ) + + def _get_braces_for_array(_object: "array[Any]") -> Tuple[str, str, str]: return (f"array({_object.typecode!r}, [", "])", f"array({_object.typecode!r})") @@ -361,7 +381,7 @@ _BRACES: Dict[type, Callable[[Any], Tuple[str, str, str]]] = { array: _get_braces_for_array, defaultdict: _get_braces_for_defaultdict, Counter: lambda _object: ("Counter({", "})", "Counter()"), - deque: lambda _object: ("deque([", "])", "deque()"), + deque: _get_braces_for_deque, dict: lambda _object: ("{", "}", "{}"), UserDict: lambda _object: ("{", "}", "{}"), frozenset: lambda _object: ("frozenset({", "})", "frozenset()"), @@ -708,9 +728,9 @@ def traverse( last=root, ) - def iter_attrs() -> Iterable[ - Tuple[str, Any, Optional[Callable[[Any], str]]] - ]: + def iter_attrs() -> ( + Iterable[Tuple[str, Any, Optional[Callable[[Any], str]]]] + ): """Iterate over attr fields and values.""" for attr in attr_fields: if attr.repr: @@ -761,7 +781,9 @@ def traverse( ) for last, field in loop_last( - field for field in fields(obj) if field.repr + field + for field in fields(obj) + if field.repr and hasattr(obj, field.name) ): child_node = _traverse(getattr(obj, field.name), depth=depth + 1) child_node.key_repr = field.name @@ -845,7 +867,7 @@ def traverse( pop_visited(obj_id) else: node = Node(value_repr=to_repr(obj), last=root) - node.is_tuple = _safe_isinstance(obj, tuple) + node.is_tuple = type(obj) == tuple node.is_namedtuple = _is_namedtuple(obj) return node @@ -985,7 +1007,7 @@ if __name__ == "__main__": # pragma: no cover from pip._vendor.rich import print - # print(Pretty(data, indent_guides=True, max_string=20)) + print(Pretty(data, indent_guides=True, max_string=20)) class Thing: def __repr__(self) -> str: diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress.py index 8b0a315..ec086d9 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress.py @@ -39,6 +39,11 @@ if sys.version_info >= (3, 8): else: from pip._vendor.typing_extensions import Literal # pragma: no cover +if sys.version_info >= (3, 11): + from typing import Self +else: + from pip._vendor.typing_extensions import Self # pragma: no cover + from . import filesize, get_console from .console import Console, Group, JustifyMethod, RenderableType from .highlighter import Highlighter @@ -70,7 +75,7 @@ class _TrackThread(Thread): self.done = Event() self.completed = 0 - super().__init__() + super().__init__(daemon=True) def run(self) -> None: task_id = self.task_id @@ -78,7 +83,7 @@ class _TrackThread(Thread): update_period = self.update_period last_completed = 0 wait = self.done.wait - while not wait(update_period): + while not wait(update_period) and self.progress.live.is_started: completed = self.completed if last_completed != completed: advance(task_id, completed - last_completed) @@ -104,6 +109,7 @@ def track( sequence: Union[Sequence[ProgressType], Iterable[ProgressType]], description: str = "Working...", total: Optional[float] = None, + completed: int = 0, auto_refresh: bool = True, console: Optional[Console] = None, transient: bool = False, @@ -123,6 +129,7 @@ def track( sequence (Iterable[ProgressType]): A sequence (must support "len") you wish to iterate over. description (str, optional): Description of task show next to progress bar. Defaults to "Working". total: (float, optional): Total number of steps. Default is len(sequence). + completed (int, optional): Number of steps completed so far. Defaults to 0. auto_refresh (bool, optional): Automatic refresh, disable to force a refresh after each iteration. Default is True. transient: (bool, optional): Clear the progress on exit. Defaults to False. console (Console, optional): Console to write to. Default creates internal Console instance. @@ -166,7 +173,11 @@ def track( with progress: yield from progress.track( - sequence, total=total, description=description, update_period=update_period + sequence, + total=total, + completed=completed, + description=description, + update_period=update_period, ) @@ -269,6 +280,9 @@ class _Reader(RawIOBase, BinaryIO): def write(self, s: Any) -> int: raise UnsupportedOperation("write") + def writelines(self, lines: Iterable[Any]) -> None: + raise UnsupportedOperation("writelines") + class _ReadContext(ContextManager[_I], Generic[_I]): """A utility class to handle a context for both a reader and a progress.""" @@ -681,7 +695,7 @@ class TimeElapsedColumn(ProgressColumn): elapsed = task.finished_time if task.finished else task.elapsed if elapsed is None: return Text("-:--:--", style="progress.elapsed") - delta = timedelta(seconds=int(elapsed)) + delta = timedelta(seconds=max(0, int(elapsed))) return Text(str(delta), style="progress.elapsed") @@ -710,7 +724,6 @@ class TaskProgressColumn(TextColumn): table_column: Optional[Column] = None, show_speed: bool = False, ) -> None: - self.text_format_no_percentage = text_format_no_percentage self.show_speed = show_speed super().__init__( @@ -1051,7 +1064,7 @@ class Progress(JupyterMixin): """Renders an auto-updating progress bar(s). Args: - console (Console, optional): Optional Console instance. Default will an internal Console instance writing to stdout. + console (Console, optional): Optional Console instance. Defaults to an internal Console instance writing to stdout. auto_refresh (bool, optional): Enable auto refresh. If disabled, you will need to call `refresh()`. refresh_per_second (Optional[float], optional): Number of times per second to refresh the progress information or None to use default (10). Defaults to None. speed_estimate_period: (float, optional): Period (in seconds) used to calculate the speed estimate. Defaults to 30. @@ -1114,7 +1127,7 @@ class Progress(JupyterMixin): progress = Progress( SpinnerColumn(), - *Progress.default_columns(), + *Progress.get_default_columns(), "Elapsed:", TimeElapsedColumn(), ) @@ -1162,10 +1175,10 @@ class Progress(JupyterMixin): def stop(self) -> None: """Stop the progress display.""" self.live.stop() - if not self.console.is_interactive: + if not self.console.is_interactive and not self.console.is_jupyter: self.console.print() - def __enter__(self) -> "Progress": + def __enter__(self) -> Self: self.start() return self @@ -1181,6 +1194,7 @@ class Progress(JupyterMixin): self, sequence: Union[Iterable[ProgressType], Sequence[ProgressType]], total: Optional[float] = None, + completed: int = 0, task_id: Optional[TaskID] = None, description: str = "Working...", update_period: float = 0.1, @@ -1190,6 +1204,7 @@ class Progress(JupyterMixin): Args: sequence (Sequence[ProgressType]): A sequence of values you want to iterate over and track progress. total: (float, optional): Total number of steps. Default is len(sequence). + completed (int, optional): Number of steps completed so far. Defaults to 0. task_id: (TaskID): Task to track. Default is new task. description: (str, optional): Description of task, if new task is created. update_period (float, optional): Minimum time (in seconds) between calls to update(). Defaults to 0.1. @@ -1201,9 +1216,9 @@ class Progress(JupyterMixin): total = float(length_hint(sequence)) or None if task_id is None: - task_id = self.add_task(description, total=total) + task_id = self.add_task(description, total=total, completed=completed) else: - self.update(task_id, total=total) + self.update(task_id, total=total, completed=completed) if self.live.auto_refresh: with _TrackThread(self, task_id, update_period) as track_thread: @@ -1327,7 +1342,7 @@ class Progress(JupyterMixin): # normalize the mode (always rb, rt) _mode = "".join(sorted(mode, reverse=False)) if _mode not in ("br", "rt", "r"): - raise ValueError("invalid mode {!r}".format(mode)) + raise ValueError(f"invalid mode {mode!r}") # patch buffering to provide the same behaviour as the builtin `open` line_buffering = buffering == 1 @@ -1636,7 +1651,6 @@ class Progress(JupyterMixin): if __name__ == "__main__": # pragma: no coverage - import random import time @@ -1689,7 +1703,6 @@ if __name__ == "__main__": # pragma: no coverage console=console, transient=False, ) as progress: - task1 = progress.add_task("[red]Downloading", total=1000) task2 = progress.add_task("[green]Processing", total=1000) task3 = progress.add_task("[yellow]Thinking", total=None) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress_bar.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress_bar.py index 67361df..41794f7 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress_bar.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/progress_bar.py @@ -108,7 +108,7 @@ class ProgressBar(JupyterMixin): for index in range(PULSE_SIZE): position = index / PULSE_SIZE - fade = 0.5 + cos((position * pi * 2)) / 2.0 + fade = 0.5 + cos(position * pi * 2) / 2.0 color = blend_rgb(fore_color, back_color, cross_fade=fade) append(_Segment(bar, _Style(color=from_triplet(color)))) return segments @@ -156,7 +156,6 @@ class ProgressBar(JupyterMixin): def __rich_console__( self, console: Console, options: ConsoleOptions ) -> RenderResult: - width = min(self.width or options.max_width, options.max_width) ascii = options.legacy_windows or options.ascii_only should_pulse = self.pulse or self.total is None diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/prompt.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/prompt.py index 2bd0a77..fccb70d 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/prompt.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/prompt.py @@ -36,6 +36,7 @@ class PromptBase(Generic[PromptType]): console (Console, optional): A Console instance or None to use global console. Defaults to None. password (bool, optional): Enable password input. Defaults to False. choices (List[str], optional): A list of valid choices. Defaults to None. + case_sensitive (bool, optional): Matching of choices should be case-sensitive. Defaults to True. show_default (bool, optional): Show default in prompt. Defaults to True. show_choices (bool, optional): Show choices in prompt. Defaults to True. """ @@ -57,6 +58,7 @@ class PromptBase(Generic[PromptType]): console: Optional[Console] = None, password: bool = False, choices: Optional[List[str]] = None, + case_sensitive: bool = True, show_default: bool = True, show_choices: bool = True, ) -> None: @@ -69,6 +71,7 @@ class PromptBase(Generic[PromptType]): self.password = password if choices is not None: self.choices = choices + self.case_sensitive = case_sensitive self.show_default = show_default self.show_choices = show_choices @@ -81,6 +84,7 @@ class PromptBase(Generic[PromptType]): console: Optional[Console] = None, password: bool = False, choices: Optional[List[str]] = None, + case_sensitive: bool = True, show_default: bool = True, show_choices: bool = True, default: DefaultType, @@ -97,6 +101,7 @@ class PromptBase(Generic[PromptType]): console: Optional[Console] = None, password: bool = False, choices: Optional[List[str]] = None, + case_sensitive: bool = True, show_default: bool = True, show_choices: bool = True, stream: Optional[TextIO] = None, @@ -111,6 +116,7 @@ class PromptBase(Generic[PromptType]): console: Optional[Console] = None, password: bool = False, choices: Optional[List[str]] = None, + case_sensitive: bool = True, show_default: bool = True, show_choices: bool = True, default: Any = ..., @@ -126,6 +132,7 @@ class PromptBase(Generic[PromptType]): console (Console, optional): A Console instance or None to use global console. Defaults to None. password (bool, optional): Enable password input. Defaults to False. choices (List[str], optional): A list of valid choices. Defaults to None. + case_sensitive (bool, optional): Matching of choices should be case-sensitive. Defaults to True. show_default (bool, optional): Show default in prompt. Defaults to True. show_choices (bool, optional): Show choices in prompt. Defaults to True. stream (TextIO, optional): Optional text file open for reading to get input. Defaults to None. @@ -135,6 +142,7 @@ class PromptBase(Generic[PromptType]): console=console, password=password, choices=choices, + case_sensitive=case_sensitive, show_default=show_default, show_choices=show_choices, ) @@ -212,7 +220,9 @@ class PromptBase(Generic[PromptType]): bool: True if choice was valid, otherwise False. """ assert self.choices is not None - return value.strip() in self.choices + if self.case_sensitive: + return value.strip() in self.choices + return value.strip().lower() in [choice.lower() for choice in self.choices] def process_response(self, value: str) -> PromptType: """Process response from user, convert to prompt type. @@ -232,9 +242,17 @@ class PromptBase(Generic[PromptType]): except ValueError: raise InvalidResponse(self.validate_error_message) - if self.choices is not None and not self.check_choice(value): - raise InvalidResponse(self.illegal_choice_message) + if self.choices is not None: + if not self.check_choice(value): + raise InvalidResponse(self.illegal_choice_message) + if not self.case_sensitive: + # return the original choice, not the lower case version + return_value = self.response_type( + self.choices[ + [choice.lower() for choice in self.choices].index(value.lower()) + ] + ) return return_value def on_validate_error(self, value: str, error: InvalidResponse) -> None: @@ -307,7 +325,7 @@ class IntPrompt(PromptBase[int]): validate_error_message = "[prompt.invalid]Please enter a valid integer number" -class FloatPrompt(PromptBase[int]): +class FloatPrompt(PromptBase[float]): """A prompt that returns a float. Example: @@ -346,7 +364,6 @@ class Confirm(PromptBase[bool]): if __name__ == "__main__": # pragma: no cover - from pip._vendor.rich import print if Confirm.ask("Run [i]prompt[/i] tests?", default=True): @@ -372,5 +389,12 @@ if __name__ == "__main__": # pragma: no cover fruit = Prompt.ask("Enter a fruit", choices=["apple", "orange", "pear"]) print(f"fruit={fruit!r}") + doggie = Prompt.ask( + "What's the best Dog? (Case INSENSITIVE)", + choices=["Border Terrier", "Collie", "Labradoodle"], + case_sensitive=False, + ) + print(f"doggie={doggie!r}") + else: print("[b]OK :loudly_crying_face:") diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/rich/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/repr.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/repr.py index f284bca..10efc42 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/repr.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/repr.py @@ -76,7 +76,7 @@ def auto( param.POSITIONAL_OR_KEYWORD, param.KEYWORD_ONLY, ): - if param.default == param.empty: + if param.default is param.empty: yield getattr(self, param.name) else: yield param.name, getattr(self, param.name), param.default diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/segment.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/segment.py index e125798..4b5f997 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/segment.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/segment.py @@ -109,42 +109,51 @@ class Segment(NamedTuple): @classmethod @lru_cache(1024 * 16) def _split_cells(cls, segment: "Segment", cut: int) -> Tuple["Segment", "Segment"]: + """Split a segment in to two at a given cell position. + Note that splitting a double-width character, may result in that character turning + into two spaces. + + Args: + segment (Segment): A segment to split. + cut (int): A cell position to cut on. + + Returns: + A tuple of two segments. + """ text, style, control = segment _Segment = Segment - cell_length = segment.cell_length if cut >= cell_length: return segment, _Segment("", style, control) cell_size = get_character_cell_size - pos = int((cut / cell_length) * (len(text) - 1)) + pos = int((cut / cell_length) * len(text)) - before = text[:pos] - cell_pos = cell_len(before) - if cell_pos == cut: - return ( - _Segment(before, style, control), - _Segment(text[pos:], style, control), - ) - while pos < len(text): - char = text[pos] - pos += 1 - cell_pos += cell_size(char) + while True: before = text[:pos] - if cell_pos == cut: + cell_pos = cell_len(before) + out_by = cell_pos - cut + if not out_by: return ( _Segment(before, style, control), _Segment(text[pos:], style, control), ) - if cell_pos > cut: + if out_by == -1 and cell_size(text[pos]) == 2: return ( - _Segment(before[: pos - 1] + " ", style, control), + _Segment(text[:pos] + " ", style, control), + _Segment(" " + text[pos + 1 :], style, control), + ) + if out_by == +1 and cell_size(text[pos - 1]) == 2: + return ( + _Segment(text[: pos - 1] + " ", style, control), _Segment(" " + text[pos:], style, control), ) - - raise AssertionError("Will never reach here") + if cell_pos < cut: + pos += 1 + else: + pos -= 1 def split_cells(self, cut: int) -> Tuple["Segment", "Segment"]: """Split segment in to two segments at the specified column. @@ -152,10 +161,14 @@ class Segment(NamedTuple): If the cut point falls in the middle of a 2-cell wide character then it is replaced by two spaces, to preserve the display width of the parent segment. + Args: + cut (int): Offset within the segment to cut. + Returns: Tuple[Segment, Segment]: Two segments. """ text, style, control = self + assert cut >= 0 if _is_single_cell_widths(text): # Fast path with all 1 cell characters @@ -605,7 +618,7 @@ class Segment(NamedTuple): while True: cut = next(iter_cuts, -1) if cut == -1: - return [] + return if cut != 0: break yield [] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/spinner.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/spinner.py index 91ea630..70570b6 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/spinner.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/spinner.py @@ -38,6 +38,7 @@ class Spinner: self.text: "Union[RenderableType, Text]" = ( Text.from_markup(text) if isinstance(text, str) else text ) + self.name = name self.frames = cast(List[str], spinner["frames"])[:] self.interval = cast(float, spinner["interval"]) self.start_time: Optional[float] = None diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/status.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/status.py index 09eff40..6574483 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/status.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/status.py @@ -107,7 +107,6 @@ class Status(JupyterMixin): if __name__ == "__main__": # pragma: no cover - from time import sleep from .console import Console diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/style.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/style.py index 313c889..262fd6e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/style.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/style.py @@ -663,7 +663,7 @@ class Style: style._set_attributes = self._set_attributes style._link = None style._link_id = "" - style._hash = self._hash + style._hash = None style._null = False style._meta = None return style diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/syntax.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/syntax.py index 5703376..f3d483c 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/syntax.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/syntax.py @@ -1,5 +1,4 @@ import os.path -import platform import re import sys import textwrap @@ -52,7 +51,7 @@ from .text import Text TokenType = Tuple[str, ...] -WINDOWS = platform.system() == "Windows" +WINDOWS = sys.platform == "win32" DEFAULT_THEME = "monokai" # The following styles are based on https://github.com/pygments/pygments/blob/master/pygments/formatters/terminal.py @@ -222,6 +221,7 @@ class _SyntaxHighlightRange(NamedTuple): style: StyleType start: SyntaxPosition end: SyntaxPosition + style_before: bool = False class Syntax(JupyterMixin): @@ -439,6 +439,16 @@ class Syntax(JupyterMixin): except ClassNotFound: return None + @property + def default_lexer(self) -> Lexer: + """A Pygments Lexer to use if one is not specified or invalid.""" + return get_lexer_by_name( + "text", + stripnl=False, + ensurenl=True, + tabsize=self.tab_size, + ) + def highlight( self, code: str, @@ -467,7 +477,7 @@ class Syntax(JupyterMixin): ) _get_theme_style = self._theme.get_style_for_token - lexer = self.lexer + lexer = self.lexer or self.default_lexer if lexer is None: text.append(code) @@ -525,7 +535,11 @@ class Syntax(JupyterMixin): return text def stylize_range( - self, style: StyleType, start: SyntaxPosition, end: SyntaxPosition + self, + style: StyleType, + start: SyntaxPosition, + end: SyntaxPosition, + style_before: bool = False, ) -> None: """ Adds a custom style on a part of the code, that will be applied to the syntax display when it's rendered. @@ -535,8 +549,11 @@ class Syntax(JupyterMixin): style (StyleType): The style to apply. start (Tuple[int, int]): The start of the range, in the form `[line number, column index]`. end (Tuple[int, int]): The end of the range, in the form `[line number, column index]`. + style_before (bool): Apply the style before any existing styles. """ - self._stylized_ranges.append(_SyntaxHighlightRange(style, start, end)) + self._stylized_ranges.append( + _SyntaxHighlightRange(style, start, end, style_before) + ) def _get_line_numbers_color(self, blend: float = 0.3) -> Color: background_style = self._theme.get_background_style() + self.background_style @@ -610,9 +627,7 @@ class Syntax(JupyterMixin): ) -> RenderResult: segments = Segments(self._get_syntax(console, options)) if self.padding: - yield Padding( - segments, style=self._theme.get_background_style(), pad=self.padding - ) + yield Padding(segments, style=self._get_base_style(), pad=self.padding) else: yield segments @@ -778,7 +793,10 @@ class Syntax(JupyterMixin): newlines_offsets, stylized_range.end ) if start is not None and end is not None: - text.stylize(stylized_range.style, start, end) + if stylized_range.style_before: + text.stylize_before(stylized_range.style, start, end) + else: + text.stylize(stylized_range.style, start, end) def _process_code(self, code: str) -> Tuple[bool, str]: """ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/table.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/table.py index 17409f2..654c855 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/table.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/table.py @@ -54,7 +54,7 @@ class Column: show_footer (bool, optional): Show a footer row. Defaults to False. show_edge (bool, optional): Draw a box around the outside of the table. Defaults to True. show_lines (bool, optional): Draw lines between every row. Defaults to False. - leading (bool, optional): Number of blank lines between rows (precludes ``show_lines``). Defaults to 0. + leading (int, optional): Number of blank lines between rows (precludes ``show_lines``). Defaults to 0. style (Union[str, Style], optional): Default style for the table. Defaults to "none". row_styles (List[Union, str], optional): Optional list of row styles, if more than one style is given then the styles will alternate. Defaults to None. header_style (Union[str, Style], optional): Style of the header. Defaults to "table.header". @@ -106,6 +106,9 @@ class Column: no_wrap: bool = False """bool: Prevent wrapping of text within the column. Defaults to ``False``.""" + highlight: bool = False + """bool: Apply highlighter to column. Defaults to ``False``.""" + _index: int = 0 """Index of column.""" @@ -167,7 +170,7 @@ class Table(JupyterMixin): show_footer (bool, optional): Show a footer row. Defaults to False. show_edge (bool, optional): Draw a box around the outside of the table. Defaults to True. show_lines (bool, optional): Draw lines between every row. Defaults to False. - leading (bool, optional): Number of blank lines between rows (precludes ``show_lines``). Defaults to 0. + leading (int, optional): Number of blank lines between rows (precludes ``show_lines``). Defaults to 0. style (Union[str, Style], optional): Default style for the table. Defaults to "none". row_styles (List[Union, str], optional): Optional list of row styles, if more than one style is given then the styles will alternate. Defaults to None. header_style (Union[str, Style], optional): Style of the header. Defaults to "table.header". @@ -212,7 +215,6 @@ class Table(JupyterMixin): caption_justify: "JustifyMethod" = "center", highlight: bool = False, ) -> None: - self.columns: List[Column] = [] self.rows: List[Row] = [] self.title = title @@ -366,6 +368,7 @@ class Table(JupyterMixin): footer: "RenderableType" = "", *, header_style: Optional[StyleType] = None, + highlight: Optional[bool] = None, footer_style: Optional[StyleType] = None, style: Optional[StyleType] = None, justify: "JustifyMethod" = "left", @@ -385,6 +388,7 @@ class Table(JupyterMixin): footer (RenderableType, optional): Text or renderable for the footer. Defaults to "". header_style (Union[str, Style], optional): Style for the header, or None for default. Defaults to None. + highlight (bool, optional): Whether to highlight the text. The default of None uses the value of the table (self) object. footer_style (Union[str, Style], optional): Style for the footer, or None for default. Defaults to None. style (Union[str, Style], optional): Style for the column cells, or None for default. Defaults to None. justify (JustifyMethod, optional): Alignment for cells. Defaults to "left". @@ -402,6 +406,7 @@ class Table(JupyterMixin): header=header, footer=footer, header_style=header_style or "", + highlight=highlight if highlight is not None else self.highlight, footer_style=footer_style or "", style=style or "", justify=justify, @@ -446,7 +451,7 @@ class Table(JupyterMixin): ] for index, renderable in enumerate(cell_renderables): if index == len(columns): - column = Column(_index=index) + column = Column(_index=index, highlight=self.highlight) for _ in self.rows: add_cell(column, Text("")) self.columns.append(column) @@ -471,7 +476,6 @@ class Table(JupyterMixin): def __rich_console__( self, console: "Console", options: "ConsoleOptions" ) -> "RenderResult": - if not self.columns: yield Segment("\n") return @@ -685,7 +689,7 @@ class Table(JupyterMixin): getattr(renderable, "vertical", None) or column.vertical, ) else: - for (style, renderable) in raw_cells: + for style, renderable in raw_cells: yield _Cell( style, renderable, @@ -777,16 +781,16 @@ class Table(JupyterMixin): _Segment(_box.head_right, border_style), _Segment(_box.head_vertical, border_style), ), - ( - _Segment(_box.foot_left, border_style), - _Segment(_box.foot_right, border_style), - _Segment(_box.foot_vertical, border_style), - ), ( _Segment(_box.mid_left, border_style), _Segment(_box.mid_right, border_style), _Segment(_box.mid_vertical, border_style), ), + ( + _Segment(_box.foot_left, border_style), + _Segment(_box.foot_right, border_style), + _Segment(_box.foot_vertical, border_style), + ), ] if show_edge: yield _Segment(_box.get_top(widths), border_style) @@ -820,6 +824,7 @@ class Table(JupyterMixin): no_wrap=column.no_wrap, overflow=column.overflow, height=None, + highlight=column.highlight, ) lines = console.render_lines( cell.renderable, diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/text.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/text.py index 998cb87..5a0c6b1 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/text.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/text.py @@ -11,6 +11,7 @@ from typing import ( List, NamedTuple, Optional, + Pattern, Tuple, Union, ) @@ -38,6 +39,7 @@ DEFAULT_OVERFLOW: "OverflowMethod" = "fold" _re_whitespace = re.compile(r"\s+$") TextType = Union[str, "Text"] +"""A plain string or a :class:`Text` instance.""" GetStyleCallable = Callable[[str], Optional[StyleType]] @@ -97,6 +99,21 @@ class Span(NamedTuple): return self return Span(start, min(offset, end), style) + def extend(self, cells: int) -> "Span": + """Extend the span by the given number of cells. + + Args: + cells (int): Additional space to add to end of span. + + Returns: + Span: A span. + """ + if cells: + start, end, style = self + return Span(start, end + cells, style) + else: + return self + class Text(JupyterMixin): """Text with color / style. @@ -108,7 +125,7 @@ class Text(JupyterMixin): overflow (str, optional): Overflow method: "crop", "fold", "ellipsis". Defaults to None. no_wrap (bool, optional): Disable text wrapping, or None for default. Defaults to None. end (str, optional): Character to end text with. Defaults to "\\\\n". - tab_size (int): Number of spaces per tab, or ``None`` to use ``console.tab_size``. Defaults to 8. + tab_size (int): Number of spaces per tab, or ``None`` to use ``console.tab_size``. Defaults to None. spans (List[Span], optional). A list of predefined style spans. Defaults to None. """ @@ -133,7 +150,7 @@ class Text(JupyterMixin): overflow: Optional["OverflowMethod"] = None, no_wrap: Optional[bool] = None, end: str = "\n", - tab_size: Optional[int] = 8, + tab_size: Optional[int] = None, spans: Optional[List[Span]] = None, ) -> None: sanitized_text = strip_control_codes(text) @@ -157,7 +174,7 @@ class Text(JupyterMixin): return self.plain def __repr__(self) -> str: - return f"" + return f"" def __add__(self, other: Any) -> "Text": if isinstance(other, (str, Text)): @@ -255,7 +272,9 @@ class Text(JupyterMixin): Args: text (str): A string containing console markup. + style (Union[str, Style], optional): Base style for text. Defaults to "". emoji (bool, optional): Also render emoji code. Defaults to True. + emoji_variant (str, optional): Optional emoji variant, either "text" or "emoji". Defaults to None. justify (str, optional): Justify method: "left", "center", "full", "right". Defaults to None. overflow (str, optional): Overflow method: "crop", "fold", "ellipsis". Defaults to None. end (str, optional): Character to end text with. Defaults to "\\\\n". @@ -292,7 +311,7 @@ class Text(JupyterMixin): overflow (str, optional): Overflow method: "crop", "fold", "ellipsis". Defaults to None. no_wrap (bool, optional): Disable text wrapping, or None for default. Defaults to None. end (str, optional): Character to end text with. Defaults to "\\\\n". - tab_size (int): Number of spaces per tab, or ``None`` to use ``console.tab_size``. Defaults to 8. + tab_size (int): Number of spaces per tab, or ``None`` to use ``console.tab_size``. Defaults to None. """ from .ansi import AnsiDecoder @@ -353,8 +372,9 @@ class Text(JupyterMixin): style (Union[str, Style], optional): Base style for text. Defaults to "". justify (str, optional): Justify method: "left", "center", "full", "right". Defaults to None. overflow (str, optional): Overflow method: "crop", "fold", "ellipsis". Defaults to None. + no_wrap (bool, optional): Disable text wrapping, or None for default. Defaults to None. end (str, optional): Character to end text with. Defaults to "\\\\n". - tab_size (int): Number of spaces per tab, or ``None`` to use ``console.tab_size``. Defaults to 8. + tab_size (int): Number of spaces per tab, or ``None`` to use ``console.tab_size``. Defaults to None. meta (Dict[str, Any], optional). Meta data to apply to text, or None for no meta data. Default to None Returns: @@ -408,7 +428,7 @@ class Text(JupyterMixin): self._spans = spans[:] def blank_copy(self, plain: str = "") -> "Text": - """Return a new Text instance with copied meta data (but not the string or spans).""" + """Return a new Text instance with copied metadata (but not the string or spans).""" copy_self = Text( plain, style=self.style, @@ -489,7 +509,7 @@ class Text(JupyterMixin): def apply_meta( self, meta: Dict[str, Any], start: int = 0, end: Optional[int] = None ) -> None: - """Apply meta data to the text, or a portion of the text. + """Apply metadata to the text, or a portion of the text. Args: meta (Dict[str, Any]): A dict of meta information. @@ -549,9 +569,30 @@ class Text(JupyterMixin): style += get_style(span_style, default="") return style + def extend_style(self, spaces: int) -> None: + """Extend the Text given number of spaces where the spaces have the same style as the last character. + + Args: + spaces (int): Number of spaces to add to the Text. + """ + if spaces <= 0: + return + spans = self.spans + new_spaces = " " * spaces + if spans: + end_offset = len(self) + self._spans[:] = [ + span.extend(spaces) if span.end >= end_offset else span + for span in spans + ] + self._text.append(new_spaces) + self._length += spaces + else: + self.plain += new_spaces + def highlight_regex( self, - re_highlight: str, + re_highlight: Union[Pattern[str], str], style: Optional[Union[GetStyleCallable, StyleType]] = None, *, style_prefix: str = "", @@ -560,7 +601,7 @@ class Text(JupyterMixin): translated to styles. Args: - re_highlight (str): A regular expression. + re_highlight (Union[re.Pattern, str]): A regular expression object or string. style (Union[GetStyleCallable, StyleType]): Optional style to apply to whole match, or a callable which accepts the matched text and returns a style. Defaults to None. style_prefix (str, optional): Optional prefix to add to style group names. @@ -572,7 +613,9 @@ class Text(JupyterMixin): append_span = self._spans.append _Span = Span plain = self.plain - for match in re.finditer(re_highlight, plain): + if isinstance(re_highlight, str): + re_highlight = re.compile(re_highlight) + for match in re_highlight.finditer(plain): get_span = match.span if style: start, end = get_span() @@ -597,9 +640,9 @@ class Text(JupyterMixin): """Highlight words with a style. Args: - words (Iterable[str]): Worlds to highlight. + words (Iterable[str]): Words to highlight. style (Union[str, Style]): Style to apply. - case_sensitive (bool, optional): Enable case sensitive matchings. Defaults to True. + case_sensitive (bool, optional): Enable case sensitive matching. Defaults to True. Returns: int: Number of words highlighted. @@ -646,7 +689,7 @@ class Text(JupyterMixin): def __rich_console__( self, console: "Console", options: "ConsoleOptions" ) -> Iterable[Segment]: - tab_size: int = console.tab_size or self.tab_size or 8 + tab_size: int = console.tab_size if self.tab_size is None else self.tab_size justify = self.justify or options.justify or DEFAULT_JUSTIFY overflow = self.overflow or options.overflow or DEFAULT_OVERFLOW @@ -781,27 +824,35 @@ class Text(JupyterMixin): """ if "\t" not in self.plain: return - pos = 0 if tab_size is None: tab_size = self.tab_size - assert tab_size is not None - result = self.blank_copy() - append = result.append + if tab_size is None: + tab_size = 8 + + new_text: List[Text] = [] + append = new_text.append - _style = self.style for line in self.split("\n", include_separator=True): - parts = line.split("\t", include_separator=True) - for part in parts: - if part.plain.endswith("\t"): - part._text = [part.plain[:-1] + " "] - append(part) - pos += len(part) - spaces = tab_size - ((pos - 1) % tab_size) - 1 - if spaces: - append(" " * spaces, _style) - pos += spaces - else: + if "\t" not in line.plain: + append(line) + else: + cell_position = 0 + parts = line.split("\t", include_separator=True) + for part in parts: + if part.plain.endswith("\t"): + part._text[-1] = part._text[-1][:-1] + " " + cell_position += part.cell_len + tab_remainder = cell_position % tab_size + if tab_remainder: + spaces = tab_size - tab_remainder + part.extend_style(spaces) + cell_position += spaces + else: + cell_position += part.cell_len append(part) + + result = Text("").join(new_text) + self._text = [result.plain] self._length = len(self.plain) self._spans[:] = result._spans @@ -852,6 +903,7 @@ class Text(JupyterMixin): Args: count (int): Width of padding. + character (str): The character to pad with. Must be a string of length 1. """ assert len(character) == 1, "Character must be a string of length 1" if count: @@ -932,7 +984,7 @@ class Text(JupyterMixin): self._text.append(sanitized_text) offset = len(self) text_length = len(sanitized_text) - if style is not None: + if style: self._spans.append(Span(offset, offset + text_length, style)) self._length += text_length elif isinstance(text, Text): @@ -942,14 +994,14 @@ class Text(JupyterMixin): "style must not be set when appending Text instance" ) text_length = self._length - if text.style is not None: + if text.style: self._spans.append( _Span(text_length, text_length + len(text), text.style) ) self._text.append(text.plain) self._spans.extend( _Span(start + text_length, end + text_length, style) - for start, end, style in text._spans + for start, end, style in text._spans.copy() ) self._length += len(text) return self @@ -958,17 +1010,20 @@ class Text(JupyterMixin): """Append another Text instance. This method is more performant that Text.append, but only works for Text. + Args: + text (Text): The Text instance to append to this instance. + Returns: Text: Returns self for chaining. """ _Span = Span text_length = self._length - if text.style is not None: + if text.style: self._spans.append(_Span(text_length, text_length + len(text), text.style)) self._text.append(text.plain) self._spans.extend( _Span(start + text_length, end + text_length, style) - for start, end, style in text._spans + for start, end, style in text._spans.copy() ) self._length += len(text) return self @@ -979,7 +1034,7 @@ class Text(JupyterMixin): """Append iterable of str and style. Style may be a Style instance or a str style definition. Args: - pairs (Iterable[Tuple[str, Optional[StyleType]]]): An iterable of tuples containing str content and style. + tokens (Iterable[Tuple[str, Optional[StyleType]]]): An iterable of tuples containing str content and style. Returns: Text: Returns self for chaining. @@ -989,8 +1044,9 @@ class Text(JupyterMixin): _Span = Span offset = len(self) for content, style in tokens: + content = strip_control_codes(content) append_text(content) - if style is not None: + if style: append_span(_Span(offset, offset + len(content), style)) offset += len(content) self._length = offset @@ -1088,7 +1144,6 @@ class Text(JupyterMixin): _Span = Span for span_start, span_end, style in self._spans: - lower_bound = 0 upper_bound = line_count start_line_no = (lower_bound + upper_bound) // 2 @@ -1158,8 +1213,7 @@ class Text(JupyterMixin): Args: console (Console): Console instance. - width (int): Number of characters per line. - emoji (bool, optional): Also render emoji code. Defaults to True. + width (int): Number of cells available per line. justify (str, optional): Justify method: "default", "left", "center", "full", "right". Defaults to "default". overflow (str, optional): Overflow method: "crop", "fold", or "ellipsis". Defaults to None. tab_size (int, optional): Default tab size. Defaults to 8. diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/theme.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/theme.py index 471dfb2..227f1d8 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/theme.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/theme.py @@ -1,5 +1,5 @@ import configparser -from typing import Dict, List, IO, Mapping, Optional +from typing import IO, Dict, List, Mapping, Optional from .default_styles import DEFAULT_STYLES from .style import Style, StyleType @@ -69,7 +69,7 @@ class Theme: Returns: Theme: A new theme instance. """ - with open(path, "rt", encoding=encoding) as config_file: + with open(path, encoding=encoding) as config_file: return cls.from_file(config_file, source=path, inherit=inherit) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/traceback.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/traceback.py index c4ffe1f..28d742b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/traceback.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/traceback.py @@ -1,10 +1,9 @@ -from __future__ import absolute_import - +import inspect import linecache import os -import platform import sys from dataclasses import dataclass, field +from itertools import islice from traceback import walk_tb from types import ModuleType, TracebackType from typing import ( @@ -39,7 +38,7 @@ from .syntax import Syntax from .text import Text from .theme import Theme -WINDOWS = platform.system() == "Windows" +WINDOWS = sys.platform == "win32" LOCALS_MAX_LENGTH = 10 LOCALS_MAX_STRING = 80 @@ -49,6 +48,7 @@ def install( *, console: Optional[Console] = None, width: Optional[int] = 100, + code_width: Optional[int] = 88, extra_lines: int = 3, theme: Optional[str] = None, word_wrap: bool = False, @@ -69,6 +69,7 @@ def install( Args: console (Optional[Console], optional): Console to write exception to. Default uses internal Console instance. width (Optional[int], optional): Width (in characters) of traceback. Defaults to 100. + code_width (Optional[int], optional): Code width (in characters) of traceback. Defaults to 88. extra_lines (int, optional): Extra lines of code. Defaults to 3. theme (Optional[str], optional): Pygments theme to use in traceback. Defaults to ``None`` which will pick a theme appropriate for the platform. @@ -105,6 +106,7 @@ def install( value, traceback, width=width, + code_width=code_width, extra_lines=extra_lines, theme=theme, word_wrap=word_wrap, @@ -179,6 +181,7 @@ class Frame: name: str line: str = "" locals: Optional[Dict[str, pretty.Node]] = None + last_instruction: Optional[Tuple[Tuple[int, int], Tuple[int, int]]] = None @dataclass @@ -215,6 +218,7 @@ class Traceback: trace (Trace, optional): A `Trace` object produced from `extract`. Defaults to None, which uses the last exception. width (Optional[int], optional): Number of characters used to traceback. Defaults to 100. + code_width (Optional[int], optional): Number of code characters used to traceback. Defaults to 88. extra_lines (int, optional): Additional lines of code to render. Defaults to 3. theme (str, optional): Override pygments theme used in traceback. word_wrap (bool, optional): Enable word wrapping of long lines. Defaults to False. @@ -243,6 +247,7 @@ class Traceback: trace: Optional[Trace] = None, *, width: Optional[int] = 100, + code_width: Optional[int] = 88, extra_lines: int = 3, theme: Optional[str] = None, word_wrap: bool = False, @@ -266,6 +271,7 @@ class Traceback: ) self.trace = trace self.width = width + self.code_width = code_width self.extra_lines = extra_lines self.theme = Syntax.get_theme(theme or "ansi_dark") self.word_wrap = word_wrap @@ -297,6 +303,7 @@ class Traceback: traceback: Optional[TracebackType], *, width: Optional[int] = 100, + code_width: Optional[int] = 88, extra_lines: int = 3, theme: Optional[str] = None, word_wrap: bool = False, @@ -316,6 +323,7 @@ class Traceback: exc_value (BaseException): Exception value. traceback (TracebackType): Python Traceback object. width (Optional[int], optional): Number of characters used to traceback. Defaults to 100. + code_width (Optional[int], optional): Number of code characters used to traceback. Defaults to 88. extra_lines (int, optional): Additional lines of code to render. Defaults to 3. theme (str, optional): Override pygments theme used in traceback. word_wrap (bool, optional): Enable word wrapping of long lines. Defaults to False. @@ -346,6 +354,7 @@ class Traceback: return cls( rich_traceback, width=width, + code_width=code_width, extra_lines=extra_lines, theme=theme, word_wrap=word_wrap, @@ -436,6 +445,35 @@ class Traceback: for frame_summary, line_no in walk_tb(traceback): filename = frame_summary.f_code.co_filename + + last_instruction: Optional[Tuple[Tuple[int, int], Tuple[int, int]]] + last_instruction = None + if sys.version_info >= (3, 11): + instruction_index = frame_summary.f_lasti // 2 + instruction_position = next( + islice( + frame_summary.f_code.co_positions(), + instruction_index, + instruction_index + 1, + ) + ) + ( + start_line, + end_line, + start_column, + end_column, + ) = instruction_position + if ( + start_line is not None + and end_line is not None + and start_column is not None + and end_column is not None + ): + last_instruction = ( + (start_line, start_column), + (end_line, end_column), + ) + if filename and not filename.startswith("<"): if not os.path.isabs(filename): filename = os.path.join(_IMPORT_CWD, filename) @@ -446,16 +484,20 @@ class Traceback: filename=filename or "?", lineno=line_no, name=frame_summary.f_code.co_name, - locals={ - key: pretty.traverse( - value, - max_length=locals_max_length, - max_string=locals_max_string, - ) - for key, value in get_locals(frame_summary.f_locals.items()) - } - if show_locals - else None, + locals=( + { + key: pretty.traverse( + value, + max_length=locals_max_length, + max_string=locals_max_string, + ) + for key, value in get_locals(frame_summary.f_locals.items()) + if not (inspect.isfunction(value) or inspect.isclass(value)) + } + if show_locals + else None + ), + last_instruction=last_instruction, ) append(frame) if frame_summary.f_locals.get("_rich_traceback_guard", False): @@ -636,7 +678,6 @@ class Traceback: excluded = False for frame_index, frame in enumerate(stack.frames): - if exclude_frames and frame_index in exclude_frames: excluded = True continue @@ -696,7 +737,7 @@ class Traceback: ), highlight_lines={frame.lineno}, word_wrap=self.word_wrap, - code_width=88, + code_width=self.code_width, indent_guides=self.indent_guides, dedent=False, ) @@ -706,6 +747,14 @@ class Traceback: (f"\n{error}", "traceback.error"), ) else: + if frame.last_instruction is not None: + start, end = frame.last_instruction + syntax.stylize_range( + style="traceback.error_range", + start=start, + end=end, + style_before=True, + ) yield ( Columns( [ @@ -720,13 +769,12 @@ class Traceback: if __name__ == "__main__": # pragma: no cover - - from .console import Console - - console = Console() + install(show_locals=True) import sys - def bar(a: Any) -> None: # 这是对亚洲语言支持的测试。面对模棱两可的想法，拒绝猜测的诱惑 + def bar( + a: Any, + ) -> None: # 这是对亚洲语言支持的测试。面对模棱两可的想法，拒绝猜测的诱惑 one = 1 print(one / a) @@ -744,13 +792,6 @@ if __name__ == "__main__": # pragma: no cover bar(a) def error() -> None: - - try: - try: - foo(0) - except: - slfkjsldkfj # type: ignore[name-defined] - except: - console.print_exception(show_locals=True) + foo(0) error() diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/tree.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/tree.py index afe8da1..27c5cf7 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/tree.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/rich/tree.py @@ -8,18 +8,32 @@ from .segment import Segment from .style import Style, StyleStack, StyleType from .styled import Styled +GuideType = Tuple[str, str, str, str] + class Tree(JupyterMixin): """A renderable for a tree structure. + Attributes: + ASCII_GUIDES (GuideType): Guide lines used when Console.ascii_only is True. + TREE_GUIDES (List[GuideType, GuideType, GuideType]): Default guide lines. + Args: label (RenderableType): The renderable or str for the tree label. style (StyleType, optional): Style of this tree. Defaults to "tree". guide_style (StyleType, optional): Style of the guide lines. Defaults to "tree.line". expanded (bool, optional): Also display children. Defaults to True. highlight (bool, optional): Highlight renderable (if str). Defaults to False. + hide_root (bool, optional): Hide the root node. Defaults to False. """ + ASCII_GUIDES = (" ", "| ", "+-- ", "`-- ") + TREE_GUIDES = [ + (" ", "│ ", "├── ", "└── "), + (" ", "┃ ", "┣━━ ", "┗━━ "), + (" ", "║ ", "╠══ ", "╚══ "), + ] + def __init__( self, label: RenderableType, @@ -72,7 +86,6 @@ class Tree(JupyterMixin): def __rich_console__( self, console: "Console", options: "ConsoleOptions" ) -> "RenderResult": - stack: List[Iterator[Tuple[bool, Tree]]] = [] pop = stack.pop push = stack.append @@ -83,21 +96,15 @@ class Tree(JupyterMixin): guide_style = get_style(self.guide_style, default="") or null_style SPACE, CONTINUE, FORK, END = range(4) - ASCII_GUIDES = (" ", "| ", "+-- ", "`-- ") - TREE_GUIDES = [ - (" ", "│ ", "├── ", "└── "), - (" ", "┃ ", "┣━━ ", "┗━━ "), - (" ", "║ ", "╠══ ", "╚══ "), - ] _Segment = Segment def make_guide(index: int, style: Style) -> Segment: """Make a Segment for a level of the guide lines.""" if options.ascii_only: - line = ASCII_GUIDES[index] + line = self.ASCII_GUIDES[index] else: guide = 1 if style.bold else (2 if style.underline2 else 0) - line = TREE_GUIDES[0 if options.legacy_windows else guide][index] + line = self.TREE_GUIDES[0 if options.legacy_windows else guide][index] return _Segment(line, style) levels: List[Segment] = [make_guide(CONTINUE, guide_style)] @@ -195,7 +202,6 @@ class Tree(JupyterMixin): if __name__ == "__main__": # pragma: no cover - from pip._vendor.rich.console import Group from pip._vendor.rich.markdown import Markdown from pip._vendor.rich.panel import Panel diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/six.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/six.py deleted file mode 100644 index 4e15675..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/six.py +++ /dev/null @@ -1,998 +0,0 @@ -# Copyright (c) 2010-2020 Benjamin Peterson -# -# Permission is hereby granted, free of charge, to any person obtaining a copy -# of this software and associated documentation files (the "Software"), to deal -# in the Software without restriction, including without limitation the rights -# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell -# copies of the Software, and to permit persons to whom the Software is -# furnished to do so, subject to the following conditions: -# -# The above copyright notice and this permission notice shall be included in all -# copies or substantial portions of the Software. -# -# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -# SOFTWARE. - -"""Utilities for writing code that runs on Python 2 and 3""" - -from __future__ import absolute_import - -import functools -import itertools -import operator -import sys -import types - -__author__ = "Benjamin Peterson " -__version__ = "1.16.0" - - -# Useful for very coarse version differentiation. -PY2 = sys.version_info[0] == 2 -PY3 = sys.version_info[0] == 3 -PY34 = sys.version_info[0:2] >= (3, 4) - -if PY3: - string_types = str, - integer_types = int, - class_types = type, - text_type = str - binary_type = bytes - - MAXSIZE = sys.maxsize -else: - string_types = basestring, - integer_types = (int, long) - class_types = (type, types.ClassType) - text_type = unicode - binary_type = str - - if sys.platform.startswith("java"): - # Jython always uses 32 bits. - MAXSIZE = int((1 << 31) - 1) - else: - # It's possible to have sizeof(long) != sizeof(Py_ssize_t). - class X(object): - - def __len__(self): - return 1 << 31 - try: - len(X()) - except OverflowError: - # 32-bit - MAXSIZE = int((1 << 31) - 1) - else: - # 64-bit - MAXSIZE = int((1 << 63) - 1) - del X - -if PY34: - from importlib.util import spec_from_loader -else: - spec_from_loader = None - - -def _add_doc(func, doc): - """Add documentation to a function.""" - func.__doc__ = doc - - -def _import_module(name): - """Import module, returning the module after the last dot.""" - __import__(name) - return sys.modules[name] - - -class _LazyDescr(object): - - def __init__(self, name): - self.name = name - - def __get__(self, obj, tp): - result = self._resolve() - setattr(obj, self.name, result) # Invokes __set__. - try: - # This is a bit ugly, but it avoids running this again by - # removing this descriptor. - delattr(obj.__class__, self.name) - except AttributeError: - pass - return result - - -class MovedModule(_LazyDescr): - - def __init__(self, name, old, new=None): - super(MovedModule, self).__init__(name) - if PY3: - if new is None: - new = name - self.mod = new - else: - self.mod = old - - def _resolve(self): - return _import_module(self.mod) - - def __getattr__(self, attr): - _module = self._resolve() - value = getattr(_module, attr) - setattr(self, attr, value) - return value - - -class _LazyModule(types.ModuleType): - - def __init__(self, name): - super(_LazyModule, self).__init__(name) - self.__doc__ = self.__class__.__doc__ - - def __dir__(self): - attrs = ["__doc__", "__name__"] - attrs += [attr.name for attr in self._moved_attributes] - return attrs - - # Subclasses should override this - _moved_attributes = [] - - -class MovedAttribute(_LazyDescr): - - def __init__(self, name, old_mod, new_mod, old_attr=None, new_attr=None): - super(MovedAttribute, self).__init__(name) - if PY3: - if new_mod is None: - new_mod = name - self.mod = new_mod - if new_attr is None: - if old_attr is None: - new_attr = name - else: - new_attr = old_attr - self.attr = new_attr - else: - self.mod = old_mod - if old_attr is None: - old_attr = name - self.attr = old_attr - - def _resolve(self): - module = _import_module(self.mod) - return getattr(module, self.attr) - - -class _SixMetaPathImporter(object): - - """ - A meta path importer to import six.moves and its submodules. - - This class implements a PEP302 finder and loader. It should be compatible - with Python 2.5 and all existing versions of Python3 - """ - - def __init__(self, six_module_name): - self.name = six_module_name - self.known_modules = {} - - def _add_module(self, mod, *fullnames): - for fullname in fullnames: - self.known_modules[self.name + "." + fullname] = mod - - def _get_module(self, fullname): - return self.known_modules[self.name + "." + fullname] - - def find_module(self, fullname, path=None): - if fullname in self.known_modules: - return self - return None - - def find_spec(self, fullname, path, target=None): - if fullname in self.known_modules: - return spec_from_loader(fullname, self) - return None - - def __get_module(self, fullname): - try: - return self.known_modules[fullname] - except KeyError: - raise ImportError("This loader does not know module " + fullname) - - def load_module(self, fullname): - try: - # in case of a reload - return sys.modules[fullname] - except KeyError: - pass - mod = self.__get_module(fullname) - if isinstance(mod, MovedModule): - mod = mod._resolve() - else: - mod.__loader__ = self - sys.modules[fullname] = mod - return mod - - def is_package(self, fullname): - """ - Return true, if the named module is a package. - - We need this method to get correct spec objects with - Python 3.4 (see PEP451) - """ - return hasattr(self.__get_module(fullname), "__path__") - - def get_code(self, fullname): - """Return None - - Required, if is_package is implemented""" - self.__get_module(fullname) # eventually raises ImportError - return None - get_source = get_code # same as get_code - - def create_module(self, spec): - return self.load_module(spec.name) - - def exec_module(self, module): - pass - -_importer = _SixMetaPathImporter(__name__) - - -class _MovedItems(_LazyModule): - - """Lazy loading of moved objects""" - __path__ = [] # mark as package - - -_moved_attributes = [ - MovedAttribute("cStringIO", "cStringIO", "io", "StringIO"), - MovedAttribute("filter", "itertools", "builtins", "ifilter", "filter"), - MovedAttribute("filterfalse", "itertools", "itertools", "ifilterfalse", "filterfalse"), - MovedAttribute("input", "__builtin__", "builtins", "raw_input", "input"), - MovedAttribute("intern", "__builtin__", "sys"), - MovedAttribute("map", "itertools", "builtins", "imap", "map"), - MovedAttribute("getcwd", "os", "os", "getcwdu", "getcwd"), - MovedAttribute("getcwdb", "os", "os", "getcwd", "getcwdb"), - MovedAttribute("getoutput", "commands", "subprocess"), - MovedAttribute("range", "__builtin__", "builtins", "xrange", "range"), - MovedAttribute("reload_module", "__builtin__", "importlib" if PY34 else "imp", "reload"), - MovedAttribute("reduce", "__builtin__", "functools"), - MovedAttribute("shlex_quote", "pipes", "shlex", "quote"), - MovedAttribute("StringIO", "StringIO", "io"), - MovedAttribute("UserDict", "UserDict", "collections"), - MovedAttribute("UserList", "UserList", "collections"), - MovedAttribute("UserString", "UserString", "collections"), - MovedAttribute("xrange", "__builtin__", "builtins", "xrange", "range"), - MovedAttribute("zip", "itertools", "builtins", "izip", "zip"), - MovedAttribute("zip_longest", "itertools", "itertools", "izip_longest", "zip_longest"), - MovedModule("builtins", "__builtin__"), - MovedModule("configparser", "ConfigParser"), - MovedModule("collections_abc", "collections", "collections.abc" if sys.version_info >= (3, 3) else "collections"), - MovedModule("copyreg", "copy_reg"), - MovedModule("dbm_gnu", "gdbm", "dbm.gnu"), - MovedModule("dbm_ndbm", "dbm", "dbm.ndbm"), - MovedModule("_dummy_thread", "dummy_thread", "_dummy_thread" if sys.version_info < (3, 9) else "_thread"), - MovedModule("http_cookiejar", "cookielib", "http.cookiejar"), - MovedModule("http_cookies", "Cookie", "http.cookies"), - MovedModule("html_entities", "htmlentitydefs", "html.entities"), - MovedModule("html_parser", "HTMLParser", "html.parser"), - MovedModule("http_client", "httplib", "http.client"), - MovedModule("email_mime_base", "email.MIMEBase", "email.mime.base"), - MovedModule("email_mime_image", "email.MIMEImage", "email.mime.image"), - MovedModule("email_mime_multipart", "email.MIMEMultipart", "email.mime.multipart"), - MovedModule("email_mime_nonmultipart", "email.MIMENonMultipart", "email.mime.nonmultipart"), - MovedModule("email_mime_text", "email.MIMEText", "email.mime.text"), - MovedModule("BaseHTTPServer", "BaseHTTPServer", "http.server"), - MovedModule("CGIHTTPServer", "CGIHTTPServer", "http.server"), - MovedModule("SimpleHTTPServer", "SimpleHTTPServer", "http.server"), - MovedModule("cPickle", "cPickle", "pickle"), - MovedModule("queue", "Queue"), - MovedModule("reprlib", "repr"), - MovedModule("socketserver", "SocketServer"), - MovedModule("_thread", "thread", "_thread"), - MovedModule("tkinter", "Tkinter"), - MovedModule("tkinter_dialog", "Dialog", "tkinter.dialog"), - MovedModule("tkinter_filedialog", "FileDialog", "tkinter.filedialog"), - MovedModule("tkinter_scrolledtext", "ScrolledText", "tkinter.scrolledtext"), - MovedModule("tkinter_simpledialog", "SimpleDialog", "tkinter.simpledialog"), - MovedModule("tkinter_tix", "Tix", "tkinter.tix"), - MovedModule("tkinter_ttk", "ttk", "tkinter.ttk"), - MovedModule("tkinter_constants", "Tkconstants", "tkinter.constants"), - MovedModule("tkinter_dnd", "Tkdnd", "tkinter.dnd"), - MovedModule("tkinter_colorchooser", "tkColorChooser", - "tkinter.colorchooser"), - MovedModule("tkinter_commondialog", "tkCommonDialog", - "tkinter.commondialog"), - MovedModule("tkinter_tkfiledialog", "tkFileDialog", "tkinter.filedialog"), - MovedModule("tkinter_font", "tkFont", "tkinter.font"), - MovedModule("tkinter_messagebox", "tkMessageBox", "tkinter.messagebox"), - MovedModule("tkinter_tksimpledialog", "tkSimpleDialog", - "tkinter.simpledialog"), - MovedModule("urllib_parse", __name__ + ".moves.urllib_parse", "urllib.parse"), - MovedModule("urllib_error", __name__ + ".moves.urllib_error", "urllib.error"), - MovedModule("urllib", __name__ + ".moves.urllib", __name__ + ".moves.urllib"), - MovedModule("urllib_robotparser", "robotparser", "urllib.robotparser"), - MovedModule("xmlrpc_client", "xmlrpclib", "xmlrpc.client"), - MovedModule("xmlrpc_server", "SimpleXMLRPCServer", "xmlrpc.server"), -] -# Add windows specific modules. -if sys.platform == "win32": - _moved_attributes += [ - MovedModule("winreg", "_winreg"), - ] - -for attr in _moved_attributes: - setattr(_MovedItems, attr.name, attr) - if isinstance(attr, MovedModule): - _importer._add_module(attr, "moves." + attr.name) -del attr - -_MovedItems._moved_attributes = _moved_attributes - -moves = _MovedItems(__name__ + ".moves") -_importer._add_module(moves, "moves") - - -class Module_six_moves_urllib_parse(_LazyModule): - - """Lazy loading of moved objects in six.moves.urllib_parse""" - - -_urllib_parse_moved_attributes = [ - MovedAttribute("ParseResult", "urlparse", "urllib.parse"), - MovedAttribute("SplitResult", "urlparse", "urllib.parse"), - MovedAttribute("parse_qs", "urlparse", "urllib.parse"), - MovedAttribute("parse_qsl", "urlparse", "urllib.parse"), - MovedAttribute("urldefrag", "urlparse", "urllib.parse"), - MovedAttribute("urljoin", "urlparse", "urllib.parse"), - MovedAttribute("urlparse", "urlparse", "urllib.parse"), - MovedAttribute("urlsplit", "urlparse", "urllib.parse"), - MovedAttribute("urlunparse", "urlparse", "urllib.parse"), - MovedAttribute("urlunsplit", "urlparse", "urllib.parse"), - MovedAttribute("quote", "urllib", "urllib.parse"), - MovedAttribute("quote_plus", "urllib", "urllib.parse"), - MovedAttribute("unquote", "urllib", "urllib.parse"), - MovedAttribute("unquote_plus", "urllib", "urllib.parse"), - MovedAttribute("unquote_to_bytes", "urllib", "urllib.parse", "unquote", "unquote_to_bytes"), - MovedAttribute("urlencode", "urllib", "urllib.parse"), - MovedAttribute("splitquery", "urllib", "urllib.parse"), - MovedAttribute("splittag", "urllib", "urllib.parse"), - MovedAttribute("splituser", "urllib", "urllib.parse"), - MovedAttribute("splitvalue", "urllib", "urllib.parse"), - MovedAttribute("uses_fragment", "urlparse", "urllib.parse"), - MovedAttribute("uses_netloc", "urlparse", "urllib.parse"), - MovedAttribute("uses_params", "urlparse", "urllib.parse"), - MovedAttribute("uses_query", "urlparse", "urllib.parse"), - MovedAttribute("uses_relative", "urlparse", "urllib.parse"), -] -for attr in _urllib_parse_moved_attributes: - setattr(Module_six_moves_urllib_parse, attr.name, attr) -del attr - -Module_six_moves_urllib_parse._moved_attributes = _urllib_parse_moved_attributes - -_importer._add_module(Module_six_moves_urllib_parse(__name__ + ".moves.urllib_parse"), - "moves.urllib_parse", "moves.urllib.parse") - - -class Module_six_moves_urllib_error(_LazyModule): - - """Lazy loading of moved objects in six.moves.urllib_error""" - - -_urllib_error_moved_attributes = [ - MovedAttribute("URLError", "urllib2", "urllib.error"), - MovedAttribute("HTTPError", "urllib2", "urllib.error"), - MovedAttribute("ContentTooShortError", "urllib", "urllib.error"), -] -for attr in _urllib_error_moved_attributes: - setattr(Module_six_moves_urllib_error, attr.name, attr) -del attr - -Module_six_moves_urllib_error._moved_attributes = _urllib_error_moved_attributes - -_importer._add_module(Module_six_moves_urllib_error(__name__ + ".moves.urllib.error"), - "moves.urllib_error", "moves.urllib.error") - - -class Module_six_moves_urllib_request(_LazyModule): - - """Lazy loading of moved objects in six.moves.urllib_request""" - - -_urllib_request_moved_attributes = [ - MovedAttribute("urlopen", "urllib2", "urllib.request"), - MovedAttribute("install_opener", "urllib2", "urllib.request"), - MovedAttribute("build_opener", "urllib2", "urllib.request"), - MovedAttribute("pathname2url", "urllib", "urllib.request"), - MovedAttribute("url2pathname", "urllib", "urllib.request"), - MovedAttribute("getproxies", "urllib", "urllib.request"), - MovedAttribute("Request", "urllib2", "urllib.request"), - MovedAttribute("OpenerDirector", "urllib2", "urllib.request"), - MovedAttribute("HTTPDefaultErrorHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPRedirectHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPCookieProcessor", "urllib2", "urllib.request"), - MovedAttribute("ProxyHandler", "urllib2", "urllib.request"), - MovedAttribute("BaseHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPPasswordMgr", "urllib2", "urllib.request"), - MovedAttribute("HTTPPasswordMgrWithDefaultRealm", "urllib2", "urllib.request"), - MovedAttribute("AbstractBasicAuthHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPBasicAuthHandler", "urllib2", "urllib.request"), - MovedAttribute("ProxyBasicAuthHandler", "urllib2", "urllib.request"), - MovedAttribute("AbstractDigestAuthHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPDigestAuthHandler", "urllib2", "urllib.request"), - MovedAttribute("ProxyDigestAuthHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPSHandler", "urllib2", "urllib.request"), - MovedAttribute("FileHandler", "urllib2", "urllib.request"), - MovedAttribute("FTPHandler", "urllib2", "urllib.request"), - MovedAttribute("CacheFTPHandler", "urllib2", "urllib.request"), - MovedAttribute("UnknownHandler", "urllib2", "urllib.request"), - MovedAttribute("HTTPErrorProcessor", "urllib2", "urllib.request"), - MovedAttribute("urlretrieve", "urllib", "urllib.request"), - MovedAttribute("urlcleanup", "urllib", "urllib.request"), - MovedAttribute("URLopener", "urllib", "urllib.request"), - MovedAttribute("FancyURLopener", "urllib", "urllib.request"), - MovedAttribute("proxy_bypass", "urllib", "urllib.request"), - MovedAttribute("parse_http_list", "urllib2", "urllib.request"), - MovedAttribute("parse_keqv_list", "urllib2", "urllib.request"), -] -for attr in _urllib_request_moved_attributes: - setattr(Module_six_moves_urllib_request, attr.name, attr) -del attr - -Module_six_moves_urllib_request._moved_attributes = _urllib_request_moved_attributes - -_importer._add_module(Module_six_moves_urllib_request(__name__ + ".moves.urllib.request"), - "moves.urllib_request", "moves.urllib.request") - - -class Module_six_moves_urllib_response(_LazyModule): - - """Lazy loading of moved objects in six.moves.urllib_response""" - - -_urllib_response_moved_attributes = [ - MovedAttribute("addbase", "urllib", "urllib.response"), - MovedAttribute("addclosehook", "urllib", "urllib.response"), - MovedAttribute("addinfo", "urllib", "urllib.response"), - MovedAttribute("addinfourl", "urllib", "urllib.response"), -] -for attr in _urllib_response_moved_attributes: - setattr(Module_six_moves_urllib_response, attr.name, attr) -del attr - -Module_six_moves_urllib_response._moved_attributes = _urllib_response_moved_attributes - -_importer._add_module(Module_six_moves_urllib_response(__name__ + ".moves.urllib.response"), - "moves.urllib_response", "moves.urllib.response") - - -class Module_six_moves_urllib_robotparser(_LazyModule): - - """Lazy loading of moved objects in six.moves.urllib_robotparser""" - - -_urllib_robotparser_moved_attributes = [ - MovedAttribute("RobotFileParser", "robotparser", "urllib.robotparser"), -] -for attr in _urllib_robotparser_moved_attributes: - setattr(Module_six_moves_urllib_robotparser, attr.name, attr) -del attr - -Module_six_moves_urllib_robotparser._moved_attributes = _urllib_robotparser_moved_attributes - -_importer._add_module(Module_six_moves_urllib_robotparser(__name__ + ".moves.urllib.robotparser"), - "moves.urllib_robotparser", "moves.urllib.robotparser") - - -class Module_six_moves_urllib(types.ModuleType): - - """Create a six.moves.urllib namespace that resembles the Python 3 namespace""" - __path__ = [] # mark as package - parse = _importer._get_module("moves.urllib_parse") - error = _importer._get_module("moves.urllib_error") - request = _importer._get_module("moves.urllib_request") - response = _importer._get_module("moves.urllib_response") - robotparser = _importer._get_module("moves.urllib_robotparser") - - def __dir__(self): - return ['parse', 'error', 'request', 'response', 'robotparser'] - -_importer._add_module(Module_six_moves_urllib(__name__ + ".moves.urllib"), - "moves.urllib") - - -def add_move(move): - """Add an item to six.moves.""" - setattr(_MovedItems, move.name, move) - - -def remove_move(name): - """Remove item from six.moves.""" - try: - delattr(_MovedItems, name) - except AttributeError: - try: - del moves.__dict__[name] - except KeyError: - raise AttributeError("no such move, %r" % (name,)) - - -if PY3: - _meth_func = "__func__" - _meth_self = "__self__" - - _func_closure = "__closure__" - _func_code = "__code__" - _func_defaults = "__defaults__" - _func_globals = "__globals__" -else: - _meth_func = "im_func" - _meth_self = "im_self" - - _func_closure = "func_closure" - _func_code = "func_code" - _func_defaults = "func_defaults" - _func_globals = "func_globals" - - -try: - advance_iterator = next -except NameError: - def advance_iterator(it): - return it.next() -next = advance_iterator - - -try: - callable = callable -except NameError: - def callable(obj): - return any("__call__" in klass.__dict__ for klass in type(obj).__mro__) - - -if PY3: - def get_unbound_function(unbound): - return unbound - - create_bound_method = types.MethodType - - def create_unbound_method(func, cls): - return func - - Iterator = object -else: - def get_unbound_function(unbound): - return unbound.im_func - - def create_bound_method(func, obj): - return types.MethodType(func, obj, obj.__class__) - - def create_unbound_method(func, cls): - return types.MethodType(func, None, cls) - - class Iterator(object): - - def next(self): - return type(self).__next__(self) - - callable = callable -_add_doc(get_unbound_function, - """Get the function out of a possibly unbound function""") - - -get_method_function = operator.attrgetter(_meth_func) -get_method_self = operator.attrgetter(_meth_self) -get_function_closure = operator.attrgetter(_func_closure) -get_function_code = operator.attrgetter(_func_code) -get_function_defaults = operator.attrgetter(_func_defaults) -get_function_globals = operator.attrgetter(_func_globals) - - -if PY3: - def iterkeys(d, **kw): - return iter(d.keys(**kw)) - - def itervalues(d, **kw): - return iter(d.values(**kw)) - - def iteritems(d, **kw): - return iter(d.items(**kw)) - - def iterlists(d, **kw): - return iter(d.lists(**kw)) - - viewkeys = operator.methodcaller("keys") - - viewvalues = operator.methodcaller("values") - - viewitems = operator.methodcaller("items") -else: - def iterkeys(d, **kw): - return d.iterkeys(**kw) - - def itervalues(d, **kw): - return d.itervalues(**kw) - - def iteritems(d, **kw): - return d.iteritems(**kw) - - def iterlists(d, **kw): - return d.iterlists(**kw) - - viewkeys = operator.methodcaller("viewkeys") - - viewvalues = operator.methodcaller("viewvalues") - - viewitems = operator.methodcaller("viewitems") - -_add_doc(iterkeys, "Return an iterator over the keys of a dictionary.") -_add_doc(itervalues, "Return an iterator over the values of a dictionary.") -_add_doc(iteritems, - "Return an iterator over the (key, value) pairs of a dictionary.") -_add_doc(iterlists, - "Return an iterator over the (key, [values]) pairs of a dictionary.") - - -if PY3: - def b(s): - return s.encode("latin-1") - - def u(s): - return s - unichr = chr - import struct - int2byte = struct.Struct(">B").pack - del struct - byte2int = operator.itemgetter(0) - indexbytes = operator.getitem - iterbytes = iter - import io - StringIO = io.StringIO - BytesIO = io.BytesIO - del io - _assertCountEqual = "assertCountEqual" - if sys.version_info[1] <= 1: - _assertRaisesRegex = "assertRaisesRegexp" - _assertRegex = "assertRegexpMatches" - _assertNotRegex = "assertNotRegexpMatches" - else: - _assertRaisesRegex = "assertRaisesRegex" - _assertRegex = "assertRegex" - _assertNotRegex = "assertNotRegex" -else: - def b(s): - return s - # Workaround for standalone backslash - - def u(s): - return unicode(s.replace(r'\\', r'\\\\'), "unicode_escape") - unichr = unichr - int2byte = chr - - def byte2int(bs): - return ord(bs[0]) - - def indexbytes(buf, i): - return ord(buf[i]) - iterbytes = functools.partial(itertools.imap, ord) - import StringIO - StringIO = BytesIO = StringIO.StringIO - _assertCountEqual = "assertItemsEqual" - _assertRaisesRegex = "assertRaisesRegexp" - _assertRegex = "assertRegexpMatches" - _assertNotRegex = "assertNotRegexpMatches" -_add_doc(b, """Byte literal""") -_add_doc(u, """Text literal""") - - -def assertCountEqual(self, *args, **kwargs): - return getattr(self, _assertCountEqual)(*args, **kwargs) - - -def assertRaisesRegex(self, *args, **kwargs): - return getattr(self, _assertRaisesRegex)(*args, **kwargs) - - -def assertRegex(self, *args, **kwargs): - return getattr(self, _assertRegex)(*args, **kwargs) - - -def assertNotRegex(self, *args, **kwargs): - return getattr(self, _assertNotRegex)(*args, **kwargs) - - -if PY3: - exec_ = getattr(moves.builtins, "exec") - - def reraise(tp, value, tb=None): - try: - if value is None: - value = tp() - if value.__traceback__ is not tb: - raise value.with_traceback(tb) - raise value - finally: - value = None - tb = None - -else: - def exec_(_code_, _globs_=None, _locs_=None): - """Execute code in a namespace.""" - if _globs_ is None: - frame = sys._getframe(1) - _globs_ = frame.f_globals - if _locs_ is None: - _locs_ = frame.f_locals - del frame - elif _locs_ is None: - _locs_ = _globs_ - exec("""exec _code_ in _globs_, _locs_""") - - exec_("""def reraise(tp, value, tb=None): - try: - raise tp, value, tb - finally: - tb = None -""") - - -if sys.version_info[:2] > (3,): - exec_("""def raise_from(value, from_value): - try: - raise value from from_value - finally: - value = None -""") -else: - def raise_from(value, from_value): - raise value - - -print_ = getattr(moves.builtins, "print", None) -if print_ is None: - def print_(*args, **kwargs): - """The new-style print function for Python 2.4 and 2.5.""" - fp = kwargs.pop("file", sys.stdout) - if fp is None: - return - - def write(data): - if not isinstance(data, basestring): - data = str(data) - # If the file has an encoding, encode unicode with it. - if (isinstance(fp, file) and - isinstance(data, unicode) and - fp.encoding is not None): - errors = getattr(fp, "errors", None) - if errors is None: - errors = "strict" - data = data.encode(fp.encoding, errors) - fp.write(data) - want_unicode = False - sep = kwargs.pop("sep", None) - if sep is not None: - if isinstance(sep, unicode): - want_unicode = True - elif not isinstance(sep, str): - raise TypeError("sep must be None or a string") - end = kwargs.pop("end", None) - if end is not None: - if isinstance(end, unicode): - want_unicode = True - elif not isinstance(end, str): - raise TypeError("end must be None or a string") - if kwargs: - raise TypeError("invalid keyword arguments to print()") - if not want_unicode: - for arg in args: - if isinstance(arg, unicode): - want_unicode = True - break - if want_unicode: - newline = unicode("\n") - space = unicode(" ") - else: - newline = "\n" - space = " " - if sep is None: - sep = space - if end is None: - end = newline - for i, arg in enumerate(args): - if i: - write(sep) - write(arg) - write(end) -if sys.version_info[:2] < (3, 3): - _print = print_ - - def print_(*args, **kwargs): - fp = kwargs.get("file", sys.stdout) - flush = kwargs.pop("flush", False) - _print(*args, **kwargs) - if flush and fp is not None: - fp.flush() - -_add_doc(reraise, """Reraise an exception.""") - -if sys.version_info[0:2] < (3, 4): - # This does exactly the same what the :func:`py3:functools.update_wrapper` - # function does on Python versions after 3.2. It sets the ``__wrapped__`` - # attribute on ``wrapper`` object and it doesn't raise an error if any of - # the attributes mentioned in ``assigned`` and ``updated`` are missing on - # ``wrapped`` object. - def _update_wrapper(wrapper, wrapped, - assigned=functools.WRAPPER_ASSIGNMENTS, - updated=functools.WRAPPER_UPDATES): - for attr in assigned: - try: - value = getattr(wrapped, attr) - except AttributeError: - continue - else: - setattr(wrapper, attr, value) - for attr in updated: - getattr(wrapper, attr).update(getattr(wrapped, attr, {})) - wrapper.__wrapped__ = wrapped - return wrapper - _update_wrapper.__doc__ = functools.update_wrapper.__doc__ - - def wraps(wrapped, assigned=functools.WRAPPER_ASSIGNMENTS, - updated=functools.WRAPPER_UPDATES): - return functools.partial(_update_wrapper, wrapped=wrapped, - assigned=assigned, updated=updated) - wraps.__doc__ = functools.wraps.__doc__ - -else: - wraps = functools.wraps - - -def with_metaclass(meta, *bases): - """Create a base class with a metaclass.""" - # This requires a bit of explanation: the basic idea is to make a dummy - # metaclass for one level of class instantiation that replaces itself with - # the actual metaclass. - class metaclass(type): - - def __new__(cls, name, this_bases, d): - if sys.version_info[:2] >= (3, 7): - # This version introduced PEP 560 that requires a bit - # of extra care (we mimic what is done by __build_class__). - resolved_bases = types.resolve_bases(bases) - if resolved_bases is not bases: - d['__orig_bases__'] = bases - else: - resolved_bases = bases - return meta(name, resolved_bases, d) - - @classmethod - def __prepare__(cls, name, this_bases): - return meta.__prepare__(name, bases) - return type.__new__(metaclass, 'temporary_class', (), {}) - - -def add_metaclass(metaclass): - """Class decorator for creating a class with a metaclass.""" - def wrapper(cls): - orig_vars = cls.__dict__.copy() - slots = orig_vars.get('__slots__') - if slots is not None: - if isinstance(slots, str): - slots = [slots] - for slots_var in slots: - orig_vars.pop(slots_var) - orig_vars.pop('__dict__', None) - orig_vars.pop('__weakref__', None) - if hasattr(cls, '__qualname__'): - orig_vars['__qualname__'] = cls.__qualname__ - return metaclass(cls.__name__, cls.__bases__, orig_vars) - return wrapper - - -def ensure_binary(s, encoding='utf-8', errors='strict'): - """Coerce **s** to six.binary_type. - - For Python 2: - - `unicode` -> encoded to `str` - - `str` -> `str` - - For Python 3: - - `str` -> encoded to `bytes` - - `bytes` -> `bytes` - """ - if isinstance(s, binary_type): - return s - if isinstance(s, text_type): - return s.encode(encoding, errors) - raise TypeError("not expecting type '%s'" % type(s)) - - -def ensure_str(s, encoding='utf-8', errors='strict'): - """Coerce *s* to `str`. - - For Python 2: - - `unicode` -> encoded to `str` - - `str` -> `str` - - For Python 3: - - `str` -> `str` - - `bytes` -> decoded to `str` - """ - # Optimization: Fast return for the common case. - if type(s) is str: - return s - if PY2 and isinstance(s, text_type): - return s.encode(encoding, errors) - elif PY3 and isinstance(s, binary_type): - return s.decode(encoding, errors) - elif not isinstance(s, (text_type, binary_type)): - raise TypeError("not expecting type '%s'" % type(s)) - return s - - -def ensure_text(s, encoding='utf-8', errors='strict'): - """Coerce *s* to six.text_type. - - For Python 2: - - `unicode` -> `unicode` - - `str` -> `unicode` - - For Python 3: - - `str` -> `str` - - `bytes` -> decoded to `str` - """ - if isinstance(s, binary_type): - return s.decode(encoding, errors) - elif isinstance(s, text_type): - return s - else: - raise TypeError("not expecting type '%s'" % type(s)) - - -def python_2_unicode_compatible(klass): - """ - A class decorator that defines __unicode__ and __str__ methods under Python 2. - Under Python 3 it does nothing. - - To support Python 2 and 3 with a single code base, define a __str__ method - returning text and apply this decorator to the class. - """ - if PY2: - if '__str__' not in klass.__dict__: - raise ValueError("@python_2_unicode_compatible cannot be applied " - "to %s because it doesn't define __str__()." % - klass.__name__) - klass.__unicode__ = klass.__str__ - klass.__str__ = lambda self: self.__unicode__().encode('utf-8') - return klass - - -# Complete the moves implementation. -# This code is at the end of this module to speed up module loading. -# Turn this module into a package. -__path__ = [] # required for PEP 302 and PEP 451 -__package__ = __name__ # see PEP 366 @ReservedAssignment -if globals().get("__spec__") is not None: - __spec__.submodule_search_locations = [] # PEP 451 @UndefinedVariable -# Remove other six meta path importers, since they cause problems. This can -# happen if six is removed from sys.modules and then reloaded. (Setuptools does -# this for some reason.) -if sys.meta_path: - for i, importer in enumerate(sys.meta_path): - # Here's some real nastiness: Another "instance" of the six module might - # be floating around. Therefore, we can't use isinstance() to check for - # the six meta path importer, since the other six instance will have - # inserted an importer with different class. - if (type(importer).__name__ == "_SixMetaPathImporter" and - importer.name == __name__): - del sys.meta_path[i] - break - del i, importer -# Finally, add the importer to the meta path import hook. -sys.meta_path.append(_importer) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__init__.py deleted file mode 100644 index 4f1603a..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__init__.py +++ /dev/null @@ -1,608 +0,0 @@ -# Copyright 2016-2018 Julien Danjou -# Copyright 2017 Elisey Zanko -# Copyright 2016 Étienne Bersac -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - - -import functools -import sys -import threading -import time -import typing as t -import warnings -from abc import ABC, abstractmethod -from concurrent import futures -from inspect import iscoroutinefunction - -# Import all built-in retry strategies for easier usage. -from .retry import retry_base # noqa -from .retry import retry_all # noqa -from .retry import retry_always # noqa -from .retry import retry_any # noqa -from .retry import retry_if_exception # noqa -from .retry import retry_if_exception_type # noqa -from .retry import retry_if_exception_cause_type # noqa -from .retry import retry_if_not_exception_type # noqa -from .retry import retry_if_not_result # noqa -from .retry import retry_if_result # noqa -from .retry import retry_never # noqa -from .retry import retry_unless_exception_type # noqa -from .retry import retry_if_exception_message # noqa -from .retry import retry_if_not_exception_message # noqa - -# Import all nap strategies for easier usage. -from .nap import sleep # noqa -from .nap import sleep_using_event # noqa - -# Import all built-in stop strategies for easier usage. -from .stop import stop_after_attempt # noqa -from .stop import stop_after_delay # noqa -from .stop import stop_all # noqa -from .stop import stop_any # noqa -from .stop import stop_never # noqa -from .stop import stop_when_event_set # noqa - -# Import all built-in wait strategies for easier usage. -from .wait import wait_chain # noqa -from .wait import wait_combine # noqa -from .wait import wait_exponential # noqa -from .wait import wait_fixed # noqa -from .wait import wait_incrementing # noqa -from .wait import wait_none # noqa -from .wait import wait_random # noqa -from .wait import wait_random_exponential # noqa -from .wait import wait_random_exponential as wait_full_jitter # noqa -from .wait import wait_exponential_jitter # noqa - -# Import all built-in before strategies for easier usage. -from .before import before_log # noqa -from .before import before_nothing # noqa - -# Import all built-in after strategies for easier usage. -from .after import after_log # noqa -from .after import after_nothing # noqa - -# Import all built-in after strategies for easier usage. -from .before_sleep import before_sleep_log # noqa -from .before_sleep import before_sleep_nothing # noqa - -# Replace a conditional import with a hard-coded None so that pip does -# not attempt to use tornado even if it is present in the environment. -# If tornado is non-None, tenacity will attempt to execute some code -# that is sensitive to the version of tornado, which could break pip -# if an old version is found. -tornado = None # type: ignore - -if t.TYPE_CHECKING: - import types - - from .retry import RetryBaseT - from .stop import StopBaseT - from .wait import WaitBaseT - - -WrappedFnReturnT = t.TypeVar("WrappedFnReturnT") -WrappedFn = t.TypeVar("WrappedFn", bound=t.Callable[..., t.Any]) - - -class TryAgain(Exception): - """Always retry the executed function when raised.""" - - -NO_RESULT = object() - - -class DoAttempt: - pass - - -class DoSleep(float): - pass - - -class BaseAction: - """Base class for representing actions to take by retry object. - - Concrete implementations must define: - - __init__: to initialize all necessary fields - - REPR_FIELDS: class variable specifying attributes to include in repr(self) - - NAME: for identification in retry object methods and callbacks - """ - - REPR_FIELDS: t.Sequence[str] = () - NAME: t.Optional[str] = None - - def __repr__(self) -> str: - state_str = ", ".join(f"{field}={getattr(self, field)!r}" for field in self.REPR_FIELDS) - return f"{self.__class__.__name__}({state_str})" - - def __str__(self) -> str: - return repr(self) - - -class RetryAction(BaseAction): - REPR_FIELDS = ("sleep",) - NAME = "retry" - - def __init__(self, sleep: t.SupportsFloat) -> None: - self.sleep = float(sleep) - - -_unset = object() - - -def _first_set(first: t.Union[t.Any, object], second: t.Any) -> t.Any: - return second if first is _unset else first - - -class RetryError(Exception): - """Encapsulates the last attempt instance right before giving up.""" - - def __init__(self, last_attempt: "Future") -> None: - self.last_attempt = last_attempt - super().__init__(last_attempt) - - def reraise(self) -> "t.NoReturn": - if self.last_attempt.failed: - raise self.last_attempt.result() - raise self - - def __str__(self) -> str: - return f"{self.__class__.__name__}[{self.last_attempt}]" - - -class AttemptManager: - """Manage attempt context.""" - - def __init__(self, retry_state: "RetryCallState"): - self.retry_state = retry_state - - def __enter__(self) -> None: - pass - - def __exit__( - self, - exc_type: t.Optional[t.Type[BaseException]], - exc_value: t.Optional[BaseException], - traceback: t.Optional["types.TracebackType"], - ) -> t.Optional[bool]: - if exc_type is not None and exc_value is not None: - self.retry_state.set_exception((exc_type, exc_value, traceback)) - return True # Swallow exception. - else: - # We don't have the result, actually. - self.retry_state.set_result(None) - return None - - -class BaseRetrying(ABC): - def __init__( - self, - sleep: t.Callable[[t.Union[int, float]], None] = sleep, - stop: "StopBaseT" = stop_never, - wait: "WaitBaseT" = wait_none(), - retry: "RetryBaseT" = retry_if_exception_type(), - before: t.Callable[["RetryCallState"], None] = before_nothing, - after: t.Callable[["RetryCallState"], None] = after_nothing, - before_sleep: t.Optional[t.Callable[["RetryCallState"], None]] = None, - reraise: bool = False, - retry_error_cls: t.Type[RetryError] = RetryError, - retry_error_callback: t.Optional[t.Callable[["RetryCallState"], t.Any]] = None, - ): - self.sleep = sleep - self.stop = stop - self.wait = wait - self.retry = retry - self.before = before - self.after = after - self.before_sleep = before_sleep - self.reraise = reraise - self._local = threading.local() - self.retry_error_cls = retry_error_cls - self.retry_error_callback = retry_error_callback - - def copy( - self, - sleep: t.Union[t.Callable[[t.Union[int, float]], None], object] = _unset, - stop: t.Union["StopBaseT", object] = _unset, - wait: t.Union["WaitBaseT", object] = _unset, - retry: t.Union[retry_base, object] = _unset, - before: t.Union[t.Callable[["RetryCallState"], None], object] = _unset, - after: t.Union[t.Callable[["RetryCallState"], None], object] = _unset, - before_sleep: t.Union[t.Optional[t.Callable[["RetryCallState"], None]], object] = _unset, - reraise: t.Union[bool, object] = _unset, - retry_error_cls: t.Union[t.Type[RetryError], object] = _unset, - retry_error_callback: t.Union[t.Optional[t.Callable[["RetryCallState"], t.Any]], object] = _unset, - ) -> "BaseRetrying": - """Copy this object with some parameters changed if needed.""" - return self.__class__( - sleep=_first_set(sleep, self.sleep), - stop=_first_set(stop, self.stop), - wait=_first_set(wait, self.wait), - retry=_first_set(retry, self.retry), - before=_first_set(before, self.before), - after=_first_set(after, self.after), - before_sleep=_first_set(before_sleep, self.before_sleep), - reraise=_first_set(reraise, self.reraise), - retry_error_cls=_first_set(retry_error_cls, self.retry_error_cls), - retry_error_callback=_first_set(retry_error_callback, self.retry_error_callback), - ) - - def __repr__(self) -> str: - return ( - f"<{self.__class__.__name__} object at 0x{id(self):x} (" - f"stop={self.stop}, " - f"wait={self.wait}, " - f"sleep={self.sleep}, " - f"retry={self.retry}, " - f"before={self.before}, " - f"after={self.after})>" - ) - - @property - def statistics(self) -> t.Dict[str, t.Any]: - """Return a dictionary of runtime statistics. - - This dictionary will be empty when the controller has never been - ran. When it is running or has ran previously it should have (but - may not) have useful and/or informational keys and values when - running is underway and/or completed. - - .. warning:: The keys in this dictionary **should** be some what - stable (not changing), but there existence **may** - change between major releases as new statistics are - gathered or removed so before accessing keys ensure that - they actually exist and handle when they do not. - - .. note:: The values in this dictionary are local to the thread - running call (so if multiple threads share the same retrying - object - either directly or indirectly) they will each have - there own view of statistics they have collected (in the - future we may provide a way to aggregate the various - statistics from each thread). - """ - try: - return self._local.statistics # type: ignore[no-any-return] - except AttributeError: - self._local.statistics = t.cast(t.Dict[str, t.Any], {}) - return self._local.statistics - - def wraps(self, f: WrappedFn) -> WrappedFn: - """Wrap a function for retrying. - - :param f: A function to wraps for retrying. - """ - - @functools.wraps(f) - def wrapped_f(*args: t.Any, **kw: t.Any) -> t.Any: - return self(f, *args, **kw) - - def retry_with(*args: t.Any, **kwargs: t.Any) -> WrappedFn: - return self.copy(*args, **kwargs).wraps(f) - - wrapped_f.retry = self # type: ignore[attr-defined] - wrapped_f.retry_with = retry_with # type: ignore[attr-defined] - - return wrapped_f # type: ignore[return-value] - - def begin(self) -> None: - self.statistics.clear() - self.statistics["start_time"] = time.monotonic() - self.statistics["attempt_number"] = 1 - self.statistics["idle_for"] = 0 - - def iter(self, retry_state: "RetryCallState") -> t.Union[DoAttempt, DoSleep, t.Any]: # noqa - fut = retry_state.outcome - if fut is None: - if self.before is not None: - self.before(retry_state) - return DoAttempt() - - is_explicit_retry = fut.failed and isinstance(fut.exception(), TryAgain) - if not (is_explicit_retry or self.retry(retry_state)): - return fut.result() - - if self.after is not None: - self.after(retry_state) - - self.statistics["delay_since_first_attempt"] = retry_state.seconds_since_start - if self.stop(retry_state): - if self.retry_error_callback: - return self.retry_error_callback(retry_state) - retry_exc = self.retry_error_cls(fut) - if self.reraise: - raise retry_exc.reraise() - raise retry_exc from fut.exception() - - if self.wait: - sleep = self.wait(retry_state) - else: - sleep = 0.0 - retry_state.next_action = RetryAction(sleep) - retry_state.idle_for += sleep - self.statistics["idle_for"] += sleep - self.statistics["attempt_number"] += 1 - - if self.before_sleep is not None: - self.before_sleep(retry_state) - - return DoSleep(sleep) - - def __iter__(self) -> t.Generator[AttemptManager, None, None]: - self.begin() - - retry_state = RetryCallState(self, fn=None, args=(), kwargs={}) - while True: - do = self.iter(retry_state=retry_state) - if isinstance(do, DoAttempt): - yield AttemptManager(retry_state=retry_state) - elif isinstance(do, DoSleep): - retry_state.prepare_for_next_attempt() - self.sleep(do) - else: - break - - @abstractmethod - def __call__( - self, - fn: t.Callable[..., WrappedFnReturnT], - *args: t.Any, - **kwargs: t.Any, - ) -> WrappedFnReturnT: - pass - - -class Retrying(BaseRetrying): - """Retrying controller.""" - - def __call__( - self, - fn: t.Callable[..., WrappedFnReturnT], - *args: t.Any, - **kwargs: t.Any, - ) -> WrappedFnReturnT: - self.begin() - - retry_state = RetryCallState(retry_object=self, fn=fn, args=args, kwargs=kwargs) - while True: - do = self.iter(retry_state=retry_state) - if isinstance(do, DoAttempt): - try: - result = fn(*args, **kwargs) - except BaseException: # noqa: B902 - retry_state.set_exception(sys.exc_info()) # type: ignore[arg-type] - else: - retry_state.set_result(result) - elif isinstance(do, DoSleep): - retry_state.prepare_for_next_attempt() - self.sleep(do) - else: - return do # type: ignore[no-any-return] - - -if sys.version_info[1] >= 9: - FutureGenericT = futures.Future[t.Any] -else: - FutureGenericT = futures.Future - - -class Future(FutureGenericT): - """Encapsulates a (future or past) attempted call to a target function.""" - - def __init__(self, attempt_number: int) -> None: - super().__init__() - self.attempt_number = attempt_number - - @property - def failed(self) -> bool: - """Return whether a exception is being held in this future.""" - return self.exception() is not None - - @classmethod - def construct(cls, attempt_number: int, value: t.Any, has_exception: bool) -> "Future": - """Construct a new Future object.""" - fut = cls(attempt_number) - if has_exception: - fut.set_exception(value) - else: - fut.set_result(value) - return fut - - -class RetryCallState: - """State related to a single call wrapped with Retrying.""" - - def __init__( - self, - retry_object: BaseRetrying, - fn: t.Optional[WrappedFn], - args: t.Any, - kwargs: t.Any, - ) -> None: - #: Retry call start timestamp - self.start_time = time.monotonic() - #: Retry manager object - self.retry_object = retry_object - #: Function wrapped by this retry call - self.fn = fn - #: Arguments of the function wrapped by this retry call - self.args = args - #: Keyword arguments of the function wrapped by this retry call - self.kwargs = kwargs - - #: The number of the current attempt - self.attempt_number: int = 1 - #: Last outcome (result or exception) produced by the function - self.outcome: t.Optional[Future] = None - #: Timestamp of the last outcome - self.outcome_timestamp: t.Optional[float] = None - #: Time spent sleeping in retries - self.idle_for: float = 0.0 - #: Next action as decided by the retry manager - self.next_action: t.Optional[RetryAction] = None - - @property - def seconds_since_start(self) -> t.Optional[float]: - if self.outcome_timestamp is None: - return None - return self.outcome_timestamp - self.start_time - - def prepare_for_next_attempt(self) -> None: - self.outcome = None - self.outcome_timestamp = None - self.attempt_number += 1 - self.next_action = None - - def set_result(self, val: t.Any) -> None: - ts = time.monotonic() - fut = Future(self.attempt_number) - fut.set_result(val) - self.outcome, self.outcome_timestamp = fut, ts - - def set_exception( - self, exc_info: t.Tuple[t.Type[BaseException], BaseException, "types.TracebackType| None"] - ) -> None: - ts = time.monotonic() - fut = Future(self.attempt_number) - fut.set_exception(exc_info[1]) - self.outcome, self.outcome_timestamp = fut, ts - - def __repr__(self) -> str: - if self.outcome is None: - result = "none yet" - elif self.outcome.failed: - exception = self.outcome.exception() - result = f"failed ({exception.__class__.__name__} {exception})" - else: - result = f"returned {self.outcome.result()}" - - slept = float(round(self.idle_for, 2)) - clsname = self.__class__.__name__ - return f"<{clsname} {id(self)}: attempt #{self.attempt_number}; slept for {slept}; last result: {result}>" - - -@t.overload -def retry(func: WrappedFn) -> WrappedFn: - ... - - -@t.overload -def retry( - sleep: t.Callable[[t.Union[int, float]], None] = sleep, - stop: "StopBaseT" = stop_never, - wait: "WaitBaseT" = wait_none(), - retry: "RetryBaseT" = retry_if_exception_type(), - before: t.Callable[["RetryCallState"], None] = before_nothing, - after: t.Callable[["RetryCallState"], None] = after_nothing, - before_sleep: t.Optional[t.Callable[["RetryCallState"], None]] = None, - reraise: bool = False, - retry_error_cls: t.Type["RetryError"] = RetryError, - retry_error_callback: t.Optional[t.Callable[["RetryCallState"], t.Any]] = None, -) -> t.Callable[[WrappedFn], WrappedFn]: - ... - - -def retry(*dargs: t.Any, **dkw: t.Any) -> t.Any: - """Wrap a function with a new `Retrying` object. - - :param dargs: positional arguments passed to Retrying object - :param dkw: keyword arguments passed to the Retrying object - """ - # support both @retry and @retry() as valid syntax - if len(dargs) == 1 and callable(dargs[0]): - return retry()(dargs[0]) - else: - - def wrap(f: WrappedFn) -> WrappedFn: - if isinstance(f, retry_base): - warnings.warn( - f"Got retry_base instance ({f.__class__.__name__}) as callable argument, " - f"this will probably hang indefinitely (did you mean retry={f.__class__.__name__}(...)?)" - ) - r: "BaseRetrying" - if iscoroutinefunction(f): - r = AsyncRetrying(*dargs, **dkw) - elif tornado and hasattr(tornado.gen, "is_coroutine_function") and tornado.gen.is_coroutine_function(f): - r = TornadoRetrying(*dargs, **dkw) - else: - r = Retrying(*dargs, **dkw) - - return r.wraps(f) - - return wrap - - -from pip._vendor.tenacity._asyncio import AsyncRetrying # noqa:E402,I100 - -if tornado: - from pip._vendor.tenacity.tornadoweb import TornadoRetrying - - -__all__ = [ - "retry_base", - "retry_all", - "retry_always", - "retry_any", - "retry_if_exception", - "retry_if_exception_type", - "retry_if_exception_cause_type", - "retry_if_not_exception_type", - "retry_if_not_result", - "retry_if_result", - "retry_never", - "retry_unless_exception_type", - "retry_if_exception_message", - "retry_if_not_exception_message", - "sleep", - "sleep_using_event", - "stop_after_attempt", - "stop_after_delay", - "stop_all", - "stop_any", - "stop_never", - "stop_when_event_set", - "wait_chain", - "wait_combine", - "wait_exponential", - "wait_fixed", - "wait_incrementing", - "wait_none", - "wait_random", - "wait_random_exponential", - "wait_full_jitter", - "wait_exponential_jitter", - "before_log", - "before_nothing", - "after_log", - "after_nothing", - "before_sleep_log", - "before_sleep_nothing", - "retry", - "WrappedFn", - "TryAgain", - "NO_RESULT", - "DoAttempt", - "DoSleep", - "BaseAction", - "RetryAction", - "RetryError", - "AttemptManager", - "BaseRetrying", - "Retrying", - "Future", - "RetryCallState", - "AsyncRetrying", -] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 99423f2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/_asyncio.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/_asyncio.cpython-312.pyc deleted file mode 100644 index b936986..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/_asyncio.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/_utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/_utils.cpython-312.pyc deleted file mode 100644 index a18d09c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/_utils.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/after.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/after.cpython-312.pyc deleted file mode 100644 index 49d083c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/after.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/before.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/before.cpython-312.pyc deleted file mode 100644 index 1ffbe36..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/before.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/before_sleep.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/before_sleep.cpython-312.pyc deleted file mode 100644 index ca166d5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/before_sleep.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/nap.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/nap.cpython-312.pyc deleted file mode 100644 index 815e067..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/nap.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/retry.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/retry.cpython-312.pyc deleted file mode 100644 index ff956ef..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/retry.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/stop.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/stop.cpython-312.pyc deleted file mode 100644 index 04731f6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/stop.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/tornadoweb.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/tornadoweb.cpython-312.pyc deleted file mode 100644 index c3a7518..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/tornadoweb.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/wait.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/wait.cpython-312.pyc deleted file mode 100644 index f1222f1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/__pycache__/wait.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/_asyncio.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/_asyncio.py deleted file mode 100644 index 2e50cd7..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/_asyncio.py +++ /dev/null @@ -1,94 +0,0 @@ -# Copyright 2016 Étienne Bersac -# Copyright 2016 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import functools -import sys -import typing as t -from asyncio import sleep - -from pip._vendor.tenacity import AttemptManager -from pip._vendor.tenacity import BaseRetrying -from pip._vendor.tenacity import DoAttempt -from pip._vendor.tenacity import DoSleep -from pip._vendor.tenacity import RetryCallState - -WrappedFnReturnT = t.TypeVar("WrappedFnReturnT") -WrappedFn = t.TypeVar("WrappedFn", bound=t.Callable[..., t.Awaitable[t.Any]]) - - -class AsyncRetrying(BaseRetrying): - sleep: t.Callable[[float], t.Awaitable[t.Any]] - - def __init__(self, sleep: t.Callable[[float], t.Awaitable[t.Any]] = sleep, **kwargs: t.Any) -> None: - super().__init__(**kwargs) - self.sleep = sleep - - async def __call__( # type: ignore[override] - self, fn: WrappedFn, *args: t.Any, **kwargs: t.Any - ) -> WrappedFnReturnT: - self.begin() - - retry_state = RetryCallState(retry_object=self, fn=fn, args=args, kwargs=kwargs) - while True: - do = self.iter(retry_state=retry_state) - if isinstance(do, DoAttempt): - try: - result = await fn(*args, **kwargs) - except BaseException: # noqa: B902 - retry_state.set_exception(sys.exc_info()) # type: ignore[arg-type] - else: - retry_state.set_result(result) - elif isinstance(do, DoSleep): - retry_state.prepare_for_next_attempt() - await self.sleep(do) - else: - return do # type: ignore[no-any-return] - - def __iter__(self) -> t.Generator[AttemptManager, None, None]: - raise TypeError("AsyncRetrying object is not iterable") - - def __aiter__(self) -> "AsyncRetrying": - self.begin() - self._retry_state = RetryCallState(self, fn=None, args=(), kwargs={}) - return self - - async def __anext__(self) -> AttemptManager: - while True: - do = self.iter(retry_state=self._retry_state) - if do is None: - raise StopAsyncIteration - elif isinstance(do, DoAttempt): - return AttemptManager(retry_state=self._retry_state) - elif isinstance(do, DoSleep): - self._retry_state.prepare_for_next_attempt() - await self.sleep(do) - else: - raise StopAsyncIteration - - def wraps(self, fn: WrappedFn) -> WrappedFn: - fn = super().wraps(fn) - # Ensure wrapper is recognized as a coroutine function. - - @functools.wraps(fn) - async def async_wrapped(*args: t.Any, **kwargs: t.Any) -> t.Any: - return await fn(*args, **kwargs) - - # Preserve attributes - async_wrapped.retry = fn.retry # type: ignore[attr-defined] - async_wrapped.retry_with = fn.retry_with # type: ignore[attr-defined] - - return async_wrapped # type: ignore[return-value] diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/_utils.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/_utils.py deleted file mode 100644 index f14ff32..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/_utils.py +++ /dev/null @@ -1,76 +0,0 @@ -# Copyright 2016 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import sys -import typing -from datetime import timedelta - - -# sys.maxsize: -# An integer giving the maximum value a variable of type Py_ssize_t can take. -MAX_WAIT = sys.maxsize / 2 - - -def find_ordinal(pos_num: int) -> str: - # See: https://en.wikipedia.org/wiki/English_numerals#Ordinal_numbers - if pos_num == 0: - return "th" - elif pos_num == 1: - return "st" - elif pos_num == 2: - return "nd" - elif pos_num == 3: - return "rd" - elif 4 <= pos_num <= 20: - return "th" - else: - return find_ordinal(pos_num % 10) - - -def to_ordinal(pos_num: int) -> str: - return f"{pos_num}{find_ordinal(pos_num)}" - - -def get_callback_name(cb: typing.Callable[..., typing.Any]) -> str: - """Get a callback fully-qualified name. - - If no name can be produced ``repr(cb)`` is called and returned. - """ - segments = [] - try: - segments.append(cb.__qualname__) - except AttributeError: - try: - segments.append(cb.__name__) - except AttributeError: - pass - if not segments: - return repr(cb) - else: - try: - # When running under sphinx it appears this can be none? - if cb.__module__: - segments.insert(0, cb.__module__) - except AttributeError: - pass - return ".".join(segments) - - -time_unit_type = typing.Union[int, float, timedelta] - - -def to_seconds(time_unit: time_unit_type) -> float: - return float(time_unit.total_seconds() if isinstance(time_unit, timedelta) else time_unit) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/after.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/after.py deleted file mode 100644 index 574c9bc..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/after.py +++ /dev/null @@ -1,51 +0,0 @@ -# Copyright 2016 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import typing - -from pip._vendor.tenacity import _utils - -if typing.TYPE_CHECKING: - import logging - - from pip._vendor.tenacity import RetryCallState - - -def after_nothing(retry_state: "RetryCallState") -> None: - """After call strategy that does nothing.""" - - -def after_log( - logger: "logging.Logger", - log_level: int, - sec_format: str = "%0.3f", -) -> typing.Callable[["RetryCallState"], None]: - """After call strategy that logs to some logger the finished attempt.""" - - def log_it(retry_state: "RetryCallState") -> None: - if retry_state.fn is None: - # NOTE(sileht): can't really happen, but we must please mypy - fn_name = "" - else: - fn_name = _utils.get_callback_name(retry_state.fn) - logger.log( - log_level, - f"Finished call to '{fn_name}' " - f"after {sec_format % retry_state.seconds_since_start}(s), " - f"this was the {_utils.to_ordinal(retry_state.attempt_number)} time calling it.", - ) - - return log_it diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/before.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/before.py deleted file mode 100644 index cfd7dc7..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/before.py +++ /dev/null @@ -1,46 +0,0 @@ -# Copyright 2016 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import typing - -from pip._vendor.tenacity import _utils - -if typing.TYPE_CHECKING: - import logging - - from pip._vendor.tenacity import RetryCallState - - -def before_nothing(retry_state: "RetryCallState") -> None: - """Before call strategy that does nothing.""" - - -def before_log(logger: "logging.Logger", log_level: int) -> typing.Callable[["RetryCallState"], None]: - """Before call strategy that logs to some logger the attempt.""" - - def log_it(retry_state: "RetryCallState") -> None: - if retry_state.fn is None: - # NOTE(sileht): can't really happen, but we must please mypy - fn_name = "" - else: - fn_name = _utils.get_callback_name(retry_state.fn) - logger.log( - log_level, - f"Starting call to '{fn_name}', " - f"this is the {_utils.to_ordinal(retry_state.attempt_number)} time calling it.", - ) - - return log_it diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/before_sleep.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/before_sleep.py deleted file mode 100644 index 8c6167f..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/before_sleep.py +++ /dev/null @@ -1,71 +0,0 @@ -# Copyright 2016 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import typing - -from pip._vendor.tenacity import _utils - -if typing.TYPE_CHECKING: - import logging - - from pip._vendor.tenacity import RetryCallState - - -def before_sleep_nothing(retry_state: "RetryCallState") -> None: - """Before call strategy that does nothing.""" - - -def before_sleep_log( - logger: "logging.Logger", - log_level: int, - exc_info: bool = False, -) -> typing.Callable[["RetryCallState"], None]: - """Before call strategy that logs to some logger the attempt.""" - - def log_it(retry_state: "RetryCallState") -> None: - local_exc_info: BaseException | bool | None - - if retry_state.outcome is None: - raise RuntimeError("log_it() called before outcome was set") - - if retry_state.next_action is None: - raise RuntimeError("log_it() called before next_action was set") - - if retry_state.outcome.failed: - ex = retry_state.outcome.exception() - verb, value = "raised", f"{ex.__class__.__name__}: {ex}" - - if exc_info: - local_exc_info = retry_state.outcome.exception() - else: - local_exc_info = False - else: - verb, value = "returned", retry_state.outcome.result() - local_exc_info = False # exc_info does not apply when no exception - - if retry_state.fn is None: - # NOTE(sileht): can't really happen, but we must please mypy - fn_name = "" - else: - fn_name = _utils.get_callback_name(retry_state.fn) - - logger.log( - log_level, - f"Retrying {fn_name} " f"in {retry_state.next_action.sleep} seconds as it {verb} {value}.", - exc_info=local_exc_info, - ) - - return log_it diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/nap.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/nap.py deleted file mode 100644 index 72aa5bf..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/nap.py +++ /dev/null @@ -1,43 +0,0 @@ -# Copyright 2016 Étienne Bersac -# Copyright 2016 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import time -import typing - -if typing.TYPE_CHECKING: - import threading - - -def sleep(seconds: float) -> None: - """ - Sleep strategy that delays execution for a given number of seconds. - - This is the default strategy, and may be mocked out for unit testing. - """ - time.sleep(seconds) - - -class sleep_using_event: - """Sleep strategy that waits on an event to be set.""" - - def __init__(self, event: "threading.Event") -> None: - self.event = event - - def __call__(self, timeout: typing.Optional[float]) -> None: - # NOTE(harlowja): this may *not* actually wait for timeout - # seconds if the event is set (ie this may eject out early). - self.event.wait(timeout=timeout) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/retry.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/retry.py deleted file mode 100644 index 3898873..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/retry.py +++ /dev/null @@ -1,272 +0,0 @@ -# Copyright 2016–2021 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import abc -import re -import typing - -if typing.TYPE_CHECKING: - from pip._vendor.tenacity import RetryCallState - - -class retry_base(abc.ABC): - """Abstract base class for retry strategies.""" - - @abc.abstractmethod - def __call__(self, retry_state: "RetryCallState") -> bool: - pass - - def __and__(self, other: "retry_base") -> "retry_all": - return retry_all(self, other) - - def __or__(self, other: "retry_base") -> "retry_any": - return retry_any(self, other) - - -RetryBaseT = typing.Union[retry_base, typing.Callable[["RetryCallState"], bool]] - - -class _retry_never(retry_base): - """Retry strategy that never rejects any result.""" - - def __call__(self, retry_state: "RetryCallState") -> bool: - return False - - -retry_never = _retry_never() - - -class _retry_always(retry_base): - """Retry strategy that always rejects any result.""" - - def __call__(self, retry_state: "RetryCallState") -> bool: - return True - - -retry_always = _retry_always() - - -class retry_if_exception(retry_base): - """Retry strategy that retries if an exception verifies a predicate.""" - - def __init__(self, predicate: typing.Callable[[BaseException], bool]) -> None: - self.predicate = predicate - - def __call__(self, retry_state: "RetryCallState") -> bool: - if retry_state.outcome is None: - raise RuntimeError("__call__() called before outcome was set") - - if retry_state.outcome.failed: - exception = retry_state.outcome.exception() - if exception is None: - raise RuntimeError("outcome failed but the exception is None") - return self.predicate(exception) - else: - return False - - -class retry_if_exception_type(retry_if_exception): - """Retries if an exception has been raised of one or more types.""" - - def __init__( - self, - exception_types: typing.Union[ - typing.Type[BaseException], - typing.Tuple[typing.Type[BaseException], ...], - ] = Exception, - ) -> None: - self.exception_types = exception_types - super().__init__(lambda e: isinstance(e, exception_types)) - - -class retry_if_not_exception_type(retry_if_exception): - """Retries except an exception has been raised of one or more types.""" - - def __init__( - self, - exception_types: typing.Union[ - typing.Type[BaseException], - typing.Tuple[typing.Type[BaseException], ...], - ] = Exception, - ) -> None: - self.exception_types = exception_types - super().__init__(lambda e: not isinstance(e, exception_types)) - - -class retry_unless_exception_type(retry_if_exception): - """Retries until an exception is raised of one or more types.""" - - def __init__( - self, - exception_types: typing.Union[ - typing.Type[BaseException], - typing.Tuple[typing.Type[BaseException], ...], - ] = Exception, - ) -> None: - self.exception_types = exception_types - super().__init__(lambda e: not isinstance(e, exception_types)) - - def __call__(self, retry_state: "RetryCallState") -> bool: - if retry_state.outcome is None: - raise RuntimeError("__call__() called before outcome was set") - - # always retry if no exception was raised - if not retry_state.outcome.failed: - return True - - exception = retry_state.outcome.exception() - if exception is None: - raise RuntimeError("outcome failed but the exception is None") - return self.predicate(exception) - - -class retry_if_exception_cause_type(retry_base): - """Retries if any of the causes of the raised exception is of one or more types. - - The check on the type of the cause of the exception is done recursively (until finding - an exception in the chain that has no `__cause__`) - """ - - def __init__( - self, - exception_types: typing.Union[ - typing.Type[BaseException], - typing.Tuple[typing.Type[BaseException], ...], - ] = Exception, - ) -> None: - self.exception_cause_types = exception_types - - def __call__(self, retry_state: "RetryCallState") -> bool: - if retry_state.outcome is None: - raise RuntimeError("__call__ called before outcome was set") - - if retry_state.outcome.failed: - exc = retry_state.outcome.exception() - while exc is not None: - if isinstance(exc.__cause__, self.exception_cause_types): - return True - exc = exc.__cause__ - - return False - - -class retry_if_result(retry_base): - """Retries if the result verifies a predicate.""" - - def __init__(self, predicate: typing.Callable[[typing.Any], bool]) -> None: - self.predicate = predicate - - def __call__(self, retry_state: "RetryCallState") -> bool: - if retry_state.outcome is None: - raise RuntimeError("__call__() called before outcome was set") - - if not retry_state.outcome.failed: - return self.predicate(retry_state.outcome.result()) - else: - return False - - -class retry_if_not_result(retry_base): - """Retries if the result refutes a predicate.""" - - def __init__(self, predicate: typing.Callable[[typing.Any], bool]) -> None: - self.predicate = predicate - - def __call__(self, retry_state: "RetryCallState") -> bool: - if retry_state.outcome is None: - raise RuntimeError("__call__() called before outcome was set") - - if not retry_state.outcome.failed: - return not self.predicate(retry_state.outcome.result()) - else: - return False - - -class retry_if_exception_message(retry_if_exception): - """Retries if an exception message equals or matches.""" - - def __init__( - self, - message: typing.Optional[str] = None, - match: typing.Optional[str] = None, - ) -> None: - if message and match: - raise TypeError(f"{self.__class__.__name__}() takes either 'message' or 'match', not both") - - # set predicate - if message: - - def message_fnc(exception: BaseException) -> bool: - return message == str(exception) - - predicate = message_fnc - elif match: - prog = re.compile(match) - - def match_fnc(exception: BaseException) -> bool: - return bool(prog.match(str(exception))) - - predicate = match_fnc - else: - raise TypeError(f"{self.__class__.__name__}() missing 1 required argument 'message' or 'match'") - - super().__init__(predicate) - - -class retry_if_not_exception_message(retry_if_exception_message): - """Retries until an exception message equals or matches.""" - - def __init__( - self, - message: typing.Optional[str] = None, - match: typing.Optional[str] = None, - ) -> None: - super().__init__(message, match) - # invert predicate - if_predicate = self.predicate - self.predicate = lambda *args_, **kwargs_: not if_predicate(*args_, **kwargs_) - - def __call__(self, retry_state: "RetryCallState") -> bool: - if retry_state.outcome is None: - raise RuntimeError("__call__() called before outcome was set") - - if not retry_state.outcome.failed: - return True - - exception = retry_state.outcome.exception() - if exception is None: - raise RuntimeError("outcome failed but the exception is None") - return self.predicate(exception) - - -class retry_any(retry_base): - """Retries if any of the retries condition is valid.""" - - def __init__(self, *retries: retry_base) -> None: - self.retries = retries - - def __call__(self, retry_state: "RetryCallState") -> bool: - return any(r(retry_state) for r in self.retries) - - -class retry_all(retry_base): - """Retries if all the retries condition are valid.""" - - def __init__(self, *retries: retry_base) -> None: - self.retries = retries - - def __call__(self, retry_state: "RetryCallState") -> bool: - return all(r(retry_state) for r in self.retries) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/stop.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/stop.py deleted file mode 100644 index bb23eff..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/stop.py +++ /dev/null @@ -1,103 +0,0 @@ -# Copyright 2016–2021 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -import abc -import typing - -from pip._vendor.tenacity import _utils - -if typing.TYPE_CHECKING: - import threading - - from pip._vendor.tenacity import RetryCallState - - -class stop_base(abc.ABC): - """Abstract base class for stop strategies.""" - - @abc.abstractmethod - def __call__(self, retry_state: "RetryCallState") -> bool: - pass - - def __and__(self, other: "stop_base") -> "stop_all": - return stop_all(self, other) - - def __or__(self, other: "stop_base") -> "stop_any": - return stop_any(self, other) - - -StopBaseT = typing.Union[stop_base, typing.Callable[["RetryCallState"], bool]] - - -class stop_any(stop_base): - """Stop if any of the stop condition is valid.""" - - def __init__(self, *stops: stop_base) -> None: - self.stops = stops - - def __call__(self, retry_state: "RetryCallState") -> bool: - return any(x(retry_state) for x in self.stops) - - -class stop_all(stop_base): - """Stop if all the stop conditions are valid.""" - - def __init__(self, *stops: stop_base) -> None: - self.stops = stops - - def __call__(self, retry_state: "RetryCallState") -> bool: - return all(x(retry_state) for x in self.stops) - - -class _stop_never(stop_base): - """Never stop.""" - - def __call__(self, retry_state: "RetryCallState") -> bool: - return False - - -stop_never = _stop_never() - - -class stop_when_event_set(stop_base): - """Stop when the given event is set.""" - - def __init__(self, event: "threading.Event") -> None: - self.event = event - - def __call__(self, retry_state: "RetryCallState") -> bool: - return self.event.is_set() - - -class stop_after_attempt(stop_base): - """Stop when the previous attempt >= max_attempt.""" - - def __init__(self, max_attempt_number: int) -> None: - self.max_attempt_number = max_attempt_number - - def __call__(self, retry_state: "RetryCallState") -> bool: - return retry_state.attempt_number >= self.max_attempt_number - - -class stop_after_delay(stop_base): - """Stop when the time from the first attempt >= limit.""" - - def __init__(self, max_delay: _utils.time_unit_type) -> None: - self.max_delay = _utils.to_seconds(max_delay) - - def __call__(self, retry_state: "RetryCallState") -> bool: - if retry_state.seconds_since_start is None: - raise RuntimeError("__call__() called but seconds_since_start is not set") - return retry_state.seconds_since_start >= self.max_delay diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/tornadoweb.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/tornadoweb.py deleted file mode 100644 index e19c30b..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/tornadoweb.py +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright 2017 Elisey Zanko -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import sys -import typing - -from pip._vendor.tenacity import BaseRetrying -from pip._vendor.tenacity import DoAttempt -from pip._vendor.tenacity import DoSleep -from pip._vendor.tenacity import RetryCallState - -from tornado import gen - -if typing.TYPE_CHECKING: - from tornado.concurrent import Future - -_RetValT = typing.TypeVar("_RetValT") - - -class TornadoRetrying(BaseRetrying): - def __init__(self, sleep: "typing.Callable[[float], Future[None]]" = gen.sleep, **kwargs: typing.Any) -> None: - super().__init__(**kwargs) - self.sleep = sleep - - @gen.coroutine # type: ignore[misc] - def __call__( - self, - fn: "typing.Callable[..., typing.Union[typing.Generator[typing.Any, typing.Any, _RetValT], Future[_RetValT]]]", - *args: typing.Any, - **kwargs: typing.Any, - ) -> "typing.Generator[typing.Any, typing.Any, _RetValT]": - self.begin() - - retry_state = RetryCallState(retry_object=self, fn=fn, args=args, kwargs=kwargs) - while True: - do = self.iter(retry_state=retry_state) - if isinstance(do, DoAttempt): - try: - result = yield fn(*args, **kwargs) - except BaseException: # noqa: B902 - retry_state.set_exception(sys.exc_info()) # type: ignore[arg-type] - else: - retry_state.set_result(result) - elif isinstance(do, DoSleep): - retry_state.prepare_for_next_attempt() - yield self.sleep(do) - else: - raise gen.Return(do) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/wait.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/wait.py deleted file mode 100644 index f9349c0..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tenacity/wait.py +++ /dev/null @@ -1,228 +0,0 @@ -# Copyright 2016–2021 Julien Danjou -# Copyright 2016 Joshua Harlow -# Copyright 2013-2014 Ray Holder -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -import abc -import random -import typing - -from pip._vendor.tenacity import _utils - -if typing.TYPE_CHECKING: - from pip._vendor.tenacity import RetryCallState - - -class wait_base(abc.ABC): - """Abstract base class for wait strategies.""" - - @abc.abstractmethod - def __call__(self, retry_state: "RetryCallState") -> float: - pass - - def __add__(self, other: "wait_base") -> "wait_combine": - return wait_combine(self, other) - - def __radd__(self, other: "wait_base") -> typing.Union["wait_combine", "wait_base"]: - # make it possible to use multiple waits with the built-in sum function - if other == 0: # type: ignore[comparison-overlap] - return self - return self.__add__(other) - - -WaitBaseT = typing.Union[wait_base, typing.Callable[["RetryCallState"], typing.Union[float, int]]] - - -class wait_fixed(wait_base): - """Wait strategy that waits a fixed amount of time between each retry.""" - - def __init__(self, wait: _utils.time_unit_type) -> None: - self.wait_fixed = _utils.to_seconds(wait) - - def __call__(self, retry_state: "RetryCallState") -> float: - return self.wait_fixed - - -class wait_none(wait_fixed): - """Wait strategy that doesn't wait at all before retrying.""" - - def __init__(self) -> None: - super().__init__(0) - - -class wait_random(wait_base): - """Wait strategy that waits a random amount of time between min/max.""" - - def __init__(self, min: _utils.time_unit_type = 0, max: _utils.time_unit_type = 1) -> None: # noqa - self.wait_random_min = _utils.to_seconds(min) - self.wait_random_max = _utils.to_seconds(max) - - def __call__(self, retry_state: "RetryCallState") -> float: - return self.wait_random_min + (random.random() * (self.wait_random_max - self.wait_random_min)) - - -class wait_combine(wait_base): - """Combine several waiting strategies.""" - - def __init__(self, *strategies: wait_base) -> None: - self.wait_funcs = strategies - - def __call__(self, retry_state: "RetryCallState") -> float: - return sum(x(retry_state=retry_state) for x in self.wait_funcs) - - -class wait_chain(wait_base): - """Chain two or more waiting strategies. - - If all strategies are exhausted, the very last strategy is used - thereafter. - - For example:: - - @retry(wait=wait_chain(*[wait_fixed(1) for i in range(3)] + - [wait_fixed(2) for j in range(5)] + - [wait_fixed(5) for k in range(4))) - def wait_chained(): - print("Wait 1s for 3 attempts, 2s for 5 attempts and 5s - thereafter.") - """ - - def __init__(self, *strategies: wait_base) -> None: - self.strategies = strategies - - def __call__(self, retry_state: "RetryCallState") -> float: - wait_func_no = min(max(retry_state.attempt_number, 1), len(self.strategies)) - wait_func = self.strategies[wait_func_no - 1] - return wait_func(retry_state=retry_state) - - -class wait_incrementing(wait_base): - """Wait an incremental amount of time after each attempt. - - Starting at a starting value and incrementing by a value for each attempt - (and restricting the upper limit to some maximum value). - """ - - def __init__( - self, - start: _utils.time_unit_type = 0, - increment: _utils.time_unit_type = 100, - max: _utils.time_unit_type = _utils.MAX_WAIT, # noqa - ) -> None: - self.start = _utils.to_seconds(start) - self.increment = _utils.to_seconds(increment) - self.max = _utils.to_seconds(max) - - def __call__(self, retry_state: "RetryCallState") -> float: - result = self.start + (self.increment * (retry_state.attempt_number - 1)) - return max(0, min(result, self.max)) - - -class wait_exponential(wait_base): - """Wait strategy that applies exponential backoff. - - It allows for a customized multiplier and an ability to restrict the - upper and lower limits to some maximum and minimum value. - - The intervals are fixed (i.e. there is no jitter), so this strategy is - suitable for balancing retries against latency when a required resource is - unavailable for an unknown duration, but *not* suitable for resolving - contention between multiple processes for a shared resource. Use - wait_random_exponential for the latter case. - """ - - def __init__( - self, - multiplier: typing.Union[int, float] = 1, - max: _utils.time_unit_type = _utils.MAX_WAIT, # noqa - exp_base: typing.Union[int, float] = 2, - min: _utils.time_unit_type = 0, # noqa - ) -> None: - self.multiplier = multiplier - self.min = _utils.to_seconds(min) - self.max = _utils.to_seconds(max) - self.exp_base = exp_base - - def __call__(self, retry_state: "RetryCallState") -> float: - try: - exp = self.exp_base ** (retry_state.attempt_number - 1) - result = self.multiplier * exp - except OverflowError: - return self.max - return max(max(0, self.min), min(result, self.max)) - - -class wait_random_exponential(wait_exponential): - """Random wait with exponentially widening window. - - An exponential backoff strategy used to mediate contention between multiple - uncoordinated processes for a shared resource in distributed systems. This - is the sense in which "exponential backoff" is meant in e.g. Ethernet - networking, and corresponds to the "Full Jitter" algorithm described in - this blog post: - - https://aws.amazon.com/blogs/architecture/exponential-backoff-and-jitter/ - - Each retry occurs at a random time in a geometrically expanding interval. - It allows for a custom multiplier and an ability to restrict the upper - limit of the random interval to some maximum value. - - Example:: - - wait_random_exponential(multiplier=0.5, # initial window 0.5s - max=60) # max 60s timeout - - When waiting for an unavailable resource to become available again, as - opposed to trying to resolve contention for a shared resource, the - wait_exponential strategy (which uses a fixed interval) may be preferable. - - """ - - def __call__(self, retry_state: "RetryCallState") -> float: - high = super().__call__(retry_state=retry_state) - return random.uniform(0, high) - - -class wait_exponential_jitter(wait_base): - """Wait strategy that applies exponential backoff and jitter. - - It allows for a customized initial wait, maximum wait and jitter. - - This implements the strategy described here: - https://cloud.google.com/storage/docs/retry-strategy - - The wait time is min(initial * 2**n + random.uniform(0, jitter), maximum) - where n is the retry count. - """ - - def __init__( - self, - initial: float = 1, - max: float = _utils.MAX_WAIT, # noqa - exp_base: float = 2, - jitter: float = 1, - ) -> None: - self.initial = initial - self.max = max - self.exp_base = exp_base - self.jitter = jitter - - def __call__(self, retry_state: "RetryCallState") -> float: - jitter = random.uniform(0, self.jitter) - try: - exp = self.exp_base ** (retry_state.attempt_number - 1) - result = self.initial * exp + jitter - except OverflowError: - result = self.max - return max(0, min(result, self.max)) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__init__.py index 4c6ec97..2b08d6e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__init__.py @@ -3,9 +3,6 @@ # Licensed to PSF under a Contributor Agreement. __all__ = ("loads", "load", "TOMLDecodeError") -__version__ = "2.0.1" # DO NOT EDIT THIS LINE MANUALLY. LET bump2version UTILITY DO IT +__version__ = "2.2.1" # DO NOT EDIT THIS LINE MANUALLY. LET bump2version UTILITY DO IT from ._parser import TOMLDecodeError, load, loads - -# Pretend this exception was created here. -TOMLDecodeError.__module__ = __name__ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/__init__.cpython-312.pyc index f6adba6..f9a3bfa 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_parser.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_parser.cpython-312.pyc index b602fcb..9538281 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_parser.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_parser.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_re.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_re.cpython-312.pyc index 0461bbe..2784d5f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_re.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_re.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_types.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_types.cpython-312.pyc index 075f635..9db7714 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_types.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/__pycache__/_types.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_parser.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_parser.py index f1bb0aa..b548e8b 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_parser.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_parser.py @@ -6,8 +6,10 @@ from __future__ import annotations from collections.abc import Iterable import string +import sys from types import MappingProxyType -from typing import Any, BinaryIO, NamedTuple +from typing import IO, Any, Final, NamedTuple +import warnings from ._re import ( RE_DATETIME, @@ -19,25 +21,36 @@ from ._re import ( ) from ._types import Key, ParseFloat, Pos -ASCII_CTRL = frozenset(chr(i) for i in range(32)) | frozenset(chr(127)) +# Inline tables/arrays are implemented using recursion. Pathologically +# nested documents cause pure Python to raise RecursionError (which is OK), +# but mypyc binary wheels will crash unrecoverably (not OK). According to +# mypyc docs this will be fixed in the future: +# https://mypyc.readthedocs.io/en/latest/differences_from_python.html#stack-overflows +# Before mypyc's fix is in, recursion needs to be limited by this library. +# Choosing `sys.getrecursionlimit()` as maximum inline table/array nesting +# level, as it allows more nesting than pure Python, but still seems a far +# lower number than where mypyc binaries crash. +MAX_INLINE_NESTING: Final = sys.getrecursionlimit() + +ASCII_CTRL: Final = frozenset(chr(i) for i in range(32)) | frozenset(chr(127)) # Neither of these sets include quotation mark or backslash. They are # currently handled as separate cases in the parser functions. -ILLEGAL_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t") -ILLEGAL_MULTILINE_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t\n") +ILLEGAL_BASIC_STR_CHARS: Final = ASCII_CTRL - frozenset("\t") +ILLEGAL_MULTILINE_BASIC_STR_CHARS: Final = ASCII_CTRL - frozenset("\t\n") -ILLEGAL_LITERAL_STR_CHARS = ILLEGAL_BASIC_STR_CHARS -ILLEGAL_MULTILINE_LITERAL_STR_CHARS = ILLEGAL_MULTILINE_BASIC_STR_CHARS +ILLEGAL_LITERAL_STR_CHARS: Final = ILLEGAL_BASIC_STR_CHARS +ILLEGAL_MULTILINE_LITERAL_STR_CHARS: Final = ILLEGAL_MULTILINE_BASIC_STR_CHARS -ILLEGAL_COMMENT_CHARS = ILLEGAL_BASIC_STR_CHARS +ILLEGAL_COMMENT_CHARS: Final = ILLEGAL_BASIC_STR_CHARS -TOML_WS = frozenset(" \t") -TOML_WS_AND_NEWLINE = TOML_WS | frozenset("\n") -BARE_KEY_CHARS = frozenset(string.ascii_letters + string.digits + "-_") -KEY_INITIAL_CHARS = BARE_KEY_CHARS | frozenset("\"'") -HEXDIGIT_CHARS = frozenset(string.hexdigits) +TOML_WS: Final = frozenset(" \t") +TOML_WS_AND_NEWLINE: Final = TOML_WS | frozenset("\n") +BARE_KEY_CHARS: Final = frozenset(string.ascii_letters + string.digits + "-_") +KEY_INITIAL_CHARS: Final = BARE_KEY_CHARS | frozenset("\"'") +HEXDIGIT_CHARS: Final = frozenset(string.hexdigits) -BASIC_STR_ESCAPE_REPLACEMENTS = MappingProxyType( +BASIC_STR_ESCAPE_REPLACEMENTS: Final = MappingProxyType( { "\\b": "\u0008", # backspace "\\t": "\u0009", # tab @@ -50,11 +63,71 @@ BASIC_STR_ESCAPE_REPLACEMENTS = MappingProxyType( ) +class DEPRECATED_DEFAULT: + """Sentinel to be used as default arg during deprecation + period of TOMLDecodeError's free-form arguments.""" + + class TOMLDecodeError(ValueError): - """An error raised if a document is not valid TOML.""" + """An error raised if a document is not valid TOML. + + Adds the following attributes to ValueError: + msg: The unformatted error message + doc: The TOML document being parsed + pos: The index of doc where parsing failed + lineno: The line corresponding to pos + colno: The column corresponding to pos + """ + + def __init__( + self, + msg: str | type[DEPRECATED_DEFAULT] = DEPRECATED_DEFAULT, + doc: str | type[DEPRECATED_DEFAULT] = DEPRECATED_DEFAULT, + pos: Pos | type[DEPRECATED_DEFAULT] = DEPRECATED_DEFAULT, + *args: Any, + ): + if ( + args + or not isinstance(msg, str) + or not isinstance(doc, str) + or not isinstance(pos, int) + ): + warnings.warn( + "Free-form arguments for TOMLDecodeError are deprecated. " + "Please set 'msg' (str), 'doc' (str) and 'pos' (int) arguments only.", + DeprecationWarning, + stacklevel=2, + ) + if pos is not DEPRECATED_DEFAULT: + args = pos, *args + if doc is not DEPRECATED_DEFAULT: + args = doc, *args + if msg is not DEPRECATED_DEFAULT: + args = msg, *args + ValueError.__init__(self, *args) + return + + lineno = doc.count("\n", 0, pos) + 1 + if lineno == 1: + colno = pos + 1 + else: + colno = pos - doc.rindex("\n", 0, pos) + + if pos >= len(doc): + coord_repr = "end of document" + else: + coord_repr = f"line {lineno}, column {colno}" + errmsg = f"{msg} (at {coord_repr})" + ValueError.__init__(self, errmsg) + + self.msg = msg + self.doc = doc + self.pos = pos + self.lineno = lineno + self.colno = colno -def load(__fp: BinaryIO, *, parse_float: ParseFloat = float) -> dict[str, Any]: +def load(__fp: IO[bytes], *, parse_float: ParseFloat = float) -> dict[str, Any]: """Parse TOML from a binary file object.""" b = __fp.read() try: @@ -71,7 +144,12 @@ def loads(__s: str, *, parse_float: ParseFloat = float) -> dict[str, Any]: # no # The spec allows converting "\r\n" to "\n", even in string # literals. Let's do so to simplify parsing. - src = __s.replace("\r\n", "\n") + try: + src = __s.replace("\r\n", "\n") + except (AttributeError, TypeError): + raise TypeError( + f"Expected str object, not '{type(__s).__qualname__}'" + ) from None pos = 0 out = Output(NestedDict(), Flags()) header: Key = () @@ -113,7 +191,7 @@ def loads(__s: str, *, parse_float: ParseFloat = float) -> dict[str, Any]: # no pos, header = create_dict_rule(src, pos, out) pos = skip_chars(src, pos, TOML_WS) elif char != "#": - raise suffixed_err(src, pos, "Invalid statement") + raise TOMLDecodeError("Invalid statement", src, pos) # 3. Skip comment pos = skip_comment(src, pos) @@ -124,8 +202,8 @@ def loads(__s: str, *, parse_float: ParseFloat = float) -> dict[str, Any]: # no except IndexError: break if char != "\n": - raise suffixed_err( - src, pos, "Expected newline or end of document after a statement" + raise TOMLDecodeError( + "Expected newline or end of document after a statement", src, pos ) pos += 1 @@ -136,10 +214,10 @@ class Flags: """Flags that map to parsed keys/namespaces.""" # Marks an immutable namespace (inline array or inline table). - FROZEN = 0 + FROZEN: Final = 0 # Marks a nest that has been explicitly created and can no longer # be opened using the "[table]" syntax. - EXPLICIT_NEST = 1 + EXPLICIT_NEST: Final = 1 def __init__(self) -> None: self._flags: dict[str, dict] = {} @@ -185,8 +263,8 @@ class Flags: cont = inner_cont["nested"] key_stem = key[-1] if key_stem in cont: - cont = cont[key_stem] - return flag in cont["flags"] or flag in cont["recursive_flags"] + inner_cont = cont[key_stem] + return flag in inner_cont["flags"] or flag in inner_cont["recursive_flags"] return False @@ -251,12 +329,12 @@ def skip_until( except ValueError: new_pos = len(src) if error_on_eof: - raise suffixed_err(src, new_pos, f"Expected {expect!r}") from None + raise TOMLDecodeError(f"Expected {expect!r}", src, new_pos) from None if not error_on.isdisjoint(src[pos:new_pos]): while src[pos] not in error_on: pos += 1 - raise suffixed_err(src, pos, f"Found invalid character {src[pos]!r}") + raise TOMLDecodeError(f"Found invalid character {src[pos]!r}", src, pos) return new_pos @@ -287,15 +365,17 @@ def create_dict_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]: pos, key = parse_key(src, pos) if out.flags.is_(key, Flags.EXPLICIT_NEST) or out.flags.is_(key, Flags.FROZEN): - raise suffixed_err(src, pos, f"Cannot declare {key} twice") + raise TOMLDecodeError(f"Cannot declare {key} twice", src, pos) out.flags.set(key, Flags.EXPLICIT_NEST, recursive=False) try: out.data.get_or_create_nest(key) except KeyError: - raise suffixed_err(src, pos, "Cannot overwrite a value") from None + raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None if not src.startswith("]", pos): - raise suffixed_err(src, pos, "Expected ']' at the end of a table declaration") + raise TOMLDecodeError( + "Expected ']' at the end of a table declaration", src, pos + ) return pos + 1, key @@ -305,7 +385,7 @@ def create_list_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]: pos, key = parse_key(src, pos) if out.flags.is_(key, Flags.FROZEN): - raise suffixed_err(src, pos, f"Cannot mutate immutable namespace {key}") + raise TOMLDecodeError(f"Cannot mutate immutable namespace {key}", src, pos) # Free the namespace now that it points to another empty list item... out.flags.unset_all(key) # ...but this key precisely is still prohibited from table declaration @@ -313,17 +393,19 @@ def create_list_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]: try: out.data.append_nest_to_list(key) except KeyError: - raise suffixed_err(src, pos, "Cannot overwrite a value") from None + raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None if not src.startswith("]]", pos): - raise suffixed_err(src, pos, "Expected ']]' at the end of an array declaration") + raise TOMLDecodeError( + "Expected ']]' at the end of an array declaration", src, pos + ) return pos + 2, key def key_value_rule( src: str, pos: Pos, out: Output, header: Key, parse_float: ParseFloat ) -> Pos: - pos, key, value = parse_key_value_pair(src, pos, parse_float) + pos, key, value = parse_key_value_pair(src, pos, parse_float, nest_lvl=0) key_parent, key_stem = key[:-1], key[-1] abs_key_parent = header + key_parent @@ -331,22 +413,22 @@ def key_value_rule( for cont_key in relative_path_cont_keys: # Check that dotted key syntax does not redefine an existing table if out.flags.is_(cont_key, Flags.EXPLICIT_NEST): - raise suffixed_err(src, pos, f"Cannot redefine namespace {cont_key}") + raise TOMLDecodeError(f"Cannot redefine namespace {cont_key}", src, pos) # Containers in the relative path can't be opened with the table syntax or # dotted key/value syntax in following table sections. out.flags.add_pending(cont_key, Flags.EXPLICIT_NEST) if out.flags.is_(abs_key_parent, Flags.FROZEN): - raise suffixed_err( - src, pos, f"Cannot mutate immutable namespace {abs_key_parent}" + raise TOMLDecodeError( + f"Cannot mutate immutable namespace {abs_key_parent}", src, pos ) try: nest = out.data.get_or_create_nest(abs_key_parent) except KeyError: - raise suffixed_err(src, pos, "Cannot overwrite a value") from None + raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None if key_stem in nest: - raise suffixed_err(src, pos, "Cannot overwrite a value") + raise TOMLDecodeError("Cannot overwrite a value", src, pos) # Mark inline table and array namespaces recursively immutable if isinstance(value, (dict, list)): out.flags.set(header + key, Flags.FROZEN, recursive=True) @@ -355,7 +437,7 @@ def key_value_rule( def parse_key_value_pair( - src: str, pos: Pos, parse_float: ParseFloat + src: str, pos: Pos, parse_float: ParseFloat, nest_lvl: int ) -> tuple[Pos, Key, Any]: pos, key = parse_key(src, pos) try: @@ -363,10 +445,10 @@ def parse_key_value_pair( except IndexError: char = None if char != "=": - raise suffixed_err(src, pos, "Expected '=' after a key in a key/value pair") + raise TOMLDecodeError("Expected '=' after a key in a key/value pair", src, pos) pos += 1 pos = skip_chars(src, pos, TOML_WS) - pos, value = parse_value(src, pos, parse_float) + pos, value = parse_value(src, pos, parse_float, nest_lvl) return pos, key, value @@ -401,7 +483,7 @@ def parse_key_part(src: str, pos: Pos) -> tuple[Pos, str]: return parse_literal_str(src, pos) if char == '"': return parse_one_line_basic_str(src, pos) - raise suffixed_err(src, pos, "Invalid initial character for a key part") + raise TOMLDecodeError("Invalid initial character for a key part", src, pos) def parse_one_line_basic_str(src: str, pos: Pos) -> tuple[Pos, str]: @@ -409,7 +491,9 @@ def parse_one_line_basic_str(src: str, pos: Pos) -> tuple[Pos, str]: return parse_basic_str(src, pos, multiline=False) -def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, list]: +def parse_array( + src: str, pos: Pos, parse_float: ParseFloat, nest_lvl: int +) -> tuple[Pos, list]: pos += 1 array: list = [] @@ -417,7 +501,7 @@ def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, list] if src.startswith("]", pos): return pos + 1, array while True: - pos, val = parse_value(src, pos, parse_float) + pos, val = parse_value(src, pos, parse_float, nest_lvl) array.append(val) pos = skip_comments_and_array_ws(src, pos) @@ -425,7 +509,7 @@ def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, list] if c == "]": return pos + 1, array if c != ",": - raise suffixed_err(src, pos, "Unclosed array") + raise TOMLDecodeError("Unclosed array", src, pos) pos += 1 pos = skip_comments_and_array_ws(src, pos) @@ -433,7 +517,9 @@ def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, list] return pos + 1, array -def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, dict]: +def parse_inline_table( + src: str, pos: Pos, parse_float: ParseFloat, nest_lvl: int +) -> tuple[Pos, dict]: pos += 1 nested_dict = NestedDict() flags = Flags() @@ -442,23 +528,23 @@ def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos if src.startswith("}", pos): return pos + 1, nested_dict.dict while True: - pos, key, value = parse_key_value_pair(src, pos, parse_float) + pos, key, value = parse_key_value_pair(src, pos, parse_float, nest_lvl) key_parent, key_stem = key[:-1], key[-1] if flags.is_(key, Flags.FROZEN): - raise suffixed_err(src, pos, f"Cannot mutate immutable namespace {key}") + raise TOMLDecodeError(f"Cannot mutate immutable namespace {key}", src, pos) try: nest = nested_dict.get_or_create_nest(key_parent, access_lists=False) except KeyError: - raise suffixed_err(src, pos, "Cannot overwrite a value") from None + raise TOMLDecodeError("Cannot overwrite a value", src, pos) from None if key_stem in nest: - raise suffixed_err(src, pos, f"Duplicate inline table key {key_stem!r}") + raise TOMLDecodeError(f"Duplicate inline table key {key_stem!r}", src, pos) nest[key_stem] = value pos = skip_chars(src, pos, TOML_WS) c = src[pos : pos + 1] if c == "}": return pos + 1, nested_dict.dict if c != ",": - raise suffixed_err(src, pos, "Unclosed inline table") + raise TOMLDecodeError("Unclosed inline table", src, pos) if isinstance(value, (dict, list)): flags.set(key, Flags.FROZEN, recursive=True) pos += 1 @@ -480,7 +566,7 @@ def parse_basic_str_escape( except IndexError: return pos, "" if char != "\n": - raise suffixed_err(src, pos, "Unescaped '\\' in a string") + raise TOMLDecodeError("Unescaped '\\' in a string", src, pos) pos += 1 pos = skip_chars(src, pos, TOML_WS_AND_NEWLINE) return pos, "" @@ -491,7 +577,7 @@ def parse_basic_str_escape( try: return pos, BASIC_STR_ESCAPE_REPLACEMENTS[escape_id] except KeyError: - raise suffixed_err(src, pos, "Unescaped '\\' in a string") from None + raise TOMLDecodeError("Unescaped '\\' in a string", src, pos) from None def parse_basic_str_escape_multiline(src: str, pos: Pos) -> tuple[Pos, str]: @@ -501,11 +587,13 @@ def parse_basic_str_escape_multiline(src: str, pos: Pos) -> tuple[Pos, str]: def parse_hex_char(src: str, pos: Pos, hex_len: int) -> tuple[Pos, str]: hex_str = src[pos : pos + hex_len] if len(hex_str) != hex_len or not HEXDIGIT_CHARS.issuperset(hex_str): - raise suffixed_err(src, pos, "Invalid hex value") + raise TOMLDecodeError("Invalid hex value", src, pos) pos += hex_len hex_int = int(hex_str, 16) if not is_unicode_scalar_value(hex_int): - raise suffixed_err(src, pos, "Escaped character is not a Unicode scalar value") + raise TOMLDecodeError( + "Escaped character is not a Unicode scalar value", src, pos + ) return pos, chr(hex_int) @@ -562,7 +650,7 @@ def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> tuple[Pos, str]: try: char = src[pos] except IndexError: - raise suffixed_err(src, pos, "Unterminated string") from None + raise TOMLDecodeError("Unterminated string", src, pos) from None if char == '"': if not multiline: return pos + 1, result + src[start_pos:pos] @@ -577,13 +665,21 @@ def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> tuple[Pos, str]: start_pos = pos continue if char in error_on: - raise suffixed_err(src, pos, f"Illegal character {char!r}") + raise TOMLDecodeError(f"Illegal character {char!r}", src, pos) pos += 1 def parse_value( # noqa: C901 - src: str, pos: Pos, parse_float: ParseFloat + src: str, pos: Pos, parse_float: ParseFloat, nest_lvl: int ) -> tuple[Pos, Any]: + if nest_lvl > MAX_INLINE_NESTING: + # Pure Python should have raised RecursionError already. + # This ensures mypyc binaries eventually do the same. + raise RecursionError( # pragma: no cover + "TOML inline arrays/tables are nested more than the allowed" + f" {MAX_INLINE_NESTING} levels" + ) + try: char: str | None = src[pos] except IndexError: @@ -613,11 +709,11 @@ def parse_value( # noqa: C901 # Arrays if char == "[": - return parse_array(src, pos, parse_float) + return parse_array(src, pos, parse_float, nest_lvl + 1) # Inline tables if char == "{": - return parse_inline_table(src, pos, parse_float) + return parse_inline_table(src, pos, parse_float, nest_lvl + 1) # Dates and times datetime_match = RE_DATETIME.match(src, pos) @@ -625,7 +721,7 @@ def parse_value( # noqa: C901 try: datetime_obj = match_to_datetime(datetime_match) except ValueError as e: - raise suffixed_err(src, pos, "Invalid date or datetime") from e + raise TOMLDecodeError("Invalid date or datetime", src, pos) from e return datetime_match.end(), datetime_obj localtime_match = RE_LOCALTIME.match(src, pos) if localtime_match: @@ -646,24 +742,7 @@ def parse_value( # noqa: C901 if first_four in {"-inf", "+inf", "-nan", "+nan"}: return pos + 4, parse_float(first_four) - raise suffixed_err(src, pos, "Invalid value") - - -def suffixed_err(src: str, pos: Pos, msg: str) -> TOMLDecodeError: - """Return a `TOMLDecodeError` where error message is suffixed with - coordinates in source.""" - - def coord_repr(src: str, pos: Pos) -> str: - if pos >= len(src): - return "end of document" - line = src.count("\n", 0, pos) + 1 - if line == 1: - column = pos + 1 - else: - column = pos - src.rindex("\n", 0, pos) - return f"line {line}, column {column}" - - return TOMLDecodeError(f"{msg} (at {coord_repr(src, pos)})") + raise TOMLDecodeError("Invalid value", src, pos) def is_unicode_scalar_value(codepoint: int) -> bool: @@ -679,7 +758,7 @@ def make_safe_parse_float(parse_float: ParseFloat) -> ParseFloat: instead of returning illegal types. """ # The default `float` callable never returns illegal types. Optimize it. - if parse_float is float: # type: ignore[comparison-overlap] + if parse_float is float: return float def safe_parse_float(float_str: str) -> Any: diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_re.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_re.py index 994bb74..5134866 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_re.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/_re.py @@ -7,16 +7,18 @@ from __future__ import annotations from datetime import date, datetime, time, timedelta, timezone, tzinfo from functools import lru_cache import re -from typing import Any +from typing import Any, Final from ._types import ParseFloat # E.g. # - 00:32:00.999999 # - 00:32:00 -_TIME_RE_STR = r"([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(?:\.([0-9]{1,6})[0-9]*)?" +_TIME_RE_STR: Final = ( + r"([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(?:\.([0-9]{1,6})[0-9]*)?" +) -RE_NUMBER = re.compile( +RE_NUMBER: Final = re.compile( r""" 0 (?: @@ -35,8 +37,8 @@ RE_NUMBER = re.compile( """, flags=re.VERBOSE, ) -RE_LOCALTIME = re.compile(_TIME_RE_STR) -RE_DATETIME = re.compile( +RE_LOCALTIME: Final = re.compile(_TIME_RE_STR) +RE_DATETIME: Final = re.compile( rf""" ([0-9]{{4}})-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01]) # date, e.g. 1988-10-27 (?: @@ -84,6 +86,9 @@ def match_to_datetime(match: re.Match) -> datetime | date: return datetime(year, month, day, hour, minute, sec, micros, tzinfo=tz) +# No need to limit cache size. This is only ever called on input +# that matched RE_DATETIME, so there is an implicit bound of +# 24 (hours) * 60 (minutes) * 2 (offset direction) = 2880. @lru_cache(maxsize=None) def cached_tz(hour_str: str, minute_str: str, sign_str: str) -> timezone: sign = 1 if sign_str == "+" else -1 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/py.typed b/llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/py.typed rename to llmlab/lib/python3.12/site-packages/pip/_vendor/tomli/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__init__.py index 59930f4..e468bf8 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__init__.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__init__.py @@ -5,9 +5,32 @@ import sys as _sys if _sys.version_info < (3, 10): raise ImportError("truststore requires Python 3.10 or later") +# Detect Python runtimes which don't implement SSLObject.get_unverified_chain() API +# This API only became public in Python 3.13 but was available in CPython and PyPy since 3.10. +if _sys.version_info < (3, 13): + try: + import ssl as _ssl + except ImportError: + raise ImportError("truststore requires the 'ssl' module") + else: + _sslmem = _ssl.MemoryBIO() + _sslobj = _ssl.create_default_context().wrap_bio( + _sslmem, + _sslmem, + ) + try: + while not hasattr(_sslobj, "get_unverified_chain"): + _sslobj = _sslobj._sslobj # type: ignore[attr-defined] + except AttributeError: + raise ImportError( + "truststore requires peer certificate chain APIs to be available" + ) from None + + del _ssl, _sslobj, _sslmem # noqa: F821 + from ._api import SSLContext, extract_from_ssl, inject_into_ssl # noqa: E402 del _api, _sys # type: ignore[name-defined] # noqa: F821 __all__ = ["SSLContext", "inject_into_ssl", "extract_from_ssl"] -__version__ = "0.8.0" +__version__ = "0.10.0" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/__init__.cpython-312.pyc index 87f8b20..7c97d3b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_api.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_api.cpython-312.pyc index d150d59..73d74ee 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_api.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_api.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_macos.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_macos.cpython-312.pyc index e079f2a..fecc117 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_macos.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_macos.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_openssl.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_openssl.cpython-312.pyc index d00b9c5..e095f50 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_openssl.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_openssl.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_ssl_constants.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_ssl_constants.cpython-312.pyc index b2e6578..f7cd89b 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_ssl_constants.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_ssl_constants.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_windows.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_windows.cpython-312.pyc index e971eaa..3760c85 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_windows.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/__pycache__/_windows.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_api.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_api.py index 829aff7..aeb023a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_api.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_api.py @@ -2,9 +2,10 @@ import os import platform import socket import ssl +import sys import typing -import _ssl # type: ignore[import] +import _ssl # type: ignore[import-not-found] from ._ssl_constants import ( _original_SSLContext, @@ -49,7 +50,7 @@ def extract_from_ssl() -> None: try: import pip._vendor.urllib3.util.ssl_ as urllib3_ssl - urllib3_ssl.SSLContext = _original_SSLContext + urllib3_ssl.SSLContext = _original_SSLContext # type: ignore[assignment] except ImportError: pass @@ -168,19 +169,19 @@ class SSLContext(_truststore_SSLContext_super_class): # type: ignore[misc] def cert_store_stats(self) -> dict[str, int]: raise NotImplementedError() + def set_default_verify_paths(self) -> None: + self._ctx.set_default_verify_paths() + @typing.overload def get_ca_certs( self, binary_form: typing.Literal[False] = ... - ) -> list[typing.Any]: - ... + ) -> list[typing.Any]: ... @typing.overload - def get_ca_certs(self, binary_form: typing.Literal[True] = ...) -> list[bytes]: - ... + def get_ca_certs(self, binary_form: typing.Literal[True] = ...) -> list[bytes]: ... @typing.overload - def get_ca_certs(self, binary_form: bool = ...) -> typing.Any: - ... + def get_ca_certs(self, binary_form: bool = ...) -> typing.Any: ... def get_ca_certs(self, binary_form: bool = False) -> list[typing.Any] | list[bytes]: raise NotImplementedError() @@ -276,6 +277,25 @@ class SSLContext(_truststore_SSLContext_super_class): # type: ignore[misc] ) +# Python 3.13+ makes get_unverified_chain() a public API that only returns DER +# encoded certificates. We detect whether we need to call public_bytes() for 3.10->3.12 +# Pre-3.13 returned None instead of an empty list from get_unverified_chain() +if sys.version_info >= (3, 13): + + def _get_unverified_chain_bytes(sslobj: ssl.SSLObject) -> list[bytes]: + unverified_chain = sslobj.get_unverified_chain() or () # type: ignore[attr-defined] + return [ + cert if isinstance(cert, bytes) else cert.public_bytes(_ssl.ENCODING_DER) + for cert in unverified_chain + ] + +else: + + def _get_unverified_chain_bytes(sslobj: ssl.SSLObject) -> list[bytes]: + unverified_chain = sslobj.get_unverified_chain() or () # type: ignore[attr-defined] + return [cert.public_bytes(_ssl.ENCODING_DER) for cert in unverified_chain] + + def _verify_peercerts( sock_or_sslobj: ssl.SSLSocket | ssl.SSLObject, server_hostname: str | None ) -> None: @@ -290,13 +310,7 @@ def _verify_peercerts( except AttributeError: pass - # SSLObject.get_unverified_chain() returns 'None' - # if the peer sends no certificates. This is common - # for the server-side scenario. - unverified_chain: typing.Sequence[_ssl.Certificate] = ( - sslobj.get_unverified_chain() or () # type: ignore[attr-defined] - ) - cert_bytes = [cert.public_bytes(_ssl.ENCODING_DER) for cert in unverified_chain] + cert_bytes = _get_unverified_chain_bytes(sslobj) _verify_peercerts_impl( sock_or_sslobj.context, cert_bytes, server_hostname=server_hostname ) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_macos.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_macos.py index 7dc440b..3450307 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_macos.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_macos.py @@ -25,6 +25,8 @@ if _mac_version_info < (10, 8): f"Only OS X 10.8 and newer are supported, not {_mac_version_info[0]}.{_mac_version_info[1]}" ) +_is_macos_version_10_14_or_later = _mac_version_info >= (10, 14) + def _load_cdll(name: str, macos10_16_path: str) -> CDLL: """Loads a CDLL by name, falling back to known path on 10.16+""" @@ -96,9 +98,6 @@ try: Security.SecTrustSetAnchorCertificatesOnly.argtypes = [SecTrustRef, Boolean] Security.SecTrustSetAnchorCertificatesOnly.restype = OSStatus - Security.SecTrustEvaluate.argtypes = [SecTrustRef, POINTER(SecTrustResultType)] - Security.SecTrustEvaluate.restype = OSStatus - Security.SecPolicyCreateRevocation.argtypes = [CFOptionFlags] Security.SecPolicyCreateRevocation.restype = SecPolicyRef @@ -118,6 +117,12 @@ try: ] Security.SecTrustGetTrustResult.restype = OSStatus + Security.SecTrustEvaluate.argtypes = [ + SecTrustRef, + POINTER(SecTrustResultType), + ] + Security.SecTrustEvaluate.restype = OSStatus + Security.SecTrustRef = SecTrustRef # type: ignore[attr-defined] Security.SecTrustResultType = SecTrustResultType # type: ignore[attr-defined] Security.OSStatus = OSStatus # type: ignore[attr-defined] @@ -200,8 +205,19 @@ try: CoreFoundation.CFStringRef = CFStringRef # type: ignore[attr-defined] CoreFoundation.CFErrorRef = CFErrorRef # type: ignore[attr-defined] -except AttributeError: - raise ImportError("Error initializing ctypes") from None +except AttributeError as e: + raise ImportError(f"Error initializing ctypes: {e}") from None + +# SecTrustEvaluateWithError is macOS 10.14+ +if _is_macos_version_10_14_or_later: + try: + Security.SecTrustEvaluateWithError.argtypes = [ + SecTrustRef, + POINTER(CFErrorRef), + ] + Security.SecTrustEvaluateWithError.restype = c_bool + except AttributeError as e: + raise ImportError(f"Error initializing ctypes: {e}") from None def _handle_osstatus(result: OSStatus, _: typing.Any, args: typing.Any) -> typing.Any: @@ -259,7 +275,9 @@ def _handle_osstatus(result: OSStatus, _: typing.Any, args: typing.Any) -> typin Security.SecTrustCreateWithCertificates.errcheck = _handle_osstatus # type: ignore[assignment] Security.SecTrustSetAnchorCertificates.errcheck = _handle_osstatus # type: ignore[assignment] +Security.SecTrustSetAnchorCertificatesOnly.errcheck = _handle_osstatus # type: ignore[assignment] Security.SecTrustGetTrustResult.errcheck = _handle_osstatus # type: ignore[assignment] +Security.SecTrustEvaluate.errcheck = _handle_osstatus # type: ignore[assignment] class CFConst: @@ -367,9 +385,10 @@ def _verify_peercerts_impl( certs = None policies = None trust = None - cf_error = None try: - if server_hostname is not None: + # Only set a hostname on the policy if we're verifying the hostname + # on the leaf certificate. + if server_hostname is not None and ssl_context.check_hostname: cf_str_hostname = None try: cf_str_hostname = _bytes_to_cf_string(server_hostname.encode("ascii")) @@ -417,85 +436,136 @@ def _verify_peercerts_impl( CoreFoundation.CFRelease(certs) # If there are additional trust anchors to load we need to transform - # the list of DER-encoded certificates into a CFArray. Otherwise - # pass 'None' to signal that we only want system / fetched certificates. + # the list of DER-encoded certificates into a CFArray. ctx_ca_certs_der: list[bytes] | None = ssl_context.get_ca_certs( binary_form=True ) if ctx_ca_certs_der: ctx_ca_certs = None try: - ctx_ca_certs = _der_certs_to_cf_cert_array(cert_chain) + ctx_ca_certs = _der_certs_to_cf_cert_array(ctx_ca_certs_der) Security.SecTrustSetAnchorCertificates(trust, ctx_ca_certs) finally: if ctx_ca_certs: CoreFoundation.CFRelease(ctx_ca_certs) + + # We always want system certificates. + Security.SecTrustSetAnchorCertificatesOnly(trust, False) + + # macOS 10.13 and earlier don't support SecTrustEvaluateWithError() + # so we use SecTrustEvaluate() which means we need to construct error + # messages ourselves. + if _is_macos_version_10_14_or_later: + _verify_peercerts_impl_macos_10_14(ssl_context, trust) else: - Security.SecTrustSetAnchorCertificates(trust, None) - - cf_error = CoreFoundation.CFErrorRef() - sec_trust_eval_result = Security.SecTrustEvaluateWithError( - trust, ctypes.byref(cf_error) - ) - # sec_trust_eval_result is a bool (0 or 1) - # where 1 means that the certs are trusted. - if sec_trust_eval_result == 1: - is_trusted = True - elif sec_trust_eval_result == 0: - is_trusted = False - else: - raise ssl.SSLError( - f"Unknown result from Security.SecTrustEvaluateWithError: {sec_trust_eval_result!r}" - ) - - cf_error_code = 0 - if not is_trusted: - cf_error_code = CoreFoundation.CFErrorGetCode(cf_error) - - # If the error is a known failure that we're - # explicitly okay with from SSLContext configuration - # we can set is_trusted accordingly. - if ssl_context.verify_mode != ssl.CERT_REQUIRED and ( - cf_error_code == CFConst.errSecNotTrusted - or cf_error_code == CFConst.errSecCertificateExpired - ): - is_trusted = True - elif ( - not ssl_context.check_hostname - and cf_error_code == CFConst.errSecHostNameMismatch - ): - is_trusted = True - - # If we're still not trusted then we start to - # construct and raise the SSLCertVerificationError. - if not is_trusted: - cf_error_string_ref = None - try: - cf_error_string_ref = CoreFoundation.CFErrorCopyDescription(cf_error) - - # Can this ever return 'None' if there's a CFError? - cf_error_message = ( - _cf_string_ref_to_str(cf_error_string_ref) - or "Certificate verification failed" - ) - - # TODO: Not sure if we need the SecTrustResultType for anything? - # We only care whether or not it's a success or failure for now. - sec_trust_result_type = Security.SecTrustResultType() - Security.SecTrustGetTrustResult( - trust, ctypes.byref(sec_trust_result_type) - ) - - err = ssl.SSLCertVerificationError(cf_error_message) - err.verify_message = cf_error_message - err.verify_code = cf_error_code - raise err - finally: - if cf_error_string_ref: - CoreFoundation.CFRelease(cf_error_string_ref) - + _verify_peercerts_impl_macos_10_13(ssl_context, trust) finally: if policies: CoreFoundation.CFRelease(policies) if trust: CoreFoundation.CFRelease(trust) + + +def _verify_peercerts_impl_macos_10_13( + ssl_context: ssl.SSLContext, sec_trust_ref: typing.Any +) -> None: + """Verify using 'SecTrustEvaluate' API for macOS 10.13 and earlier. + macOS 10.14 added the 'SecTrustEvaluateWithError' API. + """ + sec_trust_result_type = Security.SecTrustResultType() + Security.SecTrustEvaluate(sec_trust_ref, ctypes.byref(sec_trust_result_type)) + + try: + sec_trust_result_type_as_int = int(sec_trust_result_type.value) + except (ValueError, TypeError): + sec_trust_result_type_as_int = -1 + + # Apple doesn't document these values in their own API docs. + # See: https://github.com/xybp888/iOS-SDKs/blob/master/iPhoneOS13.0.sdk/System/Library/Frameworks/Security.framework/Headers/SecTrust.h#L84 + if ( + ssl_context.verify_mode == ssl.CERT_REQUIRED + and sec_trust_result_type_as_int not in (1, 4) + ): + # Note that we're not able to ignore only hostname errors + # for macOS 10.13 and earlier, so check_hostname=False will + # still return an error. + sec_trust_result_type_to_message = { + 0: "Invalid trust result type", + # 1: "Trust evaluation succeeded", + 2: "User confirmation required", + 3: "User specified that certificate is not trusted", + # 4: "Trust result is unspecified", + 5: "Recoverable trust failure occurred", + 6: "Fatal trust failure occurred", + 7: "Other error occurred, certificate may be revoked", + } + error_message = sec_trust_result_type_to_message.get( + sec_trust_result_type_as_int, + f"Unknown trust result: {sec_trust_result_type_as_int}", + ) + + err = ssl.SSLCertVerificationError(error_message) + err.verify_message = error_message + err.verify_code = sec_trust_result_type_as_int + raise err + + +def _verify_peercerts_impl_macos_10_14( + ssl_context: ssl.SSLContext, sec_trust_ref: typing.Any +) -> None: + """Verify using 'SecTrustEvaluateWithError' API for macOS 10.14+.""" + cf_error = CoreFoundation.CFErrorRef() + sec_trust_eval_result = Security.SecTrustEvaluateWithError( + sec_trust_ref, ctypes.byref(cf_error) + ) + # sec_trust_eval_result is a bool (0 or 1) + # where 1 means that the certs are trusted. + if sec_trust_eval_result == 1: + is_trusted = True + elif sec_trust_eval_result == 0: + is_trusted = False + else: + raise ssl.SSLError( + f"Unknown result from Security.SecTrustEvaluateWithError: {sec_trust_eval_result!r}" + ) + + cf_error_code = 0 + if not is_trusted: + cf_error_code = CoreFoundation.CFErrorGetCode(cf_error) + + # If the error is a known failure that we're + # explicitly okay with from SSLContext configuration + # we can set is_trusted accordingly. + if ssl_context.verify_mode != ssl.CERT_REQUIRED and ( + cf_error_code == CFConst.errSecNotTrusted + or cf_error_code == CFConst.errSecCertificateExpired + ): + is_trusted = True + + # If we're still not trusted then we start to + # construct and raise the SSLCertVerificationError. + if not is_trusted: + cf_error_string_ref = None + try: + cf_error_string_ref = CoreFoundation.CFErrorCopyDescription(cf_error) + + # Can this ever return 'None' if there's a CFError? + cf_error_message = ( + _cf_string_ref_to_str(cf_error_string_ref) + or "Certificate verification failed" + ) + + # TODO: Not sure if we need the SecTrustResultType for anything? + # We only care whether or not it's a success or failure for now. + sec_trust_result_type = Security.SecTrustResultType() + Security.SecTrustGetTrustResult( + sec_trust_ref, ctypes.byref(sec_trust_result_type) + ) + + err = ssl.SSLCertVerificationError(cf_error_message) + err.verify_message = cf_error_message + err.verify_code = cf_error_code + raise err + finally: + if cf_error_string_ref: + CoreFoundation.CFRelease(cf_error_string_ref) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_windows.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_windows.py index 3de4960..a9bf9ab 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_windows.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/_windows.py @@ -212,6 +212,7 @@ CERT_CHAIN_POLICY_IGNORE_INVALID_POLICY_FLAG = 0x00000080 CERT_CHAIN_POLICY_IGNORE_ALL_REV_UNKNOWN_FLAGS = 0x00000F00 CERT_CHAIN_POLICY_ALLOW_TESTROOT_FLAG = 0x00008000 CERT_CHAIN_POLICY_TRUST_TESTROOT_FLAG = 0x00004000 +SECURITY_FLAG_IGNORE_CERT_CN_INVALID = 0x00001000 AUTHTYPE_SERVER = 2 CERT_CHAIN_POLICY_SSL = 4 FORMAT_MESSAGE_FROM_SYSTEM = 0x00001000 @@ -325,6 +326,12 @@ def _verify_peercerts_impl( server_hostname: str | None = None, ) -> None: """Verify the cert_chain from the server using Windows APIs.""" + + # If the peer didn't send any certificates then + # we can't do verification. Raise an error. + if not cert_chain: + raise ssl.SSLCertVerificationError("Peer sent no certificates to verify") + pCertContext = None hIntermediateCertStore = CertOpenStore(CERT_STORE_PROV_MEMORY, 0, None, 0, None) try: @@ -375,7 +382,7 @@ def _verify_peercerts_impl( server_hostname, chain_flags=chain_flags, ) - except ssl.SSLCertVerificationError: + except ssl.SSLCertVerificationError as e: # If that fails but custom CA certs have been added # to the SSLContext using load_verify_locations, # try verifying using a custom chain engine @@ -384,15 +391,19 @@ def _verify_peercerts_impl( binary_form=True ) if custom_ca_certs: - _verify_using_custom_ca_certs( - ssl_context, - custom_ca_certs, - hIntermediateCertStore, - pCertContext, - pChainPara, - server_hostname, - chain_flags=chain_flags, - ) + try: + _verify_using_custom_ca_certs( + ssl_context, + custom_ca_certs, + hIntermediateCertStore, + pCertContext, + pChainPara, + server_hostname, + chain_flags=chain_flags, + ) + # Raise the original error, not the new error. + except ssl.SSLCertVerificationError: + raise e from None else: raise finally: @@ -433,6 +444,10 @@ def _get_and_verify_cert_chain( ) ssl_extra_cert_chain_policy_para.dwAuthType = AUTHTYPE_SERVER ssl_extra_cert_chain_policy_para.fdwChecks = 0 + if ssl_context.check_hostname is False: + ssl_extra_cert_chain_policy_para.fdwChecks = ( + SECURITY_FLAG_IGNORE_CERT_CN_INVALID + ) if server_hostname: ssl_extra_cert_chain_policy_para.pwszServerName = c_wchar_p(server_hostname) @@ -442,8 +457,6 @@ def _get_and_verify_cert_chain( ) if ssl_context.verify_mode == ssl.CERT_NONE: chain_policy.dwFlags |= CERT_CHAIN_POLICY_VERIFY_MODE_NONE_FLAGS - if not ssl_context.check_hostname: - chain_policy.dwFlags |= CERT_CHAIN_POLICY_IGNORE_INVALID_NAME_FLAG chain_policy.cbSize = sizeof(chain_policy) pPolicyPara = pointer(chain_policy) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/py.typed similarity index 100% rename from llmlab/lib/python3.12/site-packages/pip/_vendor/chardet/cli/__init__.py rename to llmlab/lib/python3.12/site-packages/pip/_vendor/truststore/py.typed diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/typing_extensions.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/typing_extensions.py index 4f93acf..e429384 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/typing_extensions.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/typing_extensions.py @@ -1,6 +1,7 @@ import abc import collections import collections.abc +import contextlib import functools import inspect import operator @@ -60,6 +61,7 @@ __all__ = [ 'clear_overloads', 'dataclass_transform', 'deprecated', + 'Doc', 'get_overloads', 'final', 'get_args', @@ -82,9 +84,11 @@ __all__ = [ 'TypeAlias', 'TypeAliasType', 'TypeGuard', + 'TypeIs', 'TYPE_CHECKING', 'Never', 'NoReturn', + 'ReadOnly', 'Required', 'NotRequired', @@ -113,6 +117,7 @@ __all__ = [ 'MutableMapping', 'MutableSequence', 'MutableSet', + 'NoDefault', 'Optional', 'Pattern', 'Reversible', @@ -131,6 +136,7 @@ __all__ = [ # for backward compatibility PEP_560 = True GenericMeta = type +_PEP_696_IMPLEMENTED = sys.version_info >= (3, 13, 0, "beta") # The functions below are modified copies of typing internal helpers. # They are needed by _ProtocolMeta and they provide support for PEP 646. @@ -144,27 +150,6 @@ class _Sentinel: _marker = _Sentinel() -def _check_generic(cls, parameters, elen=_marker): - """Check correct count for parameters of a generic cls (internal helper). - This gives a nice error message in case of count mismatch. - """ - if not elen: - raise TypeError(f"{cls} is not a generic class") - if elen is _marker: - if not hasattr(cls, "__parameters__") or not cls.__parameters__: - raise TypeError(f"{cls} is not a generic class") - elen = len(cls.__parameters__) - alen = len(parameters) - if alen != elen: - if hasattr(cls, "__parameters__"): - parameters = [p for p in cls.__parameters__ if not _is_unpack(p)] - num_tv_tuples = sum(isinstance(p, TypeVarTuple) for p in parameters) - if (num_tv_tuples > 0) and (alen >= elen - num_tv_tuples): - return - raise TypeError(f"Too {'many' if alen > elen else 'few'} parameters for {cls};" - f" actual {alen}, expected {elen}") - - if sys.version_info >= (3, 10): def _should_collect_from_parameters(t): return isinstance( @@ -178,27 +163,6 @@ else: return isinstance(t, typing._GenericAlias) and not t._special -def _collect_type_vars(types, typevar_types=None): - """Collect all type variable contained in types in order of - first appearance (lexicographic order). For example:: - - _collect_type_vars((T, List[S, T])) == (T, S) - """ - if typevar_types is None: - typevar_types = typing.TypeVar - tvars = [] - for t in types: - if ( - isinstance(t, typevar_types) and - t not in tvars and - not _is_unpack(t) - ): - tvars.append(t) - if _should_collect_from_parameters(t): - tvars.extend([t for t in t.__parameters__ if t not in tvars]) - return tuple(tvars) - - NoReturn = typing.NoReturn # Some unconstrained type variables. These are used by the container types. @@ -248,32 +212,7 @@ class _ExtensionsSpecialForm(typing._SpecialForm, _root=True): return 'typing_extensions.' + self._name -# On older versions of typing there is an internal class named "Final". -# 3.8+ -if hasattr(typing, 'Final') and sys.version_info[:2] >= (3, 7): - Final = typing.Final -# 3.7 -else: - class _FinalForm(_ExtensionsSpecialForm, _root=True): - def __getitem__(self, parameters): - item = typing._type_check(parameters, - f'{self._name} accepts only a single type.') - return typing._GenericAlias(self, (item,)) - - Final = _FinalForm('Final', - doc="""A special typing construct to indicate that a name - cannot be re-assigned or overridden in a subclass. - For example: - - MAX_SIZE: Final = 9000 - MAX_SIZE += 1 # Error reported by type checker - - class Connection: - TIMEOUT: Final[int] = 10 - class FastConnector(Connection): - TIMEOUT = 1 # Error reported by type checker - - There is no runtime checking of these properties.""") +Final = typing.Final if sys.version_info >= (3, 11): final = typing.final @@ -465,31 +404,101 @@ Type = typing.Type # Various ABCs mimicking those in collections.abc. # A few are simply re-exported for completeness. - - Awaitable = typing.Awaitable Coroutine = typing.Coroutine AsyncIterable = typing.AsyncIterable AsyncIterator = typing.AsyncIterator Deque = typing.Deque -ContextManager = typing.ContextManager -AsyncContextManager = typing.AsyncContextManager DefaultDict = typing.DefaultDict - -# 3.7.2+ -if hasattr(typing, 'OrderedDict'): - OrderedDict = typing.OrderedDict -# 3.7.0-3.7.2 -else: - OrderedDict = typing._alias(collections.OrderedDict, (KT, VT)) - +OrderedDict = typing.OrderedDict Counter = typing.Counter ChainMap = typing.ChainMap -AsyncGenerator = typing.AsyncGenerator Text = typing.Text TYPE_CHECKING = typing.TYPE_CHECKING +if sys.version_info >= (3, 13, 0, "beta"): + from typing import AsyncContextManager, AsyncGenerator, ContextManager, Generator +else: + def _is_dunder(attr): + return attr.startswith('__') and attr.endswith('__') + + # Python <3.9 doesn't have typing._SpecialGenericAlias + _special_generic_alias_base = getattr( + typing, "_SpecialGenericAlias", typing._GenericAlias + ) + + class _SpecialGenericAlias(_special_generic_alias_base, _root=True): + def __init__(self, origin, nparams, *, inst=True, name=None, defaults=()): + if _special_generic_alias_base is typing._GenericAlias: + # Python <3.9 + self.__origin__ = origin + self._nparams = nparams + super().__init__(origin, nparams, special=True, inst=inst, name=name) + else: + # Python >= 3.9 + super().__init__(origin, nparams, inst=inst, name=name) + self._defaults = defaults + + def __setattr__(self, attr, val): + allowed_attrs = {'_name', '_inst', '_nparams', '_defaults'} + if _special_generic_alias_base is typing._GenericAlias: + # Python <3.9 + allowed_attrs.add("__origin__") + if _is_dunder(attr) or attr in allowed_attrs: + object.__setattr__(self, attr, val) + else: + setattr(self.__origin__, attr, val) + + @typing._tp_cache + def __getitem__(self, params): + if not isinstance(params, tuple): + params = (params,) + msg = "Parameters to generic types must be types." + params = tuple(typing._type_check(p, msg) for p in params) + if ( + self._defaults + and len(params) < self._nparams + and len(params) + len(self._defaults) >= self._nparams + ): + params = (*params, *self._defaults[len(params) - self._nparams:]) + actual_len = len(params) + + if actual_len != self._nparams: + if self._defaults: + expected = f"at least {self._nparams - len(self._defaults)}" + else: + expected = str(self._nparams) + if not self._nparams: + raise TypeError(f"{self} is not a generic class") + raise TypeError( + f"Too {'many' if actual_len > self._nparams else 'few'}" + f" arguments for {self};" + f" actual {actual_len}, expected {expected}" + ) + return self.copy_with(params) + + _NoneType = type(None) + Generator = _SpecialGenericAlias( + collections.abc.Generator, 3, defaults=(_NoneType, _NoneType) + ) + AsyncGenerator = _SpecialGenericAlias( + collections.abc.AsyncGenerator, 2, defaults=(_NoneType,) + ) + ContextManager = _SpecialGenericAlias( + contextlib.AbstractContextManager, + 2, + name="ContextManager", + defaults=(typing.Optional[bool],) + ) + AsyncContextManager = _SpecialGenericAlias( + contextlib.AbstractAsyncContextManager, + 2, + name="AsyncContextManager", + defaults=(typing.Optional[bool],) + ) + + _PROTO_ALLOWLIST = { 'collections.abc': [ 'Callable', 'Awaitable', 'Iterable', 'Iterator', 'AsyncIterable', @@ -500,28 +509,11 @@ _PROTO_ALLOWLIST = { } -_EXCLUDED_ATTRS = { - "__abstractmethods__", "__annotations__", "__weakref__", "_is_protocol", - "_is_runtime_protocol", "__dict__", "__slots__", "__parameters__", - "__orig_bases__", "__module__", "_MutableMapping__marker", "__doc__", - "__subclasshook__", "__orig_class__", "__init__", "__new__", - "__protocol_attrs__", "__callable_proto_members_only__", +_EXCLUDED_ATTRS = frozenset(typing.EXCLUDED_ATTRIBUTES) | { + "__match_args__", "__protocol_attrs__", "__non_callable_proto_members__", + "__final__", } -if sys.version_info < (3, 8): - _EXCLUDED_ATTRS |= { - "_gorg", "__next_in_mro__", "__extra__", "__tree_hash__", "__args__", - "__origin__" - } - -if sys.version_info >= (3, 9): - _EXCLUDED_ATTRS.add("__class_getitem__") - -if sys.version_info >= (3, 12): - _EXCLUDED_ATTRS.add("__type_params__") - -_EXCLUDED_ATTRS = frozenset(_EXCLUDED_ATTRS) - def _get_protocol_attrs(cls): attrs = set() @@ -535,46 +527,6 @@ def _get_protocol_attrs(cls): return attrs -def _maybe_adjust_parameters(cls): - """Helper function used in Protocol.__init_subclass__ and _TypedDictMeta.__new__. - - The contents of this function are very similar - to logic found in typing.Generic.__init_subclass__ - on the CPython main branch. - """ - tvars = [] - if '__orig_bases__' in cls.__dict__: - tvars = _collect_type_vars(cls.__orig_bases__) - # Look for Generic[T1, ..., Tn] or Protocol[T1, ..., Tn]. - # If found, tvars must be a subset of it. - # If not found, tvars is it. - # Also check for and reject plain Generic, - # and reject multiple Generic[...] and/or Protocol[...]. - gvars = None - for base in cls.__orig_bases__: - if (isinstance(base, typing._GenericAlias) and - base.__origin__ in (typing.Generic, Protocol)): - # for error messages - the_base = base.__origin__.__name__ - if gvars is not None: - raise TypeError( - "Cannot inherit from Generic[...]" - " and/or Protocol[...] multiple types.") - gvars = base.__parameters__ - if gvars is None: - gvars = tvars - else: - tvarset = set(tvars) - gvarset = set(gvars) - if not tvarset <= gvarset: - s_vars = ', '.join(str(t) for t in tvars if t not in gvarset) - s_args = ', '.join(str(g) for g in gvars) - raise TypeError(f"Some type variables ({s_vars}) are" - f" not listed in {the_base}[{s_args}]") - tvars = gvars - cls.__parameters__ = tuple(tvars) - - def _caller(depth=2): try: return sys._getframe(depth).f_globals.get('__name__', '__main__') @@ -582,9 +534,9 @@ def _caller(depth=2): return None -# The performance of runtime-checkable protocols is significantly improved on Python 3.12, -# so we backport the 3.12 version of Protocol to Python <=3.11 -if sys.version_info >= (3, 12): +# `__match_args__` attribute was removed from protocol members in 3.13, +# we want to backport this change to older Python versions. +if sys.version_info >= (3, 13): Protocol = typing.Protocol else: def _allow_reckless_class_checks(depth=3): @@ -598,17 +550,26 @@ else: if type(self)._is_protocol: raise TypeError('Protocols cannot be instantiated') - if sys.version_info >= (3, 8): - # Inheriting from typing._ProtocolMeta isn't actually desirable, - # but is necessary to allow typing.Protocol and typing_extensions.Protocol - # to mix without getting TypeErrors about "metaclass conflict" - _typing_Protocol = typing.Protocol - _ProtocolMetaBase = type(_typing_Protocol) - else: - _typing_Protocol = _marker - _ProtocolMetaBase = abc.ABCMeta + def _type_check_issubclass_arg_1(arg): + """Raise TypeError if `arg` is not an instance of `type` + in `issubclass(arg, )`. - class _ProtocolMeta(_ProtocolMetaBase): + In most cases, this is verified by type.__subclasscheck__. + Checking it again unnecessarily would slow down issubclass() checks, + so, we don't perform this check unless we absolutely have to. + + For various error paths, however, + we want to ensure that *this* error message is shown to the user + where relevant, rather than a typing.py-specific error message. + """ + if not isinstance(arg, type): + # Same error message as for issubclass(1, int). + raise TypeError('issubclass() arg 1 must be a class') + + # Inheriting from typing._ProtocolMeta isn't actually desirable, + # but is necessary to allow typing.Protocol and typing_extensions.Protocol + # to mix without getting TypeErrors about "metaclass conflict" + class _ProtocolMeta(type(typing.Protocol)): # This metaclass is somewhat unfortunate, # but is necessary for several reasons... # @@ -618,10 +579,10 @@ else: def __new__(mcls, name, bases, namespace, **kwargs): if name == "Protocol" and len(bases) < 2: pass - elif {Protocol, _typing_Protocol} & set(bases): + elif {Protocol, typing.Protocol} & set(bases): for base in bases: if not ( - base in {object, typing.Generic, Protocol, _typing_Protocol} + base in {object, typing.Generic, Protocol, typing.Protocol} or base.__name__ in _PROTO_ALLOWLIST.get(base.__module__, []) or is_protocol(base) ): @@ -635,11 +596,6 @@ else: abc.ABCMeta.__init__(cls, *args, **kwargs) if getattr(cls, "_is_protocol", False): cls.__protocol_attrs__ = _get_protocol_attrs(cls) - # PEP 544 prohibits using issubclass() - # with protocols that have non-method members. - cls.__callable_proto_members_only__ = all( - callable(getattr(cls, attr, None)) for attr in cls.__protocol_attrs__ - ) def __subclasscheck__(cls, other): if cls is Protocol: @@ -648,21 +604,23 @@ else: getattr(cls, '_is_protocol', False) and not _allow_reckless_class_checks() ): - if not isinstance(other, type): - # Same error message as for issubclass(1, int). - raise TypeError('issubclass() arg 1 must be a class') - if ( - not cls.__callable_proto_members_only__ - and cls.__dict__.get("__subclasshook__") is _proto_hook - ): - raise TypeError( - "Protocols with non-method members don't support issubclass()" - ) if not getattr(cls, '_is_runtime_protocol', False): + _type_check_issubclass_arg_1(other) raise TypeError( "Instance and class checks can only be used with " "@runtime_checkable protocols" ) + if ( + # this attribute is set by @runtime_checkable: + cls.__non_callable_proto_members__ + and cls.__dict__.get("__subclasshook__") is _proto_hook + ): + _type_check_issubclass_arg_1(other) + non_method_attrs = sorted(cls.__non_callable_proto_members__) + raise TypeError( + "Protocols with non-method members don't support issubclass()." + f" Non-method members: {str(non_method_attrs)[1:-1]}." + ) return abc.ABCMeta.__subclasscheck__(cls, other) def __instancecheck__(cls, instance): @@ -689,7 +647,8 @@ else: val = inspect.getattr_static(instance, attr) except AttributeError: break - if val is None and callable(getattr(cls, attr, None)): + # this attribute is set by @runtime_checkable: + if val is None and attr not in cls.__non_callable_proto_members__: break else: return True @@ -699,12 +658,10 @@ else: def __eq__(cls, other): # Hack so that typing.Generic.__class_getitem__ # treats typing_extensions.Protocol - # as equivalent to typing.Protocol on Python 3.8+ + # as equivalent to typing.Protocol if abc.ABCMeta.__eq__(cls, other) is True: return True - return ( - cls is Protocol and other is getattr(typing, "Protocol", object()) - ) + return cls is Protocol and other is typing.Protocol # This has to be defined, or the abc-module cache # complains about classes with this metaclass being unhashable, @@ -737,146 +694,88 @@ else: return NotImplemented return True - if sys.version_info >= (3, 8): - class Protocol(typing.Generic, metaclass=_ProtocolMeta): - __doc__ = typing.Protocol.__doc__ - __slots__ = () - _is_protocol = True - _is_runtime_protocol = False + class Protocol(typing.Generic, metaclass=_ProtocolMeta): + __doc__ = typing.Protocol.__doc__ + __slots__ = () + _is_protocol = True + _is_runtime_protocol = False - def __init_subclass__(cls, *args, **kwargs): - super().__init_subclass__(*args, **kwargs) + def __init_subclass__(cls, *args, **kwargs): + super().__init_subclass__(*args, **kwargs) - # Determine if this is a protocol or a concrete subclass. - if not cls.__dict__.get('_is_protocol', False): - cls._is_protocol = any(b is Protocol for b in cls.__bases__) + # Determine if this is a protocol or a concrete subclass. + if not cls.__dict__.get('_is_protocol', False): + cls._is_protocol = any(b is Protocol for b in cls.__bases__) - # Set (or override) the protocol subclass hook. - if '__subclasshook__' not in cls.__dict__: - cls.__subclasshook__ = _proto_hook + # Set (or override) the protocol subclass hook. + if '__subclasshook__' not in cls.__dict__: + cls.__subclasshook__ = _proto_hook - # Prohibit instantiation for protocol classes - if cls._is_protocol and cls.__init__ is Protocol.__init__: - cls.__init__ = _no_init - - else: - class Protocol(metaclass=_ProtocolMeta): - # There is quite a lot of overlapping code with typing.Generic. - # Unfortunately it is hard to avoid this on Python <3.8, - # as the typing module on Python 3.7 doesn't let us subclass typing.Generic! - """Base class for protocol classes. Protocol classes are defined as:: - - class Proto(Protocol): - def meth(self) -> int: - ... - - Such classes are primarily used with static type checkers that recognize - structural subtyping (static duck-typing), for example:: - - class C: - def meth(self) -> int: - return 0 - - def func(x: Proto) -> int: - return x.meth() - - func(C()) # Passes static type check - - See PEP 544 for details. Protocol classes decorated with - @typing_extensions.runtime_checkable act - as simple-minded runtime-checkable protocols that check - only the presence of given attributes, ignoring their type signatures. - - Protocol classes can be generic, they are defined as:: - - class GenProto(Protocol[T]): - def meth(self) -> T: - ... - """ - __slots__ = () - _is_protocol = True - _is_runtime_protocol = False - - def __new__(cls, *args, **kwds): - if cls is Protocol: - raise TypeError("Type Protocol cannot be instantiated; " - "it can only be used as a base class") - return super().__new__(cls) - - @typing._tp_cache - def __class_getitem__(cls, params): - if not isinstance(params, tuple): - params = (params,) - if not params and cls is not typing.Tuple: - raise TypeError( - f"Parameter list to {cls.__qualname__}[...] cannot be empty") - msg = "Parameters to generic types must be types." - params = tuple(typing._type_check(p, msg) for p in params) - if cls is Protocol: - # Generic can only be subscripted with unique type variables. - if not all(isinstance(p, typing.TypeVar) for p in params): - i = 0 - while isinstance(params[i], typing.TypeVar): - i += 1 - raise TypeError( - "Parameters to Protocol[...] must all be type variables." - f" Parameter {i + 1} is {params[i]}") - if len(set(params)) != len(params): - raise TypeError( - "Parameters to Protocol[...] must all be unique") - else: - # Subscripting a regular Generic subclass. - _check_generic(cls, params, len(cls.__parameters__)) - return typing._GenericAlias(cls, params) - - def __init_subclass__(cls, *args, **kwargs): - if '__orig_bases__' in cls.__dict__: - error = typing.Generic in cls.__orig_bases__ - else: - error = typing.Generic in cls.__bases__ - if error: - raise TypeError("Cannot inherit from plain Generic") - _maybe_adjust_parameters(cls) - - # Determine if this is a protocol or a concrete subclass. - if not cls.__dict__.get('_is_protocol', None): - cls._is_protocol = any(b is Protocol for b in cls.__bases__) - - # Set (or override) the protocol subclass hook. - if '__subclasshook__' not in cls.__dict__: - cls.__subclasshook__ = _proto_hook - - # Prohibit instantiation for protocol classes - if cls._is_protocol and cls.__init__ is Protocol.__init__: - cls.__init__ = _no_init + # Prohibit instantiation for protocol classes + if cls._is_protocol and cls.__init__ is Protocol.__init__: + cls.__init__ = _no_init -if sys.version_info >= (3, 8): +if sys.version_info >= (3, 13): runtime_checkable = typing.runtime_checkable else: def runtime_checkable(cls): - """Mark a protocol class as a runtime protocol, so that it - can be used with isinstance() and issubclass(). Raise TypeError - if applied to a non-protocol class. + """Mark a protocol class as a runtime protocol. - This allows a simple-minded structural check very similar to the - one-offs in collections.abc such as Hashable. + Such protocol can be used with isinstance() and issubclass(). + Raise TypeError if applied to a non-protocol class. + This allows a simple-minded structural check very similar to + one trick ponies in collections.abc such as Iterable. + + For example:: + + @runtime_checkable + class Closable(Protocol): + def close(self): ... + + assert isinstance(open('/some/file'), Closable) + + Warning: this will check only the presence of the required methods, + not their type signatures! """ - if not ( - (isinstance(cls, _ProtocolMeta) or issubclass(cls, typing.Generic)) - and getattr(cls, "_is_protocol", False) - ): - raise TypeError('@runtime_checkable can be only applied to protocol classes,' + if not issubclass(cls, typing.Generic) or not getattr(cls, '_is_protocol', False): + raise TypeError(f'@runtime_checkable can be only applied to protocol classes,' f' got {cls!r}') cls._is_runtime_protocol = True + + # typing.Protocol classes on <=3.11 break if we execute this block, + # because typing.Protocol classes on <=3.11 don't have a + # `__protocol_attrs__` attribute, and this block relies on the + # `__protocol_attrs__` attribute. Meanwhile, typing.Protocol classes on 3.12.2+ + # break if we *don't* execute this block, because *they* assume that all + # protocol classes have a `__non_callable_proto_members__` attribute + # (which this block sets) + if isinstance(cls, _ProtocolMeta) or sys.version_info >= (3, 12, 2): + # PEP 544 prohibits using issubclass() + # with protocols that have non-method members. + # See gh-113320 for why we compute this attribute here, + # rather than in `_ProtocolMeta.__init__` + cls.__non_callable_proto_members__ = set() + for attr in cls.__protocol_attrs__: + try: + is_callable = callable(getattr(cls, attr, None)) + except Exception as e: + raise TypeError( + f"Failed to determine whether protocol member {attr!r} " + "is a method member" + ) from e + else: + if not is_callable: + cls.__non_callable_proto_members__.add(attr) + return cls -# Exists for backwards compatibility. +# The "runtime" alias exists for backwards compatibility. runtime = runtime_checkable -# Our version of runtime-checkable protocols is faster on Python 3.7-3.11 +# Our version of runtime-checkable protocols is faster on Python 3.8-3.11 if sys.version_info >= (3, 12): SupportsInt = typing.SupportsInt SupportsFloat = typing.SupportsFloat @@ -968,7 +867,11 @@ def _ensure_subclassable(mro_entries): return inner -if sys.version_info >= (3, 13): +# Update this to something like >=3.13.0b1 if and when +# PEP 728 is implemented in CPython +_PEP_728_IMPLEMENTED = False + +if _PEP_728_IMPLEMENTED: # The standard library TypedDict in Python 3.8 does not store runtime information # about which (if any) keys are optional. See https://bugs.python.org/issue38834 # The standard library TypedDict in Python 3.9.0/1 does not honour the "total" @@ -979,6 +882,8 @@ if sys.version_info >= (3, 13): # Aaaand on 3.12 we add __orig_bases__ to TypedDict # to enable better runtime introspection. # On 3.13 we deprecate some odd ways of creating TypedDicts. + # Also on 3.13, PEP 705 adds the ReadOnly[] qualifier. + # PEP 728 (still pending) makes more changes. TypedDict = typing.TypedDict _TypedDictMeta = typing._TypedDictMeta is_typeddict = typing.is_typeddict @@ -986,13 +891,29 @@ else: # 3.10.0 and later _TAKES_MODULE = "module" in inspect.signature(typing._type_check).parameters - if sys.version_info >= (3, 8): - _fake_name = "Protocol" - else: - _fake_name = "_Protocol" + def _get_typeddict_qualifiers(annotation_type): + while True: + annotation_origin = get_origin(annotation_type) + if annotation_origin is Annotated: + annotation_args = get_args(annotation_type) + if annotation_args: + annotation_type = annotation_args[0] + else: + break + elif annotation_origin is Required: + yield Required + annotation_type, = get_args(annotation_type) + elif annotation_origin is NotRequired: + yield NotRequired + annotation_type, = get_args(annotation_type) + elif annotation_origin is ReadOnly: + yield ReadOnly + annotation_type, = get_args(annotation_type) + else: + break class _TypedDictMeta(type): - def __new__(cls, name, bases, ns, total=True): + def __new__(cls, name, bases, ns, *, total=True, closed=False): """Create new typed dict class object. This method is called when TypedDict is subclassed, @@ -1011,17 +932,23 @@ else: generic_base = () # typing.py generally doesn't let you inherit from plain Generic, unless - # the name of the class happens to be "Protocol" (or "_Protocol" on 3.7). - tp_dict = type.__new__(_TypedDictMeta, _fake_name, (*generic_base, dict), ns) + # the name of the class happens to be "Protocol" + tp_dict = type.__new__(_TypedDictMeta, "Protocol", (*generic_base, dict), ns) tp_dict.__name__ = name - if tp_dict.__qualname__ == _fake_name: + if tp_dict.__qualname__ == "Protocol": tp_dict.__qualname__ = name if not hasattr(tp_dict, '__orig_bases__'): tp_dict.__orig_bases__ = bases annotations = {} - own_annotations = ns.get('__annotations__', {}) + if "__annotations__" in ns: + own_annotations = ns["__annotations__"] + elif "__annotate__" in ns: + # TODO: Use inspect.VALUE here, and make the annotations lazily evaluated + own_annotations = ns["__annotate__"](1) + else: + own_annotations = {} msg = "TypedDict('Name', {f0: t0, f1: t1, ...}); each t must be a type" if _TAKES_MODULE: own_annotations = { @@ -1035,35 +962,67 @@ else: } required_keys = set() optional_keys = set() + readonly_keys = set() + mutable_keys = set() + extra_items_type = None for base in bases: - annotations.update(base.__dict__.get('__annotations__', {})) - required_keys.update(base.__dict__.get('__required_keys__', ())) - optional_keys.update(base.__dict__.get('__optional_keys__', ())) + base_dict = base.__dict__ + + annotations.update(base_dict.get('__annotations__', {})) + required_keys.update(base_dict.get('__required_keys__', ())) + optional_keys.update(base_dict.get('__optional_keys__', ())) + readonly_keys.update(base_dict.get('__readonly_keys__', ())) + mutable_keys.update(base_dict.get('__mutable_keys__', ())) + base_extra_items_type = base_dict.get('__extra_items__', None) + if base_extra_items_type is not None: + extra_items_type = base_extra_items_type + + if closed and extra_items_type is None: + extra_items_type = Never + if closed and "__extra_items__" in own_annotations: + annotation_type = own_annotations.pop("__extra_items__") + qualifiers = set(_get_typeddict_qualifiers(annotation_type)) + if Required in qualifiers: + raise TypeError( + "Special key __extra_items__ does not support " + "Required" + ) + if NotRequired in qualifiers: + raise TypeError( + "Special key __extra_items__ does not support " + "NotRequired" + ) + extra_items_type = annotation_type annotations.update(own_annotations) for annotation_key, annotation_type in own_annotations.items(): - annotation_origin = get_origin(annotation_type) - if annotation_origin is Annotated: - annotation_args = get_args(annotation_type) - if annotation_args: - annotation_type = annotation_args[0] - annotation_origin = get_origin(annotation_type) + qualifiers = set(_get_typeddict_qualifiers(annotation_type)) - if annotation_origin is Required: + if Required in qualifiers: required_keys.add(annotation_key) - elif annotation_origin is NotRequired: + elif NotRequired in qualifiers: optional_keys.add(annotation_key) elif total: required_keys.add(annotation_key) else: optional_keys.add(annotation_key) + if ReadOnly in qualifiers: + mutable_keys.discard(annotation_key) + readonly_keys.add(annotation_key) + else: + mutable_keys.add(annotation_key) + readonly_keys.discard(annotation_key) tp_dict.__annotations__ = annotations tp_dict.__required_keys__ = frozenset(required_keys) tp_dict.__optional_keys__ = frozenset(optional_keys) + tp_dict.__readonly_keys__ = frozenset(readonly_keys) + tp_dict.__mutable_keys__ = frozenset(mutable_keys) if not hasattr(tp_dict, '__total__'): tp_dict.__total__ = total + tp_dict.__closed__ = closed + tp_dict.__extra_items__ = extra_items_type return tp_dict __call__ = dict # static method @@ -1077,7 +1036,7 @@ else: _TypedDict = type.__new__(_TypedDictMeta, 'TypedDict', (), {}) @_ensure_subclassable(lambda bases: (_TypedDict,)) - def TypedDict(__typename, __fields=_marker, *, total=True, **kwargs): + def TypedDict(typename, fields=_marker, /, *, total=True, closed=False, **kwargs): """A simple typed namespace. At runtime it is equivalent to a plain dict. TypedDict creates a dictionary type such that a type checker will expect all @@ -1124,24 +1083,29 @@ else: See PEP 655 for more details on Required and NotRequired. """ - if __fields is _marker or __fields is None: - if __fields is _marker: + if fields is _marker or fields is None: + if fields is _marker: deprecated_thing = "Failing to pass a value for the 'fields' parameter" else: deprecated_thing = "Passing `None` as the 'fields' parameter" - example = f"`{__typename} = TypedDict({__typename!r}, {{}})`" + example = f"`{typename} = TypedDict({typename!r}, {{}})`" deprecation_msg = ( f"{deprecated_thing} is deprecated and will be disallowed in " "Python 3.15. To create a TypedDict class with 0 fields " "using the functional syntax, pass an empty dictionary, e.g. " ) + example + "." warnings.warn(deprecation_msg, DeprecationWarning, stacklevel=2) - __fields = kwargs + if closed is not False and closed is not True: + kwargs["closed"] = closed + closed = False + fields = kwargs elif kwargs: raise TypeError("TypedDict takes either a dict or keyword arguments," " but not both") if kwargs: + if sys.version_info >= (3, 13): + raise TypeError("TypedDict takes no keyword arguments") warnings.warn( "The kwargs-based syntax for TypedDict definitions is deprecated " "in Python 3.11, will be removed in Python 3.13, and may not be " @@ -1150,13 +1114,13 @@ else: stacklevel=2, ) - ns = {'__annotations__': dict(__fields)} + ns = {'__annotations__': dict(fields)} module = _caller() if module is not None: # Setting correct module is necessary to make typed dict classes pickleable. ns['__module__'] = module - td = _TypedDictMeta(__typename, (), ns, total=total) + td = _TypedDictMeta(typename, (), ns, total=total, closed=closed) td.__orig_bases__ = (TypedDict,) return td @@ -1186,7 +1150,7 @@ if hasattr(typing, "assert_type"): assert_type = typing.assert_type else: - def assert_type(__val, __typ): + def assert_type(val, typ, /): """Assert (to the type checker) that the value is of the given type. When the type checker encounters a call to assert_type(), it @@ -1199,18 +1163,18 @@ else: At runtime this returns the first argument unchanged and otherwise does nothing. """ - return __val + return val -if hasattr(typing, "Required"): +if hasattr(typing, "ReadOnly"): # 3.13+ get_type_hints = typing.get_type_hints -else: +else: # <=3.13 # replaces _strip_annotations() def _strip_extras(t): """Strips Annotated, Required and NotRequired from a given type.""" if isinstance(t, _AnnotatedAlias): return _strip_extras(t.__origin__) - if hasattr(t, "__origin__") and t.__origin__ in (Required, NotRequired): + if hasattr(t, "__origin__") and t.__origin__ in (Required, NotRequired, ReadOnly): return _strip_extras(t.__args__[0]) if isinstance(t, typing._GenericAlias): stripped_args = tuple(_strip_extras(a) for a in t.__args__) @@ -1262,11 +1226,11 @@ else: - If two dict arguments are passed, they specify globals and locals, respectively. """ - if hasattr(typing, "Annotated"): + if hasattr(typing, "Annotated"): # 3.9+ hint = typing.get_type_hints( obj, globalns=globalns, localns=localns, include_extras=True ) - else: + else: # 3.8 hint = typing.get_type_hints(obj, globalns=globalns, localns=localns) if include_extras: return hint @@ -1279,7 +1243,7 @@ if hasattr(typing, 'Annotated'): # Not exported and not a public API, but needed for get_origin() and get_args() # to work. _AnnotatedAlias = typing._AnnotatedAlias -# 3.7-3.8 +# 3.8 else: class _AnnotatedAlias(typing._GenericAlias, _root=True): """Runtime representation of an annotated type. @@ -1307,7 +1271,7 @@ else: def __reduce__(self): return operator.getitem, ( - Annotated, (self.__origin__,) + self.__metadata__ + Annotated, (self.__origin__, *self.__metadata__) ) def __eq__(self, other): @@ -1384,7 +1348,7 @@ else: if sys.version_info[:2] >= (3, 10): get_origin = typing.get_origin get_args = typing.get_args -# 3.7-3.9 +# 3.8-3.9 else: try: # 3.9+ @@ -1433,7 +1397,7 @@ else: get_args(Callable[[], T][int]) == ([], int) """ if isinstance(tp, _AnnotatedAlias): - return (tp.__origin__,) + tp.__metadata__ + return (tp.__origin__, *tp.__metadata__) if isinstance(tp, (typing._GenericAlias, _typing_GenericAlias)): if getattr(tp, "_special", False): return () @@ -1462,7 +1426,7 @@ elif sys.version_info[:2] >= (3, 9): It's invalid when used anywhere except as in the example above. """ raise TypeError(f"{self} is not subscriptable") -# 3.7-3.8 +# 3.8 else: TypeAlias = _ExtensionsSpecialForm( 'TypeAlias', @@ -1479,14 +1443,37 @@ else: ) +if hasattr(typing, "NoDefault"): + NoDefault = typing.NoDefault +else: + class NoDefaultTypeMeta(type): + def __setattr__(cls, attr, value): + # TypeError is consistent with the behavior of NoneType + raise TypeError( + f"cannot set {attr!r} attribute of immutable type {cls.__name__!r}" + ) + + class NoDefaultType(metaclass=NoDefaultTypeMeta): + """The type of the NoDefault singleton.""" + + __slots__ = () + + def __new__(cls): + return globals().get("NoDefault") or object.__new__(cls) + + def __repr__(self): + return "typing_extensions.NoDefault" + + def __reduce__(self): + return "NoDefault" + + NoDefault = NoDefaultType() + del NoDefaultType, NoDefaultTypeMeta + + def _set_default(type_param, default): - if isinstance(default, (tuple, list)): - type_param.__default__ = tuple((typing._type_check(d, "Default must be a type") - for d in default)) - elif default != _marker: - type_param.__default__ = typing._type_check(default, "Default must be a type") - else: - type_param.__default__ = None + type_param.has_default = lambda: default is not NoDefault + type_param.__default__ = default def _set_module(typevarlike): @@ -1509,39 +1496,53 @@ class _TypeVarLikeMeta(type): return isinstance(__instance, cls._backported_typevarlike) -# Add default and infer_variance parameters from PEP 696 and 695 -class TypeVar(metaclass=_TypeVarLikeMeta): - """Type variable.""" +if _PEP_696_IMPLEMENTED: + from typing import TypeVar +else: + # Add default and infer_variance parameters from PEP 696 and 695 + class TypeVar(metaclass=_TypeVarLikeMeta): + """Type variable.""" - _backported_typevarlike = typing.TypeVar + _backported_typevarlike = typing.TypeVar - def __new__(cls, name, *constraints, bound=None, - covariant=False, contravariant=False, - default=_marker, infer_variance=False): - if hasattr(typing, "TypeAliasType"): - # PEP 695 implemented, can pass infer_variance to typing.TypeVar - typevar = typing.TypeVar(name, *constraints, bound=bound, - covariant=covariant, contravariant=contravariant, - infer_variance=infer_variance) - else: - typevar = typing.TypeVar(name, *constraints, bound=bound, - covariant=covariant, contravariant=contravariant) - if infer_variance and (covariant or contravariant): - raise ValueError("Variance cannot be specified with infer_variance.") - typevar.__infer_variance__ = infer_variance - _set_default(typevar, default) - _set_module(typevar) - return typevar + def __new__(cls, name, *constraints, bound=None, + covariant=False, contravariant=False, + default=NoDefault, infer_variance=False): + if hasattr(typing, "TypeAliasType"): + # PEP 695 implemented (3.12+), can pass infer_variance to typing.TypeVar + typevar = typing.TypeVar(name, *constraints, bound=bound, + covariant=covariant, contravariant=contravariant, + infer_variance=infer_variance) + else: + typevar = typing.TypeVar(name, *constraints, bound=bound, + covariant=covariant, contravariant=contravariant) + if infer_variance and (covariant or contravariant): + raise ValueError("Variance cannot be specified with infer_variance.") + typevar.__infer_variance__ = infer_variance - def __init_subclass__(cls) -> None: - raise TypeError(f"type '{__name__}.TypeVar' is not an acceptable base type") + _set_default(typevar, default) + _set_module(typevar) + + def _tvar_prepare_subst(alias, args): + if ( + typevar.has_default() + and alias.__parameters__.index(typevar) == len(args) + ): + args += (typevar.__default__,) + return args + + typevar.__typing_prepare_subst__ = _tvar_prepare_subst + return typevar + + def __init_subclass__(cls) -> None: + raise TypeError(f"type '{__name__}.TypeVar' is not an acceptable base type") # Python 3.10+ has PEP 612 if hasattr(typing, 'ParamSpecArgs'): ParamSpecArgs = typing.ParamSpecArgs ParamSpecKwargs = typing.ParamSpecKwargs -# 3.7-3.9 +# 3.8-3.9 else: class _Immutable: """Mixin to indicate that object should not be copied.""" @@ -1599,8 +1600,12 @@ else: return NotImplemented return self.__origin__ == other.__origin__ + +if _PEP_696_IMPLEMENTED: + from typing import ParamSpec + # 3.10+ -if hasattr(typing, 'ParamSpec'): +elif hasattr(typing, 'ParamSpec'): # Add default parameter - PEP 696 class ParamSpec(metaclass=_TypeVarLikeMeta): @@ -1610,7 +1615,7 @@ if hasattr(typing, 'ParamSpec'): def __new__(cls, name, *, bound=None, covariant=False, contravariant=False, - infer_variance=False, default=_marker): + infer_variance=False, default=NoDefault): if hasattr(typing, "TypeAliasType"): # PEP 695 implemented, can pass infer_variance to typing.TypeVar paramspec = typing.ParamSpec(name, bound=bound, @@ -1625,12 +1630,30 @@ if hasattr(typing, 'ParamSpec'): _set_default(paramspec, default) _set_module(paramspec) + + def _paramspec_prepare_subst(alias, args): + params = alias.__parameters__ + i = params.index(paramspec) + if i == len(args) and paramspec.has_default(): + args = [*args, paramspec.__default__] + if i >= len(args): + raise TypeError(f"Too few arguments for {alias}") + # Special case where Z[[int, str, bool]] == Z[int, str, bool] in PEP 612. + if len(params) == 1 and not typing._is_param_expr(args[0]): + assert i == 0 + args = (args,) + # Convert lists to tuples to help other libraries cache the results. + elif isinstance(args[i], list): + args = (*args[:i], tuple(args[i]), *args[i + 1:]) + return args + + paramspec.__typing_prepare_subst__ = _paramspec_prepare_subst return paramspec def __init_subclass__(cls) -> None: raise TypeError(f"type '{__name__}.ParamSpec' is not an acceptable base type") -# 3.7-3.9 +# 3.8-3.9 else: # Inherits from list as a workaround for Callable checks in Python < 3.9.2. @@ -1693,8 +1716,8 @@ else: return ParamSpecKwargs(self) def __init__(self, name, *, bound=None, covariant=False, contravariant=False, - infer_variance=False, default=_marker): - super().__init__([self]) + infer_variance=False, default=NoDefault): + list.__init__(self, [self]) self.__name__ = name self.__covariant__ = bool(covariant) self.__contravariant__ = bool(contravariant) @@ -1735,7 +1758,7 @@ else: pass -# 3.7-3.9 +# 3.8-3.9 if not hasattr(typing, 'Concatenate'): # Inherits from list as a workaround for Callable checks in Python < 3.9.2. class _ConcatenateGenericAlias(list): @@ -1770,7 +1793,7 @@ if not hasattr(typing, 'Concatenate'): ) -# 3.7-3.9 +# 3.8-3.9 @typing._tp_cache def _concatenate_getitem(self, parameters): if parameters == (): @@ -1788,7 +1811,7 @@ def _concatenate_getitem(self, parameters): # 3.10+ if hasattr(typing, 'Concatenate'): Concatenate = typing.Concatenate - _ConcatenateGenericAlias = typing._ConcatenateGenericAlias # noqa: F811 + _ConcatenateGenericAlias = typing._ConcatenateGenericAlias # 3.9 elif sys.version_info[:2] >= (3, 9): @_ExtensionsSpecialForm @@ -1804,7 +1827,7 @@ elif sys.version_info[:2] >= (3, 9): See PEP 612 for detailed information. """ return _concatenate_getitem(self, parameters) -# 3.7-8 +# 3.8 else: class _ConcatenateForm(_ExtensionsSpecialForm, _root=True): def __getitem__(self, parameters): @@ -1874,7 +1897,7 @@ elif sys.version_info[:2] >= (3, 9): """ item = typing._type_check(parameters, f'{self} accepts only a single type.') return typing._GenericAlias(self, (item,)) -# 3.7-3.8 +# 3.8 else: class _TypeGuardForm(_ExtensionsSpecialForm, _root=True): def __getitem__(self, parameters): @@ -1927,6 +1950,98 @@ else: PEP 647 (User-Defined Type Guards). """) +# 3.13+ +if hasattr(typing, 'TypeIs'): + TypeIs = typing.TypeIs +# 3.9 +elif sys.version_info[:2] >= (3, 9): + @_ExtensionsSpecialForm + def TypeIs(self, parameters): + """Special typing form used to annotate the return type of a user-defined + type narrower function. ``TypeIs`` only accepts a single type argument. + At runtime, functions marked this way should return a boolean. + + ``TypeIs`` aims to benefit *type narrowing* -- a technique used by static + type checkers to determine a more precise type of an expression within a + program's code flow. Usually type narrowing is done by analyzing + conditional code flow and applying the narrowing to a block of code. The + conditional expression here is sometimes referred to as a "type guard". + + Sometimes it would be convenient to use a user-defined boolean function + as a type guard. Such a function should use ``TypeIs[...]`` as its + return type to alert static type checkers to this intention. + + Using ``-> TypeIs`` tells the static type checker that for a given + function: + + 1. The return value is a boolean. + 2. If the return value is ``True``, the type of its argument + is the intersection of the type inside ``TypeGuard`` and the argument's + previously known type. + + For example:: + + def is_awaitable(val: object) -> TypeIs[Awaitable[Any]]: + return hasattr(val, '__await__') + + def f(val: Union[int, Awaitable[int]]) -> int: + if is_awaitable(val): + assert_type(val, Awaitable[int]) + else: + assert_type(val, int) + + ``TypeIs`` also works with type variables. For more information, see + PEP 742 (Narrowing types with TypeIs). + """ + item = typing._type_check(parameters, f'{self} accepts only a single type.') + return typing._GenericAlias(self, (item,)) +# 3.8 +else: + class _TypeIsForm(_ExtensionsSpecialForm, _root=True): + def __getitem__(self, parameters): + item = typing._type_check(parameters, + f'{self._name} accepts only a single type') + return typing._GenericAlias(self, (item,)) + + TypeIs = _TypeIsForm( + 'TypeIs', + doc="""Special typing form used to annotate the return type of a user-defined + type narrower function. ``TypeIs`` only accepts a single type argument. + At runtime, functions marked this way should return a boolean. + + ``TypeIs`` aims to benefit *type narrowing* -- a technique used by static + type checkers to determine a more precise type of an expression within a + program's code flow. Usually type narrowing is done by analyzing + conditional code flow and applying the narrowing to a block of code. The + conditional expression here is sometimes referred to as a "type guard". + + Sometimes it would be convenient to use a user-defined boolean function + as a type guard. Such a function should use ``TypeIs[...]`` as its + return type to alert static type checkers to this intention. + + Using ``-> TypeIs`` tells the static type checker that for a given + function: + + 1. The return value is a boolean. + 2. If the return value is ``True``, the type of its argument + is the intersection of the type inside ``TypeGuard`` and the argument's + previously known type. + + For example:: + + def is_awaitable(val: object) -> TypeIs[Awaitable[Any]]: + return hasattr(val, '__await__') + + def f(val: Union[int, Awaitable[int]]) -> int: + if is_awaitable(val): + assert_type(val, Awaitable[int]) + else: + assert_type(val, int) + + ``TypeIs`` also works with type variables. For more information, see + PEP 742 (Narrowing types with TypeIs). + """) + # Vendored from cpython typing._SpecialFrom class _SpecialForm(typing._Final, _root=True): @@ -1972,7 +2087,7 @@ class _SpecialForm(typing._Final, _root=True): return self._getitem(self, parameters) -if hasattr(typing, "LiteralString"): +if hasattr(typing, "LiteralString"): # 3.11+ LiteralString = typing.LiteralString else: @_SpecialForm @@ -1995,7 +2110,7 @@ else: raise TypeError(f"{self} is not subscriptable") -if hasattr(typing, "Self"): +if hasattr(typing, "Self"): # 3.11+ Self = typing.Self else: @_SpecialForm @@ -2016,7 +2131,7 @@ else: raise TypeError(f"{self} is not subscriptable") -if hasattr(typing, "Never"): +if hasattr(typing, "Never"): # 3.11+ Never = typing.Never else: @_SpecialForm @@ -2046,10 +2161,10 @@ else: raise TypeError(f"{self} is not subscriptable") -if hasattr(typing, 'Required'): +if hasattr(typing, 'Required'): # 3.11+ Required = typing.Required NotRequired = typing.NotRequired -elif sys.version_info[:2] >= (3, 9): +elif sys.version_info[:2] >= (3, 9): # 3.9-3.10 @_ExtensionsSpecialForm def Required(self, parameters): """A special typing construct to mark a key of a total=False TypedDict @@ -2087,7 +2202,7 @@ elif sys.version_info[:2] >= (3, 9): item = typing._type_check(parameters, f'{self._name} accepts only a single type.') return typing._GenericAlias(self, (item,)) -else: +else: # 3.8 class _RequiredForm(_ExtensionsSpecialForm, _root=True): def __getitem__(self, parameters): item = typing._type_check(parameters, @@ -2127,6 +2242,53 @@ else: """) +if hasattr(typing, 'ReadOnly'): + ReadOnly = typing.ReadOnly +elif sys.version_info[:2] >= (3, 9): # 3.9-3.12 + @_ExtensionsSpecialForm + def ReadOnly(self, parameters): + """A special typing construct to mark an item of a TypedDict as read-only. + + For example: + + class Movie(TypedDict): + title: ReadOnly[str] + year: int + + def mutate_movie(m: Movie) -> None: + m["year"] = 1992 # allowed + m["title"] = "The Matrix" # typechecker error + + There is no runtime checking for this property. + """ + item = typing._type_check(parameters, f'{self._name} accepts only a single type.') + return typing._GenericAlias(self, (item,)) + +else: # 3.8 + class _ReadOnlyForm(_ExtensionsSpecialForm, _root=True): + def __getitem__(self, parameters): + item = typing._type_check(parameters, + f'{self._name} accepts only a single type.') + return typing._GenericAlias(self, (item,)) + + ReadOnly = _ReadOnlyForm( + 'ReadOnly', + doc="""A special typing construct to mark a key of a TypedDict as read-only. + + For example: + + class Movie(TypedDict): + title: ReadOnly[str] + year: int + + def mutate_movie(m: Movie) -> None: + m["year"] = 1992 # allowed + m["title"] = "The Matrix" # typechecker error + + There is no runtime checking for this propery. + """) + + _UNPACK_DOC = """\ Type unpack operator. @@ -2175,7 +2337,7 @@ if sys.version_info >= (3, 12): # PEP 692 changed the repr of Unpack[] def _is_unpack(obj): return get_origin(obj) is Unpack -elif sys.version_info[:2] >= (3, 9): +elif sys.version_info[:2] >= (3, 9): # 3.9+ class _UnpackSpecialForm(_ExtensionsSpecialForm, _root=True): def __init__(self, getitem): super().__init__(getitem) @@ -2184,6 +2346,17 @@ elif sys.version_info[:2] >= (3, 9): class _UnpackAlias(typing._GenericAlias, _root=True): __class__ = typing.TypeVar + @property + def __typing_unpacked_tuple_args__(self): + assert self.__origin__ is Unpack + assert len(self.__args__) == 1 + arg, = self.__args__ + if isinstance(arg, (typing._GenericAlias, _types.GenericAlias)): + if arg.__origin__ is not tuple: + raise TypeError("Unpack[...] must be used with a tuple type") + return arg.__args__ + return None + @_UnpackSpecialForm def Unpack(self, parameters): item = typing._type_check(parameters, f'{self._name} accepts only a single type.') @@ -2192,7 +2365,7 @@ elif sys.version_info[:2] >= (3, 9): def _is_unpack(obj): return isinstance(obj, _UnpackAlias) -else: +else: # 3.8 class _UnpackAlias(typing._GenericAlias, _root=True): __class__ = typing.TypeVar @@ -2208,7 +2381,20 @@ else: return isinstance(obj, _UnpackAlias) -if hasattr(typing, "TypeVarTuple"): # 3.11+ +if _PEP_696_IMPLEMENTED: + from typing import TypeVarTuple + +elif hasattr(typing, "TypeVarTuple"): # 3.11+ + + def _unpack_args(*args): + newargs = [] + for arg in args: + subargs = getattr(arg, '__typing_unpacked_tuple_args__', None) + if subargs is not None and not (subargs and subargs[-1] is ...): + newargs.extend(subargs) + else: + newargs.append(arg) + return newargs # Add default parameter - PEP 696 class TypeVarTuple(metaclass=_TypeVarLikeMeta): @@ -2216,16 +2402,63 @@ if hasattr(typing, "TypeVarTuple"): # 3.11+ _backported_typevarlike = typing.TypeVarTuple - def __new__(cls, name, *, default=_marker): + def __new__(cls, name, *, default=NoDefault): tvt = typing.TypeVarTuple(name) _set_default(tvt, default) _set_module(tvt) + + def _typevartuple_prepare_subst(alias, args): + params = alias.__parameters__ + typevartuple_index = params.index(tvt) + for param in params[typevartuple_index + 1:]: + if isinstance(param, TypeVarTuple): + raise TypeError( + f"More than one TypeVarTuple parameter in {alias}" + ) + + alen = len(args) + plen = len(params) + left = typevartuple_index + right = plen - typevartuple_index - 1 + var_tuple_index = None + fillarg = None + for k, arg in enumerate(args): + if not isinstance(arg, type): + subargs = getattr(arg, '__typing_unpacked_tuple_args__', None) + if subargs and len(subargs) == 2 and subargs[-1] is ...: + if var_tuple_index is not None: + raise TypeError( + "More than one unpacked " + "arbitrary-length tuple argument" + ) + var_tuple_index = k + fillarg = subargs[0] + if var_tuple_index is not None: + left = min(left, var_tuple_index) + right = min(right, alen - var_tuple_index - 1) + elif left + right > alen: + raise TypeError(f"Too few arguments for {alias};" + f" actual {alen}, expected at least {plen - 1}") + if left == alen - right and tvt.has_default(): + replacement = _unpack_args(tvt.__default__) + else: + replacement = args[left: alen - right] + + return ( + *args[:left], + *([fillarg] * (typevartuple_index - left)), + replacement, + *([fillarg] * (plen - right - left - typevartuple_index - 1)), + *args[alen - right:], + ) + + tvt.__typing_prepare_subst__ = _typevartuple_prepare_subst return tvt def __init_subclass__(self, *args, **kwds): raise TypeError("Cannot subclass special typing classes") -else: +else: # <=3.10 class TypeVarTuple(_DefaultMixin): """Type variable tuple. @@ -2276,7 +2509,7 @@ else: def __iter__(self): yield self.__unpacked__ - def __init__(self, name, *, default=_marker): + def __init__(self, name, *, default=NoDefault): self.__name__ = name _DefaultMixin.__init__(self, default) @@ -2304,10 +2537,10 @@ else: raise TypeError("Cannot subclass special typing classes") -if hasattr(typing, "reveal_type"): +if hasattr(typing, "reveal_type"): # 3.11+ reveal_type = typing.reveal_type -else: - def reveal_type(__obj: T) -> T: +else: # <=3.10 + def reveal_type(obj: T, /) -> T: """Reveal the inferred type of a variable. When a static type checker encounters a call to ``reveal_type()``, @@ -2323,14 +2556,20 @@ else: argument and returns it unchanged. """ - print(f"Runtime type is {type(__obj).__name__!r}", file=sys.stderr) - return __obj + print(f"Runtime type is {type(obj).__name__!r}", file=sys.stderr) + return obj -if hasattr(typing, "assert_never"): +if hasattr(typing, "_ASSERT_NEVER_REPR_MAX_LENGTH"): # 3.11+ + _ASSERT_NEVER_REPR_MAX_LENGTH = typing._ASSERT_NEVER_REPR_MAX_LENGTH +else: # <=3.10 + _ASSERT_NEVER_REPR_MAX_LENGTH = 100 + + +if hasattr(typing, "assert_never"): # 3.11+ assert_never = typing.assert_never -else: - def assert_never(__arg: Never) -> Never: +else: # <=3.10 + def assert_never(arg: Never, /) -> Never: """Assert to the type checker that a line of code is unreachable. Example:: @@ -2350,13 +2589,16 @@ else: At runtime, this throws an exception when called. """ - raise AssertionError("Expected code to be unreachable") + value = repr(arg) + if len(value) > _ASSERT_NEVER_REPR_MAX_LENGTH: + value = value[:_ASSERT_NEVER_REPR_MAX_LENGTH] + '...' + raise AssertionError(f"Expected code to be unreachable, but got: {value}") -if sys.version_info >= (3, 12): +if sys.version_info >= (3, 12): # 3.12+ # dataclass_transform exists in 3.11 but lacks the frozen_default parameter dataclass_transform = typing.dataclass_transform -else: +else: # <=3.11 def dataclass_transform( *, eq_default: bool = True, @@ -2443,18 +2685,18 @@ else: return decorator -if hasattr(typing, "override"): +if hasattr(typing, "override"): # 3.12+ override = typing.override -else: +else: # <=3.11 _F = typing.TypeVar("_F", bound=typing.Callable[..., typing.Any]) - def override(__arg: _F) -> _F: + def override(arg: _F, /) -> _F: """Indicate that a method is intended to override a method in a base class. Usage: class Base: - def method(self) -> None: ... + def method(self) -> None: pass class Child(Base): @@ -2475,28 +2717,26 @@ else: """ try: - __arg.__override__ = True + arg.__override__ = True except (AttributeError, TypeError): # Skip the attribute silently if it is not writable. # AttributeError happens if the object has __slots__ or a # read-only property, TypeError if it's a builtin class. pass - return __arg + return arg -if hasattr(typing, "deprecated"): - deprecated = typing.deprecated +if hasattr(warnings, "deprecated"): + deprecated = warnings.deprecated else: _T = typing.TypeVar("_T") - def deprecated( - __msg: str, - *, - category: typing.Optional[typing.Type[Warning]] = DeprecationWarning, - stacklevel: int = 1, - ) -> typing.Callable[[_T], _T]: + class deprecated: """Indicate that a class, function or overload is deprecated. + When this decorator is applied to an object, the type checker + will generate a diagnostic on usage of the deprecated object. + Usage: @deprecated("Use B instead") @@ -2513,64 +2753,113 @@ else: @overload def g(x: str) -> int: ... - When this decorator is applied to an object, the type checker - will generate a diagnostic on usage of the deprecated object. - - The warning specified by ``category`` will be emitted on use - of deprecated objects. For functions, that happens on calls; - for classes, on instantiation. If the ``category`` is ``None``, - no warning is emitted. The ``stacklevel`` determines where the + The warning specified by *category* will be emitted at runtime + on use of deprecated objects. For functions, that happens on calls; + for classes, on instantiation and on creation of subclasses. + If the *category* is ``None``, no warning is emitted at runtime. + The *stacklevel* determines where the warning is emitted. If it is ``1`` (the default), the warning is emitted at the direct caller of the deprecated object; if it is higher, it is emitted further up the stack. + Static type checker behavior is not affected by the *category* + and *stacklevel* arguments. - The decorator sets the ``__deprecated__`` - attribute on the decorated object to the deprecation message - passed to the decorator. If applied to an overload, the decorator + The deprecation message passed to the decorator is saved in the + ``__deprecated__`` attribute on the decorated object. + If applied to an overload, the decorator must be after the ``@overload`` decorator for the attribute to exist on the overload as returned by ``get_overloads()``. See PEP 702 for details. """ - def decorator(__arg: _T) -> _T: + def __init__( + self, + message: str, + /, + *, + category: typing.Optional[typing.Type[Warning]] = DeprecationWarning, + stacklevel: int = 1, + ) -> None: + if not isinstance(message, str): + raise TypeError( + "Expected an object of type str for 'message', not " + f"{type(message).__name__!r}" + ) + self.message = message + self.category = category + self.stacklevel = stacklevel + + def __call__(self, arg: _T, /) -> _T: + # Make sure the inner functions created below don't + # retain a reference to self. + msg = self.message + category = self.category + stacklevel = self.stacklevel if category is None: - __arg.__deprecated__ = __msg - return __arg - elif isinstance(__arg, type): - original_new = __arg.__new__ - has_init = __arg.__init__ is not object.__init__ + arg.__deprecated__ = msg + return arg + elif isinstance(arg, type): + import functools + from types import MethodType + + original_new = arg.__new__ @functools.wraps(original_new) def __new__(cls, *args, **kwargs): - warnings.warn(__msg, category=category, stacklevel=stacklevel + 1) + if cls is arg: + warnings.warn(msg, category=category, stacklevel=stacklevel + 1) if original_new is not object.__new__: return original_new(cls, *args, **kwargs) # Mirrors a similar check in object.__new__. - elif not has_init and (args or kwargs): + elif cls.__init__ is object.__init__ and (args or kwargs): raise TypeError(f"{cls.__name__}() takes no arguments") else: return original_new(cls) - __arg.__new__ = staticmethod(__new__) - __arg.__deprecated__ = __new__.__deprecated__ = __msg - return __arg - elif callable(__arg): - @functools.wraps(__arg) - def wrapper(*args, **kwargs): - warnings.warn(__msg, category=category, stacklevel=stacklevel + 1) - return __arg(*args, **kwargs) + arg.__new__ = staticmethod(__new__) - __arg.__deprecated__ = wrapper.__deprecated__ = __msg + original_init_subclass = arg.__init_subclass__ + # We need slightly different behavior if __init_subclass__ + # is a bound method (likely if it was implemented in Python) + if isinstance(original_init_subclass, MethodType): + original_init_subclass = original_init_subclass.__func__ + + @functools.wraps(original_init_subclass) + def __init_subclass__(*args, **kwargs): + warnings.warn(msg, category=category, stacklevel=stacklevel + 1) + return original_init_subclass(*args, **kwargs) + + arg.__init_subclass__ = classmethod(__init_subclass__) + # Or otherwise, which likely means it's a builtin such as + # object's implementation of __init_subclass__. + else: + @functools.wraps(original_init_subclass) + def __init_subclass__(*args, **kwargs): + warnings.warn(msg, category=category, stacklevel=stacklevel + 1) + return original_init_subclass(*args, **kwargs) + + arg.__init_subclass__ = __init_subclass__ + + arg.__deprecated__ = __new__.__deprecated__ = msg + __init_subclass__.__deprecated__ = msg + return arg + elif callable(arg): + import functools + + @functools.wraps(arg) + def wrapper(*args, **kwargs): + warnings.warn(msg, category=category, stacklevel=stacklevel + 1) + return arg(*args, **kwargs) + + arg.__deprecated__ = wrapper.__deprecated__ = msg return wrapper else: raise TypeError( "@deprecated decorator with non-None category must be applied to " - f"a class or callable, not {__arg!r}" + f"a class or callable, not {arg!r}" ) - return decorator - # We have to do some monkey patching to deal with the dual nature of # Unpack/TypeVarTuple: @@ -2580,11 +2869,223 @@ else: # counting generic parameters, so that when we subscript a generic, # the runtime doesn't try to substitute the Unpack with the subscripted type. if not hasattr(typing, "TypeVarTuple"): - typing._collect_type_vars = _collect_type_vars + def _check_generic(cls, parameters, elen=_marker): + """Check correct count for parameters of a generic cls (internal helper). + + This gives a nice error message in case of count mismatch. + """ + if not elen: + raise TypeError(f"{cls} is not a generic class") + if elen is _marker: + if not hasattr(cls, "__parameters__") or not cls.__parameters__: + raise TypeError(f"{cls} is not a generic class") + elen = len(cls.__parameters__) + alen = len(parameters) + if alen != elen: + expect_val = elen + if hasattr(cls, "__parameters__"): + parameters = [p for p in cls.__parameters__ if not _is_unpack(p)] + num_tv_tuples = sum(isinstance(p, TypeVarTuple) for p in parameters) + if (num_tv_tuples > 0) and (alen >= elen - num_tv_tuples): + return + + # deal with TypeVarLike defaults + # required TypeVarLikes cannot appear after a defaulted one. + if alen < elen: + # since we validate TypeVarLike default in _collect_type_vars + # or _collect_parameters we can safely check parameters[alen] + if ( + getattr(parameters[alen], '__default__', NoDefault) + is not NoDefault + ): + return + + num_default_tv = sum(getattr(p, '__default__', NoDefault) + is not NoDefault for p in parameters) + + elen -= num_default_tv + + expect_val = f"at least {elen}" + + things = "arguments" if sys.version_info >= (3, 10) else "parameters" + raise TypeError(f"Too {'many' if alen > elen else 'few'} {things}" + f" for {cls}; actual {alen}, expected {expect_val}") +else: + # Python 3.11+ + + def _check_generic(cls, parameters, elen): + """Check correct count for parameters of a generic cls (internal helper). + + This gives a nice error message in case of count mismatch. + """ + if not elen: + raise TypeError(f"{cls} is not a generic class") + alen = len(parameters) + if alen != elen: + expect_val = elen + if hasattr(cls, "__parameters__"): + parameters = [p for p in cls.__parameters__ if not _is_unpack(p)] + + # deal with TypeVarLike defaults + # required TypeVarLikes cannot appear after a defaulted one. + if alen < elen: + # since we validate TypeVarLike default in _collect_type_vars + # or _collect_parameters we can safely check parameters[alen] + if ( + getattr(parameters[alen], '__default__', NoDefault) + is not NoDefault + ): + return + + num_default_tv = sum(getattr(p, '__default__', NoDefault) + is not NoDefault for p in parameters) + + elen -= num_default_tv + + expect_val = f"at least {elen}" + + raise TypeError(f"Too {'many' if alen > elen else 'few'} arguments" + f" for {cls}; actual {alen}, expected {expect_val}") + +if not _PEP_696_IMPLEMENTED: typing._check_generic = _check_generic -# Backport typing.NamedTuple as it exists in Python 3.12. +def _has_generic_or_protocol_as_origin() -> bool: + try: + frame = sys._getframe(2) + # - Catch AttributeError: not all Python implementations have sys._getframe() + # - Catch ValueError: maybe we're called from an unexpected module + # and the call stack isn't deep enough + except (AttributeError, ValueError): + return False # err on the side of leniency + else: + # If we somehow get invoked from outside typing.py, + # also err on the side of leniency + if frame.f_globals.get("__name__") != "typing": + return False + origin = frame.f_locals.get("origin") + # Cannot use "in" because origin may be an object with a buggy __eq__ that + # throws an error. + return origin is typing.Generic or origin is Protocol or origin is typing.Protocol + + +_TYPEVARTUPLE_TYPES = {TypeVarTuple, getattr(typing, "TypeVarTuple", None)} + + +def _is_unpacked_typevartuple(x) -> bool: + if get_origin(x) is not Unpack: + return False + args = get_args(x) + return ( + bool(args) + and len(args) == 1 + and type(args[0]) in _TYPEVARTUPLE_TYPES + ) + + +# Python 3.11+ _collect_type_vars was renamed to _collect_parameters +if hasattr(typing, '_collect_type_vars'): + def _collect_type_vars(types, typevar_types=None): + """Collect all type variable contained in types in order of + first appearance (lexicographic order). For example:: + + _collect_type_vars((T, List[S, T])) == (T, S) + """ + if typevar_types is None: + typevar_types = typing.TypeVar + tvars = [] + + # A required TypeVarLike cannot appear after a TypeVarLike with a default + # if it was a direct call to `Generic[]` or `Protocol[]` + enforce_default_ordering = _has_generic_or_protocol_as_origin() + default_encountered = False + + # Also, a TypeVarLike with a default cannot appear after a TypeVarTuple + type_var_tuple_encountered = False + + for t in types: + if _is_unpacked_typevartuple(t): + type_var_tuple_encountered = True + elif isinstance(t, typevar_types) and t not in tvars: + if enforce_default_ordering: + has_default = getattr(t, '__default__', NoDefault) is not NoDefault + if has_default: + if type_var_tuple_encountered: + raise TypeError('Type parameter with a default' + ' follows TypeVarTuple') + default_encountered = True + elif default_encountered: + raise TypeError(f'Type parameter {t!r} without a default' + ' follows type parameter with a default') + + tvars.append(t) + if _should_collect_from_parameters(t): + tvars.extend([t for t in t.__parameters__ if t not in tvars]) + return tuple(tvars) + + typing._collect_type_vars = _collect_type_vars +else: + def _collect_parameters(args): + """Collect all type variables and parameter specifications in args + in order of first appearance (lexicographic order). + + For example:: + + assert _collect_parameters((T, Callable[P, T])) == (T, P) + """ + parameters = [] + + # A required TypeVarLike cannot appear after a TypeVarLike with default + # if it was a direct call to `Generic[]` or `Protocol[]` + enforce_default_ordering = _has_generic_or_protocol_as_origin() + default_encountered = False + + # Also, a TypeVarLike with a default cannot appear after a TypeVarTuple + type_var_tuple_encountered = False + + for t in args: + if isinstance(t, type): + # We don't want __parameters__ descriptor of a bare Python class. + pass + elif isinstance(t, tuple): + # `t` might be a tuple, when `ParamSpec` is substituted with + # `[T, int]`, or `[int, *Ts]`, etc. + for x in t: + for collected in _collect_parameters([x]): + if collected not in parameters: + parameters.append(collected) + elif hasattr(t, '__typing_subst__'): + if t not in parameters: + if enforce_default_ordering: + has_default = ( + getattr(t, '__default__', NoDefault) is not NoDefault + ) + + if type_var_tuple_encountered and has_default: + raise TypeError('Type parameter with a default' + ' follows TypeVarTuple') + + if has_default: + default_encountered = True + elif default_encountered: + raise TypeError(f'Type parameter {t!r} without a default' + ' follows type parameter with a default') + + parameters.append(t) + else: + if _is_unpacked_typevartuple(t): + type_var_tuple_encountered = True + for x in getattr(t, '__parameters__', ()): + if x not in parameters: + parameters.append(x) + + return tuple(parameters) + + if not _PEP_696_IMPLEMENTED: + typing._collect_parameters = _collect_parameters + +# Backport typing.NamedTuple as it exists in Python 3.13. # In 3.11, the ability to define generic `NamedTuple`s was supported. # This was explicitly disallowed in 3.9-3.10, and only half-worked in <=3.8. # On 3.12, we added __orig_bases__ to call-based NamedTuples @@ -2616,7 +3117,13 @@ else: raise TypeError( 'can only inherit from a NamedTuple type and Generic') bases = tuple(tuple if base is _NamedTuple else base for base in bases) - types = ns.get('__annotations__', {}) + if "__annotations__" in ns: + types = ns["__annotations__"] + elif "__annotate__" in ns: + # TODO: Use inspect.VALUE here, and make the annotations lazily evaluated + types = ns["__annotate__"](1) + else: + types = {} default_names = [] for field_name in types: if field_name in ns: @@ -2639,11 +3146,35 @@ else: class_getitem = typing.Generic.__class_getitem__.__func__ nm_tpl.__class_getitem__ = classmethod(class_getitem) # update from user namespace without overriding special namedtuple attributes - for key in ns: + for key, val in ns.items(): if key in _prohibited_namedtuple_fields: raise AttributeError("Cannot overwrite NamedTuple attribute " + key) - elif key not in _special_namedtuple_fields and key not in nm_tpl._fields: - setattr(nm_tpl, key, ns[key]) + elif key not in _special_namedtuple_fields: + if key not in nm_tpl._fields: + setattr(nm_tpl, key, ns[key]) + try: + set_name = type(val).__set_name__ + except AttributeError: + pass + else: + try: + set_name(val, nm_tpl, key) + except BaseException as e: + msg = ( + f"Error calling __set_name__ on {type(val).__name__!r} " + f"instance {key!r} in {typename!r}" + ) + # BaseException.add_note() existed on py311, + # but the __set_name__ machinery didn't start + # using add_note() until py312. + # Making sure exceptions are raised in the same way + # as in "normal" classes seems most important here. + if sys.version_info >= (3, 12): + e.add_note(msg) + raise + else: + raise RuntimeError(msg) from e + if typing.Generic in bases: nm_tpl.__init_subclass__() return nm_tpl @@ -2655,7 +3186,7 @@ else: return (_NamedTuple,) @_ensure_subclassable(_namedtuple_mro_entries) - def NamedTuple(__typename, __fields=_marker, **kwargs): + def NamedTuple(typename, fields=_marker, /, **kwargs): """Typed version of namedtuple. Usage:: @@ -2675,7 +3206,7 @@ else: Employee = NamedTuple('Employee', [('name', str), ('id', int)]) """ - if __fields is _marker: + if fields is _marker: if kwargs: deprecated_thing = "Creating NamedTuple classes using keyword arguments" deprecation_msg = ( @@ -2684,14 +3215,14 @@ else: ) else: deprecated_thing = "Failing to pass a value for the 'fields' parameter" - example = f"`{__typename} = NamedTuple({__typename!r}, [])`" + example = f"`{typename} = NamedTuple({typename!r}, [])`" deprecation_msg = ( "{name} is deprecated and will be disallowed in Python {remove}. " "To create a NamedTuple class with 0 fields " "using the functional syntax, " "pass an empty list, e.g. " ) + example + "." - elif __fields is None: + elif fields is None: if kwargs: raise TypeError( "Cannot pass `None` as the 'fields' parameter " @@ -2699,7 +3230,7 @@ else: ) else: deprecated_thing = "Passing `None` as the 'fields' parameter" - example = f"`{__typename} = NamedTuple({__typename!r}, [])`" + example = f"`{typename} = NamedTuple({typename!r}, [])`" deprecation_msg = ( "{name} is deprecated and will be disallowed in Python {remove}. " "To create a NamedTuple class with 0 fields " @@ -2709,32 +3240,22 @@ else: elif kwargs: raise TypeError("Either list of fields or keywords" " can be provided to NamedTuple, not both") - if __fields is _marker or __fields is None: + if fields is _marker or fields is None: warnings.warn( deprecation_msg.format(name=deprecated_thing, remove="3.15"), DeprecationWarning, stacklevel=2, ) - __fields = kwargs.items() - nt = _make_nmtuple(__typename, __fields, module=_caller()) + fields = kwargs.items() + nt = _make_nmtuple(typename, fields, module=_caller()) nt.__orig_bases__ = (NamedTuple,) return nt - # On 3.8+, alter the signature so that it matches typing.NamedTuple. - # The signature of typing.NamedTuple on >=3.8 is invalid syntax in Python 3.7, - # so just leave the signature as it is on 3.7. - if sys.version_info >= (3, 8): - _new_signature = '(typename, fields=None, /, **kwargs)' - if isinstance(NamedTuple, _types.FunctionType): - NamedTuple.__text_signature__ = _new_signature - else: - NamedTuple.__call__.__text_signature__ = _new_signature - if hasattr(collections.abc, "Buffer"): Buffer = collections.abc.Buffer else: - class Buffer(abc.ABC): + class Buffer(abc.ABC): # noqa: B024 """Base class for classes that implement the buffer protocol. The buffer protocol allows Python objects to expose a low-level @@ -2764,7 +3285,7 @@ else: if hasattr(_types, "get_original_bases"): get_original_bases = _types.get_original_bases else: - def get_original_bases(__cls): + def get_original_bases(cls, /): """Return the class's "original" bases prior to modification by `__mro_entries__`. Examples:: @@ -2786,14 +3307,11 @@ else: assert get_original_bases(int) == (object,) """ try: - return __cls.__orig_bases__ + return cls.__dict__.get("__orig_bases__", cls.__bases__) except AttributeError: - try: - return __cls.__bases__ - except AttributeError: - raise TypeError( - f'Expected an instance of type, not {type(__cls).__name__!r}' - ) from None + raise TypeError( + f'Expected an instance of type, not {type(cls).__name__!r}' + ) from None # NewType is a class on Python 3.10+, making it pickleable @@ -2815,7 +3333,7 @@ else: num = UserId(5) + 1 # type: int """ - def __call__(self, obj): + def __call__(self, obj, /): return obj def __init__(self, name, tp): @@ -2920,13 +3438,13 @@ else: # Setting this attribute closes the TypeAliasType from further modification self.__name__ = name - def __setattr__(self, __name: str, __value: object) -> None: + def __setattr__(self, name: str, value: object, /) -> None: if hasattr(self, "__name__"): - self._raise_attribute_error(__name) - super().__setattr__(__name, __value) + self._raise_attribute_error(name) + super().__setattr__(name, value) - def __delattr__(self, __name: str) -> Never: - self._raise_attribute_error(__name) + def __delattr__(self, name: str, /) -> Never: + self._raise_attribute_error(name) def _raise_attribute_error(self, name: str) -> Never: # Match the Python 3.12 error messages exactly @@ -2987,7 +3505,7 @@ if hasattr(typing, "is_protocol"): is_protocol = typing.is_protocol get_protocol_members = typing.get_protocol_members else: - def is_protocol(__tp: type) -> bool: + def is_protocol(tp: type, /) -> bool: """Return True if the given type is a Protocol. Example:: @@ -3002,13 +3520,13 @@ else: False """ return ( - isinstance(__tp, type) - and getattr(__tp, '_is_protocol', False) - and __tp is not Protocol - and __tp is not getattr(typing, "Protocol", object()) + isinstance(tp, type) + and getattr(tp, '_is_protocol', False) + and tp is not Protocol + and tp is not typing.Protocol ) - def get_protocol_members(__tp: type) -> typing.FrozenSet[str]: + def get_protocol_members(tp: type, /) -> typing.FrozenSet[str]: """Return the set of members defined in a Protocol. Example:: @@ -3022,11 +3540,63 @@ else: Raise a TypeError for arguments that are not Protocols. """ - if not is_protocol(__tp): - raise TypeError(f'{__tp!r} is not a Protocol') - if hasattr(__tp, '__protocol_attrs__'): - return frozenset(__tp.__protocol_attrs__) - return frozenset(_get_protocol_attrs(__tp)) + if not is_protocol(tp): + raise TypeError(f'{tp!r} is not a Protocol') + if hasattr(tp, '__protocol_attrs__'): + return frozenset(tp.__protocol_attrs__) + return frozenset(_get_protocol_attrs(tp)) + + +if hasattr(typing, "Doc"): + Doc = typing.Doc +else: + class Doc: + """Define the documentation of a type annotation using ``Annotated``, to be + used in class attributes, function and method parameters, return values, + and variables. + + The value should be a positional-only string literal to allow static tools + like editors and documentation generators to use it. + + This complements docstrings. + + The string value passed is available in the attribute ``documentation``. + + Example:: + + >>> from typing_extensions import Annotated, Doc + >>> def hi(to: Annotated[str, Doc("Who to say hi to")]) -> None: ... + """ + def __init__(self, documentation: str, /) -> None: + self.documentation = documentation + + def __repr__(self) -> str: + return f"Doc({self.documentation!r})" + + def __hash__(self) -> int: + return hash(self.documentation) + + def __eq__(self, other: object) -> bool: + if not isinstance(other, Doc): + return NotImplemented + return self.documentation == other.documentation + + +_CapsuleType = getattr(_types, "CapsuleType", None) + +if _CapsuleType is None: + try: + import _socket + except ImportError: + pass + else: + _CAPI = getattr(_socket, "CAPI", None) + if _CAPI is not None: + _CapsuleType = type(_CAPI) + +if _CapsuleType is not None: + CapsuleType = _CapsuleType + __all__.append("CapsuleType") # Aliases for items that have always been in typing. @@ -3042,7 +3612,6 @@ Container = typing.Container Dict = typing.Dict ForwardRef = typing.ForwardRef FrozenSet = typing.FrozenSet -Generator = typing.Generator Generic = typing.Generic Hashable = typing.Hashable IO = typing.IO diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/__init__.cpython-312.pyc index 9e9d6ed..e55fd9a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_collections.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_collections.cpython-312.pyc index 9772015..16b3eef 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_collections.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_collections.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_version.cpython-312.pyc index 5c543c4..eb3bac6 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_version.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/_version.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connection.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connection.cpython-312.pyc index f75269f..83bbcdb 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connection.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connection.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connectionpool.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connectionpool.cpython-312.pyc index f59c124..60097b3 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connectionpool.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/connectionpool.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/exceptions.cpython-312.pyc index fe4c0eb..8a5e39d 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/exceptions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/exceptions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/fields.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/fields.cpython-312.pyc index 07d01ea..a6a5c24 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/fields.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/fields.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/filepost.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/filepost.cpython-312.pyc index ea83160..05ca0c5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/filepost.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/filepost.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/poolmanager.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/poolmanager.cpython-312.pyc index 11d85c6..12f6795 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/poolmanager.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/poolmanager.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/request.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/request.cpython-312.pyc index 41a80b6..6258273 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/request.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/request.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/response.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/response.cpython-312.pyc index 4c8f2c4..05171b5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/response.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/__pycache__/response.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_collections.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_collections.py index da9857e..bceb845 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_collections.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_collections.py @@ -268,6 +268,24 @@ class HTTPHeaderDict(MutableMapping): else: return vals[1:] + def _prepare_for_method_change(self): + """ + Remove content-specific header fields before changing the request + method to GET or HEAD according to RFC 9110, Section 15.4. + """ + content_specific_headers = [ + "Content-Encoding", + "Content-Language", + "Content-Location", + "Content-Type", + "Content-Length", + "Digest", + "Last-Modified", + ] + for header in content_specific_headers: + self.discard(header) + return self + # Backwards compatibility for httplib getheaders = getlist getallmatchingheaders = getlist diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_version.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_version.py index cad75fb..d49df2a 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_version.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/_version.py @@ -1,2 +1,2 @@ # This file is protected via CODEOWNERS -__version__ = "1.26.17" +__version__ = "1.26.20" diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connection.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connection.py index 54b96b1..de35b63 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connection.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connection.py @@ -68,7 +68,7 @@ port_by_scheme = {"http": 80, "https": 443} # When it comes time to update this value as a part of regular maintenance # (ie test_recent_date is failing) update it to ~6 months before the current date. -RECENT_DATE = datetime.date(2022, 1, 1) +RECENT_DATE = datetime.date(2024, 1, 1) _CONTAINS_CONTROL_CHAR_RE = re.compile(r"[^-!#$%&'*+.^_`|~0-9a-zA-Z]") @@ -437,7 +437,7 @@ class HTTPSConnection(HTTPConnection): and self.ssl_version is None and hasattr(self.sock, "version") and self.sock.version() in {"TLSv1", "TLSv1.1"} - ): + ): # Defensive: warnings.warn( "Negotiating TLSv1/TLSv1.1 by default is deprecated " "and will be disabled in urllib3 v2.0.0. Connecting to " diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connectionpool.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connectionpool.py index 96844d9..0872ed7 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connectionpool.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/connectionpool.py @@ -9,6 +9,7 @@ import warnings from socket import error as SocketError from socket import timeout as SocketTimeout +from ._collections import HTTPHeaderDict from .connection import ( BaseSSLError, BrokenPipeError, @@ -422,12 +423,13 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): pass except IOError as e: # Python 2 and macOS/Linux - # EPIPE and ESHUTDOWN are BrokenPipeError on Python 2, and EPROTOTYPE is needed on macOS + # EPIPE and ESHUTDOWN are BrokenPipeError on Python 2, and EPROTOTYPE/ECONNRESET are needed on macOS # https://erickt.github.io/blog/2014/11/19/adventures-in-debugging-a-potential-osx-kernel-bug/ if e.errno not in { errno.EPIPE, errno.ESHUTDOWN, errno.EPROTOTYPE, + errno.ECONNRESET, }: raise @@ -767,7 +769,9 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): # so we try to cover our bases here! message = " ".join(re.split("[^a-z]", str(ssl_error).lower())) return ( - "wrong version number" in message or "unknown protocol" in message + "wrong version number" in message + or "unknown protocol" in message + or "record layer failure" in message ) # Try to detect a common user error with proxies which is to @@ -843,7 +847,11 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods): redirect_location = redirect and response.get_redirect_location() if redirect_location: if response.status == 303: + # Change the method according to RFC 9110, Section 15.4.4. method = "GET" + # And lose the body not to transfer anything sensitive. + body = None + headers = HTTPHeaderDict(headers)._prepare_for_method_change() try: retries = retries.increment(method, url, response=response, _pool=self) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/__init__.cpython-312.pyc index 8fec4b7..fd28f07 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/_appengine_environ.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/_appengine_environ.cpython-312.pyc index 212fef1..5a25f0f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/_appengine_environ.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/_appengine_environ.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/appengine.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/appengine.cpython-312.pyc index 51aa0eb..f7060a8 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/appengine.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/appengine.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/ntlmpool.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/ntlmpool.cpython-312.pyc index 6192273..0bf8f4f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/ntlmpool.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/ntlmpool.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc index 4ae0189..2a3e0aa 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/securetransport.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/securetransport.cpython-312.pyc index 3bc7865..0b59786 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/securetransport.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/securetransport.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/socks.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/socks.cpython-312.pyc index 3961b4e..e98580f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/socks.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/__pycache__/socks.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/__init__.cpython-312.pyc index 479e1d5..57438d2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/bindings.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/bindings.cpython-312.pyc index 29ab32c..c6d5c2f 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/bindings.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/bindings.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/low_level.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/low_level.cpython-312.pyc index 95a880f..241f993 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/low_level.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/_securetransport/__pycache__/low_level.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/securetransport.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/securetransport.py index 4a06bc6..722ee4e 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/securetransport.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/contrib/securetransport.py @@ -64,9 +64,8 @@ import struct import threading import weakref -from pip._vendor import six - from .. import util +from ..packages import six from ..util.ssl_ import PROTOCOL_TLS_CLIENT from ._securetransport.bindings import CoreFoundation, Security, SecurityConst from ._securetransport.low_level import ( diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/__init__.cpython-312.pyc index 2796086..f68ca3a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/six.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/six.cpython-312.pyc index 327f3e5..37c4dae 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/six.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/__pycache__/six.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/__init__.cpython-312.pyc index ab9c30c..1cc58c8 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/makefile.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/makefile.cpython-312.pyc index d6267aa..469a541 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/makefile.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/makefile.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/weakref_finalize.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/weakref_finalize.cpython-312.pyc index ff88736..0d7f9c1 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/weakref_finalize.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/packages/backports/__pycache__/weakref_finalize.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/poolmanager.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/poolmanager.py index 14b10da..fb51bf7 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/poolmanager.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/poolmanager.py @@ -4,7 +4,7 @@ import collections import functools import logging -from ._collections import RecentlyUsedContainer +from ._collections import HTTPHeaderDict, RecentlyUsedContainer from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool, port_by_scheme from .exceptions import ( LocationValueError, @@ -382,9 +382,12 @@ class PoolManager(RequestMethods): # Support relative URLs for redirecting. redirect_location = urljoin(url, redirect_location) - # RFC 7231, Section 6.4.4 if response.status == 303: + # Change the method according to RFC 9110, Section 15.4.4. method = "GET" + # And lose the body not to transfer anything sensitive. + kw["body"] = None + kw["headers"] = HTTPHeaderDict(kw["headers"])._prepare_for_method_change() retries = kw.get("retries") if not isinstance(retries, Retry): diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/__init__.cpython-312.pyc index e7e8ceb..4b40d54 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/connection.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/connection.cpython-312.pyc index 4bcbac0..03c90fa 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/connection.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/connection.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/proxy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/proxy.cpython-312.pyc index fa4ef17..85f40bf 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/proxy.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/proxy.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/queue.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/queue.cpython-312.pyc index 42608c3..73ea945 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/queue.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/queue.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/request.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/request.cpython-312.pyc index 9864c3b..64081f5 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/request.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/request.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/response.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/response.cpython-312.pyc index 9229a43..df9f650 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/response.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/response.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/retry.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/retry.cpython-312.pyc index 2f16667..22a1b78 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/retry.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/retry.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_.cpython-312.pyc index 0ae3264..da92a28 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc index 36ef32f..31b191a 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssltransport.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssltransport.cpython-312.pyc index 4609f21..a8f00f2 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssltransport.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/ssltransport.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/timeout.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/timeout.cpython-312.pyc index 9b62dd7..f321d8c 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/timeout.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/timeout.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/url.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/url.cpython-312.pyc index 6cf69f6..db4ed54 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/url.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/url.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/wait.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/wait.cpython-312.pyc index e480def..0dd22dd 100644 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/wait.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/__pycache__/wait.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/ssl_.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/ssl_.py index 2b45d39..0a6a0e0 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/ssl_.py +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/urllib3/util/ssl_.py @@ -1,11 +1,11 @@ from __future__ import absolute_import +import hashlib import hmac import os import sys import warnings from binascii import hexlify, unhexlify -from hashlib import md5, sha1, sha256 from ..exceptions import ( InsecurePlatformWarning, @@ -24,7 +24,10 @@ IS_SECURETRANSPORT = False ALPN_PROTOCOLS = ["http/1.1"] # Maps the length of a digest to a possible hash function producing this digest -HASHFUNC_MAP = {32: md5, 40: sha1, 64: sha256} +HASHFUNC_MAP = { + length: getattr(hashlib, algorithm, None) + for length, algorithm in ((32, "md5"), (40, "sha1"), (64, "sha256")) +} def _const_compare_digest_backport(a, b): @@ -191,9 +194,15 @@ def assert_fingerprint(cert, fingerprint): fingerprint = fingerprint.replace(":", "").lower() digest_length = len(fingerprint) - hashfunc = HASHFUNC_MAP.get(digest_length) - if not hashfunc: + if digest_length not in HASHFUNC_MAP: raise SSLError("Fingerprint of invalid length: {0}".format(fingerprint)) + hashfunc = HASHFUNC_MAP.get(digest_length) + if hashfunc is None: + raise SSLError( + "Hash function implementation unavailable for fingerprint length: {0}".format( + digest_length + ) + ) # We need encode() here for py32; works on py2 and p33. fingerprint_bytes = unhexlify(fingerprint.encode()) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/vendor.txt b/llmlab/lib/python3.12/site-packages/pip/_vendor/vendor.txt index 5554c38..f04a9c1 100644 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/vendor.txt +++ b/llmlab/lib/python3.12/site-packages/pip/_vendor/vendor.txt @@ -1,24 +1,18 @@ -CacheControl==0.13.1 # Make sure to update the license in pyproject.toml for this. -colorama==0.4.6 -distlib==0.3.8 -distro==1.8.0 -msgpack==1.0.5 -packaging==21.3 -platformdirs==3.8.1 -pyparsing==3.1.0 -pyproject-hooks==1.0.0 -requests==2.31.0 - certifi==2023.7.22 - chardet==5.1.0 - idna==3.4 - urllib3==1.26.17 -rich==13.4.2 - pygments==2.15.1 - typing_extensions==4.7.1 +CacheControl==0.14.1 +distlib==0.3.9 +distro==1.9.0 +msgpack==1.1.0 +packaging==24.2 +platformdirs==4.3.6 +pyproject-hooks==1.2.0 +requests==2.32.3 + certifi==2024.8.30 + idna==3.10 + urllib3==1.26.20 +rich==13.9.4 + pygments==2.18.0 + typing_extensions==4.12.2 resolvelib==1.0.1 -setuptools==68.0.0 -six==1.16.0 -tenacity==8.2.2 -tomli==2.0.1 -truststore==0.8.0 -webencodings==0.5.1 +setuptools==70.3.0 +tomli==2.2.1 +truststore==0.10.0 diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__init__.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__init__.py deleted file mode 100644 index d21d697..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__init__.py +++ /dev/null @@ -1,342 +0,0 @@ -# coding: utf-8 -""" - - webencodings - ~~~~~~~~~~~~ - - This is a Python implementation of the `WHATWG Encoding standard - `. See README for details. - - :copyright: Copyright 2012 by Simon Sapin - :license: BSD, see LICENSE for details. - -""" - -from __future__ import unicode_literals - -import codecs - -from .labels import LABELS - - -VERSION = '0.5.1' - - -# Some names in Encoding are not valid Python aliases. Remap these. -PYTHON_NAMES = { - 'iso-8859-8-i': 'iso-8859-8', - 'x-mac-cyrillic': 'mac-cyrillic', - 'macintosh': 'mac-roman', - 'windows-874': 'cp874'} - -CACHE = {} - - -def ascii_lower(string): - r"""Transform (only) ASCII letters to lower case: A-Z is mapped to a-z. - - :param string: An Unicode string. - :returns: A new Unicode string. - - This is used for `ASCII case-insensitive - `_ - matching of encoding labels. - The same matching is also used, among other things, - for `CSS keywords `_. - - This is different from the :meth:`~py:str.lower` method of Unicode strings - which also affect non-ASCII characters, - sometimes mapping them into the ASCII range: - - >>> keyword = u'Bac\N{KELVIN SIGN}ground' - >>> assert keyword.lower() == u'background' - >>> assert ascii_lower(keyword) != keyword.lower() - >>> assert ascii_lower(keyword) == u'bac\N{KELVIN SIGN}ground' - - """ - # This turns out to be faster than unicode.translate() - return string.encode('utf8').lower().decode('utf8') - - -def lookup(label): - """ - Look for an encoding by its label. - This is the spec’s `get an encoding - `_ algorithm. - Supported labels are listed there. - - :param label: A string. - :returns: - An :class:`Encoding` object, or :obj:`None` for an unknown label. - - """ - # Only strip ASCII whitespace: U+0009, U+000A, U+000C, U+000D, and U+0020. - label = ascii_lower(label.strip('\t\n\f\r ')) - name = LABELS.get(label) - if name is None: - return None - encoding = CACHE.get(name) - if encoding is None: - if name == 'x-user-defined': - from .x_user_defined import codec_info - else: - python_name = PYTHON_NAMES.get(name, name) - # Any python_name value that gets to here should be valid. - codec_info = codecs.lookup(python_name) - encoding = Encoding(name, codec_info) - CACHE[name] = encoding - return encoding - - -def _get_encoding(encoding_or_label): - """ - Accept either an encoding object or label. - - :param encoding: An :class:`Encoding` object or a label string. - :returns: An :class:`Encoding` object. - :raises: :exc:`~exceptions.LookupError` for an unknown label. - - """ - if hasattr(encoding_or_label, 'codec_info'): - return encoding_or_label - - encoding = lookup(encoding_or_label) - if encoding is None: - raise LookupError('Unknown encoding label: %r' % encoding_or_label) - return encoding - - -class Encoding(object): - """Reresents a character encoding such as UTF-8, - that can be used for decoding or encoding. - - .. attribute:: name - - Canonical name of the encoding - - .. attribute:: codec_info - - The actual implementation of the encoding, - a stdlib :class:`~codecs.CodecInfo` object. - See :func:`codecs.register`. - - """ - def __init__(self, name, codec_info): - self.name = name - self.codec_info = codec_info - - def __repr__(self): - return '' % self.name - - -#: The UTF-8 encoding. Should be used for new content and formats. -UTF8 = lookup('utf-8') - -_UTF16LE = lookup('utf-16le') -_UTF16BE = lookup('utf-16be') - - -def decode(input, fallback_encoding, errors='replace'): - """ - Decode a single string. - - :param input: A byte string - :param fallback_encoding: - An :class:`Encoding` object or a label string. - The encoding to use if :obj:`input` does note have a BOM. - :param errors: Type of error handling. See :func:`codecs.register`. - :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. - :return: - A ``(output, encoding)`` tuple of an Unicode string - and an :obj:`Encoding`. - - """ - # Fail early if `encoding` is an invalid label. - fallback_encoding = _get_encoding(fallback_encoding) - bom_encoding, input = _detect_bom(input) - encoding = bom_encoding or fallback_encoding - return encoding.codec_info.decode(input, errors)[0], encoding - - -def _detect_bom(input): - """Return (bom_encoding, input), with any BOM removed from the input.""" - if input.startswith(b'\xFF\xFE'): - return _UTF16LE, input[2:] - if input.startswith(b'\xFE\xFF'): - return _UTF16BE, input[2:] - if input.startswith(b'\xEF\xBB\xBF'): - return UTF8, input[3:] - return None, input - - -def encode(input, encoding=UTF8, errors='strict'): - """ - Encode a single string. - - :param input: An Unicode string. - :param encoding: An :class:`Encoding` object or a label string. - :param errors: Type of error handling. See :func:`codecs.register`. - :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. - :return: A byte string. - - """ - return _get_encoding(encoding).codec_info.encode(input, errors)[0] - - -def iter_decode(input, fallback_encoding, errors='replace'): - """ - "Pull"-based decoder. - - :param input: - An iterable of byte strings. - - The input is first consumed just enough to determine the encoding - based on the precense of a BOM, - then consumed on demand when the return value is. - :param fallback_encoding: - An :class:`Encoding` object or a label string. - The encoding to use if :obj:`input` does note have a BOM. - :param errors: Type of error handling. See :func:`codecs.register`. - :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. - :returns: - An ``(output, encoding)`` tuple. - :obj:`output` is an iterable of Unicode strings, - :obj:`encoding` is the :obj:`Encoding` that is being used. - - """ - - decoder = IncrementalDecoder(fallback_encoding, errors) - generator = _iter_decode_generator(input, decoder) - encoding = next(generator) - return generator, encoding - - -def _iter_decode_generator(input, decoder): - """Return a generator that first yields the :obj:`Encoding`, - then yields output chukns as Unicode strings. - - """ - decode = decoder.decode - input = iter(input) - for chunck in input: - output = decode(chunck) - if output: - assert decoder.encoding is not None - yield decoder.encoding - yield output - break - else: - # Input exhausted without determining the encoding - output = decode(b'', final=True) - assert decoder.encoding is not None - yield decoder.encoding - if output: - yield output - return - - for chunck in input: - output = decode(chunck) - if output: - yield output - output = decode(b'', final=True) - if output: - yield output - - -def iter_encode(input, encoding=UTF8, errors='strict'): - """ - “Pull”-based encoder. - - :param input: An iterable of Unicode strings. - :param encoding: An :class:`Encoding` object or a label string. - :param errors: Type of error handling. See :func:`codecs.register`. - :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. - :returns: An iterable of byte strings. - - """ - # Fail early if `encoding` is an invalid label. - encode = IncrementalEncoder(encoding, errors).encode - return _iter_encode_generator(input, encode) - - -def _iter_encode_generator(input, encode): - for chunck in input: - output = encode(chunck) - if output: - yield output - output = encode('', final=True) - if output: - yield output - - -class IncrementalDecoder(object): - """ - “Push”-based decoder. - - :param fallback_encoding: - An :class:`Encoding` object or a label string. - The encoding to use if :obj:`input` does note have a BOM. - :param errors: Type of error handling. See :func:`codecs.register`. - :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. - - """ - def __init__(self, fallback_encoding, errors='replace'): - # Fail early if `encoding` is an invalid label. - self._fallback_encoding = _get_encoding(fallback_encoding) - self._errors = errors - self._buffer = b'' - self._decoder = None - #: The actual :class:`Encoding` that is being used, - #: or :obj:`None` if that is not determined yet. - #: (Ie. if there is not enough input yet to determine - #: if there is a BOM.) - self.encoding = None # Not known yet. - - def decode(self, input, final=False): - """Decode one chunk of the input. - - :param input: A byte string. - :param final: - Indicate that no more input is available. - Must be :obj:`True` if this is the last call. - :returns: An Unicode string. - - """ - decoder = self._decoder - if decoder is not None: - return decoder(input, final) - - input = self._buffer + input - encoding, input = _detect_bom(input) - if encoding is None: - if len(input) < 3 and not final: # Not enough data yet. - self._buffer = input - return '' - else: # No BOM - encoding = self._fallback_encoding - decoder = encoding.codec_info.incrementaldecoder(self._errors).decode - self._decoder = decoder - self.encoding = encoding - return decoder(input, final) - - -class IncrementalEncoder(object): - """ - “Push”-based encoder. - - :param encoding: An :class:`Encoding` object or a label string. - :param errors: Type of error handling. See :func:`codecs.register`. - :raises: :exc:`~exceptions.LookupError` for an unknown encoding label. - - .. method:: encode(input, final=False) - - :param input: An Unicode string. - :param final: - Indicate that no more input is available. - Must be :obj:`True` if this is the last call. - :returns: A byte string. - - """ - def __init__(self, encoding=UTF8, errors='strict'): - encoding = _get_encoding(encoding) - self.encode = encoding.codec_info.incrementalencoder(errors).encode diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 5f7f426..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/labels.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/labels.cpython-312.pyc deleted file mode 100644 index 7b97071..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/labels.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/mklabels.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/mklabels.cpython-312.pyc deleted file mode 100644 index dc6b85d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/mklabels.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/tests.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/tests.cpython-312.pyc deleted file mode 100644 index fa485d6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/tests.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/x_user_defined.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/x_user_defined.cpython-312.pyc deleted file mode 100644 index 591dee5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/__pycache__/x_user_defined.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/labels.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/labels.py deleted file mode 100644 index 29cbf91..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/labels.py +++ /dev/null @@ -1,231 +0,0 @@ -""" - - webencodings.labels - ~~~~~~~~~~~~~~~~~~~ - - Map encoding labels to their name. - - :copyright: Copyright 2012 by Simon Sapin - :license: BSD, see LICENSE for details. - -""" - -# XXX Do not edit! -# This file is automatically generated by mklabels.py - -LABELS = { - 'unicode-1-1-utf-8': 'utf-8', - 'utf-8': 'utf-8', - 'utf8': 'utf-8', - '866': 'ibm866', - 'cp866': 'ibm866', - 'csibm866': 'ibm866', - 'ibm866': 'ibm866', - 'csisolatin2': 'iso-8859-2', - 'iso-8859-2': 'iso-8859-2', - 'iso-ir-101': 'iso-8859-2', - 'iso8859-2': 'iso-8859-2', - 'iso88592': 'iso-8859-2', - 'iso_8859-2': 'iso-8859-2', - 'iso_8859-2:1987': 'iso-8859-2', - 'l2': 'iso-8859-2', - 'latin2': 'iso-8859-2', - 'csisolatin3': 'iso-8859-3', - 'iso-8859-3': 'iso-8859-3', - 'iso-ir-109': 'iso-8859-3', - 'iso8859-3': 'iso-8859-3', - 'iso88593': 'iso-8859-3', - 'iso_8859-3': 'iso-8859-3', - 'iso_8859-3:1988': 'iso-8859-3', - 'l3': 'iso-8859-3', - 'latin3': 'iso-8859-3', - 'csisolatin4': 'iso-8859-4', - 'iso-8859-4': 'iso-8859-4', - 'iso-ir-110': 'iso-8859-4', - 'iso8859-4': 'iso-8859-4', - 'iso88594': 'iso-8859-4', - 'iso_8859-4': 'iso-8859-4', - 'iso_8859-4:1988': 'iso-8859-4', - 'l4': 'iso-8859-4', - 'latin4': 'iso-8859-4', - 'csisolatincyrillic': 'iso-8859-5', - 'cyrillic': 'iso-8859-5', - 'iso-8859-5': 'iso-8859-5', - 'iso-ir-144': 'iso-8859-5', - 'iso8859-5': 'iso-8859-5', - 'iso88595': 'iso-8859-5', - 'iso_8859-5': 'iso-8859-5', - 'iso_8859-5:1988': 'iso-8859-5', - 'arabic': 'iso-8859-6', - 'asmo-708': 'iso-8859-6', - 'csiso88596e': 'iso-8859-6', - 'csiso88596i': 'iso-8859-6', - 'csisolatinarabic': 'iso-8859-6', - 'ecma-114': 'iso-8859-6', - 'iso-8859-6': 'iso-8859-6', - 'iso-8859-6-e': 'iso-8859-6', - 'iso-8859-6-i': 'iso-8859-6', - 'iso-ir-127': 'iso-8859-6', - 'iso8859-6': 'iso-8859-6', - 'iso88596': 'iso-8859-6', - 'iso_8859-6': 'iso-8859-6', - 'iso_8859-6:1987': 'iso-8859-6', - 'csisolatingreek': 'iso-8859-7', - 'ecma-118': 'iso-8859-7', - 'elot_928': 'iso-8859-7', - 'greek': 'iso-8859-7', - 'greek8': 'iso-8859-7', - 'iso-8859-7': 'iso-8859-7', - 'iso-ir-126': 'iso-8859-7', - 'iso8859-7': 'iso-8859-7', - 'iso88597': 'iso-8859-7', - 'iso_8859-7': 'iso-8859-7', - 'iso_8859-7:1987': 'iso-8859-7', - 'sun_eu_greek': 'iso-8859-7', - 'csiso88598e': 'iso-8859-8', - 'csisolatinhebrew': 'iso-8859-8', - 'hebrew': 'iso-8859-8', - 'iso-8859-8': 'iso-8859-8', - 'iso-8859-8-e': 'iso-8859-8', - 'iso-ir-138': 'iso-8859-8', - 'iso8859-8': 'iso-8859-8', - 'iso88598': 'iso-8859-8', - 'iso_8859-8': 'iso-8859-8', - 'iso_8859-8:1988': 'iso-8859-8', - 'visual': 'iso-8859-8', - 'csiso88598i': 'iso-8859-8-i', - 'iso-8859-8-i': 'iso-8859-8-i', - 'logical': 'iso-8859-8-i', - 'csisolatin6': 'iso-8859-10', - 'iso-8859-10': 'iso-8859-10', - 'iso-ir-157': 'iso-8859-10', - 'iso8859-10': 'iso-8859-10', - 'iso885910': 'iso-8859-10', - 'l6': 'iso-8859-10', - 'latin6': 'iso-8859-10', - 'iso-8859-13': 'iso-8859-13', - 'iso8859-13': 'iso-8859-13', - 'iso885913': 'iso-8859-13', - 'iso-8859-14': 'iso-8859-14', - 'iso8859-14': 'iso-8859-14', - 'iso885914': 'iso-8859-14', - 'csisolatin9': 'iso-8859-15', - 'iso-8859-15': 'iso-8859-15', - 'iso8859-15': 'iso-8859-15', - 'iso885915': 'iso-8859-15', - 'iso_8859-15': 'iso-8859-15', - 'l9': 'iso-8859-15', - 'iso-8859-16': 'iso-8859-16', - 'cskoi8r': 'koi8-r', - 'koi': 'koi8-r', - 'koi8': 'koi8-r', - 'koi8-r': 'koi8-r', - 'koi8_r': 'koi8-r', - 'koi8-u': 'koi8-u', - 'csmacintosh': 'macintosh', - 'mac': 'macintosh', - 'macintosh': 'macintosh', - 'x-mac-roman': 'macintosh', - 'dos-874': 'windows-874', - 'iso-8859-11': 'windows-874', - 'iso8859-11': 'windows-874', - 'iso885911': 'windows-874', - 'tis-620': 'windows-874', - 'windows-874': 'windows-874', - 'cp1250': 'windows-1250', - 'windows-1250': 'windows-1250', - 'x-cp1250': 'windows-1250', - 'cp1251': 'windows-1251', - 'windows-1251': 'windows-1251', - 'x-cp1251': 'windows-1251', - 'ansi_x3.4-1968': 'windows-1252', - 'ascii': 'windows-1252', - 'cp1252': 'windows-1252', - 'cp819': 'windows-1252', - 'csisolatin1': 'windows-1252', - 'ibm819': 'windows-1252', - 'iso-8859-1': 'windows-1252', - 'iso-ir-100': 'windows-1252', - 'iso8859-1': 'windows-1252', - 'iso88591': 'windows-1252', - 'iso_8859-1': 'windows-1252', - 'iso_8859-1:1987': 'windows-1252', - 'l1': 'windows-1252', - 'latin1': 'windows-1252', - 'us-ascii': 'windows-1252', - 'windows-1252': 'windows-1252', - 'x-cp1252': 'windows-1252', - 'cp1253': 'windows-1253', - 'windows-1253': 'windows-1253', - 'x-cp1253': 'windows-1253', - 'cp1254': 'windows-1254', - 'csisolatin5': 'windows-1254', - 'iso-8859-9': 'windows-1254', - 'iso-ir-148': 'windows-1254', - 'iso8859-9': 'windows-1254', - 'iso88599': 'windows-1254', - 'iso_8859-9': 'windows-1254', - 'iso_8859-9:1989': 'windows-1254', - 'l5': 'windows-1254', - 'latin5': 'windows-1254', - 'windows-1254': 'windows-1254', - 'x-cp1254': 'windows-1254', - 'cp1255': 'windows-1255', - 'windows-1255': 'windows-1255', - 'x-cp1255': 'windows-1255', - 'cp1256': 'windows-1256', - 'windows-1256': 'windows-1256', - 'x-cp1256': 'windows-1256', - 'cp1257': 'windows-1257', - 'windows-1257': 'windows-1257', - 'x-cp1257': 'windows-1257', - 'cp1258': 'windows-1258', - 'windows-1258': 'windows-1258', - 'x-cp1258': 'windows-1258', - 'x-mac-cyrillic': 'x-mac-cyrillic', - 'x-mac-ukrainian': 'x-mac-cyrillic', - 'chinese': 'gbk', - 'csgb2312': 'gbk', - 'csiso58gb231280': 'gbk', - 'gb2312': 'gbk', - 'gb_2312': 'gbk', - 'gb_2312-80': 'gbk', - 'gbk': 'gbk', - 'iso-ir-58': 'gbk', - 'x-gbk': 'gbk', - 'gb18030': 'gb18030', - 'hz-gb-2312': 'hz-gb-2312', - 'big5': 'big5', - 'big5-hkscs': 'big5', - 'cn-big5': 'big5', - 'csbig5': 'big5', - 'x-x-big5': 'big5', - 'cseucpkdfmtjapanese': 'euc-jp', - 'euc-jp': 'euc-jp', - 'x-euc-jp': 'euc-jp', - 'csiso2022jp': 'iso-2022-jp', - 'iso-2022-jp': 'iso-2022-jp', - 'csshiftjis': 'shift_jis', - 'ms_kanji': 'shift_jis', - 'shift-jis': 'shift_jis', - 'shift_jis': 'shift_jis', - 'sjis': 'shift_jis', - 'windows-31j': 'shift_jis', - 'x-sjis': 'shift_jis', - 'cseuckr': 'euc-kr', - 'csksc56011987': 'euc-kr', - 'euc-kr': 'euc-kr', - 'iso-ir-149': 'euc-kr', - 'korean': 'euc-kr', - 'ks_c_5601-1987': 'euc-kr', - 'ks_c_5601-1989': 'euc-kr', - 'ksc5601': 'euc-kr', - 'ksc_5601': 'euc-kr', - 'windows-949': 'euc-kr', - 'csiso2022kr': 'iso-2022-kr', - 'iso-2022-kr': 'iso-2022-kr', - 'utf-16be': 'utf-16be', - 'utf-16': 'utf-16le', - 'utf-16le': 'utf-16le', - 'x-user-defined': 'x-user-defined', -} diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/mklabels.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/mklabels.py deleted file mode 100644 index 295dc92..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/mklabels.py +++ /dev/null @@ -1,59 +0,0 @@ -""" - - webencodings.mklabels - ~~~~~~~~~~~~~~~~~~~~~ - - Regenarate the webencodings.labels module. - - :copyright: Copyright 2012 by Simon Sapin - :license: BSD, see LICENSE for details. - -""" - -import json -try: - from urllib import urlopen -except ImportError: - from urllib.request import urlopen - - -def assert_lower(string): - assert string == string.lower() - return string - - -def generate(url): - parts = ['''\ -""" - - webencodings.labels - ~~~~~~~~~~~~~~~~~~~ - - Map encoding labels to their name. - - :copyright: Copyright 2012 by Simon Sapin - :license: BSD, see LICENSE for details. - -""" - -# XXX Do not edit! -# This file is automatically generated by mklabels.py - -LABELS = { -'''] - labels = [ - (repr(assert_lower(label)).lstrip('u'), - repr(encoding['name']).lstrip('u')) - for category in json.loads(urlopen(url).read().decode('ascii')) - for encoding in category['encodings'] - for label in encoding['labels']] - max_len = max(len(label) for label, name in labels) - parts.extend( - ' %s:%s %s,\n' % (label, ' ' * (max_len - len(label)), name) - for label, name in labels) - parts.append('}') - return ''.join(parts) - - -if __name__ == '__main__': - print(generate('http://encoding.spec.whatwg.org/encodings.json')) diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/tests.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/tests.py deleted file mode 100644 index e12c10d..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/tests.py +++ /dev/null @@ -1,153 +0,0 @@ -# coding: utf-8 -""" - - webencodings.tests - ~~~~~~~~~~~~~~~~~~ - - A basic test suite for Encoding. - - :copyright: Copyright 2012 by Simon Sapin - :license: BSD, see LICENSE for details. - -""" - -from __future__ import unicode_literals - -from . import (lookup, LABELS, decode, encode, iter_decode, iter_encode, - IncrementalDecoder, IncrementalEncoder, UTF8) - - -def assert_raises(exception, function, *args, **kwargs): - try: - function(*args, **kwargs) - except exception: - return - else: # pragma: no cover - raise AssertionError('Did not raise %s.' % exception) - - -def test_labels(): - assert lookup('utf-8').name == 'utf-8' - assert lookup('Utf-8').name == 'utf-8' - assert lookup('UTF-8').name == 'utf-8' - assert lookup('utf8').name == 'utf-8' - assert lookup('utf8').name == 'utf-8' - assert lookup('utf8 ').name == 'utf-8' - assert lookup(' \r\nutf8\t').name == 'utf-8' - assert lookup('u8') is None # Python label. - assert lookup('utf-8 ') is None # Non-ASCII white space. - - assert lookup('US-ASCII').name == 'windows-1252' - assert lookup('iso-8859-1').name == 'windows-1252' - assert lookup('latin1').name == 'windows-1252' - assert lookup('LATIN1').name == 'windows-1252' - assert lookup('latin-1') is None - assert lookup('LATİN1') is None # ASCII-only case insensitivity. - - -def test_all_labels(): - for label in LABELS: - assert decode(b'', label) == ('', lookup(label)) - assert encode('', label) == b'' - for repeat in [0, 1, 12]: - output, _ = iter_decode([b''] * repeat, label) - assert list(output) == [] - assert list(iter_encode([''] * repeat, label)) == [] - decoder = IncrementalDecoder(label) - assert decoder.decode(b'') == '' - assert decoder.decode(b'', final=True) == '' - encoder = IncrementalEncoder(label) - assert encoder.encode('') == b'' - assert encoder.encode('', final=True) == b'' - # All encoding names are valid labels too: - for name in set(LABELS.values()): - assert lookup(name).name == name - - -def test_invalid_label(): - assert_raises(LookupError, decode, b'\xEF\xBB\xBF\xc3\xa9', 'invalid') - assert_raises(LookupError, encode, 'é', 'invalid') - assert_raises(LookupError, iter_decode, [], 'invalid') - assert_raises(LookupError, iter_encode, [], 'invalid') - assert_raises(LookupError, IncrementalDecoder, 'invalid') - assert_raises(LookupError, IncrementalEncoder, 'invalid') - - -def test_decode(): - assert decode(b'\x80', 'latin1') == ('€', lookup('latin1')) - assert decode(b'\x80', lookup('latin1')) == ('€', lookup('latin1')) - assert decode(b'\xc3\xa9', 'utf8') == ('é', lookup('utf8')) - assert decode(b'\xc3\xa9', UTF8) == ('é', lookup('utf8')) - assert decode(b'\xc3\xa9', 'ascii') == ('é', lookup('ascii')) - assert decode(b'\xEF\xBB\xBF\xc3\xa9', 'ascii') == ('é', lookup('utf8')) # UTF-8 with BOM - - assert decode(b'\xFE\xFF\x00\xe9', 'ascii') == ('é', lookup('utf-16be')) # UTF-16-BE with BOM - assert decode(b'\xFF\xFE\xe9\x00', 'ascii') == ('é', lookup('utf-16le')) # UTF-16-LE with BOM - assert decode(b'\xFE\xFF\xe9\x00', 'ascii') == ('\ue900', lookup('utf-16be')) - assert decode(b'\xFF\xFE\x00\xe9', 'ascii') == ('\ue900', lookup('utf-16le')) - - assert decode(b'\x00\xe9', 'UTF-16BE') == ('é', lookup('utf-16be')) - assert decode(b'\xe9\x00', 'UTF-16LE') == ('é', lookup('utf-16le')) - assert decode(b'\xe9\x00', 'UTF-16') == ('é', lookup('utf-16le')) - - assert decode(b'\xe9\x00', 'UTF-16BE') == ('\ue900', lookup('utf-16be')) - assert decode(b'\x00\xe9', 'UTF-16LE') == ('\ue900', lookup('utf-16le')) - assert decode(b'\x00\xe9', 'UTF-16') == ('\ue900', lookup('utf-16le')) - - -def test_encode(): - assert encode('é', 'latin1') == b'\xe9' - assert encode('é', 'utf8') == b'\xc3\xa9' - assert encode('é', 'utf8') == b'\xc3\xa9' - assert encode('é', 'utf-16') == b'\xe9\x00' - assert encode('é', 'utf-16le') == b'\xe9\x00' - assert encode('é', 'utf-16be') == b'\x00\xe9' - - -def test_iter_decode(): - def iter_decode_to_string(input, fallback_encoding): - output, _encoding = iter_decode(input, fallback_encoding) - return ''.join(output) - assert iter_decode_to_string([], 'latin1') == '' - assert iter_decode_to_string([b''], 'latin1') == '' - assert iter_decode_to_string([b'\xe9'], 'latin1') == 'é' - assert iter_decode_to_string([b'hello'], 'latin1') == 'hello' - assert iter_decode_to_string([b'he', b'llo'], 'latin1') == 'hello' - assert iter_decode_to_string([b'hell', b'o'], 'latin1') == 'hello' - assert iter_decode_to_string([b'\xc3\xa9'], 'latin1') == 'é' - assert iter_decode_to_string([b'\xEF\xBB\xBF\xc3\xa9'], 'latin1') == 'é' - assert iter_decode_to_string([ - b'\xEF\xBB\xBF', b'\xc3', b'\xa9'], 'latin1') == 'é' - assert iter_decode_to_string([ - b'\xEF\xBB\xBF', b'a', b'\xc3'], 'latin1') == 'a\uFFFD' - assert iter_decode_to_string([ - b'', b'\xEF', b'', b'', b'\xBB\xBF\xc3', b'\xa9'], 'latin1') == 'é' - assert iter_decode_to_string([b'\xEF\xBB\xBF'], 'latin1') == '' - assert iter_decode_to_string([b'\xEF\xBB'], 'latin1') == 'ï»' - assert iter_decode_to_string([b'\xFE\xFF\x00\xe9'], 'latin1') == 'é' - assert iter_decode_to_string([b'\xFF\xFE\xe9\x00'], 'latin1') == 'é' - assert iter_decode_to_string([ - b'', b'\xFF', b'', b'', b'\xFE\xe9', b'\x00'], 'latin1') == 'é' - assert iter_decode_to_string([ - b'', b'h\xe9', b'llo'], 'x-user-defined') == 'h\uF7E9llo' - - -def test_iter_encode(): - assert b''.join(iter_encode([], 'latin1')) == b'' - assert b''.join(iter_encode([''], 'latin1')) == b'' - assert b''.join(iter_encode(['é'], 'latin1')) == b'\xe9' - assert b''.join(iter_encode(['', 'é', '', ''], 'latin1')) == b'\xe9' - assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16')) == b'\xe9\x00' - assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16le')) == b'\xe9\x00' - assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16be')) == b'\x00\xe9' - assert b''.join(iter_encode([ - '', 'h\uF7E9', '', 'llo'], 'x-user-defined')) == b'h\xe9llo' - - -def test_x_user_defined(): - encoded = b'2,\x0c\x0b\x1aO\xd9#\xcb\x0f\xc9\xbbt\xcf\xa8\xca' - decoded = '2,\x0c\x0b\x1aO\uf7d9#\uf7cb\x0f\uf7c9\uf7bbt\uf7cf\uf7a8\uf7ca' - encoded = b'aa' - decoded = 'aa' - assert decode(encoded, 'x-user-defined') == (decoded, lookup('x-user-defined')) - assert encode(decoded, 'x-user-defined') == encoded diff --git a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/x_user_defined.py b/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/x_user_defined.py deleted file mode 100644 index d16e326..0000000 --- a/llmlab/lib/python3.12/site-packages/pip/_vendor/webencodings/x_user_defined.py +++ /dev/null @@ -1,325 +0,0 @@ -# coding: utf-8 -""" - - webencodings.x_user_defined - ~~~~~~~~~~~~~~~~~~~~~~~~~~~ - - An implementation of the x-user-defined encoding. - - :copyright: Copyright 2012 by Simon Sapin - :license: BSD, see LICENSE for details. - -""" - -from __future__ import unicode_literals - -import codecs - - -### Codec APIs - -class Codec(codecs.Codec): - - def encode(self, input, errors='strict'): - return codecs.charmap_encode(input, errors, encoding_table) - - def decode(self, input, errors='strict'): - return codecs.charmap_decode(input, errors, decoding_table) - - -class IncrementalEncoder(codecs.IncrementalEncoder): - def encode(self, input, final=False): - return codecs.charmap_encode(input, self.errors, encoding_table)[0] - - -class IncrementalDecoder(codecs.IncrementalDecoder): - def decode(self, input, final=False): - return codecs.charmap_decode(input, self.errors, decoding_table)[0] - - -class StreamWriter(Codec, codecs.StreamWriter): - pass - - -class StreamReader(Codec, codecs.StreamReader): - pass - - -### encodings module API - -codec_info = codecs.CodecInfo( - name='x-user-defined', - encode=Codec().encode, - decode=Codec().decode, - incrementalencoder=IncrementalEncoder, - incrementaldecoder=IncrementalDecoder, - streamreader=StreamReader, - streamwriter=StreamWriter, -) - - -### Decoding Table - -# Python 3: -# for c in range(256): print(' %r' % chr(c if c < 128 else c + 0xF700)) -decoding_table = ( - '\x00' - '\x01' - '\x02' - '\x03' - '\x04' - '\x05' - '\x06' - '\x07' - '\x08' - '\t' - '\n' - '\x0b' - '\x0c' - '\r' - '\x0e' - '\x0f' - '\x10' - '\x11' - '\x12' - '\x13' - '\x14' - '\x15' - '\x16' - '\x17' - '\x18' - '\x19' - '\x1a' - '\x1b' - '\x1c' - '\x1d' - '\x1e' - '\x1f' - ' ' - '!' - '"' - '#' - '$' - '%' - '&' - "'" - '(' - ')' - '*' - '+' - ',' - '-' - '.' - '/' - '0' - '1' - '2' - '3' - '4' - '5' - '6' - '7' - '8' - '9' - ':' - ';' - '<' - '=' - '>' - '?' - '@' - 'A' - 'B' - 'C' - 'D' - 'E' - 'F' - 'G' - 'H' - 'I' - 'J' - 'K' - 'L' - 'M' - 'N' - 'O' - 'P' - 'Q' - 'R' - 'S' - 'T' - 'U' - 'V' - 'W' - 'X' - 'Y' - 'Z' - '[' - '\\' - ']' - '^' - '_' - '`' - 'a' - 'b' - 'c' - 'd' - 'e' - 'f' - 'g' - 'h' - 'i' - 'j' - 'k' - 'l' - 'm' - 'n' - 'o' - 'p' - 'q' - 'r' - 's' - 't' - 'u' - 'v' - 'w' - 'x' - 'y' - 'z' - '{' - '|' - '}' - '~' - '\x7f' - '\uf780' - '\uf781' - '\uf782' - '\uf783' - '\uf784' - '\uf785' - '\uf786' - '\uf787' - '\uf788' - '\uf789' - '\uf78a' - '\uf78b' - '\uf78c' - '\uf78d' - '\uf78e' - '\uf78f' - '\uf790' - '\uf791' - '\uf792' - '\uf793' - '\uf794' - '\uf795' - '\uf796' - '\uf797' - '\uf798' - '\uf799' - '\uf79a' - '\uf79b' - '\uf79c' - '\uf79d' - '\uf79e' - '\uf79f' - '\uf7a0' - '\uf7a1' - '\uf7a2' - '\uf7a3' - '\uf7a4' - '\uf7a5' - '\uf7a6' - '\uf7a7' - '\uf7a8' - '\uf7a9' - '\uf7aa' - '\uf7ab' - '\uf7ac' - '\uf7ad' - '\uf7ae' - '\uf7af' - '\uf7b0' - '\uf7b1' - '\uf7b2' - '\uf7b3' - '\uf7b4' - '\uf7b5' - '\uf7b6' - '\uf7b7' - '\uf7b8' - '\uf7b9' - '\uf7ba' - '\uf7bb' - '\uf7bc' - '\uf7bd' - '\uf7be' - '\uf7bf' - '\uf7c0' - '\uf7c1' - '\uf7c2' - '\uf7c3' - '\uf7c4' - '\uf7c5' - '\uf7c6' - '\uf7c7' - '\uf7c8' - '\uf7c9' - '\uf7ca' - '\uf7cb' - '\uf7cc' - '\uf7cd' - '\uf7ce' - '\uf7cf' - '\uf7d0' - '\uf7d1' - '\uf7d2' - '\uf7d3' - '\uf7d4' - '\uf7d5' - '\uf7d6' - '\uf7d7' - '\uf7d8' - '\uf7d9' - '\uf7da' - '\uf7db' - '\uf7dc' - '\uf7dd' - '\uf7de' - '\uf7df' - '\uf7e0' - '\uf7e1' - '\uf7e2' - '\uf7e3' - '\uf7e4' - '\uf7e5' - '\uf7e6' - '\uf7e7' - '\uf7e8' - '\uf7e9' - '\uf7ea' - '\uf7eb' - '\uf7ec' - '\uf7ed' - '\uf7ee' - '\uf7ef' - '\uf7f0' - '\uf7f1' - '\uf7f2' - '\uf7f3' - '\uf7f4' - '\uf7f5' - '\uf7f6' - '\uf7f7' - '\uf7f8' - '\uf7f9' - '\uf7fa' - '\uf7fb' - '\uf7fc' - '\uf7fd' - '\uf7fe' - '\uf7ff' -) - -### Encoding table -encoding_table = codecs.charmap_build(decoding_table) diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/__init__.py b/llmlab/lib/python3.12/site-packages/pkg_resources/__init__.py deleted file mode 100644 index 8a2fbfa..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/__init__.py +++ /dev/null @@ -1,3714 +0,0 @@ -""" -Package resource API --------------------- - -A resource is a logical file contained within a package, or a logical -subdirectory thereof. The package resource API expects resource names -to have their path parts separated with ``/``, *not* whatever the local -path separator is. Do not use os.path operations to manipulate resource -names being passed into the API. - -The package resource API is designed to work with normal filesystem packages, -.egg files, and unpacked .egg files. It can also work in a limited way with -.zip files and with custom PEP 302 loaders that support the ``get_data()`` -method. - -This module is deprecated. Users are directed to :mod:`importlib.resources`, -:mod:`importlib.metadata` and :pypi:`packaging` instead. -""" - -from __future__ import annotations - -import sys - -if sys.version_info < (3, 9): # noqa: UP036 # Check for unsupported versions - raise RuntimeError("Python 3.9 or later is required") - -import _imp -import collections -import email.parser -import errno -import functools -import importlib -import importlib.abc -import importlib.machinery -import inspect -import io -import ntpath -import operator -import os -import pkgutil -import platform -import plistlib -import posixpath -import re -import stat -import tempfile -import textwrap -import time -import types -import warnings -import zipfile -import zipimport -from collections.abc import Iterable, Iterator, Mapping, MutableSequence -from pkgutil import get_importer -from typing import ( - TYPE_CHECKING, - Any, - BinaryIO, - Callable, - Literal, - NamedTuple, - NoReturn, - Protocol, - TypeVar, - Union, - overload, -) - -sys.path.extend(((vendor_path := os.path.join(os.path.dirname(os.path.dirname(__file__)), 'setuptools', '_vendor')) not in sys.path) * [vendor_path]) # fmt: skip -# workaround for #4476 -sys.modules.pop('backports', None) - -# capture these to bypass sandboxing -from os import open as os_open, utime # isort: skip -from os.path import isdir, split # isort: skip - -try: - from os import mkdir, rename, unlink - - WRITE_SUPPORT = True -except ImportError: - # no write support, probably under GAE - WRITE_SUPPORT = False - -import packaging.markers -import packaging.requirements -import packaging.specifiers -import packaging.utils -import packaging.version -from jaraco.text import drop_comment, join_continuation, yield_lines -from platformdirs import user_cache_dir as _user_cache_dir - -if TYPE_CHECKING: - from _typeshed import BytesPath, StrOrBytesPath, StrPath - from _typeshed.importlib import LoaderProtocol - from typing_extensions import Self, TypeAlias - -warnings.warn( - "pkg_resources is deprecated as an API. " - "See https://setuptools.pypa.io/en/latest/pkg_resources.html", - DeprecationWarning, - stacklevel=2, -) - -_T = TypeVar("_T") -_DistributionT = TypeVar("_DistributionT", bound="Distribution") -# Type aliases -_NestedStr: TypeAlias = Union[str, Iterable[Union[str, Iterable["_NestedStr"]]]] -_StrictInstallerType: TypeAlias = Callable[["Requirement"], "_DistributionT"] -_InstallerType: TypeAlias = Callable[["Requirement"], Union["Distribution", None]] -_PkgReqType: TypeAlias = Union[str, "Requirement"] -_EPDistType: TypeAlias = Union["Distribution", _PkgReqType] -_MetadataType: TypeAlias = Union["IResourceProvider", None] -_ResolvedEntryPoint: TypeAlias = Any # Can be any attribute in the module -_ResourceStream: TypeAlias = Any # TODO / Incomplete: A readable file-like object -# Any object works, but let's indicate we expect something like a module (optionally has __loader__ or __file__) -_ModuleLike: TypeAlias = Union[object, types.ModuleType] -# Any: Should be _ModuleLike but we end up with issues where _ModuleLike doesn't have _ZipLoaderModule's __loader__ -_ProviderFactoryType: TypeAlias = Callable[[Any], "IResourceProvider"] -_DistFinderType: TypeAlias = Callable[[_T, str, bool], Iterable["Distribution"]] -_NSHandlerType: TypeAlias = Callable[[_T, str, str, types.ModuleType], Union[str, None]] -_AdapterT = TypeVar( - "_AdapterT", _DistFinderType[Any], _ProviderFactoryType, _NSHandlerType[Any] -) - - -class _ZipLoaderModule(Protocol): - __loader__: zipimport.zipimporter - - -_PEP440_FALLBACK = re.compile(r"^v?(?P(?:[0-9]+!)?[0-9]+(?:\.[0-9]+)*)", re.I) - - -class PEP440Warning(RuntimeWarning): - """ - Used when there is an issue with a version or specifier not complying with - PEP 440. - """ - - -parse_version = packaging.version.Version - -_state_vars: dict[str, str] = {} - - -def _declare_state(vartype: str, varname: str, initial_value: _T) -> _T: - _state_vars[varname] = vartype - return initial_value - - -def __getstate__() -> dict[str, Any]: - state = {} - g = globals() - for k, v in _state_vars.items(): - state[k] = g['_sget_' + v](g[k]) - return state - - -def __setstate__(state: dict[str, Any]) -> dict[str, Any]: - g = globals() - for k, v in state.items(): - g['_sset_' + _state_vars[k]](k, g[k], v) - return state - - -def _sget_dict(val): - return val.copy() - - -def _sset_dict(key, ob, state) -> None: - ob.clear() - ob.update(state) - - -def _sget_object(val): - return val.__getstate__() - - -def _sset_object(key, ob, state) -> None: - ob.__setstate__(state) - - -_sget_none = _sset_none = lambda *args: None - - -def get_supported_platform(): - """Return this platform's maximum compatible version. - - distutils.util.get_platform() normally reports the minimum version - of macOS that would be required to *use* extensions produced by - distutils. But what we want when checking compatibility is to know the - version of macOS that we are *running*. To allow usage of packages that - explicitly require a newer version of macOS, we must also know the - current version of the OS. - - If this condition occurs for any other platform with a version in its - platform strings, this function should be extended accordingly. - """ - plat = get_build_platform() - m = macosVersionString.match(plat) - if m is not None and sys.platform == "darwin": - try: - major_minor = '.'.join(_macos_vers()[:2]) - build = m.group(3) - plat = f'macosx-{major_minor}-{build}' - except ValueError: - # not macOS - pass - return plat - - -__all__ = [ - # Basic resource access and distribution/entry point discovery - 'require', - 'run_script', - 'get_provider', - 'get_distribution', - 'load_entry_point', - 'get_entry_map', - 'get_entry_info', - 'iter_entry_points', - 'resource_string', - 'resource_stream', - 'resource_filename', - 'resource_listdir', - 'resource_exists', - 'resource_isdir', - # Environmental control - 'declare_namespace', - 'working_set', - 'add_activation_listener', - 'find_distributions', - 'set_extraction_path', - 'cleanup_resources', - 'get_default_cache', - # Primary implementation classes - 'Environment', - 'WorkingSet', - 'ResourceManager', - 'Distribution', - 'Requirement', - 'EntryPoint', - # Exceptions - 'ResolutionError', - 'VersionConflict', - 'DistributionNotFound', - 'UnknownExtra', - 'ExtractionError', - # Warnings - 'PEP440Warning', - # Parsing functions and string utilities - 'parse_requirements', - 'parse_version', - 'safe_name', - 'safe_version', - 'get_platform', - 'compatible_platforms', - 'yield_lines', - 'split_sections', - 'safe_extra', - 'to_filename', - 'invalid_marker', - 'evaluate_marker', - # filesystem utilities - 'ensure_directory', - 'normalize_path', - # Distribution "precedence" constants - 'EGG_DIST', - 'BINARY_DIST', - 'SOURCE_DIST', - 'CHECKOUT_DIST', - 'DEVELOP_DIST', - # "Provider" interfaces, implementations, and registration/lookup APIs - 'IMetadataProvider', - 'IResourceProvider', - 'FileMetadata', - 'PathMetadata', - 'EggMetadata', - 'EmptyProvider', - 'empty_provider', - 'NullProvider', - 'EggProvider', - 'DefaultProvider', - 'ZipProvider', - 'register_finder', - 'register_namespace_handler', - 'register_loader_type', - 'fixup_namespace_packages', - 'get_importer', - # Warnings - 'PkgResourcesDeprecationWarning', - # Deprecated/backward compatibility only - 'run_main', - 'AvailableDistributions', -] - - -class ResolutionError(Exception): - """Abstract base for dependency resolution errors""" - - def __repr__(self) -> str: - return self.__class__.__name__ + repr(self.args) - - -class VersionConflict(ResolutionError): - """ - An already-installed version conflicts with the requested version. - - Should be initialized with the installed Distribution and the requested - Requirement. - """ - - _template = "{self.dist} is installed but {self.req} is required" - - @property - def dist(self) -> Distribution: - return self.args[0] - - @property - def req(self) -> Requirement: - return self.args[1] - - def report(self): - return self._template.format(**locals()) - - def with_context( - self, required_by: set[Distribution | str] - ) -> Self | ContextualVersionConflict: - """ - If required_by is non-empty, return a version of self that is a - ContextualVersionConflict. - """ - if not required_by: - return self - args = self.args + (required_by,) - return ContextualVersionConflict(*args) - - -class ContextualVersionConflict(VersionConflict): - """ - A VersionConflict that accepts a third parameter, the set of the - requirements that required the installed Distribution. - """ - - _template = VersionConflict._template + ' by {self.required_by}' - - @property - def required_by(self) -> set[str]: - return self.args[2] - - -class DistributionNotFound(ResolutionError): - """A requested distribution was not found""" - - _template = ( - "The '{self.req}' distribution was not found " - "and is required by {self.requirers_str}" - ) - - @property - def req(self) -> Requirement: - return self.args[0] - - @property - def requirers(self) -> set[str] | None: - return self.args[1] - - @property - def requirers_str(self): - if not self.requirers: - return 'the application' - return ', '.join(self.requirers) - - def report(self): - return self._template.format(**locals()) - - def __str__(self) -> str: - return self.report() - - -class UnknownExtra(ResolutionError): - """Distribution doesn't have an "extra feature" of the given name""" - - -_provider_factories: dict[type[_ModuleLike], _ProviderFactoryType] = {} - -PY_MAJOR = f'{sys.version_info.major}.{sys.version_info.minor}' -EGG_DIST = 3 -BINARY_DIST = 2 -SOURCE_DIST = 1 -CHECKOUT_DIST = 0 -DEVELOP_DIST = -1 - - -def register_loader_type( - loader_type: type[_ModuleLike], provider_factory: _ProviderFactoryType -) -> None: - """Register `provider_factory` to make providers for `loader_type` - - `loader_type` is the type or class of a PEP 302 ``module.__loader__``, - and `provider_factory` is a function that, passed a *module* object, - returns an ``IResourceProvider`` for that module. - """ - _provider_factories[loader_type] = provider_factory - - -@overload -def get_provider(moduleOrReq: str) -> IResourceProvider: ... -@overload -def get_provider(moduleOrReq: Requirement) -> Distribution: ... -def get_provider(moduleOrReq: str | Requirement) -> IResourceProvider | Distribution: - """Return an IResourceProvider for the named module or requirement""" - if isinstance(moduleOrReq, Requirement): - return working_set.find(moduleOrReq) or require(str(moduleOrReq))[0] - try: - module = sys.modules[moduleOrReq] - except KeyError: - __import__(moduleOrReq) - module = sys.modules[moduleOrReq] - loader = getattr(module, '__loader__', None) - return _find_adapter(_provider_factories, loader)(module) - - -@functools.cache -def _macos_vers(): - version = platform.mac_ver()[0] - # fallback for MacPorts - if version == '': - plist = '/System/Library/CoreServices/SystemVersion.plist' - if os.path.exists(plist): - with open(plist, 'rb') as fh: - plist_content = plistlib.load(fh) - if 'ProductVersion' in plist_content: - version = plist_content['ProductVersion'] - return version.split('.') - - -def _macos_arch(machine): - return {'PowerPC': 'ppc', 'Power_Macintosh': 'ppc'}.get(machine, machine) - - -def get_build_platform(): - """Return this platform's string for platform-specific distributions - - XXX Currently this is the same as ``distutils.util.get_platform()``, but it - needs some hacks for Linux and macOS. - """ - from sysconfig import get_platform - - plat = get_platform() - if sys.platform == "darwin" and not plat.startswith('macosx-'): - try: - version = _macos_vers() - machine = _macos_arch(os.uname()[4].replace(" ", "_")) - return f"macosx-{version[0]}.{version[1]}-{machine}" - except ValueError: - # if someone is running a non-Mac darwin system, this will fall - # through to the default implementation - pass - return plat - - -macosVersionString = re.compile(r"macosx-(\d+)\.(\d+)-(.*)") -darwinVersionString = re.compile(r"darwin-(\d+)\.(\d+)\.(\d+)-(.*)") -# XXX backward compat -get_platform = get_build_platform - - -def compatible_platforms(provided: str | None, required: str | None) -> bool: - """Can code for the `provided` platform run on the `required` platform? - - Returns true if either platform is ``None``, or the platforms are equal. - - XXX Needs compatibility checks for Linux and other unixy OSes. - """ - if provided is None or required is None or provided == required: - # easy case - return True - - # macOS special cases - reqMac = macosVersionString.match(required) - if reqMac: - provMac = macosVersionString.match(provided) - - # is this a Mac package? - if not provMac: - # this is backwards compatibility for packages built before - # setuptools 0.6. All packages built after this point will - # use the new macOS designation. - provDarwin = darwinVersionString.match(provided) - if provDarwin: - dversion = int(provDarwin.group(1)) - macosversion = f"{reqMac.group(1)}.{reqMac.group(2)}" - if ( - dversion == 7 - and macosversion >= "10.3" - or dversion == 8 - and macosversion >= "10.4" - ): - return True - # egg isn't macOS or legacy darwin - return False - - # are they the same major version and machine type? - if provMac.group(1) != reqMac.group(1) or provMac.group(3) != reqMac.group(3): - return False - - # is the required OS major update >= the provided one? - if int(provMac.group(2)) > int(reqMac.group(2)): - return False - - return True - - # XXX Linux and other platforms' special cases should go here - return False - - -@overload -def get_distribution(dist: _DistributionT) -> _DistributionT: ... -@overload -def get_distribution(dist: _PkgReqType) -> Distribution: ... -def get_distribution(dist: Distribution | _PkgReqType) -> Distribution: - """Return a current distribution object for a Requirement or string""" - if isinstance(dist, str): - dist = Requirement.parse(dist) - if isinstance(dist, Requirement): - dist = get_provider(dist) - if not isinstance(dist, Distribution): - raise TypeError("Expected str, Requirement, or Distribution", dist) - return dist - - -def load_entry_point(dist: _EPDistType, group: str, name: str) -> _ResolvedEntryPoint: - """Return `name` entry point of `group` for `dist` or raise ImportError""" - return get_distribution(dist).load_entry_point(group, name) - - -@overload -def get_entry_map( - dist: _EPDistType, group: None = None -) -> dict[str, dict[str, EntryPoint]]: ... -@overload -def get_entry_map(dist: _EPDistType, group: str) -> dict[str, EntryPoint]: ... -def get_entry_map(dist: _EPDistType, group: str | None = None): - """Return the entry point map for `group`, or the full entry map""" - return get_distribution(dist).get_entry_map(group) - - -def get_entry_info(dist: _EPDistType, group: str, name: str) -> EntryPoint | None: - """Return the EntryPoint object for `group`+`name`, or ``None``""" - return get_distribution(dist).get_entry_info(group, name) - - -class IMetadataProvider(Protocol): - def has_metadata(self, name: str) -> bool: - """Does the package's distribution contain the named metadata?""" - ... - - def get_metadata(self, name: str) -> str: - """The named metadata resource as a string""" - ... - - def get_metadata_lines(self, name: str) -> Iterator[str]: - """Yield named metadata resource as list of non-blank non-comment lines - - Leading and trailing whitespace is stripped from each line, and lines - with ``#`` as the first non-blank character are omitted.""" - ... - - def metadata_isdir(self, name: str) -> bool: - """Is the named metadata a directory? (like ``os.path.isdir()``)""" - ... - - def metadata_listdir(self, name: str) -> list[str]: - """List of metadata names in the directory (like ``os.listdir()``)""" - ... - - def run_script(self, script_name: str, namespace: dict[str, Any]) -> None: - """Execute the named script in the supplied namespace dictionary""" - ... - - -class IResourceProvider(IMetadataProvider, Protocol): - """An object that provides access to package resources""" - - def get_resource_filename( - self, manager: ResourceManager, resource_name: str - ) -> str: - """Return a true filesystem path for `resource_name` - - `manager` must be a ``ResourceManager``""" - ... - - def get_resource_stream( - self, manager: ResourceManager, resource_name: str - ) -> _ResourceStream: - """Return a readable file-like object for `resource_name` - - `manager` must be a ``ResourceManager``""" - ... - - def get_resource_string( - self, manager: ResourceManager, resource_name: str - ) -> bytes: - """Return the contents of `resource_name` as :obj:`bytes` - - `manager` must be a ``ResourceManager``""" - ... - - def has_resource(self, resource_name: str) -> bool: - """Does the package contain the named resource?""" - ... - - def resource_isdir(self, resource_name: str) -> bool: - """Is the named resource a directory? (like ``os.path.isdir()``)""" - ... - - def resource_listdir(self, resource_name: str) -> list[str]: - """List of resource names in the directory (like ``os.listdir()``)""" - ... - - -class WorkingSet: - """A collection of active distributions on sys.path (or a similar list)""" - - def __init__(self, entries: Iterable[str] | None = None) -> None: - """Create working set from list of path entries (default=sys.path)""" - self.entries: list[str] = [] - self.entry_keys: dict[str | None, list[str]] = {} - self.by_key: dict[str, Distribution] = {} - self.normalized_to_canonical_keys: dict[str, str] = {} - self.callbacks: list[Callable[[Distribution], object]] = [] - - if entries is None: - entries = sys.path - - for entry in entries: - self.add_entry(entry) - - @classmethod - def _build_master(cls): - """ - Prepare the master working set. - """ - ws = cls() - try: - from __main__ import __requires__ - except ImportError: - # The main program does not list any requirements - return ws - - # ensure the requirements are met - try: - ws.require(__requires__) - except VersionConflict: - return cls._build_from_requirements(__requires__) - - return ws - - @classmethod - def _build_from_requirements(cls, req_spec): - """ - Build a working set from a requirement spec. Rewrites sys.path. - """ - # try it without defaults already on sys.path - # by starting with an empty path - ws = cls([]) - reqs = parse_requirements(req_spec) - dists = ws.resolve(reqs, Environment()) - for dist in dists: - ws.add(dist) - - # add any missing entries from sys.path - for entry in sys.path: - if entry not in ws.entries: - ws.add_entry(entry) - - # then copy back to sys.path - sys.path[:] = ws.entries - return ws - - def add_entry(self, entry: str) -> None: - """Add a path item to ``.entries``, finding any distributions on it - - ``find_distributions(entry, True)`` is used to find distributions - corresponding to the path entry, and they are added. `entry` is - always appended to ``.entries``, even if it is already present. - (This is because ``sys.path`` can contain the same value more than - once, and the ``.entries`` of the ``sys.path`` WorkingSet should always - equal ``sys.path``.) - """ - self.entry_keys.setdefault(entry, []) - self.entries.append(entry) - for dist in find_distributions(entry, True): - self.add(dist, entry, False) - - def __contains__(self, dist: Distribution) -> bool: - """True if `dist` is the active distribution for its project""" - return self.by_key.get(dist.key) == dist - - def find(self, req: Requirement) -> Distribution | None: - """Find a distribution matching requirement `req` - - If there is an active distribution for the requested project, this - returns it as long as it meets the version requirement specified by - `req`. But, if there is an active distribution for the project and it - does *not* meet the `req` requirement, ``VersionConflict`` is raised. - If there is no active distribution for the requested project, ``None`` - is returned. - """ - dist: Distribution | None = None - - candidates = ( - req.key, - self.normalized_to_canonical_keys.get(req.key), - safe_name(req.key).replace(".", "-"), - ) - - for candidate in filter(None, candidates): - dist = self.by_key.get(candidate) - if dist: - req.key = candidate - break - - if dist is not None and dist not in req: - # XXX add more info - raise VersionConflict(dist, req) - return dist - - def iter_entry_points( - self, group: str, name: str | None = None - ) -> Iterator[EntryPoint]: - """Yield entry point objects from `group` matching `name` - - If `name` is None, yields all entry points in `group` from all - distributions in the working set, otherwise only ones matching - both `group` and `name` are yielded (in distribution order). - """ - return ( - entry - for dist in self - for entry in dist.get_entry_map(group).values() - if name is None or name == entry.name - ) - - def run_script(self, requires: str, script_name: str) -> None: - """Locate distribution for `requires` and run `script_name` script""" - ns = sys._getframe(1).f_globals - name = ns['__name__'] - ns.clear() - ns['__name__'] = name - self.require(requires)[0].run_script(script_name, ns) - - def __iter__(self) -> Iterator[Distribution]: - """Yield distributions for non-duplicate projects in the working set - - The yield order is the order in which the items' path entries were - added to the working set. - """ - seen = set() - for item in self.entries: - if item not in self.entry_keys: - # workaround a cache issue - continue - - for key in self.entry_keys[item]: - if key not in seen: - seen.add(key) - yield self.by_key[key] - - def add( - self, - dist: Distribution, - entry: str | None = None, - insert: bool = True, - replace: bool = False, - ) -> None: - """Add `dist` to working set, associated with `entry` - - If `entry` is unspecified, it defaults to the ``.location`` of `dist`. - On exit from this routine, `entry` is added to the end of the working - set's ``.entries`` (if it wasn't already present). - - `dist` is only added to the working set if it's for a project that - doesn't already have a distribution in the set, unless `replace=True`. - If it's added, any callbacks registered with the ``subscribe()`` method - will be called. - """ - if insert: - dist.insert_on(self.entries, entry, replace=replace) - - if entry is None: - entry = dist.location - keys = self.entry_keys.setdefault(entry, []) - keys2 = self.entry_keys.setdefault(dist.location, []) - if not replace and dist.key in self.by_key: - # ignore hidden distros - return - - self.by_key[dist.key] = dist - normalized_name = packaging.utils.canonicalize_name(dist.key) - self.normalized_to_canonical_keys[normalized_name] = dist.key - if dist.key not in keys: - keys.append(dist.key) - if dist.key not in keys2: - keys2.append(dist.key) - self._added_new(dist) - - @overload - def resolve( - self, - requirements: Iterable[Requirement], - env: Environment | None, - installer: _StrictInstallerType[_DistributionT], - replace_conflicting: bool = False, - extras: tuple[str, ...] | None = None, - ) -> list[_DistributionT]: ... - @overload - def resolve( - self, - requirements: Iterable[Requirement], - env: Environment | None = None, - *, - installer: _StrictInstallerType[_DistributionT], - replace_conflicting: bool = False, - extras: tuple[str, ...] | None = None, - ) -> list[_DistributionT]: ... - @overload - def resolve( - self, - requirements: Iterable[Requirement], - env: Environment | None = None, - installer: _InstallerType | None = None, - replace_conflicting: bool = False, - extras: tuple[str, ...] | None = None, - ) -> list[Distribution]: ... - def resolve( - self, - requirements: Iterable[Requirement], - env: Environment | None = None, - installer: _InstallerType | None | _StrictInstallerType[_DistributionT] = None, - replace_conflicting: bool = False, - extras: tuple[str, ...] | None = None, - ) -> list[Distribution] | list[_DistributionT]: - """List all distributions needed to (recursively) meet `requirements` - - `requirements` must be a sequence of ``Requirement`` objects. `env`, - if supplied, should be an ``Environment`` instance. If - not supplied, it defaults to all distributions available within any - entry or distribution in the working set. `installer`, if supplied, - will be invoked with each requirement that cannot be met by an - already-installed distribution; it should return a ``Distribution`` or - ``None``. - - Unless `replace_conflicting=True`, raises a VersionConflict exception - if - any requirements are found on the path that have the correct name but - the wrong version. Otherwise, if an `installer` is supplied it will be - invoked to obtain the correct version of the requirement and activate - it. - - `extras` is a list of the extras to be used with these requirements. - This is important because extra requirements may look like `my_req; - extra = "my_extra"`, which would otherwise be interpreted as a purely - optional requirement. Instead, we want to be able to assert that these - requirements are truly required. - """ - - # set up the stack - requirements = list(requirements)[::-1] - # set of processed requirements - processed = set() - # key -> dist - best: dict[str, Distribution] = {} - to_activate: list[Distribution] = [] - - req_extras = _ReqExtras() - - # Mapping of requirement to set of distributions that required it; - # useful for reporting info about conflicts. - required_by = collections.defaultdict[Requirement, set[str]](set) - - while requirements: - # process dependencies breadth-first - req = requirements.pop(0) - if req in processed: - # Ignore cyclic or redundant dependencies - continue - - if not req_extras.markers_pass(req, extras): - continue - - dist = self._resolve_dist( - req, best, replace_conflicting, env, installer, required_by, to_activate - ) - - # push the new requirements onto the stack - new_requirements = dist.requires(req.extras)[::-1] - requirements.extend(new_requirements) - - # Register the new requirements needed by req - for new_requirement in new_requirements: - required_by[new_requirement].add(req.project_name) - req_extras[new_requirement] = req.extras - - processed.add(req) - - # return list of distros to activate - return to_activate - - def _resolve_dist( - self, req, best, replace_conflicting, env, installer, required_by, to_activate - ) -> Distribution: - dist = best.get(req.key) - if dist is None: - # Find the best distribution and add it to the map - dist = self.by_key.get(req.key) - if dist is None or (dist not in req and replace_conflicting): - ws = self - if env is None: - if dist is None: - env = Environment(self.entries) - else: - # Use an empty environment and workingset to avoid - # any further conflicts with the conflicting - # distribution - env = Environment([]) - ws = WorkingSet([]) - dist = best[req.key] = env.best_match( - req, ws, installer, replace_conflicting=replace_conflicting - ) - if dist is None: - requirers = required_by.get(req, None) - raise DistributionNotFound(req, requirers) - to_activate.append(dist) - if dist not in req: - # Oops, the "best" so far conflicts with a dependency - dependent_req = required_by[req] - raise VersionConflict(dist, req).with_context(dependent_req) - return dist - - @overload - def find_plugins( - self, - plugin_env: Environment, - full_env: Environment | None, - installer: _StrictInstallerType[_DistributionT], - fallback: bool = True, - ) -> tuple[list[_DistributionT], dict[Distribution, Exception]]: ... - @overload - def find_plugins( - self, - plugin_env: Environment, - full_env: Environment | None = None, - *, - installer: _StrictInstallerType[_DistributionT], - fallback: bool = True, - ) -> tuple[list[_DistributionT], dict[Distribution, Exception]]: ... - @overload - def find_plugins( - self, - plugin_env: Environment, - full_env: Environment | None = None, - installer: _InstallerType | None = None, - fallback: bool = True, - ) -> tuple[list[Distribution], dict[Distribution, Exception]]: ... - def find_plugins( - self, - plugin_env: Environment, - full_env: Environment | None = None, - installer: _InstallerType | None | _StrictInstallerType[_DistributionT] = None, - fallback: bool = True, - ) -> tuple[ - list[Distribution] | list[_DistributionT], - dict[Distribution, Exception], - ]: - """Find all activatable distributions in `plugin_env` - - Example usage:: - - distributions, errors = working_set.find_plugins( - Environment(plugin_dirlist) - ) - # add plugins+libs to sys.path - map(working_set.add, distributions) - # display errors - print('Could not load', errors) - - The `plugin_env` should be an ``Environment`` instance that contains - only distributions that are in the project's "plugin directory" or - directories. The `full_env`, if supplied, should be an ``Environment`` - contains all currently-available distributions. If `full_env` is not - supplied, one is created automatically from the ``WorkingSet`` this - method is called on, which will typically mean that every directory on - ``sys.path`` will be scanned for distributions. - - `installer` is a standard installer callback as used by the - ``resolve()`` method. The `fallback` flag indicates whether we should - attempt to resolve older versions of a plugin if the newest version - cannot be resolved. - - This method returns a 2-tuple: (`distributions`, `error_info`), where - `distributions` is a list of the distributions found in `plugin_env` - that were loadable, along with any other distributions that are needed - to resolve their dependencies. `error_info` is a dictionary mapping - unloadable plugin distributions to an exception instance describing the - error that occurred. Usually this will be a ``DistributionNotFound`` or - ``VersionConflict`` instance. - """ - - plugin_projects = list(plugin_env) - # scan project names in alphabetic order - plugin_projects.sort() - - error_info: dict[Distribution, Exception] = {} - distributions: dict[Distribution, Exception | None] = {} - - if full_env is None: - env = Environment(self.entries) - env += plugin_env - else: - env = full_env + plugin_env - - shadow_set = self.__class__([]) - # put all our entries in shadow_set - list(map(shadow_set.add, self)) - - for project_name in plugin_projects: - for dist in plugin_env[project_name]: - req = [dist.as_requirement()] - - try: - resolvees = shadow_set.resolve(req, env, installer) - - except ResolutionError as v: - # save error info - error_info[dist] = v - if fallback: - # try the next older version of project - continue - else: - # give up on this project, keep going - break - - else: - list(map(shadow_set.add, resolvees)) - distributions.update(dict.fromkeys(resolvees)) - - # success, no need to try any more versions of this project - break - - sorted_distributions = list(distributions) - sorted_distributions.sort() - - return sorted_distributions, error_info - - def require(self, *requirements: _NestedStr) -> list[Distribution]: - """Ensure that distributions matching `requirements` are activated - - `requirements` must be a string or a (possibly-nested) sequence - thereof, specifying the distributions and versions required. The - return value is a sequence of the distributions that needed to be - activated to fulfill the requirements; all relevant distributions are - included, even if they were already activated in this working set. - """ - needed = self.resolve(parse_requirements(requirements)) - - for dist in needed: - self.add(dist) - - return needed - - def subscribe( - self, callback: Callable[[Distribution], object], existing: bool = True - ) -> None: - """Invoke `callback` for all distributions - - If `existing=True` (default), - call on all existing ones, as well. - """ - if callback in self.callbacks: - return - self.callbacks.append(callback) - if not existing: - return - for dist in self: - callback(dist) - - def _added_new(self, dist) -> None: - for callback in self.callbacks: - callback(dist) - - def __getstate__( - self, - ) -> tuple[ - list[str], - dict[str | None, list[str]], - dict[str, Distribution], - dict[str, str], - list[Callable[[Distribution], object]], - ]: - return ( - self.entries[:], - self.entry_keys.copy(), - self.by_key.copy(), - self.normalized_to_canonical_keys.copy(), - self.callbacks[:], - ) - - def __setstate__(self, e_k_b_n_c) -> None: - entries, keys, by_key, normalized_to_canonical_keys, callbacks = e_k_b_n_c - self.entries = entries[:] - self.entry_keys = keys.copy() - self.by_key = by_key.copy() - self.normalized_to_canonical_keys = normalized_to_canonical_keys.copy() - self.callbacks = callbacks[:] - - -class _ReqExtras(dict["Requirement", tuple[str, ...]]): - """ - Map each requirement to the extras that demanded it. - """ - - def markers_pass(self, req: Requirement, extras: tuple[str, ...] | None = None): - """ - Evaluate markers for req against each extra that - demanded it. - - Return False if the req has a marker and fails - evaluation. Otherwise, return True. - """ - return not req.marker or any( - req.marker.evaluate({'extra': extra}) - for extra in self.get(req, ()) + (extras or ("",)) - ) - - -class Environment: - """Searchable snapshot of distributions on a search path""" - - def __init__( - self, - search_path: Iterable[str] | None = None, - platform: str | None = get_supported_platform(), - python: str | None = PY_MAJOR, - ) -> None: - """Snapshot distributions available on a search path - - Any distributions found on `search_path` are added to the environment. - `search_path` should be a sequence of ``sys.path`` items. If not - supplied, ``sys.path`` is used. - - `platform` is an optional string specifying the name of the platform - that platform-specific distributions must be compatible with. If - unspecified, it defaults to the current platform. `python` is an - optional string naming the desired version of Python (e.g. ``'3.6'``); - it defaults to the current version. - - You may explicitly set `platform` (and/or `python`) to ``None`` if you - wish to map *all* distributions, not just those compatible with the - running platform or Python version. - """ - self._distmap: dict[str, list[Distribution]] = {} - self.platform = platform - self.python = python - self.scan(search_path) - - def can_add(self, dist: Distribution) -> bool: - """Is distribution `dist` acceptable for this environment? - - The distribution must match the platform and python version - requirements specified when this environment was created, or False - is returned. - """ - py_compat = ( - self.python is None - or dist.py_version is None - or dist.py_version == self.python - ) - return py_compat and compatible_platforms(dist.platform, self.platform) - - def remove(self, dist: Distribution) -> None: - """Remove `dist` from the environment""" - self._distmap[dist.key].remove(dist) - - def scan(self, search_path: Iterable[str] | None = None) -> None: - """Scan `search_path` for distributions usable in this environment - - Any distributions found are added to the environment. - `search_path` should be a sequence of ``sys.path`` items. If not - supplied, ``sys.path`` is used. Only distributions conforming to - the platform/python version defined at initialization are added. - """ - if search_path is None: - search_path = sys.path - - for item in search_path: - for dist in find_distributions(item): - self.add(dist) - - def __getitem__(self, project_name: str) -> list[Distribution]: - """Return a newest-to-oldest list of distributions for `project_name` - - Uses case-insensitive `project_name` comparison, assuming all the - project's distributions use their project's name converted to all - lowercase as their key. - - """ - distribution_key = project_name.lower() - return self._distmap.get(distribution_key, []) - - def add(self, dist: Distribution) -> None: - """Add `dist` if we ``can_add()`` it and it has not already been added""" - if self.can_add(dist) and dist.has_version(): - dists = self._distmap.setdefault(dist.key, []) - if dist not in dists: - dists.append(dist) - dists.sort(key=operator.attrgetter('hashcmp'), reverse=True) - - @overload - def best_match( - self, - req: Requirement, - working_set: WorkingSet, - installer: _StrictInstallerType[_DistributionT], - replace_conflicting: bool = False, - ) -> _DistributionT: ... - @overload - def best_match( - self, - req: Requirement, - working_set: WorkingSet, - installer: _InstallerType | None = None, - replace_conflicting: bool = False, - ) -> Distribution | None: ... - def best_match( - self, - req: Requirement, - working_set: WorkingSet, - installer: _InstallerType | None | _StrictInstallerType[_DistributionT] = None, - replace_conflicting: bool = False, - ) -> Distribution | None: - """Find distribution best matching `req` and usable on `working_set` - - This calls the ``find(req)`` method of the `working_set` to see if a - suitable distribution is already active. (This may raise - ``VersionConflict`` if an unsuitable version of the project is already - active in the specified `working_set`.) If a suitable distribution - isn't active, this method returns the newest distribution in the - environment that meets the ``Requirement`` in `req`. If no suitable - distribution is found, and `installer` is supplied, then the result of - calling the environment's ``obtain(req, installer)`` method will be - returned. - """ - try: - dist = working_set.find(req) - except VersionConflict: - if not replace_conflicting: - raise - dist = None - if dist is not None: - return dist - for dist in self[req.key]: - if dist in req: - return dist - # try to download/install - return self.obtain(req, installer) - - @overload - def obtain( - self, - requirement: Requirement, - installer: _StrictInstallerType[_DistributionT], - ) -> _DistributionT: ... - @overload - def obtain( - self, - requirement: Requirement, - installer: Callable[[Requirement], None] | None = None, - ) -> None: ... - @overload - def obtain( - self, - requirement: Requirement, - installer: _InstallerType | None = None, - ) -> Distribution | None: ... - def obtain( - self, - requirement: Requirement, - installer: Callable[[Requirement], None] - | _InstallerType - | None - | _StrictInstallerType[_DistributionT] = None, - ) -> Distribution | None: - """Obtain a distribution matching `requirement` (e.g. via download) - - Obtain a distro that matches requirement (e.g. via download). In the - base ``Environment`` class, this routine just returns - ``installer(requirement)``, unless `installer` is None, in which case - None is returned instead. This method is a hook that allows subclasses - to attempt other ways of obtaining a distribution before falling back - to the `installer` argument.""" - return installer(requirement) if installer else None - - def __iter__(self) -> Iterator[str]: - """Yield the unique project names of the available distributions""" - for key in self._distmap.keys(): - if self[key]: - yield key - - def __iadd__(self, other: Distribution | Environment) -> Self: - """In-place addition of a distribution or environment""" - if isinstance(other, Distribution): - self.add(other) - elif isinstance(other, Environment): - for project in other: - for dist in other[project]: - self.add(dist) - else: - raise TypeError(f"Can't add {other!r} to environment") - return self - - def __add__(self, other: Distribution | Environment) -> Self: - """Add an environment or distribution to an environment""" - new = self.__class__([], platform=None, python=None) - for env in self, other: - new += env - return new - - -# XXX backward compatibility -AvailableDistributions = Environment - - -class ExtractionError(RuntimeError): - """An error occurred extracting a resource - - The following attributes are available from instances of this exception: - - manager - The resource manager that raised this exception - - cache_path - The base directory for resource extraction - - original_error - The exception instance that caused extraction to fail - """ - - manager: ResourceManager - cache_path: str - original_error: BaseException | None - - -class ResourceManager: - """Manage resource extraction and packages""" - - extraction_path: str | None = None - - def __init__(self) -> None: - # acts like a set - self.cached_files: dict[str, Literal[True]] = {} - - def resource_exists( - self, package_or_requirement: _PkgReqType, resource_name: str - ) -> bool: - """Does the named resource exist?""" - return get_provider(package_or_requirement).has_resource(resource_name) - - def resource_isdir( - self, package_or_requirement: _PkgReqType, resource_name: str - ) -> bool: - """Is the named resource an existing directory?""" - return get_provider(package_or_requirement).resource_isdir(resource_name) - - def resource_filename( - self, package_or_requirement: _PkgReqType, resource_name: str - ) -> str: - """Return a true filesystem path for specified resource""" - return get_provider(package_or_requirement).get_resource_filename( - self, resource_name - ) - - def resource_stream( - self, package_or_requirement: _PkgReqType, resource_name: str - ) -> _ResourceStream: - """Return a readable file-like object for specified resource""" - return get_provider(package_or_requirement).get_resource_stream( - self, resource_name - ) - - def resource_string( - self, package_or_requirement: _PkgReqType, resource_name: str - ) -> bytes: - """Return specified resource as :obj:`bytes`""" - return get_provider(package_or_requirement).get_resource_string( - self, resource_name - ) - - def resource_listdir( - self, package_or_requirement: _PkgReqType, resource_name: str - ) -> list[str]: - """List the contents of the named resource directory""" - return get_provider(package_or_requirement).resource_listdir(resource_name) - - def extraction_error(self) -> NoReturn: - """Give an error message for problems extracting file(s)""" - - old_exc = sys.exc_info()[1] - cache_path = self.extraction_path or get_default_cache() - - tmpl = textwrap.dedent( - """ - Can't extract file(s) to egg cache - - The following error occurred while trying to extract file(s) - to the Python egg cache: - - {old_exc} - - The Python egg cache directory is currently set to: - - {cache_path} - - Perhaps your account does not have write access to this directory? - You can change the cache directory by setting the PYTHON_EGG_CACHE - environment variable to point to an accessible directory. - """ - ).lstrip() - err = ExtractionError(tmpl.format(**locals())) - err.manager = self - err.cache_path = cache_path - err.original_error = old_exc - raise err - - def get_cache_path(self, archive_name: str, names: Iterable[StrPath] = ()) -> str: - """Return absolute location in cache for `archive_name` and `names` - - The parent directory of the resulting path will be created if it does - not already exist. `archive_name` should be the base filename of the - enclosing egg (which may not be the name of the enclosing zipfile!), - including its ".egg" extension. `names`, if provided, should be a - sequence of path name parts "under" the egg's extraction location. - - This method should only be called by resource providers that need to - obtain an extraction location, and only for names they intend to - extract, as it tracks the generated names for possible cleanup later. - """ - extract_path = self.extraction_path or get_default_cache() - target_path = os.path.join(extract_path, archive_name + '-tmp', *names) - try: - _bypass_ensure_directory(target_path) - except Exception: - self.extraction_error() - - self._warn_unsafe_extraction_path(extract_path) - - self.cached_files[target_path] = True - return target_path - - @staticmethod - def _warn_unsafe_extraction_path(path) -> None: - """ - If the default extraction path is overridden and set to an insecure - location, such as /tmp, it opens up an opportunity for an attacker to - replace an extracted file with an unauthorized payload. Warn the user - if a known insecure location is used. - - See Distribute #375 for more details. - """ - if os.name == 'nt' and not path.startswith(os.environ['windir']): - # On Windows, permissions are generally restrictive by default - # and temp directories are not writable by other users, so - # bypass the warning. - return - mode = os.stat(path).st_mode - if mode & stat.S_IWOTH or mode & stat.S_IWGRP: - msg = ( - "Extraction path is writable by group/others " - "and vulnerable to attack when " - "used with get_resource_filename ({path}). " - "Consider a more secure " - "location (set with .set_extraction_path or the " - "PYTHON_EGG_CACHE environment variable)." - ).format(**locals()) - warnings.warn(msg, UserWarning) - - def postprocess(self, tempname: StrOrBytesPath, filename: StrOrBytesPath) -> None: - """Perform any platform-specific postprocessing of `tempname` - - This is where Mac header rewrites should be done; other platforms don't - have anything special they should do. - - Resource providers should call this method ONLY after successfully - extracting a compressed resource. They must NOT call it on resources - that are already in the filesystem. - - `tempname` is the current (temporary) name of the file, and `filename` - is the name it will be renamed to by the caller after this routine - returns. - """ - - if os.name == 'posix': - # Make the resource executable - mode = ((os.stat(tempname).st_mode) | 0o555) & 0o7777 - os.chmod(tempname, mode) - - def set_extraction_path(self, path: str) -> None: - """Set the base path where resources will be extracted to, if needed. - - If you do not call this routine before any extractions take place, the - path defaults to the return value of ``get_default_cache()``. (Which - is based on the ``PYTHON_EGG_CACHE`` environment variable, with various - platform-specific fallbacks. See that routine's documentation for more - details.) - - Resources are extracted to subdirectories of this path based upon - information given by the ``IResourceProvider``. You may set this to a - temporary directory, but then you must call ``cleanup_resources()`` to - delete the extracted files when done. There is no guarantee that - ``cleanup_resources()`` will be able to remove all extracted files. - - (Note: you may not change the extraction path for a given resource - manager once resources have been extracted, unless you first call - ``cleanup_resources()``.) - """ - if self.cached_files: - raise ValueError("Can't change extraction path, files already extracted") - - self.extraction_path = path - - def cleanup_resources(self, force: bool = False) -> list[str]: - """ - Delete all extracted resource files and directories, returning a list - of the file and directory names that could not be successfully removed. - This function does not have any concurrency protection, so it should - generally only be called when the extraction path is a temporary - directory exclusive to a single process. This method is not - automatically called; you must call it explicitly or register it as an - ``atexit`` function if you wish to ensure cleanup of a temporary - directory used for extractions. - """ - # XXX - return [] - - -def get_default_cache() -> str: - """ - Return the ``PYTHON_EGG_CACHE`` environment variable - or a platform-relevant user cache dir for an app - named "Python-Eggs". - """ - return os.environ.get('PYTHON_EGG_CACHE') or _user_cache_dir(appname='Python-Eggs') - - -def safe_name(name: str) -> str: - """Convert an arbitrary string to a standard distribution name - - Any runs of non-alphanumeric/. characters are replaced with a single '-'. - """ - return re.sub('[^A-Za-z0-9.]+', '-', name) - - -def safe_version(version: str) -> str: - """ - Convert an arbitrary string to a standard version string - """ - try: - # normalize the version - return str(packaging.version.Version(version)) - except packaging.version.InvalidVersion: - version = version.replace(' ', '.') - return re.sub('[^A-Za-z0-9.]+', '-', version) - - -def _forgiving_version(version) -> str: - """Fallback when ``safe_version`` is not safe enough - >>> parse_version(_forgiving_version('0.23ubuntu1')) - - >>> parse_version(_forgiving_version('0.23-')) - - >>> parse_version(_forgiving_version('0.-_')) - - >>> parse_version(_forgiving_version('42.+?1')) - - >>> parse_version(_forgiving_version('hello world')) - - """ - version = version.replace(' ', '.') - match = _PEP440_FALLBACK.search(version) - if match: - safe = match["safe"] - rest = version[len(safe) :] - else: - safe = "0" - rest = version - local = f"sanitized.{_safe_segment(rest)}".strip(".") - return f"{safe}.dev0+{local}" - - -def _safe_segment(segment): - """Convert an arbitrary string into a safe segment""" - segment = re.sub('[^A-Za-z0-9.]+', '-', segment) - segment = re.sub('-[^A-Za-z0-9]+', '-', segment) - return re.sub(r'\.[^A-Za-z0-9]+', '.', segment).strip(".-") - - -def safe_extra(extra: str) -> str: - """Convert an arbitrary string to a standard 'extra' name - - Any runs of non-alphanumeric characters are replaced with a single '_', - and the result is always lowercased. - """ - return re.sub('[^A-Za-z0-9.-]+', '_', extra).lower() - - -def to_filename(name: str) -> str: - """Convert a project or version name to its filename-escaped form - - Any '-' characters are currently replaced with '_'. - """ - return name.replace('-', '_') - - -def invalid_marker(text: str) -> SyntaxError | Literal[False]: - """ - Validate text as a PEP 508 environment marker; return an exception - if invalid or False otherwise. - """ - try: - evaluate_marker(text) - except SyntaxError as e: - e.filename = None - e.lineno = None - return e - return False - - -def evaluate_marker(text: str, extra: str | None = None) -> bool: - """ - Evaluate a PEP 508 environment marker. - Return a boolean indicating the marker result in this environment. - Raise SyntaxError if marker is invalid. - - This implementation uses the 'pyparsing' module. - """ - try: - marker = packaging.markers.Marker(text) - return marker.evaluate() - except packaging.markers.InvalidMarker as e: - raise SyntaxError(e) from e - - -class NullProvider: - """Try to implement resources and metadata for arbitrary PEP 302 loaders""" - - egg_name: str | None = None - egg_info: str | None = None - loader: LoaderProtocol | None = None - - def __init__(self, module: _ModuleLike) -> None: - self.loader = getattr(module, '__loader__', None) - self.module_path = os.path.dirname(getattr(module, '__file__', '')) - - def get_resource_filename( - self, manager: ResourceManager, resource_name: str - ) -> str: - return self._fn(self.module_path, resource_name) - - def get_resource_stream( - self, manager: ResourceManager, resource_name: str - ) -> BinaryIO: - return io.BytesIO(self.get_resource_string(manager, resource_name)) - - def get_resource_string( - self, manager: ResourceManager, resource_name: str - ) -> bytes: - return self._get(self._fn(self.module_path, resource_name)) - - def has_resource(self, resource_name: str) -> bool: - return self._has(self._fn(self.module_path, resource_name)) - - def _get_metadata_path(self, name): - return self._fn(self.egg_info, name) - - def has_metadata(self, name: str) -> bool: - if not self.egg_info: - return False - - path = self._get_metadata_path(name) - return self._has(path) - - def get_metadata(self, name: str) -> str: - if not self.egg_info: - return "" - path = self._get_metadata_path(name) - value = self._get(path) - try: - return value.decode('utf-8') - except UnicodeDecodeError as exc: - # Include the path in the error message to simplify - # troubleshooting, and without changing the exception type. - exc.reason += f' in {name} file at path: {path}' - raise - - def get_metadata_lines(self, name: str) -> Iterator[str]: - return yield_lines(self.get_metadata(name)) - - def resource_isdir(self, resource_name: str) -> bool: - return self._isdir(self._fn(self.module_path, resource_name)) - - def metadata_isdir(self, name: str) -> bool: - return bool(self.egg_info and self._isdir(self._fn(self.egg_info, name))) - - def resource_listdir(self, resource_name: str) -> list[str]: - return self._listdir(self._fn(self.module_path, resource_name)) - - def metadata_listdir(self, name: str) -> list[str]: - if self.egg_info: - return self._listdir(self._fn(self.egg_info, name)) - return [] - - def run_script(self, script_name: str, namespace: dict[str, Any]) -> None: - script = 'scripts/' + script_name - if not self.has_metadata(script): - raise ResolutionError( - "Script {script!r} not found in metadata at {self.egg_info!r}".format( - **locals() - ), - ) - - script_text = self.get_metadata(script).replace('\r\n', '\n') - script_text = script_text.replace('\r', '\n') - script_filename = self._fn(self.egg_info, script) - namespace['__file__'] = script_filename - if os.path.exists(script_filename): - source = _read_utf8_with_fallback(script_filename) - code = compile(source, script_filename, 'exec') - exec(code, namespace, namespace) - else: - from linecache import cache - - cache[script_filename] = ( - len(script_text), - 0, - script_text.split('\n'), - script_filename, - ) - script_code = compile(script_text, script_filename, 'exec') - exec(script_code, namespace, namespace) - - def _has(self, path) -> bool: - raise NotImplementedError( - "Can't perform this operation for unregistered loader type" - ) - - def _isdir(self, path) -> bool: - raise NotImplementedError( - "Can't perform this operation for unregistered loader type" - ) - - def _listdir(self, path) -> list[str]: - raise NotImplementedError( - "Can't perform this operation for unregistered loader type" - ) - - def _fn(self, base: str | None, resource_name: str): - if base is None: - raise TypeError( - "`base` parameter in `_fn` is `None`. Either override this method or check the parameter first." - ) - self._validate_resource_path(resource_name) - if resource_name: - return os.path.join(base, *resource_name.split('/')) - return base - - @staticmethod - def _validate_resource_path(path) -> None: - """ - Validate the resource paths according to the docs. - https://setuptools.pypa.io/en/latest/pkg_resources.html#basic-resource-access - - >>> warned = getfixture('recwarn') - >>> warnings.simplefilter('always') - >>> vrp = NullProvider._validate_resource_path - >>> vrp('foo/bar.txt') - >>> bool(warned) - False - >>> vrp('../foo/bar.txt') - >>> bool(warned) - True - >>> warned.clear() - >>> vrp('/foo/bar.txt') - >>> bool(warned) - True - >>> vrp('foo/../../bar.txt') - >>> bool(warned) - True - >>> warned.clear() - >>> vrp('foo/f../bar.txt') - >>> bool(warned) - False - - Windows path separators are straight-up disallowed. - >>> vrp(r'\\foo/bar.txt') - Traceback (most recent call last): - ... - ValueError: Use of .. or absolute path in a resource path \ -is not allowed. - - >>> vrp(r'C:\\foo/bar.txt') - Traceback (most recent call last): - ... - ValueError: Use of .. or absolute path in a resource path \ -is not allowed. - - Blank values are allowed - - >>> vrp('') - >>> bool(warned) - False - - Non-string values are not. - - >>> vrp(None) - Traceback (most recent call last): - ... - AttributeError: ... - """ - invalid = ( - os.path.pardir in path.split(posixpath.sep) - or posixpath.isabs(path) - or ntpath.isabs(path) - or path.startswith("\\") - ) - if not invalid: - return - - msg = "Use of .. or absolute path in a resource path is not allowed." - - # Aggressively disallow Windows absolute paths - if (path.startswith("\\") or ntpath.isabs(path)) and not posixpath.isabs(path): - raise ValueError(msg) - - # for compatibility, warn; in future - # raise ValueError(msg) - issue_warning( - msg[:-1] + " and will raise exceptions in a future release.", - DeprecationWarning, - ) - - def _get(self, path) -> bytes: - if hasattr(self.loader, 'get_data') and self.loader: - # Already checked get_data exists - return self.loader.get_data(path) # type: ignore[attr-defined] - raise NotImplementedError( - "Can't perform this operation for loaders without 'get_data()'" - ) - - -register_loader_type(object, NullProvider) - - -def _parents(path): - """ - yield all parents of path including path - """ - last = None - while path != last: - yield path - last = path - path, _ = os.path.split(path) - - -class EggProvider(NullProvider): - """Provider based on a virtual filesystem""" - - def __init__(self, module: _ModuleLike) -> None: - super().__init__(module) - self._setup_prefix() - - def _setup_prefix(self): - # Assume that metadata may be nested inside a "basket" - # of multiple eggs and use module_path instead of .archive. - eggs = filter(_is_egg_path, _parents(self.module_path)) - egg = next(eggs, None) - egg and self._set_egg(egg) - - def _set_egg(self, path: str) -> None: - self.egg_name = os.path.basename(path) - self.egg_info = os.path.join(path, 'EGG-INFO') - self.egg_root = path - - -class DefaultProvider(EggProvider): - """Provides access to package resources in the filesystem""" - - def _has(self, path) -> bool: - return os.path.exists(path) - - def _isdir(self, path) -> bool: - return os.path.isdir(path) - - def _listdir(self, path): - return os.listdir(path) - - def get_resource_stream( - self, manager: object, resource_name: str - ) -> io.BufferedReader: - return open(self._fn(self.module_path, resource_name), 'rb') - - def _get(self, path) -> bytes: - with open(path, 'rb') as stream: - return stream.read() - - @classmethod - def _register(cls) -> None: - loader_names = ( - 'SourceFileLoader', - 'SourcelessFileLoader', - ) - for name in loader_names: - loader_cls = getattr(importlib.machinery, name, type(None)) - register_loader_type(loader_cls, cls) - - -DefaultProvider._register() - - -class EmptyProvider(NullProvider): - """Provider that returns nothing for all requests""" - - # A special case, we don't want all Providers inheriting from NullProvider to have a potentially None module_path - module_path: str | None = None # type: ignore[assignment] - - _isdir = _has = lambda self, path: False - - def _get(self, path) -> bytes: - return b'' - - def _listdir(self, path): - return [] - - def __init__(self) -> None: - pass - - -empty_provider = EmptyProvider() - - -class ZipManifests(dict[str, "MemoizedZipManifests.manifest_mod"]): - """ - zip manifest builder - """ - - # `path` could be `StrPath | IO[bytes]` but that violates the LSP for `MemoizedZipManifests.load` - @classmethod - def build(cls, path: str) -> dict[str, zipfile.ZipInfo]: - """ - Build a dictionary similar to the zipimport directory - caches, except instead of tuples, store ZipInfo objects. - - Use a platform-specific path separator (os.sep) for the path keys - for compatibility with pypy on Windows. - """ - with zipfile.ZipFile(path) as zfile: - items = ( - ( - name.replace('/', os.sep), - zfile.getinfo(name), - ) - for name in zfile.namelist() - ) - return dict(items) - - load = build - - -class MemoizedZipManifests(ZipManifests): - """ - Memoized zipfile manifests. - """ - - class manifest_mod(NamedTuple): - manifest: dict[str, zipfile.ZipInfo] - mtime: float - - def load(self, path: str) -> dict[str, zipfile.ZipInfo]: # type: ignore[override] # ZipManifests.load is a classmethod - """ - Load a manifest at path or return a suitable manifest already loaded. - """ - path = os.path.normpath(path) - mtime = os.stat(path).st_mtime - - if path not in self or self[path].mtime != mtime: - manifest = self.build(path) - self[path] = self.manifest_mod(manifest, mtime) - - return self[path].manifest - - -class ZipProvider(EggProvider): - """Resource support for zips and eggs""" - - eagers: list[str] | None = None - _zip_manifests = MemoizedZipManifests() - # ZipProvider's loader should always be a zipimporter or equivalent - loader: zipimport.zipimporter - - def __init__(self, module: _ZipLoaderModule) -> None: - super().__init__(module) - self.zip_pre = self.loader.archive + os.sep - - def _zipinfo_name(self, fspath): - # Convert a virtual filename (full path to file) into a zipfile subpath - # usable with the zipimport directory cache for our target archive - fspath = fspath.rstrip(os.sep) - if fspath == self.loader.archive: - return '' - if fspath.startswith(self.zip_pre): - return fspath[len(self.zip_pre) :] - raise AssertionError(f"{fspath} is not a subpath of {self.zip_pre}") - - def _parts(self, zip_path): - # Convert a zipfile subpath into an egg-relative path part list. - # pseudo-fs path - fspath = self.zip_pre + zip_path - if fspath.startswith(self.egg_root + os.sep): - return fspath[len(self.egg_root) + 1 :].split(os.sep) - raise AssertionError(f"{fspath} is not a subpath of {self.egg_root}") - - @property - def zipinfo(self): - return self._zip_manifests.load(self.loader.archive) - - def get_resource_filename( - self, manager: ResourceManager, resource_name: str - ) -> str: - if not self.egg_name: - raise NotImplementedError( - "resource_filename() only supported for .egg, not .zip" - ) - # no need to lock for extraction, since we use temp names - zip_path = self._resource_to_zip(resource_name) - eagers = self._get_eager_resources() - if '/'.join(self._parts(zip_path)) in eagers: - for name in eagers: - self._extract_resource(manager, self._eager_to_zip(name)) - return self._extract_resource(manager, zip_path) - - @staticmethod - def _get_date_and_size(zip_stat): - size = zip_stat.file_size - # ymdhms+wday, yday, dst - date_time = zip_stat.date_time + (0, 0, -1) - # 1980 offset already done - timestamp = time.mktime(date_time) - return timestamp, size - - # FIXME: 'ZipProvider._extract_resource' is too complex (12) - def _extract_resource(self, manager: ResourceManager, zip_path) -> str: # noqa: C901 - if zip_path in self._index(): - for name in self._index()[zip_path]: - last = self._extract_resource(manager, os.path.join(zip_path, name)) - # return the extracted directory name - return os.path.dirname(last) - - timestamp, _size = self._get_date_and_size(self.zipinfo[zip_path]) - - if not WRITE_SUPPORT: - raise OSError( - '"os.rename" and "os.unlink" are not supported on this platform' - ) - try: - if not self.egg_name: - raise OSError( - '"egg_name" is empty. This likely means no egg could be found from the "module_path".' - ) - real_path = manager.get_cache_path(self.egg_name, self._parts(zip_path)) - - if self._is_current(real_path, zip_path): - return real_path - - outf, tmpnam = _mkstemp( - ".$extract", - dir=os.path.dirname(real_path), - ) - os.write(outf, self.loader.get_data(zip_path)) - os.close(outf) - utime(tmpnam, (timestamp, timestamp)) - manager.postprocess(tmpnam, real_path) - - try: - rename(tmpnam, real_path) - - except OSError: - if os.path.isfile(real_path): - if self._is_current(real_path, zip_path): - # the file became current since it was checked above, - # so proceed. - return real_path - # Windows, del old file and retry - elif os.name == 'nt': - unlink(real_path) - rename(tmpnam, real_path) - return real_path - raise - - except OSError: - # report a user-friendly error - manager.extraction_error() - - return real_path - - def _is_current(self, file_path, zip_path): - """ - Return True if the file_path is current for this zip_path - """ - timestamp, size = self._get_date_and_size(self.zipinfo[zip_path]) - if not os.path.isfile(file_path): - return False - stat = os.stat(file_path) - if stat.st_size != size or stat.st_mtime != timestamp: - return False - # check that the contents match - zip_contents = self.loader.get_data(zip_path) - with open(file_path, 'rb') as f: - file_contents = f.read() - return zip_contents == file_contents - - def _get_eager_resources(self): - if self.eagers is None: - eagers = [] - for name in ('native_libs.txt', 'eager_resources.txt'): - if self.has_metadata(name): - eagers.extend(self.get_metadata_lines(name)) - self.eagers = eagers - return self.eagers - - def _index(self): - try: - return self._dirindex - except AttributeError: - ind = {} - for path in self.zipinfo: - parts = path.split(os.sep) - while parts: - parent = os.sep.join(parts[:-1]) - if parent in ind: - ind[parent].append(parts[-1]) - break - else: - ind[parent] = [parts.pop()] - self._dirindex = ind - return ind - - def _has(self, fspath) -> bool: - zip_path = self._zipinfo_name(fspath) - return zip_path in self.zipinfo or zip_path in self._index() - - def _isdir(self, fspath) -> bool: - return self._zipinfo_name(fspath) in self._index() - - def _listdir(self, fspath): - return list(self._index().get(self._zipinfo_name(fspath), ())) - - def _eager_to_zip(self, resource_name: str): - return self._zipinfo_name(self._fn(self.egg_root, resource_name)) - - def _resource_to_zip(self, resource_name: str): - return self._zipinfo_name(self._fn(self.module_path, resource_name)) - - -register_loader_type(zipimport.zipimporter, ZipProvider) - - -class FileMetadata(EmptyProvider): - """Metadata handler for standalone PKG-INFO files - - Usage:: - - metadata = FileMetadata("/path/to/PKG-INFO") - - This provider rejects all data and metadata requests except for PKG-INFO, - which is treated as existing, and will be the contents of the file at - the provided location. - """ - - def __init__(self, path: StrPath) -> None: - self.path = path - - def _get_metadata_path(self, name): - return self.path - - def has_metadata(self, name: str) -> bool: - return name == 'PKG-INFO' and os.path.isfile(self.path) - - def get_metadata(self, name: str) -> str: - if name != 'PKG-INFO': - raise KeyError("No metadata except PKG-INFO is available") - - with open(self.path, encoding='utf-8', errors="replace") as f: - metadata = f.read() - self._warn_on_replacement(metadata) - return metadata - - def _warn_on_replacement(self, metadata) -> None: - replacement_char = '�' - if replacement_char in metadata: - tmpl = "{self.path} could not be properly decoded in UTF-8" - msg = tmpl.format(**locals()) - warnings.warn(msg) - - def get_metadata_lines(self, name: str) -> Iterator[str]: - return yield_lines(self.get_metadata(name)) - - -class PathMetadata(DefaultProvider): - """Metadata provider for egg directories - - Usage:: - - # Development eggs: - - egg_info = "/path/to/PackageName.egg-info" - base_dir = os.path.dirname(egg_info) - metadata = PathMetadata(base_dir, egg_info) - dist_name = os.path.splitext(os.path.basename(egg_info))[0] - dist = Distribution(basedir, project_name=dist_name, metadata=metadata) - - # Unpacked egg directories: - - egg_path = "/path/to/PackageName-ver-pyver-etc.egg" - metadata = PathMetadata(egg_path, os.path.join(egg_path,'EGG-INFO')) - dist = Distribution.from_filename(egg_path, metadata=metadata) - """ - - def __init__(self, path: str, egg_info: str) -> None: - self.module_path = path - self.egg_info = egg_info - - -class EggMetadata(ZipProvider): - """Metadata provider for .egg files""" - - def __init__(self, importer: zipimport.zipimporter) -> None: - """Create a metadata provider from a zipimporter""" - - self.zip_pre = importer.archive + os.sep - self.loader = importer - if importer.prefix: - self.module_path = os.path.join(importer.archive, importer.prefix) - else: - self.module_path = importer.archive - self._setup_prefix() - - -_distribution_finders: dict[type, _DistFinderType[Any]] = _declare_state( - 'dict', '_distribution_finders', {} -) - - -def register_finder( - importer_type: type[_T], distribution_finder: _DistFinderType[_T] -) -> None: - """Register `distribution_finder` to find distributions in sys.path items - - `importer_type` is the type or class of a PEP 302 "Importer" (sys.path item - handler), and `distribution_finder` is a callable that, passed a path - item and the importer instance, yields ``Distribution`` instances found on - that path item. See ``pkg_resources.find_on_path`` for an example.""" - _distribution_finders[importer_type] = distribution_finder - - -def find_distributions(path_item: str, only: bool = False) -> Iterable[Distribution]: - """Yield distributions accessible via `path_item`""" - importer = get_importer(path_item) - finder = _find_adapter(_distribution_finders, importer) - return finder(importer, path_item, only) - - -def find_eggs_in_zip( - importer: zipimport.zipimporter, path_item: str, only: bool = False -) -> Iterator[Distribution]: - """ - Find eggs in zip files; possibly multiple nested eggs. - """ - if importer.archive.endswith('.whl'): - # wheels are not supported with this finder - # they don't have PKG-INFO metadata, and won't ever contain eggs - return - metadata = EggMetadata(importer) - if metadata.has_metadata('PKG-INFO'): - yield Distribution.from_filename(path_item, metadata=metadata) - if only: - # don't yield nested distros - return - for subitem in metadata.resource_listdir(''): - if _is_egg_path(subitem): - subpath = os.path.join(path_item, subitem) - dists = find_eggs_in_zip(zipimport.zipimporter(subpath), subpath) - yield from dists - elif subitem.lower().endswith(('.dist-info', '.egg-info')): - subpath = os.path.join(path_item, subitem) - submeta = EggMetadata(zipimport.zipimporter(subpath)) - submeta.egg_info = subpath - yield Distribution.from_location(path_item, subitem, submeta) - - -register_finder(zipimport.zipimporter, find_eggs_in_zip) - - -def find_nothing( - importer: object | None, path_item: str | None, only: bool | None = False -): - return () - - -register_finder(object, find_nothing) - - -def find_on_path(importer: object | None, path_item, only=False): - """Yield distributions accessible on a sys.path directory""" - path_item = _normalize_cached(path_item) - - if _is_unpacked_egg(path_item): - yield Distribution.from_filename( - path_item, - metadata=PathMetadata(path_item, os.path.join(path_item, 'EGG-INFO')), - ) - return - - entries = (os.path.join(path_item, child) for child in safe_listdir(path_item)) - - # scan for .egg and .egg-info in directory - for entry in sorted(entries): - fullpath = os.path.join(path_item, entry) - factory = dist_factory(path_item, entry, only) - yield from factory(fullpath) - - -def dist_factory(path_item, entry, only): - """Return a dist_factory for the given entry.""" - lower = entry.lower() - is_egg_info = lower.endswith('.egg-info') - is_dist_info = lower.endswith('.dist-info') and os.path.isdir( - os.path.join(path_item, entry) - ) - is_meta = is_egg_info or is_dist_info - return ( - distributions_from_metadata - if is_meta - else find_distributions - if not only and _is_egg_path(entry) - else resolve_egg_link - if not only and lower.endswith('.egg-link') - else NoDists() - ) - - -class NoDists: - """ - >>> bool(NoDists()) - False - - >>> list(NoDists()('anything')) - [] - """ - - def __bool__(self) -> Literal[False]: - return False - - def __call__(self, fullpath: object): - return iter(()) - - -def safe_listdir(path: StrOrBytesPath): - """ - Attempt to list contents of path, but suppress some exceptions. - """ - try: - return os.listdir(path) - except (PermissionError, NotADirectoryError): - pass - except OSError as e: - # Ignore the directory if does not exist, not a directory or - # permission denied - if e.errno not in (errno.ENOTDIR, errno.EACCES, errno.ENOENT): - raise - return () - - -def distributions_from_metadata(path: str): - root = os.path.dirname(path) - if os.path.isdir(path): - if len(os.listdir(path)) == 0: - # empty metadata dir; skip - return - metadata: _MetadataType = PathMetadata(root, path) - else: - metadata = FileMetadata(path) - entry = os.path.basename(path) - yield Distribution.from_location( - root, - entry, - metadata, - precedence=DEVELOP_DIST, - ) - - -def non_empty_lines(path): - """ - Yield non-empty lines from file at path - """ - for line in _read_utf8_with_fallback(path).splitlines(): - line = line.strip() - if line: - yield line - - -def resolve_egg_link(path): - """ - Given a path to an .egg-link, resolve distributions - present in the referenced path. - """ - referenced_paths = non_empty_lines(path) - resolved_paths = ( - os.path.join(os.path.dirname(path), ref) for ref in referenced_paths - ) - dist_groups = map(find_distributions, resolved_paths) - return next(dist_groups, ()) - - -if hasattr(pkgutil, 'ImpImporter'): - register_finder(pkgutil.ImpImporter, find_on_path) - -register_finder(importlib.machinery.FileFinder, find_on_path) - -_namespace_handlers: dict[type, _NSHandlerType[Any]] = _declare_state( - 'dict', '_namespace_handlers', {} -) -_namespace_packages: dict[str | None, list[str]] = _declare_state( - 'dict', '_namespace_packages', {} -) - - -def register_namespace_handler( - importer_type: type[_T], namespace_handler: _NSHandlerType[_T] -) -> None: - """Register `namespace_handler` to declare namespace packages - - `importer_type` is the type or class of a PEP 302 "Importer" (sys.path item - handler), and `namespace_handler` is a callable like this:: - - def namespace_handler(importer, path_entry, moduleName, module): - # return a path_entry to use for child packages - - Namespace handlers are only called if the importer object has already - agreed that it can handle the relevant path item, and they should only - return a subpath if the module __path__ does not already contain an - equivalent subpath. For an example namespace handler, see - ``pkg_resources.file_ns_handler``. - """ - _namespace_handlers[importer_type] = namespace_handler - - -def _handle_ns(packageName, path_item): - """Ensure that named package includes a subpath of path_item (if needed)""" - - importer = get_importer(path_item) - if importer is None: - return None - - # use find_spec (PEP 451) and fall-back to find_module (PEP 302) - try: - spec = importer.find_spec(packageName) - except AttributeError: - # capture warnings due to #1111 - with warnings.catch_warnings(): - warnings.simplefilter("ignore") - loader = importer.find_module(packageName) - else: - loader = spec.loader if spec else None - - if loader is None: - return None - module = sys.modules.get(packageName) - if module is None: - module = sys.modules[packageName] = types.ModuleType(packageName) - module.__path__ = [] - _set_parent_ns(packageName) - elif not hasattr(module, '__path__'): - raise TypeError("Not a package:", packageName) - handler = _find_adapter(_namespace_handlers, importer) - subpath = handler(importer, path_item, packageName, module) - if subpath is not None: - path = module.__path__ - path.append(subpath) - importlib.import_module(packageName) - _rebuild_mod_path(path, packageName, module) - return subpath - - -def _rebuild_mod_path(orig_path, package_name, module: types.ModuleType) -> None: - """ - Rebuild module.__path__ ensuring that all entries are ordered - corresponding to their sys.path order - """ - sys_path = [_normalize_cached(p) for p in sys.path] - - def safe_sys_path_index(entry): - """ - Workaround for #520 and #513. - """ - try: - return sys_path.index(entry) - except ValueError: - return float('inf') - - def position_in_sys_path(path): - """ - Return the ordinal of the path based on its position in sys.path - """ - path_parts = path.split(os.sep) - module_parts = package_name.count('.') + 1 - parts = path_parts[:-module_parts] - return safe_sys_path_index(_normalize_cached(os.sep.join(parts))) - - new_path = sorted(orig_path, key=position_in_sys_path) - new_path = [_normalize_cached(p) for p in new_path] - - if isinstance(module.__path__, list): - module.__path__[:] = new_path - else: - module.__path__ = new_path - - -def declare_namespace(packageName: str) -> None: - """Declare that package 'packageName' is a namespace package""" - - msg = ( - f"Deprecated call to `pkg_resources.declare_namespace({packageName!r})`.\n" - "Implementing implicit namespace packages (as specified in PEP 420) " - "is preferred to `pkg_resources.declare_namespace`. " - "See https://setuptools.pypa.io/en/latest/references/" - "keywords.html#keyword-namespace-packages" - ) - warnings.warn(msg, DeprecationWarning, stacklevel=2) - - _imp.acquire_lock() - try: - if packageName in _namespace_packages: - return - - path: MutableSequence[str] = sys.path - parent, _, _ = packageName.rpartition('.') - - if parent: - declare_namespace(parent) - if parent not in _namespace_packages: - __import__(parent) - try: - path = sys.modules[parent].__path__ - except AttributeError as e: - raise TypeError("Not a package:", parent) from e - - # Track what packages are namespaces, so when new path items are added, - # they can be updated - _namespace_packages.setdefault(parent or None, []).append(packageName) - _namespace_packages.setdefault(packageName, []) - - for path_item in path: - # Ensure all the parent's path items are reflected in the child, - # if they apply - _handle_ns(packageName, path_item) - - finally: - _imp.release_lock() - - -def fixup_namespace_packages(path_item: str, parent: str | None = None) -> None: - """Ensure that previously-declared namespace packages include path_item""" - _imp.acquire_lock() - try: - for package in _namespace_packages.get(parent, ()): - subpath = _handle_ns(package, path_item) - if subpath: - fixup_namespace_packages(subpath, package) - finally: - _imp.release_lock() - - -def file_ns_handler( - importer: object, - path_item: StrPath, - packageName: str, - module: types.ModuleType, -): - """Compute an ns-package subpath for a filesystem or zipfile importer""" - - subpath = os.path.join(path_item, packageName.split('.')[-1]) - normalized = _normalize_cached(subpath) - for item in module.__path__: - if _normalize_cached(item) == normalized: - break - else: - # Only return the path if it's not already there - return subpath - - -if hasattr(pkgutil, 'ImpImporter'): - register_namespace_handler(pkgutil.ImpImporter, file_ns_handler) - -register_namespace_handler(zipimport.zipimporter, file_ns_handler) -register_namespace_handler(importlib.machinery.FileFinder, file_ns_handler) - - -def null_ns_handler( - importer: object, - path_item: str | None, - packageName: str | None, - module: _ModuleLike | None, -) -> None: - return None - - -register_namespace_handler(object, null_ns_handler) - - -@overload -def normalize_path(filename: StrPath) -> str: ... -@overload -def normalize_path(filename: BytesPath) -> bytes: ... -def normalize_path(filename: StrOrBytesPath) -> str | bytes: - """Normalize a file/dir name for comparison purposes""" - return os.path.normcase(os.path.realpath(os.path.normpath(_cygwin_patch(filename)))) - - -def _cygwin_patch(filename: StrOrBytesPath): # pragma: nocover - """ - Contrary to POSIX 2008, on Cygwin, getcwd (3) contains - symlink components. Using - os.path.abspath() works around this limitation. A fix in os.getcwd() - would probably better, in Cygwin even more so, except - that this seems to be by design... - """ - return os.path.abspath(filename) if sys.platform == 'cygwin' else filename - - -if TYPE_CHECKING: - # https://github.com/python/mypy/issues/16261 - # https://github.com/python/typeshed/issues/6347 - @overload - def _normalize_cached(filename: StrPath) -> str: ... - @overload - def _normalize_cached(filename: BytesPath) -> bytes: ... - def _normalize_cached(filename: StrOrBytesPath) -> str | bytes: ... - -else: - - @functools.cache - def _normalize_cached(filename): - return normalize_path(filename) - - -def _is_egg_path(path): - """ - Determine if given path appears to be an egg. - """ - return _is_zip_egg(path) or _is_unpacked_egg(path) - - -def _is_zip_egg(path): - return ( - path.lower().endswith('.egg') - and os.path.isfile(path) - and zipfile.is_zipfile(path) - ) - - -def _is_unpacked_egg(path): - """ - Determine if given path appears to be an unpacked egg. - """ - return path.lower().endswith('.egg') and os.path.isfile( - os.path.join(path, 'EGG-INFO', 'PKG-INFO') - ) - - -def _set_parent_ns(packageName) -> None: - parts = packageName.split('.') - name = parts.pop() - if parts: - parent = '.'.join(parts) - setattr(sys.modules[parent], name, sys.modules[packageName]) - - -MODULE = re.compile(r"\w+(\.\w+)*$").match -EGG_NAME = re.compile( - r""" - (?P[^-]+) ( - -(?P[^-]+) ( - -py(?P[^-]+) ( - -(?P.+) - )? - )? - )? - """, - re.VERBOSE | re.IGNORECASE, -).match - - -class EntryPoint: - """Object representing an advertised importable object""" - - def __init__( - self, - name: str, - module_name: str, - attrs: Iterable[str] = (), - extras: Iterable[str] = (), - dist: Distribution | None = None, - ) -> None: - if not MODULE(module_name): - raise ValueError("Invalid module name", module_name) - self.name = name - self.module_name = module_name - self.attrs = tuple(attrs) - self.extras = tuple(extras) - self.dist = dist - - def __str__(self) -> str: - s = f"{self.name} = {self.module_name}" - if self.attrs: - s += ':' + '.'.join(self.attrs) - if self.extras: - extras = ','.join(self.extras) - s += f' [{extras}]' - return s - - def __repr__(self) -> str: - return f"EntryPoint.parse({str(self)!r})" - - @overload - def load( - self, - require: Literal[True] = True, - env: Environment | None = None, - installer: _InstallerType | None = None, - ) -> _ResolvedEntryPoint: ... - @overload - def load( - self, - require: Literal[False], - *args: Any, - **kwargs: Any, - ) -> _ResolvedEntryPoint: ... - def load( - self, - require: bool = True, - *args: Environment | _InstallerType | None, - **kwargs: Environment | _InstallerType | None, - ) -> _ResolvedEntryPoint: - """ - Require packages for this EntryPoint, then resolve it. - """ - if not require or args or kwargs: - warnings.warn( - "Parameters to load are deprecated. Call .resolve and " - ".require separately.", - PkgResourcesDeprecationWarning, - stacklevel=2, - ) - if require: - # We could pass `env` and `installer` directly, - # but keeping `*args` and `**kwargs` for backwards compatibility - self.require(*args, **kwargs) # type: ignore[arg-type] - return self.resolve() - - def resolve(self) -> _ResolvedEntryPoint: - """ - Resolve the entry point from its module and attrs. - """ - module = __import__(self.module_name, fromlist=['__name__'], level=0) - try: - return functools.reduce(getattr, self.attrs, module) - except AttributeError as exc: - raise ImportError(str(exc)) from exc - - def require( - self, - env: Environment | None = None, - installer: _InstallerType | None = None, - ) -> None: - if not self.dist: - error_cls = UnknownExtra if self.extras else AttributeError - raise error_cls("Can't require() without a distribution", self) - - # Get the requirements for this entry point with all its extras and - # then resolve them. We have to pass `extras` along when resolving so - # that the working set knows what extras we want. Otherwise, for - # dist-info distributions, the working set will assume that the - # requirements for that extra are purely optional and skip over them. - reqs = self.dist.requires(self.extras) - items = working_set.resolve(reqs, env, installer, extras=self.extras) - list(map(working_set.add, items)) - - pattern = re.compile( - r'\s*' - r'(?P.+?)\s*' - r'=\s*' - r'(?P[\w.]+)\s*' - r'(:\s*(?P[\w.]+))?\s*' - r'(?P\[.*\])?\s*$' - ) - - @classmethod - def parse(cls, src: str, dist: Distribution | None = None) -> Self: - """Parse a single entry point from string `src` - - Entry point syntax follows the form:: - - name = some.module:some.attr [extra1, extra2] - - The entry name and module name are required, but the ``:attrs`` and - ``[extras]`` parts are optional - """ - m = cls.pattern.match(src) - if not m: - msg = "EntryPoint must be in 'name=module:attrs [extras]' format" - raise ValueError(msg, src) - res = m.groupdict() - extras = cls._parse_extras(res['extras']) - attrs = res['attr'].split('.') if res['attr'] else () - return cls(res['name'], res['module'], attrs, extras, dist) - - @classmethod - def _parse_extras(cls, extras_spec): - if not extras_spec: - return () - req = Requirement.parse('x' + extras_spec) - if req.specs: - raise ValueError - return req.extras - - @classmethod - def parse_group( - cls, - group: str, - lines: _NestedStr, - dist: Distribution | None = None, - ) -> dict[str, Self]: - """Parse an entry point group""" - if not MODULE(group): - raise ValueError("Invalid group name", group) - this: dict[str, Self] = {} - for line in yield_lines(lines): - ep = cls.parse(line, dist) - if ep.name in this: - raise ValueError("Duplicate entry point", group, ep.name) - this[ep.name] = ep - return this - - @classmethod - def parse_map( - cls, - data: str | Iterable[str] | dict[str, str | Iterable[str]], - dist: Distribution | None = None, - ) -> dict[str, dict[str, Self]]: - """Parse a map of entry point groups""" - _data: Iterable[tuple[str | None, str | Iterable[str]]] - if isinstance(data, dict): - _data = data.items() - else: - _data = split_sections(data) - maps: dict[str, dict[str, Self]] = {} - for group, lines in _data: - if group is None: - if not lines: - continue - raise ValueError("Entry points must be listed in groups") - group = group.strip() - if group in maps: - raise ValueError("Duplicate group name", group) - maps[group] = cls.parse_group(group, lines, dist) - return maps - - -def _version_from_file(lines): - """ - Given an iterable of lines from a Metadata file, return - the value of the Version field, if present, or None otherwise. - """ - - def is_version_line(line): - return line.lower().startswith('version:') - - version_lines = filter(is_version_line, lines) - line = next(iter(version_lines), '') - _, _, value = line.partition(':') - return safe_version(value.strip()) or None - - -class Distribution: - """Wrap an actual or potential sys.path entry w/metadata""" - - PKG_INFO = 'PKG-INFO' - - def __init__( - self, - location: str | None = None, - metadata: _MetadataType = None, - project_name: str | None = None, - version: str | None = None, - py_version: str | None = PY_MAJOR, - platform: str | None = None, - precedence: int = EGG_DIST, - ) -> None: - self.project_name = safe_name(project_name or 'Unknown') - if version is not None: - self._version = safe_version(version) - self.py_version = py_version - self.platform = platform - self.location = location - self.precedence = precedence - self._provider = metadata or empty_provider - - @classmethod - def from_location( - cls, - location: str, - basename: StrPath, - metadata: _MetadataType = None, - **kw: int, # We could set `precedence` explicitly, but keeping this as `**kw` for full backwards and subclassing compatibility - ) -> Distribution: - project_name, version, py_version, platform = [None] * 4 - basename, ext = os.path.splitext(basename) - if ext.lower() in _distributionImpl: - cls = _distributionImpl[ext.lower()] - - match = EGG_NAME(basename) - if match: - project_name, version, py_version, platform = match.group( - 'name', 'ver', 'pyver', 'plat' - ) - return cls( - location, - metadata, - project_name=project_name, - version=version, - py_version=py_version, - platform=platform, - **kw, - )._reload_version() - - def _reload_version(self): - return self - - @property - def hashcmp(self): - return ( - self._forgiving_parsed_version, - self.precedence, - self.key, - self.location, - self.py_version or '', - self.platform or '', - ) - - def __hash__(self) -> int: - return hash(self.hashcmp) - - def __lt__(self, other: Distribution) -> bool: - return self.hashcmp < other.hashcmp - - def __le__(self, other: Distribution) -> bool: - return self.hashcmp <= other.hashcmp - - def __gt__(self, other: Distribution) -> bool: - return self.hashcmp > other.hashcmp - - def __ge__(self, other: Distribution) -> bool: - return self.hashcmp >= other.hashcmp - - def __eq__(self, other: object) -> bool: - if not isinstance(other, self.__class__): - # It's not a Distribution, so they are not equal - return False - return self.hashcmp == other.hashcmp - - def __ne__(self, other: object) -> bool: - return not self == other - - # These properties have to be lazy so that we don't have to load any - # metadata until/unless it's actually needed. (i.e., some distributions - # may not know their name or version without loading PKG-INFO) - - @property - def key(self): - try: - return self._key - except AttributeError: - self._key = key = self.project_name.lower() - return key - - @property - def parsed_version(self): - if not hasattr(self, "_parsed_version"): - try: - self._parsed_version = parse_version(self.version) - except packaging.version.InvalidVersion as ex: - info = f"(package: {self.project_name})" - if hasattr(ex, "add_note"): - ex.add_note(info) # PEP 678 - raise - raise packaging.version.InvalidVersion(f"{str(ex)} {info}") from None - - return self._parsed_version - - @property - def _forgiving_parsed_version(self): - try: - return self.parsed_version - except packaging.version.InvalidVersion as ex: - self._parsed_version = parse_version(_forgiving_version(self.version)) - - notes = "\n".join(getattr(ex, "__notes__", [])) # PEP 678 - msg = f"""!!\n\n - ************************************************************************* - {str(ex)}\n{notes} - - This is a long overdue deprecation. - For the time being, `pkg_resources` will use `{self._parsed_version}` - as a replacement to avoid breaking existing environments, - but no future compatibility is guaranteed. - - If you maintain package {self.project_name} you should implement - the relevant changes to adequate the project to PEP 440 immediately. - ************************************************************************* - \n\n!! - """ - warnings.warn(msg, DeprecationWarning) - - return self._parsed_version - - @property - def version(self): - try: - return self._version - except AttributeError as e: - version = self._get_version() - if version is None: - path = self._get_metadata_path_for_display(self.PKG_INFO) - msg = f"Missing 'Version:' header and/or {self.PKG_INFO} file at path: {path}" - raise ValueError(msg, self) from e - - return version - - @property - def _dep_map(self): - """ - A map of extra to its list of (direct) requirements - for this distribution, including the null extra. - """ - try: - return self.__dep_map - except AttributeError: - self.__dep_map = self._filter_extras(self._build_dep_map()) - return self.__dep_map - - @staticmethod - def _filter_extras( - dm: dict[str | None, list[Requirement]], - ) -> dict[str | None, list[Requirement]]: - """ - Given a mapping of extras to dependencies, strip off - environment markers and filter out any dependencies - not matching the markers. - """ - for extra in list(filter(None, dm)): - new_extra: str | None = extra - reqs = dm.pop(extra) - new_extra, _, marker = extra.partition(':') - fails_marker = marker and ( - invalid_marker(marker) or not evaluate_marker(marker) - ) - if fails_marker: - reqs = [] - new_extra = safe_extra(new_extra) or None - - dm.setdefault(new_extra, []).extend(reqs) - return dm - - def _build_dep_map(self): - dm = {} - for name in 'requires.txt', 'depends.txt': - for extra, reqs in split_sections(self._get_metadata(name)): - dm.setdefault(extra, []).extend(parse_requirements(reqs)) - return dm - - def requires(self, extras: Iterable[str] = ()) -> list[Requirement]: - """List of Requirements needed for this distro if `extras` are used""" - dm = self._dep_map - deps: list[Requirement] = [] - deps.extend(dm.get(None, ())) - for ext in extras: - try: - deps.extend(dm[safe_extra(ext)]) - except KeyError as e: - raise UnknownExtra(f"{self} has no such extra feature {ext!r}") from e - return deps - - def _get_metadata_path_for_display(self, name): - """ - Return the path to the given metadata file, if available. - """ - try: - # We need to access _get_metadata_path() on the provider object - # directly rather than through this class's __getattr__() - # since _get_metadata_path() is marked private. - path = self._provider._get_metadata_path(name) - - # Handle exceptions e.g. in case the distribution's metadata - # provider doesn't support _get_metadata_path(). - except Exception: - return '[could not detect]' - - return path - - def _get_metadata(self, name): - if self.has_metadata(name): - yield from self.get_metadata_lines(name) - - def _get_version(self): - lines = self._get_metadata(self.PKG_INFO) - return _version_from_file(lines) - - def activate(self, path: list[str] | None = None, replace: bool = False) -> None: - """Ensure distribution is importable on `path` (default=sys.path)""" - if path is None: - path = sys.path - self.insert_on(path, replace=replace) - if path is sys.path and self.location is not None: - fixup_namespace_packages(self.location) - for pkg in self._get_metadata('namespace_packages.txt'): - if pkg in sys.modules: - declare_namespace(pkg) - - def egg_name(self): - """Return what this distribution's standard .egg filename should be""" - filename = f"{to_filename(self.project_name)}-{to_filename(self.version)}-py{self.py_version or PY_MAJOR}" - - if self.platform: - filename += '-' + self.platform - return filename - - def __repr__(self) -> str: - if self.location: - return f"{self} ({self.location})" - else: - return str(self) - - def __str__(self) -> str: - try: - version = getattr(self, 'version', None) - except ValueError: - version = None - version = version or "[unknown version]" - return f"{self.project_name} {version}" - - def __getattr__(self, attr: str): - """Delegate all unrecognized public attributes to .metadata provider""" - if attr.startswith('_'): - raise AttributeError(attr) - return getattr(self._provider, attr) - - def __dir__(self): - return list( - set(super().__dir__()) - | set(attr for attr in self._provider.__dir__() if not attr.startswith('_')) - ) - - @classmethod - def from_filename( - cls, - filename: StrPath, - metadata: _MetadataType = None, - **kw: int, # We could set `precedence` explicitly, but keeping this as `**kw` for full backwards and subclassing compatibility - ) -> Distribution: - return cls.from_location( - _normalize_cached(filename), os.path.basename(filename), metadata, **kw - ) - - def as_requirement(self): - """Return a ``Requirement`` that matches this distribution exactly""" - if isinstance(self.parsed_version, packaging.version.Version): - spec = f"{self.project_name}=={self.parsed_version}" - else: - spec = f"{self.project_name}==={self.parsed_version}" - - return Requirement.parse(spec) - - def load_entry_point(self, group: str, name: str) -> _ResolvedEntryPoint: - """Return the `name` entry point of `group` or raise ImportError""" - ep = self.get_entry_info(group, name) - if ep is None: - raise ImportError(f"Entry point {(group, name)!r} not found") - return ep.load() - - @overload - def get_entry_map(self, group: None = None) -> dict[str, dict[str, EntryPoint]]: ... - @overload - def get_entry_map(self, group: str) -> dict[str, EntryPoint]: ... - def get_entry_map(self, group: str | None = None): - """Return the entry point map for `group`, or the full entry map""" - if not hasattr(self, "_ep_map"): - self._ep_map = EntryPoint.parse_map( - self._get_metadata('entry_points.txt'), self - ) - if group is not None: - return self._ep_map.get(group, {}) - return self._ep_map - - def get_entry_info(self, group: str, name: str) -> EntryPoint | None: - """Return the EntryPoint object for `group`+`name`, or ``None``""" - return self.get_entry_map(group).get(name) - - # FIXME: 'Distribution.insert_on' is too complex (13) - def insert_on( # noqa: C901 - self, - path: list[str], - loc=None, - replace: bool = False, - ) -> None: - """Ensure self.location is on path - - If replace=False (default): - - If location is already in path anywhere, do nothing. - - Else: - - If it's an egg and its parent directory is on path, - insert just ahead of the parent. - - Else: add to the end of path. - If replace=True: - - If location is already on path anywhere (not eggs) - or higher priority than its parent (eggs) - do nothing. - - Else: - - If it's an egg and its parent directory is on path, - insert just ahead of the parent, - removing any lower-priority entries. - - Else: add it to the front of path. - """ - - loc = loc or self.location - if not loc: - return - - nloc = _normalize_cached(loc) - bdir = os.path.dirname(nloc) - npath = [(p and _normalize_cached(p) or p) for p in path] - - for p, item in enumerate(npath): - if item == nloc: - if replace: - break - else: - # don't modify path (even removing duplicates) if - # found and not replace - return - elif item == bdir and self.precedence == EGG_DIST: - # if it's an .egg, give it precedence over its directory - # UNLESS it's already been added to sys.path and replace=False - if (not replace) and nloc in npath[p:]: - return - if path is sys.path: - self.check_version_conflict() - path.insert(p, loc) - npath.insert(p, nloc) - break - else: - if path is sys.path: - self.check_version_conflict() - if replace: - path.insert(0, loc) - else: - path.append(loc) - return - - # p is the spot where we found or inserted loc; now remove duplicates - while True: - try: - np = npath.index(nloc, p + 1) - except ValueError: - break - else: - del npath[np], path[np] - # ha! - p = np - - return - - def check_version_conflict(self): - if self.key == 'setuptools': - # ignore the inevitable setuptools self-conflicts :( - return - - nsp = dict.fromkeys(self._get_metadata('namespace_packages.txt')) - loc = normalize_path(self.location) - for modname in self._get_metadata('top_level.txt'): - if ( - modname not in sys.modules - or modname in nsp - or modname in _namespace_packages - ): - continue - if modname in ('pkg_resources', 'setuptools', 'site'): - continue - fn = getattr(sys.modules[modname], '__file__', None) - if fn and ( - normalize_path(fn).startswith(loc) or fn.startswith(self.location) - ): - continue - issue_warning( - f"Module {modname} was already imported from {fn}, " - f"but {self.location} is being added to sys.path", - ) - - def has_version(self) -> bool: - try: - self.version - except ValueError: - issue_warning("Unbuilt egg for " + repr(self)) - return False - except SystemError: - # TODO: remove this except clause when python/cpython#103632 is fixed. - return False - return True - - def clone(self, **kw: str | int | IResourceProvider | None) -> Self: - """Copy this distribution, substituting in any changed keyword args""" - names = 'project_name version py_version platform location precedence' - for attr in names.split(): - kw.setdefault(attr, getattr(self, attr, None)) - kw.setdefault('metadata', self._provider) - # Unsafely unpacking. But keeping **kw for backwards and subclassing compatibility - return self.__class__(**kw) # type:ignore[arg-type] - - @property - def extras(self): - return [dep for dep in self._dep_map if dep] - - -class EggInfoDistribution(Distribution): - def _reload_version(self): - """ - Packages installed by distutils (e.g. numpy or scipy), - which uses an old safe_version, and so - their version numbers can get mangled when - converted to filenames (e.g., 1.11.0.dev0+2329eae to - 1.11.0.dev0_2329eae). These distributions will not be - parsed properly - downstream by Distribution and safe_version, so - take an extra step and try to get the version number from - the metadata file itself instead of the filename. - """ - md_version = self._get_version() - if md_version: - self._version = md_version - return self - - -class DistInfoDistribution(Distribution): - """ - Wrap an actual or potential sys.path entry - w/metadata, .dist-info style. - """ - - PKG_INFO = 'METADATA' - EQEQ = re.compile(r"([\(,])\s*(\d.*?)\s*([,\)])") - - @property - def _parsed_pkg_info(self): - """Parse and cache metadata""" - try: - return self._pkg_info - except AttributeError: - metadata = self.get_metadata(self.PKG_INFO) - self._pkg_info = email.parser.Parser().parsestr(metadata) - return self._pkg_info - - @property - def _dep_map(self): - try: - return self.__dep_map - except AttributeError: - self.__dep_map = self._compute_dependencies() - return self.__dep_map - - def _compute_dependencies(self) -> dict[str | None, list[Requirement]]: - """Recompute this distribution's dependencies.""" - self.__dep_map: dict[str | None, list[Requirement]] = {None: []} - - reqs: list[Requirement] = [] - # Including any condition expressions - for req in self._parsed_pkg_info.get_all('Requires-Dist') or []: - reqs.extend(parse_requirements(req)) - - def reqs_for_extra(extra): - for req in reqs: - if not req.marker or req.marker.evaluate({'extra': extra}): - yield req - - common = types.MappingProxyType(dict.fromkeys(reqs_for_extra(None))) - self.__dep_map[None].extend(common) - - for extra in self._parsed_pkg_info.get_all('Provides-Extra') or []: - s_extra = safe_extra(extra.strip()) - self.__dep_map[s_extra] = [ - r for r in reqs_for_extra(extra) if r not in common - ] - - return self.__dep_map - - -_distributionImpl = { - '.egg': Distribution, - '.egg-info': EggInfoDistribution, - '.dist-info': DistInfoDistribution, -} - - -def issue_warning(*args, **kw): - level = 1 - g = globals() - try: - # find the first stack frame that is *not* code in - # the pkg_resources module, to use for the warning - while sys._getframe(level).f_globals is g: - level += 1 - except ValueError: - pass - warnings.warn(stacklevel=level + 1, *args, **kw) - - -def parse_requirements(strs: _NestedStr) -> map[Requirement]: - """ - Yield ``Requirement`` objects for each specification in `strs`. - - `strs` must be a string, or a (possibly-nested) iterable thereof. - """ - return map(Requirement, join_continuation(map(drop_comment, yield_lines(strs)))) - - -class RequirementParseError(packaging.requirements.InvalidRequirement): - "Compatibility wrapper for InvalidRequirement" - - -class Requirement(packaging.requirements.Requirement): - # prefer variable length tuple to set (as found in - # packaging.requirements.Requirement) - extras: tuple[str, ...] # type: ignore[assignment] - - def __init__(self, requirement_string: str) -> None: - """DO NOT CALL THIS UNDOCUMENTED METHOD; use Requirement.parse()!""" - super().__init__(requirement_string) - self.unsafe_name = self.name - project_name = safe_name(self.name) - self.project_name, self.key = project_name, project_name.lower() - self.specs = [(spec.operator, spec.version) for spec in self.specifier] - self.extras = tuple(map(safe_extra, self.extras)) - self.hashCmp = ( - self.key, - self.url, - self.specifier, - frozenset(self.extras), - str(self.marker) if self.marker else None, - ) - self.__hash = hash(self.hashCmp) - - def __eq__(self, other: object) -> bool: - return isinstance(other, Requirement) and self.hashCmp == other.hashCmp - - def __ne__(self, other: object) -> bool: - return not self == other - - def __contains__( - self, item: Distribution | packaging.specifiers.UnparsedVersion - ) -> bool: - if isinstance(item, Distribution): - if item.key != self.key: - return False - - version = item.version - else: - version = item - - # Allow prereleases always in order to match the previous behavior of - # this method. In the future this should be smarter and follow PEP 440 - # more accurately. - return self.specifier.contains( - version, - prereleases=True, - ) - - def __hash__(self) -> int: - return self.__hash - - def __repr__(self) -> str: - return f"Requirement.parse({str(self)!r})" - - @staticmethod - def parse(s: str | Iterable[str]) -> Requirement: - (req,) = parse_requirements(s) - return req - - -def _always_object(classes): - """ - Ensure object appears in the mro even - for old-style classes. - """ - if object not in classes: - return classes + (object,) - return classes - - -def _find_adapter(registry: Mapping[type, _AdapterT], ob: object) -> _AdapterT: - """Return an adapter factory for `ob` from `registry`""" - types = _always_object(inspect.getmro(getattr(ob, '__class__', type(ob)))) - for t in types: - if t in registry: - return registry[t] - # _find_adapter would previously return None, and immediately be called. - # So we're raising a TypeError to keep backward compatibility if anyone depended on that behaviour. - raise TypeError(f"Could not find adapter for {registry} and {ob}") - - -def ensure_directory(path: StrOrBytesPath) -> None: - """Ensure that the parent directory of `path` exists""" - dirname = os.path.dirname(path) - os.makedirs(dirname, exist_ok=True) - - -def _bypass_ensure_directory(path) -> None: - """Sandbox-bypassing version of ensure_directory()""" - if not WRITE_SUPPORT: - raise OSError('"os.mkdir" not supported on this platform.') - dirname, filename = split(path) - if dirname and filename and not isdir(dirname): - _bypass_ensure_directory(dirname) - try: - mkdir(dirname, 0o755) - except FileExistsError: - pass - - -def split_sections(s: _NestedStr) -> Iterator[tuple[str | None, list[str]]]: - """Split a string or iterable thereof into (section, content) pairs - - Each ``section`` is a stripped version of the section header ("[section]") - and each ``content`` is a list of stripped lines excluding blank lines and - comment-only lines. If there are any such lines before the first section - header, they're returned in a first ``section`` of ``None``. - """ - section = None - content: list[str] = [] - for line in yield_lines(s): - if line.startswith("["): - if line.endswith("]"): - if section or content: - yield section, content - section = line[1:-1].strip() - content = [] - else: - raise ValueError("Invalid section heading", line) - else: - content.append(line) - - # wrap up last segment - yield section, content - - -def _mkstemp(*args, **kw): - old_open = os.open - try: - # temporarily bypass sandboxing - os.open = os_open - return tempfile.mkstemp(*args, **kw) - finally: - # and then put it back - os.open = old_open - - -# Silence the PEP440Warning by default, so that end users don't get hit by it -# randomly just because they use pkg_resources. We want to append the rule -# because we want earlier uses of filterwarnings to take precedence over this -# one. -warnings.filterwarnings("ignore", category=PEP440Warning, append=True) - - -class PkgResourcesDeprecationWarning(Warning): - """ - Base class for warning about deprecations in ``pkg_resources`` - - This class is not derived from ``DeprecationWarning``, and as such is - visible by default. - """ - - -# Ported from ``setuptools`` to avoid introducing an import inter-dependency: -_LOCALE_ENCODING = "locale" if sys.version_info >= (3, 10) else None - - -# This must go before calls to `_call_aside`. See https://github.com/pypa/setuptools/pull/4422 -def _read_utf8_with_fallback(file: str, fallback_encoding=_LOCALE_ENCODING) -> str: - """See setuptools.unicode_utils._read_utf8_with_fallback""" - try: - with open(file, "r", encoding="utf-8") as f: - return f.read() - except UnicodeDecodeError: # pragma: no cover - msg = f"""\ - ******************************************************************************** - `encoding="utf-8"` fails with {file!r}, trying `encoding={fallback_encoding!r}`. - - This fallback behaviour is considered **deprecated** and future versions of - `setuptools/pkg_resources` may not implement it. - - Please encode {file!r} with "utf-8" to ensure future builds will succeed. - - If this file was produced by `setuptools` itself, cleaning up the cached files - and re-building/re-installing the package with a newer version of `setuptools` - (e.g. by updating `build-system.requires` in its `pyproject.toml`) - might solve the problem. - ******************************************************************************** - """ - # TODO: Add a deadline? - # See comment in setuptools.unicode_utils._Utf8EncodingNeeded - warnings.warn(msg, PkgResourcesDeprecationWarning, stacklevel=2) - with open(file, "r", encoding=fallback_encoding) as f: - return f.read() - - -# from jaraco.functools 1.3 -def _call_aside(f, *args, **kwargs): - f(*args, **kwargs) - return f - - -@_call_aside -def _initialize(g=globals()) -> None: - "Set up global resource manager (deliberately not state-saved)" - manager = ResourceManager() - g['_manager'] = manager - g.update( - (name, getattr(manager, name)) - for name in dir(manager) - if not name.startswith('_') - ) - - -@_call_aside -def _initialize_master_working_set() -> None: - """ - Prepare the master working set and make the ``require()`` - API available. - - This function has explicit effects on the global state - of pkg_resources. It is intended to be invoked once at - the initialization of this module. - - Invocation by other packages is unsupported and done - at their own risk. - """ - working_set = _declare_state('object', 'working_set', WorkingSet._build_master()) - - require = working_set.require - iter_entry_points = working_set.iter_entry_points - add_activation_listener = working_set.subscribe - run_script = working_set.run_script - # backward compatibility - run_main = run_script - # Activate all distributions already on sys.path with replace=False and - # ensure that all distributions added to the working set in the future - # (e.g. by calling ``require()``) will get activated as well, - # with higher priority (replace=True). - tuple(dist.activate(replace=False) for dist in working_set) - add_activation_listener( - lambda dist: dist.activate(replace=True), - existing=False, - ) - working_set.entries = [] - # match order - list(map(working_set.add_entry, sys.path)) - globals().update(locals()) - - -if TYPE_CHECKING: - # All of these are set by the @_call_aside methods above - __resource_manager = ResourceManager() # Won't exist at runtime - resource_exists = __resource_manager.resource_exists - resource_isdir = __resource_manager.resource_isdir - resource_filename = __resource_manager.resource_filename - resource_stream = __resource_manager.resource_stream - resource_string = __resource_manager.resource_string - resource_listdir = __resource_manager.resource_listdir - set_extraction_path = __resource_manager.set_extraction_path - cleanup_resources = __resource_manager.cleanup_resources - - working_set = WorkingSet() - require = working_set.require - iter_entry_points = working_set.iter_entry_points - add_activation_listener = working_set.subscribe - run_script = working_set.run_script - run_main = run_script diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 528f720..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/api_tests.txt b/llmlab/lib/python3.12/site-packages/pkg_resources/api_tests.txt deleted file mode 100644 index d72b85a..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/api_tests.txt +++ /dev/null @@ -1,424 +0,0 @@ -Pluggable Distributions of Python Software -========================================== - -Distributions -------------- - -A "Distribution" is a collection of files that represent a "Release" of a -"Project" as of a particular point in time, denoted by a -"Version":: - - >>> import sys, pkg_resources - >>> from pkg_resources import Distribution - >>> Distribution(project_name="Foo", version="1.2") - Foo 1.2 - -Distributions have a location, which can be a filename, URL, or really anything -else you care to use:: - - >>> dist = Distribution( - ... location="http://example.com/something", - ... project_name="Bar", version="0.9" - ... ) - - >>> dist - Bar 0.9 (http://example.com/something) - - -Distributions have various introspectable attributes:: - - >>> dist.location - 'http://example.com/something' - - >>> dist.project_name - 'Bar' - - >>> dist.version - '0.9' - - >>> dist.py_version == '{}.{}'.format(*sys.version_info) - True - - >>> print(dist.platform) - None - -Including various computed attributes:: - - >>> from pkg_resources import parse_version - >>> dist.parsed_version == parse_version(dist.version) - True - - >>> dist.key # case-insensitive form of the project name - 'bar' - -Distributions are compared (and hashed) by version first:: - - >>> Distribution(version='1.0') == Distribution(version='1.0') - True - >>> Distribution(version='1.0') == Distribution(version='1.1') - False - >>> Distribution(version='1.0') < Distribution(version='1.1') - True - -but also by project name (case-insensitive), platform, Python version, -location, etc.:: - - >>> Distribution(project_name="Foo",version="1.0") == \ - ... Distribution(project_name="Foo",version="1.0") - True - - >>> Distribution(project_name="Foo",version="1.0") == \ - ... Distribution(project_name="foo",version="1.0") - True - - >>> Distribution(project_name="Foo",version="1.0") == \ - ... Distribution(project_name="Foo",version="1.1") - False - - >>> Distribution(project_name="Foo",py_version="2.3",version="1.0") == \ - ... Distribution(project_name="Foo",py_version="2.4",version="1.0") - False - - >>> Distribution(location="spam",version="1.0") == \ - ... Distribution(location="spam",version="1.0") - True - - >>> Distribution(location="spam",version="1.0") == \ - ... Distribution(location="baz",version="1.0") - False - - - -Hash and compare distribution by prio/plat - -Get version from metadata -provider capabilities -egg_name() -as_requirement() -from_location, from_filename (w/path normalization) - -Releases may have zero or more "Requirements", which indicate -what releases of another project the release requires in order to -function. A Requirement names the other project, expresses some criteria -as to what releases of that project are acceptable, and lists any "Extras" -that the requiring release may need from that project. (An Extra is an -optional feature of a Release, that can only be used if its additional -Requirements are satisfied.) - - - -The Working Set ---------------- - -A collection of active distributions is called a Working Set. Note that a -Working Set can contain any importable distribution, not just pluggable ones. -For example, the Python standard library is an importable distribution that -will usually be part of the Working Set, even though it is not pluggable. -Similarly, when you are doing development work on a project, the files you are -editing are also a Distribution. (And, with a little attention to the -directory names used, and including some additional metadata, such a -"development distribution" can be made pluggable as well.) - - >>> from pkg_resources import WorkingSet - -A working set's entries are the sys.path entries that correspond to the active -distributions. By default, the working set's entries are the items on -``sys.path``:: - - >>> ws = WorkingSet() - >>> ws.entries == sys.path - True - -But you can also create an empty working set explicitly, and add distributions -to it:: - - >>> ws = WorkingSet([]) - >>> ws.add(dist) - >>> ws.entries - ['http://example.com/something'] - >>> dist in ws - True - >>> Distribution('foo',version="") in ws - False - -And you can iterate over its distributions:: - - >>> list(ws) - [Bar 0.9 (http://example.com/something)] - -Adding the same distribution more than once is a no-op:: - - >>> ws.add(dist) - >>> list(ws) - [Bar 0.9 (http://example.com/something)] - -For that matter, adding multiple distributions for the same project also does -nothing, because a working set can only hold one active distribution per -project -- the first one added to it:: - - >>> ws.add( - ... Distribution( - ... 'http://example.com/something', project_name="Bar", - ... version="7.2" - ... ) - ... ) - >>> list(ws) - [Bar 0.9 (http://example.com/something)] - -You can append a path entry to a working set using ``add_entry()``:: - - >>> ws.entries - ['http://example.com/something'] - >>> ws.add_entry(pkg_resources.__file__) - >>> ws.entries - ['http://example.com/something', '...pkg_resources...'] - -Multiple additions result in multiple entries, even if the entry is already in -the working set (because ``sys.path`` can contain the same entry more than -once):: - - >>> ws.add_entry(pkg_resources.__file__) - >>> ws.entries - ['...example.com...', '...pkg_resources...', '...pkg_resources...'] - -And you can specify the path entry a distribution was found under, using the -optional second parameter to ``add()``:: - - >>> ws = WorkingSet([]) - >>> ws.add(dist,"foo") - >>> ws.entries - ['foo'] - -But even if a distribution is found under multiple path entries, it still only -shows up once when iterating the working set: - - >>> ws.add_entry(ws.entries[0]) - >>> list(ws) - [Bar 0.9 (http://example.com/something)] - -You can ask a WorkingSet to ``find()`` a distribution matching a requirement:: - - >>> from pkg_resources import Requirement - >>> print(ws.find(Requirement.parse("Foo==1.0"))) # no match, return None - None - - >>> ws.find(Requirement.parse("Bar==0.9")) # match, return distribution - Bar 0.9 (http://example.com/something) - -Note that asking for a conflicting version of a distribution already in a -working set triggers a ``pkg_resources.VersionConflict`` error: - - >>> try: - ... ws.find(Requirement.parse("Bar==1.0")) - ... except pkg_resources.VersionConflict as exc: - ... print(str(exc)) - ... else: - ... raise AssertionError("VersionConflict was not raised") - (Bar 0.9 (http://example.com/something), Requirement.parse('Bar==1.0')) - -You can subscribe a callback function to receive notifications whenever a new -distribution is added to a working set. The callback is immediately invoked -once for each existing distribution in the working set, and then is called -again for new distributions added thereafter:: - - >>> def added(dist): print("Added %s" % dist) - >>> ws.subscribe(added) - Added Bar 0.9 - >>> foo12 = Distribution(project_name="Foo", version="1.2", location="f12") - >>> ws.add(foo12) - Added Foo 1.2 - -Note, however, that only the first distribution added for a given project name -will trigger a callback, even during the initial ``subscribe()`` callback:: - - >>> foo14 = Distribution(project_name="Foo", version="1.4", location="f14") - >>> ws.add(foo14) # no callback, because Foo 1.2 is already active - - >>> ws = WorkingSet([]) - >>> ws.add(foo12) - >>> ws.add(foo14) - >>> ws.subscribe(added) - Added Foo 1.2 - -And adding a callback more than once has no effect, either:: - - >>> ws.subscribe(added) # no callbacks - - # and no double-callbacks on subsequent additions, either - >>> just_a_test = Distribution(project_name="JustATest", version="0.99") - >>> ws.add(just_a_test) - Added JustATest 0.99 - - -Finding Plugins ---------------- - -``WorkingSet`` objects can be used to figure out what plugins in an -``Environment`` can be loaded without any resolution errors:: - - >>> from pkg_resources import Environment - - >>> plugins = Environment([]) # normally, a list of plugin directories - >>> plugins.add(foo12) - >>> plugins.add(foo14) - >>> plugins.add(just_a_test) - -In the simplest case, we just get the newest version of each distribution in -the plugin environment:: - - >>> ws = WorkingSet([]) - >>> ws.find_plugins(plugins) - ([JustATest 0.99, Foo 1.4 (f14)], {}) - -But if there's a problem with a version conflict or missing requirements, the -method falls back to older versions, and the error info dict will contain an -exception instance for each unloadable plugin:: - - >>> ws.add(foo12) # this will conflict with Foo 1.4 - >>> ws.find_plugins(plugins) - ([JustATest 0.99, Foo 1.2 (f12)], {Foo 1.4 (f14): VersionConflict(...)}) - -But if you disallow fallbacks, the failed plugin will be skipped instead of -trying older versions:: - - >>> ws.find_plugins(plugins, fallback=False) - ([JustATest 0.99], {Foo 1.4 (f14): VersionConflict(...)}) - - - -Platform Compatibility Rules ----------------------------- - -On the Mac, there are potential compatibility issues for modules compiled -on newer versions of macOS than what the user is running. Additionally, -macOS will soon have two platforms to contend with: Intel and PowerPC. - -Basic equality works as on other platforms:: - - >>> from pkg_resources import compatible_platforms as cp - >>> reqd = 'macosx-10.4-ppc' - >>> cp(reqd, reqd) - True - >>> cp("win32", reqd) - False - -Distributions made on other machine types are not compatible:: - - >>> cp("macosx-10.4-i386", reqd) - False - -Distributions made on earlier versions of the OS are compatible, as -long as they are from the same top-level version. The patchlevel version -number does not matter:: - - >>> cp("macosx-10.4-ppc", reqd) - True - >>> cp("macosx-10.3-ppc", reqd) - True - >>> cp("macosx-10.5-ppc", reqd) - False - >>> cp("macosx-9.5-ppc", reqd) - False - -Backwards compatibility for packages made via earlier versions of -setuptools is provided as well:: - - >>> cp("darwin-8.2.0-Power_Macintosh", reqd) - True - >>> cp("darwin-7.2.0-Power_Macintosh", reqd) - True - >>> cp("darwin-8.2.0-Power_Macintosh", "macosx-10.3-ppc") - False - - -Environment Markers -------------------- - - >>> from pkg_resources import invalid_marker as im, evaluate_marker as em - >>> import os - - >>> print(im("sys_platform")) - Expected marker operator, one of <=, <, !=, ==, >=, >, ~=, ===, in, not in - sys_platform - ^ - - >>> print(im("sys_platform==")) - Expected a marker variable or quoted string - sys_platform== - ^ - - >>> print(im("sys_platform=='win32'")) - False - - >>> print(im("sys=='x'")) - Expected a marker variable or quoted string - sys=='x' - ^ - - >>> print(im("(extra)")) - Expected marker operator, one of <=, <, !=, ==, >=, >, ~=, ===, in, not in - (extra) - ^ - - >>> print(im("(extra")) - Expected marker operator, one of <=, <, !=, ==, >=, >, ~=, ===, in, not in - (extra - ^ - - >>> print(im("os.open('foo')=='y'")) - Expected a marker variable or quoted string - os.open('foo')=='y' - ^ - - >>> print(im("'x'=='y' and os.open('foo')=='y'")) # no short-circuit! - Expected a marker variable or quoted string - 'x'=='y' and os.open('foo')=='y' - ^ - - >>> print(im("'x'=='x' or os.open('foo')=='y'")) # no short-circuit! - Expected a marker variable or quoted string - 'x'=='x' or os.open('foo')=='y' - ^ - - >>> print(im("r'x'=='x'")) - Expected a marker variable or quoted string - r'x'=='x' - ^ - - >>> print(im("'''x'''=='x'")) - Expected marker operator, one of <=, <, !=, ==, >=, >, ~=, ===, in, not in - '''x'''=='x' - ^ - - >>> print(im('"""x"""=="x"')) - Expected marker operator, one of <=, <, !=, ==, >=, >, ~=, ===, in, not in - """x"""=="x" - ^ - - >>> print(im(r"x\n=='x'")) - Expected a marker variable or quoted string - x\n=='x' - ^ - - >>> print(im("os.open=='y'")) - Expected a marker variable or quoted string - os.open=='y' - ^ - - >>> em("sys_platform=='win32'") == (sys.platform=='win32') - True - - >>> em("python_version >= '2.7'") - True - - >>> em("python_version > '2.6'") - True - - >>> im("implementation_name=='cpython'") - False - - >>> im("platform_python_implementation=='CPython'") - False - - >>> im("implementation_version=='3.5.1'") - False diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__init__.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index b40a69a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_find_distributions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_find_distributions.cpython-312.pyc deleted file mode 100644 index 410a8f1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_find_distributions.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_integration_zope_interface.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_integration_zope_interface.cpython-312.pyc deleted file mode 100644 index 8f754d9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_integration_zope_interface.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_markers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_markers.cpython-312.pyc deleted file mode 100644 index 6d9ab90..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_markers.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_pkg_resources.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_pkg_resources.cpython-312.pyc deleted file mode 100644 index f99665c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_pkg_resources.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_resources.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_resources.cpython-312.pyc deleted file mode 100644 index 0517709..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_resources.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_working_set.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_working_set.cpython-312.pyc deleted file mode 100644 index 08b40db..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/__pycache__/test_working_set.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/__pycache__/setup.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/__pycache__/setup.cpython-312.pyc deleted file mode 100644 index 029d54e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/__pycache__/setup.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/setup.cfg b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/setup.cfg deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/setup.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/setup.py deleted file mode 100644 index ce90806..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-source/setup.py +++ /dev/null @@ -1,7 +0,0 @@ -import setuptools - -setuptools.setup( - name="my-test-package", - version="1.0", - zip_safe=True, -) diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-zip/my-test-package.zip b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-zip/my-test-package.zip deleted file mode 100644 index 81f9a01..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package-zip/my-test-package.zip and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/PKG-INFO b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/PKG-INFO deleted file mode 100644 index 7328e3f..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/PKG-INFO +++ /dev/null @@ -1,10 +0,0 @@ -Metadata-Version: 1.0 -Name: my-test-package -Version: 1.0 -Summary: UNKNOWN -Home-page: UNKNOWN -Author: UNKNOWN -Author-email: UNKNOWN -License: UNKNOWN -Description: UNKNOWN -Platform: UNKNOWN diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/SOURCES.txt b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/SOURCES.txt deleted file mode 100644 index 3c4ee16..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/SOURCES.txt +++ /dev/null @@ -1,7 +0,0 @@ -setup.cfg -setup.py -my_test_package.egg-info/PKG-INFO -my_test_package.egg-info/SOURCES.txt -my_test_package.egg-info/dependency_links.txt -my_test_package.egg-info/top_level.txt -my_test_package.egg-info/zip-safe \ No newline at end of file diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/dependency_links.txt b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/dependency_links.txt deleted file mode 100644 index 8b13789..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/dependency_links.txt +++ /dev/null @@ -1 +0,0 @@ - diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/top_level.txt b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/top_level.txt deleted file mode 100644 index 8b13789..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/top_level.txt +++ /dev/null @@ -1 +0,0 @@ - diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/zip-safe b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/zip-safe deleted file mode 100644 index 8b13789..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/zip-safe +++ /dev/null @@ -1 +0,0 @@ - diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_zipped-egg/my_test_package-1.0-py3.7.egg b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_zipped-egg/my_test_package-1.0-py3.7.egg deleted file mode 100644 index 5115b89..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/data/my-test-package_zipped-egg/my_test_package-1.0-py3.7.egg and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_find_distributions.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_find_distributions.py deleted file mode 100644 index 301b36d..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_find_distributions.py +++ /dev/null @@ -1,56 +0,0 @@ -import shutil -from pathlib import Path - -import pytest - -import pkg_resources - -TESTS_DATA_DIR = Path(__file__).parent / 'data' - - -class TestFindDistributions: - @pytest.fixture - def target_dir(self, tmpdir): - target_dir = tmpdir.mkdir('target') - # place a .egg named directory in the target that is not an egg: - target_dir.mkdir('not.an.egg') - return target_dir - - def test_non_egg_dir_named_egg(self, target_dir): - dists = pkg_resources.find_distributions(str(target_dir)) - assert not list(dists) - - def test_standalone_egg_directory(self, target_dir): - shutil.copytree( - TESTS_DATA_DIR / 'my-test-package_unpacked-egg', - target_dir, - dirs_exist_ok=True, - ) - dists = pkg_resources.find_distributions(str(target_dir)) - assert [dist.project_name for dist in dists] == ['my-test-package'] - dists = pkg_resources.find_distributions(str(target_dir), only=True) - assert not list(dists) - - def test_zipped_egg(self, target_dir): - shutil.copytree( - TESTS_DATA_DIR / 'my-test-package_zipped-egg', - target_dir, - dirs_exist_ok=True, - ) - dists = pkg_resources.find_distributions(str(target_dir)) - assert [dist.project_name for dist in dists] == ['my-test-package'] - dists = pkg_resources.find_distributions(str(target_dir), only=True) - assert not list(dists) - - def test_zipped_sdist_one_level_removed(self, target_dir): - shutil.copytree( - TESTS_DATA_DIR / 'my-test-package-zip', target_dir, dirs_exist_ok=True - ) - dists = pkg_resources.find_distributions( - str(target_dir / "my-test-package.zip") - ) - assert [dist.project_name for dist in dists] == ['my-test-package'] - dists = pkg_resources.find_distributions( - str(target_dir / "my-test-package.zip"), only=True - ) - assert not list(dists) diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_integration_zope_interface.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_integration_zope_interface.py deleted file mode 100644 index 4e37c34..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_integration_zope_interface.py +++ /dev/null @@ -1,54 +0,0 @@ -import platform -from inspect import cleandoc - -import jaraco.path -import pytest - -pytestmark = pytest.mark.integration - - -# For the sake of simplicity this test uses fixtures defined in -# `setuptools.test.fixtures`, -# and it also exercise conditions considered deprecated... -# So if needed this test can be deleted. -@pytest.mark.skipif( - platform.system() != "Linux", - reason="only demonstrated to fail on Linux in #4399", -) -def test_interop_pkg_resources_iter_entry_points(tmp_path, venv): - """ - Importing pkg_resources.iter_entry_points on console_scripts - seems to cause trouble with zope-interface, when deprecates installation method - is used. See #4399. - """ - project = { - "pkg": { - "foo.py": cleandoc( - """ - from pkg_resources import iter_entry_points - - def bar(): - print("Print me if you can") - """ - ), - "setup.py": cleandoc( - """ - from setuptools import setup, find_packages - - setup( - install_requires=["zope-interface==6.4.post2"], - entry_points={ - "console_scripts": [ - "foo=foo:bar", - ], - }, - ) - """ - ), - } - } - jaraco.path.build(project, prefix=tmp_path) - cmd = ["pip", "install", "-e", ".", "--no-use-pep517"] - venv.run(cmd, cwd=tmp_path / "pkg") # Needs this version of pkg_resources installed - out = venv.run(["foo"]) - assert "Print me if you can" in out diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_markers.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_markers.py deleted file mode 100644 index 9306d5b..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_markers.py +++ /dev/null @@ -1,8 +0,0 @@ -from unittest import mock - -from pkg_resources import evaluate_marker - - -@mock.patch('platform.python_version', return_value='2.7.10') -def test_ordering(python_version_mock): - assert evaluate_marker("python_full_version > '2.7.3'") is True diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_pkg_resources.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_pkg_resources.py deleted file mode 100644 index cfc9b16..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_pkg_resources.py +++ /dev/null @@ -1,485 +0,0 @@ -from __future__ import annotations - -import builtins -import datetime -import inspect -import os -import plistlib -import stat -import subprocess -import sys -import tempfile -import zipfile -from unittest import mock - -import pytest - -import pkg_resources -from pkg_resources import DistInfoDistribution, Distribution, EggInfoDistribution - -import distutils.command.install_egg_info -import distutils.dist - - -class EggRemover(str): - def __call__(self): - if self in sys.path: - sys.path.remove(self) - if os.path.exists(self): - os.remove(self) - - -class TestZipProvider: - finalizers: list[EggRemover] = [] - - ref_time = datetime.datetime(2013, 5, 12, 13, 25, 0) - "A reference time for a file modification" - - @classmethod - def setup_class(cls): - "create a zip egg and add it to sys.path" - egg = tempfile.NamedTemporaryFile(suffix='.egg', delete=False) - zip_egg = zipfile.ZipFile(egg, 'w') - zip_info = zipfile.ZipInfo() - zip_info.filename = 'mod.py' - zip_info.date_time = cls.ref_time.timetuple() - zip_egg.writestr(zip_info, 'x = 3\n') - zip_info = zipfile.ZipInfo() - zip_info.filename = 'data.dat' - zip_info.date_time = cls.ref_time.timetuple() - zip_egg.writestr(zip_info, 'hello, world!') - zip_info = zipfile.ZipInfo() - zip_info.filename = 'subdir/mod2.py' - zip_info.date_time = cls.ref_time.timetuple() - zip_egg.writestr(zip_info, 'x = 6\n') - zip_info = zipfile.ZipInfo() - zip_info.filename = 'subdir/data2.dat' - zip_info.date_time = cls.ref_time.timetuple() - zip_egg.writestr(zip_info, 'goodbye, world!') - zip_egg.close() - egg.close() - - sys.path.append(egg.name) - subdir = os.path.join(egg.name, 'subdir') - sys.path.append(subdir) - cls.finalizers.append(EggRemover(subdir)) - cls.finalizers.append(EggRemover(egg.name)) - - @classmethod - def teardown_class(cls): - for finalizer in cls.finalizers: - finalizer() - - def test_resource_listdir(self): - import mod # pyright: ignore[reportMissingImports] # Temporary package for test - - zp = pkg_resources.ZipProvider(mod) - - expected_root = ['data.dat', 'mod.py', 'subdir'] - assert sorted(zp.resource_listdir('')) == expected_root - - expected_subdir = ['data2.dat', 'mod2.py'] - assert sorted(zp.resource_listdir('subdir')) == expected_subdir - assert sorted(zp.resource_listdir('subdir/')) == expected_subdir - - assert zp.resource_listdir('nonexistent') == [] - assert zp.resource_listdir('nonexistent/') == [] - - import mod2 # pyright: ignore[reportMissingImports] # Temporary package for test - - zp2 = pkg_resources.ZipProvider(mod2) - - assert sorted(zp2.resource_listdir('')) == expected_subdir - - assert zp2.resource_listdir('subdir') == [] - assert zp2.resource_listdir('subdir/') == [] - - def test_resource_filename_rewrites_on_change(self): - """ - If a previous call to get_resource_filename has saved the file, but - the file has been subsequently mutated with different file of the - same size and modification time, it should not be overwritten on a - subsequent call to get_resource_filename. - """ - import mod # pyright: ignore[reportMissingImports] # Temporary package for test - - manager = pkg_resources.ResourceManager() - zp = pkg_resources.ZipProvider(mod) - filename = zp.get_resource_filename(manager, 'data.dat') - actual = datetime.datetime.fromtimestamp(os.stat(filename).st_mtime) - assert actual == self.ref_time - f = open(filename, 'w', encoding="utf-8") - f.write('hello, world?') - f.close() - ts = self.ref_time.timestamp() - os.utime(filename, (ts, ts)) - filename = zp.get_resource_filename(manager, 'data.dat') - with open(filename, encoding="utf-8") as f: - assert f.read() == 'hello, world!' - manager.cleanup_resources() - - -class TestResourceManager: - def test_get_cache_path(self): - mgr = pkg_resources.ResourceManager() - path = mgr.get_cache_path('foo') - type_ = str(type(path)) - message = "Unexpected type from get_cache_path: " + type_ - assert isinstance(path, str), message - - def test_get_cache_path_race(self, tmpdir): - # Patch to os.path.isdir to create a race condition - def patched_isdir(dirname, unpatched_isdir=pkg_resources.isdir): - patched_isdir.dirnames.append(dirname) - - was_dir = unpatched_isdir(dirname) - if not was_dir: - os.makedirs(dirname) - return was_dir - - patched_isdir.dirnames = [] - - # Get a cache path with a "race condition" - mgr = pkg_resources.ResourceManager() - mgr.set_extraction_path(str(tmpdir)) - - archive_name = os.sep.join(('foo', 'bar', 'baz')) - with mock.patch.object(pkg_resources, 'isdir', new=patched_isdir): - mgr.get_cache_path(archive_name) - - # Because this test relies on the implementation details of this - # function, these assertions are a sentinel to ensure that the - # test suite will not fail silently if the implementation changes. - called_dirnames = patched_isdir.dirnames - assert len(called_dirnames) == 2 - assert called_dirnames[0].split(os.sep)[-2:] == ['foo', 'bar'] - assert called_dirnames[1].split(os.sep)[-1:] == ['foo'] - - """ - Tests to ensure that pkg_resources runs independently from setuptools. - """ - - def test_setuptools_not_imported(self): - """ - In a separate Python environment, import pkg_resources and assert - that action doesn't cause setuptools to be imported. - """ - lines = ( - 'import pkg_resources', - 'import sys', - ('assert "setuptools" not in sys.modules, "setuptools was imported"'), - ) - cmd = [sys.executable, '-c', '; '.join(lines)] - subprocess.check_call(cmd) - - -def make_test_distribution(metadata_path, metadata): - """ - Make a test Distribution object, and return it. - - :param metadata_path: the path to the metadata file that should be - created. This should be inside a distribution directory that should - also be created. For example, an argument value might end with - ".dist-info/METADATA". - :param metadata: the desired contents of the metadata file, as bytes. - """ - dist_dir = os.path.dirname(metadata_path) - os.mkdir(dist_dir) - with open(metadata_path, 'wb') as f: - f.write(metadata) - dists = list(pkg_resources.distributions_from_metadata(dist_dir)) - (dist,) = dists - - return dist - - -def test_get_metadata__bad_utf8(tmpdir): - """ - Test a metadata file with bytes that can't be decoded as utf-8. - """ - filename = 'METADATA' - # Convert the tmpdir LocalPath object to a string before joining. - metadata_path = os.path.join(str(tmpdir), 'foo.dist-info', filename) - # Encode a non-ascii string with the wrong encoding (not utf-8). - metadata = 'née'.encode('iso-8859-1') - dist = make_test_distribution(metadata_path, metadata=metadata) - - with pytest.raises(UnicodeDecodeError) as excinfo: - dist.get_metadata(filename) - - exc = excinfo.value - actual = str(exc) - expected = ( - # The error message starts with "'utf-8' codec ..." However, the - # spelling of "utf-8" can vary (e.g. "utf8") so we don't include it - "codec can't decode byte 0xe9 in position 1: " - 'invalid continuation byte in METADATA file at path: ' - ) - assert expected in actual, f'actual: {actual}' - assert actual.endswith(metadata_path), f'actual: {actual}' - - -def make_distribution_no_version(tmpdir, basename): - """ - Create a distribution directory with no file containing the version. - """ - dist_dir = tmpdir / basename - dist_dir.ensure_dir() - # Make the directory non-empty so distributions_from_metadata() - # will detect it and yield it. - dist_dir.join('temp.txt').ensure() - - dists = list(pkg_resources.distributions_from_metadata(dist_dir)) - assert len(dists) == 1 - (dist,) = dists - - return dist, dist_dir - - -@pytest.mark.parametrize( - ("suffix", "expected_filename", "expected_dist_type"), - [ - ('egg-info', 'PKG-INFO', EggInfoDistribution), - ('dist-info', 'METADATA', DistInfoDistribution), - ], -) -@pytest.mark.xfail( - sys.version_info[:2] == (3, 12) and sys.version_info.releaselevel != 'final', - reason="https://github.com/python/cpython/issues/103632", -) -def test_distribution_version_missing( - tmpdir, suffix, expected_filename, expected_dist_type -): - """ - Test Distribution.version when the "Version" header is missing. - """ - basename = f'foo.{suffix}' - dist, dist_dir = make_distribution_no_version(tmpdir, basename) - - expected_text = ( - f"Missing 'Version:' header and/or {expected_filename} file at path: " - ) - metadata_path = os.path.join(dist_dir, expected_filename) - - # Now check the exception raised when the "version" attribute is accessed. - with pytest.raises(ValueError) as excinfo: - dist.version - - err = str(excinfo.value) - # Include a string expression after the assert so the full strings - # will be visible for inspection on failure. - assert expected_text in err, str((expected_text, err)) - - # Also check the args passed to the ValueError. - msg, dist = excinfo.value.args - assert expected_text in msg - # Check that the message portion contains the path. - assert metadata_path in msg, str((metadata_path, msg)) - assert type(dist) is expected_dist_type - - -@pytest.mark.xfail( - sys.version_info[:2] == (3, 12) and sys.version_info.releaselevel != 'final', - reason="https://github.com/python/cpython/issues/103632", -) -def test_distribution_version_missing_undetected_path(): - """ - Test Distribution.version when the "Version" header is missing and - the path can't be detected. - """ - # Create a Distribution object with no metadata argument, which results - # in an empty metadata provider. - dist = Distribution('/foo') - with pytest.raises(ValueError) as excinfo: - dist.version - - msg, dist = excinfo.value.args - expected = ( - "Missing 'Version:' header and/or PKG-INFO file at path: [could not detect]" - ) - assert msg == expected - - -@pytest.mark.parametrize('only', [False, True]) -def test_dist_info_is_not_dir(tmp_path, only): - """Test path containing a file with dist-info extension.""" - dist_info = tmp_path / 'foobar.dist-info' - dist_info.touch() - assert not pkg_resources.dist_factory(str(tmp_path), str(dist_info), only) - - -def test_macos_vers_fallback(monkeypatch, tmp_path): - """Regression test for pkg_resources._macos_vers""" - orig_open = builtins.open - - # Pretend we need to use the plist file - monkeypatch.setattr('platform.mac_ver', mock.Mock(return_value=('', (), ''))) - - # Create fake content for the fake plist file - with open(tmp_path / 'fake.plist', 'wb') as fake_file: - plistlib.dump({"ProductVersion": "11.4"}, fake_file) - - # Pretend the fake file exists - monkeypatch.setattr('os.path.exists', mock.Mock(return_value=True)) - - def fake_open(file, *args, **kwargs): - return orig_open(tmp_path / 'fake.plist', *args, **kwargs) - - # Ensure that the _macos_vers works correctly - with mock.patch('builtins.open', mock.Mock(side_effect=fake_open)) as m: - pkg_resources._macos_vers.cache_clear() - assert pkg_resources._macos_vers() == ["11", "4"] - pkg_resources._macos_vers.cache_clear() - - m.assert_called() - - -class TestDeepVersionLookupDistutils: - @pytest.fixture - def env(self, tmpdir): - """ - Create a package environment, similar to a virtualenv, - in which packages are installed. - """ - - class Environment(str): - pass - - env = Environment(tmpdir) - tmpdir.chmod(stat.S_IRWXU) - subs = 'home', 'lib', 'scripts', 'data', 'egg-base' - env.paths = dict((dirname, str(tmpdir / dirname)) for dirname in subs) - list(map(os.mkdir, env.paths.values())) - return env - - def create_foo_pkg(self, env, version): - """ - Create a foo package installed (distutils-style) to env.paths['lib'] - as version. - """ - ld = "This package has unicode metadata! ❄" - attrs = dict(name='foo', version=version, long_description=ld) - dist = distutils.dist.Distribution(attrs) - iei_cmd = distutils.command.install_egg_info.install_egg_info(dist) - iei_cmd.initialize_options() - iei_cmd.install_dir = env.paths['lib'] - iei_cmd.finalize_options() - iei_cmd.run() - - def test_version_resolved_from_egg_info(self, env): - version = '1.11.0.dev0+2329eae' - self.create_foo_pkg(env, version) - - # this requirement parsing will raise a VersionConflict unless the - # .egg-info file is parsed (see #419 on BitBucket) - req = pkg_resources.Requirement.parse('foo>=1.9') - dist = pkg_resources.WorkingSet([env.paths['lib']]).find(req) - assert dist.version == version - - @pytest.mark.parametrize( - ("unnormalized", "normalized"), - [ - ('foo', 'foo'), - ('foo/', 'foo'), - ('foo/bar', 'foo/bar'), - ('foo/bar/', 'foo/bar'), - ], - ) - def test_normalize_path_trailing_sep(self, unnormalized, normalized): - """Ensure the trailing slash is cleaned for path comparison. - - See pypa/setuptools#1519. - """ - result_from_unnormalized = pkg_resources.normalize_path(unnormalized) - result_from_normalized = pkg_resources.normalize_path(normalized) - assert result_from_unnormalized == result_from_normalized - - @pytest.mark.skipif( - os.path.normcase('A') != os.path.normcase('a'), - reason='Testing case-insensitive filesystems.', - ) - @pytest.mark.parametrize( - ("unnormalized", "normalized"), - [ - ('MiXeD/CasE', 'mixed/case'), - ], - ) - def test_normalize_path_normcase(self, unnormalized, normalized): - """Ensure mixed case is normalized on case-insensitive filesystems.""" - result_from_unnormalized = pkg_resources.normalize_path(unnormalized) - result_from_normalized = pkg_resources.normalize_path(normalized) - assert result_from_unnormalized == result_from_normalized - - @pytest.mark.skipif( - os.path.sep != '\\', - reason='Testing systems using backslashes as path separators.', - ) - @pytest.mark.parametrize( - ("unnormalized", "expected"), - [ - ('forward/slash', 'forward\\slash'), - ('forward/slash/', 'forward\\slash'), - ('backward\\slash\\', 'backward\\slash'), - ], - ) - def test_normalize_path_backslash_sep(self, unnormalized, expected): - """Ensure path seps are cleaned on backslash path sep systems.""" - result = pkg_resources.normalize_path(unnormalized) - assert result.endswith(expected) - - -class TestWorkdirRequire: - def fake_site_packages(self, tmp_path, monkeypatch, dist_files): - site_packages = tmp_path / "site-packages" - site_packages.mkdir() - for file, content in self.FILES.items(): - path = site_packages / file - path.parent.mkdir(exist_ok=True, parents=True) - path.write_text(inspect.cleandoc(content), encoding="utf-8") - - monkeypatch.setattr(sys, "path", [site_packages]) - return os.fspath(site_packages) - - FILES = { - "pkg1_mod-1.2.3.dist-info/METADATA": """ - Metadata-Version: 2.4 - Name: pkg1.mod - Version: 1.2.3 - """, - "pkg2.mod-0.42.dist-info/METADATA": """ - Metadata-Version: 2.1 - Name: pkg2.mod - Version: 0.42 - """, - "pkg3_mod.egg-info/PKG-INFO": """ - Name: pkg3.mod - Version: 1.2.3.4 - """, - "pkg4.mod.egg-info/PKG-INFO": """ - Name: pkg4.mod - Version: 0.42.1 - """, - } - - @pytest.mark.parametrize( - ("version", "requirement"), - [ - ("1.2.3", "pkg1.mod>=1"), - ("0.42", "pkg2.mod>=0.4"), - ("1.2.3.4", "pkg3.mod<=2"), - ("0.42.1", "pkg4.mod>0.2,<1"), - ], - ) - def test_require_non_normalised_name( - self, tmp_path, monkeypatch, version, requirement - ): - # https://github.com/pypa/setuptools/issues/4853 - site_packages = self.fake_site_packages(tmp_path, monkeypatch, self.FILES) - ws = pkg_resources.WorkingSet([site_packages]) - - for req in [requirement, requirement.replace(".", "-")]: - [dist] = ws.require(req) - assert dist.version == version - assert os.path.samefile( - os.path.commonpath([dist.location, site_packages]), site_packages - ) diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_resources.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_resources.py deleted file mode 100644 index 70436c0..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_resources.py +++ /dev/null @@ -1,869 +0,0 @@ -import itertools -import os -import platform -import string -import sys - -import pytest -from packaging.specifiers import SpecifierSet - -import pkg_resources -from pkg_resources import ( - Distribution, - EntryPoint, - Requirement, - VersionConflict, - WorkingSet, - parse_requirements, - parse_version, - safe_name, - safe_version, -) - - -# from Python 3.6 docs. Available from itertools on Python 3.10 -def pairwise(iterable): - "s -> (s0,s1), (s1,s2), (s2, s3), ..." - a, b = itertools.tee(iterable) - next(b, None) - return zip(a, b) - - -class Metadata(pkg_resources.EmptyProvider): - """Mock object to return metadata as if from an on-disk distribution""" - - def __init__(self, *pairs) -> None: - self.metadata = dict(pairs) - - def has_metadata(self, name) -> bool: - return name in self.metadata - - def get_metadata(self, name): - return self.metadata[name] - - def get_metadata_lines(self, name): - return pkg_resources.yield_lines(self.get_metadata(name)) - - -dist_from_fn = pkg_resources.Distribution.from_filename - - -class TestDistro: - def testCollection(self): - # empty path should produce no distributions - ad = pkg_resources.Environment([], platform=None, python=None) - assert list(ad) == [] - assert ad['FooPkg'] == [] - ad.add(dist_from_fn("FooPkg-1.3_1.egg")) - ad.add(dist_from_fn("FooPkg-1.4-py2.4-win32.egg")) - ad.add(dist_from_fn("FooPkg-1.2-py2.4.egg")) - - # Name is in there now - assert ad['FooPkg'] - # But only 1 package - assert list(ad) == ['foopkg'] - - # Distributions sort by version - expected = ['1.4', '1.3-1', '1.2'] - assert [dist.version for dist in ad['FooPkg']] == expected - - # Removing a distribution leaves sequence alone - ad.remove(ad['FooPkg'][1]) - assert [dist.version for dist in ad['FooPkg']] == ['1.4', '1.2'] - - # And inserting adds them in order - ad.add(dist_from_fn("FooPkg-1.9.egg")) - assert [dist.version for dist in ad['FooPkg']] == ['1.9', '1.4', '1.2'] - - ws = WorkingSet([]) - foo12 = dist_from_fn("FooPkg-1.2-py2.4.egg") - foo14 = dist_from_fn("FooPkg-1.4-py2.4-win32.egg") - (req,) = parse_requirements("FooPkg>=1.3") - - # Nominal case: no distros on path, should yield all applicable - assert ad.best_match(req, ws).version == '1.9' - # If a matching distro is already installed, should return only that - ws.add(foo14) - assert ad.best_match(req, ws).version == '1.4' - - # If the first matching distro is unsuitable, it's a version conflict - ws = WorkingSet([]) - ws.add(foo12) - ws.add(foo14) - with pytest.raises(VersionConflict): - ad.best_match(req, ws) - - # If more than one match on the path, the first one takes precedence - ws = WorkingSet([]) - ws.add(foo14) - ws.add(foo12) - ws.add(foo14) - assert ad.best_match(req, ws).version == '1.4' - - def checkFooPkg(self, d): - assert d.project_name == "FooPkg" - assert d.key == "foopkg" - assert d.version == "1.3.post1" - assert d.py_version == "2.4" - assert d.platform == "win32" - assert d.parsed_version == parse_version("1.3-1") - - def testDistroBasics(self): - d = Distribution( - "/some/path", - project_name="FooPkg", - version="1.3-1", - py_version="2.4", - platform="win32", - ) - self.checkFooPkg(d) - - d = Distribution("/some/path") - assert d.py_version == f'{sys.version_info.major}.{sys.version_info.minor}' - assert d.platform is None - - def testDistroParse(self): - d = dist_from_fn("FooPkg-1.3.post1-py2.4-win32.egg") - self.checkFooPkg(d) - d = dist_from_fn("FooPkg-1.3.post1-py2.4-win32.egg-info") - self.checkFooPkg(d) - - def testDistroMetadata(self): - d = Distribution( - "/some/path", - project_name="FooPkg", - py_version="2.4", - platform="win32", - metadata=Metadata(('PKG-INFO', "Metadata-Version: 1.0\nVersion: 1.3-1\n")), - ) - self.checkFooPkg(d) - - def distRequires(self, txt): - return Distribution("/foo", metadata=Metadata(('depends.txt', txt))) - - def checkRequires(self, dist, txt, extras=()): - assert list(dist.requires(extras)) == list(parse_requirements(txt)) - - def testDistroDependsSimple(self): - for v in "Twisted>=1.5", "Twisted>=1.5\nZConfig>=2.0": - self.checkRequires(self.distRequires(v), v) - - needs_object_dir = pytest.mark.skipif( - not hasattr(object, '__dir__'), - reason='object.__dir__ necessary for self.__dir__ implementation', - ) - - def test_distribution_dir(self): - d = pkg_resources.Distribution() - dir(d) - - @needs_object_dir - def test_distribution_dir_includes_provider_dir(self): - d = pkg_resources.Distribution() - before = d.__dir__() - assert 'test_attr' not in before - d._provider.test_attr = None - after = d.__dir__() - assert len(after) == len(before) + 1 - assert 'test_attr' in after - - @needs_object_dir - def test_distribution_dir_ignores_provider_dir_leading_underscore(self): - d = pkg_resources.Distribution() - before = d.__dir__() - assert '_test_attr' not in before - d._provider._test_attr = None - after = d.__dir__() - assert len(after) == len(before) - assert '_test_attr' not in after - - def testResolve(self): - ad = pkg_resources.Environment([]) - ws = WorkingSet([]) - # Resolving no requirements -> nothing to install - assert list(ws.resolve([], ad)) == [] - # Request something not in the collection -> DistributionNotFound - with pytest.raises(pkg_resources.DistributionNotFound): - ws.resolve(parse_requirements("Foo"), ad) - - Foo = Distribution.from_filename( - "/foo_dir/Foo-1.2.egg", - metadata=Metadata(('depends.txt', "[bar]\nBaz>=2.0")), - ) - ad.add(Foo) - ad.add(Distribution.from_filename("Foo-0.9.egg")) - - # Request thing(s) that are available -> list to activate - for i in range(3): - targets = list(ws.resolve(parse_requirements("Foo"), ad)) - assert targets == [Foo] - list(map(ws.add, targets)) - with pytest.raises(VersionConflict): - ws.resolve(parse_requirements("Foo==0.9"), ad) - ws = WorkingSet([]) # reset - - # Request an extra that causes an unresolved dependency for "Baz" - with pytest.raises(pkg_resources.DistributionNotFound): - ws.resolve(parse_requirements("Foo[bar]"), ad) - Baz = Distribution.from_filename( - "/foo_dir/Baz-2.1.egg", metadata=Metadata(('depends.txt', "Foo")) - ) - ad.add(Baz) - - # Activation list now includes resolved dependency - assert list(ws.resolve(parse_requirements("Foo[bar]"), ad)) == [Foo, Baz] - # Requests for conflicting versions produce VersionConflict - with pytest.raises(VersionConflict) as vc: - ws.resolve(parse_requirements("Foo==1.2\nFoo!=1.2"), ad) - - msg = 'Foo 0.9 is installed but Foo==1.2 is required' - assert vc.value.report() == msg - - def test_environment_marker_evaluation_negative(self): - """Environment markers are evaluated at resolution time.""" - ad = pkg_resources.Environment([]) - ws = WorkingSet([]) - res = ws.resolve(parse_requirements("Foo;python_version<'2'"), ad) - assert list(res) == [] - - def test_environment_marker_evaluation_positive(self): - ad = pkg_resources.Environment([]) - ws = WorkingSet([]) - Foo = Distribution.from_filename("/foo_dir/Foo-1.2.dist-info") - ad.add(Foo) - res = ws.resolve(parse_requirements("Foo;python_version>='2'"), ad) - assert list(res) == [Foo] - - def test_environment_marker_evaluation_called(self): - """ - If one package foo requires bar without any extras, - markers should pass for bar without extras. - """ - (parent_req,) = parse_requirements("foo") - (req,) = parse_requirements("bar;python_version>='2'") - req_extras = pkg_resources._ReqExtras({req: parent_req.extras}) - assert req_extras.markers_pass(req) - - (parent_req,) = parse_requirements("foo[]") - (req,) = parse_requirements("bar;python_version>='2'") - req_extras = pkg_resources._ReqExtras({req: parent_req.extras}) - assert req_extras.markers_pass(req) - - def test_marker_evaluation_with_extras(self): - """Extras are also evaluated as markers at resolution time.""" - ad = pkg_resources.Environment([]) - ws = WorkingSet([]) - Foo = Distribution.from_filename( - "/foo_dir/Foo-1.2.dist-info", - metadata=Metadata(( - "METADATA", - "Provides-Extra: baz\nRequires-Dist: quux; extra=='baz'", - )), - ) - ad.add(Foo) - assert list(ws.resolve(parse_requirements("Foo"), ad)) == [Foo] - quux = Distribution.from_filename("/foo_dir/quux-1.0.dist-info") - ad.add(quux) - res = list(ws.resolve(parse_requirements("Foo[baz]"), ad)) - assert res == [Foo, quux] - - def test_marker_evaluation_with_extras_normlized(self): - """Extras are also evaluated as markers at resolution time.""" - ad = pkg_resources.Environment([]) - ws = WorkingSet([]) - Foo = Distribution.from_filename( - "/foo_dir/Foo-1.2.dist-info", - metadata=Metadata(( - "METADATA", - "Provides-Extra: baz-lightyear\n" - "Requires-Dist: quux; extra=='baz-lightyear'", - )), - ) - ad.add(Foo) - assert list(ws.resolve(parse_requirements("Foo"), ad)) == [Foo] - quux = Distribution.from_filename("/foo_dir/quux-1.0.dist-info") - ad.add(quux) - res = list(ws.resolve(parse_requirements("Foo[baz-lightyear]"), ad)) - assert res == [Foo, quux] - - def test_marker_evaluation_with_multiple_extras(self): - ad = pkg_resources.Environment([]) - ws = WorkingSet([]) - Foo = Distribution.from_filename( - "/foo_dir/Foo-1.2.dist-info", - metadata=Metadata(( - "METADATA", - "Provides-Extra: baz\n" - "Requires-Dist: quux; extra=='baz'\n" - "Provides-Extra: bar\n" - "Requires-Dist: fred; extra=='bar'\n", - )), - ) - ad.add(Foo) - quux = Distribution.from_filename("/foo_dir/quux-1.0.dist-info") - ad.add(quux) - fred = Distribution.from_filename("/foo_dir/fred-0.1.dist-info") - ad.add(fred) - res = list(ws.resolve(parse_requirements("Foo[baz,bar]"), ad)) - assert sorted(res) == [fred, quux, Foo] - - def test_marker_evaluation_with_extras_loop(self): - ad = pkg_resources.Environment([]) - ws = WorkingSet([]) - a = Distribution.from_filename( - "/foo_dir/a-0.2.dist-info", - metadata=Metadata(("METADATA", "Requires-Dist: c[a]")), - ) - b = Distribution.from_filename( - "/foo_dir/b-0.3.dist-info", - metadata=Metadata(("METADATA", "Requires-Dist: c[b]")), - ) - c = Distribution.from_filename( - "/foo_dir/c-1.0.dist-info", - metadata=Metadata(( - "METADATA", - "Provides-Extra: a\n" - "Requires-Dist: b;extra=='a'\n" - "Provides-Extra: b\n" - "Requires-Dist: foo;extra=='b'", - )), - ) - foo = Distribution.from_filename("/foo_dir/foo-0.1.dist-info") - for dist in (a, b, c, foo): - ad.add(dist) - res = list(ws.resolve(parse_requirements("a"), ad)) - assert res == [a, c, b, foo] - - @pytest.mark.xfail( - sys.version_info[:2] == (3, 12) and sys.version_info.releaselevel != 'final', - reason="https://github.com/python/cpython/issues/103632", - ) - def testDistroDependsOptions(self): - d = self.distRequires( - """ - Twisted>=1.5 - [docgen] - ZConfig>=2.0 - docutils>=0.3 - [fastcgi] - fcgiapp>=0.1""" - ) - self.checkRequires(d, "Twisted>=1.5") - self.checkRequires( - d, "Twisted>=1.5 ZConfig>=2.0 docutils>=0.3".split(), ["docgen"] - ) - self.checkRequires(d, "Twisted>=1.5 fcgiapp>=0.1".split(), ["fastcgi"]) - self.checkRequires( - d, - "Twisted>=1.5 ZConfig>=2.0 docutils>=0.3 fcgiapp>=0.1".split(), - ["docgen", "fastcgi"], - ) - self.checkRequires( - d, - "Twisted>=1.5 fcgiapp>=0.1 ZConfig>=2.0 docutils>=0.3".split(), - ["fastcgi", "docgen"], - ) - with pytest.raises(pkg_resources.UnknownExtra): - d.requires(["foo"]) - - -class TestWorkingSet: - def test_find_conflicting(self): - ws = WorkingSet([]) - Foo = Distribution.from_filename("/foo_dir/Foo-1.2.egg") - ws.add(Foo) - - # create a requirement that conflicts with Foo 1.2 - req = next(parse_requirements("Foo<1.2")) - - with pytest.raises(VersionConflict) as vc: - ws.find(req) - - msg = 'Foo 1.2 is installed but Foo<1.2 is required' - assert vc.value.report() == msg - - def test_resolve_conflicts_with_prior(self): - """ - A ContextualVersionConflict should be raised when a requirement - conflicts with a prior requirement for a different package. - """ - # Create installation where Foo depends on Baz 1.0 and Bar depends on - # Baz 2.0. - ws = WorkingSet([]) - md = Metadata(('depends.txt', "Baz==1.0")) - Foo = Distribution.from_filename("/foo_dir/Foo-1.0.egg", metadata=md) - ws.add(Foo) - md = Metadata(('depends.txt', "Baz==2.0")) - Bar = Distribution.from_filename("/foo_dir/Bar-1.0.egg", metadata=md) - ws.add(Bar) - Baz = Distribution.from_filename("/foo_dir/Baz-1.0.egg") - ws.add(Baz) - Baz = Distribution.from_filename("/foo_dir/Baz-2.0.egg") - ws.add(Baz) - - with pytest.raises(VersionConflict) as vc: - ws.resolve(parse_requirements("Foo\nBar\n")) - - msg = "Baz 1.0 is installed but Baz==2.0 is required by " - msg += repr(set(['Bar'])) - assert vc.value.report() == msg - - -class TestEntryPoints: - def assertfields(self, ep): - assert ep.name == "foo" - assert ep.module_name == "pkg_resources.tests.test_resources" - assert ep.attrs == ("TestEntryPoints",) - assert ep.extras == ("x",) - assert ep.load() is TestEntryPoints - expect = "foo = pkg_resources.tests.test_resources:TestEntryPoints [x]" - assert str(ep) == expect - - def setup_method(self, method): - self.dist = Distribution.from_filename( - "FooPkg-1.2-py2.4.egg", metadata=Metadata(('requires.txt', '[x]')) - ) - - def testBasics(self): - ep = EntryPoint( - "foo", - "pkg_resources.tests.test_resources", - ["TestEntryPoints"], - ["x"], - self.dist, - ) - self.assertfields(ep) - - def testParse(self): - s = "foo = pkg_resources.tests.test_resources:TestEntryPoints [x]" - ep = EntryPoint.parse(s, self.dist) - self.assertfields(ep) - - ep = EntryPoint.parse("bar baz= spammity[PING]") - assert ep.name == "bar baz" - assert ep.module_name == "spammity" - assert ep.attrs == () - assert ep.extras == ("ping",) - - ep = EntryPoint.parse(" fizzly = wocka:foo") - assert ep.name == "fizzly" - assert ep.module_name == "wocka" - assert ep.attrs == ("foo",) - assert ep.extras == () - - # plus in the name - spec = "html+mako = mako.ext.pygmentplugin:MakoHtmlLexer" - ep = EntryPoint.parse(spec) - assert ep.name == 'html+mako' - - reject_specs = "foo", "x=a:b:c", "q=x/na", "fez=pish:tush-z", "x=f[a]>2" - - @pytest.mark.parametrize("reject_spec", reject_specs) - def test_reject_spec(self, reject_spec): - with pytest.raises(ValueError): - EntryPoint.parse(reject_spec) - - def test_printable_name(self): - """ - Allow any printable character in the name. - """ - # Create a name with all printable characters; strip the whitespace. - name = string.printable.strip() - spec = "{name} = module:attr".format(**locals()) - ep = EntryPoint.parse(spec) - assert ep.name == name - - def checkSubMap(self, m): - assert len(m) == len(self.submap_expect) - for key, ep in self.submap_expect.items(): - assert m.get(key).name == ep.name - assert m.get(key).module_name == ep.module_name - assert sorted(m.get(key).attrs) == sorted(ep.attrs) - assert sorted(m.get(key).extras) == sorted(ep.extras) - - submap_expect = dict( - feature1=EntryPoint('feature1', 'somemodule', ['somefunction']), - feature2=EntryPoint( - 'feature2', 'another.module', ['SomeClass'], ['extra1', 'extra2'] - ), - feature3=EntryPoint('feature3', 'this.module', extras=['something']), - ) - submap_str = """ - # define features for blah blah - feature1 = somemodule:somefunction - feature2 = another.module:SomeClass [extra1,extra2] - feature3 = this.module [something] - """ - - def testParseList(self): - self.checkSubMap(EntryPoint.parse_group("xyz", self.submap_str)) - with pytest.raises(ValueError): - EntryPoint.parse_group("x a", "foo=bar") - with pytest.raises(ValueError): - EntryPoint.parse_group("x", ["foo=baz", "foo=bar"]) - - def testParseMap(self): - m = EntryPoint.parse_map({'xyz': self.submap_str}) - self.checkSubMap(m['xyz']) - assert list(m.keys()) == ['xyz'] - m = EntryPoint.parse_map("[xyz]\n" + self.submap_str) - self.checkSubMap(m['xyz']) - assert list(m.keys()) == ['xyz'] - with pytest.raises(ValueError): - EntryPoint.parse_map(["[xyz]", "[xyz]"]) - with pytest.raises(ValueError): - EntryPoint.parse_map(self.submap_str) - - def testDeprecationWarnings(self): - ep = EntryPoint( - "foo", "pkg_resources.tests.test_resources", ["TestEntryPoints"], ["x"] - ) - with pytest.warns(pkg_resources.PkgResourcesDeprecationWarning): - ep.load(require=False) - - -class TestRequirements: - def testBasics(self): - r = Requirement.parse("Twisted>=1.2") - assert str(r) == "Twisted>=1.2" - assert repr(r) == "Requirement.parse('Twisted>=1.2')" - assert r == Requirement("Twisted>=1.2") - assert r == Requirement("twisTed>=1.2") - assert r != Requirement("Twisted>=2.0") - assert r != Requirement("Zope>=1.2") - assert r != Requirement("Zope>=3.0") - assert r != Requirement("Twisted[extras]>=1.2") - - def testOrdering(self): - r1 = Requirement("Twisted==1.2c1,>=1.2") - r2 = Requirement("Twisted>=1.2,==1.2c1") - assert r1 == r2 - assert str(r1) == str(r2) - assert str(r2) == "Twisted==1.2c1,>=1.2" - assert Requirement("Twisted") != Requirement( - "Twisted @ https://localhost/twisted.zip" - ) - - def testBasicContains(self): - r = Requirement("Twisted>=1.2") - foo_dist = Distribution.from_filename("FooPkg-1.3_1.egg") - twist11 = Distribution.from_filename("Twisted-1.1.egg") - twist12 = Distribution.from_filename("Twisted-1.2.egg") - assert parse_version('1.2') in r - assert parse_version('1.1') not in r - assert '1.2' in r - assert '1.1' not in r - assert foo_dist not in r - assert twist11 not in r - assert twist12 in r - - def testOptionsAndHashing(self): - r1 = Requirement.parse("Twisted[foo,bar]>=1.2") - r2 = Requirement.parse("Twisted[bar,FOO]>=1.2") - assert r1 == r2 - assert set(r1.extras) == set(("foo", "bar")) - assert set(r2.extras) == set(("foo", "bar")) - assert hash(r1) == hash(r2) - assert hash(r1) == hash(( - "twisted", - None, - SpecifierSet(">=1.2"), - frozenset(["foo", "bar"]), - None, - )) - assert hash( - Requirement.parse("Twisted @ https://localhost/twisted.zip") - ) == hash(( - "twisted", - "https://localhost/twisted.zip", - SpecifierSet(), - frozenset(), - None, - )) - - def testVersionEquality(self): - r1 = Requirement.parse("foo==0.3a2") - r2 = Requirement.parse("foo!=0.3a4") - d = Distribution.from_filename - - assert d("foo-0.3a4.egg") not in r1 - assert d("foo-0.3a1.egg") not in r1 - assert d("foo-0.3a4.egg") not in r2 - - assert d("foo-0.3a2.egg") in r1 - assert d("foo-0.3a2.egg") in r2 - assert d("foo-0.3a3.egg") in r2 - assert d("foo-0.3a5.egg") in r2 - - def testSetuptoolsProjectName(self): - """ - The setuptools project should implement the setuptools package. - """ - - assert Requirement.parse('setuptools').project_name == 'setuptools' - # setuptools 0.7 and higher means setuptools. - assert Requirement.parse('setuptools == 0.7').project_name == 'setuptools' - assert Requirement.parse('setuptools == 0.7a1').project_name == 'setuptools' - assert Requirement.parse('setuptools >= 0.7').project_name == 'setuptools' - - -class TestParsing: - def testEmptyParse(self): - assert list(parse_requirements('')) == [] - - def testYielding(self): - for inp, out in [ - ([], []), - ('x', ['x']), - ([[]], []), - (' x\n y', ['x', 'y']), - (['x\n\n', 'y'], ['x', 'y']), - ]: - assert list(pkg_resources.yield_lines(inp)) == out - - def testSplitting(self): - sample = """ - x - [Y] - z - - a - [b ] - # foo - c - [ d] - [q] - v - """ - assert list(pkg_resources.split_sections(sample)) == [ - (None, ["x"]), - ("Y", ["z", "a"]), - ("b", ["c"]), - ("d", []), - ("q", ["v"]), - ] - with pytest.raises(ValueError): - list(pkg_resources.split_sections("[foo")) - - def testSafeName(self): - assert safe_name("adns-python") == "adns-python" - assert safe_name("WSGI Utils") == "WSGI-Utils" - assert safe_name("WSGI Utils") == "WSGI-Utils" - assert safe_name("Money$$$Maker") == "Money-Maker" - assert safe_name("peak.web") != "peak-web" - - def testSafeVersion(self): - assert safe_version("1.2-1") == "1.2.post1" - assert safe_version("1.2 alpha") == "1.2.alpha" - assert safe_version("2.3.4 20050521") == "2.3.4.20050521" - assert safe_version("Money$$$Maker") == "Money-Maker" - assert safe_version("peak.web") == "peak.web" - - def testSimpleRequirements(self): - assert list(parse_requirements('Twis-Ted>=1.2-1')) == [ - Requirement('Twis-Ted>=1.2-1') - ] - assert list(parse_requirements('Twisted >=1.2, \\ # more\n<2.0')) == [ - Requirement('Twisted>=1.2,<2.0') - ] - assert Requirement.parse("FooBar==1.99a3") == Requirement("FooBar==1.99a3") - with pytest.raises(ValueError): - Requirement.parse(">=2.3") - with pytest.raises(ValueError): - Requirement.parse("x\\") - with pytest.raises(ValueError): - Requirement.parse("x==2 q") - with pytest.raises(ValueError): - Requirement.parse("X==1\nY==2") - with pytest.raises(ValueError): - Requirement.parse("#") - - def test_requirements_with_markers(self): - assert Requirement.parse("foobar;os_name=='a'") == Requirement.parse( - "foobar;os_name=='a'" - ) - assert Requirement.parse( - "name==1.1;python_version=='2.7'" - ) != Requirement.parse("name==1.1;python_version=='3.6'") - assert Requirement.parse( - "name==1.0;python_version=='2.7'" - ) != Requirement.parse("name==1.2;python_version=='2.7'") - assert Requirement.parse( - "name[foo]==1.0;python_version=='3.6'" - ) != Requirement.parse("name[foo,bar]==1.0;python_version=='3.6'") - - def test_local_version(self): - parse_requirements('foo==1.0+org1') - - def test_spaces_between_multiple_versions(self): - parse_requirements('foo>=1.0, <3') - parse_requirements('foo >= 1.0, < 3') - - @pytest.mark.parametrize( - ("lower", "upper"), - [ - ('1.2-rc1', '1.2rc1'), - ('0.4', '0.4.0'), - ('0.4.0.0', '0.4.0'), - ('0.4.0-0', '0.4-0'), - ('0post1', '0.0post1'), - ('0pre1', '0.0c1'), - ('0.0.0preview1', '0c1'), - ('0.0c1', '0-rc1'), - ('1.2a1', '1.2.a.1'), - ('1.2.a', '1.2a'), - ], - ) - def testVersionEquality(self, lower, upper): - assert parse_version(lower) == parse_version(upper) - - torture = """ - 0.80.1-3 0.80.1-2 0.80.1-1 0.79.9999+0.80.0pre4-1 - 0.79.9999+0.80.0pre2-3 0.79.9999+0.80.0pre2-2 - 0.77.2-1 0.77.1-1 0.77.0-1 - """ - - @pytest.mark.parametrize( - ("lower", "upper"), - [ - ('2.1', '2.1.1'), - ('2a1', '2b0'), - ('2a1', '2.1'), - ('2.3a1', '2.3'), - ('2.1-1', '2.1-2'), - ('2.1-1', '2.1.1'), - ('2.1', '2.1post4'), - ('2.1a0-20040501', '2.1'), - ('1.1', '02.1'), - ('3.2', '3.2.post0'), - ('3.2post1', '3.2post2'), - ('0.4', '4.0'), - ('0.0.4', '0.4.0'), - ('0post1', '0.4post1'), - ('2.1.0-rc1', '2.1.0'), - ('2.1dev', '2.1a0'), - ] - + list(pairwise(reversed(torture.split()))), - ) - def testVersionOrdering(self, lower, upper): - assert parse_version(lower) < parse_version(upper) - - def testVersionHashable(self): - """ - Ensure that our versions stay hashable even though we've subclassed - them and added some shim code to them. - """ - assert hash(parse_version("1.0")) == hash(parse_version("1.0")) - - -class TestNamespaces: - ns_str = "__import__('pkg_resources').declare_namespace(__name__)\n" - - @pytest.fixture - def symlinked_tmpdir(self, tmpdir): - """ - Where available, return the tempdir as a symlink, - which as revealed in #231 is more fragile than - a natural tempdir. - """ - if not hasattr(os, 'symlink'): - yield str(tmpdir) - return - - link_name = str(tmpdir) + '-linked' - os.symlink(str(tmpdir), link_name) - try: - yield type(tmpdir)(link_name) - finally: - os.unlink(link_name) - - @pytest.fixture(autouse=True) - def patched_path(self, tmpdir): - """ - Patch sys.path to include the 'site-pkgs' dir. Also - restore pkg_resources._namespace_packages to its - former state. - """ - saved_ns_pkgs = pkg_resources._namespace_packages.copy() - saved_sys_path = sys.path[:] - site_pkgs = tmpdir.mkdir('site-pkgs') - sys.path.append(str(site_pkgs)) - try: - yield - finally: - pkg_resources._namespace_packages = saved_ns_pkgs - sys.path = saved_sys_path - - issue591 = pytest.mark.xfail(platform.system() == 'Windows', reason="#591") - - @issue591 - def test_two_levels_deep(self, symlinked_tmpdir): - """ - Test nested namespace packages - Create namespace packages in the following tree : - site-packages-1/pkg1/pkg2 - site-packages-2/pkg1/pkg2 - Check both are in the _namespace_packages dict and that their __path__ - is correct - """ - real_tmpdir = symlinked_tmpdir.realpath() - tmpdir = symlinked_tmpdir - sys.path.append(str(tmpdir / 'site-pkgs2')) - site_dirs = tmpdir / 'site-pkgs', tmpdir / 'site-pkgs2' - for site in site_dirs: - pkg1 = site / 'pkg1' - pkg2 = pkg1 / 'pkg2' - pkg2.ensure_dir() - (pkg1 / '__init__.py').write_text(self.ns_str, encoding='utf-8') - (pkg2 / '__init__.py').write_text(self.ns_str, encoding='utf-8') - with pytest.warns(DeprecationWarning, match="pkg_resources.declare_namespace"): - import pkg1 # pyright: ignore[reportMissingImports] # Temporary package for test - assert "pkg1" in pkg_resources._namespace_packages - # attempt to import pkg2 from site-pkgs2 - with pytest.warns(DeprecationWarning, match="pkg_resources.declare_namespace"): - import pkg1.pkg2 # pyright: ignore[reportMissingImports] # Temporary package for test - # check the _namespace_packages dict - assert "pkg1.pkg2" in pkg_resources._namespace_packages - assert pkg_resources._namespace_packages["pkg1"] == ["pkg1.pkg2"] - # check the __path__ attribute contains both paths - expected = [ - str(real_tmpdir / "site-pkgs" / "pkg1" / "pkg2"), - str(real_tmpdir / "site-pkgs2" / "pkg1" / "pkg2"), - ] - assert pkg1.pkg2.__path__ == expected - - @issue591 - def test_path_order(self, symlinked_tmpdir): - """ - Test that if multiple versions of the same namespace package subpackage - are on different sys.path entries, that only the one earliest on - sys.path is imported, and that the namespace package's __path__ is in - the correct order. - - Regression test for https://github.com/pypa/setuptools/issues/207 - """ - - tmpdir = symlinked_tmpdir - site_dirs = ( - tmpdir / "site-pkgs", - tmpdir / "site-pkgs2", - tmpdir / "site-pkgs3", - ) - - vers_str = "__version__ = %r" - - for number, site in enumerate(site_dirs, 1): - if number > 1: - sys.path.append(str(site)) - nspkg = site / 'nspkg' - subpkg = nspkg / 'subpkg' - subpkg.ensure_dir() - (nspkg / '__init__.py').write_text(self.ns_str, encoding='utf-8') - (subpkg / '__init__.py').write_text(vers_str % number, encoding='utf-8') - - with pytest.warns(DeprecationWarning, match="pkg_resources.declare_namespace"): - import nspkg # pyright: ignore[reportMissingImports] # Temporary package for test - import nspkg.subpkg # pyright: ignore[reportMissingImports] # Temporary package for test - expected = [str(site.realpath() / 'nspkg') for site in site_dirs] - assert nspkg.__path__ == expected - assert nspkg.subpkg.__version__ == 1 diff --git a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_working_set.py b/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_working_set.py deleted file mode 100644 index ed20c59..0000000 --- a/llmlab/lib/python3.12/site-packages/pkg_resources/tests/test_working_set.py +++ /dev/null @@ -1,505 +0,0 @@ -import functools -import inspect -import re -import textwrap - -import pytest - -import pkg_resources - -from .test_resources import Metadata - - -def strip_comments(s): - return '\n'.join( - line - for line in s.split('\n') - if line.strip() and not line.strip().startswith('#') - ) - - -def parse_distributions(s): - """ - Parse a series of distribution specs of the form: - {project_name}-{version} - [optional, indented requirements specification] - - Example: - - foo-0.2 - bar-1.0 - foo>=3.0 - [feature] - baz - - yield 2 distributions: - - project_name=foo, version=0.2 - - project_name=bar, version=1.0, - requires=['foo>=3.0', 'baz; extra=="feature"'] - """ - s = s.strip() - for spec in re.split(r'\n(?=[^\s])', s): - if not spec: - continue - fields = spec.split('\n', 1) - assert 1 <= len(fields) <= 2 - name, version = fields.pop(0).rsplit('-', 1) - if fields: - requires = textwrap.dedent(fields.pop(0)) - metadata = Metadata(('requires.txt', requires)) - else: - metadata = None - dist = pkg_resources.Distribution( - project_name=name, version=version, metadata=metadata - ) - yield dist - - -class FakeInstaller: - def __init__(self, installable_dists) -> None: - self._installable_dists = installable_dists - - def __call__(self, req): - return next( - iter(filter(lambda dist: dist in req, self._installable_dists)), None - ) - - -def parametrize_test_working_set_resolve(*test_list): - idlist = [] - argvalues = [] - for test in test_list: - ( - name, - installed_dists, - installable_dists, - requirements, - expected1, - expected2, - ) = ( - strip_comments(s.lstrip()) - for s in textwrap.dedent(test).lstrip().split('\n\n', 5) - ) - installed_dists = list(parse_distributions(installed_dists)) - installable_dists = list(parse_distributions(installable_dists)) - requirements = list(pkg_resources.parse_requirements(requirements)) - for id_, replace_conflicting, expected in ( - (name, False, expected1), - (name + '_replace_conflicting', True, expected2), - ): - idlist.append(id_) - expected = strip_comments(expected.strip()) - if re.match(r'\w+$', expected): - expected = getattr(pkg_resources, expected) - assert issubclass(expected, Exception) - else: - expected = list(parse_distributions(expected)) - argvalues.append( - pytest.param( - installed_dists, - installable_dists, - requirements, - replace_conflicting, - expected, - ) - ) - return pytest.mark.parametrize( - ( - "installed_dists", - "installable_dists", - "requirements", - "replace_conflicting", - "resolved_dists_or_exception", - ), - argvalues, - ids=idlist, - ) - - -@parametrize_test_working_set_resolve( - """ - # id - noop - - # installed - - # installable - - # wanted - - # resolved - - # resolved [replace conflicting] - """, - """ - # id - already_installed - - # installed - foo-3.0 - - # installable - - # wanted - foo>=2.1,!=3.1,<4 - - # resolved - foo-3.0 - - # resolved [replace conflicting] - foo-3.0 - """, - """ - # id - installable_not_installed - - # installed - - # installable - foo-3.0 - foo-4.0 - - # wanted - foo>=2.1,!=3.1,<4 - - # resolved - foo-3.0 - - # resolved [replace conflicting] - foo-3.0 - """, - """ - # id - not_installable - - # installed - - # installable - - # wanted - foo>=2.1,!=3.1,<4 - - # resolved - DistributionNotFound - - # resolved [replace conflicting] - DistributionNotFound - """, - """ - # id - no_matching_version - - # installed - - # installable - foo-3.1 - - # wanted - foo>=2.1,!=3.1,<4 - - # resolved - DistributionNotFound - - # resolved [replace conflicting] - DistributionNotFound - """, - """ - # id - installable_with_installed_conflict - - # installed - foo-3.1 - - # installable - foo-3.5 - - # wanted - foo>=2.1,!=3.1,<4 - - # resolved - VersionConflict - - # resolved [replace conflicting] - foo-3.5 - """, - """ - # id - not_installable_with_installed_conflict - - # installed - foo-3.1 - - # installable - - # wanted - foo>=2.1,!=3.1,<4 - - # resolved - VersionConflict - - # resolved [replace conflicting] - DistributionNotFound - """, - """ - # id - installed_with_installed_require - - # installed - foo-3.9 - baz-0.1 - foo>=2.1,!=3.1,<4 - - # installable - - # wanted - baz - - # resolved - foo-3.9 - baz-0.1 - - # resolved [replace conflicting] - foo-3.9 - baz-0.1 - """, - """ - # id - installed_with_conflicting_installed_require - - # installed - foo-5 - baz-0.1 - foo>=2.1,!=3.1,<4 - - # installable - - # wanted - baz - - # resolved - VersionConflict - - # resolved [replace conflicting] - DistributionNotFound - """, - """ - # id - installed_with_installable_conflicting_require - - # installed - foo-5 - baz-0.1 - foo>=2.1,!=3.1,<4 - - # installable - foo-2.9 - - # wanted - baz - - # resolved - VersionConflict - - # resolved [replace conflicting] - baz-0.1 - foo-2.9 - """, - """ - # id - installed_with_installable_require - - # installed - baz-0.1 - foo>=2.1,!=3.1,<4 - - # installable - foo-3.9 - - # wanted - baz - - # resolved - foo-3.9 - baz-0.1 - - # resolved [replace conflicting] - foo-3.9 - baz-0.1 - """, - """ - # id - installable_with_installed_require - - # installed - foo-3.9 - - # installable - baz-0.1 - foo>=2.1,!=3.1,<4 - - # wanted - baz - - # resolved - foo-3.9 - baz-0.1 - - # resolved [replace conflicting] - foo-3.9 - baz-0.1 - """, - """ - # id - installable_with_installable_require - - # installed - - # installable - foo-3.9 - baz-0.1 - foo>=2.1,!=3.1,<4 - - # wanted - baz - - # resolved - foo-3.9 - baz-0.1 - - # resolved [replace conflicting] - foo-3.9 - baz-0.1 - """, - """ - # id - installable_with_conflicting_installable_require - - # installed - foo-5 - - # installable - foo-2.9 - baz-0.1 - foo>=2.1,!=3.1,<4 - - # wanted - baz - - # resolved - VersionConflict - - # resolved [replace conflicting] - baz-0.1 - foo-2.9 - """, - """ - # id - conflicting_installables - - # installed - - # installable - foo-2.9 - foo-5.0 - - # wanted - foo>=2.1,!=3.1,<4 - foo>=4 - - # resolved - VersionConflict - - # resolved [replace conflicting] - VersionConflict - """, - """ - # id - installables_with_conflicting_requires - - # installed - - # installable - foo-2.9 - dep==1.0 - baz-5.0 - dep==2.0 - dep-1.0 - dep-2.0 - - # wanted - foo - baz - - # resolved - VersionConflict - - # resolved [replace conflicting] - VersionConflict - """, - """ - # id - installables_with_conflicting_nested_requires - - # installed - - # installable - foo-2.9 - dep1 - dep1-1.0 - subdep<1.0 - baz-5.0 - dep2 - dep2-1.0 - subdep>1.0 - subdep-0.9 - subdep-1.1 - - # wanted - foo - baz - - # resolved - VersionConflict - - # resolved [replace conflicting] - VersionConflict - """, - """ - # id - wanted_normalized_name_installed_canonical - - # installed - foo.bar-3.6 - - # installable - - # wanted - foo-bar==3.6 - - # resolved - foo.bar-3.6 - - # resolved [replace conflicting] - foo.bar-3.6 - """, -) -def test_working_set_resolve( - installed_dists, - installable_dists, - requirements, - replace_conflicting, - resolved_dists_or_exception, -): - ws = pkg_resources.WorkingSet([]) - list(map(ws.add, installed_dists)) - resolve_call = functools.partial( - ws.resolve, - requirements, - installer=FakeInstaller(installable_dists), - replace_conflicting=replace_conflicting, - ) - if inspect.isclass(resolved_dists_or_exception): - with pytest.raises(resolved_dists_or_exception): - resolve_call() - else: - assert sorted(resolve_call()) == sorted(resolved_dists_or_exception) diff --git a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/INSTALLER similarity index 100% rename from llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/INSTALLER rename to llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/INSTALLER diff --git a/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/LICENSE new file mode 100644 index 0000000..cff5eb7 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/LICENSE @@ -0,0 +1,29 @@ +BSD 3-Clause License + +Copyright (c) 2009, Jay Loden, Dave Daeschler, Giampaolo Rodola +All rights reserved. + +Redistribution and use in source and binary forms, with or without modification, +are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, this + list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + + * Neither the name of the psutil authors nor the names of its contributors + may be used to endorse or promote products derived from this software without + specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND +ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED +WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR +ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES +(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; +LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON +ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/METADATA new file mode 100644 index 0000000..685d2e2 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/METADATA @@ -0,0 +1,546 @@ +Metadata-Version: 2.1 +Name: psutil +Version: 7.0.0 +Summary: Cross-platform lib for process and system monitoring in Python. NOTE: the syntax of this script MUST be kept compatible with Python 2.7. +Home-page: https://github.com/giampaolo/psutil +Author: Giampaolo Rodola +Author-email: g.rodola@gmail.com +License: BSD-3-Clause +Keywords: ps,top,kill,free,lsof,netstat,nice,tty,ionice,uptime,taskmgr,process,df,iotop,iostat,ifconfig,taskset,who,pidof,pmap,smem,pstree,monitoring,ulimit,prlimit,smem,performance,metrics,agent,observability +Platform: Platform Independent +Classifier: Development Status :: 5 - Production/Stable +Classifier: Environment :: Console +Classifier: Environment :: Win32 (MS Windows) +Classifier: Intended Audience :: Developers +Classifier: Intended Audience :: Information Technology +Classifier: Intended Audience :: System Administrators +Classifier: License :: OSI Approved :: BSD License +Classifier: Operating System :: MacOS :: MacOS X +Classifier: Operating System :: Microsoft :: Windows :: Windows 10 +Classifier: Operating System :: Microsoft :: Windows :: Windows 7 +Classifier: Operating System :: Microsoft :: Windows :: Windows 8 +Classifier: Operating System :: Microsoft :: Windows :: Windows 8.1 +Classifier: Operating System :: Microsoft :: Windows :: Windows Server 2003 +Classifier: Operating System :: Microsoft :: Windows :: Windows Server 2008 +Classifier: Operating System :: Microsoft :: Windows :: Windows Vista +Classifier: Operating System :: Microsoft +Classifier: Operating System :: OS Independent +Classifier: Operating System :: POSIX :: AIX +Classifier: Operating System :: POSIX :: BSD :: FreeBSD +Classifier: Operating System :: POSIX :: BSD :: NetBSD +Classifier: Operating System :: POSIX :: BSD :: OpenBSD +Classifier: Operating System :: POSIX :: BSD +Classifier: Operating System :: POSIX :: Linux +Classifier: Operating System :: POSIX :: SunOS/Solaris +Classifier: Operating System :: POSIX +Classifier: Programming Language :: C +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: Implementation :: CPython +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Programming Language :: Python +Classifier: Topic :: Software Development :: Libraries :: Python Modules +Classifier: Topic :: Software Development :: Libraries +Classifier: Topic :: System :: Benchmark +Classifier: Topic :: System :: Hardware :: Hardware Drivers +Classifier: Topic :: System :: Hardware +Classifier: Topic :: System :: Monitoring +Classifier: Topic :: System :: Networking :: Monitoring :: Hardware Watchdog +Classifier: Topic :: System :: Networking :: Monitoring +Classifier: Topic :: System :: Networking +Classifier: Topic :: System :: Operating System +Classifier: Topic :: System :: Systems Administration +Classifier: Topic :: Utilities +Requires-Python: >=3.6 +Description-Content-Type: text/x-rst +License-File: LICENSE +Provides-Extra: dev +Requires-Dist: pytest ; extra == 'dev' +Requires-Dist: pytest-xdist ; extra == 'dev' +Requires-Dist: setuptools ; extra == 'dev' +Requires-Dist: abi3audit ; extra == 'dev' +Requires-Dist: black (==24.10.0) ; extra == 'dev' +Requires-Dist: check-manifest ; extra == 'dev' +Requires-Dist: coverage ; extra == 'dev' +Requires-Dist: packaging ; extra == 'dev' +Requires-Dist: pylint ; extra == 'dev' +Requires-Dist: pyperf ; extra == 'dev' +Requires-Dist: pypinfo ; extra == 'dev' +Requires-Dist: pytest-cov ; extra == 'dev' +Requires-Dist: requests ; extra == 'dev' +Requires-Dist: rstcheck ; extra == 'dev' +Requires-Dist: ruff ; extra == 'dev' +Requires-Dist: sphinx ; extra == 'dev' +Requires-Dist: sphinx-rtd-theme ; extra == 'dev' +Requires-Dist: toml-sort ; extra == 'dev' +Requires-Dist: twine ; extra == 'dev' +Requires-Dist: virtualenv ; extra == 'dev' +Requires-Dist: vulture ; extra == 'dev' +Requires-Dist: wheel ; extra == 'dev' +Provides-Extra: test +Requires-Dist: pytest ; extra == 'test' +Requires-Dist: pytest-xdist ; extra == 'test' +Requires-Dist: setuptools ; extra == 'test' + +| |downloads| |stars| |forks| |contributors| |coverage| +| |version| |py-versions| |packages| |license| +| |github-actions-wheels| |github-actions-bsd| |doc| |twitter| |tidelift| + +.. |downloads| image:: https://img.shields.io/pypi/dm/psutil.svg + :target: https://pepy.tech/project/psutil + :alt: Downloads + +.. |stars| image:: https://img.shields.io/github/stars/giampaolo/psutil.svg + :target: https://github.com/giampaolo/psutil/stargazers + :alt: Github stars + +.. |forks| image:: https://img.shields.io/github/forks/giampaolo/psutil.svg + :target: https://github.com/giampaolo/psutil/network/members + :alt: Github forks + +.. |contributors| image:: https://img.shields.io/github/contributors/giampaolo/psutil.svg + :target: https://github.com/giampaolo/psutil/graphs/contributors + :alt: Contributors + +.. |github-actions-wheels| image:: https://img.shields.io/github/actions/workflow/status/giampaolo/psutil/.github/workflows/build.yml.svg?label=Linux%2C%20macOS%2C%20Windows + :target: https://github.com/giampaolo/psutil/actions?query=workflow%3Abuild + :alt: Linux, macOS, Windows + +.. |github-actions-bsd| image:: https://img.shields.io/github/actions/workflow/status/giampaolo/psutil/.github/workflows/bsd.yml.svg?label=FreeBSD,%20NetBSD,%20OpenBSD + :target: https://github.com/giampaolo/psutil/actions?query=workflow%3Absd-tests + :alt: FreeBSD, NetBSD, OpenBSD + +.. |coverage| image:: https://coveralls.io/repos/github/giampaolo/psutil/badge.svg?branch=master + :target: https://coveralls.io/github/giampaolo/psutil?branch=master + :alt: Test coverage (coverall.io) + +.. |doc| image:: https://readthedocs.org/projects/psutil/badge/?version=latest + :target: https://psutil.readthedocs.io/en/latest/ + :alt: Documentation Status + +.. |version| image:: https://img.shields.io/pypi/v/psutil.svg?label=pypi + :target: https://pypi.org/project/psutil + :alt: Latest version + +.. |py-versions| image:: https://img.shields.io/pypi/pyversions/psutil.svg + :alt: Supported Python versions + +.. |packages| image:: https://repology.org/badge/tiny-repos/python:psutil.svg + :target: https://repology.org/metapackage/python:psutil/versions + :alt: Binary packages + +.. |license| image:: https://img.shields.io/pypi/l/psutil.svg + :target: https://github.com/giampaolo/psutil/blob/master/LICENSE + :alt: License + +.. |twitter| image:: https://img.shields.io/twitter/follow/grodola.svg?label=follow&style=flat&logo=twitter&logoColor=4FADFF + :target: https://twitter.com/grodola + :alt: Twitter Follow + +.. |tidelift| image:: https://tidelift.com/badges/github/giampaolo/psutil?style=flat + :target: https://tidelift.com/subscription/pkg/pypi-psutil?utm_source=pypi-psutil&utm_medium=referral&utm_campaign=readme + :alt: Tidelift + +----- + +Quick links +=========== + +- `Home page `_ +- `Install `_ +- `Documentation `_ +- `Download `_ +- `Forum `_ +- `StackOverflow `_ +- `Blog `_ +- `What's new `_ + + +Summary +======= + +psutil (process and system utilities) is a cross-platform library for +retrieving information on **running processes** and **system utilization** +(CPU, memory, disks, network, sensors) in Python. +It is useful mainly for **system monitoring**, **profiling and limiting process +resources** and **management of running processes**. +It implements many functionalities offered by classic UNIX command line tools +such as *ps, top, iotop, lsof, netstat, ifconfig, free* and others. +psutil currently supports the following platforms: + +- **Linux** +- **Windows** +- **macOS** +- **FreeBSD, OpenBSD**, **NetBSD** +- **Sun Solaris** +- **AIX** + +Supported Python versions are cPython 3.6+ and `PyPy `__. +Latest psutil version supporting Python 2.7 is +`psutil 6.1.1 `__. + +Funding +======= + +While psutil is free software and will always be, the project would benefit +immensely from some funding. +Keeping up with bug reports and maintenance has become hardly sustainable for +me alone in terms of time. +If you're a company that's making significant use of psutil you can consider +becoming a sponsor via `GitHub Sponsors `__, +`Open Collective `__ or +`PayPal `__ +and have your logo displayed in here and psutil `doc `__. + +Sponsors +======== + +.. image:: https://github.com/giampaolo/psutil/raw/master/docs/_static/tidelift-logo.png + :width: 200 + :alt: Alternative text + +`Add your logo `__. + +Example usages +============== + +This represents pretty much the whole psutil API. + +CPU +--- + +.. code-block:: python + + >>> import psutil + >>> + >>> psutil.cpu_times() + scputimes(user=3961.46, nice=169.729, system=2150.659, idle=16900.540, iowait=629.59, irq=0.0, softirq=19.42, steal=0.0, guest=0, guest_nice=0.0) + >>> + >>> for x in range(3): + ... psutil.cpu_percent(interval=1) + ... + 4.0 + 5.9 + 3.8 + >>> + >>> for x in range(3): + ... psutil.cpu_percent(interval=1, percpu=True) + ... + [4.0, 6.9, 3.7, 9.2] + [7.0, 8.5, 2.4, 2.1] + [1.2, 9.0, 9.9, 7.2] + >>> + >>> for x in range(3): + ... psutil.cpu_times_percent(interval=1, percpu=False) + ... + scputimes(user=1.5, nice=0.0, system=0.5, idle=96.5, iowait=1.5, irq=0.0, softirq=0.0, steal=0.0, guest=0.0, guest_nice=0.0) + scputimes(user=1.0, nice=0.0, system=0.0, idle=99.0, iowait=0.0, irq=0.0, softirq=0.0, steal=0.0, guest=0.0, guest_nice=0.0) + scputimes(user=2.0, nice=0.0, system=0.0, idle=98.0, iowait=0.0, irq=0.0, softirq=0.0, steal=0.0, guest=0.0, guest_nice=0.0) + >>> + >>> psutil.cpu_count() + 4 + >>> psutil.cpu_count(logical=False) + 2 + >>> + >>> psutil.cpu_stats() + scpustats(ctx_switches=20455687, interrupts=6598984, soft_interrupts=2134212, syscalls=0) + >>> + >>> psutil.cpu_freq() + scpufreq(current=931.42925, min=800.0, max=3500.0) + >>> + >>> psutil.getloadavg() # also on Windows (emulated) + (3.14, 3.89, 4.67) + +Memory +------ + +.. code-block:: python + + >>> psutil.virtual_memory() + svmem(total=10367352832, available=6472179712, percent=37.6, used=8186245120, free=2181107712, active=4748992512, inactive=2758115328, buffers=790724608, cached=3500347392, shared=787554304) + >>> psutil.swap_memory() + sswap(total=2097147904, used=296128512, free=1801019392, percent=14.1, sin=304193536, sout=677842944) + >>> + +Disks +----- + +.. code-block:: python + + >>> psutil.disk_partitions() + [sdiskpart(device='/dev/sda1', mountpoint='/', fstype='ext4', opts='rw,nosuid'), + sdiskpart(device='/dev/sda2', mountpoint='/home', fstype='ext', opts='rw')] + >>> + >>> psutil.disk_usage('/') + sdiskusage(total=21378641920, used=4809781248, free=15482871808, percent=22.5) + >>> + >>> psutil.disk_io_counters(perdisk=False) + sdiskio(read_count=719566, write_count=1082197, read_bytes=18626220032, write_bytes=24081764352, read_time=5023392, write_time=63199568, read_merged_count=619166, write_merged_count=812396, busy_time=4523412) + >>> + +Network +------- + +.. code-block:: python + + >>> psutil.net_io_counters(pernic=True) + {'eth0': netio(bytes_sent=485291293, bytes_recv=6004858642, packets_sent=3251564, packets_recv=4787798, errin=0, errout=0, dropin=0, dropout=0), + 'lo': netio(bytes_sent=2838627, bytes_recv=2838627, packets_sent=30567, packets_recv=30567, errin=0, errout=0, dropin=0, dropout=0)} + >>> + >>> psutil.net_connections(kind='tcp') + [sconn(fd=115, family=, type=, laddr=addr(ip='10.0.0.1', port=48776), raddr=addr(ip='93.186.135.91', port=80), status='ESTABLISHED', pid=1254), + sconn(fd=117, family=, type=, laddr=addr(ip='10.0.0.1', port=43761), raddr=addr(ip='72.14.234.100', port=80), status='CLOSING', pid=2987), + ...] + >>> + >>> psutil.net_if_addrs() + {'lo': [snicaddr(family=, address='127.0.0.1', netmask='255.0.0.0', broadcast='127.0.0.1', ptp=None), + snicaddr(family=, address='::1', netmask='ffff:ffff:ffff:ffff:ffff:ffff:ffff:ffff', broadcast=None, ptp=None), + snicaddr(family=, address='00:00:00:00:00:00', netmask=None, broadcast='00:00:00:00:00:00', ptp=None)], + 'wlan0': [snicaddr(family=, address='192.168.1.3', netmask='255.255.255.0', broadcast='192.168.1.255', ptp=None), + snicaddr(family=, address='fe80::c685:8ff:fe45:641%wlan0', netmask='ffff:ffff:ffff:ffff::', broadcast=None, ptp=None), + snicaddr(family=, address='c4:85:08:45:06:41', netmask=None, broadcast='ff:ff:ff:ff:ff:ff', ptp=None)]} + >>> + >>> psutil.net_if_stats() + {'lo': snicstats(isup=True, duplex=, speed=0, mtu=65536, flags='up,loopback,running'), + 'wlan0': snicstats(isup=True, duplex=, speed=100, mtu=1500, flags='up,broadcast,running,multicast')} + >>> + +Sensors +------- + +.. code-block:: python + + >>> import psutil + >>> psutil.sensors_temperatures() + {'acpitz': [shwtemp(label='', current=47.0, high=103.0, critical=103.0)], + 'asus': [shwtemp(label='', current=47.0, high=None, critical=None)], + 'coretemp': [shwtemp(label='Physical id 0', current=52.0, high=100.0, critical=100.0), + shwtemp(label='Core 0', current=45.0, high=100.0, critical=100.0)]} + >>> + >>> psutil.sensors_fans() + {'asus': [sfan(label='cpu_fan', current=3200)]} + >>> + >>> psutil.sensors_battery() + sbattery(percent=93, secsleft=16628, power_plugged=False) + >>> + +Other system info +----------------- + +.. code-block:: python + + >>> import psutil + >>> psutil.users() + [suser(name='giampaolo', terminal='pts/2', host='localhost', started=1340737536.0, pid=1352), + suser(name='giampaolo', terminal='pts/3', host='localhost', started=1340737792.0, pid=1788)] + >>> + >>> psutil.boot_time() + 1365519115.0 + >>> + +Process management +------------------ + +.. code-block:: python + + >>> import psutil + >>> psutil.pids() + [1, 2, 3, 4, 5, 6, 7, 46, 48, 50, 51, 178, 182, 222, 223, 224, 268, 1215, + 1216, 1220, 1221, 1243, 1244, 1301, 1601, 2237, 2355, 2637, 2774, 3932, + 4176, 4177, 4185, 4187, 4189, 4225, 4243, 4245, 4263, 4282, 4306, 4311, + 4312, 4313, 4314, 4337, 4339, 4357, 4358, 4363, 4383, 4395, 4408, 4433, + 4443, 4445, 4446, 5167, 5234, 5235, 5252, 5318, 5424, 5644, 6987, 7054, + 7055, 7071] + >>> + >>> p = psutil.Process(7055) + >>> p + psutil.Process(pid=7055, name='python3', status='running', started='09:04:44') + >>> p.pid + 7055 + >>> p.name() + 'python3' + >>> p.exe() + '/usr/bin/python3' + >>> p.cwd() + '/home/giampaolo' + >>> p.cmdline() + ['/usr/bin/python3', 'main.py'] + >>> + >>> p.ppid() + 7054 + >>> p.parent() + psutil.Process(pid=4699, name='bash', status='sleeping', started='09:06:44') + >>> p.parents() + [psutil.Process(pid=4699, name='bash', started='09:06:44'), + psutil.Process(pid=4689, name='gnome-terminal-server', status='sleeping', started='0:06:44'), + psutil.Process(pid=1, name='systemd', status='sleeping', started='05:56:55')] + >>> p.children(recursive=True) + [psutil.Process(pid=29835, name='python3', status='sleeping', started='11:45:38'), + psutil.Process(pid=29836, name='python3', status='waking', started='11:43:39')] + >>> + >>> p.status() + 'running' + >>> p.create_time() + 1267551141.5019531 + >>> p.terminal() + '/dev/pts/0' + >>> + >>> p.username() + 'giampaolo' + >>> p.uids() + puids(real=1000, effective=1000, saved=1000) + >>> p.gids() + pgids(real=1000, effective=1000, saved=1000) + >>> + >>> p.cpu_times() + pcputimes(user=1.02, system=0.31, children_user=0.32, children_system=0.1, iowait=0.0) + >>> p.cpu_percent(interval=1.0) + 12.1 + >>> p.cpu_affinity() + [0, 1, 2, 3] + >>> p.cpu_affinity([0, 1]) # set + >>> p.cpu_num() + 1 + >>> + >>> p.memory_info() + pmem(rss=10915840, vms=67608576, shared=3313664, text=2310144, lib=0, data=7262208, dirty=0) + >>> p.memory_full_info() # "real" USS memory usage (Linux, macOS, Win only) + pfullmem(rss=10199040, vms=52133888, shared=3887104, text=2867200, lib=0, data=5967872, dirty=0, uss=6545408, pss=6872064, swap=0) + >>> p.memory_percent() + 0.7823 + >>> p.memory_maps() + [pmmap_grouped(path='/lib/x8664-linux-gnu/libutil-2.15.so', rss=32768, size=2125824, pss=32768, shared_clean=0, shared_dirty=0, private_clean=20480, private_dirty=12288, referenced=32768, anonymous=12288, swap=0), + pmmap_grouped(path='/lib/x8664-linux-gnu/libc-2.15.so', rss=3821568, size=3842048, pss=3821568, shared_clean=0, shared_dirty=0, private_clean=0, private_dirty=3821568, referenced=3575808, anonymous=3821568, swap=0), + pmmap_grouped(path='[heap]', rss=32768, size=139264, pss=32768, shared_clean=0, shared_dirty=0, private_clean=0, private_dirty=32768, referenced=32768, anonymous=32768, swap=0), + pmmap_grouped(path='[stack]', rss=2465792, size=2494464, pss=2465792, shared_clean=0, shared_dirty=0, private_clean=0, private_dirty=2465792, referenced=2277376, anonymous=2465792, swap=0), + ...] + >>> + >>> p.io_counters() + pio(read_count=478001, write_count=59371, read_bytes=700416, write_bytes=69632, read_chars=456232, write_chars=517543) + >>> + >>> p.open_files() + [popenfile(path='/home/giampaolo/monit.py', fd=3, position=0, mode='r', flags=32768), + popenfile(path='/var/log/monit.log', fd=4, position=235542, mode='a', flags=33793)] + >>> + >>> p.net_connections(kind='tcp') + [pconn(fd=115, family=, type=, laddr=addr(ip='10.0.0.1', port=48776), raddr=addr(ip='93.186.135.91', port=80), status='ESTABLISHED'), + pconn(fd=117, family=, type=, laddr=addr(ip='10.0.0.1', port=43761), raddr=addr(ip='72.14.234.100', port=80), status='CLOSING')] + >>> + >>> p.threads() + [pthread(id=5234, user_time=22.5, system_time=9.2891), + pthread(id=5237, user_time=0.0707, system_time=1.1)] + >>> + >>> p.num_threads() + 4 + >>> p.num_fds() + 8 + >>> p.num_ctx_switches() + pctxsw(voluntary=78, involuntary=19) + >>> + >>> p.nice() + 0 + >>> p.nice(10) # set + >>> + >>> p.ionice(psutil.IOPRIO_CLASS_IDLE) # IO priority (Win and Linux only) + >>> p.ionice() + pionice(ioclass=, value=0) + >>> + >>> p.rlimit(psutil.RLIMIT_NOFILE, (5, 5)) # set resource limits (Linux only) + >>> p.rlimit(psutil.RLIMIT_NOFILE) + (5, 5) + >>> + >>> p.environ() + {'LC_PAPER': 'it_IT.UTF-8', 'SHELL': '/bin/bash', 'GREP_OPTIONS': '--color=auto', + 'XDG_CONFIG_DIRS': '/etc/xdg/xdg-ubuntu:/usr/share/upstart/xdg:/etc/xdg', + ...} + >>> + >>> p.as_dict() + {'status': 'running', 'num_ctx_switches': pctxsw(voluntary=63, involuntary=1), 'pid': 5457, ...} + >>> p.is_running() + True + >>> p.suspend() + >>> p.resume() + >>> + >>> p.terminate() + >>> p.kill() + >>> p.wait(timeout=3) + + >>> + >>> psutil.test() + USER PID %CPU %MEM VSZ RSS TTY START TIME COMMAND + root 1 0.0 0.0 24584 2240 Jun17 00:00 init + root 2 0.0 0.0 0 0 Jun17 00:00 kthreadd + ... + giampaolo 31475 0.0 0.0 20760 3024 /dev/pts/0 Jun19 00:00 python2.4 + giampaolo 31721 0.0 2.2 773060 181896 00:04 10:30 chrome + root 31763 0.0 0.0 0 0 00:05 00:00 kworker/0:1 + >>> + +Further process APIs +-------------------- + +.. code-block:: python + + >>> import psutil + >>> for proc in psutil.process_iter(['pid', 'name']): + ... print(proc.info) + ... + {'pid': 1, 'name': 'systemd'} + {'pid': 2, 'name': 'kthreadd'} + {'pid': 3, 'name': 'ksoftirqd/0'} + ... + >>> + >>> psutil.pid_exists(3) + True + >>> + >>> def on_terminate(proc): + ... print("process {} terminated".format(proc)) + ... + >>> # waits for multiple processes to terminate + >>> gone, alive = psutil.wait_procs(procs_list, timeout=3, callback=on_terminate) + >>> + +Windows services +---------------- + +.. code-block:: python + + >>> list(psutil.win_service_iter()) + [, + , + , + , + ...] + >>> s = psutil.win_service_get('alg') + >>> s.as_dict() + {'binpath': 'C:\\Windows\\System32\\alg.exe', + 'description': 'Provides support for 3rd party protocol plug-ins for Internet Connection Sharing', + 'display_name': 'Application Layer Gateway Service', + 'name': 'alg', + 'pid': None, + 'start_type': 'manual', + 'status': 'stopped', + 'username': 'NT AUTHORITY\\LocalService'} + +Projects using psutil +===================== + +Here's some I find particularly interesting: + +- https://github.com/google/grr +- https://github.com/facebook/osquery/ +- https://github.com/nicolargo/glances +- https://github.com/aristocratos/bpytop +- https://github.com/Jahaja/psdash +- https://github.com/ajenti/ajenti +- https://github.com/home-assistant/home-assistant/ + +Portings +======== + +- Go: https://github.com/shirou/gopsutil +- C: https://github.com/hamon-in/cpslib +- Rust: https://github.com/rust-psutil/rust-psutil +- Nim: https://github.com/johnscillieri/psutil-nim + + + diff --git a/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/RECORD new file mode 100644 index 0000000..e7d2481 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/RECORD @@ -0,0 +1,65 @@ +psutil-7.0.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +psutil-7.0.0.dist-info/LICENSE,sha256=uJwGOzeG4o4MCjjxkx22H-015p3SopZvvs_-4PRsjRA,1548 +psutil-7.0.0.dist-info/METADATA,sha256=BFPkVTphhSTYAB4vZKg7HCRBmCbKuHv2tzTmcj04PIk,22315 +psutil-7.0.0.dist-info/RECORD,, +psutil-7.0.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +psutil-7.0.0.dist-info/WHEEL,sha256=rgpVBmjjvbINeGKCkWEGd3f40VHMTsDkQj1Lgil82zE,221 +psutil-7.0.0.dist-info/top_level.txt,sha256=gCNhn57wzksDjSAISmgMJ0aiXzQulk0GJhb2-BAyYgw,7 +psutil/__init__.py,sha256=tPSkFUoX9EGtvKiDzRcSMYhUbHlIdFbCw57a4ysNzLE,86668 +psutil/__pycache__/__init__.cpython-312.pyc,, +psutil/__pycache__/_common.cpython-312.pyc,, +psutil/__pycache__/_psaix.cpython-312.pyc,, +psutil/__pycache__/_psbsd.cpython-312.pyc,, +psutil/__pycache__/_pslinux.cpython-312.pyc,, +psutil/__pycache__/_psosx.cpython-312.pyc,, +psutil/__pycache__/_psposix.cpython-312.pyc,, +psutil/__pycache__/_pssunos.cpython-312.pyc,, +psutil/__pycache__/_pswindows.cpython-312.pyc,, +psutil/_common.py,sha256=0V6pk_6dqkaIMB2fbdlxERWV0jIt8m1yLxMPCqsVzAo,28642 +psutil/_psaix.py,sha256=5haK5IsqogH7ws-uikbh7LJywqsQTL4ihV-KT3CJ-f8,18252 +psutil/_psbsd.py,sha256=3pdjaz9QVPj2OeCRQSXXXGf89is9Fijt328dNIi8Jng,31756 +psutil/_pslinux.py,sha256=29sX7gw6tLXwp8eSLZ_NcVqa42glkZlGGonckWWlTrc,86028 +psutil/_psosx.py,sha256=O0HA58WMQMfMw6SrjyCn2Q3oN3GpQzC66BK9826w038,15877 +psutil/_psposix.py,sha256=kHwIVJ0J3aLvtNJrcs4h0OFMRVFKRtVmGMUvBhZwaRU,7142 +psutil/_pssunos.py,sha256=_N0t0vKPv4hl-rbVkROieAWgWP_pPUBsNO29me7xgc4,24920 +psutil/_psutil_linux.abi3.so,sha256=bC66whE5AHQQCAgRoBXCSe1vsvIHsaZOAY5HrhkXQIE,115336 +psutil/_psutil_posix.abi3.so,sha256=Kl35Rx_zW8_N1mNhs4OH_y4ZR3tq9P2eHCBUWSu6kcA,71640 +psutil/_pswindows.py,sha256=12fUxO7XxwHO0-IVCsWflc2CXbXg8NzfvgHptgTr4nI,35949 +psutil/tests/__init__.py,sha256=naU3g4k4xVCBqXZel9nHJEMoJkQKltxbKyfjDE-6HwM,64104 +psutil/tests/__main__.py,sha256=GYT-hlMnWDtybkJ76DqQcjXPr0jnLeZDTe0lVVeDb7o,309 +psutil/tests/__pycache__/__init__.cpython-312.pyc,, +psutil/tests/__pycache__/__main__.cpython-312.pyc,, +psutil/tests/__pycache__/test_aix.cpython-312.pyc,, +psutil/tests/__pycache__/test_bsd.cpython-312.pyc,, +psutil/tests/__pycache__/test_connections.cpython-312.pyc,, +psutil/tests/__pycache__/test_contracts.cpython-312.pyc,, +psutil/tests/__pycache__/test_linux.cpython-312.pyc,, +psutil/tests/__pycache__/test_memleaks.cpython-312.pyc,, +psutil/tests/__pycache__/test_misc.cpython-312.pyc,, +psutil/tests/__pycache__/test_osx.cpython-312.pyc,, +psutil/tests/__pycache__/test_posix.cpython-312.pyc,, +psutil/tests/__pycache__/test_process.cpython-312.pyc,, +psutil/tests/__pycache__/test_process_all.cpython-312.pyc,, +psutil/tests/__pycache__/test_scripts.cpython-312.pyc,, +psutil/tests/__pycache__/test_sunos.cpython-312.pyc,, +psutil/tests/__pycache__/test_system.cpython-312.pyc,, +psutil/tests/__pycache__/test_testutils.cpython-312.pyc,, +psutil/tests/__pycache__/test_unicode.cpython-312.pyc,, +psutil/tests/__pycache__/test_windows.cpython-312.pyc,, +psutil/tests/test_aix.py,sha256=O5IqMAU3qw1NXvI-nhNb9v1LbNHb1q3iFRe5OkqgpoI,4408 +psutil/tests/test_bsd.py,sha256=wALt2KBsv8LmuSbADGnXx3h3AL7dTheCmPBB9_iwE38,20191 +psutil/tests/test_connections.py,sha256=nL8675MBoPLoWc35ujR7QvMGRWtZjh6u3CmnwLTmts8,21157 +psutil/tests/test_contracts.py,sha256=ffPNOZ1nK4xV7gKYxJs1nOjORkM0WL-PSSxPQvq8pnI,12001 +psutil/tests/test_linux.py,sha256=Vw1hwyn2mGXQ1DYSksBWzfBBAynaiyWhXKRMWF_-3Sg,88895 +psutil/tests/test_memleaks.py,sha256=hC0Ra6v3ZwhMmLuJoCTeLUCJuh5wa0ER8UvHVSVTsio,15121 +psutil/tests/test_misc.py,sha256=PTelE-5fdcmL_49kz46966JNl8VB3-PowwmkwcIyodc,29672 +psutil/tests/test_osx.py,sha256=ysb3dSwJfzo07ElnFJThoJKmwquqQoUsaKeL1sz8zf8,6315 +psutil/tests/test_posix.py,sha256=bNQFfIrgLYNSFxbep9Qsqej46EG7yzH69_tlbpz3odY,17187 +psutil/tests/test_process.py,sha256=7g0vLr5ZdIj_sEzWkdSIpdBlRlcxTGI2UtUDa6KufUE,59881 +psutil/tests/test_process_all.py,sha256=kbe6Hq0UNGuHCx0T9jLok8O-E7RDQi5RLBZyCU_we5Q,18347 +psutil/tests/test_scripts.py,sha256=K--xQZrcNv4ABtax76ADBU_DjWK17cceTPg-jFoGpbI,7725 +psutil/tests/test_sunos.py,sha256=78nUq_4I2ALidWLiOGRjgP7ykFiGm8eGV3JNAiIoOVs,1190 +psutil/tests/test_system.py,sha256=UhmDw0psTdmAgfNmlS176Hv7hOwUl7F148vc7qH19GE,36107 +psutil/tests/test_testutils.py,sha256=2enHiV8mMapwrLwadIj04V3Z4M1OsyH49Hhg5bf3VxU,18338 +psutil/tests/test_unicode.py,sha256=Cv2pp9qS5iQJ8RMPKRow9--QoHsP1Q9ng6aKvbJnSWs,10392 +psutil/tests/test_windows.py,sha256=OESmHBNsYCwfpcqeloFmkvRfAzJf-nV75a0b0ztPUcE,33214 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/REQUESTED similarity index 100% rename from llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/REQUESTED rename to llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/REQUESTED diff --git a/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/WHEEL new file mode 100644 index 0000000..cd91456 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/WHEEL @@ -0,0 +1,8 @@ +Wheel-Version: 1.0 +Generator: bdist_wheel (0.37.1) +Root-Is-Purelib: false +Tag: cp36-abi3-manylinux_2_12_x86_64 +Tag: cp36-abi3-manylinux2010_x86_64 +Tag: cp36-abi3-manylinux_2_17_x86_64 +Tag: cp36-abi3-manylinux2014_x86_64 + diff --git a/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/top_level.txt new file mode 100644 index 0000000..a4d92cc --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil-7.0.0.dist-info/top_level.txt @@ -0,0 +1 @@ +psutil diff --git a/llmlab/lib/python3.12/site-packages/psutil/__init__.py b/llmlab/lib/python3.12/site-packages/psutil/__init__.py new file mode 100644 index 0000000..cf4a580 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/__init__.py @@ -0,0 +1,2407 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""psutil is a cross-platform library for retrieving information on +running processes and system utilization (CPU, memory, disks, network, +sensors) in Python. Supported platforms: + + - Linux + - Windows + - macOS + - FreeBSD + - OpenBSD + - NetBSD + - Sun Solaris + - AIX + +Supported Python versions are cPython 3.6+ and PyPy. +""" + +import collections +import contextlib +import datetime +import functools +import os +import signal +import socket +import subprocess +import sys +import threading +import time + + +try: + import pwd +except ImportError: + pwd = None + +from . import _common +from ._common import AIX +from ._common import BSD +from ._common import CONN_CLOSE +from ._common import CONN_CLOSE_WAIT +from ._common import CONN_CLOSING +from ._common import CONN_ESTABLISHED +from ._common import CONN_FIN_WAIT1 +from ._common import CONN_FIN_WAIT2 +from ._common import CONN_LAST_ACK +from ._common import CONN_LISTEN +from ._common import CONN_NONE +from ._common import CONN_SYN_RECV +from ._common import CONN_SYN_SENT +from ._common import CONN_TIME_WAIT +from ._common import FREEBSD +from ._common import LINUX +from ._common import MACOS +from ._common import NETBSD +from ._common import NIC_DUPLEX_FULL +from ._common import NIC_DUPLEX_HALF +from ._common import NIC_DUPLEX_UNKNOWN +from ._common import OPENBSD +from ._common import OSX # deprecated alias +from ._common import POSIX +from ._common import POWER_TIME_UNKNOWN +from ._common import POWER_TIME_UNLIMITED +from ._common import STATUS_DEAD +from ._common import STATUS_DISK_SLEEP +from ._common import STATUS_IDLE +from ._common import STATUS_LOCKED +from ._common import STATUS_PARKED +from ._common import STATUS_RUNNING +from ._common import STATUS_SLEEPING +from ._common import STATUS_STOPPED +from ._common import STATUS_TRACING_STOP +from ._common import STATUS_WAITING +from ._common import STATUS_WAKING +from ._common import STATUS_ZOMBIE +from ._common import SUNOS +from ._common import WINDOWS +from ._common import AccessDenied +from ._common import Error +from ._common import NoSuchProcess +from ._common import TimeoutExpired +from ._common import ZombieProcess +from ._common import debug +from ._common import memoize_when_activated +from ._common import wrap_numbers as _wrap_numbers + + +if LINUX: + # This is public API and it will be retrieved from _pslinux.py + # via sys.modules. + PROCFS_PATH = "/proc" + + from . import _pslinux as _psplatform + from ._pslinux import IOPRIO_CLASS_BE # noqa: F401 + from ._pslinux import IOPRIO_CLASS_IDLE # noqa: F401 + from ._pslinux import IOPRIO_CLASS_NONE # noqa: F401 + from ._pslinux import IOPRIO_CLASS_RT # noqa: F401 + +elif WINDOWS: + from . import _pswindows as _psplatform + from ._psutil_windows import ABOVE_NORMAL_PRIORITY_CLASS # noqa: F401 + from ._psutil_windows import BELOW_NORMAL_PRIORITY_CLASS # noqa: F401 + from ._psutil_windows import HIGH_PRIORITY_CLASS # noqa: F401 + from ._psutil_windows import IDLE_PRIORITY_CLASS # noqa: F401 + from ._psutil_windows import NORMAL_PRIORITY_CLASS # noqa: F401 + from ._psutil_windows import REALTIME_PRIORITY_CLASS # noqa: F401 + from ._pswindows import CONN_DELETE_TCB # noqa: F401 + from ._pswindows import IOPRIO_HIGH # noqa: F401 + from ._pswindows import IOPRIO_LOW # noqa: F401 + from ._pswindows import IOPRIO_NORMAL # noqa: F401 + from ._pswindows import IOPRIO_VERYLOW # noqa: F401 + +elif MACOS: + from . import _psosx as _psplatform + +elif BSD: + from . import _psbsd as _psplatform + +elif SUNOS: + from . import _pssunos as _psplatform + from ._pssunos import CONN_BOUND # noqa: F401 + from ._pssunos import CONN_IDLE # noqa: F401 + + # This is public writable API which is read from _pslinux.py and + # _pssunos.py via sys.modules. + PROCFS_PATH = "/proc" + +elif AIX: + from . import _psaix as _psplatform + + # This is public API and it will be retrieved from _pslinux.py + # via sys.modules. + PROCFS_PATH = "/proc" + +else: # pragma: no cover + msg = f"platform {sys.platform} is not supported" + raise NotImplementedError(msg) + + +# fmt: off +__all__ = [ + # exceptions + "Error", "NoSuchProcess", "ZombieProcess", "AccessDenied", + "TimeoutExpired", + + # constants + "version_info", "__version__", + + "STATUS_RUNNING", "STATUS_IDLE", "STATUS_SLEEPING", "STATUS_DISK_SLEEP", + "STATUS_STOPPED", "STATUS_TRACING_STOP", "STATUS_ZOMBIE", "STATUS_DEAD", + "STATUS_WAKING", "STATUS_LOCKED", "STATUS_WAITING", "STATUS_LOCKED", + "STATUS_PARKED", + + "CONN_ESTABLISHED", "CONN_SYN_SENT", "CONN_SYN_RECV", "CONN_FIN_WAIT1", + "CONN_FIN_WAIT2", "CONN_TIME_WAIT", "CONN_CLOSE", "CONN_CLOSE_WAIT", + "CONN_LAST_ACK", "CONN_LISTEN", "CONN_CLOSING", "CONN_NONE", + # "CONN_IDLE", "CONN_BOUND", + + "AF_LINK", + + "NIC_DUPLEX_FULL", "NIC_DUPLEX_HALF", "NIC_DUPLEX_UNKNOWN", + + "POWER_TIME_UNKNOWN", "POWER_TIME_UNLIMITED", + + "BSD", "FREEBSD", "LINUX", "NETBSD", "OPENBSD", "MACOS", "OSX", "POSIX", + "SUNOS", "WINDOWS", "AIX", + + # "RLIM_INFINITY", "RLIMIT_AS", "RLIMIT_CORE", "RLIMIT_CPU", "RLIMIT_DATA", + # "RLIMIT_FSIZE", "RLIMIT_LOCKS", "RLIMIT_MEMLOCK", "RLIMIT_NOFILE", + # "RLIMIT_NPROC", "RLIMIT_RSS", "RLIMIT_STACK", "RLIMIT_MSGQUEUE", + # "RLIMIT_NICE", "RLIMIT_RTPRIO", "RLIMIT_RTTIME", "RLIMIT_SIGPENDING", + + # classes + "Process", "Popen", + + # functions + "pid_exists", "pids", "process_iter", "wait_procs", # proc + "virtual_memory", "swap_memory", # memory + "cpu_times", "cpu_percent", "cpu_times_percent", "cpu_count", # cpu + "cpu_stats", # "cpu_freq", "getloadavg" + "net_io_counters", "net_connections", "net_if_addrs", # network + "net_if_stats", + "disk_io_counters", "disk_partitions", "disk_usage", # disk + # "sensors_temperatures", "sensors_battery", "sensors_fans" # sensors + "users", "boot_time", # others +] +# fmt: on + + +__all__.extend(_psplatform.__extra__all__) + +# Linux, FreeBSD +if hasattr(_psplatform.Process, "rlimit"): + # Populate global namespace with RLIM* constants. + from . import _psutil_posix + + _globals = globals() + _name = None + for _name in dir(_psutil_posix): + if _name.startswith('RLIM') and _name.isupper(): + _globals[_name] = getattr(_psutil_posix, _name) + __all__.append(_name) + del _globals, _name + +AF_LINK = _psplatform.AF_LINK + +__author__ = "Giampaolo Rodola'" +__version__ = "7.0.0" +version_info = tuple(int(num) for num in __version__.split('.')) + +_timer = getattr(time, 'monotonic', time.time) +_TOTAL_PHYMEM = None +_LOWEST_PID = None +_SENTINEL = object() + +# Sanity check in case the user messed up with psutil installation +# or did something weird with sys.path. In this case we might end +# up importing a python module using a C extension module which +# was compiled for a different version of psutil. +# We want to prevent that by failing sooner rather than later. +# See: https://github.com/giampaolo/psutil/issues/564 +if int(__version__.replace('.', '')) != getattr( + _psplatform.cext, 'version', None +): + msg = f"version conflict: {_psplatform.cext.__file__!r} C extension " + msg += "module was built for another version of psutil" + if hasattr(_psplatform.cext, 'version'): + v = ".".join(list(str(_psplatform.cext.version))) + msg += f" ({v} instead of {__version__})" + else: + msg += f" (different than {__version__})" + what = getattr( + _psplatform.cext, + "__file__", + "the existing psutil install directory", + ) + msg += f"; you may try to 'pip uninstall psutil', manually remove {what}" + msg += " or clean the virtual env somehow, then reinstall" + raise ImportError(msg) + + +# ===================================================================== +# --- Utils +# ===================================================================== + + +if hasattr(_psplatform, 'ppid_map'): + # Faster version (Windows and Linux). + _ppid_map = _psplatform.ppid_map +else: # pragma: no cover + + def _ppid_map(): + """Return a {pid: ppid, ...} dict for all running processes in + one shot. Used to speed up Process.children(). + """ + ret = {} + for pid in pids(): + try: + ret[pid] = _psplatform.Process(pid).ppid() + except (NoSuchProcess, ZombieProcess): + pass + return ret + + +def _pprint_secs(secs): + """Format seconds in a human readable form.""" + now = time.time() + secs_ago = int(now - secs) + fmt = "%H:%M:%S" if secs_ago < 60 * 60 * 24 else "%Y-%m-%d %H:%M:%S" + return datetime.datetime.fromtimestamp(secs).strftime(fmt) + + +def _check_conn_kind(kind): + """Check net_connections()'s `kind` parameter.""" + kinds = tuple(_common.conn_tmap) + if kind not in kinds: + msg = f"invalid kind argument {kind!r}; valid ones are: {kinds}" + raise ValueError(msg) + + +# ===================================================================== +# --- Process class +# ===================================================================== + + +class Process: + """Represents an OS process with the given PID. + If PID is omitted current process PID (os.getpid()) is used. + Raise NoSuchProcess if PID does not exist. + + Note that most of the methods of this class do not make sure that + the PID of the process being queried has been reused. That means + that you may end up retrieving information for another process. + + The only exceptions for which process identity is pre-emptively + checked and guaranteed are: + + - parent() + - children() + - nice() (set) + - ionice() (set) + - rlimit() (set) + - cpu_affinity (set) + - suspend() + - resume() + - send_signal() + - terminate() + - kill() + + To prevent this problem for all other methods you can use + is_running() before querying the process. + """ + + def __init__(self, pid=None): + self._init(pid) + + def _init(self, pid, _ignore_nsp=False): + if pid is None: + pid = os.getpid() + else: + if pid < 0: + msg = f"pid must be a positive integer (got {pid})" + raise ValueError(msg) + try: + _psplatform.cext.check_pid_range(pid) + except OverflowError as err: + msg = "process PID out of range" + raise NoSuchProcess(pid, msg=msg) from err + + self._pid = pid + self._name = None + self._exe = None + self._create_time = None + self._gone = False + self._pid_reused = False + self._hash = None + self._lock = threading.RLock() + # used for caching on Windows only (on POSIX ppid may change) + self._ppid = None + # platform-specific modules define an _psplatform.Process + # implementation class + self._proc = _psplatform.Process(pid) + self._last_sys_cpu_times = None + self._last_proc_cpu_times = None + self._exitcode = _SENTINEL + self._ident = (self.pid, None) + try: + self._ident = self._get_ident() + except AccessDenied: + # This should happen on Windows only, since we use the fast + # create time method. AFAIK, on all other platforms we are + # able to get create time for all PIDs. + pass + except ZombieProcess: + # Zombies can still be queried by this class (although + # not always) and pids() return them so just go on. + pass + except NoSuchProcess: + if not _ignore_nsp: + msg = "process PID not found" + raise NoSuchProcess(pid, msg=msg) from None + self._gone = True + + def _get_ident(self): + """Return a (pid, uid) tuple which is supposed to identify a + Process instance univocally over time. The PID alone is not + enough, as it can be assigned to a new process after this one + terminates, so we add process creation time to the mix. We need + this in order to prevent killing the wrong process later on. + This is also known as PID reuse or PID recycling problem. + + The reliability of this strategy mostly depends on + create_time() precision, which is 0.01 secs on Linux. The + assumption is that, after a process terminates, the kernel + won't reuse the same PID after such a short period of time + (0.01 secs). Technically this is inherently racy, but + practically it should be good enough. + """ + if WINDOWS: + # Use create_time() fast method in order to speedup + # `process_iter()`. This means we'll get AccessDenied for + # most ADMIN processes, but that's fine since it means + # we'll also get AccessDenied on kill(). + # https://github.com/giampaolo/psutil/issues/2366#issuecomment-2381646555 + self._create_time = self._proc.create_time(fast_only=True) + return (self.pid, self._create_time) + else: + return (self.pid, self.create_time()) + + def __str__(self): + info = collections.OrderedDict() + info["pid"] = self.pid + if self._name: + info['name'] = self._name + with self.oneshot(): + if self._pid_reused: + info["status"] = "terminated + PID reused" + else: + try: + info["name"] = self.name() + info["status"] = self.status() + except ZombieProcess: + info["status"] = "zombie" + except NoSuchProcess: + info["status"] = "terminated" + except AccessDenied: + pass + + if self._exitcode not in {_SENTINEL, None}: + info["exitcode"] = self._exitcode + if self._create_time is not None: + info['started'] = _pprint_secs(self._create_time) + + return "{}.{}({})".format( + self.__class__.__module__, + self.__class__.__name__, + ", ".join([f"{k}={v!r}" for k, v in info.items()]), + ) + + __repr__ = __str__ + + def __eq__(self, other): + # Test for equality with another Process object based + # on PID and creation time. + if not isinstance(other, Process): + return NotImplemented + if OPENBSD or NETBSD: # pragma: no cover + # Zombie processes on Open/NetBSD have a creation time of + # 0.0. This covers the case when a process started normally + # (so it has a ctime), then it turned into a zombie. It's + # important to do this because is_running() depends on + # __eq__. + pid1, ident1 = self._ident + pid2, ident2 = other._ident + if pid1 == pid2: + if ident1 and not ident2: + try: + return self.status() == STATUS_ZOMBIE + except Error: + pass + return self._ident == other._ident + + def __ne__(self, other): + return not self == other + + def __hash__(self): + if self._hash is None: + self._hash = hash(self._ident) + return self._hash + + def _raise_if_pid_reused(self): + """Raises NoSuchProcess in case process PID has been reused.""" + if self._pid_reused or (not self.is_running() and self._pid_reused): + # We may directly raise NSP in here already if PID is just + # not running, but I prefer NSP to be raised naturally by + # the actual Process API call. This way unit tests will tell + # us if the API is broken (aka don't raise NSP when it + # should). We also remain consistent with all other "get" + # APIs which don't use _raise_if_pid_reused(). + msg = "process no longer exists and its PID has been reused" + raise NoSuchProcess(self.pid, self._name, msg=msg) + + @property + def pid(self): + """The process PID.""" + return self._pid + + # --- utility methods + + @contextlib.contextmanager + def oneshot(self): + """Utility context manager which considerably speeds up the + retrieval of multiple process information at the same time. + + Internally different process info (e.g. name, ppid, uids, + gids, ...) may be fetched by using the same routine, but + only one information is returned and the others are discarded. + When using this context manager the internal routine is + executed once (in the example below on name()) and the + other info are cached. + + The cache is cleared when exiting the context manager block. + The advice is to use this every time you retrieve more than + one information about the process. If you're lucky, you'll + get a hell of a speedup. + + >>> import psutil + >>> p = psutil.Process() + >>> with p.oneshot(): + ... p.name() # collect multiple info + ... p.cpu_times() # return cached value + ... p.cpu_percent() # return cached value + ... p.create_time() # return cached value + ... + >>> + """ + with self._lock: + if hasattr(self, "_cache"): + # NOOP: this covers the use case where the user enters the + # context twice: + # + # >>> with p.oneshot(): + # ... with p.oneshot(): + # ... + # + # Also, since as_dict() internally uses oneshot() + # I expect that the code below will be a pretty common + # "mistake" that the user will make, so let's guard + # against that: + # + # >>> with p.oneshot(): + # ... p.as_dict() + # ... + yield + else: + try: + # cached in case cpu_percent() is used + self.cpu_times.cache_activate(self) + # cached in case memory_percent() is used + self.memory_info.cache_activate(self) + # cached in case parent() is used + self.ppid.cache_activate(self) + # cached in case username() is used + if POSIX: + self.uids.cache_activate(self) + # specific implementation cache + self._proc.oneshot_enter() + yield + finally: + self.cpu_times.cache_deactivate(self) + self.memory_info.cache_deactivate(self) + self.ppid.cache_deactivate(self) + if POSIX: + self.uids.cache_deactivate(self) + self._proc.oneshot_exit() + + def as_dict(self, attrs=None, ad_value=None): + """Utility method returning process information as a + hashable dictionary. + If *attrs* is specified it must be a list of strings + reflecting available Process class' attribute names + (e.g. ['cpu_times', 'name']) else all public (read + only) attributes are assumed. + *ad_value* is the value which gets assigned in case + AccessDenied or ZombieProcess exception is raised when + retrieving that particular process information. + """ + valid_names = _as_dict_attrnames + if attrs is not None: + if not isinstance(attrs, (list, tuple, set, frozenset)): + msg = f"invalid attrs type {type(attrs)}" + raise TypeError(msg) + attrs = set(attrs) + invalid_names = attrs - valid_names + if invalid_names: + msg = "invalid attr name{} {}".format( + "s" if len(invalid_names) > 1 else "", + ", ".join(map(repr, invalid_names)), + ) + raise ValueError(msg) + + retdict = {} + ls = attrs or valid_names + with self.oneshot(): + for name in ls: + try: + if name == 'pid': + ret = self.pid + else: + meth = getattr(self, name) + ret = meth() + except (AccessDenied, ZombieProcess): + ret = ad_value + except NotImplementedError: + # in case of not implemented functionality (may happen + # on old or exotic systems) we want to crash only if + # the user explicitly asked for that particular attr + if attrs: + raise + continue + retdict[name] = ret + return retdict + + def parent(self): + """Return the parent process as a Process object pre-emptively + checking whether PID has been reused. + If no parent is known return None. + """ + lowest_pid = _LOWEST_PID if _LOWEST_PID is not None else pids()[0] + if self.pid == lowest_pid: + return None + ppid = self.ppid() + if ppid is not None: + ctime = self.create_time() + try: + parent = Process(ppid) + if parent.create_time() <= ctime: + return parent + # ...else ppid has been reused by another process + except NoSuchProcess: + pass + + def parents(self): + """Return the parents of this process as a list of Process + instances. If no parents are known return an empty list. + """ + parents = [] + proc = self.parent() + while proc is not None: + parents.append(proc) + proc = proc.parent() + return parents + + def is_running(self): + """Return whether this process is running. + + It also checks if PID has been reused by another process, in + which case it will remove the process from `process_iter()` + internal cache and return False. + """ + if self._gone or self._pid_reused: + return False + try: + # Checking if PID is alive is not enough as the PID might + # have been reused by another process. Process identity / + # uniqueness over time is guaranteed by (PID + creation + # time) and that is verified in __eq__. + self._pid_reused = self != Process(self.pid) + if self._pid_reused: + _pids_reused.add(self.pid) + raise NoSuchProcess(self.pid) + return True + except ZombieProcess: + # We should never get here as it's already handled in + # Process.__init__; here just for extra safety. + return True + except NoSuchProcess: + self._gone = True + return False + + # --- actual API + + @memoize_when_activated + def ppid(self): + """The process parent PID. + On Windows the return value is cached after first call. + """ + # On POSIX we don't want to cache the ppid as it may unexpectedly + # change to 1 (init) in case this process turns into a zombie: + # https://github.com/giampaolo/psutil/issues/321 + # http://stackoverflow.com/questions/356722/ + + # XXX should we check creation time here rather than in + # Process.parent()? + self._raise_if_pid_reused() + if POSIX: + return self._proc.ppid() + else: # pragma: no cover + self._ppid = self._ppid or self._proc.ppid() + return self._ppid + + def name(self): + """The process name. The return value is cached after first call.""" + # Process name is only cached on Windows as on POSIX it may + # change, see: + # https://github.com/giampaolo/psutil/issues/692 + if WINDOWS and self._name is not None: + return self._name + name = self._proc.name() + if POSIX and len(name) >= 15: + # On UNIX the name gets truncated to the first 15 characters. + # If it matches the first part of the cmdline we return that + # one instead because it's usually more explicative. + # Examples are "gnome-keyring-d" vs. "gnome-keyring-daemon". + try: + cmdline = self.cmdline() + except (AccessDenied, ZombieProcess): + # Just pass and return the truncated name: it's better + # than nothing. Note: there are actual cases where a + # zombie process can return a name() but not a + # cmdline(), see: + # https://github.com/giampaolo/psutil/issues/2239 + pass + else: + if cmdline: + extended_name = os.path.basename(cmdline[0]) + if extended_name.startswith(name): + name = extended_name + self._name = name + self._proc._name = name + return name + + def exe(self): + """The process executable as an absolute path. + May also be an empty string. + The return value is cached after first call. + """ + + def guess_it(fallback): + # try to guess exe from cmdline[0] in absence of a native + # exe representation + cmdline = self.cmdline() + if cmdline and hasattr(os, 'access') and hasattr(os, 'X_OK'): + exe = cmdline[0] # the possible exe + # Attempt to guess only in case of an absolute path. + # It is not safe otherwise as the process might have + # changed cwd. + if ( + os.path.isabs(exe) + and os.path.isfile(exe) + and os.access(exe, os.X_OK) + ): + return exe + if isinstance(fallback, AccessDenied): + raise fallback + return fallback + + if self._exe is None: + try: + exe = self._proc.exe() + except AccessDenied as err: + return guess_it(fallback=err) + else: + if not exe: + # underlying implementation can legitimately return an + # empty string; if that's the case we don't want to + # raise AD while guessing from the cmdline + try: + exe = guess_it(fallback=exe) + except AccessDenied: + pass + self._exe = exe + return self._exe + + def cmdline(self): + """The command line this process has been called with.""" + return self._proc.cmdline() + + def status(self): + """The process current status as a STATUS_* constant.""" + try: + return self._proc.status() + except ZombieProcess: + return STATUS_ZOMBIE + + def username(self): + """The name of the user that owns the process. + On UNIX this is calculated by using *real* process uid. + """ + if POSIX: + if pwd is None: + # might happen if python was installed from sources + msg = "requires pwd module shipped with standard python" + raise ImportError(msg) + real_uid = self.uids().real + try: + return pwd.getpwuid(real_uid).pw_name + except KeyError: + # the uid can't be resolved by the system + return str(real_uid) + else: + return self._proc.username() + + def create_time(self): + """The process creation time as a floating point number + expressed in seconds since the epoch. + The return value is cached after first call. + """ + if self._create_time is None: + self._create_time = self._proc.create_time() + return self._create_time + + def cwd(self): + """Process current working directory as an absolute path.""" + return self._proc.cwd() + + def nice(self, value=None): + """Get or set process niceness (priority).""" + if value is None: + return self._proc.nice_get() + else: + self._raise_if_pid_reused() + self._proc.nice_set(value) + + if POSIX: + + @memoize_when_activated + def uids(self): + """Return process UIDs as a (real, effective, saved) + namedtuple. + """ + return self._proc.uids() + + def gids(self): + """Return process GIDs as a (real, effective, saved) + namedtuple. + """ + return self._proc.gids() + + def terminal(self): + """The terminal associated with this process, if any, + else None. + """ + return self._proc.terminal() + + def num_fds(self): + """Return the number of file descriptors opened by this + process (POSIX only). + """ + return self._proc.num_fds() + + # Linux, BSD, AIX and Windows only + if hasattr(_psplatform.Process, "io_counters"): + + def io_counters(self): + """Return process I/O statistics as a + (read_count, write_count, read_bytes, write_bytes) + namedtuple. + Those are the number of read/write calls performed and the + amount of bytes read and written by the process. + """ + return self._proc.io_counters() + + # Linux and Windows + if hasattr(_psplatform.Process, "ionice_get"): + + def ionice(self, ioclass=None, value=None): + """Get or set process I/O niceness (priority). + + On Linux *ioclass* is one of the IOPRIO_CLASS_* constants. + *value* is a number which goes from 0 to 7. The higher the + value, the lower the I/O priority of the process. + + On Windows only *ioclass* is used and it can be set to 2 + (normal), 1 (low) or 0 (very low). + + Available on Linux and Windows > Vista only. + """ + if ioclass is None: + if value is not None: + msg = "'ioclass' argument must be specified" + raise ValueError(msg) + return self._proc.ionice_get() + else: + self._raise_if_pid_reused() + return self._proc.ionice_set(ioclass, value) + + # Linux / FreeBSD only + if hasattr(_psplatform.Process, "rlimit"): + + def rlimit(self, resource, limits=None): + """Get or set process resource limits as a (soft, hard) + tuple. + + *resource* is one of the RLIMIT_* constants. + *limits* is supposed to be a (soft, hard) tuple. + + See "man prlimit" for further info. + Available on Linux and FreeBSD only. + """ + if limits is not None: + self._raise_if_pid_reused() + return self._proc.rlimit(resource, limits) + + # Windows, Linux and FreeBSD only + if hasattr(_psplatform.Process, "cpu_affinity_get"): + + def cpu_affinity(self, cpus=None): + """Get or set process CPU affinity. + If specified, *cpus* must be a list of CPUs for which you + want to set the affinity (e.g. [0, 1]). + If an empty list is passed, all egible CPUs are assumed + (and set). + (Windows, Linux and BSD only). + """ + if cpus is None: + return sorted(set(self._proc.cpu_affinity_get())) + else: + self._raise_if_pid_reused() + if not cpus: + if hasattr(self._proc, "_get_eligible_cpus"): + cpus = self._proc._get_eligible_cpus() + else: + cpus = tuple(range(len(cpu_times(percpu=True)))) + self._proc.cpu_affinity_set(list(set(cpus))) + + # Linux, FreeBSD, SunOS + if hasattr(_psplatform.Process, "cpu_num"): + + def cpu_num(self): + """Return what CPU this process is currently running on. + The returned number should be <= psutil.cpu_count() + and <= len(psutil.cpu_percent(percpu=True)). + It may be used in conjunction with + psutil.cpu_percent(percpu=True) to observe the system + workload distributed across CPUs. + """ + return self._proc.cpu_num() + + # All platforms has it, but maybe not in the future. + if hasattr(_psplatform.Process, "environ"): + + def environ(self): + """The environment variables of the process as a dict. Note: this + might not reflect changes made after the process started. + """ + return self._proc.environ() + + if WINDOWS: + + def num_handles(self): + """Return the number of handles opened by this process + (Windows only). + """ + return self._proc.num_handles() + + def num_ctx_switches(self): + """Return the number of voluntary and involuntary context + switches performed by this process. + """ + return self._proc.num_ctx_switches() + + def num_threads(self): + """Return the number of threads used by this process.""" + return self._proc.num_threads() + + if hasattr(_psplatform.Process, "threads"): + + def threads(self): + """Return threads opened by process as a list of + (id, user_time, system_time) namedtuples representing + thread id and thread CPU times (user/system). + On OpenBSD this method requires root access. + """ + return self._proc.threads() + + def children(self, recursive=False): + """Return the children of this process as a list of Process + instances, pre-emptively checking whether PID has been reused. + If *recursive* is True return all the parent descendants. + + Example (A == this process): + + A ─┐ + │ + ├─ B (child) ─┐ + │ └─ X (grandchild) ─┐ + │ └─ Y (great grandchild) + ├─ C (child) + └─ D (child) + + >>> import psutil + >>> p = psutil.Process() + >>> p.children() + B, C, D + >>> p.children(recursive=True) + B, X, Y, C, D + + Note that in the example above if process X disappears + process Y won't be listed as the reference to process A + is lost. + """ + self._raise_if_pid_reused() + ppid_map = _ppid_map() + ret = [] + if not recursive: + for pid, ppid in ppid_map.items(): + if ppid == self.pid: + try: + child = Process(pid) + # if child happens to be older than its parent + # (self) it means child's PID has been reused + if self.create_time() <= child.create_time(): + ret.append(child) + except (NoSuchProcess, ZombieProcess): + pass + else: + # Construct a {pid: [child pids]} dict + reverse_ppid_map = collections.defaultdict(list) + for pid, ppid in ppid_map.items(): + reverse_ppid_map[ppid].append(pid) + # Recursively traverse that dict, starting from self.pid, + # such that we only call Process() on actual children + seen = set() + stack = [self.pid] + while stack: + pid = stack.pop() + if pid in seen: + # Since pids can be reused while the ppid_map is + # constructed, there may be rare instances where + # there's a cycle in the recorded process "tree". + continue + seen.add(pid) + for child_pid in reverse_ppid_map[pid]: + try: + child = Process(child_pid) + # if child happens to be older than its parent + # (self) it means child's PID has been reused + intime = self.create_time() <= child.create_time() + if intime: + ret.append(child) + stack.append(child_pid) + except (NoSuchProcess, ZombieProcess): + pass + return ret + + def cpu_percent(self, interval=None): + """Return a float representing the current process CPU + utilization as a percentage. + + When *interval* is 0.0 or None (default) compares process times + to system CPU times elapsed since last call, returning + immediately (non-blocking). That means that the first time + this is called it will return a meaningful 0.0 value. + + When *interval* is > 0.0 compares process times to system CPU + times elapsed before and after the interval (blocking). + + In this case is recommended for accuracy that this function + be called with at least 0.1 seconds between calls. + + A value > 100.0 can be returned in case of processes running + multiple threads on different CPU cores. + + The returned value is explicitly NOT split evenly between + all available logical CPUs. This means that a busy loop process + running on a system with 2 logical CPUs will be reported as + having 100% CPU utilization instead of 50%. + + Examples: + + >>> import psutil + >>> p = psutil.Process(os.getpid()) + >>> # blocking + >>> p.cpu_percent(interval=1) + 2.0 + >>> # non-blocking (percentage since last call) + >>> p.cpu_percent(interval=None) + 2.9 + >>> + """ + blocking = interval is not None and interval > 0.0 + if interval is not None and interval < 0: + msg = f"interval is not positive (got {interval!r})" + raise ValueError(msg) + num_cpus = cpu_count() or 1 + + def timer(): + return _timer() * num_cpus + + if blocking: + st1 = timer() + pt1 = self._proc.cpu_times() + time.sleep(interval) + st2 = timer() + pt2 = self._proc.cpu_times() + else: + st1 = self._last_sys_cpu_times + pt1 = self._last_proc_cpu_times + st2 = timer() + pt2 = self._proc.cpu_times() + if st1 is None or pt1 is None: + self._last_sys_cpu_times = st2 + self._last_proc_cpu_times = pt2 + return 0.0 + + delta_proc = (pt2.user - pt1.user) + (pt2.system - pt1.system) + delta_time = st2 - st1 + # reset values for next call in case of interval == None + self._last_sys_cpu_times = st2 + self._last_proc_cpu_times = pt2 + + try: + # This is the utilization split evenly between all CPUs. + # E.g. a busy loop process on a 2-CPU-cores system at this + # point is reported as 50% instead of 100%. + overall_cpus_percent = (delta_proc / delta_time) * 100 + except ZeroDivisionError: + # interval was too low + return 0.0 + else: + # Note 1: + # in order to emulate "top" we multiply the value for the num + # of CPU cores. This way the busy process will be reported as + # having 100% (or more) usage. + # + # Note 2: + # taskmgr.exe on Windows differs in that it will show 50% + # instead. + # + # Note 3: + # a percentage > 100 is legitimate as it can result from a + # process with multiple threads running on different CPU + # cores (top does the same), see: + # http://stackoverflow.com/questions/1032357 + # https://github.com/giampaolo/psutil/issues/474 + single_cpu_percent = overall_cpus_percent * num_cpus + return round(single_cpu_percent, 1) + + @memoize_when_activated + def cpu_times(self): + """Return a (user, system, children_user, children_system) + namedtuple representing the accumulated process time, in + seconds. + This is similar to os.times() but per-process. + On macOS and Windows children_user and children_system are + always set to 0. + """ + return self._proc.cpu_times() + + @memoize_when_activated + def memory_info(self): + """Return a namedtuple with variable fields depending on the + platform, representing memory information about the process. + + The "portable" fields available on all platforms are `rss` and `vms`. + + All numbers are expressed in bytes. + """ + return self._proc.memory_info() + + def memory_full_info(self): + """This method returns the same information as memory_info(), + plus, on some platform (Linux, macOS, Windows), also provides + additional metrics (USS, PSS and swap). + The additional metrics provide a better representation of actual + process memory usage. + + Namely USS is the memory which is unique to a process and which + would be freed if the process was terminated right now. + + It does so by passing through the whole process address. + As such it usually requires higher user privileges than + memory_info() and is considerably slower. + """ + return self._proc.memory_full_info() + + def memory_percent(self, memtype="rss"): + """Compare process memory to total physical system memory and + calculate process memory utilization as a percentage. + *memtype* argument is a string that dictates what type of + process memory you want to compare against (defaults to "rss"). + The list of available strings can be obtained like this: + + >>> psutil.Process().memory_info()._fields + ('rss', 'vms', 'shared', 'text', 'lib', 'data', 'dirty', 'uss', 'pss') + """ + valid_types = list(_psplatform.pfullmem._fields) + if memtype not in valid_types: + msg = ( + f"invalid memtype {memtype!r}; valid types are" + f" {tuple(valid_types)!r}" + ) + raise ValueError(msg) + fun = ( + self.memory_info + if memtype in _psplatform.pmem._fields + else self.memory_full_info + ) + metrics = fun() + value = getattr(metrics, memtype) + + # use cached value if available + total_phymem = _TOTAL_PHYMEM or virtual_memory().total + if not total_phymem > 0: + # we should never get here + msg = ( + "can't calculate process memory percent because total physical" + f" system memory is not positive ({total_phymem!r})" + ) + raise ValueError(msg) + return (value / float(total_phymem)) * 100 + + if hasattr(_psplatform.Process, "memory_maps"): + + def memory_maps(self, grouped=True): + """Return process' mapped memory regions as a list of namedtuples + whose fields are variable depending on the platform. + + If *grouped* is True the mapped regions with the same 'path' + are grouped together and the different memory fields are summed. + + If *grouped* is False every mapped region is shown as a single + entity and the namedtuple will also include the mapped region's + address space ('addr') and permission set ('perms'). + """ + it = self._proc.memory_maps() + if grouped: + d = {} + for tupl in it: + path = tupl[2] + nums = tupl[3:] + try: + d[path] = list(map(lambda x, y: x + y, d[path], nums)) + except KeyError: + d[path] = nums + nt = _psplatform.pmmap_grouped + return [nt(path, *d[path]) for path in d] + else: + nt = _psplatform.pmmap_ext + return [nt(*x) for x in it] + + def open_files(self): + """Return files opened by process as a list of + (path, fd) namedtuples including the absolute file name + and file descriptor number. + """ + return self._proc.open_files() + + def net_connections(self, kind='inet'): + """Return socket connections opened by process as a list of + (fd, family, type, laddr, raddr, status) namedtuples. + The *kind* parameter filters for connections that match the + following criteria: + + +------------+----------------------------------------------------+ + | Kind Value | Connections using | + +------------+----------------------------------------------------+ + | inet | IPv4 and IPv6 | + | inet4 | IPv4 | + | inet6 | IPv6 | + | tcp | TCP | + | tcp4 | TCP over IPv4 | + | tcp6 | TCP over IPv6 | + | udp | UDP | + | udp4 | UDP over IPv4 | + | udp6 | UDP over IPv6 | + | unix | UNIX socket (both UDP and TCP protocols) | + | all | the sum of all the possible families and protocols | + +------------+----------------------------------------------------+ + """ + _check_conn_kind(kind) + return self._proc.net_connections(kind) + + @_common.deprecated_method(replacement="net_connections") + def connections(self, kind="inet"): + return self.net_connections(kind=kind) + + # --- signals + + if POSIX: + + def _send_signal(self, sig): + assert not self.pid < 0, self.pid + self._raise_if_pid_reused() + + pid, ppid, name = self.pid, self._ppid, self._name + if pid == 0: + # see "man 2 kill" + msg = ( + "preventing sending signal to process with PID 0 as it " + "would affect every process in the process group of the " + "calling process (os.getpid()) instead of PID 0" + ) + raise ValueError(msg) + try: + os.kill(pid, sig) + except ProcessLookupError as err: + if OPENBSD and pid_exists(pid): + # We do this because os.kill() lies in case of + # zombie processes. + raise ZombieProcess(pid, name, ppid) from err + self._gone = True + raise NoSuchProcess(pid, name) from err + except PermissionError as err: + raise AccessDenied(pid, name) from err + + def send_signal(self, sig): + """Send a signal *sig* to process pre-emptively checking + whether PID has been reused (see signal module constants) . + On Windows only SIGTERM is valid and is treated as an alias + for kill(). + """ + if POSIX: + self._send_signal(sig) + else: # pragma: no cover + self._raise_if_pid_reused() + if sig != signal.SIGTERM and not self.is_running(): + msg = "process no longer exists" + raise NoSuchProcess(self.pid, self._name, msg=msg) + self._proc.send_signal(sig) + + def suspend(self): + """Suspend process execution with SIGSTOP pre-emptively checking + whether PID has been reused. + On Windows this has the effect of suspending all process threads. + """ + if POSIX: + self._send_signal(signal.SIGSTOP) + else: # pragma: no cover + self._raise_if_pid_reused() + self._proc.suspend() + + def resume(self): + """Resume process execution with SIGCONT pre-emptively checking + whether PID has been reused. + On Windows this has the effect of resuming all process threads. + """ + if POSIX: + self._send_signal(signal.SIGCONT) + else: # pragma: no cover + self._raise_if_pid_reused() + self._proc.resume() + + def terminate(self): + """Terminate the process with SIGTERM pre-emptively checking + whether PID has been reused. + On Windows this is an alias for kill(). + """ + if POSIX: + self._send_signal(signal.SIGTERM) + else: # pragma: no cover + self._raise_if_pid_reused() + self._proc.kill() + + def kill(self): + """Kill the current process with SIGKILL pre-emptively checking + whether PID has been reused. + """ + if POSIX: + self._send_signal(signal.SIGKILL) + else: # pragma: no cover + self._raise_if_pid_reused() + self._proc.kill() + + def wait(self, timeout=None): + """Wait for process to terminate and, if process is a children + of os.getpid(), also return its exit code, else None. + On Windows there's no such limitation (exit code is always + returned). + + If the process is already terminated immediately return None + instead of raising NoSuchProcess. + + If *timeout* (in seconds) is specified and process is still + alive raise TimeoutExpired. + + To wait for multiple Process(es) use psutil.wait_procs(). + """ + if timeout is not None and not timeout >= 0: + msg = "timeout must be a positive integer" + raise ValueError(msg) + if self._exitcode is not _SENTINEL: + return self._exitcode + self._exitcode = self._proc.wait(timeout) + return self._exitcode + + +# The valid attr names which can be processed by Process.as_dict(). +# fmt: off +_as_dict_attrnames = { + x for x in dir(Process) if not x.startswith("_") and x not in + {'send_signal', 'suspend', 'resume', 'terminate', 'kill', 'wait', + 'is_running', 'as_dict', 'parent', 'parents', 'children', 'rlimit', + 'connections', 'oneshot'} +} +# fmt: on + + +# ===================================================================== +# --- Popen class +# ===================================================================== + + +class Popen(Process): + """Same as subprocess.Popen, but in addition it provides all + psutil.Process methods in a single class. + For the following methods which are common to both classes, psutil + implementation takes precedence: + + * send_signal() + * terminate() + * kill() + + This is done in order to avoid killing another process in case its + PID has been reused, fixing BPO-6973. + + >>> import psutil + >>> from subprocess import PIPE + >>> p = psutil.Popen(["python", "-c", "print 'hi'"], stdout=PIPE) + >>> p.name() + 'python' + >>> p.uids() + user(real=1000, effective=1000, saved=1000) + >>> p.username() + 'giampaolo' + >>> p.communicate() + ('hi', None) + >>> p.terminate() + >>> p.wait(timeout=2) + 0 + >>> + """ + + def __init__(self, *args, **kwargs): + # Explicitly avoid to raise NoSuchProcess in case the process + # spawned by subprocess.Popen terminates too quickly, see: + # https://github.com/giampaolo/psutil/issues/193 + self.__subproc = subprocess.Popen(*args, **kwargs) + self._init(self.__subproc.pid, _ignore_nsp=True) + + def __dir__(self): + return sorted(set(dir(Popen) + dir(subprocess.Popen))) + + def __enter__(self): + if hasattr(self.__subproc, '__enter__'): + self.__subproc.__enter__() + return self + + def __exit__(self, *args, **kwargs): + if hasattr(self.__subproc, '__exit__'): + return self.__subproc.__exit__(*args, **kwargs) + else: + if self.stdout: + self.stdout.close() + if self.stderr: + self.stderr.close() + try: + # Flushing a BufferedWriter may raise an error. + if self.stdin: + self.stdin.close() + finally: + # Wait for the process to terminate, to avoid zombies. + self.wait() + + def __getattribute__(self, name): + try: + return object.__getattribute__(self, name) + except AttributeError: + try: + return object.__getattribute__(self.__subproc, name) + except AttributeError: + msg = f"{self.__class__!r} has no attribute {name!r}" + raise AttributeError(msg) from None + + def wait(self, timeout=None): + if self.__subproc.returncode is not None: + return self.__subproc.returncode + ret = super().wait(timeout) + self.__subproc.returncode = ret + return ret + + +# ===================================================================== +# --- system processes related functions +# ===================================================================== + + +def pids(): + """Return a list of current running PIDs.""" + global _LOWEST_PID + ret = sorted(_psplatform.pids()) + _LOWEST_PID = ret[0] + return ret + + +def pid_exists(pid): + """Return True if given PID exists in the current process list. + This is faster than doing "pid in psutil.pids()" and + should be preferred. + """ + if pid < 0: + return False + elif pid == 0 and POSIX: + # On POSIX we use os.kill() to determine PID existence. + # According to "man 2 kill" PID 0 has a special meaning + # though: it refers to <> and that is not we want + # to do here. + return pid in pids() + else: + return _psplatform.pid_exists(pid) + + +_pmap = {} +_pids_reused = set() + + +def process_iter(attrs=None, ad_value=None): + """Return a generator yielding a Process instance for all + running processes. + + Every new Process instance is only created once and then cached + into an internal table which is updated every time this is used. + Cache can optionally be cleared via `process_iter.clear_cache()`. + + The sorting order in which processes are yielded is based on + their PIDs. + + *attrs* and *ad_value* have the same meaning as in + Process.as_dict(). If *attrs* is specified as_dict() is called + and the resulting dict is stored as a 'info' attribute attached + to returned Process instance. + If *attrs* is an empty list it will retrieve all process info + (slow). + """ + global _pmap + + def add(pid): + proc = Process(pid) + pmap[proc.pid] = proc + return proc + + def remove(pid): + pmap.pop(pid, None) + + pmap = _pmap.copy() + a = set(pids()) + b = set(pmap.keys()) + new_pids = a - b + gone_pids = b - a + for pid in gone_pids: + remove(pid) + while _pids_reused: + pid = _pids_reused.pop() + debug(f"refreshing Process instance for reused PID {pid}") + remove(pid) + try: + ls = sorted(list(pmap.items()) + list(dict.fromkeys(new_pids).items())) + for pid, proc in ls: + try: + if proc is None: # new process + proc = add(pid) + if attrs is not None: + proc.info = proc.as_dict(attrs=attrs, ad_value=ad_value) + yield proc + except NoSuchProcess: + remove(pid) + finally: + _pmap = pmap + + +process_iter.cache_clear = lambda: _pmap.clear() # noqa: PLW0108 +process_iter.cache_clear.__doc__ = "Clear process_iter() internal cache." + + +def wait_procs(procs, timeout=None, callback=None): + """Convenience function which waits for a list of processes to + terminate. + + Return a (gone, alive) tuple indicating which processes + are gone and which ones are still alive. + + The gone ones will have a new *returncode* attribute indicating + process exit status (may be None). + + *callback* is a function which gets called every time a process + terminates (a Process instance is passed as callback argument). + + Function will return as soon as all processes terminate or when + *timeout* occurs. + Differently from Process.wait() it will not raise TimeoutExpired if + *timeout* occurs. + + Typical use case is: + + - send SIGTERM to a list of processes + - give them some time to terminate + - send SIGKILL to those ones which are still alive + + Example: + + >>> def on_terminate(proc): + ... print("process {} terminated".format(proc)) + ... + >>> for p in procs: + ... p.terminate() + ... + >>> gone, alive = wait_procs(procs, timeout=3, callback=on_terminate) + >>> for p in alive: + ... p.kill() + """ + + def check_gone(proc, timeout): + try: + returncode = proc.wait(timeout=timeout) + except (TimeoutExpired, subprocess.TimeoutExpired): + pass + else: + if returncode is not None or not proc.is_running(): + # Set new Process instance attribute. + proc.returncode = returncode + gone.add(proc) + if callback is not None: + callback(proc) + + if timeout is not None and not timeout >= 0: + msg = f"timeout must be a positive integer, got {timeout}" + raise ValueError(msg) + gone = set() + alive = set(procs) + if callback is not None and not callable(callback): + msg = f"callback {callback!r} is not a callable" + raise TypeError(msg) + if timeout is not None: + deadline = _timer() + timeout + + while alive: + if timeout is not None and timeout <= 0: + break + for proc in alive: + # Make sure that every complete iteration (all processes) + # will last max 1 sec. + # We do this because we don't want to wait too long on a + # single process: in case it terminates too late other + # processes may disappear in the meantime and their PID + # reused. + max_timeout = 1.0 / len(alive) + if timeout is not None: + timeout = min((deadline - _timer()), max_timeout) + if timeout <= 0: + break + check_gone(proc, timeout) + else: + check_gone(proc, max_timeout) + alive = alive - gone # noqa: PLR6104 + + if alive: + # Last attempt over processes survived so far. + # timeout == 0 won't make this function wait any further. + for proc in alive: + check_gone(proc, 0) + alive = alive - gone # noqa: PLR6104 + + return (list(gone), list(alive)) + + +# ===================================================================== +# --- CPU related functions +# ===================================================================== + + +def cpu_count(logical=True): + """Return the number of logical CPUs in the system (same as + os.cpu_count()). + + If *logical* is False return the number of physical cores only + (e.g. hyper thread CPUs are excluded). + + Return None if undetermined. + + The return value is cached after first call. + If desired cache can be cleared like this: + + >>> psutil.cpu_count.cache_clear() + """ + if logical: + ret = _psplatform.cpu_count_logical() + else: + ret = _psplatform.cpu_count_cores() + if ret is not None and ret < 1: + ret = None + return ret + + +def cpu_times(percpu=False): + """Return system-wide CPU times as a namedtuple. + Every CPU time represents the seconds the CPU has spent in the + given mode. The namedtuple's fields availability varies depending on the + platform: + + - user + - system + - idle + - nice (UNIX) + - iowait (Linux) + - irq (Linux, FreeBSD) + - softirq (Linux) + - steal (Linux >= 2.6.11) + - guest (Linux >= 2.6.24) + - guest_nice (Linux >= 3.2.0) + + When *percpu* is True return a list of namedtuples for each CPU. + First element of the list refers to first CPU, second element + to second CPU and so on. + The order of the list is consistent across calls. + """ + if not percpu: + return _psplatform.cpu_times() + else: + return _psplatform.per_cpu_times() + + +try: + _last_cpu_times = {threading.current_thread().ident: cpu_times()} +except Exception: # noqa: BLE001 + # Don't want to crash at import time. + _last_cpu_times = {} + +try: + _last_per_cpu_times = { + threading.current_thread().ident: cpu_times(percpu=True) + } +except Exception: # noqa: BLE001 + # Don't want to crash at import time. + _last_per_cpu_times = {} + + +def _cpu_tot_time(times): + """Given a cpu_time() ntuple calculates the total CPU time + (including idle time). + """ + tot = sum(times) + if LINUX: + # On Linux guest times are already accounted in "user" or + # "nice" times, so we subtract them from total. + # Htop does the same. References: + # https://github.com/giampaolo/psutil/pull/940 + # http://unix.stackexchange.com/questions/178045 + # https://github.com/torvalds/linux/blob/ + # 447976ef4fd09b1be88b316d1a81553f1aa7cd07/kernel/sched/ + # cputime.c#L158 + tot -= getattr(times, "guest", 0) # Linux 2.6.24+ + tot -= getattr(times, "guest_nice", 0) # Linux 3.2.0+ + return tot + + +def _cpu_busy_time(times): + """Given a cpu_time() ntuple calculates the busy CPU time. + We do so by subtracting all idle CPU times. + """ + busy = _cpu_tot_time(times) + busy -= times.idle + # Linux: "iowait" is time during which the CPU does not do anything + # (waits for IO to complete). On Linux IO wait is *not* accounted + # in "idle" time so we subtract it. Htop does the same. + # References: + # https://github.com/torvalds/linux/blob/ + # 447976ef4fd09b1be88b316d1a81553f1aa7cd07/kernel/sched/cputime.c#L244 + busy -= getattr(times, "iowait", 0) + return busy + + +def _cpu_times_deltas(t1, t2): + assert t1._fields == t2._fields, (t1, t2) + field_deltas = [] + for field in _psplatform.scputimes._fields: + field_delta = getattr(t2, field) - getattr(t1, field) + # CPU times are always supposed to increase over time + # or at least remain the same and that's because time + # cannot go backwards. + # Surprisingly sometimes this might not be the case (at + # least on Windows and Linux), see: + # https://github.com/giampaolo/psutil/issues/392 + # https://github.com/giampaolo/psutil/issues/645 + # https://github.com/giampaolo/psutil/issues/1210 + # Trim negative deltas to zero to ignore decreasing fields. + # top does the same. Reference: + # https://gitlab.com/procps-ng/procps/blob/v3.3.12/top/top.c#L5063 + field_delta = max(0, field_delta) + field_deltas.append(field_delta) + return _psplatform.scputimes(*field_deltas) + + +def cpu_percent(interval=None, percpu=False): + """Return a float representing the current system-wide CPU + utilization as a percentage. + + When *interval* is > 0.0 compares system CPU times elapsed before + and after the interval (blocking). + + When *interval* is 0.0 or None compares system CPU times elapsed + since last call or module import, returning immediately (non + blocking). That means the first time this is called it will + return a meaningless 0.0 value which you should ignore. + In this case is recommended for accuracy that this function be + called with at least 0.1 seconds between calls. + + When *percpu* is True returns a list of floats representing the + utilization as a percentage for each CPU. + First element of the list refers to first CPU, second element + to second CPU and so on. + The order of the list is consistent across calls. + + Examples: + + >>> # blocking, system-wide + >>> psutil.cpu_percent(interval=1) + 2.0 + >>> + >>> # blocking, per-cpu + >>> psutil.cpu_percent(interval=1, percpu=True) + [2.0, 1.0] + >>> + >>> # non-blocking (percentage since last call) + >>> psutil.cpu_percent(interval=None) + 2.9 + >>> + """ + tid = threading.current_thread().ident + blocking = interval is not None and interval > 0.0 + if interval is not None and interval < 0: + msg = f"interval is not positive (got {interval})" + raise ValueError(msg) + + def calculate(t1, t2): + times_delta = _cpu_times_deltas(t1, t2) + all_delta = _cpu_tot_time(times_delta) + busy_delta = _cpu_busy_time(times_delta) + + try: + busy_perc = (busy_delta / all_delta) * 100 + except ZeroDivisionError: + return 0.0 + else: + return round(busy_perc, 1) + + # system-wide usage + if not percpu: + if blocking: + t1 = cpu_times() + time.sleep(interval) + else: + t1 = _last_cpu_times.get(tid) or cpu_times() + _last_cpu_times[tid] = cpu_times() + return calculate(t1, _last_cpu_times[tid]) + # per-cpu usage + else: + ret = [] + if blocking: + tot1 = cpu_times(percpu=True) + time.sleep(interval) + else: + tot1 = _last_per_cpu_times.get(tid) or cpu_times(percpu=True) + _last_per_cpu_times[tid] = cpu_times(percpu=True) + for t1, t2 in zip(tot1, _last_per_cpu_times[tid]): + ret.append(calculate(t1, t2)) + return ret + + +# Use a separate dict for cpu_times_percent(), so it's independent from +# cpu_percent() and they can both be used within the same program. +_last_cpu_times_2 = _last_cpu_times.copy() +_last_per_cpu_times_2 = _last_per_cpu_times.copy() + + +def cpu_times_percent(interval=None, percpu=False): + """Same as cpu_percent() but provides utilization percentages + for each specific CPU time as is returned by cpu_times(). + For instance, on Linux we'll get: + + >>> cpu_times_percent() + cpupercent(user=4.8, nice=0.0, system=4.8, idle=90.5, iowait=0.0, + irq=0.0, softirq=0.0, steal=0.0, guest=0.0, guest_nice=0.0) + >>> + + *interval* and *percpu* arguments have the same meaning as in + cpu_percent(). + """ + tid = threading.current_thread().ident + blocking = interval is not None and interval > 0.0 + if interval is not None and interval < 0: + msg = f"interval is not positive (got {interval!r})" + raise ValueError(msg) + + def calculate(t1, t2): + nums = [] + times_delta = _cpu_times_deltas(t1, t2) + all_delta = _cpu_tot_time(times_delta) + # "scale" is the value to multiply each delta with to get percentages. + # We use "max" to avoid division by zero (if all_delta is 0, then all + # fields are 0 so percentages will be 0 too. all_delta cannot be a + # fraction because cpu times are integers) + scale = 100.0 / max(1, all_delta) + for field_delta in times_delta: + field_perc = field_delta * scale + field_perc = round(field_perc, 1) + # make sure we don't return negative values or values over 100% + field_perc = min(max(0.0, field_perc), 100.0) + nums.append(field_perc) + return _psplatform.scputimes(*nums) + + # system-wide usage + if not percpu: + if blocking: + t1 = cpu_times() + time.sleep(interval) + else: + t1 = _last_cpu_times_2.get(tid) or cpu_times() + _last_cpu_times_2[tid] = cpu_times() + return calculate(t1, _last_cpu_times_2[tid]) + # per-cpu usage + else: + ret = [] + if blocking: + tot1 = cpu_times(percpu=True) + time.sleep(interval) + else: + tot1 = _last_per_cpu_times_2.get(tid) or cpu_times(percpu=True) + _last_per_cpu_times_2[tid] = cpu_times(percpu=True) + for t1, t2 in zip(tot1, _last_per_cpu_times_2[tid]): + ret.append(calculate(t1, t2)) + return ret + + +def cpu_stats(): + """Return CPU statistics.""" + return _psplatform.cpu_stats() + + +if hasattr(_psplatform, "cpu_freq"): + + def cpu_freq(percpu=False): + """Return CPU frequency as a namedtuple including current, + min and max frequency expressed in Mhz. + + If *percpu* is True and the system supports per-cpu frequency + retrieval (Linux only) a list of frequencies is returned for + each CPU. If not a list with one element is returned. + """ + ret = _psplatform.cpu_freq() + if percpu: + return ret + else: + num_cpus = float(len(ret)) + if num_cpus == 0: + return None + elif num_cpus == 1: + return ret[0] + else: + currs, mins, maxs = 0.0, 0.0, 0.0 + set_none = False + for cpu in ret: + currs += cpu.current + # On Linux if /proc/cpuinfo is used min/max are set + # to None. + if LINUX and cpu.min is None: + set_none = True + continue + mins += cpu.min + maxs += cpu.max + + current = currs / num_cpus + + if set_none: + min_ = max_ = None + else: + min_ = mins / num_cpus + max_ = maxs / num_cpus + + return _common.scpufreq(current, min_, max_) + + __all__.append("cpu_freq") + + +if hasattr(os, "getloadavg") or hasattr(_psplatform, "getloadavg"): + # Perform this hasattr check once on import time to either use the + # platform based code or proxy straight from the os module. + if hasattr(os, "getloadavg"): + getloadavg = os.getloadavg + else: + getloadavg = _psplatform.getloadavg + + __all__.append("getloadavg") + + +# ===================================================================== +# --- system memory related functions +# ===================================================================== + + +def virtual_memory(): + """Return statistics about system memory usage as a namedtuple + including the following fields, expressed in bytes: + + - total: + total physical memory available. + + - available: + the memory that can be given instantly to processes without the + system going into swap. + This is calculated by summing different memory values depending + on the platform and it is supposed to be used to monitor actual + memory usage in a cross platform fashion. + + - percent: + the percentage usage calculated as (total - available) / total * 100 + + - used: + memory used, calculated differently depending on the platform and + designed for informational purposes only: + macOS: active + wired + BSD: active + wired + cached + Linux: total - free + + - free: + memory not being used at all (zeroed) that is readily available; + note that this doesn't reflect the actual memory available + (use 'available' instead) + + Platform-specific fields: + + - active (UNIX): + memory currently in use or very recently used, and so it is in RAM. + + - inactive (UNIX): + memory that is marked as not used. + + - buffers (BSD, Linux): + cache for things like file system metadata. + + - cached (BSD, macOS): + cache for various things. + + - wired (macOS, BSD): + memory that is marked to always stay in RAM. It is never moved to disk. + + - shared (BSD): + memory that may be simultaneously accessed by multiple processes. + + The sum of 'used' and 'available' does not necessarily equal total. + On Windows 'available' and 'free' are the same. + """ + global _TOTAL_PHYMEM + ret = _psplatform.virtual_memory() + # cached for later use in Process.memory_percent() + _TOTAL_PHYMEM = ret.total + return ret + + +def swap_memory(): + """Return system swap memory statistics as a namedtuple including + the following fields: + + - total: total swap memory in bytes + - used: used swap memory in bytes + - free: free swap memory in bytes + - percent: the percentage usage + - sin: no. of bytes the system has swapped in from disk (cumulative) + - sout: no. of bytes the system has swapped out from disk (cumulative) + + 'sin' and 'sout' on Windows are meaningless and always set to 0. + """ + return _psplatform.swap_memory() + + +# ===================================================================== +# --- disks/partitions related functions +# ===================================================================== + + +def disk_usage(path): + """Return disk usage statistics about the given *path* as a + namedtuple including total, used and free space expressed in bytes + plus the percentage usage. + """ + return _psplatform.disk_usage(path) + + +def disk_partitions(all=False): + """Return mounted partitions as a list of + (device, mountpoint, fstype, opts) namedtuple. + 'opts' field is a raw string separated by commas indicating mount + options which may vary depending on the platform. + + If *all* parameter is False return physical devices only and ignore + all others. + """ + return _psplatform.disk_partitions(all) + + +def disk_io_counters(perdisk=False, nowrap=True): + """Return system disk I/O statistics as a namedtuple including + the following fields: + + - read_count: number of reads + - write_count: number of writes + - read_bytes: number of bytes read + - write_bytes: number of bytes written + - read_time: time spent reading from disk (in ms) + - write_time: time spent writing to disk (in ms) + + Platform specific: + + - busy_time: (Linux, FreeBSD) time spent doing actual I/Os (in ms) + - read_merged_count (Linux): number of merged reads + - write_merged_count (Linux): number of merged writes + + If *perdisk* is True return the same information for every + physical disk installed on the system as a dictionary + with partition names as the keys and the namedtuple + described above as the values. + + If *nowrap* is True it detects and adjust the numbers which overflow + and wrap (restart from 0) and add "old value" to "new value" so that + the returned numbers will always be increasing or remain the same, + but never decrease. + "disk_io_counters.cache_clear()" can be used to invalidate the + cache. + + On recent Windows versions 'diskperf -y' command may need to be + executed first otherwise this function won't find any disk. + """ + kwargs = dict(perdisk=perdisk) if LINUX else {} + rawdict = _psplatform.disk_io_counters(**kwargs) + if not rawdict: + return {} if perdisk else None + if nowrap: + rawdict = _wrap_numbers(rawdict, 'psutil.disk_io_counters') + nt = getattr(_psplatform, "sdiskio", _common.sdiskio) + if perdisk: + for disk, fields in rawdict.items(): + rawdict[disk] = nt(*fields) + return rawdict + else: + return nt(*(sum(x) for x in zip(*rawdict.values()))) + + +disk_io_counters.cache_clear = functools.partial( + _wrap_numbers.cache_clear, 'psutil.disk_io_counters' +) +disk_io_counters.cache_clear.__doc__ = "Clears nowrap argument cache" + + +# ===================================================================== +# --- network related functions +# ===================================================================== + + +def net_io_counters(pernic=False, nowrap=True): + """Return network I/O statistics as a namedtuple including + the following fields: + + - bytes_sent: number of bytes sent + - bytes_recv: number of bytes received + - packets_sent: number of packets sent + - packets_recv: number of packets received + - errin: total number of errors while receiving + - errout: total number of errors while sending + - dropin: total number of incoming packets which were dropped + - dropout: total number of outgoing packets which were dropped + (always 0 on macOS and BSD) + + If *pernic* is True return the same information for every + network interface installed on the system as a dictionary + with network interface names as the keys and the namedtuple + described above as the values. + + If *nowrap* is True it detects and adjust the numbers which overflow + and wrap (restart from 0) and add "old value" to "new value" so that + the returned numbers will always be increasing or remain the same, + but never decrease. + "net_io_counters.cache_clear()" can be used to invalidate the + cache. + """ + rawdict = _psplatform.net_io_counters() + if not rawdict: + return {} if pernic else None + if nowrap: + rawdict = _wrap_numbers(rawdict, 'psutil.net_io_counters') + if pernic: + for nic, fields in rawdict.items(): + rawdict[nic] = _common.snetio(*fields) + return rawdict + else: + return _common.snetio(*[sum(x) for x in zip(*rawdict.values())]) + + +net_io_counters.cache_clear = functools.partial( + _wrap_numbers.cache_clear, 'psutil.net_io_counters' +) +net_io_counters.cache_clear.__doc__ = "Clears nowrap argument cache" + + +def net_connections(kind='inet'): + """Return system-wide socket connections as a list of + (fd, family, type, laddr, raddr, status, pid) namedtuples. + In case of limited privileges 'fd' and 'pid' may be set to -1 + and None respectively. + The *kind* parameter filters for connections that fit the + following criteria: + + +------------+----------------------------------------------------+ + | Kind Value | Connections using | + +------------+----------------------------------------------------+ + | inet | IPv4 and IPv6 | + | inet4 | IPv4 | + | inet6 | IPv6 | + | tcp | TCP | + | tcp4 | TCP over IPv4 | + | tcp6 | TCP over IPv6 | + | udp | UDP | + | udp4 | UDP over IPv4 | + | udp6 | UDP over IPv6 | + | unix | UNIX socket (both UDP and TCP protocols) | + | all | the sum of all the possible families and protocols | + +------------+----------------------------------------------------+ + + On macOS this function requires root privileges. + """ + _check_conn_kind(kind) + return _psplatform.net_connections(kind) + + +def net_if_addrs(): + """Return the addresses associated to each NIC (network interface + card) installed on the system as a dictionary whose keys are the + NIC names and value is a list of namedtuples for each address + assigned to the NIC. Each namedtuple includes 5 fields: + + - family: can be either socket.AF_INET, socket.AF_INET6 or + psutil.AF_LINK, which refers to a MAC address. + - address: is the primary address and it is always set. + - netmask: and 'broadcast' and 'ptp' may be None. + - ptp: stands for "point to point" and references the + destination address on a point to point interface + (typically a VPN). + - broadcast: and *ptp* are mutually exclusive. + + Note: you can have more than one address of the same family + associated with each interface. + """ + rawlist = _psplatform.net_if_addrs() + rawlist.sort(key=lambda x: x[1]) # sort by family + ret = collections.defaultdict(list) + for name, fam, addr, mask, broadcast, ptp in rawlist: + try: + fam = socket.AddressFamily(fam) + except ValueError: + if WINDOWS and fam == -1: + fam = _psplatform.AF_LINK + elif ( + hasattr(_psplatform, "AF_LINK") and fam == _psplatform.AF_LINK + ): + # Linux defines AF_LINK as an alias for AF_PACKET. + # We re-set the family here so that repr(family) + # will show AF_LINK rather than AF_PACKET + fam = _psplatform.AF_LINK + + if fam == _psplatform.AF_LINK: + # The underlying C function may return an incomplete MAC + # address in which case we fill it with null bytes, see: + # https://github.com/giampaolo/psutil/issues/786 + separator = ":" if POSIX else "-" + while addr.count(separator) < 5: + addr += f"{separator}00" + + nt = _common.snicaddr(fam, addr, mask, broadcast, ptp) + + # On Windows broadcast is None, so we determine it via + # ipaddress module. + if WINDOWS and fam in {socket.AF_INET, socket.AF_INET6}: + try: + broadcast = _common.broadcast_addr(nt) + except Exception as err: # noqa: BLE001 + debug(err) + else: + if broadcast is not None: + nt._replace(broadcast=broadcast) + + ret[name].append(nt) + + return dict(ret) + + +def net_if_stats(): + """Return information about each NIC (network interface card) + installed on the system as a dictionary whose keys are the + NIC names and value is a namedtuple with the following fields: + + - isup: whether the interface is up (bool) + - duplex: can be either NIC_DUPLEX_FULL, NIC_DUPLEX_HALF or + NIC_DUPLEX_UNKNOWN + - speed: the NIC speed expressed in mega bits (MB); if it can't + be determined (e.g. 'localhost') it will be set to 0. + - mtu: the maximum transmission unit expressed in bytes. + """ + return _psplatform.net_if_stats() + + +# ===================================================================== +# --- sensors +# ===================================================================== + + +# Linux, macOS +if hasattr(_psplatform, "sensors_temperatures"): + + def sensors_temperatures(fahrenheit=False): + """Return hardware temperatures. Each entry is a namedtuple + representing a certain hardware sensor (it may be a CPU, an + hard disk or something else, depending on the OS and its + configuration). + All temperatures are expressed in celsius unless *fahrenheit* + is set to True. + """ + + def convert(n): + if n is not None: + return (float(n) * 9 / 5) + 32 if fahrenheit else n + + ret = collections.defaultdict(list) + rawdict = _psplatform.sensors_temperatures() + + for name, values in rawdict.items(): + while values: + label, current, high, critical = values.pop(0) + current = convert(current) + high = convert(high) + critical = convert(critical) + + if high and not critical: + critical = high + elif critical and not high: + high = critical + + ret[name].append( + _common.shwtemp(label, current, high, critical) + ) + + return dict(ret) + + __all__.append("sensors_temperatures") + + +# Linux +if hasattr(_psplatform, "sensors_fans"): + + def sensors_fans(): + """Return fans speed. Each entry is a namedtuple + representing a certain hardware sensor. + All speed are expressed in RPM (rounds per minute). + """ + return _psplatform.sensors_fans() + + __all__.append("sensors_fans") + + +# Linux, Windows, FreeBSD, macOS +if hasattr(_psplatform, "sensors_battery"): + + def sensors_battery(): + """Return battery information. If no battery is installed + returns None. + + - percent: battery power left as a percentage. + - secsleft: a rough approximation of how many seconds are left + before the battery runs out of power. May be + POWER_TIME_UNLIMITED or POWER_TIME_UNLIMITED. + - power_plugged: True if the AC power cable is connected. + """ + return _psplatform.sensors_battery() + + __all__.append("sensors_battery") + + +# ===================================================================== +# --- other system related functions +# ===================================================================== + + +def boot_time(): + """Return the system boot time expressed in seconds since the epoch.""" + # Note: we are not caching this because it is subject to + # system clock updates. + return _psplatform.boot_time() + + +def users(): + """Return users currently connected on the system as a list of + namedtuples including the following fields. + + - user: the name of the user + - terminal: the tty or pseudo-tty associated with the user, if any. + - host: the host name associated with the entry, if any. + - started: the creation time as a floating point number expressed in + seconds since the epoch. + """ + return _psplatform.users() + + +# ===================================================================== +# --- Windows services +# ===================================================================== + + +if WINDOWS: + + def win_service_iter(): + """Return a generator yielding a WindowsService instance for all + Windows services installed. + """ + return _psplatform.win_service_iter() + + def win_service_get(name): + """Get a Windows service by *name*. + Raise NoSuchProcess if no service with such name exists. + """ + return _psplatform.win_service_get(name) + + +# ===================================================================== + + +def _set_debug(value): + """Enable or disable PSUTIL_DEBUG option, which prints debugging + messages to stderr. + """ + import psutil._common + + psutil._common.PSUTIL_DEBUG = bool(value) + _psplatform.cext.set_debug(bool(value)) + + +del memoize_when_activated diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000..f369ac2 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_common.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_common.cpython-312.pyc new file mode 100644 index 0000000..7a84b6a Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_common.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psaix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psaix.cpython-312.pyc new file mode 100644 index 0000000..71501ee Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psaix.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psbsd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psbsd.cpython-312.pyc new file mode 100644 index 0000000..f7c7aa1 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psbsd.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pslinux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pslinux.cpython-312.pyc new file mode 100644 index 0000000..44d9595 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pslinux.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psosx.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psosx.cpython-312.pyc new file mode 100644 index 0000000..54c79b3 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psosx.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psposix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psposix.cpython-312.pyc new file mode 100644 index 0000000..0bab779 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_psposix.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pssunos.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pssunos.cpython-312.pyc new file mode 100644 index 0000000..7504c53 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pssunos.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pswindows.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pswindows.cpython-312.pyc new file mode 100644 index 0000000..61eaac8 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/__pycache__/_pswindows.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/_common.py b/llmlab/lib/python3.12/site-packages/psutil/_common.py new file mode 100644 index 0000000..4096c0a --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_common.py @@ -0,0 +1,950 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Common objects shared by __init__.py and _ps*.py modules. + +Note: this module is imported by setup.py, so it should not import +psutil or third-party modules. +""" + +import collections +import enum +import functools +import os +import socket +import stat +import sys +import threading +import warnings +from collections import namedtuple +from socket import AF_INET +from socket import SOCK_DGRAM +from socket import SOCK_STREAM + + +try: + from socket import AF_INET6 +except ImportError: + AF_INET6 = None +try: + from socket import AF_UNIX +except ImportError: + AF_UNIX = None + + +PSUTIL_DEBUG = bool(os.getenv('PSUTIL_DEBUG')) +_DEFAULT = object() + +# fmt: off +__all__ = [ + # OS constants + 'FREEBSD', 'BSD', 'LINUX', 'NETBSD', 'OPENBSD', 'MACOS', 'OSX', 'POSIX', + 'SUNOS', 'WINDOWS', + # connection constants + 'CONN_CLOSE', 'CONN_CLOSE_WAIT', 'CONN_CLOSING', 'CONN_ESTABLISHED', + 'CONN_FIN_WAIT1', 'CONN_FIN_WAIT2', 'CONN_LAST_ACK', 'CONN_LISTEN', + 'CONN_NONE', 'CONN_SYN_RECV', 'CONN_SYN_SENT', 'CONN_TIME_WAIT', + # net constants + 'NIC_DUPLEX_FULL', 'NIC_DUPLEX_HALF', 'NIC_DUPLEX_UNKNOWN', # noqa: F822 + # process status constants + 'STATUS_DEAD', 'STATUS_DISK_SLEEP', 'STATUS_IDLE', 'STATUS_LOCKED', + 'STATUS_RUNNING', 'STATUS_SLEEPING', 'STATUS_STOPPED', 'STATUS_SUSPENDED', + 'STATUS_TRACING_STOP', 'STATUS_WAITING', 'STATUS_WAKE_KILL', + 'STATUS_WAKING', 'STATUS_ZOMBIE', 'STATUS_PARKED', + # other constants + 'ENCODING', 'ENCODING_ERRS', 'AF_INET6', + # named tuples + 'pconn', 'pcputimes', 'pctxsw', 'pgids', 'pio', 'pionice', 'popenfile', + 'pthread', 'puids', 'sconn', 'scpustats', 'sdiskio', 'sdiskpart', + 'sdiskusage', 'snetio', 'snicaddr', 'snicstats', 'sswap', 'suser', + # utility functions + 'conn_tmap', 'deprecated_method', 'isfile_strict', 'memoize', + 'parse_environ_block', 'path_exists_strict', 'usage_percent', + 'supports_ipv6', 'sockfam_to_enum', 'socktype_to_enum', "wrap_numbers", + 'open_text', 'open_binary', 'cat', 'bcat', + 'bytes2human', 'conn_to_ntuple', 'debug', + # shell utils + 'hilite', 'term_supports_colors', 'print_color', +] +# fmt: on + + +# =================================================================== +# --- OS constants +# =================================================================== + + +POSIX = os.name == "posix" +WINDOWS = os.name == "nt" +LINUX = sys.platform.startswith("linux") +MACOS = sys.platform.startswith("darwin") +OSX = MACOS # deprecated alias +FREEBSD = sys.platform.startswith(("freebsd", "midnightbsd")) +OPENBSD = sys.platform.startswith("openbsd") +NETBSD = sys.platform.startswith("netbsd") +BSD = FREEBSD or OPENBSD or NETBSD +SUNOS = sys.platform.startswith(("sunos", "solaris")) +AIX = sys.platform.startswith("aix") + + +# =================================================================== +# --- API constants +# =================================================================== + + +# Process.status() +STATUS_RUNNING = "running" +STATUS_SLEEPING = "sleeping" +STATUS_DISK_SLEEP = "disk-sleep" +STATUS_STOPPED = "stopped" +STATUS_TRACING_STOP = "tracing-stop" +STATUS_ZOMBIE = "zombie" +STATUS_DEAD = "dead" +STATUS_WAKE_KILL = "wake-kill" +STATUS_WAKING = "waking" +STATUS_IDLE = "idle" # Linux, macOS, FreeBSD +STATUS_LOCKED = "locked" # FreeBSD +STATUS_WAITING = "waiting" # FreeBSD +STATUS_SUSPENDED = "suspended" # NetBSD +STATUS_PARKED = "parked" # Linux + +# Process.net_connections() and psutil.net_connections() +CONN_ESTABLISHED = "ESTABLISHED" +CONN_SYN_SENT = "SYN_SENT" +CONN_SYN_RECV = "SYN_RECV" +CONN_FIN_WAIT1 = "FIN_WAIT1" +CONN_FIN_WAIT2 = "FIN_WAIT2" +CONN_TIME_WAIT = "TIME_WAIT" +CONN_CLOSE = "CLOSE" +CONN_CLOSE_WAIT = "CLOSE_WAIT" +CONN_LAST_ACK = "LAST_ACK" +CONN_LISTEN = "LISTEN" +CONN_CLOSING = "CLOSING" +CONN_NONE = "NONE" + + +# net_if_stats() +class NicDuplex(enum.IntEnum): + NIC_DUPLEX_FULL = 2 + NIC_DUPLEX_HALF = 1 + NIC_DUPLEX_UNKNOWN = 0 + + +globals().update(NicDuplex.__members__) + + +# sensors_battery() +class BatteryTime(enum.IntEnum): + POWER_TIME_UNKNOWN = -1 + POWER_TIME_UNLIMITED = -2 + + +globals().update(BatteryTime.__members__) + +# --- others + +ENCODING = sys.getfilesystemencoding() +ENCODING_ERRS = sys.getfilesystemencodeerrors() + + +# =================================================================== +# --- namedtuples +# =================================================================== + +# --- for system functions + +# fmt: off +# psutil.swap_memory() +sswap = namedtuple('sswap', ['total', 'used', 'free', 'percent', 'sin', + 'sout']) +# psutil.disk_usage() +sdiskusage = namedtuple('sdiskusage', ['total', 'used', 'free', 'percent']) +# psutil.disk_io_counters() +sdiskio = namedtuple('sdiskio', ['read_count', 'write_count', + 'read_bytes', 'write_bytes', + 'read_time', 'write_time']) +# psutil.disk_partitions() +sdiskpart = namedtuple('sdiskpart', ['device', 'mountpoint', 'fstype', 'opts']) +# psutil.net_io_counters() +snetio = namedtuple('snetio', ['bytes_sent', 'bytes_recv', + 'packets_sent', 'packets_recv', + 'errin', 'errout', + 'dropin', 'dropout']) +# psutil.users() +suser = namedtuple('suser', ['name', 'terminal', 'host', 'started', 'pid']) +# psutil.net_connections() +sconn = namedtuple('sconn', ['fd', 'family', 'type', 'laddr', 'raddr', + 'status', 'pid']) +# psutil.net_if_addrs() +snicaddr = namedtuple('snicaddr', + ['family', 'address', 'netmask', 'broadcast', 'ptp']) +# psutil.net_if_stats() +snicstats = namedtuple('snicstats', + ['isup', 'duplex', 'speed', 'mtu', 'flags']) +# psutil.cpu_stats() +scpustats = namedtuple( + 'scpustats', ['ctx_switches', 'interrupts', 'soft_interrupts', 'syscalls']) +# psutil.cpu_freq() +scpufreq = namedtuple('scpufreq', ['current', 'min', 'max']) +# psutil.sensors_temperatures() +shwtemp = namedtuple( + 'shwtemp', ['label', 'current', 'high', 'critical']) +# psutil.sensors_battery() +sbattery = namedtuple('sbattery', ['percent', 'secsleft', 'power_plugged']) +# psutil.sensors_fans() +sfan = namedtuple('sfan', ['label', 'current']) +# fmt: on + +# --- for Process methods + +# psutil.Process.cpu_times() +pcputimes = namedtuple( + 'pcputimes', ['user', 'system', 'children_user', 'children_system'] +) +# psutil.Process.open_files() +popenfile = namedtuple('popenfile', ['path', 'fd']) +# psutil.Process.threads() +pthread = namedtuple('pthread', ['id', 'user_time', 'system_time']) +# psutil.Process.uids() +puids = namedtuple('puids', ['real', 'effective', 'saved']) +# psutil.Process.gids() +pgids = namedtuple('pgids', ['real', 'effective', 'saved']) +# psutil.Process.io_counters() +pio = namedtuple( + 'pio', ['read_count', 'write_count', 'read_bytes', 'write_bytes'] +) +# psutil.Process.ionice() +pionice = namedtuple('pionice', ['ioclass', 'value']) +# psutil.Process.ctx_switches() +pctxsw = namedtuple('pctxsw', ['voluntary', 'involuntary']) +# psutil.Process.net_connections() +pconn = namedtuple( + 'pconn', ['fd', 'family', 'type', 'laddr', 'raddr', 'status'] +) + +# psutil.net_connections() and psutil.Process.net_connections() +addr = namedtuple('addr', ['ip', 'port']) + + +# =================================================================== +# --- Process.net_connections() 'kind' parameter mapping +# =================================================================== + + +conn_tmap = { + "all": ([AF_INET, AF_INET6, AF_UNIX], [SOCK_STREAM, SOCK_DGRAM]), + "tcp": ([AF_INET, AF_INET6], [SOCK_STREAM]), + "tcp4": ([AF_INET], [SOCK_STREAM]), + "udp": ([AF_INET, AF_INET6], [SOCK_DGRAM]), + "udp4": ([AF_INET], [SOCK_DGRAM]), + "inet": ([AF_INET, AF_INET6], [SOCK_STREAM, SOCK_DGRAM]), + "inet4": ([AF_INET], [SOCK_STREAM, SOCK_DGRAM]), + "inet6": ([AF_INET6], [SOCK_STREAM, SOCK_DGRAM]), +} + +if AF_INET6 is not None: + conn_tmap.update({ + "tcp6": ([AF_INET6], [SOCK_STREAM]), + "udp6": ([AF_INET6], [SOCK_DGRAM]), + }) + +if AF_UNIX is not None and not SUNOS: + conn_tmap.update({"unix": ([AF_UNIX], [SOCK_STREAM, SOCK_DGRAM])}) + + +# ===================================================================== +# --- Exceptions +# ===================================================================== + + +class Error(Exception): + """Base exception class. All other psutil exceptions inherit + from this one. + """ + + __module__ = 'psutil' + + def _infodict(self, attrs): + info = collections.OrderedDict() + for name in attrs: + value = getattr(self, name, None) + if value or (name == "pid" and value == 0): + info[name] = value + return info + + def __str__(self): + # invoked on `raise Error` + info = self._infodict(("pid", "ppid", "name")) + if info: + details = "({})".format( + ", ".join([f"{k}={v!r}" for k, v in info.items()]) + ) + else: + details = None + return " ".join([x for x in (getattr(self, "msg", ""), details) if x]) + + def __repr__(self): + # invoked on `repr(Error)` + info = self._infodict(("pid", "ppid", "name", "seconds", "msg")) + details = ", ".join([f"{k}={v!r}" for k, v in info.items()]) + return f"psutil.{self.__class__.__name__}({details})" + + +class NoSuchProcess(Error): + """Exception raised when a process with a certain PID doesn't + or no longer exists. + """ + + __module__ = 'psutil' + + def __init__(self, pid, name=None, msg=None): + Error.__init__(self) + self.pid = pid + self.name = name + self.msg = msg or "process no longer exists" + + def __reduce__(self): + return (self.__class__, (self.pid, self.name, self.msg)) + + +class ZombieProcess(NoSuchProcess): + """Exception raised when querying a zombie process. This is + raised on macOS, BSD and Solaris only, and not always: depending + on the query the OS may be able to succeed anyway. + On Linux all zombie processes are querable (hence this is never + raised). Windows doesn't have zombie processes. + """ + + __module__ = 'psutil' + + def __init__(self, pid, name=None, ppid=None, msg=None): + NoSuchProcess.__init__(self, pid, name, msg) + self.ppid = ppid + self.msg = msg or "PID still exists but it's a zombie" + + def __reduce__(self): + return (self.__class__, (self.pid, self.name, self.ppid, self.msg)) + + +class AccessDenied(Error): + """Exception raised when permission to perform an action is denied.""" + + __module__ = 'psutil' + + def __init__(self, pid=None, name=None, msg=None): + Error.__init__(self) + self.pid = pid + self.name = name + self.msg = msg or "" + + def __reduce__(self): + return (self.__class__, (self.pid, self.name, self.msg)) + + +class TimeoutExpired(Error): + """Raised on Process.wait(timeout) if timeout expires and process + is still alive. + """ + + __module__ = 'psutil' + + def __init__(self, seconds, pid=None, name=None): + Error.__init__(self) + self.seconds = seconds + self.pid = pid + self.name = name + self.msg = f"timeout after {seconds} seconds" + + def __reduce__(self): + return (self.__class__, (self.seconds, self.pid, self.name)) + + +# =================================================================== +# --- utils +# =================================================================== + + +def usage_percent(used, total, round_=None): + """Calculate percentage usage of 'used' against 'total'.""" + try: + ret = (float(used) / total) * 100 + except ZeroDivisionError: + return 0.0 + else: + if round_ is not None: + ret = round(ret, round_) + return ret + + +def memoize(fun): + """A simple memoize decorator for functions supporting (hashable) + positional arguments. + It also provides a cache_clear() function for clearing the cache: + + >>> @memoize + ... def foo() + ... return 1 + ... + >>> foo() + 1 + >>> foo.cache_clear() + >>> + + It supports: + - functions + - classes (acts as a @singleton) + - staticmethods + - classmethods + + It does NOT support: + - methods + """ + + @functools.wraps(fun) + def wrapper(*args, **kwargs): + key = (args, frozenset(sorted(kwargs.items()))) + try: + return cache[key] + except KeyError: + try: + ret = cache[key] = fun(*args, **kwargs) + except Exception as err: # noqa: BLE001 + raise err from None + return ret + + def cache_clear(): + """Clear cache.""" + cache.clear() + + cache = {} + wrapper.cache_clear = cache_clear + return wrapper + + +def memoize_when_activated(fun): + """A memoize decorator which is disabled by default. It can be + activated and deactivated on request. + For efficiency reasons it can be used only against class methods + accepting no arguments. + + >>> class Foo: + ... @memoize + ... def foo() + ... print(1) + ... + >>> f = Foo() + >>> # deactivated (default) + >>> foo() + 1 + >>> foo() + 1 + >>> + >>> # activated + >>> foo.cache_activate(self) + >>> foo() + 1 + >>> foo() + >>> foo() + >>> + """ + + @functools.wraps(fun) + def wrapper(self): + try: + # case 1: we previously entered oneshot() ctx + ret = self._cache[fun] + except AttributeError: + # case 2: we never entered oneshot() ctx + try: + return fun(self) + except Exception as err: # noqa: BLE001 + raise err from None + except KeyError: + # case 3: we entered oneshot() ctx but there's no cache + # for this entry yet + try: + ret = fun(self) + except Exception as err: # noqa: BLE001 + raise err from None + try: + self._cache[fun] = ret + except AttributeError: + # multi-threading race condition, see: + # https://github.com/giampaolo/psutil/issues/1948 + pass + return ret + + def cache_activate(proc): + """Activate cache. Expects a Process instance. Cache will be + stored as a "_cache" instance attribute. + """ + proc._cache = {} + + def cache_deactivate(proc): + """Deactivate and clear cache.""" + try: + del proc._cache + except AttributeError: + pass + + wrapper.cache_activate = cache_activate + wrapper.cache_deactivate = cache_deactivate + return wrapper + + +def isfile_strict(path): + """Same as os.path.isfile() but does not swallow EACCES / EPERM + exceptions, see: + http://mail.python.org/pipermail/python-dev/2012-June/120787.html. + """ + try: + st = os.stat(path) + except PermissionError: + raise + except OSError: + return False + else: + return stat.S_ISREG(st.st_mode) + + +def path_exists_strict(path): + """Same as os.path.exists() but does not swallow EACCES / EPERM + exceptions. See: + http://mail.python.org/pipermail/python-dev/2012-June/120787.html. + """ + try: + os.stat(path) + except PermissionError: + raise + except OSError: + return False + else: + return True + + +@memoize +def supports_ipv6(): + """Return True if IPv6 is supported on this platform.""" + if not socket.has_ipv6 or AF_INET6 is None: + return False + try: + with socket.socket(AF_INET6, socket.SOCK_STREAM) as sock: + sock.bind(("::1", 0)) + return True + except OSError: + return False + + +def parse_environ_block(data): + """Parse a C environ block of environment variables into a dictionary.""" + # The block is usually raw data from the target process. It might contain + # trailing garbage and lines that do not look like assignments. + ret = {} + pos = 0 + + # localize global variable to speed up access. + WINDOWS_ = WINDOWS + while True: + next_pos = data.find("\0", pos) + # nul byte at the beginning or double nul byte means finish + if next_pos <= pos: + break + # there might not be an equals sign + equal_pos = data.find("=", pos, next_pos) + if equal_pos > pos: + key = data[pos:equal_pos] + value = data[equal_pos + 1 : next_pos] + # Windows expects environment variables to be uppercase only + if WINDOWS_: + key = key.upper() + ret[key] = value + pos = next_pos + 1 + + return ret + + +def sockfam_to_enum(num): + """Convert a numeric socket family value to an IntEnum member. + If it's not a known member, return the numeric value itself. + """ + try: + return socket.AddressFamily(num) + except ValueError: + return num + + +def socktype_to_enum(num): + """Convert a numeric socket type value to an IntEnum member. + If it's not a known member, return the numeric value itself. + """ + try: + return socket.SocketKind(num) + except ValueError: + return num + + +def conn_to_ntuple(fd, fam, type_, laddr, raddr, status, status_map, pid=None): + """Convert a raw connection tuple to a proper ntuple.""" + if fam in {socket.AF_INET, AF_INET6}: + if laddr: + laddr = addr(*laddr) + if raddr: + raddr = addr(*raddr) + if type_ == socket.SOCK_STREAM and fam in {AF_INET, AF_INET6}: + status = status_map.get(status, CONN_NONE) + else: + status = CONN_NONE # ignore whatever C returned to us + fam = sockfam_to_enum(fam) + type_ = socktype_to_enum(type_) + if pid is None: + return pconn(fd, fam, type_, laddr, raddr, status) + else: + return sconn(fd, fam, type_, laddr, raddr, status, pid) + + +def broadcast_addr(addr): + """Given the address ntuple returned by ``net_if_addrs()`` + calculates the broadcast address. + """ + import ipaddress + + if not addr.address or not addr.netmask: + return None + if addr.family == socket.AF_INET: + return str( + ipaddress.IPv4Network( + f"{addr.address}/{addr.netmask}", strict=False + ).broadcast_address + ) + if addr.family == socket.AF_INET6: + return str( + ipaddress.IPv6Network( + f"{addr.address}/{addr.netmask}", strict=False + ).broadcast_address + ) + + +def deprecated_method(replacement): + """A decorator which can be used to mark a method as deprecated + 'replcement' is the method name which will be called instead. + """ + + def outer(fun): + msg = ( + f"{fun.__name__}() is deprecated and will be removed; use" + f" {replacement}() instead" + ) + if fun.__doc__ is None: + fun.__doc__ = msg + + @functools.wraps(fun) + def inner(self, *args, **kwargs): + warnings.warn(msg, category=DeprecationWarning, stacklevel=2) + return getattr(self, replacement)(*args, **kwargs) + + return inner + + return outer + + +class _WrapNumbers: + """Watches numbers so that they don't overflow and wrap + (reset to zero). + """ + + def __init__(self): + self.lock = threading.Lock() + self.cache = {} + self.reminders = {} + self.reminder_keys = {} + + def _add_dict(self, input_dict, name): + assert name not in self.cache + assert name not in self.reminders + assert name not in self.reminder_keys + self.cache[name] = input_dict + self.reminders[name] = collections.defaultdict(int) + self.reminder_keys[name] = collections.defaultdict(set) + + def _remove_dead_reminders(self, input_dict, name): + """In case the number of keys changed between calls (e.g. a + disk disappears) this removes the entry from self.reminders. + """ + old_dict = self.cache[name] + gone_keys = set(old_dict.keys()) - set(input_dict.keys()) + for gone_key in gone_keys: + for remkey in self.reminder_keys[name][gone_key]: + del self.reminders[name][remkey] + del self.reminder_keys[name][gone_key] + + def run(self, input_dict, name): + """Cache dict and sum numbers which overflow and wrap. + Return an updated copy of `input_dict`. + """ + if name not in self.cache: + # This was the first call. + self._add_dict(input_dict, name) + return input_dict + + self._remove_dead_reminders(input_dict, name) + + old_dict = self.cache[name] + new_dict = {} + for key in input_dict: + input_tuple = input_dict[key] + try: + old_tuple = old_dict[key] + except KeyError: + # The input dict has a new key (e.g. a new disk or NIC) + # which didn't exist in the previous call. + new_dict[key] = input_tuple + continue + + bits = [] + for i in range(len(input_tuple)): + input_value = input_tuple[i] + old_value = old_tuple[i] + remkey = (key, i) + if input_value < old_value: + # it wrapped! + self.reminders[name][remkey] += old_value + self.reminder_keys[name][key].add(remkey) + bits.append(input_value + self.reminders[name][remkey]) + + new_dict[key] = tuple(bits) + + self.cache[name] = input_dict + return new_dict + + def cache_clear(self, name=None): + """Clear the internal cache, optionally only for function 'name'.""" + with self.lock: + if name is None: + self.cache.clear() + self.reminders.clear() + self.reminder_keys.clear() + else: + self.cache.pop(name, None) + self.reminders.pop(name, None) + self.reminder_keys.pop(name, None) + + def cache_info(self): + """Return internal cache dicts as a tuple of 3 elements.""" + with self.lock: + return (self.cache, self.reminders, self.reminder_keys) + + +def wrap_numbers(input_dict, name): + """Given an `input_dict` and a function `name`, adjust the numbers + which "wrap" (restart from zero) across different calls by adding + "old value" to "new value" and return an updated dict. + """ + with _wn.lock: + return _wn.run(input_dict, name) + + +_wn = _WrapNumbers() +wrap_numbers.cache_clear = _wn.cache_clear +wrap_numbers.cache_info = _wn.cache_info + + +# The read buffer size for open() builtin. This (also) dictates how +# much data we read(2) when iterating over file lines as in: +# >>> with open(file) as f: +# ... for line in f: +# ... ... +# Default per-line buffer size for binary files is 1K. For text files +# is 8K. We use a bigger buffer (32K) in order to have more consistent +# results when reading /proc pseudo files on Linux, see: +# https://github.com/giampaolo/psutil/issues/2050 +# https://github.com/giampaolo/psutil/issues/708 +FILE_READ_BUFFER_SIZE = 32 * 1024 + + +def open_binary(fname): + return open(fname, "rb", buffering=FILE_READ_BUFFER_SIZE) + + +def open_text(fname): + """Open a file in text mode by using the proper FS encoding and + en/decoding error handlers. + """ + # See: + # https://github.com/giampaolo/psutil/issues/675 + # https://github.com/giampaolo/psutil/pull/733 + fobj = open( # noqa: SIM115 + fname, + buffering=FILE_READ_BUFFER_SIZE, + encoding=ENCODING, + errors=ENCODING_ERRS, + ) + try: + # Dictates per-line read(2) buffer size. Defaults is 8k. See: + # https://github.com/giampaolo/psutil/issues/2050#issuecomment-1013387546 + fobj._CHUNK_SIZE = FILE_READ_BUFFER_SIZE + except AttributeError: + pass + except Exception: + fobj.close() + raise + + return fobj + + +def cat(fname, fallback=_DEFAULT, _open=open_text): + """Read entire file content and return it as a string. File is + opened in text mode. If specified, `fallback` is the value + returned in case of error, either if the file does not exist or + it can't be read(). + """ + if fallback is _DEFAULT: + with _open(fname) as f: + return f.read() + else: + try: + with _open(fname) as f: + return f.read() + except OSError: + return fallback + + +def bcat(fname, fallback=_DEFAULT): + """Same as above but opens file in binary mode.""" + return cat(fname, fallback=fallback, _open=open_binary) + + +def bytes2human(n, format="%(value).1f%(symbol)s"): + """Used by various scripts. See: https://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/?in=user-4178764. + + >>> bytes2human(10000) + '9.8K' + >>> bytes2human(100001221) + '95.4M' + """ + symbols = ('B', 'K', 'M', 'G', 'T', 'P', 'E', 'Z', 'Y') + prefix = {} + for i, s in enumerate(symbols[1:]): + prefix[s] = 1 << (i + 1) * 10 + for symbol in reversed(symbols[1:]): + if abs(n) >= prefix[symbol]: + value = float(n) / prefix[symbol] + return format % locals() + return format % dict(symbol=symbols[0], value=n) + + +def get_procfs_path(): + """Return updated psutil.PROCFS_PATH constant.""" + return sys.modules['psutil'].PROCFS_PATH + + +def decode(s): + return s.decode(encoding=ENCODING, errors=ENCODING_ERRS) + + +# ===================================================================== +# --- shell utils +# ===================================================================== + + +@memoize +def term_supports_colors(file=sys.stdout): # pragma: no cover + if os.name == 'nt': + return True + try: + import curses + + assert file.isatty() + curses.setupterm() + assert curses.tigetnum("colors") > 0 + except Exception: # noqa: BLE001 + return False + else: + return True + + +def hilite(s, color=None, bold=False): # pragma: no cover + """Return an highlighted version of 'string'.""" + if not term_supports_colors(): + return s + attr = [] + colors = dict( + blue='34', + brown='33', + darkgrey='30', + green='32', + grey='37', + lightblue='36', + red='91', + violet='35', + yellow='93', + ) + colors[None] = '29' + try: + color = colors[color] + except KeyError: + msg = f"invalid color {color!r}; choose amongst {list(colors.keys())}" + raise ValueError(msg) from None + attr.append(color) + if bold: + attr.append('1') + return f"\x1b[{';'.join(attr)}m{s}\x1b[0m" + + +def print_color( + s, color=None, bold=False, file=sys.stdout +): # pragma: no cover + """Print a colorized version of string.""" + if not term_supports_colors(): + print(s, file=file) + elif POSIX: + print(hilite(s, color, bold), file=file) + else: + import ctypes + + DEFAULT_COLOR = 7 + GetStdHandle = ctypes.windll.Kernel32.GetStdHandle + SetConsoleTextAttribute = ( + ctypes.windll.Kernel32.SetConsoleTextAttribute + ) + + colors = dict(green=2, red=4, brown=6, yellow=6) + colors[None] = DEFAULT_COLOR + try: + color = colors[color] + except KeyError: + msg = ( + f"invalid color {color!r}; choose between" + f" {list(colors.keys())!r}" + ) + raise ValueError(msg) from None + if bold and color <= 7: + color += 8 + + handle_id = -12 if file is sys.stderr else -11 + GetStdHandle.restype = ctypes.c_ulong + handle = GetStdHandle(handle_id) + SetConsoleTextAttribute(handle, color) + try: + print(s, file=file) + finally: + SetConsoleTextAttribute(handle, DEFAULT_COLOR) + + +def debug(msg): + """If PSUTIL_DEBUG env var is set, print a debug message to stderr.""" + if PSUTIL_DEBUG: + import inspect + + fname, lineno, _, _lines, _index = inspect.getframeinfo( + inspect.currentframe().f_back + ) + if isinstance(msg, Exception): + if isinstance(msg, OSError): + # ...because str(exc) may contain info about the file name + msg = f"ignoring {msg}" + else: + msg = f"ignoring {msg!r}" + print( # noqa: T201 + f"psutil-debug [{fname}:{lineno}]> {msg}", file=sys.stderr + ) diff --git a/llmlab/lib/python3.12/site-packages/psutil/_psaix.py b/llmlab/lib/python3.12/site-packages/psutil/_psaix.py new file mode 100644 index 0000000..ba2725f --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_psaix.py @@ -0,0 +1,565 @@ +# Copyright (c) 2009, Giampaolo Rodola' +# Copyright (c) 2017, Arnon Yaari +# All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""AIX platform implementation.""" + +import functools +import glob +import os +import re +import subprocess +import sys +from collections import namedtuple + +from . import _common +from . import _psposix +from . import _psutil_aix as cext +from . import _psutil_posix as cext_posix +from ._common import NIC_DUPLEX_FULL +from ._common import NIC_DUPLEX_HALF +from ._common import NIC_DUPLEX_UNKNOWN +from ._common import AccessDenied +from ._common import NoSuchProcess +from ._common import ZombieProcess +from ._common import conn_to_ntuple +from ._common import get_procfs_path +from ._common import memoize_when_activated +from ._common import usage_percent + + +__extra__all__ = ["PROCFS_PATH"] + + +# ===================================================================== +# --- globals +# ===================================================================== + + +HAS_THREADS = hasattr(cext, "proc_threads") +HAS_NET_IO_COUNTERS = hasattr(cext, "net_io_counters") +HAS_PROC_IO_COUNTERS = hasattr(cext, "proc_io_counters") + +PAGE_SIZE = cext_posix.getpagesize() +AF_LINK = cext_posix.AF_LINK + +PROC_STATUSES = { + cext.SIDL: _common.STATUS_IDLE, + cext.SZOMB: _common.STATUS_ZOMBIE, + cext.SACTIVE: _common.STATUS_RUNNING, + cext.SSWAP: _common.STATUS_RUNNING, # TODO what status is this? + cext.SSTOP: _common.STATUS_STOPPED, +} + +TCP_STATUSES = { + cext.TCPS_ESTABLISHED: _common.CONN_ESTABLISHED, + cext.TCPS_SYN_SENT: _common.CONN_SYN_SENT, + cext.TCPS_SYN_RCVD: _common.CONN_SYN_RECV, + cext.TCPS_FIN_WAIT_1: _common.CONN_FIN_WAIT1, + cext.TCPS_FIN_WAIT_2: _common.CONN_FIN_WAIT2, + cext.TCPS_TIME_WAIT: _common.CONN_TIME_WAIT, + cext.TCPS_CLOSED: _common.CONN_CLOSE, + cext.TCPS_CLOSE_WAIT: _common.CONN_CLOSE_WAIT, + cext.TCPS_LAST_ACK: _common.CONN_LAST_ACK, + cext.TCPS_LISTEN: _common.CONN_LISTEN, + cext.TCPS_CLOSING: _common.CONN_CLOSING, + cext.PSUTIL_CONN_NONE: _common.CONN_NONE, +} + +proc_info_map = dict( + ppid=0, + rss=1, + vms=2, + create_time=3, + nice=4, + num_threads=5, + status=6, + ttynr=7, +) + + +# ===================================================================== +# --- named tuples +# ===================================================================== + + +# psutil.Process.memory_info() +pmem = namedtuple('pmem', ['rss', 'vms']) +# psutil.Process.memory_full_info() +pfullmem = pmem +# psutil.Process.cpu_times() +scputimes = namedtuple('scputimes', ['user', 'system', 'idle', 'iowait']) +# psutil.virtual_memory() +svmem = namedtuple('svmem', ['total', 'available', 'percent', 'used', 'free']) + + +# ===================================================================== +# --- memory +# ===================================================================== + + +def virtual_memory(): + total, avail, free, _pinned, inuse = cext.virtual_mem() + percent = usage_percent((total - avail), total, round_=1) + return svmem(total, avail, percent, inuse, free) + + +def swap_memory(): + """Swap system memory as a (total, used, free, sin, sout) tuple.""" + total, free, sin, sout = cext.swap_mem() + used = total - free + percent = usage_percent(used, total, round_=1) + return _common.sswap(total, used, free, percent, sin, sout) + + +# ===================================================================== +# --- CPU +# ===================================================================== + + +def cpu_times(): + """Return system-wide CPU times as a named tuple.""" + ret = cext.per_cpu_times() + return scputimes(*[sum(x) for x in zip(*ret)]) + + +def per_cpu_times(): + """Return system per-CPU times as a list of named tuples.""" + ret = cext.per_cpu_times() + return [scputimes(*x) for x in ret] + + +def cpu_count_logical(): + """Return the number of logical CPUs in the system.""" + try: + return os.sysconf("SC_NPROCESSORS_ONLN") + except ValueError: + # mimic os.cpu_count() behavior + return None + + +def cpu_count_cores(): + cmd = ["lsdev", "-Cc", "processor"] + p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + stdout, stderr = p.communicate() + stdout, stderr = (x.decode(sys.stdout.encoding) for x in (stdout, stderr)) + if p.returncode != 0: + msg = f"{cmd!r} command error\n{stderr}" + raise RuntimeError(msg) + processors = stdout.strip().splitlines() + return len(processors) or None + + +def cpu_stats(): + """Return various CPU stats as a named tuple.""" + ctx_switches, interrupts, soft_interrupts, syscalls = cext.cpu_stats() + return _common.scpustats( + ctx_switches, interrupts, soft_interrupts, syscalls + ) + + +# ===================================================================== +# --- disks +# ===================================================================== + + +disk_io_counters = cext.disk_io_counters +disk_usage = _psposix.disk_usage + + +def disk_partitions(all=False): + """Return system disk partitions.""" + # TODO - the filtering logic should be better checked so that + # it tries to reflect 'df' as much as possible + retlist = [] + partitions = cext.disk_partitions() + for partition in partitions: + device, mountpoint, fstype, opts = partition + if device == 'none': + device = '' + if not all: + # Differently from, say, Linux, we don't have a list of + # common fs types so the best we can do, AFAIK, is to + # filter by filesystem having a total size > 0. + if not disk_usage(mountpoint).total: + continue + ntuple = _common.sdiskpart(device, mountpoint, fstype, opts) + retlist.append(ntuple) + return retlist + + +# ===================================================================== +# --- network +# ===================================================================== + + +net_if_addrs = cext_posix.net_if_addrs + +if HAS_NET_IO_COUNTERS: + net_io_counters = cext.net_io_counters + + +def net_connections(kind, _pid=-1): + """Return socket connections. If pid == -1 return system-wide + connections (as opposed to connections opened by one process only). + """ + families, types = _common.conn_tmap[kind] + rawlist = cext.net_connections(_pid) + ret = [] + for item in rawlist: + fd, fam, type_, laddr, raddr, status, pid = item + if fam not in families: + continue + if type_ not in types: + continue + nt = conn_to_ntuple( + fd, + fam, + type_, + laddr, + raddr, + status, + TCP_STATUSES, + pid=pid if _pid == -1 else None, + ) + ret.append(nt) + return ret + + +def net_if_stats(): + """Get NIC stats (isup, duplex, speed, mtu).""" + duplex_map = {"Full": NIC_DUPLEX_FULL, "Half": NIC_DUPLEX_HALF} + names = {x[0] for x in net_if_addrs()} + ret = {} + for name in names: + mtu = cext_posix.net_if_mtu(name) + flags = cext_posix.net_if_flags(name) + + # try to get speed and duplex + # TODO: rewrite this in C (entstat forks, so use truss -f to follow. + # looks like it is using an undocumented ioctl?) + duplex = "" + speed = 0 + p = subprocess.Popen( + ["/usr/bin/entstat", "-d", name], + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + ) + stdout, stderr = p.communicate() + stdout, stderr = ( + x.decode(sys.stdout.encoding) for x in (stdout, stderr) + ) + if p.returncode == 0: + re_result = re.search( + r"Running: (\d+) Mbps.*?(\w+) Duplex", stdout + ) + if re_result is not None: + speed = int(re_result.group(1)) + duplex = re_result.group(2) + + output_flags = ','.join(flags) + isup = 'running' in flags + duplex = duplex_map.get(duplex, NIC_DUPLEX_UNKNOWN) + ret[name] = _common.snicstats(isup, duplex, speed, mtu, output_flags) + return ret + + +# ===================================================================== +# --- other system functions +# ===================================================================== + + +def boot_time(): + """The system boot time expressed in seconds since the epoch.""" + return cext.boot_time() + + +def users(): + """Return currently connected users as a list of namedtuples.""" + retlist = [] + rawlist = cext.users() + localhost = (':0.0', ':0') + for item in rawlist: + user, tty, hostname, tstamp, user_process, pid = item + # note: the underlying C function includes entries about + # system boot, run level and others. We might want + # to use them in the future. + if not user_process: + continue + if hostname in localhost: + hostname = 'localhost' + nt = _common.suser(user, tty, hostname, tstamp, pid) + retlist.append(nt) + return retlist + + +# ===================================================================== +# --- processes +# ===================================================================== + + +def pids(): + """Returns a list of PIDs currently running on the system.""" + return [int(x) for x in os.listdir(get_procfs_path()) if x.isdigit()] + + +def pid_exists(pid): + """Check for the existence of a unix pid.""" + return os.path.exists(os.path.join(get_procfs_path(), str(pid), "psinfo")) + + +def wrap_exceptions(fun): + """Call callable into a try/except clause and translate ENOENT, + EACCES and EPERM in NoSuchProcess or AccessDenied exceptions. + """ + + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + pid, ppid, name = self.pid, self._ppid, self._name + try: + return fun(self, *args, **kwargs) + except (FileNotFoundError, ProcessLookupError) as err: + # ENOENT (no such file or directory) gets raised on open(). + # ESRCH (no such process) can get raised on read() if + # process is gone in meantime. + if not pid_exists(pid): + raise NoSuchProcess(pid, name) from err + raise ZombieProcess(pid, name, ppid) from err + except PermissionError as err: + raise AccessDenied(pid, name) from err + + return wrapper + + +class Process: + """Wrapper class around underlying C implementation.""" + + __slots__ = ["_cache", "_name", "_ppid", "_procfs_path", "pid"] + + def __init__(self, pid): + self.pid = pid + self._name = None + self._ppid = None + self._procfs_path = get_procfs_path() + + def oneshot_enter(self): + self._proc_basic_info.cache_activate(self) + self._proc_cred.cache_activate(self) + + def oneshot_exit(self): + self._proc_basic_info.cache_deactivate(self) + self._proc_cred.cache_deactivate(self) + + @wrap_exceptions + @memoize_when_activated + def _proc_basic_info(self): + return cext.proc_basic_info(self.pid, self._procfs_path) + + @wrap_exceptions + @memoize_when_activated + def _proc_cred(self): + return cext.proc_cred(self.pid, self._procfs_path) + + @wrap_exceptions + def name(self): + if self.pid == 0: + return "swapper" + # note: max 16 characters + return cext.proc_name(self.pid, self._procfs_path).rstrip("\x00") + + @wrap_exceptions + def exe(self): + # there is no way to get executable path in AIX other than to guess, + # and guessing is more complex than what's in the wrapping class + cmdline = self.cmdline() + if not cmdline: + return '' + exe = cmdline[0] + if os.path.sep in exe: + # relative or absolute path + if not os.path.isabs(exe): + # if cwd has changed, we're out of luck - this may be wrong! + exe = os.path.abspath(os.path.join(self.cwd(), exe)) + if ( + os.path.isabs(exe) + and os.path.isfile(exe) + and os.access(exe, os.X_OK) + ): + return exe + # not found, move to search in PATH using basename only + exe = os.path.basename(exe) + # search for exe name PATH + for path in os.environ["PATH"].split(":"): + possible_exe = os.path.abspath(os.path.join(path, exe)) + if os.path.isfile(possible_exe) and os.access( + possible_exe, os.X_OK + ): + return possible_exe + return '' + + @wrap_exceptions + def cmdline(self): + return cext.proc_args(self.pid) + + @wrap_exceptions + def environ(self): + return cext.proc_environ(self.pid) + + @wrap_exceptions + def create_time(self): + return self._proc_basic_info()[proc_info_map['create_time']] + + @wrap_exceptions + def num_threads(self): + return self._proc_basic_info()[proc_info_map['num_threads']] + + if HAS_THREADS: + + @wrap_exceptions + def threads(self): + rawlist = cext.proc_threads(self.pid) + retlist = [] + for thread_id, utime, stime in rawlist: + ntuple = _common.pthread(thread_id, utime, stime) + retlist.append(ntuple) + # The underlying C implementation retrieves all OS threads + # and filters them by PID. At this point we can't tell whether + # an empty list means there were no connections for process or + # process is no longer active so we force NSP in case the PID + # is no longer there. + if not retlist: + # will raise NSP if process is gone + os.stat(f"{self._procfs_path}/{self.pid}") + return retlist + + @wrap_exceptions + def net_connections(self, kind='inet'): + ret = net_connections(kind, _pid=self.pid) + # The underlying C implementation retrieves all OS connections + # and filters them by PID. At this point we can't tell whether + # an empty list means there were no connections for process or + # process is no longer active so we force NSP in case the PID + # is no longer there. + if not ret: + # will raise NSP if process is gone + os.stat(f"{self._procfs_path}/{self.pid}") + return ret + + @wrap_exceptions + def nice_get(self): + return cext_posix.getpriority(self.pid) + + @wrap_exceptions + def nice_set(self, value): + return cext_posix.setpriority(self.pid, value) + + @wrap_exceptions + def ppid(self): + self._ppid = self._proc_basic_info()[proc_info_map['ppid']] + return self._ppid + + @wrap_exceptions + def uids(self): + real, effective, saved, _, _, _ = self._proc_cred() + return _common.puids(real, effective, saved) + + @wrap_exceptions + def gids(self): + _, _, _, real, effective, saved = self._proc_cred() + return _common.puids(real, effective, saved) + + @wrap_exceptions + def cpu_times(self): + t = cext.proc_cpu_times(self.pid, self._procfs_path) + return _common.pcputimes(*t) + + @wrap_exceptions + def terminal(self): + ttydev = self._proc_basic_info()[proc_info_map['ttynr']] + # convert from 64-bit dev_t to 32-bit dev_t and then map the device + ttydev = ((ttydev & 0x0000FFFF00000000) >> 16) | (ttydev & 0xFFFF) + # try to match rdev of /dev/pts/* files ttydev + for dev in glob.glob("/dev/**/*"): + if os.stat(dev).st_rdev == ttydev: + return dev + return None + + @wrap_exceptions + def cwd(self): + procfs_path = self._procfs_path + try: + result = os.readlink(f"{procfs_path}/{self.pid}/cwd") + return result.rstrip('/') + except FileNotFoundError: + os.stat(f"{procfs_path}/{self.pid}") # raise NSP or AD + return "" + + @wrap_exceptions + def memory_info(self): + ret = self._proc_basic_info() + rss = ret[proc_info_map['rss']] * 1024 + vms = ret[proc_info_map['vms']] * 1024 + return pmem(rss, vms) + + memory_full_info = memory_info + + @wrap_exceptions + def status(self): + code = self._proc_basic_info()[proc_info_map['status']] + # XXX is '?' legit? (we're not supposed to return it anyway) + return PROC_STATUSES.get(code, '?') + + def open_files(self): + # TODO rewrite without using procfiles (stat /proc/pid/fd/* and then + # find matching name of the inode) + p = subprocess.Popen( + ["/usr/bin/procfiles", "-n", str(self.pid)], + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + ) + stdout, stderr = p.communicate() + stdout, stderr = ( + x.decode(sys.stdout.encoding) for x in (stdout, stderr) + ) + if "no such process" in stderr.lower(): + raise NoSuchProcess(self.pid, self._name) + procfiles = re.findall(r"(\d+): S_IFREG.*name:(.*)\n", stdout) + retlist = [] + for fd, path in procfiles: + path = path.strip() + if path.startswith("//"): + path = path[1:] + if path.lower() == "cannot be retrieved": + continue + retlist.append(_common.popenfile(path, int(fd))) + return retlist + + @wrap_exceptions + def num_fds(self): + if self.pid == 0: # no /proc/0/fd + return 0 + return len(os.listdir(f"{self._procfs_path}/{self.pid}/fd")) + + @wrap_exceptions + def num_ctx_switches(self): + return _common.pctxsw(*cext.proc_num_ctx_switches(self.pid)) + + @wrap_exceptions + def wait(self, timeout=None): + return _psposix.wait_pid(self.pid, timeout, self._name) + + if HAS_PROC_IO_COUNTERS: + + @wrap_exceptions + def io_counters(self): + try: + rc, wc, rb, wb = cext.proc_io_counters(self.pid) + except OSError as err: + # if process is terminated, proc_io_counters returns OSError + # instead of NSP + if not pid_exists(self.pid): + raise NoSuchProcess(self.pid, self._name) from err + raise + return _common.pio(rc, wc, rb, wb) diff --git a/llmlab/lib/python3.12/site-packages/psutil/_psbsd.py b/llmlab/lib/python3.12/site-packages/psutil/_psbsd.py new file mode 100644 index 0000000..13bd926 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_psbsd.py @@ -0,0 +1,971 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""FreeBSD, OpenBSD and NetBSD platforms implementation.""" + +import contextlib +import errno +import functools +import os +from collections import defaultdict +from collections import namedtuple +from xml.etree import ElementTree # noqa: ICN001 + +from . import _common +from . import _psposix +from . import _psutil_bsd as cext +from . import _psutil_posix as cext_posix +from ._common import FREEBSD +from ._common import NETBSD +from ._common import OPENBSD +from ._common import AccessDenied +from ._common import NoSuchProcess +from ._common import ZombieProcess +from ._common import conn_tmap +from ._common import conn_to_ntuple +from ._common import debug +from ._common import memoize +from ._common import memoize_when_activated +from ._common import usage_percent + + +__extra__all__ = [] + + +# ===================================================================== +# --- globals +# ===================================================================== + + +if FREEBSD: + PROC_STATUSES = { + cext.SIDL: _common.STATUS_IDLE, + cext.SRUN: _common.STATUS_RUNNING, + cext.SSLEEP: _common.STATUS_SLEEPING, + cext.SSTOP: _common.STATUS_STOPPED, + cext.SZOMB: _common.STATUS_ZOMBIE, + cext.SWAIT: _common.STATUS_WAITING, + cext.SLOCK: _common.STATUS_LOCKED, + } +elif OPENBSD: + PROC_STATUSES = { + cext.SIDL: _common.STATUS_IDLE, + cext.SSLEEP: _common.STATUS_SLEEPING, + cext.SSTOP: _common.STATUS_STOPPED, + # According to /usr/include/sys/proc.h SZOMB is unused. + # test_zombie_process() shows that SDEAD is the right + # equivalent. Also it appears there's no equivalent of + # psutil.STATUS_DEAD. SDEAD really means STATUS_ZOMBIE. + # cext.SZOMB: _common.STATUS_ZOMBIE, + cext.SDEAD: _common.STATUS_ZOMBIE, + cext.SZOMB: _common.STATUS_ZOMBIE, + # From http://www.eecs.harvard.edu/~margo/cs161/videos/proc.h.txt + # OpenBSD has SRUN and SONPROC: SRUN indicates that a process + # is runnable but *not* yet running, i.e. is on a run queue. + # SONPROC indicates that the process is actually executing on + # a CPU, i.e. it is no longer on a run queue. + # As such we'll map SRUN to STATUS_WAKING and SONPROC to + # STATUS_RUNNING + cext.SRUN: _common.STATUS_WAKING, + cext.SONPROC: _common.STATUS_RUNNING, + } +elif NETBSD: + PROC_STATUSES = { + cext.SIDL: _common.STATUS_IDLE, + cext.SSLEEP: _common.STATUS_SLEEPING, + cext.SSTOP: _common.STATUS_STOPPED, + cext.SZOMB: _common.STATUS_ZOMBIE, + cext.SRUN: _common.STATUS_WAKING, + cext.SONPROC: _common.STATUS_RUNNING, + } + +TCP_STATUSES = { + cext.TCPS_ESTABLISHED: _common.CONN_ESTABLISHED, + cext.TCPS_SYN_SENT: _common.CONN_SYN_SENT, + cext.TCPS_SYN_RECEIVED: _common.CONN_SYN_RECV, + cext.TCPS_FIN_WAIT_1: _common.CONN_FIN_WAIT1, + cext.TCPS_FIN_WAIT_2: _common.CONN_FIN_WAIT2, + cext.TCPS_TIME_WAIT: _common.CONN_TIME_WAIT, + cext.TCPS_CLOSED: _common.CONN_CLOSE, + cext.TCPS_CLOSE_WAIT: _common.CONN_CLOSE_WAIT, + cext.TCPS_LAST_ACK: _common.CONN_LAST_ACK, + cext.TCPS_LISTEN: _common.CONN_LISTEN, + cext.TCPS_CLOSING: _common.CONN_CLOSING, + cext.PSUTIL_CONN_NONE: _common.CONN_NONE, +} + +PAGESIZE = cext_posix.getpagesize() +AF_LINK = cext_posix.AF_LINK + +HAS_PER_CPU_TIMES = hasattr(cext, "per_cpu_times") +HAS_PROC_NUM_THREADS = hasattr(cext, "proc_num_threads") +HAS_PROC_OPEN_FILES = hasattr(cext, 'proc_open_files') +HAS_PROC_NUM_FDS = hasattr(cext, 'proc_num_fds') + +kinfo_proc_map = dict( + ppid=0, + status=1, + real_uid=2, + effective_uid=3, + saved_uid=4, + real_gid=5, + effective_gid=6, + saved_gid=7, + ttynr=8, + create_time=9, + ctx_switches_vol=10, + ctx_switches_unvol=11, + read_io_count=12, + write_io_count=13, + user_time=14, + sys_time=15, + ch_user_time=16, + ch_sys_time=17, + rss=18, + vms=19, + memtext=20, + memdata=21, + memstack=22, + cpunum=23, + name=24, +) + + +# ===================================================================== +# --- named tuples +# ===================================================================== + + +# fmt: off +# psutil.virtual_memory() +svmem = namedtuple( + 'svmem', ['total', 'available', 'percent', 'used', 'free', + 'active', 'inactive', 'buffers', 'cached', 'shared', 'wired']) +# psutil.cpu_times() +scputimes = namedtuple( + 'scputimes', ['user', 'nice', 'system', 'idle', 'irq']) +# psutil.Process.memory_info() +pmem = namedtuple('pmem', ['rss', 'vms', 'text', 'data', 'stack']) +# psutil.Process.memory_full_info() +pfullmem = pmem +# psutil.Process.cpu_times() +pcputimes = namedtuple('pcputimes', + ['user', 'system', 'children_user', 'children_system']) +# psutil.Process.memory_maps(grouped=True) +pmmap_grouped = namedtuple( + 'pmmap_grouped', 'path rss, private, ref_count, shadow_count') +# psutil.Process.memory_maps(grouped=False) +pmmap_ext = namedtuple( + 'pmmap_ext', 'addr, perms path rss, private, ref_count, shadow_count') +# psutil.disk_io_counters() +if FREEBSD: + sdiskio = namedtuple('sdiskio', ['read_count', 'write_count', + 'read_bytes', 'write_bytes', + 'read_time', 'write_time', + 'busy_time']) +else: + sdiskio = namedtuple('sdiskio', ['read_count', 'write_count', + 'read_bytes', 'write_bytes']) +# fmt: on + + +# ===================================================================== +# --- memory +# ===================================================================== + + +def virtual_memory(): + mem = cext.virtual_mem() + if NETBSD: + total, free, active, inactive, wired, cached = mem + # On NetBSD buffers and shared mem is determined via /proc. + # The C ext set them to 0. + with open('/proc/meminfo', 'rb') as f: + for line in f: + if line.startswith(b'Buffers:'): + buffers = int(line.split()[1]) * 1024 + elif line.startswith(b'MemShared:'): + shared = int(line.split()[1]) * 1024 + # Before avail was calculated as (inactive + cached + free), + # same as zabbix, but it turned out it could exceed total (see + # #2233), so zabbix seems to be wrong. Htop calculates it + # differently, and the used value seem more realistic, so let's + # match htop. + # https://github.com/htop-dev/htop/blob/e7f447b/netbsd/NetBSDProcessList.c#L162 + # https://github.com/zabbix/zabbix/blob/af5e0f8/src/libs/zbxsysinfo/netbsd/memory.c#L135 + used = active + wired + avail = total - used + else: + total, free, active, inactive, wired, cached, buffers, shared = mem + # matches freebsd-memory CLI: + # * https://people.freebsd.org/~rse/dist/freebsd-memory + # * https://www.cyberciti.biz/files/scripts/freebsd-memory.pl.txt + # matches zabbix: + # * https://github.com/zabbix/zabbix/blob/af5e0f8/src/libs/zbxsysinfo/freebsd/memory.c#L143 + avail = inactive + cached + free + used = active + wired + cached + + percent = usage_percent((total - avail), total, round_=1) + return svmem( + total, + avail, + percent, + used, + free, + active, + inactive, + buffers, + cached, + shared, + wired, + ) + + +def swap_memory(): + """System swap memory as (total, used, free, sin, sout) namedtuple.""" + total, used, free, sin, sout = cext.swap_mem() + percent = usage_percent(used, total, round_=1) + return _common.sswap(total, used, free, percent, sin, sout) + + +# ===================================================================== +# --- CPU +# ===================================================================== + + +def cpu_times(): + """Return system per-CPU times as a namedtuple.""" + user, nice, system, idle, irq = cext.cpu_times() + return scputimes(user, nice, system, idle, irq) + + +if HAS_PER_CPU_TIMES: + + def per_cpu_times(): + """Return system CPU times as a namedtuple.""" + ret = [] + for cpu_t in cext.per_cpu_times(): + user, nice, system, idle, irq = cpu_t + item = scputimes(user, nice, system, idle, irq) + ret.append(item) + return ret + +else: + # XXX + # Ok, this is very dirty. + # On FreeBSD < 8 we cannot gather per-cpu information, see: + # https://github.com/giampaolo/psutil/issues/226 + # If num cpus > 1, on first call we return single cpu times to avoid a + # crash at psutil import time. + # Next calls will fail with NotImplementedError + def per_cpu_times(): + """Return system CPU times as a namedtuple.""" + if cpu_count_logical() == 1: + return [cpu_times()] + if per_cpu_times.__called__: + msg = "supported only starting from FreeBSD 8" + raise NotImplementedError(msg) + per_cpu_times.__called__ = True + return [cpu_times()] + + per_cpu_times.__called__ = False + + +def cpu_count_logical(): + """Return the number of logical CPUs in the system.""" + return cext.cpu_count_logical() + + +if OPENBSD or NETBSD: + + def cpu_count_cores(): + # OpenBSD and NetBSD do not implement this. + return 1 if cpu_count_logical() == 1 else None + +else: + + def cpu_count_cores(): + """Return the number of CPU cores in the system.""" + # From the C module we'll get an XML string similar to this: + # http://manpages.ubuntu.com/manpages/precise/man4/smp.4freebsd.html + # We may get None in case "sysctl kern.sched.topology_spec" + # is not supported on this BSD version, in which case we'll mimic + # os.cpu_count() and return None. + ret = None + s = cext.cpu_topology() + if s is not None: + # get rid of padding chars appended at the end of the string + index = s.rfind("") + if index != -1: + s = s[: index + 9] + root = ElementTree.fromstring(s) + try: + ret = len(root.findall('group/children/group/cpu')) or None + finally: + # needed otherwise it will memleak + root.clear() + if not ret: + # If logical CPUs == 1 it's obvious we' have only 1 core. + if cpu_count_logical() == 1: + return 1 + return ret + + +def cpu_stats(): + """Return various CPU stats as a named tuple.""" + if FREEBSD: + # Note: the C ext is returning some metrics we are not exposing: + # traps. + ctxsw, intrs, soft_intrs, syscalls, _traps = cext.cpu_stats() + elif NETBSD: + # XXX + # Note about intrs: the C extension returns 0. intrs + # can be determined via /proc/stat; it has the same value as + # soft_intrs thought so the kernel is faking it (?). + # + # Note about syscalls: the C extension always sets it to 0 (?). + # + # Note: the C ext is returning some metrics we are not exposing: + # traps, faults and forks. + ctxsw, intrs, soft_intrs, syscalls, _traps, _faults, _forks = ( + cext.cpu_stats() + ) + with open('/proc/stat', 'rb') as f: + for line in f: + if line.startswith(b'intr'): + intrs = int(line.split()[1]) + elif OPENBSD: + # Note: the C ext is returning some metrics we are not exposing: + # traps, faults and forks. + ctxsw, intrs, soft_intrs, syscalls, _traps, _faults, _forks = ( + cext.cpu_stats() + ) + return _common.scpustats(ctxsw, intrs, soft_intrs, syscalls) + + +if FREEBSD: + + def cpu_freq(): + """Return frequency metrics for CPUs. As of Dec 2018 only + CPU 0 appears to be supported by FreeBSD and all other cores + match the frequency of CPU 0. + """ + ret = [] + num_cpus = cpu_count_logical() + for cpu in range(num_cpus): + try: + current, available_freq = cext.cpu_freq(cpu) + except NotImplementedError: + continue + if available_freq: + try: + min_freq = int(available_freq.split(" ")[-1].split("/")[0]) + except (IndexError, ValueError): + min_freq = None + try: + max_freq = int(available_freq.split(" ")[0].split("/")[0]) + except (IndexError, ValueError): + max_freq = None + ret.append(_common.scpufreq(current, min_freq, max_freq)) + return ret + +elif OPENBSD: + + def cpu_freq(): + curr = float(cext.cpu_freq()) + return [_common.scpufreq(curr, 0.0, 0.0)] + + +# ===================================================================== +# --- disks +# ===================================================================== + + +def disk_partitions(all=False): + """Return mounted disk partitions as a list of namedtuples. + 'all' argument is ignored, see: + https://github.com/giampaolo/psutil/issues/906. + """ + retlist = [] + partitions = cext.disk_partitions() + for partition in partitions: + device, mountpoint, fstype, opts = partition + ntuple = _common.sdiskpart(device, mountpoint, fstype, opts) + retlist.append(ntuple) + return retlist + + +disk_usage = _psposix.disk_usage +disk_io_counters = cext.disk_io_counters + + +# ===================================================================== +# --- network +# ===================================================================== + + +net_io_counters = cext.net_io_counters +net_if_addrs = cext_posix.net_if_addrs + + +def net_if_stats(): + """Get NIC stats (isup, duplex, speed, mtu).""" + names = net_io_counters().keys() + ret = {} + for name in names: + try: + mtu = cext_posix.net_if_mtu(name) + flags = cext_posix.net_if_flags(name) + duplex, speed = cext_posix.net_if_duplex_speed(name) + except OSError as err: + # https://github.com/giampaolo/psutil/issues/1279 + if err.errno != errno.ENODEV: + raise + else: + if hasattr(_common, 'NicDuplex'): + duplex = _common.NicDuplex(duplex) + output_flags = ','.join(flags) + isup = 'running' in flags + ret[name] = _common.snicstats( + isup, duplex, speed, mtu, output_flags + ) + return ret + + +def net_connections(kind): + """System-wide network connections.""" + families, types = conn_tmap[kind] + ret = set() + if OPENBSD: + rawlist = cext.net_connections(-1, families, types) + elif NETBSD: + rawlist = cext.net_connections(-1, kind) + else: # FreeBSD + rawlist = cext.net_connections(families, types) + + for item in rawlist: + fd, fam, type, laddr, raddr, status, pid = item + nt = conn_to_ntuple( + fd, fam, type, laddr, raddr, status, TCP_STATUSES, pid + ) + ret.add(nt) + return list(ret) + + +# ===================================================================== +# --- sensors +# ===================================================================== + + +if FREEBSD: + + def sensors_battery(): + """Return battery info.""" + try: + percent, minsleft, power_plugged = cext.sensors_battery() + except NotImplementedError: + # See: https://github.com/giampaolo/psutil/issues/1074 + return None + power_plugged = power_plugged == 1 + if power_plugged: + secsleft = _common.POWER_TIME_UNLIMITED + elif minsleft == -1: + secsleft = _common.POWER_TIME_UNKNOWN + else: + secsleft = minsleft * 60 + return _common.sbattery(percent, secsleft, power_plugged) + + def sensors_temperatures(): + """Return CPU cores temperatures if available, else an empty dict.""" + ret = defaultdict(list) + num_cpus = cpu_count_logical() + for cpu in range(num_cpus): + try: + current, high = cext.sensors_cpu_temperature(cpu) + if high <= 0: + high = None + name = f"Core {cpu}" + ret["coretemp"].append( + _common.shwtemp(name, current, high, high) + ) + except NotImplementedError: + pass + + return ret + + +# ===================================================================== +# --- other system functions +# ===================================================================== + + +def boot_time(): + """The system boot time expressed in seconds since the epoch.""" + return cext.boot_time() + + +def users(): + """Return currently connected users as a list of namedtuples.""" + retlist = [] + rawlist = cext.users() + for item in rawlist: + user, tty, hostname, tstamp, pid = item + if pid == -1: + assert OPENBSD + pid = None + if tty == '~': + continue # reboot or shutdown + nt = _common.suser(user, tty or None, hostname, tstamp, pid) + retlist.append(nt) + return retlist + + +# ===================================================================== +# --- processes +# ===================================================================== + + +@memoize +def _pid_0_exists(): + try: + Process(0).name() + except NoSuchProcess: + return False + except AccessDenied: + return True + else: + return True + + +def pids(): + """Returns a list of PIDs currently running on the system.""" + ret = cext.pids() + if OPENBSD and (0 not in ret) and _pid_0_exists(): + # On OpenBSD the kernel does not return PID 0 (neither does + # ps) but it's actually querable (Process(0) will succeed). + ret.insert(0, 0) + return ret + + +if NETBSD: + + def pid_exists(pid): + exists = _psposix.pid_exists(pid) + if not exists: + # We do this because _psposix.pid_exists() lies in case of + # zombie processes. + return pid in pids() + else: + return True + +elif OPENBSD: + + def pid_exists(pid): + exists = _psposix.pid_exists(pid) + if not exists: + return False + else: + # OpenBSD seems to be the only BSD platform where + # _psposix.pid_exists() returns True for thread IDs (tids), + # so we can't use it. + return pid in pids() + +else: # FreeBSD + pid_exists = _psposix.pid_exists + + +def is_zombie(pid): + try: + st = cext.proc_oneshot_info(pid)[kinfo_proc_map['status']] + return PROC_STATUSES.get(st) == _common.STATUS_ZOMBIE + except OSError: + return False + + +def wrap_exceptions(fun): + """Decorator which translates bare OSError exceptions into + NoSuchProcess and AccessDenied. + """ + + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + pid, ppid, name = self.pid, self._ppid, self._name + try: + return fun(self, *args, **kwargs) + except ProcessLookupError as err: + if is_zombie(pid): + raise ZombieProcess(pid, name, ppid) from err + raise NoSuchProcess(pid, name) from err + except PermissionError as err: + raise AccessDenied(pid, name) from err + except OSError as err: + if pid == 0 and 0 in pids(): + raise AccessDenied(pid, name) from err + raise + + return wrapper + + +@contextlib.contextmanager +def wrap_exceptions_procfs(inst): + """Same as above, for routines relying on reading /proc fs.""" + pid, name, ppid = inst.pid, inst._name, inst._ppid + try: + yield + except (ProcessLookupError, FileNotFoundError) as err: + # ENOENT (no such file or directory) gets raised on open(). + # ESRCH (no such process) can get raised on read() if + # process is gone in meantime. + if is_zombie(inst.pid): + raise ZombieProcess(pid, name, ppid) from err + else: + raise NoSuchProcess(pid, name) from err + except PermissionError as err: + raise AccessDenied(pid, name) from err + + +class Process: + """Wrapper class around underlying C implementation.""" + + __slots__ = ["_cache", "_name", "_ppid", "pid"] + + def __init__(self, pid): + self.pid = pid + self._name = None + self._ppid = None + + def _assert_alive(self): + """Raise NSP if the process disappeared on us.""" + # For those C function who do not raise NSP, possibly returning + # incorrect or incomplete result. + cext.proc_name(self.pid) + + @wrap_exceptions + @memoize_when_activated + def oneshot(self): + """Retrieves multiple process info in one shot as a raw tuple.""" + ret = cext.proc_oneshot_info(self.pid) + assert len(ret) == len(kinfo_proc_map) + return ret + + def oneshot_enter(self): + self.oneshot.cache_activate(self) + + def oneshot_exit(self): + self.oneshot.cache_deactivate(self) + + @wrap_exceptions + def name(self): + name = self.oneshot()[kinfo_proc_map['name']] + return name if name is not None else cext.proc_name(self.pid) + + @wrap_exceptions + def exe(self): + if FREEBSD: + if self.pid == 0: + return '' # else NSP + return cext.proc_exe(self.pid) + elif NETBSD: + if self.pid == 0: + # /proc/0 dir exists but /proc/0/exe doesn't + return "" + with wrap_exceptions_procfs(self): + return os.readlink(f"/proc/{self.pid}/exe") + else: + # OpenBSD: exe cannot be determined; references: + # https://chromium.googlesource.com/chromium/src/base/+/ + # master/base_paths_posix.cc + # We try our best guess by using which against the first + # cmdline arg (may return None). + import shutil + + cmdline = self.cmdline() + if cmdline: + return shutil.which(cmdline[0]) or "" + else: + return "" + + @wrap_exceptions + def cmdline(self): + if OPENBSD and self.pid == 0: + return [] # ...else it crashes + elif NETBSD: + # XXX - most of the times the underlying sysctl() call on + # NetBSD and OpenBSD returns a truncated string. Also + # /proc/pid/cmdline behaves the same so it looks like this + # is a kernel bug. + try: + return cext.proc_cmdline(self.pid) + except OSError as err: + if err.errno == errno.EINVAL: + pid, name, ppid = self.pid, self._name, self._ppid + if is_zombie(self.pid): + raise ZombieProcess(pid, name, ppid) from err + if not pid_exists(self.pid): + raise NoSuchProcess(pid, name, ppid) from err + # XXX: this happens with unicode tests. It means the C + # routine is unable to decode invalid unicode chars. + debug(f"ignoring {err!r} and returning an empty list") + return [] + else: + raise + else: + return cext.proc_cmdline(self.pid) + + @wrap_exceptions + def environ(self): + return cext.proc_environ(self.pid) + + @wrap_exceptions + def terminal(self): + tty_nr = self.oneshot()[kinfo_proc_map['ttynr']] + tmap = _psposix.get_terminal_map() + try: + return tmap[tty_nr] + except KeyError: + return None + + @wrap_exceptions + def ppid(self): + self._ppid = self.oneshot()[kinfo_proc_map['ppid']] + return self._ppid + + @wrap_exceptions + def uids(self): + rawtuple = self.oneshot() + return _common.puids( + rawtuple[kinfo_proc_map['real_uid']], + rawtuple[kinfo_proc_map['effective_uid']], + rawtuple[kinfo_proc_map['saved_uid']], + ) + + @wrap_exceptions + def gids(self): + rawtuple = self.oneshot() + return _common.pgids( + rawtuple[kinfo_proc_map['real_gid']], + rawtuple[kinfo_proc_map['effective_gid']], + rawtuple[kinfo_proc_map['saved_gid']], + ) + + @wrap_exceptions + def cpu_times(self): + rawtuple = self.oneshot() + return _common.pcputimes( + rawtuple[kinfo_proc_map['user_time']], + rawtuple[kinfo_proc_map['sys_time']], + rawtuple[kinfo_proc_map['ch_user_time']], + rawtuple[kinfo_proc_map['ch_sys_time']], + ) + + if FREEBSD: + + @wrap_exceptions + def cpu_num(self): + return self.oneshot()[kinfo_proc_map['cpunum']] + + @wrap_exceptions + def memory_info(self): + rawtuple = self.oneshot() + return pmem( + rawtuple[kinfo_proc_map['rss']], + rawtuple[kinfo_proc_map['vms']], + rawtuple[kinfo_proc_map['memtext']], + rawtuple[kinfo_proc_map['memdata']], + rawtuple[kinfo_proc_map['memstack']], + ) + + memory_full_info = memory_info + + @wrap_exceptions + def create_time(self): + return self.oneshot()[kinfo_proc_map['create_time']] + + @wrap_exceptions + def num_threads(self): + if HAS_PROC_NUM_THREADS: + # FreeBSD + return cext.proc_num_threads(self.pid) + else: + return len(self.threads()) + + @wrap_exceptions + def num_ctx_switches(self): + rawtuple = self.oneshot() + return _common.pctxsw( + rawtuple[kinfo_proc_map['ctx_switches_vol']], + rawtuple[kinfo_proc_map['ctx_switches_unvol']], + ) + + @wrap_exceptions + def threads(self): + # Note: on OpenSBD this (/dev/mem) requires root access. + rawlist = cext.proc_threads(self.pid) + retlist = [] + for thread_id, utime, stime in rawlist: + ntuple = _common.pthread(thread_id, utime, stime) + retlist.append(ntuple) + if OPENBSD: + self._assert_alive() + return retlist + + @wrap_exceptions + def net_connections(self, kind='inet'): + families, types = conn_tmap[kind] + ret = [] + + if NETBSD: + rawlist = cext.net_connections(self.pid, kind) + elif OPENBSD: + rawlist = cext.net_connections(self.pid, families, types) + else: + rawlist = cext.proc_net_connections(self.pid, families, types) + + for item in rawlist: + fd, fam, type, laddr, raddr, status = item[:6] + if FREEBSD: + if (fam not in families) or (type not in types): + continue + nt = conn_to_ntuple( + fd, fam, type, laddr, raddr, status, TCP_STATUSES + ) + ret.append(nt) + + self._assert_alive() + return ret + + @wrap_exceptions + def wait(self, timeout=None): + return _psposix.wait_pid(self.pid, timeout, self._name) + + @wrap_exceptions + def nice_get(self): + return cext_posix.getpriority(self.pid) + + @wrap_exceptions + def nice_set(self, value): + return cext_posix.setpriority(self.pid, value) + + @wrap_exceptions + def status(self): + code = self.oneshot()[kinfo_proc_map['status']] + # XXX is '?' legit? (we're not supposed to return it anyway) + return PROC_STATUSES.get(code, '?') + + @wrap_exceptions + def io_counters(self): + rawtuple = self.oneshot() + return _common.pio( + rawtuple[kinfo_proc_map['read_io_count']], + rawtuple[kinfo_proc_map['write_io_count']], + -1, + -1, + ) + + @wrap_exceptions + def cwd(self): + """Return process current working directory.""" + # sometimes we get an empty string, in which case we turn + # it into None + if OPENBSD and self.pid == 0: + return "" # ...else it would raise EINVAL + elif NETBSD or HAS_PROC_OPEN_FILES: + # FreeBSD < 8 does not support functions based on + # kinfo_getfile() and kinfo_getvmmap() + return cext.proc_cwd(self.pid) + else: + raise NotImplementedError( + "supported only starting from FreeBSD 8" if FREEBSD else "" + ) + + nt_mmap_grouped = namedtuple( + 'mmap', 'path rss, private, ref_count, shadow_count' + ) + nt_mmap_ext = namedtuple( + 'mmap', 'addr, perms path rss, private, ref_count, shadow_count' + ) + + def _not_implemented(self): + raise NotImplementedError + + # FreeBSD < 8 does not support functions based on kinfo_getfile() + # and kinfo_getvmmap() + if HAS_PROC_OPEN_FILES: + + @wrap_exceptions + def open_files(self): + """Return files opened by process as a list of namedtuples.""" + rawlist = cext.proc_open_files(self.pid) + return [_common.popenfile(path, fd) for path, fd in rawlist] + + else: + open_files = _not_implemented + + # FreeBSD < 8 does not support functions based on kinfo_getfile() + # and kinfo_getvmmap() + if HAS_PROC_NUM_FDS: + + @wrap_exceptions + def num_fds(self): + """Return the number of file descriptors opened by this process.""" + ret = cext.proc_num_fds(self.pid) + if NETBSD: + self._assert_alive() + return ret + + else: + num_fds = _not_implemented + + # --- FreeBSD only APIs + + if FREEBSD: + + @wrap_exceptions + def cpu_affinity_get(self): + return cext.proc_cpu_affinity_get(self.pid) + + @wrap_exceptions + def cpu_affinity_set(self, cpus): + # Pre-emptively check if CPUs are valid because the C + # function has a weird behavior in case of invalid CPUs, + # see: https://github.com/giampaolo/psutil/issues/586 + allcpus = set(range(len(per_cpu_times()))) + for cpu in cpus: + if cpu not in allcpus: + msg = f"invalid CPU {cpu!r} (choose between {allcpus})" + raise ValueError(msg) + try: + cext.proc_cpu_affinity_set(self.pid, cpus) + except OSError as err: + # 'man cpuset_setaffinity' about EDEADLK: + # <> + if err.errno in {errno.EINVAL, errno.EDEADLK}: + for cpu in cpus: + if cpu not in allcpus: + msg = ( + f"invalid CPU {cpu!r} (choose between" + f" {allcpus})" + ) + raise ValueError(msg) from err + raise + + @wrap_exceptions + def memory_maps(self): + return cext.proc_memory_maps(self.pid) + + @wrap_exceptions + def rlimit(self, resource, limits=None): + if limits is None: + return cext.proc_getrlimit(self.pid, resource) + else: + if len(limits) != 2: + msg = ( + "second argument must be a (soft, hard) tuple, got" + f" {limits!r}" + ) + raise ValueError(msg) + soft, hard = limits + return cext.proc_setrlimit(self.pid, resource, soft, hard) diff --git a/llmlab/lib/python3.12/site-packages/psutil/_pslinux.py b/llmlab/lib/python3.12/site-packages/psutil/_pslinux.py new file mode 100644 index 0000000..8cc64e9 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_pslinux.py @@ -0,0 +1,2295 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Linux platform implementation.""" + + +import base64 +import collections +import enum +import errno +import functools +import glob +import os +import re +import resource +import socket +import struct +import sys +import warnings +from collections import defaultdict +from collections import namedtuple + +from . import _common +from . import _psposix +from . import _psutil_linux as cext +from . import _psutil_posix as cext_posix +from ._common import ENCODING +from ._common import NIC_DUPLEX_FULL +from ._common import NIC_DUPLEX_HALF +from ._common import NIC_DUPLEX_UNKNOWN +from ._common import AccessDenied +from ._common import NoSuchProcess +from ._common import ZombieProcess +from ._common import bcat +from ._common import cat +from ._common import debug +from ._common import decode +from ._common import get_procfs_path +from ._common import isfile_strict +from ._common import memoize +from ._common import memoize_when_activated +from ._common import open_binary +from ._common import open_text +from ._common import parse_environ_block +from ._common import path_exists_strict +from ._common import supports_ipv6 +from ._common import usage_percent + + +# fmt: off +__extra__all__ = [ + 'PROCFS_PATH', + # io prio constants + "IOPRIO_CLASS_NONE", "IOPRIO_CLASS_RT", "IOPRIO_CLASS_BE", + "IOPRIO_CLASS_IDLE", + # connection status constants + "CONN_ESTABLISHED", "CONN_SYN_SENT", "CONN_SYN_RECV", "CONN_FIN_WAIT1", + "CONN_FIN_WAIT2", "CONN_TIME_WAIT", "CONN_CLOSE", "CONN_CLOSE_WAIT", + "CONN_LAST_ACK", "CONN_LISTEN", "CONN_CLOSING", +] + +if hasattr(resource, "prlimit"): + __extra__all__.extend( + [x for x in dir(cext) if x.startswith('RLIM') and x.isupper()] + ) +# fmt: on + + +# ===================================================================== +# --- globals +# ===================================================================== + + +POWER_SUPPLY_PATH = "/sys/class/power_supply" +HAS_PROC_SMAPS = os.path.exists(f"/proc/{os.getpid()}/smaps") +HAS_PROC_SMAPS_ROLLUP = os.path.exists(f"/proc/{os.getpid()}/smaps_rollup") +HAS_PROC_IO_PRIORITY = hasattr(cext, "proc_ioprio_get") +HAS_CPU_AFFINITY = hasattr(cext, "proc_cpu_affinity_get") + +# Number of clock ticks per second +CLOCK_TICKS = os.sysconf("SC_CLK_TCK") +PAGESIZE = cext_posix.getpagesize() +BOOT_TIME = None # set later +LITTLE_ENDIAN = sys.byteorder == 'little' + +# "man iostat" states that sectors are equivalent with blocks and have +# a size of 512 bytes. Despite this value can be queried at runtime +# via /sys/block/{DISK}/queue/hw_sector_size and results may vary +# between 1k, 2k, or 4k... 512 appears to be a magic constant used +# throughout Linux source code: +# * https://stackoverflow.com/a/38136179/376587 +# * https://lists.gt.net/linux/kernel/2241060 +# * https://github.com/giampaolo/psutil/issues/1305 +# * https://github.com/torvalds/linux/blob/ +# 4f671fe2f9523a1ea206f63fe60a7c7b3a56d5c7/include/linux/bio.h#L99 +# * https://lkml.org/lkml/2015/8/17/234 +DISK_SECTOR_SIZE = 512 + +AddressFamily = enum.IntEnum( + 'AddressFamily', {'AF_LINK': int(socket.AF_PACKET)} +) +AF_LINK = AddressFamily.AF_LINK + + +# ioprio_* constants http://linux.die.net/man/2/ioprio_get +class IOPriority(enum.IntEnum): + IOPRIO_CLASS_NONE = 0 + IOPRIO_CLASS_RT = 1 + IOPRIO_CLASS_BE = 2 + IOPRIO_CLASS_IDLE = 3 + + +globals().update(IOPriority.__members__) + +# See: +# https://github.com/torvalds/linux/blame/master/fs/proc/array.c +# ...and (TASK_* constants): +# https://github.com/torvalds/linux/blob/master/include/linux/sched.h +PROC_STATUSES = { + "R": _common.STATUS_RUNNING, + "S": _common.STATUS_SLEEPING, + "D": _common.STATUS_DISK_SLEEP, + "T": _common.STATUS_STOPPED, + "t": _common.STATUS_TRACING_STOP, + "Z": _common.STATUS_ZOMBIE, + "X": _common.STATUS_DEAD, + "x": _common.STATUS_DEAD, + "K": _common.STATUS_WAKE_KILL, + "W": _common.STATUS_WAKING, + "I": _common.STATUS_IDLE, + "P": _common.STATUS_PARKED, +} + +# https://github.com/torvalds/linux/blob/master/include/net/tcp_states.h +TCP_STATUSES = { + "01": _common.CONN_ESTABLISHED, + "02": _common.CONN_SYN_SENT, + "03": _common.CONN_SYN_RECV, + "04": _common.CONN_FIN_WAIT1, + "05": _common.CONN_FIN_WAIT2, + "06": _common.CONN_TIME_WAIT, + "07": _common.CONN_CLOSE, + "08": _common.CONN_CLOSE_WAIT, + "09": _common.CONN_LAST_ACK, + "0A": _common.CONN_LISTEN, + "0B": _common.CONN_CLOSING, +} + + +# ===================================================================== +# --- named tuples +# ===================================================================== + + +# fmt: off +# psutil.virtual_memory() +svmem = namedtuple( + 'svmem', ['total', 'available', 'percent', 'used', 'free', + 'active', 'inactive', 'buffers', 'cached', 'shared', 'slab']) +# psutil.disk_io_counters() +sdiskio = namedtuple( + 'sdiskio', ['read_count', 'write_count', + 'read_bytes', 'write_bytes', + 'read_time', 'write_time', + 'read_merged_count', 'write_merged_count', + 'busy_time']) +# psutil.Process().open_files() +popenfile = namedtuple( + 'popenfile', ['path', 'fd', 'position', 'mode', 'flags']) +# psutil.Process().memory_info() +pmem = namedtuple('pmem', 'rss vms shared text lib data dirty') +# psutil.Process().memory_full_info() +pfullmem = namedtuple('pfullmem', pmem._fields + ('uss', 'pss', 'swap')) +# psutil.Process().memory_maps(grouped=True) +pmmap_grouped = namedtuple( + 'pmmap_grouped', + ['path', 'rss', 'size', 'pss', 'shared_clean', 'shared_dirty', + 'private_clean', 'private_dirty', 'referenced', 'anonymous', 'swap']) +# psutil.Process().memory_maps(grouped=False) +pmmap_ext = namedtuple( + 'pmmap_ext', 'addr perms ' + ' '.join(pmmap_grouped._fields)) +# psutil.Process.io_counters() +pio = namedtuple('pio', ['read_count', 'write_count', + 'read_bytes', 'write_bytes', + 'read_chars', 'write_chars']) +# psutil.Process.cpu_times() +pcputimes = namedtuple('pcputimes', + ['user', 'system', 'children_user', 'children_system', + 'iowait']) +# fmt: on + + +# ===================================================================== +# --- utils +# ===================================================================== + + +def readlink(path): + """Wrapper around os.readlink().""" + assert isinstance(path, str), path + path = os.readlink(path) + # readlink() might return paths containing null bytes ('\x00') + # resulting in "TypeError: must be encoded string without NULL + # bytes, not str" errors when the string is passed to other + # fs-related functions (os.*, open(), ...). + # Apparently everything after '\x00' is garbage (we can have + # ' (deleted)', 'new' and possibly others), see: + # https://github.com/giampaolo/psutil/issues/717 + path = path.split('\x00')[0] + # Certain paths have ' (deleted)' appended. Usually this is + # bogus as the file actually exists. Even if it doesn't we + # don't care. + if path.endswith(' (deleted)') and not path_exists_strict(path): + path = path[:-10] + return path + + +def file_flags_to_mode(flags): + """Convert file's open() flags into a readable string. + Used by Process.open_files(). + """ + modes_map = {os.O_RDONLY: 'r', os.O_WRONLY: 'w', os.O_RDWR: 'w+'} + mode = modes_map[flags & (os.O_RDONLY | os.O_WRONLY | os.O_RDWR)] + if flags & os.O_APPEND: + mode = mode.replace('w', 'a', 1) + mode = mode.replace('w+', 'r+') + # possible values: r, w, a, r+, a+ + return mode + + +def is_storage_device(name): + """Return True if the given name refers to a root device (e.g. + "sda", "nvme0n1") as opposed to a logical partition (e.g. "sda1", + "nvme0n1p1"). If name is a virtual device (e.g. "loop1", "ram") + return True. + """ + # Re-adapted from iostat source code, see: + # https://github.com/sysstat/sysstat/blob/ + # 97912938cd476645b267280069e83b1c8dc0e1c7/common.c#L208 + # Some devices may have a slash in their name (e.g. cciss/c0d0...). + name = name.replace('/', '!') + including_virtual = True + if including_virtual: + path = f"/sys/block/{name}" + else: + path = f"/sys/block/{name}/device" + return os.access(path, os.F_OK) + + +@memoize +def set_scputimes_ntuple(procfs_path): + """Set a namedtuple of variable fields depending on the CPU times + available on this Linux kernel version which may be: + (user, nice, system, idle, iowait, irq, softirq, [steal, [guest, + [guest_nice]]]) + Used by cpu_times() function. + """ + global scputimes + with open_binary(f"{procfs_path}/stat") as f: + values = f.readline().split()[1:] + fields = ['user', 'nice', 'system', 'idle', 'iowait', 'irq', 'softirq'] + vlen = len(values) + if vlen >= 8: + # Linux >= 2.6.11 + fields.append('steal') + if vlen >= 9: + # Linux >= 2.6.24 + fields.append('guest') + if vlen >= 10: + # Linux >= 3.2.0 + fields.append('guest_nice') + scputimes = namedtuple('scputimes', fields) + + +try: + set_scputimes_ntuple("/proc") +except Exception as err: # noqa: BLE001 + # Don't want to crash at import time. + debug(f"ignoring exception on import: {err!r}") + scputimes = namedtuple('scputimes', 'user system idle')(0.0, 0.0, 0.0) + + +# ===================================================================== +# --- system memory +# ===================================================================== + + +def calculate_avail_vmem(mems): + """Fallback for kernels < 3.14 where /proc/meminfo does not provide + "MemAvailable", see: + https://blog.famzah.net/2014/09/24/. + + This code reimplements the algorithm outlined here: + https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/ + commit/?id=34e431b0ae398fc54ea69ff85ec700722c9da773 + + We use this function also when "MemAvailable" returns 0 (possibly a + kernel bug, see: https://github.com/giampaolo/psutil/issues/1915). + In that case this routine matches "free" CLI tool result ("available" + column). + + XXX: on recent kernels this calculation may differ by ~1.5% compared + to "MemAvailable:", as it's calculated slightly differently. + It is still way more realistic than doing (free + cached) though. + See: + * https://gitlab.com/procps-ng/procps/issues/42 + * https://github.com/famzah/linux-memavailable-procfs/issues/2 + """ + # Note about "fallback" value. According to: + # https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/ + # commit/?id=34e431b0ae398fc54ea69ff85ec700722c9da773 + # ...long ago "available" memory was calculated as (free + cached), + # We use fallback when one of these is missing from /proc/meminfo: + # "Active(file)": introduced in 2.6.28 / Dec 2008 + # "Inactive(file)": introduced in 2.6.28 / Dec 2008 + # "SReclaimable": introduced in 2.6.19 / Nov 2006 + # /proc/zoneinfo: introduced in 2.6.13 / Aug 2005 + free = mems[b'MemFree:'] + fallback = free + mems.get(b"Cached:", 0) + try: + lru_active_file = mems[b'Active(file):'] + lru_inactive_file = mems[b'Inactive(file):'] + slab_reclaimable = mems[b'SReclaimable:'] + except KeyError as err: + debug( + f"{err.args[0]} is missing from /proc/meminfo; using an" + " approximation for calculating available memory" + ) + return fallback + try: + f = open_binary(f"{get_procfs_path()}/zoneinfo") + except OSError: + return fallback # kernel 2.6.13 + + watermark_low = 0 + with f: + for line in f: + line = line.strip() + if line.startswith(b'low'): + watermark_low += int(line.split()[1]) + watermark_low *= PAGESIZE + + avail = free - watermark_low + pagecache = lru_active_file + lru_inactive_file + pagecache -= min(pagecache / 2, watermark_low) + avail += pagecache + avail += slab_reclaimable - min(slab_reclaimable / 2.0, watermark_low) + return int(avail) + + +def virtual_memory(): + """Report virtual memory stats. + This implementation mimics procps-ng-3.3.12, aka "free" CLI tool: + https://gitlab.com/procps-ng/procps/blob/ + 24fd2605c51fccc375ab0287cec33aa767f06718/proc/sysinfo.c#L778-791 + The returned values are supposed to match both "free" and "vmstat -s" + CLI tools. + """ + missing_fields = [] + mems = {} + with open_binary(f"{get_procfs_path()}/meminfo") as f: + for line in f: + fields = line.split() + mems[fields[0]] = int(fields[1]) * 1024 + + # /proc doc states that the available fields in /proc/meminfo vary + # by architecture and compile options, but these 3 values are also + # returned by sysinfo(2); as such we assume they are always there. + total = mems[b'MemTotal:'] + free = mems[b'MemFree:'] + try: + buffers = mems[b'Buffers:'] + except KeyError: + # https://github.com/giampaolo/psutil/issues/1010 + buffers = 0 + missing_fields.append('buffers') + try: + cached = mems[b"Cached:"] + except KeyError: + cached = 0 + missing_fields.append('cached') + else: + # "free" cmdline utility sums reclaimable to cached. + # Older versions of procps used to add slab memory instead. + # This got changed in: + # https://gitlab.com/procps-ng/procps/commit/ + # 05d751c4f076a2f0118b914c5e51cfbb4762ad8e + cached += mems.get(b"SReclaimable:", 0) # since kernel 2.6.19 + + try: + shared = mems[b'Shmem:'] # since kernel 2.6.32 + except KeyError: + try: + shared = mems[b'MemShared:'] # kernels 2.4 + except KeyError: + shared = 0 + missing_fields.append('shared') + + try: + active = mems[b"Active:"] + except KeyError: + active = 0 + missing_fields.append('active') + + try: + inactive = mems[b"Inactive:"] + except KeyError: + try: + inactive = ( + mems[b"Inact_dirty:"] + + mems[b"Inact_clean:"] + + mems[b"Inact_laundry:"] + ) + except KeyError: + inactive = 0 + missing_fields.append('inactive') + + try: + slab = mems[b"Slab:"] + except KeyError: + slab = 0 + + used = total - free - cached - buffers + if used < 0: + # May be symptomatic of running within a LCX container where such + # values will be dramatically distorted over those of the host. + used = total - free + + # - starting from 4.4.0 we match free's "available" column. + # Before 4.4.0 we calculated it as (free + buffers + cached) + # which matched htop. + # - free and htop available memory differs as per: + # http://askubuntu.com/a/369589 + # http://unix.stackexchange.com/a/65852/168884 + # - MemAvailable has been introduced in kernel 3.14 + try: + avail = mems[b'MemAvailable:'] + except KeyError: + avail = calculate_avail_vmem(mems) + else: + if avail == 0: + # Yes, it can happen (probably a kernel bug): + # https://github.com/giampaolo/psutil/issues/1915 + # In this case "free" CLI tool makes an estimate. We do the same, + # and it matches "free" CLI tool. + avail = calculate_avail_vmem(mems) + + if avail < 0: + avail = 0 + missing_fields.append('available') + elif avail > total: + # If avail is greater than total or our calculation overflows, + # that's symptomatic of running within a LCX container where such + # values will be dramatically distorted over those of the host. + # https://gitlab.com/procps-ng/procps/blob/ + # 24fd2605c51fccc375ab0287cec33aa767f06718/proc/sysinfo.c#L764 + avail = free + + percent = usage_percent((total - avail), total, round_=1) + + # Warn about missing metrics which are set to 0. + if missing_fields: + msg = "{} memory stats couldn't be determined and {} set to 0".format( + ", ".join(missing_fields), + "was" if len(missing_fields) == 1 else "were", + ) + warnings.warn(msg, RuntimeWarning, stacklevel=2) + + return svmem( + total, + avail, + percent, + used, + free, + active, + inactive, + buffers, + cached, + shared, + slab, + ) + + +def swap_memory(): + """Return swap memory metrics.""" + mems = {} + with open_binary(f"{get_procfs_path()}/meminfo") as f: + for line in f: + fields = line.split() + mems[fields[0]] = int(fields[1]) * 1024 + # We prefer /proc/meminfo over sysinfo() syscall so that + # psutil.PROCFS_PATH can be used in order to allow retrieval + # for linux containers, see: + # https://github.com/giampaolo/psutil/issues/1015 + try: + total = mems[b'SwapTotal:'] + free = mems[b'SwapFree:'] + except KeyError: + _, _, _, _, total, free, unit_multiplier = cext.linux_sysinfo() + total *= unit_multiplier + free *= unit_multiplier + + used = total - free + percent = usage_percent(used, total, round_=1) + # get pgin/pgouts + try: + f = open_binary(f"{get_procfs_path()}/vmstat") + except OSError as err: + # see https://github.com/giampaolo/psutil/issues/722 + msg = ( + "'sin' and 'sout' swap memory stats couldn't " + f"be determined and were set to 0 ({err})" + ) + warnings.warn(msg, RuntimeWarning, stacklevel=2) + sin = sout = 0 + else: + with f: + sin = sout = None + for line in f: + # values are expressed in 4 kilo bytes, we want + # bytes instead + if line.startswith(b'pswpin'): + sin = int(line.split(b' ')[1]) * 4 * 1024 + elif line.startswith(b'pswpout'): + sout = int(line.split(b' ')[1]) * 4 * 1024 + if sin is not None and sout is not None: + break + else: + # we might get here when dealing with exotic Linux + # flavors, see: + # https://github.com/giampaolo/psutil/issues/313 + msg = "'sin' and 'sout' swap memory stats couldn't " + msg += "be determined and were set to 0" + warnings.warn(msg, RuntimeWarning, stacklevel=2) + sin = sout = 0 + return _common.sswap(total, used, free, percent, sin, sout) + + +# ===================================================================== +# --- CPU +# ===================================================================== + + +def cpu_times(): + """Return a named tuple representing the following system-wide + CPU times: + (user, nice, system, idle, iowait, irq, softirq [steal, [guest, + [guest_nice]]]) + Last 3 fields may not be available on all Linux kernel versions. + """ + procfs_path = get_procfs_path() + set_scputimes_ntuple(procfs_path) + with open_binary(f"{procfs_path}/stat") as f: + values = f.readline().split() + fields = values[1 : len(scputimes._fields) + 1] + fields = [float(x) / CLOCK_TICKS for x in fields] + return scputimes(*fields) + + +def per_cpu_times(): + """Return a list of namedtuple representing the CPU times + for every CPU available on the system. + """ + procfs_path = get_procfs_path() + set_scputimes_ntuple(procfs_path) + cpus = [] + with open_binary(f"{procfs_path}/stat") as f: + # get rid of the first line which refers to system wide CPU stats + f.readline() + for line in f: + if line.startswith(b'cpu'): + values = line.split() + fields = values[1 : len(scputimes._fields) + 1] + fields = [float(x) / CLOCK_TICKS for x in fields] + entry = scputimes(*fields) + cpus.append(entry) + return cpus + + +def cpu_count_logical(): + """Return the number of logical CPUs in the system.""" + try: + return os.sysconf("SC_NPROCESSORS_ONLN") + except ValueError: + # as a second fallback we try to parse /proc/cpuinfo + num = 0 + with open_binary(f"{get_procfs_path()}/cpuinfo") as f: + for line in f: + if line.lower().startswith(b'processor'): + num += 1 + + # unknown format (e.g. amrel/sparc architectures), see: + # https://github.com/giampaolo/psutil/issues/200 + # try to parse /proc/stat as a last resort + if num == 0: + search = re.compile(r'cpu\d') + with open_text(f"{get_procfs_path()}/stat") as f: + for line in f: + line = line.split(' ')[0] + if search.match(line): + num += 1 + + if num == 0: + # mimic os.cpu_count() + return None + return num + + +def cpu_count_cores(): + """Return the number of CPU cores in the system.""" + # Method #1 + ls = set() + # These 2 files are the same but */core_cpus_list is newer while + # */thread_siblings_list is deprecated and may disappear in the future. + # https://www.kernel.org/doc/Documentation/admin-guide/cputopology.rst + # https://github.com/giampaolo/psutil/pull/1727#issuecomment-707624964 + # https://lkml.org/lkml/2019/2/26/41 + p1 = "/sys/devices/system/cpu/cpu[0-9]*/topology/core_cpus_list" + p2 = "/sys/devices/system/cpu/cpu[0-9]*/topology/thread_siblings_list" + for path in glob.glob(p1) or glob.glob(p2): + with open_binary(path) as f: + ls.add(f.read().strip()) + result = len(ls) + if result != 0: + return result + + # Method #2 + mapping = {} + current_info = {} + with open_binary(f"{get_procfs_path()}/cpuinfo") as f: + for line in f: + line = line.strip().lower() + if not line: + # new section + try: + mapping[current_info[b'physical id']] = current_info[ + b'cpu cores' + ] + except KeyError: + pass + current_info = {} + elif line.startswith((b'physical id', b'cpu cores')): + # ongoing section + key, value = line.split(b'\t:', 1) + current_info[key] = int(value) + + result = sum(mapping.values()) + return result or None # mimic os.cpu_count() + + +def cpu_stats(): + """Return various CPU stats as a named tuple.""" + with open_binary(f"{get_procfs_path()}/stat") as f: + ctx_switches = None + interrupts = None + soft_interrupts = None + for line in f: + if line.startswith(b'ctxt'): + ctx_switches = int(line.split()[1]) + elif line.startswith(b'intr'): + interrupts = int(line.split()[1]) + elif line.startswith(b'softirq'): + soft_interrupts = int(line.split()[1]) + if ( + ctx_switches is not None + and soft_interrupts is not None + and interrupts is not None + ): + break + syscalls = 0 + return _common.scpustats( + ctx_switches, interrupts, soft_interrupts, syscalls + ) + + +def _cpu_get_cpuinfo_freq(): + """Return current CPU frequency from cpuinfo if available.""" + with open_binary(f"{get_procfs_path()}/cpuinfo") as f: + return [ + float(line.split(b':', 1)[1]) + for line in f + if line.lower().startswith(b'cpu mhz') + ] + + +if os.path.exists("/sys/devices/system/cpu/cpufreq/policy0") or os.path.exists( + "/sys/devices/system/cpu/cpu0/cpufreq" +): + + def cpu_freq(): + """Return frequency metrics for all CPUs. + Contrarily to other OSes, Linux updates these values in + real-time. + """ + cpuinfo_freqs = _cpu_get_cpuinfo_freq() + paths = glob.glob( + "/sys/devices/system/cpu/cpufreq/policy[0-9]*" + ) or glob.glob("/sys/devices/system/cpu/cpu[0-9]*/cpufreq") + paths.sort(key=lambda x: int(re.search(r"[0-9]+", x).group())) + ret = [] + pjoin = os.path.join + for i, path in enumerate(paths): + if len(paths) == len(cpuinfo_freqs): + # take cached value from cpuinfo if available, see: + # https://github.com/giampaolo/psutil/issues/1851 + curr = cpuinfo_freqs[i] * 1000 + else: + curr = bcat(pjoin(path, "scaling_cur_freq"), fallback=None) + if curr is None: + # Likely an old RedHat, see: + # https://github.com/giampaolo/psutil/issues/1071 + curr = bcat(pjoin(path, "cpuinfo_cur_freq"), fallback=None) + if curr is None: + online_path = f"/sys/devices/system/cpu/cpu{i}/online" + # if cpu core is offline, set to all zeroes + if cat(online_path, fallback=None) == "0\n": + ret.append(_common.scpufreq(0.0, 0.0, 0.0)) + continue + msg = "can't find current frequency file" + raise NotImplementedError(msg) + curr = int(curr) / 1000 + max_ = int(bcat(pjoin(path, "scaling_max_freq"))) / 1000 + min_ = int(bcat(pjoin(path, "scaling_min_freq"))) / 1000 + ret.append(_common.scpufreq(curr, min_, max_)) + return ret + +else: + + def cpu_freq(): + """Alternate implementation using /proc/cpuinfo. + min and max frequencies are not available and are set to None. + """ + return [_common.scpufreq(x, 0.0, 0.0) for x in _cpu_get_cpuinfo_freq()] + + +# ===================================================================== +# --- network +# ===================================================================== + + +net_if_addrs = cext_posix.net_if_addrs + + +class _Ipv6UnsupportedError(Exception): + pass + + +class NetConnections: + """A wrapper on top of /proc/net/* files, retrieving per-process + and system-wide open connections (TCP, UDP, UNIX) similarly to + "netstat -an". + + Note: in case of UNIX sockets we're only able to determine the + local endpoint/path, not the one it's connected to. + According to [1] it would be possible but not easily. + + [1] http://serverfault.com/a/417946 + """ + + def __init__(self): + # The string represents the basename of the corresponding + # /proc/net/{proto_name} file. + tcp4 = ("tcp", socket.AF_INET, socket.SOCK_STREAM) + tcp6 = ("tcp6", socket.AF_INET6, socket.SOCK_STREAM) + udp4 = ("udp", socket.AF_INET, socket.SOCK_DGRAM) + udp6 = ("udp6", socket.AF_INET6, socket.SOCK_DGRAM) + unix = ("unix", socket.AF_UNIX, None) + self.tmap = { + "all": (tcp4, tcp6, udp4, udp6, unix), + "tcp": (tcp4, tcp6), + "tcp4": (tcp4,), + "tcp6": (tcp6,), + "udp": (udp4, udp6), + "udp4": (udp4,), + "udp6": (udp6,), + "unix": (unix,), + "inet": (tcp4, tcp6, udp4, udp6), + "inet4": (tcp4, udp4), + "inet6": (tcp6, udp6), + } + self._procfs_path = None + + def get_proc_inodes(self, pid): + inodes = defaultdict(list) + for fd in os.listdir(f"{self._procfs_path}/{pid}/fd"): + try: + inode = readlink(f"{self._procfs_path}/{pid}/fd/{fd}") + except (FileNotFoundError, ProcessLookupError): + # ENOENT == file which is gone in the meantime; + # os.stat(f"/proc/{self.pid}") will be done later + # to force NSP (if it's the case) + continue + except OSError as err: + if err.errno == errno.EINVAL: + # not a link + continue + if err.errno == errno.ENAMETOOLONG: + # file name too long + debug(err) + continue + raise + else: + if inode.startswith('socket:['): + # the process is using a socket + inode = inode[8:][:-1] + inodes[inode].append((pid, int(fd))) + return inodes + + def get_all_inodes(self): + inodes = {} + for pid in pids(): + try: + inodes.update(self.get_proc_inodes(pid)) + except (FileNotFoundError, ProcessLookupError, PermissionError): + # os.listdir() is gonna raise a lot of access denied + # exceptions in case of unprivileged user; that's fine + # as we'll just end up returning a connection with PID + # and fd set to None anyway. + # Both netstat -an and lsof does the same so it's + # unlikely we can do any better. + # ENOENT just means a PID disappeared on us. + continue + return inodes + + @staticmethod + def decode_address(addr, family): + """Accept an "ip:port" address as displayed in /proc/net/* + and convert it into a human readable form, like: + + "0500000A:0016" -> ("10.0.0.5", 22) + "0000000000000000FFFF00000100007F:9E49" -> ("::ffff:127.0.0.1", 40521) + + The IP address portion is a little or big endian four-byte + hexadecimal number; that is, the least significant byte is listed + first, so we need to reverse the order of the bytes to convert it + to an IP address. + The port is represented as a two-byte hexadecimal number. + + Reference: + http://linuxdevcenter.com/pub/a/linux/2000/11/16/LinuxAdmin.html + """ + ip, port = addr.split(':') + port = int(port, 16) + # this usually refers to a local socket in listen mode with + # no end-points connected + if not port: + return () + ip = ip.encode('ascii') + if family == socket.AF_INET: + # see: https://github.com/giampaolo/psutil/issues/201 + if LITTLE_ENDIAN: + ip = socket.inet_ntop(family, base64.b16decode(ip)[::-1]) + else: + ip = socket.inet_ntop(family, base64.b16decode(ip)) + else: # IPv6 + ip = base64.b16decode(ip) + try: + # see: https://github.com/giampaolo/psutil/issues/201 + if LITTLE_ENDIAN: + ip = socket.inet_ntop( + socket.AF_INET6, + struct.pack('>4I', *struct.unpack('<4I', ip)), + ) + else: + ip = socket.inet_ntop( + socket.AF_INET6, + struct.pack('<4I', *struct.unpack('<4I', ip)), + ) + except ValueError: + # see: https://github.com/giampaolo/psutil/issues/623 + if not supports_ipv6(): + raise _Ipv6UnsupportedError from None + raise + return _common.addr(ip, port) + + @staticmethod + def process_inet(file, family, type_, inodes, filter_pid=None): + """Parse /proc/net/tcp* and /proc/net/udp* files.""" + if file.endswith('6') and not os.path.exists(file): + # IPv6 not supported + return + with open_text(file) as f: + f.readline() # skip the first line + for lineno, line in enumerate(f, 1): + try: + _, laddr, raddr, status, _, _, _, _, _, inode = ( + line.split()[:10] + ) + except ValueError: + msg = ( + f"error while parsing {file}; malformed line" + f" {lineno} {line!r}" + ) + raise RuntimeError(msg) from None + if inode in inodes: + # # We assume inet sockets are unique, so we error + # # out if there are multiple references to the + # # same inode. We won't do this for UNIX sockets. + # if len(inodes[inode]) > 1 and family != socket.AF_UNIX: + # raise ValueError("ambiguous inode with multiple " + # "PIDs references") + pid, fd = inodes[inode][0] + else: + pid, fd = None, -1 + if filter_pid is not None and filter_pid != pid: + continue + else: + if type_ == socket.SOCK_STREAM: + status = TCP_STATUSES[status] + else: + status = _common.CONN_NONE + try: + laddr = NetConnections.decode_address(laddr, family) + raddr = NetConnections.decode_address(raddr, family) + except _Ipv6UnsupportedError: + continue + yield (fd, family, type_, laddr, raddr, status, pid) + + @staticmethod + def process_unix(file, family, inodes, filter_pid=None): + """Parse /proc/net/unix files.""" + with open_text(file) as f: + f.readline() # skip the first line + for line in f: + tokens = line.split() + try: + _, _, _, _, type_, _, inode = tokens[0:7] + except ValueError: + if ' ' not in line: + # see: https://github.com/giampaolo/psutil/issues/766 + continue + msg = ( + f"error while parsing {file}; malformed line {line!r}" + ) + raise RuntimeError(msg) # noqa: B904 + if inode in inodes: # noqa: SIM108 + # With UNIX sockets we can have a single inode + # referencing many file descriptors. + pairs = inodes[inode] + else: + pairs = [(None, -1)] + for pid, fd in pairs: + if filter_pid is not None and filter_pid != pid: + continue + else: + path = tokens[-1] if len(tokens) == 8 else '' + type_ = _common.socktype_to_enum(int(type_)) + # XXX: determining the remote endpoint of a + # UNIX socket on Linux is not possible, see: + # https://serverfault.com/questions/252723/ + raddr = "" + status = _common.CONN_NONE + yield (fd, family, type_, path, raddr, status, pid) + + def retrieve(self, kind, pid=None): + self._procfs_path = get_procfs_path() + if pid is not None: + inodes = self.get_proc_inodes(pid) + if not inodes: + # no connections for this process + return [] + else: + inodes = self.get_all_inodes() + ret = set() + for proto_name, family, type_ in self.tmap[kind]: + path = f"{self._procfs_path}/net/{proto_name}" + if family in {socket.AF_INET, socket.AF_INET6}: + ls = self.process_inet( + path, family, type_, inodes, filter_pid=pid + ) + else: + ls = self.process_unix(path, family, inodes, filter_pid=pid) + for fd, family, type_, laddr, raddr, status, bound_pid in ls: + if pid: + conn = _common.pconn( + fd, family, type_, laddr, raddr, status + ) + else: + conn = _common.sconn( + fd, family, type_, laddr, raddr, status, bound_pid + ) + ret.add(conn) + return list(ret) + + +_net_connections = NetConnections() + + +def net_connections(kind='inet'): + """Return system-wide open connections.""" + return _net_connections.retrieve(kind) + + +def net_io_counters(): + """Return network I/O statistics for every network interface + installed on the system as a dict of raw tuples. + """ + with open_text(f"{get_procfs_path()}/net/dev") as f: + lines = f.readlines() + retdict = {} + for line in lines[2:]: + colon = line.rfind(':') + assert colon > 0, repr(line) + name = line[:colon].strip() + fields = line[colon + 1 :].strip().split() + + ( + # in + bytes_recv, + packets_recv, + errin, + dropin, + _fifoin, # unused + _framein, # unused + _compressedin, # unused + _multicastin, # unused + # out + bytes_sent, + packets_sent, + errout, + dropout, + _fifoout, # unused + _collisionsout, # unused + _carrierout, # unused + _compressedout, # unused + ) = map(int, fields) + + retdict[name] = ( + bytes_sent, + bytes_recv, + packets_sent, + packets_recv, + errin, + errout, + dropin, + dropout, + ) + return retdict + + +def net_if_stats(): + """Get NIC stats (isup, duplex, speed, mtu).""" + duplex_map = { + cext.DUPLEX_FULL: NIC_DUPLEX_FULL, + cext.DUPLEX_HALF: NIC_DUPLEX_HALF, + cext.DUPLEX_UNKNOWN: NIC_DUPLEX_UNKNOWN, + } + names = net_io_counters().keys() + ret = {} + for name in names: + try: + mtu = cext_posix.net_if_mtu(name) + flags = cext_posix.net_if_flags(name) + duplex, speed = cext.net_if_duplex_speed(name) + except OSError as err: + # https://github.com/giampaolo/psutil/issues/1279 + if err.errno != errno.ENODEV: + raise + debug(err) + else: + output_flags = ','.join(flags) + isup = 'running' in flags + ret[name] = _common.snicstats( + isup, duplex_map[duplex], speed, mtu, output_flags + ) + return ret + + +# ===================================================================== +# --- disks +# ===================================================================== + + +disk_usage = _psposix.disk_usage + + +def disk_io_counters(perdisk=False): + """Return disk I/O statistics for every disk installed on the + system as a dict of raw tuples. + """ + + def read_procfs(): + # OK, this is a bit confusing. The format of /proc/diskstats can + # have 3 variations. + # On Linux 2.4 each line has always 15 fields, e.g.: + # "3 0 8 hda 8 8 8 8 8 8 8 8 8 8 8" + # On Linux 2.6+ each line *usually* has 14 fields, and the disk + # name is in another position, like this: + # "3 0 hda 8 8 8 8 8 8 8 8 8 8 8" + # ...unless (Linux 2.6) the line refers to a partition instead + # of a disk, in which case the line has less fields (7): + # "3 1 hda1 8 8 8 8" + # 4.18+ has 4 fields added: + # "3 0 hda 8 8 8 8 8 8 8 8 8 8 8 0 0 0 0" + # 5.5 has 2 more fields. + # See: + # https://www.kernel.org/doc/Documentation/iostats.txt + # https://www.kernel.org/doc/Documentation/ABI/testing/procfs-diskstats + with open_text(f"{get_procfs_path()}/diskstats") as f: + lines = f.readlines() + for line in lines: + fields = line.split() + flen = len(fields) + # fmt: off + if flen == 15: + # Linux 2.4 + name = fields[3] + reads = int(fields[2]) + (reads_merged, rbytes, rtime, writes, writes_merged, + wbytes, wtime, _, busy_time, _) = map(int, fields[4:14]) + elif flen == 14 or flen >= 18: + # Linux 2.6+, line referring to a disk + name = fields[2] + (reads, reads_merged, rbytes, rtime, writes, writes_merged, + wbytes, wtime, _, busy_time, _) = map(int, fields[3:14]) + elif flen == 7: + # Linux 2.6+, line referring to a partition + name = fields[2] + reads, rbytes, writes, wbytes = map(int, fields[3:]) + rtime = wtime = reads_merged = writes_merged = busy_time = 0 + else: + msg = f"not sure how to interpret line {line!r}" + raise ValueError(msg) + yield (name, reads, writes, rbytes, wbytes, rtime, wtime, + reads_merged, writes_merged, busy_time) + # fmt: on + + def read_sysfs(): + for block in os.listdir('/sys/block'): + for root, _, files in os.walk(os.path.join('/sys/block', block)): + if 'stat' not in files: + continue + with open_text(os.path.join(root, 'stat')) as f: + fields = f.read().strip().split() + name = os.path.basename(root) + # fmt: off + (reads, reads_merged, rbytes, rtime, writes, writes_merged, + wbytes, wtime, _, busy_time) = map(int, fields[:10]) + yield (name, reads, writes, rbytes, wbytes, rtime, + wtime, reads_merged, writes_merged, busy_time) + # fmt: on + + if os.path.exists(f"{get_procfs_path()}/diskstats"): + gen = read_procfs() + elif os.path.exists('/sys/block'): + gen = read_sysfs() + else: + msg = ( + f"{get_procfs_path()}/diskstats nor /sys/block are available on" + " this system" + ) + raise NotImplementedError(msg) + + retdict = {} + for entry in gen: + # fmt: off + (name, reads, writes, rbytes, wbytes, rtime, wtime, reads_merged, + writes_merged, busy_time) = entry + if not perdisk and not is_storage_device(name): + # perdisk=False means we want to calculate totals so we skip + # partitions (e.g. 'sda1', 'nvme0n1p1') and only include + # base disk devices (e.g. 'sda', 'nvme0n1'). Base disks + # include a total of all their partitions + some extra size + # of their own: + # $ cat /proc/diskstats + # 259 0 sda 10485760 ... + # 259 1 sda1 5186039 ... + # 259 1 sda2 5082039 ... + # See: + # https://github.com/giampaolo/psutil/pull/1313 + continue + + rbytes *= DISK_SECTOR_SIZE + wbytes *= DISK_SECTOR_SIZE + retdict[name] = (reads, writes, rbytes, wbytes, rtime, wtime, + reads_merged, writes_merged, busy_time) + # fmt: on + + return retdict + + +class RootFsDeviceFinder: + """disk_partitions() may return partitions with device == "/dev/root" + or "rootfs". This container class uses different strategies to try to + obtain the real device path. Resources: + https://bootlin.com/blog/find-root-device/ + https://www.systutorials.com/how-to-find-the-disk-where-root-is-on-in-bash-on-linux/. + """ + + __slots__ = ['major', 'minor'] + + def __init__(self): + dev = os.stat("/").st_dev + self.major = os.major(dev) + self.minor = os.minor(dev) + + def ask_proc_partitions(self): + with open_text(f"{get_procfs_path()}/partitions") as f: + for line in f.readlines()[2:]: + fields = line.split() + if len(fields) < 4: # just for extra safety + continue + major = int(fields[0]) if fields[0].isdigit() else None + minor = int(fields[1]) if fields[1].isdigit() else None + name = fields[3] + if major == self.major and minor == self.minor: + if name: # just for extra safety + return f"/dev/{name}" + + def ask_sys_dev_block(self): + path = f"/sys/dev/block/{self.major}:{self.minor}/uevent" + with open_text(path) as f: + for line in f: + if line.startswith("DEVNAME="): + name = line.strip().rpartition("DEVNAME=")[2] + if name: # just for extra safety + return f"/dev/{name}" + + def ask_sys_class_block(self): + needle = f"{self.major}:{self.minor}" + files = glob.iglob("/sys/class/block/*/dev") + for file in files: + try: + f = open_text(file) + except FileNotFoundError: # race condition + continue + else: + with f: + data = f.read().strip() + if data == needle: + name = os.path.basename(os.path.dirname(file)) + return f"/dev/{name}" + + def find(self): + path = None + if path is None: + try: + path = self.ask_proc_partitions() + except OSError as err: + debug(err) + if path is None: + try: + path = self.ask_sys_dev_block() + except OSError as err: + debug(err) + if path is None: + try: + path = self.ask_sys_class_block() + except OSError as err: + debug(err) + # We use exists() because the "/dev/*" part of the path is hard + # coded, so we want to be sure. + if path is not None and os.path.exists(path): + return path + + +def disk_partitions(all=False): + """Return mounted disk partitions as a list of namedtuples.""" + fstypes = set() + procfs_path = get_procfs_path() + if not all: + with open_text(f"{procfs_path}/filesystems") as f: + for line in f: + line = line.strip() + if not line.startswith("nodev"): + fstypes.add(line.strip()) + else: + # ignore all lines starting with "nodev" except "nodev zfs" + fstype = line.split("\t")[1] + if fstype == "zfs": + fstypes.add("zfs") + + # See: https://github.com/giampaolo/psutil/issues/1307 + if procfs_path == "/proc" and os.path.isfile('/etc/mtab'): + mounts_path = os.path.realpath("/etc/mtab") + else: + mounts_path = os.path.realpath(f"{procfs_path}/self/mounts") + + retlist = [] + partitions = cext.disk_partitions(mounts_path) + for partition in partitions: + device, mountpoint, fstype, opts = partition + if device == 'none': + device = '' + if device in {"/dev/root", "rootfs"}: + device = RootFsDeviceFinder().find() or device + if not all: + if not device or fstype not in fstypes: + continue + ntuple = _common.sdiskpart(device, mountpoint, fstype, opts) + retlist.append(ntuple) + + return retlist + + +# ===================================================================== +# --- sensors +# ===================================================================== + + +def sensors_temperatures(): + """Return hardware (CPU and others) temperatures as a dict + including hardware name, label, current, max and critical + temperatures. + + Implementation notes: + - /sys/class/hwmon looks like the most recent interface to + retrieve this info, and this implementation relies on it + only (old distros will probably use something else) + - lm-sensors on Ubuntu 16.04 relies on /sys/class/hwmon + - /sys/class/thermal/thermal_zone* is another one but it's more + difficult to parse + """ + ret = collections.defaultdict(list) + basenames = glob.glob('/sys/class/hwmon/hwmon*/temp*_*') + # CentOS has an intermediate /device directory: + # https://github.com/giampaolo/psutil/issues/971 + # https://github.com/nicolargo/glances/issues/1060 + basenames.extend(glob.glob('/sys/class/hwmon/hwmon*/device/temp*_*')) + basenames = sorted({x.split('_')[0] for x in basenames}) + + # Only add the coretemp hwmon entries if they're not already in + # /sys/class/hwmon/ + # https://github.com/giampaolo/psutil/issues/1708 + # https://github.com/giampaolo/psutil/pull/1648 + basenames2 = glob.glob( + '/sys/devices/platform/coretemp.*/hwmon/hwmon*/temp*_*' + ) + repl = re.compile(r"/sys/devices/platform/coretemp.*/hwmon/") + for name in basenames2: + altname = repl.sub('/sys/class/hwmon/', name) + if altname not in basenames: + basenames.append(name) + + for base in basenames: + try: + path = base + '_input' + current = float(bcat(path)) / 1000.0 + path = os.path.join(os.path.dirname(base), 'name') + unit_name = cat(path).strip() + except (OSError, ValueError): + # A lot of things can go wrong here, so let's just skip the + # whole entry. Sure thing is Linux's /sys/class/hwmon really + # is a stinky broken mess. + # https://github.com/giampaolo/psutil/issues/1009 + # https://github.com/giampaolo/psutil/issues/1101 + # https://github.com/giampaolo/psutil/issues/1129 + # https://github.com/giampaolo/psutil/issues/1245 + # https://github.com/giampaolo/psutil/issues/1323 + continue + + high = bcat(base + '_max', fallback=None) + critical = bcat(base + '_crit', fallback=None) + label = cat(base + '_label', fallback='').strip() + + if high is not None: + try: + high = float(high) / 1000.0 + except ValueError: + high = None + if critical is not None: + try: + critical = float(critical) / 1000.0 + except ValueError: + critical = None + + ret[unit_name].append((label, current, high, critical)) + + # Indication that no sensors were detected in /sys/class/hwmon/ + if not basenames: + basenames = glob.glob('/sys/class/thermal/thermal_zone*') + basenames = sorted(set(basenames)) + + for base in basenames: + try: + path = os.path.join(base, 'temp') + current = float(bcat(path)) / 1000.0 + path = os.path.join(base, 'type') + unit_name = cat(path).strip() + except (OSError, ValueError) as err: + debug(err) + continue + + trip_paths = glob.glob(base + '/trip_point*') + trip_points = { + '_'.join(os.path.basename(p).split('_')[0:3]) + for p in trip_paths + } + critical = None + high = None + for trip_point in trip_points: + path = os.path.join(base, trip_point + "_type") + trip_type = cat(path, fallback='').strip() + if trip_type == 'critical': + critical = bcat( + os.path.join(base, trip_point + "_temp"), fallback=None + ) + elif trip_type == 'high': + high = bcat( + os.path.join(base, trip_point + "_temp"), fallback=None + ) + + if high is not None: + try: + high = float(high) / 1000.0 + except ValueError: + high = None + if critical is not None: + try: + critical = float(critical) / 1000.0 + except ValueError: + critical = None + + ret[unit_name].append(('', current, high, critical)) + + return dict(ret) + + +def sensors_fans(): + """Return hardware fans info (for CPU and other peripherals) as a + dict including hardware label and current speed. + + Implementation notes: + - /sys/class/hwmon looks like the most recent interface to + retrieve this info, and this implementation relies on it + only (old distros will probably use something else) + - lm-sensors on Ubuntu 16.04 relies on /sys/class/hwmon + """ + ret = collections.defaultdict(list) + basenames = glob.glob('/sys/class/hwmon/hwmon*/fan*_*') + if not basenames: + # CentOS has an intermediate /device directory: + # https://github.com/giampaolo/psutil/issues/971 + basenames = glob.glob('/sys/class/hwmon/hwmon*/device/fan*_*') + + basenames = sorted({x.split("_")[0] for x in basenames}) + for base in basenames: + try: + current = int(bcat(base + '_input')) + except OSError as err: + debug(err) + continue + unit_name = cat(os.path.join(os.path.dirname(base), 'name')).strip() + label = cat(base + '_label', fallback='').strip() + ret[unit_name].append(_common.sfan(label, current)) + + return dict(ret) + + +def sensors_battery(): + """Return battery information. + Implementation note: it appears /sys/class/power_supply/BAT0/ + directory structure may vary and provide files with the same + meaning but under different names, see: + https://github.com/giampaolo/psutil/issues/966. + """ + null = object() + + def multi_bcat(*paths): + """Attempt to read the content of multiple files which may + not exist. If none of them exist return None. + """ + for path in paths: + ret = bcat(path, fallback=null) + if ret != null: + try: + return int(ret) + except ValueError: + return ret.strip() + return None + + bats = [ + x + for x in os.listdir(POWER_SUPPLY_PATH) + if x.startswith('BAT') or 'battery' in x.lower() + ] + if not bats: + return None + # Get the first available battery. Usually this is "BAT0", except + # some rare exceptions: + # https://github.com/giampaolo/psutil/issues/1238 + root = os.path.join(POWER_SUPPLY_PATH, min(bats)) + + # Base metrics. + energy_now = multi_bcat(root + "/energy_now", root + "/charge_now") + power_now = multi_bcat(root + "/power_now", root + "/current_now") + energy_full = multi_bcat(root + "/energy_full", root + "/charge_full") + time_to_empty = multi_bcat(root + "/time_to_empty_now") + + # Percent. If we have energy_full the percentage will be more + # accurate compared to reading /capacity file (float vs. int). + if energy_full is not None and energy_now is not None: + try: + percent = 100.0 * energy_now / energy_full + except ZeroDivisionError: + percent = 0.0 + else: + percent = int(cat(root + "/capacity", fallback=-1)) + if percent == -1: + return None + + # Is AC power cable plugged in? + # Note: AC0 is not always available and sometimes (e.g. CentOS7) + # it's called "AC". + power_plugged = None + online = multi_bcat( + os.path.join(POWER_SUPPLY_PATH, "AC0/online"), + os.path.join(POWER_SUPPLY_PATH, "AC/online"), + ) + if online is not None: + power_plugged = online == 1 + else: + status = cat(root + "/status", fallback="").strip().lower() + if status == "discharging": + power_plugged = False + elif status in {"charging", "full"}: + power_plugged = True + + # Seconds left. + # Note to self: we may also calculate the charging ETA as per: + # https://github.com/thialfihar/dotfiles/blob/ + # 013937745fd9050c30146290e8f963d65c0179e6/bin/battery.py#L55 + if power_plugged: + secsleft = _common.POWER_TIME_UNLIMITED + elif energy_now is not None and power_now is not None: + try: + secsleft = int(energy_now / power_now * 3600) + except ZeroDivisionError: + secsleft = _common.POWER_TIME_UNKNOWN + elif time_to_empty is not None: + secsleft = int(time_to_empty * 60) + if secsleft < 0: + secsleft = _common.POWER_TIME_UNKNOWN + else: + secsleft = _common.POWER_TIME_UNKNOWN + + return _common.sbattery(percent, secsleft, power_plugged) + + +# ===================================================================== +# --- other system functions +# ===================================================================== + + +def users(): + """Return currently connected users as a list of namedtuples.""" + retlist = [] + rawlist = cext.users() + for item in rawlist: + user, tty, hostname, tstamp, pid = item + nt = _common.suser(user, tty or None, hostname, tstamp, pid) + retlist.append(nt) + return retlist + + +def boot_time(): + """Return the system boot time expressed in seconds since the epoch.""" + global BOOT_TIME + path = f"{get_procfs_path()}/stat" + with open_binary(path) as f: + for line in f: + if line.startswith(b'btime'): + ret = float(line.strip().split()[1]) + BOOT_TIME = ret + return ret + msg = f"line 'btime' not found in {path}" + raise RuntimeError(msg) + + +# ===================================================================== +# --- processes +# ===================================================================== + + +def pids(): + """Returns a list of PIDs currently running on the system.""" + path = get_procfs_path().encode(ENCODING) + return [int(x) for x in os.listdir(path) if x.isdigit()] + + +def pid_exists(pid): + """Check for the existence of a unix PID. Linux TIDs are not + supported (always return False). + """ + if not _psposix.pid_exists(pid): + return False + else: + # Linux's apparently does not distinguish between PIDs and TIDs + # (thread IDs). + # listdir("/proc") won't show any TID (only PIDs) but + # os.stat("/proc/{tid}") will succeed if {tid} exists. + # os.kill() can also be passed a TID. This is quite confusing. + # In here we want to enforce this distinction and support PIDs + # only, see: + # https://github.com/giampaolo/psutil/issues/687 + try: + # Note: already checked that this is faster than using a + # regular expr. Also (a lot) faster than doing + # 'return pid in pids()' + path = f"{get_procfs_path()}/{pid}/status" + with open_binary(path) as f: + for line in f: + if line.startswith(b"Tgid:"): + tgid = int(line.split()[1]) + # If tgid and pid are the same then we're + # dealing with a process PID. + return tgid == pid + msg = f"'Tgid' line not found in {path}" + raise ValueError(msg) + except (OSError, ValueError): + return pid in pids() + + +def ppid_map(): + """Obtain a {pid: ppid, ...} dict for all running processes in + one shot. Used to speed up Process.children(). + """ + ret = {} + procfs_path = get_procfs_path() + for pid in pids(): + try: + with open_binary(f"{procfs_path}/{pid}/stat") as f: + data = f.read() + except (FileNotFoundError, ProcessLookupError): + # Note: we should be able to access /stat for all processes + # aka it's unlikely we'll bump into EPERM, which is good. + pass + else: + rpar = data.rfind(b')') + dset = data[rpar + 2 :].split() + ppid = int(dset[1]) + ret[pid] = ppid + return ret + + +def wrap_exceptions(fun): + """Decorator which translates bare OSError and OSError exceptions + into NoSuchProcess and AccessDenied. + """ + + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + pid, name = self.pid, self._name + try: + return fun(self, *args, **kwargs) + except PermissionError as err: + raise AccessDenied(pid, name) from err + except ProcessLookupError as err: + self._raise_if_zombie() + raise NoSuchProcess(pid, name) from err + except FileNotFoundError as err: + self._raise_if_zombie() + # /proc/PID directory may still exist, but the files within + # it may not, indicating the process is gone, see: + # https://github.com/giampaolo/psutil/issues/2418 + if not os.path.exists(f"{self._procfs_path}/{pid}/stat"): + raise NoSuchProcess(pid, name) from err + raise + + return wrapper + + +class Process: + """Linux process implementation.""" + + __slots__ = ["_cache", "_name", "_ppid", "_procfs_path", "pid"] + + def __init__(self, pid): + self.pid = pid + self._name = None + self._ppid = None + self._procfs_path = get_procfs_path() + + def _is_zombie(self): + # Note: most of the times Linux is able to return info about the + # process even if it's a zombie, and /proc/{pid} will exist. + # There are some exceptions though, like exe(), cmdline() and + # memory_maps(). In these cases /proc/{pid}/{file} exists but + # it's empty. Instead of returning a "null" value we'll raise an + # exception. + try: + data = bcat(f"{self._procfs_path}/{self.pid}/stat") + except OSError: + return False + else: + rpar = data.rfind(b')') + status = data[rpar + 2 : rpar + 3] + return status == b"Z" + + def _raise_if_zombie(self): + if self._is_zombie(): + raise ZombieProcess(self.pid, self._name, self._ppid) + + def _raise_if_not_alive(self): + """Raise NSP if the process disappeared on us.""" + # For those C function who do not raise NSP, possibly returning + # incorrect or incomplete result. + os.stat(f"{self._procfs_path}/{self.pid}") + + @wrap_exceptions + @memoize_when_activated + def _parse_stat_file(self): + """Parse /proc/{pid}/stat file and return a dict with various + process info. + Using "man proc" as a reference: where "man proc" refers to + position N always subtract 3 (e.g ppid position 4 in + 'man proc' == position 1 in here). + The return value is cached in case oneshot() ctx manager is + in use. + """ + data = bcat(f"{self._procfs_path}/{self.pid}/stat") + # Process name is between parentheses. It can contain spaces and + # other parentheses. This is taken into account by looking for + # the first occurrence of "(" and the last occurrence of ")". + rpar = data.rfind(b')') + name = data[data.find(b'(') + 1 : rpar] + fields = data[rpar + 2 :].split() + + ret = {} + ret['name'] = name + ret['status'] = fields[0] + ret['ppid'] = fields[1] + ret['ttynr'] = fields[4] + ret['utime'] = fields[11] + ret['stime'] = fields[12] + ret['children_utime'] = fields[13] + ret['children_stime'] = fields[14] + ret['create_time'] = fields[19] + ret['cpu_num'] = fields[36] + try: + ret['blkio_ticks'] = fields[39] # aka 'delayacct_blkio_ticks' + except IndexError: + # https://github.com/giampaolo/psutil/issues/2455 + debug("can't get blkio_ticks, set iowait to 0") + ret['blkio_ticks'] = 0 + + return ret + + @wrap_exceptions + @memoize_when_activated + def _read_status_file(self): + """Read /proc/{pid}/stat file and return its content. + The return value is cached in case oneshot() ctx manager is + in use. + """ + with open_binary(f"{self._procfs_path}/{self.pid}/status") as f: + return f.read() + + @wrap_exceptions + @memoize_when_activated + def _read_smaps_file(self): + with open_binary(f"{self._procfs_path}/{self.pid}/smaps") as f: + return f.read().strip() + + def oneshot_enter(self): + self._parse_stat_file.cache_activate(self) + self._read_status_file.cache_activate(self) + self._read_smaps_file.cache_activate(self) + + def oneshot_exit(self): + self._parse_stat_file.cache_deactivate(self) + self._read_status_file.cache_deactivate(self) + self._read_smaps_file.cache_deactivate(self) + + @wrap_exceptions + def name(self): + # XXX - gets changed later and probably needs refactoring + return decode(self._parse_stat_file()['name']) + + @wrap_exceptions + def exe(self): + try: + return readlink(f"{self._procfs_path}/{self.pid}/exe") + except (FileNotFoundError, ProcessLookupError): + self._raise_if_zombie() + # no such file error; might be raised also if the + # path actually exists for system processes with + # low pids (about 0-20) + if os.path.lexists(f"{self._procfs_path}/{self.pid}"): + return "" + raise + + @wrap_exceptions + def cmdline(self): + with open_text(f"{self._procfs_path}/{self.pid}/cmdline") as f: + data = f.read() + if not data: + # may happen in case of zombie process + self._raise_if_zombie() + return [] + # 'man proc' states that args are separated by null bytes '\0' + # and last char is supposed to be a null byte. Nevertheless + # some processes may change their cmdline after being started + # (via setproctitle() or similar), they are usually not + # compliant with this rule and use spaces instead. Google + # Chrome process is an example. See: + # https://github.com/giampaolo/psutil/issues/1179 + sep = '\x00' if data.endswith('\x00') else ' ' + if data.endswith(sep): + data = data[:-1] + cmdline = data.split(sep) + # Sometimes last char is a null byte '\0' but the args are + # separated by spaces, see: https://github.com/giampaolo/psutil/ + # issues/1179#issuecomment-552984549 + if sep == '\x00' and len(cmdline) == 1 and ' ' in data: + cmdline = data.split(' ') + return cmdline + + @wrap_exceptions + def environ(self): + with open_text(f"{self._procfs_path}/{self.pid}/environ") as f: + data = f.read() + return parse_environ_block(data) + + @wrap_exceptions + def terminal(self): + tty_nr = int(self._parse_stat_file()['ttynr']) + tmap = _psposix.get_terminal_map() + try: + return tmap[tty_nr] + except KeyError: + return None + + # May not be available on old kernels. + if os.path.exists(f"/proc/{os.getpid()}/io"): + + @wrap_exceptions + def io_counters(self): + fname = f"{self._procfs_path}/{self.pid}/io" + fields = {} + with open_binary(fname) as f: + for line in f: + # https://github.com/giampaolo/psutil/issues/1004 + line = line.strip() + if line: + try: + name, value = line.split(b': ') + except ValueError: + # https://github.com/giampaolo/psutil/issues/1004 + continue + else: + fields[name] = int(value) + if not fields: + msg = f"{fname} file was empty" + raise RuntimeError(msg) + try: + return pio( + fields[b'syscr'], # read syscalls + fields[b'syscw'], # write syscalls + fields[b'read_bytes'], # read bytes + fields[b'write_bytes'], # write bytes + fields[b'rchar'], # read chars + fields[b'wchar'], # write chars + ) + except KeyError as err: + msg = ( + f"{err.args[0]!r} field was not found in {fname}; found" + f" fields are {fields!r}" + ) + raise ValueError(msg) from None + + @wrap_exceptions + def cpu_times(self): + values = self._parse_stat_file() + utime = float(values['utime']) / CLOCK_TICKS + stime = float(values['stime']) / CLOCK_TICKS + children_utime = float(values['children_utime']) / CLOCK_TICKS + children_stime = float(values['children_stime']) / CLOCK_TICKS + iowait = float(values['blkio_ticks']) / CLOCK_TICKS + return pcputimes(utime, stime, children_utime, children_stime, iowait) + + @wrap_exceptions + def cpu_num(self): + """What CPU the process is on.""" + return int(self._parse_stat_file()['cpu_num']) + + @wrap_exceptions + def wait(self, timeout=None): + return _psposix.wait_pid(self.pid, timeout, self._name) + + @wrap_exceptions + def create_time(self): + ctime = float(self._parse_stat_file()['create_time']) + # According to documentation, starttime is in field 21 and the + # unit is jiffies (clock ticks). + # We first divide it for clock ticks and then add uptime returning + # seconds since the epoch. + # Also use cached value if available. + bt = BOOT_TIME or boot_time() + return (ctime / CLOCK_TICKS) + bt + + @wrap_exceptions + def memory_info(self): + # ============================================================ + # | FIELD | DESCRIPTION | AKA | TOP | + # ============================================================ + # | rss | resident set size | | RES | + # | vms | total program size | size | VIRT | + # | shared | shared pages (from shared mappings) | | SHR | + # | text | text ('code') | trs | CODE | + # | lib | library (unused in Linux 2.6) | lrs | | + # | data | data + stack | drs | DATA | + # | dirty | dirty pages (unused in Linux 2.6) | dt | | + # ============================================================ + with open_binary(f"{self._procfs_path}/{self.pid}/statm") as f: + vms, rss, shared, text, lib, data, dirty = ( + int(x) * PAGESIZE for x in f.readline().split()[:7] + ) + return pmem(rss, vms, shared, text, lib, data, dirty) + + if HAS_PROC_SMAPS_ROLLUP or HAS_PROC_SMAPS: + + def _parse_smaps_rollup(self): + # /proc/pid/smaps_rollup was added to Linux in 2017. Faster + # than /proc/pid/smaps. It reports higher PSS than */smaps + # (from 1k up to 200k higher; tested against all processes). + # IMPORTANT: /proc/pid/smaps_rollup is weird, because it + # raises ESRCH / ENOENT for many PIDs, even if they're alive + # (also as root). In that case we'll use /proc/pid/smaps as + # fallback, which is slower but has a +50% success rate + # compared to /proc/pid/smaps_rollup. + uss = pss = swap = 0 + with open_binary( + f"{self._procfs_path}/{self.pid}/smaps_rollup" + ) as f: + for line in f: + if line.startswith(b"Private_"): + # Private_Clean, Private_Dirty, Private_Hugetlb + uss += int(line.split()[1]) * 1024 + elif line.startswith(b"Pss:"): + pss = int(line.split()[1]) * 1024 + elif line.startswith(b"Swap:"): + swap = int(line.split()[1]) * 1024 + return (uss, pss, swap) + + @wrap_exceptions + def _parse_smaps( + self, + # Gets Private_Clean, Private_Dirty, Private_Hugetlb. + _private_re=re.compile(br"\nPrivate.*:\s+(\d+)"), + _pss_re=re.compile(br"\nPss\:\s+(\d+)"), + _swap_re=re.compile(br"\nSwap\:\s+(\d+)"), + ): + # /proc/pid/smaps does not exist on kernels < 2.6.14 or if + # CONFIG_MMU kernel configuration option is not enabled. + + # Note: using 3 regexes is faster than reading the file + # line by line. + # + # You might be tempted to calculate USS by subtracting + # the "shared" value from the "resident" value in + # /proc//statm. But at least on Linux, statm's "shared" + # value actually counts pages backed by files, which has + # little to do with whether the pages are actually shared. + # /proc/self/smaps on the other hand appears to give us the + # correct information. + smaps_data = self._read_smaps_file() + # Note: smaps file can be empty for certain processes. + # The code below will not crash though and will result to 0. + uss = sum(map(int, _private_re.findall(smaps_data))) * 1024 + pss = sum(map(int, _pss_re.findall(smaps_data))) * 1024 + swap = sum(map(int, _swap_re.findall(smaps_data))) * 1024 + return (uss, pss, swap) + + @wrap_exceptions + def memory_full_info(self): + if HAS_PROC_SMAPS_ROLLUP: # faster + try: + uss, pss, swap = self._parse_smaps_rollup() + except (ProcessLookupError, FileNotFoundError): + uss, pss, swap = self._parse_smaps() + else: + uss, pss, swap = self._parse_smaps() + basic_mem = self.memory_info() + return pfullmem(*basic_mem + (uss, pss, swap)) + + else: + memory_full_info = memory_info + + if HAS_PROC_SMAPS: + + @wrap_exceptions + def memory_maps(self): + """Return process's mapped memory regions as a list of named + tuples. Fields are explained in 'man proc'; here is an updated + (Apr 2012) version: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/filesystems/proc.txt?id=b76437579d1344b612cf1851ae610c636cec7db0. + + /proc/{PID}/smaps does not exist on kernels < 2.6.14 or if + CONFIG_MMU kernel configuration option is not enabled. + """ + + def get_blocks(lines, current_block): + data = {} + for line in lines: + fields = line.split(None, 5) + if not fields[0].endswith(b':'): + # new block section + yield (current_block.pop(), data) + current_block.append(line) + else: + try: + data[fields[0]] = int(fields[1]) * 1024 + except ValueError: + if fields[0].startswith(b'VmFlags:'): + # see issue #369 + continue + msg = f"don't know how to interpret line {line!r}" + raise ValueError(msg) from None + yield (current_block.pop(), data) + + data = self._read_smaps_file() + # Note: smaps file can be empty for certain processes or for + # zombies. + if not data: + self._raise_if_zombie() + return [] + lines = data.split(b'\n') + ls = [] + first_line = lines.pop(0) + current_block = [first_line] + for header, data in get_blocks(lines, current_block): + hfields = header.split(None, 5) + try: + addr, perms, _offset, _dev, _inode, path = hfields + except ValueError: + addr, perms, _offset, _dev, _inode, path = hfields + [''] + if not path: + path = '[anon]' + else: + path = decode(path) + path = path.strip() + if path.endswith(' (deleted)') and not path_exists_strict( + path + ): + path = path[:-10] + item = ( + decode(addr), + decode(perms), + path, + data.get(b'Rss:', 0), + data.get(b'Size:', 0), + data.get(b'Pss:', 0), + data.get(b'Shared_Clean:', 0), + data.get(b'Shared_Dirty:', 0), + data.get(b'Private_Clean:', 0), + data.get(b'Private_Dirty:', 0), + data.get(b'Referenced:', 0), + data.get(b'Anonymous:', 0), + data.get(b'Swap:', 0), + ) + ls.append(item) + return ls + + @wrap_exceptions + def cwd(self): + return readlink(f"{self._procfs_path}/{self.pid}/cwd") + + @wrap_exceptions + def num_ctx_switches( + self, _ctxsw_re=re.compile(br'ctxt_switches:\t(\d+)') + ): + data = self._read_status_file() + ctxsw = _ctxsw_re.findall(data) + if not ctxsw: + msg = ( + "'voluntary_ctxt_switches' and" + " 'nonvoluntary_ctxt_switches'lines were not found in" + f" {self._procfs_path}/{self.pid}/status; the kernel is" + " probably older than 2.6.23" + ) + raise NotImplementedError(msg) + return _common.pctxsw(int(ctxsw[0]), int(ctxsw[1])) + + @wrap_exceptions + def num_threads(self, _num_threads_re=re.compile(br'Threads:\t(\d+)')): + # Using a re is faster than iterating over file line by line. + data = self._read_status_file() + return int(_num_threads_re.findall(data)[0]) + + @wrap_exceptions + def threads(self): + thread_ids = os.listdir(f"{self._procfs_path}/{self.pid}/task") + thread_ids.sort() + retlist = [] + hit_enoent = False + for thread_id in thread_ids: + fname = f"{self._procfs_path}/{self.pid}/task/{thread_id}/stat" + try: + with open_binary(fname) as f: + st = f.read().strip() + except (FileNotFoundError, ProcessLookupError): + # no such file or directory or no such process; + # it means thread disappeared on us + hit_enoent = True + continue + # ignore the first two values ("pid (exe)") + st = st[st.find(b')') + 2 :] + values = st.split(b' ') + utime = float(values[11]) / CLOCK_TICKS + stime = float(values[12]) / CLOCK_TICKS + ntuple = _common.pthread(int(thread_id), utime, stime) + retlist.append(ntuple) + if hit_enoent: + self._raise_if_not_alive() + return retlist + + @wrap_exceptions + def nice_get(self): + # with open_text(f"{self._procfs_path}/{self.pid}/stat") as f: + # data = f.read() + # return int(data.split()[18]) + + # Use C implementation + return cext_posix.getpriority(self.pid) + + @wrap_exceptions + def nice_set(self, value): + return cext_posix.setpriority(self.pid, value) + + # starting from CentOS 6. + if HAS_CPU_AFFINITY: + + @wrap_exceptions + def cpu_affinity_get(self): + return cext.proc_cpu_affinity_get(self.pid) + + def _get_eligible_cpus( + self, _re=re.compile(br"Cpus_allowed_list:\t(\d+)-(\d+)") + ): + # See: https://github.com/giampaolo/psutil/issues/956 + data = self._read_status_file() + match = _re.findall(data) + if match: + return list(range(int(match[0][0]), int(match[0][1]) + 1)) + else: + return list(range(len(per_cpu_times()))) + + @wrap_exceptions + def cpu_affinity_set(self, cpus): + try: + cext.proc_cpu_affinity_set(self.pid, cpus) + except (OSError, ValueError) as err: + if isinstance(err, ValueError) or err.errno == errno.EINVAL: + eligible_cpus = self._get_eligible_cpus() + all_cpus = tuple(range(len(per_cpu_times()))) + for cpu in cpus: + if cpu not in all_cpus: + msg = ( + f"invalid CPU {cpu!r}; choose between" + f" {eligible_cpus!r}" + ) + raise ValueError(msg) from None + if cpu not in eligible_cpus: + msg = ( + f"CPU number {cpu} is not eligible; choose" + f" between {eligible_cpus}" + ) + raise ValueError(msg) from err + raise + + # only starting from kernel 2.6.13 + if HAS_PROC_IO_PRIORITY: + + @wrap_exceptions + def ionice_get(self): + ioclass, value = cext.proc_ioprio_get(self.pid) + ioclass = IOPriority(ioclass) + return _common.pionice(ioclass, value) + + @wrap_exceptions + def ionice_set(self, ioclass, value): + if value is None: + value = 0 + if value and ioclass in { + IOPriority.IOPRIO_CLASS_IDLE, + IOPriority.IOPRIO_CLASS_NONE, + }: + msg = f"{ioclass!r} ioclass accepts no value" + raise ValueError(msg) + if value < 0 or value > 7: + msg = "value not in 0-7 range" + raise ValueError(msg) + return cext.proc_ioprio_set(self.pid, ioclass, value) + + if hasattr(resource, "prlimit"): + + @wrap_exceptions + def rlimit(self, resource_, limits=None): + # If pid is 0 prlimit() applies to the calling process and + # we don't want that. We should never get here though as + # PID 0 is not supported on Linux. + if self.pid == 0: + msg = "can't use prlimit() against PID 0 process" + raise ValueError(msg) + try: + if limits is None: + # get + return resource.prlimit(self.pid, resource_) + else: + # set + if len(limits) != 2: + msg = ( + "second argument must be a (soft, hard) " + f"tuple, got {limits!r}" + ) + raise ValueError(msg) + resource.prlimit(self.pid, resource_, limits) + except OSError as err: + if err.errno == errno.ENOSYS: + # I saw this happening on Travis: + # https://travis-ci.org/giampaolo/psutil/jobs/51368273 + self._raise_if_zombie() + raise + + @wrap_exceptions + def status(self): + letter = self._parse_stat_file()['status'] + letter = letter.decode() + # XXX is '?' legit? (we're not supposed to return it anyway) + return PROC_STATUSES.get(letter, '?') + + @wrap_exceptions + def open_files(self): + retlist = [] + files = os.listdir(f"{self._procfs_path}/{self.pid}/fd") + hit_enoent = False + for fd in files: + file = f"{self._procfs_path}/{self.pid}/fd/{fd}" + try: + path = readlink(file) + except (FileNotFoundError, ProcessLookupError): + # ENOENT == file which is gone in the meantime + hit_enoent = True + continue + except OSError as err: + if err.errno == errno.EINVAL: + # not a link + continue + if err.errno == errno.ENAMETOOLONG: + # file name too long + debug(err) + continue + raise + else: + # If path is not an absolute there's no way to tell + # whether it's a regular file or not, so we skip it. + # A regular file is always supposed to be have an + # absolute path though. + if path.startswith('/') and isfile_strict(path): + # Get file position and flags. + file = f"{self._procfs_path}/{self.pid}/fdinfo/{fd}" + try: + with open_binary(file) as f: + pos = int(f.readline().split()[1]) + flags = int(f.readline().split()[1], 8) + except (FileNotFoundError, ProcessLookupError): + # fd gone in the meantime; process may + # still be alive + hit_enoent = True + else: + mode = file_flags_to_mode(flags) + ntuple = popenfile( + path, int(fd), int(pos), mode, flags + ) + retlist.append(ntuple) + if hit_enoent: + self._raise_if_not_alive() + return retlist + + @wrap_exceptions + def net_connections(self, kind='inet'): + ret = _net_connections.retrieve(kind, self.pid) + self._raise_if_not_alive() + return ret + + @wrap_exceptions + def num_fds(self): + return len(os.listdir(f"{self._procfs_path}/{self.pid}/fd")) + + @wrap_exceptions + def ppid(self): + return int(self._parse_stat_file()['ppid']) + + @wrap_exceptions + def uids(self, _uids_re=re.compile(br'Uid:\t(\d+)\t(\d+)\t(\d+)')): + data = self._read_status_file() + real, effective, saved = _uids_re.findall(data)[0] + return _common.puids(int(real), int(effective), int(saved)) + + @wrap_exceptions + def gids(self, _gids_re=re.compile(br'Gid:\t(\d+)\t(\d+)\t(\d+)')): + data = self._read_status_file() + real, effective, saved = _gids_re.findall(data)[0] + return _common.pgids(int(real), int(effective), int(saved)) diff --git a/llmlab/lib/python3.12/site-packages/psutil/_psosx.py b/llmlab/lib/python3.12/site-packages/psutil/_psosx.py new file mode 100644 index 0000000..620497b --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_psosx.py @@ -0,0 +1,544 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""macOS platform implementation.""" + +import errno +import functools +import os +from collections import namedtuple + +from . import _common +from . import _psposix +from . import _psutil_osx as cext +from . import _psutil_posix as cext_posix +from ._common import AccessDenied +from ._common import NoSuchProcess +from ._common import ZombieProcess +from ._common import conn_tmap +from ._common import conn_to_ntuple +from ._common import isfile_strict +from ._common import memoize_when_activated +from ._common import parse_environ_block +from ._common import usage_percent + + +__extra__all__ = [] + + +# ===================================================================== +# --- globals +# ===================================================================== + + +PAGESIZE = cext_posix.getpagesize() +AF_LINK = cext_posix.AF_LINK + +TCP_STATUSES = { + cext.TCPS_ESTABLISHED: _common.CONN_ESTABLISHED, + cext.TCPS_SYN_SENT: _common.CONN_SYN_SENT, + cext.TCPS_SYN_RECEIVED: _common.CONN_SYN_RECV, + cext.TCPS_FIN_WAIT_1: _common.CONN_FIN_WAIT1, + cext.TCPS_FIN_WAIT_2: _common.CONN_FIN_WAIT2, + cext.TCPS_TIME_WAIT: _common.CONN_TIME_WAIT, + cext.TCPS_CLOSED: _common.CONN_CLOSE, + cext.TCPS_CLOSE_WAIT: _common.CONN_CLOSE_WAIT, + cext.TCPS_LAST_ACK: _common.CONN_LAST_ACK, + cext.TCPS_LISTEN: _common.CONN_LISTEN, + cext.TCPS_CLOSING: _common.CONN_CLOSING, + cext.PSUTIL_CONN_NONE: _common.CONN_NONE, +} + +PROC_STATUSES = { + cext.SIDL: _common.STATUS_IDLE, + cext.SRUN: _common.STATUS_RUNNING, + cext.SSLEEP: _common.STATUS_SLEEPING, + cext.SSTOP: _common.STATUS_STOPPED, + cext.SZOMB: _common.STATUS_ZOMBIE, +} + +kinfo_proc_map = dict( + ppid=0, + ruid=1, + euid=2, + suid=3, + rgid=4, + egid=5, + sgid=6, + ttynr=7, + ctime=8, + status=9, + name=10, +) + +pidtaskinfo_map = dict( + cpuutime=0, + cpustime=1, + rss=2, + vms=3, + pfaults=4, + pageins=5, + numthreads=6, + volctxsw=7, +) + + +# ===================================================================== +# --- named tuples +# ===================================================================== + + +# fmt: off +# psutil.cpu_times() +scputimes = namedtuple('scputimes', ['user', 'nice', 'system', 'idle']) +# psutil.virtual_memory() +svmem = namedtuple( + 'svmem', ['total', 'available', 'percent', 'used', 'free', + 'active', 'inactive', 'wired']) +# psutil.Process.memory_info() +pmem = namedtuple('pmem', ['rss', 'vms', 'pfaults', 'pageins']) +# psutil.Process.memory_full_info() +pfullmem = namedtuple('pfullmem', pmem._fields + ('uss', )) +# fmt: on + + +# ===================================================================== +# --- memory +# ===================================================================== + + +def virtual_memory(): + """System virtual memory as a namedtuple.""" + total, active, inactive, wired, free, speculative = cext.virtual_mem() + # This is how Zabbix calculate avail and used mem: + # https://github.com/zabbix/zabbix/blob/master/src/libs/zbxsysinfo/osx/memory.c + # Also see: https://github.com/giampaolo/psutil/issues/1277 + avail = inactive + free + used = active + wired + # This is NOT how Zabbix calculates free mem but it matches "free" + # cmdline utility. + free -= speculative + percent = usage_percent((total - avail), total, round_=1) + return svmem(total, avail, percent, used, free, active, inactive, wired) + + +def swap_memory(): + """Swap system memory as a (total, used, free, sin, sout) tuple.""" + total, used, free, sin, sout = cext.swap_mem() + percent = usage_percent(used, total, round_=1) + return _common.sswap(total, used, free, percent, sin, sout) + + +# ===================================================================== +# --- CPU +# ===================================================================== + + +def cpu_times(): + """Return system CPU times as a namedtuple.""" + user, nice, system, idle = cext.cpu_times() + return scputimes(user, nice, system, idle) + + +def per_cpu_times(): + """Return system CPU times as a named tuple.""" + ret = [] + for cpu_t in cext.per_cpu_times(): + user, nice, system, idle = cpu_t + item = scputimes(user, nice, system, idle) + ret.append(item) + return ret + + +def cpu_count_logical(): + """Return the number of logical CPUs in the system.""" + return cext.cpu_count_logical() + + +def cpu_count_cores(): + """Return the number of CPU cores in the system.""" + return cext.cpu_count_cores() + + +def cpu_stats(): + ctx_switches, interrupts, soft_interrupts, syscalls, _traps = ( + cext.cpu_stats() + ) + return _common.scpustats( + ctx_switches, interrupts, soft_interrupts, syscalls + ) + + +def cpu_freq(): + """Return CPU frequency. + On macOS per-cpu frequency is not supported. + Also, the returned frequency never changes, see: + https://arstechnica.com/civis/viewtopic.php?f=19&t=465002. + """ + curr, min_, max_ = cext.cpu_freq() + return [_common.scpufreq(curr, min_, max_)] + + +# ===================================================================== +# --- disks +# ===================================================================== + + +disk_usage = _psposix.disk_usage +disk_io_counters = cext.disk_io_counters + + +def disk_partitions(all=False): + """Return mounted disk partitions as a list of namedtuples.""" + retlist = [] + partitions = cext.disk_partitions() + for partition in partitions: + device, mountpoint, fstype, opts = partition + if device == 'none': + device = '' + if not all: + if not os.path.isabs(device) or not os.path.exists(device): + continue + ntuple = _common.sdiskpart(device, mountpoint, fstype, opts) + retlist.append(ntuple) + return retlist + + +# ===================================================================== +# --- sensors +# ===================================================================== + + +def sensors_battery(): + """Return battery information.""" + try: + percent, minsleft, power_plugged = cext.sensors_battery() + except NotImplementedError: + # no power source - return None according to interface + return None + power_plugged = power_plugged == 1 + if power_plugged: + secsleft = _common.POWER_TIME_UNLIMITED + elif minsleft == -1: + secsleft = _common.POWER_TIME_UNKNOWN + else: + secsleft = minsleft * 60 + return _common.sbattery(percent, secsleft, power_plugged) + + +# ===================================================================== +# --- network +# ===================================================================== + + +net_io_counters = cext.net_io_counters +net_if_addrs = cext_posix.net_if_addrs + + +def net_connections(kind='inet'): + """System-wide network connections.""" + # Note: on macOS this will fail with AccessDenied unless + # the process is owned by root. + ret = [] + for pid in pids(): + try: + cons = Process(pid).net_connections(kind) + except NoSuchProcess: + continue + else: + if cons: + for c in cons: + c = list(c) + [pid] + ret.append(_common.sconn(*c)) + return ret + + +def net_if_stats(): + """Get NIC stats (isup, duplex, speed, mtu).""" + names = net_io_counters().keys() + ret = {} + for name in names: + try: + mtu = cext_posix.net_if_mtu(name) + flags = cext_posix.net_if_flags(name) + duplex, speed = cext_posix.net_if_duplex_speed(name) + except OSError as err: + # https://github.com/giampaolo/psutil/issues/1279 + if err.errno != errno.ENODEV: + raise + else: + if hasattr(_common, 'NicDuplex'): + duplex = _common.NicDuplex(duplex) + output_flags = ','.join(flags) + isup = 'running' in flags + ret[name] = _common.snicstats( + isup, duplex, speed, mtu, output_flags + ) + return ret + + +# ===================================================================== +# --- other system functions +# ===================================================================== + + +def boot_time(): + """The system boot time expressed in seconds since the epoch.""" + return cext.boot_time() + + +def users(): + """Return currently connected users as a list of namedtuples.""" + retlist = [] + rawlist = cext.users() + for item in rawlist: + user, tty, hostname, tstamp, pid = item + if tty == '~': + continue # reboot or shutdown + if not tstamp: + continue + nt = _common.suser(user, tty or None, hostname or None, tstamp, pid) + retlist.append(nt) + return retlist + + +# ===================================================================== +# --- processes +# ===================================================================== + + +def pids(): + ls = cext.pids() + if 0 not in ls: + # On certain macOS versions pids() C doesn't return PID 0 but + # "ps" does and the process is querable via sysctl(): + # https://travis-ci.org/giampaolo/psutil/jobs/309619941 + try: + Process(0).create_time() + ls.insert(0, 0) + except NoSuchProcess: + pass + except AccessDenied: + ls.insert(0, 0) + return ls + + +pid_exists = _psposix.pid_exists + + +def is_zombie(pid): + try: + st = cext.proc_kinfo_oneshot(pid)[kinfo_proc_map['status']] + return st == cext.SZOMB + except OSError: + return False + + +def wrap_exceptions(fun): + """Decorator which translates bare OSError exceptions into + NoSuchProcess and AccessDenied. + """ + + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + pid, ppid, name = self.pid, self._ppid, self._name + try: + return fun(self, *args, **kwargs) + except ProcessLookupError as err: + if is_zombie(pid): + raise ZombieProcess(pid, name, ppid) from err + raise NoSuchProcess(pid, name) from err + except PermissionError as err: + raise AccessDenied(pid, name) from err + + return wrapper + + +class Process: + """Wrapper class around underlying C implementation.""" + + __slots__ = ["_cache", "_name", "_ppid", "pid"] + + def __init__(self, pid): + self.pid = pid + self._name = None + self._ppid = None + + @wrap_exceptions + @memoize_when_activated + def _get_kinfo_proc(self): + # Note: should work with all PIDs without permission issues. + ret = cext.proc_kinfo_oneshot(self.pid) + assert len(ret) == len(kinfo_proc_map) + return ret + + @wrap_exceptions + @memoize_when_activated + def _get_pidtaskinfo(self): + # Note: should work for PIDs owned by user only. + ret = cext.proc_pidtaskinfo_oneshot(self.pid) + assert len(ret) == len(pidtaskinfo_map) + return ret + + def oneshot_enter(self): + self._get_kinfo_proc.cache_activate(self) + self._get_pidtaskinfo.cache_activate(self) + + def oneshot_exit(self): + self._get_kinfo_proc.cache_deactivate(self) + self._get_pidtaskinfo.cache_deactivate(self) + + @wrap_exceptions + def name(self): + name = self._get_kinfo_proc()[kinfo_proc_map['name']] + return name if name is not None else cext.proc_name(self.pid) + + @wrap_exceptions + def exe(self): + return cext.proc_exe(self.pid) + + @wrap_exceptions + def cmdline(self): + return cext.proc_cmdline(self.pid) + + @wrap_exceptions + def environ(self): + return parse_environ_block(cext.proc_environ(self.pid)) + + @wrap_exceptions + def ppid(self): + self._ppid = self._get_kinfo_proc()[kinfo_proc_map['ppid']] + return self._ppid + + @wrap_exceptions + def cwd(self): + return cext.proc_cwd(self.pid) + + @wrap_exceptions + def uids(self): + rawtuple = self._get_kinfo_proc() + return _common.puids( + rawtuple[kinfo_proc_map['ruid']], + rawtuple[kinfo_proc_map['euid']], + rawtuple[kinfo_proc_map['suid']], + ) + + @wrap_exceptions + def gids(self): + rawtuple = self._get_kinfo_proc() + return _common.puids( + rawtuple[kinfo_proc_map['rgid']], + rawtuple[kinfo_proc_map['egid']], + rawtuple[kinfo_proc_map['sgid']], + ) + + @wrap_exceptions + def terminal(self): + tty_nr = self._get_kinfo_proc()[kinfo_proc_map['ttynr']] + tmap = _psposix.get_terminal_map() + try: + return tmap[tty_nr] + except KeyError: + return None + + @wrap_exceptions + def memory_info(self): + rawtuple = self._get_pidtaskinfo() + return pmem( + rawtuple[pidtaskinfo_map['rss']], + rawtuple[pidtaskinfo_map['vms']], + rawtuple[pidtaskinfo_map['pfaults']], + rawtuple[pidtaskinfo_map['pageins']], + ) + + @wrap_exceptions + def memory_full_info(self): + basic_mem = self.memory_info() + uss = cext.proc_memory_uss(self.pid) + return pfullmem(*basic_mem + (uss,)) + + @wrap_exceptions + def cpu_times(self): + rawtuple = self._get_pidtaskinfo() + return _common.pcputimes( + rawtuple[pidtaskinfo_map['cpuutime']], + rawtuple[pidtaskinfo_map['cpustime']], + # children user / system times are not retrievable (set to 0) + 0.0, + 0.0, + ) + + @wrap_exceptions + def create_time(self): + return self._get_kinfo_proc()[kinfo_proc_map['ctime']] + + @wrap_exceptions + def num_ctx_switches(self): + # Unvoluntary value seems not to be available; + # getrusage() numbers seems to confirm this theory. + # We set it to 0. + vol = self._get_pidtaskinfo()[pidtaskinfo_map['volctxsw']] + return _common.pctxsw(vol, 0) + + @wrap_exceptions + def num_threads(self): + return self._get_pidtaskinfo()[pidtaskinfo_map['numthreads']] + + @wrap_exceptions + def open_files(self): + if self.pid == 0: + return [] + files = [] + rawlist = cext.proc_open_files(self.pid) + for path, fd in rawlist: + if isfile_strict(path): + ntuple = _common.popenfile(path, fd) + files.append(ntuple) + return files + + @wrap_exceptions + def net_connections(self, kind='inet'): + families, types = conn_tmap[kind] + rawlist = cext.proc_net_connections(self.pid, families, types) + ret = [] + for item in rawlist: + fd, fam, type, laddr, raddr, status = item + nt = conn_to_ntuple( + fd, fam, type, laddr, raddr, status, TCP_STATUSES + ) + ret.append(nt) + return ret + + @wrap_exceptions + def num_fds(self): + if self.pid == 0: + return 0 + return cext.proc_num_fds(self.pid) + + @wrap_exceptions + def wait(self, timeout=None): + return _psposix.wait_pid(self.pid, timeout, self._name) + + @wrap_exceptions + def nice_get(self): + return cext_posix.getpriority(self.pid) + + @wrap_exceptions + def nice_set(self, value): + return cext_posix.setpriority(self.pid, value) + + @wrap_exceptions + def status(self): + code = self._get_kinfo_proc()[kinfo_proc_map['status']] + # XXX is '?' legit? (we're not supposed to return it anyway) + return PROC_STATUSES.get(code, '?') + + @wrap_exceptions + def threads(self): + rawlist = cext.proc_threads(self.pid) + retlist = [] + for thread_id, utime, stime in rawlist: + ntuple = _common.pthread(thread_id, utime, stime) + retlist.append(ntuple) + return retlist diff --git a/llmlab/lib/python3.12/site-packages/psutil/_psposix.py b/llmlab/lib/python3.12/site-packages/psutil/_psposix.py new file mode 100644 index 0000000..88703fd --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_psposix.py @@ -0,0 +1,207 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Routines common to all posix systems.""" + +import enum +import glob +import os +import signal +import time + +from ._common import MACOS +from ._common import TimeoutExpired +from ._common import memoize +from ._common import sdiskusage +from ._common import usage_percent + + +if MACOS: + from . import _psutil_osx + + +__all__ = ['pid_exists', 'wait_pid', 'disk_usage', 'get_terminal_map'] + + +def pid_exists(pid): + """Check whether pid exists in the current process table.""" + if pid == 0: + # According to "man 2 kill" PID 0 has a special meaning: + # it refers to <> so we don't want to go any further. + # If we get here it means this UNIX platform *does* have + # a process with id 0. + return True + try: + os.kill(pid, 0) + except ProcessLookupError: + return False + except PermissionError: + # EPERM clearly means there's a process to deny access to + return True + # According to "man 2 kill" possible error values are + # (EINVAL, EPERM, ESRCH) + else: + return True + + +Negsignal = enum.IntEnum( + 'Negsignal', {x.name: -x.value for x in signal.Signals} +) + + +def negsig_to_enum(num): + """Convert a negative signal value to an enum.""" + try: + return Negsignal(num) + except ValueError: + return num + + +def wait_pid( + pid, + timeout=None, + proc_name=None, + _waitpid=os.waitpid, + _timer=getattr(time, 'monotonic', time.time), # noqa: B008 + _min=min, + _sleep=time.sleep, + _pid_exists=pid_exists, +): + """Wait for a process PID to terminate. + + If the process terminated normally by calling exit(3) or _exit(2), + or by returning from main(), the return value is the positive integer + passed to *exit(). + + If it was terminated by a signal it returns the negated value of the + signal which caused the termination (e.g. -SIGTERM). + + If PID is not a children of os.getpid() (current process) just + wait until the process disappears and return None. + + If PID does not exist at all return None immediately. + + If *timeout* != None and process is still alive raise TimeoutExpired. + timeout=0 is also possible (either return immediately or raise). + """ + if pid <= 0: + # see "man waitpid" + msg = "can't wait for PID 0" + raise ValueError(msg) + interval = 0.0001 + flags = 0 + if timeout is not None: + flags |= os.WNOHANG + stop_at = _timer() + timeout + + def sleep(interval): + # Sleep for some time and return a new increased interval. + if timeout is not None: + if _timer() >= stop_at: + raise TimeoutExpired(timeout, pid=pid, name=proc_name) + _sleep(interval) + return _min(interval * 2, 0.04) + + # See: https://linux.die.net/man/2/waitpid + while True: + try: + retpid, status = os.waitpid(pid, flags) + except InterruptedError: + interval = sleep(interval) + except ChildProcessError: + # This has two meanings: + # - PID is not a child of os.getpid() in which case + # we keep polling until it's gone + # - PID never existed in the first place + # In both cases we'll eventually return None as we + # can't determine its exit status code. + while _pid_exists(pid): + interval = sleep(interval) + return None + else: + if retpid == 0: + # WNOHANG flag was used and PID is still running. + interval = sleep(interval) + continue + + if os.WIFEXITED(status): + # Process terminated normally by calling exit(3) or _exit(2), + # or by returning from main(). The return value is the + # positive integer passed to *exit(). + return os.WEXITSTATUS(status) + elif os.WIFSIGNALED(status): + # Process exited due to a signal. Return the negative value + # of that signal. + return negsig_to_enum(-os.WTERMSIG(status)) + # elif os.WIFSTOPPED(status): + # # Process was stopped via SIGSTOP or is being traced, and + # # waitpid() was called with WUNTRACED flag. PID is still + # # alive. From now on waitpid() will keep returning (0, 0) + # # until the process state doesn't change. + # # It may make sense to catch/enable this since stopped PIDs + # # ignore SIGTERM. + # interval = sleep(interval) + # continue + # elif os.WIFCONTINUED(status): + # # Process was resumed via SIGCONT and waitpid() was called + # # with WCONTINUED flag. + # interval = sleep(interval) + # continue + else: + # Should never happen. + msg = f"unknown process exit status {status!r}" + raise ValueError(msg) + + +def disk_usage(path): + """Return disk usage associated with path. + Note: UNIX usually reserves 5% disk space which is not accessible + by user. In this function "total" and "used" values reflect the + total and used disk space whereas "free" and "percent" represent + the "free" and "used percent" user disk space. + """ + st = os.statvfs(path) + # Total space which is only available to root (unless changed + # at system level). + total = st.f_blocks * st.f_frsize + # Remaining free space usable by root. + avail_to_root = st.f_bfree * st.f_frsize + # Remaining free space usable by user. + avail_to_user = st.f_bavail * st.f_frsize + # Total space being used in general. + used = total - avail_to_root + if MACOS: + # see: https://github.com/giampaolo/psutil/pull/2152 + used = _psutil_osx.disk_usage_used(path, used) + # Total space which is available to user (same as 'total' but + # for the user). + total_user = used + avail_to_user + # User usage percent compared to the total amount of space + # the user can use. This number would be higher if compared + # to root's because the user has less space (usually -5%). + usage_percent_user = usage_percent(used, total_user, round_=1) + + # NB: the percentage is -5% than what shown by df due to + # reserved blocks that we are currently not considering: + # https://github.com/giampaolo/psutil/issues/829#issuecomment-223750462 + return sdiskusage( + total=total, used=used, free=avail_to_user, percent=usage_percent_user + ) + + +@memoize +def get_terminal_map(): + """Get a map of device-id -> path as a dict. + Used by Process.terminal(). + """ + ret = {} + ls = glob.glob('/dev/tty*') + glob.glob('/dev/pts/*') + for name in ls: + assert name not in ret, name + try: + ret[os.stat(name).st_rdev] = name + except FileNotFoundError: + pass + return ret diff --git a/llmlab/lib/python3.12/site-packages/psutil/_pssunos.py b/llmlab/lib/python3.12/site-packages/psutil/_pssunos.py new file mode 100644 index 0000000..78d941c --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_pssunos.py @@ -0,0 +1,734 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Sun OS Solaris platform implementation.""" + +import errno +import functools +import os +import socket +import subprocess +import sys +from collections import namedtuple +from socket import AF_INET + +from . import _common +from . import _psposix +from . import _psutil_posix as cext_posix +from . import _psutil_sunos as cext +from ._common import AF_INET6 +from ._common import ENCODING +from ._common import AccessDenied +from ._common import NoSuchProcess +from ._common import ZombieProcess +from ._common import debug +from ._common import get_procfs_path +from ._common import isfile_strict +from ._common import memoize_when_activated +from ._common import sockfam_to_enum +from ._common import socktype_to_enum +from ._common import usage_percent + + +__extra__all__ = ["CONN_IDLE", "CONN_BOUND", "PROCFS_PATH"] + + +# ===================================================================== +# --- globals +# ===================================================================== + + +PAGE_SIZE = cext_posix.getpagesize() +AF_LINK = cext_posix.AF_LINK +IS_64_BIT = sys.maxsize > 2**32 + +CONN_IDLE = "IDLE" +CONN_BOUND = "BOUND" + +PROC_STATUSES = { + cext.SSLEEP: _common.STATUS_SLEEPING, + cext.SRUN: _common.STATUS_RUNNING, + cext.SZOMB: _common.STATUS_ZOMBIE, + cext.SSTOP: _common.STATUS_STOPPED, + cext.SIDL: _common.STATUS_IDLE, + cext.SONPROC: _common.STATUS_RUNNING, # same as run + cext.SWAIT: _common.STATUS_WAITING, +} + +TCP_STATUSES = { + cext.TCPS_ESTABLISHED: _common.CONN_ESTABLISHED, + cext.TCPS_SYN_SENT: _common.CONN_SYN_SENT, + cext.TCPS_SYN_RCVD: _common.CONN_SYN_RECV, + cext.TCPS_FIN_WAIT_1: _common.CONN_FIN_WAIT1, + cext.TCPS_FIN_WAIT_2: _common.CONN_FIN_WAIT2, + cext.TCPS_TIME_WAIT: _common.CONN_TIME_WAIT, + cext.TCPS_CLOSED: _common.CONN_CLOSE, + cext.TCPS_CLOSE_WAIT: _common.CONN_CLOSE_WAIT, + cext.TCPS_LAST_ACK: _common.CONN_LAST_ACK, + cext.TCPS_LISTEN: _common.CONN_LISTEN, + cext.TCPS_CLOSING: _common.CONN_CLOSING, + cext.PSUTIL_CONN_NONE: _common.CONN_NONE, + cext.TCPS_IDLE: CONN_IDLE, # sunos specific + cext.TCPS_BOUND: CONN_BOUND, # sunos specific +} + +proc_info_map = dict( + ppid=0, + rss=1, + vms=2, + create_time=3, + nice=4, + num_threads=5, + status=6, + ttynr=7, + uid=8, + euid=9, + gid=10, + egid=11, +) + + +# ===================================================================== +# --- named tuples +# ===================================================================== + + +# psutil.cpu_times() +scputimes = namedtuple('scputimes', ['user', 'system', 'idle', 'iowait']) +# psutil.cpu_times(percpu=True) +pcputimes = namedtuple( + 'pcputimes', ['user', 'system', 'children_user', 'children_system'] +) +# psutil.virtual_memory() +svmem = namedtuple('svmem', ['total', 'available', 'percent', 'used', 'free']) +# psutil.Process.memory_info() +pmem = namedtuple('pmem', ['rss', 'vms']) +pfullmem = pmem +# psutil.Process.memory_maps(grouped=True) +pmmap_grouped = namedtuple( + 'pmmap_grouped', ['path', 'rss', 'anonymous', 'locked'] +) +# psutil.Process.memory_maps(grouped=False) +pmmap_ext = namedtuple( + 'pmmap_ext', 'addr perms ' + ' '.join(pmmap_grouped._fields) +) + + +# ===================================================================== +# --- memory +# ===================================================================== + + +def virtual_memory(): + """Report virtual memory metrics.""" + # we could have done this with kstat, but IMHO this is good enough + total = os.sysconf('SC_PHYS_PAGES') * PAGE_SIZE + # note: there's no difference on Solaris + free = avail = os.sysconf('SC_AVPHYS_PAGES') * PAGE_SIZE + used = total - free + percent = usage_percent(used, total, round_=1) + return svmem(total, avail, percent, used, free) + + +def swap_memory(): + """Report swap memory metrics.""" + sin, sout = cext.swap_mem() + # XXX + # we are supposed to get total/free by doing so: + # http://cvs.opensolaris.org/source/xref/onnv/onnv-gate/ + # usr/src/cmd/swap/swap.c + # ...nevertheless I can't manage to obtain the same numbers as 'swap' + # cmdline utility, so let's parse its output (sigh!) + p = subprocess.Popen( + [ + '/usr/bin/env', + f"PATH=/usr/sbin:/sbin:{os.environ['PATH']}", + 'swap', + '-l', + ], + stdout=subprocess.PIPE, + ) + stdout, _ = p.communicate() + stdout = stdout.decode(sys.stdout.encoding) + if p.returncode != 0: + msg = f"'swap -l' failed (retcode={p.returncode})" + raise RuntimeError(msg) + + lines = stdout.strip().split('\n')[1:] + if not lines: + msg = 'no swap device(s) configured' + raise RuntimeError(msg) + total = free = 0 + for line in lines: + line = line.split() + t, f = line[3:5] + total += int(int(t) * 512) + free += int(int(f) * 512) + used = total - free + percent = usage_percent(used, total, round_=1) + return _common.sswap( + total, used, free, percent, sin * PAGE_SIZE, sout * PAGE_SIZE + ) + + +# ===================================================================== +# --- CPU +# ===================================================================== + + +def cpu_times(): + """Return system-wide CPU times as a named tuple.""" + ret = cext.per_cpu_times() + return scputimes(*[sum(x) for x in zip(*ret)]) + + +def per_cpu_times(): + """Return system per-CPU times as a list of named tuples.""" + ret = cext.per_cpu_times() + return [scputimes(*x) for x in ret] + + +def cpu_count_logical(): + """Return the number of logical CPUs in the system.""" + try: + return os.sysconf("SC_NPROCESSORS_ONLN") + except ValueError: + # mimic os.cpu_count() behavior + return None + + +def cpu_count_cores(): + """Return the number of CPU cores in the system.""" + return cext.cpu_count_cores() + + +def cpu_stats(): + """Return various CPU stats as a named tuple.""" + ctx_switches, interrupts, syscalls, _traps = cext.cpu_stats() + soft_interrupts = 0 + return _common.scpustats( + ctx_switches, interrupts, soft_interrupts, syscalls + ) + + +# ===================================================================== +# --- disks +# ===================================================================== + + +disk_io_counters = cext.disk_io_counters +disk_usage = _psposix.disk_usage + + +def disk_partitions(all=False): + """Return system disk partitions.""" + # TODO - the filtering logic should be better checked so that + # it tries to reflect 'df' as much as possible + retlist = [] + partitions = cext.disk_partitions() + for partition in partitions: + device, mountpoint, fstype, opts = partition + if device == 'none': + device = '' + if not all: + # Differently from, say, Linux, we don't have a list of + # common fs types so the best we can do, AFAIK, is to + # filter by filesystem having a total size > 0. + try: + if not disk_usage(mountpoint).total: + continue + except OSError as err: + # https://github.com/giampaolo/psutil/issues/1674 + debug(f"skipping {mountpoint!r}: {err}") + continue + ntuple = _common.sdiskpart(device, mountpoint, fstype, opts) + retlist.append(ntuple) + return retlist + + +# ===================================================================== +# --- network +# ===================================================================== + + +net_io_counters = cext.net_io_counters +net_if_addrs = cext_posix.net_if_addrs + + +def net_connections(kind, _pid=-1): + """Return socket connections. If pid == -1 return system-wide + connections (as opposed to connections opened by one process only). + Only INET sockets are returned (UNIX are not). + """ + families, types = _common.conn_tmap[kind] + rawlist = cext.net_connections(_pid) + ret = set() + for item in rawlist: + fd, fam, type_, laddr, raddr, status, pid = item + if fam not in families: + continue + if type_ not in types: + continue + # TODO: refactor and use _common.conn_to_ntuple. + if fam in {AF_INET, AF_INET6}: + if laddr: + laddr = _common.addr(*laddr) + if raddr: + raddr = _common.addr(*raddr) + status = TCP_STATUSES[status] + fam = sockfam_to_enum(fam) + type_ = socktype_to_enum(type_) + if _pid == -1: + nt = _common.sconn(fd, fam, type_, laddr, raddr, status, pid) + else: + nt = _common.pconn(fd, fam, type_, laddr, raddr, status) + ret.add(nt) + return list(ret) + + +def net_if_stats(): + """Get NIC stats (isup, duplex, speed, mtu).""" + ret = cext.net_if_stats() + for name, items in ret.items(): + isup, duplex, speed, mtu = items + if hasattr(_common, 'NicDuplex'): + duplex = _common.NicDuplex(duplex) + ret[name] = _common.snicstats(isup, duplex, speed, mtu, '') + return ret + + +# ===================================================================== +# --- other system functions +# ===================================================================== + + +def boot_time(): + """The system boot time expressed in seconds since the epoch.""" + return cext.boot_time() + + +def users(): + """Return currently connected users as a list of namedtuples.""" + retlist = [] + rawlist = cext.users() + localhost = (':0.0', ':0') + for item in rawlist: + user, tty, hostname, tstamp, user_process, pid = item + # note: the underlying C function includes entries about + # system boot, run level and others. We might want + # to use them in the future. + if not user_process: + continue + if hostname in localhost: + hostname = 'localhost' + nt = _common.suser(user, tty, hostname, tstamp, pid) + retlist.append(nt) + return retlist + + +# ===================================================================== +# --- processes +# ===================================================================== + + +def pids(): + """Returns a list of PIDs currently running on the system.""" + path = get_procfs_path().encode(ENCODING) + return [int(x) for x in os.listdir(path) if x.isdigit()] + + +def pid_exists(pid): + """Check for the existence of a unix pid.""" + return _psposix.pid_exists(pid) + + +def wrap_exceptions(fun): + """Call callable into a try/except clause and translate ENOENT, + EACCES and EPERM in NoSuchProcess or AccessDenied exceptions. + """ + + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + pid, ppid, name = self.pid, self._ppid, self._name + try: + return fun(self, *args, **kwargs) + except (FileNotFoundError, ProcessLookupError) as err: + # ENOENT (no such file or directory) gets raised on open(). + # ESRCH (no such process) can get raised on read() if + # process is gone in meantime. + if not pid_exists(pid): + raise NoSuchProcess(pid, name) from err + raise ZombieProcess(pid, name, ppid) from err + except PermissionError as err: + raise AccessDenied(pid, name) from err + except OSError as err: + if pid == 0: + if 0 in pids(): + raise AccessDenied(pid, name) from err + raise + raise + + return wrapper + + +class Process: + """Wrapper class around underlying C implementation.""" + + __slots__ = ["_cache", "_name", "_ppid", "_procfs_path", "pid"] + + def __init__(self, pid): + self.pid = pid + self._name = None + self._ppid = None + self._procfs_path = get_procfs_path() + + def _assert_alive(self): + """Raise NSP if the process disappeared on us.""" + # For those C function who do not raise NSP, possibly returning + # incorrect or incomplete result. + os.stat(f"{self._procfs_path}/{self.pid}") + + def oneshot_enter(self): + self._proc_name_and_args.cache_activate(self) + self._proc_basic_info.cache_activate(self) + self._proc_cred.cache_activate(self) + + def oneshot_exit(self): + self._proc_name_and_args.cache_deactivate(self) + self._proc_basic_info.cache_deactivate(self) + self._proc_cred.cache_deactivate(self) + + @wrap_exceptions + @memoize_when_activated + def _proc_name_and_args(self): + return cext.proc_name_and_args(self.pid, self._procfs_path) + + @wrap_exceptions + @memoize_when_activated + def _proc_basic_info(self): + if self.pid == 0 and not os.path.exists( + f"{self._procfs_path}/{self.pid}/psinfo" + ): + raise AccessDenied(self.pid) + ret = cext.proc_basic_info(self.pid, self._procfs_path) + assert len(ret) == len(proc_info_map) + return ret + + @wrap_exceptions + @memoize_when_activated + def _proc_cred(self): + return cext.proc_cred(self.pid, self._procfs_path) + + @wrap_exceptions + def name(self): + # note: max len == 15 + return self._proc_name_and_args()[0] + + @wrap_exceptions + def exe(self): + try: + return os.readlink(f"{self._procfs_path}/{self.pid}/path/a.out") + except OSError: + pass # continue and guess the exe name from the cmdline + # Will be guessed later from cmdline but we want to explicitly + # invoke cmdline here in order to get an AccessDenied + # exception if the user has not enough privileges. + self.cmdline() + return "" + + @wrap_exceptions + def cmdline(self): + return self._proc_name_and_args()[1].split(' ') + + @wrap_exceptions + def environ(self): + return cext.proc_environ(self.pid, self._procfs_path) + + @wrap_exceptions + def create_time(self): + return self._proc_basic_info()[proc_info_map['create_time']] + + @wrap_exceptions + def num_threads(self): + return self._proc_basic_info()[proc_info_map['num_threads']] + + @wrap_exceptions + def nice_get(self): + # Note #1: getpriority(3) doesn't work for realtime processes. + # Psinfo is what ps uses, see: + # https://github.com/giampaolo/psutil/issues/1194 + return self._proc_basic_info()[proc_info_map['nice']] + + @wrap_exceptions + def nice_set(self, value): + if self.pid in {2, 3}: + # Special case PIDs: internally setpriority(3) return ESRCH + # (no such process), no matter what. + # The process actually exists though, as it has a name, + # creation time, etc. + raise AccessDenied(self.pid, self._name) + return cext_posix.setpriority(self.pid, value) + + @wrap_exceptions + def ppid(self): + self._ppid = self._proc_basic_info()[proc_info_map['ppid']] + return self._ppid + + @wrap_exceptions + def uids(self): + try: + real, effective, saved, _, _, _ = self._proc_cred() + except AccessDenied: + real = self._proc_basic_info()[proc_info_map['uid']] + effective = self._proc_basic_info()[proc_info_map['euid']] + saved = None + return _common.puids(real, effective, saved) + + @wrap_exceptions + def gids(self): + try: + _, _, _, real, effective, saved = self._proc_cred() + except AccessDenied: + real = self._proc_basic_info()[proc_info_map['gid']] + effective = self._proc_basic_info()[proc_info_map['egid']] + saved = None + return _common.puids(real, effective, saved) + + @wrap_exceptions + def cpu_times(self): + try: + times = cext.proc_cpu_times(self.pid, self._procfs_path) + except OSError as err: + if err.errno == errno.EOVERFLOW and not IS_64_BIT: + # We may get here if we attempt to query a 64bit process + # with a 32bit python. + # Error originates from read() and also tools like "cat" + # fail in the same way (!). + # Since there simply is no way to determine CPU times we + # return 0.0 as a fallback. See: + # https://github.com/giampaolo/psutil/issues/857 + times = (0.0, 0.0, 0.0, 0.0) + else: + raise + return _common.pcputimes(*times) + + @wrap_exceptions + def cpu_num(self): + return cext.proc_cpu_num(self.pid, self._procfs_path) + + @wrap_exceptions + def terminal(self): + procfs_path = self._procfs_path + hit_enoent = False + tty = wrap_exceptions(self._proc_basic_info()[proc_info_map['ttynr']]) + if tty != cext.PRNODEV: + for x in (0, 1, 2, 255): + try: + return os.readlink(f"{procfs_path}/{self.pid}/path/{x}") + except FileNotFoundError: + hit_enoent = True + continue + if hit_enoent: + self._assert_alive() + + @wrap_exceptions + def cwd(self): + # /proc/PID/path/cwd may not be resolved by readlink() even if + # it exists (ls shows it). If that's the case and the process + # is still alive return None (we can return None also on BSD). + # Reference: https://groups.google.com/g/comp.unix.solaris/c/tcqvhTNFCAs + procfs_path = self._procfs_path + try: + return os.readlink(f"{procfs_path}/{self.pid}/path/cwd") + except FileNotFoundError: + os.stat(f"{procfs_path}/{self.pid}") # raise NSP or AD + return "" + + @wrap_exceptions + def memory_info(self): + ret = self._proc_basic_info() + rss = ret[proc_info_map['rss']] * 1024 + vms = ret[proc_info_map['vms']] * 1024 + return pmem(rss, vms) + + memory_full_info = memory_info + + @wrap_exceptions + def status(self): + code = self._proc_basic_info()[proc_info_map['status']] + # XXX is '?' legit? (we're not supposed to return it anyway) + return PROC_STATUSES.get(code, '?') + + @wrap_exceptions + def threads(self): + procfs_path = self._procfs_path + ret = [] + tids = os.listdir(f"{procfs_path}/{self.pid}/lwp") + hit_enoent = False + for tid in tids: + tid = int(tid) + try: + utime, stime = cext.query_process_thread( + self.pid, tid, procfs_path + ) + except OSError as err: + if err.errno == errno.EOVERFLOW and not IS_64_BIT: + # We may get here if we attempt to query a 64bit process + # with a 32bit python. + # Error originates from read() and also tools like "cat" + # fail in the same way (!). + # Since there simply is no way to determine CPU times we + # return 0.0 as a fallback. See: + # https://github.com/giampaolo/psutil/issues/857 + continue + # ENOENT == thread gone in meantime + if err.errno == errno.ENOENT: + hit_enoent = True + continue + raise + else: + nt = _common.pthread(tid, utime, stime) + ret.append(nt) + if hit_enoent: + self._assert_alive() + return ret + + @wrap_exceptions + def open_files(self): + retlist = [] + hit_enoent = False + procfs_path = self._procfs_path + pathdir = f"{procfs_path}/{self.pid}/path" + for fd in os.listdir(f"{procfs_path}/{self.pid}/fd"): + path = os.path.join(pathdir, fd) + if os.path.islink(path): + try: + file = os.readlink(path) + except FileNotFoundError: + hit_enoent = True + continue + else: + if isfile_strict(file): + retlist.append(_common.popenfile(file, int(fd))) + if hit_enoent: + self._assert_alive() + return retlist + + def _get_unix_sockets(self, pid): + """Get UNIX sockets used by process by parsing 'pfiles' output.""" + # TODO: rewrite this in C (...but the damn netstat source code + # does not include this part! Argh!!) + cmd = ["pfiles", str(pid)] + p = subprocess.Popen( + cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE + ) + stdout, stderr = p.communicate() + stdout, stderr = ( + x.decode(sys.stdout.encoding) for x in (stdout, stderr) + ) + if p.returncode != 0: + if 'permission denied' in stderr.lower(): + raise AccessDenied(self.pid, self._name) + if 'no such process' in stderr.lower(): + raise NoSuchProcess(self.pid, self._name) + msg = f"{cmd!r} command error\n{stderr}" + raise RuntimeError(msg) + + lines = stdout.split('\n')[2:] + for i, line in enumerate(lines): + line = line.lstrip() + if line.startswith('sockname: AF_UNIX'): + path = line.split(' ', 2)[2] + type = lines[i - 2].strip() + if type == 'SOCK_STREAM': + type = socket.SOCK_STREAM + elif type == 'SOCK_DGRAM': + type = socket.SOCK_DGRAM + else: + type = -1 + yield (-1, socket.AF_UNIX, type, path, "", _common.CONN_NONE) + + @wrap_exceptions + def net_connections(self, kind='inet'): + ret = net_connections(kind, _pid=self.pid) + # The underlying C implementation retrieves all OS connections + # and filters them by PID. At this point we can't tell whether + # an empty list means there were no connections for process or + # process is no longer active so we force NSP in case the PID + # is no longer there. + if not ret: + # will raise NSP if process is gone + os.stat(f"{self._procfs_path}/{self.pid}") + + # UNIX sockets + if kind in {'all', 'unix'}: + ret.extend([ + _common.pconn(*conn) + for conn in self._get_unix_sockets(self.pid) + ]) + return ret + + nt_mmap_grouped = namedtuple('mmap', 'path rss anon locked') + nt_mmap_ext = namedtuple('mmap', 'addr perms path rss anon locked') + + @wrap_exceptions + def memory_maps(self): + def toaddr(start, end): + return "{}-{}".format( + hex(start)[2:].strip('L'), hex(end)[2:].strip('L') + ) + + procfs_path = self._procfs_path + retlist = [] + try: + rawlist = cext.proc_memory_maps(self.pid, procfs_path) + except OSError as err: + if err.errno == errno.EOVERFLOW and not IS_64_BIT: + # We may get here if we attempt to query a 64bit process + # with a 32bit python. + # Error originates from read() and also tools like "cat" + # fail in the same way (!). + # Since there simply is no way to determine CPU times we + # return 0.0 as a fallback. See: + # https://github.com/giampaolo/psutil/issues/857 + return [] + else: + raise + hit_enoent = False + for item in rawlist: + addr, addrsize, perm, name, rss, anon, locked = item + addr = toaddr(addr, addrsize) + if not name.startswith('['): + try: + name = os.readlink(f"{procfs_path}/{self.pid}/path/{name}") + except OSError as err: + if err.errno == errno.ENOENT: + # sometimes the link may not be resolved by + # readlink() even if it exists (ls shows it). + # If that's the case we just return the + # unresolved link path. + # This seems an inconsistency with /proc similar + # to: http://goo.gl/55XgO + name = f"{procfs_path}/{self.pid}/path/{name}" + hit_enoent = True + else: + raise + retlist.append((addr, perm, name, rss, anon, locked)) + if hit_enoent: + self._assert_alive() + return retlist + + @wrap_exceptions + def num_fds(self): + return len(os.listdir(f"{self._procfs_path}/{self.pid}/fd")) + + @wrap_exceptions + def num_ctx_switches(self): + return _common.pctxsw( + *cext.proc_num_ctx_switches(self.pid, self._procfs_path) + ) + + @wrap_exceptions + def wait(self, timeout=None): + return _psposix.wait_pid(self.pid, timeout, self._name) diff --git a/llmlab/lib/python3.12/site-packages/psutil/_psutil_linux.abi3.so b/llmlab/lib/python3.12/site-packages/psutil/_psutil_linux.abi3.so new file mode 100755 index 0000000..eea093c Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/_psutil_linux.abi3.so differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/_psutil_posix.abi3.so b/llmlab/lib/python3.12/site-packages/psutil/_psutil_posix.abi3.so new file mode 100755 index 0000000..70bd296 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/_psutil_posix.abi3.so differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/_pswindows.py b/llmlab/lib/python3.12/site-packages/psutil/_pswindows.py new file mode 100644 index 0000000..e5af3c9 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/_pswindows.py @@ -0,0 +1,1103 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Windows platform implementation.""" + +import contextlib +import enum +import functools +import os +import signal +import sys +import time +from collections import namedtuple + +from . import _common +from ._common import ENCODING +from ._common import AccessDenied +from ._common import NoSuchProcess +from ._common import TimeoutExpired +from ._common import conn_tmap +from ._common import conn_to_ntuple +from ._common import debug +from ._common import isfile_strict +from ._common import memoize +from ._common import memoize_when_activated +from ._common import parse_environ_block +from ._common import usage_percent +from ._psutil_windows import ABOVE_NORMAL_PRIORITY_CLASS +from ._psutil_windows import BELOW_NORMAL_PRIORITY_CLASS +from ._psutil_windows import HIGH_PRIORITY_CLASS +from ._psutil_windows import IDLE_PRIORITY_CLASS +from ._psutil_windows import NORMAL_PRIORITY_CLASS +from ._psutil_windows import REALTIME_PRIORITY_CLASS + + +try: + from . import _psutil_windows as cext +except ImportError as err: + if ( + str(err).lower().startswith("dll load failed") + and sys.getwindowsversion()[0] < 6 + ): + # We may get here if: + # 1) we are on an old Windows version + # 2) psutil was installed via pip + wheel + # See: https://github.com/giampaolo/psutil/issues/811 + msg = "this Windows version is too old (< Windows Vista); " + msg += "psutil 3.4.2 is the latest version which supports Windows " + msg += "2000, XP and 2003 server" + raise RuntimeError(msg) from err + else: + raise + + +# process priority constants, import from __init__.py: +# http://msdn.microsoft.com/en-us/library/ms686219(v=vs.85).aspx +# fmt: off +__extra__all__ = [ + "win_service_iter", "win_service_get", + # Process priority + "ABOVE_NORMAL_PRIORITY_CLASS", "BELOW_NORMAL_PRIORITY_CLASS", + "HIGH_PRIORITY_CLASS", "IDLE_PRIORITY_CLASS", "NORMAL_PRIORITY_CLASS", + "REALTIME_PRIORITY_CLASS", + # IO priority + "IOPRIO_VERYLOW", "IOPRIO_LOW", "IOPRIO_NORMAL", "IOPRIO_HIGH", + # others + "CONN_DELETE_TCB", "AF_LINK", +] +# fmt: on + + +# ===================================================================== +# --- globals +# ===================================================================== + +CONN_DELETE_TCB = "DELETE_TCB" +ERROR_PARTIAL_COPY = 299 +PYPY = '__pypy__' in sys.builtin_module_names + +AddressFamily = enum.IntEnum('AddressFamily', {'AF_LINK': -1}) +AF_LINK = AddressFamily.AF_LINK + +TCP_STATUSES = { + cext.MIB_TCP_STATE_ESTAB: _common.CONN_ESTABLISHED, + cext.MIB_TCP_STATE_SYN_SENT: _common.CONN_SYN_SENT, + cext.MIB_TCP_STATE_SYN_RCVD: _common.CONN_SYN_RECV, + cext.MIB_TCP_STATE_FIN_WAIT1: _common.CONN_FIN_WAIT1, + cext.MIB_TCP_STATE_FIN_WAIT2: _common.CONN_FIN_WAIT2, + cext.MIB_TCP_STATE_TIME_WAIT: _common.CONN_TIME_WAIT, + cext.MIB_TCP_STATE_CLOSED: _common.CONN_CLOSE, + cext.MIB_TCP_STATE_CLOSE_WAIT: _common.CONN_CLOSE_WAIT, + cext.MIB_TCP_STATE_LAST_ACK: _common.CONN_LAST_ACK, + cext.MIB_TCP_STATE_LISTEN: _common.CONN_LISTEN, + cext.MIB_TCP_STATE_CLOSING: _common.CONN_CLOSING, + cext.MIB_TCP_STATE_DELETE_TCB: CONN_DELETE_TCB, + cext.PSUTIL_CONN_NONE: _common.CONN_NONE, +} + + +class Priority(enum.IntEnum): + ABOVE_NORMAL_PRIORITY_CLASS = ABOVE_NORMAL_PRIORITY_CLASS + BELOW_NORMAL_PRIORITY_CLASS = BELOW_NORMAL_PRIORITY_CLASS + HIGH_PRIORITY_CLASS = HIGH_PRIORITY_CLASS + IDLE_PRIORITY_CLASS = IDLE_PRIORITY_CLASS + NORMAL_PRIORITY_CLASS = NORMAL_PRIORITY_CLASS + REALTIME_PRIORITY_CLASS = REALTIME_PRIORITY_CLASS + + +globals().update(Priority.__members__) + + +class IOPriority(enum.IntEnum): + IOPRIO_VERYLOW = 0 + IOPRIO_LOW = 1 + IOPRIO_NORMAL = 2 + IOPRIO_HIGH = 3 + + +globals().update(IOPriority.__members__) + +pinfo_map = dict( + num_handles=0, + ctx_switches=1, + user_time=2, + kernel_time=3, + create_time=4, + num_threads=5, + io_rcount=6, + io_wcount=7, + io_rbytes=8, + io_wbytes=9, + io_count_others=10, + io_bytes_others=11, + num_page_faults=12, + peak_wset=13, + wset=14, + peak_paged_pool=15, + paged_pool=16, + peak_non_paged_pool=17, + non_paged_pool=18, + pagefile=19, + peak_pagefile=20, + mem_private=21, +) + + +# ===================================================================== +# --- named tuples +# ===================================================================== + + +# fmt: off +# psutil.cpu_times() +scputimes = namedtuple('scputimes', + ['user', 'system', 'idle', 'interrupt', 'dpc']) +# psutil.virtual_memory() +svmem = namedtuple('svmem', ['total', 'available', 'percent', 'used', 'free']) +# psutil.Process.memory_info() +pmem = namedtuple( + 'pmem', ['rss', 'vms', + 'num_page_faults', 'peak_wset', 'wset', 'peak_paged_pool', + 'paged_pool', 'peak_nonpaged_pool', 'nonpaged_pool', + 'pagefile', 'peak_pagefile', 'private']) +# psutil.Process.memory_full_info() +pfullmem = namedtuple('pfullmem', pmem._fields + ('uss', )) +# psutil.Process.memory_maps(grouped=True) +pmmap_grouped = namedtuple('pmmap_grouped', ['path', 'rss']) +# psutil.Process.memory_maps(grouped=False) +pmmap_ext = namedtuple( + 'pmmap_ext', 'addr perms ' + ' '.join(pmmap_grouped._fields)) +# psutil.Process.io_counters() +pio = namedtuple('pio', ['read_count', 'write_count', + 'read_bytes', 'write_bytes', + 'other_count', 'other_bytes']) +# fmt: on + + +# ===================================================================== +# --- utils +# ===================================================================== + + +@functools.lru_cache(maxsize=512) +def convert_dos_path(s): + r"""Convert paths using native DOS format like: + "\Device\HarddiskVolume1\Windows\systemew\file.txt" + into: + "C:\Windows\systemew\file.txt". + """ + rawdrive = '\\'.join(s.split('\\')[:3]) + driveletter = cext.QueryDosDevice(rawdrive) + remainder = s[len(rawdrive) :] + return os.path.join(driveletter, remainder) + + +@memoize +def getpagesize(): + return cext.getpagesize() + + +# ===================================================================== +# --- memory +# ===================================================================== + + +def virtual_memory(): + """System virtual memory as a namedtuple.""" + mem = cext.virtual_mem() + totphys, availphys, _totsys, _availsys = mem + total = totphys + avail = availphys + free = availphys + used = total - avail + percent = usage_percent((total - avail), total, round_=1) + return svmem(total, avail, percent, used, free) + + +def swap_memory(): + """Swap system memory as a (total, used, free, sin, sout) tuple.""" + mem = cext.virtual_mem() + + total_phys = mem[0] + total_system = mem[2] + + # system memory (commit total/limit) is the sum of physical and swap + # thus physical memory values need to be subtracted to get swap values + total = total_system - total_phys + # commit total is incremented immediately (decrementing free_system) + # while the corresponding free physical value is not decremented until + # pages are accessed, so we can't use free system memory for swap. + # instead, we calculate page file usage based on performance counter + if total > 0: + percentswap = cext.swap_percent() + used = int(0.01 * percentswap * total) + else: + percentswap = 0.0 + used = 0 + + free = total - used + percent = round(percentswap, 1) + return _common.sswap(total, used, free, percent, 0, 0) + + +# ===================================================================== +# --- disk +# ===================================================================== + + +disk_io_counters = cext.disk_io_counters + + +def disk_usage(path): + """Return disk usage associated with path.""" + if isinstance(path, bytes): + # XXX: do we want to use "strict"? Probably yes, in order + # to fail immediately. After all we are accepting input here... + path = path.decode(ENCODING, errors="strict") + total, free = cext.disk_usage(path) + used = total - free + percent = usage_percent(used, total, round_=1) + return _common.sdiskusage(total, used, free, percent) + + +def disk_partitions(all): + """Return disk partitions.""" + rawlist = cext.disk_partitions(all) + return [_common.sdiskpart(*x) for x in rawlist] + + +# ===================================================================== +# --- CPU +# ===================================================================== + + +def cpu_times(): + """Return system CPU times as a named tuple.""" + user, system, idle = cext.cpu_times() + # Internally, GetSystemTimes() is used, and it doesn't return + # interrupt and dpc times. cext.per_cpu_times() does, so we + # rely on it to get those only. + percpu_summed = scputimes(*[sum(n) for n in zip(*cext.per_cpu_times())]) + return scputimes( + user, system, idle, percpu_summed.interrupt, percpu_summed.dpc + ) + + +def per_cpu_times(): + """Return system per-CPU times as a list of named tuples.""" + ret = [] + for user, system, idle, interrupt, dpc in cext.per_cpu_times(): + item = scputimes(user, system, idle, interrupt, dpc) + ret.append(item) + return ret + + +def cpu_count_logical(): + """Return the number of logical CPUs in the system.""" + return cext.cpu_count_logical() + + +def cpu_count_cores(): + """Return the number of CPU cores in the system.""" + return cext.cpu_count_cores() + + +def cpu_stats(): + """Return CPU statistics.""" + ctx_switches, interrupts, _dpcs, syscalls = cext.cpu_stats() + soft_interrupts = 0 + return _common.scpustats( + ctx_switches, interrupts, soft_interrupts, syscalls + ) + + +def cpu_freq(): + """Return CPU frequency. + On Windows per-cpu frequency is not supported. + """ + curr, max_ = cext.cpu_freq() + min_ = 0.0 + return [_common.scpufreq(float(curr), min_, float(max_))] + + +_loadavg_inititialized = False + + +def getloadavg(): + """Return the number of processes in the system run queue averaged + over the last 1, 5, and 15 minutes respectively as a tuple. + """ + global _loadavg_inititialized + + if not _loadavg_inititialized: + cext.init_loadavg_counter() + _loadavg_inititialized = True + + # Drop to 2 decimal points which is what Linux does + raw_loads = cext.getloadavg() + return tuple(round(load, 2) for load in raw_loads) + + +# ===================================================================== +# --- network +# ===================================================================== + + +def net_connections(kind, _pid=-1): + """Return socket connections. If pid == -1 return system-wide + connections (as opposed to connections opened by one process only). + """ + families, types = conn_tmap[kind] + rawlist = cext.net_connections(_pid, families, types) + ret = set() + for item in rawlist: + fd, fam, type, laddr, raddr, status, pid = item + nt = conn_to_ntuple( + fd, + fam, + type, + laddr, + raddr, + status, + TCP_STATUSES, + pid=pid if _pid == -1 else None, + ) + ret.add(nt) + return list(ret) + + +def net_if_stats(): + """Get NIC stats (isup, duplex, speed, mtu).""" + ret = {} + rawdict = cext.net_if_stats() + for name, items in rawdict.items(): + isup, duplex, speed, mtu = items + if hasattr(_common, 'NicDuplex'): + duplex = _common.NicDuplex(duplex) + ret[name] = _common.snicstats(isup, duplex, speed, mtu, '') + return ret + + +def net_io_counters(): + """Return network I/O statistics for every network interface + installed on the system as a dict of raw tuples. + """ + return cext.net_io_counters() + + +def net_if_addrs(): + """Return the addresses associated to each NIC.""" + return cext.net_if_addrs() + + +# ===================================================================== +# --- sensors +# ===================================================================== + + +def sensors_battery(): + """Return battery information.""" + # For constants meaning see: + # https://msdn.microsoft.com/en-us/library/windows/desktop/ + # aa373232(v=vs.85).aspx + acline_status, flags, percent, secsleft = cext.sensors_battery() + power_plugged = acline_status == 1 + no_battery = bool(flags & 128) + charging = bool(flags & 8) + + if no_battery: + return None + if power_plugged or charging: + secsleft = _common.POWER_TIME_UNLIMITED + elif secsleft == -1: + secsleft = _common.POWER_TIME_UNKNOWN + + return _common.sbattery(percent, secsleft, power_plugged) + + +# ===================================================================== +# --- other system functions +# ===================================================================== + + +_last_btime = 0 + + +def boot_time(): + """The system boot time expressed in seconds since the epoch.""" + # This dirty hack is to adjust the precision of the returned + # value which may have a 1 second fluctuation, see: + # https://github.com/giampaolo/psutil/issues/1007 + global _last_btime + ret = float(cext.boot_time()) + if abs(ret - _last_btime) <= 1: + return _last_btime + else: + _last_btime = ret + return ret + + +def users(): + """Return currently connected users as a list of namedtuples.""" + retlist = [] + rawlist = cext.users() + for item in rawlist: + user, hostname, tstamp = item + nt = _common.suser(user, None, hostname, tstamp, None) + retlist.append(nt) + return retlist + + +# ===================================================================== +# --- Windows services +# ===================================================================== + + +def win_service_iter(): + """Yields a list of WindowsService instances.""" + for name, display_name in cext.winservice_enumerate(): + yield WindowsService(name, display_name) + + +def win_service_get(name): + """Open a Windows service and return it as a WindowsService instance.""" + service = WindowsService(name, None) + service._display_name = service._query_config()['display_name'] + return service + + +class WindowsService: # noqa: PLW1641 + """Represents an installed Windows service.""" + + def __init__(self, name, display_name): + self._name = name + self._display_name = display_name + + def __str__(self): + details = f"(name={self._name!r}, display_name={self._display_name!r})" + return f"{self.__class__.__name__}{details}" + + def __repr__(self): + return f"<{self.__str__()} at {id(self)}>" + + def __eq__(self, other): + # Test for equality with another WindosService object based + # on name. + if not isinstance(other, WindowsService): + return NotImplemented + return self._name == other._name + + def __ne__(self, other): + return not self == other + + def _query_config(self): + with self._wrap_exceptions(): + display_name, binpath, username, start_type = ( + cext.winservice_query_config(self._name) + ) + # XXX - update _self.display_name? + return dict( + display_name=display_name, + binpath=binpath, + username=username, + start_type=start_type, + ) + + def _query_status(self): + with self._wrap_exceptions(): + status, pid = cext.winservice_query_status(self._name) + if pid == 0: + pid = None + return dict(status=status, pid=pid) + + @contextlib.contextmanager + def _wrap_exceptions(self): + """Ctx manager which translates bare OSError and WindowsError + exceptions into NoSuchProcess and AccessDenied. + """ + try: + yield + except OSError as err: + name = self._name + if is_permission_err(err): + msg = ( + f"service {name!r} is not querable (not enough privileges)" + ) + raise AccessDenied(pid=None, name=name, msg=msg) from err + elif err.winerror in { + cext.ERROR_INVALID_NAME, + cext.ERROR_SERVICE_DOES_NOT_EXIST, + }: + msg = f"service {name!r} does not exist" + raise NoSuchProcess(pid=None, name=name, msg=msg) from err + else: + raise + + # config query + + def name(self): + """The service name. This string is how a service is referenced + and can be passed to win_service_get() to get a new + WindowsService instance. + """ + return self._name + + def display_name(self): + """The service display name. The value is cached when this class + is instantiated. + """ + return self._display_name + + def binpath(self): + """The fully qualified path to the service binary/exe file as + a string, including command line arguments. + """ + return self._query_config()['binpath'] + + def username(self): + """The name of the user that owns this service.""" + return self._query_config()['username'] + + def start_type(self): + """A string which can either be "automatic", "manual" or + "disabled". + """ + return self._query_config()['start_type'] + + # status query + + def pid(self): + """The process PID, if any, else None. This can be passed + to Process class to control the service's process. + """ + return self._query_status()['pid'] + + def status(self): + """Service status as a string.""" + return self._query_status()['status'] + + def description(self): + """Service long description.""" + return cext.winservice_query_descr(self.name()) + + # utils + + def as_dict(self): + """Utility method retrieving all the information above as a + dictionary. + """ + d = self._query_config() + d.update(self._query_status()) + d['name'] = self.name() + d['display_name'] = self.display_name() + d['description'] = self.description() + return d + + # actions + # XXX: the necessary C bindings for start() and stop() are + # implemented but for now I prefer not to expose them. + # I may change my mind in the future. Reasons: + # - they require Administrator privileges + # - can't implement a timeout for stop() (unless by using a thread, + # which sucks) + # - would require adding ServiceAlreadyStarted and + # ServiceAlreadyStopped exceptions, adding two new APIs. + # - we might also want to have modify(), which would basically mean + # rewriting win32serviceutil.ChangeServiceConfig, which involves a + # lot of stuff (and API constants which would pollute the API), see: + # http://pyxr.sourceforge.net/PyXR/c/python24/lib/site-packages/ + # win32/lib/win32serviceutil.py.html#0175 + # - psutil is typically about "read only" monitoring stuff; + # win_service_* APIs should only be used to retrieve a service and + # check whether it's running + + # def start(self, timeout=None): + # with self._wrap_exceptions(): + # cext.winservice_start(self.name()) + # if timeout: + # giveup_at = time.time() + timeout + # while True: + # if self.status() == "running": + # return + # else: + # if time.time() > giveup_at: + # raise TimeoutExpired(timeout) + # else: + # time.sleep(.1) + + # def stop(self): + # # Note: timeout is not implemented because it's just not + # # possible, see: + # # http://stackoverflow.com/questions/11973228/ + # with self._wrap_exceptions(): + # return cext.winservice_stop(self.name()) + + +# ===================================================================== +# --- processes +# ===================================================================== + + +pids = cext.pids +pid_exists = cext.pid_exists +ppid_map = cext.ppid_map # used internally by Process.children() + + +def is_permission_err(exc): + """Return True if this is a permission error.""" + assert isinstance(exc, OSError), exc + return isinstance(exc, PermissionError) or exc.winerror in { + cext.ERROR_ACCESS_DENIED, + cext.ERROR_PRIVILEGE_NOT_HELD, + } + + +def convert_oserror(exc, pid=None, name=None): + """Convert OSError into NoSuchProcess or AccessDenied.""" + assert isinstance(exc, OSError), exc + if is_permission_err(exc): + return AccessDenied(pid=pid, name=name) + if isinstance(exc, ProcessLookupError): + return NoSuchProcess(pid=pid, name=name) + raise exc + + +def wrap_exceptions(fun): + """Decorator which converts OSError into NoSuchProcess or AccessDenied.""" + + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + try: + return fun(self, *args, **kwargs) + except OSError as err: + raise convert_oserror(err, pid=self.pid, name=self._name) from err + + return wrapper + + +def retry_error_partial_copy(fun): + """Workaround for https://github.com/giampaolo/psutil/issues/875. + See: https://stackoverflow.com/questions/4457745#4457745. + """ + + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + delay = 0.0001 + times = 33 + for _ in range(times): # retries for roughly 1 second + try: + return fun(self, *args, **kwargs) + except OSError as _: + err = _ + if err.winerror == ERROR_PARTIAL_COPY: + time.sleep(delay) + delay = min(delay * 2, 0.04) + continue + raise + msg = ( + f"{fun} retried {times} times, converted to AccessDenied as it's " + f"still returning {err}" + ) + raise AccessDenied(pid=self.pid, name=self._name, msg=msg) + + return wrapper + + +class Process: + """Wrapper class around underlying C implementation.""" + + __slots__ = ["_cache", "_name", "_ppid", "pid"] + + def __init__(self, pid): + self.pid = pid + self._name = None + self._ppid = None + + # --- oneshot() stuff + + def oneshot_enter(self): + self._proc_info.cache_activate(self) + self.exe.cache_activate(self) + + def oneshot_exit(self): + self._proc_info.cache_deactivate(self) + self.exe.cache_deactivate(self) + + @memoize_when_activated + def _proc_info(self): + """Return multiple information about this process as a + raw tuple. + """ + ret = cext.proc_info(self.pid) + assert len(ret) == len(pinfo_map) + return ret + + def name(self): + """Return process name, which on Windows is always the final + part of the executable. + """ + # This is how PIDs 0 and 4 are always represented in taskmgr + # and process-hacker. + if self.pid == 0: + return "System Idle Process" + if self.pid == 4: + return "System" + return os.path.basename(self.exe()) + + @wrap_exceptions + @memoize_when_activated + def exe(self): + if PYPY: + try: + exe = cext.proc_exe(self.pid) + except OSError as err: + # 24 = ERROR_TOO_MANY_OPEN_FILES. Not sure why this happens + # (perhaps PyPy's JIT delaying garbage collection of files?). + if err.errno == 24: + debug(f"{err!r} translated into AccessDenied") + raise AccessDenied(self.pid, self._name) from err + raise + else: + exe = cext.proc_exe(self.pid) + if exe.startswith('\\'): + return convert_dos_path(exe) + return exe # May be "Registry", "MemCompression", ... + + @wrap_exceptions + @retry_error_partial_copy + def cmdline(self): + if cext.WINVER >= cext.WINDOWS_8_1: + # PEB method detects cmdline changes but requires more + # privileges: https://github.com/giampaolo/psutil/pull/1398 + try: + return cext.proc_cmdline(self.pid, use_peb=True) + except OSError as err: + if is_permission_err(err): + return cext.proc_cmdline(self.pid, use_peb=False) + else: + raise + else: + return cext.proc_cmdline(self.pid, use_peb=True) + + @wrap_exceptions + @retry_error_partial_copy + def environ(self): + s = cext.proc_environ(self.pid) + return parse_environ_block(s) + + def ppid(self): + try: + return ppid_map()[self.pid] + except KeyError: + raise NoSuchProcess(self.pid, self._name) from None + + def _get_raw_meminfo(self): + try: + return cext.proc_memory_info(self.pid) + except OSError as err: + if is_permission_err(err): + # TODO: the C ext can probably be refactored in order + # to get this from cext.proc_info() + debug("attempting memory_info() fallback (slower)") + info = self._proc_info() + return ( + info[pinfo_map['num_page_faults']], + info[pinfo_map['peak_wset']], + info[pinfo_map['wset']], + info[pinfo_map['peak_paged_pool']], + info[pinfo_map['paged_pool']], + info[pinfo_map['peak_non_paged_pool']], + info[pinfo_map['non_paged_pool']], + info[pinfo_map['pagefile']], + info[pinfo_map['peak_pagefile']], + info[pinfo_map['mem_private']], + ) + raise + + @wrap_exceptions + def memory_info(self): + # on Windows RSS == WorkingSetSize and VSM == PagefileUsage. + # Underlying C function returns fields of PROCESS_MEMORY_COUNTERS + # struct. + t = self._get_raw_meminfo() + rss = t[2] # wset + vms = t[7] # pagefile + return pmem(*(rss, vms) + t) + + @wrap_exceptions + def memory_full_info(self): + basic_mem = self.memory_info() + uss = cext.proc_memory_uss(self.pid) + uss *= getpagesize() + return pfullmem(*basic_mem + (uss,)) + + def memory_maps(self): + try: + raw = cext.proc_memory_maps(self.pid) + except OSError as err: + # XXX - can't use wrap_exceptions decorator as we're + # returning a generator; probably needs refactoring. + raise convert_oserror(err, self.pid, self._name) from err + else: + for addr, perm, path, rss in raw: + path = convert_dos_path(path) + addr = hex(addr) + yield (addr, perm, path, rss) + + @wrap_exceptions + def kill(self): + return cext.proc_kill(self.pid) + + @wrap_exceptions + def send_signal(self, sig): + if sig == signal.SIGTERM: + cext.proc_kill(self.pid) + elif sig in {signal.CTRL_C_EVENT, signal.CTRL_BREAK_EVENT}: + os.kill(self.pid, sig) + else: + msg = ( + "only SIGTERM, CTRL_C_EVENT and CTRL_BREAK_EVENT signals " + "are supported on Windows" + ) + raise ValueError(msg) + + @wrap_exceptions + def wait(self, timeout=None): + if timeout is None: + cext_timeout = cext.INFINITE + else: + # WaitForSingleObject() expects time in milliseconds. + cext_timeout = int(timeout * 1000) + + timer = getattr(time, 'monotonic', time.time) + stop_at = timer() + timeout if timeout is not None else None + + try: + # Exit code is supposed to come from GetExitCodeProcess(). + # May also be None if OpenProcess() failed with + # ERROR_INVALID_PARAMETER, meaning PID is already gone. + exit_code = cext.proc_wait(self.pid, cext_timeout) + except cext.TimeoutExpired as err: + # WaitForSingleObject() returned WAIT_TIMEOUT. Just raise. + raise TimeoutExpired(timeout, self.pid, self._name) from err + except cext.TimeoutAbandoned: + # WaitForSingleObject() returned WAIT_ABANDONED, see: + # https://github.com/giampaolo/psutil/issues/1224 + # We'll just rely on the internal polling and return None + # when the PID disappears. Subprocess module does the same + # (return None): + # https://github.com/python/cpython/blob/ + # be50a7b627d0aa37e08fa8e2d5568891f19903ce/ + # Lib/subprocess.py#L1193-L1194 + exit_code = None + + # At this point WaitForSingleObject() returned WAIT_OBJECT_0, + # meaning the process is gone. Stupidly there are cases where + # its PID may still stick around so we do a further internal + # polling. + delay = 0.0001 + while True: + if not pid_exists(self.pid): + return exit_code + if stop_at and timer() >= stop_at: + raise TimeoutExpired(timeout, pid=self.pid, name=self._name) + time.sleep(delay) + delay = min(delay * 2, 0.04) # incremental delay + + @wrap_exceptions + def username(self): + if self.pid in {0, 4}: + return 'NT AUTHORITY\\SYSTEM' + domain, user = cext.proc_username(self.pid) + return f"{domain}\\{user}" + + @wrap_exceptions + def create_time(self, fast_only=False): + # Note: proc_times() not put under oneshot() 'cause create_time() + # is already cached by the main Process class. + try: + _user, _system, created = cext.proc_times(self.pid) + return created + except OSError as err: + if is_permission_err(err): + if fast_only: + raise + debug("attempting create_time() fallback (slower)") + return self._proc_info()[pinfo_map['create_time']] + raise + + @wrap_exceptions + def num_threads(self): + return self._proc_info()[pinfo_map['num_threads']] + + @wrap_exceptions + def threads(self): + rawlist = cext.proc_threads(self.pid) + retlist = [] + for thread_id, utime, stime in rawlist: + ntuple = _common.pthread(thread_id, utime, stime) + retlist.append(ntuple) + return retlist + + @wrap_exceptions + def cpu_times(self): + try: + user, system, _created = cext.proc_times(self.pid) + except OSError as err: + if not is_permission_err(err): + raise + debug("attempting cpu_times() fallback (slower)") + info = self._proc_info() + user = info[pinfo_map['user_time']] + system = info[pinfo_map['kernel_time']] + # Children user/system times are not retrievable (set to 0). + return _common.pcputimes(user, system, 0.0, 0.0) + + @wrap_exceptions + def suspend(self): + cext.proc_suspend_or_resume(self.pid, True) + + @wrap_exceptions + def resume(self): + cext.proc_suspend_or_resume(self.pid, False) + + @wrap_exceptions + @retry_error_partial_copy + def cwd(self): + if self.pid in {0, 4}: + raise AccessDenied(self.pid, self._name) + # return a normalized pathname since the native C function appends + # "\\" at the and of the path + path = cext.proc_cwd(self.pid) + return os.path.normpath(path) + + @wrap_exceptions + def open_files(self): + if self.pid in {0, 4}: + return [] + ret = set() + # Filenames come in in native format like: + # "\Device\HarddiskVolume1\Windows\systemew\file.txt" + # Convert the first part in the corresponding drive letter + # (e.g. "C:\") by using Windows's QueryDosDevice() + raw_file_names = cext.proc_open_files(self.pid) + for file in raw_file_names: + file = convert_dos_path(file) + if isfile_strict(file): + ntuple = _common.popenfile(file, -1) + ret.add(ntuple) + return list(ret) + + @wrap_exceptions + def net_connections(self, kind='inet'): + return net_connections(kind, _pid=self.pid) + + @wrap_exceptions + def nice_get(self): + value = cext.proc_priority_get(self.pid) + value = Priority(value) + return value + + @wrap_exceptions + def nice_set(self, value): + return cext.proc_priority_set(self.pid, value) + + @wrap_exceptions + def ionice_get(self): + ret = cext.proc_io_priority_get(self.pid) + ret = IOPriority(ret) + return ret + + @wrap_exceptions + def ionice_set(self, ioclass, value): + if value: + msg = "value argument not accepted on Windows" + raise TypeError(msg) + if ioclass not in { + IOPriority.IOPRIO_VERYLOW, + IOPriority.IOPRIO_LOW, + IOPriority.IOPRIO_NORMAL, + IOPriority.IOPRIO_HIGH, + }: + msg = f"{ioclass} is not a valid priority" + raise ValueError(msg) + cext.proc_io_priority_set(self.pid, ioclass) + + @wrap_exceptions + def io_counters(self): + try: + ret = cext.proc_io_counters(self.pid) + except OSError as err: + if not is_permission_err(err): + raise + debug("attempting io_counters() fallback (slower)") + info = self._proc_info() + ret = ( + info[pinfo_map['io_rcount']], + info[pinfo_map['io_wcount']], + info[pinfo_map['io_rbytes']], + info[pinfo_map['io_wbytes']], + info[pinfo_map['io_count_others']], + info[pinfo_map['io_bytes_others']], + ) + return pio(*ret) + + @wrap_exceptions + def status(self): + suspended = cext.proc_is_suspended(self.pid) + if suspended: + return _common.STATUS_STOPPED + else: + return _common.STATUS_RUNNING + + @wrap_exceptions + def cpu_affinity_get(self): + def from_bitmask(x): + return [i for i in range(64) if (1 << i) & x] + + bitmask = cext.proc_cpu_affinity_get(self.pid) + return from_bitmask(bitmask) + + @wrap_exceptions + def cpu_affinity_set(self, value): + def to_bitmask(ls): + if not ls: + msg = f"invalid argument {ls!r}" + raise ValueError(msg) + out = 0 + for b in ls: + out |= 2**b + return out + + # SetProcessAffinityMask() states that ERROR_INVALID_PARAMETER + # is returned for an invalid CPU but this seems not to be true, + # therefore we check CPUs validy beforehand. + allcpus = list(range(len(per_cpu_times()))) + for cpu in value: + if cpu not in allcpus: + if not isinstance(cpu, int): + msg = f"invalid CPU {cpu!r}; an integer is required" + raise TypeError(msg) + msg = f"invalid CPU {cpu!r}" + raise ValueError(msg) + + bitmask = to_bitmask(value) + cext.proc_cpu_affinity_set(self.pid, bitmask) + + @wrap_exceptions + def num_handles(self): + try: + return cext.proc_num_handles(self.pid) + except OSError as err: + if is_permission_err(err): + debug("attempting num_handles() fallback (slower)") + return self._proc_info()[pinfo_map['num_handles']] + raise + + @wrap_exceptions + def num_ctx_switches(self): + ctx_switches = self._proc_info()[pinfo_map['ctx_switches']] + # only voluntary ctx switches are supported + return _common.pctxsw(ctx_switches, 0) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__init__.py b/llmlab/lib/python3.12/site-packages/psutil/tests/__init__.py new file mode 100644 index 0000000..5d4b3ab --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/__init__.py @@ -0,0 +1,2025 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Test utilities.""" + + +import atexit +import contextlib +import ctypes +import enum +import errno +import functools +import gc +import importlib +import ipaddress +import os +import platform +import random +import re +import select +import shlex +import shutil +import signal +import socket +import stat +import subprocess +import sys +import tempfile +import textwrap +import threading +import time +import unittest +import warnings +from socket import AF_INET +from socket import AF_INET6 +from socket import SOCK_STREAM + + +try: + import pytest +except ImportError: + pytest = None + +import psutil +from psutil import AIX +from psutil import LINUX +from psutil import MACOS +from psutil import NETBSD +from psutil import OPENBSD +from psutil import POSIX +from psutil import SUNOS +from psutil import WINDOWS +from psutil._common import bytes2human +from psutil._common import debug +from psutil._common import memoize +from psutil._common import print_color +from psutil._common import supports_ipv6 + + +if POSIX: + from psutil._psposix import wait_pid + + +# fmt: off +__all__ = [ + # constants + 'DEVNULL', 'GLOBAL_TIMEOUT', 'TOLERANCE_SYS_MEM', 'NO_RETRIES', + 'PYPY', 'PYTHON_EXE', 'PYTHON_EXE_ENV', 'ROOT_DIR', 'SCRIPTS_DIR', + 'TESTFN_PREFIX', 'UNICODE_SUFFIX', 'INVALID_UNICODE_SUFFIX', + 'CI_TESTING', 'VALID_PROC_STATUSES', 'TOLERANCE_DISK_USAGE', 'IS_64BIT', + "HAS_CPU_AFFINITY", "HAS_CPU_FREQ", "HAS_ENVIRON", "HAS_PROC_IO_COUNTERS", + "HAS_IONICE", "HAS_MEMORY_MAPS", "HAS_PROC_CPU_NUM", "HAS_RLIMIT", + "HAS_SENSORS_BATTERY", "HAS_BATTERY", "HAS_SENSORS_FANS", + "HAS_SENSORS_TEMPERATURES", "HAS_NET_CONNECTIONS_UNIX", "MACOS_11PLUS", + "MACOS_12PLUS", "COVERAGE", 'AARCH64', "PYTEST_PARALLEL", + # subprocesses + 'pyrun', 'terminate', 'reap_children', 'spawn_testproc', 'spawn_zombie', + 'spawn_children_pair', + # threads + 'ThreadTask', + # test utils + 'unittest', 'skip_on_access_denied', 'skip_on_not_implemented', + 'retry_on_failure', 'TestMemoryLeak', 'PsutilTestCase', + 'process_namespace', 'system_namespace', 'print_sysinfo', + 'is_win_secure_system_proc', 'fake_pytest', + # fs utils + 'chdir', 'safe_rmpath', 'create_py_exe', 'create_c_exe', 'get_testfn', + # os + 'get_winver', 'kernel_version', + # sync primitives + 'call_until', 'wait_for_pid', 'wait_for_file', + # network + 'check_net_address', 'filter_proc_net_connections', + 'get_free_port', 'bind_socket', 'bind_unix_socket', 'tcp_socketpair', + 'unix_socketpair', 'create_sockets', + # compat + 'reload_module', 'import_module_by_path', + # others + 'warn', 'copyload_shared_lib', 'is_namedtuple', +] +# fmt: on + + +# =================================================================== +# --- constants +# =================================================================== + +# --- platforms + +PYPY = '__pypy__' in sys.builtin_module_names +# whether we're running this test suite on a Continuous Integration service +GITHUB_ACTIONS = 'GITHUB_ACTIONS' in os.environ or 'CIBUILDWHEEL' in os.environ +CI_TESTING = GITHUB_ACTIONS +COVERAGE = 'COVERAGE_RUN' in os.environ +PYTEST_PARALLEL = "PYTEST_XDIST_WORKER" in os.environ # `make test-parallel` +# are we a 64 bit process? +IS_64BIT = sys.maxsize > 2**32 +AARCH64 = platform.machine() == "aarch64" + + +@memoize +def macos_version(): + version_str = platform.mac_ver()[0] + version = tuple(map(int, version_str.split(".")[:2])) + if version == (10, 16): + # When built against an older macOS SDK, Python will report + # macOS 10.16 instead of the real version. + version_str = subprocess.check_output( + [ + sys.executable, + "-sS", + "-c", + "import platform; print(platform.mac_ver()[0])", + ], + env={"SYSTEM_VERSION_COMPAT": "0"}, + universal_newlines=True, + ) + version = tuple(map(int, version_str.split(".")[:2])) + return version + + +if MACOS: + MACOS_11PLUS = macos_version() > (10, 15) + MACOS_12PLUS = macos_version() >= (12, 0) +else: + MACOS_11PLUS = False + MACOS_12PLUS = False + + +# --- configurable defaults + +# how many times retry_on_failure() decorator will retry +NO_RETRIES = 10 +# bytes tolerance for system-wide related tests +TOLERANCE_SYS_MEM = 5 * 1024 * 1024 # 5MB +TOLERANCE_DISK_USAGE = 10 * 1024 * 1024 # 10MB +# the timeout used in functions which have to wait +GLOBAL_TIMEOUT = 5 +# be more tolerant if we're on CI in order to avoid false positives +if CI_TESTING: + NO_RETRIES *= 3 + GLOBAL_TIMEOUT *= 3 + TOLERANCE_SYS_MEM *= 4 + TOLERANCE_DISK_USAGE *= 3 + +# --- file names + +# Disambiguate TESTFN for parallel testing. +if os.name == 'java': + # Jython disallows @ in module names + TESTFN_PREFIX = f"$psutil-{os.getpid()}-" +else: + TESTFN_PREFIX = f"@psutil-{os.getpid()}-" +UNICODE_SUFFIX = "-ƒőő" +# An invalid unicode string. +INVALID_UNICODE_SUFFIX = b"f\xc0\x80".decode('utf8', 'surrogateescape') +ASCII_FS = sys.getfilesystemencoding().lower() in {"ascii", "us-ascii"} + +# --- paths + +ROOT_DIR = os.path.realpath( + os.path.join(os.path.dirname(__file__), '..', '..') +) +SCRIPTS_DIR = os.environ.get( + "PSUTIL_SCRIPTS_DIR", os.path.join(ROOT_DIR, 'scripts') +) +HERE = os.path.realpath(os.path.dirname(__file__)) + +# --- support + +HAS_CPU_AFFINITY = hasattr(psutil.Process, "cpu_affinity") +HAS_CPU_FREQ = hasattr(psutil, "cpu_freq") +HAS_ENVIRON = hasattr(psutil.Process, "environ") +HAS_GETLOADAVG = hasattr(psutil, "getloadavg") +HAS_IONICE = hasattr(psutil.Process, "ionice") +HAS_MEMORY_MAPS = hasattr(psutil.Process, "memory_maps") +HAS_NET_CONNECTIONS_UNIX = POSIX and not SUNOS +HAS_NET_IO_COUNTERS = hasattr(psutil, "net_io_counters") +HAS_PROC_CPU_NUM = hasattr(psutil.Process, "cpu_num") +HAS_PROC_IO_COUNTERS = hasattr(psutil.Process, "io_counters") +HAS_RLIMIT = hasattr(psutil.Process, "rlimit") +HAS_SENSORS_BATTERY = hasattr(psutil, "sensors_battery") +try: + HAS_BATTERY = HAS_SENSORS_BATTERY and bool(psutil.sensors_battery()) +except Exception: # noqa: BLE001 + HAS_BATTERY = False +HAS_SENSORS_FANS = hasattr(psutil, "sensors_fans") +HAS_SENSORS_TEMPERATURES = hasattr(psutil, "sensors_temperatures") +HAS_THREADS = hasattr(psutil.Process, "threads") +SKIP_SYSCONS = (MACOS or AIX) and os.getuid() != 0 + +# --- misc + + +def _get_py_exe(): + def attempt(exe): + try: + subprocess.check_call( + [exe, "-V"], stdout=subprocess.PIPE, stderr=subprocess.PIPE + ) + except subprocess.CalledProcessError: + return None + else: + return exe + + env = os.environ.copy() + + # On Windows, starting with python 3.7, virtual environments use a + # venv launcher startup process. This does not play well when + # counting spawned processes, or when relying on the PID of the + # spawned process to do some checks, e.g. connections check per PID. + # Let's use the base python in this case. + base = getattr(sys, "_base_executable", None) + if WINDOWS and sys.version_info >= (3, 7) and base is not None: + # We need to set __PYVENV_LAUNCHER__ to sys.executable for the + # base python executable to know about the environment. + env["__PYVENV_LAUNCHER__"] = sys.executable + return base, env + elif GITHUB_ACTIONS: + return sys.executable, env + elif MACOS: + exe = ( + attempt(sys.executable) + or attempt(os.path.realpath(sys.executable)) + or attempt( + shutil.which("python{}.{}".format(*sys.version_info[:2])) + ) + or attempt(psutil.Process().exe()) + ) + if not exe: + raise ValueError("can't find python exe real abspath") + return exe, env + else: + exe = os.path.realpath(sys.executable) + assert os.path.exists(exe), exe + return exe, env + + +PYTHON_EXE, PYTHON_EXE_ENV = _get_py_exe() +DEVNULL = open(os.devnull, 'r+') # noqa: SIM115 +atexit.register(DEVNULL.close) + +VALID_PROC_STATUSES = [ + getattr(psutil, x) for x in dir(psutil) if x.startswith('STATUS_') +] +AF_UNIX = getattr(socket, "AF_UNIX", object()) + +_subprocesses_started = set() +_pids_started = set() + + +# =================================================================== +# --- threads +# =================================================================== + + +class ThreadTask(threading.Thread): + """A thread task which does nothing expect staying alive.""" + + def __init__(self): + super().__init__() + self._running = False + self._interval = 0.001 + self._flag = threading.Event() + + def __repr__(self): + name = self.__class__.__name__ + return f"<{name} running={self._running} at {id(self):#x}>" + + def __enter__(self): + self.start() + return self + + def __exit__(self, *args, **kwargs): + self.stop() + + def start(self): + """Start thread and keep it running until an explicit + stop() request. Polls for shutdown every 'timeout' seconds. + """ + if self._running: + raise ValueError("already started") + threading.Thread.start(self) + self._flag.wait() + + def run(self): + self._running = True + self._flag.set() + while self._running: + time.sleep(self._interval) + + def stop(self): + """Stop thread execution and and waits until it is stopped.""" + if not self._running: + raise ValueError("already stopped") + self._running = False + self.join() + + +# =================================================================== +# --- subprocesses +# =================================================================== + + +def _reap_children_on_err(fun): + @functools.wraps(fun) + def wrapper(*args, **kwargs): + try: + return fun(*args, **kwargs) + except Exception: + reap_children() + raise + + return wrapper + + +@_reap_children_on_err +def spawn_testproc(cmd=None, **kwds): + """Create a python subprocess which does nothing for some secs and + return it as a subprocess.Popen instance. + If "cmd" is specified that is used instead of python. + By default stdin and stdout are redirected to /dev/null. + It also attempts to make sure the process is in a reasonably + initialized state. + The process is registered for cleanup on reap_children(). + """ + kwds.setdefault("stdin", DEVNULL) + kwds.setdefault("stdout", DEVNULL) + kwds.setdefault("cwd", os.getcwd()) + kwds.setdefault("env", PYTHON_EXE_ENV) + if WINDOWS: + # Prevents the subprocess to open error dialogs. This will also + # cause stderr to be suppressed, which is suboptimal in order + # to debug broken tests. + CREATE_NO_WINDOW = 0x8000000 + kwds.setdefault("creationflags", CREATE_NO_WINDOW) + if cmd is None: + testfn = get_testfn(dir=os.getcwd()) + try: + safe_rmpath(testfn) + pyline = ( + "import time;" + f"open(r'{testfn}', 'w').close();" + "[time.sleep(0.1) for x in range(100)];" # 10 secs + ) + cmd = [PYTHON_EXE, "-c", pyline] + sproc = subprocess.Popen(cmd, **kwds) + _subprocesses_started.add(sproc) + wait_for_file(testfn, delete=True, empty=True) + finally: + safe_rmpath(testfn) + else: + sproc = subprocess.Popen(cmd, **kwds) + _subprocesses_started.add(sproc) + wait_for_pid(sproc.pid) + return sproc + + +@_reap_children_on_err +def spawn_children_pair(): + """Create a subprocess which creates another one as in: + A (us) -> B (child) -> C (grandchild). + Return a (child, grandchild) tuple. + The 2 processes are fully initialized and will live for 60 secs + and are registered for cleanup on reap_children(). + """ + tfile = None + testfn = get_testfn(dir=os.getcwd()) + try: + s = textwrap.dedent(f"""\ + import subprocess, os, sys, time + s = "import os, time;" + s += "f = open('{os.path.basename(testfn)}', 'w');" + s += "f.write(str(os.getpid()));" + s += "f.close();" + s += "[time.sleep(0.1) for x in range(100 * 6)];" + p = subprocess.Popen([r'{PYTHON_EXE}', '-c', s]) + p.wait() + """) + # On Windows if we create a subprocess with CREATE_NO_WINDOW flag + # set (which is the default) a "conhost.exe" extra process will be + # spawned as a child. We don't want that. + if WINDOWS: + subp, tfile = pyrun(s, creationflags=0) + else: + subp, tfile = pyrun(s) + child = psutil.Process(subp.pid) + grandchild_pid = int(wait_for_file(testfn, delete=True, empty=False)) + _pids_started.add(grandchild_pid) + grandchild = psutil.Process(grandchild_pid) + return (child, grandchild) + finally: + safe_rmpath(testfn) + if tfile is not None: + safe_rmpath(tfile) + + +def spawn_zombie(): + """Create a zombie process and return a (parent, zombie) process tuple. + In order to kill the zombie parent must be terminate()d first, then + zombie must be wait()ed on. + """ + assert psutil.POSIX + unix_file = get_testfn() + src = textwrap.dedent(f"""\ + import os, sys, time, socket, contextlib + child_pid = os.fork() + if child_pid > 0: + time.sleep(3000) + else: + # this is the zombie process + with socket.socket(socket.AF_UNIX) as s: + s.connect('{unix_file}') + pid = bytes(str(os.getpid()), 'ascii') + s.sendall(pid) + """) + tfile = None + sock = bind_unix_socket(unix_file) + try: + sock.settimeout(GLOBAL_TIMEOUT) + parent, tfile = pyrun(src) + conn, _ = sock.accept() + try: + select.select([conn.fileno()], [], [], GLOBAL_TIMEOUT) + zpid = int(conn.recv(1024)) + _pids_started.add(zpid) + zombie = psutil.Process(zpid) + call_until(lambda: zombie.status() == psutil.STATUS_ZOMBIE) + return (parent, zombie) + finally: + conn.close() + finally: + sock.close() + safe_rmpath(unix_file) + if tfile is not None: + safe_rmpath(tfile) + + +@_reap_children_on_err +def pyrun(src, **kwds): + """Run python 'src' code string in a separate interpreter. + Returns a subprocess.Popen instance and the test file where the source + code was written. + """ + kwds.setdefault("stdout", None) + kwds.setdefault("stderr", None) + srcfile = get_testfn() + try: + with open(srcfile, "w") as f: + f.write(src) + subp = spawn_testproc([PYTHON_EXE, f.name], **kwds) + wait_for_pid(subp.pid) + return (subp, srcfile) + except Exception: + safe_rmpath(srcfile) + raise + + +@_reap_children_on_err +def sh(cmd, **kwds): + """Run cmd in a subprocess and return its output. + raises RuntimeError on error. + """ + # Prevents subprocess to open error dialogs in case of error. + flags = 0x8000000 if WINDOWS else 0 + kwds.setdefault("stdout", subprocess.PIPE) + kwds.setdefault("stderr", subprocess.PIPE) + kwds.setdefault("universal_newlines", True) + kwds.setdefault("creationflags", flags) + if isinstance(cmd, str): + cmd = shlex.split(cmd) + p = subprocess.Popen(cmd, **kwds) + _subprocesses_started.add(p) + stdout, stderr = p.communicate(timeout=GLOBAL_TIMEOUT) + if p.returncode != 0: + raise RuntimeError(stdout + stderr) + if stderr: + warn(stderr) + if stdout.endswith('\n'): + stdout = stdout[:-1] + return stdout + + +def terminate(proc_or_pid, sig=signal.SIGTERM, wait_timeout=GLOBAL_TIMEOUT): + """Terminate a process and wait() for it. + Process can be a PID or an instance of psutil.Process(), + subprocess.Popen() or psutil.Popen(). + If it's a subprocess.Popen() or psutil.Popen() instance also closes + its stdin / stdout / stderr fds. + PID is wait()ed even if the process is already gone (kills zombies). + Does nothing if the process does not exist. + Return process exit status. + """ + + def wait(proc, timeout): + proc.wait(timeout) + if WINDOWS and isinstance(proc, subprocess.Popen): + # Otherwise PID may still hang around. + try: + return psutil.Process(proc.pid).wait(timeout) + except psutil.NoSuchProcess: + pass + + def sendsig(proc, sig): + # XXX: otherwise the build hangs for some reason. + if MACOS and GITHUB_ACTIONS: + sig = signal.SIGKILL + # If the process received SIGSTOP, SIGCONT is necessary first, + # otherwise SIGTERM won't work. + if POSIX and sig != signal.SIGKILL: + proc.send_signal(signal.SIGCONT) + proc.send_signal(sig) + + def term_subprocess_proc(proc, timeout): + try: + sendsig(proc, sig) + except ProcessLookupError: + pass + except OSError as err: + if WINDOWS and err.winerror == 6: # "invalid handle" + pass + raise + return wait(proc, timeout) + + def term_psutil_proc(proc, timeout): + try: + sendsig(proc, sig) + except psutil.NoSuchProcess: + pass + return wait(proc, timeout) + + def term_pid(pid, timeout): + try: + proc = psutil.Process(pid) + except psutil.NoSuchProcess: + # Needed to kill zombies. + if POSIX: + return wait_pid(pid, timeout) + else: + return term_psutil_proc(proc, timeout) + + def flush_popen(proc): + if proc.stdout: + proc.stdout.close() + if proc.stderr: + proc.stderr.close() + # Flushing a BufferedWriter may raise an error. + if proc.stdin: + proc.stdin.close() + + p = proc_or_pid + try: + if isinstance(p, int): + return term_pid(p, wait_timeout) + elif isinstance(p, (psutil.Process, psutil.Popen)): + return term_psutil_proc(p, wait_timeout) + elif isinstance(p, subprocess.Popen): + return term_subprocess_proc(p, wait_timeout) + else: + raise TypeError(f"wrong type {p!r}") + finally: + if isinstance(p, (subprocess.Popen, psutil.Popen)): + flush_popen(p) + pid = p if isinstance(p, int) else p.pid + assert not psutil.pid_exists(pid), pid + + +def reap_children(recursive=False): + """Terminate and wait() any subprocess started by this test suite + and any children currently running, ensuring that no processes stick + around to hog resources. + If recursive is True it also tries to terminate and wait() + all grandchildren started by this process. + """ + # Get the children here before terminating them, as in case of + # recursive=True we don't want to lose the intermediate reference + # pointing to the grandchildren. + children = psutil.Process().children(recursive=recursive) + + # Terminate subprocess.Popen. + while _subprocesses_started: + subp = _subprocesses_started.pop() + terminate(subp) + + # Collect started pids. + while _pids_started: + pid = _pids_started.pop() + terminate(pid) + + # Terminate children. + if children: + for p in children: + terminate(p, wait_timeout=None) + _, alive = psutil.wait_procs(children, timeout=GLOBAL_TIMEOUT) + for p in alive: + warn(f"couldn't terminate process {p!r}; attempting kill()") + terminate(p, sig=signal.SIGKILL) + + +# =================================================================== +# --- OS +# =================================================================== + + +def kernel_version(): + """Return a tuple such as (2, 6, 36).""" + if not POSIX: + raise NotImplementedError("not POSIX") + s = "" + uname = os.uname()[2] + for c in uname: + if c.isdigit() or c == '.': + s += c + else: + break + if not s: + raise ValueError(f"can't parse {uname!r}") + minor = 0 + micro = 0 + nums = s.split('.') + major = int(nums[0]) + if len(nums) >= 2: + minor = int(nums[1]) + if len(nums) >= 3: + micro = int(nums[2]) + return (major, minor, micro) + + +def get_winver(): + if not WINDOWS: + raise NotImplementedError("not WINDOWS") + wv = sys.getwindowsversion() + sp = wv.service_pack_major or 0 + return (wv[0], wv[1], sp) + + +# =================================================================== +# --- sync primitives +# =================================================================== + + +class retry: + """A retry decorator.""" + + def __init__( + self, + exception=Exception, + timeout=None, + retries=None, + interval=0.001, + logfun=None, + ): + if timeout and retries: + raise ValueError("timeout and retries args are mutually exclusive") + self.exception = exception + self.timeout = timeout + self.retries = retries + self.interval = interval + self.logfun = logfun + + def __iter__(self): + if self.timeout: + stop_at = time.time() + self.timeout + while time.time() < stop_at: + yield + elif self.retries: + for _ in range(self.retries): + yield + else: + while True: + yield + + def sleep(self): + if self.interval is not None: + time.sleep(self.interval) + + def __call__(self, fun): + @functools.wraps(fun) + def wrapper(*args, **kwargs): + exc = None + for _ in self: + try: + return fun(*args, **kwargs) + except self.exception as _: + exc = _ + if self.logfun is not None: + self.logfun(exc) + self.sleep() + continue + + raise exc + + # This way the user of the decorated function can change config + # parameters. + wrapper.decorator = self + return wrapper + + +@retry( + exception=psutil.NoSuchProcess, + logfun=None, + timeout=GLOBAL_TIMEOUT, + interval=0.001, +) +def wait_for_pid(pid): + """Wait for pid to show up in the process list then return. + Used in the test suite to give time the sub process to initialize. + """ + if pid not in psutil.pids(): + raise psutil.NoSuchProcess(pid) + psutil.Process(pid) + + +@retry( + exception=(FileNotFoundError, AssertionError), + logfun=None, + timeout=GLOBAL_TIMEOUT, + interval=0.001, +) +def wait_for_file(fname, delete=True, empty=False): + """Wait for a file to be written on disk with some content.""" + with open(fname, "rb") as f: + data = f.read() + if not empty: + assert data + if delete: + safe_rmpath(fname) + return data + + +@retry( + exception=AssertionError, + logfun=None, + timeout=GLOBAL_TIMEOUT, + interval=0.001, +) +def call_until(fun): + """Keep calling function until it evaluates to True.""" + ret = fun() + assert ret + return ret + + +# =================================================================== +# --- fs +# =================================================================== + + +def safe_rmpath(path): + """Convenience function for removing temporary test files or dirs.""" + + def retry_fun(fun): + # On Windows it could happen that the file or directory has + # open handles or references preventing the delete operation + # to succeed immediately, so we retry for a while. See: + # https://bugs.python.org/issue33240 + stop_at = time.time() + GLOBAL_TIMEOUT + while time.time() < stop_at: + try: + return fun() + except FileNotFoundError: + pass + except OSError as _: + err = _ + warn(f"ignoring {err}") + time.sleep(0.01) + raise err + + try: + st = os.stat(path) + if stat.S_ISDIR(st.st_mode): + fun = functools.partial(shutil.rmtree, path) + else: + fun = functools.partial(os.remove, path) + if POSIX: + fun() + else: + retry_fun(fun) + except FileNotFoundError: + pass + + +def safe_mkdir(dir): + """Convenience function for creating a directory.""" + try: + os.mkdir(dir) + except FileExistsError: + pass + + +@contextlib.contextmanager +def chdir(dirname): + """Context manager which temporarily changes the current directory.""" + curdir = os.getcwd() + try: + os.chdir(dirname) + yield + finally: + os.chdir(curdir) + + +def create_py_exe(path): + """Create a Python executable file in the given location.""" + assert not os.path.exists(path), path + atexit.register(safe_rmpath, path) + shutil.copyfile(PYTHON_EXE, path) + if POSIX: + st = os.stat(path) + os.chmod(path, st.st_mode | stat.S_IEXEC) + return path + + +def create_c_exe(path, c_code=None): + """Create a compiled C executable in the given location.""" + assert not os.path.exists(path), path + if not shutil.which("gcc"): + raise pytest.skip("gcc is not installed") + if c_code is None: + c_code = textwrap.dedent(""" + #include + int main() { + pause(); + return 1; + } + """) + else: + assert isinstance(c_code, str), c_code + + atexit.register(safe_rmpath, path) + with open(get_testfn(suffix='.c'), "w") as f: + f.write(c_code) + try: + subprocess.check_call(["gcc", f.name, "-o", path]) + finally: + safe_rmpath(f.name) + return path + + +def get_testfn(suffix="", dir=None): + """Return an absolute pathname of a file or dir that did not + exist at the time this call is made. Also schedule it for safe + deletion at interpreter exit. It's technically racy but probably + not really due to the time variant. + """ + while True: + name = tempfile.mktemp(prefix=TESTFN_PREFIX, suffix=suffix, dir=dir) + if not os.path.exists(name): # also include dirs + path = os.path.realpath(name) # needed for OSX + atexit.register(safe_rmpath, path) + return path + + +# =================================================================== +# --- testing +# =================================================================== + + +class fake_pytest: + """A class that mimics some basic pytest APIs. This is meant for + when unit tests are run in production, where pytest may not be + installed. Still, the user can test psutil installation via: + + $ python3 -m psutil.tests + """ + + @staticmethod + def main(*args, **kw): # noqa: ARG004 + """Mimics pytest.main(). It has the same effect as running + `python3 -m unittest -v` from the project root directory. + """ + suite = unittest.TestLoader().discover(HERE) + unittest.TextTestRunner(verbosity=2).run(suite) + warnings.warn( + "Fake pytest module was used. Test results may be inaccurate.", + UserWarning, + stacklevel=1, + ) + return suite + + @staticmethod + def raises(exc, match=None): + """Mimics `pytest.raises`.""" + + class ExceptionInfo: + _exc = None + + @property + def value(self): + return self._exc + + @contextlib.contextmanager + def context(exc, match=None): + einfo = ExceptionInfo() + try: + yield einfo + except exc as err: + if match and not re.search(match, str(err)): + msg = f'"{match}" does not match "{err}"' + raise AssertionError(msg) + einfo._exc = err + else: + raise AssertionError(f"{exc!r} not raised") + + return context(exc, match=match) + + @staticmethod + def warns(warning, match=None): + """Mimics `pytest.warns`.""" + if match: + return unittest.TestCase().assertWarnsRegex(warning, match) + return unittest.TestCase().assertWarns(warning) + + @staticmethod + def skip(reason=""): + """Mimics `unittest.SkipTest`.""" + raise unittest.SkipTest(reason) + + class mark: + + @staticmethod + def skipif(condition, reason=""): + """Mimics `@pytest.mark.skipif` decorator.""" + return unittest.skipIf(condition, reason) + + class xdist_group: + """Mimics `@pytest.mark.xdist_group` decorator (no-op).""" + + def __init__(self, name=None): + pass + + def __call__(self, cls_or_meth): + return cls_or_meth + + +if pytest is None: + pytest = fake_pytest + + +class PsutilTestCase(unittest.TestCase): + """Test class providing auto-cleanup wrappers on top of process + test utilities. All test classes should derive from this one, even + if we use pytest. + """ + + def get_testfn(self, suffix="", dir=None): + fname = get_testfn(suffix=suffix, dir=dir) + self.addCleanup(safe_rmpath, fname) + return fname + + def spawn_testproc(self, *args, **kwds): + sproc = spawn_testproc(*args, **kwds) + self.addCleanup(terminate, sproc) + return sproc + + def spawn_children_pair(self): + child1, child2 = spawn_children_pair() + self.addCleanup(terminate, child2) + self.addCleanup(terminate, child1) # executed first + return (child1, child2) + + def spawn_zombie(self): + parent, zombie = spawn_zombie() + self.addCleanup(terminate, zombie) + self.addCleanup(terminate, parent) # executed first + return (parent, zombie) + + def pyrun(self, *args, **kwds): + sproc, srcfile = pyrun(*args, **kwds) + self.addCleanup(safe_rmpath, srcfile) + self.addCleanup(terminate, sproc) # executed first + return sproc + + def _check_proc_exc(self, proc, exc): + assert isinstance(exc, psutil.Error) + assert exc.pid == proc.pid + assert exc.name == proc._name + if exc.name: + assert exc.name + if isinstance(exc, psutil.ZombieProcess): + assert exc.ppid == proc._ppid + if exc.ppid is not None: + assert exc.ppid >= 0 + str(exc) + repr(exc) + + def assertPidGone(self, pid): + with pytest.raises(psutil.NoSuchProcess) as cm: + try: + psutil.Process(pid) + except psutil.ZombieProcess: + raise AssertionError("wasn't supposed to raise ZombieProcess") + assert cm.value.pid == pid + assert cm.value.name is None + assert not psutil.pid_exists(pid), pid + assert pid not in psutil.pids() + assert pid not in [x.pid for x in psutil.process_iter()] + + def assertProcessGone(self, proc): + self.assertPidGone(proc.pid) + ns = process_namespace(proc) + for fun, name in ns.iter(ns.all, clear_cache=True): + with self.subTest(proc=proc, name=name): + try: + ret = fun() + except psutil.ZombieProcess: + raise + except psutil.NoSuchProcess as exc: + self._check_proc_exc(proc, exc) + else: + msg = ( + f"Process.{name}() didn't raise NSP and returned" + f" {ret!r}" + ) + raise AssertionError(msg) + proc.wait(timeout=0) # assert not raise TimeoutExpired + + def assertProcessZombie(self, proc): + # A zombie process should always be instantiable. + clone = psutil.Process(proc.pid) + # Cloned zombie on Open/NetBSD has null creation time, see: + # https://github.com/giampaolo/psutil/issues/2287 + assert proc == clone + if not (OPENBSD or NETBSD): + assert hash(proc) == hash(clone) + # Its status always be querable. + assert proc.status() == psutil.STATUS_ZOMBIE + # It should be considered 'running'. + assert proc.is_running() + assert psutil.pid_exists(proc.pid) + # as_dict() shouldn't crash. + proc.as_dict() + # It should show up in pids() and process_iter(). + assert proc.pid in psutil.pids() + assert proc.pid in [x.pid for x in psutil.process_iter()] + psutil._pmap = {} + assert proc.pid in [x.pid for x in psutil.process_iter()] + # Call all methods. + ns = process_namespace(proc) + for fun, name in ns.iter(ns.all, clear_cache=True): + with self.subTest(proc=proc, name=name): + try: + fun() + except (psutil.ZombieProcess, psutil.AccessDenied) as exc: + self._check_proc_exc(proc, exc) + if LINUX: + # https://github.com/giampaolo/psutil/pull/2288 + with pytest.raises(psutil.ZombieProcess) as cm: + proc.cmdline() + self._check_proc_exc(proc, cm.value) + with pytest.raises(psutil.ZombieProcess) as cm: + proc.exe() + self._check_proc_exc(proc, cm.value) + with pytest.raises(psutil.ZombieProcess) as cm: + proc.memory_maps() + self._check_proc_exc(proc, cm.value) + # Zombie cannot be signaled or terminated. + proc.suspend() + proc.resume() + proc.terminate() + proc.kill() + assert proc.is_running() + assert psutil.pid_exists(proc.pid) + assert proc.pid in psutil.pids() + assert proc.pid in [x.pid for x in psutil.process_iter()] + psutil._pmap = {} + assert proc.pid in [x.pid for x in psutil.process_iter()] + + # Its parent should 'see' it (edit: not true on BSD and MACOS). + # descendants = [x.pid for x in psutil.Process().children( + # recursive=True)] + # self.assertIn(proc.pid, descendants) + + # __eq__ can't be relied upon because creation time may not be + # querable. + # self.assertEqual(proc, psutil.Process(proc.pid)) + + # XXX should we also assume ppid() to be usable? Note: this + # would be an important use case as the only way to get + # rid of a zombie is to kill its parent. + # self.assertEqual(proc.ppid(), os.getpid()) + + +@pytest.mark.skipif(PYPY, reason="unreliable on PYPY") +class TestMemoryLeak(PsutilTestCase): + """Test framework class for detecting function memory leaks, + typically functions implemented in C which forgot to free() memory + from the heap. It does so by checking whether the process memory + usage increased before and after calling the function many times. + + Note that this is hard (probably impossible) to do reliably, due + to how the OS handles memory, the GC and so on (memory can even + decrease!). In order to avoid false positives, in case of failure + (mem > 0) we retry the test for up to 5 times, increasing call + repetitions each time. If the memory keeps increasing then it's a + failure. + + If available (Linux, OSX, Windows), USS memory is used for comparison, + since it's supposed to be more precise, see: + https://gmpy.dev/blog/2016/real-process-memory-and-environ-in-python + If not, RSS memory is used. mallinfo() on Linux and _heapwalk() on + Windows may give even more precision, but at the moment are not + implemented. + + PyPy appears to be completely unstable for this framework, probably + because of its JIT, so tests on PYPY are skipped. + + Usage: + + class TestLeaks(psutil.tests.TestMemoryLeak): + + def test_fun(self): + self.execute(some_function) + """ + + # Configurable class attrs. + times = 200 + warmup_times = 10 + tolerance = 0 # memory + retries = 10 if CI_TESTING else 5 + verbose = True + _thisproc = psutil.Process() + _psutil_debug_orig = bool(os.getenv('PSUTIL_DEBUG')) + + @classmethod + def setUpClass(cls): + psutil._set_debug(False) # avoid spamming to stderr + + @classmethod + def tearDownClass(cls): + psutil._set_debug(cls._psutil_debug_orig) + + def _get_mem(self): + # USS is the closest thing we have to "real" memory usage and it + # should be less likely to produce false positives. + mem = self._thisproc.memory_full_info() + return getattr(mem, "uss", mem.rss) + + def _get_num_fds(self): + if POSIX: + return self._thisproc.num_fds() + else: + return self._thisproc.num_handles() + + def _log(self, msg): + if self.verbose: + print_color(msg, color="yellow", file=sys.stderr) + + def _check_fds(self, fun): + """Makes sure num_fds() (POSIX) or num_handles() (Windows) does + not increase after calling a function. Used to discover forgotten + close(2) and CloseHandle syscalls. + """ + before = self._get_num_fds() + self.call(fun) + after = self._get_num_fds() + diff = after - before + if diff < 0: + msg = ( + f"negative diff {diff!r} (gc probably collected a" + " resource from a previous test)" + ) + raise self.fail(msg) + if diff > 0: + type_ = "fd" if POSIX else "handle" + if diff > 1: + type_ += "s" + msg = f"{diff} unclosed {type_} after calling {fun!r}" + raise self.fail(msg) + + def _call_ntimes(self, fun, times): + """Get 2 distinct memory samples, before and after having + called fun repeatedly, and return the memory difference. + """ + gc.collect(generation=1) + mem1 = self._get_mem() + for x in range(times): + ret = self.call(fun) + del x, ret + gc.collect(generation=1) + mem2 = self._get_mem() + assert gc.garbage == [] + diff = mem2 - mem1 # can also be negative + return diff + + def _check_mem(self, fun, times, retries, tolerance): + messages = [] + prev_mem = 0 + increase = times + for idx in range(1, retries + 1): + mem = self._call_ntimes(fun, times) + msg = "Run #{}: extra-mem={}, per-call={}, calls={}".format( + idx, + bytes2human(mem), + bytes2human(mem / times), + times, + ) + messages.append(msg) + success = mem <= tolerance or mem <= prev_mem + if success: + if idx > 1: + self._log(msg) + return + else: + if idx == 1: + print() # noqa: T201 + self._log(msg) + times += increase + prev_mem = mem + raise self.fail(". ".join(messages)) + + # --- + + def call(self, fun): + return fun() + + def execute( + self, fun, times=None, warmup_times=None, retries=None, tolerance=None + ): + """Test a callable.""" + times = times if times is not None else self.times + warmup_times = ( + warmup_times if warmup_times is not None else self.warmup_times + ) + retries = retries if retries is not None else self.retries + tolerance = tolerance if tolerance is not None else self.tolerance + try: + assert times >= 1, "times must be >= 1" + assert warmup_times >= 0, "warmup_times must be >= 0" + assert retries >= 0, "retries must be >= 0" + assert tolerance >= 0, "tolerance must be >= 0" + except AssertionError as err: + raise ValueError(str(err)) + + self._call_ntimes(fun, warmup_times) # warm up + self._check_fds(fun) + self._check_mem(fun, times=times, retries=retries, tolerance=tolerance) + + def execute_w_exc(self, exc, fun, **kwargs): + """Convenience method to test a callable while making sure it + raises an exception on every call. + """ + + def call(): + self.assertRaises(exc, fun) + + self.execute(call, **kwargs) + + +def print_sysinfo(): + import collections + import datetime + import getpass + import locale + import pprint + + try: + import pip + except ImportError: + pip = None + try: + import wheel + except ImportError: + wheel = None + + info = collections.OrderedDict() + + # OS + if psutil.LINUX and shutil.which("lsb_release"): + info['OS'] = sh('lsb_release -d -s') + elif psutil.OSX: + info['OS'] = f"Darwin {platform.mac_ver()[0]}" + elif psutil.WINDOWS: + info['OS'] = "Windows " + ' '.join(map(str, platform.win32_ver())) + if hasattr(platform, 'win32_edition'): + info['OS'] += ", " + platform.win32_edition() + else: + info['OS'] = f"{platform.system()} {platform.version()}" + info['arch'] = ', '.join( + list(platform.architecture()) + [platform.machine()] + ) + if psutil.POSIX: + info['kernel'] = platform.uname()[2] + + # python + info['python'] = ', '.join([ + platform.python_implementation(), + platform.python_version(), + platform.python_compiler(), + ]) + info['pip'] = getattr(pip, '__version__', 'not installed') + if wheel is not None: + info['pip'] += f" (wheel={wheel.__version__})" + + # UNIX + if psutil.POSIX: + if shutil.which("gcc"): + out = sh(['gcc', '--version']) + info['gcc'] = str(out).split('\n')[0] + else: + info['gcc'] = 'not installed' + s = platform.libc_ver()[1] + if s: + info['glibc'] = s + + # system + info['fs-encoding'] = sys.getfilesystemencoding() + lang = locale.getlocale() + info['lang'] = f"{lang[0]}, {lang[1]}" + info['boot-time'] = datetime.datetime.fromtimestamp( + psutil.boot_time() + ).strftime("%Y-%m-%d %H:%M:%S") + info['time'] = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S") + info['user'] = getpass.getuser() + info['home'] = os.path.expanduser("~") + info['cwd'] = os.getcwd() + info['pyexe'] = PYTHON_EXE + info['hostname'] = platform.node() + info['PID'] = os.getpid() + + # metrics + info['cpus'] = psutil.cpu_count() + info['loadavg'] = "{:.1f}%, {:.1f}%, {:.1f}%".format( + *tuple(x / psutil.cpu_count() * 100 for x in psutil.getloadavg()) + ) + mem = psutil.virtual_memory() + info['memory'] = "{}%%, used={}, total={}".format( + int(mem.percent), + bytes2human(mem.used), + bytes2human(mem.total), + ) + swap = psutil.swap_memory() + info['swap'] = "{}%%, used={}, total={}".format( + int(swap.percent), + bytes2human(swap.used), + bytes2human(swap.total), + ) + info['pids'] = len(psutil.pids()) + pinfo = psutil.Process().as_dict() + pinfo.pop('memory_maps', None) + info['proc'] = pprint.pformat(pinfo) + + print("=" * 70, file=sys.stderr) # noqa: T201 + for k, v in info.items(): + print("{:<17} {}".format(k + ":", v), file=sys.stderr) # noqa: T201 + print("=" * 70, file=sys.stderr) # noqa: T201 + sys.stdout.flush() + + # if WINDOWS: + # os.system("tasklist") + # elif shutil.which("ps"): + # os.system("ps aux") + # print("=" * 70, file=sys.stderr) + + sys.stdout.flush() + + +def is_win_secure_system_proc(pid): + # see: https://github.com/giampaolo/psutil/issues/2338 + @memoize + def get_procs(): + ret = {} + out = sh("tasklist.exe /NH /FO csv") + for line in out.splitlines()[1:]: + bits = [x.replace('"', "") for x in line.split(",")] + name, pid = bits[0], int(bits[1]) + ret[pid] = name + return ret + + try: + return get_procs()[pid] == "Secure System" + except KeyError: + return False + + +def _get_eligible_cpu(): + p = psutil.Process() + if hasattr(p, "cpu_num"): + return p.cpu_num() + elif hasattr(p, "cpu_affinity"): + return random.choice(p.cpu_affinity()) + return 0 + + +class process_namespace: + """A container that lists all Process class method names + some + reasonable parameters to be called with. Utility methods (parent(), + children(), ...) are excluded. + + >>> ns = process_namespace(psutil.Process()) + >>> for fun, name in ns.iter(ns.getters): + ... fun() + """ + + utils = [('cpu_percent', (), {}), ('memory_percent', (), {})] + + ignored = [ + ('as_dict', (), {}), + ('children', (), {'recursive': True}), + ('connections', (), {}), # deprecated + ('is_running', (), {}), + ('oneshot', (), {}), + ('parent', (), {}), + ('parents', (), {}), + ('pid', (), {}), + ('wait', (0,), {}), + ] + + getters = [ + ('cmdline', (), {}), + ('cpu_times', (), {}), + ('create_time', (), {}), + ('cwd', (), {}), + ('exe', (), {}), + ('memory_full_info', (), {}), + ('memory_info', (), {}), + ('name', (), {}), + ('net_connections', (), {'kind': 'all'}), + ('nice', (), {}), + ('num_ctx_switches', (), {}), + ('num_threads', (), {}), + ('open_files', (), {}), + ('ppid', (), {}), + ('status', (), {}), + ('threads', (), {}), + ('username', (), {}), + ] + if POSIX: + getters += [('uids', (), {})] + getters += [('gids', (), {})] + getters += [('terminal', (), {})] + getters += [('num_fds', (), {})] + if HAS_PROC_IO_COUNTERS: + getters += [('io_counters', (), {})] + if HAS_IONICE: + getters += [('ionice', (), {})] + if HAS_RLIMIT: + getters += [('rlimit', (psutil.RLIMIT_NOFILE,), {})] + if HAS_CPU_AFFINITY: + getters += [('cpu_affinity', (), {})] + if HAS_PROC_CPU_NUM: + getters += [('cpu_num', (), {})] + if HAS_ENVIRON: + getters += [('environ', (), {})] + if WINDOWS: + getters += [('num_handles', (), {})] + if HAS_MEMORY_MAPS: + getters += [('memory_maps', (), {'grouped': False})] + + setters = [] + if POSIX: + setters += [('nice', (0,), {})] + else: + setters += [('nice', (psutil.NORMAL_PRIORITY_CLASS,), {})] + if HAS_RLIMIT: + setters += [('rlimit', (psutil.RLIMIT_NOFILE, (1024, 4096)), {})] + if HAS_IONICE: + if LINUX: + setters += [('ionice', (psutil.IOPRIO_CLASS_NONE, 0), {})] + else: + setters += [('ionice', (psutil.IOPRIO_NORMAL,), {})] + if HAS_CPU_AFFINITY: + setters += [('cpu_affinity', ([_get_eligible_cpu()],), {})] + + killers = [ + ('send_signal', (signal.SIGTERM,), {}), + ('suspend', (), {}), + ('resume', (), {}), + ('terminate', (), {}), + ('kill', (), {}), + ] + if WINDOWS: + killers += [('send_signal', (signal.CTRL_C_EVENT,), {})] + killers += [('send_signal', (signal.CTRL_BREAK_EVENT,), {})] + + all = utils + getters + setters + killers + + def __init__(self, proc): + self._proc = proc + + def iter(self, ls, clear_cache=True): + """Given a list of tuples yields a set of (fun, fun_name) tuples + in random order. + """ + ls = list(ls) + random.shuffle(ls) + for fun_name, args, kwds in ls: + if clear_cache: + self.clear_cache() + fun = getattr(self._proc, fun_name) + fun = functools.partial(fun, *args, **kwds) + yield (fun, fun_name) + + def clear_cache(self): + """Clear the cache of a Process instance.""" + self._proc._init(self._proc.pid, _ignore_nsp=True) + + @classmethod + def test_class_coverage(cls, test_class, ls): + """Given a TestCase instance and a list of tuples checks that + the class defines the required test method names. + """ + for fun_name, _, _ in ls: + meth_name = 'test_' + fun_name + if not hasattr(test_class, meth_name): + msg = ( + f"{test_class.__class__.__name__!r} class should define a" + f" {meth_name!r} method" + ) + raise AttributeError(msg) + + @classmethod + def test(cls): + this = {x[0] for x in cls.all} + ignored = {x[0] for x in cls.ignored} + klass = {x for x in dir(psutil.Process) if x[0] != '_'} + leftout = (this | ignored) ^ klass + if leftout: + raise ValueError(f"uncovered Process class names: {leftout!r}") + + +class system_namespace: + """A container that lists all the module-level, system-related APIs. + Utilities such as cpu_percent() are excluded. Usage: + + >>> ns = system_namespace + >>> for fun, name in ns.iter(ns.getters): + ... fun() + """ + + getters = [ + ('boot_time', (), {}), + ('cpu_count', (), {'logical': False}), + ('cpu_count', (), {'logical': True}), + ('cpu_stats', (), {}), + ('cpu_times', (), {'percpu': False}), + ('cpu_times', (), {'percpu': True}), + ('disk_io_counters', (), {'perdisk': True}), + ('disk_partitions', (), {'all': True}), + ('disk_usage', (os.getcwd(),), {}), + ('net_connections', (), {'kind': 'all'}), + ('net_if_addrs', (), {}), + ('net_if_stats', (), {}), + ('net_io_counters', (), {'pernic': True}), + ('pid_exists', (os.getpid(),), {}), + ('pids', (), {}), + ('swap_memory', (), {}), + ('users', (), {}), + ('virtual_memory', (), {}), + ] + if HAS_CPU_FREQ: + if MACOS and platform.machine() == 'arm64': # skipped due to #1892 + pass + else: + getters += [('cpu_freq', (), {'percpu': True})] + if HAS_GETLOADAVG: + getters += [('getloadavg', (), {})] + if HAS_SENSORS_TEMPERATURES: + getters += [('sensors_temperatures', (), {})] + if HAS_SENSORS_FANS: + getters += [('sensors_fans', (), {})] + if HAS_SENSORS_BATTERY: + getters += [('sensors_battery', (), {})] + if WINDOWS: + getters += [('win_service_iter', (), {})] + getters += [('win_service_get', ('alg',), {})] + + ignored = [ + ('process_iter', (), {}), + ('wait_procs', ([psutil.Process()],), {}), + ('cpu_percent', (), {}), + ('cpu_times_percent', (), {}), + ] + + all = getters + + @staticmethod + def iter(ls): + """Given a list of tuples yields a set of (fun, fun_name) tuples + in random order. + """ + ls = list(ls) + random.shuffle(ls) + for fun_name, args, kwds in ls: + fun = getattr(psutil, fun_name) + fun = functools.partial(fun, *args, **kwds) + yield (fun, fun_name) + + test_class_coverage = process_namespace.test_class_coverage + + +def retry_on_failure(retries=NO_RETRIES): + """Decorator which runs a test function and retries N times before + actually failing. + """ + + def logfun(exc): + print(f"{exc!r}, retrying", file=sys.stderr) # noqa: T201 + + return retry( + exception=AssertionError, timeout=None, retries=retries, logfun=logfun + ) + + +def skip_on_access_denied(only_if=None): + """Decorator to Ignore AccessDenied exceptions.""" + + def decorator(fun): + @functools.wraps(fun) + def wrapper(*args, **kwargs): + try: + return fun(*args, **kwargs) + except psutil.AccessDenied: + if only_if is not None: + if not only_if: + raise + raise pytest.skip("raises AccessDenied") + + return wrapper + + return decorator + + +def skip_on_not_implemented(only_if=None): + """Decorator to Ignore NotImplementedError exceptions.""" + + def decorator(fun): + @functools.wraps(fun) + def wrapper(*args, **kwargs): + try: + return fun(*args, **kwargs) + except NotImplementedError: + if only_if is not None: + if not only_if: + raise + msg = ( + f"{fun.__name__!r} was skipped because it raised" + " NotImplementedError" + ) + raise pytest.skip(msg) + + return wrapper + + return decorator + + +# =================================================================== +# --- network +# =================================================================== + + +# XXX: no longer used +def get_free_port(host='127.0.0.1'): + """Return an unused TCP port. Subject to race conditions.""" + with socket.socket() as sock: + sock.bind((host, 0)) + return sock.getsockname()[1] + + +def bind_socket(family=AF_INET, type=SOCK_STREAM, addr=None): + """Binds a generic socket.""" + if addr is None and family in {AF_INET, AF_INET6}: + addr = ("", 0) + sock = socket.socket(family, type) + try: + if os.name not in {'nt', 'cygwin'}: + sock.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1) + sock.bind(addr) + if type == socket.SOCK_STREAM: + sock.listen(5) + return sock + except Exception: + sock.close() + raise + + +def bind_unix_socket(name, type=socket.SOCK_STREAM): + """Bind a UNIX socket.""" + assert psutil.POSIX + assert not os.path.exists(name), name + sock = socket.socket(socket.AF_UNIX, type) + try: + sock.bind(name) + if type == socket.SOCK_STREAM: + sock.listen(5) + except Exception: + sock.close() + raise + return sock + + +def tcp_socketpair(family, addr=("", 0)): + """Build a pair of TCP sockets connected to each other. + Return a (server, client) tuple. + """ + with socket.socket(family, SOCK_STREAM) as ll: + ll.bind(addr) + ll.listen(5) + addr = ll.getsockname() + c = socket.socket(family, SOCK_STREAM) + try: + c.connect(addr) + caddr = c.getsockname() + while True: + a, addr = ll.accept() + # check that we've got the correct client + if addr == caddr: + return (a, c) + a.close() + except OSError: + c.close() + raise + + +def unix_socketpair(name): + """Build a pair of UNIX sockets connected to each other through + the same UNIX file name. + Return a (server, client) tuple. + """ + assert psutil.POSIX + server = client = None + try: + server = bind_unix_socket(name, type=socket.SOCK_STREAM) + server.setblocking(0) + client = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + client.setblocking(0) + client.connect(name) + # new = server.accept() + except Exception: + if server is not None: + server.close() + if client is not None: + client.close() + raise + return (server, client) + + +@contextlib.contextmanager +def create_sockets(): + """Open as many socket families / types as possible.""" + socks = [] + fname1 = fname2 = None + try: + socks.extend(( + bind_socket(socket.AF_INET, socket.SOCK_STREAM), + bind_socket(socket.AF_INET, socket.SOCK_DGRAM), + )) + if supports_ipv6(): + socks.extend(( + bind_socket(socket.AF_INET6, socket.SOCK_STREAM), + bind_socket(socket.AF_INET6, socket.SOCK_DGRAM), + )) + if POSIX and HAS_NET_CONNECTIONS_UNIX: + fname1 = get_testfn() + fname2 = get_testfn() + s1, s2 = unix_socketpair(fname1) + s3 = bind_unix_socket(fname2, type=socket.SOCK_DGRAM) + for s in (s1, s2, s3): + socks.append(s) + yield socks + finally: + for s in socks: + s.close() + for fname in (fname1, fname2): + if fname is not None: + safe_rmpath(fname) + + +def check_net_address(addr, family): + """Check a net address validity. Supported families are IPv4, + IPv6 and MAC addresses. + """ + assert isinstance(family, enum.IntEnum), family + if family == socket.AF_INET: + octs = [int(x) for x in addr.split('.')] + assert len(octs) == 4, addr + for num in octs: + assert 0 <= num <= 255, addr + ipaddress.IPv4Address(addr) + elif family == socket.AF_INET6: + assert isinstance(addr, str), addr + ipaddress.IPv6Address(addr) + elif family == psutil.AF_LINK: + assert re.match(r'([a-fA-F0-9]{2}[:|\-]?){6}', addr) is not None, addr + else: + raise ValueError(f"unknown family {family!r}") + + +def check_connection_ntuple(conn): + """Check validity of a connection namedtuple.""" + + def check_ntuple(conn): + has_pid = len(conn) == 7 + assert len(conn) in {6, 7}, len(conn) + assert conn[0] == conn.fd, conn.fd + assert conn[1] == conn.family, conn.family + assert conn[2] == conn.type, conn.type + assert conn[3] == conn.laddr, conn.laddr + assert conn[4] == conn.raddr, conn.raddr + assert conn[5] == conn.status, conn.status + if has_pid: + assert conn[6] == conn.pid, conn.pid + + def check_family(conn): + assert conn.family in {AF_INET, AF_INET6, AF_UNIX}, conn.family + assert isinstance(conn.family, enum.IntEnum), conn + if conn.family == AF_INET: + # actually try to bind the local socket; ignore IPv6 + # sockets as their address might be represented as + # an IPv4-mapped-address (e.g. "::127.0.0.1") + # and that's rejected by bind() + with socket.socket(conn.family, conn.type) as s: + try: + s.bind((conn.laddr[0], 0)) + except OSError as err: + if err.errno != errno.EADDRNOTAVAIL: + raise + elif conn.family == AF_UNIX: + assert conn.status == psutil.CONN_NONE, conn.status + + def check_type(conn): + # SOCK_SEQPACKET may happen in case of AF_UNIX socks + SOCK_SEQPACKET = getattr(socket, "SOCK_SEQPACKET", object()) + assert conn.type in { + socket.SOCK_STREAM, + socket.SOCK_DGRAM, + SOCK_SEQPACKET, + }, conn.type + assert isinstance(conn.type, enum.IntEnum), conn + if conn.type == socket.SOCK_DGRAM: + assert conn.status == psutil.CONN_NONE, conn.status + + def check_addrs(conn): + # check IP address and port sanity + for addr in (conn.laddr, conn.raddr): + if conn.family in {AF_INET, AF_INET6}: + assert isinstance(addr, tuple), type(addr) + if not addr: + continue + assert isinstance(addr.port, int), type(addr.port) + assert 0 <= addr.port <= 65535, addr.port + check_net_address(addr.ip, conn.family) + elif conn.family == AF_UNIX: + assert isinstance(addr, str), type(addr) + + def check_status(conn): + assert isinstance(conn.status, str), conn.status + valids = [ + getattr(psutil, x) for x in dir(psutil) if x.startswith('CONN_') + ] + assert conn.status in valids, conn.status + if conn.family in {AF_INET, AF_INET6} and conn.type == SOCK_STREAM: + assert conn.status != psutil.CONN_NONE, conn.status + else: + assert conn.status == psutil.CONN_NONE, conn.status + + check_ntuple(conn) + check_family(conn) + check_type(conn) + check_addrs(conn) + check_status(conn) + + +def filter_proc_net_connections(cons): + """Our process may start with some open UNIX sockets which are not + initialized by us, invalidating unit tests. + """ + new = [] + for conn in cons: + if POSIX and conn.family == socket.AF_UNIX: + if MACOS and "/syslog" in conn.raddr: + debug(f"skipping {conn}") + continue + new.append(conn) + return new + + +# =================================================================== +# --- import utils +# =================================================================== + + +def reload_module(module): + return importlib.reload(module) + + +def import_module_by_path(path): + name = os.path.splitext(os.path.basename(path))[0] + spec = importlib.util.spec_from_file_location(name, path) + mod = importlib.util.module_from_spec(spec) + spec.loader.exec_module(mod) + return mod + + +# =================================================================== +# --- others +# =================================================================== + + +def warn(msg): + """Raise a warning msg.""" + warnings.warn(msg, UserWarning, stacklevel=2) + + +def is_namedtuple(x): + """Check if object is an instance of namedtuple.""" + t = type(x) + b = t.__bases__ + if len(b) != 1 or b[0] is not tuple: + return False + f = getattr(t, '_fields', None) + if not isinstance(f, tuple): + return False + return all(isinstance(n, str) for n in f) + + +if POSIX: + + @contextlib.contextmanager + def copyload_shared_lib(suffix=""): + """Ctx manager which picks up a random shared CO lib used + by this process, copies it in another location and loads it + in memory via ctypes. Return the new absolutized path. + """ + exe = 'pypy' if PYPY else 'python' + ext = ".so" + dst = get_testfn(suffix=suffix + ext) + libs = [ + x.path + for x in psutil.Process().memory_maps() + if os.path.splitext(x.path)[1] == ext and exe in x.path.lower() + ] + src = random.choice(libs) + shutil.copyfile(src, dst) + try: + ctypes.CDLL(dst) + yield dst + finally: + safe_rmpath(dst) + +else: + + @contextlib.contextmanager + def copyload_shared_lib(suffix=""): + """Ctx manager which picks up a random shared DLL lib used + by this process, copies it in another location and loads it + in memory via ctypes. + Return the new absolutized, normcased path. + """ + from ctypes import WinError + from ctypes import wintypes + + ext = ".dll" + dst = get_testfn(suffix=suffix + ext) + libs = [ + x.path + for x in psutil.Process().memory_maps() + if x.path.lower().endswith(ext) + and 'python' in os.path.basename(x.path).lower() + and 'wow64' not in x.path.lower() + ] + if PYPY and not libs: + libs = [ + x.path + for x in psutil.Process().memory_maps() + if 'pypy' in os.path.basename(x.path).lower() + ] + src = random.choice(libs) + shutil.copyfile(src, dst) + cfile = None + try: + cfile = ctypes.WinDLL(dst) + yield dst + finally: + # Work around OverflowError: + # - https://ci.appveyor.com/project/giampaolo/psutil/build/1207/ + # job/o53330pbnri9bcw7 + # - http://bugs.python.org/issue30286 + # - http://stackoverflow.com/questions/23522055 + if cfile is not None: + FreeLibrary = ctypes.windll.kernel32.FreeLibrary + FreeLibrary.argtypes = [wintypes.HMODULE] + ret = FreeLibrary(cfile._handle) + if ret == 0: + raise WinError() + safe_rmpath(dst) + + +# =================================================================== +# --- Exit funs (first is executed last) +# =================================================================== + + +# this is executed first +@atexit.register +def cleanup_test_procs(): + reap_children(recursive=True) + + +# atexit module does not execute exit functions in case of SIGTERM, which +# gets sent to test subprocesses, which is a problem if they import this +# module. With this it will. See: +# https://gmpy.dev/blog/2016/how-to-always-execute-exit-functions-in-python +if POSIX: + signal.signal(signal.SIGTERM, lambda sig, _: sys.exit(sig)) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__main__.py b/llmlab/lib/python3.12/site-packages/psutil/tests/__main__.py new file mode 100644 index 0000000..ce6fc24 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/__main__.py @@ -0,0 +1,12 @@ +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Run unit tests. This is invoked by: +$ python -m psutil.tests. +""" + +from psutil.tests import pytest + + +pytest.main(["-v", "-s", "--tb=short"]) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000..39481f5 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/__main__.cpython-312.pyc new file mode 100644 index 0000000..f0e6909 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/__main__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_aix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_aix.cpython-312.pyc new file mode 100644 index 0000000..64d080b Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_aix.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_bsd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_bsd.cpython-312.pyc new file mode 100644 index 0000000..a3a466a Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_bsd.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_connections.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_connections.cpython-312.pyc new file mode 100644 index 0000000..90a0edd Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_connections.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_contracts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_contracts.cpython-312.pyc new file mode 100644 index 0000000..5285208 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_contracts.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_linux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_linux.cpython-312.pyc new file mode 100644 index 0000000..6bf1993 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_linux.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_memleaks.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_memleaks.cpython-312.pyc new file mode 100644 index 0000000..162a868 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_memleaks.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_misc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_misc.cpython-312.pyc new file mode 100644 index 0000000..330d922 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_misc.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_osx.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_osx.cpython-312.pyc new file mode 100644 index 0000000..f20bcd1 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_osx.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_posix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_posix.cpython-312.pyc new file mode 100644 index 0000000..4229745 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_posix.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_process.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_process.cpython-312.pyc new file mode 100644 index 0000000..1046515 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_process.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_process_all.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_process_all.cpython-312.pyc new file mode 100644 index 0000000..8c38464 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_process_all.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_scripts.cpython-312.pyc new file mode 100644 index 0000000..ea7342f Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_scripts.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_sunos.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_sunos.cpython-312.pyc new file mode 100644 index 0000000..f0e6ceb Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_sunos.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_system.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_system.cpython-312.pyc new file mode 100644 index 0000000..72fc790 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_system.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_testutils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_testutils.cpython-312.pyc new file mode 100644 index 0000000..d0477cb Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_testutils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_unicode.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_unicode.cpython-312.pyc new file mode 100644 index 0000000..a821ab6 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_unicode.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_windows.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_windows.cpython-312.pyc new file mode 100644 index 0000000..43ddd22 Binary files /dev/null and b/llmlab/lib/python3.12/site-packages/psutil/tests/__pycache__/test_windows.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_aix.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_aix.py new file mode 100644 index 0000000..10934c1 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_aix.py @@ -0,0 +1,142 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola' +# Copyright (c) 2017, Arnon Yaari +# All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""AIX specific tests.""" + +import re + +import psutil +from psutil import AIX +from psutil.tests import PsutilTestCase +from psutil.tests import pytest +from psutil.tests import sh + + +@pytest.mark.skipif(not AIX, reason="AIX only") +class AIXSpecificTestCase(PsutilTestCase): + def test_virtual_memory(self): + out = sh('/usr/bin/svmon -O unit=KB') + re_pattern = r"memory\s*" + for field in [ + "size", + "inuse", + "free", + "pin", + "virtual", + "available", + "mmode", + ]: + re_pattern += rf"(?P<{field}>\S+)\s+" + matchobj = re.search(re_pattern, out) + + assert matchobj is not None + + KB = 1024 + total = int(matchobj.group("size")) * KB + available = int(matchobj.group("available")) * KB + used = int(matchobj.group("inuse")) * KB + free = int(matchobj.group("free")) * KB + + psutil_result = psutil.virtual_memory() + + # TOLERANCE_SYS_MEM from psutil.tests is not enough. For some reason + # we're seeing differences of ~1.2 MB. 2 MB is still a good tolerance + # when compared to GBs. + TOLERANCE_SYS_MEM = 2 * KB * KB # 2 MB + assert psutil_result.total == total + assert abs(psutil_result.used - used) < TOLERANCE_SYS_MEM + assert abs(psutil_result.available - available) < TOLERANCE_SYS_MEM + assert abs(psutil_result.free - free) < TOLERANCE_SYS_MEM + + def test_swap_memory(self): + out = sh('/usr/sbin/lsps -a') + # From the man page, "The size is given in megabytes" so we assume + # we'll always have 'MB' in the result + # TODO maybe try to use "swap -l" to check "used" too, but its units + # are not guaranteed to be "MB" so parsing may not be consistent + matchobj = re.search( + r"(?P\S+)\s+" + r"(?P\S+)\s+" + r"(?P\S+)\s+" + r"(?P\d+)MB", + out, + ) + + assert matchobj is not None + + total_mb = int(matchobj.group("size")) + MB = 1024**2 + psutil_result = psutil.swap_memory() + # we divide our result by MB instead of multiplying the lsps value by + # MB because lsps may round down, so we round down too + assert int(psutil_result.total / MB) == total_mb + + def test_cpu_stats(self): + out = sh('/usr/bin/mpstat -a') + + re_pattern = r"ALL\s*" + for field in [ + "min", + "maj", + "mpcs", + "mpcr", + "dev", + "soft", + "dec", + "ph", + "cs", + "ics", + "bound", + "rq", + "push", + "S3pull", + "S3grd", + "S0rd", + "S1rd", + "S2rd", + "S3rd", + "S4rd", + "S5rd", + "sysc", + ]: + re_pattern += rf"(?P<{field}>\S+)\s+" + matchobj = re.search(re_pattern, out) + + assert matchobj is not None + + # numbers are usually in the millions so 1000 is ok for tolerance + CPU_STATS_TOLERANCE = 1000 + psutil_result = psutil.cpu_stats() + assert ( + abs(psutil_result.ctx_switches - int(matchobj.group("cs"))) + < CPU_STATS_TOLERANCE + ) + assert ( + abs(psutil_result.syscalls - int(matchobj.group("sysc"))) + < CPU_STATS_TOLERANCE + ) + assert ( + abs(psutil_result.interrupts - int(matchobj.group("dev"))) + < CPU_STATS_TOLERANCE + ) + assert ( + abs(psutil_result.soft_interrupts - int(matchobj.group("soft"))) + < CPU_STATS_TOLERANCE + ) + + def test_cpu_count_logical(self): + out = sh('/usr/bin/mpstat -a') + mpstat_lcpu = int(re.search(r"lcpu=(\d+)", out).group(1)) + psutil_lcpu = psutil.cpu_count(logical=True) + assert mpstat_lcpu == psutil_lcpu + + def test_net_if_addrs_names(self): + out = sh('/etc/ifconfig -l') + ifconfig_names = set(out.split()) + psutil_names = set(psutil.net_if_addrs().keys()) + assert ifconfig_names == psutil_names diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_bsd.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_bsd.py new file mode 100644 index 0000000..2786c34 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_bsd.py @@ -0,0 +1,593 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +# TODO: (FreeBSD) add test for comparing connections with 'sockstat' cmd. + + +"""Tests specific to all BSD platforms.""" + +import datetime +import os +import re +import shutil +import time + +import psutil +from psutil import BSD +from psutil import FREEBSD +from psutil import NETBSD +from psutil import OPENBSD +from psutil.tests import HAS_BATTERY +from psutil.tests import TOLERANCE_SYS_MEM +from psutil.tests import PsutilTestCase +from psutil.tests import pytest +from psutil.tests import retry_on_failure +from psutil.tests import sh +from psutil.tests import spawn_testproc +from psutil.tests import terminate + + +if BSD: + from psutil._psutil_posix import getpagesize + + PAGESIZE = getpagesize() + # muse requires root privileges + MUSE_AVAILABLE = os.getuid() == 0 and shutil.which("muse") +else: + PAGESIZE = None + MUSE_AVAILABLE = False + + +def sysctl(cmdline): + """Expects a sysctl command with an argument and parse the result + returning only the value of interest. + """ + result = sh("sysctl " + cmdline) + if FREEBSD: + result = result[result.find(": ") + 2 :] + elif OPENBSD or NETBSD: + result = result[result.find("=") + 1 :] + try: + return int(result) + except ValueError: + return result + + +def muse(field): + """Thin wrapper around 'muse' cmdline utility.""" + out = sh('muse') + for line in out.split('\n'): + if line.startswith(field): + break + else: + raise ValueError("line not found") + return int(line.split()[1]) + + +# ===================================================================== +# --- All BSD* +# ===================================================================== + + +@pytest.mark.skipif(not BSD, reason="BSD only") +class BSDTestCase(PsutilTestCase): + """Generic tests common to all BSD variants.""" + + @classmethod + def setUpClass(cls): + cls.pid = spawn_testproc().pid + + @classmethod + def tearDownClass(cls): + terminate(cls.pid) + + @pytest.mark.skipif(NETBSD, reason="-o lstart doesn't work on NETBSD") + def test_process_create_time(self): + output = sh(f"ps -o lstart -p {self.pid}") + start_ps = output.replace('STARTED', '').strip() + start_psutil = psutil.Process(self.pid).create_time() + start_psutil = time.strftime( + "%a %b %e %H:%M:%S %Y", time.localtime(start_psutil) + ) + assert start_ps == start_psutil + + def test_disks(self): + # test psutil.disk_usage() and psutil.disk_partitions() + # against "df -a" + def df(path): + out = sh(f'df -k "{path}"').strip() + lines = out.split('\n') + lines.pop(0) + line = lines.pop(0) + dev, total, used, free = line.split()[:4] + if dev == 'none': + dev = '' + total = int(total) * 1024 + used = int(used) * 1024 + free = int(free) * 1024 + return dev, total, used, free + + for part in psutil.disk_partitions(all=False): + usage = psutil.disk_usage(part.mountpoint) + dev, total, used, free = df(part.mountpoint) + assert part.device == dev + assert usage.total == total + # 10 MB tolerance + if abs(usage.free - free) > 10 * 1024 * 1024: + raise self.fail(f"psutil={usage.free}, df={free}") + if abs(usage.used - used) > 10 * 1024 * 1024: + raise self.fail(f"psutil={usage.used}, df={used}") + + @pytest.mark.skipif( + not shutil.which("sysctl"), reason="sysctl cmd not available" + ) + def test_cpu_count_logical(self): + syst = sysctl("hw.ncpu") + assert psutil.cpu_count(logical=True) == syst + + @pytest.mark.skipif( + not shutil.which("sysctl"), reason="sysctl cmd not available" + ) + @pytest.mark.skipif( + NETBSD, reason="skipped on NETBSD" # we check /proc/meminfo + ) + def test_virtual_memory_total(self): + num = sysctl('hw.physmem') + assert num == psutil.virtual_memory().total + + @pytest.mark.skipif( + not shutil.which("ifconfig"), reason="ifconfig cmd not available" + ) + def test_net_if_stats(self): + for name, stats in psutil.net_if_stats().items(): + try: + out = sh(f"ifconfig {name}") + except RuntimeError: + pass + else: + assert stats.isup == ('RUNNING' in out) + if "mtu" in out: + assert stats.mtu == int(re.findall(r'mtu (\d+)', out)[0]) + + +# ===================================================================== +# --- FreeBSD +# ===================================================================== + + +@pytest.mark.skipif(not FREEBSD, reason="FREEBSD only") +class FreeBSDPsutilTestCase(PsutilTestCase): + @classmethod + def setUpClass(cls): + cls.pid = spawn_testproc().pid + + @classmethod + def tearDownClass(cls): + terminate(cls.pid) + + @retry_on_failure() + def test_memory_maps(self): + out = sh(f"procstat -v {self.pid}") + maps = psutil.Process(self.pid).memory_maps(grouped=False) + lines = out.split('\n')[1:] + while lines: + line = lines.pop() + fields = line.split() + _, start, stop, _perms, res = fields[:5] + map = maps.pop() + assert f"{start}-{stop}" == map.addr + assert int(res) == map.rss + if not map.path.startswith('['): + assert fields[10] == map.path + + def test_exe(self): + out = sh(f"procstat -b {self.pid}") + assert psutil.Process(self.pid).exe() == out.split('\n')[1].split()[-1] + + def test_cmdline(self): + out = sh(f"procstat -c {self.pid}") + assert ' '.join(psutil.Process(self.pid).cmdline()) == ' '.join( + out.split('\n')[1].split()[2:] + ) + + def test_uids_gids(self): + out = sh(f"procstat -s {self.pid}") + euid, ruid, suid, egid, rgid, sgid = out.split('\n')[1].split()[2:8] + p = psutil.Process(self.pid) + uids = p.uids() + gids = p.gids() + assert uids.real == int(ruid) + assert uids.effective == int(euid) + assert uids.saved == int(suid) + assert gids.real == int(rgid) + assert gids.effective == int(egid) + assert gids.saved == int(sgid) + + @retry_on_failure() + def test_ctx_switches(self): + tested = [] + out = sh(f"procstat -r {self.pid}") + p = psutil.Process(self.pid) + for line in out.split('\n'): + line = line.lower().strip() + if ' voluntary context' in line: + pstat_value = int(line.split()[-1]) + psutil_value = p.num_ctx_switches().voluntary + assert pstat_value == psutil_value + tested.append(None) + elif ' involuntary context' in line: + pstat_value = int(line.split()[-1]) + psutil_value = p.num_ctx_switches().involuntary + assert pstat_value == psutil_value + tested.append(None) + if len(tested) != 2: + raise RuntimeError("couldn't find lines match in procstat out") + + @retry_on_failure() + def test_cpu_times(self): + tested = [] + out = sh(f"procstat -r {self.pid}") + p = psutil.Process(self.pid) + for line in out.split('\n'): + line = line.lower().strip() + if 'user time' in line: + pstat_value = float('0.' + line.split()[-1].split('.')[-1]) + psutil_value = p.cpu_times().user + assert pstat_value == psutil_value + tested.append(None) + elif 'system time' in line: + pstat_value = float('0.' + line.split()[-1].split('.')[-1]) + psutil_value = p.cpu_times().system + assert pstat_value == psutil_value + tested.append(None) + if len(tested) != 2: + raise RuntimeError("couldn't find lines match in procstat out") + + +@pytest.mark.skipif(not FREEBSD, reason="FREEBSD only") +class FreeBSDSystemTestCase(PsutilTestCase): + @staticmethod + def parse_swapinfo(): + # the last line is always the total + output = sh("swapinfo -k").splitlines()[-1] + parts = re.split(r'\s+', output) + + if not parts: + raise ValueError(f"Can't parse swapinfo: {output}") + + # the size is in 1k units, so multiply by 1024 + total, used, free = (int(p) * 1024 for p in parts[1:4]) + return total, used, free + + def test_cpu_frequency_against_sysctl(self): + # Currently only cpu 0 is frequency is supported in FreeBSD + # All other cores use the same frequency. + sensor = "dev.cpu.0.freq" + try: + sysctl_result = int(sysctl(sensor)) + except RuntimeError: + raise pytest.skip("frequencies not supported by kernel") + assert psutil.cpu_freq().current == sysctl_result + + sensor = "dev.cpu.0.freq_levels" + sysctl_result = sysctl(sensor) + # sysctl returns a string of the format: + # / /... + # Ordered highest available to lowest available. + max_freq = int(sysctl_result.split()[0].split("/")[0]) + min_freq = int(sysctl_result.split()[-1].split("/")[0]) + assert psutil.cpu_freq().max == max_freq + assert psutil.cpu_freq().min == min_freq + + # --- virtual_memory(); tests against sysctl + + @retry_on_failure() + def test_vmem_active(self): + syst = sysctl("vm.stats.vm.v_active_count") * PAGESIZE + assert abs(psutil.virtual_memory().active - syst) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_inactive(self): + syst = sysctl("vm.stats.vm.v_inactive_count") * PAGESIZE + assert abs(psutil.virtual_memory().inactive - syst) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_wired(self): + syst = sysctl("vm.stats.vm.v_wire_count") * PAGESIZE + assert abs(psutil.virtual_memory().wired - syst) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_cached(self): + syst = sysctl("vm.stats.vm.v_cache_count") * PAGESIZE + assert abs(psutil.virtual_memory().cached - syst) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_free(self): + syst = sysctl("vm.stats.vm.v_free_count") * PAGESIZE + assert abs(psutil.virtual_memory().free - syst) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_buffers(self): + syst = sysctl("vfs.bufspace") + assert abs(psutil.virtual_memory().buffers - syst) < TOLERANCE_SYS_MEM + + # --- virtual_memory(); tests against muse + + @pytest.mark.skipif(not MUSE_AVAILABLE, reason="muse not installed") + def test_muse_vmem_total(self): + num = muse('Total') + assert psutil.virtual_memory().total == num + + @pytest.mark.skipif(not MUSE_AVAILABLE, reason="muse not installed") + @retry_on_failure() + def test_muse_vmem_active(self): + num = muse('Active') + assert abs(psutil.virtual_memory().active - num) < TOLERANCE_SYS_MEM + + @pytest.mark.skipif(not MUSE_AVAILABLE, reason="muse not installed") + @retry_on_failure() + def test_muse_vmem_inactive(self): + num = muse('Inactive') + assert abs(psutil.virtual_memory().inactive - num) < TOLERANCE_SYS_MEM + + @pytest.mark.skipif(not MUSE_AVAILABLE, reason="muse not installed") + @retry_on_failure() + def test_muse_vmem_wired(self): + num = muse('Wired') + assert abs(psutil.virtual_memory().wired - num) < TOLERANCE_SYS_MEM + + @pytest.mark.skipif(not MUSE_AVAILABLE, reason="muse not installed") + @retry_on_failure() + def test_muse_vmem_cached(self): + num = muse('Cache') + assert abs(psutil.virtual_memory().cached - num) < TOLERANCE_SYS_MEM + + @pytest.mark.skipif(not MUSE_AVAILABLE, reason="muse not installed") + @retry_on_failure() + def test_muse_vmem_free(self): + num = muse('Free') + assert abs(psutil.virtual_memory().free - num) < TOLERANCE_SYS_MEM + + @pytest.mark.skipif(not MUSE_AVAILABLE, reason="muse not installed") + @retry_on_failure() + def test_muse_vmem_buffers(self): + num = muse('Buffer') + assert abs(psutil.virtual_memory().buffers - num) < TOLERANCE_SYS_MEM + + def test_cpu_stats_ctx_switches(self): + assert ( + abs( + psutil.cpu_stats().ctx_switches + - sysctl('vm.stats.sys.v_swtch') + ) + < 1000 + ) + + def test_cpu_stats_interrupts(self): + assert ( + abs(psutil.cpu_stats().interrupts - sysctl('vm.stats.sys.v_intr')) + < 1000 + ) + + def test_cpu_stats_soft_interrupts(self): + assert ( + abs( + psutil.cpu_stats().soft_interrupts + - sysctl('vm.stats.sys.v_soft') + ) + < 1000 + ) + + @retry_on_failure() + def test_cpu_stats_syscalls(self): + # pretty high tolerance but it looks like it's OK. + assert ( + abs(psutil.cpu_stats().syscalls - sysctl('vm.stats.sys.v_syscall')) + < 200000 + ) + + # def test_cpu_stats_traps(self): + # self.assertAlmostEqual(psutil.cpu_stats().traps, + # sysctl('vm.stats.sys.v_trap'), delta=1000) + + # --- swap memory + + def test_swapmem_free(self): + _total, _used, free = self.parse_swapinfo() + assert abs(psutil.swap_memory().free - free) < TOLERANCE_SYS_MEM + + def test_swapmem_used(self): + _total, used, _free = self.parse_swapinfo() + assert abs(psutil.swap_memory().used - used) < TOLERANCE_SYS_MEM + + def test_swapmem_total(self): + total, _used, _free = self.parse_swapinfo() + assert abs(psutil.swap_memory().total - total) < TOLERANCE_SYS_MEM + + # --- others + + def test_boot_time(self): + s = sysctl('sysctl kern.boottime') + s = s[s.find(" sec = ") + 7 :] + s = s[: s.find(',')] + btime = int(s) + assert btime == psutil.boot_time() + + # --- sensors_battery + + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_sensors_battery(self): + def secs2hours(secs): + m, _s = divmod(secs, 60) + h, m = divmod(m, 60) + return f"{int(h)}:{int(m):02}" + + out = sh("acpiconf -i 0") + fields = {x.split('\t')[0]: x.split('\t')[-1] for x in out.split("\n")} + metrics = psutil.sensors_battery() + percent = int(fields['Remaining capacity:'].replace('%', '')) + remaining_time = fields['Remaining time:'] + assert metrics.percent == percent + if remaining_time == 'unknown': + assert metrics.secsleft == psutil.POWER_TIME_UNLIMITED + else: + assert secs2hours(metrics.secsleft) == remaining_time + + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_sensors_battery_against_sysctl(self): + assert psutil.sensors_battery().percent == sysctl( + "hw.acpi.battery.life" + ) + assert psutil.sensors_battery().power_plugged == ( + sysctl("hw.acpi.acline") == 1 + ) + secsleft = psutil.sensors_battery().secsleft + if secsleft < 0: + assert sysctl("hw.acpi.battery.time") == -1 + else: + assert secsleft == sysctl("hw.acpi.battery.time") * 60 + + @pytest.mark.skipif(HAS_BATTERY, reason="has battery") + def test_sensors_battery_no_battery(self): + # If no battery is present one of these calls is supposed + # to fail, see: + # https://github.com/giampaolo/psutil/issues/1074 + with pytest.raises(RuntimeError): + sysctl("hw.acpi.battery.life") + sysctl("hw.acpi.battery.time") + sysctl("hw.acpi.acline") + assert psutil.sensors_battery() is None + + # --- sensors_temperatures + + def test_sensors_temperatures_against_sysctl(self): + num_cpus = psutil.cpu_count(True) + for cpu in range(num_cpus): + sensor = f"dev.cpu.{cpu}.temperature" + # sysctl returns a string in the format 46.0C + try: + sysctl_result = int(float(sysctl(sensor)[:-1])) + except RuntimeError: + raise pytest.skip("temperatures not supported by kernel") + assert ( + abs( + psutil.sensors_temperatures()["coretemp"][cpu].current + - sysctl_result + ) + < 10 + ) + + sensor = f"dev.cpu.{cpu}.coretemp.tjmax" + sysctl_result = int(float(sysctl(sensor)[:-1])) + assert ( + psutil.sensors_temperatures()["coretemp"][cpu].high + == sysctl_result + ) + + +# ===================================================================== +# --- OpenBSD +# ===================================================================== + + +@pytest.mark.skipif(not OPENBSD, reason="OPENBSD only") +class OpenBSDTestCase(PsutilTestCase): + def test_boot_time(self): + s = sysctl('kern.boottime') + sys_bt = datetime.datetime.strptime(s, "%a %b %d %H:%M:%S %Y") + psutil_bt = datetime.datetime.fromtimestamp(psutil.boot_time()) + assert sys_bt == psutil_bt + + +# ===================================================================== +# --- NetBSD +# ===================================================================== + + +@pytest.mark.skipif(not NETBSD, reason="NETBSD only") +class NetBSDTestCase(PsutilTestCase): + @staticmethod + def parse_meminfo(look_for): + with open('/proc/meminfo') as f: + for line in f: + if line.startswith(look_for): + return int(line.split()[1]) * 1024 + raise ValueError(f"can't find {look_for}") + + # --- virtual mem + + def test_vmem_total(self): + assert psutil.virtual_memory().total == self.parse_meminfo("MemTotal:") + + def test_vmem_free(self): + assert ( + abs(psutil.virtual_memory().free - self.parse_meminfo("MemFree:")) + < TOLERANCE_SYS_MEM + ) + + def test_vmem_buffers(self): + assert ( + abs( + psutil.virtual_memory().buffers + - self.parse_meminfo("Buffers:") + ) + < TOLERANCE_SYS_MEM + ) + + def test_vmem_shared(self): + assert ( + abs( + psutil.virtual_memory().shared + - self.parse_meminfo("MemShared:") + ) + < TOLERANCE_SYS_MEM + ) + + def test_vmem_cached(self): + assert ( + abs(psutil.virtual_memory().cached - self.parse_meminfo("Cached:")) + < TOLERANCE_SYS_MEM + ) + + # --- swap mem + + def test_swapmem_total(self): + assert ( + abs(psutil.swap_memory().total - self.parse_meminfo("SwapTotal:")) + < TOLERANCE_SYS_MEM + ) + + def test_swapmem_free(self): + assert ( + abs(psutil.swap_memory().free - self.parse_meminfo("SwapFree:")) + < TOLERANCE_SYS_MEM + ) + + def test_swapmem_used(self): + smem = psutil.swap_memory() + assert smem.used == smem.total - smem.free + + # --- others + + def test_cpu_stats_interrupts(self): + with open('/proc/stat', 'rb') as f: + for line in f: + if line.startswith(b'intr'): + interrupts = int(line.split()[1]) + break + else: + raise ValueError("couldn't find line") + assert abs(psutil.cpu_stats().interrupts - interrupts) < 1000 + + def test_cpu_stats_ctx_switches(self): + with open('/proc/stat', 'rb') as f: + for line in f: + if line.startswith(b'ctxt'): + ctx_switches = int(line.split()[1]) + break + else: + raise ValueError("couldn't find line") + assert abs(psutil.cpu_stats().ctx_switches - ctx_switches) < 1000 diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_connections.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_connections.py new file mode 100644 index 0000000..5ddeb85 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_connections.py @@ -0,0 +1,566 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Tests for psutil.net_connections() and Process.net_connections() APIs.""" + +import os +import socket +import textwrap +from contextlib import closing +from socket import AF_INET +from socket import AF_INET6 +from socket import SOCK_DGRAM +from socket import SOCK_STREAM + +import psutil +from psutil import FREEBSD +from psutil import LINUX +from psutil import MACOS +from psutil import NETBSD +from psutil import OPENBSD +from psutil import POSIX +from psutil import SUNOS +from psutil import WINDOWS +from psutil._common import supports_ipv6 +from psutil.tests import AF_UNIX +from psutil.tests import HAS_NET_CONNECTIONS_UNIX +from psutil.tests import SKIP_SYSCONS +from psutil.tests import PsutilTestCase +from psutil.tests import bind_socket +from psutil.tests import bind_unix_socket +from psutil.tests import check_connection_ntuple +from psutil.tests import create_sockets +from psutil.tests import filter_proc_net_connections +from psutil.tests import pytest +from psutil.tests import reap_children +from psutil.tests import retry_on_failure +from psutil.tests import skip_on_access_denied +from psutil.tests import tcp_socketpair +from psutil.tests import unix_socketpair +from psutil.tests import wait_for_file + + +SOCK_SEQPACKET = getattr(socket, "SOCK_SEQPACKET", object()) + + +def this_proc_net_connections(kind): + cons = psutil.Process().net_connections(kind=kind) + if kind in {"all", "unix"}: + return filter_proc_net_connections(cons) + return cons + + +@pytest.mark.xdist_group(name="serial") +class ConnectionTestCase(PsutilTestCase): + def setUp(self): + assert this_proc_net_connections(kind='all') == [] + + def tearDown(self): + # Make sure we closed all resources. + assert this_proc_net_connections(kind='all') == [] + + def compare_procsys_connections(self, pid, proc_cons, kind='all'): + """Given a process PID and its list of connections compare + those against system-wide connections retrieved via + psutil.net_connections. + """ + try: + sys_cons = psutil.net_connections(kind=kind) + except psutil.AccessDenied: + # On MACOS, system-wide connections are retrieved by iterating + # over all processes + if MACOS: + return + else: + raise + # Filter for this proc PID and exlucde PIDs from the tuple. + sys_cons = [c[:-1] for c in sys_cons if c.pid == pid] + sys_cons.sort() + proc_cons.sort() + assert proc_cons == sys_cons + + +class TestBasicOperations(ConnectionTestCase): + @pytest.mark.skipif(SKIP_SYSCONS, reason="requires root") + def test_system(self): + with create_sockets(): + for conn in psutil.net_connections(kind='all'): + check_connection_ntuple(conn) + + def test_process(self): + with create_sockets(): + for conn in this_proc_net_connections(kind='all'): + check_connection_ntuple(conn) + + def test_invalid_kind(self): + with pytest.raises(ValueError): + this_proc_net_connections(kind='???') + with pytest.raises(ValueError): + psutil.net_connections(kind='???') + + +@pytest.mark.xdist_group(name="serial") +class TestUnconnectedSockets(ConnectionTestCase): + """Tests sockets which are open but not connected to anything.""" + + def get_conn_from_sock(self, sock): + cons = this_proc_net_connections(kind='all') + smap = {c.fd: c for c in cons} + if NETBSD or FREEBSD: + # NetBSD opens a UNIX socket to /var/log/run + # so there may be more connections. + return smap[sock.fileno()] + else: + assert len(cons) == 1 + if cons[0].fd != -1: + assert smap[sock.fileno()].fd == sock.fileno() + return cons[0] + + def check_socket(self, sock): + """Given a socket, makes sure it matches the one obtained + via psutil. It assumes this process created one connection + only (the one supposed to be checked). + """ + conn = self.get_conn_from_sock(sock) + check_connection_ntuple(conn) + + # fd, family, type + if conn.fd != -1: + assert conn.fd == sock.fileno() + assert conn.family == sock.family + # see: http://bugs.python.org/issue30204 + assert conn.type == sock.getsockopt(socket.SOL_SOCKET, socket.SO_TYPE) + + # local address + laddr = sock.getsockname() + if not laddr and isinstance(laddr, bytes): + # See: http://bugs.python.org/issue30205 + laddr = laddr.decode() + if sock.family == AF_INET6: + laddr = laddr[:2] + assert conn.laddr == laddr + + # XXX Solaris can't retrieve system-wide UNIX sockets + if sock.family == AF_UNIX and HAS_NET_CONNECTIONS_UNIX: + cons = this_proc_net_connections(kind='all') + self.compare_procsys_connections(os.getpid(), cons, kind='all') + return conn + + def test_tcp_v4(self): + addr = ("127.0.0.1", 0) + with closing(bind_socket(AF_INET, SOCK_STREAM, addr=addr)) as sock: + conn = self.check_socket(sock) + assert conn.raddr == () + assert conn.status == psutil.CONN_LISTEN + + @pytest.mark.skipif(not supports_ipv6(), reason="IPv6 not supported") + def test_tcp_v6(self): + addr = ("::1", 0) + with closing(bind_socket(AF_INET6, SOCK_STREAM, addr=addr)) as sock: + conn = self.check_socket(sock) + assert conn.raddr == () + assert conn.status == psutil.CONN_LISTEN + + def test_udp_v4(self): + addr = ("127.0.0.1", 0) + with closing(bind_socket(AF_INET, SOCK_DGRAM, addr=addr)) as sock: + conn = self.check_socket(sock) + assert conn.raddr == () + assert conn.status == psutil.CONN_NONE + + @pytest.mark.skipif(not supports_ipv6(), reason="IPv6 not supported") + def test_udp_v6(self): + addr = ("::1", 0) + with closing(bind_socket(AF_INET6, SOCK_DGRAM, addr=addr)) as sock: + conn = self.check_socket(sock) + assert conn.raddr == () + assert conn.status == psutil.CONN_NONE + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_unix_tcp(self): + testfn = self.get_testfn() + with closing(bind_unix_socket(testfn, type=SOCK_STREAM)) as sock: + conn = self.check_socket(sock) + assert conn.raddr == "" + assert conn.status == psutil.CONN_NONE + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_unix_udp(self): + testfn = self.get_testfn() + with closing(bind_unix_socket(testfn, type=SOCK_STREAM)) as sock: + conn = self.check_socket(sock) + assert conn.raddr == "" + assert conn.status == psutil.CONN_NONE + + +@pytest.mark.xdist_group(name="serial") +class TestConnectedSocket(ConnectionTestCase): + """Test socket pairs which are actually connected to + each other. + """ + + # On SunOS, even after we close() it, the server socket stays around + # in TIME_WAIT state. + @pytest.mark.skipif(SUNOS, reason="unreliable on SUONS") + def test_tcp(self): + addr = ("127.0.0.1", 0) + assert this_proc_net_connections(kind='tcp4') == [] + server, client = tcp_socketpair(AF_INET, addr=addr) + try: + cons = this_proc_net_connections(kind='tcp4') + assert len(cons) == 2 + assert cons[0].status == psutil.CONN_ESTABLISHED + assert cons[1].status == psutil.CONN_ESTABLISHED + # May not be fast enough to change state so it stays + # commenteed. + # client.close() + # cons = this_proc_net_connections(kind='all') + # self.assertEqual(len(cons), 1) + # self.assertEqual(cons[0].status, psutil.CONN_CLOSE_WAIT) + finally: + server.close() + client.close() + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_unix(self): + testfn = self.get_testfn() + server, client = unix_socketpair(testfn) + try: + cons = this_proc_net_connections(kind='unix') + assert not (cons[0].laddr and cons[0].raddr), cons + assert not (cons[1].laddr and cons[1].raddr), cons + if NETBSD or FREEBSD: + # On NetBSD creating a UNIX socket will cause + # a UNIX connection to /var/run/log. + cons = [c for c in cons if c.raddr != '/var/run/log'] + assert len(cons) == 2 + if LINUX or FREEBSD or SUNOS or OPENBSD: + # remote path is never set + assert cons[0].raddr == "" + assert cons[1].raddr == "" + # one local address should though + assert testfn == (cons[0].laddr or cons[1].laddr) + else: + # On other systems either the laddr or raddr + # of both peers are set. + assert (cons[0].laddr or cons[1].laddr) == testfn + finally: + server.close() + client.close() + + +class TestFilters(ConnectionTestCase): + def test_filters(self): + def check(kind, families, types): + for conn in this_proc_net_connections(kind=kind): + assert conn.family in families + assert conn.type in types + if not SKIP_SYSCONS: + for conn in psutil.net_connections(kind=kind): + assert conn.family in families + assert conn.type in types + + with create_sockets(): + check( + 'all', + [AF_INET, AF_INET6, AF_UNIX], + [SOCK_STREAM, SOCK_DGRAM, SOCK_SEQPACKET], + ) + check('inet', [AF_INET, AF_INET6], [SOCK_STREAM, SOCK_DGRAM]) + check('inet4', [AF_INET], [SOCK_STREAM, SOCK_DGRAM]) + check('tcp', [AF_INET, AF_INET6], [SOCK_STREAM]) + check('tcp4', [AF_INET], [SOCK_STREAM]) + check('tcp6', [AF_INET6], [SOCK_STREAM]) + check('udp', [AF_INET, AF_INET6], [SOCK_DGRAM]) + check('udp4', [AF_INET], [SOCK_DGRAM]) + check('udp6', [AF_INET6], [SOCK_DGRAM]) + if HAS_NET_CONNECTIONS_UNIX: + check( + 'unix', + [AF_UNIX], + [SOCK_STREAM, SOCK_DGRAM, SOCK_SEQPACKET], + ) + + @skip_on_access_denied(only_if=MACOS) + def test_combos(self): + reap_children() + + def check_conn(proc, conn, family, type, laddr, raddr, status, kinds): + all_kinds = ( + "all", + "inet", + "inet4", + "inet6", + "tcp", + "tcp4", + "tcp6", + "udp", + "udp4", + "udp6", + ) + check_connection_ntuple(conn) + assert conn.family == family + assert conn.type == type + assert conn.laddr == laddr + assert conn.raddr == raddr + assert conn.status == status + for kind in all_kinds: + cons = proc.net_connections(kind=kind) + if kind in kinds: + assert cons != [] + else: + assert cons == [] + # compare against system-wide connections + # XXX Solaris can't retrieve system-wide UNIX + # sockets. + if HAS_NET_CONNECTIONS_UNIX: + self.compare_procsys_connections(proc.pid, [conn]) + + tcp_template = textwrap.dedent(""" + import socket, time + s = socket.socket({family}, socket.SOCK_STREAM) + s.bind(('{addr}', 0)) + s.listen(5) + with open('{testfn}', 'w') as f: + f.write(str(s.getsockname()[:2])) + [time.sleep(0.1) for x in range(100)] + """) + + udp_template = textwrap.dedent(""" + import socket, time + s = socket.socket({family}, socket.SOCK_DGRAM) + s.bind(('{addr}', 0)) + with open('{testfn}', 'w') as f: + f.write(str(s.getsockname()[:2])) + [time.sleep(0.1) for x in range(100)] + """) + + # must be relative on Windows + testfile = os.path.basename(self.get_testfn(dir=os.getcwd())) + tcp4_template = tcp_template.format( + family=int(AF_INET), addr="127.0.0.1", testfn=testfile + ) + udp4_template = udp_template.format( + family=int(AF_INET), addr="127.0.0.1", testfn=testfile + ) + tcp6_template = tcp_template.format( + family=int(AF_INET6), addr="::1", testfn=testfile + ) + udp6_template = udp_template.format( + family=int(AF_INET6), addr="::1", testfn=testfile + ) + + # launch various subprocess instantiating a socket of various + # families and types to enrich psutil results + tcp4_proc = self.pyrun(tcp4_template) + tcp4_addr = eval(wait_for_file(testfile, delete=True)) + udp4_proc = self.pyrun(udp4_template) + udp4_addr = eval(wait_for_file(testfile, delete=True)) + if supports_ipv6(): + tcp6_proc = self.pyrun(tcp6_template) + tcp6_addr = eval(wait_for_file(testfile, delete=True)) + udp6_proc = self.pyrun(udp6_template) + udp6_addr = eval(wait_for_file(testfile, delete=True)) + else: + tcp6_proc = None + udp6_proc = None + tcp6_addr = None + udp6_addr = None + + for p in psutil.Process().children(): + cons = p.net_connections() + assert len(cons) == 1 + for conn in cons: + # TCP v4 + if p.pid == tcp4_proc.pid: + check_conn( + p, + conn, + AF_INET, + SOCK_STREAM, + tcp4_addr, + (), + psutil.CONN_LISTEN, + ("all", "inet", "inet4", "tcp", "tcp4"), + ) + # UDP v4 + elif p.pid == udp4_proc.pid: + check_conn( + p, + conn, + AF_INET, + SOCK_DGRAM, + udp4_addr, + (), + psutil.CONN_NONE, + ("all", "inet", "inet4", "udp", "udp4"), + ) + # TCP v6 + elif p.pid == getattr(tcp6_proc, "pid", None): + check_conn( + p, + conn, + AF_INET6, + SOCK_STREAM, + tcp6_addr, + (), + psutil.CONN_LISTEN, + ("all", "inet", "inet6", "tcp", "tcp6"), + ) + # UDP v6 + elif p.pid == getattr(udp6_proc, "pid", None): + check_conn( + p, + conn, + AF_INET6, + SOCK_DGRAM, + udp6_addr, + (), + psutil.CONN_NONE, + ("all", "inet", "inet6", "udp", "udp6"), + ) + + def test_count(self): + with create_sockets(): + # tcp + cons = this_proc_net_connections(kind='tcp') + assert len(cons) == (2 if supports_ipv6() else 1) + for conn in cons: + assert conn.family in {AF_INET, AF_INET6} + assert conn.type == SOCK_STREAM + # tcp4 + cons = this_proc_net_connections(kind='tcp4') + assert len(cons) == 1 + assert cons[0].family == AF_INET + assert cons[0].type == SOCK_STREAM + # tcp6 + if supports_ipv6(): + cons = this_proc_net_connections(kind='tcp6') + assert len(cons) == 1 + assert cons[0].family == AF_INET6 + assert cons[0].type == SOCK_STREAM + # udp + cons = this_proc_net_connections(kind='udp') + assert len(cons) == (2 if supports_ipv6() else 1) + for conn in cons: + assert conn.family in {AF_INET, AF_INET6} + assert conn.type == SOCK_DGRAM + # udp4 + cons = this_proc_net_connections(kind='udp4') + assert len(cons) == 1 + assert cons[0].family == AF_INET + assert cons[0].type == SOCK_DGRAM + # udp6 + if supports_ipv6(): + cons = this_proc_net_connections(kind='udp6') + assert len(cons) == 1 + assert cons[0].family == AF_INET6 + assert cons[0].type == SOCK_DGRAM + # inet + cons = this_proc_net_connections(kind='inet') + assert len(cons) == (4 if supports_ipv6() else 2) + for conn in cons: + assert conn.family in {AF_INET, AF_INET6} + assert conn.type in {SOCK_STREAM, SOCK_DGRAM} + # inet6 + if supports_ipv6(): + cons = this_proc_net_connections(kind='inet6') + assert len(cons) == 2 + for conn in cons: + assert conn.family == AF_INET6 + assert conn.type in {SOCK_STREAM, SOCK_DGRAM} + # Skipped on BSD becayse by default the Python process + # creates a UNIX socket to '/var/run/log'. + if HAS_NET_CONNECTIONS_UNIX and not (FREEBSD or NETBSD): + cons = this_proc_net_connections(kind='unix') + assert len(cons) == 3 + for conn in cons: + assert conn.family == AF_UNIX + assert conn.type in {SOCK_STREAM, SOCK_DGRAM} + + +@pytest.mark.skipif(SKIP_SYSCONS, reason="requires root") +class TestSystemWideConnections(ConnectionTestCase): + """Tests for net_connections().""" + + def test_it(self): + def check(cons, families, types_): + for conn in cons: + assert conn.family in families + if conn.family != AF_UNIX: + assert conn.type in types_ + check_connection_ntuple(conn) + + with create_sockets(): + from psutil._common import conn_tmap + + for kind, groups in conn_tmap.items(): + # XXX: SunOS does not retrieve UNIX sockets. + if kind == 'unix' and not HAS_NET_CONNECTIONS_UNIX: + continue + families, types_ = groups + cons = psutil.net_connections(kind) + assert len(cons) == len(set(cons)) + check(cons, families, types_) + + @retry_on_failure() + def test_multi_sockets_procs(self): + # Creates multiple sub processes, each creating different + # sockets. For each process check that proc.net_connections() + # and psutil.net_connections() return the same results. + # This is done mainly to check whether net_connections()'s + # pid is properly set, see: + # https://github.com/giampaolo/psutil/issues/1013 + with create_sockets() as socks: + expected = len(socks) + pids = [] + times = 10 + fnames = [] + for _ in range(times): + fname = self.get_testfn() + fnames.append(fname) + src = textwrap.dedent(f"""\ + import time, os + from psutil.tests import create_sockets + with create_sockets(): + with open(r'{fname}', 'w') as f: + f.write("hello") + [time.sleep(0.1) for x in range(100)] + """) + sproc = self.pyrun(src) + pids.append(sproc.pid) + + # sync + for fname in fnames: + wait_for_file(fname) + + syscons = [ + x for x in psutil.net_connections(kind='all') if x.pid in pids + ] + for pid in pids: + assert len([x for x in syscons if x.pid == pid]) == expected + p = psutil.Process(pid) + assert len(p.net_connections('all')) == expected + + +class TestMisc(PsutilTestCase): + def test_net_connection_constants(self): + ints = [] + strs = [] + for name in dir(psutil): + if name.startswith('CONN_'): + num = getattr(psutil, name) + str_ = str(num) + assert str_.isupper(), str_ + assert str not in strs + assert num not in ints + ints.append(num) + strs.append(str_) + if SUNOS: + psutil.CONN_IDLE # noqa: B018 + psutil.CONN_BOUND # noqa: B018 + if WINDOWS: + psutil.CONN_DELETE_TCB # noqa: B018 diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_contracts.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_contracts.py new file mode 100644 index 0000000..55f3a5d --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_contracts.py @@ -0,0 +1,325 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Contracts tests. These tests mainly check API sanity in terms of +returned types and APIs availability. +Some of these are duplicates of tests test_system.py and test_process.py. +""" + +import platform +import signal + +import psutil +from psutil import AIX +from psutil import FREEBSD +from psutil import LINUX +from psutil import MACOS +from psutil import NETBSD +from psutil import OPENBSD +from psutil import POSIX +from psutil import SUNOS +from psutil import WINDOWS +from psutil.tests import GITHUB_ACTIONS +from psutil.tests import HAS_CPU_FREQ +from psutil.tests import HAS_NET_IO_COUNTERS +from psutil.tests import HAS_SENSORS_FANS +from psutil.tests import HAS_SENSORS_TEMPERATURES +from psutil.tests import SKIP_SYSCONS +from psutil.tests import PsutilTestCase +from psutil.tests import create_sockets +from psutil.tests import enum +from psutil.tests import is_namedtuple +from psutil.tests import kernel_version +from psutil.tests import pytest + + +# =================================================================== +# --- APIs availability +# =================================================================== + +# Make sure code reflects what doc promises in terms of APIs +# availability. + + +class TestAvailConstantsAPIs(PsutilTestCase): + def test_PROCFS_PATH(self): + assert hasattr(psutil, "PROCFS_PATH") == (LINUX or SUNOS or AIX) + + def test_win_priority(self): + ae = self.assertEqual + ae(hasattr(psutil, "ABOVE_NORMAL_PRIORITY_CLASS"), WINDOWS) + ae(hasattr(psutil, "BELOW_NORMAL_PRIORITY_CLASS"), WINDOWS) + ae(hasattr(psutil, "HIGH_PRIORITY_CLASS"), WINDOWS) + ae(hasattr(psutil, "IDLE_PRIORITY_CLASS"), WINDOWS) + ae(hasattr(psutil, "NORMAL_PRIORITY_CLASS"), WINDOWS) + ae(hasattr(psutil, "REALTIME_PRIORITY_CLASS"), WINDOWS) + + def test_linux_ioprio_linux(self): + ae = self.assertEqual + ae(hasattr(psutil, "IOPRIO_CLASS_NONE"), LINUX) + ae(hasattr(psutil, "IOPRIO_CLASS_RT"), LINUX) + ae(hasattr(psutil, "IOPRIO_CLASS_BE"), LINUX) + ae(hasattr(psutil, "IOPRIO_CLASS_IDLE"), LINUX) + + def test_linux_ioprio_windows(self): + ae = self.assertEqual + ae(hasattr(psutil, "IOPRIO_HIGH"), WINDOWS) + ae(hasattr(psutil, "IOPRIO_NORMAL"), WINDOWS) + ae(hasattr(psutil, "IOPRIO_LOW"), WINDOWS) + ae(hasattr(psutil, "IOPRIO_VERYLOW"), WINDOWS) + + @pytest.mark.skipif( + GITHUB_ACTIONS and LINUX, + reason="unsupported on GITHUB_ACTIONS + LINUX", + ) + def test_rlimit(self): + ae = self.assertEqual + ae(hasattr(psutil, "RLIM_INFINITY"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_AS"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_CORE"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_CPU"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_DATA"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_FSIZE"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_MEMLOCK"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_NOFILE"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_NPROC"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_RSS"), LINUX or FREEBSD) + ae(hasattr(psutil, "RLIMIT_STACK"), LINUX or FREEBSD) + + ae(hasattr(psutil, "RLIMIT_LOCKS"), LINUX) + if POSIX: + if kernel_version() >= (2, 6, 8): + ae(hasattr(psutil, "RLIMIT_MSGQUEUE"), LINUX) + if kernel_version() >= (2, 6, 12): + ae(hasattr(psutil, "RLIMIT_NICE"), LINUX) + if kernel_version() >= (2, 6, 12): + ae(hasattr(psutil, "RLIMIT_RTPRIO"), LINUX) + if kernel_version() >= (2, 6, 25): + ae(hasattr(psutil, "RLIMIT_RTTIME"), LINUX) + if kernel_version() >= (2, 6, 8): + ae(hasattr(psutil, "RLIMIT_SIGPENDING"), LINUX) + + ae(hasattr(psutil, "RLIMIT_SWAP"), FREEBSD) + ae(hasattr(psutil, "RLIMIT_SBSIZE"), FREEBSD) + ae(hasattr(psutil, "RLIMIT_NPTS"), FREEBSD) + + +class TestAvailSystemAPIs(PsutilTestCase): + def test_win_service_iter(self): + assert hasattr(psutil, "win_service_iter") == WINDOWS + + def test_win_service_get(self): + assert hasattr(psutil, "win_service_get") == WINDOWS + + def test_cpu_freq(self): + assert hasattr(psutil, "cpu_freq") == ( + LINUX or MACOS or WINDOWS or FREEBSD or OPENBSD + ) + + def test_sensors_temperatures(self): + assert hasattr(psutil, "sensors_temperatures") == (LINUX or FREEBSD) + + def test_sensors_fans(self): + assert hasattr(psutil, "sensors_fans") == LINUX + + def test_battery(self): + assert hasattr(psutil, "sensors_battery") == ( + LINUX or WINDOWS or FREEBSD or MACOS + ) + + +class TestAvailProcessAPIs(PsutilTestCase): + def test_environ(self): + assert hasattr(psutil.Process, "environ") == ( + LINUX + or MACOS + or WINDOWS + or AIX + or SUNOS + or FREEBSD + or OPENBSD + or NETBSD + ) + + def test_uids(self): + assert hasattr(psutil.Process, "uids") == POSIX + + def test_gids(self): + assert hasattr(psutil.Process, "uids") == POSIX + + def test_terminal(self): + assert hasattr(psutil.Process, "terminal") == POSIX + + def test_ionice(self): + assert hasattr(psutil.Process, "ionice") == (LINUX or WINDOWS) + + @pytest.mark.skipif( + GITHUB_ACTIONS and LINUX, + reason="unsupported on GITHUB_ACTIONS + LINUX", + ) + def test_rlimit(self): + assert hasattr(psutil.Process, "rlimit") == (LINUX or FREEBSD) + + def test_io_counters(self): + hasit = hasattr(psutil.Process, "io_counters") + assert hasit == (not (MACOS or SUNOS)) + + def test_num_fds(self): + assert hasattr(psutil.Process, "num_fds") == POSIX + + def test_num_handles(self): + assert hasattr(psutil.Process, "num_handles") == WINDOWS + + def test_cpu_affinity(self): + assert hasattr(psutil.Process, "cpu_affinity") == ( + LINUX or WINDOWS or FREEBSD + ) + + def test_cpu_num(self): + assert hasattr(psutil.Process, "cpu_num") == ( + LINUX or FREEBSD or SUNOS + ) + + def test_memory_maps(self): + hasit = hasattr(psutil.Process, "memory_maps") + assert hasit == (not (OPENBSD or NETBSD or AIX or MACOS)) + + +# =================================================================== +# --- API types +# =================================================================== + + +class TestSystemAPITypes(PsutilTestCase): + """Check the return types of system related APIs. + https://github.com/giampaolo/psutil/issues/1039. + """ + + @classmethod + def setUpClass(cls): + cls.proc = psutil.Process() + + def assert_ntuple_of_nums(self, nt, type_=float, gezero=True): + assert is_namedtuple(nt) + for n in nt: + assert isinstance(n, type_) + if gezero: + assert n >= 0 + + def test_cpu_times(self): + self.assert_ntuple_of_nums(psutil.cpu_times()) + for nt in psutil.cpu_times(percpu=True): + self.assert_ntuple_of_nums(nt) + + def test_cpu_percent(self): + assert isinstance(psutil.cpu_percent(interval=None), float) + assert isinstance(psutil.cpu_percent(interval=0.00001), float) + + def test_cpu_times_percent(self): + self.assert_ntuple_of_nums(psutil.cpu_times_percent(interval=None)) + self.assert_ntuple_of_nums(psutil.cpu_times_percent(interval=0.0001)) + + def test_cpu_count(self): + assert isinstance(psutil.cpu_count(), int) + + # TODO: remove this once 1892 is fixed + @pytest.mark.skipif( + MACOS and platform.machine() == 'arm64', reason="skipped due to #1892" + ) + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + def test_cpu_freq(self): + if psutil.cpu_freq() is None: + raise pytest.skip("cpu_freq() returns None") + self.assert_ntuple_of_nums(psutil.cpu_freq(), type_=(float, int)) + + def test_disk_io_counters(self): + # Duplicate of test_system.py. Keep it anyway. + for k, v in psutil.disk_io_counters(perdisk=True).items(): + assert isinstance(k, str) + self.assert_ntuple_of_nums(v, type_=int) + + def test_disk_partitions(self): + # Duplicate of test_system.py. Keep it anyway. + for disk in psutil.disk_partitions(): + assert isinstance(disk.device, str) + assert isinstance(disk.mountpoint, str) + assert isinstance(disk.fstype, str) + assert isinstance(disk.opts, str) + + @pytest.mark.skipif(SKIP_SYSCONS, reason="requires root") + def test_net_connections(self): + with create_sockets(): + ret = psutil.net_connections('all') + assert len(ret) == len(set(ret)) + for conn in ret: + assert is_namedtuple(conn) + + def test_net_if_addrs(self): + # Duplicate of test_system.py. Keep it anyway. + for ifname, addrs in psutil.net_if_addrs().items(): + assert isinstance(ifname, str) + for addr in addrs: + assert isinstance(addr.family, enum.IntEnum) + assert isinstance(addr.address, str) + assert isinstance(addr.netmask, (str, type(None))) + assert isinstance(addr.broadcast, (str, type(None))) + + def test_net_if_stats(self): + # Duplicate of test_system.py. Keep it anyway. + for ifname, info in psutil.net_if_stats().items(): + assert isinstance(ifname, str) + assert isinstance(info.isup, bool) + assert isinstance(info.duplex, enum.IntEnum) + assert isinstance(info.speed, int) + assert isinstance(info.mtu, int) + + @pytest.mark.skipif(not HAS_NET_IO_COUNTERS, reason="not supported") + def test_net_io_counters(self): + # Duplicate of test_system.py. Keep it anyway. + for ifname in psutil.net_io_counters(pernic=True): + assert isinstance(ifname, str) + + @pytest.mark.skipif(not HAS_SENSORS_FANS, reason="not supported") + def test_sensors_fans(self): + # Duplicate of test_system.py. Keep it anyway. + for name, units in psutil.sensors_fans().items(): + assert isinstance(name, str) + for unit in units: + assert isinstance(unit.label, str) + assert isinstance(unit.current, (float, int, type(None))) + + @pytest.mark.skipif(not HAS_SENSORS_TEMPERATURES, reason="not supported") + def test_sensors_temperatures(self): + # Duplicate of test_system.py. Keep it anyway. + for name, units in psutil.sensors_temperatures().items(): + assert isinstance(name, str) + for unit in units: + assert isinstance(unit.label, str) + assert isinstance(unit.current, (float, int, type(None))) + assert isinstance(unit.high, (float, int, type(None))) + assert isinstance(unit.critical, (float, int, type(None))) + + def test_boot_time(self): + # Duplicate of test_system.py. Keep it anyway. + assert isinstance(psutil.boot_time(), float) + + def test_users(self): + # Duplicate of test_system.py. Keep it anyway. + for user in psutil.users(): + assert isinstance(user.name, str) + assert isinstance(user.terminal, (str, type(None))) + assert isinstance(user.host, (str, type(None))) + assert isinstance(user.pid, (int, type(None))) + + +class TestProcessWaitType(PsutilTestCase): + @pytest.mark.skipif(not POSIX, reason="not POSIX") + def test_negative_signal(self): + p = psutil.Process(self.spawn_testproc().pid) + p.terminate() + code = p.wait() + assert code == -signal.SIGTERM + assert isinstance(code, enum.IntEnum) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_linux.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_linux.py new file mode 100644 index 0000000..f4342d7 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_linux.py @@ -0,0 +1,2292 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Linux specific tests.""" + + +import collections +import contextlib +import errno +import io +import os +import platform +import re +import shutil +import socket +import struct +import textwrap +import time +import warnings +from unittest import mock + +import psutil +from psutil import LINUX +from psutil.tests import AARCH64 +from psutil.tests import GITHUB_ACTIONS +from psutil.tests import GLOBAL_TIMEOUT +from psutil.tests import HAS_BATTERY +from psutil.tests import HAS_CPU_FREQ +from psutil.tests import HAS_GETLOADAVG +from psutil.tests import HAS_RLIMIT +from psutil.tests import PYPY +from psutil.tests import PYTEST_PARALLEL +from psutil.tests import TOLERANCE_DISK_USAGE +from psutil.tests import TOLERANCE_SYS_MEM +from psutil.tests import PsutilTestCase +from psutil.tests import ThreadTask +from psutil.tests import call_until +from psutil.tests import pytest +from psutil.tests import reload_module +from psutil.tests import retry_on_failure +from psutil.tests import safe_rmpath +from psutil.tests import sh +from psutil.tests import skip_on_not_implemented + + +if LINUX: + from psutil._pslinux import CLOCK_TICKS + from psutil._pslinux import RootFsDeviceFinder + from psutil._pslinux import calculate_avail_vmem + from psutil._pslinux import open_binary + + +HERE = os.path.abspath(os.path.dirname(__file__)) +SIOCGIFADDR = 0x8915 +SIOCGIFHWADDR = 0x8927 +SIOCGIFNETMASK = 0x891B +SIOCGIFBRDADDR = 0x8919 +if LINUX: + SECTOR_SIZE = 512 +# ===================================================================== +# --- utils +# ===================================================================== + + +def get_ipv4_address(ifname): + import fcntl + + ifname = bytes(ifname[:15], "ascii") + with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as s: + return socket.inet_ntoa( + fcntl.ioctl(s.fileno(), SIOCGIFADDR, struct.pack('256s', ifname))[ + 20:24 + ] + ) + + +def get_ipv4_netmask(ifname): + import fcntl + + ifname = bytes(ifname[:15], "ascii") + with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as s: + return socket.inet_ntoa( + fcntl.ioctl( + s.fileno(), SIOCGIFNETMASK, struct.pack('256s', ifname) + )[20:24] + ) + + +def get_ipv4_broadcast(ifname): + import fcntl + + ifname = bytes(ifname[:15], "ascii") + with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as s: + return socket.inet_ntoa( + fcntl.ioctl( + s.fileno(), SIOCGIFBRDADDR, struct.pack('256s', ifname) + )[20:24] + ) + + +def get_ipv6_addresses(ifname): + with open("/proc/net/if_inet6") as f: + all_fields = [] + for line in f: + fields = line.split() + if fields[-1] == ifname: + all_fields.append(fields) + + if len(all_fields) == 0: + raise ValueError(f"could not find interface {ifname!r}") + + for i in range(len(all_fields)): + unformatted = all_fields[i][0] + groups = [ + unformatted[j : j + 4] for j in range(0, len(unformatted), 4) + ] + formatted = ":".join(groups) + packed = socket.inet_pton(socket.AF_INET6, formatted) + all_fields[i] = socket.inet_ntop(socket.AF_INET6, packed) + return all_fields + + +def get_mac_address(ifname): + import fcntl + + ifname = bytes(ifname[:15], "ascii") + with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as s: + info = fcntl.ioctl( + s.fileno(), SIOCGIFHWADDR, struct.pack('256s', ifname) + ) + return "".join([f"{char:02x}:" for char in info[18:24]])[:-1] + + +def free_swap(): + """Parse 'free' cmd and return swap memory's s total, used and free + values. + """ + out = sh(["free", "-b"], env={"LANG": "C.UTF-8"}) + lines = out.split('\n') + for line in lines: + if line.startswith('Swap'): + _, total, used, free = line.split() + nt = collections.namedtuple('free', 'total used free') + return nt(int(total), int(used), int(free)) + raise ValueError(f"can't find 'Swap' in 'free' output:\n{out}") + + +def free_physmem(): + """Parse 'free' cmd and return physical memory's total, used + and free values. + """ + # Note: free can have 2 different formats, invalidating 'shared' + # and 'cached' memory which may have different positions so we + # do not return them. + # https://github.com/giampaolo/psutil/issues/538#issuecomment-57059946 + out = sh(["free", "-b"], env={"LANG": "C.UTF-8"}) + lines = out.split('\n') + for line in lines: + if line.startswith('Mem'): + total, used, free, shared = (int(x) for x in line.split()[1:5]) + nt = collections.namedtuple( + 'free', 'total used free shared output' + ) + return nt(total, used, free, shared, out) + raise ValueError(f"can't find 'Mem' in 'free' output:\n{out}") + + +def vmstat(stat): + out = sh(["vmstat", "-s"], env={"LANG": "C.UTF-8"}) + for line in out.split("\n"): + line = line.strip() + if stat in line: + return int(line.split(' ')[0]) + raise ValueError(f"can't find {stat!r} in 'vmstat' output") + + +def get_free_version_info(): + out = sh(["free", "-V"]).strip() + if 'UNKNOWN' in out: + raise pytest.skip("can't determine free version") + return tuple(map(int, re.findall(r'\d+', out.split()[-1]))) + + +@contextlib.contextmanager +def mock_open_content(pairs): + """Mock open() builtin and forces it to return a certain content + for a given path. `pairs` is a {"path": "content", ...} dict. + """ + + def open_mock(name, *args, **kwargs): + if name in pairs: + content = pairs[name] + if isinstance(content, str): + return io.StringIO(content) + else: + return io.BytesIO(content) + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", create=True, side_effect=open_mock) as m: + yield m + + +@contextlib.contextmanager +def mock_open_exception(for_path, exc): + """Mock open() builtin and raises `exc` if the path being opened + matches `for_path`. + """ + + def open_mock(name, *args, **kwargs): + if name == for_path: + raise exc + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", create=True, side_effect=open_mock) as m: + yield m + + +# ===================================================================== +# --- system virtual memory +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemVirtualMemoryAgainstFree(PsutilTestCase): + def test_total(self): + cli_value = free_physmem().total + psutil_value = psutil.virtual_memory().total + assert cli_value == psutil_value + + @retry_on_failure() + def test_used(self): + # Older versions of procps used slab memory to calculate used memory. + # This got changed in: + # https://gitlab.com/procps-ng/procps/commit/ + # 05d751c4f076a2f0118b914c5e51cfbb4762ad8e + # Newer versions of procps are using yet another way to compute used + # memory. + # https://gitlab.com/procps-ng/procps/commit/ + # 2184e90d2e7cdb582f9a5b706b47015e56707e4d + if get_free_version_info() < (3, 3, 12): + raise pytest.skip("free version too old") + if get_free_version_info() >= (4, 0, 0): + raise pytest.skip("free version too recent") + cli_value = free_physmem().used + psutil_value = psutil.virtual_memory().used + assert abs(cli_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_free(self): + cli_value = free_physmem().free + psutil_value = psutil.virtual_memory().free + assert abs(cli_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_shared(self): + free = free_physmem() + free_value = free.shared + if free_value == 0: + raise pytest.skip("free does not support 'shared' column") + psutil_value = psutil.virtual_memory().shared + assert ( + abs(free_value - psutil_value) < TOLERANCE_SYS_MEM + ), f"{free_value} {psutil_value} \n{free.output}" + + @retry_on_failure() + def test_available(self): + # "free" output format has changed at some point: + # https://github.com/giampaolo/psutil/issues/538#issuecomment-147192098 + out = sh(["free", "-b"]) + lines = out.split('\n') + if 'available' not in lines[0]: + raise pytest.skip("free does not support 'available' column") + free_value = int(lines[1].split()[-1]) + psutil_value = psutil.virtual_memory().available + assert abs(free_value - psutil_value) < TOLERANCE_SYS_MEM + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemVirtualMemoryAgainstVmstat(PsutilTestCase): + def test_total(self): + vmstat_value = vmstat('total memory') * 1024 + psutil_value = psutil.virtual_memory().total + assert abs(vmstat_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_used(self): + # Older versions of procps used slab memory to calculate used memory. + # This got changed in: + # https://gitlab.com/procps-ng/procps/commit/ + # 05d751c4f076a2f0118b914c5e51cfbb4762ad8e + # Newer versions of procps are using yet another way to compute used + # memory. + # https://gitlab.com/procps-ng/procps/commit/ + # 2184e90d2e7cdb582f9a5b706b47015e56707e4d + if get_free_version_info() < (3, 3, 12): + raise pytest.skip("free version too old") + if get_free_version_info() >= (4, 0, 0): + raise pytest.skip("free version too recent") + vmstat_value = vmstat('used memory') * 1024 + psutil_value = psutil.virtual_memory().used + assert abs(vmstat_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_free(self): + vmstat_value = vmstat('free memory') * 1024 + psutil_value = psutil.virtual_memory().free + assert abs(vmstat_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_buffers(self): + vmstat_value = vmstat('buffer memory') * 1024 + psutil_value = psutil.virtual_memory().buffers + assert abs(vmstat_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_active(self): + vmstat_value = vmstat('active memory') * 1024 + psutil_value = psutil.virtual_memory().active + assert abs(vmstat_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_inactive(self): + vmstat_value = vmstat('inactive memory') * 1024 + psutil_value = psutil.virtual_memory().inactive + assert abs(vmstat_value - psutil_value) < TOLERANCE_SYS_MEM + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemVirtualMemoryMocks(PsutilTestCase): + def test_warnings_on_misses(self): + # Emulate a case where /proc/meminfo provides few info. + # psutil is supposed to set the missing fields to 0 and + # raise a warning. + content = textwrap.dedent("""\ + Active(anon): 6145416 kB + Active(file): 2950064 kB + Inactive(anon): 574764 kB + Inactive(file): 1567648 kB + MemAvailable: -1 kB + MemFree: 2057400 kB + MemTotal: 16325648 kB + SReclaimable: 346648 kB + """).encode() + with mock_open_content({'/proc/meminfo': content}) as m: + with warnings.catch_warnings(record=True) as ws: + warnings.simplefilter("always") + ret = psutil.virtual_memory() + assert m.called + assert len(ws) == 1 + w = ws[0] + assert "memory stats couldn't be determined" in str(w.message) + assert "cached" in str(w.message) + assert "shared" in str(w.message) + assert "active" in str(w.message) + assert "inactive" in str(w.message) + assert "buffers" in str(w.message) + assert "available" in str(w.message) + assert ret.cached == 0 + assert ret.active == 0 + assert ret.inactive == 0 + assert ret.shared == 0 + assert ret.buffers == 0 + assert ret.available == 0 + assert ret.slab == 0 + + @retry_on_failure() + def test_avail_old_percent(self): + # Make sure that our calculation of avail mem for old kernels + # is off by max 15%. + mems = {} + with open_binary('/proc/meminfo') as f: + for line in f: + fields = line.split() + mems[fields[0]] = int(fields[1]) * 1024 + + a = calculate_avail_vmem(mems) + if b'MemAvailable:' in mems: + b = mems[b'MemAvailable:'] + diff_percent = abs(a - b) / a * 100 + assert diff_percent < 15 + + def test_avail_old_comes_from_kernel(self): + # Make sure "MemAvailable:" coluimn is used instead of relying + # on our internal algorithm to calculate avail mem. + content = textwrap.dedent("""\ + Active: 9444728 kB + Active(anon): 6145416 kB + Active(file): 2950064 kB + Buffers: 287952 kB + Cached: 4818144 kB + Inactive(file): 1578132 kB + Inactive(anon): 574764 kB + Inactive(file): 1567648 kB + MemAvailable: 6574984 kB + MemFree: 2057400 kB + MemTotal: 16325648 kB + Shmem: 577588 kB + SReclaimable: 346648 kB + """).encode() + with mock_open_content({'/proc/meminfo': content}) as m: + with warnings.catch_warnings(record=True) as ws: + ret = psutil.virtual_memory() + assert m.called + assert ret.available == 6574984 * 1024 + w = ws[0] + assert "inactive memory stats couldn't be determined" in str( + w.message + ) + + def test_avail_old_missing_fields(self): + # Remove Active(file), Inactive(file) and SReclaimable + # from /proc/meminfo and make sure the fallback is used + # (free + cached), + content = textwrap.dedent("""\ + Active: 9444728 kB + Active(anon): 6145416 kB + Buffers: 287952 kB + Cached: 4818144 kB + Inactive(file): 1578132 kB + Inactive(anon): 574764 kB + MemFree: 2057400 kB + MemTotal: 16325648 kB + Shmem: 577588 kB + """).encode() + with mock_open_content({"/proc/meminfo": content}) as m: + with warnings.catch_warnings(record=True) as ws: + ret = psutil.virtual_memory() + assert m.called + assert ret.available == 2057400 * 1024 + 4818144 * 1024 + w = ws[0] + assert "inactive memory stats couldn't be determined" in str( + w.message + ) + + def test_avail_old_missing_zoneinfo(self): + # Remove /proc/zoneinfo file. Make sure fallback is used + # (free + cached). + content = textwrap.dedent("""\ + Active: 9444728 kB + Active(anon): 6145416 kB + Active(file): 2950064 kB + Buffers: 287952 kB + Cached: 4818144 kB + Inactive(file): 1578132 kB + Inactive(anon): 574764 kB + Inactive(file): 1567648 kB + MemFree: 2057400 kB + MemTotal: 16325648 kB + Shmem: 577588 kB + SReclaimable: 346648 kB + """).encode() + with mock_open_content({"/proc/meminfo": content}): + with mock_open_exception("/proc/zoneinfo", FileNotFoundError): + with warnings.catch_warnings(record=True) as ws: + ret = psutil.virtual_memory() + assert ret.available == 2057400 * 1024 + 4818144 * 1024 + w = ws[0] + assert ( + "inactive memory stats couldn't be determined" + in str(w.message) + ) + + def test_virtual_memory_mocked(self): + # Emulate /proc/meminfo because neither vmstat nor free return slab. + content = textwrap.dedent("""\ + MemTotal: 100 kB + MemFree: 2 kB + MemAvailable: 3 kB + Buffers: 4 kB + Cached: 5 kB + SwapCached: 6 kB + Active: 7 kB + Inactive: 8 kB + Active(anon): 9 kB + Inactive(anon): 10 kB + Active(file): 11 kB + Inactive(file): 12 kB + Unevictable: 13 kB + Mlocked: 14 kB + SwapTotal: 15 kB + SwapFree: 16 kB + Dirty: 17 kB + Writeback: 18 kB + AnonPages: 19 kB + Mapped: 20 kB + Shmem: 21 kB + Slab: 22 kB + SReclaimable: 23 kB + SUnreclaim: 24 kB + KernelStack: 25 kB + PageTables: 26 kB + NFS_Unstable: 27 kB + Bounce: 28 kB + WritebackTmp: 29 kB + CommitLimit: 30 kB + Committed_AS: 31 kB + VmallocTotal: 32 kB + VmallocUsed: 33 kB + VmallocChunk: 34 kB + HardwareCorrupted: 35 kB + AnonHugePages: 36 kB + ShmemHugePages: 37 kB + ShmemPmdMapped: 38 kB + CmaTotal: 39 kB + CmaFree: 40 kB + HugePages_Total: 41 kB + HugePages_Free: 42 kB + HugePages_Rsvd: 43 kB + HugePages_Surp: 44 kB + Hugepagesize: 45 kB + DirectMap46k: 46 kB + DirectMap47M: 47 kB + DirectMap48G: 48 kB + """).encode() + with mock_open_content({"/proc/meminfo": content}) as m: + mem = psutil.virtual_memory() + assert m.called + assert mem.total == 100 * 1024 + assert mem.free == 2 * 1024 + assert mem.buffers == 4 * 1024 + # cached mem also includes reclaimable memory + assert mem.cached == (5 + 23) * 1024 + assert mem.shared == 21 * 1024 + assert mem.active == 7 * 1024 + assert mem.inactive == 8 * 1024 + assert mem.slab == 22 * 1024 + assert mem.available == 3 * 1024 + + +# ===================================================================== +# --- system swap memory +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemSwapMemory(PsutilTestCase): + @staticmethod + def meminfo_has_swap_info(): + """Return True if /proc/meminfo provides swap metrics.""" + with open("/proc/meminfo") as f: + data = f.read() + return 'SwapTotal:' in data and 'SwapFree:' in data + + def test_total(self): + free_value = free_swap().total + psutil_value = psutil.swap_memory().total + assert abs(free_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_used(self): + free_value = free_swap().used + psutil_value = psutil.swap_memory().used + assert abs(free_value - psutil_value) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_free(self): + free_value = free_swap().free + psutil_value = psutil.swap_memory().free + assert abs(free_value - psutil_value) < TOLERANCE_SYS_MEM + + def test_missing_sin_sout(self): + with mock.patch('psutil._common.open', create=True) as m: + with warnings.catch_warnings(record=True) as ws: + warnings.simplefilter("always") + ret = psutil.swap_memory() + assert m.called + assert len(ws) == 1 + w = ws[0] + assert ( + "'sin' and 'sout' swap memory stats couldn't be determined" + in str(w.message) + ) + assert ret.sin == 0 + assert ret.sout == 0 + + def test_no_vmstat_mocked(self): + # see https://github.com/giampaolo/psutil/issues/722 + with mock_open_exception("/proc/vmstat", FileNotFoundError) as m: + with warnings.catch_warnings(record=True) as ws: + warnings.simplefilter("always") + ret = psutil.swap_memory() + assert m.called + assert len(ws) == 1 + w = ws[0] + assert ( + "'sin' and 'sout' swap memory stats couldn't " + "be determined and were set to 0" + in str(w.message) + ) + assert ret.sin == 0 + assert ret.sout == 0 + + def test_meminfo_against_sysinfo(self): + # Make sure the content of /proc/meminfo about swap memory + # matches sysinfo() syscall, see: + # https://github.com/giampaolo/psutil/issues/1015 + if not self.meminfo_has_swap_info(): + raise pytest.skip("/proc/meminfo has no swap metrics") + with mock.patch('psutil._pslinux.cext.linux_sysinfo') as m: + swap = psutil.swap_memory() + assert not m.called + import psutil._psutil_linux as cext + + _, _, _, _, total, free, unit_multiplier = cext.linux_sysinfo() + total *= unit_multiplier + free *= unit_multiplier + assert swap.total == total + assert abs(swap.free - free) < TOLERANCE_SYS_MEM + + def test_emulate_meminfo_has_no_metrics(self): + # Emulate a case where /proc/meminfo provides no swap metrics + # in which case sysinfo() syscall is supposed to be used + # as a fallback. + with mock_open_content({"/proc/meminfo": b""}) as m: + psutil.swap_memory() + assert m.called + + +# ===================================================================== +# --- system CPU +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemCPUTimes(PsutilTestCase): + def test_fields(self): + fields = psutil.cpu_times()._fields + kernel_ver = re.findall(r'\d+\.\d+\.\d+', os.uname()[2])[0] + kernel_ver_info = tuple(map(int, kernel_ver.split('.'))) + if kernel_ver_info >= (2, 6, 11): + assert 'steal' in fields + else: + assert 'steal' not in fields + if kernel_ver_info >= (2, 6, 24): + assert 'guest' in fields + else: + assert 'guest' not in fields + if kernel_ver_info >= (3, 2, 0): + assert 'guest_nice' in fields + else: + assert 'guest_nice' not in fields + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemCPUCountLogical(PsutilTestCase): + @pytest.mark.skipif( + not os.path.exists("/sys/devices/system/cpu/online"), + reason="/sys/devices/system/cpu/online does not exist", + ) + def test_against_sysdev_cpu_online(self): + with open("/sys/devices/system/cpu/online") as f: + value = f.read().strip() + if "-" in str(value): + value = int(value.split('-')[1]) + 1 + assert psutil.cpu_count() == value + + @pytest.mark.skipif( + not os.path.exists("/sys/devices/system/cpu"), + reason="/sys/devices/system/cpu does not exist", + ) + def test_against_sysdev_cpu_num(self): + ls = os.listdir("/sys/devices/system/cpu") + count = len([x for x in ls if re.search(r"cpu\d+$", x) is not None]) + assert psutil.cpu_count() == count + + @pytest.mark.skipif( + not shutil.which("nproc"), reason="nproc utility not available" + ) + def test_against_nproc(self): + num = int(sh("nproc --all")) + assert psutil.cpu_count(logical=True) == num + + @pytest.mark.skipif( + not shutil.which("lscpu"), reason="lscpu utility not available" + ) + def test_against_lscpu(self): + out = sh("lscpu -p") + num = len([x for x in out.split('\n') if not x.startswith('#')]) + assert psutil.cpu_count(logical=True) == num + + def test_emulate_fallbacks(self): + import psutil._pslinux + + original = psutil._pslinux.cpu_count_logical() + # Here we want to mock os.sysconf("SC_NPROCESSORS_ONLN") in + # order to cause the parsing of /proc/cpuinfo and /proc/stat. + with mock.patch( + 'psutil._pslinux.os.sysconf', side_effect=ValueError + ) as m: + assert psutil._pslinux.cpu_count_logical() == original + assert m.called + + # Let's have open() return empty data and make sure None is + # returned ('cause we mimic os.cpu_count()). + with mock.patch('psutil._common.open', create=True) as m: + assert psutil._pslinux.cpu_count_logical() is None + assert m.call_count == 2 + # /proc/stat should be the last one + assert m.call_args[0][0] == '/proc/stat' + + # Let's push this a bit further and make sure /proc/cpuinfo + # parsing works as expected. + with open('/proc/cpuinfo', 'rb') as f: + cpuinfo_data = f.read() + fake_file = io.BytesIO(cpuinfo_data) + with mock.patch( + 'psutil._common.open', return_value=fake_file, create=True + ) as m: + assert psutil._pslinux.cpu_count_logical() == original + + # Finally, let's make /proc/cpuinfo return meaningless data; + # this way we'll fall back on relying on /proc/stat + with mock_open_content({"/proc/cpuinfo": b""}) as m: + assert psutil._pslinux.cpu_count_logical() == original + assert m.called + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemCPUCountCores(PsutilTestCase): + @pytest.mark.skipif( + not shutil.which("lscpu"), reason="lscpu utility not available" + ) + def test_against_lscpu(self): + out = sh("lscpu -p") + core_ids = set() + for line in out.split('\n'): + if not line.startswith('#'): + fields = line.split(',') + core_ids.add(fields[1]) + assert psutil.cpu_count(logical=False) == len(core_ids) + + @pytest.mark.skipif( + platform.machine() not in {"x86_64", "i686"}, reason="x86_64/i686 only" + ) + def test_method_2(self): + meth_1 = psutil._pslinux.cpu_count_cores() + with mock.patch('glob.glob', return_value=[]) as m: + meth_2 = psutil._pslinux.cpu_count_cores() + assert m.called + if meth_1 is not None: + assert meth_1 == meth_2 + + def test_emulate_none(self): + with mock.patch('glob.glob', return_value=[]) as m1: + with mock.patch('psutil._common.open', create=True) as m2: + assert psutil._pslinux.cpu_count_cores() is None + assert m1.called + assert m2.called + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemCPUFrequency(PsutilTestCase): + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + @pytest.mark.skipif( + AARCH64, reason="aarch64 does not always expose frequency" + ) + def test_emulate_use_second_file(self): + # https://github.com/giampaolo/psutil/issues/981 + def path_exists_mock(path): + if path.startswith("/sys/devices/system/cpu/cpufreq/policy"): + return False + else: + return orig_exists(path) + + orig_exists = os.path.exists + with mock.patch( + "os.path.exists", side_effect=path_exists_mock, create=True + ): + assert psutil.cpu_freq() + + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + @pytest.mark.skipif( + AARCH64, reason="aarch64 does not report mhz in /proc/cpuinfo" + ) + def test_emulate_use_cpuinfo(self): + # Emulate a case where /sys/devices/system/cpu/cpufreq* does not + # exist and /proc/cpuinfo is used instead. + def path_exists_mock(path): + if path.startswith('/sys/devices/system/cpu/'): + return False + else: + return os_path_exists(path) + + os_path_exists = os.path.exists + try: + with mock.patch("os.path.exists", side_effect=path_exists_mock): + reload_module(psutil._pslinux) + ret = psutil.cpu_freq() + assert ret, ret + assert ret.max == 0.0 + assert ret.min == 0.0 + for freq in psutil.cpu_freq(percpu=True): + assert freq.max == 0.0 + assert freq.min == 0.0 + finally: + reload_module(psutil._pslinux) + reload_module(psutil) + + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + def test_emulate_data(self): + def open_mock(name, *args, **kwargs): + if name.endswith('/scaling_cur_freq') and name.startswith( + "/sys/devices/system/cpu/cpufreq/policy" + ): + return io.BytesIO(b"500000") + elif name.endswith('/scaling_min_freq') and name.startswith( + "/sys/devices/system/cpu/cpufreq/policy" + ): + return io.BytesIO(b"600000") + elif name.endswith('/scaling_max_freq') and name.startswith( + "/sys/devices/system/cpu/cpufreq/policy" + ): + return io.BytesIO(b"700000") + elif name == '/proc/cpuinfo': + return io.BytesIO(b"cpu MHz : 500") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock): + with mock.patch('os.path.exists', return_value=True): + freq = psutil.cpu_freq() + assert freq.current == 500.0 + # when /proc/cpuinfo is used min and max frequencies are not + # available and are set to 0. + if freq.min != 0.0: + assert freq.min == 600.0 + if freq.max != 0.0: + assert freq.max == 700.0 + + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + def test_emulate_multi_cpu(self): + def open_mock(name, *args, **kwargs): + n = name + if n.endswith('/scaling_cur_freq') and n.startswith( + "/sys/devices/system/cpu/cpufreq/policy0" + ): + return io.BytesIO(b"100000") + elif n.endswith('/scaling_min_freq') and n.startswith( + "/sys/devices/system/cpu/cpufreq/policy0" + ): + return io.BytesIO(b"200000") + elif n.endswith('/scaling_max_freq') and n.startswith( + "/sys/devices/system/cpu/cpufreq/policy0" + ): + return io.BytesIO(b"300000") + elif n.endswith('/scaling_cur_freq') and n.startswith( + "/sys/devices/system/cpu/cpufreq/policy1" + ): + return io.BytesIO(b"400000") + elif n.endswith('/scaling_min_freq') and n.startswith( + "/sys/devices/system/cpu/cpufreq/policy1" + ): + return io.BytesIO(b"500000") + elif n.endswith('/scaling_max_freq') and n.startswith( + "/sys/devices/system/cpu/cpufreq/policy1" + ): + return io.BytesIO(b"600000") + elif name == '/proc/cpuinfo': + return io.BytesIO(b"cpu MHz : 100\ncpu MHz : 400") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock): + with mock.patch('os.path.exists', return_value=True): + with mock.patch( + 'psutil._pslinux.cpu_count_logical', return_value=2 + ): + freq = psutil.cpu_freq(percpu=True) + assert freq[0].current == 100.0 + if freq[0].min != 0.0: + assert freq[0].min == 200.0 + if freq[0].max != 0.0: + assert freq[0].max == 300.0 + assert freq[1].current == 400.0 + if freq[1].min != 0.0: + assert freq[1].min == 500.0 + if freq[1].max != 0.0: + assert freq[1].max == 600.0 + + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + def test_emulate_no_scaling_cur_freq_file(self): + # See: https://github.com/giampaolo/psutil/issues/1071 + def open_mock(name, *args, **kwargs): + if name.endswith('/scaling_cur_freq'): + raise FileNotFoundError + if name.endswith('/cpuinfo_cur_freq'): + return io.BytesIO(b"200000") + elif name == '/proc/cpuinfo': + return io.BytesIO(b"cpu MHz : 200") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock): + with mock.patch('os.path.exists', return_value=True): + with mock.patch( + 'psutil._pslinux.cpu_count_logical', return_value=1 + ): + freq = psutil.cpu_freq() + assert freq.current == 200 + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemCPUStats(PsutilTestCase): + + # XXX: fails too often. + # def test_ctx_switches(self): + # vmstat_value = vmstat("context switches") + # psutil_value = psutil.cpu_stats().ctx_switches + # self.assertAlmostEqual(vmstat_value, psutil_value, delta=500) + + def test_interrupts(self): + vmstat_value = vmstat("interrupts") + psutil_value = psutil.cpu_stats().interrupts + assert abs(vmstat_value - psutil_value) < 500 + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestLoadAvg(PsutilTestCase): + @pytest.mark.skipif(not HAS_GETLOADAVG, reason="not supported") + def test_getloadavg(self): + psutil_value = psutil.getloadavg() + with open("/proc/loadavg") as f: + proc_value = f.read().split() + + assert abs(float(proc_value[0]) - psutil_value[0]) < 1 + assert abs(float(proc_value[1]) - psutil_value[1]) < 1 + assert abs(float(proc_value[2]) - psutil_value[2]) < 1 + + +# ===================================================================== +# --- system network +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemNetIfAddrs(PsutilTestCase): + def test_ips(self): + for name, addrs in psutil.net_if_addrs().items(): + for addr in addrs: + if addr.family == psutil.AF_LINK: + assert addr.address == get_mac_address(name) + elif addr.family == socket.AF_INET: + assert addr.address == get_ipv4_address(name) + assert addr.netmask == get_ipv4_netmask(name) + if addr.broadcast is not None: + assert addr.broadcast == get_ipv4_broadcast(name) + else: + assert get_ipv4_broadcast(name) == '0.0.0.0' + elif addr.family == socket.AF_INET6: + # IPv6 addresses can have a percent symbol at the end. + # E.g. these 2 are equivalent: + # "fe80::1ff:fe23:4567:890a" + # "fe80::1ff:fe23:4567:890a%eth0" + # That is the "zone id" portion, which usually is the name + # of the network interface. + address = addr.address.split('%')[0] + assert address in get_ipv6_addresses(name) + + # XXX - not reliable when having virtual NICs installed by Docker. + # @pytest.mark.skipif(not shutil.which("ip"), + # reason="'ip' utility not available") + # def test_net_if_names(self): + # out = sh("ip addr").strip() + # nics = [x for x in psutil.net_if_addrs().keys() if ':' not in x] + # found = 0 + # for line in out.split('\n'): + # line = line.strip() + # if re.search(r"^\d+:", line): + # found += 1 + # name = line.split(':')[1].strip() + # self.assertIn(name, nics) + # self.assertEqual(len(nics), found, msg="{}\n---\n{}".format( + # pprint.pformat(nics), out)) + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemNetIfStats(PsutilTestCase): + @pytest.mark.skipif( + not shutil.which("ifconfig"), reason="ifconfig utility not available" + ) + def test_against_ifconfig(self): + for name, stats in psutil.net_if_stats().items(): + try: + out = sh(f"ifconfig {name}") + except RuntimeError: + pass + else: + assert stats.isup == ('RUNNING' in out), out + assert stats.mtu == int( + re.findall(r'(?i)MTU[: ](\d+)', out)[0] + ) + + def test_mtu(self): + for name, stats in psutil.net_if_stats().items(): + with open(f"/sys/class/net/{name}/mtu") as f: + assert stats.mtu == int(f.read().strip()) + + @pytest.mark.skipif( + not shutil.which("ifconfig"), reason="ifconfig utility not available" + ) + def test_flags(self): + # first line looks like this: + # "eth0: flags=4163 mtu 1500" + matches_found = 0 + for name, stats in psutil.net_if_stats().items(): + try: + out = sh(f"ifconfig {name}") + except RuntimeError: + pass + else: + match = re.search(r"flags=(\d+)?<(.*?)>", out) + if match and len(match.groups()) >= 2: + matches_found += 1 + ifconfig_flags = set(match.group(2).lower().split(",")) + psutil_flags = set(stats.flags.split(",")) + assert ifconfig_flags == psutil_flags + else: + # ifconfig has a different output on CentOS 6 + # let's try that + match = re.search(r"(.*) MTU:(\d+) Metric:(\d+)", out) + if match and len(match.groups()) >= 3: + matches_found += 1 + ifconfig_flags = set(match.group(1).lower().split()) + psutil_flags = set(stats.flags.split(",")) + assert ifconfig_flags == psutil_flags + + if not matches_found: + raise self.fail("no matches were found") + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemNetIOCounters(PsutilTestCase): + @pytest.mark.skipif( + not shutil.which("ifconfig"), reason="ifconfig utility not available" + ) + @retry_on_failure() + def test_against_ifconfig(self): + def ifconfig(nic): + ret = {} + out = sh(f"ifconfig {nic}") + ret['packets_recv'] = int( + re.findall(r'RX packets[: ](\d+)', out)[0] + ) + ret['packets_sent'] = int( + re.findall(r'TX packets[: ](\d+)', out)[0] + ) + ret['errin'] = int(re.findall(r'errors[: ](\d+)', out)[0]) + ret['errout'] = int(re.findall(r'errors[: ](\d+)', out)[1]) + ret['dropin'] = int(re.findall(r'dropped[: ](\d+)', out)[0]) + ret['dropout'] = int(re.findall(r'dropped[: ](\d+)', out)[1]) + ret['bytes_recv'] = int( + re.findall(r'RX (?:packets \d+ +)?bytes[: ](\d+)', out)[0] + ) + ret['bytes_sent'] = int( + re.findall(r'TX (?:packets \d+ +)?bytes[: ](\d+)', out)[0] + ) + return ret + + nio = psutil.net_io_counters(pernic=True, nowrap=False) + for name, stats in nio.items(): + try: + ifconfig_ret = ifconfig(name) + except RuntimeError: + continue + assert ( + abs(stats.bytes_recv - ifconfig_ret['bytes_recv']) < 1024 * 10 + ) + assert ( + abs(stats.bytes_sent - ifconfig_ret['bytes_sent']) < 1024 * 10 + ) + assert ( + abs(stats.packets_recv - ifconfig_ret['packets_recv']) < 1024 + ) + assert ( + abs(stats.packets_sent - ifconfig_ret['packets_sent']) < 1024 + ) + assert abs(stats.errin - ifconfig_ret['errin']) < 10 + assert abs(stats.errout - ifconfig_ret['errout']) < 10 + assert abs(stats.dropin - ifconfig_ret['dropin']) < 10 + assert abs(stats.dropout - ifconfig_ret['dropout']) < 10 + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemNetConnections(PsutilTestCase): + @mock.patch('psutil._pslinux.socket.inet_ntop', side_effect=ValueError) + @mock.patch('psutil._pslinux.supports_ipv6', return_value=False) + def test_emulate_ipv6_unsupported(self, supports_ipv6, inet_ntop): + # see: https://github.com/giampaolo/psutil/issues/623 + try: + s = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) + self.addCleanup(s.close) + s.bind(("::1", 0)) + except OSError: + pass + psutil.net_connections(kind='inet6') + + def test_emulate_unix(self): + content = textwrap.dedent("""\ + 0: 00000003 000 000 0001 03 462170 @/tmp/dbus-Qw2hMPIU3n + 0: 00000003 000 000 0001 03 35010 @/tmp/dbus-tB2X8h69BQ + 0: 00000003 000 000 0001 03 34424 @/tmp/dbus-cHy80Y8O + 000000000000000000000000000000000000000000000000000000 + """) + with mock_open_content({"/proc/net/unix": content}) as m: + psutil.net_connections(kind='unix') + assert m.called + + +# ===================================================================== +# --- system disks +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemDiskPartitions(PsutilTestCase): + @pytest.mark.skipif( + not hasattr(os, 'statvfs'), reason="os.statvfs() not available" + ) + @skip_on_not_implemented() + def test_against_df(self): + # test psutil.disk_usage() and psutil.disk_partitions() + # against "df -a" + def df(path): + out = sh(f'df -P -B 1 "{path}"').strip() + lines = out.split('\n') + lines.pop(0) + line = lines.pop(0) + dev, total, used, free = line.split()[:4] + if dev == 'none': + dev = '' + total, used, free = int(total), int(used), int(free) + return dev, total, used, free + + for part in psutil.disk_partitions(all=False): + usage = psutil.disk_usage(part.mountpoint) + _, total, used, free = df(part.mountpoint) + assert usage.total == total + assert abs(usage.free - free) < TOLERANCE_DISK_USAGE + assert abs(usage.used - used) < TOLERANCE_DISK_USAGE + + def test_zfs_fs(self): + # Test that ZFS partitions are returned. + with open("/proc/filesystems") as f: + data = f.read() + if 'zfs' in data: + for part in psutil.disk_partitions(): + if part.fstype == 'zfs': + return + + # No ZFS partitions on this system. Let's fake one. + fake_file = io.StringIO("nodev\tzfs\n") + with mock.patch( + 'psutil._common.open', return_value=fake_file, create=True + ) as m1: + with mock.patch( + 'psutil._pslinux.cext.disk_partitions', + return_value=[('/dev/sdb3', '/', 'zfs', 'rw')], + ) as m2: + ret = psutil.disk_partitions() + assert m1.called + assert m2.called + assert ret + assert ret[0].fstype == 'zfs' + + def test_emulate_realpath_fail(self): + # See: https://github.com/giampaolo/psutil/issues/1307 + try: + with mock.patch( + 'os.path.realpath', return_value='/non/existent' + ) as m: + with pytest.raises(FileNotFoundError): + psutil.disk_partitions() + assert m.called + finally: + psutil.PROCFS_PATH = "/proc" + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSystemDiskIoCounters(PsutilTestCase): + def test_emulate_kernel_2_4(self): + # Tests /proc/diskstats parsing format for 2.4 kernels, see: + # https://github.com/giampaolo/psutil/issues/767 + content = " 3 0 1 hda 2 3 4 5 6 7 8 9 10 11 12" + with mock_open_content({'/proc/diskstats': content}): + with mock.patch( + 'psutil._pslinux.is_storage_device', return_value=True + ): + ret = psutil.disk_io_counters(nowrap=False) + assert ret.read_count == 1 + assert ret.read_merged_count == 2 + assert ret.read_bytes == 3 * SECTOR_SIZE + assert ret.read_time == 4 + assert ret.write_count == 5 + assert ret.write_merged_count == 6 + assert ret.write_bytes == 7 * SECTOR_SIZE + assert ret.write_time == 8 + assert ret.busy_time == 10 + + def test_emulate_kernel_2_6_full(self): + # Tests /proc/diskstats parsing format for 2.6 kernels, + # lines reporting all metrics: + # https://github.com/giampaolo/psutil/issues/767 + content = " 3 0 hda 1 2 3 4 5 6 7 8 9 10 11" + with mock_open_content({"/proc/diskstats": content}): + with mock.patch( + 'psutil._pslinux.is_storage_device', return_value=True + ): + ret = psutil.disk_io_counters(nowrap=False) + assert ret.read_count == 1 + assert ret.read_merged_count == 2 + assert ret.read_bytes == 3 * SECTOR_SIZE + assert ret.read_time == 4 + assert ret.write_count == 5 + assert ret.write_merged_count == 6 + assert ret.write_bytes == 7 * SECTOR_SIZE + assert ret.write_time == 8 + assert ret.busy_time == 10 + + def test_emulate_kernel_2_6_limited(self): + # Tests /proc/diskstats parsing format for 2.6 kernels, + # where one line of /proc/partitions return a limited + # amount of metrics when it bumps into a partition + # (instead of a disk). See: + # https://github.com/giampaolo/psutil/issues/767 + with mock_open_content({"/proc/diskstats": " 3 1 hda 1 2 3 4"}): + with mock.patch( + 'psutil._pslinux.is_storage_device', return_value=True + ): + ret = psutil.disk_io_counters(nowrap=False) + assert ret.read_count == 1 + assert ret.read_bytes == 2 * SECTOR_SIZE + assert ret.write_count == 3 + assert ret.write_bytes == 4 * SECTOR_SIZE + + assert ret.read_merged_count == 0 + assert ret.read_time == 0 + assert ret.write_merged_count == 0 + assert ret.write_time == 0 + assert ret.busy_time == 0 + + def test_emulate_include_partitions(self): + # Make sure that when perdisk=True disk partitions are returned, + # see: + # https://github.com/giampaolo/psutil/pull/1313#issuecomment-408626842 + content = textwrap.dedent("""\ + 3 0 nvme0n1 1 2 3 4 5 6 7 8 9 10 11 + 3 0 nvme0n1p1 1 2 3 4 5 6 7 8 9 10 11 + """) + with mock_open_content({"/proc/diskstats": content}): + with mock.patch( + 'psutil._pslinux.is_storage_device', return_value=False + ): + ret = psutil.disk_io_counters(perdisk=True, nowrap=False) + assert len(ret) == 2 + assert ret['nvme0n1'].read_count == 1 + assert ret['nvme0n1p1'].read_count == 1 + assert ret['nvme0n1'].write_count == 5 + assert ret['nvme0n1p1'].write_count == 5 + + def test_emulate_exclude_partitions(self): + # Make sure that when perdisk=False partitions (e.g. 'sda1', + # 'nvme0n1p1') are skipped and not included in the total count. + # https://github.com/giampaolo/psutil/pull/1313#issuecomment-408626842 + content = textwrap.dedent("""\ + 3 0 nvme0n1 1 2 3 4 5 6 7 8 9 10 11 + 3 0 nvme0n1p1 1 2 3 4 5 6 7 8 9 10 11 + """) + with mock_open_content({"/proc/diskstats": content}): + with mock.patch( + 'psutil._pslinux.is_storage_device', return_value=False + ): + ret = psutil.disk_io_counters(perdisk=False, nowrap=False) + assert ret is None + + def is_storage_device(name): + return name == 'nvme0n1' + + content = textwrap.dedent("""\ + 3 0 nvme0n1 1 2 3 4 5 6 7 8 9 10 11 + 3 0 nvme0n1p1 1 2 3 4 5 6 7 8 9 10 11 + """) + with mock_open_content({"/proc/diskstats": content}): + with mock.patch( + 'psutil._pslinux.is_storage_device', + create=True, + side_effect=is_storage_device, + ): + ret = psutil.disk_io_counters(perdisk=False, nowrap=False) + assert ret.read_count == 1 + assert ret.write_count == 5 + + def test_emulate_use_sysfs(self): + def exists(path): + return path == '/proc/diskstats' + + wprocfs = psutil.disk_io_counters(perdisk=True) + with mock.patch( + 'psutil._pslinux.os.path.exists', create=True, side_effect=exists + ): + wsysfs = psutil.disk_io_counters(perdisk=True) + assert len(wprocfs) == len(wsysfs) + + def test_emulate_not_impl(self): + def exists(path): + return False + + with mock.patch( + 'psutil._pslinux.os.path.exists', create=True, side_effect=exists + ): + with pytest.raises(NotImplementedError): + psutil.disk_io_counters() + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestRootFsDeviceFinder(PsutilTestCase): + def setUp(self): + dev = os.stat("/").st_dev + self.major = os.major(dev) + self.minor = os.minor(dev) + + def test_call_methods(self): + finder = RootFsDeviceFinder() + if os.path.exists("/proc/partitions"): + finder.ask_proc_partitions() + else: + with pytest.raises(FileNotFoundError): + finder.ask_proc_partitions() + if os.path.exists(f"/sys/dev/block/{self.major}:{self.minor}/uevent"): + finder.ask_sys_dev_block() + else: + with pytest.raises(FileNotFoundError): + finder.ask_sys_dev_block() + finder.ask_sys_class_block() + + @pytest.mark.skipif(GITHUB_ACTIONS, reason="unsupported on GITHUB_ACTIONS") + def test_comparisons(self): + finder = RootFsDeviceFinder() + assert finder.find() is not None + + a = b = c = None + if os.path.exists("/proc/partitions"): + a = finder.ask_proc_partitions() + if os.path.exists(f"/sys/dev/block/{self.major}:{self.minor}/uevent"): + b = finder.ask_sys_class_block() + c = finder.ask_sys_dev_block() + + base = a or b or c + if base and a: + assert base == a + if base and b: + assert base == b + if base and c: + assert base == c + + @pytest.mark.skipif( + not shutil.which("findmnt"), reason="findmnt utility not available" + ) + @pytest.mark.skipif(GITHUB_ACTIONS, reason="unsupported on GITHUB_ACTIONS") + def test_against_findmnt(self): + psutil_value = RootFsDeviceFinder().find() + findmnt_value = sh("findmnt -o SOURCE -rn /") + assert psutil_value == findmnt_value + + def test_disk_partitions_mocked(self): + with mock.patch( + 'psutil._pslinux.cext.disk_partitions', + return_value=[('/dev/root', '/', 'ext4', 'rw')], + ) as m: + part = psutil.disk_partitions()[0] + assert m.called + if not GITHUB_ACTIONS: + assert part.device != "/dev/root" + assert part.device == RootFsDeviceFinder().find() + else: + assert part.device == "/dev/root" + + +# ===================================================================== +# --- misc +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestMisc(PsutilTestCase): + def test_boot_time(self): + vmstat_value = vmstat('boot time') + psutil_value = psutil.boot_time() + assert int(vmstat_value) == int(psutil_value) + + def test_no_procfs_on_import(self): + my_procfs = self.get_testfn() + os.mkdir(my_procfs) + + with open(os.path.join(my_procfs, 'stat'), 'w') as f: + f.write('cpu 0 0 0 0 0 0 0 0 0 0\n') + f.write('cpu0 0 0 0 0 0 0 0 0 0 0\n') + f.write('cpu1 0 0 0 0 0 0 0 0 0 0\n') + + try: + orig_open = open + + def open_mock(name, *args, **kwargs): + if name.startswith('/proc'): + raise FileNotFoundError + return orig_open(name, *args, **kwargs) + + with mock.patch("builtins.open", side_effect=open_mock): + reload_module(psutil) + + with pytest.raises(OSError): + psutil.cpu_times() + with pytest.raises(OSError): + psutil.cpu_times(percpu=True) + with pytest.raises(OSError): + psutil.cpu_percent() + with pytest.raises(OSError): + psutil.cpu_percent(percpu=True) + with pytest.raises(OSError): + psutil.cpu_times_percent() + with pytest.raises(OSError): + psutil.cpu_times_percent(percpu=True) + + psutil.PROCFS_PATH = my_procfs + + assert psutil.cpu_percent() == 0 + assert sum(psutil.cpu_times_percent()) == 0 + + # since we don't know the number of CPUs at import time, + # we awkwardly say there are none until the second call + per_cpu_percent = psutil.cpu_percent(percpu=True) + assert sum(per_cpu_percent) == 0 + + # ditto awkward length + per_cpu_times_percent = psutil.cpu_times_percent(percpu=True) + assert sum(map(sum, per_cpu_times_percent)) == 0 + + # much user, very busy + with open(os.path.join(my_procfs, 'stat'), 'w') as f: + f.write('cpu 1 0 0 0 0 0 0 0 0 0\n') + f.write('cpu0 1 0 0 0 0 0 0 0 0 0\n') + f.write('cpu1 1 0 0 0 0 0 0 0 0 0\n') + + assert psutil.cpu_percent() != 0 + assert sum(psutil.cpu_percent(percpu=True)) != 0 + assert sum(psutil.cpu_times_percent()) != 0 + assert ( + sum(map(sum, psutil.cpu_times_percent(percpu=True))) != 0 + ) + finally: + shutil.rmtree(my_procfs) + reload_module(psutil) + + assert psutil.PROCFS_PATH == '/proc' + + def test_cpu_steal_decrease(self): + # Test cumulative cpu stats decrease. We should ignore this. + # See issue #1210. + content = textwrap.dedent("""\ + cpu 0 0 0 0 0 0 0 1 0 0 + cpu0 0 0 0 0 0 0 0 1 0 0 + cpu1 0 0 0 0 0 0 0 1 0 0 + """).encode() + with mock_open_content({"/proc/stat": content}) as m: + # first call to "percent" functions should read the new stat file + # and compare to the "real" file read at import time - so the + # values are meaningless + psutil.cpu_percent() + assert m.called + psutil.cpu_percent(percpu=True) + psutil.cpu_times_percent() + psutil.cpu_times_percent(percpu=True) + + content = textwrap.dedent("""\ + cpu 1 0 0 0 0 0 0 0 0 0 + cpu0 1 0 0 0 0 0 0 0 0 0 + cpu1 1 0 0 0 0 0 0 0 0 0 + """).encode() + with mock_open_content({"/proc/stat": content}): + # Increase "user" while steal goes "backwards" to zero. + cpu_percent = psutil.cpu_percent() + assert m.called + cpu_percent_percpu = psutil.cpu_percent(percpu=True) + cpu_times_percent = psutil.cpu_times_percent() + cpu_times_percent_percpu = psutil.cpu_times_percent(percpu=True) + assert cpu_percent != 0 + assert sum(cpu_percent_percpu) != 0 + assert sum(cpu_times_percent) != 0 + assert sum(cpu_times_percent) != 100.0 + assert sum(map(sum, cpu_times_percent_percpu)) != 0 + assert sum(map(sum, cpu_times_percent_percpu)) != 100.0 + assert cpu_times_percent.steal == 0 + assert cpu_times_percent.user != 0 + + def test_boot_time_mocked(self): + with mock.patch('psutil._common.open', create=True) as m: + with pytest.raises(RuntimeError): + psutil._pslinux.boot_time() + assert m.called + + def test_users(self): + # Make sure the C extension converts ':0' and ':0.0' to + # 'localhost'. + for user in psutil.users(): + assert user.host not in {":0", ":0.0"} + + def test_procfs_path(self): + tdir = self.get_testfn() + os.mkdir(tdir) + try: + psutil.PROCFS_PATH = tdir + with pytest.raises(OSError): + psutil.virtual_memory() + with pytest.raises(OSError): + psutil.cpu_times() + with pytest.raises(OSError): + psutil.cpu_times(percpu=True) + with pytest.raises(OSError): + psutil.boot_time() + # self.assertRaises(OSError, psutil.pids) + with pytest.raises(OSError): + psutil.net_connections() + with pytest.raises(OSError): + psutil.net_io_counters() + with pytest.raises(OSError): + psutil.net_if_stats() + # self.assertRaises(OSError, psutil.disk_io_counters) + with pytest.raises(OSError): + psutil.disk_partitions() + with pytest.raises(psutil.NoSuchProcess): + psutil.Process() + finally: + psutil.PROCFS_PATH = "/proc" + + @retry_on_failure() + @pytest.mark.skipif(PYTEST_PARALLEL, reason="skip if pytest-parallel") + def test_issue_687(self): + # In case of thread ID: + # - pid_exists() is supposed to return False + # - Process(tid) is supposed to work + # - pids() should not return the TID + # See: https://github.com/giampaolo/psutil/issues/687 + with ThreadTask(): + p = psutil.Process() + threads = p.threads() + assert len(threads) == 2 + tid = sorted(threads, key=lambda x: x.id)[1].id + assert p.pid != tid + pt = psutil.Process(tid) + pt.as_dict() + assert tid not in psutil.pids() + + def test_pid_exists_no_proc_status(self): + # Internally pid_exists relies on /proc/{pid}/status. + # Emulate a case where this file is empty in which case + # psutil is supposed to fall back on using pids(). + with mock_open_content({"/proc/%s/status": ""}) as m: + assert psutil.pid_exists(os.getpid()) + assert m.called + + +# ===================================================================== +# --- sensors +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +@pytest.mark.skipif(not HAS_BATTERY, reason="no battery") +class TestSensorsBattery(PsutilTestCase): + @pytest.mark.skipif( + not shutil.which("acpi"), reason="acpi utility not available" + ) + def test_percent(self): + out = sh("acpi -b") + acpi_value = int(out.split(",")[1].strip().replace('%', '')) + psutil_value = psutil.sensors_battery().percent + assert abs(acpi_value - psutil_value) < 1 + + def test_emulate_power_plugged(self): + # Pretend the AC power cable is connected. + def open_mock(name, *args, **kwargs): + if name.endswith(('AC0/online', 'AC/online')): + return io.BytesIO(b"1") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock) as m: + assert psutil.sensors_battery().power_plugged is True + assert ( + psutil.sensors_battery().secsleft + == psutil.POWER_TIME_UNLIMITED + ) + assert m.called + + def test_emulate_power_plugged_2(self): + # Same as above but pretend /AC0/online does not exist in which + # case code relies on /status file. + def open_mock(name, *args, **kwargs): + if name.endswith(('AC0/online', 'AC/online')): + raise FileNotFoundError + if name.endswith("/status"): + return io.StringIO("charging") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock) as m: + assert psutil.sensors_battery().power_plugged is True + assert m.called + + def test_emulate_power_not_plugged(self): + # Pretend the AC power cable is not connected. + def open_mock(name, *args, **kwargs): + if name.endswith(('AC0/online', 'AC/online')): + return io.BytesIO(b"0") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock) as m: + assert psutil.sensors_battery().power_plugged is False + assert m.called + + def test_emulate_power_not_plugged_2(self): + # Same as above but pretend /AC0/online does not exist in which + # case code relies on /status file. + def open_mock(name, *args, **kwargs): + if name.endswith(('AC0/online', 'AC/online')): + raise FileNotFoundError + if name.endswith("/status"): + return io.StringIO("discharging") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock) as m: + assert psutil.sensors_battery().power_plugged is False + assert m.called + + def test_emulate_power_undetermined(self): + # Pretend we can't know whether the AC power cable not + # connected (assert fallback to False). + def open_mock(name, *args, **kwargs): + if name.startswith(( + '/sys/class/power_supply/AC0/online', + '/sys/class/power_supply/AC/online', + )): + raise FileNotFoundError + if name.startswith("/sys/class/power_supply/BAT0/status"): + return io.BytesIO(b"???") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock) as m: + assert psutil.sensors_battery().power_plugged is None + assert m.called + + def test_emulate_energy_full_0(self): + # Emulate a case where energy_full files returns 0. + with mock_open_content( + {"/sys/class/power_supply/BAT0/energy_full": b"0"} + ) as m: + assert psutil.sensors_battery().percent == 0 + assert m.called + + def test_emulate_energy_full_not_avail(self): + # Emulate a case where energy_full file does not exist. + # Expected fallback on /capacity. + with mock_open_exception( + "/sys/class/power_supply/BAT0/energy_full", + FileNotFoundError, + ): + with mock_open_exception( + "/sys/class/power_supply/BAT0/charge_full", + FileNotFoundError, + ): + with mock_open_content( + {"/sys/class/power_supply/BAT0/capacity": b"88"} + ): + assert psutil.sensors_battery().percent == 88 + + def test_emulate_no_power(self): + # Emulate a case where /AC0/online file nor /BAT0/status exist. + with mock_open_exception( + "/sys/class/power_supply/AC/online", FileNotFoundError + ): + with mock_open_exception( + "/sys/class/power_supply/AC0/online", FileNotFoundError + ): + with mock_open_exception( + "/sys/class/power_supply/BAT0/status", + FileNotFoundError, + ): + assert psutil.sensors_battery().power_plugged is None + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSensorsBatteryEmulated(PsutilTestCase): + def test_it(self): + def open_mock(name, *args, **kwargs): + if name.endswith("/energy_now"): + return io.StringIO("60000000") + elif name.endswith("/power_now"): + return io.StringIO("0") + elif name.endswith("/energy_full"): + return io.StringIO("60000001") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch('os.listdir', return_value=["BAT0"]) as mlistdir: + with mock.patch("builtins.open", side_effect=open_mock) as mopen: + assert psutil.sensors_battery() is not None + assert mlistdir.called + assert mopen.called + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSensorsTemperatures(PsutilTestCase): + def test_emulate_class_hwmon(self): + def open_mock(name, *args, **kwargs): + if name.endswith('/name'): + return io.StringIO("name") + elif name.endswith('/temp1_label'): + return io.StringIO("label") + elif name.endswith('/temp1_input'): + return io.BytesIO(b"30000") + elif name.endswith('/temp1_max'): + return io.BytesIO(b"40000") + elif name.endswith('/temp1_crit'): + return io.BytesIO(b"50000") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock): + # Test case with /sys/class/hwmon + with mock.patch( + 'glob.glob', return_value=['/sys/class/hwmon/hwmon0/temp1'] + ): + temp = psutil.sensors_temperatures()['name'][0] + assert temp.label == 'label' + assert temp.current == 30.0 + assert temp.high == 40.0 + assert temp.critical == 50.0 + + def test_emulate_class_thermal(self): + def open_mock(name, *args, **kwargs): + if name.endswith('0_temp'): + return io.BytesIO(b"50000") + elif name.endswith('temp'): + return io.BytesIO(b"30000") + elif name.endswith('0_type'): + return io.StringIO("critical") + elif name.endswith('type'): + return io.StringIO("name") + else: + return orig_open(name, *args, **kwargs) + + def glob_mock(path): + if path in { + '/sys/class/hwmon/hwmon*/temp*_*', + '/sys/class/hwmon/hwmon*/device/temp*_*', + }: + return [] + elif path == '/sys/class/thermal/thermal_zone*': + return ['/sys/class/thermal/thermal_zone0'] + elif path == '/sys/class/thermal/thermal_zone0/trip_point*': + return [ + '/sys/class/thermal/thermal_zone1/trip_point_0_type', + '/sys/class/thermal/thermal_zone1/trip_point_0_temp', + ] + return [] + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock): + with mock.patch('glob.glob', create=True, side_effect=glob_mock): + temp = psutil.sensors_temperatures()['name'][0] + assert temp.label == '' + assert temp.current == 30.0 + assert temp.high == 50.0 + assert temp.critical == 50.0 + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestSensorsFans(PsutilTestCase): + def test_emulate_data(self): + def open_mock(name, *args, **kwargs): + if name.endswith('/name'): + return io.StringIO("name") + elif name.endswith('/fan1_label'): + return io.StringIO("label") + elif name.endswith('/fan1_input'): + return io.StringIO("2000") + else: + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock): + with mock.patch( + 'glob.glob', return_value=['/sys/class/hwmon/hwmon2/fan1'] + ): + fan = psutil.sensors_fans()['name'][0] + assert fan.label == 'label' + assert fan.current == 2000 + + +# ===================================================================== +# --- test process +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestProcess(PsutilTestCase): + @retry_on_failure() + def test_parse_smaps_vs_memory_maps(self): + sproc = self.spawn_testproc() + uss, pss, swap = psutil._pslinux.Process(sproc.pid)._parse_smaps() + maps = psutil.Process(sproc.pid).memory_maps(grouped=False) + assert ( + abs(uss - sum(x.private_dirty + x.private_clean for x in maps)) + < 4096 + ) + assert abs(pss - sum(x.pss for x in maps)) < 4096 + assert abs(swap - sum(x.swap for x in maps)) < 4096 + + def test_parse_smaps_mocked(self): + # See: https://github.com/giampaolo/psutil/issues/1222 + content = textwrap.dedent("""\ + fffff0 r-xp 00000000 00:00 0 [vsyscall] + Size: 1 kB + Rss: 2 kB + Pss: 3 kB + Shared_Clean: 4 kB + Shared_Dirty: 5 kB + Private_Clean: 6 kB + Private_Dirty: 7 kB + Referenced: 8 kB + Anonymous: 9 kB + LazyFree: 10 kB + AnonHugePages: 11 kB + ShmemPmdMapped: 12 kB + Shared_Hugetlb: 13 kB + Private_Hugetlb: 14 kB + Swap: 15 kB + SwapPss: 16 kB + KernelPageSize: 17 kB + MMUPageSize: 18 kB + Locked: 19 kB + VmFlags: rd ex + """).encode() + with mock_open_content({f"/proc/{os.getpid()}/smaps": content}) as m: + p = psutil._pslinux.Process(os.getpid()) + uss, pss, swap = p._parse_smaps() + assert m.called + assert uss == (6 + 7 + 14) * 1024 + assert pss == 3 * 1024 + assert swap == 15 * 1024 + + # On PYPY file descriptors are not closed fast enough. + @pytest.mark.skipif(PYPY, reason="unreliable on PYPY") + def test_open_files_mode(self): + def get_test_file(fname): + p = psutil.Process() + giveup_at = time.time() + GLOBAL_TIMEOUT + while True: + for file in p.open_files(): + if file.path == os.path.abspath(fname): + return file + elif time.time() > giveup_at: + break + raise RuntimeError("timeout looking for test file") + + testfn = self.get_testfn() + with open(testfn, "w"): + assert get_test_file(testfn).mode == "w" + with open(testfn): + assert get_test_file(testfn).mode == "r" + with open(testfn, "a"): + assert get_test_file(testfn).mode == "a" + with open(testfn, "r+"): + assert get_test_file(testfn).mode == "r+" + with open(testfn, "w+"): + assert get_test_file(testfn).mode == "r+" + with open(testfn, "a+"): + assert get_test_file(testfn).mode == "a+" + + safe_rmpath(testfn) + with open(testfn, "x"): + assert get_test_file(testfn).mode == "w" + safe_rmpath(testfn) + with open(testfn, "x+"): + assert get_test_file(testfn).mode == "r+" + + def test_open_files_file_gone(self): + # simulates a file which gets deleted during open_files() + # execution + p = psutil.Process() + files = p.open_files() + with open(self.get_testfn(), 'w'): + # give the kernel some time to see the new file + call_until(lambda: len(p.open_files()) != len(files)) + with mock.patch( + 'psutil._pslinux.os.readlink', + side_effect=FileNotFoundError, + ) as m: + assert p.open_files() == [] + assert m.called + # also simulate the case where os.readlink() returns EINVAL + # in which case psutil is supposed to 'continue' + with mock.patch( + 'psutil._pslinux.os.readlink', + side_effect=OSError(errno.EINVAL, ""), + ) as m: + assert p.open_files() == [] + assert m.called + + def test_open_files_fd_gone(self): + # Simulate a case where /proc/{pid}/fdinfo/{fd} disappears + # while iterating through fds. + # https://travis-ci.org/giampaolo/psutil/jobs/225694530 + p = psutil.Process() + files = p.open_files() + with open(self.get_testfn(), 'w'): + # give the kernel some time to see the new file + call_until(lambda: len(p.open_files()) != len(files)) + with mock.patch( + "builtins.open", side_effect=FileNotFoundError + ) as m: + assert p.open_files() == [] + assert m.called + + def test_open_files_enametoolong(self): + # Simulate a case where /proc/{pid}/fd/{fd} symlink + # points to a file with full path longer than PATH_MAX, see: + # https://github.com/giampaolo/psutil/issues/1940 + p = psutil.Process() + files = p.open_files() + with open(self.get_testfn(), 'w'): + # give the kernel some time to see the new file + call_until(lambda: len(p.open_files()) != len(files)) + patch_point = 'psutil._pslinux.os.readlink' + with mock.patch( + patch_point, side_effect=OSError(errno.ENAMETOOLONG, "") + ) as m: + with mock.patch("psutil._pslinux.debug"): + assert p.open_files() == [] + assert m.called + + # --- mocked tests + + def test_terminal_mocked(self): + with mock.patch( + 'psutil._pslinux._psposix.get_terminal_map', return_value={} + ) as m: + assert psutil._pslinux.Process(os.getpid()).terminal() is None + assert m.called + + # TODO: re-enable this test. + # def test_num_ctx_switches_mocked(self): + # with mock.patch('psutil._common.open', create=True) as m: + # self.assertRaises( + # NotImplementedError, + # psutil._pslinux.Process(os.getpid()).num_ctx_switches) + # assert m.called + + def test_cmdline_mocked(self): + # see: https://github.com/giampaolo/psutil/issues/639 + p = psutil.Process() + fake_file = io.StringIO('foo\x00bar\x00') + with mock.patch( + 'psutil._common.open', return_value=fake_file, create=True + ) as m: + assert p.cmdline() == ['foo', 'bar'] + assert m.called + fake_file = io.StringIO('foo\x00bar\x00\x00') + with mock.patch( + 'psutil._common.open', return_value=fake_file, create=True + ) as m: + assert p.cmdline() == ['foo', 'bar', ''] + assert m.called + + def test_cmdline_spaces_mocked(self): + # see: https://github.com/giampaolo/psutil/issues/1179 + p = psutil.Process() + fake_file = io.StringIO('foo bar ') + with mock.patch( + 'psutil._common.open', return_value=fake_file, create=True + ) as m: + assert p.cmdline() == ['foo', 'bar'] + assert m.called + fake_file = io.StringIO('foo bar ') + with mock.patch( + 'psutil._common.open', return_value=fake_file, create=True + ) as m: + assert p.cmdline() == ['foo', 'bar', ''] + assert m.called + + def test_cmdline_mixed_separators(self): + # https://github.com/giampaolo/psutil/issues/ + # 1179#issuecomment-552984549 + p = psutil.Process() + fake_file = io.StringIO('foo\x20bar\x00') + with mock.patch( + 'psutil._common.open', return_value=fake_file, create=True + ) as m: + assert p.cmdline() == ['foo', 'bar'] + assert m.called + + def test_readlink_path_deleted_mocked(self): + with mock.patch( + 'psutil._pslinux.os.readlink', return_value='/home/foo (deleted)' + ): + assert psutil.Process().exe() == "/home/foo" + assert psutil.Process().cwd() == "/home/foo" + + def test_threads_mocked(self): + # Test the case where os.listdir() returns a file (thread) + # which no longer exists by the time we open() it (race + # condition). threads() is supposed to ignore that instead + # of raising NSP. + def open_mock_1(name, *args, **kwargs): + if name.startswith(f"/proc/{os.getpid()}/task"): + raise FileNotFoundError + return orig_open(name, *args, **kwargs) + + orig_open = open + with mock.patch("builtins.open", side_effect=open_mock_1) as m: + ret = psutil.Process().threads() + assert m.called + assert ret == [] + + # ...but if it bumps into something != ENOENT we want an + # exception. + def open_mock_2(name, *args, **kwargs): + if name.startswith(f"/proc/{os.getpid()}/task"): + raise PermissionError + return orig_open(name, *args, **kwargs) + + with mock.patch("builtins.open", side_effect=open_mock_2): + with pytest.raises(psutil.AccessDenied): + psutil.Process().threads() + + def test_exe_mocked(self): + with mock.patch( + 'psutil._pslinux.readlink', side_effect=FileNotFoundError + ) as m: + # de-activate guessing from cmdline() + with mock.patch( + 'psutil._pslinux.Process.cmdline', return_value=[] + ): + ret = psutil.Process().exe() + assert m.called + assert ret == "" + + def test_issue_1014(self): + # Emulates a case where smaps file does not exist. In this case + # wrap_exception decorator should not raise NoSuchProcess. + with mock_open_exception( + f"/proc/{os.getpid()}/smaps", FileNotFoundError + ) as m: + p = psutil.Process() + with pytest.raises(FileNotFoundError): + p.memory_maps() + assert m.called + + def test_issue_2418(self): + p = psutil.Process() + with mock_open_exception( + f"/proc/{os.getpid()}/statm", FileNotFoundError + ): + with mock.patch("os.path.exists", return_value=False): + with pytest.raises(psutil.NoSuchProcess): + p.memory_info() + + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit_zombie(self): + # Emulate a case where rlimit() raises ENOSYS, which may + # happen in case of zombie process: + # https://travis-ci.org/giampaolo/psutil/jobs/51368273 + with mock.patch( + "resource.prlimit", side_effect=OSError(errno.ENOSYS, "") + ) as m1: + with mock.patch( + "psutil._pslinux.Process._is_zombie", return_value=True + ) as m2: + p = psutil.Process() + p.name() + with pytest.raises(psutil.ZombieProcess) as cm: + p.rlimit(psutil.RLIMIT_NOFILE) + assert m1.called + assert m2.called + assert cm.value.pid == p.pid + assert cm.value.name == p.name() + + def test_stat_file_parsing(self): + args = [ + "0", # pid + "(cat)", # name + "Z", # status + "1", # ppid + "0", # pgrp + "0", # session + "0", # tty + "0", # tpgid + "0", # flags + "0", # minflt + "0", # cminflt + "0", # majflt + "0", # cmajflt + "2", # utime + "3", # stime + "4", # cutime + "5", # cstime + "0", # priority + "0", # nice + "0", # num_threads + "0", # itrealvalue + "6", # starttime + "0", # vsize + "0", # rss + "0", # rsslim + "0", # startcode + "0", # endcode + "0", # startstack + "0", # kstkesp + "0", # kstkeip + "0", # signal + "0", # blocked + "0", # sigignore + "0", # sigcatch + "0", # wchan + "0", # nswap + "0", # cnswap + "0", # exit_signal + "6", # processor + "0", # rt priority + "0", # policy + "7", # delayacct_blkio_ticks + ] + content = " ".join(args).encode() + with mock_open_content({f"/proc/{os.getpid()}/stat": content}): + p = psutil.Process() + assert p.name() == 'cat' + assert p.status() == psutil.STATUS_ZOMBIE + assert p.ppid() == 1 + assert p.create_time() == 6 / CLOCK_TICKS + psutil.boot_time() + cpu = p.cpu_times() + assert cpu.user == 2 / CLOCK_TICKS + assert cpu.system == 3 / CLOCK_TICKS + assert cpu.children_user == 4 / CLOCK_TICKS + assert cpu.children_system == 5 / CLOCK_TICKS + assert cpu.iowait == 7 / CLOCK_TICKS + assert p.cpu_num() == 6 + + def test_status_file_parsing(self): + content = textwrap.dedent("""\ + Uid:\t1000\t1001\t1002\t1003 + Gid:\t1004\t1005\t1006\t1007 + Threads:\t66 + Cpus_allowed:\tf + Cpus_allowed_list:\t0-7 + voluntary_ctxt_switches:\t12 + nonvoluntary_ctxt_switches:\t13""").encode() + with mock_open_content({f"/proc/{os.getpid()}/status": content}): + p = psutil.Process() + assert p.num_ctx_switches().voluntary == 12 + assert p.num_ctx_switches().involuntary == 13 + assert p.num_threads() == 66 + uids = p.uids() + assert uids.real == 1000 + assert uids.effective == 1001 + assert uids.saved == 1002 + gids = p.gids() + assert gids.real == 1004 + assert gids.effective == 1005 + assert gids.saved == 1006 + assert p._proc._get_eligible_cpus() == list(range(8)) + + def test_net_connections_enametoolong(self): + # Simulate a case where /proc/{pid}/fd/{fd} symlink points to + # a file with full path longer than PATH_MAX, see: + # https://github.com/giampaolo/psutil/issues/1940 + with mock.patch( + 'psutil._pslinux.os.readlink', + side_effect=OSError(errno.ENAMETOOLONG, ""), + ) as m: + p = psutil.Process() + with mock.patch("psutil._pslinux.debug"): + assert p.net_connections() == [] + assert m.called + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestProcessAgainstStatus(PsutilTestCase): + """/proc/pid/stat and /proc/pid/status have many values in common. + Whenever possible, psutil uses /proc/pid/stat (it's faster). + For all those cases we check that the value found in + /proc/pid/stat (by psutil) matches the one found in + /proc/pid/status. + """ + + @classmethod + def setUpClass(cls): + cls.proc = psutil.Process() + + def read_status_file(self, linestart): + with psutil._psplatform.open_text( + f"/proc/{self.proc.pid}/status" + ) as f: + for line in f: + line = line.strip() + if line.startswith(linestart): + value = line.partition('\t')[2] + try: + return int(value) + except ValueError: + return value + raise ValueError(f"can't find {linestart!r}") + + def test_name(self): + value = self.read_status_file("Name:") + assert self.proc.name() == value + + def test_status(self): + value = self.read_status_file("State:") + value = value[value.find('(') + 1 : value.rfind(')')] + value = value.replace(' ', '-') + assert self.proc.status() == value + + def test_ppid(self): + value = self.read_status_file("PPid:") + assert self.proc.ppid() == value + + def test_num_threads(self): + value = self.read_status_file("Threads:") + assert self.proc.num_threads() == value + + def test_uids(self): + value = self.read_status_file("Uid:") + value = tuple(map(int, value.split()[1:4])) + assert self.proc.uids() == value + + def test_gids(self): + value = self.read_status_file("Gid:") + value = tuple(map(int, value.split()[1:4])) + assert self.proc.gids() == value + + @retry_on_failure() + def test_num_ctx_switches(self): + value = self.read_status_file("voluntary_ctxt_switches:") + assert self.proc.num_ctx_switches().voluntary == value + value = self.read_status_file("nonvoluntary_ctxt_switches:") + assert self.proc.num_ctx_switches().involuntary == value + + def test_cpu_affinity(self): + value = self.read_status_file("Cpus_allowed_list:") + if '-' in str(value): + min_, max_ = map(int, value.split('-')) + assert self.proc.cpu_affinity() == list(range(min_, max_ + 1)) + + def test_cpu_affinity_eligible_cpus(self): + value = self.read_status_file("Cpus_allowed_list:") + with mock.patch("psutil._pslinux.per_cpu_times") as m: + self.proc._proc._get_eligible_cpus() + if '-' in str(value): + assert not m.called + else: + assert m.called + + +# ===================================================================== +# --- test utils +# ===================================================================== + + +@pytest.mark.skipif(not LINUX, reason="LINUX only") +class TestUtils(PsutilTestCase): + def test_readlink(self): + with mock.patch("os.readlink", return_value="foo (deleted)") as m: + assert psutil._psplatform.readlink("bar") == "foo" + assert m.called diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_memleaks.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_memleaks.py new file mode 100644 index 0000000..7f78fae --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_memleaks.py @@ -0,0 +1,487 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Tests for detecting function memory leaks (typically the ones +implemented in C). It does so by calling a function many times and +checking whether process memory usage keeps increasing between +calls or over time. +Note that this may produce false positives (especially on Windows +for some reason). +PyPy appears to be completely unstable for this framework, probably +because of how its JIT handles memory, so tests are skipped. +""" + + +import functools +import os +import platform + +import psutil +import psutil._common +from psutil import LINUX +from psutil import MACOS +from psutil import OPENBSD +from psutil import POSIX +from psutil import SUNOS +from psutil import WINDOWS +from psutil.tests import HAS_CPU_AFFINITY +from psutil.tests import HAS_CPU_FREQ +from psutil.tests import HAS_ENVIRON +from psutil.tests import HAS_IONICE +from psutil.tests import HAS_MEMORY_MAPS +from psutil.tests import HAS_NET_IO_COUNTERS +from psutil.tests import HAS_PROC_CPU_NUM +from psutil.tests import HAS_PROC_IO_COUNTERS +from psutil.tests import HAS_RLIMIT +from psutil.tests import HAS_SENSORS_BATTERY +from psutil.tests import HAS_SENSORS_FANS +from psutil.tests import HAS_SENSORS_TEMPERATURES +from psutil.tests import TestMemoryLeak +from psutil.tests import create_sockets +from psutil.tests import get_testfn +from psutil.tests import process_namespace +from psutil.tests import pytest +from psutil.tests import skip_on_access_denied +from psutil.tests import spawn_testproc +from psutil.tests import system_namespace +from psutil.tests import terminate + + +cext = psutil._psplatform.cext +thisproc = psutil.Process() +FEW_TIMES = 5 + + +def fewtimes_if_linux(): + """Decorator for those Linux functions which are implemented in pure + Python, and which we want to run faster. + """ + + def decorator(fun): + @functools.wraps(fun) + def wrapper(self, *args, **kwargs): + if LINUX: + before = self.__class__.times + try: + self.__class__.times = FEW_TIMES + return fun(self, *args, **kwargs) + finally: + self.__class__.times = before + else: + return fun(self, *args, **kwargs) + + return wrapper + + return decorator + + +# =================================================================== +# Process class +# =================================================================== + + +class TestProcessObjectLeaks(TestMemoryLeak): + """Test leaks of Process class methods.""" + + proc = thisproc + + def test_coverage(self): + ns = process_namespace(None) + ns.test_class_coverage(self, ns.getters + ns.setters) + + @fewtimes_if_linux() + def test_name(self): + self.execute(self.proc.name) + + @fewtimes_if_linux() + def test_cmdline(self): + self.execute(self.proc.cmdline) + + @fewtimes_if_linux() + def test_exe(self): + self.execute(self.proc.exe) + + @fewtimes_if_linux() + def test_ppid(self): + self.execute(self.proc.ppid) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + @fewtimes_if_linux() + def test_uids(self): + self.execute(self.proc.uids) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + @fewtimes_if_linux() + def test_gids(self): + self.execute(self.proc.gids) + + @fewtimes_if_linux() + def test_status(self): + self.execute(self.proc.status) + + def test_nice(self): + self.execute(self.proc.nice) + + def test_nice_set(self): + niceness = thisproc.nice() + self.execute(lambda: self.proc.nice(niceness)) + + @pytest.mark.skipif(not HAS_IONICE, reason="not supported") + def test_ionice(self): + self.execute(self.proc.ionice) + + @pytest.mark.skipif(not HAS_IONICE, reason="not supported") + def test_ionice_set(self): + if WINDOWS: + value = thisproc.ionice() + self.execute(lambda: self.proc.ionice(value)) + else: + self.execute(lambda: self.proc.ionice(psutil.IOPRIO_CLASS_NONE)) + fun = functools.partial(cext.proc_ioprio_set, os.getpid(), -1, 0) + self.execute_w_exc(OSError, fun) + + @pytest.mark.skipif(not HAS_PROC_IO_COUNTERS, reason="not supported") + @fewtimes_if_linux() + def test_io_counters(self): + self.execute(self.proc.io_counters) + + @pytest.mark.skipif(POSIX, reason="worthless on POSIX") + def test_username(self): + # always open 1 handle on Windows (only once) + psutil.Process().username() + self.execute(self.proc.username) + + @fewtimes_if_linux() + def test_create_time(self): + self.execute(self.proc.create_time) + + @fewtimes_if_linux() + @skip_on_access_denied(only_if=OPENBSD) + def test_num_threads(self): + self.execute(self.proc.num_threads) + + @pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") + def test_num_handles(self): + self.execute(self.proc.num_handles) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + @fewtimes_if_linux() + def test_num_fds(self): + self.execute(self.proc.num_fds) + + @fewtimes_if_linux() + def test_num_ctx_switches(self): + self.execute(self.proc.num_ctx_switches) + + @fewtimes_if_linux() + @skip_on_access_denied(only_if=OPENBSD) + def test_threads(self): + self.execute(self.proc.threads) + + @fewtimes_if_linux() + def test_cpu_times(self): + self.execute(self.proc.cpu_times) + + @fewtimes_if_linux() + @pytest.mark.skipif(not HAS_PROC_CPU_NUM, reason="not supported") + def test_cpu_num(self): + self.execute(self.proc.cpu_num) + + @fewtimes_if_linux() + def test_memory_info(self): + self.execute(self.proc.memory_info) + + @fewtimes_if_linux() + def test_memory_full_info(self): + self.execute(self.proc.memory_full_info) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + @fewtimes_if_linux() + def test_terminal(self): + self.execute(self.proc.terminal) + + def test_resume(self): + times = FEW_TIMES if POSIX else self.times + self.execute(self.proc.resume, times=times) + + @fewtimes_if_linux() + def test_cwd(self): + self.execute(self.proc.cwd) + + @pytest.mark.skipif(not HAS_CPU_AFFINITY, reason="not supported") + def test_cpu_affinity(self): + self.execute(self.proc.cpu_affinity) + + @pytest.mark.skipif(not HAS_CPU_AFFINITY, reason="not supported") + def test_cpu_affinity_set(self): + affinity = thisproc.cpu_affinity() + self.execute(lambda: self.proc.cpu_affinity(affinity)) + self.execute_w_exc(ValueError, lambda: self.proc.cpu_affinity([-1])) + + @fewtimes_if_linux() + def test_open_files(self): + with open(get_testfn(), 'w'): + self.execute(self.proc.open_files) + + @pytest.mark.skipif(not HAS_MEMORY_MAPS, reason="not supported") + @fewtimes_if_linux() + def test_memory_maps(self): + self.execute(self.proc.memory_maps) + + @pytest.mark.skipif(not LINUX, reason="LINUX only") + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit(self): + self.execute(lambda: self.proc.rlimit(psutil.RLIMIT_NOFILE)) + + @pytest.mark.skipif(not LINUX, reason="LINUX only") + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit_set(self): + limit = thisproc.rlimit(psutil.RLIMIT_NOFILE) + self.execute(lambda: self.proc.rlimit(psutil.RLIMIT_NOFILE, limit)) + self.execute_w_exc((OSError, ValueError), lambda: self.proc.rlimit(-1)) + + @fewtimes_if_linux() + # Windows implementation is based on a single system-wide + # function (tested later). + @pytest.mark.skipif(WINDOWS, reason="worthless on WINDOWS") + def test_net_connections(self): + # TODO: UNIX sockets are temporarily implemented by parsing + # 'pfiles' cmd output; we don't want that part of the code to + # be executed. + with create_sockets(): + kind = 'inet' if SUNOS else 'all' + self.execute(lambda: self.proc.net_connections(kind)) + + @pytest.mark.skipif(not HAS_ENVIRON, reason="not supported") + def test_environ(self): + self.execute(self.proc.environ) + + @pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") + def test_proc_info(self): + self.execute(lambda: cext.proc_info(os.getpid())) + + +class TestTerminatedProcessLeaks(TestProcessObjectLeaks): + """Repeat the tests above looking for leaks occurring when dealing + with terminated processes raising NoSuchProcess exception. + The C functions are still invoked but will follow different code + paths. We'll check those code paths. + """ + + @classmethod + def setUpClass(cls): + super().setUpClass() + cls.subp = spawn_testproc() + cls.proc = psutil.Process(cls.subp.pid) + cls.proc.kill() + cls.proc.wait() + + @classmethod + def tearDownClass(cls): + super().tearDownClass() + terminate(cls.subp) + + def call(self, fun): + try: + fun() + except psutil.NoSuchProcess: + pass + + if WINDOWS: + + def test_kill(self): + self.execute(self.proc.kill) + + def test_terminate(self): + self.execute(self.proc.terminate) + + def test_suspend(self): + self.execute(self.proc.suspend) + + def test_resume(self): + self.execute(self.proc.resume) + + def test_wait(self): + self.execute(self.proc.wait) + + def test_proc_info(self): + # test dual implementation + def call(): + try: + return cext.proc_info(self.proc.pid) + except ProcessLookupError: + pass + + self.execute(call) + + +@pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") +class TestProcessDualImplementation(TestMemoryLeak): + def test_cmdline_peb_true(self): + self.execute(lambda: cext.proc_cmdline(os.getpid(), use_peb=True)) + + def test_cmdline_peb_false(self): + self.execute(lambda: cext.proc_cmdline(os.getpid(), use_peb=False)) + + +# =================================================================== +# system APIs +# =================================================================== + + +class TestModuleFunctionsLeaks(TestMemoryLeak): + """Test leaks of psutil module functions.""" + + def test_coverage(self): + ns = system_namespace() + ns.test_class_coverage(self, ns.all) + + # --- cpu + + @fewtimes_if_linux() + def test_cpu_count(self): # logical + self.execute(lambda: psutil.cpu_count(logical=True)) + + @fewtimes_if_linux() + def test_cpu_count_cores(self): + self.execute(lambda: psutil.cpu_count(logical=False)) + + @fewtimes_if_linux() + def test_cpu_times(self): + self.execute(psutil.cpu_times) + + @fewtimes_if_linux() + def test_per_cpu_times(self): + self.execute(lambda: psutil.cpu_times(percpu=True)) + + @fewtimes_if_linux() + def test_cpu_stats(self): + self.execute(psutil.cpu_stats) + + @fewtimes_if_linux() + # TODO: remove this once 1892 is fixed + @pytest.mark.skipif( + MACOS and platform.machine() == 'arm64', reason="skipped due to #1892" + ) + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + def test_cpu_freq(self): + self.execute(psutil.cpu_freq) + + @pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") + def test_getloadavg(self): + psutil.getloadavg() + self.execute(psutil.getloadavg) + + # --- mem + + def test_virtual_memory(self): + self.execute(psutil.virtual_memory) + + # TODO: remove this skip when this gets fixed + @pytest.mark.skipif(SUNOS, reason="worthless on SUNOS (uses a subprocess)") + def test_swap_memory(self): + self.execute(psutil.swap_memory) + + def test_pid_exists(self): + times = FEW_TIMES if POSIX else self.times + self.execute(lambda: psutil.pid_exists(os.getpid()), times=times) + + # --- disk + + def test_disk_usage(self): + times = FEW_TIMES if POSIX else self.times + self.execute(lambda: psutil.disk_usage('.'), times=times) + + def test_disk_partitions(self): + self.execute(psutil.disk_partitions) + + @pytest.mark.skipif( + LINUX and not os.path.exists('/proc/diskstats'), + reason="/proc/diskstats not available on this Linux version", + ) + @fewtimes_if_linux() + def test_disk_io_counters(self): + self.execute(lambda: psutil.disk_io_counters(nowrap=False)) + + # --- proc + + @fewtimes_if_linux() + def test_pids(self): + self.execute(psutil.pids) + + # --- net + + @fewtimes_if_linux() + @pytest.mark.skipif(not HAS_NET_IO_COUNTERS, reason="not supported") + def test_net_io_counters(self): + self.execute(lambda: psutil.net_io_counters(nowrap=False)) + + @fewtimes_if_linux() + @pytest.mark.skipif(MACOS and os.getuid() != 0, reason="need root access") + def test_net_connections(self): + # always opens and handle on Windows() (once) + psutil.net_connections(kind='all') + with create_sockets(): + self.execute(lambda: psutil.net_connections(kind='all')) + + def test_net_if_addrs(self): + # Note: verified that on Windows this was a false positive. + tolerance = 80 * 1024 if WINDOWS else self.tolerance + self.execute(psutil.net_if_addrs, tolerance=tolerance) + + def test_net_if_stats(self): + self.execute(psutil.net_if_stats) + + # --- sensors + + @fewtimes_if_linux() + @pytest.mark.skipif(not HAS_SENSORS_BATTERY, reason="not supported") + def test_sensors_battery(self): + self.execute(psutil.sensors_battery) + + @fewtimes_if_linux() + @pytest.mark.skipif(not HAS_SENSORS_TEMPERATURES, reason="not supported") + def test_sensors_temperatures(self): + self.execute(psutil.sensors_temperatures) + + @fewtimes_if_linux() + @pytest.mark.skipif(not HAS_SENSORS_FANS, reason="not supported") + def test_sensors_fans(self): + self.execute(psutil.sensors_fans) + + # --- others + + @fewtimes_if_linux() + def test_boot_time(self): + self.execute(psutil.boot_time) + + def test_users(self): + self.execute(psutil.users) + + def test_set_debug(self): + self.execute(lambda: psutil._set_debug(False)) + + if WINDOWS: + + # --- win services + + def test_win_service_iter(self): + self.execute(cext.winservice_enumerate) + + def test_win_service_get(self): + pass + + def test_win_service_get_config(self): + name = next(psutil.win_service_iter()).name() + self.execute(lambda: cext.winservice_query_config(name)) + + def test_win_service_get_status(self): + name = next(psutil.win_service_iter()).name() + self.execute(lambda: cext.winservice_query_status(name)) + + def test_win_service_get_description(self): + name = next(psutil.win_service_iter()).name() + self.execute(lambda: cext.winservice_query_descr(name)) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_misc.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_misc.py new file mode 100644 index 0000000..c484264 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_misc.py @@ -0,0 +1,873 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Miscellaneous tests.""" + +import collections +import contextlib +import io +import json +import os +import pickle +import socket +import sys +from unittest import mock + +import psutil +import psutil.tests +from psutil import WINDOWS +from psutil._common import bcat +from psutil._common import cat +from psutil._common import debug +from psutil._common import isfile_strict +from psutil._common import memoize +from psutil._common import memoize_when_activated +from psutil._common import parse_environ_block +from psutil._common import supports_ipv6 +from psutil._common import wrap_numbers +from psutil.tests import HAS_NET_IO_COUNTERS +from psutil.tests import PsutilTestCase +from psutil.tests import process_namespace +from psutil.tests import pytest +from psutil.tests import reload_module +from psutil.tests import system_namespace + + +# =================================================================== +# --- Test classes' repr(), str(), ... +# =================================================================== + + +class TestSpecialMethods(PsutilTestCase): + def test_check_pid_range(self): + with pytest.raises(OverflowError): + psutil._psplatform.cext.check_pid_range(2**128) + with pytest.raises(psutil.NoSuchProcess): + psutil.Process(2**128) + + def test_process__repr__(self, func=repr): + p = psutil.Process(self.spawn_testproc().pid) + r = func(p) + assert "psutil.Process" in r + assert f"pid={p.pid}" in r + assert f"name='{p.name()}'" in r.replace("name=u'", "name='") + assert "status=" in r + assert "exitcode=" not in r + p.terminate() + p.wait() + r = func(p) + assert "status='terminated'" in r + assert "exitcode=" in r + + with mock.patch.object( + psutil.Process, + "name", + side_effect=psutil.ZombieProcess(os.getpid()), + ): + p = psutil.Process() + r = func(p) + assert f"pid={p.pid}" in r + assert "status='zombie'" in r + assert "name=" not in r + with mock.patch.object( + psutil.Process, + "name", + side_effect=psutil.NoSuchProcess(os.getpid()), + ): + p = psutil.Process() + r = func(p) + assert f"pid={p.pid}" in r + assert "terminated" in r + assert "name=" not in r + with mock.patch.object( + psutil.Process, + "name", + side_effect=psutil.AccessDenied(os.getpid()), + ): + p = psutil.Process() + r = func(p) + assert f"pid={p.pid}" in r + assert "name=" not in r + + def test_process__str__(self): + self.test_process__repr__(func=str) + + def test_error__repr__(self): + assert repr(psutil.Error()) == "psutil.Error()" + + def test_error__str__(self): + assert str(psutil.Error()) == "" + + def test_no_such_process__repr__(self): + assert ( + repr(psutil.NoSuchProcess(321)) + == "psutil.NoSuchProcess(pid=321, msg='process no longer exists')" + ) + assert ( + repr(psutil.NoSuchProcess(321, name="name", msg="msg")) + == "psutil.NoSuchProcess(pid=321, name='name', msg='msg')" + ) + + def test_no_such_process__str__(self): + assert ( + str(psutil.NoSuchProcess(321)) + == "process no longer exists (pid=321)" + ) + assert ( + str(psutil.NoSuchProcess(321, name="name", msg="msg")) + == "msg (pid=321, name='name')" + ) + + def test_zombie_process__repr__(self): + assert ( + repr(psutil.ZombieProcess(321)) + == 'psutil.ZombieProcess(pid=321, msg="PID still ' + 'exists but it\'s a zombie")' + ) + assert ( + repr(psutil.ZombieProcess(321, name="name", ppid=320, msg="foo")) + == "psutil.ZombieProcess(pid=321, ppid=320, name='name'," + " msg='foo')" + ) + + def test_zombie_process__str__(self): + assert ( + str(psutil.ZombieProcess(321)) + == "PID still exists but it's a zombie (pid=321)" + ) + assert ( + str(psutil.ZombieProcess(321, name="name", ppid=320, msg="foo")) + == "foo (pid=321, ppid=320, name='name')" + ) + + def test_access_denied__repr__(self): + assert repr(psutil.AccessDenied(321)) == "psutil.AccessDenied(pid=321)" + assert ( + repr(psutil.AccessDenied(321, name="name", msg="msg")) + == "psutil.AccessDenied(pid=321, name='name', msg='msg')" + ) + + def test_access_denied__str__(self): + assert str(psutil.AccessDenied(321)) == "(pid=321)" + assert ( + str(psutil.AccessDenied(321, name="name", msg="msg")) + == "msg (pid=321, name='name')" + ) + + def test_timeout_expired__repr__(self): + assert ( + repr(psutil.TimeoutExpired(5)) + == "psutil.TimeoutExpired(seconds=5, msg='timeout after 5" + " seconds')" + ) + assert ( + repr(psutil.TimeoutExpired(5, pid=321, name="name")) + == "psutil.TimeoutExpired(pid=321, name='name', seconds=5, " + "msg='timeout after 5 seconds')" + ) + + def test_timeout_expired__str__(self): + assert str(psutil.TimeoutExpired(5)) == "timeout after 5 seconds" + assert ( + str(psutil.TimeoutExpired(5, pid=321, name="name")) + == "timeout after 5 seconds (pid=321, name='name')" + ) + + def test_process__eq__(self): + p1 = psutil.Process() + p2 = psutil.Process() + assert p1 == p2 + p2._ident = (0, 0) + assert p1 != p2 + assert p1 != 'foo' + + def test_process__hash__(self): + s = {psutil.Process(), psutil.Process()} + assert len(s) == 1 + + +# =================================================================== +# --- Misc, generic, corner cases +# =================================================================== + + +class TestMisc(PsutilTestCase): + def test__all__(self): + dir_psutil = dir(psutil) + for name in dir_psutil: + if name in { + 'debug', + 'tests', + 'test', + 'PermissionError', + 'ProcessLookupError', + }: + continue + if not name.startswith('_'): + try: + __import__(name) + except ImportError: + if name not in psutil.__all__: + fun = getattr(psutil, name) + if fun is None: + continue + if ( + fun.__doc__ is not None + and 'deprecated' not in fun.__doc__.lower() + ): + raise self.fail(f"{name!r} not in psutil.__all__") + + # Import 'star' will break if __all__ is inconsistent, see: + # https://github.com/giampaolo/psutil/issues/656 + # Can't do `from psutil import *` as it won't work + # so we simply iterate over __all__. + for name in psutil.__all__: + assert name in dir_psutil + + def test_version(self): + assert ( + '.'.join([str(x) for x in psutil.version_info]) + == psutil.__version__ + ) + + def test_process_as_dict_no_new_names(self): + # See https://github.com/giampaolo/psutil/issues/813 + p = psutil.Process() + p.foo = '1' + assert 'foo' not in p.as_dict() + + def test_serialization(self): + def check(ret): + json.loads(json.dumps(ret)) + + a = pickle.dumps(ret) + b = pickle.loads(a) + assert ret == b + + # --- process APIs + + proc = psutil.Process() + check(psutil.Process().as_dict()) + + ns = process_namespace(proc) + for fun, name in ns.iter(ns.getters, clear_cache=True): + with self.subTest(proc=proc, name=name): + try: + ret = fun() + except psutil.Error: + pass + else: + check(ret) + + # --- system APIs + + ns = system_namespace() + for fun, name in ns.iter(ns.getters): + if name in {"win_service_iter", "win_service_get"}: + continue + with self.subTest(name=name): + try: + ret = fun() + except psutil.AccessDenied: + pass + else: + check(ret) + + # --- exception classes + + b = pickle.loads( + pickle.dumps( + psutil.NoSuchProcess(pid=4567, name='name', msg='msg') + ) + ) + assert isinstance(b, psutil.NoSuchProcess) + assert b.pid == 4567 + assert b.name == 'name' + assert b.msg == 'msg' + + b = pickle.loads( + pickle.dumps( + psutil.ZombieProcess(pid=4567, name='name', ppid=42, msg='msg') + ) + ) + assert isinstance(b, psutil.ZombieProcess) + assert b.pid == 4567 + assert b.ppid == 42 + assert b.name == 'name' + assert b.msg == 'msg' + + b = pickle.loads( + pickle.dumps(psutil.AccessDenied(pid=123, name='name', msg='msg')) + ) + assert isinstance(b, psutil.AccessDenied) + assert b.pid == 123 + assert b.name == 'name' + assert b.msg == 'msg' + + b = pickle.loads( + pickle.dumps( + psutil.TimeoutExpired(seconds=33, pid=4567, name='name') + ) + ) + assert isinstance(b, psutil.TimeoutExpired) + assert b.seconds == 33 + assert b.pid == 4567 + assert b.name == 'name' + + def test_ad_on_process_creation(self): + # We are supposed to be able to instantiate Process also in case + # of zombie processes or access denied. + with mock.patch.object( + psutil.Process, '_get_ident', side_effect=psutil.AccessDenied + ) as meth: + psutil.Process() + assert meth.called + + with mock.patch.object( + psutil.Process, '_get_ident', side_effect=psutil.ZombieProcess(1) + ) as meth: + psutil.Process() + assert meth.called + + with mock.patch.object( + psutil.Process, '_get_ident', side_effect=ValueError + ) as meth: + with pytest.raises(ValueError): + psutil.Process() + assert meth.called + + with mock.patch.object( + psutil.Process, '_get_ident', side_effect=psutil.NoSuchProcess(1) + ) as meth: + with self.assertRaises(psutil.NoSuchProcess): + psutil.Process() + assert meth.called + + def test_sanity_version_check(self): + # see: https://github.com/giampaolo/psutil/issues/564 + with mock.patch( + "psutil._psplatform.cext.version", return_value="0.0.0" + ): + with pytest.raises(ImportError) as cm: + reload_module(psutil) + assert "version conflict" in str(cm.value).lower() + + +# =================================================================== +# --- psutil/_common.py utils +# =================================================================== + + +class TestMemoizeDecorator(PsutilTestCase): + def setUp(self): + self.calls = [] + + tearDown = setUp + + def run_against(self, obj, expected_retval=None): + # no args + for _ in range(2): + ret = obj() + assert self.calls == [((), {})] + if expected_retval is not None: + assert ret == expected_retval + # with args + for _ in range(2): + ret = obj(1) + assert self.calls == [((), {}), ((1,), {})] + if expected_retval is not None: + assert ret == expected_retval + # with args + kwargs + for _ in range(2): + ret = obj(1, bar=2) + assert self.calls == [((), {}), ((1,), {}), ((1,), {'bar': 2})] + if expected_retval is not None: + assert ret == expected_retval + # clear cache + assert len(self.calls) == 3 + obj.cache_clear() + ret = obj() + if expected_retval is not None: + assert ret == expected_retval + assert len(self.calls) == 4 + # docstring + assert obj.__doc__ == "My docstring." + + def test_function(self): + @memoize + def foo(*args, **kwargs): + """My docstring.""" + baseclass.calls.append((args, kwargs)) + return 22 + + baseclass = self + self.run_against(foo, expected_retval=22) + + def test_class(self): + @memoize + class Foo: + """My docstring.""" + + def __init__(self, *args, **kwargs): + baseclass.calls.append((args, kwargs)) + + def bar(self): + return 22 + + baseclass = self + self.run_against(Foo, expected_retval=None) + assert Foo().bar() == 22 + + def test_class_singleton(self): + # @memoize can be used against classes to create singletons + @memoize + class Bar: + def __init__(self, *args, **kwargs): + pass + + assert Bar() is Bar() + assert id(Bar()) == id(Bar()) + assert id(Bar(1)) == id(Bar(1)) + assert id(Bar(1, foo=3)) == id(Bar(1, foo=3)) + assert id(Bar(1)) != id(Bar(2)) + + def test_staticmethod(self): + class Foo: + @staticmethod + @memoize + def bar(*args, **kwargs): + """My docstring.""" + baseclass.calls.append((args, kwargs)) + return 22 + + baseclass = self + self.run_against(Foo().bar, expected_retval=22) + + def test_classmethod(self): + class Foo: + @classmethod + @memoize + def bar(cls, *args, **kwargs): + """My docstring.""" + baseclass.calls.append((args, kwargs)) + return 22 + + baseclass = self + self.run_against(Foo().bar, expected_retval=22) + + def test_original(self): + # This was the original test before I made it dynamic to test it + # against different types. Keeping it anyway. + @memoize + def foo(*args, **kwargs): + """Foo docstring.""" + calls.append(None) + return (args, kwargs) + + calls = [] + # no args + for _ in range(2): + ret = foo() + expected = ((), {}) + assert ret == expected + assert len(calls) == 1 + # with args + for _ in range(2): + ret = foo(1) + expected = ((1,), {}) + assert ret == expected + assert len(calls) == 2 + # with args + kwargs + for _ in range(2): + ret = foo(1, bar=2) + expected = ((1,), {'bar': 2}) + assert ret == expected + assert len(calls) == 3 + # clear cache + foo.cache_clear() + ret = foo() + expected = ((), {}) + assert ret == expected + assert len(calls) == 4 + # docstring + assert foo.__doc__ == "Foo docstring." + + +class TestCommonModule(PsutilTestCase): + def test_memoize_when_activated(self): + class Foo: + @memoize_when_activated + def foo(self): + calls.append(None) + + f = Foo() + calls = [] + f.foo() + f.foo() + assert len(calls) == 2 + + # activate + calls = [] + f.foo.cache_activate(f) + f.foo() + f.foo() + assert len(calls) == 1 + + # deactivate + calls = [] + f.foo.cache_deactivate(f) + f.foo() + f.foo() + assert len(calls) == 2 + + def test_parse_environ_block(self): + def k(s): + return s.upper() if WINDOWS else s + + assert parse_environ_block("a=1\0") == {k("a"): "1"} + assert parse_environ_block("a=1\0b=2\0\0") == { + k("a"): "1", + k("b"): "2", + } + assert parse_environ_block("a=1\0b=\0\0") == {k("a"): "1", k("b"): ""} + # ignore everything after \0\0 + assert parse_environ_block("a=1\0b=2\0\0c=3\0") == { + k("a"): "1", + k("b"): "2", + } + # ignore everything that is not an assignment + assert parse_environ_block("xxx\0a=1\0") == {k("a"): "1"} + assert parse_environ_block("a=1\0=b=2\0") == {k("a"): "1"} + # do not fail if the block is incomplete + assert parse_environ_block("a=1\0b=2") == {k("a"): "1"} + + def test_supports_ipv6(self): + self.addCleanup(supports_ipv6.cache_clear) + if supports_ipv6(): + with mock.patch('psutil._common.socket') as s: + s.has_ipv6 = False + supports_ipv6.cache_clear() + assert not supports_ipv6() + + supports_ipv6.cache_clear() + with mock.patch( + 'psutil._common.socket.socket', side_effect=OSError + ) as s: + assert not supports_ipv6() + assert s.called + + supports_ipv6.cache_clear() + with mock.patch( + 'psutil._common.socket.socket', side_effect=socket.gaierror + ) as s: + assert not supports_ipv6() + supports_ipv6.cache_clear() + assert s.called + + supports_ipv6.cache_clear() + with mock.patch( + 'psutil._common.socket.socket.bind', + side_effect=socket.gaierror, + ) as s: + assert not supports_ipv6() + supports_ipv6.cache_clear() + assert s.called + else: + with pytest.raises(OSError): + sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) + try: + sock.bind(("::1", 0)) + finally: + sock.close() + + def test_isfile_strict(self): + this_file = os.path.abspath(__file__) + assert isfile_strict(this_file) + assert not isfile_strict(os.path.dirname(this_file)) + with mock.patch('psutil._common.os.stat', side_effect=PermissionError): + with pytest.raises(OSError): + isfile_strict(this_file) + with mock.patch( + 'psutil._common.os.stat', side_effect=FileNotFoundError + ): + assert not isfile_strict(this_file) + with mock.patch('psutil._common.stat.S_ISREG', return_value=False): + assert not isfile_strict(this_file) + + def test_debug(self): + with mock.patch.object(psutil._common, "PSUTIL_DEBUG", True): + with contextlib.redirect_stderr(io.StringIO()) as f: + debug("hello") + sys.stderr.flush() + msg = f.getvalue() + assert msg.startswith("psutil-debug"), msg + assert "hello" in msg + assert __file__.replace('.pyc', '.py') in msg + + # supposed to use repr(exc) + with mock.patch.object(psutil._common, "PSUTIL_DEBUG", True): + with contextlib.redirect_stderr(io.StringIO()) as f: + debug(ValueError("this is an error")) + msg = f.getvalue() + assert "ignoring ValueError" in msg + assert "'this is an error'" in msg + + # supposed to use str(exc), because of extra info about file name + with mock.patch.object(psutil._common, "PSUTIL_DEBUG", True): + with contextlib.redirect_stderr(io.StringIO()) as f: + exc = OSError(2, "no such file") + exc.filename = "/foo" + debug(exc) + msg = f.getvalue() + assert "no such file" in msg + assert "/foo" in msg + + def test_cat_bcat(self): + testfn = self.get_testfn() + with open(testfn, "w") as f: + f.write("foo") + assert cat(testfn) == "foo" + assert bcat(testfn) == b"foo" + with pytest.raises(FileNotFoundError): + cat(testfn + '-invalid') + with pytest.raises(FileNotFoundError): + bcat(testfn + '-invalid') + assert cat(testfn + '-invalid', fallback="bar") == "bar" + assert bcat(testfn + '-invalid', fallback="bar") == "bar" + + +# =================================================================== +# --- Tests for wrap_numbers() function. +# =================================================================== + + +nt = collections.namedtuple('foo', 'a b c') + + +class TestWrapNumbers(PsutilTestCase): + def setUp(self): + wrap_numbers.cache_clear() + + tearDown = setUp + + def test_first_call(self): + input = {'disk1': nt(5, 5, 5)} + assert wrap_numbers(input, 'disk_io') == input + + def test_input_hasnt_changed(self): + input = {'disk1': nt(5, 5, 5)} + assert wrap_numbers(input, 'disk_io') == input + assert wrap_numbers(input, 'disk_io') == input + + def test_increase_but_no_wrap(self): + input = {'disk1': nt(5, 5, 5)} + assert wrap_numbers(input, 'disk_io') == input + input = {'disk1': nt(10, 15, 20)} + assert wrap_numbers(input, 'disk_io') == input + input = {'disk1': nt(20, 25, 30)} + assert wrap_numbers(input, 'disk_io') == input + input = {'disk1': nt(20, 25, 30)} + assert wrap_numbers(input, 'disk_io') == input + + def test_wrap(self): + # let's say 100 is the threshold + input = {'disk1': nt(100, 100, 100)} + assert wrap_numbers(input, 'disk_io') == input + # first wrap restarts from 10 + input = {'disk1': nt(100, 100, 10)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(100, 100, 110)} + # then it remains the same + input = {'disk1': nt(100, 100, 10)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(100, 100, 110)} + # then it goes up + input = {'disk1': nt(100, 100, 90)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(100, 100, 190)} + # then it wraps again + input = {'disk1': nt(100, 100, 20)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(100, 100, 210)} + # and remains the same + input = {'disk1': nt(100, 100, 20)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(100, 100, 210)} + # now wrap another num + input = {'disk1': nt(50, 100, 20)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(150, 100, 210)} + # and again + input = {'disk1': nt(40, 100, 20)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(190, 100, 210)} + # keep it the same + input = {'disk1': nt(40, 100, 20)} + assert wrap_numbers(input, 'disk_io') == {'disk1': nt(190, 100, 210)} + + def test_changing_keys(self): + # Emulate a case where the second call to disk_io() + # (or whatever) provides a new disk, then the new disk + # disappears on the third call. + input = {'disk1': nt(5, 5, 5)} + assert wrap_numbers(input, 'disk_io') == input + input = {'disk1': nt(5, 5, 5), 'disk2': nt(7, 7, 7)} + assert wrap_numbers(input, 'disk_io') == input + input = {'disk1': nt(8, 8, 8)} + assert wrap_numbers(input, 'disk_io') == input + + def test_changing_keys_w_wrap(self): + input = {'disk1': nt(50, 50, 50), 'disk2': nt(100, 100, 100)} + assert wrap_numbers(input, 'disk_io') == input + # disk 2 wraps + input = {'disk1': nt(50, 50, 50), 'disk2': nt(100, 100, 10)} + assert wrap_numbers(input, 'disk_io') == { + 'disk1': nt(50, 50, 50), + 'disk2': nt(100, 100, 110), + } + # disk 2 disappears + input = {'disk1': nt(50, 50, 50)} + assert wrap_numbers(input, 'disk_io') == input + + # then it appears again; the old wrap is supposed to be + # gone. + input = {'disk1': nt(50, 50, 50), 'disk2': nt(100, 100, 100)} + assert wrap_numbers(input, 'disk_io') == input + # remains the same + input = {'disk1': nt(50, 50, 50), 'disk2': nt(100, 100, 100)} + assert wrap_numbers(input, 'disk_io') == input + # and then wraps again + input = {'disk1': nt(50, 50, 50), 'disk2': nt(100, 100, 10)} + assert wrap_numbers(input, 'disk_io') == { + 'disk1': nt(50, 50, 50), + 'disk2': nt(100, 100, 110), + } + + def test_real_data(self): + d = { + 'nvme0n1': (300, 508, 640, 1571, 5970, 1987, 2049, 451751, 47048), + 'nvme0n1p1': (1171, 2, 5600256, 1024, 516, 0, 0, 0, 8), + 'nvme0n1p2': (54, 54, 2396160, 5165056, 4, 24, 30, 1207, 28), + 'nvme0n1p3': (2389, 4539, 5154, 150, 4828, 1844, 2019, 398, 348), + } + assert wrap_numbers(d, 'disk_io') == d + assert wrap_numbers(d, 'disk_io') == d + # decrease this ↓ + d = { + 'nvme0n1': (100, 508, 640, 1571, 5970, 1987, 2049, 451751, 47048), + 'nvme0n1p1': (1171, 2, 5600256, 1024, 516, 0, 0, 0, 8), + 'nvme0n1p2': (54, 54, 2396160, 5165056, 4, 24, 30, 1207, 28), + 'nvme0n1p3': (2389, 4539, 5154, 150, 4828, 1844, 2019, 398, 348), + } + out = wrap_numbers(d, 'disk_io') + assert out['nvme0n1'][0] == 400 + + # --- cache tests + + def test_cache_first_call(self): + input = {'disk1': nt(5, 5, 5)} + wrap_numbers(input, 'disk_io') + cache = wrap_numbers.cache_info() + assert cache[0] == {'disk_io': input} + assert cache[1] == {'disk_io': {}} + assert cache[2] == {'disk_io': {}} + + def test_cache_call_twice(self): + input = {'disk1': nt(5, 5, 5)} + wrap_numbers(input, 'disk_io') + input = {'disk1': nt(10, 10, 10)} + wrap_numbers(input, 'disk_io') + cache = wrap_numbers.cache_info() + assert cache[0] == {'disk_io': input} + assert cache[1] == { + 'disk_io': {('disk1', 0): 0, ('disk1', 1): 0, ('disk1', 2): 0} + } + assert cache[2] == {'disk_io': {}} + + def test_cache_wrap(self): + # let's say 100 is the threshold + input = {'disk1': nt(100, 100, 100)} + wrap_numbers(input, 'disk_io') + + # first wrap restarts from 10 + input = {'disk1': nt(100, 100, 10)} + wrap_numbers(input, 'disk_io') + cache = wrap_numbers.cache_info() + assert cache[0] == {'disk_io': input} + assert cache[1] == { + 'disk_io': {('disk1', 0): 0, ('disk1', 1): 0, ('disk1', 2): 100} + } + assert cache[2] == {'disk_io': {'disk1': {('disk1', 2)}}} + + def check_cache_info(): + cache = wrap_numbers.cache_info() + assert cache[1] == { + 'disk_io': { + ('disk1', 0): 0, + ('disk1', 1): 0, + ('disk1', 2): 100, + } + } + assert cache[2] == {'disk_io': {'disk1': {('disk1', 2)}}} + + # then it remains the same + input = {'disk1': nt(100, 100, 10)} + wrap_numbers(input, 'disk_io') + cache = wrap_numbers.cache_info() + assert cache[0] == {'disk_io': input} + check_cache_info() + + # then it goes up + input = {'disk1': nt(100, 100, 90)} + wrap_numbers(input, 'disk_io') + cache = wrap_numbers.cache_info() + assert cache[0] == {'disk_io': input} + check_cache_info() + + # then it wraps again + input = {'disk1': nt(100, 100, 20)} + wrap_numbers(input, 'disk_io') + cache = wrap_numbers.cache_info() + assert cache[0] == {'disk_io': input} + assert cache[1] == { + 'disk_io': {('disk1', 0): 0, ('disk1', 1): 0, ('disk1', 2): 190} + } + assert cache[2] == {'disk_io': {'disk1': {('disk1', 2)}}} + + def test_cache_changing_keys(self): + input = {'disk1': nt(5, 5, 5)} + wrap_numbers(input, 'disk_io') + input = {'disk1': nt(5, 5, 5), 'disk2': nt(7, 7, 7)} + wrap_numbers(input, 'disk_io') + cache = wrap_numbers.cache_info() + assert cache[0] == {'disk_io': input} + assert cache[1] == { + 'disk_io': {('disk1', 0): 0, ('disk1', 1): 0, ('disk1', 2): 0} + } + assert cache[2] == {'disk_io': {}} + + def test_cache_clear(self): + input = {'disk1': nt(5, 5, 5)} + wrap_numbers(input, 'disk_io') + wrap_numbers(input, 'disk_io') + wrap_numbers.cache_clear('disk_io') + assert wrap_numbers.cache_info() == ({}, {}, {}) + wrap_numbers.cache_clear('disk_io') + wrap_numbers.cache_clear('?!?') + + @pytest.mark.skipif(not HAS_NET_IO_COUNTERS, reason="not supported") + def test_cache_clear_public_apis(self): + if not psutil.disk_io_counters() or not psutil.net_io_counters(): + raise pytest.skip("no disks or NICs available") + psutil.disk_io_counters() + psutil.net_io_counters() + caches = wrap_numbers.cache_info() + for cache in caches: + assert 'psutil.disk_io_counters' in cache + assert 'psutil.net_io_counters' in cache + + psutil.disk_io_counters.cache_clear() + caches = wrap_numbers.cache_info() + for cache in caches: + assert 'psutil.net_io_counters' in cache + assert 'psutil.disk_io_counters' not in cache + + psutil.net_io_counters.cache_clear() + caches = wrap_numbers.cache_info() + assert caches == ({}, {}, {}) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_osx.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_osx.py new file mode 100644 index 0000000..050418c --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_osx.py @@ -0,0 +1,197 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""macOS specific tests.""" + +import platform +import re +import time + +import psutil +from psutil import MACOS +from psutil import POSIX +from psutil.tests import CI_TESTING +from psutil.tests import HAS_BATTERY +from psutil.tests import TOLERANCE_DISK_USAGE +from psutil.tests import TOLERANCE_SYS_MEM +from psutil.tests import PsutilTestCase +from psutil.tests import pytest +from psutil.tests import retry_on_failure +from psutil.tests import sh +from psutil.tests import spawn_testproc +from psutil.tests import terminate + + +if POSIX: + from psutil._psutil_posix import getpagesize + + +def sysctl(cmdline): + """Expects a sysctl command with an argument and parse the result + returning only the value of interest. + """ + out = sh(cmdline) + result = out.split()[1] + try: + return int(result) + except ValueError: + return result + + +def vm_stat(field): + """Wrapper around 'vm_stat' cmdline utility.""" + out = sh('vm_stat') + for line in out.split('\n'): + if field in line: + break + else: + raise ValueError("line not found") + return int(re.search(r'\d+', line).group(0)) * getpagesize() + + +@pytest.mark.skipif(not MACOS, reason="MACOS only") +class TestProcess(PsutilTestCase): + @classmethod + def setUpClass(cls): + cls.pid = spawn_testproc().pid + + @classmethod + def tearDownClass(cls): + terminate(cls.pid) + + def test_process_create_time(self): + output = sh(f"ps -o lstart -p {self.pid}") + start_ps = output.replace('STARTED', '').strip() + hhmmss = start_ps.split(' ')[-2] + year = start_ps.split(' ')[-1] + start_psutil = psutil.Process(self.pid).create_time() + assert hhmmss == time.strftime( + "%H:%M:%S", time.localtime(start_psutil) + ) + assert year == time.strftime("%Y", time.localtime(start_psutil)) + + +@pytest.mark.skipif(not MACOS, reason="MACOS only") +class TestSystemAPIs(PsutilTestCase): + + # --- disk + + @retry_on_failure() + def test_disks(self): + # test psutil.disk_usage() and psutil.disk_partitions() + # against "df -a" + def df(path): + out = sh(f'df -k "{path}"').strip() + lines = out.split('\n') + lines.pop(0) + line = lines.pop(0) + dev, total, used, free = line.split()[:4] + if dev == 'none': + dev = '' + total = int(total) * 1024 + used = int(used) * 1024 + free = int(free) * 1024 + return dev, total, used, free + + for part in psutil.disk_partitions(all=False): + usage = psutil.disk_usage(part.mountpoint) + dev, total, used, free = df(part.mountpoint) + assert part.device == dev + assert usage.total == total + assert abs(usage.free - free) < TOLERANCE_DISK_USAGE + assert abs(usage.used - used) < TOLERANCE_DISK_USAGE + + # --- cpu + + def test_cpu_count_logical(self): + num = sysctl("sysctl hw.logicalcpu") + assert num == psutil.cpu_count(logical=True) + + def test_cpu_count_cores(self): + num = sysctl("sysctl hw.physicalcpu") + assert num == psutil.cpu_count(logical=False) + + # TODO: remove this once 1892 is fixed + @pytest.mark.skipif( + MACOS and platform.machine() == 'arm64', reason="skipped due to #1892" + ) + def test_cpu_freq(self): + freq = psutil.cpu_freq() + assert freq.current * 1000 * 1000 == sysctl("sysctl hw.cpufrequency") + assert freq.min * 1000 * 1000 == sysctl("sysctl hw.cpufrequency_min") + assert freq.max * 1000 * 1000 == sysctl("sysctl hw.cpufrequency_max") + + # --- virtual mem + + def test_vmem_total(self): + sysctl_hwphymem = sysctl('sysctl hw.memsize') + assert sysctl_hwphymem == psutil.virtual_memory().total + + @pytest.mark.skipif( + CI_TESTING and MACOS and platform.machine() == 'arm64', + reason="skipped on MACOS + ARM64 + CI_TESTING", + ) + @retry_on_failure() + def test_vmem_free(self): + vmstat_val = vm_stat("free") + psutil_val = psutil.virtual_memory().free + assert abs(psutil_val - vmstat_val) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_active(self): + vmstat_val = vm_stat("active") + psutil_val = psutil.virtual_memory().active + assert abs(psutil_val - vmstat_val) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_inactive(self): + vmstat_val = vm_stat("inactive") + psutil_val = psutil.virtual_memory().inactive + assert abs(psutil_val - vmstat_val) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_vmem_wired(self): + vmstat_val = vm_stat("wired") + psutil_val = psutil.virtual_memory().wired + assert abs(psutil_val - vmstat_val) < TOLERANCE_SYS_MEM + + # --- swap mem + + @retry_on_failure() + def test_swapmem_sin(self): + vmstat_val = vm_stat("Pageins") + psutil_val = psutil.swap_memory().sin + assert abs(psutil_val - vmstat_val) < TOLERANCE_SYS_MEM + + @retry_on_failure() + def test_swapmem_sout(self): + vmstat_val = vm_stat("Pageout") + psutil_val = psutil.swap_memory().sout + assert abs(psutil_val - vmstat_val) < TOLERANCE_SYS_MEM + + # --- network + + def test_net_if_stats(self): + for name, stats in psutil.net_if_stats().items(): + try: + out = sh(f"ifconfig {name}") + except RuntimeError: + pass + else: + assert stats.isup == ('RUNNING' in out), out + assert stats.mtu == int(re.findall(r'mtu (\d+)', out)[0]) + + # --- sensors_battery + + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_sensors_battery(self): + out = sh("pmset -g batt") + percent = re.search(r"(\d+)%", out).group(1) + drawing_from = re.search(r"Now drawing from '([^']+)'", out).group(1) + power_plugged = drawing_from == "AC Power" + psutil_result = psutil.sensors_battery() + assert psutil_result.power_plugged == power_plugged + assert psutil_result.percent == int(percent) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_posix.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_posix.py new file mode 100644 index 0000000..a784492 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_posix.py @@ -0,0 +1,488 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""POSIX specific tests.""" + +import datetime +import errno +import os +import re +import shutil +import subprocess +import time +from unittest import mock + +import psutil +from psutil import AIX +from psutil import BSD +from psutil import LINUX +from psutil import MACOS +from psutil import OPENBSD +from psutil import POSIX +from psutil import SUNOS +from psutil.tests import AARCH64 +from psutil.tests import HAS_NET_IO_COUNTERS +from psutil.tests import PYTHON_EXE +from psutil.tests import PsutilTestCase +from psutil.tests import pytest +from psutil.tests import retry_on_failure +from psutil.tests import sh +from psutil.tests import skip_on_access_denied +from psutil.tests import spawn_testproc +from psutil.tests import terminate + + +if POSIX: + import mmap + import resource + + from psutil._psutil_posix import getpagesize + + +def ps(fmt, pid=None): + """Wrapper for calling the ps command with a little bit of cross-platform + support for a narrow range of features. + """ + + cmd = ['ps'] + + if LINUX: + cmd.append('--no-headers') + + if pid is not None: + cmd.extend(['-p', str(pid)]) + elif SUNOS or AIX: + cmd.append('-A') + else: + cmd.append('ax') + + if SUNOS: + fmt = fmt.replace("start", "stime") + + cmd.extend(['-o', fmt]) + + output = sh(cmd) + + output = output.splitlines() if LINUX else output.splitlines()[1:] + + all_output = [] + for line in output: + line = line.strip() + + try: + line = int(line) + except ValueError: + pass + + all_output.append(line) + + if pid is None: + return all_output + else: + return all_output[0] + + +# ps "-o" field names differ wildly between platforms. +# "comm" means "only executable name" but is not available on BSD platforms. +# "args" means "command with all its arguments", and is also not available +# on BSD platforms. +# "command" is like "args" on most platforms, but like "comm" on AIX, +# and not available on SUNOS. +# so for the executable name we can use "comm" on Solaris and split "command" +# on other platforms. +# to get the cmdline (with args) we have to use "args" on AIX and +# Solaris, and can use "command" on all others. + + +def ps_name(pid): + field = "command" + if SUNOS: + field = "comm" + command = ps(field, pid).split() + return command[0] + + +def ps_args(pid): + field = "command" + if AIX or SUNOS: + field = "args" + out = ps(field, pid) + # observed on BSD + Github CI: '/usr/local/bin/python3 -E -O (python3.9)' + out = re.sub(r"\(python.*?\)$", "", out) + return out.strip() + + +def ps_rss(pid): + field = "rss" + if AIX: + field = "rssize" + return ps(field, pid) + + +def ps_vsz(pid): + field = "vsz" + if AIX: + field = "vsize" + return ps(field, pid) + + +def df(device): + try: + out = sh(f"df -k {device}").strip() + except RuntimeError as err: + if "device busy" in str(err).lower(): + raise pytest.skip("df returned EBUSY") + raise + line = out.split('\n')[1] + fields = line.split() + sys_total = int(fields[1]) * 1024 + sys_used = int(fields[2]) * 1024 + sys_free = int(fields[3]) * 1024 + sys_percent = float(fields[4].replace('%', '')) + return (sys_total, sys_used, sys_free, sys_percent) + + +@pytest.mark.skipif(not POSIX, reason="POSIX only") +class TestProcess(PsutilTestCase): + """Compare psutil results against 'ps' command line utility (mainly).""" + + @classmethod + def setUpClass(cls): + cls.pid = spawn_testproc( + [PYTHON_EXE, "-E", "-O"], stdin=subprocess.PIPE + ).pid + + @classmethod + def tearDownClass(cls): + terminate(cls.pid) + + def test_ppid(self): + ppid_ps = ps('ppid', self.pid) + ppid_psutil = psutil.Process(self.pid).ppid() + assert ppid_ps == ppid_psutil + + def test_uid(self): + uid_ps = ps('uid', self.pid) + uid_psutil = psutil.Process(self.pid).uids().real + assert uid_ps == uid_psutil + + def test_gid(self): + gid_ps = ps('rgid', self.pid) + gid_psutil = psutil.Process(self.pid).gids().real + assert gid_ps == gid_psutil + + def test_username(self): + username_ps = ps('user', self.pid) + username_psutil = psutil.Process(self.pid).username() + assert username_ps == username_psutil + + def test_username_no_resolution(self): + # Emulate a case where the system can't resolve the uid to + # a username in which case psutil is supposed to return + # the stringified uid. + p = psutil.Process() + with mock.patch("psutil.pwd.getpwuid", side_effect=KeyError) as fun: + assert p.username() == str(p.uids().real) + assert fun.called + + @skip_on_access_denied() + @retry_on_failure() + def test_rss_memory(self): + # give python interpreter some time to properly initialize + # so that the results are the same + time.sleep(0.1) + rss_ps = ps_rss(self.pid) + rss_psutil = psutil.Process(self.pid).memory_info()[0] / 1024 + assert rss_ps == rss_psutil + + @skip_on_access_denied() + @retry_on_failure() + def test_vsz_memory(self): + # give python interpreter some time to properly initialize + # so that the results are the same + time.sleep(0.1) + vsz_ps = ps_vsz(self.pid) + vsz_psutil = psutil.Process(self.pid).memory_info()[1] / 1024 + assert vsz_ps == vsz_psutil + + def test_name(self): + name_ps = ps_name(self.pid) + # remove path if there is any, from the command + name_ps = os.path.basename(name_ps).lower() + name_psutil = psutil.Process(self.pid).name().lower() + # ...because of how we calculate PYTHON_EXE; on MACOS this may + # be "pythonX.Y". + name_ps = re.sub(r"\d.\d", "", name_ps) + name_psutil = re.sub(r"\d.\d", "", name_psutil) + # ...may also be "python.X" + name_ps = re.sub(r"\d", "", name_ps) + name_psutil = re.sub(r"\d", "", name_psutil) + assert name_ps == name_psutil + + def test_name_long(self): + # On UNIX the kernel truncates the name to the first 15 + # characters. In such a case psutil tries to determine the + # full name from the cmdline. + name = "long-program-name" + cmdline = ["long-program-name-extended", "foo", "bar"] + with mock.patch("psutil._psplatform.Process.name", return_value=name): + with mock.patch( + "psutil._psplatform.Process.cmdline", return_value=cmdline + ): + p = psutil.Process() + assert p.name() == "long-program-name-extended" + + def test_name_long_cmdline_ad_exc(self): + # Same as above but emulates a case where cmdline() raises + # AccessDenied in which case psutil is supposed to return + # the truncated name instead of crashing. + name = "long-program-name" + with mock.patch("psutil._psplatform.Process.name", return_value=name): + with mock.patch( + "psutil._psplatform.Process.cmdline", + side_effect=psutil.AccessDenied(0, ""), + ): + p = psutil.Process() + assert p.name() == "long-program-name" + + def test_name_long_cmdline_nsp_exc(self): + # Same as above but emulates a case where cmdline() raises NSP + # which is supposed to propagate. + name = "long-program-name" + with mock.patch("psutil._psplatform.Process.name", return_value=name): + with mock.patch( + "psutil._psplatform.Process.cmdline", + side_effect=psutil.NoSuchProcess(0, ""), + ): + p = psutil.Process() + with pytest.raises(psutil.NoSuchProcess): + p.name() + + @pytest.mark.skipif(MACOS or BSD, reason="ps -o start not available") + def test_create_time(self): + time_ps = ps('start', self.pid) + time_psutil = psutil.Process(self.pid).create_time() + time_psutil_tstamp = datetime.datetime.fromtimestamp( + time_psutil + ).strftime("%H:%M:%S") + # sometimes ps shows the time rounded up instead of down, so we check + # for both possible values + round_time_psutil = round(time_psutil) + round_time_psutil_tstamp = datetime.datetime.fromtimestamp( + round_time_psutil + ).strftime("%H:%M:%S") + assert time_ps in {time_psutil_tstamp, round_time_psutil_tstamp} + + def test_exe(self): + ps_pathname = ps_name(self.pid) + psutil_pathname = psutil.Process(self.pid).exe() + try: + assert ps_pathname == psutil_pathname + except AssertionError: + # certain platforms such as BSD are more accurate returning: + # "/usr/local/bin/python3.7" + # ...instead of: + # "/usr/local/bin/python" + # We do not want to consider this difference in accuracy + # an error. + adjusted_ps_pathname = ps_pathname[: len(ps_pathname)] + assert ps_pathname == adjusted_ps_pathname + + # On macOS the official python installer exposes a python wrapper that + # executes a python executable hidden inside an application bundle inside + # the Python framework. + # There's a race condition between the ps call & the psutil call below + # depending on the completion of the execve call so let's retry on failure + @retry_on_failure() + def test_cmdline(self): + ps_cmdline = ps_args(self.pid) + psutil_cmdline = " ".join(psutil.Process(self.pid).cmdline()) + if AARCH64 and len(ps_cmdline) < len(psutil_cmdline): + assert psutil_cmdline.startswith(ps_cmdline) + else: + assert ps_cmdline == psutil_cmdline + + # On SUNOS "ps" reads niceness /proc/pid/psinfo which returns an + # incorrect value (20); the real deal is getpriority(2) which + # returns 0; psutil relies on it, see: + # https://github.com/giampaolo/psutil/issues/1082 + # AIX has the same issue + @pytest.mark.skipif(SUNOS, reason="not reliable on SUNOS") + @pytest.mark.skipif(AIX, reason="not reliable on AIX") + def test_nice(self): + ps_nice = ps('nice', self.pid) + psutil_nice = psutil.Process().nice() + assert ps_nice == psutil_nice + + +@pytest.mark.skipif(not POSIX, reason="POSIX only") +class TestSystemAPIs(PsutilTestCase): + """Test some system APIs.""" + + @retry_on_failure() + def test_pids(self): + # Note: this test might fail if the OS is starting/killing + # other processes in the meantime + pids_ps = sorted(ps("pid")) + pids_psutil = psutil.pids() + + # on MACOS and OPENBSD ps doesn't show pid 0 + if MACOS or (OPENBSD and 0 not in pids_ps): + pids_ps.insert(0, 0) + + # There will often be one more process in pids_ps for ps itself + if len(pids_ps) - len(pids_psutil) > 1: + difference = [x for x in pids_psutil if x not in pids_ps] + [ + x for x in pids_ps if x not in pids_psutil + ] + raise self.fail("difference: " + str(difference)) + + # for some reason ifconfig -a does not report all interfaces + # returned by psutil + @pytest.mark.skipif(SUNOS, reason="unreliable on SUNOS") + @pytest.mark.skipif(not shutil.which("ifconfig"), reason="no ifconfig cmd") + @pytest.mark.skipif(not HAS_NET_IO_COUNTERS, reason="not supported") + def test_nic_names(self): + output = sh("ifconfig -a") + for nic in psutil.net_io_counters(pernic=True): + for line in output.split(): + if line.startswith(nic): + break + else: + raise self.fail( + f"couldn't find {nic} nic in 'ifconfig -a'" + f" output\n{output}" + ) + + # @pytest.mark.skipif(CI_TESTING and not psutil.users(), + # reason="unreliable on CI") + @retry_on_failure() + def test_users(self): + out = sh("who -u") + if not out.strip(): + raise pytest.skip("no users on this system") + lines = out.split('\n') + users = [x.split()[0] for x in lines] + terminals = [x.split()[1] for x in lines] + assert len(users) == len(psutil.users()) + with self.subTest(psutil=psutil.users(), who=out): + for idx, u in enumerate(psutil.users()): + assert u.name == users[idx] + assert u.terminal == terminals[idx] + if u.pid is not None: # None on OpenBSD + psutil.Process(u.pid) + + @retry_on_failure() + def test_users_started(self): + out = sh("who -u") + if not out.strip(): + raise pytest.skip("no users on this system") + tstamp = None + # '2023-04-11 09:31' (Linux) + started = re.findall(r"\d\d\d\d-\d\d-\d\d \d\d:\d\d", out) + if started: + tstamp = "%Y-%m-%d %H:%M" + else: + # 'Apr 10 22:27' (macOS) + started = re.findall(r"[A-Z][a-z][a-z] \d\d \d\d:\d\d", out) + if started: + tstamp = "%b %d %H:%M" + else: + # 'Apr 10' + started = re.findall(r"[A-Z][a-z][a-z] \d\d", out) + if started: + tstamp = "%b %d" + else: + # 'apr 10' (sunOS) + started = re.findall(r"[a-z][a-z][a-z] \d\d", out) + if started: + tstamp = "%b %d" + started = [x.capitalize() for x in started] + + if not tstamp: + raise pytest.skip(f"cannot interpret tstamp in who output\n{out}") + + with self.subTest(psutil=psutil.users(), who=out): + for idx, u in enumerate(psutil.users()): + psutil_value = datetime.datetime.fromtimestamp( + u.started + ).strftime(tstamp) + assert psutil_value == started[idx] + + def test_pid_exists_let_raise(self): + # According to "man 2 kill" possible error values for kill + # are (EINVAL, EPERM, ESRCH). Test that any other errno + # results in an exception. + with mock.patch( + "psutil._psposix.os.kill", side_effect=OSError(errno.EBADF, "") + ) as m: + with pytest.raises(OSError): + psutil._psposix.pid_exists(os.getpid()) + assert m.called + + def test_os_waitpid_let_raise(self): + # os.waitpid() is supposed to catch EINTR and ECHILD only. + # Test that any other errno results in an exception. + with mock.patch( + "psutil._psposix.os.waitpid", side_effect=OSError(errno.EBADF, "") + ) as m: + with pytest.raises(OSError): + psutil._psposix.wait_pid(os.getpid()) + assert m.called + + def test_os_waitpid_eintr(self): + # os.waitpid() is supposed to "retry" on EINTR. + with mock.patch( + "psutil._psposix.os.waitpid", side_effect=OSError(errno.EINTR, "") + ) as m: + with pytest.raises(psutil._psposix.TimeoutExpired): + psutil._psposix.wait_pid(os.getpid(), timeout=0.01) + assert m.called + + def test_os_waitpid_bad_ret_status(self): + # Simulate os.waitpid() returning a bad status. + with mock.patch( + "psutil._psposix.os.waitpid", return_value=(1, -1) + ) as m: + with pytest.raises(ValueError): + psutil._psposix.wait_pid(os.getpid()) + assert m.called + + # AIX can return '-' in df output instead of numbers, e.g. for /proc + @pytest.mark.skipif(AIX, reason="unreliable on AIX") + @retry_on_failure() + def test_disk_usage(self): + tolerance = 4 * 1024 * 1024 # 4MB + for part in psutil.disk_partitions(all=False): + usage = psutil.disk_usage(part.mountpoint) + try: + sys_total, sys_used, sys_free, sys_percent = df(part.device) + except RuntimeError as err: + # see: + # https://travis-ci.org/giampaolo/psutil/jobs/138338464 + # https://travis-ci.org/giampaolo/psutil/jobs/138343361 + err = str(err).lower() + if ( + "no such file or directory" in err + or "raw devices not supported" in err + or "permission denied" in err + ): + continue + raise + else: + assert abs(usage.total - sys_total) < tolerance + assert abs(usage.used - sys_used) < tolerance + assert abs(usage.free - sys_free) < tolerance + assert abs(usage.percent - sys_percent) <= 1 + + +@pytest.mark.skipif(not POSIX, reason="POSIX only") +class TestMisc(PsutilTestCase): + def test_getpagesize(self): + pagesize = getpagesize() + assert pagesize > 0 + assert pagesize == resource.getpagesize() + assert pagesize == mmap.PAGESIZE diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_process.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_process.py new file mode 100644 index 0000000..9ba1ba0 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_process.py @@ -0,0 +1,1667 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Tests for psutil.Process class.""" + +import collections +import contextlib +import errno +import getpass +import io +import itertools +import os +import signal +import socket +import stat +import string +import subprocess +import sys +import textwrap +import time +from unittest import mock + +import psutil +from psutil import AIX +from psutil import BSD +from psutil import LINUX +from psutil import MACOS +from psutil import NETBSD +from psutil import OPENBSD +from psutil import OSX +from psutil import POSIX +from psutil import WINDOWS +from psutil._common import open_text +from psutil.tests import CI_TESTING +from psutil.tests import GITHUB_ACTIONS +from psutil.tests import GLOBAL_TIMEOUT +from psutil.tests import HAS_CPU_AFFINITY +from psutil.tests import HAS_ENVIRON +from psutil.tests import HAS_IONICE +from psutil.tests import HAS_MEMORY_MAPS +from psutil.tests import HAS_PROC_CPU_NUM +from psutil.tests import HAS_PROC_IO_COUNTERS +from psutil.tests import HAS_RLIMIT +from psutil.tests import HAS_THREADS +from psutil.tests import MACOS_11PLUS +from psutil.tests import PYPY +from psutil.tests import PYTHON_EXE +from psutil.tests import PYTHON_EXE_ENV +from psutil.tests import PsutilTestCase +from psutil.tests import ThreadTask +from psutil.tests import call_until +from psutil.tests import copyload_shared_lib +from psutil.tests import create_c_exe +from psutil.tests import create_py_exe +from psutil.tests import process_namespace +from psutil.tests import pytest +from psutil.tests import reap_children +from psutil.tests import retry_on_failure +from psutil.tests import sh +from psutil.tests import skip_on_access_denied +from psutil.tests import skip_on_not_implemented +from psutil.tests import wait_for_pid + + +# =================================================================== +# --- psutil.Process class tests +# =================================================================== + + +class TestProcess(PsutilTestCase): + """Tests for psutil.Process class.""" + + def spawn_psproc(self, *args, **kwargs): + sproc = self.spawn_testproc(*args, **kwargs) + try: + return psutil.Process(sproc.pid) + except psutil.NoSuchProcess: + self.assertPidGone(sproc.pid) + raise + + # --- + + def test_pid(self): + p = psutil.Process() + assert p.pid == os.getpid() + with pytest.raises(AttributeError): + p.pid = 33 + + def test_kill(self): + p = self.spawn_psproc() + p.kill() + code = p.wait() + if WINDOWS: + assert code == signal.SIGTERM + else: + assert code == -signal.SIGKILL + self.assertProcessGone(p) + + def test_terminate(self): + p = self.spawn_psproc() + p.terminate() + code = p.wait() + if WINDOWS: + assert code == signal.SIGTERM + else: + assert code == -signal.SIGTERM + self.assertProcessGone(p) + + def test_send_signal(self): + sig = signal.SIGKILL if POSIX else signal.SIGTERM + p = self.spawn_psproc() + p.send_signal(sig) + code = p.wait() + if WINDOWS: + assert code == sig + else: + assert code == -sig + self.assertProcessGone(p) + + @pytest.mark.skipif(not POSIX, reason="not POSIX") + def test_send_signal_mocked(self): + sig = signal.SIGTERM + p = self.spawn_psproc() + with mock.patch('psutil.os.kill', side_effect=ProcessLookupError): + with pytest.raises(psutil.NoSuchProcess): + p.send_signal(sig) + + p = self.spawn_psproc() + with mock.patch('psutil.os.kill', side_effect=PermissionError): + with pytest.raises(psutil.AccessDenied): + p.send_signal(sig) + + def test_wait_exited(self): + # Test waitpid() + WIFEXITED -> WEXITSTATUS. + # normal return, same as exit(0) + cmd = [PYTHON_EXE, "-c", "pass"] + p = self.spawn_psproc(cmd) + code = p.wait() + assert code == 0 + self.assertProcessGone(p) + # exit(1), implicit in case of error + cmd = [PYTHON_EXE, "-c", "1 / 0"] + p = self.spawn_psproc(cmd, stderr=subprocess.PIPE) + code = p.wait() + assert code == 1 + self.assertProcessGone(p) + # via sys.exit() + cmd = [PYTHON_EXE, "-c", "import sys; sys.exit(5);"] + p = self.spawn_psproc(cmd) + code = p.wait() + assert code == 5 + self.assertProcessGone(p) + # via os._exit() + cmd = [PYTHON_EXE, "-c", "import os; os._exit(5);"] + p = self.spawn_psproc(cmd) + code = p.wait() + assert code == 5 + self.assertProcessGone(p) + + @pytest.mark.skipif(NETBSD, reason="fails on NETBSD") + def test_wait_stopped(self): + p = self.spawn_psproc() + if POSIX: + # Test waitpid() + WIFSTOPPED and WIFCONTINUED. + # Note: if a process is stopped it ignores SIGTERM. + p.send_signal(signal.SIGSTOP) + with pytest.raises(psutil.TimeoutExpired): + p.wait(timeout=0.001) + p.send_signal(signal.SIGCONT) + with pytest.raises(psutil.TimeoutExpired): + p.wait(timeout=0.001) + p.send_signal(signal.SIGTERM) + assert p.wait() == -signal.SIGTERM + assert p.wait() == -signal.SIGTERM + else: + p.suspend() + with pytest.raises(psutil.TimeoutExpired): + p.wait(timeout=0.001) + p.resume() + with pytest.raises(psutil.TimeoutExpired): + p.wait(timeout=0.001) + p.terminate() + assert p.wait() == signal.SIGTERM + assert p.wait() == signal.SIGTERM + + def test_wait_non_children(self): + # Test wait() against a process which is not our direct + # child. + child, grandchild = self.spawn_children_pair() + with pytest.raises(psutil.TimeoutExpired): + child.wait(0.01) + with pytest.raises(psutil.TimeoutExpired): + grandchild.wait(0.01) + # We also terminate the direct child otherwise the + # grandchild will hang until the parent is gone. + child.terminate() + grandchild.terminate() + child_ret = child.wait() + grandchild_ret = grandchild.wait() + if POSIX: + assert child_ret == -signal.SIGTERM + # For processes which are not our children we're supposed + # to get None. + assert grandchild_ret is None + else: + assert child_ret == signal.SIGTERM + assert child_ret == signal.SIGTERM + + def test_wait_timeout(self): + p = self.spawn_psproc() + p.name() + with pytest.raises(psutil.TimeoutExpired): + p.wait(0.01) + with pytest.raises(psutil.TimeoutExpired): + p.wait(0) + with pytest.raises(ValueError): + p.wait(-1) + + def test_wait_timeout_nonblocking(self): + p = self.spawn_psproc() + with pytest.raises(psutil.TimeoutExpired): + p.wait(0) + p.kill() + stop_at = time.time() + GLOBAL_TIMEOUT + while time.time() < stop_at: + try: + code = p.wait(0) + break + except psutil.TimeoutExpired: + pass + else: + raise self.fail('timeout') + if POSIX: + assert code == -signal.SIGKILL + else: + assert code == signal.SIGTERM + self.assertProcessGone(p) + + def test_cpu_percent(self): + p = psutil.Process() + p.cpu_percent(interval=0.001) + p.cpu_percent(interval=0.001) + for _ in range(100): + percent = p.cpu_percent(interval=None) + assert isinstance(percent, float) + assert percent >= 0.0 + with pytest.raises(ValueError): + p.cpu_percent(interval=-1) + + def test_cpu_percent_numcpus_none(self): + # See: https://github.com/giampaolo/psutil/issues/1087 + with mock.patch('psutil.cpu_count', return_value=None) as m: + psutil.Process().cpu_percent() + assert m.called + + def test_cpu_times(self): + times = psutil.Process().cpu_times() + assert times.user >= 0.0, times + assert times.system >= 0.0, times + assert times.children_user >= 0.0, times + assert times.children_system >= 0.0, times + if LINUX: + assert times.iowait >= 0.0, times + # make sure returned values can be pretty printed with strftime + for name in times._fields: + time.strftime("%H:%M:%S", time.localtime(getattr(times, name))) + + def test_cpu_times_2(self): + def waste_cpu(): + stop_at = os.times().user + 0.2 + while os.times().user < stop_at: + for x in range(100000): + x **= 2 + + waste_cpu() + a = psutil.Process().cpu_times() + b = os.times() + self.assertAlmostEqual(a.user, b.user, delta=0.1) + self.assertAlmostEqual(a.system, b.system, delta=0.1) + + @pytest.mark.skipif(not HAS_PROC_CPU_NUM, reason="not supported") + def test_cpu_num(self): + p = psutil.Process() + num = p.cpu_num() + assert num >= 0 + if psutil.cpu_count() == 1: + assert num == 0 + assert p.cpu_num() in range(psutil.cpu_count()) + + def test_create_time(self): + p = self.spawn_psproc() + now = time.time() + create_time = p.create_time() + + # Use time.time() as base value to compare our result using a + # tolerance of +/- 1 second. + # It will fail if the difference between the values is > 2s. + difference = abs(create_time - now) + if difference > 2: + raise self.fail( + f"expected: {now}, found: {create_time}, difference:" + f" {difference}" + ) + + # make sure returned value can be pretty printed with strftime + time.strftime("%Y %m %d %H:%M:%S", time.localtime(p.create_time())) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_terminal(self): + terminal = psutil.Process().terminal() + if terminal is not None: + try: + tty = os.path.realpath(sh('tty')) + except RuntimeError: + # Note: happens if pytest is run without the `-s` opt. + raise pytest.skip("can't rely on `tty` CLI") + else: + assert terminal == tty + + @pytest.mark.skipif(not HAS_PROC_IO_COUNTERS, reason="not supported") + @skip_on_not_implemented(only_if=LINUX) + def test_io_counters(self): + p = psutil.Process() + # test reads + io1 = p.io_counters() + with open(PYTHON_EXE, 'rb') as f: + f.read() + io2 = p.io_counters() + if not BSD and not AIX: + assert io2.read_count > io1.read_count + assert io2.write_count == io1.write_count + if LINUX: + assert io2.read_chars > io1.read_chars + assert io2.write_chars == io1.write_chars + else: + assert io2.read_bytes >= io1.read_bytes + assert io2.write_bytes >= io1.write_bytes + + # test writes + io1 = p.io_counters() + with open(self.get_testfn(), 'wb') as f: + f.write(bytes("x" * 1000000, 'ascii')) + io2 = p.io_counters() + assert io2.write_count >= io1.write_count + assert io2.write_bytes >= io1.write_bytes + assert io2.read_count >= io1.read_count + assert io2.read_bytes >= io1.read_bytes + if LINUX: + assert io2.write_chars > io1.write_chars + assert io2.read_chars >= io1.read_chars + + # sanity check + for i in range(len(io2)): + if BSD and i >= 2: + # On BSD read_bytes and write_bytes are always set to -1. + continue + assert io2[i] >= 0 + assert io2[i] >= 0 + + @pytest.mark.skipif(not HAS_IONICE, reason="not supported") + @pytest.mark.skipif(not LINUX, reason="linux only") + def test_ionice_linux(self): + def cleanup(init): + ioclass, value = init + if ioclass == psutil.IOPRIO_CLASS_NONE: + value = 0 + p.ionice(ioclass, value) + + p = psutil.Process() + if not CI_TESTING: + assert p.ionice()[0] == psutil.IOPRIO_CLASS_NONE + assert psutil.IOPRIO_CLASS_NONE == 0 + assert psutil.IOPRIO_CLASS_RT == 1 # high + assert psutil.IOPRIO_CLASS_BE == 2 # normal + assert psutil.IOPRIO_CLASS_IDLE == 3 # low + init = p.ionice() + self.addCleanup(cleanup, init) + + # low + p.ionice(psutil.IOPRIO_CLASS_IDLE) + assert tuple(p.ionice()) == (psutil.IOPRIO_CLASS_IDLE, 0) + with pytest.raises(ValueError): # accepts no value + p.ionice(psutil.IOPRIO_CLASS_IDLE, value=7) + # normal + p.ionice(psutil.IOPRIO_CLASS_BE) + assert tuple(p.ionice()) == (psutil.IOPRIO_CLASS_BE, 0) + p.ionice(psutil.IOPRIO_CLASS_BE, value=7) + assert tuple(p.ionice()) == (psutil.IOPRIO_CLASS_BE, 7) + with pytest.raises(ValueError): + p.ionice(psutil.IOPRIO_CLASS_BE, value=8) + try: + p.ionice(psutil.IOPRIO_CLASS_RT, value=7) + except psutil.AccessDenied: + pass + # errs + with pytest.raises(ValueError, match="ioclass accepts no value"): + p.ionice(psutil.IOPRIO_CLASS_NONE, 1) + with pytest.raises(ValueError, match="ioclass accepts no value"): + p.ionice(psutil.IOPRIO_CLASS_IDLE, 1) + with pytest.raises( + ValueError, match="'ioclass' argument must be specified" + ): + p.ionice(value=1) + + @pytest.mark.skipif(not HAS_IONICE, reason="not supported") + @pytest.mark.skipif( + not WINDOWS, reason="not supported on this win version" + ) + def test_ionice_win(self): + p = psutil.Process() + if not CI_TESTING: + assert p.ionice() == psutil.IOPRIO_NORMAL + init = p.ionice() + self.addCleanup(p.ionice, init) + + # base + p.ionice(psutil.IOPRIO_VERYLOW) + assert p.ionice() == psutil.IOPRIO_VERYLOW + p.ionice(psutil.IOPRIO_LOW) + assert p.ionice() == psutil.IOPRIO_LOW + try: + p.ionice(psutil.IOPRIO_HIGH) + except psutil.AccessDenied: + pass + else: + assert p.ionice() == psutil.IOPRIO_HIGH + # errs + with pytest.raises( + TypeError, match="value argument not accepted on Windows" + ): + p.ionice(psutil.IOPRIO_NORMAL, value=1) + with pytest.raises(ValueError, match="is not a valid priority"): + p.ionice(psutil.IOPRIO_HIGH + 1) + + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit_get(self): + import resource + + p = psutil.Process(os.getpid()) + names = [x for x in dir(psutil) if x.startswith('RLIMIT')] + assert names, names + for name in names: + value = getattr(psutil, name) + assert value >= 0 + if name in dir(resource): + assert value == getattr(resource, name) + # XXX - On PyPy RLIMIT_INFINITY returned by + # resource.getrlimit() is reported as a very big long + # number instead of -1. It looks like a bug with PyPy. + if PYPY: + continue + assert p.rlimit(value) == resource.getrlimit(value) + else: + ret = p.rlimit(value) + assert len(ret) == 2 + assert ret[0] >= -1 + assert ret[1] >= -1 + + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit_set(self): + p = self.spawn_psproc() + p.rlimit(psutil.RLIMIT_NOFILE, (5, 5)) + assert p.rlimit(psutil.RLIMIT_NOFILE) == (5, 5) + # If pid is 0 prlimit() applies to the calling process and + # we don't want that. + if LINUX: + with pytest.raises(ValueError, match="can't use prlimit"): + psutil._psplatform.Process(0).rlimit(0) + with pytest.raises(ValueError): + p.rlimit(psutil.RLIMIT_NOFILE, (5, 5, 5)) + + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit(self): + p = psutil.Process() + testfn = self.get_testfn() + soft, hard = p.rlimit(psutil.RLIMIT_FSIZE) + try: + p.rlimit(psutil.RLIMIT_FSIZE, (1024, hard)) + with open(testfn, "wb") as f: + f.write(b"X" * 1024) + # write() or flush() doesn't always cause the exception + # but close() will. + with pytest.raises(OSError) as exc: + with open(testfn, "wb") as f: + f.write(b"X" * 1025) + assert exc.value.errno == errno.EFBIG + finally: + p.rlimit(psutil.RLIMIT_FSIZE, (soft, hard)) + assert p.rlimit(psutil.RLIMIT_FSIZE) == (soft, hard) + + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit_infinity(self): + # First set a limit, then re-set it by specifying INFINITY + # and assume we overridden the previous limit. + p = psutil.Process() + soft, hard = p.rlimit(psutil.RLIMIT_FSIZE) + try: + p.rlimit(psutil.RLIMIT_FSIZE, (1024, hard)) + p.rlimit(psutil.RLIMIT_FSIZE, (psutil.RLIM_INFINITY, hard)) + with open(self.get_testfn(), "wb") as f: + f.write(b"X" * 2048) + finally: + p.rlimit(psutil.RLIMIT_FSIZE, (soft, hard)) + assert p.rlimit(psutil.RLIMIT_FSIZE) == (soft, hard) + + @pytest.mark.skipif(not HAS_RLIMIT, reason="not supported") + def test_rlimit_infinity_value(self): + # RLIMIT_FSIZE should be RLIM_INFINITY, which will be a really + # big number on a platform with large file support. On these + # platforms we need to test that the get/setrlimit functions + # properly convert the number to a C long long and that the + # conversion doesn't raise an error. + p = psutil.Process() + soft, hard = p.rlimit(psutil.RLIMIT_FSIZE) + assert hard == psutil.RLIM_INFINITY + p.rlimit(psutil.RLIMIT_FSIZE, (soft, hard)) + + def test_num_threads(self): + # on certain platforms such as Linux we might test for exact + # thread number, since we always have with 1 thread per process, + # but this does not apply across all platforms (MACOS, Windows) + p = psutil.Process() + if OPENBSD: + try: + step1 = p.num_threads() + except psutil.AccessDenied: + raise pytest.skip("on OpenBSD this requires root access") + else: + step1 = p.num_threads() + + with ThreadTask(): + step2 = p.num_threads() + assert step2 == step1 + 1 + + @pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") + def test_num_handles(self): + # a better test is done later into test/_windows.py + p = psutil.Process() + assert p.num_handles() > 0 + + @pytest.mark.skipif(not HAS_THREADS, reason="not supported") + def test_threads(self): + p = psutil.Process() + if OPENBSD: + try: + step1 = p.threads() + except psutil.AccessDenied: + raise pytest.skip("on OpenBSD this requires root access") + else: + step1 = p.threads() + + with ThreadTask(): + step2 = p.threads() + assert len(step2) == len(step1) + 1 + athread = step2[0] + # test named tuple + assert athread.id == athread[0] + assert athread.user_time == athread[1] + assert athread.system_time == athread[2] + + @retry_on_failure() + @skip_on_access_denied(only_if=MACOS) + @pytest.mark.skipif(not HAS_THREADS, reason="not supported") + def test_threads_2(self): + p = self.spawn_psproc() + if OPENBSD: + try: + p.threads() + except psutil.AccessDenied: + raise pytest.skip("on OpenBSD this requires root access") + assert ( + abs(p.cpu_times().user - sum(x.user_time for x in p.threads())) + < 0.1 + ) + assert ( + abs(p.cpu_times().system - sum(x.system_time for x in p.threads())) + < 0.1 + ) + + @retry_on_failure() + def test_memory_info(self): + p = psutil.Process() + + # step 1 - get a base value to compare our results + rss1, vms1 = p.memory_info()[:2] + percent1 = p.memory_percent() + assert rss1 > 0 + assert vms1 > 0 + + # step 2 - allocate some memory + memarr = [None] * 1500000 + + rss2, vms2 = p.memory_info()[:2] + percent2 = p.memory_percent() + + # step 3 - make sure that the memory usage bumped up + assert rss2 > rss1 + assert vms2 >= vms1 # vms might be equal + assert percent2 > percent1 + del memarr + + if WINDOWS: + mem = p.memory_info() + assert mem.rss == mem.wset + assert mem.vms == mem.pagefile + + mem = p.memory_info() + for name in mem._fields: + assert getattr(mem, name) >= 0 + + def test_memory_full_info(self): + p = psutil.Process() + total = psutil.virtual_memory().total + mem = p.memory_full_info() + for name in mem._fields: + value = getattr(mem, name) + assert value >= 0 + if (name == "vms" and OSX) or LINUX: + continue + assert value <= total + if LINUX or WINDOWS or MACOS: + assert mem.uss >= 0 + if LINUX: + assert mem.pss >= 0 + assert mem.swap >= 0 + + @pytest.mark.skipif(not HAS_MEMORY_MAPS, reason="not supported") + def test_memory_maps(self): + p = psutil.Process() + maps = p.memory_maps() + assert len(maps) == len(set(maps)) + ext_maps = p.memory_maps(grouped=False) + + for nt in maps: + if nt.path.startswith('['): + continue + if BSD and nt.path == "pvclock": + continue + assert os.path.isabs(nt.path), nt.path + + if POSIX: + try: + assert os.path.exists(nt.path) or os.path.islink( + nt.path + ), nt.path + except AssertionError: + if not LINUX: + raise + # https://github.com/giampaolo/psutil/issues/759 + with open_text('/proc/self/smaps') as f: + data = f.read() + if f"{nt.path} (deleted)" not in data: + raise + elif '64' not in os.path.basename(nt.path): + # XXX - On Windows we have this strange behavior with + # 64 bit dlls: they are visible via explorer but cannot + # be accessed via os.stat() (wtf?). + try: + st = os.stat(nt.path) + except FileNotFoundError: + pass + else: + assert stat.S_ISREG(st.st_mode), nt.path + + for nt in ext_maps: + for fname in nt._fields: + value = getattr(nt, fname) + if fname == 'path': + continue + if fname in {'addr', 'perms'}: + assert value, value + else: + assert isinstance(value, int) + assert value >= 0, value + + @pytest.mark.skipif(not HAS_MEMORY_MAPS, reason="not supported") + def test_memory_maps_lists_lib(self): + # Make sure a newly loaded shared lib is listed. + p = psutil.Process() + with copyload_shared_lib() as path: + + def normpath(p): + return os.path.realpath(os.path.normcase(p)) + + libpaths = [normpath(x.path) for x in p.memory_maps()] + assert normpath(path) in libpaths + + def test_memory_percent(self): + p = psutil.Process() + p.memory_percent() + with pytest.raises(ValueError): + p.memory_percent(memtype="?!?") + if LINUX or MACOS or WINDOWS: + p.memory_percent(memtype='uss') + + def test_is_running(self): + p = self.spawn_psproc() + assert p.is_running() + assert p.is_running() + p.kill() + p.wait() + assert not p.is_running() + assert not p.is_running() + + def test_exe(self): + p = self.spawn_psproc() + exe = p.exe() + try: + assert exe == PYTHON_EXE + except AssertionError: + if WINDOWS and len(exe) == len(PYTHON_EXE): + # on Windows we don't care about case sensitivity + normcase = os.path.normcase + assert normcase(exe) == normcase(PYTHON_EXE) + else: + # certain platforms such as BSD are more accurate returning: + # "/usr/local/bin/python3.7" + # ...instead of: + # "/usr/local/bin/python" + # We do not want to consider this difference in accuracy + # an error. + ver = f"{sys.version_info[0]}.{sys.version_info[1]}" + try: + assert exe.replace(ver, '') == PYTHON_EXE.replace(ver, '') + except AssertionError: + # Typically MACOS. Really not sure what to do here. + pass + + out = sh([exe, "-c", "import os; print('hey')"]) + assert out == 'hey' + + def test_cmdline(self): + cmdline = [ + PYTHON_EXE, + "-c", + "import time; [time.sleep(0.1) for x in range(100)]", + ] + p = self.spawn_psproc(cmdline) + + if NETBSD and p.cmdline() == []: + # https://github.com/giampaolo/psutil/issues/2250 + raise pytest.skip("OPENBSD: returned EBUSY") + + # XXX - most of the times the underlying sysctl() call on Net + # and Open BSD returns a truncated string. + # Also /proc/pid/cmdline behaves the same so it looks + # like this is a kernel bug. + # XXX - AIX truncates long arguments in /proc/pid/cmdline + if NETBSD or OPENBSD or AIX: + assert p.cmdline()[0] == PYTHON_EXE + else: + if MACOS and CI_TESTING: + pyexe = p.cmdline()[0] + if pyexe != PYTHON_EXE: + assert ' '.join(p.cmdline()[1:]) == ' '.join(cmdline[1:]) + return + assert ' '.join(p.cmdline()) == ' '.join(cmdline) + + @pytest.mark.skipif(PYPY, reason="broken on PYPY") + def test_long_cmdline(self): + cmdline = [PYTHON_EXE] + cmdline.extend(["-v"] * 50) + cmdline.extend( + ["-c", "import time; [time.sleep(0.1) for x in range(100)]"] + ) + p = self.spawn_psproc(cmdline) + if OPENBSD: + # XXX: for some reason the test process may turn into a + # zombie (don't know why). + try: + assert p.cmdline() == cmdline + except psutil.ZombieProcess: + raise pytest.skip("OPENBSD: process turned into zombie") + else: + ret = p.cmdline() + if NETBSD and ret == []: + # https://github.com/giampaolo/psutil/issues/2250 + raise pytest.skip("OPENBSD: returned EBUSY") + assert ret == cmdline + + def test_name(self): + p = self.spawn_psproc() + name = p.name().lower() + pyexe = os.path.basename(os.path.realpath(sys.executable)).lower() + assert pyexe.startswith(name), (pyexe, name) + + @pytest.mark.skipif(PYPY, reason="unreliable on PYPY") + def test_long_name(self): + pyexe = create_py_exe(self.get_testfn(suffix=string.digits * 2)) + cmdline = [ + pyexe, + "-c", + "import time; [time.sleep(0.1) for x in range(100)]", + ] + p = self.spawn_psproc(cmdline) + if OPENBSD: + # XXX: for some reason the test process may turn into a + # zombie (don't know why). Because the name() is long, all + # UNIX kernels truncate it to 15 chars, so internally psutil + # tries to guess the full name() from the cmdline(). But the + # cmdline() of a zombie on OpenBSD fails (internally), so we + # just compare the first 15 chars. Full explanation: + # https://github.com/giampaolo/psutil/issues/2239 + try: + assert p.name() == os.path.basename(pyexe) + except AssertionError: + if p.status() == psutil.STATUS_ZOMBIE: + assert os.path.basename(pyexe).startswith(p.name()) + else: + raise + else: + assert p.name() == os.path.basename(pyexe) + + # XXX: fails too often + # @pytest.mark.skipif(SUNOS, reason="broken on SUNOS") + # @pytest.mark.skipif(AIX, reason="broken on AIX") + # @pytest.mark.skipif(PYPY, reason="broken on PYPY") + # def test_prog_w_funky_name(self): + # # Test that name(), exe() and cmdline() correctly handle programs + # # with funky chars such as spaces and ")", see: + # # https://github.com/giampaolo/psutil/issues/628 + # pyexe = create_py_exe(self.get_testfn(suffix='foo bar )')) + # cmdline = [ + # pyexe, + # "-c", + # "import time; [time.sleep(0.1) for x in range(100)]", + # ] + # p = self.spawn_psproc(cmdline) + # assert p.cmdline() == cmdline + # assert p.name() == os.path.basename(pyexe) + # assert os.path.normcase(p.exe()) == os.path.normcase(pyexe) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_uids(self): + p = psutil.Process() + real, effective, _saved = p.uids() + # os.getuid() refers to "real" uid + assert real == os.getuid() + # os.geteuid() refers to "effective" uid + assert effective == os.geteuid() + # No such thing as os.getsuid() ("saved" uid), but we have + # os.getresuid() which returns all of them. + if hasattr(os, "getresuid"): + assert os.getresuid() == p.uids() + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_gids(self): + p = psutil.Process() + real, effective, _saved = p.gids() + # os.getuid() refers to "real" uid + assert real == os.getgid() + # os.geteuid() refers to "effective" uid + assert effective == os.getegid() + # No such thing as os.getsgid() ("saved" gid), but we have + # os.getresgid() which returns all of them. + if hasattr(os, "getresuid"): + assert os.getresgid() == p.gids() + + def test_nice(self): + def cleanup(init): + try: + p.nice(init) + except psutil.AccessDenied: + pass + + p = psutil.Process() + with pytest.raises(TypeError): + p.nice("str") + init = p.nice() + self.addCleanup(cleanup, init) + + if WINDOWS: + highest_prio = None + for prio in [ + psutil.IDLE_PRIORITY_CLASS, + psutil.BELOW_NORMAL_PRIORITY_CLASS, + psutil.NORMAL_PRIORITY_CLASS, + psutil.ABOVE_NORMAL_PRIORITY_CLASS, + psutil.HIGH_PRIORITY_CLASS, + psutil.REALTIME_PRIORITY_CLASS, + ]: + with self.subTest(prio=prio): + try: + p.nice(prio) + except psutil.AccessDenied: + pass + else: + new_prio = p.nice() + # The OS may limit our maximum priority, + # even if the function succeeds. For higher + # priorities, we match either the expected + # value or the highest so far. + if prio in { + psutil.ABOVE_NORMAL_PRIORITY_CLASS, + psutil.HIGH_PRIORITY_CLASS, + psutil.REALTIME_PRIORITY_CLASS, + }: + if new_prio == prio or highest_prio is None: + highest_prio = prio + assert new_prio == highest_prio + else: + assert new_prio == prio + else: + try: + if hasattr(os, "getpriority"): + assert ( + os.getpriority(os.PRIO_PROCESS, os.getpid()) + == p.nice() + ) + p.nice(1) + assert p.nice() == 1 + if hasattr(os, "getpriority"): + assert ( + os.getpriority(os.PRIO_PROCESS, os.getpid()) + == p.nice() + ) + # XXX - going back to previous nice value raises + # AccessDenied on MACOS + if not MACOS: + p.nice(0) + assert p.nice() == 0 + except psutil.AccessDenied: + pass + + def test_status(self): + p = psutil.Process() + assert p.status() == psutil.STATUS_RUNNING + + def test_username(self): + p = self.spawn_psproc() + username = p.username() + if WINDOWS: + domain, username = username.split('\\') + getpass_user = getpass.getuser() + if getpass_user.endswith('$'): + # When running as a service account (most likely to be + # NetworkService), these user name calculations don't produce + # the same result, causing the test to fail. + raise pytest.skip('running as service account') + assert username == getpass_user + if 'USERDOMAIN' in os.environ: + assert domain == os.environ['USERDOMAIN'] + else: + assert username == getpass.getuser() + + def test_cwd(self): + p = self.spawn_psproc() + assert p.cwd() == os.getcwd() + + def test_cwd_2(self): + cmd = [ + PYTHON_EXE, + "-c", + ( + "import os, time; os.chdir('..'); [time.sleep(0.1) for x in" + " range(100)]" + ), + ] + p = self.spawn_psproc(cmd) + call_until(lambda: p.cwd() == os.path.dirname(os.getcwd())) + + @pytest.mark.skipif(not HAS_CPU_AFFINITY, reason="not supported") + def test_cpu_affinity(self): + p = psutil.Process() + initial = p.cpu_affinity() + assert initial, initial + self.addCleanup(p.cpu_affinity, initial) + + if hasattr(os, "sched_getaffinity"): + assert initial == list(os.sched_getaffinity(p.pid)) + assert len(initial) == len(set(initial)) + + all_cpus = list(range(len(psutil.cpu_percent(percpu=True)))) + for n in all_cpus: + p.cpu_affinity([n]) + assert p.cpu_affinity() == [n] + if hasattr(os, "sched_getaffinity"): + assert p.cpu_affinity() == list(os.sched_getaffinity(p.pid)) + # also test num_cpu() + if hasattr(p, "num_cpu"): + assert p.cpu_affinity()[0] == p.num_cpu() + + # [] is an alias for "all eligible CPUs"; on Linux this may + # not be equal to all available CPUs, see: + # https://github.com/giampaolo/psutil/issues/956 + p.cpu_affinity([]) + if LINUX: + assert p.cpu_affinity() == p._proc._get_eligible_cpus() + else: + assert p.cpu_affinity() == all_cpus + if hasattr(os, "sched_getaffinity"): + assert p.cpu_affinity() == list(os.sched_getaffinity(p.pid)) + + with pytest.raises(TypeError): + p.cpu_affinity(1) + p.cpu_affinity(initial) + # it should work with all iterables, not only lists + p.cpu_affinity(set(all_cpus)) + p.cpu_affinity(tuple(all_cpus)) + + @pytest.mark.skipif(not HAS_CPU_AFFINITY, reason="not supported") + def test_cpu_affinity_errs(self): + p = self.spawn_psproc() + invalid_cpu = [len(psutil.cpu_times(percpu=True)) + 10] + with pytest.raises(ValueError): + p.cpu_affinity(invalid_cpu) + with pytest.raises(ValueError): + p.cpu_affinity(range(10000, 11000)) + with pytest.raises((TypeError, ValueError)): + p.cpu_affinity([0, "1"]) + with pytest.raises(ValueError): + p.cpu_affinity([0, -1]) + + @pytest.mark.skipif(not HAS_CPU_AFFINITY, reason="not supported") + def test_cpu_affinity_all_combinations(self): + p = psutil.Process() + initial = p.cpu_affinity() + assert initial, initial + self.addCleanup(p.cpu_affinity, initial) + + # All possible CPU set combinations. + if len(initial) > 12: + initial = initial[:12] # ...otherwise it will take forever + combos = [] + for i in range(len(initial) + 1): + combos.extend( + list(subset) + for subset in itertools.combinations(initial, i) + if subset + ) + + for combo in combos: + p.cpu_affinity(combo) + assert sorted(p.cpu_affinity()) == sorted(combo) + + # TODO: #595 + @pytest.mark.skipif(BSD, reason="broken on BSD") + def test_open_files(self): + p = psutil.Process() + testfn = self.get_testfn() + files = p.open_files() + assert testfn not in files + with open(testfn, 'wb') as f: + f.write(b'x' * 1024) + f.flush() + # give the kernel some time to see the new file + call_until(lambda: len(p.open_files()) != len(files)) + files = p.open_files() + filenames = [os.path.normcase(x.path) for x in files] + assert os.path.normcase(testfn) in filenames + if LINUX: + for file in files: + if file.path == testfn: + assert file.position == 1024 + for file in files: + assert os.path.isfile(file.path), file + + # another process + cmdline = ( + f"import time; f = open(r'{testfn}', 'r'); [time.sleep(0.1) for x" + " in range(100)];" + ) + p = self.spawn_psproc([PYTHON_EXE, "-c", cmdline]) + + for x in range(100): + filenames = [os.path.normcase(x.path) for x in p.open_files()] + if testfn in filenames: + break + time.sleep(0.01) + else: + assert os.path.normcase(testfn) in filenames + for file in filenames: + assert os.path.isfile(file), file + + # TODO: #595 + @pytest.mark.skipif(BSD, reason="broken on BSD") + def test_open_files_2(self): + # test fd and path fields + p = psutil.Process() + normcase = os.path.normcase + testfn = self.get_testfn() + with open(testfn, 'w') as fileobj: + for file in p.open_files(): + if ( + normcase(file.path) == normcase(fileobj.name) + or file.fd == fileobj.fileno() + ): + break + else: + raise self.fail(f"no file found; files={p.open_files()!r}") + assert normcase(file.path) == normcase(fileobj.name) + if WINDOWS: + assert file.fd == -1 + else: + assert file.fd == fileobj.fileno() + # test positions + ntuple = p.open_files()[0] + assert ntuple[0] == ntuple.path + assert ntuple[1] == ntuple.fd + # test file is gone + assert fileobj.name not in p.open_files() + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_num_fds(self): + p = psutil.Process() + testfn = self.get_testfn() + start = p.num_fds() + file = open(testfn, 'w') # noqa: SIM115 + self.addCleanup(file.close) + assert p.num_fds() == start + 1 + sock = socket.socket() + self.addCleanup(sock.close) + assert p.num_fds() == start + 2 + file.close() + sock.close() + assert p.num_fds() == start + + @skip_on_not_implemented(only_if=LINUX) + @pytest.mark.skipif( + OPENBSD or NETBSD, reason="not reliable on OPENBSD & NETBSD" + ) + def test_num_ctx_switches(self): + p = psutil.Process() + before = sum(p.num_ctx_switches()) + for _ in range(2): + time.sleep(0.05) # this shall ensure a context switch happens + after = sum(p.num_ctx_switches()) + if after > before: + return + raise self.fail("num ctx switches still the same after 2 iterations") + + def test_ppid(self): + p = psutil.Process() + if hasattr(os, 'getppid'): + assert p.ppid() == os.getppid() + p = self.spawn_psproc() + assert p.ppid() == os.getpid() + + def test_parent(self): + p = self.spawn_psproc() + assert p.parent().pid == os.getpid() + + lowest_pid = psutil.pids()[0] + assert psutil.Process(lowest_pid).parent() is None + + def test_parent_multi(self): + parent = psutil.Process() + child, grandchild = self.spawn_children_pair() + assert grandchild.parent() == child + assert child.parent() == parent + + @retry_on_failure() + def test_parents(self): + parent = psutil.Process() + assert parent.parents() + child, grandchild = self.spawn_children_pair() + assert child.parents()[0] == parent + assert grandchild.parents()[0] == child + assert grandchild.parents()[1] == parent + + def test_children(self): + parent = psutil.Process() + assert not parent.children() + assert not parent.children(recursive=True) + # On Windows we set the flag to 0 in order to cancel out the + # CREATE_NO_WINDOW flag (enabled by default) which creates + # an extra "conhost.exe" child. + child = self.spawn_psproc(creationflags=0) + children1 = parent.children() + children2 = parent.children(recursive=True) + for children in (children1, children2): + assert len(children) == 1 + assert children[0].pid == child.pid + assert children[0].ppid() == parent.pid + + def test_children_recursive(self): + # Test children() against two sub processes, p1 and p2, where + # p1 (our child) spawned p2 (our grandchild). + parent = psutil.Process() + child, grandchild = self.spawn_children_pair() + assert parent.children() == [child] + assert parent.children(recursive=True) == [child, grandchild] + # If the intermediate process is gone there's no way for + # children() to recursively find it. + child.terminate() + child.wait() + assert not parent.children(recursive=True) + + def test_children_duplicates(self): + # find the process which has the highest number of children + table = collections.defaultdict(int) + for p in psutil.process_iter(): + try: + table[p.ppid()] += 1 + except psutil.Error: + pass + # this is the one, now let's make sure there are no duplicates + pid = max(table.items(), key=lambda x: x[1])[0] + if LINUX and pid == 0: + raise pytest.skip("PID 0") + p = psutil.Process(pid) + try: + c = p.children(recursive=True) + except psutil.AccessDenied: # windows + pass + else: + assert len(c) == len(set(c)) + + def test_parents_and_children(self): + parent = psutil.Process() + child, grandchild = self.spawn_children_pair() + # forward + children = parent.children(recursive=True) + assert len(children) == 2 + assert children[0] == child + assert children[1] == grandchild + # backward + parents = grandchild.parents() + assert parents[0] == child + assert parents[1] == parent + + def test_suspend_resume(self): + p = self.spawn_psproc() + p.suspend() + for _ in range(100): + if p.status() == psutil.STATUS_STOPPED: + break + time.sleep(0.01) + p.resume() + assert p.status() != psutil.STATUS_STOPPED + + def test_invalid_pid(self): + with pytest.raises(TypeError): + psutil.Process("1") + with pytest.raises(ValueError): + psutil.Process(-1) + + def test_as_dict(self): + p = psutil.Process() + d = p.as_dict(attrs=['exe', 'name']) + assert sorted(d.keys()) == ['exe', 'name'] + + p = psutil.Process(min(psutil.pids())) + d = p.as_dict(attrs=['net_connections'], ad_value='foo') + if not isinstance(d['net_connections'], list): + assert d['net_connections'] == 'foo' + + # Test ad_value is set on AccessDenied. + with mock.patch( + 'psutil.Process.nice', create=True, side_effect=psutil.AccessDenied + ): + assert p.as_dict(attrs=["nice"], ad_value=1) == {"nice": 1} + + # Test that NoSuchProcess bubbles up. + with mock.patch( + 'psutil.Process.nice', + create=True, + side_effect=psutil.NoSuchProcess(p.pid, "name"), + ): + with pytest.raises(psutil.NoSuchProcess): + p.as_dict(attrs=["nice"]) + + # Test that ZombieProcess is swallowed. + with mock.patch( + 'psutil.Process.nice', + create=True, + side_effect=psutil.ZombieProcess(p.pid, "name"), + ): + assert p.as_dict(attrs=["nice"], ad_value="foo") == {"nice": "foo"} + + # By default APIs raising NotImplementedError are + # supposed to be skipped. + with mock.patch( + 'psutil.Process.nice', create=True, side_effect=NotImplementedError + ): + d = p.as_dict() + assert 'nice' not in list(d.keys()) + # ...unless the user explicitly asked for some attr. + with pytest.raises(NotImplementedError): + p.as_dict(attrs=["nice"]) + + # errors + with pytest.raises(TypeError): + p.as_dict('name') + with pytest.raises(ValueError): + p.as_dict(['foo']) + with pytest.raises(ValueError): + p.as_dict(['foo', 'bar']) + + def test_oneshot(self): + p = psutil.Process() + with mock.patch("psutil._psplatform.Process.cpu_times") as m: + with p.oneshot(): + p.cpu_times() + p.cpu_times() + assert m.call_count == 1 + + with mock.patch("psutil._psplatform.Process.cpu_times") as m: + p.cpu_times() + p.cpu_times() + assert m.call_count == 2 + + def test_oneshot_twice(self): + # Test the case where the ctx manager is __enter__ed twice. + # The second __enter__ is supposed to resut in a NOOP. + p = psutil.Process() + with mock.patch("psutil._psplatform.Process.cpu_times") as m1: + with mock.patch("psutil._psplatform.Process.oneshot_enter") as m2: + with p.oneshot(): + p.cpu_times() + p.cpu_times() + with p.oneshot(): + p.cpu_times() + p.cpu_times() + assert m1.call_count == 1 + assert m2.call_count == 1 + + with mock.patch("psutil._psplatform.Process.cpu_times") as m: + p.cpu_times() + p.cpu_times() + assert m.call_count == 2 + + def test_oneshot_cache(self): + # Make sure oneshot() cache is nonglobal. Instead it's + # supposed to be bound to the Process instance, see: + # https://github.com/giampaolo/psutil/issues/1373 + p1, p2 = self.spawn_children_pair() + p1_ppid = p1.ppid() + p2_ppid = p2.ppid() + assert p1_ppid != p2_ppid + with p1.oneshot(): + assert p1.ppid() == p1_ppid + assert p2.ppid() == p2_ppid + with p2.oneshot(): + assert p1.ppid() == p1_ppid + assert p2.ppid() == p2_ppid + + def test_halfway_terminated_process(self): + # Test that NoSuchProcess exception gets raised in case the + # process dies after we create the Process object. + # Example: + # >>> proc = Process(1234) + # >>> time.sleep(2) # time-consuming task, process dies in meantime + # >>> proc.name() + # Refers to Issue #15 + def assert_raises_nsp(fun, fun_name): + try: + ret = fun() + except psutil.ZombieProcess: # differentiate from NSP + raise + except psutil.NoSuchProcess: + pass + except psutil.AccessDenied: + if OPENBSD and fun_name in {'threads', 'num_threads'}: + return + raise + else: + # NtQuerySystemInformation succeeds even if process is gone. + if WINDOWS and fun_name in {'exe', 'name'}: + return + raise self.fail( + f"{fun!r} didn't raise NSP and returned {ret!r} instead" + ) + + p = self.spawn_psproc() + p.terminate() + p.wait() + if WINDOWS: # XXX + call_until(lambda: p.pid not in psutil.pids()) + self.assertProcessGone(p) + + ns = process_namespace(p) + for fun, name in ns.iter(ns.all): + assert_raises_nsp(fun, name) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_zombie_process(self): + _parent, zombie = self.spawn_zombie() + self.assertProcessZombie(zombie) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_zombie_process_is_running_w_exc(self): + # Emulate a case where internally is_running() raises + # ZombieProcess. + p = psutil.Process() + with mock.patch( + "psutil.Process", side_effect=psutil.ZombieProcess(0) + ) as m: + assert p.is_running() + assert m.called + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_zombie_process_status_w_exc(self): + # Emulate a case where internally status() raises + # ZombieProcess. + p = psutil.Process() + with mock.patch( + "psutil._psplatform.Process.status", + side_effect=psutil.ZombieProcess(0), + ) as m: + assert p.status() == psutil.STATUS_ZOMBIE + assert m.called + + def test_reused_pid(self): + # Emulate a case where PID has been reused by another process. + subp = self.spawn_testproc() + p = psutil.Process(subp.pid) + p._ident = (p.pid, p.create_time() + 100) + + list(psutil.process_iter()) + assert p.pid in psutil._pmap + assert not p.is_running() + + # make sure is_running() removed PID from process_iter() + # internal cache + with mock.patch.object(psutil._common, "PSUTIL_DEBUG", True): + with contextlib.redirect_stderr(io.StringIO()) as f: + list(psutil.process_iter()) + assert ( + f"refreshing Process instance for reused PID {p.pid}" + in f.getvalue() + ) + assert p.pid not in psutil._pmap + + assert p != psutil.Process(subp.pid) + msg = "process no longer exists and its PID has been reused" + ns = process_namespace(p) + for fun, name in ns.iter(ns.setters + ns.killers, clear_cache=False): + with self.subTest(name=name): + with pytest.raises(psutil.NoSuchProcess, match=msg): + fun() + + assert "terminated + PID reused" in str(p) + assert "terminated + PID reused" in repr(p) + + with pytest.raises(psutil.NoSuchProcess, match=msg): + p.ppid() + with pytest.raises(psutil.NoSuchProcess, match=msg): + p.parent() + with pytest.raises(psutil.NoSuchProcess, match=msg): + p.parents() + with pytest.raises(psutil.NoSuchProcess, match=msg): + p.children() + + def test_pid_0(self): + # Process(0) is supposed to work on all platforms except Linux + if 0 not in psutil.pids(): + with pytest.raises(psutil.NoSuchProcess): + psutil.Process(0) + # These 2 are a contradiction, but "ps" says PID 1's parent + # is PID 0. + assert not psutil.pid_exists(0) + assert psutil.Process(1).ppid() == 0 + return + + p = psutil.Process(0) + exc = psutil.AccessDenied if WINDOWS else ValueError + with pytest.raises(exc): + p.wait() + with pytest.raises(exc): + p.terminate() + with pytest.raises(exc): + p.suspend() + with pytest.raises(exc): + p.resume() + with pytest.raises(exc): + p.kill() + with pytest.raises(exc): + p.send_signal(signal.SIGTERM) + + # test all methods + ns = process_namespace(p) + for fun, name in ns.iter(ns.getters + ns.setters): + try: + ret = fun() + except psutil.AccessDenied: + pass + else: + if name in {"uids", "gids"}: + assert ret.real == 0 + elif name == "username": + user = 'NT AUTHORITY\\SYSTEM' if WINDOWS else 'root' + assert p.username() == user + elif name == "name": + assert name, name + + if not OPENBSD: + assert 0 in psutil.pids() + assert psutil.pid_exists(0) + + @pytest.mark.skipif(not HAS_ENVIRON, reason="not supported") + def test_environ(self): + def clean_dict(d): + exclude = ["PLAT", "HOME", "PYTEST_CURRENT_TEST", "PYTEST_VERSION"] + if MACOS: + exclude.extend([ + "__CF_USER_TEXT_ENCODING", + "VERSIONER_PYTHON_PREFER_32_BIT", + "VERSIONER_PYTHON_VERSION", + "VERSIONER_PYTHON_VERSION", + ]) + for name in exclude: + d.pop(name, None) + return { + k.replace("\r", "").replace("\n", ""): v.replace( + "\r", "" + ).replace("\n", "") + for k, v in d.items() + } + + self.maxDiff = None + p = psutil.Process() + d1 = clean_dict(p.environ()) + d2 = clean_dict(os.environ.copy()) + if not OSX and GITHUB_ACTIONS: + assert d1 == d2 + + @pytest.mark.skipif(not HAS_ENVIRON, reason="not supported") + @pytest.mark.skipif(not POSIX, reason="POSIX only") + @pytest.mark.skipif( + MACOS_11PLUS, + reason="macOS 11+ can't get another process environment, issue #2084", + ) + @pytest.mark.skipif( + NETBSD, reason="sometimes fails on `assert is_running()`" + ) + def test_weird_environ(self): + # environment variables can contain values without an equals sign + code = textwrap.dedent(""" + #include + #include + + char * const argv[] = {"cat", 0}; + char * const envp[] = {"A=1", "X", "C=3", 0}; + + int main(void) { + // Close stderr on exec so parent can wait for the + // execve to finish. + if (fcntl(2, F_SETFD, FD_CLOEXEC) != 0) + return 0; + return execve("/bin/cat", argv, envp); + } + """) + cexe = create_c_exe(self.get_testfn(), c_code=code) + sproc = self.spawn_testproc( + [cexe], stdin=subprocess.PIPE, stderr=subprocess.PIPE + ) + p = psutil.Process(sproc.pid) + wait_for_pid(p.pid) + assert p.is_running() + # Wait for process to exec or exit. + assert sproc.stderr.read() == b"" + if MACOS and CI_TESTING: + try: + env = p.environ() + except psutil.AccessDenied: + # XXX: fails sometimes with: + # PermissionError from 'sysctl(KERN_PROCARGS2) -> EIO' + return + else: + env = p.environ() + assert env == {"A": "1", "C": "3"} + sproc.communicate() + assert sproc.returncode == 0 + + +# =================================================================== +# --- psutil.Popen tests +# =================================================================== + + +class TestPopen(PsutilTestCase): + """Tests for psutil.Popen class.""" + + @classmethod + def tearDownClass(cls): + reap_children() + + def test_misc(self): + # XXX this test causes a ResourceWarning because + # psutil.__subproc instance doesn't get properly freed. + # Not sure what to do though. + cmd = [ + PYTHON_EXE, + "-c", + "import time; [time.sleep(0.1) for x in range(100)];", + ] + with psutil.Popen( + cmd, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + env=PYTHON_EXE_ENV, + ) as proc: + proc.name() + proc.cpu_times() + proc.stdin # noqa: B018 + assert dir(proc) + with pytest.raises(AttributeError): + proc.foo # noqa: B018 + proc.terminate() + if POSIX: + assert proc.wait(5) == -signal.SIGTERM + else: + assert proc.wait(5) == signal.SIGTERM + + def test_ctx_manager(self): + with psutil.Popen( + [PYTHON_EXE, "-V"], + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + stdin=subprocess.PIPE, + env=PYTHON_EXE_ENV, + ) as proc: + proc.communicate() + assert proc.stdout.closed + assert proc.stderr.closed + assert proc.stdin.closed + assert proc.returncode == 0 + + def test_kill_terminate(self): + # subprocess.Popen()'s terminate(), kill() and send_signal() do + # not raise exception after the process is gone. psutil.Popen + # diverges from that. + cmd = [ + PYTHON_EXE, + "-c", + "import time; [time.sleep(0.1) for x in range(100)];", + ] + with psutil.Popen( + cmd, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + env=PYTHON_EXE_ENV, + ) as proc: + proc.terminate() + proc.wait() + with pytest.raises(psutil.NoSuchProcess): + proc.terminate() + with pytest.raises(psutil.NoSuchProcess): + proc.kill() + with pytest.raises(psutil.NoSuchProcess): + proc.send_signal(signal.SIGTERM) + if WINDOWS: + with pytest.raises(psutil.NoSuchProcess): + proc.send_signal(signal.CTRL_C_EVENT) + with pytest.raises(psutil.NoSuchProcess): + proc.send_signal(signal.CTRL_BREAK_EVENT) + + def test__getattribute__(self): + cmd = [ + PYTHON_EXE, + "-c", + "import time; [time.sleep(0.1) for x in range(100)];", + ] + with psutil.Popen( + cmd, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + env=PYTHON_EXE_ENV, + ) as proc: + proc.terminate() + proc.wait() + with pytest.raises(AttributeError): + proc.foo # noqa: B018 diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_process_all.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_process_all.py new file mode 100644 index 0000000..aaa3fa0 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_process_all.py @@ -0,0 +1,535 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Iterate over all process PIDs and for each one of them invoke and +test all psutil.Process() methods. +""" + +import enum +import errno +import multiprocessing +import os +import stat +import time +import traceback + +import psutil +from psutil import AIX +from psutil import BSD +from psutil import FREEBSD +from psutil import LINUX +from psutil import MACOS +from psutil import NETBSD +from psutil import OPENBSD +from psutil import OSX +from psutil import POSIX +from psutil import WINDOWS +from psutil.tests import CI_TESTING +from psutil.tests import PYTEST_PARALLEL +from psutil.tests import VALID_PROC_STATUSES +from psutil.tests import PsutilTestCase +from psutil.tests import check_connection_ntuple +from psutil.tests import create_sockets +from psutil.tests import is_namedtuple +from psutil.tests import is_win_secure_system_proc +from psutil.tests import process_namespace +from psutil.tests import pytest + + +# Cuts the time in half, but (e.g.) on macOS the process pool stays +# alive after join() (multiprocessing bug?), messing up other tests. +USE_PROC_POOL = LINUX and not CI_TESTING and not PYTEST_PARALLEL + + +def proc_info(pid): + tcase = PsutilTestCase() + + def check_exception(exc, proc, name, ppid): + tcase.assertEqual(exc.pid, pid) + if exc.name is not None: + tcase.assertEqual(exc.name, name) + if isinstance(exc, psutil.ZombieProcess): + tcase.assertProcessZombie(proc) + if exc.ppid is not None: + tcase.assertGreaterEqual(exc.ppid, 0) + tcase.assertEqual(exc.ppid, ppid) + elif isinstance(exc, psutil.NoSuchProcess): + tcase.assertProcessGone(proc) + str(exc) + repr(exc) + + def do_wait(): + if pid != 0: + try: + proc.wait(0) + except psutil.Error as exc: + check_exception(exc, proc, name, ppid) + + try: + proc = psutil.Process(pid) + except psutil.NoSuchProcess: + tcase.assertPidGone(pid) + return {} + try: + d = proc.as_dict(['ppid', 'name']) + except psutil.NoSuchProcess: + tcase.assertProcessGone(proc) + else: + name, ppid = d['name'], d['ppid'] + info = {'pid': proc.pid} + ns = process_namespace(proc) + # We don't use oneshot() because in order not to fool + # check_exception() in case of NSP. + for fun, fun_name in ns.iter(ns.getters, clear_cache=False): + try: + info[fun_name] = fun() + except psutil.Error as exc: + check_exception(exc, proc, name, ppid) + continue + do_wait() + return info + + +class TestFetchAllProcesses(PsutilTestCase): + """Test which iterates over all running processes and performs + some sanity checks against Process API's returned values. + Uses a process pool to get info about all processes. + """ + + def setUp(self): + psutil._set_debug(False) + # Using a pool in a CI env may result in deadlock, see: + # https://github.com/giampaolo/psutil/issues/2104 + if USE_PROC_POOL: + self.pool = multiprocessing.Pool() + + def tearDown(self): + psutil._set_debug(True) + if USE_PROC_POOL: + self.pool.terminate() + self.pool.join() + + def iter_proc_info(self): + # Fixes "can't pickle : it's not the + # same object as test_process_all.proc_info". + from psutil.tests.test_process_all import proc_info + + if USE_PROC_POOL: + return self.pool.imap_unordered(proc_info, psutil.pids()) + else: + ls = [proc_info(pid) for pid in psutil.pids()] + return ls + + def test_all(self): + failures = [] + for info in self.iter_proc_info(): + for name, value in info.items(): + meth = getattr(self, name) + try: + meth(value, info) + except Exception: # noqa: BLE001 + s = '\n' + '=' * 70 + '\n' + s += ( + "FAIL: name=test_{}, pid={}, ret={}\ninfo={}\n".format( + name, + info['pid'], + repr(value), + info, + ) + ) + s += '-' * 70 + s += f"\n{traceback.format_exc()}" + s = "\n".join((" " * 4) + i for i in s.splitlines()) + "\n" + failures.append(s) + else: + if value not in (0, 0.0, [], None, '', {}): + assert value, value + if failures: + raise self.fail(''.join(failures)) + + def cmdline(self, ret, info): + assert isinstance(ret, list) + for part in ret: + assert isinstance(part, str) + + def exe(self, ret, info): + assert isinstance(ret, str) + assert ret.strip() == ret + if ret: + if WINDOWS and not ret.endswith('.exe'): + return # May be "Registry", "MemCompression", ... + assert os.path.isabs(ret), ret + # Note: os.stat() may return False even if the file is there + # hence we skip the test, see: + # http://stackoverflow.com/questions/3112546/os-path-exists-lies + if POSIX and os.path.isfile(ret): + if hasattr(os, 'access') and hasattr(os, "X_OK"): + # XXX: may fail on MACOS + try: + assert os.access(ret, os.X_OK) + except AssertionError: + if os.path.exists(ret) and not CI_TESTING: + raise + + def pid(self, ret, info): + assert isinstance(ret, int) + assert ret >= 0 + + def ppid(self, ret, info): + assert isinstance(ret, int) + assert ret >= 0 + proc_info(ret) + + def name(self, ret, info): + assert isinstance(ret, str) + if WINDOWS and not ret and is_win_secure_system_proc(info['pid']): + # https://github.com/giampaolo/psutil/issues/2338 + return + # on AIX, "" processes don't have names + if not AIX: + assert ret, repr(ret) + + def create_time(self, ret, info): + assert isinstance(ret, float) + try: + assert ret >= 0 + except AssertionError: + # XXX + if OPENBSD and info['status'] == psutil.STATUS_ZOMBIE: + pass + else: + raise + # this can't be taken for granted on all platforms + # self.assertGreaterEqual(ret, psutil.boot_time()) + # make sure returned value can be pretty printed + # with strftime + time.strftime("%Y %m %d %H:%M:%S", time.localtime(ret)) + + def uids(self, ret, info): + assert is_namedtuple(ret) + for uid in ret: + assert isinstance(uid, int) + assert uid >= 0 + + def gids(self, ret, info): + assert is_namedtuple(ret) + # note: testing all gids as above seems not to be reliable for + # gid == 30 (nodoby); not sure why. + for gid in ret: + assert isinstance(gid, int) + if not MACOS and not NETBSD: + assert gid >= 0 + + def username(self, ret, info): + assert isinstance(ret, str) + assert ret.strip() == ret + assert ret.strip() + + def status(self, ret, info): + assert isinstance(ret, str) + assert ret, ret + assert ret != '?' # XXX + assert ret in VALID_PROC_STATUSES + + def io_counters(self, ret, info): + assert is_namedtuple(ret) + for field in ret: + assert isinstance(field, int) + if field != -1: + assert field >= 0 + + def ionice(self, ret, info): + if LINUX: + assert isinstance(ret.ioclass, int) + assert isinstance(ret.value, int) + assert ret.ioclass >= 0 + assert ret.value >= 0 + else: # Windows, Cygwin + choices = [ + psutil.IOPRIO_VERYLOW, + psutil.IOPRIO_LOW, + psutil.IOPRIO_NORMAL, + psutil.IOPRIO_HIGH, + ] + assert isinstance(ret, int) + assert ret >= 0 + assert ret in choices + + def num_threads(self, ret, info): + assert isinstance(ret, int) + if WINDOWS and ret == 0 and is_win_secure_system_proc(info['pid']): + # https://github.com/giampaolo/psutil/issues/2338 + return + assert ret >= 1 + + def threads(self, ret, info): + assert isinstance(ret, list) + for t in ret: + assert is_namedtuple(t) + assert t.id >= 0 + assert t.user_time >= 0 + assert t.system_time >= 0 + for field in t: + assert isinstance(field, (int, float)) + + def cpu_times(self, ret, info): + assert is_namedtuple(ret) + for n in ret: + assert isinstance(n, float) + assert n >= 0 + # TODO: check ntuple fields + + def cpu_percent(self, ret, info): + assert isinstance(ret, float) + assert 0.0 <= ret <= 100.0, ret + + def cpu_num(self, ret, info): + assert isinstance(ret, int) + if FREEBSD and ret == -1: + return + assert ret >= 0 + if psutil.cpu_count() == 1: + assert ret == 0 + assert ret in list(range(psutil.cpu_count())) + + def memory_info(self, ret, info): + assert is_namedtuple(ret) + for value in ret: + assert isinstance(value, int) + assert value >= 0 + if WINDOWS: + assert ret.peak_wset >= ret.wset + assert ret.peak_paged_pool >= ret.paged_pool + assert ret.peak_nonpaged_pool >= ret.nonpaged_pool + assert ret.peak_pagefile >= ret.pagefile + + def memory_full_info(self, ret, info): + assert is_namedtuple(ret) + total = psutil.virtual_memory().total + for name in ret._fields: + value = getattr(ret, name) + assert isinstance(value, int) + assert value >= 0 + if LINUX or (OSX and name in {'vms', 'data'}): + # On Linux there are processes (e.g. 'goa-daemon') whose + # VMS is incredibly high for some reason. + continue + assert value <= total, name + + if LINUX: + assert ret.pss >= ret.uss + + def open_files(self, ret, info): + assert isinstance(ret, list) + for f in ret: + assert isinstance(f.fd, int) + assert isinstance(f.path, str) + assert f.path.strip() == f.path + if WINDOWS: + assert f.fd == -1 + elif LINUX: + assert isinstance(f.position, int) + assert isinstance(f.mode, str) + assert isinstance(f.flags, int) + assert f.position >= 0 + assert f.mode in {'r', 'w', 'a', 'r+', 'a+'} + assert f.flags > 0 + elif BSD and not f.path: + # XXX see: https://github.com/giampaolo/psutil/issues/595 + continue + assert os.path.isabs(f.path), f + try: + st = os.stat(f.path) + except FileNotFoundError: + pass + else: + assert stat.S_ISREG(st.st_mode), f + + def num_fds(self, ret, info): + assert isinstance(ret, int) + assert ret >= 0 + + def net_connections(self, ret, info): + with create_sockets(): + assert len(ret) == len(set(ret)) + for conn in ret: + assert is_namedtuple(conn) + check_connection_ntuple(conn) + + def cwd(self, ret, info): + assert isinstance(ret, str) + assert ret.strip() == ret + if ret: + assert os.path.isabs(ret), ret + try: + st = os.stat(ret) + except OSError as err: + if WINDOWS and psutil._psplatform.is_permission_err(err): + pass + # directory has been removed in mean time + elif err.errno != errno.ENOENT: + raise + else: + assert stat.S_ISDIR(st.st_mode) + + def memory_percent(self, ret, info): + assert isinstance(ret, float) + assert 0 <= ret <= 100, ret + + def is_running(self, ret, info): + assert isinstance(ret, bool) + + def cpu_affinity(self, ret, info): + assert isinstance(ret, list) + assert ret != [] + cpus = list(range(psutil.cpu_count())) + for n in ret: + assert isinstance(n, int) + assert n in cpus + + def terminal(self, ret, info): + assert isinstance(ret, (str, type(None))) + if ret is not None: + assert os.path.isabs(ret), ret + assert os.path.exists(ret), ret + + def memory_maps(self, ret, info): + for nt in ret: + assert isinstance(nt.addr, str) + assert isinstance(nt.perms, str) + assert isinstance(nt.path, str) + for fname in nt._fields: + value = getattr(nt, fname) + if fname == 'path': + if value.startswith(("[", "anon_inode:")): # linux + continue + if BSD and value == "pvclock": # seen on FreeBSD + continue + assert os.path.isabs(nt.path), nt.path + # commented as on Linux we might get + # '/foo/bar (deleted)' + # assert os.path.exists(nt.path), nt.path + elif fname == 'addr': + assert value, repr(value) + elif fname == 'perms': + if not WINDOWS: + assert value, repr(value) + else: + assert isinstance(value, int) + assert value >= 0 + + def num_handles(self, ret, info): + assert isinstance(ret, int) + assert ret >= 0 + + def nice(self, ret, info): + assert isinstance(ret, int) + if POSIX: + assert -20 <= ret <= 20, ret + else: + priorities = [ + getattr(psutil, x) + for x in dir(psutil) + if x.endswith('_PRIORITY_CLASS') + ] + assert ret in priorities + assert isinstance(ret, enum.IntEnum) + + def num_ctx_switches(self, ret, info): + assert is_namedtuple(ret) + for value in ret: + assert isinstance(value, int) + assert value >= 0 + + def rlimit(self, ret, info): + assert isinstance(ret, tuple) + assert len(ret) == 2 + assert ret[0] >= -1 + assert ret[1] >= -1 + + def environ(self, ret, info): + assert isinstance(ret, dict) + for k, v in ret.items(): + assert isinstance(k, str) + assert isinstance(v, str) + + +class TestPidsRange(PsutilTestCase): + """Given pid_exists() return value for a range of PIDs which may or + may not exist, make sure that psutil.Process() and psutil.pids() + agree with pid_exists(). This guarantees that the 3 APIs are all + consistent with each other. See: + https://github.com/giampaolo/psutil/issues/2359 + + XXX - Note about Windows: it turns out there are some "hidden" PIDs + which are not returned by psutil.pids() and are also not revealed + by taskmgr.exe and ProcessHacker, still they can be instantiated by + psutil.Process() and queried. One of such PIDs is "conhost.exe". + Running as_dict() for it reveals that some Process() APIs + erroneously raise NoSuchProcess, so we know we have problem there. + Let's ignore this for now, since it's quite a corner case (who even + imagined hidden PIDs existed on Windows?). + """ + + def setUp(self): + psutil._set_debug(False) + + def tearDown(self): + psutil._set_debug(True) + + def test_it(self): + def is_linux_tid(pid): + try: + f = open(f"/proc/{pid}/status", "rb") # noqa: SIM115 + except FileNotFoundError: + return False + else: + with f: + for line in f: + if line.startswith(b"Tgid:"): + tgid = int(line.split()[1]) + # If tgid and pid are different then we're + # dealing with a process TID. + return tgid != pid + raise ValueError("'Tgid' line not found") + + def check(pid): + # In case of failure retry up to 3 times in order to avoid + # race conditions, especially when running in a CI + # environment where PIDs may appear and disappear at any + # time. + x = 3 + while True: + exists = psutil.pid_exists(pid) + try: + if exists: + psutil.Process(pid) + if not WINDOWS: # see docstring + assert pid in psutil.pids() + else: + # On OpenBSD thread IDs can be instantiated, + # and oneshot() succeeds, but other APIs fail + # with EINVAL. + if not OPENBSD: + with pytest.raises(psutil.NoSuchProcess): + psutil.Process(pid) + if not WINDOWS: # see docstring + assert pid not in psutil.pids() + except (psutil.Error, AssertionError): + x -= 1 + if x == 0: + raise + else: + return + + for pid in range(1, 3000): + if LINUX and is_linux_tid(pid): + # On Linux a TID (thread ID) can be passed to the + # Process class and is querable like a PID (process + # ID). Skip it. + continue + with self.subTest(pid=pid): + check(pid) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_scripts.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_scripts.py new file mode 100644 index 0000000..de0ad2a --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_scripts.py @@ -0,0 +1,240 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Test various scripts.""" + +import ast +import os +import shutil +import stat +import subprocess + +import pytest + +from psutil import POSIX +from psutil import WINDOWS +from psutil.tests import CI_TESTING +from psutil.tests import HAS_BATTERY +from psutil.tests import HAS_MEMORY_MAPS +from psutil.tests import HAS_SENSORS_BATTERY +from psutil.tests import HAS_SENSORS_FANS +from psutil.tests import HAS_SENSORS_TEMPERATURES +from psutil.tests import PYTHON_EXE +from psutil.tests import PYTHON_EXE_ENV +from psutil.tests import ROOT_DIR +from psutil.tests import SCRIPTS_DIR +from psutil.tests import PsutilTestCase +from psutil.tests import import_module_by_path +from psutil.tests import psutil +from psutil.tests import sh + + +INTERNAL_SCRIPTS_DIR = os.path.join(SCRIPTS_DIR, "internal") +SETUP_PY = os.path.join(ROOT_DIR, 'setup.py') + + +# =================================================================== +# --- Tests scripts in scripts/ directory +# =================================================================== + + +@pytest.mark.skipif( + CI_TESTING and not os.path.exists(SCRIPTS_DIR), + reason="can't find scripts/ directory", +) +class TestExampleScripts(PsutilTestCase): + @staticmethod + def assert_stdout(exe, *args, **kwargs): + kwargs.setdefault("env", PYTHON_EXE_ENV) + exe = os.path.join(SCRIPTS_DIR, exe) + cmd = [PYTHON_EXE, exe] + for arg in args: + cmd.append(arg) + try: + out = sh(cmd, **kwargs).strip() + except RuntimeError as err: + if 'AccessDenied' in str(err): + return str(err) + else: + raise + assert out, out + return out + + @staticmethod + def assert_syntax(exe): + exe = os.path.join(SCRIPTS_DIR, exe) + with open(exe, encoding="utf8") as f: + src = f.read() + ast.parse(src) + + def test_coverage(self): + # make sure all example scripts have a test method defined + meths = dir(self) + for name in os.listdir(SCRIPTS_DIR): + if name.endswith('.py'): + if 'test_' + os.path.splitext(name)[0] not in meths: + # self.assert_stdout(name) + raise self.fail( + "no test defined for" + f" {os.path.join(SCRIPTS_DIR, name)!r} script" + ) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_executable(self): + for root, dirs, files in os.walk(SCRIPTS_DIR): + for file in files: + if file.endswith('.py'): + path = os.path.join(root, file) + if not stat.S_IXUSR & os.stat(path)[stat.ST_MODE]: + raise self.fail(f"{path!r} is not executable") + + def test_disk_usage(self): + self.assert_stdout('disk_usage.py') + + def test_free(self): + self.assert_stdout('free.py') + + def test_meminfo(self): + self.assert_stdout('meminfo.py') + + def test_procinfo(self): + self.assert_stdout('procinfo.py', str(os.getpid())) + + @pytest.mark.skipif(CI_TESTING and not psutil.users(), reason="no users") + def test_who(self): + self.assert_stdout('who.py') + + def test_ps(self): + self.assert_stdout('ps.py') + + def test_pstree(self): + self.assert_stdout('pstree.py') + + def test_netstat(self): + self.assert_stdout('netstat.py') + + def test_ifconfig(self): + self.assert_stdout('ifconfig.py') + + @pytest.mark.skipif(not HAS_MEMORY_MAPS, reason="not supported") + def test_pmap(self): + self.assert_stdout('pmap.py', str(os.getpid())) + + def test_procsmem(self): + if 'uss' not in psutil.Process().memory_full_info()._fields: + raise pytest.skip("not supported") + self.assert_stdout('procsmem.py') + + def test_killall(self): + self.assert_syntax('killall.py') + + def test_nettop(self): + self.assert_syntax('nettop.py') + + def test_top(self): + self.assert_syntax('top.py') + + def test_iotop(self): + self.assert_syntax('iotop.py') + + def test_pidof(self): + output = self.assert_stdout('pidof.py', psutil.Process().name()) + assert str(os.getpid()) in output + + @pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") + def test_winservices(self): + self.assert_stdout('winservices.py') + + def test_cpu_distribution(self): + self.assert_syntax('cpu_distribution.py') + + @pytest.mark.skipif(not HAS_SENSORS_TEMPERATURES, reason="not supported") + def test_temperatures(self): + if not psutil.sensors_temperatures(): + raise pytest.skip("no temperatures") + self.assert_stdout('temperatures.py') + + @pytest.mark.skipif(not HAS_SENSORS_FANS, reason="not supported") + def test_fans(self): + if not psutil.sensors_fans(): + raise pytest.skip("no fans") + self.assert_stdout('fans.py') + + @pytest.mark.skipif(not HAS_SENSORS_BATTERY, reason="not supported") + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_battery(self): + self.assert_stdout('battery.py') + + @pytest.mark.skipif(not HAS_SENSORS_BATTERY, reason="not supported") + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_sensors(self): + self.assert_stdout('sensors.py') + + +# =================================================================== +# --- Tests scripts in scripts/internal/ directory +# =================================================================== + + +@pytest.mark.skipif( + CI_TESTING and not os.path.exists(INTERNAL_SCRIPTS_DIR), + reason="can't find scripts/internal/ directory", +) +class TestInternalScripts(PsutilTestCase): + @staticmethod + def ls(): + for name in os.listdir(INTERNAL_SCRIPTS_DIR): + if name.endswith(".py"): + yield os.path.join(INTERNAL_SCRIPTS_DIR, name) + + def test_syntax_all(self): + for path in self.ls(): + with open(path, encoding="utf8") as f: + data = f.read() + ast.parse(data) + + @pytest.mark.skipif(CI_TESTING, reason="not on CI") + def test_import_all(self): + for path in self.ls(): + try: + import_module_by_path(path) + except SystemExit: + pass + + +# =================================================================== +# --- Tests for setup.py script +# =================================================================== + + +@pytest.mark.skipif( + CI_TESTING and not os.path.exists(SETUP_PY), reason="can't find setup.py" +) +class TestSetupScript(PsutilTestCase): + def test_invocation(self): + module = import_module_by_path(SETUP_PY) + with pytest.raises(SystemExit): + module.setup() + assert module.get_version() == psutil.__version__ + + @pytest.mark.skipif( + not shutil.which("python2.7"), reason="python2.7 not installed" + ) + def test_python2(self): + # There's a duplicate of this test in scripts/internal + # directory, which is only executed by CI. We replicate it here + # to run it when developing locally. + p = subprocess.Popen( + [shutil.which("python2.7"), SETUP_PY], + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + universal_newlines=True, + ) + stdout, stderr = p.communicate() + assert p.wait() == 1 + assert not stdout + assert "psutil no longer supports Python 2.7" in stderr + assert "Latest version supporting Python 2.7 is" in stderr diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_sunos.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_sunos.py new file mode 100644 index 0000000..b5d9d35 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_sunos.py @@ -0,0 +1,39 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Sun OS specific tests.""" + +import os + +import psutil +from psutil import SUNOS +from psutil.tests import PsutilTestCase +from psutil.tests import pytest +from psutil.tests import sh + + +@pytest.mark.skipif(not SUNOS, reason="SUNOS only") +class SunOSSpecificTestCase(PsutilTestCase): + def test_swap_memory(self): + out = sh(f"env PATH=/usr/sbin:/sbin:{os.environ['PATH']} swap -l") + lines = out.strip().split('\n')[1:] + if not lines: + raise ValueError('no swap device(s) configured') + total = free = 0 + for line in lines: + fields = line.split() + total = int(fields[3]) * 512 + free = int(fields[4]) * 512 + used = total - free + + psutil_swap = psutil.swap_memory() + assert psutil_swap.total == total + assert psutil_swap.used == used + assert psutil_swap.free == free + + def test_cpu_count(self): + out = sh("/usr/sbin/psrinfo") + assert psutil.cpu_count() == len(out.split('\n')) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_system.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_system.py new file mode 100644 index 0000000..b961e1f --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_system.py @@ -0,0 +1,979 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Tests for system APIS.""" + +import datetime +import enum +import errno +import os +import platform +import pprint +import shutil +import signal +import socket +import sys +import time +from unittest import mock + +import psutil +from psutil import AIX +from psutil import BSD +from psutil import FREEBSD +from psutil import LINUX +from psutil import MACOS +from psutil import NETBSD +from psutil import OPENBSD +from psutil import POSIX +from psutil import SUNOS +from psutil import WINDOWS +from psutil._common import broadcast_addr +from psutil.tests import AARCH64 +from psutil.tests import ASCII_FS +from psutil.tests import CI_TESTING +from psutil.tests import GITHUB_ACTIONS +from psutil.tests import GLOBAL_TIMEOUT +from psutil.tests import HAS_BATTERY +from psutil.tests import HAS_CPU_FREQ +from psutil.tests import HAS_GETLOADAVG +from psutil.tests import HAS_NET_IO_COUNTERS +from psutil.tests import HAS_SENSORS_BATTERY +from psutil.tests import HAS_SENSORS_FANS +from psutil.tests import HAS_SENSORS_TEMPERATURES +from psutil.tests import IS_64BIT +from psutil.tests import MACOS_12PLUS +from psutil.tests import PYPY +from psutil.tests import UNICODE_SUFFIX +from psutil.tests import PsutilTestCase +from psutil.tests import check_net_address +from psutil.tests import pytest +from psutil.tests import retry_on_failure + + +# =================================================================== +# --- System-related API tests +# =================================================================== + + +class TestProcessIter(PsutilTestCase): + def test_pid_presence(self): + assert os.getpid() in [x.pid for x in psutil.process_iter()] + sproc = self.spawn_testproc() + assert sproc.pid in [x.pid for x in psutil.process_iter()] + p = psutil.Process(sproc.pid) + p.kill() + p.wait() + assert sproc.pid not in [x.pid for x in psutil.process_iter()] + + def test_no_duplicates(self): + ls = list(psutil.process_iter()) + assert sorted(ls, key=lambda x: x.pid) == sorted( + set(ls), key=lambda x: x.pid + ) + + def test_emulate_nsp(self): + list(psutil.process_iter()) # populate cache + for x in range(2): + with mock.patch( + 'psutil.Process.as_dict', + side_effect=psutil.NoSuchProcess(os.getpid()), + ): + assert not list(psutil.process_iter(attrs=["cpu_times"])) + psutil.process_iter.cache_clear() # repeat test without cache + + def test_emulate_access_denied(self): + list(psutil.process_iter()) # populate cache + for x in range(2): + with mock.patch( + 'psutil.Process.as_dict', + side_effect=psutil.AccessDenied(os.getpid()), + ): + with pytest.raises(psutil.AccessDenied): + list(psutil.process_iter(attrs=["cpu_times"])) + psutil.process_iter.cache_clear() # repeat test without cache + + def test_attrs(self): + for p in psutil.process_iter(attrs=['pid']): + assert list(p.info.keys()) == ['pid'] + # yield again + for p in psutil.process_iter(attrs=['pid']): + assert list(p.info.keys()) == ['pid'] + with pytest.raises(ValueError): + list(psutil.process_iter(attrs=['foo'])) + with mock.patch( + "psutil._psplatform.Process.cpu_times", + side_effect=psutil.AccessDenied(0, ""), + ) as m: + for p in psutil.process_iter(attrs=["pid", "cpu_times"]): + assert p.info['cpu_times'] is None + assert p.info['pid'] >= 0 + assert m.called + with mock.patch( + "psutil._psplatform.Process.cpu_times", + side_effect=psutil.AccessDenied(0, ""), + ) as m: + flag = object() + for p in psutil.process_iter( + attrs=["pid", "cpu_times"], ad_value=flag + ): + assert p.info['cpu_times'] is flag + assert p.info['pid'] >= 0 + assert m.called + + def test_cache_clear(self): + list(psutil.process_iter()) # populate cache + assert psutil._pmap + psutil.process_iter.cache_clear() + assert not psutil._pmap + + +class TestProcessAPIs(PsutilTestCase): + @pytest.mark.skipif( + PYPY and WINDOWS, + reason="spawn_testproc() unreliable on PYPY + WINDOWS", + ) + def test_wait_procs(self): + def callback(p): + pids.append(p.pid) + + pids = [] + sproc1 = self.spawn_testproc() + sproc2 = self.spawn_testproc() + sproc3 = self.spawn_testproc() + procs = [psutil.Process(x.pid) for x in (sproc1, sproc2, sproc3)] + with pytest.raises(ValueError): + psutil.wait_procs(procs, timeout=-1) + with pytest.raises(TypeError): + psutil.wait_procs(procs, callback=1) + t = time.time() + gone, alive = psutil.wait_procs(procs, timeout=0.01, callback=callback) + + assert time.time() - t < 0.5 + assert not gone + assert len(alive) == 3 + assert not pids + for p in alive: + assert not hasattr(p, 'returncode') + + @retry_on_failure(30) + def test_1(procs, callback): + gone, alive = psutil.wait_procs( + procs, timeout=0.03, callback=callback + ) + assert len(gone) == 1 + assert len(alive) == 2 + return gone, alive + + sproc3.terminate() + gone, alive = test_1(procs, callback) + assert sproc3.pid in [x.pid for x in gone] + if POSIX: + assert gone.pop().returncode == -signal.SIGTERM + else: + assert gone.pop().returncode == 1 + assert pids == [sproc3.pid] + for p in alive: + assert not hasattr(p, 'returncode') + + @retry_on_failure(30) + def test_2(procs, callback): + gone, alive = psutil.wait_procs( + procs, timeout=0.03, callback=callback + ) + assert len(gone) == 3 + assert len(alive) == 0 + return gone, alive + + sproc1.terminate() + sproc2.terminate() + gone, alive = test_2(procs, callback) + assert set(pids) == {sproc1.pid, sproc2.pid, sproc3.pid} + for p in gone: + assert hasattr(p, 'returncode') + + @pytest.mark.skipif( + PYPY and WINDOWS, + reason="spawn_testproc() unreliable on PYPY + WINDOWS", + ) + def test_wait_procs_no_timeout(self): + sproc1 = self.spawn_testproc() + sproc2 = self.spawn_testproc() + sproc3 = self.spawn_testproc() + procs = [psutil.Process(x.pid) for x in (sproc1, sproc2, sproc3)] + for p in procs: + p.terminate() + psutil.wait_procs(procs) + + def test_pid_exists(self): + sproc = self.spawn_testproc() + assert psutil.pid_exists(sproc.pid) + p = psutil.Process(sproc.pid) + p.kill() + p.wait() + assert not psutil.pid_exists(sproc.pid) + assert not psutil.pid_exists(-1) + assert psutil.pid_exists(0) == (0 in psutil.pids()) + + def test_pid_exists_2(self): + pids = psutil.pids() + for pid in pids: + try: + assert psutil.pid_exists(pid) + except AssertionError: + # in case the process disappeared in meantime fail only + # if it is no longer in psutil.pids() + time.sleep(0.1) + assert pid not in psutil.pids() + pids = range(max(pids) + 15000, max(pids) + 16000) + for pid in pids: + assert not psutil.pid_exists(pid) + + +class TestMiscAPIs(PsutilTestCase): + def test_boot_time(self): + bt = psutil.boot_time() + assert isinstance(bt, float) + assert bt > 0 + assert bt < time.time() + + @pytest.mark.skipif( + CI_TESTING and not psutil.users(), reason="unreliable on CI" + ) + def test_users(self): + users = psutil.users() + assert users + for user in users: + with self.subTest(user=user): + assert user.name + assert isinstance(user.name, str) + assert isinstance(user.terminal, (str, type(None))) + if user.host is not None: + assert isinstance(user.host, (str, type(None))) + user.terminal # noqa: B018 + user.host # noqa: B018 + assert user.started > 0.0 + datetime.datetime.fromtimestamp(user.started) + if WINDOWS or OPENBSD: + assert user.pid is None + else: + psutil.Process(user.pid) + + def test_os_constants(self): + names = [ + "POSIX", + "WINDOWS", + "LINUX", + "MACOS", + "FREEBSD", + "OPENBSD", + "NETBSD", + "BSD", + "SUNOS", + ] + for name in names: + assert isinstance(getattr(psutil, name), bool), name + + if os.name == 'posix': + assert psutil.POSIX + assert not psutil.WINDOWS + names.remove("POSIX") + if "linux" in sys.platform.lower(): + assert psutil.LINUX + names.remove("LINUX") + elif "bsd" in sys.platform.lower(): + assert psutil.BSD + assert [psutil.FREEBSD, psutil.OPENBSD, psutil.NETBSD].count( + True + ) == 1 + names.remove("BSD") + names.remove("FREEBSD") + names.remove("OPENBSD") + names.remove("NETBSD") + elif ( + "sunos" in sys.platform.lower() + or "solaris" in sys.platform.lower() + ): + assert psutil.SUNOS + names.remove("SUNOS") + elif "darwin" in sys.platform.lower(): + assert psutil.MACOS + names.remove("MACOS") + else: + assert psutil.WINDOWS + assert not psutil.POSIX + names.remove("WINDOWS") + + # assert all other constants are set to False + for name in names: + assert not getattr(psutil, name), name + + +class TestMemoryAPIs(PsutilTestCase): + def test_virtual_memory(self): + mem = psutil.virtual_memory() + assert mem.total > 0, mem + assert mem.available > 0, mem + assert 0 <= mem.percent <= 100, mem + assert mem.used > 0, mem + assert mem.free >= 0, mem + for name in mem._fields: + value = getattr(mem, name) + if name != 'percent': + assert isinstance(value, int) + if name != 'total': + if not value >= 0: + raise self.fail(f"{name!r} < 0 ({value})") + if value > mem.total: + raise self.fail( + f"{name!r} > total (total={mem.total}, {name}={value})" + ) + + def test_swap_memory(self): + mem = psutil.swap_memory() + assert mem._fields == ( + 'total', + 'used', + 'free', + 'percent', + 'sin', + 'sout', + ) + + assert mem.total >= 0, mem + assert mem.used >= 0, mem + if mem.total > 0: + # likely a system with no swap partition + assert mem.free > 0, mem + else: + assert mem.free == 0, mem + assert 0 <= mem.percent <= 100, mem + assert mem.sin >= 0, mem + assert mem.sout >= 0, mem + + +class TestCpuAPIs(PsutilTestCase): + def test_cpu_count_logical(self): + logical = psutil.cpu_count() + assert logical is not None + assert logical == len(psutil.cpu_times(percpu=True)) + assert logical >= 1 + + if os.path.exists("/proc/cpuinfo"): + with open("/proc/cpuinfo") as fd: + cpuinfo_data = fd.read() + if "physical id" not in cpuinfo_data: + raise pytest.skip("cpuinfo doesn't include physical id") + + def test_cpu_count_cores(self): + logical = psutil.cpu_count() + cores = psutil.cpu_count(logical=False) + if cores is None: + raise pytest.skip("cpu_count_cores() is None") + if WINDOWS and sys.getwindowsversion()[:2] <= (6, 1): # <= Vista + assert cores is None + else: + assert cores >= 1 + assert logical >= cores + + def test_cpu_count_none(self): + # https://github.com/giampaolo/psutil/issues/1085 + for val in (-1, 0, None): + with mock.patch( + 'psutil._psplatform.cpu_count_logical', return_value=val + ) as m: + assert psutil.cpu_count() is None + assert m.called + with mock.patch( + 'psutil._psplatform.cpu_count_cores', return_value=val + ) as m: + assert psutil.cpu_count(logical=False) is None + assert m.called + + def test_cpu_times(self): + # Check type, value >= 0, str(). + total = 0 + times = psutil.cpu_times() + sum(times) + for cp_time in times: + assert isinstance(cp_time, float) + assert cp_time >= 0.0 + total += cp_time + assert round(abs(total - sum(times)), 6) == 0 + str(times) + # CPU times are always supposed to increase over time + # or at least remain the same and that's because time + # cannot go backwards. + # Surprisingly sometimes this might not be the case (at + # least on Windows and Linux), see: + # https://github.com/giampaolo/psutil/issues/392 + # https://github.com/giampaolo/psutil/issues/645 + # if not WINDOWS: + # last = psutil.cpu_times() + # for x in range(100): + # new = psutil.cpu_times() + # for field in new._fields: + # new_t = getattr(new, field) + # last_t = getattr(last, field) + # self.assertGreaterEqual( + # new_t, last_t, + # msg="{} {}".format(new_t, last_t)) + # last = new + + def test_cpu_times_time_increases(self): + # Make sure time increases between calls. + t1 = sum(psutil.cpu_times()) + stop_at = time.time() + GLOBAL_TIMEOUT + while time.time() < stop_at: + t2 = sum(psutil.cpu_times()) + if t2 > t1: + return + raise self.fail("time remained the same") + + def test_per_cpu_times(self): + # Check type, value >= 0, str(). + for times in psutil.cpu_times(percpu=True): + total = 0 + sum(times) + for cp_time in times: + assert isinstance(cp_time, float) + assert cp_time >= 0.0 + total += cp_time + assert round(abs(total - sum(times)), 6) == 0 + str(times) + assert len(psutil.cpu_times(percpu=True)[0]) == len( + psutil.cpu_times(percpu=False) + ) + + # Note: in theory CPU times are always supposed to increase over + # time or remain the same but never go backwards. In practice + # sometimes this is not the case. + # This issue seemd to be afflict Windows: + # https://github.com/giampaolo/psutil/issues/392 + # ...but it turns out also Linux (rarely) behaves the same. + # last = psutil.cpu_times(percpu=True) + # for x in range(100): + # new = psutil.cpu_times(percpu=True) + # for index in range(len(new)): + # newcpu = new[index] + # lastcpu = last[index] + # for field in newcpu._fields: + # new_t = getattr(newcpu, field) + # last_t = getattr(lastcpu, field) + # self.assertGreaterEqual( + # new_t, last_t, msg="{} {}".format(lastcpu, newcpu)) + # last = new + + def test_per_cpu_times_2(self): + # Simulate some work load then make sure time have increased + # between calls. + tot1 = psutil.cpu_times(percpu=True) + giveup_at = time.time() + GLOBAL_TIMEOUT + while True: + if time.time() >= giveup_at: + return self.fail("timeout") + tot2 = psutil.cpu_times(percpu=True) + for t1, t2 in zip(tot1, tot2): + t1, t2 = psutil._cpu_busy_time(t1), psutil._cpu_busy_time(t2) + difference = t2 - t1 + if difference >= 0.05: + return None + + @pytest.mark.skipif( + CI_TESTING and OPENBSD, reason="unreliable on OPENBSD + CI" + ) + @retry_on_failure(30) + def test_cpu_times_comparison(self): + # Make sure the sum of all per cpu times is almost equal to + # base "one cpu" times. On OpenBSD the sum of per-CPUs is + # higher for some reason. + base = psutil.cpu_times() + per_cpu = psutil.cpu_times(percpu=True) + summed_values = base._make([sum(num) for num in zip(*per_cpu)]) + for field in base._fields: + with self.subTest(field=field, base=base, per_cpu=per_cpu): + assert ( + abs(getattr(base, field) - getattr(summed_values, field)) + < 2 + ) + + def _test_cpu_percent(self, percent, last_ret, new_ret): + try: + assert isinstance(percent, float) + assert percent >= 0.0 + assert percent <= 100.0 * psutil.cpu_count() + except AssertionError as err: + raise AssertionError( + "\n{}\nlast={}\nnew={}".format( + err, pprint.pformat(last_ret), pprint.pformat(new_ret) + ) + ) + + def test_cpu_percent(self): + last = psutil.cpu_percent(interval=0.001) + for _ in range(100): + new = psutil.cpu_percent(interval=None) + self._test_cpu_percent(new, last, new) + last = new + with pytest.raises(ValueError): + psutil.cpu_percent(interval=-1) + + def test_per_cpu_percent(self): + last = psutil.cpu_percent(interval=0.001, percpu=True) + assert len(last) == psutil.cpu_count() + for _ in range(100): + new = psutil.cpu_percent(interval=None, percpu=True) + for percent in new: + self._test_cpu_percent(percent, last, new) + last = new + with pytest.raises(ValueError): + psutil.cpu_percent(interval=-1, percpu=True) + + def test_cpu_times_percent(self): + last = psutil.cpu_times_percent(interval=0.001) + for _ in range(100): + new = psutil.cpu_times_percent(interval=None) + for percent in new: + self._test_cpu_percent(percent, last, new) + self._test_cpu_percent(sum(new), last, new) + last = new + with pytest.raises(ValueError): + psutil.cpu_times_percent(interval=-1) + + def test_per_cpu_times_percent(self): + last = psutil.cpu_times_percent(interval=0.001, percpu=True) + assert len(last) == psutil.cpu_count() + for _ in range(100): + new = psutil.cpu_times_percent(interval=None, percpu=True) + for cpu in new: + for percent in cpu: + self._test_cpu_percent(percent, last, new) + self._test_cpu_percent(sum(cpu), last, new) + last = new + + def test_per_cpu_times_percent_negative(self): + # see: https://github.com/giampaolo/psutil/issues/645 + psutil.cpu_times_percent(percpu=True) + zero_times = [ + x._make([0 for x in range(len(x._fields))]) + for x in psutil.cpu_times(percpu=True) + ] + with mock.patch('psutil.cpu_times', return_value=zero_times): + for cpu in psutil.cpu_times_percent(percpu=True): + for percent in cpu: + self._test_cpu_percent(percent, None, None) + + def test_cpu_stats(self): + # Tested more extensively in per-platform test modules. + infos = psutil.cpu_stats() + assert infos._fields == ( + 'ctx_switches', + 'interrupts', + 'soft_interrupts', + 'syscalls', + ) + for name in infos._fields: + value = getattr(infos, name) + assert value >= 0 + # on AIX, ctx_switches is always 0 + if not AIX and name in {'ctx_switches', 'interrupts'}: + assert value > 0 + + # TODO: remove this once 1892 is fixed + @pytest.mark.skipif( + MACOS and platform.machine() == 'arm64', reason="skipped due to #1892" + ) + @pytest.mark.skipif(not HAS_CPU_FREQ, reason="not supported") + def test_cpu_freq(self): + def check_ls(ls): + for nt in ls: + assert nt._fields == ('current', 'min', 'max') + if nt.max != 0.0: + assert nt.current <= nt.max + for name in nt._fields: + value = getattr(nt, name) + assert isinstance(value, (int, float)) + assert value >= 0 + + ls = psutil.cpu_freq(percpu=True) + if (FREEBSD or AARCH64) and not ls: + raise pytest.skip( + "returns empty list on FreeBSD and Linux aarch64" + ) + + assert ls, ls + check_ls([psutil.cpu_freq(percpu=False)]) + + if LINUX: + assert len(ls) == psutil.cpu_count() + + @pytest.mark.skipif(not HAS_GETLOADAVG, reason="not supported") + def test_getloadavg(self): + loadavg = psutil.getloadavg() + assert len(loadavg) == 3 + for load in loadavg: + assert isinstance(load, float) + assert load >= 0.0 + + +class TestDiskAPIs(PsutilTestCase): + @pytest.mark.skipif( + PYPY and not IS_64BIT, reason="unreliable on PYPY32 + 32BIT" + ) + def test_disk_usage(self): + usage = psutil.disk_usage(os.getcwd()) + assert usage._fields == ('total', 'used', 'free', 'percent') + + assert usage.total > 0, usage + assert usage.used > 0, usage + assert usage.free > 0, usage + assert usage.total > usage.used, usage + assert usage.total > usage.free, usage + assert 0 <= usage.percent <= 100, usage.percent + if hasattr(shutil, 'disk_usage'): + # py >= 3.3, see: http://bugs.python.org/issue12442 + shutil_usage = shutil.disk_usage(os.getcwd()) + tolerance = 5 * 1024 * 1024 # 5MB + assert usage.total == shutil_usage.total + assert abs(usage.free - shutil_usage.free) < tolerance + if not MACOS_12PLUS: + # see https://github.com/giampaolo/psutil/issues/2147 + assert abs(usage.used - shutil_usage.used) < tolerance + + # if path does not exist OSError ENOENT is expected across + # all platforms + fname = self.get_testfn() + with pytest.raises(FileNotFoundError): + psutil.disk_usage(fname) + + @pytest.mark.skipif(not ASCII_FS, reason="not an ASCII fs") + def test_disk_usage_unicode(self): + # See: https://github.com/giampaolo/psutil/issues/416 + with pytest.raises(UnicodeEncodeError): + psutil.disk_usage(UNICODE_SUFFIX) + + def test_disk_usage_bytes(self): + psutil.disk_usage(b'.') + + def test_disk_partitions(self): + def check_ntuple(nt): + assert isinstance(nt.device, str) + assert isinstance(nt.mountpoint, str) + assert isinstance(nt.fstype, str) + assert isinstance(nt.opts, str) + + # all = False + ls = psutil.disk_partitions(all=False) + assert ls + for disk in ls: + check_ntuple(disk) + if WINDOWS and 'cdrom' in disk.opts: + continue + if not POSIX: + assert os.path.exists(disk.device), disk + else: + # we cannot make any assumption about this, see: + # http://goo.gl/p9c43 + disk.device # noqa: B018 + # on modern systems mount points can also be files + assert os.path.exists(disk.mountpoint), disk + assert disk.fstype, disk + + # all = True + ls = psutil.disk_partitions(all=True) + assert ls + for disk in psutil.disk_partitions(all=True): + check_ntuple(disk) + if not WINDOWS and disk.mountpoint: + try: + os.stat(disk.mountpoint) + except OSError as err: + if GITHUB_ACTIONS and MACOS and err.errno == errno.EIO: + continue + # http://mail.python.org/pipermail/python-dev/ + # 2012-June/120787.html + if err.errno not in {errno.EPERM, errno.EACCES}: + raise + else: + assert os.path.exists(disk.mountpoint), disk + + # --- + + def find_mount_point(path): + path = os.path.abspath(path) + while not os.path.ismount(path): + path = os.path.dirname(path) + return path.lower() + + mount = find_mount_point(__file__) + mounts = [ + x.mountpoint.lower() + for x in psutil.disk_partitions(all=True) + if x.mountpoint + ] + assert mount in mounts + + @pytest.mark.skipif( + LINUX and not os.path.exists('/proc/diskstats'), + reason="/proc/diskstats not available on this linux version", + ) + @pytest.mark.skipif( + CI_TESTING and not psutil.disk_io_counters(), reason="unreliable on CI" + ) # no visible disks + def test_disk_io_counters(self): + def check_ntuple(nt): + assert nt[0] == nt.read_count + assert nt[1] == nt.write_count + assert nt[2] == nt.read_bytes + assert nt[3] == nt.write_bytes + if not (OPENBSD or NETBSD): + assert nt[4] == nt.read_time + assert nt[5] == nt.write_time + if LINUX: + assert nt[6] == nt.read_merged_count + assert nt[7] == nt.write_merged_count + assert nt[8] == nt.busy_time + elif FREEBSD: + assert nt[6] == nt.busy_time + for name in nt._fields: + assert getattr(nt, name) >= 0, nt + + ret = psutil.disk_io_counters(perdisk=False) + assert ret is not None, "no disks on this system?" + check_ntuple(ret) + ret = psutil.disk_io_counters(perdisk=True) + # make sure there are no duplicates + assert len(ret) == len(set(ret)) + for key in ret: + assert key, key + check_ntuple(ret[key]) + + def test_disk_io_counters_no_disks(self): + # Emulate a case where no disks are installed, see: + # https://github.com/giampaolo/psutil/issues/1062 + with mock.patch( + 'psutil._psplatform.disk_io_counters', return_value={} + ) as m: + assert psutil.disk_io_counters(perdisk=False) is None + assert psutil.disk_io_counters(perdisk=True) == {} + assert m.called + + +class TestNetAPIs(PsutilTestCase): + @pytest.mark.skipif(not HAS_NET_IO_COUNTERS, reason="not supported") + def test_net_io_counters(self): + def check_ntuple(nt): + assert nt[0] == nt.bytes_sent + assert nt[1] == nt.bytes_recv + assert nt[2] == nt.packets_sent + assert nt[3] == nt.packets_recv + assert nt[4] == nt.errin + assert nt[5] == nt.errout + assert nt[6] == nt.dropin + assert nt[7] == nt.dropout + assert nt.bytes_sent >= 0, nt + assert nt.bytes_recv >= 0, nt + assert nt.packets_sent >= 0, nt + assert nt.packets_recv >= 0, nt + assert nt.errin >= 0, nt + assert nt.errout >= 0, nt + assert nt.dropin >= 0, nt + assert nt.dropout >= 0, nt + + ret = psutil.net_io_counters(pernic=False) + check_ntuple(ret) + ret = psutil.net_io_counters(pernic=True) + assert ret != [] + for key in ret: + assert key + assert isinstance(key, str) + check_ntuple(ret[key]) + + @pytest.mark.skipif(not HAS_NET_IO_COUNTERS, reason="not supported") + def test_net_io_counters_no_nics(self): + # Emulate a case where no NICs are installed, see: + # https://github.com/giampaolo/psutil/issues/1062 + with mock.patch( + 'psutil._psplatform.net_io_counters', return_value={} + ) as m: + assert psutil.net_io_counters(pernic=False) is None + assert psutil.net_io_counters(pernic=True) == {} + assert m.called + + def test_net_if_addrs(self): + nics = psutil.net_if_addrs() + assert nics, nics + + nic_stats = psutil.net_if_stats() + + # Not reliable on all platforms (net_if_addrs() reports more + # interfaces). + # self.assertEqual(sorted(nics.keys()), + # sorted(psutil.net_io_counters(pernic=True).keys())) + + families = {socket.AF_INET, socket.AF_INET6, psutil.AF_LINK} + for nic, addrs in nics.items(): + assert isinstance(nic, str) + assert len(set(addrs)) == len(addrs) + for addr in addrs: + assert isinstance(addr.family, int) + assert isinstance(addr.address, str) + assert isinstance(addr.netmask, (str, type(None))) + assert isinstance(addr.broadcast, (str, type(None))) + assert addr.family in families + assert isinstance(addr.family, enum.IntEnum) + if nic_stats[nic].isup: + # Do not test binding to addresses of interfaces + # that are down + if addr.family == socket.AF_INET: + with socket.socket(addr.family) as s: + s.bind((addr.address, 0)) + elif addr.family == socket.AF_INET6: + info = socket.getaddrinfo( + addr.address, + 0, + socket.AF_INET6, + socket.SOCK_STREAM, + 0, + socket.AI_PASSIVE, + )[0] + af, socktype, proto, _canonname, sa = info + with socket.socket(af, socktype, proto) as s: + s.bind(sa) + for ip in ( + addr.address, + addr.netmask, + addr.broadcast, + addr.ptp, + ): + if ip is not None: + # TODO: skip AF_INET6 for now because I get: + # AddressValueError: Only hex digits permitted in + # u'c6f3%lxcbr0' in u'fe80::c8e0:fff:fe54:c6f3%lxcbr0' + if addr.family != socket.AF_INET6: + check_net_address(ip, addr.family) + # broadcast and ptp addresses are mutually exclusive + if addr.broadcast: + assert addr.ptp is None + elif addr.ptp: + assert addr.broadcast is None + + # check broadcast address + if ( + addr.broadcast + and addr.netmask + and addr.family in {socket.AF_INET, socket.AF_INET6} + ): + assert addr.broadcast == broadcast_addr(addr) + + if BSD or MACOS or SUNOS: + if hasattr(socket, "AF_LINK"): + assert psutil.AF_LINK == socket.AF_LINK + elif LINUX: + assert psutil.AF_LINK == socket.AF_PACKET + elif WINDOWS: + assert psutil.AF_LINK == -1 + + def test_net_if_addrs_mac_null_bytes(self): + # Simulate that the underlying C function returns an incomplete + # MAC address. psutil is supposed to fill it with null bytes. + # https://github.com/giampaolo/psutil/issues/786 + if POSIX: + ret = [('em1', psutil.AF_LINK, '06:3d:29', None, None, None)] + else: + ret = [('em1', -1, '06-3d-29', None, None, None)] + with mock.patch( + 'psutil._psplatform.net_if_addrs', return_value=ret + ) as m: + addr = psutil.net_if_addrs()['em1'][0] + assert m.called + if POSIX: + assert addr.address == '06:3d:29:00:00:00' + else: + assert addr.address == '06-3d-29-00-00-00' + + def test_net_if_stats(self): + nics = psutil.net_if_stats() + assert nics, nics + all_duplexes = ( + psutil.NIC_DUPLEX_FULL, + psutil.NIC_DUPLEX_HALF, + psutil.NIC_DUPLEX_UNKNOWN, + ) + for name, stats in nics.items(): + assert isinstance(name, str) + isup, duplex, speed, mtu, flags = stats + assert isinstance(isup, bool) + assert duplex in all_duplexes + assert duplex in all_duplexes + assert speed >= 0 + assert mtu >= 0 + assert isinstance(flags, str) + + @pytest.mark.skipif( + not (LINUX or BSD or MACOS), reason="LINUX or BSD or MACOS specific" + ) + def test_net_if_stats_enodev(self): + # See: https://github.com/giampaolo/psutil/issues/1279 + with mock.patch( + 'psutil._psutil_posix.net_if_mtu', + side_effect=OSError(errno.ENODEV, ""), + ) as m: + ret = psutil.net_if_stats() + assert ret == {} + assert m.called + + +class TestSensorsAPIs(PsutilTestCase): + @pytest.mark.skipif(not HAS_SENSORS_TEMPERATURES, reason="not supported") + def test_sensors_temperatures(self): + temps = psutil.sensors_temperatures() + for name, entries in temps.items(): + assert isinstance(name, str) + for entry in entries: + assert isinstance(entry.label, str) + if entry.current is not None: + assert entry.current >= 0 + if entry.high is not None: + assert entry.high >= 0 + if entry.critical is not None: + assert entry.critical >= 0 + + @pytest.mark.skipif(not HAS_SENSORS_TEMPERATURES, reason="not supported") + def test_sensors_temperatures_fahreneit(self): + d = {'coretemp': [('label', 50.0, 60.0, 70.0)]} + with mock.patch( + "psutil._psplatform.sensors_temperatures", return_value=d + ) as m: + temps = psutil.sensors_temperatures(fahrenheit=True)['coretemp'][0] + assert m.called + assert temps.current == 122.0 + assert temps.high == 140.0 + assert temps.critical == 158.0 + + @pytest.mark.skipif(not HAS_SENSORS_BATTERY, reason="not supported") + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_sensors_battery(self): + ret = psutil.sensors_battery() + assert ret.percent >= 0 + assert ret.percent <= 100 + if ret.secsleft not in { + psutil.POWER_TIME_UNKNOWN, + psutil.POWER_TIME_UNLIMITED, + }: + assert ret.secsleft >= 0 + elif ret.secsleft == psutil.POWER_TIME_UNLIMITED: + assert ret.power_plugged + assert isinstance(ret.power_plugged, bool) + + @pytest.mark.skipif(not HAS_SENSORS_FANS, reason="not supported") + def test_sensors_fans(self): + fans = psutil.sensors_fans() + for name, entries in fans.items(): + assert isinstance(name, str) + for entry in entries: + assert isinstance(entry.label, str) + assert isinstance(entry.current, int) + assert entry.current >= 0 diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_testutils.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_testutils.py new file mode 100644 index 0000000..6db66e5 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_testutils.py @@ -0,0 +1,577 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Tests for testing utils (psutil.tests namespace).""" + +import collections +import errno +import os +import socket +import stat +import subprocess +import textwrap +import unittest +import warnings +from unittest import mock + +import psutil +import psutil.tests +from psutil import FREEBSD +from psutil import NETBSD +from psutil import POSIX +from psutil._common import open_binary +from psutil._common import open_text +from psutil._common import supports_ipv6 +from psutil.tests import CI_TESTING +from psutil.tests import COVERAGE +from psutil.tests import HAS_NET_CONNECTIONS_UNIX +from psutil.tests import HERE +from psutil.tests import PYTHON_EXE +from psutil.tests import PYTHON_EXE_ENV +from psutil.tests import PsutilTestCase +from psutil.tests import TestMemoryLeak +from psutil.tests import bind_socket +from psutil.tests import bind_unix_socket +from psutil.tests import call_until +from psutil.tests import chdir +from psutil.tests import create_sockets +from psutil.tests import fake_pytest +from psutil.tests import filter_proc_net_connections +from psutil.tests import get_free_port +from psutil.tests import is_namedtuple +from psutil.tests import process_namespace +from psutil.tests import pytest +from psutil.tests import reap_children +from psutil.tests import retry +from psutil.tests import retry_on_failure +from psutil.tests import safe_mkdir +from psutil.tests import safe_rmpath +from psutil.tests import system_namespace +from psutil.tests import tcp_socketpair +from psutil.tests import terminate +from psutil.tests import unix_socketpair +from psutil.tests import wait_for_file +from psutil.tests import wait_for_pid + + +# =================================================================== +# --- Unit tests for test utilities. +# =================================================================== + + +class TestRetryDecorator(PsutilTestCase): + @mock.patch('time.sleep') + def test_retry_success(self, sleep): + # Fail 3 times out of 5; make sure the decorated fun returns. + + @retry(retries=5, interval=1, logfun=None) + def foo(): + while queue: + queue.pop() + 1 / 0 # noqa: B018 + return 1 + + queue = list(range(3)) + assert foo() == 1 + assert sleep.call_count == 3 + + @mock.patch('time.sleep') + def test_retry_failure(self, sleep): + # Fail 6 times out of 5; th function is supposed to raise exc. + @retry(retries=5, interval=1, logfun=None) + def foo(): + while queue: + queue.pop() + 1 / 0 # noqa: B018 + return 1 + + queue = list(range(6)) + with pytest.raises(ZeroDivisionError): + foo() + assert sleep.call_count == 5 + + @mock.patch('time.sleep') + def test_exception_arg(self, sleep): + @retry(exception=ValueError, interval=1) + def foo(): + raise TypeError + + with pytest.raises(TypeError): + foo() + assert sleep.call_count == 0 + + @mock.patch('time.sleep') + def test_no_interval_arg(self, sleep): + # if interval is not specified sleep is not supposed to be called + + @retry(retries=5, interval=None, logfun=None) + def foo(): + 1 / 0 # noqa: B018 + + with pytest.raises(ZeroDivisionError): + foo() + assert sleep.call_count == 0 + + @mock.patch('time.sleep') + def test_retries_arg(self, sleep): + @retry(retries=5, interval=1, logfun=None) + def foo(): + 1 / 0 # noqa: B018 + + with pytest.raises(ZeroDivisionError): + foo() + assert sleep.call_count == 5 + + @mock.patch('time.sleep') + def test_retries_and_timeout_args(self, sleep): + with pytest.raises(ValueError): + retry(retries=5, timeout=1) + + +class TestSyncTestUtils(PsutilTestCase): + def test_wait_for_pid(self): + wait_for_pid(os.getpid()) + nopid = max(psutil.pids()) + 99999 + with mock.patch('psutil.tests.retry.__iter__', return_value=iter([0])): + with pytest.raises(psutil.NoSuchProcess): + wait_for_pid(nopid) + + def test_wait_for_file(self): + testfn = self.get_testfn() + with open(testfn, 'w') as f: + f.write('foo') + wait_for_file(testfn) + assert not os.path.exists(testfn) + + def test_wait_for_file_empty(self): + testfn = self.get_testfn() + with open(testfn, 'w'): + pass + wait_for_file(testfn, empty=True) + assert not os.path.exists(testfn) + + def test_wait_for_file_no_file(self): + testfn = self.get_testfn() + with mock.patch('psutil.tests.retry.__iter__', return_value=iter([0])): + with pytest.raises(OSError): + wait_for_file(testfn) + + def test_wait_for_file_no_delete(self): + testfn = self.get_testfn() + with open(testfn, 'w') as f: + f.write('foo') + wait_for_file(testfn, delete=False) + assert os.path.exists(testfn) + + def test_call_until(self): + call_until(lambda: 1) + # TODO: test for timeout + + +class TestFSTestUtils(PsutilTestCase): + def test_open_text(self): + with open_text(__file__) as f: + assert f.mode == 'r' + + def test_open_binary(self): + with open_binary(__file__) as f: + assert f.mode == 'rb' + + def test_safe_mkdir(self): + testfn = self.get_testfn() + safe_mkdir(testfn) + assert os.path.isdir(testfn) + safe_mkdir(testfn) + assert os.path.isdir(testfn) + + def test_safe_rmpath(self): + # test file is removed + testfn = self.get_testfn() + open(testfn, 'w').close() + safe_rmpath(testfn) + assert not os.path.exists(testfn) + # test no exception if path does not exist + safe_rmpath(testfn) + # test dir is removed + os.mkdir(testfn) + safe_rmpath(testfn) + assert not os.path.exists(testfn) + # test other exceptions are raised + with mock.patch( + 'psutil.tests.os.stat', side_effect=OSError(errno.EINVAL, "") + ) as m: + with pytest.raises(OSError): + safe_rmpath(testfn) + assert m.called + + def test_chdir(self): + testfn = self.get_testfn() + base = os.getcwd() + os.mkdir(testfn) + with chdir(testfn): + assert os.getcwd() == os.path.join(base, testfn) + assert os.getcwd() == base + + +class TestProcessUtils(PsutilTestCase): + def test_reap_children(self): + subp = self.spawn_testproc() + p = psutil.Process(subp.pid) + assert p.is_running() + reap_children() + assert not p.is_running() + assert not psutil.tests._pids_started + assert not psutil.tests._subprocesses_started + + def test_spawn_children_pair(self): + child, grandchild = self.spawn_children_pair() + assert child.pid != grandchild.pid + assert child.is_running() + assert grandchild.is_running() + children = psutil.Process().children() + assert children == [child] + children = psutil.Process().children(recursive=True) + assert len(children) == 2 + assert child in children + assert grandchild in children + assert child.ppid() == os.getpid() + assert grandchild.ppid() == child.pid + + terminate(child) + assert not child.is_running() + assert grandchild.is_running() + + terminate(grandchild) + assert not grandchild.is_running() + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_spawn_zombie(self): + _parent, zombie = self.spawn_zombie() + assert zombie.status() == psutil.STATUS_ZOMBIE + + def test_terminate(self): + # by subprocess.Popen + p = self.spawn_testproc() + terminate(p) + self.assertPidGone(p.pid) + terminate(p) + # by psutil.Process + p = psutil.Process(self.spawn_testproc().pid) + terminate(p) + self.assertPidGone(p.pid) + terminate(p) + # by psutil.Popen + cmd = [ + PYTHON_EXE, + "-c", + "import time; [time.sleep(0.1) for x in range(100)];", + ] + p = psutil.Popen( + cmd, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + env=PYTHON_EXE_ENV, + ) + terminate(p) + self.assertPidGone(p.pid) + terminate(p) + # by PID + pid = self.spawn_testproc().pid + terminate(pid) + self.assertPidGone(p.pid) + terminate(pid) + # zombie + if POSIX: + parent, zombie = self.spawn_zombie() + terminate(parent) + terminate(zombie) + self.assertPidGone(parent.pid) + self.assertPidGone(zombie.pid) + + +class TestNetUtils(PsutilTestCase): + def bind_socket(self): + port = get_free_port() + with bind_socket(addr=('', port)) as s: + assert s.getsockname()[1] == port + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_bind_unix_socket(self): + name = self.get_testfn() + with bind_unix_socket(name) as sock: + assert sock.family == socket.AF_UNIX + assert sock.type == socket.SOCK_STREAM + assert sock.getsockname() == name + assert os.path.exists(name) + assert stat.S_ISSOCK(os.stat(name).st_mode) + # UDP + name = self.get_testfn() + with bind_unix_socket(name, type=socket.SOCK_DGRAM) as sock: + assert sock.type == socket.SOCK_DGRAM + + def test_tcp_socketpair(self): + addr = ("127.0.0.1", get_free_port()) + server, client = tcp_socketpair(socket.AF_INET, addr=addr) + with server, client: + # Ensure they are connected and the positions are correct. + assert server.getsockname() == addr + assert client.getpeername() == addr + assert client.getsockname() != addr + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + @pytest.mark.skipif( + NETBSD or FREEBSD, reason="/var/run/log UNIX socket opened by default" + ) + def test_unix_socketpair(self): + p = psutil.Process() + num_fds = p.num_fds() + assert not filter_proc_net_connections(p.net_connections(kind='unix')) + name = self.get_testfn() + server, client = unix_socketpair(name) + try: + assert os.path.exists(name) + assert stat.S_ISSOCK(os.stat(name).st_mode) + assert p.num_fds() - num_fds == 2 + assert ( + len( + filter_proc_net_connections(p.net_connections(kind='unix')) + ) + == 2 + ) + assert server.getsockname() == name + assert client.getpeername() == name + finally: + client.close() + server.close() + + def test_create_sockets(self): + with create_sockets() as socks: + fams = collections.defaultdict(int) + types = collections.defaultdict(int) + for s in socks: + fams[s.family] += 1 + # work around http://bugs.python.org/issue30204 + types[s.getsockopt(socket.SOL_SOCKET, socket.SO_TYPE)] += 1 + assert fams[socket.AF_INET] >= 2 + if supports_ipv6(): + assert fams[socket.AF_INET6] >= 2 + if POSIX and HAS_NET_CONNECTIONS_UNIX: + assert fams[socket.AF_UNIX] >= 2 + assert types[socket.SOCK_STREAM] >= 2 + assert types[socket.SOCK_DGRAM] >= 2 + + +@pytest.mark.xdist_group(name="serial") +class TestMemLeakClass(TestMemoryLeak): + @retry_on_failure() + def test_times(self): + def fun(): + cnt['cnt'] += 1 + + cnt = {'cnt': 0} + self.execute(fun, times=10, warmup_times=15) + assert cnt['cnt'] == 26 + + def test_param_err(self): + with pytest.raises(ValueError): + self.execute(lambda: 0, times=0) + with pytest.raises(ValueError): + self.execute(lambda: 0, times=-1) + with pytest.raises(ValueError): + self.execute(lambda: 0, warmup_times=-1) + with pytest.raises(ValueError): + self.execute(lambda: 0, tolerance=-1) + with pytest.raises(ValueError): + self.execute(lambda: 0, retries=-1) + + @retry_on_failure() + @pytest.mark.skipif(CI_TESTING, reason="skipped on CI") + @pytest.mark.skipif(COVERAGE, reason="skipped during test coverage") + def test_leak_mem(self): + ls = [] + + def fun(ls=ls): + ls.append("x" * 248 * 1024) + + try: + # will consume around 60M in total + with pytest.raises(AssertionError, match="extra-mem"): + self.execute(fun, times=100) + finally: + del ls + + def test_unclosed_files(self): + def fun(): + f = open(__file__) # noqa: SIM115 + self.addCleanup(f.close) + box.append(f) + + box = [] + kind = "fd" if POSIX else "handle" + with pytest.raises(AssertionError, match="unclosed " + kind): + self.execute(fun) + + def test_tolerance(self): + def fun(): + ls.append("x" * 24 * 1024) + + ls = [] + times = 100 + self.execute( + fun, times=times, warmup_times=0, tolerance=200 * 1024 * 1024 + ) + assert len(ls) == times + 1 + + def test_execute_w_exc(self): + def fun_1(): + 1 / 0 # noqa: B018 + + self.execute_w_exc(ZeroDivisionError, fun_1) + with pytest.raises(ZeroDivisionError): + self.execute_w_exc(OSError, fun_1) + + def fun_2(): + pass + + with pytest.raises(AssertionError): + self.execute_w_exc(ZeroDivisionError, fun_2) + + +class TestFakePytest(PsutilTestCase): + def run_test_class(self, klass): + suite = unittest.TestSuite() + suite.addTest(klass) + runner = unittest.TextTestRunner() + result = runner.run(suite) + return result + + def test_raises(self): + with fake_pytest.raises(ZeroDivisionError) as cm: + 1 / 0 # noqa: B018 + assert isinstance(cm.value, ZeroDivisionError) + + with fake_pytest.raises(ValueError, match="foo") as cm: + raise ValueError("foo") + + try: + with fake_pytest.raises(ValueError, match="foo") as cm: + raise ValueError("bar") + except AssertionError as err: + assert str(err) == '"foo" does not match "bar"' + else: + raise self.fail("exception not raised") + + def test_mark(self): + @fake_pytest.mark.xdist_group(name="serial") + def foo(): + return 1 + + assert foo() == 1 + + @fake_pytest.mark.xdist_group(name="serial") + class Foo: + def bar(self): + return 1 + + assert Foo().bar() == 1 + + def test_skipif(self): + class TestCase(unittest.TestCase): + @fake_pytest.mark.skipif(True, reason="reason") + def foo(self): + assert 1 == 1 # noqa: PLR0133 + + result = self.run_test_class(TestCase("foo")) + assert result.wasSuccessful() + assert len(result.skipped) == 1 + assert result.skipped[0][1] == "reason" + + class TestCase(unittest.TestCase): + @fake_pytest.mark.skipif(False, reason="reason") + def foo(self): + assert 1 == 1 # noqa: PLR0133 + + result = self.run_test_class(TestCase("foo")) + assert result.wasSuccessful() + assert len(result.skipped) == 0 + + def test_skip(self): + class TestCase(unittest.TestCase): + def foo(self): + fake_pytest.skip("reason") + assert 1 == 0 # noqa: PLR0133 + + result = self.run_test_class(TestCase("foo")) + assert result.wasSuccessful() + assert len(result.skipped) == 1 + assert result.skipped[0][1] == "reason" + + def test_main(self): + tmpdir = self.get_testfn(dir=HERE) + os.mkdir(tmpdir) + with open(os.path.join(tmpdir, "__init__.py"), "w"): + pass + with open(os.path.join(tmpdir, "test_file.py"), "w") as f: + f.write(textwrap.dedent("""\ + import unittest + + class TestCase(unittest.TestCase): + def test_passed(self): + pass + """).lstrip()) + with mock.patch.object(psutil.tests, "HERE", tmpdir): + with self.assertWarnsRegex( + UserWarning, "Fake pytest module was used" + ): + suite = fake_pytest.main() + assert suite.countTestCases() == 1 + + def test_warns(self): + # success + with fake_pytest.warns(UserWarning): + warnings.warn("foo", UserWarning, stacklevel=1) + + # failure + try: + with fake_pytest.warns(UserWarning): + warnings.warn("foo", DeprecationWarning, stacklevel=1) + except AssertionError: + pass + else: + raise self.fail("exception not raised") + + # match success + with fake_pytest.warns(UserWarning, match="foo"): + warnings.warn("foo", UserWarning, stacklevel=1) + + # match failure + try: + with fake_pytest.warns(UserWarning, match="foo"): + warnings.warn("bar", UserWarning, stacklevel=1) + except AssertionError: + pass + else: + raise self.fail("exception not raised") + + +class TestTestingUtils(PsutilTestCase): + def test_process_namespace(self): + p = psutil.Process() + ns = process_namespace(p) + ns.test() + fun = next(x for x in ns.iter(ns.getters) if x[1] == 'ppid')[0] + assert fun() == p.ppid() + + def test_system_namespace(self): + ns = system_namespace() + fun = next(x for x in ns.iter(ns.getters) if x[1] == 'net_if_addrs')[0] + assert fun() == psutil.net_if_addrs() + + +class TestOtherUtils(PsutilTestCase): + def test_is_namedtuple(self): + assert is_namedtuple(collections.namedtuple('foo', 'a b c')(1, 2, 3)) + assert not is_namedtuple(tuple()) diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_unicode.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_unicode.py new file mode 100644 index 0000000..d8a8c4b --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_unicode.py @@ -0,0 +1,313 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Notes about unicode handling in psutil +======================================. + +Starting from version 5.3.0 psutil adds unicode support, see: +https://github.com/giampaolo/psutil/issues/1040 +The notes below apply to *any* API returning a string such as +process exe(), cwd() or username(): + +* all strings are encoded by using the OS filesystem encoding + (sys.getfilesystemencoding()) which varies depending on the platform + (e.g. "UTF-8" on macOS, "mbcs" on Win) +* no API call is supposed to crash with UnicodeDecodeError +* instead, in case of badly encoded data returned by the OS, the + following error handlers are used to replace the corrupted characters in + the string: + * sys.getfilesystemencodeerrors() or "surrogatescape" on POSIX and + "replace" on Windows. + +For a detailed explanation of how psutil handles unicode see #1040. + +Tests +===== + +List of APIs returning or dealing with a string: +('not tested' means they are not tested to deal with non-ASCII strings): + +* Process.cmdline() +* Process.cwd() +* Process.environ() +* Process.exe() +* Process.memory_maps() +* Process.name() +* Process.net_connections('unix') +* Process.open_files() +* Process.username() (not tested) + +* disk_io_counters() (not tested) +* disk_partitions() (not tested) +* disk_usage(str) +* net_connections('unix') +* net_if_addrs() (not tested) +* net_if_stats() (not tested) +* net_io_counters() (not tested) +* sensors_fans() (not tested) +* sensors_temperatures() (not tested) +* users() (not tested) + +* WindowsService.binpath() (not tested) +* WindowsService.description() (not tested) +* WindowsService.display_name() (not tested) +* WindowsService.name() (not tested) +* WindowsService.status() (not tested) +* WindowsService.username() (not tested) + +In here we create a unicode path with a funky non-ASCII name and (where +possible) make psutil return it back (e.g. on name(), exe(), open_files(), +etc.) and make sure that: + +* psutil never crashes with UnicodeDecodeError +* the returned path matches +""" + +import os +import shutil +import warnings +from contextlib import closing + +import psutil +from psutil import BSD +from psutil import POSIX +from psutil import WINDOWS +from psutil.tests import ASCII_FS +from psutil.tests import CI_TESTING +from psutil.tests import HAS_ENVIRON +from psutil.tests import HAS_MEMORY_MAPS +from psutil.tests import HAS_NET_CONNECTIONS_UNIX +from psutil.tests import INVALID_UNICODE_SUFFIX +from psutil.tests import PYPY +from psutil.tests import TESTFN_PREFIX +from psutil.tests import UNICODE_SUFFIX +from psutil.tests import PsutilTestCase +from psutil.tests import bind_unix_socket +from psutil.tests import chdir +from psutil.tests import copyload_shared_lib +from psutil.tests import create_py_exe +from psutil.tests import get_testfn +from psutil.tests import pytest +from psutil.tests import safe_mkdir +from psutil.tests import safe_rmpath +from psutil.tests import skip_on_access_denied +from psutil.tests import spawn_testproc +from psutil.tests import terminate + + +def try_unicode(suffix): + """Return True if both the fs and the subprocess module can + deal with a unicode file name. + """ + sproc = None + testfn = get_testfn(suffix=suffix) + try: + safe_rmpath(testfn) + create_py_exe(testfn) + sproc = spawn_testproc(cmd=[testfn]) + shutil.copyfile(testfn, testfn + '-2') + safe_rmpath(testfn + '-2') + except (UnicodeEncodeError, OSError): + return False + else: + return True + finally: + if sproc is not None: + terminate(sproc) + safe_rmpath(testfn) + + +# =================================================================== +# FS APIs +# =================================================================== + + +class BaseUnicodeTest(PsutilTestCase): + funky_suffix = None + + @classmethod + def setUpClass(cls): + super().setUpClass() + cls.skip_tests = False + cls.funky_name = None + if cls.funky_suffix is not None: + if not try_unicode(cls.funky_suffix): + cls.skip_tests = True + else: + cls.funky_name = get_testfn(suffix=cls.funky_suffix) + create_py_exe(cls.funky_name) + + def setUp(self): + super().setUp() + if self.skip_tests: + raise pytest.skip("can't handle unicode str") + + +@pytest.mark.xdist_group(name="serial") +@pytest.mark.skipif(ASCII_FS, reason="ASCII fs") +class TestFSAPIs(BaseUnicodeTest): + """Test FS APIs with a funky, valid, UTF8 path name.""" + + funky_suffix = UNICODE_SUFFIX + + def expect_exact_path_match(self): + with warnings.catch_warnings(): + warnings.simplefilter("ignore") + return self.funky_name in os.listdir(".") + + # --- + + def test_proc_exe(self): + cmd = [ + self.funky_name, + "-c", + "import time; [time.sleep(0.1) for x in range(100)]", + ] + subp = self.spawn_testproc(cmd) + p = psutil.Process(subp.pid) + exe = p.exe() + assert isinstance(exe, str) + if self.expect_exact_path_match(): + assert os.path.normcase(exe) == os.path.normcase(self.funky_name) + + def test_proc_name(self): + cmd = [ + self.funky_name, + "-c", + "import time; [time.sleep(0.1) for x in range(100)]", + ] + subp = self.spawn_testproc(cmd) + name = psutil.Process(subp.pid).name() + assert isinstance(name, str) + if self.expect_exact_path_match(): + assert name == os.path.basename(self.funky_name) + + def test_proc_cmdline(self): + cmd = [ + self.funky_name, + "-c", + "import time; [time.sleep(0.1) for x in range(100)]", + ] + subp = self.spawn_testproc(cmd) + p = psutil.Process(subp.pid) + cmdline = p.cmdline() + for part in cmdline: + assert isinstance(part, str) + if self.expect_exact_path_match(): + assert cmdline == cmd + + def test_proc_cwd(self): + dname = self.funky_name + "2" + self.addCleanup(safe_rmpath, dname) + safe_mkdir(dname) + with chdir(dname): + p = psutil.Process() + cwd = p.cwd() + assert isinstance(p.cwd(), str) + if self.expect_exact_path_match(): + assert cwd == dname + + @pytest.mark.skipif(PYPY and WINDOWS, reason="fails on PYPY + WINDOWS") + def test_proc_open_files(self): + p = psutil.Process() + start = set(p.open_files()) + with open(self.funky_name, 'rb'): + new = set(p.open_files()) + path = (new - start).pop().path + assert isinstance(path, str) + if BSD and not path: + # XXX - see https://github.com/giampaolo/psutil/issues/595 + raise pytest.skip("open_files on BSD is broken") + if self.expect_exact_path_match(): + assert os.path.normcase(path) == os.path.normcase(self.funky_name) + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + def test_proc_net_connections(self): + name = self.get_testfn(suffix=self.funky_suffix) + sock = bind_unix_socket(name) + with closing(sock): + conn = psutil.Process().net_connections('unix')[0] + assert isinstance(conn.laddr, str) + assert conn.laddr == name + + @pytest.mark.skipif(not POSIX, reason="POSIX only") + @pytest.mark.skipif( + not HAS_NET_CONNECTIONS_UNIX, reason="can't list UNIX sockets" + ) + @skip_on_access_denied() + def test_net_connections(self): + def find_sock(cons): + for conn in cons: + if os.path.basename(conn.laddr).startswith(TESTFN_PREFIX): + return conn + raise ValueError("connection not found") + + name = self.get_testfn(suffix=self.funky_suffix) + sock = bind_unix_socket(name) + with closing(sock): + cons = psutil.net_connections(kind='unix') + conn = find_sock(cons) + assert isinstance(conn.laddr, str) + assert conn.laddr == name + + def test_disk_usage(self): + dname = self.funky_name + "2" + self.addCleanup(safe_rmpath, dname) + safe_mkdir(dname) + psutil.disk_usage(dname) + + @pytest.mark.skipif(not HAS_MEMORY_MAPS, reason="not supported") + @pytest.mark.skipif(PYPY, reason="unstable on PYPY") + def test_memory_maps(self): + with copyload_shared_lib(suffix=self.funky_suffix) as funky_path: + + def normpath(p): + return os.path.realpath(os.path.normcase(p)) + + libpaths = [ + normpath(x.path) for x in psutil.Process().memory_maps() + ] + # ...just to have a clearer msg in case of failure + libpaths = [x for x in libpaths if TESTFN_PREFIX in x] + assert normpath(funky_path) in libpaths + for path in libpaths: + assert isinstance(path, str) + + +@pytest.mark.skipif(CI_TESTING, reason="unreliable on CI") +class TestFSAPIsWithInvalidPath(TestFSAPIs): + """Test FS APIs with a funky, invalid path name.""" + + funky_suffix = INVALID_UNICODE_SUFFIX + + def expect_exact_path_match(self): + return True + + +# =================================================================== +# Non fs APIs +# =================================================================== + + +class TestNonFSAPIS(BaseUnicodeTest): + """Unicode tests for non fs-related APIs.""" + + funky_suffix = UNICODE_SUFFIX + + @pytest.mark.skipif(not HAS_ENVIRON, reason="not supported") + @pytest.mark.skipif(PYPY and WINDOWS, reason="segfaults on PYPY + WINDOWS") + def test_proc_environ(self): + # Note: differently from others, this test does not deal + # with fs paths. + env = os.environ.copy() + env['FUNNY_ARG'] = self.funky_suffix + sproc = self.spawn_testproc(env=env) + p = psutil.Process(sproc.pid) + env = p.environ() + for k, v in env.items(): + assert isinstance(k, str) + assert isinstance(v, str) + assert env['FUNNY_ARG'] == self.funky_suffix diff --git a/llmlab/lib/python3.12/site-packages/psutil/tests/test_windows.py b/llmlab/lib/python3.12/site-packages/psutil/tests/test_windows.py new file mode 100644 index 0000000..c5c536b --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/psutil/tests/test_windows.py @@ -0,0 +1,914 @@ +#!/usr/bin/env python3 + +# Copyright (c) 2009, Giampaolo Rodola'. All rights reserved. +# Use of this source code is governed by a BSD-style license that can be +# found in the LICENSE file. + +"""Windows specific tests.""" + +import datetime +import glob +import os +import platform +import re +import shutil +import signal +import subprocess +import sys +import time +import warnings +from unittest import mock + +import psutil +from psutil import WINDOWS +from psutil.tests import GITHUB_ACTIONS +from psutil.tests import HAS_BATTERY +from psutil.tests import IS_64BIT +from psutil.tests import PYPY +from psutil.tests import TOLERANCE_DISK_USAGE +from psutil.tests import TOLERANCE_SYS_MEM +from psutil.tests import PsutilTestCase +from psutil.tests import pytest +from psutil.tests import retry_on_failure +from psutil.tests import sh +from psutil.tests import spawn_testproc +from psutil.tests import terminate + + +if WINDOWS and not PYPY: + with warnings.catch_warnings(): + warnings.simplefilter("ignore") + import win32api # requires "pip install pywin32" + import win32con + import win32process + import wmi # requires "pip install wmi" / "make install-pydeps-test" + +if WINDOWS: + from psutil._pswindows import convert_oserror + + +cext = psutil._psplatform.cext + + +@pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") +@pytest.mark.skipif(PYPY, reason="pywin32 not available on PYPY") +class WindowsTestCase(PsutilTestCase): + pass + + +def powershell(cmd): + """Currently not used, but available just in case. Usage: + + >>> powershell( + "Get-CIMInstance Win32_PageFileUsage | Select AllocatedBaseSize") + """ + if not shutil.which("powershell.exe"): + raise pytest.skip("powershell.exe not available") + cmdline = ( + "powershell.exe -ExecutionPolicy Bypass -NoLogo -NonInteractive " + f"-NoProfile -WindowStyle Hidden -Command \"{cmd}\"" # noqa: Q003 + ) + return sh(cmdline) + + +def wmic(path, what, converter=int): + """Currently not used, but available just in case. Usage: + + >>> wmic("Win32_OperatingSystem", "FreePhysicalMemory") + 2134124534 + """ + out = sh(f"wmic path {path} get {what}").strip() + data = "".join(out.splitlines()[1:]).strip() # get rid of the header + if converter is not None: + if "," in what: + return tuple(converter(x) for x in data.split()) + else: + return converter(data) + else: + return data + + +# =================================================================== +# System APIs +# =================================================================== + + +class TestCpuAPIs(WindowsTestCase): + @pytest.mark.skipif( + 'NUMBER_OF_PROCESSORS' not in os.environ, + reason="NUMBER_OF_PROCESSORS env var is not available", + ) + def test_cpu_count_vs_NUMBER_OF_PROCESSORS(self): + # Will likely fail on many-cores systems: + # https://stackoverflow.com/questions/31209256 + num_cpus = int(os.environ['NUMBER_OF_PROCESSORS']) + assert num_cpus == psutil.cpu_count() + + def test_cpu_count_vs_GetSystemInfo(self): + # Will likely fail on many-cores systems: + # https://stackoverflow.com/questions/31209256 + sys_value = win32api.GetSystemInfo()[5] + psutil_value = psutil.cpu_count() + assert sys_value == psutil_value + + def test_cpu_count_logical_vs_wmi(self): + w = wmi.WMI() + procs = sum( + proc.NumberOfLogicalProcessors for proc in w.Win32_Processor() + ) + assert psutil.cpu_count() == procs + + def test_cpu_count_cores_vs_wmi(self): + w = wmi.WMI() + cores = sum(proc.NumberOfCores for proc in w.Win32_Processor()) + assert psutil.cpu_count(logical=False) == cores + + def test_cpu_count_vs_cpu_times(self): + assert psutil.cpu_count() == len(psutil.cpu_times(percpu=True)) + + def test_cpu_freq(self): + w = wmi.WMI() + proc = w.Win32_Processor()[0] + assert proc.CurrentClockSpeed == psutil.cpu_freq().current + assert proc.MaxClockSpeed == psutil.cpu_freq().max + + +class TestSystemAPIs(WindowsTestCase): + def test_nic_names(self): + out = sh('ipconfig /all') + nics = psutil.net_io_counters(pernic=True).keys() + for nic in nics: + if "pseudo-interface" in nic.replace(' ', '-').lower(): + continue + if nic not in out: + raise self.fail( + f"{nic!r} nic wasn't found in 'ipconfig /all' output" + ) + + def test_total_phymem(self): + w = wmi.WMI().Win32_ComputerSystem()[0] + assert int(w.TotalPhysicalMemory) == psutil.virtual_memory().total + + def test_free_phymem(self): + w = wmi.WMI().Win32_PerfRawData_PerfOS_Memory()[0] + assert ( + abs(int(w.AvailableBytes) - psutil.virtual_memory().free) + < TOLERANCE_SYS_MEM + ) + + def test_total_swapmem(self): + w = wmi.WMI().Win32_PerfRawData_PerfOS_Memory()[0] + assert ( + int(w.CommitLimit) - psutil.virtual_memory().total + == psutil.swap_memory().total + ) + if psutil.swap_memory().total == 0: + assert psutil.swap_memory().free == 0 + assert psutil.swap_memory().used == 0 + + def test_percent_swapmem(self): + if psutil.swap_memory().total > 0: + w = wmi.WMI().Win32_PerfRawData_PerfOS_PagingFile(Name="_Total")[0] + # calculate swap usage to percent + percentSwap = int(w.PercentUsage) * 100 / int(w.PercentUsage_Base) + # exact percent may change but should be reasonable + # assert within +/- 5% and between 0 and 100% + assert psutil.swap_memory().percent >= 0 + assert abs(psutil.swap_memory().percent - percentSwap) < 5 + assert psutil.swap_memory().percent <= 100 + + # @pytest.mark.skipif(wmi is None, reason="wmi module is not installed") + # def test__UPTIME(self): + # # _UPTIME constant is not public but it is used internally + # # as value to return for pid 0 creation time. + # # WMI behaves the same. + # w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + # p = psutil.Process(0) + # wmic_create = str(w.CreationDate.split('.')[0]) + # psutil_create = time.strftime("%Y%m%d%H%M%S", + # time.localtime(p.create_time())) + + # Note: this test is not very reliable + @retry_on_failure() + def test_pids(self): + # Note: this test might fail if the OS is starting/killing + # other processes in the meantime + w = wmi.WMI().Win32_Process() + wmi_pids = {x.ProcessId for x in w} + psutil_pids = set(psutil.pids()) + assert wmi_pids == psutil_pids + + @retry_on_failure() + def test_disks(self): + ps_parts = psutil.disk_partitions(all=True) + wmi_parts = wmi.WMI().Win32_LogicalDisk() + for ps_part in ps_parts: + for wmi_part in wmi_parts: + if ps_part.device.replace('\\', '') == wmi_part.DeviceID: + if not ps_part.mountpoint: + # this is usually a CD-ROM with no disk inserted + break + if 'cdrom' in ps_part.opts: + break + if ps_part.mountpoint.startswith('A:'): + break # floppy + try: + usage = psutil.disk_usage(ps_part.mountpoint) + except FileNotFoundError: + # usually this is the floppy + break + assert usage.total == int(wmi_part.Size) + wmi_free = int(wmi_part.FreeSpace) + assert usage.free == wmi_free + # 10 MB tolerance + if abs(usage.free - wmi_free) > 10 * 1024 * 1024: + raise self.fail(f"psutil={usage.free}, wmi={wmi_free}") + break + else: + raise self.fail(f"can't find partition {ps_part!r}") + + @retry_on_failure() + def test_disk_usage(self): + for disk in psutil.disk_partitions(): + if 'cdrom' in disk.opts: + continue + sys_value = win32api.GetDiskFreeSpaceEx(disk.mountpoint) + psutil_value = psutil.disk_usage(disk.mountpoint) + assert abs(sys_value[0] - psutil_value.free) < TOLERANCE_DISK_USAGE + assert ( + abs(sys_value[1] - psutil_value.total) < TOLERANCE_DISK_USAGE + ) + assert psutil_value.used == psutil_value.total - psutil_value.free + + def test_disk_partitions(self): + sys_value = [ + x + '\\' + for x in win32api.GetLogicalDriveStrings().split("\\\x00") + if x and not x.startswith('A:') + ] + psutil_value = [ + x.mountpoint + for x in psutil.disk_partitions(all=True) + if not x.mountpoint.startswith('A:') + ] + assert sys_value == psutil_value + + def test_net_if_stats(self): + ps_names = set(cext.net_if_stats()) + wmi_adapters = wmi.WMI().Win32_NetworkAdapter() + wmi_names = set() + for wmi_adapter in wmi_adapters: + wmi_names.add(wmi_adapter.Name) + wmi_names.add(wmi_adapter.NetConnectionID) + assert ( + ps_names & wmi_names + ), f"no common entries in {ps_names}, {wmi_names}" + + def test_boot_time(self): + wmi_os = wmi.WMI().Win32_OperatingSystem() + wmi_btime_str = wmi_os[0].LastBootUpTime.split('.')[0] + wmi_btime_dt = datetime.datetime.strptime( + wmi_btime_str, "%Y%m%d%H%M%S" + ) + psutil_dt = datetime.datetime.fromtimestamp(psutil.boot_time()) + diff = abs((wmi_btime_dt - psutil_dt).total_seconds()) + assert diff <= 5 + + def test_boot_time_fluctuation(self): + # https://github.com/giampaolo/psutil/issues/1007 + with mock.patch('psutil._pswindows.cext.boot_time', return_value=5): + assert psutil.boot_time() == 5 + with mock.patch('psutil._pswindows.cext.boot_time', return_value=4): + assert psutil.boot_time() == 5 + with mock.patch('psutil._pswindows.cext.boot_time', return_value=6): + assert psutil.boot_time() == 5 + with mock.patch('psutil._pswindows.cext.boot_time', return_value=333): + assert psutil.boot_time() == 333 + + +# =================================================================== +# sensors_battery() +# =================================================================== + + +class TestSensorsBattery(WindowsTestCase): + def test_has_battery(self): + if win32api.GetPwrCapabilities()['SystemBatteriesPresent']: + assert psutil.sensors_battery() is not None + else: + assert psutil.sensors_battery() is None + + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_percent(self): + w = wmi.WMI() + battery_wmi = w.query('select * from Win32_Battery')[0] + battery_psutil = psutil.sensors_battery() + assert ( + abs(battery_psutil.percent - battery_wmi.EstimatedChargeRemaining) + < 1 + ) + + @pytest.mark.skipif(not HAS_BATTERY, reason="no battery") + def test_power_plugged(self): + w = wmi.WMI() + battery_wmi = w.query('select * from Win32_Battery')[0] + battery_psutil = psutil.sensors_battery() + # Status codes: + # https://msdn.microsoft.com/en-us/library/aa394074(v=vs.85).aspx + assert battery_psutil.power_plugged == (battery_wmi.BatteryStatus == 2) + + def test_emulate_no_battery(self): + with mock.patch( + "psutil._pswindows.cext.sensors_battery", + return_value=(0, 128, 0, 0), + ) as m: + assert psutil.sensors_battery() is None + assert m.called + + def test_emulate_power_connected(self): + with mock.patch( + "psutil._pswindows.cext.sensors_battery", return_value=(1, 0, 0, 0) + ) as m: + assert ( + psutil.sensors_battery().secsleft + == psutil.POWER_TIME_UNLIMITED + ) + assert m.called + + def test_emulate_power_charging(self): + with mock.patch( + "psutil._pswindows.cext.sensors_battery", return_value=(0, 8, 0, 0) + ) as m: + assert ( + psutil.sensors_battery().secsleft + == psutil.POWER_TIME_UNLIMITED + ) + assert m.called + + def test_emulate_secs_left_unknown(self): + with mock.patch( + "psutil._pswindows.cext.sensors_battery", + return_value=(0, 0, 0, -1), + ) as m: + assert ( + psutil.sensors_battery().secsleft == psutil.POWER_TIME_UNKNOWN + ) + assert m.called + + +# =================================================================== +# Process APIs +# =================================================================== + + +class TestProcess(WindowsTestCase): + @classmethod + def setUpClass(cls): + cls.pid = spawn_testproc().pid + + @classmethod + def tearDownClass(cls): + terminate(cls.pid) + + def test_issue_24(self): + p = psutil.Process(0) + with pytest.raises(psutil.AccessDenied): + p.kill() + + def test_special_pid(self): + p = psutil.Process(4) + assert p.name() == 'System' + # use __str__ to access all common Process properties to check + # that nothing strange happens + str(p) + p.username() + assert p.create_time() >= 0.0 + try: + rss, _vms = p.memory_info()[:2] + except psutil.AccessDenied: + # expected on Windows Vista and Windows 7 + if platform.uname()[1] not in {'vista', 'win-7', 'win7'}: + raise + else: + assert rss > 0 + + def test_send_signal(self): + p = psutil.Process(self.pid) + with pytest.raises(ValueError): + p.send_signal(signal.SIGINT) + + def test_num_handles_increment(self): + p = psutil.Process(os.getpid()) + before = p.num_handles() + handle = win32api.OpenProcess( + win32con.PROCESS_QUERY_INFORMATION, win32con.FALSE, os.getpid() + ) + after = p.num_handles() + assert after == before + 1 + win32api.CloseHandle(handle) + assert p.num_handles() == before + + def test_ctrl_signals(self): + p = psutil.Process(self.spawn_testproc().pid) + p.send_signal(signal.CTRL_C_EVENT) + p.send_signal(signal.CTRL_BREAK_EVENT) + p.kill() + p.wait() + with pytest.raises(psutil.NoSuchProcess): + p.send_signal(signal.CTRL_C_EVENT) + with pytest.raises(psutil.NoSuchProcess): + p.send_signal(signal.CTRL_BREAK_EVENT) + + def test_username(self): + name = win32api.GetUserNameEx(win32con.NameSamCompatible) + if name.endswith('$'): + # When running as a service account (most likely to be + # NetworkService), these user name calculations don't produce the + # same result, causing the test to fail. + raise pytest.skip('running as service account') + assert psutil.Process().username() == name + + def test_cmdline(self): + sys_value = re.sub(r"[ ]+", " ", win32api.GetCommandLine()).strip() + psutil_value = ' '.join(psutil.Process().cmdline()) + if sys_value[0] == '"' != psutil_value[0]: + # The PyWin32 command line may retain quotes around argv[0] if they + # were used unnecessarily, while psutil will omit them. So remove + # the first 2 quotes from sys_value if not in psutil_value. + # A path to an executable will not contain quotes, so this is safe. + sys_value = sys_value.replace('"', '', 2) + assert sys_value == psutil_value + + # XXX - occasional failures + + # def test_cpu_times(self): + # handle = win32api.OpenProcess(win32con.PROCESS_QUERY_INFORMATION, + # win32con.FALSE, os.getpid()) + # self.addCleanup(win32api.CloseHandle, handle) + # sys_value = win32process.GetProcessTimes(handle) + # psutil_value = psutil.Process().cpu_times() + # self.assertAlmostEqual( + # psutil_value.user, sys_value['UserTime'] / 10000000.0, + # delta=0.2) + # self.assertAlmostEqual( + # psutil_value.user, sys_value['KernelTime'] / 10000000.0, + # delta=0.2) + + def test_nice(self): + handle = win32api.OpenProcess( + win32con.PROCESS_QUERY_INFORMATION, win32con.FALSE, os.getpid() + ) + self.addCleanup(win32api.CloseHandle, handle) + sys_value = win32process.GetPriorityClass(handle) + psutil_value = psutil.Process().nice() + assert psutil_value == sys_value + + def test_memory_info(self): + handle = win32api.OpenProcess( + win32con.PROCESS_QUERY_INFORMATION, win32con.FALSE, self.pid + ) + self.addCleanup(win32api.CloseHandle, handle) + sys_value = win32process.GetProcessMemoryInfo(handle) + psutil_value = psutil.Process(self.pid).memory_info() + assert sys_value['PeakWorkingSetSize'] == psutil_value.peak_wset + assert sys_value['WorkingSetSize'] == psutil_value.wset + assert ( + sys_value['QuotaPeakPagedPoolUsage'] + == psutil_value.peak_paged_pool + ) + assert sys_value['QuotaPagedPoolUsage'] == psutil_value.paged_pool + assert ( + sys_value['QuotaPeakNonPagedPoolUsage'] + == psutil_value.peak_nonpaged_pool + ) + assert ( + sys_value['QuotaNonPagedPoolUsage'] == psutil_value.nonpaged_pool + ) + assert sys_value['PagefileUsage'] == psutil_value.pagefile + assert sys_value['PeakPagefileUsage'] == psutil_value.peak_pagefile + + assert psutil_value.rss == psutil_value.wset + assert psutil_value.vms == psutil_value.pagefile + + def test_wait(self): + handle = win32api.OpenProcess( + win32con.PROCESS_QUERY_INFORMATION, win32con.FALSE, self.pid + ) + self.addCleanup(win32api.CloseHandle, handle) + p = psutil.Process(self.pid) + p.terminate() + psutil_value = p.wait() + sys_value = win32process.GetExitCodeProcess(handle) + assert psutil_value == sys_value + + def test_cpu_affinity(self): + def from_bitmask(x): + return [i for i in range(64) if (1 << i) & x] + + handle = win32api.OpenProcess( + win32con.PROCESS_QUERY_INFORMATION, win32con.FALSE, self.pid + ) + self.addCleanup(win32api.CloseHandle, handle) + sys_value = from_bitmask( + win32process.GetProcessAffinityMask(handle)[0] + ) + psutil_value = psutil.Process(self.pid).cpu_affinity() + assert psutil_value == sys_value + + def test_io_counters(self): + handle = win32api.OpenProcess( + win32con.PROCESS_QUERY_INFORMATION, win32con.FALSE, os.getpid() + ) + self.addCleanup(win32api.CloseHandle, handle) + sys_value = win32process.GetProcessIoCounters(handle) + psutil_value = psutil.Process().io_counters() + assert psutil_value.read_count == sys_value['ReadOperationCount'] + assert psutil_value.write_count == sys_value['WriteOperationCount'] + assert psutil_value.read_bytes == sys_value['ReadTransferCount'] + assert psutil_value.write_bytes == sys_value['WriteTransferCount'] + assert psutil_value.other_count == sys_value['OtherOperationCount'] + assert psutil_value.other_bytes == sys_value['OtherTransferCount'] + + def test_num_handles(self): + import ctypes + import ctypes.wintypes + + PROCESS_QUERY_INFORMATION = 0x400 + handle = ctypes.windll.kernel32.OpenProcess( + PROCESS_QUERY_INFORMATION, 0, self.pid + ) + self.addCleanup(ctypes.windll.kernel32.CloseHandle, handle) + + hndcnt = ctypes.wintypes.DWORD() + ctypes.windll.kernel32.GetProcessHandleCount( + handle, ctypes.byref(hndcnt) + ) + sys_value = hndcnt.value + psutil_value = psutil.Process(self.pid).num_handles() + assert psutil_value == sys_value + + def test_error_partial_copy(self): + # https://github.com/giampaolo/psutil/issues/875 + exc = OSError() + exc.winerror = 299 + with mock.patch("psutil._psplatform.cext.proc_cwd", side_effect=exc): + with mock.patch("time.sleep") as m: + p = psutil.Process() + with pytest.raises(psutil.AccessDenied): + p.cwd() + assert m.call_count >= 5 + + def test_exe(self): + # NtQuerySystemInformation succeeds if process is gone. Make sure + # it raises NSP for a non existent pid. + pid = psutil.pids()[-1] + 99999 + proc = psutil._psplatform.Process(pid) + with pytest.raises(psutil.NoSuchProcess): + proc.exe() + + +class TestProcessWMI(WindowsTestCase): + """Compare Process API results with WMI.""" + + @classmethod + def setUpClass(cls): + cls.pid = spawn_testproc().pid + + @classmethod + def tearDownClass(cls): + terminate(cls.pid) + + def test_name(self): + w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + p = psutil.Process(self.pid) + assert p.name() == w.Caption + + # This fail on github because using virtualenv for test environment + @pytest.mark.skipif( + GITHUB_ACTIONS, reason="unreliable path on GITHUB_ACTIONS" + ) + def test_exe(self): + w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + p = psutil.Process(self.pid) + # Note: wmi reports the exe as a lower case string. + # Being Windows paths case-insensitive we ignore that. + assert p.exe().lower() == w.ExecutablePath.lower() + + def test_cmdline(self): + w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + p = psutil.Process(self.pid) + assert ' '.join(p.cmdline()) == w.CommandLine.replace('"', '') + + def test_username(self): + w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + p = psutil.Process(self.pid) + domain, _, username = w.GetOwner() + username = f"{domain}\\{username}" + assert p.username() == username + + @retry_on_failure() + def test_memory_rss(self): + w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + p = psutil.Process(self.pid) + rss = p.memory_info().rss + assert rss == int(w.WorkingSetSize) + + @retry_on_failure() + def test_memory_vms(self): + w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + p = psutil.Process(self.pid) + vms = p.memory_info().vms + # http://msdn.microsoft.com/en-us/library/aa394372(VS.85).aspx + # ...claims that PageFileUsage is represented in Kilo + # bytes but funnily enough on certain platforms bytes are + # returned instead. + wmi_usage = int(w.PageFileUsage) + if vms not in {wmi_usage, wmi_usage * 1024}: + raise self.fail(f"wmi={wmi_usage}, psutil={vms}") + + def test_create_time(self): + w = wmi.WMI().Win32_Process(ProcessId=self.pid)[0] + p = psutil.Process(self.pid) + wmic_create = str(w.CreationDate.split('.')[0]) + psutil_create = time.strftime( + "%Y%m%d%H%M%S", time.localtime(p.create_time()) + ) + assert wmic_create == psutil_create + + +# --- + + +@pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") +class TestDualProcessImplementation(PsutilTestCase): + """Certain APIs on Windows have 2 internal implementations, one + based on documented Windows APIs, another one based + NtQuerySystemInformation() which gets called as fallback in + case the first fails because of limited permission error. + Here we test that the two methods return the exact same value, + see: + https://github.com/giampaolo/psutil/issues/304. + """ + + @classmethod + def setUpClass(cls): + cls.pid = spawn_testproc().pid + + @classmethod + def tearDownClass(cls): + terminate(cls.pid) + + def test_memory_info(self): + mem_1 = psutil.Process(self.pid).memory_info() + with mock.patch( + "psutil._psplatform.cext.proc_memory_info", + side_effect=PermissionError, + ) as fun: + mem_2 = psutil.Process(self.pid).memory_info() + assert len(mem_1) == len(mem_2) + for i in range(len(mem_1)): + assert mem_1[i] >= 0 + assert mem_2[i] >= 0 + assert abs(mem_1[i] - mem_2[i]) < 512 + assert fun.called + + def test_create_time(self): + ctime = psutil.Process(self.pid).create_time() + with mock.patch( + "psutil._psplatform.cext.proc_times", + side_effect=PermissionError, + ) as fun: + assert psutil.Process(self.pid).create_time() == ctime + assert fun.called + + def test_cpu_times(self): + cpu_times_1 = psutil.Process(self.pid).cpu_times() + with mock.patch( + "psutil._psplatform.cext.proc_times", + side_effect=PermissionError, + ) as fun: + cpu_times_2 = psutil.Process(self.pid).cpu_times() + assert fun.called + assert abs(cpu_times_1.user - cpu_times_2.user) < 0.01 + assert abs(cpu_times_1.system - cpu_times_2.system) < 0.01 + + def test_io_counters(self): + io_counters_1 = psutil.Process(self.pid).io_counters() + with mock.patch( + "psutil._psplatform.cext.proc_io_counters", + side_effect=PermissionError, + ) as fun: + io_counters_2 = psutil.Process(self.pid).io_counters() + for i in range(len(io_counters_1)): + assert abs(io_counters_1[i] - io_counters_2[i]) < 5 + assert fun.called + + def test_num_handles(self): + num_handles = psutil.Process(self.pid).num_handles() + with mock.patch( + "psutil._psplatform.cext.proc_num_handles", + side_effect=PermissionError, + ) as fun: + assert psutil.Process(self.pid).num_handles() == num_handles + assert fun.called + + def test_cmdline(self): + for pid in psutil.pids(): + try: + a = cext.proc_cmdline(pid, use_peb=True) + b = cext.proc_cmdline(pid, use_peb=False) + except OSError as err: + err = convert_oserror(err) + if not isinstance( + err, (psutil.AccessDenied, psutil.NoSuchProcess) + ): + raise + else: + assert a == b + + +@pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") +class RemoteProcessTestCase(PsutilTestCase): + """Certain functions require calling ReadProcessMemory. + This trivially works when called on the current process. + Check that this works on other processes, especially when they + have a different bitness. + """ + + @staticmethod + def find_other_interpreter(): + # find a python interpreter that is of the opposite bitness from us + code = "import sys; sys.stdout.write(str(sys.maxsize > 2**32))" + + # XXX: a different and probably more stable approach might be to access + # the registry but accessing 64 bit paths from a 32 bit process + for filename in glob.glob(r"C:\Python*\python.exe"): + proc = subprocess.Popen( + args=[filename, "-c", code], + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + ) + output, _ = proc.communicate() + proc.wait() + if output == str(not IS_64BIT): + return filename + + test_args = ["-c", "import sys; sys.stdin.read()"] + + def setUp(self): + super().setUp() + + other_python = self.find_other_interpreter() + if other_python is None: + raise pytest.skip( + "could not find interpreter with opposite bitness" + ) + if IS_64BIT: + self.python64 = sys.executable + self.python32 = other_python + else: + self.python64 = other_python + self.python32 = sys.executable + + env = os.environ.copy() + env["THINK_OF_A_NUMBER"] = str(os.getpid()) + self.proc32 = self.spawn_testproc( + [self.python32] + self.test_args, env=env, stdin=subprocess.PIPE + ) + self.proc64 = self.spawn_testproc( + [self.python64] + self.test_args, env=env, stdin=subprocess.PIPE + ) + + def tearDown(self): + super().tearDown() + self.proc32.communicate() + self.proc64.communicate() + + def test_cmdline_32(self): + p = psutil.Process(self.proc32.pid) + assert len(p.cmdline()) == 3 + assert p.cmdline()[1:] == self.test_args + + def test_cmdline_64(self): + p = psutil.Process(self.proc64.pid) + assert len(p.cmdline()) == 3 + assert p.cmdline()[1:] == self.test_args + + def test_cwd_32(self): + p = psutil.Process(self.proc32.pid) + assert p.cwd() == os.getcwd() + + def test_cwd_64(self): + p = psutil.Process(self.proc64.pid) + assert p.cwd() == os.getcwd() + + def test_environ_32(self): + p = psutil.Process(self.proc32.pid) + e = p.environ() + assert "THINK_OF_A_NUMBER" in e + assert e["THINK_OF_A_NUMBER"] == str(os.getpid()) + + def test_environ_64(self): + p = psutil.Process(self.proc64.pid) + try: + p.environ() + except psutil.AccessDenied: + pass + + +# =================================================================== +# Windows services +# =================================================================== + + +@pytest.mark.skipif(not WINDOWS, reason="WINDOWS only") +class TestServices(PsutilTestCase): + def test_win_service_iter(self): + valid_statuses = { + "running", + "paused", + "start", + "pause", + "continue", + "stop", + "stopped", + } + valid_start_types = {"automatic", "manual", "disabled"} + valid_statuses = { + "running", + "paused", + "start_pending", + "pause_pending", + "continue_pending", + "stop_pending", + "stopped", + } + for serv in psutil.win_service_iter(): + data = serv.as_dict() + assert isinstance(data['name'], str) + assert data['name'].strip() + assert isinstance(data['display_name'], str) + assert isinstance(data['username'], str) + assert data['status'] in valid_statuses + if data['pid'] is not None: + psutil.Process(data['pid']) + assert isinstance(data['binpath'], str) + assert isinstance(data['username'], str) + assert isinstance(data['start_type'], str) + assert data['start_type'] in valid_start_types + assert data['status'] in valid_statuses + assert isinstance(data['description'], str) + pid = serv.pid() + if pid is not None: + p = psutil.Process(pid) + assert p.is_running() + # win_service_get + s = psutil.win_service_get(serv.name()) + # test __eq__ + assert serv == s + + def test_win_service_get(self): + ERROR_SERVICE_DOES_NOT_EXIST = ( + psutil._psplatform.cext.ERROR_SERVICE_DOES_NOT_EXIST + ) + ERROR_ACCESS_DENIED = psutil._psplatform.cext.ERROR_ACCESS_DENIED + + name = next(psutil.win_service_iter()).name() + with pytest.raises(psutil.NoSuchProcess) as cm: + psutil.win_service_get(name + '???') + assert cm.value.name == name + '???' + + # test NoSuchProcess + service = psutil.win_service_get(name) + exc = OSError(0, "msg", 0) + exc.winerror = ERROR_SERVICE_DOES_NOT_EXIST + with mock.patch( + "psutil._psplatform.cext.winservice_query_status", side_effect=exc + ): + with pytest.raises(psutil.NoSuchProcess): + service.status() + with mock.patch( + "psutil._psplatform.cext.winservice_query_config", side_effect=exc + ): + with pytest.raises(psutil.NoSuchProcess): + service.username() + + # test AccessDenied + exc = OSError(0, "msg", 0) + exc.winerror = ERROR_ACCESS_DENIED + with mock.patch( + "psutil._psplatform.cext.winservice_query_status", side_effect=exc + ): + with pytest.raises(psutil.AccessDenied): + service.status() + with mock.patch( + "psutil._psplatform.cext.winservice_query_config", side_effect=exc + ): + with pytest.raises(psutil.AccessDenied): + service.username() + + # test __str__ and __repr__ + assert service.name() in str(service) + assert service.display_name() in str(service) + assert service.name() in repr(service) + assert service.display_name() in repr(service) diff --git a/llmlab/lib/python3.12/site-packages/pynvml.py b/llmlab/lib/python3.12/site-packages/pynvml.py new file mode 100644 index 0000000..1aaea22 --- /dev/null +++ b/llmlab/lib/python3.12/site-packages/pynvml.py @@ -0,0 +1,6135 @@ +##### +# Copyright (c) 2011-2023, NVIDIA Corporation. All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions are met: +# +# * Redistributions of source code must retain the above copyright notice, +# this list of conditions and the following disclaimer. +# * Redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in the +# documentation and/or other materials provided with the distribution. +# * Neither the name of the NVIDIA Corporation nor the names of its +# contributors may be used to endorse or promote products derived from +# this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE +# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF +# THE POSSIBILITY OF SUCH DAMAGE. +##### + +## +# Python bindings for the NVML library +## +from ctypes import * +from ctypes.util import find_library +from functools import wraps +import sys +import os +import threading +import string + +## C Type mappings ## +## Enums +_nvmlEnableState_t = c_uint +NVML_FEATURE_DISABLED = 0 +NVML_FEATURE_ENABLED = 1 + +_nvmlBrandType_t = c_uint +NVML_BRAND_UNKNOWN = 0 +NVML_BRAND_QUADRO = 1 +NVML_BRAND_TESLA = 2 +NVML_BRAND_NVS = 3 +NVML_BRAND_GRID = 4 # Deprecated from API reporting. Keeping definition for backward compatibility. +NVML_BRAND_GEFORCE = 5 +NVML_BRAND_TITAN = 6 +NVML_BRAND_NVIDIA_VAPPS = 7 # NVIDIA Virtual Applications +NVML_BRAND_NVIDIA_VPC = 8 # NVIDIA Virtual PC +NVML_BRAND_NVIDIA_VCS = 9 # NVIDIA Virtual Compute Server +NVML_BRAND_NVIDIA_VWS = 10 # NVIDIA RTX Virtual Workstation +NVML_BRAND_NVIDIA_CLOUD_GAMING = 11 # NVIDIA Cloud Gaming +NVML_BRAND_NVIDIA_VGAMING = NVML_BRAND_NVIDIA_CLOUD_GAMING # Deprecated from API reporting. Keeping definition for backward compatibility. +NVML_BRAND_QUADRO_RTX = 12 +NVML_BRAND_NVIDIA_RTX = 13 +NVML_BRAND_NVIDIA = 14 +NVML_BRAND_GEFORCE_RTX = 15 # Unused +NVML_BRAND_TITAN_RTX = 16 # Unused +NVML_BRAND_COUNT = 17 + +_nvmlTemperatureThresholds_t = c_uint +NVML_TEMPERATURE_THRESHOLD_SHUTDOWN = 0 +NVML_TEMPERATURE_THRESHOLD_SLOWDOWN = 1 +NVML_TEMPERATURE_THRESHOLD_MEM_MAX = 2 +NVML_TEMPERATURE_THRESHOLD_GPU_MAX = 3 +NVML_TEMPERATURE_THRESHOLD_ACOUSTIC_MIN = 4 +NVML_TEMPERATURE_THRESHOLD_ACOUSTIC_CURR = 5 +NVML_TEMPERATURE_THRESHOLD_ACOUSTIC_MAX = 6 +NVML_TEMPERATURE_THRESHOLD_GPS_CURR = 7 +NVML_TEMPERATURE_THRESHOLD_COUNT = 8 + +_nvmlTemperatureSensors_t = c_uint +NVML_TEMPERATURE_GPU = 0 +NVML_TEMPERATURE_COUNT = 1 + + +_nvmlComputeMode_t = c_uint +NVML_COMPUTEMODE_DEFAULT = 0 +NVML_COMPUTEMODE_EXCLUSIVE_THREAD = 1 ## Support Removed +NVML_COMPUTEMODE_PROHIBITED = 2 +NVML_COMPUTEMODE_EXCLUSIVE_PROCESS = 3 +NVML_COMPUTEMODE_COUNT = 4 + +_nvmlMemoryLocation_t = c_uint +NVML_MEMORY_LOCATION_L1_CACHE = 0 +NVML_MEMORY_LOCATION_L2_CACHE = 1 +NVML_MEMORY_LOCATION_DEVICE_MEMORY = 2 +NVML_MEMORY_LOCATION_DRAM = 2 +NVML_MEMORY_LOCATION_REGISTER_FILE = 3 +NVML_MEMORY_LOCATION_TEXTURE_MEMORY = 4 +NVML_MEMORY_LOCATION_TEXTURE_SHM = 5 +NVML_MEMORY_LOCATION_CBU = 6 +NVML_MEMORY_LOCATION_SRAM = 7 +NVML_MEMORY_LOCATION_COUNT = 8 + +NVML_NVLINK_MAX_LINKS = 18 + +# For backwards compatibility, maintain the incorrectly-named "LANES" define +NVML_NVLINK_MAX_LANES = NVML_NVLINK_MAX_LINKS + +_nvmlNvLinkErrorCounter_t = c_uint +NVML_NVLINK_ERROR_DL_REPLAY = 0 +NVML_NVLINK_ERROR_DL_RECOVERY = 1 +NVML_NVLINK_ERROR_DL_CRC_FLIT = 2 +NVML_NVLINK_ERROR_DL_CRC_DATA = 3 +NVML_NVLINK_ERROR_DL_ECC_DATA = 4 +NVML_NVLINK_ERROR_COUNT = 5 + +_nvmlNvLinkEccLaneErrorCounter_t = c_uint +NVML_NVLINK_ERROR_DL_ECC_LANE0 = 0 +NVML_NVLINK_ERROR_DL_ECC_LANE1 = 1 +NVML_NVLINK_ERROR_DL_ECC_LANE2 = 2 +NVML_NVLINK_ERROR_DL_ECC_LANE3 = 3 +NVML_NVLINK_ERROR_DL_ECC_COUNT = 5 + +_nvmlNvLinkCapability_t = c_uint +NVML_NVLINK_CAP_P2P_SUPPORTED = 0 +NVML_NVLINK_CAP_SYSMEM_ACCESS = 1 +NVML_NVLINK_CAP_P2P_ATOMICS = 2 +NVML_NVLINK_CAP_SYSMEM_ATOMICS= 3 +NVML_NVLINK_CAP_SLI_BRIDGE = 4 +NVML_NVLINK_CAP_VALID = 5 +NVML_NVLINK_CAP_COUNT = 6 + +_nvmlNvLinkUtilizationCountPktTypes_t = c_uint +NVML_NVLINK_COUNTER_PKTFILTER_NOP = 0x1 +NVML_NVLINK_COUNTER_PKTFILTER_READ = 0x2 +NVML_NVLINK_COUNTER_PKTFILTER_WRITE = 0x4 +NVML_NVLINK_COUNTER_PKTFILTER_RATOM = 0x8 +NVML_NVLINK_COUNTER_PKTFILTER_NRATOM = 0x10 +NVML_NVLINK_COUNTER_PKTFILTER_FLUSH = 0x20 +NVML_NVLINK_COUNTER_PKTFILTER_RESPDATA = 0x40 +NVML_NVLINK_COUNTER_PKTFILTER_RESPNODATA = 0x80 +NVML_NVLINK_COUNTER_PKTFILTER_ALL = 0xFF + +_nvmlNvLinkUtilizationCountUnits_t = c_uint +NVML_NVLINK_COUNTER_UNIT_CYCLES = 0 +NVML_NVLINK_COUNTER_UNIT_PACKETS = 1 +NVML_NVLINK_COUNTER_UNIT_BYTES = 2 +NVML_NVLINK_COUNTER_UNIT_RESERVED = 3 +NVML_NVLINK_COUNTER_UNIT_COUNT = 4 + +_nvmlNvLinkDeviceType_t = c_uint +NVML_NVLINK_DEVICE_TYPE_GPU = 0x00 +NVML_NVLINK_DEVICE_TYPE_IBMNPU = 0x01 +NVML_NVLINK_DEVICE_TYPE_SWITCH = 0x02 +NVML_NVLINK_DEVICE_TYPE_UNKNOWN = 0xFF + +# These are deprecated, instead use _nvmlMemoryErrorType_t +_nvmlEccBitType_t = c_uint +NVML_SINGLE_BIT_ECC = 0 +NVML_DOUBLE_BIT_ECC = 1 +NVML_ECC_ERROR_TYPE_COUNT = 2 + +_nvmlEccCounterType_t = c_uint +NVML_VOLATILE_ECC = 0 +NVML_AGGREGATE_ECC = 1 +NVML_ECC_COUNTER_TYPE_COUNT = 2 + +_nvmlMemoryErrorType_t = c_uint +NVML_MEMORY_ERROR_TYPE_CORRECTED = 0 +NVML_MEMORY_ERROR_TYPE_UNCORRECTED = 1 +NVML_MEMORY_ERROR_TYPE_COUNT = 2 + +_nvmlClockType_t = c_uint +NVML_CLOCK_GRAPHICS = 0 +NVML_CLOCK_SM = 1 +NVML_CLOCK_MEM = 2 +NVML_CLOCK_VIDEO = 3 +NVML_CLOCK_COUNT = 4 + +_nvmlClockId_t = c_uint +NVML_CLOCK_ID_CURRENT = 0 +NVML_CLOCK_ID_APP_CLOCK_TARGET = 1 +NVML_CLOCK_ID_APP_CLOCK_DEFAULT = 2 +NVML_CLOCK_ID_CUSTOMER_BOOST_MAX = 3 +NVML_CLOCK_ID_COUNT = 4 + +_nvmlDriverModel_t = c_uint +NVML_DRIVER_WDDM = 0 +NVML_DRIVER_WDM = 1 +NVML_DRIVER_MCDM = 2 + +NVML_MAX_GPU_PERF_PSTATES = 16 + +_nvmlPstates_t = c_uint +NVML_PSTATE_0 = 0 +NVML_PSTATE_1 = 1 +NVML_PSTATE_2 = 2 +NVML_PSTATE_3 = 3 +NVML_PSTATE_4 = 4 +NVML_PSTATE_5 = 5 +NVML_PSTATE_6 = 6 +NVML_PSTATE_7 = 7 +NVML_PSTATE_8 = 8 +NVML_PSTATE_9 = 9 +NVML_PSTATE_10 = 10 +NVML_PSTATE_11 = 11 +NVML_PSTATE_12 = 12 +NVML_PSTATE_13 = 13 +NVML_PSTATE_14 = 14 +NVML_PSTATE_15 = 15 +NVML_PSTATE_UNKNOWN = 32 + +_nvmlInforomObject_t = c_uint +NVML_INFOROM_OEM = 0 +NVML_INFOROM_ECC = 1 +NVML_INFOROM_POWER = 2 +NVML_INFOROM_DEN = 3 +NVML_INFOROM_COUNT = 4 + +_nvmlReturn_t = c_uint +NVML_SUCCESS = 0 +NVML_ERROR_UNINITIALIZED = 1 +NVML_ERROR_INVALID_ARGUMENT = 2 +NVML_ERROR_NOT_SUPPORTED = 3 +NVML_ERROR_NO_PERMISSION = 4 +NVML_ERROR_ALREADY_INITIALIZED = 5 +NVML_ERROR_NOT_FOUND = 6 +NVML_ERROR_INSUFFICIENT_SIZE = 7 +NVML_ERROR_INSUFFICIENT_POWER = 8 +NVML_ERROR_DRIVER_NOT_LOADED = 9 +NVML_ERROR_TIMEOUT = 10 +NVML_ERROR_IRQ_ISSUE = 11 +NVML_ERROR_LIBRARY_NOT_FOUND = 12 +NVML_ERROR_FUNCTION_NOT_FOUND = 13 +NVML_ERROR_CORRUPTED_INFOROM = 14 +NVML_ERROR_GPU_IS_LOST = 15 +NVML_ERROR_RESET_REQUIRED = 16 +NVML_ERROR_OPERATING_SYSTEM = 17 +NVML_ERROR_LIB_RM_VERSION_MISMATCH = 18 +NVML_ERROR_IN_USE = 19 +NVML_ERROR_MEMORY = 20 +NVML_ERROR_NO_DATA = 21 +NVML_ERROR_VGPU_ECC_NOT_SUPPORTED = 22 +NVML_ERROR_INSUFFICIENT_RESOURCES = 23 +NVML_ERROR_FREQ_NOT_SUPPORTED = 24 +NVML_ERROR_ARGUMENT_VERSION_MISMATCH = 25 +NVML_ERROR_DEPRECATED = 26 +NVML_ERROR_NOT_READY = 27 +NVML_ERROR_GPU_NOT_FOUND = 28 +NVML_ERROR_INVALID_STATE = 29 +NVML_ERROR_UNKNOWN = 999 + +_nvmlFanState_t = c_uint +NVML_FAN_NORMAL = 0 +NVML_FAN_FAILED = 1 + +_nvmlFanControlPolicy_t = c_uint +NVML_FAN_POLICY_TEMPERATURE_CONTINOUS_SW = 0 +NVML_FAN_POLICY_MANUAL = 1 + +_nvmlLedColor_t = c_uint +NVML_LED_COLOR_GREEN = 0 +NVML_LED_COLOR_AMBER = 1 + +_nvmlGpuOperationMode_t = c_uint +NVML_GOM_ALL_ON = 0 +NVML_GOM_COMPUTE = 1 +NVML_GOM_LOW_DP = 2 + +_nvmlPageRetirementCause_t = c_uint +NVML_PAGE_RETIREMENT_CAUSE_MULTIPLE_SINGLE_BIT_ECC_ERRORS = 0 +NVML_PAGE_RETIREMENT_CAUSE_DOUBLE_BIT_ECC_ERROR = 1 +NVML_PAGE_RETIREMENT_CAUSE_COUNT = 2 + +_nvmlRestrictedAPI_t = c_uint +NVML_RESTRICTED_API_SET_APPLICATION_CLOCKS = 0 +NVML_RESTRICTED_API_SET_AUTO_BOOSTED_CLOCKS = 1 +NVML_RESTRICTED_API_COUNT = 2 + +_nvmlBridgeChipType_t = c_uint +NVML_BRIDGE_CHIP_PLX = 0 +NVML_BRIDGE_CHIP_BRO4 = 1 +NVML_MAX_PHYSICAL_BRIDGE = 128 + +_nvmlValueType_t = c_uint +NVML_VALUE_TYPE_DOUBLE = 0 +NVML_VALUE_TYPE_UNSIGNED_INT = 1 +NVML_VALUE_TYPE_UNSIGNED_LONG = 2 +NVML_VALUE_TYPE_UNSIGNED_LONG_LONG = 3 +NVML_VALUE_TYPE_SIGNED_LONG_LONG = 4 +NVML_VALUE_TYPE_SIGNED_INT = 5 +NVML_VALUE_TYPE_UNSIGNED_SHORT = 6 +NVML_VALUE_TYPE_COUNT = 7 + +_nvmlNvlinkVersion_t = c_uint +NVML_NVLINK_VERSION_INVALID = 0 +NVML_NVLINK_VERSION_1_0 = 1 +NVML_NVLINK_VERSION_2_0 = 2 +NVML_NVLINK_VERSION_2_2 = 3 +NVML_NVLINK_VERSION_3_0 = 4 +NVML_NVLINK_VERSION_3_1 = 5 +NVML_NVLINK_VERSION_4_0 = 6 +NVML_NVLINK_VERSION_5_0 = 7 + +_nvmlPerfPolicyType_t = c_uint +NVML_PERF_POLICY_POWER = 0 +NVML_PERF_POLICY_THERMAL = 1 +NVML_PERF_POLICY_SYNC_BOOST = 2 +NVML_PERF_POLICY_BOARD_LIMIT = 3 +NVML_PERF_POLICY_LOW_UTILIZATION = 4 +NVML_PERF_POLICY_RELIABILITY = 5 +NVML_PERF_POLICY_TOTAL_APP_CLOCKS = 10 +NVML_PERF_POLICY_TOTAL_BASE_CLOCKS = 11 +NVML_PERF_POLICY_COUNT = 12 + +_nvmlEncoderQueryType_t = c_uint +NVML_ENCODER_QUERY_H264 = 0 +NVML_ENCODER_QUERY_HEVC = 1 +NVML_ENCODER_QUERY_AV1 = 2 +NVML_ENCODER_QUERY_UNKNOWN = 255 + +_nvmlFBCSessionType_t = c_uint +NVML_FBC_SESSION_TYPE_UNKNOWN = 0 +NVML_FBC_SESSION_TYPE_TOSYS = 1 +NVML_FBC_SESSION_TYPE_CUDA = 2 +NVML_FBC_SESSION_TYPE_VID = 3 +NVML_FBC_SESSION_TYPE_HWENC = 4 + +_nvmlDetachGpuState_t = c_uint +NVML_DETACH_GPU_KEEP = 0 +NVML_DETACH_GPU_REMOVE = 1 + +_nvmlPcieLinkState_t = c_uint +NVML_PCIE_LINK_KEEP = 0 +NVML_PCIE_LINK_SHUT_DOWN = 1 + +_nvmlSamplingType_t = c_uint +NVML_TOTAL_POWER_SAMPLES = 0 +NVML_GPU_UTILIZATION_SAMPLES = 1 +NVML_MEMORY_UTILIZATION_SAMPLES = 2 +NVML_ENC_UTILIZATION_SAMPLES = 3 +NVML_DEC_UTILIZATION_SAMPLES = 4 +NVML_PROCESSOR_CLK_SAMPLES = 5 +NVML_MEMORY_CLK_SAMPLES = 6 +NVML_MODULE_POWER_SAMPLES = 7 +NVML_JPG_UTILIZATION_SAMPLES = 8 +NVML_OFA_UTILIZATION_SAMPLES = 9 +NVML_SAMPLINGTYPE_COUNT = 10 + +_nvmlPcieUtilCounter_t = c_uint +NVML_PCIE_UTIL_TX_BYTES = 0 +NVML_PCIE_UTIL_RX_BYTES = 1 +NVML_PCIE_UTIL_COUNT = 2 + +_nvmlGpuTopologyLevel_t = c_uint +NVML_TOPOLOGY_INTERNAL = 0 +NVML_TOPOLOGY_SINGLE = 10 +NVML_TOPOLOGY_MULTIPLE = 20 +NVML_TOPOLOGY_HOSTBRIDGE = 30 +NVML_TOPOLOGY_NODE = 40 +NVML_TOPOLOGY_CPU = NVML_TOPOLOGY_NODE +NVML_TOPOLOGY_SYSTEM = 50 + +_nvmlGpuP2PCapsIndex_t = c_uint +NVML_P2P_CAPS_INDEX_READ = 0, +NVML_P2P_CAPS_INDEX_WRITE = 1 +NVML_P2P_CAPS_INDEX_NVLINK =2 +NVML_P2P_CAPS_INDEX_ATOMICS = 3 +# +# NVML_P2P_CAPS_INDEX_PROP is deprecated. +# Use NVML_P2P_CAPS_INDEX_PCI instead. +# +NVML_P2P_CAPS_INDEX_PROP = 4 +NVML_P2P_CAPS_INDEX_PCI = 4 +NVML_P2P_CAPS_INDEX_UNKNOWN = 5 + +_nvmlGpuP2PStatus_t = c_uint +NVML_P2P_STATUS_OK = 0 +NVML_P2P_STATUS_CHIPSET_NOT_SUPPORED = 1 +NVML_P2P_STATUS_CHIPSET_NOT_SUPPORTED = NVML_P2P_STATUS_CHIPSET_NOT_SUPPORED +NVML_P2P_STATUS_GPU_NOT_SUPPORTED = 2 +NVML_P2P_STATUS_IOH_TOPOLOGY_NOT_SUPPORTED =3 +NVML_P2P_STATUS_DISABLED_BY_REGKEY =4 +NVML_P2P_STATUS_NOT_SUPPORTED =5 +NVML_P2P_STATUS_UNKNOWN =6 + +_nvmlDeviceArchitecture_t = c_uint +NVML_DEVICE_ARCH_KEPLER = 2 +NVML_DEVICE_ARCH_MAXWELL = 3 +NVML_DEVICE_ARCH_PASCAL = 4 +NVML_DEVICE_ARCH_VOLTA = 5 +NVML_DEVICE_ARCH_TURING = 6 +NVML_DEVICE_ARCH_AMPERE = 7 +NVML_DEVICE_ARCH_ADA = 8 +NVML_DEVICE_ARCH_HOPPER = 9 +NVML_DEVICE_ARCH_BLACKWELL = 10 +NVML_DEVICE_ARCH_T23X = 11 +NVML_DEVICE_ARCH_UNKNOWN = 0xffffffff + +# PCI bus Types +_nvmlBusType_t = c_uint +NVML_BUS_TYPE_UNKNOWN = 0 +NVML_BUS_TYPE_PCI = 1 +NVML_BUS_TYPE_PCIE = 2 +NVML_BUS_TYPE_FPCI = 3 +NVML_BUS_TYPE_AGP = 4 + +_nvmlPowerSource_t = c_uint +NVML_POWER_SOURCE_AC = 0x00000000 +NVML_POWER_SOURCE_BATTERY = 0x00000001 +NVML_POWER_SOURCE_UNDERSIZED = 0x00000002 + +_nvmlAdaptiveClockInfoStatus_t = c_uint +NVML_ADAPTIVE_CLOCKING_INFO_STATUS_DISABLED = 0x00000000 +NVML_ADAPTIVE_CLOCKING_INFO_STATUS_ENABLED = 0x00000001 + +_nvmlClockLimitId_t = c_uint +NVML_CLOCK_LIMIT_ID_RANGE_START = 0xffffff00 +NVML_CLOCK_LIMIT_ID_TDP = 0xffffff01 +NVML_CLOCK_LIMIT_ID_UNLIMITED = 0xffffff02 + +_nvmlPcieLinkMaxSpeed_t = c_uint +NVML_PCIE_LINK_MAX_SPEED_INVALID = 0x00000000 +NVML_PCIE_LINK_MAX_SPEED_2500MBPS = 0x00000001 +NVML_PCIE_LINK_MAX_SPEED_5000MBPS = 0x00000002 +NVML_PCIE_LINK_MAX_SPEED_8000MBPS = 0x00000003 +NVML_PCIE_LINK_MAX_SPEED_16000MBPS = 0x00000004 +NVML_PCIE_LINK_MAX_SPEED_32000MBPS = 0x00000005 +NVML_PCIE_LINK_MAX_SPEED_64000MBPS = 0x00000006 + +_nvmlPcieAtomicsCapability_t = c_uint +NVML_PCIE_ATOMICS_CAP_FETCHADD32 = 0x01 +NVML_PCIE_ATOMICS_CAP_FETCHADD64 = 0x02 +NVML_PCIE_ATOMICS_CAP_SWAP32 = 0x04 +NVML_PCIE_ATOMICS_CAP_SWAP64 = 0x08 +NVML_PCIE_ATOMICS_CAP_CAS32 = 0x10 +NVML_PCIE_ATOMICS_CAP_CAS64 = 0x20 +NVML_PCIE_ATOMICS_CAP_CAS128 = 0x40 +NVML_PCIE_ATOMICS_OPS_MAX = 7 + +_nvmlAffinityScope_t = c_uint +NVML_AFFINITY_SCOPE_NODE = 0 +NVML_AFFINITY_SCOPE_SOCKET = 1 + +_nvmlDeviceGpuRecoveryAction_t = c_uint +NVML_GPU_RECOVERY_ACTION_NONE = 0 +NVML_GPU_RECOVERY_ACTION_GPU_RESET = 1 +NVML_GPU_RECOVERY_ACTION_NODE_REBOOT = 2 +NVML_GPU_RECOVERY_ACTION_DRAIN_P2P = 3 +NVML_GPU_RECOVERY_ACTION_DRAIN_AND_RESET = 4 + +# C preprocessor defined values +nvmlFlagDefault = 0 +nvmlFlagForce = 1 +NVML_INIT_FLAG_NO_GPUS = 1 +NVML_INIT_FLAG_NO_ATTACH = 2 + +NVML_MAX_GPC_COUNT = 32 + +# buffer size +NVML_DEVICE_INFOROM_VERSION_BUFFER_SIZE = 16 +NVML_DEVICE_UUID_BUFFER_SIZE = 80 +NVML_DEVICE_UUID_V2_BUFFER_SIZE = 96 +NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE = 80 +NVML_SYSTEM_NVML_VERSION_BUFFER_SIZE = 80 +NVML_DEVICE_NAME_BUFFER_SIZE = 64 +NVML_DEVICE_NAME_V2_BUFFER_SIZE = 96 +NVML_DEVICE_SERIAL_BUFFER_SIZE = 30 +NVML_DEVICE_PART_NUMBER_BUFFER_SIZE = 80 +NVML_DEVICE_GPU_PART_NUMBER_BUFFER_SIZE = 80 +NVML_DEVICE_VBIOS_VERSION_BUFFER_SIZE = 32 +NVML_DEVICE_PCI_BUS_ID_BUFFER_SIZE = 32 +NVML_DEVICE_PCI_BUS_ID_BUFFER_V2_SIZE = 16 +NVML_GRID_LICENSE_BUFFER_SIZE = 128 +NVML_VGPU_NAME_BUFFER_SIZE = 64 +NVML_GRID_LICENSE_FEATURE_MAX_COUNT = 3 +NVML_VGPU_METADATA_OPAQUE_DATA_SIZE = sizeof(c_uint) + 256 +NVML_VGPU_PGPU_METADATA_OPAQUE_DATA_SIZE = 256 +NVML_DEVICE_GPU_FRU_PART_NUMBER_BUFFER_SIZE = 0x14 # NV2080_GPU_MAX_PRODUCT_PART_NUMBER_LENGTH +NVML_PERF_MODES_BUFFER_SIZE = 2048 + +# Format strings +NVML_DEVICE_PCI_BUS_ID_LEGACY_FMT = "%04X:%02X:%02X.0" +NVML_DEVICE_PCI_BUS_ID_FMT = "%08X:%02X:%02X.0" + +NVML_VALUE_NOT_AVAILABLE_ulonglong = c_ulonglong(-1) +NVML_VALUE_NOT_AVAILABLE_uint = c_uint(-1) + +''' + Field Identifiers. + + All Identifiers pertain to a device. Each ID is only used once and is guaranteed never to change. +''' +NVML_FI_DEV_ECC_CURRENT = 1 # Current ECC mode. 1=Active. 0=Inactive +NVML_FI_DEV_ECC_PENDING = 2 # Pending ECC mode. 1=Active. 0=Inactive + +#ECC Count Totals +NVML_FI_DEV_ECC_SBE_VOL_TOTAL = 3 # Total single bit volatile ECC errors +NVML_FI_DEV_ECC_DBE_VOL_TOTAL = 4 # Total double bit volatile ECC errors +NVML_FI_DEV_ECC_SBE_AGG_TOTAL = 5 # Total single bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_DBE_AGG_TOTAL = 6 # Total double bit aggregate (persistent) ECC errors +#Individual ECC locations +NVML_FI_DEV_ECC_SBE_VOL_L1 = 7 # L1 cache single bit volatile ECC errors +NVML_FI_DEV_ECC_DBE_VOL_L1 = 8 # L1 cache double bit volatile ECC errors +NVML_FI_DEV_ECC_SBE_VOL_L2 = 9 # L2 cache single bit volatile ECC errors +NVML_FI_DEV_ECC_DBE_VOL_L2 = 10 # L2 cache double bit volatile ECC errors +NVML_FI_DEV_ECC_SBE_VOL_DEV = 11 # Device memory single bit volatile ECC errors +NVML_FI_DEV_ECC_DBE_VOL_DEV = 12 # Device memory double bit volatile ECC errors +NVML_FI_DEV_ECC_SBE_VOL_REG = 13 # Register file single bit volatile ECC errors +NVML_FI_DEV_ECC_DBE_VOL_REG = 14 # Register file double bit volatile ECC errors +NVML_FI_DEV_ECC_SBE_VOL_TEX = 15 # Texture memory single bit volatile ECC errors +NVML_FI_DEV_ECC_DBE_VOL_TEX = 16 # Texture memory double bit volatile ECC errors +NVML_FI_DEV_ECC_DBE_VOL_CBU = 17 # CBU double bit volatile ECC errors +NVML_FI_DEV_ECC_SBE_AGG_L1 = 18 # L1 cache single bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_DBE_AGG_L1 = 19 # L1 cache double bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_SBE_AGG_L2 = 20 # L2 cache single bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_DBE_AGG_L2 = 21 # L2 cache double bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_SBE_AGG_DEV = 22 # Device memory single bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_DBE_AGG_DEV = 23 # Device memory double bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_SBE_AGG_REG = 24 # Register File single bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_DBE_AGG_REG = 25 # Register File double bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_SBE_AGG_TEX = 26 # Texture memory single bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_DBE_AGG_TEX = 27 # Texture memory double bit aggregate (persistent) ECC errors +NVML_FI_DEV_ECC_DBE_AGG_CBU = 28 # CBU double bit aggregate ECC errors + +# Page Retirement +NVML_FI_DEV_RETIRED_SBE = 29 # Number of retired pages because of single bit errors +NVML_FI_DEV_RETIRED_DBE = 30 # Number of retired pages because of double bit errors +NVML_FI_DEV_RETIRED_PENDING = 31 # If any pages are pending retirement. 1=yes. 0=no. + +# NvLink Flit Error Counters +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L0 = 32 # NVLink flow control CRC Error Counter for Lane 0 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L1 = 33 # NVLink flow control CRC Error Counter for Lane 1 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L2 = 34 # NVLink flow control CRC Error Counter for Lane 2 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L3 = 35 # NVLink flow control CRC Error Counter for Lane 3 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L4 = 36 # NVLink flow control CRC Error Counter for Lane 4 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L5 = 37 # NVLink flow control CRC Error Counter for Lane 5 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_TOTAL = 38 # NVLink flow control CRC Error Counter total for all Lanes + +# NvLink CRC Data Error Counters +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L0 = 39 # NVLink data CRC Error Counter for Lane 0 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L1 = 40 # NVLink data CRC Error Counter for Lane 1 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L2 = 41 # NVLink data CRC Error Counter for Lane 2 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L3 = 42 # NVLink data CRC Error Counter for Lane 3 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L4 = 43 # NVLink data CRC Error Counter for Lane 4 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L5 = 44 # NVLink data CRC Error Counter for Lane 5 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_TOTAL = 45 # NvLink data CRC Error Counter total for all Lanes + +# NvLink Replay Error Counters +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L0 = 46 # NVLink Replay Error Counter for Lane 0 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L1 = 47 # NVLink Replay Error Counter for Lane 1 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L2 = 48 # NVLink Replay Error Counter for Lane 2 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L3 = 49 # NVLink Replay Error Counter for Lane 3 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L4 = 50 # NVLink Replay Error Counter for Lane 4 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L5 = 51 # NVLink Replay Error Counter for Lane 5 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_TOTAL = 52 # NVLink Replay Error Counter total for all Lanes + +# NvLink Recovery Error Counters +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L0 = 53 # NVLink Recovery Error Counter for Lane 0 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L1 = 54 # NVLink Recovery Error Counter for Lane 1 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L2 = 55 # NVLink Recovery Error Counter for Lane 2 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L3 = 56 # NVLink Recovery Error Counter for Lane 3 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L4 = 57 # NVLink Recovery Error Counter for Lane 4 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L5 = 58 # NVLink Recovery Error Counter for Lane 5 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_TOTAL = 59 # NVLink Recovery Error Counter total for all Lanes + +# NvLink Bandwidth Counters +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L0 = 60 # NVLink Bandwidth Counter for Counter Set 0, Lane 0 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L1 = 61 # NVLink Bandwidth Counter for Counter Set 0, Lane 1 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L2 = 62 # NVLink Bandwidth Counter for Counter Set 0, Lane 2 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L3 = 63 # NVLink Bandwidth Counter for Counter Set 0, Lane 3 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L4 = 64 # NVLink Bandwidth Counter for Counter Set 0, Lane 4 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L5 = 65 # NVLink Bandwidth Counter for Counter Set 0, Lane 5 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_TOTAL = 66 # NVLink Bandwidth Counter Total for Counter Set 0, All Lanes + +# NvLink Bandwidth Counters +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L0 = 67 # NVLink Bandwidth Counter for Counter Set 1, Lane 0 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L1 = 68 # NVLink Bandwidth Counter for Counter Set 1, Lane 1 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L2 = 69 # NVLink Bandwidth Counter for Counter Set 1, Lane 2 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L3 = 70 # NVLink Bandwidth Counter for Counter Set 1, Lane 3 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L4 = 71 # NVLink Bandwidth Counter for Counter Set 1, Lane 4 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L5 = 72 # NVLink Bandwidth Counter for Counter Set 1, Lane 5 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_TOTAL = 73 # NVLink Bandwidth Counter Total for Counter Set 1, All Lanes + +# Perf Policy Counters +NVML_FI_DEV_PERF_POLICY_POWER = 74 # Perf Policy Counter for Power Policy +NVML_FI_DEV_PERF_POLICY_THERMAL = 75 # Perf Policy Counter for Thermal Policy +NVML_FI_DEV_PERF_POLICY_SYNC_BOOST = 76 # Perf Policy Counter for Sync boost Policy +NVML_FI_DEV_PERF_POLICY_BOARD_LIMIT = 77 # Perf Policy Counter for Board Limit +NVML_FI_DEV_PERF_POLICY_LOW_UTILIZATION = 78 # Perf Policy Counter for Low GPU Utilization Policy +NVML_FI_DEV_PERF_POLICY_RELIABILITY = 79 # Perf Policy Counter for Reliability Policy +NVML_FI_DEV_PERF_POLICY_TOTAL_APP_CLOCKS = 80 # Perf Policy Counter for Total App Clock Policy +NVML_FI_DEV_PERF_POLICY_TOTAL_BASE_CLOCKS = 81 # Perf Policy Counter for Total Base Clocks Policy + +# Memory temperatures +NVML_FI_DEV_MEMORY_TEMP = 82 # Memory temperature for the device + +# Energy Counter +NVML_FI_DEV_TOTAL_ENERGY_CONSUMPTION = 83 # Total energy consumption for the GPU in mJ since the driver was last reloaded + +# NVLink Speed +NVML_FI_DEV_NVLINK_SPEED_MBPS_L0 = 84 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L1 = 85 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L2 = 86 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L3 = 87 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L4 = 88 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L5 = 89 +NVML_FI_DEV_NVLINK_SPEED_MBPS_COMMON = 90 + +# NVLink Link Count +NVML_FI_DEV_NVLINK_LINK_COUNT = 91 + +# Page Retirement pending fields +NVML_FI_DEV_RETIRED_PENDING_SBE = 92 +NVML_FI_DEV_RETIRED_PENDING_DBE = 93 + +# PCIe replay and replay rollover counters +NVML_FI_DEV_PCIE_REPLAY_COUNTER = 94 +NVML_FI_DEV_PCIE_REPLAY_ROLLOVER_COUNTER = 95 + +# NvLink Flit Error Counters +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L6 = 96 # NVLink flow control CRC Error Counter for Lane 6 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L7 = 97 # NVLink flow control CRC Error Counter for Lane 7 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L8 = 98 # NVLink flow control CRC Error Counter for Lane 8 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L9 = 99 # NVLink flow control CRC Error Counter for Lane 9 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L10 = 100 # NVLink flow control CRC Error Counter for Lane 10 +NVML_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L11 = 101 # NVLink flow control CRC Error Counter for Lane 11 + +# NvLink CRC Data Error Counters +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L6 = 102 # NVLink data CRC Error Counter for Lane 6 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L7 = 103 # NVLink data CRC Error Counter for Lane 7 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L8 = 104 # NVLink data CRC Error Counter for Lane 8 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L9 = 105 # NVLink data CRC Error Counter for Lane 9 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L10 = 106 # NVLink data CRC Error Counter for Lane 10 +NVML_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L11 = 107 # NVLink data CRC Error Counter for Lane 11 + +# NvLink Replay Error Counters +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L6 = 108 # NVLink Replay Error Counter for Lane 6 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L7 = 109 # NVLink Replay Error Counter for Lane 7 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L8 = 110 # NVLink Replay Error Counter for Lane 8 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L9 = 111 # NVLink Replay Error Counter for Lane 9 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L10 = 112 # NVLink Replay Error Counter for Lane 10 +NVML_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L11 = 113 # NVLink Replay Error Counter for Lane 11 + +# NvLink Recovery Error Counters +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L6 = 114 # NVLink Recovery Error Counter for Lane 6 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L7 = 115 # NVLink Recovery Error Counter for Lane 7 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L8 = 116 # NVLink Recovery Error Counter for Lane 8 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L9 = 117 # NVLink Recovery Error Counter for Lane 9 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L10 = 118 # NVLink Recovery Error Counter for Lane 10 +NVML_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L11 = 119 # NVLink Recovery Error Counter for Lane 11 + +# NvLink Bandwidth Counters +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L6 = 120 # NVLink Bandwidth Counter for Counter Set 0, Lane 6 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L7 = 121 # NVLink Bandwidth Counter for Counter Set 0, Lane 7 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L8 = 122 # NVLink Bandwidth Counter for Counter Set 0, Lane 8 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L9 = 123 # NVLink Bandwidth Counter for Counter Set 0, Lane 9 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L10 = 124 # NVLink Bandwidth Counter for Counter Set 0, Lane 10 +NVML_FI_DEV_NVLINK_BANDWIDTH_C0_L11 = 125 # NVLink Bandwidth Counter for Counter Set 0, Lane 11 + +# NvLink Bandwidth Counters +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L6 = 126 # NVLink Bandwidth Counter for Counter Set 1, Lane 6 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L7 = 127 # NVLink Bandwidth Counter for Counter Set 1, Lane 7 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L8 = 128 # NVLink Bandwidth Counter for Counter Set 1, Lane 8 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L9 = 129 # NVLink Bandwidth Counter for Counter Set 1, Lane 9 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L10 = 130 # NVLink Bandwidth Counter for Counter Set 1, Lane 10 +NVML_FI_DEV_NVLINK_BANDWIDTH_C1_L11 = 131 # NVLink Bandwidth Counter for Counter Set 1, Lane 11 + +# NVLink Speed +NVML_FI_DEV_NVLINK_SPEED_MBPS_L6 = 132 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L7 = 133 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L8 = 134 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L9 = 135 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L10 = 136 +NVML_FI_DEV_NVLINK_SPEED_MBPS_L11 = 137 + +# NVLink Throughput Counters +NVML_FI_DEV_NVLINK_THROUGHPUT_DATA_TX = 138 # NVLink TX Data throughput in KiB +NVML_FI_DEV_NVLINK_THROUGHPUT_DATA_RX = 139 # NVLink RX Data throughput in KiB +NVML_FI_DEV_NVLINK_THROUGHPUT_RAW_TX = 140 # NVLink TX Data + protocol overhead in KiB +NVML_FI_DEV_NVLINK_THROUGHPUT_RAW_RX = 141 # NVLink RX Data + protocol overhead in KiB + +# Row Remapper +NVML_FI_DEV_REMAPPED_COR = 142 +NVML_FI_DEV_REMAPPED_UNC = 143 +NVML_FI_DEV_REMAPPED_PENDING = 144 +NVML_FI_DEV_REMAPPED_FAILURE = 145 + +#Remote device NVLink ID +NVML_FI_DEV_NVLINK_REMOTE_NVLINK_ID = 146 + +# Number of NVLinks connected to NVSwitch +NVML_FI_DEV_NVSWITCH_CONNECTED_LINK_COUNT = 147 + +# NvLink ECC Data Error Counters +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L0 = 148 #< NVLink data ECC Error Counter for Link 0 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L1 = 149 #< NVLink data ECC Error Counter for Link 1 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L2 = 150 #< NVLink data ECC Error Counter for Link 2 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L3 = 151 #< NVLink data ECC Error Counter for Link 3 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L4 = 152 #< NVLink data ECC Error Counter for Link 4 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L5 = 153 #< NVLink data ECC Error Counter for Link 5 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L6 = 154 #< NVLink data ECC Error Counter for Link 6 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L7 = 155 #< NVLink data ECC Error Counter for Link 7 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L8 = 156 #< NVLink data ECC Error Counter for Link 8 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L9 = 157 #< NVLink data ECC Error Counter for Link 9 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L10 = 158 #< NVLink data ECC Error Counter for Link 10 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_L11 = 159 #< NVLink data ECC Error Counter for Link 11 +NVML_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_TOTAL = 160 #< NvLink data ECC Error Counter total for all Links + +NVML_FI_DEV_NVLINK_ERROR_DL_REPLAY = 161 +NVML_FI_DEV_NVLINK_ERROR_DL_RECOVERY = 162 +NVML_FI_DEV_NVLINK_ERROR_DL_CRC = 163 +NVML_FI_DEV_NVLINK_GET_SPEED = 164 +NVML_FI_DEV_NVLINK_GET_STATE = 165 +NVML_FI_DEV_NVLINK_GET_VERSION = 166 + +NVML_FI_DEV_NVLINK_GET_POWER_STATE = 167 +NVML_FI_DEV_NVLINK_GET_POWER_THRESHOLD = 168 + +NVML_FI_DEV_PCIE_L0_TO_RECOVERY_COUNTER = 169 + +NVML_FI_DEV_C2C_LINK_COUNT = 170 +NVML_FI_DEV_C2C_LINK_GET_STATUS = 171 +NVML_FI_DEV_C2C_LINK_GET_MAX_BW = 172 + +NVML_FI_DEV_PCIE_COUNT_CORRECTABLE_ERRORS = 173 +NVML_FI_DEV_PCIE_COUNT_NAKS_RECEIVED = 174 +NVML_FI_DEV_PCIE_COUNT_RECEIVER_ERROR = 175 +NVML_FI_DEV_PCIE_COUNT_BAD_TLP = 176 +NVML_FI_DEV_PCIE_COUNT_NAKS_SENT = 177 +NVML_FI_DEV_PCIE_COUNT_BAD_DLLP = 178 +NVML_FI_DEV_PCIE_COUNT_NON_FATAL_ERROR = 179 +NVML_FI_DEV_PCIE_COUNT_FATAL_ERROR = 180 +NVML_FI_DEV_PCIE_COUNT_UNSUPPORTED_REQ = 181 +NVML_FI_DEV_PCIE_COUNT_LCRC_ERROR = 182 +NVML_FI_DEV_PCIE_COUNT_LANE_ERROR = 183 + +NVML_FI_DEV_IS_RESETLESS_MIG_SUPPORTED = 184 + +NVML_FI_DEV_POWER_AVERAGE = 185 +NVML_FI_DEV_POWER_INSTANT = 186 +NVML_FI_DEV_POWER_MIN_LIMIT = 187 +NVML_FI_DEV_POWER_MAX_LIMIT = 188 +NVML_FI_DEV_POWER_DEFAULT_LIMIT = 189 +NVML_FI_DEV_POWER_CURRENT_LIMIT = 190 +NVML_FI_DEV_ENERGY = 191 +NVML_FI_DEV_POWER_REQUESTED_LIMIT = 192 + +NVML_FI_DEV_TEMPERATURE_SHUTDOWN_TLIMIT = 193 +NVML_FI_DEV_TEMPERATURE_SLOWDOWN_TLIMIT = 194 +NVML_FI_DEV_TEMPERATURE_MEM_MAX_TLIMIT = 195 +NVML_FI_DEV_TEMPERATURE_GPU_MAX_TLIMIT = 196 + +NVML_FI_DEV_PCIE_COUNT_TX_BYTES = 197 +NVML_FI_DEV_PCIE_COUNT_RX_BYTES = 198 + +NVML_FI_DEV_IS_MIG_MODE_INDEPENDENT_MIG_QUERY_CAPABLE = 199 + +NVML_FI_DEV_NVLINK_GET_POWER_THRESHOLD_MAX = 200 + +NVML_FI_DEV_NVLINK_COUNT_XMIT_PACKETS = 201 +NVML_FI_DEV_NVLINK_COUNT_XMIT_BYTES = 202 +NVML_FI_DEV_NVLINK_COUNT_RCV_PACKETS = 203 +NVML_FI_DEV_NVLINK_COUNT_RCV_BYTES = 204 +NVML_FI_DEV_NVLINK_COUNT_VL15_DROPPED = 205 # Deprecated, do not use +NVML_FI_DEV_NVLINK_COUNT_MALFORMED_PACKET_ERRORS = 206 +NVML_FI_DEV_NVLINK_COUNT_BUFFER_OVERRUN_ERRORS = 207 +NVML_FI_DEV_NVLINK_COUNT_RCV_ERRORS = 208 +NVML_FI_DEV_NVLINK_COUNT_RCV_REMOTE_ERRORS = 209 +NVML_FI_DEV_NVLINK_COUNT_RCV_GENERAL_ERRORS = 210 +NVML_FI_DEV_NVLINK_COUNT_LOCAL_LINK_INTEGRITY_ERRORS = 211 +NVML_FI_DEV_NVLINK_COUNT_XMIT_DISCARDS = 212 + +NVML_FI_DEV_NVLINK_COUNT_LINK_RECOVERY_SUCCESSFUL_EVENTS = 213 +NVML_FI_DEV_NVLINK_COUNT_LINK_RECOVERY_FAILED_EVENTS = 214 +NVML_FI_DEV_NVLINK_COUNT_LINK_RECOVERY_EVENTS = 215 + +NVML_FI_DEV_NVLINK_COUNT_RAW_BER_LANE0 = 216 # Deprecated, do not use +NVML_FI_DEV_NVLINK_COUNT_RAW_BER_LANE1 = 217 # Deprecated, do not use +NVML_FI_DEV_NVLINK_COUNT_RAW_BER = 218 # Deprecated, do not use +NVML_FI_DEV_NVLINK_COUNT_EFFECTIVE_ERRORS = 219 +NVML_FI_DEV_NVLINK_COUNT_EFFECTIVE_BER = 220 +NVML_FI_DEV_NVLINK_COUNT_SYMBOL_ERRORS = 221 +NVML_FI_DEV_NVLINK_COUNT_SYMBOL_BER = 222 + +NVML_FI_DEV_NVLINK_GET_POWER_THRESHOLD_MIN = 223 +NVML_FI_DEV_NVLINK_GET_POWER_THRESHOLD_UNITS = 224 # Values are in the form NVML_NVLINK_LOW_POWER_THRESHOLD_UNIT_* +NVML_FI_DEV_NVLINK_GET_POWER_THRESHOLD_SUPPORTED = 225 + +NVML_FI_DEV_RESET_STATUS = 226 # Deprecated use NVML_FI_DEV_GET_GPU_RECOVERY_ACTION instead +NVML_FI_DEV_DRAIN_AND_RESET_STATUS = 227 # Deprecated use NVML_FI_DEV_GET_GPU_RECOVERY_ACTION instead +NVML_FI_DEV_PCIE_OUTBOUND_ATOMICS_MASK = 228 +NVML_FI_DEV_PCIE_INBOUND_ATOMICS_MASK = 229 +NVML_FI_DEV_GET_GPU_RECOVERY_ACTION = 230 + +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_0 = 235 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_1 = 236 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_2 = 237 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_3 = 238 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_4 = 239 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_5 = 240 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_6 = 241 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_7 = 242 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_8 = 243 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_9 = 244 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_10 = 245 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_11 = 246 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_12 = 247 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_13 = 248 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_14 = 249 +NVML_FI_DEV_NVLINK_COUNT_FEC_HISTORY_15 = 250 +NVML_FI_PWR_SMOOTHING_ENABLED = 251 # Enablement (0/DISABLED or 1/ENABLED) +NVML_FI_PWR_SMOOTHING_PRIV_LVL = 252 # Current privilege level +NVML_FI_PWR_SMOOTHING_IMM_RAMP_DOWN_ENABLED = 253 # Immediate ramp down enablement (0/DISABLED or 1/ENABLED) +NVML_FI_PWR_SMOOTHING_APPLIED_TMP_CEIL = 254 # Applied TMP ceiling value +NVML_FI_PWR_SMOOTHING_APPLIED_TMP_FLOOR = 255 # Applied TMP floor value +NVML_FI_PWR_SMOOTHING_MAX_PERCENT_TMP_FLOOR_SETTING = 256 # Max % TMP Floor value +NVML_FI_PWR_SMOOTHING_MIN_PERCENT_TMP_FLOOR_SETTING = 257 # Min % TMP Floor value +NVML_FI_PWR_SMOOTHING_HW_CIRCUITRY_PERCENT_LIFETIME_REMAINING = 258 # HW Circuitry % lifetime remaining +NVML_FI_PWR_SMOOTHING_MAX_NUM_PRESET_PROFILES = 259 # Max number of preset profiles +NVML_FI_PWR_SMOOTHING_PROFILE_PERCENT_TMP_FLOOR = 260 # % TMP floor for a given profile +NVML_FI_PWR_SMOOTHING_PROFILE_RAMP_UP_RATE = 261 # Ramp up rate in mW/s for a given profile +NVML_FI_PWR_SMOOTHING_PROFILE_RAMP_DOWN_RATE = 262 # Ramp down rate in mW/s for a given profile +NVML_FI_PWR_SMOOTHING_PROFILE_RAMP_DOWN_HYST_VAL = 263 # Ramp down hysteresis value in ms for a given profile +NVML_FI_PWR_SMOOTHING_ACTIVE_PRESET_PROFILE = 264 # Active preset profile number +NVML_FI_PWR_SMOOTHING_ADMIN_OVERRIDE_PERCENT_TMP_FLOOR = 265 # % TMP floor for a given profile +NVML_FI_PWR_SMOOTHING_ADMIN_OVERRIDE_RAMP_UP_RATE = 266 # Ramp up rate in mW/s for a given profile +NVML_FI_PWR_SMOOTHING_ADMIN_OVERRIDE_RAMP_DOWN_RATE = 267 # Ramp down rate in mW/s for a given profile +NVML_FI_PWR_SMOOTHING_ADMIN_OVERRIDE_RAMP_DOWN_HYST_VAL = 268 # Ramp down hysteresis value in ms for a given profile + +NVML_FI_MAX = 269 # One greater than the largest field ID defined above + +# NVML_FI_DEV_NVLINK_GET_STATE state enums +NVML_NVLINK_STATE_INACTIVE = 0x0 +NVML_NVLINK_STATE_ACTIVE = 0x1 +NVML_NVLINK_STATE_SLEEP = 0x2 + +NVML_NVLINK_LOW_POWER_THRESHOLD_UNIT_100US = 0 # NVML_FI_DEV_NVLINK_GET_POWER_THRESHOLD_UNITS +NVML_NVLINK_LOW_POWER_THRESHOLD_UNIT_50US = 1 # NVML_FI_DEV_NVLINK_GET_POWER_THRESHOLD_UNITS + +## Enums needed for the method nvmlDeviceGetVirtualizationMode and nvmlDeviceSetVirtualizationMode +NVML_GPU_VIRTUALIZATION_MODE_NONE = 0 # Represents Bare Metal GPU +NVML_GPU_VIRTUALIZATION_MODE_PASSTHROUGH = 1 # Device is associated with GPU-Passthorugh +NVML_GPU_VIRTUALIZATION_MODE_VGPU = 2 # Device is associated with vGPU inside virtual machine. +NVML_GPU_VIRTUALIZATION_MODE_HOST_VGPU = 3 # Device is associated with VGX hypervisor in vGPU mode +NVML_GPU_VIRTUALIZATION_MODE_HOST_VSGA = 4 # Device is associated with VGX hypervisor in vSGA mode + +## Lib loading ## +nvmlLib = None +libLoadLock = threading.Lock() +_nvmlLib_refcount = 0 # Incremented on each nvmlInit and decremented on nvmlShutdown + +## vGPU Management +_nvmlVgpuTypeId_t = c_uint +_nvmlVgpuInstance_t = c_uint + +_nvmlVgpuVmIdType_t = c_uint +NVML_VGPU_VM_ID_DOMAIN_ID = 0 +NVML_VGPU_VM_ID_UUID = 1 + +_nvmlGridLicenseFeatureCode_t = c_uint +NVML_GRID_LICENSE_FEATURE_CODE_UNKNOWN = 0 +NVML_GRID_LICENSE_FEATURE_CODE_VGPU = 1 +NVML_GRID_LICENSE_FEATURE_CODE_NVIDIA_RTX = 2 +NVML_GRID_LICENSE_FEATURE_CODE_VWORKSTATION = 2 # deprecated, use NVML_GRID_LICENSE_FEATURE_CODE_NVIDIA_RTX. +NVML_GRID_LICENSE_FEATURE_CODE_GAMING = 3 +NVML_GRID_LICENSE_FEATURE_CODE_COMPUTE = 4 + +_nvmlGridLicenseExpiryStatus_t = c_uint8 +NVML_GRID_LICENSE_EXPIRY_NOT_AVAILABLE = 0, # Expiry information not available +NVML_GRID_LICENSE_EXPIRY_INVALID = 1, # Invalid expiry or error fetching expiry +NVML_GRID_LICENSE_EXPIRY_VALID = 2, # Valid expiry +NVML_GRID_LICENSE_EXPIRY_NOT_APPLICABLE = 3, # Expiry not applicable +NVML_GRID_LICENSE_EXPIRY_PERMANENT = 4, # Permanent expiry + +_nvmlVgpuCapability_t = c_uint +NVML_VGPU_CAP_NVLINK_P2P = 0 # vGPU P2P over NVLink is supported +NVML_VGPU_CAP_GPUDIRECT = 1 # GPUDirect capability is supported +NVML_VGPU_CAP_MULTI_VGPU_EXCLUSIVE = 2 # vGPU profile cannot be mixed with other vGPU profiles in same VM +NVML_VGPU_CAP_EXCLUSIVE_TYPE = 3 # vGPU profile cannot run on a GPU alongside other profiles of different type +NVML_VGPU_CAP_EXCLUSIVE_SIZE = 4 # vGPU profile cannot run on a GPU alongside other profiles of different size +NVML_VGPU_CAP_COUNT = 5 + +_nvmlVgpuDriverCapability_t = c_uint +NVML_VGPU_DRIVER_CAP_HETEROGENEOUS_MULTI_VGPU = 0 # Supports mixing of different vGPU profiles within one guest VM +NVML_VGPU_DRIVER_CAP_WARM_UPDATE = 1 # Supports FSR and warm update of vGPU host driver without terminating the running guest VM +NVML_VGPU_DRIVER_CAP_COUNT = 2 + +_nvmlDeviceVgpuCapability_t = c_uint +NVML_DEVICE_VGPU_CAP_FRACTIONAL_MULTI_VGPU = 0 # Query whether the fractional vGPU profiles on this GPU can be used in multi-vGPU configurations +NVML_DEVICE_VGPU_CAP_HETEROGENEOUS_TIMESLICE_PROFILES = 1 # Query whether the GPU supports concurrent execution of timesliced vGPU profiles of differing types +NVML_DEVICE_VGPU_CAP_HETEROGENEOUS_TIMESLICE_SIZES = 2 # Query whether the GPU supports concurrent execution of timesliced vGPU profiles of differing framebuffer sizes +NVML_DEVICE_VGPU_CAP_READ_DEVICE_BUFFER_BW = 3 # Query the GPU's read_device_buffer expected bandwidth capacity in megabytes per second +NVML_DEVICE_VGPU_CAP_WRITE_DEVICE_BUFFER_BW = 4 # Query the GPU's write_device_buffer expected bandwidth capacity in megabytes per second +NVML_DEVICE_VGPU_CAP_DEVICE_STREAMING = 5 # Query whether the vGPU profiles on the GPU supports migration data streaming +NVML_DEVICE_VGPU_CAP_MINI_QUARTER_GPU = 6 # Set/Get support of mini-quarter vGPU profiles +NVML_DEVICE_VGPU_CAP_COMPUTE_MEDIA_ENGINE_GPU = 7 # Set/Get support for compute media engine vGPU profiles +NVML_DEVICE_VGPU_CAP_WARM_UPDATE = 8 # Query whether the GPU supports FSR and warm update +NVML_DEVICE_VGPU_CAP_HOMOGENEOUS_PLACEMENTS = 9 # Query whether the GPU supports reporting of placements of timesliced vGPU profiles with identical framebuffer sizes +NVML_DEVICE_VGPU_CAP_COUNT = 10 + +_nvmlVgpuGuestInfoState_t = c_uint +NVML_VGPU_INSTANCE_GUEST_INFO_STATE_UNINITIALIZED = 0 +NVML_VGPU_INSTANCE_GUEST_INFO_STATE_INITIALIZED = 1 + +_nvmlVgpuVmCompatibility_t = c_uint +NVML_VGPU_VM_COMPATIBILITY_NONE = 0x0 +NVML_VGPU_VM_COMPATIBILITY_COLD = 0x1 +NVML_VGPU_VM_COMPATIBILITY_HIBERNATE = 0x2 +NVML_VGPU_VM_COMPATIBILITY_SLEEP = 0x4 +NVML_VGPU_VM_COMPATIBILITY_LIVE = 0x8 + +_nvmlVgpuPgpuCompatibilityLimitCode_t = c_uint +NVML_VGPU_COMPATIBILITY_LIMIT_NONE = 0x0 +NVML_VGPU_COMPATIBILITY_LIMIT_HOST_DRIVER = 0x1 +NVML_VGPU_COMPATIBILITY_LIMIT_GUEST_DRIVER = 0x2 +NVML_VGPU_COMPATIBILITY_LIMIT_GPU = 0x4 +NVML_VGPU_COMPATIBILITY_LIMIT_OTHER = 0x80000000 + +_nvmlHostVgpuMode_t = c_uint +NVML_HOST_VGPU_MODE_NON_SRIOV = 0 +NVML_HOST_VGPU_MODE_SRIOV = 1 + +_nvmlConfComputeGpusReadyState_t = c_uint +NVML_CC_ACCEPTING_CLIENT_REQUESTS_FALSE = 0 +NVML_CC_ACCEPTING_CLIENT_REQUESTS_TRUE = 1 + +_nvmlConfComputeGpuCaps_t = c_uint +NVML_CC_SYSTEM_GPUS_CC_NOT_CAPABLE = 0 +NVML_CC_SYSTEM_GPUS_CC_CAPABLE = 1 + +_nvmlConfComputeCpuCaps_t = c_uint +NVML_CC_SYSTEM_CPU_CAPS_NONE = 0 +NVML_CC_SYSTEM_CPU_CAPS_AMD_SEV = 1 +NVML_CC_SYSTEM_CPU_CAPS_INTEL_TDX = 2 +NVML_CC_SYSTEM_CPU_CAPS_AMD_SEV_SNP = 3 +NVML_CC_SYSTEM_CPU_CAPS_AMD_SNP_VTOM = 4 + +_nvmlConfComputeDevToolsMode_t = c_uint +NVML_CC_SYSTEM_DEVTOOLS_MODE_OFF = 0 +NVML_CC_SYSTEM_DEVTOOLS_MODE_ON = 1 + +NVML_CC_SYSTEM_MULTIGPU_NONE = 0 +NVML_CC_SYSTEM_MULTIGPU_PROTECTED_PCIE = 1 + +NVML_CC_SYSTEM_ENVIRONMENT_UNAVAILABLE = 0 +NVML_CC_SYSTEM_ENVIRONMENT_SIM = 1 +NVML_CC_SYSTEM_ENVIRONMENT_PROD = 2 + +_nvmlConfComputeCcFeature_t = c_uint +NVML_CC_SYSTEM_FEATURE_DISABLED = 0 +NVML_CC_SYSTEM_FEATURE_ENABLED = 1 + +_nvmlConfComputeCcKeyRotationThreshAttackerAdv_t = c_uint +NVML_CC_KEY_ROTATION_THRESH_ATTACKER_ADVANTAGE_MIN = 50 +NVML_CC_KEY_ROTATION_THRESH_ATTACKER_ADVANTAGE_MAX = 65 + +# GSP firmware +NVML_GSP_FIRMWARE_VERSION_BUF_SIZE = 0x40 + +class NVMLLibraryMismatchError(Exception): + pass + +## Error Checking ## +class NVMLError(Exception): + _valClassMapping = dict() + # List of currently known error codes + _errcode_to_string = { + NVML_ERROR_UNINITIALIZED: "Uninitialized", + NVML_ERROR_INVALID_ARGUMENT: "Invalid Argument", + NVML_ERROR_NOT_SUPPORTED: "Not Supported", + NVML_ERROR_NO_PERMISSION: "Insufficient Permissions", + NVML_ERROR_ALREADY_INITIALIZED: "Already Initialized", + NVML_ERROR_NOT_FOUND: "Not Found", + NVML_ERROR_INSUFFICIENT_SIZE: "Insufficient Size", + NVML_ERROR_INSUFFICIENT_POWER: "Insufficient External Power", + NVML_ERROR_DRIVER_NOT_LOADED: "Driver Not Loaded", + NVML_ERROR_TIMEOUT: "Timeout", + NVML_ERROR_IRQ_ISSUE: "Interrupt Request Issue", + NVML_ERROR_LIBRARY_NOT_FOUND: "NVML Shared Library Not Found", + NVML_ERROR_FUNCTION_NOT_FOUND: "Function Not Found", + NVML_ERROR_CORRUPTED_INFOROM: "Corrupted infoROM", + NVML_ERROR_GPU_IS_LOST: "GPU is lost", + NVML_ERROR_RESET_REQUIRED: "GPU requires restart", + NVML_ERROR_OPERATING_SYSTEM: "The operating system has blocked the request.", + NVML_ERROR_LIB_RM_VERSION_MISMATCH: "RM has detected an NVML/RM version mismatch.", + NVML_ERROR_MEMORY: "Insufficient Memory", + NVML_ERROR_UNKNOWN: "Unknown Error", + } + def __new__(typ, value): + ''' + Maps value to a proper subclass of NVMLError. + See _extractNVMLErrorsAsClasses function for more details + ''' + if typ == NVMLError: + typ = NVMLError._valClassMapping.get(value, typ) + obj = Exception.__new__(typ) + obj.value = value + return obj + def __str__(self): + try: + if self.value not in NVMLError._errcode_to_string: + NVMLError._errcode_to_string[self.value] = str(nvmlErrorString(self.value)) + return NVMLError._errcode_to_string[self.value] + except NVMLError: + return "NVML Error with code %d" % self.value + def __eq__(self, other): + return self.value == other.value + +def nvmlExceptionClass(nvmlErrorCode): + if nvmlErrorCode not in NVMLError._valClassMapping: + raise ValueError('nvmlErrorCode %s is not valid' % nvmlErrorCode) + return NVMLError._valClassMapping[nvmlErrorCode] + +def _extractNVMLErrorsAsClasses(): + ''' + Generates a hierarchy of classes on top of NVMLError class. + + Each NVML Error gets a new NVMLError subclass. This way try,except blocks can filter appropriate + exceptions more easily. + + NVMLError is a parent class. Each NVML_ERROR_* gets it's own subclass. + e.g. NVML_ERROR_ALREADY_INITIALIZED will be turned into NVMLError_AlreadyInitialized + ''' + this_module = sys.modules[__name__] + nvmlErrorsNames = [x for x in dir(this_module) if x.startswith("NVML_ERROR_")] + for err_name in nvmlErrorsNames: + # e.g. Turn NVML_ERROR_ALREADY_INITIALIZED into NVMLError_AlreadyInitialized + class_name = "NVMLError_" + string.capwords(err_name.replace("NVML_ERROR_", ""), "_").replace("_", "") + err_val = getattr(this_module, err_name) + def gen_new(val): + def new(typ): + obj = NVMLError.__new__(typ, val) + return obj + return new + new_error_class = type(class_name, (NVMLError,), {'__new__': gen_new(err_val)}) + new_error_class.__module__ = __name__ + setattr(this_module, class_name, new_error_class) + NVMLError._valClassMapping[err_val] = new_error_class +_extractNVMLErrorsAsClasses() + +def _nvmlCheckReturn(ret): + if (ret != NVML_SUCCESS): + raise NVMLError(ret) + return ret + +## Function access ## +_nvmlGetFunctionPointer_cache = dict() # function pointers are cached to prevent unnecessary libLoadLock locking +def _nvmlGetFunctionPointer(name): + global nvmlLib + + if name in _nvmlGetFunctionPointer_cache: + return _nvmlGetFunctionPointer_cache[name] + + libLoadLock.acquire() + try: + # ensure library was loaded + if (nvmlLib == None): + raise NVMLError(NVML_ERROR_UNINITIALIZED) + try: + _nvmlGetFunctionPointer_cache[name] = getattr(nvmlLib, name) + return _nvmlGetFunctionPointer_cache[name] + except AttributeError: + raise NVMLError(NVML_ERROR_FUNCTION_NOT_FOUND) + finally: + # lock is always freed + libLoadLock.release() + +## Alternative object +# Allows the object to be printed +# Allows mismatched types to be assigned +# - like None when the Structure variant requires c_uint +class nvmlFriendlyObject(object): + def __init__(self, dictionary): + for x in dictionary: + setattr(self, x, dictionary[x]) + def __str__(self): + return self.__dict__.__str__() + +def nvmlStructToFriendlyObject(struct): + d = {} + for x in struct._fields_: + key = x[0] + value = getattr(struct, key) + # only need to convert from bytes if bytes, no need to check python version. + d[key] = value.decode() if isinstance(value, bytes) else value + obj = nvmlFriendlyObject(d) + return obj + +# pack the object so it can be passed to the NVML library +def nvmlFriendlyObjectToStruct(obj, model): + for x in model._fields_: + key = x[0] + value = obj.__dict__[key] + # any c_char_p in python3 needs to be bytes, default encoding works fine. + if sys.version_info >= (3,): + setattr(model, key, value.encode()) + else: + setattr(model, key, value) + return model + +## Unit structures +class struct_c_nvmlUnit_t(Structure): + pass # opaque handle +c_nvmlUnit_t = POINTER(struct_c_nvmlUnit_t) + +class _PrintableStructure(Structure): + """ + Abstract class that produces nicer __str__ output than ctypes.Structure. + e.g. instead of: + >>> print str(obj) + + this class will print + class_name(field_name: formatted_value, field_name: formatted_value) + + _fmt_ dictionary of -> + e.g. class that has _field_ 'hex_value', c_uint could be formatted with + _fmt_ = {"hex_value" : "%08X"} + to produce nicer output. + Default fomratting string for all fields can be set with key "" like: + _fmt_ = {"" : "%d MHz"} # e.g all values are numbers in MHz. + If not set it's assumed to be just "%s" + + Exact format of returned str from this class is subject to change in the future. + """ + _fmt_ = {} + def __str__(self): + result = [] + for x in self._fields_: + key = x[0] + value = getattr(self, key) + fmt = "%s" + if key in self._fmt_: + fmt = self._fmt_[key] + elif "" in self._fmt_: + fmt = self._fmt_[""] + result.append(("%s: " + fmt) % (key, value)) + return self.__class__.__name__ + "(" + ", ".join(result) + ")" + + def __getattribute__(self, name): + res = super(_PrintableStructure, self).__getattribute__(name) + # need to convert bytes to unicode for python3 don't need to for python2 + # Python 2 strings are of both str and bytes + # Python 3 strings are not of type bytes + # ctypes should convert everything to the correct values otherwise + if isinstance(res, bytes): + if isinstance(res, str): + return res + return res.decode() + return res + + def __setattr__(self, name, value): + if isinstance(value, str): + # encoding a python2 string returns the same value, since python2 strings are bytes already + # bytes passed in python3 will be ignored. + value = value.encode() + super(_PrintableStructure, self).__setattr__(name, value) + +class c_nvmlUnitInfo_t(_PrintableStructure): + _fields_ = [ + ('name', c_char * 96), + ('id', c_char * 96), + ('serial', c_char * 96), + ('firmwareVersion', c_char * 96), + ] + +class c_nvmlC2cModeInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('isC2cEnabled', c_uint) + ] + +nvmlC2cModeInfo_v1 = 0x1000008; + +class c_nvmlLedState_t(_PrintableStructure): + _fields_ = [ + ('cause', c_char * 256), + ('color', _nvmlLedColor_t), + ] + +class c_nvmlPSUInfo_t(_PrintableStructure): + _fields_ = [ + ('state', c_char * 256), + ('current', c_uint), + ('voltage', c_uint), + ('power', c_uint), + ] + +class c_nvmlUnitFanInfo_t(_PrintableStructure): + _fields_ = [ + ('speed', c_uint), + ('state', _nvmlFanState_t), + ] + +class c_nvmlUnitFanSpeeds_t(_PrintableStructure): + _fields_ = [ + ('fans', c_nvmlUnitFanInfo_t * 24), + ('count', c_uint) + ] + +## Device structures +class struct_c_nvmlDevice_t(Structure): + pass # opaque handle +c_nvmlDevice_t = POINTER(struct_c_nvmlDevice_t) + +class nvmlPciInfoExt_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('domain', c_uint), + ('bus', c_uint), + ('device', c_uint), + ('pciDeviceId', c_uint), + ('pciSubSystemId', c_uint), + ('baseClass', c_uint), + ('subClass', c_uint), + ('busId', c_char * NVML_DEVICE_PCI_BUS_ID_BUFFER_SIZE), + ] + _fmt_ = { + 'version' : "0x%04X", + 'domain' : "0x%04X", + 'bus' : "0x%02X", + 'device' : "0x%02X", + 'pciDeviceId' : "0x%08X", + 'pciSubSystemId' : "0x%08X", + 'baseClass' : "0x%01X", + 'subClass' : "0x%01X", + } + +nvmlPciInfoExt_v1 = 0x1000040 + +# Legacy pciInfo used for _v1 and _v2 +class nvmlPciInfo_v2_t(_PrintableStructure): + _fields_ = [ + ('busId', c_char * NVML_DEVICE_PCI_BUS_ID_BUFFER_V2_SIZE), + ('domain', c_uint), + ('bus', c_uint), + ('device', c_uint), + ('pciDeviceId', c_uint), + + # Added in 2.285 + ('pciSubSystemId', c_uint), + ('reserved0', c_uint), + ('reserved1', c_uint), + ('reserved2', c_uint), + ('reserved3', c_uint), + ] + _fmt_ = { + 'domain' : "0x%04X", + 'bus' : "0x%02X", + 'device' : "0x%02X", + 'pciDeviceId' : "0x%08X", + 'pciSubSystemId' : "0x%08X", + } + +class nvmlPciInfo_t(_PrintableStructure): + _fields_ = [ + # Moved to the new busId location below + ('busIdLegacy', c_char * NVML_DEVICE_PCI_BUS_ID_BUFFER_V2_SIZE), + ('domain', c_uint), + ('bus', c_uint), + ('device', c_uint), + ('pciDeviceId', c_uint), + + # Added in 2.285 + ('pciSubSystemId', c_uint), + # New busId replaced the long deprecated and reserved fields with a + # field of the same size in 9.0 + ('busId', c_char * NVML_DEVICE_PCI_BUS_ID_BUFFER_SIZE), + ] + _fmt_ = { + 'domain' : "0x%08X", + 'bus' : "0x%02X", + 'device' : "0x%02X", + 'pciDeviceId' : "0x%08X", + 'pciSubSystemId' : "0x%08X", + } + +class c_nvmlSystemDriverBranchInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ("branch", c_char * NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE), + ] + +SystemDriverBranchInfo_v1 = 0x1000054 + +class c_nvmlExcludedDeviceInfo_t(_PrintableStructure): + _fields_ = [ + ('pci', nvmlPciInfo_t), + ('uuid', c_char * NVML_DEVICE_UUID_BUFFER_SIZE) + ] + +class nvmlNvLinkUtilizationControl_t(_PrintableStructure): + _fields_ = [ + ('units', _nvmlNvLinkUtilizationCountUnits_t), + ('pktfilter', _nvmlNvLinkUtilizationCountPktTypes_t), + ] + +class c_nvmlMemory_t(_PrintableStructure): + _fields_ = [ + ('total', c_ulonglong), + ('free', c_ulonglong), + ('used', c_ulonglong), + ] + _fmt_ = {'': "%d B"} + +class c_nvmlMemory_v2_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('total', c_ulonglong), + ('reserved', c_ulonglong), + ('free', c_ulonglong), + ('used', c_ulonglong), + ] + _fmt_ = {'': "%d B"} + +nvmlMemory_v2 = 0x02000028 + +class c_nvmlBAR1Memory_t(_PrintableStructure): + _fields_ = [ + ('bar1Total', c_ulonglong), + ('bar1Free', c_ulonglong), + ('bar1Used', c_ulonglong), + ] + _fmt_ = {'': "%d B"} + +class nvmlClkMonFaultInfo_t(Structure): + _fields_ = [("clkApiDomain", c_uint), + ("clkDomainFaultMask", c_uint) + ] + +MAX_CLK_DOMAINS = 32 + +class nvmlClkMonStatus_t(Structure): + _fields_ = [("bGlobalStatus", c_uint), + ("clkMonListSize", c_uint), + ("clkMonList", nvmlClkMonFaultInfo_t * MAX_CLK_DOMAINS) + ] + +# On Windows with the WDDM driver, usedGpuMemory is reported as None +# Code that processes this structure should check for None, I.E. +# +# if (info.usedGpuMemory == None): +# # TODO handle the error +# pass +# else: +# print("Using %d MiB of memory" % (info.usedGpuMemory / 1024 / 1024)) +# endif +# +# See NVML documentation for more information +class c_nvmlProcessInfo_v2_t(_PrintableStructure): + _fields_ = [ + ('pid', c_uint), + ('usedGpuMemory', c_ulonglong), + ('gpuInstanceId', c_uint), + ('computeInstanceId', c_uint), + ] + _fmt_ = {'usedGpuMemory': "%d B"} + +c_nvmlProcessInfo_v3_t = c_nvmlProcessInfo_v2_t + +c_nvmlProcessInfo_t = c_nvmlProcessInfo_v3_t + +_nvmlProcessMode_t = c_uint +NVML_PROCESS_MODE_COMPUTE = 0 +NVML_PROCESS_MODE_GRAPHICS = 1 +NVML_PROCESS_MODE_MPS = 2 + +class c_nvmlProcessDetail_v1_t(Structure): + _fields_ = [ + ('pid', c_uint), + ('usedGpuMemory', c_ulonglong), + ('gpuInstanceId', c_uint), + ('computeInstanceId', c_uint), + ('usedGpuCcProtectedMemory', c_ulonglong), + ] + +class c_nvmlProcessDetailList_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('mode', _nvmlProcessMode_t), + ('numProcArrayEntries', c_uint), + ('procArray', POINTER(c_nvmlProcessDetail_v1_t)), + ] + _fmt_ = {'numProcArrayEntries': "%d B"} + +c_nvmlProcessDetailList_t = c_nvmlProcessDetailList_v1_t + +nvmlProcessDetailList_v1 = 0x1000018 + +class c_nvmlBridgeChipInfo_t(_PrintableStructure): + _fields_ = [ + ('type', _nvmlBridgeChipType_t), + ('fwVersion', c_uint), + ] + +class c_nvmlBridgeChipHierarchy_t(_PrintableStructure): + _fields_ = [ + ('bridgeCount', c_uint), + ('bridgeChipInfo', c_nvmlBridgeChipInfo_t * 128), + ] + +class c_nvmlEccErrorCounts_t(_PrintableStructure): + _fields_ = [ + ('l1Cache', c_ulonglong), + ('l2Cache', c_ulonglong), + ('deviceMemory', c_ulonglong), + ('registerFile', c_ulonglong), + ] + +class c_nvmlUtilization_t(_PrintableStructure): + _fields_ = [ + ('gpu', c_uint), + ('memory', c_uint), + ] + _fmt_ = {'': "%d %%"} + +# Added in 2.285 +class c_nvmlHwbcEntry_t(_PrintableStructure): + _fields_ = [ + ('hwbcId', c_uint), + ('firmwareVersion', c_char * 32), + ] + +class c_nvmlValue_t(Union): + _fields_ = [ + ('dVal', c_double), + ('uiVal', c_uint), + ('ulVal', c_ulong), + ('ullVal', c_ulonglong), + ('sllVal', c_longlong), + ('siVal', c_int), + ('usVal', c_ushort), + ] + +class c_nvmlSample_t(_PrintableStructure): + _fields_ = [ + ('timeStamp', c_ulonglong), + ('sampleValue', c_nvmlValue_t), + ] + +class c_nvmlViolationTime_t(_PrintableStructure): + _fields_ = [ + ('referenceTime', c_ulonglong), + ('violationTime', c_ulonglong), + ] + +class c_nvmlFieldValue_t(_PrintableStructure): + _fields_ = [ + ('fieldId', c_uint32), + ('scopeId', c_uint32), + ('timestamp', c_int64), + ('latencyUsec', c_int64), + ('valueType', _nvmlValueType_t), + ('nvmlReturn', _nvmlReturn_t), + ('value', c_nvmlValue_t) + ] + +NVML_NVLINK_TOTAL_SUPPORTED_BW_MODES = 23 + +nvmlNvlinkSupportedBwModes_v1 = 0x100001c +class c_nvmlNvlinkSupportedBwModes_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('bwModes', c_uint8 * NVML_NVLINK_TOTAL_SUPPORTED_BW_MODES), + ('totalBwModes', c_uint8) + ] + + def __init__(self): + super(c_nvmlNvlinkSupportedBwModes_v1_t, self).__init__(version=nvmlNvlinkSupportedBwModes_v1) + +nvmlNvlinkGetBwMode_v1 = 0x100000c +class c_nvmlNvlinkGetBwMode_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('bIsBest', c_uint), + ('bwMode', c_uint8) + ] + + def __init__(self): + super(c_nvmlNvlinkGetBwMode_v1_t, self).__init__(version=nvmlNvlinkGetBwMode_v1) + +nvmlNvlinkSetBwMode_v1 = 0x100000c +class c_nvmlNvlinkSetBwMode_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('bSetBest', c_uint), + ('bwMode', c_uint8) + ] + + def __init__(self): + super(c_nvmlNvlinkSetBwMode_v1_t, self).__init__(version=nvmlNvlinkSetBwMode_v1) + +class c_nvmlVgpuHeterogeneousMode_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('mode', c_uint), + ] + +VgpuHeterogeneousMode_v1 = 0x1000008 + +class c_nvmlVgpuPlacementId_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('placementId', c_uint), + ] + +VgpuPlacementId_v1 = 0x1000008 + +class c_nvmlVgpuPlacementList_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('count', c_uint), + ('placementSize', c_uint), + ('placementIds', POINTER(c_uint)), + ] + +VgpuPlacementList_v1 = 0x1000018 + +NVML_VGPU_PGPU_HETEROGENEOUS_MODE = 0 +NVML_VGPU_PGPU_HOMOGENEOUS_MODE = 1 + +class c_nvmlVgpuPlacementList_v2_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('placementSize', c_uint), + ('count', c_uint), + ('placementIds', POINTER(c_uint)), + ('mode', c_uint), + ] + +VgpuPlacementList_v2 = 0x2000020 + +class c_nvmlVgpuTypeBar1Info_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('bar1Size', c_ulonglong), + ] + +VgpuTypeBar1Info_v1 = 0x1000010 + +class c_nvmlVgpuInstanceUtilizationSample_t(_PrintableStructure): + _fields_ = [ + ('vgpuInstance', _nvmlVgpuInstance_t), + ('timeStamp', c_ulonglong), + ('smUtil', c_nvmlValue_t), + ('memUtil', c_nvmlValue_t), + ('encUtil', c_nvmlValue_t), + ('decUtil', c_nvmlValue_t), + ] + +class c_nvmlVgpuInstanceUtilizationInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('timeStamp', c_ulonglong), + ('vgpuInstance', _nvmlVgpuInstance_t), + ('smUtil', c_nvmlValue_t), + ('memUtil', c_nvmlValue_t), + ('encUtil', c_nvmlValue_t), + ('decUtil', c_nvmlValue_t), + ('jpgUtil', c_nvmlValue_t), + ('ofaUtil', c_nvmlValue_t), + ] + +class c_nvmlVgpuInstancesUtilizationInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('sampleValType', _nvmlValueType_t), + ('vgpuInstanceCount', c_uint), + ('lastSeenTimeStamp', c_ulonglong), + ('vgpuUtilArray', POINTER(c_nvmlVgpuInstanceUtilizationInfo_v1_t)), + ] + +VgpuInstancesUtilizationInfo_v1 = 0x01000020 + +class c_nvmlVgpuProcessUtilizationSample_t(_PrintableStructure): + _fields_ = [ + ('vgpuInstance', _nvmlVgpuInstance_t), + ('pid', c_uint), + ('processName', c_char * NVML_VGPU_NAME_BUFFER_SIZE), + ('timeStamp', c_ulonglong), + ('smUtil', c_uint), + ('memUtil', c_uint), + ('encUtil', c_uint), + ('decUtil', c_uint), + ] + +class c_nvmlVgpuProcessUtilizationInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('processName', c_char * NVML_VGPU_NAME_BUFFER_SIZE), + ('timeStamp', c_ulonglong), + ('vgpuInstance', _nvmlVgpuInstance_t), + ('pid', c_uint), + ('smUtil', c_uint), + ('memUtil', c_uint), + ('encUtil', c_uint), + ('decUtil', c_uint), + ('jpgUtil', c_uint), + ('ofaUtil', c_uint), + ] + +class c_nvmlVgpuProcessesUtilizationInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('vgpuProcessCount', c_uint), + ('lastSeenTimeStamp', c_ulonglong), + ('vgpuProcUtilArray', POINTER(c_nvmlVgpuProcessUtilizationInfo_v1_t)), + ] + +VgpuProcessesUtilizationInfo_v1 = 0x01000018 + +class nvmlVgpuRuntimeState_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('size', c_ulonglong), + ] + +VgpuRuntimeState_v1 = 0x1000010 + +class c_nvmlVgpuLicenseExpiry_t(_PrintableStructure): + _fields_ = [ + ('year', c_uint32), + ('month', c_uint16), + ('day', c_uint16), + ('hour', c_uint16), + ('min', c_uint16), + ('sec', c_uint16), + ('status', c_uint8), + ] + +NVML_GRID_LICENSE_STATE_UNKNOWN = 0 +NVML_GRID_LICENSE_STATE_UNINITIALIZED = 1 +NVML_GRID_LICENSE_STATE_UNLICENSED_UNRESTRICTED = 2 +NVML_GRID_LICENSE_STATE_UNLICENSED_RESTRICTED = 3 +NVML_GRID_LICENSE_STATE_UNLICENSED = 4 +NVML_GRID_LICENSE_STATE_LICENSED = 5 + +class c_nvmlVgpuLicenseInfo_t(_PrintableStructure): + _fields_ = [ + ('isLicensed', c_uint8), + ('licenseExpiry', c_nvmlVgpuLicenseExpiry_t), + ('currentState', c_uint), + ] + +class c_nvmlEncoderSession_t(_PrintableStructure): + _fields_ = [ + ('sessionId', c_uint), + ('pid', c_uint), + ('vgpuInstance', _nvmlVgpuInstance_t), + ('codecType', c_uint), + ('hResolution', c_uint), + ('vResolution', c_uint), + ('averageFps', c_uint), + ('encodeLatency', c_uint), + ] + +class c_nvmlProcessUtilizationSample_t(_PrintableStructure): + _fields_ = [ + ('pid', c_uint), + ('timeStamp', c_ulonglong), + ('smUtil', c_uint), + ('memUtil', c_uint), + ('encUtil', c_uint), + ('decUtil', c_uint), + ] + +class c_nvmlProcessUtilizationInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('timeStamp', c_ulonglong), + ('pid', c_uint), + ('smUtil', c_uint), + ('memUtil', c_uint), + ('encUtil', c_uint), + ('decUtil', c_uint), + ('jpgUtil', c_uint), + ('ofaUtil', c_uint), + ] + +class c_nvmlProcessesUtilizationInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('processSamplesCount', c_uint), + ('lastSeenTimeStamp', c_ulonglong), + ('procUtilArray', POINTER(c_nvmlProcessUtilizationInfo_v1_t)), + ] + +ProcessesUtilizationInfo_v1 = 0x01000018 + +class c_nvmlGridLicenseExpiry_t(_PrintableStructure): + _fields_ = [ + ('year', c_uint32), + ('month', c_uint16), + ('day', c_uint16), + ('hour', c_uint16), + ('min', c_uint16), + ('sec', c_uint16), + ('status', c_uint8), + ] + +class c_nvmlGridLicensableFeature_v4_t(_PrintableStructure): + _fields_ = [ + ('featureCode', _nvmlGridLicenseFeatureCode_t), + ('featureState', c_uint), + ('licenseInfo', c_char * NVML_GRID_LICENSE_BUFFER_SIZE), + ('productName', c_char * NVML_GRID_LICENSE_BUFFER_SIZE), + ('featureEnabled', c_uint), + ('licenseExpiry', c_nvmlGridLicenseExpiry_t), + ] + +class c_nvmlGridLicensableFeatures_v4_t(_PrintableStructure): + _fields_ = [ + ('isGridLicenseSupported', c_int), + ('licensableFeaturesCount', c_uint), + ('gridLicensableFeatures', c_nvmlGridLicensableFeature_v4_t * NVML_GRID_LICENSE_FEATURE_MAX_COUNT), + ] + +class c_nvmlGridLicensableFeature_v3_t(_PrintableStructure): + _fields_ = [ + ('featureCode', _nvmlGridLicenseFeatureCode_t), + ('featureState', c_uint), + ('licenseInfo', c_char * NVML_GRID_LICENSE_BUFFER_SIZE), + ('productName', c_char * NVML_GRID_LICENSE_BUFFER_SIZE), + ('featureEnabled', c_uint), + ] + +class c_nvmlGridLicensableFeatures_v3_t(_PrintableStructure): + _fields_ = [ + ('isGridLicenseSupported', c_int), + ('licensableFeaturesCount', c_uint), + ('gridLicensableFeatures', c_nvmlGridLicensableFeature_v3_t * NVML_GRID_LICENSE_FEATURE_MAX_COUNT), + ] + +class c_nvmlGridLicensableFeature_v2_t(_PrintableStructure): + _fields_ = [ + ('featureCode', _nvmlGridLicenseFeatureCode_t), + ('featureState', c_uint), + ('licenseInfo', c_char * NVML_GRID_LICENSE_BUFFER_SIZE), + ('productName', c_char * NVML_GRID_LICENSE_BUFFER_SIZE), + ] + +class c_nvmlGridLicensableFeatures_v2_t(_PrintableStructure): + _fields_ = [ + ('isGridLicenseSupported', c_int), + ('licensableFeaturesCount', c_uint), + ('gridLicensableFeatures', c_nvmlGridLicensableFeature_v2_t * NVML_GRID_LICENSE_FEATURE_MAX_COUNT), + ] + +class c_nvmlGridLicensableFeature_t(_PrintableStructure): + _fields_ = [ + ('featureCode', _nvmlGridLicenseFeatureCode_t), + ('featureState', c_uint), + ('licenseInfo', c_char * NVML_GRID_LICENSE_BUFFER_SIZE), + ] + +class c_nvmlGridLicensableFeatures_t(_PrintableStructure): + _fields_ = [ + ('isGridLicenseSupported', c_int), + ('licensableFeaturesCount', c_uint), + ('gridLicensableFeatures', c_nvmlGridLicensableFeature_t * NVML_GRID_LICENSE_FEATURE_MAX_COUNT), + ] + +class c_nvmlMarginTemperature_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('marginTemperature', c_int), + ] + +nvmlMarginTemperature_v1 = 0x1000008 + +## Event structures +class struct_c_nvmlEventSet_t(Structure): + pass # opaque handle +c_nvmlEventSet_t = POINTER(struct_c_nvmlEventSet_t) + +nvmlEventTypeSingleBitEccError = 0x0000000000000001 +nvmlEventTypeDoubleBitEccError = 0x0000000000000002 +nvmlEventTypePState = 0x0000000000000004 +nvmlEventTypeXidCriticalError = 0x0000000000000008 +nvmlEventTypeClock = 0x0000000000000010 +nvmlEventTypePowerSourceChange = 0x0000000000000080 +nvmlEventMigConfigChange = 0x0000000000000100 +nvmlEventTypeSingleBitEccErrorStorm = 0x0000000000000200 +nvmlEventTypeDramRetirementEvent = 0x0000000000000400 +nvmlEventTypeDramRetirementFailure = 0x0000000000000800 +nvmlEventTypeNonFatalPoisonError = 0x0000000000001000 +nvmlEventTypeFatalPoisonError = 0x0000000000002000 +nvmlEventTypeGpuUnavailableError = 0x0000000000004000 +nvmlEventTypeGpuRecoveryAction = 0x0000000000008000 +nvmlEventTypeNone = 0x0000000000000000 +nvmlEventTypeAll = ( + nvmlEventTypeNone + | nvmlEventTypeSingleBitEccError + | nvmlEventTypeDoubleBitEccError + | nvmlEventTypePState + | nvmlEventTypeClock + | nvmlEventTypePowerSourceChange + | nvmlEventTypeXidCriticalError + | nvmlEventMigConfigChange + | nvmlEventTypeSingleBitEccErrorStorm + | nvmlEventTypeDramRetirementEvent + | nvmlEventTypeDramRetirementFailure + | nvmlEventTypeNonFatalPoisonError + | nvmlEventTypeFatalPoisonError + | nvmlEventTypeGpuUnavailableError + | nvmlEventTypeGpuRecoveryAction + ) + +## Clock Event Reasons defines +nvmlClocksEventReasonGpuIdle = 0x0000000000000001 +nvmlClocksEventReasonApplicationsClocksSetting = 0x0000000000000002 +nvmlClocksEventReasonUserDefinedClocks = nvmlClocksEventReasonApplicationsClocksSetting # deprecated, use nvmlClocksEventReasonApplicationsClocksSetting +nvmlClocksEventReasonSwPowerCap = 0x0000000000000004 +nvmlClocksEventReasonHwSlowdown = 0x0000000000000008 +nvmlClocksEventReasonSyncBoost = 0x0000000000000010 +nvmlClocksEventReasonSwThermalSlowdown = 0x0000000000000020 +nvmlClocksEventReasonHwThermalSlowdown = 0x0000000000000040 +nvmlClocksEventReasonHwPowerBrakeSlowdown = 0x0000000000000080 +nvmlClocksEventReasonDisplayClockSetting = 0x0000000000000100 +nvmlClocksEventReasonNone = 0x0000000000000000 +nvmlClocksEventReasonAll = ( + nvmlClocksEventReasonNone | + nvmlClocksEventReasonGpuIdle | + nvmlClocksEventReasonApplicationsClocksSetting | + nvmlClocksEventReasonSwPowerCap | + nvmlClocksEventReasonHwSlowdown | + nvmlClocksEventReasonSyncBoost | + nvmlClocksEventReasonSwThermalSlowdown | + nvmlClocksEventReasonHwThermalSlowdown | + nvmlClocksEventReasonHwPowerBrakeSlowdown | + nvmlClocksEventReasonDisplayClockSetting + ) + +## Following have been deprecated +nvmlClocksThrottleReasonGpuIdle = 0x0000000000000001 +nvmlClocksThrottleReasonApplicationsClocksSetting = 0x0000000000000002 +nvmlClocksThrottleReasonUserDefinedClocks = nvmlClocksThrottleReasonApplicationsClocksSetting # deprecated, use nvmlClocksThrottleReasonApplicationsClocksSetting +nvmlClocksThrottleReasonSwPowerCap = 0x0000000000000004 +nvmlClocksThrottleReasonHwSlowdown = 0x0000000000000008 +nvmlClocksThrottleReasonSyncBoost = 0x0000000000000010 +nvmlClocksThrottleReasonSwThermalSlowdown = 0x0000000000000020 +nvmlClocksThrottleReasonHwThermalSlowdown = 0x0000000000000040 +nvmlClocksThrottleReasonHwPowerBrakeSlowdown = 0x0000000000000080 +nvmlClocksThrottleReasonDisplayClockSetting = 0x0000000000000100 +nvmlClocksThrottleReasonNone = 0x0000000000000000 +nvmlClocksThrottleReasonAll = ( + nvmlClocksThrottleReasonNone | + nvmlClocksThrottleReasonGpuIdle | + nvmlClocksThrottleReasonApplicationsClocksSetting | + nvmlClocksThrottleReasonSwPowerCap | + nvmlClocksThrottleReasonHwSlowdown | + nvmlClocksThrottleReasonSyncBoost | + nvmlClocksThrottleReasonSwThermalSlowdown | + nvmlClocksThrottleReasonHwThermalSlowdown | + nvmlClocksThrottleReasonHwPowerBrakeSlowdown | + nvmlClocksThrottleReasonDisplayClockSetting + ) + +class c_nvmlEventData_t(_PrintableStructure): + _fields_ = [ + ('device', c_nvmlDevice_t), + ('eventType', c_ulonglong), + ('eventData', c_ulonglong), + ('gpuInstanceId', c_uint), + ('computeInstanceId', c_uint) + ] + _fmt_ = {'eventType': "0x%08X"} + +class c_nvmlAccountingStats_t(_PrintableStructure): + _fields_ = [ + ('gpuUtilization', c_uint), + ('memoryUtilization', c_uint), + ('maxMemoryUsage', c_ulonglong), + ('time', c_ulonglong), + ('startTime', c_ulonglong), + ('isRunning', c_uint), + ('reserved', c_uint * 5) + ] + +class c_nvmlVgpuVersion_t(Structure): + _fields_ = [("minVersion", c_uint), + ("maxVersion", c_uint) + ] + +class c_nvmlVgpuMetadata_t(_PrintableStructure): + _fields_ = [("version", c_uint), + ("revision", c_uint), + ("guestInfoState", _nvmlVgpuGuestInfoState_t), + ("guestDriverVersion", c_char * NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE), + ("hostDriverVersion", c_char * NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE), + ("reserved", c_uint * 6), + ("vgpuVirtualizationCaps", c_uint), + ("guestVgpuVersion", c_uint), + ("opaqueDataSize", c_uint), + ("opaqueData", c_char * NVML_VGPU_METADATA_OPAQUE_DATA_SIZE) + ] + +class c_nvmlVgpuPgpuMetadata_t(_PrintableStructure): + _fields_ = [("version", c_uint), + ("revision", c_uint), + ("hostDriverVersion", c_char * NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE), + ("pgpuVirtualizationCaps", c_uint), + ("reserved", c_uint * 5), + ("hostSupportedVgpuRange", c_nvmlVgpuVersion_t), + ("opaqueDataSize", c_uint), + ("opaqueData", c_char * NVML_VGPU_PGPU_METADATA_OPAQUE_DATA_SIZE) + ] + +class c_nvmlVgpuPgpuCompatibility_t(Structure): + _fields_ = [("vgpuVmCompatibility", _nvmlVgpuVmCompatibility_t), + ("compatibilityLimitCode", _nvmlVgpuPgpuCompatibilityLimitCode_t) + ] + +## vGPU scheduler policy defines +NVML_VGPU_SCHEDULER_POLICY_UNKNOWN = 0 +NVML_VGPU_SCHEDULER_POLICY_BEST_EFFORT = 1 +NVML_VGPU_SCHEDULER_POLICY_EQUAL_SHARE = 2 +NVML_VGPU_SCHEDULER_POLICY_FIXED_SHARE = 3 + +## Supported vGPU scheduler policy count +NVML_SUPPORTED_VGPU_SCHEDULER_POLICY_COUNT = 3 + +NVML_SCHEDULER_SW_MAX_LOG_ENTRIES = 200 + +NVML_VGPU_SCHEDULER_ARR_DEFAULT = 0 +NVML_VGPU_SCHEDULER_ARR_DISABLE = 1 +NVML_VGPU_SCHEDULER_ARR_ENABLE = 2 + +class c_nvmlVgpuSchedDataWithARR_t(_PrintableStructure): + _fields_ = [ + ('avgFactor', c_uint), + ('timeslice', c_uint), + ] + +class c_nvmlVgpuSchedData_t(_PrintableStructure): + _fields_ = [ + ('timeslice', c_uint), + ] + +class c_nvmlVgpuSchedulerParams_t(Union): + _fields_ = [ + ('vgpuSchedDataWithARR', c_nvmlVgpuSchedDataWithARR_t), + ('vgpuSchedData', c_nvmlVgpuSchedData_t), + ] + +class c_nvmlVgpuSchedulerLogEntry_t(_PrintableStructure): + _fields_ = [ + ('timestamp', c_ulonglong), + ('timeRunTotal', c_ulonglong), + ('timeRun', c_ulonglong), + ('swRunlistId', c_uint), + ('targetTimeSlice', c_ulonglong), + ('cumulativePreemptionTime', c_ulonglong), + ] + +class c_nvmlVgpuSchedulerLog_t(_PrintableStructure): + _fields_ = [ + ('engineId', c_uint), + ('schedulerPolicy', c_uint), + ('arrMode', c_uint), + ('schedulerParams', c_nvmlVgpuSchedulerParams_t), + ('entriesCount', c_uint), + ('logEntries', c_nvmlVgpuSchedulerLogEntry_t * NVML_SCHEDULER_SW_MAX_LOG_ENTRIES), + ] + +class c_nvmlVgpuSchedulerGetState_t(_PrintableStructure): + _fields_ = [ + ('schedulerPolicy', c_uint), + ('arrMode', c_uint), + ('schedulerParams', c_nvmlVgpuSchedulerParams_t), + ] + +class c_nvmlVgpuSchedSetDataWithARR_t(_PrintableStructure): + _fields_ = [ + ('avgFactor', c_uint), + ('frequency', c_uint), + ] + +class c_nvmlVgpuSchedSetData_t(_PrintableStructure): + _fields_ = [ + ('timeslice', c_uint), + ] + +class c_nvmlVgpuSchedulerSetParams_t(Union): + _fields_ = [ + ('vgpuSchedDataWithARR', c_nvmlVgpuSchedSetDataWithARR_t), + ('vgpuSchedData', c_nvmlVgpuSchedSetData_t), + ] + +class c_nvmlVgpuSchedulerSetState_t(_PrintableStructure): + _fields_ = [ + ('schedulerPolicy', c_uint), + ('enableARRMode', c_uint), + ('schedulerParams', c_nvmlVgpuSchedulerSetParams_t), + ] + +class c_nvmlVgpuSchedulerCapabilities_t(_PrintableStructure): + _fields_ = [ + ('supportedSchedulers', c_uint * NVML_SUPPORTED_VGPU_SCHEDULER_POLICY_COUNT), + ('maxTimeslice', c_uint), + ('minTimeslice', c_uint), + ('isArrModeSupported', c_uint), + ('maxFrequencyForARR', c_uint), + ('minFrequencyForARR', c_uint), + ('maxAvgFactorForARR', c_uint), + ('minAvgFactorForARR', c_uint), + ] + +class c_nvmlFBCStats_t(Structure): + _fields_ = [("sessionsCount", c_uint), + ("averageFPS", c_uint), + ("averageLatency", c_uint) + ] + +class c_nvmlFBCSession_t(_PrintableStructure): + _fields_ = [ + ('sessionId', c_uint), + ('pid', c_uint), + ('vgpuInstance', _nvmlVgpuInstance_t), + ('displayOrdinal', c_uint), + ('sessionType', c_uint), + ('sessionFlags', c_uint), + ('hMaxResolution', c_uint), + ('vMaxResolution', c_uint), + ('hResolution', c_uint), + ('vResolution', c_uint), + ('averageFPS', c_uint), + ('averageLatency', c_uint), + ] + +NVML_DEVICE_MIG_DISABLE = 0x0 +NVML_DEVICE_MIG_ENABLE = 0x1 + +NVML_GPU_INSTANCE_PROFILE_1_SLICE = 0x0 +NVML_GPU_INSTANCE_PROFILE_2_SLICE = 0x1 +NVML_GPU_INSTANCE_PROFILE_3_SLICE = 0x2 +NVML_GPU_INSTANCE_PROFILE_4_SLICE = 0x3 +NVML_GPU_INSTANCE_PROFILE_7_SLICE = 0x4 +NVML_GPU_INSTANCE_PROFILE_8_SLICE = 0x5 +NVML_GPU_INSTANCE_PROFILE_6_SLICE = 0x6 +NVML_GPU_INSTANCE_PROFILE_1_SLICE_REV1 = 0x7 +NVML_GPU_INSTANCE_PROFILE_2_SLICE_REV1 = 0x8 +NVML_GPU_INSTANCE_PROFILE_1_SLICE_REV2 = 0x9 +NVML_GPU_INSTANCE_PROFILE_1_SLICE_GFX = 0xA +NVML_GPU_INSTANCE_PROFILE_2_SLICE_GFX = 0xB +NVML_GPU_INSTANCE_PROFILE_4_SLICE_GFX = 0xC +NVML_GPU_INSTANCE_PROFILE_COUNT = 0xD + +class c_nvmlGpuInstancePlacement_t(Structure): + _fields_ = [("start", c_uint), + ("size", c_uint) + ] + +class c_nvmlGpuInstanceProfileInfo_t(Structure): + _fields_ = [("id", c_uint), + ("isP2pSupported", c_uint), + ("sliceCount", c_uint), + ("instanceCount", c_uint), + ("multiprocessorCount", c_uint), + ("copyEngineCount", c_uint), + ("decoderCount", c_uint), + ("encoderCount", c_uint), + ("jpegCount", c_uint), + ("ofaCount", c_uint), + ("memorySizeMB", c_ulonglong), + ] + +nvmlGpuInstanceProfileInfo_v2 = 0x02000098 + +class c_nvmlGpuInstanceProfileInfo_v2_t(_PrintableStructure): + _fields_ = [("version", c_uint), + ("id", c_uint), + ("isP2pSupported", c_uint), + ("sliceCount", c_uint), + ("instanceCount", c_uint), + ("multiprocessorCount", c_uint), + ("copyEngineCount", c_uint), + ("decoderCount", c_uint), + ("encoderCount", c_uint), + ("jpegCount", c_uint), + ("ofaCount", c_uint), + ("memorySizeMB", c_ulonglong), + ("name", c_char * NVML_DEVICE_NAME_V2_BUFFER_SIZE) + ] + + def __init__(self): + super(c_nvmlGpuInstanceProfileInfo_v2_t, self).__init__(version=nvmlGpuInstanceProfileInfo_v2) + +class c_nvmlGpuInstanceInfo_t(Structure): + _fields_ = [("device", c_nvmlDevice_t), + ("id", c_uint), + ("profileId", c_uint), + ("placement", c_nvmlGpuInstancePlacement_t) + ] + +class struct_c_nvmlGpuInstance_t(Structure): + pass # opaque handle +c_nvmlGpuInstance_t = POINTER(struct_c_nvmlGpuInstance_t) + +NVML_COMPUTE_INSTANCE_PROFILE_1_SLICE = 0x0 +NVML_COMPUTE_INSTANCE_PROFILE_2_SLICE = 0x1 +NVML_COMPUTE_INSTANCE_PROFILE_3_SLICE = 0x2 +NVML_COMPUTE_INSTANCE_PROFILE_4_SLICE = 0x3 +NVML_COMPUTE_INSTANCE_PROFILE_7_SLICE = 0x4 +NVML_COMPUTE_INSTANCE_PROFILE_8_SLICE = 0x5 +NVML_COMPUTE_INSTANCE_PROFILE_6_SLICE = 0x6 +NVML_COMPUTE_INSTANCE_PROFILE_1_SLICE_REV1 = 0x7 +NVML_COMPUTE_INSTANCE_PROFILE_COUNT = 0x8 + +NVML_COMPUTE_INSTANCE_ENGINE_PROFILE_SHARED = 0x0 +NVML_COMPUTE_INSTANCE_ENGINE_PROFILE_COUNT = 0x1 + +class c_nvmlComputeInstancePlacement_t(Structure): + _fields_ = [("start", c_uint), + ("size", c_uint) + ] + +class c_nvmlComputeInstanceProfileInfo_t(Structure): + _fields_ = [("id", c_uint), + ("sliceCount", c_uint), + ("instanceCount", c_uint), + ("multiprocessorCount", c_uint), + ("sharedCopyEngineCount", c_uint), + ("sharedDecoderCount", c_uint), + ("sharedEncoderCount", c_uint), + ("sharedJpegCount", c_uint), + ("sharedOfaCount", c_uint) + ] + +nvmlComputeInstanceProfileInfo_v2 = 0x02000088 + +class c_nvmlComputeInstanceProfileInfo_v2_t(_PrintableStructure): + _fields_ = [("version", c_uint), + ("id", c_uint), + ("sliceCount", c_uint), + ("instanceCount", c_uint), + ("multiprocessorCount", c_uint), + ("sharedCopyEngineCount", c_uint), + ("sharedDecoderCount", c_uint), + ("sharedEncoderCount", c_uint), + ("sharedJpegCount", c_uint), + ("sharedOfaCount", c_uint), + ("name", c_char * NVML_DEVICE_NAME_V2_BUFFER_SIZE) + ] + + def __init__(self): + super(c_nvmlComputeInstanceProfileInfo_v2_t, self).__init__(version=nvmlComputeInstanceProfileInfo_v2) + +class c_nvmlComputeInstanceInfo_t(Structure): + _fields_ = [("device", c_nvmlDevice_t), + ("gpuInstance", c_nvmlGpuInstance_t), + ("id", c_uint), + ("profileId", c_uint), + ("placement", c_nvmlComputeInstancePlacement_t) + ] + +NVML_MAX_GPU_UTILIZATIONS = 8 +NVML_GPU_UTILIZATION_DOMAIN_GPU = 0 +NVML_GPU_UTILIZATION_DOMAIN_FB = 1 +NVML_GPU_UTILIZATION_DOMAIN_VID = 2 +NVML_GPU_UTILIZATION_DOMAIN_BUS = 3 +class c_nvmlGpuDynamicPstatesUtilization_t(Structure): + _fields_ = [("bIsPresent", c_uint, 1), + ("percentage", c_uint), + ("incThreshold", c_uint), + ("decThreshold", c_uint)] +class c_nvmlGpuDynamicPstatesInfo_t(Structure): + _fields_ = [("flags", c_uint), + ("utilization", c_nvmlGpuDynamicPstatesUtilization_t * NVML_MAX_GPU_UTILIZATIONS)] + +NVML_MAX_THERMAL_SENSORS_PER_GPU = 3 + +NVML_THERMAL_TARGET_NONE = 0 +NVML_THERMAL_TARGET_GPU = 1 +NVML_THERMAL_TARGET_MEMORY = 2 +NVML_THERMAL_TARGET_POWER_SUPPLY = 4 +NVML_THERMAL_TARGET_BOARD = 8 +NVML_THERMAL_TARGET_VCD_BOARD = 9 +NVML_THERMAL_TARGET_VCD_INLET = 10 +NVML_THERMAL_TARGET_VCD_OUTLET = 11 +NVML_THERMAL_TARGET_ALL = 15 +NVML_THERMAL_TARGET_UNKNOWN = -1 + +NVML_THERMAL_CONTROLLER_NONE = 0 +NVML_THERMAL_CONTROLLER_GPU_INTERNAL = 1 +NVML_THERMAL_CONTROLLER_ADM1032 = 2 +NVML_THERMAL_CONTROLLER_ADT7461 = 3 +NVML_THERMAL_CONTROLLER_MAX6649 = 4 +NVML_THERMAL_CONTROLLER_MAX1617 = 5 +NVML_THERMAL_CONTROLLER_LM99 = 6 +NVML_THERMAL_CONTROLLER_LM89 = 7 +NVML_THERMAL_CONTROLLER_LM64 = 8 +NVML_THERMAL_CONTROLLER_G781 = 9 +NVML_THERMAL_CONTROLLER_ADT7473 = 10 +NVML_THERMAL_CONTROLLER_SBMAX6649 = 11 +NVML_THERMAL_CONTROLLER_VBIOSEVT = 12 +NVML_THERMAL_CONTROLLER_OS = 13 +NVML_THERMAL_CONTROLLER_NVSYSCON_CANOAS = 14 +NVML_THERMAL_CONTROLLER_NVSYSCON_E551 = 15 +NVML_THERMAL_CONTROLLER_MAX6649R = 16 +NVML_THERMAL_CONTROLLER_ADT7473S = 17 +NVML_THERMAL_CONTROLLER_UNKNOWN = -1 + +class c_nvmlGpuThermalSensor_t(Structure): + _fields_ = [("controller", c_int), + ("defaultMinTemp", c_int), + ("defaultMaxTemp", c_int), + ("currentTemp", c_int), + ("target", c_int)] +class c_nvmlGpuThermalSettings_t(Structure): + _fields_ = [("count", c_uint), + ("sensor", c_nvmlGpuThermalSensor_t * NVML_MAX_THERMAL_SENSORS_PER_GPU)] + +_nvmlCoolerControl_t = c_uint +NVML_THERMAL_COOLER_SIGNAL_NONE = 0 +NVML_THERMAL_COOLER_SIGNAL_TOGGLE = 1 +NVML_THERMAL_COOLER_SIGNAL_VARIABLE = 2 +NVML_THERMAL_COOLER_SIGNAL_COUNT = 3 + +_nvmlCoolerTarget_t = c_uint +NVML_THERMAL_COOLER_TARGET_NONE = (1 << 0) +NVML_THERMAL_COOLER_TARGET_GPU = (1 << 1) +NVML_THERMAL_COOLER_TARGET_MEMORY = (1 << 2) +NVML_THERMAL_COOLER_TARGET_POWER_SUPPLY = (1 << 3) +NVML_THERMAL_COOLER_TARGET_GPU_RELATED = (NVML_THERMAL_COOLER_TARGET_GPU | NVML_THERMAL_COOLER_TARGET_MEMORY | NVML_THERMAL_COOLER_TARGET_POWER_SUPPLY) + +class c_nvmlCoolerInfo_t(_PrintableStructure): + _fields_ = [("version", c_uint), + ("index", c_uint), + ("coolerControlType", _nvmlCoolerControl_t), + ("coolerTarget", _nvmlCoolerTarget_t) + ] + +nvmlCoolerInfo_v1 = 0x1000010 + +def nvmlDeviceGetCoolerInfo(handle): + c_coolerInfo = c_nvmlCoolerInfo_t() + c_coolerInfo.version = nvmlCoolerInfo_v1 + c_coolerInfo.index = 0 + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCoolerInfo") + ret = fn(handle, byref(c_coolerInfo)) + _nvmlCheckReturn(ret) + return [c_coolerInfo.coolerControlType, c_coolerInfo.coolerTarget] + +class struct_c_nvmlComputeInstance_t(Structure): + pass # opaque handle +c_nvmlComputeInstance_t = POINTER(struct_c_nvmlComputeInstance_t) + +class c_nvmlDeviceAttributes(Structure): + _fields_ = [("multiprocessorCount", c_uint), + ("sharedCopyEngineCount", c_uint), + ("sharedDecoderCount", c_uint), + ("sharedEncoderCount", c_uint), + ("sharedJpegCount", c_uint), + ("sharedOfaCount", c_uint), + ("gpuInstanceSliceCount", c_uint), + ("computeInstanceSliceCount", c_uint), + ("memorySizeMB", c_ulonglong), + ] + +class c_nvmlRowRemapperHistogramValues(Structure): + _fields_ = [("max", c_uint), + ("high", c_uint), + ("partial", c_uint), + ("low", c_uint), + ("none", c_uint) + ] + +NVML_GPU_CERT_CHAIN_SIZE = 0x1000 +NVML_GPU_ATTESTATION_CERT_CHAIN_SIZE = 0x1400 +NVML_CC_GPU_CEC_NONCE_SIZE = 0x20 +NVML_CC_GPU_ATTESTATION_REPORT_SIZE = 0x2000 +NVML_CC_GPU_CEC_ATTESTATION_REPORT_SIZE = 0x1000 +NVML_CC_CEC_ATTESTATION_REPORT_NOT_PRESENT = 0 +NVML_CC_CEC_ATTESTATION_REPORT_PRESENT = 1 + +class c_nvmlConfComputeSystemState_t(Structure): + _fields_ = [('environment', c_uint), + ('ccFeature', c_uint), + ('devToolsMode', c_uint), + ] + +nvmlSystemConfComputeSettings_v1 = 0x1000014 + +class c_nvmlSystemConfComputeSettings_v1_t(Structure): + _fields_ = [('version', c_uint), + ('environment', c_uint), + ('ccFeature', c_uint), + ('devToolsMode', c_uint), + ('multiGpuMode', c_uint), + ] + def __init__(self): + super(c_nvmlSystemConfComputeSettings_v1_t, self).__init__(version=nvmlSystemConfComputeSettings_v1) + +class c_nvmlConfComputeSystemCaps_t(Structure): + _fields_ = [('cpuCaps', c_uint), + ('gpusCaps', c_uint), + ] + +class c_nvmlConfComputeMemSizeInfo_t(Structure): + _fields_ = [('protectedMemSizeKib', c_ulonglong), + ('unprotectedMemSizeKib', c_ulonglong), + ] + +class c_nvmlConfComputeGpuCertificate_t(Structure): + _fields_ = [('certChainSize', c_uint), + ('attestationCertChainSize', c_uint), + ('certChain', c_uint8 * NVML_GPU_CERT_CHAIN_SIZE), + ('attestationCertChain', c_uint8 * NVML_GPU_ATTESTATION_CERT_CHAIN_SIZE), + ] + +class c_nvmlConfComputeGpuAttestationReport_t(Structure): + _fields_ = [('isCecAttestationReportPresent', c_uint), + ('attestationReportSize', c_uint), + ('cecAttestationReportSize', c_uint), + ('nonce', c_uint8 * NVML_CC_GPU_CEC_NONCE_SIZE), + ('attestationReport', c_uint8 * NVML_CC_GPU_ATTESTATION_REPORT_SIZE), + ('cecAttestationReport', c_uint8 * NVML_CC_GPU_CEC_ATTESTATION_REPORT_SIZE), + ] + +class c_nvmlConfComputeSetKeyRotationThresholdInfo_t(Structure): + _fields_ = [('version', c_uint), + ('maxAttackerAdvantage', c_ulong), + ] +ConfComputeSetKeyRotationThresholdInfo_v1 = 0x1000010 + +class c_nvmlConfComputeGetKeyRotationThresholdInfo_t(Structure): + _fields_ = [('version', c_uint), + ('attackerAdvantage', c_ulong), + ] +ConfComputeGetKeyRotationThresholdInfo_v1 = 0x1000010 + + +## string/bytes conversion for ease of use +def convertStrBytes(func): + ''' + In python 3, strings are unicode instead of bytes, and need to be converted for ctypes + Args from caller: (1, 'string', <__main__.c_nvmlDevice_t at 0xFFFFFFFF>) + Args passed to function: (1, b'string', <__main__.c_nvmlDevice_t at 0xFFFFFFFF)> + ---- + Returned from function: b'returned string' + Returned to caller: 'returned string' + ''' + @wraps(func) + def wrapper(*args, **kwargs): + # encoding a str returns bytes in python 2 and 3 + args = [arg.encode() if isinstance(arg, str) else arg for arg in args] + res = func(*args, **kwargs) + # In python 2, str and bytes are the same + # In python 3, str is unicode and should be decoded. + # Ctypes handles most conversions, this only effects c_char and char arrays. + if isinstance(res, bytes): + if isinstance(res, str): + return res + return res.decode() + return res + + if sys.version_info >= (3,): + return wrapper + return func + +def throwOnVersionMismatch(func): + @wraps(func) + def wrapper(*args, **kwargs): + try: + return func(*args, **kwargs) + except NVMLError_FunctionNotFound: + raise NVMLLibraryMismatchError("Unversioned function called and the " + "pyNVML version does not match the NVML lib version. " + "Either use matching pyNVML and NVML lib versions or " + "use a versioned function such as " + func.__name__ + "_v2") + return wrapper + +## C function wrappers ## +def nvmlInitWithFlags(flags): + _LoadNvmlLibrary() + + # + # Initialize the library + # + fn = _nvmlGetFunctionPointer("nvmlInitWithFlags") + ret = fn(flags) + _nvmlCheckReturn(ret) + + # Atomically update refcount + global _nvmlLib_refcount + libLoadLock.acquire() + _nvmlLib_refcount += 1 + libLoadLock.release() + return None + +def nvmlInit(): + nvmlInitWithFlags(0) + return None + +def _LoadNvmlLibrary(): + ''' + Load the library if it isn't loaded already + ''' + global nvmlLib + + if (nvmlLib == None): + # lock to ensure only one caller loads the library + libLoadLock.acquire() + + try: + # ensure the library still isn't loaded + if (nvmlLib == None): + try: + if (sys.platform[:3] == "win"): + # cdecl calling convention + try: + # Check for nvml.dll in System32 first for DCH drivers + nvmlLib = CDLL(os.path.join(os.getenv("WINDIR", "C:/Windows"), "System32/nvml.dll")) + except OSError as ose: + # If nvml.dll is not found in System32, it should be in ProgramFiles + # load nvml.dll from %ProgramFiles%/NVIDIA Corporation/NVSMI/nvml.dll + nvmlLib = CDLL(os.path.join(os.getenv("ProgramFiles", "C:/Program Files"), "NVIDIA Corporation/NVSMI/nvml.dll")) + else: + # assume linux + nvmlLib = CDLL("libnvidia-ml.so.1") + except OSError as ose: + _nvmlCheckReturn(NVML_ERROR_LIBRARY_NOT_FOUND) + if (nvmlLib == None): + _nvmlCheckReturn(NVML_ERROR_LIBRARY_NOT_FOUND) + finally: + # lock is always freed + libLoadLock.release() + +def nvmlShutdown(): + # + # Leave the library loaded, but shutdown the interface + # + fn = _nvmlGetFunctionPointer("nvmlShutdown") + ret = fn() + _nvmlCheckReturn(ret) + + # Atomically update refcount + global _nvmlLib_refcount + libLoadLock.acquire() + if (0 < _nvmlLib_refcount): + _nvmlLib_refcount -= 1 + libLoadLock.release() + return None + +# Added in 2.285 +@convertStrBytes +def nvmlErrorString(result): + fn = _nvmlGetFunctionPointer("nvmlErrorString") + fn.restype = c_char_p # otherwise return is an int + ret = fn(result) + return ret + +# Added in 2.285 +@convertStrBytes +def nvmlSystemGetNVMLVersion(): + c_version = create_string_buffer(NVML_SYSTEM_NVML_VERSION_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlSystemGetNVMLVersion") + ret = fn(c_version, c_uint(NVML_SYSTEM_NVML_VERSION_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_version.value + +def nvmlSystemGetCudaDriverVersion(): + c_cuda_version = c_int() + fn = _nvmlGetFunctionPointer("nvmlSystemGetCudaDriverVersion") + ret = fn(byref(c_cuda_version)) + _nvmlCheckReturn(ret) + return c_cuda_version.value + +def nvmlSystemGetCudaDriverVersion_v2(): + c_cuda_version = c_int() + fn = _nvmlGetFunctionPointer("nvmlSystemGetCudaDriverVersion_v2") + ret = fn(byref(c_cuda_version)) + _nvmlCheckReturn(ret) + return c_cuda_version.value + +# Added in 2.285 +@convertStrBytes +def nvmlSystemGetProcessName(pid): + c_name = create_string_buffer(1024) + fn = _nvmlGetFunctionPointer("nvmlSystemGetProcessName") + ret = fn(c_uint(pid), c_name, c_uint(1024)) + _nvmlCheckReturn(ret) + return c_name.value + +@convertStrBytes +def nvmlSystemGetDriverVersion(): + c_version = create_string_buffer(NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlSystemGetDriverVersion") + ret = fn(c_version, c_uint(NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_version.value + +# Added in 2.285 +def nvmlSystemGetHicVersion(): + c_count = c_uint(0) + hics = None + fn = _nvmlGetFunctionPointer("nvmlSystemGetHicVersion") + + # get the count + ret = fn(byref(c_count), None) + + # this should only fail with insufficient size + if ((ret != NVML_SUCCESS) and + (ret != NVML_ERROR_INSUFFICIENT_SIZE)): + raise NVMLError(ret) + + # If there are no hics + if (c_count.value == 0): + return [] + + hic_array = c_nvmlHwbcEntry_t * c_count.value + hics = hic_array() + ret = fn(byref(c_count), hics) + _nvmlCheckReturn(ret) + return hics + +def nvmlSystemGetDriverBranch(): + c_branchInfo = c_nvmlSystemDriverBranchInfo_v1_t(0) + c_branchInfo.version = SystemDriverBranchInfo_v1 + fn = _nvmlGetFunctionPointer("nvmlSystemGetDriverBranch") + ret = fn(byref(c_branchInfo), c_uint(NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_branchInfo + +## Unit get functions +def nvmlUnitGetCount(): + c_count = c_uint() + fn = _nvmlGetFunctionPointer("nvmlUnitGetCount") + ret = fn(byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlUnitGetHandleByIndex(index): + c_index = c_uint(index) + unit = c_nvmlUnit_t() + fn = _nvmlGetFunctionPointer("nvmlUnitGetHandleByIndex") + ret = fn(c_index, byref(unit)) + _nvmlCheckReturn(ret) + return unit + +def nvmlUnitGetUnitInfo(unit): + c_info = c_nvmlUnitInfo_t() + fn = _nvmlGetFunctionPointer("nvmlUnitGetUnitInfo") + ret = fn(unit, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +def nvmlUnitGetLedState(unit): + c_state = c_nvmlLedState_t() + fn = _nvmlGetFunctionPointer("nvmlUnitGetLedState") + ret = fn(unit, byref(c_state)) + _nvmlCheckReturn(ret) + return c_state + +def nvmlUnitGetPsuInfo(unit): + c_info = c_nvmlPSUInfo_t() + fn = _nvmlGetFunctionPointer("nvmlUnitGetPsuInfo") + ret = fn(unit, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +def nvmlUnitGetTemperature(unit, type): + c_temp = c_uint() + fn = _nvmlGetFunctionPointer("nvmlUnitGetTemperature") + ret = fn(unit, c_uint(type), byref(c_temp)) + _nvmlCheckReturn(ret) + return c_temp.value + +def nvmlUnitGetFanSpeedInfo(unit): + c_speeds = c_nvmlUnitFanSpeeds_t() + fn = _nvmlGetFunctionPointer("nvmlUnitGetFanSpeedInfo") + ret = fn(unit, byref(c_speeds)) + _nvmlCheckReturn(ret) + return c_speeds + +# added to API +def nvmlUnitGetDeviceCount(unit): + c_count = c_uint(0) + # query the unit to determine device count + fn = _nvmlGetFunctionPointer("nvmlUnitGetDevices") + ret = fn(unit, byref(c_count), None) + if (ret == NVML_ERROR_INSUFFICIENT_SIZE): + ret = NVML_SUCCESS + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlUnitGetDevices(unit): + c_count = c_uint(nvmlUnitGetDeviceCount(unit)) + device_array = c_nvmlDevice_t * c_count.value + c_devices = device_array() + fn = _nvmlGetFunctionPointer("nvmlUnitGetDevices") + ret = fn(unit, byref(c_count), c_devices) + _nvmlCheckReturn(ret) + return c_devices + +## Device get functions +def nvmlDeviceGetCount(): + c_count = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCount_v2") + ret = fn(byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlDeviceGetHandleByIndex(index): + c_index = c_uint(index) + device = c_nvmlDevice_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetHandleByIndex_v2") + ret = fn(c_index, byref(device)) + _nvmlCheckReturn(ret) + return device + +@convertStrBytes +def nvmlDeviceGetHandleBySerial(serial): + c_serial = c_char_p(serial) + device = c_nvmlDevice_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetHandleBySerial") + ret = fn(c_serial, byref(device)) + _nvmlCheckReturn(ret) + return device + +@convertStrBytes +def nvmlDeviceGetHandleByUUID(uuid): + c_uuid = c_char_p(uuid) + device = c_nvmlDevice_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetHandleByUUID") + ret = fn(c_uuid, byref(device)) + _nvmlCheckReturn(ret) + return device + +@convertStrBytes +def nvmlDeviceGetHandleByPciBusId(pciBusId): + c_busId = c_char_p(pciBusId) + device = c_nvmlDevice_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetHandleByPciBusId_v2") + ret = fn(c_busId, byref(device)) + _nvmlCheckReturn(ret) + return device + +@convertStrBytes +def nvmlDeviceGetName(handle): + c_name = create_string_buffer(NVML_DEVICE_NAME_V2_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetName") + ret = fn(handle, c_name, c_uint(NVML_DEVICE_NAME_V2_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_name.value + +class c_nvmlDevicePerfModes_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('str', c_char * NVML_PERF_MODES_BUFFER_SIZE), + ] + +nvmlDevicePerfModes_v1 = 0x1000804 + +@convertStrBytes +def nvmlDeviceGetPerformanceModes(handle): + perfModes = c_nvmlDevicePerfModes_v1_t() + perfModes.version = nvmlDevicePerfModes_v1 + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPerformanceModes") + ret = fn(handle, byref(perfModes)) + _nvmlCheckReturn(ret) + return perfModes.str + +class c_nvmlDeviceCurrentClockFreqs_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('str', c_char * NVML_PERF_MODES_BUFFER_SIZE), + ] + +nvmlDeviceCurrentClockFreqs_v1 = 0x1000804 + +@convertStrBytes +def nvmlDeviceGetCurrentClockFreqs(handle): + currentClockFreqs = c_nvmlDeviceCurrentClockFreqs_v1_t() + currentClockFreqs.version = nvmlDeviceCurrentClockFreqs_v1 + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCurrentClockFreqs") + ret = fn(handle, byref(currentClockFreqs)) + _nvmlCheckReturn(ret) + return currentClockFreqs.str + +def nvmlDeviceGetBoardId(handle): + c_id = c_uint(); + fn = _nvmlGetFunctionPointer("nvmlDeviceGetBoardId") + ret = fn(handle, byref(c_id)) + _nvmlCheckReturn(ret) + return c_id.value + +def nvmlDeviceGetMultiGpuBoard(handle): + c_multiGpu = c_uint(); + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMultiGpuBoard") + ret = fn(handle, byref(c_multiGpu)) + _nvmlCheckReturn(ret) + return c_multiGpu.value + +def nvmlDeviceGetBrand(handle): + c_type = _nvmlBrandType_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetBrand") + ret = fn(handle, byref(c_type)) + _nvmlCheckReturn(ret) + return c_type.value + +def nvmlDeviceGetC2cModeInfoV1(handle): + c_info = c_nvmlC2cModeInfo_v1_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetC2cModeInfoV") + ret = fn(handle, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +def nvmlDeviceGetC2cModeInfoV(handle): + return nvmlDeviceGetC2cModeInfoV1(handle) + +@convertStrBytes +def nvmlDeviceGetBoardPartNumber(handle): + c_part_number = create_string_buffer(NVML_DEVICE_PART_NUMBER_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetBoardPartNumber") + ret = fn(handle, c_part_number, c_uint(NVML_DEVICE_PART_NUMBER_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_part_number.value + +@convertStrBytes +def nvmlDeviceGetSerial(handle): + c_serial = create_string_buffer(NVML_DEVICE_SERIAL_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSerial") + ret = fn(handle, c_serial, c_uint(NVML_DEVICE_SERIAL_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_serial.value + +def nvmlDeviceGetModuleId(handle, moduleId=c_uint()): + isReference = type(moduleId) is not c_uint + moduleIdRef = moduleId if isReference else byref(moduleId) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetModuleId") + ret = fn(handle, moduleIdRef) + if isReference: + return ret + else: + _nvmlCheckReturn(ret) + return moduleId.value + +def nvmlDeviceGetMemoryAffinity(handle, nodeSetSize, scope): + affinity_array = c_ulonglong * nodeSetSize + c_affinity = affinity_array() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMemoryAffinity") + ret = fn(handle, nodeSetSize, byref(c_affinity), _nvmlAffinityScope_t(scope)) + _nvmlCheckReturn(ret) + return c_affinity + +def nvmlDeviceGetCpuAffinityWithinScope(handle, cpuSetSize, scope): + affinity_array = c_ulonglong * cpuSetSize + c_affinity = affinity_array() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCpuAffinityWithinScope") + ret = fn(handle, cpuSetSize, byref(c_affinity), _nvmlAffinityScope_t(scope)) + _nvmlCheckReturn(ret) + return c_affinity + +def nvmlDeviceGetCpuAffinity(handle, cpuSetSize): + affinity_array = c_ulonglong * cpuSetSize + c_affinity = affinity_array() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCpuAffinity") + ret = fn(handle, cpuSetSize, byref(c_affinity)) + _nvmlCheckReturn(ret) + return c_affinity + +def nvmlDeviceSetCpuAffinity(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetCpuAffinity") + ret = fn(handle) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceClearCpuAffinity(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceClearCpuAffinity") + ret = fn(handle) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetNumaNodeId(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNumaNodeId") + node = c_int() + ret = fn(handle, byref(node)) + _nvmlCheckReturn(ret) + return node.value + +def nvmlDeviceGetMinorNumber(handle): + c_minor_number = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMinorNumber") + ret = fn(handle, byref(c_minor_number)) + _nvmlCheckReturn(ret) + return c_minor_number.value + +@convertStrBytes +def nvmlDeviceGetUUID(handle): + c_uuid = create_string_buffer(NVML_DEVICE_UUID_V2_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetUUID") + ret = fn(handle, c_uuid, c_uint(NVML_DEVICE_UUID_V2_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_uuid.value + +@convertStrBytes +def nvmlDeviceGetInforomVersion(handle, infoRomObject): + c_version = create_string_buffer(NVML_DEVICE_INFOROM_VERSION_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetInforomVersion") + ret = fn(handle, _nvmlInforomObject_t(infoRomObject), + c_version, c_uint(NVML_DEVICE_INFOROM_VERSION_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_version.value + +# Added in 4.304 +@convertStrBytes +def nvmlDeviceGetInforomImageVersion(handle): + c_version = create_string_buffer(NVML_DEVICE_INFOROM_VERSION_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetInforomImageVersion") + ret = fn(handle, c_version, c_uint(NVML_DEVICE_INFOROM_VERSION_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_version.value + +# Added in 4.304 +def nvmlDeviceGetInforomConfigurationChecksum(handle): + c_checksum = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetInforomConfigurationChecksum") + ret = fn(handle, byref(c_checksum)) + _nvmlCheckReturn(ret) + return c_checksum.value + +# Added in 4.304 +def nvmlDeviceValidateInforom(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceValidateInforom") + ret = fn(handle) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetLastBBXFlushTime(handle): + c_timestamp = c_ulonglong() + c_durationUs = c_ulong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetLastBBXFlushTime") + ret = fn(handle, byref(c_timestamp), byref(c_durationUs)) + _nvmlCheckReturn(ret) + return [c_timestamp.value, c_durationUs.value] + +def nvmlDeviceGetDisplayMode(handle): + c_mode = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDisplayMode") + ret = fn(handle, byref(c_mode)) + _nvmlCheckReturn(ret) + return c_mode.value + +def nvmlDeviceGetDisplayActive(handle): + c_mode = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDisplayActive") + ret = fn(handle, byref(c_mode)) + _nvmlCheckReturn(ret) + return c_mode.value + + +def nvmlDeviceGetPersistenceMode(handle): + c_state = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPersistenceMode") + ret = fn(handle, byref(c_state)) + _nvmlCheckReturn(ret) + return c_state.value + +def nvmlDeviceGetPciInfoExt(handle, c_info): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPciInfoExt") + ret = fn(handle, c_info) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetPciInfo_v3(handle): + c_info = nvmlPciInfo_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPciInfo_v3") + ret = fn(handle, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +def nvmlDeviceGetPciInfo(handle): + return nvmlDeviceGetPciInfo_v3(handle) + +def nvmlDeviceGetClockInfo(handle, type): + c_clock = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetClockInfo") + ret = fn(handle, _nvmlClockType_t(type), byref(c_clock)) + _nvmlCheckReturn(ret) + return c_clock.value + +# Added in 2.285 +def nvmlDeviceGetMaxClockInfo(handle, type): + c_clock = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMaxClockInfo") + ret = fn(handle, _nvmlClockType_t(type), byref(c_clock)) + _nvmlCheckReturn(ret) + return c_clock.value + +# Added in 4.304 +def nvmlDeviceGetApplicationsClock(handle, type): + c_clock = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetApplicationsClock") + ret = fn(handle, _nvmlClockType_t(type), byref(c_clock)) + _nvmlCheckReturn(ret) + return c_clock.value + +def nvmlDeviceGetMaxCustomerBoostClock(handle, type): + c_clock = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMaxCustomerBoostClock") + ret = fn(handle, _nvmlClockType_t(type), byref(c_clock)) + _nvmlCheckReturn(ret) + return c_clock.value + +def nvmlDeviceGetClock(handle, type, id): + c_clock = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetClock") + ret = fn(handle, _nvmlClockType_t(type), _nvmlClockId_t(id), byref(c_clock)) + _nvmlCheckReturn(ret) + return c_clock.value + +# Added in 5.319 +def nvmlDeviceGetDefaultApplicationsClock(handle, type): + c_clock = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDefaultApplicationsClock") + ret = fn(handle, _nvmlClockType_t(type), byref(c_clock)) + _nvmlCheckReturn(ret) + return c_clock.value + +# Added in 4.304 +def nvmlDeviceGetSupportedMemoryClocks(handle): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSupportedMemoryClocks") + ret = fn(handle, byref(c_count), None) + + if (ret == NVML_SUCCESS): + # special case, no clocks + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + clocks_array = c_uint * c_count.value + c_clocks = clocks_array() + + # make the call again + ret = fn(handle, byref(c_count), c_clocks) + _nvmlCheckReturn(ret) + + procs = [] + for i in range(c_count.value): + procs.append(c_clocks[i]) + + return procs + else: + # error case + raise NVMLError(ret) + +# Added in 4.304 +def nvmlDeviceGetSupportedGraphicsClocks(handle, memoryClockMHz): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSupportedGraphicsClocks") + ret = fn(handle, c_uint(memoryClockMHz), byref(c_count), None) + + if (ret == NVML_SUCCESS): + # special case, no clocks + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + clocks_array = c_uint * c_count.value + c_clocks = clocks_array() + + # make the call again + ret = fn(handle, c_uint(memoryClockMHz), byref(c_count), c_clocks) + _nvmlCheckReturn(ret) + + procs = [] + for i in range(c_count.value): + procs.append(c_clocks[i]) + + return procs + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetFanSpeed(handle): + c_speed = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetFanSpeed") + ret = fn(handle, byref(c_speed)) + _nvmlCheckReturn(ret) + return c_speed.value + +def nvmlDeviceGetFanSpeed_v2(handle, fan): + c_speed = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetFanSpeed_v2") + ret = fn(handle, fan, byref(c_speed)) + _nvmlCheckReturn(ret) + return c_speed.value + +class c_nvmlFanSpeedInfo_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('fan', c_uint), + ('speed', c_uint), + ] + +nvmlFanSpeedInfo_v1 = 0x100000C + +def nvmlDeviceGetFanSpeedRPM(handle): + c_fanSpeed = c_nvmlFanSpeedInfo_t() + c_fanSpeed.fan = 0 + c_fanSpeed.version = nvmlFanSpeedInfo_v1 + fn = _nvmlGetFunctionPointer("nvmlDeviceGetFanSpeedRPM") + ret = fn(handle, byref(c_fanSpeed)) + _nvmlCheckReturn(ret) + return c_fanSpeed.speed + +def nvmlDeviceGetTargetFanSpeed(handle, fan): + c_speed = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTargetFanSpeed") + ret = fn(handle, fan, byref(c_speed)) + _nvmlCheckReturn(ret) + return c_speed.value + +def nvmlDeviceGetNumFans(device): + c_numFans = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNumFans") + ret = fn(device, byref(c_numFans)) + _nvmlCheckReturn(ret) + return c_numFans.value + +def nvmlDeviceSetDefaultFanSpeed_v2(handle, index): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetDefaultFanSpeed_v2"); + ret = fn(handle, index) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetMinMaxFanSpeed(handle, minSpeed=c_uint(), maxSpeed=c_uint()): + isReference = (type(minSpeed) is not c_uint) or (type(maxSpeed) is not c_uint) + minSpeedRef = minSpeed if isReference else byref(minSpeed) + maxSpeedRef = maxSpeed if isReference else byref(maxSpeed) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMinMaxFanSpeed") + ret = fn(handle, minSpeedRef, maxSpeedRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else [minSpeed.value, maxSpeed.value] + +def nvmlDeviceGetFanControlPolicy_v2(handle, fan, fanControlPolicy=c_uint()): + isReference = type(fanControlPolicy) is not c_uint + fanControlPolicyRef = fanControlPolicy if isReference else byref(fanControlPolicy) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetFanControlPolicy_v2") + ret = fn(handle, fan, fanControlPolicyRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else fanControlPolicy.value + +def nvmlDeviceSetFanControlPolicy(handle, fan, fanControlPolicy): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetFanControlPolicy") + ret = fn(handle, fan, _nvmlFanControlPolicy_t(fanControlPolicy)) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +class c_nvmlTemperature_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('sensorType', _nvmlTemperatureSensors_t), + ('temperature', c_int), + ] +nvmlTemperature_v1 = 0x100000C + +def nvmlDeviceGetTemperatureV1(handle, sensor): + c_temp = c_nvmlTemperature_v1_t() + c_temp.version = nvmlTemperature_v1 + c_temp.sensorType = _nvmlTemperatureSensors_t(sensor) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTemperatureV") + ret = fn(handle, byref(c_temp)) + _nvmlCheckReturn(ret) + return c_temp.temperature + +def nvmlDeviceGetTemperatureV(handle, sensor, version=nvmlTemperature_v1): + if version == nvmlTemperature_v1: + return nvmlDeviceGetTemperatureV1(handle, sensor) + else: + raise NVMLError(NVML_ERROR_ARGUMENT_VERSION_MISMATCH) + +# DEPRECATED use nvmlDeviceGetTemperatureV instead +def nvmlDeviceGetTemperature(handle, sensor): + c_temp = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTemperature") + ret = fn(handle, _nvmlTemperatureSensors_t(sensor), byref(c_temp)) + _nvmlCheckReturn(ret) + return c_temp.value + +def nvmlDeviceGetTemperatureThreshold(handle, threshold): + c_temp = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTemperatureThreshold") + ret = fn(handle, _nvmlTemperatureThresholds_t(threshold), byref(c_temp)) + _nvmlCheckReturn(ret) + return c_temp.value + +def nvmlDeviceSetTemperatureThreshold(handle, threshold, temp): + c_temp = c_uint() + c_temp.value = temp + fn = _nvmlGetFunctionPointer("nvmlDeviceSetTemperatureThreshold") + ret = fn(handle, _nvmlTemperatureThresholds_t(threshold), byref(c_temp)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetMarginTemperature(handle): + c_marginTempInfo = c_nvmlMarginTemperature_v1_t() + c_marginTempInfo.version = nvmlMarginTemperature_v1 + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMarginTemperature") + ret = fn(handle, byref(c_marginTempInfo)) + _nvmlCheckReturn(ret) + return c_marginTempInfo.marginTemperature + +# DEPRECATED use nvmlDeviceGetPerformanceState +def nvmlDeviceGetPowerState(handle): + c_pstate = _nvmlPstates_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPowerState") + ret = fn(handle, byref(c_pstate)) + _nvmlCheckReturn(ret) + return c_pstate.value + +def nvmlDeviceGetPerformanceState(handle): + c_pstate = _nvmlPstates_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPerformanceState") + ret = fn(handle, byref(c_pstate)) + _nvmlCheckReturn(ret) + return c_pstate.value + +def nvmlDeviceGetPowerManagementMode(handle): + c_pcapMode = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPowerManagementMode") + ret = fn(handle, byref(c_pcapMode)) + _nvmlCheckReturn(ret) + return c_pcapMode.value + +def nvmlDeviceGetPowerManagementLimit(handle): + c_limit = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPowerManagementLimit") + ret = fn(handle, byref(c_limit)) + _nvmlCheckReturn(ret) + return c_limit.value + +# Added in 4.304 +def nvmlDeviceGetPowerManagementLimitConstraints(handle): + c_minLimit = c_uint() + c_maxLimit = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPowerManagementLimitConstraints") + ret = fn(handle, byref(c_minLimit), byref(c_maxLimit)) + _nvmlCheckReturn(ret) + return [c_minLimit.value, c_maxLimit.value] + +# Added in 4.304 +def nvmlDeviceGetPowerManagementDefaultLimit(handle): + c_limit = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPowerManagementDefaultLimit") + ret = fn(handle, byref(c_limit)) + _nvmlCheckReturn(ret) + return c_limit.value + + +# Added in 331 +def nvmlDeviceGetEnforcedPowerLimit(handle): + c_limit = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetEnforcedPowerLimit") + ret = fn(handle, byref(c_limit)) + _nvmlCheckReturn(ret) + return c_limit.value + +def nvmlDeviceGetPowerUsage(handle): + c_watts = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPowerUsage") + ret = fn(handle, byref(c_watts)) + _nvmlCheckReturn(ret) + return c_watts.value + +def nvmlDeviceGetTotalEnergyConsumption(handle): + c_millijoules = c_uint64() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTotalEnergyConsumption") + ret = fn(handle, byref(c_millijoules)) + _nvmlCheckReturn(ret) + return c_millijoules.value + +# Added in 4.304 +def nvmlDeviceGetGpuOperationMode(handle): + c_currState = _nvmlGpuOperationMode_t() + c_pendingState = _nvmlGpuOperationMode_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuOperationMode") + ret = fn(handle, byref(c_currState), byref(c_pendingState)) + _nvmlCheckReturn(ret) + return [c_currState.value, c_pendingState.value] + +# Added in 4.304 +def nvmlDeviceGetCurrentGpuOperationMode(handle): + return nvmlDeviceGetGpuOperationMode(handle)[0] + +# Added in 4.304 +def nvmlDeviceGetPendingGpuOperationMode(handle): + return nvmlDeviceGetGpuOperationMode(handle)[1] + +def nvmlDeviceGetMemoryInfo(handle, version=None): + if not version: + c_memory = c_nvmlMemory_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMemoryInfo") + else: + c_memory = c_nvmlMemory_v2_t() + c_memory.version = version + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMemoryInfo_v2") + ret = fn(handle, byref(c_memory)) + _nvmlCheckReturn(ret) + return c_memory + +def nvmlDeviceGetBAR1MemoryInfo(handle): + c_bar1_memory = c_nvmlBAR1Memory_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetBAR1MemoryInfo") + ret = fn(handle, byref(c_bar1_memory)) + _nvmlCheckReturn(ret) + return c_bar1_memory + +def nvmlDeviceGetComputeMode(handle): + c_mode = _nvmlComputeMode_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetComputeMode") + ret = fn(handle, byref(c_mode)) + _nvmlCheckReturn(ret) + return c_mode.value + +def nvmlDeviceGetCudaComputeCapability(handle): + c_major = c_int() + c_minor = c_int() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCudaComputeCapability") + ret = fn(handle, byref(c_major), byref(c_minor)) + _nvmlCheckReturn(ret) + return (c_major.value, c_minor.value) + +def nvmlDeviceGetEccMode(handle): + c_currState = _nvmlEnableState_t() + c_pendingState = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetEccMode") + ret = fn(handle, byref(c_currState), byref(c_pendingState)) + _nvmlCheckReturn(ret) + return [c_currState.value, c_pendingState.value] + +# added to API +def nvmlDeviceGetCurrentEccMode(handle): + return nvmlDeviceGetEccMode(handle)[0] + +# added to API +def nvmlDeviceGetPendingEccMode(handle): + return nvmlDeviceGetEccMode(handle)[1] + +def nvmlDeviceGetDefaultEccMode(handle): + c_defaultState = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDefaultEccMode") + ret = fn(handle, byref(c_defaultState)) + _nvmlCheckReturn(ret) + return [c_defaultState.value] + +def nvmlDeviceGetTotalEccErrors(handle, errorType, counterType): + c_count = c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTotalEccErrors") + ret = fn(handle, _nvmlMemoryErrorType_t(errorType), + _nvmlEccCounterType_t(counterType), byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +# This is deprecated, instead use nvmlDeviceGetMemoryErrorCounter +def nvmlDeviceGetDetailedEccErrors(handle, errorType, counterType): + c_counts = c_nvmlEccErrorCounts_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDetailedEccErrors") + ret = fn(handle, _nvmlMemoryErrorType_t(errorType), + _nvmlEccCounterType_t(counterType), byref(c_counts)) + _nvmlCheckReturn(ret) + return c_counts + +# Added in 4.304 +def nvmlDeviceGetMemoryErrorCounter(handle, errorType, counterType, locationType): + c_count = c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMemoryErrorCounter") + ret = fn(handle, + _nvmlMemoryErrorType_t(errorType), + _nvmlEccCounterType_t(counterType), + _nvmlMemoryLocation_t(locationType), + byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlDeviceGetUtilizationRates(handle): + c_util = c_nvmlUtilization_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetUtilizationRates") + ret = fn(handle, byref(c_util)) + _nvmlCheckReturn(ret) + return c_util + +def nvmlDeviceGetEncoderUtilization(handle): + c_util = c_uint() + c_samplingPeriod = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetEncoderUtilization") + ret = fn(handle, byref(c_util), byref(c_samplingPeriod)) + _nvmlCheckReturn(ret) + return [c_util.value, c_samplingPeriod.value] + +def nvmlDeviceGetDecoderUtilization(handle): + c_util = c_uint() + c_samplingPeriod = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDecoderUtilization") + ret = fn(handle, byref(c_util), byref(c_samplingPeriod)) + _nvmlCheckReturn(ret) + return [c_util.value, c_samplingPeriod.value] + +def nvmlDeviceGetJpgUtilization(handle): + c_util = c_uint() + c_samplingPeriod = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetJpgUtilization") + ret = fn(handle, byref(c_util), byref(c_samplingPeriod)) + _nvmlCheckReturn(ret) + return [c_util.value, c_samplingPeriod.value] + +def nvmlDeviceGetOfaUtilization(handle): + c_util = c_uint() + c_samplingPeriod = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetOfaUtilization") + ret = fn(handle, byref(c_util), byref(c_samplingPeriod)) + _nvmlCheckReturn(ret) + return [c_util.value, c_samplingPeriod.value] + +def nvmlDeviceGetPcieReplayCounter(handle): + c_replay = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPcieReplayCounter") + ret = fn(handle, byref(c_replay)) + _nvmlCheckReturn(ret) + return c_replay.value + +def nvmlDeviceGetDriverModel(handle): + c_currModel = _nvmlDriverModel_t() + c_pendingModel = _nvmlDriverModel_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDriverModel") + ret = fn(handle, byref(c_currModel), byref(c_pendingModel)) + _nvmlCheckReturn(ret) + return [c_currModel.value, c_pendingModel.value] + +# added to API +def nvmlDeviceGetCurrentDriverModel(handle): + return nvmlDeviceGetDriverModel(handle)[0] + +# added to API +def nvmlDeviceGetPendingDriverModel(handle): + return nvmlDeviceGetDriverModel(handle)[1] + +# Added in 2.285 +@convertStrBytes +def nvmlDeviceGetVbiosVersion(handle): + c_version = create_string_buffer(NVML_DEVICE_VBIOS_VERSION_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVbiosVersion") + ret = fn(handle, c_version, c_uint(NVML_DEVICE_VBIOS_VERSION_BUFFER_SIZE)) + _nvmlCheckReturn(ret) + return c_version.value + +# Added in 2.285 +def nvmlDeviceGetComputeRunningProcesses_v2(handle): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetComputeRunningProcesses_v2") + ret = fn(handle, byref(c_count), None) + if (ret == NVML_SUCCESS): + # special case, no running processes + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + # oversize the array incase more processes are created + c_count.value = c_count.value * 2 + 5 + proc_array = c_nvmlProcessInfo_v2_t * c_count.value + c_procs = proc_array() + # make the call again + ret = fn(handle, byref(c_count), c_procs) + _nvmlCheckReturn(ret) + procs = [] + for i in range(c_count.value): + # use an alternative struct for this object + obj = nvmlStructToFriendlyObject(c_procs[i]) + if (obj.usedGpuMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + # special case for WDDM on Windows, see comment above + obj.usedGpuMemory = None + procs.append(obj) + return procs + else: + # error case + raise NVMLError(ret) + +# Added in 2.285 +def nvmlDeviceGetComputeRunningProcesses_v3(handle): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetComputeRunningProcesses_v3") + ret = fn(handle, byref(c_count), None) + + if (ret == NVML_SUCCESS): + # special case, no running processes + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + # oversize the array incase more processes are created + c_count.value = c_count.value * 2 + 5 + proc_array = c_nvmlProcessInfo_v3_t * c_count.value + c_procs = proc_array() + + # make the call again + ret = fn(handle, byref(c_count), c_procs) + _nvmlCheckReturn(ret) + + procs = [] + for i in range(c_count.value): + # use an alternative struct for this object + obj = nvmlStructToFriendlyObject(c_procs[i]) + if (obj.usedGpuMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + # special case for WDDM on Windows, see comment above + obj.usedGpuMemory = None + procs.append(obj) + + return procs + else: + # error case + raise NVMLError(ret) + +@throwOnVersionMismatch +def nvmlDeviceGetComputeRunningProcesses(handle): + return nvmlDeviceGetComputeRunningProcesses_v3(handle) + +def nvmlDeviceGetGraphicsRunningProcesses_v2(handle): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGraphicsRunningProcesses_v2") + ret = fn(handle, byref(c_count), None) + if (ret == NVML_SUCCESS): + # special case, no running processes + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + # oversize the array incase more processes are created + c_count.value = c_count.value * 2 + 5 + proc_array = c_nvmlProcessInfo_v2_t * c_count.value + c_procs = proc_array() + # make the call again + ret = fn(handle, byref(c_count), c_procs) + _nvmlCheckReturn(ret) + procs = [] + for i in range(c_count.value): + # use an alternative struct for this object + obj = nvmlStructToFriendlyObject(c_procs[i]) + if (obj.usedGpuMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + # special case for WDDM on Windows, see comment above + obj.usedGpuMemory = None + procs.append(obj) + return procs + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetGraphicsRunningProcesses_v3(handle): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGraphicsRunningProcesses_v3") + ret = fn(handle, byref(c_count), None) + + if (ret == NVML_SUCCESS): + # special case, no running processes + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + # oversize the array incase more processes are created + c_count.value = c_count.value * 2 + 5 + proc_array = c_nvmlProcessInfo_v3_t * c_count.value + c_procs = proc_array() + + # make the call again + ret = fn(handle, byref(c_count), c_procs) + _nvmlCheckReturn(ret) + + procs = [] + for i in range(c_count.value): + # use an alternative struct for this object + obj = nvmlStructToFriendlyObject(c_procs[i]) + if (obj.usedGpuMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + # special case for WDDM on Windows, see comment above + obj.usedGpuMemory = None + procs.append(obj) + + return procs + else: + # error case + raise NVMLError(ret) + +@throwOnVersionMismatch +def nvmlDeviceGetGraphicsRunningProcesses(handle): + return nvmlDeviceGetGraphicsRunningProcesses_v3(handle) + +@throwOnVersionMismatch +def nvmlDeviceGetMPSComputeRunningProcesses(handle): + return nvmlDeviceGetMPSComputeRunningProcesses_v3(handle) + +def nvmlDeviceGetMPSComputeRunningProcesses_v2(handle): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMPSComputeRunningProcesses_v2") + ret = fn(handle, byref(c_count), None) + + if (ret == NVML_SUCCESS): + # special case, no running processes + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + # oversize the array incase more processes are created + c_count.value = c_count.value * 2 + 5 + proc_array = c_nvmlProcessInfo_v2_t * c_count.value + c_procs = proc_array() + + # make the call again + ret = fn(handle, byref(c_count), c_procs) + _nvmlCheckReturn(ret) + + procs = [] + for i in range(c_count.value): + # use an alternative struct for this object + obj = nvmlStructToFriendlyObject(c_procs[i]) + if (obj.usedGpuMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + # special case for WDDM on Windows, see comment above + obj.usedGpuMemory = None + procs.append(obj) + + return procs + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetMPSComputeRunningProcesses_v3(handle): + # first call to get the size + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMPSComputeRunningProcesses_v3") + ret = fn(handle, byref(c_count), None) + + if (ret == NVML_SUCCESS): + # special case, no running processes + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + # oversize the array incase more processes are created + c_count.value = c_count.value * 2 + 5 + proc_array = c_nvmlProcessInfo_v3_t * c_count.value + c_procs = proc_array() + + # make the call again + ret = fn(handle, byref(c_count), c_procs) + _nvmlCheckReturn(ret) + + procs = [] + for i in range(c_count.value): + # use an alternative struct for this object + obj = nvmlStructToFriendlyObject(c_procs[i]) + if (obj.usedGpuMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + # special case for WDDM on Windows, see comment above + obj.usedGpuMemory = None + procs.append(obj) + + return procs + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetRunningProcessDetailList(handle, version, mode): + c_processDetailList = c_nvmlProcessDetailList_t() + c_processDetailList.version = version + c_processDetailList.mode = mode + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetRunningProcessDetailList") + + # first call to get the size + ret = fn(handle, byref(c_processDetailList)) + if (ret == NVML_SUCCESS): + # special case, no running processes + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + c_procs = c_nvmlProcessDetail_v1_t * c_processDetailList.numProcArrayEntries + c_processDetailList.procArray = cast((c_procs)(), POINTER(c_nvmlProcessDetail_v1_t)) + + # make the call again + ret = fn(handle, byref(c_processDetailList)) + _nvmlCheckReturn(ret) + + procs = [] + for i in range(c_processDetailList.numProcArrayEntries): + # use an alternative struct for this object + obj = c_processDetailList.procArray[i] + if (obj.usedGpuMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + obj.usedGpuMemory = None + if (obj.usedGpuCcProtectedMemory == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + obj.usedGpuCcProtectedMemory = None + procs.append(obj) + + return procs + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetAutoBoostedClocksEnabled(handle): + c_isEnabled = _nvmlEnableState_t() + c_defaultIsEnabled = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAutoBoostedClocksEnabled") + ret = fn(handle, byref(c_isEnabled), byref(c_defaultIsEnabled)) + _nvmlCheckReturn(ret) + return [c_isEnabled.value, c_defaultIsEnabled.value] + #Throws NVML_ERROR_NOT_SUPPORTED if hardware doesn't support setting auto boosted clocks + +## Set functions +def nvmlUnitSetLedState(unit, color): + fn = _nvmlGetFunctionPointer("nvmlUnitSetLedState") + ret = fn(unit, _nvmlLedColor_t(color)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceSetPersistenceMode(handle, mode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetPersistenceMode") + ret = fn(handle, _nvmlEnableState_t(mode)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceSetComputeMode(handle, mode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetComputeMode") + ret = fn(handle, _nvmlComputeMode_t(mode)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceSetEccMode(handle, mode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetEccMode") + ret = fn(handle, _nvmlEnableState_t(mode)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceClearEccErrorCounts(handle, counterType): + fn = _nvmlGetFunctionPointer("nvmlDeviceClearEccErrorCounts") + ret = fn(handle, _nvmlEccCounterType_t(counterType)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceSetDriverModel(handle, model): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetDriverModel") + ret = fn(handle, _nvmlDriverModel_t(model)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceSetAutoBoostedClocksEnabled(handle, enabled): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetAutoBoostedClocksEnabled") + ret = fn(handle, _nvmlEnableState_t(enabled)) + _nvmlCheckReturn(ret) + return None + #Throws NVML_ERROR_NOT_SUPPORTED if hardware doesn't support setting auto boosted clocks + +def nvmlDeviceSetDefaultAutoBoostedClocksEnabled(handle, enabled, flags): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetDefaultAutoBoostedClocksEnabled") + ret = fn(handle, _nvmlEnableState_t(enabled), c_uint(flags)) + _nvmlCheckReturn(ret) + return None + #Throws NVML_ERROR_NOT_SUPPORTED if hardware doesn't support setting auto boosted clocks + +def nvmlDeviceSetGpuLockedClocks(handle, minGpuClockMHz, maxGpuClockMHz): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetGpuLockedClocks") + ret = fn(handle, c_uint(minGpuClockMHz), c_uint(maxGpuClockMHz)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceResetGpuLockedClocks(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceResetGpuLockedClocks") + ret = fn(handle) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceSetMemoryLockedClocks(handle, minMemClockMHz, maxMemClockMHz): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetMemoryLockedClocks") + ret = fn(handle, c_uint(minMemClockMHz), c_uint(maxMemClockMHz)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceResetMemoryLockedClocks(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceResetMemoryLockedClocks") + ret = fn(handle) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetClkMonStatus(handle, c_clkMonInfo=nvmlClkMonStatus_t()): + isReference = type(c_clkMonInfo) is not nvmlClkMonStatus_t + c_clkMonInfoRef = c_clkMonInfo if isReference else byref(c_clkMonInfo) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetClkMonStatus") + ret = fn(handle, c_clkMonInfoRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else c_clkMonInfo + +# Added in 4.304 +def nvmlDeviceSetApplicationsClocks(handle, maxMemClockMHz, maxGraphicsClockMHz): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetApplicationsClocks") + ret = fn(handle, c_uint(maxMemClockMHz), c_uint(maxGraphicsClockMHz)) + _nvmlCheckReturn(ret) + return None + +# Added in 4.304 +def nvmlDeviceResetApplicationsClocks(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceResetApplicationsClocks") + ret = fn(handle) + _nvmlCheckReturn(ret) + return None + +# Added in 4.304 +def nvmlDeviceSetPowerManagementLimit(handle, limit): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetPowerManagementLimit") + ret = fn(handle, c_uint(limit)) + _nvmlCheckReturn(ret) + return None + +# Added in 4.304 +def nvmlDeviceSetGpuOperationMode(handle, mode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetGpuOperationMode") + ret = fn(handle, _nvmlGpuOperationMode_t(mode)) + _nvmlCheckReturn(ret) + return None + +# Added in 2.285 +def nvmlEventSetCreate(): + fn = _nvmlGetFunctionPointer("nvmlEventSetCreate") + eventSet = c_nvmlEventSet_t() + ret = fn(byref(eventSet)) + _nvmlCheckReturn(ret) + return eventSet + +# Added in 2.285 +def nvmlDeviceRegisterEvents(handle, eventTypes, eventSet): + fn = _nvmlGetFunctionPointer("nvmlDeviceRegisterEvents") + ret = fn(handle, c_ulonglong(eventTypes), eventSet) + _nvmlCheckReturn(ret) + return None + +# Added in 2.285 +def nvmlDeviceGetSupportedEventTypes(handle): + c_eventTypes = c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSupportedEventTypes") + ret = fn(handle, byref(c_eventTypes)) + _nvmlCheckReturn(ret) + return c_eventTypes.value + +# raises NVML_ERROR_TIMEOUT exception on timeout +def nvmlEventSetWait_v2(eventSet, timeoutms): + fn = _nvmlGetFunctionPointer("nvmlEventSetWait_v2") + data = c_nvmlEventData_t() + ret = fn(eventSet, byref(data), c_uint(timeoutms)) + _nvmlCheckReturn(ret) + return data + +def nvmlEventSetWait(eventSet, timeoutms): + return nvmlEventSetWait_v2(eventSet, timeoutms) + +# Added in 2.285 +def nvmlEventSetFree(eventSet): + fn = _nvmlGetFunctionPointer("nvmlEventSetFree") + ret = fn(eventSet) + _nvmlCheckReturn(ret) + return None + +# Added in 3.295 +def nvmlDeviceOnSameBoard(handle1, handle2): + fn = _nvmlGetFunctionPointer("nvmlDeviceOnSameBoard") + onSameBoard = c_int() + ret = fn(handle1, handle2, byref(onSameBoard)) + _nvmlCheckReturn(ret) + return (onSameBoard.value != 0) + +# Added in 3.295 +def nvmlDeviceGetCurrPcieLinkGeneration(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCurrPcieLinkGeneration") + gen = c_uint() + ret = fn(handle, byref(gen)) + _nvmlCheckReturn(ret) + return gen.value + +# Added in 3.295 +def nvmlDeviceGetMaxPcieLinkGeneration(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMaxPcieLinkGeneration") + gen = c_uint() + ret = fn(handle, byref(gen)) + _nvmlCheckReturn(ret) + return gen.value + +# Added in 3.295 +def nvmlDeviceGetCurrPcieLinkWidth(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCurrPcieLinkWidth") + width = c_uint() + ret = fn(handle, byref(width)) + _nvmlCheckReturn(ret) + return width.value + +# Added in 3.295 +def nvmlDeviceGetMaxPcieLinkWidth(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMaxPcieLinkWidth") + width = c_uint() + ret = fn(handle, byref(width)) + _nvmlCheckReturn(ret) + return width.value + +def nvmlDeviceGetGpuMaxPcieLinkGeneration(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuMaxPcieLinkGeneration") + gen = c_uint() + ret = fn(handle, byref(gen)) + _nvmlCheckReturn(ret) + return gen.value + +# Added in 4.304 +def nvmlDeviceGetSupportedClocksThrottleReasons(handle): + c_reasons= c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSupportedClocksThrottleReasons") + ret = fn(handle, byref(c_reasons)) + _nvmlCheckReturn(ret) + return c_reasons.value + +def nvmlDeviceGetSupportedClocksEventReasons(handle): + c_reasons= c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSupportedClocksEventReasons") + ret = fn(handle, byref(c_reasons)) + _nvmlCheckReturn(ret) + return c_reasons.value + +# Added in 4.304 +def nvmlDeviceGetCurrentClocksThrottleReasons(handle): + c_reasons= c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCurrentClocksThrottleReasons") + ret = fn(handle, byref(c_reasons)) + _nvmlCheckReturn(ret) + return c_reasons.value + +def nvmlDeviceGetCurrentClocksEventReasons(handle): + c_reasons= c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCurrentClocksEventReasons") + ret = fn(handle, byref(c_reasons)) + _nvmlCheckReturn(ret) + return c_reasons.value + +# Added in 5.319 +def nvmlDeviceGetIndex(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetIndex") + c_index = c_uint() + ret = fn(handle, byref(c_index)) + _nvmlCheckReturn(ret) + return c_index.value + +# Added in 5.319 +def nvmlDeviceGetAccountingMode(handle): + c_mode = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAccountingMode") + ret = fn(handle, byref(c_mode)) + _nvmlCheckReturn(ret) + return c_mode.value + +def nvmlDeviceSetAccountingMode(handle, mode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetAccountingMode") + ret = fn(handle, _nvmlEnableState_t(mode)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceClearAccountingPids(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceClearAccountingPids") + ret = fn(handle) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetAccountingStats(handle, pid): + stats = c_nvmlAccountingStats_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAccountingStats") + ret = fn(handle, c_uint(pid), byref(stats)) + _nvmlCheckReturn(ret) + if (stats.maxMemoryUsage == NVML_VALUE_NOT_AVAILABLE_ulonglong.value): + # special case for WDDM on Windows, see comment above + stats.maxMemoryUsage = None + return stats + +def nvmlDeviceGetAccountingPids(handle): + count = c_uint(nvmlDeviceGetAccountingBufferSize(handle)) + pids = (c_uint * count.value)() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAccountingPids") + ret = fn(handle, byref(count), pids) + _nvmlCheckReturn(ret) + return list(map(int, pids[0:count.value])) + +def nvmlDeviceGetAccountingBufferSize(handle): + bufferSize = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAccountingBufferSize") + ret = fn(handle, byref(bufferSize)) + _nvmlCheckReturn(ret) + return int(bufferSize.value) + +def nvmlDeviceGetRetiredPages(device, sourceFilter): + c_source = _nvmlPageRetirementCause_t(sourceFilter) + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetRetiredPages") + + # First call will get the size + ret = fn(device, c_source, byref(c_count), None) + + # this should only fail with insufficient size + if ((ret != NVML_SUCCESS) and + (ret != NVML_ERROR_INSUFFICIENT_SIZE)): + raise NVMLError(ret) + + # call again with a buffer + # oversize the array for the rare cases where additional pages + # are retired between NVML calls + c_count.value = c_count.value * 2 + 5 + page_array = c_ulonglong * c_count.value + c_pages = page_array() + ret = fn(device, c_source, byref(c_count), c_pages) + _nvmlCheckReturn(ret) + return list(map(int, c_pages[0:c_count.value])) + +def nvmlDeviceGetRetiredPages_v2(device, sourceFilter): + c_source = _nvmlPageRetirementCause_t(sourceFilter) + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetRetiredPages_v2") + + # First call will get the size + ret = fn(device, c_source, byref(c_count), None) + + # this should only fail with insufficient size + if ((ret != NVML_SUCCESS) and + (ret != NVML_ERROR_INSUFFICIENT_SIZE)): + raise NVMLError(ret) + + # call again with a buffer + # oversize the array for the rare cases where additional pages + # are retired between NVML calls + c_count.value = c_count.value * 2 + 5 + page_array = c_ulonglong * c_count.value + c_pages = page_array() + times_array = c_ulonglong * c_count.value + c_times = times_array() + ret = fn(device, c_source, byref(c_count), c_pages, c_times) + _nvmlCheckReturn(ret) + return [ { 'address': int(c_pages[i]), 'timestamp': int(c_times[i]) } for i in range(c_count.value) ]; + +def nvmlDeviceGetRetiredPagesPendingStatus(device): + c_pending = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetRetiredPagesPendingStatus") + ret = fn(device, byref(c_pending)) + _nvmlCheckReturn(ret) + return int(c_pending.value) + +def nvmlDeviceGetAPIRestriction(device, apiType): + c_permission = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAPIRestriction") + ret = fn(device, _nvmlRestrictedAPI_t(apiType), byref(c_permission)) + _nvmlCheckReturn(ret) + return int(c_permission.value) + +def nvmlDeviceSetAPIRestriction(handle, apiType, isRestricted): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetAPIRestriction") + ret = fn(handle, _nvmlRestrictedAPI_t(apiType), _nvmlEnableState_t(isRestricted)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetBridgeChipInfo(handle): + bridgeHierarchy = c_nvmlBridgeChipHierarchy_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetBridgeChipInfo") + ret = fn(handle, byref(bridgeHierarchy)) + _nvmlCheckReturn(ret) + return bridgeHierarchy + +def nvmlDeviceGetSamples(device, sampling_type, timeStamp): + c_sampling_type = _nvmlSamplingType_t(sampling_type) + c_time_stamp = c_ulonglong(timeStamp) + c_sample_count = c_uint(0) + c_sample_value_type = _nvmlValueType_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSamples") + + ## First Call gets the size + ret = fn(device, c_sampling_type, c_time_stamp, byref(c_sample_value_type), byref(c_sample_count), None) + + # Stop if this fails + if (ret != NVML_SUCCESS): + raise NVMLError(ret) + + sampleArray = c_sample_count.value * c_nvmlSample_t + c_samples = sampleArray() + ret = fn(device, c_sampling_type, c_time_stamp, byref(c_sample_value_type), byref(c_sample_count), c_samples) + _nvmlCheckReturn(ret) + return (c_sample_value_type.value, c_samples[0:c_sample_count.value]) + +def nvmlDeviceGetViolationStatus(device, perfPolicyType): + c_perfPolicy_type = _nvmlPerfPolicyType_t(perfPolicyType) + c_violTime = c_nvmlViolationTime_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetViolationStatus") + + ## Invoke the method to get violation time + ret = fn(device, c_perfPolicy_type, byref(c_violTime)) + _nvmlCheckReturn(ret) + return c_violTime + +def nvmlDeviceGetPcieThroughput(device, counter): + c_util = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPcieThroughput") + ret = fn(device, _nvmlPcieUtilCounter_t(counter), byref(c_util)) + _nvmlCheckReturn(ret) + return c_util.value + +def nvmlSystemGetTopologyGpuSet(cpuNumber): + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlSystemGetTopologyGpuSet") + + # First call will get the size + ret = fn(cpuNumber, byref(c_count), None) + + if ret != NVML_SUCCESS: + raise NVMLError(ret) + # call again with a buffer + device_array = c_nvmlDevice_t * c_count.value + c_devices = device_array() + ret = fn(cpuNumber, byref(c_count), c_devices) + _nvmlCheckReturn(ret) + return list(c_devices[0:c_count.value]) + +def nvmlDeviceGetTopologyNearestGpus(device, level): + c_count = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTopologyNearestGpus") + + # First call will get the size + ret = fn(device, level, byref(c_count), None) + + if ret != NVML_SUCCESS: + raise NVMLError(ret) + + # call again with a buffer + device_array = c_nvmlDevice_t * c_count.value + c_devices = device_array() + ret = fn(device, level, byref(c_count), c_devices) + _nvmlCheckReturn(ret) + return list(c_devices[0:c_count.value]) + +def nvmlDeviceGetTopologyCommonAncestor(device1, device2): + c_level = _nvmlGpuTopologyLevel_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetTopologyCommonAncestor") + ret = fn(device1, device2, byref(c_level)) + _nvmlCheckReturn(ret) + return c_level.value + +def nvmlDeviceGetNvLinkUtilizationCounter(device, link, counter): + c_rxcounter = c_ulonglong() + c_txcounter = c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkUtilizationCounter") + ret = fn(device, link, counter, byref(c_rxcounter), byref(c_txcounter)) + _nvmlCheckReturn(ret) + return (c_rxcounter.value, c_txcounter.value) + +def nvmlDeviceFreezeNvLinkUtilizationCounter(device, link, counter, freeze): + fn = _nvmlGetFunctionPointer("nvmlDeviceFreezeNvLinkUtilizationCounter") + ret = fn(device, link, counter, freeze) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceResetNvLinkUtilizationCounter(device, link, counter): + fn = _nvmlGetFunctionPointer("nvmlDeviceResetNvLinkUtilizationCounter") + ret = fn(device, link, counter) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceSetNvLinkUtilizationControl(device, link, counter, control, reset): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetNvLinkUtilizationControl") + ret = fn(device, link, counter, byref(control), reset) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetNvLinkUtilizationControl(device, link, counter): + c_control = nvmlNvLinkUtilizationControl_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkUtilizationControl") + ret = fn(device, link, counter, byref(c_control)) + _nvmlCheckReturn(ret) + return c_control + +def nvmlDeviceGetNvLinkCapability(device, link, capability): + c_capResult = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkCapability") + ret = fn(device, link, capability, byref(c_capResult)) + _nvmlCheckReturn(ret) + return c_capResult.value + +def nvmlDeviceGetNvLinkErrorCounter(device, link, counter): + c_result = c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkErrorCounter") + ret = fn(device, link, counter, byref(c_result)) + _nvmlCheckReturn(ret) + return c_result.value + +def nvmlDeviceResetNvLinkErrorCounters(device, link): + fn = _nvmlGetFunctionPointer("nvmlDeviceResetNvLinkErrorCounters") + ret = fn(device, link) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetNvLinkRemotePciInfo(device, link): + c_pci = nvmlPciInfo_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkRemotePciInfo_v2") + ret = fn(device, link, byref(c_pci)) + _nvmlCheckReturn(ret) + return c_pci + +def nvmlDeviceGetNvLinkRemoteDeviceType(handle, link): + c_type = _nvmlNvLinkDeviceType_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkRemoteDeviceType") + ret = fn(handle, link, byref(c_type)) + _nvmlCheckReturn(ret) + return c_type.value + +def nvmlDeviceGetNvLinkState(device, link): + c_isActive = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkState") + ret = fn(device, link, byref(c_isActive)) + _nvmlCheckReturn(ret) + return c_isActive.value + +def nvmlDeviceGetNvLinkVersion(device, link): + c_version = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvLinkVersion") + ret = fn(device, link, byref(c_version)) + _nvmlCheckReturn(ret) + return c_version.value + +def nvmlDeviceModifyDrainState(pciInfo, newState): + fn = _nvmlGetFunctionPointer("nvmlDeviceModifyDrainState") + ret = fn(pointer(pciInfo), newState) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceQueryDrainState(pciInfo): + c_newState = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceQueryDrainState") + ret = fn(pointer(pciInfo), byref(c_newState)) + _nvmlCheckReturn(ret) + return c_newState.value + +def nvmlDeviceRemoveGpu(pciInfo): + fn = _nvmlGetFunctionPointer("nvmlDeviceRemoveGpu") + ret = fn(pointer(pciInfo)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceDiscoverGpus(pciInfo): + fn = _nvmlGetFunctionPointer("nvmlDeviceDiscoverGpus") + ret = fn(pointer(pciInfo)) + _nvmlCheckReturn(ret) + return None + +def nvmlDeviceGetFieldValues(handle, fieldIds): + values_arr = c_nvmlFieldValue_t * len(fieldIds) + values = values_arr() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetFieldValues") + + for i, fieldId in enumerate(fieldIds): + try: + (values[i].fieldId, values[i].scopeId) = fieldId + except TypeError: + values[i].fieldId = fieldId + + ret = fn(handle, c_int32(len(fieldIds)), byref(values)) + _nvmlCheckReturn(ret) + return values + +def nvmlDeviceClearFieldValues(handle, fieldIds): + values_arr = c_nvmlFieldValue_t * len(fieldIds) + values = values_arr() + fn = _nvmlGetFunctionPointer("nvmlDeviceClearFieldValues") + + for i, fieldId in enumerate(fieldIds): + try: + (values[i].fieldId, values[i].scopeId) = fieldId + except TypeError: + values[i].fieldId = fieldId + + ret = fn(handle, c_int32(len(fieldIds)), byref(values)) + _nvmlCheckReturn(ret) + return values + +def nvmlDeviceGetVirtualizationMode(handle): + c_virtualization_mode = c_ulonglong() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVirtualizationMode") + ret = fn(handle, byref(c_virtualization_mode)) + _nvmlCheckReturn(ret) + return c_virtualization_mode.value + +def nvmlDeviceSetVirtualizationMode(handle, virtualization_mode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetVirtualizationMode") + return fn(handle, virtualization_mode) + +def nvmlDeviceGetVgpuHeterogeneousMode(handle): + c_vgpuHeterogeneousMode = c_nvmlVgpuHeterogeneousMode_v1_t(0) + c_vgpuHeterogeneousMode.version = VgpuHeterogeneousMode_v1 + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuHeterogeneousMode") + ret = fn(handle, byref(c_vgpuHeterogeneousMode)) + _nvmlCheckReturn(ret) + return c_vgpuHeterogeneousMode.mode + +def nvmlDeviceSetVgpuHeterogeneousMode(handle, heterogeneous_mode): + c_vgpuHeterogeneousMode = c_nvmlVgpuHeterogeneousMode_v1_t(0) + c_vgpuHeterogeneousMode.version = VgpuHeterogeneousMode_v1 + c_vgpuHeterogeneousMode.mode = heterogeneous_mode + fn = _nvmlGetFunctionPointer("nvmlDeviceSetVgpuHeterogeneousMode") + ret = fn(handle, byref(c_vgpuHeterogeneousMode)) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlVgpuInstanceGetPlacementId(vgpuInstance): + c_placement = c_nvmlVgpuPlacementId_v1_t(0) + c_placement.version = VgpuPlacementId_v1 + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetPlacementId") + ret = fn(vgpuInstance, byref(c_placement)) + _nvmlCheckReturn(ret) + return c_placement.placementId + +def nvmlDeviceGetVgpuTypeSupportedPlacements(handle, vgpuTypeId, mode=0, version=1): + c_max_instances = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetMaxInstances") + ret = fn(handle, vgpuTypeId, byref(c_max_instances)) + _nvmlCheckReturn(ret) + + if version == 2: + c_vgpu_placements = c_nvmlVgpuPlacementList_v2_t() + c_vgpu_placements.version = VgpuPlacementList_v2 + c_vgpu_placements.count = c_max_instances.value + c_vgpu_placements.mode = mode + elif version == 1: + c_vgpu_placements = c_nvmlVgpuPlacementList_v1_t() + c_vgpu_placements.version = VgpuPlacementList_v1 + else: + raise NVMLError(NVML_ERROR_ARGUMENT_VERSION_MISMATCH) + + c_placements = c_uint * c_max_instances.value + c_vgpu_placements.placementIds = c_placements() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuTypeSupportedPlacements") + ret = fn(handle, vgpuTypeId, byref(c_vgpu_placements)) + _nvmlCheckReturn(ret) + return c_vgpu_placements + +def nvmlDeviceGetVgpuTypeCreatablePlacements(handle, vgpuTypeId, version=1): + c_max_instances = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetMaxInstances") + ret = fn(handle, vgpuTypeId, byref(c_max_instances)) + _nvmlCheckReturn(ret) + + if version == 2: + c_vgpu_placements = c_nvmlVgpuPlacementList_v2_t() + c_vgpu_placements.version = VgpuPlacementList_v2 + c_vgpu_placements.count = c_max_instances.value + elif version == 1: + c_vgpu_placements = c_nvmlVgpuPlacementList_v1_t() + c_vgpu_placements.version = VgpuPlacementList_v1 + + c_placements = c_uint * c_max_instances.value + c_vgpu_placements.placementIds = c_placements() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuTypeCreatablePlacements") + ret = fn(handle, vgpuTypeId, byref(c_vgpu_placements)) + _nvmlCheckReturn(ret) + return c_vgpu_placements + +def nvmlGetVgpuDriverCapabilities(capability): + c_capResult = c_uint() + fn = _nvmlGetFunctionPointer("nvmlGetVgpuDriverCapabilities") + ret = fn(_nvmlVgpuDriverCapability_t(capability), byref(c_capResult)) + _nvmlCheckReturn(ret) + return c_capResult.value + +def nvmlDeviceGetVgpuCapabilities(handle, capability): + c_capResult = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuCapabilities") + ret = fn(handle, _nvmlDeviceVgpuCapability_t(capability), byref(c_capResult)) + _nvmlCheckReturn(ret) + return c_capResult.value + +def nvmlDeviceSetVgpuCapabilities(handle, capability, state): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetVgpuCapabilities") + ret = fn(handle, _nvmlDeviceVgpuCapability_t(capability), state) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetSupportedVgpus(handle): + # first call to get the size + c_vgpu_count = c_uint(0) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSupportedVgpus") + ret = fn(handle, byref(c_vgpu_count), None) + + if (ret == NVML_SUCCESS): + # special case, no supported vGPUs + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + vgpu_type_ids_array = _nvmlVgpuTypeId_t * c_vgpu_count.value + c_vgpu_type_ids = vgpu_type_ids_array() + + # make the call again + ret = fn(handle, byref(c_vgpu_count), c_vgpu_type_ids) + _nvmlCheckReturn(ret) + vgpus = [] + for i in range(c_vgpu_count.value): + vgpus.append(c_vgpu_type_ids[i]) + return vgpus + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetCreatableVgpus(handle): + # first call to get the size + c_vgpu_count = c_uint(0) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCreatableVgpus") + ret = fn(handle, byref(c_vgpu_count), None) + + if (ret == NVML_SUCCESS): + # special case, no supported vGPUs + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + vgpu_type_ids_array = _nvmlVgpuTypeId_t * c_vgpu_count.value + c_vgpu_type_ids = vgpu_type_ids_array() + + # make the call again + ret = fn(handle, byref(c_vgpu_count), c_vgpu_type_ids) + _nvmlCheckReturn(ret) + vgpus = [] + for i in range(c_vgpu_count.value): + vgpus.append(c_vgpu_type_ids[i]) + return vgpus + else: + # error case + raise NVMLError(ret) + +def nvmlVgpuTypeGetGpuInstanceProfileId(vgpuTypeId): + c_profile_id = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetGpuInstanceProfileId") + ret = fn(vgpuTypeId, byref(c_profile_id)) + _nvmlCheckReturn(ret) + return (c_profile_id.value) + +@convertStrBytes +def nvmlVgpuTypeGetClass(vgpuTypeId): + c_class = create_string_buffer(NVML_DEVICE_NAME_BUFFER_SIZE) + c_buffer_size = c_uint(NVML_DEVICE_NAME_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetClass") + ret = fn(vgpuTypeId, c_class, byref(c_buffer_size)) + _nvmlCheckReturn(ret) + return c_class.value + +@convertStrBytes +def nvmlVgpuTypeGetName(vgpuTypeId): + c_name = create_string_buffer(NVML_DEVICE_NAME_BUFFER_SIZE) + c_buffer_size = c_uint(NVML_DEVICE_NAME_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetName") + ret = fn(vgpuTypeId, c_name, byref(c_buffer_size)) + _nvmlCheckReturn(ret) + return c_name.value + +def nvmlVgpuTypeGetDeviceID(vgpuTypeId): + c_device_id = c_ulonglong(0) + c_subsystem_id = c_ulonglong(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetDeviceID") + ret = fn(vgpuTypeId, byref(c_device_id), byref(c_subsystem_id)) + _nvmlCheckReturn(ret) + return (c_device_id.value, c_subsystem_id.value) + +def nvmlVgpuTypeGetFramebufferSize(vgpuTypeId): + c_fb_size = c_ulonglong(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetFramebufferSize") + ret = fn(vgpuTypeId, byref(c_fb_size)) + _nvmlCheckReturn(ret) + return c_fb_size.value + +def nvmlVgpuTypeGetNumDisplayHeads(vgpuTypeId): + c_num_heads = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetNumDisplayHeads") + ret = fn(vgpuTypeId, byref(c_num_heads)) + _nvmlCheckReturn(ret) + return c_num_heads.value + +def nvmlVgpuTypeGetResolution(vgpuTypeId): + c_xdim = c_uint(0) + c_ydim = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetResolution") + ret = fn(vgpuTypeId, 0, byref(c_xdim), byref(c_ydim)) + _nvmlCheckReturn(ret) + return (c_xdim.value, c_ydim.value) + +@convertStrBytes +def nvmlVgpuTypeGetLicense(vgpuTypeId): + c_license = create_string_buffer(NVML_GRID_LICENSE_BUFFER_SIZE) + c_buffer_size = c_uint(NVML_GRID_LICENSE_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetLicense") + ret = fn(vgpuTypeId, c_license, c_buffer_size) + _nvmlCheckReturn(ret) + return c_license.value + +def nvmlVgpuTypeGetFrameRateLimit(vgpuTypeId): + c_frl_config = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetFrameRateLimit") + ret = fn(vgpuTypeId, byref(c_frl_config)) + _nvmlCheckReturn(ret) + return c_frl_config.value + +def nvmlVgpuTypeGetGspHeapSize(vgpuTypeId): + c_gsp_heap = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetGspHeapSize") + ret = fn(vgpuTypeId, byref(c_gsp_heap)) + _nvmlCheckReturn(ret) + return c_gsp_heap.value + +def nvmlVgpuTypeGetFbReservation(vgpuTypeId): + c_fb_reservation = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetFbReservation") + ret = fn(vgpuTypeId, byref(c_fb_reservation)) + _nvmlCheckReturn(ret) + return c_fb_reservation.value + +def nvmlVgpuInstanceGetRuntimeStateSize(vgpuInstance): + c_runtime_state = nvmlVgpuRuntimeState_v1_t() + c_runtime_state.version = VgpuRuntimeState_v1 + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetRuntimeStateSize") + ret = fn(vgpuInstance, byref(c_runtime_state)) + _nvmlCheckReturn(ret) + return c_runtime_state + +def nvmlVgpuTypeGetMaxInstances(handle, vgpuTypeId): + c_max_instances = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetMaxInstances") + ret = fn(handle, vgpuTypeId, byref(c_max_instances)) + _nvmlCheckReturn(ret) + return c_max_instances.value + +def nvmlVgpuTypeGetMaxInstancesPerVm(vgpuTypeId): + c_max_instances_per_vm = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetMaxInstancesPerVm") + ret = fn(vgpuTypeId, byref(c_max_instances_per_vm)) + _nvmlCheckReturn(ret) + return c_max_instances_per_vm.value + +def nvmlVgpuTypeGetBAR1Info(vgpuTypeId): + c_bar1Info = c_nvmlVgpuTypeBar1Info_v1_t(0) + c_bar1Info.version = VgpuTypeBar1Info_v1 + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetBAR1Info") + ret = fn(vgpuTypeId, byref(c_bar1Info)) + _nvmlCheckReturn(ret) + return c_bar1Info + +def nvmlDeviceGetActiveVgpus(handle): + # first call to get the size + c_vgpu_count = c_uint(0) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetActiveVgpus") + ret = fn(handle, byref(c_vgpu_count), None) + + if (ret == NVML_SUCCESS): + # special case, no active vGPUs + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + vgpu_instance_array = _nvmlVgpuInstance_t * c_vgpu_count.value + c_vgpu_instances = vgpu_instance_array() + + # make the call again + ret = fn(handle, byref(c_vgpu_count), c_vgpu_instances) + _nvmlCheckReturn(ret) + vgpus = [] + for i in range(c_vgpu_count.value): + vgpus.append(c_vgpu_instances[i]) + return vgpus + else: + # error case + raise NVMLError(ret) + +@convertStrBytes +def nvmlVgpuInstanceGetVmID(vgpuInstance): + c_vm_id = create_string_buffer(NVML_DEVICE_UUID_BUFFER_SIZE) + c_buffer_size = c_uint(NVML_GRID_LICENSE_BUFFER_SIZE) + c_vm_id_type = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetVmID") + ret = fn(vgpuInstance, byref(c_vm_id), c_buffer_size, byref(c_vm_id_type)) + _nvmlCheckReturn(ret) + return (c_vm_id.value, c_vm_id_type.value) + +@convertStrBytes +def nvmlVgpuInstanceGetUUID(vgpuInstance): + c_uuid = create_string_buffer(NVML_DEVICE_UUID_BUFFER_SIZE) + c_buffer_size = c_uint(NVML_DEVICE_UUID_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetUUID") + ret = fn(vgpuInstance, byref(c_uuid), c_buffer_size) + _nvmlCheckReturn(ret) + return c_uuid.value + +@convertStrBytes +def nvmlVgpuInstanceGetMdevUUID(vgpuInstance): + c_uuid = create_string_buffer(NVML_DEVICE_UUID_BUFFER_SIZE) + c_buffer_size = c_uint(NVML_DEVICE_UUID_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetMdevUUID") + ret = fn(vgpuInstance, byref(c_uuid), c_buffer_size) + _nvmlCheckReturn(ret) + return c_uuid.value + +@convertStrBytes +def nvmlVgpuInstanceGetVmDriverVersion(vgpuInstance): + c_driver_version = create_string_buffer(NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE) + c_buffer_size = c_uint(NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetVmDriverVersion") + ret = fn(vgpuInstance, byref(c_driver_version), c_buffer_size) + _nvmlCheckReturn(ret) + return c_driver_version.value + +def nvmlVgpuInstanceGetLicenseStatus(vgpuInstance): + c_license_status = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetLicenseStatus") + ret = fn(vgpuInstance, byref(c_license_status)) + _nvmlCheckReturn(ret) + return c_license_status.value + +def nvmlVgpuInstanceGetLicenseInfo_v2(vgpuInstance): + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetLicenseInfo_v2") + c_license_info = c_nvmlVgpuLicenseInfo_t() + ret = fn(vgpuInstance, byref(c_license_info)) + _nvmlCheckReturn(ret) + return c_license_info + +def nvmlVgpuInstanceGetLicenseInfo(vgpuInstance): + return nvmlVgpuInstanceGetLicenseInfo_v2(vgpuInstance) + +def nvmlVgpuInstanceGetFrameRateLimit(vgpuInstance): + c_frl = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetFrameRateLimit") + ret = fn(vgpuInstance, byref(c_frl)) + _nvmlCheckReturn(ret) + return c_frl.value + +def nvmlVgpuInstanceGetEccMode(vgpuInstance): + c_mode = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetEccMode") + ret = fn(vgpuInstance, byref(c_mode)) + _nvmlCheckReturn(ret) + return c_mode.value + +def nvmlVgpuInstanceGetType(vgpuInstance): + c_vgpu_type = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetType") + ret = fn(vgpuInstance, byref(c_vgpu_type)) + _nvmlCheckReturn(ret) + return c_vgpu_type.value + +def nvmlVgpuInstanceGetEncoderCapacity(vgpuInstance): + c_encoder_capacity = c_ulonglong(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetEncoderCapacity") + ret = fn(vgpuInstance, byref(c_encoder_capacity)) + _nvmlCheckReturn(ret) + return c_encoder_capacity.value + +def nvmlVgpuInstanceSetEncoderCapacity(vgpuInstance, encoder_capacity): + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceSetEncoderCapacity") + return fn(vgpuInstance, encoder_capacity) + +def nvmlVgpuInstanceGetFbUsage(vgpuInstance): + c_fb_usage = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetFbUsage") + ret = fn(vgpuInstance, byref(c_fb_usage)) + _nvmlCheckReturn(ret) + return c_fb_usage.value + +def nvmlVgpuTypeGetCapabilities(vgpuTypeId, capability): + c_cap_result = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuTypeGetCapabilities") + ret = fn(vgpuTypeId, _nvmlVgpuCapability_t(capability), byref(c_cap_result)) + _nvmlCheckReturn(ret) + return (c_cap_result.value) + +def nvmlVgpuInstanceGetGpuInstanceId(vgpuInstance): + c_id = c_uint(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetGpuInstanceId") + ret = fn(vgpuInstance, byref(c_id)) + _nvmlCheckReturn(ret) + return (c_id.value) + +@convertStrBytes +def nvmlVgpuInstanceGetGpuPciId(vgpuInstance): + c_vgpuPciId = create_string_buffer(NVML_DEVICE_PCI_BUS_ID_BUFFER_SIZE) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetGpuPciId") + ret = fn(vgpuInstance, c_vgpuPciId, byref(c_uint(NVML_DEVICE_PCI_BUS_ID_BUFFER_SIZE))) + _nvmlCheckReturn(ret) + return c_vgpuPciId.value + +def nvmlDeviceGetVgpuUtilization(handle, timeStamp): + # first call to get the size + c_vgpu_count = c_uint(0) + c_time_stamp = c_ulonglong(timeStamp) + c_sample_value_type = _nvmlValueType_t() + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuUtilization") + ret = fn(handle, c_time_stamp, byref(c_sample_value_type), byref(c_vgpu_count), None) + + if (ret == NVML_SUCCESS): + # special case, no active vGPUs + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + sampleArray = c_vgpu_count.value * c_nvmlVgpuInstanceUtilizationSample_t + c_samples = sampleArray() + + # make the call again + ret = fn(handle, c_time_stamp, byref(c_sample_value_type), byref(c_vgpu_count), c_samples) + _nvmlCheckReturn(ret) + + return c_samples[0:c_vgpu_count.value] + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetVgpuInstancesUtilizationInfo(handle, timeStamp): + # first call to get the size + c_time_stamp = c_ulonglong(timeStamp) + c_vgpuUtilInfo = c_nvmlVgpuInstancesUtilizationInfo_v1_t(0) + c_vgpuUtilInfo.version = VgpuInstancesUtilizationInfo_v1 + c_vgpuUtilInfo.sampleValType = _nvmlValueType_t() + c_vgpuUtilInfo.vgpuInstanceCount = c_uint(0) + c_vgpuUtilInfo.lastSeenTimeStamp = c_time_stamp + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuInstancesUtilizationInfo") + ret = fn(handle, byref(c_vgpuUtilInfo)) + + if (ret == NVML_SUCCESS): + # special case, no active vGPUs + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + sampleArray = c_vgpuUtilInfo.vgpuInstanceCount * c_nvmlVgpuInstanceUtilizationInfo_v1_t + c_samples = sampleArray() + c_vgpuUtilInfo.vgpuUtilArray = c_samples + + # make the call again + ret = fn(handle, byref(c_vgpuUtilInfo)) + _nvmlCheckReturn(ret) + + return c_samples[0:c_vgpuUtilInfo.vgpuInstanceCount] + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetP2PStatus(device1, device2, p2pIndex): + c_p2pstatus = _nvmlGpuP2PStatus_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetP2PStatus") + ret = fn(device1, device2,p2pIndex, byref(c_p2pstatus)) + _nvmlCheckReturn(ret) + return c_p2pstatus.value + +def nvmlDeviceGetGridLicensableFeatures_v4(handle): + c_get_grid_licensable_features = c_nvmlGridLicensableFeatures_v4_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGridLicensableFeatures_v4") + ret = fn(handle, byref(c_get_grid_licensable_features)) + _nvmlCheckReturn(ret) + + return (c_get_grid_licensable_features) + +def nvmlDeviceGetGridLicensableFeatures(handle): + return nvmlDeviceGetGridLicensableFeatures_v4(handle) + +def nvmlDeviceGetGspFirmwareVersion(handle, version=None): + isUserDefined = version is not None + if not isUserDefined: + version = (c_char * NVML_GSP_FIRMWARE_VERSION_BUF_SIZE)() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGspFirmwareVersion") + ret = fn(handle, version) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isUserDefined else version.value + +def nvmlDeviceGetGspFirmwareMode(handle, isEnabled=c_uint(), defaultMode=c_uint()): + isReference = type(isEnabled) is not c_uint + isEnabledRef = isEnabled if isReference else byref(isEnabled) + defaultModeRef = defaultMode if isReference else byref(defaultMode) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGspFirmwareMode") + ret = fn(handle, isEnabledRef, defaultModeRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else [isEnabled.value, defaultMode.value] + +def nvmlDeviceGetEncoderCapacity(handle, encoderQueryType): + c_encoder_capacity = c_ulonglong(0) + c_encoderQuery_type = _nvmlEncoderQueryType_t(encoderQueryType) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetEncoderCapacity") + ret = fn(handle, c_encoderQuery_type, byref(c_encoder_capacity)) + _nvmlCheckReturn(ret) + return c_encoder_capacity.value + +def nvmlDeviceGetVgpuProcessUtilization(handle, timeStamp): + # first call to get the size + c_vgpu_count = c_uint(0) + c_time_stamp = c_ulonglong(timeStamp) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuProcessUtilization") + ret = fn(handle, c_time_stamp, byref(c_vgpu_count), None) + + if (ret == NVML_SUCCESS): + # special case, no active vGPUs + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + sampleArray = c_vgpu_count.value * c_nvmlVgpuProcessUtilizationSample_t + c_samples = sampleArray() + + # make the call again + ret = fn(handle, c_time_stamp, byref(c_vgpu_count), c_samples) + _nvmlCheckReturn(ret) + + return c_samples[0:c_vgpu_count.value] + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetVgpuProcessesUtilizationInfo(handle, timeStamp): + # first call to get the size + c_time_stamp = c_ulonglong(timeStamp) + c_vgpuProcUtilInfo = c_nvmlVgpuProcessesUtilizationInfo_v1_t(0) + c_vgpuProcUtilInfo.version = VgpuProcessesUtilizationInfo_v1 + c_vgpuProcUtilInfo.vgpuProcessCount = c_uint(0) + c_vgpuProcUtilInfo.lastSeenTimeStamp = c_time_stamp + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuProcessesUtilizationInfo") + ret = fn(handle, byref(c_vgpuProcUtilInfo)) + + if (ret == NVML_SUCCESS): + # special case, no active vGPUs + return [] + elif (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + sampleArray = c_vgpuProcUtilInfo.vgpuProcessCount * c_nvmlVgpuProcessUtilizationInfo_v1_t + c_samples = sampleArray() + c_vgpuProcUtilInfo.vgpuProcUtilArray = c_samples + + # make the call again + ret = fn(handle, byref(c_vgpuProcUtilInfo)) + _nvmlCheckReturn(ret) + + return c_samples[0:c_vgpuProcUtilInfo.vgpuProcessCount] + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetEncoderStats(handle): + c_encoderCount = c_ulonglong(0) + c_encodeFps = c_ulonglong(0) + c_encoderLatency = c_ulonglong(0) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetEncoderStats") + ret = fn(handle, byref(c_encoderCount), byref(c_encodeFps), byref(c_encoderLatency)) + _nvmlCheckReturn(ret) + return (c_encoderCount.value, c_encodeFps.value, c_encoderLatency.value) + +def nvmlDeviceGetEncoderSessions(handle): + # first call to get the size + c_session_count = c_uint(0) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetEncoderSessions") + ret = fn(handle, byref(c_session_count), None) + + if (ret == NVML_SUCCESS): + if (c_session_count.value != 0): + # typical case + session_array = c_nvmlEncoderSession_t * c_session_count.value + c_sessions = session_array() + + # make the call again + ret = fn(handle, byref(c_session_count), c_sessions) + _nvmlCheckReturn(ret) + sessions = [] + for i in range(c_session_count.value): + sessions.append(c_sessions[i]) + return sessions + else: + return [] # no active sessions + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetFBCStats(handle): + c_fbcStats = c_nvmlFBCStats_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetFBCStats") + ret = fn(handle, byref(c_fbcStats)) + _nvmlCheckReturn(ret) + return c_fbcStats + +def nvmlDeviceGetFBCSessions(handle): + # first call to get the size + c_session_count = c_uint(0) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetFBCSessions") + ret = fn(handle, byref(c_session_count), None) + + if (ret == NVML_SUCCESS): + if (c_session_count.value != 0): + # typical case + session_array = c_nvmlFBCSession_t * c_session_count.value + c_sessions = session_array() + + # make the call again + ret = fn(handle, byref(c_session_count), c_sessions) + _nvmlCheckReturn(ret) + sessions = [] + for i in range(c_session_count.value): + sessions.append(c_sessions[i]) + return sessions + else: + return [] # no active sessions + else: + # error case + raise NVMLError(ret) + +def nvmlVgpuInstanceGetEncoderStats(vgpuInstance): + c_encoderCount = c_ulonglong(0) + c_encodeFps = c_ulonglong(0) + c_encoderLatency = c_ulonglong(0) + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetEncoderStats") + ret = fn(vgpuInstance, byref(c_encoderCount), byref(c_encodeFps), byref(c_encoderLatency)) + _nvmlCheckReturn(ret) + return (c_encoderCount.value, c_encodeFps.value, c_encoderLatency.value) + +def nvmlVgpuInstanceGetEncoderSessions(vgpuInstance): + # first call to get the size + c_session_count = c_uint(0) + + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetEncoderSessions") + ret = fn(vgpuInstance, byref(c_session_count), None) + + if (ret == NVML_SUCCESS): + if (c_session_count.value != 0): + # typical case + session_array = c_nvmlEncoderSession_t * c_session_count.value + c_sessions = session_array() + + # make the call again + ret = fn(vgpuInstance, byref(c_session_count), c_sessions) + _nvmlCheckReturn(ret) + sessions = [] + for i in range(c_session_count.value): + sessions.append(c_sessions[i]) + return sessions + else: + return [] # no active sessions + else: + # error case + raise NVMLError(ret) + +def nvmlVgpuInstanceGetFBCStats(vgpuInstance): + c_fbcStats = c_nvmlFBCStats_t() + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetFBCStats") + ret = fn(vgpuInstance, byref(c_fbcStats)) + _nvmlCheckReturn(ret) + return c_fbcStats + +def nvmlVgpuInstanceGetFBCSessions(vgpuInstance): + # first call to get the size + c_session_count = c_uint(0) + + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetFBCSessions") + ret = fn(vgpuInstance, byref(c_session_count), None) + + if (ret == NVML_SUCCESS): + if (c_session_count.value != 0): + # typical case + session_array = c_nvmlFBCSession_t * c_session_count.value + c_sessions = session_array() + + # make the call again + ret = fn(vgpuInstance, byref(c_session_count), c_sessions) + _nvmlCheckReturn(ret) + sessions = [] + for i in range(c_session_count.value): + sessions.append(c_sessions[i]) + return sessions + else: + return [] # no active sessions + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetProcessUtilization(handle, timeStamp): + # first call to get the size + c_count = c_uint(0) + c_time_stamp = c_ulonglong(timeStamp) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetProcessUtilization") + ret = fn(handle, None, byref(c_count), c_time_stamp) + + if (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + sampleArray = c_count.value * c_nvmlProcessUtilizationSample_t + c_samples = sampleArray() + + # make the call again + ret = fn(handle, c_samples, byref(c_count), c_time_stamp) + _nvmlCheckReturn(ret) + + return c_samples[0:c_count.value] + else: + # error case + raise NVMLError(ret) + +def nvmlDeviceGetProcessesUtilizationInfo(handle, timeStamp): + # first call to get the size + c_time_stamp = c_ulonglong(timeStamp) + c_processesUtilInfo = c_nvmlProcessesUtilizationInfo_v1_t(0) + c_processesUtilInfo.version = ProcessesUtilizationInfo_v1 + c_processesUtilInfo.processSamplesCount = c_uint(0) + c_processesUtilInfo.lastSeenTimeStamp = c_time_stamp + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetProcessesUtilizationInfo") + ret = fn(handle, byref(c_processesUtilInfo)) + + if (ret == NVML_ERROR_INSUFFICIENT_SIZE): + # typical case + sampleArray = c_processesUtilInfo.processSamplesCount * c_nvmlProcessUtilizationInfo_v1_t + c_samples = sampleArray() + c_processesUtilInfo.procUtilArray = c_samples + + # make the call again + ret = fn(handle, byref(c_processesUtilInfo)) + _nvmlCheckReturn(ret) + + return c_samples[0:c_processesUtilInfo.processSamplesCount] + else: + # error case + raise NVMLError(ret) + +def nvmlVgpuInstanceGetMetadata(vgpuInstance): + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetMetadata") + c_vgpuMetadata = c_nvmlVgpuMetadata_t() + c_bufferSize = c_uint(0) + # Make the first NVML API call to get the c_bufferSize value. + # We have already allocated required buffer above. + ret = fn(vgpuInstance, byref(c_vgpuMetadata), byref(c_bufferSize)) + if (ret == NVML_ERROR_INSUFFICIENT_SIZE): + ret = fn(vgpuInstance, byref(c_vgpuMetadata), byref(c_bufferSize)) + _nvmlCheckReturn(ret) + else: + raise NVMLError(ret) + return c_vgpuMetadata + +def nvmlDeviceGetVgpuMetadata(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuMetadata") + c_vgpuPgpuMetadata = c_nvmlVgpuPgpuMetadata_t() + c_bufferSize = c_uint(0) + # Make the first NVML API call to get the c_bufferSize value. + # We have already allocated required buffer above. + ret = fn(handle, byref(c_vgpuPgpuMetadata), byref(c_bufferSize)) + if (ret == NVML_ERROR_INSUFFICIENT_SIZE): + ret = fn(handle, byref(c_vgpuPgpuMetadata), byref(c_bufferSize)) + _nvmlCheckReturn(ret) + else: + raise NVMLError(ret) + return c_vgpuPgpuMetadata + +def nvmlGetVgpuCompatibility(vgpuMetadata, pgpuMetadata): + fn = _nvmlGetFunctionPointer("nvmlGetVgpuCompatibility") + c_vgpuPgpuCompatibility = c_nvmlVgpuPgpuCompatibility_t() + ret = fn(byref(vgpuMetadata), byref(pgpuMetadata), byref(c_vgpuPgpuCompatibility)) + _nvmlCheckReturn(ret) + return c_vgpuPgpuCompatibility + +@convertStrBytes +def nvmlDeviceGetPgpuMetadataString(handle): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPgpuMetadataString") + c_pgpuMetadata = create_string_buffer(NVML_VGPU_PGPU_METADATA_OPAQUE_DATA_SIZE) + c_bufferSize = c_uint(0) + # Make the first NVML API call to get the c_bufferSize value. + # We have already allocated required buffer above. + ret = fn(handle, byref(c_pgpuMetadata), byref(c_bufferSize)) + if (ret == NVML_ERROR_INSUFFICIENT_SIZE): + ret = fn(handle, byref(c_pgpuMetadata), byref(c_bufferSize)) + _nvmlCheckReturn(ret) + else: + raise NVMLError(ret) + return (c_pgpuMetadata.value, c_bufferSize.value) + +def nvmlDeviceGetVgpuSchedulerLog(handle): + c_vgpu_sched_log = c_nvmlVgpuSchedulerLog_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuSchedulerLog") + ret = fn(handle, byref(c_vgpu_sched_log)) + _nvmlCheckReturn(ret) + return c_vgpu_sched_log + +def nvmlDeviceGetVgpuSchedulerState(handle): + c_vgpu_sched_state = c_nvmlVgpuSchedulerGetState_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuSchedulerState") + ret = fn(handle, byref(c_vgpu_sched_state)) + _nvmlCheckReturn(ret) + return c_vgpu_sched_state + +def nvmlDeviceGetVgpuSchedulerCapabilities(handle): + c_vgpu_sched_caps = c_nvmlVgpuSchedulerCapabilities_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetVgpuSchedulerCapabilities") + ret = fn(handle, byref(c_vgpu_sched_caps)) + _nvmlCheckReturn(ret) + return c_vgpu_sched_caps + +def nvmlDeviceSetVgpuSchedulerState(handle, sched_state): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetVgpuSchedulerState") + ret = fn(handle, byref(sched_state)) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlSetVgpuVersion(vgpuVersion): + fn = _nvmlGetFunctionPointer("nvmlSetVgpuVersion") + ret = fn(byref(vgpuVersion)) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlGetVgpuVersion(supported=None, current=None): + isUserDefined = (supported is not None) or (current is not None) + if not isUserDefined: + supported = c_nvmlVgpuVersion_t() + current = c_nvmlVgpuVersion_t() + fn = _nvmlGetFunctionPointer("nvmlGetVgpuVersion") + ret = fn(byref(supported), byref(current)) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isUserDefined else [(supported.minVersion, + supported.maxVersion), + (current.minVersion, + current.maxVersion)] + +def nvmlVgpuInstanceGetAccountingMode(vgpuInstance): + c_mode = _nvmlEnableState_t() + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetAccountingMode") + ret = fn(vgpuInstance, byref(c_mode)) + _nvmlCheckReturn(ret) + return c_mode.value + +def nvmlVgpuInstanceGetAccountingPids(vgpuInstance): + c_pidCount = c_uint() + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetAccountingPids") + ret = fn(vgpuInstance, byref(c_pidCount), None) + if (ret == NVML_ERROR_INSUFFICIENT_SIZE): + sampleArray = c_pidCount.value * c_uint + c_pidArray = sampleArray() + ret = fn(vgpuInstance, byref(c_pidCount), byref(c_pidArray)) + _nvmlCheckReturn(ret) + else: + raise NVMLError(ret) + return (c_pidCount, c_pidArray) + +def nvmlVgpuInstanceGetAccountingStats(vgpuInstance, pid): + c_accountingStats = c_nvmlAccountingStats_t() + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceGetAccountingStats") + ret = fn(vgpuInstance, pid, byref(c_accountingStats)) + _nvmlCheckReturn(ret) + return c_accountingStats + +def nvmlVgpuInstanceClearAccountingPids(vgpuInstance): + fn = _nvmlGetFunctionPointer("nvmlVgpuInstanceClearAccountingPids") + ret = fn(vgpuInstance) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlGetExcludedDeviceCount(): + c_count = c_uint() + fn = _nvmlGetFunctionPointer("nvmlGetExcludedDeviceCount") + ret = fn(byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlGetExcludedDeviceInfoByIndex(index): + c_index = c_uint(index) + info = c_nvmlExcludedDeviceInfo_t() + fn = _nvmlGetFunctionPointer("nvmlGetExcludedDeviceInfoByIndex") + ret = fn(c_index, byref(info)) + _nvmlCheckReturn(ret) + return info + +def nvmlDeviceGetHostVgpuMode(handle): + c_host_vgpu_mode = _nvmlHostVgpuMode_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetHostVgpuMode") + ret = fn(handle, byref(c_host_vgpu_mode)) + _nvmlCheckReturn(ret) + return c_host_vgpu_mode.value + +def nvmlDeviceSetMigMode(device, mode): + c_activationStatus = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceSetMigMode") + ret = fn(device, mode, byref(c_activationStatus)) + _nvmlCheckReturn(ret) + return c_activationStatus.value + +def nvmlDeviceGetMigMode(device): + c_currentMode = c_uint() + c_pendingMode = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMigMode") + ret = fn(device, byref(c_currentMode), byref(c_pendingMode)) + _nvmlCheckReturn(ret) + return [c_currentMode.value, c_pendingMode.value] + +def nvmlDeviceGetGpuInstanceProfileInfo(device, profile, version=2): + if version == 2: + c_info = c_nvmlGpuInstanceProfileInfo_v2_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuInstanceProfileInfoV") + elif version == 1: + c_info = c_nvmlGpuInstanceProfileInfo_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuInstanceProfileInfo") + else: + raise NVMLError(NVML_ERROR_FUNCTION_NOT_FOUND) + ret = fn(device, profile, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +# Define function alias for the API exposed by NVML +nvmlDeviceGetGpuInstanceProfileInfoV = nvmlDeviceGetGpuInstanceProfileInfo + +def nvmlDeviceGetGpuInstanceRemainingCapacity(device, profileId): + c_count = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuInstanceRemainingCapacity") + ret = fn(device, profileId, byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlDeviceGetGpuInstancePossiblePlacements(device, profileId, placementsRef, countRef): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuInstancePossiblePlacements_v2") + ret = fn(device, profileId, placementsRef, countRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceCreateGpuInstance(device, profileId): + c_instance = c_nvmlGpuInstance_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceCreateGpuInstance") + ret = fn(device, profileId, byref(c_instance)) + _nvmlCheckReturn(ret) + return c_instance + +def nvmlDeviceCreateGpuInstanceWithPlacement(device, profileId, placement): + c_instance = c_nvmlGpuInstance_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceCreateGpuInstanceWithPlacement") + ret = fn(device, profileId, placement, byref(c_instance)) + _nvmlCheckReturn(ret) + return c_instance + +def nvmlGpuInstanceDestroy(gpuInstance): + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceDestroy") + ret = fn(gpuInstance) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetGpuInstances(device, profileId, gpuInstancesRef, countRef): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuInstances") + ret = fn(device, profileId, gpuInstancesRef, countRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetGpuInstanceById(device, gpuInstanceId): + c_instance = c_nvmlGpuInstance_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuInstanceById") + ret = fn(device, gpuInstanceId, byref(c_instance)) + _nvmlCheckReturn(ret) + return c_instance + +def nvmlGpuInstanceGetInfo(gpuInstance): + c_info = c_nvmlGpuInstanceInfo_t() + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceGetInfo") + ret = fn(gpuInstance, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +def nvmlGpuInstanceGetComputeInstanceProfileInfo(device, profile, engProfile, version=2): + if version == 2: + c_info = c_nvmlComputeInstanceProfileInfo_v2_t() + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceGetComputeInstanceProfileInfoV") + elif version == 1: + c_info = c_nvmlComputeInstanceProfileInfo_t() + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceGetComputeInstanceProfileInfo") + else: + raise NVMLError(NVML_ERROR_FUNCTION_NOT_FOUND) + ret = fn(device, profile, engProfile, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +# Define function alias for the API exposed by NVML +nvmlGpuInstanceGetComputeInstanceProfileInfoV = nvmlGpuInstanceGetComputeInstanceProfileInfo + +def nvmlGpuInstanceGetComputeInstanceRemainingCapacity(gpuInstance, profileId): + c_count = c_uint() + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceGetComputeInstanceRemainingCapacity") + ret = fn(gpuInstance, profileId, byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlGpuInstanceGetComputeInstancePossiblePlacements(gpuInstance, profileId, placementsRef, countRef): + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceGetComputeInstancePossiblePlacements") + ret = fn(gpuInstance, profileId, placementsRef, countRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlGpuInstanceCreateComputeInstance(gpuInstance, profileId): + c_instance = c_nvmlComputeInstance_t() + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceCreateComputeInstance") + ret = fn(gpuInstance, profileId, byref(c_instance)) + _nvmlCheckReturn(ret) + return c_instance + +def nvmlGpuInstanceCreateComputeInstanceWithPlacement(gpuInstance, profileId, placement): + c_instance = c_nvmlComputeInstance_t() + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceCreateComputeInstanceWithPlacement") + ret = fn(gpuInstance, profileId, placement, byref(c_instance)) + _nvmlCheckReturn(ret) + return c_instance + +def nvmlComputeInstanceDestroy(computeInstance): + fn = _nvmlGetFunctionPointer("nvmlComputeInstanceDestroy") + ret = fn(computeInstance) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlGpuInstanceGetComputeInstances(gpuInstance, profileId, computeInstancesRef, countRef): + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceGetComputeInstances") + ret = fn(gpuInstance, profileId, computeInstancesRef, countRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlGpuInstanceGetComputeInstanceById(gpuInstance, computeInstanceId): + c_instance = c_nvmlComputeInstance_t() + fn = _nvmlGetFunctionPointer("nvmlGpuInstanceGetComputeInstanceById") + ret = fn(gpuInstance, computeInstanceId, byref(c_instance)) + _nvmlCheckReturn(ret) + return c_instance + +def nvmlComputeInstanceGetInfo_v2(computeInstance): + c_info = c_nvmlComputeInstanceInfo_t() + fn = _nvmlGetFunctionPointer("nvmlComputeInstanceGetInfo_v2") + ret = fn(computeInstance, byref(c_info)) + _nvmlCheckReturn(ret) + return c_info + +def nvmlComputeInstanceGetInfo(computeInstance): + return nvmlComputeInstanceGetInfo_v2(computeInstance) + +def nvmlDeviceIsMigDeviceHandle(device): + c_isMigDevice = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceIsMigDeviceHandle") + ret = fn(device, byref(c_isMigDevice)) + _nvmlCheckReturn(ret) + return c_isMigDevice + +def nvmlDeviceGetGpuInstanceId(device): + c_gpuInstanceId = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuInstanceId") + ret = fn(device, byref(c_gpuInstanceId)) + _nvmlCheckReturn(ret) + return c_gpuInstanceId.value + +def nvmlDeviceGetComputeInstanceId(device): + c_computeInstanceId = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetComputeInstanceId") + ret = fn(device, byref(c_computeInstanceId)) + _nvmlCheckReturn(ret) + return c_computeInstanceId.value + +def nvmlDeviceGetMaxMigDeviceCount(device): + c_count = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMaxMigDeviceCount") + ret = fn(device, byref(c_count)) + _nvmlCheckReturn(ret) + return c_count.value + +def nvmlDeviceGetMigDeviceHandleByIndex(device, index): + c_index = c_uint(index) + migDevice = c_nvmlDevice_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMigDeviceHandleByIndex") + ret = fn(device, c_index, byref(migDevice)) + _nvmlCheckReturn(ret) + return migDevice + +def nvmlDeviceGetDeviceHandleFromMigDeviceHandle(migDevice): + device = c_nvmlDevice_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDeviceHandleFromMigDeviceHandle") + ret = fn(migDevice, byref(device)) + _nvmlCheckReturn(ret) + return device + +def nvmlDeviceGetAttributes_v2(device): + c_attrs = c_nvmlDeviceAttributes() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAttributes_v2") + ret = fn(device, byref(c_attrs)) + _nvmlCheckReturn(ret) + return c_attrs + +def nvmlDeviceGetAttributes(device): + return nvmlDeviceGetAttributes_v2(device) + +def nvmlDeviceGetRemappedRows(device): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetRemappedRows") + c_corr = c_uint() + c_unc = c_uint() + c_bpending = c_uint() + c_bfailure = c_uint() + ret = fn(device, byref(c_corr), byref(c_unc), byref(c_bpending), byref(c_bfailure)) + _nvmlCheckReturn(ret) + return (c_corr.value, c_unc.value, c_bpending.value, c_bfailure.value) + +def nvmlDeviceGetRowRemapperHistogram(device): + c_vals = c_nvmlRowRemapperHistogramValues() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetRowRemapperHistogram") + ret = fn(device, byref(c_vals)) + _nvmlCheckReturn(ret) + return c_vals + +def nvmlDeviceGetArchitecture(device): + arch = _nvmlDeviceArchitecture_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetArchitecture") + ret = fn(device, byref(arch)) + _nvmlCheckReturn(ret) + return arch.value + +def nvmlDeviceGetBusType(device): + c_busType = _nvmlBusType_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetBusType") + ret = fn(device, byref(c_busType)) + _nvmlCheckReturn(ret) + return c_busType.value + +def nvmlDeviceGetIrqNum(device): + c_irqNum = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetIrqNum") + ret = fn(device, byref(c_irqNum)) + _nvmlCheckReturn(ret) + return c_irqNum.value + +def nvmlDeviceGetNumGpuCores(device): + c_numCores = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNumGpuCores") + ret = fn(device, byref(c_numCores)) + _nvmlCheckReturn(ret) + return c_numCores.value + +def nvmlDeviceGetPowerSource(device): + c_powerSource = _nvmlPowerSource_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPowerSource") + ret = fn(device, byref(c_powerSource)) + _nvmlCheckReturn(ret) + return c_powerSource.value + +def nvmlDeviceGetMemoryBusWidth(device): + c_memBusWidth = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMemoryBusWidth") + ret = fn(device, byref(c_memBusWidth)) + _nvmlCheckReturn(ret) + return c_memBusWidth.value + +def nvmlDeviceGetPcieLinkMaxSpeed(device): + c_speed = _nvmlPcieLinkMaxSpeed_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPcieLinkMaxSpeed") + ret = fn(device, byref(c_speed)) + _nvmlCheckReturn(ret) + return c_speed.value + +def nvmlDeviceGetAdaptiveClockInfoStatus(device): + c_adaptiveClockInfoStatus = _nvmlAdaptiveClockInfoStatus_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetAdaptiveClockInfoStatus") + ret = fn(device, byref(c_adaptiveClockInfoStatus)) + _nvmlCheckReturn(ret) + return c_adaptiveClockInfoStatus.value + +def nvmlDeviceGetPcieSpeed(device): + c_speed = c_uint() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPcieSpeed") + ret = fn(device, byref(c_speed)) + _nvmlCheckReturn(ret) + return c_speed.value + +def nvmlDeviceGetDynamicPstatesInfo(device, c_dynamicpstatesinfo=c_nvmlGpuDynamicPstatesInfo_t()): + isReference = type(c_dynamicpstatesinfo) is not c_nvmlGpuDynamicPstatesInfo_t + dynamicpstatesinfoRef = c_dynamicpstatesinfo if isReference else byref(c_dynamicpstatesinfo) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDynamicPstatesInfo"); + ret = fn(device, dynamicpstatesinfoRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else c_dynamicpstatesinfo + +def nvmlDeviceSetFanSpeed_v2(handle, index, speed): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetFanSpeed_v2"); + ret = fn(handle, index, speed) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetThermalSettings(device, sensorindex, c_thermalsettings=c_nvmlGpuThermalSettings_t()): + isReference = type(c_thermalsettings) is not c_nvmlGpuThermalSettings_t + thermalsettingsRef = c_thermalsettings if isReference else byref(c_thermalsettings) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetThermalSettings"); + ret = fn(device, sensorindex, thermalsettingsRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else c_thermalsettings.sensor[:] + +def nvmlDeviceGetMinMaxClockOfPState(device, clockType, pstate, minClockMHz=c_uint(), maxClockMHz=c_uint()): + isReference = (type(minClockMHz) is not c_uint) or (type(maxClockMHz) is not c_uint) + minClockMHzRef = minClockMHz if isReference else byref(minClockMHz) + maxClockMHzRef = maxClockMHz if isReference else byref(maxClockMHz) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMinMaxClockOfPState"); + ret = fn(device, _nvmlClockType_t(clockType), _nvmlClockType_t(pstate), minClockMHzRef, maxClockMHzRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else (minClockMHz.value, maxClockMHz.value) + +class c_nvmlClockOffset_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('type', _nvmlClockType_t), + ('pstate', _nvmlPstates_t), + ('clockOffsetMHz', c_int), + ('minClockOffsetMHz', c_int), + ('maxClockOffsetMHz', c_int), + ] + +nvmlClockOffset_v1 = 0x1000018 + +def nvmlDeviceGetClockOffsets(device, info): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetClockOffsets"); + ret = fn(device, info) + return NVML_SUCCESS + +def nvmlDeviceSetClockOffsets(device, info): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetClockOffsets"); + ret = fn(device, info) + return NVML_SUCCESS + +def nvmlDeviceGetSupportedPerformanceStates(device): + pstates = [] + c_count = c_uint(NVML_MAX_GPU_PERF_PSTATES) + c_size = sizeof(c_uint)*c_count.value + + # NOTE: use 'c_uint' to represent the size of the nvmlPstate_t enumeration. + pstates_array = _nvmlPstates_t * c_count.value + c_pstates = pstates_array() + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSupportedPerformanceStates") + ret = fn(device, c_pstates, c_size) + _nvmlCheckReturn(ret) + + for value in c_pstates: + if value != NVML_PSTATE_UNKNOWN: + pstates.append(value) + + return pstates + +def nvmlDeviceGetGpcClkVfOffset(device): + offset = c_int32() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpcClkVfOffset") + ret = fn(device, byref(offset)) + _nvmlCheckReturn(ret) + return offset.value + +def nvmlDeviceSetGpcClkVfOffset(device, offset): + c_offset = c_int32(offset) + fn = _nvmlGetFunctionPointer("nvmlDeviceSetGpcClkVfOffset") + ret = fn(device, c_offset) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetGpcClkMinMaxVfOffset(device, minOffset=c_int(), maxOffset=c_int()): + isReference = (type(minOffset) is not c_int) or (type(maxOffset) is not c_int) + minOffsetRef = minOffset if isReference else byref(minOffset) + maxOffsetRef = maxOffset if isReference else byref(maxOffset) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpcClkMinMaxVfOffset") + ret = fn(device, minOffsetRef, maxOffsetRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else (minOffset.value, maxOffset.value) + +def nvmlDeviceGetMemClkVfOffset(device): + offset = c_int32() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMemClkVfOffset") + ret = fn(device, byref(offset)) + _nvmlCheckReturn(ret) + return offset.value + +def nvmlDeviceSetMemClkVfOffset(device, offset): + c_offset = c_int32(offset) + fn = _nvmlGetFunctionPointer("nvmlDeviceSetMemClkVfOffset") + ret = fn(device, c_offset) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetMemClkMinMaxVfOffset(device, minOffset=c_int(), maxOffset=c_int()): + isReference = (type(minOffset) is not c_int) or (type(maxOffset) is not c_int) + minOffsetRef = minOffset if isReference else byref(minOffset) + maxOffsetRef = maxOffset if isReference else byref(maxOffset) + + fn = _nvmlGetFunctionPointer("nvmlDeviceGetMemClkMinMaxVfOffset") + ret = fn(device, minOffsetRef, maxOffsetRef) + _nvmlCheckReturn(ret) + return NVML_SUCCESS if isReference else (minOffset.value, maxOffset.value) + +def nvmlSystemSetConfComputeGpusReadyState(state): + c_state = c_uint(state) + fn = _nvmlGetFunctionPointer("nvmlSystemSetConfComputeGpusReadyState") + ret = fn(c_state) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlSystemGetConfComputeGpusReadyState(): + c_state = c_uint() + fn = _nvmlGetFunctionPointer("nvmlSystemGetConfComputeGpusReadyState") + ret = fn(byref(c_state)) + _nvmlCheckReturn(ret) + return c_state.value + +def nvmlSystemGetConfComputeCapabilities(): + c_ccSysCaps = c_nvmlConfComputeSystemCaps_t() + fn = _nvmlGetFunctionPointer("nvmlSystemGetConfComputeCapabilities") + ret = fn(byref(c_ccSysCaps)) + _nvmlCheckReturn(ret) + return c_ccSysCaps + +def nvmlSystemGetConfComputeState(): + c_state = c_nvmlConfComputeSystemState_t() + fn = _nvmlGetFunctionPointer("nvmlSystemGetConfComputeState") + ret = fn(byref(c_state)) + _nvmlCheckReturn(ret) + return c_state + +def nvmlSystemGetConfComputeSettings(settings): + fn = _nvmlGetFunctionPointer("nvmlSystemGetConfComputeSettings") + return fn(settings) + +def nvmlDeviceSetConfComputeUnprotectedMemSize(device, c_ccMemSize): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetConfComputeUnprotectedMemSize") + ret = fn(device, c_ccMemSize) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetConfComputeMemSizeInfo(device): + c_ccMemSize = c_nvmlConfComputeMemSizeInfo_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetConfComputeMemSizeInfo") + ret = fn(device, byref(c_ccMemSize)) + _nvmlCheckReturn(ret) + return c_ccMemSize + +def nvmlDeviceGetConfComputeProtectedMemoryUsage(device): + c_memory = c_nvmlMemory_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetConfComputeProtectedMemoryUsage") + ret = fn(device, byref(c_memory)) + _nvmlCheckReturn(ret) + return c_memory + +def nvmlDeviceGetConfComputeGpuCertificate(device): + c_cert = c_nvmlConfComputeGpuCertificate_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetConfComputeGpuCertificate") + ret = fn(device, byref(c_cert)) + _nvmlCheckReturn(ret) + return c_cert + +def nvmlDeviceGetConfComputeGpuAttestationReport(device, c_nonce): + c_attestReport = c_nvmlConfComputeGpuAttestationReport_t() + c_nonce_arr = (c_uint8 * len(c_nonce))(*(c_nonce)) + setattr(c_attestReport, 'nonce', c_nonce_arr) + fn = _nvmlGetFunctionPointer("nvmlDeviceGetConfComputeGpuAttestationReport") + ret = fn(device, byref(c_attestReport)) + _nvmlCheckReturn(ret) + return c_attestReport + +def nvmlSystemSetConfComputeKeyRotationThresholdInfo(max_atk_adv): + c_keyRotationThrInfo = c_nvmlConfComputeSetKeyRotationThresholdInfo_t(0) + c_keyRotationThrInfo.version = ConfComputeSetKeyRotationThresholdInfo_v1 + c_keyRotationThrInfo.maxAttackerAdvantage = max_atk_adv + fn = _nvmlGetFunctionPointer("nvmlSystemSetConfComputeKeyRotationThresholdInfo") + ret = fn(byref(c_keyRotationThrInfo)) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlSystemGetConfComputeKeyRotationThresholdInfo(): + c_keyRotationThrInfo = c_nvmlConfComputeGetKeyRotationThresholdInfo_t(0) + c_keyRotationThrInfo.version = ConfComputeGetKeyRotationThresholdInfo_v1 + fn = _nvmlGetFunctionPointer("nvmlSystemGetConfComputeKeyRotationThresholdInfo") + ret = fn(byref(c_keyRotationThrInfo)) + _nvmlCheckReturn(ret) + return c_keyRotationThrInfo + +## GPM ## +######### + +## Enums/defines + +#### GPM Metric Identifiers +NVML_GPM_METRIC_GRAPHICS_UTIL = 1 # Percentage of time any compute/graphics app was active on the GPU. 0.0 - 100.0 +NVML_GPM_METRIC_SM_UTIL = 2 # Percentage of SMs that were busy. 0.0 - 100.0 +NVML_GPM_METRIC_SM_OCCUPANCY = 3 # Percentage of warps that were active vs theoretical maximum. 0.0 - 100.0 +NVML_GPM_METRIC_INTEGER_UTIL = 4 # Percentage of time the GPU's SMs were doing integer operations. 0.0 - 100.0 +NVML_GPM_METRIC_ANY_TENSOR_UTIL = 5 # Percentage of time the GPU's SMs were doing ANY tensor operations. 0.0 - 100.0 +NVML_GPM_METRIC_DFMA_TENSOR_UTIL = 6 # Percentage of time the GPU's SMs were doing DFMA tensor operations. 0.0 - 100.0 +NVML_GPM_METRIC_HMMA_TENSOR_UTIL = 7 # Percentage of time the GPU's SMs were doing HMMA tensor operations. 0.0 - 100.0 +NVML_GPM_METRIC_IMMA_TENSOR_UTIL = 9 # Percentage of time the GPU's SMs were doing IMMA tensor operations. 0.0 - 100.0 +NVML_GPM_METRIC_DRAM_BW_UTIL = 10 # Percentage of DRAM bw used vs theoretical maximum. 0.0 - 100.0 +NVML_GPM_METRIC_FP64_UTIL = 11 # Percentage of time the GPU's SMs were doing non-tensor FP64 math. 0.0 - 100.0 +NVML_GPM_METRIC_FP32_UTIL = 12 # Percentage of time the GPU's SMs were doing non-tensor FP32 math. 0.0 - 100.0 +NVML_GPM_METRIC_FP16_UTIL = 13 # Percentage of time the GPU's SMs were doing non-tensor FP16 math. 0.0 - 100.0 +NVML_GPM_METRIC_PCIE_TX_PER_SEC = 20 # PCIe traffic from this GPU in MiB/sec +NVML_GPM_METRIC_PCIE_RX_PER_SEC = 21 # PCIe traffic to this GPU in MiB/sec +NVML_GPM_METRIC_NVDEC_0_UTIL = 30 # Percent utilization of NVDEC 0. 0.0 - 100.0 +NVML_GPM_METRIC_NVDEC_1_UTIL = 31 # Percent utilization of NVDEC 1. 0.0 - 100.0 +NVML_GPM_METRIC_NVDEC_2_UTIL = 32 # Percent utilization of NVDEC 2. 0.0 - 100.0 +NVML_GPM_METRIC_NVDEC_3_UTIL = 33 # Percent utilization of NVDEC 3. 0.0 - 100.0 +NVML_GPM_METRIC_NVDEC_4_UTIL = 34 # Percent utilization of NVDEC 4. 0.0 - 100.0 +NVML_GPM_METRIC_NVDEC_5_UTIL = 35 # Percent utilization of NVDEC 5. 0.0 - 100.0 +NVML_GPM_METRIC_NVDEC_6_UTIL = 36 # Percent utilization of NVDEC 6. 0.0 - 100.0 +NVML_GPM_METRIC_NVDEC_7_UTIL = 37 # Percent utilization of NVDEC 7. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_0_UTIL = 40 # Percent utilization of NVJPG 0. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_1_UTIL = 41 # Percent utilization of NVJPG 1. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_2_UTIL = 42 # Percent utilization of NVJPG 2. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_3_UTIL = 43 # Percent utilization of NVJPG 3. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_4_UTIL = 44 # Percent utilization of NVJPG 4. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_5_UTIL = 45 # Percent utilization of NVJPG 5. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_6_UTIL = 46 # Percent utilization of NVJPG 6. 0.0 - 100.0 +NVML_GPM_METRIC_NVJPG_7_UTIL = 47 # Percent utilization of NVJPG 7. 0.0 - 100.0 +NVML_GPM_METRIC_NVOFA_0_UTIL = 50 # Percent utilization of NVOFA 0. 0.0 - 100.0 +NVML_GPM_METRIC_NVOFA_1_UTIL = 51 # Percent utilization of NVOFA 1. 0.0 - 100.0 +NVML_GPM_METRIC_NVLINK_TOTAL_RX_PER_SEC = 60 # NvLink read bandwidth for all links in MiB/sec +NVML_GPM_METRIC_NVLINK_TOTAL_TX_PER_SEC = 61 # NvLink write bandwidth for all links in MiB/sec +NVML_GPM_METRIC_NVLINK_L0_RX_PER_SEC = 62 # NvLink read bandwidth for link 0 in MiB/sec +NVML_GPM_METRIC_NVLINK_L0_TX_PER_SEC = 63 # NvLink write bandwidth for link 0 in MiB/sec +NVML_GPM_METRIC_NVLINK_L1_RX_PER_SEC = 64 # NvLink read bandwidth for link 1 in MiB/sec +NVML_GPM_METRIC_NVLINK_L1_TX_PER_SEC = 65 # NvLink write bandwidth for link 1 in MiB/sec +NVML_GPM_METRIC_NVLINK_L2_RX_PER_SEC = 66 # NvLink read bandwidth for link 2 in MiB/sec +NVML_GPM_METRIC_NVLINK_L2_TX_PER_SEC = 67 # NvLink write bandwidth for link 2 in MiB/sec +NVML_GPM_METRIC_NVLINK_L3_RX_PER_SEC = 68 # NvLink read bandwidth for link 3 in MiB/sec +NVML_GPM_METRIC_NVLINK_L3_TX_PER_SEC = 69 # NvLink write bandwidth for link 3 in MiB/sec +NVML_GPM_METRIC_NVLINK_L4_RX_PER_SEC = 70 # NvLink read bandwidth for link 4 in MiB/sec +NVML_GPM_METRIC_NVLINK_L4_TX_PER_SEC = 71 # NvLink write bandwidth for link 4 in MiB/sec +NVML_GPM_METRIC_NVLINK_L5_RX_PER_SEC = 72 # NvLink read bandwidth for link 5 in MiB/sec +NVML_GPM_METRIC_NVLINK_L5_TX_PER_SEC = 73 # NvLink write bandwidth for link 5 in MiB/sec +NVML_GPM_METRIC_NVLINK_L6_RX_PER_SEC = 74 # NvLink read bandwidth for link 6 in MiB/sec +NVML_GPM_METRIC_NVLINK_L6_TX_PER_SEC = 75 # NvLink write bandwidth for link 6 in MiB/sec +NVML_GPM_METRIC_NVLINK_L7_RX_PER_SEC = 76 # NvLink read bandwidth for link 7 in MiB/sec +NVML_GPM_METRIC_NVLINK_L7_TX_PER_SEC = 77 # NvLink write bandwidth for link 7 in MiB/sec +NVML_GPM_METRIC_NVLINK_L8_RX_PER_SEC = 78 # NvLink read bandwidth for link 8 in MiB/sec +NVML_GPM_METRIC_NVLINK_L8_TX_PER_SEC = 79 # NvLink write bandwidth for link 8 in MiB/sec +NVML_GPM_METRIC_NVLINK_L9_RX_PER_SEC = 80 # NvLink read bandwidth for link 9 in MiB/sec +NVML_GPM_METRIC_NVLINK_L9_TX_PER_SEC = 81 # NvLink write bandwidth for link 9 in MiB/sec +NVML_GPM_METRIC_NVLINK_L10_RX_PER_SEC = 82 # NvLink read bandwidth for link 10 in MiB/sec +NVML_GPM_METRIC_NVLINK_L10_TX_PER_SEC = 83 # NvLink write bandwidth for link 10 in MiB/sec +NVML_GPM_METRIC_NVLINK_L11_RX_PER_SEC = 84 # NvLink read bandwidth for link 11 in MiB/sec +NVML_GPM_METRIC_NVLINK_L11_TX_PER_SEC = 85 # NvLink write bandwidth for link 11 in MiB/sec +NVML_GPM_METRIC_NVLINK_L12_RX_PER_SEC = 86 # NvLink read bandwidth for link 12 in MiB/sec +NVML_GPM_METRIC_NVLINK_L12_TX_PER_SEC = 87 # NvLink write bandwidth for link 12 in MiB/sec +NVML_GPM_METRIC_NVLINK_L13_RX_PER_SEC = 88 # NvLink read bandwidth for link 13 in MiB/sec +NVML_GPM_METRIC_NVLINK_L13_TX_PER_SEC = 89 # NvLink write bandwidth for link 13 in MiB/sec +NVML_GPM_METRIC_NVLINK_L14_RX_PER_SEC = 90 # NvLink read bandwidth for link 14 in MiB/sec +NVML_GPM_METRIC_NVLINK_L14_TX_PER_SEC = 91 # NvLink write bandwidth for link 14 in MiB/sec +NVML_GPM_METRIC_NVLINK_L15_RX_PER_SEC = 92 # NvLink read bandwidth for link 15 in MiB/sec +NVML_GPM_METRIC_NVLINK_L15_TX_PER_SEC = 93 # NvLink write bandwidth for link 15 in MiB/sec +NVML_GPM_METRIC_NVLINK_L16_RX_PER_SEC = 94 # NvLink read bandwidth for link 16 in MiB/sec +NVML_GPM_METRIC_NVLINK_L16_TX_PER_SEC = 95 # NvLink write bandwidth for link 16 in MiB/sec +NVML_GPM_METRIC_NVLINK_L17_RX_PER_SEC = 96 # NvLink read bandwidth for link 17 in MiB/sec +NVML_GPM_METRIC_NVLINK_L17_TX_PER_SEC = 97 # NvLink write bandwidth for link 17 in MiB/sec +NVML_GPM_METRIC_MAX = 98 + +## Structs + +class c_nvmlUnitInfo_t(_PrintableStructure): + _fields_ = [ + ('name', c_char * 96), + ('id', c_char * 96), + ('serial', c_char * 96), + ('firmwareVersion', c_char * 96), + ] + +class struct_c_nvmlGpmSample_t(Structure): + pass # opaque handle +c_nvmlGpmSample_t = POINTER(struct_c_nvmlGpmSample_t) + +class c_metricInfo_t(Structure): + _fields_ = [ + ("shortName", c_char_p), + ("longName", c_char_p), + ("unit", c_char_p), + ] + +class c_nvmlGpmMetric_t(_PrintableStructure): + _fields_ = [ + ('metricId', c_uint), + ('nvmlReturn', _nvmlReturn_t), + ('value', c_double), + ('metricInfo', c_metricInfo_t) + ] + +class c_nvmlGpmMetricsGet_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('numMetrics', c_uint), + ('sample1', c_nvmlGpmSample_t), + ('sample2', c_nvmlGpmSample_t), + ('metrics', c_nvmlGpmMetric_t * NVML_GPM_METRIC_MAX) + ] + +NVML_GPM_METRICS_GET_VERSION = 1 + +class c_nvmlGpmSupport_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('isSupportedDevice', c_uint), + ] + +NVML_GPM_SUPPORT_VERSION = 1 + +## Functions + +def nvmlGpmMetricsGet(metricsGet): + fn = _nvmlGetFunctionPointer("nvmlGpmMetricsGet") + ret = fn(byref(metricsGet)) + _nvmlCheckReturn(ret) + return metricsGet + +def nvmlGpmSampleFree(gpmSample): + fn = _nvmlGetFunctionPointer("nvmlGpmSampleFree") + ret = fn(gpmSample) + _nvmlCheckReturn(ret) + return + +def nvmlGpmSampleAlloc(): + gpmSample = c_nvmlGpmSample_t() + fn = _nvmlGetFunctionPointer("nvmlGpmSampleAlloc") + ret = fn(byref(gpmSample)) + _nvmlCheckReturn(ret) + return gpmSample + +def nvmlGpmSampleGet(device, gpmSample): + fn = _nvmlGetFunctionPointer("nvmlGpmSampleGet") + ret = fn(device, gpmSample) + _nvmlCheckReturn(ret) + return gpmSample + +def nvmlGpmMigSampleGet(device, gpuInstanceId, gpmSample): + fn = _nvmlGetFunctionPointer("nvmlGpmMigSampleGet") + ret = fn(device, gpuInstanceId, gpmSample) + _nvmlCheckReturn(ret) + return gpmSample + +def nvmlGpmQueryDeviceSupport(device): + gpmSupport = c_nvmlGpmSupport_t() + gpmSupport.version = NVML_GPM_SUPPORT_VERSION + fn = _nvmlGetFunctionPointer("nvmlGpmQueryDeviceSupport") + ret = fn(device, byref(gpmSupport)) + _nvmlCheckReturn(ret) + return gpmSupport + +def nvmlGpmSetStreamingEnabled(device, state): + c_state = c_uint(state) + fn = _nvmlGetFunctionPointer("nvmlGpmSetStreamingEnabled") + ret = fn(device, c_state) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlGpmQueryIfStreamingEnabled(device): + c_state = c_uint() + fn = _nvmlGetFunctionPointer("nvmlGpmQueryIfStreamingEnabled") + ret = fn(device, byref(c_state)) + _nvmlCheckReturn(ret) + return c_state.value + +# Low Power Structure and Function + +NVML_NVLINK_POWER_STATE_HIGH_SPEED = 0x0 +NVML_NVLINK_POWER_STATE_LOW = 0x1 + +NVML_NVLINK_LOW_POWER_THRESHOLD_MIN = 0x1 +NVML_NVLINK_LOW_POWER_THRESHOLD_MAX = 0x1FFF +NVML_NVLINK_LOW_POWER_THRESHOLD_RESET = 0xFFFFFFFF +NVML_NVLINK_LOW_POWER_THRESHOLD_DEFAULT = NVML_NVLINK_LOW_POWER_THRESHOLD_RESET + +class c_nvmlNvLinkPowerThres_t(Structure): + _fields_ = [ + ("lowPwrThreshold", c_uint), + ] + +def nvmlDeviceSetNvLinkDeviceLowPowerThreshold(device, l1threshold): + c_info = c_nvmlNvLinkPowerThres_t() + c_info.lowPwrThreshold = l1threshold + fn = _nvmlGetFunctionPointer("nvmlDeviceSetNvLinkDeviceLowPowerThreshold") + ret = fn(device, byref(c_info)) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +NVML_GPU_FABRIC_UUID_LEN = 16 + +_nvmlGpuFabricState_t = c_uint +NVML_GPU_FABRIC_STATE_NOT_SUPPORTED = 0 +NVML_GPU_FABRIC_STATE_NOT_STARTED = 1 +NVML_GPU_FABRIC_STATE_IN_PROGRESS = 2 +NVML_GPU_FABRIC_STATE_COMPLETED = 3 + +class c_nvmlGpuFabricInfo_t(_PrintableStructure): + _fields_ = [ + ("clusterUuid", c_char * NVML_DEVICE_UUID_BUFFER_SIZE), + ("status", _nvmlReturn_t), + ("cliqueId", c_uint32), + ("state", _nvmlGpuFabricState_t) + ] + +NVML_GPU_FABRIC_HEALTH_MASK_DEGRADED_BW_NOT_SUPPORTED = 0 +NVML_GPU_FABRIC_HEALTH_MASK_DEGRADED_BW_TRUE = 1 +NVML_GPU_FABRIC_HEALTH_MASK_DEGRADED_BW_FALSE = 2 +NVML_GPU_FABRIC_HEALTH_MASK_SHIFT_DEGRADED_BW = 0 +NVML_GPU_FABRIC_HEALTH_MASK_WIDTH_DEGRADED_BW = 0x11 + +NVML_GPU_FABRIC_HEALTH_MASK_ROUTE_RECOVERY_NOT_SUPPORTED = 0 +NVML_GPU_FABRIC_HEALTH_MASK_ROUTE_RECOVERY_TRUE = 1 +NVML_GPU_FABRIC_HEALTH_MASK_ROUTE_RECOVERY_FALSE = 2 +NVML_GPU_FABRIC_HEALTH_MASK_SHIFT_ROUTE_RECOVERY = 2 +NVML_GPU_FABRIC_HEALTH_MASK_WIDTH_ROUTE_RECOVERY = 0x11 + +NVML_GPU_FABRIC_HEALTH_MASK_ROUTE_UNHEALTHY_NOT_SUPPORTED = 0 +NVML_GPU_FABRIC_HEALTH_MASK_ROUTE_UNHEALTHY_TRUE = 1 +NVML_GPU_FABRIC_HEALTH_MASK_ROUTE_UNHEALTHY_FALSE = 2 +NVML_GPU_FABRIC_HEALTH_MASK_SHIFT_ROUTE_UNHEALTHY = 4 +NVML_GPU_FABRIC_HEALTH_MASK_WIDTH_ROUTE_UNHEALTHY = 0x11 + +NVML_GPU_FABRIC_HEALTH_MASK_ACCESS_TIMEOUT_RECOVERY_NOT_SUPPORTED = 0 +NVML_GPU_FABRIC_HEALTH_MASK_ACCESS_TIMEOUT_RECOVERY_TRUE = 1 +NVML_GPU_FABRIC_HEALTH_MASK_ACCESS_TIMEOUT_RECOVERY_FALSE = 2 +NVML_GPU_FABRIC_HEALTH_MASK_SHIFT_ACCESS_TIMEOUT_RECOVERY = 6 +NVML_GPU_FABRIC_HEALTH_MASK_WIDTH_ACCESS_TIMEOUT_RECOVERY = 0x11 + +nvmlGpuFabricInfo_v2 = 0x02000024 + +class c_nvmlGpuFabricInfoV_t(_PrintableStructure): + _fields_ = [ + ("version", c_uint), + ("clusterUuid", c_char * NVML_GPU_FABRIC_UUID_LEN), + ("status", _nvmlReturn_t), + ("cliqueId", c_uint32), + ("state", _nvmlGpuFabricState_t), + ("healthMask", c_uint32) + ] + + def __init__(self): + super(c_nvmlGpuFabricInfoV_t, self).__init__(version=nvmlGpuFabricInfo_v2) + +def nvmlDeviceGetGpuFabricInfo(device, gpuFabricInfo): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuFabricInfo"); + ret = fn(device, gpuFabricInfo) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetGpuFabricInfoV(device, gpuFabricInfo): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetGpuFabricInfoV"); + ret = fn(device, gpuFabricInfo) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +###################### +## Enums/defines +#### NVML GPU NVLINK BW MODE +NVML_GPU_NVLINK_BW_MODE_FULL = 0x0 +NVML_GPU_NVLINK_BW_MODE_OFF = 0x1 +NVML_GPU_NVLINK_BW_MODE_MIN = 0x2 +NVML_GPU_NVLINK_BW_MODE_HALF = 0x3 +NVML_GPU_NVLINK_BW_MODE_3QUARTER = 0x4 +NVML_GPU_NVLINK_BW_MODE_COUNT = 0x5 + +def nvmlSystemSetNvlinkBwMode(mode): + fn = _nvmlGetFunctionPointer("nvmlSystemSetNvlinkBwMode") + ret = fn(mode) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlSystemGetNvlinkBwMode(): + mode = c_uint() + fn = _nvmlGetFunctionPointer("nvmlSystemGetNvlinkBwMode") + ret = fn(byref(mode)) + _nvmlCheckReturn(ret) + return mode.value + +_nvmlPowerScopeType_t = c_uint +NVML_POWER_SCOPE_GPU = 0 +NVML_POWER_SCOPE_MODULE = 1 +NVML_POWER_SCOPE_MEMORY = 2 + +class c_nvmlPowerValue_v2_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('powerScope', _nvmlPowerScopeType_t), + ('powerValueMw', c_uint), + ] + _fmt_ = {'': "%d B"} + +nvmlPowerValue_v2 = 0x0200000C + +def nvmlDeviceSetPowerManagementLimit_v2(device, powerScope, powerLimit, version=nvmlPowerValue_v2): + c_powerScope = _nvmlPowerScopeType_t(powerScope) + c_powerValue = c_nvmlPowerValue_v2_t() + c_powerValue.version = c_uint(version) + c_powerValue.powerScope = c_powerScope + c_powerValue.powerValueMw = c_uint(powerLimit) + fn = _nvmlGetFunctionPointer("nvmlDeviceSetPowerManagementLimit_v2") + ret = fn(device, byref(c_powerValue)) + return NVML_SUCCESS + +class c_nvmlEccSramErrorStatus_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('aggregateUncParity', c_ulonglong), + ('aggregateUncSecDed', c_ulonglong), + ('aggregateCor', c_ulonglong), + ('volatileUncParity', c_ulonglong), + ('volatileUncSecDed', c_ulonglong), + ('volatileCor', c_ulonglong), + ('aggregateUncBucketL2', c_ulonglong), + ('aggregateUncBucketSm', c_ulonglong), + ('aggregateUncBucketPcie', c_ulonglong), + ('aggregateUncBucketMcu', c_ulonglong), + ('aggregateUncBucketOther', c_ulonglong), + ('bThresholdExceeded', c_uint) + ] + + def __init__(self): + super(c_nvmlEccSramErrorStatus_v1_t, self).__init__(version=nvmlEccSramErrorStatus_v1) + +nvmlEccSramErrorStatus_v1 = 0x1000068 +def nvmlDeviceGetSramEccErrorStatus(device, status): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetSramEccErrorStatus") + ret = fn(device, status) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +NVML_DEV_CAP_EGM = (1 << 0) +nvmlDeviceCapabilities_v1 = 0x1000008 + +class c_nvmlDeviceCapabilities_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('capMask', c_uint), + ] + + def __init__(self): + super(c_nvmlDeviceCapabilities_v1_t, self).__init__(version=nvmlDeviceCapabilities_v1) + + +def nvmlDeviceGetCapabilities(device, caps): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetCapabilities") + return fn(device, caps) + +class c_nvmlPlatformInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('ibGuid', c_char * 16), + ('rackGuid', c_char * 16), + ('chassisPhysicalSlotNumber', c_char), + ('computeSlotIndex', c_char), + ('nodeIndex', c_char), + ('peerType', c_char), + ('moduleId', c_char) + ] + + def __init__(self): + super(c_nvmlPlatformInfo_v1_t, self).__init__(version=nvmlPlatformInfo_v1) + +nvmlPlatformInfo_v1 = 0x100002c +def nvmlDeviceGetPlatformInfo(device, platformInfo): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetPlatformInfo") + ret = fn(device, platformInfo) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +class c_nvmlMask255_t(_PrintableStructure): + _fields_ = [ + ('mask', c_uint * 8), + ] + +NVML_WORKLOAD_POWER_MAX_PROFILES = 255 +NVML_POWER_PROFILE_MAX_P = 0 +NVML_POWER_PROFILE_MAX_Q = 1 +NVML_POWER_PROFILE_COMPUTE = 2 +NVML_POWER_PROFILE_MEMORY_BOUND = 3 +NVML_POWER_PROFILE_NETWORK = 4 +NVML_POWER_PROFILE_BALANCED = 5 +NVML_POWER_PROFILE_LLM_INFERENCE = 6 +NVML_POWER_PROFILE_LLM_TRAINING = 7 +NVML_POWER_PROFILE_RBM = 8 +NVML_POWER_PROFILE_DCPCIE = 9 +NVML_POWER_PROFILE_HMMA_SPARSE = 10 +NVML_POWER_PROFILE_HMMA_DENSE = 11 +NVML_POWER_PROFILE_SYNC_BALANCED = 12 +NVML_POWER_PROFILE_HPC = 13 +NVML_POWER_PROFILE_MIG = 14 +NVML_POWER_PROFILE_MAX = 15 + +nvmlWorkloadPowerProfileInfo_v1 = 0x100002c +class c_nvmlWorkloadPowerProfileInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('profileId', c_uint), + ('priority', c_uint), + ('conflictingmask', c_nvmlMask255_t) + ] + + def __init__(self): + super(c_nvmlWorkloadPowerProfileInfo_v1_t, self).__init__(version=nvmlWorkloadPowerProfileInfo_v1) + +nvmlWorkloadPowerProfileProfilesInfo_v1 = 0x1002bf8 +class c_nvmlWorkloadPowerProfileProfilesInfo_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('perfProfilesMask', c_nvmlMask255_t), + ('perfProfile', c_nvmlWorkloadPowerProfileInfo_v1_t * NVML_WORKLOAD_POWER_MAX_PROFILES) + ] + + def __init__(self): + super(c_nvmlWorkloadPowerProfileProfilesInfo_v1_t, self).__init__(version=nvmlWorkloadPowerProfileProfilesInfo_v1) + +nvmlWorkloadPowerProfileCurrentProfiles_v1 = 0x1000064 +class c_nvmlWorkloadPowerProfileCurrentProfiles_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('perfProfilesMask', c_nvmlMask255_t), + ('requestedProfilesMask', c_nvmlMask255_t), + ('enforcedProfilesMask', c_nvmlMask255_t) + ] + + def __init__(self): + super(c_nvmlWorkloadPowerProfileCurrentProfiles_v1_t, self).__init__(version=nvmlWorkloadPowerProfileCurrentProfiles_v1) + +nvmlWorkloadPowerProfileRequestedProfiles_v1 = 0x1000024 +class c_nvmlWorkloadPowerProfileRequestedProfiles_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('requestedProfilesMask', c_nvmlMask255_t), + ] + + def __init__(self): + super(c_nvmlWorkloadPowerProfileRequestedProfiles_v1_t, self).__init__(version=nvmlWorkloadPowerProfileRequestedProfiles_v1) + +def nvmlDeviceWorkloadPowerProfileGetProfilesInfo(device, profilesInfo): + fn = _nvmlGetFunctionPointer("nvmlDeviceWorkloadPowerProfileGetProfilesInfo") + ret = fn(device, profilesInfo) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceWorkloadPowerProfileGetCurrentProfiles(device, currentProfiles): + fn = _nvmlGetFunctionPointer("nvmlDeviceWorkloadPowerProfileGetCurrentProfiles") + ret = fn(device, currentProfiles) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceWorkloadPowerProfileSetRequestedProfiles(device, requestedProfiles): + fn = _nvmlGetFunctionPointer("nvmlDeviceWorkloadPowerProfileSetRequestedProfiles") + ret = fn(device, requestedProfiles) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceWorkloadPowerProfileClearRequestedProfiles(device, requestedProfiles): + fn = _nvmlGetFunctionPointer("nvmlDeviceWorkloadPowerProfileClearRequestedProfiles") + ret = fn(device, requestedProfiles) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetNvlinkSupportedBwModes(device, supportedBwModes): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvlinkSupportedBwModes") + ret = fn(device, supportedBwModes) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceGetNvlinkBwMode(device, getBwMode): + fn = _nvmlGetFunctionPointer("nvmlDeviceGetNvlinkBwMode") + ret = fn(device, getBwMode) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +def nvmlDeviceSetNvlinkBwMode(device, setBwMode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetNvlinkBwMode") + ret = fn(device, setBwMode) + _nvmlCheckReturn(ret) + return NVML_SUCCESS + +nvmlDramEncryptionInfo_v1 = 0x01000008 + +class c_nvmlDramEncryptionInfo_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('encryptionState', _nvmlEnableState_t), + ] + + def __init__(self): + super(c_nvmlDramEncryptionInfo_t, self).__init__(version=nvmlDramEncryptionInfo_v1) + +def nvmlDeviceGetDramEncryptionMode(handle): + c_currState = c_nvmlDramEncryptionInfo_t() + c_pendingState = c_nvmlDramEncryptionInfo_t() + fn = _nvmlGetFunctionPointer("nvmlDeviceGetDramEncryptionMode") + ret = fn(handle, byref(c_currState), byref(c_pendingState)) + _nvmlCheckReturn(ret) + return [c_currState.encryptionState, c_pendingState.encryptionState] + +# added to API +def nvmlDeviceGetCurrentDramEncryptionMode(handle): + return nvmlDeviceGetDramEncryptionMode(handle)[0] + +# added to API +def nvmlDeviceGetPendingDramEncryptionMode(handle): + return nvmlDeviceGetDramEncryptionMode(handle)[1] + +def nvmlDeviceSetDramEncryptionMode(handle, mode): + fn = _nvmlGetFunctionPointer("nvmlDeviceSetDramEncryptionMode") + c_dramEncryptionMode = c_nvmlDramEncryptionInfo_t() + c_dramEncryptionMode.encryptionState = mode; + ret = fn(handle, byref(c_dramEncryptionMode)) + _nvmlCheckReturn(ret) + return None + +# Power Smoothing defines +NVML_POWER_SMOOTHING_MAX_NUM_PROFILES = 5 +NVML_POWER_SMOOTHING_ADMIN_OVERRIDE_NOT_SET = 0xFFFFFFFF +NVML_POWER_SMOOTHING_PROFILE_PARAM_PERCENT_TMP_FLOOR = 0 +NVML_POWER_SMOOTHING_PROFILE_PARAM_RAMP_UP_RATE = 1 +NVML_POWER_SMOOTHING_PROFILE_PARAM_RAMP_DOWN_RATE = 2 +NVML_POWER_SMOOTHING_PROFILE_PARAM_RAMP_DOWN_HYSTERESIS = 3 + +nvmlPowerSmoothingState_v1=0x1000008 +class c_nvmlPowerSmoothingState_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('state', c_uint), + ] + + def __init__(self): + super(c_nvmlPowerSmoothingState_v1_t, self).__init__(version=nvmlPowerSmoothingState_v1) + +nvmlPowerSmoothingProfile_v1=0x1000018 +class c_nvmlPowerSmoothingProfile_v1_t(_PrintableStructure): + _fields_ = [ + ('version', c_uint), + ('profileId', c_uint), + ('paramId', c_uint), + ('value', c_double), + ] + + def __init__(self): + super(c_nvmlPowerSmoothingProfile_v1_t, self).__init__(version=nvmlPowerSmoothingProfile_v1) + +def nvmlDevicePowerSmoothingActivatePresetProfile(device, profile): + fn = _nvmlGetFunctionPointer("nvmlDevicePowerSmoothingActivatePresetProfile") + ret = fn(device, profile) + _nvmlCheckReturn(ret) + +def nvmlDevicePowerSmoothingUpdatePresetProfileParam(device, profile): + fn = _nvmlGetFunctionPointer("nvmlDevicePowerSmoothingUpdatePresetProfileParam") + ret = fn(device, profile) + _nvmlCheckReturn(ret) + +def nvmlDevicePowerSmoothingSetState(device, state): + fn = _nvmlGetFunctionPointer("nvmlDevicePowerSmoothingSetState") + ret = fn(device, state) + _nvmlCheckReturn(ret) + diff --git a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/LICENSE.txt b/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/LICENSE.txt deleted file mode 100644 index 5f1c112..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/LICENSE.txt +++ /dev/null @@ -1,19 +0,0 @@ -Copyright (c) 2003-2019 Stuart Bishop - -Permission is hereby granted, free of charge, to any person obtaining a -copy of this software and associated documentation files (the "Software"), -to deal in the Software without restriction, including without limitation -the rights to use, copy, modify, merge, publish, distribute, sublicense, -and/or sell copies of the Software, and to permit persons to whom the -Software is furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL -THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER -DEALINGS IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/METADATA deleted file mode 100644 index 6ecc5a3..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/METADATA +++ /dev/null @@ -1,648 +0,0 @@ -Metadata-Version: 2.1 -Name: pytz -Version: 2025.2 -Summary: World timezone definitions, modern and historical -Home-page: http://pythonhosted.org/pytz -Download-URL: https://pypi.org/project/pytz/ -Author: Stuart Bishop -Author-email: stuart@stuartbishop.net -Maintainer: Stuart Bishop -Maintainer-email: stuart@stuartbishop.net -License: MIT -Keywords: timezone,tzinfo,datetime,olson,time -Platform: Independent -Classifier: Development Status :: 6 - Mature -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Natural Language :: English -Classifier: Operating System :: OS Independent -Classifier: Programming Language :: Python -Classifier: Programming Language :: Python :: 2 -Classifier: Programming Language :: Python :: 2.4 -Classifier: Programming Language :: Python :: 2.5 -Classifier: Programming Language :: Python :: 2.6 -Classifier: Programming Language :: Python :: 2.7 -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3.1 -Classifier: Programming Language :: Python :: 3.2 -Classifier: Programming Language :: Python :: 3.3 -Classifier: Programming Language :: Python :: 3.4 -Classifier: Programming Language :: Python :: 3.5 -Classifier: Programming Language :: Python :: 3.6 -Classifier: Programming Language :: Python :: 3.7 -Classifier: Programming Language :: Python :: 3.8 -Classifier: Programming Language :: Python :: 3.9 -Classifier: Programming Language :: Python :: 3.10 -Classifier: Programming Language :: Python :: 3.11 -Classifier: Programming Language :: Python :: 3.12 -Classifier: Programming Language :: Python :: 3.13 -Classifier: Topic :: Software Development :: Libraries :: Python Modules -License-File: LICENSE.txt - -pytz - World Timezone Definitions for Python -============================================ - -:Author: Stuart Bishop - -Introduction -~~~~~~~~~~~~ - -pytz brings the Olson tz database into Python. This library allows -accurate and cross platform timezone calculations using Python 2.4 -or higher. It also solves the issue of ambiguous times at the end -of daylight saving time, which you can read more about in the Python -Library Reference (``datetime.tzinfo``). - -Almost all of the Olson timezones are supported. - -.. note:: - - Projects using Python 3.9 or later should be using the support - now included as part of the standard library, and third party - packages work with it such as `tzdata `_. - pytz offers no advantages beyond backwards compatibility with - code written for earlier versions of Python. - -.. note:: - - This library differs from the documented Python API for - tzinfo implementations; if you want to create local wallclock - times you need to use the ``localize()`` method documented in this - document. In addition, if you perform date arithmetic on local - times that cross DST boundaries, the result may be in an incorrect - timezone (ie. subtract 1 minute from 2002-10-27 1:00 EST and you get - 2002-10-27 0:59 EST instead of the correct 2002-10-27 1:59 EDT). A - ``normalize()`` method is provided to correct this. Unfortunately these - issues cannot be resolved without modifying the Python datetime - implementation (see PEP-431). - - -Installation -~~~~~~~~~~~~ - -This package can either be installed using ``pip`` or from a tarball using the -standard Python distutils. - -If you are installing using ``pip``, you don't need to download anything as the -latest version will be downloaded for you from PyPI:: - - pip install pytz - -If you are installing from a tarball, run the following command as an -administrative user:: - - python setup.py install - - -pytz for Enterprise -~~~~~~~~~~~~~~~~~~~ - -Available as part of the Tidelift Subscription. - -The maintainers of pytz and thousands of other packages are working with Tidelift to deliver commercial support and maintenance for the open source dependencies you use to build your applications. Save time, reduce risk, and improve code health, while paying the maintainers of the exact dependencies you use. `Learn more. `_. - - -Example & Usage -~~~~~~~~~~~~~~~ - -Localized times and date arithmetic ------------------------------------ - ->>> from datetime import datetime, timedelta ->>> from pytz import timezone ->>> import pytz ->>> utc = pytz.utc ->>> utc.zone -'UTC' ->>> eastern = timezone('US/Eastern') ->>> eastern.zone -'US/Eastern' ->>> amsterdam = timezone('Europe/Amsterdam') ->>> fmt = '%Y-%m-%d %H:%M:%S %Z%z' - -This library only supports two ways of building a localized time. The -first is to use the ``localize()`` method provided by the pytz library. -This is used to localize a naive datetime (datetime with no timezone -information): - ->>> loc_dt = eastern.localize(datetime(2002, 10, 27, 6, 0, 0)) ->>> print(loc_dt.strftime(fmt)) -2002-10-27 06:00:00 EST-0500 - -The second way of building a localized time is by converting an existing -localized time using the standard ``astimezone()`` method: - ->>> ams_dt = loc_dt.astimezone(amsterdam) ->>> ams_dt.strftime(fmt) -'2002-10-27 12:00:00 CET+0100' - -Unfortunately using the tzinfo argument of the standard datetime -constructors ''does not work'' with pytz for many timezones. - ->>> datetime(2002, 10, 27, 12, 0, 0, tzinfo=amsterdam).strftime(fmt) # /!\ Does not work this way! -'2002-10-27 12:00:00 LMT+0018' - -It is safe for timezones without daylight saving transitions though, such -as UTC: - ->>> datetime(2002, 10, 27, 12, 0, 0, tzinfo=pytz.utc).strftime(fmt) # /!\ Not recommended except for UTC -'2002-10-27 12:00:00 UTC+0000' - -The preferred way of dealing with times is to always work in UTC, -converting to localtime only when generating output to be read -by humans. - ->>> utc_dt = datetime(2002, 10, 27, 6, 0, 0, tzinfo=utc) ->>> loc_dt = utc_dt.astimezone(eastern) ->>> loc_dt.strftime(fmt) -'2002-10-27 01:00:00 EST-0500' - -This library also allows you to do date arithmetic using local -times, although it is more complicated than working in UTC as you -need to use the ``normalize()`` method to handle daylight saving time -and other timezone transitions. In this example, ``loc_dt`` is set -to the instant when daylight saving time ends in the US/Eastern -timezone. - ->>> before = loc_dt - timedelta(minutes=10) ->>> before.strftime(fmt) -'2002-10-27 00:50:00 EST-0500' ->>> eastern.normalize(before).strftime(fmt) -'2002-10-27 01:50:00 EDT-0400' ->>> after = eastern.normalize(before + timedelta(minutes=20)) ->>> after.strftime(fmt) -'2002-10-27 01:10:00 EST-0500' - -Creating local times is also tricky, and the reason why working with -local times is not recommended. Unfortunately, you cannot just pass -a ``tzinfo`` argument when constructing a datetime (see the next -section for more details) - ->>> dt = datetime(2002, 10, 27, 1, 30, 0) ->>> dt1 = eastern.localize(dt, is_dst=True) ->>> dt1.strftime(fmt) -'2002-10-27 01:30:00 EDT-0400' ->>> dt2 = eastern.localize(dt, is_dst=False) ->>> dt2.strftime(fmt) -'2002-10-27 01:30:00 EST-0500' - -Converting between timezones is more easily done, using the -standard astimezone method. - ->>> utc_dt = datetime.fromtimestamp(1143408899, tz=utc) ->>> utc_dt.strftime(fmt) -'2006-03-26 21:34:59 UTC+0000' ->>> au_tz = timezone('Australia/Sydney') ->>> au_dt = utc_dt.astimezone(au_tz) ->>> au_dt.strftime(fmt) -'2006-03-27 08:34:59 AEDT+1100' ->>> utc_dt2 = au_dt.astimezone(utc) ->>> utc_dt2.strftime(fmt) -'2006-03-26 21:34:59 UTC+0000' ->>> utc_dt == utc_dt2 -True - -You can take shortcuts when dealing with the UTC side of timezone -conversions. ``normalize()`` and ``localize()`` are not really -necessary when there are no daylight saving time transitions to -deal with. - ->>> utc_dt = datetime.fromtimestamp(1143408899, tz=utc) ->>> utc_dt.strftime(fmt) -'2006-03-26 21:34:59 UTC+0000' ->>> au_tz = timezone('Australia/Sydney') ->>> au_dt = au_tz.normalize(utc_dt.astimezone(au_tz)) ->>> au_dt.strftime(fmt) -'2006-03-27 08:34:59 AEDT+1100' ->>> utc_dt2 = au_dt.astimezone(utc) ->>> utc_dt2.strftime(fmt) -'2006-03-26 21:34:59 UTC+0000' - - -``tzinfo`` API --------------- - -The ``tzinfo`` instances returned by the ``timezone()`` function have -been extended to cope with ambiguous times by adding an ``is_dst`` -parameter to the ``utcoffset()``, ``dst()`` && ``tzname()`` methods. - ->>> tz = timezone('America/St_Johns') - ->>> normal = datetime(2009, 9, 1) ->>> ambiguous = datetime(2009, 10, 31, 23, 30) - -The ``is_dst`` parameter is ignored for most timestamps. It is only used -during DST transition ambiguous periods to resolve that ambiguity. - ->>> print(tz.utcoffset(normal, is_dst=True)) --1 day, 21:30:00 ->>> print(tz.dst(normal, is_dst=True)) -1:00:00 ->>> tz.tzname(normal, is_dst=True) -'NDT' - ->>> print(tz.utcoffset(ambiguous, is_dst=True)) --1 day, 21:30:00 ->>> print(tz.dst(ambiguous, is_dst=True)) -1:00:00 ->>> tz.tzname(ambiguous, is_dst=True) -'NDT' - ->>> print(tz.utcoffset(normal, is_dst=False)) --1 day, 21:30:00 ->>> tz.dst(normal, is_dst=False).seconds -3600 ->>> tz.tzname(normal, is_dst=False) -'NDT' - ->>> print(tz.utcoffset(ambiguous, is_dst=False)) --1 day, 20:30:00 ->>> tz.dst(ambiguous, is_dst=False) -datetime.timedelta(0) ->>> tz.tzname(ambiguous, is_dst=False) -'NST' - -If ``is_dst`` is not specified, ambiguous timestamps will raise -an ``pytz.exceptions.AmbiguousTimeError`` exception. - ->>> print(tz.utcoffset(normal)) --1 day, 21:30:00 ->>> print(tz.dst(normal)) -1:00:00 ->>> tz.tzname(normal) -'NDT' - ->>> import pytz.exceptions ->>> try: -... tz.utcoffset(ambiguous) -... except pytz.exceptions.AmbiguousTimeError: -... print('pytz.exceptions.AmbiguousTimeError: %s' % ambiguous) -pytz.exceptions.AmbiguousTimeError: 2009-10-31 23:30:00 ->>> try: -... tz.dst(ambiguous) -... except pytz.exceptions.AmbiguousTimeError: -... print('pytz.exceptions.AmbiguousTimeError: %s' % ambiguous) -pytz.exceptions.AmbiguousTimeError: 2009-10-31 23:30:00 ->>> try: -... tz.tzname(ambiguous) -... except pytz.exceptions.AmbiguousTimeError: -... print('pytz.exceptions.AmbiguousTimeError: %s' % ambiguous) -pytz.exceptions.AmbiguousTimeError: 2009-10-31 23:30:00 - - -Problems with Localtime -~~~~~~~~~~~~~~~~~~~~~~~ - -The major problem we have to deal with is that certain datetimes -may occur twice in a year. For example, in the US/Eastern timezone -on the last Sunday morning in October, the following sequence -happens: - - - 01:00 EDT occurs - - 1 hour later, instead of 2:00am the clock is turned back 1 hour - and 01:00 happens again (this time 01:00 EST) - -In fact, every instant between 01:00 and 02:00 occurs twice. This means -that if you try and create a time in the 'US/Eastern' timezone -the standard datetime syntax, there is no way to specify if you meant -before of after the end-of-daylight-saving-time transition. Using the -pytz custom syntax, the best you can do is make an educated guess: - ->>> loc_dt = eastern.localize(datetime(2002, 10, 27, 1, 30, 00)) ->>> loc_dt.strftime(fmt) -'2002-10-27 01:30:00 EST-0500' - -As you can see, the system has chosen one for you and there is a 50% -chance of it being out by one hour. For some applications, this does -not matter. However, if you are trying to schedule meetings with people -in different timezones or analyze log files it is not acceptable. - -The best and simplest solution is to stick with using UTC. The pytz -package encourages using UTC for internal timezone representation by -including a special UTC implementation based on the standard Python -reference implementation in the Python documentation. - -The UTC timezone unpickles to be the same instance, and pickles to a -smaller size than other pytz tzinfo instances. The UTC implementation -can be obtained as pytz.utc, pytz.UTC, or pytz.timezone('UTC'). - ->>> import pickle, pytz ->>> dt = datetime(2005, 3, 1, 14, 13, 21, tzinfo=utc) ->>> naive = dt.replace(tzinfo=None) ->>> p = pickle.dumps(dt, 1) ->>> naive_p = pickle.dumps(naive, 1) ->>> len(p) - len(naive_p) -17 ->>> new = pickle.loads(p) ->>> new == dt -True ->>> new is dt -False ->>> new.tzinfo is dt.tzinfo -True ->>> pytz.utc is pytz.UTC is pytz.timezone('UTC') -True - -Note that some other timezones are commonly thought of as the same (GMT, -Greenwich, Universal, etc.). The definition of UTC is distinct from these -other timezones, and they are not equivalent. For this reason, they will -not compare the same in Python. - ->>> utc == pytz.timezone('GMT') -False - -See the section `What is UTC`_, below. - -If you insist on working with local times, this library provides a -facility for constructing them unambiguously: - ->>> loc_dt = datetime(2002, 10, 27, 1, 30, 00) ->>> est_dt = eastern.localize(loc_dt, is_dst=True) ->>> edt_dt = eastern.localize(loc_dt, is_dst=False) ->>> print(est_dt.strftime(fmt) + ' / ' + edt_dt.strftime(fmt)) -2002-10-27 01:30:00 EDT-0400 / 2002-10-27 01:30:00 EST-0500 - -If you pass None as the is_dst flag to localize(), pytz will refuse to -guess and raise exceptions if you try to build ambiguous or non-existent -times. - -For example, 1:30am on 27th Oct 2002 happened twice in the US/Eastern -timezone when the clocks where put back at the end of Daylight Saving -Time: - ->>> dt = datetime(2002, 10, 27, 1, 30, 00) ->>> try: -... eastern.localize(dt, is_dst=None) -... except pytz.exceptions.AmbiguousTimeError: -... print('pytz.exceptions.AmbiguousTimeError: %s' % dt) -pytz.exceptions.AmbiguousTimeError: 2002-10-27 01:30:00 - -Similarly, 2:30am on 7th April 2002 never happened at all in the -US/Eastern timezone, as the clocks where put forward at 2:00am skipping -the entire hour: - ->>> dt = datetime(2002, 4, 7, 2, 30, 00) ->>> try: -... eastern.localize(dt, is_dst=None) -... except pytz.exceptions.NonExistentTimeError: -... print('pytz.exceptions.NonExistentTimeError: %s' % dt) -pytz.exceptions.NonExistentTimeError: 2002-04-07 02:30:00 - -Both of these exceptions share a common base class to make error handling -easier: - ->>> isinstance(pytz.AmbiguousTimeError(), pytz.InvalidTimeError) -True ->>> isinstance(pytz.NonExistentTimeError(), pytz.InvalidTimeError) -True - - -A special case is where countries change their timezone definitions -with no daylight savings time switch. For example, in 1915 Warsaw -switched from Warsaw time to Central European time with no daylight savings -transition. So at the stroke of midnight on August 5th 1915 the clocks -were wound back 24 minutes creating an ambiguous time period that cannot -be specified without referring to the timezone abbreviation or the -actual UTC offset. In this case midnight happened twice, neither time -during a daylight saving time period. pytz handles this transition by -treating the ambiguous period before the switch as daylight savings -time, and the ambiguous period after as standard time. - - ->>> warsaw = pytz.timezone('Europe/Warsaw') ->>> amb_dt1 = warsaw.localize(datetime(1915, 8, 4, 23, 59, 59), is_dst=True) ->>> amb_dt1.strftime(fmt) -'1915-08-04 23:59:59 WMT+0124' ->>> amb_dt2 = warsaw.localize(datetime(1915, 8, 4, 23, 59, 59), is_dst=False) ->>> amb_dt2.strftime(fmt) -'1915-08-04 23:59:59 CET+0100' ->>> switch_dt = warsaw.localize(datetime(1915, 8, 5, 00, 00, 00), is_dst=False) ->>> switch_dt.strftime(fmt) -'1915-08-05 00:00:00 CET+0100' ->>> str(switch_dt - amb_dt1) -'0:24:01' ->>> str(switch_dt - amb_dt2) -'0:00:01' - -The best way of creating a time during an ambiguous time period is -by converting from another timezone such as UTC: - ->>> utc_dt = datetime(1915, 8, 4, 22, 36, tzinfo=pytz.utc) ->>> utc_dt.astimezone(warsaw).strftime(fmt) -'1915-08-04 23:36:00 CET+0100' - -The standard Python way of handling all these ambiguities is not to -handle them, such as demonstrated in this example using the US/Eastern -timezone definition from the Python documentation (Note that this -implementation only works for dates between 1987 and 2006 - it is -included for tests only!): - ->>> from pytz.reference import Eastern # pytz.reference only for tests ->>> dt = datetime(2002, 10, 27, 0, 30, tzinfo=Eastern) ->>> str(dt) -'2002-10-27 00:30:00-04:00' ->>> str(dt + timedelta(hours=1)) -'2002-10-27 01:30:00-05:00' ->>> str(dt + timedelta(hours=2)) -'2002-10-27 02:30:00-05:00' ->>> str(dt + timedelta(hours=3)) -'2002-10-27 03:30:00-05:00' - -Notice the first two results? At first glance you might think they are -correct, but taking the UTC offset into account you find that they are -actually two hours appart instead of the 1 hour we asked for. - ->>> from pytz.reference import UTC # pytz.reference only for tests ->>> str(dt.astimezone(UTC)) -'2002-10-27 04:30:00+00:00' ->>> str((dt + timedelta(hours=1)).astimezone(UTC)) -'2002-10-27 06:30:00+00:00' - - -Country Information -~~~~~~~~~~~~~~~~~~~ - -A mechanism is provided to access the timezones commonly in use -for a particular country, looked up using the ISO 3166 country code. -It returns a list of strings that can be used to retrieve the relevant -tzinfo instance using ``pytz.timezone()``: - ->>> print(' '.join(pytz.country_timezones['nz'])) -Pacific/Auckland Pacific/Chatham - -The Olson database comes with a ISO 3166 country code to English country -name mapping that pytz exposes as a dictionary: - ->>> print(pytz.country_names['nz']) -New Zealand - - -What is UTC -~~~~~~~~~~~ - -'UTC' is `Coordinated Universal Time`_. It is a successor to, but distinct -from, Greenwich Mean Time (GMT) and the various definitions of Universal -Time. UTC is now the worldwide standard for regulating clocks and time -measurement. - -All other timezones are defined relative to UTC, and include offsets like -UTC+0800 - hours to add or subtract from UTC to derive the local time. No -daylight saving time occurs in UTC, making it a useful timezone to perform -date arithmetic without worrying about the confusion and ambiguities caused -by daylight saving time transitions, your country changing its timezone, or -mobile computers that roam through multiple timezones. - -.. _Coordinated Universal Time: https://en.wikipedia.org/wiki/Coordinated_Universal_Time - - -Helpers -~~~~~~~ - -There are two lists of timezones provided. - -``all_timezones`` is the exhaustive list of the timezone names that can -be used. - ->>> from pytz import all_timezones ->>> len(all_timezones) >= 500 -True ->>> 'Etc/Greenwich' in all_timezones -True - -``common_timezones`` is a list of useful, current timezones. It doesn't -contain deprecated zones or historical zones, except for a few I've -deemed in common usage, such as US/Eastern (open a bug report if you -think other timezones are deserving of being included here). It is also -a sequence of strings. - ->>> from pytz import common_timezones ->>> len(common_timezones) < len(all_timezones) -True ->>> 'Etc/Greenwich' in common_timezones -False ->>> 'Australia/Melbourne' in common_timezones -True ->>> 'US/Eastern' in common_timezones -True ->>> 'Canada/Eastern' in common_timezones -True ->>> 'Australia/Yancowinna' in all_timezones -True ->>> 'Australia/Yancowinna' in common_timezones -False - -Both ``common_timezones`` and ``all_timezones`` are alphabetically -sorted: - ->>> common_timezones_dupe = common_timezones[:] ->>> common_timezones_dupe.sort() ->>> common_timezones == common_timezones_dupe -True ->>> all_timezones_dupe = all_timezones[:] ->>> all_timezones_dupe.sort() ->>> all_timezones == all_timezones_dupe -True - -``all_timezones`` and ``common_timezones`` are also available as sets. - ->>> from pytz import all_timezones_set, common_timezones_set ->>> 'US/Eastern' in all_timezones_set -True ->>> 'US/Eastern' in common_timezones_set -True ->>> 'Australia/Victoria' in common_timezones_set -False - -You can also retrieve lists of timezones used by particular countries -using the ``country_timezones()`` function. It requires an ISO-3166 -two letter country code. - ->>> from pytz import country_timezones ->>> print(' '.join(country_timezones('ch'))) -Europe/Zurich ->>> print(' '.join(country_timezones('CH'))) -Europe/Zurich - - -Internationalization - i18n/l10n -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -Pytz is an interface to the IANA database, which uses ASCII names. The `Unicode Consortium's Unicode Locales (CLDR) `_ -project provides translations. Python packages such as -`Babel `_ -and Thomas Khyn's `l18n `_ package can be used -to access these translations from Python. - - -License -~~~~~~~ - -MIT license. - -This code is also available as part of Zope 3 under the Zope Public -License, Version 2.1 (ZPL). - -I'm happy to relicense this code if necessary for inclusion in other -open source projects. - - -Latest Versions -~~~~~~~~~~~~~~~ - -This package will be updated after releases of the Olson timezone -database. The latest version can be downloaded from the `Python Package -Index `_. The code that is used -to generate this distribution is hosted on Github and available -using git:: - - git clone https://github.com/stub42/pytz.git - -Announcements of new releases are made on -`Launchpad `_, and the -`Atom feed `_ -hosted there. - - -Bugs, Feature Requests & Patches -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -Bugs should be reported on `Github `_. -Feature requests are unlikely to be considered, and efforts instead directed -to timezone support now built into Python or packages that work with it. - - -Security Issues -~~~~~~~~~~~~~~~ - -Reports about security issues can be made via `Tidelift `_. - - -Issues & Limitations -~~~~~~~~~~~~~~~~~~~~ - -- This project is in maintenance mode. Projects using Python 3.9 or later - are best served by using the timezone functionaly now included in core - Python and packages that work with it such as `tzdata `_. - -- Offsets from UTC are rounded to the nearest whole minute, so timezones - such as Europe/Amsterdam pre 1937 will be up to 30 seconds out. This - was a limitation of the Python datetime library. - -- If you think a timezone definition is incorrect, I probably can't fix - it. pytz is a direct translation of the Olson timezone database, and - changes to the timezone definitions need to be made to this source. - If you find errors they should be reported to the time zone mailing - list, linked from http://www.iana.org/time-zones. - - -Further Reading -~~~~~~~~~~~~~~~ - -More info than you want to know about timezones: -https://data.iana.org/time-zones/tz-link.html - - -Contact -~~~~~~~ - -Stuart Bishop diff --git a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/RECORD deleted file mode 100644 index f9afc2a..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/RECORD +++ /dev/null @@ -1,623 +0,0 @@ -pytz-2025.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -pytz-2025.2.dist-info/LICENSE.txt,sha256=vosaN-vibFkqkPbA6zMQOn84POL010mMCvmlJpkKB7g,1088 -pytz-2025.2.dist-info/METADATA,sha256=5iDk4fnxyAGWGTiNTaSW6wIRmhPzWqrVXwImlKPIH2w,22374 -pytz-2025.2.dist-info/RECORD,, -pytz-2025.2.dist-info/WHEEL,sha256=-G_t0oGuE7UD0DrSpVZnq1hHMBV9DD2XkS5v7XpmTnk,110 -pytz-2025.2.dist-info/top_level.txt,sha256=6xRYlt934v1yHb1JIrXgHyGxn3cqACvd-yE8ski_kcc,5 -pytz-2025.2.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1 -pytz/__init__.py,sha256=dml-pbWn-1xqv_ZWHoKoPmhruaO63GoIubnxtFnEvDc,35125 -pytz/__pycache__/__init__.cpython-312.pyc,, -pytz/__pycache__/exceptions.cpython-312.pyc,, -pytz/__pycache__/lazy.cpython-312.pyc,, -pytz/__pycache__/reference.cpython-312.pyc,, -pytz/__pycache__/tzfile.cpython-312.pyc,, -pytz/__pycache__/tzinfo.cpython-312.pyc,, -pytz/exceptions.py,sha256=434ZcuLlpLQY9mWoGq7zJMV1TyiYvVgpKBU1qZkbDjM,1571 -pytz/lazy.py,sha256=toeR5uDWKBj6ezsUZ4elNP6CEMtK7CO2jS9A30nsFbo,5404 -pytz/reference.py,sha256=zUtCki7JFEmrzrjNsfMD7YL0lWDxynKc1Ubo4iXSs74,3778 -pytz/tzfile.py,sha256=K2y7pZs4vydpZVftrfAA_-hgw17y1Szc7z_QCse6udU,4723 -pytz/tzinfo.py,sha256=XfaVOoO3KsCvtUYaCd0fvgBXWZ8tgevGYUoBh_uiE60,19340 -pytz/zoneinfo/Africa/Abidjan,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Accra,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Addis_Ababa,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Algiers,sha256=vaFpjNVCwObnbfu82rOQzdJvN6nVgmpXpQ1aqzfzsqY,735 -pytz/zoneinfo/Africa/Asmara,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Asmera,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Bamako,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Bangui,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Banjul,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Bissau,sha256=IjuxDP6EZiDHFvl_bHS6NN7sdRxLKXllooBC829poak,194 -pytz/zoneinfo/Africa/Blantyre,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Brazzaville,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Bujumbura,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Cairo,sha256=Lft-GCLQhaSJm9VqUmsEFoHIS1Vhfa7pFJn9GZCpifs,2399 -pytz/zoneinfo/Africa/Casablanca,sha256=4RqVbw_F3ZucopIC2ivAJ8WDwj5wRODAB67tBpdXcgA,2429 -pytz/zoneinfo/Africa/Ceuta,sha256=Cw-2_nFDGbN8WqIsVpcauyZooWX8j3Kmx2PnC0fHut8,2052 -pytz/zoneinfo/Africa/Conakry,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Dakar,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Dar_es_Salaam,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Djibouti,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Douala,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/El_Aaiun,sha256=UWCCqQLJxd8qsTYw82kz9W1suwW5TRgnZw31sDWDz20,2295 -pytz/zoneinfo/Africa/Freetown,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Gaborone,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Harare,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Johannesburg,sha256=bBvMdSZo53WFowiuhUO9C8zY6BOGViboCb-U8_49l34,246 -pytz/zoneinfo/Africa/Juba,sha256=UVnIqEPJwHLTMC-r5qZQHNv9opoYVsKdq-ta_5XUw_Q,679 -pytz/zoneinfo/Africa/Kampala,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Khartoum,sha256=MYWDoJ3AcCItZdApoeOgtWWDDxquwTon5v5TOGP70-o,679 -pytz/zoneinfo/Africa/Kigali,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Kinshasa,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Lagos,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Libreville,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Lome,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Luanda,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Lubumbashi,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Lusaka,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Malabo,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Maputo,sha256=RE7TpxBBS8a_Q-sn5ZHaSdO-PbFTRJpqDJRz9-Of28s,149 -pytz/zoneinfo/Africa/Maseru,sha256=bBvMdSZo53WFowiuhUO9C8zY6BOGViboCb-U8_49l34,246 -pytz/zoneinfo/Africa/Mbabane,sha256=bBvMdSZo53WFowiuhUO9C8zY6BOGViboCb-U8_49l34,246 -pytz/zoneinfo/Africa/Mogadishu,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Monrovia,sha256=-VsJW5cU4KdvfgYaQVv4lcuzmaKIVFMd42nO6RXOBdU,208 -pytz/zoneinfo/Africa/Nairobi,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Africa/Ndjamena,sha256=8T3A0Zm9Gj0Bvm6rd88t3GAXKiKdGUfHlIqYlkYI0KM,199 -pytz/zoneinfo/Africa/Niamey,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Nouakchott,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Ouagadougou,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Porto-Novo,sha256=z_6wKCzL1_ug5JP_hneh5abdUZeIUELkN_ladz-ESEY,235 -pytz/zoneinfo/Africa/Sao_Tome,sha256=MdjxpQ268uzJ7Zx1ZroFUtRUwqsJ6F_yY3AYV9FXw1I,254 -pytz/zoneinfo/Africa/Timbuktu,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Africa/Tripoli,sha256=W1dptGD70T7ppGoo0fczFQeDiIp0nultLNPV66MwB2c,625 -pytz/zoneinfo/Africa/Tunis,sha256=OFVMEM4eYT2Ez0beuhEUCTSIpcFldWxsV2uEoTZIUNI,689 -pytz/zoneinfo/Africa/Windhoek,sha256=xuhvudrMH4alnVmouSTQI8YL8F_HbgsF2EQ7AZKzuHs,955 -pytz/zoneinfo/America/Adak,sha256=IB1DhwJQAKbhPJ9jHLf8zW5Dad7HIkBS-dhv64E1OlM,2356 -pytz/zoneinfo/America/Anchorage,sha256=oZA1NSPS2BWdymYpnCHFO8BlYVS-ll5KLg2Ez9CbETs,2371 -pytz/zoneinfo/America/Anguilla,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Antigua,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Araguaina,sha256=G6v9wYFZ8EB4WQfIsqRbbiiKd2b27j7Zt5dFjBbzx2o,870 -pytz/zoneinfo/America/Argentina/Buenos_Aires,sha256=JmU8lBwmy29gR6OmeytvFdMRx6ObJKnYNHmLyMmXX2M,1062 -pytz/zoneinfo/America/Argentina/Catamarca,sha256=uMCJXXGYmNESHVvj5RYBZ0McrOdE14hwm17l25MgRW0,1062 -pytz/zoneinfo/America/Argentina/ComodRivadavia,sha256=uMCJXXGYmNESHVvj5RYBZ0McrOdE14hwm17l25MgRW0,1062 -pytz/zoneinfo/America/Argentina/Cordoba,sha256=uniNihhMHnr4XK4WpwiPUnrAT0YPmvzqB6f0hRLtXvY,1062 -pytz/zoneinfo/America/Argentina/Jujuy,sha256=PGmAehypCxj0XCenCSWqylDIPbKLK0DlrwJK_24D590,1034 -pytz/zoneinfo/America/Argentina/La_Rioja,sha256=Um6XoVXhsr62ad1mWuebe6NY0ZHauBdR9tMGDgqCOHg,1076 -pytz/zoneinfo/America/Argentina/Mendoza,sha256=xcOVtvRyVYFAU90y2QYwpyQhpMLyAp7-Fxvku4kgl0c,1062 -pytz/zoneinfo/America/Argentina/Rio_Gallegos,sha256=F9ZKR4o8gLHX7QBuIjMapGIdmzJxpqwbouPgZ5MqDpY,1062 -pytz/zoneinfo/America/Argentina/Salta,sha256=h1KYrDNIapvDkYhi1PaB8WD1qWOe4vhhgDJWDCGV4jc,1034 -pytz/zoneinfo/America/Argentina/San_Juan,sha256=AI2GltA80mPNzhHxYycuEwIbO1ANXyIqBQZMpjqKqdQ,1076 -pytz/zoneinfo/America/Argentina/San_Luis,sha256=2ItGRcLVK2wx8MyJsHbIBBeAkU4B-MN5x1ZxNyZ7UJE,1088 -pytz/zoneinfo/America/Argentina/Tucuman,sha256=twO-FqtNJV8XOzWTvFQ-xnEcWCoDUHY3gpVIG0Mzbf8,1090 -pytz/zoneinfo/America/Argentina/Ushuaia,sha256=A6IbpVlY9IIPoSKMFRR9DMROdwXUSDc2HsASueOSnqo,1062 -pytz/zoneinfo/America/Aruba,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Asuncion,sha256=9yfGiENhXNgd2_0xHVsF-hLeJkGSqRs-zD9O945KJWc,1644 -pytz/zoneinfo/America/Atikokan,sha256=kayA_pdpMcSQ0FjIzotdcf-m1JYfbKE-qcFT8LC8zqA,182 -pytz/zoneinfo/America/Atka,sha256=IB1DhwJQAKbhPJ9jHLf8zW5Dad7HIkBS-dhv64E1OlM,2356 -pytz/zoneinfo/America/Bahia,sha256=qi7dA6FofDhLxVMmd2L8bK3HeaQnc9X-jiijwyfhs3g,1010 -pytz/zoneinfo/America/Bahia_Banderas,sha256=MvrXGJ5LzaHOeguJqxszxjxMhVafGVbk-ojXEc7_YEI,1100 -pytz/zoneinfo/America/Barbados,sha256=ima-Qrrhazu4Qfvu2Z0-e6E-GTiYknuJBu6c2yVG9LE,436 -pytz/zoneinfo/America/Belem,sha256=aZMUgtFDdHNISpqyQRYbmS2IBD-BAS3CaJnhu6onLCY,562 -pytz/zoneinfo/America/Belize,sha256=pkfLY2KfPchbeJa1pWcXmWAwp4ZlRvxWLVezXnrbkws,1614 -pytz/zoneinfo/America/Blanc-Sablon,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Boa_Vista,sha256=dMtaG11kGlJrgJJgGWEDZZAmnO_HfT3L4X8pI72LLFY,618 -pytz/zoneinfo/America/Bogota,sha256=Z1ernZZGQxulE8KFWHYWcM3SV1jn2_QEc1Q0OJzHRak,232 -pytz/zoneinfo/America/Boise,sha256=7HQsNPJiUheQgFz5kVLvTnf5xhXAYaeANqDskxKz2Vs,2410 -pytz/zoneinfo/America/Buenos_Aires,sha256=JmU8lBwmy29gR6OmeytvFdMRx6ObJKnYNHmLyMmXX2M,1062 -pytz/zoneinfo/America/Cambridge_Bay,sha256=_4xRlX3WdVpEcqoT6myD7NeTCXnn9OYk_iH006bwULo,2254 -pytz/zoneinfo/America/Campo_Grande,sha256=gINiXg5i2e6Rh2Nbo2bFqhPAJL4F4cAqGnBankXTDXw,1430 -pytz/zoneinfo/America/Cancun,sha256=EdV0Nw2WjM7VnjFHoq5jsSbLuuE7eP1OE74utEyWJG4,864 -pytz/zoneinfo/America/Caracas,sha256=mUNMFdDzZLav_ePA1ocBdmqVBierkeEszTIFpNCm5J0,250 -pytz/zoneinfo/America/Catamarca,sha256=uMCJXXGYmNESHVvj5RYBZ0McrOdE14hwm17l25MgRW0,1062 -pytz/zoneinfo/America/Cayenne,sha256=4k7Iv1woX4atqePKrcvMQD2Vk9Tmma7rW_AW_R62pCc,184 -pytz/zoneinfo/America/Cayman,sha256=kayA_pdpMcSQ0FjIzotdcf-m1JYfbKE-qcFT8LC8zqA,182 -pytz/zoneinfo/America/Chicago,sha256=_roybr6I6sIAF6cYdIxGxoRpoef153Fty48dQ6bm9oY,3592 -pytz/zoneinfo/America/Chihuahua,sha256=3Ngzbedg8AzAqxsbQSG0jVRx-LxYlw1i3kx-Yzl-2Ic,1102 -pytz/zoneinfo/America/Ciudad_Juarez,sha256=ir4b27DiFrhL0H4fZQ92nEa-BBoPfLWIz3phU373dgE,1538 -pytz/zoneinfo/America/Coral_Harbour,sha256=kayA_pdpMcSQ0FjIzotdcf-m1JYfbKE-qcFT8LC8zqA,182 -pytz/zoneinfo/America/Cordoba,sha256=uniNihhMHnr4XK4WpwiPUnrAT0YPmvzqB6f0hRLtXvY,1062 -pytz/zoneinfo/America/Costa_Rica,sha256=74rYa6lrgIkyls9PkHo8SCYl9oOqiuG5S7MWdnJelP4,316 -pytz/zoneinfo/America/Coyhaique,sha256=beZXU6Lw5jx2Wp3dNRkFiofXGma2dM6DsqvJT9CSHdc,2126 -pytz/zoneinfo/America/Creston,sha256=illz0sYuLL8lIPK0Tkou6dL0Vck_D0W_3rRTOvFYRmQ,360 -pytz/zoneinfo/America/Cuiaba,sha256=GRJqkhRXNsOUcgjZddQxRIJdRYaw9pM_YLWbun88dkg,1402 -pytz/zoneinfo/America/Curacao,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Danmarkshavn,sha256=YRZAfUCoVtaL1L-MYMYMH1wyOaVQnfUo_gFnvMXSuzw,698 -pytz/zoneinfo/America/Dawson,sha256=rAHhyuMuyjf_eyA2SBG76MRBf_fj_xi5FAuiWVQgJhw,1614 -pytz/zoneinfo/America/Dawson_Creek,sha256=aJXCyP4j3ggE4wGCN-LrS9hpD_5zWHzQTeSAKTWEPUM,1050 -pytz/zoneinfo/America/Denver,sha256=MugZwApDs8NI9TnXANQlUE8guNBowWQY0m-ptpPndck,2460 -pytz/zoneinfo/America/Detroit,sha256=hecz8yqY2Cj5B61G3gLZdAVZvRgK9l0P90c_gN-uD5g,2230 -pytz/zoneinfo/America/Dominica,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Edmonton,sha256=-TkIfc3QlvaCf0p8COZ43Y1HRBAl-nARUi-JdXeK1vE,2332 -pytz/zoneinfo/America/Eirunepe,sha256=j5eExkjFaqtC-D8XK0rGzoF9yEgbSlTbPqVG9WKhEa8,642 -pytz/zoneinfo/America/El_Salvador,sha256=gvGN8Lkj-sGm2_rs8OUjAMf1oMtKp2Xes6UfWT0WqgU,224 -pytz/zoneinfo/America/Ensenada,sha256=SluV7xzZm24LgMXSUVt1cD1AlE7y_bdE65HhDIdXLcs,2458 -pytz/zoneinfo/America/Fort_Nelson,sha256=erfODr3DrSpz65kAdO7Ts2dGbZxvddEP6gx4BX3y2J0,2240 -pytz/zoneinfo/America/Fort_Wayne,sha256=kNKy9Kj9ICsiYYfCCbAggzMA7exf-GpGPMxoXocHUyw,1682 -pytz/zoneinfo/America/Fortaleza,sha256=rjiSB0q1cBuMDOM9orW_uwe5UOLBwTlfjFotwOYe1mU,702 -pytz/zoneinfo/America/Glace_Bay,sha256=G8DGLGCapH_aYCF_OhaL5Qonf7FOAgAPwelO5htCWBc,2192 -pytz/zoneinfo/America/Godthab,sha256=KGXrMN-YkYpVCgLdpcfwMFQ77EsRAGsjUCG3yAUvVfw,1889 -pytz/zoneinfo/America/Goose_Bay,sha256=JgaLueghSvX2g725FOfIgpgvsqxZGykWOhAZWGpQZRY,3210 -pytz/zoneinfo/America/Grand_Turk,sha256=4YOFEPK60Bel2_fCsY6vSZxUcMJKjiKtyOf_Q0khEwU,1834 -pytz/zoneinfo/America/Grenada,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Guadeloupe,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Guatemala,sha256=dugUgCd6QY52yHkHuUP4jRWzo5x439IQigaYCvEF46Q,280 -pytz/zoneinfo/America/Guayaquil,sha256=j2UuIo-4RgSOlTNfu77mhZ92waNTeKFSvmoVemJooT0,232 -pytz/zoneinfo/America/Guyana,sha256=R0bOvCRDC8SRIexmhsduPdHbbRPwI2GviD9otExiUrk,248 -pytz/zoneinfo/America/Halifax,sha256=TZpmc5PwWoLfTfQoQ_b3U17BE2iVKSeNkR0Ho8mbTn8,3424 -pytz/zoneinfo/America/Havana,sha256=HUQeAuKBsEkI5SLZjqynXICOUVOajkKzKH5r-Ov5Odc,2416 -pytz/zoneinfo/America/Hermosillo,sha256=ixYKestLmS7gWobk9Kq6FtLZo1yqbWActrFUKluzctw,388 -pytz/zoneinfo/America/Indiana/Indianapolis,sha256=kNKy9Kj9ICsiYYfCCbAggzMA7exf-GpGPMxoXocHUyw,1682 -pytz/zoneinfo/America/Indiana/Knox,sha256=CsvZ5BKw2qVav3x_F8CU9taJdDk7jX41Cfsqms6jXV8,2444 -pytz/zoneinfo/America/Indiana/Marengo,sha256=f3tQ-lgMSUA7nvn64pXhKtJL7mWzGajoCega5MEJSbI,1738 -pytz/zoneinfo/America/Indiana/Petersburg,sha256=A88OHuM0Rg3iMLHjKgXq_d2jZCdVSytUQs-9W0KcFyQ,1920 -pytz/zoneinfo/America/Indiana/Tell_City,sha256=4dWqAr9Y2BXfL4pAQk-81c3gGl2cNdHXOD7_wJhhhn8,1700 -pytz/zoneinfo/America/Indiana/Vevay,sha256=H7VR2G-_sD_C5Rm4P3g1iRC1FWCPg4m0MGD3P1PLzsk,1430 -pytz/zoneinfo/America/Indiana/Vincennes,sha256=62mAxT7APFCaoygflnEzdOpe-fuW1yObI6m6EUUcS7A,1710 -pytz/zoneinfo/America/Indiana/Winamac,sha256=aZGM2jR8CH9BHSUq7XygiweDd6dorXLPXg246XsbR6s,1794 -pytz/zoneinfo/America/Indianapolis,sha256=kNKy9Kj9ICsiYYfCCbAggzMA7exf-GpGPMxoXocHUyw,1682 -pytz/zoneinfo/America/Inuvik,sha256=6J-mapDnrk9A1LtswoE34tqSy_ufedcEBNxixkrEjIo,2074 -pytz/zoneinfo/America/Iqaluit,sha256=feOnxAN0N0r-M1qlkrA4JMyawoc0tqae0iiBCPDAs4k,2202 -pytz/zoneinfo/America/Jamaica,sha256=wlagieUPRf5-beie-h7QsONbNzjGsm8vMs8uf28pw28,482 -pytz/zoneinfo/America/Jujuy,sha256=PGmAehypCxj0XCenCSWqylDIPbKLK0DlrwJK_24D590,1034 -pytz/zoneinfo/America/Juneau,sha256=k7hxb0aGRnfnE-DBi3LkcjAzRPyAf0_Hw0vVFfjGeb0,2353 -pytz/zoneinfo/America/Kentucky/Louisville,sha256=tP072xV_n_vIQjxxcJ77AGeGj6yL1KPpn3fwids9g1U,2788 -pytz/zoneinfo/America/Kentucky/Monticello,sha256=LtdyCo85BrXQs6rlH61Ym-8KqWHH6PwAOjD0QxhIdzM,2368 -pytz/zoneinfo/America/Knox_IN,sha256=CsvZ5BKw2qVav3x_F8CU9taJdDk7jX41Cfsqms6jXV8,2444 -pytz/zoneinfo/America/Kralendijk,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/La_Paz,sha256=hqfD8LQHupdZhji2e93_9pOQAT-R7muzzjP0nyfbFXY,218 -pytz/zoneinfo/America/Lima,sha256=HHgTnDUnCZzibvL0MrG8qyOuvjmYYw3e3R5VbnxMZs8,392 -pytz/zoneinfo/America/Los_Angeles,sha256=aJd7ua1tGG_vxser02AQpm4wAI3LLTdgh6QcSYYecmg,2852 -pytz/zoneinfo/America/Louisville,sha256=tP072xV_n_vIQjxxcJ77AGeGj6yL1KPpn3fwids9g1U,2788 -pytz/zoneinfo/America/Lower_Princes,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Maceio,sha256=3R5DlSe32kQDmoSVIWpcyk2o7qohr-rliwqDSGFIMyQ,730 -pytz/zoneinfo/America/Managua,sha256=xBzF01AHn2E2fD8Qdy-DHFe36UqoeNpKPfChduBKWdk,430 -pytz/zoneinfo/America/Manaus,sha256=F6RLOOeOi9lymZiQmQ9pR8tFpPZ6EguNdPfOc6BhXDE,590 -pytz/zoneinfo/America/Marigot,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Martinique,sha256=fMs80kOU2YFvC0f9y2eje97JeAtTYBamXrnlTunNLzQ,232 -pytz/zoneinfo/America/Matamoros,sha256=fq-PqdmZrQ98UsFmHA9ivjBZv5GEBRTOuLQ5Cu5ajW8,1418 -pytz/zoneinfo/America/Mazatlan,sha256=BWH2NqVPA1PsyELPN_2BF8KllrsmQkqg1eujsQvnnx8,1060 -pytz/zoneinfo/America/Mendoza,sha256=xcOVtvRyVYFAU90y2QYwpyQhpMLyAp7-Fxvku4kgl0c,1062 -pytz/zoneinfo/America/Menominee,sha256=Arv9WLbfhNcpRsUjHDU757BEdwlp08Gt30AixG3gZ04,2274 -pytz/zoneinfo/America/Merida,sha256=SVNEHCazjomftnuPVBayFI-E-IQ0WmluHfTpHP0h3d0,1004 -pytz/zoneinfo/America/Metlakatla,sha256=twmieGTVY2V-U8nFxqvx7asYv8GVjeWdLtrOI7UApVI,1423 -pytz/zoneinfo/America/Mexico_City,sha256=Uog2-FMWz2o12jR6sK9vemJamLeo6OEFMQR3s0xTxkc,1222 -pytz/zoneinfo/America/Miquelon,sha256=l5txBJYe9HTRZlILcbSL_HNDYrjUb0ouecNy7QEkg9c,1652 -pytz/zoneinfo/America/Moncton,sha256=Wmv-bk9aKKcWWzOpc1UFu67HOfwaIk2Wmh3LgqGctys,3154 -pytz/zoneinfo/America/Monterrey,sha256=YixTESJubf6ZBUXy6g32hAM2gR4GXXPqOU4tv0L3kG0,1114 -pytz/zoneinfo/America/Montevideo,sha256=dQEBE4mjZPtyRjKXK6Z-bMHJdFqpwhIzxDH4x04rKYk,1496 -pytz/zoneinfo/America/Montreal,sha256=pYehoWB0Ofe6woPhgV8r26-5ZJpFPRjgbC5E5pltiI8,3494 -pytz/zoneinfo/America/Montserrat,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Nassau,sha256=pYehoWB0Ofe6woPhgV8r26-5ZJpFPRjgbC5E5pltiI8,3494 -pytz/zoneinfo/America/New_York,sha256=6e0H177gx2qdRC0JHvHwFmj-58TyYBTAqGixn-bBipU,3552 -pytz/zoneinfo/America/Nipigon,sha256=pYehoWB0Ofe6woPhgV8r26-5ZJpFPRjgbC5E5pltiI8,3494 -pytz/zoneinfo/America/Nome,sha256=2izM3-P-PqJ9za6MdhzFfMvPFNq7Gim69tAvEwPeY2s,2367 -pytz/zoneinfo/America/Noronha,sha256=feeRAijQqKylZgqe84nKhsFLycT5zIBm7mLIvdyGw4w,702 -pytz/zoneinfo/America/North_Dakota/Beulah,sha256=qtgbqNu8M3AkHF2n-_oSps1pYT4SxgclbkkPKbXaBHs,2396 -pytz/zoneinfo/America/North_Dakota/Center,sha256=9ZWbK9YKkquULyBUFS3Lr_idxbt7V7y4W4EO0Kn20sw,2396 -pytz/zoneinfo/America/North_Dakota/New_Salem,sha256=DH_bsQfuUnK2obdb06KgisO4XLqht12BXdrgUsZZveg,2396 -pytz/zoneinfo/America/Nuuk,sha256=KGXrMN-YkYpVCgLdpcfwMFQ77EsRAGsjUCG3yAUvVfw,1889 -pytz/zoneinfo/America/Ojinaga,sha256=b38Q_7VdkCZzaVwb7OXuddihJAzUKPTTqXcmpBm1ntE,1524 -pytz/zoneinfo/America/Panama,sha256=kayA_pdpMcSQ0FjIzotdcf-m1JYfbKE-qcFT8LC8zqA,182 -pytz/zoneinfo/America/Pangnirtung,sha256=feOnxAN0N0r-M1qlkrA4JMyawoc0tqae0iiBCPDAs4k,2202 -pytz/zoneinfo/America/Paramaribo,sha256=Z7UZvNlgd-qEUHjEPYXIkLNTgjMcCzk9EfUUEmUyd7M,248 -pytz/zoneinfo/America/Phoenix,sha256=illz0sYuLL8lIPK0Tkou6dL0Vck_D0W_3rRTOvFYRmQ,360 -pytz/zoneinfo/America/Port-au-Prince,sha256=09ZAJd4IOiMpfdpUuF1U44R_hRt6BvpAkFXOnYO9yOM,1434 -pytz/zoneinfo/America/Port_of_Spain,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Porto_Acre,sha256=0gpJUl46hQbp0P6Xj1S0NArIWeAryuuDXjsldvB5GHE,614 -pytz/zoneinfo/America/Porto_Velho,sha256=uSMV2hZWj-VyBhFBwC950wcThfN3jq6KlycESmQTLOA,562 -pytz/zoneinfo/America/Puerto_Rico,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Punta_Arenas,sha256=tR5uIf1351AWFqrqNtmXnhQWnKREmJaZqKBzaWRVMTQ,1902 -pytz/zoneinfo/America/Rainy_River,sha256=7P-_YQrneFcon7QKSTOnkiGjEppFDn3Z48MJ1qq8VBw,2868 -pytz/zoneinfo/America/Rankin_Inlet,sha256=nXgqjL3O2BV0em-Xk8qVRRZb_X0yQmHE6vmSSvI9Kzc,2066 -pytz/zoneinfo/America/Recife,sha256=bJ_HE0-JFio4-owpZ0pLO8U3ai0fiGu8QHL0DexLiLc,702 -pytz/zoneinfo/America/Regina,sha256=yjqT08pHbICYe83H8JmtaDBvCFqRv7Tfze3Y8xuXukw,980 -pytz/zoneinfo/America/Resolute,sha256=CnMU2dBI-63vt8-J0Q1Ropx-8b9pRCLjhvrycMIedGg,2066 -pytz/zoneinfo/America/Rio_Branco,sha256=0gpJUl46hQbp0P6Xj1S0NArIWeAryuuDXjsldvB5GHE,614 -pytz/zoneinfo/America/Rosario,sha256=uniNihhMHnr4XK4WpwiPUnrAT0YPmvzqB6f0hRLtXvY,1062 -pytz/zoneinfo/America/Santa_Isabel,sha256=SluV7xzZm24LgMXSUVt1cD1AlE7y_bdE65HhDIdXLcs,2458 -pytz/zoneinfo/America/Santarem,sha256=VmZP9S5pPucFxyqAOV908EmWXQZvgCgWLmlJJTUl0LE,588 -pytz/zoneinfo/America/Santiago,sha256=0CDw13dCMUsoquMupoJgupkzAUNhDK6E0lVxURA7osA,2515 -pytz/zoneinfo/America/Santo_Domingo,sha256=DKtaEj8fQ92ybITTWU4Bm160S9pzJmUVbjaWRnenxU4,458 -pytz/zoneinfo/America/Sao_Paulo,sha256=BMBnRO4_4HjvO4t3njjrMGZr-ZPmegkvyvL8KPY6ZM4,1430 -pytz/zoneinfo/America/Scoresbysund,sha256=K-qkiMCCFgOe8ccPMABA-lDjc9vb6wpluBOCVfiBdLI,1935 -pytz/zoneinfo/America/Shiprock,sha256=MugZwApDs8NI9TnXANQlUE8guNBowWQY0m-ptpPndck,2460 -pytz/zoneinfo/America/Sitka,sha256=aiS7Fk37hZpzZ9VkeJQeF-BqTLRC1QOTCgMAJwT8UxA,2329 -pytz/zoneinfo/America/St_Barthelemy,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/St_Johns,sha256=r1-17uKv27eZ3JsVkw_DLZQbo6wvjuuVu7C2pDsmOgI,3655 -pytz/zoneinfo/America/St_Kitts,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/St_Lucia,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/St_Thomas,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/St_Vincent,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Swift_Current,sha256=RRKOF7vZC8VvYxD8PP4J1_hUPayKBP7Lu80avRkfPDY,560 -pytz/zoneinfo/America/Tegucigalpa,sha256=EzOz7ntTlreMq69JZ2CcAb8Ps98V9bUMN480tpPIyw4,252 -pytz/zoneinfo/America/Thule,sha256=8xuPRaZU8RgO5ECqFYHYmnHioc81sBOailkVu8Y02i8,1502 -pytz/zoneinfo/America/Thunder_Bay,sha256=pYehoWB0Ofe6woPhgV8r26-5ZJpFPRjgbC5E5pltiI8,3494 -pytz/zoneinfo/America/Tijuana,sha256=SluV7xzZm24LgMXSUVt1cD1AlE7y_bdE65HhDIdXLcs,2458 -pytz/zoneinfo/America/Toronto,sha256=pYehoWB0Ofe6woPhgV8r26-5ZJpFPRjgbC5E5pltiI8,3494 -pytz/zoneinfo/America/Tortola,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Vancouver,sha256=sknKH0jSPWam-DHfM35qXs8Nam7d5TFlkUI9Sgxryyg,2892 -pytz/zoneinfo/America/Virgin,sha256=hJHlV_-AGoMGUWuMpZRv9fLmghrzFHfrR9fRkcxaZJc,246 -pytz/zoneinfo/America/Whitehorse,sha256=TrR6PCnYG-mSClBMohqlP8qnYhXMUsydI-L-quXFxyM,1614 -pytz/zoneinfo/America/Winnipeg,sha256=7P-_YQrneFcon7QKSTOnkiGjEppFDn3Z48MJ1qq8VBw,2868 -pytz/zoneinfo/America/Yakutat,sha256=tFwnKbvwhyyn4LNTAn5ye_JWDdxjCerNDt7oOwUwO2M,2305 -pytz/zoneinfo/America/Yellowknife,sha256=-TkIfc3QlvaCf0p8COZ43Y1HRBAl-nARUi-JdXeK1vE,2332 -pytz/zoneinfo/Antarctica/Casey,sha256=VeaLOxTfDyjfGXq5Ul95JEIMXNWHSW-0N3yOoS7VK-c,423 -pytz/zoneinfo/Antarctica/Davis,sha256=XB12dEq0Q-3XkzBNTNC7G1fzH-WxxctIuZqI3zp8ypI,283 -pytz/zoneinfo/Antarctica/DumontDUrville,sha256=nB36HBWZTdh3TlP0DLFNz1KRQ0aHIfHbp7LC4Urp9fA,172 -pytz/zoneinfo/Antarctica/Macquarie,sha256=ie7RlaU8RHTorVVj-MX8StKMqx_oXf4UH2PUqpzcwe0,2260 -pytz/zoneinfo/Antarctica/Mawson,sha256=EjIFbqRdr2ZJBaI1XvoWRptnnW1LFrlhydxDDuIQjSI,185 -pytz/zoneinfo/Antarctica/McMurdo,sha256=gADjoyPo_QISQU6UJrAgcHp3HDaMoOFRdH-d23uBSyc,2437 -pytz/zoneinfo/Antarctica/Palmer,sha256=HTZY0M8td7oUx5REPgRCHuqKg5V3fjJEi4lYBNL4Etg,1404 -pytz/zoneinfo/Antarctica/Rothera,sha256=_9NY-f8vkozQYrjbUHP5YjcICg0-LuyA9PnIeK123RU,150 -pytz/zoneinfo/Antarctica/South_Pole,sha256=gADjoyPo_QISQU6UJrAgcHp3HDaMoOFRdH-d23uBSyc,2437 -pytz/zoneinfo/Antarctica/Syowa,sha256=oCKH7uafN8R1o-ijXGoT5U1JZxwvoLzJu_2Cqyi2hUM,151 -pytz/zoneinfo/Antarctica/Troll,sha256=fjcYppwr1FnjEssee-RLgGOANzoUyfjse-RGK46PR2E,1148 -pytz/zoneinfo/Antarctica/Vostok,sha256=KfftwdzK6PkMDz0d-D3z4HKIBgY9KqsqHnTnqsPMrUg,213 -pytz/zoneinfo/Arctic/Longyearbyen,sha256=XuR19xoPwaMvrrhJ-MOcbnqmbW1B7HQrl7OnQ2s7BwE,2298 -pytz/zoneinfo/Asia/Aden,sha256=oCKH7uafN8R1o-ijXGoT5U1JZxwvoLzJu_2Cqyi2hUM,151 -pytz/zoneinfo/Asia/Almaty,sha256=lPLWXk2f1mWYRQZFkIrq_5HkhocsUBis0M-yhdDHcBQ,983 -pytz/zoneinfo/Asia/Amman,sha256=Qv4cXXw7KBQWE882cgj0kjQ3wh1vpV1orJ2v2Jjxr2U,1433 -pytz/zoneinfo/Asia/Anadyr,sha256=WqKnHo5IHSWZ08d2sS5ytHtv0MQMoczP3W9zbDDrbYU,1174 -pytz/zoneinfo/Asia/Aqtau,sha256=4n654FZtDssXSfhQszjZG5OmtbE2zo1KbiWcYrFJg00,969 -pytz/zoneinfo/Asia/Aqtobe,sha256=1oFHTb-ybcTqLXm0r1ZOVgdYMTHlGoNs-Pgvux50d3E,997 -pytz/zoneinfo/Asia/Ashgabat,sha256=-sfGnRumio7_Bs8w9YH4xRDWgjB3wBeW7c0C56Qqk64,605 -pytz/zoneinfo/Asia/Ashkhabad,sha256=-sfGnRumio7_Bs8w9YH4xRDWgjB3wBeW7c0C56Qqk64,605 -pytz/zoneinfo/Asia/Atyrau,sha256=_U8COUIE9nG_HKddZE1Q0sPuz3rMwfjwmfnVDY_vSmg,977 -pytz/zoneinfo/Asia/Baghdad,sha256=S-plKI4zCLqI0idGABEk3oRTazNyrIj2T98-EtWtZD8,969 -pytz/zoneinfo/Asia/Bahrain,sha256=wklGY3WPGp-z1OUwb_KOHzRTwBndt1RfDg9Uttt36G4,185 -pytz/zoneinfo/Asia/Baku,sha256=6_hq98SGG0j0JA8qYx96WcIMZSLW4w460QXh_OM_ccg,1213 -pytz/zoneinfo/Asia/Bangkok,sha256=hf_5PVegQcFSS60CjS80C7h-TGOrfQ4ncm83N8VmZkk,185 -pytz/zoneinfo/Asia/Barnaul,sha256=3zeUimLTMrIZE0vX6XHFvB3MoqExoVbE5CSm6GV0zf0,1207 -pytz/zoneinfo/Asia/Beirut,sha256=_Z_2ZAg_iL9vU51JDB8CB04uXBDrf1kLIis-JnXaS2o,2154 -pytz/zoneinfo/Asia/Bishkek,sha256=IOoUyjABILCkXu1rjCIqSwAufRYFklc5YAC4jdhVw6Q,969 -pytz/zoneinfo/Asia/Brunei,sha256=D5qtyWJ_SM8bTQeJJIYhqqojxlVKbrFC1EYMDU9GzXQ,469 -pytz/zoneinfo/Asia/Calcutta,sha256=6Qw0EDbLcgMgDik8s7UTJn4QSjmllPNeGVJU5rwKF88,285 -pytz/zoneinfo/Asia/Chita,sha256=LbSlS23swFkANUScg8zkNR0imANWNfOIaYd39HbLdIQ,1207 -pytz/zoneinfo/Asia/Choibalsan,sha256=qUkXRsTc_u7B90JxULSu7yzKbGtGfKcfEFIasGPC2ec,877 -pytz/zoneinfo/Asia/Chongqing,sha256=ZP_C5DqUQ1oEPAQNHTr36S0DGtx453N68YYbqk7u8-Y,561 -pytz/zoneinfo/Asia/Chungking,sha256=ZP_C5DqUQ1oEPAQNHTr36S0DGtx453N68YYbqk7u8-Y,561 -pytz/zoneinfo/Asia/Colombo,sha256=w52L7bgT4m5hcgRuevIPY83xytfkBmkLhnKMwp16KsY,358 -pytz/zoneinfo/Asia/Dacca,sha256=-xulJ2KVhvKp6rlZLMydpw7oXVirk-riEH-181xPE54,323 -pytz/zoneinfo/Asia/Damascus,sha256=EthGheaHWmy5IrLCc9NmM3jvASQFHt8TsBF07I1tgbg,1873 -pytz/zoneinfo/Asia/Dhaka,sha256=-xulJ2KVhvKp6rlZLMydpw7oXVirk-riEH-181xPE54,323 -pytz/zoneinfo/Asia/Dili,sha256=2A9uFmwSwoFA5o2ek1LA0ucohPnM42ghWvD9D5TdnJk,257 -pytz/zoneinfo/Asia/Dubai,sha256=pmdhPhaJRwKwONvxiZNGeFSICjlWzyY9JlFHv-H9upY,151 -pytz/zoneinfo/Asia/Dushanbe,sha256=koYnnYWuFsBXd1vJfZsGdpwnbFHEwvkGBmSrrx3KIss,577 -pytz/zoneinfo/Asia/Famagusta,sha256=CFrcygd8ude5x6OEtfM_Dw0KYHoxpPPzq46KoHVxjjc,2028 -pytz/zoneinfo/Asia/Gaza,sha256=t0YxcUQL53VNKnKbKijn0OE_MaryEynonabse-iTtzs,3844 -pytz/zoneinfo/Asia/Harbin,sha256=ZP_C5DqUQ1oEPAQNHTr36S0DGtx453N68YYbqk7u8-Y,561 -pytz/zoneinfo/Asia/Hebron,sha256=6Y0USHKx-xoCxCr_WpCuM3olP1vUGnzrcnGiyQFcqdQ,3872 -pytz/zoneinfo/Asia/Ho_Chi_Minh,sha256=Lnv1vpUNAXBo8v0b9d9AQpy-AEyO5Qa2Ig0PvDkjrmU,337 -pytz/zoneinfo/Asia/Hong_Kong,sha256=al_O4kPlq5JpgkLYjEaZzrcgiiLul9NC0R5B69JVWhc,1233 -pytz/zoneinfo/Asia/Hovd,sha256=Zn4PLGlD-URJDsbChor5bqWTzuAil2tbrGJW0j5TLbs,877 -pytz/zoneinfo/Asia/Irkutsk,sha256=IVuoXCwdeI-KIUfFkEt6yBjqYP3V9GTrF-_WLnffFzk,1229 -pytz/zoneinfo/Asia/Istanbul,sha256=Jk4wjndDta_uLWc8W1dWdjbavJJbsL5ROTmZboVnGKU,1933 -pytz/zoneinfo/Asia/Jakarta,sha256=TvEzBvSzfzFCdOsMAZ0QgR95JA5xf3kAZONhy5gEXRE,383 -pytz/zoneinfo/Asia/Jayapura,sha256=ihzUd-L8HUVqG-Na10MyPE-YYwjVFj-xerqjTN4EJZs,221 -pytz/zoneinfo/Asia/Jerusalem,sha256=JUuWQmW5Tha0pJjw61Q5aN7CX0z4D7ops9OOSnda6Dc,2388 -pytz/zoneinfo/Asia/Kabul,sha256=JZEbo8bSj_L7HnXUm2gAUlNlCvJlRJhFkSHCg5o3ggk,194 -pytz/zoneinfo/Asia/Kamchatka,sha256=KY1PlJvRSNkY_5hyJBxj5DDweeYVQaBK05ZgL3kdcCY,1152 -pytz/zoneinfo/Asia/Karachi,sha256=iB-mWMTXUyfBwAkZdz8_UmEw0xsgxIub-KNI7akzhkk,379 -pytz/zoneinfo/Asia/Kashgar,sha256=F1ZOdZZDsVHwDJinksR-hjcqPzqOljvdreZIWFulJxY,151 -pytz/zoneinfo/Asia/Kathmandu,sha256=_RsfeSWbCr8kM4YRJi7Xv6hAEiHW14IFhsXsfhbPjoM,198 -pytz/zoneinfo/Asia/Katmandu,sha256=_RsfeSWbCr8kM4YRJi7Xv6hAEiHW14IFhsXsfhbPjoM,198 -pytz/zoneinfo/Asia/Khandyga,sha256=bKfmw6k5qYDQsEHG3Mv-VYis3YhCeV7qijDxfxQNn_g,1257 -pytz/zoneinfo/Asia/Kolkata,sha256=6Qw0EDbLcgMgDik8s7UTJn4QSjmllPNeGVJU5rwKF88,285 -pytz/zoneinfo/Asia/Krasnoyarsk,sha256=D5KE_1wWSD2YdixDy8n3LBNaAlE1_y3TWXw6NrxFKKA,1193 -pytz/zoneinfo/Asia/Kuala_Lumpur,sha256=XmeVImeqcJ8hJzm7TjAti1nWJAxawOqq7jIzDnHX2hI,401 -pytz/zoneinfo/Asia/Kuching,sha256=D5qtyWJ_SM8bTQeJJIYhqqojxlVKbrFC1EYMDU9GzXQ,469 -pytz/zoneinfo/Asia/Kuwait,sha256=oCKH7uafN8R1o-ijXGoT5U1JZxwvoLzJu_2Cqyi2hUM,151 -pytz/zoneinfo/Asia/Macao,sha256=MvAkRyRsrA2r052ItlyF5bh2FheRjI0jPwg0uIiH2Yk,1227 -pytz/zoneinfo/Asia/Macau,sha256=MvAkRyRsrA2r052ItlyF5bh2FheRjI0jPwg0uIiH2Yk,1227 -pytz/zoneinfo/Asia/Magadan,sha256=HccEEXBQvMmLoC_JE-zP_MlLAZ1WmNLQLfM3tJt55M4,1208 -pytz/zoneinfo/Asia/Makassar,sha256=OhJtCqSTEU-u5n0opBVO5Bu-wQzcYPy9S_6aAhJXgOw,254 -pytz/zoneinfo/Asia/Manila,sha256=8xTSHFQuYVdW3ThdNqiWzVe6Fv75g_5rTQYURLvxrJ4,422 -pytz/zoneinfo/Asia/Muscat,sha256=pmdhPhaJRwKwONvxiZNGeFSICjlWzyY9JlFHv-H9upY,151 -pytz/zoneinfo/Asia/Nicosia,sha256=0Unm0IFT7HyGeQ7F3vTa_-klfysCgrulqFO6BD1plZU,2002 -pytz/zoneinfo/Asia/Novokuznetsk,sha256=pyxxtSUtYDeVmFk0Cg-F33laZS0iKtde9_GJnL9f0KM,1151 -pytz/zoneinfo/Asia/Novosibirsk,sha256=5K2-Gx15ThlHfolyW85S5zREtAcMjeHBYWK4E8x2LdY,1207 -pytz/zoneinfo/Asia/Omsk,sha256=HyXIWItJXBKVHUzWcQPi1Mmd6ZLmZk-QhRUo9Kv2XOI,1193 -pytz/zoneinfo/Asia/Oral,sha256=WQT4qRmC9RI_ll8zB9FvkAL8ezGb8qoqWd75GTlC7kQ,991 -pytz/zoneinfo/Asia/Phnom_Penh,sha256=hf_5PVegQcFSS60CjS80C7h-TGOrfQ4ncm83N8VmZkk,185 -pytz/zoneinfo/Asia/Pontianak,sha256=inOXwuKtjKv1z_eliPZSIqjSt6whtuxhPeG1YpjU_BQ,353 -pytz/zoneinfo/Asia/Pyongyang,sha256=_-g3GnDAtfDX4XAktXH9jFouLUDmOovnjoOfvRpUDsE,237 -pytz/zoneinfo/Asia/Qatar,sha256=wklGY3WPGp-z1OUwb_KOHzRTwBndt1RfDg9Uttt36G4,185 -pytz/zoneinfo/Asia/Qostanay,sha256=HIjln8QIPNRU6MkWzyPi6vDrjlmVZ4XzFxcUHtXMi7s,1025 -pytz/zoneinfo/Asia/Qyzylorda,sha256=JZLNN6NuLkqaWEeVaCZiW_gL6BrIFL9lr65iK7myVPg,1011 -pytz/zoneinfo/Asia/Rangoon,sha256=_YHASq4Z5YcUILIdhEzg27CGLzarUHPDHs1Dj0QgNGM,254 -pytz/zoneinfo/Asia/Riyadh,sha256=oCKH7uafN8R1o-ijXGoT5U1JZxwvoLzJu_2Cqyi2hUM,151 -pytz/zoneinfo/Asia/Saigon,sha256=Lnv1vpUNAXBo8v0b9d9AQpy-AEyO5Qa2Ig0PvDkjrmU,337 -pytz/zoneinfo/Asia/Sakhalin,sha256=xzAor82ihAe-yXEwC6OWiMzo9b6Z-oQl39NIkU5Hhbs,1188 -pytz/zoneinfo/Asia/Samarkand,sha256=zJKSRt3lEvd6Qvg9b49QAyO4cTJyVnTKyPYcyudpHxk,563 -pytz/zoneinfo/Asia/Seoul,sha256=LI9LsV3XcJC0l-KoQf8zI-y7rk-du57erS-N2Ptdi7Q,617 -pytz/zoneinfo/Asia/Shanghai,sha256=ZP_C5DqUQ1oEPAQNHTr36S0DGtx453N68YYbqk7u8-Y,561 -pytz/zoneinfo/Asia/Singapore,sha256=XmeVImeqcJ8hJzm7TjAti1nWJAxawOqq7jIzDnHX2hI,401 -pytz/zoneinfo/Asia/Srednekolymsk,sha256=efaaT8iFHrcccp-VZKNMvtTuPLNjG5V9JH5KKHhH3SI,1194 -pytz/zoneinfo/Asia/Taipei,sha256=DMmQwOpPql25ue3Nf8vAKKT4em06D1Z9rHbLIitxixk,761 -pytz/zoneinfo/Asia/Tashkent,sha256=apRPy251fSRy_ixsg3BOZNmUbHdO86P5-PdgC1Xws7U,577 -pytz/zoneinfo/Asia/Tbilisi,sha256=zQ-2bVq5_USUSbwN6q0qvWjD-HXkKaH4ifMVq1lEeIM,1021 -pytz/zoneinfo/Asia/Tehran,sha256=Lb2H9BCBXtz819FL6E3gBA7w2ROiIgPgx-f08XpqkVo,1248 -pytz/zoneinfo/Asia/Tel_Aviv,sha256=JUuWQmW5Tha0pJjw61Q5aN7CX0z4D7ops9OOSnda6Dc,2388 -pytz/zoneinfo/Asia/Thimbu,sha256=G2nTQVEMmKlWt0B74_fUAL7KQ3YAu__J6HciiYs2IyU,189 -pytz/zoneinfo/Asia/Thimphu,sha256=G2nTQVEMmKlWt0B74_fUAL7KQ3YAu__J6HciiYs2IyU,189 -pytz/zoneinfo/Asia/Tokyo,sha256=oCueZgRNxcNcX3ZGdif9y6Su4cyVhga4XHdwlcrYLOs,309 -pytz/zoneinfo/Asia/Tomsk,sha256=cr0ULZgWBnQfzDiJeYmqpA7Xo5QRzurvrHsrbZsnhOQ,1207 -pytz/zoneinfo/Asia/Ujung_Pandang,sha256=OhJtCqSTEU-u5n0opBVO5Bu-wQzcYPy9S_6aAhJXgOw,254 -pytz/zoneinfo/Asia/Ulaanbaatar,sha256=qUkXRsTc_u7B90JxULSu7yzKbGtGfKcfEFIasGPC2ec,877 -pytz/zoneinfo/Asia/Ulan_Bator,sha256=qUkXRsTc_u7B90JxULSu7yzKbGtGfKcfEFIasGPC2ec,877 -pytz/zoneinfo/Asia/Urumqi,sha256=F1ZOdZZDsVHwDJinksR-hjcqPzqOljvdreZIWFulJxY,151 -pytz/zoneinfo/Asia/Ust-Nera,sha256=zsG8kgnw0Fcs5N2WwNTVmvWkTlpwf7Oo8y68HcXjYyw,1238 -pytz/zoneinfo/Asia/Vientiane,sha256=hf_5PVegQcFSS60CjS80C7h-TGOrfQ4ncm83N8VmZkk,185 -pytz/zoneinfo/Asia/Vladivostok,sha256=XMQLMh5SPbI6C4R3UO4KhbnG4hWVkHNedzCQeqxFk6A,1194 -pytz/zoneinfo/Asia/Yakutsk,sha256=PPNrRGgg9jefOUM-6M8XqaIm-ElfmRZSWAtSGKLzNXQ,1193 -pytz/zoneinfo/Asia/Yangon,sha256=_YHASq4Z5YcUILIdhEzg27CGLzarUHPDHs1Dj0QgNGM,254 -pytz/zoneinfo/Asia/Yekaterinburg,sha256=4NyEW6Xjr4UsWPh63HIPI4G6GT_tVG1Xkgc2xbwGjzA,1229 -pytz/zoneinfo/Asia/Yerevan,sha256=FM0pUA4NbTWBb_CsJ5KCLVrLoNmad7njBKqFrJBDoxE,1137 -pytz/zoneinfo/Atlantic/Azores,sha256=66hDxaK8xFnktLMrpNxkD4r1gGkhS-PEpleuwzuGRA0,3442 -pytz/zoneinfo/Atlantic/Bermuda,sha256=LNGKfMsnYvwImjTyzXrLhMOHHDu7qI67RbYNKvvI15I,2396 -pytz/zoneinfo/Atlantic/Canary,sha256=ymK9ufqphvNjDK3hzikN4GfkcR3QeCBiPKyVc6FjlbA,1897 -pytz/zoneinfo/Atlantic/Cape_Verde,sha256=o92pLdLFX_b9vUiq3rNpca4tupIO3dx9rNrnPcA8474,256 -pytz/zoneinfo/Atlantic/Faeroe,sha256=NibdZPZtapnYR_myIZnMdTaSKGsOBGgujj0_T2NvAzs,1815 -pytz/zoneinfo/Atlantic/Faroe,sha256=NibdZPZtapnYR_myIZnMdTaSKGsOBGgujj0_T2NvAzs,1815 -pytz/zoneinfo/Atlantic/Jan_Mayen,sha256=XuR19xoPwaMvrrhJ-MOcbnqmbW1B7HQrl7OnQ2s7BwE,2298 -pytz/zoneinfo/Atlantic/Madeira,sha256=lYY85MC5-GUKExm353ixwtZDxasYavTTWELvv5RXLxE,3377 -pytz/zoneinfo/Atlantic/Reykjavik,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Atlantic/South_Georgia,sha256=I9SAcPPumy6Xf9P7dg2aE16oxwDIqyKFqinJTC-XsgM,150 -pytz/zoneinfo/Atlantic/St_Helena,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Atlantic/Stanley,sha256=siEjXTAuTum_4XGtS98MBE34XW_5xgXShEX5OMnSFjo,1200 -pytz/zoneinfo/Australia/ACT,sha256=QsOFdYWxbbL4_9R7oZ-qYPRzNA3o1P6TIOp76GFgWQY,2190 -pytz/zoneinfo/Australia/Adelaide,sha256=ld2EbxU75oVgmPe703z-I6aqLg0Kmv62ZcCGzkT5R20,2208 -pytz/zoneinfo/Australia/Brisbane,sha256=eW6Qzze2t0-speJmmvt1JMzbkSadIKdE84XHc7JUtGc,419 -pytz/zoneinfo/Australia/Broken_Hill,sha256=3k_3ljTvS5GSfo7Xh6w71UgR3aAwYPBsnCJ-mlEYCqQ,2229 -pytz/zoneinfo/Australia/Canberra,sha256=QsOFdYWxbbL4_9R7oZ-qYPRzNA3o1P6TIOp76GFgWQY,2190 -pytz/zoneinfo/Australia/Currie,sha256=GLQSzgIfsWxOvmKOrhpfofWqINQf6h36NYy3mcq6gcg,2358 -pytz/zoneinfo/Australia/Darwin,sha256=fn0IZhIW98FAnzLig-_GBtW5LA54jajdeeUzg4tCGvo,325 -pytz/zoneinfo/Australia/Eucla,sha256=i1-XGG8I6E0dXIdWGF4DlkfDLWhiAxJ_3gMpt-nm_u4,456 -pytz/zoneinfo/Australia/Hobart,sha256=GLQSzgIfsWxOvmKOrhpfofWqINQf6h36NYy3mcq6gcg,2358 -pytz/zoneinfo/Australia/LHI,sha256=oyPFQzmRqWPrSXt9pNHQmEi_PvX11k2clknziOS6ud8,1846 -pytz/zoneinfo/Australia/Lindeman,sha256=xM6Udx22oLNoLR1Y7GQhHOYov8nw3xQNqgc_NVQ2JK4,475 -pytz/zoneinfo/Australia/Lord_Howe,sha256=oyPFQzmRqWPrSXt9pNHQmEi_PvX11k2clknziOS6ud8,1846 -pytz/zoneinfo/Australia/Melbourne,sha256=lvx_MQcunMc6u2smIrl8X427bLsXvjkgpCSdjYCTNBM,2190 -pytz/zoneinfo/Australia/NSW,sha256=QsOFdYWxbbL4_9R7oZ-qYPRzNA3o1P6TIOp76GFgWQY,2190 -pytz/zoneinfo/Australia/North,sha256=fn0IZhIW98FAnzLig-_GBtW5LA54jajdeeUzg4tCGvo,325 -pytz/zoneinfo/Australia/Perth,sha256=Al1DOUh4U_ofMUQSeVlzSyD3x7SUjP9dchSaBUGmeWg,446 -pytz/zoneinfo/Australia/Queensland,sha256=eW6Qzze2t0-speJmmvt1JMzbkSadIKdE84XHc7JUtGc,419 -pytz/zoneinfo/Australia/South,sha256=ld2EbxU75oVgmPe703z-I6aqLg0Kmv62ZcCGzkT5R20,2208 -pytz/zoneinfo/Australia/Sydney,sha256=QsOFdYWxbbL4_9R7oZ-qYPRzNA3o1P6TIOp76GFgWQY,2190 -pytz/zoneinfo/Australia/Tasmania,sha256=GLQSzgIfsWxOvmKOrhpfofWqINQf6h36NYy3mcq6gcg,2358 -pytz/zoneinfo/Australia/Victoria,sha256=lvx_MQcunMc6u2smIrl8X427bLsXvjkgpCSdjYCTNBM,2190 -pytz/zoneinfo/Australia/West,sha256=Al1DOUh4U_ofMUQSeVlzSyD3x7SUjP9dchSaBUGmeWg,446 -pytz/zoneinfo/Australia/Yancowinna,sha256=3k_3ljTvS5GSfo7Xh6w71UgR3aAwYPBsnCJ-mlEYCqQ,2229 -pytz/zoneinfo/Brazil/Acre,sha256=0gpJUl46hQbp0P6Xj1S0NArIWeAryuuDXjsldvB5GHE,614 -pytz/zoneinfo/Brazil/DeNoronha,sha256=feeRAijQqKylZgqe84nKhsFLycT5zIBm7mLIvdyGw4w,702 -pytz/zoneinfo/Brazil/East,sha256=BMBnRO4_4HjvO4t3njjrMGZr-ZPmegkvyvL8KPY6ZM4,1430 -pytz/zoneinfo/Brazil/West,sha256=F6RLOOeOi9lymZiQmQ9pR8tFpPZ6EguNdPfOc6BhXDE,590 -pytz/zoneinfo/CET,sha256=gS9Vrrbozend9HhuFetCVrIegs9fXSjaG60X2UVwysA,2933 -pytz/zoneinfo/CST6CDT,sha256=_roybr6I6sIAF6cYdIxGxoRpoef153Fty48dQ6bm9oY,3592 -pytz/zoneinfo/Canada/Atlantic,sha256=TZpmc5PwWoLfTfQoQ_b3U17BE2iVKSeNkR0Ho8mbTn8,3424 -pytz/zoneinfo/Canada/Central,sha256=7P-_YQrneFcon7QKSTOnkiGjEppFDn3Z48MJ1qq8VBw,2868 -pytz/zoneinfo/Canada/Eastern,sha256=pYehoWB0Ofe6woPhgV8r26-5ZJpFPRjgbC5E5pltiI8,3494 -pytz/zoneinfo/Canada/Mountain,sha256=-TkIfc3QlvaCf0p8COZ43Y1HRBAl-nARUi-JdXeK1vE,2332 -pytz/zoneinfo/Canada/Newfoundland,sha256=r1-17uKv27eZ3JsVkw_DLZQbo6wvjuuVu7C2pDsmOgI,3655 -pytz/zoneinfo/Canada/Pacific,sha256=sknKH0jSPWam-DHfM35qXs8Nam7d5TFlkUI9Sgxryyg,2892 -pytz/zoneinfo/Canada/Saskatchewan,sha256=yjqT08pHbICYe83H8JmtaDBvCFqRv7Tfze3Y8xuXukw,980 -pytz/zoneinfo/Canada/Yukon,sha256=TrR6PCnYG-mSClBMohqlP8qnYhXMUsydI-L-quXFxyM,1614 -pytz/zoneinfo/Chile/Continental,sha256=0CDw13dCMUsoquMupoJgupkzAUNhDK6E0lVxURA7osA,2515 -pytz/zoneinfo/Chile/EasterIsland,sha256=QbubBs_xQlvKweAnurhyHjIK4ji77Gh4G-usXul6XVM,2219 -pytz/zoneinfo/Cuba,sha256=HUQeAuKBsEkI5SLZjqynXICOUVOajkKzKH5r-Ov5Odc,2416 -pytz/zoneinfo/EET,sha256=XDY-FBUddRyQHN8GxQLZ4awjuOlWlzlUdjv7OdXFNzA,2262 -pytz/zoneinfo/EST,sha256=kayA_pdpMcSQ0FjIzotdcf-m1JYfbKE-qcFT8LC8zqA,182 -pytz/zoneinfo/EST5EDT,sha256=6e0H177gx2qdRC0JHvHwFmj-58TyYBTAqGixn-bBipU,3552 -pytz/zoneinfo/Egypt,sha256=Lft-GCLQhaSJm9VqUmsEFoHIS1Vhfa7pFJn9GZCpifs,2399 -pytz/zoneinfo/Eire,sha256=QOjSocO1cihNo59vQkWxvIFPRSxE9apz0KARVx1czEM,3492 -pytz/zoneinfo/Etc/GMT,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/Etc/GMT+0,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/Etc/GMT+1,sha256=1Qzl2X9rQ_RXEf11yH09wQZCr_ph6UdFP7E0yu9s-IQ,116 -pytz/zoneinfo/Etc/GMT+10,sha256=JEQyQyQlkC0o6ZTdeVjZhCIOh6cK5TF7H00Pkls-sUI,117 -pytz/zoneinfo/Etc/GMT+11,sha256=tWvcvYMFCaE60nJVvDrrov7stJvs1KQYOyrhl3dzcUs,117 -pytz/zoneinfo/Etc/GMT+12,sha256=b70HEhErq8IJmq8x7cOZy4eR__3fq5uHHpjvPBEHqMA,117 -pytz/zoneinfo/Etc/GMT+2,sha256=T6Ep5zhslBKbYaECFUB6gUKh3iTZPyMoW1kjhonxrUo,116 -pytz/zoneinfo/Etc/GMT+3,sha256=QGoYrE04bUJ-OzL37dt2MZT5FxWNLpJDPVXgJbstYZA,116 -pytz/zoneinfo/Etc/GMT+4,sha256=RWrkNki-wV7X-coe0VvufBe6LrWVpkPJgia5QQYEnBo,116 -pytz/zoneinfo/Etc/GMT+5,sha256=oRmeC41dgYXT-zzyZIRKXN9IvdL2Da5nTuwmG2_prIA,116 -pytz/zoneinfo/Etc/GMT+6,sha256=d6dAnwiejyFI2n7AzFlFW0aFAT6zYNEjBIEG0uu0sbQ,116 -pytz/zoneinfo/Etc/GMT+7,sha256=TqjYbzd0YHpx1wisFg08J19wTpg6ztJLLongZY_lozs,116 -pytz/zoneinfo/Etc/GMT+8,sha256=th_8bIMmYgRPCesBrbmBhRr0jQO7whd70LiY9HfwJyk,116 -pytz/zoneinfo/Etc/GMT+9,sha256=Qq5E6iUS7JMJIymT7YoqlI8MtqtVy0mr9t6zWFtWc9Y,116 -pytz/zoneinfo/Etc/GMT-0,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/Etc/GMT-1,sha256=73F1eU8uAQGP3mcoB2q99CjfManGFHk3fefljp9pYC4,117 -pytz/zoneinfo/Etc/GMT-10,sha256=fKWWNwLBOp1OkKjtc1w9LIXJR1mTTD-JdvYflRy1IrU,118 -pytz/zoneinfo/Etc/GMT-11,sha256=D2S79n6psa9t9_2vj5wIrFpHH2OJLcCKP6vtwzFZINY,118 -pytz/zoneinfo/Etc/GMT-12,sha256=me4V6lmWI8gSr8H7N41WAD0Eww1anh_EF34Qr9UoSnI,118 -pytz/zoneinfo/Etc/GMT-13,sha256=xbmbG1BQA6Dlpa_iUwEGyJxW4a3t6lmawdPKAE8vbR8,118 -pytz/zoneinfo/Etc/GMT-14,sha256=PpXoREBh02qFpvxVMj2pV9IAzSQvBE7XPvnN9qSZ-Kc,118 -pytz/zoneinfo/Etc/GMT-2,sha256=ve6hWLdeuiLhqagaWLqMD6HNybS1chRwjudfTZ2bYBE,117 -pytz/zoneinfo/Etc/GMT-3,sha256=N77jILanuLDVkLsdujXZSu-dsHiwN5MIpwh7fMUifso,117 -pytz/zoneinfo/Etc/GMT-4,sha256=LSko5fVHqPl5zfwjGqkbMa_OFnvtpT6o_4xYxNz9n5o,117 -pytz/zoneinfo/Etc/GMT-5,sha256=uLaSR5Mb18HRTsAA5SveY9PAJ97dO8QzIWqNXe3wZb4,117 -pytz/zoneinfo/Etc/GMT-6,sha256=JSN-RUAphJ50fpIv7cYC6unrtrz9S1Wma-piDHlGe7c,117 -pytz/zoneinfo/Etc/GMT-7,sha256=vVAOF8xU9T9ESnw68c0SFXpcvkoopaiwTR0zbefHHSU,117 -pytz/zoneinfo/Etc/GMT-8,sha256=S7xFQbFMpiDZy4v5L4D9fCrjRIzzoLC5p8Se23xi7us,117 -pytz/zoneinfo/Etc/GMT-9,sha256=I5vHNmUK-Yyg_S1skFN44VGVzBgktjFgVQiDIKO4aMI,117 -pytz/zoneinfo/Etc/GMT0,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/Etc/Greenwich,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/Etc/UCT,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/Etc/UTC,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/Etc/Universal,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/Etc/Zulu,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/Europe/Amsterdam,sha256=gS9Vrrbozend9HhuFetCVrIegs9fXSjaG60X2UVwysA,2933 -pytz/zoneinfo/Europe/Andorra,sha256=gTB5jCQmvIw3JJi1_vAcOYuhtzPBR6RXUx9gVV6p6ug,1742 -pytz/zoneinfo/Europe/Astrakhan,sha256=ZeGDZjwVVRoeR-J642zEnN26BPL58ViTJLbwnk7pLXk,1151 -pytz/zoneinfo/Europe/Athens,sha256=XDY-FBUddRyQHN8GxQLZ4awjuOlWlzlUdjv7OdXFNzA,2262 -pytz/zoneinfo/Europe/Belfast,sha256=yFSVBw3KQmh99qHD7ngKJ8vLgvGER1Dqb2QoM6RNKbQ,3664 -pytz/zoneinfo/Europe/Belgrade,sha256=OpWtsGFWBE_S-mYoQcAmjCta9HwbGQANnSmVY9OHCTo,1920 -pytz/zoneinfo/Europe/Berlin,sha256=XuR19xoPwaMvrrhJ-MOcbnqmbW1B7HQrl7OnQ2s7BwE,2298 -pytz/zoneinfo/Europe/Bratislava,sha256=G9fdhUXmzx651BnyZ6V7AOYIV9EV5aMJMm44eJaLLZw,2301 -pytz/zoneinfo/Europe/Brussels,sha256=gS9Vrrbozend9HhuFetCVrIegs9fXSjaG60X2UVwysA,2933 -pytz/zoneinfo/Europe/Bucharest,sha256=nfg6-bU2D6DMEWb9EMIBR5kxnNsbDSx0UKfHH_ZzqFc,2184 -pytz/zoneinfo/Europe/Budapest,sha256=lNwqxWciBvw9ei81VQwIKHbC_ZDJjpgHU6HFg4wCUkY,2368 -pytz/zoneinfo/Europe/Busingen,sha256=K5QY7Ujj2VUchKR4bhhb0hgdAJhmwED71ykXDQOGKe8,1909 -pytz/zoneinfo/Europe/Chisinau,sha256=p1J_rqFE13pL8cpBRrEFe-teCI8f0fKK4uTUy_4diF4,2390 -pytz/zoneinfo/Europe/Copenhagen,sha256=XuR19xoPwaMvrrhJ-MOcbnqmbW1B7HQrl7OnQ2s7BwE,2298 -pytz/zoneinfo/Europe/Dublin,sha256=QOjSocO1cihNo59vQkWxvIFPRSxE9apz0KARVx1czEM,3492 -pytz/zoneinfo/Europe/Gibraltar,sha256=a87WpaBlvxI4gAU9OpQOkN8VUJbirVWYf-VfFLTIoS4,3068 -pytz/zoneinfo/Europe/Guernsey,sha256=yFSVBw3KQmh99qHD7ngKJ8vLgvGER1Dqb2QoM6RNKbQ,3664 -pytz/zoneinfo/Europe/Helsinki,sha256=GEkB7LsVhmegt7YuuWheCDvDGC7b7Nw9bTdDGS9qkJc,1900 -pytz/zoneinfo/Europe/Isle_of_Man,sha256=yFSVBw3KQmh99qHD7ngKJ8vLgvGER1Dqb2QoM6RNKbQ,3664 -pytz/zoneinfo/Europe/Istanbul,sha256=Jk4wjndDta_uLWc8W1dWdjbavJJbsL5ROTmZboVnGKU,1933 -pytz/zoneinfo/Europe/Jersey,sha256=yFSVBw3KQmh99qHD7ngKJ8vLgvGER1Dqb2QoM6RNKbQ,3664 -pytz/zoneinfo/Europe/Kaliningrad,sha256=s7GXSe1YvMcs7AiUhHNTA6I4nAOQn_Kmz_ZqJYO-LMM,1493 -pytz/zoneinfo/Europe/Kiev,sha256=-wrpG9jPuIKFP1NgBVvnxsMRf9L_h5z3J6Q3jj1AwNM,2120 -pytz/zoneinfo/Europe/Kirov,sha256=P7T2Zf5Eo6o4L4Dbg_BfiFjUgTj0dQXlrwY-QZ1eBVk,1185 -pytz/zoneinfo/Europe/Kyiv,sha256=-wrpG9jPuIKFP1NgBVvnxsMRf9L_h5z3J6Q3jj1AwNM,2120 -pytz/zoneinfo/Europe/Lisbon,sha256=krB8skaJImv5NDCNHxvTPDBqpNphDFLNW84lB3lgUCw,3527 -pytz/zoneinfo/Europe/Ljubljana,sha256=OpWtsGFWBE_S-mYoQcAmjCta9HwbGQANnSmVY9OHCTo,1920 -pytz/zoneinfo/Europe/London,sha256=yFSVBw3KQmh99qHD7ngKJ8vLgvGER1Dqb2QoM6RNKbQ,3664 -pytz/zoneinfo/Europe/Luxembourg,sha256=gS9Vrrbozend9HhuFetCVrIegs9fXSjaG60X2UVwysA,2933 -pytz/zoneinfo/Europe/Madrid,sha256=mkLX03rW3t0tmzKBIPe_noUvaFDErwC6_5ZPZZsWHOo,2614 -pytz/zoneinfo/Europe/Malta,sha256=EhKcbPL47765tWAiQ57cusaK2TaIQqZCgtJoEZs3Ud0,2620 -pytz/zoneinfo/Europe/Mariehamn,sha256=GEkB7LsVhmegt7YuuWheCDvDGC7b7Nw9bTdDGS9qkJc,1900 -pytz/zoneinfo/Europe/Minsk,sha256=KgPm0fHycntgd3xbTmmDl4O13Xh_9e2zUnd8XFSU29o,1307 -pytz/zoneinfo/Europe/Monaco,sha256=q3ehSIot1GZ6TyMHIjbg0oRf4ghAXuwbSDSYVim6evg,2962 -pytz/zoneinfo/Europe/Moscow,sha256=KmkofRcj6T8Ph28PJChm8JVp13uRvef6TZ0GuPzUiDw,1535 -pytz/zoneinfo/Europe/Nicosia,sha256=0Unm0IFT7HyGeQ7F3vTa_-klfysCgrulqFO6BD1plZU,2002 -pytz/zoneinfo/Europe/Oslo,sha256=XuR19xoPwaMvrrhJ-MOcbnqmbW1B7HQrl7OnQ2s7BwE,2298 -pytz/zoneinfo/Europe/Paris,sha256=q3ehSIot1GZ6TyMHIjbg0oRf4ghAXuwbSDSYVim6evg,2962 -pytz/zoneinfo/Europe/Podgorica,sha256=OpWtsGFWBE_S-mYoQcAmjCta9HwbGQANnSmVY9OHCTo,1920 -pytz/zoneinfo/Europe/Prague,sha256=G9fdhUXmzx651BnyZ6V7AOYIV9EV5aMJMm44eJaLLZw,2301 -pytz/zoneinfo/Europe/Riga,sha256=hJ2_0m1taW9IuA-hMyP5n-WX7YOrR0heKszJhgljRWk,2198 -pytz/zoneinfo/Europe/Rome,sha256=1a3oLMSiMpSbh9QxV8hLLDVbZqash89iUO1urYC1AY8,2641 -pytz/zoneinfo/Europe/Samara,sha256=nXL0IxbT6qu10CNuaDHxx4W1OaAnaaKTtIJ9N9URMoU,1201 -pytz/zoneinfo/Europe/San_Marino,sha256=1a3oLMSiMpSbh9QxV8hLLDVbZqash89iUO1urYC1AY8,2641 -pytz/zoneinfo/Europe/Sarajevo,sha256=OpWtsGFWBE_S-mYoQcAmjCta9HwbGQANnSmVY9OHCTo,1920 -pytz/zoneinfo/Europe/Saratov,sha256=ygwjvXN13TgaWxjg6ysWEnHWNxwrVtkEbrk8t9bzVVw,1169 -pytz/zoneinfo/Europe/Simferopol,sha256=tzl7xdNVSZprNCul4YE5LSpoR9JoujmOq8VbbB8wHic,1469 -pytz/zoneinfo/Europe/Skopje,sha256=OpWtsGFWBE_S-mYoQcAmjCta9HwbGQANnSmVY9OHCTo,1920 -pytz/zoneinfo/Europe/Sofia,sha256=hCQKXfMNrnA5xHNw_uzTjKzVw4-Bvsq5oGO4yUCv5tY,2077 -pytz/zoneinfo/Europe/Stockholm,sha256=XuR19xoPwaMvrrhJ-MOcbnqmbW1B7HQrl7OnQ2s7BwE,2298 -pytz/zoneinfo/Europe/Tallinn,sha256=4a6JC0aIpMzqIV7O35zoG0LLJwkQq5AoXZ2ivkic6-w,2148 -pytz/zoneinfo/Europe/Tirane,sha256=ztlZyCS9WCXeVW8nBun3Tyi5HUY0EtFbiBbEc1gucuw,2084 -pytz/zoneinfo/Europe/Tiraspol,sha256=p1J_rqFE13pL8cpBRrEFe-teCI8f0fKK4uTUy_4diF4,2390 -pytz/zoneinfo/Europe/Ulyanovsk,sha256=c8Ad5p7CKj_1cCA7lVRpcPqbQXGYaX83cuu6uIFx-Bg,1253 -pytz/zoneinfo/Europe/Uzhgorod,sha256=-wrpG9jPuIKFP1NgBVvnxsMRf9L_h5z3J6Q3jj1AwNM,2120 -pytz/zoneinfo/Europe/Vaduz,sha256=K5QY7Ujj2VUchKR4bhhb0hgdAJhmwED71ykXDQOGKe8,1909 -pytz/zoneinfo/Europe/Vatican,sha256=1a3oLMSiMpSbh9QxV8hLLDVbZqash89iUO1urYC1AY8,2641 -pytz/zoneinfo/Europe/Vienna,sha256=ZmI3kADE6bnrJEccqh73XXBY36L1G4DkpiTQImtNrUk,2200 -pytz/zoneinfo/Europe/Vilnius,sha256=UFzRX3orCTB8d9IzlxJPy5eUA2oBPuCu1UJl-2D7C3U,2162 -pytz/zoneinfo/Europe/Volgograd,sha256=RgFvt7mzZ-TtIKL9BVHmoNZLIeLIuiDdXeY10g2_vks,1193 -pytz/zoneinfo/Europe/Warsaw,sha256=TiLDPbeVF0ckgLVEkaSeDaKZ8wctdJDOl_HE_Wd5rKs,2654 -pytz/zoneinfo/Europe/Zagreb,sha256=OpWtsGFWBE_S-mYoQcAmjCta9HwbGQANnSmVY9OHCTo,1920 -pytz/zoneinfo/Europe/Zaporozhye,sha256=-wrpG9jPuIKFP1NgBVvnxsMRf9L_h5z3J6Q3jj1AwNM,2120 -pytz/zoneinfo/Europe/Zurich,sha256=K5QY7Ujj2VUchKR4bhhb0hgdAJhmwED71ykXDQOGKe8,1909 -pytz/zoneinfo/Factory,sha256=aFFlKx93HXoJoF4SSuTlD8cZtJA-ne5oKzAa6eX2V4k,116 -pytz/zoneinfo/GB,sha256=yFSVBw3KQmh99qHD7ngKJ8vLgvGER1Dqb2QoM6RNKbQ,3664 -pytz/zoneinfo/GB-Eire,sha256=yFSVBw3KQmh99qHD7ngKJ8vLgvGER1Dqb2QoM6RNKbQ,3664 -pytz/zoneinfo/GMT,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/GMT+0,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/GMT-0,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/GMT0,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/Greenwich,sha256=bZ83iIPAefhsA4elVHqSxEmGnYBuB94QCEqwTwJJAY0,114 -pytz/zoneinfo/HST,sha256=fwPRv1Jk56sCOi75uZfd_Iy2k2aSQHx3B2K5xUlSPzM,329 -pytz/zoneinfo/Hongkong,sha256=al_O4kPlq5JpgkLYjEaZzrcgiiLul9NC0R5B69JVWhc,1233 -pytz/zoneinfo/Iceland,sha256=0u-sTl8j2IyV1ywdtCgHFw9S9D3ZiiBa9akqkbny2Zc,148 -pytz/zoneinfo/Indian/Antananarivo,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Indian/Chagos,sha256=2errXzKdFIcpU0L-XRhSHxhNabIzbI5lXV3Pq6lt40Y,185 -pytz/zoneinfo/Indian/Christmas,sha256=hf_5PVegQcFSS60CjS80C7h-TGOrfQ4ncm83N8VmZkk,185 -pytz/zoneinfo/Indian/Cocos,sha256=_YHASq4Z5YcUILIdhEzg27CGLzarUHPDHs1Dj0QgNGM,254 -pytz/zoneinfo/Indian/Comoro,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Indian/Kerguelen,sha256=F73ffVfBoUoHre0-DwsiQrYJcLpPOW-JJGk3n88lM5U,185 -pytz/zoneinfo/Indian/Mahe,sha256=pmdhPhaJRwKwONvxiZNGeFSICjlWzyY9JlFHv-H9upY,151 -pytz/zoneinfo/Indian/Maldives,sha256=F73ffVfBoUoHre0-DwsiQrYJcLpPOW-JJGk3n88lM5U,185 -pytz/zoneinfo/Indian/Mauritius,sha256=Znqrc1chimlciJsYBOl0NvIHnrNdCxncGxWczq1PBeI,227 -pytz/zoneinfo/Indian/Mayotte,sha256=yJsuJTqJJqbOz37_NOS_zbf-JNr_IthHGMMN7sDqSWg,265 -pytz/zoneinfo/Indian/Reunion,sha256=pmdhPhaJRwKwONvxiZNGeFSICjlWzyY9JlFHv-H9upY,151 -pytz/zoneinfo/Iran,sha256=Lb2H9BCBXtz819FL6E3gBA7w2ROiIgPgx-f08XpqkVo,1248 -pytz/zoneinfo/Israel,sha256=JUuWQmW5Tha0pJjw61Q5aN7CX0z4D7ops9OOSnda6Dc,2388 -pytz/zoneinfo/Jamaica,sha256=wlagieUPRf5-beie-h7QsONbNzjGsm8vMs8uf28pw28,482 -pytz/zoneinfo/Japan,sha256=oCueZgRNxcNcX3ZGdif9y6Su4cyVhga4XHdwlcrYLOs,309 -pytz/zoneinfo/Kwajalein,sha256=TmZ_0f-ySQ-saBAlRXV0f49Itwne51VBXn6rWcrWqHQ,302 -pytz/zoneinfo/Libya,sha256=W1dptGD70T7ppGoo0fczFQeDiIp0nultLNPV66MwB2c,625 -pytz/zoneinfo/MET,sha256=gS9Vrrbozend9HhuFetCVrIegs9fXSjaG60X2UVwysA,2933 -pytz/zoneinfo/MST,sha256=illz0sYuLL8lIPK0Tkou6dL0Vck_D0W_3rRTOvFYRmQ,360 -pytz/zoneinfo/MST7MDT,sha256=MugZwApDs8NI9TnXANQlUE8guNBowWQY0m-ptpPndck,2460 -pytz/zoneinfo/Mexico/BajaNorte,sha256=SluV7xzZm24LgMXSUVt1cD1AlE7y_bdE65HhDIdXLcs,2458 -pytz/zoneinfo/Mexico/BajaSur,sha256=BWH2NqVPA1PsyELPN_2BF8KllrsmQkqg1eujsQvnnx8,1060 -pytz/zoneinfo/Mexico/General,sha256=Uog2-FMWz2o12jR6sK9vemJamLeo6OEFMQR3s0xTxkc,1222 -pytz/zoneinfo/NZ,sha256=gADjoyPo_QISQU6UJrAgcHp3HDaMoOFRdH-d23uBSyc,2437 -pytz/zoneinfo/NZ-CHAT,sha256=xhexVc5lfJ_qAv2d3HrII6lfRSxKZYBAjY2zpYkCGE8,2054 -pytz/zoneinfo/Navajo,sha256=MugZwApDs8NI9TnXANQlUE8guNBowWQY0m-ptpPndck,2460 -pytz/zoneinfo/PRC,sha256=ZP_C5DqUQ1oEPAQNHTr36S0DGtx453N68YYbqk7u8-Y,561 -pytz/zoneinfo/PST8PDT,sha256=aJd7ua1tGG_vxser02AQpm4wAI3LLTdgh6QcSYYecmg,2852 -pytz/zoneinfo/Pacific/Apia,sha256=M3QKsp75Q7H1X3aeE_9ZqQli9aEkNCCQctZQ5sEKu00,598 -pytz/zoneinfo/Pacific/Auckland,sha256=gADjoyPo_QISQU6UJrAgcHp3HDaMoOFRdH-d23uBSyc,2437 -pytz/zoneinfo/Pacific/Bougainville,sha256=hWE86eXnNx-vABbp7-YSIqWyecHPMIWLftVloAoPhL8,254 -pytz/zoneinfo/Pacific/Chatham,sha256=xhexVc5lfJ_qAv2d3HrII6lfRSxKZYBAjY2zpYkCGE8,2054 -pytz/zoneinfo/Pacific/Chuuk,sha256=nB36HBWZTdh3TlP0DLFNz1KRQ0aHIfHbp7LC4Urp9fA,172 -pytz/zoneinfo/Pacific/Easter,sha256=QbubBs_xQlvKweAnurhyHjIK4ji77Gh4G-usXul6XVM,2219 -pytz/zoneinfo/Pacific/Efate,sha256=oSxNcQYx5-1FU2_yHzHI-hT-dMJcPxzy4XmdI1UxXAo,524 -pytz/zoneinfo/Pacific/Enderbury,sha256=HNTAKrsH_R2W3QRlKcmNld5KcXdP0ygXCjEovc1i-6Q,220 -pytz/zoneinfo/Pacific/Fakaofo,sha256=qOodpTMKjztvZIXVLe_f_kZ6WcHl9fCLE9ZsyvdFKLI,186 -pytz/zoneinfo/Pacific/Fiji,sha256=jB5FbOsCnHVQQ2ohPiWEQUPhG6JybB3Nog3qT6WJQ0I,564 -pytz/zoneinfo/Pacific/Funafuti,sha256=UyaKimsR8LjgL8Z2g65I0HTvr3tMZuA2wUeBB6_Zp9c,152 -pytz/zoneinfo/Pacific/Galapagos,sha256=_GJUYOjSiIjoNBO2qdq23isLMJ4NCVk3DKIRGeDc8BA,224 -pytz/zoneinfo/Pacific/Gambier,sha256=gAS7gr1HH_re0uYnL6eWo5KGJ-B5QaiM8mV2cY5mQxE,150 -pytz/zoneinfo/Pacific/Guadalcanal,sha256=M4kTWqaSQaV1AMhyLSvmwoBJF7X9icrILbvQJwp940g,152 -pytz/zoneinfo/Pacific/Guam,sha256=Ex9znmf6rNfGze6gNpZJCMr1TT4rkl2SnrhecrdJufI,494 -pytz/zoneinfo/Pacific/Honolulu,sha256=fwPRv1Jk56sCOi75uZfd_Iy2k2aSQHx3B2K5xUlSPzM,329 -pytz/zoneinfo/Pacific/Johnston,sha256=fwPRv1Jk56sCOi75uZfd_Iy2k2aSQHx3B2K5xUlSPzM,329 -pytz/zoneinfo/Pacific/Kanton,sha256=HNTAKrsH_R2W3QRlKcmNld5KcXdP0ygXCjEovc1i-6Q,220 -pytz/zoneinfo/Pacific/Kiritimati,sha256=hYk1Ooz-Lj1PuZCbNV2WJIvOLtCwSwq2u63cb1Z-3NQ,224 -pytz/zoneinfo/Pacific/Kosrae,sha256=Q0jrb4zeDrd61bU4V8TqjMc0Iep8rWZyZqJ0uqsunxs,337 -pytz/zoneinfo/Pacific/Kwajalein,sha256=TmZ_0f-ySQ-saBAlRXV0f49Itwne51VBXn6rWcrWqHQ,302 -pytz/zoneinfo/Pacific/Majuro,sha256=UyaKimsR8LjgL8Z2g65I0HTvr3tMZuA2wUeBB6_Zp9c,152 -pytz/zoneinfo/Pacific/Marquesas,sha256=FTxPJTWtk48LVb3N2U64KLpLsmvu0DQBubTCg-dvyGM,159 -pytz/zoneinfo/Pacific/Midway,sha256=fCYrYphYY6rUfxOw712y5cyRe104AC3pouqD3bCINFg,175 -pytz/zoneinfo/Pacific/Nauru,sha256=9ASKgLHB-8nsTEK1ApzfTH0yQtbNAmGX-JI7uHZiqnA,238 -pytz/zoneinfo/Pacific/Niue,sha256=OllXxukncR7a-SMmdFox5az1xpIPMhbahQhtObmpuDM,189 -pytz/zoneinfo/Pacific/Norfolk,sha256=DMdX1Bm18lzNuiCWzwfeHUMRGXPS8v5AWnh-_EX_AZw,866 -pytz/zoneinfo/Pacific/Noumea,sha256=tkHxxnxsXTOqz3YzWi0mkhTCIONzg-W7EpSRMdPjKdQ,290 -pytz/zoneinfo/Pacific/Pago_Pago,sha256=fCYrYphYY6rUfxOw712y5cyRe104AC3pouqD3bCINFg,175 -pytz/zoneinfo/Pacific/Palau,sha256=aN2HbT0reqwKrtLKDK9M2zb0d0ikdNlTrrntVxdH66o,166 -pytz/zoneinfo/Pacific/Pitcairn,sha256=U4jAUuvsRNoy8XrPa16YpcXCcqHJY0u6JvCNgPEWO1c,188 -pytz/zoneinfo/Pacific/Pohnpei,sha256=M4kTWqaSQaV1AMhyLSvmwoBJF7X9icrILbvQJwp940g,152 -pytz/zoneinfo/Pacific/Ponape,sha256=M4kTWqaSQaV1AMhyLSvmwoBJF7X9icrILbvQJwp940g,152 -pytz/zoneinfo/Pacific/Port_Moresby,sha256=nB36HBWZTdh3TlP0DLFNz1KRQ0aHIfHbp7LC4Urp9fA,172 -pytz/zoneinfo/Pacific/Rarotonga,sha256=wPEsoXbyDnuhfzkgLvUqhSzrMx_FD42uAPluSPMh3Bc,589 -pytz/zoneinfo/Pacific/Saipan,sha256=Ex9znmf6rNfGze6gNpZJCMr1TT4rkl2SnrhecrdJufI,494 -pytz/zoneinfo/Pacific/Samoa,sha256=fCYrYphYY6rUfxOw712y5cyRe104AC3pouqD3bCINFg,175 -pytz/zoneinfo/Pacific/Tahiti,sha256=BRff9G3E-iWKhOWR1Wu02Z0iMgjrwDXV-XNrqItXdTY,151 -pytz/zoneinfo/Pacific/Tarawa,sha256=UyaKimsR8LjgL8Z2g65I0HTvr3tMZuA2wUeBB6_Zp9c,152 -pytz/zoneinfo/Pacific/Tongatapu,sha256=OppBZqTAZib9HY7U9AC-JavO7m6NxPGUtUfPQAl9oBY,358 -pytz/zoneinfo/Pacific/Truk,sha256=nB36HBWZTdh3TlP0DLFNz1KRQ0aHIfHbp7LC4Urp9fA,172 -pytz/zoneinfo/Pacific/Wake,sha256=UyaKimsR8LjgL8Z2g65I0HTvr3tMZuA2wUeBB6_Zp9c,152 -pytz/zoneinfo/Pacific/Wallis,sha256=UyaKimsR8LjgL8Z2g65I0HTvr3tMZuA2wUeBB6_Zp9c,152 -pytz/zoneinfo/Pacific/Yap,sha256=nB36HBWZTdh3TlP0DLFNz1KRQ0aHIfHbp7LC4Urp9fA,172 -pytz/zoneinfo/Poland,sha256=TiLDPbeVF0ckgLVEkaSeDaKZ8wctdJDOl_HE_Wd5rKs,2654 -pytz/zoneinfo/Portugal,sha256=krB8skaJImv5NDCNHxvTPDBqpNphDFLNW84lB3lgUCw,3527 -pytz/zoneinfo/ROC,sha256=DMmQwOpPql25ue3Nf8vAKKT4em06D1Z9rHbLIitxixk,761 -pytz/zoneinfo/ROK,sha256=LI9LsV3XcJC0l-KoQf8zI-y7rk-du57erS-N2Ptdi7Q,617 -pytz/zoneinfo/Singapore,sha256=XmeVImeqcJ8hJzm7TjAti1nWJAxawOqq7jIzDnHX2hI,401 -pytz/zoneinfo/Turkey,sha256=Jk4wjndDta_uLWc8W1dWdjbavJJbsL5ROTmZboVnGKU,1933 -pytz/zoneinfo/UCT,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/US/Alaska,sha256=oZA1NSPS2BWdymYpnCHFO8BlYVS-ll5KLg2Ez9CbETs,2371 -pytz/zoneinfo/US/Aleutian,sha256=IB1DhwJQAKbhPJ9jHLf8zW5Dad7HIkBS-dhv64E1OlM,2356 -pytz/zoneinfo/US/Arizona,sha256=illz0sYuLL8lIPK0Tkou6dL0Vck_D0W_3rRTOvFYRmQ,360 -pytz/zoneinfo/US/Central,sha256=_roybr6I6sIAF6cYdIxGxoRpoef153Fty48dQ6bm9oY,3592 -pytz/zoneinfo/US/East-Indiana,sha256=kNKy9Kj9ICsiYYfCCbAggzMA7exf-GpGPMxoXocHUyw,1682 -pytz/zoneinfo/US/Eastern,sha256=6e0H177gx2qdRC0JHvHwFmj-58TyYBTAqGixn-bBipU,3552 -pytz/zoneinfo/US/Hawaii,sha256=fwPRv1Jk56sCOi75uZfd_Iy2k2aSQHx3B2K5xUlSPzM,329 -pytz/zoneinfo/US/Indiana-Starke,sha256=CsvZ5BKw2qVav3x_F8CU9taJdDk7jX41Cfsqms6jXV8,2444 -pytz/zoneinfo/US/Michigan,sha256=hecz8yqY2Cj5B61G3gLZdAVZvRgK9l0P90c_gN-uD5g,2230 -pytz/zoneinfo/US/Mountain,sha256=MugZwApDs8NI9TnXANQlUE8guNBowWQY0m-ptpPndck,2460 -pytz/zoneinfo/US/Pacific,sha256=aJd7ua1tGG_vxser02AQpm4wAI3LLTdgh6QcSYYecmg,2852 -pytz/zoneinfo/US/Samoa,sha256=fCYrYphYY6rUfxOw712y5cyRe104AC3pouqD3bCINFg,175 -pytz/zoneinfo/UTC,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/Universal,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/W-SU,sha256=KmkofRcj6T8Ph28PJChm8JVp13uRvef6TZ0GuPzUiDw,1535 -pytz/zoneinfo/WET,sha256=krB8skaJImv5NDCNHxvTPDBqpNphDFLNW84lB3lgUCw,3527 -pytz/zoneinfo/Zulu,sha256=i4WEZ5GrLIpUY8g6W-PAQ-JXDXRIQ01BOYlp7Ufj5vI,114 -pytz/zoneinfo/iso3166.tab,sha256=oBpdFY8x1GrY5vjMKgbGQYEGgqk5fUYDIPaNVCG2XnE,4791 -pytz/zoneinfo/leapseconds,sha256=gWAzwRuERloD6ADF5V6tUV26U_oVm5xh2nYC6jVwYOg,3257 -pytz/zoneinfo/tzdata.zi,sha256=-EeBhT7eWZNN3RIVLVFnf0Ekn2iff5gPQIxShpDY0lA,107471 -pytz/zoneinfo/zone.tab,sha256=WGtCB-bHZyLegq3Npr9J12H2aFF_RaZz9k2oOzM-7MQ,18822 -pytz/zoneinfo/zone1970.tab,sha256=VxlOQ7ABuPgymHshuClT2Zeu6uvrU6hSAUC8EtfYz8w,17597 -pytz/zoneinfo/zonenow.tab,sha256=JGdDvM4N0VGEYGVD2AgcuxIExbb_gje3WMtnwQkAzi8,8084 diff --git a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/WHEEL deleted file mode 100644 index 4724c45..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/WHEEL +++ /dev/null @@ -1,6 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.42.0) -Root-Is-Purelib: true -Tag: py2-none-any -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/top_level.txt deleted file mode 100644 index af44f19..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -pytz diff --git a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/zip-safe b/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/zip-safe deleted file mode 100644 index 8b13789..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz-2025.2.dist-info/zip-safe +++ /dev/null @@ -1 +0,0 @@ - diff --git a/llmlab/lib/python3.12/site-packages/pytz/__init__.py b/llmlab/lib/python3.12/site-packages/pytz/__init__.py deleted file mode 100644 index 8e44c3c..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/__init__.py +++ /dev/null @@ -1,1556 +0,0 @@ -''' -datetime.tzinfo timezone definitions generated from the -Olson timezone database: - - ftp://elsie.nci.nih.gov/pub/tz*.tar.gz - -See the datetime section of the Python Library Reference for information -on how to use these modules. -''' - -import sys -import datetime -import os.path - -from pytz.exceptions import AmbiguousTimeError -from pytz.exceptions import InvalidTimeError -from pytz.exceptions import NonExistentTimeError -from pytz.exceptions import UnknownTimeZoneError -from pytz.lazy import LazyDict, LazyList, LazySet # noqa -from pytz.tzinfo import unpickler, BaseTzInfo -from pytz.tzfile import build_tzinfo - - -# The IANA (nee Olson) database is updated several times a year. -OLSON_VERSION = '2025b' -VERSION = '2025.2' # pip compatible version number. -__version__ = VERSION - -OLSEN_VERSION = OLSON_VERSION # Old releases had this misspelling - -__all__ = [ - 'timezone', 'utc', 'country_timezones', 'country_names', - 'AmbiguousTimeError', 'InvalidTimeError', - 'NonExistentTimeError', 'UnknownTimeZoneError', - 'all_timezones', 'all_timezones_set', - 'common_timezones', 'common_timezones_set', - 'BaseTzInfo', 'FixedOffset', -] - - -if sys.version_info[0] > 2: # Python 3.x - - # Python 3.x doesn't have unicode(), making writing code - # for Python 2.3 and Python 3.x a pain. - unicode = str - - def ascii(s): - r""" - >>> ascii('Hello') - 'Hello' - >>> ascii('\N{TRADE MARK SIGN}') #doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - UnicodeEncodeError: ... - """ - if type(s) == bytes: - s = s.decode('ASCII') - else: - s.encode('ASCII') # Raise an exception if not ASCII - return s # But the string - not a byte string. - -else: # Python 2.x - - def ascii(s): - r""" - >>> ascii('Hello') - 'Hello' - >>> ascii(u'Hello') - 'Hello' - >>> ascii(u'\N{TRADE MARK SIGN}') #doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - UnicodeEncodeError: ... - """ - return s.encode('ASCII') - - -def open_resource(name): - """Open a resource from the zoneinfo subdir for reading. - - Uses the pkg_resources module if available and no standard file - found at the calculated location. - - It is possible to specify different location for zoneinfo - subdir by using the PYTZ_TZDATADIR environment variable. - """ - name_parts = name.lstrip('/').split('/') - for part in name_parts: - if part == os.path.pardir or os.sep in part: - raise ValueError('Bad path segment: %r' % part) - zoneinfo_dir = os.environ.get('PYTZ_TZDATADIR', None) - if zoneinfo_dir is not None: - filename = os.path.join(zoneinfo_dir, *name_parts) - else: - filename = os.path.join(os.path.dirname(__file__), - 'zoneinfo', *name_parts) - if not os.path.exists(filename): - # http://bugs.launchpad.net/bugs/383171 - we avoid using this - # unless absolutely necessary to help when a broken version of - # pkg_resources is installed. - try: - from pkg_resources import resource_stream - except ImportError: - resource_stream = None - - if resource_stream is not None: - return resource_stream(__name__, 'zoneinfo/' + name) - return open(filename, 'rb') - - -def resource_exists(name): - """Return true if the given resource exists""" - try: - if os.environ.get('PYTZ_SKIPEXISTSCHECK', ''): - # In "standard" distributions, we can assume that - # all the listed timezones are present. As an - # import-speed optimization, you can set the - # PYTZ_SKIPEXISTSCHECK flag to skip checking - # for the presence of the resource file on disk. - return True - open_resource(name).close() - return True - except IOError: - return False - - -_tzinfo_cache = {} - - -def timezone(zone): - r''' Return a datetime.tzinfo implementation for the given timezone - - >>> from datetime import datetime, timedelta - >>> utc = timezone('UTC') - >>> eastern = timezone('US/Eastern') - >>> eastern.zone - 'US/Eastern' - >>> timezone(unicode('US/Eastern')) is eastern - True - >>> utc_dt = datetime(2002, 10, 27, 6, 0, 0, tzinfo=utc) - >>> loc_dt = utc_dt.astimezone(eastern) - >>> fmt = '%Y-%m-%d %H:%M:%S %Z (%z)' - >>> loc_dt.strftime(fmt) - '2002-10-27 01:00:00 EST (-0500)' - >>> (loc_dt - timedelta(minutes=10)).strftime(fmt) - '2002-10-27 00:50:00 EST (-0500)' - >>> eastern.normalize(loc_dt - timedelta(minutes=10)).strftime(fmt) - '2002-10-27 01:50:00 EDT (-0400)' - >>> (loc_dt + timedelta(minutes=10)).strftime(fmt) - '2002-10-27 01:10:00 EST (-0500)' - - Raises UnknownTimeZoneError if passed an unknown zone. - - >>> try: - ... timezone('Asia/Shangri-La') - ... except UnknownTimeZoneError: - ... print('Unknown') - Unknown - - >>> try: - ... timezone(unicode('\N{TRADE MARK SIGN}')) - ... except UnknownTimeZoneError: - ... print('Unknown') - Unknown - - ''' - if zone is None: - raise UnknownTimeZoneError(None) - - if zone.upper() == 'UTC': - return utc - - try: - zone = ascii(zone) - except UnicodeEncodeError: - # All valid timezones are ASCII - raise UnknownTimeZoneError(zone) - - zone = _case_insensitive_zone_lookup(_unmunge_zone(zone)) - if zone not in _tzinfo_cache: - if zone in all_timezones_set: # noqa - fp = open_resource(zone) - try: - _tzinfo_cache[zone] = build_tzinfo(zone, fp) - finally: - fp.close() - else: - raise UnknownTimeZoneError(zone) - - return _tzinfo_cache[zone] - - -def _unmunge_zone(zone): - """Undo the time zone name munging done by older versions of pytz.""" - return zone.replace('_plus_', '+').replace('_minus_', '-') - - -_all_timezones_lower_to_standard = None - - -def _case_insensitive_zone_lookup(zone): - """case-insensitively matching timezone, else return zone unchanged""" - global _all_timezones_lower_to_standard - if _all_timezones_lower_to_standard is None: - _all_timezones_lower_to_standard = dict((tz.lower(), tz) for tz in _all_timezones_unchecked) # noqa - return _all_timezones_lower_to_standard.get(zone.lower()) or zone # noqa - - -ZERO = datetime.timedelta(0) -HOUR = datetime.timedelta(hours=1) - - -class UTC(BaseTzInfo): - """UTC - - Optimized UTC implementation. It unpickles using the single module global - instance defined beneath this class declaration. - """ - zone = "UTC" - - _utcoffset = ZERO - _dst = ZERO - _tzname = zone - - def fromutc(self, dt): - if dt.tzinfo is None: - return self.localize(dt) - return super(utc.__class__, self).fromutc(dt) - - def utcoffset(self, dt): - return ZERO - - def tzname(self, dt): - return "UTC" - - def dst(self, dt): - return ZERO - - def __reduce__(self): - return _UTC, () - - def localize(self, dt, is_dst=False): - '''Convert naive time to local time''' - if dt.tzinfo is not None: - raise ValueError('Not naive datetime (tzinfo is already set)') - return dt.replace(tzinfo=self) - - def normalize(self, dt, is_dst=False): - '''Correct the timezone information on the given datetime''' - if dt.tzinfo is self: - return dt - if dt.tzinfo is None: - raise ValueError('Naive time - no tzinfo set') - return dt.astimezone(self) - - def __repr__(self): - return "" - - def __str__(self): - return "UTC" - - -UTC = utc = UTC() # UTC is a singleton - - -def _UTC(): - """Factory function for utc unpickling. - - Makes sure that unpickling a utc instance always returns the same - module global. - - These examples belong in the UTC class above, but it is obscured; or in - the README.rst, but we are not depending on Python 2.4 so integrating - the README.rst examples with the unit tests is not trivial. - - >>> import datetime, pickle - >>> dt = datetime.datetime(2005, 3, 1, 14, 13, 21, tzinfo=utc) - >>> naive = dt.replace(tzinfo=None) - >>> p = pickle.dumps(dt, 1) - >>> naive_p = pickle.dumps(naive, 1) - >>> len(p) - len(naive_p) - 17 - >>> new = pickle.loads(p) - >>> new == dt - True - >>> new is dt - False - >>> new.tzinfo is dt.tzinfo - True - >>> utc is UTC is timezone('UTC') - True - >>> utc is timezone('GMT') - False - """ - return utc - - -_UTC.__safe_for_unpickling__ = True - - -def _p(*args): - """Factory function for unpickling pytz tzinfo instances. - - Just a wrapper around tzinfo.unpickler to save a few bytes in each pickle - by shortening the path. - """ - return unpickler(*args) - - -_p.__safe_for_unpickling__ = True - - -class _CountryTimezoneDict(LazyDict): - """Map ISO 3166 country code to a list of timezone names commonly used - in that country. - - iso3166_code is the two letter code used to identify the country. - - >>> def print_list(list_of_strings): - ... 'We use a helper so doctests work under Python 2.3 -> 3.x' - ... for s in list_of_strings: - ... print(s) - - >>> print_list(country_timezones['nz']) - Pacific/Auckland - Pacific/Chatham - >>> print_list(country_timezones['ch']) - Europe/Zurich - >>> print_list(country_timezones['CH']) - Europe/Zurich - >>> print_list(country_timezones[unicode('ch')]) - Europe/Zurich - >>> print_list(country_timezones['XXX']) - Traceback (most recent call last): - ... - KeyError: 'XXX' - - Previously, this information was exposed as a function rather than a - dictionary. This is still supported:: - - >>> print_list(country_timezones('nz')) - Pacific/Auckland - Pacific/Chatham - """ - def __call__(self, iso3166_code): - """Backwards compatibility.""" - return self[iso3166_code] - - def _fill(self): - data = {} - zone_tab = open_resource('zone.tab') - try: - for line in zone_tab: - line = line.decode('UTF-8') - if line.startswith('#'): - continue - code, coordinates, zone = line.split(None, 4)[:3] - if zone not in all_timezones_set: # noqa - continue - try: - data[code].append(zone) - except KeyError: - data[code] = [zone] - self.data = data - finally: - zone_tab.close() - - -country_timezones = _CountryTimezoneDict() - - -class _CountryNameDict(LazyDict): - '''Dictionary proving ISO3166 code -> English name. - - >>> print(country_names['au']) - Australia - ''' - def _fill(self): - data = {} - zone_tab = open_resource('iso3166.tab') - try: - for line in zone_tab.readlines(): - line = line.decode('UTF-8') - if line.startswith('#'): - continue - code, name = line.split(None, 1) - data[code] = name.strip() - self.data = data - finally: - zone_tab.close() - - -country_names = _CountryNameDict() - - -# Time-zone info based solely on fixed offsets - -class _FixedOffset(datetime.tzinfo): - - zone = None # to match the standard pytz API - - def __init__(self, minutes): - if abs(minutes) >= 1440: - raise ValueError("absolute offset is too large", minutes) - self._minutes = minutes - self._offset = datetime.timedelta(minutes=minutes) - - def utcoffset(self, dt): - return self._offset - - def __reduce__(self): - return FixedOffset, (self._minutes, ) - - def dst(self, dt): - return ZERO - - def tzname(self, dt): - return None - - def __repr__(self): - return 'pytz.FixedOffset(%d)' % self._minutes - - def localize(self, dt, is_dst=False): - '''Convert naive time to local time''' - if dt.tzinfo is not None: - raise ValueError('Not naive datetime (tzinfo is already set)') - return dt.replace(tzinfo=self) - - def normalize(self, dt, is_dst=False): - '''Correct the timezone information on the given datetime''' - if dt.tzinfo is self: - return dt - if dt.tzinfo is None: - raise ValueError('Naive time - no tzinfo set') - return dt.astimezone(self) - - -def FixedOffset(offset, _tzinfos={}): - """return a fixed-offset timezone based off a number of minutes. - - >>> one = FixedOffset(-330) - >>> one - pytz.FixedOffset(-330) - >>> str(one.utcoffset(datetime.datetime.now())) - '-1 day, 18:30:00' - >>> str(one.dst(datetime.datetime.now())) - '0:00:00' - - >>> two = FixedOffset(1380) - >>> two - pytz.FixedOffset(1380) - >>> str(two.utcoffset(datetime.datetime.now())) - '23:00:00' - >>> str(two.dst(datetime.datetime.now())) - '0:00:00' - - The datetime.timedelta must be between the range of -1 and 1 day, - non-inclusive. - - >>> FixedOffset(1440) - Traceback (most recent call last): - ... - ValueError: ('absolute offset is too large', 1440) - - >>> FixedOffset(-1440) - Traceback (most recent call last): - ... - ValueError: ('absolute offset is too large', -1440) - - An offset of 0 is special-cased to return UTC. - - >>> FixedOffset(0) is UTC - True - - There should always be only one instance of a FixedOffset per timedelta. - This should be true for multiple creation calls. - - >>> FixedOffset(-330) is one - True - >>> FixedOffset(1380) is two - True - - It should also be true for pickling. - - >>> import pickle - >>> pickle.loads(pickle.dumps(one)) is one - True - >>> pickle.loads(pickle.dumps(two)) is two - True - """ - if offset == 0: - return UTC - - info = _tzinfos.get(offset) - if info is None: - # We haven't seen this one before. we need to save it. - - # Use setdefault to avoid a race condition and make sure we have - # only one - info = _tzinfos.setdefault(offset, _FixedOffset(offset)) - - return info - - -FixedOffset.__safe_for_unpickling__ = True - - -def _test(): - import doctest - sys.path.insert(0, os.pardir) - import pytz - return doctest.testmod(pytz) - - -if __name__ == '__main__': - _test() -_all_timezones_unchecked = \ -['Africa/Abidjan', - 'Africa/Accra', - 'Africa/Addis_Ababa', - 'Africa/Algiers', - 'Africa/Asmara', - 'Africa/Asmera', - 'Africa/Bamako', - 'Africa/Bangui', - 'Africa/Banjul', - 'Africa/Bissau', - 'Africa/Blantyre', - 'Africa/Brazzaville', - 'Africa/Bujumbura', - 'Africa/Cairo', - 'Africa/Casablanca', - 'Africa/Ceuta', - 'Africa/Conakry', - 'Africa/Dakar', - 'Africa/Dar_es_Salaam', - 'Africa/Djibouti', - 'Africa/Douala', - 'Africa/El_Aaiun', - 'Africa/Freetown', - 'Africa/Gaborone', - 'Africa/Harare', - 'Africa/Johannesburg', - 'Africa/Juba', - 'Africa/Kampala', - 'Africa/Khartoum', - 'Africa/Kigali', - 'Africa/Kinshasa', - 'Africa/Lagos', - 'Africa/Libreville', - 'Africa/Lome', - 'Africa/Luanda', - 'Africa/Lubumbashi', - 'Africa/Lusaka', - 'Africa/Malabo', - 'Africa/Maputo', - 'Africa/Maseru', - 'Africa/Mbabane', - 'Africa/Mogadishu', - 'Africa/Monrovia', - 'Africa/Nairobi', - 'Africa/Ndjamena', - 'Africa/Niamey', - 'Africa/Nouakchott', - 'Africa/Ouagadougou', - 'Africa/Porto-Novo', - 'Africa/Sao_Tome', - 'Africa/Timbuktu', - 'Africa/Tripoli', - 'Africa/Tunis', - 'Africa/Windhoek', - 'America/Adak', - 'America/Anchorage', - 'America/Anguilla', - 'America/Antigua', - 'America/Araguaina', - 'America/Argentina/Buenos_Aires', - 'America/Argentina/Catamarca', - 'America/Argentina/ComodRivadavia', - 'America/Argentina/Cordoba', - 'America/Argentina/Jujuy', - 'America/Argentina/La_Rioja', - 'America/Argentina/Mendoza', - 'America/Argentina/Rio_Gallegos', - 'America/Argentina/Salta', - 'America/Argentina/San_Juan', - 'America/Argentina/San_Luis', - 'America/Argentina/Tucuman', - 'America/Argentina/Ushuaia', - 'America/Aruba', - 'America/Asuncion', - 'America/Atikokan', - 'America/Atka', - 'America/Bahia', - 'America/Bahia_Banderas', - 'America/Barbados', - 'America/Belem', - 'America/Belize', - 'America/Blanc-Sablon', - 'America/Boa_Vista', - 'America/Bogota', - 'America/Boise', - 'America/Buenos_Aires', - 'America/Cambridge_Bay', - 'America/Campo_Grande', - 'America/Cancun', - 'America/Caracas', - 'America/Catamarca', - 'America/Cayenne', - 'America/Cayman', - 'America/Chicago', - 'America/Chihuahua', - 'America/Ciudad_Juarez', - 'America/Coral_Harbour', - 'America/Cordoba', - 'America/Costa_Rica', - 'America/Coyhaique', - 'America/Creston', - 'America/Cuiaba', - 'America/Curacao', - 'America/Danmarkshavn', - 'America/Dawson', - 'America/Dawson_Creek', - 'America/Denver', - 'America/Detroit', - 'America/Dominica', - 'America/Edmonton', - 'America/Eirunepe', - 'America/El_Salvador', - 'America/Ensenada', - 'America/Fort_Nelson', - 'America/Fort_Wayne', - 'America/Fortaleza', - 'America/Glace_Bay', - 'America/Godthab', - 'America/Goose_Bay', - 'America/Grand_Turk', - 'America/Grenada', - 'America/Guadeloupe', - 'America/Guatemala', - 'America/Guayaquil', - 'America/Guyana', - 'America/Halifax', - 'America/Havana', - 'America/Hermosillo', - 'America/Indiana/Indianapolis', - 'America/Indiana/Knox', - 'America/Indiana/Marengo', - 'America/Indiana/Petersburg', - 'America/Indiana/Tell_City', - 'America/Indiana/Vevay', - 'America/Indiana/Vincennes', - 'America/Indiana/Winamac', - 'America/Indianapolis', - 'America/Inuvik', - 'America/Iqaluit', - 'America/Jamaica', - 'America/Jujuy', - 'America/Juneau', - 'America/Kentucky/Louisville', - 'America/Kentucky/Monticello', - 'America/Knox_IN', - 'America/Kralendijk', - 'America/La_Paz', - 'America/Lima', - 'America/Los_Angeles', - 'America/Louisville', - 'America/Lower_Princes', - 'America/Maceio', - 'America/Managua', - 'America/Manaus', - 'America/Marigot', - 'America/Martinique', - 'America/Matamoros', - 'America/Mazatlan', - 'America/Mendoza', - 'America/Menominee', - 'America/Merida', - 'America/Metlakatla', - 'America/Mexico_City', - 'America/Miquelon', - 'America/Moncton', - 'America/Monterrey', - 'America/Montevideo', - 'America/Montreal', - 'America/Montserrat', - 'America/Nassau', - 'America/New_York', - 'America/Nipigon', - 'America/Nome', - 'America/Noronha', - 'America/North_Dakota/Beulah', - 'America/North_Dakota/Center', - 'America/North_Dakota/New_Salem', - 'America/Nuuk', - 'America/Ojinaga', - 'America/Panama', - 'America/Pangnirtung', - 'America/Paramaribo', - 'America/Phoenix', - 'America/Port-au-Prince', - 'America/Port_of_Spain', - 'America/Porto_Acre', - 'America/Porto_Velho', - 'America/Puerto_Rico', - 'America/Punta_Arenas', - 'America/Rainy_River', - 'America/Rankin_Inlet', - 'America/Recife', - 'America/Regina', - 'America/Resolute', - 'America/Rio_Branco', - 'America/Rosario', - 'America/Santa_Isabel', - 'America/Santarem', - 'America/Santiago', - 'America/Santo_Domingo', - 'America/Sao_Paulo', - 'America/Scoresbysund', - 'America/Shiprock', - 'America/Sitka', - 'America/St_Barthelemy', - 'America/St_Johns', - 'America/St_Kitts', - 'America/St_Lucia', - 'America/St_Thomas', - 'America/St_Vincent', - 'America/Swift_Current', - 'America/Tegucigalpa', - 'America/Thule', - 'America/Thunder_Bay', - 'America/Tijuana', - 'America/Toronto', - 'America/Tortola', - 'America/Vancouver', - 'America/Virgin', - 'America/Whitehorse', - 'America/Winnipeg', - 'America/Yakutat', - 'America/Yellowknife', - 'Antarctica/Casey', - 'Antarctica/Davis', - 'Antarctica/DumontDUrville', - 'Antarctica/Macquarie', - 'Antarctica/Mawson', - 'Antarctica/McMurdo', - 'Antarctica/Palmer', - 'Antarctica/Rothera', - 'Antarctica/South_Pole', - 'Antarctica/Syowa', - 'Antarctica/Troll', - 'Antarctica/Vostok', - 'Arctic/Longyearbyen', - 'Asia/Aden', - 'Asia/Almaty', - 'Asia/Amman', - 'Asia/Anadyr', - 'Asia/Aqtau', - 'Asia/Aqtobe', - 'Asia/Ashgabat', - 'Asia/Ashkhabad', - 'Asia/Atyrau', - 'Asia/Baghdad', - 'Asia/Bahrain', - 'Asia/Baku', - 'Asia/Bangkok', - 'Asia/Barnaul', - 'Asia/Beirut', - 'Asia/Bishkek', - 'Asia/Brunei', - 'Asia/Calcutta', - 'Asia/Chita', - 'Asia/Choibalsan', - 'Asia/Chongqing', - 'Asia/Chungking', - 'Asia/Colombo', - 'Asia/Dacca', - 'Asia/Damascus', - 'Asia/Dhaka', - 'Asia/Dili', - 'Asia/Dubai', - 'Asia/Dushanbe', - 'Asia/Famagusta', - 'Asia/Gaza', - 'Asia/Harbin', - 'Asia/Hebron', - 'Asia/Ho_Chi_Minh', - 'Asia/Hong_Kong', - 'Asia/Hovd', - 'Asia/Irkutsk', - 'Asia/Istanbul', - 'Asia/Jakarta', - 'Asia/Jayapura', - 'Asia/Jerusalem', - 'Asia/Kabul', - 'Asia/Kamchatka', - 'Asia/Karachi', - 'Asia/Kashgar', - 'Asia/Kathmandu', - 'Asia/Katmandu', - 'Asia/Khandyga', - 'Asia/Kolkata', - 'Asia/Krasnoyarsk', - 'Asia/Kuala_Lumpur', - 'Asia/Kuching', - 'Asia/Kuwait', - 'Asia/Macao', - 'Asia/Macau', - 'Asia/Magadan', - 'Asia/Makassar', - 'Asia/Manila', - 'Asia/Muscat', - 'Asia/Nicosia', - 'Asia/Novokuznetsk', - 'Asia/Novosibirsk', - 'Asia/Omsk', - 'Asia/Oral', - 'Asia/Phnom_Penh', - 'Asia/Pontianak', - 'Asia/Pyongyang', - 'Asia/Qatar', - 'Asia/Qostanay', - 'Asia/Qyzylorda', - 'Asia/Rangoon', - 'Asia/Riyadh', - 'Asia/Saigon', - 'Asia/Sakhalin', - 'Asia/Samarkand', - 'Asia/Seoul', - 'Asia/Shanghai', - 'Asia/Singapore', - 'Asia/Srednekolymsk', - 'Asia/Taipei', - 'Asia/Tashkent', - 'Asia/Tbilisi', - 'Asia/Tehran', - 'Asia/Tel_Aviv', - 'Asia/Thimbu', - 'Asia/Thimphu', - 'Asia/Tokyo', - 'Asia/Tomsk', - 'Asia/Ujung_Pandang', - 'Asia/Ulaanbaatar', - 'Asia/Ulan_Bator', - 'Asia/Urumqi', - 'Asia/Ust-Nera', - 'Asia/Vientiane', - 'Asia/Vladivostok', - 'Asia/Yakutsk', - 'Asia/Yangon', - 'Asia/Yekaterinburg', - 'Asia/Yerevan', - 'Atlantic/Azores', - 'Atlantic/Bermuda', - 'Atlantic/Canary', - 'Atlantic/Cape_Verde', - 'Atlantic/Faeroe', - 'Atlantic/Faroe', - 'Atlantic/Jan_Mayen', - 'Atlantic/Madeira', - 'Atlantic/Reykjavik', - 'Atlantic/South_Georgia', - 'Atlantic/St_Helena', - 'Atlantic/Stanley', - 'Australia/ACT', - 'Australia/Adelaide', - 'Australia/Brisbane', - 'Australia/Broken_Hill', - 'Australia/Canberra', - 'Australia/Currie', - 'Australia/Darwin', - 'Australia/Eucla', - 'Australia/Hobart', - 'Australia/LHI', - 'Australia/Lindeman', - 'Australia/Lord_Howe', - 'Australia/Melbourne', - 'Australia/NSW', - 'Australia/North', - 'Australia/Perth', - 'Australia/Queensland', - 'Australia/South', - 'Australia/Sydney', - 'Australia/Tasmania', - 'Australia/Victoria', - 'Australia/West', - 'Australia/Yancowinna', - 'Brazil/Acre', - 'Brazil/DeNoronha', - 'Brazil/East', - 'Brazil/West', - 'CET', - 'CST6CDT', - 'Canada/Atlantic', - 'Canada/Central', - 'Canada/Eastern', - 'Canada/Mountain', - 'Canada/Newfoundland', - 'Canada/Pacific', - 'Canada/Saskatchewan', - 'Canada/Yukon', - 'Chile/Continental', - 'Chile/EasterIsland', - 'Cuba', - 'EET', - 'EST', - 'EST5EDT', - 'Egypt', - 'Eire', - 'Etc/GMT', - 'Etc/GMT+0', - 'Etc/GMT+1', - 'Etc/GMT+10', - 'Etc/GMT+11', - 'Etc/GMT+12', - 'Etc/GMT+2', - 'Etc/GMT+3', - 'Etc/GMT+4', - 'Etc/GMT+5', - 'Etc/GMT+6', - 'Etc/GMT+7', - 'Etc/GMT+8', - 'Etc/GMT+9', - 'Etc/GMT-0', - 'Etc/GMT-1', - 'Etc/GMT-10', - 'Etc/GMT-11', - 'Etc/GMT-12', - 'Etc/GMT-13', - 'Etc/GMT-14', - 'Etc/GMT-2', - 'Etc/GMT-3', - 'Etc/GMT-4', - 'Etc/GMT-5', - 'Etc/GMT-6', - 'Etc/GMT-7', - 'Etc/GMT-8', - 'Etc/GMT-9', - 'Etc/GMT0', - 'Etc/Greenwich', - 'Etc/UCT', - 'Etc/UTC', - 'Etc/Universal', - 'Etc/Zulu', - 'Europe/Amsterdam', - 'Europe/Andorra', - 'Europe/Astrakhan', - 'Europe/Athens', - 'Europe/Belfast', - 'Europe/Belgrade', - 'Europe/Berlin', - 'Europe/Bratislava', - 'Europe/Brussels', - 'Europe/Bucharest', - 'Europe/Budapest', - 'Europe/Busingen', - 'Europe/Chisinau', - 'Europe/Copenhagen', - 'Europe/Dublin', - 'Europe/Gibraltar', - 'Europe/Guernsey', - 'Europe/Helsinki', - 'Europe/Isle_of_Man', - 'Europe/Istanbul', - 'Europe/Jersey', - 'Europe/Kaliningrad', - 'Europe/Kiev', - 'Europe/Kirov', - 'Europe/Kyiv', - 'Europe/Lisbon', - 'Europe/Ljubljana', - 'Europe/London', - 'Europe/Luxembourg', - 'Europe/Madrid', - 'Europe/Malta', - 'Europe/Mariehamn', - 'Europe/Minsk', - 'Europe/Monaco', - 'Europe/Moscow', - 'Europe/Nicosia', - 'Europe/Oslo', - 'Europe/Paris', - 'Europe/Podgorica', - 'Europe/Prague', - 'Europe/Riga', - 'Europe/Rome', - 'Europe/Samara', - 'Europe/San_Marino', - 'Europe/Sarajevo', - 'Europe/Saratov', - 'Europe/Simferopol', - 'Europe/Skopje', - 'Europe/Sofia', - 'Europe/Stockholm', - 'Europe/Tallinn', - 'Europe/Tirane', - 'Europe/Tiraspol', - 'Europe/Ulyanovsk', - 'Europe/Uzhgorod', - 'Europe/Vaduz', - 'Europe/Vatican', - 'Europe/Vienna', - 'Europe/Vilnius', - 'Europe/Volgograd', - 'Europe/Warsaw', - 'Europe/Zagreb', - 'Europe/Zaporozhye', - 'Europe/Zurich', - 'GB', - 'GB-Eire', - 'GMT', - 'GMT+0', - 'GMT-0', - 'GMT0', - 'Greenwich', - 'HST', - 'Hongkong', - 'Iceland', - 'Indian/Antananarivo', - 'Indian/Chagos', - 'Indian/Christmas', - 'Indian/Cocos', - 'Indian/Comoro', - 'Indian/Kerguelen', - 'Indian/Mahe', - 'Indian/Maldives', - 'Indian/Mauritius', - 'Indian/Mayotte', - 'Indian/Reunion', - 'Iran', - 'Israel', - 'Jamaica', - 'Japan', - 'Kwajalein', - 'Libya', - 'MET', - 'MST', - 'MST7MDT', - 'Mexico/BajaNorte', - 'Mexico/BajaSur', - 'Mexico/General', - 'NZ', - 'NZ-CHAT', - 'Navajo', - 'PRC', - 'PST8PDT', - 'Pacific/Apia', - 'Pacific/Auckland', - 'Pacific/Bougainville', - 'Pacific/Chatham', - 'Pacific/Chuuk', - 'Pacific/Easter', - 'Pacific/Efate', - 'Pacific/Enderbury', - 'Pacific/Fakaofo', - 'Pacific/Fiji', - 'Pacific/Funafuti', - 'Pacific/Galapagos', - 'Pacific/Gambier', - 'Pacific/Guadalcanal', - 'Pacific/Guam', - 'Pacific/Honolulu', - 'Pacific/Johnston', - 'Pacific/Kanton', - 'Pacific/Kiritimati', - 'Pacific/Kosrae', - 'Pacific/Kwajalein', - 'Pacific/Majuro', - 'Pacific/Marquesas', - 'Pacific/Midway', - 'Pacific/Nauru', - 'Pacific/Niue', - 'Pacific/Norfolk', - 'Pacific/Noumea', - 'Pacific/Pago_Pago', - 'Pacific/Palau', - 'Pacific/Pitcairn', - 'Pacific/Pohnpei', - 'Pacific/Ponape', - 'Pacific/Port_Moresby', - 'Pacific/Rarotonga', - 'Pacific/Saipan', - 'Pacific/Samoa', - 'Pacific/Tahiti', - 'Pacific/Tarawa', - 'Pacific/Tongatapu', - 'Pacific/Truk', - 'Pacific/Wake', - 'Pacific/Wallis', - 'Pacific/Yap', - 'Poland', - 'Portugal', - 'ROC', - 'ROK', - 'Singapore', - 'Turkey', - 'UCT', - 'US/Alaska', - 'US/Aleutian', - 'US/Arizona', - 'US/Central', - 'US/East-Indiana', - 'US/Eastern', - 'US/Hawaii', - 'US/Indiana-Starke', - 'US/Michigan', - 'US/Mountain', - 'US/Pacific', - 'US/Samoa', - 'UTC', - 'Universal', - 'W-SU', - 'WET', - 'Zulu'] -all_timezones = LazyList( - tz for tz in _all_timezones_unchecked if resource_exists(tz)) - -all_timezones_set = LazySet(all_timezones) -common_timezones = \ -['Africa/Abidjan', - 'Africa/Accra', - 'Africa/Addis_Ababa', - 'Africa/Algiers', - 'Africa/Asmara', - 'Africa/Bamako', - 'Africa/Bangui', - 'Africa/Banjul', - 'Africa/Bissau', - 'Africa/Blantyre', - 'Africa/Brazzaville', - 'Africa/Bujumbura', - 'Africa/Cairo', - 'Africa/Casablanca', - 'Africa/Ceuta', - 'Africa/Conakry', - 'Africa/Dakar', - 'Africa/Dar_es_Salaam', - 'Africa/Djibouti', - 'Africa/Douala', - 'Africa/El_Aaiun', - 'Africa/Freetown', - 'Africa/Gaborone', - 'Africa/Harare', - 'Africa/Johannesburg', - 'Africa/Juba', - 'Africa/Kampala', - 'Africa/Khartoum', - 'Africa/Kigali', - 'Africa/Kinshasa', - 'Africa/Lagos', - 'Africa/Libreville', - 'Africa/Lome', - 'Africa/Luanda', - 'Africa/Lubumbashi', - 'Africa/Lusaka', - 'Africa/Malabo', - 'Africa/Maputo', - 'Africa/Maseru', - 'Africa/Mbabane', - 'Africa/Mogadishu', - 'Africa/Monrovia', - 'Africa/Nairobi', - 'Africa/Ndjamena', - 'Africa/Niamey', - 'Africa/Nouakchott', - 'Africa/Ouagadougou', - 'Africa/Porto-Novo', - 'Africa/Sao_Tome', - 'Africa/Tripoli', - 'Africa/Tunis', - 'Africa/Windhoek', - 'America/Adak', - 'America/Anchorage', - 'America/Anguilla', - 'America/Antigua', - 'America/Araguaina', - 'America/Argentina/Buenos_Aires', - 'America/Argentina/Catamarca', - 'America/Argentina/Cordoba', - 'America/Argentina/Jujuy', - 'America/Argentina/La_Rioja', - 'America/Argentina/Mendoza', - 'America/Argentina/Rio_Gallegos', - 'America/Argentina/Salta', - 'America/Argentina/San_Juan', - 'America/Argentina/San_Luis', - 'America/Argentina/Tucuman', - 'America/Argentina/Ushuaia', - 'America/Aruba', - 'America/Asuncion', - 'America/Atikokan', - 'America/Bahia', - 'America/Bahia_Banderas', - 'America/Barbados', - 'America/Belem', - 'America/Belize', - 'America/Blanc-Sablon', - 'America/Boa_Vista', - 'America/Bogota', - 'America/Boise', - 'America/Cambridge_Bay', - 'America/Campo_Grande', - 'America/Cancun', - 'America/Caracas', - 'America/Cayenne', - 'America/Cayman', - 'America/Chicago', - 'America/Chihuahua', - 'America/Ciudad_Juarez', - 'America/Costa_Rica', - 'America/Coyhaique', - 'America/Creston', - 'America/Cuiaba', - 'America/Curacao', - 'America/Danmarkshavn', - 'America/Dawson', - 'America/Dawson_Creek', - 'America/Denver', - 'America/Detroit', - 'America/Dominica', - 'America/Edmonton', - 'America/Eirunepe', - 'America/El_Salvador', - 'America/Fort_Nelson', - 'America/Fortaleza', - 'America/Glace_Bay', - 'America/Goose_Bay', - 'America/Grand_Turk', - 'America/Grenada', - 'America/Guadeloupe', - 'America/Guatemala', - 'America/Guayaquil', - 'America/Guyana', - 'America/Halifax', - 'America/Havana', - 'America/Hermosillo', - 'America/Indiana/Indianapolis', - 'America/Indiana/Knox', - 'America/Indiana/Marengo', - 'America/Indiana/Petersburg', - 'America/Indiana/Tell_City', - 'America/Indiana/Vevay', - 'America/Indiana/Vincennes', - 'America/Indiana/Winamac', - 'America/Inuvik', - 'America/Iqaluit', - 'America/Jamaica', - 'America/Juneau', - 'America/Kentucky/Louisville', - 'America/Kentucky/Monticello', - 'America/Kralendijk', - 'America/La_Paz', - 'America/Lima', - 'America/Los_Angeles', - 'America/Lower_Princes', - 'America/Maceio', - 'America/Managua', - 'America/Manaus', - 'America/Marigot', - 'America/Martinique', - 'America/Matamoros', - 'America/Mazatlan', - 'America/Menominee', - 'America/Merida', - 'America/Metlakatla', - 'America/Mexico_City', - 'America/Miquelon', - 'America/Moncton', - 'America/Monterrey', - 'America/Montevideo', - 'America/Montserrat', - 'America/Nassau', - 'America/New_York', - 'America/Nome', - 'America/Noronha', - 'America/North_Dakota/Beulah', - 'America/North_Dakota/Center', - 'America/North_Dakota/New_Salem', - 'America/Nuuk', - 'America/Ojinaga', - 'America/Panama', - 'America/Paramaribo', - 'America/Phoenix', - 'America/Port-au-Prince', - 'America/Port_of_Spain', - 'America/Porto_Velho', - 'America/Puerto_Rico', - 'America/Punta_Arenas', - 'America/Rankin_Inlet', - 'America/Recife', - 'America/Regina', - 'America/Resolute', - 'America/Rio_Branco', - 'America/Santarem', - 'America/Santiago', - 'America/Santo_Domingo', - 'America/Sao_Paulo', - 'America/Scoresbysund', - 'America/Sitka', - 'America/St_Barthelemy', - 'America/St_Johns', - 'America/St_Kitts', - 'America/St_Lucia', - 'America/St_Thomas', - 'America/St_Vincent', - 'America/Swift_Current', - 'America/Tegucigalpa', - 'America/Thule', - 'America/Tijuana', - 'America/Toronto', - 'America/Tortola', - 'America/Vancouver', - 'America/Whitehorse', - 'America/Winnipeg', - 'America/Yakutat', - 'Antarctica/Casey', - 'Antarctica/Davis', - 'Antarctica/DumontDUrville', - 'Antarctica/Macquarie', - 'Antarctica/Mawson', - 'Antarctica/McMurdo', - 'Antarctica/Palmer', - 'Antarctica/Rothera', - 'Antarctica/Syowa', - 'Antarctica/Troll', - 'Antarctica/Vostok', - 'Arctic/Longyearbyen', - 'Asia/Aden', - 'Asia/Almaty', - 'Asia/Amman', - 'Asia/Anadyr', - 'Asia/Aqtau', - 'Asia/Aqtobe', - 'Asia/Ashgabat', - 'Asia/Atyrau', - 'Asia/Baghdad', - 'Asia/Bahrain', - 'Asia/Baku', - 'Asia/Bangkok', - 'Asia/Barnaul', - 'Asia/Beirut', - 'Asia/Bishkek', - 'Asia/Brunei', - 'Asia/Chita', - 'Asia/Colombo', - 'Asia/Damascus', - 'Asia/Dhaka', - 'Asia/Dili', - 'Asia/Dubai', - 'Asia/Dushanbe', - 'Asia/Famagusta', - 'Asia/Gaza', - 'Asia/Hebron', - 'Asia/Ho_Chi_Minh', - 'Asia/Hong_Kong', - 'Asia/Hovd', - 'Asia/Irkutsk', - 'Asia/Jakarta', - 'Asia/Jayapura', - 'Asia/Jerusalem', - 'Asia/Kabul', - 'Asia/Kamchatka', - 'Asia/Karachi', - 'Asia/Kathmandu', - 'Asia/Khandyga', - 'Asia/Kolkata', - 'Asia/Krasnoyarsk', - 'Asia/Kuala_Lumpur', - 'Asia/Kuching', - 'Asia/Kuwait', - 'Asia/Macau', - 'Asia/Magadan', - 'Asia/Makassar', - 'Asia/Manila', - 'Asia/Muscat', - 'Asia/Nicosia', - 'Asia/Novokuznetsk', - 'Asia/Novosibirsk', - 'Asia/Omsk', - 'Asia/Oral', - 'Asia/Phnom_Penh', - 'Asia/Pontianak', - 'Asia/Pyongyang', - 'Asia/Qatar', - 'Asia/Qostanay', - 'Asia/Qyzylorda', - 'Asia/Riyadh', - 'Asia/Sakhalin', - 'Asia/Samarkand', - 'Asia/Seoul', - 'Asia/Shanghai', - 'Asia/Singapore', - 'Asia/Srednekolymsk', - 'Asia/Taipei', - 'Asia/Tashkent', - 'Asia/Tbilisi', - 'Asia/Tehran', - 'Asia/Thimphu', - 'Asia/Tokyo', - 'Asia/Tomsk', - 'Asia/Ulaanbaatar', - 'Asia/Urumqi', - 'Asia/Ust-Nera', - 'Asia/Vientiane', - 'Asia/Vladivostok', - 'Asia/Yakutsk', - 'Asia/Yangon', - 'Asia/Yekaterinburg', - 'Asia/Yerevan', - 'Atlantic/Azores', - 'Atlantic/Bermuda', - 'Atlantic/Canary', - 'Atlantic/Cape_Verde', - 'Atlantic/Faroe', - 'Atlantic/Madeira', - 'Atlantic/Reykjavik', - 'Atlantic/South_Georgia', - 'Atlantic/St_Helena', - 'Atlantic/Stanley', - 'Australia/Adelaide', - 'Australia/Brisbane', - 'Australia/Broken_Hill', - 'Australia/Darwin', - 'Australia/Eucla', - 'Australia/Hobart', - 'Australia/Lindeman', - 'Australia/Lord_Howe', - 'Australia/Melbourne', - 'Australia/Perth', - 'Australia/Sydney', - 'Canada/Atlantic', - 'Canada/Central', - 'Canada/Eastern', - 'Canada/Mountain', - 'Canada/Newfoundland', - 'Canada/Pacific', - 'Europe/Amsterdam', - 'Europe/Andorra', - 'Europe/Astrakhan', - 'Europe/Athens', - 'Europe/Belgrade', - 'Europe/Berlin', - 'Europe/Bratislava', - 'Europe/Brussels', - 'Europe/Bucharest', - 'Europe/Budapest', - 'Europe/Busingen', - 'Europe/Chisinau', - 'Europe/Copenhagen', - 'Europe/Dublin', - 'Europe/Gibraltar', - 'Europe/Guernsey', - 'Europe/Helsinki', - 'Europe/Isle_of_Man', - 'Europe/Istanbul', - 'Europe/Jersey', - 'Europe/Kaliningrad', - 'Europe/Kirov', - 'Europe/Kyiv', - 'Europe/Lisbon', - 'Europe/Ljubljana', - 'Europe/London', - 'Europe/Luxembourg', - 'Europe/Madrid', - 'Europe/Malta', - 'Europe/Mariehamn', - 'Europe/Minsk', - 'Europe/Monaco', - 'Europe/Moscow', - 'Europe/Oslo', - 'Europe/Paris', - 'Europe/Podgorica', - 'Europe/Prague', - 'Europe/Riga', - 'Europe/Rome', - 'Europe/Samara', - 'Europe/San_Marino', - 'Europe/Sarajevo', - 'Europe/Saratov', - 'Europe/Simferopol', - 'Europe/Skopje', - 'Europe/Sofia', - 'Europe/Stockholm', - 'Europe/Tallinn', - 'Europe/Tirane', - 'Europe/Ulyanovsk', - 'Europe/Vaduz', - 'Europe/Vatican', - 'Europe/Vienna', - 'Europe/Vilnius', - 'Europe/Volgograd', - 'Europe/Warsaw', - 'Europe/Zagreb', - 'Europe/Zurich', - 'GMT', - 'Indian/Antananarivo', - 'Indian/Chagos', - 'Indian/Christmas', - 'Indian/Cocos', - 'Indian/Comoro', - 'Indian/Kerguelen', - 'Indian/Mahe', - 'Indian/Maldives', - 'Indian/Mauritius', - 'Indian/Mayotte', - 'Indian/Reunion', - 'Pacific/Apia', - 'Pacific/Auckland', - 'Pacific/Bougainville', - 'Pacific/Chatham', - 'Pacific/Chuuk', - 'Pacific/Easter', - 'Pacific/Efate', - 'Pacific/Fakaofo', - 'Pacific/Fiji', - 'Pacific/Funafuti', - 'Pacific/Galapagos', - 'Pacific/Gambier', - 'Pacific/Guadalcanal', - 'Pacific/Guam', - 'Pacific/Honolulu', - 'Pacific/Kanton', - 'Pacific/Kiritimati', - 'Pacific/Kosrae', - 'Pacific/Kwajalein', - 'Pacific/Majuro', - 'Pacific/Marquesas', - 'Pacific/Midway', - 'Pacific/Nauru', - 'Pacific/Niue', - 'Pacific/Norfolk', - 'Pacific/Noumea', - 'Pacific/Pago_Pago', - 'Pacific/Palau', - 'Pacific/Pitcairn', - 'Pacific/Pohnpei', - 'Pacific/Port_Moresby', - 'Pacific/Rarotonga', - 'Pacific/Saipan', - 'Pacific/Tahiti', - 'Pacific/Tarawa', - 'Pacific/Tongatapu', - 'Pacific/Wake', - 'Pacific/Wallis', - 'US/Alaska', - 'US/Arizona', - 'US/Central', - 'US/Eastern', - 'US/Hawaii', - 'US/Mountain', - 'US/Pacific', - 'UTC'] -common_timezones = LazyList( - tz for tz in common_timezones if tz in all_timezones) - -common_timezones_set = LazySet(common_timezones) diff --git a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pytz/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 8727396..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pytz/__pycache__/exceptions.cpython-312.pyc deleted file mode 100644 index 4dd73c3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/exceptions.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/lazy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pytz/__pycache__/lazy.cpython-312.pyc deleted file mode 100644 index 99e2ff0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/lazy.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/reference.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pytz/__pycache__/reference.cpython-312.pyc deleted file mode 100644 index 262d369..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/reference.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/tzfile.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pytz/__pycache__/tzfile.cpython-312.pyc deleted file mode 100644 index d9e0887..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/tzfile.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/tzinfo.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/pytz/__pycache__/tzinfo.cpython-312.pyc deleted file mode 100644 index ba5a873..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/__pycache__/tzinfo.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/exceptions.py b/llmlab/lib/python3.12/site-packages/pytz/exceptions.py deleted file mode 100644 index 4b20bde..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/exceptions.py +++ /dev/null @@ -1,59 +0,0 @@ -''' -Custom exceptions raised by pytz. -''' - -__all__ = [ - 'UnknownTimeZoneError', 'InvalidTimeError', 'AmbiguousTimeError', - 'NonExistentTimeError', -] - - -class Error(Exception): - '''Base class for all exceptions raised by the pytz library''' - - -class UnknownTimeZoneError(KeyError, Error): - '''Exception raised when pytz is passed an unknown timezone. - - >>> isinstance(UnknownTimeZoneError(), LookupError) - True - - This class is actually a subclass of KeyError to provide backwards - compatibility with code relying on the undocumented behavior of earlier - pytz releases. - - >>> isinstance(UnknownTimeZoneError(), KeyError) - True - - And also a subclass of pytz.exceptions.Error, as are other pytz - exceptions. - - >>> isinstance(UnknownTimeZoneError(), Error) - True - - ''' - pass - - -class InvalidTimeError(Error): - '''Base class for invalid time exceptions.''' - - -class AmbiguousTimeError(InvalidTimeError): - '''Exception raised when attempting to create an ambiguous wallclock time. - - At the end of a DST transition period, a particular wallclock time will - occur twice (once before the clocks are set back, once after). Both - possibilities may be correct, unless further information is supplied. - - See DstTzInfo.normalize() for more info - ''' - - -class NonExistentTimeError(InvalidTimeError): - '''Exception raised when attempting to create a wallclock time that - cannot exist. - - At the start of a DST transition period, the wallclock time jumps forward. - The instants jumped over never occur. - ''' diff --git a/llmlab/lib/python3.12/site-packages/pytz/lazy.py b/llmlab/lib/python3.12/site-packages/pytz/lazy.py deleted file mode 100644 index 39344fc..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/lazy.py +++ /dev/null @@ -1,172 +0,0 @@ -from threading import RLock -try: - from collections.abc import Mapping as DictMixin -except ImportError: # Python < 3.3 - try: - from UserDict import DictMixin # Python 2 - except ImportError: # Python 3.0-3.3 - from collections import Mapping as DictMixin - - -# With lazy loading, we might end up with multiple threads triggering -# it at the same time. We need a lock. -_fill_lock = RLock() - - -class LazyDict(DictMixin): - """Dictionary populated on first use.""" - data = None - - def __getitem__(self, key): - if self.data is None: - _fill_lock.acquire() - try: - if self.data is None: - self._fill() - finally: - _fill_lock.release() - return self.data[key.upper()] - - def __contains__(self, key): - if self.data is None: - _fill_lock.acquire() - try: - if self.data is None: - self._fill() - finally: - _fill_lock.release() - return key in self.data - - def __iter__(self): - if self.data is None: - _fill_lock.acquire() - try: - if self.data is None: - self._fill() - finally: - _fill_lock.release() - return iter(self.data) - - def __len__(self): - if self.data is None: - _fill_lock.acquire() - try: - if self.data is None: - self._fill() - finally: - _fill_lock.release() - return len(self.data) - - def keys(self): - if self.data is None: - _fill_lock.acquire() - try: - if self.data is None: - self._fill() - finally: - _fill_lock.release() - return self.data.keys() - - -class LazyList(list): - """List populated on first use.""" - - _props = [ - '__str__', '__repr__', '__unicode__', - '__hash__', '__sizeof__', '__cmp__', - '__lt__', '__le__', '__eq__', '__ne__', '__gt__', '__ge__', - 'append', 'count', 'index', 'extend', 'insert', 'pop', 'remove', - 'reverse', 'sort', '__add__', '__radd__', '__iadd__', '__mul__', - '__rmul__', '__imul__', '__contains__', '__len__', '__nonzero__', - '__getitem__', '__setitem__', '__delitem__', '__iter__', - '__reversed__', '__getslice__', '__setslice__', '__delslice__'] - - def __new__(cls, fill_iter=None): - - if fill_iter is None: - return list() - - # We need a new class as we will be dynamically messing with its - # methods. - class LazyList(list): - pass - - fill_iter = [fill_iter] - - def lazy(name): - def _lazy(self, *args, **kw): - _fill_lock.acquire() - try: - if len(fill_iter) > 0: - list.extend(self, fill_iter.pop()) - for method_name in cls._props: - delattr(LazyList, method_name) - finally: - _fill_lock.release() - return getattr(list, name)(self, *args, **kw) - return _lazy - - for name in cls._props: - setattr(LazyList, name, lazy(name)) - - new_list = LazyList() - return new_list - -# Not all versions of Python declare the same magic methods. -# Filter out properties that don't exist in this version of Python -# from the list. -LazyList._props = [prop for prop in LazyList._props if hasattr(list, prop)] - - -class LazySet(set): - """Set populated on first use.""" - - _props = ( - '__str__', '__repr__', '__unicode__', - '__hash__', '__sizeof__', '__cmp__', - '__lt__', '__le__', '__eq__', '__ne__', '__gt__', '__ge__', - '__contains__', '__len__', '__nonzero__', - '__getitem__', '__setitem__', '__delitem__', '__iter__', - '__sub__', '__and__', '__xor__', '__or__', - '__rsub__', '__rand__', '__rxor__', '__ror__', - '__isub__', '__iand__', '__ixor__', '__ior__', - 'add', 'clear', 'copy', 'difference', 'difference_update', - 'discard', 'intersection', 'intersection_update', 'isdisjoint', - 'issubset', 'issuperset', 'pop', 'remove', - 'symmetric_difference', 'symmetric_difference_update', - 'union', 'update') - - def __new__(cls, fill_iter=None): - - if fill_iter is None: - return set() - - class LazySet(set): - pass - - fill_iter = [fill_iter] - - def lazy(name): - def _lazy(self, *args, **kw): - _fill_lock.acquire() - try: - if len(fill_iter) > 0: - for i in fill_iter.pop(): - set.add(self, i) - for method_name in cls._props: - delattr(LazySet, method_name) - finally: - _fill_lock.release() - return getattr(set, name)(self, *args, **kw) - return _lazy - - for name in cls._props: - setattr(LazySet, name, lazy(name)) - - new_set = LazySet() - return new_set - -# Not all versions of Python declare the same magic methods. -# Filter out properties that don't exist in this version of Python -# from the list. -LazySet._props = [prop for prop in LazySet._props if hasattr(set, prop)] diff --git a/llmlab/lib/python3.12/site-packages/pytz/reference.py b/llmlab/lib/python3.12/site-packages/pytz/reference.py deleted file mode 100644 index f765ca0..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/reference.py +++ /dev/null @@ -1,140 +0,0 @@ -''' -Reference tzinfo implementations from the Python docs. -Used for testing against as they are only correct for the years -1987 to 2006. Do not use these for real code. -''' - -from datetime import tzinfo, timedelta, datetime -from pytz import HOUR, ZERO, UTC - -__all__ = [ - 'FixedOffset', - 'LocalTimezone', - 'USTimeZone', - 'Eastern', - 'Central', - 'Mountain', - 'Pacific', - 'UTC' -] - - -# A class building tzinfo objects for fixed-offset time zones. -# Note that FixedOffset(0, "UTC") is a different way to build a -# UTC tzinfo object. -class FixedOffset(tzinfo): - """Fixed offset in minutes east from UTC.""" - - def __init__(self, offset, name): - self.__offset = timedelta(minutes=offset) - self.__name = name - - def utcoffset(self, dt): - return self.__offset - - def tzname(self, dt): - return self.__name - - def dst(self, dt): - return ZERO - - -import time as _time - -STDOFFSET = timedelta(seconds=-_time.timezone) -if _time.daylight: - DSTOFFSET = timedelta(seconds=-_time.altzone) -else: - DSTOFFSET = STDOFFSET - -DSTDIFF = DSTOFFSET - STDOFFSET - - -# A class capturing the platform's idea of local time. -class LocalTimezone(tzinfo): - - def utcoffset(self, dt): - if self._isdst(dt): - return DSTOFFSET - else: - return STDOFFSET - - def dst(self, dt): - if self._isdst(dt): - return DSTDIFF - else: - return ZERO - - def tzname(self, dt): - return _time.tzname[self._isdst(dt)] - - def _isdst(self, dt): - tt = (dt.year, dt.month, dt.day, - dt.hour, dt.minute, dt.second, - dt.weekday(), 0, -1) - stamp = _time.mktime(tt) - tt = _time.localtime(stamp) - return tt.tm_isdst > 0 - -Local = LocalTimezone() - - -def first_sunday_on_or_after(dt): - days_to_go = 6 - dt.weekday() - if days_to_go: - dt += timedelta(days_to_go) - return dt - - -# In the US, DST starts at 2am (standard time) on the first Sunday in April. -DSTSTART = datetime(1, 4, 1, 2) -# and ends at 2am (DST time; 1am standard time) on the last Sunday of Oct. -# which is the first Sunday on or after Oct 25. -DSTEND = datetime(1, 10, 25, 1) - - -# A complete implementation of current DST rules for major US time zones. -class USTimeZone(tzinfo): - - def __init__(self, hours, reprname, stdname, dstname): - self.stdoffset = timedelta(hours=hours) - self.reprname = reprname - self.stdname = stdname - self.dstname = dstname - - def __repr__(self): - return self.reprname - - def tzname(self, dt): - if self.dst(dt): - return self.dstname - else: - return self.stdname - - def utcoffset(self, dt): - return self.stdoffset + self.dst(dt) - - def dst(self, dt): - if dt is None or dt.tzinfo is None: - # An exception may be sensible here, in one or both cases. - # It depends on how you want to treat them. The default - # fromutc() implementation (called by the default astimezone() - # implementation) passes a datetime with dt.tzinfo is self. - return ZERO - assert dt.tzinfo is self - - # Find first Sunday in April & the last in October. - start = first_sunday_on_or_after(DSTSTART.replace(year=dt.year)) - end = first_sunday_on_or_after(DSTEND.replace(year=dt.year)) - - # Can't compare naive to aware objects, so strip the timezone from - # dt first. - if start <= dt.replace(tzinfo=None) < end: - return HOUR - else: - return ZERO - -Eastern = USTimeZone(-5, "Eastern", "EST", "EDT") -Central = USTimeZone(-6, "Central", "CST", "CDT") -Mountain = USTimeZone(-7, "Mountain", "MST", "MDT") -Pacific = USTimeZone(-8, "Pacific", "PST", "PDT") diff --git a/llmlab/lib/python3.12/site-packages/pytz/tzfile.py b/llmlab/lib/python3.12/site-packages/pytz/tzfile.py deleted file mode 100644 index 99e7448..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/tzfile.py +++ /dev/null @@ -1,133 +0,0 @@ -''' -$Id: tzfile.py,v 1.8 2004/06/03 00:15:24 zenzen Exp $ -''' - -from datetime import datetime -from struct import unpack, calcsize - -from pytz.tzinfo import StaticTzInfo, DstTzInfo, memorized_ttinfo -from pytz.tzinfo import memorized_datetime, memorized_timedelta - - -def _byte_string(s): - """Cast a string or byte string to an ASCII byte string.""" - return s.encode('ASCII') - -_NULL = _byte_string('\0') - - -def _std_string(s): - """Cast a string or byte string to an ASCII string.""" - return str(s.decode('ASCII')) - - -def build_tzinfo(zone, fp): - head_fmt = '>4s c 15x 6l' - head_size = calcsize(head_fmt) - (magic, format, ttisgmtcnt, ttisstdcnt, leapcnt, timecnt, - typecnt, charcnt) = unpack(head_fmt, fp.read(head_size)) - - # Make sure it is a tzfile(5) file - assert magic == _byte_string('TZif'), 'Got magic %s' % repr(magic) - - # Read out the transition times, localtime indices and ttinfo structures. - data_fmt = '>%(timecnt)dl %(timecnt)dB %(ttinfo)s %(charcnt)ds' % dict( - timecnt=timecnt, ttinfo='lBB' * typecnt, charcnt=charcnt) - data_size = calcsize(data_fmt) - data = unpack(data_fmt, fp.read(data_size)) - - # make sure we unpacked the right number of values - assert len(data) == 2 * timecnt + 3 * typecnt + 1 - transitions = [memorized_datetime(trans) - for trans in data[:timecnt]] - lindexes = list(data[timecnt:2 * timecnt]) - ttinfo_raw = data[2 * timecnt:-1] - tznames_raw = data[-1] - del data - - # Process ttinfo into separate structs - ttinfo = [] - tznames = {} - i = 0 - while i < len(ttinfo_raw): - # have we looked up this timezone name yet? - tzname_offset = ttinfo_raw[i + 2] - if tzname_offset not in tznames: - nul = tznames_raw.find(_NULL, tzname_offset) - if nul < 0: - nul = len(tznames_raw) - tznames[tzname_offset] = _std_string( - tznames_raw[tzname_offset:nul]) - ttinfo.append((ttinfo_raw[i], - bool(ttinfo_raw[i + 1]), - tznames[tzname_offset])) - i += 3 - - # Now build the timezone object - if len(ttinfo) == 1 or len(transitions) == 0: - ttinfo[0][0], ttinfo[0][2] - cls = type(zone, (StaticTzInfo,), dict( - zone=zone, - _utcoffset=memorized_timedelta(ttinfo[0][0]), - _tzname=ttinfo[0][2])) - else: - # Early dates use the first standard time ttinfo - i = 0 - while ttinfo[i][1]: - i += 1 - if ttinfo[i] == ttinfo[lindexes[0]]: - transitions[0] = datetime.min - else: - transitions.insert(0, datetime.min) - lindexes.insert(0, i) - - # calculate transition info - transition_info = [] - for i in range(len(transitions)): - inf = ttinfo[lindexes[i]] - utcoffset = inf[0] - if not inf[1]: - dst = 0 - else: - for j in range(i - 1, -1, -1): - prev_inf = ttinfo[lindexes[j]] - if not prev_inf[1]: - break - dst = inf[0] - prev_inf[0] # dst offset - - # Bad dst? Look further. DST > 24 hours happens when - # a timzone has moved across the international dateline. - if dst <= 0 or dst > 3600 * 3: - for j in range(i + 1, len(transitions)): - stdinf = ttinfo[lindexes[j]] - if not stdinf[1]: - dst = inf[0] - stdinf[0] - if dst > 0: - break # Found a useful std time. - - tzname = inf[2] - - # Round utcoffset and dst to the nearest minute or the - # datetime library will complain. Conversions to these timezones - # might be up to plus or minus 30 seconds out, but it is - # the best we can do. - utcoffset = int((utcoffset + 30) // 60) * 60 - dst = int((dst + 30) // 60) * 60 - transition_info.append(memorized_ttinfo(utcoffset, dst, tzname)) - - cls = type(zone, (DstTzInfo,), dict( - zone=zone, - _utc_transition_times=transitions, - _transition_info=transition_info)) - - return cls() - -if __name__ == '__main__': - import os.path - from pprint import pprint - base = os.path.join(os.path.dirname(__file__), 'zoneinfo') - tz = build_tzinfo('Australia/Melbourne', - open(os.path.join(base, 'Australia', 'Melbourne'), 'rb')) - tz = build_tzinfo('US/Eastern', - open(os.path.join(base, 'US', 'Eastern'), 'rb')) - pprint(tz._utc_transition_times) diff --git a/llmlab/lib/python3.12/site-packages/pytz/tzinfo.py b/llmlab/lib/python3.12/site-packages/pytz/tzinfo.py deleted file mode 100644 index 49b5c3f..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/tzinfo.py +++ /dev/null @@ -1,580 +0,0 @@ -'''Base classes and helpers for building zone specific tzinfo classes''' - -from datetime import datetime, timedelta, tzinfo -from bisect import bisect_right -try: - set -except NameError: - from sets import Set as set - -import pytz -from pytz.exceptions import AmbiguousTimeError, NonExistentTimeError - -__all__ = [] - -_timedelta_cache = {} - - -def memorized_timedelta(seconds): - '''Create only one instance of each distinct timedelta''' - try: - return _timedelta_cache[seconds] - except KeyError: - delta = timedelta(seconds=seconds) - _timedelta_cache[seconds] = delta - return delta - - -_epoch = datetime(1970, 1, 1, 0, 0) # datetime.utcfromtimestamp(0) -_datetime_cache = {0: _epoch} - - -def memorized_datetime(seconds): - '''Create only one instance of each distinct datetime''' - try: - return _datetime_cache[seconds] - except KeyError: - # NB. We can't just do datetime.fromtimestamp(seconds, tz=timezone.utc).replace(tzinfo=None) - # as this fails with negative values under Windows (Bug #90096) - dt = _epoch + timedelta(seconds=seconds) - _datetime_cache[seconds] = dt - return dt - - -_ttinfo_cache = {} - - -def memorized_ttinfo(*args): - '''Create only one instance of each distinct tuple''' - try: - return _ttinfo_cache[args] - except KeyError: - ttinfo = ( - memorized_timedelta(args[0]), - memorized_timedelta(args[1]), - args[2] - ) - _ttinfo_cache[args] = ttinfo - return ttinfo - - -_notime = memorized_timedelta(0) - - -def _to_seconds(td): - '''Convert a timedelta to seconds''' - return td.seconds + td.days * 24 * 60 * 60 - - -class BaseTzInfo(tzinfo): - # Overridden in subclass - _utcoffset = None - _tzname = None - zone = None - - def __str__(self): - return self.zone - - -class StaticTzInfo(BaseTzInfo): - '''A timezone that has a constant offset from UTC - - These timezones are rare, as most locations have changed their - offset at some point in their history - ''' - def fromutc(self, dt): - '''See datetime.tzinfo.fromutc''' - if dt.tzinfo is not None and dt.tzinfo is not self: - raise ValueError('fromutc: dt.tzinfo is not self') - return (dt + self._utcoffset).replace(tzinfo=self) - - def utcoffset(self, dt, is_dst=None): - '''See datetime.tzinfo.utcoffset - - is_dst is ignored for StaticTzInfo, and exists only to - retain compatibility with DstTzInfo. - ''' - return self._utcoffset - - def dst(self, dt, is_dst=None): - '''See datetime.tzinfo.dst - - is_dst is ignored for StaticTzInfo, and exists only to - retain compatibility with DstTzInfo. - ''' - return _notime - - def tzname(self, dt, is_dst=None): - '''See datetime.tzinfo.tzname - - is_dst is ignored for StaticTzInfo, and exists only to - retain compatibility with DstTzInfo. - ''' - return self._tzname - - def localize(self, dt, is_dst=False): - '''Convert naive time to local time''' - if dt.tzinfo is not None: - raise ValueError('Not naive datetime (tzinfo is already set)') - return dt.replace(tzinfo=self) - - def normalize(self, dt, is_dst=False): - '''Correct the timezone information on the given datetime. - - This is normally a no-op, as StaticTzInfo timezones never have - ambiguous cases to correct: - - >>> from pytz import timezone - >>> gmt = timezone('GMT') - >>> isinstance(gmt, StaticTzInfo) - True - >>> dt = datetime(2011, 5, 8, 1, 2, 3, tzinfo=gmt) - >>> gmt.normalize(dt) is dt - True - - The supported method of converting between timezones is to use - datetime.astimezone(). Currently normalize() also works: - - >>> la = timezone('America/Los_Angeles') - >>> dt = la.localize(datetime(2011, 5, 7, 1, 2, 3)) - >>> fmt = '%Y-%m-%d %H:%M:%S %Z (%z)' - >>> gmt.normalize(dt).strftime(fmt) - '2011-05-07 08:02:03 GMT (+0000)' - ''' - if dt.tzinfo is self: - return dt - if dt.tzinfo is None: - raise ValueError('Naive time - no tzinfo set') - return dt.astimezone(self) - - def __repr__(self): - return '' % (self.zone,) - - def __reduce__(self): - # Special pickle to zone remains a singleton and to cope with - # database changes. - return pytz._p, (self.zone,) - - -class DstTzInfo(BaseTzInfo): - '''A timezone that has a variable offset from UTC - - The offset might change if daylight saving time comes into effect, - or at a point in history when the region decides to change their - timezone definition. - ''' - # Overridden in subclass - - # Sorted list of DST transition times, UTC - _utc_transition_times = None - - # [(utcoffset, dstoffset, tzname)] corresponding to - # _utc_transition_times entries - _transition_info = None - - zone = None - - # Set in __init__ - - _tzinfos = None - _dst = None # DST offset - - def __init__(self, _inf=None, _tzinfos=None): - if _inf: - self._tzinfos = _tzinfos - self._utcoffset, self._dst, self._tzname = _inf - else: - _tzinfos = {} - self._tzinfos = _tzinfos - self._utcoffset, self._dst, self._tzname = ( - self._transition_info[0]) - _tzinfos[self._transition_info[0]] = self - for inf in self._transition_info[1:]: - if inf not in _tzinfos: - _tzinfos[inf] = self.__class__(inf, _tzinfos) - - def fromutc(self, dt): - '''See datetime.tzinfo.fromutc''' - if (dt.tzinfo is not None and - getattr(dt.tzinfo, '_tzinfos', None) is not self._tzinfos): - raise ValueError('fromutc: dt.tzinfo is not self') - dt = dt.replace(tzinfo=None) - idx = max(0, bisect_right(self._utc_transition_times, dt) - 1) - inf = self._transition_info[idx] - return (dt + inf[0]).replace(tzinfo=self._tzinfos[inf]) - - def normalize(self, dt): - '''Correct the timezone information on the given datetime - - If date arithmetic crosses DST boundaries, the tzinfo - is not magically adjusted. This method normalizes the - tzinfo to the correct one. - - To test, first we need to do some setup - - >>> from pytz import timezone - >>> utc = timezone('UTC') - >>> eastern = timezone('US/Eastern') - >>> fmt = '%Y-%m-%d %H:%M:%S %Z (%z)' - - We next create a datetime right on an end-of-DST transition point, - the instant when the wallclocks are wound back one hour. - - >>> utc_dt = datetime(2002, 10, 27, 6, 0, 0, tzinfo=utc) - >>> loc_dt = utc_dt.astimezone(eastern) - >>> loc_dt.strftime(fmt) - '2002-10-27 01:00:00 EST (-0500)' - - Now, if we subtract a few minutes from it, note that the timezone - information has not changed. - - >>> before = loc_dt - timedelta(minutes=10) - >>> before.strftime(fmt) - '2002-10-27 00:50:00 EST (-0500)' - - But we can fix that by calling the normalize method - - >>> before = eastern.normalize(before) - >>> before.strftime(fmt) - '2002-10-27 01:50:00 EDT (-0400)' - - The supported method of converting between timezones is to use - datetime.astimezone(). Currently, normalize() also works: - - >>> th = timezone('Asia/Bangkok') - >>> am = timezone('Europe/Amsterdam') - >>> dt = th.localize(datetime(2011, 5, 7, 1, 2, 3)) - >>> fmt = '%Y-%m-%d %H:%M:%S %Z (%z)' - >>> am.normalize(dt).strftime(fmt) - '2011-05-06 20:02:03 CEST (+0200)' - ''' - if dt.tzinfo is None: - raise ValueError('Naive time - no tzinfo set') - - # Convert dt in localtime to UTC - offset = dt.tzinfo._utcoffset - dt = dt.replace(tzinfo=None) - dt = dt - offset - # convert it back, and return it - return self.fromutc(dt) - - def localize(self, dt, is_dst=False): - '''Convert naive time to local time. - - This method should be used to construct localtimes, rather - than passing a tzinfo argument to a datetime constructor. - - is_dst is used to determine the correct timezone in the ambigous - period at the end of daylight saving time. - - >>> from pytz import timezone - >>> fmt = '%Y-%m-%d %H:%M:%S %Z (%z)' - >>> amdam = timezone('Europe/Amsterdam') - >>> dt = datetime(2004, 10, 31, 2, 0, 0) - >>> loc_dt1 = amdam.localize(dt, is_dst=True) - >>> loc_dt2 = amdam.localize(dt, is_dst=False) - >>> loc_dt1.strftime(fmt) - '2004-10-31 02:00:00 CEST (+0200)' - >>> loc_dt2.strftime(fmt) - '2004-10-31 02:00:00 CET (+0100)' - >>> str(loc_dt2 - loc_dt1) - '1:00:00' - - Use is_dst=None to raise an AmbiguousTimeError for ambiguous - times at the end of daylight saving time - - >>> try: - ... loc_dt1 = amdam.localize(dt, is_dst=None) - ... except AmbiguousTimeError: - ... print('Ambiguous') - Ambiguous - - is_dst defaults to False - - >>> amdam.localize(dt) == amdam.localize(dt, False) - True - - is_dst is also used to determine the correct timezone in the - wallclock times jumped over at the start of daylight saving time. - - >>> pacific = timezone('US/Pacific') - >>> dt = datetime(2008, 3, 9, 2, 0, 0) - >>> ploc_dt1 = pacific.localize(dt, is_dst=True) - >>> ploc_dt2 = pacific.localize(dt, is_dst=False) - >>> ploc_dt1.strftime(fmt) - '2008-03-09 02:00:00 PDT (-0700)' - >>> ploc_dt2.strftime(fmt) - '2008-03-09 02:00:00 PST (-0800)' - >>> str(ploc_dt2 - ploc_dt1) - '1:00:00' - - Use is_dst=None to raise a NonExistentTimeError for these skipped - times. - - >>> try: - ... loc_dt1 = pacific.localize(dt, is_dst=None) - ... except NonExistentTimeError: - ... print('Non-existent') - Non-existent - ''' - if dt.tzinfo is not None: - raise ValueError('Not naive datetime (tzinfo is already set)') - - # Find the two best possibilities. - possible_loc_dt = set() - for delta in [timedelta(days=-1), timedelta(days=1)]: - loc_dt = dt + delta - idx = max(0, bisect_right( - self._utc_transition_times, loc_dt) - 1) - inf = self._transition_info[idx] - tzinfo = self._tzinfos[inf] - loc_dt = tzinfo.normalize(dt.replace(tzinfo=tzinfo)) - if loc_dt.replace(tzinfo=None) == dt: - possible_loc_dt.add(loc_dt) - - if len(possible_loc_dt) == 1: - return possible_loc_dt.pop() - - # If there are no possibly correct timezones, we are attempting - # to convert a time that never happened - the time period jumped - # during the start-of-DST transition period. - if len(possible_loc_dt) == 0: - # If we refuse to guess, raise an exception. - if is_dst is None: - raise NonExistentTimeError(dt) - - # If we are forcing the pre-DST side of the DST transition, we - # obtain the correct timezone by winding the clock forward a few - # hours. - elif is_dst: - return self.localize( - dt + timedelta(hours=6), is_dst=True) - timedelta(hours=6) - - # If we are forcing the post-DST side of the DST transition, we - # obtain the correct timezone by winding the clock back. - else: - return self.localize( - dt - timedelta(hours=6), - is_dst=False) + timedelta(hours=6) - - # If we get this far, we have multiple possible timezones - this - # is an ambiguous case occurring during the end-of-DST transition. - - # If told to be strict, raise an exception since we have an - # ambiguous case - if is_dst is None: - raise AmbiguousTimeError(dt) - - # Filter out the possiblilities that don't match the requested - # is_dst - filtered_possible_loc_dt = [ - p for p in possible_loc_dt if bool(p.tzinfo._dst) == is_dst - ] - - # Hopefully we only have one possibility left. Return it. - if len(filtered_possible_loc_dt) == 1: - return filtered_possible_loc_dt[0] - - if len(filtered_possible_loc_dt) == 0: - filtered_possible_loc_dt = list(possible_loc_dt) - - # If we get this far, we have in a wierd timezone transition - # where the clocks have been wound back but is_dst is the same - # in both (eg. Europe/Warsaw 1915 when they switched to CET). - # At this point, we just have to guess unless we allow more - # hints to be passed in (such as the UTC offset or abbreviation), - # but that is just getting silly. - # - # Choose the earliest (by UTC) applicable timezone if is_dst=True - # Choose the latest (by UTC) applicable timezone if is_dst=False - # i.e., behave like end-of-DST transition - dates = {} # utc -> local - for local_dt in filtered_possible_loc_dt: - utc_time = ( - local_dt.replace(tzinfo=None) - local_dt.tzinfo._utcoffset) - assert utc_time not in dates - dates[utc_time] = local_dt - return dates[[min, max][not is_dst](dates)] - - def utcoffset(self, dt, is_dst=None): - '''See datetime.tzinfo.utcoffset - - The is_dst parameter may be used to remove ambiguity during DST - transitions. - - >>> from pytz import timezone - >>> tz = timezone('America/St_Johns') - >>> ambiguous = datetime(2009, 10, 31, 23, 30) - - >>> str(tz.utcoffset(ambiguous, is_dst=False)) - '-1 day, 20:30:00' - - >>> str(tz.utcoffset(ambiguous, is_dst=True)) - '-1 day, 21:30:00' - - >>> try: - ... tz.utcoffset(ambiguous) - ... except AmbiguousTimeError: - ... print('Ambiguous') - Ambiguous - - ''' - if dt is None: - return None - elif dt.tzinfo is not self: - dt = self.localize(dt, is_dst) - return dt.tzinfo._utcoffset - else: - return self._utcoffset - - def dst(self, dt, is_dst=None): - '''See datetime.tzinfo.dst - - The is_dst parameter may be used to remove ambiguity during DST - transitions. - - >>> from pytz import timezone - >>> tz = timezone('America/St_Johns') - - >>> normal = datetime(2009, 9, 1) - - >>> str(tz.dst(normal)) - '1:00:00' - >>> str(tz.dst(normal, is_dst=False)) - '1:00:00' - >>> str(tz.dst(normal, is_dst=True)) - '1:00:00' - - >>> ambiguous = datetime(2009, 10, 31, 23, 30) - - >>> str(tz.dst(ambiguous, is_dst=False)) - '0:00:00' - >>> str(tz.dst(ambiguous, is_dst=True)) - '1:00:00' - >>> try: - ... tz.dst(ambiguous) - ... except AmbiguousTimeError: - ... print('Ambiguous') - Ambiguous - - ''' - if dt is None: - return None - elif dt.tzinfo is not self: - dt = self.localize(dt, is_dst) - return dt.tzinfo._dst - else: - return self._dst - - def tzname(self, dt, is_dst=None): - '''See datetime.tzinfo.tzname - - The is_dst parameter may be used to remove ambiguity during DST - transitions. - - >>> from pytz import timezone - >>> tz = timezone('America/St_Johns') - - >>> normal = datetime(2009, 9, 1) - - >>> tz.tzname(normal) - 'NDT' - >>> tz.tzname(normal, is_dst=False) - 'NDT' - >>> tz.tzname(normal, is_dst=True) - 'NDT' - - >>> ambiguous = datetime(2009, 10, 31, 23, 30) - - >>> tz.tzname(ambiguous, is_dst=False) - 'NST' - >>> tz.tzname(ambiguous, is_dst=True) - 'NDT' - >>> try: - ... tz.tzname(ambiguous) - ... except AmbiguousTimeError: - ... print('Ambiguous') - Ambiguous - ''' - if dt is None: - return self.zone - elif dt.tzinfo is not self: - dt = self.localize(dt, is_dst) - return dt.tzinfo._tzname - else: - return self._tzname - - def __repr__(self): - if self._dst: - dst = 'DST' - else: - dst = 'STD' - if self._utcoffset > _notime: - return '' % ( - self.zone, self._tzname, self._utcoffset, dst - ) - else: - return '' % ( - self.zone, self._tzname, self._utcoffset, dst - ) - - def __reduce__(self): - # Special pickle to zone remains a singleton and to cope with - # database changes. - return pytz._p, ( - self.zone, - _to_seconds(self._utcoffset), - _to_seconds(self._dst), - self._tzname - ) - - -def unpickler(zone, utcoffset=None, dstoffset=None, tzname=None): - """Factory function for unpickling pytz tzinfo instances. - - This is shared for both StaticTzInfo and DstTzInfo instances, because - database changes could cause a zones implementation to switch between - these two base classes and we can't break pickles on a pytz version - upgrade. - """ - # Raises a KeyError if zone no longer exists, which should never happen - # and would be a bug. - tz = pytz.timezone(zone) - - # A StaticTzInfo - just return it - if utcoffset is None: - return tz - - # This pickle was created from a DstTzInfo. We need to - # determine which of the list of tzinfo instances for this zone - # to use in order to restore the state of any datetime instances using - # it correctly. - utcoffset = memorized_timedelta(utcoffset) - dstoffset = memorized_timedelta(dstoffset) - try: - return tz._tzinfos[(utcoffset, dstoffset, tzname)] - except KeyError: - # The particular state requested in this timezone no longer exists. - # This indicates a corrupt pickle, or the timezone database has been - # corrected violently enough to make this particular - # (utcoffset,dstoffset) no longer exist in the zone, or the - # abbreviation has been changed. - pass - - # See if we can find an entry differing only by tzname. Abbreviations - # get changed from the initial guess by the database maintainers to - # match reality when this information is discovered. - for localized_tz in tz._tzinfos.values(): - if (localized_tz._utcoffset == utcoffset and - localized_tz._dst == dstoffset): - return localized_tz - - # This (utcoffset, dstoffset) information has been removed from the - # zone. Add it back. This might occur when the database maintainers have - # corrected incorrect information. datetime instances using this - # incorrect information will continue to do so, exactly as they were - # before being pickled. This is purely an overly paranoid safety net - I - # doubt this will ever been needed in real life. - inf = (utcoffset, dstoffset, tzname) - tz._tzinfos[inf] = tz.__class__(inf, tz._tzinfos) - return tz._tzinfos[inf] diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Abidjan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Abidjan deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Abidjan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Accra b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Accra deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Accra and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Addis_Ababa b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Addis_Ababa deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Addis_Ababa and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Algiers b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Algiers deleted file mode 100644 index 6cfd8a1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Algiers and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Asmara b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Asmara deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Asmara and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Asmera b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Asmera deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Asmera and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bamako b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bamako deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bamako and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bangui b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bangui deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bangui and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Banjul b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Banjul deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Banjul and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bissau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bissau deleted file mode 100644 index 82ea5aa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bissau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Blantyre b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Blantyre deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Blantyre and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Brazzaville b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Brazzaville deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Brazzaville and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bujumbura b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bujumbura deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Bujumbura and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Cairo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Cairo deleted file mode 100644 index dd538c6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Cairo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Casablanca b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Casablanca deleted file mode 100644 index d39016b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Casablanca and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ceuta b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ceuta deleted file mode 100644 index b41ec4f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ceuta and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Conakry b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Conakry deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Conakry and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Dakar b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Dakar deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Dakar and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Dar_es_Salaam b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Dar_es_Salaam deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Dar_es_Salaam and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Djibouti b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Djibouti deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Djibouti and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Douala b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Douala deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Douala and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/El_Aaiun b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/El_Aaiun deleted file mode 100644 index 066fbed..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/El_Aaiun and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Freetown b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Freetown deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Freetown and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Gaborone b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Gaborone deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Gaborone and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Harare b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Harare deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Harare and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Johannesburg b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Johannesburg deleted file mode 100644 index b1c425d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Johannesburg and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Juba b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Juba deleted file mode 100644 index 0648294..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Juba and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kampala b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kampala deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kampala and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Khartoum b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Khartoum deleted file mode 100644 index 8ee8cb9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Khartoum and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kigali b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kigali deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kigali and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kinshasa b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kinshasa deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Kinshasa and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lagos b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lagos deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lagos and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Libreville b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Libreville deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Libreville and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lome b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lome deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lome and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Luanda b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Luanda deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Luanda and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lubumbashi b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lubumbashi deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lubumbashi and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lusaka b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lusaka deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Lusaka and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Malabo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Malabo deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Malabo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Maputo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Maputo deleted file mode 100644 index 65f043f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Maputo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Maseru b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Maseru deleted file mode 100644 index b1c425d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Maseru and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Mbabane b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Mbabane deleted file mode 100644 index b1c425d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Mbabane and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Mogadishu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Mogadishu deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Mogadishu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Monrovia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Monrovia deleted file mode 100644 index 6d68850..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Monrovia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Nairobi b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Nairobi deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Nairobi and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ndjamena b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ndjamena deleted file mode 100644 index a968845..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ndjamena and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Niamey b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Niamey deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Niamey and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Nouakchott b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Nouakchott deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Nouakchott and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ouagadougou b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ouagadougou deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Ouagadougou and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Porto-Novo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Porto-Novo deleted file mode 100644 index afb6a4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Porto-Novo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Sao_Tome b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Sao_Tome deleted file mode 100644 index 59f3759..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Sao_Tome and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Timbuktu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Timbuktu deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Timbuktu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Tripoli b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Tripoli deleted file mode 100644 index 07b393b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Tripoli and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Tunis b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Tunis deleted file mode 100644 index 427fa56..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Tunis and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Windhoek b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Windhoek deleted file mode 100644 index abecd13..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Africa/Windhoek and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Adak b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Adak deleted file mode 100644 index 4323649..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Adak and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Anchorage b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Anchorage deleted file mode 100644 index 9bbb2fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Anchorage and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Anguilla b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Anguilla deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Anguilla and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Antigua b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Antigua deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Antigua and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Araguaina b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Araguaina deleted file mode 100644 index 919723d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Araguaina and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Buenos_Aires b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Buenos_Aires deleted file mode 100644 index cc82e69..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Buenos_Aires and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Catamarca b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Catamarca deleted file mode 100644 index 7268eb3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Catamarca and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/ComodRivadavia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/ComodRivadavia deleted file mode 100644 index 7268eb3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/ComodRivadavia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Cordoba b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Cordoba deleted file mode 100644 index 2ad6ea5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Cordoba and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Jujuy b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Jujuy deleted file mode 100644 index 7ca0b46..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Jujuy and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/La_Rioja b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/La_Rioja deleted file mode 100644 index a6a6694..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/La_Rioja and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Mendoza b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Mendoza deleted file mode 100644 index 3232c80..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Mendoza and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Rio_Gallegos b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Rio_Gallegos deleted file mode 100644 index 8b1a281..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Rio_Gallegos and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Salta b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Salta deleted file mode 100644 index 7072dec..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Salta and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/San_Juan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/San_Juan deleted file mode 100644 index f3e185c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/San_Juan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/San_Luis b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/San_Luis deleted file mode 100644 index 2d1da3a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/San_Luis and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Tucuman b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Tucuman deleted file mode 100644 index c6449f5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Tucuman and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Ushuaia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Ushuaia deleted file mode 100644 index e74ce04..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Argentina/Ushuaia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Aruba b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Aruba deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Aruba and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Asuncion b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Asuncion deleted file mode 100644 index 9b07a80..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Asuncion and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Atikokan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Atikokan deleted file mode 100644 index 9964b9a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Atikokan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Atka b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Atka deleted file mode 100644 index 4323649..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Atka and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bahia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bahia deleted file mode 100644 index 0b65e49..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bahia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bahia_Banderas b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bahia_Banderas deleted file mode 100644 index 3a493e3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bahia_Banderas and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Barbados b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Barbados deleted file mode 100644 index 00cd045..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Barbados and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Belem b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Belem deleted file mode 100644 index 0ae1202..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Belem and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Belize b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Belize deleted file mode 100644 index e6f5dfa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Belize and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Blanc-Sablon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Blanc-Sablon deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Blanc-Sablon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Boa_Vista b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Boa_Vista deleted file mode 100644 index 08d518b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Boa_Vista and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bogota b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bogota deleted file mode 100644 index 331a1b7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Bogota and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Boise b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Boise deleted file mode 100644 index aad1d99..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Boise and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Buenos_Aires b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Buenos_Aires deleted file mode 100644 index cc82e69..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Buenos_Aires and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cambridge_Bay b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cambridge_Bay deleted file mode 100644 index 7e58a20..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cambridge_Bay and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Campo_Grande b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Campo_Grande deleted file mode 100644 index 53b3330..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Campo_Grande and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cancun b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cancun deleted file mode 100644 index 0f7771e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cancun and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Caracas b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Caracas deleted file mode 100644 index 3f3ebc9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Caracas and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Catamarca b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Catamarca deleted file mode 100644 index 7268eb3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Catamarca and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cayenne b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cayenne deleted file mode 100644 index e898594..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cayenne and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cayman b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cayman deleted file mode 100644 index 9964b9a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cayman and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Chicago b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Chicago deleted file mode 100644 index c6981a0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Chicago and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Chihuahua b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Chihuahua deleted file mode 100644 index 667a219..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Chihuahua and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ciudad_Juarez b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ciudad_Juarez deleted file mode 100644 index 29af598..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ciudad_Juarez and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Coral_Harbour b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Coral_Harbour deleted file mode 100644 index 9964b9a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Coral_Harbour and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cordoba b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cordoba deleted file mode 100644 index 2ad6ea5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cordoba and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Costa_Rica b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Costa_Rica deleted file mode 100644 index 37cb85e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Costa_Rica and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Coyhaique b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Coyhaique deleted file mode 100644 index e0c6832..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Coyhaique and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Creston b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Creston deleted file mode 100644 index ab37e84..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Creston and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cuiaba b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cuiaba deleted file mode 100644 index 26e97f6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Cuiaba and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Curacao b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Curacao deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Curacao and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Danmarkshavn b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Danmarkshavn deleted file mode 100644 index 9549adc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Danmarkshavn and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dawson b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dawson deleted file mode 100644 index 343b632..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dawson and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dawson_Creek b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dawson_Creek deleted file mode 100644 index db9e339..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dawson_Creek and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Denver b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Denver deleted file mode 100644 index abb2b97..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Denver and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Detroit b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Detroit deleted file mode 100644 index e104faa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Detroit and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dominica b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dominica deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Dominica and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Edmonton b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Edmonton deleted file mode 100644 index cd78a6f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Edmonton and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Eirunepe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Eirunepe deleted file mode 100644 index d4c46e3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Eirunepe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/El_Salvador b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/El_Salvador deleted file mode 100644 index e2f2230..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/El_Salvador and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ensenada b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ensenada deleted file mode 100644 index 0fe7391..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ensenada and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fort_Nelson b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fort_Nelson deleted file mode 100644 index 5a0b7f1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fort_Nelson and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fort_Wayne b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fort_Wayne deleted file mode 100644 index a84b6e9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fort_Wayne and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fortaleza b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fortaleza deleted file mode 100644 index bee1a95..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Fortaleza and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Glace_Bay b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Glace_Bay deleted file mode 100644 index 48412a4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Glace_Bay and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Godthab b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Godthab deleted file mode 100644 index 29958cf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Godthab and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Goose_Bay b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Goose_Bay deleted file mode 100644 index a3f2990..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Goose_Bay and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Grand_Turk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Grand_Turk deleted file mode 100644 index 06da1a6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Grand_Turk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Grenada b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Grenada deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Grenada and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guadeloupe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guadeloupe deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guadeloupe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guatemala b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guatemala deleted file mode 100644 index 407138c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guatemala and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guayaquil b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guayaquil deleted file mode 100644 index 40831be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guayaquil and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guyana b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guyana deleted file mode 100644 index 9b70367..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Guyana and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Halifax b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Halifax deleted file mode 100644 index 756099a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Halifax and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Havana b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Havana deleted file mode 100644 index b69ac45..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Havana and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Hermosillo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Hermosillo deleted file mode 100644 index 441fe3f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Hermosillo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Indianapolis b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Indianapolis deleted file mode 100644 index a84b6e9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Indianapolis and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Knox b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Knox deleted file mode 100644 index 025d132..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Knox and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Marengo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Marengo deleted file mode 100644 index 677bbff..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Marengo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Petersburg b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Petersburg deleted file mode 100644 index 3082de0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Petersburg and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Tell_City b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Tell_City deleted file mode 100644 index 103c5cb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Tell_City and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Vevay b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Vevay deleted file mode 100644 index 315b4c4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Vevay and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Vincennes b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Vincennes deleted file mode 100644 index 35a2413..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Vincennes and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Winamac b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Winamac deleted file mode 100644 index 6d4e193..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indiana/Winamac and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indianapolis b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indianapolis deleted file mode 100644 index a84b6e9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Indianapolis and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Inuvik b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Inuvik deleted file mode 100644 index 04c2df4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Inuvik and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Iqaluit b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Iqaluit deleted file mode 100644 index 0b47b90..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Iqaluit and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Jamaica b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Jamaica deleted file mode 100644 index 2a9b7fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Jamaica and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Jujuy b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Jujuy deleted file mode 100644 index 7ca0b46..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Jujuy and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Juneau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Juneau deleted file mode 100644 index 451f349..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Juneau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kentucky/Louisville b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kentucky/Louisville deleted file mode 100644 index 3a335b3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kentucky/Louisville and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kentucky/Monticello b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kentucky/Monticello deleted file mode 100644 index 576f16b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kentucky/Monticello and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Knox_IN b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Knox_IN deleted file mode 100644 index 025d132..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Knox_IN and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kralendijk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kralendijk deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Kralendijk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/La_Paz b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/La_Paz deleted file mode 100644 index 374586e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/La_Paz and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Lima b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Lima deleted file mode 100644 index c13bb6b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Lima and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Los_Angeles b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Los_Angeles deleted file mode 100644 index 610e7af..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Los_Angeles and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Louisville b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Louisville deleted file mode 100644 index 3a335b3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Louisville and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Lower_Princes b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Lower_Princes deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Lower_Princes and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Maceio b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Maceio deleted file mode 100644 index 437a473..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Maceio and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Managua b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Managua deleted file mode 100644 index e0242bf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Managua and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Manaus b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Manaus deleted file mode 100644 index 2708bae..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Manaus and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Marigot b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Marigot deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Marigot and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Martinique b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Martinique deleted file mode 100644 index 8df43dc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Martinique and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Matamoros b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Matamoros deleted file mode 100644 index bbe04e8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Matamoros and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mazatlan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mazatlan deleted file mode 100644 index 386616a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mazatlan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mendoza b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mendoza deleted file mode 100644 index 3232c80..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mendoza and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Menominee b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Menominee deleted file mode 100644 index 3146138..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Menominee and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Merida b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Merida deleted file mode 100644 index c4b9b4e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Merida and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Metlakatla b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Metlakatla deleted file mode 100644 index 1e94be3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Metlakatla and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mexico_City b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mexico_City deleted file mode 100644 index ad70cf3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Mexico_City and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Miquelon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Miquelon deleted file mode 100644 index f780ea9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Miquelon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Moncton b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Moncton deleted file mode 100644 index 9df8d0f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Moncton and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Monterrey b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Monterrey deleted file mode 100644 index 2d7993a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Monterrey and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montevideo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montevideo deleted file mode 100644 index e7bbfbb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montevideo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montreal b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montreal deleted file mode 100644 index 1701373..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montreal and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montserrat b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montserrat deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Montserrat and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nassau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nassau deleted file mode 100644 index 1701373..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nassau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/New_York b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/New_York deleted file mode 100644 index a8b9ab1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/New_York and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nipigon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nipigon deleted file mode 100644 index 1701373..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nipigon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nome b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nome deleted file mode 100644 index 10998df..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nome and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Noronha b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Noronha deleted file mode 100644 index 73b4b33..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Noronha and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/Beulah b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/Beulah deleted file mode 100644 index 33e317e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/Beulah and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/Center b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/Center deleted file mode 100644 index 17fe13b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/Center and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/New_Salem b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/New_Salem deleted file mode 100644 index 12dbe80..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/North_Dakota/New_Salem and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nuuk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nuuk deleted file mode 100644 index 29958cf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Nuuk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ojinaga b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ojinaga deleted file mode 100644 index 45118a4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Ojinaga and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Panama b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Panama deleted file mode 100644 index 9964b9a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Panama and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Pangnirtung b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Pangnirtung deleted file mode 100644 index 0b47b90..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Pangnirtung and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Paramaribo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Paramaribo deleted file mode 100644 index f1b82b4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Paramaribo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Phoenix b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Phoenix deleted file mode 100644 index ab37e84..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Phoenix and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Port-au-Prince b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Port-au-Prince deleted file mode 100644 index 287f143..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Port-au-Prince and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Port_of_Spain b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Port_of_Spain deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Port_of_Spain and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Porto_Acre b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Porto_Acre deleted file mode 100644 index cdda168..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Porto_Acre and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Porto_Velho b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Porto_Velho deleted file mode 100644 index e003986..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Porto_Velho and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Puerto_Rico b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Puerto_Rico deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Puerto_Rico and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Punta_Arenas b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Punta_Arenas deleted file mode 100644 index 411a839..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Punta_Arenas and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rainy_River b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rainy_River deleted file mode 100644 index ac40299..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rainy_River and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rankin_Inlet b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rankin_Inlet deleted file mode 100644 index e271492..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rankin_Inlet and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Recife b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Recife deleted file mode 100644 index 5bf6c21..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Recife and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Regina b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Regina deleted file mode 100644 index 20c9c84..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Regina and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Resolute b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Resolute deleted file mode 100644 index 1966890..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Resolute and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rio_Branco b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rio_Branco deleted file mode 100644 index cdda168..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rio_Branco and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rosario b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rosario deleted file mode 100644 index 2ad6ea5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Rosario and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santa_Isabel b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santa_Isabel deleted file mode 100644 index 0fe7391..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santa_Isabel and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santarem b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santarem deleted file mode 100644 index 001638c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santarem and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santiago b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santiago deleted file mode 100644 index 010c6bd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santiago and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santo_Domingo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santo_Domingo deleted file mode 100644 index 4fe36fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Santo_Domingo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Sao_Paulo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Sao_Paulo deleted file mode 100644 index 67935ff..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Sao_Paulo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Scoresbysund b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Scoresbysund deleted file mode 100644 index 9bf411e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Scoresbysund and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Shiprock b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Shiprock deleted file mode 100644 index abb2b97..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Shiprock and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Sitka b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Sitka deleted file mode 100644 index 31f7061..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Sitka and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Barthelemy b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Barthelemy deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Barthelemy and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Johns b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Johns deleted file mode 100644 index 65a5b0c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Johns and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Kitts b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Kitts deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Kitts and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Lucia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Lucia deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Lucia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Thomas b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Thomas deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Thomas and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Vincent b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Vincent deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/St_Vincent and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Swift_Current b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Swift_Current deleted file mode 100644 index 8e9ef25..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Swift_Current and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tegucigalpa b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tegucigalpa deleted file mode 100644 index 2adacb2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tegucigalpa and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Thule b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Thule deleted file mode 100644 index 6f802f1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Thule and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Thunder_Bay b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Thunder_Bay deleted file mode 100644 index 1701373..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Thunder_Bay and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tijuana b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tijuana deleted file mode 100644 index 0fe7391..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tijuana and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Toronto b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Toronto deleted file mode 100644 index 1701373..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Toronto and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tortola b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tortola deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Tortola and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Vancouver b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Vancouver deleted file mode 100644 index bb60cbc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Vancouver and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Virgin b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Virgin deleted file mode 100644 index a662a57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Virgin and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Whitehorse b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Whitehorse deleted file mode 100644 index 318c4a8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Whitehorse and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Winnipeg b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Winnipeg deleted file mode 100644 index ac40299..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Winnipeg and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Yakutat b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Yakutat deleted file mode 100644 index da209f9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Yakutat and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Yellowknife b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Yellowknife deleted file mode 100644 index cd78a6f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/America/Yellowknife and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Casey b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Casey deleted file mode 100644 index 586a765..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Casey and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Davis b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Davis deleted file mode 100644 index d4d47b2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Davis and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/DumontDUrville b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/DumontDUrville deleted file mode 100644 index 7be2474..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/DumontDUrville and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Macquarie b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Macquarie deleted file mode 100644 index 9e7cc68..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Macquarie and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Mawson b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Mawson deleted file mode 100644 index 6d93f6e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Mawson and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/McMurdo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/McMurdo deleted file mode 100644 index 6575fdc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/McMurdo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Palmer b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Palmer deleted file mode 100644 index 9c8fd31..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Palmer and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Rothera b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Rothera deleted file mode 100644 index 241cc44..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Rothera and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/South_Pole b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/South_Pole deleted file mode 100644 index 6575fdc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/South_Pole and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Syowa b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Syowa deleted file mode 100644 index 8c80624..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Syowa and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Troll b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Troll deleted file mode 100644 index a1dcea1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Troll and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Vostok b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Vostok deleted file mode 100644 index 016e06b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Antarctica/Vostok and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Arctic/Longyearbyen b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Arctic/Longyearbyen deleted file mode 100644 index 7f6d958..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Arctic/Longyearbyen and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aden b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aden deleted file mode 100644 index 8c80624..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aden and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Almaty b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Almaty deleted file mode 100644 index 855abbd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Almaty and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Amman b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Amman deleted file mode 100644 index 0a8e350..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Amman and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Anadyr b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Anadyr deleted file mode 100644 index 35c531c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Anadyr and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aqtau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aqtau deleted file mode 100644 index 0e1c16d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aqtau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aqtobe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aqtobe deleted file mode 100644 index 3b5d6eb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Aqtobe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ashgabat b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ashgabat deleted file mode 100644 index 2bd1cb3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ashgabat and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ashkhabad b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ashkhabad deleted file mode 100644 index 2bd1cb3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ashkhabad and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Atyrau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Atyrau deleted file mode 100644 index e7ea9c5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Atyrau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Baghdad b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Baghdad deleted file mode 100644 index c0e6072..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Baghdad and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bahrain b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bahrain deleted file mode 100644 index 098997e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bahrain and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Baku b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Baku deleted file mode 100644 index ae0ce4e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Baku and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bangkok b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bangkok deleted file mode 100644 index fa799db..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bangkok and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Barnaul b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Barnaul deleted file mode 100644 index 2f6b810..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Barnaul and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Beirut b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Beirut deleted file mode 100644 index fb266ed..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Beirut and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bishkek b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bishkek deleted file mode 100644 index 547fd5e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Bishkek and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Brunei b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Brunei deleted file mode 100644 index 098c6a0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Brunei and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Calcutta b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Calcutta deleted file mode 100644 index 0014046..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Calcutta and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chita b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chita deleted file mode 100644 index 75b3d7b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chita and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Choibalsan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Choibalsan deleted file mode 100644 index 2aa5cc4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Choibalsan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chongqing b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chongqing deleted file mode 100644 index 91f6f8b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chongqing and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chungking b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chungking deleted file mode 100644 index 91f6f8b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Chungking and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Colombo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Colombo deleted file mode 100644 index 353fe2a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Colombo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dacca b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dacca deleted file mode 100644 index 3cf597d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dacca and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Damascus b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Damascus deleted file mode 100644 index afd956c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Damascus and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dhaka b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dhaka deleted file mode 100644 index 3cf597d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dhaka and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dili b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dili deleted file mode 100644 index 4614e4f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dili and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dubai b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dubai deleted file mode 100644 index b3ac791..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dubai and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dushanbe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dushanbe deleted file mode 100644 index 89e875b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Dushanbe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Famagusta b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Famagusta deleted file mode 100644 index 653b146..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Famagusta and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Gaza b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Gaza deleted file mode 100644 index dd5781e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Gaza and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Harbin b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Harbin deleted file mode 100644 index 91f6f8b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Harbin and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hebron b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hebron deleted file mode 100644 index a64fc9e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hebron and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ho_Chi_Minh b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ho_Chi_Minh deleted file mode 100644 index 9c45ed9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ho_Chi_Minh and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hong_Kong b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hong_Kong deleted file mode 100644 index f9f7b13..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hong_Kong and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hovd b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hovd deleted file mode 100644 index 8b9abca..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Hovd and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Irkutsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Irkutsk deleted file mode 100644 index e74a4d3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Irkutsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Istanbul b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Istanbul deleted file mode 100644 index 7c2336d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Istanbul and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jakarta b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jakarta deleted file mode 100644 index ec4bd57..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jakarta and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jayapura b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jayapura deleted file mode 100644 index 3002c82..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jayapura and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jerusalem b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jerusalem deleted file mode 100644 index 1ebd066..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Jerusalem and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kabul b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kabul deleted file mode 100644 index 661efc8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kabul and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kamchatka b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kamchatka deleted file mode 100644 index 99776f5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kamchatka and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Karachi b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Karachi deleted file mode 100644 index ba65c0e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Karachi and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kashgar b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kashgar deleted file mode 100644 index 62bdcac..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kashgar and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kathmandu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kathmandu deleted file mode 100644 index 751cf4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kathmandu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Katmandu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Katmandu deleted file mode 100644 index 751cf4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Katmandu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Khandyga b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Khandyga deleted file mode 100644 index 7cdc99a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Khandyga and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kolkata b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kolkata deleted file mode 100644 index 0014046..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kolkata and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Krasnoyarsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Krasnoyarsk deleted file mode 100644 index 4c27b2d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Krasnoyarsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuala_Lumpur b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuala_Lumpur deleted file mode 100644 index 3d9f191..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuala_Lumpur and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuching b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuching deleted file mode 100644 index 098c6a0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuching and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuwait b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuwait deleted file mode 100644 index 8c80624..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Kuwait and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Macao b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Macao deleted file mode 100644 index cac6506..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Macao and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Macau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Macau deleted file mode 100644 index cac6506..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Macau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Magadan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Magadan deleted file mode 100644 index 70c198b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Magadan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Makassar b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Makassar deleted file mode 100644 index 556ba86..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Makassar and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Manila b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Manila deleted file mode 100644 index 168f720..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Manila and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Muscat b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Muscat deleted file mode 100644 index b3ac791..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Muscat and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Nicosia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Nicosia deleted file mode 100644 index f7f10ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Nicosia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Novokuznetsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Novokuznetsk deleted file mode 100644 index a5e1b79..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Novokuznetsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Novosibirsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Novosibirsk deleted file mode 100644 index 4ac7582..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Novosibirsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Omsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Omsk deleted file mode 100644 index 16c5f3c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Omsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Oral b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Oral deleted file mode 100644 index 3b9ecac..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Oral and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Phnom_Penh b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Phnom_Penh deleted file mode 100644 index fa799db..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Phnom_Penh and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Pontianak b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Pontianak deleted file mode 100644 index 12ce24c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Pontianak and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Pyongyang b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Pyongyang deleted file mode 100644 index 7ad7e0b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Pyongyang and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qatar b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qatar deleted file mode 100644 index 098997e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qatar and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qostanay b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qostanay deleted file mode 100644 index 2ee9ef7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qostanay and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qyzylorda b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qyzylorda deleted file mode 100644 index 27b522a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Qyzylorda and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Rangoon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Rangoon deleted file mode 100644 index eef37b4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Rangoon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Riyadh b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Riyadh deleted file mode 100644 index 8c80624..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Riyadh and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Saigon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Saigon deleted file mode 100644 index 9c45ed9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Saigon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Sakhalin b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Sakhalin deleted file mode 100644 index beb77b4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Sakhalin and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Samarkand b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Samarkand deleted file mode 100644 index 8a93767..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Samarkand and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Seoul b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Seoul deleted file mode 100644 index 96199e7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Seoul and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Shanghai b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Shanghai deleted file mode 100644 index 91f6f8b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Shanghai and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Singapore b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Singapore deleted file mode 100644 index 3d9f191..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Singapore and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Srednekolymsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Srednekolymsk deleted file mode 100644 index d21e7ee..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Srednekolymsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Taipei b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Taipei deleted file mode 100644 index 24c4344..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Taipei and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tashkent b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tashkent deleted file mode 100644 index a9f6cd9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tashkent and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tbilisi b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tbilisi deleted file mode 100644 index 3b131bb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tbilisi and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tehran b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tehran deleted file mode 100644 index 78f28cc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tehran and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tel_Aviv b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tel_Aviv deleted file mode 100644 index 1ebd066..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tel_Aviv and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Thimbu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Thimbu deleted file mode 100644 index 95a9de9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Thimbu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Thimphu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Thimphu deleted file mode 100644 index 95a9de9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Thimphu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tokyo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tokyo deleted file mode 100644 index 26f4d34..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tokyo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tomsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tomsk deleted file mode 100644 index a6e494a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Tomsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ujung_Pandang b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ujung_Pandang deleted file mode 100644 index 556ba86..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ujung_Pandang and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ulaanbaatar b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ulaanbaatar deleted file mode 100644 index 2aa5cc4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ulaanbaatar and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ulan_Bator b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ulan_Bator deleted file mode 100644 index 2aa5cc4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ulan_Bator and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Urumqi b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Urumqi deleted file mode 100644 index 62bdcac..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Urumqi and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ust-Nera b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ust-Nera deleted file mode 100644 index d05726a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Ust-Nera and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Vientiane b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Vientiane deleted file mode 100644 index fa799db..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Vientiane and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Vladivostok b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Vladivostok deleted file mode 100644 index 274a10b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Vladivostok and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yakutsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yakutsk deleted file mode 100644 index ae65a5f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yakutsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yangon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yangon deleted file mode 100644 index eef37b4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yangon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yekaterinburg b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yekaterinburg deleted file mode 100644 index d4d19cc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yekaterinburg and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yerevan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yerevan deleted file mode 100644 index 0d5f685..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Asia/Yerevan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Azores b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Azores deleted file mode 100644 index dd2c235..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Azores and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Bermuda b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Bermuda deleted file mode 100644 index 527524e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Bermuda and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Canary b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Canary deleted file mode 100644 index f319215..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Canary and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Cape_Verde b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Cape_Verde deleted file mode 100644 index 0d0d31a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Cape_Verde and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Faeroe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Faeroe deleted file mode 100644 index 4dab7ef..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Faeroe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Faroe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Faroe deleted file mode 100644 index 4dab7ef..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Faroe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Jan_Mayen b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Jan_Mayen deleted file mode 100644 index 7f6d958..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Jan_Mayen and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Madeira b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Madeira deleted file mode 100644 index 6725a0f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Madeira and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Reykjavik b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Reykjavik deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Reykjavik and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/South_Georgia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/South_Georgia deleted file mode 100644 index a2b59a9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/South_Georgia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/St_Helena b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/St_Helena deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/St_Helena and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Stanley b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Stanley deleted file mode 100644 index 1527d0e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Atlantic/Stanley and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/ACT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/ACT deleted file mode 100644 index 0aea4c3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/ACT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Adelaide b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Adelaide deleted file mode 100644 index f5dedca..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Adelaide and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Brisbane b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Brisbane deleted file mode 100644 index 7ff9949..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Brisbane and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Broken_Hill b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Broken_Hill deleted file mode 100644 index 698c76e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Broken_Hill and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Canberra b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Canberra deleted file mode 100644 index 0aea4c3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Canberra and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Currie b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Currie deleted file mode 100644 index 3adb8e1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Currie and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Darwin b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Darwin deleted file mode 100644 index 74a3087..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Darwin and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Eucla b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Eucla deleted file mode 100644 index 1551e96..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Eucla and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Hobart b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Hobart deleted file mode 100644 index 3adb8e1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Hobart and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/LHI b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/LHI deleted file mode 100644 index 069a95a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/LHI and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Lindeman b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Lindeman deleted file mode 100644 index 4ee1825..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Lindeman and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Lord_Howe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Lord_Howe deleted file mode 100644 index 069a95a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Lord_Howe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Melbourne b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Melbourne deleted file mode 100644 index ee903f4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Melbourne and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/NSW b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/NSW deleted file mode 100644 index 0aea4c3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/NSW and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/North b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/North deleted file mode 100644 index 74a3087..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/North and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Perth b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Perth deleted file mode 100644 index f8ddbdf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Perth and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Queensland b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Queensland deleted file mode 100644 index 7ff9949..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Queensland and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/South b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/South deleted file mode 100644 index f5dedca..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/South and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Sydney b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Sydney deleted file mode 100644 index 0aea4c3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Sydney and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Tasmania b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Tasmania deleted file mode 100644 index 3adb8e1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Tasmania and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Victoria b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Victoria deleted file mode 100644 index ee903f4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Victoria and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/West b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/West deleted file mode 100644 index f8ddbdf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/West and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Yancowinna b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Yancowinna deleted file mode 100644 index 698c76e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Australia/Yancowinna and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/Acre b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/Acre deleted file mode 100644 index cdda168..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/Acre and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/DeNoronha b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/DeNoronha deleted file mode 100644 index 73b4b33..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/DeNoronha and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/East b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/East deleted file mode 100644 index 67935ff..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/East and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/West b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/West deleted file mode 100644 index 2708bae..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Brazil/West and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/CET b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/CET deleted file mode 100644 index 40d7124..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/CET and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/CST6CDT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/CST6CDT deleted file mode 100644 index c6981a0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/CST6CDT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Atlantic b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Atlantic deleted file mode 100644 index 756099a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Atlantic and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Central b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Central deleted file mode 100644 index ac40299..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Central and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Eastern b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Eastern deleted file mode 100644 index 1701373..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Eastern and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Mountain b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Mountain deleted file mode 100644 index cd78a6f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Mountain and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Newfoundland b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Newfoundland deleted file mode 100644 index 65a5b0c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Newfoundland and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Pacific b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Pacific deleted file mode 100644 index bb60cbc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Pacific and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Saskatchewan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Saskatchewan deleted file mode 100644 index 20c9c84..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Saskatchewan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Yukon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Yukon deleted file mode 100644 index 318c4a8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Canada/Yukon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Chile/Continental b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Chile/Continental deleted file mode 100644 index 010c6bd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Chile/Continental and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Chile/EasterIsland b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Chile/EasterIsland deleted file mode 100644 index 184cb6a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Chile/EasterIsland and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Cuba b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Cuba deleted file mode 100644 index b69ac45..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Cuba and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EET b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EET deleted file mode 100644 index 9f3a067..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EET and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EST b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EST deleted file mode 100644 index 9964b9a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EST and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EST5EDT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EST5EDT deleted file mode 100644 index a8b9ab1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/EST5EDT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Egypt b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Egypt deleted file mode 100644 index dd538c6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Egypt and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Eire b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Eire deleted file mode 100644 index c729def..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Eire and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+0 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+0 deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+0 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+1 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+1 deleted file mode 100644 index 4dab6f9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+1 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+10 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+10 deleted file mode 100644 index c749290..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+10 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+11 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+11 deleted file mode 100644 index d969982..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+11 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+12 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+12 deleted file mode 100644 index cdeec90..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+12 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+2 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+2 deleted file mode 100644 index fbd2a94..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+2 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+3 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+3 deleted file mode 100644 index ee246ef..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+3 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+4 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+4 deleted file mode 100644 index 5a25ff2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+4 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+5 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+5 deleted file mode 100644 index c0b745f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+5 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+6 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+6 deleted file mode 100644 index 06e777d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+6 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+7 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+7 deleted file mode 100644 index 4e0b53a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+7 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+8 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+8 deleted file mode 100644 index 714b0c5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+8 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+9 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+9 deleted file mode 100644 index 78b9daa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT+9 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-0 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-0 deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-0 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-1 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-1 deleted file mode 100644 index a838beb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-1 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-10 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-10 deleted file mode 100644 index 68ff77d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-10 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-11 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-11 deleted file mode 100644 index 66af5a4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-11 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-12 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-12 deleted file mode 100644 index 17ba505..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-12 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-13 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-13 deleted file mode 100644 index 5f3706c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-13 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-14 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-14 deleted file mode 100644 index 7e9f9c4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-14 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-2 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-2 deleted file mode 100644 index fcef6d9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-2 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-3 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-3 deleted file mode 100644 index 27973bc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-3 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-4 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-4 deleted file mode 100644 index 1efd841..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-4 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-5 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-5 deleted file mode 100644 index 1f76184..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-5 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-6 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-6 deleted file mode 100644 index 952681e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-6 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-7 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-7 deleted file mode 100644 index cefc912..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-7 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-8 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-8 deleted file mode 100644 index afb093d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-8 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-9 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-9 deleted file mode 100644 index 9265fb7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT-9 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT0 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT0 deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/GMT0 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Greenwich b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Greenwich deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Greenwich and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/UCT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/UCT deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/UCT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/UTC b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/UTC deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/UTC and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Universal b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Universal deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Universal and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Zulu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Zulu deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Etc/Zulu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Amsterdam b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Amsterdam deleted file mode 100644 index 40d7124..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Amsterdam and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Andorra b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Andorra deleted file mode 100644 index 5962550..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Andorra and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Astrakhan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Astrakhan deleted file mode 100644 index a41624f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Astrakhan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Athens b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Athens deleted file mode 100644 index 9f3a067..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Athens and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Belfast b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Belfast deleted file mode 100644 index 5ad7422..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Belfast and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Belgrade b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Belgrade deleted file mode 100644 index 27de456..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Belgrade and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Berlin b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Berlin deleted file mode 100644 index 7f6d958..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Berlin and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Bratislava b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Bratislava deleted file mode 100644 index ce8f433..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Bratislava and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Brussels b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Brussels deleted file mode 100644 index 40d7124..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Brussels and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Bucharest b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Bucharest deleted file mode 100644 index 4303b90..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Bucharest and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Budapest b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Budapest deleted file mode 100644 index b76c873..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Budapest and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Busingen b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Busingen deleted file mode 100644 index ad6cf59..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Busingen and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Chisinau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Chisinau deleted file mode 100644 index 5ee23fe..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Chisinau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Copenhagen b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Copenhagen deleted file mode 100644 index 7f6d958..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Copenhagen and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Dublin b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Dublin deleted file mode 100644 index c729def..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Dublin and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Gibraltar b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Gibraltar deleted file mode 100644 index a38f11f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Gibraltar and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Guernsey b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Guernsey deleted file mode 100644 index 5ad7422..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Guernsey and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Helsinki b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Helsinki deleted file mode 100644 index b4f8f9c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Helsinki and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Isle_of_Man b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Isle_of_Man deleted file mode 100644 index 5ad7422..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Isle_of_Man and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Istanbul b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Istanbul deleted file mode 100644 index 7c2336d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Istanbul and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Jersey b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Jersey deleted file mode 100644 index 5ad7422..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Jersey and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kaliningrad b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kaliningrad deleted file mode 100644 index cc99bea..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kaliningrad and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kiev b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kiev deleted file mode 100644 index 52efea8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kiev and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kirov b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kirov deleted file mode 100644 index 0cfb956..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kirov and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kyiv b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kyiv deleted file mode 100644 index 52efea8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Kyiv and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Lisbon b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Lisbon deleted file mode 100644 index 616de16..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Lisbon and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Ljubljana b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Ljubljana deleted file mode 100644 index 27de456..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Ljubljana and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/London b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/London deleted file mode 100644 index 5ad7422..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/London and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Luxembourg b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Luxembourg deleted file mode 100644 index 40d7124..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Luxembourg and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Madrid b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Madrid deleted file mode 100644 index 53f4cd1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Madrid and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Malta b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Malta deleted file mode 100644 index 1d1a7bc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Malta and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Mariehamn b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Mariehamn deleted file mode 100644 index b4f8f9c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Mariehamn and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Minsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Minsk deleted file mode 100644 index 3731e40..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Minsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Monaco b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Monaco deleted file mode 100644 index 7d366c6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Monaco and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Moscow b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Moscow deleted file mode 100644 index ddb3f4e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Moscow and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Nicosia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Nicosia deleted file mode 100644 index f7f10ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Nicosia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Oslo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Oslo deleted file mode 100644 index 7f6d958..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Oslo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Paris b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Paris deleted file mode 100644 index 7d366c6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Paris and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Podgorica b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Podgorica deleted file mode 100644 index 27de456..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Podgorica and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Prague b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Prague deleted file mode 100644 index ce8f433..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Prague and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Riga b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Riga deleted file mode 100644 index 8db477d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Riga and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Rome b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Rome deleted file mode 100644 index 32b2899..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Rome and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Samara b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Samara deleted file mode 100644 index d0ea2f2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Samara and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/San_Marino b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/San_Marino deleted file mode 100644 index 32b2899..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/San_Marino and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Sarajevo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Sarajevo deleted file mode 100644 index 27de456..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Sarajevo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Saratov b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Saratov deleted file mode 100644 index a863913..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Saratov and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Simferopol b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Simferopol deleted file mode 100644 index 4bf24de..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Simferopol and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Skopje b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Skopje deleted file mode 100644 index 27de456..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Skopje and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Sofia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Sofia deleted file mode 100644 index 0e4d879..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Sofia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Stockholm b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Stockholm deleted file mode 100644 index 7f6d958..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Stockholm and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tallinn b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tallinn deleted file mode 100644 index b5acca3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tallinn and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tirane b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tirane deleted file mode 100644 index 0b86017..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tirane and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tiraspol b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tiraspol deleted file mode 100644 index 5ee23fe..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Tiraspol and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Ulyanovsk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Ulyanovsk deleted file mode 100644 index d668233..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Ulyanovsk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Uzhgorod b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Uzhgorod deleted file mode 100644 index 52efea8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Uzhgorod and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vaduz b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vaduz deleted file mode 100644 index ad6cf59..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vaduz and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vatican b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vatican deleted file mode 100644 index 32b2899..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vatican and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vienna b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vienna deleted file mode 100644 index 3582bb1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vienna and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vilnius b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vilnius deleted file mode 100644 index 7abd63f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Vilnius and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Volgograd b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Volgograd deleted file mode 100644 index 9d51a38..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Volgograd and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Warsaw b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Warsaw deleted file mode 100644 index e33cf67..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Warsaw and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zagreb b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zagreb deleted file mode 100644 index 27de456..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zagreb and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zaporozhye b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zaporozhye deleted file mode 100644 index 52efea8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zaporozhye and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zurich b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zurich deleted file mode 100644 index ad6cf59..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Europe/Zurich and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Factory b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Factory deleted file mode 100644 index 60aa2a0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Factory and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GB b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GB deleted file mode 100644 index 5ad7422..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GB and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GB-Eire b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GB-Eire deleted file mode 100644 index 5ad7422..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GB-Eire and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT+0 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT+0 deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT+0 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT-0 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT-0 deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT-0 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT0 b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT0 deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/GMT0 and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Greenwich b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Greenwich deleted file mode 100644 index c634746..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Greenwich and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/HST b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/HST deleted file mode 100644 index c7cd060..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/HST and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Hongkong b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Hongkong deleted file mode 100644 index f9f7b13..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Hongkong and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Iceland b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Iceland deleted file mode 100644 index 28b32ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Iceland and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Antananarivo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Antananarivo deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Antananarivo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Chagos b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Chagos deleted file mode 100644 index a555481..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Chagos and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Christmas b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Christmas deleted file mode 100644 index fa799db..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Christmas and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Cocos b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Cocos deleted file mode 100644 index eef37b4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Cocos and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Comoro b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Comoro deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Comoro and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Kerguelen b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Kerguelen deleted file mode 100644 index 555728b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Kerguelen and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mahe b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mahe deleted file mode 100644 index b3ac791..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mahe and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Maldives b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Maldives deleted file mode 100644 index 555728b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Maldives and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mauritius b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mauritius deleted file mode 100644 index 212d4b2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mauritius and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mayotte b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mayotte deleted file mode 100644 index 9dcfc19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Mayotte and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Reunion b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Reunion deleted file mode 100644 index b3ac791..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Indian/Reunion and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Iran b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Iran deleted file mode 100644 index 78f28cc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Iran and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Israel b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Israel deleted file mode 100644 index 1ebd066..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Israel and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Jamaica b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Jamaica deleted file mode 100644 index 2a9b7fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Jamaica and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Japan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Japan deleted file mode 100644 index 26f4d34..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Japan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Kwajalein b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Kwajalein deleted file mode 100644 index 1887a60..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Kwajalein and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Libya b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Libya deleted file mode 100644 index 07b393b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Libya and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MET b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MET deleted file mode 100644 index 40d7124..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MET and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MST b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MST deleted file mode 100644 index ab37e84..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MST and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MST7MDT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MST7MDT deleted file mode 100644 index abb2b97..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/MST7MDT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/BajaNorte b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/BajaNorte deleted file mode 100644 index 0fe7391..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/BajaNorte and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/BajaSur b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/BajaSur deleted file mode 100644 index 386616a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/BajaSur and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/General b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/General deleted file mode 100644 index ad70cf3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Mexico/General and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/NZ b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/NZ deleted file mode 100644 index 6575fdc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/NZ and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/NZ-CHAT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/NZ-CHAT deleted file mode 100644 index bde46cf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/NZ-CHAT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Navajo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Navajo deleted file mode 100644 index abb2b97..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Navajo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/PRC b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/PRC deleted file mode 100644 index 91f6f8b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/PRC and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/PST8PDT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/PST8PDT deleted file mode 100644 index 610e7af..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/PST8PDT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Apia b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Apia deleted file mode 100644 index e592a68..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Apia and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Auckland b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Auckland deleted file mode 100644 index 6575fdc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Auckland and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Bougainville b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Bougainville deleted file mode 100644 index c535acd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Bougainville and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Chatham b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Chatham deleted file mode 100644 index bde46cf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Chatham and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Chuuk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Chuuk deleted file mode 100644 index 7be2474..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Chuuk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Easter b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Easter deleted file mode 100644 index 184cb6a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Easter and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Efate b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Efate deleted file mode 100644 index 777325f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Efate and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Enderbury b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Enderbury deleted file mode 100644 index b1c4b07..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Enderbury and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Fakaofo b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Fakaofo deleted file mode 100644 index 4905ea7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Fakaofo and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Fiji b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Fiji deleted file mode 100644 index acf8091..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Fiji and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Funafuti b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Funafuti deleted file mode 100644 index 47661d4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Funafuti and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Galapagos b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Galapagos deleted file mode 100644 index 40051dd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Galapagos and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Gambier b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Gambier deleted file mode 100644 index 84acaf4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Gambier and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Guadalcanal b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Guadalcanal deleted file mode 100644 index 1ab8353..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Guadalcanal and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Guam b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Guam deleted file mode 100644 index 66490d2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Guam and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Honolulu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Honolulu deleted file mode 100644 index c7cd060..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Honolulu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Johnston b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Johnston deleted file mode 100644 index c7cd060..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Johnston and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kanton b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kanton deleted file mode 100644 index b1c4b07..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kanton and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kiritimati b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kiritimati deleted file mode 100644 index b4c6037..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kiritimati and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kosrae b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kosrae deleted file mode 100644 index 0666fb0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kosrae and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kwajalein b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kwajalein deleted file mode 100644 index 1887a60..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Kwajalein and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Majuro b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Majuro deleted file mode 100644 index 47661d4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Majuro and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Marquesas b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Marquesas deleted file mode 100644 index f546c03..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Marquesas and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Midway b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Midway deleted file mode 100644 index cb56709..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Midway and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Nauru b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Nauru deleted file mode 100644 index 3339b6c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Nauru and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Niue b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Niue deleted file mode 100644 index f76972f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Niue and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Norfolk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Norfolk deleted file mode 100644 index 3b4186d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Norfolk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Noumea b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Noumea deleted file mode 100644 index 959cc8c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Noumea and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pago_Pago b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pago_Pago deleted file mode 100644 index cb56709..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pago_Pago and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Palau b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Palau deleted file mode 100644 index 1cbebe2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Palau and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pitcairn b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pitcairn deleted file mode 100644 index 5ee90e7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pitcairn and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pohnpei b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pohnpei deleted file mode 100644 index 1ab8353..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Pohnpei and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Ponape b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Ponape deleted file mode 100644 index 1ab8353..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Ponape and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Port_Moresby b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Port_Moresby deleted file mode 100644 index 7be2474..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Port_Moresby and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Rarotonga b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Rarotonga deleted file mode 100644 index 184a87c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Rarotonga and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Saipan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Saipan deleted file mode 100644 index 66490d2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Saipan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Samoa b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Samoa deleted file mode 100644 index cb56709..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Samoa and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tahiti b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tahiti deleted file mode 100644 index 481edd3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tahiti and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tarawa b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tarawa deleted file mode 100644 index 47661d4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tarawa and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tongatapu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tongatapu deleted file mode 100644 index c8824ab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Tongatapu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Truk b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Truk deleted file mode 100644 index 7be2474..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Truk and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Wake b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Wake deleted file mode 100644 index 47661d4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Wake and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Wallis b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Wallis deleted file mode 100644 index 47661d4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Wallis and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Yap b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Yap deleted file mode 100644 index 7be2474..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Pacific/Yap and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Poland b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Poland deleted file mode 100644 index e33cf67..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Poland and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Portugal b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Portugal deleted file mode 100644 index 616de16..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Portugal and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/ROC b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/ROC deleted file mode 100644 index 24c4344..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/ROC and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/ROK b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/ROK deleted file mode 100644 index 96199e7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/ROK and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Singapore b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Singapore deleted file mode 100644 index 3d9f191..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Singapore and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Turkey b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Turkey deleted file mode 100644 index 7c2336d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Turkey and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/UCT b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/UCT deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/UCT and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Alaska b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Alaska deleted file mode 100644 index 9bbb2fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Alaska and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Aleutian b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Aleutian deleted file mode 100644 index 4323649..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Aleutian and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Arizona b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Arizona deleted file mode 100644 index ab37e84..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Arizona and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Central b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Central deleted file mode 100644 index c6981a0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Central and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/East-Indiana b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/East-Indiana deleted file mode 100644 index a84b6e9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/East-Indiana and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Eastern b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Eastern deleted file mode 100644 index a8b9ab1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Eastern and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Hawaii b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Hawaii deleted file mode 100644 index c7cd060..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Hawaii and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Indiana-Starke b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Indiana-Starke deleted file mode 100644 index 025d132..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Indiana-Starke and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Michigan b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Michigan deleted file mode 100644 index e104faa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Michigan and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Mountain b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Mountain deleted file mode 100644 index abb2b97..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Mountain and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Pacific b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Pacific deleted file mode 100644 index 610e7af..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Pacific and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Samoa b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Samoa deleted file mode 100644 index cb56709..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/US/Samoa and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/UTC b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/UTC deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/UTC and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Universal b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Universal deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Universal and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/W-SU b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/W-SU deleted file mode 100644 index ddb3f4e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/W-SU and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/WET b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/WET deleted file mode 100644 index 616de16..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/WET and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Zulu b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Zulu deleted file mode 100644 index 91558be..0000000 Binary files a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/Zulu and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/iso3166.tab b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/iso3166.tab deleted file mode 100644 index 402c015..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/iso3166.tab +++ /dev/null @@ -1,279 +0,0 @@ -# ISO 3166 alpha-2 country codes -# -# This file is in the public domain, so clarified as of -# 2009-05-17 by Arthur David Olson. -# -# From Paul Eggert (2023-09-06): -# This file contains a table of two-letter country codes. Columns are -# separated by a single tab. Lines beginning with '#' are comments. -# All text uses UTF-8 encoding. The columns of the table are as follows: -# -# 1. ISO 3166-1 alpha-2 country code, current as of -# ISO/TC 46 N1108 (2023-04-05). See: ISO/TC 46 Documents -# https://www.iso.org/committee/48750.html?view=documents -# 2. The usual English name for the coded region. This sometimes -# departs from ISO-listed names, sometimes so that sorted subsets -# of names are useful (e.g., "Samoa (American)" and "Samoa -# (western)" rather than "American Samoa" and "Samoa"), -# sometimes to avoid confusion among non-experts (e.g., -# "Czech Republic" and "Turkey" rather than "Czechia" and "Türkiye"), -# and sometimes to omit needless detail or churn (e.g., "Netherlands" -# rather than "Netherlands (the)" or "Netherlands (Kingdom of the)"). -# -# The table is sorted by country code. -# -# This table is intended as an aid for users, to help them select time -# zone data appropriate for their practical needs. It is not intended -# to take or endorse any position on legal or territorial claims. -# -#country- -#code name of country, territory, area, or subdivision -AD Andorra -AE United Arab Emirates -AF Afghanistan -AG Antigua & Barbuda -AI Anguilla -AL Albania -AM Armenia -AO Angola -AQ Antarctica -AR Argentina -AS Samoa (American) -AT Austria -AU Australia -AW Aruba -AX Åland Islands -AZ Azerbaijan -BA Bosnia & Herzegovina -BB Barbados -BD Bangladesh -BE Belgium -BF Burkina Faso -BG Bulgaria -BH Bahrain -BI Burundi -BJ Benin -BL St Barthelemy -BM Bermuda -BN Brunei -BO Bolivia -BQ Caribbean NL -BR Brazil -BS Bahamas -BT Bhutan -BV Bouvet Island -BW Botswana -BY Belarus -BZ Belize -CA Canada -CC Cocos (Keeling) Islands -CD Congo (Dem. Rep.) -CF Central African Rep. -CG Congo (Rep.) -CH Switzerland -CI Côte d'Ivoire -CK Cook Islands -CL Chile -CM Cameroon -CN China -CO Colombia -CR Costa Rica -CU Cuba -CV Cape Verde -CW Curaçao -CX Christmas Island -CY Cyprus -CZ Czech Republic -DE Germany -DJ Djibouti -DK Denmark -DM Dominica -DO Dominican Republic -DZ Algeria -EC Ecuador -EE Estonia -EG Egypt -EH Western Sahara -ER Eritrea -ES Spain -ET Ethiopia -FI Finland -FJ Fiji -FK Falkland Islands -FM Micronesia -FO Faroe Islands -FR France -GA Gabon -GB Britain (UK) -GD Grenada -GE Georgia -GF French Guiana -GG Guernsey -GH Ghana -GI Gibraltar -GL Greenland -GM Gambia -GN Guinea -GP Guadeloupe -GQ Equatorial Guinea -GR Greece -GS South Georgia & the South Sandwich Islands -GT Guatemala -GU Guam -GW Guinea-Bissau -GY Guyana -HK Hong Kong -HM Heard Island & McDonald Islands -HN Honduras -HR Croatia -HT Haiti -HU Hungary -ID Indonesia -IE Ireland -IL Israel -IM Isle of Man -IN India -IO British Indian Ocean Territory -IQ Iraq -IR Iran -IS Iceland -IT Italy -JE Jersey -JM Jamaica -JO Jordan -JP Japan -KE Kenya -KG Kyrgyzstan -KH Cambodia -KI Kiribati -KM Comoros -KN St Kitts & Nevis -KP Korea (North) -KR Korea (South) -KW Kuwait -KY Cayman Islands -KZ Kazakhstan -LA Laos -LB Lebanon -LC St Lucia -LI Liechtenstein -LK Sri Lanka -LR Liberia -LS Lesotho -LT Lithuania -LU Luxembourg -LV Latvia -LY Libya -MA Morocco -MC Monaco -MD Moldova -ME Montenegro -MF St Martin (French) -MG Madagascar -MH Marshall Islands -MK North Macedonia -ML Mali -MM Myanmar (Burma) -MN Mongolia -MO Macau -MP Northern Mariana Islands -MQ Martinique -MR Mauritania -MS Montserrat -MT Malta -MU Mauritius -MV Maldives -MW Malawi -MX Mexico -MY Malaysia -MZ Mozambique -NA Namibia -NC New Caledonia -NE Niger -NF Norfolk Island -NG Nigeria -NI Nicaragua -NL Netherlands -NO Norway -NP Nepal -NR Nauru -NU Niue -NZ New Zealand -OM Oman -PA Panama -PE Peru -PF French Polynesia -PG Papua New Guinea -PH Philippines -PK Pakistan -PL Poland -PM St Pierre & Miquelon -PN Pitcairn -PR Puerto Rico -PS Palestine -PT Portugal -PW Palau -PY Paraguay -QA Qatar -RE Réunion -RO Romania -RS Serbia -RU Russia -RW Rwanda -SA Saudi Arabia -SB Solomon Islands -SC Seychelles -SD Sudan -SE Sweden -SG Singapore -SH St Helena -SI Slovenia -SJ Svalbard & Jan Mayen -SK Slovakia -SL Sierra Leone -SM San Marino -SN Senegal -SO Somalia -SR Suriname -SS South Sudan -ST Sao Tome & Principe -SV El Salvador -SX St Maarten (Dutch) -SY Syria -SZ Eswatini (Swaziland) -TC Turks & Caicos Is -TD Chad -TF French S. Terr. -TG Togo -TH Thailand -TJ Tajikistan -TK Tokelau -TL East Timor -TM Turkmenistan -TN Tunisia -TO Tonga -TR Turkey -TT Trinidad & Tobago -TV Tuvalu -TW Taiwan -TZ Tanzania -UA Ukraine -UG Uganda -UM US minor outlying islands -US United States -UY Uruguay -UZ Uzbekistan -VA Vatican City -VC St Vincent -VE Venezuela -VG Virgin Islands (UK) -VI Virgin Islands (US) -VN Vietnam -VU Vanuatu -WF Wallis & Futuna -WS Samoa (western) -YE Yemen -YT Mayotte -ZA South Africa -ZM Zambia -ZW Zimbabwe diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/leapseconds b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/leapseconds deleted file mode 100644 index 76f7714..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/leapseconds +++ /dev/null @@ -1,79 +0,0 @@ -# Allowance for leap seconds added to each time zone file. - -# This file is in the public domain. - -# This file is generated automatically from the data in the public-domain -# NIST/IERS format leap-seconds.list file, which can be copied from -# -# or, in a variant with different comments, from -# . -# For more about leap-seconds.list, please see -# The NTP Timescale and Leap Seconds -# . - -# The rules for leap seconds are specified in Annex 1 (Time scales) of: -# Standard-frequency and time-signal emissions. -# International Telecommunication Union - Radiocommunication Sector -# (ITU-R) Recommendation TF.460-6 (02/2002) -# . -# The International Earth Rotation and Reference Systems Service (IERS) -# periodically uses leap seconds to keep UTC to within 0.9 s of UT1 -# (a proxy for Earth's angle in space as measured by astronomers) -# and publishes leap second data in a copyrighted file -# . -# See: Levine J. Coordinated Universal Time and the leap second. -# URSI Radio Sci Bull. 2016;89(4):30-6. doi:10.23919/URSIRSB.2016.7909995 -# . - -# There were no leap seconds before 1972, as no official mechanism -# accounted for the discrepancy between atomic time (TAI) and the earth's -# rotation. The first ("1 Jan 1972") data line in leap-seconds.list -# does not denote a leap second; it denotes the start of the current definition -# of UTC. - -# All leap-seconds are Stationary (S) at the given UTC time. -# The correction (+ or -) is made at the given time, so in the unlikely -# event of a negative leap second, a line would look like this: -# Leap YEAR MON DAY 23:59:59 - S -# Typical lines look like this: -# Leap YEAR MON DAY 23:59:60 + S -Leap 1972 Jun 30 23:59:60 + S -Leap 1972 Dec 31 23:59:60 + S -Leap 1973 Dec 31 23:59:60 + S -Leap 1974 Dec 31 23:59:60 + S -Leap 1975 Dec 31 23:59:60 + S -Leap 1976 Dec 31 23:59:60 + S -Leap 1977 Dec 31 23:59:60 + S -Leap 1978 Dec 31 23:59:60 + S -Leap 1979 Dec 31 23:59:60 + S -Leap 1981 Jun 30 23:59:60 + S -Leap 1982 Jun 30 23:59:60 + S -Leap 1983 Jun 30 23:59:60 + S -Leap 1985 Jun 30 23:59:60 + S -Leap 1987 Dec 31 23:59:60 + S -Leap 1989 Dec 31 23:59:60 + S -Leap 1990 Dec 31 23:59:60 + S -Leap 1992 Jun 30 23:59:60 + S -Leap 1993 Jun 30 23:59:60 + S -Leap 1994 Jun 30 23:59:60 + S -Leap 1995 Dec 31 23:59:60 + S -Leap 1997 Jun 30 23:59:60 + S -Leap 1998 Dec 31 23:59:60 + S -Leap 2005 Dec 31 23:59:60 + S -Leap 2008 Dec 31 23:59:60 + S -Leap 2012 Jun 30 23:59:60 + S -Leap 2015 Jun 30 23:59:60 + S -Leap 2016 Dec 31 23:59:60 + S - -# UTC timestamp when this leap second list expires. -# Any additional leap seconds will come after this. -# This Expires line is commented out for now, -# so that pre-2020a zic implementations do not reject this file. -#Expires 2025 Dec 28 00:00:00 - -# POSIX timestamps for the data in this file: -#updated 1736208000 (2025-01-07 00:00:00 UTC) -#expires 1766880000 (2025-12-28 00:00:00 UTC) - -# Updated through IERS Bulletin C (https://hpiers.obspm.fr/iers/bul/bulc/bulletinc.dat) -# File expires on 28 December 2025 diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/tzdata.zi b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/tzdata.zi deleted file mode 100644 index 0bcae52..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/tzdata.zi +++ /dev/null @@ -1,4300 +0,0 @@ -# version unknown -# This zic input file is in the public domain. -R d 1916 o - Jun 14 23s 1 S -R d 1916 1919 - O Su>=1 23s 0 - -R d 1917 o - Mar 24 23s 1 S -R d 1918 o - Mar 9 23s 1 S -R d 1919 o - Mar 1 23s 1 S -R d 1920 o - F 14 23s 1 S -R d 1920 o - O 23 23s 0 - -R d 1921 o - Mar 14 23s 1 S -R d 1921 o - Jun 21 23s 0 - -R d 1939 o - S 11 23s 1 S -R d 1939 o - N 19 1 0 - -R d 1944 1945 - Ap M>=1 2 1 S -R d 1944 o - O 8 2 0 - -R d 1945 o - S 16 1 0 - -R d 1971 o - Ap 25 23s 1 S -R d 1971 o - S 26 23s 0 - -R d 1977 o - May 6 0 1 S -R d 1977 o - O 21 0 0 - -R d 1978 o - Mar 24 1 1 S -R d 1978 o - S 22 3 0 - -R d 1980 o - Ap 25 0 1 S -R d 1980 o - O 31 2 0 - -R K 1940 o - Jul 15 0 1 S -R K 1940 o - O 1 0 0 - -R K 1941 o - Ap 15 0 1 S -R K 1941 o - S 16 0 0 - -R K 1942 1944 - Ap 1 0 1 S -R K 1942 o - O 27 0 0 - -R K 1943 1945 - N 1 0 0 - -R K 1945 o - Ap 16 0 1 S -R K 1957 o - May 10 0 1 S -R K 1957 1958 - O 1 0 0 - -R K 1958 o - May 1 0 1 S -R K 1959 1981 - May 1 1 1 S -R K 1959 1965 - S 30 3 0 - -R K 1966 1994 - O 1 3 0 - -R K 1982 o - Jul 25 1 1 S -R K 1983 o - Jul 12 1 1 S -R K 1984 1988 - May 1 1 1 S -R K 1989 o - May 6 1 1 S -R K 1990 1994 - May 1 1 1 S -R K 1995 2010 - Ap lastF 0s 1 S -R K 1995 2005 - S lastTh 24 0 - -R K 2006 o - S 21 24 0 - -R K 2007 o - S Th>=1 24 0 - -R K 2008 o - Au lastTh 24 0 - -R K 2009 o - Au 20 24 0 - -R K 2010 o - Au 10 24 0 - -R K 2010 o - S 9 24 1 S -R K 2010 o - S lastTh 24 0 - -R K 2014 o - May 15 24 1 S -R K 2014 o - Jun 26 24 0 - -R K 2014 o - Jul 31 24 1 S -R K 2014 o - S lastTh 24 0 - -R K 2023 ma - Ap lastF 0 1 S -R K 2023 ma - O lastTh 24 0 - -R L 1951 o - O 14 2 1 S -R L 1952 o - Ja 1 0 0 - -R L 1953 o - O 9 2 1 S -R L 1954 o - Ja 1 0 0 - -R L 1955 o - S 30 0 1 S -R L 1956 o - Ja 1 0 0 - -R L 1982 1984 - Ap 1 0 1 S -R L 1982 1985 - O 1 0 0 - -R L 1985 o - Ap 6 0 1 S -R L 1986 o - Ap 4 0 1 S -R L 1986 o - O 3 0 0 - -R L 1987 1989 - Ap 1 0 1 S -R L 1987 1989 - O 1 0 0 - -R L 1997 o - Ap 4 0 1 S -R L 1997 o - O 4 0 0 - -R L 2013 o - Mar lastF 1 1 S -R L 2013 o - O lastF 2 0 - -R MU 1982 o - O 10 0 1 - -R MU 1983 o - Mar 21 0 0 - -R MU 2008 o - O lastSu 2 1 - -R MU 2009 o - Mar lastSu 2 0 - -R M 1939 o - S 12 0 1 - -R M 1939 o - N 19 0 0 - -R M 1940 o - F 25 0 1 - -R M 1945 o - N 18 0 0 - -R M 1950 o - Jun 11 0 1 - -R M 1950 o - O 29 0 0 - -R M 1967 o - Jun 3 12 1 - -R M 1967 o - O 1 0 0 - -R M 1974 o - Jun 24 0 1 - -R M 1974 o - S 1 0 0 - -R M 1976 1977 - May 1 0 1 - -R M 1976 o - Au 1 0 0 - -R M 1977 o - S 28 0 0 - -R M 1978 o - Jun 1 0 1 - -R M 1978 o - Au 4 0 0 - -R M 2008 o - Jun 1 0 1 - -R M 2008 o - S 1 0 0 - -R M 2009 o - Jun 1 0 1 - -R M 2009 o - Au 21 0 0 - -R M 2010 o - May 2 0 1 - -R M 2010 o - Au 8 0 0 - -R M 2011 o - Ap 3 0 1 - -R M 2011 o - Jul 31 0 0 - -R M 2012 2013 - Ap lastSu 2 1 - -R M 2012 o - Jul 20 3 0 - -R M 2012 o - Au 20 2 1 - -R M 2012 o - S 30 3 0 - -R M 2013 o - Jul 7 3 0 - -R M 2013 o - Au 10 2 1 - -R M 2013 2018 - O lastSu 3 0 - -R M 2014 2018 - Mar lastSu 2 1 - -R M 2014 o - Jun 28 3 0 - -R M 2014 o - Au 2 2 1 - -R M 2015 o - Jun 14 3 0 - -R M 2015 o - Jul 19 2 1 - -R M 2016 o - Jun 5 3 0 - -R M 2016 o - Jul 10 2 1 - -R M 2017 o - May 21 3 0 - -R M 2017 o - Jul 2 2 1 - -R M 2018 o - May 13 3 0 - -R M 2018 o - Jun 17 2 1 - -R M 2019 o - May 5 3 -1 - -R M 2019 o - Jun 9 2 0 - -R M 2020 o - Ap 19 3 -1 - -R M 2020 o - May 31 2 0 - -R M 2021 o - Ap 11 3 -1 - -R M 2021 o - May 16 2 0 - -R M 2022 o - Mar 27 3 -1 - -R M 2022 o - May 8 2 0 - -R M 2023 o - Mar 19 3 -1 - -R M 2023 o - Ap 23 2 0 - -R M 2024 o - Mar 10 3 -1 - -R M 2024 o - Ap 14 2 0 - -R M 2025 o - F 23 3 -1 - -R M 2025 o - Ap 6 2 0 - -R M 2026 o - F 15 3 -1 - -R M 2026 o - Mar 22 2 0 - -R M 2027 o - F 7 3 -1 - -R M 2027 o - Mar 14 2 0 - -R M 2028 o - Ja 23 3 -1 - -R M 2028 o - Mar 5 2 0 - -R M 2029 o - Ja 14 3 -1 - -R M 2029 o - F 18 2 0 - -R M 2029 o - D 30 3 -1 - -R M 2030 o - F 10 2 0 - -R M 2030 o - D 22 3 -1 - -R M 2031 o - Ja 26 2 0 - -R M 2031 o - D 14 3 -1 - -R M 2032 o - Ja 18 2 0 - -R M 2032 o - N 28 3 -1 - -R M 2033 o - Ja 9 2 0 - -R M 2033 o - N 20 3 -1 - -R M 2033 o - D 25 2 0 - -R M 2034 o - N 5 3 -1 - -R M 2034 o - D 17 2 0 - -R M 2035 o - O 28 3 -1 - -R M 2035 o - D 9 2 0 - -R M 2036 o - O 19 3 -1 - -R M 2036 o - N 23 2 0 - -R M 2037 o - O 4 3 -1 - -R M 2037 o - N 15 2 0 - -R M 2038 o - S 26 3 -1 - -R M 2038 o - O 31 2 0 - -R M 2039 o - S 18 3 -1 - -R M 2039 o - O 23 2 0 - -R M 2040 o - S 2 3 -1 - -R M 2040 o - O 14 2 0 - -R M 2041 o - Au 25 3 -1 - -R M 2041 o - S 29 2 0 - -R M 2042 o - Au 10 3 -1 - -R M 2042 o - S 21 2 0 - -R M 2043 o - Au 2 3 -1 - -R M 2043 o - S 13 2 0 - -R M 2044 o - Jul 24 3 -1 - -R M 2044 o - Au 28 2 0 - -R M 2045 o - Jul 9 3 -1 - -R M 2045 o - Au 20 2 0 - -R M 2046 o - Jul 1 3 -1 - -R M 2046 o - Au 5 2 0 - -R M 2047 o - Jun 23 3 -1 - -R M 2047 o - Jul 28 2 0 - -R M 2048 o - Jun 7 3 -1 - -R M 2048 o - Jul 19 2 0 - -R M 2049 o - May 30 3 -1 - -R M 2049 o - Jul 4 2 0 - -R M 2050 o - May 15 3 -1 - -R M 2050 o - Jun 26 2 0 - -R M 2051 o - May 7 3 -1 - -R M 2051 o - Jun 18 2 0 - -R M 2052 o - Ap 28 3 -1 - -R M 2052 o - Jun 2 2 0 - -R M 2053 o - Ap 13 3 -1 - -R M 2053 o - May 25 2 0 - -R M 2054 o - Ap 5 3 -1 - -R M 2054 o - May 10 2 0 - -R M 2055 o - Mar 28 3 -1 - -R M 2055 o - May 2 2 0 - -R M 2056 o - Mar 12 3 -1 - -R M 2056 o - Ap 23 2 0 - -R M 2057 o - Mar 4 3 -1 - -R M 2057 o - Ap 8 2 0 - -R M 2058 o - F 17 3 -1 - -R M 2058 o - Mar 31 2 0 - -R M 2059 o - F 9 3 -1 - -R M 2059 o - Mar 23 2 0 - -R M 2060 o - F 1 3 -1 - -R M 2060 o - Mar 7 2 0 - -R M 2061 o - Ja 16 3 -1 - -R M 2061 o - F 27 2 0 - -R M 2062 o - Ja 8 3 -1 - -R M 2062 o - F 12 2 0 - -R M 2062 o - D 31 3 -1 - -R M 2063 o - F 4 2 0 - -R M 2063 o - D 16 3 -1 - -R M 2064 o - Ja 27 2 0 - -R M 2064 o - D 7 3 -1 - -R M 2065 o - Ja 11 2 0 - -R M 2065 o - N 22 3 -1 - -R M 2066 o - Ja 3 2 0 - -R M 2066 o - N 14 3 -1 - -R M 2066 o - D 26 2 0 - -R M 2067 o - N 6 3 -1 - -R M 2067 o - D 11 2 0 - -R M 2068 o - O 21 3 -1 - -R M 2068 o - D 2 2 0 - -R M 2069 o - O 13 3 -1 - -R M 2069 o - N 17 2 0 - -R M 2070 o - O 5 3 -1 - -R M 2070 o - N 9 2 0 - -R M 2071 o - S 20 3 -1 - -R M 2071 o - N 1 2 0 - -R M 2072 o - S 11 3 -1 - -R M 2072 o - O 16 2 0 - -R M 2073 o - Au 27 3 -1 - -R M 2073 o - O 8 2 0 - -R M 2074 o - Au 19 3 -1 - -R M 2074 o - S 30 2 0 - -R M 2075 o - Au 11 3 -1 - -R M 2075 o - S 15 2 0 - -R M 2076 o - Jul 26 3 -1 - -R M 2076 o - S 6 2 0 - -R M 2077 o - Jul 18 3 -1 - -R M 2077 o - Au 22 2 0 - -R M 2078 o - Jul 10 3 -1 - -R M 2078 o - Au 14 2 0 - -R M 2079 o - Jun 25 3 -1 - -R M 2079 o - Au 6 2 0 - -R M 2080 o - Jun 16 3 -1 - -R M 2080 o - Jul 21 2 0 - -R M 2081 o - Jun 1 3 -1 - -R M 2081 o - Jul 13 2 0 - -R M 2082 o - May 24 3 -1 - -R M 2082 o - Jun 28 2 0 - -R M 2083 o - May 16 3 -1 - -R M 2083 o - Jun 20 2 0 - -R M 2084 o - Ap 30 3 -1 - -R M 2084 o - Jun 11 2 0 - -R M 2085 o - Ap 22 3 -1 - -R M 2085 o - May 27 2 0 - -R M 2086 o - Ap 14 3 -1 - -R M 2086 o - May 19 2 0 - -R M 2087 o - Mar 30 3 -1 - -R M 2087 o - May 11 2 0 - -R NA 1994 o - Mar 21 0 -1 WAT -R NA 1994 2017 - S Su>=1 2 0 CAT -R NA 1995 2017 - Ap Su>=1 2 -1 WAT -R SA 1942 1943 - S Su>=15 2 1 - -R SA 1943 1944 - Mar Su>=15 2 0 - -R SD 1970 o - May 1 0 1 S -R SD 1970 1985 - O 15 0 0 - -R SD 1971 o - Ap 30 0 1 S -R SD 1972 1985 - Ap lastSu 0 1 S -R n 1939 o - Ap 15 23s 1 S -R n 1939 o - N 18 23s 0 - -R n 1940 o - F 25 23s 1 S -R n 1941 o - O 6 0 0 - -R n 1942 o - Mar 9 0 1 S -R n 1942 o - N 2 3 0 - -R n 1943 o - Mar 29 2 1 S -R n 1943 o - Ap 17 2 0 - -R n 1943 o - Ap 25 2 1 S -R n 1943 o - O 4 2 0 - -R n 1944 1945 - Ap M>=1 2 1 S -R n 1944 o - O 8 0 0 - -R n 1945 o - S 16 0 0 - -R n 1977 o - Ap 30 0s 1 S -R n 1977 o - S 24 0s 0 - -R n 1978 o - May 1 0s 1 S -R n 1978 o - O 1 0s 0 - -R n 1988 o - Jun 1 0s 1 S -R n 1988 1990 - S lastSu 0s 0 - -R n 1989 o - Mar 26 0s 1 S -R n 1990 o - May 1 0s 1 S -R n 2005 o - May 1 0s 1 S -R n 2005 o - S 30 1s 0 - -R n 2006 2008 - Mar lastSu 2s 1 S -R n 2006 2008 - O lastSu 2s 0 - -R Tr 2005 ma - Mar lastSu 1u 2 +02 -R Tr 2004 ma - O lastSu 1u 0 +00 -R AM 2011 o - Mar lastSu 2s 1 - -R AM 2011 o - O lastSu 2s 0 - -R AZ 1997 2015 - Mar lastSu 4 1 - -R AZ 1997 2015 - O lastSu 5 0 - -R BD 2009 o - Jun 19 23 1 - -R BD 2009 o - D 31 24 0 - -R Sh 1919 o - Ap 12 24 1 D -R Sh 1919 o - S 30 24 0 S -R Sh 1940 o - Jun 1 0 1 D -R Sh 1940 o - O 12 24 0 S -R Sh 1941 o - Mar 15 0 1 D -R Sh 1941 o - N 1 24 0 S -R Sh 1942 o - Ja 31 0 1 D -R Sh 1945 o - S 1 24 0 S -R Sh 1946 o - May 15 0 1 D -R Sh 1946 o - S 30 24 0 S -R Sh 1947 o - Ap 15 0 1 D -R Sh 1947 o - O 31 24 0 S -R Sh 1948 1949 - May 1 0 1 D -R Sh 1948 1949 - S 30 24 0 S -R CN 1986 o - May 4 2 1 D -R CN 1986 1991 - S Su>=11 2 0 S -R CN 1987 1991 - Ap Su>=11 2 1 D -R HK 1946 o - Ap 21 0 1 S -R HK 1946 o - D 1 3:30s 0 - -R HK 1947 o - Ap 13 3:30s 1 S -R HK 1947 o - N 30 3:30s 0 - -R HK 1948 o - May 2 3:30s 1 S -R HK 1948 1952 - O Su>=28 3:30s 0 - -R HK 1949 1953 - Ap Su>=1 3:30 1 S -R HK 1953 1964 - O Su>=31 3:30 0 - -R HK 1954 1964 - Mar Su>=18 3:30 1 S -R HK 1965 1976 - Ap Su>=16 3:30 1 S -R HK 1965 1976 - O Su>=16 3:30 0 - -R HK 1973 o - D 30 3:30 1 S -R HK 1979 o - May 13 3:30 1 S -R HK 1979 o - O 21 3:30 0 - -R f 1946 o - May 15 0 1 D -R f 1946 o - O 1 0 0 S -R f 1947 o - Ap 15 0 1 D -R f 1947 o - N 1 0 0 S -R f 1948 1951 - May 1 0 1 D -R f 1948 1951 - O 1 0 0 S -R f 1952 o - Mar 1 0 1 D -R f 1952 1954 - N 1 0 0 S -R f 1953 1959 - Ap 1 0 1 D -R f 1955 1961 - O 1 0 0 S -R f 1960 1961 - Jun 1 0 1 D -R f 1974 1975 - Ap 1 0 1 D -R f 1974 1975 - O 1 0 0 S -R f 1979 o - Jul 1 0 1 D -R f 1979 o - O 1 0 0 S -R _ 1942 1943 - Ap 30 23 1 - -R _ 1942 o - N 17 23 0 - -R _ 1943 o - S 30 23 0 S -R _ 1946 o - Ap 30 23s 1 D -R _ 1946 o - S 30 23s 0 S -R _ 1947 o - Ap 19 23s 1 D -R _ 1947 o - N 30 23s 0 S -R _ 1948 o - May 2 23s 1 D -R _ 1948 o - O 31 23s 0 S -R _ 1949 1950 - Ap Sa>=1 23s 1 D -R _ 1949 1950 - O lastSa 23s 0 S -R _ 1951 o - Mar 31 23s 1 D -R _ 1951 o - O 28 23s 0 S -R _ 1952 1953 - Ap Sa>=1 23s 1 D -R _ 1952 o - N 1 23s 0 S -R _ 1953 1954 - O lastSa 23s 0 S -R _ 1954 1956 - Mar Sa>=17 23s 1 D -R _ 1955 o - N 5 23s 0 S -R _ 1956 1964 - N Su>=1 3:30 0 S -R _ 1957 1964 - Mar Su>=18 3:30 1 D -R _ 1965 1973 - Ap Su>=16 3:30 1 D -R _ 1965 1966 - O Su>=16 2:30 0 S -R _ 1967 1976 - O Su>=16 3:30 0 S -R _ 1973 o - D 30 3:30 1 D -R _ 1975 1976 - Ap Su>=16 3:30 1 D -R _ 1979 o - May 13 3:30 1 D -R _ 1979 o - O Su>=16 3:30 0 S -R CY 1975 o - Ap 13 0 1 S -R CY 1975 o - O 12 0 0 - -R CY 1976 o - May 15 0 1 S -R CY 1976 o - O 11 0 0 - -R CY 1977 1980 - Ap Su>=1 0 1 S -R CY 1977 o - S 25 0 0 - -R CY 1978 o - O 2 0 0 - -R CY 1979 1997 - S lastSu 0 0 - -R CY 1981 1998 - Mar lastSu 0 1 S -R i 1910 o - Ja 1 0 0 - -R i 1977 o - Mar 21 23 1 - -R i 1977 o - O 20 24 0 - -R i 1978 o - Mar 24 24 1 - -R i 1978 o - Au 5 1 0 - -R i 1979 o - May 26 24 1 - -R i 1979 o - S 18 24 0 - -R i 1980 o - Mar 20 24 1 - -R i 1980 o - S 22 24 0 - -R i 1991 o - May 2 24 1 - -R i 1992 1995 - Mar 21 24 1 - -R i 1991 1995 - S 21 24 0 - -R i 1996 o - Mar 20 24 1 - -R i 1996 o - S 20 24 0 - -R i 1997 1999 - Mar 21 24 1 - -R i 1997 1999 - S 21 24 0 - -R i 2000 o - Mar 20 24 1 - -R i 2000 o - S 20 24 0 - -R i 2001 2003 - Mar 21 24 1 - -R i 2001 2003 - S 21 24 0 - -R i 2004 o - Mar 20 24 1 - -R i 2004 o - S 20 24 0 - -R i 2005 o - Mar 21 24 1 - -R i 2005 o - S 21 24 0 - -R i 2008 o - Mar 20 24 1 - -R i 2008 o - S 20 24 0 - -R i 2009 2011 - Mar 21 24 1 - -R i 2009 2011 - S 21 24 0 - -R i 2012 o - Mar 20 24 1 - -R i 2012 o - S 20 24 0 - -R i 2013 2015 - Mar 21 24 1 - -R i 2013 2015 - S 21 24 0 - -R i 2016 o - Mar 20 24 1 - -R i 2016 o - S 20 24 0 - -R i 2017 2019 - Mar 21 24 1 - -R i 2017 2019 - S 21 24 0 - -R i 2020 o - Mar 20 24 1 - -R i 2020 o - S 20 24 0 - -R i 2021 2022 - Mar 21 24 1 - -R i 2021 2022 - S 21 24 0 - -R IQ 1982 o - May 1 0 1 - -R IQ 1982 1984 - O 1 0 0 - -R IQ 1983 o - Mar 31 0 1 - -R IQ 1984 1985 - Ap 1 0 1 - -R IQ 1985 1990 - S lastSu 1s 0 - -R IQ 1986 1990 - Mar lastSu 1s 1 - -R IQ 1991 2007 - Ap 1 3s 1 - -R IQ 1991 2007 - O 1 3s 0 - -R Z 1940 o - May 31 24u 1 D -R Z 1940 o - S 30 24u 0 S -R Z 1940 o - N 16 24u 1 D -R Z 1942 1946 - O 31 24u 0 S -R Z 1943 1944 - Mar 31 24u 1 D -R Z 1945 1946 - Ap 15 24u 1 D -R Z 1948 o - May 22 24u 2 DD -R Z 1948 o - Au 31 24u 1 D -R Z 1948 1949 - O 31 24u 0 S -R Z 1949 o - Ap 30 24u 1 D -R Z 1950 o - Ap 15 24u 1 D -R Z 1950 o - S 14 24u 0 S -R Z 1951 o - Mar 31 24u 1 D -R Z 1951 o - N 10 24u 0 S -R Z 1952 o - Ap 19 24u 1 D -R Z 1952 o - O 18 24u 0 S -R Z 1953 o - Ap 11 24u 1 D -R Z 1953 o - S 12 24u 0 S -R Z 1954 o - Jun 12 24u 1 D -R Z 1954 o - S 11 24u 0 S -R Z 1955 o - Jun 11 24u 1 D -R Z 1955 o - S 10 24u 0 S -R Z 1956 o - Jun 2 24u 1 D -R Z 1956 o - S 29 24u 0 S -R Z 1957 o - Ap 27 24u 1 D -R Z 1957 o - S 21 24u 0 S -R Z 1974 o - Jul 6 24 1 D -R Z 1974 o - O 12 24 0 S -R Z 1975 o - Ap 19 24 1 D -R Z 1975 o - Au 30 24 0 S -R Z 1980 o - Au 2 24s 1 D -R Z 1980 o - S 13 24s 0 S -R Z 1984 o - May 5 24s 1 D -R Z 1984 o - Au 25 24s 0 S -R Z 1985 o - Ap 13 24 1 D -R Z 1985 o - Au 31 24 0 S -R Z 1986 o - May 17 24 1 D -R Z 1986 o - S 6 24 0 S -R Z 1987 o - Ap 14 24 1 D -R Z 1987 o - S 12 24 0 S -R Z 1988 o - Ap 9 24 1 D -R Z 1988 o - S 3 24 0 S -R Z 1989 o - Ap 29 24 1 D -R Z 1989 o - S 2 24 0 S -R Z 1990 o - Mar 24 24 1 D -R Z 1990 o - Au 25 24 0 S -R Z 1991 o - Mar 23 24 1 D -R Z 1991 o - Au 31 24 0 S -R Z 1992 o - Mar 28 24 1 D -R Z 1992 o - S 5 24 0 S -R Z 1993 o - Ap 2 0 1 D -R Z 1993 o - S 5 0 0 S -R Z 1994 o - Ap 1 0 1 D -R Z 1994 o - Au 28 0 0 S -R Z 1995 o - Mar 31 0 1 D -R Z 1995 o - S 3 0 0 S -R Z 1996 o - Mar 14 24 1 D -R Z 1996 o - S 15 24 0 S -R Z 1997 o - Mar 20 24 1 D -R Z 1997 o - S 13 24 0 S -R Z 1998 o - Mar 20 0 1 D -R Z 1998 o - S 6 0 0 S -R Z 1999 o - Ap 2 2 1 D -R Z 1999 o - S 3 2 0 S -R Z 2000 o - Ap 14 2 1 D -R Z 2000 o - O 6 1 0 S -R Z 2001 o - Ap 9 1 1 D -R Z 2001 o - S 24 1 0 S -R Z 2002 o - Mar 29 1 1 D -R Z 2002 o - O 7 1 0 S -R Z 2003 o - Mar 28 1 1 D -R Z 2003 o - O 3 1 0 S -R Z 2004 o - Ap 7 1 1 D -R Z 2004 o - S 22 1 0 S -R Z 2005 2012 - Ap F<=1 2 1 D -R Z 2005 o - O 9 2 0 S -R Z 2006 o - O 1 2 0 S -R Z 2007 o - S 16 2 0 S -R Z 2008 o - O 5 2 0 S -R Z 2009 o - S 27 2 0 S -R Z 2010 o - S 12 2 0 S -R Z 2011 o - O 2 2 0 S -R Z 2012 o - S 23 2 0 S -R Z 2013 ma - Mar F>=23 2 1 D -R Z 2013 ma - O lastSu 2 0 S -R JP 1948 o - May Sa>=1 24 1 D -R JP 1948 1951 - S Sa>=8 25 0 S -R JP 1949 o - Ap Sa>=1 24 1 D -R JP 1950 1951 - May Sa>=1 24 1 D -R J 1973 o - Jun 6 0 1 S -R J 1973 1975 - O 1 0 0 - -R J 1974 1977 - May 1 0 1 S -R J 1976 o - N 1 0 0 - -R J 1977 o - O 1 0 0 - -R J 1978 o - Ap 30 0 1 S -R J 1978 o - S 30 0 0 - -R J 1985 o - Ap 1 0 1 S -R J 1985 o - O 1 0 0 - -R J 1986 1988 - Ap F>=1 0 1 S -R J 1986 1990 - O F>=1 0 0 - -R J 1989 o - May 8 0 1 S -R J 1990 o - Ap 27 0 1 S -R J 1991 o - Ap 17 0 1 S -R J 1991 o - S 27 0 0 - -R J 1992 o - Ap 10 0 1 S -R J 1992 1993 - O F>=1 0 0 - -R J 1993 1998 - Ap F>=1 0 1 S -R J 1994 o - S F>=15 0 0 - -R J 1995 1998 - S F>=15 0s 0 - -R J 1999 o - Jul 1 0s 1 S -R J 1999 2002 - S lastF 0s 0 - -R J 2000 2001 - Mar lastTh 0s 1 S -R J 2002 2012 - Mar lastTh 24 1 S -R J 2003 o - O 24 0s 0 - -R J 2004 o - O 15 0s 0 - -R J 2005 o - S lastF 0s 0 - -R J 2006 2011 - O lastF 0s 0 - -R J 2013 o - D 20 0 0 - -R J 2014 2021 - Mar lastTh 24 1 S -R J 2014 2022 - O lastF 0s 0 - -R J 2022 o - F lastTh 24 1 S -R KG 1992 1996 - Ap Su>=7 0s 1 - -R KG 1992 1996 - S lastSu 0 0 - -R KG 1997 2005 - Mar lastSu 2:30 1 - -R KG 1997 2004 - O lastSu 2:30 0 - -R KR 1948 o - Jun 1 0 1 D -R KR 1948 o - S 12 24 0 S -R KR 1949 o - Ap 3 0 1 D -R KR 1949 1951 - S Sa>=7 24 0 S -R KR 1950 o - Ap 1 0 1 D -R KR 1951 o - May 6 0 1 D -R KR 1955 o - May 5 0 1 D -R KR 1955 o - S 8 24 0 S -R KR 1956 o - May 20 0 1 D -R KR 1956 o - S 29 24 0 S -R KR 1957 1960 - May Su>=1 0 1 D -R KR 1957 1960 - S Sa>=17 24 0 S -R KR 1987 1988 - May Su>=8 2 1 D -R KR 1987 1988 - O Su>=8 3 0 S -R l 1920 o - Mar 28 0 1 S -R l 1920 o - O 25 0 0 - -R l 1921 o - Ap 3 0 1 S -R l 1921 o - O 3 0 0 - -R l 1922 o - Mar 26 0 1 S -R l 1922 o - O 8 0 0 - -R l 1923 o - Ap 22 0 1 S -R l 1923 o - S 16 0 0 - -R l 1957 1961 - May 1 0 1 S -R l 1957 1961 - O 1 0 0 - -R l 1972 o - Jun 22 0 1 S -R l 1972 1977 - O 1 0 0 - -R l 1973 1977 - May 1 0 1 S -R l 1978 o - Ap 30 0 1 S -R l 1978 o - S 30 0 0 - -R l 1984 1987 - May 1 0 1 S -R l 1984 1991 - O 16 0 0 - -R l 1988 o - Jun 1 0 1 S -R l 1989 o - May 10 0 1 S -R l 1990 1992 - May 1 0 1 S -R l 1992 o - O 4 0 0 - -R l 1993 ma - Mar lastSu 0 1 S -R l 1993 1998 - S lastSu 0 0 - -R l 1999 ma - O lastSu 0 0 - -R NB 1935 1941 - S 14 0 0:20 - -R NB 1935 1941 - D 14 0 0 - -R X 1983 1984 - Ap 1 0 1 - -R X 1983 o - O 1 0 0 - -R X 1985 1998 - Mar lastSu 0 1 - -R X 1984 1998 - S lastSu 0 0 - -R X 2001 o - Ap lastSa 2 1 - -R X 2001 2006 - S lastSa 2 0 - -R X 2002 2006 - Mar lastSa 2 1 - -R X 2015 2016 - Mar lastSa 2 1 - -R X 2015 2016 - S lastSa 0 0 - -R PK 2002 o - Ap Su>=2 0 1 S -R PK 2002 o - O Su>=2 0 0 - -R PK 2008 o - Jun 1 0 1 S -R PK 2008 2009 - N 1 0 0 - -R PK 2009 o - Ap 15 0 1 S -R P 1999 2005 - Ap F>=15 0 1 S -R P 1999 2003 - O F>=15 0 0 - -R P 2004 o - O 1 1 0 - -R P 2005 o - O 4 2 0 - -R P 2006 2007 - Ap 1 0 1 S -R P 2006 o - S 22 0 0 - -R P 2007 o - S 13 2 0 - -R P 2008 2009 - Mar lastF 0 1 S -R P 2008 o - S 1 0 0 - -R P 2009 o - S 4 1 0 - -R P 2010 o - Mar 26 0 1 S -R P 2010 o - Au 11 0 0 - -R P 2011 o - Ap 1 0:1 1 S -R P 2011 o - Au 1 0 0 - -R P 2011 o - Au 30 0 1 S -R P 2011 o - S 30 0 0 - -R P 2012 2014 - Mar lastTh 24 1 S -R P 2012 o - S 21 1 0 - -R P 2013 o - S 27 0 0 - -R P 2014 o - O 24 0 0 - -R P 2015 o - Mar 28 0 1 S -R P 2015 o - O 23 1 0 - -R P 2016 2018 - Mar Sa<=30 1 1 S -R P 2016 2018 - O Sa<=30 1 0 - -R P 2019 o - Mar 29 0 1 S -R P 2019 o - O Sa<=30 0 0 - -R P 2020 2021 - Mar Sa<=30 0 1 S -R P 2020 o - O 24 1 0 - -R P 2021 o - O 29 1 0 - -R P 2022 o - Mar 27 0 1 S -R P 2022 2035 - O Sa<=30 2 0 - -R P 2023 o - Ap 29 2 1 S -R P 2024 o - Ap 20 2 1 S -R P 2025 o - Ap 12 2 1 S -R P 2026 2054 - Mar Sa<=30 2 1 S -R P 2036 o - O 18 2 0 - -R P 2037 o - O 10 2 0 - -R P 2038 o - S 25 2 0 - -R P 2039 o - S 17 2 0 - -R P 2040 o - S 1 2 0 - -R P 2040 o - O 20 2 1 S -R P 2040 2067 - O Sa<=30 2 0 - -R P 2041 o - Au 24 2 0 - -R P 2041 o - O 5 2 1 S -R P 2042 o - Au 16 2 0 - -R P 2042 o - S 27 2 1 S -R P 2043 o - Au 1 2 0 - -R P 2043 o - S 19 2 1 S -R P 2044 o - Jul 23 2 0 - -R P 2044 o - S 3 2 1 S -R P 2045 o - Jul 15 2 0 - -R P 2045 o - Au 26 2 1 S -R P 2046 o - Jun 30 2 0 - -R P 2046 o - Au 18 2 1 S -R P 2047 o - Jun 22 2 0 - -R P 2047 o - Au 3 2 1 S -R P 2048 o - Jun 6 2 0 - -R P 2048 o - Jul 25 2 1 S -R P 2049 o - May 29 2 0 - -R P 2049 o - Jul 10 2 1 S -R P 2050 o - May 21 2 0 - -R P 2050 o - Jul 2 2 1 S -R P 2051 o - May 6 2 0 - -R P 2051 o - Jun 24 2 1 S -R P 2052 o - Ap 27 2 0 - -R P 2052 o - Jun 8 2 1 S -R P 2053 o - Ap 12 2 0 - -R P 2053 o - May 31 2 1 S -R P 2054 o - Ap 4 2 0 - -R P 2054 o - May 23 2 1 S -R P 2055 o - May 8 2 1 S -R P 2056 o - Ap 29 2 1 S -R P 2057 o - Ap 14 2 1 S -R P 2058 o - Ap 6 2 1 S -R P 2059 ma - Mar Sa<=30 2 1 S -R P 2068 o - O 20 2 0 - -R P 2069 o - O 12 2 0 - -R P 2070 o - O 4 2 0 - -R P 2071 o - S 19 2 0 - -R P 2072 o - S 10 2 0 - -R P 2072 o - O 22 2 1 S -R P 2072 ma - O Sa<=30 2 0 - -R P 2073 o - S 2 2 0 - -R P 2073 o - O 14 2 1 S -R P 2074 o - Au 18 2 0 - -R P 2074 o - O 6 2 1 S -R P 2075 o - Au 10 2 0 - -R P 2075 o - S 21 2 1 S -R P 2076 o - Jul 25 2 0 - -R P 2076 o - S 12 2 1 S -R P 2077 o - Jul 17 2 0 - -R P 2077 o - S 4 2 1 S -R P 2078 o - Jul 9 2 0 - -R P 2078 o - Au 20 2 1 S -R P 2079 o - Jun 24 2 0 - -R P 2079 o - Au 12 2 1 S -R P 2080 o - Jun 15 2 0 - -R P 2080 o - Jul 27 2 1 S -R P 2081 o - Jun 7 2 0 - -R P 2081 o - Jul 19 2 1 S -R P 2082 o - May 23 2 0 - -R P 2082 o - Jul 11 2 1 S -R P 2083 o - May 15 2 0 - -R P 2083 o - Jun 26 2 1 S -R P 2084 o - Ap 29 2 0 - -R P 2084 o - Jun 17 2 1 S -R P 2085 o - Ap 21 2 0 - -R P 2085 o - Jun 9 2 1 S -R P 2086 o - Ap 13 2 0 - -R P 2086 o - May 25 2 1 S -R PH 1936 o - O 31 24 1 D -R PH 1937 o - Ja 15 24 0 S -R PH 1941 o - D 15 24 1 D -R PH 1945 o - N 30 24 0 S -R PH 1954 o - Ap 11 24 1 D -R PH 1954 o - Jun 4 24 0 S -R PH 1977 o - Mar 27 24 1 D -R PH 1977 o - S 21 24 0 S -R PH 1990 o - May 21 0 1 D -R PH 1990 o - Jul 28 24 0 S -R S 1920 1923 - Ap Su>=15 2 1 S -R S 1920 1923 - O Su>=1 2 0 - -R S 1962 o - Ap 29 2 1 S -R S 1962 o - O 1 2 0 - -R S 1963 1965 - May 1 2 1 S -R S 1963 o - S 30 2 0 - -R S 1964 o - O 1 2 0 - -R S 1965 o - S 30 2 0 - -R S 1966 o - Ap 24 2 1 S -R S 1966 1976 - O 1 2 0 - -R S 1967 1978 - May 1 2 1 S -R S 1977 1978 - S 1 2 0 - -R S 1983 1984 - Ap 9 2 1 S -R S 1983 1984 - O 1 2 0 - -R S 1986 o - F 16 2 1 S -R S 1986 o - O 9 2 0 - -R S 1987 o - Mar 1 2 1 S -R S 1987 1988 - O 31 2 0 - -R S 1988 o - Mar 15 2 1 S -R S 1989 o - Mar 31 2 1 S -R S 1989 o - O 1 2 0 - -R S 1990 o - Ap 1 2 1 S -R S 1990 o - S 30 2 0 - -R S 1991 o - Ap 1 0 1 S -R S 1991 1992 - O 1 0 0 - -R S 1992 o - Ap 8 0 1 S -R S 1993 o - Mar 26 0 1 S -R S 1993 o - S 25 0 0 - -R S 1994 1996 - Ap 1 0 1 S -R S 1994 2005 - O 1 0 0 - -R S 1997 1998 - Mar lastM 0 1 S -R S 1999 2006 - Ap 1 0 1 S -R S 2006 o - S 22 0 0 - -R S 2007 o - Mar lastF 0 1 S -R S 2007 o - N F>=1 0 0 - -R S 2008 o - Ap F>=1 0 1 S -R S 2008 o - N 1 0 0 - -R S 2009 o - Mar lastF 0 1 S -R S 2010 2011 - Ap F>=1 0 1 S -R S 2012 2022 - Mar lastF 0 1 S -R S 2009 2022 - O lastF 0 0 - -R AU 1917 o - Ja 1 2s 1 D -R AU 1917 o - Mar lastSu 2s 0 S -R AU 1942 o - Ja 1 2s 1 D -R AU 1942 o - Mar lastSu 2s 0 S -R AU 1942 o - S 27 2s 1 D -R AU 1943 1944 - Mar lastSu 2s 0 S -R AU 1943 o - O 3 2s 1 D -R AW 1974 o - O lastSu 2s 1 D -R AW 1975 o - Mar Su>=1 2s 0 S -R AW 1983 o - O lastSu 2s 1 D -R AW 1984 o - Mar Su>=1 2s 0 S -R AW 1991 o - N 17 2s 1 D -R AW 1992 o - Mar Su>=1 2s 0 S -R AW 2006 o - D 3 2s 1 D -R AW 2007 2009 - Mar lastSu 2s 0 S -R AW 2007 2008 - O lastSu 2s 1 D -R AQ 1971 o - O lastSu 2s 1 D -R AQ 1972 o - F lastSu 2s 0 S -R AQ 1989 1991 - O lastSu 2s 1 D -R AQ 1990 1992 - Mar Su>=1 2s 0 S -R Ho 1992 1993 - O lastSu 2s 1 D -R Ho 1993 1994 - Mar Su>=1 2s 0 S -R AS 1971 1985 - O lastSu 2s 1 D -R AS 1986 o - O 19 2s 1 D -R AS 1987 2007 - O lastSu 2s 1 D -R AS 1972 o - F 27 2s 0 S -R AS 1973 1985 - Mar Su>=1 2s 0 S -R AS 1986 1990 - Mar Su>=15 2s 0 S -R AS 1991 o - Mar 3 2s 0 S -R AS 1992 o - Mar 22 2s 0 S -R AS 1993 o - Mar 7 2s 0 S -R AS 1994 o - Mar 20 2s 0 S -R AS 1995 2005 - Mar lastSu 2s 0 S -R AS 2006 o - Ap 2 2s 0 S -R AS 2007 o - Mar lastSu 2s 0 S -R AS 2008 ma - Ap Su>=1 2s 0 S -R AS 2008 ma - O Su>=1 2s 1 D -R AT 1916 o - O Su>=1 2s 1 D -R AT 1917 o - Mar lastSu 2s 0 S -R AT 1917 1918 - O Su>=22 2s 1 D -R AT 1918 1919 - Mar Su>=1 2s 0 S -R AT 1967 o - O Su>=1 2s 1 D -R AT 1968 o - Mar Su>=29 2s 0 S -R AT 1968 1985 - O lastSu 2s 1 D -R AT 1969 1971 - Mar Su>=8 2s 0 S -R AT 1972 o - F lastSu 2s 0 S -R AT 1973 1981 - Mar Su>=1 2s 0 S -R AT 1982 1983 - Mar lastSu 2s 0 S -R AT 1984 1986 - Mar Su>=1 2s 0 S -R AT 1986 o - O Su>=15 2s 1 D -R AT 1987 1990 - Mar Su>=15 2s 0 S -R AT 1987 o - O Su>=22 2s 1 D -R AT 1988 1990 - O lastSu 2s 1 D -R AT 1991 1999 - O Su>=1 2s 1 D -R AT 1991 2005 - Mar lastSu 2s 0 S -R AT 2000 o - Au lastSu 2s 1 D -R AT 2001 ma - O Su>=1 2s 1 D -R AT 2006 o - Ap Su>=1 2s 0 S -R AT 2007 o - Mar lastSu 2s 0 S -R AT 2008 ma - Ap Su>=1 2s 0 S -R AV 1971 1985 - O lastSu 2s 1 D -R AV 1972 o - F lastSu 2s 0 S -R AV 1973 1985 - Mar Su>=1 2s 0 S -R AV 1986 1990 - Mar Su>=15 2s 0 S -R AV 1986 1987 - O Su>=15 2s 1 D -R AV 1988 1999 - O lastSu 2s 1 D -R AV 1991 1994 - Mar Su>=1 2s 0 S -R AV 1995 2005 - Mar lastSu 2s 0 S -R AV 2000 o - Au lastSu 2s 1 D -R AV 2001 2007 - O lastSu 2s 1 D -R AV 2006 o - Ap Su>=1 2s 0 S -R AV 2007 o - Mar lastSu 2s 0 S -R AV 2008 ma - Ap Su>=1 2s 0 S -R AV 2008 ma - O Su>=1 2s 1 D -R AN 1971 1985 - O lastSu 2s 1 D -R AN 1972 o - F 27 2s 0 S -R AN 1973 1981 - Mar Su>=1 2s 0 S -R AN 1982 o - Ap Su>=1 2s 0 S -R AN 1983 1985 - Mar Su>=1 2s 0 S -R AN 1986 1989 - Mar Su>=15 2s 0 S -R AN 1986 o - O 19 2s 1 D -R AN 1987 1999 - O lastSu 2s 1 D -R AN 1990 1995 - Mar Su>=1 2s 0 S -R AN 1996 2005 - Mar lastSu 2s 0 S -R AN 2000 o - Au lastSu 2s 1 D -R AN 2001 2007 - O lastSu 2s 1 D -R AN 2006 o - Ap Su>=1 2s 0 S -R AN 2007 o - Mar lastSu 2s 0 S -R AN 2008 ma - Ap Su>=1 2s 0 S -R AN 2008 ma - O Su>=1 2s 1 D -R LH 1981 1984 - O lastSu 2 1 - -R LH 1982 1985 - Mar Su>=1 2 0 - -R LH 1985 o - O lastSu 2 0:30 - -R LH 1986 1989 - Mar Su>=15 2 0 - -R LH 1986 o - O 19 2 0:30 - -R LH 1987 1999 - O lastSu 2 0:30 - -R LH 1990 1995 - Mar Su>=1 2 0 - -R LH 1996 2005 - Mar lastSu 2 0 - -R LH 2000 o - Au lastSu 2 0:30 - -R LH 2001 2007 - O lastSu 2 0:30 - -R LH 2006 o - Ap Su>=1 2 0 - -R LH 2007 o - Mar lastSu 2 0 - -R LH 2008 ma - Ap Su>=1 2 0 - -R LH 2008 ma - O Su>=1 2 0:30 - -R FJ 1998 1999 - N Su>=1 2 1 - -R FJ 1999 2000 - F lastSu 3 0 - -R FJ 2009 o - N 29 2 1 - -R FJ 2010 o - Mar lastSu 3 0 - -R FJ 2010 2013 - O Su>=21 2 1 - -R FJ 2011 o - Mar Su>=1 3 0 - -R FJ 2012 2013 - Ja Su>=18 3 0 - -R FJ 2014 o - Ja Su>=18 2 0 - -R FJ 2014 2018 - N Su>=1 2 1 - -R FJ 2015 2021 - Ja Su>=12 3 0 - -R FJ 2019 o - N Su>=8 2 1 - -R FJ 2020 o - D 20 2 1 - -R Gu 1959 o - Jun 27 2 1 D -R Gu 1961 o - Ja 29 2 0 S -R Gu 1967 o - S 1 2 1 D -R Gu 1969 o - Ja 26 0:1 0 S -R Gu 1969 o - Jun 22 2 1 D -R Gu 1969 o - Au 31 2 0 S -R Gu 1970 1971 - Ap lastSu 2 1 D -R Gu 1970 1971 - S Su>=1 2 0 S -R Gu 1973 o - D 16 2 1 D -R Gu 1974 o - F 24 2 0 S -R Gu 1976 o - May 26 2 1 D -R Gu 1976 o - Au 22 2:1 0 S -R Gu 1977 o - Ap 24 2 1 D -R Gu 1977 o - Au 28 2 0 S -R NC 1977 1978 - D Su>=1 0 1 - -R NC 1978 1979 - F 27 0 0 - -R NC 1996 o - D 1 2s 1 - -R NC 1997 o - Mar 2 2s 0 - -R NZ 1927 o - N 6 2 1 S -R NZ 1928 o - Mar 4 2 0 M -R NZ 1928 1933 - O Su>=8 2 0:30 S -R NZ 1929 1933 - Mar Su>=15 2 0 M -R NZ 1934 1940 - Ap lastSu 2 0 M -R NZ 1934 1940 - S lastSu 2 0:30 S -R NZ 1946 o - Ja 1 0 0 S -R NZ 1974 o - N Su>=1 2s 1 D -R k 1974 o - N Su>=1 2:45s 1 - -R NZ 1975 o - F lastSu 2s 0 S -R k 1975 o - F lastSu 2:45s 0 - -R NZ 1975 1988 - O lastSu 2s 1 D -R k 1975 1988 - O lastSu 2:45s 1 - -R NZ 1976 1989 - Mar Su>=1 2s 0 S -R k 1976 1989 - Mar Su>=1 2:45s 0 - -R NZ 1989 o - O Su>=8 2s 1 D -R k 1989 o - O Su>=8 2:45s 1 - -R NZ 1990 2006 - O Su>=1 2s 1 D -R k 1990 2006 - O Su>=1 2:45s 1 - -R NZ 1990 2007 - Mar Su>=15 2s 0 S -R k 1990 2007 - Mar Su>=15 2:45s 0 - -R NZ 2007 ma - S lastSu 2s 1 D -R k 2007 ma - S lastSu 2:45s 1 - -R NZ 2008 ma - Ap Su>=1 2s 0 S -R k 2008 ma - Ap Su>=1 2:45s 0 - -R CK 1978 o - N 12 0 0:30 - -R CK 1979 1991 - Mar Su>=1 0 0 - -R CK 1979 1990 - O lastSu 0 0:30 - -R WS 2010 o - S lastSu 0 1 - -R WS 2011 o - Ap Sa>=1 4 0 - -R WS 2011 o - S lastSa 3 1 - -R WS 2012 2021 - Ap Su>=1 4 0 - -R WS 2012 2020 - S lastSu 3 1 - -R TO 1999 o - O 7 2s 1 - -R TO 2000 o - Mar 19 2s 0 - -R TO 2000 2001 - N Su>=1 2 1 - -R TO 2001 2002 - Ja lastSu 2 0 - -R TO 2016 o - N Su>=1 2 1 - -R TO 2017 o - Ja Su>=15 3 0 - -R VU 1973 o - D 22 12u 1 - -R VU 1974 o - Mar 30 12u 0 - -R VU 1983 1991 - S Sa>=22 24 1 - -R VU 1984 1991 - Mar Sa>=22 24 0 - -R VU 1992 1993 - Ja Sa>=22 24 0 - -R VU 1992 o - O Sa>=22 24 1 - -R G 1916 o - May 21 2s 1 BST -R G 1916 o - O 1 2s 0 GMT -R G 1917 o - Ap 8 2s 1 BST -R G 1917 o - S 17 2s 0 GMT -R G 1918 o - Mar 24 2s 1 BST -R G 1918 o - S 30 2s 0 GMT -R G 1919 o - Mar 30 2s 1 BST -R G 1919 o - S 29 2s 0 GMT -R G 1920 o - Mar 28 2s 1 BST -R G 1920 o - O 25 2s 0 GMT -R G 1921 o - Ap 3 2s 1 BST -R G 1921 o - O 3 2s 0 GMT -R G 1922 o - Mar 26 2s 1 BST -R G 1922 o - O 8 2s 0 GMT -R G 1923 o - Ap Su>=16 2s 1 BST -R G 1923 1924 - S Su>=16 2s 0 GMT -R G 1924 o - Ap Su>=9 2s 1 BST -R G 1925 1926 - Ap Su>=16 2s 1 BST -R G 1925 1938 - O Su>=2 2s 0 GMT -R G 1927 o - Ap Su>=9 2s 1 BST -R G 1928 1929 - Ap Su>=16 2s 1 BST -R G 1930 o - Ap Su>=9 2s 1 BST -R G 1931 1932 - Ap Su>=16 2s 1 BST -R G 1933 o - Ap Su>=9 2s 1 BST -R G 1934 o - Ap Su>=16 2s 1 BST -R G 1935 o - Ap Su>=9 2s 1 BST -R G 1936 1937 - Ap Su>=16 2s 1 BST -R G 1938 o - Ap Su>=9 2s 1 BST -R G 1939 o - Ap Su>=16 2s 1 BST -R G 1939 o - N Su>=16 2s 0 GMT -R G 1940 o - F Su>=23 2s 1 BST -R G 1941 o - May Su>=2 1s 2 BDST -R G 1941 1943 - Au Su>=9 1s 1 BST -R G 1942 1944 - Ap Su>=2 1s 2 BDST -R G 1944 o - S Su>=16 1s 1 BST -R G 1945 o - Ap M>=2 1s 2 BDST -R G 1945 o - Jul Su>=9 1s 1 BST -R G 1945 1946 - O Su>=2 2s 0 GMT -R G 1946 o - Ap Su>=9 2s 1 BST -R G 1947 o - Mar 16 2s 1 BST -R G 1947 o - Ap 13 1s 2 BDST -R G 1947 o - Au 10 1s 1 BST -R G 1947 o - N 2 2s 0 GMT -R G 1948 o - Mar 14 2s 1 BST -R G 1948 o - O 31 2s 0 GMT -R G 1949 o - Ap 3 2s 1 BST -R G 1949 o - O 30 2s 0 GMT -R G 1950 1952 - Ap Su>=14 2s 1 BST -R G 1950 1952 - O Su>=21 2s 0 GMT -R G 1953 o - Ap Su>=16 2s 1 BST -R G 1953 1960 - O Su>=2 2s 0 GMT -R G 1954 o - Ap Su>=9 2s 1 BST -R G 1955 1956 - Ap Su>=16 2s 1 BST -R G 1957 o - Ap Su>=9 2s 1 BST -R G 1958 1959 - Ap Su>=16 2s 1 BST -R G 1960 o - Ap Su>=9 2s 1 BST -R G 1961 1963 - Mar lastSu 2s 1 BST -R G 1961 1968 - O Su>=23 2s 0 GMT -R G 1964 1967 - Mar Su>=19 2s 1 BST -R G 1968 o - F 18 2s 1 BST -R G 1972 1980 - Mar Su>=16 2s 1 BST -R G 1972 1980 - O Su>=23 2s 0 GMT -R G 1981 1995 - Mar lastSu 1u 1 BST -R G 1981 1989 - O Su>=23 1u 0 GMT -R G 1990 1995 - O Su>=22 1u 0 GMT -R IE 1971 o - O 31 2u -1 - -R IE 1972 1980 - Mar Su>=16 2u 0 - -R IE 1972 1980 - O Su>=23 2u -1 - -R IE 1981 ma - Mar lastSu 1u 0 - -R IE 1981 1989 - O Su>=23 1u -1 - -R IE 1990 1995 - O Su>=22 1u -1 - -R IE 1996 ma - O lastSu 1u -1 - -R E 1977 1980 - Ap Su>=1 1u 1 S -R E 1977 o - S lastSu 1u 0 - -R E 1978 o - O 1 1u 0 - -R E 1979 1995 - S lastSu 1u 0 - -R E 1981 ma - Mar lastSu 1u 1 S -R E 1996 ma - O lastSu 1u 0 - -R W- 1977 1980 - Ap Su>=1 1s 1 S -R W- 1977 o - S lastSu 1s 0 - -R W- 1978 o - O 1 1s 0 - -R W- 1979 1995 - S lastSu 1s 0 - -R W- 1981 ma - Mar lastSu 1s 1 S -R W- 1996 ma - O lastSu 1s 0 - -R c 1916 o - Ap 30 23 1 S -R c 1916 o - O 1 1 0 - -R c 1917 1918 - Ap M>=15 2s 1 S -R c 1917 1918 - S M>=15 2s 0 - -R c 1940 o - Ap 1 2s 1 S -R c 1942 o - N 2 2s 0 - -R c 1943 o - Mar 29 2s 1 S -R c 1943 o - O 4 2s 0 - -R c 1944 1945 - Ap M>=1 2s 1 S -R c 1944 o - O 2 2s 0 - -R c 1945 o - S 16 2s 0 - -R c 1977 1980 - Ap Su>=1 2s 1 S -R c 1977 o - S lastSu 2s 0 - -R c 1978 o - O 1 2s 0 - -R c 1979 1995 - S lastSu 2s 0 - -R c 1981 ma - Mar lastSu 2s 1 S -R c 1996 ma - O lastSu 2s 0 - -R e 1977 1980 - Ap Su>=1 0 1 S -R e 1977 o - S lastSu 0 0 - -R e 1978 o - O 1 0 0 - -R e 1979 1995 - S lastSu 0 0 - -R e 1981 ma - Mar lastSu 0 1 S -R e 1996 ma - O lastSu 0 0 - -R R 1917 o - Jul 1 23 1 MST -R R 1917 o - D 28 0 0 MMT -R R 1918 o - May 31 22 2 MDST -R R 1918 o - S 16 1 1 MST -R R 1919 o - May 31 23 2 MDST -R R 1919 o - Jul 1 0u 1 MSD -R R 1919 o - Au 16 0 0 MSK -R R 1921 o - F 14 23 1 MSD -R R 1921 o - Mar 20 23 2 +05 -R R 1921 o - S 1 0 1 MSD -R R 1921 o - O 1 0 0 - -R R 1981 1984 - Ap 1 0 1 S -R R 1981 1983 - O 1 0 0 - -R R 1984 1995 - S lastSu 2s 0 - -R R 1985 2010 - Mar lastSu 2s 1 S -R R 1996 2010 - O lastSu 2s 0 - -R q 1940 o - Jun 16 0 1 S -R q 1942 o - N 2 3 0 - -R q 1943 o - Mar 29 2 1 S -R q 1943 o - Ap 10 3 0 - -R q 1974 o - May 4 0 1 S -R q 1974 o - O 2 0 0 - -R q 1975 o - May 1 0 1 S -R q 1975 o - O 2 0 0 - -R q 1976 o - May 2 0 1 S -R q 1976 o - O 3 0 0 - -R q 1977 o - May 8 0 1 S -R q 1977 o - O 2 0 0 - -R q 1978 o - May 6 0 1 S -R q 1978 o - O 1 0 0 - -R q 1979 o - May 5 0 1 S -R q 1979 o - S 30 0 0 - -R q 1980 o - May 3 0 1 S -R q 1980 o - O 4 0 0 - -R q 1981 o - Ap 26 0 1 S -R q 1981 o - S 27 0 0 - -R q 1982 o - May 2 0 1 S -R q 1982 o - O 3 0 0 - -R q 1983 o - Ap 18 0 1 S -R q 1983 o - O 1 0 0 - -R q 1984 o - Ap 1 0 1 S -R a 1920 o - Ap 5 2s 1 S -R a 1920 o - S 13 2s 0 - -R a 1946 o - Ap 14 2s 1 S -R a 1946 o - O 7 2s 0 - -R a 1947 1948 - O Su>=1 2s 0 - -R a 1947 o - Ap 6 2s 1 S -R a 1948 o - Ap 18 2s 1 S -R a 1980 o - Ap 6 0 1 S -R a 1980 o - S 28 0 0 - -R b 1918 o - Mar 9 0s 1 S -R b 1918 1919 - O Sa>=1 23s 0 - -R b 1919 o - Mar 1 23s 1 S -R b 1920 o - F 14 23s 1 S -R b 1920 o - O 23 23s 0 - -R b 1921 o - Mar 14 23s 1 S -R b 1921 o - O 25 23s 0 - -R b 1922 o - Mar 25 23s 1 S -R b 1922 1927 - O Sa>=1 23s 0 - -R b 1923 o - Ap 21 23s 1 S -R b 1924 o - Mar 29 23s 1 S -R b 1925 o - Ap 4 23s 1 S -R b 1926 o - Ap 17 23s 1 S -R b 1927 o - Ap 9 23s 1 S -R b 1928 o - Ap 14 23s 1 S -R b 1928 1938 - O Su>=2 2s 0 - -R b 1929 o - Ap 21 2s 1 S -R b 1930 o - Ap 13 2s 1 S -R b 1931 o - Ap 19 2s 1 S -R b 1932 o - Ap 3 2s 1 S -R b 1933 o - Mar 26 2s 1 S -R b 1934 o - Ap 8 2s 1 S -R b 1935 o - Mar 31 2s 1 S -R b 1936 o - Ap 19 2s 1 S -R b 1937 o - Ap 4 2s 1 S -R b 1938 o - Mar 27 2s 1 S -R b 1939 o - Ap 16 2s 1 S -R b 1939 o - N 19 2s 0 - -R b 1940 o - F 25 2s 1 S -R b 1944 o - S 17 2s 0 - -R b 1945 o - Ap 2 2s 1 S -R b 1945 o - S 16 2s 0 - -R b 1946 o - May 19 2s 1 S -R b 1946 o - O 7 2s 0 - -R BG 1979 o - Mar 31 23 1 S -R BG 1979 o - O 1 1 0 - -R BG 1980 1982 - Ap Sa>=1 23 1 S -R BG 1980 o - S 29 1 0 - -R BG 1981 o - S 27 2 0 - -R CZ 1945 o - Ap M>=1 2s 1 S -R CZ 1945 o - O 1 2s 0 - -R CZ 1946 o - May 6 2s 1 S -R CZ 1946 1949 - O Su>=1 2s 0 - -R CZ 1947 1948 - Ap Su>=15 2s 1 S -R CZ 1949 o - Ap 9 2s 1 S -R Th 1991 1992 - Mar lastSu 2 1 D -R Th 1991 1992 - S lastSu 2 0 S -R Th 1993 2006 - Ap Su>=1 2 1 D -R Th 1993 2006 - O lastSu 2 0 S -R Th 2007 ma - Mar Su>=8 2 1 D -R Th 2007 ma - N Su>=1 2 0 S -R FI 1942 o - Ap 2 24 1 S -R FI 1942 o - O 4 1 0 - -R FI 1981 1982 - Mar lastSu 2 1 S -R FI 1981 1982 - S lastSu 3 0 - -R F 1916 o - Jun 14 23s 1 S -R F 1916 1919 - O Su>=1 23s 0 - -R F 1917 o - Mar 24 23s 1 S -R F 1918 o - Mar 9 23s 1 S -R F 1919 o - Mar 1 23s 1 S -R F 1920 o - F 14 23s 1 S -R F 1920 o - O 23 23s 0 - -R F 1921 o - Mar 14 23s 1 S -R F 1921 o - O 25 23s 0 - -R F 1922 o - Mar 25 23s 1 S -R F 1922 1938 - O Sa>=1 23s 0 - -R F 1923 o - May 26 23s 1 S -R F 1924 o - Mar 29 23s 1 S -R F 1925 o - Ap 4 23s 1 S -R F 1926 o - Ap 17 23s 1 S -R F 1927 o - Ap 9 23s 1 S -R F 1928 o - Ap 14 23s 1 S -R F 1929 o - Ap 20 23s 1 S -R F 1930 o - Ap 12 23s 1 S -R F 1931 o - Ap 18 23s 1 S -R F 1932 o - Ap 2 23s 1 S -R F 1933 o - Mar 25 23s 1 S -R F 1934 o - Ap 7 23s 1 S -R F 1935 o - Mar 30 23s 1 S -R F 1936 o - Ap 18 23s 1 S -R F 1937 o - Ap 3 23s 1 S -R F 1938 o - Mar 26 23s 1 S -R F 1939 o - Ap 15 23s 1 S -R F 1939 o - N 18 23s 0 - -R F 1940 o - F 25 2 1 S -R F 1941 o - May 5 0 2 M -R F 1941 o - O 6 0 1 S -R F 1942 o - Mar 9 0 2 M -R F 1942 o - N 2 3 1 S -R F 1943 o - Mar 29 2 2 M -R F 1943 o - O 4 3 1 S -R F 1944 o - Ap 3 2 2 M -R F 1944 o - O 8 1 1 S -R F 1945 o - Ap 2 2 2 M -R F 1945 o - S 16 3 0 - -R F 1976 o - Mar 28 1 1 S -R F 1976 o - S 26 1 0 - -R DE 1946 o - Ap 14 2s 1 S -R DE 1946 o - O 7 2s 0 - -R DE 1947 1949 - O Su>=1 2s 0 - -R DE 1947 o - Ap 6 3s 1 S -R DE 1947 o - May 11 2s 2 M -R DE 1947 o - Jun 29 3 1 S -R DE 1948 o - Ap 18 2s 1 S -R DE 1949 o - Ap 10 2s 1 S -R So 1945 o - May 24 2 2 M -R So 1945 o - S 24 3 1 S -R So 1945 o - N 18 2s 0 - -R g 1932 o - Jul 7 0 1 S -R g 1932 o - S 1 0 0 - -R g 1941 o - Ap 7 0 1 S -R g 1942 o - N 2 3 0 - -R g 1943 o - Mar 30 0 1 S -R g 1943 o - O 4 0 0 - -R g 1952 o - Jul 1 0 1 S -R g 1952 o - N 2 0 0 - -R g 1975 o - Ap 12 0s 1 S -R g 1975 o - N 26 0s 0 - -R g 1976 o - Ap 11 2s 1 S -R g 1976 o - O 10 2s 0 - -R g 1977 1978 - Ap Su>=1 2s 1 S -R g 1977 o - S 26 2s 0 - -R g 1978 o - S 24 4 0 - -R g 1979 o - Ap 1 9 1 S -R g 1979 o - S 29 2 0 - -R g 1980 o - Ap 1 0 1 S -R g 1980 o - S 28 0 0 - -R h 1918 1919 - Ap 15 2 1 S -R h 1918 1920 - S M>=15 3 0 - -R h 1920 o - Ap 5 2 1 S -R h 1945 o - May 1 23 1 S -R h 1945 o - N 1 1 0 - -R h 1946 o - Mar 31 2s 1 S -R h 1946 o - O 7 2 0 - -R h 1947 1949 - Ap Su>=4 2s 1 S -R h 1947 1949 - O Su>=1 2s 0 - -R h 1954 o - May 23 0 1 S -R h 1954 o - O 3 0 0 - -R h 1955 o - May 22 2 1 S -R h 1955 o - O 2 3 0 - -R h 1956 1957 - Jun Su>=1 2 1 S -R h 1956 1957 - S lastSu 3 0 - -R h 1980 o - Ap 6 0 1 S -R h 1980 o - S 28 1 0 - -R h 1981 1983 - Mar lastSu 0 1 S -R h 1981 1983 - S lastSu 1 0 - -R I 1916 o - Jun 3 24 1 S -R I 1916 1917 - S 30 24 0 - -R I 1917 o - Mar 31 24 1 S -R I 1918 o - Mar 9 24 1 S -R I 1918 o - O 6 24 0 - -R I 1919 o - Mar 1 24 1 S -R I 1919 o - O 4 24 0 - -R I 1920 o - Mar 20 24 1 S -R I 1920 o - S 18 24 0 - -R I 1940 o - Jun 14 24 1 S -R I 1942 o - N 2 2s 0 - -R I 1943 o - Mar 29 2s 1 S -R I 1943 o - O 4 2s 0 - -R I 1944 o - Ap 2 2s 1 S -R I 1944 o - S 17 2s 0 - -R I 1945 o - Ap 2 2 1 S -R I 1945 o - S 15 1 0 - -R I 1946 o - Mar 17 2s 1 S -R I 1946 o - O 6 2s 0 - -R I 1947 o - Mar 16 0s 1 S -R I 1947 o - O 5 0s 0 - -R I 1948 o - F 29 2s 1 S -R I 1948 o - O 3 2s 0 - -R I 1966 1968 - May Su>=22 0s 1 S -R I 1966 o - S 24 24 0 - -R I 1967 1969 - S Su>=22 0s 0 - -R I 1969 o - Jun 1 0s 1 S -R I 1970 o - May 31 0s 1 S -R I 1970 o - S lastSu 0s 0 - -R I 1971 1972 - May Su>=22 0s 1 S -R I 1971 o - S lastSu 0s 0 - -R I 1972 o - O 1 0s 0 - -R I 1973 o - Jun 3 0s 1 S -R I 1973 1974 - S lastSu 0s 0 - -R I 1974 o - May 26 0s 1 S -R I 1975 o - Jun 1 0s 1 S -R I 1975 1977 - S lastSu 0s 0 - -R I 1976 o - May 30 0s 1 S -R I 1977 1979 - May Su>=22 0s 1 S -R I 1978 o - O 1 0s 0 - -R I 1979 o - S 30 0s 0 - -R LV 1989 1996 - Mar lastSu 2s 1 S -R LV 1989 1996 - S lastSu 2s 0 - -R MT 1973 o - Mar 31 0s 1 S -R MT 1973 o - S 29 0s 0 - -R MT 1974 o - Ap 21 0s 1 S -R MT 1974 o - S 16 0s 0 - -R MT 1975 1979 - Ap Su>=15 2 1 S -R MT 1975 1980 - S Su>=15 2 0 - -R MT 1980 o - Mar 31 2 1 S -R MD 1997 ma - Mar lastSu 2 1 S -R MD 1997 ma - O lastSu 3 0 - -R O 1918 1919 - S 16 2s 0 - -R O 1919 o - Ap 15 2s 1 S -R O 1944 o - Ap 3 2s 1 S -R O 1944 o - O 4 2 0 - -R O 1945 o - Ap 29 0 1 S -R O 1945 o - N 1 0 0 - -R O 1946 o - Ap 14 0s 1 S -R O 1946 o - O 7 2s 0 - -R O 1947 o - May 4 2s 1 S -R O 1947 1949 - O Su>=1 2s 0 - -R O 1948 o - Ap 18 2s 1 S -R O 1949 o - Ap 10 2s 1 S -R O 1957 o - Jun 2 1s 1 S -R O 1957 1958 - S lastSu 1s 0 - -R O 1958 o - Mar 30 1s 1 S -R O 1959 o - May 31 1s 1 S -R O 1959 1961 - O Su>=1 1s 0 - -R O 1960 o - Ap 3 1s 1 S -R O 1961 1964 - May lastSu 1s 1 S -R O 1962 1964 - S lastSu 1s 0 - -R p 1916 o - Jun 17 23 1 S -R p 1916 o - N 1 1 0 - -R p 1917 1921 - Mar 1 0 1 S -R p 1917 1921 - O 14 24 0 - -R p 1924 o - Ap 16 23s 1 S -R p 1924 o - O 4 23s 0 - -R p 1926 o - Ap 17 23s 1 S -R p 1926 1929 - O Sa>=1 23s 0 - -R p 1927 o - Ap 9 23s 1 S -R p 1928 o - Ap 14 23s 1 S -R p 1929 o - Ap 20 23s 1 S -R p 1931 o - Ap 18 23s 1 S -R p 1931 1932 - O Sa>=1 23s 0 - -R p 1932 o - Ap 2 23s 1 S -R p 1934 o - Ap 7 23s 1 S -R p 1934 1938 - O Sa>=1 23s 0 - -R p 1935 o - Mar 30 23s 1 S -R p 1936 o - Ap 18 23s 1 S -R p 1937 o - Ap 3 23s 1 S -R p 1938 o - Mar 26 23s 1 S -R p 1939 o - Ap 15 23s 1 S -R p 1939 o - N 18 23s 0 - -R p 1940 o - F 24 23s 1 S -R p 1940 o - O 7 23s 0 - -R p 1941 o - Ap 5 23s 1 S -R p 1941 o - O 5 23s 0 - -R p 1942 1945 - Mar Sa>=8 23s 1 S -R p 1942 o - Ap 25 22s 2 M -R p 1942 o - Au 15 22s 1 S -R p 1942 1945 - O Sa>=24 23s 0 - -R p 1943 o - Ap 17 22s 2 M -R p 1943 1945 - Au Sa>=25 22s 1 S -R p 1944 1945 - Ap Sa>=21 22s 2 M -R p 1946 o - Ap Sa>=1 23s 1 S -R p 1946 o - O Sa>=1 23s 0 - -R p 1947 1966 - Ap Su>=1 2s 1 S -R p 1947 1965 - O Su>=1 2s 0 - -R p 1976 o - S lastSu 1 0 - -R p 1977 o - Mar lastSu 0s 1 S -R p 1977 o - S lastSu 0s 0 - -R p 1978 1980 - Ap Su>=1 1s 1 S -R p 1978 o - O 1 1s 0 - -R p 1979 1980 - S lastSu 1s 0 - -R p 1981 1986 - Mar lastSu 0s 1 S -R p 1981 1985 - S lastSu 0s 0 - -R z 1932 o - May 21 0s 1 S -R z 1932 1939 - O Su>=1 0s 0 - -R z 1933 1939 - Ap Su>=2 0s 1 S -R z 1979 o - May 27 0 1 S -R z 1979 o - S lastSu 0 0 - -R z 1980 o - Ap 5 23 1 S -R z 1980 o - S lastSu 1 0 - -R z 1991 1993 - Mar lastSu 0s 1 S -R z 1991 1993 - S lastSu 0s 0 - -R s 1918 o - Ap 15 23 1 S -R s 1918 1919 - O 6 24s 0 - -R s 1919 o - Ap 6 23 1 S -R s 1924 o - Ap 16 23 1 S -R s 1924 o - O 4 24s 0 - -R s 1926 o - Ap 17 23 1 S -R s 1926 1929 - O Sa>=1 24s 0 - -R s 1927 o - Ap 9 23 1 S -R s 1928 o - Ap 15 0 1 S -R s 1929 o - Ap 20 23 1 S -R s 1937 o - Jun 16 23 1 S -R s 1937 o - O 2 24s 0 - -R s 1938 o - Ap 2 23 1 S -R s 1938 o - Ap 30 23 2 M -R s 1938 o - O 2 24 1 S -R s 1939 o - O 7 24s 0 - -R s 1942 o - May 2 23 1 S -R s 1942 o - S 1 1 0 - -R s 1943 1946 - Ap Sa>=13 23 1 S -R s 1943 1944 - O Su>=1 1 0 - -R s 1945 1946 - S lastSu 1 0 - -R s 1949 o - Ap 30 23 1 S -R s 1949 o - O 2 1 0 - -R s 1974 1975 - Ap Sa>=12 23 1 S -R s 1974 1975 - O Su>=1 1 0 - -R s 1976 o - Mar 27 23 1 S -R s 1976 1977 - S lastSu 1 0 - -R s 1977 o - Ap 2 23 1 S -R s 1978 o - Ap 2 2s 1 S -R s 1978 o - O 1 2s 0 - -R Sp 1967 o - Jun 3 12 1 S -R Sp 1967 o - O 1 0 0 - -R Sp 1974 o - Jun 24 0 1 S -R Sp 1974 o - S 1 0 0 - -R Sp 1976 1977 - May 1 0 1 S -R Sp 1976 o - Au 1 0 0 - -R Sp 1977 o - S 28 0 0 - -R Sp 1978 o - Jun 1 0 1 S -R Sp 1978 o - Au 4 0 0 - -R CH 1941 1942 - May M>=1 1 1 S -R CH 1941 1942 - O M>=1 2 0 - -R T 1916 o - May 1 0 1 S -R T 1916 o - O 1 0 0 - -R T 1920 o - Mar 28 0 1 S -R T 1920 o - O 25 0 0 - -R T 1921 o - Ap 3 0 1 S -R T 1921 o - O 3 0 0 - -R T 1922 o - Mar 26 0 1 S -R T 1922 o - O 8 0 0 - -R T 1924 o - May 13 0 1 S -R T 1924 1925 - O 1 0 0 - -R T 1925 o - May 1 0 1 S -R T 1940 o - Jul 1 0 1 S -R T 1940 o - O 6 0 0 - -R T 1940 o - D 1 0 1 S -R T 1941 o - S 21 0 0 - -R T 1942 o - Ap 1 0 1 S -R T 1945 o - O 8 0 0 - -R T 1946 o - Jun 1 0 1 S -R T 1946 o - O 1 0 0 - -R T 1947 1948 - Ap Su>=16 0 1 S -R T 1947 1951 - O Su>=2 0 0 - -R T 1949 o - Ap 10 0 1 S -R T 1950 o - Ap 16 0 1 S -R T 1951 o - Ap 22 0 1 S -R T 1962 o - Jul 15 0 1 S -R T 1963 o - O 30 0 0 - -R T 1964 o - May 15 0 1 S -R T 1964 o - O 1 0 0 - -R T 1973 o - Jun 3 1 1 S -R T 1973 1976 - O Su>=31 2 0 - -R T 1974 o - Mar 31 2 1 S -R T 1975 o - Mar 22 2 1 S -R T 1976 o - Mar 21 2 1 S -R T 1977 1978 - Ap Su>=1 2 1 S -R T 1977 1978 - O Su>=15 2 0 - -R T 1978 o - Jun 29 0 0 - -R T 1983 o - Jul 31 2 1 S -R T 1983 o - O 2 2 0 - -R T 1985 o - Ap 20 1s 1 S -R T 1985 o - S 28 1s 0 - -R T 1986 1993 - Mar lastSu 1s 1 S -R T 1986 1995 - S lastSu 1s 0 - -R T 1994 o - Mar 20 1s 1 S -R T 1995 2006 - Mar lastSu 1s 1 S -R T 1996 2006 - O lastSu 1s 0 - -R u 1918 1919 - Mar lastSu 2 1 D -R u 1918 1919 - O lastSu 2 0 S -R u 1942 o - F 9 2 1 W -R u 1945 o - Au 14 23u 1 P -R u 1945 o - S 30 2 0 S -R u 1967 2006 - O lastSu 2 0 S -R u 1967 1973 - Ap lastSu 2 1 D -R u 1974 o - Ja 6 2 1 D -R u 1975 o - F lastSu 2 1 D -R u 1976 1986 - Ap lastSu 2 1 D -R u 1987 2006 - Ap Su>=1 2 1 D -R u 2007 ma - Mar Su>=8 2 1 D -R u 2007 ma - N Su>=1 2 0 S -R NY 1920 o - Mar lastSu 2 1 D -R NY 1920 o - O lastSu 2 0 S -R NY 1921 1966 - Ap lastSu 2 1 D -R NY 1921 1954 - S lastSu 2 0 S -R NY 1955 1966 - O lastSu 2 0 S -R Ch 1920 o - Jun 13 2 1 D -R Ch 1920 1921 - O lastSu 2 0 S -R Ch 1921 o - Mar lastSu 2 1 D -R Ch 1922 1966 - Ap lastSu 2 1 D -R Ch 1922 1954 - S lastSu 2 0 S -R Ch 1955 1966 - O lastSu 2 0 S -R De 1920 1921 - Mar lastSu 2 1 D -R De 1920 o - O lastSu 2 0 S -R De 1921 o - May 22 2 0 S -R De 1965 1966 - Ap lastSu 2 1 D -R De 1965 1966 - O lastSu 2 0 S -R CA 1948 o - Mar 14 2:1 1 D -R CA 1949 o - Ja 1 2 0 S -R CA 1950 1966 - Ap lastSu 1 1 D -R CA 1950 1961 - S lastSu 2 0 S -R CA 1962 1966 - O lastSu 2 0 S -R In 1941 o - Jun 22 2 1 D -R In 1941 1954 - S lastSu 2 0 S -R In 1946 1954 - Ap lastSu 2 1 D -R Ma 1951 o - Ap lastSu 2 1 D -R Ma 1951 o - S lastSu 2 0 S -R Ma 1954 1960 - Ap lastSu 2 1 D -R Ma 1954 1960 - S lastSu 2 0 S -R V 1946 o - Ap lastSu 2 1 D -R V 1946 o - S lastSu 2 0 S -R V 1953 1954 - Ap lastSu 2 1 D -R V 1953 1959 - S lastSu 2 0 S -R V 1955 o - May 1 0 1 D -R V 1956 1963 - Ap lastSu 2 1 D -R V 1960 o - O lastSu 2 0 S -R V 1961 o - S lastSu 2 0 S -R V 1962 1963 - O lastSu 2 0 S -R Pe 1955 o - May 1 0 1 D -R Pe 1955 1960 - S lastSu 2 0 S -R Pe 1956 1963 - Ap lastSu 2 1 D -R Pe 1961 1963 - O lastSu 2 0 S -R Pi 1955 o - May 1 0 1 D -R Pi 1955 1960 - S lastSu 2 0 S -R Pi 1956 1964 - Ap lastSu 2 1 D -R Pi 1961 1964 - O lastSu 2 0 S -R St 1947 1961 - Ap lastSu 2 1 D -R St 1947 1954 - S lastSu 2 0 S -R St 1955 1956 - O lastSu 2 0 S -R St 1957 1958 - S lastSu 2 0 S -R St 1959 1961 - O lastSu 2 0 S -R Pu 1946 1960 - Ap lastSu 2 1 D -R Pu 1946 1954 - S lastSu 2 0 S -R Pu 1955 1956 - O lastSu 2 0 S -R Pu 1957 1960 - S lastSu 2 0 S -R v 1921 o - May 1 2 1 D -R v 1921 o - S 1 2 0 S -R v 1941 o - Ap lastSu 2 1 D -R v 1941 o - S lastSu 2 0 S -R v 1946 o - Ap lastSu 0:1 1 D -R v 1946 o - Jun 2 2 0 S -R v 1950 1961 - Ap lastSu 2 1 D -R v 1950 1955 - S lastSu 2 0 S -R v 1956 1961 - O lastSu 2 0 S -R Dt 1948 o - Ap lastSu 2 1 D -R Dt 1948 o - S lastSu 2 0 S -R Me 1946 o - Ap lastSu 2 1 D -R Me 1946 o - S lastSu 2 0 S -R Me 1966 o - Ap lastSu 2 1 D -R Me 1966 o - O lastSu 2 0 S -R C 1918 o - Ap 14 2 1 D -R C 1918 o - O 27 2 0 S -R C 1942 o - F 9 2 1 W -R C 1945 o - Au 14 23u 1 P -R C 1945 o - S 30 2 0 S -R C 1974 1986 - Ap lastSu 2 1 D -R C 1974 2006 - O lastSu 2 0 S -R C 1987 2006 - Ap Su>=1 2 1 D -R C 2007 ma - Mar Su>=8 2 1 D -R C 2007 ma - N Su>=1 2 0 S -R j 1917 o - Ap 8 2 1 D -R j 1917 o - S 17 2 0 S -R j 1919 o - May 5 23 1 D -R j 1919 o - Au 12 23 0 S -R j 1920 1935 - May Su>=1 23 1 D -R j 1920 1935 - O lastSu 23 0 S -R j 1936 1941 - May M>=9 0 1 D -R j 1936 1941 - O M>=2 0 0 S -R j 1946 1950 - May Su>=8 2 1 D -R j 1946 1950 - O Su>=2 2 0 S -R j 1951 1986 - Ap lastSu 2 1 D -R j 1951 1959 - S lastSu 2 0 S -R j 1960 1986 - O lastSu 2 0 S -R j 1987 o - Ap Su>=1 0:1 1 D -R j 1987 2006 - O lastSu 0:1 0 S -R j 1988 o - Ap Su>=1 0:1 2 DD -R j 1989 2006 - Ap Su>=1 0:1 1 D -R j 2007 2011 - Mar Su>=8 0:1 1 D -R j 2007 2010 - N Su>=1 0:1 0 S -R H 1916 o - Ap 1 0 1 D -R H 1916 o - O 1 0 0 S -R H 1920 o - May 9 0 1 D -R H 1920 o - Au 29 0 0 S -R H 1921 o - May 6 0 1 D -R H 1921 1922 - S 5 0 0 S -R H 1922 o - Ap 30 0 1 D -R H 1923 1925 - May Su>=1 0 1 D -R H 1923 o - S 4 0 0 S -R H 1924 o - S 15 0 0 S -R H 1925 o - S 28 0 0 S -R H 1926 o - May 16 0 1 D -R H 1926 o - S 13 0 0 S -R H 1927 o - May 1 0 1 D -R H 1927 o - S 26 0 0 S -R H 1928 1931 - May Su>=8 0 1 D -R H 1928 o - S 9 0 0 S -R H 1929 o - S 3 0 0 S -R H 1930 o - S 15 0 0 S -R H 1931 1932 - S M>=24 0 0 S -R H 1932 o - May 1 0 1 D -R H 1933 o - Ap 30 0 1 D -R H 1933 o - O 2 0 0 S -R H 1934 o - May 20 0 1 D -R H 1934 o - S 16 0 0 S -R H 1935 o - Jun 2 0 1 D -R H 1935 o - S 30 0 0 S -R H 1936 o - Jun 1 0 1 D -R H 1936 o - S 14 0 0 S -R H 1937 1938 - May Su>=1 0 1 D -R H 1937 1941 - S M>=24 0 0 S -R H 1939 o - May 28 0 1 D -R H 1940 1941 - May Su>=1 0 1 D -R H 1946 1949 - Ap lastSu 2 1 D -R H 1946 1949 - S lastSu 2 0 S -R H 1951 1954 - Ap lastSu 2 1 D -R H 1951 1954 - S lastSu 2 0 S -R H 1956 1959 - Ap lastSu 2 1 D -R H 1956 1959 - S lastSu 2 0 S -R H 1962 1973 - Ap lastSu 2 1 D -R H 1962 1973 - O lastSu 2 0 S -R o 1933 1935 - Jun Su>=8 1 1 D -R o 1933 1935 - S Su>=8 1 0 S -R o 1936 1938 - Jun Su>=1 1 1 D -R o 1936 1938 - S Su>=1 1 0 S -R o 1939 o - May 27 1 1 D -R o 1939 1941 - S Sa>=21 1 0 S -R o 1940 o - May 19 1 1 D -R o 1941 o - May 4 1 1 D -R o 1946 1972 - Ap lastSu 2 1 D -R o 1946 1956 - S lastSu 2 0 S -R o 1957 1972 - O lastSu 2 0 S -R o 1993 2006 - Ap Su>=1 0:1 1 D -R o 1993 2006 - O lastSu 0:1 0 S -R t 1919 o - Mar 30 23:30 1 D -R t 1919 o - O 26 0 0 S -R t 1920 o - May 2 2 1 D -R t 1920 o - S 26 0 0 S -R t 1921 o - May 15 2 1 D -R t 1921 o - S 15 2 0 S -R t 1922 1923 - May Su>=8 2 1 D -R t 1922 1926 - S Su>=15 2 0 S -R t 1924 1927 - May Su>=1 2 1 D -R t 1927 1937 - S Su>=25 2 0 S -R t 1928 1937 - Ap Su>=25 2 1 D -R t 1938 1940 - Ap lastSu 2 1 D -R t 1938 1939 - S lastSu 2 0 S -R t 1945 1948 - S lastSu 2 0 S -R t 1946 1973 - Ap lastSu 2 1 D -R t 1949 1950 - N lastSu 2 0 S -R t 1951 1956 - S lastSu 2 0 S -R t 1957 1973 - O lastSu 2 0 S -R W 1916 o - Ap 23 0 1 D -R W 1916 o - S 17 0 0 S -R W 1918 o - Ap 14 2 1 D -R W 1918 o - O 27 2 0 S -R W 1937 o - May 16 2 1 D -R W 1937 o - S 26 2 0 S -R W 1942 o - F 9 2 1 W -R W 1945 o - Au 14 23u 1 P -R W 1945 o - S lastSu 2 0 S -R W 1946 o - May 12 2 1 D -R W 1946 o - O 13 2 0 S -R W 1947 1949 - Ap lastSu 2 1 D -R W 1947 1949 - S lastSu 2 0 S -R W 1950 o - May 1 2 1 D -R W 1950 o - S 30 2 0 S -R W 1951 1960 - Ap lastSu 2 1 D -R W 1951 1958 - S lastSu 2 0 S -R W 1959 o - O lastSu 2 0 S -R W 1960 o - S lastSu 2 0 S -R W 1963 o - Ap lastSu 2 1 D -R W 1963 o - S 22 2 0 S -R W 1966 1986 - Ap lastSu 2s 1 D -R W 1966 2005 - O lastSu 2s 0 S -R W 1987 2005 - Ap Su>=1 2s 1 D -R r 1918 o - Ap 14 2 1 D -R r 1918 o - O 27 2 0 S -R r 1930 1934 - May Su>=1 0 1 D -R r 1930 1934 - O Su>=1 0 0 S -R r 1937 1941 - Ap Su>=8 0 1 D -R r 1937 o - O Su>=8 0 0 S -R r 1938 o - O Su>=1 0 0 S -R r 1939 1941 - O Su>=8 0 0 S -R r 1942 o - F 9 2 1 W -R r 1945 o - Au 14 23u 1 P -R r 1945 o - S lastSu 2 0 S -R r 1946 o - Ap Su>=8 2 1 D -R r 1946 o - O Su>=8 2 0 S -R r 1947 1957 - Ap lastSu 2 1 D -R r 1947 1957 - S lastSu 2 0 S -R r 1959 o - Ap lastSu 2 1 D -R r 1959 o - O lastSu 2 0 S -R Sw 1957 o - Ap lastSu 2 1 D -R Sw 1957 o - O lastSu 2 0 S -R Sw 1959 1961 - Ap lastSu 2 1 D -R Sw 1959 o - O lastSu 2 0 S -R Sw 1960 1961 - S lastSu 2 0 S -R Ed 1918 1919 - Ap Su>=8 2 1 D -R Ed 1918 o - O 27 2 0 S -R Ed 1919 o - May 27 2 0 S -R Ed 1920 1923 - Ap lastSu 2 1 D -R Ed 1920 o - O lastSu 2 0 S -R Ed 1921 1923 - S lastSu 2 0 S -R Ed 1942 o - F 9 2 1 W -R Ed 1945 o - Au 14 23u 1 P -R Ed 1945 o - S lastSu 2 0 S -R Ed 1947 o - Ap lastSu 2 1 D -R Ed 1947 o - S lastSu 2 0 S -R Ed 1972 1986 - Ap lastSu 2 1 D -R Ed 1972 2006 - O lastSu 2 0 S -R Va 1918 o - Ap 14 2 1 D -R Va 1918 o - O 27 2 0 S -R Va 1942 o - F 9 2 1 W -R Va 1945 o - Au 14 23u 1 P -R Va 1945 o - S 30 2 0 S -R Va 1946 1986 - Ap lastSu 2 1 D -R Va 1946 o - S 29 2 0 S -R Va 1947 1961 - S lastSu 2 0 S -R Va 1962 2006 - O lastSu 2 0 S -R Y 1918 o - Ap 14 2 1 D -R Y 1918 o - O 27 2 0 S -R Y 1919 o - May 25 2 1 D -R Y 1919 o - N 1 0 0 S -R Y 1942 o - F 9 2 1 W -R Y 1945 o - Au 14 23u 1 P -R Y 1945 o - S 30 2 0 S -R Y 1972 1986 - Ap lastSu 2 1 D -R Y 1972 2006 - O lastSu 2 0 S -R Y 1987 2006 - Ap Su>=1 2 1 D -R Yu 1965 o - Ap lastSu 0 2 DD -R Yu 1965 o - O lastSu 2 0 S -R m 1931 o - Ap 30 0 1 D -R m 1931 o - O 1 0 0 S -R m 1939 o - F 5 0 1 D -R m 1939 o - Jun 25 0 0 S -R m 1940 o - D 9 0 1 D -R m 1941 o - Ap 1 0 0 S -R m 1943 o - D 16 0 1 W -R m 1944 o - May 1 0 0 S -R m 1950 o - F 12 0 1 D -R m 1950 o - Jul 30 0 0 S -R m 1996 2000 - Ap Su>=1 2 1 D -R m 1996 2000 - O lastSu 2 0 S -R m 2001 o - May Su>=1 2 1 D -R m 2001 o - S lastSu 2 0 S -R m 2002 2022 - Ap Su>=1 2 1 D -R m 2002 2022 - O lastSu 2 0 S -R BB 1942 o - Ap 19 5u 1 D -R BB 1942 o - Au 31 6u 0 S -R BB 1943 o - May 2 5u 1 D -R BB 1943 o - S 5 6u 0 S -R BB 1944 o - Ap 10 5u 0:30 - -R BB 1944 o - S 10 6u 0 S -R BB 1977 o - Jun 12 2 1 D -R BB 1977 1978 - O Su>=1 2 0 S -R BB 1978 1980 - Ap Su>=15 2 1 D -R BB 1979 o - S 30 2 0 S -R BB 1980 o - S 25 2 0 S -R BZ 1918 1941 - O Sa>=1 24 0:30 -0530 -R BZ 1919 1942 - F Sa>=8 24 0 CST -R BZ 1942 o - Jun 27 24 1 CWT -R BZ 1945 o - Au 14 23u 1 CPT -R BZ 1945 o - D 15 24 0 CST -R BZ 1947 1967 - O Sa>=1 24 0:30 -0530 -R BZ 1948 1968 - F Sa>=8 24 0 CST -R BZ 1973 o - D 5 0 1 CDT -R BZ 1974 o - F 9 0 0 CST -R BZ 1982 o - D 18 0 1 CDT -R BZ 1983 o - F 12 0 0 CST -R Be 1917 o - Ap 5 24 1 - -R Be 1917 o - S 30 24 0 - -R Be 1918 o - Ap 13 24 1 - -R Be 1918 o - S 15 24 0 S -R Be 1942 o - Ja 11 2 1 D -R Be 1942 o - O 18 2 0 S -R Be 1943 o - Mar 21 2 1 D -R Be 1943 o - O 31 2 0 S -R Be 1944 1945 - Mar Su>=8 2 1 D -R Be 1944 1945 - N Su>=1 2 0 S -R Be 1947 o - May Su>=15 2 1 D -R Be 1947 o - S Su>=8 2 0 S -R Be 1948 1952 - May Su>=22 2 1 D -R Be 1948 1952 - S Su>=1 2 0 S -R Be 1956 o - May Su>=22 2 1 D -R Be 1956 o - O lastSu 2 0 S -R CR 1979 1980 - F lastSu 0 1 D -R CR 1979 1980 - Jun Su>=1 0 0 S -R CR 1991 1992 - Ja Sa>=15 0 1 D -R CR 1991 o - Jul 1 0 0 S -R CR 1992 o - Mar 15 0 0 S -R Q 1928 o - Jun 10 0 1 D -R Q 1928 o - O 10 0 0 S -R Q 1940 1942 - Jun Su>=1 0 1 D -R Q 1940 1942 - S Su>=1 0 0 S -R Q 1945 1946 - Jun Su>=1 0 1 D -R Q 1945 1946 - S Su>=1 0 0 S -R Q 1965 o - Jun 1 0 1 D -R Q 1965 o - S 30 0 0 S -R Q 1966 o - May 29 0 1 D -R Q 1966 o - O 2 0 0 S -R Q 1967 o - Ap 8 0 1 D -R Q 1967 1968 - S Su>=8 0 0 S -R Q 1968 o - Ap 14 0 1 D -R Q 1969 1977 - Ap lastSu 0 1 D -R Q 1969 1971 - O lastSu 0 0 S -R Q 1972 1974 - O 8 0 0 S -R Q 1975 1977 - O lastSu 0 0 S -R Q 1978 o - May 7 0 1 D -R Q 1978 1990 - O Su>=8 0 0 S -R Q 1979 1980 - Mar Su>=15 0 1 D -R Q 1981 1985 - May Su>=5 0 1 D -R Q 1986 1989 - Mar Su>=14 0 1 D -R Q 1990 1997 - Ap Su>=1 0 1 D -R Q 1991 1995 - O Su>=8 0s 0 S -R Q 1996 o - O 6 0s 0 S -R Q 1997 o - O 12 0s 0 S -R Q 1998 1999 - Mar lastSu 0s 1 D -R Q 1998 2003 - O lastSu 0s 0 S -R Q 2000 2003 - Ap Su>=1 0s 1 D -R Q 2004 o - Mar lastSu 0s 1 D -R Q 2006 2010 - O lastSu 0s 0 S -R Q 2007 o - Mar Su>=8 0s 1 D -R Q 2008 o - Mar Su>=15 0s 1 D -R Q 2009 2010 - Mar Su>=8 0s 1 D -R Q 2011 o - Mar Su>=15 0s 1 D -R Q 2011 o - N 13 0s 0 S -R Q 2012 o - Ap 1 0s 1 D -R Q 2012 ma - N Su>=1 0s 0 S -R Q 2013 ma - Mar Su>=8 0s 1 D -R DO 1966 o - O 30 0 1 EDT -R DO 1967 o - F 28 0 0 EST -R DO 1969 1973 - O lastSu 0 0:30 -0430 -R DO 1970 o - F 21 0 0 EST -R DO 1971 o - Ja 20 0 0 EST -R DO 1972 1974 - Ja 21 0 0 EST -R SV 1987 1988 - May Su>=1 0 1 D -R SV 1987 1988 - S lastSu 0 0 S -R GT 1973 o - N 25 0 1 D -R GT 1974 o - F 24 0 0 S -R GT 1983 o - May 21 0 1 D -R GT 1983 o - S 22 0 0 S -R GT 1991 o - Mar 23 0 1 D -R GT 1991 o - S 7 0 0 S -R GT 2006 o - Ap 30 0 1 D -R GT 2006 o - O 1 0 0 S -R HT 1983 o - May 8 0 1 D -R HT 1984 1987 - Ap lastSu 0 1 D -R HT 1983 1987 - O lastSu 0 0 S -R HT 1988 1997 - Ap Su>=1 1s 1 D -R HT 1988 1997 - O lastSu 1s 0 S -R HT 2005 2006 - Ap Su>=1 0 1 D -R HT 2005 2006 - O lastSu 0 0 S -R HT 2012 2015 - Mar Su>=8 2 1 D -R HT 2012 2015 - N Su>=1 2 0 S -R HT 2017 ma - Mar Su>=8 2 1 D -R HT 2017 ma - N Su>=1 2 0 S -R HN 1987 1988 - May Su>=1 0 1 D -R HN 1987 1988 - S lastSu 0 0 S -R HN 2006 o - May Su>=1 0 1 D -R HN 2006 o - Au M>=1 0 0 S -R NI 1979 1980 - Mar Su>=16 0 1 D -R NI 1979 1980 - Jun M>=23 0 0 S -R NI 2005 o - Ap 10 0 1 D -R NI 2005 o - O Su>=1 0 0 S -R NI 2006 o - Ap 30 2 1 D -R NI 2006 o - O Su>=1 1 0 S -R A 1930 o - D 1 0 1 - -R A 1931 o - Ap 1 0 0 - -R A 1931 o - O 15 0 1 - -R A 1932 1940 - Mar 1 0 0 - -R A 1932 1939 - N 1 0 1 - -R A 1940 o - Jul 1 0 1 - -R A 1941 o - Jun 15 0 0 - -R A 1941 o - O 15 0 1 - -R A 1943 o - Au 1 0 0 - -R A 1943 o - O 15 0 1 - -R A 1946 o - Mar 1 0 0 - -R A 1946 o - O 1 0 1 - -R A 1963 o - O 1 0 0 - -R A 1963 o - D 15 0 1 - -R A 1964 1966 - Mar 1 0 0 - -R A 1964 1966 - O 15 0 1 - -R A 1967 o - Ap 2 0 0 - -R A 1967 1968 - O Su>=1 0 1 - -R A 1968 1969 - Ap Su>=1 0 0 - -R A 1974 o - Ja 23 0 1 - -R A 1974 o - May 1 0 0 - -R A 1988 o - D 1 0 1 - -R A 1989 1993 - Mar Su>=1 0 0 - -R A 1989 1992 - O Su>=15 0 1 - -R A 1999 o - O Su>=1 0 1 - -R A 2000 o - Mar 3 0 0 - -R A 2007 o - D 30 0 1 - -R A 2008 2009 - Mar Su>=15 0 0 - -R A 2008 o - O Su>=15 0 1 - -R Sa 2008 2009 - Mar Su>=8 0 0 - -R Sa 2007 2008 - O Su>=8 0 1 - -R B 1931 o - O 3 11 1 - -R B 1932 1933 - Ap 1 0 0 - -R B 1932 o - O 3 0 1 - -R B 1949 1952 - D 1 0 1 - -R B 1950 o - Ap 16 1 0 - -R B 1951 1952 - Ap 1 0 0 - -R B 1953 o - Mar 1 0 0 - -R B 1963 o - D 9 0 1 - -R B 1964 o - Mar 1 0 0 - -R B 1965 o - Ja 31 0 1 - -R B 1965 o - Mar 31 0 0 - -R B 1965 o - D 1 0 1 - -R B 1966 1968 - Mar 1 0 0 - -R B 1966 1967 - N 1 0 1 - -R B 1985 o - N 2 0 1 - -R B 1986 o - Mar 15 0 0 - -R B 1986 o - O 25 0 1 - -R B 1987 o - F 14 0 0 - -R B 1987 o - O 25 0 1 - -R B 1988 o - F 7 0 0 - -R B 1988 o - O 16 0 1 - -R B 1989 o - Ja 29 0 0 - -R B 1989 o - O 15 0 1 - -R B 1990 o - F 11 0 0 - -R B 1990 o - O 21 0 1 - -R B 1991 o - F 17 0 0 - -R B 1991 o - O 20 0 1 - -R B 1992 o - F 9 0 0 - -R B 1992 o - O 25 0 1 - -R B 1993 o - Ja 31 0 0 - -R B 1993 1995 - O Su>=11 0 1 - -R B 1994 1995 - F Su>=15 0 0 - -R B 1996 o - F 11 0 0 - -R B 1996 o - O 6 0 1 - -R B 1997 o - F 16 0 0 - -R B 1997 o - O 6 0 1 - -R B 1998 o - Mar 1 0 0 - -R B 1998 o - O 11 0 1 - -R B 1999 o - F 21 0 0 - -R B 1999 o - O 3 0 1 - -R B 2000 o - F 27 0 0 - -R B 2000 2001 - O Su>=8 0 1 - -R B 2001 2006 - F Su>=15 0 0 - -R B 2002 o - N 3 0 1 - -R B 2003 o - O 19 0 1 - -R B 2004 o - N 2 0 1 - -R B 2005 o - O 16 0 1 - -R B 2006 o - N 5 0 1 - -R B 2007 o - F 25 0 0 - -R B 2007 o - O Su>=8 0 1 - -R B 2008 2017 - O Su>=15 0 1 - -R B 2008 2011 - F Su>=15 0 0 - -R B 2012 o - F Su>=22 0 0 - -R B 2013 2014 - F Su>=15 0 0 - -R B 2015 o - F Su>=22 0 0 - -R B 2016 2019 - F Su>=15 0 0 - -R B 2018 o - N Su>=1 0 1 - -R x 1927 1931 - S 1 0 1 - -R x 1928 1932 - Ap 1 0 0 - -R x 1968 o - N 3 4u 1 - -R x 1969 o - Mar 30 3u 0 - -R x 1969 o - N 23 4u 1 - -R x 1970 o - Mar 29 3u 0 - -R x 1971 o - Mar 14 3u 0 - -R x 1970 1972 - O Su>=9 4u 1 - -R x 1972 1986 - Mar Su>=9 3u 0 - -R x 1973 o - S 30 4u 1 - -R x 1974 1987 - O Su>=9 4u 1 - -R x 1987 o - Ap 12 3u 0 - -R x 1988 1990 - Mar Su>=9 3u 0 - -R x 1988 1989 - O Su>=9 4u 1 - -R x 1990 o - S 16 4u 1 - -R x 1991 1996 - Mar Su>=9 3u 0 - -R x 1991 1997 - O Su>=9 4u 1 - -R x 1997 o - Mar 30 3u 0 - -R x 1998 o - Mar Su>=9 3u 0 - -R x 1998 o - S 27 4u 1 - -R x 1999 o - Ap 4 3u 0 - -R x 1999 2010 - O Su>=9 4u 1 - -R x 2000 2007 - Mar Su>=9 3u 0 - -R x 2008 o - Mar 30 3u 0 - -R x 2009 o - Mar Su>=9 3u 0 - -R x 2010 o - Ap Su>=1 3u 0 - -R x 2011 o - May Su>=2 3u 0 - -R x 2011 o - Au Su>=16 4u 1 - -R x 2012 2014 - Ap Su>=23 3u 0 - -R x 2012 2014 - S Su>=2 4u 1 - -R x 2016 2018 - May Su>=9 3u 0 - -R x 2016 2018 - Au Su>=9 4u 1 - -R x 2019 ma - Ap Su>=2 3u 0 - -R x 2019 2021 - S Su>=2 4u 1 - -R x 2022 o - S Su>=9 4u 1 - -R x 2023 ma - S Su>=2 4u 1 - -R CO 1992 o - May 3 0 1 - -R CO 1993 o - F 6 24 0 - -R EC 1992 o - N 28 0 1 - -R EC 1993 o - F 5 0 0 - -R FK 1937 1938 - S lastSu 0 1 - -R FK 1938 1942 - Mar Su>=19 0 0 - -R FK 1939 o - O 1 0 1 - -R FK 1940 1942 - S lastSu 0 1 - -R FK 1943 o - Ja 1 0 0 - -R FK 1983 o - S lastSu 0 1 - -R FK 1984 1985 - Ap lastSu 0 0 - -R FK 1984 o - S 16 0 1 - -R FK 1985 2000 - S Su>=9 0 1 - -R FK 1986 2000 - Ap Su>=16 0 0 - -R FK 2001 2010 - Ap Su>=15 2 0 - -R FK 2001 2010 - S Su>=1 2 1 - -R y 1975 1988 - O 1 0 1 - -R y 1975 1978 - Mar 1 0 0 - -R y 1979 1991 - Ap 1 0 0 - -R y 1989 o - O 22 0 1 - -R y 1990 o - O 1 0 1 - -R y 1991 o - O 6 0 1 - -R y 1992 o - Mar 1 0 0 - -R y 1992 o - O 5 0 1 - -R y 1993 o - Mar 31 0 0 - -R y 1993 1995 - O 1 0 1 - -R y 1994 1995 - F lastSu 0 0 - -R y 1996 o - Mar 1 0 0 - -R y 1996 2001 - O Su>=1 0 1 - -R y 1997 o - F lastSu 0 0 - -R y 1998 2001 - Mar Su>=1 0 0 - -R y 2002 2004 - Ap Su>=1 0 0 - -R y 2002 2003 - S Su>=1 0 1 - -R y 2004 2009 - O Su>=15 0 1 - -R y 2005 2009 - Mar Su>=8 0 0 - -R y 2010 2024 - O Su>=1 0 1 - -R y 2010 2012 - Ap Su>=8 0 0 - -R y 2013 2024 - Mar Su>=22 0 0 - -R PE 1938 o - Ja 1 0 1 - -R PE 1938 o - Ap 1 0 0 - -R PE 1938 1939 - S lastSu 0 1 - -R PE 1939 1940 - Mar Su>=24 0 0 - -R PE 1986 1987 - Ja 1 0 1 - -R PE 1986 1987 - Ap 1 0 0 - -R PE 1990 o - Ja 1 0 1 - -R PE 1990 o - Ap 1 0 0 - -R PE 1994 o - Ja 1 0 1 - -R PE 1994 o - Ap 1 0 0 - -R U 1923 1925 - O 1 0 0:30 - -R U 1924 1926 - Ap 1 0 0 - -R U 1933 1938 - O lastSu 0 0:30 - -R U 1934 1941 - Mar lastSa 24 0 - -R U 1939 o - O 1 0 0:30 - -R U 1940 o - O 27 0 0:30 - -R U 1941 o - Au 1 0 0:30 - -R U 1942 o - D 14 0 0:30 - -R U 1943 o - Mar 14 0 0 - -R U 1959 o - May 24 0 0:30 - -R U 1959 o - N 15 0 0 - -R U 1960 o - Ja 17 0 1 - -R U 1960 o - Mar 6 0 0 - -R U 1965 o - Ap 4 0 1 - -R U 1965 o - S 26 0 0 - -R U 1968 o - May 27 0 0:30 - -R U 1968 o - D 1 0 0 - -R U 1970 o - Ap 25 0 1 - -R U 1970 o - Jun 14 0 0 - -R U 1972 o - Ap 23 0 1 - -R U 1972 o - Jul 16 0 0 - -R U 1974 o - Ja 13 0 1:30 - -R U 1974 o - Mar 10 0 0:30 - -R U 1974 o - S 1 0 0 - -R U 1974 o - D 22 0 1 - -R U 1975 o - Mar 30 0 0 - -R U 1976 o - D 19 0 1 - -R U 1977 o - Mar 6 0 0 - -R U 1977 o - D 4 0 1 - -R U 1978 1979 - Mar Su>=1 0 0 - -R U 1978 o - D 17 0 1 - -R U 1979 o - Ap 29 0 1 - -R U 1980 o - Mar 16 0 0 - -R U 1987 o - D 14 0 1 - -R U 1988 o - F 28 0 0 - -R U 1988 o - D 11 0 1 - -R U 1989 o - Mar 5 0 0 - -R U 1989 o - O 29 0 1 - -R U 1990 o - F 25 0 0 - -R U 1990 1991 - O Su>=21 0 1 - -R U 1991 1992 - Mar Su>=1 0 0 - -R U 1992 o - O 18 0 1 - -R U 1993 o - F 28 0 0 - -R U 2004 o - S 19 0 1 - -R U 2005 o - Mar 27 2 0 - -R U 2005 o - O 9 2 1 - -R U 2006 2015 - Mar Su>=8 2 0 - -R U 2006 2014 - O Su>=1 2 1 - -Z Africa/Abidjan -0:16:8 - LMT 1912 -0 - GMT -Z Africa/Algiers 0:12:12 - LMT 1891 Mar 16 -0:9:21 - PMT 1911 Mar 11 -0 d WE%sT 1940 F 25 2 -1 d CE%sT 1946 O 7 -0 - WET 1956 Ja 29 -1 - CET 1963 Ap 14 -0 d WE%sT 1977 O 21 -1 d CE%sT 1979 O 26 -0 d WE%sT 1981 May -1 - CET -Z Africa/Bissau -1:2:20 - LMT 1912 Ja 1 1u --1 - %z 1975 -0 - GMT -Z Africa/Cairo 2:5:9 - LMT 1900 O -2 K EE%sT -Z Africa/Casablanca -0:30:20 - LMT 1913 O 26 -0 M %z 1984 Mar 16 -1 - %z 1986 -0 M %z 2018 O 28 3 -1 M %z -Z Africa/Ceuta -0:21:16 - LMT 1901 Ja 1 0u -0 - WET 1918 May 6 23 -0 1 WEST 1918 O 7 23 -0 - WET 1924 -0 s WE%sT 1929 -0 - WET 1967 -0 Sp WE%sT 1984 Mar 16 -1 - CET 1986 -1 E CE%sT -Z Africa/El_Aaiun -0:52:48 - LMT 1934 --1 - %z 1976 Ap 14 -0 M %z 2018 O 28 3 -1 M %z -Z Africa/Johannesburg 1:52 - LMT 1892 F 8 -1:30 - SAST 1903 Mar -2 SA SAST -Z Africa/Juba 2:6:28 - LMT 1931 -2 SD CA%sT 2000 Ja 15 12 -3 - EAT 2021 F -2 - CAT -Z Africa/Khartoum 2:10:8 - LMT 1931 -2 SD CA%sT 2000 Ja 15 12 -3 - EAT 2017 N -2 - CAT -Z Africa/Lagos 0:13:35 - LMT 1905 Jul -0 - GMT 1908 Jul -0:13:35 - LMT 1914 -0:30 - %z 1919 S -1 - WAT -Z Africa/Maputo 2:10:18 - LMT 1909 -2 - CAT -Z Africa/Monrovia -0:43:8 - LMT 1882 --0:43:8 - MMT 1919 Mar --0:44:30 - MMT 1972 Ja 7 -0 - GMT -Z Africa/Nairobi 2:27:16 - LMT 1908 May -2:30 - %z 1928 Jun 30 24 -3 - EAT 1930 Ja 4 24 -2:30 - %z 1936 D 31 24 -2:45 - %z 1942 Jul 31 24 -3 - EAT -Z Africa/Ndjamena 1:0:12 - LMT 1912 -1 - WAT 1979 O 14 -1 1 WAST 1980 Mar 8 -1 - WAT -Z Africa/Sao_Tome 0:26:56 - LMT 1884 --0:36:45 - LMT 1912 Ja 1 0u -0 - GMT 2018 Ja 1 1 -1 - WAT 2019 Ja 1 2 -0 - GMT -Z Africa/Tripoli 0:52:44 - LMT 1920 -1 L CE%sT 1959 -2 - EET 1982 -1 L CE%sT 1990 May 4 -2 - EET 1996 S 30 -1 L CE%sT 1997 O 4 -2 - EET 2012 N 10 2 -1 L CE%sT 2013 O 25 2 -2 - EET -Z Africa/Tunis 0:40:44 - LMT 1881 May 12 -0:9:21 - PMT 1911 Mar 11 -1 n CE%sT -Z Africa/Windhoek 1:8:24 - LMT 1892 F 8 -1:30 - %z 1903 Mar -2 - SAST 1942 S 20 2 -2 1 SAST 1943 Mar 21 2 -2 - SAST 1990 Mar 21 -2 NA %s -Z America/Adak 12:13:22 - LMT 1867 O 19 12:44:35 --11:46:38 - LMT 1900 Au 20 12 --11 - NST 1942 --11 u N%sT 1946 --11 - NST 1967 Ap --11 - BST 1969 --11 u B%sT 1983 O 30 2 --10 u AH%sT 1983 N 30 --10 u H%sT -Z America/Anchorage 14:0:24 - LMT 1867 O 19 14:31:37 --9:59:36 - LMT 1900 Au 20 12 --10 - AST 1942 --10 u A%sT 1967 Ap --10 - AHST 1969 --10 u AH%sT 1983 O 30 2 --9 u Y%sT 1983 N 30 --9 u AK%sT -Z America/Araguaina -3:12:48 - LMT 1914 --3 B %z 1990 S 17 --3 - %z 1995 S 14 --3 B %z 2003 S 24 --3 - %z 2012 O 21 --3 B %z 2013 S --3 - %z -Z America/Argentina/Buenos_Aires -3:53:48 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 A %z -Z America/Argentina/Catamarca -4:23:8 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1991 Mar 3 --4 - %z 1991 O 20 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 - %z 2004 Jun --4 - %z 2004 Jun 20 --3 A %z 2008 O 18 --3 - %z -Z America/Argentina/Cordoba -4:16:48 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1991 Mar 3 --4 - %z 1991 O 20 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 A %z -Z America/Argentina/Jujuy -4:21:12 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1990 Mar 4 --4 - %z 1990 O 28 --4 1 %z 1991 Mar 17 --4 - %z 1991 O 6 --3 1 %z 1992 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 A %z 2008 O 18 --3 - %z -Z America/Argentina/La_Rioja -4:27:24 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1991 Mar --4 - %z 1991 May 7 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 - %z 2004 Jun --4 - %z 2004 Jun 20 --3 A %z 2008 O 18 --3 - %z -Z America/Argentina/Mendoza -4:35:16 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1990 Mar 4 --4 - %z 1990 O 15 --4 1 %z 1991 Mar --4 - %z 1991 O 15 --4 1 %z 1992 Mar --4 - %z 1992 O 18 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 - %z 2004 May 23 --4 - %z 2004 S 26 --3 A %z 2008 O 18 --3 - %z -Z America/Argentina/Rio_Gallegos -4:36:52 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 - %z 2004 Jun --4 - %z 2004 Jun 20 --3 A %z 2008 O 18 --3 - %z -Z America/Argentina/Salta -4:21:40 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1991 Mar 3 --4 - %z 1991 O 20 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 A %z 2008 O 18 --3 - %z -Z America/Argentina/San_Juan -4:34:4 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1991 Mar --4 - %z 1991 May 7 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 - %z 2004 May 31 --4 - %z 2004 Jul 25 --3 A %z 2008 O 18 --3 - %z -Z America/Argentina/San_Luis -4:25:24 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1990 --3 1 %z 1990 Mar 14 --4 - %z 1990 O 15 --4 1 %z 1991 Mar --4 - %z 1991 Jun --3 - %z 1999 O 3 --4 1 %z 2000 Mar 3 --3 - %z 2004 May 31 --4 - %z 2004 Jul 25 --3 A %z 2008 Ja 21 --4 Sa %z 2009 O 11 --3 - %z -Z America/Argentina/Tucuman -4:20:52 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1991 Mar 3 --4 - %z 1991 O 20 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 - %z 2004 Jun --4 - %z 2004 Jun 13 --3 A %z -Z America/Argentina/Ushuaia -4:33:12 - LMT 1894 O 31 --4:16:48 - CMT 1920 May --4 - %z 1930 D --4 A %z 1969 O 5 --3 A %z 1999 O 3 --4 A %z 2000 Mar 3 --3 - %z 2004 May 30 --4 - %z 2004 Jun 20 --3 A %z 2008 O 18 --3 - %z -Z America/Asuncion -3:50:40 - LMT 1890 --3:50:40 - AMT 1931 O 10 --4 - %z 1972 O --3 - %z 1974 Ap --4 y %z 2024 O 15 --3 - %z -Z America/Bahia -2:34:4 - LMT 1914 --3 B %z 2003 S 24 --3 - %z 2011 O 16 --3 B %z 2012 O 21 --3 - %z -Z America/Bahia_Banderas -7:1 - LMT 1922 Ja 1 7u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 - CST 1942 Ap 24 --7 - MST 1970 --7 m M%sT 2010 Ap 4 2 --6 m C%sT -Z America/Barbados -3:58:29 - LMT 1911 Au 28 --4 BB A%sT 1944 --4 BB AST/-0330 1945 --4 BB A%sT -Z America/Belem -3:13:56 - LMT 1914 --3 B %z 1988 S 12 --3 - %z -Z America/Belize -5:52:48 - LMT 1912 Ap --6 BZ %s -Z America/Boa_Vista -4:2:40 - LMT 1914 --4 B %z 1988 S 12 --4 - %z 1999 S 30 --4 B %z 2000 O 15 --4 - %z -Z America/Bogota -4:56:16 - LMT 1884 Mar 13 --4:56:16 - BMT 1914 N 23 --5 CO %z -Z America/Boise -7:44:49 - LMT 1883 N 18 20u --8 u P%sT 1923 May 13 2 --7 u M%sT 1974 --7 - MST 1974 F 3 2 --7 u M%sT -Z America/Cambridge_Bay 0 - -00 1920 --7 Y M%sT 1999 O 31 2 --6 C C%sT 2000 O 29 2 --5 - EST 2000 N 5 --6 - CST 2001 Ap 1 3 --7 C M%sT -Z America/Campo_Grande -3:38:28 - LMT 1914 --4 B %z -Z America/Cancun -5:47:4 - LMT 1922 Ja 1 6u --6 - CST 1981 D 26 2 --5 - EST 1983 Ja 4 --6 m C%sT 1997 O 26 2 --5 m E%sT 1998 Au 2 2 --6 m C%sT 2015 F 1 2 --5 - EST -Z America/Caracas -4:27:44 - LMT 1890 --4:27:40 - CMT 1912 F 12 --4:30 - %z 1965 --4 - %z 2007 D 9 3 --4:30 - %z 2016 May 1 2:30 --4 - %z -Z America/Cayenne -3:29:20 - LMT 1911 Jul --4 - %z 1967 O --3 - %z -Z America/Chicago -5:50:36 - LMT 1883 N 18 18u --6 u C%sT 1920 --6 Ch C%sT 1936 Mar 1 2 --5 - EST 1936 N 15 2 --6 Ch C%sT 1942 --6 u C%sT 1946 --6 Ch C%sT 1967 --6 u C%sT -Z America/Chihuahua -7:4:20 - LMT 1922 Ja 1 7u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 - CST 1996 --6 m C%sT 1998 --6 - CST 1998 Ap Su>=1 3 --7 m M%sT 2022 O 30 2 --6 - CST -Z America/Ciudad_Juarez -7:5:56 - LMT 1922 Ja 1 7u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 - CST 1996 --6 m C%sT 1998 --6 - CST 1998 Ap Su>=1 3 --7 m M%sT 2010 --7 u M%sT 2022 O 30 2 --6 - CST 2022 N 30 --7 u M%sT -Z America/Costa_Rica -5:36:13 - LMT 1890 --5:36:13 - SJMT 1921 Ja 15 --6 CR C%sT -Z America/Coyhaique -4:48:16 - LMT 1890 --4:42:45 - SMT 1910 Ja 10 --5 - %z 1916 Jul --4:42:45 - SMT 1918 S 10 --4 - %z 1919 Jul --4:42:45 - SMT 1927 S --5 x %z 1932 S --4 - %z 1942 Jun --5 - %z 1942 Au --4 - %z 1946 Au 28 24 --5 1 %z 1947 Mar 31 24 --5 - %z 1947 May 21 23 --4 x %z 2025 Mar 20 --3 - %z -Z America/Cuiaba -3:44:20 - LMT 1914 --4 B %z 2003 S 24 --4 - %z 2004 O --4 B %z -Z America/Danmarkshavn -1:14:40 - LMT 1916 Jul 28 --3 - %z 1980 Ap 6 2 --3 E %z 1996 -0 - GMT -Z America/Dawson -9:17:40 - LMT 1900 Au 20 --9 Y Y%sT 1965 --9 Yu Y%sT 1973 O 28 --8 - PST 1980 --8 C P%sT 2020 N --7 - MST -Z America/Dawson_Creek -8:0:56 - LMT 1884 --8 C P%sT 1947 --8 Va P%sT 1972 Au 30 2 --7 - MST -Z America/Denver -6:59:56 - LMT 1883 N 18 19u --7 u M%sT 1920 --7 De M%sT 1942 --7 u M%sT 1946 --7 De M%sT 1967 --7 u M%sT -Z America/Detroit -5:32:11 - LMT 1905 --6 - CST 1915 May 15 2 --5 - EST 1942 --5 u E%sT 1946 --5 Dt E%sT 1967 Jun 14 0:1 --5 u E%sT 1969 --5 - EST 1973 --5 u E%sT 1975 --5 - EST 1975 Ap 27 2 --5 u E%sT -Z America/Edmonton -7:33:52 - LMT 1906 S --7 Ed M%sT 1987 --7 C M%sT -Z America/Eirunepe -4:39:28 - LMT 1914 --5 B %z 1988 S 12 --5 - %z 1993 S 28 --5 B %z 1994 S 22 --5 - %z 2008 Jun 24 --4 - %z 2013 N 10 --5 - %z -Z America/El_Salvador -5:56:48 - LMT 1921 --6 SV C%sT -Z America/Fort_Nelson -8:10:47 - LMT 1884 --8 Va P%sT 1946 --8 - PST 1947 --8 Va P%sT 1987 --8 C P%sT 2015 Mar 8 2 --7 - MST -Z America/Fortaleza -2:34 - LMT 1914 --3 B %z 1990 S 17 --3 - %z 1999 S 30 --3 B %z 2000 O 22 --3 - %z 2001 S 13 --3 B %z 2002 O --3 - %z -Z America/Glace_Bay -3:59:48 - LMT 1902 Jun 15 --4 C A%sT 1953 --4 H A%sT 1954 --4 - AST 1972 --4 H A%sT 1974 --4 C A%sT -Z America/Goose_Bay -4:1:40 - LMT 1884 --3:30:52 - NST 1918 --3:30:52 C N%sT 1919 --3:30:52 - NST 1935 Mar 30 --3:30 - NST 1936 --3:30 j N%sT 1942 May 11 --3:30 C N%sT 1946 --3:30 j N%sT 1966 Mar 15 2 --4 j A%sT 2011 N --4 C A%sT -Z America/Grand_Turk -4:44:32 - LMT 1890 --5:7:10 - KMT 1912 F --5 - EST 1979 --5 u E%sT 2015 Mar 8 2 --4 - AST 2018 Mar 11 3 --5 u E%sT -Z America/Guatemala -6:2:4 - LMT 1918 O 5 --6 GT C%sT -Z America/Guayaquil -5:19:20 - LMT 1890 --5:14 - QMT 1931 --5 EC %z -Z America/Guyana -3:52:39 - LMT 1911 Au --4 - %z 1915 Mar --3:45 - %z 1975 Au --3 - %z 1992 Mar 29 1 --4 - %z -Z America/Halifax -4:14:24 - LMT 1902 Jun 15 --4 H A%sT 1918 --4 C A%sT 1919 --4 H A%sT 1942 F 9 2s --4 C A%sT 1946 --4 H A%sT 1974 --4 C A%sT -Z America/Havana -5:29:28 - LMT 1890 --5:29:36 - HMT 1925 Jul 19 12 --5 Q C%sT -Z America/Hermosillo -7:23:52 - LMT 1922 Ja 1 7u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 - CST 1942 Ap 24 --7 - MST 1996 --7 m M%sT 1999 --7 - MST -Z America/Indiana/Indianapolis -5:44:38 - LMT 1883 N 18 18u --6 u C%sT 1920 --6 In C%sT 1942 --6 u C%sT 1946 --6 In C%sT 1955 Ap 24 2 --5 - EST 1957 S 29 2 --6 - CST 1958 Ap 27 2 --5 - EST 1969 --5 u E%sT 1971 --5 - EST 2006 --5 u E%sT -Z America/Indiana/Knox -5:46:30 - LMT 1883 N 18 18u --6 u C%sT 1947 --6 St C%sT 1962 Ap 29 2 --5 - EST 1963 O 27 2 --6 u C%sT 1991 O 27 2 --5 - EST 2006 Ap 2 2 --6 u C%sT -Z America/Indiana/Marengo -5:45:23 - LMT 1883 N 18 18u --6 u C%sT 1951 --6 Ma C%sT 1961 Ap 30 2 --5 - EST 1969 --5 u E%sT 1974 Ja 6 2 --6 1 CDT 1974 O 27 2 --5 u E%sT 1976 --5 - EST 2006 --5 u E%sT -Z America/Indiana/Petersburg -5:49:7 - LMT 1883 N 18 18u --6 u C%sT 1955 --6 Pi C%sT 1965 Ap 25 2 --5 - EST 1966 O 30 2 --6 u C%sT 1977 O 30 2 --5 - EST 2006 Ap 2 2 --6 u C%sT 2007 N 4 2 --5 u E%sT -Z America/Indiana/Tell_City -5:47:3 - LMT 1883 N 18 18u --6 u C%sT 1946 --6 Pe C%sT 1964 Ap 26 2 --5 - EST 1967 O 29 2 --6 u C%sT 1969 Ap 27 2 --5 u E%sT 1971 --5 - EST 2006 Ap 2 2 --6 u C%sT -Z America/Indiana/Vevay -5:40:16 - LMT 1883 N 18 18u --6 u C%sT 1954 Ap 25 2 --5 - EST 1969 --5 u E%sT 1973 --5 - EST 2006 --5 u E%sT -Z America/Indiana/Vincennes -5:50:7 - LMT 1883 N 18 18u --6 u C%sT 1946 --6 V C%sT 1964 Ap 26 2 --5 - EST 1969 --5 u E%sT 1971 --5 - EST 2006 Ap 2 2 --6 u C%sT 2007 N 4 2 --5 u E%sT -Z America/Indiana/Winamac -5:46:25 - LMT 1883 N 18 18u --6 u C%sT 1946 --6 Pu C%sT 1961 Ap 30 2 --5 - EST 1969 --5 u E%sT 1971 --5 - EST 2006 Ap 2 2 --6 u C%sT 2007 Mar 11 2 --5 u E%sT -Z America/Inuvik 0 - -00 1953 --8 Y P%sT 1979 Ap lastSu 2 --7 Y M%sT 1980 --7 C M%sT -Z America/Iqaluit 0 - -00 1942 Au --5 Y E%sT 1999 O 31 2 --6 C C%sT 2000 O 29 2 --5 C E%sT -Z America/Jamaica -5:7:10 - LMT 1890 --5:7:10 - KMT 1912 F --5 - EST 1974 --5 u E%sT 1984 --5 - EST -Z America/Juneau 15:2:19 - LMT 1867 O 19 15:33:32 --8:57:41 - LMT 1900 Au 20 12 --8 - PST 1942 --8 u P%sT 1946 --8 - PST 1969 --8 u P%sT 1980 Ap 27 2 --9 u Y%sT 1980 O 26 2 --8 u P%sT 1983 O 30 2 --9 u Y%sT 1983 N 30 --9 u AK%sT -Z America/Kentucky/Louisville -5:43:2 - LMT 1883 N 18 18u --6 u C%sT 1921 --6 v C%sT 1942 --6 u C%sT 1946 --6 v C%sT 1961 Jul 23 2 --5 - EST 1968 --5 u E%sT 1974 Ja 6 2 --6 1 CDT 1974 O 27 2 --5 u E%sT -Z America/Kentucky/Monticello -5:39:24 - LMT 1883 N 18 18u --6 u C%sT 1946 --6 - CST 1968 --6 u C%sT 2000 O 29 2 --5 u E%sT -Z America/La_Paz -4:32:36 - LMT 1890 --4:32:36 - CMT 1931 O 15 --4:32:36 1 BST 1932 Mar 21 --4 - %z -Z America/Lima -5:8:12 - LMT 1890 --5:8:36 - LMT 1908 Jul 28 --5 PE %z -Z America/Los_Angeles -7:52:58 - LMT 1883 N 18 20u --8 u P%sT 1946 --8 CA P%sT 1967 --8 u P%sT -Z America/Maceio -2:22:52 - LMT 1914 --3 B %z 1990 S 17 --3 - %z 1995 O 13 --3 B %z 1996 S 4 --3 - %z 1999 S 30 --3 B %z 2000 O 22 --3 - %z 2001 S 13 --3 B %z 2002 O --3 - %z -Z America/Managua -5:45:8 - LMT 1890 --5:45:12 - MMT 1934 Jun 23 --6 - CST 1973 May --5 - EST 1975 F 16 --6 NI C%sT 1992 Ja 1 4 --5 - EST 1992 S 24 --6 - CST 1993 --5 - EST 1997 --6 NI C%sT -Z America/Manaus -4:0:4 - LMT 1914 --4 B %z 1988 S 12 --4 - %z 1993 S 28 --4 B %z 1994 S 22 --4 - %z -Z America/Martinique -4:4:20 - LMT 1890 --4:4:20 - FFMT 1911 May --4 - AST 1980 Ap 6 --4 1 ADT 1980 S 28 --4 - AST -Z America/Matamoros -6:30 - LMT 1922 Ja 1 6u --6 - CST 1988 --6 u C%sT 1989 --6 m C%sT 2010 --6 u C%sT -Z America/Mazatlan -7:5:40 - LMT 1922 Ja 1 7u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 - CST 1942 Ap 24 --7 - MST 1970 --7 m M%sT -Z America/Menominee -5:50:27 - LMT 1885 S 18 12 --6 u C%sT 1946 --6 Me C%sT 1969 Ap 27 2 --5 - EST 1973 Ap 29 2 --6 u C%sT -Z America/Merida -5:58:28 - LMT 1922 Ja 1 6u --6 - CST 1981 D 26 2 --5 - EST 1982 N 2 2 --6 m C%sT -Z America/Metlakatla 15:13:42 - LMT 1867 O 19 15:44:55 --8:46:18 - LMT 1900 Au 20 12 --8 - PST 1942 --8 u P%sT 1946 --8 - PST 1969 --8 u P%sT 1983 O 30 2 --8 - PST 2015 N 1 2 --9 u AK%sT 2018 N 4 2 --8 - PST 2019 Ja 20 2 --9 u AK%sT -Z America/Mexico_City -6:36:36 - LMT 1922 Ja 1 7u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 m C%sT 2001 S 30 2 --6 - CST 2002 F 20 --6 m C%sT -Z America/Miquelon -3:44:40 - LMT 1911 Jun 15 --4 - AST 1980 May --3 - %z 1987 --3 C %z -Z America/Moncton -4:19:8 - LMT 1883 D 9 --5 - EST 1902 Jun 15 --4 C A%sT 1933 --4 o A%sT 1942 --4 C A%sT 1946 --4 o A%sT 1973 --4 C A%sT 1993 --4 o A%sT 2007 --4 C A%sT -Z America/Monterrey -6:41:16 - LMT 1922 Ja 1 6u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 - CST 1988 --6 u C%sT 1989 --6 m C%sT -Z America/Montevideo -3:44:51 - LMT 1908 Jun 10 --3:44:51 - MMT 1920 May --4 - %z 1923 O --3:30 U %z 1942 D 14 --3 U %z 1960 --3 U %z 1968 --3 U %z 1970 --3 U %z 1974 --3 U %z 1974 Mar 10 --3 U %z 1974 D 22 --3 U %z -Z America/New_York -4:56:2 - LMT 1883 N 18 17u --5 u E%sT 1920 --5 NY E%sT 1942 --5 u E%sT 1946 --5 NY E%sT 1967 --5 u E%sT -Z America/Nome 12:58:22 - LMT 1867 O 19 13:29:35 --11:1:38 - LMT 1900 Au 20 12 --11 - NST 1942 --11 u N%sT 1946 --11 - NST 1967 Ap --11 - BST 1969 --11 u B%sT 1983 O 30 2 --9 u Y%sT 1983 N 30 --9 u AK%sT -Z America/Noronha -2:9:40 - LMT 1914 --2 B %z 1990 S 17 --2 - %z 1999 S 30 --2 B %z 2000 O 15 --2 - %z 2001 S 13 --2 B %z 2002 O --2 - %z -Z America/North_Dakota/Beulah -6:47:7 - LMT 1883 N 18 19u --7 u M%sT 2010 N 7 2 --6 u C%sT -Z America/North_Dakota/Center -6:45:12 - LMT 1883 N 18 19u --7 u M%sT 1992 O 25 2 --6 u C%sT -Z America/North_Dakota/New_Salem -6:45:39 - LMT 1883 N 18 19u --7 u M%sT 2003 O 26 2 --6 u C%sT -Z America/Nuuk -3:26:56 - LMT 1916 Jul 28 --3 - %z 1980 Ap 6 2 --3 E %z 2023 Mar 26 1u --2 - %z 2023 O 29 1u --2 E %z -Z America/Ojinaga -6:57:40 - LMT 1922 Ja 1 7u --7 - MST 1927 Jun 10 --6 - CST 1930 N 15 --7 m M%sT 1932 Ap --6 - CST 1996 --6 m C%sT 1998 --6 - CST 1998 Ap Su>=1 3 --7 m M%sT 2010 --7 u M%sT 2022 O 30 2 --6 - CST 2022 N 30 --6 u C%sT -Z America/Panama -5:18:8 - LMT 1890 --5:19:36 - CMT 1908 Ap 22 --5 - EST -Z America/Paramaribo -3:40:40 - LMT 1911 --3:40:52 - PMT 1935 --3:40:36 - PMT 1945 O --3:30 - %z 1984 O --3 - %z -Z America/Phoenix -7:28:18 - LMT 1883 N 18 19u --7 u M%sT 1944 Ja 1 0:1 --7 - MST 1944 Ap 1 0:1 --7 u M%sT 1944 O 1 0:1 --7 - MST 1967 --7 u M%sT 1968 Mar 21 --7 - MST -Z America/Port-au-Prince -4:49:20 - LMT 1890 --4:49 - PPMT 1917 Ja 24 12 --5 HT E%sT -Z America/Porto_Velho -4:15:36 - LMT 1914 --4 B %z 1988 S 12 --4 - %z -Z America/Puerto_Rico -4:24:25 - LMT 1899 Mar 28 12 --4 - AST 1942 May 3 --4 u A%sT 1946 --4 - AST -Z America/Punta_Arenas -4:43:40 - LMT 1890 --4:42:45 - SMT 1910 Ja 10 --5 - %z 1916 Jul --4:42:45 - SMT 1918 S 10 --4 - %z 1919 Jul --4:42:45 - SMT 1927 S --5 x %z 1932 S --4 - %z 1942 Jun --5 - %z 1942 Au --4 - %z 1946 Au 28 24 --5 1 %z 1947 Mar 31 24 --5 - %z 1947 May 21 23 --4 x %z 2016 D 4 --3 - %z -Z America/Rankin_Inlet 0 - -00 1957 --6 Y C%sT 2000 O 29 2 --5 - EST 2001 Ap 1 3 --6 C C%sT -Z America/Recife -2:19:36 - LMT 1914 --3 B %z 1990 S 17 --3 - %z 1999 S 30 --3 B %z 2000 O 15 --3 - %z 2001 S 13 --3 B %z 2002 O --3 - %z -Z America/Regina -6:58:36 - LMT 1905 S --7 r M%sT 1960 Ap lastSu 2 --6 - CST -Z America/Resolute 0 - -00 1947 Au 31 --6 Y C%sT 2000 O 29 2 --5 - EST 2001 Ap 1 3 --6 C C%sT 2006 O 29 2 --5 - EST 2007 Mar 11 3 --6 C C%sT -Z America/Rio_Branco -4:31:12 - LMT 1914 --5 B %z 1988 S 12 --5 - %z 2008 Jun 24 --4 - %z 2013 N 10 --5 - %z -Z America/Santarem -3:38:48 - LMT 1914 --4 B %z 1988 S 12 --4 - %z 2008 Jun 24 --3 - %z -Z America/Santiago -4:42:45 - LMT 1890 --4:42:45 - SMT 1910 Ja 10 --5 - %z 1916 Jul --4:42:45 - SMT 1918 S 10 --4 - %z 1919 Jul --4:42:45 - SMT 1927 S --5 x %z 1932 S --4 - %z 1942 Jun --5 - %z 1942 Au --4 - %z 1946 Jul 14 24 --4 1 %z 1946 Au 28 24 --5 1 %z 1947 Mar 31 24 --5 - %z 1947 May 21 23 --4 x %z -Z America/Santo_Domingo -4:39:36 - LMT 1890 --4:40 - SDMT 1933 Ap 1 12 --5 DO %s 1974 O 27 --4 - AST 2000 O 29 2 --5 u E%sT 2000 D 3 1 --4 - AST -Z America/Sao_Paulo -3:6:28 - LMT 1914 --3 B %z 1963 O 23 --3 1 %z 1964 --3 B %z -Z America/Scoresbysund -1:27:52 - LMT 1916 Jul 28 --2 - %z 1980 Ap 6 2 --2 c %z 1981 Mar 29 --1 E %z 2024 Mar 31 --2 E %z -Z America/Sitka 14:58:47 - LMT 1867 O 19 15:30 --9:1:13 - LMT 1900 Au 20 12 --8 - PST 1942 --8 u P%sT 1946 --8 - PST 1969 --8 u P%sT 1983 O 30 2 --9 u Y%sT 1983 N 30 --9 u AK%sT -Z America/St_Johns -3:30:52 - LMT 1884 --3:30:52 j N%sT 1918 --3:30:52 C N%sT 1919 --3:30:52 j N%sT 1935 Mar 30 --3:30 j N%sT 1942 May 11 --3:30 C N%sT 1946 --3:30 j N%sT 2011 N --3:30 C N%sT -Z America/Swift_Current -7:11:20 - LMT 1905 S --7 C M%sT 1946 Ap lastSu 2 --7 r M%sT 1950 --7 Sw M%sT 1972 Ap lastSu 2 --6 - CST -Z America/Tegucigalpa -5:48:52 - LMT 1921 Ap --6 HN C%sT -Z America/Thule -4:35:8 - LMT 1916 Jul 28 --4 Th A%sT -Z America/Tijuana -7:48:4 - LMT 1922 Ja 1 7u --7 - MST 1924 --8 - PST 1927 Jun 10 --7 - MST 1930 N 15 --8 - PST 1931 Ap --8 1 PDT 1931 S 30 --8 - PST 1942 Ap 24 --8 1 PWT 1945 Au 14 23u --8 1 PPT 1945 N 15 --8 - PST 1948 Ap 5 --8 1 PDT 1949 Ja 14 --8 - PST 1950 May --8 1 PDT 1950 S 24 --8 - PST 1951 Ap 29 2 --8 1 PDT 1951 S 30 2 --8 - PST 1952 Ap 27 2 --8 1 PDT 1952 S 28 2 --8 - PST 1954 --8 CA P%sT 1961 --8 - PST 1976 --8 u P%sT 1996 --8 m P%sT 2001 --8 u P%sT 2002 F 20 --8 m P%sT 2010 --8 u P%sT -Z America/Toronto -5:17:32 - LMT 1895 --5 C E%sT 1919 --5 t E%sT 1942 F 9 2s --5 C E%sT 1946 --5 t E%sT 1974 --5 C E%sT -Z America/Vancouver -8:12:28 - LMT 1884 --8 Va P%sT 1987 --8 C P%sT -Z America/Whitehorse -9:0:12 - LMT 1900 Au 20 --9 Y Y%sT 1965 --9 Yu Y%sT 1966 F 27 --8 - PST 1980 --8 C P%sT 2020 N --7 - MST -Z America/Winnipeg -6:28:36 - LMT 1887 Jul 16 --6 W C%sT 2006 --6 C C%sT -Z America/Yakutat 14:41:5 - LMT 1867 O 19 15:12:18 --9:18:55 - LMT 1900 Au 20 12 --9 - YST 1942 --9 u Y%sT 1946 --9 - YST 1969 --9 u Y%sT 1983 N 30 --9 u AK%sT -Z Antarctica/Casey 0 - -00 1969 -8 - %z 2009 O 18 2 -11 - %z 2010 Mar 5 2 -8 - %z 2011 O 28 2 -11 - %z 2012 F 21 17u -8 - %z 2016 O 22 -11 - %z 2018 Mar 11 4 -8 - %z 2018 O 7 4 -11 - %z 2019 Mar 17 3 -8 - %z 2019 O 4 3 -11 - %z 2020 Mar 8 3 -8 - %z 2020 O 4 0:1 -11 - %z 2021 Mar 14 -8 - %z 2021 O 3 0:1 -11 - %z 2022 Mar 13 -8 - %z 2022 O 2 0:1 -11 - %z 2023 Mar 9 3 -8 - %z -Z Antarctica/Davis 0 - -00 1957 Ja 13 -7 - %z 1964 N -0 - -00 1969 F -7 - %z 2009 O 18 2 -5 - %z 2010 Mar 10 20u -7 - %z 2011 O 28 2 -5 - %z 2012 F 21 20u -7 - %z -Z Antarctica/Macquarie 0 - -00 1899 N -10 - AEST 1916 O 1 2 -10 1 AEDT 1917 F -10 AU AE%sT 1919 Ap 1 0s -0 - -00 1948 Mar 25 -10 AU AE%sT 1967 -10 AT AE%sT 2010 -10 1 AEDT 2011 -10 AT AE%sT -Z Antarctica/Mawson 0 - -00 1954 F 13 -6 - %z 2009 O 18 2 -5 - %z -Z Antarctica/Palmer 0 - -00 1965 --4 A %z 1969 O 5 --3 A %z 1982 May --4 x %z 2016 D 4 --3 - %z -Z Antarctica/Rothera 0 - -00 1976 D --3 - %z -Z Antarctica/Troll 0 - -00 2005 F 12 -0 Tr %s -Z Antarctica/Vostok 0 - -00 1957 D 16 -7 - %z 1994 F -0 - -00 1994 N -7 - %z 2023 D 18 2 -5 - %z -Z Asia/Almaty 5:7:48 - LMT 1924 May 2 -5 - %z 1930 Jun 21 -6 R %z 1991 Mar 31 2s -5 R %z 1992 Ja 19 2s -6 R %z 2004 O 31 2s -6 - %z 2024 Mar -5 - %z -Z Asia/Amman 2:23:44 - LMT 1931 -2 J EE%sT 2022 O 28 0s -3 - %z -Z Asia/Anadyr 11:49:56 - LMT 1924 May 2 -12 - %z 1930 Jun 21 -13 R %z 1982 Ap 1 0s -12 R %z 1991 Mar 31 2s -11 R %z 1992 Ja 19 2s -12 R %z 2010 Mar 28 2s -11 R %z 2011 Mar 27 2s -12 - %z -Z Asia/Aqtau 3:21:4 - LMT 1924 May 2 -4 - %z 1930 Jun 21 -5 - %z 1981 O -6 - %z 1982 Ap -5 R %z 1991 Mar 31 2s -4 R %z 1992 Ja 19 2s -5 R %z 1994 S 25 2s -4 R %z 2004 O 31 2s -5 - %z -Z Asia/Aqtobe 3:48:40 - LMT 1924 May 2 -4 - %z 1930 Jun 21 -5 - %z 1981 Ap -5 1 %z 1981 O -6 - %z 1982 Ap -5 R %z 1991 Mar 31 2s -4 R %z 1992 Ja 19 2s -5 R %z 2004 O 31 2s -5 - %z -Z Asia/Ashgabat 3:53:32 - LMT 1924 May 2 -4 - %z 1930 Jun 21 -5 R %z 1991 Mar 31 2 -4 R %z 1992 Ja 19 2 -5 - %z -Z Asia/Atyrau 3:27:44 - LMT 1924 May 2 -3 - %z 1930 Jun 21 -5 - %z 1981 O -6 - %z 1982 Ap -5 R %z 1991 Mar 31 2s -4 R %z 1992 Ja 19 2s -5 R %z 1999 Mar 28 2s -4 R %z 2004 O 31 2s -5 - %z -Z Asia/Baghdad 2:57:40 - LMT 1890 -2:57:36 - BMT 1918 -3 - %z 1982 May -3 IQ %z -Z Asia/Baku 3:19:24 - LMT 1924 May 2 -3 - %z 1957 Mar -4 R %z 1991 Mar 31 2s -3 R %z 1992 S lastSu 2s -4 - %z 1996 -4 E %z 1997 -4 AZ %z -Z Asia/Bangkok 6:42:4 - LMT 1880 -6:42:4 - BMT 1920 Ap -7 - %z -Z Asia/Barnaul 5:35 - LMT 1919 D 10 -6 - %z 1930 Jun 21 -7 R %z 1991 Mar 31 2s -6 R %z 1992 Ja 19 2s -7 R %z 1995 May 28 -6 R %z 2011 Mar 27 2s -7 - %z 2014 O 26 2s -6 - %z 2016 Mar 27 2s -7 - %z -Z Asia/Beirut 2:22 - LMT 1880 -2 l EE%sT -Z Asia/Bishkek 4:58:24 - LMT 1924 May 2 -5 - %z 1930 Jun 21 -6 R %z 1991 Mar 31 2s -5 R %z 1991 Au 31 2 -5 KG %z 2005 Au 12 -6 - %z -Z Asia/Chita 7:33:52 - LMT 1919 D 15 -8 - %z 1930 Jun 21 -9 R %z 1991 Mar 31 2s -8 R %z 1992 Ja 19 2s -9 R %z 2011 Mar 27 2s -10 - %z 2014 O 26 2s -8 - %z 2016 Mar 27 2 -9 - %z -Z Asia/Colombo 5:19:24 - LMT 1880 -5:19:32 - MMT 1906 -5:30 - %z 1942 Ja 5 -5:30 0:30 %z 1942 S -5:30 1 %z 1945 O 16 2 -5:30 - %z 1996 May 25 -6:30 - %z 1996 O 26 0:30 -6 - %z 2006 Ap 15 0:30 -5:30 - %z -Z Asia/Damascus 2:25:12 - LMT 1920 -2 S EE%sT 2022 O 28 -3 - %z -Z Asia/Dhaka 6:1:40 - LMT 1890 -5:53:20 - HMT 1941 O -6:30 - %z 1942 May 15 -5:30 - %z 1942 S -6:30 - %z 1951 S 30 -6 - %z 2009 -6 BD %z -Z Asia/Dili 8:22:20 - LMT 1911 D 31 16u -8 - %z 1942 F 21 23 -9 - %z 1976 May 3 -8 - %z 2000 S 17 -9 - %z -Z Asia/Dubai 3:41:12 - LMT 1920 -4 - %z -Z Asia/Dushanbe 4:35:12 - LMT 1924 May 2 -5 - %z 1930 Jun 21 -6 R %z 1991 Mar 31 2s -5 1 %z 1991 S 9 2s -5 - %z -Z Asia/Famagusta 2:15:48 - LMT 1921 N 14 -2 CY EE%sT 1998 S -2 E EE%sT 2016 S 8 -3 - %z 2017 O 29 1u -2 E EE%sT -Z Asia/Gaza 2:17:52 - LMT 1900 O -2 Z EET/EEST 1948 May 15 -2 K EE%sT 1967 Jun 5 -2 Z I%sT 1996 -2 J EE%sT 1999 -2 P EE%sT 2008 Au 29 -2 - EET 2008 S -2 P EE%sT 2010 -2 - EET 2010 Mar 27 0:1 -2 P EE%sT 2011 Au -2 - EET 2012 -2 P EE%sT -Z Asia/Hebron 2:20:23 - LMT 1900 O -2 Z EET/EEST 1948 May 15 -2 K EE%sT 1967 Jun 5 -2 Z I%sT 1996 -2 J EE%sT 1999 -2 P EE%sT -Z Asia/Ho_Chi_Minh 7:6:30 - LMT 1906 Jul -7:6:30 - PLMT 1911 May -7 - %z 1942 D 31 23 -8 - %z 1945 Mar 14 23 -9 - %z 1945 S 1 24 -7 - %z 1947 Ap -8 - %z 1955 Jul 1 1 -7 - %z 1959 D 31 23 -8 - %z 1975 Jun 13 -7 - %z -Z Asia/Hong_Kong 7:36:42 - LMT 1904 O 29 17u -8 - HKT 1941 Jun 15 3 -8 1 HKST 1941 O 1 4 -8 0:30 HKWT 1941 D 25 -9 - JST 1945 N 18 2 -8 HK HK%sT -Z Asia/Hovd 6:6:36 - LMT 1905 Au -6 - %z 1978 -7 X %z -Z Asia/Irkutsk 6:57:5 - LMT 1880 -6:57:5 - IMT 1920 Ja 25 -7 - %z 1930 Jun 21 -8 R %z 1991 Mar 31 2s -7 R %z 1992 Ja 19 2s -8 R %z 2011 Mar 27 2s -9 - %z 2014 O 26 2s -8 - %z -Z Asia/Jakarta 7:7:12 - LMT 1867 Au 10 -7:7:12 - BMT 1923 D 31 16:40u -7:20 - %z 1932 N -7:30 - %z 1942 Mar 23 -9 - %z 1945 S 23 -7:30 - %z 1948 May -8 - %z 1950 May -7:30 - %z 1964 -7 - WIB -Z Asia/Jayapura 9:22:48 - LMT 1932 N -9 - %z 1944 S -9:30 - %z 1964 -9 - WIT -Z Asia/Jerusalem 2:20:54 - LMT 1880 -2:20:40 - JMT 1918 -2 Z I%sT -Z Asia/Kabul 4:36:48 - LMT 1890 -4 - %z 1945 -4:30 - %z -Z Asia/Kamchatka 10:34:36 - LMT 1922 N 10 -11 - %z 1930 Jun 21 -12 R %z 1991 Mar 31 2s -11 R %z 1992 Ja 19 2s -12 R %z 2010 Mar 28 2s -11 R %z 2011 Mar 27 2s -12 - %z -Z Asia/Karachi 4:28:12 - LMT 1907 -5:30 - %z 1942 S -5:30 1 %z 1945 O 15 -5:30 - %z 1951 S 30 -5 - %z 1971 Mar 26 -5 PK PK%sT -Z Asia/Kathmandu 5:41:16 - LMT 1920 -5:30 - %z 1986 -5:45 - %z -Z Asia/Khandyga 9:2:13 - LMT 1919 D 15 -8 - %z 1930 Jun 21 -9 R %z 1991 Mar 31 2s -8 R %z 1992 Ja 19 2s -9 R %z 2004 -10 R %z 2011 Mar 27 2s -11 - %z 2011 S 13 0s -10 - %z 2014 O 26 2s -9 - %z -Z Asia/Kolkata 5:53:28 - LMT 1854 Jun 28 -5:53:20 - HMT 1870 -5:21:10 - MMT 1906 -5:30 - IST 1941 O -5:30 1 %z 1942 May 15 -5:30 - IST 1942 S -5:30 1 %z 1945 O 15 -5:30 - IST -Z Asia/Krasnoyarsk 6:11:26 - LMT 1920 Ja 6 -6 - %z 1930 Jun 21 -7 R %z 1991 Mar 31 2s -6 R %z 1992 Ja 19 2s -7 R %z 2011 Mar 27 2s -8 - %z 2014 O 26 2s -7 - %z -Z Asia/Kuching 7:21:20 - LMT 1926 Mar -7:30 - %z 1933 -8 NB %z 1942 F 16 -9 - %z 1945 S 12 -8 - %z -Z Asia/Macau 7:34:10 - LMT 1904 O 30 -8 - CST 1941 D 21 23 -9 _ %z 1945 S 30 24 -8 _ C%sT -Z Asia/Magadan 10:3:12 - LMT 1924 May 2 -10 - %z 1930 Jun 21 -11 R %z 1991 Mar 31 2s -10 R %z 1992 Ja 19 2s -11 R %z 2011 Mar 27 2s -12 - %z 2014 O 26 2s -10 - %z 2016 Ap 24 2s -11 - %z -Z Asia/Makassar 7:57:36 - LMT 1920 -7:57:36 - MMT 1932 N -8 - %z 1942 F 9 -9 - %z 1945 S 23 -8 - WITA -Z Asia/Manila -15:56:8 - LMT 1844 D 31 -8:3:52 - LMT 1899 S 6 4u -8 PH P%sT 1942 F 11 24 -9 - JST 1945 Mar 4 -8 PH P%sT -Z Asia/Nicosia 2:13:28 - LMT 1921 N 14 -2 CY EE%sT 1998 S -2 E EE%sT -Z Asia/Novokuznetsk 5:48:48 - LMT 1924 May -6 - %z 1930 Jun 21 -7 R %z 1991 Mar 31 2s -6 R %z 1992 Ja 19 2s -7 R %z 2010 Mar 28 2s -6 R %z 2011 Mar 27 2s -7 - %z -Z Asia/Novosibirsk 5:31:40 - LMT 1919 D 14 6 -6 - %z 1930 Jun 21 -7 R %z 1991 Mar 31 2s -6 R %z 1992 Ja 19 2s -7 R %z 1993 May 23 -6 R %z 2011 Mar 27 2s -7 - %z 2014 O 26 2s -6 - %z 2016 Jul 24 2s -7 - %z -Z Asia/Omsk 4:53:30 - LMT 1919 N 14 -5 - %z 1930 Jun 21 -6 R %z 1991 Mar 31 2s -5 R %z 1992 Ja 19 2s -6 R %z 2011 Mar 27 2s -7 - %z 2014 O 26 2s -6 - %z -Z Asia/Oral 3:25:24 - LMT 1924 May 2 -3 - %z 1930 Jun 21 -5 - %z 1981 Ap -5 1 %z 1981 O -6 - %z 1982 Ap -5 R %z 1989 Mar 26 2s -4 R %z 1992 Ja 19 2s -5 R %z 1992 Mar 29 2s -4 R %z 2004 O 31 2s -5 - %z -Z Asia/Pontianak 7:17:20 - LMT 1908 May -7:17:20 - PMT 1932 N -7:30 - %z 1942 Ja 29 -9 - %z 1945 S 23 -7:30 - %z 1948 May -8 - %z 1950 May -7:30 - %z 1964 -8 - WITA 1988 -7 - WIB -Z Asia/Pyongyang 8:23 - LMT 1908 Ap -8:30 - KST 1912 -9 - JST 1945 Au 24 -9 - KST 2015 Au 15 -8:30 - KST 2018 May 4 23:30 -9 - KST -Z Asia/Qatar 3:26:8 - LMT 1920 -4 - %z 1972 Jun -3 - %z -Z Asia/Qostanay 4:14:28 - LMT 1924 May 2 -4 - %z 1930 Jun 21 -5 - %z 1981 Ap -5 1 %z 1981 O -6 - %z 1982 Ap -5 R %z 1991 Mar 31 2s -4 R %z 1992 Ja 19 2s -5 R %z 2004 O 31 2s -6 - %z 2024 Mar -5 - %z -Z Asia/Qyzylorda 4:21:52 - LMT 1924 May 2 -4 - %z 1930 Jun 21 -5 - %z 1981 Ap -5 1 %z 1981 O -6 - %z 1982 Ap -5 R %z 1991 Mar 31 2s -4 R %z 1991 S 29 2s -5 R %z 1992 Ja 19 2s -6 R %z 1992 Mar 29 2s -5 R %z 2004 O 31 2s -6 - %z 2018 D 21 -5 - %z -Z Asia/Riyadh 3:6:52 - LMT 1947 Mar 14 -3 - %z -Z Asia/Sakhalin 9:30:48 - LMT 1905 Au 23 -9 - %z 1945 Au 25 -11 R %z 1991 Mar 31 2s -10 R %z 1992 Ja 19 2s -11 R %z 1997 Mar lastSu 2s -10 R %z 2011 Mar 27 2s -11 - %z 2014 O 26 2s -10 - %z 2016 Mar 27 2s -11 - %z -Z Asia/Samarkand 4:27:53 - LMT 1924 May 2 -4 - %z 1930 Jun 21 -5 - %z 1981 Ap -5 1 %z 1981 O -6 - %z 1982 Ap -5 R %z 1992 -5 - %z -Z Asia/Seoul 8:27:52 - LMT 1908 Ap -8:30 - KST 1912 -9 - JST 1945 S 8 -9 KR K%sT 1954 Mar 21 -8:30 KR K%sT 1961 Au 10 -9 KR K%sT -Z Asia/Shanghai 8:5:43 - LMT 1901 -8 Sh C%sT 1949 May 28 -8 CN C%sT -Z Asia/Singapore 6:55:25 - LMT 1901 -6:55:25 - SMT 1905 Jun -7 - %z 1933 -7 0:20 %z 1936 -7:20 - %z 1941 S -7:30 - %z 1942 F 16 -9 - %z 1945 S 12 -7:30 - %z 1981 D 31 16u -8 - %z -Z Asia/Srednekolymsk 10:14:52 - LMT 1924 May 2 -10 - %z 1930 Jun 21 -11 R %z 1991 Mar 31 2s -10 R %z 1992 Ja 19 2s -11 R %z 2011 Mar 27 2s -12 - %z 2014 O 26 2s -11 - %z -Z Asia/Taipei 8:6 - LMT 1896 -8 - CST 1937 O -9 - JST 1945 S 21 1 -8 f C%sT -Z Asia/Tashkent 4:37:11 - LMT 1924 May 2 -5 - %z 1930 Jun 21 -6 R %z 1991 Mar 31 2 -5 R %z 1992 -5 - %z -Z Asia/Tbilisi 2:59:11 - LMT 1880 -2:59:11 - TBMT 1924 May 2 -3 - %z 1957 Mar -4 R %z 1991 Mar 31 2s -3 R %z 1992 -3 e %z 1994 S lastSu -4 e %z 1996 O lastSu -4 1 %z 1997 Mar lastSu -4 e %z 2004 Jun 27 -3 R %z 2005 Mar lastSu 2 -4 - %z -Z Asia/Tehran 3:25:44 - LMT 1916 -3:25:44 - TMT 1935 Jun 13 -3:30 i %z 1977 O 20 24 -4 i %z 1978 N 10 24 -3:30 i %z -Z Asia/Thimphu 5:58:36 - LMT 1947 Au 15 -5:30 - %z 1987 O -6 - %z -Z Asia/Tokyo 9:18:59 - LMT 1887 D 31 15u -9 JP J%sT -Z Asia/Tomsk 5:39:51 - LMT 1919 D 22 -6 - %z 1930 Jun 21 -7 R %z 1991 Mar 31 2s -6 R %z 1992 Ja 19 2s -7 R %z 2002 May 1 3 -6 R %z 2011 Mar 27 2s -7 - %z 2014 O 26 2s -6 - %z 2016 May 29 2s -7 - %z -Z Asia/Ulaanbaatar 7:7:32 - LMT 1905 Au -7 - %z 1978 -8 X %z -Z Asia/Urumqi 5:50:20 - LMT 1928 -6 - %z -Z Asia/Ust-Nera 9:32:54 - LMT 1919 D 15 -8 - %z 1930 Jun 21 -9 R %z 1981 Ap -11 R %z 1991 Mar 31 2s -10 R %z 1992 Ja 19 2s -11 R %z 2011 Mar 27 2s -12 - %z 2011 S 13 0s -11 - %z 2014 O 26 2s -10 - %z -Z Asia/Vladivostok 8:47:31 - LMT 1922 N 15 -9 - %z 1930 Jun 21 -10 R %z 1991 Mar 31 2s -9 R %z 1992 Ja 19 2s -10 R %z 2011 Mar 27 2s -11 - %z 2014 O 26 2s -10 - %z -Z Asia/Yakutsk 8:38:58 - LMT 1919 D 15 -8 - %z 1930 Jun 21 -9 R %z 1991 Mar 31 2s -8 R %z 1992 Ja 19 2s -9 R %z 2011 Mar 27 2s -10 - %z 2014 O 26 2s -9 - %z -Z Asia/Yangon 6:24:47 - LMT 1880 -6:24:47 - RMT 1920 -6:30 - %z 1942 May -9 - %z 1945 May 3 -6:30 - %z -Z Asia/Yekaterinburg 4:2:33 - LMT 1916 Jul 3 -3:45:5 - PMT 1919 Jul 15 4 -4 - %z 1930 Jun 21 -5 R %z 1991 Mar 31 2s -4 R %z 1992 Ja 19 2s -5 R %z 2011 Mar 27 2s -6 - %z 2014 O 26 2s -5 - %z -Z Asia/Yerevan 2:58 - LMT 1924 May 2 -3 - %z 1957 Mar -4 R %z 1991 Mar 31 2s -3 R %z 1995 S 24 2s -4 - %z 1997 -4 R %z 2011 -4 AM %z -Z Atlantic/Azores -1:42:40 - LMT 1884 --1:54:32 - HMT 1912 Ja 1 2u --2 p %z 1966 O 2 2s --1 - %z 1982 Mar 28 0s --1 p %z 1986 --1 E %z 1992 D 27 1s -0 E WE%sT 1993 Jun 17 1u --1 E %z -Z Atlantic/Bermuda -4:19:18 - LMT 1890 --4:19:18 Be BMT/BST 1930 Ja 1 2 --4 Be A%sT 1974 Ap 28 2 --4 C A%sT 1976 --4 u A%sT -Z Atlantic/Canary -1:1:36 - LMT 1922 Mar --1 - %z 1946 S 30 1 -0 - WET 1980 Ap 6 0s -0 1 WEST 1980 S 28 1u -0 E WE%sT -Z Atlantic/Cape_Verde -1:34:4 - LMT 1912 Ja 1 2u --2 - %z 1942 S --2 1 %z 1945 O 15 --2 - %z 1975 N 25 2 --1 - %z -Z Atlantic/Faroe -0:27:4 - LMT 1908 Ja 11 -0 - WET 1981 -0 E WE%sT -Z Atlantic/Madeira -1:7:36 - LMT 1884 --1:7:36 - FMT 1912 Ja 1 1u --1 p %z 1966 O 2 2s -0 - WET 1982 Ap 4 -0 p WE%sT 1986 Jul 31 -0 E WE%sT -Z Atlantic/South_Georgia -2:26:8 - LMT 1890 --2 - %z -Z Atlantic/Stanley -3:51:24 - LMT 1890 --3:51:24 - SMT 1912 Mar 12 --4 FK %z 1983 May --3 FK %z 1985 S 15 --4 FK %z 2010 S 5 2 --3 - %z -Z Australia/Adelaide 9:14:20 - LMT 1895 F -9 - ACST 1899 May -9:30 AU AC%sT 1971 -9:30 AS AC%sT -Z Australia/Brisbane 10:12:8 - LMT 1895 -10 AU AE%sT 1971 -10 AQ AE%sT -Z Australia/Broken_Hill 9:25:48 - LMT 1895 F -10 - AEST 1896 Au 23 -9 - ACST 1899 May -9:30 AU AC%sT 1971 -9:30 AN AC%sT 2000 -9:30 AS AC%sT -Z Australia/Darwin 8:43:20 - LMT 1895 F -9 - ACST 1899 May -9:30 AU AC%sT -Z Australia/Eucla 8:35:28 - LMT 1895 D -8:45 AU %z 1943 Jul -8:45 AW %z -Z Australia/Hobart 9:49:16 - LMT 1895 S -10 AT AE%sT 1919 O 24 -10 AU AE%sT 1967 -10 AT AE%sT -Z Australia/Lindeman 9:55:56 - LMT 1895 -10 AU AE%sT 1971 -10 AQ AE%sT 1992 Jul -10 Ho AE%sT -Z Australia/Lord_Howe 10:36:20 - LMT 1895 F -10 - AEST 1981 Mar -10:30 LH %z 1985 Jul -10:30 LH %z -Z Australia/Melbourne 9:39:52 - LMT 1895 F -10 AU AE%sT 1971 -10 AV AE%sT -Z Australia/Perth 7:43:24 - LMT 1895 D -8 AU AW%sT 1943 Jul -8 AW AW%sT -Z Australia/Sydney 10:4:52 - LMT 1895 F -10 AU AE%sT 1971 -10 AN AE%sT -Z Etc/GMT 0 - GMT -Z Etc/GMT+1 -1 - %z -Z Etc/GMT+10 -10 - %z -Z Etc/GMT+11 -11 - %z -Z Etc/GMT+12 -12 - %z -Z Etc/GMT+2 -2 - %z -Z Etc/GMT+3 -3 - %z -Z Etc/GMT+4 -4 - %z -Z Etc/GMT+5 -5 - %z -Z Etc/GMT+6 -6 - %z -Z Etc/GMT+7 -7 - %z -Z Etc/GMT+8 -8 - %z -Z Etc/GMT+9 -9 - %z -Z Etc/GMT-1 1 - %z -Z Etc/GMT-10 10 - %z -Z Etc/GMT-11 11 - %z -Z Etc/GMT-12 12 - %z -Z Etc/GMT-13 13 - %z -Z Etc/GMT-14 14 - %z -Z Etc/GMT-2 2 - %z -Z Etc/GMT-3 3 - %z -Z Etc/GMT-4 4 - %z -Z Etc/GMT-5 5 - %z -Z Etc/GMT-6 6 - %z -Z Etc/GMT-7 7 - %z -Z Etc/GMT-8 8 - %z -Z Etc/GMT-9 9 - %z -Z Etc/UTC 0 - UTC -Z Europe/Andorra 0:6:4 - LMT 1901 -0 - WET 1946 S 30 -1 - CET 1985 Mar 31 2 -1 E CE%sT -Z Europe/Astrakhan 3:12:12 - LMT 1924 May -3 - %z 1930 Jun 21 -4 R %z 1989 Mar 26 2s -3 R %z 1991 Mar 31 2s -4 - %z 1992 Mar 29 2s -3 R %z 2011 Mar 27 2s -4 - %z 2014 O 26 2s -3 - %z 2016 Mar 27 2s -4 - %z -Z Europe/Athens 1:34:52 - LMT 1895 S 14 -1:34:52 - AMT 1916 Jul 28 0:1 -2 g EE%sT 1941 Ap 30 -1 g CE%sT 1944 Ap 4 -2 g EE%sT 1981 -2 E EE%sT -Z Europe/Belgrade 1:22 - LMT 1884 -1 - CET 1941 Ap 18 23 -1 c CE%sT 1945 -1 - CET 1945 May 8 2s -1 1 CEST 1945 S 16 2s -1 - CET 1982 N 27 -1 E CE%sT -Z Europe/Berlin 0:53:28 - LMT 1893 Ap -1 c CE%sT 1945 May 24 2 -1 So CE%sT 1946 -1 DE CE%sT 1980 -1 E CE%sT -Z Europe/Brussels 0:17:30 - LMT 1880 -0:17:30 - BMT 1892 May 1 0:17:30 -0 - WET 1914 N 8 -1 - CET 1916 May -1 c CE%sT 1918 N 11 11u -0 b WE%sT 1940 May 20 2s -1 c CE%sT 1944 S 3 -1 b CE%sT 1977 -1 E CE%sT -Z Europe/Bucharest 1:44:24 - LMT 1891 O -1:44:24 - BMT 1931 Jul 24 -2 z EE%sT 1981 Mar 29 2s -2 c EE%sT 1991 -2 z EE%sT 1994 -2 e EE%sT 1997 -2 E EE%sT -Z Europe/Budapest 1:16:20 - LMT 1890 N -1 c CE%sT 1918 -1 h CE%sT 1941 Ap 7 23 -1 c CE%sT 1945 -1 h CE%sT 1984 -1 E CE%sT -Z Europe/Chisinau 1:55:20 - LMT 1880 -1:55 - CMT 1918 F 15 -1:44:24 - BMT 1931 Jul 24 -2 z EE%sT 1940 Au 15 -2 1 EEST 1941 Jul 17 -1 c CE%sT 1944 Au 24 -3 R MSK/MSD 1990 May 6 2 -2 R EE%sT 1992 -2 e EE%sT 1997 -2 MD EE%sT -Z Europe/Dublin -0:25:21 - LMT 1880 Au 2 --0:25:21 - DMT 1916 May 21 2s --0:25:21 1 IST 1916 O 1 2s -0 G %s 1921 D 6 -0 G GMT/IST 1940 F 25 2s -0 1 IST 1946 O 6 2s -0 - GMT 1947 Mar 16 2s -0 1 IST 1947 N 2 2s -0 - GMT 1948 Ap 18 2s -0 G GMT/IST 1968 O 27 -1 IE IST/GMT -Z Europe/Gibraltar -0:21:24 - LMT 1880 Au 2 -0 G %s 1957 Ap 14 2 -1 - CET 1982 -1 E CE%sT -Z Europe/Helsinki 1:39:49 - LMT 1878 May 31 -1:39:49 - HMT 1921 May -2 FI EE%sT 1983 -2 E EE%sT -Z Europe/Istanbul 1:55:52 - LMT 1880 -1:56:56 - IMT 1910 O -2 T EE%sT 1978 Jun 29 -3 T %z 1984 N 1 2 -2 T EE%sT 2007 -2 E EE%sT 2011 Mar 27 1u -2 - EET 2011 Mar 28 1u -2 E EE%sT 2014 Mar 30 1u -2 - EET 2014 Mar 31 1u -2 E EE%sT 2015 O 25 1u -2 1 EEST 2015 N 8 1u -2 E EE%sT 2016 S 7 -3 - %z -Z Europe/Kaliningrad 1:22 - LMT 1893 Ap -1 c CE%sT 1945 Ap 10 -2 O EE%sT 1946 Ap 7 -3 R MSK/MSD 1989 Mar 26 2s -2 R EE%sT 2011 Mar 27 2s -3 - %z 2014 O 26 2s -2 - EET -Z Europe/Kirov 3:18:48 - LMT 1919 Jul 1 0u -3 - %z 1930 Jun 21 -4 R %z 1989 Mar 26 2s -3 R MSK/MSD 1991 Mar 31 2s -4 - %z 1992 Mar 29 2s -3 R MSK/MSD 2011 Mar 27 2s -4 - MSK 2014 O 26 2s -3 - MSK -Z Europe/Kyiv 2:2:4 - LMT 1880 -2:2:4 - KMT 1924 May 2 -2 - EET 1930 Jun 21 -3 - MSK 1941 S 20 -1 c CE%sT 1943 N 6 -3 R MSK/MSD 1990 Jul 1 2 -2 1 EEST 1991 S 29 3 -2 c EE%sT 1996 May 13 -2 E EE%sT -Z Europe/Lisbon -0:36:45 - LMT 1884 --0:36:45 - LMT 1912 Ja 1 0u -0 p WE%sT 1966 O 2 2s -1 - CET 1976 S 26 1 -0 p WE%sT 1986 -0 E WE%sT 1992 S 27 1u -1 E CE%sT 1996 Mar 31 1u -0 E WE%sT -Z Europe/London -0:1:15 - LMT 1847 D -0 G %s 1968 O 27 -1 - BST 1971 O 31 2u -0 G %s 1996 -0 E GMT/BST -Z Europe/Madrid -0:14:44 - LMT 1901 Ja 1 0u -0 s WE%sT 1940 Mar 16 23 -1 s CE%sT 1979 -1 E CE%sT -Z Europe/Malta 0:58:4 - LMT 1893 N 2 -1 I CE%sT 1973 Mar 31 -1 MT CE%sT 1981 -1 E CE%sT -Z Europe/Minsk 1:50:16 - LMT 1880 -1:50 - MMT 1924 May 2 -2 - EET 1930 Jun 21 -3 - MSK 1941 Jun 28 -1 c CE%sT 1944 Jul 3 -3 R MSK/MSD 1990 -3 - MSK 1991 Mar 31 2s -2 R EE%sT 2011 Mar 27 2s -3 - %z -Z Europe/Moscow 2:30:17 - LMT 1880 -2:30:17 - MMT 1916 Jul 3 -2:31:19 R %s 1919 Jul 1 0u -3 R %s 1921 O -3 R MSK/MSD 1922 O -2 - EET 1930 Jun 21 -3 R MSK/MSD 1991 Mar 31 2s -2 R EE%sT 1992 Ja 19 2s -3 R MSK/MSD 2011 Mar 27 2s -4 - MSK 2014 O 26 2s -3 - MSK -Z Europe/Paris 0:9:21 - LMT 1891 Mar 16 -0:9:21 - PMT 1911 Mar 11 -0 F WE%sT 1940 Jun 14 23 -1 c CE%sT 1944 Au 25 -0 F WE%sT 1945 S 16 3 -1 F CE%sT 1977 -1 E CE%sT -Z Europe/Prague 0:57:44 - LMT 1850 -0:57:44 - PMT 1891 O -1 c CE%sT 1945 May 9 -1 CZ CE%sT 1946 D 1 3 -1 -1 GMT 1947 F 23 2 -1 CZ CE%sT 1979 -1 E CE%sT -Z Europe/Riga 1:36:34 - LMT 1880 -1:36:34 - RMT 1918 Ap 15 2 -1:36:34 1 LST 1918 S 16 3 -1:36:34 - RMT 1919 Ap 1 2 -1:36:34 1 LST 1919 May 22 3 -1:36:34 - RMT 1926 May 11 -2 - EET 1940 Au 5 -3 - MSK 1941 Jul -1 c CE%sT 1944 O 13 -3 R MSK/MSD 1989 Mar lastSu 2s -2 1 EEST 1989 S lastSu 2s -2 LV EE%sT 1997 Ja 21 -2 E EE%sT 2000 F 29 -2 - EET 2001 Ja 2 -2 E EE%sT -Z Europe/Rome 0:49:56 - LMT 1866 D 12 -0:49:56 - RMT 1893 O 31 23u -1 I CE%sT 1943 S 10 -1 c CE%sT 1944 Jun 4 -1 I CE%sT 1980 -1 E CE%sT -Z Europe/Samara 3:20:20 - LMT 1919 Jul 1 0u -3 - %z 1930 Jun 21 -4 - %z 1935 Ja 27 -4 R %z 1989 Mar 26 2s -3 R %z 1991 Mar 31 2s -2 R %z 1991 S 29 2s -3 - %z 1991 O 20 3 -4 R %z 2010 Mar 28 2s -3 R %z 2011 Mar 27 2s -4 - %z -Z Europe/Saratov 3:4:18 - LMT 1919 Jul 1 0u -3 - %z 1930 Jun 21 -4 R %z 1988 Mar 27 2s -3 R %z 1991 Mar 31 2s -4 - %z 1992 Mar 29 2s -3 R %z 2011 Mar 27 2s -4 - %z 2014 O 26 2s -3 - %z 2016 D 4 2s -4 - %z -Z Europe/Simferopol 2:16:24 - LMT 1880 -2:16 - SMT 1924 May 2 -2 - EET 1930 Jun 21 -3 - MSK 1941 N -1 c CE%sT 1944 Ap 13 -3 R MSK/MSD 1990 -3 - MSK 1990 Jul 1 2 -2 - EET 1992 Mar 20 -2 c EE%sT 1994 May -3 c MSK/MSD 1996 Mar 31 0s -3 1 MSD 1996 O 27 3s -3 - MSK 1997 Mar lastSu 1u -2 E EE%sT 2014 Mar 30 2 -4 - MSK 2014 O 26 2s -3 - MSK -Z Europe/Sofia 1:33:16 - LMT 1880 -1:56:56 - IMT 1894 N 30 -2 - EET 1942 N 2 3 -1 c CE%sT 1945 -1 - CET 1945 Ap 2 3 -2 - EET 1979 Mar 31 23 -2 BG EE%sT 1982 S 26 3 -2 c EE%sT 1991 -2 e EE%sT 1997 -2 E EE%sT -Z Europe/Tallinn 1:39 - LMT 1880 -1:39 - TMT 1918 F -1 c CE%sT 1919 Jul -1:39 - TMT 1921 May -2 - EET 1940 Au 6 -3 - MSK 1941 S 15 -1 c CE%sT 1944 S 22 -3 R MSK/MSD 1989 Mar 26 2s -2 1 EEST 1989 S 24 2s -2 c EE%sT 1998 S 22 -2 E EE%sT 1999 O 31 4 -2 - EET 2002 F 21 -2 E EE%sT -Z Europe/Tirane 1:19:20 - LMT 1914 -1 - CET 1940 Jun 16 -1 q CE%sT 1984 Jul -1 E CE%sT -Z Europe/Ulyanovsk 3:13:36 - LMT 1919 Jul 1 0u -3 - %z 1930 Jun 21 -4 R %z 1989 Mar 26 2s -3 R %z 1991 Mar 31 2s -2 R %z 1992 Ja 19 2s -3 R %z 2011 Mar 27 2s -4 - %z 2014 O 26 2s -3 - %z 2016 Mar 27 2s -4 - %z -Z Europe/Vienna 1:5:21 - LMT 1893 Ap -1 c CE%sT 1920 -1 a CE%sT 1940 Ap 1 2s -1 c CE%sT 1945 Ap 2 2s -1 1 CEST 1945 Ap 12 2s -1 - CET 1946 -1 a CE%sT 1981 -1 E CE%sT -Z Europe/Vilnius 1:41:16 - LMT 1880 -1:24 - WMT 1917 -1:35:36 - KMT 1919 O 10 -1 - CET 1920 Jul 12 -2 - EET 1920 O 9 -1 - CET 1940 Au 3 -3 - MSK 1941 Jun 24 -1 c CE%sT 1944 Au -3 R MSK/MSD 1989 Mar 26 2s -2 R EE%sT 1991 S 29 2s -2 c EE%sT 1998 -2 - EET 1998 Mar 29 1u -1 E CE%sT 1999 O 31 1u -2 - EET 2003 -2 E EE%sT -Z Europe/Volgograd 2:57:40 - LMT 1920 Ja 3 -3 - %z 1930 Jun 21 -4 - %z 1961 N 11 -4 R %z 1988 Mar 27 2s -3 R MSK/MSD 1991 Mar 31 2s -4 - %z 1992 Mar 29 2s -3 R MSK/MSD 2011 Mar 27 2s -4 - MSK 2014 O 26 2s -3 - MSK 2018 O 28 2s -4 - %z 2020 D 27 2s -3 - MSK -Z Europe/Warsaw 1:24 - LMT 1880 -1:24 - WMT 1915 Au 5 -1 c CE%sT 1918 S 16 3 -2 O EE%sT 1922 Jun -1 O CE%sT 1940 Jun 23 2 -1 c CE%sT 1944 O -1 O CE%sT 1977 -1 W- CE%sT 1988 -1 E CE%sT -Z Europe/Zurich 0:34:8 - LMT 1853 Jul 16 -0:29:46 - BMT 1894 Jun -1 CH CE%sT 1981 -1 E CE%sT -Z Factory 0 - -00 -Z Indian/Chagos 4:49:40 - LMT 1907 -5 - %z 1996 -6 - %z -Z Indian/Maldives 4:54 - LMT 1880 -4:54 - MMT 1960 -5 - %z -Z Indian/Mauritius 3:50 - LMT 1907 -4 MU %z -Z Pacific/Apia 12:33:4 - LMT 1892 Jul 5 --11:26:56 - LMT 1911 --11:30 - %z 1950 --11 WS %z 2011 D 29 24 -13 WS %z -Z Pacific/Auckland 11:39:4 - LMT 1868 N 2 -11:30 NZ NZ%sT 1946 -12 NZ NZ%sT -Z Pacific/Bougainville 10:22:16 - LMT 1880 -9:48:32 - PMMT 1895 -10 - %z 1942 Jul -9 - %z 1945 Au 21 -10 - %z 2014 D 28 2 -11 - %z -Z Pacific/Chatham 12:13:48 - LMT 1868 N 2 -12:15 - %z 1946 -12:45 k %z -Z Pacific/Easter -7:17:28 - LMT 1890 --7:17:28 - EMT 1932 S --7 x %z 1982 Mar 14 3u --6 x %z -Z Pacific/Efate 11:13:16 - LMT 1912 Ja 13 -11 VU %z -Z Pacific/Fakaofo -11:24:56 - LMT 1901 --11 - %z 2011 D 30 -13 - %z -Z Pacific/Fiji 11:55:44 - LMT 1915 O 26 -12 FJ %z -Z Pacific/Galapagos -5:58:24 - LMT 1931 --5 - %z 1986 --6 EC %z -Z Pacific/Gambier -8:59:48 - LMT 1912 O --9 - %z -Z Pacific/Guadalcanal 10:39:48 - LMT 1912 O -11 - %z -Z Pacific/Guam -14:21 - LMT 1844 D 31 -9:39 - LMT 1901 -10 - GST 1941 D 10 -9 - %z 1944 Jul 31 -10 Gu G%sT 2000 D 23 -10 - ChST -Z Pacific/Honolulu -10:31:26 - LMT 1896 Ja 13 12 --10:30 - HST 1933 Ap 30 2 --10:30 1 HDT 1933 May 21 12 --10:30 u H%sT 1947 Jun 8 2 --10 - HST -Z Pacific/Kanton 0 - -00 1937 Au 31 --12 - %z 1979 O --11 - %z 1994 D 31 -13 - %z -Z Pacific/Kiritimati -10:29:20 - LMT 1901 --10:40 - %z 1979 O --10 - %z 1994 D 31 -14 - %z -Z Pacific/Kosrae -13:8:4 - LMT 1844 D 31 -10:51:56 - LMT 1901 -11 - %z 1914 O -9 - %z 1919 F -11 - %z 1937 -10 - %z 1941 Ap -9 - %z 1945 Au -11 - %z 1969 O -12 - %z 1999 -11 - %z -Z Pacific/Kwajalein 11:9:20 - LMT 1901 -11 - %z 1937 -10 - %z 1941 Ap -9 - %z 1944 F 6 -11 - %z 1969 O --12 - %z 1993 Au 20 24 -12 - %z -Z Pacific/Marquesas -9:18 - LMT 1912 O --9:30 - %z -Z Pacific/Nauru 11:7:40 - LMT 1921 Ja 15 -11:30 - %z 1942 Au 29 -9 - %z 1945 S 8 -11:30 - %z 1979 F 10 2 -12 - %z -Z Pacific/Niue -11:19:40 - LMT 1952 O 16 --11:20 - %z 1964 Jul --11 - %z -Z Pacific/Norfolk 11:11:52 - LMT 1901 -11:12 - %z 1951 -11:30 - %z 1974 O 27 2s -11:30 1 %z 1975 Mar 2 2s -11:30 - %z 2015 O 4 2s -11 - %z 2019 Jul -11 AN %z -Z Pacific/Noumea 11:5:48 - LMT 1912 Ja 13 -11 NC %z -Z Pacific/Pago_Pago 12:37:12 - LMT 1892 Jul 5 --11:22:48 - LMT 1911 --11 - SST -Z Pacific/Palau -15:2:4 - LMT 1844 D 31 -8:57:56 - LMT 1901 -9 - %z -Z Pacific/Pitcairn -8:40:20 - LMT 1901 --8:30 - %z 1998 Ap 27 --8 - %z -Z Pacific/Port_Moresby 9:48:40 - LMT 1880 -9:48:32 - PMMT 1895 -10 - %z -Z Pacific/Rarotonga 13:20:56 - LMT 1899 D 26 --10:39:4 - LMT 1952 O 16 --10:30 - %z 1978 N 12 --10 CK %z -Z Pacific/Tahiti -9:58:16 - LMT 1912 O --10 - %z -Z Pacific/Tarawa 11:32:4 - LMT 1901 -12 - %z -Z Pacific/Tongatapu 12:19:12 - LMT 1945 S 10 -12:20 - %z 1961 -13 - %z 1999 -13 TO %z -L Etc/GMT GMT -L Australia/Sydney Australia/ACT -L Australia/Lord_Howe Australia/LHI -L Australia/Sydney Australia/NSW -L Australia/Darwin Australia/North -L Australia/Brisbane Australia/Queensland -L Australia/Adelaide Australia/South -L Australia/Hobart Australia/Tasmania -L Australia/Melbourne Australia/Victoria -L Australia/Perth Australia/West -L Australia/Broken_Hill Australia/Yancowinna -L America/Rio_Branco Brazil/Acre -L America/Noronha Brazil/DeNoronha -L America/Sao_Paulo Brazil/East -L America/Manaus Brazil/West -L Europe/Brussels CET -L America/Chicago CST6CDT -L America/Halifax Canada/Atlantic -L America/Winnipeg Canada/Central -L America/Toronto Canada/Eastern -L America/Edmonton Canada/Mountain -L America/St_Johns Canada/Newfoundland -L America/Vancouver Canada/Pacific -L America/Regina Canada/Saskatchewan -L America/Whitehorse Canada/Yukon -L America/Santiago Chile/Continental -L Pacific/Easter Chile/EasterIsland -L America/Havana Cuba -L Europe/Athens EET -L America/Panama EST -L America/New_York EST5EDT -L Africa/Cairo Egypt -L Europe/Dublin Eire -L Etc/GMT Etc/GMT+0 -L Etc/GMT Etc/GMT-0 -L Etc/GMT Etc/GMT0 -L Etc/GMT Etc/Greenwich -L Etc/UTC Etc/UCT -L Etc/UTC Etc/Universal -L Etc/UTC Etc/Zulu -L Europe/London GB -L Europe/London GB-Eire -L Etc/GMT GMT+0 -L Etc/GMT GMT-0 -L Etc/GMT GMT0 -L Etc/GMT Greenwich -L Asia/Hong_Kong Hongkong -L Africa/Abidjan Iceland -L Asia/Tehran Iran -L Asia/Jerusalem Israel -L America/Jamaica Jamaica -L Asia/Tokyo Japan -L Pacific/Kwajalein Kwajalein -L Africa/Tripoli Libya -L Europe/Brussels MET -L America/Phoenix MST -L America/Denver MST7MDT -L America/Tijuana Mexico/BajaNorte -L America/Mazatlan Mexico/BajaSur -L America/Mexico_City Mexico/General -L Pacific/Auckland NZ -L Pacific/Chatham NZ-CHAT -L America/Denver Navajo -L Asia/Shanghai PRC -L Europe/Warsaw Poland -L Europe/Lisbon Portugal -L Asia/Taipei ROC -L Asia/Seoul ROK -L Asia/Singapore Singapore -L Europe/Istanbul Turkey -L Etc/UTC UCT -L America/Anchorage US/Alaska -L America/Adak US/Aleutian -L America/Phoenix US/Arizona -L America/Chicago US/Central -L America/Indiana/Indianapolis US/East-Indiana -L America/New_York US/Eastern -L Pacific/Honolulu US/Hawaii -L America/Indiana/Knox US/Indiana-Starke -L America/Detroit US/Michigan -L America/Denver US/Mountain -L America/Los_Angeles US/Pacific -L Pacific/Pago_Pago US/Samoa -L Etc/UTC UTC -L Etc/UTC Universal -L Europe/Moscow W-SU -L Etc/UTC Zulu -L America/Argentina/Buenos_Aires America/Buenos_Aires -L America/Argentina/Catamarca America/Catamarca -L America/Argentina/Cordoba America/Cordoba -L America/Indiana/Indianapolis America/Indianapolis -L America/Argentina/Jujuy America/Jujuy -L America/Indiana/Knox America/Knox_IN -L America/Kentucky/Louisville America/Louisville -L America/Argentina/Mendoza America/Mendoza -L America/Puerto_Rico America/Virgin -L Pacific/Pago_Pago Pacific/Samoa -L Africa/Abidjan Africa/Accra -L Africa/Nairobi Africa/Addis_Ababa -L Africa/Nairobi Africa/Asmara -L Africa/Abidjan Africa/Bamako -L Africa/Lagos Africa/Bangui -L Africa/Abidjan Africa/Banjul -L Africa/Maputo Africa/Blantyre -L Africa/Lagos Africa/Brazzaville -L Africa/Maputo Africa/Bujumbura -L Africa/Abidjan Africa/Conakry -L Africa/Abidjan Africa/Dakar -L Africa/Nairobi Africa/Dar_es_Salaam -L Africa/Nairobi Africa/Djibouti -L Africa/Lagos Africa/Douala -L Africa/Abidjan Africa/Freetown -L Africa/Maputo Africa/Gaborone -L Africa/Maputo Africa/Harare -L Africa/Nairobi Africa/Kampala -L Africa/Maputo Africa/Kigali -L Africa/Lagos Africa/Kinshasa -L Africa/Lagos Africa/Libreville -L Africa/Abidjan Africa/Lome -L Africa/Lagos Africa/Luanda -L Africa/Maputo Africa/Lubumbashi -L Africa/Maputo Africa/Lusaka -L Africa/Lagos Africa/Malabo -L Africa/Johannesburg Africa/Maseru -L Africa/Johannesburg Africa/Mbabane -L Africa/Nairobi Africa/Mogadishu -L Africa/Lagos Africa/Niamey -L Africa/Abidjan Africa/Nouakchott -L Africa/Abidjan Africa/Ouagadougou -L Africa/Lagos Africa/Porto-Novo -L America/Puerto_Rico America/Anguilla -L America/Puerto_Rico America/Antigua -L America/Puerto_Rico America/Aruba -L America/Panama America/Atikokan -L America/Puerto_Rico America/Blanc-Sablon -L America/Panama America/Cayman -L America/Phoenix America/Creston -L America/Puerto_Rico America/Curacao -L America/Puerto_Rico America/Dominica -L America/Puerto_Rico America/Grenada -L America/Puerto_Rico America/Guadeloupe -L America/Puerto_Rico America/Kralendijk -L America/Puerto_Rico America/Lower_Princes -L America/Puerto_Rico America/Marigot -L America/Puerto_Rico America/Montserrat -L America/Toronto America/Nassau -L America/Puerto_Rico America/Port_of_Spain -L America/Puerto_Rico America/St_Barthelemy -L America/Puerto_Rico America/St_Kitts -L America/Puerto_Rico America/St_Lucia -L America/Puerto_Rico America/St_Thomas -L America/Puerto_Rico America/St_Vincent -L America/Puerto_Rico America/Tortola -L Pacific/Port_Moresby Antarctica/DumontDUrville -L Pacific/Auckland Antarctica/McMurdo -L Asia/Riyadh Antarctica/Syowa -L Europe/Berlin Arctic/Longyearbyen -L Asia/Riyadh Asia/Aden -L Asia/Qatar Asia/Bahrain -L Asia/Kuching Asia/Brunei -L Asia/Singapore Asia/Kuala_Lumpur -L Asia/Riyadh Asia/Kuwait -L Asia/Dubai Asia/Muscat -L Asia/Bangkok Asia/Phnom_Penh -L Asia/Bangkok Asia/Vientiane -L Africa/Abidjan Atlantic/Reykjavik -L Africa/Abidjan Atlantic/St_Helena -L Europe/Brussels Europe/Amsterdam -L Europe/Prague Europe/Bratislava -L Europe/Zurich Europe/Busingen -L Europe/Berlin Europe/Copenhagen -L Europe/London Europe/Guernsey -L Europe/London Europe/Isle_of_Man -L Europe/London Europe/Jersey -L Europe/Belgrade Europe/Ljubljana -L Europe/Brussels Europe/Luxembourg -L Europe/Helsinki Europe/Mariehamn -L Europe/Paris Europe/Monaco -L Europe/Berlin Europe/Oslo -L Europe/Belgrade Europe/Podgorica -L Europe/Rome Europe/San_Marino -L Europe/Belgrade Europe/Sarajevo -L Europe/Belgrade Europe/Skopje -L Europe/Berlin Europe/Stockholm -L Europe/Zurich Europe/Vaduz -L Europe/Rome Europe/Vatican -L Europe/Belgrade Europe/Zagreb -L Africa/Nairobi Indian/Antananarivo -L Asia/Bangkok Indian/Christmas -L Asia/Yangon Indian/Cocos -L Africa/Nairobi Indian/Comoro -L Indian/Maldives Indian/Kerguelen -L Asia/Dubai Indian/Mahe -L Africa/Nairobi Indian/Mayotte -L Asia/Dubai Indian/Reunion -L Pacific/Port_Moresby Pacific/Chuuk -L Pacific/Tarawa Pacific/Funafuti -L Pacific/Tarawa Pacific/Majuro -L Pacific/Pago_Pago Pacific/Midway -L Pacific/Guadalcanal Pacific/Pohnpei -L Pacific/Guam Pacific/Saipan -L Pacific/Tarawa Pacific/Wake -L Pacific/Tarawa Pacific/Wallis -L Africa/Abidjan Africa/Timbuktu -L America/Argentina/Catamarca America/Argentina/ComodRivadavia -L America/Adak America/Atka -L America/Panama America/Coral_Harbour -L America/Tijuana America/Ensenada -L America/Indiana/Indianapolis America/Fort_Wayne -L America/Toronto America/Montreal -L America/Toronto America/Nipigon -L America/Iqaluit America/Pangnirtung -L America/Rio_Branco America/Porto_Acre -L America/Winnipeg America/Rainy_River -L America/Argentina/Cordoba America/Rosario -L America/Tijuana America/Santa_Isabel -L America/Denver America/Shiprock -L America/Toronto America/Thunder_Bay -L America/Edmonton America/Yellowknife -L Pacific/Auckland Antarctica/South_Pole -L Asia/Ulaanbaatar Asia/Choibalsan -L Asia/Shanghai Asia/Chongqing -L Asia/Shanghai Asia/Harbin -L Asia/Urumqi Asia/Kashgar -L Asia/Jerusalem Asia/Tel_Aviv -L Europe/Berlin Atlantic/Jan_Mayen -L Australia/Sydney Australia/Canberra -L Australia/Hobart Australia/Currie -L Europe/London Europe/Belfast -L Europe/Chisinau Europe/Tiraspol -L Europe/Kyiv Europe/Uzhgorod -L Europe/Kyiv Europe/Zaporozhye -L Pacific/Kanton Pacific/Enderbury -L Pacific/Honolulu Pacific/Johnston -L Pacific/Port_Moresby Pacific/Yap -L Europe/Lisbon WET -L Africa/Nairobi Africa/Asmera -L America/Nuuk America/Godthab -L Asia/Ashgabat Asia/Ashkhabad -L Asia/Kolkata Asia/Calcutta -L Asia/Shanghai Asia/Chungking -L Asia/Dhaka Asia/Dacca -L Europe/Istanbul Asia/Istanbul -L Asia/Kathmandu Asia/Katmandu -L Asia/Macau Asia/Macao -L Asia/Yangon Asia/Rangoon -L Asia/Ho_Chi_Minh Asia/Saigon -L Asia/Thimphu Asia/Thimbu -L Asia/Makassar Asia/Ujung_Pandang -L Asia/Ulaanbaatar Asia/Ulan_Bator -L Atlantic/Faroe Atlantic/Faeroe -L Europe/Kyiv Europe/Kiev -L Asia/Nicosia Europe/Nicosia -L Pacific/Honolulu HST -L America/Los_Angeles PST8PDT -L Pacific/Guadalcanal Pacific/Ponape -L Pacific/Port_Moresby Pacific/Truk diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zone.tab b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zone.tab deleted file mode 100644 index 2626b05..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zone.tab +++ /dev/null @@ -1,448 +0,0 @@ -# tzdb timezone descriptions (deprecated version) -# -# This file is in the public domain, so clarified as of -# 2009-05-17 by Arthur David Olson. -# -# From Paul Eggert (2021-09-20): -# This file is intended as a backward-compatibility aid for older programs. -# New programs should use zone1970.tab. This file is like zone1970.tab (see -# zone1970.tab's comments), but with the following additional restrictions: -# -# 1. This file contains only ASCII characters. -# 2. The first data column contains exactly one country code. -# -# Because of (2), each row stands for an area that is the intersection -# of a region identified by a country code and of a timezone where civil -# clocks have agreed since 1970; this is a narrower definition than -# that of zone1970.tab. -# -# Unlike zone1970.tab, a row's third column can be a Link from -# 'backward' instead of a Zone. -# -# This table is intended as an aid for users, to help them select timezones -# appropriate for their practical needs. It is not intended to take or -# endorse any position on legal or territorial claims. -# -#country- -#code coordinates TZ comments -AD +4230+00131 Europe/Andorra -AE +2518+05518 Asia/Dubai -AF +3431+06912 Asia/Kabul -AG +1703-06148 America/Antigua -AI +1812-06304 America/Anguilla -AL +4120+01950 Europe/Tirane -AM +4011+04430 Asia/Yerevan -AO -0848+01314 Africa/Luanda -AQ -7750+16636 Antarctica/McMurdo New Zealand time - McMurdo, South Pole -AQ -6617+11031 Antarctica/Casey Casey -AQ -6835+07758 Antarctica/Davis Davis -AQ -6640+14001 Antarctica/DumontDUrville Dumont-d'Urville -AQ -6736+06253 Antarctica/Mawson Mawson -AQ -6448-06406 Antarctica/Palmer Palmer -AQ -6734-06808 Antarctica/Rothera Rothera -AQ -690022+0393524 Antarctica/Syowa Syowa -AQ -720041+0023206 Antarctica/Troll Troll -AQ -7824+10654 Antarctica/Vostok Vostok -AR -3436-05827 America/Argentina/Buenos_Aires Buenos Aires (BA, CF) -AR -3124-06411 America/Argentina/Cordoba Argentina (most areas: CB, CC, CN, ER, FM, MN, SE, SF) -AR -2447-06525 America/Argentina/Salta Salta (SA, LP, NQ, RN) -AR -2411-06518 America/Argentina/Jujuy Jujuy (JY) -AR -2649-06513 America/Argentina/Tucuman Tucuman (TM) -AR -2828-06547 America/Argentina/Catamarca Catamarca (CT), Chubut (CH) -AR -2926-06651 America/Argentina/La_Rioja La Rioja (LR) -AR -3132-06831 America/Argentina/San_Juan San Juan (SJ) -AR -3253-06849 America/Argentina/Mendoza Mendoza (MZ) -AR -3319-06621 America/Argentina/San_Luis San Luis (SL) -AR -5138-06913 America/Argentina/Rio_Gallegos Santa Cruz (SC) -AR -5448-06818 America/Argentina/Ushuaia Tierra del Fuego (TF) -AS -1416-17042 Pacific/Pago_Pago -AT +4813+01620 Europe/Vienna -AU -3133+15905 Australia/Lord_Howe Lord Howe Island -AU -5430+15857 Antarctica/Macquarie Macquarie Island -AU -4253+14719 Australia/Hobart Tasmania -AU -3749+14458 Australia/Melbourne Victoria -AU -3352+15113 Australia/Sydney New South Wales (most areas) -AU -3157+14127 Australia/Broken_Hill New South Wales (Yancowinna) -AU -2728+15302 Australia/Brisbane Queensland (most areas) -AU -2016+14900 Australia/Lindeman Queensland (Whitsunday Islands) -AU -3455+13835 Australia/Adelaide South Australia -AU -1228+13050 Australia/Darwin Northern Territory -AU -3157+11551 Australia/Perth Western Australia (most areas) -AU -3143+12852 Australia/Eucla Western Australia (Eucla) -AW +1230-06958 America/Aruba -AX +6006+01957 Europe/Mariehamn -AZ +4023+04951 Asia/Baku -BA +4352+01825 Europe/Sarajevo -BB +1306-05937 America/Barbados -BD +2343+09025 Asia/Dhaka -BE +5050+00420 Europe/Brussels -BF +1222-00131 Africa/Ouagadougou -BG +4241+02319 Europe/Sofia -BH +2623+05035 Asia/Bahrain -BI -0323+02922 Africa/Bujumbura -BJ +0629+00237 Africa/Porto-Novo -BL +1753-06251 America/St_Barthelemy -BM +3217-06446 Atlantic/Bermuda -BN +0456+11455 Asia/Brunei -BO -1630-06809 America/La_Paz -BQ +120903-0681636 America/Kralendijk -BR -0351-03225 America/Noronha Atlantic islands -BR -0127-04829 America/Belem Para (east), Amapa -BR -0343-03830 America/Fortaleza Brazil (northeast: MA, PI, CE, RN, PB) -BR -0803-03454 America/Recife Pernambuco -BR -0712-04812 America/Araguaina Tocantins -BR -0940-03543 America/Maceio Alagoas, Sergipe -BR -1259-03831 America/Bahia Bahia -BR -2332-04637 America/Sao_Paulo Brazil (southeast: GO, DF, MG, ES, RJ, SP, PR, SC, RS) -BR -2027-05437 America/Campo_Grande Mato Grosso do Sul -BR -1535-05605 America/Cuiaba Mato Grosso -BR -0226-05452 America/Santarem Para (west) -BR -0846-06354 America/Porto_Velho Rondonia -BR +0249-06040 America/Boa_Vista Roraima -BR -0308-06001 America/Manaus Amazonas (east) -BR -0640-06952 America/Eirunepe Amazonas (west) -BR -0958-06748 America/Rio_Branco Acre -BS +2505-07721 America/Nassau -BT +2728+08939 Asia/Thimphu -BW -2439+02555 Africa/Gaborone -BY +5354+02734 Europe/Minsk -BZ +1730-08812 America/Belize -CA +4734-05243 America/St_Johns Newfoundland, Labrador (SE) -CA +4439-06336 America/Halifax Atlantic - NS (most areas), PE -CA +4612-05957 America/Glace_Bay Atlantic - NS (Cape Breton) -CA +4606-06447 America/Moncton Atlantic - New Brunswick -CA +5320-06025 America/Goose_Bay Atlantic - Labrador (most areas) -CA +5125-05707 America/Blanc-Sablon AST - QC (Lower North Shore) -CA +4339-07923 America/Toronto Eastern - ON & QC (most areas) -CA +6344-06828 America/Iqaluit Eastern - NU (most areas) -CA +484531-0913718 America/Atikokan EST - ON (Atikokan), NU (Coral H) -CA +4953-09709 America/Winnipeg Central - ON (west), Manitoba -CA +744144-0944945 America/Resolute Central - NU (Resolute) -CA +624900-0920459 America/Rankin_Inlet Central - NU (central) -CA +5024-10439 America/Regina CST - SK (most areas) -CA +5017-10750 America/Swift_Current CST - SK (midwest) -CA +5333-11328 America/Edmonton Mountain - AB, BC(E), NT(E), SK(W) -CA +690650-1050310 America/Cambridge_Bay Mountain - NU (west) -CA +682059-1334300 America/Inuvik Mountain - NT (west) -CA +4906-11631 America/Creston MST - BC (Creston) -CA +5546-12014 America/Dawson_Creek MST - BC (Dawson Cr, Ft St John) -CA +5848-12242 America/Fort_Nelson MST - BC (Ft Nelson) -CA +6043-13503 America/Whitehorse MST - Yukon (east) -CA +6404-13925 America/Dawson MST - Yukon (west) -CA +4916-12307 America/Vancouver Pacific - BC (most areas) -CC -1210+09655 Indian/Cocos -CD -0418+01518 Africa/Kinshasa Dem. Rep. of Congo (west) -CD -1140+02728 Africa/Lubumbashi Dem. Rep. of Congo (east) -CF +0422+01835 Africa/Bangui -CG -0416+01517 Africa/Brazzaville -CH +4723+00832 Europe/Zurich -CI +0519-00402 Africa/Abidjan -CK -2114-15946 Pacific/Rarotonga -CL -3327-07040 America/Santiago most of Chile -CL -4534-07204 America/Coyhaique Aysen Region -CL -5309-07055 America/Punta_Arenas Magallanes Region -CL -2709-10926 Pacific/Easter Easter Island -CM +0403+00942 Africa/Douala -CN +3114+12128 Asia/Shanghai Beijing Time -CN +4348+08735 Asia/Urumqi Xinjiang Time -CO +0436-07405 America/Bogota -CR +0956-08405 America/Costa_Rica -CU +2308-08222 America/Havana -CV +1455-02331 Atlantic/Cape_Verde -CW +1211-06900 America/Curacao -CX -1025+10543 Indian/Christmas -CY +3510+03322 Asia/Nicosia most of Cyprus -CY +3507+03357 Asia/Famagusta Northern Cyprus -CZ +5005+01426 Europe/Prague -DE +5230+01322 Europe/Berlin most of Germany -DE +4742+00841 Europe/Busingen Busingen -DJ +1136+04309 Africa/Djibouti -DK +5540+01235 Europe/Copenhagen -DM +1518-06124 America/Dominica -DO +1828-06954 America/Santo_Domingo -DZ +3647+00303 Africa/Algiers -EC -0210-07950 America/Guayaquil Ecuador (mainland) -EC -0054-08936 Pacific/Galapagos Galapagos Islands -EE +5925+02445 Europe/Tallinn -EG +3003+03115 Africa/Cairo -EH +2709-01312 Africa/El_Aaiun -ER +1520+03853 Africa/Asmara -ES +4024-00341 Europe/Madrid Spain (mainland) -ES +3553-00519 Africa/Ceuta Ceuta, Melilla -ES +2806-01524 Atlantic/Canary Canary Islands -ET +0902+03842 Africa/Addis_Ababa -FI +6010+02458 Europe/Helsinki -FJ -1808+17825 Pacific/Fiji -FK -5142-05751 Atlantic/Stanley -FM +0725+15147 Pacific/Chuuk Chuuk/Truk, Yap -FM +0658+15813 Pacific/Pohnpei Pohnpei/Ponape -FM +0519+16259 Pacific/Kosrae Kosrae -FO +6201-00646 Atlantic/Faroe -FR +4852+00220 Europe/Paris -GA +0023+00927 Africa/Libreville -GB +513030-0000731 Europe/London -GD +1203-06145 America/Grenada -GE +4143+04449 Asia/Tbilisi -GF +0456-05220 America/Cayenne -GG +492717-0023210 Europe/Guernsey -GH +0533-00013 Africa/Accra -GI +3608-00521 Europe/Gibraltar -GL +6411-05144 America/Nuuk most of Greenland -GL +7646-01840 America/Danmarkshavn National Park (east coast) -GL +7029-02158 America/Scoresbysund Scoresbysund/Ittoqqortoormiit -GL +7634-06847 America/Thule Thule/Pituffik -GM +1328-01639 Africa/Banjul -GN +0931-01343 Africa/Conakry -GP +1614-06132 America/Guadeloupe -GQ +0345+00847 Africa/Malabo -GR +3758+02343 Europe/Athens -GS -5416-03632 Atlantic/South_Georgia -GT +1438-09031 America/Guatemala -GU +1328+14445 Pacific/Guam -GW +1151-01535 Africa/Bissau -GY +0648-05810 America/Guyana -HK +2217+11409 Asia/Hong_Kong -HN +1406-08713 America/Tegucigalpa -HR +4548+01558 Europe/Zagreb -HT +1832-07220 America/Port-au-Prince -HU +4730+01905 Europe/Budapest -ID -0610+10648 Asia/Jakarta Java, Sumatra -ID -0002+10920 Asia/Pontianak Borneo (west, central) -ID -0507+11924 Asia/Makassar Borneo (east, south), Sulawesi/Celebes, Bali, Nusa Tengarra, Timor (west) -ID -0232+14042 Asia/Jayapura New Guinea (West Papua / Irian Jaya), Malukus/Moluccas -IE +5320-00615 Europe/Dublin -IL +314650+0351326 Asia/Jerusalem -IM +5409-00428 Europe/Isle_of_Man -IN +2232+08822 Asia/Kolkata -IO -0720+07225 Indian/Chagos -IQ +3321+04425 Asia/Baghdad -IR +3540+05126 Asia/Tehran -IS +6409-02151 Atlantic/Reykjavik -IT +4154+01229 Europe/Rome -JE +491101-0020624 Europe/Jersey -JM +175805-0764736 America/Jamaica -JO +3157+03556 Asia/Amman -JP +353916+1394441 Asia/Tokyo -KE -0117+03649 Africa/Nairobi -KG +4254+07436 Asia/Bishkek -KH +1133+10455 Asia/Phnom_Penh -KI +0125+17300 Pacific/Tarawa Gilbert Islands -KI -0247-17143 Pacific/Kanton Phoenix Islands -KI +0152-15720 Pacific/Kiritimati Line Islands -KM -1141+04316 Indian/Comoro -KN +1718-06243 America/St_Kitts -KP +3901+12545 Asia/Pyongyang -KR +3733+12658 Asia/Seoul -KW +2920+04759 Asia/Kuwait -KY +1918-08123 America/Cayman -KZ +4315+07657 Asia/Almaty most of Kazakhstan -KZ +4448+06528 Asia/Qyzylorda Qyzylorda/Kyzylorda/Kzyl-Orda -KZ +5312+06337 Asia/Qostanay Qostanay/Kostanay/Kustanay -KZ +5017+05710 Asia/Aqtobe Aqtobe/Aktobe -KZ +4431+05016 Asia/Aqtau Mangghystau/Mankistau -KZ +4707+05156 Asia/Atyrau Atyrau/Atirau/Gur'yev -KZ +5113+05121 Asia/Oral West Kazakhstan -LA +1758+10236 Asia/Vientiane -LB +3353+03530 Asia/Beirut -LC +1401-06100 America/St_Lucia -LI +4709+00931 Europe/Vaduz -LK +0656+07951 Asia/Colombo -LR +0618-01047 Africa/Monrovia -LS -2928+02730 Africa/Maseru -LT +5441+02519 Europe/Vilnius -LU +4936+00609 Europe/Luxembourg -LV +5657+02406 Europe/Riga -LY +3254+01311 Africa/Tripoli -MA +3339-00735 Africa/Casablanca -MC +4342+00723 Europe/Monaco -MD +4700+02850 Europe/Chisinau -ME +4226+01916 Europe/Podgorica -MF +1804-06305 America/Marigot -MG -1855+04731 Indian/Antananarivo -MH +0709+17112 Pacific/Majuro most of Marshall Islands -MH +0905+16720 Pacific/Kwajalein Kwajalein -MK +4159+02126 Europe/Skopje -ML +1239-00800 Africa/Bamako -MM +1647+09610 Asia/Yangon -MN +4755+10653 Asia/Ulaanbaatar most of Mongolia -MN +4801+09139 Asia/Hovd Bayan-Olgii, Hovd, Uvs -MO +221150+1133230 Asia/Macau -MP +1512+14545 Pacific/Saipan -MQ +1436-06105 America/Martinique -MR +1806-01557 Africa/Nouakchott -MS +1643-06213 America/Montserrat -MT +3554+01431 Europe/Malta -MU -2010+05730 Indian/Mauritius -MV +0410+07330 Indian/Maldives -MW -1547+03500 Africa/Blantyre -MX +1924-09909 America/Mexico_City Central Mexico -MX +2105-08646 America/Cancun Quintana Roo -MX +2058-08937 America/Merida Campeche, Yucatan -MX +2540-10019 America/Monterrey Durango; Coahuila, Nuevo Leon, Tamaulipas (most areas) -MX +2550-09730 America/Matamoros Coahuila, Nuevo Leon, Tamaulipas (US border) -MX +2838-10605 America/Chihuahua Chihuahua (most areas) -MX +3144-10629 America/Ciudad_Juarez Chihuahua (US border - west) -MX +2934-10425 America/Ojinaga Chihuahua (US border - east) -MX +2313-10625 America/Mazatlan Baja California Sur, Nayarit (most areas), Sinaloa -MX +2048-10515 America/Bahia_Banderas Bahia de Banderas -MX +2904-11058 America/Hermosillo Sonora -MX +3232-11701 America/Tijuana Baja California -MY +0310+10142 Asia/Kuala_Lumpur Malaysia (peninsula) -MY +0133+11020 Asia/Kuching Sabah, Sarawak -MZ -2558+03235 Africa/Maputo -NA -2234+01706 Africa/Windhoek -NC -2216+16627 Pacific/Noumea -NE +1331+00207 Africa/Niamey -NF -2903+16758 Pacific/Norfolk -NG +0627+00324 Africa/Lagos -NI +1209-08617 America/Managua -NL +5222+00454 Europe/Amsterdam -NO +5955+01045 Europe/Oslo -NP +2743+08519 Asia/Kathmandu -NR -0031+16655 Pacific/Nauru -NU -1901-16955 Pacific/Niue -NZ -3652+17446 Pacific/Auckland most of New Zealand -NZ -4357-17633 Pacific/Chatham Chatham Islands -OM +2336+05835 Asia/Muscat -PA +0858-07932 America/Panama -PE -1203-07703 America/Lima -PF -1732-14934 Pacific/Tahiti Society Islands -PF -0900-13930 Pacific/Marquesas Marquesas Islands -PF -2308-13457 Pacific/Gambier Gambier Islands -PG -0930+14710 Pacific/Port_Moresby most of Papua New Guinea -PG -0613+15534 Pacific/Bougainville Bougainville -PH +143512+1205804 Asia/Manila -PK +2452+06703 Asia/Karachi -PL +5215+02100 Europe/Warsaw -PM +4703-05620 America/Miquelon -PN -2504-13005 Pacific/Pitcairn -PR +182806-0660622 America/Puerto_Rico -PS +3130+03428 Asia/Gaza Gaza Strip -PS +313200+0350542 Asia/Hebron West Bank -PT +3843-00908 Europe/Lisbon Portugal (mainland) -PT +3238-01654 Atlantic/Madeira Madeira Islands -PT +3744-02540 Atlantic/Azores Azores -PW +0720+13429 Pacific/Palau -PY -2516-05740 America/Asuncion -QA +2517+05132 Asia/Qatar -RE -2052+05528 Indian/Reunion -RO +4426+02606 Europe/Bucharest -RS +4450+02030 Europe/Belgrade -RU +5443+02030 Europe/Kaliningrad MSK-01 - Kaliningrad -RU +554521+0373704 Europe/Moscow MSK+00 - Moscow area -# The obsolescent zone.tab format cannot represent Europe/Simferopol well. -# Put it in RU section and list as UA. See "territorial claims" above. -# Programs should use zone1970.tab instead; see above. -UA +4457+03406 Europe/Simferopol Crimea -RU +5836+04939 Europe/Kirov MSK+00 - Kirov -RU +4844+04425 Europe/Volgograd MSK+00 - Volgograd -RU +4621+04803 Europe/Astrakhan MSK+01 - Astrakhan -RU +5134+04602 Europe/Saratov MSK+01 - Saratov -RU +5420+04824 Europe/Ulyanovsk MSK+01 - Ulyanovsk -RU +5312+05009 Europe/Samara MSK+01 - Samara, Udmurtia -RU +5651+06036 Asia/Yekaterinburg MSK+02 - Urals -RU +5500+07324 Asia/Omsk MSK+03 - Omsk -RU +5502+08255 Asia/Novosibirsk MSK+04 - Novosibirsk -RU +5322+08345 Asia/Barnaul MSK+04 - Altai -RU +5630+08458 Asia/Tomsk MSK+04 - Tomsk -RU +5345+08707 Asia/Novokuznetsk MSK+04 - Kemerovo -RU +5601+09250 Asia/Krasnoyarsk MSK+04 - Krasnoyarsk area -RU +5216+10420 Asia/Irkutsk MSK+05 - Irkutsk, Buryatia -RU +5203+11328 Asia/Chita MSK+06 - Zabaykalsky -RU +6200+12940 Asia/Yakutsk MSK+06 - Lena River -RU +623923+1353314 Asia/Khandyga MSK+06 - Tomponsky, Ust-Maysky -RU +4310+13156 Asia/Vladivostok MSK+07 - Amur River -RU +643337+1431336 Asia/Ust-Nera MSK+07 - Oymyakonsky -RU +5934+15048 Asia/Magadan MSK+08 - Magadan -RU +4658+14242 Asia/Sakhalin MSK+08 - Sakhalin Island -RU +6728+15343 Asia/Srednekolymsk MSK+08 - Sakha (E), N Kuril Is -RU +5301+15839 Asia/Kamchatka MSK+09 - Kamchatka -RU +6445+17729 Asia/Anadyr MSK+09 - Bering Sea -RW -0157+03004 Africa/Kigali -SA +2438+04643 Asia/Riyadh -SB -0932+16012 Pacific/Guadalcanal -SC -0440+05528 Indian/Mahe -SD +1536+03232 Africa/Khartoum -SE +5920+01803 Europe/Stockholm -SG +0117+10351 Asia/Singapore -SH -1555-00542 Atlantic/St_Helena -SI +4603+01431 Europe/Ljubljana -SJ +7800+01600 Arctic/Longyearbyen -SK +4809+01707 Europe/Bratislava -SL +0830-01315 Africa/Freetown -SM +4355+01228 Europe/San_Marino -SN +1440-01726 Africa/Dakar -SO +0204+04522 Africa/Mogadishu -SR +0550-05510 America/Paramaribo -SS +0451+03137 Africa/Juba -ST +0020+00644 Africa/Sao_Tome -SV +1342-08912 America/El_Salvador -SX +180305-0630250 America/Lower_Princes -SY +3330+03618 Asia/Damascus -SZ -2618+03106 Africa/Mbabane -TC +2128-07108 America/Grand_Turk -TD +1207+01503 Africa/Ndjamena -TF -492110+0701303 Indian/Kerguelen -TG +0608+00113 Africa/Lome -TH +1345+10031 Asia/Bangkok -TJ +3835+06848 Asia/Dushanbe -TK -0922-17114 Pacific/Fakaofo -TL -0833+12535 Asia/Dili -TM +3757+05823 Asia/Ashgabat -TN +3648+01011 Africa/Tunis -TO -210800-1751200 Pacific/Tongatapu -TR +4101+02858 Europe/Istanbul -TT +1039-06131 America/Port_of_Spain -TV -0831+17913 Pacific/Funafuti -TW +2503+12130 Asia/Taipei -TZ -0648+03917 Africa/Dar_es_Salaam -UA +5026+03031 Europe/Kyiv most of Ukraine -UG +0019+03225 Africa/Kampala -UM +2813-17722 Pacific/Midway Midway Islands -UM +1917+16637 Pacific/Wake Wake Island -US +404251-0740023 America/New_York Eastern (most areas) -US +421953-0830245 America/Detroit Eastern - MI (most areas) -US +381515-0854534 America/Kentucky/Louisville Eastern - KY (Louisville area) -US +364947-0845057 America/Kentucky/Monticello Eastern - KY (Wayne) -US +394606-0860929 America/Indiana/Indianapolis Eastern - IN (most areas) -US +384038-0873143 America/Indiana/Vincennes Eastern - IN (Da, Du, K, Mn) -US +410305-0863611 America/Indiana/Winamac Eastern - IN (Pulaski) -US +382232-0862041 America/Indiana/Marengo Eastern - IN (Crawford) -US +382931-0871643 America/Indiana/Petersburg Eastern - IN (Pike) -US +384452-0850402 America/Indiana/Vevay Eastern - IN (Switzerland) -US +415100-0873900 America/Chicago Central (most areas) -US +375711-0864541 America/Indiana/Tell_City Central - IN (Perry) -US +411745-0863730 America/Indiana/Knox Central - IN (Starke) -US +450628-0873651 America/Menominee Central - MI (Wisconsin border) -US +470659-1011757 America/North_Dakota/Center Central - ND (Oliver) -US +465042-1012439 America/North_Dakota/New_Salem Central - ND (Morton rural) -US +471551-1014640 America/North_Dakota/Beulah Central - ND (Mercer) -US +394421-1045903 America/Denver Mountain (most areas) -US +433649-1161209 America/Boise Mountain - ID (south), OR (east) -US +332654-1120424 America/Phoenix MST - AZ (except Navajo) -US +340308-1181434 America/Los_Angeles Pacific -US +611305-1495401 America/Anchorage Alaska (most areas) -US +581807-1342511 America/Juneau Alaska - Juneau area -US +571035-1351807 America/Sitka Alaska - Sitka area -US +550737-1313435 America/Metlakatla Alaska - Annette Island -US +593249-1394338 America/Yakutat Alaska - Yakutat -US +643004-1652423 America/Nome Alaska (west) -US +515248-1763929 America/Adak Alaska - western Aleutians -US +211825-1575130 Pacific/Honolulu Hawaii -UY -345433-0561245 America/Montevideo -UZ +3940+06648 Asia/Samarkand Uzbekistan (west) -UZ +4120+06918 Asia/Tashkent Uzbekistan (east) -VA +415408+0122711 Europe/Vatican -VC +1309-06114 America/St_Vincent -VE +1030-06656 America/Caracas -VG +1827-06437 America/Tortola -VI +1821-06456 America/St_Thomas -VN +1045+10640 Asia/Ho_Chi_Minh -VU -1740+16825 Pacific/Efate -WF -1318-17610 Pacific/Wallis -WS -1350-17144 Pacific/Apia -YE +1245+04512 Asia/Aden -YT -1247+04514 Indian/Mayotte -ZA -2615+02800 Africa/Johannesburg -ZM -1525+02817 Africa/Lusaka -ZW -1750+03103 Africa/Harare diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zone1970.tab b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zone1970.tab deleted file mode 100644 index 36535bd..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zone1970.tab +++ /dev/null @@ -1,375 +0,0 @@ -# tzdb timezone descriptions -# -# This file is in the public domain. -# -# From Paul Eggert (2018-06-27): -# This file contains a table where each row stands for a timezone where -# civil timestamps have agreed since 1970. Columns are separated by -# a single tab. Lines beginning with '#' are comments. All text uses -# UTF-8 encoding. The columns of the table are as follows: -# -# 1. The countries that overlap the timezone, as a comma-separated list -# of ISO 3166 2-character country codes. See the file 'iso3166.tab'. -# 2. Latitude and longitude of the timezone's principal location -# in ISO 6709 sign-degrees-minutes-seconds format, -# either ±DDMM±DDDMM or ±DDMMSS±DDDMMSS, -# first latitude (+ is north), then longitude (+ is east). -# 3. Timezone name used in value of TZ environment variable. -# Please see the theory.html file for how these names are chosen. -# If multiple timezones overlap a country, each has a row in the -# table, with each column 1 containing the country code. -# 4. Comments; present if and only if countries have multiple timezones, -# and useful only for those countries. For example, the comments -# for the row with countries CH,DE,LI and name Europe/Zurich -# are useful only for DE, since CH and LI have no other timezones. -# -# If a timezone covers multiple countries, the most-populous city is used, -# and that country is listed first in column 1; any other countries -# are listed alphabetically by country code. The table is sorted -# first by country code, then (if possible) by an order within the -# country that (1) makes some geographical sense, and (2) puts the -# most populous timezones first, where that does not contradict (1). -# -# This table is intended as an aid for users, to help them select timezones -# appropriate for their practical needs. It is not intended to take or -# endorse any position on legal or territorial claims. -# -#country- -#codes coordinates TZ comments -AD +4230+00131 Europe/Andorra -AE,OM,RE,SC,TF +2518+05518 Asia/Dubai Crozet -AF +3431+06912 Asia/Kabul -AL +4120+01950 Europe/Tirane -AM +4011+04430 Asia/Yerevan -AQ -6617+11031 Antarctica/Casey Casey -AQ -6835+07758 Antarctica/Davis Davis -AQ -6736+06253 Antarctica/Mawson Mawson -AQ -6448-06406 Antarctica/Palmer Palmer -AQ -6734-06808 Antarctica/Rothera Rothera -AQ -720041+0023206 Antarctica/Troll Troll -AQ -7824+10654 Antarctica/Vostok Vostok -AR -3436-05827 America/Argentina/Buenos_Aires Buenos Aires (BA, CF) -AR -3124-06411 America/Argentina/Cordoba most areas: CB, CC, CN, ER, FM, MN, SE, SF -AR -2447-06525 America/Argentina/Salta Salta (SA, LP, NQ, RN) -AR -2411-06518 America/Argentina/Jujuy Jujuy (JY) -AR -2649-06513 America/Argentina/Tucuman Tucumán (TM) -AR -2828-06547 America/Argentina/Catamarca Catamarca (CT), Chubut (CH) -AR -2926-06651 America/Argentina/La_Rioja La Rioja (LR) -AR -3132-06831 America/Argentina/San_Juan San Juan (SJ) -AR -3253-06849 America/Argentina/Mendoza Mendoza (MZ) -AR -3319-06621 America/Argentina/San_Luis San Luis (SL) -AR -5138-06913 America/Argentina/Rio_Gallegos Santa Cruz (SC) -AR -5448-06818 America/Argentina/Ushuaia Tierra del Fuego (TF) -AS,UM -1416-17042 Pacific/Pago_Pago Midway -AT +4813+01620 Europe/Vienna -AU -3133+15905 Australia/Lord_Howe Lord Howe Island -AU -5430+15857 Antarctica/Macquarie Macquarie Island -AU -4253+14719 Australia/Hobart Tasmania -AU -3749+14458 Australia/Melbourne Victoria -AU -3352+15113 Australia/Sydney New South Wales (most areas) -AU -3157+14127 Australia/Broken_Hill New South Wales (Yancowinna) -AU -2728+15302 Australia/Brisbane Queensland (most areas) -AU -2016+14900 Australia/Lindeman Queensland (Whitsunday Islands) -AU -3455+13835 Australia/Adelaide South Australia -AU -1228+13050 Australia/Darwin Northern Territory -AU -3157+11551 Australia/Perth Western Australia (most areas) -AU -3143+12852 Australia/Eucla Western Australia (Eucla) -AZ +4023+04951 Asia/Baku -BB +1306-05937 America/Barbados -BD +2343+09025 Asia/Dhaka -BE,LU,NL +5050+00420 Europe/Brussels -BG +4241+02319 Europe/Sofia -BM +3217-06446 Atlantic/Bermuda -BO -1630-06809 America/La_Paz -BR -0351-03225 America/Noronha Atlantic islands -BR -0127-04829 America/Belem Pará (east), Amapá -BR -0343-03830 America/Fortaleza Brazil (northeast: MA, PI, CE, RN, PB) -BR -0803-03454 America/Recife Pernambuco -BR -0712-04812 America/Araguaina Tocantins -BR -0940-03543 America/Maceio Alagoas, Sergipe -BR -1259-03831 America/Bahia Bahia -BR -2332-04637 America/Sao_Paulo Brazil (southeast: GO, DF, MG, ES, RJ, SP, PR, SC, RS) -BR -2027-05437 America/Campo_Grande Mato Grosso do Sul -BR -1535-05605 America/Cuiaba Mato Grosso -BR -0226-05452 America/Santarem Pará (west) -BR -0846-06354 America/Porto_Velho Rondônia -BR +0249-06040 America/Boa_Vista Roraima -BR -0308-06001 America/Manaus Amazonas (east) -BR -0640-06952 America/Eirunepe Amazonas (west) -BR -0958-06748 America/Rio_Branco Acre -BT +2728+08939 Asia/Thimphu -BY +5354+02734 Europe/Minsk -BZ +1730-08812 America/Belize -CA +4734-05243 America/St_Johns Newfoundland, Labrador (SE) -CA +4439-06336 America/Halifax Atlantic - NS (most areas), PE -CA +4612-05957 America/Glace_Bay Atlantic - NS (Cape Breton) -CA +4606-06447 America/Moncton Atlantic - New Brunswick -CA +5320-06025 America/Goose_Bay Atlantic - Labrador (most areas) -CA,BS +4339-07923 America/Toronto Eastern - ON & QC (most areas) -CA +6344-06828 America/Iqaluit Eastern - NU (most areas) -CA +4953-09709 America/Winnipeg Central - ON (west), Manitoba -CA +744144-0944945 America/Resolute Central - NU (Resolute) -CA +624900-0920459 America/Rankin_Inlet Central - NU (central) -CA +5024-10439 America/Regina CST - SK (most areas) -CA +5017-10750 America/Swift_Current CST - SK (midwest) -CA +5333-11328 America/Edmonton Mountain - AB, BC(E), NT(E), SK(W) -CA +690650-1050310 America/Cambridge_Bay Mountain - NU (west) -CA +682059-1334300 America/Inuvik Mountain - NT (west) -CA +5546-12014 America/Dawson_Creek MST - BC (Dawson Cr, Ft St John) -CA +5848-12242 America/Fort_Nelson MST - BC (Ft Nelson) -CA +6043-13503 America/Whitehorse MST - Yukon (east) -CA +6404-13925 America/Dawson MST - Yukon (west) -CA +4916-12307 America/Vancouver Pacific - BC (most areas) -CH,DE,LI +4723+00832 Europe/Zurich Büsingen -CI,BF,GH,GM,GN,IS,ML,MR,SH,SL,SN,TG +0519-00402 Africa/Abidjan -CK -2114-15946 Pacific/Rarotonga -CL -3327-07040 America/Santiago most of Chile -CL -4534-07204 America/Coyhaique Aysén Region -CL -5309-07055 America/Punta_Arenas Magallanes Region -CL -2709-10926 Pacific/Easter Easter Island -CN +3114+12128 Asia/Shanghai Beijing Time -CN +4348+08735 Asia/Urumqi Xinjiang Time -CO +0436-07405 America/Bogota -CR +0956-08405 America/Costa_Rica -CU +2308-08222 America/Havana -CV +1455-02331 Atlantic/Cape_Verde -CY +3510+03322 Asia/Nicosia most of Cyprus -CY +3507+03357 Asia/Famagusta Northern Cyprus -CZ,SK +5005+01426 Europe/Prague -DE,DK,NO,SE,SJ +5230+01322 Europe/Berlin most of Germany -DO +1828-06954 America/Santo_Domingo -DZ +3647+00303 Africa/Algiers -EC -0210-07950 America/Guayaquil Ecuador (mainland) -EC -0054-08936 Pacific/Galapagos Galápagos Islands -EE +5925+02445 Europe/Tallinn -EG +3003+03115 Africa/Cairo -EH +2709-01312 Africa/El_Aaiun -ES +4024-00341 Europe/Madrid Spain (mainland) -ES +3553-00519 Africa/Ceuta Ceuta, Melilla -ES +2806-01524 Atlantic/Canary Canary Islands -FI,AX +6010+02458 Europe/Helsinki -FJ -1808+17825 Pacific/Fiji -FK -5142-05751 Atlantic/Stanley -FM +0519+16259 Pacific/Kosrae Kosrae -FO +6201-00646 Atlantic/Faroe -FR,MC +4852+00220 Europe/Paris -GB,GG,IM,JE +513030-0000731 Europe/London -GE +4143+04449 Asia/Tbilisi -GF +0456-05220 America/Cayenne -GI +3608-00521 Europe/Gibraltar -GL +6411-05144 America/Nuuk most of Greenland -GL +7646-01840 America/Danmarkshavn National Park (east coast) -GL +7029-02158 America/Scoresbysund Scoresbysund/Ittoqqortoormiit -GL +7634-06847 America/Thule Thule/Pituffik -GR +3758+02343 Europe/Athens -GS -5416-03632 Atlantic/South_Georgia -GT +1438-09031 America/Guatemala -GU,MP +1328+14445 Pacific/Guam -GW +1151-01535 Africa/Bissau -GY +0648-05810 America/Guyana -HK +2217+11409 Asia/Hong_Kong -HN +1406-08713 America/Tegucigalpa -HT +1832-07220 America/Port-au-Prince -HU +4730+01905 Europe/Budapest -ID -0610+10648 Asia/Jakarta Java, Sumatra -ID -0002+10920 Asia/Pontianak Borneo (west, central) -ID -0507+11924 Asia/Makassar Borneo (east, south), Sulawesi/Celebes, Bali, Nusa Tengarra, Timor (west) -ID -0232+14042 Asia/Jayapura New Guinea (West Papua / Irian Jaya), Malukus/Moluccas -IE +5320-00615 Europe/Dublin -IL +314650+0351326 Asia/Jerusalem -IN +2232+08822 Asia/Kolkata -IO -0720+07225 Indian/Chagos -IQ +3321+04425 Asia/Baghdad -IR +3540+05126 Asia/Tehran -IT,SM,VA +4154+01229 Europe/Rome -JM +175805-0764736 America/Jamaica -JO +3157+03556 Asia/Amman -JP,AU +353916+1394441 Asia/Tokyo Eyre Bird Observatory -KE,DJ,ER,ET,KM,MG,SO,TZ,UG,YT -0117+03649 Africa/Nairobi -KG +4254+07436 Asia/Bishkek -KI,MH,TV,UM,WF +0125+17300 Pacific/Tarawa Gilberts, Marshalls, Wake -KI -0247-17143 Pacific/Kanton Phoenix Islands -KI +0152-15720 Pacific/Kiritimati Line Islands -KP +3901+12545 Asia/Pyongyang -KR +3733+12658 Asia/Seoul -KZ +4315+07657 Asia/Almaty most of Kazakhstan -KZ +4448+06528 Asia/Qyzylorda Qyzylorda/Kyzylorda/Kzyl-Orda -KZ +5312+06337 Asia/Qostanay Qostanay/Kostanay/Kustanay -KZ +5017+05710 Asia/Aqtobe Aqtöbe/Aktobe -KZ +4431+05016 Asia/Aqtau Mangghystaū/Mankistau -KZ +4707+05156 Asia/Atyrau Atyraū/Atirau/Gur'yev -KZ +5113+05121 Asia/Oral West Kazakhstan -LB +3353+03530 Asia/Beirut -LK +0656+07951 Asia/Colombo -LR +0618-01047 Africa/Monrovia -LT +5441+02519 Europe/Vilnius -LV +5657+02406 Europe/Riga -LY +3254+01311 Africa/Tripoli -MA +3339-00735 Africa/Casablanca -MD +4700+02850 Europe/Chisinau -MH +0905+16720 Pacific/Kwajalein Kwajalein -MM,CC +1647+09610 Asia/Yangon -MN +4755+10653 Asia/Ulaanbaatar most of Mongolia -MN +4801+09139 Asia/Hovd Bayan-Ölgii, Hovd, Uvs -MO +221150+1133230 Asia/Macau -MQ +1436-06105 America/Martinique -MT +3554+01431 Europe/Malta -MU -2010+05730 Indian/Mauritius -MV,TF +0410+07330 Indian/Maldives Kerguelen, St Paul I, Amsterdam I -MX +1924-09909 America/Mexico_City Central Mexico -MX +2105-08646 America/Cancun Quintana Roo -MX +2058-08937 America/Merida Campeche, Yucatán -MX +2540-10019 America/Monterrey Durango; Coahuila, Nuevo León, Tamaulipas (most areas) -MX +2550-09730 America/Matamoros Coahuila, Nuevo León, Tamaulipas (US border) -MX +2838-10605 America/Chihuahua Chihuahua (most areas) -MX +3144-10629 America/Ciudad_Juarez Chihuahua (US border - west) -MX +2934-10425 America/Ojinaga Chihuahua (US border - east) -MX +2313-10625 America/Mazatlan Baja California Sur, Nayarit (most areas), Sinaloa -MX +2048-10515 America/Bahia_Banderas Bahía de Banderas -MX +2904-11058 America/Hermosillo Sonora -MX +3232-11701 America/Tijuana Baja California -MY,BN +0133+11020 Asia/Kuching Sabah, Sarawak -MZ,BI,BW,CD,MW,RW,ZM,ZW -2558+03235 Africa/Maputo Central Africa Time -NA -2234+01706 Africa/Windhoek -NC -2216+16627 Pacific/Noumea -NF -2903+16758 Pacific/Norfolk -NG,AO,BJ,CD,CF,CG,CM,GA,GQ,NE +0627+00324 Africa/Lagos West Africa Time -NI +1209-08617 America/Managua -NP +2743+08519 Asia/Kathmandu -NR -0031+16655 Pacific/Nauru -NU -1901-16955 Pacific/Niue -NZ,AQ -3652+17446 Pacific/Auckland New Zealand time -NZ -4357-17633 Pacific/Chatham Chatham Islands -PA,CA,KY +0858-07932 America/Panama EST - ON (Atikokan), NU (Coral H) -PE -1203-07703 America/Lima -PF -1732-14934 Pacific/Tahiti Society Islands -PF -0900-13930 Pacific/Marquesas Marquesas Islands -PF -2308-13457 Pacific/Gambier Gambier Islands -PG,AQ,FM -0930+14710 Pacific/Port_Moresby Papua New Guinea (most areas), Chuuk, Yap, Dumont d'Urville -PG -0613+15534 Pacific/Bougainville Bougainville -PH +143512+1205804 Asia/Manila -PK +2452+06703 Asia/Karachi -PL +5215+02100 Europe/Warsaw -PM +4703-05620 America/Miquelon -PN -2504-13005 Pacific/Pitcairn -PR,AG,CA,AI,AW,BL,BQ,CW,DM,GD,GP,KN,LC,MF,MS,SX,TT,VC,VG,VI +182806-0660622 America/Puerto_Rico AST - QC (Lower North Shore) -PS +3130+03428 Asia/Gaza Gaza Strip -PS +313200+0350542 Asia/Hebron West Bank -PT +3843-00908 Europe/Lisbon Portugal (mainland) -PT +3238-01654 Atlantic/Madeira Madeira Islands -PT +3744-02540 Atlantic/Azores Azores -PW +0720+13429 Pacific/Palau -PY -2516-05740 America/Asuncion -QA,BH +2517+05132 Asia/Qatar -RO +4426+02606 Europe/Bucharest -RS,BA,HR,ME,MK,SI +4450+02030 Europe/Belgrade -RU +5443+02030 Europe/Kaliningrad MSK-01 - Kaliningrad -RU +554521+0373704 Europe/Moscow MSK+00 - Moscow area -# Mention RU and UA alphabetically. See "territorial claims" above. -RU,UA +4457+03406 Europe/Simferopol Crimea -RU +5836+04939 Europe/Kirov MSK+00 - Kirov -RU +4844+04425 Europe/Volgograd MSK+00 - Volgograd -RU +4621+04803 Europe/Astrakhan MSK+01 - Astrakhan -RU +5134+04602 Europe/Saratov MSK+01 - Saratov -RU +5420+04824 Europe/Ulyanovsk MSK+01 - Ulyanovsk -RU +5312+05009 Europe/Samara MSK+01 - Samara, Udmurtia -RU +5651+06036 Asia/Yekaterinburg MSK+02 - Urals -RU +5500+07324 Asia/Omsk MSK+03 - Omsk -RU +5502+08255 Asia/Novosibirsk MSK+04 - Novosibirsk -RU +5322+08345 Asia/Barnaul MSK+04 - Altai -RU +5630+08458 Asia/Tomsk MSK+04 - Tomsk -RU +5345+08707 Asia/Novokuznetsk MSK+04 - Kemerovo -RU +5601+09250 Asia/Krasnoyarsk MSK+04 - Krasnoyarsk area -RU +5216+10420 Asia/Irkutsk MSK+05 - Irkutsk, Buryatia -RU +5203+11328 Asia/Chita MSK+06 - Zabaykalsky -RU +6200+12940 Asia/Yakutsk MSK+06 - Lena River -RU +623923+1353314 Asia/Khandyga MSK+06 - Tomponsky, Ust-Maysky -RU +4310+13156 Asia/Vladivostok MSK+07 - Amur River -RU +643337+1431336 Asia/Ust-Nera MSK+07 - Oymyakonsky -RU +5934+15048 Asia/Magadan MSK+08 - Magadan -RU +4658+14242 Asia/Sakhalin MSK+08 - Sakhalin Island -RU +6728+15343 Asia/Srednekolymsk MSK+08 - Sakha (E), N Kuril Is -RU +5301+15839 Asia/Kamchatka MSK+09 - Kamchatka -RU +6445+17729 Asia/Anadyr MSK+09 - Bering Sea -SA,AQ,KW,YE +2438+04643 Asia/Riyadh Syowa -SB,FM -0932+16012 Pacific/Guadalcanal Pohnpei -SD +1536+03232 Africa/Khartoum -SG,AQ,MY +0117+10351 Asia/Singapore peninsular Malaysia, Concordia -SR +0550-05510 America/Paramaribo -SS +0451+03137 Africa/Juba -ST +0020+00644 Africa/Sao_Tome -SV +1342-08912 America/El_Salvador -SY +3330+03618 Asia/Damascus -TC +2128-07108 America/Grand_Turk -TD +1207+01503 Africa/Ndjamena -TH,CX,KH,LA,VN +1345+10031 Asia/Bangkok north Vietnam -TJ +3835+06848 Asia/Dushanbe -TK -0922-17114 Pacific/Fakaofo -TL -0833+12535 Asia/Dili -TM +3757+05823 Asia/Ashgabat -TN +3648+01011 Africa/Tunis -TO -210800-1751200 Pacific/Tongatapu -TR +4101+02858 Europe/Istanbul -TW +2503+12130 Asia/Taipei -UA +5026+03031 Europe/Kyiv most of Ukraine -US +404251-0740023 America/New_York Eastern (most areas) -US +421953-0830245 America/Detroit Eastern - MI (most areas) -US +381515-0854534 America/Kentucky/Louisville Eastern - KY (Louisville area) -US +364947-0845057 America/Kentucky/Monticello Eastern - KY (Wayne) -US +394606-0860929 America/Indiana/Indianapolis Eastern - IN (most areas) -US +384038-0873143 America/Indiana/Vincennes Eastern - IN (Da, Du, K, Mn) -US +410305-0863611 America/Indiana/Winamac Eastern - IN (Pulaski) -US +382232-0862041 America/Indiana/Marengo Eastern - IN (Crawford) -US +382931-0871643 America/Indiana/Petersburg Eastern - IN (Pike) -US +384452-0850402 America/Indiana/Vevay Eastern - IN (Switzerland) -US +415100-0873900 America/Chicago Central (most areas) -US +375711-0864541 America/Indiana/Tell_City Central - IN (Perry) -US +411745-0863730 America/Indiana/Knox Central - IN (Starke) -US +450628-0873651 America/Menominee Central - MI (Wisconsin border) -US +470659-1011757 America/North_Dakota/Center Central - ND (Oliver) -US +465042-1012439 America/North_Dakota/New_Salem Central - ND (Morton rural) -US +471551-1014640 America/North_Dakota/Beulah Central - ND (Mercer) -US +394421-1045903 America/Denver Mountain (most areas) -US +433649-1161209 America/Boise Mountain - ID (south), OR (east) -US,CA +332654-1120424 America/Phoenix MST - AZ (most areas), Creston BC -US +340308-1181434 America/Los_Angeles Pacific -US +611305-1495401 America/Anchorage Alaska (most areas) -US +581807-1342511 America/Juneau Alaska - Juneau area -US +571035-1351807 America/Sitka Alaska - Sitka area -US +550737-1313435 America/Metlakatla Alaska - Annette Island -US +593249-1394338 America/Yakutat Alaska - Yakutat -US +643004-1652423 America/Nome Alaska (west) -US +515248-1763929 America/Adak Alaska - western Aleutians -US +211825-1575130 Pacific/Honolulu Hawaii -UY -345433-0561245 America/Montevideo -UZ +3940+06648 Asia/Samarkand Uzbekistan (west) -UZ +4120+06918 Asia/Tashkent Uzbekistan (east) -VE +1030-06656 America/Caracas -VN +1045+10640 Asia/Ho_Chi_Minh south Vietnam -VU -1740+16825 Pacific/Efate -WS -1350-17144 Pacific/Apia -ZA,LS,SZ -2615+02800 Africa/Johannesburg -# -# The next section contains experimental tab-separated comments for -# use by user agents like tzselect that identify continents and oceans. -# -# For example, the comment "#@AQAntarctica/" means the country code -# AQ is in the continent Antarctica regardless of the Zone name, -# so Pacific/Auckland should be listed under Antarctica as well as -# under the Pacific because its line's country codes include AQ. -# -# If more than one country code is affected each is listed separated -# by commas, e.g., #@IS,SHAtlantic/". If a country code is in -# more than one continent or ocean, each is listed separated by -# commas, e.g., the second column of "#@CY,TRAsia/,Europe/". -# -# These experimental comments are present only for country codes where -# the continent or ocean is not already obvious from the Zone name. -# For example, there is no such comment for RU since it already -# corresponds to Zone names starting with both "Europe/" and "Asia/". -# -#@AQ Antarctica/ -#@IS,SH Atlantic/ -#@CY,TR Asia/,Europe/ -#@SJ Arctic/ -#@CC,CX,KM,MG,YT Indian/ diff --git a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zonenow.tab b/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zonenow.tab deleted file mode 100644 index 093f0a0..0000000 --- a/llmlab/lib/python3.12/site-packages/pytz/zoneinfo/zonenow.tab +++ /dev/null @@ -1,296 +0,0 @@ -# tzdb timezone descriptions, for users who do not care about old timestamps -# -# This file is in the public domain. -# -# From Paul Eggert (2023-12-18): -# This file contains a table where each row stands for a timezone -# where civil timestamps are predicted to agree from now on. -# This file is like zone1970.tab (see zone1970.tab's comments), -# but with the following changes: -# -# 1. Each timezone corresponds to a set of clocks that are planned -# to agree from now on. This is a larger set of clocks than in -# zone1970.tab, where each timezone's clocks must agree from 1970 on. -# 2. The first column is irrelevant and ignored. -# 3. The table is sorted in a different way: -# first by standard time UTC offset; -# then, if DST is used, by daylight saving UTC offset; -# then by time zone abbreviation. -# 4. Every timezone has a nonempty comments column, with wording -# distinguishing the timezone only from other timezones with the -# same UTC offset at some point during the year. -# -# The format of this table is experimental, and may change in future versions. -# -# This table is intended as an aid for users, to help them select timezones -# appropriate for their practical needs. It is not intended to take or -# endorse any position on legal or territorial claims. -# -#XX coordinates TZ comments -# -# -11 - SST -XX -1416-17042 Pacific/Pago_Pago Midway; Samoa ("SST") -# -# -11 -XX -1901-16955 Pacific/Niue Niue -# -# -10 - HST -XX +211825-1575130 Pacific/Honolulu Hawaii ("HST") -# -# -10 -XX -1732-14934 Pacific/Tahiti Tahiti; Cook Islands -# -# -10/-09 - HST / HDT (North America DST) -XX +515248-1763929 America/Adak western Aleutians in Alaska ("HST/HDT") -# -# -09:30 -XX -0900-13930 Pacific/Marquesas Marquesas -# -# -09 -XX -2308-13457 Pacific/Gambier Gambier -# -# -09/-08 - AKST/AKDT (North America DST) -XX +611305-1495401 America/Anchorage most of Alaska ("AKST/AKDT") -# -# -08 -XX -2504-13005 Pacific/Pitcairn Pitcairn -# -# -08/-07 - PST/PDT (North America DST) -XX +340308-1181434 America/Los_Angeles Pacific ("PST/PDT") - US & Canada; Mexico near US border -# -# -07 - MST -XX +332654-1120424 America/Phoenix Mountain Standard ("MST") - Arizona; western Mexico; Yukon -# -# -07/-06 - MST/MDT (North America DST) -XX +394421-1045903 America/Denver Mountain ("MST/MDT") - US & Canada; Mexico near US border -# -# -06 -XX -0054-08936 Pacific/Galapagos Galápagos -# -# -06 - CST -XX +1924-09909 America/Mexico_City Central Standard ("CST") - Saskatchewan; central Mexico; Central America -# -# -06/-05 (Chile DST) -XX -2709-10926 Pacific/Easter Easter Island -# -# -06/-05 - CST/CDT (North America DST) -XX +415100-0873900 America/Chicago Central ("CST/CDT") - US & Canada; Mexico near US border -# -# -05 -XX -1203-07703 America/Lima eastern South America -# -# -05 - EST -XX +175805-0764736 America/Jamaica Eastern Standard ("EST") - Caymans; Jamaica; eastern Mexico; Panama -# -# -05/-04 - CST/CDT (Cuba DST) -XX +2308-08222 America/Havana Cuba -# -# -05/-04 - EST/EDT (North America DST) -XX +404251-0740023 America/New_York Eastern ("EST/EDT") - US & Canada -# -# -04 -XX +1030-06656 America/Caracas western South America -# -# -04 - AST -XX +1828-06954 America/Santo_Domingo Atlantic Standard ("AST") - eastern Caribbean -# -# -04/-03 (Chile DST) -XX -3327-07040 America/Santiago most of Chile -# -# -04/-03 - AST/ADT (North America DST) -XX +4439-06336 America/Halifax Atlantic ("AST/ADT") - Canada; Bermuda -# -# -03:30/-02:30 - NST/NDT (North America DST) -XX +4734-05243 America/St_Johns Newfoundland ("NST/NDT") -# -# -03 -XX -2332-04637 America/Sao_Paulo eastern and southern South America -# -# -03/-02 (North America DST) -XX +4703-05620 America/Miquelon St Pierre & Miquelon -# -# -02 -XX -0351-03225 America/Noronha Fernando de Noronha; South Georgia -# -# -02/-01 (EU DST) -XX +6411-05144 America/Nuuk most of Greenland -# -# -01 -XX +1455-02331 Atlantic/Cape_Verde Cape Verde -# -# -01/+00 (EU DST) -XX +3744-02540 Atlantic/Azores Azores -# -# +00 - GMT -XX +0519-00402 Africa/Abidjan far western Africa; Iceland ("GMT") -# -# +00/+01 - GMT/BST (EU DST) -XX +513030-0000731 Europe/London United Kingdom ("GMT/BST") -# -# +00/+01 - WET/WEST (EU DST) -XX +3843-00908 Europe/Lisbon western Europe ("WET/WEST") -# -# +00/+02 - Troll DST -XX -720041+0023206 Antarctica/Troll Troll Station in Antarctica -# -# +01 - CET -XX +3647+00303 Africa/Algiers Algeria, Tunisia ("CET") -# -# +01 - WAT -XX +0627+00324 Africa/Lagos western Africa ("WAT") -# -# +01/+00 - IST/GMT (EU DST in reverse) -XX +5320-00615 Europe/Dublin Ireland ("IST/GMT") -# -# +01/+00 - (Morocco DST) -XX +3339-00735 Africa/Casablanca Morocco -# -# +01/+02 - CET/CEST (EU DST) -XX +4852+00220 Europe/Paris central Europe ("CET/CEST") -# -# +02 - CAT -XX -2558+03235 Africa/Maputo central Africa ("CAT") -# -# +02 - EET -XX +3254+01311 Africa/Tripoli Libya; Kaliningrad ("EET") -# -# +02 - SAST -XX -2615+02800 Africa/Johannesburg southern Africa ("SAST") -# -# +02/+03 - EET/EEST (EU DST) -XX +3758+02343 Europe/Athens eastern Europe ("EET/EEST") -# -# +02/+03 - EET/EEST (Egypt DST) -XX +3003+03115 Africa/Cairo Egypt -# -# +02/+03 - EET/EEST (Lebanon DST) -XX +3353+03530 Asia/Beirut Lebanon -# -# +02/+03 - EET/EEST (Moldova DST) -XX +4700+02850 Europe/Chisinau Moldova -# -# +02/+03 - EET/EEST (Palestine DST) -XX +3130+03428 Asia/Gaza Palestine -# -# +02/+03 - IST/IDT (Israel DST) -XX +314650+0351326 Asia/Jerusalem Israel -# -# +03 -XX +4101+02858 Europe/Istanbul Near East; Belarus -# -# +03 - EAT -XX -0117+03649 Africa/Nairobi eastern Africa ("EAT") -# -# +03 - MSK -XX +554521+0373704 Europe/Moscow Moscow ("MSK") -# -# +03:30 -XX +3540+05126 Asia/Tehran Iran -# -# +04 -XX +2518+05518 Asia/Dubai Russia; Caucasus; Persian Gulf; Seychelles; Réunion -# -# +04:30 -XX +3431+06912 Asia/Kabul Afghanistan -# -# +05 -XX +4120+06918 Asia/Tashkent Russia; Kazakhstan; Tajikistan; Turkmenistan; Uzbekistan; Maldives -# -# +05 - PKT -XX +2452+06703 Asia/Karachi Pakistan ("PKT") -# -# +05:30 -XX +0656+07951 Asia/Colombo Sri Lanka -# -# +05:30 - IST -XX +2232+08822 Asia/Kolkata India ("IST") -# -# +05:45 -XX +2743+08519 Asia/Kathmandu Nepal -# -# +06 -XX +2343+09025 Asia/Dhaka Russia; Kyrgyzstan; Bhutan; Bangladesh; Chagos -# -# +06:30 -XX +1647+09610 Asia/Yangon Myanmar; Cocos -# -# +07 -XX +1345+10031 Asia/Bangkok Russia; Indochina; Christmas Island -# -# +07 - WIB -XX -0610+10648 Asia/Jakarta Indonesia ("WIB") -# -# +08 -XX +0117+10351 Asia/Singapore Russia; Brunei; Malaysia; Singapore; Concordia -# -# +08 - AWST -XX -3157+11551 Australia/Perth Western Australia ("AWST") -# -# +08 - CST -XX +3114+12128 Asia/Shanghai China ("CST") -# -# +08 - HKT -XX +2217+11409 Asia/Hong_Kong Hong Kong ("HKT") -# -# +08 - PHT -XX +143512+1205804 Asia/Manila Philippines ("PHT") -# -# +08 - WITA -XX -0507+11924 Asia/Makassar Indonesia ("WITA") -# -# +08:45 -XX -3143+12852 Australia/Eucla Eucla -# -# +09 -XX +5203+11328 Asia/Chita Russia; Palau; East Timor -# -# +09 - JST -XX +353916+1394441 Asia/Tokyo Japan ("JST"); Eyre Bird Observatory -# -# +09 - KST -XX +3733+12658 Asia/Seoul Korea ("KST") -# -# +09 - WIT -XX -0232+14042 Asia/Jayapura Indonesia ("WIT") -# -# +09:30 - ACST -XX -1228+13050 Australia/Darwin Northern Territory ("ACST") -# -# +09:30/+10:30 - ACST/ACDT (Australia DST) -XX -3455+13835 Australia/Adelaide South Australia ("ACST/ACDT") -# -# +10 -XX +4310+13156 Asia/Vladivostok Russia; Yap; Chuuk; Papua New Guinea; Dumont d'Urville -# -# +10 - AEST -XX -2728+15302 Australia/Brisbane Queensland ("AEST") -# -# +10 - ChST -XX +1328+14445 Pacific/Guam Mariana Islands ("ChST") -# -# +10/+11 - AEST/AEDT (Australia DST) -XX -3352+15113 Australia/Sydney southeast Australia ("AEST/AEDT") -# -# +10:30/+11 -XX -3133+15905 Australia/Lord_Howe Lord Howe Island -# -# +11 -XX -0613+15534 Pacific/Bougainville Russia; Kosrae; Bougainville; Solomons -# -# +11/+12 (Australia DST) -XX -2903+16758 Pacific/Norfolk Norfolk Island -# -# +12 -XX +5301+15839 Asia/Kamchatka Russia; Tuvalu; Fiji; etc. -# -# +12/+13 (New Zealand DST) -XX -3652+17446 Pacific/Auckland New Zealand ("NZST/NZDT") -# -# +12:45/+13:45 (Chatham DST) -XX -4357-17633 Pacific/Chatham Chatham Islands -# -# +13 -XX -210800-1751200 Pacific/Tongatapu Kanton; Tokelau; Samoa (western); Tonga -# -# +14 -XX +0152-15720 Pacific/Kiritimati Kiritimati diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/__init__.cpython-312.pyc index 4891607..3ba27b7 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/__init__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/__version__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/__version__.cpython-312.pyc index cbeb69e..c3f5ad7 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/__version__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/__version__.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/_internal_utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/_internal_utils.cpython-312.pyc index 4261370..3f599b7 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/_internal_utils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/_internal_utils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/adapters.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/adapters.cpython-312.pyc index 94a7f3d..39fb05d 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/adapters.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/adapters.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/api.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/api.cpython-312.pyc index 5d8dcbf..b1f3313 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/api.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/api.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/auth.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/auth.cpython-312.pyc index 3cd595d..af69a8f 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/auth.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/auth.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/certs.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/certs.cpython-312.pyc index 9c0a354..402a436 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/certs.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/certs.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/compat.cpython-312.pyc index 8001c07..81d329d 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/compat.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/compat.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/cookies.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/cookies.cpython-312.pyc index 8738399..3a64566 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/cookies.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/cookies.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/exceptions.cpython-312.pyc index 1f9ec81..aa58736 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/exceptions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/exceptions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/help.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/help.cpython-312.pyc index 81657e6..9cdad77 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/help.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/help.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/hooks.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/hooks.cpython-312.pyc index 051529d..b434ff3 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/hooks.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/hooks.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/models.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/models.cpython-312.pyc index a5e6cb2..d9d9a10 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/models.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/models.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/packages.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/packages.cpython-312.pyc index daf52b0..4936f33 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/packages.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/packages.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/sessions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/sessions.cpython-312.pyc index a5df427..aedd75d 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/sessions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/sessions.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/status_codes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/status_codes.cpython-312.pyc index e59f91a..d6d7b98 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/status_codes.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/status_codes.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/structures.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/structures.cpython-312.pyc index 18fe482..5727d05 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/structures.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/structures.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/requests/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/requests/__pycache__/utils.cpython-312.pyc index 015ecc8..66a88e5 100644 Binary files a/llmlab/lib/python3.12/site-packages/requests/__pycache__/utils.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/requests/__pycache__/utils.cpython-312.pyc differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/METADATA deleted file mode 100644 index a710533..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/METADATA +++ /dev/null @@ -1,141 +0,0 @@ -Metadata-Version: 2.4 -Name: setuptools -Version: 78.0.2 -Summary: Easily download, build, install, upgrade, and uninstall Python packages -Author-email: Python Packaging Authority -Project-URL: Source, https://github.com/pypa/setuptools -Project-URL: Documentation, https://setuptools.pypa.io/ -Project-URL: Changelog, https://setuptools.pypa.io/en/stable/history.html -Keywords: CPAN PyPI distutils eggs package management -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Classifier: Topic :: Software Development :: Libraries :: Python Modules -Classifier: Topic :: System :: Archiving :: Packaging -Classifier: Topic :: System :: Systems Administration -Classifier: Topic :: Utilities -Requires-Python: >=3.9 -Description-Content-Type: text/x-rst -License-File: LICENSE -Provides-Extra: test -Requires-Dist: pytest!=8.1.*,>=6; extra == "test" -Requires-Dist: virtualenv>=13.0.0; extra == "test" -Requires-Dist: wheel>=0.44.0; extra == "test" -Requires-Dist: pip>=19.1; extra == "test" -Requires-Dist: packaging>=24.2; extra == "test" -Requires-Dist: jaraco.envs>=2.2; extra == "test" -Requires-Dist: pytest-xdist>=3; extra == "test" -Requires-Dist: jaraco.path>=3.7.2; extra == "test" -Requires-Dist: build[virtualenv]>=1.0.3; extra == "test" -Requires-Dist: filelock>=3.4.0; extra == "test" -Requires-Dist: ini2toml[lite]>=0.14; extra == "test" -Requires-Dist: tomli-w>=1.0.0; extra == "test" -Requires-Dist: pytest-timeout; extra == "test" -Requires-Dist: pytest-perf; sys_platform != "cygwin" and extra == "test" -Requires-Dist: jaraco.develop>=7.21; (python_version >= "3.9" and sys_platform != "cygwin") and extra == "test" -Requires-Dist: pytest-home>=0.5; extra == "test" -Requires-Dist: pytest-subprocess; extra == "test" -Requires-Dist: pyproject-hooks!=1.1; extra == "test" -Requires-Dist: jaraco.test>=5.5; extra == "test" -Provides-Extra: doc -Requires-Dist: sphinx>=3.5; extra == "doc" -Requires-Dist: jaraco.packaging>=9.3; extra == "doc" -Requires-Dist: rst.linker>=1.9; extra == "doc" -Requires-Dist: furo; extra == "doc" -Requires-Dist: sphinx-lint; extra == "doc" -Requires-Dist: jaraco.tidelift>=1.4; extra == "doc" -Requires-Dist: pygments-github-lexers==0.0.5; extra == "doc" -Requires-Dist: sphinx-favicon; extra == "doc" -Requires-Dist: sphinx-inline-tabs; extra == "doc" -Requires-Dist: sphinx-reredirects; extra == "doc" -Requires-Dist: sphinxcontrib-towncrier; extra == "doc" -Requires-Dist: sphinx-notfound-page<2,>=1; extra == "doc" -Requires-Dist: pyproject-hooks!=1.1; extra == "doc" -Requires-Dist: towncrier<24.7; extra == "doc" -Provides-Extra: ssl -Provides-Extra: certs -Provides-Extra: core -Requires-Dist: packaging>=24.2; extra == "core" -Requires-Dist: more_itertools>=8.8; extra == "core" -Requires-Dist: jaraco.text>=3.7; extra == "core" -Requires-Dist: importlib_metadata>=6; python_version < "3.10" and extra == "core" -Requires-Dist: tomli>=2.0.1; python_version < "3.11" and extra == "core" -Requires-Dist: wheel>=0.43.0; extra == "core" -Requires-Dist: platformdirs>=4.2.2; extra == "core" -Requires-Dist: jaraco.functools>=4; extra == "core" -Requires-Dist: more_itertools; extra == "core" -Provides-Extra: check -Requires-Dist: pytest-checkdocs>=2.4; extra == "check" -Requires-Dist: pytest-ruff>=0.2.1; sys_platform != "cygwin" and extra == "check" -Requires-Dist: ruff>=0.8.0; sys_platform != "cygwin" and extra == "check" -Provides-Extra: cover -Requires-Dist: pytest-cov; extra == "cover" -Provides-Extra: enabler -Requires-Dist: pytest-enabler>=2.2; extra == "enabler" -Provides-Extra: type -Requires-Dist: pytest-mypy; extra == "type" -Requires-Dist: mypy==1.14.*; extra == "type" -Requires-Dist: importlib_metadata>=7.0.2; python_version < "3.10" and extra == "type" -Requires-Dist: jaraco.develop>=7.21; sys_platform != "cygwin" and extra == "type" -Dynamic: license-file - -.. |pypi-version| image:: https://img.shields.io/pypi/v/setuptools.svg - :target: https://pypi.org/project/setuptools - -.. |py-version| image:: https://img.shields.io/pypi/pyversions/setuptools.svg - -.. |test-badge| image:: https://github.com/pypa/setuptools/actions/workflows/main.yml/badge.svg - :target: https://github.com/pypa/setuptools/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. |ruff-badge| image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. |docs-badge| image:: https://img.shields.io/readthedocs/setuptools/latest.svg - :target: https://setuptools.pypa.io - -.. |skeleton-badge| image:: https://img.shields.io/badge/skeleton-2025-informational - :target: https://blog.jaraco.com/skeleton - -.. |codecov-badge| image:: https://img.shields.io/codecov/c/github/pypa/setuptools/master.svg?logo=codecov&logoColor=white - :target: https://codecov.io/gh/pypa/setuptools - -.. |tidelift-badge| image:: https://tidelift.com/badges/github/pypa/setuptools?style=flat - :target: https://tidelift.com/subscription/pkg/pypi-setuptools?utm_source=pypi-setuptools&utm_medium=readme - -.. |discord-badge| image:: https://img.shields.io/discord/803025117553754132 - :target: https://discord.com/channels/803025117553754132/815945031150993468 - :alt: Discord - -|pypi-version| |py-version| |test-badge| |ruff-badge| |docs-badge| |skeleton-badge| |codecov-badge| |discord-badge| - -See the `Quickstart `_ -and the `User's Guide `_ for -instructions on how to use Setuptools. - -Questions and comments should be directed to `GitHub Discussions -`_. -Bug reports and especially tested patches may be -submitted directly to the `bug tracker -`_. - - -Code of Conduct -=============== - -Everyone interacting in the setuptools project's codebases, issue trackers, -chat rooms, and fora is expected to follow the -`PSF Code of Conduct `_. - - -For Enterprise -============== - -Available as part of the Tidelift Subscription. - -Setuptools and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. - -`Learn more `_. diff --git a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/RECORD deleted file mode 100644 index fe68373..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/RECORD +++ /dev/null @@ -1,872 +0,0 @@ -_distutils_hack/__init__.py,sha256=34HmvLo07j45Uvd2VR-2aRQ7lJD91sTK6zJgn5fphbQ,6755 -_distutils_hack/__pycache__/__init__.cpython-312.pyc,, -_distutils_hack/__pycache__/override.cpython-312.pyc,, -_distutils_hack/override.py,sha256=Eu_s-NF6VIZ4Cqd0tbbA5wtWky2IZPNd8et6GLt1mzo,44 -distutils-precedence.pth,sha256=JjjOniUA5XKl4N5_rtZmHrVp0baW_LoHsN0iPaX10iQ,151 -pkg_resources/__init__.py,sha256=-rh7XOnTxdGuC-_9FAyu5D6s8BL1UsBehxUtj7a-IVo,126203 -pkg_resources/__pycache__/__init__.cpython-312.pyc,, -pkg_resources/api_tests.txt,sha256=XEdvy4igHHrq2qNHNMHnlfO6XSQKNqOyLHbl6QcpfAI,12595 -pkg_resources/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pkg_resources/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pkg_resources/tests/__pycache__/__init__.cpython-312.pyc,, -pkg_resources/tests/__pycache__/test_find_distributions.cpython-312.pyc,, -pkg_resources/tests/__pycache__/test_integration_zope_interface.cpython-312.pyc,, -pkg_resources/tests/__pycache__/test_markers.cpython-312.pyc,, -pkg_resources/tests/__pycache__/test_pkg_resources.cpython-312.pyc,, -pkg_resources/tests/__pycache__/test_resources.cpython-312.pyc,, -pkg_resources/tests/__pycache__/test_working_set.cpython-312.pyc,, -pkg_resources/tests/data/my-test-package-source/__pycache__/setup.cpython-312.pyc,, -pkg_resources/tests/data/my-test-package-source/setup.cfg,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -pkg_resources/tests/data/my-test-package-source/setup.py,sha256=1VobhAZbMb7M9mfhb_NE8PwDsvukoWLs9aUAS0pYhe8,105 -pkg_resources/tests/data/my-test-package-zip/my-test-package.zip,sha256=AYRcQ39GVePPnMT8TknP1gdDHyJnXhthESmpAjnzSCI,1809 -pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/PKG-INFO,sha256=JvWv9Io2PAuYwEEw2fBW4Qc5YvdbkscpKX1kmLzsoHk,187 -pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/SOURCES.txt,sha256=4ClkH8eTovZrdVrJFsVuxdbMEF--lBVSuKonDAPE5Jc,208 -pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/dependency_links.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1 -pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/top_level.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1 -pkg_resources/tests/data/my-test-package_unpacked-egg/my_test_package-1.0-py3.7.egg/EGG-INFO/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1 -pkg_resources/tests/data/my-test-package_zipped-egg/my_test_package-1.0-py3.7.egg,sha256=ZTlMGxjRGiKDNkiA2c75jbQH2TWIteP00irF9gvczbo,843 -pkg_resources/tests/test_find_distributions.py,sha256=U91cov5L1COAIWLNq3Xy4plU7_MnOE1WtXMu6iV2waM,1972 -pkg_resources/tests/test_integration_zope_interface.py,sha256=nzVoK557KZQN0V3DIQ1sVeaCOgt4Kpl-CODAWsO7pmc,1652 -pkg_resources/tests/test_markers.py,sha256=0orKg7UMDf7fnuNQvRMOc-EF9EAP_JTQnk4mtGgbW50,241 -pkg_resources/tests/test_pkg_resources.py,sha256=5Mt4bJQhLCL8j8cC46Uv32Np2Xc1TTxLGawIfET55Fk,17111 -pkg_resources/tests/test_resources.py,sha256=K0LqMAUGpRQ9pUb9K0vyI7GesvtlQvTH074m-E2VQlo,31252 -pkg_resources/tests/test_working_set.py,sha256=lRtGJWIixSwSMSbjHgRxeJEQiLMRXcz3xzJL2qL7eXY,8602 -setuptools-78.0.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools-78.0.2.dist-info/METADATA,sha256=iMxFapDEf8mq6b5gYRBxz7_s3MUGtIGN0p5v_5NXKkc,6599 -setuptools-78.0.2.dist-info/RECORD,, -setuptools-78.0.2.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91 -setuptools-78.0.2.dist-info/entry_points.txt,sha256=zkgthpf_Fa9NVE9p6FKT3Xk9DR1faAcRU4coggsV7jA,2449 -setuptools-78.0.2.dist-info/licenses/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools-78.0.2.dist-info/top_level.txt,sha256=d9yL39v_W7qmKDDSH6sT4bE0j_Ls1M3P161OGgdsm4g,41 -setuptools/__init__.py,sha256=AQsMeRFWz9CQ9aBtcSkbB4Dn8t2w86-GPriklpoAjew,10406 -setuptools/__pycache__/__init__.cpython-312.pyc,, -setuptools/__pycache__/_core_metadata.cpython-312.pyc,, -setuptools/__pycache__/_entry_points.cpython-312.pyc,, -setuptools/__pycache__/_imp.cpython-312.pyc,, -setuptools/__pycache__/_importlib.cpython-312.pyc,, -setuptools/__pycache__/_itertools.cpython-312.pyc,, -setuptools/__pycache__/_normalization.cpython-312.pyc,, -setuptools/__pycache__/_path.cpython-312.pyc,, -setuptools/__pycache__/_reqs.cpython-312.pyc,, -setuptools/__pycache__/_shutil.cpython-312.pyc,, -setuptools/__pycache__/_static.cpython-312.pyc,, -setuptools/__pycache__/archive_util.cpython-312.pyc,, -setuptools/__pycache__/build_meta.cpython-312.pyc,, -setuptools/__pycache__/depends.cpython-312.pyc,, -setuptools/__pycache__/discovery.cpython-312.pyc,, -setuptools/__pycache__/dist.cpython-312.pyc,, -setuptools/__pycache__/errors.cpython-312.pyc,, -setuptools/__pycache__/extension.cpython-312.pyc,, -setuptools/__pycache__/glob.cpython-312.pyc,, -setuptools/__pycache__/installer.cpython-312.pyc,, -setuptools/__pycache__/launch.cpython-312.pyc,, -setuptools/__pycache__/logging.cpython-312.pyc,, -setuptools/__pycache__/modified.cpython-312.pyc,, -setuptools/__pycache__/monkey.cpython-312.pyc,, -setuptools/__pycache__/msvc.cpython-312.pyc,, -setuptools/__pycache__/namespaces.cpython-312.pyc,, -setuptools/__pycache__/package_index.cpython-312.pyc,, -setuptools/__pycache__/sandbox.cpython-312.pyc,, -setuptools/__pycache__/unicode_utils.cpython-312.pyc,, -setuptools/__pycache__/version.cpython-312.pyc,, -setuptools/__pycache__/warnings.cpython-312.pyc,, -setuptools/__pycache__/wheel.cpython-312.pyc,, -setuptools/__pycache__/windows_support.cpython-312.pyc,, -setuptools/_core_metadata.py,sha256=T7Tjp-WSoN881adev3R1wzXCPnkDHqbC2MgylN1yjS8,11978 -setuptools/_distutils/__init__.py,sha256=xGYuhWwLG07J0Q49BVnEjPy6wyDcd6veJMDJX7ljlyM,359 -setuptools/_distutils/__pycache__/__init__.cpython-312.pyc,, -setuptools/_distutils/__pycache__/_log.cpython-312.pyc,, -setuptools/_distutils/__pycache__/_macos_compat.cpython-312.pyc,, -setuptools/_distutils/__pycache__/_modified.cpython-312.pyc,, -setuptools/_distutils/__pycache__/_msvccompiler.cpython-312.pyc,, -setuptools/_distutils/__pycache__/archive_util.cpython-312.pyc,, -setuptools/_distutils/__pycache__/ccompiler.cpython-312.pyc,, -setuptools/_distutils/__pycache__/cmd.cpython-312.pyc,, -setuptools/_distutils/__pycache__/core.cpython-312.pyc,, -setuptools/_distutils/__pycache__/cygwinccompiler.cpython-312.pyc,, -setuptools/_distutils/__pycache__/debug.cpython-312.pyc,, -setuptools/_distutils/__pycache__/dep_util.cpython-312.pyc,, -setuptools/_distutils/__pycache__/dir_util.cpython-312.pyc,, -setuptools/_distutils/__pycache__/dist.cpython-312.pyc,, -setuptools/_distutils/__pycache__/errors.cpython-312.pyc,, -setuptools/_distutils/__pycache__/extension.cpython-312.pyc,, -setuptools/_distutils/__pycache__/fancy_getopt.cpython-312.pyc,, -setuptools/_distutils/__pycache__/file_util.cpython-312.pyc,, -setuptools/_distutils/__pycache__/filelist.cpython-312.pyc,, -setuptools/_distutils/__pycache__/log.cpython-312.pyc,, -setuptools/_distutils/__pycache__/spawn.cpython-312.pyc,, -setuptools/_distutils/__pycache__/sysconfig.cpython-312.pyc,, -setuptools/_distutils/__pycache__/text_file.cpython-312.pyc,, -setuptools/_distutils/__pycache__/unixccompiler.cpython-312.pyc,, -setuptools/_distutils/__pycache__/util.cpython-312.pyc,, -setuptools/_distutils/__pycache__/version.cpython-312.pyc,, -setuptools/_distutils/__pycache__/versionpredicate.cpython-312.pyc,, -setuptools/_distutils/__pycache__/zosccompiler.cpython-312.pyc,, -setuptools/_distutils/_log.py,sha256=i-lNTTcXS8TmWITJ6DODGvtW5z5tMattJQ76h8rZxQU,42 -setuptools/_distutils/_macos_compat.py,sha256=JzUGhF4E5yIITHbUaPobZEWjGHdrrcNV63z86S4RjBc,239 -setuptools/_distutils/_modified.py,sha256=RF1n1CexyDYV3lvGbeXS0s-XCJVboDOIUbA8wEQqYTY,3211 -setuptools/_distutils/_msvccompiler.py,sha256=QdFAH4JlMIxLoOaHUzm-ngK3H8jAoTo924XJ3Fe7SCQ,88 -setuptools/_distutils/archive_util.py,sha256=Qw2z-Pt-NV8lNUQrzjs3XDGWCWHMPnqHLyt8TiD2XEA,8884 -setuptools/_distutils/ccompiler.py,sha256=FKVjqzGJ7c-FtouNjhLiaMPm5LKMZHHAruXf8LU216c,524 -setuptools/_distutils/cmd.py,sha256=hXtaRaH7QBnfNOIqEvCt47iwZzD9MVvBdhhdQctHsxM,22186 -setuptools/_distutils/command/__init__.py,sha256=GfFAzbBqk1qxSH4BdaKioKS4hRRnD44BAmwEN85C4u8,386 -setuptools/_distutils/command/__pycache__/__init__.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/_framework_compat.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/bdist.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/bdist_dumb.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/bdist_rpm.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/build.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/build_clib.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/build_ext.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/build_py.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/build_scripts.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/check.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/clean.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/config.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/install.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/install_data.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/install_egg_info.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/install_headers.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/install_lib.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/install_scripts.cpython-312.pyc,, -setuptools/_distutils/command/__pycache__/sdist.cpython-312.pyc,, -setuptools/_distutils/command/_framework_compat.py,sha256=0iZdSJYzGRWCCvzRDKE-R0-_yaAYvFMd1ylXb2eYXug,1609 -setuptools/_distutils/command/bdist.py,sha256=jWtk61R7fWNUUNxJV0thTZzU5n80L3Ay1waSiP9kiLA,5854 -setuptools/_distutils/command/bdist_dumb.py,sha256=Hx1jAqoZNxYIy4N5TLzUp6J5fi8Ls18py7UlLNFhO2E,4631 -setuptools/_distutils/command/bdist_rpm.py,sha256=nxcXXv5a7B-1ntWu4DbGmCtES4EBINrJaBQcRNAYCJI,21785 -setuptools/_distutils/command/build.py,sha256=SpHlagf0iNaKVyIhxDfhPFZ8X1-LAWOCQACy-yt2K0w,5923 -setuptools/_distutils/command/build_clib.py,sha256=aMqZcUfCbOAu_xr-A9iW-Q9YZHzpDGLRTezOgMQJmSQ,7777 -setuptools/_distutils/command/build_ext.py,sha256=zrrsu9HXnzV6bXYbJuZCK4SwVZMjKnl4pG1o3bNcxtc,32710 -setuptools/_distutils/command/build_py.py,sha256=Vfq-INemoMbg6f003BTy_Ufp8bjOZhmFIhpKMcfXLgs,16696 -setuptools/_distutils/command/build_scripts.py,sha256=tUpEzwTsnrP8qrNory3ldPB240QDCFkMp-pdYPs2wTk,5118 -setuptools/_distutils/command/check.py,sha256=yoNe2MPY4JcTM7rwoIQdfZ75q5Ri058I2coi-Gq9CjM,4946 -setuptools/_distutils/command/clean.py,sha256=dQAacOabwBXU9JoZ-1GFusq3eFltDaeXJFSYncqGbvE,2644 -setuptools/_distutils/command/config.py,sha256=BuUdPu91Vo9w44xzD1RQfiyXfSfVcNpeX3aeoKcGAOw,12818 -setuptools/_distutils/command/install.py,sha256=-JenB-mua4hc2RI_-W8F9PnP_J-OaFO7E0PJGKxLo1o,30072 -setuptools/_distutils/command/install_data.py,sha256=GzBlUWWKubTYJlP-L0auUriq9cL-5RKOcoyHTttKj0Q,2875 -setuptools/_distutils/command/install_egg_info.py,sha256=ffiLoU1ivQJ8q2_WL7ZygZbUcOsgdFLKL7otEIJWWkI,2868 -setuptools/_distutils/command/install_headers.py,sha256=5ciKCj8c3XKsYNKdkdMvnypaUCKcoWCDeeZij3fD-Z4,1272 -setuptools/_distutils/command/install_lib.py,sha256=2s9-m5-b1qKm51F28lB5L39Z6vv_GHMlv9dNBSupok0,8588 -setuptools/_distutils/command/install_scripts.py,sha256=M0pPdiaqB7TGmqTMujpGGeiL0Iq_CTeGjMFtrmDmwzM,2002 -setuptools/_distutils/command/sdist.py,sha256=cRIF6Ht1hJ6ayOOFVycMFBUNxjo94e_rFYPx4Hi8Ahc,19151 -setuptools/_distutils/compat/__init__.py,sha256=J20aXGjJ86Rg41xFLIWlcWCgZ9edMdJ9vvdNEQ87vPQ,522 -setuptools/_distutils/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/_distutils/compat/__pycache__/numpy.cpython-312.pyc,, -setuptools/_distutils/compat/__pycache__/py39.cpython-312.pyc,, -setuptools/_distutils/compat/numpy.py,sha256=UFgneZw9w97g4c-yGoAIOyLxUOWQ-fPRIhhfMs7_Ouc,167 -setuptools/_distutils/compat/py39.py,sha256=hOsD6lwZLqZoMnacNJ3P6nUA-LJQhEpVtYTzVH0o96M,1964 -setuptools/_distutils/compilers/C/__pycache__/base.cpython-312.pyc,, -setuptools/_distutils/compilers/C/__pycache__/cygwin.cpython-312.pyc,, -setuptools/_distutils/compilers/C/__pycache__/errors.cpython-312.pyc,, -setuptools/_distutils/compilers/C/__pycache__/msvc.cpython-312.pyc,, -setuptools/_distutils/compilers/C/__pycache__/unix.cpython-312.pyc,, -setuptools/_distutils/compilers/C/__pycache__/zos.cpython-312.pyc,, -setuptools/_distutils/compilers/C/base.py,sha256=XR1rBCStCquqm7QOYXD41-LfvsFcPpGxrwxeXzJyn_w,54876 -setuptools/_distutils/compilers/C/cygwin.py,sha256=DUlwQSb55aj7OdcmcddrmCmVEjEaxIiJ5hHUO3GBPNs,11844 -setuptools/_distutils/compilers/C/errors.py,sha256=sKOVzJajMUmNdfywo9UM_QQGsKFcclDhtI5TlCiXMLc,573 -setuptools/_distutils/compilers/C/msvc.py,sha256=elzG8v9jN5QytLMwLCdUdSuZ3eZ3R98VUvnm9Y2PBCA,21404 -setuptools/_distutils/compilers/C/tests/__pycache__/test_base.cpython-312.pyc,, -setuptools/_distutils/compilers/C/tests/__pycache__/test_cygwin.cpython-312.pyc,, -setuptools/_distutils/compilers/C/tests/__pycache__/test_mingw.cpython-312.pyc,, -setuptools/_distutils/compilers/C/tests/__pycache__/test_msvc.cpython-312.pyc,, -setuptools/_distutils/compilers/C/tests/__pycache__/test_unix.cpython-312.pyc,, -setuptools/_distutils/compilers/C/tests/test_base.py,sha256=rdhHc56bhXtm5NnN9BSHwr6c69UqzMItZQzlw2AsdMc,2706 -setuptools/_distutils/compilers/C/tests/test_cygwin.py,sha256=UgV2VgUXj3VulcbDc0UBWfEyJDx42tgSwS4LzHix3mY,2701 -setuptools/_distutils/compilers/C/tests/test_mingw.py,sha256=hCmwyywISpRoyOySbFHBL4TprWRV0mUWDKmOLO8XBXE,1900 -setuptools/_distutils/compilers/C/tests/test_msvc.py,sha256=DlGjmZ1mBSMXIgmlu80BKc7V-EJOZuYucwJwFh5dn28,4151 -setuptools/_distutils/compilers/C/tests/test_unix.py,sha256=ErbYWio7ejY2ZqQmPk4AwOu1HFW4-_-aZdUvGa1W2Fw,11834 -setuptools/_distutils/compilers/C/unix.py,sha256=l7CxY4rDJAECJo-vcv6io0SBmmPJ9JmN5mSmZcin2VU,16502 -setuptools/_distutils/compilers/C/zos.py,sha256=vnNeWLRZkdIkdZ-YyBnL8idTUfcCOn0tLMW5OBJ0ScU,6586 -setuptools/_distutils/core.py,sha256=GEHKaFC48T3o-_SmH4864GvKyx1IgbVC6ISIPVlx7a4,9364 -setuptools/_distutils/cygwinccompiler.py,sha256=mG_cU8SVZ4amD_VtF5vH6BXP0-kghGsDPbDSXrQ963c,594 -setuptools/_distutils/debug.py,sha256=N6MrTAqK6l9SVk6tWweR108PM8Ol7qNlfyV-nHcLhsY,139 -setuptools/_distutils/dep_util.py,sha256=xN75p6ZpHhMiHEc-rpL2XilJQynHnDNiafHteaZ4tjU,349 -setuptools/_distutils/dir_util.py,sha256=DXPUlfVVGsg9B-Jgg4At_j9T7vM60OgwNXkQHqTo7-I,7236 -setuptools/_distutils/dist.py,sha256=gW598UE0WMkzXQQ31Nr-8L7MPw0oIOz5OSSRzYZlwrM,55794 -setuptools/_distutils/errors.py,sha256=PPE2oDRh5y9Q1beKK9rhdvDaCzQhi4HCXs4KcqfqgZY,3092 -setuptools/_distutils/extension.py,sha256=Foyu4gULcPqm1_U9zrYYHxNk4NqglXv1rbsOk_QrSds,11155 -setuptools/_distutils/fancy_getopt.py,sha256=PjdO-bWCW0imV_UN-MGEw9R2GP2OiE8pHjITgmTAY3Q,17895 -setuptools/_distutils/file_util.py,sha256=YFQL_pD3hLuER9II_H6-hDC_YIGEookdd4wedLuiTW0,7978 -setuptools/_distutils/filelist.py,sha256=MBeSRJmPcKmDv8ooZgSU4BiQPZ0Khwv8l_jhD50XycI,15337 -setuptools/_distutils/log.py,sha256=VyBs5j7z4-K6XTEEBThUc9HyMpoPLGtQpERqbz5ylww,1200 -setuptools/_distutils/spawn.py,sha256=zseCh9sEifyp0I5Vg719JNIASlROJ2ehXqQnHlpt89Q,4086 -setuptools/_distutils/sysconfig.py,sha256=KeI8OHbMuEzHJ8Q0cBez9KZny8iRy6Z6Y0AkMz1jlsU,19728 -setuptools/_distutils/tests/__init__.py,sha256=j-IoPZEtQv3EOPuqNTwalr6GLyRjzCC-OOaNvZzmHsI,1485 -setuptools/_distutils/tests/__pycache__/__init__.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/support.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_archive_util.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_bdist.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_bdist_dumb.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_bdist_rpm.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_build.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_build_clib.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_build_ext.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_build_py.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_build_scripts.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_check.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_clean.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_cmd.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_config_cmd.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_core.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_dir_util.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_dist.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_extension.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_file_util.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_filelist.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_install.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_install_data.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_install_headers.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_install_lib.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_install_scripts.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_log.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_modified.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_sdist.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_spawn.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_sysconfig.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_text_file.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_util.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_version.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/test_versionpredicate.cpython-312.pyc,, -setuptools/_distutils/tests/__pycache__/unix_compat.cpython-312.pyc,, -setuptools/_distutils/tests/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_distutils/tests/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/_distutils/tests/compat/__pycache__/py39.cpython-312.pyc,, -setuptools/_distutils/tests/compat/py39.py,sha256=t0GBTM-30jX-9zCfkwlNBFtzzabemx6065mJ0d9_VRw,1026 -setuptools/_distutils/tests/support.py,sha256=tjsYsyxvpTK4NrkCseh2ujvDIGV0Mf_b5SI5fP2T0yM,4099 -setuptools/_distutils/tests/test_archive_util.py,sha256=jozimSwPBF-JoJfN_vDaiVGZp66BNcWZGh34FlW57DQ,11787 -setuptools/_distutils/tests/test_bdist.py,sha256=xNHxUsLlHsZQRwkzLb_iSD24s-9Mk-NX2ffBWwOyPyc,1396 -setuptools/_distutils/tests/test_bdist_dumb.py,sha256=QF05MHNhPOdZyh88Xpw8KsO64s7pRFkl8KL-RoV4XK0,2247 -setuptools/_distutils/tests/test_bdist_rpm.py,sha256=Hdm-pwWgyaoGdGbEcGZa8cRhGU45y8gHK8umOanTjik,3932 -setuptools/_distutils/tests/test_build.py,sha256=JJY5XpOZco25ZY0pstxl-iI8mHsWP0ujf5o8aOtuZYY,1742 -setuptools/_distutils/tests/test_build_clib.py,sha256=Mo1ZFb4C1VXBYOGvnallwN7YCnTtr24akLDO8Zi4CsY,4331 -setuptools/_distutils/tests/test_build_ext.py,sha256=QFO9qYVhWWdJu17HXc4x9RMnLZlhk0lAHi9HVppbuX4,22545 -setuptools/_distutils/tests/test_build_py.py,sha256=NsfmRrojOHBXNMqWR_mp5g4PLTgjhD7iZFUffGZFIdw,6882 -setuptools/_distutils/tests/test_build_scripts.py,sha256=cD-FRy-oX55sXRX5Ez5xQCaeHrWajyKc4Xuwv2fe48w,2880 -setuptools/_distutils/tests/test_check.py,sha256=hHSV07qf7YoSxGsTbbsUQ9tssZz5RRNdbrY1s2SwaFI,6226 -setuptools/_distutils/tests/test_clean.py,sha256=hPH6jfIpGFUrvWbF1txkiNVSNaAxt2wq5XjV499zO4E,1240 -setuptools/_distutils/tests/test_cmd.py,sha256=bgRB79mitoOKR1OiyZHnCogvGxt3pWkxeTqIC04lQWQ,3254 -setuptools/_distutils/tests/test_config_cmd.py,sha256=Zs6WX0IfxDvmuC19XzuVNnYCnTr9Y-hl73TAmDSBN4Y,2664 -setuptools/_distutils/tests/test_core.py,sha256=L7XKVAxa-MGoAZeANopnuK9fRKneYhkSQpgw8XQvcF8,3829 -setuptools/_distutils/tests/test_dir_util.py,sha256=E84lC-k4riVUwURyWaQ0Jqx2ui2-io-0RuJa3M7qkJs,4500 -setuptools/_distutils/tests/test_dist.py,sha256=a6wlc5fQJd5qQ6HOndzcupNhjTxvj6-_JLtpuYvaP1M,18793 -setuptools/_distutils/tests/test_extension.py,sha256=-YejLgZCuycFrOBd64pVH0JvwMc9NwhzHvQxvvjXHqk,3670 -setuptools/_distutils/tests/test_file_util.py,sha256=livjnl3FkilQlrB2rFdFQq9nvjEVZHynNya0bfzv_b4,3522 -setuptools/_distutils/tests/test_filelist.py,sha256=rJwkqCUfkGDgWlD22TozsT8ycbupMHB8DXqThzwT1T4,10766 -setuptools/_distutils/tests/test_install.py,sha256=TfCB0ykhIxydIC2Q4SuTAZzSHvteMHgrBL9whoSgK9Q,8618 -setuptools/_distutils/tests/test_install_data.py,sha256=vKq3K97k0hBAnOg38nmwEdf7cEDVr9rTVyCeJolgb4A,2464 -setuptools/_distutils/tests/test_install_headers.py,sha256=PVAYpo_tYl980Qf64DPOmmSvyefIHdU06f7VsJeZykE,936 -setuptools/_distutils/tests/test_install_lib.py,sha256=qri6Rl-maNTQrNDV8DbeXNl0hjsfRIKiI4rfZLrmWBI,3612 -setuptools/_distutils/tests/test_install_scripts.py,sha256=KE3v0cDkFW-90IOID-OmZZGM2mhy-ZkEuuW7UXS2SHw,1600 -setuptools/_distutils/tests/test_log.py,sha256=isFtOufloCyEdZaQOV7cVUr46GwtdVMj43mGBB5XH7k,323 -setuptools/_distutils/tests/test_modified.py,sha256=h1--bOWmtJo1bpVV6uRhdnS9br71CBiNDM1MDwSGpug,4221 -setuptools/_distutils/tests/test_sdist.py,sha256=cfzUhlCA418-1vH9ta3IBs26c_jUBbkJoFOK5GnAyNk,15062 -setuptools/_distutils/tests/test_spawn.py,sha256=eS8w9D7bTxyFLSyRahJWeuh8Kc1F8RWWiY_dSG5B5Bc,4803 -setuptools/_distutils/tests/test_sysconfig.py,sha256=lxM8LsUi1TomjDV4HoYK8u5nUoBkeNL60Uq8PY1DcwU,11986 -setuptools/_distutils/tests/test_text_file.py,sha256=WQWSB5AfdBDZaMA8BFgipJPnsJb_2SKMfL90fSkRVtw,3460 -setuptools/_distutils/tests/test_util.py,sha256=H9zlZ4z4Vh4TfjNYDBsxP7wguQLpxCfJYyOcm1yZU3c,7988 -setuptools/_distutils/tests/test_version.py,sha256=ahfg_mP8wRy1sgwY-_Px5hrjgf6_upTIpnCgpR4yWRk,2750 -setuptools/_distutils/tests/test_versionpredicate.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_distutils/tests/unix_compat.py,sha256=z-op6C2iVdX1aq5BIBR7cqOxijKE97alNwJqHNdLpoI,386 -setuptools/_distutils/text_file.py,sha256=z4dkOJBr9Bo2LG0TNqm8sD63LEEaKSSP0J0bWBrFG3c,12101 -setuptools/_distutils/unixccompiler.py,sha256=1bXJWH4fiu_A2WfriHzf88xjllQTXnnjUkZdRKs9cWU,212 -setuptools/_distutils/util.py,sha256=Njfnqk60zMdkiAjRnGcTWX3t49-obHapOlbNvyIl02I,18094 -setuptools/_distutils/version.py,sha256=vImT5-ECXkQ21oKL0XYFiTqK6NyM09cpzBNoA_34CQU,12619 -setuptools/_distutils/versionpredicate.py,sha256=qBWQ6wTj12ODytoTmIydefIY2jb4uY1sdbgbuLn-IJM,5205 -setuptools/_distutils/zosccompiler.py,sha256=svdiXZ2kdcwKrJKfhUhib03y8gz7aGZKukXH3I7YkBc,58 -setuptools/_entry_points.py,sha256=Y3QUE9JKFW_YyquDnpffNWSs6f3jKEt1e-dnx--9-Kw,2310 -setuptools/_imp.py,sha256=YY1EjZEN-0zYci1cxO10B_adAEOr7i8eK8JoCc9Ierc,2435 -setuptools/_importlib.py,sha256=aKIjcK0HKXNz2D-XTrxaixGn_juTkONwmu3dcheMOF0,223 -setuptools/_itertools.py,sha256=jWRfsIrpC7myooz3hDURj9GtvpswZeKXg2HakmEhNjo,657 -setuptools/_normalization.py,sha256=kAmGfrwjF5djydEfLLyKgjkXCbL_0_ZxUPO-DlLlmIY,5824 -setuptools/_path.py,sha256=cPv41v03HD7uEYqCIo-E_cGRfpPVr4lywBCiK-HSrCg,2685 -setuptools/_reqs.py,sha256=QI3C9uOBSNRccu208qPnixHx51nxCry7_nPTIJaSYxM,1438 -setuptools/_shutil.py,sha256=cAOllcoyMTXs5JLoybQi29yI5gABk82hepJyOBv2bMw,1496 -setuptools/_static.py,sha256=GTR79gESF1_JaK4trLkpDrEuCeEtPlwQW0MRv7VNQX4,4855 -setuptools/_vendor/__pycache__/typing_extensions.cpython-312.pyc,, -setuptools/_vendor/autocommand-2.2.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/autocommand-2.2.2.dist-info/LICENSE,sha256=reeNBJgtaZctREqOFKlPh6IzTdOFXMgDSOqOJAqg3y0,7634 -setuptools/_vendor/autocommand-2.2.2.dist-info/METADATA,sha256=OADZuR3O6iBlpu1ieTgzYul6w4uOVrk0P0BO5TGGAJk,15006 -setuptools/_vendor/autocommand-2.2.2.dist-info/RECORD,sha256=giu6ZrQVJvpUcYa4AiH4XaUNZSvuVJPb_l0UCFES8MM,1308 -setuptools/_vendor/autocommand-2.2.2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92 -setuptools/_vendor/autocommand-2.2.2.dist-info/top_level.txt,sha256=AzfhgKKS8EdAwWUTSF8mgeVQbXOY9kokHB6kSqwwqu0,12 -setuptools/_vendor/autocommand/__init__.py,sha256=zko5Rnvolvb-UXjCx_2ArPTGBWwUK5QY4LIQIKYR7As,1037 -setuptools/_vendor/autocommand/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/autocommand/__pycache__/autoasync.cpython-312.pyc,, -setuptools/_vendor/autocommand/__pycache__/autocommand.cpython-312.pyc,, -setuptools/_vendor/autocommand/__pycache__/automain.cpython-312.pyc,, -setuptools/_vendor/autocommand/__pycache__/autoparse.cpython-312.pyc,, -setuptools/_vendor/autocommand/__pycache__/errors.cpython-312.pyc,, -setuptools/_vendor/autocommand/autoasync.py,sha256=AMdyrxNS4pqWJfP_xuoOcImOHWD-qT7x06wmKN1Vp-U,5680 -setuptools/_vendor/autocommand/autocommand.py,sha256=hmkEmQ72HtL55gnURVjDOnsfYlGd5lLXbvT4KG496Qw,2505 -setuptools/_vendor/autocommand/automain.py,sha256=A2b8i754Mxc_DjU9WFr6vqYDWlhz0cn8miu8d8EsxV8,2076 -setuptools/_vendor/autocommand/autoparse.py,sha256=WVWmZJPcbzUKXP40raQw_0HD8qPJ2V9VG1eFFmmnFxw,11642 -setuptools/_vendor/autocommand/errors.py,sha256=7aa3roh9Herd6nIKpQHNWEslWE8oq7GiHYVUuRqORnA,886 -setuptools/_vendor/backports.tarfile-1.2.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/backports.tarfile-1.2.0.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools/_vendor/backports.tarfile-1.2.0.dist-info/METADATA,sha256=ghXFTq132dxaEIolxr3HK1mZqm9iyUmaRANZQSr6WlE,2020 -setuptools/_vendor/backports.tarfile-1.2.0.dist-info/RECORD,sha256=JYofHISeEXUGmlWl1s41ev3QTjTNXeJwk-Ss7HqdLOE,1360 -setuptools/_vendor/backports.tarfile-1.2.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/backports.tarfile-1.2.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -setuptools/_vendor/backports.tarfile-1.2.0.dist-info/top_level.txt,sha256=cGjaLMOoBR1FK0ApojtzWVmViTtJ7JGIK_HwXiEsvtU,10 -setuptools/_vendor/backports/__init__.py,sha256=iOEMwnlORWezdO8-2vxBIPSR37D7JGjluZ8f55vzxls,81 -setuptools/_vendor/backports/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/backports/tarfile/__init__.py,sha256=Pwf2qUIfB0SolJPCKcx3vz3UEu_aids4g4sAfxy94qg,108491 -setuptools/_vendor/backports/tarfile/__main__.py,sha256=Yw2oGT1afrz2eBskzdPYL8ReB_3liApmhFkN2EbDmc4,59 -setuptools/_vendor/backports/tarfile/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/backports/tarfile/__pycache__/__main__.cpython-312.pyc,, -setuptools/_vendor/backports/tarfile/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/backports/tarfile/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/backports/tarfile/compat/__pycache__/py38.cpython-312.pyc,, -setuptools/_vendor/backports/tarfile/compat/py38.py,sha256=iYkyt_gvWjLzGUTJD9TuTfMMjOk-ersXZmRlvQYN2qE,568 -setuptools/_vendor/importlib_metadata-8.0.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/importlib_metadata-8.0.0.dist-info/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358 -setuptools/_vendor/importlib_metadata-8.0.0.dist-info/METADATA,sha256=anuQ7_7h4J1bSEzfcjIBakPi2cyVQ7y7jklLHsBeH1k,4648 -setuptools/_vendor/importlib_metadata-8.0.0.dist-info/RECORD,sha256=DY08buueu-hsrH1ghhVSQzwynanqUSSLYdAr4uXmQDA,2518 -setuptools/_vendor/importlib_metadata-8.0.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/importlib_metadata-8.0.0.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91 -setuptools/_vendor/importlib_metadata-8.0.0.dist-info/top_level.txt,sha256=CO3fD9yylANiXkrMo4qHLV_mqXL2sC5JFKgt1yWAT-A,19 -setuptools/_vendor/importlib_metadata/__init__.py,sha256=tZNB-23h8Bixi9uCrQqj9Yf0aeC--Josdy3IZRIQeB0,33798 -setuptools/_vendor/importlib_metadata/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/_adapters.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/_collections.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/_compat.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/_functools.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/_itertools.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/_meta.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/_text.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/__pycache__/diagnose.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/_adapters.py,sha256=rIhWTwBvYA1bV7i-5FfVX38qEXDTXFeS5cb5xJtP3ks,2317 -setuptools/_vendor/importlib_metadata/_collections.py,sha256=CJ0OTCHIjWA0ZIVS4voORAsn2R4R2cQBEtPsZEJpASY,743 -setuptools/_vendor/importlib_metadata/_compat.py,sha256=73QKrN9KNoaZzhbX5yPCCZa-FaALwXe8TPlDR72JgBU,1314 -setuptools/_vendor/importlib_metadata/_functools.py,sha256=PsY2-4rrKX4RVeRC1oGp1lB1pmC9eKN88_f-bD9uOoA,2895 -setuptools/_vendor/importlib_metadata/_itertools.py,sha256=cvr_2v8BRbxcIl5x5ldfqdHjhI8Yi8s8yk50G_nm6jQ,2068 -setuptools/_vendor/importlib_metadata/_meta.py,sha256=nxZ7C8GVlcBFAKWyVOn_dn7ot_twBcbm1NmvjIetBHI,1801 -setuptools/_vendor/importlib_metadata/_text.py,sha256=HCsFksZpJLeTP3NEk_ngrAeXVRRtTrtyh9eOABoRP4A,2166 -setuptools/_vendor/importlib_metadata/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/importlib_metadata/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/compat/__pycache__/py311.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/compat/__pycache__/py39.cpython-312.pyc,, -setuptools/_vendor/importlib_metadata/compat/py311.py,sha256=uqm-K-uohyj1042TH4a9Er_I5o7667DvulcD-gC_fSA,608 -setuptools/_vendor/importlib_metadata/compat/py39.py,sha256=cPkMv6-0ilK-0Jw_Tkn0xYbOKJZc4WJKQHow0c2T44w,1102 -setuptools/_vendor/importlib_metadata/diagnose.py,sha256=nkSRMiowlmkhLYhKhvCg9glmt_11Cox-EmLzEbqYTa8,379 -setuptools/_vendor/importlib_metadata/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/inflect-7.3.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/inflect-7.3.1.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools/_vendor/inflect-7.3.1.dist-info/METADATA,sha256=ZgMNY0WAZRs-U8wZiV2SMfjSKqBrMngXyDMs_CAwMwg,21079 -setuptools/_vendor/inflect-7.3.1.dist-info/RECORD,sha256=XXg0rBuiYSxoAQUP3lenuYsPNqz4jDwtTzdv2JEbMJE,943 -setuptools/_vendor/inflect-7.3.1.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91 -setuptools/_vendor/inflect-7.3.1.dist-info/top_level.txt,sha256=m52ujdp10CqT6jh1XQxZT6kEntcnv-7Tl7UiGNTzWZA,8 -setuptools/_vendor/inflect/__init__.py,sha256=Jxy1HJXZiZ85kHeLAhkmvz6EMTdFqBe-duvt34R6IOc,103796 -setuptools/_vendor/inflect/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/inflect/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/inflect/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/inflect/compat/__pycache__/py38.cpython-312.pyc,, -setuptools/_vendor/inflect/compat/py38.py,sha256=oObVfVnWX9_OpnOuEJn1mFbJxVhwyR5epbiTNXDDaso,160 -setuptools/_vendor/inflect/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/jaraco.collections-5.1.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/jaraco.collections-5.1.0.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools/_vendor/jaraco.collections-5.1.0.dist-info/METADATA,sha256=IMUaliNsA5X1Ox9MXUWOagch5R4Wwb_3M7erp29dBtg,3933 -setuptools/_vendor/jaraco.collections-5.1.0.dist-info/RECORD,sha256=HptivXDkpfom6VlMu4CGD_7KPev-6Hc9rvp3TNJZygY,873 -setuptools/_vendor/jaraco.collections-5.1.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/jaraco.collections-5.1.0.dist-info/WHEEL,sha256=Mdi9PDNwEZptOjTlUcAth7XJDFtKrHYaQMPulZeBCiQ,91 -setuptools/_vendor/jaraco.collections-5.1.0.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -setuptools/_vendor/jaraco.context-5.3.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/jaraco.context-5.3.0.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools/_vendor/jaraco.context-5.3.0.dist-info/METADATA,sha256=xDtguJej0tN9iEXCUvxEJh2a7xceIRVBEakBLSr__tY,4020 -setuptools/_vendor/jaraco.context-5.3.0.dist-info/RECORD,sha256=VRl7iKeEQyl7stgnp1uq50CzOJYlHYcoNdS0x17C9X4,641 -setuptools/_vendor/jaraco.context-5.3.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -setuptools/_vendor/jaraco.context-5.3.0.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -setuptools/_vendor/jaraco.functools-4.0.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/jaraco.functools-4.0.1.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools/_vendor/jaraco.functools-4.0.1.dist-info/METADATA,sha256=i4aUaQDX-jjdEQK5wevhegyx8JyLfin2HyvaSk3FHso,2891 -setuptools/_vendor/jaraco.functools-4.0.1.dist-info/RECORD,sha256=YyqnwE98S8wBwCevW5vHb-iVj0oYEDW5V6O9MBS6JIs,843 -setuptools/_vendor/jaraco.functools-4.0.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -setuptools/_vendor/jaraco.functools-4.0.1.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -setuptools/_vendor/jaraco.text-3.12.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/jaraco.text-3.12.1.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools/_vendor/jaraco.text-3.12.1.dist-info/METADATA,sha256=AzWdm6ViMfDOPoQMfLWn2zgBQSGJScyqeN29TcuWXVI,3658 -setuptools/_vendor/jaraco.text-3.12.1.dist-info/RECORD,sha256=gW2UV0HcokYJk4jKPu10_AZnrLqjb3C1WbJJTDl5sfY,1500 -setuptools/_vendor/jaraco.text-3.12.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/jaraco.text-3.12.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -setuptools/_vendor/jaraco.text-3.12.1.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -setuptools/_vendor/jaraco/__pycache__/context.cpython-312.pyc,, -setuptools/_vendor/jaraco/collections/__init__.py,sha256=Pc1-SqjWm81ad1P0-GttpkwO_LWlnaY6gUq8gcKh2v0,26640 -setuptools/_vendor/jaraco/collections/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/jaraco/collections/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/jaraco/context.py,sha256=REoLIxDkO5MfEYowt_WoupNCRoxBS5v7YX2PbW8lIcs,9552 -setuptools/_vendor/jaraco/functools/__init__.py,sha256=hEAJaS2uSZRuF_JY4CxCHIYh79ZpxaPp9OiHyr9EJ1w,16642 -setuptools/_vendor/jaraco/functools/__init__.pyi,sha256=gk3dsgHzo5F_U74HzAvpNivFAPCkPJ1b2-yCd62dfnw,3878 -setuptools/_vendor/jaraco/functools/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/jaraco/functools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/jaraco/text/Lorem ipsum.txt,sha256=N_7c_79zxOufBY9HZ3yzMgOkNv-TkOTTio4BydrSjgs,1335 -setuptools/_vendor/jaraco/text/__init__.py,sha256=Y2YUqXR_orUoDaY4SkPRe6ZZhb5HUHB_Ah9RCNsVyho,16250 -setuptools/_vendor/jaraco/text/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/jaraco/text/__pycache__/layouts.cpython-312.pyc,, -setuptools/_vendor/jaraco/text/__pycache__/show-newlines.cpython-312.pyc,, -setuptools/_vendor/jaraco/text/__pycache__/strip-prefix.cpython-312.pyc,, -setuptools/_vendor/jaraco/text/__pycache__/to-dvorak.cpython-312.pyc,, -setuptools/_vendor/jaraco/text/__pycache__/to-qwerty.cpython-312.pyc,, -setuptools/_vendor/jaraco/text/layouts.py,sha256=HTC8aSTLZ7uXipyOXapRMC158juecjK6RVwitfmZ9_w,643 -setuptools/_vendor/jaraco/text/show-newlines.py,sha256=WGQa65e8lyhb92LUOLqVn6KaCtoeVgVws6WtSRmLk6w,904 -setuptools/_vendor/jaraco/text/strip-prefix.py,sha256=NfVXV8JVNo6nqcuYASfMV7_y4Eo8zMQqlCOGvAnRIVw,412 -setuptools/_vendor/jaraco/text/to-dvorak.py,sha256=1SNcbSsvISpXXg-LnybIHHY-RUFOQr36zcHkY1pWFqw,119 -setuptools/_vendor/jaraco/text/to-qwerty.py,sha256=s4UMQUnPwFn_dB5uZC27BurHOQcYondBfzIpVL5pEzw,119 -setuptools/_vendor/more_itertools-10.3.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/more_itertools-10.3.0.dist-info/LICENSE,sha256=CfHIyelBrz5YTVlkHqm4fYPAyw_QB-te85Gn4mQ8GkY,1053 -setuptools/_vendor/more_itertools-10.3.0.dist-info/METADATA,sha256=BFO90O-fLNiVQMpj7oIS5ztzgJUUQZ3TA32P5HH3N-A,36293 -setuptools/_vendor/more_itertools-10.3.0.dist-info/RECORD,sha256=d8jnPgGNwP1-ntbICwWkQEVF9kH7CFIgzkKzaLWao9M,1259 -setuptools/_vendor/more_itertools-10.3.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/more_itertools-10.3.0.dist-info/WHEEL,sha256=rSgq_JpHF9fHR1lx53qwg_1-2LypZE_qmcuXbVUq948,81 -setuptools/_vendor/more_itertools/__init__.py,sha256=dtAbGjTDmn_ghiU5YXfhyDy0phAlXVdt5klZA5fUa-Q,149 -setuptools/_vendor/more_itertools/__init__.pyi,sha256=5B3eTzON1BBuOLob1vCflyEb2lSd6usXQQ-Cv-hXkeA,43 -setuptools/_vendor/more_itertools/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/more_itertools/__pycache__/more.cpython-312.pyc,, -setuptools/_vendor/more_itertools/__pycache__/recipes.cpython-312.pyc,, -setuptools/_vendor/more_itertools/more.py,sha256=1E5kzFncRKTDw0cYv1yRXMgDdunstLQd1QStcnL6U90,148370 -setuptools/_vendor/more_itertools/more.pyi,sha256=iXXeqt48Nxe8VGmIWpkVXuKpR2FYNuu2DU8nQLWCCu0,21484 -setuptools/_vendor/more_itertools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/more_itertools/recipes.py,sha256=WedhhfhGVgr6zii8fIbGJVmRTw0ZKRiLKnYBDGJv4nY,28591 -setuptools/_vendor/more_itertools/recipes.pyi,sha256=T_mdGpcFdfrP3JSWbwzYP9JyNV-Go-7RPfpxfftAWlA,4617 -setuptools/_vendor/packaging-24.2.dist-info/INSTALLER,sha256=5hhM4Q4mYTT9z6QB6PGpUAW81PGNFrYrdXMj4oM_6ak,2 -setuptools/_vendor/packaging-24.2.dist-info/LICENSE,sha256=ytHvW9NA1z4HS6YU0m996spceUDD2MNIUuZcSQlobEg,197 -setuptools/_vendor/packaging-24.2.dist-info/LICENSE.APACHE,sha256=DVQuDIgE45qn836wDaWnYhSdxoLXgpRRKH4RuTjpRZQ,10174 -setuptools/_vendor/packaging-24.2.dist-info/LICENSE.BSD,sha256=tw5-m3QvHMb5SLNMFqo5_-zpQZY2S8iP8NIYDwAo-sU,1344 -setuptools/_vendor/packaging-24.2.dist-info/METADATA,sha256=ohH86s6k5mIfQxY2TS0LcSfADeOFa4BiCC-bxZV-pNs,3204 -setuptools/_vendor/packaging-24.2.dist-info/RECORD,sha256=Y4DrXM0KY0ArfzhbAEa1LYFPwW3WEgEeL4iCqXe-A-M,2009 -setuptools/_vendor/packaging-24.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/packaging-24.2.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82 -setuptools/_vendor/packaging/__init__.py,sha256=dk4Ta_vmdVJxYHDcfyhvQNw8V3PgSBomKNXqg-D2JDY,494 -setuptools/_vendor/packaging/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/_elffile.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/_parser.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/_structures.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/_tokenizer.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/markers.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/metadata.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/requirements.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/tags.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/utils.cpython-312.pyc,, -setuptools/_vendor/packaging/__pycache__/version.cpython-312.pyc,, -setuptools/_vendor/packaging/_elffile.py,sha256=cflAQAkE25tzhYmq_aCi72QfbT_tn891tPzfpbeHOwE,3306 -setuptools/_vendor/packaging/_manylinux.py,sha256=vl5OCoz4kx80H5rwXKeXWjl9WNISGmr4ZgTpTP9lU9c,9612 -setuptools/_vendor/packaging/_musllinux.py,sha256=p9ZqNYiOItGee8KcZFeHF_YcdhVwGHdK6r-8lgixvGQ,2694 -setuptools/_vendor/packaging/_parser.py,sha256=s_TvTvDNK0NrM2QB3VKThdWFM4Nc0P6JnkObkl3MjpM,10236 -setuptools/_vendor/packaging/_structures.py,sha256=q3eVNmbWJGG_S0Dit_S3Ao8qQqz_5PYTXFAKBZe5yr4,1431 -setuptools/_vendor/packaging/_tokenizer.py,sha256=J6v5H7Jzvb-g81xp_2QACKwO7LxHQA6ikryMU7zXwN8,5273 -setuptools/_vendor/packaging/licenses/__init__.py,sha256=1x5M1nEYjcgwEbLt0dXwz2ukjr18DiCzC0sraQqJ-Ww,5715 -setuptools/_vendor/packaging/licenses/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/packaging/licenses/__pycache__/_spdx.cpython-312.pyc,, -setuptools/_vendor/packaging/licenses/_spdx.py,sha256=oAm1ztPFwlsmCKe7lAAsv_OIOfS1cWDu9bNBkeu-2ns,48398 -setuptools/_vendor/packaging/markers.py,sha256=c89TNzB7ZdGYhkovm6PYmqGyHxXlYVaLW591PHUNKD8,10561 -setuptools/_vendor/packaging/metadata.py,sha256=YJibM7GYe4re8-0a3OlXmGS-XDgTEoO4tlBt2q25Bng,34762 -setuptools/_vendor/packaging/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/packaging/requirements.py,sha256=gYyRSAdbrIyKDY66ugIDUQjRMvxkH2ALioTmX3tnL6o,2947 -setuptools/_vendor/packaging/specifiers.py,sha256=GG1wPNMcL0fMJO68vF53wKMdwnfehDcaI-r9NpTfilA,40074 -setuptools/_vendor/packaging/tags.py,sha256=CFqrJzAzc2XNGexerH__T-Y5Iwq7WbsYXsiLERLWxY0,21014 -setuptools/_vendor/packaging/utils.py,sha256=0F3Hh9OFuRgrhTgGZUl5K22Fv1YP2tZl1z_2gO6kJiA,5050 -setuptools/_vendor/packaging/version.py,sha256=olfyuk_DPbflNkJ4wBWetXQ17c74x3DB501degUv7DY,16676 -setuptools/_vendor/platformdirs-4.2.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/platformdirs-4.2.2.dist-info/METADATA,sha256=zmsie01G1MtXR0wgIv5XpVeTO7idr0WWvfmxKsKWuGk,11429 -setuptools/_vendor/platformdirs-4.2.2.dist-info/RECORD,sha256=TCEddtQu1A78Os_Mhm2JEqcYr7yit-UYSUQjZtbpn-g,1642 -setuptools/_vendor/platformdirs-4.2.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/platformdirs-4.2.2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87 -setuptools/_vendor/platformdirs-4.2.2.dist-info/licenses/LICENSE,sha256=KeD9YukphQ6G6yjD_czwzv30-pSHkBHP-z0NS-1tTbY,1089 -setuptools/_vendor/platformdirs/__init__.py,sha256=EMGE8qeHRR9CzDFr8kL3tA8hdZZniYjXBVZd0UGTWK0,22225 -setuptools/_vendor/platformdirs/__main__.py,sha256=HnsUQHpiBaiTxwcmwVw-nFaPdVNZtQIdi1eWDtI-MzI,1493 -setuptools/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc,, -setuptools/_vendor/platformdirs/__pycache__/android.cpython-312.pyc,, -setuptools/_vendor/platformdirs/__pycache__/api.cpython-312.pyc,, -setuptools/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc,, -setuptools/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc,, -setuptools/_vendor/platformdirs/__pycache__/version.cpython-312.pyc,, -setuptools/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc,, -setuptools/_vendor/platformdirs/android.py,sha256=xZXY9Jd46WOsxT2U6-5HsNtDZ-IQqxcEUrBLl3hYk4o,9016 -setuptools/_vendor/platformdirs/api.py,sha256=QBYdUac2eC521ek_y53uD1Dcq-lJX8IgSRVd4InC6uc,8996 -setuptools/_vendor/platformdirs/macos.py,sha256=wftsbsvq6nZ0WORXSiCrZNkRHz_WKuktl0a6mC7MFkI,5580 -setuptools/_vendor/platformdirs/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/platformdirs/unix.py,sha256=Cci9Wqt35dAMsg6HT9nRGHSBW5obb0pR3AE1JJnsCXg,10643 -setuptools/_vendor/platformdirs/version.py,sha256=r7F76tZRjgQKzrpx_I0_ZMQOMU-PS7eGnHD7zEK3KB0,411 -setuptools/_vendor/platformdirs/windows.py,sha256=IFpiohUBwxPtCzlyKwNtxyW4Jk8haa6W8o59mfrDXVo,10125 -setuptools/_vendor/tomli-2.0.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/tomli-2.0.1.dist-info/LICENSE,sha256=uAgWsNUwuKzLTCIReDeQmEpuO2GSLCte6S8zcqsnQv4,1072 -setuptools/_vendor/tomli-2.0.1.dist-info/METADATA,sha256=zPDceKmPwJGLWtZykrHixL7WVXWmJGzZ1jyRT5lCoPI,8875 -setuptools/_vendor/tomli-2.0.1.dist-info/RECORD,sha256=DLn5pFGh42WsVLTIhmLh2gy1SnLRalJY-wq_-dPhwCI,999 -setuptools/_vendor/tomli-2.0.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/tomli-2.0.1.dist-info/WHEEL,sha256=jPMR_Dzkc4X4icQtmz81lnNY_kAsfog7ry7qoRvYLXw,81 -setuptools/_vendor/tomli/__init__.py,sha256=JhUwV66DB1g4Hvt1UQCVMdfCu-IgAV8FXmvDU9onxd4,396 -setuptools/_vendor/tomli/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/tomli/__pycache__/_parser.cpython-312.pyc,, -setuptools/_vendor/tomli/__pycache__/_re.cpython-312.pyc,, -setuptools/_vendor/tomli/__pycache__/_types.cpython-312.pyc,, -setuptools/_vendor/tomli/_parser.py,sha256=g9-ENaALS-B8dokYpCuzUFalWlog7T-SIYMjLZSWrtM,22633 -setuptools/_vendor/tomli/_re.py,sha256=dbjg5ChZT23Ka9z9DHOXfdtSpPwUfdgMXnj8NOoly-w,2943 -setuptools/_vendor/tomli/_types.py,sha256=-GTG2VUqkpxwMqzmVO4F7ybKddIbAnuAHXfmWQcTi3Q,254 -setuptools/_vendor/tomli/py.typed,sha256=8PjyZ1aVoQpRVvt71muvuq5qE-jTFZkK-GLHkhdebmc,26 -setuptools/_vendor/typeguard-4.3.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/typeguard-4.3.0.dist-info/LICENSE,sha256=YWP3mH37ONa8MgzitwsvArhivEESZRbVUu8c1DJH51g,1130 -setuptools/_vendor/typeguard-4.3.0.dist-info/METADATA,sha256=z2dcHAp0TwhYCFU5Deh8x31nazElgujUz9tbuP0pjSE,3717 -setuptools/_vendor/typeguard-4.3.0.dist-info/RECORD,sha256=SKUZWVgkeDUidUKM7s1473fXmsna55bjmi6vJUAoJVI,2402 -setuptools/_vendor/typeguard-4.3.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -setuptools/_vendor/typeguard-4.3.0.dist-info/entry_points.txt,sha256=qp7NQ1aLtiSgMQqo6gWlfGpy0IIXzoMJmeQTLpzqFZQ,48 -setuptools/_vendor/typeguard-4.3.0.dist-info/top_level.txt,sha256=4z28AhuDodwRS_c1J_l8H51t5QuwfTseskYzlxp6grs,10 -setuptools/_vendor/typeguard/__init__.py,sha256=Onh4w38elPCjtlcU3JY9k3h70NjsxXIkAflmQn-Z0FY,2071 -setuptools/_vendor/typeguard/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_checkers.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_config.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_decorators.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_exceptions.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_functions.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_importhook.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_memo.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_pytest_plugin.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_suppression.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_transformer.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_union_transformer.cpython-312.pyc,, -setuptools/_vendor/typeguard/__pycache__/_utils.cpython-312.pyc,, -setuptools/_vendor/typeguard/_checkers.py,sha256=JRrgKicdOEfIBoNEtegYCEIlhpad-a1u1Em7GCj0WCI,31360 -setuptools/_vendor/typeguard/_config.py,sha256=nIz8QwDa-oFO3L9O8_6srzlmd99pSby2wOM4Wb7F_B0,2846 -setuptools/_vendor/typeguard/_decorators.py,sha256=v6dsIeWvPhExGLP_wXF-RmDUyjZf_Ak28g7gBJ_v0-0,9033 -setuptools/_vendor/typeguard/_exceptions.py,sha256=ZIPeiV-FBd5Emw2EaWd2Fvlsrwi4ocwT2fVGBIAtHcQ,1121 -setuptools/_vendor/typeguard/_functions.py,sha256=ibgSAKa5ptIm1eR9ARG0BSozAFJPFNASZqhPVyQeqig,10393 -setuptools/_vendor/typeguard/_importhook.py,sha256=ugjCDvFcdWMU7UugqlJG91IpVNpEIxtRr-99s0h1k7M,6389 -setuptools/_vendor/typeguard/_memo.py,sha256=1juQV_vxnD2JYKbSrebiQuj4oKHz6n67v9pYA-CCISg,1303 -setuptools/_vendor/typeguard/_pytest_plugin.py,sha256=-fcSqkv54rIfIF8pDavY5YQPkj4OX8GMt_lL7CQSD4I,4416 -setuptools/_vendor/typeguard/_suppression.py,sha256=VQfzxcwIbu3if0f7VBkKM7hkYOA7tNFw9a7jMBsmMg4,2266 -setuptools/_vendor/typeguard/_transformer.py,sha256=9Ha7_QhdwoUni_6hvdY-hZbuEergowHrNL2vzHIakFY,44937 -setuptools/_vendor/typeguard/_union_transformer.py,sha256=v_42r7-6HuRX2SoFwnyJ-E5PlxXpVeUJPJR1-HU9qSo,1354 -setuptools/_vendor/typeguard/_utils.py,sha256=5HhO1rPn5f1M6ymkVAEv7Xmlz1cX-j0OnTMlyHqqrR8,5270 -setuptools/_vendor/typeguard/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/typing_extensions-4.12.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/typing_extensions-4.12.2.dist-info/LICENSE,sha256=Oy-B_iHRgcSZxZolbI4ZaEVdZonSaaqFNzv7avQdo78,13936 -setuptools/_vendor/typing_extensions-4.12.2.dist-info/METADATA,sha256=BeUQIa8cnYbrjWx-N8TOznM9UGW5Gm2DicVpDtRA8W0,3018 -setuptools/_vendor/typing_extensions-4.12.2.dist-info/RECORD,sha256=dxAALYGXHmMqpqL8M9xddKr118quIgQKZdPjFQOwXuk,571 -setuptools/_vendor/typing_extensions-4.12.2.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81 -setuptools/_vendor/typing_extensions.py,sha256=gwekpyG9DVG3lxWKX4ni8u7nk3We5slG98mA9F3DJQw,134451 -setuptools/_vendor/wheel-0.45.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/wheel-0.45.1.dist-info/LICENSE.txt,sha256=MMI2GGeRCPPo6h0qZYx8pBe9_IkcmO8aifpP8MmChlQ,1107 -setuptools/_vendor/wheel-0.45.1.dist-info/METADATA,sha256=mKz84H7m7jsxJyzeIcTVORiTb0NPMV39KvOIYhGgmjA,2313 -setuptools/_vendor/wheel-0.45.1.dist-info/RECORD,sha256=1jnxrHyZPDcVvULyfGFhiba4Z5L9_RsXr9dxcNbhaYQ,4900 -setuptools/_vendor/wheel-0.45.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/wheel-0.45.1.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82 -setuptools/_vendor/wheel-0.45.1.dist-info/entry_points.txt,sha256=rTY1BbkPHhkGMm4Q3F0pIzJBzW2kMxoG1oriffvGdA0,104 -setuptools/_vendor/wheel/__init__.py,sha256=mrxMnvdXACur_LWegbUfh5g5ysWZrd63UJn890wvGNk,59 -setuptools/_vendor/wheel/__main__.py,sha256=NkMUnuTCGcOkgY0IBLgBCVC_BGGcWORx2K8jYGS12UE,455 -setuptools/_vendor/wheel/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/__main__.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/_bdist_wheel.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/_setuptools_logging.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/bdist_wheel.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/macosx_libfile.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/metadata.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/util.cpython-312.pyc,, -setuptools/_vendor/wheel/__pycache__/wheelfile.cpython-312.pyc,, -setuptools/_vendor/wheel/_bdist_wheel.py,sha256=UghCQjSH_pVfcZh6oRjzSw_TQhcf3anSx1OkiLSL82M,21694 -setuptools/_vendor/wheel/_setuptools_logging.py,sha256=-5KC-lne0ilOUWIDfOkqapUWGMFZhuKYDIavIZiB5kM,781 -setuptools/_vendor/wheel/bdist_wheel.py,sha256=tpf9WufiSO1RuEMg5oPhIfSG8DMziCZ_4muCKF69Cqo,1107 -setuptools/_vendor/wheel/cli/__init__.py,sha256=Npq6_jKi03dhIcRnmbuFhwviVJxwO0tYEnEhWMv9cJo,4402 -setuptools/_vendor/wheel/cli/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/wheel/cli/__pycache__/convert.cpython-312.pyc,, -setuptools/_vendor/wheel/cli/__pycache__/pack.cpython-312.pyc,, -setuptools/_vendor/wheel/cli/__pycache__/tags.cpython-312.pyc,, -setuptools/_vendor/wheel/cli/__pycache__/unpack.cpython-312.pyc,, -setuptools/_vendor/wheel/cli/convert.py,sha256=Bi0ntEXb9nTllCxWeTRQ4j-nPs3szWSEKipG_GgnMkQ,12634 -setuptools/_vendor/wheel/cli/pack.py,sha256=CAFcHdBVulvsHYJlndKVO7KMI9JqBTZz5ii0PKxxCOs,3103 -setuptools/_vendor/wheel/cli/tags.py,sha256=lHw-LaWrkS5Jy_qWcw-6pSjeNM6yAjDnqKI3E5JTTCU,4760 -setuptools/_vendor/wheel/cli/unpack.py,sha256=Y_J7ynxPSoFFTT7H0fMgbBlVErwyDGcObgme5MBuz58,1021 -setuptools/_vendor/wheel/macosx_libfile.py,sha256=k1x7CE3LPtOVGqj6NXQ1nTGYVPaeRrhVzUG_KPq3zDs,16572 -setuptools/_vendor/wheel/metadata.py,sha256=JC4p7jlQZu2bUTAQ2fevkqLjg_X6gnNyRhLn6OUO1tc,6171 -setuptools/_vendor/wheel/util.py,sha256=aL7aibHwYUgfc8WlolL5tXdkV4DatbJxZHb1kwHFJAU,423 -setuptools/_vendor/wheel/vendored/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/wheel/vendored/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/LICENSE,sha256=ytHvW9NA1z4HS6YU0m996spceUDD2MNIUuZcSQlobEg,197 -setuptools/_vendor/wheel/vendored/packaging/LICENSE.APACHE,sha256=DVQuDIgE45qn836wDaWnYhSdxoLXgpRRKH4RuTjpRZQ,10174 -setuptools/_vendor/wheel/vendored/packaging/LICENSE.BSD,sha256=tw5-m3QvHMb5SLNMFqo5_-zpQZY2S8iP8NIYDwAo-sU,1344 -setuptools/_vendor/wheel/vendored/packaging/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/wheel/vendored/packaging/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/_elffile.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/_manylinux.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/_musllinux.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/_parser.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/_structures.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/_tokenizer.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/markers.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/requirements.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/specifiers.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/tags.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/utils.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/__pycache__/version.cpython-312.pyc,, -setuptools/_vendor/wheel/vendored/packaging/_elffile.py,sha256=hbmK8OD6Z7fY6hwinHEUcD1by7czkGiNYu7ShnFEk2k,3266 -setuptools/_vendor/wheel/vendored/packaging/_manylinux.py,sha256=P7sdR5_7XBY09LVYYPhHmydMJIIwPXWsh4olk74Uuj4,9588 -setuptools/_vendor/wheel/vendored/packaging/_musllinux.py,sha256=z1s8To2hQ0vpn_d-O2i5qxGwEK8WmGlLt3d_26V7NeY,2674 -setuptools/_vendor/wheel/vendored/packaging/_parser.py,sha256=4tT4emSl2qTaU7VTQE1Xa9o1jMPCsBezsYBxyNMUN-s,10347 -setuptools/_vendor/wheel/vendored/packaging/_structures.py,sha256=q3eVNmbWJGG_S0Dit_S3Ao8qQqz_5PYTXFAKBZe5yr4,1431 -setuptools/_vendor/wheel/vendored/packaging/_tokenizer.py,sha256=alCtbwXhOFAmFGZ6BQ-wCTSFoRAJ2z-ysIf7__MTJ_k,5292 -setuptools/_vendor/wheel/vendored/packaging/markers.py,sha256=_TSPI1BhJYO7Bp9AzTmHQxIqHEVXaTjmDh9G-w8qzPA,8232 -setuptools/_vendor/wheel/vendored/packaging/requirements.py,sha256=dgoBeVprPu2YE6Q8nGfwOPTjATHbRa_ZGLyXhFEln6Q,2933 -setuptools/_vendor/wheel/vendored/packaging/specifiers.py,sha256=IWSt0SrLSP72heWhAC8UL0eGvas7XIQHjqiViVfmPKE,39778 -setuptools/_vendor/wheel/vendored/packaging/tags.py,sha256=fedHXiOHkBxNZTXotXv8uXPmMFU9ae-TKBujgYHigcA,18950 -setuptools/_vendor/wheel/vendored/packaging/utils.py,sha256=XgdmP3yx9-wQEFjO7OvMj9RjEf5JlR5HFFR69v7SQ9E,5268 -setuptools/_vendor/wheel/vendored/packaging/version.py,sha256=PFJaYZDxBgyxkfYhH3SQw4qfE9ICCWrTmitvq14y3bs,16234 -setuptools/_vendor/wheel/vendored/vendor.txt,sha256=Z2ENjB1i5prfez8CdM1Sdr3c6Zxv2rRRolMpLmBncAE,16 -setuptools/_vendor/wheel/wheelfile.py,sha256=USCttNlJwafxt51YYFFKG7jnxz8dfhbyqAZL6jMTA9s,8411 -setuptools/_vendor/zipp-3.19.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -setuptools/_vendor/zipp-3.19.2.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -setuptools/_vendor/zipp-3.19.2.dist-info/METADATA,sha256=UIrk_kMIHGSwsKKChYizqMw0MMZpPRZ2ZiVpQAsN_bE,3575 -setuptools/_vendor/zipp-3.19.2.dist-info/RECORD,sha256=8xby4D_ZrefrvAsVRwaEjiu4_VaLkJNRCfDY484rm_4,1039 -setuptools/_vendor/zipp-3.19.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/zipp-3.19.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -setuptools/_vendor/zipp-3.19.2.dist-info/top_level.txt,sha256=iAbdoSHfaGqBfVb2XuR9JqSQHCoOsOtG6y9C_LSpqFw,5 -setuptools/_vendor/zipp/__init__.py,sha256=QuI1g00G4fRAcGt-HqbV0oWIkmSgedCGGYsHHYzNa8A,13412 -setuptools/_vendor/zipp/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/zipp/__pycache__/glob.cpython-312.pyc,, -setuptools/_vendor/zipp/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/_vendor/zipp/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/_vendor/zipp/compat/__pycache__/py310.cpython-312.pyc,, -setuptools/_vendor/zipp/compat/py310.py,sha256=eZpkW0zRtunkhEh8jjX3gCGe22emoKCBJw72Zt4RkhA,219 -setuptools/_vendor/zipp/glob.py,sha256=etWpnfEoRyfUvrUsi6sTiGmErvPwe6HzY6pT8jg_lUI,3082 -setuptools/archive_util.py,sha256=Tl_64hSTtc4y8x7xa98rFVUbG24oArpjzLAYGYP2_sI,7356 -setuptools/build_meta.py,sha256=rry-LowqvWFsxG6Qm5QWetHJGeETzRdiQ5-bs4bOkjo,20446 -setuptools/cli-32.exe,sha256=MqzBvFQxFsviz_EMuGd3LfLyVP8mNMhwrvC0bEtpb9s,11776 -setuptools/cli-64.exe,sha256=u7PeVwdinmpgoMI4zUd7KPB_AGaYL9qVP6b87DkHOko,14336 -setuptools/cli-arm64.exe,sha256=uafQjaiA36yLz1SOuksG-1m28JsX0zFIoPZhgyiSbGE,13824 -setuptools/cli.exe,sha256=MqzBvFQxFsviz_EMuGd3LfLyVP8mNMhwrvC0bEtpb9s,11776 -setuptools/command/__init__.py,sha256=wdSrlNR0P6nCz9_oFtCAiAkeFJMsZa1jPcpXT53f0SM,803 -setuptools/command/__pycache__/__init__.cpython-312.pyc,, -setuptools/command/__pycache__/_requirestxt.cpython-312.pyc,, -setuptools/command/__pycache__/alias.cpython-312.pyc,, -setuptools/command/__pycache__/bdist_egg.cpython-312.pyc,, -setuptools/command/__pycache__/bdist_rpm.cpython-312.pyc,, -setuptools/command/__pycache__/bdist_wheel.cpython-312.pyc,, -setuptools/command/__pycache__/build.cpython-312.pyc,, -setuptools/command/__pycache__/build_clib.cpython-312.pyc,, -setuptools/command/__pycache__/build_ext.cpython-312.pyc,, -setuptools/command/__pycache__/build_py.cpython-312.pyc,, -setuptools/command/__pycache__/develop.cpython-312.pyc,, -setuptools/command/__pycache__/dist_info.cpython-312.pyc,, -setuptools/command/__pycache__/easy_install.cpython-312.pyc,, -setuptools/command/__pycache__/editable_wheel.cpython-312.pyc,, -setuptools/command/__pycache__/egg_info.cpython-312.pyc,, -setuptools/command/__pycache__/install.cpython-312.pyc,, -setuptools/command/__pycache__/install_egg_info.cpython-312.pyc,, -setuptools/command/__pycache__/install_lib.cpython-312.pyc,, -setuptools/command/__pycache__/install_scripts.cpython-312.pyc,, -setuptools/command/__pycache__/rotate.cpython-312.pyc,, -setuptools/command/__pycache__/saveopts.cpython-312.pyc,, -setuptools/command/__pycache__/sdist.cpython-312.pyc,, -setuptools/command/__pycache__/setopt.cpython-312.pyc,, -setuptools/command/__pycache__/test.cpython-312.pyc,, -setuptools/command/_requirestxt.py,sha256=ItYMTJGh_i5TlQstX_nFopqEhkC4PJFadBL2Zd3V670,4228 -setuptools/command/alias.py,sha256=rDdrMt32DS6qf3K7tjZZyHD_dMKrm77AXcAtx-nBQ0I,2380 -setuptools/command/bdist_egg.py,sha256=3eDucQ4fdeYMsLO9PhBfY1JkcMLhZXgnAI_9FdFNsEE,16972 -setuptools/command/bdist_rpm.py,sha256=LyqI49w48SKk0FmuHsE9MLzX1SuXjL7YMNbZMFZqFII,1435 -setuptools/command/bdist_wheel.py,sha256=_LfGHB7CV_uyncqlOTSETEi2gjVCoPKuAXcyRFoq7Cs,22246 -setuptools/command/build.py,sha256=eI7STMERGGZEpzk1tvJN8p9IOjAAXMcGLzljv2mwI3M,6052 -setuptools/command/build_clib.py,sha256=AbgpPIF_3qL8fZr3JIebI-WHTMTBiMfrFkVQz8K40G4,4528 -setuptools/command/build_ext.py,sha256=bUH4M0NizaJJrv10wK-ZD3uY0TxCSZlYQDhiwwzHslM,18377 -setuptools/command/build_py.py,sha256=DCbjvB18kkL-xUK5rvlzm0C6twTeOxNhyvJDxxa7fII,15539 -setuptools/command/develop.py,sha256=zX22119sI1G1gfJ1gNCE4hkg2zbLKx0uUwvNmC5bIu8,6886 -setuptools/command/dist_info.py,sha256=HU752iLLmmYMHbsDBgz2ubRjkgJobugOp8H71LzzDys,3450 -setuptools/command/easy_install.py,sha256=0Z4kFlE78Ae2AfHXYTxZFUa2t3qlNqXCtQu4J1Nx8iA,87870 -setuptools/command/editable_wheel.py,sha256=3bBipRZA3E4poQ8LEWhMYEjHjCzqU_pIdO86C3t7oNY,35624 -setuptools/command/egg_info.py,sha256=WWUozR3DZCrWsTQhHXOygMiEUcrjLWphET0-Zsocsm4,25982 -setuptools/command/install.py,sha256=MmTGb8m1R8fJ0cc5FTWCF6uq-s1ZJmvpYm-N_CtqEaI,7046 -setuptools/command/install_egg_info.py,sha256=3I9IPCH7D59Sh-6aVYz-h6wwyxq-wkxrKwKg3nDdJqs,2075 -setuptools/command/install_lib.py,sha256=9n1_U83eHcERL_a_rv_LhHCkhXlLdqyZ4SdBow-9qcE,4319 -setuptools/command/install_scripts.py,sha256=tVOCj3e8OTIrkoL_bGbT5pOksdxZfQblH_bdI4DtVV4,2637 -setuptools/command/launcher manifest.xml,sha256=xlLbjWrB01tKC0-hlVkOKkiSPbzMml2eOPtJ_ucCnbE,628 -setuptools/command/rotate.py,sha256=XNd_BEEOWAJHW1FcLTMUWWl4QB6zAuk7b8VWQg3FHos,2187 -setuptools/command/saveopts.py,sha256=Np0PVb7SD7oTbu9Z9sosS7D-CkkIkU7x4glu5Es1tjA,692 -setuptools/command/sdist.py,sha256=JaQm2-ebXI2kvyrBjJKP8yNLPa5eMbMeis88CXBMYlk,7374 -setuptools/command/setopt.py,sha256=xZF2RCc4ABvE9eHHAzF50-fkQg3au8fcRUVVGd58k3U,5100 -setuptools/command/test.py,sha256=k7xcq7D7bEehgxarbw-dW3AtmGZORqz8HjKR6FGJ3jk,1343 -setuptools/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/compat/__pycache__/py310.cpython-312.pyc,, -setuptools/compat/__pycache__/py311.cpython-312.pyc,, -setuptools/compat/__pycache__/py312.cpython-312.pyc,, -setuptools/compat/__pycache__/py39.cpython-312.pyc,, -setuptools/compat/py310.py,sha256=8sqwWczIcrkzeAbhaim4pKVd4tXZdcqmebgdvzji0rc,141 -setuptools/compat/py311.py,sha256=e6tJAFwZEP82hmMBl10HYeSypelo_Ti2wTjKZVKLwOE,790 -setuptools/compat/py312.py,sha256=vYKVtdrdOTsO_R90dJkEXsFwfMJFuIFJflhIgHrjJ-Y,366 -setuptools/compat/py39.py,sha256=BJMtnkfcqyTfccqjYQxfoRtU2nTnWaEESBVkshTiXqY,493 -setuptools/config/NOTICE,sha256=Ld3wiBgpejuJ1D2V_2WdjahXQRCMkTbfo6TYVsBiO9g,493 -setuptools/config/__init__.py,sha256=aiPnL9BJn1O6MfmuNXyn8W2Lp8u9qizRVqwPiOdPIjY,1499 -setuptools/config/__pycache__/__init__.cpython-312.pyc,, -setuptools/config/__pycache__/_apply_pyprojecttoml.cpython-312.pyc,, -setuptools/config/__pycache__/expand.cpython-312.pyc,, -setuptools/config/__pycache__/pyprojecttoml.cpython-312.pyc,, -setuptools/config/__pycache__/setupcfg.cpython-312.pyc,, -setuptools/config/_apply_pyprojecttoml.py,sha256=SUyTw7A2btZ1lBuWKN5o42-Diyv95eGTiYJ3rZOnGSc,19120 -setuptools/config/_validate_pyproject/NOTICE,sha256=XTANv6ZDE4sBO3WsnK7uWR-VG4sO4kKIw0zNkmxHgMg,18737 -setuptools/config/_validate_pyproject/__init__.py,sha256=dnp6T7ePP1R5z4OuC7Fd2dkFlIrtIfizUfvpGJP6nz0,1042 -setuptools/config/_validate_pyproject/__pycache__/__init__.cpython-312.pyc,, -setuptools/config/_validate_pyproject/__pycache__/error_reporting.cpython-312.pyc,, -setuptools/config/_validate_pyproject/__pycache__/extra_validations.cpython-312.pyc,, -setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_exceptions.cpython-312.pyc,, -setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_validations.cpython-312.pyc,, -setuptools/config/_validate_pyproject/__pycache__/formats.cpython-312.pyc,, -setuptools/config/_validate_pyproject/error_reporting.py,sha256=meldD7nBQdolQhvG-43r1Ue-gU1n7ORAJR86vh3Rrvk,11813 -setuptools/config/_validate_pyproject/extra_validations.py,sha256=-GUG5S--ijY8WfXbdXPoHl6ywGsyEF9dtDpenSoJPHg,2858 -setuptools/config/_validate_pyproject/fastjsonschema_exceptions.py,sha256=w749JgqKi8clBFcObdcbZVqsmF4oJ_QByhZ1SGbUFNw,1612 -setuptools/config/_validate_pyproject/fastjsonschema_validations.py,sha256=FihD5ZcM6p77BPZ04CGqh3BEwVNoPMKJZJAyuJpkAU0,354682 -setuptools/config/_validate_pyproject/formats.py,sha256=TETokJBK9hjl-cVg1olsojkJwLxfP7_chgJQNmzAB98,13564 -setuptools/config/distutils.schema.json,sha256=Tcp32kRnhwORGw_9p6GEi08lj2h15tQRzOYBbzGmcBU,972 -setuptools/config/expand.py,sha256=JNAktRCsyyRB-rQodbPnCucmLWqcYvzCDC8Ebn2Z7xM,16041 -setuptools/config/pyprojecttoml.py,sha256=YMu5PdbJJI5azp6kR_boM1mflf5nqOA-InF4s6LnLgw,18320 -setuptools/config/setupcfg.py,sha256=VZDkwE7DYv45SbadJD8CwKrDtiXvjgllL8PYSvoRCyg,26575 -setuptools/config/setuptools.schema.json,sha256=dZBRuSEnZkatoVlt1kVwG8ocTeRdO7BD0xvOWKH54PY,16071 -setuptools/depends.py,sha256=jKYfjmt_2ZQYVghb8L9bU7LJ6erHJ5ze-K_fKV1BMXk,5965 -setuptools/discovery.py,sha256=-42c3XhwzkfodDKKP50C2YBzr11fncAgmUzBdBRb0-Q,21258 -setuptools/dist.py,sha256=RZz7aj9RxqSYriqgFoZOu-7KIV82cmlaMFx9owZrApQ,44897 -setuptools/errors.py,sha256=gY2x2PIaIgy01yRANRC-zcCwxDCqCScgJoCOZFe0yio,3024 -setuptools/extension.py,sha256=KCnv9p3tgm0ZVqtgE451fyILsm4hCyvOiUtOu787D-4,6683 -setuptools/glob.py,sha256=AC_B33DY8g-CHELxDsJrtwFrpiucSAZsakPFdSOQzhc,6062 -setuptools/gui-32.exe,sha256=hdrh6V13hF8stZvKw9Sv50u-TJGpvMW_SnHNQxBNvnw,11776 -setuptools/gui-64.exe,sha256=NHG2FA6txkEid9u-_j_vjDRaDxpZd2CGuAo2GMOoPjs,14336 -setuptools/gui-arm64.exe,sha256=5pT0dDQFyLWSb_RX22_n8aEt7HwWqcOGR4TT9OB64Jc,13824 -setuptools/gui.exe,sha256=hdrh6V13hF8stZvKw9Sv50u-TJGpvMW_SnHNQxBNvnw,11776 -setuptools/installer.py,sha256=_4Wegx4r3L05sMo3-IlqFp-OuxnWyBqjyMZ7LWQXmh8,5110 -setuptools/launch.py,sha256=IBb5lEv69CyuZ9ewIrmKlXh154kdLmP29LKfTMkximE,820 -setuptools/logging.py,sha256=W16iHJ1HcCXYQ0RxyrEfJ83FT4175tCtoYg-E6uSpVI,1261 -setuptools/modified.py,sha256=ZwbfBfCFP88ltvbv_dJDz-t1LsQjnM-JUpgZnnQZjjM,568 -setuptools/monkey.py,sha256=FwMWl2n1v2bHbeqBy-o9g8yUNaAkYFbszCbXe9d5Za8,3717 -setuptools/msvc.py,sha256=vmM0qL4rIzrtD9pia9ZEwtqZ4LbbrgL0dU0EANVYRm8,41631 -setuptools/namespaces.py,sha256=2GGqYY1BNDEhMtBc1rHTv7klgmNVRdksJeW-L1f--ys,3171 -setuptools/package_index.py,sha256=yHXj4Z_QaUeh8W6rwq08I5LxnyHrSkNf01uXHwdE8K0,39095 -setuptools/sandbox.py,sha256=fMqtcOuipHO6RKPh1YB5o7d985dLKo76Whp3vrIei2E,14906 -setuptools/script (dev).tmpl,sha256=RUzQzCQUaXtwdLtYHWYbIQmOaES5Brqq1FvUA_tu-5I,218 -setuptools/script.tmpl,sha256=WGTt5piezO27c-Dbx6l5Q4T3Ff20A5z7872hv3aAhYY,138 -setuptools/tests/__init__.py,sha256=AnBfls2iJbTDQzmMKeLRt-9lxhaOHUVOZEgXv89Uwvs,335 -setuptools/tests/__pycache__/__init__.cpython-312.pyc,, -setuptools/tests/__pycache__/contexts.cpython-312.pyc,, -setuptools/tests/__pycache__/environment.cpython-312.pyc,, -setuptools/tests/__pycache__/fixtures.cpython-312.pyc,, -setuptools/tests/__pycache__/mod_with_constant.cpython-312.pyc,, -setuptools/tests/__pycache__/namespaces.cpython-312.pyc,, -setuptools/tests/__pycache__/script-with-bom.cpython-312.pyc,, -setuptools/tests/__pycache__/server.cpython-312.pyc,, -setuptools/tests/__pycache__/test_archive_util.cpython-312.pyc,, -setuptools/tests/__pycache__/test_bdist_deprecations.cpython-312.pyc,, -setuptools/tests/__pycache__/test_bdist_egg.cpython-312.pyc,, -setuptools/tests/__pycache__/test_bdist_wheel.cpython-312.pyc,, -setuptools/tests/__pycache__/test_build.cpython-312.pyc,, -setuptools/tests/__pycache__/test_build_clib.cpython-312.pyc,, -setuptools/tests/__pycache__/test_build_ext.cpython-312.pyc,, -setuptools/tests/__pycache__/test_build_meta.cpython-312.pyc,, -setuptools/tests/__pycache__/test_build_py.cpython-312.pyc,, -setuptools/tests/__pycache__/test_config_discovery.cpython-312.pyc,, -setuptools/tests/__pycache__/test_core_metadata.cpython-312.pyc,, -setuptools/tests/__pycache__/test_depends.cpython-312.pyc,, -setuptools/tests/__pycache__/test_develop.cpython-312.pyc,, -setuptools/tests/__pycache__/test_dist.cpython-312.pyc,, -setuptools/tests/__pycache__/test_dist_info.cpython-312.pyc,, -setuptools/tests/__pycache__/test_distutils_adoption.cpython-312.pyc,, -setuptools/tests/__pycache__/test_easy_install.cpython-312.pyc,, -setuptools/tests/__pycache__/test_editable_install.cpython-312.pyc,, -setuptools/tests/__pycache__/test_egg_info.cpython-312.pyc,, -setuptools/tests/__pycache__/test_extern.cpython-312.pyc,, -setuptools/tests/__pycache__/test_find_packages.cpython-312.pyc,, -setuptools/tests/__pycache__/test_find_py_modules.cpython-312.pyc,, -setuptools/tests/__pycache__/test_glob.cpython-312.pyc,, -setuptools/tests/__pycache__/test_install_scripts.cpython-312.pyc,, -setuptools/tests/__pycache__/test_logging.cpython-312.pyc,, -setuptools/tests/__pycache__/test_manifest.cpython-312.pyc,, -setuptools/tests/__pycache__/test_namespaces.cpython-312.pyc,, -setuptools/tests/__pycache__/test_packageindex.cpython-312.pyc,, -setuptools/tests/__pycache__/test_sandbox.cpython-312.pyc,, -setuptools/tests/__pycache__/test_sdist.cpython-312.pyc,, -setuptools/tests/__pycache__/test_setopt.cpython-312.pyc,, -setuptools/tests/__pycache__/test_setuptools.cpython-312.pyc,, -setuptools/tests/__pycache__/test_shutil_wrapper.cpython-312.pyc,, -setuptools/tests/__pycache__/test_unicode_utils.cpython-312.pyc,, -setuptools/tests/__pycache__/test_virtualenv.cpython-312.pyc,, -setuptools/tests/__pycache__/test_warnings.cpython-312.pyc,, -setuptools/tests/__pycache__/test_wheel.cpython-312.pyc,, -setuptools/tests/__pycache__/test_windows_wrappers.cpython-312.pyc,, -setuptools/tests/__pycache__/text.cpython-312.pyc,, -setuptools/tests/__pycache__/textwrap.cpython-312.pyc,, -setuptools/tests/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/tests/compat/__pycache__/__init__.cpython-312.pyc,, -setuptools/tests/compat/__pycache__/py39.cpython-312.pyc,, -setuptools/tests/compat/py39.py,sha256=eUy7_F-6KRTOIKl-veshUu6I0EdTSdBZMh0EV0lZ1-g,135 -setuptools/tests/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/tests/config/__pycache__/__init__.cpython-312.pyc,, -setuptools/tests/config/__pycache__/test_apply_pyprojecttoml.cpython-312.pyc,, -setuptools/tests/config/__pycache__/test_expand.cpython-312.pyc,, -setuptools/tests/config/__pycache__/test_pyprojecttoml.cpython-312.pyc,, -setuptools/tests/config/__pycache__/test_pyprojecttoml_dynamic_deps.cpython-312.pyc,, -setuptools/tests/config/__pycache__/test_setupcfg.cpython-312.pyc,, -setuptools/tests/config/downloads/__init__.py,sha256=9ixnDEdyL_arKbUzfuiJftAj9bGxKz8M9alOFZMjx9Y,1827 -setuptools/tests/config/downloads/__pycache__/__init__.cpython-312.pyc,, -setuptools/tests/config/downloads/__pycache__/preload.cpython-312.pyc,, -setuptools/tests/config/downloads/preload.py,sha256=sIGGZpY3cmMpMwiJYYYYHG2ifZJkvJgEotRFtiulV1I,450 -setuptools/tests/config/setupcfg_examples.txt,sha256=cAbVvCbkFZuTUL6xRRzRgqyB0rLvJTfvw3D30glo2OE,1912 -setuptools/tests/config/test_apply_pyprojecttoml.py,sha256=l6nE4d8WLU_eSWRic7VSoqeKv9Bi7CZGHcEuB2ehk2w,28807 -setuptools/tests/config/test_expand.py,sha256=S0oT6JvgA_oujR4YS4RUuf5gmOt1CTQV66RQDzV8xd4,8933 -setuptools/tests/config/test_pyprojecttoml.py,sha256=0LefSljUhA6MqtJ5AVzLhomqZcYiFKdu_1ckDeMT1LY,12406 -setuptools/tests/config/test_pyprojecttoml_dynamic_deps.py,sha256=9W73-yLhZJmvCiO4rTiQoBpZT5wNA90Xbd5n2HCshd4,3271 -setuptools/tests/config/test_setupcfg.py,sha256=ZvN-O-2Dgon1adp6oM6il8JWdgT9y196fRvqESU5ELI,33427 -setuptools/tests/contexts.py,sha256=TAdZKxmmodx1ExMVo01o4QpRjpIpo4X3IWKq_BnjxpU,3480 -setuptools/tests/environment.py,sha256=95_UtTaRiuvwYC9eXKEHbn02kDtZysvZq3UZJmPUj1I,3102 -setuptools/tests/fixtures.py,sha256=-V7iD6BeE2E0Rw6dVvTOCm36JG8ZTTnrXhN0GISlgrg,5197 -setuptools/tests/indexes/test_links_priority/external.html,sha256=eL9euOuE93JKZdqlXxBOlHbKwIuNuIdq7GBRpsaPMcU,92 -setuptools/tests/indexes/test_links_priority/simple/foobar/index.html,sha256=DD-TKr7UU4zAjHHz4VexYDNSAzR27levSh1c-k3ZdLE,174 -setuptools/tests/integration/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -setuptools/tests/integration/__pycache__/__init__.cpython-312.pyc,, -setuptools/tests/integration/__pycache__/helpers.cpython-312.pyc,, -setuptools/tests/integration/__pycache__/test_pip_install_sdist.cpython-312.pyc,, -setuptools/tests/integration/helpers.py,sha256=3PHcS9SCA-fwVJmUP2ad5NQOttJAETI5Nnoc_xroO5k,2522 -setuptools/tests/integration/test_pip_install_sdist.py,sha256=SFbvuYF_hDzt6OtsQ5GjFNnxmoJ_eElfvpYsiyyGJ-g,8256 -setuptools/tests/mod_with_constant.py,sha256=X_Kj80M55w1tmQ4f7uZY91ZTALo4hKVT6EHxgYocUMQ,22 -setuptools/tests/namespaces.py,sha256=HPcI3nR5MCFWXpaADIJ1fwKxymcQgBkuw87Ic5PUSAQ,2774 -setuptools/tests/script-with-bom.py,sha256=hRRgIizEULGiG_ZTNoMY46HhKhxpWfy5FGcD6Qbh5fc,18 -setuptools/tests/server.py,sha256=0FDZf0cSInCP5n1haK7AxHo3jD261RK7D3-RjP-F53k,2397 -setuptools/tests/test_archive_util.py,sha256=buuKdY8XkW26Pe3IKAoBRGHG0MDumnuNoPg2WsAQzIg,845 -setuptools/tests/test_bdist_deprecations.py,sha256=75Xq3gYn79LIIyusEltbHan0bEgAt2e_CaL7KLS8-KQ,775 -setuptools/tests/test_bdist_egg.py,sha256=6PaYN1F3JDbIh1uK0urv7yJFcx98z5dn9SOJ8Mv91l8,1957 -setuptools/tests/test_bdist_wheel.py,sha256=dZ9a7OT_UyRvLnoCi2KGEIbtzhEQjM3YutYMA6ZCezs,23083 -setuptools/tests/test_build.py,sha256=wJgMz2hwHADcLFg-nXrwRVhus7hjmAeEGgrpIQwCGnA,798 -setuptools/tests/test_build_clib.py,sha256=bX51XRAf4uO7IuHFpjePnoK8mE74N2gsoeEqF-ofgws,3123 -setuptools/tests/test_build_ext.py,sha256=e4ZSxsYPB5zq1KSqGEuATZ0t0PJQzMhjjkKJ-hIjcgc,10099 -setuptools/tests/test_build_meta.py,sha256=Iakpp9Micvhxi9_F2RPyY2NnCB1G90a38s4O5A3CuiE,34118 -setuptools/tests/test_build_py.py,sha256=gobME_Cvzf6Ugxq70iWfXekb_xyyT61khwjFq8zkwfw,14186 -setuptools/tests/test_config_discovery.py,sha256=FqV-lOtkqaI-ayzU2zocSdD5TaRAgCZnixNDilKA6FQ,22580 -setuptools/tests/test_core_metadata.py,sha256=vbVJ5_Lsx_hsO_GdB6nQEXJRjA2ydx6_qSbr5LpheAA,20881 -setuptools/tests/test_depends.py,sha256=yQBXoQbNQlJit6mbRVoz6Bb553f3sNrq02lZimNz5XY,424 -setuptools/tests/test_develop.py,sha256=CLzXZ8-b5-VFTuau4P4yXEdLx1UdyTFcOfrV0qyUIdE,5142 -setuptools/tests/test_dist.py,sha256=GFjyL2etAxvVM3q7NhFEGcXS5gyKj8VzbqcbKzpqbOk,8901 -setuptools/tests/test_dist_info.py,sha256=5kBRj9tuBsVreBsY22H2feMO_JQZsSoOZMU_MJfUevY,7077 -setuptools/tests/test_distutils_adoption.py,sha256=_eynrOfyEqXFEmjUJhzpe8GXPyTUPvNSObs4qAAmBy8,5987 -setuptools/tests/test_easy_install.py,sha256=jx4lpFyee0G432cdnwBow3AkL4ibw-0QILwldwv5SCI,53534 -setuptools/tests/test_editable_install.py,sha256=7eTEtpT0k7QeVyZg64eh3kZn-SjckuB9LcokOuV37DI,43383 -setuptools/tests/test_egg_info.py,sha256=QCzoUOkFocmbkwS6XU7F8WNzKE8CGEMRxYBqKLgfUrc,44866 -setuptools/tests/test_extern.py,sha256=rpKU6oCcksumLwf5TeKlDluFQ0TUfbPwTLQbpxcFrCU,296 -setuptools/tests/test_find_packages.py,sha256=CTLAcTzWGWBLCcd2aAsUVkvO3ibrlqexFBdDKOWPoq8,7819 -setuptools/tests/test_find_py_modules.py,sha256=zQjuhIG5TQN2SJPix9ARo4DL_w84Ln8QsHDUjjbrtAQ,2404 -setuptools/tests/test_glob.py,sha256=P3JvpH-kXQ4BZ3zvRF-zKxOgwyWzwIaQIz0WHdxS0kk,887 -setuptools/tests/test_install_scripts.py,sha256=scIrJ6a_ssKqg4vIBNaUjmAKHEYLUUZ9WKnPeKnE6gc,3433 -setuptools/tests/test_logging.py,sha256=zlE5DlldukC7Jc54FNvDV_7ux3ErAkrfrN5CSsnNOUQ,2099 -setuptools/tests/test_manifest.py,sha256=eMg65pIA52DizB6mpktSU-b8CjwaNCS5MSgL_V1LrFI,18562 -setuptools/tests/test_namespaces.py,sha256=Y6utoe5PHHqL_DlgawqB9F8XpsUDPvvw1sQMenK04e0,4515 -setuptools/tests/test_packageindex.py,sha256=qEjLHpSu2gAkegwEstzHQT-Om1uQIYjA8zeNzEX79uo,8775 -setuptools/tests/test_sandbox.py,sha256=shUWE7fLTWe7Jzdfi6NheBWauG3oUukbUV46cArD0u0,4330 -setuptools/tests/test_sdist.py,sha256=RYLvPa_nfyC1ZmoinzqMzJynTDG4RtPYC19_0LU6pvs,32872 -setuptools/tests/test_setopt.py,sha256=3VxxM4ATfP-P4AGnDjoWCnHr5-i9CSEQTFYU1-FTnvI,1365 -setuptools/tests/test_setuptools.py,sha256=_eIhqKf45-OtHqxRf20KndOZJlJdS0PuFLXBO3M-LN8,9008 -setuptools/tests/test_shutil_wrapper.py,sha256=g15E11PtZxG-InB2BWNFyH-svObXx2XcMhgMLJPuFnc,641 -setuptools/tests/test_unicode_utils.py,sha256=xWfEEl8jkQCt9othUTXJfFmdyATAFggJs2tTxjbumbw,316 -setuptools/tests/test_virtualenv.py,sha256=g-njC_9JTAs1YVx_1dGJ_Q6RlInO4qKVu9-XAgNb6TY,3730 -setuptools/tests/test_warnings.py,sha256=zwR2zcnCeCeDqILZlJOPAcuyPHoDvGu1OtOVYiLMk74,3347 -setuptools/tests/test_wheel.py,sha256=J-83W1KdXTgAjFZE3H-ytohhvDE1iqdbE5YF5jLQlGQ,19370 -setuptools/tests/test_windows_wrappers.py,sha256=aF6UTowN3yzCgdBh9nDQVvYIfSYogrTK776TEyXEBqg,7881 -setuptools/tests/text.py,sha256=a12197pMVTvB6FAWQ0ujT8fIQiLIWJlFAl1UCaDUDfg,123 -setuptools/tests/textwrap.py,sha256=FNNNq_MiaEJx88PnsbJQIRxmj1qmgcAOCXXRsODPJN4,98 -setuptools/unicode_utils.py,sha256=ukMGh8pEAw6F_Ezb-K5D3c-078RgA_GcF0oW6lg4lSs,3189 -setuptools/version.py,sha256=WJCeUuyq74Aok2TeK9-OexZOu8XrlQy7-y0BEuWNovQ,161 -setuptools/warnings.py,sha256=oY0Se5eOqje_FEyjTgonUc0XGwgsrI5cgm1kkwulz_w,3796 -setuptools/wheel.py,sha256=xkAtvgm7uPTyYV2zqVmQ0wA8kLwOyRT2Jes1zAy07Ks,8624 -setuptools/windows_support.py,sha256=wW4IYLM1Bv7Z1MaauP2xmPjyy-wkmQnXdyvXscAf9fw,726 diff --git a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/WHEEL deleted file mode 100644 index 91720dd..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: setuptools (78.0.2) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/entry_points.txt b/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/entry_points.txt deleted file mode 100644 index 0db0a6c..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/entry_points.txt +++ /dev/null @@ -1,51 +0,0 @@ -[distutils.commands] -alias = setuptools.command.alias:alias -bdist_egg = setuptools.command.bdist_egg:bdist_egg -bdist_rpm = setuptools.command.bdist_rpm:bdist_rpm -bdist_wheel = setuptools.command.bdist_wheel:bdist_wheel -build = setuptools.command.build:build -build_clib = setuptools.command.build_clib:build_clib -build_ext = setuptools.command.build_ext:build_ext -build_py = setuptools.command.build_py:build_py -develop = setuptools.command.develop:develop -dist_info = setuptools.command.dist_info:dist_info -easy_install = setuptools.command.easy_install:easy_install -editable_wheel = setuptools.command.editable_wheel:editable_wheel -egg_info = setuptools.command.egg_info:egg_info -install = setuptools.command.install:install -install_egg_info = setuptools.command.install_egg_info:install_egg_info -install_lib = setuptools.command.install_lib:install_lib -install_scripts = setuptools.command.install_scripts:install_scripts -rotate = setuptools.command.rotate:rotate -saveopts = setuptools.command.saveopts:saveopts -sdist = setuptools.command.sdist:sdist -setopt = setuptools.command.setopt:setopt - -[distutils.setup_keywords] -dependency_links = setuptools.dist:assert_string_list -eager_resources = setuptools.dist:assert_string_list -entry_points = setuptools.dist:check_entry_points -exclude_package_data = setuptools.dist:check_package_data -extras_require = setuptools.dist:check_extras -include_package_data = setuptools.dist:assert_bool -install_requires = setuptools.dist:check_requirements -namespace_packages = setuptools.dist:check_nsp -package_data = setuptools.dist:check_package_data -packages = setuptools.dist:check_packages -python_requires = setuptools.dist:check_specifier -setup_requires = setuptools.dist:check_requirements -use_2to3 = setuptools.dist:invalid_unless_false -zip_safe = setuptools.dist:assert_bool - -[egg_info.writers] -PKG-INFO = setuptools.command.egg_info:write_pkg_info -dependency_links.txt = setuptools.command.egg_info:overwrite_arg -eager_resources.txt = setuptools.command.egg_info:overwrite_arg -entry_points.txt = setuptools.command.egg_info:write_entries -namespace_packages.txt = setuptools.command.egg_info:overwrite_arg -requires.txt = setuptools.command.egg_info:write_requirements -top_level.txt = setuptools.command.egg_info:write_toplevel_names - -[setuptools.finalize_distribution_options] -keywords = setuptools.dist:Distribution._finalize_setup_keywords -parent_finalize = setuptools.dist:_Distribution.finalize_options diff --git a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/licenses/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/licenses/LICENSE deleted file mode 100644 index 1bb5a44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/licenses/LICENSE +++ /dev/null @@ -1,17 +0,0 @@ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/top_level.txt deleted file mode 100644 index b5ac107..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools-78.0.2.dist-info/top_level.txt +++ /dev/null @@ -1,3 +0,0 @@ -_distutils_hack -pkg_resources -setuptools diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/__init__.py deleted file mode 100644 index 64464df..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/__init__.py +++ /dev/null @@ -1,286 +0,0 @@ -"""Extensions to the 'distutils' for large or complex distributions""" -# mypy: disable_error_code=override -# Command.reinitialize_command has an extra **kw param that distutils doesn't have -# Can't disable on the exact line because distutils doesn't exists on Python 3.12 -# and mypy isn't aware of distutils_hack, causing distutils.core.Command to be Any, -# and a [unused-ignore] to be raised on 3.12+ - -from __future__ import annotations - -import functools -import os -import re -import sys -from abc import abstractmethod -from collections.abc import Mapping -from typing import TYPE_CHECKING, TypeVar, overload - -sys.path.extend(((vendor_path := os.path.join(os.path.dirname(os.path.dirname(__file__)), 'setuptools', '_vendor')) not in sys.path) * [vendor_path]) # fmt: skip -# workaround for #4476 -sys.modules.pop('backports', None) - -import _distutils_hack.override # noqa: F401 - -from . import logging, monkey -from .depends import Require -from .discovery import PackageFinder, PEP420PackageFinder -from .dist import Distribution -from .extension import Extension -from .version import __version__ as __version__ -from .warnings import SetuptoolsDeprecationWarning - -import distutils.core -from distutils.errors import DistutilsOptionError - -__all__ = [ - 'setup', - 'Distribution', - 'Command', - 'Extension', - 'Require', - 'SetuptoolsDeprecationWarning', - 'find_packages', - 'find_namespace_packages', -] - -_CommandT = TypeVar("_CommandT", bound="_Command") - -bootstrap_install_from = None - -find_packages = PackageFinder.find -find_namespace_packages = PEP420PackageFinder.find - - -def _install_setup_requires(attrs): - # Note: do not use `setuptools.Distribution` directly, as - # our PEP 517 backend patch `distutils.core.Distribution`. - class MinimalDistribution(distutils.core.Distribution): - """ - A minimal version of a distribution for supporting the - fetch_build_eggs interface. - """ - - def __init__(self, attrs: Mapping[str, object]) -> None: - _incl = 'dependency_links', 'setup_requires' - filtered = {k: attrs[k] for k in set(_incl) & set(attrs)} - super().__init__(filtered) - # Prevent accidentally triggering discovery with incomplete set of attrs - self.set_defaults._disable() - - def _get_project_config_files(self, filenames=None): - """Ignore ``pyproject.toml``, they are not related to setup_requires""" - try: - cfg, _toml = super()._split_standard_project_metadata(filenames) - except Exception: - return filenames, () - return cfg, () - - def finalize_options(self): - """ - Disable finalize_options to avoid building the working set. - Ref #2158. - """ - - dist = MinimalDistribution(attrs) - - # Honor setup.cfg's options. - dist.parse_config_files(ignore_option_errors=True) - if dist.setup_requires: - _fetch_build_eggs(dist) - - -def _fetch_build_eggs(dist: Distribution): - try: - dist.fetch_build_eggs(dist.setup_requires) - except Exception as ex: - msg = """ - It is possible a package already installed in your system - contains an version that is invalid according to PEP 440. - You can try `pip install --use-pep517` as a workaround for this problem, - or rely on a new virtual environment. - - If the problem refers to a package that is not installed yet, - please contact that package's maintainers or distributors. - """ - if "InvalidVersion" in ex.__class__.__name__: - if hasattr(ex, "add_note"): - ex.add_note(msg) # PEP 678 - else: - dist.announce(f"\n{msg}\n") - raise - - -def setup(**attrs): - logging.configure() - # Make sure we have any requirements needed to interpret 'attrs'. - _install_setup_requires(attrs) - return distutils.core.setup(**attrs) - - -setup.__doc__ = distutils.core.setup.__doc__ - -if TYPE_CHECKING: - # Work around a mypy issue where type[T] can't be used as a base: https://github.com/python/mypy/issues/10962 - from distutils.core import Command as _Command -else: - _Command = monkey.get_unpatched(distutils.core.Command) - - -class Command(_Command): - """ - Setuptools internal actions are organized using a *command design pattern*. - This means that each action (or group of closely related actions) executed during - the build should be implemented as a ``Command`` subclass. - - These commands are abstractions and do not necessarily correspond to a command that - can (or should) be executed via a terminal, in a CLI fashion (although historically - they would). - - When creating a new command from scratch, custom defined classes **SHOULD** inherit - from ``setuptools.Command`` and implement a few mandatory methods. - Between these mandatory methods, are listed: - :meth:`initialize_options`, :meth:`finalize_options` and :meth:`run`. - - A useful analogy for command classes is to think of them as subroutines with local - variables called "options". The options are "declared" in :meth:`initialize_options` - and "defined" (given their final values, aka "finalized") in :meth:`finalize_options`, - both of which must be defined by every command class. The "body" of the subroutine, - (where it does all the work) is the :meth:`run` method. - Between :meth:`initialize_options` and :meth:`finalize_options`, ``setuptools`` may set - the values for options/attributes based on user's input (or circumstance), - which means that the implementation should be careful to not overwrite values in - :meth:`finalize_options` unless necessary. - - Please note that other commands (or other parts of setuptools) may also overwrite - the values of the command's options/attributes multiple times during the build - process. - Therefore it is important to consistently implement :meth:`initialize_options` and - :meth:`finalize_options`. For example, all derived attributes (or attributes that - depend on the value of other attributes) **SHOULD** be recomputed in - :meth:`finalize_options`. - - When overwriting existing commands, custom defined classes **MUST** abide by the - same APIs implemented by the original class. They also **SHOULD** inherit from the - original class. - """ - - command_consumes_arguments = False - distribution: Distribution # override distutils.dist.Distribution with setuptools.dist.Distribution - - def __init__(self, dist: Distribution, **kw) -> None: - """ - Construct the command for dist, updating - vars(self) with any keyword parameters. - """ - super().__init__(dist) - vars(self).update(kw) - - def _ensure_stringlike(self, option, what, default=None): - val = getattr(self, option) - if val is None: - setattr(self, option, default) - return default - elif not isinstance(val, str): - raise DistutilsOptionError(f"'{option}' must be a {what} (got `{val}`)") - return val - - def ensure_string_list(self, option: str) -> None: - r"""Ensure that 'option' is a list of strings. If 'option' is - currently a string, we split it either on /,\s*/ or /\s+/, so - "foo bar baz", "foo,bar,baz", and "foo, bar baz" all become - ["foo", "bar", "baz"]. - - .. - TODO: This method seems to be similar to the one in ``distutils.cmd`` - Probably it is just here for backward compatibility with old Python versions? - - :meta private: - """ - val = getattr(self, option) - if val is None: - return - elif isinstance(val, str): - setattr(self, option, re.split(r',\s*|\s+', val)) - else: - if isinstance(val, list): - ok = all(isinstance(v, str) for v in val) - else: - ok = False - if not ok: - raise DistutilsOptionError( - f"'{option}' must be a list of strings (got {val!r})" - ) - - @overload - def reinitialize_command( - self, command: str, reinit_subcommands: bool = False, **kw - ) -> _Command: ... - @overload - def reinitialize_command( - self, command: _CommandT, reinit_subcommands: bool = False, **kw - ) -> _CommandT: ... - def reinitialize_command( - self, command: str | _Command, reinit_subcommands: bool = False, **kw - ) -> _Command: - cmd = _Command.reinitialize_command(self, command, reinit_subcommands) - vars(cmd).update(kw) - return cmd # pyright: ignore[reportReturnType] # pypa/distutils#307 - - @abstractmethod - def initialize_options(self) -> None: - """ - Set or (reset) all options/attributes/caches used by the command - to their default values. Note that these values may be overwritten during - the build. - """ - raise NotImplementedError - - @abstractmethod - def finalize_options(self) -> None: - """ - Set final values for all options/attributes used by the command. - Most of the time, each option/attribute/cache should only be set if it does not - have any value yet (e.g. ``if self.attr is None: self.attr = val``). - """ - raise NotImplementedError - - @abstractmethod - def run(self) -> None: - """ - Execute the actions intended by the command. - (Side effects **SHOULD** only take place when :meth:`run` is executed, - for example, creating new files or writing to the terminal output). - """ - raise NotImplementedError - - -def _find_all_simple(path): - """ - Find all files under 'path' - """ - results = ( - os.path.join(base, file) - for base, dirs, files in os.walk(path, followlinks=True) - for file in files - ) - return filter(os.path.isfile, results) - - -def findall(dir=os.curdir): - """ - Find all files under 'dir' and return the list of full filenames. - Unless dir is '.', return full filenames with dir prepended. - """ - files = _find_all_simple(dir) - if dir == os.curdir: - make_rel = functools.partial(os.path.relpath, start=dir) - files = map(make_rel, files) - return list(files) - - -class sic(str): - """Treat this string as-is (https://en.wikipedia.org/wiki/Sic)""" - - -# Apply monkey patches -monkey.patch_all() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index fe9d6cf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_core_metadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_core_metadata.cpython-312.pyc deleted file mode 100644 index ce8f676..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_core_metadata.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_entry_points.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_entry_points.cpython-312.pyc deleted file mode 100644 index abaa627..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_entry_points.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_imp.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_imp.cpython-312.pyc deleted file mode 100644 index a4293d5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_imp.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_importlib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_importlib.cpython-312.pyc deleted file mode 100644 index 64f0900..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_importlib.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_itertools.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_itertools.cpython-312.pyc deleted file mode 100644 index 6ad3cde..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_itertools.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_normalization.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_normalization.cpython-312.pyc deleted file mode 100644 index 008fd13..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_normalization.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_path.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_path.cpython-312.pyc deleted file mode 100644 index 3d53b50..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_path.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_reqs.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_reqs.cpython-312.pyc deleted file mode 100644 index a1cdafb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_reqs.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_shutil.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_shutil.cpython-312.pyc deleted file mode 100644 index 06eeed2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_shutil.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_static.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_static.cpython-312.pyc deleted file mode 100644 index dcc81bf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/_static.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/archive_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/archive_util.cpython-312.pyc deleted file mode 100644 index 68f5717..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/archive_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/build_meta.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/build_meta.cpython-312.pyc deleted file mode 100644 index ca7c733..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/build_meta.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/depends.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/depends.cpython-312.pyc deleted file mode 100644 index 93f5899..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/depends.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/discovery.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/discovery.cpython-312.pyc deleted file mode 100644 index e102411..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/discovery.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/dist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/dist.cpython-312.pyc deleted file mode 100644 index 757e4f3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/dist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/errors.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/errors.cpython-312.pyc deleted file mode 100644 index 65bf7c0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/errors.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/extension.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/extension.cpython-312.pyc deleted file mode 100644 index f8682ed..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/extension.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/glob.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/glob.cpython-312.pyc deleted file mode 100644 index 89569d5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/glob.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/installer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/installer.cpython-312.pyc deleted file mode 100644 index 0025204..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/installer.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/launch.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/launch.cpython-312.pyc deleted file mode 100644 index 73ff949..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/launch.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/logging.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/logging.cpython-312.pyc deleted file mode 100644 index 0763a63..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/logging.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/modified.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/modified.cpython-312.pyc deleted file mode 100644 index a955af8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/modified.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/monkey.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/monkey.cpython-312.pyc deleted file mode 100644 index 7a759d0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/monkey.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/msvc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/msvc.cpython-312.pyc deleted file mode 100644 index 64a734c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/msvc.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/namespaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/namespaces.cpython-312.pyc deleted file mode 100644 index 73dbc9a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/namespaces.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/package_index.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/package_index.cpython-312.pyc deleted file mode 100644 index ba323a0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/package_index.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/sandbox.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/sandbox.cpython-312.pyc deleted file mode 100644 index 9dd8687..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/sandbox.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/unicode_utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/unicode_utils.cpython-312.pyc deleted file mode 100644 index 048440b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/unicode_utils.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/version.cpython-312.pyc deleted file mode 100644 index 8ccdffe..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/version.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/warnings.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/warnings.cpython-312.pyc deleted file mode 100644 index 5b203d8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/warnings.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/wheel.cpython-312.pyc deleted file mode 100644 index 0022dac..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/wheel.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/windows_support.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/windows_support.cpython-312.pyc deleted file mode 100644 index fb1ef68..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/__pycache__/windows_support.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_core_metadata.py b/llmlab/lib/python3.12/site-packages/setuptools/_core_metadata.py deleted file mode 100644 index a52d5cf..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_core_metadata.py +++ /dev/null @@ -1,337 +0,0 @@ -""" -Handling of Core Metadata for Python packages (including reading and writing). - -See: https://packaging.python.org/en/latest/specifications/core-metadata/ -""" - -from __future__ import annotations - -import os -import stat -import textwrap -from email import message_from_file -from email.message import Message -from tempfile import NamedTemporaryFile - -from packaging.markers import Marker -from packaging.requirements import Requirement -from packaging.utils import canonicalize_name, canonicalize_version -from packaging.version import Version - -from . import _normalization, _reqs -from ._static import is_static -from .warnings import SetuptoolsDeprecationWarning - -from distutils.util import rfc822_escape - - -def get_metadata_version(self): - mv = getattr(self, 'metadata_version', None) - if mv is None: - mv = Version('2.4') - self.metadata_version = mv - return mv - - -def rfc822_unescape(content: str) -> str: - """Reverse RFC-822 escaping by removing leading whitespaces from content.""" - lines = content.splitlines() - if len(lines) == 1: - return lines[0].lstrip() - return '\n'.join((lines[0].lstrip(), textwrap.dedent('\n'.join(lines[1:])))) - - -def _read_field_from_msg(msg: Message, field: str) -> str | None: - """Read Message header field.""" - value = msg[field] - if value == 'UNKNOWN': - return None - return value - - -def _read_field_unescaped_from_msg(msg: Message, field: str) -> str | None: - """Read Message header field and apply rfc822_unescape.""" - value = _read_field_from_msg(msg, field) - if value is None: - return value - return rfc822_unescape(value) - - -def _read_list_from_msg(msg: Message, field: str) -> list[str] | None: - """Read Message header field and return all results as list.""" - values = msg.get_all(field, None) - if values == []: - return None - return values - - -def _read_payload_from_msg(msg: Message) -> str | None: - value = str(msg.get_payload()).strip() - if value == 'UNKNOWN' or not value: - return None - return value - - -def read_pkg_file(self, file): - """Reads the metadata values from a file object.""" - msg = message_from_file(file) - - self.metadata_version = Version(msg['metadata-version']) - self.name = _read_field_from_msg(msg, 'name') - self.version = _read_field_from_msg(msg, 'version') - self.description = _read_field_from_msg(msg, 'summary') - # we are filling author only. - self.author = _read_field_from_msg(msg, 'author') - self.maintainer = None - self.author_email = _read_field_from_msg(msg, 'author-email') - self.maintainer_email = None - self.url = _read_field_from_msg(msg, 'home-page') - self.download_url = _read_field_from_msg(msg, 'download-url') - self.license = _read_field_unescaped_from_msg(msg, 'license') - self.license_expression = _read_field_unescaped_from_msg(msg, 'license-expression') - - self.long_description = _read_field_unescaped_from_msg(msg, 'description') - if self.long_description is None and self.metadata_version >= Version('2.1'): - self.long_description = _read_payload_from_msg(msg) - self.description = _read_field_from_msg(msg, 'summary') - - if 'keywords' in msg: - self.keywords = _read_field_from_msg(msg, 'keywords').split(',') - - self.platforms = _read_list_from_msg(msg, 'platform') - self.classifiers = _read_list_from_msg(msg, 'classifier') - - # PEP 314 - these fields only exist in 1.1 - if self.metadata_version == Version('1.1'): - self.requires = _read_list_from_msg(msg, 'requires') - self.provides = _read_list_from_msg(msg, 'provides') - self.obsoletes = _read_list_from_msg(msg, 'obsoletes') - else: - self.requires = None - self.provides = None - self.obsoletes = None - - self.license_files = _read_list_from_msg(msg, 'license-file') - - -def single_line(val): - """ - Quick and dirty validation for Summary pypa/setuptools#1390. - """ - if '\n' in val: - # TODO: Replace with `raise ValueError("newlines not allowed")` - # after reviewing #2893. - msg = "newlines are not allowed in `summary` and will break in the future" - SetuptoolsDeprecationWarning.emit("Invalid config.", msg) - # due_date is undefined. Controversial change, there was a lot of push back. - val = val.strip().split('\n')[0] - return val - - -def write_pkg_info(self, base_dir): - """Write the PKG-INFO file into the release tree.""" - temp = "" - final = os.path.join(base_dir, 'PKG-INFO') - try: - # Use a temporary file while writing to avoid race conditions - # (e.g. `importlib.metadata` reading `.egg-info/PKG-INFO`): - with NamedTemporaryFile("w", encoding="utf-8", dir=base_dir, delete=False) as f: - temp = f.name - self.write_pkg_file(f) - permissions = stat.S_IMODE(os.lstat(temp).st_mode) - os.chmod(temp, permissions | stat.S_IRGRP | stat.S_IROTH) - os.replace(temp, final) # atomic operation. - finally: - if temp and os.path.exists(temp): - os.remove(temp) - - -# Based on Python 3.5 version -def write_pkg_file(self, file): # noqa: C901 # is too complex (14) # FIXME - """Write the PKG-INFO format data to a file object.""" - version = self.get_metadata_version() - - def write_field(key, value): - file.write(f"{key}: {value}\n") - - write_field('Metadata-Version', str(version)) - write_field('Name', self.get_name()) - write_field('Version', self.get_version()) - - summary = self.get_description() - if summary: - write_field('Summary', single_line(summary)) - - optional_fields = ( - ('Home-page', 'url'), - ('Download-URL', 'download_url'), - ('Author', 'author'), - ('Author-email', 'author_email'), - ('Maintainer', 'maintainer'), - ('Maintainer-email', 'maintainer_email'), - ) - - for field, attr in optional_fields: - attr_val = getattr(self, attr, None) - if attr_val is not None: - write_field(field, attr_val) - - if license_expression := self.license_expression: - write_field('License-Expression', license_expression) - elif license := self.get_license(): - write_field('License', rfc822_escape(license)) - - for label, url in self.project_urls.items(): - write_field('Project-URL', f'{label}, {url}') - - keywords = ','.join(self.get_keywords()) - if keywords: - write_field('Keywords', keywords) - - platforms = self.get_platforms() or [] - for platform in platforms: - write_field('Platform', platform) - - self._write_list(file, 'Classifier', self.get_classifiers()) - - # PEP 314 - self._write_list(file, 'Requires', self.get_requires()) - self._write_list(file, 'Provides', self.get_provides()) - self._write_list(file, 'Obsoletes', self.get_obsoletes()) - - # Setuptools specific for PEP 345 - if hasattr(self, 'python_requires'): - write_field('Requires-Python', self.python_requires) - - # PEP 566 - if self.long_description_content_type: - write_field('Description-Content-Type', self.long_description_content_type) - - safe_license_files = map(_safe_license_file, self.license_files or []) - self._write_list(file, 'License-File', safe_license_files) - _write_requirements(self, file) - - for field, attr in _POSSIBLE_DYNAMIC_FIELDS.items(): - if (val := getattr(self, attr, None)) and not is_static(val): - write_field('Dynamic', field) - - long_description = self.get_long_description() - if long_description: - file.write(f"\n{long_description}") - if not long_description.endswith("\n"): - file.write("\n") - - -def _write_requirements(self, file): - for req in _reqs.parse(self.install_requires): - file.write(f"Requires-Dist: {req}\n") - - processed_extras = {} - for augmented_extra, reqs in self.extras_require.items(): - # Historically, setuptools allows "augmented extras": `:` - unsafe_extra, _, condition = augmented_extra.partition(":") - unsafe_extra = unsafe_extra.strip() - extra = _normalization.safe_extra(unsafe_extra) - - if extra: - _write_provides_extra(file, processed_extras, extra, unsafe_extra) - for req in _reqs.parse_strings(reqs): - r = _include_extra(req, extra, condition.strip()) - file.write(f"Requires-Dist: {r}\n") - - return processed_extras - - -def _include_extra(req: str, extra: str, condition: str) -> Requirement: - r = Requirement(req) # create a fresh object that can be modified - parts = ( - f"({r.marker})" if r.marker else None, - f"({condition})" if condition else None, - f"extra == {extra!r}" if extra else None, - ) - r.marker = Marker(" and ".join(x for x in parts if x)) - return r - - -def _write_provides_extra(file, processed_extras, safe, unsafe): - previous = processed_extras.get(safe) - if previous == unsafe: - SetuptoolsDeprecationWarning.emit( - 'Ambiguity during "extra" normalization for dependencies.', - f""" - {previous!r} and {unsafe!r} normalize to the same value:\n - {safe!r}\n - In future versions, setuptools might halt the build process. - """, - see_url="https://peps.python.org/pep-0685/", - ) - else: - processed_extras[safe] = unsafe - file.write(f"Provides-Extra: {safe}\n") - - -# from pypa/distutils#244; needed only until that logic is always available -def get_fullname(self): - return _distribution_fullname(self.get_name(), self.get_version()) - - -def _distribution_fullname(name: str, version: str) -> str: - """ - >>> _distribution_fullname('setup.tools', '1.0-2') - 'setup_tools-1.0.post2' - >>> _distribution_fullname('setup-tools', '1.2post2') - 'setup_tools-1.2.post2' - >>> _distribution_fullname('setup-tools', '1.0-r2') - 'setup_tools-1.0.post2' - >>> _distribution_fullname('setup.tools', '1.0.post') - 'setup_tools-1.0.post0' - >>> _distribution_fullname('setup.tools', '1.0+ubuntu-1') - 'setup_tools-1.0+ubuntu.1' - """ - return "{}-{}".format( - canonicalize_name(name).replace('-', '_'), - canonicalize_version(version, strip_trailing_zero=False), - ) - - -def _safe_license_file(file): - # XXX: Do we need this after the deprecation discussed in #4892, #4896?? - normalized = os.path.normpath(file).replace(os.sep, "/") - if "../" in normalized: - return os.path.basename(normalized) # Temporarily restore pre PEP639 behaviour - return normalized - - -_POSSIBLE_DYNAMIC_FIELDS = { - # Core Metadata Field x related Distribution attribute - "author": "author", - "author-email": "author_email", - "classifier": "classifiers", - "description": "long_description", - "description-content-type": "long_description_content_type", - "download-url": "download_url", - "home-page": "url", - "keywords": "keywords", - "license": "license", - # XXX: License-File is complicated because the user gives globs that are expanded - # during the build. Without special handling it is likely always - # marked as Dynamic, which is an acceptable outcome according to: - # https://github.com/pypa/setuptools/issues/4629#issuecomment-2331233677 - "license-file": "license_files", - "license-expression": "license_expression", # PEP 639 - "maintainer": "maintainer", - "maintainer-email": "maintainer_email", - "obsoletes": "obsoletes", - # "obsoletes-dist": "obsoletes_dist", # NOT USED - "platform": "platforms", - "project-url": "project_urls", - "provides": "provides", - # "provides-dist": "provides_dist", # NOT USED - "provides-extra": "extras_require", - "requires": "requires", - "requires-dist": "install_requires", - # "requires-external": "requires_external", # NOT USED - "requires-python": "python_requires", - "summary": "description", - # "supported-platform": "supported_platforms", # NOT USED -} diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__init__.py deleted file mode 100644 index e374d5c..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__init__.py +++ /dev/null @@ -1,14 +0,0 @@ -import importlib -import sys - -__version__, _, _ = sys.version.partition(' ') - - -try: - # Allow Debian and pkgsrc (only) to customize system - # behavior. Ref pypa/distutils#2 and pypa/distutils#16. - # This hook is deprecated and no other environments - # should use it. - importlib.import_module('_distutils_system_mod') -except ImportError: - pass diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 1e8e9d9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_log.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_log.cpython-312.pyc deleted file mode 100644 index c13ddfa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_log.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_macos_compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_macos_compat.cpython-312.pyc deleted file mode 100644 index 1bae518..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_macos_compat.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_modified.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_modified.cpython-312.pyc deleted file mode 100644 index b15ebd2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_modified.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_msvccompiler.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_msvccompiler.cpython-312.pyc deleted file mode 100644 index b595ac9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/_msvccompiler.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/archive_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/archive_util.cpython-312.pyc deleted file mode 100644 index fdf6384..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/archive_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/ccompiler.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/ccompiler.cpython-312.pyc deleted file mode 100644 index 52f24f0..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/ccompiler.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/cmd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/cmd.cpython-312.pyc deleted file mode 100644 index a741879..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/cmd.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/core.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/core.cpython-312.pyc deleted file mode 100644 index 1b440fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/core.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/cygwinccompiler.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/cygwinccompiler.cpython-312.pyc deleted file mode 100644 index 45ac43e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/cygwinccompiler.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/debug.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/debug.cpython-312.pyc deleted file mode 100644 index 74eae89..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/debug.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dep_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dep_util.cpython-312.pyc deleted file mode 100644 index 37bdf28..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dep_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dir_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dir_util.cpython-312.pyc deleted file mode 100644 index a2e703f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dir_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dist.cpython-312.pyc deleted file mode 100644 index 1366f5d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/dist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/errors.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/errors.cpython-312.pyc deleted file mode 100644 index 89cabf2..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/errors.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/extension.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/extension.cpython-312.pyc deleted file mode 100644 index ed04fcc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/extension.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/fancy_getopt.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/fancy_getopt.cpython-312.pyc deleted file mode 100644 index 2e7da98..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/fancy_getopt.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/file_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/file_util.cpython-312.pyc deleted file mode 100644 index aac1d53..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/file_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/filelist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/filelist.cpython-312.pyc deleted file mode 100644 index da25ba8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/filelist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/log.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/log.cpython-312.pyc deleted file mode 100644 index 7bb3494..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/log.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/spawn.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/spawn.cpython-312.pyc deleted file mode 100644 index 51fabda..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/spawn.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/sysconfig.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/sysconfig.cpython-312.pyc deleted file mode 100644 index 4c4cdfe..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/sysconfig.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/text_file.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/text_file.cpython-312.pyc deleted file mode 100644 index 0acfd02..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/text_file.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/unixccompiler.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/unixccompiler.cpython-312.pyc deleted file mode 100644 index 626f3f5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/unixccompiler.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/util.cpython-312.pyc deleted file mode 100644 index 6d32a87..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/version.cpython-312.pyc deleted file mode 100644 index 782d613..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/version.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/versionpredicate.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/versionpredicate.cpython-312.pyc deleted file mode 100644 index f8b37d8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/versionpredicate.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/zosccompiler.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/zosccompiler.cpython-312.pyc deleted file mode 100644 index 2dfbf69..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/__pycache__/zosccompiler.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_log.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_log.py deleted file mode 100644 index 0148f15..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_log.py +++ /dev/null @@ -1,3 +0,0 @@ -import logging - -log = logging.getLogger() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_macos_compat.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_macos_compat.py deleted file mode 100644 index 76ecb96..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_macos_compat.py +++ /dev/null @@ -1,12 +0,0 @@ -import importlib -import sys - - -def bypass_compiler_fixup(cmd, args): - return cmd - - -if sys.platform == 'darwin': - compiler_fixup = importlib.import_module('_osx_support').compiler_fixup -else: - compiler_fixup = bypass_compiler_fixup diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_modified.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_modified.py deleted file mode 100644 index f64cab7..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_modified.py +++ /dev/null @@ -1,95 +0,0 @@ -"""Timestamp comparison of files and groups of files.""" - -from __future__ import annotations - -import functools -import os.path -from collections.abc import Callable, Iterable -from typing import Literal, TypeVar - -from jaraco.functools import splat - -from .compat.py39 import zip_strict -from .errors import DistutilsFileError - -_SourcesT = TypeVar( - "_SourcesT", bound="str | bytes | os.PathLike[str] | os.PathLike[bytes]" -) -_TargetsT = TypeVar( - "_TargetsT", bound="str | bytes | os.PathLike[str] | os.PathLike[bytes]" -) - - -def _newer(source, target): - return not os.path.exists(target) or ( - os.path.getmtime(source) > os.path.getmtime(target) - ) - - -def newer( - source: str | bytes | os.PathLike[str] | os.PathLike[bytes], - target: str | bytes | os.PathLike[str] | os.PathLike[bytes], -) -> bool: - """ - Is source modified more recently than target. - - Returns True if 'source' is modified more recently than - 'target' or if 'target' does not exist. - - Raises DistutilsFileError if 'source' does not exist. - """ - if not os.path.exists(source): - raise DistutilsFileError(f"file {os.path.abspath(source)!r} does not exist") - - return _newer(source, target) - - -def newer_pairwise( - sources: Iterable[_SourcesT], - targets: Iterable[_TargetsT], - newer: Callable[[_SourcesT, _TargetsT], bool] = newer, -) -> tuple[list[_SourcesT], list[_TargetsT]]: - """ - Filter filenames where sources are newer than targets. - - Walk two filename iterables in parallel, testing if each source is newer - than its corresponding target. Returns a pair of lists (sources, - targets) where source is newer than target, according to the semantics - of 'newer()'. - """ - newer_pairs = filter(splat(newer), zip_strict(sources, targets)) - return tuple(map(list, zip(*newer_pairs))) or ([], []) - - -def newer_group( - sources: Iterable[str | bytes | os.PathLike[str] | os.PathLike[bytes]], - target: str | bytes | os.PathLike[str] | os.PathLike[bytes], - missing: Literal["error", "ignore", "newer"] = "error", -) -> bool: - """ - Is target out-of-date with respect to any file in sources. - - Return True if 'target' is out-of-date with respect to any file - listed in 'sources'. In other words, if 'target' exists and is newer - than every file in 'sources', return False; otherwise return True. - ``missing`` controls how to handle a missing source file: - - - error (default): allow the ``stat()`` call to fail. - - ignore: silently disregard any missing source files. - - newer: treat missing source files as "target out of date". This - mode is handy in "dry-run" mode: it will pretend to carry out - commands that wouldn't work because inputs are missing, but - that doesn't matter because dry-run won't run the commands. - """ - - def missing_as_newer(source): - return missing == 'newer' and not os.path.exists(source) - - ignored = os.path.exists if missing == 'ignore' else None - return not os.path.exists(target) or any( - missing_as_newer(source) or _newer(source, target) - for source in filter(ignored, sources) - ) - - -newer_pairwise_group = functools.partial(newer_pairwise, newer=newer_group) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_msvccompiler.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_msvccompiler.py deleted file mode 100644 index 8471cca..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/_msvccompiler.py +++ /dev/null @@ -1,5 +0,0 @@ -from .compilers.C import msvc - -__all__ = ["MSVCCompiler"] - -MSVCCompiler = msvc.Compiler diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/archive_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/archive_util.py deleted file mode 100644 index d860f55..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/archive_util.py +++ /dev/null @@ -1,294 +0,0 @@ -"""distutils.archive_util - -Utility functions for creating archive files (tarballs, zip files, -that sort of thing).""" - -from __future__ import annotations - -import os -from typing import Literal, overload - -try: - import zipfile -except ImportError: - zipfile = None - - -from ._log import log -from .dir_util import mkpath -from .errors import DistutilsExecError -from .spawn import spawn - -try: - from pwd import getpwnam -except ImportError: - getpwnam = None - -try: - from grp import getgrnam -except ImportError: - getgrnam = None - - -def _get_gid(name): - """Returns a gid, given a group name.""" - if getgrnam is None or name is None: - return None - try: - result = getgrnam(name) - except KeyError: - result = None - if result is not None: - return result[2] - return None - - -def _get_uid(name): - """Returns an uid, given a user name.""" - if getpwnam is None or name is None: - return None - try: - result = getpwnam(name) - except KeyError: - result = None - if result is not None: - return result[2] - return None - - -def make_tarball( - base_name: str, - base_dir: str | os.PathLike[str], - compress: Literal["gzip", "bzip2", "xz"] | None = "gzip", - verbose: bool = False, - dry_run: bool = False, - owner: str | None = None, - group: str | None = None, -) -> str: - """Create a (possibly compressed) tar file from all the files under - 'base_dir'. - - 'compress' must be "gzip" (the default), "bzip2", "xz", or None. - - 'owner' and 'group' can be used to define an owner and a group for the - archive that is being built. If not provided, the current owner and group - will be used. - - The output tar file will be named 'base_dir' + ".tar", possibly plus - the appropriate compression extension (".gz", ".bz2", ".xz" or ".Z"). - - Returns the output filename. - """ - tar_compression = { - 'gzip': 'gz', - 'bzip2': 'bz2', - 'xz': 'xz', - None: '', - } - compress_ext = {'gzip': '.gz', 'bzip2': '.bz2', 'xz': '.xz'} - - # flags for compression program, each element of list will be an argument - if compress is not None and compress not in compress_ext.keys(): - raise ValueError( - "bad value for 'compress': must be None, 'gzip', 'bzip2', 'xz'" - ) - - archive_name = base_name + '.tar' - archive_name += compress_ext.get(compress, '') - - mkpath(os.path.dirname(archive_name), dry_run=dry_run) - - # creating the tarball - import tarfile # late import so Python build itself doesn't break - - log.info('Creating tar archive') - - uid = _get_uid(owner) - gid = _get_gid(group) - - def _set_uid_gid(tarinfo): - if gid is not None: - tarinfo.gid = gid - tarinfo.gname = group - if uid is not None: - tarinfo.uid = uid - tarinfo.uname = owner - return tarinfo - - if not dry_run: - tar = tarfile.open(archive_name, f'w|{tar_compression[compress]}') - try: - tar.add(base_dir, filter=_set_uid_gid) - finally: - tar.close() - - return archive_name - - -def make_zipfile( # noqa: C901 - base_name: str, - base_dir: str | os.PathLike[str], - verbose: bool = False, - dry_run: bool = False, -) -> str: - """Create a zip file from all the files under 'base_dir'. - - The output zip file will be named 'base_name' + ".zip". Uses either the - "zipfile" Python module (if available) or the InfoZIP "zip" utility - (if installed and found on the default search path). If neither tool is - available, raises DistutilsExecError. Returns the name of the output zip - file. - """ - zip_filename = base_name + ".zip" - mkpath(os.path.dirname(zip_filename), dry_run=dry_run) - - # If zipfile module is not available, try spawning an external - # 'zip' command. - if zipfile is None: - if verbose: - zipoptions = "-r" - else: - zipoptions = "-rq" - - try: - spawn(["zip", zipoptions, zip_filename, base_dir], dry_run=dry_run) - except DistutilsExecError: - # XXX really should distinguish between "couldn't find - # external 'zip' command" and "zip failed". - raise DistutilsExecError( - f"unable to create zip file '{zip_filename}': " - "could neither import the 'zipfile' module nor " - "find a standalone zip utility" - ) - - else: - log.info("creating '%s' and adding '%s' to it", zip_filename, base_dir) - - if not dry_run: - try: - zip = zipfile.ZipFile( - zip_filename, "w", compression=zipfile.ZIP_DEFLATED - ) - except RuntimeError: - zip = zipfile.ZipFile(zip_filename, "w", compression=zipfile.ZIP_STORED) - - with zip: - if base_dir != os.curdir: - path = os.path.normpath(os.path.join(base_dir, '')) - zip.write(path, path) - log.info("adding '%s'", path) - for dirpath, dirnames, filenames in os.walk(base_dir): - for name in dirnames: - path = os.path.normpath(os.path.join(dirpath, name, '')) - zip.write(path, path) - log.info("adding '%s'", path) - for name in filenames: - path = os.path.normpath(os.path.join(dirpath, name)) - if os.path.isfile(path): - zip.write(path, path) - log.info("adding '%s'", path) - - return zip_filename - - -ARCHIVE_FORMATS = { - 'gztar': (make_tarball, [('compress', 'gzip')], "gzip'ed tar-file"), - 'bztar': (make_tarball, [('compress', 'bzip2')], "bzip2'ed tar-file"), - 'xztar': (make_tarball, [('compress', 'xz')], "xz'ed tar-file"), - 'ztar': (make_tarball, [('compress', 'compress')], "compressed tar file"), - 'tar': (make_tarball, [('compress', None)], "uncompressed tar file"), - 'zip': (make_zipfile, [], "ZIP file"), -} - - -def check_archive_formats(formats): - """Returns the first format from the 'format' list that is unknown. - - If all formats are known, returns None - """ - for format in formats: - if format not in ARCHIVE_FORMATS: - return format - return None - - -@overload -def make_archive( - base_name: str, - format: str, - root_dir: str | os.PathLike[str] | bytes | os.PathLike[bytes] | None = None, - base_dir: str | None = None, - verbose: bool = False, - dry_run: bool = False, - owner: str | None = None, - group: str | None = None, -) -> str: ... -@overload -def make_archive( - base_name: str | os.PathLike[str], - format: str, - root_dir: str | os.PathLike[str] | bytes | os.PathLike[bytes], - base_dir: str | None = None, - verbose: bool = False, - dry_run: bool = False, - owner: str | None = None, - group: str | None = None, -) -> str: ... -def make_archive( - base_name: str | os.PathLike[str], - format: str, - root_dir: str | os.PathLike[str] | bytes | os.PathLike[bytes] | None = None, - base_dir: str | None = None, - verbose: bool = False, - dry_run: bool = False, - owner: str | None = None, - group: str | None = None, -) -> str: - """Create an archive file (eg. zip or tar). - - 'base_name' is the name of the file to create, minus any format-specific - extension; 'format' is the archive format: one of "zip", "tar", "gztar", - "bztar", "xztar", or "ztar". - - 'root_dir' is a directory that will be the root directory of the - archive; ie. we typically chdir into 'root_dir' before creating the - archive. 'base_dir' is the directory where we start archiving from; - ie. 'base_dir' will be the common prefix of all files and - directories in the archive. 'root_dir' and 'base_dir' both default - to the current directory. Returns the name of the archive file. - - 'owner' and 'group' are used when creating a tar archive. By default, - uses the current owner and group. - """ - save_cwd = os.getcwd() - if root_dir is not None: - log.debug("changing into '%s'", root_dir) - base_name = os.path.abspath(base_name) - if not dry_run: - os.chdir(root_dir) - - if base_dir is None: - base_dir = os.curdir - - kwargs = {'dry_run': dry_run} - - try: - format_info = ARCHIVE_FORMATS[format] - except KeyError: - raise ValueError(f"unknown archive format '{format}'") - - func = format_info[0] - kwargs.update(format_info[1]) - - if format != 'zip': - kwargs['owner'] = owner - kwargs['group'] = group - - try: - filename = func(base_name, base_dir, **kwargs) - finally: - if root_dir is not None: - log.debug("changing back to '%s'", save_cwd) - os.chdir(save_cwd) - - return filename diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/ccompiler.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/ccompiler.py deleted file mode 100644 index 58bc6a5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/ccompiler.py +++ /dev/null @@ -1,26 +0,0 @@ -from .compat.numpy import ( # noqa: F401 - _default_compilers, - compiler_class, -) -from .compilers.C import base -from .compilers.C.base import ( - gen_lib_options, - gen_preprocess_options, - get_default_compiler, - new_compiler, - show_compilers, -) -from .compilers.C.errors import CompileError, LinkError - -__all__ = [ - 'CompileError', - 'LinkError', - 'gen_lib_options', - 'gen_preprocess_options', - 'get_default_compiler', - 'new_compiler', - 'show_compilers', -] - - -CCompiler = base.Compiler diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/cmd.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/cmd.py deleted file mode 100644 index 241621b..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/cmd.py +++ /dev/null @@ -1,554 +0,0 @@ -"""distutils.cmd - -Provides the Command class, the base class for the command classes -in the distutils.command package. -""" - -from __future__ import annotations - -import logging -import os -import re -import sys -from abc import abstractmethod -from collections.abc import Callable, MutableSequence -from typing import TYPE_CHECKING, Any, ClassVar, TypeVar, overload - -from . import _modified, archive_util, dir_util, file_util, util -from ._log import log -from .errors import DistutilsOptionError - -if TYPE_CHECKING: - # type-only import because of mutual dependence between these classes - from distutils.dist import Distribution - - from typing_extensions import TypeVarTuple, Unpack - - _Ts = TypeVarTuple("_Ts") - -_StrPathT = TypeVar("_StrPathT", bound="str | os.PathLike[str]") -_BytesPathT = TypeVar("_BytesPathT", bound="bytes | os.PathLike[bytes]") -_CommandT = TypeVar("_CommandT", bound="Command") - - -class Command: - """Abstract base class for defining command classes, the "worker bees" - of the Distutils. A useful analogy for command classes is to think of - them as subroutines with local variables called "options". The options - are "declared" in 'initialize_options()' and "defined" (given their - final values, aka "finalized") in 'finalize_options()', both of which - must be defined by every command class. The distinction between the - two is necessary because option values might come from the outside - world (command line, config file, ...), and any options dependent on - other options must be computed *after* these outside influences have - been processed -- hence 'finalize_options()'. The "body" of the - subroutine, where it does all its work based on the values of its - options, is the 'run()' method, which must also be implemented by every - command class. - """ - - # 'sub_commands' formalizes the notion of a "family" of commands, - # eg. "install" as the parent with sub-commands "install_lib", - # "install_headers", etc. The parent of a family of commands - # defines 'sub_commands' as a class attribute; it's a list of - # (command_name : string, predicate : unbound_method | string | None) - # tuples, where 'predicate' is a method of the parent command that - # determines whether the corresponding command is applicable in the - # current situation. (Eg. we "install_headers" is only applicable if - # we have any C header files to install.) If 'predicate' is None, - # that command is always applicable. - # - # 'sub_commands' is usually defined at the *end* of a class, because - # predicates can be unbound methods, so they must already have been - # defined. The canonical example is the "install" command. - sub_commands: ClassVar[ # Any to work around variance issues - list[tuple[str, Callable[[Any], bool] | None]] - ] = [] - - user_options: ClassVar[ - # Specifying both because list is invariant. Avoids mypy override assignment issues - list[tuple[str, str, str]] | list[tuple[str, str | None, str]] - ] = [] - - # -- Creation/initialization methods ------------------------------- - - def __init__(self, dist: Distribution) -> None: - """Create and initialize a new Command object. Most importantly, - invokes the 'initialize_options()' method, which is the real - initializer and depends on the actual command being - instantiated. - """ - # late import because of mutual dependence between these classes - from distutils.dist import Distribution - - if not isinstance(dist, Distribution): - raise TypeError("dist must be a Distribution instance") - if self.__class__ is Command: - raise RuntimeError("Command is an abstract class") - - self.distribution = dist - self.initialize_options() - - # Per-command versions of the global flags, so that the user can - # customize Distutils' behaviour command-by-command and let some - # commands fall back on the Distribution's behaviour. None means - # "not defined, check self.distribution's copy", while 0 or 1 mean - # false and true (duh). Note that this means figuring out the real - # value of each flag is a touch complicated -- hence "self._dry_run" - # will be handled by __getattr__, below. - # XXX This needs to be fixed. - self._dry_run = None - - # verbose is largely ignored, but needs to be set for - # backwards compatibility (I think)? - self.verbose = dist.verbose - - # Some commands define a 'self.force' option to ignore file - # timestamps, but methods defined *here* assume that - # 'self.force' exists for all commands. So define it here - # just to be safe. - self.force = None - - # The 'help' flag is just used for command-line parsing, so - # none of that complicated bureaucracy is needed. - self.help = False - - # 'finalized' records whether or not 'finalize_options()' has been - # called. 'finalize_options()' itself should not pay attention to - # this flag: it is the business of 'ensure_finalized()', which - # always calls 'finalize_options()', to respect/update it. - self.finalized = False - - # XXX A more explicit way to customize dry_run would be better. - def __getattr__(self, attr): - if attr == 'dry_run': - myval = getattr(self, "_" + attr) - if myval is None: - return getattr(self.distribution, attr) - else: - return myval - else: - raise AttributeError(attr) - - def ensure_finalized(self) -> None: - if not self.finalized: - self.finalize_options() - self.finalized = True - - # Subclasses must define: - # initialize_options() - # provide default values for all options; may be customized by - # setup script, by options from config file(s), or by command-line - # options - # finalize_options() - # decide on the final values for all options; this is called - # after all possible intervention from the outside world - # (command-line, option file, etc.) has been processed - # run() - # run the command: do whatever it is we're here to do, - # controlled by the command's various option values - - @abstractmethod - def initialize_options(self) -> None: - """Set default values for all the options that this command - supports. Note that these defaults may be overridden by other - commands, by the setup script, by config files, or by the - command-line. Thus, this is not the place to code dependencies - between options; generally, 'initialize_options()' implementations - are just a bunch of "self.foo = None" assignments. - - This method must be implemented by all command classes. - """ - raise RuntimeError( - f"abstract method -- subclass {self.__class__} must override" - ) - - @abstractmethod - def finalize_options(self) -> None: - """Set final values for all the options that this command supports. - This is always called as late as possible, ie. after any option - assignments from the command-line or from other commands have been - done. Thus, this is the place to code option dependencies: if - 'foo' depends on 'bar', then it is safe to set 'foo' from 'bar' as - long as 'foo' still has the same value it was assigned in - 'initialize_options()'. - - This method must be implemented by all command classes. - """ - raise RuntimeError( - f"abstract method -- subclass {self.__class__} must override" - ) - - def dump_options(self, header=None, indent=""): - from distutils.fancy_getopt import longopt_xlate - - if header is None: - header = f"command options for '{self.get_command_name()}':" - self.announce(indent + header, level=logging.INFO) - indent = indent + " " - for option, _, _ in self.user_options: - option = option.translate(longopt_xlate) - if option[-1] == "=": - option = option[:-1] - value = getattr(self, option) - self.announce(indent + f"{option} = {value}", level=logging.INFO) - - @abstractmethod - def run(self) -> None: - """A command's raison d'etre: carry out the action it exists to - perform, controlled by the options initialized in - 'initialize_options()', customized by other commands, the setup - script, the command-line, and config files, and finalized in - 'finalize_options()'. All terminal output and filesystem - interaction should be done by 'run()'. - - This method must be implemented by all command classes. - """ - raise RuntimeError( - f"abstract method -- subclass {self.__class__} must override" - ) - - def announce(self, msg: object, level: int = logging.DEBUG) -> None: - log.log(level, msg) - - def debug_print(self, msg: object) -> None: - """Print 'msg' to stdout if the global DEBUG (taken from the - DISTUTILS_DEBUG environment variable) flag is true. - """ - from distutils.debug import DEBUG - - if DEBUG: - print(msg) - sys.stdout.flush() - - # -- Option validation methods ------------------------------------- - # (these are very handy in writing the 'finalize_options()' method) - # - # NB. the general philosophy here is to ensure that a particular option - # value meets certain type and value constraints. If not, we try to - # force it into conformance (eg. if we expect a list but have a string, - # split the string on comma and/or whitespace). If we can't force the - # option into conformance, raise DistutilsOptionError. Thus, command - # classes need do nothing more than (eg.) - # self.ensure_string_list('foo') - # and they can be guaranteed that thereafter, self.foo will be - # a list of strings. - - def _ensure_stringlike(self, option, what, default=None): - val = getattr(self, option) - if val is None: - setattr(self, option, default) - return default - elif not isinstance(val, str): - raise DistutilsOptionError(f"'{option}' must be a {what} (got `{val}`)") - return val - - def ensure_string(self, option: str, default: str | None = None) -> None: - """Ensure that 'option' is a string; if not defined, set it to - 'default'. - """ - self._ensure_stringlike(option, "string", default) - - def ensure_string_list(self, option: str) -> None: - r"""Ensure that 'option' is a list of strings. If 'option' is - currently a string, we split it either on /,\s*/ or /\s+/, so - "foo bar baz", "foo,bar,baz", and "foo, bar baz" all become - ["foo", "bar", "baz"]. - """ - val = getattr(self, option) - if val is None: - return - elif isinstance(val, str): - setattr(self, option, re.split(r',\s*|\s+', val)) - else: - if isinstance(val, list): - ok = all(isinstance(v, str) for v in val) - else: - ok = False - if not ok: - raise DistutilsOptionError( - f"'{option}' must be a list of strings (got {val!r})" - ) - - def _ensure_tested_string(self, option, tester, what, error_fmt, default=None): - val = self._ensure_stringlike(option, what, default) - if val is not None and not tester(val): - raise DistutilsOptionError( - ("error in '%s' option: " + error_fmt) % (option, val) - ) - - def ensure_filename(self, option: str) -> None: - """Ensure that 'option' is the name of an existing file.""" - self._ensure_tested_string( - option, os.path.isfile, "filename", "'%s' does not exist or is not a file" - ) - - def ensure_dirname(self, option: str) -> None: - self._ensure_tested_string( - option, - os.path.isdir, - "directory name", - "'%s' does not exist or is not a directory", - ) - - # -- Convenience methods for commands ------------------------------ - - def get_command_name(self) -> str: - if hasattr(self, 'command_name'): - return self.command_name - else: - return self.__class__.__name__ - - def set_undefined_options( - self, src_cmd: str, *option_pairs: tuple[str, str] - ) -> None: - """Set the values of any "undefined" options from corresponding - option values in some other command object. "Undefined" here means - "is None", which is the convention used to indicate that an option - has not been changed between 'initialize_options()' and - 'finalize_options()'. Usually called from 'finalize_options()' for - options that depend on some other command rather than another - option of the same command. 'src_cmd' is the other command from - which option values will be taken (a command object will be created - for it if necessary); the remaining arguments are - '(src_option,dst_option)' tuples which mean "take the value of - 'src_option' in the 'src_cmd' command object, and copy it to - 'dst_option' in the current command object". - """ - # Option_pairs: list of (src_option, dst_option) tuples - src_cmd_obj = self.distribution.get_command_obj(src_cmd) - src_cmd_obj.ensure_finalized() - for src_option, dst_option in option_pairs: - if getattr(self, dst_option) is None: - setattr(self, dst_option, getattr(src_cmd_obj, src_option)) - - # NOTE: Because distutils is private to Setuptools and not all commands are exposed here, - # not every possible command is enumerated in the signature. - def get_finalized_command(self, command: str, create: bool = True) -> Command: - """Wrapper around Distribution's 'get_command_obj()' method: find - (create if necessary and 'create' is true) the command object for - 'command', call its 'ensure_finalized()' method, and return the - finalized command object. - """ - cmd_obj = self.distribution.get_command_obj(command, create) - cmd_obj.ensure_finalized() - return cmd_obj - - # XXX rename to 'get_reinitialized_command()'? (should do the - # same in dist.py, if so) - @overload - def reinitialize_command( - self, command: str, reinit_subcommands: bool = False - ) -> Command: ... - @overload - def reinitialize_command( - self, command: _CommandT, reinit_subcommands: bool = False - ) -> _CommandT: ... - def reinitialize_command( - self, command: str | Command, reinit_subcommands=False - ) -> Command: - return self.distribution.reinitialize_command(command, reinit_subcommands) - - def run_command(self, command: str) -> None: - """Run some other command: uses the 'run_command()' method of - Distribution, which creates and finalizes the command object if - necessary and then invokes its 'run()' method. - """ - self.distribution.run_command(command) - - def get_sub_commands(self) -> list[str]: - """Determine the sub-commands that are relevant in the current - distribution (ie., that need to be run). This is based on the - 'sub_commands' class attribute: each tuple in that list may include - a method that we call to determine if the subcommand needs to be - run for the current distribution. Return a list of command names. - """ - commands = [] - for cmd_name, method in self.sub_commands: - if method is None or method(self): - commands.append(cmd_name) - return commands - - # -- External world manipulation ----------------------------------- - - def warn(self, msg: object) -> None: - log.warning("warning: %s: %s\n", self.get_command_name(), msg) - - def execute( - self, - func: Callable[[Unpack[_Ts]], object], - args: tuple[Unpack[_Ts]], - msg: object = None, - level: int = 1, - ) -> None: - util.execute(func, args, msg, dry_run=self.dry_run) - - def mkpath(self, name: str, mode: int = 0o777) -> None: - dir_util.mkpath(name, mode, dry_run=self.dry_run) - - @overload - def copy_file( - self, - infile: str | os.PathLike[str], - outfile: _StrPathT, - preserve_mode: bool = True, - preserve_times: bool = True, - link: str | None = None, - level: int = 1, - ) -> tuple[_StrPathT | str, bool]: ... - @overload - def copy_file( - self, - infile: bytes | os.PathLike[bytes], - outfile: _BytesPathT, - preserve_mode: bool = True, - preserve_times: bool = True, - link: str | None = None, - level: int = 1, - ) -> tuple[_BytesPathT | bytes, bool]: ... - def copy_file( - self, - infile: str | os.PathLike[str] | bytes | os.PathLike[bytes], - outfile: str | os.PathLike[str] | bytes | os.PathLike[bytes], - preserve_mode: bool = True, - preserve_times: bool = True, - link: str | None = None, - level: int = 1, - ) -> tuple[str | os.PathLike[str] | bytes | os.PathLike[bytes], bool]: - """Copy a file respecting verbose, dry-run and force flags. (The - former two default to whatever is in the Distribution object, and - the latter defaults to false for commands that don't define it.)""" - return file_util.copy_file( - infile, - outfile, - preserve_mode, - preserve_times, - not self.force, - link, - dry_run=self.dry_run, - ) - - def copy_tree( - self, - infile: str | os.PathLike[str], - outfile: str, - preserve_mode: bool = True, - preserve_times: bool = True, - preserve_symlinks: bool = False, - level: int = 1, - ) -> list[str]: - """Copy an entire directory tree respecting verbose, dry-run, - and force flags. - """ - return dir_util.copy_tree( - infile, - outfile, - preserve_mode, - preserve_times, - preserve_symlinks, - not self.force, - dry_run=self.dry_run, - ) - - @overload - def move_file( - self, src: str | os.PathLike[str], dst: _StrPathT, level: int = 1 - ) -> _StrPathT | str: ... - @overload - def move_file( - self, src: bytes | os.PathLike[bytes], dst: _BytesPathT, level: int = 1 - ) -> _BytesPathT | bytes: ... - def move_file( - self, - src: str | os.PathLike[str] | bytes | os.PathLike[bytes], - dst: str | os.PathLike[str] | bytes | os.PathLike[bytes], - level: int = 1, - ) -> str | os.PathLike[str] | bytes | os.PathLike[bytes]: - """Move a file respecting dry-run flag.""" - return file_util.move_file(src, dst, dry_run=self.dry_run) - - def spawn( - self, cmd: MutableSequence[str], search_path: bool = True, level: int = 1 - ) -> None: - """Spawn an external command respecting dry-run flag.""" - from distutils.spawn import spawn - - spawn(cmd, search_path, dry_run=self.dry_run) - - @overload - def make_archive( - self, - base_name: str, - format: str, - root_dir: str | os.PathLike[str] | bytes | os.PathLike[bytes] | None = None, - base_dir: str | None = None, - owner: str | None = None, - group: str | None = None, - ) -> str: ... - @overload - def make_archive( - self, - base_name: str | os.PathLike[str], - format: str, - root_dir: str | os.PathLike[str] | bytes | os.PathLike[bytes], - base_dir: str | None = None, - owner: str | None = None, - group: str | None = None, - ) -> str: ... - def make_archive( - self, - base_name: str | os.PathLike[str], - format: str, - root_dir: str | os.PathLike[str] | bytes | os.PathLike[bytes] | None = None, - base_dir: str | None = None, - owner: str | None = None, - group: str | None = None, - ) -> str: - return archive_util.make_archive( - base_name, - format, - root_dir, - base_dir, - dry_run=self.dry_run, - owner=owner, - group=group, - ) - - def make_file( - self, - infiles: str | list[str] | tuple[str, ...], - outfile: str | os.PathLike[str] | bytes | os.PathLike[bytes], - func: Callable[[Unpack[_Ts]], object], - args: tuple[Unpack[_Ts]], - exec_msg: object = None, - skip_msg: object = None, - level: int = 1, - ) -> None: - """Special case of 'execute()' for operations that process one or - more input files and generate one output file. Works just like - 'execute()', except the operation is skipped and a different - message printed if 'outfile' already exists and is newer than all - files listed in 'infiles'. If the command defined 'self.force', - and it is true, then the command is unconditionally run -- does no - timestamp checks. - """ - if skip_msg is None: - skip_msg = f"skipping {outfile} (inputs unchanged)" - - # Allow 'infiles' to be a single string - if isinstance(infiles, str): - infiles = (infiles,) - elif not isinstance(infiles, (list, tuple)): - raise TypeError("'infiles' must be a string, or a list or tuple of strings") - - if exec_msg is None: - exec_msg = "generating {} from {}".format(outfile, ', '.join(infiles)) - - # If 'outfile' must be regenerated (either because it doesn't - # exist, is out-of-date, or the 'force' flag is true) then - # perform the action that presumably regenerates it - if self.force or _modified.newer_group(infiles, outfile): - self.execute(func, args, exec_msg, level) - # Otherwise, print the "skip" message - else: - log.debug(skip_msg) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__init__.py deleted file mode 100644 index 0f8a169..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__init__.py +++ /dev/null @@ -1,23 +0,0 @@ -"""distutils.command - -Package containing implementation of all the standard Distutils -commands.""" - -__all__ = [ - 'build', - 'build_py', - 'build_ext', - 'build_clib', - 'build_scripts', - 'clean', - 'install', - 'install_lib', - 'install_headers', - 'install_scripts', - 'install_data', - 'sdist', - 'bdist', - 'bdist_dumb', - 'bdist_rpm', - 'check', -] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index a10a9a6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/_framework_compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/_framework_compat.cpython-312.pyc deleted file mode 100644 index b2f222f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/_framework_compat.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist.cpython-312.pyc deleted file mode 100644 index b80c3ee..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist_dumb.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist_dumb.cpython-312.pyc deleted file mode 100644 index 96c6b99..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist_dumb.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist_rpm.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist_rpm.cpython-312.pyc deleted file mode 100644 index 17ebc56..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/bdist_rpm.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build.cpython-312.pyc deleted file mode 100644 index 9d8036a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_clib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_clib.cpython-312.pyc deleted file mode 100644 index 6583c05..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_clib.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_ext.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_ext.cpython-312.pyc deleted file mode 100644 index b7c6b9f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_ext.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_py.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_py.cpython-312.pyc deleted file mode 100644 index 096a8d9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_py.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_scripts.cpython-312.pyc deleted file mode 100644 index 01eea1c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/build_scripts.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/check.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/check.cpython-312.pyc deleted file mode 100644 index bd4bdaa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/check.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/clean.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/clean.cpython-312.pyc deleted file mode 100644 index c017542..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/clean.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/config.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/config.cpython-312.pyc deleted file mode 100644 index 4ac498d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/config.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install.cpython-312.pyc deleted file mode 100644 index 5ee152f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_data.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_data.cpython-312.pyc deleted file mode 100644 index aa737ee..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_data.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_egg_info.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_egg_info.cpython-312.pyc deleted file mode 100644 index 6330544..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_egg_info.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_headers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_headers.cpython-312.pyc deleted file mode 100644 index 1e3e978..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_headers.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_lib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_lib.cpython-312.pyc deleted file mode 100644 index 77d3f44..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_lib.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_scripts.cpython-312.pyc deleted file mode 100644 index df1a606..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/install_scripts.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/sdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/sdist.cpython-312.pyc deleted file mode 100644 index 9e72f27..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/__pycache__/sdist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/_framework_compat.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/_framework_compat.py deleted file mode 100644 index 00d34bc..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/_framework_compat.py +++ /dev/null @@ -1,54 +0,0 @@ -""" -Backward compatibility for homebrew builds on macOS. -""" - -import functools -import os -import subprocess -import sys -import sysconfig - - -@functools.lru_cache -def enabled(): - """ - Only enabled for Python 3.9 framework homebrew builds - except ensurepip and venv. - """ - PY39 = (3, 9) < sys.version_info < (3, 10) - framework = sys.platform == 'darwin' and sys._framework - homebrew = "Cellar" in sysconfig.get_config_var('projectbase') - venv = sys.prefix != sys.base_prefix - ensurepip = os.environ.get("ENSUREPIP_OPTIONS") - return PY39 and framework and homebrew and not venv and not ensurepip - - -schemes = dict( - osx_framework_library=dict( - stdlib='{installed_base}/{platlibdir}/python{py_version_short}', - platstdlib='{platbase}/{platlibdir}/python{py_version_short}', - purelib='{homebrew_prefix}/lib/python{py_version_short}/site-packages', - platlib='{homebrew_prefix}/{platlibdir}/python{py_version_short}/site-packages', - include='{installed_base}/include/python{py_version_short}{abiflags}', - platinclude='{installed_platbase}/include/python{py_version_short}{abiflags}', - scripts='{homebrew_prefix}/bin', - data='{homebrew_prefix}', - ) -) - - -@functools.lru_cache -def vars(): - if not enabled(): - return {} - homebrew_prefix = subprocess.check_output(['brew', '--prefix'], text=True).strip() - return locals() - - -def scheme(name): - """ - Override the selected scheme for posix_prefix. - """ - if not enabled() or not name.endswith('_prefix'): - return name - return 'osx_framework_library' diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist.py deleted file mode 100644 index 07811aa..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist.py +++ /dev/null @@ -1,167 +0,0 @@ -"""distutils.command.bdist - -Implements the Distutils 'bdist' command (create a built [binary] -distribution).""" - -from __future__ import annotations - -import os -import warnings -from collections.abc import Callable -from typing import TYPE_CHECKING, ClassVar - -from ..core import Command -from ..errors import DistutilsOptionError, DistutilsPlatformError -from ..util import get_platform - -if TYPE_CHECKING: - from typing_extensions import deprecated -else: - - def deprecated(message): - return lambda fn: fn - - -def show_formats(): - """Print list of available formats (arguments to "--format" option).""" - from ..fancy_getopt import FancyGetopt - - formats = [ - ("formats=" + format, None, bdist.format_commands[format][1]) - for format in bdist.format_commands - ] - pretty_printer = FancyGetopt(formats) - pretty_printer.print_help("List of available distribution formats:") - - -class ListCompat(dict[str, tuple[str, str]]): - # adapter to allow for Setuptools compatibility in format_commands - @deprecated("format_commands is now a dict. append is deprecated.") - def append(self, item: object) -> None: - warnings.warn( - "format_commands is now a dict. append is deprecated.", - DeprecationWarning, - stacklevel=2, - ) - - -class bdist(Command): - description = "create a built (binary) distribution" - - user_options = [ - ('bdist-base=', 'b', "temporary directory for creating built distributions"), - ( - 'plat-name=', - 'p', - "platform name to embed in generated filenames " - f"[default: {get_platform()}]", - ), - ('formats=', None, "formats for distribution (comma-separated list)"), - ( - 'dist-dir=', - 'd', - "directory to put final built distributions in [default: dist]", - ), - ('skip-build', None, "skip rebuilding everything (for testing/debugging)"), - ( - 'owner=', - 'u', - "Owner name used when creating a tar file [default: current user]", - ), - ( - 'group=', - 'g', - "Group name used when creating a tar file [default: current group]", - ), - ] - - boolean_options: ClassVar[list[str]] = ['skip-build'] - - help_options: ClassVar[list[tuple[str, str | None, str, Callable[[], object]]]] = [ - ('help-formats', None, "lists available distribution formats", show_formats), - ] - - # The following commands do not take a format option from bdist - no_format_option: ClassVar[tuple[str, ...]] = ('bdist_rpm',) - - # This won't do in reality: will need to distinguish RPM-ish Linux, - # Debian-ish Linux, Solaris, FreeBSD, ..., Windows, Mac OS. - default_format: ClassVar[dict[str, str]] = {'posix': 'gztar', 'nt': 'zip'} - - # Define commands in preferred order for the --help-formats option - format_commands = ListCompat({ - 'rpm': ('bdist_rpm', "RPM distribution"), - 'gztar': ('bdist_dumb', "gzip'ed tar file"), - 'bztar': ('bdist_dumb', "bzip2'ed tar file"), - 'xztar': ('bdist_dumb', "xz'ed tar file"), - 'ztar': ('bdist_dumb', "compressed tar file"), - 'tar': ('bdist_dumb', "tar file"), - 'zip': ('bdist_dumb', "ZIP file"), - }) - - # for compatibility until consumers only reference format_commands - format_command = format_commands - - def initialize_options(self): - self.bdist_base = None - self.plat_name = None - self.formats = None - self.dist_dir = None - self.skip_build = False - self.group = None - self.owner = None - - def finalize_options(self) -> None: - # have to finalize 'plat_name' before 'bdist_base' - if self.plat_name is None: - if self.skip_build: - self.plat_name = get_platform() - else: - self.plat_name = self.get_finalized_command('build').plat_name - - # 'bdist_base' -- parent of per-built-distribution-format - # temporary directories (eg. we'll probably have - # "build/bdist./dumb", "build/bdist./rpm", etc.) - if self.bdist_base is None: - build_base = self.get_finalized_command('build').build_base - self.bdist_base = os.path.join(build_base, 'bdist.' + self.plat_name) - - self.ensure_string_list('formats') - if self.formats is None: - try: - self.formats = [self.default_format[os.name]] - except KeyError: - raise DistutilsPlatformError( - "don't know how to create built distributions " - f"on platform {os.name}" - ) - - if self.dist_dir is None: - self.dist_dir = "dist" - - def run(self) -> None: - # Figure out which sub-commands we need to run. - commands = [] - for format in self.formats: - try: - commands.append(self.format_commands[format][0]) - except KeyError: - raise DistutilsOptionError(f"invalid format '{format}'") - - # Reinitialize and run each command. - for i in range(len(self.formats)): - cmd_name = commands[i] - sub_cmd = self.reinitialize_command(cmd_name) - if cmd_name not in self.no_format_option: - sub_cmd.format = self.formats[i] - - # passing the owner and group names for tar archiving - if cmd_name == 'bdist_dumb': - sub_cmd.owner = self.owner - sub_cmd.group = self.group - - # If we're going to need to run this command again, tell it to - # keep its temporary files around so subsequent runs go faster. - if cmd_name in commands[i + 1 :]: - sub_cmd.keep_temp = True - self.run_command(cmd_name) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist_dumb.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist_dumb.py deleted file mode 100644 index ccad66f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist_dumb.py +++ /dev/null @@ -1,141 +0,0 @@ -"""distutils.command.bdist_dumb - -Implements the Distutils 'bdist_dumb' command (create a "dumb" built -distribution -- i.e., just an archive to be unpacked under $prefix or -$exec_prefix).""" - -import os -from distutils._log import log -from typing import ClassVar - -from ..core import Command -from ..dir_util import ensure_relative, remove_tree -from ..errors import DistutilsPlatformError -from ..sysconfig import get_python_version -from ..util import get_platform - - -class bdist_dumb(Command): - description = "create a \"dumb\" built distribution" - - user_options = [ - ('bdist-dir=', 'd', "temporary directory for creating the distribution"), - ( - 'plat-name=', - 'p', - "platform name to embed in generated filenames " - f"[default: {get_platform()}]", - ), - ( - 'format=', - 'f', - "archive format to create (tar, gztar, bztar, xztar, ztar, zip)", - ), - ( - 'keep-temp', - 'k', - "keep the pseudo-installation tree around after creating the distribution archive", - ), - ('dist-dir=', 'd', "directory to put final built distributions in"), - ('skip-build', None, "skip rebuilding everything (for testing/debugging)"), - ( - 'relative', - None, - "build the archive using relative paths [default: false]", - ), - ( - 'owner=', - 'u', - "Owner name used when creating a tar file [default: current user]", - ), - ( - 'group=', - 'g', - "Group name used when creating a tar file [default: current group]", - ), - ] - - boolean_options: ClassVar[list[str]] = ['keep-temp', 'skip-build', 'relative'] - - default_format = {'posix': 'gztar', 'nt': 'zip'} - - def initialize_options(self): - self.bdist_dir = None - self.plat_name = None - self.format = None - self.keep_temp = False - self.dist_dir = None - self.skip_build = None - self.relative = False - self.owner = None - self.group = None - - def finalize_options(self): - if self.bdist_dir is None: - bdist_base = self.get_finalized_command('bdist').bdist_base - self.bdist_dir = os.path.join(bdist_base, 'dumb') - - if self.format is None: - try: - self.format = self.default_format[os.name] - except KeyError: - raise DistutilsPlatformError( - "don't know how to create dumb built distributions " - f"on platform {os.name}" - ) - - self.set_undefined_options( - 'bdist', - ('dist_dir', 'dist_dir'), - ('plat_name', 'plat_name'), - ('skip_build', 'skip_build'), - ) - - def run(self): - if not self.skip_build: - self.run_command('build') - - install = self.reinitialize_command('install', reinit_subcommands=True) - install.root = self.bdist_dir - install.skip_build = self.skip_build - install.warn_dir = False - - log.info("installing to %s", self.bdist_dir) - self.run_command('install') - - # And make an archive relative to the root of the - # pseudo-installation tree. - archive_basename = f"{self.distribution.get_fullname()}.{self.plat_name}" - - pseudoinstall_root = os.path.join(self.dist_dir, archive_basename) - if not self.relative: - archive_root = self.bdist_dir - else: - if self.distribution.has_ext_modules() and ( - install.install_base != install.install_platbase - ): - raise DistutilsPlatformError( - "can't make a dumb built distribution where " - f"base and platbase are different ({install.install_base!r}, {install.install_platbase!r})" - ) - else: - archive_root = os.path.join( - self.bdist_dir, ensure_relative(install.install_base) - ) - - # Make the archive - filename = self.make_archive( - pseudoinstall_root, - self.format, - root_dir=archive_root, - owner=self.owner, - group=self.group, - ) - if self.distribution.has_ext_modules(): - pyversion = get_python_version() - else: - pyversion = 'any' - self.distribution.dist_files.append(('bdist_dumb', pyversion, filename)) - - if not self.keep_temp: - remove_tree(self.bdist_dir, dry_run=self.dry_run) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist_rpm.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist_rpm.py deleted file mode 100644 index 357b4e8..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/bdist_rpm.py +++ /dev/null @@ -1,598 +0,0 @@ -"""distutils.command.bdist_rpm - -Implements the Distutils 'bdist_rpm' command (create RPM source and binary -distributions).""" - -import os -import subprocess -import sys -from distutils._log import log -from typing import ClassVar - -from ..core import Command -from ..debug import DEBUG -from ..errors import ( - DistutilsExecError, - DistutilsFileError, - DistutilsOptionError, - DistutilsPlatformError, -) -from ..file_util import write_file -from ..sysconfig import get_python_version - - -class bdist_rpm(Command): - description = "create an RPM distribution" - - user_options = [ - ('bdist-base=', None, "base directory for creating built distributions"), - ( - 'rpm-base=', - None, - "base directory for creating RPMs (defaults to \"rpm\" under " - "--bdist-base; must be specified for RPM 2)", - ), - ( - 'dist-dir=', - 'd', - "directory to put final RPM files in (and .spec files if --spec-only)", - ), - ( - 'python=', - None, - "path to Python interpreter to hard-code in the .spec file " - "[default: \"python\"]", - ), - ( - 'fix-python', - None, - "hard-code the exact path to the current Python interpreter in " - "the .spec file", - ), - ('spec-only', None, "only regenerate spec file"), - ('source-only', None, "only generate source RPM"), - ('binary-only', None, "only generate binary RPM"), - ('use-bzip2', None, "use bzip2 instead of gzip to create source distribution"), - # More meta-data: too RPM-specific to put in the setup script, - # but needs to go in the .spec file -- so we make these options - # to "bdist_rpm". The idea is that packagers would put this - # info in setup.cfg, although they are of course free to - # supply it on the command line. - ( - 'distribution-name=', - None, - "name of the (Linux) distribution to which this " - "RPM applies (*not* the name of the module distribution!)", - ), - ('group=', None, "package classification [default: \"Development/Libraries\"]"), - ('release=', None, "RPM release number"), - ('serial=', None, "RPM serial number"), - ( - 'vendor=', - None, - "RPM \"vendor\" (eg. \"Joe Blow \") " - "[default: maintainer or author from setup script]", - ), - ( - 'packager=', - None, - "RPM packager (eg. \"Jane Doe \") [default: vendor]", - ), - ('doc-files=', None, "list of documentation files (space or comma-separated)"), - ('changelog=', None, "RPM changelog"), - ('icon=', None, "name of icon file"), - ('provides=', None, "capabilities provided by this package"), - ('requires=', None, "capabilities required by this package"), - ('conflicts=', None, "capabilities which conflict with this package"), - ('build-requires=', None, "capabilities required to build this package"), - ('obsoletes=', None, "capabilities made obsolete by this package"), - ('no-autoreq', None, "do not automatically calculate dependencies"), - # Actions to take when building RPM - ('keep-temp', 'k', "don't clean up RPM build directory"), - ('no-keep-temp', None, "clean up RPM build directory [default]"), - ( - 'use-rpm-opt-flags', - None, - "compile with RPM_OPT_FLAGS when building from source RPM", - ), - ('no-rpm-opt-flags', None, "do not pass any RPM CFLAGS to compiler"), - ('rpm3-mode', None, "RPM 3 compatibility mode (default)"), - ('rpm2-mode', None, "RPM 2 compatibility mode"), - # Add the hooks necessary for specifying custom scripts - ('prep-script=', None, "Specify a script for the PREP phase of RPM building"), - ('build-script=', None, "Specify a script for the BUILD phase of RPM building"), - ( - 'pre-install=', - None, - "Specify a script for the pre-INSTALL phase of RPM building", - ), - ( - 'install-script=', - None, - "Specify a script for the INSTALL phase of RPM building", - ), - ( - 'post-install=', - None, - "Specify a script for the post-INSTALL phase of RPM building", - ), - ( - 'pre-uninstall=', - None, - "Specify a script for the pre-UNINSTALL phase of RPM building", - ), - ( - 'post-uninstall=', - None, - "Specify a script for the post-UNINSTALL phase of RPM building", - ), - ('clean-script=', None, "Specify a script for the CLEAN phase of RPM building"), - ( - 'verify-script=', - None, - "Specify a script for the VERIFY phase of the RPM build", - ), - # Allow a packager to explicitly force an architecture - ('force-arch=', None, "Force an architecture onto the RPM build process"), - ('quiet', 'q', "Run the INSTALL phase of RPM building in quiet mode"), - ] - - boolean_options: ClassVar[list[str]] = [ - 'keep-temp', - 'use-rpm-opt-flags', - 'rpm3-mode', - 'no-autoreq', - 'quiet', - ] - - negative_opt: ClassVar[dict[str, str]] = { - 'no-keep-temp': 'keep-temp', - 'no-rpm-opt-flags': 'use-rpm-opt-flags', - 'rpm2-mode': 'rpm3-mode', - } - - def initialize_options(self): - self.bdist_base = None - self.rpm_base = None - self.dist_dir = None - self.python = None - self.fix_python = None - self.spec_only = None - self.binary_only = None - self.source_only = None - self.use_bzip2 = None - - self.distribution_name = None - self.group = None - self.release = None - self.serial = None - self.vendor = None - self.packager = None - self.doc_files = None - self.changelog = None - self.icon = None - - self.prep_script = None - self.build_script = None - self.install_script = None - self.clean_script = None - self.verify_script = None - self.pre_install = None - self.post_install = None - self.pre_uninstall = None - self.post_uninstall = None - self.prep = None - self.provides = None - self.requires = None - self.conflicts = None - self.build_requires = None - self.obsoletes = None - - self.keep_temp = False - self.use_rpm_opt_flags = True - self.rpm3_mode = True - self.no_autoreq = False - - self.force_arch = None - self.quiet = False - - def finalize_options(self) -> None: - self.set_undefined_options('bdist', ('bdist_base', 'bdist_base')) - if self.rpm_base is None: - if not self.rpm3_mode: - raise DistutilsOptionError("you must specify --rpm-base in RPM 2 mode") - self.rpm_base = os.path.join(self.bdist_base, "rpm") - - if self.python is None: - if self.fix_python: - self.python = sys.executable - else: - self.python = "python3" - elif self.fix_python: - raise DistutilsOptionError( - "--python and --fix-python are mutually exclusive options" - ) - - if os.name != 'posix': - raise DistutilsPlatformError( - f"don't know how to create RPM distributions on platform {os.name}" - ) - if self.binary_only and self.source_only: - raise DistutilsOptionError( - "cannot supply both '--source-only' and '--binary-only'" - ) - - # don't pass CFLAGS to pure python distributions - if not self.distribution.has_ext_modules(): - self.use_rpm_opt_flags = False - - self.set_undefined_options('bdist', ('dist_dir', 'dist_dir')) - self.finalize_package_data() - - def finalize_package_data(self) -> None: - self.ensure_string('group', "Development/Libraries") - self.ensure_string( - 'vendor', - f"{self.distribution.get_contact()} <{self.distribution.get_contact_email()}>", - ) - self.ensure_string('packager') - self.ensure_string_list('doc_files') - if isinstance(self.doc_files, list): - for readme in ('README', 'README.txt'): - if os.path.exists(readme) and readme not in self.doc_files: - self.doc_files.append(readme) - - self.ensure_string('release', "1") - self.ensure_string('serial') # should it be an int? - - self.ensure_string('distribution_name') - - self.ensure_string('changelog') - # Format changelog correctly - self.changelog = self._format_changelog(self.changelog) - - self.ensure_filename('icon') - - self.ensure_filename('prep_script') - self.ensure_filename('build_script') - self.ensure_filename('install_script') - self.ensure_filename('clean_script') - self.ensure_filename('verify_script') - self.ensure_filename('pre_install') - self.ensure_filename('post_install') - self.ensure_filename('pre_uninstall') - self.ensure_filename('post_uninstall') - - # XXX don't forget we punted on summaries and descriptions -- they - # should be handled here eventually! - - # Now *this* is some meta-data that belongs in the setup script... - self.ensure_string_list('provides') - self.ensure_string_list('requires') - self.ensure_string_list('conflicts') - self.ensure_string_list('build_requires') - self.ensure_string_list('obsoletes') - - self.ensure_string('force_arch') - - def run(self) -> None: # noqa: C901 - if DEBUG: - print("before _get_package_data():") - print("vendor =", self.vendor) - print("packager =", self.packager) - print("doc_files =", self.doc_files) - print("changelog =", self.changelog) - - # make directories - if self.spec_only: - spec_dir = self.dist_dir - self.mkpath(spec_dir) - else: - rpm_dir = {} - for d in ('SOURCES', 'SPECS', 'BUILD', 'RPMS', 'SRPMS'): - rpm_dir[d] = os.path.join(self.rpm_base, d) - self.mkpath(rpm_dir[d]) - spec_dir = rpm_dir['SPECS'] - - # Spec file goes into 'dist_dir' if '--spec-only specified', - # build/rpm. otherwise. - spec_path = os.path.join(spec_dir, f"{self.distribution.get_name()}.spec") - self.execute( - write_file, (spec_path, self._make_spec_file()), f"writing '{spec_path}'" - ) - - if self.spec_only: # stop if requested - return - - # Make a source distribution and copy to SOURCES directory with - # optional icon. - saved_dist_files = self.distribution.dist_files[:] - sdist = self.reinitialize_command('sdist') - if self.use_bzip2: - sdist.formats = ['bztar'] - else: - sdist.formats = ['gztar'] - self.run_command('sdist') - self.distribution.dist_files = saved_dist_files - - source = sdist.get_archive_files()[0] - source_dir = rpm_dir['SOURCES'] - self.copy_file(source, source_dir) - - if self.icon: - if os.path.exists(self.icon): - self.copy_file(self.icon, source_dir) - else: - raise DistutilsFileError(f"icon file '{self.icon}' does not exist") - - # build package - log.info("building RPMs") - rpm_cmd = ['rpmbuild'] - - if self.source_only: # what kind of RPMs? - rpm_cmd.append('-bs') - elif self.binary_only: - rpm_cmd.append('-bb') - else: - rpm_cmd.append('-ba') - rpm_cmd.extend(['--define', f'__python {self.python}']) - if self.rpm3_mode: - rpm_cmd.extend(['--define', f'_topdir {os.path.abspath(self.rpm_base)}']) - if not self.keep_temp: - rpm_cmd.append('--clean') - - if self.quiet: - rpm_cmd.append('--quiet') - - rpm_cmd.append(spec_path) - # Determine the binary rpm names that should be built out of this spec - # file - # Note that some of these may not be really built (if the file - # list is empty) - nvr_string = "%{name}-%{version}-%{release}" - src_rpm = nvr_string + ".src.rpm" - non_src_rpm = "%{arch}/" + nvr_string + ".%{arch}.rpm" - q_cmd = rf"rpm -q --qf '{src_rpm} {non_src_rpm}\n' --specfile '{spec_path}'" - - out = os.popen(q_cmd) - try: - binary_rpms = [] - source_rpm = None - while True: - line = out.readline() - if not line: - break - ell = line.strip().split() - assert len(ell) == 2 - binary_rpms.append(ell[1]) - # The source rpm is named after the first entry in the spec file - if source_rpm is None: - source_rpm = ell[0] - - status = out.close() - if status: - raise DistutilsExecError(f"Failed to execute: {q_cmd!r}") - - finally: - out.close() - - self.spawn(rpm_cmd) - - if not self.dry_run: - if self.distribution.has_ext_modules(): - pyversion = get_python_version() - else: - pyversion = 'any' - - if not self.binary_only: - srpm = os.path.join(rpm_dir['SRPMS'], source_rpm) - assert os.path.exists(srpm) - self.move_file(srpm, self.dist_dir) - filename = os.path.join(self.dist_dir, source_rpm) - self.distribution.dist_files.append(('bdist_rpm', pyversion, filename)) - - if not self.source_only: - for rpm in binary_rpms: - rpm = os.path.join(rpm_dir['RPMS'], rpm) - if os.path.exists(rpm): - self.move_file(rpm, self.dist_dir) - filename = os.path.join(self.dist_dir, os.path.basename(rpm)) - self.distribution.dist_files.append(( - 'bdist_rpm', - pyversion, - filename, - )) - - def _dist_path(self, path): - return os.path.join(self.dist_dir, os.path.basename(path)) - - def _make_spec_file(self): # noqa: C901 - """Generate the text of an RPM spec file and return it as a - list of strings (one per line). - """ - # definitions and headers - spec_file = [ - '%define name ' + self.distribution.get_name(), - '%define version ' + self.distribution.get_version().replace('-', '_'), - '%define unmangled_version ' + self.distribution.get_version(), - '%define release ' + self.release.replace('-', '_'), - '', - 'Summary: ' + (self.distribution.get_description() or "UNKNOWN"), - ] - - # Workaround for #14443 which affects some RPM based systems such as - # RHEL6 (and probably derivatives) - vendor_hook = subprocess.getoutput('rpm --eval %{__os_install_post}') - # Generate a potential replacement value for __os_install_post (whilst - # normalizing the whitespace to simplify the test for whether the - # invocation of brp-python-bytecompile passes in __python): - vendor_hook = '\n'.join([ - f' {line.strip()} \\' for line in vendor_hook.splitlines() - ]) - problem = "brp-python-bytecompile \\\n" - fixed = "brp-python-bytecompile %{__python} \\\n" - fixed_hook = vendor_hook.replace(problem, fixed) - if fixed_hook != vendor_hook: - spec_file.append('# Workaround for https://bugs.python.org/issue14443') - spec_file.append('%define __os_install_post ' + fixed_hook + '\n') - - # put locale summaries into spec file - # XXX not supported for now (hard to put a dictionary - # in a config file -- arg!) - # for locale in self.summaries.keys(): - # spec_file.append('Summary(%s): %s' % (locale, - # self.summaries[locale])) - - spec_file.extend([ - 'Name: %{name}', - 'Version: %{version}', - 'Release: %{release}', - ]) - - # XXX yuck! this filename is available from the "sdist" command, - # but only after it has run: and we create the spec file before - # running "sdist", in case of --spec-only. - if self.use_bzip2: - spec_file.append('Source0: %{name}-%{unmangled_version}.tar.bz2') - else: - spec_file.append('Source0: %{name}-%{unmangled_version}.tar.gz') - - spec_file.extend([ - 'License: ' + (self.distribution.get_license() or "UNKNOWN"), - 'Group: ' + self.group, - 'BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-buildroot', - 'Prefix: %{_prefix}', - ]) - - if not self.force_arch: - # noarch if no extension modules - if not self.distribution.has_ext_modules(): - spec_file.append('BuildArch: noarch') - else: - spec_file.append(f'BuildArch: {self.force_arch}') - - for field in ( - 'Vendor', - 'Packager', - 'Provides', - 'Requires', - 'Conflicts', - 'Obsoletes', - ): - val = getattr(self, field.lower()) - if isinstance(val, list): - spec_file.append('{}: {}'.format(field, ' '.join(val))) - elif val is not None: - spec_file.append(f'{field}: {val}') - - if self.distribution.get_url(): - spec_file.append('Url: ' + self.distribution.get_url()) - - if self.distribution_name: - spec_file.append('Distribution: ' + self.distribution_name) - - if self.build_requires: - spec_file.append('BuildRequires: ' + ' '.join(self.build_requires)) - - if self.icon: - spec_file.append('Icon: ' + os.path.basename(self.icon)) - - if self.no_autoreq: - spec_file.append('AutoReq: 0') - - spec_file.extend([ - '', - '%description', - self.distribution.get_long_description() or "", - ]) - - # put locale descriptions into spec file - # XXX again, suppressed because config file syntax doesn't - # easily support this ;-( - # for locale in self.descriptions.keys(): - # spec_file.extend([ - # '', - # '%description -l ' + locale, - # self.descriptions[locale], - # ]) - - # rpm scripts - # figure out default build script - def_setup_call = f"{self.python} {os.path.basename(sys.argv[0])}" - def_build = f"{def_setup_call} build" - if self.use_rpm_opt_flags: - def_build = 'env CFLAGS="$RPM_OPT_FLAGS" ' + def_build - - # insert contents of files - - # XXX this is kind of misleading: user-supplied options are files - # that we open and interpolate into the spec file, but the defaults - # are just text that we drop in as-is. Hmmm. - - install_cmd = f'{def_setup_call} install -O1 --root=$RPM_BUILD_ROOT --record=INSTALLED_FILES' - - script_options = [ - ('prep', 'prep_script', "%setup -n %{name}-%{unmangled_version}"), - ('build', 'build_script', def_build), - ('install', 'install_script', install_cmd), - ('clean', 'clean_script', "rm -rf $RPM_BUILD_ROOT"), - ('verifyscript', 'verify_script', None), - ('pre', 'pre_install', None), - ('post', 'post_install', None), - ('preun', 'pre_uninstall', None), - ('postun', 'post_uninstall', None), - ] - - for rpm_opt, attr, default in script_options: - # Insert contents of file referred to, if no file is referred to - # use 'default' as contents of script - val = getattr(self, attr) - if val or default: - spec_file.extend([ - '', - '%' + rpm_opt, - ]) - if val: - with open(val) as f: - spec_file.extend(f.read().split('\n')) - else: - spec_file.append(default) - - # files section - spec_file.extend([ - '', - '%files -f INSTALLED_FILES', - '%defattr(-,root,root)', - ]) - - if self.doc_files: - spec_file.append('%doc ' + ' '.join(self.doc_files)) - - if self.changelog: - spec_file.extend([ - '', - '%changelog', - ]) - spec_file.extend(self.changelog) - - return spec_file - - def _format_changelog(self, changelog): - """Format the changelog correctly and convert it to a list of strings""" - if not changelog: - return changelog - new_changelog = [] - for line in changelog.strip().split('\n'): - line = line.strip() - if line[0] == '*': - new_changelog.extend(['', line]) - elif line[0] == '-': - new_changelog.append(line) - else: - new_changelog.append(' ' + line) - - # strip trailing newline inserted by first changelog entry - if not new_changelog[0]: - del new_changelog[0] - - return new_changelog diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build.py deleted file mode 100644 index 6a8303a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build.py +++ /dev/null @@ -1,156 +0,0 @@ -"""distutils.command.build - -Implements the Distutils 'build' command.""" - -from __future__ import annotations - -import os -import sys -import sysconfig -from collections.abc import Callable -from typing import ClassVar - -from ..ccompiler import show_compilers -from ..core import Command -from ..errors import DistutilsOptionError -from ..util import get_platform - - -class build(Command): - description = "build everything needed to install" - - user_options = [ - ('build-base=', 'b', "base directory for build library"), - ('build-purelib=', None, "build directory for platform-neutral distributions"), - ('build-platlib=', None, "build directory for platform-specific distributions"), - ( - 'build-lib=', - None, - "build directory for all distribution (defaults to either build-purelib or build-platlib", - ), - ('build-scripts=', None, "build directory for scripts"), - ('build-temp=', 't', "temporary build directory"), - ( - 'plat-name=', - 'p', - f"platform name to build for, if supported [default: {get_platform()}]", - ), - ('compiler=', 'c', "specify the compiler type"), - ('parallel=', 'j', "number of parallel build jobs"), - ('debug', 'g', "compile extensions and libraries with debugging information"), - ('force', 'f', "forcibly build everything (ignore file timestamps)"), - ('executable=', 'e', "specify final destination interpreter path (build.py)"), - ] - - boolean_options: ClassVar[list[str]] = ['debug', 'force'] - - help_options: ClassVar[list[tuple[str, str | None, str, Callable[[], object]]]] = [ - ('help-compiler', None, "list available compilers", show_compilers), - ] - - def initialize_options(self): - self.build_base = 'build' - # these are decided only after 'build_base' has its final value - # (unless overridden by the user or client) - self.build_purelib = None - self.build_platlib = None - self.build_lib = None - self.build_temp = None - self.build_scripts = None - self.compiler = None - self.plat_name = None - self.debug = None - self.force = False - self.executable = None - self.parallel = None - - def finalize_options(self) -> None: # noqa: C901 - if self.plat_name is None: - self.plat_name = get_platform() - else: - # plat-name only supported for windows (other platforms are - # supported via ./configure flags, if at all). Avoid misleading - # other platforms. - if os.name != 'nt': - raise DistutilsOptionError( - "--plat-name only supported on Windows (try " - "using './configure --help' on your platform)" - ) - - plat_specifier = f".{self.plat_name}-{sys.implementation.cache_tag}" - - # Python 3.13+ with --disable-gil shouldn't share build directories - if sysconfig.get_config_var('Py_GIL_DISABLED'): - plat_specifier += 't' - - # Make it so Python 2.x and Python 2.x with --with-pydebug don't - # share the same build directories. Doing so confuses the build - # process for C modules - if hasattr(sys, 'gettotalrefcount'): - plat_specifier += '-pydebug' - - # 'build_purelib' and 'build_platlib' just default to 'lib' and - # 'lib.' under the base build directory. We only use one of - # them for a given distribution, though -- - if self.build_purelib is None: - self.build_purelib = os.path.join(self.build_base, 'lib') - if self.build_platlib is None: - self.build_platlib = os.path.join(self.build_base, 'lib' + plat_specifier) - - # 'build_lib' is the actual directory that we will use for this - # particular module distribution -- if user didn't supply it, pick - # one of 'build_purelib' or 'build_platlib'. - if self.build_lib is None: - if self.distribution.has_ext_modules(): - self.build_lib = self.build_platlib - else: - self.build_lib = self.build_purelib - - # 'build_temp' -- temporary directory for compiler turds, - # "build/temp." - if self.build_temp is None: - self.build_temp = os.path.join(self.build_base, 'temp' + plat_specifier) - if self.build_scripts is None: - self.build_scripts = os.path.join( - self.build_base, - f'scripts-{sys.version_info.major}.{sys.version_info.minor}', - ) - - if self.executable is None and sys.executable: - self.executable = os.path.normpath(sys.executable) - - if isinstance(self.parallel, str): - try: - self.parallel = int(self.parallel) - except ValueError: - raise DistutilsOptionError("parallel should be an integer") - - def run(self) -> None: - # Run all relevant sub-commands. This will be some subset of: - # - build_py - pure Python modules - # - build_clib - standalone C libraries - # - build_ext - Python extensions - # - build_scripts - (Python) scripts - for cmd_name in self.get_sub_commands(): - self.run_command(cmd_name) - - # -- Predicates for the sub-command list --------------------------- - - def has_pure_modules(self): - return self.distribution.has_pure_modules() - - def has_c_libraries(self): - return self.distribution.has_c_libraries() - - def has_ext_modules(self): - return self.distribution.has_ext_modules() - - def has_scripts(self): - return self.distribution.has_scripts() - - sub_commands = [ - ('build_py', has_pure_modules), - ('build_clib', has_c_libraries), - ('build_ext', has_ext_modules), - ('build_scripts', has_scripts), - ] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_clib.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_clib.py deleted file mode 100644 index 8b65b3d..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_clib.py +++ /dev/null @@ -1,201 +0,0 @@ -"""distutils.command.build_clib - -Implements the Distutils 'build_clib' command, to build a C/C++ library -that is included in the module distribution and needed by an extension -module.""" - -# XXX this module has *lots* of code ripped-off quite transparently from -# build_ext.py -- not surprisingly really, as the work required to build -# a static library from a collection of C source files is not really all -# that different from what's required to build a shared object file from -# a collection of C source files. Nevertheless, I haven't done the -# necessary refactoring to account for the overlap in code between the -# two modules, mainly because a number of subtle details changed in the -# cut 'n paste. Sigh. -from __future__ import annotations - -import os -from collections.abc import Callable -from distutils._log import log -from typing import ClassVar - -from ..ccompiler import new_compiler, show_compilers -from ..core import Command -from ..errors import DistutilsSetupError -from ..sysconfig import customize_compiler - - -class build_clib(Command): - description = "build C/C++ libraries used by Python extensions" - - user_options: ClassVar[list[tuple[str, str, str]]] = [ - ('build-clib=', 'b', "directory to build C/C++ libraries to"), - ('build-temp=', 't', "directory to put temporary build by-products"), - ('debug', 'g', "compile with debugging information"), - ('force', 'f', "forcibly build everything (ignore file timestamps)"), - ('compiler=', 'c', "specify the compiler type"), - ] - - boolean_options: ClassVar[list[str]] = ['debug', 'force'] - - help_options: ClassVar[list[tuple[str, str | None, str, Callable[[], object]]]] = [ - ('help-compiler', None, "list available compilers", show_compilers), - ] - - def initialize_options(self): - self.build_clib = None - self.build_temp = None - - # List of libraries to build - self.libraries = None - - # Compilation options for all libraries - self.include_dirs = None - self.define = None - self.undef = None - self.debug = None - self.force = False - self.compiler = None - - def finalize_options(self) -> None: - # This might be confusing: both build-clib and build-temp default - # to build-temp as defined by the "build" command. This is because - # I think that C libraries are really just temporary build - # by-products, at least from the point of view of building Python - # extensions -- but I want to keep my options open. - self.set_undefined_options( - 'build', - ('build_temp', 'build_clib'), - ('build_temp', 'build_temp'), - ('compiler', 'compiler'), - ('debug', 'debug'), - ('force', 'force'), - ) - - self.libraries = self.distribution.libraries - if self.libraries: - self.check_library_list(self.libraries) - - if self.include_dirs is None: - self.include_dirs = self.distribution.include_dirs or [] - if isinstance(self.include_dirs, str): - self.include_dirs = self.include_dirs.split(os.pathsep) - - # XXX same as for build_ext -- what about 'self.define' and - # 'self.undef' ? - - def run(self) -> None: - if not self.libraries: - return - - self.compiler = new_compiler( - compiler=self.compiler, dry_run=self.dry_run, force=self.force - ) - customize_compiler(self.compiler) - - if self.include_dirs is not None: - self.compiler.set_include_dirs(self.include_dirs) - if self.define is not None: - # 'define' option is a list of (name,value) tuples - for name, value in self.define: - self.compiler.define_macro(name, value) - if self.undef is not None: - for macro in self.undef: - self.compiler.undefine_macro(macro) - - self.build_libraries(self.libraries) - - def check_library_list(self, libraries) -> None: - """Ensure that the list of libraries is valid. - - `library` is presumably provided as a command option 'libraries'. - This method checks that it is a list of 2-tuples, where the tuples - are (library_name, build_info_dict). - - Raise DistutilsSetupError if the structure is invalid anywhere; - just returns otherwise. - """ - if not isinstance(libraries, list): - raise DistutilsSetupError("'libraries' option must be a list of tuples") - - for lib in libraries: - if not isinstance(lib, tuple) and len(lib) != 2: - raise DistutilsSetupError("each element of 'libraries' must a 2-tuple") - - name, build_info = lib - - if not isinstance(name, str): - raise DistutilsSetupError( - "first element of each tuple in 'libraries' " - "must be a string (the library name)" - ) - - if '/' in name or (os.sep != '/' and os.sep in name): - raise DistutilsSetupError( - f"bad library name '{lib[0]}': may not contain directory separators" - ) - - if not isinstance(build_info, dict): - raise DistutilsSetupError( - "second element of each tuple in 'libraries' " - "must be a dictionary (build info)" - ) - - def get_library_names(self): - # Assume the library list is valid -- 'check_library_list()' is - # called from 'finalize_options()', so it should be! - if not self.libraries: - return None - - lib_names = [] - for lib_name, _build_info in self.libraries: - lib_names.append(lib_name) - return lib_names - - def get_source_files(self): - self.check_library_list(self.libraries) - filenames = [] - for lib_name, build_info in self.libraries: - sources = build_info.get('sources') - if sources is None or not isinstance(sources, (list, tuple)): - raise DistutilsSetupError( - f"in 'libraries' option (library '{lib_name}'), " - "'sources' must be present and must be " - "a list of source filenames" - ) - - filenames.extend(sources) - return filenames - - def build_libraries(self, libraries) -> None: - for lib_name, build_info in libraries: - sources = build_info.get('sources') - if sources is None or not isinstance(sources, (list, tuple)): - raise DistutilsSetupError( - f"in 'libraries' option (library '{lib_name}'), " - "'sources' must be present and must be " - "a list of source filenames" - ) - sources = list(sources) - - log.info("building '%s' library", lib_name) - - # First, compile the source code to object files in the library - # directory. (This should probably change to putting object - # files in a temporary build directory.) - macros = build_info.get('macros') - include_dirs = build_info.get('include_dirs') - objects = self.compiler.compile( - sources, - output_dir=self.build_temp, - macros=macros, - include_dirs=include_dirs, - debug=self.debug, - ) - - # Now "link" the object files together into a static library. - # (On Unix at least, this isn't really linking -- it just - # builds an archive. Whatever.) - self.compiler.create_static_lib( - objects, lib_name, output_dir=self.build_clib, debug=self.debug - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_ext.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_ext.py deleted file mode 100644 index ec45b44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_ext.py +++ /dev/null @@ -1,812 +0,0 @@ -"""distutils.command.build_ext - -Implements the Distutils 'build_ext' command, for building extension -modules (currently limited to C extensions, should accommodate C++ -extensions ASAP).""" - -from __future__ import annotations - -import contextlib -import os -import re -import sys -from collections.abc import Callable -from distutils._log import log -from site import USER_BASE -from typing import ClassVar - -from .._modified import newer_group -from ..ccompiler import new_compiler, show_compilers -from ..core import Command -from ..errors import ( - CCompilerError, - CompileError, - DistutilsError, - DistutilsOptionError, - DistutilsPlatformError, - DistutilsSetupError, -) -from ..extension import Extension -from ..sysconfig import customize_compiler, get_config_h_filename, get_python_version -from ..util import get_platform, is_freethreaded, is_mingw - -# An extension name is just a dot-separated list of Python NAMEs (ie. -# the same as a fully-qualified module name). -extension_name_re = re.compile(r'^[a-zA-Z_][a-zA-Z_0-9]*(\.[a-zA-Z_][a-zA-Z_0-9]*)*$') - - -class build_ext(Command): - description = "build C/C++ extensions (compile/link to build directory)" - - # XXX thoughts on how to deal with complex command-line options like - # these, i.e. how to make it so fancy_getopt can suck them off the - # command line and make it look like setup.py defined the appropriate - # lists of tuples of what-have-you. - # - each command needs a callback to process its command-line options - # - Command.__init__() needs access to its share of the whole - # command line (must ultimately come from - # Distribution.parse_command_line()) - # - it then calls the current command class' option-parsing - # callback to deal with weird options like -D, which have to - # parse the option text and churn out some custom data - # structure - # - that data structure (in this case, a list of 2-tuples) - # will then be present in the command object by the time - # we get to finalize_options() (i.e. the constructor - # takes care of both command-line and client options - # in between initialize_options() and finalize_options()) - - sep_by = f" (separated by '{os.pathsep}')" - user_options = [ - ('build-lib=', 'b', "directory for compiled extension modules"), - ('build-temp=', 't', "directory for temporary files (build by-products)"), - ( - 'plat-name=', - 'p', - "platform name to cross-compile for, if supported " - f"[default: {get_platform()}]", - ), - ( - 'inplace', - 'i', - "ignore build-lib and put compiled extensions into the source " - "directory alongside your pure Python modules", - ), - ( - 'include-dirs=', - 'I', - "list of directories to search for header files" + sep_by, - ), - ('define=', 'D', "C preprocessor macros to define"), - ('undef=', 'U', "C preprocessor macros to undefine"), - ('libraries=', 'l', "external C libraries to link with"), - ( - 'library-dirs=', - 'L', - "directories to search for external C libraries" + sep_by, - ), - ('rpath=', 'R', "directories to search for shared C libraries at runtime"), - ('link-objects=', 'O', "extra explicit link objects to include in the link"), - ('debug', 'g', "compile/link with debugging information"), - ('force', 'f', "forcibly build everything (ignore file timestamps)"), - ('compiler=', 'c', "specify the compiler type"), - ('parallel=', 'j', "number of parallel build jobs"), - ('swig-cpp', None, "make SWIG create C++ files (default is C)"), - ('swig-opts=', None, "list of SWIG command line options"), - ('swig=', None, "path to the SWIG executable"), - ('user', None, "add user include, library and rpath"), - ] - - boolean_options: ClassVar[list[str]] = [ - 'inplace', - 'debug', - 'force', - 'swig-cpp', - 'user', - ] - - help_options: ClassVar[list[tuple[str, str | None, str, Callable[[], object]]]] = [ - ('help-compiler', None, "list available compilers", show_compilers), - ] - - def initialize_options(self): - self.extensions = None - self.build_lib = None - self.plat_name = None - self.build_temp = None - self.inplace = False - self.package = None - - self.include_dirs = None - self.define = None - self.undef = None - self.libraries = None - self.library_dirs = None - self.rpath = None - self.link_objects = None - self.debug = None - self.force = None - self.compiler = None - self.swig = None - self.swig_cpp = None - self.swig_opts = None - self.user = None - self.parallel = None - - @staticmethod - def _python_lib_dir(sysconfig): - """ - Resolve Python's library directory for building extensions - that rely on a shared Python library. - - See python/cpython#44264 and python/cpython#48686 - """ - if not sysconfig.get_config_var('Py_ENABLE_SHARED'): - return - - if sysconfig.python_build: - yield '.' - return - - if sys.platform == 'zos': - # On z/OS, a user is not required to install Python to - # a predetermined path, but can use Python portably - installed_dir = sysconfig.get_config_var('base') - lib_dir = sysconfig.get_config_var('platlibdir') - yield os.path.join(installed_dir, lib_dir) - else: - # building third party extensions - yield sysconfig.get_config_var('LIBDIR') - - def finalize_options(self) -> None: # noqa: C901 - from distutils import sysconfig - - self.set_undefined_options( - 'build', - ('build_lib', 'build_lib'), - ('build_temp', 'build_temp'), - ('compiler', 'compiler'), - ('debug', 'debug'), - ('force', 'force'), - ('parallel', 'parallel'), - ('plat_name', 'plat_name'), - ) - - if self.package is None: - self.package = self.distribution.ext_package - - self.extensions = self.distribution.ext_modules - - # Make sure Python's include directories (for Python.h, pyconfig.h, - # etc.) are in the include search path. - py_include = sysconfig.get_python_inc() - plat_py_include = sysconfig.get_python_inc(plat_specific=True) - if self.include_dirs is None: - self.include_dirs = self.distribution.include_dirs or [] - if isinstance(self.include_dirs, str): - self.include_dirs = self.include_dirs.split(os.pathsep) - - # If in a virtualenv, add its include directory - # Issue 16116 - if sys.exec_prefix != sys.base_exec_prefix: - self.include_dirs.append(os.path.join(sys.exec_prefix, 'include')) - - # Put the Python "system" include dir at the end, so that - # any local include dirs take precedence. - self.include_dirs.extend(py_include.split(os.path.pathsep)) - if plat_py_include != py_include: - self.include_dirs.extend(plat_py_include.split(os.path.pathsep)) - - self.ensure_string_list('libraries') - self.ensure_string_list('link_objects') - - # Life is easier if we're not forever checking for None, so - # simplify these options to empty lists if unset - if self.libraries is None: - self.libraries = [] - if self.library_dirs is None: - self.library_dirs = [] - elif isinstance(self.library_dirs, str): - self.library_dirs = self.library_dirs.split(os.pathsep) - - if self.rpath is None: - self.rpath = [] - elif isinstance(self.rpath, str): - self.rpath = self.rpath.split(os.pathsep) - - # for extensions under windows use different directories - # for Release and Debug builds. - # also Python's library directory must be appended to library_dirs - if os.name == 'nt' and not is_mingw(): - # the 'libs' directory is for binary installs - we assume that - # must be the *native* platform. But we don't really support - # cross-compiling via a binary install anyway, so we let it go. - self.library_dirs.append(os.path.join(sys.exec_prefix, 'libs')) - if sys.base_exec_prefix != sys.prefix: # Issue 16116 - self.library_dirs.append(os.path.join(sys.base_exec_prefix, 'libs')) - if self.debug: - self.build_temp = os.path.join(self.build_temp, "Debug") - else: - self.build_temp = os.path.join(self.build_temp, "Release") - - # Append the source distribution include and library directories, - # this allows distutils on windows to work in the source tree - self.include_dirs.append(os.path.dirname(get_config_h_filename())) - self.library_dirs.append(sys.base_exec_prefix) - - # Use the .lib files for the correct architecture - if self.plat_name == 'win32': - suffix = 'win32' - else: - # win-amd64 - suffix = self.plat_name[4:] - new_lib = os.path.join(sys.exec_prefix, 'PCbuild') - if suffix: - new_lib = os.path.join(new_lib, suffix) - self.library_dirs.append(new_lib) - - # For extensions under Cygwin, Python's library directory must be - # appended to library_dirs - if sys.platform[:6] == 'cygwin': - if not sysconfig.python_build: - # building third party extensions - self.library_dirs.append( - os.path.join( - sys.prefix, "lib", "python" + get_python_version(), "config" - ) - ) - else: - # building python standard extensions - self.library_dirs.append('.') - - self.library_dirs.extend(self._python_lib_dir(sysconfig)) - - # The argument parsing will result in self.define being a string, but - # it has to be a list of 2-tuples. All the preprocessor symbols - # specified by the 'define' option will be set to '1'. Multiple - # symbols can be separated with commas. - - if self.define: - defines = self.define.split(',') - self.define = [(symbol, '1') for symbol in defines] - - # The option for macros to undefine is also a string from the - # option parsing, but has to be a list. Multiple symbols can also - # be separated with commas here. - if self.undef: - self.undef = self.undef.split(',') - - if self.swig_opts is None: - self.swig_opts = [] - else: - self.swig_opts = self.swig_opts.split(' ') - - # Finally add the user include and library directories if requested - if self.user: - user_include = os.path.join(USER_BASE, "include") - user_lib = os.path.join(USER_BASE, "lib") - if os.path.isdir(user_include): - self.include_dirs.append(user_include) - if os.path.isdir(user_lib): - self.library_dirs.append(user_lib) - self.rpath.append(user_lib) - - if isinstance(self.parallel, str): - try: - self.parallel = int(self.parallel) - except ValueError: - raise DistutilsOptionError("parallel should be an integer") - - def run(self) -> None: # noqa: C901 - # 'self.extensions', as supplied by setup.py, is a list of - # Extension instances. See the documentation for Extension (in - # distutils.extension) for details. - # - # For backwards compatibility with Distutils 0.8.2 and earlier, we - # also allow the 'extensions' list to be a list of tuples: - # (ext_name, build_info) - # where build_info is a dictionary containing everything that - # Extension instances do except the name, with a few things being - # differently named. We convert these 2-tuples to Extension - # instances as needed. - - if not self.extensions: - return - - # If we were asked to build any C/C++ libraries, make sure that the - # directory where we put them is in the library search path for - # linking extensions. - if self.distribution.has_c_libraries(): - build_clib = self.get_finalized_command('build_clib') - self.libraries.extend(build_clib.get_library_names() or []) - self.library_dirs.append(build_clib.build_clib) - - # Setup the CCompiler object that we'll use to do all the - # compiling and linking - self.compiler = new_compiler( - compiler=self.compiler, - verbose=self.verbose, - dry_run=self.dry_run, - force=self.force, - ) - customize_compiler(self.compiler) - # If we are cross-compiling, init the compiler now (if we are not - # cross-compiling, init would not hurt, but people may rely on - # late initialization of compiler even if they shouldn't...) - if os.name == 'nt' and self.plat_name != get_platform(): - self.compiler.initialize(self.plat_name) - - # The official Windows free threaded Python installer doesn't set - # Py_GIL_DISABLED because its pyconfig.h is shared with the - # default build, so define it here (pypa/setuptools#4662). - if os.name == 'nt' and is_freethreaded(): - self.compiler.define_macro('Py_GIL_DISABLED', '1') - - # And make sure that any compile/link-related options (which might - # come from the command-line or from the setup script) are set in - # that CCompiler object -- that way, they automatically apply to - # all compiling and linking done here. - if self.include_dirs is not None: - self.compiler.set_include_dirs(self.include_dirs) - if self.define is not None: - # 'define' option is a list of (name,value) tuples - for name, value in self.define: - self.compiler.define_macro(name, value) - if self.undef is not None: - for macro in self.undef: - self.compiler.undefine_macro(macro) - if self.libraries is not None: - self.compiler.set_libraries(self.libraries) - if self.library_dirs is not None: - self.compiler.set_library_dirs(self.library_dirs) - if self.rpath is not None: - self.compiler.set_runtime_library_dirs(self.rpath) - if self.link_objects is not None: - self.compiler.set_link_objects(self.link_objects) - - # Now actually compile and link everything. - self.build_extensions() - - def check_extensions_list(self, extensions) -> None: # noqa: C901 - """Ensure that the list of extensions (presumably provided as a - command option 'extensions') is valid, i.e. it is a list of - Extension objects. We also support the old-style list of 2-tuples, - where the tuples are (ext_name, build_info), which are converted to - Extension instances here. - - Raise DistutilsSetupError if the structure is invalid anywhere; - just returns otherwise. - """ - if not isinstance(extensions, list): - raise DistutilsSetupError( - "'ext_modules' option must be a list of Extension instances" - ) - - for i, ext in enumerate(extensions): - if isinstance(ext, Extension): - continue # OK! (assume type-checking done - # by Extension constructor) - - if not isinstance(ext, tuple) or len(ext) != 2: - raise DistutilsSetupError( - "each element of 'ext_modules' option must be an " - "Extension instance or 2-tuple" - ) - - ext_name, build_info = ext - - log.warning( - "old-style (ext_name, build_info) tuple found in " - "ext_modules for extension '%s' " - "-- please convert to Extension instance", - ext_name, - ) - - if not (isinstance(ext_name, str) and extension_name_re.match(ext_name)): - raise DistutilsSetupError( - "first element of each tuple in 'ext_modules' " - "must be the extension name (a string)" - ) - - if not isinstance(build_info, dict): - raise DistutilsSetupError( - "second element of each tuple in 'ext_modules' " - "must be a dictionary (build info)" - ) - - # OK, the (ext_name, build_info) dict is type-safe: convert it - # to an Extension instance. - ext = Extension(ext_name, build_info['sources']) - - # Easy stuff: one-to-one mapping from dict elements to - # instance attributes. - for key in ( - 'include_dirs', - 'library_dirs', - 'libraries', - 'extra_objects', - 'extra_compile_args', - 'extra_link_args', - ): - val = build_info.get(key) - if val is not None: - setattr(ext, key, val) - - # Medium-easy stuff: same syntax/semantics, different names. - ext.runtime_library_dirs = build_info.get('rpath') - if 'def_file' in build_info: - log.warning("'def_file' element of build info dict no longer supported") - - # Non-trivial stuff: 'macros' split into 'define_macros' - # and 'undef_macros'. - macros = build_info.get('macros') - if macros: - ext.define_macros = [] - ext.undef_macros = [] - for macro in macros: - if not (isinstance(macro, tuple) and len(macro) in (1, 2)): - raise DistutilsSetupError( - "'macros' element of build info dict must be 1- or 2-tuple" - ) - if len(macro) == 1: - ext.undef_macros.append(macro[0]) - elif len(macro) == 2: - ext.define_macros.append(macro) - - extensions[i] = ext - - def get_source_files(self): - self.check_extensions_list(self.extensions) - filenames = [] - - # Wouldn't it be neat if we knew the names of header files too... - for ext in self.extensions: - filenames.extend(ext.sources) - return filenames - - def get_outputs(self): - # Sanity check the 'extensions' list -- can't assume this is being - # done in the same run as a 'build_extensions()' call (in fact, we - # can probably assume that it *isn't*!). - self.check_extensions_list(self.extensions) - - # And build the list of output (built) filenames. Note that this - # ignores the 'inplace' flag, and assumes everything goes in the - # "build" tree. - return [self.get_ext_fullpath(ext.name) for ext in self.extensions] - - def build_extensions(self) -> None: - # First, sanity-check the 'extensions' list - self.check_extensions_list(self.extensions) - if self.parallel: - self._build_extensions_parallel() - else: - self._build_extensions_serial() - - def _build_extensions_parallel(self): - workers = self.parallel - if self.parallel is True: - workers = os.cpu_count() # may return None - try: - from concurrent.futures import ThreadPoolExecutor - except ImportError: - workers = None - - if workers is None: - self._build_extensions_serial() - return - - with ThreadPoolExecutor(max_workers=workers) as executor: - futures = [ - executor.submit(self.build_extension, ext) for ext in self.extensions - ] - for ext, fut in zip(self.extensions, futures): - with self._filter_build_errors(ext): - fut.result() - - def _build_extensions_serial(self): - for ext in self.extensions: - with self._filter_build_errors(ext): - self.build_extension(ext) - - @contextlib.contextmanager - def _filter_build_errors(self, ext): - try: - yield - except (CCompilerError, DistutilsError, CompileError) as e: - if not ext.optional: - raise - self.warn(f'building extension "{ext.name}" failed: {e}') - - def build_extension(self, ext) -> None: - sources = ext.sources - if sources is None or not isinstance(sources, (list, tuple)): - raise DistutilsSetupError( - f"in 'ext_modules' option (extension '{ext.name}'), " - "'sources' must be present and must be " - "a list of source filenames" - ) - # sort to make the resulting .so file build reproducible - sources = sorted(sources) - - ext_path = self.get_ext_fullpath(ext.name) - depends = sources + ext.depends - if not (self.force or newer_group(depends, ext_path, 'newer')): - log.debug("skipping '%s' extension (up-to-date)", ext.name) - return - else: - log.info("building '%s' extension", ext.name) - - # First, scan the sources for SWIG definition files (.i), run - # SWIG on 'em to create .c files, and modify the sources list - # accordingly. - sources = self.swig_sources(sources, ext) - - # Next, compile the source code to object files. - - # XXX not honouring 'define_macros' or 'undef_macros' -- the - # CCompiler API needs to change to accommodate this, and I - # want to do one thing at a time! - - # Two possible sources for extra compiler arguments: - # - 'extra_compile_args' in Extension object - # - CFLAGS environment variable (not particularly - # elegant, but people seem to expect it and I - # guess it's useful) - # The environment variable should take precedence, and - # any sensible compiler will give precedence to later - # command line args. Hence we combine them in order: - extra_args = ext.extra_compile_args or [] - - macros = ext.define_macros[:] - for undef in ext.undef_macros: - macros.append((undef,)) - - objects = self.compiler.compile( - sources, - output_dir=self.build_temp, - macros=macros, - include_dirs=ext.include_dirs, - debug=self.debug, - extra_postargs=extra_args, - depends=ext.depends, - ) - - # XXX outdated variable, kept here in case third-part code - # needs it. - self._built_objects = objects[:] - - # Now link the object files together into a "shared object" -- - # of course, first we have to figure out all the other things - # that go into the mix. - if ext.extra_objects: - objects.extend(ext.extra_objects) - extra_args = ext.extra_link_args or [] - - # Detect target language, if not provided - language = ext.language or self.compiler.detect_language(sources) - - self.compiler.link_shared_object( - objects, - ext_path, - libraries=self.get_libraries(ext), - library_dirs=ext.library_dirs, - runtime_library_dirs=ext.runtime_library_dirs, - extra_postargs=extra_args, - export_symbols=self.get_export_symbols(ext), - debug=self.debug, - build_temp=self.build_temp, - target_lang=language, - ) - - def swig_sources(self, sources, extension): - """Walk the list of source files in 'sources', looking for SWIG - interface (.i) files. Run SWIG on all that are found, and - return a modified 'sources' list with SWIG source files replaced - by the generated C (or C++) files. - """ - new_sources = [] - swig_sources = [] - swig_targets = {} - - # XXX this drops generated C/C++ files into the source tree, which - # is fine for developers who want to distribute the generated - # source -- but there should be an option to put SWIG output in - # the temp dir. - - if self.swig_cpp: - log.warning("--swig-cpp is deprecated - use --swig-opts=-c++") - - if ( - self.swig_cpp - or ('-c++' in self.swig_opts) - or ('-c++' in extension.swig_opts) - ): - target_ext = '.cpp' - else: - target_ext = '.c' - - for source in sources: - (base, ext) = os.path.splitext(source) - if ext == ".i": # SWIG interface file - new_sources.append(base + '_wrap' + target_ext) - swig_sources.append(source) - swig_targets[source] = new_sources[-1] - else: - new_sources.append(source) - - if not swig_sources: - return new_sources - - swig = self.swig or self.find_swig() - swig_cmd = [swig, "-python"] - swig_cmd.extend(self.swig_opts) - if self.swig_cpp: - swig_cmd.append("-c++") - - # Do not override commandline arguments - if not self.swig_opts: - swig_cmd.extend(extension.swig_opts) - - for source in swig_sources: - target = swig_targets[source] - log.info("swigging %s to %s", source, target) - self.spawn(swig_cmd + ["-o", target, source]) - - return new_sources - - def find_swig(self): - """Return the name of the SWIG executable. On Unix, this is - just "swig" -- it should be in the PATH. Tries a bit harder on - Windows. - """ - if os.name == "posix": - return "swig" - elif os.name == "nt": - # Look for SWIG in its standard installation directory on - # Windows (or so I presume!). If we find it there, great; - # if not, act like Unix and assume it's in the PATH. - for vers in ("1.3", "1.2", "1.1"): - fn = os.path.join(f"c:\\swig{vers}", "swig.exe") - if os.path.isfile(fn): - return fn - else: - return "swig.exe" - else: - raise DistutilsPlatformError( - f"I don't know how to find (much less run) SWIG on platform '{os.name}'" - ) - - # -- Name generators ----------------------------------------------- - # (extension names, filenames, whatever) - def get_ext_fullpath(self, ext_name: str) -> str: - """Returns the path of the filename for a given extension. - - The file is located in `build_lib` or directly in the package - (inplace option). - """ - fullname = self.get_ext_fullname(ext_name) - modpath = fullname.split('.') - filename = self.get_ext_filename(modpath[-1]) - - if not self.inplace: - # no further work needed - # returning : - # build_dir/package/path/filename - filename = os.path.join(*modpath[:-1] + [filename]) - return os.path.join(self.build_lib, filename) - - # the inplace option requires to find the package directory - # using the build_py command for that - package = '.'.join(modpath[0:-1]) - build_py = self.get_finalized_command('build_py') - package_dir = os.path.abspath(build_py.get_package_dir(package)) - - # returning - # package_dir/filename - return os.path.join(package_dir, filename) - - def get_ext_fullname(self, ext_name: str) -> str: - """Returns the fullname of a given extension name. - - Adds the `package.` prefix""" - if self.package is None: - return ext_name - else: - return self.package + '.' + ext_name - - def get_ext_filename(self, ext_name: str) -> str: - r"""Convert the name of an extension (eg. "foo.bar") into the name - of the file from which it will be loaded (eg. "foo/bar.so", or - "foo\bar.pyd"). - """ - from ..sysconfig import get_config_var - - ext_path = ext_name.split('.') - ext_suffix = get_config_var('EXT_SUFFIX') - return os.path.join(*ext_path) + ext_suffix - - def get_export_symbols(self, ext: Extension) -> list[str]: - """Return the list of symbols that a shared extension has to - export. This either uses 'ext.export_symbols' or, if it's not - provided, "PyInit_" + module_name. Only relevant on Windows, where - the .pyd file (DLL) must export the module "PyInit_" function. - """ - name = self._get_module_name_for_symbol(ext) - try: - # Unicode module name support as defined in PEP-489 - # https://peps.python.org/pep-0489/#export-hook-name - name.encode('ascii') - except UnicodeEncodeError: - suffix = 'U_' + name.encode('punycode').replace(b'-', b'_').decode('ascii') - else: - suffix = "_" + name - - initfunc_name = "PyInit" + suffix - if initfunc_name not in ext.export_symbols: - ext.export_symbols.append(initfunc_name) - return ext.export_symbols - - def _get_module_name_for_symbol(self, ext): - # Package name should be used for `__init__` modules - # https://github.com/python/cpython/issues/80074 - # https://github.com/pypa/setuptools/issues/4826 - parts = ext.name.split(".") - if parts[-1] == "__init__" and len(parts) >= 2: - return parts[-2] - return parts[-1] - - def get_libraries(self, ext: Extension) -> list[str]: # noqa: C901 - """Return the list of libraries to link against when building a - shared extension. On most platforms, this is just 'ext.libraries'; - on Windows, we add the Python library (eg. python20.dll). - """ - # The python library is always needed on Windows. For MSVC, this - # is redundant, since the library is mentioned in a pragma in - # pyconfig.h that MSVC groks. The other Windows compilers all seem - # to need it mentioned explicitly, though, so that's what we do. - # Append '_d' to the python import library on debug builds. - if sys.platform == "win32" and not is_mingw(): - from .._msvccompiler import MSVCCompiler - - if not isinstance(self.compiler, MSVCCompiler): - template = "python%d%d" - if self.debug: - template = template + '_d' - pythonlib = template % ( - sys.hexversion >> 24, - (sys.hexversion >> 16) & 0xFF, - ) - # don't extend ext.libraries, it may be shared with other - # extensions, it is a reference to the original list - return ext.libraries + [pythonlib] - else: - # On Android only the main executable and LD_PRELOADs are considered - # to be RTLD_GLOBAL, all the dependencies of the main executable - # remain RTLD_LOCAL and so the shared libraries must be linked with - # libpython when python is built with a shared python library (issue - # bpo-21536). - # On Cygwin (and if required, other POSIX-like platforms based on - # Windows like MinGW) it is simply necessary that all symbols in - # shared libraries are resolved at link time. - from ..sysconfig import get_config_var - - link_libpython = False - if get_config_var('Py_ENABLE_SHARED'): - # A native build on an Android device or on Cygwin - if hasattr(sys, 'getandroidapilevel'): - link_libpython = True - elif sys.platform == 'cygwin' or is_mingw(): - link_libpython = True - elif '_PYTHON_HOST_PLATFORM' in os.environ: - # We are cross-compiling for one of the relevant platforms - if get_config_var('ANDROID_API_LEVEL') != 0: - link_libpython = True - elif get_config_var('MACHDEP') == 'cygwin': - link_libpython = True - - if link_libpython: - ldversion = get_config_var('LDVERSION') - return ext.libraries + ['python' + ldversion] - - return ext.libraries diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_py.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_py.py deleted file mode 100644 index a20b076..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_py.py +++ /dev/null @@ -1,407 +0,0 @@ -"""distutils.command.build_py - -Implements the Distutils 'build_py' command.""" - -import glob -import importlib.util -import os -import sys -from distutils._log import log -from typing import ClassVar - -from ..core import Command -from ..errors import DistutilsFileError, DistutilsOptionError -from ..util import convert_path - - -class build_py(Command): - description = "\"build\" pure Python modules (copy to build directory)" - - user_options = [ - ('build-lib=', 'd', "directory to \"build\" (copy) to"), - ('compile', 'c', "compile .py to .pyc"), - ('no-compile', None, "don't compile .py files [default]"), - ( - 'optimize=', - 'O', - "also compile with optimization: -O1 for \"python -O\", " - "-O2 for \"python -OO\", and -O0 to disable [default: -O0]", - ), - ('force', 'f', "forcibly build everything (ignore file timestamps)"), - ] - - boolean_options: ClassVar[list[str]] = ['compile', 'force'] - negative_opt: ClassVar[dict[str, str]] = {'no-compile': 'compile'} - - def initialize_options(self): - self.build_lib = None - self.py_modules = None - self.package = None - self.package_data = None - self.package_dir = None - self.compile = False - self.optimize = 0 - self.force = None - - def finalize_options(self) -> None: - self.set_undefined_options( - 'build', ('build_lib', 'build_lib'), ('force', 'force') - ) - - # Get the distribution options that are aliases for build_py - # options -- list of packages and list of modules. - self.packages = self.distribution.packages - self.py_modules = self.distribution.py_modules - self.package_data = self.distribution.package_data - self.package_dir = {} - if self.distribution.package_dir: - for name, path in self.distribution.package_dir.items(): - self.package_dir[name] = convert_path(path) - self.data_files = self.get_data_files() - - # Ick, copied straight from install_lib.py (fancy_getopt needs a - # type system! Hell, *everything* needs a type system!!!) - if not isinstance(self.optimize, int): - try: - self.optimize = int(self.optimize) - assert 0 <= self.optimize <= 2 - except (ValueError, AssertionError): - raise DistutilsOptionError("optimize must be 0, 1, or 2") - - def run(self) -> None: - # XXX copy_file by default preserves atime and mtime. IMHO this is - # the right thing to do, but perhaps it should be an option -- in - # particular, a site administrator might want installed files to - # reflect the time of installation rather than the last - # modification time before the installed release. - - # XXX copy_file by default preserves mode, which appears to be the - # wrong thing to do: if a file is read-only in the working - # directory, we want it to be installed read/write so that the next - # installation of the same module distribution can overwrite it - # without problems. (This might be a Unix-specific issue.) Thus - # we turn off 'preserve_mode' when copying to the build directory, - # since the build directory is supposed to be exactly what the - # installation will look like (ie. we preserve mode when - # installing). - - # Two options control which modules will be installed: 'packages' - # and 'py_modules'. The former lets us work with whole packages, not - # specifying individual modules at all; the latter is for - # specifying modules one-at-a-time. - - if self.py_modules: - self.build_modules() - if self.packages: - self.build_packages() - self.build_package_data() - - self.byte_compile(self.get_outputs(include_bytecode=False)) - - def get_data_files(self): - """Generate list of '(package,src_dir,build_dir,filenames)' tuples""" - data = [] - if not self.packages: - return data - for package in self.packages: - # Locate package source directory - src_dir = self.get_package_dir(package) - - # Compute package build directory - build_dir = os.path.join(*([self.build_lib] + package.split('.'))) - - # Length of path to strip from found files - plen = 0 - if src_dir: - plen = len(src_dir) + 1 - - # Strip directory from globbed filenames - filenames = [file[plen:] for file in self.find_data_files(package, src_dir)] - data.append((package, src_dir, build_dir, filenames)) - return data - - def find_data_files(self, package, src_dir): - """Return filenames for package's data files in 'src_dir'""" - globs = self.package_data.get('', []) + self.package_data.get(package, []) - files = [] - for pattern in globs: - # Each pattern has to be converted to a platform-specific path - filelist = glob.glob( - os.path.join(glob.escape(src_dir), convert_path(pattern)) - ) - # Files that match more than one pattern are only added once - files.extend([ - fn for fn in filelist if fn not in files and os.path.isfile(fn) - ]) - return files - - def build_package_data(self) -> None: - """Copy data files into build directory""" - for _package, src_dir, build_dir, filenames in self.data_files: - for filename in filenames: - target = os.path.join(build_dir, filename) - self.mkpath(os.path.dirname(target)) - self.copy_file( - os.path.join(src_dir, filename), target, preserve_mode=False - ) - - def get_package_dir(self, package): - """Return the directory, relative to the top of the source - distribution, where package 'package' should be found - (at least according to the 'package_dir' option, if any).""" - path = package.split('.') - - if not self.package_dir: - if path: - return os.path.join(*path) - else: - return '' - else: - tail = [] - while path: - try: - pdir = self.package_dir['.'.join(path)] - except KeyError: - tail.insert(0, path[-1]) - del path[-1] - else: - tail.insert(0, pdir) - return os.path.join(*tail) - else: - # Oops, got all the way through 'path' without finding a - # match in package_dir. If package_dir defines a directory - # for the root (nameless) package, then fallback on it; - # otherwise, we might as well have not consulted - # package_dir at all, as we just use the directory implied - # by 'tail' (which should be the same as the original value - # of 'path' at this point). - pdir = self.package_dir.get('') - if pdir is not None: - tail.insert(0, pdir) - - if tail: - return os.path.join(*tail) - else: - return '' - - def check_package(self, package, package_dir): - # Empty dir name means current directory, which we can probably - # assume exists. Also, os.path.exists and isdir don't know about - # my "empty string means current dir" convention, so we have to - # circumvent them. - if package_dir != "": - if not os.path.exists(package_dir): - raise DistutilsFileError( - f"package directory '{package_dir}' does not exist" - ) - if not os.path.isdir(package_dir): - raise DistutilsFileError( - f"supposed package directory '{package_dir}' exists, " - "but is not a directory" - ) - - # Directories without __init__.py are namespace packages (PEP 420). - if package: - init_py = os.path.join(package_dir, "__init__.py") - if os.path.isfile(init_py): - return init_py - - # Either not in a package at all (__init__.py not expected), or - # __init__.py doesn't exist -- so don't return the filename. - return None - - def check_module(self, module, module_file): - if not os.path.isfile(module_file): - log.warning("file %s (for module %s) not found", module_file, module) - return False - else: - return True - - def find_package_modules(self, package, package_dir): - self.check_package(package, package_dir) - module_files = glob.glob(os.path.join(glob.escape(package_dir), "*.py")) - modules = [] - setup_script = os.path.abspath(self.distribution.script_name) - - for f in module_files: - abs_f = os.path.abspath(f) - if abs_f != setup_script: - module = os.path.splitext(os.path.basename(f))[0] - modules.append((package, module, f)) - else: - self.debug_print(f"excluding {setup_script}") - return modules - - def find_modules(self): - """Finds individually-specified Python modules, ie. those listed by - module name in 'self.py_modules'. Returns a list of tuples (package, - module_base, filename): 'package' is a tuple of the path through - package-space to the module; 'module_base' is the bare (no - packages, no dots) module name, and 'filename' is the path to the - ".py" file (relative to the distribution root) that implements the - module. - """ - # Map package names to tuples of useful info about the package: - # (package_dir, checked) - # package_dir - the directory where we'll find source files for - # this package - # checked - true if we have checked that the package directory - # is valid (exists, contains __init__.py, ... ?) - packages = {} - - # List of (package, module, filename) tuples to return - modules = [] - - # We treat modules-in-packages almost the same as toplevel modules, - # just the "package" for a toplevel is empty (either an empty - # string or empty list, depending on context). Differences: - # - don't check for __init__.py in directory for empty package - for module in self.py_modules: - path = module.split('.') - package = '.'.join(path[0:-1]) - module_base = path[-1] - - try: - (package_dir, checked) = packages[package] - except KeyError: - package_dir = self.get_package_dir(package) - checked = False - - if not checked: - init_py = self.check_package(package, package_dir) - packages[package] = (package_dir, 1) - if init_py: - modules.append((package, "__init__", init_py)) - - # XXX perhaps we should also check for just .pyc files - # (so greedy closed-source bastards can distribute Python - # modules too) - module_file = os.path.join(package_dir, module_base + ".py") - if not self.check_module(module, module_file): - continue - - modules.append((package, module_base, module_file)) - - return modules - - def find_all_modules(self): - """Compute the list of all modules that will be built, whether - they are specified one-module-at-a-time ('self.py_modules') or - by whole packages ('self.packages'). Return a list of tuples - (package, module, module_file), just like 'find_modules()' and - 'find_package_modules()' do.""" - modules = [] - if self.py_modules: - modules.extend(self.find_modules()) - if self.packages: - for package in self.packages: - package_dir = self.get_package_dir(package) - m = self.find_package_modules(package, package_dir) - modules.extend(m) - return modules - - def get_source_files(self): - return [module[-1] for module in self.find_all_modules()] - - def get_module_outfile(self, build_dir, package, module): - outfile_path = [build_dir] + list(package) + [module + ".py"] - return os.path.join(*outfile_path) - - def get_outputs(self, include_bytecode: bool = True) -> list[str]: - modules = self.find_all_modules() - outputs = [] - for package, module, _module_file in modules: - package = package.split('.') - filename = self.get_module_outfile(self.build_lib, package, module) - outputs.append(filename) - if include_bytecode: - if self.compile: - outputs.append( - importlib.util.cache_from_source(filename, optimization='') - ) - if self.optimize > 0: - outputs.append( - importlib.util.cache_from_source( - filename, optimization=self.optimize - ) - ) - - outputs += [ - os.path.join(build_dir, filename) - for package, src_dir, build_dir, filenames in self.data_files - for filename in filenames - ] - - return outputs - - def build_module(self, module, module_file, package): - if isinstance(package, str): - package = package.split('.') - elif not isinstance(package, (list, tuple)): - raise TypeError( - "'package' must be a string (dot-separated), list, or tuple" - ) - - # Now put the module source file into the "build" area -- this is - # easy, we just copy it somewhere under self.build_lib (the build - # directory for Python source). - outfile = self.get_module_outfile(self.build_lib, package, module) - dir = os.path.dirname(outfile) - self.mkpath(dir) - return self.copy_file(module_file, outfile, preserve_mode=False) - - def build_modules(self) -> None: - modules = self.find_modules() - for package, module, module_file in modules: - # Now "build" the module -- ie. copy the source file to - # self.build_lib (the build directory for Python source). - # (Actually, it gets copied to the directory for this package - # under self.build_lib.) - self.build_module(module, module_file, package) - - def build_packages(self) -> None: - for package in self.packages: - # Get list of (package, module, module_file) tuples based on - # scanning the package directory. 'package' is only included - # in the tuple so that 'find_modules()' and - # 'find_package_tuples()' have a consistent interface; it's - # ignored here (apart from a sanity check). Also, 'module' is - # the *unqualified* module name (ie. no dots, no package -- we - # already know its package!), and 'module_file' is the path to - # the .py file, relative to the current directory - # (ie. including 'package_dir'). - package_dir = self.get_package_dir(package) - modules = self.find_package_modules(package, package_dir) - - # Now loop over the modules we found, "building" each one (just - # copy it to self.build_lib). - for package_, module, module_file in modules: - assert package == package_ - self.build_module(module, module_file, package) - - def byte_compile(self, files) -> None: - if sys.dont_write_bytecode: - self.warn('byte-compiling is disabled, skipping.') - return - - from ..util import byte_compile - - prefix = self.build_lib - if prefix[-1] != os.sep: - prefix = prefix + os.sep - - # XXX this code is essentially the same as the 'byte_compile() - # method of the "install_lib" command, except for the determination - # of the 'prefix' string. Hmmm. - if self.compile: - byte_compile( - files, optimize=0, force=self.force, prefix=prefix, dry_run=self.dry_run - ) - if self.optimize > 0: - byte_compile( - files, - optimize=self.optimize, - force=self.force, - prefix=prefix, - dry_run=self.dry_run, - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_scripts.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_scripts.py deleted file mode 100644 index 127c51d..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/build_scripts.py +++ /dev/null @@ -1,160 +0,0 @@ -"""distutils.command.build_scripts - -Implements the Distutils 'build_scripts' command.""" - -import os -import re -import tokenize -from distutils._log import log -from stat import ST_MODE -from typing import ClassVar - -from .._modified import newer -from ..core import Command -from ..util import convert_path - -shebang_pattern = re.compile('^#!.*python[0-9.]*([ \t].*)?$') -""" -Pattern matching a Python interpreter indicated in first line of a script. -""" - -# for Setuptools compatibility -first_line_re = shebang_pattern - - -class build_scripts(Command): - description = "\"build\" scripts (copy and fixup #! line)" - - user_options: ClassVar[list[tuple[str, str, str]]] = [ - ('build-dir=', 'd', "directory to \"build\" (copy) to"), - ('force', 'f', "forcibly build everything (ignore file timestamps"), - ('executable=', 'e', "specify final destination interpreter path"), - ] - - boolean_options: ClassVar[list[str]] = ['force'] - - def initialize_options(self): - self.build_dir = None - self.scripts = None - self.force = None - self.executable = None - - def finalize_options(self): - self.set_undefined_options( - 'build', - ('build_scripts', 'build_dir'), - ('force', 'force'), - ('executable', 'executable'), - ) - self.scripts = self.distribution.scripts - - def get_source_files(self): - return self.scripts - - def run(self): - if not self.scripts: - return - self.copy_scripts() - - def copy_scripts(self): - """ - Copy each script listed in ``self.scripts``. - - If a script is marked as a Python script (first line matches - 'shebang_pattern', i.e. starts with ``#!`` and contains - "python"), then adjust in the copy the first line to refer to - the current Python interpreter. - """ - self.mkpath(self.build_dir) - outfiles = [] - updated_files = [] - for script in self.scripts: - self._copy_script(script, outfiles, updated_files) - - self._change_modes(outfiles) - - return outfiles, updated_files - - def _copy_script(self, script, outfiles, updated_files): - shebang_match = None - script = convert_path(script) - outfile = os.path.join(self.build_dir, os.path.basename(script)) - outfiles.append(outfile) - - if not self.force and not newer(script, outfile): - log.debug("not copying %s (up-to-date)", script) - return - - # Always open the file, but ignore failures in dry-run mode - # in order to attempt to copy directly. - try: - f = tokenize.open(script) - except OSError: - if not self.dry_run: - raise - f = None - else: - first_line = f.readline() - if not first_line: - self.warn(f"{script} is an empty file (skipping)") - return - - shebang_match = shebang_pattern.match(first_line) - - updated_files.append(outfile) - if shebang_match: - log.info("copying and adjusting %s -> %s", script, self.build_dir) - if not self.dry_run: - post_interp = shebang_match.group(1) or '' - shebang = f"#!python{post_interp}\n" - self._validate_shebang(shebang, f.encoding) - with open(outfile, "w", encoding=f.encoding) as outf: - outf.write(shebang) - outf.writelines(f.readlines()) - if f: - f.close() - else: - if f: - f.close() - self.copy_file(script, outfile) - - def _change_modes(self, outfiles): - if os.name != 'posix': - return - - for file in outfiles: - self._change_mode(file) - - def _change_mode(self, file): - if self.dry_run: - log.info("changing mode of %s", file) - return - - oldmode = os.stat(file)[ST_MODE] & 0o7777 - newmode = (oldmode | 0o555) & 0o7777 - if newmode != oldmode: - log.info("changing mode of %s from %o to %o", file, oldmode, newmode) - os.chmod(file, newmode) - - @staticmethod - def _validate_shebang(shebang, encoding): - # Python parser starts to read a script using UTF-8 until - # it gets a #coding:xxx cookie. The shebang has to be the - # first line of a file, the #coding:xxx cookie cannot be - # written before. So the shebang has to be encodable to - # UTF-8. - try: - shebang.encode('utf-8') - except UnicodeEncodeError: - raise ValueError(f"The shebang ({shebang!r}) is not encodable to utf-8") - - # If the script is encoded to a custom encoding (use a - # #coding:xxx cookie), the shebang has to be encodable to - # the script encoding too. - try: - shebang.encode(encoding) - except UnicodeEncodeError: - raise ValueError( - f"The shebang ({shebang!r}) is not encodable " - f"to the script encoding ({encoding})" - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/check.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/check.py deleted file mode 100644 index 58a823d..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/check.py +++ /dev/null @@ -1,152 +0,0 @@ -"""distutils.command.check - -Implements the Distutils 'check' command. -""" - -import contextlib -from typing import ClassVar - -from ..core import Command -from ..errors import DistutilsSetupError - -with contextlib.suppress(ImportError): - import docutils.frontend - import docutils.nodes - import docutils.parsers.rst - import docutils.utils - - class SilentReporter(docutils.utils.Reporter): - def __init__( - self, - source, - report_level, - halt_level, - stream=None, - debug=False, - encoding='ascii', - error_handler='replace', - ): - self.messages = [] - super().__init__( - source, report_level, halt_level, stream, debug, encoding, error_handler - ) - - def system_message(self, level, message, *children, **kwargs): - self.messages.append((level, message, children, kwargs)) - return docutils.nodes.system_message( - message, *children, level=level, type=self.levels[level], **kwargs - ) - - -class check(Command): - """This command checks the meta-data of the package.""" - - description = "perform some checks on the package" - user_options: ClassVar[list[tuple[str, str, str]]] = [ - ('metadata', 'm', 'Verify meta-data'), - ( - 'restructuredtext', - 'r', - 'Checks if long string meta-data syntax are reStructuredText-compliant', - ), - ('strict', 's', 'Will exit with an error if a check fails'), - ] - - boolean_options: ClassVar[list[str]] = ['metadata', 'restructuredtext', 'strict'] - - def initialize_options(self): - """Sets default values for options.""" - self.restructuredtext = False - self.metadata = 1 - self.strict = False - self._warnings = 0 - - def finalize_options(self): - pass - - def warn(self, msg): - """Counts the number of warnings that occurs.""" - self._warnings += 1 - return Command.warn(self, msg) - - def run(self): - """Runs the command.""" - # perform the various tests - if self.metadata: - self.check_metadata() - if self.restructuredtext: - if 'docutils' in globals(): - try: - self.check_restructuredtext() - except TypeError as exc: - raise DistutilsSetupError(str(exc)) - elif self.strict: - raise DistutilsSetupError('The docutils package is needed.') - - # let's raise an error in strict mode, if we have at least - # one warning - if self.strict and self._warnings > 0: - raise DistutilsSetupError('Please correct your package.') - - def check_metadata(self): - """Ensures that all required elements of meta-data are supplied. - - Required fields: - name, version - - Warns if any are missing. - """ - metadata = self.distribution.metadata - - missing = [ - attr for attr in ('name', 'version') if not getattr(metadata, attr, None) - ] - - if missing: - self.warn("missing required meta-data: {}".format(', '.join(missing))) - - def check_restructuredtext(self): - """Checks if the long string fields are reST-compliant.""" - data = self.distribution.get_long_description() - for warning in self._check_rst_data(data): - line = warning[-1].get('line') - if line is None: - warning = warning[1] - else: - warning = f'{warning[1]} (line {line})' - self.warn(warning) - - def _check_rst_data(self, data): - """Returns warnings when the provided data doesn't compile.""" - # the include and csv_table directives need this to be a path - source_path = self.distribution.script_name or 'setup.py' - parser = docutils.parsers.rst.Parser() - settings = docutils.frontend.OptionParser( - components=(docutils.parsers.rst.Parser,) - ).get_default_values() - settings.tab_width = 4 - settings.pep_references = None - settings.rfc_references = None - reporter = SilentReporter( - source_path, - settings.report_level, - settings.halt_level, - stream=settings.warning_stream, - debug=settings.debug, - encoding=settings.error_encoding, - error_handler=settings.error_encoding_error_handler, - ) - - document = docutils.nodes.document(settings, reporter, source=source_path) - document.note_source(source_path, -1) - try: - parser.parse(data, document) - except (AttributeError, TypeError) as e: - reporter.messages.append(( - -1, - f'Could not finish the parsing: {e}.', - '', - {}, - )) - - return reporter.messages diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/clean.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/clean.py deleted file mode 100644 index 23427ab..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/clean.py +++ /dev/null @@ -1,77 +0,0 @@ -"""distutils.command.clean - -Implements the Distutils 'clean' command.""" - -# contributed by Bastian Kleineidam , added 2000-03-18 - -import os -from distutils._log import log -from typing import ClassVar - -from ..core import Command -from ..dir_util import remove_tree - - -class clean(Command): - description = "clean up temporary files from 'build' command" - user_options = [ - ('build-base=', 'b', "base build directory [default: 'build.build-base']"), - ( - 'build-lib=', - None, - "build directory for all modules [default: 'build.build-lib']", - ), - ('build-temp=', 't', "temporary build directory [default: 'build.build-temp']"), - ( - 'build-scripts=', - None, - "build directory for scripts [default: 'build.build-scripts']", - ), - ('bdist-base=', None, "temporary directory for built distributions"), - ('all', 'a', "remove all build output, not just temporary by-products"), - ] - - boolean_options: ClassVar[list[str]] = ['all'] - - def initialize_options(self): - self.build_base = None - self.build_lib = None - self.build_temp = None - self.build_scripts = None - self.bdist_base = None - self.all = None - - def finalize_options(self): - self.set_undefined_options( - 'build', - ('build_base', 'build_base'), - ('build_lib', 'build_lib'), - ('build_scripts', 'build_scripts'), - ('build_temp', 'build_temp'), - ) - self.set_undefined_options('bdist', ('bdist_base', 'bdist_base')) - - def run(self): - # remove the build/temp. directory (unless it's already - # gone) - if os.path.exists(self.build_temp): - remove_tree(self.build_temp, dry_run=self.dry_run) - else: - log.debug("'%s' does not exist -- can't clean it", self.build_temp) - - if self.all: - # remove build directories - for directory in (self.build_lib, self.bdist_base, self.build_scripts): - if os.path.exists(directory): - remove_tree(directory, dry_run=self.dry_run) - else: - log.warning("'%s' does not exist -- can't clean it", directory) - - # just for the heck of it, try to remove the base build directory: - # we might have emptied it right now, but if not we don't care - if not self.dry_run: - try: - os.rmdir(self.build_base) - log.info("removing '%s'", self.build_base) - except OSError: - pass diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/config.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/config.py deleted file mode 100644 index 44df823..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/config.py +++ /dev/null @@ -1,360 +0,0 @@ -"""distutils.command.config - -Implements the Distutils 'config' command, a (mostly) empty command class -that exists mainly to be sub-classed by specific module distributions and -applications. The idea is that while every "config" command is different, -at least they're all named the same, and users always see "config" in the -list of standard commands. Also, this is a good place to put common -configure-like tasks: "try to compile this C code", or "figure out where -this header file lives". -""" - -from __future__ import annotations - -import os -import pathlib -import re -from collections.abc import Sequence -from distutils._log import log - -from ..ccompiler import CCompiler, CompileError, LinkError, new_compiler -from ..core import Command -from ..errors import DistutilsExecError -from ..sysconfig import customize_compiler - -LANG_EXT = {"c": ".c", "c++": ".cxx"} - - -class config(Command): - description = "prepare to build" - - user_options = [ - ('compiler=', None, "specify the compiler type"), - ('cc=', None, "specify the compiler executable"), - ('include-dirs=', 'I', "list of directories to search for header files"), - ('define=', 'D', "C preprocessor macros to define"), - ('undef=', 'U', "C preprocessor macros to undefine"), - ('libraries=', 'l', "external C libraries to link with"), - ('library-dirs=', 'L', "directories to search for external C libraries"), - ('noisy', None, "show every action (compile, link, run, ...) taken"), - ( - 'dump-source', - None, - "dump generated source files before attempting to compile them", - ), - ] - - # The three standard command methods: since the "config" command - # does nothing by default, these are empty. - - def initialize_options(self): - self.compiler = None - self.cc = None - self.include_dirs = None - self.libraries = None - self.library_dirs = None - - # maximal output for now - self.noisy = 1 - self.dump_source = 1 - - # list of temporary files generated along-the-way that we have - # to clean at some point - self.temp_files = [] - - def finalize_options(self): - if self.include_dirs is None: - self.include_dirs = self.distribution.include_dirs or [] - elif isinstance(self.include_dirs, str): - self.include_dirs = self.include_dirs.split(os.pathsep) - - if self.libraries is None: - self.libraries = [] - elif isinstance(self.libraries, str): - self.libraries = [self.libraries] - - if self.library_dirs is None: - self.library_dirs = [] - elif isinstance(self.library_dirs, str): - self.library_dirs = self.library_dirs.split(os.pathsep) - - def run(self): - pass - - # Utility methods for actual "config" commands. The interfaces are - # loosely based on Autoconf macros of similar names. Sub-classes - # may use these freely. - - def _check_compiler(self): - """Check that 'self.compiler' really is a CCompiler object; - if not, make it one. - """ - # We do this late, and only on-demand, because this is an expensive - # import. - if not isinstance(self.compiler, CCompiler): - self.compiler = new_compiler( - compiler=self.compiler, dry_run=self.dry_run, force=True - ) - customize_compiler(self.compiler) - if self.include_dirs: - self.compiler.set_include_dirs(self.include_dirs) - if self.libraries: - self.compiler.set_libraries(self.libraries) - if self.library_dirs: - self.compiler.set_library_dirs(self.library_dirs) - - def _gen_temp_sourcefile(self, body, headers, lang): - filename = "_configtest" + LANG_EXT[lang] - with open(filename, "w", encoding='utf-8') as file: - if headers: - for header in headers: - file.write(f"#include <{header}>\n") - file.write("\n") - file.write(body) - if body[-1] != "\n": - file.write("\n") - return filename - - def _preprocess(self, body, headers, include_dirs, lang): - src = self._gen_temp_sourcefile(body, headers, lang) - out = "_configtest.i" - self.temp_files.extend([src, out]) - self.compiler.preprocess(src, out, include_dirs=include_dirs) - return (src, out) - - def _compile(self, body, headers, include_dirs, lang): - src = self._gen_temp_sourcefile(body, headers, lang) - if self.dump_source: - dump_file(src, f"compiling '{src}':") - (obj,) = self.compiler.object_filenames([src]) - self.temp_files.extend([src, obj]) - self.compiler.compile([src], include_dirs=include_dirs) - return (src, obj) - - def _link(self, body, headers, include_dirs, libraries, library_dirs, lang): - (src, obj) = self._compile(body, headers, include_dirs, lang) - prog = os.path.splitext(os.path.basename(src))[0] - self.compiler.link_executable( - [obj], - prog, - libraries=libraries, - library_dirs=library_dirs, - target_lang=lang, - ) - - if self.compiler.exe_extension is not None: - prog = prog + self.compiler.exe_extension - self.temp_files.append(prog) - - return (src, obj, prog) - - def _clean(self, *filenames): - if not filenames: - filenames = self.temp_files - self.temp_files = [] - log.info("removing: %s", ' '.join(filenames)) - for filename in filenames: - try: - os.remove(filename) - except OSError: - pass - - # XXX these ignore the dry-run flag: what to do, what to do? even if - # you want a dry-run build, you still need some sort of configuration - # info. My inclination is to make it up to the real config command to - # consult 'dry_run', and assume a default (minimal) configuration if - # true. The problem with trying to do it here is that you'd have to - # return either true or false from all the 'try' methods, neither of - # which is correct. - - # XXX need access to the header search path and maybe default macros. - - def try_cpp(self, body=None, headers=None, include_dirs=None, lang="c"): - """Construct a source file from 'body' (a string containing lines - of C/C++ code) and 'headers' (a list of header files to include) - and run it through the preprocessor. Return true if the - preprocessor succeeded, false if there were any errors. - ('body' probably isn't of much use, but what the heck.) - """ - self._check_compiler() - ok = True - try: - self._preprocess(body, headers, include_dirs, lang) - except CompileError: - ok = False - - self._clean() - return ok - - def search_cpp(self, pattern, body=None, headers=None, include_dirs=None, lang="c"): - """Construct a source file (just like 'try_cpp()'), run it through - the preprocessor, and return true if any line of the output matches - 'pattern'. 'pattern' should either be a compiled regex object or a - string containing a regex. If both 'body' and 'headers' are None, - preprocesses an empty file -- which can be useful to determine the - symbols the preprocessor and compiler set by default. - """ - self._check_compiler() - src, out = self._preprocess(body, headers, include_dirs, lang) - - if isinstance(pattern, str): - pattern = re.compile(pattern) - - with open(out, encoding='utf-8') as file: - match = any(pattern.search(line) for line in file) - - self._clean() - return match - - def try_compile(self, body, headers=None, include_dirs=None, lang="c"): - """Try to compile a source file built from 'body' and 'headers'. - Return true on success, false otherwise. - """ - self._check_compiler() - try: - self._compile(body, headers, include_dirs, lang) - ok = True - except CompileError: - ok = False - - log.info(ok and "success!" or "failure.") - self._clean() - return ok - - def try_link( - self, - body, - headers=None, - include_dirs=None, - libraries=None, - library_dirs=None, - lang="c", - ): - """Try to compile and link a source file, built from 'body' and - 'headers', to executable form. Return true on success, false - otherwise. - """ - self._check_compiler() - try: - self._link(body, headers, include_dirs, libraries, library_dirs, lang) - ok = True - except (CompileError, LinkError): - ok = False - - log.info(ok and "success!" or "failure.") - self._clean() - return ok - - def try_run( - self, - body, - headers=None, - include_dirs=None, - libraries=None, - library_dirs=None, - lang="c", - ): - """Try to compile, link to an executable, and run a program - built from 'body' and 'headers'. Return true on success, false - otherwise. - """ - self._check_compiler() - try: - src, obj, exe = self._link( - body, headers, include_dirs, libraries, library_dirs, lang - ) - self.spawn([exe]) - ok = True - except (CompileError, LinkError, DistutilsExecError): - ok = False - - log.info(ok and "success!" or "failure.") - self._clean() - return ok - - # -- High-level methods -------------------------------------------- - # (these are the ones that are actually likely to be useful - # when implementing a real-world config command!) - - def check_func( - self, - func, - headers=None, - include_dirs=None, - libraries=None, - library_dirs=None, - decl=False, - call=False, - ): - """Determine if function 'func' is available by constructing a - source file that refers to 'func', and compiles and links it. - If everything succeeds, returns true; otherwise returns false. - - The constructed source file starts out by including the header - files listed in 'headers'. If 'decl' is true, it then declares - 'func' (as "int func()"); you probably shouldn't supply 'headers' - and set 'decl' true in the same call, or you might get errors about - a conflicting declarations for 'func'. Finally, the constructed - 'main()' function either references 'func' or (if 'call' is true) - calls it. 'libraries' and 'library_dirs' are used when - linking. - """ - self._check_compiler() - body = [] - if decl: - body.append(f"int {func} ();") - body.append("int main () {") - if call: - body.append(f" {func}();") - else: - body.append(f" {func};") - body.append("}") - body = "\n".join(body) + "\n" - - return self.try_link(body, headers, include_dirs, libraries, library_dirs) - - def check_lib( - self, - library, - library_dirs=None, - headers=None, - include_dirs=None, - other_libraries: Sequence[str] = [], - ): - """Determine if 'library' is available to be linked against, - without actually checking that any particular symbols are provided - by it. 'headers' will be used in constructing the source file to - be compiled, but the only effect of this is to check if all the - header files listed are available. Any libraries listed in - 'other_libraries' will be included in the link, in case 'library' - has symbols that depend on other libraries. - """ - self._check_compiler() - return self.try_link( - "int main (void) { }", - headers, - include_dirs, - [library] + list(other_libraries), - library_dirs, - ) - - def check_header(self, header, include_dirs=None, library_dirs=None, lang="c"): - """Determine if the system header file named by 'header_file' - exists and can be found by the preprocessor; return true if so, - false otherwise. - """ - return self.try_cpp( - body="/* No body */", headers=[header], include_dirs=include_dirs - ) - - -def dump_file(filename, head=None): - """Dumps a file content into log.info. - - If head is not None, will be dumped before the file content. - """ - if head is None: - log.info('%s', filename) - else: - log.info(head) - log.info(pathlib.Path(filename).read_text(encoding='utf-8')) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install.py deleted file mode 100644 index dc17e56..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install.py +++ /dev/null @@ -1,805 +0,0 @@ -"""distutils.command.install - -Implements the Distutils 'install' command.""" - -from __future__ import annotations - -import collections -import contextlib -import itertools -import os -import sys -import sysconfig -from distutils._log import log -from site import USER_BASE, USER_SITE -from typing import ClassVar - -from ..core import Command -from ..debug import DEBUG -from ..errors import DistutilsOptionError, DistutilsPlatformError -from ..file_util import write_file -from ..sysconfig import get_config_vars -from ..util import change_root, convert_path, get_platform, subst_vars -from . import _framework_compat as fw - -HAS_USER_SITE = True - -WINDOWS_SCHEME = { - 'purelib': '{base}/Lib/site-packages', - 'platlib': '{base}/Lib/site-packages', - 'headers': '{base}/Include/{dist_name}', - 'scripts': '{base}/Scripts', - 'data': '{base}', -} - -INSTALL_SCHEMES = { - 'posix_prefix': { - 'purelib': '{base}/lib/{implementation_lower}{py_version_short}/site-packages', - 'platlib': '{platbase}/{platlibdir}/{implementation_lower}' - '{py_version_short}/site-packages', - 'headers': '{base}/include/{implementation_lower}' - '{py_version_short}{abiflags}/{dist_name}', - 'scripts': '{base}/bin', - 'data': '{base}', - }, - 'posix_home': { - 'purelib': '{base}/lib/{implementation_lower}', - 'platlib': '{base}/{platlibdir}/{implementation_lower}', - 'headers': '{base}/include/{implementation_lower}/{dist_name}', - 'scripts': '{base}/bin', - 'data': '{base}', - }, - 'nt': WINDOWS_SCHEME, - 'pypy': { - 'purelib': '{base}/site-packages', - 'platlib': '{base}/site-packages', - 'headers': '{base}/include/{dist_name}', - 'scripts': '{base}/bin', - 'data': '{base}', - }, - 'pypy_nt': { - 'purelib': '{base}/site-packages', - 'platlib': '{base}/site-packages', - 'headers': '{base}/include/{dist_name}', - 'scripts': '{base}/Scripts', - 'data': '{base}', - }, -} - -# user site schemes -if HAS_USER_SITE: - INSTALL_SCHEMES['nt_user'] = { - 'purelib': '{usersite}', - 'platlib': '{usersite}', - 'headers': '{userbase}/{implementation}{py_version_nodot_plat}' - '/Include/{dist_name}', - 'scripts': '{userbase}/{implementation}{py_version_nodot_plat}/Scripts', - 'data': '{userbase}', - } - - INSTALL_SCHEMES['posix_user'] = { - 'purelib': '{usersite}', - 'platlib': '{usersite}', - 'headers': '{userbase}/include/{implementation_lower}' - '{py_version_short}{abiflags}/{dist_name}', - 'scripts': '{userbase}/bin', - 'data': '{userbase}', - } - - -INSTALL_SCHEMES.update(fw.schemes) - - -# The keys to an installation scheme; if any new types of files are to be -# installed, be sure to add an entry to every installation scheme above, -# and to SCHEME_KEYS here. -SCHEME_KEYS = ('purelib', 'platlib', 'headers', 'scripts', 'data') - - -def _load_sysconfig_schemes(): - with contextlib.suppress(AttributeError): - return { - scheme: sysconfig.get_paths(scheme, expand=False) - for scheme in sysconfig.get_scheme_names() - } - - -def _load_schemes(): - """ - Extend default schemes with schemes from sysconfig. - """ - - sysconfig_schemes = _load_sysconfig_schemes() or {} - - return { - scheme: { - **INSTALL_SCHEMES.get(scheme, {}), - **sysconfig_schemes.get(scheme, {}), - } - for scheme in set(itertools.chain(INSTALL_SCHEMES, sysconfig_schemes)) - } - - -def _get_implementation(): - if hasattr(sys, 'pypy_version_info'): - return 'PyPy' - else: - return 'Python' - - -def _select_scheme(ob, name): - scheme = _inject_headers(name, _load_scheme(_resolve_scheme(name))) - vars(ob).update(_remove_set(ob, _scheme_attrs(scheme))) - - -def _remove_set(ob, attrs): - """ - Include only attrs that are None in ob. - """ - return {key: value for key, value in attrs.items() if getattr(ob, key) is None} - - -def _resolve_scheme(name): - os_name, sep, key = name.partition('_') - try: - resolved = sysconfig.get_preferred_scheme(key) - except Exception: - resolved = fw.scheme(name) - return resolved - - -def _load_scheme(name): - return _load_schemes()[name] - - -def _inject_headers(name, scheme): - """ - Given a scheme name and the resolved scheme, - if the scheme does not include headers, resolve - the fallback scheme for the name and use headers - from it. pypa/distutils#88 - """ - # Bypass the preferred scheme, which may not - # have defined headers. - fallback = _load_scheme(name) - scheme.setdefault('headers', fallback['headers']) - return scheme - - -def _scheme_attrs(scheme): - """Resolve install directories by applying the install schemes.""" - return {f'install_{key}': scheme[key] for key in SCHEME_KEYS} - - -class install(Command): - description = "install everything from build directory" - - user_options = [ - # Select installation scheme and set base director(y|ies) - ('prefix=', None, "installation prefix"), - ('exec-prefix=', None, "(Unix only) prefix for platform-specific files"), - ('home=', None, "(Unix only) home directory to install under"), - # Or, just set the base director(y|ies) - ( - 'install-base=', - None, - "base installation directory (instead of --prefix or --home)", - ), - ( - 'install-platbase=', - None, - "base installation directory for platform-specific files (instead of --exec-prefix or --home)", - ), - ('root=', None, "install everything relative to this alternate root directory"), - # Or, explicitly set the installation scheme - ( - 'install-purelib=', - None, - "installation directory for pure Python module distributions", - ), - ( - 'install-platlib=', - None, - "installation directory for non-pure module distributions", - ), - ( - 'install-lib=', - None, - "installation directory for all module distributions (overrides --install-purelib and --install-platlib)", - ), - ('install-headers=', None, "installation directory for C/C++ headers"), - ('install-scripts=', None, "installation directory for Python scripts"), - ('install-data=', None, "installation directory for data files"), - # Byte-compilation options -- see install_lib.py for details, as - # these are duplicated from there (but only install_lib does - # anything with them). - ('compile', 'c', "compile .py to .pyc [default]"), - ('no-compile', None, "don't compile .py files"), - ( - 'optimize=', - 'O', - "also compile with optimization: -O1 for \"python -O\", " - "-O2 for \"python -OO\", and -O0 to disable [default: -O0]", - ), - # Miscellaneous control options - ('force', 'f', "force installation (overwrite any existing files)"), - ('skip-build', None, "skip rebuilding everything (for testing/debugging)"), - # Where to install documentation (eventually!) - # ('doc-format=', None, "format of documentation to generate"), - # ('install-man=', None, "directory for Unix man pages"), - # ('install-html=', None, "directory for HTML documentation"), - # ('install-info=', None, "directory for GNU info files"), - ('record=', None, "filename in which to record list of installed files"), - ] - - boolean_options: ClassVar[list[str]] = ['compile', 'force', 'skip-build'] - - if HAS_USER_SITE: - user_options.append(( - 'user', - None, - f"install in user site-package '{USER_SITE}'", - )) - boolean_options.append('user') - - negative_opt: ClassVar[dict[str, str]] = {'no-compile': 'compile'} - - def initialize_options(self) -> None: - """Initializes options.""" - # High-level options: these select both an installation base - # and scheme. - self.prefix: str | None = None - self.exec_prefix: str | None = None - self.home: str | None = None - self.user = False - - # These select only the installation base; it's up to the user to - # specify the installation scheme (currently, that means supplying - # the --install-{platlib,purelib,scripts,data} options). - self.install_base = None - self.install_platbase = None - self.root: str | None = None - - # These options are the actual installation directories; if not - # supplied by the user, they are filled in using the installation - # scheme implied by prefix/exec-prefix/home and the contents of - # that installation scheme. - self.install_purelib = None # for pure module distributions - self.install_platlib = None # non-pure (dists w/ extensions) - self.install_headers = None # for C/C++ headers - self.install_lib: str | None = None # set to either purelib or platlib - self.install_scripts = None - self.install_data = None - self.install_userbase = USER_BASE - self.install_usersite = USER_SITE - - self.compile = None - self.optimize = None - - # Deprecated - # These two are for putting non-packagized distributions into their - # own directory and creating a .pth file if it makes sense. - # 'extra_path' comes from the setup file; 'install_path_file' can - # be turned off if it makes no sense to install a .pth file. (But - # better to install it uselessly than to guess wrong and not - # install it when it's necessary and would be used!) Currently, - # 'install_path_file' is always true unless some outsider meddles - # with it. - self.extra_path = None - self.install_path_file = True - - # 'force' forces installation, even if target files are not - # out-of-date. 'skip_build' skips running the "build" command, - # handy if you know it's not necessary. 'warn_dir' (which is *not* - # a user option, it's just there so the bdist_* commands can turn - # it off) determines whether we warn about installing to a - # directory not in sys.path. - self.force = False - self.skip_build = False - self.warn_dir = True - - # These are only here as a conduit from the 'build' command to the - # 'install_*' commands that do the real work. ('build_base' isn't - # actually used anywhere, but it might be useful in future.) They - # are not user options, because if the user told the install - # command where the build directory is, that wouldn't affect the - # build command. - self.build_base = None - self.build_lib = None - - # Not defined yet because we don't know anything about - # documentation yet. - # self.install_man = None - # self.install_html = None - # self.install_info = None - - self.record = None - - # -- Option finalizing methods ------------------------------------- - # (This is rather more involved than for most commands, - # because this is where the policy for installing third- - # party Python modules on various platforms given a wide - # array of user input is decided. Yes, it's quite complex!) - - def finalize_options(self) -> None: # noqa: C901 - """Finalizes options.""" - # This method (and its helpers, like 'finalize_unix()', - # 'finalize_other()', and 'select_scheme()') is where the default - # installation directories for modules, extension modules, and - # anything else we care to install from a Python module - # distribution. Thus, this code makes a pretty important policy - # statement about how third-party stuff is added to a Python - # installation! Note that the actual work of installation is done - # by the relatively simple 'install_*' commands; they just take - # their orders from the installation directory options determined - # here. - - # Check for errors/inconsistencies in the options; first, stuff - # that's wrong on any platform. - - if (self.prefix or self.exec_prefix or self.home) and ( - self.install_base or self.install_platbase - ): - raise DistutilsOptionError( - "must supply either prefix/exec-prefix/home or install-base/install-platbase -- not both" - ) - - if self.home and (self.prefix or self.exec_prefix): - raise DistutilsOptionError( - "must supply either home or prefix/exec-prefix -- not both" - ) - - if self.user and ( - self.prefix - or self.exec_prefix - or self.home - or self.install_base - or self.install_platbase - ): - raise DistutilsOptionError( - "can't combine user with prefix, " - "exec_prefix/home, or install_(plat)base" - ) - - # Next, stuff that's wrong (or dubious) only on certain platforms. - if os.name != "posix": - if self.exec_prefix: - self.warn("exec-prefix option ignored on this platform") - self.exec_prefix = None - - # Now the interesting logic -- so interesting that we farm it out - # to other methods. The goal of these methods is to set the final - # values for the install_{lib,scripts,data,...} options, using as - # input a heady brew of prefix, exec_prefix, home, install_base, - # install_platbase, user-supplied versions of - # install_{purelib,platlib,lib,scripts,data,...}, and the - # install schemes. Phew! - - self.dump_dirs("pre-finalize_{unix,other}") - - if os.name == 'posix': - self.finalize_unix() - else: - self.finalize_other() - - self.dump_dirs("post-finalize_{unix,other}()") - - # Expand configuration variables, tilde, etc. in self.install_base - # and self.install_platbase -- that way, we can use $base or - # $platbase in the other installation directories and not worry - # about needing recursive variable expansion (shudder). - - py_version = sys.version.split()[0] - (prefix, exec_prefix) = get_config_vars('prefix', 'exec_prefix') - try: - abiflags = sys.abiflags - except AttributeError: - # sys.abiflags may not be defined on all platforms. - abiflags = '' - local_vars = { - 'dist_name': self.distribution.get_name(), - 'dist_version': self.distribution.get_version(), - 'dist_fullname': self.distribution.get_fullname(), - 'py_version': py_version, - 'py_version_short': f'{sys.version_info.major}.{sys.version_info.minor}', - 'py_version_nodot': f'{sys.version_info.major}{sys.version_info.minor}', - 'sys_prefix': prefix, - 'prefix': prefix, - 'sys_exec_prefix': exec_prefix, - 'exec_prefix': exec_prefix, - 'abiflags': abiflags, - 'platlibdir': getattr(sys, 'platlibdir', 'lib'), - 'implementation_lower': _get_implementation().lower(), - 'implementation': _get_implementation(), - } - - # vars for compatibility on older Pythons - compat_vars = dict( - # Python 3.9 and earlier - py_version_nodot_plat=getattr(sys, 'winver', '').replace('.', ''), - ) - - if HAS_USER_SITE: - local_vars['userbase'] = self.install_userbase - local_vars['usersite'] = self.install_usersite - - self.config_vars = collections.ChainMap( - local_vars, - sysconfig.get_config_vars(), - compat_vars, - fw.vars(), - ) - - self.expand_basedirs() - - self.dump_dirs("post-expand_basedirs()") - - # Now define config vars for the base directories so we can expand - # everything else. - local_vars['base'] = self.install_base - local_vars['platbase'] = self.install_platbase - - if DEBUG: - from pprint import pprint - - print("config vars:") - pprint(dict(self.config_vars)) - - # Expand "~" and configuration variables in the installation - # directories. - self.expand_dirs() - - self.dump_dirs("post-expand_dirs()") - - # Create directories in the home dir: - if self.user: - self.create_home_path() - - # Pick the actual directory to install all modules to: either - # install_purelib or install_platlib, depending on whether this - # module distribution is pure or not. Of course, if the user - # already specified install_lib, use their selection. - if self.install_lib is None: - if self.distribution.has_ext_modules(): # has extensions: non-pure - self.install_lib = self.install_platlib - else: - self.install_lib = self.install_purelib - - # Convert directories from Unix /-separated syntax to the local - # convention. - self.convert_paths( - 'lib', - 'purelib', - 'platlib', - 'scripts', - 'data', - 'headers', - 'userbase', - 'usersite', - ) - - # Deprecated - # Well, we're not actually fully completely finalized yet: we still - # have to deal with 'extra_path', which is the hack for allowing - # non-packagized module distributions (hello, Numerical Python!) to - # get their own directories. - self.handle_extra_path() - self.install_libbase = self.install_lib # needed for .pth file - self.install_lib = os.path.join(self.install_lib, self.extra_dirs) - - # If a new root directory was supplied, make all the installation - # dirs relative to it. - if self.root is not None: - self.change_roots( - 'libbase', 'lib', 'purelib', 'platlib', 'scripts', 'data', 'headers' - ) - - self.dump_dirs("after prepending root") - - # Find out the build directories, ie. where to install from. - self.set_undefined_options( - 'build', ('build_base', 'build_base'), ('build_lib', 'build_lib') - ) - - # Punt on doc directories for now -- after all, we're punting on - # documentation completely! - - def dump_dirs(self, msg) -> None: - """Dumps the list of user options.""" - if not DEBUG: - return - from ..fancy_getopt import longopt_xlate - - log.debug(msg + ":") - for opt in self.user_options: - opt_name = opt[0] - if opt_name[-1] == "=": - opt_name = opt_name[0:-1] - if opt_name in self.negative_opt: - opt_name = self.negative_opt[opt_name] - opt_name = opt_name.translate(longopt_xlate) - val = not getattr(self, opt_name) - else: - opt_name = opt_name.translate(longopt_xlate) - val = getattr(self, opt_name) - log.debug(" %s: %s", opt_name, val) - - def finalize_unix(self) -> None: - """Finalizes options for posix platforms.""" - if self.install_base is not None or self.install_platbase is not None: - incomplete_scheme = ( - ( - self.install_lib is None - and self.install_purelib is None - and self.install_platlib is None - ) - or self.install_headers is None - or self.install_scripts is None - or self.install_data is None - ) - if incomplete_scheme: - raise DistutilsOptionError( - "install-base or install-platbase supplied, but " - "installation scheme is incomplete" - ) - return - - if self.user: - if self.install_userbase is None: - raise DistutilsPlatformError("User base directory is not specified") - self.install_base = self.install_platbase = self.install_userbase - self.select_scheme("posix_user") - elif self.home is not None: - self.install_base = self.install_platbase = self.home - self.select_scheme("posix_home") - else: - if self.prefix is None: - if self.exec_prefix is not None: - raise DistutilsOptionError( - "must not supply exec-prefix without prefix" - ) - - # Allow Fedora to add components to the prefix - _prefix_addition = getattr(sysconfig, '_prefix_addition', "") - - self.prefix = os.path.normpath(sys.prefix) + _prefix_addition - self.exec_prefix = os.path.normpath(sys.exec_prefix) + _prefix_addition - - else: - if self.exec_prefix is None: - self.exec_prefix = self.prefix - - self.install_base = self.prefix - self.install_platbase = self.exec_prefix - self.select_scheme("posix_prefix") - - def finalize_other(self) -> None: - """Finalizes options for non-posix platforms""" - if self.user: - if self.install_userbase is None: - raise DistutilsPlatformError("User base directory is not specified") - self.install_base = self.install_platbase = self.install_userbase - self.select_scheme(os.name + "_user") - elif self.home is not None: - self.install_base = self.install_platbase = self.home - self.select_scheme("posix_home") - else: - if self.prefix is None: - self.prefix = os.path.normpath(sys.prefix) - - self.install_base = self.install_platbase = self.prefix - try: - self.select_scheme(os.name) - except KeyError: - raise DistutilsPlatformError( - f"I don't know how to install stuff on '{os.name}'" - ) - - def select_scheme(self, name) -> None: - _select_scheme(self, name) - - def _expand_attrs(self, attrs): - for attr in attrs: - val = getattr(self, attr) - if val is not None: - if os.name in ('posix', 'nt'): - val = os.path.expanduser(val) - val = subst_vars(val, self.config_vars) - setattr(self, attr, val) - - def expand_basedirs(self) -> None: - """Calls `os.path.expanduser` on install_base, install_platbase and - root.""" - self._expand_attrs(['install_base', 'install_platbase', 'root']) - - def expand_dirs(self) -> None: - """Calls `os.path.expanduser` on install dirs.""" - self._expand_attrs([ - 'install_purelib', - 'install_platlib', - 'install_lib', - 'install_headers', - 'install_scripts', - 'install_data', - ]) - - def convert_paths(self, *names) -> None: - """Call `convert_path` over `names`.""" - for name in names: - attr = "install_" + name - setattr(self, attr, convert_path(getattr(self, attr))) - - def handle_extra_path(self) -> None: - """Set `path_file` and `extra_dirs` using `extra_path`.""" - if self.extra_path is None: - self.extra_path = self.distribution.extra_path - - if self.extra_path is not None: - log.warning( - "Distribution option extra_path is deprecated. " - "See issue27919 for details." - ) - if isinstance(self.extra_path, str): - self.extra_path = self.extra_path.split(',') - - if len(self.extra_path) == 1: - path_file = extra_dirs = self.extra_path[0] - elif len(self.extra_path) == 2: - path_file, extra_dirs = self.extra_path - else: - raise DistutilsOptionError( - "'extra_path' option must be a list, tuple, or " - "comma-separated string with 1 or 2 elements" - ) - - # convert to local form in case Unix notation used (as it - # should be in setup scripts) - extra_dirs = convert_path(extra_dirs) - else: - path_file = None - extra_dirs = '' - - # XXX should we warn if path_file and not extra_dirs? (in which - # case the path file would be harmless but pointless) - self.path_file = path_file - self.extra_dirs = extra_dirs - - def change_roots(self, *names) -> None: - """Change the install directories pointed by name using root.""" - for name in names: - attr = "install_" + name - setattr(self, attr, change_root(self.root, getattr(self, attr))) - - def create_home_path(self) -> None: - """Create directories under ~.""" - if not self.user: - return - home = convert_path(os.path.expanduser("~")) - for path in self.config_vars.values(): - if str(path).startswith(home) and not os.path.isdir(path): - self.debug_print(f"os.makedirs('{path}', 0o700)") - os.makedirs(path, 0o700) - - # -- Command execution methods ------------------------------------- - - def run(self): - """Runs the command.""" - # Obviously have to build before we can install - if not self.skip_build: - self.run_command('build') - # If we built for any other platform, we can't install. - build_plat = self.distribution.get_command_obj('build').plat_name - # check warn_dir - it is a clue that the 'install' is happening - # internally, and not to sys.path, so we don't check the platform - # matches what we are running. - if self.warn_dir and build_plat != get_platform(): - raise DistutilsPlatformError("Can't install when cross-compiling") - - # Run all sub-commands (at least those that need to be run) - for cmd_name in self.get_sub_commands(): - self.run_command(cmd_name) - - if self.path_file: - self.create_path_file() - - # write list of installed files, if requested. - if self.record: - outputs = self.get_outputs() - if self.root: # strip any package prefix - root_len = len(self.root) - for counter in range(len(outputs)): - outputs[counter] = outputs[counter][root_len:] - self.execute( - write_file, - (self.record, outputs), - f"writing list of installed files to '{self.record}'", - ) - - sys_path = map(os.path.normpath, sys.path) - sys_path = map(os.path.normcase, sys_path) - install_lib = os.path.normcase(os.path.normpath(self.install_lib)) - if ( - self.warn_dir - and not (self.path_file and self.install_path_file) - and install_lib not in sys_path - ): - log.debug( - ( - "modules installed to '%s', which is not in " - "Python's module search path (sys.path) -- " - "you'll have to change the search path yourself" - ), - self.install_lib, - ) - - def create_path_file(self): - """Creates the .pth file""" - filename = os.path.join(self.install_libbase, self.path_file + ".pth") - if self.install_path_file: - self.execute( - write_file, (filename, [self.extra_dirs]), f"creating {filename}" - ) - else: - self.warn(f"path file '{filename}' not created") - - # -- Reporting methods --------------------------------------------- - - def get_outputs(self): - """Assembles the outputs of all the sub-commands.""" - outputs = [] - for cmd_name in self.get_sub_commands(): - cmd = self.get_finalized_command(cmd_name) - # Add the contents of cmd.get_outputs(), ensuring - # that outputs doesn't contain duplicate entries - for filename in cmd.get_outputs(): - if filename not in outputs: - outputs.append(filename) - - if self.path_file and self.install_path_file: - outputs.append(os.path.join(self.install_libbase, self.path_file + ".pth")) - - return outputs - - def get_inputs(self): - """Returns the inputs of all the sub-commands""" - # XXX gee, this looks familiar ;-( - inputs = [] - for cmd_name in self.get_sub_commands(): - cmd = self.get_finalized_command(cmd_name) - inputs.extend(cmd.get_inputs()) - - return inputs - - # -- Predicates for sub-command list ------------------------------- - - def has_lib(self): - """Returns true if the current distribution has any Python - modules to install.""" - return ( - self.distribution.has_pure_modules() or self.distribution.has_ext_modules() - ) - - def has_headers(self): - """Returns true if the current distribution has any headers to - install.""" - return self.distribution.has_headers() - - def has_scripts(self): - """Returns true if the current distribution has any scripts to. - install.""" - return self.distribution.has_scripts() - - def has_data(self): - """Returns true if the current distribution has any data to. - install.""" - return self.distribution.has_data_files() - - # 'sub_commands': a list of commands this command might have to run to - # get its work done. See cmd.py for more info. - sub_commands = [ - ('install_lib', has_lib), - ('install_headers', has_headers), - ('install_scripts', has_scripts), - ('install_data', has_data), - ('install_egg_info', lambda self: True), - ] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_data.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_data.py deleted file mode 100644 index 4ad186e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_data.py +++ /dev/null @@ -1,94 +0,0 @@ -"""distutils.command.install_data - -Implements the Distutils 'install_data' command, for installing -platform-independent data files.""" - -# contributed by Bastian Kleineidam - -from __future__ import annotations - -import functools -import os -from collections.abc import Iterable -from typing import ClassVar - -from ..core import Command -from ..util import change_root, convert_path - - -class install_data(Command): - description = "install data files" - - user_options = [ - ( - 'install-dir=', - 'd', - "base directory for installing data files [default: installation base dir]", - ), - ('root=', None, "install everything relative to this alternate root directory"), - ('force', 'f', "force installation (overwrite existing files)"), - ] - - boolean_options: ClassVar[list[str]] = ['force'] - - def initialize_options(self): - self.install_dir = None - self.outfiles = [] - self.root = None - self.force = False - self.data_files = self.distribution.data_files - self.warn_dir = True - - def finalize_options(self) -> None: - self.set_undefined_options( - 'install', - ('install_data', 'install_dir'), - ('root', 'root'), - ('force', 'force'), - ) - - def run(self) -> None: - self.mkpath(self.install_dir) - for f in self.data_files: - self._copy(f) - - @functools.singledispatchmethod - def _copy(self, f: tuple[str | os.PathLike, Iterable[str | os.PathLike]]): - # it's a tuple with path to install to and a list of files - dir = convert_path(f[0]) - if not os.path.isabs(dir): - dir = os.path.join(self.install_dir, dir) - elif self.root: - dir = change_root(self.root, dir) - self.mkpath(dir) - - if f[1] == []: - # If there are no files listed, the user must be - # trying to create an empty directory, so add the - # directory to the list of output files. - self.outfiles.append(dir) - else: - # Copy files, adding them to the list of output files. - for data in f[1]: - data = convert_path(data) - (out, _) = self.copy_file(data, dir) - self.outfiles.append(out) - - @_copy.register(str) - @_copy.register(os.PathLike) - def _(self, f: str | os.PathLike): - # it's a simple file, so copy it - f = convert_path(f) - if self.warn_dir: - self.warn( - "setup script did not provide a directory for " - f"'{f}' -- installing right in '{self.install_dir}'" - ) - (out, _) = self.copy_file(f, self.install_dir) - self.outfiles.append(out) - - def get_inputs(self): - return self.data_files or [] - - def get_outputs(self): - return self.outfiles diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_egg_info.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_egg_info.py deleted file mode 100644 index 230e94a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_egg_info.py +++ /dev/null @@ -1,91 +0,0 @@ -""" -distutils.command.install_egg_info - -Implements the Distutils 'install_egg_info' command, for installing -a package's PKG-INFO metadata. -""" - -import os -import re -import sys -from typing import ClassVar - -from .. import dir_util -from .._log import log -from ..cmd import Command - - -class install_egg_info(Command): - """Install an .egg-info file for the package""" - - description = "Install package's PKG-INFO metadata as an .egg-info file" - user_options: ClassVar[list[tuple[str, str, str]]] = [ - ('install-dir=', 'd', "directory to install to"), - ] - - def initialize_options(self): - self.install_dir = None - - @property - def basename(self): - """ - Allow basename to be overridden by child class. - Ref pypa/distutils#2. - """ - name = to_filename(safe_name(self.distribution.get_name())) - version = to_filename(safe_version(self.distribution.get_version())) - return f"{name}-{version}-py{sys.version_info.major}.{sys.version_info.minor}.egg-info" - - def finalize_options(self): - self.set_undefined_options('install_lib', ('install_dir', 'install_dir')) - self.target = os.path.join(self.install_dir, self.basename) - self.outputs = [self.target] - - def run(self): - target = self.target - if os.path.isdir(target) and not os.path.islink(target): - dir_util.remove_tree(target, dry_run=self.dry_run) - elif os.path.exists(target): - self.execute(os.unlink, (self.target,), "Removing " + target) - elif not os.path.isdir(self.install_dir): - self.execute( - os.makedirs, (self.install_dir,), "Creating " + self.install_dir - ) - log.info("Writing %s", target) - if not self.dry_run: - with open(target, 'w', encoding='UTF-8') as f: - self.distribution.metadata.write_pkg_file(f) - - def get_outputs(self): - return self.outputs - - -# The following routines are taken from setuptools' pkg_resources module and -# can be replaced by importing them from pkg_resources once it is included -# in the stdlib. - - -def safe_name(name): - """Convert an arbitrary string to a standard distribution name - - Any runs of non-alphanumeric/. characters are replaced with a single '-'. - """ - return re.sub('[^A-Za-z0-9.]+', '-', name) - - -def safe_version(version): - """Convert an arbitrary string to a standard version string - - Spaces become dots, and all other non-alphanumeric characters become - dashes, with runs of multiple dashes condensed to a single dash. - """ - version = version.replace(' ', '.') - return re.sub('[^A-Za-z0-9.]+', '-', version) - - -def to_filename(name): - """Convert a project or version name to its filename-escaped form - - Any '-' characters are currently replaced with '_'. - """ - return name.replace('-', '_') diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_headers.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_headers.py deleted file mode 100644 index 97af137..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_headers.py +++ /dev/null @@ -1,46 +0,0 @@ -"""distutils.command.install_headers - -Implements the Distutils 'install_headers' command, to install C/C++ header -files to the Python include directory.""" - -from typing import ClassVar - -from ..core import Command - - -# XXX force is never used -class install_headers(Command): - description = "install C/C++ header files" - - user_options: ClassVar[list[tuple[str, str, str]]] = [ - ('install-dir=', 'd', "directory to install header files to"), - ('force', 'f', "force installation (overwrite existing files)"), - ] - - boolean_options: ClassVar[list[str]] = ['force'] - - def initialize_options(self): - self.install_dir = None - self.force = False - self.outfiles = [] - - def finalize_options(self): - self.set_undefined_options( - 'install', ('install_headers', 'install_dir'), ('force', 'force') - ) - - def run(self): - headers = self.distribution.headers - if not headers: - return - - self.mkpath(self.install_dir) - for header in headers: - (out, _) = self.copy_file(header, self.install_dir) - self.outfiles.append(out) - - def get_inputs(self): - return self.distribution.headers or [] - - def get_outputs(self): - return self.outfiles diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_lib.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_lib.py deleted file mode 100644 index 2aababf..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_lib.py +++ /dev/null @@ -1,238 +0,0 @@ -"""distutils.command.install_lib - -Implements the Distutils 'install_lib' command -(install all Python modules).""" - -from __future__ import annotations - -import importlib.util -import os -import sys -from typing import Any, ClassVar - -from ..core import Command -from ..errors import DistutilsOptionError - -# Extension for Python source files. -PYTHON_SOURCE_EXTENSION = ".py" - - -class install_lib(Command): - description = "install all Python modules (extensions and pure Python)" - - # The byte-compilation options are a tad confusing. Here are the - # possible scenarios: - # 1) no compilation at all (--no-compile --no-optimize) - # 2) compile .pyc only (--compile --no-optimize; default) - # 3) compile .pyc and "opt-1" .pyc (--compile --optimize) - # 4) compile "opt-1" .pyc only (--no-compile --optimize) - # 5) compile .pyc and "opt-2" .pyc (--compile --optimize-more) - # 6) compile "opt-2" .pyc only (--no-compile --optimize-more) - # - # The UI for this is two options, 'compile' and 'optimize'. - # 'compile' is strictly boolean, and only decides whether to - # generate .pyc files. 'optimize' is three-way (0, 1, or 2), and - # decides both whether to generate .pyc files and what level of - # optimization to use. - - user_options = [ - ('install-dir=', 'd', "directory to install to"), - ('build-dir=', 'b', "build directory (where to install from)"), - ('force', 'f', "force installation (overwrite existing files)"), - ('compile', 'c', "compile .py to .pyc [default]"), - ('no-compile', None, "don't compile .py files"), - ( - 'optimize=', - 'O', - "also compile with optimization: -O1 for \"python -O\", " - "-O2 for \"python -OO\", and -O0 to disable [default: -O0]", - ), - ('skip-build', None, "skip the build steps"), - ] - - boolean_options: ClassVar[list[str]] = ['force', 'compile', 'skip-build'] - negative_opt: ClassVar[dict[str, str]] = {'no-compile': 'compile'} - - def initialize_options(self): - # let the 'install' command dictate our installation directory - self.install_dir = None - self.build_dir = None - self.force = False - self.compile = None - self.optimize = None - self.skip_build = None - - def finalize_options(self) -> None: - # Get all the information we need to install pure Python modules - # from the umbrella 'install' command -- build (source) directory, - # install (target) directory, and whether to compile .py files. - self.set_undefined_options( - 'install', - ('build_lib', 'build_dir'), - ('install_lib', 'install_dir'), - ('force', 'force'), - ('compile', 'compile'), - ('optimize', 'optimize'), - ('skip_build', 'skip_build'), - ) - - if self.compile is None: - self.compile = True - if self.optimize is None: - self.optimize = False - - if not isinstance(self.optimize, int): - try: - self.optimize = int(self.optimize) - except ValueError: - pass - if self.optimize not in (0, 1, 2): - raise DistutilsOptionError("optimize must be 0, 1, or 2") - - def run(self) -> None: - # Make sure we have built everything we need first - self.build() - - # Install everything: simply dump the entire contents of the build - # directory to the installation directory (that's the beauty of - # having a build directory!) - outfiles = self.install() - - # (Optionally) compile .py to .pyc - if outfiles is not None and self.distribution.has_pure_modules(): - self.byte_compile(outfiles) - - # -- Top-level worker functions ------------------------------------ - # (called from 'run()') - - def build(self) -> None: - if not self.skip_build: - if self.distribution.has_pure_modules(): - self.run_command('build_py') - if self.distribution.has_ext_modules(): - self.run_command('build_ext') - - # Any: https://typing.readthedocs.io/en/latest/guides/writing_stubs.html#the-any-trick - def install(self) -> list[str] | Any: - if os.path.isdir(self.build_dir): - outfiles = self.copy_tree(self.build_dir, self.install_dir) - else: - self.warn( - f"'{self.build_dir}' does not exist -- no Python modules to install" - ) - return - return outfiles - - def byte_compile(self, files) -> None: - if sys.dont_write_bytecode: - self.warn('byte-compiling is disabled, skipping.') - return - - from ..util import byte_compile - - # Get the "--root" directory supplied to the "install" command, - # and use it as a prefix to strip off the purported filename - # encoded in bytecode files. This is far from complete, but it - # should at least generate usable bytecode in RPM distributions. - install_root = self.get_finalized_command('install').root - - if self.compile: - byte_compile( - files, - optimize=0, - force=self.force, - prefix=install_root, - dry_run=self.dry_run, - ) - if self.optimize > 0: - byte_compile( - files, - optimize=self.optimize, - force=self.force, - prefix=install_root, - verbose=self.verbose, - dry_run=self.dry_run, - ) - - # -- Utility methods ----------------------------------------------- - - def _mutate_outputs(self, has_any, build_cmd, cmd_option, output_dir): - if not has_any: - return [] - - build_cmd = self.get_finalized_command(build_cmd) - build_files = build_cmd.get_outputs() - build_dir = getattr(build_cmd, cmd_option) - - prefix_len = len(build_dir) + len(os.sep) - outputs = [os.path.join(output_dir, file[prefix_len:]) for file in build_files] - - return outputs - - def _bytecode_filenames(self, py_filenames): - bytecode_files = [] - for py_file in py_filenames: - # Since build_py handles package data installation, the - # list of outputs can contain more than just .py files. - # Make sure we only report bytecode for the .py files. - ext = os.path.splitext(os.path.normcase(py_file))[1] - if ext != PYTHON_SOURCE_EXTENSION: - continue - if self.compile: - bytecode_files.append( - importlib.util.cache_from_source(py_file, optimization='') - ) - if self.optimize > 0: - bytecode_files.append( - importlib.util.cache_from_source( - py_file, optimization=self.optimize - ) - ) - - return bytecode_files - - # -- External interface -------------------------------------------- - # (called by outsiders) - - def get_outputs(self): - """Return the list of files that would be installed if this command - were actually run. Not affected by the "dry-run" flag or whether - modules have actually been built yet. - """ - pure_outputs = self._mutate_outputs( - self.distribution.has_pure_modules(), - 'build_py', - 'build_lib', - self.install_dir, - ) - if self.compile: - bytecode_outputs = self._bytecode_filenames(pure_outputs) - else: - bytecode_outputs = [] - - ext_outputs = self._mutate_outputs( - self.distribution.has_ext_modules(), - 'build_ext', - 'build_lib', - self.install_dir, - ) - - return pure_outputs + bytecode_outputs + ext_outputs - - def get_inputs(self): - """Get the list of files that are input to this command, ie. the - files that get installed as they are named in the build tree. - The files in this list correspond one-to-one to the output - filenames returned by 'get_outputs()'. - """ - inputs = [] - - if self.distribution.has_pure_modules(): - build_py = self.get_finalized_command('build_py') - inputs.extend(build_py.get_outputs()) - - if self.distribution.has_ext_modules(): - build_ext = self.get_finalized_command('build_ext') - inputs.extend(build_ext.get_outputs()) - - return inputs diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_scripts.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_scripts.py deleted file mode 100644 index 92e8694..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/install_scripts.py +++ /dev/null @@ -1,62 +0,0 @@ -"""distutils.command.install_scripts - -Implements the Distutils 'install_scripts' command, for installing -Python scripts.""" - -# contributed by Bastian Kleineidam - -import os -from distutils._log import log -from stat import ST_MODE -from typing import ClassVar - -from ..core import Command - - -class install_scripts(Command): - description = "install scripts (Python or otherwise)" - - user_options = [ - ('install-dir=', 'd', "directory to install scripts to"), - ('build-dir=', 'b', "build directory (where to install from)"), - ('force', 'f', "force installation (overwrite existing files)"), - ('skip-build', None, "skip the build steps"), - ] - - boolean_options: ClassVar[list[str]] = ['force', 'skip-build'] - - def initialize_options(self): - self.install_dir = None - self.force = False - self.build_dir = None - self.skip_build = None - - def finalize_options(self) -> None: - self.set_undefined_options('build', ('build_scripts', 'build_dir')) - self.set_undefined_options( - 'install', - ('install_scripts', 'install_dir'), - ('force', 'force'), - ('skip_build', 'skip_build'), - ) - - def run(self) -> None: - if not self.skip_build: - self.run_command('build_scripts') - self.outfiles = self.copy_tree(self.build_dir, self.install_dir) - if os.name == 'posix': - # Set the executable bits (owner, group, and world) on - # all the scripts we just installed. - for file in self.get_outputs(): - if self.dry_run: - log.info("changing mode of %s", file) - else: - mode = ((os.stat(file)[ST_MODE]) | 0o555) & 0o7777 - log.info("changing mode of %s to %o", file, mode) - os.chmod(file, mode) - - def get_inputs(self): - return self.distribution.scripts or [] - - def get_outputs(self): - return self.outfiles or [] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/sdist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/sdist.py deleted file mode 100644 index b3bf0c3..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/command/sdist.py +++ /dev/null @@ -1,521 +0,0 @@ -"""distutils.command.sdist - -Implements the Distutils 'sdist' command (create a source distribution).""" - -from __future__ import annotations - -import os -import sys -from collections.abc import Callable -from distutils import archive_util, dir_util, file_util -from distutils._log import log -from glob import glob -from itertools import filterfalse -from typing import ClassVar - -from ..core import Command -from ..errors import DistutilsOptionError, DistutilsTemplateError -from ..filelist import FileList -from ..text_file import TextFile -from ..util import convert_path - - -def show_formats(): - """Print all possible values for the 'formats' option (used by - the "--help-formats" command-line option). - """ - from ..archive_util import ARCHIVE_FORMATS - from ..fancy_getopt import FancyGetopt - - formats = sorted( - ("formats=" + format, None, ARCHIVE_FORMATS[format][2]) - for format in ARCHIVE_FORMATS.keys() - ) - FancyGetopt(formats).print_help("List of available source distribution formats:") - - -class sdist(Command): - description = "create a source distribution (tarball, zip file, etc.)" - - def checking_metadata(self) -> bool: - """Callable used for the check sub-command. - - Placed here so user_options can view it""" - return self.metadata_check - - user_options = [ - ('template=', 't', "name of manifest template file [default: MANIFEST.in]"), - ('manifest=', 'm', "name of manifest file [default: MANIFEST]"), - ( - 'use-defaults', - None, - "include the default file set in the manifest " - "[default; disable with --no-defaults]", - ), - ('no-defaults', None, "don't include the default file set"), - ( - 'prune', - None, - "specifically exclude files/directories that should not be " - "distributed (build tree, RCS/CVS dirs, etc.) " - "[default; disable with --no-prune]", - ), - ('no-prune', None, "don't automatically exclude anything"), - ( - 'manifest-only', - 'o', - "just regenerate the manifest and then stop (implies --force-manifest)", - ), - ( - 'force-manifest', - 'f', - "forcibly regenerate the manifest and carry on as usual. " - "Deprecated: now the manifest is always regenerated.", - ), - ('formats=', None, "formats for source distribution (comma-separated list)"), - ( - 'keep-temp', - 'k', - "keep the distribution tree around after creating " + "archive file(s)", - ), - ( - 'dist-dir=', - 'd', - "directory to put the source distribution archive(s) in [default: dist]", - ), - ( - 'metadata-check', - None, - "Ensure that all required elements of meta-data " - "are supplied. Warn if any missing. [default]", - ), - ( - 'owner=', - 'u', - "Owner name used when creating a tar file [default: current user]", - ), - ( - 'group=', - 'g', - "Group name used when creating a tar file [default: current group]", - ), - ] - - boolean_options: ClassVar[list[str]] = [ - 'use-defaults', - 'prune', - 'manifest-only', - 'force-manifest', - 'keep-temp', - 'metadata-check', - ] - - help_options: ClassVar[list[tuple[str, str | None, str, Callable[[], object]]]] = [ - ('help-formats', None, "list available distribution formats", show_formats), - ] - - negative_opt: ClassVar[dict[str, str]] = { - 'no-defaults': 'use-defaults', - 'no-prune': 'prune', - } - - sub_commands = [('check', checking_metadata)] - - READMES: ClassVar[tuple[str, ...]] = ('README', 'README.txt', 'README.rst') - - def initialize_options(self): - # 'template' and 'manifest' are, respectively, the names of - # the manifest template and manifest file. - self.template = None - self.manifest = None - - # 'use_defaults': if true, we will include the default file set - # in the manifest - self.use_defaults = True - self.prune = True - - self.manifest_only = False - self.force_manifest = False - - self.formats = ['gztar'] - self.keep_temp = False - self.dist_dir = None - - self.archive_files = None - self.metadata_check = True - self.owner = None - self.group = None - - def finalize_options(self) -> None: - if self.manifest is None: - self.manifest = "MANIFEST" - if self.template is None: - self.template = "MANIFEST.in" - - self.ensure_string_list('formats') - - bad_format = archive_util.check_archive_formats(self.formats) - if bad_format: - raise DistutilsOptionError(f"unknown archive format '{bad_format}'") - - if self.dist_dir is None: - self.dist_dir = "dist" - - def run(self) -> None: - # 'filelist' contains the list of files that will make up the - # manifest - self.filelist = FileList() - - # Run sub commands - for cmd_name in self.get_sub_commands(): - self.run_command(cmd_name) - - # Do whatever it takes to get the list of files to process - # (process the manifest template, read an existing manifest, - # whatever). File list is accumulated in 'self.filelist'. - self.get_file_list() - - # If user just wanted us to regenerate the manifest, stop now. - if self.manifest_only: - return - - # Otherwise, go ahead and create the source distribution tarball, - # or zipfile, or whatever. - self.make_distribution() - - def get_file_list(self) -> None: - """Figure out the list of files to include in the source - distribution, and put it in 'self.filelist'. This might involve - reading the manifest template (and writing the manifest), or just - reading the manifest, or just using the default file set -- it all - depends on the user's options. - """ - # new behavior when using a template: - # the file list is recalculated every time because - # even if MANIFEST.in or setup.py are not changed - # the user might have added some files in the tree that - # need to be included. - # - # This makes --force the default and only behavior with templates. - template_exists = os.path.isfile(self.template) - if not template_exists and self._manifest_is_not_generated(): - self.read_manifest() - self.filelist.sort() - self.filelist.remove_duplicates() - return - - if not template_exists: - self.warn( - ("manifest template '%s' does not exist " + "(using default file list)") - % self.template - ) - self.filelist.findall() - - if self.use_defaults: - self.add_defaults() - - if template_exists: - self.read_template() - - if self.prune: - self.prune_file_list() - - self.filelist.sort() - self.filelist.remove_duplicates() - self.write_manifest() - - def add_defaults(self) -> None: - """Add all the default files to self.filelist: - - README or README.txt - - setup.py - - tests/test*.py and test/test*.py - - all pure Python modules mentioned in setup script - - all files pointed by package_data (build_py) - - all files defined in data_files. - - all files defined as scripts. - - all C sources listed as part of extensions or C libraries - in the setup script (doesn't catch C headers!) - Warns if (README or README.txt) or setup.py are missing; everything - else is optional. - """ - self._add_defaults_standards() - self._add_defaults_optional() - self._add_defaults_python() - self._add_defaults_data_files() - self._add_defaults_ext() - self._add_defaults_c_libs() - self._add_defaults_scripts() - - @staticmethod - def _cs_path_exists(fspath): - """ - Case-sensitive path existence check - - >>> sdist._cs_path_exists(__file__) - True - >>> sdist._cs_path_exists(__file__.upper()) - False - """ - if not os.path.exists(fspath): - return False - # make absolute so we always have a directory - abspath = os.path.abspath(fspath) - directory, filename = os.path.split(abspath) - return filename in os.listdir(directory) - - def _add_defaults_standards(self): - standards = [self.READMES, self.distribution.script_name] - for fn in standards: - if isinstance(fn, tuple): - alts = fn - got_it = False - for fn in alts: - if self._cs_path_exists(fn): - got_it = True - self.filelist.append(fn) - break - - if not got_it: - self.warn( - "standard file not found: should have one of " + ', '.join(alts) - ) - else: - if self._cs_path_exists(fn): - self.filelist.append(fn) - else: - self.warn(f"standard file '{fn}' not found") - - def _add_defaults_optional(self): - optional = ['tests/test*.py', 'test/test*.py', 'setup.cfg'] - for pattern in optional: - files = filter(os.path.isfile, glob(pattern)) - self.filelist.extend(files) - - def _add_defaults_python(self): - # build_py is used to get: - # - python modules - # - files defined in package_data - build_py = self.get_finalized_command('build_py') - - # getting python files - if self.distribution.has_pure_modules(): - self.filelist.extend(build_py.get_source_files()) - - # getting package_data files - # (computed in build_py.data_files by build_py.finalize_options) - for _pkg, src_dir, _build_dir, filenames in build_py.data_files: - for filename in filenames: - self.filelist.append(os.path.join(src_dir, filename)) - - def _add_defaults_data_files(self): - # getting distribution.data_files - if self.distribution.has_data_files(): - for item in self.distribution.data_files: - if isinstance(item, str): - # plain file - item = convert_path(item) - if os.path.isfile(item): - self.filelist.append(item) - else: - # a (dirname, filenames) tuple - dirname, filenames = item - for f in filenames: - f = convert_path(f) - if os.path.isfile(f): - self.filelist.append(f) - - def _add_defaults_ext(self): - if self.distribution.has_ext_modules(): - build_ext = self.get_finalized_command('build_ext') - self.filelist.extend(build_ext.get_source_files()) - - def _add_defaults_c_libs(self): - if self.distribution.has_c_libraries(): - build_clib = self.get_finalized_command('build_clib') - self.filelist.extend(build_clib.get_source_files()) - - def _add_defaults_scripts(self): - if self.distribution.has_scripts(): - build_scripts = self.get_finalized_command('build_scripts') - self.filelist.extend(build_scripts.get_source_files()) - - def read_template(self) -> None: - """Read and parse manifest template file named by self.template. - - (usually "MANIFEST.in") The parsing and processing is done by - 'self.filelist', which updates itself accordingly. - """ - log.info("reading manifest template '%s'", self.template) - template = TextFile( - self.template, - strip_comments=True, - skip_blanks=True, - join_lines=True, - lstrip_ws=True, - rstrip_ws=True, - collapse_join=True, - ) - - try: - while True: - line = template.readline() - if line is None: # end of file - break - - try: - self.filelist.process_template_line(line) - # the call above can raise a DistutilsTemplateError for - # malformed lines, or a ValueError from the lower-level - # convert_path function - except (DistutilsTemplateError, ValueError) as msg: - self.warn( - f"{template.filename}, line {int(template.current_line)}: {msg}" - ) - finally: - template.close() - - def prune_file_list(self) -> None: - """Prune off branches that might slip into the file list as created - by 'read_template()', but really don't belong there: - * the build tree (typically "build") - * the release tree itself (only an issue if we ran "sdist" - previously with --keep-temp, or it aborted) - * any RCS, CVS, .svn, .hg, .git, .bzr, _darcs directories - """ - build = self.get_finalized_command('build') - base_dir = self.distribution.get_fullname() - - self.filelist.exclude_pattern(None, prefix=os.fspath(build.build_base)) - self.filelist.exclude_pattern(None, prefix=base_dir) - - if sys.platform == 'win32': - seps = r'/|\\' - else: - seps = '/' - - vcs_dirs = ['RCS', 'CVS', r'\.svn', r'\.hg', r'\.git', r'\.bzr', '_darcs'] - vcs_ptrn = r'(^|{})({})({}).*'.format(seps, '|'.join(vcs_dirs), seps) - self.filelist.exclude_pattern(vcs_ptrn, is_regex=True) - - def write_manifest(self) -> None: - """Write the file list in 'self.filelist' (presumably as filled in - by 'add_defaults()' and 'read_template()') to the manifest file - named by 'self.manifest'. - """ - if self._manifest_is_not_generated(): - log.info( - f"not writing to manually maintained manifest file '{self.manifest}'" - ) - return - - content = self.filelist.files[:] - content.insert(0, '# file GENERATED by distutils, do NOT edit') - self.execute( - file_util.write_file, - (self.manifest, content), - f"writing manifest file '{self.manifest}'", - ) - - def _manifest_is_not_generated(self): - # check for special comment used in 3.1.3 and higher - if not os.path.isfile(self.manifest): - return False - - with open(self.manifest, encoding='utf-8') as fp: - first_line = next(fp) - return first_line != '# file GENERATED by distutils, do NOT edit\n' - - def read_manifest(self) -> None: - """Read the manifest file (named by 'self.manifest') and use it to - fill in 'self.filelist', the list of files to include in the source - distribution. - """ - log.info("reading manifest file '%s'", self.manifest) - with open(self.manifest, encoding='utf-8') as lines: - self.filelist.extend( - # ignore comments and blank lines - filter(None, filterfalse(is_comment, map(str.strip, lines))) - ) - - def make_release_tree(self, base_dir, files) -> None: - """Create the directory tree that will become the source - distribution archive. All directories implied by the filenames in - 'files' are created under 'base_dir', and then we hard link or copy - (if hard linking is unavailable) those files into place. - Essentially, this duplicates the developer's source tree, but in a - directory named after the distribution, containing only the files - to be distributed. - """ - # Create all the directories under 'base_dir' necessary to - # put 'files' there; the 'mkpath()' is just so we don't die - # if the manifest happens to be empty. - self.mkpath(base_dir) - dir_util.create_tree(base_dir, files, dry_run=self.dry_run) - - # And walk over the list of files, either making a hard link (if - # os.link exists) to each one that doesn't already exist in its - # corresponding location under 'base_dir', or copying each file - # that's out-of-date in 'base_dir'. (Usually, all files will be - # out-of-date, because by default we blow away 'base_dir' when - # we're done making the distribution archives.) - - if hasattr(os, 'link'): # can make hard links on this system - link = 'hard' - msg = f"making hard links in {base_dir}..." - else: # nope, have to copy - link = None - msg = f"copying files to {base_dir}..." - - if not files: - log.warning("no files to distribute -- empty manifest?") - else: - log.info(msg) - for file in files: - if not os.path.isfile(file): - log.warning("'%s' not a regular file -- skipping", file) - else: - dest = os.path.join(base_dir, file) - self.copy_file(file, dest, link=link) - - self.distribution.metadata.write_pkg_info(base_dir) - - def make_distribution(self) -> None: - """Create the source distribution(s). First, we create the release - tree with 'make_release_tree()'; then, we create all required - archive files (according to 'self.formats') from the release tree. - Finally, we clean up by blowing away the release tree (unless - 'self.keep_temp' is true). The list of archive files created is - stored so it can be retrieved later by 'get_archive_files()'. - """ - # Don't warn about missing meta-data here -- should be (and is!) - # done elsewhere. - base_dir = self.distribution.get_fullname() - base_name = os.path.join(self.dist_dir, base_dir) - - self.make_release_tree(base_dir, self.filelist.files) - archive_files = [] # remember names of files we create - # tar archive must be created last to avoid overwrite and remove - if 'tar' in self.formats: - self.formats.append(self.formats.pop(self.formats.index('tar'))) - - for fmt in self.formats: - file = self.make_archive( - base_name, fmt, base_dir=base_dir, owner=self.owner, group=self.group - ) - archive_files.append(file) - self.distribution.dist_files.append(('sdist', '', file)) - - self.archive_files = archive_files - - if not self.keep_temp: - dir_util.remove_tree(base_dir, dry_run=self.dry_run) - - def get_archive_files(self): - """Return the list of archive files created when the command - was run, or None if the command hasn't run yet. - """ - return self.archive_files - - -def is_comment(line: str) -> bool: - return line.startswith('#') diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__init__.py deleted file mode 100644 index 2c43729..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__init__.py +++ /dev/null @@ -1,18 +0,0 @@ -from __future__ import annotations - -from collections.abc import Iterable -from typing import TypeVar - -_IterableT = TypeVar("_IterableT", bound="Iterable[str]") - - -def consolidate_linker_args(args: _IterableT) -> _IterableT | str: - """ - Ensure the return value is a string for backward compatibility. - - Retain until at least 2025-04-31. See pypa/distutils#246 - """ - - if not all(arg.startswith('-Wl,') for arg in args): - return args - return '-Wl,' + ','.join(arg.removeprefix('-Wl,') for arg in args) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index c4f6841..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/numpy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/numpy.cpython-312.pyc deleted file mode 100644 index cb8b781..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/numpy.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/py39.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/py39.cpython-312.pyc deleted file mode 100644 index 520a129..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/__pycache__/py39.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/numpy.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/numpy.py deleted file mode 100644 index 73eca7a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/numpy.py +++ /dev/null @@ -1,2 +0,0 @@ -# required for older numpy versions on Pythons prior to 3.12; see pypa/setuptools#4876 -from ..compilers.C.base import _default_compilers, compiler_class # noqa: F401 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/py39.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/py39.py deleted file mode 100644 index 1b436d7..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compat/py39.py +++ /dev/null @@ -1,66 +0,0 @@ -import functools -import itertools -import platform -import sys - - -def add_ext_suffix_39(vars): - """ - Ensure vars contains 'EXT_SUFFIX'. pypa/distutils#130 - """ - import _imp - - ext_suffix = _imp.extension_suffixes()[0] - vars.update( - EXT_SUFFIX=ext_suffix, - # sysconfig sets SO to match EXT_SUFFIX, so maintain - # that expectation. - # https://github.com/python/cpython/blob/785cc6770588de087d09e89a69110af2542be208/Lib/sysconfig.py#L671-L673 - SO=ext_suffix, - ) - - -needs_ext_suffix = sys.version_info < (3, 10) and platform.system() == 'Windows' -add_ext_suffix = add_ext_suffix_39 if needs_ext_suffix else lambda vars: None - - -# from more_itertools -class UnequalIterablesError(ValueError): - def __init__(self, details=None): - msg = 'Iterables have different lengths' - if details is not None: - msg += (': index 0 has length {}; index {} has length {}').format(*details) - - super().__init__(msg) - - -# from more_itertools -def _zip_equal_generator(iterables): - _marker = object() - for combo in itertools.zip_longest(*iterables, fillvalue=_marker): - for val in combo: - if val is _marker: - raise UnequalIterablesError() - yield combo - - -# from more_itertools -def _zip_equal(*iterables): - # Check whether the iterables are all the same size. - try: - first_size = len(iterables[0]) - for i, it in enumerate(iterables[1:], 1): - size = len(it) - if size != first_size: - raise UnequalIterablesError(details=(first_size, i, size)) - # All sizes are equal, we can use the built-in zip. - return zip(*iterables) - # If any one of the iterables didn't have a length, start reading - # them until one runs out. - except TypeError: - return _zip_equal_generator(iterables) - - -zip_strict = ( - _zip_equal if sys.version_info < (3, 10) else functools.partial(zip, strict=True) -) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/base.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/base.cpython-312.pyc deleted file mode 100644 index 546bd35..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/base.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/cygwin.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/cygwin.cpython-312.pyc deleted file mode 100644 index 5ff28c9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/cygwin.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/errors.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/errors.cpython-312.pyc deleted file mode 100644 index 6418e62..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/errors.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/msvc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/msvc.cpython-312.pyc deleted file mode 100644 index 9137853..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/msvc.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/unix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/unix.cpython-312.pyc deleted file mode 100644 index a599343..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/unix.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/zos.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/zos.cpython-312.pyc deleted file mode 100644 index b4449aa..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/__pycache__/zos.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/base.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/base.py deleted file mode 100644 index 5efd2a3..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/base.py +++ /dev/null @@ -1,1394 +0,0 @@ -"""distutils.ccompiler - -Contains Compiler, an abstract base class that defines the interface -for the Distutils compiler abstraction model.""" - -from __future__ import annotations - -import os -import pathlib -import re -import sys -import warnings -from collections.abc import Callable, Iterable, MutableSequence, Sequence -from typing import ( - TYPE_CHECKING, - ClassVar, - Literal, - TypeVar, - Union, - overload, -) - -from more_itertools import always_iterable - -from ..._log import log -from ..._modified import newer_group -from ...dir_util import mkpath -from ...errors import ( - DistutilsModuleError, - DistutilsPlatformError, -) -from ...file_util import move_file -from ...spawn import spawn -from ...util import execute, is_mingw, split_quoted -from .errors import ( - CompileError, - LinkError, - UnknownFileType, -) - -if TYPE_CHECKING: - from typing_extensions import TypeAlias, TypeVarTuple, Unpack - - _Ts = TypeVarTuple("_Ts") - -_Macro: TypeAlias = Union[tuple[str], tuple[str, Union[str, None]]] -_StrPathT = TypeVar("_StrPathT", bound="str | os.PathLike[str]") -_BytesPathT = TypeVar("_BytesPathT", bound="bytes | os.PathLike[bytes]") - - -class Compiler: - """Abstract base class to define the interface that must be implemented - by real compiler classes. Also has some utility methods used by - several compiler classes. - - The basic idea behind a compiler abstraction class is that each - instance can be used for all the compile/link steps in building a - single project. Thus, attributes common to all of those compile and - link steps -- include directories, macros to define, libraries to link - against, etc. -- are attributes of the compiler instance. To allow for - variability in how individual files are treated, most of those - attributes may be varied on a per-compilation or per-link basis. - """ - - # 'compiler_type' is a class attribute that identifies this class. It - # keeps code that wants to know what kind of compiler it's dealing with - # from having to import all possible compiler classes just to do an - # 'isinstance'. In concrete CCompiler subclasses, 'compiler_type' - # should really, really be one of the keys of the 'compiler_class' - # dictionary (see below -- used by the 'new_compiler()' factory - # function) -- authors of new compiler interface classes are - # responsible for updating 'compiler_class'! - compiler_type: ClassVar[str] = None # type: ignore[assignment] - - # XXX things not handled by this compiler abstraction model: - # * client can't provide additional options for a compiler, - # e.g. warning, optimization, debugging flags. Perhaps this - # should be the domain of concrete compiler abstraction classes - # (UnixCCompiler, MSVCCompiler, etc.) -- or perhaps the base - # class should have methods for the common ones. - # * can't completely override the include or library searchg - # path, ie. no "cc -I -Idir1 -Idir2" or "cc -L -Ldir1 -Ldir2". - # I'm not sure how widely supported this is even by Unix - # compilers, much less on other platforms. And I'm even less - # sure how useful it is; maybe for cross-compiling, but - # support for that is a ways off. (And anyways, cross - # compilers probably have a dedicated binary with the - # right paths compiled in. I hope.) - # * can't do really freaky things with the library list/library - # dirs, e.g. "-Ldir1 -lfoo -Ldir2 -lfoo" to link against - # different versions of libfoo.a in different locations. I - # think this is useless without the ability to null out the - # library search path anyways. - - executables: ClassVar[dict] - - # Subclasses that rely on the standard filename generation methods - # implemented below should override these; see the comment near - # those methods ('object_filenames()' et. al.) for details: - src_extensions: ClassVar[list[str] | None] = None - obj_extension: ClassVar[str | None] = None - static_lib_extension: ClassVar[str | None] = None - shared_lib_extension: ClassVar[str | None] = None - static_lib_format: ClassVar[str | None] = None # format string - shared_lib_format: ClassVar[str | None] = None # prob. same as static_lib_format - exe_extension: ClassVar[str | None] = None - - # Default language settings. language_map is used to detect a source - # file or Extension target language, checking source filenames. - # language_order is used to detect the language precedence, when deciding - # what language to use when mixing source types. For example, if some - # extension has two files with ".c" extension, and one with ".cpp", it - # is still linked as c++. - language_map: ClassVar[dict[str, str]] = { - ".c": "c", - ".cc": "c++", - ".cpp": "c++", - ".cxx": "c++", - ".m": "objc", - } - language_order: ClassVar[list[str]] = ["c++", "objc", "c"] - - include_dirs: list[str] = [] - """ - include dirs specific to this compiler class - """ - - library_dirs: list[str] = [] - """ - library dirs specific to this compiler class - """ - - def __init__( - self, verbose: bool = False, dry_run: bool = False, force: bool = False - ) -> None: - self.dry_run = dry_run - self.force = force - self.verbose = verbose - - # 'output_dir': a common output directory for object, library, - # shared object, and shared library files - self.output_dir: str | None = None - - # 'macros': a list of macro definitions (or undefinitions). A - # macro definition is a 2-tuple (name, value), where the value is - # either a string or None (no explicit value). A macro - # undefinition is a 1-tuple (name,). - self.macros: list[_Macro] = [] - - # 'include_dirs': a list of directories to search for include files - self.include_dirs = [] - - # 'libraries': a list of libraries to include in any link - # (library names, not filenames: eg. "foo" not "libfoo.a") - self.libraries: list[str] = [] - - # 'library_dirs': a list of directories to search for libraries - self.library_dirs = [] - - # 'runtime_library_dirs': a list of directories to search for - # shared libraries/objects at runtime - self.runtime_library_dirs: list[str] = [] - - # 'objects': a list of object files (or similar, such as explicitly - # named library files) to include on any link - self.objects: list[str] = [] - - for key in self.executables.keys(): - self.set_executable(key, self.executables[key]) - - def set_executables(self, **kwargs: str) -> None: - """Define the executables (and options for them) that will be run - to perform the various stages of compilation. The exact set of - executables that may be specified here depends on the compiler - class (via the 'executables' class attribute), but most will have: - compiler the C/C++ compiler - linker_so linker used to create shared objects and libraries - linker_exe linker used to create binary executables - archiver static library creator - - On platforms with a command-line (Unix, DOS/Windows), each of these - is a string that will be split into executable name and (optional) - list of arguments. (Splitting the string is done similarly to how - Unix shells operate: words are delimited by spaces, but quotes and - backslashes can override this. See - 'distutils.util.split_quoted()'.) - """ - - # Note that some CCompiler implementation classes will define class - # attributes 'cpp', 'cc', etc. with hard-coded executable names; - # this is appropriate when a compiler class is for exactly one - # compiler/OS combination (eg. MSVCCompiler). Other compiler - # classes (UnixCCompiler, in particular) are driven by information - # discovered at run-time, since there are many different ways to do - # basically the same things with Unix C compilers. - - for key in kwargs: - if key not in self.executables: - raise ValueError( - f"unknown executable '{key}' for class {self.__class__.__name__}" - ) - self.set_executable(key, kwargs[key]) - - def set_executable(self, key, value): - if isinstance(value, str): - setattr(self, key, split_quoted(value)) - else: - setattr(self, key, value) - - def _find_macro(self, name): - i = 0 - for defn in self.macros: - if defn[0] == name: - return i - i += 1 - return None - - def _check_macro_definitions(self, definitions): - """Ensure that every element of 'definitions' is valid.""" - for defn in definitions: - self._check_macro_definition(*defn) - - def _check_macro_definition(self, defn): - """ - Raise a TypeError if defn is not valid. - - A valid definition is either a (name, value) 2-tuple or a (name,) tuple. - """ - if not isinstance(defn, tuple) or not self._is_valid_macro(*defn): - raise TypeError( - f"invalid macro definition '{defn}': " - "must be tuple (string,), (string, string), or (string, None)" - ) - - @staticmethod - def _is_valid_macro(name, value=None): - """ - A valid macro is a ``name : str`` and a ``value : str | None``. - - >>> Compiler._is_valid_macro('foo', None) - True - """ - return isinstance(name, str) and isinstance(value, (str, type(None))) - - # -- Bookkeeping methods ------------------------------------------- - - def define_macro(self, name: str, value: str | None = None) -> None: - """Define a preprocessor macro for all compilations driven by this - compiler object. The optional parameter 'value' should be a - string; if it is not supplied, then the macro will be defined - without an explicit value and the exact outcome depends on the - compiler used (XXX true? does ANSI say anything about this?) - """ - # Delete from the list of macro definitions/undefinitions if - # already there (so that this one will take precedence). - i = self._find_macro(name) - if i is not None: - del self.macros[i] - - self.macros.append((name, value)) - - def undefine_macro(self, name: str) -> None: - """Undefine a preprocessor macro for all compilations driven by - this compiler object. If the same macro is defined by - 'define_macro()' and undefined by 'undefine_macro()' the last call - takes precedence (including multiple redefinitions or - undefinitions). If the macro is redefined/undefined on a - per-compilation basis (ie. in the call to 'compile()'), then that - takes precedence. - """ - # Delete from the list of macro definitions/undefinitions if - # already there (so that this one will take precedence). - i = self._find_macro(name) - if i is not None: - del self.macros[i] - - undefn = (name,) - self.macros.append(undefn) - - def add_include_dir(self, dir: str) -> None: - """Add 'dir' to the list of directories that will be searched for - header files. The compiler is instructed to search directories in - the order in which they are supplied by successive calls to - 'add_include_dir()'. - """ - self.include_dirs.append(dir) - - def set_include_dirs(self, dirs: list[str]) -> None: - """Set the list of directories that will be searched to 'dirs' (a - list of strings). Overrides any preceding calls to - 'add_include_dir()'; subsequence calls to 'add_include_dir()' add - to the list passed to 'set_include_dirs()'. This does not affect - any list of standard include directories that the compiler may - search by default. - """ - self.include_dirs = dirs[:] - - def add_library(self, libname: str) -> None: - """Add 'libname' to the list of libraries that will be included in - all links driven by this compiler object. Note that 'libname' - should *not* be the name of a file containing a library, but the - name of the library itself: the actual filename will be inferred by - the linker, the compiler, or the compiler class (depending on the - platform). - - The linker will be instructed to link against libraries in the - order they were supplied to 'add_library()' and/or - 'set_libraries()'. It is perfectly valid to duplicate library - names; the linker will be instructed to link against libraries as - many times as they are mentioned. - """ - self.libraries.append(libname) - - def set_libraries(self, libnames: list[str]) -> None: - """Set the list of libraries to be included in all links driven by - this compiler object to 'libnames' (a list of strings). This does - not affect any standard system libraries that the linker may - include by default. - """ - self.libraries = libnames[:] - - def add_library_dir(self, dir: str) -> None: - """Add 'dir' to the list of directories that will be searched for - libraries specified to 'add_library()' and 'set_libraries()'. The - linker will be instructed to search for libraries in the order they - are supplied to 'add_library_dir()' and/or 'set_library_dirs()'. - """ - self.library_dirs.append(dir) - - def set_library_dirs(self, dirs: list[str]) -> None: - """Set the list of library search directories to 'dirs' (a list of - strings). This does not affect any standard library search path - that the linker may search by default. - """ - self.library_dirs = dirs[:] - - def add_runtime_library_dir(self, dir: str) -> None: - """Add 'dir' to the list of directories that will be searched for - shared libraries at runtime. - """ - self.runtime_library_dirs.append(dir) - - def set_runtime_library_dirs(self, dirs: list[str]) -> None: - """Set the list of directories to search for shared libraries at - runtime to 'dirs' (a list of strings). This does not affect any - standard search path that the runtime linker may search by - default. - """ - self.runtime_library_dirs = dirs[:] - - def add_link_object(self, object: str) -> None: - """Add 'object' to the list of object files (or analogues, such as - explicitly named library files or the output of "resource - compilers") to be included in every link driven by this compiler - object. - """ - self.objects.append(object) - - def set_link_objects(self, objects: list[str]) -> None: - """Set the list of object files (or analogues) to be included in - every link to 'objects'. This does not affect any standard object - files that the linker may include by default (such as system - libraries). - """ - self.objects = objects[:] - - # -- Private utility methods -------------------------------------- - # (here for the convenience of subclasses) - - # Helper method to prep compiler in subclass compile() methods - - def _setup_compile( - self, - outdir: str | None, - macros: list[_Macro] | None, - incdirs: list[str] | tuple[str, ...] | None, - sources, - depends, - extra, - ): - """Process arguments and decide which source files to compile.""" - outdir, macros, incdirs = self._fix_compile_args(outdir, macros, incdirs) - - if extra is None: - extra = [] - - # Get the list of expected output (object) files - objects = self.object_filenames(sources, strip_dir=False, output_dir=outdir) - assert len(objects) == len(sources) - - pp_opts = gen_preprocess_options(macros, incdirs) - - build = {} - for i in range(len(sources)): - src = sources[i] - obj = objects[i] - ext = os.path.splitext(src)[1] - self.mkpath(os.path.dirname(obj)) - build[obj] = (src, ext) - - return macros, objects, extra, pp_opts, build - - def _get_cc_args(self, pp_opts, debug, before): - # works for unixccompiler, cygwinccompiler - cc_args = pp_opts + ['-c'] - if debug: - cc_args[:0] = ['-g'] - if before: - cc_args[:0] = before - return cc_args - - def _fix_compile_args( - self, - output_dir: str | None, - macros: list[_Macro] | None, - include_dirs: list[str] | tuple[str, ...] | None, - ) -> tuple[str, list[_Macro], list[str]]: - """Typecheck and fix-up some of the arguments to the 'compile()' - method, and return fixed-up values. Specifically: if 'output_dir' - is None, replaces it with 'self.output_dir'; ensures that 'macros' - is a list, and augments it with 'self.macros'; ensures that - 'include_dirs' is a list, and augments it with 'self.include_dirs'. - Guarantees that the returned values are of the correct type, - i.e. for 'output_dir' either string or None, and for 'macros' and - 'include_dirs' either list or None. - """ - if output_dir is None: - output_dir = self.output_dir - elif not isinstance(output_dir, str): - raise TypeError("'output_dir' must be a string or None") - - if macros is None: - macros = list(self.macros) - elif isinstance(macros, list): - macros = macros + (self.macros or []) - else: - raise TypeError("'macros' (if supplied) must be a list of tuples") - - if include_dirs is None: - include_dirs = list(self.include_dirs) - elif isinstance(include_dirs, (list, tuple)): - include_dirs = list(include_dirs) + (self.include_dirs or []) - else: - raise TypeError("'include_dirs' (if supplied) must be a list of strings") - - # add include dirs for class - include_dirs += self.__class__.include_dirs - - return output_dir, macros, include_dirs - - def _prep_compile(self, sources, output_dir, depends=None): - """Decide which source files must be recompiled. - - Determine the list of object files corresponding to 'sources', - and figure out which ones really need to be recompiled. - Return a list of all object files and a dictionary telling - which source files can be skipped. - """ - # Get the list of expected output (object) files - objects = self.object_filenames(sources, output_dir=output_dir) - assert len(objects) == len(sources) - - # Return an empty dict for the "which source files can be skipped" - # return value to preserve API compatibility. - return objects, {} - - def _fix_object_args( - self, objects: list[str] | tuple[str, ...], output_dir: str | None - ) -> tuple[list[str], str]: - """Typecheck and fix up some arguments supplied to various methods. - Specifically: ensure that 'objects' is a list; if output_dir is - None, replace with self.output_dir. Return fixed versions of - 'objects' and 'output_dir'. - """ - if not isinstance(objects, (list, tuple)): - raise TypeError("'objects' must be a list or tuple of strings") - objects = list(objects) - - if output_dir is None: - output_dir = self.output_dir - elif not isinstance(output_dir, str): - raise TypeError("'output_dir' must be a string or None") - - return (objects, output_dir) - - def _fix_lib_args( - self, - libraries: list[str] | tuple[str, ...] | None, - library_dirs: list[str] | tuple[str, ...] | None, - runtime_library_dirs: list[str] | tuple[str, ...] | None, - ) -> tuple[list[str], list[str], list[str]]: - """Typecheck and fix up some of the arguments supplied to the - 'link_*' methods. Specifically: ensure that all arguments are - lists, and augment them with their permanent versions - (eg. 'self.libraries' augments 'libraries'). Return a tuple with - fixed versions of all arguments. - """ - if libraries is None: - libraries = list(self.libraries) - elif isinstance(libraries, (list, tuple)): - libraries = list(libraries) + (self.libraries or []) - else: - raise TypeError("'libraries' (if supplied) must be a list of strings") - - if library_dirs is None: - library_dirs = list(self.library_dirs) - elif isinstance(library_dirs, (list, tuple)): - library_dirs = list(library_dirs) + (self.library_dirs or []) - else: - raise TypeError("'library_dirs' (if supplied) must be a list of strings") - - # add library dirs for class - library_dirs += self.__class__.library_dirs - - if runtime_library_dirs is None: - runtime_library_dirs = list(self.runtime_library_dirs) - elif isinstance(runtime_library_dirs, (list, tuple)): - runtime_library_dirs = list(runtime_library_dirs) + ( - self.runtime_library_dirs or [] - ) - else: - raise TypeError( - "'runtime_library_dirs' (if supplied) must be a list of strings" - ) - - return (libraries, library_dirs, runtime_library_dirs) - - def _need_link(self, objects, output_file): - """Return true if we need to relink the files listed in 'objects' - to recreate 'output_file'. - """ - if self.force: - return True - else: - if self.dry_run: - newer = newer_group(objects, output_file, missing='newer') - else: - newer = newer_group(objects, output_file) - return newer - - def detect_language(self, sources: str | list[str]) -> str | None: - """Detect the language of a given file, or list of files. Uses - language_map, and language_order to do the job. - """ - if not isinstance(sources, list): - sources = [sources] - lang = None - index = len(self.language_order) - for source in sources: - base, ext = os.path.splitext(source) - extlang = self.language_map.get(ext) - try: - extindex = self.language_order.index(extlang) - if extindex < index: - lang = extlang - index = extindex - except ValueError: - pass - return lang - - # -- Worker methods ------------------------------------------------ - # (must be implemented by subclasses) - - def preprocess( - self, - source: str | os.PathLike[str], - output_file: str | os.PathLike[str] | None = None, - macros: list[_Macro] | None = None, - include_dirs: list[str] | tuple[str, ...] | None = None, - extra_preargs: list[str] | None = None, - extra_postargs: Iterable[str] | None = None, - ): - """Preprocess a single C/C++ source file, named in 'source'. - Output will be written to file named 'output_file', or stdout if - 'output_file' not supplied. 'macros' is a list of macro - definitions as for 'compile()', which will augment the macros set - with 'define_macro()' and 'undefine_macro()'. 'include_dirs' is a - list of directory names that will be added to the default list. - - Raises PreprocessError on failure. - """ - pass - - def compile( - self, - sources: Sequence[str | os.PathLike[str]], - output_dir: str | None = None, - macros: list[_Macro] | None = None, - include_dirs: list[str] | tuple[str, ...] | None = None, - debug: bool = False, - extra_preargs: list[str] | None = None, - extra_postargs: list[str] | None = None, - depends: list[str] | tuple[str, ...] | None = None, - ) -> list[str]: - """Compile one or more source files. - - 'sources' must be a list of filenames, most likely C/C++ - files, but in reality anything that can be handled by a - particular compiler and compiler class (eg. MSVCCompiler can - handle resource files in 'sources'). Return a list of object - filenames, one per source filename in 'sources'. Depending on - the implementation, not all source files will necessarily be - compiled, but all corresponding object filenames will be - returned. - - If 'output_dir' is given, object files will be put under it, while - retaining their original path component. That is, "foo/bar.c" - normally compiles to "foo/bar.o" (for a Unix implementation); if - 'output_dir' is "build", then it would compile to - "build/foo/bar.o". - - 'macros', if given, must be a list of macro definitions. A macro - definition is either a (name, value) 2-tuple or a (name,) 1-tuple. - The former defines a macro; if the value is None, the macro is - defined without an explicit value. The 1-tuple case undefines a - macro. Later definitions/redefinitions/ undefinitions take - precedence. - - 'include_dirs', if given, must be a list of strings, the - directories to add to the default include file search path for this - compilation only. - - 'debug' is a boolean; if true, the compiler will be instructed to - output debug symbols in (or alongside) the object file(s). - - 'extra_preargs' and 'extra_postargs' are implementation- dependent. - On platforms that have the notion of a command-line (e.g. Unix, - DOS/Windows), they are most likely lists of strings: extra - command-line arguments to prepend/append to the compiler command - line. On other platforms, consult the implementation class - documentation. In any event, they are intended as an escape hatch - for those occasions when the abstract compiler framework doesn't - cut the mustard. - - 'depends', if given, is a list of filenames that all targets - depend on. If a source file is older than any file in - depends, then the source file will be recompiled. This - supports dependency tracking, but only at a coarse - granularity. - - Raises CompileError on failure. - """ - # A concrete compiler class can either override this method - # entirely or implement _compile(). - macros, objects, extra_postargs, pp_opts, build = self._setup_compile( - output_dir, macros, include_dirs, sources, depends, extra_postargs - ) - cc_args = self._get_cc_args(pp_opts, debug, extra_preargs) - - for obj in objects: - try: - src, ext = build[obj] - except KeyError: - continue - self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts) - - # Return *all* object filenames, not just the ones we just built. - return objects - - def _compile(self, obj, src, ext, cc_args, extra_postargs, pp_opts): - """Compile 'src' to product 'obj'.""" - # A concrete compiler class that does not override compile() - # should implement _compile(). - pass - - def create_static_lib( - self, - objects: list[str] | tuple[str, ...], - output_libname: str, - output_dir: str | None = None, - debug: bool = False, - target_lang: str | None = None, - ) -> None: - """Link a bunch of stuff together to create a static library file. - The "bunch of stuff" consists of the list of object files supplied - as 'objects', the extra object files supplied to - 'add_link_object()' and/or 'set_link_objects()', the libraries - supplied to 'add_library()' and/or 'set_libraries()', and the - libraries supplied as 'libraries' (if any). - - 'output_libname' should be a library name, not a filename; the - filename will be inferred from the library name. 'output_dir' is - the directory where the library file will be put. - - 'debug' is a boolean; if true, debugging information will be - included in the library (note that on most platforms, it is the - compile step where this matters: the 'debug' flag is included here - just for consistency). - - 'target_lang' is the target language for which the given objects - are being compiled. This allows specific linkage time treatment of - certain languages. - - Raises LibError on failure. - """ - pass - - # values for target_desc parameter in link() - SHARED_OBJECT = "shared_object" - SHARED_LIBRARY = "shared_library" - EXECUTABLE = "executable" - - def link( - self, - target_desc: str, - objects: list[str] | tuple[str, ...], - output_filename: str, - output_dir: str | None = None, - libraries: list[str] | tuple[str, ...] | None = None, - library_dirs: list[str] | tuple[str, ...] | None = None, - runtime_library_dirs: list[str] | tuple[str, ...] | None = None, - export_symbols: Iterable[str] | None = None, - debug: bool = False, - extra_preargs: list[str] | None = None, - extra_postargs: list[str] | None = None, - build_temp: str | os.PathLike[str] | None = None, - target_lang: str | None = None, - ): - """Link a bunch of stuff together to create an executable or - shared library file. - - The "bunch of stuff" consists of the list of object files supplied - as 'objects'. 'output_filename' should be a filename. If - 'output_dir' is supplied, 'output_filename' is relative to it - (i.e. 'output_filename' can provide directory components if - needed). - - 'libraries' is a list of libraries to link against. These are - library names, not filenames, since they're translated into - filenames in a platform-specific way (eg. "foo" becomes "libfoo.a" - on Unix and "foo.lib" on DOS/Windows). However, they can include a - directory component, which means the linker will look in that - specific directory rather than searching all the normal locations. - - 'library_dirs', if supplied, should be a list of directories to - search for libraries that were specified as bare library names - (ie. no directory component). These are on top of the system - default and those supplied to 'add_library_dir()' and/or - 'set_library_dirs()'. 'runtime_library_dirs' is a list of - directories that will be embedded into the shared library and used - to search for other shared libraries that *it* depends on at - run-time. (This may only be relevant on Unix.) - - 'export_symbols' is a list of symbols that the shared library will - export. (This appears to be relevant only on Windows.) - - 'debug' is as for 'compile()' and 'create_static_lib()', with the - slight distinction that it actually matters on most platforms (as - opposed to 'create_static_lib()', which includes a 'debug' flag - mostly for form's sake). - - 'extra_preargs' and 'extra_postargs' are as for 'compile()' (except - of course that they supply command-line arguments for the - particular linker being used). - - 'target_lang' is the target language for which the given objects - are being compiled. This allows specific linkage time treatment of - certain languages. - - Raises LinkError on failure. - """ - raise NotImplementedError - - # Old 'link_*()' methods, rewritten to use the new 'link()' method. - - def link_shared_lib( - self, - objects: list[str] | tuple[str, ...], - output_libname: str, - output_dir: str | None = None, - libraries: list[str] | tuple[str, ...] | None = None, - library_dirs: list[str] | tuple[str, ...] | None = None, - runtime_library_dirs: list[str] | tuple[str, ...] | None = None, - export_symbols: Iterable[str] | None = None, - debug: bool = False, - extra_preargs: list[str] | None = None, - extra_postargs: list[str] | None = None, - build_temp: str | os.PathLike[str] | None = None, - target_lang: str | None = None, - ): - self.link( - Compiler.SHARED_LIBRARY, - objects, - self.library_filename(output_libname, lib_type='shared'), - output_dir, - libraries, - library_dirs, - runtime_library_dirs, - export_symbols, - debug, - extra_preargs, - extra_postargs, - build_temp, - target_lang, - ) - - def link_shared_object( - self, - objects: list[str] | tuple[str, ...], - output_filename: str, - output_dir: str | None = None, - libraries: list[str] | tuple[str, ...] | None = None, - library_dirs: list[str] | tuple[str, ...] | None = None, - runtime_library_dirs: list[str] | tuple[str, ...] | None = None, - export_symbols: Iterable[str] | None = None, - debug: bool = False, - extra_preargs: list[str] | None = None, - extra_postargs: list[str] | None = None, - build_temp: str | os.PathLike[str] | None = None, - target_lang: str | None = None, - ): - self.link( - Compiler.SHARED_OBJECT, - objects, - output_filename, - output_dir, - libraries, - library_dirs, - runtime_library_dirs, - export_symbols, - debug, - extra_preargs, - extra_postargs, - build_temp, - target_lang, - ) - - def link_executable( - self, - objects: list[str] | tuple[str, ...], - output_progname: str, - output_dir: str | None = None, - libraries: list[str] | tuple[str, ...] | None = None, - library_dirs: list[str] | tuple[str, ...] | None = None, - runtime_library_dirs: list[str] | tuple[str, ...] | None = None, - debug: bool = False, - extra_preargs: list[str] | None = None, - extra_postargs: list[str] | None = None, - target_lang: str | None = None, - ): - self.link( - Compiler.EXECUTABLE, - objects, - self.executable_filename(output_progname), - output_dir, - libraries, - library_dirs, - runtime_library_dirs, - None, - debug, - extra_preargs, - extra_postargs, - None, - target_lang, - ) - - # -- Miscellaneous methods ----------------------------------------- - # These are all used by the 'gen_lib_options() function; there is - # no appropriate default implementation so subclasses should - # implement all of these. - - def library_dir_option(self, dir: str) -> str: - """Return the compiler option to add 'dir' to the list of - directories searched for libraries. - """ - raise NotImplementedError - - def runtime_library_dir_option(self, dir: str) -> str: - """Return the compiler option to add 'dir' to the list of - directories searched for runtime libraries. - """ - raise NotImplementedError - - def library_option(self, lib: str) -> str: - """Return the compiler option to add 'lib' to the list of libraries - linked into the shared library or executable. - """ - raise NotImplementedError - - def has_function( # noqa: C901 - self, - funcname: str, - includes: Iterable[str] | None = None, - include_dirs: list[str] | tuple[str, ...] | None = None, - libraries: list[str] | None = None, - library_dirs: list[str] | tuple[str, ...] | None = None, - ) -> bool: - """Return a boolean indicating whether funcname is provided as - a symbol on the current platform. The optional arguments can - be used to augment the compilation environment. - - The libraries argument is a list of flags to be passed to the - linker to make additional symbol definitions available for - linking. - - The includes and include_dirs arguments are deprecated. - Usually, supplying include files with function declarations - will cause function detection to fail even in cases where the - symbol is available for linking. - - """ - # this can't be included at module scope because it tries to - # import math which might not be available at that point - maybe - # the necessary logic should just be inlined? - import tempfile - - if includes is None: - includes = [] - else: - warnings.warn("includes is deprecated", DeprecationWarning) - if include_dirs is None: - include_dirs = [] - else: - warnings.warn("include_dirs is deprecated", DeprecationWarning) - if libraries is None: - libraries = [] - if library_dirs is None: - library_dirs = [] - fd, fname = tempfile.mkstemp(".c", funcname, text=True) - with os.fdopen(fd, "w", encoding='utf-8') as f: - for incl in includes: - f.write(f"""#include "{incl}"\n""") - if not includes: - # Use "char func(void);" as the prototype to follow - # what autoconf does. This prototype does not match - # any well-known function the compiler might recognize - # as a builtin, so this ends up as a true link test. - # Without a fake prototype, the test would need to - # know the exact argument types, and the has_function - # interface does not provide that level of information. - f.write( - f"""\ -#ifdef __cplusplus -extern "C" -#endif -char {funcname}(void); -""" - ) - f.write( - f"""\ -int main (int argc, char **argv) {{ - {funcname}(); - return 0; -}} -""" - ) - - try: - objects = self.compile([fname], include_dirs=include_dirs) - except CompileError: - return False - finally: - os.remove(fname) - - try: - self.link_executable( - objects, "a.out", libraries=libraries, library_dirs=library_dirs - ) - except (LinkError, TypeError): - return False - else: - os.remove( - self.executable_filename("a.out", output_dir=self.output_dir or '') - ) - finally: - for fn in objects: - os.remove(fn) - return True - - def find_library_file( - self, dirs: Iterable[str], lib: str, debug: bool = False - ) -> str | None: - """Search the specified list of directories for a static or shared - library file 'lib' and return the full path to that file. If - 'debug' true, look for a debugging version (if that makes sense on - the current platform). Return None if 'lib' wasn't found in any of - the specified directories. - """ - raise NotImplementedError - - # -- Filename generation methods ----------------------------------- - - # The default implementation of the filename generating methods are - # prejudiced towards the Unix/DOS/Windows view of the world: - # * object files are named by replacing the source file extension - # (eg. .c/.cpp -> .o/.obj) - # * library files (shared or static) are named by plugging the - # library name and extension into a format string, eg. - # "lib%s.%s" % (lib_name, ".a") for Unix static libraries - # * executables are named by appending an extension (possibly - # empty) to the program name: eg. progname + ".exe" for - # Windows - # - # To reduce redundant code, these methods expect to find - # several attributes in the current object (presumably defined - # as class attributes): - # * src_extensions - - # list of C/C++ source file extensions, eg. ['.c', '.cpp'] - # * obj_extension - - # object file extension, eg. '.o' or '.obj' - # * static_lib_extension - - # extension for static library files, eg. '.a' or '.lib' - # * shared_lib_extension - - # extension for shared library/object files, eg. '.so', '.dll' - # * static_lib_format - - # format string for generating static library filenames, - # eg. 'lib%s.%s' or '%s.%s' - # * shared_lib_format - # format string for generating shared library filenames - # (probably same as static_lib_format, since the extension - # is one of the intended parameters to the format string) - # * exe_extension - - # extension for executable files, eg. '' or '.exe' - - def object_filenames( - self, - source_filenames: Iterable[str | os.PathLike[str]], - strip_dir: bool = False, - output_dir: str | os.PathLike[str] | None = '', - ) -> list[str]: - if output_dir is None: - output_dir = '' - return list( - self._make_out_path(output_dir, strip_dir, src_name) - for src_name in source_filenames - ) - - @property - def out_extensions(self): - return dict.fromkeys(self.src_extensions, self.obj_extension) - - def _make_out_path(self, output_dir, strip_dir, src_name): - return self._make_out_path_exts( - output_dir, strip_dir, src_name, self.out_extensions - ) - - @classmethod - def _make_out_path_exts(cls, output_dir, strip_dir, src_name, extensions): - r""" - >>> exts = {'.c': '.o'} - >>> Compiler._make_out_path_exts('.', False, '/foo/bar.c', exts).replace('\\', '/') - './foo/bar.o' - >>> Compiler._make_out_path_exts('.', True, '/foo/bar.c', exts).replace('\\', '/') - './bar.o' - """ - src = pathlib.PurePath(src_name) - # Ensure base is relative to honor output_dir (python/cpython#37775). - base = cls._make_relative(src) - try: - new_ext = extensions[src.suffix] - except LookupError: - raise UnknownFileType(f"unknown file type '{src.suffix}' (from '{src}')") - if strip_dir: - base = pathlib.PurePath(base.name) - return os.path.join(output_dir, base.with_suffix(new_ext)) - - @staticmethod - def _make_relative(base: pathlib.Path): - return base.relative_to(base.anchor) - - @overload - def shared_object_filename( - self, - basename: str, - strip_dir: Literal[False] = False, - output_dir: str | os.PathLike[str] = "", - ) -> str: ... - @overload - def shared_object_filename( - self, - basename: str | os.PathLike[str], - strip_dir: Literal[True], - output_dir: str | os.PathLike[str] = "", - ) -> str: ... - def shared_object_filename( - self, - basename: str | os.PathLike[str], - strip_dir: bool = False, - output_dir: str | os.PathLike[str] = '', - ) -> str: - assert output_dir is not None - if strip_dir: - basename = os.path.basename(basename) - return os.path.join(output_dir, basename + self.shared_lib_extension) - - @overload - def executable_filename( - self, - basename: str, - strip_dir: Literal[False] = False, - output_dir: str | os.PathLike[str] = "", - ) -> str: ... - @overload - def executable_filename( - self, - basename: str | os.PathLike[str], - strip_dir: Literal[True], - output_dir: str | os.PathLike[str] = "", - ) -> str: ... - def executable_filename( - self, - basename: str | os.PathLike[str], - strip_dir: bool = False, - output_dir: str | os.PathLike[str] = '', - ) -> str: - assert output_dir is not None - if strip_dir: - basename = os.path.basename(basename) - return os.path.join(output_dir, basename + (self.exe_extension or '')) - - def library_filename( - self, - libname: str, - lib_type: str = "static", - strip_dir: bool = False, - output_dir: str | os.PathLike[str] = "", # or 'shared' - ): - assert output_dir is not None - expected = '"static", "shared", "dylib", "xcode_stub"' - if lib_type not in eval(expected): - raise ValueError(f"'lib_type' must be {expected}") - fmt = getattr(self, lib_type + "_lib_format") - ext = getattr(self, lib_type + "_lib_extension") - - dir, base = os.path.split(libname) - filename = fmt % (base, ext) - if strip_dir: - dir = '' - - return os.path.join(output_dir, dir, filename) - - # -- Utility methods ----------------------------------------------- - - def announce(self, msg: object, level: int = 1) -> None: - log.debug(msg) - - def debug_print(self, msg: object) -> None: - from distutils.debug import DEBUG - - if DEBUG: - print(msg) - - def warn(self, msg: object) -> None: - sys.stderr.write(f"warning: {msg}\n") - - def execute( - self, - func: Callable[[Unpack[_Ts]], object], - args: tuple[Unpack[_Ts]], - msg: object = None, - level: int = 1, - ) -> None: - execute(func, args, msg, self.dry_run) - - def spawn( - self, cmd: MutableSequence[bytes | str | os.PathLike[str]], **kwargs - ) -> None: - spawn(cmd, dry_run=self.dry_run, **kwargs) - - @overload - def move_file( - self, src: str | os.PathLike[str], dst: _StrPathT - ) -> _StrPathT | str: ... - @overload - def move_file( - self, src: bytes | os.PathLike[bytes], dst: _BytesPathT - ) -> _BytesPathT | bytes: ... - def move_file( - self, - src: str | os.PathLike[str] | bytes | os.PathLike[bytes], - dst: str | os.PathLike[str] | bytes | os.PathLike[bytes], - ) -> str | os.PathLike[str] | bytes | os.PathLike[bytes]: - return move_file(src, dst, dry_run=self.dry_run) - - def mkpath(self, name, mode=0o777): - mkpath(name, mode, dry_run=self.dry_run) - - -# Map a sys.platform/os.name ('posix', 'nt') to the default compiler -# type for that platform. Keys are interpreted as re match -# patterns. Order is important; platform mappings are preferred over -# OS names. -_default_compilers = ( - # Platform string mappings - # on a cygwin built python we can use gcc like an ordinary UNIXish - # compiler - ('cygwin.*', 'unix'), - ('zos', 'zos'), - # OS name mappings - ('posix', 'unix'), - ('nt', 'msvc'), -) - - -def get_default_compiler(osname: str | None = None, platform: str | None = None) -> str: - """Determine the default compiler to use for the given platform. - - osname should be one of the standard Python OS names (i.e. the - ones returned by os.name) and platform the common value - returned by sys.platform for the platform in question. - - The default values are os.name and sys.platform in case the - parameters are not given. - """ - if osname is None: - osname = os.name - if platform is None: - platform = sys.platform - # Mingw is a special case where sys.platform is 'win32' but we - # want to use the 'mingw32' compiler, so check it first - if is_mingw(): - return 'mingw32' - for pattern, compiler in _default_compilers: - if ( - re.match(pattern, platform) is not None - or re.match(pattern, osname) is not None - ): - return compiler - # Default to Unix compiler - return 'unix' - - -# Map compiler types to (module_name, class_name) pairs -- ie. where to -# find the code that implements an interface to this compiler. (The module -# is assumed to be in the 'distutils' package.) -compiler_class = { - 'unix': ('unixccompiler', 'UnixCCompiler', "standard UNIX-style compiler"), - 'msvc': ('_msvccompiler', 'MSVCCompiler', "Microsoft Visual C++"), - 'cygwin': ( - 'cygwinccompiler', - 'CygwinCCompiler', - "Cygwin port of GNU C Compiler for Win32", - ), - 'mingw32': ( - 'cygwinccompiler', - 'Mingw32CCompiler', - "Mingw32 port of GNU C Compiler for Win32", - ), - 'bcpp': ('bcppcompiler', 'BCPPCompiler', "Borland C++ Compiler"), - 'zos': ('zosccompiler', 'zOSCCompiler', 'IBM XL C/C++ Compilers'), -} - - -def show_compilers() -> None: - """Print list of available compilers (used by the "--help-compiler" - options to "build", "build_ext", "build_clib"). - """ - # XXX this "knows" that the compiler option it's describing is - # "--compiler", which just happens to be the case for the three - # commands that use it. - from distutils.fancy_getopt import FancyGetopt - - compilers = sorted( - ("compiler=" + compiler, None, compiler_class[compiler][2]) - for compiler in compiler_class.keys() - ) - pretty_printer = FancyGetopt(compilers) - pretty_printer.print_help("List of available compilers:") - - -def new_compiler( - plat: str | None = None, - compiler: str | None = None, - verbose: bool = False, - dry_run: bool = False, - force: bool = False, -) -> Compiler: - """Generate an instance of some CCompiler subclass for the supplied - platform/compiler combination. 'plat' defaults to 'os.name' - (eg. 'posix', 'nt'), and 'compiler' defaults to the default compiler - for that platform. Currently only 'posix' and 'nt' are supported, and - the default compilers are "traditional Unix interface" (UnixCCompiler - class) and Visual C++ (MSVCCompiler class). Note that it's perfectly - possible to ask for a Unix compiler object under Windows, and a - Microsoft compiler object under Unix -- if you supply a value for - 'compiler', 'plat' is ignored. - """ - if plat is None: - plat = os.name - - try: - if compiler is None: - compiler = get_default_compiler(plat) - - (module_name, class_name, long_description) = compiler_class[compiler] - except KeyError: - msg = f"don't know how to compile C/C++ code on platform '{plat}'" - if compiler is not None: - msg = msg + f" with '{compiler}' compiler" - raise DistutilsPlatformError(msg) - - try: - module_name = "distutils." + module_name - __import__(module_name) - module = sys.modules[module_name] - klass = vars(module)[class_name] - except ImportError: - raise DistutilsModuleError( - f"can't compile C/C++ code: unable to load module '{module_name}'" - ) - except KeyError: - raise DistutilsModuleError( - f"can't compile C/C++ code: unable to find class '{class_name}' " - f"in module '{module_name}'" - ) - - # XXX The None is necessary to preserve backwards compatibility - # with classes that expect verbose to be the first positional - # argument. - return klass(None, dry_run, force) - - -def gen_preprocess_options( - macros: Iterable[_Macro], include_dirs: Iterable[str] -) -> list[str]: - """Generate C pre-processor options (-D, -U, -I) as used by at least - two types of compilers: the typical Unix compiler and Visual C++. - 'macros' is the usual thing, a list of 1- or 2-tuples, where (name,) - means undefine (-U) macro 'name', and (name,value) means define (-D) - macro 'name' to 'value'. 'include_dirs' is just a list of directory - names to be added to the header file search path (-I). Returns a list - of command-line options suitable for either Unix compilers or Visual - C++. - """ - # XXX it would be nice (mainly aesthetic, and so we don't generate - # stupid-looking command lines) to go over 'macros' and eliminate - # redundant definitions/undefinitions (ie. ensure that only the - # latest mention of a particular macro winds up on the command - # line). I don't think it's essential, though, since most (all?) - # Unix C compilers only pay attention to the latest -D or -U - # mention of a macro on their command line. Similar situation for - # 'include_dirs'. I'm punting on both for now. Anyways, weeding out - # redundancies like this should probably be the province of - # CCompiler, since the data structures used are inherited from it - # and therefore common to all CCompiler classes. - pp_opts = [] - for macro in macros: - if not (isinstance(macro, tuple) and 1 <= len(macro) <= 2): - raise TypeError( - f"bad macro definition '{macro}': " - "each element of 'macros' list must be a 1- or 2-tuple" - ) - - if len(macro) == 1: # undefine this macro - pp_opts.append(f"-U{macro[0]}") - elif len(macro) == 2: - if macro[1] is None: # define with no explicit value - pp_opts.append(f"-D{macro[0]}") - else: - # XXX *don't* need to be clever about quoting the - # macro value here, because we're going to avoid the - # shell at all costs when we spawn the command! - pp_opts.append("-D{}={}".format(*macro)) - - pp_opts.extend(f"-I{dir}" for dir in include_dirs) - return pp_opts - - -def gen_lib_options( - compiler: Compiler, - library_dirs: Iterable[str], - runtime_library_dirs: Iterable[str], - libraries: Iterable[str], -) -> list[str]: - """Generate linker options for searching library directories and - linking with specific libraries. 'libraries' and 'library_dirs' are, - respectively, lists of library names (not filenames!) and search - directories. Returns a list of command-line options suitable for use - with some compiler (depending on the two format strings passed in). - """ - lib_opts = [compiler.library_dir_option(dir) for dir in library_dirs] - - for dir in runtime_library_dirs: - lib_opts.extend(always_iterable(compiler.runtime_library_dir_option(dir))) - - # XXX it's important that we *not* remove redundant library mentions! - # sometimes you really do have to say "-lfoo -lbar -lfoo" in order to - # resolve all symbols. I just hope we never have to say "-lfoo obj.o - # -lbar" to get things to work -- that's certainly a possibility, but a - # pretty nasty way to arrange your C code. - - for lib in libraries: - (lib_dir, lib_name) = os.path.split(lib) - if lib_dir: - lib_file = compiler.find_library_file([lib_dir], lib_name) - if lib_file: - lib_opts.append(lib_file) - else: - compiler.warn( - f"no library file corresponding to '{lib}' found (skipping)" - ) - else: - lib_opts.append(compiler.library_option(lib)) - return lib_opts diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/cygwin.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/cygwin.py deleted file mode 100644 index bfabbb3..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/cygwin.py +++ /dev/null @@ -1,340 +0,0 @@ -"""distutils.cygwinccompiler - -Provides the CygwinCCompiler class, a subclass of UnixCCompiler that -handles the Cygwin port of the GNU C compiler to Windows. It also contains -the Mingw32CCompiler class which handles the mingw32 port of GCC (same as -cygwin in no-cygwin mode). -""" - -import copy -import os -import pathlib -import shlex -import sys -import warnings -from subprocess import check_output - -from ...errors import ( - DistutilsExecError, - DistutilsPlatformError, -) -from ...file_util import write_file -from ...sysconfig import get_config_vars -from ...version import LooseVersion, suppress_known_deprecation -from . import unix -from .errors import ( - CompileError, - Error, -) - - -def get_msvcr(): - """No longer needed, but kept for backward compatibility.""" - return [] - - -_runtime_library_dirs_msg = ( - "Unable to set runtime library search path on Windows, " - "usually indicated by `runtime_library_dirs` parameter to Extension" -) - - -class Compiler(unix.Compiler): - """Handles the Cygwin port of the GNU C compiler to Windows.""" - - compiler_type = 'cygwin' - obj_extension = ".o" - static_lib_extension = ".a" - shared_lib_extension = ".dll.a" - dylib_lib_extension = ".dll" - static_lib_format = "lib%s%s" - shared_lib_format = "lib%s%s" - dylib_lib_format = "cyg%s%s" - exe_extension = ".exe" - - def __init__(self, verbose=False, dry_run=False, force=False): - super().__init__(verbose, dry_run, force) - - status, details = check_config_h() - self.debug_print(f"Python's GCC status: {status} (details: {details})") - if status is not CONFIG_H_OK: - self.warn( - "Python's pyconfig.h doesn't seem to support your compiler. " - f"Reason: {details}. " - "Compiling may fail because of undefined preprocessor macros." - ) - - self.cc, self.cxx = get_config_vars('CC', 'CXX') - - # Override 'CC' and 'CXX' environment variables for - # building using MINGW compiler for MSVC python. - self.cc = os.environ.get('CC', self.cc or 'gcc') - self.cxx = os.environ.get('CXX', self.cxx or 'g++') - - self.linker_dll = self.cc - self.linker_dll_cxx = self.cxx - shared_option = "-shared" - - self.set_executables( - compiler=f'{self.cc} -mcygwin -O -Wall', - compiler_so=f'{self.cc} -mcygwin -mdll -O -Wall', - compiler_cxx=f'{self.cxx} -mcygwin -O -Wall', - compiler_so_cxx=f'{self.cxx} -mcygwin -mdll -O -Wall', - linker_exe=f'{self.cc} -mcygwin', - linker_so=f'{self.linker_dll} -mcygwin {shared_option}', - linker_exe_cxx=f'{self.cxx} -mcygwin', - linker_so_cxx=f'{self.linker_dll_cxx} -mcygwin {shared_option}', - ) - - self.dll_libraries = get_msvcr() - - @property - def gcc_version(self): - # Older numpy depended on this existing to check for ancient - # gcc versions. This doesn't make much sense with clang etc so - # just hardcode to something recent. - # https://github.com/numpy/numpy/pull/20333 - warnings.warn( - "gcc_version attribute of CygwinCCompiler is deprecated. " - "Instead of returning actual gcc version a fixed value 11.2.0 is returned.", - DeprecationWarning, - stacklevel=2, - ) - with suppress_known_deprecation(): - return LooseVersion("11.2.0") - - def _compile(self, obj, src, ext, cc_args, extra_postargs, pp_opts): - """Compiles the source by spawning GCC and windres if needed.""" - if ext in ('.rc', '.res'): - # gcc needs '.res' and '.rc' compiled to object files !!! - try: - self.spawn(["windres", "-i", src, "-o", obj]) - except DistutilsExecError as msg: - raise CompileError(msg) - else: # for other files use the C-compiler - try: - if self.detect_language(src) == 'c++': - self.spawn( - self.compiler_so_cxx - + cc_args - + [src, '-o', obj] - + extra_postargs - ) - else: - self.spawn( - self.compiler_so + cc_args + [src, '-o', obj] + extra_postargs - ) - except DistutilsExecError as msg: - raise CompileError(msg) - - def link( - self, - target_desc, - objects, - output_filename, - output_dir=None, - libraries=None, - library_dirs=None, - runtime_library_dirs=None, - export_symbols=None, - debug=False, - extra_preargs=None, - extra_postargs=None, - build_temp=None, - target_lang=None, - ): - """Link the objects.""" - # use separate copies, so we can modify the lists - extra_preargs = copy.copy(extra_preargs or []) - libraries = copy.copy(libraries or []) - objects = copy.copy(objects or []) - - if runtime_library_dirs: - self.warn(_runtime_library_dirs_msg) - - # Additional libraries - libraries.extend(self.dll_libraries) - - # handle export symbols by creating a def-file - # with executables this only works with gcc/ld as linker - if (export_symbols is not None) and ( - target_desc != self.EXECUTABLE or self.linker_dll == "gcc" - ): - # (The linker doesn't do anything if output is up-to-date. - # So it would probably better to check if we really need this, - # but for this we had to insert some unchanged parts of - # UnixCCompiler, and this is not what we want.) - - # we want to put some files in the same directory as the - # object files are, build_temp doesn't help much - # where are the object files - temp_dir = os.path.dirname(objects[0]) - # name of dll to give the helper files the same base name - (dll_name, dll_extension) = os.path.splitext( - os.path.basename(output_filename) - ) - - # generate the filenames for these files - def_file = os.path.join(temp_dir, dll_name + ".def") - - # Generate .def file - contents = [f"LIBRARY {os.path.basename(output_filename)}", "EXPORTS"] - contents.extend(export_symbols) - self.execute(write_file, (def_file, contents), f"writing {def_file}") - - # next add options for def-file - - # for gcc/ld the def-file is specified as any object files - objects.append(def_file) - - # end: if ((export_symbols is not None) and - # (target_desc != self.EXECUTABLE or self.linker_dll == "gcc")): - - # who wants symbols and a many times larger output file - # should explicitly switch the debug mode on - # otherwise we let ld strip the output file - # (On my machine: 10KiB < stripped_file < ??100KiB - # unstripped_file = stripped_file + XXX KiB - # ( XXX=254 for a typical python extension)) - if not debug: - extra_preargs.append("-s") - - super().link( - target_desc, - objects, - output_filename, - output_dir, - libraries, - library_dirs, - runtime_library_dirs, - None, # export_symbols, we do this in our def-file - debug, - extra_preargs, - extra_postargs, - build_temp, - target_lang, - ) - - def runtime_library_dir_option(self, dir): - # cygwin doesn't support rpath. While in theory we could error - # out like MSVC does, code might expect it to work like on Unix, so - # just warn and hope for the best. - self.warn(_runtime_library_dirs_msg) - return [] - - # -- Miscellaneous methods ----------------------------------------- - - def _make_out_path(self, output_dir, strip_dir, src_name): - # use normcase to make sure '.rc' is really '.rc' and not '.RC' - norm_src_name = os.path.normcase(src_name) - return super()._make_out_path(output_dir, strip_dir, norm_src_name) - - @property - def out_extensions(self): - """ - Add support for rc and res files. - """ - return { - **super().out_extensions, - **{ext: ext + self.obj_extension for ext in ('.res', '.rc')}, - } - - -# the same as cygwin plus some additional parameters -class MinGW32Compiler(Compiler): - """Handles the Mingw32 port of the GNU C compiler to Windows.""" - - compiler_type = 'mingw32' - - def __init__(self, verbose=False, dry_run=False, force=False): - super().__init__(verbose, dry_run, force) - - shared_option = "-shared" - - if is_cygwincc(self.cc): - raise Error('Cygwin gcc cannot be used with --compiler=mingw32') - - self.set_executables( - compiler=f'{self.cc} -O -Wall', - compiler_so=f'{self.cc} -shared -O -Wall', - compiler_so_cxx=f'{self.cxx} -shared -O -Wall', - compiler_cxx=f'{self.cxx} -O -Wall', - linker_exe=f'{self.cc}', - linker_so=f'{self.linker_dll} {shared_option}', - linker_exe_cxx=f'{self.cxx}', - linker_so_cxx=f'{self.linker_dll_cxx} {shared_option}', - ) - - def runtime_library_dir_option(self, dir): - raise DistutilsPlatformError(_runtime_library_dirs_msg) - - -# Because these compilers aren't configured in Python's pyconfig.h file by -# default, we should at least warn the user if he is using an unmodified -# version. - -CONFIG_H_OK = "ok" -CONFIG_H_NOTOK = "not ok" -CONFIG_H_UNCERTAIN = "uncertain" - - -def check_config_h(): - """Check if the current Python installation appears amenable to building - extensions with GCC. - - Returns a tuple (status, details), where 'status' is one of the following - constants: - - - CONFIG_H_OK: all is well, go ahead and compile - - CONFIG_H_NOTOK: doesn't look good - - CONFIG_H_UNCERTAIN: not sure -- unable to read pyconfig.h - - 'details' is a human-readable string explaining the situation. - - Note there are two ways to conclude "OK": either 'sys.version' contains - the string "GCC" (implying that this Python was built with GCC), or the - installed "pyconfig.h" contains the string "__GNUC__". - """ - - # XXX since this function also checks sys.version, it's not strictly a - # "pyconfig.h" check -- should probably be renamed... - - from distutils import sysconfig - - # if sys.version contains GCC then python was compiled with GCC, and the - # pyconfig.h file should be OK - if "GCC" in sys.version: - return CONFIG_H_OK, "sys.version mentions 'GCC'" - - # Clang would also work - if "Clang" in sys.version: - return CONFIG_H_OK, "sys.version mentions 'Clang'" - - # let's see if __GNUC__ is mentioned in python.h - fn = sysconfig.get_config_h_filename() - try: - config_h = pathlib.Path(fn).read_text(encoding='utf-8') - except OSError as exc: - return (CONFIG_H_UNCERTAIN, f"couldn't read '{fn}': {exc.strerror}") - else: - substring = '__GNUC__' - if substring in config_h: - code = CONFIG_H_OK - mention_inflected = 'mentions' - else: - code = CONFIG_H_NOTOK - mention_inflected = 'does not mention' - return code, f"{fn!r} {mention_inflected} {substring!r}" - - -def is_cygwincc(cc): - """Try to determine if the compiler that would be used is from cygwin.""" - out_string = check_output(shlex.split(cc) + ['-dumpmachine']) - return out_string.strip().endswith(b'cygwin') - - -get_versions = None -""" -A stand-in for the previous get_versions() function to prevent failures -when monkeypatched. See pypa/setuptools#2969. -""" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/errors.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/errors.py deleted file mode 100644 index 0132859..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/errors.py +++ /dev/null @@ -1,24 +0,0 @@ -class Error(Exception): - """Some compile/link operation failed.""" - - -class PreprocessError(Error): - """Failure to preprocess one or more C/C++ files.""" - - -class CompileError(Error): - """Failure to compile one or more C/C++ source files.""" - - -class LibError(Error): - """Failure to create a static library from one or more C/C++ object - files.""" - - -class LinkError(Error): - """Failure to link one or more C/C++ object files into an executable - or shared library file.""" - - -class UnknownFileType(Error): - """Attempt to process an unknown file type.""" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/msvc.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/msvc.py deleted file mode 100644 index 6db062a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/msvc.py +++ /dev/null @@ -1,614 +0,0 @@ -"""distutils._msvccompiler - -Contains MSVCCompiler, an implementation of the abstract CCompiler class -for Microsoft Visual Studio 2015. - -This module requires VS 2015 or later. -""" - -# Written by Perry Stoll -# hacked by Robin Becker and Thomas Heller to do a better job of -# finding DevStudio (through the registry) -# ported to VS 2005 and VS 2008 by Christian Heimes -# ported to VS 2015 by Steve Dower -from __future__ import annotations - -import contextlib -import os -import subprocess -import unittest.mock as mock -import warnings -from collections.abc import Iterable - -with contextlib.suppress(ImportError): - import winreg - -from itertools import count - -from ..._log import log -from ...errors import ( - DistutilsExecError, - DistutilsPlatformError, -) -from ...util import get_host_platform, get_platform -from . import base -from .base import gen_lib_options -from .errors import ( - CompileError, - LibError, - LinkError, -) - - -def _find_vc2015(): - try: - key = winreg.OpenKeyEx( - winreg.HKEY_LOCAL_MACHINE, - r"Software\Microsoft\VisualStudio\SxS\VC7", - access=winreg.KEY_READ | winreg.KEY_WOW64_32KEY, - ) - except OSError: - log.debug("Visual C++ is not registered") - return None, None - - best_version = 0 - best_dir = None - with key: - for i in count(): - try: - v, vc_dir, vt = winreg.EnumValue(key, i) - except OSError: - break - if v and vt == winreg.REG_SZ and os.path.isdir(vc_dir): - try: - version = int(float(v)) - except (ValueError, TypeError): - continue - if version >= 14 and version > best_version: - best_version, best_dir = version, vc_dir - return best_version, best_dir - - -def _find_vc2017(): - """Returns "15, path" based on the result of invoking vswhere.exe - If no install is found, returns "None, None" - - The version is returned to avoid unnecessarily changing the function - result. It may be ignored when the path is not None. - - If vswhere.exe is not available, by definition, VS 2017 is not - installed. - """ - root = os.environ.get("ProgramFiles(x86)") or os.environ.get("ProgramFiles") - if not root: - return None, None - - variant = 'arm64' if get_platform() == 'win-arm64' else 'x86.x64' - suitable_components = ( - f"Microsoft.VisualStudio.Component.VC.Tools.{variant}", - "Microsoft.VisualStudio.Workload.WDExpress", - ) - - for component in suitable_components: - # Workaround for `-requiresAny` (only available on VS 2017 > 15.6) - with contextlib.suppress( - subprocess.CalledProcessError, OSError, UnicodeDecodeError - ): - path = ( - subprocess.check_output([ - os.path.join( - root, "Microsoft Visual Studio", "Installer", "vswhere.exe" - ), - "-latest", - "-prerelease", - "-requires", - component, - "-property", - "installationPath", - "-products", - "*", - ]) - .decode(encoding="mbcs", errors="strict") - .strip() - ) - - path = os.path.join(path, "VC", "Auxiliary", "Build") - if os.path.isdir(path): - return 15, path - - return None, None # no suitable component found - - -PLAT_SPEC_TO_RUNTIME = { - 'x86': 'x86', - 'x86_amd64': 'x64', - 'x86_arm': 'arm', - 'x86_arm64': 'arm64', -} - - -def _find_vcvarsall(plat_spec): - # bpo-38597: Removed vcruntime return value - _, best_dir = _find_vc2017() - - if not best_dir: - best_version, best_dir = _find_vc2015() - - if not best_dir: - log.debug("No suitable Visual C++ version found") - return None, None - - vcvarsall = os.path.join(best_dir, "vcvarsall.bat") - if not os.path.isfile(vcvarsall): - log.debug("%s cannot be found", vcvarsall) - return None, None - - return vcvarsall, None - - -def _get_vc_env(plat_spec): - if os.getenv("DISTUTILS_USE_SDK"): - return {key.lower(): value for key, value in os.environ.items()} - - vcvarsall, _ = _find_vcvarsall(plat_spec) - if not vcvarsall: - raise DistutilsPlatformError( - 'Microsoft Visual C++ 14.0 or greater is required. ' - 'Get it with "Microsoft C++ Build Tools": ' - 'https://visualstudio.microsoft.com/visual-cpp-build-tools/' - ) - - try: - out = subprocess.check_output( - f'cmd /u /c "{vcvarsall}" {plat_spec} && set', - stderr=subprocess.STDOUT, - ).decode('utf-16le', errors='replace') - except subprocess.CalledProcessError as exc: - log.error(exc.output) - raise DistutilsPlatformError(f"Error executing {exc.cmd}") - - env = { - key.lower(): value - for key, _, value in (line.partition('=') for line in out.splitlines()) - if key and value - } - - return env - - -def _find_exe(exe, paths=None): - """Return path to an MSVC executable program. - - Tries to find the program in several places: first, one of the - MSVC program search paths from the registry; next, the directories - in the PATH environment variable. If any of those work, return an - absolute path that is known to exist. If none of them work, just - return the original program name, 'exe'. - """ - if not paths: - paths = os.getenv('path').split(os.pathsep) - for p in paths: - fn = os.path.join(os.path.abspath(p), exe) - if os.path.isfile(fn): - return fn - return exe - - -_vcvars_names = { - 'win32': 'x86', - 'win-amd64': 'amd64', - 'win-arm32': 'arm', - 'win-arm64': 'arm64', -} - - -def _get_vcvars_spec(host_platform, platform): - """ - Given a host platform and platform, determine the spec for vcvarsall. - - Uses the native MSVC host if the host platform would need expensive - emulation for x86. - - >>> _get_vcvars_spec('win-arm64', 'win32') - 'arm64_x86' - >>> _get_vcvars_spec('win-arm64', 'win-amd64') - 'arm64_amd64' - - Otherwise, always cross-compile from x86 to work with the - lighter-weight MSVC installs that do not include native 64-bit tools. - - >>> _get_vcvars_spec('win32', 'win32') - 'x86' - >>> _get_vcvars_spec('win-arm32', 'win-arm32') - 'x86_arm' - >>> _get_vcvars_spec('win-amd64', 'win-arm64') - 'x86_arm64' - """ - if host_platform != 'win-arm64': - host_platform = 'win32' - vc_hp = _vcvars_names[host_platform] - vc_plat = _vcvars_names[platform] - return vc_hp if vc_hp == vc_plat else f'{vc_hp}_{vc_plat}' - - -class Compiler(base.Compiler): - """Concrete class that implements an interface to Microsoft Visual C++, - as defined by the CCompiler abstract class.""" - - compiler_type = 'msvc' - - # Just set this so CCompiler's constructor doesn't barf. We currently - # don't use the 'set_executables()' bureaucracy provided by CCompiler, - # as it really isn't necessary for this sort of single-compiler class. - # Would be nice to have a consistent interface with UnixCCompiler, - # though, so it's worth thinking about. - executables = {} - - # Private class data (need to distinguish C from C++ source for compiler) - _c_extensions = ['.c'] - _cpp_extensions = ['.cc', '.cpp', '.cxx'] - _rc_extensions = ['.rc'] - _mc_extensions = ['.mc'] - - # Needed for the filename generation methods provided by the - # base class, CCompiler. - src_extensions = _c_extensions + _cpp_extensions + _rc_extensions + _mc_extensions - res_extension = '.res' - obj_extension = '.obj' - static_lib_extension = '.lib' - shared_lib_extension = '.dll' - static_lib_format = shared_lib_format = '%s%s' - exe_extension = '.exe' - - def __init__(self, verbose=False, dry_run=False, force=False) -> None: - super().__init__(verbose, dry_run, force) - # target platform (.plat_name is consistent with 'bdist') - self.plat_name = None - self.initialized = False - - @classmethod - def _configure(cls, vc_env): - """ - Set class-level include/lib dirs. - """ - cls.include_dirs = cls._parse_path(vc_env.get('include', '')) - cls.library_dirs = cls._parse_path(vc_env.get('lib', '')) - - @staticmethod - def _parse_path(val): - return [dir.rstrip(os.sep) for dir in val.split(os.pathsep) if dir] - - def initialize(self, plat_name: str | None = None) -> None: - # multi-init means we would need to check platform same each time... - assert not self.initialized, "don't init multiple times" - if plat_name is None: - plat_name = get_platform() - # sanity check for platforms to prevent obscure errors later. - if plat_name not in _vcvars_names: - raise DistutilsPlatformError( - f"--plat-name must be one of {tuple(_vcvars_names)}" - ) - - plat_spec = _get_vcvars_spec(get_host_platform(), plat_name) - - vc_env = _get_vc_env(plat_spec) - if not vc_env: - raise DistutilsPlatformError( - "Unable to find a compatible Visual Studio installation." - ) - self._configure(vc_env) - - self._paths = vc_env.get('path', '') - paths = self._paths.split(os.pathsep) - self.cc = _find_exe("cl.exe", paths) - self.linker = _find_exe("link.exe", paths) - self.lib = _find_exe("lib.exe", paths) - self.rc = _find_exe("rc.exe", paths) # resource compiler - self.mc = _find_exe("mc.exe", paths) # message compiler - self.mt = _find_exe("mt.exe", paths) # message compiler - - self.preprocess_options = None - # bpo-38597: Always compile with dynamic linking - # Future releases of Python 3.x will include all past - # versions of vcruntime*.dll for compatibility. - self.compile_options = ['/nologo', '/O2', '/W3', '/GL', '/DNDEBUG', '/MD'] - - self.compile_options_debug = [ - '/nologo', - '/Od', - '/MDd', - '/Zi', - '/W3', - '/D_DEBUG', - ] - - ldflags = ['/nologo', '/INCREMENTAL:NO', '/LTCG'] - - ldflags_debug = ['/nologo', '/INCREMENTAL:NO', '/LTCG', '/DEBUG:FULL'] - - self.ldflags_exe = [*ldflags, '/MANIFEST:EMBED,ID=1'] - self.ldflags_exe_debug = [*ldflags_debug, '/MANIFEST:EMBED,ID=1'] - self.ldflags_shared = [ - *ldflags, - '/DLL', - '/MANIFEST:EMBED,ID=2', - '/MANIFESTUAC:NO', - ] - self.ldflags_shared_debug = [ - *ldflags_debug, - '/DLL', - '/MANIFEST:EMBED,ID=2', - '/MANIFESTUAC:NO', - ] - self.ldflags_static = [*ldflags] - self.ldflags_static_debug = [*ldflags_debug] - - self._ldflags = { - (base.Compiler.EXECUTABLE, None): self.ldflags_exe, - (base.Compiler.EXECUTABLE, False): self.ldflags_exe, - (base.Compiler.EXECUTABLE, True): self.ldflags_exe_debug, - (base.Compiler.SHARED_OBJECT, None): self.ldflags_shared, - (base.Compiler.SHARED_OBJECT, False): self.ldflags_shared, - (base.Compiler.SHARED_OBJECT, True): self.ldflags_shared_debug, - (base.Compiler.SHARED_LIBRARY, None): self.ldflags_static, - (base.Compiler.SHARED_LIBRARY, False): self.ldflags_static, - (base.Compiler.SHARED_LIBRARY, True): self.ldflags_static_debug, - } - - self.initialized = True - - # -- Worker methods ------------------------------------------------ - - @property - def out_extensions(self) -> dict[str, str]: - return { - **super().out_extensions, - **{ - ext: self.res_extension - for ext in self._rc_extensions + self._mc_extensions - }, - } - - def compile( # noqa: C901 - self, - sources, - output_dir=None, - macros=None, - include_dirs=None, - debug=False, - extra_preargs=None, - extra_postargs=None, - depends=None, - ): - if not self.initialized: - self.initialize() - compile_info = self._setup_compile( - output_dir, macros, include_dirs, sources, depends, extra_postargs - ) - macros, objects, extra_postargs, pp_opts, build = compile_info - - compile_opts = extra_preargs or [] - compile_opts.append('/c') - if debug: - compile_opts.extend(self.compile_options_debug) - else: - compile_opts.extend(self.compile_options) - - add_cpp_opts = False - - for obj in objects: - try: - src, ext = build[obj] - except KeyError: - continue - if debug: - # pass the full pathname to MSVC in debug mode, - # this allows the debugger to find the source file - # without asking the user to browse for it - src = os.path.abspath(src) - - if ext in self._c_extensions: - input_opt = f"/Tc{src}" - elif ext in self._cpp_extensions: - input_opt = f"/Tp{src}" - add_cpp_opts = True - elif ext in self._rc_extensions: - # compile .RC to .RES file - input_opt = src - output_opt = "/fo" + obj - try: - self.spawn([self.rc] + pp_opts + [output_opt, input_opt]) - except DistutilsExecError as msg: - raise CompileError(msg) - continue - elif ext in self._mc_extensions: - # Compile .MC to .RC file to .RES file. - # * '-h dir' specifies the directory for the - # generated include file - # * '-r dir' specifies the target directory of the - # generated RC file and the binary message resource - # it includes - # - # For now (since there are no options to change this), - # we use the source-directory for the include file and - # the build directory for the RC file and message - # resources. This works at least for win32all. - h_dir = os.path.dirname(src) - rc_dir = os.path.dirname(obj) - try: - # first compile .MC to .RC and .H file - self.spawn([self.mc, '-h', h_dir, '-r', rc_dir, src]) - base, _ = os.path.splitext(os.path.basename(src)) - rc_file = os.path.join(rc_dir, base + '.rc') - # then compile .RC to .RES file - self.spawn([self.rc, "/fo" + obj, rc_file]) - - except DistutilsExecError as msg: - raise CompileError(msg) - continue - else: - # how to handle this file? - raise CompileError(f"Don't know how to compile {src} to {obj}") - - args = [self.cc] + compile_opts + pp_opts - if add_cpp_opts: - args.append('/EHsc') - args.extend((input_opt, "/Fo" + obj)) - args.extend(extra_postargs) - - try: - self.spawn(args) - except DistutilsExecError as msg: - raise CompileError(msg) - - return objects - - def create_static_lib( - self, - objects: list[str] | tuple[str, ...], - output_libname: str, - output_dir: str | None = None, - debug: bool = False, - target_lang: str | None = None, - ) -> None: - if not self.initialized: - self.initialize() - objects, output_dir = self._fix_object_args(objects, output_dir) - output_filename = self.library_filename(output_libname, output_dir=output_dir) - - if self._need_link(objects, output_filename): - lib_args = objects + ['/OUT:' + output_filename] - if debug: - pass # XXX what goes here? - try: - log.debug('Executing "%s" %s', self.lib, ' '.join(lib_args)) - self.spawn([self.lib] + lib_args) - except DistutilsExecError as msg: - raise LibError(msg) - else: - log.debug("skipping %s (up-to-date)", output_filename) - - def link( - self, - target_desc: str, - objects: list[str] | tuple[str, ...], - output_filename: str, - output_dir: str | None = None, - libraries: list[str] | tuple[str, ...] | None = None, - library_dirs: list[str] | tuple[str, ...] | None = None, - runtime_library_dirs: list[str] | tuple[str, ...] | None = None, - export_symbols: Iterable[str] | None = None, - debug: bool = False, - extra_preargs: list[str] | None = None, - extra_postargs: Iterable[str] | None = None, - build_temp: str | os.PathLike[str] | None = None, - target_lang: str | None = None, - ) -> None: - if not self.initialized: - self.initialize() - objects, output_dir = self._fix_object_args(objects, output_dir) - fixed_args = self._fix_lib_args(libraries, library_dirs, runtime_library_dirs) - libraries, library_dirs, runtime_library_dirs = fixed_args - - if runtime_library_dirs: - self.warn( - "I don't know what to do with 'runtime_library_dirs': " - + str(runtime_library_dirs) - ) - - lib_opts = gen_lib_options(self, library_dirs, runtime_library_dirs, libraries) - if output_dir is not None: - output_filename = os.path.join(output_dir, output_filename) - - if self._need_link(objects, output_filename): - ldflags = self._ldflags[target_desc, debug] - - export_opts = ["/EXPORT:" + sym for sym in (export_symbols or [])] - - ld_args = ( - ldflags + lib_opts + export_opts + objects + ['/OUT:' + output_filename] - ) - - # The MSVC linker generates .lib and .exp files, which cannot be - # suppressed by any linker switches. The .lib files may even be - # needed! Make sure they are generated in the temporary build - # directory. Since they have different names for debug and release - # builds, they can go into the same directory. - build_temp = os.path.dirname(objects[0]) - if export_symbols is not None: - (dll_name, dll_ext) = os.path.splitext( - os.path.basename(output_filename) - ) - implib_file = os.path.join(build_temp, self.library_filename(dll_name)) - ld_args.append('/IMPLIB:' + implib_file) - - if extra_preargs: - ld_args[:0] = extra_preargs - if extra_postargs: - ld_args.extend(extra_postargs) - - output_dir = os.path.dirname(os.path.abspath(output_filename)) - self.mkpath(output_dir) - try: - log.debug('Executing "%s" %s', self.linker, ' '.join(ld_args)) - self.spawn([self.linker] + ld_args) - except DistutilsExecError as msg: - raise LinkError(msg) - else: - log.debug("skipping %s (up-to-date)", output_filename) - - def spawn(self, cmd): - env = dict(os.environ, PATH=self._paths) - with self._fallback_spawn(cmd, env) as fallback: - return super().spawn(cmd, env=env) - return fallback.value - - @contextlib.contextmanager - def _fallback_spawn(self, cmd, env): - """ - Discovered in pypa/distutils#15, some tools monkeypatch the compiler, - so the 'env' kwarg causes a TypeError. Detect this condition and - restore the legacy, unsafe behavior. - """ - bag = type('Bag', (), {})() - try: - yield bag - except TypeError as exc: - if "unexpected keyword argument 'env'" not in str(exc): - raise - else: - return - warnings.warn("Fallback spawn triggered. Please update distutils monkeypatch.") - with mock.patch.dict('os.environ', env): - bag.value = super().spawn(cmd) - - # -- Miscellaneous methods ----------------------------------------- - # These are all used by the 'gen_lib_options() function, in - # ccompiler.py. - - def library_dir_option(self, dir): - return "/LIBPATH:" + dir - - def runtime_library_dir_option(self, dir): - raise DistutilsPlatformError( - "don't know how to set runtime library search path for MSVC" - ) - - def library_option(self, lib): - return self.library_filename(lib) - - def find_library_file(self, dirs, lib, debug=False): - # Prefer a debugging library if found (and requested), but deal - # with it if we don't have one. - if debug: - try_names = [lib + "_d", lib] - else: - try_names = [lib] - for dir in dirs: - for name in try_names: - libfile = os.path.join(dir, self.library_filename(name)) - if os.path.isfile(libfile): - return libfile - else: - # Oops, didn't find it in *any* of 'dirs' - return None diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_base.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_base.cpython-312.pyc deleted file mode 100644 index c3501bc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_base.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_cygwin.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_cygwin.cpython-312.pyc deleted file mode 100644 index 78f770e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_cygwin.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_mingw.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_mingw.cpython-312.pyc deleted file mode 100644 index 9e7a52c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_mingw.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_msvc.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_msvc.cpython-312.pyc deleted file mode 100644 index 829b2bb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_msvc.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_unix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_unix.cpython-312.pyc deleted file mode 100644 index a5cc6d8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/__pycache__/test_unix.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_base.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_base.py deleted file mode 100644 index a762e2b..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_base.py +++ /dev/null @@ -1,83 +0,0 @@ -import platform -import sysconfig -import textwrap - -import pytest - -from .. import base - -pytestmark = pytest.mark.usefixtures('suppress_path_mangle') - - -@pytest.fixture -def c_file(tmp_path): - c_file = tmp_path / 'foo.c' - gen_headers = ('Python.h',) - is_windows = platform.system() == "Windows" - plat_headers = ('windows.h',) * is_windows - all_headers = gen_headers + plat_headers - headers = '\n'.join(f'#include <{header}>\n' for header in all_headers) - payload = ( - textwrap.dedent( - """ - #headers - void PyInit_foo(void) {} - """ - ) - .lstrip() - .replace('#headers', headers) - ) - c_file.write_text(payload, encoding='utf-8') - return c_file - - -def test_set_include_dirs(c_file): - """ - Extensions should build even if set_include_dirs is invoked. - In particular, compiler-specific paths should not be overridden. - """ - compiler = base.new_compiler() - python = sysconfig.get_paths()['include'] - compiler.set_include_dirs([python]) - compiler.compile([c_file]) - - # do it again, setting include dirs after any initialization - compiler.set_include_dirs([python]) - compiler.compile([c_file]) - - -def test_has_function_prototype(): - # Issue https://github.com/pypa/setuptools/issues/3648 - # Test prototype-generating behavior. - - compiler = base.new_compiler() - - # Every C implementation should have these. - assert compiler.has_function('abort') - assert compiler.has_function('exit') - with pytest.deprecated_call(match='includes is deprecated'): - # abort() is a valid expression with the prototype. - assert compiler.has_function('abort', includes=['stdlib.h']) - with pytest.deprecated_call(match='includes is deprecated'): - # But exit() is not valid with the actual prototype in scope. - assert not compiler.has_function('exit', includes=['stdlib.h']) - # And setuptools_does_not_exist is not declared or defined at all. - assert not compiler.has_function('setuptools_does_not_exist') - with pytest.deprecated_call(match='includes is deprecated'): - assert not compiler.has_function( - 'setuptools_does_not_exist', includes=['stdio.h'] - ) - - -def test_include_dirs_after_multiple_compile_calls(c_file): - """ - Calling compile multiple times should not change the include dirs - (regression test for setuptools issue #3591). - """ - compiler = base.new_compiler() - python = sysconfig.get_paths()['include'] - compiler.set_include_dirs([python]) - compiler.compile([c_file]) - assert compiler.include_dirs == [python] - compiler.compile([c_file]) - assert compiler.include_dirs == [python] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_cygwin.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_cygwin.py deleted file mode 100644 index 9adf6b8..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_cygwin.py +++ /dev/null @@ -1,76 +0,0 @@ -"""Tests for distutils.cygwinccompiler.""" - -import os -import sys -from distutils import sysconfig -from distutils.tests import support - -import pytest - -from .. import cygwin - - -@pytest.fixture(autouse=True) -def stuff(request, monkeypatch, distutils_managed_tempdir): - self = request.instance - self.python_h = os.path.join(self.mkdtemp(), 'python.h') - monkeypatch.setattr(sysconfig, 'get_config_h_filename', self._get_config_h_filename) - monkeypatch.setattr(sys, 'version', sys.version) - - -class TestCygwinCCompiler(support.TempdirManager): - def _get_config_h_filename(self): - return self.python_h - - @pytest.mark.skipif('sys.platform != "cygwin"') - @pytest.mark.skipif('not os.path.exists("/usr/lib/libbash.dll.a")') - def test_find_library_file(self): - from distutils.cygwinccompiler import CygwinCCompiler - - compiler = CygwinCCompiler() - link_name = "bash" - linkable_file = compiler.find_library_file(["/usr/lib"], link_name) - assert linkable_file is not None - assert os.path.exists(linkable_file) - assert linkable_file == f"/usr/lib/lib{link_name:s}.dll.a" - - @pytest.mark.skipif('sys.platform != "cygwin"') - def test_runtime_library_dir_option(self): - from distutils.cygwinccompiler import CygwinCCompiler - - compiler = CygwinCCompiler() - assert compiler.runtime_library_dir_option('/foo') == [] - - def test_check_config_h(self): - # check_config_h looks for "GCC" in sys.version first - # returns CONFIG_H_OK if found - sys.version = ( - '2.6.1 (r261:67515, Dec 6 2008, 16:42:21) \n[GCC ' - '4.0.1 (Apple Computer, Inc. build 5370)]' - ) - - assert cygwin.check_config_h()[0] == cygwin.CONFIG_H_OK - - # then it tries to see if it can find "__GNUC__" in pyconfig.h - sys.version = 'something without the *CC word' - - # if the file doesn't exist it returns CONFIG_H_UNCERTAIN - assert cygwin.check_config_h()[0] == cygwin.CONFIG_H_UNCERTAIN - - # if it exists but does not contain __GNUC__, it returns CONFIG_H_NOTOK - self.write_file(self.python_h, 'xxx') - assert cygwin.check_config_h()[0] == cygwin.CONFIG_H_NOTOK - - # and CONFIG_H_OK if __GNUC__ is found - self.write_file(self.python_h, 'xxx __GNUC__ xxx') - assert cygwin.check_config_h()[0] == cygwin.CONFIG_H_OK - - def test_get_msvcr(self): - assert cygwin.get_msvcr() == [] - - @pytest.mark.skipif('sys.platform != "cygwin"') - def test_dll_libraries_not_none(self): - from distutils.cygwinccompiler import CygwinCCompiler - - compiler = CygwinCCompiler() - assert compiler.dll_libraries is not None diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_mingw.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_mingw.py deleted file mode 100644 index dc45687..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_mingw.py +++ /dev/null @@ -1,48 +0,0 @@ -from distutils import sysconfig -from distutils.errors import DistutilsPlatformError -from distutils.util import is_mingw, split_quoted - -import pytest - -from .. import cygwin, errors - - -class TestMinGW32Compiler: - @pytest.mark.skipif(not is_mingw(), reason='not on mingw') - def test_compiler_type(self): - compiler = cygwin.MinGW32Compiler() - assert compiler.compiler_type == 'mingw32' - - @pytest.mark.skipif(not is_mingw(), reason='not on mingw') - def test_set_executables(self, monkeypatch): - monkeypatch.setenv('CC', 'cc') - monkeypatch.setenv('CXX', 'c++') - - compiler = cygwin.MinGW32Compiler() - - assert compiler.compiler == split_quoted('cc -O -Wall') - assert compiler.compiler_so == split_quoted('cc -shared -O -Wall') - assert compiler.compiler_cxx == split_quoted('c++ -O -Wall') - assert compiler.linker_exe == split_quoted('cc') - assert compiler.linker_so == split_quoted('cc -shared') - - @pytest.mark.skipif(not is_mingw(), reason='not on mingw') - def test_runtime_library_dir_option(self): - compiler = cygwin.MinGW32Compiler() - with pytest.raises(DistutilsPlatformError): - compiler.runtime_library_dir_option('/usr/lib') - - @pytest.mark.skipif(not is_mingw(), reason='not on mingw') - def test_cygwincc_error(self, monkeypatch): - monkeypatch.setattr(cygwin, 'is_cygwincc', lambda _: True) - - with pytest.raises(errors.Error): - cygwin.MinGW32Compiler() - - @pytest.mark.skipif('sys.platform == "cygwin"') - def test_customize_compiler_with_msvc_python(self): - # In case we have an MSVC Python build, but still want to use - # MinGW32Compiler, then customize_compiler() shouldn't fail at least. - # https://github.com/pypa/setuptools/issues/4456 - compiler = cygwin.MinGW32Compiler() - sysconfig.customize_compiler(compiler) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_msvc.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_msvc.py deleted file mode 100644 index eca8319..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_msvc.py +++ /dev/null @@ -1,136 +0,0 @@ -import os -import sys -import sysconfig -import threading -import unittest.mock as mock -from distutils.errors import DistutilsPlatformError -from distutils.tests import support -from distutils.util import get_platform - -import pytest - -from .. import msvc - -needs_winreg = pytest.mark.skipif('not hasattr(msvc, "winreg")') - - -class Testmsvccompiler(support.TempdirManager): - def test_no_compiler(self, monkeypatch): - # makes sure query_vcvarsall raises - # a DistutilsPlatformError if the compiler - # is not found - def _find_vcvarsall(plat_spec): - return None, None - - monkeypatch.setattr(msvc, '_find_vcvarsall', _find_vcvarsall) - - with pytest.raises(DistutilsPlatformError): - msvc._get_vc_env( - 'wont find this version', - ) - - @pytest.mark.skipif( - not sysconfig.get_platform().startswith("win"), - reason="Only run test for non-mingw Windows platforms", - ) - @pytest.mark.parametrize( - "plat_name, expected", - [ - ("win-arm64", "win-arm64"), - ("win-amd64", "win-amd64"), - (None, get_platform()), - ], - ) - def test_cross_platform_compilation_paths(self, monkeypatch, plat_name, expected): - """ - Ensure a specified target platform is passed to _get_vcvars_spec. - """ - compiler = msvc.Compiler() - - def _get_vcvars_spec(host_platform, platform): - assert platform == expected - - monkeypatch.setattr(msvc, '_get_vcvars_spec', _get_vcvars_spec) - compiler.initialize(plat_name) - - @needs_winreg - def test_get_vc_env_unicode(self): - test_var = 'ṰḖṤṪ┅ṼẨṜ' - test_value = '₃⁴₅' - - # Ensure we don't early exit from _get_vc_env - old_distutils_use_sdk = os.environ.pop('DISTUTILS_USE_SDK', None) - os.environ[test_var] = test_value - try: - env = msvc._get_vc_env('x86') - assert test_var.lower() in env - assert test_value == env[test_var.lower()] - finally: - os.environ.pop(test_var) - if old_distutils_use_sdk: - os.environ['DISTUTILS_USE_SDK'] = old_distutils_use_sdk - - @needs_winreg - @pytest.mark.parametrize('ver', (2015, 2017)) - def test_get_vc(self, ver): - # This function cannot be mocked, so pass if VC is found - # and skip otherwise. - lookup = getattr(msvc, f'_find_vc{ver}') - expected_version = {2015: 14, 2017: 15}[ver] - version, path = lookup() - if not version: - pytest.skip(f"VS {ver} is not installed") - assert version >= expected_version - assert os.path.isdir(path) - - -class CheckThread(threading.Thread): - exc_info = None - - def run(self): - try: - super().run() - except Exception: - self.exc_info = sys.exc_info() - - def __bool__(self): - return not self.exc_info - - -class TestSpawn: - def test_concurrent_safe(self): - """ - Concurrent calls to spawn should have consistent results. - """ - compiler = msvc.Compiler() - compiler._paths = "expected" - inner_cmd = 'import os; assert os.environ["PATH"] == "expected"' - command = [sys.executable, '-c', inner_cmd] - - threads = [ - CheckThread(target=compiler.spawn, args=[command]) for n in range(100) - ] - for thread in threads: - thread.start() - for thread in threads: - thread.join() - assert all(threads) - - def test_concurrent_safe_fallback(self): - """ - If CCompiler.spawn has been monkey-patched without support - for an env, it should still execute. - """ - from distutils import ccompiler - - compiler = msvc.Compiler() - compiler._paths = "expected" - - def CCompiler_spawn(self, cmd): - "A spawn without an env argument." - assert os.environ["PATH"] == "expected" - - with mock.patch.object(ccompiler.CCompiler, 'spawn', CCompiler_spawn): - compiler.spawn(["n/a"]) - - assert os.environ.get("PATH") != "expected" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_unix.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_unix.py deleted file mode 100644 index f4e2898..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/tests/test_unix.py +++ /dev/null @@ -1,350 +0,0 @@ -"""Tests for distutils.unixccompiler.""" - -import os -import sys -import unittest.mock as mock -from distutils import sysconfig -from distutils.compat import consolidate_linker_args -from distutils.errors import DistutilsPlatformError -from distutils.tests import support -from distutils.tests.compat.py39 import EnvironmentVarGuard -from distutils.util import _clear_cached_macosx_ver - -import pytest - -from .. import unix - - -@pytest.fixture(autouse=True) -def save_values(monkeypatch): - monkeypatch.setattr(sys, 'platform', sys.platform) - monkeypatch.setattr(sysconfig, 'get_config_var', sysconfig.get_config_var) - monkeypatch.setattr(sysconfig, 'get_config_vars', sysconfig.get_config_vars) - - -@pytest.fixture(autouse=True) -def compiler_wrapper(request): - class CompilerWrapper(unix.Compiler): - def rpath_foo(self): - return self.runtime_library_dir_option('/foo') - - request.instance.cc = CompilerWrapper() - - -class TestUnixCCompiler(support.TempdirManager): - @pytest.mark.skipif('platform.system == "Windows"') - def test_runtime_libdir_option(self): # noqa: C901 - # Issue #5900; GitHub Issue #37 - # - # Ensure RUNPATH is added to extension modules with RPATH if - # GNU ld is used - - # darwin - sys.platform = 'darwin' - darwin_ver_var = 'MACOSX_DEPLOYMENT_TARGET' - darwin_rpath_flag = '-Wl,-rpath,/foo' - darwin_lib_flag = '-L/foo' - - # (macOS version from syscfg, macOS version from env var) -> flag - # Version value of None generates two tests: as None and as empty string - # Expected flag value of None means an mismatch exception is expected - darwin_test_cases = [ - ((None, None), darwin_lib_flag), - ((None, '11'), darwin_rpath_flag), - (('10', None), darwin_lib_flag), - (('10.3', None), darwin_lib_flag), - (('10.3.1', None), darwin_lib_flag), - (('10.5', None), darwin_rpath_flag), - (('10.5.1', None), darwin_rpath_flag), - (('10.3', '10.3'), darwin_lib_flag), - (('10.3', '10.5'), darwin_rpath_flag), - (('10.5', '10.3'), darwin_lib_flag), - (('10.5', '11'), darwin_rpath_flag), - (('10.4', '10'), None), - ] - - def make_darwin_gcv(syscfg_macosx_ver): - def gcv(var): - if var == darwin_ver_var: - return syscfg_macosx_ver - return "xxx" - - return gcv - - def do_darwin_test(syscfg_macosx_ver, env_macosx_ver, expected_flag): - env = os.environ - msg = f"macOS version = (sysconfig={syscfg_macosx_ver!r}, env={env_macosx_ver!r})" - - # Save - old_gcv = sysconfig.get_config_var - old_env_macosx_ver = env.get(darwin_ver_var) - - # Setup environment - _clear_cached_macosx_ver() - sysconfig.get_config_var = make_darwin_gcv(syscfg_macosx_ver) - if env_macosx_ver is not None: - env[darwin_ver_var] = env_macosx_ver - elif darwin_ver_var in env: - env.pop(darwin_ver_var) - - # Run the test - if expected_flag is not None: - assert self.cc.rpath_foo() == expected_flag, msg - else: - with pytest.raises( - DistutilsPlatformError, match=darwin_ver_var + r' mismatch' - ): - self.cc.rpath_foo() - - # Restore - if old_env_macosx_ver is not None: - env[darwin_ver_var] = old_env_macosx_ver - elif darwin_ver_var in env: - env.pop(darwin_ver_var) - sysconfig.get_config_var = old_gcv - _clear_cached_macosx_ver() - - for macosx_vers, expected_flag in darwin_test_cases: - syscfg_macosx_ver, env_macosx_ver = macosx_vers - do_darwin_test(syscfg_macosx_ver, env_macosx_ver, expected_flag) - # Bonus test cases with None interpreted as empty string - if syscfg_macosx_ver is None: - do_darwin_test("", env_macosx_ver, expected_flag) - if env_macosx_ver is None: - do_darwin_test(syscfg_macosx_ver, "", expected_flag) - if syscfg_macosx_ver is None and env_macosx_ver is None: - do_darwin_test("", "", expected_flag) - - old_gcv = sysconfig.get_config_var - - # hp-ux - sys.platform = 'hp-ux' - - def gcv(v): - return 'xxx' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == ['+s', '-L/foo'] - - def gcv(v): - return 'gcc' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == ['-Wl,+s', '-L/foo'] - - def gcv(v): - return 'g++' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == ['-Wl,+s', '-L/foo'] - - sysconfig.get_config_var = old_gcv - - # GCC GNULD - sys.platform = 'bar' - - def gcv(v): - if v == 'CC': - return 'gcc' - elif v == 'GNULD': - return 'yes' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == consolidate_linker_args([ - '-Wl,--enable-new-dtags', - '-Wl,-rpath,/foo', - ]) - - def gcv(v): - if v == 'CC': - return 'gcc -pthread -B /bar' - elif v == 'GNULD': - return 'yes' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == consolidate_linker_args([ - '-Wl,--enable-new-dtags', - '-Wl,-rpath,/foo', - ]) - - # GCC non-GNULD - sys.platform = 'bar' - - def gcv(v): - if v == 'CC': - return 'gcc' - elif v == 'GNULD': - return 'no' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == '-Wl,-R/foo' - - # GCC GNULD with fully qualified configuration prefix - # see #7617 - sys.platform = 'bar' - - def gcv(v): - if v == 'CC': - return 'x86_64-pc-linux-gnu-gcc-4.4.2' - elif v == 'GNULD': - return 'yes' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == consolidate_linker_args([ - '-Wl,--enable-new-dtags', - '-Wl,-rpath,/foo', - ]) - - # non-GCC GNULD - sys.platform = 'bar' - - def gcv(v): - if v == 'CC': - return 'cc' - elif v == 'GNULD': - return 'yes' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == consolidate_linker_args([ - '-Wl,--enable-new-dtags', - '-Wl,-rpath,/foo', - ]) - - # non-GCC non-GNULD - sys.platform = 'bar' - - def gcv(v): - if v == 'CC': - return 'cc' - elif v == 'GNULD': - return 'no' - - sysconfig.get_config_var = gcv - assert self.cc.rpath_foo() == '-Wl,-R/foo' - - @pytest.mark.skipif('platform.system == "Windows"') - def test_cc_overrides_ldshared(self): - # Issue #18080: - # ensure that setting CC env variable also changes default linker - def gcv(v): - if v == 'LDSHARED': - return 'gcc-4.2 -bundle -undefined dynamic_lookup ' - return 'gcc-4.2' - - def gcvs(*args, _orig=sysconfig.get_config_vars): - if args: - return list(map(sysconfig.get_config_var, args)) - return _orig() - - sysconfig.get_config_var = gcv - sysconfig.get_config_vars = gcvs - with EnvironmentVarGuard() as env: - env['CC'] = 'my_cc' - del env['LDSHARED'] - sysconfig.customize_compiler(self.cc) - assert self.cc.linker_so[0] == 'my_cc' - - @pytest.mark.skipif('platform.system == "Windows"') - @pytest.mark.usefixtures('disable_macos_customization') - def test_cc_overrides_ldshared_for_cxx_correctly(self): - """ - Ensure that setting CC env variable also changes default linker - correctly when building C++ extensions. - - pypa/distutils#126 - """ - - def gcv(v): - if v == 'LDSHARED': - return 'gcc-4.2 -bundle -undefined dynamic_lookup ' - elif v == 'LDCXXSHARED': - return 'g++-4.2 -bundle -undefined dynamic_lookup ' - elif v == 'CXX': - return 'g++-4.2' - elif v == 'CC': - return 'gcc-4.2' - return '' - - def gcvs(*args, _orig=sysconfig.get_config_vars): - if args: - return list(map(sysconfig.get_config_var, args)) - return _orig() - - sysconfig.get_config_var = gcv - sysconfig.get_config_vars = gcvs - with ( - mock.patch.object(self.cc, 'spawn', return_value=None) as mock_spawn, - mock.patch.object(self.cc, '_need_link', return_value=True), - mock.patch.object(self.cc, 'mkpath', return_value=None), - EnvironmentVarGuard() as env, - ): - env['CC'] = 'ccache my_cc' - env['CXX'] = 'my_cxx' - del env['LDSHARED'] - sysconfig.customize_compiler(self.cc) - assert self.cc.linker_so[0:2] == ['ccache', 'my_cc'] - self.cc.link(None, [], 'a.out', target_lang='c++') - call_args = mock_spawn.call_args[0][0] - expected = ['my_cxx', '-bundle', '-undefined', 'dynamic_lookup'] - assert call_args[:4] == expected - - @pytest.mark.skipif('platform.system == "Windows"') - def test_explicit_ldshared(self): - # Issue #18080: - # ensure that setting CC env variable does not change - # explicit LDSHARED setting for linker - def gcv(v): - if v == 'LDSHARED': - return 'gcc-4.2 -bundle -undefined dynamic_lookup ' - return 'gcc-4.2' - - def gcvs(*args, _orig=sysconfig.get_config_vars): - if args: - return list(map(sysconfig.get_config_var, args)) - return _orig() - - sysconfig.get_config_var = gcv - sysconfig.get_config_vars = gcvs - with EnvironmentVarGuard() as env: - env['CC'] = 'my_cc' - env['LDSHARED'] = 'my_ld -bundle -dynamic' - sysconfig.customize_compiler(self.cc) - assert self.cc.linker_so[0] == 'my_ld' - - def test_has_function(self): - # Issue https://github.com/pypa/distutils/issues/64: - # ensure that setting output_dir does not raise - # FileNotFoundError: [Errno 2] No such file or directory: 'a.out' - self.cc.output_dir = 'scratch' - os.chdir(self.mkdtemp()) - self.cc.has_function('abort') - - def test_find_library_file(self, monkeypatch): - compiler = unix.Compiler() - compiler._library_root = lambda dir: dir - monkeypatch.setattr(os.path, 'exists', lambda d: 'existing' in d) - - libname = 'libabc.dylib' if sys.platform != 'cygwin' else 'cygabc.dll' - dirs = ('/foo/bar/missing', '/foo/bar/existing') - assert ( - compiler.find_library_file(dirs, 'abc').replace('\\', '/') - == f'/foo/bar/existing/{libname}' - ) - assert ( - compiler.find_library_file(reversed(dirs), 'abc').replace('\\', '/') - == f'/foo/bar/existing/{libname}' - ) - - monkeypatch.setattr( - os.path, - 'exists', - lambda d: 'existing' in d and '.a' in d and '.dll.a' not in d, - ) - assert ( - compiler.find_library_file(dirs, 'abc').replace('\\', '/') - == '/foo/bar/existing/libabc.a' - ) - assert ( - compiler.find_library_file(reversed(dirs), 'abc').replace('\\', '/') - == '/foo/bar/existing/libabc.a' - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/unix.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/unix.py deleted file mode 100644 index e8a53d4..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/unix.py +++ /dev/null @@ -1,423 +0,0 @@ -"""distutils.unixccompiler - -Contains the UnixCCompiler class, a subclass of CCompiler that handles -the "typical" Unix-style command-line C compiler: - * macros defined with -Dname[=value] - * macros undefined with -Uname - * include search directories specified with -Idir - * libraries specified with -lllib - * library search directories specified with -Ldir - * compile handled by 'cc' (or similar) executable with -c option: - compiles .c to .o - * link static library handled by 'ar' command (possibly with 'ranlib') - * link shared library handled by 'cc -shared' -""" - -from __future__ import annotations - -import itertools -import os -import re -import shlex -import sys -from collections.abc import Iterable - -from ... import sysconfig -from ..._log import log -from ..._macos_compat import compiler_fixup -from ..._modified import newer -from ...compat import consolidate_linker_args -from ...errors import DistutilsExecError -from . import base -from .base import _Macro, gen_lib_options, gen_preprocess_options -from .errors import ( - CompileError, - LibError, - LinkError, -) - -# XXX Things not currently handled: -# * optimization/debug/warning flags; we just use whatever's in Python's -# Makefile and live with it. Is this adequate? If not, we might -# have to have a bunch of subclasses GNUCCompiler, SGICCompiler, -# SunCCompiler, and I suspect down that road lies madness. -# * even if we don't know a warning flag from an optimization flag, -# we need some way for outsiders to feed preprocessor/compiler/linker -# flags in to us -- eg. a sysadmin might want to mandate certain flags -# via a site config file, or a user might want to set something for -# compiling this module distribution only via the setup.py command -# line, whatever. As long as these options come from something on the -# current system, they can be as system-dependent as they like, and we -# should just happily stuff them into the preprocessor/compiler/linker -# options and carry on. - - -def _split_env(cmd): - """ - For macOS, split command into 'env' portion (if any) - and the rest of the linker command. - - >>> _split_env(['a', 'b', 'c']) - ([], ['a', 'b', 'c']) - >>> _split_env(['/usr/bin/env', 'A=3', 'gcc']) - (['/usr/bin/env', 'A=3'], ['gcc']) - """ - pivot = 0 - if os.path.basename(cmd[0]) == "env": - pivot = 1 - while '=' in cmd[pivot]: - pivot += 1 - return cmd[:pivot], cmd[pivot:] - - -def _split_aix(cmd): - """ - AIX platforms prefix the compiler with the ld_so_aix - script, so split that from the linker command. - - >>> _split_aix(['a', 'b', 'c']) - ([], ['a', 'b', 'c']) - >>> _split_aix(['/bin/foo/ld_so_aix', 'gcc']) - (['/bin/foo/ld_so_aix'], ['gcc']) - """ - pivot = os.path.basename(cmd[0]) == 'ld_so_aix' - return cmd[:pivot], cmd[pivot:] - - -def _linker_params(linker_cmd, compiler_cmd): - """ - The linker command usually begins with the compiler - command (possibly multiple elements), followed by zero or more - params for shared library building. - - If the LDSHARED env variable overrides the linker command, - however, the commands may not match. - - Return the best guess of the linker parameters by stripping - the linker command. If the compiler command does not - match the linker command, assume the linker command is - just the first element. - - >>> _linker_params('gcc foo bar'.split(), ['gcc']) - ['foo', 'bar'] - >>> _linker_params('gcc foo bar'.split(), ['other']) - ['foo', 'bar'] - >>> _linker_params('ccache gcc foo bar'.split(), 'ccache gcc'.split()) - ['foo', 'bar'] - >>> _linker_params(['gcc'], ['gcc']) - [] - """ - c_len = len(compiler_cmd) - pivot = c_len if linker_cmd[:c_len] == compiler_cmd else 1 - return linker_cmd[pivot:] - - -class Compiler(base.Compiler): - compiler_type = 'unix' - - # These are used by CCompiler in two places: the constructor sets - # instance attributes 'preprocessor', 'compiler', etc. from them, and - # 'set_executable()' allows any of these to be set. The defaults here - # are pretty generic; they will probably have to be set by an outsider - # (eg. using information discovered by the sysconfig about building - # Python extensions). - executables = { - 'preprocessor': None, - 'compiler': ["cc"], - 'compiler_so': ["cc"], - 'compiler_cxx': ["c++"], - 'compiler_so_cxx': ["c++"], - 'linker_so': ["cc", "-shared"], - 'linker_so_cxx': ["c++", "-shared"], - 'linker_exe': ["cc"], - 'linker_exe_cxx': ["c++", "-shared"], - 'archiver': ["ar", "-cr"], - 'ranlib': None, - } - - if sys.platform[:6] == "darwin": - executables['ranlib'] = ["ranlib"] - - # Needed for the filename generation methods provided by the base - # class, CCompiler. NB. whoever instantiates/uses a particular - # UnixCCompiler instance should set 'shared_lib_ext' -- we set a - # reasonable common default here, but it's not necessarily used on all - # Unices! - - src_extensions = [".c", ".C", ".cc", ".cxx", ".cpp", ".m"] - obj_extension = ".o" - static_lib_extension = ".a" - shared_lib_extension = ".so" - dylib_lib_extension = ".dylib" - xcode_stub_lib_extension = ".tbd" - static_lib_format = shared_lib_format = dylib_lib_format = "lib%s%s" - xcode_stub_lib_format = dylib_lib_format - if sys.platform == "cygwin": - exe_extension = ".exe" - shared_lib_extension = ".dll.a" - dylib_lib_extension = ".dll" - dylib_lib_format = "cyg%s%s" - - def _fix_lib_args(self, libraries, library_dirs, runtime_library_dirs): - """Remove standard library path from rpath""" - libraries, library_dirs, runtime_library_dirs = super()._fix_lib_args( - libraries, library_dirs, runtime_library_dirs - ) - libdir = sysconfig.get_config_var('LIBDIR') - if ( - runtime_library_dirs - and libdir.startswith("/usr/lib") - and (libdir in runtime_library_dirs) - ): - runtime_library_dirs.remove(libdir) - return libraries, library_dirs, runtime_library_dirs - - def preprocess( - self, - source: str | os.PathLike[str], - output_file: str | os.PathLike[str] | None = None, - macros: list[_Macro] | None = None, - include_dirs: list[str] | tuple[str, ...] | None = None, - extra_preargs: list[str] | None = None, - extra_postargs: Iterable[str] | None = None, - ): - fixed_args = self._fix_compile_args(None, macros, include_dirs) - ignore, macros, include_dirs = fixed_args - pp_opts = gen_preprocess_options(macros, include_dirs) - pp_args = self.preprocessor + pp_opts - if output_file: - pp_args.extend(['-o', output_file]) - if extra_preargs: - pp_args[:0] = extra_preargs - if extra_postargs: - pp_args.extend(extra_postargs) - pp_args.append(source) - - # reasons to preprocess: - # - force is indicated - # - output is directed to stdout - # - source file is newer than the target - preprocess = self.force or output_file is None or newer(source, output_file) - if not preprocess: - return - - if output_file: - self.mkpath(os.path.dirname(output_file)) - - try: - self.spawn(pp_args) - except DistutilsExecError as msg: - raise CompileError(msg) - - def _compile(self, obj, src, ext, cc_args, extra_postargs, pp_opts): - compiler_so = compiler_fixup(self.compiler_so, cc_args + extra_postargs) - compiler_so_cxx = compiler_fixup(self.compiler_so_cxx, cc_args + extra_postargs) - try: - if self.detect_language(src) == 'c++': - self.spawn( - compiler_so_cxx + cc_args + [src, '-o', obj] + extra_postargs - ) - else: - self.spawn(compiler_so + cc_args + [src, '-o', obj] + extra_postargs) - except DistutilsExecError as msg: - raise CompileError(msg) - - def create_static_lib( - self, objects, output_libname, output_dir=None, debug=False, target_lang=None - ): - objects, output_dir = self._fix_object_args(objects, output_dir) - - output_filename = self.library_filename(output_libname, output_dir=output_dir) - - if self._need_link(objects, output_filename): - self.mkpath(os.path.dirname(output_filename)) - self.spawn(self.archiver + [output_filename] + objects + self.objects) - - # Not many Unices required ranlib anymore -- SunOS 4.x is, I - # think the only major Unix that does. Maybe we need some - # platform intelligence here to skip ranlib if it's not - # needed -- or maybe Python's configure script took care of - # it for us, hence the check for leading colon. - if self.ranlib: - try: - self.spawn(self.ranlib + [output_filename]) - except DistutilsExecError as msg: - raise LibError(msg) - else: - log.debug("skipping %s (up-to-date)", output_filename) - - def link( - self, - target_desc, - objects: list[str] | tuple[str, ...], - output_filename, - output_dir: str | None = None, - libraries: list[str] | tuple[str, ...] | None = None, - library_dirs: list[str] | tuple[str, ...] | None = None, - runtime_library_dirs: list[str] | tuple[str, ...] | None = None, - export_symbols=None, - debug=False, - extra_preargs=None, - extra_postargs=None, - build_temp=None, - target_lang=None, - ): - objects, output_dir = self._fix_object_args(objects, output_dir) - fixed_args = self._fix_lib_args(libraries, library_dirs, runtime_library_dirs) - libraries, library_dirs, runtime_library_dirs = fixed_args - - lib_opts = gen_lib_options(self, library_dirs, runtime_library_dirs, libraries) - if not isinstance(output_dir, (str, type(None))): - raise TypeError("'output_dir' must be a string or None") - if output_dir is not None: - output_filename = os.path.join(output_dir, output_filename) - - if self._need_link(objects, output_filename): - ld_args = objects + self.objects + lib_opts + ['-o', output_filename] - if debug: - ld_args[:0] = ['-g'] - if extra_preargs: - ld_args[:0] = extra_preargs - if extra_postargs: - ld_args.extend(extra_postargs) - self.mkpath(os.path.dirname(output_filename)) - try: - # Select a linker based on context: linker_exe when - # building an executable or linker_so (with shared options) - # when building a shared library. - building_exe = target_desc == base.Compiler.EXECUTABLE - linker = ( - self.linker_exe - if building_exe - else ( - self.linker_so_cxx if target_lang == "c++" else self.linker_so - ) - )[:] - - if target_lang == "c++" and self.compiler_cxx: - env, linker_ne = _split_env(linker) - aix, linker_na = _split_aix(linker_ne) - _, compiler_cxx_ne = _split_env(self.compiler_cxx) - _, linker_exe_ne = _split_env(self.linker_exe) - - params = _linker_params(linker_na, linker_exe_ne) - linker = env + aix + compiler_cxx_ne + params - - linker = compiler_fixup(linker, ld_args) - - self.spawn(linker + ld_args) - except DistutilsExecError as msg: - raise LinkError(msg) - else: - log.debug("skipping %s (up-to-date)", output_filename) - - # -- Miscellaneous methods ----------------------------------------- - # These are all used by the 'gen_lib_options() function, in - # ccompiler.py. - - def library_dir_option(self, dir): - return "-L" + dir - - def _is_gcc(self): - cc_var = sysconfig.get_config_var("CC") - compiler = os.path.basename(shlex.split(cc_var)[0]) - return "gcc" in compiler or "g++" in compiler - - def runtime_library_dir_option(self, dir: str) -> str | list[str]: # type: ignore[override] # Fixed in pypa/distutils#339 - # XXX Hackish, at the very least. See Python bug #445902: - # https://bugs.python.org/issue445902 - # Linkers on different platforms need different options to - # specify that directories need to be added to the list of - # directories searched for dependencies when a dynamic library - # is sought. GCC on GNU systems (Linux, FreeBSD, ...) has to - # be told to pass the -R option through to the linker, whereas - # other compilers and gcc on other systems just know this. - # Other compilers may need something slightly different. At - # this time, there's no way to determine this information from - # the configuration data stored in the Python installation, so - # we use this hack. - if sys.platform[:6] == "darwin": - from distutils.util import get_macosx_target_ver, split_version - - macosx_target_ver = get_macosx_target_ver() - if macosx_target_ver and split_version(macosx_target_ver) >= [10, 5]: - return "-Wl,-rpath," + dir - else: # no support for -rpath on earlier macOS versions - return "-L" + dir - elif sys.platform[:7] == "freebsd": - return "-Wl,-rpath=" + dir - elif sys.platform[:5] == "hp-ux": - return [ - "-Wl,+s" if self._is_gcc() else "+s", - "-L" + dir, - ] - - # For all compilers, `-Wl` is the presumed way to pass a - # compiler option to the linker - if sysconfig.get_config_var("GNULD") == "yes": - return consolidate_linker_args([ - # Force RUNPATH instead of RPATH - "-Wl,--enable-new-dtags", - "-Wl,-rpath," + dir, - ]) - else: - return "-Wl,-R" + dir - - def library_option(self, lib): - return "-l" + lib - - @staticmethod - def _library_root(dir): - """ - macOS users can specify an alternate SDK using'-isysroot'. - Calculate the SDK root if it is specified. - - Note that, as of Xcode 7, Apple SDKs may contain textual stub - libraries with .tbd extensions rather than the normal .dylib - shared libraries installed in /. The Apple compiler tool - chain handles this transparently but it can cause problems - for programs that are being built with an SDK and searching - for specific libraries. Callers of find_library_file need to - keep in mind that the base filename of the returned SDK library - file might have a different extension from that of the library - file installed on the running system, for example: - /Applications/Xcode.app/Contents/Developer/Platforms/ - MacOSX.platform/Developer/SDKs/MacOSX10.11.sdk/ - usr/lib/libedit.tbd - vs - /usr/lib/libedit.dylib - """ - cflags = sysconfig.get_config_var('CFLAGS') - match = re.search(r'-isysroot\s*(\S+)', cflags) - - apply_root = ( - sys.platform == 'darwin' - and match - and ( - dir.startswith('/System/') - or (dir.startswith('/usr/') and not dir.startswith('/usr/local/')) - ) - ) - - return os.path.join(match.group(1), dir[1:]) if apply_root else dir - - def find_library_file(self, dirs, lib, debug=False): - """ - Second-guess the linker with not much hard - data to go on: GCC seems to prefer the shared library, so - assume that *all* Unix C compilers do, - ignoring even GCC's "-static" option. - """ - lib_names = ( - self.library_filename(lib, lib_type=type) - for type in 'dylib xcode_stub shared static'.split() - ) - - roots = map(self._library_root, dirs) - - searched = itertools.starmap(os.path.join, itertools.product(roots, lib_names)) - - found = filter(os.path.exists, searched) - - # Return None if it could not be found in any dir. - return next(found, None) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/zos.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/zos.py deleted file mode 100644 index 82d017f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/compilers/C/zos.py +++ /dev/null @@ -1,230 +0,0 @@ -"""distutils.zosccompiler - -Contains the selection of the c & c++ compilers on z/OS. There are several -different c compilers on z/OS, all of them are optional, so the correct -one needs to be chosen based on the users input. This is compatible with -the following compilers: - -IBM C/C++ For Open Enterprise Languages on z/OS 2.0 -IBM Open XL C/C++ 1.1 for z/OS -IBM XL C/C++ V2.4.1 for z/OS 2.4 and 2.5 -IBM z/OS XL C/C++ -""" - -import os - -from ... import sysconfig -from ...errors import DistutilsExecError -from . import unix -from .errors import CompileError - -_cc_args = { - 'ibm-openxl': [ - '-m64', - '-fvisibility=default', - '-fzos-le-char-mode=ascii', - '-fno-short-enums', - ], - 'ibm-xlclang': [ - '-q64', - '-qexportall', - '-qascii', - '-qstrict', - '-qnocsect', - '-Wa,asa,goff', - '-Wa,xplink', - '-qgonumber', - '-qenum=int', - '-Wc,DLL', - ], - 'ibm-xlc': [ - '-q64', - '-qexportall', - '-qascii', - '-qstrict', - '-qnocsect', - '-Wa,asa,goff', - '-Wa,xplink', - '-qgonumber', - '-qenum=int', - '-Wc,DLL', - '-qlanglvl=extc99', - ], -} - -_cxx_args = { - 'ibm-openxl': [ - '-m64', - '-fvisibility=default', - '-fzos-le-char-mode=ascii', - '-fno-short-enums', - ], - 'ibm-xlclang': [ - '-q64', - '-qexportall', - '-qascii', - '-qstrict', - '-qnocsect', - '-Wa,asa,goff', - '-Wa,xplink', - '-qgonumber', - '-qenum=int', - '-Wc,DLL', - ], - 'ibm-xlc': [ - '-q64', - '-qexportall', - '-qascii', - '-qstrict', - '-qnocsect', - '-Wa,asa,goff', - '-Wa,xplink', - '-qgonumber', - '-qenum=int', - '-Wc,DLL', - '-qlanglvl=extended0x', - ], -} - -_asm_args = { - 'ibm-openxl': ['-fasm', '-fno-integrated-as', '-Wa,--ASA', '-Wa,--GOFF'], - 'ibm-xlclang': [], - 'ibm-xlc': [], -} - -_ld_args = { - 'ibm-openxl': [], - 'ibm-xlclang': ['-Wl,dll', '-q64'], - 'ibm-xlc': ['-Wl,dll', '-q64'], -} - - -# Python on z/OS is built with no compiler specific options in it's CFLAGS. -# But each compiler requires it's own specific options to build successfully, -# though some of the options are common between them -class Compiler(unix.Compiler): - src_extensions = ['.c', '.C', '.cc', '.cxx', '.cpp', '.m', '.s'] - _cpp_extensions = ['.cc', '.cpp', '.cxx', '.C'] - _asm_extensions = ['.s'] - - def _get_zos_compiler_name(self): - zos_compiler_names = [ - os.path.basename(binary) - for envvar in ('CC', 'CXX', 'LDSHARED') - if (binary := os.environ.get(envvar, None)) - ] - if len(zos_compiler_names) == 0: - return 'ibm-openxl' - - zos_compilers = {} - for compiler in ( - 'ibm-clang', - 'ibm-clang64', - 'ibm-clang++', - 'ibm-clang++64', - 'clang', - 'clang++', - 'clang-14', - ): - zos_compilers[compiler] = 'ibm-openxl' - - for compiler in ('xlclang', 'xlclang++', 'njsc', 'njsc++'): - zos_compilers[compiler] = 'ibm-xlclang' - - for compiler in ('xlc', 'xlC', 'xlc++'): - zos_compilers[compiler] = 'ibm-xlc' - - return zos_compilers.get(zos_compiler_names[0], 'ibm-openxl') - - def __init__(self, verbose=False, dry_run=False, force=False): - super().__init__(verbose, dry_run, force) - self.zos_compiler = self._get_zos_compiler_name() - sysconfig.customize_compiler(self) - - def _compile(self, obj, src, ext, cc_args, extra_postargs, pp_opts): - local_args = [] - if ext in self._cpp_extensions: - compiler = self.compiler_cxx - local_args.extend(_cxx_args[self.zos_compiler]) - elif ext in self._asm_extensions: - compiler = self.compiler_so - local_args.extend(_cc_args[self.zos_compiler]) - local_args.extend(_asm_args[self.zos_compiler]) - else: - compiler = self.compiler_so - local_args.extend(_cc_args[self.zos_compiler]) - local_args.extend(cc_args) - - try: - self.spawn(compiler + local_args + [src, '-o', obj] + extra_postargs) - except DistutilsExecError as msg: - raise CompileError(msg) - - def runtime_library_dir_option(self, dir): - return '-L' + dir - - def link( - self, - target_desc, - objects, - output_filename, - output_dir=None, - libraries=None, - library_dirs=None, - runtime_library_dirs=None, - export_symbols=None, - debug=False, - extra_preargs=None, - extra_postargs=None, - build_temp=None, - target_lang=None, - ): - # For a built module to use functions from cpython, it needs to use Pythons - # side deck file. The side deck is located beside the libpython3.xx.so - ldversion = sysconfig.get_config_var('LDVERSION') - if sysconfig.python_build: - side_deck_path = os.path.join( - sysconfig.get_config_var('abs_builddir'), - f'libpython{ldversion}.x', - ) - else: - side_deck_path = os.path.join( - sysconfig.get_config_var('installed_base'), - sysconfig.get_config_var('platlibdir'), - f'libpython{ldversion}.x', - ) - - if os.path.exists(side_deck_path): - if extra_postargs: - extra_postargs.append(side_deck_path) - else: - extra_postargs = [side_deck_path] - - # Check and replace libraries included side deck files - if runtime_library_dirs: - for dir in runtime_library_dirs: - for library in libraries[:]: - library_side_deck = os.path.join(dir, f'{library}.x') - if os.path.exists(library_side_deck): - libraries.remove(library) - extra_postargs.append(library_side_deck) - break - - # Any required ld args for the given compiler - extra_postargs.extend(_ld_args[self.zos_compiler]) - - super().link( - target_desc, - objects, - output_filename, - output_dir, - libraries, - library_dirs, - runtime_library_dirs, - export_symbols, - debug, - extra_preargs, - extra_postargs, - build_temp, - target_lang, - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/core.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/core.py deleted file mode 100644 index bd62546..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/core.py +++ /dev/null @@ -1,289 +0,0 @@ -"""distutils.core - -The only module that needs to be imported to use the Distutils; provides -the 'setup' function (which is to be called from the setup script). Also -indirectly provides the Distribution and Command classes, although they are -really defined in distutils.dist and distutils.cmd. -""" - -from __future__ import annotations - -import os -import sys -import tokenize -from collections.abc import Iterable - -from .cmd import Command -from .debug import DEBUG - -# Mainly import these so setup scripts can "from distutils.core import" them. -from .dist import Distribution -from .errors import ( - CCompilerError, - DistutilsArgError, - DistutilsError, - DistutilsSetupError, -) -from .extension import Extension - -__all__ = ['Distribution', 'Command', 'Extension', 'setup'] - -# This is a barebones help message generated displayed when the user -# runs the setup script with no arguments at all. More useful help -# is generated with various --help options: global help, list commands, -# and per-command help. -USAGE = """\ -usage: %(script)s [global_opts] cmd1 [cmd1_opts] [cmd2 [cmd2_opts] ...] - or: %(script)s --help [cmd1 cmd2 ...] - or: %(script)s --help-commands - or: %(script)s cmd --help -""" - - -def gen_usage(script_name): - script = os.path.basename(script_name) - return USAGE % locals() - - -# Some mild magic to control the behaviour of 'setup()' from 'run_setup()'. -_setup_stop_after = None -_setup_distribution = None - -# Legal keyword arguments for the setup() function -setup_keywords = ( - 'distclass', - 'script_name', - 'script_args', - 'options', - 'name', - 'version', - 'author', - 'author_email', - 'maintainer', - 'maintainer_email', - 'url', - 'license', - 'description', - 'long_description', - 'keywords', - 'platforms', - 'classifiers', - 'download_url', - 'requires', - 'provides', - 'obsoletes', -) - -# Legal keyword arguments for the Extension constructor -extension_keywords = ( - 'name', - 'sources', - 'include_dirs', - 'define_macros', - 'undef_macros', - 'library_dirs', - 'libraries', - 'runtime_library_dirs', - 'extra_objects', - 'extra_compile_args', - 'extra_link_args', - 'swig_opts', - 'export_symbols', - 'depends', - 'language', -) - - -def setup(**attrs): # noqa: C901 - """The gateway to the Distutils: do everything your setup script needs - to do, in a highly flexible and user-driven way. Briefly: create a - Distribution instance; find and parse config files; parse the command - line; run each Distutils command found there, customized by the options - supplied to 'setup()' (as keyword arguments), in config files, and on - the command line. - - The Distribution instance might be an instance of a class supplied via - the 'distclass' keyword argument to 'setup'; if no such class is - supplied, then the Distribution class (in dist.py) is instantiated. - All other arguments to 'setup' (except for 'cmdclass') are used to set - attributes of the Distribution instance. - - The 'cmdclass' argument, if supplied, is a dictionary mapping command - names to command classes. Each command encountered on the command line - will be turned into a command class, which is in turn instantiated; any - class found in 'cmdclass' is used in place of the default, which is - (for command 'foo_bar') class 'foo_bar' in module - 'distutils.command.foo_bar'. The command class must provide a - 'user_options' attribute which is a list of option specifiers for - 'distutils.fancy_getopt'. Any command-line options between the current - and the next command are used to set attributes of the current command - object. - - When the entire command-line has been successfully parsed, calls the - 'run()' method on each command object in turn. This method will be - driven entirely by the Distribution object (which each command object - has a reference to, thanks to its constructor), and the - command-specific options that became attributes of each command - object. - """ - - global _setup_stop_after, _setup_distribution - - # Determine the distribution class -- either caller-supplied or - # our Distribution (see below). - klass = attrs.get('distclass') - if klass: - attrs.pop('distclass') - else: - klass = Distribution - - if 'script_name' not in attrs: - attrs['script_name'] = os.path.basename(sys.argv[0]) - if 'script_args' not in attrs: - attrs['script_args'] = sys.argv[1:] - - # Create the Distribution instance, using the remaining arguments - # (ie. everything except distclass) to initialize it - try: - _setup_distribution = dist = klass(attrs) - except DistutilsSetupError as msg: - if 'name' not in attrs: - raise SystemExit(f"error in setup command: {msg}") - else: - raise SystemExit("error in {} setup command: {}".format(attrs['name'], msg)) - - if _setup_stop_after == "init": - return dist - - # Find and parse the config file(s): they will override options from - # the setup script, but be overridden by the command line. - dist.parse_config_files() - - if DEBUG: - print("options (after parsing config files):") - dist.dump_option_dicts() - - if _setup_stop_after == "config": - return dist - - # Parse the command line and override config files; any - # command-line errors are the end user's fault, so turn them into - # SystemExit to suppress tracebacks. - try: - ok = dist.parse_command_line() - except DistutilsArgError as msg: - raise SystemExit(gen_usage(dist.script_name) + f"\nerror: {msg}") - - if DEBUG: - print("options (after parsing command line):") - dist.dump_option_dicts() - - if _setup_stop_after == "commandline": - return dist - - # And finally, run all the commands found on the command line. - if ok: - return run_commands(dist) - - return dist - - -# setup () - - -def run_commands(dist): - """Given a Distribution object run all the commands, - raising ``SystemExit`` errors in the case of failure. - - This function assumes that either ``sys.argv`` or ``dist.script_args`` - is already set accordingly. - """ - try: - dist.run_commands() - except KeyboardInterrupt: - raise SystemExit("interrupted") - except OSError as exc: - if DEBUG: - sys.stderr.write(f"error: {exc}\n") - raise - else: - raise SystemExit(f"error: {exc}") - - except (DistutilsError, CCompilerError) as msg: - if DEBUG: - raise - else: - raise SystemExit("error: " + str(msg)) - - return dist - - -def run_setup(script_name, script_args: Iterable[str] | None = None, stop_after="run"): - """Run a setup script in a somewhat controlled environment, and - return the Distribution instance that drives things. This is useful - if you need to find out the distribution meta-data (passed as - keyword args from 'script' to 'setup()', or the contents of the - config files or command-line. - - 'script_name' is a file that will be read and run with 'exec()'; - 'sys.argv[0]' will be replaced with 'script' for the duration of the - call. 'script_args' is a list of strings; if supplied, - 'sys.argv[1:]' will be replaced by 'script_args' for the duration of - the call. - - 'stop_after' tells 'setup()' when to stop processing; possible - values: - init - stop after the Distribution instance has been created and - populated with the keyword arguments to 'setup()' - config - stop after config files have been parsed (and their data - stored in the Distribution instance) - commandline - stop after the command-line ('sys.argv[1:]' or 'script_args') - have been parsed (and the data stored in the Distribution) - run [default] - stop after all commands have been run (the same as if 'setup()' - had been called in the usual way - - Returns the Distribution instance, which provides all information - used to drive the Distutils. - """ - if stop_after not in ('init', 'config', 'commandline', 'run'): - raise ValueError(f"invalid value for 'stop_after': {stop_after!r}") - - global _setup_stop_after, _setup_distribution - _setup_stop_after = stop_after - - save_argv = sys.argv.copy() - g = {'__file__': script_name, '__name__': '__main__'} - try: - try: - sys.argv[0] = script_name - if script_args is not None: - sys.argv[1:] = script_args - # tokenize.open supports automatic encoding detection - with tokenize.open(script_name) as f: - code = f.read().replace(r'\r\n', r'\n') - exec(code, g) - finally: - sys.argv = save_argv - _setup_stop_after = None - except SystemExit: - # Hmm, should we do something if exiting with a non-zero code - # (ie. error)? - pass - - if _setup_distribution is None: - raise RuntimeError( - "'distutils.core.setup()' was never called -- " - f"perhaps '{script_name}' is not a Distutils setup script?" - ) - - # I wonder if the setup script's namespace -- g and l -- would be of - # any interest to callers? - # print "_setup_distribution:", _setup_distribution - return _setup_distribution - - -# run_setup () diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/cygwinccompiler.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/cygwinccompiler.py deleted file mode 100644 index de89e3c..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/cygwinccompiler.py +++ /dev/null @@ -1,31 +0,0 @@ -from .compilers.C import cygwin -from .compilers.C.cygwin import ( - CONFIG_H_NOTOK, - CONFIG_H_OK, - CONFIG_H_UNCERTAIN, - check_config_h, - get_msvcr, - is_cygwincc, -) - -__all__ = [ - 'CONFIG_H_NOTOK', - 'CONFIG_H_OK', - 'CONFIG_H_UNCERTAIN', - 'CygwinCCompiler', - 'Mingw32CCompiler', - 'check_config_h', - 'get_msvcr', - 'is_cygwincc', -] - - -CygwinCCompiler = cygwin.Compiler -Mingw32CCompiler = cygwin.MinGW32Compiler - - -get_versions = None -""" -A stand-in for the previous get_versions() function to prevent failures -when monkeypatched. See pypa/setuptools#2969. -""" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/debug.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/debug.py deleted file mode 100644 index daf1660..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/debug.py +++ /dev/null @@ -1,5 +0,0 @@ -import os - -# If DISTUTILS_DEBUG is anything other than the empty string, we run in -# debug mode. -DEBUG = os.environ.get('DISTUTILS_DEBUG') diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dep_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dep_util.py deleted file mode 100644 index 09a8a2e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dep_util.py +++ /dev/null @@ -1,14 +0,0 @@ -import warnings - -from . import _modified - - -def __getattr__(name): - if name not in ['newer', 'newer_group', 'newer_pairwise']: - raise AttributeError(name) - warnings.warn( - "dep_util is Deprecated. Use functions from setuptools instead.", - DeprecationWarning, - stacklevel=2, - ) - return getattr(_modified, name) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dir_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dir_util.py deleted file mode 100644 index d978260..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dir_util.py +++ /dev/null @@ -1,244 +0,0 @@ -"""distutils.dir_util - -Utility functions for manipulating directories and directory trees.""" - -import functools -import itertools -import os -import pathlib - -from . import file_util -from ._log import log -from .errors import DistutilsFileError, DistutilsInternalError - - -class SkipRepeatAbsolutePaths(set): - """ - Cache for mkpath. - - In addition to cheapening redundant calls, eliminates redundant - "creating /foo/bar/baz" messages in dry-run mode. - """ - - def __init__(self): - SkipRepeatAbsolutePaths.instance = self - - @classmethod - def clear(cls): - super(cls, cls.instance).clear() - - def wrap(self, func): - @functools.wraps(func) - def wrapper(path, *args, **kwargs): - if path.absolute() in self: - return - result = func(path, *args, **kwargs) - self.add(path.absolute()) - return result - - return wrapper - - -# Python 3.8 compatibility -wrapper = SkipRepeatAbsolutePaths().wrap - - -@functools.singledispatch -@wrapper -def mkpath(name: pathlib.Path, mode=0o777, verbose=True, dry_run=False) -> None: - """Create a directory and any missing ancestor directories. - - If the directory already exists (or if 'name' is the empty string, which - means the current directory, which of course exists), then do nothing. - Raise DistutilsFileError if unable to create some directory along the way - (eg. some sub-path exists, but is a file rather than a directory). - If 'verbose' is true, log the directory created. - """ - if verbose and not name.is_dir(): - log.info("creating %s", name) - - try: - dry_run or name.mkdir(mode=mode, parents=True, exist_ok=True) - except OSError as exc: - raise DistutilsFileError(f"could not create '{name}': {exc.args[-1]}") - - -@mkpath.register -def _(name: str, *args, **kwargs): - return mkpath(pathlib.Path(name), *args, **kwargs) - - -@mkpath.register -def _(name: None, *args, **kwargs): - """ - Detect a common bug -- name is None. - """ - raise DistutilsInternalError(f"mkpath: 'name' must be a string (got {name!r})") - - -def create_tree(base_dir, files, mode=0o777, verbose=True, dry_run=False): - """Create all the empty directories under 'base_dir' needed to put 'files' - there. - - 'base_dir' is just the name of a directory which doesn't necessarily - exist yet; 'files' is a list of filenames to be interpreted relative to - 'base_dir'. 'base_dir' + the directory portion of every file in 'files' - will be created if it doesn't already exist. 'mode', 'verbose' and - 'dry_run' flags are as for 'mkpath()'. - """ - # First get the list of directories to create - need_dir = set(os.path.join(base_dir, os.path.dirname(file)) for file in files) - - # Now create them - for dir in sorted(need_dir): - mkpath(dir, mode, verbose=verbose, dry_run=dry_run) - - -def copy_tree( - src, - dst, - preserve_mode=True, - preserve_times=True, - preserve_symlinks=False, - update=False, - verbose=True, - dry_run=False, -): - """Copy an entire directory tree 'src' to a new location 'dst'. - - Both 'src' and 'dst' must be directory names. If 'src' is not a - directory, raise DistutilsFileError. If 'dst' does not exist, it is - created with 'mkpath()'. The end result of the copy is that every - file in 'src' is copied to 'dst', and directories under 'src' are - recursively copied to 'dst'. Return the list of files that were - copied or might have been copied, using their output name. The - return value is unaffected by 'update' or 'dry_run': it is simply - the list of all files under 'src', with the names changed to be - under 'dst'. - - 'preserve_mode' and 'preserve_times' are the same as for - 'copy_file'; note that they only apply to regular files, not to - directories. If 'preserve_symlinks' is true, symlinks will be - copied as symlinks (on platforms that support them!); otherwise - (the default), the destination of the symlink will be copied. - 'update' and 'verbose' are the same as for 'copy_file'. - """ - if not dry_run and not os.path.isdir(src): - raise DistutilsFileError(f"cannot copy tree '{src}': not a directory") - try: - names = os.listdir(src) - except OSError as e: - if dry_run: - names = [] - else: - raise DistutilsFileError(f"error listing files in '{src}': {e.strerror}") - - if not dry_run: - mkpath(dst, verbose=verbose) - - copy_one = functools.partial( - _copy_one, - src=src, - dst=dst, - preserve_symlinks=preserve_symlinks, - verbose=verbose, - dry_run=dry_run, - preserve_mode=preserve_mode, - preserve_times=preserve_times, - update=update, - ) - return list(itertools.chain.from_iterable(map(copy_one, names))) - - -def _copy_one( - name, - *, - src, - dst, - preserve_symlinks, - verbose, - dry_run, - preserve_mode, - preserve_times, - update, -): - src_name = os.path.join(src, name) - dst_name = os.path.join(dst, name) - - if name.startswith('.nfs'): - # skip NFS rename files - return - - if preserve_symlinks and os.path.islink(src_name): - link_dest = os.readlink(src_name) - if verbose >= 1: - log.info("linking %s -> %s", dst_name, link_dest) - if not dry_run: - os.symlink(link_dest, dst_name) - yield dst_name - - elif os.path.isdir(src_name): - yield from copy_tree( - src_name, - dst_name, - preserve_mode, - preserve_times, - preserve_symlinks, - update, - verbose=verbose, - dry_run=dry_run, - ) - else: - file_util.copy_file( - src_name, - dst_name, - preserve_mode, - preserve_times, - update, - verbose=verbose, - dry_run=dry_run, - ) - yield dst_name - - -def _build_cmdtuple(path, cmdtuples): - """Helper for remove_tree().""" - for f in os.listdir(path): - real_f = os.path.join(path, f) - if os.path.isdir(real_f) and not os.path.islink(real_f): - _build_cmdtuple(real_f, cmdtuples) - else: - cmdtuples.append((os.remove, real_f)) - cmdtuples.append((os.rmdir, path)) - - -def remove_tree(directory, verbose=True, dry_run=False): - """Recursively remove an entire directory tree. - - Any errors are ignored (apart from being reported to stdout if 'verbose' - is true). - """ - if verbose >= 1: - log.info("removing '%s' (and everything under it)", directory) - if dry_run: - return - cmdtuples = [] - _build_cmdtuple(directory, cmdtuples) - for cmd in cmdtuples: - try: - cmd[0](cmd[1]) - # Clear the cache - SkipRepeatAbsolutePaths.clear() - except OSError as exc: - log.warning("error removing %s: %s", directory, exc) - - -def ensure_relative(path): - """Take the full path 'path', and make it a relative path. - - This is useful to make 'path' the second argument to os.path.join(). - """ - drive, path = os.path.splitdrive(path) - if path[0:1] == os.sep: - path = drive + path[1:] - return path diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dist.py deleted file mode 100644 index 37b788d..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/dist.py +++ /dev/null @@ -1,1386 +0,0 @@ -"""distutils.dist - -Provides the Distribution class, which represents the module distribution -being built/installed/distributed. -""" - -from __future__ import annotations - -import contextlib -import logging -import os -import pathlib -import re -import sys -import warnings -from collections.abc import Iterable, MutableMapping -from email import message_from_file -from typing import ( - IO, - TYPE_CHECKING, - Any, - ClassVar, - Literal, - TypeVar, - Union, - overload, -) - -from packaging.utils import canonicalize_name, canonicalize_version - -from ._log import log -from .debug import DEBUG -from .errors import ( - DistutilsArgError, - DistutilsClassError, - DistutilsModuleError, - DistutilsOptionError, -) -from .fancy_getopt import FancyGetopt, translate_longopt -from .util import check_environ, rfc822_escape, strtobool - -if TYPE_CHECKING: - from _typeshed import SupportsWrite - from typing_extensions import TypeAlias - - # type-only import because of mutual dependence between these modules - from .cmd import Command - -_CommandT = TypeVar("_CommandT", bound="Command") -_OptionsList: TypeAlias = list[ - Union[tuple[str, Union[str, None], str, int], tuple[str, Union[str, None], str]] -] - - -# Regex to define acceptable Distutils command names. This is not *quite* -# the same as a Python NAME -- I don't allow leading underscores. The fact -# that they're very similar is no coincidence; the default naming scheme is -# to look for a Python module named after the command. -command_re = re.compile(r'^[a-zA-Z]([a-zA-Z0-9_]*)$') - - -def _ensure_list(value: str | Iterable[str], fieldname) -> str | list[str]: - if isinstance(value, str): - # a string containing comma separated values is okay. It will - # be converted to a list by Distribution.finalize_options(). - pass - elif not isinstance(value, list): - # passing a tuple or an iterator perhaps, warn and convert - typename = type(value).__name__ - msg = "Warning: '{fieldname}' should be a list, got type '{typename}'" - msg = msg.format(**locals()) - log.warning(msg) - value = list(value) - return value - - -class Distribution: - """The core of the Distutils. Most of the work hiding behind 'setup' - is really done within a Distribution instance, which farms the work out - to the Distutils commands specified on the command line. - - Setup scripts will almost never instantiate Distribution directly, - unless the 'setup()' function is totally inadequate to their needs. - However, it is conceivable that a setup script might wish to subclass - Distribution for some specialized purpose, and then pass the subclass - to 'setup()' as the 'distclass' keyword argument. If so, it is - necessary to respect the expectations that 'setup' has of Distribution. - See the code for 'setup()', in core.py, for details. - """ - - # 'global_options' describes the command-line options that may be - # supplied to the setup script prior to any actual commands. - # Eg. "./setup.py -n" or "./setup.py --quiet" both take advantage of - # these global options. This list should be kept to a bare minimum, - # since every global option is also valid as a command option -- and we - # don't want to pollute the commands with too many options that they - # have minimal control over. - # The fourth entry for verbose means that it can be repeated. - global_options: ClassVar[_OptionsList] = [ - ('verbose', 'v', "run verbosely (default)", 1), - ('quiet', 'q', "run quietly (turns verbosity off)"), - ('dry-run', 'n', "don't actually do anything"), - ('help', 'h', "show detailed help message"), - ('no-user-cfg', None, 'ignore pydistutils.cfg in your home directory'), - ] - - # 'common_usage' is a short (2-3 line) string describing the common - # usage of the setup script. - common_usage: ClassVar[str] = """\ -Common commands: (see '--help-commands' for more) - - setup.py build will build the package underneath 'build/' - setup.py install will install the package -""" - - # options that are not propagated to the commands - display_options: ClassVar[_OptionsList] = [ - ('help-commands', None, "list all available commands"), - ('name', None, "print package name"), - ('version', 'V', "print package version"), - ('fullname', None, "print -"), - ('author', None, "print the author's name"), - ('author-email', None, "print the author's email address"), - ('maintainer', None, "print the maintainer's name"), - ('maintainer-email', None, "print the maintainer's email address"), - ('contact', None, "print the maintainer's name if known, else the author's"), - ( - 'contact-email', - None, - "print the maintainer's email address if known, else the author's", - ), - ('url', None, "print the URL for this package"), - ('license', None, "print the license of the package"), - ('licence', None, "alias for --license"), - ('description', None, "print the package description"), - ('long-description', None, "print the long package description"), - ('platforms', None, "print the list of platforms"), - ('classifiers', None, "print the list of classifiers"), - ('keywords', None, "print the list of keywords"), - ('provides', None, "print the list of packages/modules provided"), - ('requires', None, "print the list of packages/modules required"), - ('obsoletes', None, "print the list of packages/modules made obsolete"), - ] - display_option_names: ClassVar[list[str]] = [ - translate_longopt(x[0]) for x in display_options - ] - - # negative options are options that exclude other options - negative_opt: ClassVar[dict[str, str]] = {'quiet': 'verbose'} - - # -- Creation/initialization methods ------------------------------- - - # Can't Unpack a TypedDict with optional properties, so using Any instead - def __init__(self, attrs: MutableMapping[str, Any] | None = None) -> None: # noqa: C901 - """Construct a new Distribution instance: initialize all the - attributes of a Distribution, and then use 'attrs' (a dictionary - mapping attribute names to values) to assign some of those - attributes their "real" values. (Any attributes not mentioned in - 'attrs' will be assigned to some null value: 0, None, an empty list - or dictionary, etc.) Most importantly, initialize the - 'command_obj' attribute to the empty dictionary; this will be - filled in with real command objects by 'parse_command_line()'. - """ - - # Default values for our command-line options - self.verbose = True - self.dry_run = False - self.help = False - for attr in self.display_option_names: - setattr(self, attr, False) - - # Store the distribution meta-data (name, version, author, and so - # forth) in a separate object -- we're getting to have enough - # information here (and enough command-line options) that it's - # worth it. Also delegate 'get_XXX()' methods to the 'metadata' - # object in a sneaky and underhanded (but efficient!) way. - self.metadata = DistributionMetadata() - for basename in self.metadata._METHOD_BASENAMES: - method_name = "get_" + basename - setattr(self, method_name, getattr(self.metadata, method_name)) - - # 'cmdclass' maps command names to class objects, so we - # can 1) quickly figure out which class to instantiate when - # we need to create a new command object, and 2) have a way - # for the setup script to override command classes - self.cmdclass: dict[str, type[Command]] = {} - - # 'command_packages' is a list of packages in which commands - # are searched for. The factory for command 'foo' is expected - # to be named 'foo' in the module 'foo' in one of the packages - # named here. This list is searched from the left; an error - # is raised if no named package provides the command being - # searched for. (Always access using get_command_packages().) - self.command_packages: str | list[str] | None = None - - # 'script_name' and 'script_args' are usually set to sys.argv[0] - # and sys.argv[1:], but they can be overridden when the caller is - # not necessarily a setup script run from the command-line. - self.script_name: str | os.PathLike[str] | None = None - self.script_args: list[str] | None = None - - # 'command_options' is where we store command options between - # parsing them (from config files, the command-line, etc.) and when - # they are actually needed -- ie. when the command in question is - # instantiated. It is a dictionary of dictionaries of 2-tuples: - # command_options = { command_name : { option : (source, value) } } - self.command_options: dict[str, dict[str, tuple[str, str]]] = {} - - # 'dist_files' is the list of (command, pyversion, file) that - # have been created by any dist commands run so far. This is - # filled regardless of whether the run is dry or not. pyversion - # gives sysconfig.get_python_version() if the dist file is - # specific to a Python version, 'any' if it is good for all - # Python versions on the target platform, and '' for a source - # file. pyversion should not be used to specify minimum or - # maximum required Python versions; use the metainfo for that - # instead. - self.dist_files: list[tuple[str, str, str]] = [] - - # These options are really the business of various commands, rather - # than of the Distribution itself. We provide aliases for them in - # Distribution as a convenience to the developer. - self.packages = None - self.package_data: dict[str, list[str]] = {} - self.package_dir = None - self.py_modules = None - self.libraries = None - self.headers = None - self.ext_modules = None - self.ext_package = None - self.include_dirs = None - self.extra_path = None - self.scripts = None - self.data_files = None - self.password = '' - - # And now initialize bookkeeping stuff that can't be supplied by - # the caller at all. 'command_obj' maps command names to - # Command instances -- that's how we enforce that every command - # class is a singleton. - self.command_obj: dict[str, Command] = {} - - # 'have_run' maps command names to boolean values; it keeps track - # of whether we have actually run a particular command, to make it - # cheap to "run" a command whenever we think we might need to -- if - # it's already been done, no need for expensive filesystem - # operations, we just check the 'have_run' dictionary and carry on. - # It's only safe to query 'have_run' for a command class that has - # been instantiated -- a false value will be inserted when the - # command object is created, and replaced with a true value when - # the command is successfully run. Thus it's probably best to use - # '.get()' rather than a straight lookup. - self.have_run: dict[str, bool] = {} - - # Now we'll use the attrs dictionary (ultimately, keyword args from - # the setup script) to possibly override any or all of these - # distribution options. - - if attrs: - # Pull out the set of command options and work on them - # specifically. Note that this order guarantees that aliased - # command options will override any supplied redundantly - # through the general options dictionary. - options = attrs.get('options') - if options is not None: - del attrs['options'] - for command, cmd_options in options.items(): - opt_dict = self.get_option_dict(command) - for opt, val in cmd_options.items(): - opt_dict[opt] = ("setup script", val) - - if 'licence' in attrs: - attrs['license'] = attrs['licence'] - del attrs['licence'] - msg = "'licence' distribution option is deprecated; use 'license'" - warnings.warn(msg) - - # Now work on the rest of the attributes. Any attribute that's - # not already defined is invalid! - for key, val in attrs.items(): - if hasattr(self.metadata, "set_" + key): - getattr(self.metadata, "set_" + key)(val) - elif hasattr(self.metadata, key): - setattr(self.metadata, key, val) - elif hasattr(self, key): - setattr(self, key, val) - else: - msg = f"Unknown distribution option: {key!r}" - warnings.warn(msg) - - # no-user-cfg is handled before other command line args - # because other args override the config files, and this - # one is needed before we can load the config files. - # If attrs['script_args'] wasn't passed, assume false. - # - # This also make sure we just look at the global options - self.want_user_cfg = True - - if self.script_args is not None: - # Coerce any possible iterable from attrs into a list - self.script_args = list(self.script_args) - for arg in self.script_args: - if not arg.startswith('-'): - break - if arg == '--no-user-cfg': - self.want_user_cfg = False - break - - self.finalize_options() - - def get_option_dict(self, command): - """Get the option dictionary for a given command. If that - command's option dictionary hasn't been created yet, then create it - and return the new dictionary; otherwise, return the existing - option dictionary. - """ - dict = self.command_options.get(command) - if dict is None: - dict = self.command_options[command] = {} - return dict - - def dump_option_dicts(self, header=None, commands=None, indent: str = "") -> None: - from pprint import pformat - - if commands is None: # dump all command option dicts - commands = sorted(self.command_options.keys()) - - if header is not None: - self.announce(indent + header) - indent = indent + " " - - if not commands: - self.announce(indent + "no commands known yet") - return - - for cmd_name in commands: - opt_dict = self.command_options.get(cmd_name) - if opt_dict is None: - self.announce(indent + f"no option dict for '{cmd_name}' command") - else: - self.announce(indent + f"option dict for '{cmd_name}' command:") - out = pformat(opt_dict) - for line in out.split('\n'): - self.announce(indent + " " + line) - - # -- Config file finding/parsing methods --------------------------- - - def find_config_files(self): - """Find as many configuration files as should be processed for this - platform, and return a list of filenames in the order in which they - should be parsed. The filenames returned are guaranteed to exist - (modulo nasty race conditions). - - There are multiple possible config files: - - distutils.cfg in the Distutils installation directory (i.e. - where the top-level Distutils __inst__.py file lives) - - a file in the user's home directory named .pydistutils.cfg - on Unix and pydistutils.cfg on Windows/Mac; may be disabled - with the ``--no-user-cfg`` option - - setup.cfg in the current directory - - a file named by an environment variable - """ - check_environ() - files = [str(path) for path in self._gen_paths() if os.path.isfile(path)] - - if DEBUG: - self.announce("using config files: {}".format(', '.join(files))) - - return files - - def _gen_paths(self): - # The system-wide Distutils config file - sys_dir = pathlib.Path(sys.modules['distutils'].__file__).parent - yield sys_dir / "distutils.cfg" - - # The per-user config file - prefix = '.' * (os.name == 'posix') - filename = prefix + 'pydistutils.cfg' - if self.want_user_cfg: - with contextlib.suppress(RuntimeError): - yield pathlib.Path('~').expanduser() / filename - - # All platforms support local setup.cfg - yield pathlib.Path('setup.cfg') - - # Additional config indicated in the environment - with contextlib.suppress(TypeError): - yield pathlib.Path(os.getenv("DIST_EXTRA_CONFIG")) - - def parse_config_files(self, filenames=None): # noqa: C901 - from configparser import ConfigParser - - # Ignore install directory options if we have a venv - if sys.prefix != sys.base_prefix: - ignore_options = [ - 'install-base', - 'install-platbase', - 'install-lib', - 'install-platlib', - 'install-purelib', - 'install-headers', - 'install-scripts', - 'install-data', - 'prefix', - 'exec-prefix', - 'home', - 'user', - 'root', - ] - else: - ignore_options = [] - - ignore_options = frozenset(ignore_options) - - if filenames is None: - filenames = self.find_config_files() - - if DEBUG: - self.announce("Distribution.parse_config_files():") - - parser = ConfigParser() - for filename in filenames: - if DEBUG: - self.announce(f" reading {filename}") - parser.read(filename, encoding='utf-8') - for section in parser.sections(): - options = parser.options(section) - opt_dict = self.get_option_dict(section) - - for opt in options: - if opt != '__name__' and opt not in ignore_options: - val = parser.get(section, opt) - opt = opt.replace('-', '_') - opt_dict[opt] = (filename, val) - - # Make the ConfigParser forget everything (so we retain - # the original filenames that options come from) - parser.__init__() - - # If there was a "global" section in the config file, use it - # to set Distribution options. - - if 'global' in self.command_options: - for opt, (_src, val) in self.command_options['global'].items(): - alias = self.negative_opt.get(opt) - try: - if alias: - setattr(self, alias, not strtobool(val)) - elif opt in ('verbose', 'dry_run'): # ugh! - setattr(self, opt, strtobool(val)) - else: - setattr(self, opt, val) - except ValueError as msg: - raise DistutilsOptionError(msg) - - # -- Command-line parsing methods ---------------------------------- - - def parse_command_line(self): - """Parse the setup script's command line, taken from the - 'script_args' instance attribute (which defaults to 'sys.argv[1:]' - -- see 'setup()' in core.py). This list is first processed for - "global options" -- options that set attributes of the Distribution - instance. Then, it is alternately scanned for Distutils commands - and options for that command. Each new command terminates the - options for the previous command. The allowed options for a - command are determined by the 'user_options' attribute of the - command class -- thus, we have to be able to load command classes - in order to parse the command line. Any error in that 'options' - attribute raises DistutilsGetoptError; any error on the - command-line raises DistutilsArgError. If no Distutils commands - were found on the command line, raises DistutilsArgError. Return - true if command-line was successfully parsed and we should carry - on with executing commands; false if no errors but we shouldn't - execute commands (currently, this only happens if user asks for - help). - """ - # - # We now have enough information to show the Macintosh dialog - # that allows the user to interactively specify the "command line". - # - toplevel_options = self._get_toplevel_options() - - # We have to parse the command line a bit at a time -- global - # options, then the first command, then its options, and so on -- - # because each command will be handled by a different class, and - # the options that are valid for a particular class aren't known - # until we have loaded the command class, which doesn't happen - # until we know what the command is. - - self.commands = [] - parser = FancyGetopt(toplevel_options + self.display_options) - parser.set_negative_aliases(self.negative_opt) - parser.set_aliases({'licence': 'license'}) - args = parser.getopt(args=self.script_args, object=self) - option_order = parser.get_option_order() - logging.getLogger().setLevel(logging.WARN - 10 * self.verbose) - - # for display options we return immediately - if self.handle_display_options(option_order): - return - while args: - args = self._parse_command_opts(parser, args) - if args is None: # user asked for help (and got it) - return - - # Handle the cases of --help as a "global" option, ie. - # "setup.py --help" and "setup.py --help command ...". For the - # former, we show global options (--verbose, --dry-run, etc.) - # and display-only options (--name, --version, etc.); for the - # latter, we omit the display-only options and show help for - # each command listed on the command line. - if self.help: - self._show_help( - parser, display_options=len(self.commands) == 0, commands=self.commands - ) - return - - # Oops, no commands found -- an end-user error - if not self.commands: - raise DistutilsArgError("no commands supplied") - - # All is well: return true - return True - - def _get_toplevel_options(self): - """Return the non-display options recognized at the top level. - - This includes options that are recognized *only* at the top - level as well as options recognized for commands. - """ - return self.global_options + [ - ( - "command-packages=", - None, - "list of packages that provide distutils commands", - ), - ] - - def _parse_command_opts(self, parser, args): # noqa: C901 - """Parse the command-line options for a single command. - 'parser' must be a FancyGetopt instance; 'args' must be the list - of arguments, starting with the current command (whose options - we are about to parse). Returns a new version of 'args' with - the next command at the front of the list; will be the empty - list if there are no more commands on the command line. Returns - None if the user asked for help on this command. - """ - # late import because of mutual dependence between these modules - from distutils.cmd import Command - - # Pull the current command from the head of the command line - command = args[0] - if not command_re.match(command): - raise SystemExit(f"invalid command name '{command}'") - self.commands.append(command) - - # Dig up the command class that implements this command, so we - # 1) know that it's a valid command, and 2) know which options - # it takes. - try: - cmd_class = self.get_command_class(command) - except DistutilsModuleError as msg: - raise DistutilsArgError(msg) - - # Require that the command class be derived from Command -- want - # to be sure that the basic "command" interface is implemented. - if not issubclass(cmd_class, Command): - raise DistutilsClassError( - f"command class {cmd_class} must subclass Command" - ) - - # Also make sure that the command object provides a list of its - # known options. - if not ( - hasattr(cmd_class, 'user_options') - and isinstance(cmd_class.user_options, list) - ): - msg = ( - "command class %s must provide " - "'user_options' attribute (a list of tuples)" - ) - raise DistutilsClassError(msg % cmd_class) - - # If the command class has a list of negative alias options, - # merge it in with the global negative aliases. - negative_opt = self.negative_opt - if hasattr(cmd_class, 'negative_opt'): - negative_opt = negative_opt.copy() - negative_opt.update(cmd_class.negative_opt) - - # Check for help_options in command class. They have a different - # format (tuple of four) so we need to preprocess them here. - if hasattr(cmd_class, 'help_options') and isinstance( - cmd_class.help_options, list - ): - help_options = fix_help_options(cmd_class.help_options) - else: - help_options = [] - - # All commands support the global options too, just by adding - # in 'global_options'. - parser.set_option_table( - self.global_options + cmd_class.user_options + help_options - ) - parser.set_negative_aliases(negative_opt) - (args, opts) = parser.getopt(args[1:]) - if hasattr(opts, 'help') and opts.help: - self._show_help(parser, display_options=False, commands=[cmd_class]) - return - - if hasattr(cmd_class, 'help_options') and isinstance( - cmd_class.help_options, list - ): - help_option_found = 0 - for help_option, _short, _desc, func in cmd_class.help_options: - if hasattr(opts, parser.get_attr_name(help_option)): - help_option_found = 1 - if callable(func): - func() - else: - raise DistutilsClassError( - f"invalid help function {func!r} for help option '{help_option}': " - "must be a callable object (function, etc.)" - ) - - if help_option_found: - return - - # Put the options from the command-line into their official - # holding pen, the 'command_options' dictionary. - opt_dict = self.get_option_dict(command) - for name, value in vars(opts).items(): - opt_dict[name] = ("command line", value) - - return args - - def finalize_options(self) -> None: - """Set final values for all the options on the Distribution - instance, analogous to the .finalize_options() method of Command - objects. - """ - for attr in ('keywords', 'platforms'): - value = getattr(self.metadata, attr) - if value is None: - continue - if isinstance(value, str): - value = [elm.strip() for elm in value.split(',')] - setattr(self.metadata, attr, value) - - def _show_help( - self, parser, global_options=True, display_options=True, commands: Iterable = () - ): - """Show help for the setup script command-line in the form of - several lists of command-line options. 'parser' should be a - FancyGetopt instance; do not expect it to be returned in the - same state, as its option table will be reset to make it - generate the correct help text. - - If 'global_options' is true, lists the global options: - --verbose, --dry-run, etc. If 'display_options' is true, lists - the "display-only" options: --name, --version, etc. Finally, - lists per-command help for every command name or command class - in 'commands'. - """ - # late import because of mutual dependence between these modules - from distutils.cmd import Command - from distutils.core import gen_usage - - if global_options: - if display_options: - options = self._get_toplevel_options() - else: - options = self.global_options - parser.set_option_table(options) - parser.print_help(self.common_usage + "\nGlobal options:") - print() - - if display_options: - parser.set_option_table(self.display_options) - parser.print_help( - "Information display options (just display information, ignore any commands)" - ) - print() - - for command in commands: - if isinstance(command, type) and issubclass(command, Command): - klass = command - else: - klass = self.get_command_class(command) - if hasattr(klass, 'help_options') and isinstance(klass.help_options, list): - parser.set_option_table( - klass.user_options + fix_help_options(klass.help_options) - ) - else: - parser.set_option_table(klass.user_options) - parser.print_help(f"Options for '{klass.__name__}' command:") - print() - - print(gen_usage(self.script_name)) - - def handle_display_options(self, option_order): - """If there were any non-global "display-only" options - (--help-commands or the metadata display options) on the command - line, display the requested info and return true; else return - false. - """ - from distutils.core import gen_usage - - # User just wants a list of commands -- we'll print it out and stop - # processing now (ie. if they ran "setup --help-commands foo bar", - # we ignore "foo bar"). - if self.help_commands: - self.print_commands() - print() - print(gen_usage(self.script_name)) - return 1 - - # If user supplied any of the "display metadata" options, then - # display that metadata in the order in which the user supplied the - # metadata options. - any_display_options = 0 - is_display_option = set() - for option in self.display_options: - is_display_option.add(option[0]) - - for opt, val in option_order: - if val and opt in is_display_option: - opt = translate_longopt(opt) - value = getattr(self.metadata, "get_" + opt)() - if opt in ('keywords', 'platforms'): - print(','.join(value)) - elif opt in ('classifiers', 'provides', 'requires', 'obsoletes'): - print('\n'.join(value)) - else: - print(value) - any_display_options = 1 - - return any_display_options - - def print_command_list(self, commands, header, max_length) -> None: - """Print a subset of the list of all commands -- used by - 'print_commands()'. - """ - print(header + ":") - - for cmd in commands: - klass = self.cmdclass.get(cmd) - if not klass: - klass = self.get_command_class(cmd) - try: - description = klass.description - except AttributeError: - description = "(no description available)" - - print(f" {cmd:<{max_length}} {description}") - - def print_commands(self) -> None: - """Print out a help message listing all available commands with a - description of each. The list is divided into "standard commands" - (listed in distutils.command.__all__) and "extra commands" - (mentioned in self.cmdclass, but not a standard command). The - descriptions come from the command class attribute - 'description'. - """ - import distutils.command - - std_commands = distutils.command.__all__ - is_std = set(std_commands) - - extra_commands = [cmd for cmd in self.cmdclass.keys() if cmd not in is_std] - - max_length = 0 - for cmd in std_commands + extra_commands: - if len(cmd) > max_length: - max_length = len(cmd) - - self.print_command_list(std_commands, "Standard commands", max_length) - if extra_commands: - print() - self.print_command_list(extra_commands, "Extra commands", max_length) - - def get_command_list(self): - """Get a list of (command, description) tuples. - The list is divided into "standard commands" (listed in - distutils.command.__all__) and "extra commands" (mentioned in - self.cmdclass, but not a standard command). The descriptions come - from the command class attribute 'description'. - """ - # Currently this is only used on Mac OS, for the Mac-only GUI - # Distutils interface (by Jack Jansen) - import distutils.command - - std_commands = distutils.command.__all__ - is_std = set(std_commands) - - extra_commands = [cmd for cmd in self.cmdclass.keys() if cmd not in is_std] - - rv = [] - for cmd in std_commands + extra_commands: - klass = self.cmdclass.get(cmd) - if not klass: - klass = self.get_command_class(cmd) - try: - description = klass.description - except AttributeError: - description = "(no description available)" - rv.append((cmd, description)) - return rv - - # -- Command class/object methods ---------------------------------- - - def get_command_packages(self): - """Return a list of packages from which commands are loaded.""" - pkgs = self.command_packages - if not isinstance(pkgs, list): - if pkgs is None: - pkgs = '' - pkgs = [pkg.strip() for pkg in pkgs.split(',') if pkg != ''] - if "distutils.command" not in pkgs: - pkgs.insert(0, "distutils.command") - self.command_packages = pkgs - return pkgs - - def get_command_class(self, command: str) -> type[Command]: - """Return the class that implements the Distutils command named by - 'command'. First we check the 'cmdclass' dictionary; if the - command is mentioned there, we fetch the class object from the - dictionary and return it. Otherwise we load the command module - ("distutils.command." + command) and fetch the command class from - the module. The loaded class is also stored in 'cmdclass' - to speed future calls to 'get_command_class()'. - - Raises DistutilsModuleError if the expected module could not be - found, or if that module does not define the expected class. - """ - klass = self.cmdclass.get(command) - if klass: - return klass - - for pkgname in self.get_command_packages(): - module_name = f"{pkgname}.{command}" - klass_name = command - - try: - __import__(module_name) - module = sys.modules[module_name] - except ImportError: - continue - - try: - klass = getattr(module, klass_name) - except AttributeError: - raise DistutilsModuleError( - f"invalid command '{command}' (no class '{klass_name}' in module '{module_name}')" - ) - - self.cmdclass[command] = klass - return klass - - raise DistutilsModuleError(f"invalid command '{command}'") - - @overload - def get_command_obj( - self, command: str, create: Literal[True] = True - ) -> Command: ... - @overload - def get_command_obj( - self, command: str, create: Literal[False] - ) -> Command | None: ... - def get_command_obj(self, command: str, create: bool = True) -> Command | None: - """Return the command object for 'command'. Normally this object - is cached on a previous call to 'get_command_obj()'; if no command - object for 'command' is in the cache, then we either create and - return it (if 'create' is true) or return None. - """ - cmd_obj = self.command_obj.get(command) - if not cmd_obj and create: - if DEBUG: - self.announce( - "Distribution.get_command_obj(): " - f"creating '{command}' command object" - ) - - klass = self.get_command_class(command) - cmd_obj = self.command_obj[command] = klass(self) - self.have_run[command] = False - - # Set any options that were supplied in config files - # or on the command line. (NB. support for error - # reporting is lame here: any errors aren't reported - # until 'finalize_options()' is called, which means - # we won't report the source of the error.) - options = self.command_options.get(command) - if options: - self._set_command_options(cmd_obj, options) - - return cmd_obj - - def _set_command_options(self, command_obj, option_dict=None): # noqa: C901 - """Set the options for 'command_obj' from 'option_dict'. Basically - this means copying elements of a dictionary ('option_dict') to - attributes of an instance ('command'). - - 'command_obj' must be a Command instance. If 'option_dict' is not - supplied, uses the standard option dictionary for this command - (from 'self.command_options'). - """ - command_name = command_obj.get_command_name() - if option_dict is None: - option_dict = self.get_option_dict(command_name) - - if DEBUG: - self.announce(f" setting options for '{command_name}' command:") - for option, (source, value) in option_dict.items(): - if DEBUG: - self.announce(f" {option} = {value} (from {source})") - try: - bool_opts = [translate_longopt(o) for o in command_obj.boolean_options] - except AttributeError: - bool_opts = [] - try: - neg_opt = command_obj.negative_opt - except AttributeError: - neg_opt = {} - - try: - is_string = isinstance(value, str) - if option in neg_opt and is_string: - setattr(command_obj, neg_opt[option], not strtobool(value)) - elif option in bool_opts and is_string: - setattr(command_obj, option, strtobool(value)) - elif hasattr(command_obj, option): - setattr(command_obj, option, value) - else: - raise DistutilsOptionError( - f"error in {source}: command '{command_name}' has no such option '{option}'" - ) - except ValueError as msg: - raise DistutilsOptionError(msg) - - @overload - def reinitialize_command( - self, command: str, reinit_subcommands: bool = False - ) -> Command: ... - @overload - def reinitialize_command( - self, command: _CommandT, reinit_subcommands: bool = False - ) -> _CommandT: ... - def reinitialize_command( - self, command: str | Command, reinit_subcommands=False - ) -> Command: - """Reinitializes a command to the state it was in when first - returned by 'get_command_obj()': ie., initialized but not yet - finalized. This provides the opportunity to sneak option - values in programmatically, overriding or supplementing - user-supplied values from the config files and command line. - You'll have to re-finalize the command object (by calling - 'finalize_options()' or 'ensure_finalized()') before using it for - real. - - 'command' should be a command name (string) or command object. If - 'reinit_subcommands' is true, also reinitializes the command's - sub-commands, as declared by the 'sub_commands' class attribute (if - it has one). See the "install" command for an example. Only - reinitializes the sub-commands that actually matter, ie. those - whose test predicates return true. - - Returns the reinitialized command object. - """ - from distutils.cmd import Command - - if not isinstance(command, Command): - command_name = command - command = self.get_command_obj(command_name) - else: - command_name = command.get_command_name() - - if not command.finalized: - return command - command.initialize_options() - command.finalized = False - self.have_run[command_name] = False - self._set_command_options(command) - - if reinit_subcommands: - for sub in command.get_sub_commands(): - self.reinitialize_command(sub, reinit_subcommands) - - return command - - # -- Methods that operate on the Distribution ---------------------- - - def announce(self, msg, level: int = logging.INFO) -> None: - log.log(level, msg) - - def run_commands(self) -> None: - """Run each command that was seen on the setup script command line. - Uses the list of commands found and cache of command objects - created by 'get_command_obj()'. - """ - for cmd in self.commands: - self.run_command(cmd) - - # -- Methods that operate on its Commands -------------------------- - - def run_command(self, command: str) -> None: - """Do whatever it takes to run a command (including nothing at all, - if the command has already been run). Specifically: if we have - already created and run the command named by 'command', return - silently without doing anything. If the command named by 'command' - doesn't even have a command object yet, create one. Then invoke - 'run()' on that command object (or an existing one). - """ - # Already been here, done that? then return silently. - if self.have_run.get(command): - return - - log.info("running %s", command) - cmd_obj = self.get_command_obj(command) - cmd_obj.ensure_finalized() - cmd_obj.run() - self.have_run[command] = True - - # -- Distribution query methods ------------------------------------ - - def has_pure_modules(self) -> bool: - return len(self.packages or self.py_modules or []) > 0 - - def has_ext_modules(self) -> bool: - return self.ext_modules and len(self.ext_modules) > 0 - - def has_c_libraries(self) -> bool: - return self.libraries and len(self.libraries) > 0 - - def has_modules(self) -> bool: - return self.has_pure_modules() or self.has_ext_modules() - - def has_headers(self) -> bool: - return self.headers and len(self.headers) > 0 - - def has_scripts(self) -> bool: - return self.scripts and len(self.scripts) > 0 - - def has_data_files(self) -> bool: - return self.data_files and len(self.data_files) > 0 - - def is_pure(self) -> bool: - return ( - self.has_pure_modules() - and not self.has_ext_modules() - and not self.has_c_libraries() - ) - - # -- Metadata query methods ---------------------------------------- - - # If you're looking for 'get_name()', 'get_version()', and so forth, - # they are defined in a sneaky way: the constructor binds self.get_XXX - # to self.metadata.get_XXX. The actual code is in the - # DistributionMetadata class, below. - if TYPE_CHECKING: - # Unfortunately this means we need to specify them manually or not expose statically - def _(self) -> None: - self.get_name = self.metadata.get_name - self.get_version = self.metadata.get_version - self.get_fullname = self.metadata.get_fullname - self.get_author = self.metadata.get_author - self.get_author_email = self.metadata.get_author_email - self.get_maintainer = self.metadata.get_maintainer - self.get_maintainer_email = self.metadata.get_maintainer_email - self.get_contact = self.metadata.get_contact - self.get_contact_email = self.metadata.get_contact_email - self.get_url = self.metadata.get_url - self.get_license = self.metadata.get_license - self.get_licence = self.metadata.get_licence - self.get_description = self.metadata.get_description - self.get_long_description = self.metadata.get_long_description - self.get_keywords = self.metadata.get_keywords - self.get_platforms = self.metadata.get_platforms - self.get_classifiers = self.metadata.get_classifiers - self.get_download_url = self.metadata.get_download_url - self.get_requires = self.metadata.get_requires - self.get_provides = self.metadata.get_provides - self.get_obsoletes = self.metadata.get_obsoletes - - # Default attributes generated in __init__ from self.display_option_names - help_commands: bool - name: str | Literal[False] - version: str | Literal[False] - fullname: str | Literal[False] - author: str | Literal[False] - author_email: str | Literal[False] - maintainer: str | Literal[False] - maintainer_email: str | Literal[False] - contact: str | Literal[False] - contact_email: str | Literal[False] - url: str | Literal[False] - license: str | Literal[False] - licence: str | Literal[False] - description: str | Literal[False] - long_description: str | Literal[False] - platforms: str | list[str] | Literal[False] - classifiers: str | list[str] | Literal[False] - keywords: str | list[str] | Literal[False] - provides: list[str] | Literal[False] - requires: list[str] | Literal[False] - obsoletes: list[str] | Literal[False] - - -class DistributionMetadata: - """Dummy class to hold the distribution meta-data: name, version, - author, and so forth. - """ - - _METHOD_BASENAMES = ( - "name", - "version", - "author", - "author_email", - "maintainer", - "maintainer_email", - "url", - "license", - "description", - "long_description", - "keywords", - "platforms", - "fullname", - "contact", - "contact_email", - "classifiers", - "download_url", - # PEP 314 - "provides", - "requires", - "obsoletes", - ) - - def __init__( - self, path: str | bytes | os.PathLike[str] | os.PathLike[bytes] | None = None - ) -> None: - if path is not None: - self.read_pkg_file(open(path)) - else: - self.name: str | None = None - self.version: str | None = None - self.author: str | None = None - self.author_email: str | None = None - self.maintainer: str | None = None - self.maintainer_email: str | None = None - self.url: str | None = None - self.license: str | None = None - self.description: str | None = None - self.long_description: str | None = None - self.keywords: str | list[str] | None = None - self.platforms: str | list[str] | None = None - self.classifiers: str | list[str] | None = None - self.download_url: str | None = None - # PEP 314 - self.provides: str | list[str] | None = None - self.requires: str | list[str] | None = None - self.obsoletes: str | list[str] | None = None - - def read_pkg_file(self, file: IO[str]) -> None: - """Reads the metadata values from a file object.""" - msg = message_from_file(file) - - def _read_field(name: str) -> str | None: - value = msg[name] - if value and value != "UNKNOWN": - return value - return None - - def _read_list(name): - values = msg.get_all(name, None) - if values == []: - return None - return values - - metadata_version = msg['metadata-version'] - self.name = _read_field('name') - self.version = _read_field('version') - self.description = _read_field('summary') - # we are filling author only. - self.author = _read_field('author') - self.maintainer = None - self.author_email = _read_field('author-email') - self.maintainer_email = None - self.url = _read_field('home-page') - self.license = _read_field('license') - - if 'download-url' in msg: - self.download_url = _read_field('download-url') - else: - self.download_url = None - - self.long_description = _read_field('description') - self.description = _read_field('summary') - - if 'keywords' in msg: - self.keywords = _read_field('keywords').split(',') - - self.platforms = _read_list('platform') - self.classifiers = _read_list('classifier') - - # PEP 314 - these fields only exist in 1.1 - if metadata_version == '1.1': - self.requires = _read_list('requires') - self.provides = _read_list('provides') - self.obsoletes = _read_list('obsoletes') - else: - self.requires = None - self.provides = None - self.obsoletes = None - - def write_pkg_info(self, base_dir: str | os.PathLike[str]) -> None: - """Write the PKG-INFO file into the release tree.""" - with open( - os.path.join(base_dir, 'PKG-INFO'), 'w', encoding='UTF-8' - ) as pkg_info: - self.write_pkg_file(pkg_info) - - def write_pkg_file(self, file: SupportsWrite[str]) -> None: - """Write the PKG-INFO format data to a file object.""" - version = '1.0' - if ( - self.provides - or self.requires - or self.obsoletes - or self.classifiers - or self.download_url - ): - version = '1.1' - - # required fields - file.write(f'Metadata-Version: {version}\n') - file.write(f'Name: {self.get_name()}\n') - file.write(f'Version: {self.get_version()}\n') - - def maybe_write(header, val): - if val: - file.write(f"{header}: {val}\n") - - # optional fields - maybe_write("Summary", self.get_description()) - maybe_write("Home-page", self.get_url()) - maybe_write("Author", self.get_contact()) - maybe_write("Author-email", self.get_contact_email()) - maybe_write("License", self.get_license()) - maybe_write("Download-URL", self.download_url) - maybe_write("Description", rfc822_escape(self.get_long_description() or "")) - maybe_write("Keywords", ",".join(self.get_keywords())) - - self._write_list(file, 'Platform', self.get_platforms()) - self._write_list(file, 'Classifier', self.get_classifiers()) - - # PEP 314 - self._write_list(file, 'Requires', self.get_requires()) - self._write_list(file, 'Provides', self.get_provides()) - self._write_list(file, 'Obsoletes', self.get_obsoletes()) - - def _write_list(self, file, name, values): - values = values or [] - for value in values: - file.write(f'{name}: {value}\n') - - # -- Metadata query methods ---------------------------------------- - - def get_name(self) -> str: - return self.name or "UNKNOWN" - - def get_version(self) -> str: - return self.version or "0.0.0" - - def get_fullname(self) -> str: - return self._fullname(self.get_name(), self.get_version()) - - @staticmethod - def _fullname(name: str, version: str) -> str: - """ - >>> DistributionMetadata._fullname('setup.tools', '1.0-2') - 'setup_tools-1.0.post2' - >>> DistributionMetadata._fullname('setup-tools', '1.2post2') - 'setup_tools-1.2.post2' - >>> DistributionMetadata._fullname('setup-tools', '1.0-r2') - 'setup_tools-1.0.post2' - >>> DistributionMetadata._fullname('setup.tools', '1.0.post') - 'setup_tools-1.0.post0' - >>> DistributionMetadata._fullname('setup.tools', '1.0+ubuntu-1') - 'setup_tools-1.0+ubuntu.1' - """ - return "{}-{}".format( - canonicalize_name(name).replace('-', '_'), - canonicalize_version(version, strip_trailing_zero=False), - ) - - def get_author(self) -> str | None: - return self.author - - def get_author_email(self) -> str | None: - return self.author_email - - def get_maintainer(self) -> str | None: - return self.maintainer - - def get_maintainer_email(self) -> str | None: - return self.maintainer_email - - def get_contact(self) -> str | None: - return self.maintainer or self.author - - def get_contact_email(self) -> str | None: - return self.maintainer_email or self.author_email - - def get_url(self) -> str | None: - return self.url - - def get_license(self) -> str | None: - return self.license - - get_licence = get_license - - def get_description(self) -> str | None: - return self.description - - def get_long_description(self) -> str | None: - return self.long_description - - def get_keywords(self) -> str | list[str]: - return self.keywords or [] - - def set_keywords(self, value: str | Iterable[str]) -> None: - self.keywords = _ensure_list(value, 'keywords') - - def get_platforms(self) -> str | list[str] | None: - return self.platforms - - def set_platforms(self, value: str | Iterable[str]) -> None: - self.platforms = _ensure_list(value, 'platforms') - - def get_classifiers(self) -> str | list[str]: - return self.classifiers or [] - - def set_classifiers(self, value: str | Iterable[str]) -> None: - self.classifiers = _ensure_list(value, 'classifiers') - - def get_download_url(self) -> str | None: - return self.download_url - - # PEP 314 - def get_requires(self) -> str | list[str]: - return self.requires or [] - - def set_requires(self, value: Iterable[str]) -> None: - import distutils.versionpredicate - - for v in value: - distutils.versionpredicate.VersionPredicate(v) - self.requires = list(value) - - def get_provides(self) -> str | list[str]: - return self.provides or [] - - def set_provides(self, value: Iterable[str]) -> None: - value = [v.strip() for v in value] - for v in value: - import distutils.versionpredicate - - distutils.versionpredicate.split_provision(v) - self.provides = value - - def get_obsoletes(self) -> str | list[str]: - return self.obsoletes or [] - - def set_obsoletes(self, value: Iterable[str]) -> None: - import distutils.versionpredicate - - for v in value: - distutils.versionpredicate.VersionPredicate(v) - self.obsoletes = list(value) - - -def fix_help_options(options): - """Convert a 4-tuple 'help_options' list as found in various command - classes to the 3-tuple form required by FancyGetopt. - """ - return [opt[0:3] for opt in options] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/errors.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/errors.py deleted file mode 100644 index 409d21f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/errors.py +++ /dev/null @@ -1,108 +0,0 @@ -""" -Exceptions used by the Distutils modules. - -Distutils modules may raise these or standard exceptions, -including :exc:`SystemExit`. -""" - -# compiler exceptions aliased for compatibility -from .compilers.C.errors import CompileError as CompileError -from .compilers.C.errors import Error as _Error -from .compilers.C.errors import LibError as LibError -from .compilers.C.errors import LinkError as LinkError -from .compilers.C.errors import PreprocessError as PreprocessError -from .compilers.C.errors import UnknownFileType as _UnknownFileType - -CCompilerError = _Error -UnknownFileError = _UnknownFileType - - -class DistutilsError(Exception): - """The root of all Distutils evil.""" - - pass - - -class DistutilsModuleError(DistutilsError): - """Unable to load an expected module, or to find an expected class - within some module (in particular, command modules and classes).""" - - pass - - -class DistutilsClassError(DistutilsError): - """Some command class (or possibly distribution class, if anyone - feels a need to subclass Distribution) is found not to be holding - up its end of the bargain, ie. implementing some part of the - "command "interface.""" - - pass - - -class DistutilsGetoptError(DistutilsError): - """The option table provided to 'fancy_getopt()' is bogus.""" - - pass - - -class DistutilsArgError(DistutilsError): - """Raised by fancy_getopt in response to getopt.error -- ie. an - error in the command line usage.""" - - pass - - -class DistutilsFileError(DistutilsError): - """Any problems in the filesystem: expected file not found, etc. - Typically this is for problems that we detect before OSError - could be raised.""" - - pass - - -class DistutilsOptionError(DistutilsError): - """Syntactic/semantic errors in command options, such as use of - mutually conflicting options, or inconsistent options, - badly-spelled values, etc. No distinction is made between option - values originating in the setup script, the command line, config - files, or what-have-you -- but if we *know* something originated in - the setup script, we'll raise DistutilsSetupError instead.""" - - pass - - -class DistutilsSetupError(DistutilsError): - """For errors that can be definitely blamed on the setup script, - such as invalid keyword arguments to 'setup()'.""" - - pass - - -class DistutilsPlatformError(DistutilsError): - """We don't know how to do something on the current platform (but - we do know how to do it on some platform) -- eg. trying to compile - C files on a platform not supported by a CCompiler subclass.""" - - pass - - -class DistutilsExecError(DistutilsError): - """Any problems executing an external program (such as the C - compiler, when compiling C files).""" - - pass - - -class DistutilsInternalError(DistutilsError): - """Internal inconsistencies or impossibilities (obviously, this - should never be seen if the code is working!).""" - - pass - - -class DistutilsTemplateError(DistutilsError): - """Syntax error in a file list template.""" - - -class DistutilsByteCompileError(DistutilsError): - """Byte compile error.""" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/extension.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/extension.py deleted file mode 100644 index f514112..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/extension.py +++ /dev/null @@ -1,258 +0,0 @@ -"""distutils.extension - -Provides the Extension class, used to describe C/C++ extension -modules in setup scripts.""" - -from __future__ import annotations - -import os -import warnings -from collections.abc import Iterable - -# This class is really only used by the "build_ext" command, so it might -# make sense to put it in distutils.command.build_ext. However, that -# module is already big enough, and I want to make this class a bit more -# complex to simplify some common cases ("foo" module in "foo.c") and do -# better error-checking ("foo.c" actually exists). -# -# Also, putting this in build_ext.py means every setup script would have to -# import that large-ish module (indirectly, through distutils.core) in -# order to do anything. - - -class Extension: - """Just a collection of attributes that describes an extension - module and everything needed to build it (hopefully in a portable - way, but there are hooks that let you be as unportable as you need). - - Instance attributes: - name : string - the full name of the extension, including any packages -- ie. - *not* a filename or pathname, but Python dotted name - sources : Iterable[string | os.PathLike] - iterable of source filenames (except strings, which could be misinterpreted - as a single filename), relative to the distribution root (where the setup - script lives), in Unix form (slash-separated) for portability. Can be any - non-string iterable (list, tuple, set, etc.) containing strings or - PathLike objects. Source files may be C, C++, SWIG (.i), platform-specific - resource files, or whatever else is recognized by the "build_ext" command - as source for a Python extension. - include_dirs : [string] - list of directories to search for C/C++ header files (in Unix - form for portability) - define_macros : [(name : string, value : string|None)] - list of macros to define; each macro is defined using a 2-tuple, - where 'value' is either the string to define it to or None to - define it without a particular value (equivalent of "#define - FOO" in source or -DFOO on Unix C compiler command line) - undef_macros : [string] - list of macros to undefine explicitly - library_dirs : [string] - list of directories to search for C/C++ libraries at link time - libraries : [string] - list of library names (not filenames or paths) to link against - runtime_library_dirs : [string] - list of directories to search for C/C++ libraries at run time - (for shared extensions, this is when the extension is loaded) - extra_objects : [string] - list of extra files to link with (eg. object files not implied - by 'sources', static library that must be explicitly specified, - binary resource files, etc.) - extra_compile_args : [string] - any extra platform- and compiler-specific information to use - when compiling the source files in 'sources'. For platforms and - compilers where "command line" makes sense, this is typically a - list of command-line arguments, but for other platforms it could - be anything. - extra_link_args : [string] - any extra platform- and compiler-specific information to use - when linking object files together to create the extension (or - to create a new static Python interpreter). Similar - interpretation as for 'extra_compile_args'. - export_symbols : [string] - list of symbols to be exported from a shared extension. Not - used on all platforms, and not generally necessary for Python - extensions, which typically export exactly one symbol: "init" + - extension_name. - swig_opts : [string] - any extra options to pass to SWIG if a source file has the .i - extension. - depends : [string] - list of files that the extension depends on - language : string - extension language (i.e. "c", "c++", "objc"). Will be detected - from the source extensions if not provided. - optional : boolean - specifies that a build failure in the extension should not abort the - build process, but simply not install the failing extension. - """ - - # When adding arguments to this constructor, be sure to update - # setup_keywords in core.py. - def __init__( - self, - name: str, - sources: Iterable[str | os.PathLike[str]], - include_dirs: list[str] | None = None, - define_macros: list[tuple[str, str | None]] | None = None, - undef_macros: list[str] | None = None, - library_dirs: list[str] | None = None, - libraries: list[str] | None = None, - runtime_library_dirs: list[str] | None = None, - extra_objects: list[str] | None = None, - extra_compile_args: list[str] | None = None, - extra_link_args: list[str] | None = None, - export_symbols: list[str] | None = None, - swig_opts: list[str] | None = None, - depends: list[str] | None = None, - language: str | None = None, - optional: bool | None = None, - **kw, # To catch unknown keywords - ): - if not isinstance(name, str): - raise TypeError("'name' must be a string") - - # handle the string case first; since strings are iterable, disallow them - if isinstance(sources, str): - raise TypeError( - "'sources' must be an iterable of strings or PathLike objects, not a string" - ) - - # now we check if it's iterable and contains valid types - try: - self.sources = list(map(os.fspath, sources)) - except TypeError: - raise TypeError( - "'sources' must be an iterable of strings or PathLike objects" - ) - - self.name = name - self.include_dirs = include_dirs or [] - self.define_macros = define_macros or [] - self.undef_macros = undef_macros or [] - self.library_dirs = library_dirs or [] - self.libraries = libraries or [] - self.runtime_library_dirs = runtime_library_dirs or [] - self.extra_objects = extra_objects or [] - self.extra_compile_args = extra_compile_args or [] - self.extra_link_args = extra_link_args or [] - self.export_symbols = export_symbols or [] - self.swig_opts = swig_opts or [] - self.depends = depends or [] - self.language = language - self.optional = optional - - # If there are unknown keyword options, warn about them - if len(kw) > 0: - options = [repr(option) for option in kw] - options = ', '.join(sorted(options)) - msg = f"Unknown Extension options: {options}" - warnings.warn(msg) - - def __repr__(self): - return f'<{self.__class__.__module__}.{self.__class__.__qualname__}({self.name!r}) at {id(self):#x}>' - - -def read_setup_file(filename): # noqa: C901 - """Reads a Setup file and returns Extension instances.""" - from distutils.sysconfig import _variable_rx, expand_makefile_vars, parse_makefile - from distutils.text_file import TextFile - from distutils.util import split_quoted - - # First pass over the file to gather "VAR = VALUE" assignments. - vars = parse_makefile(filename) - - # Second pass to gobble up the real content: lines of the form - # ... [ ...] [ ...] [ ...] - file = TextFile( - filename, - strip_comments=True, - skip_blanks=True, - join_lines=True, - lstrip_ws=True, - rstrip_ws=True, - ) - try: - extensions = [] - - while True: - line = file.readline() - if line is None: # eof - break - if _variable_rx.match(line): # VAR=VALUE, handled in first pass - continue - - if line[0] == line[-1] == "*": - file.warn(f"'{line}' lines not handled yet") - continue - - line = expand_makefile_vars(line, vars) - words = split_quoted(line) - - # NB. this parses a slightly different syntax than the old - # makesetup script: here, there must be exactly one extension per - # line, and it must be the first word of the line. I have no idea - # why the old syntax supported multiple extensions per line, as - # they all wind up being the same. - - module = words[0] - ext = Extension(module, []) - append_next_word = None - - for word in words[1:]: - if append_next_word is not None: - append_next_word.append(word) - append_next_word = None - continue - - suffix = os.path.splitext(word)[1] - switch = word[0:2] - value = word[2:] - - if suffix in (".c", ".cc", ".cpp", ".cxx", ".c++", ".m", ".mm"): - # hmm, should we do something about C vs. C++ sources? - # or leave it up to the CCompiler implementation to - # worry about? - ext.sources.append(word) - elif switch == "-I": - ext.include_dirs.append(value) - elif switch == "-D": - equals = value.find("=") - if equals == -1: # bare "-DFOO" -- no value - ext.define_macros.append((value, None)) - else: # "-DFOO=blah" - ext.define_macros.append((value[0:equals], value[equals + 2 :])) - elif switch == "-U": - ext.undef_macros.append(value) - elif switch == "-C": # only here 'cause makesetup has it! - ext.extra_compile_args.append(word) - elif switch == "-l": - ext.libraries.append(value) - elif switch == "-L": - ext.library_dirs.append(value) - elif switch == "-R": - ext.runtime_library_dirs.append(value) - elif word == "-rpath": - append_next_word = ext.runtime_library_dirs - elif word == "-Xlinker": - append_next_word = ext.extra_link_args - elif word == "-Xcompiler": - append_next_word = ext.extra_compile_args - elif switch == "-u": - ext.extra_link_args.append(word) - if not value: - append_next_word = ext.extra_link_args - elif suffix in (".a", ".so", ".sl", ".o", ".dylib"): - # NB. a really faithful emulation of makesetup would - # append a .o file to extra_objects only if it - # had a slash in it; otherwise, it would s/.o/.c/ - # and append it to sources. Hmmmm. - ext.extra_objects.append(word) - else: - file.warn(f"unrecognized argument '{word}'") - - extensions.append(ext) - finally: - file.close() - - return extensions diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/fancy_getopt.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/fancy_getopt.py deleted file mode 100644 index 1a1d3a0..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/fancy_getopt.py +++ /dev/null @@ -1,471 +0,0 @@ -"""distutils.fancy_getopt - -Wrapper around the standard getopt module that provides the following -additional features: - * short and long options are tied together - * options have help strings, so fancy_getopt could potentially - create a complete usage summary - * options set attributes of a passed-in object -""" - -from __future__ import annotations - -import getopt -import re -import string -import sys -from collections.abc import Sequence -from typing import Any - -from .errors import DistutilsArgError, DistutilsGetoptError - -# Much like command_re in distutils.core, this is close to but not quite -# the same as a Python NAME -- except, in the spirit of most GNU -# utilities, we use '-' in place of '_'. (The spirit of LISP lives on!) -# The similarities to NAME are again not a coincidence... -longopt_pat = r'[a-zA-Z](?:[a-zA-Z0-9-]*)' -longopt_re = re.compile(rf'^{longopt_pat}$') - -# For recognizing "negative alias" options, eg. "quiet=!verbose" -neg_alias_re = re.compile(f"^({longopt_pat})=!({longopt_pat})$") - -# This is used to translate long options to legitimate Python identifiers -# (for use as attributes of some object). -longopt_xlate = str.maketrans('-', '_') - - -class FancyGetopt: - """Wrapper around the standard 'getopt()' module that provides some - handy extra functionality: - * short and long options are tied together - * options have help strings, and help text can be assembled - from them - * options set attributes of a passed-in object - * boolean options can have "negative aliases" -- eg. if - --quiet is the "negative alias" of --verbose, then "--quiet" - on the command line sets 'verbose' to false - """ - - def __init__(self, option_table=None): - # The option table is (currently) a list of tuples. The - # tuples may have 3 or four values: - # (long_option, short_option, help_string [, repeatable]) - # if an option takes an argument, its long_option should have '=' - # appended; short_option should just be a single character, no ':' - # in any case. If a long_option doesn't have a corresponding - # short_option, short_option should be None. All option tuples - # must have long options. - self.option_table = option_table - - # 'option_index' maps long option names to entries in the option - # table (ie. those 3-tuples). - self.option_index = {} - if self.option_table: - self._build_index() - - # 'alias' records (duh) alias options; {'foo': 'bar'} means - # --foo is an alias for --bar - self.alias = {} - - # 'negative_alias' keeps track of options that are the boolean - # opposite of some other option - self.negative_alias = {} - - # These keep track of the information in the option table. We - # don't actually populate these structures until we're ready to - # parse the command-line, since the 'option_table' passed in here - # isn't necessarily the final word. - self.short_opts = [] - self.long_opts = [] - self.short2long = {} - self.attr_name = {} - self.takes_arg = {} - - # And 'option_order' is filled up in 'getopt()'; it records the - # original order of options (and their values) on the command-line, - # but expands short options, converts aliases, etc. - self.option_order = [] - - def _build_index(self): - self.option_index.clear() - for option in self.option_table: - self.option_index[option[0]] = option - - def set_option_table(self, option_table): - self.option_table = option_table - self._build_index() - - def add_option(self, long_option, short_option=None, help_string=None): - if long_option in self.option_index: - raise DistutilsGetoptError( - f"option conflict: already an option '{long_option}'" - ) - else: - option = (long_option, short_option, help_string) - self.option_table.append(option) - self.option_index[long_option] = option - - def has_option(self, long_option): - """Return true if the option table for this parser has an - option with long name 'long_option'.""" - return long_option in self.option_index - - def get_attr_name(self, long_option): - """Translate long option name 'long_option' to the form it - has as an attribute of some object: ie., translate hyphens - to underscores.""" - return long_option.translate(longopt_xlate) - - def _check_alias_dict(self, aliases, what): - assert isinstance(aliases, dict) - for alias, opt in aliases.items(): - if alias not in self.option_index: - raise DistutilsGetoptError( - f"invalid {what} '{alias}': option '{alias}' not defined" - ) - if opt not in self.option_index: - raise DistutilsGetoptError( - f"invalid {what} '{alias}': aliased option '{opt}' not defined" - ) - - def set_aliases(self, alias): - """Set the aliases for this option parser.""" - self._check_alias_dict(alias, "alias") - self.alias = alias - - def set_negative_aliases(self, negative_alias): - """Set the negative aliases for this option parser. - 'negative_alias' should be a dictionary mapping option names to - option names, both the key and value must already be defined - in the option table.""" - self._check_alias_dict(negative_alias, "negative alias") - self.negative_alias = negative_alias - - def _grok_option_table(self): # noqa: C901 - """Populate the various data structures that keep tabs on the - option table. Called by 'getopt()' before it can do anything - worthwhile. - """ - self.long_opts = [] - self.short_opts = [] - self.short2long.clear() - self.repeat = {} - - for option in self.option_table: - if len(option) == 3: - long, short, help = option - repeat = 0 - elif len(option) == 4: - long, short, help, repeat = option - else: - # the option table is part of the code, so simply - # assert that it is correct - raise ValueError(f"invalid option tuple: {option!r}") - - # Type- and value-check the option names - if not isinstance(long, str) or len(long) < 2: - raise DistutilsGetoptError( - f"invalid long option '{long}': must be a string of length >= 2" - ) - - if not ((short is None) or (isinstance(short, str) and len(short) == 1)): - raise DistutilsGetoptError( - f"invalid short option '{short}': must a single character or None" - ) - - self.repeat[long] = repeat - self.long_opts.append(long) - - if long[-1] == '=': # option takes an argument? - if short: - short = short + ':' - long = long[0:-1] - self.takes_arg[long] = True - else: - # Is option is a "negative alias" for some other option (eg. - # "quiet" == "!verbose")? - alias_to = self.negative_alias.get(long) - if alias_to is not None: - if self.takes_arg[alias_to]: - raise DistutilsGetoptError( - f"invalid negative alias '{long}': " - f"aliased option '{alias_to}' takes a value" - ) - - self.long_opts[-1] = long # XXX redundant?! - self.takes_arg[long] = False - - # If this is an alias option, make sure its "takes arg" flag is - # the same as the option it's aliased to. - alias_to = self.alias.get(long) - if alias_to is not None: - if self.takes_arg[long] != self.takes_arg[alias_to]: - raise DistutilsGetoptError( - f"invalid alias '{long}': inconsistent with " - f"aliased option '{alias_to}' (one of them takes a value, " - "the other doesn't" - ) - - # Now enforce some bondage on the long option name, so we can - # later translate it to an attribute name on some object. Have - # to do this a bit late to make sure we've removed any trailing - # '='. - if not longopt_re.match(long): - raise DistutilsGetoptError( - f"invalid long option name '{long}' " - "(must be letters, numbers, hyphens only" - ) - - self.attr_name[long] = self.get_attr_name(long) - if short: - self.short_opts.append(short) - self.short2long[short[0]] = long - - def getopt(self, args: Sequence[str] | None = None, object=None): # noqa: C901 - """Parse command-line options in args. Store as attributes on object. - - If 'args' is None or not supplied, uses 'sys.argv[1:]'. If - 'object' is None or not supplied, creates a new OptionDummy - object, stores option values there, and returns a tuple (args, - object). If 'object' is supplied, it is modified in place and - 'getopt()' just returns 'args'; in both cases, the returned - 'args' is a modified copy of the passed-in 'args' list, which - is left untouched. - """ - if args is None: - args = sys.argv[1:] - if object is None: - object = OptionDummy() - created_object = True - else: - created_object = False - - self._grok_option_table() - - short_opts = ' '.join(self.short_opts) - try: - opts, args = getopt.getopt(args, short_opts, self.long_opts) - except getopt.error as msg: - raise DistutilsArgError(msg) - - for opt, val in opts: - if len(opt) == 2 and opt[0] == '-': # it's a short option - opt = self.short2long[opt[1]] - else: - assert len(opt) > 2 and opt[:2] == '--' - opt = opt[2:] - - alias = self.alias.get(opt) - if alias: - opt = alias - - if not self.takes_arg[opt]: # boolean option? - assert val == '', "boolean option can't have value" - alias = self.negative_alias.get(opt) - if alias: - opt = alias - val = 0 - else: - val = 1 - - attr = self.attr_name[opt] - # The only repeating option at the moment is 'verbose'. - # It has a negative option -q quiet, which should set verbose = False. - if val and self.repeat.get(attr) is not None: - val = getattr(object, attr, 0) + 1 - setattr(object, attr, val) - self.option_order.append((opt, val)) - - # for opts - if created_object: - return args, object - else: - return args - - def get_option_order(self): - """Returns the list of (option, value) tuples processed by the - previous run of 'getopt()'. Raises RuntimeError if - 'getopt()' hasn't been called yet. - """ - if self.option_order is None: - raise RuntimeError("'getopt()' hasn't been called yet") - else: - return self.option_order - - def generate_help(self, header=None): # noqa: C901 - """Generate help text (a list of strings, one per suggested line of - output) from the option table for this FancyGetopt object. - """ - # Blithely assume the option table is good: probably wouldn't call - # 'generate_help()' unless you've already called 'getopt()'. - - # First pass: determine maximum length of long option names - max_opt = 0 - for option in self.option_table: - long = option[0] - short = option[1] - ell = len(long) - if long[-1] == '=': - ell = ell - 1 - if short is not None: - ell = ell + 5 # " (-x)" where short == 'x' - if ell > max_opt: - max_opt = ell - - opt_width = max_opt + 2 + 2 + 2 # room for indent + dashes + gutter - - # Typical help block looks like this: - # --foo controls foonabulation - # Help block for longest option looks like this: - # --flimflam set the flim-flam level - # and with wrapped text: - # --flimflam set the flim-flam level (must be between - # 0 and 100, except on Tuesdays) - # Options with short names will have the short name shown (but - # it doesn't contribute to max_opt): - # --foo (-f) controls foonabulation - # If adding the short option would make the left column too wide, - # we push the explanation off to the next line - # --flimflam (-l) - # set the flim-flam level - # Important parameters: - # - 2 spaces before option block start lines - # - 2 dashes for each long option name - # - min. 2 spaces between option and explanation (gutter) - # - 5 characters (incl. space) for short option name - - # Now generate lines of help text. (If 80 columns were good enough - # for Jesus, then 78 columns are good enough for me!) - line_width = 78 - text_width = line_width - opt_width - big_indent = ' ' * opt_width - if header: - lines = [header] - else: - lines = ['Option summary:'] - - for option in self.option_table: - long, short, help = option[:3] - text = wrap_text(help, text_width) - if long[-1] == '=': - long = long[0:-1] - - # Case 1: no short option at all (makes life easy) - if short is None: - if text: - lines.append(f" --{long:<{max_opt}} {text[0]}") - else: - lines.append(f" --{long:<{max_opt}}") - - # Case 2: we have a short option, so we have to include it - # just after the long option - else: - opt_names = f"{long} (-{short})" - if text: - lines.append(f" --{opt_names:<{max_opt}} {text[0]}") - else: - lines.append(f" --{opt_names:<{max_opt}}") - - for ell in text[1:]: - lines.append(big_indent + ell) - return lines - - def print_help(self, header=None, file=None): - if file is None: - file = sys.stdout - for line in self.generate_help(header): - file.write(line + "\n") - - -def fancy_getopt(options, negative_opt, object, args: Sequence[str] | None): - parser = FancyGetopt(options) - parser.set_negative_aliases(negative_opt) - return parser.getopt(args, object) - - -WS_TRANS = {ord(_wschar): ' ' for _wschar in string.whitespace} - - -def wrap_text(text, width): - """wrap_text(text : string, width : int) -> [string] - - Split 'text' into multiple lines of no more than 'width' characters - each, and return the list of strings that results. - """ - if text is None: - return [] - if len(text) <= width: - return [text] - - text = text.expandtabs() - text = text.translate(WS_TRANS) - chunks = re.split(r'( +|-+)', text) - chunks = [ch for ch in chunks if ch] # ' - ' results in empty strings - lines = [] - - while chunks: - cur_line = [] # list of chunks (to-be-joined) - cur_len = 0 # length of current line - - while chunks: - ell = len(chunks[0]) - if cur_len + ell <= width: # can squeeze (at least) this chunk in - cur_line.append(chunks[0]) - del chunks[0] - cur_len = cur_len + ell - else: # this line is full - # drop last chunk if all space - if cur_line and cur_line[-1][0] == ' ': - del cur_line[-1] - break - - if chunks: # any chunks left to process? - # if the current line is still empty, then we had a single - # chunk that's too big too fit on a line -- so we break - # down and break it up at the line width - if cur_len == 0: - cur_line.append(chunks[0][0:width]) - chunks[0] = chunks[0][width:] - - # all-whitespace chunks at the end of a line can be discarded - # (and we know from the re.split above that if a chunk has - # *any* whitespace, it is *all* whitespace) - if chunks[0][0] == ' ': - del chunks[0] - - # and store this line in the list-of-all-lines -- as a single - # string, of course! - lines.append(''.join(cur_line)) - - return lines - - -def translate_longopt(opt): - """Convert a long option name to a valid Python identifier by - changing "-" to "_". - """ - return opt.translate(longopt_xlate) - - -class OptionDummy: - """Dummy class just used as a place to hold command-line option - values as instance attributes.""" - - def __init__(self, options: Sequence[Any] = []): - """Create a new OptionDummy instance. The attributes listed in - 'options' will be initialized to None.""" - for opt in options: - setattr(self, opt, None) - - -if __name__ == "__main__": - text = """\ -Tra-la-la, supercalifragilisticexpialidocious. -How *do* you spell that odd word, anyways? -(Someone ask Mary -- she'll know [or she'll -say, "How should I know?"].)""" - - for w in (10, 20, 30, 40): - print(f"width: {w}") - print("\n".join(wrap_text(text, w))) - print() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/file_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/file_util.py deleted file mode 100644 index 0acc8cb..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/file_util.py +++ /dev/null @@ -1,236 +0,0 @@ -"""distutils.file_util - -Utility functions for operating on single files. -""" - -import os - -from ._log import log -from .errors import DistutilsFileError - -# for generating verbose output in 'copy_file()' -_copy_action = {None: 'copying', 'hard': 'hard linking', 'sym': 'symbolically linking'} - - -def _copy_file_contents(src, dst, buffer_size=16 * 1024): # noqa: C901 - """Copy the file 'src' to 'dst'; both must be filenames. Any error - opening either file, reading from 'src', or writing to 'dst', raises - DistutilsFileError. Data is read/written in chunks of 'buffer_size' - bytes (default 16k). No attempt is made to handle anything apart from - regular files. - """ - # Stolen from shutil module in the standard library, but with - # custom error-handling added. - fsrc = None - fdst = None - try: - try: - fsrc = open(src, 'rb') - except OSError as e: - raise DistutilsFileError(f"could not open '{src}': {e.strerror}") - - if os.path.exists(dst): - try: - os.unlink(dst) - except OSError as e: - raise DistutilsFileError(f"could not delete '{dst}': {e.strerror}") - - try: - fdst = open(dst, 'wb') - except OSError as e: - raise DistutilsFileError(f"could not create '{dst}': {e.strerror}") - - while True: - try: - buf = fsrc.read(buffer_size) - except OSError as e: - raise DistutilsFileError(f"could not read from '{src}': {e.strerror}") - - if not buf: - break - - try: - fdst.write(buf) - except OSError as e: - raise DistutilsFileError(f"could not write to '{dst}': {e.strerror}") - finally: - if fdst: - fdst.close() - if fsrc: - fsrc.close() - - -def copy_file( # noqa: C901 - src, - dst, - preserve_mode=True, - preserve_times=True, - update=False, - link=None, - verbose=True, - dry_run=False, -): - """Copy a file 'src' to 'dst'. If 'dst' is a directory, then 'src' is - copied there with the same name; otherwise, it must be a filename. (If - the file exists, it will be ruthlessly clobbered.) If 'preserve_mode' - is true (the default), the file's mode (type and permission bits, or - whatever is analogous on the current platform) is copied. If - 'preserve_times' is true (the default), the last-modified and - last-access times are copied as well. If 'update' is true, 'src' will - only be copied if 'dst' does not exist, or if 'dst' does exist but is - older than 'src'. - - 'link' allows you to make hard links (os.link) or symbolic links - (os.symlink) instead of copying: set it to "hard" or "sym"; if it is - None (the default), files are copied. Don't set 'link' on systems that - don't support it: 'copy_file()' doesn't check if hard or symbolic - linking is available. If hardlink fails, falls back to - _copy_file_contents(). - - Under Mac OS, uses the native file copy function in macostools; on - other systems, uses '_copy_file_contents()' to copy file contents. - - Return a tuple (dest_name, copied): 'dest_name' is the actual name of - the output file, and 'copied' is true if the file was copied (or would - have been copied, if 'dry_run' true). - """ - # XXX if the destination file already exists, we clobber it if - # copying, but blow up if linking. Hmmm. And I don't know what - # macostools.copyfile() does. Should definitely be consistent, and - # should probably blow up if destination exists and we would be - # changing it (ie. it's not already a hard/soft link to src OR - # (not update) and (src newer than dst). - - from distutils._modified import newer - from stat import S_IMODE, ST_ATIME, ST_MODE, ST_MTIME - - if not os.path.isfile(src): - raise DistutilsFileError( - f"can't copy '{src}': doesn't exist or not a regular file" - ) - - if os.path.isdir(dst): - dir = dst - dst = os.path.join(dst, os.path.basename(src)) - else: - dir = os.path.dirname(dst) - - if update and not newer(src, dst): - if verbose >= 1: - log.debug("not copying %s (output up-to-date)", src) - return (dst, False) - - try: - action = _copy_action[link] - except KeyError: - raise ValueError(f"invalid value '{link}' for 'link' argument") - - if verbose >= 1: - if os.path.basename(dst) == os.path.basename(src): - log.info("%s %s -> %s", action, src, dir) - else: - log.info("%s %s -> %s", action, src, dst) - - if dry_run: - return (dst, True) - - # If linking (hard or symbolic), use the appropriate system call - # (Unix only, of course, but that's the caller's responsibility) - elif link == 'hard': - if not (os.path.exists(dst) and os.path.samefile(src, dst)): - try: - os.link(src, dst) - except OSError: - # If hard linking fails, fall back on copying file - # (some special filesystems don't support hard linking - # even under Unix, see issue #8876). - pass - else: - return (dst, True) - elif link == 'sym': - if not (os.path.exists(dst) and os.path.samefile(src, dst)): - os.symlink(src, dst) - return (dst, True) - - # Otherwise (non-Mac, not linking), copy the file contents and - # (optionally) copy the times and mode. - _copy_file_contents(src, dst) - if preserve_mode or preserve_times: - st = os.stat(src) - - # According to David Ascher , utime() should be done - # before chmod() (at least under NT). - if preserve_times: - os.utime(dst, (st[ST_ATIME], st[ST_MTIME])) - if preserve_mode: - os.chmod(dst, S_IMODE(st[ST_MODE])) - - return (dst, True) - - -# XXX I suspect this is Unix-specific -- need porting help! -def move_file(src, dst, verbose=True, dry_run=False): # noqa: C901 - """Move a file 'src' to 'dst'. If 'dst' is a directory, the file will - be moved into it with the same name; otherwise, 'src' is just renamed - to 'dst'. Return the new full name of the file. - - Handles cross-device moves on Unix using 'copy_file()'. What about - other systems??? - """ - import errno - from os.path import basename, dirname, exists, isdir, isfile - - if verbose >= 1: - log.info("moving %s -> %s", src, dst) - - if dry_run: - return dst - - if not isfile(src): - raise DistutilsFileError(f"can't move '{src}': not a regular file") - - if isdir(dst): - dst = os.path.join(dst, basename(src)) - elif exists(dst): - raise DistutilsFileError( - f"can't move '{src}': destination '{dst}' already exists" - ) - - if not isdir(dirname(dst)): - raise DistutilsFileError( - f"can't move '{src}': destination '{dst}' not a valid path" - ) - - copy_it = False - try: - os.rename(src, dst) - except OSError as e: - (num, msg) = e.args - if num == errno.EXDEV: - copy_it = True - else: - raise DistutilsFileError(f"couldn't move '{src}' to '{dst}': {msg}") - - if copy_it: - copy_file(src, dst, verbose=verbose) - try: - os.unlink(src) - except OSError as e: - (num, msg) = e.args - try: - os.unlink(dst) - except OSError: - pass - raise DistutilsFileError( - f"couldn't move '{src}' to '{dst}' by copy/delete: " - f"delete '{src}' failed: {msg}" - ) - return dst - - -def write_file(filename, contents): - """Create a file with the specified name and write 'contents' (a - sequence of strings without line terminators) to it. - """ - with open(filename, 'w', encoding='utf-8') as f: - f.writelines(line + '\n' for line in contents) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/filelist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/filelist.py deleted file mode 100644 index 70dc0fd..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/filelist.py +++ /dev/null @@ -1,431 +0,0 @@ -"""distutils.filelist - -Provides the FileList class, used for poking about the filesystem -and building lists of files. -""" - -from __future__ import annotations - -import fnmatch -import functools -import os -import re -from collections.abc import Iterable -from typing import Literal, overload - -from ._log import log -from .errors import DistutilsInternalError, DistutilsTemplateError -from .util import convert_path - - -class FileList: - """A list of files built by on exploring the filesystem and filtered by - applying various patterns to what we find there. - - Instance attributes: - dir - directory from which files will be taken -- only used if - 'allfiles' not supplied to constructor - files - list of filenames currently being built/filtered/manipulated - allfiles - complete list of files under consideration (ie. without any - filtering applied) - """ - - def __init__(self, warn: object = None, debug_print: object = None) -> None: - # ignore argument to FileList, but keep them for backwards - # compatibility - self.allfiles: Iterable[str] | None = None - self.files: list[str] = [] - - def set_allfiles(self, allfiles: Iterable[str]) -> None: - self.allfiles = allfiles - - def findall(self, dir: str | os.PathLike[str] = os.curdir) -> None: - self.allfiles = findall(dir) - - def debug_print(self, msg: object) -> None: - """Print 'msg' to stdout if the global DEBUG (taken from the - DISTUTILS_DEBUG environment variable) flag is true. - """ - from distutils.debug import DEBUG - - if DEBUG: - print(msg) - - # Collection methods - - def append(self, item: str) -> None: - self.files.append(item) - - def extend(self, items: Iterable[str]) -> None: - self.files.extend(items) - - def sort(self) -> None: - # Not a strict lexical sort! - sortable_files = sorted(map(os.path.split, self.files)) - self.files = [] - for sort_tuple in sortable_files: - self.files.append(os.path.join(*sort_tuple)) - - # Other miscellaneous utility methods - - def remove_duplicates(self) -> None: - # Assumes list has been sorted! - for i in range(len(self.files) - 1, 0, -1): - if self.files[i] == self.files[i - 1]: - del self.files[i] - - # "File template" methods - - def _parse_template_line(self, line): - words = line.split() - action = words[0] - - patterns = dir = dir_pattern = None - - if action in ('include', 'exclude', 'global-include', 'global-exclude'): - if len(words) < 2: - raise DistutilsTemplateError( - f"'{action}' expects ..." - ) - patterns = [convert_path(w) for w in words[1:]] - elif action in ('recursive-include', 'recursive-exclude'): - if len(words) < 3: - raise DistutilsTemplateError( - f"'{action}' expects ..." - ) - dir = convert_path(words[1]) - patterns = [convert_path(w) for w in words[2:]] - elif action in ('graft', 'prune'): - if len(words) != 2: - raise DistutilsTemplateError( - f"'{action}' expects a single " - ) - dir_pattern = convert_path(words[1]) - else: - raise DistutilsTemplateError(f"unknown action '{action}'") - - return (action, patterns, dir, dir_pattern) - - def process_template_line(self, line: str) -> None: # noqa: C901 - # Parse the line: split it up, make sure the right number of words - # is there, and return the relevant words. 'action' is always - # defined: it's the first word of the line. Which of the other - # three are defined depends on the action; it'll be either - # patterns, (dir and patterns), or (dir_pattern). - (action, patterns, dir, dir_pattern) = self._parse_template_line(line) - - # OK, now we know that the action is valid and we have the - # right number of words on the line for that action -- so we - # can proceed with minimal error-checking. - if action == 'include': - self.debug_print("include " + ' '.join(patterns)) - for pattern in patterns: - if not self.include_pattern(pattern, anchor=True): - log.warning("warning: no files found matching '%s'", pattern) - - elif action == 'exclude': - self.debug_print("exclude " + ' '.join(patterns)) - for pattern in patterns: - if not self.exclude_pattern(pattern, anchor=True): - log.warning( - "warning: no previously-included files found matching '%s'", - pattern, - ) - - elif action == 'global-include': - self.debug_print("global-include " + ' '.join(patterns)) - for pattern in patterns: - if not self.include_pattern(pattern, anchor=False): - log.warning( - ( - "warning: no files found matching '%s' " - "anywhere in distribution" - ), - pattern, - ) - - elif action == 'global-exclude': - self.debug_print("global-exclude " + ' '.join(patterns)) - for pattern in patterns: - if not self.exclude_pattern(pattern, anchor=False): - log.warning( - ( - "warning: no previously-included files matching " - "'%s' found anywhere in distribution" - ), - pattern, - ) - - elif action == 'recursive-include': - self.debug_print("recursive-include {} {}".format(dir, ' '.join(patterns))) - for pattern in patterns: - if not self.include_pattern(pattern, prefix=dir): - msg = "warning: no files found matching '%s' under directory '%s'" - log.warning(msg, pattern, dir) - - elif action == 'recursive-exclude': - self.debug_print("recursive-exclude {} {}".format(dir, ' '.join(patterns))) - for pattern in patterns: - if not self.exclude_pattern(pattern, prefix=dir): - log.warning( - ( - "warning: no previously-included files matching " - "'%s' found under directory '%s'" - ), - pattern, - dir, - ) - - elif action == 'graft': - self.debug_print("graft " + dir_pattern) - if not self.include_pattern(None, prefix=dir_pattern): - log.warning("warning: no directories found matching '%s'", dir_pattern) - - elif action == 'prune': - self.debug_print("prune " + dir_pattern) - if not self.exclude_pattern(None, prefix=dir_pattern): - log.warning( - ("no previously-included directories found matching '%s'"), - dir_pattern, - ) - else: - raise DistutilsInternalError( - f"this cannot happen: invalid action '{action}'" - ) - - # Filtering/selection methods - @overload - def include_pattern( - self, - pattern: str, - anchor: bool = True, - prefix: str | None = None, - is_regex: Literal[False] = False, - ) -> bool: ... - @overload - def include_pattern( - self, - pattern: str | re.Pattern[str], - anchor: bool = True, - prefix: str | None = None, - *, - is_regex: Literal[True], - ) -> bool: ... - @overload - def include_pattern( - self, - pattern: str | re.Pattern[str], - anchor: bool, - prefix: str | None, - is_regex: Literal[True], - ) -> bool: ... - def include_pattern( - self, - pattern: str | re.Pattern, - anchor: bool = True, - prefix: str | None = None, - is_regex: bool = False, - ) -> bool: - """Select strings (presumably filenames) from 'self.files' that - match 'pattern', a Unix-style wildcard (glob) pattern. Patterns - are not quite the same as implemented by the 'fnmatch' module: '*' - and '?' match non-special characters, where "special" is platform- - dependent: slash on Unix; colon, slash, and backslash on - DOS/Windows; and colon on Mac OS. - - If 'anchor' is true (the default), then the pattern match is more - stringent: "*.py" will match "foo.py" but not "foo/bar.py". If - 'anchor' is false, both of these will match. - - If 'prefix' is supplied, then only filenames starting with 'prefix' - (itself a pattern) and ending with 'pattern', with anything in between - them, will match. 'anchor' is ignored in this case. - - If 'is_regex' is true, 'anchor' and 'prefix' are ignored, and - 'pattern' is assumed to be either a string containing a regex or a - regex object -- no translation is done, the regex is just compiled - and used as-is. - - Selected strings will be added to self.files. - - Return True if files are found, False otherwise. - """ - # XXX docstring lying about what the special chars are? - files_found = False - pattern_re = translate_pattern(pattern, anchor, prefix, is_regex) - self.debug_print(f"include_pattern: applying regex r'{pattern_re.pattern}'") - - # delayed loading of allfiles list - if self.allfiles is None: - self.findall() - - for name in self.allfiles: - if pattern_re.search(name): - self.debug_print(" adding " + name) - self.files.append(name) - files_found = True - return files_found - - @overload - def exclude_pattern( - self, - pattern: str, - anchor: bool = True, - prefix: str | None = None, - is_regex: Literal[False] = False, - ) -> bool: ... - @overload - def exclude_pattern( - self, - pattern: str | re.Pattern[str], - anchor: bool = True, - prefix: str | None = None, - *, - is_regex: Literal[True], - ) -> bool: ... - @overload - def exclude_pattern( - self, - pattern: str | re.Pattern[str], - anchor: bool, - prefix: str | None, - is_regex: Literal[True], - ) -> bool: ... - def exclude_pattern( - self, - pattern: str | re.Pattern, - anchor: bool = True, - prefix: str | None = None, - is_regex: bool = False, - ) -> bool: - """Remove strings (presumably filenames) from 'files' that match - 'pattern'. Other parameters are the same as for - 'include_pattern()', above. - The list 'self.files' is modified in place. - Return True if files are found, False otherwise. - """ - files_found = False - pattern_re = translate_pattern(pattern, anchor, prefix, is_regex) - self.debug_print(f"exclude_pattern: applying regex r'{pattern_re.pattern}'") - for i in range(len(self.files) - 1, -1, -1): - if pattern_re.search(self.files[i]): - self.debug_print(" removing " + self.files[i]) - del self.files[i] - files_found = True - return files_found - - -# Utility functions - - -def _find_all_simple(path): - """ - Find all files under 'path' - """ - all_unique = _UniqueDirs.filter(os.walk(path, followlinks=True)) - results = ( - os.path.join(base, file) for base, dirs, files in all_unique for file in files - ) - return filter(os.path.isfile, results) - - -class _UniqueDirs(set): - """ - Exclude previously-seen dirs from walk results, - avoiding infinite recursion. - Ref https://bugs.python.org/issue44497. - """ - - def __call__(self, walk_item): - """ - Given an item from an os.walk result, determine - if the item represents a unique dir for this instance - and if not, prevent further traversal. - """ - base, dirs, files = walk_item - stat = os.stat(base) - candidate = stat.st_dev, stat.st_ino - found = candidate in self - if found: - del dirs[:] - self.add(candidate) - return not found - - @classmethod - def filter(cls, items): - return filter(cls(), items) - - -def findall(dir: str | os.PathLike[str] = os.curdir): - """ - Find all files under 'dir' and return the list of full filenames. - Unless dir is '.', return full filenames with dir prepended. - """ - files = _find_all_simple(dir) - if dir == os.curdir: - make_rel = functools.partial(os.path.relpath, start=dir) - files = map(make_rel, files) - return list(files) - - -def glob_to_re(pattern): - """Translate a shell-like glob pattern to a regular expression; return - a string containing the regex. Differs from 'fnmatch.translate()' in - that '*' does not match "special characters" (which are - platform-specific). - """ - pattern_re = fnmatch.translate(pattern) - - # '?' and '*' in the glob pattern become '.' and '.*' in the RE, which - # IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix, - # and by extension they shouldn't match such "special characters" under - # any OS. So change all non-escaped dots in the RE to match any - # character except the special characters (currently: just os.sep). - sep = os.sep - if os.sep == '\\': - # we're using a regex to manipulate a regex, so we need - # to escape the backslash twice - sep = r'\\\\' - escaped = rf'\1[^{sep}]' - pattern_re = re.sub(r'((?= 2: - set_threshold(logging.DEBUG) - - -class Log(logging.Logger): - """distutils.log.Log is deprecated, please use an alternative from `logging`.""" - - def __init__(self, threshold=WARN): - warnings.warn(Log.__doc__) # avoid DeprecationWarning to ensure warn is shown - super().__init__(__name__, level=threshold) - - @property - def threshold(self): - return self.level - - @threshold.setter - def threshold(self, level): - self.setLevel(level) - - warn = logging.Logger.warning diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/spawn.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/spawn.py deleted file mode 100644 index 973668f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/spawn.py +++ /dev/null @@ -1,134 +0,0 @@ -"""distutils.spawn - -Provides the 'spawn()' function, a front-end to various platform- -specific functions for launching another program in a sub-process. -""" - -from __future__ import annotations - -import os -import platform -import shutil -import subprocess -import sys -import warnings -from collections.abc import Mapping, MutableSequence -from typing import TYPE_CHECKING, TypeVar, overload - -from ._log import log -from .debug import DEBUG -from .errors import DistutilsExecError - -if TYPE_CHECKING: - from subprocess import _ENV - - -_MappingT = TypeVar("_MappingT", bound=Mapping) - - -def _debug(cmd): - """ - Render a subprocess command differently depending on DEBUG. - """ - return cmd if DEBUG else cmd[0] - - -def _inject_macos_ver(env: _MappingT | None) -> _MappingT | dict[str, str | int] | None: - if platform.system() != 'Darwin': - return env - - from .util import MACOSX_VERSION_VAR, get_macosx_target_ver - - target_ver = get_macosx_target_ver() - update = {MACOSX_VERSION_VAR: target_ver} if target_ver else {} - return {**_resolve(env), **update} - - -@overload -def _resolve(env: None) -> os._Environ[str]: ... -@overload -def _resolve(env: _MappingT) -> _MappingT: ... -def _resolve(env: _MappingT | None) -> _MappingT | os._Environ[str]: - return os.environ if env is None else env - - -def spawn( - cmd: MutableSequence[bytes | str | os.PathLike[str]], - search_path: bool = True, - verbose: bool = False, - dry_run: bool = False, - env: _ENV | None = None, -) -> None: - """Run another program, specified as a command list 'cmd', in a new process. - - 'cmd' is just the argument list for the new process, ie. - cmd[0] is the program to run and cmd[1:] are the rest of its arguments. - There is no way to run a program with a name different from that of its - executable. - - If 'search_path' is true (the default), the system's executable - search path will be used to find the program; otherwise, cmd[0] - must be the exact path to the executable. If 'dry_run' is true, - the command will not actually be run. - - Raise DistutilsExecError if running the program fails in any way; just - return on success. - """ - log.info(subprocess.list2cmdline(cmd)) - if dry_run: - return - - if search_path: - executable = shutil.which(cmd[0]) - if executable is not None: - cmd[0] = executable - - try: - subprocess.check_call(cmd, env=_inject_macos_ver(env)) - except OSError as exc: - raise DistutilsExecError( - f"command {_debug(cmd)!r} failed: {exc.args[-1]}" - ) from exc - except subprocess.CalledProcessError as err: - raise DistutilsExecError( - f"command {_debug(cmd)!r} failed with exit code {err.returncode}" - ) from err - - -def find_executable(executable: str, path: str | None = None) -> str | None: - """Tries to find 'executable' in the directories listed in 'path'. - - A string listing directories separated by 'os.pathsep'; defaults to - os.environ['PATH']. Returns the complete filename or None if not found. - """ - warnings.warn( - 'Use shutil.which instead of find_executable', DeprecationWarning, stacklevel=2 - ) - _, ext = os.path.splitext(executable) - if (sys.platform == 'win32') and (ext != '.exe'): - executable = executable + '.exe' - - if os.path.isfile(executable): - return executable - - if path is None: - path = os.environ.get('PATH', None) - # bpo-35755: Don't fall through if PATH is the empty string - if path is None: - try: - path = os.confstr("CS_PATH") - except (AttributeError, ValueError): - # os.confstr() or CS_PATH is not available - path = os.defpath - - # PATH='' doesn't match, whereas PATH=':' looks in the current directory - if not path: - return None - - paths = path.split(os.pathsep) - for p in paths: - f = os.path.join(p, executable) - if os.path.isfile(f): - # the file exists, we have a shot at spawn working - return f - return None diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/sysconfig.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/sysconfig.py deleted file mode 100644 index 7ddc869..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/sysconfig.py +++ /dev/null @@ -1,598 +0,0 @@ -"""Provide access to Python's configuration information. The specific -configuration variables available depend heavily on the platform and -configuration. The values may be retrieved using -get_config_var(name), and the list of variables is available via -get_config_vars().keys(). Additional convenience functions are also -available. - -Written by: Fred L. Drake, Jr. -Email: -""" - -from __future__ import annotations - -import functools -import os -import pathlib -import re -import sys -import sysconfig -from typing import TYPE_CHECKING, Literal, overload - -from jaraco.functools import pass_none - -from .ccompiler import CCompiler -from .compat import py39 -from .errors import DistutilsPlatformError -from .util import is_mingw - -if TYPE_CHECKING: - from typing_extensions import deprecated -else: - - def deprecated(message): - return lambda fn: fn - - -IS_PYPY = '__pypy__' in sys.builtin_module_names - -# These are needed in a couple of spots, so just compute them once. -PREFIX = os.path.normpath(sys.prefix) -EXEC_PREFIX = os.path.normpath(sys.exec_prefix) -BASE_PREFIX = os.path.normpath(sys.base_prefix) -BASE_EXEC_PREFIX = os.path.normpath(sys.base_exec_prefix) - -# Path to the base directory of the project. On Windows the binary may -# live in project/PCbuild/win32 or project/PCbuild/amd64. -# set for cross builds -if "_PYTHON_PROJECT_BASE" in os.environ: - project_base = os.path.abspath(os.environ["_PYTHON_PROJECT_BASE"]) -else: - if sys.executable: - project_base = os.path.dirname(os.path.abspath(sys.executable)) - else: - # sys.executable can be empty if argv[0] has been changed and Python is - # unable to retrieve the real program name - project_base = os.getcwd() - - -def _is_python_source_dir(d): - """ - Return True if the target directory appears to point to an - un-installed Python. - """ - modules = pathlib.Path(d).joinpath('Modules') - return any(modules.joinpath(fn).is_file() for fn in ('Setup', 'Setup.local')) - - -_sys_home = getattr(sys, '_home', None) - - -def _is_parent(dir_a, dir_b): - """ - Return True if a is a parent of b. - """ - return os.path.normcase(dir_a).startswith(os.path.normcase(dir_b)) - - -if os.name == 'nt': - - @pass_none - def _fix_pcbuild(d): - # In a venv, sys._home will be inside BASE_PREFIX rather than PREFIX. - prefixes = PREFIX, BASE_PREFIX - matched = ( - prefix - for prefix in prefixes - if _is_parent(d, os.path.join(prefix, "PCbuild")) - ) - return next(matched, d) - - project_base = _fix_pcbuild(project_base) - _sys_home = _fix_pcbuild(_sys_home) - - -def _python_build(): - if _sys_home: - return _is_python_source_dir(_sys_home) - return _is_python_source_dir(project_base) - - -python_build = _python_build() - - -# Calculate the build qualifier flags if they are defined. Adding the flags -# to the include and lib directories only makes sense for an installation, not -# an in-source build. -build_flags = '' -try: - if not python_build: - build_flags = sys.abiflags -except AttributeError: - # It's not a configure-based build, so the sys module doesn't have - # this attribute, which is fine. - pass - - -def get_python_version(): - """Return a string containing the major and minor Python version, - leaving off the patchlevel. Sample return values could be '1.5' - or '2.2'. - """ - return f'{sys.version_info.major}.{sys.version_info.minor}' - - -def get_python_inc(plat_specific: bool = False, prefix: str | None = None) -> str: - """Return the directory containing installed Python header files. - - If 'plat_specific' is false (the default), this is the path to the - non-platform-specific header files, i.e. Python.h and so on; - otherwise, this is the path to platform-specific header files - (namely pyconfig.h). - - If 'prefix' is supplied, use it instead of sys.base_prefix or - sys.base_exec_prefix -- i.e., ignore 'plat_specific'. - """ - default_prefix = BASE_EXEC_PREFIX if plat_specific else BASE_PREFIX - resolved_prefix = prefix if prefix is not None else default_prefix - # MinGW imitates posix like layout, but os.name != posix - os_name = "posix" if is_mingw() else os.name - try: - getter = globals()[f'_get_python_inc_{os_name}'] - except KeyError: - raise DistutilsPlatformError( - "I don't know where Python installs its C header files " - f"on platform '{os.name}'" - ) - return getter(resolved_prefix, prefix, plat_specific) - - -@pass_none -def _extant(path): - """ - Replace path with None if it doesn't exist. - """ - return path if os.path.exists(path) else None - - -def _get_python_inc_posix(prefix, spec_prefix, plat_specific): - return ( - _get_python_inc_posix_python(plat_specific) - or _extant(_get_python_inc_from_config(plat_specific, spec_prefix)) - or _get_python_inc_posix_prefix(prefix) - ) - - -def _get_python_inc_posix_python(plat_specific): - """ - Assume the executable is in the build directory. The - pyconfig.h file should be in the same directory. Since - the build directory may not be the source directory, - use "srcdir" from the makefile to find the "Include" - directory. - """ - if not python_build: - return - if plat_specific: - return _sys_home or project_base - incdir = os.path.join(get_config_var('srcdir'), 'Include') - return os.path.normpath(incdir) - - -def _get_python_inc_from_config(plat_specific, spec_prefix): - """ - If no prefix was explicitly specified, provide the include - directory from the config vars. Useful when - cross-compiling, since the config vars may come from - the host - platform Python installation, while the current Python - executable is from the build platform installation. - - >>> monkeypatch = getfixture('monkeypatch') - >>> gpifc = _get_python_inc_from_config - >>> monkeypatch.setitem(gpifc.__globals__, 'get_config_var', str.lower) - >>> gpifc(False, '/usr/bin/') - >>> gpifc(False, '') - >>> gpifc(False, None) - 'includepy' - >>> gpifc(True, None) - 'confincludepy' - """ - if spec_prefix is None: - return get_config_var('CONF' * plat_specific + 'INCLUDEPY') - - -def _get_python_inc_posix_prefix(prefix): - implementation = 'pypy' if IS_PYPY else 'python' - python_dir = implementation + get_python_version() + build_flags - return os.path.join(prefix, "include", python_dir) - - -def _get_python_inc_nt(prefix, spec_prefix, plat_specific): - if python_build: - # Include both include dirs to ensure we can find pyconfig.h - return ( - os.path.join(prefix, "include") - + os.path.pathsep - + os.path.dirname(sysconfig.get_config_h_filename()) - ) - return os.path.join(prefix, "include") - - -# allow this behavior to be monkey-patched. Ref pypa/distutils#2. -def _posix_lib(standard_lib, libpython, early_prefix, prefix): - if standard_lib: - return libpython - else: - return os.path.join(libpython, "site-packages") - - -def get_python_lib( - plat_specific: bool = False, standard_lib: bool = False, prefix: str | None = None -) -> str: - """Return the directory containing the Python library (standard or - site additions). - - If 'plat_specific' is true, return the directory containing - platform-specific modules, i.e. any module from a non-pure-Python - module distribution; otherwise, return the platform-shared library - directory. If 'standard_lib' is true, return the directory - containing standard Python library modules; otherwise, return the - directory for site-specific modules. - - If 'prefix' is supplied, use it instead of sys.base_prefix or - sys.base_exec_prefix -- i.e., ignore 'plat_specific'. - """ - - early_prefix = prefix - - if prefix is None: - if standard_lib: - prefix = plat_specific and BASE_EXEC_PREFIX or BASE_PREFIX - else: - prefix = plat_specific and EXEC_PREFIX or PREFIX - - if os.name == "posix" or is_mingw(): - if plat_specific or standard_lib: - # Platform-specific modules (any module from a non-pure-Python - # module distribution) or standard Python library modules. - libdir = getattr(sys, "platlibdir", "lib") - else: - # Pure Python - libdir = "lib" - implementation = 'pypy' if IS_PYPY else 'python' - libpython = os.path.join(prefix, libdir, implementation + get_python_version()) - return _posix_lib(standard_lib, libpython, early_prefix, prefix) - elif os.name == "nt": - if standard_lib: - return os.path.join(prefix, "Lib") - else: - return os.path.join(prefix, "Lib", "site-packages") - else: - raise DistutilsPlatformError( - f"I don't know where Python installs its library on platform '{os.name}'" - ) - - -@functools.lru_cache -def _customize_macos(): - """ - Perform first-time customization of compiler-related - config vars on macOS. Use after a compiler is known - to be needed. This customization exists primarily to support Pythons - from binary installers. The kind and paths to build tools on - the user system may vary significantly from the system - that Python itself was built on. Also the user OS - version and build tools may not support the same set - of CPU architectures for universal builds. - """ - - sys.platform == "darwin" and __import__('_osx_support').customize_compiler( - get_config_vars() - ) - - -def customize_compiler(compiler: CCompiler) -> None: - """Do any platform-specific customization of a CCompiler instance. - - Mainly needed on Unix, so we can plug in the information that - varies across Unices and is stored in Python's Makefile. - """ - if compiler.compiler_type in ["unix", "cygwin"] or ( - compiler.compiler_type == "mingw32" and is_mingw() - ): - _customize_macos() - - ( - cc, - cxx, - cflags, - ccshared, - ldshared, - ldcxxshared, - shlib_suffix, - ar, - ar_flags, - ) = get_config_vars( - 'CC', - 'CXX', - 'CFLAGS', - 'CCSHARED', - 'LDSHARED', - 'LDCXXSHARED', - 'SHLIB_SUFFIX', - 'AR', - 'ARFLAGS', - ) - - cxxflags = cflags - - if 'CC' in os.environ: - newcc = os.environ['CC'] - if 'LDSHARED' not in os.environ and ldshared.startswith(cc): - # If CC is overridden, use that as the default - # command for LDSHARED as well - ldshared = newcc + ldshared[len(cc) :] - cc = newcc - cxx = os.environ.get('CXX', cxx) - ldshared = os.environ.get('LDSHARED', ldshared) - ldcxxshared = os.environ.get('LDCXXSHARED', ldcxxshared) - cpp = os.environ.get( - 'CPP', - cc + " -E", # not always - ) - - ldshared = _add_flags(ldshared, 'LD') - ldcxxshared = _add_flags(ldcxxshared, 'LD') - cflags = os.environ.get('CFLAGS', cflags) - ldshared = _add_flags(ldshared, 'C') - cxxflags = os.environ.get('CXXFLAGS', cxxflags) - ldcxxshared = _add_flags(ldcxxshared, 'CXX') - cpp = _add_flags(cpp, 'CPP') - cflags = _add_flags(cflags, 'CPP') - cxxflags = _add_flags(cxxflags, 'CPP') - ldshared = _add_flags(ldshared, 'CPP') - ldcxxshared = _add_flags(ldcxxshared, 'CPP') - - ar = os.environ.get('AR', ar) - - archiver = ar + ' ' + os.environ.get('ARFLAGS', ar_flags) - cc_cmd = cc + ' ' + cflags - cxx_cmd = cxx + ' ' + cxxflags - - compiler.set_executables( - preprocessor=cpp, - compiler=cc_cmd, - compiler_so=cc_cmd + ' ' + ccshared, - compiler_cxx=cxx_cmd, - compiler_so_cxx=cxx_cmd + ' ' + ccshared, - linker_so=ldshared, - linker_so_cxx=ldcxxshared, - linker_exe=cc, - linker_exe_cxx=cxx, - archiver=archiver, - ) - - if 'RANLIB' in os.environ and compiler.executables.get('ranlib', None): - compiler.set_executables(ranlib=os.environ['RANLIB']) - - compiler.shared_lib_extension = shlib_suffix - - -def get_config_h_filename() -> str: - """Return full pathname of installed pyconfig.h file.""" - return sysconfig.get_config_h_filename() - - -def get_makefile_filename() -> str: - """Return full pathname of installed Makefile from the Python build.""" - return sysconfig.get_makefile_filename() - - -def parse_config_h(fp, g=None): - """Parse a config.h-style file. - - A dictionary containing name/value pairs is returned. If an - optional dictionary is passed in as the second argument, it is - used instead of a new dictionary. - """ - return sysconfig.parse_config_h(fp, vars=g) - - -# Regexes needed for parsing Makefile (and similar syntaxes, -# like old-style Setup files). -_variable_rx = re.compile(r"([a-zA-Z][a-zA-Z0-9_]+)\s*=\s*(.*)") -_findvar1_rx = re.compile(r"\$\(([A-Za-z][A-Za-z0-9_]*)\)") -_findvar2_rx = re.compile(r"\${([A-Za-z][A-Za-z0-9_]*)}") - - -def parse_makefile(fn, g=None): # noqa: C901 - """Parse a Makefile-style file. - - A dictionary containing name/value pairs is returned. If an - optional dictionary is passed in as the second argument, it is - used instead of a new dictionary. - """ - from distutils.text_file import TextFile - - fp = TextFile( - fn, - strip_comments=True, - skip_blanks=True, - join_lines=True, - errors="surrogateescape", - ) - - if g is None: - g = {} - done = {} - notdone = {} - - while True: - line = fp.readline() - if line is None: # eof - break - m = _variable_rx.match(line) - if m: - n, v = m.group(1, 2) - v = v.strip() - # `$$' is a literal `$' in make - tmpv = v.replace('$$', '') - - if "$" in tmpv: - notdone[n] = v - else: - try: - v = int(v) - except ValueError: - # insert literal `$' - done[n] = v.replace('$$', '$') - else: - done[n] = v - - # Variables with a 'PY_' prefix in the makefile. These need to - # be made available without that prefix through sysconfig. - # Special care is needed to ensure that variable expansion works, even - # if the expansion uses the name without a prefix. - renamed_variables = ('CFLAGS', 'LDFLAGS', 'CPPFLAGS') - - # do variable interpolation here - while notdone: - for name in list(notdone): - value = notdone[name] - m = _findvar1_rx.search(value) or _findvar2_rx.search(value) - if m: - n = m.group(1) - found = True - if n in done: - item = str(done[n]) - elif n in notdone: - # get it on a subsequent round - found = False - elif n in os.environ: - # do it like make: fall back to environment - item = os.environ[n] - - elif n in renamed_variables: - if name.startswith('PY_') and name[3:] in renamed_variables: - item = "" - - elif 'PY_' + n in notdone: - found = False - - else: - item = str(done['PY_' + n]) - else: - done[n] = item = "" - if found: - after = value[m.end() :] - value = value[: m.start()] + item + after - if "$" in after: - notdone[name] = value - else: - try: - value = int(value) - except ValueError: - done[name] = value.strip() - else: - done[name] = value - del notdone[name] - - if name.startswith('PY_') and name[3:] in renamed_variables: - name = name[3:] - if name not in done: - done[name] = value - else: - # bogus variable reference; just drop it since we can't deal - del notdone[name] - - fp.close() - - # strip spurious spaces - for k, v in done.items(): - if isinstance(v, str): - done[k] = v.strip() - - # save the results in the global dictionary - g.update(done) - return g - - -def expand_makefile_vars(s, vars): - """Expand Makefile-style variables -- "${foo}" or "$(foo)" -- in - 'string' according to 'vars' (a dictionary mapping variable names to - values). Variables not present in 'vars' are silently expanded to the - empty string. The variable values in 'vars' should not contain further - variable expansions; if 'vars' is the output of 'parse_makefile()', - you're fine. Returns a variable-expanded version of 's'. - """ - - # This algorithm does multiple expansion, so if vars['foo'] contains - # "${bar}", it will expand ${foo} to ${bar}, and then expand - # ${bar}... and so forth. This is fine as long as 'vars' comes from - # 'parse_makefile()', which takes care of such expansions eagerly, - # according to make's variable expansion semantics. - - while True: - m = _findvar1_rx.search(s) or _findvar2_rx.search(s) - if m: - (beg, end) = m.span() - s = s[0:beg] + vars.get(m.group(1)) + s[end:] - else: - break - return s - - -_config_vars = None - - -@overload -def get_config_vars() -> dict[str, str | int]: ... -@overload -def get_config_vars(arg: str, /, *args: str) -> list[str | int]: ... -def get_config_vars(*args: str) -> list[str | int] | dict[str, str | int]: - """With no arguments, return a dictionary of all configuration - variables relevant for the current platform. Generally this includes - everything needed to build extensions and install both pure modules and - extensions. On Unix, this means every variable defined in Python's - installed Makefile; on Windows it's a much smaller set. - - With arguments, return a list of values that result from looking up - each argument in the configuration variable dictionary. - """ - global _config_vars - if _config_vars is None: - _config_vars = sysconfig.get_config_vars().copy() - py39.add_ext_suffix(_config_vars) - - return [_config_vars.get(name) for name in args] if args else _config_vars - - -@overload -@deprecated( - "SO is deprecated, use EXT_SUFFIX. Support will be removed when this module is synchronized with stdlib Python 3.11" -) -def get_config_var(name: Literal["SO"]) -> int | str | None: ... -@overload -def get_config_var(name: str) -> int | str | None: ... -def get_config_var(name: str) -> int | str | None: - """Return the value of a single variable using the dictionary - returned by 'get_config_vars()'. Equivalent to - get_config_vars().get(name) - """ - if name == 'SO': - import warnings - - warnings.warn('SO is deprecated, use EXT_SUFFIX', DeprecationWarning, 2) - return get_config_vars().get(name) - - -@pass_none -def _add_flags(value: str, type: str) -> str: - """ - Add any flags from the environment for the given type. - - type is the prefix to FLAGS in the environment key (e.g. "C" for "CFLAGS"). - """ - flags = os.environ.get(f'{type}FLAGS') - return f'{value} {flags}' if flags else value diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__init__.py deleted file mode 100644 index 5a8ab06..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__init__.py +++ /dev/null @@ -1,42 +0,0 @@ -""" -Test suite for distutils. - -Tests for the command classes in the distutils.command package are -included in distutils.tests as well, instead of using a separate -distutils.command.tests package, since command identification is done -by import rather than matching pre-defined names. -""" - -import shutil -from collections.abc import Sequence - - -def missing_compiler_executable(cmd_names: Sequence[str] = []): # pragma: no cover - """Check if the compiler components used to build the interpreter exist. - - Check for the existence of the compiler executables whose names are listed - in 'cmd_names' or all the compiler executables when 'cmd_names' is empty - and return the first missing executable or None when none is found - missing. - - """ - from distutils import ccompiler, errors, sysconfig - - compiler = ccompiler.new_compiler() - sysconfig.customize_compiler(compiler) - if compiler.compiler_type == "msvc": - # MSVC has no executables, so check whether initialization succeeds - try: - compiler.initialize() - except errors.DistutilsPlatformError: - return "msvc" - for name in compiler.executables: - if cmd_names and name not in cmd_names: - continue - cmd = getattr(compiler, name) - if cmd_names: - assert cmd is not None, f"the '{name}' executable is not configured" - elif not cmd: - continue - if shutil.which(cmd[0]) is None: - return cmd[0] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 0a2e27d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/support.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/support.cpython-312.pyc deleted file mode 100644 index 44b7cfd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/support.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_archive_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_archive_util.cpython-312.pyc deleted file mode 100644 index 916efc1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_archive_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist.cpython-312.pyc deleted file mode 100644 index e7586e1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist_dumb.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist_dumb.cpython-312.pyc deleted file mode 100644 index 3694e19..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist_dumb.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist_rpm.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist_rpm.cpython-312.pyc deleted file mode 100644 index 0612ad8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_bdist_rpm.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build.cpython-312.pyc deleted file mode 100644 index ee28f86..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_clib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_clib.cpython-312.pyc deleted file mode 100644 index b07d6df..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_clib.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_ext.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_ext.cpython-312.pyc deleted file mode 100644 index be1e72a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_ext.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_py.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_py.cpython-312.pyc deleted file mode 100644 index 9cdbe8d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_py.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_scripts.cpython-312.pyc deleted file mode 100644 index ce49778..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_build_scripts.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_check.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_check.cpython-312.pyc deleted file mode 100644 index 5626384..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_check.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_clean.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_clean.cpython-312.pyc deleted file mode 100644 index e902da1..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_clean.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_cmd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_cmd.cpython-312.pyc deleted file mode 100644 index 48e53bd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_cmd.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_config_cmd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_config_cmd.cpython-312.pyc deleted file mode 100644 index de5047f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_config_cmd.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_core.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_core.cpython-312.pyc deleted file mode 100644 index 4622b4a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_core.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_dir_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_dir_util.cpython-312.pyc deleted file mode 100644 index 9c24e8d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_dir_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_dist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_dist.cpython-312.pyc deleted file mode 100644 index 67cf8d9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_dist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_extension.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_extension.cpython-312.pyc deleted file mode 100644 index 10ec910..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_extension.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_file_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_file_util.cpython-312.pyc deleted file mode 100644 index d8be6a9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_file_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_filelist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_filelist.cpython-312.pyc deleted file mode 100644 index 27e019c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_filelist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install.cpython-312.pyc deleted file mode 100644 index 231a9bc..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_data.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_data.cpython-312.pyc deleted file mode 100644 index 06c8eee..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_data.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_headers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_headers.cpython-312.pyc deleted file mode 100644 index 351f349..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_headers.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_lib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_lib.cpython-312.pyc deleted file mode 100644 index c088d8d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_lib.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_scripts.cpython-312.pyc deleted file mode 100644 index f345b33..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_install_scripts.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_log.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_log.cpython-312.pyc deleted file mode 100644 index 90eeaab..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_log.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_modified.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_modified.cpython-312.pyc deleted file mode 100644 index 6ecbe72..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_modified.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_sdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_sdist.cpython-312.pyc deleted file mode 100644 index 9b1cd06..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_sdist.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_spawn.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_spawn.cpython-312.pyc deleted file mode 100644 index b83bf0d..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_spawn.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_sysconfig.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_sysconfig.cpython-312.pyc deleted file mode 100644 index 2f0c85c..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_sysconfig.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_text_file.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_text_file.cpython-312.pyc deleted file mode 100644 index 7be224b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_text_file.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_util.cpython-312.pyc deleted file mode 100644 index 383f2d5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_util.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_version.cpython-312.pyc deleted file mode 100644 index 1127ba3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_version.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_versionpredicate.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_versionpredicate.cpython-312.pyc deleted file mode 100644 index cf0962b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/test_versionpredicate.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/unix_compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/unix_compat.cpython-312.pyc deleted file mode 100644 index 2abff71..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/__pycache__/unix_compat.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index bdf18e5..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__pycache__/py39.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__pycache__/py39.cpython-312.pyc deleted file mode 100644 index 832ab2b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/__pycache__/py39.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/py39.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/py39.py deleted file mode 100644 index aca3939..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/compat/py39.py +++ /dev/null @@ -1,40 +0,0 @@ -import sys - -if sys.version_info >= (3, 10): - from test.support.import_helper import ( - CleanImport as CleanImport, - ) - from test.support.import_helper import ( - DirsOnSysPath as DirsOnSysPath, - ) - from test.support.os_helper import ( - EnvironmentVarGuard as EnvironmentVarGuard, - ) - from test.support.os_helper import ( - rmtree as rmtree, - ) - from test.support.os_helper import ( - skip_unless_symlink as skip_unless_symlink, - ) - from test.support.os_helper import ( - unlink as unlink, - ) -else: - from test.support import ( - CleanImport as CleanImport, - ) - from test.support import ( - DirsOnSysPath as DirsOnSysPath, - ) - from test.support import ( - EnvironmentVarGuard as EnvironmentVarGuard, - ) - from test.support import ( - rmtree as rmtree, - ) - from test.support import ( - skip_unless_symlink as skip_unless_symlink, - ) - from test.support import ( - unlink as unlink, - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/support.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/support.py deleted file mode 100644 index 9cd2b8a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/support.py +++ /dev/null @@ -1,134 +0,0 @@ -"""Support code for distutils test cases.""" - -import itertools -import os -import pathlib -import shutil -import sys -import sysconfig -import tempfile -from distutils.core import Distribution - -import pytest -from more_itertools import always_iterable - - -@pytest.mark.usefixtures('distutils_managed_tempdir') -class TempdirManager: - """ - Mix-in class that handles temporary directories for test cases. - """ - - def mkdtemp(self): - """Create a temporary directory that will be cleaned up. - - Returns the path of the directory. - """ - d = tempfile.mkdtemp() - self.tempdirs.append(d) - return d - - def write_file(self, path, content='xxx'): - """Writes a file in the given path. - - path can be a string or a sequence. - """ - pathlib.Path(*always_iterable(path)).write_text(content, encoding='utf-8') - - def create_dist(self, pkg_name='foo', **kw): - """Will generate a test environment. - - This function creates: - - a Distribution instance using keywords - - a temporary directory with a package structure - - It returns the package directory and the distribution - instance. - """ - tmp_dir = self.mkdtemp() - pkg_dir = os.path.join(tmp_dir, pkg_name) - os.mkdir(pkg_dir) - dist = Distribution(attrs=kw) - - return pkg_dir, dist - - -class DummyCommand: - """Class to store options for retrieval via set_undefined_options().""" - - def __init__(self, **kwargs): - vars(self).update(kwargs) - - def ensure_finalized(self): - pass - - -def copy_xxmodule_c(directory): - """Helper for tests that need the xxmodule.c source file. - - Example use: - - def test_compile(self): - copy_xxmodule_c(self.tmpdir) - self.assertIn('xxmodule.c', os.listdir(self.tmpdir)) - - If the source file can be found, it will be copied to *directory*. If not, - the test will be skipped. Errors during copy are not caught. - """ - shutil.copy(_get_xxmodule_path(), os.path.join(directory, 'xxmodule.c')) - - -def _get_xxmodule_path(): - source_name = 'xxmodule.c' if sys.version_info > (3, 9) else 'xxmodule-3.8.c' - return os.path.join(os.path.dirname(__file__), source_name) - - -def fixup_build_ext(cmd): - """Function needed to make build_ext tests pass. - - When Python was built with --enable-shared on Unix, -L. is not enough to - find libpython.so, because regrtest runs in a tempdir, not in the - source directory where the .so lives. - - When Python was built with in debug mode on Windows, build_ext commands - need their debug attribute set, and it is not done automatically for - some reason. - - This function handles both of these things. Example use: - - cmd = build_ext(dist) - support.fixup_build_ext(cmd) - cmd.ensure_finalized() - - Unlike most other Unix platforms, Mac OS X embeds absolute paths - to shared libraries into executables, so the fixup is not needed there. - """ - if os.name == 'nt': - cmd.debug = sys.executable.endswith('_d.exe') - elif sysconfig.get_config_var('Py_ENABLE_SHARED'): - # To further add to the shared builds fun on Unix, we can't just add - # library_dirs to the Extension() instance because that doesn't get - # plumbed through to the final compiler command. - runshared = sysconfig.get_config_var('RUNSHARED') - if runshared is None: - cmd.library_dirs = ['.'] - else: - if sys.platform == 'darwin': - cmd.library_dirs = [] - else: - name, equals, value = runshared.partition('=') - cmd.library_dirs = [d for d in value.split(os.pathsep) if d] - - -def combine_markers(cls): - """ - pytest will honor markers as found on the class, but when - markers are on multiple subclasses, only one appears. Use - this decorator to combine those markers. - """ - cls.pytestmark = [ - mark - for base in itertools.chain([cls], cls.__bases__) - for mark in getattr(base, 'pytestmark', []) - ] - return cls diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_archive_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_archive_util.py deleted file mode 100644 index 3e4ed75..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_archive_util.py +++ /dev/null @@ -1,353 +0,0 @@ -"""Tests for distutils.archive_util.""" - -import functools -import operator -import os -import pathlib -import sys -import tarfile -from distutils import archive_util -from distutils.archive_util import ( - ARCHIVE_FORMATS, - check_archive_formats, - make_archive, - make_tarball, - make_zipfile, -) -from distutils.spawn import spawn -from distutils.tests import support -from os.path import splitdrive - -import path -import pytest -from test.support import patch - -from .unix_compat import UID_0_SUPPORT, grp, pwd, require_uid_0, require_unix_id - - -def can_fs_encode(filename): - """ - Return True if the filename can be saved in the file system. - """ - if os.path.supports_unicode_filenames: - return True - try: - filename.encode(sys.getfilesystemencoding()) - except UnicodeEncodeError: - return False - return True - - -def all_equal(values): - return functools.reduce(operator.eq, values) - - -def same_drive(*paths): - return all_equal(pathlib.Path(path).drive for path in paths) - - -class ArchiveUtilTestCase(support.TempdirManager): - @pytest.mark.usefixtures('needs_zlib') - def test_make_tarball(self, name='archive'): - # creating something to tar - tmpdir = self._create_files() - self._make_tarball(tmpdir, name, '.tar.gz') - # trying an uncompressed one - self._make_tarball(tmpdir, name, '.tar', compress=None) - - @pytest.mark.usefixtures('needs_zlib') - def test_make_tarball_gzip(self): - tmpdir = self._create_files() - self._make_tarball(tmpdir, 'archive', '.tar.gz', compress='gzip') - - def test_make_tarball_bzip2(self): - pytest.importorskip('bz2') - tmpdir = self._create_files() - self._make_tarball(tmpdir, 'archive', '.tar.bz2', compress='bzip2') - - def test_make_tarball_xz(self): - pytest.importorskip('lzma') - tmpdir = self._create_files() - self._make_tarball(tmpdir, 'archive', '.tar.xz', compress='xz') - - @pytest.mark.skipif("not can_fs_encode('årchiv')") - def test_make_tarball_latin1(self): - """ - Mirror test_make_tarball, except filename contains latin characters. - """ - self.test_make_tarball('årchiv') # note this isn't a real word - - @pytest.mark.skipif("not can_fs_encode('のアーカイブ')") - def test_make_tarball_extended(self): - """ - Mirror test_make_tarball, except filename contains extended - characters outside the latin charset. - """ - self.test_make_tarball('のアーカイブ') # japanese for archive - - def _make_tarball(self, tmpdir, target_name, suffix, **kwargs): - tmpdir2 = self.mkdtemp() - if same_drive(tmpdir, tmpdir2): - pytest.skip("source and target should be on same drive") - - base_name = os.path.join(tmpdir2, target_name) - - # working with relative paths to avoid tar warnings - with path.Path(tmpdir): - make_tarball(splitdrive(base_name)[1], 'dist', **kwargs) - - # check if the compressed tarball was created - tarball = base_name + suffix - assert os.path.exists(tarball) - assert self._tarinfo(tarball) == self._created_files - - def _tarinfo(self, path): - tar = tarfile.open(path) - try: - names = tar.getnames() - names.sort() - return names - finally: - tar.close() - - _zip_created_files = [ - 'dist/', - 'dist/file1', - 'dist/file2', - 'dist/sub/', - 'dist/sub/file3', - 'dist/sub2/', - ] - _created_files = [p.rstrip('/') for p in _zip_created_files] - - def _create_files(self): - # creating something to tar - tmpdir = self.mkdtemp() - dist = os.path.join(tmpdir, 'dist') - os.mkdir(dist) - self.write_file([dist, 'file1'], 'xxx') - self.write_file([dist, 'file2'], 'xxx') - os.mkdir(os.path.join(dist, 'sub')) - self.write_file([dist, 'sub', 'file3'], 'xxx') - os.mkdir(os.path.join(dist, 'sub2')) - return tmpdir - - @pytest.mark.usefixtures('needs_zlib') - @pytest.mark.skipif("not (shutil.which('tar') and shutil.which('gzip'))") - def test_tarfile_vs_tar(self): - tmpdir = self._create_files() - tmpdir2 = self.mkdtemp() - base_name = os.path.join(tmpdir2, 'archive') - old_dir = os.getcwd() - os.chdir(tmpdir) - try: - make_tarball(base_name, 'dist') - finally: - os.chdir(old_dir) - - # check if the compressed tarball was created - tarball = base_name + '.tar.gz' - assert os.path.exists(tarball) - - # now create another tarball using `tar` - tarball2 = os.path.join(tmpdir, 'archive2.tar.gz') - tar_cmd = ['tar', '-cf', 'archive2.tar', 'dist'] - gzip_cmd = ['gzip', '-f', '-9', 'archive2.tar'] - old_dir = os.getcwd() - os.chdir(tmpdir) - try: - spawn(tar_cmd) - spawn(gzip_cmd) - finally: - os.chdir(old_dir) - - assert os.path.exists(tarball2) - # let's compare both tarballs - assert self._tarinfo(tarball) == self._created_files - assert self._tarinfo(tarball2) == self._created_files - - # trying an uncompressed one - base_name = os.path.join(tmpdir2, 'archive') - old_dir = os.getcwd() - os.chdir(tmpdir) - try: - make_tarball(base_name, 'dist', compress=None) - finally: - os.chdir(old_dir) - tarball = base_name + '.tar' - assert os.path.exists(tarball) - - # now for a dry_run - base_name = os.path.join(tmpdir2, 'archive') - old_dir = os.getcwd() - os.chdir(tmpdir) - try: - make_tarball(base_name, 'dist', compress=None, dry_run=True) - finally: - os.chdir(old_dir) - tarball = base_name + '.tar' - assert os.path.exists(tarball) - - @pytest.mark.usefixtures('needs_zlib') - def test_make_zipfile(self): - zipfile = pytest.importorskip('zipfile') - # creating something to tar - tmpdir = self._create_files() - base_name = os.path.join(self.mkdtemp(), 'archive') - with path.Path(tmpdir): - make_zipfile(base_name, 'dist') - - # check if the compressed tarball was created - tarball = base_name + '.zip' - assert os.path.exists(tarball) - with zipfile.ZipFile(tarball) as zf: - assert sorted(zf.namelist()) == self._zip_created_files - - def test_make_zipfile_no_zlib(self): - zipfile = pytest.importorskip('zipfile') - patch(self, archive_util.zipfile, 'zlib', None) # force zlib ImportError - - called = [] - zipfile_class = zipfile.ZipFile - - def fake_zipfile(*a, **kw): - if kw.get('compression', None) == zipfile.ZIP_STORED: - called.append((a, kw)) - return zipfile_class(*a, **kw) - - patch(self, archive_util.zipfile, 'ZipFile', fake_zipfile) - - # create something to tar and compress - tmpdir = self._create_files() - base_name = os.path.join(self.mkdtemp(), 'archive') - with path.Path(tmpdir): - make_zipfile(base_name, 'dist') - - tarball = base_name + '.zip' - assert called == [((tarball, "w"), {'compression': zipfile.ZIP_STORED})] - assert os.path.exists(tarball) - with zipfile.ZipFile(tarball) as zf: - assert sorted(zf.namelist()) == self._zip_created_files - - def test_check_archive_formats(self): - assert check_archive_formats(['gztar', 'xxx', 'zip']) == 'xxx' - assert ( - check_archive_formats(['gztar', 'bztar', 'xztar', 'ztar', 'tar', 'zip']) - is None - ) - - def test_make_archive(self): - tmpdir = self.mkdtemp() - base_name = os.path.join(tmpdir, 'archive') - with pytest.raises(ValueError): - make_archive(base_name, 'xxx') - - def test_make_archive_cwd(self): - current_dir = os.getcwd() - - def _breaks(*args, **kw): - raise RuntimeError() - - ARCHIVE_FORMATS['xxx'] = (_breaks, [], 'xxx file') - try: - try: - make_archive('xxx', 'xxx', root_dir=self.mkdtemp()) - except Exception: - pass - assert os.getcwd() == current_dir - finally: - ARCHIVE_FORMATS.pop('xxx') - - def test_make_archive_tar(self): - base_dir = self._create_files() - base_name = os.path.join(self.mkdtemp(), 'archive') - res = make_archive(base_name, 'tar', base_dir, 'dist') - assert os.path.exists(res) - assert os.path.basename(res) == 'archive.tar' - assert self._tarinfo(res) == self._created_files - - @pytest.mark.usefixtures('needs_zlib') - def test_make_archive_gztar(self): - base_dir = self._create_files() - base_name = os.path.join(self.mkdtemp(), 'archive') - res = make_archive(base_name, 'gztar', base_dir, 'dist') - assert os.path.exists(res) - assert os.path.basename(res) == 'archive.tar.gz' - assert self._tarinfo(res) == self._created_files - - def test_make_archive_bztar(self): - pytest.importorskip('bz2') - base_dir = self._create_files() - base_name = os.path.join(self.mkdtemp(), 'archive') - res = make_archive(base_name, 'bztar', base_dir, 'dist') - assert os.path.exists(res) - assert os.path.basename(res) == 'archive.tar.bz2' - assert self._tarinfo(res) == self._created_files - - def test_make_archive_xztar(self): - pytest.importorskip('lzma') - base_dir = self._create_files() - base_name = os.path.join(self.mkdtemp(), 'archive') - res = make_archive(base_name, 'xztar', base_dir, 'dist') - assert os.path.exists(res) - assert os.path.basename(res) == 'archive.tar.xz' - assert self._tarinfo(res) == self._created_files - - def test_make_archive_owner_group(self): - # testing make_archive with owner and group, with various combinations - # this works even if there's not gid/uid support - if UID_0_SUPPORT: - group = grp.getgrgid(0)[0] - owner = pwd.getpwuid(0)[0] - else: - group = owner = 'root' - - base_dir = self._create_files() - root_dir = self.mkdtemp() - base_name = os.path.join(self.mkdtemp(), 'archive') - res = make_archive( - base_name, 'zip', root_dir, base_dir, owner=owner, group=group - ) - assert os.path.exists(res) - - res = make_archive(base_name, 'zip', root_dir, base_dir) - assert os.path.exists(res) - - res = make_archive( - base_name, 'tar', root_dir, base_dir, owner=owner, group=group - ) - assert os.path.exists(res) - - res = make_archive( - base_name, 'tar', root_dir, base_dir, owner='kjhkjhkjg', group='oihohoh' - ) - assert os.path.exists(res) - - @pytest.mark.usefixtures('needs_zlib') - @require_unix_id - @require_uid_0 - def test_tarfile_root_owner(self): - tmpdir = self._create_files() - base_name = os.path.join(self.mkdtemp(), 'archive') - old_dir = os.getcwd() - os.chdir(tmpdir) - group = grp.getgrgid(0)[0] - owner = pwd.getpwuid(0)[0] - try: - archive_name = make_tarball( - base_name, 'dist', compress=None, owner=owner, group=group - ) - finally: - os.chdir(old_dir) - - # check if the compressed tarball was created - assert os.path.exists(archive_name) - - # now checks the rights - archive = tarfile.open(archive_name) - try: - for member in archive.getmembers(): - assert member.uid == 0 - assert member.gid == 0 - finally: - archive.close() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist.py deleted file mode 100644 index d5696fc..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist.py +++ /dev/null @@ -1,47 +0,0 @@ -"""Tests for distutils.command.bdist.""" - -from distutils.command.bdist import bdist -from distutils.tests import support - - -class TestBuild(support.TempdirManager): - def test_formats(self): - # let's create a command and make sure - # we can set the format - dist = self.create_dist()[1] - cmd = bdist(dist) - cmd.formats = ['gztar'] - cmd.ensure_finalized() - assert cmd.formats == ['gztar'] - - # what formats does bdist offer? - formats = [ - 'bztar', - 'gztar', - 'rpm', - 'tar', - 'xztar', - 'zip', - 'ztar', - ] - found = sorted(cmd.format_commands) - assert found == formats - - def test_skip_build(self): - # bug #10946: bdist --skip-build should trickle down to subcommands - dist = self.create_dist()[1] - cmd = bdist(dist) - cmd.skip_build = True - cmd.ensure_finalized() - dist.command_obj['bdist'] = cmd - - names = [ - 'bdist_dumb', - ] # bdist_rpm does not support --skip-build - - for name in names: - subcmd = cmd.get_finalized_command(name) - if getattr(subcmd, '_unsupported', False): - # command is not supported on this build - continue - assert subcmd.skip_build, f'{name} should take --skip-build from bdist' diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist_dumb.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist_dumb.py deleted file mode 100644 index 1fc51d2..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist_dumb.py +++ /dev/null @@ -1,78 +0,0 @@ -"""Tests for distutils.command.bdist_dumb.""" - -import os -import sys -import zipfile -from distutils.command.bdist_dumb import bdist_dumb -from distutils.core import Distribution -from distutils.tests import support - -import pytest - -SETUP_PY = """\ -from distutils.core import setup -import foo - -setup(name='foo', version='0.1', py_modules=['foo'], - url='xxx', author='xxx', author_email='xxx') - -""" - - -@support.combine_markers -@pytest.mark.usefixtures('save_env') -@pytest.mark.usefixtures('save_argv') -@pytest.mark.usefixtures('save_cwd') -class TestBuildDumb( - support.TempdirManager, -): - @pytest.mark.usefixtures('needs_zlib') - def test_simple_built(self): - # let's create a simple package - tmp_dir = self.mkdtemp() - pkg_dir = os.path.join(tmp_dir, 'foo') - os.mkdir(pkg_dir) - self.write_file((pkg_dir, 'setup.py'), SETUP_PY) - self.write_file((pkg_dir, 'foo.py'), '#') - self.write_file((pkg_dir, 'MANIFEST.in'), 'include foo.py') - self.write_file((pkg_dir, 'README'), '') - - dist = Distribution({ - 'name': 'foo', - 'version': '0.1', - 'py_modules': ['foo'], - 'url': 'xxx', - 'author': 'xxx', - 'author_email': 'xxx', - }) - dist.script_name = 'setup.py' - os.chdir(pkg_dir) - - sys.argv = ['setup.py'] - cmd = bdist_dumb(dist) - - # so the output is the same no matter - # what is the platform - cmd.format = 'zip' - - cmd.ensure_finalized() - cmd.run() - - # see what we have - dist_created = os.listdir(os.path.join(pkg_dir, 'dist')) - base = f"{dist.get_fullname()}.{cmd.plat_name}.zip" - - assert dist_created == [base] - - # now let's check what we have in the zip file - fp = zipfile.ZipFile(os.path.join('dist', base)) - try: - contents = fp.namelist() - finally: - fp.close() - - contents = sorted(filter(None, map(os.path.basename, contents))) - wanted = ['foo-0.1-py{}.{}.egg-info'.format(*sys.version_info[:2]), 'foo.py'] - if not sys.dont_write_bytecode: - wanted.append(f'foo.{sys.implementation.cache_tag}.pyc') - assert contents == sorted(wanted) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist_rpm.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist_rpm.py deleted file mode 100644 index 7505143..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_bdist_rpm.py +++ /dev/null @@ -1,127 +0,0 @@ -"""Tests for distutils.command.bdist_rpm.""" - -import os -import shutil # noqa: F401 -import sys -from distutils.command.bdist_rpm import bdist_rpm -from distutils.core import Distribution -from distutils.tests import support - -import pytest -from test.support import requires_zlib - -SETUP_PY = """\ -from distutils.core import setup -import foo - -setup(name='foo', version='0.1', py_modules=['foo'], - url='xxx', author='xxx', author_email='xxx') - -""" - - -@pytest.fixture(autouse=True) -def sys_executable_encodable(): - try: - sys.executable.encode('UTF-8') - except UnicodeEncodeError: - pytest.skip("sys.executable is not encodable to UTF-8") - - -mac_woes = pytest.mark.skipif( - "not sys.platform.startswith('linux')", - reason='spurious sdtout/stderr output under macOS', -) - - -@pytest.mark.usefixtures('save_env') -@pytest.mark.usefixtures('save_argv') -@pytest.mark.usefixtures('save_cwd') -class TestBuildRpm( - support.TempdirManager, -): - @mac_woes - @requires_zlib() - @pytest.mark.skipif("not shutil.which('rpm')") - @pytest.mark.skipif("not shutil.which('rpmbuild')") - def test_quiet(self): - # let's create a package - tmp_dir = self.mkdtemp() - os.environ['HOME'] = tmp_dir # to confine dir '.rpmdb' creation - pkg_dir = os.path.join(tmp_dir, 'foo') - os.mkdir(pkg_dir) - self.write_file((pkg_dir, 'setup.py'), SETUP_PY) - self.write_file((pkg_dir, 'foo.py'), '#') - self.write_file((pkg_dir, 'MANIFEST.in'), 'include foo.py') - self.write_file((pkg_dir, 'README'), '') - - dist = Distribution({ - 'name': 'foo', - 'version': '0.1', - 'py_modules': ['foo'], - 'url': 'xxx', - 'author': 'xxx', - 'author_email': 'xxx', - }) - dist.script_name = 'setup.py' - os.chdir(pkg_dir) - - sys.argv = ['setup.py'] - cmd = bdist_rpm(dist) - cmd.fix_python = True - - # running in quiet mode - cmd.quiet = True - cmd.ensure_finalized() - cmd.run() - - dist_created = os.listdir(os.path.join(pkg_dir, 'dist')) - assert 'foo-0.1-1.noarch.rpm' in dist_created - - # bug #2945: upload ignores bdist_rpm files - assert ('bdist_rpm', 'any', 'dist/foo-0.1-1.src.rpm') in dist.dist_files - assert ('bdist_rpm', 'any', 'dist/foo-0.1-1.noarch.rpm') in dist.dist_files - - @mac_woes - @requires_zlib() - # https://bugs.python.org/issue1533164 - @pytest.mark.skipif("not shutil.which('rpm')") - @pytest.mark.skipif("not shutil.which('rpmbuild')") - def test_no_optimize_flag(self): - # let's create a package that breaks bdist_rpm - tmp_dir = self.mkdtemp() - os.environ['HOME'] = tmp_dir # to confine dir '.rpmdb' creation - pkg_dir = os.path.join(tmp_dir, 'foo') - os.mkdir(pkg_dir) - self.write_file((pkg_dir, 'setup.py'), SETUP_PY) - self.write_file((pkg_dir, 'foo.py'), '#') - self.write_file((pkg_dir, 'MANIFEST.in'), 'include foo.py') - self.write_file((pkg_dir, 'README'), '') - - dist = Distribution({ - 'name': 'foo', - 'version': '0.1', - 'py_modules': ['foo'], - 'url': 'xxx', - 'author': 'xxx', - 'author_email': 'xxx', - }) - dist.script_name = 'setup.py' - os.chdir(pkg_dir) - - sys.argv = ['setup.py'] - cmd = bdist_rpm(dist) - cmd.fix_python = True - - cmd.quiet = True - cmd.ensure_finalized() - cmd.run() - - dist_created = os.listdir(os.path.join(pkg_dir, 'dist')) - assert 'foo-0.1-1.noarch.rpm' in dist_created - - # bug #2945: upload ignores bdist_rpm files - assert ('bdist_rpm', 'any', 'dist/foo-0.1-1.src.rpm') in dist.dist_files - assert ('bdist_rpm', 'any', 'dist/foo-0.1-1.noarch.rpm') in dist.dist_files - - os.remove(os.path.join(pkg_dir, 'dist', 'foo-0.1-1.noarch.rpm')) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build.py deleted file mode 100644 index f7fe69a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build.py +++ /dev/null @@ -1,49 +0,0 @@ -"""Tests for distutils.command.build.""" - -import os -import sys -from distutils.command.build import build -from distutils.tests import support -from sysconfig import get_config_var, get_platform - - -class TestBuild(support.TempdirManager): - def test_finalize_options(self): - pkg_dir, dist = self.create_dist() - cmd = build(dist) - cmd.finalize_options() - - # if not specified, plat_name gets the current platform - assert cmd.plat_name == get_platform() - - # build_purelib is build + lib - wanted = os.path.join(cmd.build_base, 'lib') - assert cmd.build_purelib == wanted - - # build_platlib is 'build/lib.platform-cache_tag[-pydebug]' - # examples: - # build/lib.macosx-10.3-i386-cpython39 - plat_spec = f'.{cmd.plat_name}-{sys.implementation.cache_tag}' - if get_config_var('Py_GIL_DISABLED'): - plat_spec += 't' - if hasattr(sys, 'gettotalrefcount'): - assert cmd.build_platlib.endswith('-pydebug') - plat_spec += '-pydebug' - wanted = os.path.join(cmd.build_base, 'lib' + plat_spec) - assert cmd.build_platlib == wanted - - # by default, build_lib = build_purelib - assert cmd.build_lib == cmd.build_purelib - - # build_temp is build/temp. - wanted = os.path.join(cmd.build_base, 'temp' + plat_spec) - assert cmd.build_temp == wanted - - # build_scripts is build/scripts-x.x - wanted = os.path.join( - cmd.build_base, f'scripts-{sys.version_info.major}.{sys.version_info.minor}' - ) - assert cmd.build_scripts == wanted - - # executable is os.path.normpath(sys.executable) - assert cmd.executable == os.path.normpath(sys.executable) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_clib.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_clib.py deleted file mode 100644 index f76f26b..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_clib.py +++ /dev/null @@ -1,134 +0,0 @@ -"""Tests for distutils.command.build_clib.""" - -import os -from distutils.command.build_clib import build_clib -from distutils.errors import DistutilsSetupError -from distutils.tests import missing_compiler_executable, support - -import pytest - - -class TestBuildCLib(support.TempdirManager): - def test_check_library_dist(self): - pkg_dir, dist = self.create_dist() - cmd = build_clib(dist) - - # 'libraries' option must be a list - with pytest.raises(DistutilsSetupError): - cmd.check_library_list('foo') - - # each element of 'libraries' must a 2-tuple - with pytest.raises(DistutilsSetupError): - cmd.check_library_list(['foo1', 'foo2']) - - # first element of each tuple in 'libraries' - # must be a string (the library name) - with pytest.raises(DistutilsSetupError): - cmd.check_library_list([(1, 'foo1'), ('name', 'foo2')]) - - # library name may not contain directory separators - with pytest.raises(DistutilsSetupError): - cmd.check_library_list( - [('name', 'foo1'), ('another/name', 'foo2')], - ) - - # second element of each tuple must be a dictionary (build info) - with pytest.raises(DistutilsSetupError): - cmd.check_library_list( - [('name', {}), ('another', 'foo2')], - ) - - # those work - libs = [('name', {}), ('name', {'ok': 'good'})] - cmd.check_library_list(libs) - - def test_get_source_files(self): - pkg_dir, dist = self.create_dist() - cmd = build_clib(dist) - - # "in 'libraries' option 'sources' must be present and must be - # a list of source filenames - cmd.libraries = [('name', {})] - with pytest.raises(DistutilsSetupError): - cmd.get_source_files() - - cmd.libraries = [('name', {'sources': 1})] - with pytest.raises(DistutilsSetupError): - cmd.get_source_files() - - cmd.libraries = [('name', {'sources': ['a', 'b']})] - assert cmd.get_source_files() == ['a', 'b'] - - cmd.libraries = [('name', {'sources': ('a', 'b')})] - assert cmd.get_source_files() == ['a', 'b'] - - cmd.libraries = [ - ('name', {'sources': ('a', 'b')}), - ('name2', {'sources': ['c', 'd']}), - ] - assert cmd.get_source_files() == ['a', 'b', 'c', 'd'] - - def test_build_libraries(self): - pkg_dir, dist = self.create_dist() - cmd = build_clib(dist) - - class FakeCompiler: - def compile(*args, **kw): - pass - - create_static_lib = compile - - cmd.compiler = FakeCompiler() - - # build_libraries is also doing a bit of typo checking - lib = [('name', {'sources': 'notvalid'})] - with pytest.raises(DistutilsSetupError): - cmd.build_libraries(lib) - - lib = [('name', {'sources': list()})] - cmd.build_libraries(lib) - - lib = [('name', {'sources': tuple()})] - cmd.build_libraries(lib) - - def test_finalize_options(self): - pkg_dir, dist = self.create_dist() - cmd = build_clib(dist) - - cmd.include_dirs = 'one-dir' - cmd.finalize_options() - assert cmd.include_dirs == ['one-dir'] - - cmd.include_dirs = None - cmd.finalize_options() - assert cmd.include_dirs == [] - - cmd.distribution.libraries = 'WONTWORK' - with pytest.raises(DistutilsSetupError): - cmd.finalize_options() - - @pytest.mark.skipif('platform.system() == "Windows"') - def test_run(self): - pkg_dir, dist = self.create_dist() - cmd = build_clib(dist) - - foo_c = os.path.join(pkg_dir, 'foo.c') - self.write_file(foo_c, 'int main(void) { return 1;}\n') - cmd.libraries = [('foo', {'sources': [foo_c]})] - - build_temp = os.path.join(pkg_dir, 'build') - os.mkdir(build_temp) - cmd.build_temp = build_temp - cmd.build_clib = build_temp - - # Before we run the command, we want to make sure - # all commands are present on the system. - ccmd = missing_compiler_executable() - if ccmd is not None: - self.skipTest(f'The {ccmd!r} command is not found') - - # this should work - cmd.run() - - # let's check the result - assert 'libfoo.a' in os.listdir(build_temp) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_ext.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_ext.py deleted file mode 100644 index dab0507..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_ext.py +++ /dev/null @@ -1,628 +0,0 @@ -import contextlib -import glob -import importlib -import os.path -import platform -import re -import shutil -import site -import subprocess -import sys -import tempfile -import textwrap -import time -from distutils import sysconfig -from distutils.command.build_ext import build_ext -from distutils.core import Distribution -from distutils.errors import ( - CompileError, - DistutilsPlatformError, - DistutilsSetupError, - UnknownFileError, -) -from distutils.extension import Extension -from distutils.tests import missing_compiler_executable -from distutils.tests.support import TempdirManager, copy_xxmodule_c, fixup_build_ext -from io import StringIO - -import jaraco.path -import path -import pytest -from test import support - -from .compat import py39 as import_helper - - -@pytest.fixture() -def user_site_dir(request): - self = request.instance - self.tmp_dir = self.mkdtemp() - self.tmp_path = path.Path(self.tmp_dir) - from distutils.command import build_ext - - orig_user_base = site.USER_BASE - - site.USER_BASE = self.mkdtemp() - build_ext.USER_BASE = site.USER_BASE - - # bpo-30132: On Windows, a .pdb file may be created in the current - # working directory. Create a temporary working directory to cleanup - # everything at the end of the test. - with self.tmp_path: - yield - - site.USER_BASE = orig_user_base - build_ext.USER_BASE = orig_user_base - - if sys.platform == 'cygwin': - time.sleep(1) - - -@contextlib.contextmanager -def safe_extension_import(name, path): - with import_helper.CleanImport(name): - with extension_redirect(name, path) as new_path: - with import_helper.DirsOnSysPath(new_path): - yield - - -@contextlib.contextmanager -def extension_redirect(mod, path): - """ - Tests will fail to tear down an extension module if it's been imported. - - Before importing, copy the file to a temporary directory that won't - be cleaned up. Yield the new path. - """ - if platform.system() != "Windows" and sys.platform != "cygwin": - yield path - return - with import_helper.DirsOnSysPath(path): - spec = importlib.util.find_spec(mod) - filename = os.path.basename(spec.origin) - trash_dir = tempfile.mkdtemp(prefix='deleteme') - dest = os.path.join(trash_dir, os.path.basename(filename)) - shutil.copy(spec.origin, dest) - yield trash_dir - # TODO: can the file be scheduled for deletion? - - -@pytest.mark.usefixtures('user_site_dir') -class TestBuildExt(TempdirManager): - def build_ext(self, *args, **kwargs): - return build_ext(*args, **kwargs) - - @pytest.mark.parametrize("copy_so", [False]) - def test_build_ext(self, copy_so): - missing_compiler_executable() - copy_xxmodule_c(self.tmp_dir) - xx_c = os.path.join(self.tmp_dir, 'xxmodule.c') - xx_ext = Extension('xx', [xx_c]) - if sys.platform != "win32": - if not copy_so: - xx_ext = Extension( - 'xx', - [xx_c], - library_dirs=['/usr/lib'], - libraries=['z'], - runtime_library_dirs=['/usr/lib'], - ) - elif sys.platform == 'linux': - libz_so = { - os.path.realpath(name) for name in glob.iglob('/usr/lib*/libz.so*') - } - libz_so = sorted(libz_so, key=lambda lib_path: len(lib_path)) - shutil.copyfile(libz_so[-1], '/tmp/libxx_z.so') - - xx_ext = Extension( - 'xx', - [xx_c], - library_dirs=['/tmp'], - libraries=['xx_z'], - runtime_library_dirs=['/tmp'], - ) - dist = Distribution({'name': 'xx', 'ext_modules': [xx_ext]}) - dist.package_dir = self.tmp_dir - cmd = self.build_ext(dist) - fixup_build_ext(cmd) - cmd.build_lib = self.tmp_dir - cmd.build_temp = self.tmp_dir - - old_stdout = sys.stdout - if not support.verbose: - # silence compiler output - sys.stdout = StringIO() - try: - cmd.ensure_finalized() - cmd.run() - finally: - sys.stdout = old_stdout - - with safe_extension_import('xx', self.tmp_dir): - self._test_xx(copy_so) - - if sys.platform == 'linux' and copy_so: - os.unlink('/tmp/libxx_z.so') - - @staticmethod - def _test_xx(copy_so): - import xx # type: ignore[import-not-found] # Module generated for tests - - for attr in ('error', 'foo', 'new', 'roj'): - assert hasattr(xx, attr) - - assert xx.foo(2, 5) == 7 - assert xx.foo(13, 15) == 28 - assert xx.new().demo() is None - if support.HAVE_DOCSTRINGS: - doc = 'This is a template module just for instruction.' - assert xx.__doc__ == doc - assert isinstance(xx.Null(), xx.Null) - assert isinstance(xx.Str(), xx.Str) - - if sys.platform == 'linux': - so_headers = subprocess.check_output( - ["readelf", "-d", xx.__file__], universal_newlines=True - ) - import pprint - - pprint.pprint(so_headers) - rpaths = [ - rpath - for line in so_headers.split("\n") - if "RPATH" in line or "RUNPATH" in line - for rpath in line.split()[2][1:-1].split(":") - ] - if not copy_so: - pprint.pprint(rpaths) - # Linked against a library in /usr/lib{,64} - assert "/usr/lib" not in rpaths and "/usr/lib64" not in rpaths - else: - # Linked against a library in /tmp - assert "/tmp" in rpaths - # The import is the real test here - - def test_solaris_enable_shared(self): - dist = Distribution({'name': 'xx'}) - cmd = self.build_ext(dist) - old = sys.platform - - sys.platform = 'sunos' # fooling finalize_options - from distutils.sysconfig import _config_vars - - old_var = _config_vars.get('Py_ENABLE_SHARED') - _config_vars['Py_ENABLE_SHARED'] = True - try: - cmd.ensure_finalized() - finally: - sys.platform = old - if old_var is None: - del _config_vars['Py_ENABLE_SHARED'] - else: - _config_vars['Py_ENABLE_SHARED'] = old_var - - # make sure we get some library dirs under solaris - assert len(cmd.library_dirs) > 0 - - def test_user_site(self): - import site - - dist = Distribution({'name': 'xx'}) - cmd = self.build_ext(dist) - - # making sure the user option is there - options = [name for name, short, label in cmd.user_options] - assert 'user' in options - - # setting a value - cmd.user = True - - # setting user based lib and include - lib = os.path.join(site.USER_BASE, 'lib') - incl = os.path.join(site.USER_BASE, 'include') - os.mkdir(lib) - os.mkdir(incl) - - # let's run finalize - cmd.ensure_finalized() - - # see if include_dirs and library_dirs - # were set - assert lib in cmd.library_dirs - assert lib in cmd.rpath - assert incl in cmd.include_dirs - - def test_optional_extension(self): - # this extension will fail, but let's ignore this failure - # with the optional argument. - modules = [Extension('foo', ['xxx'], optional=False)] - dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = self.build_ext(dist) - cmd.ensure_finalized() - with pytest.raises((UnknownFileError, CompileError)): - cmd.run() # should raise an error - - modules = [Extension('foo', ['xxx'], optional=True)] - dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = self.build_ext(dist) - cmd.ensure_finalized() - cmd.run() # should pass - - def test_finalize_options(self): - # Make sure Python's include directories (for Python.h, pyconfig.h, - # etc.) are in the include search path. - modules = [Extension('foo', ['xxx'], optional=False)] - dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = self.build_ext(dist) - cmd.finalize_options() - - py_include = sysconfig.get_python_inc() - for p in py_include.split(os.path.pathsep): - assert p in cmd.include_dirs - - plat_py_include = sysconfig.get_python_inc(plat_specific=True) - for p in plat_py_include.split(os.path.pathsep): - assert p in cmd.include_dirs - - # make sure cmd.libraries is turned into a list - # if it's a string - cmd = self.build_ext(dist) - cmd.libraries = 'my_lib, other_lib lastlib' - cmd.finalize_options() - assert cmd.libraries == ['my_lib', 'other_lib', 'lastlib'] - - # make sure cmd.library_dirs is turned into a list - # if it's a string - cmd = self.build_ext(dist) - cmd.library_dirs = f'my_lib_dir{os.pathsep}other_lib_dir' - cmd.finalize_options() - assert 'my_lib_dir' in cmd.library_dirs - assert 'other_lib_dir' in cmd.library_dirs - - # make sure rpath is turned into a list - # if it's a string - cmd = self.build_ext(dist) - cmd.rpath = f'one{os.pathsep}two' - cmd.finalize_options() - assert cmd.rpath == ['one', 'two'] - - # make sure cmd.link_objects is turned into a list - # if it's a string - cmd = build_ext(dist) - cmd.link_objects = 'one two,three' - cmd.finalize_options() - assert cmd.link_objects == ['one', 'two', 'three'] - - # XXX more tests to perform for win32 - - # make sure define is turned into 2-tuples - # strings if they are ','-separated strings - cmd = self.build_ext(dist) - cmd.define = 'one,two' - cmd.finalize_options() - assert cmd.define == [('one', '1'), ('two', '1')] - - # make sure undef is turned into a list of - # strings if they are ','-separated strings - cmd = self.build_ext(dist) - cmd.undef = 'one,two' - cmd.finalize_options() - assert cmd.undef == ['one', 'two'] - - # make sure swig_opts is turned into a list - cmd = self.build_ext(dist) - cmd.swig_opts = None - cmd.finalize_options() - assert cmd.swig_opts == [] - - cmd = self.build_ext(dist) - cmd.swig_opts = '1 2' - cmd.finalize_options() - assert cmd.swig_opts == ['1', '2'] - - def test_check_extensions_list(self): - dist = Distribution() - cmd = self.build_ext(dist) - cmd.finalize_options() - - # 'extensions' option must be a list of Extension instances - with pytest.raises(DistutilsSetupError): - cmd.check_extensions_list('foo') - - # each element of 'ext_modules' option must be an - # Extension instance or 2-tuple - exts = [('bar', 'foo', 'bar'), 'foo'] - with pytest.raises(DistutilsSetupError): - cmd.check_extensions_list(exts) - - # first element of each tuple in 'ext_modules' - # must be the extension name (a string) and match - # a python dotted-separated name - exts = [('foo-bar', '')] - with pytest.raises(DistutilsSetupError): - cmd.check_extensions_list(exts) - - # second element of each tuple in 'ext_modules' - # must be a dictionary (build info) - exts = [('foo.bar', '')] - with pytest.raises(DistutilsSetupError): - cmd.check_extensions_list(exts) - - # ok this one should pass - exts = [('foo.bar', {'sources': [''], 'libraries': 'foo', 'some': 'bar'})] - cmd.check_extensions_list(exts) - ext = exts[0] - assert isinstance(ext, Extension) - - # check_extensions_list adds in ext the values passed - # when they are in ('include_dirs', 'library_dirs', 'libraries' - # 'extra_objects', 'extra_compile_args', 'extra_link_args') - assert ext.libraries == 'foo' - assert not hasattr(ext, 'some') - - # 'macros' element of build info dict must be 1- or 2-tuple - exts = [ - ( - 'foo.bar', - { - 'sources': [''], - 'libraries': 'foo', - 'some': 'bar', - 'macros': [('1', '2', '3'), 'foo'], - }, - ) - ] - with pytest.raises(DistutilsSetupError): - cmd.check_extensions_list(exts) - - exts[0][1]['macros'] = [('1', '2'), ('3',)] - cmd.check_extensions_list(exts) - assert exts[0].undef_macros == ['3'] - assert exts[0].define_macros == [('1', '2')] - - def test_get_source_files(self): - modules = [Extension('foo', ['xxx'], optional=False)] - dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = self.build_ext(dist) - cmd.ensure_finalized() - assert cmd.get_source_files() == ['xxx'] - - def test_unicode_module_names(self): - modules = [ - Extension('foo', ['aaa'], optional=False), - Extension('föö', ['uuu'], optional=False), - ] - dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = self.build_ext(dist) - cmd.ensure_finalized() - assert re.search(r'foo(_d)?\..*', cmd.get_ext_filename(modules[0].name)) - assert re.search(r'föö(_d)?\..*', cmd.get_ext_filename(modules[1].name)) - assert cmd.get_export_symbols(modules[0]) == ['PyInit_foo'] - assert cmd.get_export_symbols(modules[1]) == ['PyInitU_f_1gaa'] - - def test_export_symbols__init__(self): - # https://github.com/python/cpython/issues/80074 - # https://github.com/pypa/setuptools/issues/4826 - modules = [ - Extension('foo.__init__', ['aaa']), - Extension('föö.__init__', ['uuu']), - ] - dist = Distribution({'name': 'xx', 'ext_modules': modules}) - cmd = self.build_ext(dist) - cmd.ensure_finalized() - assert cmd.get_export_symbols(modules[0]) == ['PyInit_foo'] - assert cmd.get_export_symbols(modules[1]) == ['PyInitU_f_1gaa'] - - def test_compiler_option(self): - # cmd.compiler is an option and - # should not be overridden by a compiler instance - # when the command is run - dist = Distribution() - cmd = self.build_ext(dist) - cmd.compiler = 'unix' - cmd.ensure_finalized() - cmd.run() - assert cmd.compiler == 'unix' - - def test_get_outputs(self): - missing_compiler_executable() - tmp_dir = self.mkdtemp() - c_file = os.path.join(tmp_dir, 'foo.c') - self.write_file(c_file, 'void PyInit_foo(void) {}\n') - ext = Extension('foo', [c_file], optional=False) - dist = Distribution({'name': 'xx', 'ext_modules': [ext]}) - cmd = self.build_ext(dist) - fixup_build_ext(cmd) - cmd.ensure_finalized() - assert len(cmd.get_outputs()) == 1 - - cmd.build_lib = os.path.join(self.tmp_dir, 'build') - cmd.build_temp = os.path.join(self.tmp_dir, 'tempt') - - # issue #5977 : distutils build_ext.get_outputs - # returns wrong result with --inplace - other_tmp_dir = os.path.realpath(self.mkdtemp()) - old_wd = os.getcwd() - os.chdir(other_tmp_dir) - try: - cmd.inplace = True - cmd.run() - so_file = cmd.get_outputs()[0] - finally: - os.chdir(old_wd) - assert os.path.exists(so_file) - ext_suffix = sysconfig.get_config_var('EXT_SUFFIX') - assert so_file.endswith(ext_suffix) - so_dir = os.path.dirname(so_file) - assert so_dir == other_tmp_dir - - cmd.inplace = False - cmd.compiler = None - cmd.run() - so_file = cmd.get_outputs()[0] - assert os.path.exists(so_file) - assert so_file.endswith(ext_suffix) - so_dir = os.path.dirname(so_file) - assert so_dir == cmd.build_lib - - # inplace = False, cmd.package = 'bar' - build_py = cmd.get_finalized_command('build_py') - build_py.package_dir = {'': 'bar'} - path = cmd.get_ext_fullpath('foo') - # checking that the last directory is the build_dir - path = os.path.split(path)[0] - assert path == cmd.build_lib - - # inplace = True, cmd.package = 'bar' - cmd.inplace = True - other_tmp_dir = os.path.realpath(self.mkdtemp()) - old_wd = os.getcwd() - os.chdir(other_tmp_dir) - try: - path = cmd.get_ext_fullpath('foo') - finally: - os.chdir(old_wd) - # checking that the last directory is bar - path = os.path.split(path)[0] - lastdir = os.path.split(path)[-1] - assert lastdir == 'bar' - - def test_ext_fullpath(self): - ext = sysconfig.get_config_var('EXT_SUFFIX') - # building lxml.etree inplace - # etree_c = os.path.join(self.tmp_dir, 'lxml.etree.c') - # etree_ext = Extension('lxml.etree', [etree_c]) - # dist = Distribution({'name': 'lxml', 'ext_modules': [etree_ext]}) - dist = Distribution() - cmd = self.build_ext(dist) - cmd.inplace = True - cmd.distribution.package_dir = {'': 'src'} - cmd.distribution.packages = ['lxml', 'lxml.html'] - curdir = os.getcwd() - wanted = os.path.join(curdir, 'src', 'lxml', 'etree' + ext) - path = cmd.get_ext_fullpath('lxml.etree') - assert wanted == path - - # building lxml.etree not inplace - cmd.inplace = False - cmd.build_lib = os.path.join(curdir, 'tmpdir') - wanted = os.path.join(curdir, 'tmpdir', 'lxml', 'etree' + ext) - path = cmd.get_ext_fullpath('lxml.etree') - assert wanted == path - - # building twisted.runner.portmap not inplace - build_py = cmd.get_finalized_command('build_py') - build_py.package_dir = {} - cmd.distribution.packages = ['twisted', 'twisted.runner.portmap'] - path = cmd.get_ext_fullpath('twisted.runner.portmap') - wanted = os.path.join(curdir, 'tmpdir', 'twisted', 'runner', 'portmap' + ext) - assert wanted == path - - # building twisted.runner.portmap inplace - cmd.inplace = True - path = cmd.get_ext_fullpath('twisted.runner.portmap') - wanted = os.path.join(curdir, 'twisted', 'runner', 'portmap' + ext) - assert wanted == path - - @pytest.mark.skipif('platform.system() != "Darwin"') - @pytest.mark.usefixtures('save_env') - def test_deployment_target_default(self): - # Issue 9516: Test that, in the absence of the environment variable, - # an extension module is compiled with the same deployment target as - # the interpreter. - self._try_compile_deployment_target('==', None) - - @pytest.mark.skipif('platform.system() != "Darwin"') - @pytest.mark.usefixtures('save_env') - def test_deployment_target_too_low(self): - # Issue 9516: Test that an extension module is not allowed to be - # compiled with a deployment target less than that of the interpreter. - with pytest.raises(DistutilsPlatformError): - self._try_compile_deployment_target('>', '10.1') - - @pytest.mark.skipif('platform.system() != "Darwin"') - @pytest.mark.usefixtures('save_env') - def test_deployment_target_higher_ok(self): # pragma: no cover - # Issue 9516: Test that an extension module can be compiled with a - # deployment target higher than that of the interpreter: the ext - # module may depend on some newer OS feature. - deptarget = sysconfig.get_config_var('MACOSX_DEPLOYMENT_TARGET') - if deptarget: - # increment the minor version number (i.e. 10.6 -> 10.7) - deptarget = [int(x) for x in deptarget.split('.')] - deptarget[-1] += 1 - deptarget = '.'.join(str(i) for i in deptarget) - self._try_compile_deployment_target('<', deptarget) - - def _try_compile_deployment_target(self, operator, target): # pragma: no cover - if target is None: - if os.environ.get('MACOSX_DEPLOYMENT_TARGET'): - del os.environ['MACOSX_DEPLOYMENT_TARGET'] - else: - os.environ['MACOSX_DEPLOYMENT_TARGET'] = target - - jaraco.path.build( - { - 'deptargetmodule.c': textwrap.dedent(f"""\ - #include - - int dummy; - - #if TARGET {operator} MAC_OS_X_VERSION_MIN_REQUIRED - #else - #error "Unexpected target" - #endif - - """), - }, - self.tmp_path, - ) - - # get the deployment target that the interpreter was built with - target = sysconfig.get_config_var('MACOSX_DEPLOYMENT_TARGET') - target = tuple(map(int, target.split('.')[0:2])) - # format the target value as defined in the Apple - # Availability Macros. We can't use the macro names since - # at least one value we test with will not exist yet. - if target[:2] < (10, 10): - # for 10.1 through 10.9.x -> "10n0" - tmpl = '{:02}{:01}0' - else: - # for 10.10 and beyond -> "10nn00" - if len(target) >= 2: - tmpl = '{:02}{:02}00' - else: - # 11 and later can have no minor version (11 instead of 11.0) - tmpl = '{:02}0000' - target = tmpl.format(*target) - deptarget_ext = Extension( - 'deptarget', - [self.tmp_path / 'deptargetmodule.c'], - extra_compile_args=[f'-DTARGET={target}'], - ) - dist = Distribution({'name': 'deptarget', 'ext_modules': [deptarget_ext]}) - dist.package_dir = self.tmp_dir - cmd = self.build_ext(dist) - cmd.build_lib = self.tmp_dir - cmd.build_temp = self.tmp_dir - - try: - old_stdout = sys.stdout - if not support.verbose: - # silence compiler output - sys.stdout = StringIO() - try: - cmd.ensure_finalized() - cmd.run() - finally: - sys.stdout = old_stdout - - except CompileError: - self.fail("Wrong deployment target during compilation") - - -class TestParallelBuildExt(TestBuildExt): - def build_ext(self, *args, **kwargs): - build_ext = super().build_ext(*args, **kwargs) - build_ext.parallel = True - return build_ext diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_py.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_py.py deleted file mode 100644 index b316ed4..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_py.py +++ /dev/null @@ -1,196 +0,0 @@ -"""Tests for distutils.command.build_py.""" - -import os -import sys -from distutils.command.build_py import build_py -from distutils.core import Distribution -from distutils.errors import DistutilsFileError -from distutils.tests import support - -import jaraco.path -import pytest - - -@support.combine_markers -class TestBuildPy(support.TempdirManager): - def test_package_data(self): - sources = self.mkdtemp() - jaraco.path.build( - { - '__init__.py': "# Pretend this is a package.", - 'README.txt': 'Info about this package', - }, - sources, - ) - - destination = self.mkdtemp() - - dist = Distribution({"packages": ["pkg"], "package_dir": {"pkg": sources}}) - # script_name need not exist, it just need to be initialized - dist.script_name = os.path.join(sources, "setup.py") - dist.command_obj["build"] = support.DummyCommand( - force=False, build_lib=destination - ) - dist.packages = ["pkg"] - dist.package_data = {"pkg": ["README.txt"]} - dist.package_dir = {"pkg": sources} - - cmd = build_py(dist) - cmd.compile = True - cmd.ensure_finalized() - assert cmd.package_data == dist.package_data - - cmd.run() - - # This makes sure the list of outputs includes byte-compiled - # files for Python modules but not for package data files - # (there shouldn't *be* byte-code files for those!). - assert len(cmd.get_outputs()) == 3 - pkgdest = os.path.join(destination, "pkg") - files = os.listdir(pkgdest) - pycache_dir = os.path.join(pkgdest, "__pycache__") - assert "__init__.py" in files - assert "README.txt" in files - if sys.dont_write_bytecode: - assert not os.path.exists(pycache_dir) - else: - pyc_files = os.listdir(pycache_dir) - assert f"__init__.{sys.implementation.cache_tag}.pyc" in pyc_files - - def test_empty_package_dir(self): - # See bugs #1668596/#1720897 - sources = self.mkdtemp() - jaraco.path.build({'__init__.py': '', 'doc': {'testfile': ''}}, sources) - - os.chdir(sources) - dist = Distribution({ - "packages": ["pkg"], - "package_dir": {"pkg": ""}, - "package_data": {"pkg": ["doc/*"]}, - }) - # script_name need not exist, it just need to be initialized - dist.script_name = os.path.join(sources, "setup.py") - dist.script_args = ["build"] - dist.parse_command_line() - - try: - dist.run_commands() - except DistutilsFileError: - self.fail("failed package_data test when package_dir is ''") - - @pytest.mark.skipif('sys.dont_write_bytecode') - def test_byte_compile(self): - project_dir, dist = self.create_dist(py_modules=['boiledeggs']) - os.chdir(project_dir) - self.write_file('boiledeggs.py', 'import antigravity') - cmd = build_py(dist) - cmd.compile = True - cmd.build_lib = 'here' - cmd.finalize_options() - cmd.run() - - found = os.listdir(cmd.build_lib) - assert sorted(found) == ['__pycache__', 'boiledeggs.py'] - found = os.listdir(os.path.join(cmd.build_lib, '__pycache__')) - assert found == [f'boiledeggs.{sys.implementation.cache_tag}.pyc'] - - @pytest.mark.skipif('sys.dont_write_bytecode') - def test_byte_compile_optimized(self): - project_dir, dist = self.create_dist(py_modules=['boiledeggs']) - os.chdir(project_dir) - self.write_file('boiledeggs.py', 'import antigravity') - cmd = build_py(dist) - cmd.compile = False - cmd.optimize = 1 - cmd.build_lib = 'here' - cmd.finalize_options() - cmd.run() - - found = os.listdir(cmd.build_lib) - assert sorted(found) == ['__pycache__', 'boiledeggs.py'] - found = os.listdir(os.path.join(cmd.build_lib, '__pycache__')) - expect = f'boiledeggs.{sys.implementation.cache_tag}.opt-1.pyc' - assert sorted(found) == [expect] - - def test_dir_in_package_data(self): - """ - A directory in package_data should not be added to the filelist. - """ - # See bug 19286 - sources = self.mkdtemp() - jaraco.path.build( - { - 'pkg': { - '__init__.py': '', - 'doc': { - 'testfile': '', - # create a directory that could be incorrectly detected as a file - 'otherdir': {}, - }, - } - }, - sources, - ) - - os.chdir(sources) - dist = Distribution({"packages": ["pkg"], "package_data": {"pkg": ["doc/*"]}}) - # script_name need not exist, it just need to be initialized - dist.script_name = os.path.join(sources, "setup.py") - dist.script_args = ["build"] - dist.parse_command_line() - - try: - dist.run_commands() - except DistutilsFileError: - self.fail("failed package_data when data dir includes a dir") - - def test_dont_write_bytecode(self, caplog): - # makes sure byte_compile is not used - dist = self.create_dist()[1] - cmd = build_py(dist) - cmd.compile = True - cmd.optimize = 1 - - old_dont_write_bytecode = sys.dont_write_bytecode - sys.dont_write_bytecode = True - try: - cmd.byte_compile([]) - finally: - sys.dont_write_bytecode = old_dont_write_bytecode - - assert 'byte-compiling is disabled' in caplog.records[0].message - - def test_namespace_package_does_not_warn(self, caplog): - """ - Originally distutils implementation did not account for PEP 420 - and included warns for package directories that did not contain - ``__init__.py`` files. - After the acceptance of PEP 420, these warnings don't make more sense - so we want to ensure there are not displayed to not confuse the users. - """ - # Create a fake project structure with a package namespace: - tmp = self.mkdtemp() - jaraco.path.build({'ns': {'pkg': {'module.py': ''}}}, tmp) - os.chdir(tmp) - - # Configure the package: - attrs = { - "name": "ns.pkg", - "packages": ["ns", "ns.pkg"], - "script_name": "setup.py", - } - dist = Distribution(attrs) - - # Run code paths that would trigger the trap: - cmd = dist.get_command_obj("build_py") - cmd.finalize_options() - modules = cmd.find_all_modules() - assert len(modules) == 1 - module_path = modules[0][-1] - assert module_path.replace(os.sep, "/") == "ns/pkg/module.py" - - cmd.run() - - assert not any( - "package init file" in msg and "not found" in msg for msg in caplog.messages - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_scripts.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_scripts.py deleted file mode 100644 index 3582f69..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_build_scripts.py +++ /dev/null @@ -1,96 +0,0 @@ -"""Tests for distutils.command.build_scripts.""" - -import os -import textwrap -from distutils import sysconfig -from distutils.command.build_scripts import build_scripts -from distutils.core import Distribution -from distutils.tests import support - -import jaraco.path - - -class TestBuildScripts(support.TempdirManager): - def test_default_settings(self): - cmd = self.get_build_scripts_cmd("/foo/bar", []) - assert not cmd.force - assert cmd.build_dir is None - - cmd.finalize_options() - - assert cmd.force - assert cmd.build_dir == "/foo/bar" - - def test_build(self): - source = self.mkdtemp() - target = self.mkdtemp() - expected = self.write_sample_scripts(source) - - cmd = self.get_build_scripts_cmd( - target, [os.path.join(source, fn) for fn in expected] - ) - cmd.finalize_options() - cmd.run() - - built = os.listdir(target) - for name in expected: - assert name in built - - def get_build_scripts_cmd(self, target, scripts): - import sys - - dist = Distribution() - dist.scripts = scripts - dist.command_obj["build"] = support.DummyCommand( - build_scripts=target, force=True, executable=sys.executable - ) - return build_scripts(dist) - - @staticmethod - def write_sample_scripts(dir): - spec = { - 'script1.py': textwrap.dedent(""" - #! /usr/bin/env python2.3 - # bogus script w/ Python sh-bang - pass - """).lstrip(), - 'script2.py': textwrap.dedent(""" - #!/usr/bin/python - # bogus script w/ Python sh-bang - pass - """).lstrip(), - 'shell.sh': textwrap.dedent(""" - #!/bin/sh - # bogus shell script w/ sh-bang - exit 0 - """).lstrip(), - } - jaraco.path.build(spec, dir) - return list(spec) - - def test_version_int(self): - source = self.mkdtemp() - target = self.mkdtemp() - expected = self.write_sample_scripts(source) - - cmd = self.get_build_scripts_cmd( - target, [os.path.join(source, fn) for fn in expected] - ) - cmd.finalize_options() - - # https://bugs.python.org/issue4524 - # - # On linux-g++-32 with command line `./configure --enable-ipv6 - # --with-suffix=3`, python is compiled okay but the build scripts - # failed when writing the name of the executable - old = sysconfig.get_config_vars().get('VERSION') - sysconfig._config_vars['VERSION'] = 4 - try: - cmd.run() - finally: - if old is not None: - sysconfig._config_vars['VERSION'] = old - - built = os.listdir(target) - for name in expected: - assert name in built diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_check.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_check.py deleted file mode 100644 index b672b1f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_check.py +++ /dev/null @@ -1,194 +0,0 @@ -"""Tests for distutils.command.check.""" - -import os -import textwrap -from distutils.command.check import check -from distutils.errors import DistutilsSetupError -from distutils.tests import support - -import pytest - -try: - import pygments -except ImportError: - pygments = None - - -HERE = os.path.dirname(__file__) - - -@support.combine_markers -class TestCheck(support.TempdirManager): - def _run(self, metadata=None, cwd=None, **options): - if metadata is None: - metadata = {} - if cwd is not None: - old_dir = os.getcwd() - os.chdir(cwd) - pkg_info, dist = self.create_dist(**metadata) - cmd = check(dist) - cmd.initialize_options() - for name, value in options.items(): - setattr(cmd, name, value) - cmd.ensure_finalized() - cmd.run() - if cwd is not None: - os.chdir(old_dir) - return cmd - - def test_check_metadata(self): - # let's run the command with no metadata at all - # by default, check is checking the metadata - # should have some warnings - cmd = self._run() - assert cmd._warnings == 1 - - # now let's add the required fields - # and run it again, to make sure we don't get - # any warning anymore - metadata = { - 'url': 'xxx', - 'author': 'xxx', - 'author_email': 'xxx', - 'name': 'xxx', - 'version': 'xxx', - } - cmd = self._run(metadata) - assert cmd._warnings == 0 - - # now with the strict mode, we should - # get an error if there are missing metadata - with pytest.raises(DistutilsSetupError): - self._run({}, **{'strict': 1}) - - # and of course, no error when all metadata are present - cmd = self._run(metadata, strict=True) - assert cmd._warnings == 0 - - # now a test with non-ASCII characters - metadata = { - 'url': 'xxx', - 'author': '\u00c9ric', - 'author_email': 'xxx', - 'name': 'xxx', - 'version': 'xxx', - 'description': 'Something about esszet \u00df', - 'long_description': 'More things about esszet \u00df', - } - cmd = self._run(metadata) - assert cmd._warnings == 0 - - def test_check_author_maintainer(self): - for kind in ("author", "maintainer"): - # ensure no warning when author_email or maintainer_email is given - # (the spec allows these fields to take the form "Name ") - metadata = { - 'url': 'xxx', - kind + '_email': 'Name ', - 'name': 'xxx', - 'version': 'xxx', - } - cmd = self._run(metadata) - assert cmd._warnings == 0 - - # the check should not warn if only email is given - metadata[kind + '_email'] = 'name@email.com' - cmd = self._run(metadata) - assert cmd._warnings == 0 - - # the check should not warn if only the name is given - metadata[kind] = "Name" - del metadata[kind + '_email'] - cmd = self._run(metadata) - assert cmd._warnings == 0 - - def test_check_document(self): - pytest.importorskip('docutils') - pkg_info, dist = self.create_dist() - cmd = check(dist) - - # let's see if it detects broken rest - broken_rest = 'title\n===\n\ntest' - msgs = cmd._check_rst_data(broken_rest) - assert len(msgs) == 1 - - # and non-broken rest - rest = 'title\n=====\n\ntest' - msgs = cmd._check_rst_data(rest) - assert len(msgs) == 0 - - def test_check_restructuredtext(self): - pytest.importorskip('docutils') - # let's see if it detects broken rest in long_description - broken_rest = 'title\n===\n\ntest' - pkg_info, dist = self.create_dist(long_description=broken_rest) - cmd = check(dist) - cmd.check_restructuredtext() - assert cmd._warnings == 1 - - # let's see if we have an error with strict=True - metadata = { - 'url': 'xxx', - 'author': 'xxx', - 'author_email': 'xxx', - 'name': 'xxx', - 'version': 'xxx', - 'long_description': broken_rest, - } - with pytest.raises(DistutilsSetupError): - self._run(metadata, **{'strict': 1, 'restructuredtext': 1}) - - # and non-broken rest, including a non-ASCII character to test #12114 - metadata['long_description'] = 'title\n=====\n\ntest \u00df' - cmd = self._run(metadata, strict=True, restructuredtext=True) - assert cmd._warnings == 0 - - # check that includes work to test #31292 - metadata['long_description'] = 'title\n=====\n\n.. include:: includetest.rst' - cmd = self._run(metadata, cwd=HERE, strict=True, restructuredtext=True) - assert cmd._warnings == 0 - - def test_check_restructuredtext_with_syntax_highlight(self): - pytest.importorskip('docutils') - # Don't fail if there is a `code` or `code-block` directive - - example_rst_docs = [ - textwrap.dedent( - """\ - Here's some code: - - .. code:: python - - def foo(): - pass - """ - ), - textwrap.dedent( - """\ - Here's some code: - - .. code-block:: python - - def foo(): - pass - """ - ), - ] - - for rest_with_code in example_rst_docs: - pkg_info, dist = self.create_dist(long_description=rest_with_code) - cmd = check(dist) - cmd.check_restructuredtext() - msgs = cmd._check_rst_data(rest_with_code) - if pygments is not None: - assert len(msgs) == 0 - else: - assert len(msgs) == 1 - assert ( - str(msgs[0][1]) - == 'Cannot analyze code. Pygments package not found.' - ) - - def test_check_all(self): - with pytest.raises(DistutilsSetupError): - self._run({}, **{'strict': 1, 'restructuredtext': 1}) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_clean.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_clean.py deleted file mode 100644 index cc78f30..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_clean.py +++ /dev/null @@ -1,45 +0,0 @@ -"""Tests for distutils.command.clean.""" - -import os -from distutils.command.clean import clean -from distutils.tests import support - - -class TestClean(support.TempdirManager): - def test_simple_run(self): - pkg_dir, dist = self.create_dist() - cmd = clean(dist) - - # let's add some elements clean should remove - dirs = [ - (d, os.path.join(pkg_dir, d)) - for d in ( - 'build_temp', - 'build_lib', - 'bdist_base', - 'build_scripts', - 'build_base', - ) - ] - - for name, path in dirs: - os.mkdir(path) - setattr(cmd, name, path) - if name == 'build_base': - continue - for f in ('one', 'two', 'three'): - self.write_file(os.path.join(path, f)) - - # let's run the command - cmd.all = 1 - cmd.ensure_finalized() - cmd.run() - - # make sure the files where removed - for _name, path in dirs: - assert not os.path.exists(path), f'{path} was not removed' - - # let's run the command again (should spit warnings but succeed) - cmd.all = 1 - cmd.ensure_finalized() - cmd.run() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_cmd.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_cmd.py deleted file mode 100644 index 76e8f59..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_cmd.py +++ /dev/null @@ -1,107 +0,0 @@ -"""Tests for distutils.cmd.""" - -import os -from distutils import debug -from distutils.cmd import Command -from distutils.dist import Distribution -from distutils.errors import DistutilsOptionError - -import pytest - - -class MyCmd(Command): - def initialize_options(self): - pass - - -@pytest.fixture -def cmd(request): - return MyCmd(Distribution()) - - -class TestCommand: - def test_ensure_string_list(self, cmd): - cmd.not_string_list = ['one', 2, 'three'] - cmd.yes_string_list = ['one', 'two', 'three'] - cmd.not_string_list2 = object() - cmd.yes_string_list2 = 'ok' - cmd.ensure_string_list('yes_string_list') - cmd.ensure_string_list('yes_string_list2') - - with pytest.raises(DistutilsOptionError): - cmd.ensure_string_list('not_string_list') - - with pytest.raises(DistutilsOptionError): - cmd.ensure_string_list('not_string_list2') - - cmd.option1 = 'ok,dok' - cmd.ensure_string_list('option1') - assert cmd.option1 == ['ok', 'dok'] - - cmd.option2 = ['xxx', 'www'] - cmd.ensure_string_list('option2') - - cmd.option3 = ['ok', 2] - with pytest.raises(DistutilsOptionError): - cmd.ensure_string_list('option3') - - def test_make_file(self, cmd): - # making sure it raises when infiles is not a string or a list/tuple - with pytest.raises(TypeError): - cmd.make_file(infiles=True, outfile='', func='func', args=()) - - # making sure execute gets called properly - def _execute(func, args, exec_msg, level): - assert exec_msg == 'generating out from in' - - cmd.force = True - cmd.execute = _execute - cmd.make_file(infiles='in', outfile='out', func='func', args=()) - - def test_dump_options(self, cmd): - msgs = [] - - def _announce(msg, level): - msgs.append(msg) - - cmd.announce = _announce - cmd.option1 = 1 - cmd.option2 = 1 - cmd.user_options = [('option1', '', ''), ('option2', '', '')] - cmd.dump_options() - - wanted = ["command options for 'MyCmd':", ' option1 = 1', ' option2 = 1'] - assert msgs == wanted - - def test_ensure_string(self, cmd): - cmd.option1 = 'ok' - cmd.ensure_string('option1') - - cmd.option2 = None - cmd.ensure_string('option2', 'xxx') - assert hasattr(cmd, 'option2') - - cmd.option3 = 1 - with pytest.raises(DistutilsOptionError): - cmd.ensure_string('option3') - - def test_ensure_filename(self, cmd): - cmd.option1 = __file__ - cmd.ensure_filename('option1') - cmd.option2 = 'xxx' - with pytest.raises(DistutilsOptionError): - cmd.ensure_filename('option2') - - def test_ensure_dirname(self, cmd): - cmd.option1 = os.path.dirname(__file__) or os.curdir - cmd.ensure_dirname('option1') - cmd.option2 = 'xxx' - with pytest.raises(DistutilsOptionError): - cmd.ensure_dirname('option2') - - def test_debug_print(self, cmd, capsys, monkeypatch): - cmd.debug_print('xxx') - assert capsys.readouterr().out == '' - monkeypatch.setattr(debug, 'DEBUG', True) - cmd.debug_print('xxx') - assert capsys.readouterr().out == 'xxx\n' diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_config_cmd.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_config_cmd.py deleted file mode 100644 index ebee2ef..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_config_cmd.py +++ /dev/null @@ -1,87 +0,0 @@ -"""Tests for distutils.command.config.""" - -import os -import sys -from distutils._log import log -from distutils.command.config import config, dump_file -from distutils.tests import missing_compiler_executable, support - -import more_itertools -import path -import pytest - - -@pytest.fixture(autouse=True) -def info_log(request, monkeypatch): - self = request.instance - self._logs = [] - monkeypatch.setattr(log, 'info', self._info) - - -@support.combine_markers -class TestConfig(support.TempdirManager): - def _info(self, msg, *args): - for line in msg.splitlines(): - self._logs.append(line) - - def test_dump_file(self): - this_file = path.Path(__file__).with_suffix('.py') - with this_file.open(encoding='utf-8') as f: - numlines = more_itertools.ilen(f) - - dump_file(this_file, 'I am the header') - assert len(self._logs) == numlines + 1 - - @pytest.mark.skipif('platform.system() == "Windows"') - def test_search_cpp(self): - cmd = missing_compiler_executable(['preprocessor']) - if cmd is not None: - self.skipTest(f'The {cmd!r} command is not found') - pkg_dir, dist = self.create_dist() - cmd = config(dist) - cmd._check_compiler() - compiler = cmd.compiler - if sys.platform[:3] == "aix" and "xlc" in compiler.preprocessor[0].lower(): - self.skipTest( - 'xlc: The -E option overrides the -P, -o, and -qsyntaxonly options' - ) - - # simple pattern searches - match = cmd.search_cpp(pattern='xxx', body='/* xxx */') - assert match == 0 - - match = cmd.search_cpp(pattern='_configtest', body='/* xxx */') - assert match == 1 - - def test_finalize_options(self): - # finalize_options does a bit of transformation - # on options - pkg_dir, dist = self.create_dist() - cmd = config(dist) - cmd.include_dirs = f'one{os.pathsep}two' - cmd.libraries = 'one' - cmd.library_dirs = f'three{os.pathsep}four' - cmd.ensure_finalized() - - assert cmd.include_dirs == ['one', 'two'] - assert cmd.libraries == ['one'] - assert cmd.library_dirs == ['three', 'four'] - - def test_clean(self): - # _clean removes files - tmp_dir = self.mkdtemp() - f1 = os.path.join(tmp_dir, 'one') - f2 = os.path.join(tmp_dir, 'two') - - self.write_file(f1, 'xxx') - self.write_file(f2, 'xxx') - - for f in (f1, f2): - assert os.path.exists(f) - - pkg_dir, dist = self.create_dist() - cmd = config(dist) - cmd._clean(f1, f2) - - for f in (f1, f2): - assert not os.path.exists(f) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_core.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_core.py deleted file mode 100644 index bad3fb7..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_core.py +++ /dev/null @@ -1,130 +0,0 @@ -"""Tests for distutils.core.""" - -import distutils.core -import io -import os -import sys -from distutils.dist import Distribution - -import pytest - -# setup script that uses __file__ -setup_using___file__ = """\ - -__file__ - -from distutils.core import setup -setup() -""" - -setup_prints_cwd = """\ - -import os -print(os.getcwd()) - -from distutils.core import setup -setup() -""" - -setup_does_nothing = """\ -from distutils.core import setup -setup() -""" - - -setup_defines_subclass = """\ -from distutils.core import setup -from distutils.command.install import install as _install - -class install(_install): - sub_commands = _install.sub_commands + ['cmd'] - -setup(cmdclass={'install': install}) -""" - -setup_within_if_main = """\ -from distutils.core import setup - -def main(): - return setup(name="setup_within_if_main") - -if __name__ == "__main__": - main() -""" - - -@pytest.fixture(autouse=True) -def save_stdout(monkeypatch): - monkeypatch.setattr(sys, 'stdout', sys.stdout) - - -@pytest.fixture -def temp_file(tmp_path): - return tmp_path / 'file' - - -@pytest.mark.usefixtures('save_env') -@pytest.mark.usefixtures('save_argv') -class TestCore: - def test_run_setup_provides_file(self, temp_file): - # Make sure the script can use __file__; if that's missing, the test - # setup.py script will raise NameError. - temp_file.write_text(setup_using___file__, encoding='utf-8') - distutils.core.run_setup(temp_file) - - def test_run_setup_preserves_sys_argv(self, temp_file): - # Make sure run_setup does not clobber sys.argv - argv_copy = sys.argv.copy() - temp_file.write_text(setup_does_nothing, encoding='utf-8') - distutils.core.run_setup(temp_file) - assert sys.argv == argv_copy - - def test_run_setup_defines_subclass(self, temp_file): - # Make sure the script can use __file__; if that's missing, the test - # setup.py script will raise NameError. - temp_file.write_text(setup_defines_subclass, encoding='utf-8') - dist = distutils.core.run_setup(temp_file) - install = dist.get_command_obj('install') - assert 'cmd' in install.sub_commands - - def test_run_setup_uses_current_dir(self, tmp_path): - """ - Test that the setup script is run with the current directory - as its own current directory. - """ - sys.stdout = io.StringIO() - cwd = os.getcwd() - - # Create a directory and write the setup.py file there: - setup_py = tmp_path / 'setup.py' - setup_py.write_text(setup_prints_cwd, encoding='utf-8') - distutils.core.run_setup(setup_py) - - output = sys.stdout.getvalue() - if output.endswith("\n"): - output = output[:-1] - assert cwd == output - - def test_run_setup_within_if_main(self, temp_file): - temp_file.write_text(setup_within_if_main, encoding='utf-8') - dist = distutils.core.run_setup(temp_file, stop_after="config") - assert isinstance(dist, Distribution) - assert dist.get_name() == "setup_within_if_main" - - def test_run_commands(self, temp_file): - sys.argv = ['setup.py', 'build'] - temp_file.write_text(setup_within_if_main, encoding='utf-8') - dist = distutils.core.run_setup(temp_file, stop_after="commandline") - assert 'build' not in dist.have_run - distutils.core.run_commands(dist) - assert 'build' in dist.have_run - - def test_debug_mode(self, capsys, monkeypatch): - # this covers the code called when DEBUG is set - sys.argv = ['setup.py', '--name'] - distutils.core.setup(name='bar') - assert capsys.readouterr().out == 'bar\n' - monkeypatch.setattr(distutils.core, 'DEBUG', True) - distutils.core.setup(name='bar') - wanted = "options (after parsing config files):\n" - assert capsys.readouterr().out.startswith(wanted) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_dir_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_dir_util.py deleted file mode 100644 index 326cb34..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_dir_util.py +++ /dev/null @@ -1,139 +0,0 @@ -"""Tests for distutils.dir_util.""" - -import os -import pathlib -import stat -import sys -import unittest.mock as mock -from distutils import dir_util, errors -from distutils.dir_util import ( - copy_tree, - create_tree, - ensure_relative, - mkpath, - remove_tree, -) -from distutils.tests import support - -import jaraco.path -import path -import pytest - - -@pytest.fixture(autouse=True) -def stuff(request, monkeypatch, distutils_managed_tempdir): - self = request.instance - tmp_dir = self.mkdtemp() - self.root_target = os.path.join(tmp_dir, 'deep') - self.target = os.path.join(self.root_target, 'here') - self.target2 = os.path.join(tmp_dir, 'deep2') - - -class TestDirUtil(support.TempdirManager): - def test_mkpath_remove_tree_verbosity(self, caplog): - mkpath(self.target, verbose=False) - assert not caplog.records - remove_tree(self.root_target, verbose=False) - - mkpath(self.target, verbose=True) - wanted = [f'creating {self.target}'] - assert caplog.messages == wanted - caplog.clear() - - remove_tree(self.root_target, verbose=True) - wanted = [f"removing '{self.root_target}' (and everything under it)"] - assert caplog.messages == wanted - - @pytest.mark.skipif("platform.system() == 'Windows'") - def test_mkpath_with_custom_mode(self): - # Get and set the current umask value for testing mode bits. - umask = os.umask(0o002) - os.umask(umask) - mkpath(self.target, 0o700) - assert stat.S_IMODE(os.stat(self.target).st_mode) == 0o700 & ~umask - mkpath(self.target2, 0o555) - assert stat.S_IMODE(os.stat(self.target2).st_mode) == 0o555 & ~umask - - def test_create_tree_verbosity(self, caplog): - create_tree(self.root_target, ['one', 'two', 'three'], verbose=False) - assert caplog.messages == [] - remove_tree(self.root_target, verbose=False) - - wanted = [f'creating {self.root_target}'] - create_tree(self.root_target, ['one', 'two', 'three'], verbose=True) - assert caplog.messages == wanted - - remove_tree(self.root_target, verbose=False) - - def test_copy_tree_verbosity(self, caplog): - mkpath(self.target, verbose=False) - - copy_tree(self.target, self.target2, verbose=False) - assert caplog.messages == [] - - remove_tree(self.root_target, verbose=False) - - mkpath(self.target, verbose=False) - a_file = path.Path(self.target) / 'ok.txt' - jaraco.path.build({'ok.txt': 'some content'}, self.target) - - wanted = [f'copying {a_file} -> {self.target2}'] - copy_tree(self.target, self.target2, verbose=True) - assert caplog.messages == wanted - - remove_tree(self.root_target, verbose=False) - remove_tree(self.target2, verbose=False) - - def test_copy_tree_skips_nfs_temp_files(self): - mkpath(self.target, verbose=False) - - jaraco.path.build({'ok.txt': 'some content', '.nfs123abc': ''}, self.target) - - copy_tree(self.target, self.target2) - assert os.listdir(self.target2) == ['ok.txt'] - - remove_tree(self.root_target, verbose=False) - remove_tree(self.target2, verbose=False) - - def test_ensure_relative(self): - if os.sep == '/': - assert ensure_relative('/home/foo') == 'home/foo' - assert ensure_relative('some/path') == 'some/path' - else: # \\ - assert ensure_relative('c:\\home\\foo') == 'c:home\\foo' - assert ensure_relative('home\\foo') == 'home\\foo' - - def test_copy_tree_exception_in_listdir(self): - """ - An exception in listdir should raise a DistutilsFileError - """ - with ( - mock.patch("os.listdir", side_effect=OSError()), - pytest.raises(errors.DistutilsFileError), - ): - src = self.tempdirs[-1] - dir_util.copy_tree(src, None) - - def test_mkpath_exception_uncached(self, monkeypatch, tmp_path): - """ - Caching should not remember failed attempts. - - pypa/distutils#304 - """ - - class FailPath(pathlib.Path): - def mkdir(self, *args, **kwargs): - raise OSError("Failed to create directory") - - if sys.version_info < (3, 12): - _flavour = pathlib.Path()._flavour - - target = tmp_path / 'foodir' - - with pytest.raises(errors.DistutilsFileError): - mkpath(FailPath(target)) - - assert not target.exists() - - mkpath(target) - assert target.exists() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_dist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_dist.py deleted file mode 100644 index 2c5beeb..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_dist.py +++ /dev/null @@ -1,552 +0,0 @@ -"""Tests for distutils.dist.""" - -import email -import email.generator -import email.policy -import functools -import io -import os -import sys -import textwrap -import unittest.mock as mock -import warnings -from distutils.cmd import Command -from distutils.dist import Distribution, fix_help_options -from distutils.tests import support -from typing import ClassVar - -import jaraco.path -import pytest - -pydistutils_cfg = '.' * (os.name == 'posix') + 'pydistutils.cfg' - - -class test_dist(Command): - """Sample distutils extension command.""" - - user_options: ClassVar[list[tuple[str, str, str]]] = [ - ("sample-option=", "S", "help text"), - ] - - def initialize_options(self): - self.sample_option = None - - -class TestDistribution(Distribution): - """Distribution subclasses that avoids the default search for - configuration files. - - The ._config_files attribute must be set before - .parse_config_files() is called. - """ - - def find_config_files(self): - return self._config_files - - -@pytest.fixture -def clear_argv(): - del sys.argv[1:] - - -@support.combine_markers -@pytest.mark.usefixtures('save_env') -@pytest.mark.usefixtures('save_argv') -class TestDistributionBehavior(support.TempdirManager): - def create_distribution(self, configfiles=()): - d = TestDistribution() - d._config_files = configfiles - d.parse_config_files() - d.parse_command_line() - return d - - def test_command_packages_unspecified(self, clear_argv): - sys.argv.append("build") - d = self.create_distribution() - assert d.get_command_packages() == ["distutils.command"] - - def test_command_packages_cmdline(self, clear_argv): - from distutils.tests.test_dist import test_dist - - sys.argv.extend([ - "--command-packages", - "foo.bar,distutils.tests", - "test_dist", - "-Ssometext", - ]) - d = self.create_distribution() - # let's actually try to load our test command: - assert d.get_command_packages() == [ - "distutils.command", - "foo.bar", - "distutils.tests", - ] - cmd = d.get_command_obj("test_dist") - assert isinstance(cmd, test_dist) - assert cmd.sample_option == "sometext" - - @pytest.mark.skipif( - 'distutils' not in Distribution.parse_config_files.__module__, - reason='Cannot test when virtualenv has monkey-patched Distribution', - ) - def test_venv_install_options(self, tmp_path, clear_argv): - sys.argv.append("install") - file = str(tmp_path / 'file') - - fakepath = '/somedir' - - jaraco.path.build({ - file: f""" - [install] - install-base = {fakepath} - install-platbase = {fakepath} - install-lib = {fakepath} - install-platlib = {fakepath} - install-purelib = {fakepath} - install-headers = {fakepath} - install-scripts = {fakepath} - install-data = {fakepath} - prefix = {fakepath} - exec-prefix = {fakepath} - home = {fakepath} - user = {fakepath} - root = {fakepath} - """, - }) - - # Base case: Not in a Virtual Environment - with mock.patch.multiple(sys, prefix='/a', base_prefix='/a'): - d = self.create_distribution([file]) - - option_tuple = (file, fakepath) - - result_dict = { - 'install_base': option_tuple, - 'install_platbase': option_tuple, - 'install_lib': option_tuple, - 'install_platlib': option_tuple, - 'install_purelib': option_tuple, - 'install_headers': option_tuple, - 'install_scripts': option_tuple, - 'install_data': option_tuple, - 'prefix': option_tuple, - 'exec_prefix': option_tuple, - 'home': option_tuple, - 'user': option_tuple, - 'root': option_tuple, - } - - assert sorted(d.command_options.get('install').keys()) == sorted( - result_dict.keys() - ) - - for key, value in d.command_options.get('install').items(): - assert value == result_dict[key] - - # Test case: In a Virtual Environment - with mock.patch.multiple(sys, prefix='/a', base_prefix='/b'): - d = self.create_distribution([file]) - - for key in result_dict.keys(): - assert key not in d.command_options.get('install', {}) - - def test_command_packages_configfile(self, tmp_path, clear_argv): - sys.argv.append("build") - file = str(tmp_path / "file") - jaraco.path.build({ - file: """ - [global] - command_packages = foo.bar, splat - """, - }) - - d = self.create_distribution([file]) - assert d.get_command_packages() == ["distutils.command", "foo.bar", "splat"] - - # ensure command line overrides config: - sys.argv[1:] = ["--command-packages", "spork", "build"] - d = self.create_distribution([file]) - assert d.get_command_packages() == ["distutils.command", "spork"] - - # Setting --command-packages to '' should cause the default to - # be used even if a config file specified something else: - sys.argv[1:] = ["--command-packages", "", "build"] - d = self.create_distribution([file]) - assert d.get_command_packages() == ["distutils.command"] - - def test_empty_options(self, request): - # an empty options dictionary should not stay in the - # list of attributes - - # catching warnings - warns = [] - - def _warn(msg): - warns.append(msg) - - request.addfinalizer( - functools.partial(setattr, warnings, 'warn', warnings.warn) - ) - warnings.warn = _warn - dist = Distribution( - attrs={ - 'author': 'xxx', - 'name': 'xxx', - 'version': 'xxx', - 'url': 'xxxx', - 'options': {}, - } - ) - - assert len(warns) == 0 - assert 'options' not in dir(dist) - - def test_finalize_options(self): - attrs = {'keywords': 'one,two', 'platforms': 'one,two'} - - dist = Distribution(attrs=attrs) - dist.finalize_options() - - # finalize_option splits platforms and keywords - assert dist.metadata.platforms == ['one', 'two'] - assert dist.metadata.keywords == ['one', 'two'] - - attrs = {'keywords': 'foo bar', 'platforms': 'foo bar'} - dist = Distribution(attrs=attrs) - dist.finalize_options() - assert dist.metadata.platforms == ['foo bar'] - assert dist.metadata.keywords == ['foo bar'] - - def test_get_command_packages(self): - dist = Distribution() - assert dist.command_packages is None - cmds = dist.get_command_packages() - assert cmds == ['distutils.command'] - assert dist.command_packages == ['distutils.command'] - - dist.command_packages = 'one,two' - cmds = dist.get_command_packages() - assert cmds == ['distutils.command', 'one', 'two'] - - def test_announce(self): - # make sure the level is known - dist = Distribution() - with pytest.raises(TypeError): - dist.announce('ok', level='ok2') - - def test_find_config_files_disable(self, temp_home): - # Ticket #1180: Allow user to disable their home config file. - jaraco.path.build({pydistutils_cfg: '[distutils]\n'}, temp_home) - - d = Distribution() - all_files = d.find_config_files() - - d = Distribution(attrs={'script_args': ['--no-user-cfg']}) - files = d.find_config_files() - - # make sure --no-user-cfg disables the user cfg file - assert len(all_files) - 1 == len(files) - - def test_script_args_list_coercion(self): - d = Distribution(attrs={'script_args': ('build', '--no-user-cfg')}) - - # make sure script_args is a list even if it started as a different iterable - assert d.script_args == ['build', '--no-user-cfg'] - - @pytest.mark.skipif( - 'platform.system() == "Windows"', - reason='Windows does not honor chmod 000', - ) - def test_find_config_files_permission_error(self, fake_home): - """ - Finding config files should not fail when directory is inaccessible. - """ - fake_home.joinpath(pydistutils_cfg).write_text('', encoding='utf-8') - fake_home.chmod(0o000) - Distribution().find_config_files() - - -@pytest.mark.usefixtures('save_env') -@pytest.mark.usefixtures('save_argv') -class TestMetadata(support.TempdirManager): - def format_metadata(self, dist): - sio = io.StringIO() - dist.metadata.write_pkg_file(sio) - return sio.getvalue() - - def test_simple_metadata(self): - attrs = {"name": "package", "version": "1.0"} - dist = Distribution(attrs) - meta = self.format_metadata(dist) - assert "Metadata-Version: 1.0" in meta - assert "provides:" not in meta.lower() - assert "requires:" not in meta.lower() - assert "obsoletes:" not in meta.lower() - - def test_provides(self): - attrs = { - "name": "package", - "version": "1.0", - "provides": ["package", "package.sub"], - } - dist = Distribution(attrs) - assert dist.metadata.get_provides() == ["package", "package.sub"] - assert dist.get_provides() == ["package", "package.sub"] - meta = self.format_metadata(dist) - assert "Metadata-Version: 1.1" in meta - assert "requires:" not in meta.lower() - assert "obsoletes:" not in meta.lower() - - def test_provides_illegal(self): - with pytest.raises(ValueError): - Distribution( - {"name": "package", "version": "1.0", "provides": ["my.pkg (splat)"]}, - ) - - def test_requires(self): - attrs = { - "name": "package", - "version": "1.0", - "requires": ["other", "another (==1.0)"], - } - dist = Distribution(attrs) - assert dist.metadata.get_requires() == ["other", "another (==1.0)"] - assert dist.get_requires() == ["other", "another (==1.0)"] - meta = self.format_metadata(dist) - assert "Metadata-Version: 1.1" in meta - assert "provides:" not in meta.lower() - assert "Requires: other" in meta - assert "Requires: another (==1.0)" in meta - assert "obsoletes:" not in meta.lower() - - def test_requires_illegal(self): - with pytest.raises(ValueError): - Distribution( - {"name": "package", "version": "1.0", "requires": ["my.pkg (splat)"]}, - ) - - def test_requires_to_list(self): - attrs = {"name": "package", "requires": iter(["other"])} - dist = Distribution(attrs) - assert isinstance(dist.metadata.requires, list) - - def test_obsoletes(self): - attrs = { - "name": "package", - "version": "1.0", - "obsoletes": ["other", "another (<1.0)"], - } - dist = Distribution(attrs) - assert dist.metadata.get_obsoletes() == ["other", "another (<1.0)"] - assert dist.get_obsoletes() == ["other", "another (<1.0)"] - meta = self.format_metadata(dist) - assert "Metadata-Version: 1.1" in meta - assert "provides:" not in meta.lower() - assert "requires:" not in meta.lower() - assert "Obsoletes: other" in meta - assert "Obsoletes: another (<1.0)" in meta - - def test_obsoletes_illegal(self): - with pytest.raises(ValueError): - Distribution( - {"name": "package", "version": "1.0", "obsoletes": ["my.pkg (splat)"]}, - ) - - def test_obsoletes_to_list(self): - attrs = {"name": "package", "obsoletes": iter(["other"])} - dist = Distribution(attrs) - assert isinstance(dist.metadata.obsoletes, list) - - def test_classifier(self): - attrs = { - 'name': 'Boa', - 'version': '3.0', - 'classifiers': ['Programming Language :: Python :: 3'], - } - dist = Distribution(attrs) - assert dist.get_classifiers() == ['Programming Language :: Python :: 3'] - meta = self.format_metadata(dist) - assert 'Metadata-Version: 1.1' in meta - - def test_classifier_invalid_type(self, caplog): - attrs = { - 'name': 'Boa', - 'version': '3.0', - 'classifiers': ('Programming Language :: Python :: 3',), - } - d = Distribution(attrs) - # should have warning about passing a non-list - assert 'should be a list' in caplog.messages[0] - # should be converted to a list - assert isinstance(d.metadata.classifiers, list) - assert d.metadata.classifiers == list(attrs['classifiers']) - - def test_keywords(self): - attrs = { - 'name': 'Monty', - 'version': '1.0', - 'keywords': ['spam', 'eggs', 'life of brian'], - } - dist = Distribution(attrs) - assert dist.get_keywords() == ['spam', 'eggs', 'life of brian'] - - def test_keywords_invalid_type(self, caplog): - attrs = { - 'name': 'Monty', - 'version': '1.0', - 'keywords': ('spam', 'eggs', 'life of brian'), - } - d = Distribution(attrs) - # should have warning about passing a non-list - assert 'should be a list' in caplog.messages[0] - # should be converted to a list - assert isinstance(d.metadata.keywords, list) - assert d.metadata.keywords == list(attrs['keywords']) - - def test_platforms(self): - attrs = { - 'name': 'Monty', - 'version': '1.0', - 'platforms': ['GNU/Linux', 'Some Evil Platform'], - } - dist = Distribution(attrs) - assert dist.get_platforms() == ['GNU/Linux', 'Some Evil Platform'] - - def test_platforms_invalid_types(self, caplog): - attrs = { - 'name': 'Monty', - 'version': '1.0', - 'platforms': ('GNU/Linux', 'Some Evil Platform'), - } - d = Distribution(attrs) - # should have warning about passing a non-list - assert 'should be a list' in caplog.messages[0] - # should be converted to a list - assert isinstance(d.metadata.platforms, list) - assert d.metadata.platforms == list(attrs['platforms']) - - def test_download_url(self): - attrs = { - 'name': 'Boa', - 'version': '3.0', - 'download_url': 'http://example.org/boa', - } - dist = Distribution(attrs) - meta = self.format_metadata(dist) - assert 'Metadata-Version: 1.1' in meta - - def test_long_description(self): - long_desc = textwrap.dedent( - """\ - example:: - We start here - and continue here - and end here.""" - ) - attrs = {"name": "package", "version": "1.0", "long_description": long_desc} - - dist = Distribution(attrs) - meta = self.format_metadata(dist) - meta = meta.replace('\n' + 8 * ' ', '\n') - assert long_desc in meta - - def test_custom_pydistutils(self, temp_home): - """ - pydistutils.cfg is found - """ - jaraco.path.build({pydistutils_cfg: ''}, temp_home) - config_path = temp_home / pydistutils_cfg - - assert str(config_path) in Distribution().find_config_files() - - def test_extra_pydistutils(self, monkeypatch, tmp_path): - jaraco.path.build({'overrides.cfg': ''}, tmp_path) - filename = tmp_path / 'overrides.cfg' - monkeypatch.setenv('DIST_EXTRA_CONFIG', str(filename)) - assert str(filename) in Distribution().find_config_files() - - def test_fix_help_options(self): - help_tuples = [('a', 'b', 'c', 'd'), (1, 2, 3, 4)] - fancy_options = fix_help_options(help_tuples) - assert fancy_options[0] == ('a', 'b', 'c') - assert fancy_options[1] == (1, 2, 3) - - def test_show_help(self, request, capsys): - # smoke test, just makes sure some help is displayed - dist = Distribution() - sys.argv = [] - dist.help = True - dist.script_name = 'setup.py' - dist.parse_command_line() - - output = [ - line for line in capsys.readouterr().out.split('\n') if line.strip() != '' - ] - assert output - - def test_read_metadata(self): - attrs = { - "name": "package", - "version": "1.0", - "long_description": "desc", - "description": "xxx", - "download_url": "http://example.com", - "keywords": ['one', 'two'], - "requires": ['foo'], - } - - dist = Distribution(attrs) - metadata = dist.metadata - - # write it then reloads it - PKG_INFO = io.StringIO() - metadata.write_pkg_file(PKG_INFO) - PKG_INFO.seek(0) - metadata.read_pkg_file(PKG_INFO) - - assert metadata.name == "package" - assert metadata.version == "1.0" - assert metadata.description == "xxx" - assert metadata.download_url == 'http://example.com' - assert metadata.keywords == ['one', 'two'] - assert metadata.platforms is None - assert metadata.obsoletes is None - assert metadata.requires == ['foo'] - - def test_round_trip_through_email_generator(self): - """ - In pypa/setuptools#4033, it was shown that once PKG-INFO is - re-generated using ``email.generator.Generator``, some control - characters might cause problems. - """ - # Given a PKG-INFO file ... - attrs = { - "name": "package", - "version": "1.0", - "long_description": "hello\x0b\nworld\n", - } - dist = Distribution(attrs) - metadata = dist.metadata - - with io.StringIO() as buffer: - metadata.write_pkg_file(buffer) - msg = buffer.getvalue() - - # ... when it is read and re-written using stdlib's email library, - orig = email.message_from_string(msg) - policy = email.policy.EmailPolicy( - utf8=True, - mangle_from_=False, - max_line_length=0, - ) - with io.StringIO() as buffer: - email.generator.Generator(buffer, policy=policy).flatten(orig) - - buffer.seek(0) - regen = email.message_from_file(buffer) - - # ... then it should be the same as the original - # (except for the specific line break characters) - orig_desc = set(orig["Description"].splitlines()) - regen_desc = set(regen["Description"].splitlines()) - assert regen_desc == orig_desc diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_extension.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_extension.py deleted file mode 100644 index 5e8e768..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_extension.py +++ /dev/null @@ -1,117 +0,0 @@ -"""Tests for distutils.extension.""" - -import os -import pathlib -import warnings -from distutils.extension import Extension, read_setup_file - -import pytest -from test.support.warnings_helper import check_warnings - - -class TestExtension: - def test_read_setup_file(self): - # trying to read a Setup file - # (sample extracted from the PyGame project) - setup = os.path.join(os.path.dirname(__file__), 'Setup.sample') - - exts = read_setup_file(setup) - names = [ext.name for ext in exts] - names.sort() - - # here are the extensions read_setup_file should have created - # out of the file - wanted = [ - '_arraysurfarray', - '_camera', - '_numericsndarray', - '_numericsurfarray', - 'base', - 'bufferproxy', - 'cdrom', - 'color', - 'constants', - 'display', - 'draw', - 'event', - 'fastevent', - 'font', - 'gfxdraw', - 'image', - 'imageext', - 'joystick', - 'key', - 'mask', - 'mixer', - 'mixer_music', - 'mouse', - 'movie', - 'overlay', - 'pixelarray', - 'pypm', - 'rect', - 'rwobject', - 'scrap', - 'surface', - 'surflock', - 'time', - 'transform', - ] - - assert names == wanted - - def test_extension_init(self): - # the first argument, which is the name, must be a string - with pytest.raises(TypeError): - Extension(1, []) - ext = Extension('name', []) - assert ext.name == 'name' - - # the second argument, which is the list of files, must - # be an iterable of strings or PathLike objects, and not a string - with pytest.raises(TypeError): - Extension('name', 'file') - with pytest.raises(TypeError): - Extension('name', ['file', 1]) - ext = Extension('name', ['file1', 'file2']) - assert ext.sources == ['file1', 'file2'] - ext = Extension('name', [pathlib.Path('file1'), pathlib.Path('file2')]) - assert ext.sources == ['file1', 'file2'] - - # any non-string iterable of strings or PathLike objects should work - ext = Extension('name', ('file1', 'file2')) # tuple - assert ext.sources == ['file1', 'file2'] - ext = Extension('name', {'file1', 'file2'}) # set - assert sorted(ext.sources) == ['file1', 'file2'] - ext = Extension('name', iter(['file1', 'file2'])) # iterator - assert ext.sources == ['file1', 'file2'] - ext = Extension('name', [pathlib.Path('file1'), 'file2']) # mixed types - assert ext.sources == ['file1', 'file2'] - - # others arguments have defaults - for attr in ( - 'include_dirs', - 'define_macros', - 'undef_macros', - 'library_dirs', - 'libraries', - 'runtime_library_dirs', - 'extra_objects', - 'extra_compile_args', - 'extra_link_args', - 'export_symbols', - 'swig_opts', - 'depends', - ): - assert getattr(ext, attr) == [] - - assert ext.language is None - assert ext.optional is None - - # if there are unknown keyword options, warn about them - with check_warnings() as w: - warnings.simplefilter('always') - ext = Extension('name', ['file1', 'file2'], chic=True) - - assert len(w.warnings) == 1 - assert str(w.warnings[0].message) == "Unknown Extension options: 'chic'" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_file_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_file_util.py deleted file mode 100644 index a75d4a0..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_file_util.py +++ /dev/null @@ -1,95 +0,0 @@ -"""Tests for distutils.file_util.""" - -import errno -import os -import unittest.mock as mock -from distutils.errors import DistutilsFileError -from distutils.file_util import copy_file, move_file - -import jaraco.path -import pytest - - -@pytest.fixture(autouse=True) -def stuff(request, tmp_path): - self = request.instance - self.source = tmp_path / 'f1' - self.target = tmp_path / 'f2' - self.target_dir = tmp_path / 'd1' - - -class TestFileUtil: - def test_move_file_verbosity(self, caplog): - jaraco.path.build({self.source: 'some content'}) - - move_file(self.source, self.target, verbose=False) - assert not caplog.messages - - # back to original state - move_file(self.target, self.source, verbose=False) - - move_file(self.source, self.target, verbose=True) - wanted = [f'moving {self.source} -> {self.target}'] - assert caplog.messages == wanted - - # back to original state - move_file(self.target, self.source, verbose=False) - - caplog.clear() - # now the target is a dir - os.mkdir(self.target_dir) - move_file(self.source, self.target_dir, verbose=True) - wanted = [f'moving {self.source} -> {self.target_dir}'] - assert caplog.messages == wanted - - def test_move_file_exception_unpacking_rename(self): - # see issue 22182 - with ( - mock.patch("os.rename", side_effect=OSError("wrong", 1)), - pytest.raises(DistutilsFileError), - ): - jaraco.path.build({self.source: 'spam eggs'}) - move_file(self.source, self.target, verbose=False) - - def test_move_file_exception_unpacking_unlink(self): - # see issue 22182 - with ( - mock.patch("os.rename", side_effect=OSError(errno.EXDEV, "wrong")), - mock.patch("os.unlink", side_effect=OSError("wrong", 1)), - pytest.raises(DistutilsFileError), - ): - jaraco.path.build({self.source: 'spam eggs'}) - move_file(self.source, self.target, verbose=False) - - def test_copy_file_hard_link(self): - jaraco.path.build({self.source: 'some content'}) - # Check first that copy_file() will not fall back on copying the file - # instead of creating the hard link. - try: - os.link(self.source, self.target) - except OSError as e: - self.skipTest(f'os.link: {e}') - else: - self.target.unlink() - st = os.stat(self.source) - copy_file(self.source, self.target, link='hard') - st2 = os.stat(self.source) - st3 = os.stat(self.target) - assert os.path.samestat(st, st2), (st, st2) - assert os.path.samestat(st2, st3), (st2, st3) - assert self.source.read_text(encoding='utf-8') == 'some content' - - def test_copy_file_hard_link_failure(self): - # If hard linking fails, copy_file() falls back on copying file - # (some special filesystems don't support hard linking even under - # Unix, see issue #8876). - jaraco.path.build({self.source: 'some content'}) - st = os.stat(self.source) - with mock.patch("os.link", side_effect=OSError(0, "linking unsupported")): - copy_file(self.source, self.target, link='hard') - st2 = os.stat(self.source) - st3 = os.stat(self.target) - assert os.path.samestat(st, st2), (st, st2) - assert not os.path.samestat(st2, st3), (st2, st3) - for fn in (self.source, self.target): - assert fn.read_text(encoding='utf-8') == 'some content' diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_filelist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_filelist.py deleted file mode 100644 index 130e6fb..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_filelist.py +++ /dev/null @@ -1,336 +0,0 @@ -"""Tests for distutils.filelist.""" - -import logging -import os -import re -from distutils import debug, filelist -from distutils.errors import DistutilsTemplateError -from distutils.filelist import FileList, glob_to_re, translate_pattern - -import jaraco.path -import pytest - -from .compat import py39 as os_helper - -MANIFEST_IN = """\ -include ok -include xo -exclude xo -include foo.tmp -include buildout.cfg -global-include *.x -global-include *.txt -global-exclude *.tmp -recursive-include f *.oo -recursive-exclude global *.x -graft dir -prune dir3 -""" - - -def make_local_path(s): - """Converts '/' in a string to os.sep""" - return s.replace('/', os.sep) - - -class TestFileList: - def assertNoWarnings(self, caplog): - warnings = [rec for rec in caplog.records if rec.levelno == logging.WARNING] - assert not warnings - caplog.clear() - - def assertWarnings(self, caplog): - warnings = [rec for rec in caplog.records if rec.levelno == logging.WARNING] - assert warnings - caplog.clear() - - def test_glob_to_re(self): - sep = os.sep - if os.sep == '\\': - sep = re.escape(os.sep) - - for glob, regex in ( - # simple cases - ('foo*', r'(?s:foo[^%(sep)s]*)\Z'), - ('foo?', r'(?s:foo[^%(sep)s])\Z'), - ('foo??', r'(?s:foo[^%(sep)s][^%(sep)s])\Z'), - # special cases - (r'foo\\*', r'(?s:foo\\\\[^%(sep)s]*)\Z'), - (r'foo\\\*', r'(?s:foo\\\\\\[^%(sep)s]*)\Z'), - ('foo????', r'(?s:foo[^%(sep)s][^%(sep)s][^%(sep)s][^%(sep)s])\Z'), - (r'foo\\??', r'(?s:foo\\\\[^%(sep)s][^%(sep)s])\Z'), - ): - regex = regex % {'sep': sep} - assert glob_to_re(glob) == regex - - def test_process_template_line(self): - # testing all MANIFEST.in template patterns - file_list = FileList() - mlp = make_local_path - - # simulated file list - file_list.allfiles = [ - 'foo.tmp', - 'ok', - 'xo', - 'four.txt', - 'buildout.cfg', - # filelist does not filter out VCS directories, - # it's sdist that does - mlp('.hg/last-message.txt'), - mlp('global/one.txt'), - mlp('global/two.txt'), - mlp('global/files.x'), - mlp('global/here.tmp'), - mlp('f/o/f.oo'), - mlp('dir/graft-one'), - mlp('dir/dir2/graft2'), - mlp('dir3/ok'), - mlp('dir3/sub/ok.txt'), - ] - - for line in MANIFEST_IN.split('\n'): - if line.strip() == '': - continue - file_list.process_template_line(line) - - wanted = [ - 'ok', - 'buildout.cfg', - 'four.txt', - mlp('.hg/last-message.txt'), - mlp('global/one.txt'), - mlp('global/two.txt'), - mlp('f/o/f.oo'), - mlp('dir/graft-one'), - mlp('dir/dir2/graft2'), - ] - - assert file_list.files == wanted - - def test_debug_print(self, capsys, monkeypatch): - file_list = FileList() - file_list.debug_print('xxx') - assert capsys.readouterr().out == '' - - monkeypatch.setattr(debug, 'DEBUG', True) - file_list.debug_print('xxx') - assert capsys.readouterr().out == 'xxx\n' - - def test_set_allfiles(self): - file_list = FileList() - files = ['a', 'b', 'c'] - file_list.set_allfiles(files) - assert file_list.allfiles == files - - def test_remove_duplicates(self): - file_list = FileList() - file_list.files = ['a', 'b', 'a', 'g', 'c', 'g'] - # files must be sorted beforehand (sdist does it) - file_list.sort() - file_list.remove_duplicates() - assert file_list.files == ['a', 'b', 'c', 'g'] - - def test_translate_pattern(self): - # not regex - assert hasattr(translate_pattern('a', anchor=True, is_regex=False), 'search') - - # is a regex - regex = re.compile('a') - assert translate_pattern(regex, anchor=True, is_regex=True) == regex - - # plain string flagged as regex - assert hasattr(translate_pattern('a', anchor=True, is_regex=True), 'search') - - # glob support - assert translate_pattern('*.py', anchor=True, is_regex=False).search( - 'filelist.py' - ) - - def test_exclude_pattern(self): - # return False if no match - file_list = FileList() - assert not file_list.exclude_pattern('*.py') - - # return True if files match - file_list = FileList() - file_list.files = ['a.py', 'b.py'] - assert file_list.exclude_pattern('*.py') - - # test excludes - file_list = FileList() - file_list.files = ['a.py', 'a.txt'] - file_list.exclude_pattern('*.py') - assert file_list.files == ['a.txt'] - - def test_include_pattern(self): - # return False if no match - file_list = FileList() - file_list.set_allfiles([]) - assert not file_list.include_pattern('*.py') - - # return True if files match - file_list = FileList() - file_list.set_allfiles(['a.py', 'b.txt']) - assert file_list.include_pattern('*.py') - - # test * matches all files - file_list = FileList() - assert file_list.allfiles is None - file_list.set_allfiles(['a.py', 'b.txt']) - file_list.include_pattern('*') - assert file_list.allfiles == ['a.py', 'b.txt'] - - def test_process_template(self, caplog): - mlp = make_local_path - # invalid lines - file_list = FileList() - for action in ( - 'include', - 'exclude', - 'global-include', - 'global-exclude', - 'recursive-include', - 'recursive-exclude', - 'graft', - 'prune', - 'blarg', - ): - with pytest.raises(DistutilsTemplateError): - file_list.process_template_line(action) - - # include - file_list = FileList() - file_list.set_allfiles(['a.py', 'b.txt', mlp('d/c.py')]) - - file_list.process_template_line('include *.py') - assert file_list.files == ['a.py'] - self.assertNoWarnings(caplog) - - file_list.process_template_line('include *.rb') - assert file_list.files == ['a.py'] - self.assertWarnings(caplog) - - # exclude - file_list = FileList() - file_list.files = ['a.py', 'b.txt', mlp('d/c.py')] - - file_list.process_template_line('exclude *.py') - assert file_list.files == ['b.txt', mlp('d/c.py')] - self.assertNoWarnings(caplog) - - file_list.process_template_line('exclude *.rb') - assert file_list.files == ['b.txt', mlp('d/c.py')] - self.assertWarnings(caplog) - - # global-include - file_list = FileList() - file_list.set_allfiles(['a.py', 'b.txt', mlp('d/c.py')]) - - file_list.process_template_line('global-include *.py') - assert file_list.files == ['a.py', mlp('d/c.py')] - self.assertNoWarnings(caplog) - - file_list.process_template_line('global-include *.rb') - assert file_list.files == ['a.py', mlp('d/c.py')] - self.assertWarnings(caplog) - - # global-exclude - file_list = FileList() - file_list.files = ['a.py', 'b.txt', mlp('d/c.py')] - - file_list.process_template_line('global-exclude *.py') - assert file_list.files == ['b.txt'] - self.assertNoWarnings(caplog) - - file_list.process_template_line('global-exclude *.rb') - assert file_list.files == ['b.txt'] - self.assertWarnings(caplog) - - # recursive-include - file_list = FileList() - file_list.set_allfiles(['a.py', mlp('d/b.py'), mlp('d/c.txt'), mlp('d/d/e.py')]) - - file_list.process_template_line('recursive-include d *.py') - assert file_list.files == [mlp('d/b.py'), mlp('d/d/e.py')] - self.assertNoWarnings(caplog) - - file_list.process_template_line('recursive-include e *.py') - assert file_list.files == [mlp('d/b.py'), mlp('d/d/e.py')] - self.assertWarnings(caplog) - - # recursive-exclude - file_list = FileList() - file_list.files = ['a.py', mlp('d/b.py'), mlp('d/c.txt'), mlp('d/d/e.py')] - - file_list.process_template_line('recursive-exclude d *.py') - assert file_list.files == ['a.py', mlp('d/c.txt')] - self.assertNoWarnings(caplog) - - file_list.process_template_line('recursive-exclude e *.py') - assert file_list.files == ['a.py', mlp('d/c.txt')] - self.assertWarnings(caplog) - - # graft - file_list = FileList() - file_list.set_allfiles(['a.py', mlp('d/b.py'), mlp('d/d/e.py'), mlp('f/f.py')]) - - file_list.process_template_line('graft d') - assert file_list.files == [mlp('d/b.py'), mlp('d/d/e.py')] - self.assertNoWarnings(caplog) - - file_list.process_template_line('graft e') - assert file_list.files == [mlp('d/b.py'), mlp('d/d/e.py')] - self.assertWarnings(caplog) - - # prune - file_list = FileList() - file_list.files = ['a.py', mlp('d/b.py'), mlp('d/d/e.py'), mlp('f/f.py')] - - file_list.process_template_line('prune d') - assert file_list.files == ['a.py', mlp('f/f.py')] - self.assertNoWarnings(caplog) - - file_list.process_template_line('prune e') - assert file_list.files == ['a.py', mlp('f/f.py')] - self.assertWarnings(caplog) - - -class TestFindAll: - @os_helper.skip_unless_symlink - def test_missing_symlink(self, temp_cwd): - os.symlink('foo', 'bar') - assert filelist.findall() == [] - - def test_basic_discovery(self, temp_cwd): - """ - When findall is called with no parameters or with - '.' as the parameter, the dot should be omitted from - the results. - """ - jaraco.path.build({'foo': {'file1.txt': ''}, 'bar': {'file2.txt': ''}}) - file1 = os.path.join('foo', 'file1.txt') - file2 = os.path.join('bar', 'file2.txt') - expected = [file2, file1] - assert sorted(filelist.findall()) == expected - - def test_non_local_discovery(self, tmp_path): - """ - When findall is called with another path, the full - path name should be returned. - """ - jaraco.path.build({'file1.txt': ''}, tmp_path) - expected = [str(tmp_path / 'file1.txt')] - assert filelist.findall(tmp_path) == expected - - @os_helper.skip_unless_symlink - def test_symlink_loop(self, tmp_path): - jaraco.path.build( - { - 'link-to-parent': jaraco.path.Symlink('.'), - 'somefile': '', - }, - tmp_path, - ) - files = filelist.findall(tmp_path) - assert len(files) == 1 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install.py deleted file mode 100644 index b3ffb2e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install.py +++ /dev/null @@ -1,245 +0,0 @@ -"""Tests for distutils.command.install.""" - -import logging -import os -import pathlib -import site -import sys -from distutils import sysconfig -from distutils.command import install as install_module -from distutils.command.build_ext import build_ext -from distutils.command.install import INSTALL_SCHEMES, install -from distutils.core import Distribution -from distutils.errors import DistutilsOptionError -from distutils.extension import Extension -from distutils.tests import missing_compiler_executable, support -from distutils.util import is_mingw - -import pytest - - -def _make_ext_name(modname): - return modname + sysconfig.get_config_var('EXT_SUFFIX') - - -@support.combine_markers -@pytest.mark.usefixtures('save_env') -class TestInstall( - support.TempdirManager, -): - @pytest.mark.xfail( - 'platform.system() == "Windows" and sys.version_info > (3, 11)', - reason="pypa/distutils#148", - ) - def test_home_installation_scheme(self): - # This ensure two things: - # - that --home generates the desired set of directory names - # - test --home is supported on all platforms - builddir = self.mkdtemp() - destination = os.path.join(builddir, "installation") - - dist = Distribution({"name": "foopkg"}) - # script_name need not exist, it just need to be initialized - dist.script_name = os.path.join(builddir, "setup.py") - dist.command_obj["build"] = support.DummyCommand( - build_base=builddir, - build_lib=os.path.join(builddir, "lib"), - ) - - cmd = install(dist) - cmd.home = destination - cmd.ensure_finalized() - - assert cmd.install_base == destination - assert cmd.install_platbase == destination - - def check_path(got, expected): - got = os.path.normpath(got) - expected = os.path.normpath(expected) - assert got == expected - - impl_name = sys.implementation.name.replace("cpython", "python") - libdir = os.path.join(destination, "lib", impl_name) - check_path(cmd.install_lib, libdir) - _platlibdir = getattr(sys, "platlibdir", "lib") - platlibdir = os.path.join(destination, _platlibdir, impl_name) - check_path(cmd.install_platlib, platlibdir) - check_path(cmd.install_purelib, libdir) - check_path( - cmd.install_headers, - os.path.join(destination, "include", impl_name, "foopkg"), - ) - check_path(cmd.install_scripts, os.path.join(destination, "bin")) - check_path(cmd.install_data, destination) - - def test_user_site(self, monkeypatch): - # test install with --user - # preparing the environment for the test - self.tmpdir = self.mkdtemp() - orig_site = site.USER_SITE - orig_base = site.USER_BASE - monkeypatch.setattr(site, 'USER_BASE', os.path.join(self.tmpdir, 'B')) - monkeypatch.setattr(site, 'USER_SITE', os.path.join(self.tmpdir, 'S')) - monkeypatch.setattr(install_module, 'USER_BASE', site.USER_BASE) - monkeypatch.setattr(install_module, 'USER_SITE', site.USER_SITE) - - def _expanduser(path): - if path.startswith('~'): - return os.path.normpath(self.tmpdir + path[1:]) - return path - - monkeypatch.setattr(os.path, 'expanduser', _expanduser) - - for key in ('nt_user', 'posix_user'): - assert key in INSTALL_SCHEMES - - dist = Distribution({'name': 'xx'}) - cmd = install(dist) - - # making sure the user option is there - options = [name for name, short, label in cmd.user_options] - assert 'user' in options - - # setting a value - cmd.user = True - - # user base and site shouldn't be created yet - assert not os.path.exists(site.USER_BASE) - assert not os.path.exists(site.USER_SITE) - - # let's run finalize - cmd.ensure_finalized() - - # now they should - assert os.path.exists(site.USER_BASE) - assert os.path.exists(site.USER_SITE) - - assert 'userbase' in cmd.config_vars - assert 'usersite' in cmd.config_vars - - actual_headers = os.path.relpath(cmd.install_headers, site.USER_BASE) - if os.name == 'nt' and not is_mingw(): - site_path = os.path.relpath(os.path.dirname(orig_site), orig_base) - include = os.path.join(site_path, 'Include') - else: - include = sysconfig.get_python_inc(0, '') - expect_headers = os.path.join(include, 'xx') - - assert os.path.normcase(actual_headers) == os.path.normcase(expect_headers) - - def test_handle_extra_path(self): - dist = Distribution({'name': 'xx', 'extra_path': 'path,dirs'}) - cmd = install(dist) - - # two elements - cmd.handle_extra_path() - assert cmd.extra_path == ['path', 'dirs'] - assert cmd.extra_dirs == 'dirs' - assert cmd.path_file == 'path' - - # one element - cmd.extra_path = ['path'] - cmd.handle_extra_path() - assert cmd.extra_path == ['path'] - assert cmd.extra_dirs == 'path' - assert cmd.path_file == 'path' - - # none - dist.extra_path = cmd.extra_path = None - cmd.handle_extra_path() - assert cmd.extra_path is None - assert cmd.extra_dirs == '' - assert cmd.path_file is None - - # three elements (no way !) - cmd.extra_path = 'path,dirs,again' - with pytest.raises(DistutilsOptionError): - cmd.handle_extra_path() - - def test_finalize_options(self): - dist = Distribution({'name': 'xx'}) - cmd = install(dist) - - # must supply either prefix/exec-prefix/home or - # install-base/install-platbase -- not both - cmd.prefix = 'prefix' - cmd.install_base = 'base' - with pytest.raises(DistutilsOptionError): - cmd.finalize_options() - - # must supply either home or prefix/exec-prefix -- not both - cmd.install_base = None - cmd.home = 'home' - with pytest.raises(DistutilsOptionError): - cmd.finalize_options() - - # can't combine user with prefix/exec_prefix/home or - # install_(plat)base - cmd.prefix = None - cmd.user = 'user' - with pytest.raises(DistutilsOptionError): - cmd.finalize_options() - - def test_record(self): - install_dir = self.mkdtemp() - project_dir, dist = self.create_dist(py_modules=['hello'], scripts=['sayhi']) - os.chdir(project_dir) - self.write_file('hello.py', "def main(): print('o hai')") - self.write_file('sayhi', 'from hello import main; main()') - - cmd = install(dist) - dist.command_obj['install'] = cmd - cmd.root = install_dir - cmd.record = os.path.join(project_dir, 'filelist') - cmd.ensure_finalized() - cmd.run() - - content = pathlib.Path(cmd.record).read_text(encoding='utf-8') - - found = [pathlib.Path(line).name for line in content.splitlines()] - expected = [ - 'hello.py', - f'hello.{sys.implementation.cache_tag}.pyc', - 'sayhi', - 'UNKNOWN-0.0.0-py{}.{}.egg-info'.format(*sys.version_info[:2]), - ] - assert found == expected - - def test_record_extensions(self): - cmd = missing_compiler_executable() - if cmd is not None: - pytest.skip(f'The {cmd!r} command is not found') - install_dir = self.mkdtemp() - project_dir, dist = self.create_dist( - ext_modules=[Extension('xx', ['xxmodule.c'])] - ) - os.chdir(project_dir) - support.copy_xxmodule_c(project_dir) - - buildextcmd = build_ext(dist) - support.fixup_build_ext(buildextcmd) - buildextcmd.ensure_finalized() - - cmd = install(dist) - dist.command_obj['install'] = cmd - dist.command_obj['build_ext'] = buildextcmd - cmd.root = install_dir - cmd.record = os.path.join(project_dir, 'filelist') - cmd.ensure_finalized() - cmd.run() - - content = pathlib.Path(cmd.record).read_text(encoding='utf-8') - - found = [pathlib.Path(line).name for line in content.splitlines()] - expected = [ - _make_ext_name('xx'), - 'UNKNOWN-0.0.0-py{}.{}.egg-info'.format(*sys.version_info[:2]), - ] - assert found == expected - - def test_debug_mode(self, caplog, monkeypatch): - # this covers the code called when DEBUG is set - monkeypatch.setattr(install_module, 'DEBUG', True) - caplog.set_level(logging.DEBUG) - self.test_record() - assert any(rec for rec in caplog.records if rec.levelno == logging.DEBUG) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_data.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_data.py deleted file mode 100644 index c800f86..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_data.py +++ /dev/null @@ -1,74 +0,0 @@ -"""Tests for distutils.command.install_data.""" - -import os -import pathlib -from distutils.command.install_data import install_data -from distutils.tests import support - -import pytest - - -@pytest.mark.usefixtures('save_env') -class TestInstallData( - support.TempdirManager, -): - def test_simple_run(self): - pkg_dir, dist = self.create_dist() - cmd = install_data(dist) - cmd.install_dir = inst = os.path.join(pkg_dir, 'inst') - - # data_files can contain - # - simple files - # - a Path object - # - a tuple with a path, and a list of file - one = os.path.join(pkg_dir, 'one') - self.write_file(one, 'xxx') - inst2 = os.path.join(pkg_dir, 'inst2') - two = os.path.join(pkg_dir, 'two') - self.write_file(two, 'xxx') - three = pathlib.Path(pkg_dir) / 'three' - self.write_file(three, 'xxx') - - cmd.data_files = [one, (inst2, [two]), three] - assert cmd.get_inputs() == [one, (inst2, [two]), three] - - # let's run the command - cmd.ensure_finalized() - cmd.run() - - # let's check the result - assert len(cmd.get_outputs()) == 3 - rthree = os.path.split(one)[-1] - assert os.path.exists(os.path.join(inst, rthree)) - rtwo = os.path.split(two)[-1] - assert os.path.exists(os.path.join(inst2, rtwo)) - rone = os.path.split(one)[-1] - assert os.path.exists(os.path.join(inst, rone)) - cmd.outfiles = [] - - # let's try with warn_dir one - cmd.warn_dir = True - cmd.ensure_finalized() - cmd.run() - - # let's check the result - assert len(cmd.get_outputs()) == 3 - assert os.path.exists(os.path.join(inst, rthree)) - assert os.path.exists(os.path.join(inst2, rtwo)) - assert os.path.exists(os.path.join(inst, rone)) - cmd.outfiles = [] - - # now using root and empty dir - cmd.root = os.path.join(pkg_dir, 'root') - inst5 = os.path.join(pkg_dir, 'inst5') - four = os.path.join(cmd.install_dir, 'four') - self.write_file(four, 'xx') - cmd.data_files = [one, (inst2, [two]), three, ('inst5', [four]), (inst5, [])] - cmd.ensure_finalized() - cmd.run() - - # let's check the result - assert len(cmd.get_outputs()) == 5 - assert os.path.exists(os.path.join(inst, rthree)) - assert os.path.exists(os.path.join(inst2, rtwo)) - assert os.path.exists(os.path.join(inst, rone)) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_headers.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_headers.py deleted file mode 100644 index 2c74f06..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_headers.py +++ /dev/null @@ -1,33 +0,0 @@ -"""Tests for distutils.command.install_headers.""" - -import os -from distutils.command.install_headers import install_headers -from distutils.tests import support - -import pytest - - -@pytest.mark.usefixtures('save_env') -class TestInstallHeaders( - support.TempdirManager, -): - def test_simple_run(self): - # we have two headers - header_list = self.mkdtemp() - header1 = os.path.join(header_list, 'header1') - header2 = os.path.join(header_list, 'header2') - self.write_file(header1) - self.write_file(header2) - headers = [header1, header2] - - pkg_dir, dist = self.create_dist(headers=headers) - cmd = install_headers(dist) - assert cmd.get_inputs() == headers - - # let's run the command - cmd.install_dir = os.path.join(pkg_dir, 'inst') - cmd.ensure_finalized() - cmd.run() - - # let's check the results - assert len(cmd.get_outputs()) == 2 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_lib.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_lib.py deleted file mode 100644 index f685a57..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_lib.py +++ /dev/null @@ -1,110 +0,0 @@ -"""Tests for distutils.command.install_data.""" - -import importlib.util -import os -import sys -from distutils.command.install_lib import install_lib -from distutils.errors import DistutilsOptionError -from distutils.extension import Extension -from distutils.tests import support - -import pytest - - -@support.combine_markers -@pytest.mark.usefixtures('save_env') -class TestInstallLib( - support.TempdirManager, -): - def test_finalize_options(self): - dist = self.create_dist()[1] - cmd = install_lib(dist) - - cmd.finalize_options() - assert cmd.compile == 1 - assert cmd.optimize == 0 - - # optimize must be 0, 1, or 2 - cmd.optimize = 'foo' - with pytest.raises(DistutilsOptionError): - cmd.finalize_options() - cmd.optimize = '4' - with pytest.raises(DistutilsOptionError): - cmd.finalize_options() - - cmd.optimize = '2' - cmd.finalize_options() - assert cmd.optimize == 2 - - @pytest.mark.skipif('sys.dont_write_bytecode') - def test_byte_compile(self): - project_dir, dist = self.create_dist() - os.chdir(project_dir) - cmd = install_lib(dist) - cmd.compile = cmd.optimize = 1 - - f = os.path.join(project_dir, 'foo.py') - self.write_file(f, '# python file') - cmd.byte_compile([f]) - pyc_file = importlib.util.cache_from_source('foo.py', optimization='') - pyc_opt_file = importlib.util.cache_from_source( - 'foo.py', optimization=cmd.optimize - ) - assert os.path.exists(pyc_file) - assert os.path.exists(pyc_opt_file) - - def test_get_outputs(self): - project_dir, dist = self.create_dist() - os.chdir(project_dir) - os.mkdir('spam') - cmd = install_lib(dist) - - # setting up a dist environment - cmd.compile = cmd.optimize = 1 - cmd.install_dir = self.mkdtemp() - f = os.path.join(project_dir, 'spam', '__init__.py') - self.write_file(f, '# python package') - cmd.distribution.ext_modules = [Extension('foo', ['xxx'])] - cmd.distribution.packages = ['spam'] - cmd.distribution.script_name = 'setup.py' - - # get_outputs should return 4 elements: spam/__init__.py and .pyc, - # foo.import-tag-abiflags.so / foo.pyd - outputs = cmd.get_outputs() - assert len(outputs) == 4, outputs - - def test_get_inputs(self): - project_dir, dist = self.create_dist() - os.chdir(project_dir) - os.mkdir('spam') - cmd = install_lib(dist) - - # setting up a dist environment - cmd.compile = cmd.optimize = 1 - cmd.install_dir = self.mkdtemp() - f = os.path.join(project_dir, 'spam', '__init__.py') - self.write_file(f, '# python package') - cmd.distribution.ext_modules = [Extension('foo', ['xxx'])] - cmd.distribution.packages = ['spam'] - cmd.distribution.script_name = 'setup.py' - - # get_inputs should return 2 elements: spam/__init__.py and - # foo.import-tag-abiflags.so / foo.pyd - inputs = cmd.get_inputs() - assert len(inputs) == 2, inputs - - def test_dont_write_bytecode(self, caplog): - # makes sure byte_compile is not used - dist = self.create_dist()[1] - cmd = install_lib(dist) - cmd.compile = True - cmd.optimize = 1 - - old_dont_write_bytecode = sys.dont_write_bytecode - sys.dont_write_bytecode = True - try: - cmd.byte_compile([]) - finally: - sys.dont_write_bytecode = old_dont_write_bytecode - - assert 'byte-compiling is disabled' in caplog.messages[0] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_scripts.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_scripts.py deleted file mode 100644 index 868b1c2..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_install_scripts.py +++ /dev/null @@ -1,52 +0,0 @@ -"""Tests for distutils.command.install_scripts.""" - -import os -from distutils.command.install_scripts import install_scripts -from distutils.core import Distribution -from distutils.tests import support - -from . import test_build_scripts - - -class TestInstallScripts(support.TempdirManager): - def test_default_settings(self): - dist = Distribution() - dist.command_obj["build"] = support.DummyCommand(build_scripts="/foo/bar") - dist.command_obj["install"] = support.DummyCommand( - install_scripts="/splat/funk", - force=True, - skip_build=True, - ) - cmd = install_scripts(dist) - assert not cmd.force - assert not cmd.skip_build - assert cmd.build_dir is None - assert cmd.install_dir is None - - cmd.finalize_options() - - assert cmd.force - assert cmd.skip_build - assert cmd.build_dir == "/foo/bar" - assert cmd.install_dir == "/splat/funk" - - def test_installation(self): - source = self.mkdtemp() - - expected = test_build_scripts.TestBuildScripts.write_sample_scripts(source) - - target = self.mkdtemp() - dist = Distribution() - dist.command_obj["build"] = support.DummyCommand(build_scripts=source) - dist.command_obj["install"] = support.DummyCommand( - install_scripts=target, - force=True, - skip_build=True, - ) - cmd = install_scripts(dist) - cmd.finalize_options() - cmd.run() - - installed = os.listdir(target) - for name in expected: - assert name in installed diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_log.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_log.py deleted file mode 100644 index d67779f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_log.py +++ /dev/null @@ -1,12 +0,0 @@ -"""Tests for distutils.log""" - -import logging -from distutils._log import log - - -class TestLog: - def test_non_ascii(self, caplog): - caplog.set_level(logging.DEBUG) - log.debug('Dεbug\tMėssãge') - log.fatal('Fαtal\tÈrrōr') - assert caplog.messages == ['Dεbug\tMėssãge', 'Fαtal\tÈrrōr'] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_modified.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_modified.py deleted file mode 100644 index e35cec2..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_modified.py +++ /dev/null @@ -1,126 +0,0 @@ -"""Tests for distutils._modified.""" - -import os -import types -from distutils._modified import newer, newer_group, newer_pairwise, newer_pairwise_group -from distutils.errors import DistutilsFileError -from distutils.tests import support - -import pytest - - -class TestDepUtil(support.TempdirManager): - def test_newer(self): - tmpdir = self.mkdtemp() - new_file = os.path.join(tmpdir, 'new') - old_file = os.path.abspath(__file__) - - # Raise DistutilsFileError if 'new_file' does not exist. - with pytest.raises(DistutilsFileError): - newer(new_file, old_file) - - # Return true if 'new_file' exists and is more recently modified than - # 'old_file', or if 'new_file' exists and 'old_file' doesn't. - self.write_file(new_file) - assert newer(new_file, 'I_dont_exist') - assert newer(new_file, old_file) - - # Return false if both exist and 'old_file' is the same age or younger - # than 'new_file'. - assert not newer(old_file, new_file) - - def _setup_1234(self): - tmpdir = self.mkdtemp() - sources = os.path.join(tmpdir, 'sources') - targets = os.path.join(tmpdir, 'targets') - os.mkdir(sources) - os.mkdir(targets) - one = os.path.join(sources, 'one') - two = os.path.join(sources, 'two') - three = os.path.abspath(__file__) # I am the old file - four = os.path.join(targets, 'four') - self.write_file(one) - self.write_file(two) - self.write_file(four) - return one, two, three, four - - def test_newer_pairwise(self): - one, two, three, four = self._setup_1234() - - assert newer_pairwise([one, two], [three, four]) == ([one], [three]) - - def test_newer_pairwise_mismatch(self): - one, two, three, four = self._setup_1234() - - with pytest.raises(ValueError): - newer_pairwise([one], [three, four]) - - with pytest.raises(ValueError): - newer_pairwise([one, two], [three]) - - def test_newer_pairwise_empty(self): - assert newer_pairwise([], []) == ([], []) - - def test_newer_pairwise_fresh(self): - one, two, three, four = self._setup_1234() - - assert newer_pairwise([one, three], [two, four]) == ([], []) - - def test_newer_group(self): - tmpdir = self.mkdtemp() - sources = os.path.join(tmpdir, 'sources') - os.mkdir(sources) - one = os.path.join(sources, 'one') - two = os.path.join(sources, 'two') - three = os.path.join(sources, 'three') - old_file = os.path.abspath(__file__) - - # return true if 'old_file' is out-of-date with respect to any file - # listed in 'sources'. - self.write_file(one) - self.write_file(two) - self.write_file(three) - assert newer_group([one, two, three], old_file) - assert not newer_group([one, two, old_file], three) - - # missing handling - os.remove(one) - with pytest.raises(OSError): - newer_group([one, two, old_file], three) - - assert not newer_group([one, two, old_file], three, missing='ignore') - - assert newer_group([one, two, old_file], three, missing='newer') - - -@pytest.fixture -def groups_target(tmp_path): - """ - Set up some older sources, a target, and newer sources. - - Returns a simple namespace with these values. - """ - filenames = ['older.c', 'older.h', 'target.o', 'newer.c', 'newer.h'] - paths = [tmp_path / name for name in filenames] - - for mtime, path in enumerate(paths): - path.write_text('', encoding='utf-8') - - # make sure modification times are sequential - os.utime(path, (mtime, mtime)) - - return types.SimpleNamespace(older=paths[:2], target=paths[2], newer=paths[3:]) - - -def test_newer_pairwise_group(groups_target): - older = newer_pairwise_group([groups_target.older], [groups_target.target]) - newer = newer_pairwise_group([groups_target.newer], [groups_target.target]) - assert older == ([], []) - assert newer == ([groups_target.newer], [groups_target.target]) - - -def test_newer_group_no_sources_no_target(tmp_path): - """ - Consider no sources and no target "newer". - """ - assert newer_group([], str(tmp_path / 'does-not-exist')) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_sdist.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_sdist.py deleted file mode 100644 index 6b1a376..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_sdist.py +++ /dev/null @@ -1,470 +0,0 @@ -"""Tests for distutils.command.sdist.""" - -import os -import pathlib -import shutil # noqa: F401 -import tarfile -import zipfile -from distutils.archive_util import ARCHIVE_FORMATS -from distutils.command.sdist import sdist, show_formats -from distutils.core import Distribution -from distutils.errors import DistutilsOptionError -from distutils.filelist import FileList -from os.path import join -from textwrap import dedent - -import jaraco.path -import path -import pytest -from more_itertools import ilen - -from . import support -from .unix_compat import grp, pwd, require_uid_0, require_unix_id - -SETUP_PY = """ -from distutils.core import setup -import somecode - -setup(name='fake') -""" - -MANIFEST = """\ -# file GENERATED by distutils, do NOT edit -README -buildout.cfg -inroot.txt -setup.py -data%(sep)sdata.dt -scripts%(sep)sscript.py -some%(sep)sfile.txt -some%(sep)sother_file.txt -somecode%(sep)s__init__.py -somecode%(sep)sdoc.dat -somecode%(sep)sdoc.txt -""" - - -@pytest.fixture(autouse=True) -def project_dir(request, distutils_managed_tempdir): - self = request.instance - self.tmp_dir = self.mkdtemp() - jaraco.path.build( - { - 'somecode': { - '__init__.py': '#', - }, - 'README': 'xxx', - 'setup.py': SETUP_PY, - }, - self.tmp_dir, - ) - with path.Path(self.tmp_dir): - yield - - -def clean_lines(filepath): - with pathlib.Path(filepath).open(encoding='utf-8') as f: - yield from filter(None, map(str.strip, f)) - - -class TestSDist(support.TempdirManager): - def get_cmd(self, metadata=None): - """Returns a cmd""" - if metadata is None: - metadata = { - 'name': 'ns.fake--pkg', - 'version': '1.0', - 'url': 'xxx', - 'author': 'xxx', - 'author_email': 'xxx', - } - dist = Distribution(metadata) - dist.script_name = 'setup.py' - dist.packages = ['somecode'] - dist.include_package_data = True - cmd = sdist(dist) - cmd.dist_dir = 'dist' - return dist, cmd - - @pytest.mark.usefixtures('needs_zlib') - def test_prune_file_list(self): - # this test creates a project with some VCS dirs and an NFS rename - # file, then launches sdist to check they get pruned on all systems - - # creating VCS directories with some files in them - os.mkdir(join(self.tmp_dir, 'somecode', '.svn')) - self.write_file((self.tmp_dir, 'somecode', '.svn', 'ok.py'), 'xxx') - - os.mkdir(join(self.tmp_dir, 'somecode', '.hg')) - self.write_file((self.tmp_dir, 'somecode', '.hg', 'ok'), 'xxx') - - os.mkdir(join(self.tmp_dir, 'somecode', '.git')) - self.write_file((self.tmp_dir, 'somecode', '.git', 'ok'), 'xxx') - - self.write_file((self.tmp_dir, 'somecode', '.nfs0001'), 'xxx') - - # now building a sdist - dist, cmd = self.get_cmd() - - # zip is available universally - # (tar might not be installed under win32) - cmd.formats = ['zip'] - - cmd.ensure_finalized() - cmd.run() - - # now let's check what we have - dist_folder = join(self.tmp_dir, 'dist') - files = os.listdir(dist_folder) - assert files == ['ns_fake_pkg-1.0.zip'] - - zip_file = zipfile.ZipFile(join(dist_folder, 'ns_fake_pkg-1.0.zip')) - try: - content = zip_file.namelist() - finally: - zip_file.close() - - # making sure everything has been pruned correctly - expected = [ - '', - 'PKG-INFO', - 'README', - 'setup.py', - 'somecode/', - 'somecode/__init__.py', - ] - assert sorted(content) == ['ns_fake_pkg-1.0/' + x for x in expected] - - @pytest.mark.usefixtures('needs_zlib') - @pytest.mark.skipif("not shutil.which('tar')") - @pytest.mark.skipif("not shutil.which('gzip')") - def test_make_distribution(self): - # now building a sdist - dist, cmd = self.get_cmd() - - # creating a gztar then a tar - cmd.formats = ['gztar', 'tar'] - cmd.ensure_finalized() - cmd.run() - - # making sure we have two files - dist_folder = join(self.tmp_dir, 'dist') - result = os.listdir(dist_folder) - result.sort() - assert result == ['ns_fake_pkg-1.0.tar', 'ns_fake_pkg-1.0.tar.gz'] - - os.remove(join(dist_folder, 'ns_fake_pkg-1.0.tar')) - os.remove(join(dist_folder, 'ns_fake_pkg-1.0.tar.gz')) - - # now trying a tar then a gztar - cmd.formats = ['tar', 'gztar'] - - cmd.ensure_finalized() - cmd.run() - - result = os.listdir(dist_folder) - result.sort() - assert result == ['ns_fake_pkg-1.0.tar', 'ns_fake_pkg-1.0.tar.gz'] - - @pytest.mark.usefixtures('needs_zlib') - def test_add_defaults(self): - # https://bugs.python.org/issue2279 - - # add_default should also include - # data_files and package_data - dist, cmd = self.get_cmd() - - # filling data_files by pointing files - # in package_data - dist.package_data = {'': ['*.cfg', '*.dat'], 'somecode': ['*.txt']} - self.write_file((self.tmp_dir, 'somecode', 'doc.txt'), '#') - self.write_file((self.tmp_dir, 'somecode', 'doc.dat'), '#') - - # adding some data in data_files - data_dir = join(self.tmp_dir, 'data') - os.mkdir(data_dir) - self.write_file((data_dir, 'data.dt'), '#') - some_dir = join(self.tmp_dir, 'some') - os.mkdir(some_dir) - # make sure VCS directories are pruned (#14004) - hg_dir = join(self.tmp_dir, '.hg') - os.mkdir(hg_dir) - self.write_file((hg_dir, 'last-message.txt'), '#') - # a buggy regex used to prevent this from working on windows (#6884) - self.write_file((self.tmp_dir, 'buildout.cfg'), '#') - self.write_file((self.tmp_dir, 'inroot.txt'), '#') - self.write_file((some_dir, 'file.txt'), '#') - self.write_file((some_dir, 'other_file.txt'), '#') - - dist.data_files = [ - ('data', ['data/data.dt', 'buildout.cfg', 'inroot.txt', 'notexisting']), - 'some/file.txt', - 'some/other_file.txt', - ] - - # adding a script - script_dir = join(self.tmp_dir, 'scripts') - os.mkdir(script_dir) - self.write_file((script_dir, 'script.py'), '#') - dist.scripts = [join('scripts', 'script.py')] - - cmd.formats = ['zip'] - cmd.use_defaults = True - - cmd.ensure_finalized() - cmd.run() - - # now let's check what we have - dist_folder = join(self.tmp_dir, 'dist') - files = os.listdir(dist_folder) - assert files == ['ns_fake_pkg-1.0.zip'] - - zip_file = zipfile.ZipFile(join(dist_folder, 'ns_fake_pkg-1.0.zip')) - try: - content = zip_file.namelist() - finally: - zip_file.close() - - # making sure everything was added - expected = [ - '', - 'PKG-INFO', - 'README', - 'buildout.cfg', - 'data/', - 'data/data.dt', - 'inroot.txt', - 'scripts/', - 'scripts/script.py', - 'setup.py', - 'some/', - 'some/file.txt', - 'some/other_file.txt', - 'somecode/', - 'somecode/__init__.py', - 'somecode/doc.dat', - 'somecode/doc.txt', - ] - assert sorted(content) == ['ns_fake_pkg-1.0/' + x for x in expected] - - # checking the MANIFEST - manifest = pathlib.Path(self.tmp_dir, 'MANIFEST').read_text(encoding='utf-8') - assert manifest == MANIFEST % {'sep': os.sep} - - @staticmethod - def warnings(messages, prefix='warning: '): - return [msg for msg in messages if msg.startswith(prefix)] - - @pytest.mark.usefixtures('needs_zlib') - def test_metadata_check_option(self, caplog): - # testing the `medata-check` option - dist, cmd = self.get_cmd(metadata={}) - - # this should raise some warnings ! - # with the `check` subcommand - cmd.ensure_finalized() - cmd.run() - assert len(self.warnings(caplog.messages, 'warning: check: ')) == 1 - - # trying with a complete set of metadata - caplog.clear() - dist, cmd = self.get_cmd() - cmd.ensure_finalized() - cmd.metadata_check = False - cmd.run() - assert len(self.warnings(caplog.messages, 'warning: check: ')) == 0 - - def test_show_formats(self, capsys): - show_formats() - - # the output should be a header line + one line per format - num_formats = len(ARCHIVE_FORMATS.keys()) - output = [ - line - for line in capsys.readouterr().out.split('\n') - if line.strip().startswith('--formats=') - ] - assert len(output) == num_formats - - def test_finalize_options(self): - dist, cmd = self.get_cmd() - cmd.finalize_options() - - # default options set by finalize - assert cmd.manifest == 'MANIFEST' - assert cmd.template == 'MANIFEST.in' - assert cmd.dist_dir == 'dist' - - # formats has to be a string splitable on (' ', ',') or - # a stringlist - cmd.formats = 1 - with pytest.raises(DistutilsOptionError): - cmd.finalize_options() - cmd.formats = ['zip'] - cmd.finalize_options() - - # formats has to be known - cmd.formats = 'supazipa' - with pytest.raises(DistutilsOptionError): - cmd.finalize_options() - - # the following tests make sure there is a nice error message instead - # of a traceback when parsing an invalid manifest template - - def _check_template(self, content, caplog): - dist, cmd = self.get_cmd() - os.chdir(self.tmp_dir) - self.write_file('MANIFEST.in', content) - cmd.ensure_finalized() - cmd.filelist = FileList() - cmd.read_template() - assert len(self.warnings(caplog.messages)) == 1 - - def test_invalid_template_unknown_command(self, caplog): - self._check_template('taunt knights *', caplog) - - def test_invalid_template_wrong_arguments(self, caplog): - # this manifest command takes one argument - self._check_template('prune', caplog) - - @pytest.mark.skipif("platform.system() != 'Windows'") - def test_invalid_template_wrong_path(self, caplog): - # on Windows, trailing slashes are not allowed - # this used to crash instead of raising a warning: #8286 - self._check_template('include examples/', caplog) - - @pytest.mark.usefixtures('needs_zlib') - def test_get_file_list(self): - # make sure MANIFEST is recalculated - dist, cmd = self.get_cmd() - - # filling data_files by pointing files in package_data - dist.package_data = {'somecode': ['*.txt']} - self.write_file((self.tmp_dir, 'somecode', 'doc.txt'), '#') - cmd.formats = ['gztar'] - cmd.ensure_finalized() - cmd.run() - - assert ilen(clean_lines(cmd.manifest)) == 5 - - # adding a file - self.write_file((self.tmp_dir, 'somecode', 'doc2.txt'), '#') - - # make sure build_py is reinitialized, like a fresh run - build_py = dist.get_command_obj('build_py') - build_py.finalized = False - build_py.ensure_finalized() - - cmd.run() - - manifest2 = list(clean_lines(cmd.manifest)) - - # do we have the new file in MANIFEST ? - assert len(manifest2) == 6 - assert 'doc2.txt' in manifest2[-1] - - @pytest.mark.usefixtures('needs_zlib') - def test_manifest_marker(self): - # check that autogenerated MANIFESTs have a marker - dist, cmd = self.get_cmd() - cmd.ensure_finalized() - cmd.run() - - assert ( - next(clean_lines(cmd.manifest)) - == '# file GENERATED by distutils, do NOT edit' - ) - - @pytest.mark.usefixtures('needs_zlib') - def test_manifest_comments(self): - # make sure comments don't cause exceptions or wrong includes - contents = dedent( - """\ - # bad.py - #bad.py - good.py - """ - ) - dist, cmd = self.get_cmd() - cmd.ensure_finalized() - self.write_file((self.tmp_dir, cmd.manifest), contents) - self.write_file((self.tmp_dir, 'good.py'), '# pick me!') - self.write_file((self.tmp_dir, 'bad.py'), "# don't pick me!") - self.write_file((self.tmp_dir, '#bad.py'), "# don't pick me!") - cmd.run() - assert cmd.filelist.files == ['good.py'] - - @pytest.mark.usefixtures('needs_zlib') - def test_manual_manifest(self): - # check that a MANIFEST without a marker is left alone - dist, cmd = self.get_cmd() - cmd.formats = ['gztar'] - cmd.ensure_finalized() - self.write_file((self.tmp_dir, cmd.manifest), 'README.manual') - self.write_file( - (self.tmp_dir, 'README.manual'), - 'This project maintains its MANIFEST file itself.', - ) - cmd.run() - assert cmd.filelist.files == ['README.manual'] - - assert list(clean_lines(cmd.manifest)) == ['README.manual'] - - archive_name = join(self.tmp_dir, 'dist', 'ns_fake_pkg-1.0.tar.gz') - archive = tarfile.open(archive_name) - try: - filenames = [tarinfo.name for tarinfo in archive] - finally: - archive.close() - assert sorted(filenames) == [ - 'ns_fake_pkg-1.0', - 'ns_fake_pkg-1.0/PKG-INFO', - 'ns_fake_pkg-1.0/README.manual', - ] - - @pytest.mark.usefixtures('needs_zlib') - @require_unix_id - @require_uid_0 - @pytest.mark.skipif("not shutil.which('tar')") - @pytest.mark.skipif("not shutil.which('gzip')") - def test_make_distribution_owner_group(self): - # now building a sdist - dist, cmd = self.get_cmd() - - # creating a gztar and specifying the owner+group - cmd.formats = ['gztar'] - cmd.owner = pwd.getpwuid(0)[0] - cmd.group = grp.getgrgid(0)[0] - cmd.ensure_finalized() - cmd.run() - - # making sure we have the good rights - archive_name = join(self.tmp_dir, 'dist', 'ns_fake_pkg-1.0.tar.gz') - archive = tarfile.open(archive_name) - try: - for member in archive.getmembers(): - assert member.uid == 0 - assert member.gid == 0 - finally: - archive.close() - - # building a sdist again - dist, cmd = self.get_cmd() - - # creating a gztar - cmd.formats = ['gztar'] - cmd.ensure_finalized() - cmd.run() - - # making sure we have the good rights - archive_name = join(self.tmp_dir, 'dist', 'ns_fake_pkg-1.0.tar.gz') - archive = tarfile.open(archive_name) - - # note that we are not testing the group ownership here - # because, depending on the platforms and the container - # rights (see #7408) - try: - for member in archive.getmembers(): - assert member.uid == os.getuid() - finally: - archive.close() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_spawn.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_spawn.py deleted file mode 100644 index 3b9fc92..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_spawn.py +++ /dev/null @@ -1,141 +0,0 @@ -"""Tests for distutils.spawn.""" - -import os -import stat -import sys -import unittest.mock as mock -from distutils.errors import DistutilsExecError -from distutils.spawn import find_executable, spawn -from distutils.tests import support - -import path -import pytest -from test.support import unix_shell - -from .compat import py39 as os_helper - - -class TestSpawn(support.TempdirManager): - @pytest.mark.skipif("os.name not in ('nt', 'posix')") - def test_spawn(self): - tmpdir = self.mkdtemp() - - # creating something executable - # through the shell that returns 1 - if sys.platform != 'win32': - exe = os.path.join(tmpdir, 'foo.sh') - self.write_file(exe, f'#!{unix_shell}\nexit 1') - else: - exe = os.path.join(tmpdir, 'foo.bat') - self.write_file(exe, 'exit 1') - - os.chmod(exe, 0o777) - with pytest.raises(DistutilsExecError): - spawn([exe]) - - # now something that works - if sys.platform != 'win32': - exe = os.path.join(tmpdir, 'foo.sh') - self.write_file(exe, f'#!{unix_shell}\nexit 0') - else: - exe = os.path.join(tmpdir, 'foo.bat') - self.write_file(exe, 'exit 0') - - os.chmod(exe, 0o777) - spawn([exe]) # should work without any error - - def test_find_executable(self, tmp_path): - program_path = self._make_executable(tmp_path, '.exe') - program = program_path.name - program_noeext = program_path.with_suffix('').name - filename = str(program_path) - tmp_dir = path.Path(tmp_path) - - # test path parameter - rv = find_executable(program, path=tmp_dir) - assert rv == filename - - if sys.platform == 'win32': - # test without ".exe" extension - rv = find_executable(program_noeext, path=tmp_dir) - assert rv == filename - - # test find in the current directory - with tmp_dir: - rv = find_executable(program) - assert rv == program - - # test non-existent program - dont_exist_program = "dontexist_" + program - rv = find_executable(dont_exist_program, path=tmp_dir) - assert rv is None - - # PATH='': no match, except in the current directory - with os_helper.EnvironmentVarGuard() as env: - env['PATH'] = '' - with ( - mock.patch( - 'distutils.spawn.os.confstr', return_value=tmp_dir, create=True - ), - mock.patch('distutils.spawn.os.defpath', tmp_dir), - ): - rv = find_executable(program) - assert rv is None - - # look in current directory - with tmp_dir: - rv = find_executable(program) - assert rv == program - - # PATH=':': explicitly looks in the current directory - with os_helper.EnvironmentVarGuard() as env: - env['PATH'] = os.pathsep - with ( - mock.patch('distutils.spawn.os.confstr', return_value='', create=True), - mock.patch('distutils.spawn.os.defpath', ''), - ): - rv = find_executable(program) - assert rv is None - - # look in current directory - with tmp_dir: - rv = find_executable(program) - assert rv == program - - # missing PATH: test os.confstr("CS_PATH") and os.defpath - with os_helper.EnvironmentVarGuard() as env: - env.pop('PATH', None) - - # without confstr - with ( - mock.patch( - 'distutils.spawn.os.confstr', side_effect=ValueError, create=True - ), - mock.patch('distutils.spawn.os.defpath', tmp_dir), - ): - rv = find_executable(program) - assert rv == filename - - # with confstr - with ( - mock.patch( - 'distutils.spawn.os.confstr', return_value=tmp_dir, create=True - ), - mock.patch('distutils.spawn.os.defpath', ''), - ): - rv = find_executable(program) - assert rv == filename - - @staticmethod - def _make_executable(tmp_path, ext): - # Give the temporary program a suffix regardless of platform. - # It's needed on Windows and not harmful on others. - program = tmp_path.joinpath('program').with_suffix(ext) - program.write_text("", encoding='utf-8') - program.chmod(stat.S_IXUSR) - return program - - def test_spawn_missing_exe(self): - with pytest.raises(DistutilsExecError) as ctx: - spawn(['does-not-exist']) - assert "command 'does-not-exist' failed" in str(ctx.value) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_sysconfig.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_sysconfig.py deleted file mode 100644 index 43d77c2..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_sysconfig.py +++ /dev/null @@ -1,319 +0,0 @@ -"""Tests for distutils.sysconfig.""" - -import contextlib -import distutils -import os -import pathlib -import subprocess -import sys -from distutils import sysconfig -from distutils.ccompiler import new_compiler # noqa: F401 -from distutils.unixccompiler import UnixCCompiler - -import jaraco.envs -import path -import pytest -from jaraco.text import trim -from test.support import swap_item - - -def _gen_makefile(root, contents): - jaraco.path.build({'Makefile': trim(contents)}, root) - return root / 'Makefile' - - -@pytest.mark.usefixtures('save_env') -class TestSysconfig: - def test_get_config_h_filename(self): - config_h = sysconfig.get_config_h_filename() - assert os.path.isfile(config_h) - - @pytest.mark.skipif("platform.system() == 'Windows'") - @pytest.mark.skipif("sys.implementation.name != 'cpython'") - def test_get_makefile_filename(self): - makefile = sysconfig.get_makefile_filename() - assert os.path.isfile(makefile) - - def test_get_python_lib(self, tmp_path): - assert sysconfig.get_python_lib() != sysconfig.get_python_lib(prefix=tmp_path) - - def test_get_config_vars(self): - cvars = sysconfig.get_config_vars() - assert isinstance(cvars, dict) - assert cvars - - @pytest.mark.skipif('sysconfig.IS_PYPY') - @pytest.mark.skipif('sysconfig.python_build') - @pytest.mark.xfail('platform.system() == "Windows"') - def test_srcdir_simple(self): - # See #15364. - srcdir = pathlib.Path(sysconfig.get_config_var('srcdir')) - - assert srcdir.absolute() - assert srcdir.is_dir() - - makefile = pathlib.Path(sysconfig.get_makefile_filename()) - assert makefile.parent.samefile(srcdir) - - @pytest.mark.skipif('sysconfig.IS_PYPY') - @pytest.mark.skipif('not sysconfig.python_build') - def test_srcdir_python_build(self): - # See #15364. - srcdir = pathlib.Path(sysconfig.get_config_var('srcdir')) - - # The python executable has not been installed so srcdir - # should be a full source checkout. - Python_h = srcdir.joinpath('Include', 'Python.h') - assert Python_h.is_file() - assert sysconfig._is_python_source_dir(srcdir) - assert sysconfig._is_python_source_dir(str(srcdir)) - - def test_srcdir_independent_of_cwd(self): - """ - srcdir should be independent of the current working directory - """ - # See #15364. - srcdir = sysconfig.get_config_var('srcdir') - with path.Path('..'): - srcdir2 = sysconfig.get_config_var('srcdir') - assert srcdir == srcdir2 - - def customize_compiler(self): - # make sure AR gets caught - class compiler: - compiler_type = 'unix' - executables = UnixCCompiler.executables - - def __init__(self): - self.exes = {} - - def set_executables(self, **kw): - for k, v in kw.items(): - self.exes[k] = v - - sysconfig_vars = { - 'AR': 'sc_ar', - 'CC': 'sc_cc', - 'CXX': 'sc_cxx', - 'ARFLAGS': '--sc-arflags', - 'CFLAGS': '--sc-cflags', - 'CCSHARED': '--sc-ccshared', - 'LDSHARED': 'sc_ldshared', - 'SHLIB_SUFFIX': 'sc_shutil_suffix', - } - - comp = compiler() - with contextlib.ExitStack() as cm: - for key, value in sysconfig_vars.items(): - cm.enter_context(swap_item(sysconfig._config_vars, key, value)) - sysconfig.customize_compiler(comp) - - return comp - - @pytest.mark.skipif("not isinstance(new_compiler(), UnixCCompiler)") - @pytest.mark.usefixtures('disable_macos_customization') - def test_customize_compiler(self): - # Make sure that sysconfig._config_vars is initialized - sysconfig.get_config_vars() - - os.environ['AR'] = 'env_ar' - os.environ['CC'] = 'env_cc' - os.environ['CPP'] = 'env_cpp' - os.environ['CXX'] = 'env_cxx --env-cxx-flags' - os.environ['LDSHARED'] = 'env_ldshared' - os.environ['LDFLAGS'] = '--env-ldflags' - os.environ['ARFLAGS'] = '--env-arflags' - os.environ['CFLAGS'] = '--env-cflags' - os.environ['CPPFLAGS'] = '--env-cppflags' - os.environ['RANLIB'] = 'env_ranlib' - - comp = self.customize_compiler() - assert comp.exes['archiver'] == 'env_ar --env-arflags' - assert comp.exes['preprocessor'] == 'env_cpp --env-cppflags' - assert comp.exes['compiler'] == 'env_cc --env-cflags --env-cppflags' - assert comp.exes['compiler_so'] == ( - 'env_cc --env-cflags --env-cppflags --sc-ccshared' - ) - assert ( - comp.exes['compiler_cxx'] - == 'env_cxx --env-cxx-flags --sc-cflags --env-cppflags' - ) - assert comp.exes['linker_exe'] == 'env_cc' - assert comp.exes['linker_so'] == ( - 'env_ldshared --env-ldflags --env-cflags --env-cppflags' - ) - assert comp.shared_lib_extension == 'sc_shutil_suffix' - - if sys.platform == "darwin": - assert comp.exes['ranlib'] == 'env_ranlib' - else: - assert 'ranlib' not in comp.exes - - del os.environ['AR'] - del os.environ['CC'] - del os.environ['CPP'] - del os.environ['CXX'] - del os.environ['LDSHARED'] - del os.environ['LDFLAGS'] - del os.environ['ARFLAGS'] - del os.environ['CFLAGS'] - del os.environ['CPPFLAGS'] - del os.environ['RANLIB'] - - comp = self.customize_compiler() - assert comp.exes['archiver'] == 'sc_ar --sc-arflags' - assert comp.exes['preprocessor'] == 'sc_cc -E' - assert comp.exes['compiler'] == 'sc_cc --sc-cflags' - assert comp.exes['compiler_so'] == 'sc_cc --sc-cflags --sc-ccshared' - assert comp.exes['compiler_cxx'] == 'sc_cxx --sc-cflags' - assert comp.exes['linker_exe'] == 'sc_cc' - assert comp.exes['linker_so'] == 'sc_ldshared' - assert comp.shared_lib_extension == 'sc_shutil_suffix' - assert 'ranlib' not in comp.exes - - def test_parse_makefile_base(self, tmp_path): - makefile = _gen_makefile( - tmp_path, - """ - CONFIG_ARGS= '--arg1=optarg1' 'ENV=LIB' - VAR=$OTHER - OTHER=foo - """, - ) - d = sysconfig.parse_makefile(makefile) - assert d == {'CONFIG_ARGS': "'--arg1=optarg1' 'ENV=LIB'", 'OTHER': 'foo'} - - def test_parse_makefile_literal_dollar(self, tmp_path): - makefile = _gen_makefile( - tmp_path, - """ - CONFIG_ARGS= '--arg1=optarg1' 'ENV=\\$$LIB' - VAR=$OTHER - OTHER=foo - """, - ) - d = sysconfig.parse_makefile(makefile) - assert d == {'CONFIG_ARGS': r"'--arg1=optarg1' 'ENV=\$LIB'", 'OTHER': 'foo'} - - def test_sysconfig_module(self): - import sysconfig as global_sysconfig - - assert global_sysconfig.get_config_var('CFLAGS') == sysconfig.get_config_var( - 'CFLAGS' - ) - assert global_sysconfig.get_config_var('LDFLAGS') == sysconfig.get_config_var( - 'LDFLAGS' - ) - - # On macOS, binary installers support extension module building on - # various levels of the operating system with differing Xcode - # configurations, requiring customization of some of the - # compiler configuration directives to suit the environment on - # the installed machine. Some of these customizations may require - # running external programs and are thus deferred until needed by - # the first extension module build. Only - # the Distutils version of sysconfig is used for extension module - # builds, which happens earlier in the Distutils tests. This may - # cause the following tests to fail since no tests have caused - # the global version of sysconfig to call the customization yet. - # The solution for now is to simply skip this test in this case. - # The longer-term solution is to only have one version of sysconfig. - @pytest.mark.skipif("sysconfig.get_config_var('CUSTOMIZED_OSX_COMPILER')") - def test_sysconfig_compiler_vars(self): - import sysconfig as global_sysconfig - - if sysconfig.get_config_var('CUSTOMIZED_OSX_COMPILER'): - pytest.skip('compiler flags customized') - assert global_sysconfig.get_config_var('LDSHARED') == sysconfig.get_config_var( - 'LDSHARED' - ) - assert global_sysconfig.get_config_var('CC') == sysconfig.get_config_var('CC') - - @pytest.mark.skipif("not sysconfig.get_config_var('EXT_SUFFIX')") - def test_SO_deprecation(self): - with pytest.warns(DeprecationWarning): - sysconfig.get_config_var('SO') - - def test_customize_compiler_before_get_config_vars(self, tmp_path): - # Issue #21923: test that a Distribution compiler - # instance can be called without an explicit call to - # get_config_vars(). - jaraco.path.build( - { - 'file': trim(""" - from distutils.core import Distribution - config = Distribution().get_command_obj('config') - # try_compile may pass or it may fail if no compiler - # is found but it should not raise an exception. - rc = config.try_compile('int x;') - """) - }, - tmp_path, - ) - p = subprocess.Popen( - [sys.executable, tmp_path / 'file'], - stdout=subprocess.PIPE, - stderr=subprocess.STDOUT, - universal_newlines=True, - encoding='utf-8', - ) - outs, errs = p.communicate() - assert 0 == p.returncode, "Subprocess failed: " + outs - - def test_parse_config_h(self): - config_h = sysconfig.get_config_h_filename() - input = {} - with open(config_h, encoding="utf-8") as f: - result = sysconfig.parse_config_h(f, g=input) - assert input is result - with open(config_h, encoding="utf-8") as f: - result = sysconfig.parse_config_h(f) - assert isinstance(result, dict) - - @pytest.mark.skipif("platform.system() != 'Windows'") - @pytest.mark.skipif("sys.implementation.name != 'cpython'") - def test_win_ext_suffix(self): - assert sysconfig.get_config_var("EXT_SUFFIX").endswith(".pyd") - assert sysconfig.get_config_var("EXT_SUFFIX") != ".pyd" - - @pytest.mark.skipif("platform.system() != 'Windows'") - @pytest.mark.skipif("sys.implementation.name != 'cpython'") - @pytest.mark.skipif( - '\\PCbuild\\'.casefold() not in sys.executable.casefold(), - reason='Need sys.executable to be in a source tree', - ) - def test_win_build_venv_from_source_tree(self, tmp_path): - """Ensure distutils.sysconfig detects venvs from source tree builds.""" - env = jaraco.envs.VEnv() - env.create_opts = env.clean_opts - env.root = tmp_path - env.ensure_env() - cmd = [ - env.exe(), - "-c", - "import distutils.sysconfig; print(distutils.sysconfig.python_build)", - ] - distutils_path = os.path.dirname(os.path.dirname(distutils.__file__)) - out = subprocess.check_output( - cmd, env={**os.environ, "PYTHONPATH": distutils_path} - ) - assert out == "True" - - def test_get_python_inc_missing_config_dir(self, monkeypatch): - """ - In portable Python installations, the sysconfig will be broken, - pointing to the directories where the installation was built and - not where it currently is. In this case, ensure that the missing - directory isn't used for get_python_inc. - - See pypa/distutils#178. - """ - - def override(name): - if name == 'INCLUDEPY': - return '/does-not-exist' - return sysconfig.get_config_var(name) - - monkeypatch.setattr(sysconfig, 'get_config_var', override) - - assert os.path.exists(sysconfig.get_python_inc()) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_text_file.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_text_file.py deleted file mode 100644 index f511156..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_text_file.py +++ /dev/null @@ -1,127 +0,0 @@ -"""Tests for distutils.text_file.""" - -from distutils.tests import support -from distutils.text_file import TextFile - -import jaraco.path -import path - -TEST_DATA = """# test file - -line 3 \\ -# intervening comment - continues on next line -""" - - -class TestTextFile(support.TempdirManager): - def test_class(self): - # old tests moved from text_file.__main__ - # so they are really called by the buildbots - - # result 1: no fancy options - result1 = [ - '# test file\n', - '\n', - 'line 3 \\\n', - '# intervening comment\n', - ' continues on next line\n', - ] - - # result 2: just strip comments - result2 = ["\n", "line 3 \\\n", " continues on next line\n"] - - # result 3: just strip blank lines - result3 = [ - "# test file\n", - "line 3 \\\n", - "# intervening comment\n", - " continues on next line\n", - ] - - # result 4: default, strip comments, blank lines, - # and trailing whitespace - result4 = ["line 3 \\", " continues on next line"] - - # result 5: strip comments and blanks, plus join lines (but don't - # "collapse" joined lines - result5 = ["line 3 continues on next line"] - - # result 6: strip comments and blanks, plus join lines (and - # "collapse" joined lines - result6 = ["line 3 continues on next line"] - - def test_input(count, description, file, expected_result): - result = file.readlines() - assert result == expected_result - - tmp_path = path.Path(self.mkdtemp()) - filename = tmp_path / 'test.txt' - jaraco.path.build({filename.name: TEST_DATA}, tmp_path) - - in_file = TextFile( - filename, - strip_comments=False, - skip_blanks=False, - lstrip_ws=False, - rstrip_ws=False, - ) - try: - test_input(1, "no processing", in_file, result1) - finally: - in_file.close() - - in_file = TextFile( - filename, - strip_comments=True, - skip_blanks=False, - lstrip_ws=False, - rstrip_ws=False, - ) - try: - test_input(2, "strip comments", in_file, result2) - finally: - in_file.close() - - in_file = TextFile( - filename, - strip_comments=False, - skip_blanks=True, - lstrip_ws=False, - rstrip_ws=False, - ) - try: - test_input(3, "strip blanks", in_file, result3) - finally: - in_file.close() - - in_file = TextFile(filename) - try: - test_input(4, "default processing", in_file, result4) - finally: - in_file.close() - - in_file = TextFile( - filename, - strip_comments=True, - skip_blanks=True, - join_lines=True, - rstrip_ws=True, - ) - try: - test_input(5, "join lines without collapsing", in_file, result5) - finally: - in_file.close() - - in_file = TextFile( - filename, - strip_comments=True, - skip_blanks=True, - join_lines=True, - rstrip_ws=True, - collapse_join=True, - ) - try: - test_input(6, "join lines with collapsing", in_file, result6) - finally: - in_file.close() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_util.py deleted file mode 100644 index 00c9743..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_util.py +++ /dev/null @@ -1,243 +0,0 @@ -"""Tests for distutils.util.""" - -import email -import email.generator -import email.policy -import io -import os -import pathlib -import sys -import sysconfig as stdlib_sysconfig -import unittest.mock as mock -from copy import copy -from distutils import sysconfig, util -from distutils.errors import DistutilsByteCompileError, DistutilsPlatformError -from distutils.util import ( - byte_compile, - change_root, - check_environ, - convert_path, - get_host_platform, - get_platform, - grok_environment_error, - rfc822_escape, - split_quoted, - strtobool, -) - -import pytest - - -@pytest.fixture(autouse=True) -def environment(monkeypatch): - monkeypatch.setattr(os, 'name', os.name) - monkeypatch.setattr(sys, 'platform', sys.platform) - monkeypatch.setattr(sys, 'version', sys.version) - monkeypatch.setattr(os, 'sep', os.sep) - monkeypatch.setattr(os.path, 'join', os.path.join) - monkeypatch.setattr(os.path, 'isabs', os.path.isabs) - monkeypatch.setattr(os.path, 'splitdrive', os.path.splitdrive) - monkeypatch.setattr(sysconfig, '_config_vars', copy(sysconfig._config_vars)) - - -@pytest.mark.usefixtures('save_env') -class TestUtil: - def test_get_host_platform(self): - with mock.patch('os.name', 'nt'): - with mock.patch('sys.version', '... [... (ARM64)]'): - assert get_host_platform() == 'win-arm64' - with mock.patch('sys.version', '... [... (ARM)]'): - assert get_host_platform() == 'win-arm32' - - with mock.patch('sys.version_info', (3, 9, 0, 'final', 0)): - assert get_host_platform() == stdlib_sysconfig.get_platform() - - def test_get_platform(self): - with mock.patch('os.name', 'nt'): - with mock.patch.dict('os.environ', {'VSCMD_ARG_TGT_ARCH': 'x86'}): - assert get_platform() == 'win32' - with mock.patch.dict('os.environ', {'VSCMD_ARG_TGT_ARCH': 'x64'}): - assert get_platform() == 'win-amd64' - with mock.patch.dict('os.environ', {'VSCMD_ARG_TGT_ARCH': 'arm'}): - assert get_platform() == 'win-arm32' - with mock.patch.dict('os.environ', {'VSCMD_ARG_TGT_ARCH': 'arm64'}): - assert get_platform() == 'win-arm64' - - def test_convert_path(self): - expected = os.sep.join(('', 'home', 'to', 'my', 'stuff')) - assert convert_path('/home/to/my/stuff') == expected - assert convert_path(pathlib.Path('/home/to/my/stuff')) == expected - assert convert_path('.') == os.curdir - - def test_change_root(self): - # linux/mac - os.name = 'posix' - - def _isabs(path): - return path[0] == '/' - - os.path.isabs = _isabs - - def _join(*path): - return '/'.join(path) - - os.path.join = _join - - assert change_root('/root', '/old/its/here') == '/root/old/its/here' - assert change_root('/root', 'its/here') == '/root/its/here' - - # windows - os.name = 'nt' - os.sep = '\\' - - def _isabs(path): - return path.startswith('c:\\') - - os.path.isabs = _isabs - - def _splitdrive(path): - if path.startswith('c:'): - return ('', path.replace('c:', '')) - return ('', path) - - os.path.splitdrive = _splitdrive - - def _join(*path): - return '\\'.join(path) - - os.path.join = _join - - assert ( - change_root('c:\\root', 'c:\\old\\its\\here') == 'c:\\root\\old\\its\\here' - ) - assert change_root('c:\\root', 'its\\here') == 'c:\\root\\its\\here' - - # BugsBunny os (it's a great os) - os.name = 'BugsBunny' - with pytest.raises(DistutilsPlatformError): - change_root('c:\\root', 'its\\here') - - # XXX platforms to be covered: mac - - def test_check_environ(self): - util.check_environ.cache_clear() - os.environ.pop('HOME', None) - - check_environ() - - assert os.environ['PLAT'] == get_platform() - - @pytest.mark.skipif("os.name != 'posix'") - def test_check_environ_getpwuid(self): - util.check_environ.cache_clear() - os.environ.pop('HOME', None) - - import pwd - - # only set pw_dir field, other fields are not used - result = pwd.struct_passwd(( - None, - None, - None, - None, - None, - '/home/distutils', - None, - )) - with mock.patch.object(pwd, 'getpwuid', return_value=result): - check_environ() - assert os.environ['HOME'] == '/home/distutils' - - util.check_environ.cache_clear() - os.environ.pop('HOME', None) - - # bpo-10496: Catch pwd.getpwuid() error - with mock.patch.object(pwd, 'getpwuid', side_effect=KeyError): - check_environ() - assert 'HOME' not in os.environ - - def test_split_quoted(self): - assert split_quoted('""one"" "two" \'three\' \\four') == [ - 'one', - 'two', - 'three', - 'four', - ] - - def test_strtobool(self): - yes = ('y', 'Y', 'yes', 'True', 't', 'true', 'True', 'On', 'on', '1') - no = ('n', 'no', 'f', 'false', 'off', '0', 'Off', 'No', 'N') - - for y in yes: - assert strtobool(y) - - for n in no: - assert not strtobool(n) - - indent = 8 * ' ' - - @pytest.mark.parametrize( - "given,wanted", - [ - # 0x0b, 0x0c, ..., etc are also considered a line break by Python - ("hello\x0b\nworld\n", f"hello\x0b{indent}\n{indent}world\n{indent}"), - ("hello\x1eworld", f"hello\x1e{indent}world"), - ("", ""), - ( - "I am a\npoor\nlonesome\nheader\n", - f"I am a\n{indent}poor\n{indent}lonesome\n{indent}header\n{indent}", - ), - ], - ) - def test_rfc822_escape(self, given, wanted): - """ - We want to ensure a multi-line header parses correctly. - - For interoperability, the escaped value should also "round-trip" over - `email.generator.Generator.flatten` and `email.message_from_*` - (see pypa/setuptools#4033). - - The main issue is that internally `email.policy.EmailPolicy` uses - `splitlines` which will split on some control chars. If all the new lines - are not prefixed with spaces, the parser will interrupt reading - the current header and produce an incomplete value, while - incorrectly interpreting the rest of the headers as part of the payload. - """ - res = rfc822_escape(given) - - policy = email.policy.EmailPolicy( - utf8=True, - mangle_from_=False, - max_line_length=0, - ) - with io.StringIO() as buffer: - raw = f"header: {res}\nother-header: 42\n\npayload\n" - orig = email.message_from_string(raw) - email.generator.Generator(buffer, policy=policy).flatten(orig) - buffer.seek(0) - regen = email.message_from_file(buffer) - - for msg in (orig, regen): - assert msg.get_payload() == "payload\n" - assert msg["other-header"] == "42" - # Generator may replace control chars with `\n` - assert set(msg["header"].splitlines()) == set(res.splitlines()) - - assert res == wanted - - def test_dont_write_bytecode(self): - # makes sure byte_compile raise a DistutilsError - # if sys.dont_write_bytecode is True - old_dont_write_bytecode = sys.dont_write_bytecode - sys.dont_write_bytecode = True - try: - with pytest.raises(DistutilsByteCompileError): - byte_compile([]) - finally: - sys.dont_write_bytecode = old_dont_write_bytecode - - def test_grok_environment_error(self): - # test obsolete function to ensure backward compat (#4931) - exc = OSError("Unable to find batch file") - msg = grok_environment_error(exc) - assert msg == "error: Unable to find batch file" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_version.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_version.py deleted file mode 100644 index b68f097..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_version.py +++ /dev/null @@ -1,80 +0,0 @@ -"""Tests for distutils.version.""" - -import distutils -from distutils.version import LooseVersion, StrictVersion - -import pytest - - -@pytest.fixture(autouse=True) -def suppress_deprecation(): - with distutils.version.suppress_known_deprecation(): - yield - - -class TestVersion: - def test_prerelease(self): - version = StrictVersion('1.2.3a1') - assert version.version == (1, 2, 3) - assert version.prerelease == ('a', 1) - assert str(version) == '1.2.3a1' - - version = StrictVersion('1.2.0') - assert str(version) == '1.2' - - def test_cmp_strict(self): - versions = ( - ('1.5.1', '1.5.2b2', -1), - ('161', '3.10a', ValueError), - ('8.02', '8.02', 0), - ('3.4j', '1996.07.12', ValueError), - ('3.2.pl0', '3.1.1.6', ValueError), - ('2g6', '11g', ValueError), - ('0.9', '2.2', -1), - ('1.2.1', '1.2', 1), - ('1.1', '1.2.2', -1), - ('1.2', '1.1', 1), - ('1.2.1', '1.2.2', -1), - ('1.2.2', '1.2', 1), - ('1.2', '1.2.2', -1), - ('0.4.0', '0.4', 0), - ('1.13++', '5.5.kw', ValueError), - ) - - for v1, v2, wanted in versions: - try: - res = StrictVersion(v1)._cmp(StrictVersion(v2)) - except ValueError: - if wanted is ValueError: - continue - else: - raise AssertionError(f"cmp({v1}, {v2}) shouldn't raise ValueError") - assert res == wanted, f'cmp({v1}, {v2}) should be {wanted}, got {res}' - res = StrictVersion(v1)._cmp(v2) - assert res == wanted, f'cmp({v1}, {v2}) should be {wanted}, got {res}' - res = StrictVersion(v1)._cmp(object()) - assert res is NotImplemented, ( - f'cmp({v1}, {v2}) should be NotImplemented, got {res}' - ) - - def test_cmp(self): - versions = ( - ('1.5.1', '1.5.2b2', -1), - ('161', '3.10a', 1), - ('8.02', '8.02', 0), - ('3.4j', '1996.07.12', -1), - ('3.2.pl0', '3.1.1.6', 1), - ('2g6', '11g', -1), - ('0.960923', '2.2beta29', -1), - ('1.13++', '5.5.kw', -1), - ) - - for v1, v2, wanted in versions: - res = LooseVersion(v1)._cmp(LooseVersion(v2)) - assert res == wanted, f'cmp({v1}, {v2}) should be {wanted}, got {res}' - res = LooseVersion(v1)._cmp(v2) - assert res == wanted, f'cmp({v1}, {v2}) should be {wanted}, got {res}' - res = LooseVersion(v1)._cmp(object()) - assert res is NotImplemented, ( - f'cmp({v1}, {v2}) should be NotImplemented, got {res}' - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_versionpredicate.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/test_versionpredicate.py deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/unix_compat.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/unix_compat.py deleted file mode 100644 index a5d9ee4..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/tests/unix_compat.py +++ /dev/null @@ -1,17 +0,0 @@ -import sys - -try: - import grp - import pwd -except ImportError: - grp = pwd = None - -import pytest - -UNIX_ID_SUPPORT = grp and pwd -UID_0_SUPPORT = UNIX_ID_SUPPORT and sys.platform != "cygwin" - -require_unix_id = pytest.mark.skipif( - not UNIX_ID_SUPPORT, reason="Requires grp and pwd support" -) -require_uid_0 = pytest.mark.skipif(not UID_0_SUPPORT, reason="Requires UID 0 support") diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/text_file.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/text_file.py deleted file mode 100644 index 89d9048..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/text_file.py +++ /dev/null @@ -1,286 +0,0 @@ -"""text_file - -provides the TextFile class, which gives an interface to text files -that (optionally) takes care of stripping comments, ignoring blank -lines, and joining lines with backslashes.""" - -import sys - - -class TextFile: - """Provides a file-like object that takes care of all the things you - commonly want to do when processing a text file that has some - line-by-line syntax: strip comments (as long as "#" is your - comment character), skip blank lines, join adjacent lines by - escaping the newline (ie. backslash at end of line), strip - leading and/or trailing whitespace. All of these are optional - and independently controllable. - - Provides a 'warn()' method so you can generate warning messages that - report physical line number, even if the logical line in question - spans multiple physical lines. Also provides 'unreadline()' for - implementing line-at-a-time lookahead. - - Constructor is called as: - - TextFile (filename=None, file=None, **options) - - It bombs (RuntimeError) if both 'filename' and 'file' are None; - 'filename' should be a string, and 'file' a file object (or - something that provides 'readline()' and 'close()' methods). It is - recommended that you supply at least 'filename', so that TextFile - can include it in warning messages. If 'file' is not supplied, - TextFile creates its own using 'io.open()'. - - The options are all boolean, and affect the value returned by - 'readline()': - strip_comments [default: true] - strip from "#" to end-of-line, as well as any whitespace - leading up to the "#" -- unless it is escaped by a backslash - lstrip_ws [default: false] - strip leading whitespace from each line before returning it - rstrip_ws [default: true] - strip trailing whitespace (including line terminator!) from - each line before returning it - skip_blanks [default: true} - skip lines that are empty *after* stripping comments and - whitespace. (If both lstrip_ws and rstrip_ws are false, - then some lines may consist of solely whitespace: these will - *not* be skipped, even if 'skip_blanks' is true.) - join_lines [default: false] - if a backslash is the last non-newline character on a line - after stripping comments and whitespace, join the following line - to it to form one "logical line"; if N consecutive lines end - with a backslash, then N+1 physical lines will be joined to - form one logical line. - collapse_join [default: false] - strip leading whitespace from lines that are joined to their - predecessor; only matters if (join_lines and not lstrip_ws) - errors [default: 'strict'] - error handler used to decode the file content - - Note that since 'rstrip_ws' can strip the trailing newline, the - semantics of 'readline()' must differ from those of the builtin file - object's 'readline()' method! In particular, 'readline()' returns - None for end-of-file: an empty string might just be a blank line (or - an all-whitespace line), if 'rstrip_ws' is true but 'skip_blanks' is - not.""" - - default_options = { - 'strip_comments': 1, - 'skip_blanks': 1, - 'lstrip_ws': 0, - 'rstrip_ws': 1, - 'join_lines': 0, - 'collapse_join': 0, - 'errors': 'strict', - } - - def __init__(self, filename=None, file=None, **options): - """Construct a new TextFile object. At least one of 'filename' - (a string) and 'file' (a file-like object) must be supplied. - They keyword argument options are described above and affect - the values returned by 'readline()'.""" - if filename is None and file is None: - raise RuntimeError( - "you must supply either or both of 'filename' and 'file'" - ) - - # set values for all options -- either from client option hash - # or fallback to default_options - for opt in self.default_options.keys(): - if opt in options: - setattr(self, opt, options[opt]) - else: - setattr(self, opt, self.default_options[opt]) - - # sanity check client option hash - for opt in options.keys(): - if opt not in self.default_options: - raise KeyError(f"invalid TextFile option '{opt}'") - - if file is None: - self.open(filename) - else: - self.filename = filename - self.file = file - self.current_line = 0 # assuming that file is at BOF! - - # 'linebuf' is a stack of lines that will be emptied before we - # actually read from the file; it's only populated by an - # 'unreadline()' operation - self.linebuf = [] - - def open(self, filename): - """Open a new file named 'filename'. This overrides both the - 'filename' and 'file' arguments to the constructor.""" - self.filename = filename - self.file = open(self.filename, errors=self.errors, encoding='utf-8') - self.current_line = 0 - - def close(self): - """Close the current file and forget everything we know about it - (filename, current line number).""" - file = self.file - self.file = None - self.filename = None - self.current_line = None - file.close() - - def gen_error(self, msg, line=None): - outmsg = [] - if line is None: - line = self.current_line - outmsg.append(self.filename + ", ") - if isinstance(line, (list, tuple)): - outmsg.append("lines {}-{}: ".format(*line)) - else: - outmsg.append(f"line {int(line)}: ") - outmsg.append(str(msg)) - return "".join(outmsg) - - def error(self, msg, line=None): - raise ValueError("error: " + self.gen_error(msg, line)) - - def warn(self, msg, line=None): - """Print (to stderr) a warning message tied to the current logical - line in the current file. If the current logical line in the - file spans multiple physical lines, the warning refers to the - whole range, eg. "lines 3-5". If 'line' supplied, it overrides - the current line number; it may be a list or tuple to indicate a - range of physical lines, or an integer for a single physical - line.""" - sys.stderr.write("warning: " + self.gen_error(msg, line) + "\n") - - def readline(self): # noqa: C901 - """Read and return a single logical line from the current file (or - from an internal buffer if lines have previously been "unread" - with 'unreadline()'). If the 'join_lines' option is true, this - may involve reading multiple physical lines concatenated into a - single string. Updates the current line number, so calling - 'warn()' after 'readline()' emits a warning about the physical - line(s) just read. Returns None on end-of-file, since the empty - string can occur if 'rstrip_ws' is true but 'strip_blanks' is - not.""" - # If any "unread" lines waiting in 'linebuf', return the top - # one. (We don't actually buffer read-ahead data -- lines only - # get put in 'linebuf' if the client explicitly does an - # 'unreadline()'. - if self.linebuf: - line = self.linebuf[-1] - del self.linebuf[-1] - return line - - buildup_line = '' - - while True: - # read the line, make it None if EOF - line = self.file.readline() - if line == '': - line = None - - if self.strip_comments and line: - # Look for the first "#" in the line. If none, never - # mind. If we find one and it's the first character, or - # is not preceded by "\", then it starts a comment -- - # strip the comment, strip whitespace before it, and - # carry on. Otherwise, it's just an escaped "#", so - # unescape it (and any other escaped "#"'s that might be - # lurking in there) and otherwise leave the line alone. - - pos = line.find("#") - if pos == -1: # no "#" -- no comments - pass - - # It's definitely a comment -- either "#" is the first - # character, or it's elsewhere and unescaped. - elif pos == 0 or line[pos - 1] != "\\": - # Have to preserve the trailing newline, because it's - # the job of a later step (rstrip_ws) to remove it -- - # and if rstrip_ws is false, we'd better preserve it! - # (NB. this means that if the final line is all comment - # and has no trailing newline, we will think that it's - # EOF; I think that's OK.) - eol = (line[-1] == '\n') and '\n' or '' - line = line[0:pos] + eol - - # If all that's left is whitespace, then skip line - # *now*, before we try to join it to 'buildup_line' -- - # that way constructs like - # hello \\ - # # comment that should be ignored - # there - # result in "hello there". - if line.strip() == "": - continue - else: # it's an escaped "#" - line = line.replace("\\#", "#") - - # did previous line end with a backslash? then accumulate - if self.join_lines and buildup_line: - # oops: end of file - if line is None: - self.warn("continuation line immediately precedes end-of-file") - return buildup_line - - if self.collapse_join: - line = line.lstrip() - line = buildup_line + line - - # careful: pay attention to line number when incrementing it - if isinstance(self.current_line, list): - self.current_line[1] = self.current_line[1] + 1 - else: - self.current_line = [self.current_line, self.current_line + 1] - # just an ordinary line, read it as usual - else: - if line is None: # eof - return None - - # still have to be careful about incrementing the line number! - if isinstance(self.current_line, list): - self.current_line = self.current_line[1] + 1 - else: - self.current_line = self.current_line + 1 - - # strip whitespace however the client wants (leading and - # trailing, or one or the other, or neither) - if self.lstrip_ws and self.rstrip_ws: - line = line.strip() - elif self.lstrip_ws: - line = line.lstrip() - elif self.rstrip_ws: - line = line.rstrip() - - # blank line (whether we rstrip'ed or not)? skip to next line - # if appropriate - if line in ('', '\n') and self.skip_blanks: - continue - - if self.join_lines: - if line[-1] == '\\': - buildup_line = line[:-1] - continue - - if line[-2:] == '\\\n': - buildup_line = line[0:-2] + '\n' - continue - - # well, I guess there's some actual content there: return it - return line - - def readlines(self): - """Read and return the list of all logical lines remaining in the - current file.""" - lines = [] - while True: - line = self.readline() - if line is None: - return lines - lines.append(line) - - def unreadline(self, line): - """Push 'line' (a string) onto an internal buffer that will be - checked by future 'readline()' calls. Handy for implementing - a parser with line-at-a-time lookahead.""" - self.linebuf.append(line) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/unixccompiler.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/unixccompiler.py deleted file mode 100644 index 20b8ce6..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/unixccompiler.py +++ /dev/null @@ -1,9 +0,0 @@ -import importlib - -from .compilers.C import unix - -UnixCCompiler = unix.Compiler - -# ensure import of unixccompiler implies ccompiler imported -# (pypa/setuptools#4871) -importlib.import_module('distutils.ccompiler') diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/util.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/util.py deleted file mode 100644 index 6dbe049..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/util.py +++ /dev/null @@ -1,518 +0,0 @@ -"""distutils.util - -Miscellaneous utility functions -- anything that doesn't fit into -one of the other *util.py modules. -""" - -from __future__ import annotations - -import functools -import importlib.util -import os -import pathlib -import re -import string -import subprocess -import sys -import sysconfig -import tempfile -from collections.abc import Callable, Iterable, Mapping -from typing import TYPE_CHECKING, AnyStr - -from jaraco.functools import pass_none - -from ._log import log -from ._modified import newer -from .errors import DistutilsByteCompileError, DistutilsPlatformError -from .spawn import spawn - -if TYPE_CHECKING: - from typing_extensions import TypeVarTuple, Unpack - - _Ts = TypeVarTuple("_Ts") - - -def get_host_platform() -> str: - """ - Return a string that identifies the current platform. Use this - function to distinguish platform-specific build directories and - platform-specific built distributions. - """ - - # This function initially exposed platforms as defined in Python 3.9 - # even with older Python versions when distutils was split out. - # Now it delegates to stdlib sysconfig. - - return sysconfig.get_platform() - - -def get_platform() -> str: - if os.name == 'nt': - TARGET_TO_PLAT = { - 'x86': 'win32', - 'x64': 'win-amd64', - 'arm': 'win-arm32', - 'arm64': 'win-arm64', - } - target = os.environ.get('VSCMD_ARG_TGT_ARCH') - return TARGET_TO_PLAT.get(target) or get_host_platform() - return get_host_platform() - - -if sys.platform == 'darwin': - _syscfg_macosx_ver = None # cache the version pulled from sysconfig -MACOSX_VERSION_VAR = 'MACOSX_DEPLOYMENT_TARGET' - - -def _clear_cached_macosx_ver(): - """For testing only. Do not call.""" - global _syscfg_macosx_ver - _syscfg_macosx_ver = None - - -def get_macosx_target_ver_from_syscfg(): - """Get the version of macOS latched in the Python interpreter configuration. - Returns the version as a string or None if can't obtain one. Cached.""" - global _syscfg_macosx_ver - if _syscfg_macosx_ver is None: - from distutils import sysconfig - - ver = sysconfig.get_config_var(MACOSX_VERSION_VAR) or '' - if ver: - _syscfg_macosx_ver = ver - return _syscfg_macosx_ver - - -def get_macosx_target_ver(): - """Return the version of macOS for which we are building. - - The target version defaults to the version in sysconfig latched at time - the Python interpreter was built, unless overridden by an environment - variable. If neither source has a value, then None is returned""" - - syscfg_ver = get_macosx_target_ver_from_syscfg() - env_ver = os.environ.get(MACOSX_VERSION_VAR) - - if env_ver: - # Validate overridden version against sysconfig version, if have both. - # Ensure that the deployment target of the build process is not less - # than 10.3 if the interpreter was built for 10.3 or later. This - # ensures extension modules are built with correct compatibility - # values, specifically LDSHARED which can use - # '-undefined dynamic_lookup' which only works on >= 10.3. - if ( - syscfg_ver - and split_version(syscfg_ver) >= [10, 3] - and split_version(env_ver) < [10, 3] - ): - my_msg = ( - '$' + MACOSX_VERSION_VAR + ' mismatch: ' - f'now "{env_ver}" but "{syscfg_ver}" during configure; ' - 'must use 10.3 or later' - ) - raise DistutilsPlatformError(my_msg) - return env_ver - return syscfg_ver - - -def split_version(s: str) -> list[int]: - """Convert a dot-separated string into a list of numbers for comparisons""" - return [int(n) for n in s.split('.')] - - -@pass_none -def convert_path(pathname: str | os.PathLike[str]) -> str: - r""" - Allow for pathlib.Path inputs, coax to a native path string. - - If None is passed, will just pass it through as - Setuptools relies on this behavior. - - >>> convert_path(None) is None - True - - Removes empty paths. - - >>> convert_path('foo/./bar').replace('\\', '/') - 'foo/bar' - """ - return os.fspath(pathlib.PurePath(pathname)) - - -def change_root( - new_root: AnyStr | os.PathLike[AnyStr], pathname: AnyStr | os.PathLike[AnyStr] -) -> AnyStr: - """Return 'pathname' with 'new_root' prepended. If 'pathname' is - relative, this is equivalent to "os.path.join(new_root,pathname)". - Otherwise, it requires making 'pathname' relative and then joining the - two, which is tricky on DOS/Windows and Mac OS. - """ - if os.name == 'posix': - if not os.path.isabs(pathname): - return os.path.join(new_root, pathname) - else: - return os.path.join(new_root, pathname[1:]) - - elif os.name == 'nt': - (drive, path) = os.path.splitdrive(pathname) - if path[0] == os.sep: - path = path[1:] - return os.path.join(new_root, path) - - raise DistutilsPlatformError(f"nothing known about platform '{os.name}'") - - -@functools.lru_cache -def check_environ() -> None: - """Ensure that 'os.environ' has all the environment variables we - guarantee that users can use in config files, command-line options, - etc. Currently this includes: - HOME - user's home directory (Unix only) - PLAT - description of the current platform, including hardware - and OS (see 'get_platform()') - """ - if os.name == 'posix' and 'HOME' not in os.environ: - try: - import pwd - - os.environ['HOME'] = pwd.getpwuid(os.getuid())[5] - except (ImportError, KeyError): - # bpo-10496: if the current user identifier doesn't exist in the - # password database, do nothing - pass - - if 'PLAT' not in os.environ: - os.environ['PLAT'] = get_platform() - - -def subst_vars(s, local_vars: Mapping[str, object]) -> str: - """ - Perform variable substitution on 'string'. - Variables are indicated by format-style braces ("{var}"). - Variable is substituted by the value found in the 'local_vars' - dictionary or in 'os.environ' if it's not in 'local_vars'. - 'os.environ' is first checked/augmented to guarantee that it contains - certain values: see 'check_environ()'. Raise ValueError for any - variables not found in either 'local_vars' or 'os.environ'. - """ - check_environ() - lookup = dict(os.environ) - lookup.update((name, str(value)) for name, value in local_vars.items()) - try: - return _subst_compat(s).format_map(lookup) - except KeyError as var: - raise ValueError(f"invalid variable {var}") - - -def _subst_compat(s): - """ - Replace shell/Perl-style variable substitution with - format-style. For compatibility. - """ - - def _subst(match): - return f'{{{match.group(1)}}}' - - repl = re.sub(r'\$([a-zA-Z_][a-zA-Z_0-9]*)', _subst, s) - if repl != s: - import warnings - - warnings.warn( - "shell/Perl-style substitutions are deprecated", - DeprecationWarning, - ) - return repl - - -def grok_environment_error(exc: object, prefix: str = "error: ") -> str: - # Function kept for backward compatibility. - # Used to try clever things with EnvironmentErrors, - # but nowadays str(exception) produces good messages. - return prefix + str(exc) - - -# Needed by 'split_quoted()' -_wordchars_re = _squote_re = _dquote_re = None - - -def _init_regex(): - global _wordchars_re, _squote_re, _dquote_re - _wordchars_re = re.compile(rf'[^\\\'\"{string.whitespace} ]*') - _squote_re = re.compile(r"'(?:[^'\\]|\\.)*'") - _dquote_re = re.compile(r'"(?:[^"\\]|\\.)*"') - - -def split_quoted(s: str) -> list[str]: - """Split a string up according to Unix shell-like rules for quotes and - backslashes. In short: words are delimited by spaces, as long as those - spaces are not escaped by a backslash, or inside a quoted string. - Single and double quotes are equivalent, and the quote characters can - be backslash-escaped. The backslash is stripped from any two-character - escape sequence, leaving only the escaped character. The quote - characters are stripped from any quoted string. Returns a list of - words. - """ - - # This is a nice algorithm for splitting up a single string, since it - # doesn't require character-by-character examination. It was a little - # bit of a brain-bender to get it working right, though... - if _wordchars_re is None: - _init_regex() - - s = s.strip() - words = [] - pos = 0 - - while s: - m = _wordchars_re.match(s, pos) - end = m.end() - if end == len(s): - words.append(s[:end]) - break - - if s[end] in string.whitespace: - # unescaped, unquoted whitespace: now - # we definitely have a word delimiter - words.append(s[:end]) - s = s[end:].lstrip() - pos = 0 - - elif s[end] == '\\': - # preserve whatever is being escaped; - # will become part of the current word - s = s[:end] + s[end + 1 :] - pos = end + 1 - - else: - if s[end] == "'": # slurp singly-quoted string - m = _squote_re.match(s, end) - elif s[end] == '"': # slurp doubly-quoted string - m = _dquote_re.match(s, end) - else: - raise RuntimeError(f"this can't happen (bad char '{s[end]}')") - - if m is None: - raise ValueError(f"bad string (mismatched {s[end]} quotes?)") - - (beg, end) = m.span() - s = s[:beg] + s[beg + 1 : end - 1] + s[end:] - pos = m.end() - 2 - - if pos >= len(s): - words.append(s) - break - - return words - - -# split_quoted () - - -def execute( - func: Callable[[Unpack[_Ts]], object], - args: tuple[Unpack[_Ts]], - msg: object = None, - verbose: bool = False, - dry_run: bool = False, -) -> None: - """ - Perform some action that affects the outside world (e.g. by - writing to the filesystem). Such actions are special because they - are disabled by the 'dry_run' flag. This method handles that - complication; simply supply the - function to call and an argument tuple for it (to embody the - "external action" being performed) and an optional message to - emit. - """ - if msg is None: - msg = f"{func.__name__}{args!r}" - if msg[-2:] == ',)': # correct for singleton tuple - msg = msg[0:-2] + ')' - - log.info(msg) - if not dry_run: - func(*args) - - -def strtobool(val: str) -> bool: - """Convert a string representation of truth to true (1) or false (0). - - True values are 'y', 'yes', 't', 'true', 'on', and '1'; false values - are 'n', 'no', 'f', 'false', 'off', and '0'. Raises ValueError if - 'val' is anything else. - """ - val = val.lower() - if val in ('y', 'yes', 't', 'true', 'on', '1'): - return True - elif val in ('n', 'no', 'f', 'false', 'off', '0'): - return False - else: - raise ValueError(f"invalid truth value {val!r}") - - -def byte_compile( # noqa: C901 - py_files: Iterable[str], - optimize: int = 0, - force: bool = False, - prefix: str | None = None, - base_dir: str | None = None, - verbose: bool = True, - dry_run: bool = False, - direct: bool | None = None, -) -> None: - """Byte-compile a collection of Python source files to .pyc - files in a __pycache__ subdirectory. 'py_files' is a list - of files to compile; any files that don't end in ".py" are silently - skipped. 'optimize' must be one of the following: - 0 - don't optimize - 1 - normal optimization (like "python -O") - 2 - extra optimization (like "python -OO") - If 'force' is true, all files are recompiled regardless of - timestamps. - - The source filename encoded in each bytecode file defaults to the - filenames listed in 'py_files'; you can modify these with 'prefix' and - 'basedir'. 'prefix' is a string that will be stripped off of each - source filename, and 'base_dir' is a directory name that will be - prepended (after 'prefix' is stripped). You can supply either or both - (or neither) of 'prefix' and 'base_dir', as you wish. - - If 'dry_run' is true, doesn't actually do anything that would - affect the filesystem. - - Byte-compilation is either done directly in this interpreter process - with the standard py_compile module, or indirectly by writing a - temporary script and executing it. Normally, you should let - 'byte_compile()' figure out to use direct compilation or not (see - the source for details). The 'direct' flag is used by the script - generated in indirect mode; unless you know what you're doing, leave - it set to None. - """ - - # nothing is done if sys.dont_write_bytecode is True - if sys.dont_write_bytecode: - raise DistutilsByteCompileError('byte-compiling is disabled.') - - # First, if the caller didn't force us into direct or indirect mode, - # figure out which mode we should be in. We take a conservative - # approach: choose direct mode *only* if the current interpreter is - # in debug mode and optimize is 0. If we're not in debug mode (-O - # or -OO), we don't know which level of optimization this - # interpreter is running with, so we can't do direct - # byte-compilation and be certain that it's the right thing. Thus, - # always compile indirectly if the current interpreter is in either - # optimize mode, or if either optimization level was requested by - # the caller. - if direct is None: - direct = __debug__ and optimize == 0 - - # "Indirect" byte-compilation: write a temporary script and then - # run it with the appropriate flags. - if not direct: - (script_fd, script_name) = tempfile.mkstemp(".py") - log.info("writing byte-compilation script '%s'", script_name) - if not dry_run: - script = os.fdopen(script_fd, "w", encoding='utf-8') - - with script: - script.write( - """\ -from distutils.util import byte_compile -files = [ -""" - ) - - # XXX would be nice to write absolute filenames, just for - # safety's sake (script should be more robust in the face of - # chdir'ing before running it). But this requires abspath'ing - # 'prefix' as well, and that breaks the hack in build_lib's - # 'byte_compile()' method that carefully tacks on a trailing - # slash (os.sep really) to make sure the prefix here is "just - # right". This whole prefix business is rather delicate -- the - # problem is that it's really a directory, but I'm treating it - # as a dumb string, so trailing slashes and so forth matter. - - script.write(",\n".join(map(repr, py_files)) + "]\n") - script.write( - f""" -byte_compile(files, optimize={optimize!r}, force={force!r}, - prefix={prefix!r}, base_dir={base_dir!r}, - verbose={verbose!r}, dry_run=False, - direct=True) -""" - ) - - cmd = [sys.executable] - cmd.extend(subprocess._optim_args_from_interpreter_flags()) - cmd.append(script_name) - spawn(cmd, dry_run=dry_run) - execute(os.remove, (script_name,), f"removing {script_name}", dry_run=dry_run) - - # "Direct" byte-compilation: use the py_compile module to compile - # right here, right now. Note that the script generated in indirect - # mode simply calls 'byte_compile()' in direct mode, a weird sort of - # cross-process recursion. Hey, it works! - else: - from py_compile import compile - - for file in py_files: - if file[-3:] != ".py": - # This lets us be lazy and not filter filenames in - # the "install_lib" command. - continue - - # Terminology from the py_compile module: - # cfile - byte-compiled file - # dfile - purported source filename (same as 'file' by default) - if optimize >= 0: - opt = '' if optimize == 0 else optimize - cfile = importlib.util.cache_from_source(file, optimization=opt) - else: - cfile = importlib.util.cache_from_source(file) - dfile = file - if prefix: - if file[: len(prefix)] != prefix: - raise ValueError( - f"invalid prefix: filename {file!r} doesn't start with {prefix!r}" - ) - dfile = dfile[len(prefix) :] - if base_dir: - dfile = os.path.join(base_dir, dfile) - - cfile_base = os.path.basename(cfile) - if direct: - if force or newer(file, cfile): - log.info("byte-compiling %s to %s", file, cfile_base) - if not dry_run: - compile(file, cfile, dfile) - else: - log.debug("skipping byte-compilation of %s to %s", file, cfile_base) - - -def rfc822_escape(header: str) -> str: - """Return a version of the string escaped for inclusion in an - RFC-822 header, by ensuring there are 8 spaces space after each newline. - """ - indent = 8 * " " - lines = header.splitlines(keepends=True) - - # Emulate the behaviour of `str.split` - # (the terminal line break in `splitlines` does not result in an extra line): - ends_in_newline = lines and lines[-1].splitlines()[0] != lines[-1] - suffix = indent if ends_in_newline else "" - - return indent.join(lines) + suffix - - -def is_mingw() -> bool: - """Returns True if the current platform is mingw. - - Python compiled with Mingw-w64 has sys.platform == 'win32' and - get_platform() starts with 'mingw'. - """ - return sys.platform == 'win32' and get_platform().startswith('mingw') - - -def is_freethreaded(): - """Return True if the Python interpreter is built with free threading support.""" - return bool(sysconfig.get_config_var('Py_GIL_DISABLED')) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/version.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/version.py deleted file mode 100644 index 2223ee9..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/version.py +++ /dev/null @@ -1,348 +0,0 @@ -# -# distutils/version.py -# -# Implements multiple version numbering conventions for the -# Python Module Distribution Utilities. -# -# $Id$ -# - -"""Provides classes to represent module version numbers (one class for -each style of version numbering). There are currently two such classes -implemented: StrictVersion and LooseVersion. - -Every version number class implements the following interface: - * the 'parse' method takes a string and parses it to some internal - representation; if the string is an invalid version number, - 'parse' raises a ValueError exception - * the class constructor takes an optional string argument which, - if supplied, is passed to 'parse' - * __str__ reconstructs the string that was passed to 'parse' (or - an equivalent string -- ie. one that will generate an equivalent - version number instance) - * __repr__ generates Python code to recreate the version number instance - * _cmp compares the current instance with either another instance - of the same class or a string (which will be parsed to an instance - of the same class, thus must follow the same rules) -""" - -import contextlib -import re -import warnings - - -@contextlib.contextmanager -def suppress_known_deprecation(): - with warnings.catch_warnings(record=True) as ctx: - warnings.filterwarnings( - action='default', - category=DeprecationWarning, - message="distutils Version classes are deprecated.", - ) - yield ctx - - -class Version: - """Abstract base class for version numbering classes. Just provides - constructor (__init__) and reproducer (__repr__), because those - seem to be the same for all version numbering classes; and route - rich comparisons to _cmp. - """ - - def __init__(self, vstring=None): - if vstring: - self.parse(vstring) - warnings.warn( - "distutils Version classes are deprecated. Use packaging.version instead.", - DeprecationWarning, - stacklevel=2, - ) - - def __repr__(self): - return f"{self.__class__.__name__} ('{self}')" - - def __eq__(self, other): - c = self._cmp(other) - if c is NotImplemented: - return c - return c == 0 - - def __lt__(self, other): - c = self._cmp(other) - if c is NotImplemented: - return c - return c < 0 - - def __le__(self, other): - c = self._cmp(other) - if c is NotImplemented: - return c - return c <= 0 - - def __gt__(self, other): - c = self._cmp(other) - if c is NotImplemented: - return c - return c > 0 - - def __ge__(self, other): - c = self._cmp(other) - if c is NotImplemented: - return c - return c >= 0 - - -# Interface for version-number classes -- must be implemented -# by the following classes (the concrete ones -- Version should -# be treated as an abstract class). -# __init__ (string) - create and take same action as 'parse' -# (string parameter is optional) -# parse (string) - convert a string representation to whatever -# internal representation is appropriate for -# this style of version numbering -# __str__ (self) - convert back to a string; should be very similar -# (if not identical to) the string supplied to parse -# __repr__ (self) - generate Python code to recreate -# the instance -# _cmp (self, other) - compare two version numbers ('other' may -# be an unparsed version string, or another -# instance of your version class) - - -class StrictVersion(Version): - """Version numbering for anal retentives and software idealists. - Implements the standard interface for version number classes as - described above. A version number consists of two or three - dot-separated numeric components, with an optional "pre-release" tag - on the end. The pre-release tag consists of the letter 'a' or 'b' - followed by a number. If the numeric components of two version - numbers are equal, then one with a pre-release tag will always - be deemed earlier (lesser) than one without. - - The following are valid version numbers (shown in the order that - would be obtained by sorting according to the supplied cmp function): - - 0.4 0.4.0 (these two are equivalent) - 0.4.1 - 0.5a1 - 0.5b3 - 0.5 - 0.9.6 - 1.0 - 1.0.4a3 - 1.0.4b1 - 1.0.4 - - The following are examples of invalid version numbers: - - 1 - 2.7.2.2 - 1.3.a4 - 1.3pl1 - 1.3c4 - - The rationale for this version numbering system will be explained - in the distutils documentation. - """ - - version_re = re.compile( - r'^(\d+) \. (\d+) (\. (\d+))? ([ab](\d+))?$', re.VERBOSE | re.ASCII - ) - - def parse(self, vstring): - match = self.version_re.match(vstring) - if not match: - raise ValueError(f"invalid version number '{vstring}'") - - (major, minor, patch, prerelease, prerelease_num) = match.group(1, 2, 4, 5, 6) - - if patch: - self.version = tuple(map(int, [major, minor, patch])) - else: - self.version = tuple(map(int, [major, minor])) + (0,) - - if prerelease: - self.prerelease = (prerelease[0], int(prerelease_num)) - else: - self.prerelease = None - - def __str__(self): - if self.version[2] == 0: - vstring = '.'.join(map(str, self.version[0:2])) - else: - vstring = '.'.join(map(str, self.version)) - - if self.prerelease: - vstring = vstring + self.prerelease[0] + str(self.prerelease[1]) - - return vstring - - def _cmp(self, other): - if isinstance(other, str): - with suppress_known_deprecation(): - other = StrictVersion(other) - elif not isinstance(other, StrictVersion): - return NotImplemented - - if self.version == other.version: - # versions match; pre-release drives the comparison - return self._cmp_prerelease(other) - - return -1 if self.version < other.version else 1 - - def _cmp_prerelease(self, other): - """ - case 1: self has prerelease, other doesn't; other is greater - case 2: self doesn't have prerelease, other does: self is greater - case 3: both or neither have prerelease: compare them! - """ - if self.prerelease and not other.prerelease: - return -1 - elif not self.prerelease and other.prerelease: - return 1 - - if self.prerelease == other.prerelease: - return 0 - elif self.prerelease < other.prerelease: - return -1 - else: - return 1 - - -# end class StrictVersion - - -# The rules according to Greg Stein: -# 1) a version number has 1 or more numbers separated by a period or by -# sequences of letters. If only periods, then these are compared -# left-to-right to determine an ordering. -# 2) sequences of letters are part of the tuple for comparison and are -# compared lexicographically -# 3) recognize the numeric components may have leading zeroes -# -# The LooseVersion class below implements these rules: a version number -# string is split up into a tuple of integer and string components, and -# comparison is a simple tuple comparison. This means that version -# numbers behave in a predictable and obvious way, but a way that might -# not necessarily be how people *want* version numbers to behave. There -# wouldn't be a problem if people could stick to purely numeric version -# numbers: just split on period and compare the numbers as tuples. -# However, people insist on putting letters into their version numbers; -# the most common purpose seems to be: -# - indicating a "pre-release" version -# ('alpha', 'beta', 'a', 'b', 'pre', 'p') -# - indicating a post-release patch ('p', 'pl', 'patch') -# but of course this can't cover all version number schemes, and there's -# no way to know what a programmer means without asking him. -# -# The problem is what to do with letters (and other non-numeric -# characters) in a version number. The current implementation does the -# obvious and predictable thing: keep them as strings and compare -# lexically within a tuple comparison. This has the desired effect if -# an appended letter sequence implies something "post-release": -# eg. "0.99" < "0.99pl14" < "1.0", and "5.001" < "5.001m" < "5.002". -# -# However, if letters in a version number imply a pre-release version, -# the "obvious" thing isn't correct. Eg. you would expect that -# "1.5.1" < "1.5.2a2" < "1.5.2", but under the tuple/lexical comparison -# implemented here, this just isn't so. -# -# Two possible solutions come to mind. The first is to tie the -# comparison algorithm to a particular set of semantic rules, as has -# been done in the StrictVersion class above. This works great as long -# as everyone can go along with bondage and discipline. Hopefully a -# (large) subset of Python module programmers will agree that the -# particular flavour of bondage and discipline provided by StrictVersion -# provides enough benefit to be worth using, and will submit their -# version numbering scheme to its domination. The free-thinking -# anarchists in the lot will never give in, though, and something needs -# to be done to accommodate them. -# -# Perhaps a "moderately strict" version class could be implemented that -# lets almost anything slide (syntactically), and makes some heuristic -# assumptions about non-digits in version number strings. This could -# sink into special-case-hell, though; if I was as talented and -# idiosyncratic as Larry Wall, I'd go ahead and implement a class that -# somehow knows that "1.2.1" < "1.2.2a2" < "1.2.2" < "1.2.2pl3", and is -# just as happy dealing with things like "2g6" and "1.13++". I don't -# think I'm smart enough to do it right though. -# -# In any case, I've coded the test suite for this module (see -# ../test/test_version.py) specifically to fail on things like comparing -# "1.2a2" and "1.2". That's not because the *code* is doing anything -# wrong, it's because the simple, obvious design doesn't match my -# complicated, hairy expectations for real-world version numbers. It -# would be a snap to fix the test suite to say, "Yep, LooseVersion does -# the Right Thing" (ie. the code matches the conception). But I'd rather -# have a conception that matches common notions about version numbers. - - -class LooseVersion(Version): - """Version numbering for anarchists and software realists. - Implements the standard interface for version number classes as - described above. A version number consists of a series of numbers, - separated by either periods or strings of letters. When comparing - version numbers, the numeric components will be compared - numerically, and the alphabetic components lexically. The following - are all valid version numbers, in no particular order: - - 1.5.1 - 1.5.2b2 - 161 - 3.10a - 8.02 - 3.4j - 1996.07.12 - 3.2.pl0 - 3.1.1.6 - 2g6 - 11g - 0.960923 - 2.2beta29 - 1.13++ - 5.5.kw - 2.0b1pl0 - - In fact, there is no such thing as an invalid version number under - this scheme; the rules for comparison are simple and predictable, - but may not always give the results you want (for some definition - of "want"). - """ - - component_re = re.compile(r'(\d+ | [a-z]+ | \.)', re.VERBOSE) - - def parse(self, vstring): - # I've given up on thinking I can reconstruct the version string - # from the parsed tuple -- so I just store the string here for - # use by __str__ - self.vstring = vstring - components = [x for x in self.component_re.split(vstring) if x and x != '.'] - for i, obj in enumerate(components): - try: - components[i] = int(obj) - except ValueError: - pass - - self.version = components - - def __str__(self): - return self.vstring - - def __repr__(self): - return f"LooseVersion ('{self}')" - - def _cmp(self, other): - if isinstance(other, str): - other = LooseVersion(other) - elif not isinstance(other, LooseVersion): - return NotImplemented - - if self.version == other.version: - return 0 - if self.version < other.version: - return -1 - if self.version > other.version: - return 1 - - -# end class LooseVersion diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/versionpredicate.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/versionpredicate.py deleted file mode 100644 index fe31b0e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/versionpredicate.py +++ /dev/null @@ -1,175 +0,0 @@ -"""Module for parsing and testing package version predicate strings.""" - -import operator -import re - -from . import version - -re_validPackage = re.compile(r"(?i)^\s*([a-z_]\w*(?:\.[a-z_]\w*)*)(.*)", re.ASCII) -# (package) (rest) - -re_paren = re.compile(r"^\s*\((.*)\)\s*$") # (list) inside of parentheses -re_splitComparison = re.compile(r"^\s*(<=|>=|<|>|!=|==)\s*([^\s,]+)\s*$") -# (comp) (version) - - -def splitUp(pred): - """Parse a single version comparison. - - Return (comparison string, StrictVersion) - """ - res = re_splitComparison.match(pred) - if not res: - raise ValueError(f"bad package restriction syntax: {pred!r}") - comp, verStr = res.groups() - with version.suppress_known_deprecation(): - other = version.StrictVersion(verStr) - return (comp, other) - - -compmap = { - "<": operator.lt, - "<=": operator.le, - "==": operator.eq, - ">": operator.gt, - ">=": operator.ge, - "!=": operator.ne, -} - - -class VersionPredicate: - """Parse and test package version predicates. - - >>> v = VersionPredicate('pyepat.abc (>1.0, <3333.3a1, !=1555.1b3)') - - The `name` attribute provides the full dotted name that is given:: - - >>> v.name - 'pyepat.abc' - - The str() of a `VersionPredicate` provides a normalized - human-readable version of the expression:: - - >>> print(v) - pyepat.abc (> 1.0, < 3333.3a1, != 1555.1b3) - - The `satisfied_by()` method can be used to determine with a given - version number is included in the set described by the version - restrictions:: - - >>> v.satisfied_by('1.1') - True - >>> v.satisfied_by('1.4') - True - >>> v.satisfied_by('1.0') - False - >>> v.satisfied_by('4444.4') - False - >>> v.satisfied_by('1555.1b3') - False - - `VersionPredicate` is flexible in accepting extra whitespace:: - - >>> v = VersionPredicate(' pat( == 0.1 ) ') - >>> v.name - 'pat' - >>> v.satisfied_by('0.1') - True - >>> v.satisfied_by('0.2') - False - - If any version numbers passed in do not conform to the - restrictions of `StrictVersion`, a `ValueError` is raised:: - - >>> v = VersionPredicate('p1.p2.p3.p4(>=1.0, <=1.3a1, !=1.2zb3)') - Traceback (most recent call last): - ... - ValueError: invalid version number '1.2zb3' - - It the module or package name given does not conform to what's - allowed as a legal module or package name, `ValueError` is - raised:: - - >>> v = VersionPredicate('foo-bar') - Traceback (most recent call last): - ... - ValueError: expected parenthesized list: '-bar' - - >>> v = VersionPredicate('foo bar (12.21)') - Traceback (most recent call last): - ... - ValueError: expected parenthesized list: 'bar (12.21)' - - """ - - def __init__(self, versionPredicateStr): - """Parse a version predicate string.""" - # Fields: - # name: package name - # pred: list of (comparison string, StrictVersion) - - versionPredicateStr = versionPredicateStr.strip() - if not versionPredicateStr: - raise ValueError("empty package restriction") - match = re_validPackage.match(versionPredicateStr) - if not match: - raise ValueError(f"bad package name in {versionPredicateStr!r}") - self.name, paren = match.groups() - paren = paren.strip() - if paren: - match = re_paren.match(paren) - if not match: - raise ValueError(f"expected parenthesized list: {paren!r}") - str = match.groups()[0] - self.pred = [splitUp(aPred) for aPred in str.split(",")] - if not self.pred: - raise ValueError(f"empty parenthesized list in {versionPredicateStr!r}") - else: - self.pred = [] - - def __str__(self): - if self.pred: - seq = [cond + " " + str(ver) for cond, ver in self.pred] - return self.name + " (" + ", ".join(seq) + ")" - else: - return self.name - - def satisfied_by(self, version): - """True if version is compatible with all the predicates in self. - The parameter version must be acceptable to the StrictVersion - constructor. It may be either a string or StrictVersion. - """ - for cond, ver in self.pred: - if not compmap[cond](version, ver): - return False - return True - - -_provision_rx = None - - -def split_provision(value): - """Return the name and optional version number of a provision. - - The version number, if given, will be returned as a `StrictVersion` - instance, otherwise it will be `None`. - - >>> split_provision('mypkg') - ('mypkg', None) - >>> split_provision(' mypkg( 1.2 ) ') - ('mypkg', StrictVersion ('1.2')) - """ - global _provision_rx - if _provision_rx is None: - _provision_rx = re.compile( - r"([a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*)(?:\s*\(\s*([^)\s]+)\s*\))?$", re.ASCII - ) - value = value.strip() - m = _provision_rx.match(value) - if not m: - raise ValueError(f"illegal provides specification: {value!r}") - ver = m.group(2) or None - if ver: - with version.suppress_known_deprecation(): - ver = version.StrictVersion(ver) - return m.group(1), ver diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/zosccompiler.py b/llmlab/lib/python3.12/site-packages/setuptools/_distutils/zosccompiler.py deleted file mode 100644 index e49630a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_distutils/zosccompiler.py +++ /dev/null @@ -1,3 +0,0 @@ -from .compilers.C import zos - -zOSCCompiler = zos.Compiler diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_entry_points.py b/llmlab/lib/python3.12/site-packages/setuptools/_entry_points.py deleted file mode 100644 index e785fc7..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_entry_points.py +++ /dev/null @@ -1,90 +0,0 @@ -import functools -import itertools -import operator - -from jaraco.functools import pass_none -from jaraco.text import yield_lines -from more_itertools import consume - -from ._importlib import metadata -from ._itertools import ensure_unique -from .errors import OptionError - - -def ensure_valid(ep): - """ - Exercise one of the dynamic properties to trigger - the pattern match. - """ - try: - ep.extras - except (AttributeError, AssertionError) as ex: - # Why both? See https://github.com/python/importlib_metadata/issues/488 - msg = ( - f"Problems to parse {ep}.\nPlease ensure entry-point follows the spec: " - "https://packaging.python.org/en/latest/specifications/entry-points/" - ) - raise OptionError(msg) from ex - - -def load_group(value, group): - """ - Given a value of an entry point or series of entry points, - return each as an EntryPoint. - """ - # normalize to a single sequence of lines - lines = yield_lines(value) - text = f'[{group}]\n' + '\n'.join(lines) - return metadata.EntryPoints._from_text(text) - - -def by_group_and_name(ep): - return ep.group, ep.name - - -def validate(eps: metadata.EntryPoints): - """ - Ensure entry points are unique by group and name and validate each. - """ - consume(map(ensure_valid, ensure_unique(eps, key=by_group_and_name))) - return eps - - -@functools.singledispatch -def load(eps): - """ - Given a Distribution.entry_points, produce EntryPoints. - """ - groups = itertools.chain.from_iterable( - load_group(value, group) for group, value in eps.items() - ) - return validate(metadata.EntryPoints(groups)) - - -@load.register(str) -def _(eps): - r""" - >>> ep, = load('[console_scripts]\nfoo=bar') - >>> ep.group - 'console_scripts' - >>> ep.name - 'foo' - >>> ep.value - 'bar' - """ - return validate(metadata.EntryPoints(metadata.EntryPoints._from_text(eps))) - - -load.register(type(None), lambda x: x) - - -@pass_none -def render(eps: metadata.EntryPoints): - by_group = operator.attrgetter('group') - groups = itertools.groupby(sorted(eps, key=by_group), by_group) - - return '\n'.join(f'[{group}]\n{render_items(items)}\n' for group, items in groups) - - -def render_items(eps): - return '\n'.join(f'{ep.name} = {ep.value}' for ep in sorted(eps)) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_imp.py b/llmlab/lib/python3.12/site-packages/setuptools/_imp.py deleted file mode 100644 index f1d9f29..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_imp.py +++ /dev/null @@ -1,87 +0,0 @@ -""" -Re-implementation of find_module and get_frozen_object -from the deprecated imp module. -""" - -import importlib.machinery -import importlib.util -import os -import tokenize -from importlib.util import module_from_spec - -PY_SOURCE = 1 -PY_COMPILED = 2 -C_EXTENSION = 3 -C_BUILTIN = 6 -PY_FROZEN = 7 - - -def find_spec(module, paths): - finder = ( - importlib.machinery.PathFinder().find_spec - if isinstance(paths, list) - else importlib.util.find_spec - ) - return finder(module, paths) - - -def find_module(module, paths=None): - """Just like 'imp.find_module()', but with package support""" - spec = find_spec(module, paths) - if spec is None: - raise ImportError(f"Can't find {module}") - if not spec.has_location and hasattr(spec, 'submodule_search_locations'): - spec = importlib.util.spec_from_loader('__init__.py', spec.loader) - - kind = -1 - file = None - static = isinstance(spec.loader, type) - if ( - spec.origin == 'frozen' - or static - and issubclass(spec.loader, importlib.machinery.FrozenImporter) - ): - kind = PY_FROZEN - path = None # imp compabilty - suffix = mode = '' # imp compatibility - elif ( - spec.origin == 'built-in' - or static - and issubclass(spec.loader, importlib.machinery.BuiltinImporter) - ): - kind = C_BUILTIN - path = None # imp compabilty - suffix = mode = '' # imp compatibility - elif spec.has_location: - path = spec.origin - suffix = os.path.splitext(path)[1] - mode = 'r' if suffix in importlib.machinery.SOURCE_SUFFIXES else 'rb' - - if suffix in importlib.machinery.SOURCE_SUFFIXES: - kind = PY_SOURCE - file = tokenize.open(path) - elif suffix in importlib.machinery.BYTECODE_SUFFIXES: - kind = PY_COMPILED - file = open(path, 'rb') - elif suffix in importlib.machinery.EXTENSION_SUFFIXES: - kind = C_EXTENSION - - else: - path = None - suffix = mode = '' - - return file, path, (suffix, mode, kind) - - -def get_frozen_object(module, paths=None): - spec = find_spec(module, paths) - if not spec: - raise ImportError(f"Can't find {module}") - return spec.loader.get_code(module) - - -def get_module(module, paths, info): - spec = find_spec(module, paths) - if not spec: - raise ImportError(f"Can't find {module}") - return module_from_spec(spec) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_importlib.py b/llmlab/lib/python3.12/site-packages/setuptools/_importlib.py deleted file mode 100644 index ce0fd52..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_importlib.py +++ /dev/null @@ -1,9 +0,0 @@ -import sys - -if sys.version_info < (3, 10): - import importlib_metadata as metadata # pragma: no cover -else: - import importlib.metadata as metadata # noqa: F401 - - -import importlib.resources as resources # noqa: F401 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_itertools.py b/llmlab/lib/python3.12/site-packages/setuptools/_itertools.py deleted file mode 100644 index d6ca841..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_itertools.py +++ /dev/null @@ -1,23 +0,0 @@ -from more_itertools import consume # noqa: F401 - - -# copied from jaraco.itertools 6.1 -def ensure_unique(iterable, key=lambda x: x): - """ - Wrap an iterable to raise a ValueError if non-unique values are encountered. - - >>> list(ensure_unique('abc')) - ['a', 'b', 'c'] - >>> consume(ensure_unique('abca')) - Traceback (most recent call last): - ... - ValueError: Duplicate element 'a' encountered. - """ - seen = set() - seen_add = seen.add - for element in iterable: - k = key(element) - if k in seen: - raise ValueError(f"Duplicate element {element!r} encountered.") - seen_add(k) - yield element diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_normalization.py b/llmlab/lib/python3.12/site-packages/setuptools/_normalization.py deleted file mode 100644 index 0937a4f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_normalization.py +++ /dev/null @@ -1,179 +0,0 @@ -""" -Helpers for normalization as expected in wheel/sdist/module file names -and core metadata -""" - -import re -from typing import TYPE_CHECKING - -import packaging - -# https://packaging.python.org/en/latest/specifications/core-metadata/#name -_VALID_NAME = re.compile(r"^([A-Z0-9]|[A-Z0-9][A-Z0-9._-]*[A-Z0-9])$", re.I) -_UNSAFE_NAME_CHARS = re.compile(r"[^A-Z0-9._-]+", re.I) -_NON_ALPHANUMERIC = re.compile(r"[^A-Z0-9]+", re.I) -_PEP440_FALLBACK = re.compile(r"^v?(?P(?:[0-9]+!)?[0-9]+(?:\.[0-9]+)*)", re.I) - - -def safe_identifier(name: str) -> str: - """Make a string safe to be used as Python identifier. - >>> safe_identifier("12abc") - '_12abc' - >>> safe_identifier("__editable__.myns.pkg-78.9.3_local") - '__editable___myns_pkg_78_9_3_local' - """ - safe = re.sub(r'\W|^(?=\d)', '_', name) - assert safe.isidentifier() - return safe - - -def safe_name(component: str) -> str: - """Escape a component used as a project name according to Core Metadata. - >>> safe_name("hello world") - 'hello-world' - >>> safe_name("hello?world") - 'hello-world' - >>> safe_name("hello_world") - 'hello_world' - """ - # See pkg_resources.safe_name - return _UNSAFE_NAME_CHARS.sub("-", component) - - -def safe_version(version: str) -> str: - """Convert an arbitrary string into a valid version string. - Can still raise an ``InvalidVersion`` exception. - To avoid exceptions use ``best_effort_version``. - >>> safe_version("1988 12 25") - '1988.12.25' - >>> safe_version("v0.2.1") - '0.2.1' - >>> safe_version("v0.2?beta") - '0.2b0' - >>> safe_version("v0.2 beta") - '0.2b0' - >>> safe_version("ubuntu lts") - Traceback (most recent call last): - ... - packaging.version.InvalidVersion: Invalid version: 'ubuntu.lts' - """ - v = version.replace(' ', '.') - try: - return str(packaging.version.Version(v)) - except packaging.version.InvalidVersion: - attempt = _UNSAFE_NAME_CHARS.sub("-", v) - return str(packaging.version.Version(attempt)) - - -def best_effort_version(version: str) -> str: - """Convert an arbitrary string into a version-like string. - Fallback when ``safe_version`` is not safe enough. - >>> best_effort_version("v0.2 beta") - '0.2b0' - >>> best_effort_version("ubuntu lts") - '0.dev0+sanitized.ubuntu.lts' - >>> best_effort_version("0.23ubuntu1") - '0.23.dev0+sanitized.ubuntu1' - >>> best_effort_version("0.23-") - '0.23.dev0+sanitized' - >>> best_effort_version("0.-_") - '0.dev0+sanitized' - >>> best_effort_version("42.+?1") - '42.dev0+sanitized.1' - """ - # See pkg_resources._forgiving_version - try: - return safe_version(version) - except packaging.version.InvalidVersion: - v = version.replace(' ', '.') - match = _PEP440_FALLBACK.search(v) - if match: - safe = match["safe"] - rest = v[len(safe) :] - else: - safe = "0" - rest = version - safe_rest = _NON_ALPHANUMERIC.sub(".", rest).strip(".") - local = f"sanitized.{safe_rest}".strip(".") - return safe_version(f"{safe}.dev0+{local}") - - -def safe_extra(extra: str) -> str: - """Normalize extra name according to PEP 685 - >>> safe_extra("_FrIeNdLy-._.-bArD") - 'friendly-bard' - >>> safe_extra("FrIeNdLy-._.-bArD__._-") - 'friendly-bard' - """ - return _NON_ALPHANUMERIC.sub("-", extra).strip("-").lower() - - -def filename_component(value: str) -> str: - """Normalize each component of a filename (e.g. distribution/version part of wheel) - Note: ``value`` needs to be already normalized. - >>> filename_component("my-pkg") - 'my_pkg' - """ - return value.replace("-", "_").strip("_") - - -def filename_component_broken(value: str) -> str: - """ - Produce the incorrect filename component for compatibility. - - See pypa/setuptools#4167 for detailed analysis. - - TODO: replace this with filename_component after pip 24 is - nearly-ubiquitous. - - >>> filename_component_broken('foo_bar-baz') - 'foo-bar-baz' - """ - return value.replace('_', '-') - - -def safer_name(value: str) -> str: - """Like ``safe_name`` but can be used as filename component for wheel""" - # See bdist_wheel.safer_name - return ( - # Per https://packaging.python.org/en/latest/specifications/name-normalization/#name-normalization - re.sub(r"[-_.]+", "-", safe_name(value)) - .lower() - # Per https://packaging.python.org/en/latest/specifications/binary-distribution-format/#escaping-and-unicode - .replace("-", "_") - ) - - -def safer_best_effort_version(value: str) -> str: - """Like ``best_effort_version`` but can be used as filename component for wheel""" - # See bdist_wheel.safer_verion - # TODO: Replace with only safe_version in the future (no need for best effort) - return filename_component(best_effort_version(value)) - - -def _missing_canonicalize_license_expression(expression: str) -> str: - """ - Defer import error to affect only users that actually use it - https://github.com/pypa/setuptools/issues/4894 - >>> _missing_canonicalize_license_expression("a OR b") - Traceback (most recent call last): - ... - ImportError: ...Cannot import `packaging.licenses`... - """ - raise ImportError( - "Cannot import `packaging.licenses`." - """ - Setuptools>=77.0.0 requires "packaging>=24.2" to work properly. - Please make sure you have a suitable version installed. - """ - ) - - -try: - from packaging.licenses import ( - canonicalize_license_expression as _canonicalize_license_expression, - ) -except ImportError: # pragma: nocover - if not TYPE_CHECKING: - # XXX: pyright is still upset even with # pyright: ignore[reportAssignmentType] - _canonicalize_license_expression = _missing_canonicalize_license_expression diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_path.py b/llmlab/lib/python3.12/site-packages/setuptools/_path.py deleted file mode 100644 index 0d99b0f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_path.py +++ /dev/null @@ -1,84 +0,0 @@ -from __future__ import annotations - -import contextlib -import os -import sys -from typing import TYPE_CHECKING, TypeVar, Union - -from more_itertools import unique_everseen - -if TYPE_CHECKING: - from typing_extensions import TypeAlias - -StrPath: TypeAlias = Union[str, os.PathLike[str]] # Same as _typeshed.StrPath -StrPathT = TypeVar("StrPathT", bound=Union[str, os.PathLike[str]]) - - -def ensure_directory(path): - """Ensure that the parent directory of `path` exists""" - dirname = os.path.dirname(path) - os.makedirs(dirname, exist_ok=True) - - -def same_path(p1: StrPath, p2: StrPath) -> bool: - """Differs from os.path.samefile because it does not require paths to exist. - Purely string based (no comparison between i-nodes). - >>> same_path("a/b", "./a/b") - True - >>> same_path("a/b", "a/./b") - True - >>> same_path("a/b", "././a/b") - True - >>> same_path("a/b", "./a/b/c/..") - True - >>> same_path("a/b", "../a/b/c") - False - >>> same_path("a", "a/b") - False - """ - return normpath(p1) == normpath(p2) - - -def normpath(filename: StrPath) -> str: - """Normalize a file/dir name for comparison purposes.""" - # See pkg_resources.normalize_path for notes about cygwin - file = os.path.abspath(filename) if sys.platform == 'cygwin' else filename - return os.path.normcase(os.path.realpath(os.path.normpath(file))) - - -@contextlib.contextmanager -def paths_on_pythonpath(paths): - """ - Add the indicated paths to the head of the PYTHONPATH environment - variable so that subprocesses will also see the packages at - these paths. - - Do this in a context that restores the value on exit. - - >>> getfixture('monkeypatch').setenv('PYTHONPATH', 'anything') - >>> with paths_on_pythonpath(['foo', 'bar']): - ... assert 'foo' in os.environ['PYTHONPATH'] - ... assert 'anything' in os.environ['PYTHONPATH'] - >>> os.environ['PYTHONPATH'] - 'anything' - - >>> getfixture('monkeypatch').delenv('PYTHONPATH') - >>> with paths_on_pythonpath(['foo', 'bar']): - ... assert 'foo' in os.environ['PYTHONPATH'] - >>> os.environ.get('PYTHONPATH') - """ - nothing = object() - orig_pythonpath = os.environ.get('PYTHONPATH', nothing) - current_pythonpath = os.environ.get('PYTHONPATH', '') - try: - prefix = os.pathsep.join(unique_everseen(paths)) - to_join = filter(None, [prefix, current_pythonpath]) - new_path = os.pathsep.join(to_join) - if new_path: - os.environ['PYTHONPATH'] = new_path - yield - finally: - if orig_pythonpath is nothing: - os.environ.pop('PYTHONPATH', None) - else: - os.environ['PYTHONPATH'] = orig_pythonpath diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_reqs.py b/llmlab/lib/python3.12/site-packages/setuptools/_reqs.py deleted file mode 100644 index c793be4..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_reqs.py +++ /dev/null @@ -1,42 +0,0 @@ -from __future__ import annotations - -from collections.abc import Iterable, Iterator -from functools import lru_cache -from typing import TYPE_CHECKING, Callable, TypeVar, Union, overload - -import jaraco.text as text -from packaging.requirements import Requirement - -if TYPE_CHECKING: - from typing_extensions import TypeAlias - -_T = TypeVar("_T") -_StrOrIter: TypeAlias = Union[str, Iterable[str]] - - -parse_req: Callable[[str], Requirement] = lru_cache()(Requirement) -# Setuptools parses the same requirement many times -# (e.g. first for validation than for normalisation), -# so it might be worth to cache. - - -def parse_strings(strs: _StrOrIter) -> Iterator[str]: - """ - Yield requirement strings for each specification in `strs`. - - `strs` must be a string, or a (possibly-nested) iterable thereof. - """ - return text.join_continuation(map(text.drop_comment, text.yield_lines(strs))) - - -# These overloads are only needed because of a mypy false-positive, pyright gets it right -# https://github.com/python/mypy/issues/3737 -@overload -def parse(strs: _StrOrIter) -> Iterator[Requirement]: ... -@overload -def parse(strs: _StrOrIter, parser: Callable[[str], _T]) -> Iterator[_T]: ... -def parse(strs: _StrOrIter, parser: Callable[[str], _T] = parse_req) -> Iterator[_T]: # type: ignore[assignment] - """ - Replacement for ``pkg_resources.parse_requirements`` that uses ``packaging``. - """ - return map(parser, parse_strings(strs)) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_shutil.py b/llmlab/lib/python3.12/site-packages/setuptools/_shutil.py deleted file mode 100644 index 6acbb42..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_shutil.py +++ /dev/null @@ -1,53 +0,0 @@ -"""Convenience layer on top of stdlib's shutil and os""" - -import os -import stat -from typing import Callable, TypeVar - -from .compat import py311 - -from distutils import log - -try: - from os import chmod # pyright: ignore[reportAssignmentType] - # Losing type-safety w/ pyright, but that's ok -except ImportError: # pragma: no cover - # Jython compatibility - def chmod(*args: object, **kwargs: object) -> None: # type: ignore[misc] # Mypy reuses the imported definition anyway - pass - - -_T = TypeVar("_T") - - -def attempt_chmod_verbose(path, mode): - log.debug("changing mode of %s to %o", path, mode) - try: - chmod(path, mode) - except OSError as e: # pragma: no cover - log.debug("chmod failed: %s", e) - - -# Must match shutil._OnExcCallback -def _auto_chmod( - func: Callable[..., _T], arg: str, exc: BaseException -) -> _T: # pragma: no cover - """shutils onexc callback to automatically call chmod for certain functions.""" - # Only retry for scenarios known to have an issue - if func in [os.unlink, os.remove] and os.name == 'nt': - attempt_chmod_verbose(arg, stat.S_IWRITE) - return func(arg) - raise exc - - -def rmtree(path, ignore_errors=False, onexc=_auto_chmod): - """ - Similar to ``shutil.rmtree`` but automatically executes ``chmod`` - for well know Windows failure scenarios. - """ - return py311.shutil_rmtree(path, ignore_errors, onexc) - - -def rmdir(path, **opts): - if os.path.isdir(path): - rmtree(path, **opts) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_static.py b/llmlab/lib/python3.12/site-packages/setuptools/_static.py deleted file mode 100644 index af35862..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_static.py +++ /dev/null @@ -1,188 +0,0 @@ -from functools import wraps -from typing import TypeVar - -import packaging.specifiers - -from .warnings import SetuptoolsDeprecationWarning - - -class Static: - """ - Wrapper for built-in object types that are allow setuptools to identify - static core metadata (in opposition to ``Dynamic``, as defined :pep:`643`). - - The trick is to mark values with :class:`Static` when they come from - ``pyproject.toml`` or ``setup.cfg``, so if any plugin overwrite the value - with a built-in, setuptools will be able to recognise the change. - - We inherit from built-in classes, so that we don't need to change the existing - code base to deal with the new types. - We also should strive for immutability objects to avoid changes after the - initial parsing. - """ - - _mutated_: bool = False # TODO: Remove after deprecation warning is solved - - -def _prevent_modification(target: type, method: str, copying: str) -> None: - """ - Because setuptools is very flexible we cannot fully prevent - plugins and user customizations from modifying static values that were - parsed from config files. - But we can attempt to block "in-place" mutations and identify when they - were done. - """ - fn = getattr(target, method, None) - if fn is None: - return - - @wraps(fn) - def _replacement(self: Static, *args, **kwargs): - # TODO: After deprecation period raise NotImplementedError instead of warning - # which obviated the existence and checks of the `_mutated_` attribute. - self._mutated_ = True - SetuptoolsDeprecationWarning.emit( - "Direct modification of value will be disallowed", - f""" - In an effort to implement PEP 643, direct/in-place changes of static values - that come from configuration files are deprecated. - If you need to modify this value, please first create a copy with {copying} - and make sure conform to all relevant standards when overriding setuptools - functionality (https://packaging.python.org/en/latest/specifications/). - """, - due_date=(2025, 10, 10), # Initially introduced in 2024-09-06 - ) - return fn(self, *args, **kwargs) - - _replacement.__doc__ = "" # otherwise doctest may fail. - setattr(target, method, _replacement) - - -class Str(str, Static): - pass - - -class Tuple(tuple, Static): - pass - - -class List(list, Static): - """ - :meta private: - >>> x = List([1, 2, 3]) - >>> is_static(x) - True - >>> x += [0] # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - SetuptoolsDeprecationWarning: Direct modification ... - >>> is_static(x) # no longer static after modification - False - >>> y = list(x) - >>> y.clear() - >>> y - [] - >>> y == x - False - >>> is_static(List(y)) - True - """ - - -# Make `List` immutable-ish -# (certain places of setuptools/distutils issue a warn if we use tuple instead of list) -for _method in ( - '__delitem__', - '__iadd__', - '__setitem__', - 'append', - 'clear', - 'extend', - 'insert', - 'remove', - 'reverse', - 'pop', -): - _prevent_modification(List, _method, "`list(value)`") - - -class Dict(dict, Static): - """ - :meta private: - >>> x = Dict({'a': 1, 'b': 2}) - >>> is_static(x) - True - >>> x['c'] = 0 # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - SetuptoolsDeprecationWarning: Direct modification ... - >>> x._mutated_ - True - >>> is_static(x) # no longer static after modification - False - >>> y = dict(x) - >>> y.popitem() - ('b', 2) - >>> y == x - False - >>> is_static(Dict(y)) - True - """ - - -# Make `Dict` immutable-ish (we cannot inherit from types.MappingProxyType): -for _method in ( - '__delitem__', - '__ior__', - '__setitem__', - 'clear', - 'pop', - 'popitem', - 'setdefault', - 'update', -): - _prevent_modification(Dict, _method, "`dict(value)`") - - -class SpecifierSet(packaging.specifiers.SpecifierSet, Static): - """Not exactly a built-in type but useful for ``requires-python``""" - - -T = TypeVar("T") - - -def noop(value: T) -> T: - """ - >>> noop(42) - 42 - """ - return value - - -_CONVERSIONS = {str: Str, tuple: Tuple, list: List, dict: Dict} - - -def attempt_conversion(value: T) -> T: - """ - >>> is_static(attempt_conversion("hello")) - True - >>> is_static(object()) - False - """ - return _CONVERSIONS.get(type(value), noop)(value) # type: ignore[call-overload] - - -def is_static(value: object) -> bool: - """ - >>> is_static(a := Dict({'a': 1})) - True - >>> is_static(dict(a)) - False - >>> is_static(b := List([1, 2, 3])) - True - >>> is_static(list(b)) - False - """ - return isinstance(value, Static) and not value._mutated_ - - -EMPTY_LIST = List() -EMPTY_DICT = Dict() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/__pycache__/typing_extensions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/__pycache__/typing_extensions.cpython-312.pyc deleted file mode 100644 index cfd4553..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/__pycache__/typing_extensions.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/LICENSE deleted file mode 100644 index b49c3af..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/LICENSE +++ /dev/null @@ -1,166 +0,0 @@ -GNU LESSER GENERAL PUBLIC LICENSE - Version 3, 29 June 2007 - - Copyright (C) 2007 Free Software Foundation, Inc. - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - - - This version of the GNU Lesser General Public License incorporates -the terms and conditions of version 3 of the GNU General Public -License, supplemented by the additional permissions listed below. - - 0. Additional Definitions. - - As used herein, "this License" refers to version 3 of the GNU Lesser -General Public License, and the "GNU GPL" refers to version 3 of the GNU -General Public License. - - "The Library" refers to a covered work governed by this License, -other than an Application or a Combined Work as defined below. - - An "Application" is any work that makes use of an interface provided -by the Library, but which is not otherwise based on the Library. -Defining a subclass of a class defined by the Library is deemed a mode -of using an interface provided by the Library. - - A "Combined Work" is a work produced by combining or linking an -Application with the Library. The particular version of the Library -with which the Combined Work was made is also called the "Linked -Version". - - The "Minimal Corresponding Source" for a Combined Work means the -Corresponding Source for the Combined Work, excluding any source code -for portions of the Combined Work that, considered in isolation, are -based on the Application, and not on the Linked Version. - - The "Corresponding Application Code" for a Combined Work means the -object code and/or source code for the Application, including any data -and utility programs needed for reproducing the Combined Work from the -Application, but excluding the System Libraries of the Combined Work. - - 1. Exception to Section 3 of the GNU GPL. - - You may convey a covered work under sections 3 and 4 of this License -without being bound by section 3 of the GNU GPL. - - 2. Conveying Modified Versions. - - If you modify a copy of the Library, and, in your modifications, a -facility refers to a function or data to be supplied by an Application -that uses the facility (other than as an argument passed when the -facility is invoked), then you may convey a copy of the modified -version: - - a) under this License, provided that you make a good faith effort to - ensure that, in the event an Application does not supply the - function or data, the facility still operates, and performs - whatever part of its purpose remains meaningful, or - - b) under the GNU GPL, with none of the additional permissions of - this License applicable to that copy. - - 3. Object Code Incorporating Material from Library Header Files. - - The object code form of an Application may incorporate material from -a header file that is part of the Library. You may convey such object -code under terms of your choice, provided that, if the incorporated -material is not limited to numerical parameters, data structure -layouts and accessors, or small macros, inline functions and templates -(ten or fewer lines in length), you do both of the following: - - a) Give prominent notice with each copy of the object code that the - Library is used in it and that the Library and its use are - covered by this License. - - b) Accompany the object code with a copy of the GNU GPL and this license - document. - - 4. Combined Works. - - You may convey a Combined Work under terms of your choice that, -taken together, effectively do not restrict modification of the -portions of the Library contained in the Combined Work and reverse -engineering for debugging such modifications, if you also do each of -the following: - - a) Give prominent notice with each copy of the Combined Work that - the Library is used in it and that the Library and its use are - covered by this License. - - b) Accompany the Combined Work with a copy of the GNU GPL and this license - document. - - c) For a Combined Work that displays copyright notices during - execution, include the copyright notice for the Library among - these notices, as well as a reference directing the user to the - copies of the GNU GPL and this license document. - - d) Do one of the following: - - 0) Convey the Minimal Corresponding Source under the terms of this - License, and the Corresponding Application Code in a form - suitable for, and under terms that permit, the user to - recombine or relink the Application with a modified version of - the Linked Version to produce a modified Combined Work, in the - manner specified by section 6 of the GNU GPL for conveying - Corresponding Source. - - 1) Use a suitable shared library mechanism for linking with the - Library. A suitable mechanism is one that (a) uses at run time - a copy of the Library already present on the user's computer - system, and (b) will operate properly with a modified version - of the Library that is interface-compatible with the Linked - Version. - - e) Provide Installation Information, but only if you would otherwise - be required to provide such information under section 6 of the - GNU GPL, and only to the extent that such information is - necessary to install and execute a modified version of the - Combined Work produced by recombining or relinking the - Application with a modified version of the Linked Version. (If - you use option 4d0, the Installation Information must accompany - the Minimal Corresponding Source and Corresponding Application - Code. If you use option 4d1, you must provide the Installation - Information in the manner specified by section 6 of the GNU GPL - for conveying Corresponding Source.) - - 5. Combined Libraries. - - You may place library facilities that are a work based on the -Library side by side in a single library together with other library -facilities that are not Applications and are not covered by this -License, and convey such a combined library under terms of your -choice, if you do both of the following: - - a) Accompany the combined library with a copy of the same work based - on the Library, uncombined with any other library facilities, - conveyed under the terms of this License. - - b) Give prominent notice with the combined library that part of it - is a work based on the Library, and explaining where to find the - accompanying uncombined form of the same work. - - 6. Revised Versions of the GNU Lesser General Public License. - - The Free Software Foundation may publish revised and/or new versions -of the GNU Lesser General Public License from time to time. Such new -versions will be similar in spirit to the present version, but may -differ in detail to address new problems or concerns. - - Each version is given a distinguishing version number. If the -Library as you received it specifies that a certain numbered version -of the GNU Lesser General Public License "or any later version" -applies to it, you have the option of following the terms and -conditions either of that published version or of any later version -published by the Free Software Foundation. If the Library as you -received it does not specify a version number of the GNU Lesser -General Public License, you may choose any version of the GNU Lesser -General Public License ever published by the Free Software Foundation. - - If the Library as you received it specifies that a proxy can decide -whether future versions of the GNU Lesser General Public License shall -apply, that proxy's public statement of acceptance of any version is -permanent authorization for you to choose that version for the -Library. - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/METADATA deleted file mode 100644 index 32214fb..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/METADATA +++ /dev/null @@ -1,420 +0,0 @@ -Metadata-Version: 2.1 -Name: autocommand -Version: 2.2.2 -Summary: A library to create a command-line program from a function -Home-page: https://github.com/Lucretiel/autocommand -Author: Nathan West -License: LGPLv3 -Project-URL: Homepage, https://github.com/Lucretiel/autocommand -Project-URL: Bug Tracker, https://github.com/Lucretiel/autocommand/issues -Platform: any -Classifier: Development Status :: 6 - Mature -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3) -Classifier: Programming Language :: Python -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Classifier: Topic :: Software Development -Classifier: Topic :: Software Development :: Libraries -Classifier: Topic :: Software Development :: Libraries :: Python Modules -Requires-Python: >=3.7 -Description-Content-Type: text/markdown -License-File: LICENSE - -[![PyPI version](https://badge.fury.io/py/autocommand.svg)](https://badge.fury.io/py/autocommand) - -# autocommand - -A library to automatically generate and run simple argparse parsers from function signatures. - -## Installation - -Autocommand is installed via pip: - -``` -$ pip install autocommand -``` - -## Usage - -Autocommand turns a function into a command-line program. It converts the function's parameter signature into command-line arguments, and automatically runs the function if the module was called as `__main__`. In effect, it lets your create a smart main function. - -```python -from autocommand import autocommand - -# This program takes exactly one argument and echos it. -@autocommand(__name__) -def echo(thing): - print(thing) -``` - -``` -$ python echo.py hello -hello -$ python echo.py -h -usage: echo [-h] thing - -positional arguments: - thing - -optional arguments: - -h, --help show this help message and exit -$ python echo.py hello world # too many arguments -usage: echo.py [-h] thing -echo.py: error: unrecognized arguments: world -``` - -As you can see, autocommand converts the signature of the function into an argument spec. When you run the file as a program, autocommand collects the command-line arguments and turns them into function arguments. The function is executed with these arguments, and then the program exits with the return value of the function, via `sys.exit`. Autocommand also automatically creates a usage message, which can be invoked with `-h` or `--help`, and automatically prints an error message when provided with invalid arguments. - -### Types - -You can use a type annotation to give an argument a type. Any type (or in fact any callable) that returns an object when given a string argument can be used, though there are a few special cases that are described later. - -```python -@autocommand(__name__) -def net_client(host, port: int): - ... -``` - -Autocommand will catch `TypeErrors` raised by the type during argument parsing, so you can supply a callable and do some basic argument validation as well. - -### Trailing Arguments - -You can add a `*args` parameter to your function to give it trailing arguments. The command will collect 0 or more trailing arguments and supply them to `args` as a tuple. If a type annotation is supplied, the type is applied to each argument. - -```python -# Write the contents of each file, one by one -@autocommand(__name__) -def cat(*files): - for filename in files: - with open(filename) as file: - for line in file: - print(line.rstrip()) -``` - -``` -$ python cat.py -h -usage: ipython [-h] [file [file ...]] - -positional arguments: - file - -optional arguments: - -h, --help show this help message and exit -``` - -### Options - -To create `--option` switches, just assign a default. Autocommand will automatically create `--long` and `-s`hort switches. - -```python -@autocommand(__name__) -def do_with_config(argument, config='~/foo.conf'): - pass -``` - -``` -$ python example.py -h -usage: example.py [-h] [-c CONFIG] argument - -positional arguments: - argument - -optional arguments: - -h, --help show this help message and exit - -c CONFIG, --config CONFIG -``` - -The option's type is automatically deduced from the default, unless one is explicitly given in an annotation: - -```python -@autocommand(__name__) -def http_connect(host, port=80): - print('{}:{}'.format(host, port)) -``` - -``` -$ python http.py -h -usage: http.py [-h] [-p PORT] host - -positional arguments: - host - -optional arguments: - -h, --help show this help message and exit - -p PORT, --port PORT -$ python http.py localhost -localhost:80 -$ python http.py localhost -p 8080 -localhost:8080 -$ python http.py localhost -p blah -usage: http.py [-h] [-p PORT] host -http.py: error: argument -p/--port: invalid int value: 'blah' -``` - -#### None - -If an option is given a default value of `None`, it reads in a value as normal, but supplies `None` if the option isn't provided. - -#### Switches - -If an argument is given a default value of `True` or `False`, or -given an explicit `bool` type, it becomes an option switch. - -```python - @autocommand(__name__) - def example(verbose=False, quiet=False): - pass -``` - -``` -$ python example.py -h -usage: example.py [-h] [-v] [-q] - -optional arguments: - -h, --help show this help message and exit - -v, --verbose - -q, --quiet -``` - -Autocommand attempts to do the "correct thing" in these cases- if the default is `True`, then supplying the switch makes the argument `False`; if the type is `bool` and the default is some other `True` value, then supplying the switch makes the argument `False`, while not supplying the switch makes the argument the default value. - -Autocommand also supports the creation of switch inverters. Pass `add_nos=True` to `autocommand` to enable this. - -``` - @autocommand(__name__, add_nos=True) - def example(verbose=False): - pass -``` - -``` -$ python example.py -h -usage: ipython [-h] [-v] [--no-verbose] - -optional arguments: - -h, --help show this help message and exit - -v, --verbose - --no-verbose -``` - -Using the `--no-` version of a switch will pass the opposite value in as a function argument. If multiple switches are present, the last one takes precedence. - -#### Files - -If the default value is a file object, such as `sys.stdout`, then autocommand just looks for a string, for a file path. It doesn't do any special checking on the string, though (such as checking if the file exists); it's better to let the client decide how to handle errors in this case. Instead, it provides a special context manager called `smart_open`, which behaves exactly like `open` if a filename or other openable type is provided, but also lets you use already open files: - -```python -from autocommand import autocommand, smart_open -import sys - -# Write the contents of stdin, or a file, to stdout -@autocommand(__name__) -def write_out(infile=sys.stdin): - with smart_open(infile) as f: - for line in f: - print(line.rstrip()) - # If a file was opened, it is closed here. If it was just stdin, it is untouched. -``` - -``` -$ echo "Hello World!" | python write_out.py | tee hello.txt -Hello World! -$ python write_out.py --infile hello.txt -Hello World! -``` - -### Descriptions and docstrings - -The `autocommand` decorator accepts `description` and `epilog` kwargs, corresponding to the `description `_ and `epilog `_ of the `ArgumentParser`. If no description is given, but the decorated function has a docstring, then it is taken as the `description` for the `ArgumentParser`. You can also provide both the description and epilog in the docstring by splitting it into two sections with 4 or more - characters. - -```python -@autocommand(__name__) -def copy(infile=sys.stdin, outfile=sys.stdout): - ''' - Copy an the contents of a file (or stdin) to another file (or stdout) - ---------- - Some extra documentation in the epilog - ''' - with smart_open(infile) as istr: - with smart_open(outfile, 'w') as ostr: - for line in istr: - ostr.write(line) -``` - -``` -$ python copy.py -h -usage: copy.py [-h] [-i INFILE] [-o OUTFILE] - -Copy an the contents of a file (or stdin) to another file (or stdout) - -optional arguments: - -h, --help show this help message and exit - -i INFILE, --infile INFILE - -o OUTFILE, --outfile OUTFILE - -Some extra documentation in the epilog -$ echo "Hello World" | python copy.py --outfile hello.txt -$ python copy.py --infile hello.txt --outfile hello2.txt -$ python copy.py --infile hello2.txt -Hello World -``` - -### Parameter descriptions - -You can also attach description text to individual parameters in the annotation. To attach both a type and a description, supply them both in any order in a tuple - -```python -@autocommand(__name__) -def copy_net( - infile: 'The name of the file to send', - host: 'The host to send the file to', - port: (int, 'The port to connect to')): - - ''' - Copy a file over raw TCP to a remote destination. - ''' - # Left as an exercise to the reader -``` - -### Decorators and wrappers - -Autocommand automatically follows wrapper chains created by `@functools.wraps`. This means that you can apply other wrapping decorators to your main function, and autocommand will still correctly detect the signature. - -```python -from functools import wraps -from autocommand import autocommand - -def print_yielded(func): - ''' - Convert a generator into a function that prints all yielded elements - ''' - @wraps(func) - def wrapper(*args, **kwargs): - for thing in func(*args, **kwargs): - print(thing) - return wrapper - -@autocommand(__name__, - description= 'Print all the values from START to STOP, inclusive, in steps of STEP', - epilog= 'STOP and STEP default to 1') -@print_yielded -def seq(stop, start=1, step=1): - for i in range(start, stop + 1, step): - yield i -``` - -``` -$ seq.py -h -usage: seq.py [-h] [-s START] [-S STEP] stop - -Print all the values from START to STOP, inclusive, in steps of STEP - -positional arguments: - stop - -optional arguments: - -h, --help show this help message and exit - -s START, --start START - -S STEP, --step STEP - -STOP and STEP default to 1 -``` - -Even though autocommand is being applied to the `wrapper` returned by `print_yielded`, it still retreives the signature of the underlying `seq` function to create the argument parsing. - -### Custom Parser - -While autocommand's automatic parser generator is a powerful convenience, it doesn't cover all of the different features that argparse provides. If you need these features, you can provide your own parser as a kwarg to `autocommand`: - -```python -from argparse import ArgumentParser -from autocommand import autocommand - -parser = ArgumentParser() -# autocommand can't do optional positonal parameters -parser.add_argument('arg', nargs='?') -# or mutually exclusive options -group = parser.add_mutually_exclusive_group() -group.add_argument('-v', '--verbose', action='store_true') -group.add_argument('-q', '--quiet', action='store_true') - -@autocommand(__name__, parser=parser) -def main(arg, verbose, quiet): - print(arg, verbose, quiet) -``` - -``` -$ python parser.py -h -usage: write_file.py [-h] [-v | -q] [arg] - -positional arguments: - arg - -optional arguments: - -h, --help show this help message and exit - -v, --verbose - -q, --quiet -$ python parser.py -None False False -$ python parser.py hello -hello False False -$ python parser.py -v -None True False -$ python parser.py -q -None False True -$ python parser.py -vq -usage: parser.py [-h] [-v | -q] [arg] -parser.py: error: argument -q/--quiet: not allowed with argument -v/--verbose -``` - -Any parser should work fine, so long as each of the parser's arguments has a corresponding parameter in the decorated main function. The order of parameters doesn't matter, as long as they are all present. Note that when using a custom parser, autocommand doesn't modify the parser or the retrieved arguments. This means that no description/epilog will be added, and the function's type annotations and defaults (if present) will be ignored. - -## Testing and Library use - -The decorated function is only called and exited from if the first argument to `autocommand` is `'__main__'` or `True`. If it is neither of these values, or no argument is given, then a new main function is created by the decorator. This function has the signature `main(argv=None)`, and is intended to be called with arguments as if via `main(sys.argv[1:])`. The function has the attributes `parser` and `main`, which are the generated `ArgumentParser` and the original main function that was decorated. This is to facilitate testing and library use of your main. Calling the function triggers a `parse_args()` with the supplied arguments, and returns the result of the main function. Note that, while it returns instead of calling `sys.exit`, the `parse_args()` function will raise a `SystemExit` in the event of a parsing error or `-h/--help` argument. - -```python - @autocommand() - def test_prog(arg1, arg2: int, quiet=False, verbose=False): - if not quiet: - print(arg1, arg2) - if verbose: - print("LOUD NOISES") - - return 0 - - print(test_prog(['-v', 'hello', '80'])) -``` - -``` -$ python test_prog.py -hello 80 -LOUD NOISES -0 -``` - -If the function is called with no arguments, `sys.argv[1:]` is used. This is to allow the autocommand function to be used as a setuptools entry point. - -## Exceptions and limitations - -- There are a few possible exceptions that `autocommand` can raise. All of them derive from `autocommand.AutocommandError`. - - - If an invalid annotation is given (that is, it isn't a `type`, `str`, `(type, str)`, or `(str, type)`, an `AnnotationError` is raised. The `type` may be any callable, as described in the `Types`_ section. - - If the function has a `**kwargs` parameter, a `KWargError` is raised. - - If, somehow, the function has a positional-only parameter, a `PositionalArgError` is raised. This means that the argument doesn't have a name, which is currently not possible with a plain `def` or `lambda`, though many built-in functions have this kind of parameter. - -- There are a few argparse features that are not supported by autocommand. - - - It isn't possible to have an optional positional argument (as opposed to a `--option`). POSIX thinks this is bad form anyway. - - It isn't possible to have mutually exclusive arguments or options - - It isn't possible to have subcommands or subparsers, though I'm working on a few solutions involving classes or nested function definitions to allow this. - -## Development - -Autocommand cannot be important from the project root; this is to enforce separation of concerns and prevent accidental importing of `setup.py` or tests. To develop, install the project in editable mode: - -``` -$ python setup.py develop -``` - -This will create a link to the source files in the deployment directory, so that any source changes are reflected when it is imported. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/RECORD deleted file mode 100644 index e6e12ea..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/RECORD +++ /dev/null @@ -1,18 +0,0 @@ -autocommand-2.2.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -autocommand-2.2.2.dist-info/LICENSE,sha256=reeNBJgtaZctREqOFKlPh6IzTdOFXMgDSOqOJAqg3y0,7634 -autocommand-2.2.2.dist-info/METADATA,sha256=OADZuR3O6iBlpu1ieTgzYul6w4uOVrk0P0BO5TGGAJk,15006 -autocommand-2.2.2.dist-info/RECORD,, -autocommand-2.2.2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92 -autocommand-2.2.2.dist-info/top_level.txt,sha256=AzfhgKKS8EdAwWUTSF8mgeVQbXOY9kokHB6kSqwwqu0,12 -autocommand/__init__.py,sha256=zko5Rnvolvb-UXjCx_2ArPTGBWwUK5QY4LIQIKYR7As,1037 -autocommand/__pycache__/__init__.cpython-312.pyc,, -autocommand/__pycache__/autoasync.cpython-312.pyc,, -autocommand/__pycache__/autocommand.cpython-312.pyc,, -autocommand/__pycache__/automain.cpython-312.pyc,, -autocommand/__pycache__/autoparse.cpython-312.pyc,, -autocommand/__pycache__/errors.cpython-312.pyc,, -autocommand/autoasync.py,sha256=AMdyrxNS4pqWJfP_xuoOcImOHWD-qT7x06wmKN1Vp-U,5680 -autocommand/autocommand.py,sha256=hmkEmQ72HtL55gnURVjDOnsfYlGd5lLXbvT4KG496Qw,2505 -autocommand/automain.py,sha256=A2b8i754Mxc_DjU9WFr6vqYDWlhz0cn8miu8d8EsxV8,2076 -autocommand/autoparse.py,sha256=WVWmZJPcbzUKXP40raQw_0HD8qPJ2V9VG1eFFmmnFxw,11642 -autocommand/errors.py,sha256=7aa3roh9Herd6nIKpQHNWEslWE8oq7GiHYVUuRqORnA,886 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/WHEEL deleted file mode 100644 index 57e3d84..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.38.4) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/top_level.txt deleted file mode 100644 index dda5158..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand-2.2.2.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -autocommand diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__init__.py deleted file mode 100644 index 73fbfca..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__init__.py +++ /dev/null @@ -1,27 +0,0 @@ -# Copyright 2014-2016 Nathan West -# -# This file is part of autocommand. -# -# autocommand is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# autocommand is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public License -# along with autocommand. If not, see . - -# flake8 flags all these imports as unused, hence the NOQAs everywhere. - -from .automain import automain # NOQA -from .autoparse import autoparse, smart_open # NOQA -from .autocommand import autocommand # NOQA - -try: - from .autoasync import autoasync # NOQA -except ImportError: # pragma: no cover - pass diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 6640641..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autoasync.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autoasync.cpython-312.pyc deleted file mode 100644 index 5038fb3..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autoasync.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autocommand.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autocommand.cpython-312.pyc deleted file mode 100644 index 7fd248b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autocommand.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/automain.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/automain.cpython-312.pyc deleted file mode 100644 index 52ca430..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/automain.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autoparse.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autoparse.cpython-312.pyc deleted file mode 100644 index 4472e07..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/autoparse.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/errors.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/errors.cpython-312.pyc deleted file mode 100644 index ba4c36f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/__pycache__/errors.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autoasync.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autoasync.py deleted file mode 100644 index 688f7e0..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autoasync.py +++ /dev/null @@ -1,142 +0,0 @@ -# Copyright 2014-2015 Nathan West -# -# This file is part of autocommand. -# -# autocommand is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# autocommand is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public License -# along with autocommand. If not, see . - -from asyncio import get_event_loop, iscoroutine -from functools import wraps -from inspect import signature - - -async def _run_forever_coro(coro, args, kwargs, loop): - ''' - This helper function launches an async main function that was tagged with - forever=True. There are two possibilities: - - - The function is a normal function, which handles initializing the event - loop, which is then run forever - - The function is a coroutine, which needs to be scheduled in the event - loop, which is then run forever - - There is also the possibility that the function is a normal function - wrapping a coroutine function - - The function is therefore called unconditionally and scheduled in the event - loop if the return value is a coroutine object. - - The reason this is a separate function is to make absolutely sure that all - the objects created are garbage collected after all is said and done; we - do this to ensure that any exceptions raised in the tasks are collected - ASAP. - ''' - - # Personal note: I consider this an antipattern, as it relies on the use of - # unowned resources. The setup function dumps some stuff into the event - # loop where it just whirls in the ether without a well defined owner or - # lifetime. For this reason, there's a good chance I'll remove the - # forever=True feature from autoasync at some point in the future. - thing = coro(*args, **kwargs) - if iscoroutine(thing): - await thing - - -def autoasync(coro=None, *, loop=None, forever=False, pass_loop=False): - ''' - Convert an asyncio coroutine into a function which, when called, is - evaluted in an event loop, and the return value returned. This is intented - to make it easy to write entry points into asyncio coroutines, which - otherwise need to be explictly evaluted with an event loop's - run_until_complete. - - If `loop` is given, it is used as the event loop to run the coro in. If it - is None (the default), the loop is retreived using asyncio.get_event_loop. - This call is defered until the decorated function is called, so that - callers can install custom event loops or event loop policies after - @autoasync is applied. - - If `forever` is True, the loop is run forever after the decorated coroutine - is finished. Use this for servers created with asyncio.start_server and the - like. - - If `pass_loop` is True, the event loop object is passed into the coroutine - as the `loop` kwarg when the wrapper function is called. In this case, the - wrapper function's __signature__ is updated to remove this parameter, so - that autoparse can still be used on it without generating a parameter for - `loop`. - - This coroutine can be called with ( @autoasync(...) ) or without - ( @autoasync ) arguments. - - Examples: - - @autoasync - def get_file(host, port): - reader, writer = yield from asyncio.open_connection(host, port) - data = reader.read() - sys.stdout.write(data.decode()) - - get_file(host, port) - - @autoasync(forever=True, pass_loop=True) - def server(host, port, loop): - yield_from loop.create_server(Proto, host, port) - - server('localhost', 8899) - - ''' - if coro is None: - return lambda c: autoasync( - c, loop=loop, - forever=forever, - pass_loop=pass_loop) - - # The old and new signatures are required to correctly bind the loop - # parameter in 100% of cases, even if it's a positional parameter. - # NOTE: A future release will probably require the loop parameter to be - # a kwonly parameter. - if pass_loop: - old_sig = signature(coro) - new_sig = old_sig.replace(parameters=( - param for name, param in old_sig.parameters.items() - if name != "loop")) - - @wraps(coro) - def autoasync_wrapper(*args, **kwargs): - # Defer the call to get_event_loop so that, if a custom policy is - # installed after the autoasync decorator, it is respected at call time - local_loop = get_event_loop() if loop is None else loop - - # Inject the 'loop' argument. We have to use this signature binding to - # ensure it's injected in the correct place (positional, keyword, etc) - if pass_loop: - bound_args = old_sig.bind_partial() - bound_args.arguments.update( - loop=local_loop, - **new_sig.bind(*args, **kwargs).arguments) - args, kwargs = bound_args.args, bound_args.kwargs - - if forever: - local_loop.create_task(_run_forever_coro( - coro, args, kwargs, local_loop - )) - local_loop.run_forever() - else: - return local_loop.run_until_complete(coro(*args, **kwargs)) - - # Attach the updated signature. This allows 'pass_loop' to be used with - # autoparse - if pass_loop: - autoasync_wrapper.__signature__ = new_sig - - return autoasync_wrapper diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autocommand.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autocommand.py deleted file mode 100644 index 097e86d..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autocommand.py +++ /dev/null @@ -1,70 +0,0 @@ -# Copyright 2014-2015 Nathan West -# -# This file is part of autocommand. -# -# autocommand is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# autocommand is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public License -# along with autocommand. If not, see . - -from .autoparse import autoparse -from .automain import automain -try: - from .autoasync import autoasync -except ImportError: # pragma: no cover - pass - - -def autocommand( - module, *, - description=None, - epilog=None, - add_nos=False, - parser=None, - loop=None, - forever=False, - pass_loop=False): - - if callable(module): - raise TypeError('autocommand requires a module name argument') - - def autocommand_decorator(func): - # Step 1: if requested, run it all in an asyncio event loop. autoasync - # patches the __signature__ of the decorated function, so that in the - # event that pass_loop is True, the `loop` parameter of the original - # function will *not* be interpreted as a command-line argument by - # autoparse - if loop is not None or forever or pass_loop: - func = autoasync( - func, - loop=None if loop is True else loop, - pass_loop=pass_loop, - forever=forever) - - # Step 2: create parser. We do this second so that the arguments are - # parsed and passed *before* entering the asyncio event loop, if it - # exists. This simplifies the stack trace and ensures errors are - # reported earlier. It also ensures that errors raised during parsing & - # passing are still raised if `forever` is True. - func = autoparse( - func, - description=description, - epilog=epilog, - add_nos=add_nos, - parser=parser) - - # Step 3: call the function automatically if __name__ == '__main__' (or - # if True was provided) - func = automain(module)(func) - - return func - - return autocommand_decorator diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/automain.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/automain.py deleted file mode 100644 index 6cc45db..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/automain.py +++ /dev/null @@ -1,59 +0,0 @@ -# Copyright 2014-2015 Nathan West -# -# This file is part of autocommand. -# -# autocommand is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# autocommand is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public License -# along with autocommand. If not, see . - -import sys -from .errors import AutocommandError - - -class AutomainRequiresModuleError(AutocommandError, TypeError): - pass - - -def automain(module, *, args=(), kwargs=None): - ''' - This decorator automatically invokes a function if the module is being run - as the "__main__" module. Optionally, provide args or kwargs with which to - call the function. If `module` is "__main__", the function is called, and - the program is `sys.exit`ed with the return value. You can also pass `True` - to cause the function to be called unconditionally. If the function is not - called, it is returned unchanged by the decorator. - - Usage: - - @automain(__name__) # Pass __name__ to check __name__=="__main__" - def main(): - ... - - If __name__ is "__main__" here, the main function is called, and then - sys.exit called with the return value. - ''' - - # Check that @automain(...) was called, rather than @automain - if callable(module): - raise AutomainRequiresModuleError(module) - - if module == '__main__' or module is True: - if kwargs is None: - kwargs = {} - - # Use a function definition instead of a lambda for a neater traceback - def automain_decorator(main): - sys.exit(main(*args, **kwargs)) - - return automain_decorator - else: - return lambda main: main diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autoparse.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autoparse.py deleted file mode 100644 index 0276a3f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/autoparse.py +++ /dev/null @@ -1,333 +0,0 @@ -# Copyright 2014-2015 Nathan West -# -# This file is part of autocommand. -# -# autocommand is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# autocommand is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public License -# along with autocommand. If not, see . - -import sys -from re import compile as compile_regex -from inspect import signature, getdoc, Parameter -from argparse import ArgumentParser -from contextlib import contextmanager -from functools import wraps -from io import IOBase -from autocommand.errors import AutocommandError - - -_empty = Parameter.empty - - -class AnnotationError(AutocommandError): - '''Annotation error: annotation must be a string, type, or tuple of both''' - - -class PositionalArgError(AutocommandError): - ''' - Postional Arg Error: autocommand can't handle postional-only parameters - ''' - - -class KWArgError(AutocommandError): - '''kwarg Error: autocommand can't handle a **kwargs parameter''' - - -class DocstringError(AutocommandError): - '''Docstring error''' - - -class TooManySplitsError(DocstringError): - ''' - The docstring had too many ---- section splits. Currently we only support - using up to a single split, to split the docstring into description and - epilog parts. - ''' - - -def _get_type_description(annotation): - ''' - Given an annotation, return the (type, description) for the parameter. - If you provide an annotation that is somehow both a string and a callable, - the behavior is undefined. - ''' - if annotation is _empty: - return None, None - elif callable(annotation): - return annotation, None - elif isinstance(annotation, str): - return None, annotation - elif isinstance(annotation, tuple): - try: - arg1, arg2 = annotation - except ValueError as e: - raise AnnotationError(annotation) from e - else: - if callable(arg1) and isinstance(arg2, str): - return arg1, arg2 - elif isinstance(arg1, str) and callable(arg2): - return arg2, arg1 - - raise AnnotationError(annotation) - - -def _add_arguments(param, parser, used_char_args, add_nos): - ''' - Add the argument(s) to an ArgumentParser (using add_argument) for a given - parameter. used_char_args is the set of -short options currently already in - use, and is updated (if necessary) by this function. If add_nos is True, - this will also add an inverse switch for all boolean options. For - instance, for the boolean parameter "verbose", this will create --verbose - and --no-verbose. - ''' - - # Impl note: This function is kept separate from make_parser because it's - # already very long and I wanted to separate out as much as possible into - # its own call scope, to prevent even the possibility of suble mutation - # bugs. - if param.kind is param.POSITIONAL_ONLY: - raise PositionalArgError(param) - elif param.kind is param.VAR_KEYWORD: - raise KWArgError(param) - - # These are the kwargs for the add_argument function. - arg_spec = {} - is_option = False - - # Get the type and default from the annotation. - arg_type, description = _get_type_description(param.annotation) - - # Get the default value - default = param.default - - # If there is no explicit type, and the default is present and not None, - # infer the type from the default. - if arg_type is None and default not in {_empty, None}: - arg_type = type(default) - - # Add default. The presence of a default means this is an option, not an - # argument. - if default is not _empty: - arg_spec['default'] = default - is_option = True - - # Add the type - if arg_type is not None: - # Special case for bool: make it just a --switch - if arg_type is bool: - if not default or default is _empty: - arg_spec['action'] = 'store_true' - else: - arg_spec['action'] = 'store_false' - - # Switches are always options - is_option = True - - # Special case for file types: make it a string type, for filename - elif isinstance(default, IOBase): - arg_spec['type'] = str - - # TODO: special case for list type. - # - How to specificy type of list members? - # - param: [int] - # - param: int =[] - # - action='append' vs nargs='*' - - else: - arg_spec['type'] = arg_type - - # nargs: if the signature includes *args, collect them as trailing CLI - # arguments in a list. *args can't have a default value, so it can never be - # an option. - if param.kind is param.VAR_POSITIONAL: - # TODO: consider depluralizing metavar/name here. - arg_spec['nargs'] = '*' - - # Add description. - if description is not None: - arg_spec['help'] = description - - # Get the --flags - flags = [] - name = param.name - - if is_option: - # Add the first letter as a -short option. - for letter in name[0], name[0].swapcase(): - if letter not in used_char_args: - used_char_args.add(letter) - flags.append('-{}'.format(letter)) - break - - # If the parameter is a --long option, or is a -short option that - # somehow failed to get a flag, add it. - if len(name) > 1 or not flags: - flags.append('--{}'.format(name)) - - arg_spec['dest'] = name - else: - flags.append(name) - - parser.add_argument(*flags, **arg_spec) - - # Create the --no- version for boolean switches - if add_nos and arg_type is bool: - parser.add_argument( - '--no-{}'.format(name), - action='store_const', - dest=name, - const=default if default is not _empty else False) - - -def make_parser(func_sig, description, epilog, add_nos): - ''' - Given the signature of a function, create an ArgumentParser - ''' - parser = ArgumentParser(description=description, epilog=epilog) - - used_char_args = {'h'} - - # Arange the params so that single-character arguments are first. This - # esnures they don't have to get --long versions. sorted is stable, so the - # parameters will otherwise still be in relative order. - params = sorted( - func_sig.parameters.values(), - key=lambda param: len(param.name) > 1) - - for param in params: - _add_arguments(param, parser, used_char_args, add_nos) - - return parser - - -_DOCSTRING_SPLIT = compile_regex(r'\n\s*-{4,}\s*\n') - - -def parse_docstring(docstring): - ''' - Given a docstring, parse it into a description and epilog part - ''' - if docstring is None: - return '', '' - - parts = _DOCSTRING_SPLIT.split(docstring) - - if len(parts) == 1: - return docstring, '' - elif len(parts) == 2: - return parts[0], parts[1] - else: - raise TooManySplitsError() - - -def autoparse( - func=None, *, - description=None, - epilog=None, - add_nos=False, - parser=None): - ''' - This decorator converts a function that takes normal arguments into a - function which takes a single optional argument, argv, parses it using an - argparse.ArgumentParser, and calls the underlying function with the parsed - arguments. If it is not given, sys.argv[1:] is used. This is so that the - function can be used as a setuptools entry point, as well as a normal main - function. sys.argv[1:] is not evaluated until the function is called, to - allow injecting different arguments for testing. - - It uses the argument signature of the function to create an - ArgumentParser. Parameters without defaults become positional parameters, - while parameters *with* defaults become --options. Use annotations to set - the type of the parameter. - - The `desctiption` and `epilog` parameters corrospond to the same respective - argparse parameters. If no description is given, it defaults to the - decorated functions's docstring, if present. - - If add_nos is True, every boolean option (that is, every parameter with a - default of True/False or a type of bool) will have a --no- version created - as well, which inverts the option. For instance, the --verbose option will - have a --no-verbose counterpart. These are not mutually exclusive- - whichever one appears last in the argument list will have precedence. - - If a parser is given, it is used instead of one generated from the function - signature. In this case, no parser is created; instead, the given parser is - used to parse the argv argument. The parser's results' argument names must - match up with the parameter names of the decorated function. - - The decorated function is attached to the result as the `func` attribute, - and the parser is attached as the `parser` attribute. - ''' - - # If @autoparse(...) is used instead of @autoparse - if func is None: - return lambda f: autoparse( - f, description=description, - epilog=epilog, - add_nos=add_nos, - parser=parser) - - func_sig = signature(func) - - docstr_description, docstr_epilog = parse_docstring(getdoc(func)) - - if parser is None: - parser = make_parser( - func_sig, - description or docstr_description, - epilog or docstr_epilog, - add_nos) - - @wraps(func) - def autoparse_wrapper(argv=None): - if argv is None: - argv = sys.argv[1:] - - # Get empty argument binding, to fill with parsed arguments. This - # object does all the heavy lifting of turning named arguments into - # into correctly bound *args and **kwargs. - parsed_args = func_sig.bind_partial() - parsed_args.arguments.update(vars(parser.parse_args(argv))) - - return func(*parsed_args.args, **parsed_args.kwargs) - - # TODO: attach an updated __signature__ to autoparse_wrapper, just in case. - - # Attach the wrapped function and parser, and return the wrapper. - autoparse_wrapper.func = func - autoparse_wrapper.parser = parser - return autoparse_wrapper - - -@contextmanager -def smart_open(filename_or_file, *args, **kwargs): - ''' - This context manager allows you to open a filename, if you want to default - some already-existing file object, like sys.stdout, which shouldn't be - closed at the end of the context. If the filename argument is a str, bytes, - or int, the file object is created via a call to open with the given *args - and **kwargs, sent to the context, and closed at the end of the context, - just like "with open(filename) as f:". If it isn't one of the openable - types, the object simply sent to the context unchanged, and left unclosed - at the end of the context. Example: - - def work_with_file(name=sys.stdout): - with smart_open(name) as f: - # Works correctly if name is a str filename or sys.stdout - print("Some stuff", file=f) - # If it was a filename, f is closed at the end here. - ''' - if isinstance(filename_or_file, (str, bytes, int)): - with open(filename_or_file, *args, **kwargs) as file: - yield file - else: - yield filename_or_file diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/errors.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/errors.py deleted file mode 100644 index 2570607..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/autocommand/errors.py +++ /dev/null @@ -1,23 +0,0 @@ -# Copyright 2014-2016 Nathan West -# -# This file is part of autocommand. -# -# autocommand is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# autocommand is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License for more details. -# -# You should have received a copy of the GNU Lesser General Public License -# along with autocommand. If not, see . - - -class AutocommandError(Exception): - '''Base class for autocommand exceptions''' - pass - -# Individual modules will define errors specific to that module. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/LICENSE deleted file mode 100644 index 1bb5a44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/LICENSE +++ /dev/null @@ -1,17 +0,0 @@ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/METADATA deleted file mode 100644 index db0a2dc..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/METADATA +++ /dev/null @@ -1,46 +0,0 @@ -Metadata-Version: 2.1 -Name: backports.tarfile -Version: 1.2.0 -Summary: Backport of CPython tarfile module -Author-email: "Jason R. Coombs" -Project-URL: Homepage, https://github.com/jaraco/backports.tarfile -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -License-File: LICENSE -Provides-Extra: docs -Requires-Dist: sphinx >=3.5 ; extra == 'docs' -Requires-Dist: jaraco.packaging >=9.3 ; extra == 'docs' -Requires-Dist: rst.linker >=1.9 ; extra == 'docs' -Requires-Dist: furo ; extra == 'docs' -Requires-Dist: sphinx-lint ; extra == 'docs' -Provides-Extra: testing -Requires-Dist: pytest !=8.1.*,>=6 ; extra == 'testing' -Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'testing' -Requires-Dist: pytest-cov ; extra == 'testing' -Requires-Dist: pytest-enabler >=2.2 ; extra == 'testing' -Requires-Dist: jaraco.test ; extra == 'testing' -Requires-Dist: pytest !=8.0.* ; extra == 'testing' - -.. image:: https://img.shields.io/pypi/v/backports.tarfile.svg - :target: https://pypi.org/project/backports.tarfile - -.. image:: https://img.shields.io/pypi/pyversions/backports.tarfile.svg - -.. image:: https://github.com/jaraco/backports.tarfile/actions/workflows/main.yml/badge.svg - :target: https://github.com/jaraco/backports.tarfile/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. .. image:: https://readthedocs.org/projects/backportstarfile/badge/?version=latest -.. :target: https://backportstarfile.readthedocs.io/en/latest/?badge=latest - -.. image:: https://img.shields.io/badge/skeleton-2024-informational - :target: https://blog.jaraco.com/skeleton diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/RECORD deleted file mode 100644 index 536dc2f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/RECORD +++ /dev/null @@ -1,17 +0,0 @@ -backports.tarfile-1.2.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -backports.tarfile-1.2.0.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -backports.tarfile-1.2.0.dist-info/METADATA,sha256=ghXFTq132dxaEIolxr3HK1mZqm9iyUmaRANZQSr6WlE,2020 -backports.tarfile-1.2.0.dist-info/RECORD,, -backports.tarfile-1.2.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -backports.tarfile-1.2.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -backports.tarfile-1.2.0.dist-info/top_level.txt,sha256=cGjaLMOoBR1FK0ApojtzWVmViTtJ7JGIK_HwXiEsvtU,10 -backports/__init__.py,sha256=iOEMwnlORWezdO8-2vxBIPSR37D7JGjluZ8f55vzxls,81 -backports/__pycache__/__init__.cpython-312.pyc,, -backports/tarfile/__init__.py,sha256=Pwf2qUIfB0SolJPCKcx3vz3UEu_aids4g4sAfxy94qg,108491 -backports/tarfile/__main__.py,sha256=Yw2oGT1afrz2eBskzdPYL8ReB_3liApmhFkN2EbDmc4,59 -backports/tarfile/__pycache__/__init__.cpython-312.pyc,, -backports/tarfile/__pycache__/__main__.cpython-312.pyc,, -backports/tarfile/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -backports/tarfile/compat/__pycache__/__init__.cpython-312.pyc,, -backports/tarfile/compat/__pycache__/py38.cpython-312.pyc,, -backports/tarfile/compat/py38.py,sha256=iYkyt_gvWjLzGUTJD9TuTfMMjOk-ersXZmRlvQYN2qE,568 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/WHEEL deleted file mode 100644 index bab98d6..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.43.0) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/top_level.txt deleted file mode 100644 index 99d2be5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports.tarfile-1.2.0.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -backports diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/__init__.py deleted file mode 100644 index 0d1f7ed..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/__init__.py +++ /dev/null @@ -1 +0,0 @@ -__path__ = __import__('pkgutil').extend_path(__path__, __name__) # type: ignore diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index f8aa932..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__init__.py deleted file mode 100644 index 8c16881..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__init__.py +++ /dev/null @@ -1,2937 +0,0 @@ -#------------------------------------------------------------------- -# tarfile.py -#------------------------------------------------------------------- -# Copyright (C) 2002 Lars Gustaebel -# All rights reserved. -# -# Permission is hereby granted, free of charge, to any person -# obtaining a copy of this software and associated documentation -# files (the "Software"), to deal in the Software without -# restriction, including without limitation the rights to use, -# copy, modify, merge, publish, distribute, sublicense, and/or sell -# copies of the Software, and to permit persons to whom the -# Software is furnished to do so, subject to the following -# conditions: -# -# The above copyright notice and this permission notice shall be -# included in all copies or substantial portions of the Software. -# -# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, -# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES -# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND -# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT -# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, -# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR -# OTHER DEALINGS IN THE SOFTWARE. -# -"""Read from and write to tar format archives. -""" - -version = "0.9.0" -__author__ = "Lars Gust\u00e4bel (lars@gustaebel.de)" -__credits__ = "Gustavo Niemeyer, Niels Gust\u00e4bel, Richard Townsend." - -#--------- -# Imports -#--------- -from builtins import open as bltn_open -import sys -import os -import io -import shutil -import stat -import time -import struct -import copy -import re - -from .compat.py38 import removesuffix - -try: - import pwd -except ImportError: - pwd = None -try: - import grp -except ImportError: - grp = None - -# os.symlink on Windows prior to 6.0 raises NotImplementedError -# OSError (winerror=1314) will be raised if the caller does not hold the -# SeCreateSymbolicLinkPrivilege privilege -symlink_exception = (AttributeError, NotImplementedError, OSError) - -# from tarfile import * -__all__ = ["TarFile", "TarInfo", "is_tarfile", "TarError", "ReadError", - "CompressionError", "StreamError", "ExtractError", "HeaderError", - "ENCODING", "USTAR_FORMAT", "GNU_FORMAT", "PAX_FORMAT", - "DEFAULT_FORMAT", "open","fully_trusted_filter", "data_filter", - "tar_filter", "FilterError", "AbsoluteLinkError", - "OutsideDestinationError", "SpecialFileError", "AbsolutePathError", - "LinkOutsideDestinationError"] - - -#--------------------------------------------------------- -# tar constants -#--------------------------------------------------------- -NUL = b"\0" # the null character -BLOCKSIZE = 512 # length of processing blocks -RECORDSIZE = BLOCKSIZE * 20 # length of records -GNU_MAGIC = b"ustar \0" # magic gnu tar string -POSIX_MAGIC = b"ustar\x0000" # magic posix tar string - -LENGTH_NAME = 100 # maximum length of a filename -LENGTH_LINK = 100 # maximum length of a linkname -LENGTH_PREFIX = 155 # maximum length of the prefix field - -REGTYPE = b"0" # regular file -AREGTYPE = b"\0" # regular file -LNKTYPE = b"1" # link (inside tarfile) -SYMTYPE = b"2" # symbolic link -CHRTYPE = b"3" # character special device -BLKTYPE = b"4" # block special device -DIRTYPE = b"5" # directory -FIFOTYPE = b"6" # fifo special device -CONTTYPE = b"7" # contiguous file - -GNUTYPE_LONGNAME = b"L" # GNU tar longname -GNUTYPE_LONGLINK = b"K" # GNU tar longlink -GNUTYPE_SPARSE = b"S" # GNU tar sparse file - -XHDTYPE = b"x" # POSIX.1-2001 extended header -XGLTYPE = b"g" # POSIX.1-2001 global header -SOLARIS_XHDTYPE = b"X" # Solaris extended header - -USTAR_FORMAT = 0 # POSIX.1-1988 (ustar) format -GNU_FORMAT = 1 # GNU tar format -PAX_FORMAT = 2 # POSIX.1-2001 (pax) format -DEFAULT_FORMAT = PAX_FORMAT - -#--------------------------------------------------------- -# tarfile constants -#--------------------------------------------------------- -# File types that tarfile supports: -SUPPORTED_TYPES = (REGTYPE, AREGTYPE, LNKTYPE, - SYMTYPE, DIRTYPE, FIFOTYPE, - CONTTYPE, CHRTYPE, BLKTYPE, - GNUTYPE_LONGNAME, GNUTYPE_LONGLINK, - GNUTYPE_SPARSE) - -# File types that will be treated as a regular file. -REGULAR_TYPES = (REGTYPE, AREGTYPE, - CONTTYPE, GNUTYPE_SPARSE) - -# File types that are part of the GNU tar format. -GNU_TYPES = (GNUTYPE_LONGNAME, GNUTYPE_LONGLINK, - GNUTYPE_SPARSE) - -# Fields from a pax header that override a TarInfo attribute. -PAX_FIELDS = ("path", "linkpath", "size", "mtime", - "uid", "gid", "uname", "gname") - -# Fields from a pax header that are affected by hdrcharset. -PAX_NAME_FIELDS = {"path", "linkpath", "uname", "gname"} - -# Fields in a pax header that are numbers, all other fields -# are treated as strings. -PAX_NUMBER_FIELDS = { - "atime": float, - "ctime": float, - "mtime": float, - "uid": int, - "gid": int, - "size": int -} - -#--------------------------------------------------------- -# initialization -#--------------------------------------------------------- -if os.name == "nt": - ENCODING = "utf-8" -else: - ENCODING = sys.getfilesystemencoding() - -#--------------------------------------------------------- -# Some useful functions -#--------------------------------------------------------- - -def stn(s, length, encoding, errors): - """Convert a string to a null-terminated bytes object. - """ - if s is None: - raise ValueError("metadata cannot contain None") - s = s.encode(encoding, errors) - return s[:length] + (length - len(s)) * NUL - -def nts(s, encoding, errors): - """Convert a null-terminated bytes object to a string. - """ - p = s.find(b"\0") - if p != -1: - s = s[:p] - return s.decode(encoding, errors) - -def nti(s): - """Convert a number field to a python number. - """ - # There are two possible encodings for a number field, see - # itn() below. - if s[0] in (0o200, 0o377): - n = 0 - for i in range(len(s) - 1): - n <<= 8 - n += s[i + 1] - if s[0] == 0o377: - n = -(256 ** (len(s) - 1) - n) - else: - try: - s = nts(s, "ascii", "strict") - n = int(s.strip() or "0", 8) - except ValueError: - raise InvalidHeaderError("invalid header") - return n - -def itn(n, digits=8, format=DEFAULT_FORMAT): - """Convert a python number to a number field. - """ - # POSIX 1003.1-1988 requires numbers to be encoded as a string of - # octal digits followed by a null-byte, this allows values up to - # (8**(digits-1))-1. GNU tar allows storing numbers greater than - # that if necessary. A leading 0o200 or 0o377 byte indicate this - # particular encoding, the following digits-1 bytes are a big-endian - # base-256 representation. This allows values up to (256**(digits-1))-1. - # A 0o200 byte indicates a positive number, a 0o377 byte a negative - # number. - original_n = n - n = int(n) - if 0 <= n < 8 ** (digits - 1): - s = bytes("%0*o" % (digits - 1, n), "ascii") + NUL - elif format == GNU_FORMAT and -256 ** (digits - 1) <= n < 256 ** (digits - 1): - if n >= 0: - s = bytearray([0o200]) - else: - s = bytearray([0o377]) - n = 256 ** digits + n - - for i in range(digits - 1): - s.insert(1, n & 0o377) - n >>= 8 - else: - raise ValueError("overflow in number field") - - return s - -def calc_chksums(buf): - """Calculate the checksum for a member's header by summing up all - characters except for the chksum field which is treated as if - it was filled with spaces. According to the GNU tar sources, - some tars (Sun and NeXT) calculate chksum with signed char, - which will be different if there are chars in the buffer with - the high bit set. So we calculate two checksums, unsigned and - signed. - """ - unsigned_chksum = 256 + sum(struct.unpack_from("148B8x356B", buf)) - signed_chksum = 256 + sum(struct.unpack_from("148b8x356b", buf)) - return unsigned_chksum, signed_chksum - -def copyfileobj(src, dst, length=None, exception=OSError, bufsize=None): - """Copy length bytes from fileobj src to fileobj dst. - If length is None, copy the entire content. - """ - bufsize = bufsize or 16 * 1024 - if length == 0: - return - if length is None: - shutil.copyfileobj(src, dst, bufsize) - return - - blocks, remainder = divmod(length, bufsize) - for b in range(blocks): - buf = src.read(bufsize) - if len(buf) < bufsize: - raise exception("unexpected end of data") - dst.write(buf) - - if remainder != 0: - buf = src.read(remainder) - if len(buf) < remainder: - raise exception("unexpected end of data") - dst.write(buf) - return - -def _safe_print(s): - encoding = getattr(sys.stdout, 'encoding', None) - if encoding is not None: - s = s.encode(encoding, 'backslashreplace').decode(encoding) - print(s, end=' ') - - -class TarError(Exception): - """Base exception.""" - pass -class ExtractError(TarError): - """General exception for extract errors.""" - pass -class ReadError(TarError): - """Exception for unreadable tar archives.""" - pass -class CompressionError(TarError): - """Exception for unavailable compression methods.""" - pass -class StreamError(TarError): - """Exception for unsupported operations on stream-like TarFiles.""" - pass -class HeaderError(TarError): - """Base exception for header errors.""" - pass -class EmptyHeaderError(HeaderError): - """Exception for empty headers.""" - pass -class TruncatedHeaderError(HeaderError): - """Exception for truncated headers.""" - pass -class EOFHeaderError(HeaderError): - """Exception for end of file headers.""" - pass -class InvalidHeaderError(HeaderError): - """Exception for invalid headers.""" - pass -class SubsequentHeaderError(HeaderError): - """Exception for missing and invalid extended headers.""" - pass - -#--------------------------- -# internal stream interface -#--------------------------- -class _LowLevelFile: - """Low-level file object. Supports reading and writing. - It is used instead of a regular file object for streaming - access. - """ - - def __init__(self, name, mode): - mode = { - "r": os.O_RDONLY, - "w": os.O_WRONLY | os.O_CREAT | os.O_TRUNC, - }[mode] - if hasattr(os, "O_BINARY"): - mode |= os.O_BINARY - self.fd = os.open(name, mode, 0o666) - - def close(self): - os.close(self.fd) - - def read(self, size): - return os.read(self.fd, size) - - def write(self, s): - os.write(self.fd, s) - -class _Stream: - """Class that serves as an adapter between TarFile and - a stream-like object. The stream-like object only - needs to have a read() or write() method that works with bytes, - and the method is accessed blockwise. - Use of gzip or bzip2 compression is possible. - A stream-like object could be for example: sys.stdin.buffer, - sys.stdout.buffer, a socket, a tape device etc. - - _Stream is intended to be used only internally. - """ - - def __init__(self, name, mode, comptype, fileobj, bufsize, - compresslevel): - """Construct a _Stream object. - """ - self._extfileobj = True - if fileobj is None: - fileobj = _LowLevelFile(name, mode) - self._extfileobj = False - - if comptype == '*': - # Enable transparent compression detection for the - # stream interface - fileobj = _StreamProxy(fileobj) - comptype = fileobj.getcomptype() - - self.name = name or "" - self.mode = mode - self.comptype = comptype - self.fileobj = fileobj - self.bufsize = bufsize - self.buf = b"" - self.pos = 0 - self.closed = False - - try: - if comptype == "gz": - try: - import zlib - except ImportError: - raise CompressionError("zlib module is not available") from None - self.zlib = zlib - self.crc = zlib.crc32(b"") - if mode == "r": - self.exception = zlib.error - self._init_read_gz() - else: - self._init_write_gz(compresslevel) - - elif comptype == "bz2": - try: - import bz2 - except ImportError: - raise CompressionError("bz2 module is not available") from None - if mode == "r": - self.dbuf = b"" - self.cmp = bz2.BZ2Decompressor() - self.exception = OSError - else: - self.cmp = bz2.BZ2Compressor(compresslevel) - - elif comptype == "xz": - try: - import lzma - except ImportError: - raise CompressionError("lzma module is not available") from None - if mode == "r": - self.dbuf = b"" - self.cmp = lzma.LZMADecompressor() - self.exception = lzma.LZMAError - else: - self.cmp = lzma.LZMACompressor() - - elif comptype != "tar": - raise CompressionError("unknown compression type %r" % comptype) - - except: - if not self._extfileobj: - self.fileobj.close() - self.closed = True - raise - - def __del__(self): - if hasattr(self, "closed") and not self.closed: - self.close() - - def _init_write_gz(self, compresslevel): - """Initialize for writing with gzip compression. - """ - self.cmp = self.zlib.compressobj(compresslevel, - self.zlib.DEFLATED, - -self.zlib.MAX_WBITS, - self.zlib.DEF_MEM_LEVEL, - 0) - timestamp = struct.pack(" self.bufsize: - self.fileobj.write(self.buf[:self.bufsize]) - self.buf = self.buf[self.bufsize:] - - def close(self): - """Close the _Stream object. No operation should be - done on it afterwards. - """ - if self.closed: - return - - self.closed = True - try: - if self.mode == "w" and self.comptype != "tar": - self.buf += self.cmp.flush() - - if self.mode == "w" and self.buf: - self.fileobj.write(self.buf) - self.buf = b"" - if self.comptype == "gz": - self.fileobj.write(struct.pack("= 0: - blocks, remainder = divmod(pos - self.pos, self.bufsize) - for i in range(blocks): - self.read(self.bufsize) - self.read(remainder) - else: - raise StreamError("seeking backwards is not allowed") - return self.pos - - def read(self, size): - """Return the next size number of bytes from the stream.""" - assert size is not None - buf = self._read(size) - self.pos += len(buf) - return buf - - def _read(self, size): - """Return size bytes from the stream. - """ - if self.comptype == "tar": - return self.__read(size) - - c = len(self.dbuf) - t = [self.dbuf] - while c < size: - # Skip underlying buffer to avoid unaligned double buffering. - if self.buf: - buf = self.buf - self.buf = b"" - else: - buf = self.fileobj.read(self.bufsize) - if not buf: - break - try: - buf = self.cmp.decompress(buf) - except self.exception as e: - raise ReadError("invalid compressed data") from e - t.append(buf) - c += len(buf) - t = b"".join(t) - self.dbuf = t[size:] - return t[:size] - - def __read(self, size): - """Return size bytes from stream. If internal buffer is empty, - read another block from the stream. - """ - c = len(self.buf) - t = [self.buf] - while c < size: - buf = self.fileobj.read(self.bufsize) - if not buf: - break - t.append(buf) - c += len(buf) - t = b"".join(t) - self.buf = t[size:] - return t[:size] -# class _Stream - -class _StreamProxy(object): - """Small proxy class that enables transparent compression - detection for the Stream interface (mode 'r|*'). - """ - - def __init__(self, fileobj): - self.fileobj = fileobj - self.buf = self.fileobj.read(BLOCKSIZE) - - def read(self, size): - self.read = self.fileobj.read - return self.buf - - def getcomptype(self): - if self.buf.startswith(b"\x1f\x8b\x08"): - return "gz" - elif self.buf[0:3] == b"BZh" and self.buf[4:10] == b"1AY&SY": - return "bz2" - elif self.buf.startswith((b"\x5d\x00\x00\x80", b"\xfd7zXZ")): - return "xz" - else: - return "tar" - - def close(self): - self.fileobj.close() -# class StreamProxy - -#------------------------ -# Extraction file object -#------------------------ -class _FileInFile(object): - """A thin wrapper around an existing file object that - provides a part of its data as an individual file - object. - """ - - def __init__(self, fileobj, offset, size, name, blockinfo=None): - self.fileobj = fileobj - self.offset = offset - self.size = size - self.position = 0 - self.name = name - self.closed = False - - if blockinfo is None: - blockinfo = [(0, size)] - - # Construct a map with data and zero blocks. - self.map_index = 0 - self.map = [] - lastpos = 0 - realpos = self.offset - for offset, size in blockinfo: - if offset > lastpos: - self.map.append((False, lastpos, offset, None)) - self.map.append((True, offset, offset + size, realpos)) - realpos += size - lastpos = offset + size - if lastpos < self.size: - self.map.append((False, lastpos, self.size, None)) - - def flush(self): - pass - - @property - def mode(self): - return 'rb' - - def readable(self): - return True - - def writable(self): - return False - - def seekable(self): - return self.fileobj.seekable() - - def tell(self): - """Return the current file position. - """ - return self.position - - def seek(self, position, whence=io.SEEK_SET): - """Seek to a position in the file. - """ - if whence == io.SEEK_SET: - self.position = min(max(position, 0), self.size) - elif whence == io.SEEK_CUR: - if position < 0: - self.position = max(self.position + position, 0) - else: - self.position = min(self.position + position, self.size) - elif whence == io.SEEK_END: - self.position = max(min(self.size + position, self.size), 0) - else: - raise ValueError("Invalid argument") - return self.position - - def read(self, size=None): - """Read data from the file. - """ - if size is None: - size = self.size - self.position - else: - size = min(size, self.size - self.position) - - buf = b"" - while size > 0: - while True: - data, start, stop, offset = self.map[self.map_index] - if start <= self.position < stop: - break - else: - self.map_index += 1 - if self.map_index == len(self.map): - self.map_index = 0 - length = min(size, stop - self.position) - if data: - self.fileobj.seek(offset + (self.position - start)) - b = self.fileobj.read(length) - if len(b) != length: - raise ReadError("unexpected end of data") - buf += b - else: - buf += NUL * length - size -= length - self.position += length - return buf - - def readinto(self, b): - buf = self.read(len(b)) - b[:len(buf)] = buf - return len(buf) - - def close(self): - self.closed = True -#class _FileInFile - -class ExFileObject(io.BufferedReader): - - def __init__(self, tarfile, tarinfo): - fileobj = _FileInFile(tarfile.fileobj, tarinfo.offset_data, - tarinfo.size, tarinfo.name, tarinfo.sparse) - super().__init__(fileobj) -#class ExFileObject - - -#----------------------------- -# extraction filters (PEP 706) -#----------------------------- - -class FilterError(TarError): - pass - -class AbsolutePathError(FilterError): - def __init__(self, tarinfo): - self.tarinfo = tarinfo - super().__init__(f'member {tarinfo.name!r} has an absolute path') - -class OutsideDestinationError(FilterError): - def __init__(self, tarinfo, path): - self.tarinfo = tarinfo - self._path = path - super().__init__(f'{tarinfo.name!r} would be extracted to {path!r}, ' - + 'which is outside the destination') - -class SpecialFileError(FilterError): - def __init__(self, tarinfo): - self.tarinfo = tarinfo - super().__init__(f'{tarinfo.name!r} is a special file') - -class AbsoluteLinkError(FilterError): - def __init__(self, tarinfo): - self.tarinfo = tarinfo - super().__init__(f'{tarinfo.name!r} is a link to an absolute path') - -class LinkOutsideDestinationError(FilterError): - def __init__(self, tarinfo, path): - self.tarinfo = tarinfo - self._path = path - super().__init__(f'{tarinfo.name!r} would link to {path!r}, ' - + 'which is outside the destination') - -def _get_filtered_attrs(member, dest_path, for_data=True): - new_attrs = {} - name = member.name - dest_path = os.path.realpath(dest_path) - # Strip leading / (tar's directory separator) from filenames. - # Include os.sep (target OS directory separator) as well. - if name.startswith(('/', os.sep)): - name = new_attrs['name'] = member.path.lstrip('/' + os.sep) - if os.path.isabs(name): - # Path is absolute even after stripping. - # For example, 'C:/foo' on Windows. - raise AbsolutePathError(member) - # Ensure we stay in the destination - target_path = os.path.realpath(os.path.join(dest_path, name)) - if os.path.commonpath([target_path, dest_path]) != dest_path: - raise OutsideDestinationError(member, target_path) - # Limit permissions (no high bits, and go-w) - mode = member.mode - if mode is not None: - # Strip high bits & group/other write bits - mode = mode & 0o755 - if for_data: - # For data, handle permissions & file types - if member.isreg() or member.islnk(): - if not mode & 0o100: - # Clear executable bits if not executable by user - mode &= ~0o111 - # Ensure owner can read & write - mode |= 0o600 - elif member.isdir() or member.issym(): - # Ignore mode for directories & symlinks - mode = None - else: - # Reject special files - raise SpecialFileError(member) - if mode != member.mode: - new_attrs['mode'] = mode - if for_data: - # Ignore ownership for 'data' - if member.uid is not None: - new_attrs['uid'] = None - if member.gid is not None: - new_attrs['gid'] = None - if member.uname is not None: - new_attrs['uname'] = None - if member.gname is not None: - new_attrs['gname'] = None - # Check link destination for 'data' - if member.islnk() or member.issym(): - if os.path.isabs(member.linkname): - raise AbsoluteLinkError(member) - if member.issym(): - target_path = os.path.join(dest_path, - os.path.dirname(name), - member.linkname) - else: - target_path = os.path.join(dest_path, - member.linkname) - target_path = os.path.realpath(target_path) - if os.path.commonpath([target_path, dest_path]) != dest_path: - raise LinkOutsideDestinationError(member, target_path) - return new_attrs - -def fully_trusted_filter(member, dest_path): - return member - -def tar_filter(member, dest_path): - new_attrs = _get_filtered_attrs(member, dest_path, False) - if new_attrs: - return member.replace(**new_attrs, deep=False) - return member - -def data_filter(member, dest_path): - new_attrs = _get_filtered_attrs(member, dest_path, True) - if new_attrs: - return member.replace(**new_attrs, deep=False) - return member - -_NAMED_FILTERS = { - "fully_trusted": fully_trusted_filter, - "tar": tar_filter, - "data": data_filter, -} - -#------------------ -# Exported Classes -#------------------ - -# Sentinel for replace() defaults, meaning "don't change the attribute" -_KEEP = object() - -class TarInfo(object): - """Informational class which holds the details about an - archive member given by a tar header block. - TarInfo objects are returned by TarFile.getmember(), - TarFile.getmembers() and TarFile.gettarinfo() and are - usually created internally. - """ - - __slots__ = dict( - name = 'Name of the archive member.', - mode = 'Permission bits.', - uid = 'User ID of the user who originally stored this member.', - gid = 'Group ID of the user who originally stored this member.', - size = 'Size in bytes.', - mtime = 'Time of last modification.', - chksum = 'Header checksum.', - type = ('File type. type is usually one of these constants: ' - 'REGTYPE, AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, ' - 'CONTTYPE, CHRTYPE, BLKTYPE, GNUTYPE_SPARSE.'), - linkname = ('Name of the target file name, which is only present ' - 'in TarInfo objects of type LNKTYPE and SYMTYPE.'), - uname = 'User name.', - gname = 'Group name.', - devmajor = 'Device major number.', - devminor = 'Device minor number.', - offset = 'The tar header starts here.', - offset_data = "The file's data starts here.", - pax_headers = ('A dictionary containing key-value pairs of an ' - 'associated pax extended header.'), - sparse = 'Sparse member information.', - _tarfile = None, - _sparse_structs = None, - _link_target = None, - ) - - def __init__(self, name=""): - """Construct a TarInfo object. name is the optional name - of the member. - """ - self.name = name # member name - self.mode = 0o644 # file permissions - self.uid = 0 # user id - self.gid = 0 # group id - self.size = 0 # file size - self.mtime = 0 # modification time - self.chksum = 0 # header checksum - self.type = REGTYPE # member type - self.linkname = "" # link name - self.uname = "" # user name - self.gname = "" # group name - self.devmajor = 0 # device major number - self.devminor = 0 # device minor number - - self.offset = 0 # the tar header starts here - self.offset_data = 0 # the file's data starts here - - self.sparse = None # sparse member information - self.pax_headers = {} # pax header information - - @property - def tarfile(self): - import warnings - warnings.warn( - 'The undocumented "tarfile" attribute of TarInfo objects ' - + 'is deprecated and will be removed in Python 3.16', - DeprecationWarning, stacklevel=2) - return self._tarfile - - @tarfile.setter - def tarfile(self, tarfile): - import warnings - warnings.warn( - 'The undocumented "tarfile" attribute of TarInfo objects ' - + 'is deprecated and will be removed in Python 3.16', - DeprecationWarning, stacklevel=2) - self._tarfile = tarfile - - @property - def path(self): - 'In pax headers, "name" is called "path".' - return self.name - - @path.setter - def path(self, name): - self.name = name - - @property - def linkpath(self): - 'In pax headers, "linkname" is called "linkpath".' - return self.linkname - - @linkpath.setter - def linkpath(self, linkname): - self.linkname = linkname - - def __repr__(self): - return "<%s %r at %#x>" % (self.__class__.__name__,self.name,id(self)) - - def replace(self, *, - name=_KEEP, mtime=_KEEP, mode=_KEEP, linkname=_KEEP, - uid=_KEEP, gid=_KEEP, uname=_KEEP, gname=_KEEP, - deep=True, _KEEP=_KEEP): - """Return a deep copy of self with the given attributes replaced. - """ - if deep: - result = copy.deepcopy(self) - else: - result = copy.copy(self) - if name is not _KEEP: - result.name = name - if mtime is not _KEEP: - result.mtime = mtime - if mode is not _KEEP: - result.mode = mode - if linkname is not _KEEP: - result.linkname = linkname - if uid is not _KEEP: - result.uid = uid - if gid is not _KEEP: - result.gid = gid - if uname is not _KEEP: - result.uname = uname - if gname is not _KEEP: - result.gname = gname - return result - - def get_info(self): - """Return the TarInfo's attributes as a dictionary. - """ - if self.mode is None: - mode = None - else: - mode = self.mode & 0o7777 - info = { - "name": self.name, - "mode": mode, - "uid": self.uid, - "gid": self.gid, - "size": self.size, - "mtime": self.mtime, - "chksum": self.chksum, - "type": self.type, - "linkname": self.linkname, - "uname": self.uname, - "gname": self.gname, - "devmajor": self.devmajor, - "devminor": self.devminor - } - - if info["type"] == DIRTYPE and not info["name"].endswith("/"): - info["name"] += "/" - - return info - - def tobuf(self, format=DEFAULT_FORMAT, encoding=ENCODING, errors="surrogateescape"): - """Return a tar header as a string of 512 byte blocks. - """ - info = self.get_info() - for name, value in info.items(): - if value is None: - raise ValueError("%s may not be None" % name) - - if format == USTAR_FORMAT: - return self.create_ustar_header(info, encoding, errors) - elif format == GNU_FORMAT: - return self.create_gnu_header(info, encoding, errors) - elif format == PAX_FORMAT: - return self.create_pax_header(info, encoding) - else: - raise ValueError("invalid format") - - def create_ustar_header(self, info, encoding, errors): - """Return the object as a ustar header block. - """ - info["magic"] = POSIX_MAGIC - - if len(info["linkname"].encode(encoding, errors)) > LENGTH_LINK: - raise ValueError("linkname is too long") - - if len(info["name"].encode(encoding, errors)) > LENGTH_NAME: - info["prefix"], info["name"] = self._posix_split_name(info["name"], encoding, errors) - - return self._create_header(info, USTAR_FORMAT, encoding, errors) - - def create_gnu_header(self, info, encoding, errors): - """Return the object as a GNU header block sequence. - """ - info["magic"] = GNU_MAGIC - - buf = b"" - if len(info["linkname"].encode(encoding, errors)) > LENGTH_LINK: - buf += self._create_gnu_long_header(info["linkname"], GNUTYPE_LONGLINK, encoding, errors) - - if len(info["name"].encode(encoding, errors)) > LENGTH_NAME: - buf += self._create_gnu_long_header(info["name"], GNUTYPE_LONGNAME, encoding, errors) - - return buf + self._create_header(info, GNU_FORMAT, encoding, errors) - - def create_pax_header(self, info, encoding): - """Return the object as a ustar header block. If it cannot be - represented this way, prepend a pax extended header sequence - with supplement information. - """ - info["magic"] = POSIX_MAGIC - pax_headers = self.pax_headers.copy() - - # Test string fields for values that exceed the field length or cannot - # be represented in ASCII encoding. - for name, hname, length in ( - ("name", "path", LENGTH_NAME), ("linkname", "linkpath", LENGTH_LINK), - ("uname", "uname", 32), ("gname", "gname", 32)): - - if hname in pax_headers: - # The pax header has priority. - continue - - # Try to encode the string as ASCII. - try: - info[name].encode("ascii", "strict") - except UnicodeEncodeError: - pax_headers[hname] = info[name] - continue - - if len(info[name]) > length: - pax_headers[hname] = info[name] - - # Test number fields for values that exceed the field limit or values - # that like to be stored as float. - for name, digits in (("uid", 8), ("gid", 8), ("size", 12), ("mtime", 12)): - needs_pax = False - - val = info[name] - val_is_float = isinstance(val, float) - val_int = round(val) if val_is_float else val - if not 0 <= val_int < 8 ** (digits - 1): - # Avoid overflow. - info[name] = 0 - needs_pax = True - elif val_is_float: - # Put rounded value in ustar header, and full - # precision value in pax header. - info[name] = val_int - needs_pax = True - - # The existing pax header has priority. - if needs_pax and name not in pax_headers: - pax_headers[name] = str(val) - - # Create a pax extended header if necessary. - if pax_headers: - buf = self._create_pax_generic_header(pax_headers, XHDTYPE, encoding) - else: - buf = b"" - - return buf + self._create_header(info, USTAR_FORMAT, "ascii", "replace") - - @classmethod - def create_pax_global_header(cls, pax_headers): - """Return the object as a pax global header block sequence. - """ - return cls._create_pax_generic_header(pax_headers, XGLTYPE, "utf-8") - - def _posix_split_name(self, name, encoding, errors): - """Split a name longer than 100 chars into a prefix - and a name part. - """ - components = name.split("/") - for i in range(1, len(components)): - prefix = "/".join(components[:i]) - name = "/".join(components[i:]) - if len(prefix.encode(encoding, errors)) <= LENGTH_PREFIX and \ - len(name.encode(encoding, errors)) <= LENGTH_NAME: - break - else: - raise ValueError("name is too long") - - return prefix, name - - @staticmethod - def _create_header(info, format, encoding, errors): - """Return a header block. info is a dictionary with file - information, format must be one of the *_FORMAT constants. - """ - has_device_fields = info.get("type") in (CHRTYPE, BLKTYPE) - if has_device_fields: - devmajor = itn(info.get("devmajor", 0), 8, format) - devminor = itn(info.get("devminor", 0), 8, format) - else: - devmajor = stn("", 8, encoding, errors) - devminor = stn("", 8, encoding, errors) - - # None values in metadata should cause ValueError. - # itn()/stn() do this for all fields except type. - filetype = info.get("type", REGTYPE) - if filetype is None: - raise ValueError("TarInfo.type must not be None") - - parts = [ - stn(info.get("name", ""), 100, encoding, errors), - itn(info.get("mode", 0) & 0o7777, 8, format), - itn(info.get("uid", 0), 8, format), - itn(info.get("gid", 0), 8, format), - itn(info.get("size", 0), 12, format), - itn(info.get("mtime", 0), 12, format), - b" ", # checksum field - filetype, - stn(info.get("linkname", ""), 100, encoding, errors), - info.get("magic", POSIX_MAGIC), - stn(info.get("uname", ""), 32, encoding, errors), - stn(info.get("gname", ""), 32, encoding, errors), - devmajor, - devminor, - stn(info.get("prefix", ""), 155, encoding, errors) - ] - - buf = struct.pack("%ds" % BLOCKSIZE, b"".join(parts)) - chksum = calc_chksums(buf[-BLOCKSIZE:])[0] - buf = buf[:-364] + bytes("%06o\0" % chksum, "ascii") + buf[-357:] - return buf - - @staticmethod - def _create_payload(payload): - """Return the string payload filled with zero bytes - up to the next 512 byte border. - """ - blocks, remainder = divmod(len(payload), BLOCKSIZE) - if remainder > 0: - payload += (BLOCKSIZE - remainder) * NUL - return payload - - @classmethod - def _create_gnu_long_header(cls, name, type, encoding, errors): - """Return a GNUTYPE_LONGNAME or GNUTYPE_LONGLINK sequence - for name. - """ - name = name.encode(encoding, errors) + NUL - - info = {} - info["name"] = "././@LongLink" - info["type"] = type - info["size"] = len(name) - info["magic"] = GNU_MAGIC - - # create extended header + name blocks. - return cls._create_header(info, USTAR_FORMAT, encoding, errors) + \ - cls._create_payload(name) - - @classmethod - def _create_pax_generic_header(cls, pax_headers, type, encoding): - """Return a POSIX.1-2008 extended or global header sequence - that contains a list of keyword, value pairs. The values - must be strings. - """ - # Check if one of the fields contains surrogate characters and thereby - # forces hdrcharset=BINARY, see _proc_pax() for more information. - binary = False - for keyword, value in pax_headers.items(): - try: - value.encode("utf-8", "strict") - except UnicodeEncodeError: - binary = True - break - - records = b"" - if binary: - # Put the hdrcharset field at the beginning of the header. - records += b"21 hdrcharset=BINARY\n" - - for keyword, value in pax_headers.items(): - keyword = keyword.encode("utf-8") - if binary: - # Try to restore the original byte representation of 'value'. - # Needless to say, that the encoding must match the string. - value = value.encode(encoding, "surrogateescape") - else: - value = value.encode("utf-8") - - l = len(keyword) + len(value) + 3 # ' ' + '=' + '\n' - n = p = 0 - while True: - n = l + len(str(p)) - if n == p: - break - p = n - records += bytes(str(p), "ascii") + b" " + keyword + b"=" + value + b"\n" - - # We use a hardcoded "././@PaxHeader" name like star does - # instead of the one that POSIX recommends. - info = {} - info["name"] = "././@PaxHeader" - info["type"] = type - info["size"] = len(records) - info["magic"] = POSIX_MAGIC - - # Create pax header + record blocks. - return cls._create_header(info, USTAR_FORMAT, "ascii", "replace") + \ - cls._create_payload(records) - - @classmethod - def frombuf(cls, buf, encoding, errors): - """Construct a TarInfo object from a 512 byte bytes object. - """ - if len(buf) == 0: - raise EmptyHeaderError("empty header") - if len(buf) != BLOCKSIZE: - raise TruncatedHeaderError("truncated header") - if buf.count(NUL) == BLOCKSIZE: - raise EOFHeaderError("end of file header") - - chksum = nti(buf[148:156]) - if chksum not in calc_chksums(buf): - raise InvalidHeaderError("bad checksum") - - obj = cls() - obj.name = nts(buf[0:100], encoding, errors) - obj.mode = nti(buf[100:108]) - obj.uid = nti(buf[108:116]) - obj.gid = nti(buf[116:124]) - obj.size = nti(buf[124:136]) - obj.mtime = nti(buf[136:148]) - obj.chksum = chksum - obj.type = buf[156:157] - obj.linkname = nts(buf[157:257], encoding, errors) - obj.uname = nts(buf[265:297], encoding, errors) - obj.gname = nts(buf[297:329], encoding, errors) - obj.devmajor = nti(buf[329:337]) - obj.devminor = nti(buf[337:345]) - prefix = nts(buf[345:500], encoding, errors) - - # Old V7 tar format represents a directory as a regular - # file with a trailing slash. - if obj.type == AREGTYPE and obj.name.endswith("/"): - obj.type = DIRTYPE - - # The old GNU sparse format occupies some of the unused - # space in the buffer for up to 4 sparse structures. - # Save them for later processing in _proc_sparse(). - if obj.type == GNUTYPE_SPARSE: - pos = 386 - structs = [] - for i in range(4): - try: - offset = nti(buf[pos:pos + 12]) - numbytes = nti(buf[pos + 12:pos + 24]) - except ValueError: - break - structs.append((offset, numbytes)) - pos += 24 - isextended = bool(buf[482]) - origsize = nti(buf[483:495]) - obj._sparse_structs = (structs, isextended, origsize) - - # Remove redundant slashes from directories. - if obj.isdir(): - obj.name = obj.name.rstrip("/") - - # Reconstruct a ustar longname. - if prefix and obj.type not in GNU_TYPES: - obj.name = prefix + "/" + obj.name - return obj - - @classmethod - def fromtarfile(cls, tarfile): - """Return the next TarInfo object from TarFile object - tarfile. - """ - buf = tarfile.fileobj.read(BLOCKSIZE) - obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors) - obj.offset = tarfile.fileobj.tell() - BLOCKSIZE - return obj._proc_member(tarfile) - - #-------------------------------------------------------------------------- - # The following are methods that are called depending on the type of a - # member. The entry point is _proc_member() which can be overridden in a - # subclass to add custom _proc_*() methods. A _proc_*() method MUST - # implement the following - # operations: - # 1. Set self.offset_data to the position where the data blocks begin, - # if there is data that follows. - # 2. Set tarfile.offset to the position where the next member's header will - # begin. - # 3. Return self or another valid TarInfo object. - def _proc_member(self, tarfile): - """Choose the right processing method depending on - the type and call it. - """ - if self.type in (GNUTYPE_LONGNAME, GNUTYPE_LONGLINK): - return self._proc_gnulong(tarfile) - elif self.type == GNUTYPE_SPARSE: - return self._proc_sparse(tarfile) - elif self.type in (XHDTYPE, XGLTYPE, SOLARIS_XHDTYPE): - return self._proc_pax(tarfile) - else: - return self._proc_builtin(tarfile) - - def _proc_builtin(self, tarfile): - """Process a builtin type or an unknown type which - will be treated as a regular file. - """ - self.offset_data = tarfile.fileobj.tell() - offset = self.offset_data - if self.isreg() or self.type not in SUPPORTED_TYPES: - # Skip the following data blocks. - offset += self._block(self.size) - tarfile.offset = offset - - # Patch the TarInfo object with saved global - # header information. - self._apply_pax_info(tarfile.pax_headers, tarfile.encoding, tarfile.errors) - - # Remove redundant slashes from directories. This is to be consistent - # with frombuf(). - if self.isdir(): - self.name = self.name.rstrip("/") - - return self - - def _proc_gnulong(self, tarfile): - """Process the blocks that hold a GNU longname - or longlink member. - """ - buf = tarfile.fileobj.read(self._block(self.size)) - - # Fetch the next header and process it. - try: - next = self.fromtarfile(tarfile) - except HeaderError as e: - raise SubsequentHeaderError(str(e)) from None - - # Patch the TarInfo object from the next header with - # the longname information. - next.offset = self.offset - if self.type == GNUTYPE_LONGNAME: - next.name = nts(buf, tarfile.encoding, tarfile.errors) - elif self.type == GNUTYPE_LONGLINK: - next.linkname = nts(buf, tarfile.encoding, tarfile.errors) - - # Remove redundant slashes from directories. This is to be consistent - # with frombuf(). - if next.isdir(): - next.name = removesuffix(next.name, "/") - - return next - - def _proc_sparse(self, tarfile): - """Process a GNU sparse header plus extra headers. - """ - # We already collected some sparse structures in frombuf(). - structs, isextended, origsize = self._sparse_structs - del self._sparse_structs - - # Collect sparse structures from extended header blocks. - while isextended: - buf = tarfile.fileobj.read(BLOCKSIZE) - pos = 0 - for i in range(21): - try: - offset = nti(buf[pos:pos + 12]) - numbytes = nti(buf[pos + 12:pos + 24]) - except ValueError: - break - if offset and numbytes: - structs.append((offset, numbytes)) - pos += 24 - isextended = bool(buf[504]) - self.sparse = structs - - self.offset_data = tarfile.fileobj.tell() - tarfile.offset = self.offset_data + self._block(self.size) - self.size = origsize - return self - - def _proc_pax(self, tarfile): - """Process an extended or global header as described in - POSIX.1-2008. - """ - # Read the header information. - buf = tarfile.fileobj.read(self._block(self.size)) - - # A pax header stores supplemental information for either - # the following file (extended) or all following files - # (global). - if self.type == XGLTYPE: - pax_headers = tarfile.pax_headers - else: - pax_headers = tarfile.pax_headers.copy() - - # Check if the pax header contains a hdrcharset field. This tells us - # the encoding of the path, linkpath, uname and gname fields. Normally, - # these fields are UTF-8 encoded but since POSIX.1-2008 tar - # implementations are allowed to store them as raw binary strings if - # the translation to UTF-8 fails. - match = re.search(br"\d+ hdrcharset=([^\n]+)\n", buf) - if match is not None: - pax_headers["hdrcharset"] = match.group(1).decode("utf-8") - - # For the time being, we don't care about anything other than "BINARY". - # The only other value that is currently allowed by the standard is - # "ISO-IR 10646 2000 UTF-8" in other words UTF-8. - hdrcharset = pax_headers.get("hdrcharset") - if hdrcharset == "BINARY": - encoding = tarfile.encoding - else: - encoding = "utf-8" - - # Parse pax header information. A record looks like that: - # "%d %s=%s\n" % (length, keyword, value). length is the size - # of the complete record including the length field itself and - # the newline. keyword and value are both UTF-8 encoded strings. - regex = re.compile(br"(\d+) ([^=]+)=") - pos = 0 - while match := regex.match(buf, pos): - length, keyword = match.groups() - length = int(length) - if length == 0: - raise InvalidHeaderError("invalid header") - value = buf[match.end(2) + 1:match.start(1) + length - 1] - - # Normally, we could just use "utf-8" as the encoding and "strict" - # as the error handler, but we better not take the risk. For - # example, GNU tar <= 1.23 is known to store filenames it cannot - # translate to UTF-8 as raw strings (unfortunately without a - # hdrcharset=BINARY header). - # We first try the strict standard encoding, and if that fails we - # fall back on the user's encoding and error handler. - keyword = self._decode_pax_field(keyword, "utf-8", "utf-8", - tarfile.errors) - if keyword in PAX_NAME_FIELDS: - value = self._decode_pax_field(value, encoding, tarfile.encoding, - tarfile.errors) - else: - value = self._decode_pax_field(value, "utf-8", "utf-8", - tarfile.errors) - - pax_headers[keyword] = value - pos += length - - # Fetch the next header. - try: - next = self.fromtarfile(tarfile) - except HeaderError as e: - raise SubsequentHeaderError(str(e)) from None - - # Process GNU sparse information. - if "GNU.sparse.map" in pax_headers: - # GNU extended sparse format version 0.1. - self._proc_gnusparse_01(next, pax_headers) - - elif "GNU.sparse.size" in pax_headers: - # GNU extended sparse format version 0.0. - self._proc_gnusparse_00(next, pax_headers, buf) - - elif pax_headers.get("GNU.sparse.major") == "1" and pax_headers.get("GNU.sparse.minor") == "0": - # GNU extended sparse format version 1.0. - self._proc_gnusparse_10(next, pax_headers, tarfile) - - if self.type in (XHDTYPE, SOLARIS_XHDTYPE): - # Patch the TarInfo object with the extended header info. - next._apply_pax_info(pax_headers, tarfile.encoding, tarfile.errors) - next.offset = self.offset - - if "size" in pax_headers: - # If the extended header replaces the size field, - # we need to recalculate the offset where the next - # header starts. - offset = next.offset_data - if next.isreg() or next.type not in SUPPORTED_TYPES: - offset += next._block(next.size) - tarfile.offset = offset - - return next - - def _proc_gnusparse_00(self, next, pax_headers, buf): - """Process a GNU tar extended sparse header, version 0.0. - """ - offsets = [] - for match in re.finditer(br"\d+ GNU.sparse.offset=(\d+)\n", buf): - offsets.append(int(match.group(1))) - numbytes = [] - for match in re.finditer(br"\d+ GNU.sparse.numbytes=(\d+)\n", buf): - numbytes.append(int(match.group(1))) - next.sparse = list(zip(offsets, numbytes)) - - def _proc_gnusparse_01(self, next, pax_headers): - """Process a GNU tar extended sparse header, version 0.1. - """ - sparse = [int(x) for x in pax_headers["GNU.sparse.map"].split(",")] - next.sparse = list(zip(sparse[::2], sparse[1::2])) - - def _proc_gnusparse_10(self, next, pax_headers, tarfile): - """Process a GNU tar extended sparse header, version 1.0. - """ - fields = None - sparse = [] - buf = tarfile.fileobj.read(BLOCKSIZE) - fields, buf = buf.split(b"\n", 1) - fields = int(fields) - while len(sparse) < fields * 2: - if b"\n" not in buf: - buf += tarfile.fileobj.read(BLOCKSIZE) - number, buf = buf.split(b"\n", 1) - sparse.append(int(number)) - next.offset_data = tarfile.fileobj.tell() - next.sparse = list(zip(sparse[::2], sparse[1::2])) - - def _apply_pax_info(self, pax_headers, encoding, errors): - """Replace fields with supplemental information from a previous - pax extended or global header. - """ - for keyword, value in pax_headers.items(): - if keyword == "GNU.sparse.name": - setattr(self, "path", value) - elif keyword == "GNU.sparse.size": - setattr(self, "size", int(value)) - elif keyword == "GNU.sparse.realsize": - setattr(self, "size", int(value)) - elif keyword in PAX_FIELDS: - if keyword in PAX_NUMBER_FIELDS: - try: - value = PAX_NUMBER_FIELDS[keyword](value) - except ValueError: - value = 0 - if keyword == "path": - value = value.rstrip("/") - setattr(self, keyword, value) - - self.pax_headers = pax_headers.copy() - - def _decode_pax_field(self, value, encoding, fallback_encoding, fallback_errors): - """Decode a single field from a pax record. - """ - try: - return value.decode(encoding, "strict") - except UnicodeDecodeError: - return value.decode(fallback_encoding, fallback_errors) - - def _block(self, count): - """Round up a byte count by BLOCKSIZE and return it, - e.g. _block(834) => 1024. - """ - blocks, remainder = divmod(count, BLOCKSIZE) - if remainder: - blocks += 1 - return blocks * BLOCKSIZE - - def isreg(self): - 'Return True if the Tarinfo object is a regular file.' - return self.type in REGULAR_TYPES - - def isfile(self): - 'Return True if the Tarinfo object is a regular file.' - return self.isreg() - - def isdir(self): - 'Return True if it is a directory.' - return self.type == DIRTYPE - - def issym(self): - 'Return True if it is a symbolic link.' - return self.type == SYMTYPE - - def islnk(self): - 'Return True if it is a hard link.' - return self.type == LNKTYPE - - def ischr(self): - 'Return True if it is a character device.' - return self.type == CHRTYPE - - def isblk(self): - 'Return True if it is a block device.' - return self.type == BLKTYPE - - def isfifo(self): - 'Return True if it is a FIFO.' - return self.type == FIFOTYPE - - def issparse(self): - return self.sparse is not None - - def isdev(self): - 'Return True if it is one of character device, block device or FIFO.' - return self.type in (CHRTYPE, BLKTYPE, FIFOTYPE) -# class TarInfo - -class TarFile(object): - """The TarFile Class provides an interface to tar archives. - """ - - debug = 0 # May be set from 0 (no msgs) to 3 (all msgs) - - dereference = False # If true, add content of linked file to the - # tar file, else the link. - - ignore_zeros = False # If true, skips empty or invalid blocks and - # continues processing. - - errorlevel = 1 # If 0, fatal errors only appear in debug - # messages (if debug >= 0). If > 0, errors - # are passed to the caller as exceptions. - - format = DEFAULT_FORMAT # The format to use when creating an archive. - - encoding = ENCODING # Encoding for 8-bit character strings. - - errors = None # Error handler for unicode conversion. - - tarinfo = TarInfo # The default TarInfo class to use. - - fileobject = ExFileObject # The file-object for extractfile(). - - extraction_filter = None # The default filter for extraction. - - def __init__(self, name=None, mode="r", fileobj=None, format=None, - tarinfo=None, dereference=None, ignore_zeros=None, encoding=None, - errors="surrogateescape", pax_headers=None, debug=None, - errorlevel=None, copybufsize=None, stream=False): - """Open an (uncompressed) tar archive 'name'. 'mode' is either 'r' to - read from an existing archive, 'a' to append data to an existing - file or 'w' to create a new file overwriting an existing one. 'mode' - defaults to 'r'. - If 'fileobj' is given, it is used for reading or writing data. If it - can be determined, 'mode' is overridden by 'fileobj's mode. - 'fileobj' is not closed, when TarFile is closed. - """ - modes = {"r": "rb", "a": "r+b", "w": "wb", "x": "xb"} - if mode not in modes: - raise ValueError("mode must be 'r', 'a', 'w' or 'x'") - self.mode = mode - self._mode = modes[mode] - - if not fileobj: - if self.mode == "a" and not os.path.exists(name): - # Create nonexistent files in append mode. - self.mode = "w" - self._mode = "wb" - fileobj = bltn_open(name, self._mode) - self._extfileobj = False - else: - if (name is None and hasattr(fileobj, "name") and - isinstance(fileobj.name, (str, bytes))): - name = fileobj.name - if hasattr(fileobj, "mode"): - self._mode = fileobj.mode - self._extfileobj = True - self.name = os.path.abspath(name) if name else None - self.fileobj = fileobj - - self.stream = stream - - # Init attributes. - if format is not None: - self.format = format - if tarinfo is not None: - self.tarinfo = tarinfo - if dereference is not None: - self.dereference = dereference - if ignore_zeros is not None: - self.ignore_zeros = ignore_zeros - if encoding is not None: - self.encoding = encoding - self.errors = errors - - if pax_headers is not None and self.format == PAX_FORMAT: - self.pax_headers = pax_headers - else: - self.pax_headers = {} - - if debug is not None: - self.debug = debug - if errorlevel is not None: - self.errorlevel = errorlevel - - # Init datastructures. - self.copybufsize = copybufsize - self.closed = False - self.members = [] # list of members as TarInfo objects - self._loaded = False # flag if all members have been read - self.offset = self.fileobj.tell() - # current position in the archive file - self.inodes = {} # dictionary caching the inodes of - # archive members already added - - try: - if self.mode == "r": - self.firstmember = None - self.firstmember = self.next() - - if self.mode == "a": - # Move to the end of the archive, - # before the first empty block. - while True: - self.fileobj.seek(self.offset) - try: - tarinfo = self.tarinfo.fromtarfile(self) - self.members.append(tarinfo) - except EOFHeaderError: - self.fileobj.seek(self.offset) - break - except HeaderError as e: - raise ReadError(str(e)) from None - - if self.mode in ("a", "w", "x"): - self._loaded = True - - if self.pax_headers: - buf = self.tarinfo.create_pax_global_header(self.pax_headers.copy()) - self.fileobj.write(buf) - self.offset += len(buf) - except: - if not self._extfileobj: - self.fileobj.close() - self.closed = True - raise - - #-------------------------------------------------------------------------- - # Below are the classmethods which act as alternate constructors to the - # TarFile class. The open() method is the only one that is needed for - # public use; it is the "super"-constructor and is able to select an - # adequate "sub"-constructor for a particular compression using the mapping - # from OPEN_METH. - # - # This concept allows one to subclass TarFile without losing the comfort of - # the super-constructor. A sub-constructor is registered and made available - # by adding it to the mapping in OPEN_METH. - - @classmethod - def open(cls, name=None, mode="r", fileobj=None, bufsize=RECORDSIZE, **kwargs): - r"""Open a tar archive for reading, writing or appending. Return - an appropriate TarFile class. - - mode: - 'r' or 'r:\*' open for reading with transparent compression - 'r:' open for reading exclusively uncompressed - 'r:gz' open for reading with gzip compression - 'r:bz2' open for reading with bzip2 compression - 'r:xz' open for reading with lzma compression - 'a' or 'a:' open for appending, creating the file if necessary - 'w' or 'w:' open for writing without compression - 'w:gz' open for writing with gzip compression - 'w:bz2' open for writing with bzip2 compression - 'w:xz' open for writing with lzma compression - - 'x' or 'x:' create a tarfile exclusively without compression, raise - an exception if the file is already created - 'x:gz' create a gzip compressed tarfile, raise an exception - if the file is already created - 'x:bz2' create a bzip2 compressed tarfile, raise an exception - if the file is already created - 'x:xz' create an lzma compressed tarfile, raise an exception - if the file is already created - - 'r|\*' open a stream of tar blocks with transparent compression - 'r|' open an uncompressed stream of tar blocks for reading - 'r|gz' open a gzip compressed stream of tar blocks - 'r|bz2' open a bzip2 compressed stream of tar blocks - 'r|xz' open an lzma compressed stream of tar blocks - 'w|' open an uncompressed stream for writing - 'w|gz' open a gzip compressed stream for writing - 'w|bz2' open a bzip2 compressed stream for writing - 'w|xz' open an lzma compressed stream for writing - """ - - if not name and not fileobj: - raise ValueError("nothing to open") - - if mode in ("r", "r:*"): - # Find out which *open() is appropriate for opening the file. - def not_compressed(comptype): - return cls.OPEN_METH[comptype] == 'taropen' - error_msgs = [] - for comptype in sorted(cls.OPEN_METH, key=not_compressed): - func = getattr(cls, cls.OPEN_METH[comptype]) - if fileobj is not None: - saved_pos = fileobj.tell() - try: - return func(name, "r", fileobj, **kwargs) - except (ReadError, CompressionError) as e: - error_msgs.append(f'- method {comptype}: {e!r}') - if fileobj is not None: - fileobj.seek(saved_pos) - continue - error_msgs_summary = '\n'.join(error_msgs) - raise ReadError(f"file could not be opened successfully:\n{error_msgs_summary}") - - elif ":" in mode: - filemode, comptype = mode.split(":", 1) - filemode = filemode or "r" - comptype = comptype or "tar" - - # Select the *open() function according to - # given compression. - if comptype in cls.OPEN_METH: - func = getattr(cls, cls.OPEN_METH[comptype]) - else: - raise CompressionError("unknown compression type %r" % comptype) - return func(name, filemode, fileobj, **kwargs) - - elif "|" in mode: - filemode, comptype = mode.split("|", 1) - filemode = filemode or "r" - comptype = comptype or "tar" - - if filemode not in ("r", "w"): - raise ValueError("mode must be 'r' or 'w'") - - compresslevel = kwargs.pop("compresslevel", 9) - stream = _Stream(name, filemode, comptype, fileobj, bufsize, - compresslevel) - try: - t = cls(name, filemode, stream, **kwargs) - except: - stream.close() - raise - t._extfileobj = False - return t - - elif mode in ("a", "w", "x"): - return cls.taropen(name, mode, fileobj, **kwargs) - - raise ValueError("undiscernible mode") - - @classmethod - def taropen(cls, name, mode="r", fileobj=None, **kwargs): - """Open uncompressed tar archive name for reading or writing. - """ - if mode not in ("r", "a", "w", "x"): - raise ValueError("mode must be 'r', 'a', 'w' or 'x'") - return cls(name, mode, fileobj, **kwargs) - - @classmethod - def gzopen(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs): - """Open gzip compressed tar archive name for reading or writing. - Appending is not allowed. - """ - if mode not in ("r", "w", "x"): - raise ValueError("mode must be 'r', 'w' or 'x'") - - try: - from gzip import GzipFile - except ImportError: - raise CompressionError("gzip module is not available") from None - - try: - fileobj = GzipFile(name, mode + "b", compresslevel, fileobj) - except OSError as e: - if fileobj is not None and mode == 'r': - raise ReadError("not a gzip file") from e - raise - - try: - t = cls.taropen(name, mode, fileobj, **kwargs) - except OSError as e: - fileobj.close() - if mode == 'r': - raise ReadError("not a gzip file") from e - raise - except: - fileobj.close() - raise - t._extfileobj = False - return t - - @classmethod - def bz2open(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs): - """Open bzip2 compressed tar archive name for reading or writing. - Appending is not allowed. - """ - if mode not in ("r", "w", "x"): - raise ValueError("mode must be 'r', 'w' or 'x'") - - try: - from bz2 import BZ2File - except ImportError: - raise CompressionError("bz2 module is not available") from None - - fileobj = BZ2File(fileobj or name, mode, compresslevel=compresslevel) - - try: - t = cls.taropen(name, mode, fileobj, **kwargs) - except (OSError, EOFError) as e: - fileobj.close() - if mode == 'r': - raise ReadError("not a bzip2 file") from e - raise - except: - fileobj.close() - raise - t._extfileobj = False - return t - - @classmethod - def xzopen(cls, name, mode="r", fileobj=None, preset=None, **kwargs): - """Open lzma compressed tar archive name for reading or writing. - Appending is not allowed. - """ - if mode not in ("r", "w", "x"): - raise ValueError("mode must be 'r', 'w' or 'x'") - - try: - from lzma import LZMAFile, LZMAError - except ImportError: - raise CompressionError("lzma module is not available") from None - - fileobj = LZMAFile(fileobj or name, mode, preset=preset) - - try: - t = cls.taropen(name, mode, fileobj, **kwargs) - except (LZMAError, EOFError) as e: - fileobj.close() - if mode == 'r': - raise ReadError("not an lzma file") from e - raise - except: - fileobj.close() - raise - t._extfileobj = False - return t - - # All *open() methods are registered here. - OPEN_METH = { - "tar": "taropen", # uncompressed tar - "gz": "gzopen", # gzip compressed tar - "bz2": "bz2open", # bzip2 compressed tar - "xz": "xzopen" # lzma compressed tar - } - - #-------------------------------------------------------------------------- - # The public methods which TarFile provides: - - def close(self): - """Close the TarFile. In write-mode, two finishing zero blocks are - appended to the archive. - """ - if self.closed: - return - - self.closed = True - try: - if self.mode in ("a", "w", "x"): - self.fileobj.write(NUL * (BLOCKSIZE * 2)) - self.offset += (BLOCKSIZE * 2) - # fill up the end with zero-blocks - # (like option -b20 for tar does) - blocks, remainder = divmod(self.offset, RECORDSIZE) - if remainder > 0: - self.fileobj.write(NUL * (RECORDSIZE - remainder)) - finally: - if not self._extfileobj: - self.fileobj.close() - - def getmember(self, name): - """Return a TarInfo object for member 'name'. If 'name' can not be - found in the archive, KeyError is raised. If a member occurs more - than once in the archive, its last occurrence is assumed to be the - most up-to-date version. - """ - tarinfo = self._getmember(name.rstrip('/')) - if tarinfo is None: - raise KeyError("filename %r not found" % name) - return tarinfo - - def getmembers(self): - """Return the members of the archive as a list of TarInfo objects. The - list has the same order as the members in the archive. - """ - self._check() - if not self._loaded: # if we want to obtain a list of - self._load() # all members, we first have to - # scan the whole archive. - return self.members - - def getnames(self): - """Return the members of the archive as a list of their names. It has - the same order as the list returned by getmembers(). - """ - return [tarinfo.name for tarinfo in self.getmembers()] - - def gettarinfo(self, name=None, arcname=None, fileobj=None): - """Create a TarInfo object from the result of os.stat or equivalent - on an existing file. The file is either named by 'name', or - specified as a file object 'fileobj' with a file descriptor. If - given, 'arcname' specifies an alternative name for the file in the - archive, otherwise, the name is taken from the 'name' attribute of - 'fileobj', or the 'name' argument. The name should be a text - string. - """ - self._check("awx") - - # When fileobj is given, replace name by - # fileobj's real name. - if fileobj is not None: - name = fileobj.name - - # Building the name of the member in the archive. - # Backward slashes are converted to forward slashes, - # Absolute paths are turned to relative paths. - if arcname is None: - arcname = name - drv, arcname = os.path.splitdrive(arcname) - arcname = arcname.replace(os.sep, "/") - arcname = arcname.lstrip("/") - - # Now, fill the TarInfo object with - # information specific for the file. - tarinfo = self.tarinfo() - tarinfo._tarfile = self # To be removed in 3.16. - - # Use os.stat or os.lstat, depending on if symlinks shall be resolved. - if fileobj is None: - if not self.dereference: - statres = os.lstat(name) - else: - statres = os.stat(name) - else: - statres = os.fstat(fileobj.fileno()) - linkname = "" - - stmd = statres.st_mode - if stat.S_ISREG(stmd): - inode = (statres.st_ino, statres.st_dev) - if not self.dereference and statres.st_nlink > 1 and \ - inode in self.inodes and arcname != self.inodes[inode]: - # Is it a hardlink to an already - # archived file? - type = LNKTYPE - linkname = self.inodes[inode] - else: - # The inode is added only if its valid. - # For win32 it is always 0. - type = REGTYPE - if inode[0]: - self.inodes[inode] = arcname - elif stat.S_ISDIR(stmd): - type = DIRTYPE - elif stat.S_ISFIFO(stmd): - type = FIFOTYPE - elif stat.S_ISLNK(stmd): - type = SYMTYPE - linkname = os.readlink(name) - elif stat.S_ISCHR(stmd): - type = CHRTYPE - elif stat.S_ISBLK(stmd): - type = BLKTYPE - else: - return None - - # Fill the TarInfo object with all - # information we can get. - tarinfo.name = arcname - tarinfo.mode = stmd - tarinfo.uid = statres.st_uid - tarinfo.gid = statres.st_gid - if type == REGTYPE: - tarinfo.size = statres.st_size - else: - tarinfo.size = 0 - tarinfo.mtime = statres.st_mtime - tarinfo.type = type - tarinfo.linkname = linkname - if pwd: - try: - tarinfo.uname = pwd.getpwuid(tarinfo.uid)[0] - except KeyError: - pass - if grp: - try: - tarinfo.gname = grp.getgrgid(tarinfo.gid)[0] - except KeyError: - pass - - if type in (CHRTYPE, BLKTYPE): - if hasattr(os, "major") and hasattr(os, "minor"): - tarinfo.devmajor = os.major(statres.st_rdev) - tarinfo.devminor = os.minor(statres.st_rdev) - return tarinfo - - def list(self, verbose=True, *, members=None): - """Print a table of contents to sys.stdout. If 'verbose' is False, only - the names of the members are printed. If it is True, an 'ls -l'-like - output is produced. 'members' is optional and must be a subset of the - list returned by getmembers(). - """ - # Convert tarinfo type to stat type. - type2mode = {REGTYPE: stat.S_IFREG, SYMTYPE: stat.S_IFLNK, - FIFOTYPE: stat.S_IFIFO, CHRTYPE: stat.S_IFCHR, - DIRTYPE: stat.S_IFDIR, BLKTYPE: stat.S_IFBLK} - self._check() - - if members is None: - members = self - for tarinfo in members: - if verbose: - if tarinfo.mode is None: - _safe_print("??????????") - else: - modetype = type2mode.get(tarinfo.type, 0) - _safe_print(stat.filemode(modetype | tarinfo.mode)) - _safe_print("%s/%s" % (tarinfo.uname or tarinfo.uid, - tarinfo.gname or tarinfo.gid)) - if tarinfo.ischr() or tarinfo.isblk(): - _safe_print("%10s" % - ("%d,%d" % (tarinfo.devmajor, tarinfo.devminor))) - else: - _safe_print("%10d" % tarinfo.size) - if tarinfo.mtime is None: - _safe_print("????-??-?? ??:??:??") - else: - _safe_print("%d-%02d-%02d %02d:%02d:%02d" \ - % time.localtime(tarinfo.mtime)[:6]) - - _safe_print(tarinfo.name + ("/" if tarinfo.isdir() else "")) - - if verbose: - if tarinfo.issym(): - _safe_print("-> " + tarinfo.linkname) - if tarinfo.islnk(): - _safe_print("link to " + tarinfo.linkname) - print() - - def add(self, name, arcname=None, recursive=True, *, filter=None): - """Add the file 'name' to the archive. 'name' may be any type of file - (directory, fifo, symbolic link, etc.). If given, 'arcname' - specifies an alternative name for the file in the archive. - Directories are added recursively by default. This can be avoided by - setting 'recursive' to False. 'filter' is a function - that expects a TarInfo object argument and returns the changed - TarInfo object, if it returns None the TarInfo object will be - excluded from the archive. - """ - self._check("awx") - - if arcname is None: - arcname = name - - # Skip if somebody tries to archive the archive... - if self.name is not None and os.path.abspath(name) == self.name: - self._dbg(2, "tarfile: Skipped %r" % name) - return - - self._dbg(1, name) - - # Create a TarInfo object from the file. - tarinfo = self.gettarinfo(name, arcname) - - if tarinfo is None: - self._dbg(1, "tarfile: Unsupported type %r" % name) - return - - # Change or exclude the TarInfo object. - if filter is not None: - tarinfo = filter(tarinfo) - if tarinfo is None: - self._dbg(2, "tarfile: Excluded %r" % name) - return - - # Append the tar header and data to the archive. - if tarinfo.isreg(): - with bltn_open(name, "rb") as f: - self.addfile(tarinfo, f) - - elif tarinfo.isdir(): - self.addfile(tarinfo) - if recursive: - for f in sorted(os.listdir(name)): - self.add(os.path.join(name, f), os.path.join(arcname, f), - recursive, filter=filter) - - else: - self.addfile(tarinfo) - - def addfile(self, tarinfo, fileobj=None): - """Add the TarInfo object 'tarinfo' to the archive. If 'tarinfo' represents - a non zero-size regular file, the 'fileobj' argument should be a binary file, - and tarinfo.size bytes are read from it and added to the archive. - You can create TarInfo objects directly, or by using gettarinfo(). - """ - self._check("awx") - - if fileobj is None and tarinfo.isreg() and tarinfo.size != 0: - raise ValueError("fileobj not provided for non zero-size regular file") - - tarinfo = copy.copy(tarinfo) - - buf = tarinfo.tobuf(self.format, self.encoding, self.errors) - self.fileobj.write(buf) - self.offset += len(buf) - bufsize=self.copybufsize - # If there's data to follow, append it. - if fileobj is not None: - copyfileobj(fileobj, self.fileobj, tarinfo.size, bufsize=bufsize) - blocks, remainder = divmod(tarinfo.size, BLOCKSIZE) - if remainder > 0: - self.fileobj.write(NUL * (BLOCKSIZE - remainder)) - blocks += 1 - self.offset += blocks * BLOCKSIZE - - self.members.append(tarinfo) - - def _get_filter_function(self, filter): - if filter is None: - filter = self.extraction_filter - if filter is None: - import warnings - warnings.warn( - 'Python 3.14 will, by default, filter extracted tar ' - + 'archives and reject files or modify their metadata. ' - + 'Use the filter argument to control this behavior.', - DeprecationWarning, stacklevel=3) - return fully_trusted_filter - if isinstance(filter, str): - raise TypeError( - 'String names are not supported for ' - + 'TarFile.extraction_filter. Use a function such as ' - + 'tarfile.data_filter directly.') - return filter - if callable(filter): - return filter - try: - return _NAMED_FILTERS[filter] - except KeyError: - raise ValueError(f"filter {filter!r} not found") from None - - def extractall(self, path=".", members=None, *, numeric_owner=False, - filter=None): - """Extract all members from the archive to the current working - directory and set owner, modification time and permissions on - directories afterwards. 'path' specifies a different directory - to extract to. 'members' is optional and must be a subset of the - list returned by getmembers(). If 'numeric_owner' is True, only - the numbers for user/group names are used and not the names. - - The 'filter' function will be called on each member just - before extraction. - It can return a changed TarInfo or None to skip the member. - String names of common filters are accepted. - """ - directories = [] - - filter_function = self._get_filter_function(filter) - if members is None: - members = self - - for member in members: - tarinfo = self._get_extract_tarinfo(member, filter_function, path) - if tarinfo is None: - continue - if tarinfo.isdir(): - # For directories, delay setting attributes until later, - # since permissions can interfere with extraction and - # extracting contents can reset mtime. - directories.append(tarinfo) - self._extract_one(tarinfo, path, set_attrs=not tarinfo.isdir(), - numeric_owner=numeric_owner) - - # Reverse sort directories. - directories.sort(key=lambda a: a.name, reverse=True) - - # Set correct owner, mtime and filemode on directories. - for tarinfo in directories: - dirpath = os.path.join(path, tarinfo.name) - try: - self.chown(tarinfo, dirpath, numeric_owner=numeric_owner) - self.utime(tarinfo, dirpath) - self.chmod(tarinfo, dirpath) - except ExtractError as e: - self._handle_nonfatal_error(e) - - def extract(self, member, path="", set_attrs=True, *, numeric_owner=False, - filter=None): - """Extract a member from the archive to the current working directory, - using its full name. Its file information is extracted as accurately - as possible. 'member' may be a filename or a TarInfo object. You can - specify a different directory using 'path'. File attributes (owner, - mtime, mode) are set unless 'set_attrs' is False. If 'numeric_owner' - is True, only the numbers for user/group names are used and not - the names. - - The 'filter' function will be called before extraction. - It can return a changed TarInfo or None to skip the member. - String names of common filters are accepted. - """ - filter_function = self._get_filter_function(filter) - tarinfo = self._get_extract_tarinfo(member, filter_function, path) - if tarinfo is not None: - self._extract_one(tarinfo, path, set_attrs, numeric_owner) - - def _get_extract_tarinfo(self, member, filter_function, path): - """Get filtered TarInfo (or None) from member, which might be a str""" - if isinstance(member, str): - tarinfo = self.getmember(member) - else: - tarinfo = member - - unfiltered = tarinfo - try: - tarinfo = filter_function(tarinfo, path) - except (OSError, FilterError) as e: - self._handle_fatal_error(e) - except ExtractError as e: - self._handle_nonfatal_error(e) - if tarinfo is None: - self._dbg(2, "tarfile: Excluded %r" % unfiltered.name) - return None - # Prepare the link target for makelink(). - if tarinfo.islnk(): - tarinfo = copy.copy(tarinfo) - tarinfo._link_target = os.path.join(path, tarinfo.linkname) - return tarinfo - - def _extract_one(self, tarinfo, path, set_attrs, numeric_owner): - """Extract from filtered tarinfo to disk""" - self._check("r") - - try: - self._extract_member(tarinfo, os.path.join(path, tarinfo.name), - set_attrs=set_attrs, - numeric_owner=numeric_owner) - except OSError as e: - self._handle_fatal_error(e) - except ExtractError as e: - self._handle_nonfatal_error(e) - - def _handle_nonfatal_error(self, e): - """Handle non-fatal error (ExtractError) according to errorlevel""" - if self.errorlevel > 1: - raise - else: - self._dbg(1, "tarfile: %s" % e) - - def _handle_fatal_error(self, e): - """Handle "fatal" error according to self.errorlevel""" - if self.errorlevel > 0: - raise - elif isinstance(e, OSError): - if e.filename is None: - self._dbg(1, "tarfile: %s" % e.strerror) - else: - self._dbg(1, "tarfile: %s %r" % (e.strerror, e.filename)) - else: - self._dbg(1, "tarfile: %s %s" % (type(e).__name__, e)) - - def extractfile(self, member): - """Extract a member from the archive as a file object. 'member' may be - a filename or a TarInfo object. If 'member' is a regular file or - a link, an io.BufferedReader object is returned. For all other - existing members, None is returned. If 'member' does not appear - in the archive, KeyError is raised. - """ - self._check("r") - - if isinstance(member, str): - tarinfo = self.getmember(member) - else: - tarinfo = member - - if tarinfo.isreg() or tarinfo.type not in SUPPORTED_TYPES: - # Members with unknown types are treated as regular files. - return self.fileobject(self, tarinfo) - - elif tarinfo.islnk() or tarinfo.issym(): - if isinstance(self.fileobj, _Stream): - # A small but ugly workaround for the case that someone tries - # to extract a (sym)link as a file-object from a non-seekable - # stream of tar blocks. - raise StreamError("cannot extract (sym)link as file object") - else: - # A (sym)link's file object is its target's file object. - return self.extractfile(self._find_link_target(tarinfo)) - else: - # If there's no data associated with the member (directory, chrdev, - # blkdev, etc.), return None instead of a file object. - return None - - def _extract_member(self, tarinfo, targetpath, set_attrs=True, - numeric_owner=False): - """Extract the TarInfo object tarinfo to a physical - file called targetpath. - """ - # Fetch the TarInfo object for the given name - # and build the destination pathname, replacing - # forward slashes to platform specific separators. - targetpath = targetpath.rstrip("/") - targetpath = targetpath.replace("/", os.sep) - - # Create all upper directories. - upperdirs = os.path.dirname(targetpath) - if upperdirs and not os.path.exists(upperdirs): - # Create directories that are not part of the archive with - # default permissions. - os.makedirs(upperdirs, exist_ok=True) - - if tarinfo.islnk() or tarinfo.issym(): - self._dbg(1, "%s -> %s" % (tarinfo.name, tarinfo.linkname)) - else: - self._dbg(1, tarinfo.name) - - if tarinfo.isreg(): - self.makefile(tarinfo, targetpath) - elif tarinfo.isdir(): - self.makedir(tarinfo, targetpath) - elif tarinfo.isfifo(): - self.makefifo(tarinfo, targetpath) - elif tarinfo.ischr() or tarinfo.isblk(): - self.makedev(tarinfo, targetpath) - elif tarinfo.islnk() or tarinfo.issym(): - self.makelink(tarinfo, targetpath) - elif tarinfo.type not in SUPPORTED_TYPES: - self.makeunknown(tarinfo, targetpath) - else: - self.makefile(tarinfo, targetpath) - - if set_attrs: - self.chown(tarinfo, targetpath, numeric_owner) - if not tarinfo.issym(): - self.chmod(tarinfo, targetpath) - self.utime(tarinfo, targetpath) - - #-------------------------------------------------------------------------- - # Below are the different file methods. They are called via - # _extract_member() when extract() is called. They can be replaced in a - # subclass to implement other functionality. - - def makedir(self, tarinfo, targetpath): - """Make a directory called targetpath. - """ - try: - if tarinfo.mode is None: - # Use the system's default mode - os.mkdir(targetpath) - else: - # Use a safe mode for the directory, the real mode is set - # later in _extract_member(). - os.mkdir(targetpath, 0o700) - except FileExistsError: - if not os.path.isdir(targetpath): - raise - - def makefile(self, tarinfo, targetpath): - """Make a file called targetpath. - """ - source = self.fileobj - source.seek(tarinfo.offset_data) - bufsize = self.copybufsize - with bltn_open(targetpath, "wb") as target: - if tarinfo.sparse is not None: - for offset, size in tarinfo.sparse: - target.seek(offset) - copyfileobj(source, target, size, ReadError, bufsize) - target.seek(tarinfo.size) - target.truncate() - else: - copyfileobj(source, target, tarinfo.size, ReadError, bufsize) - - def makeunknown(self, tarinfo, targetpath): - """Make a file from a TarInfo object with an unknown type - at targetpath. - """ - self.makefile(tarinfo, targetpath) - self._dbg(1, "tarfile: Unknown file type %r, " \ - "extracted as regular file." % tarinfo.type) - - def makefifo(self, tarinfo, targetpath): - """Make a fifo called targetpath. - """ - if hasattr(os, "mkfifo"): - os.mkfifo(targetpath) - else: - raise ExtractError("fifo not supported by system") - - def makedev(self, tarinfo, targetpath): - """Make a character or block device called targetpath. - """ - if not hasattr(os, "mknod") or not hasattr(os, "makedev"): - raise ExtractError("special devices not supported by system") - - mode = tarinfo.mode - if mode is None: - # Use mknod's default - mode = 0o600 - if tarinfo.isblk(): - mode |= stat.S_IFBLK - else: - mode |= stat.S_IFCHR - - os.mknod(targetpath, mode, - os.makedev(tarinfo.devmajor, tarinfo.devminor)) - - def makelink(self, tarinfo, targetpath): - """Make a (symbolic) link called targetpath. If it cannot be created - (platform limitation), we try to make a copy of the referenced file - instead of a link. - """ - try: - # For systems that support symbolic and hard links. - if tarinfo.issym(): - if os.path.lexists(targetpath): - # Avoid FileExistsError on following os.symlink. - os.unlink(targetpath) - os.symlink(tarinfo.linkname, targetpath) - else: - if os.path.exists(tarinfo._link_target): - os.link(tarinfo._link_target, targetpath) - else: - self._extract_member(self._find_link_target(tarinfo), - targetpath) - except symlink_exception: - try: - self._extract_member(self._find_link_target(tarinfo), - targetpath) - except KeyError: - raise ExtractError("unable to resolve link inside archive") from None - - def chown(self, tarinfo, targetpath, numeric_owner): - """Set owner of targetpath according to tarinfo. If numeric_owner - is True, use .gid/.uid instead of .gname/.uname. If numeric_owner - is False, fall back to .gid/.uid when the search based on name - fails. - """ - if hasattr(os, "geteuid") and os.geteuid() == 0: - # We have to be root to do so. - g = tarinfo.gid - u = tarinfo.uid - if not numeric_owner: - try: - if grp and tarinfo.gname: - g = grp.getgrnam(tarinfo.gname)[2] - except KeyError: - pass - try: - if pwd and tarinfo.uname: - u = pwd.getpwnam(tarinfo.uname)[2] - except KeyError: - pass - if g is None: - g = -1 - if u is None: - u = -1 - try: - if tarinfo.issym() and hasattr(os, "lchown"): - os.lchown(targetpath, u, g) - else: - os.chown(targetpath, u, g) - except (OSError, OverflowError) as e: - # OverflowError can be raised if an ID doesn't fit in 'id_t' - raise ExtractError("could not change owner") from e - - def chmod(self, tarinfo, targetpath): - """Set file permissions of targetpath according to tarinfo. - """ - if tarinfo.mode is None: - return - try: - os.chmod(targetpath, tarinfo.mode) - except OSError as e: - raise ExtractError("could not change mode") from e - - def utime(self, tarinfo, targetpath): - """Set modification time of targetpath according to tarinfo. - """ - mtime = tarinfo.mtime - if mtime is None: - return - if not hasattr(os, 'utime'): - return - try: - os.utime(targetpath, (mtime, mtime)) - except OSError as e: - raise ExtractError("could not change modification time") from e - - #-------------------------------------------------------------------------- - def next(self): - """Return the next member of the archive as a TarInfo object, when - TarFile is opened for reading. Return None if there is no more - available. - """ - self._check("ra") - if self.firstmember is not None: - m = self.firstmember - self.firstmember = None - return m - - # Advance the file pointer. - if self.offset != self.fileobj.tell(): - if self.offset == 0: - return None - self.fileobj.seek(self.offset - 1) - if not self.fileobj.read(1): - raise ReadError("unexpected end of data") - - # Read the next block. - tarinfo = None - while True: - try: - tarinfo = self.tarinfo.fromtarfile(self) - except EOFHeaderError as e: - if self.ignore_zeros: - self._dbg(2, "0x%X: %s" % (self.offset, e)) - self.offset += BLOCKSIZE - continue - except InvalidHeaderError as e: - if self.ignore_zeros: - self._dbg(2, "0x%X: %s" % (self.offset, e)) - self.offset += BLOCKSIZE - continue - elif self.offset == 0: - raise ReadError(str(e)) from None - except EmptyHeaderError: - if self.offset == 0: - raise ReadError("empty file") from None - except TruncatedHeaderError as e: - if self.offset == 0: - raise ReadError(str(e)) from None - except SubsequentHeaderError as e: - raise ReadError(str(e)) from None - except Exception as e: - try: - import zlib - if isinstance(e, zlib.error): - raise ReadError(f'zlib error: {e}') from None - else: - raise e - except ImportError: - raise e - break - - if tarinfo is not None: - # if streaming the file we do not want to cache the tarinfo - if not self.stream: - self.members.append(tarinfo) - else: - self._loaded = True - - return tarinfo - - #-------------------------------------------------------------------------- - # Little helper methods: - - def _getmember(self, name, tarinfo=None, normalize=False): - """Find an archive member by name from bottom to top. - If tarinfo is given, it is used as the starting point. - """ - # Ensure that all members have been loaded. - members = self.getmembers() - - # Limit the member search list up to tarinfo. - skipping = False - if tarinfo is not None: - try: - index = members.index(tarinfo) - except ValueError: - # The given starting point might be a (modified) copy. - # We'll later skip members until we find an equivalent. - skipping = True - else: - # Happy fast path - members = members[:index] - - if normalize: - name = os.path.normpath(name) - - for member in reversed(members): - if skipping: - if tarinfo.offset == member.offset: - skipping = False - continue - if normalize: - member_name = os.path.normpath(member.name) - else: - member_name = member.name - - if name == member_name: - return member - - if skipping: - # Starting point was not found - raise ValueError(tarinfo) - - def _load(self): - """Read through the entire archive file and look for readable - members. This should not run if the file is set to stream. - """ - if not self.stream: - while self.next() is not None: - pass - self._loaded = True - - def _check(self, mode=None): - """Check if TarFile is still open, and if the operation's mode - corresponds to TarFile's mode. - """ - if self.closed: - raise OSError("%s is closed" % self.__class__.__name__) - if mode is not None and self.mode not in mode: - raise OSError("bad operation for mode %r" % self.mode) - - def _find_link_target(self, tarinfo): - """Find the target member of a symlink or hardlink member in the - archive. - """ - if tarinfo.issym(): - # Always search the entire archive. - linkname = "/".join(filter(None, (os.path.dirname(tarinfo.name), tarinfo.linkname))) - limit = None - else: - # Search the archive before the link, because a hard link is - # just a reference to an already archived file. - linkname = tarinfo.linkname - limit = tarinfo - - member = self._getmember(linkname, tarinfo=limit, normalize=True) - if member is None: - raise KeyError("linkname %r not found" % linkname) - return member - - def __iter__(self): - """Provide an iterator object. - """ - if self._loaded: - yield from self.members - return - - # Yield items using TarFile's next() method. - # When all members have been read, set TarFile as _loaded. - index = 0 - # Fix for SF #1100429: Under rare circumstances it can - # happen that getmembers() is called during iteration, - # which will have already exhausted the next() method. - if self.firstmember is not None: - tarinfo = self.next() - index += 1 - yield tarinfo - - while True: - if index < len(self.members): - tarinfo = self.members[index] - elif not self._loaded: - tarinfo = self.next() - if not tarinfo: - self._loaded = True - return - else: - return - index += 1 - yield tarinfo - - def _dbg(self, level, msg): - """Write debugging output to sys.stderr. - """ - if level <= self.debug: - print(msg, file=sys.stderr) - - def __enter__(self): - self._check() - return self - - def __exit__(self, type, value, traceback): - if type is None: - self.close() - else: - # An exception occurred. We must not call close() because - # it would try to write end-of-archive blocks and padding. - if not self._extfileobj: - self.fileobj.close() - self.closed = True - -#-------------------- -# exported functions -#-------------------- - -def is_tarfile(name): - """Return True if name points to a tar archive that we - are able to handle, else return False. - - 'name' should be a string, file, or file-like object. - """ - try: - if hasattr(name, "read"): - pos = name.tell() - t = open(fileobj=name) - name.seek(pos) - else: - t = open(name) - t.close() - return True - except TarError: - return False - -open = TarFile.open - - -def main(): - import argparse - - description = 'A simple command-line interface for tarfile module.' - parser = argparse.ArgumentParser(description=description) - parser.add_argument('-v', '--verbose', action='store_true', default=False, - help='Verbose output') - parser.add_argument('--filter', metavar='', - choices=_NAMED_FILTERS, - help='Filter for extraction') - - group = parser.add_mutually_exclusive_group(required=True) - group.add_argument('-l', '--list', metavar='', - help='Show listing of a tarfile') - group.add_argument('-e', '--extract', nargs='+', - metavar=('', ''), - help='Extract tarfile into target dir') - group.add_argument('-c', '--create', nargs='+', - metavar=('', ''), - help='Create tarfile from sources') - group.add_argument('-t', '--test', metavar='', - help='Test if a tarfile is valid') - - args = parser.parse_args() - - if args.filter and args.extract is None: - parser.exit(1, '--filter is only valid for extraction\n') - - if args.test is not None: - src = args.test - if is_tarfile(src): - with open(src, 'r') as tar: - tar.getmembers() - print(tar.getmembers(), file=sys.stderr) - if args.verbose: - print('{!r} is a tar archive.'.format(src)) - else: - parser.exit(1, '{!r} is not a tar archive.\n'.format(src)) - - elif args.list is not None: - src = args.list - if is_tarfile(src): - with TarFile.open(src, 'r:*') as tf: - tf.list(verbose=args.verbose) - else: - parser.exit(1, '{!r} is not a tar archive.\n'.format(src)) - - elif args.extract is not None: - if len(args.extract) == 1: - src = args.extract[0] - curdir = os.curdir - elif len(args.extract) == 2: - src, curdir = args.extract - else: - parser.exit(1, parser.format_help()) - - if is_tarfile(src): - with TarFile.open(src, 'r:*') as tf: - tf.extractall(path=curdir, filter=args.filter) - if args.verbose: - if curdir == '.': - msg = '{!r} file is extracted.'.format(src) - else: - msg = ('{!r} file is extracted ' - 'into {!r} directory.').format(src, curdir) - print(msg) - else: - parser.exit(1, '{!r} is not a tar archive.\n'.format(src)) - - elif args.create is not None: - tar_name = args.create.pop(0) - _, ext = os.path.splitext(tar_name) - compressions = { - # gz - '.gz': 'gz', - '.tgz': 'gz', - # xz - '.xz': 'xz', - '.txz': 'xz', - # bz2 - '.bz2': 'bz2', - '.tbz': 'bz2', - '.tbz2': 'bz2', - '.tb2': 'bz2', - } - tar_mode = 'w:' + compressions[ext] if ext in compressions else 'w' - tar_files = args.create - - with TarFile.open(tar_name, tar_mode) as tf: - for file_name in tar_files: - tf.add(file_name) - - if args.verbose: - print('{!r} file created.'.format(tar_name)) - -if __name__ == '__main__': - main() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__main__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__main__.py deleted file mode 100644 index daf5509..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__main__.py +++ /dev/null @@ -1,5 +0,0 @@ -from . import main - - -if __name__ == '__main__': - main() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 71b012b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__pycache__/__main__.cpython-312.pyc deleted file mode 100644 index a7d4e23..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/__pycache__/__main__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 156175a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__pycache__/py38.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__pycache__/py38.cpython-312.pyc deleted file mode 100644 index 8fb7820..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/__pycache__/py38.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/py38.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/py38.py deleted file mode 100644 index 20fbbfc..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/backports/tarfile/compat/py38.py +++ /dev/null @@ -1,24 +0,0 @@ -import sys - - -if sys.version_info < (3, 9): - - def removesuffix(self, suffix): - # suffix='' should not call self[:-0]. - if suffix and self.endswith(suffix): - return self[: -len(suffix)] - else: - return self[:] - - def removeprefix(self, prefix): - if self.startswith(prefix): - return self[len(prefix) :] - else: - return self[:] -else: - - def removesuffix(self, suffix): - return self.removesuffix(suffix) - - def removeprefix(self, prefix): - return self.removeprefix(prefix) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/LICENSE deleted file mode 100644 index d645695..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/LICENSE +++ /dev/null @@ -1,202 +0,0 @@ - - Apache License - Version 2.0, January 2004 - http://www.apache.org/licenses/ - - TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION - - 1. Definitions. - - "License" shall mean the terms and conditions for use, reproduction, - and distribution as defined by Sections 1 through 9 of this document. - - "Licensor" shall mean the copyright owner or entity authorized by - the copyright owner that is granting the License. - - "Legal Entity" shall mean the union of the acting entity and all - other entities that control, are controlled by, or are under common - control with that entity. For the purposes of this definition, - "control" means (i) the power, direct or indirect, to cause the - direction or management of such entity, whether by contract or - otherwise, or (ii) ownership of fifty percent (50%) or more of the - outstanding shares, or (iii) beneficial ownership of such entity. - - "You" (or "Your") shall mean an individual or Legal Entity - exercising permissions granted by this License. - - "Source" form shall mean the preferred form for making modifications, - including but not limited to software source code, documentation - source, and configuration files. - - "Object" form shall mean any form resulting from mechanical - transformation or translation of a Source form, including but - not limited to compiled object code, generated documentation, - and conversions to other media types. - - "Work" shall mean the work of authorship, whether in Source or - Object form, made available under the License, as indicated by a - copyright notice that is included in or attached to the work - (an example is provided in the Appendix below). - - "Derivative Works" shall mean any work, whether in Source or Object - form, that is based on (or derived from) the Work and for which the - editorial revisions, annotations, elaborations, or other modifications - represent, as a whole, an original work of authorship. For the purposes - of this License, Derivative Works shall not include works that remain - separable from, or merely link (or bind by name) to the interfaces of, - the Work and Derivative Works thereof. - - "Contribution" shall mean any work of authorship, including - the original version of the Work and any modifications or additions - to that Work or Derivative Works thereof, that is intentionally - submitted to Licensor for inclusion in the Work by the copyright owner - or by an individual or Legal Entity authorized to submit on behalf of - the copyright owner. For the purposes of this definition, "submitted" - means any form of electronic, verbal, or written communication sent - to the Licensor or its representatives, including but not limited to - communication on electronic mailing lists, source code control systems, - and issue tracking systems that are managed by, or on behalf of, the - Licensor for the purpose of discussing and improving the Work, but - excluding communication that is conspicuously marked or otherwise - designated in writing by the copyright owner as "Not a Contribution." - - "Contributor" shall mean Licensor and any individual or Legal Entity - on behalf of whom a Contribution has been received by Licensor and - subsequently incorporated within the Work. - - 2. Grant of Copyright License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - copyright license to reproduce, prepare Derivative Works of, - publicly display, publicly perform, sublicense, and distribute the - Work and such Derivative Works in Source or Object form. - - 3. Grant of Patent License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - (except as stated in this section) patent license to make, have made, - use, offer to sell, sell, import, and otherwise transfer the Work, - where such license applies only to those patent claims licensable - by such Contributor that are necessarily infringed by their - Contribution(s) alone or by combination of their Contribution(s) - with the Work to which such Contribution(s) was submitted. If You - institute patent litigation against any entity (including a - cross-claim or counterclaim in a lawsuit) alleging that the Work - or a Contribution incorporated within the Work constitutes direct - or contributory patent infringement, then any patent licenses - granted to You under this License for that Work shall terminate - as of the date such litigation is filed. - - 4. Redistribution. You may reproduce and distribute copies of the - Work or Derivative Works thereof in any medium, with or without - modifications, and in Source or Object form, provided that You - meet the following conditions: - - (a) You must give any other recipients of the Work or - Derivative Works a copy of this License; and - - (b) You must cause any modified files to carry prominent notices - stating that You changed the files; and - - (c) You must retain, in the Source form of any Derivative Works - that You distribute, all copyright, patent, trademark, and - attribution notices from the Source form of the Work, - excluding those notices that do not pertain to any part of - the Derivative Works; and - - (d) If the Work includes a "NOTICE" text file as part of its - distribution, then any Derivative Works that You distribute must - include a readable copy of the attribution notices contained - within such NOTICE file, excluding those notices that do not - pertain to any part of the Derivative Works, in at least one - of the following places: within a NOTICE text file distributed - as part of the Derivative Works; within the Source form or - documentation, if provided along with the Derivative Works; or, - within a display generated by the Derivative Works, if and - wherever such third-party notices normally appear. The contents - of the NOTICE file are for informational purposes only and - do not modify the License. You may add Your own attribution - notices within Derivative Works that You distribute, alongside - or as an addendum to the NOTICE text from the Work, provided - that such additional attribution notices cannot be construed - as modifying the License. - - You may add Your own copyright statement to Your modifications and - may provide additional or different license terms and conditions - for use, reproduction, or distribution of Your modifications, or - for any such Derivative Works as a whole, provided Your use, - reproduction, and distribution of the Work otherwise complies with - the conditions stated in this License. - - 5. Submission of Contributions. Unless You explicitly state otherwise, - any Contribution intentionally submitted for inclusion in the Work - by You to the Licensor shall be under the terms and conditions of - this License, without any additional terms or conditions. - Notwithstanding the above, nothing herein shall supersede or modify - the terms of any separate license agreement you may have executed - with Licensor regarding such Contributions. - - 6. Trademarks. This License does not grant permission to use the trade - names, trademarks, service marks, or product names of the Licensor, - except as required for reasonable and customary use in describing the - origin of the Work and reproducing the content of the NOTICE file. - - 7. Disclaimer of Warranty. Unless required by applicable law or - agreed to in writing, Licensor provides the Work (and each - Contributor provides its Contributions) on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or - implied, including, without limitation, any warranties or conditions - of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A - PARTICULAR PURPOSE. You are solely responsible for determining the - appropriateness of using or redistributing the Work and assume any - risks associated with Your exercise of permissions under this License. - - 8. Limitation of Liability. In no event and under no legal theory, - whether in tort (including negligence), contract, or otherwise, - unless required by applicable law (such as deliberate and grossly - negligent acts) or agreed to in writing, shall any Contributor be - liable to You for damages, including any direct, indirect, special, - incidental, or consequential damages of any character arising as a - result of this License or out of the use or inability to use the - Work (including but not limited to damages for loss of goodwill, - work stoppage, computer failure or malfunction, or any and all - other commercial damages or losses), even if such Contributor - has been advised of the possibility of such damages. - - 9. Accepting Warranty or Additional Liability. While redistributing - the Work or Derivative Works thereof, You may choose to offer, - and charge a fee for, acceptance of support, warranty, indemnity, - or other liability obligations and/or rights consistent with this - License. However, in accepting such obligations, You may act only - on Your own behalf and on Your sole responsibility, not on behalf - of any other Contributor, and only if You agree to indemnify, - defend, and hold each Contributor harmless for any liability - incurred by, or claims asserted against, such Contributor by reason - of your accepting any such warranty or additional liability. - - END OF TERMS AND CONDITIONS - - APPENDIX: How to apply the Apache License to your work. - - To apply the Apache License to your work, attach the following - boilerplate notice, with the fields enclosed by brackets "[]" - replaced with your own identifying information. (Don't include - the brackets!) The text should be enclosed in the appropriate - comment syntax for the file format. We also recommend that a - file or class name and description of purpose be included on the - same "printed page" as the copyright notice for easier - identification within third-party archives. - - Copyright [yyyy] [name of copyright owner] - - Licensed under the Apache License, Version 2.0 (the "License"); - you may not use this file except in compliance with the License. - You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - - Unless required by applicable law or agreed to in writing, software - distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the License for the specific language governing permissions and - limitations under the License. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/METADATA deleted file mode 100644 index 85513e8..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/METADATA +++ /dev/null @@ -1,129 +0,0 @@ -Metadata-Version: 2.1 -Name: importlib_metadata -Version: 8.0.0 -Summary: Read metadata from Python packages -Author-email: "Jason R. Coombs" -Project-URL: Source, https://github.com/python/importlib_metadata -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: Apache Software License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -License-File: LICENSE -Requires-Dist: zipp >=0.5 -Requires-Dist: typing-extensions >=3.6.4 ; python_version < "3.8" -Provides-Extra: doc -Requires-Dist: sphinx >=3.5 ; extra == 'doc' -Requires-Dist: jaraco.packaging >=9.3 ; extra == 'doc' -Requires-Dist: rst.linker >=1.9 ; extra == 'doc' -Requires-Dist: furo ; extra == 'doc' -Requires-Dist: sphinx-lint ; extra == 'doc' -Requires-Dist: jaraco.tidelift >=1.4 ; extra == 'doc' -Provides-Extra: perf -Requires-Dist: ipython ; extra == 'perf' -Provides-Extra: test -Requires-Dist: pytest !=8.1.*,>=6 ; extra == 'test' -Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'test' -Requires-Dist: pytest-cov ; extra == 'test' -Requires-Dist: pytest-mypy ; extra == 'test' -Requires-Dist: pytest-enabler >=2.2 ; extra == 'test' -Requires-Dist: pytest-ruff >=0.2.1 ; extra == 'test' -Requires-Dist: packaging ; extra == 'test' -Requires-Dist: pyfakefs ; extra == 'test' -Requires-Dist: flufl.flake8 ; extra == 'test' -Requires-Dist: pytest-perf >=0.9.2 ; extra == 'test' -Requires-Dist: jaraco.test >=5.4 ; extra == 'test' -Requires-Dist: importlib-resources >=1.3 ; (python_version < "3.9") and extra == 'test' - -.. image:: https://img.shields.io/pypi/v/importlib_metadata.svg - :target: https://pypi.org/project/importlib_metadata - -.. image:: https://img.shields.io/pypi/pyversions/importlib_metadata.svg - -.. image:: https://github.com/python/importlib_metadata/actions/workflows/main.yml/badge.svg - :target: https://github.com/python/importlib_metadata/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. image:: https://readthedocs.org/projects/importlib-metadata/badge/?version=latest - :target: https://importlib-metadata.readthedocs.io/en/latest/?badge=latest - -.. image:: https://img.shields.io/badge/skeleton-2024-informational - :target: https://blog.jaraco.com/skeleton - -.. image:: https://tidelift.com/badges/package/pypi/importlib-metadata - :target: https://tidelift.com/subscription/pkg/pypi-importlib-metadata?utm_source=pypi-importlib-metadata&utm_medium=readme - -Library to access the metadata for a Python package. - -This package supplies third-party access to the functionality of -`importlib.metadata `_ -including improvements added to subsequent Python versions. - - -Compatibility -============= - -New features are introduced in this third-party library and later merged -into CPython. The following table indicates which versions of this library -were contributed to different versions in the standard library: - -.. list-table:: - :header-rows: 1 - - * - importlib_metadata - - stdlib - * - 7.0 - - 3.13 - * - 6.5 - - 3.12 - * - 4.13 - - 3.11 - * - 4.6 - - 3.10 - * - 1.4 - - 3.8 - - -Usage -===== - -See the `online documentation `_ -for usage details. - -`Finder authors -`_ can -also add support for custom package installers. See the above documentation -for details. - - -Caveats -======= - -This project primarily supports third-party packages installed by PyPA -tools (or other conforming packages). It does not support: - -- Packages in the stdlib. -- Packages installed without metadata. - -Project details -=============== - - * Project home: https://github.com/python/importlib_metadata - * Report bugs at: https://github.com/python/importlib_metadata/issues - * Code hosting: https://github.com/python/importlib_metadata - * Documentation: https://importlib-metadata.readthedocs.io/ - -For Enterprise -============== - -Available as part of the Tidelift Subscription. - -This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. - -`Learn more `_. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/RECORD deleted file mode 100644 index 07b7dc5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/RECORD +++ /dev/null @@ -1,32 +0,0 @@ -importlib_metadata-8.0.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -importlib_metadata-8.0.0.dist-info/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358 -importlib_metadata-8.0.0.dist-info/METADATA,sha256=anuQ7_7h4J1bSEzfcjIBakPi2cyVQ7y7jklLHsBeH1k,4648 -importlib_metadata-8.0.0.dist-info/RECORD,, -importlib_metadata-8.0.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -importlib_metadata-8.0.0.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91 -importlib_metadata-8.0.0.dist-info/top_level.txt,sha256=CO3fD9yylANiXkrMo4qHLV_mqXL2sC5JFKgt1yWAT-A,19 -importlib_metadata/__init__.py,sha256=tZNB-23h8Bixi9uCrQqj9Yf0aeC--Josdy3IZRIQeB0,33798 -importlib_metadata/__pycache__/__init__.cpython-312.pyc,, -importlib_metadata/__pycache__/_adapters.cpython-312.pyc,, -importlib_metadata/__pycache__/_collections.cpython-312.pyc,, -importlib_metadata/__pycache__/_compat.cpython-312.pyc,, -importlib_metadata/__pycache__/_functools.cpython-312.pyc,, -importlib_metadata/__pycache__/_itertools.cpython-312.pyc,, -importlib_metadata/__pycache__/_meta.cpython-312.pyc,, -importlib_metadata/__pycache__/_text.cpython-312.pyc,, -importlib_metadata/__pycache__/diagnose.cpython-312.pyc,, -importlib_metadata/_adapters.py,sha256=rIhWTwBvYA1bV7i-5FfVX38qEXDTXFeS5cb5xJtP3ks,2317 -importlib_metadata/_collections.py,sha256=CJ0OTCHIjWA0ZIVS4voORAsn2R4R2cQBEtPsZEJpASY,743 -importlib_metadata/_compat.py,sha256=73QKrN9KNoaZzhbX5yPCCZa-FaALwXe8TPlDR72JgBU,1314 -importlib_metadata/_functools.py,sha256=PsY2-4rrKX4RVeRC1oGp1lB1pmC9eKN88_f-bD9uOoA,2895 -importlib_metadata/_itertools.py,sha256=cvr_2v8BRbxcIl5x5ldfqdHjhI8Yi8s8yk50G_nm6jQ,2068 -importlib_metadata/_meta.py,sha256=nxZ7C8GVlcBFAKWyVOn_dn7ot_twBcbm1NmvjIetBHI,1801 -importlib_metadata/_text.py,sha256=HCsFksZpJLeTP3NEk_ngrAeXVRRtTrtyh9eOABoRP4A,2166 -importlib_metadata/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -importlib_metadata/compat/__pycache__/__init__.cpython-312.pyc,, -importlib_metadata/compat/__pycache__/py311.cpython-312.pyc,, -importlib_metadata/compat/__pycache__/py39.cpython-312.pyc,, -importlib_metadata/compat/py311.py,sha256=uqm-K-uohyj1042TH4a9Er_I5o7667DvulcD-gC_fSA,608 -importlib_metadata/compat/py39.py,sha256=cPkMv6-0ilK-0Jw_Tkn0xYbOKJZc4WJKQHow0c2T44w,1102 -importlib_metadata/diagnose.py,sha256=nkSRMiowlmkhLYhKhvCg9glmt_11Cox-EmLzEbqYTa8,379 -importlib_metadata/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/REQUESTED deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/top_level.txt deleted file mode 100644 index bbb0754..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata-8.0.0.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -importlib_metadata diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__init__.py deleted file mode 100644 index ed48135..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__init__.py +++ /dev/null @@ -1,1083 +0,0 @@ -from __future__ import annotations - -import os -import re -import abc -import sys -import json -import zipp -import email -import types -import inspect -import pathlib -import operator -import textwrap -import functools -import itertools -import posixpath -import collections - -from . import _meta -from .compat import py39, py311 -from ._collections import FreezableDefaultDict, Pair -from ._compat import ( - NullFinder, - install, -) -from ._functools import method_cache, pass_none -from ._itertools import always_iterable, unique_everseen -from ._meta import PackageMetadata, SimplePath - -from contextlib import suppress -from importlib import import_module -from importlib.abc import MetaPathFinder -from itertools import starmap -from typing import Any, Iterable, List, Mapping, Match, Optional, Set, cast - -__all__ = [ - 'Distribution', - 'DistributionFinder', - 'PackageMetadata', - 'PackageNotFoundError', - 'distribution', - 'distributions', - 'entry_points', - 'files', - 'metadata', - 'packages_distributions', - 'requires', - 'version', -] - - -class PackageNotFoundError(ModuleNotFoundError): - """The package was not found.""" - - def __str__(self) -> str: - return f"No package metadata was found for {self.name}" - - @property - def name(self) -> str: # type: ignore[override] - (name,) = self.args - return name - - -class Sectioned: - """ - A simple entry point config parser for performance - - >>> for item in Sectioned.read(Sectioned._sample): - ... print(item) - Pair(name='sec1', value='# comments ignored') - Pair(name='sec1', value='a = 1') - Pair(name='sec1', value='b = 2') - Pair(name='sec2', value='a = 2') - - >>> res = Sectioned.section_pairs(Sectioned._sample) - >>> item = next(res) - >>> item.name - 'sec1' - >>> item.value - Pair(name='a', value='1') - >>> item = next(res) - >>> item.value - Pair(name='b', value='2') - >>> item = next(res) - >>> item.name - 'sec2' - >>> item.value - Pair(name='a', value='2') - >>> list(res) - [] - """ - - _sample = textwrap.dedent( - """ - [sec1] - # comments ignored - a = 1 - b = 2 - - [sec2] - a = 2 - """ - ).lstrip() - - @classmethod - def section_pairs(cls, text): - return ( - section._replace(value=Pair.parse(section.value)) - for section in cls.read(text, filter_=cls.valid) - if section.name is not None - ) - - @staticmethod - def read(text, filter_=None): - lines = filter(filter_, map(str.strip, text.splitlines())) - name = None - for value in lines: - section_match = value.startswith('[') and value.endswith(']') - if section_match: - name = value.strip('[]') - continue - yield Pair(name, value) - - @staticmethod - def valid(line: str): - return line and not line.startswith('#') - - -class EntryPoint: - """An entry point as defined by Python packaging conventions. - - See `the packaging docs on entry points - `_ - for more information. - - >>> ep = EntryPoint( - ... name=None, group=None, value='package.module:attr [extra1, extra2]') - >>> ep.module - 'package.module' - >>> ep.attr - 'attr' - >>> ep.extras - ['extra1', 'extra2'] - """ - - pattern = re.compile( - r'(?P[\w.]+)\s*' - r'(:\s*(?P[\w.]+)\s*)?' - r'((?P\[.*\])\s*)?$' - ) - """ - A regular expression describing the syntax for an entry point, - which might look like: - - - module - - package.module - - package.module:attribute - - package.module:object.attribute - - package.module:attr [extra1, extra2] - - Other combinations are possible as well. - - The expression is lenient about whitespace around the ':', - following the attr, and following any extras. - """ - - name: str - value: str - group: str - - dist: Optional[Distribution] = None - - def __init__(self, name: str, value: str, group: str) -> None: - vars(self).update(name=name, value=value, group=group) - - def load(self) -> Any: - """Load the entry point from its definition. If only a module - is indicated by the value, return that module. Otherwise, - return the named object. - """ - match = cast(Match, self.pattern.match(self.value)) - module = import_module(match.group('module')) - attrs = filter(None, (match.group('attr') or '').split('.')) - return functools.reduce(getattr, attrs, module) - - @property - def module(self) -> str: - match = self.pattern.match(self.value) - assert match is not None - return match.group('module') - - @property - def attr(self) -> str: - match = self.pattern.match(self.value) - assert match is not None - return match.group('attr') - - @property - def extras(self) -> List[str]: - match = self.pattern.match(self.value) - assert match is not None - return re.findall(r'\w+', match.group('extras') or '') - - def _for(self, dist): - vars(self).update(dist=dist) - return self - - def matches(self, **params): - """ - EntryPoint matches the given parameters. - - >>> ep = EntryPoint(group='foo', name='bar', value='bing:bong [extra1, extra2]') - >>> ep.matches(group='foo') - True - >>> ep.matches(name='bar', value='bing:bong [extra1, extra2]') - True - >>> ep.matches(group='foo', name='other') - False - >>> ep.matches() - True - >>> ep.matches(extras=['extra1', 'extra2']) - True - >>> ep.matches(module='bing') - True - >>> ep.matches(attr='bong') - True - """ - attrs = (getattr(self, param) for param in params) - return all(map(operator.eq, params.values(), attrs)) - - def _key(self): - return self.name, self.value, self.group - - def __lt__(self, other): - return self._key() < other._key() - - def __eq__(self, other): - return self._key() == other._key() - - def __setattr__(self, name, value): - raise AttributeError("EntryPoint objects are immutable.") - - def __repr__(self): - return ( - f'EntryPoint(name={self.name!r}, value={self.value!r}, ' - f'group={self.group!r})' - ) - - def __hash__(self) -> int: - return hash(self._key()) - - -class EntryPoints(tuple): - """ - An immutable collection of selectable EntryPoint objects. - """ - - __slots__ = () - - def __getitem__(self, name: str) -> EntryPoint: # type: ignore[override] - """ - Get the EntryPoint in self matching name. - """ - try: - return next(iter(self.select(name=name))) - except StopIteration: - raise KeyError(name) - - def __repr__(self): - """ - Repr with classname and tuple constructor to - signal that we deviate from regular tuple behavior. - """ - return '%s(%r)' % (self.__class__.__name__, tuple(self)) - - def select(self, **params) -> EntryPoints: - """ - Select entry points from self that match the - given parameters (typically group and/or name). - """ - return EntryPoints(ep for ep in self if py39.ep_matches(ep, **params)) - - @property - def names(self) -> Set[str]: - """ - Return the set of all names of all entry points. - """ - return {ep.name for ep in self} - - @property - def groups(self) -> Set[str]: - """ - Return the set of all groups of all entry points. - """ - return {ep.group for ep in self} - - @classmethod - def _from_text_for(cls, text, dist): - return cls(ep._for(dist) for ep in cls._from_text(text)) - - @staticmethod - def _from_text(text): - return ( - EntryPoint(name=item.value.name, value=item.value.value, group=item.name) - for item in Sectioned.section_pairs(text or '') - ) - - -class PackagePath(pathlib.PurePosixPath): - """A reference to a path in a package""" - - hash: Optional[FileHash] - size: int - dist: Distribution - - def read_text(self, encoding: str = 'utf-8') -> str: # type: ignore[override] - return self.locate().read_text(encoding=encoding) - - def read_binary(self) -> bytes: - return self.locate().read_bytes() - - def locate(self) -> SimplePath: - """Return a path-like object for this path""" - return self.dist.locate_file(self) - - -class FileHash: - def __init__(self, spec: str) -> None: - self.mode, _, self.value = spec.partition('=') - - def __repr__(self) -> str: - return f'' - - -class Distribution(metaclass=abc.ABCMeta): - """ - An abstract Python distribution package. - - Custom providers may derive from this class and define - the abstract methods to provide a concrete implementation - for their environment. Some providers may opt to override - the default implementation of some properties to bypass - the file-reading mechanism. - """ - - @abc.abstractmethod - def read_text(self, filename) -> Optional[str]: - """Attempt to load metadata file given by the name. - - Python distribution metadata is organized by blobs of text - typically represented as "files" in the metadata directory - (e.g. package-1.0.dist-info). These files include things - like: - - - METADATA: The distribution metadata including fields - like Name and Version and Description. - - entry_points.txt: A series of entry points as defined in - `the entry points spec `_. - - RECORD: A record of files according to - `this recording spec `_. - - A package may provide any set of files, including those - not listed here or none at all. - - :param filename: The name of the file in the distribution info. - :return: The text if found, otherwise None. - """ - - @abc.abstractmethod - def locate_file(self, path: str | os.PathLike[str]) -> SimplePath: - """ - Given a path to a file in this distribution, return a SimplePath - to it. - """ - - @classmethod - def from_name(cls, name: str) -> Distribution: - """Return the Distribution for the given package name. - - :param name: The name of the distribution package to search for. - :return: The Distribution instance (or subclass thereof) for the named - package, if found. - :raises PackageNotFoundError: When the named package's distribution - metadata cannot be found. - :raises ValueError: When an invalid value is supplied for name. - """ - if not name: - raise ValueError("A distribution name is required.") - try: - return next(iter(cls.discover(name=name))) - except StopIteration: - raise PackageNotFoundError(name) - - @classmethod - def discover( - cls, *, context: Optional[DistributionFinder.Context] = None, **kwargs - ) -> Iterable[Distribution]: - """Return an iterable of Distribution objects for all packages. - - Pass a ``context`` or pass keyword arguments for constructing - a context. - - :context: A ``DistributionFinder.Context`` object. - :return: Iterable of Distribution objects for packages matching - the context. - """ - if context and kwargs: - raise ValueError("cannot accept context and kwargs") - context = context or DistributionFinder.Context(**kwargs) - return itertools.chain.from_iterable( - resolver(context) for resolver in cls._discover_resolvers() - ) - - @staticmethod - def at(path: str | os.PathLike[str]) -> Distribution: - """Return a Distribution for the indicated metadata path. - - :param path: a string or path-like object - :return: a concrete Distribution instance for the path - """ - return PathDistribution(pathlib.Path(path)) - - @staticmethod - def _discover_resolvers(): - """Search the meta_path for resolvers (MetadataPathFinders).""" - declared = ( - getattr(finder, 'find_distributions', None) for finder in sys.meta_path - ) - return filter(None, declared) - - @property - def metadata(self) -> _meta.PackageMetadata: - """Return the parsed metadata for this Distribution. - - The returned object will have keys that name the various bits of - metadata per the - `Core metadata specifications `_. - - Custom providers may provide the METADATA file or override this - property. - """ - # deferred for performance (python/cpython#109829) - from . import _adapters - - opt_text = ( - self.read_text('METADATA') - or self.read_text('PKG-INFO') - # This last clause is here to support old egg-info files. Its - # effect is to just end up using the PathDistribution's self._path - # (which points to the egg-info file) attribute unchanged. - or self.read_text('') - ) - text = cast(str, opt_text) - return _adapters.Message(email.message_from_string(text)) - - @property - def name(self) -> str: - """Return the 'Name' metadata for the distribution package.""" - return self.metadata['Name'] - - @property - def _normalized_name(self): - """Return a normalized version of the name.""" - return Prepared.normalize(self.name) - - @property - def version(self) -> str: - """Return the 'Version' metadata for the distribution package.""" - return self.metadata['Version'] - - @property - def entry_points(self) -> EntryPoints: - """ - Return EntryPoints for this distribution. - - Custom providers may provide the ``entry_points.txt`` file - or override this property. - """ - return EntryPoints._from_text_for(self.read_text('entry_points.txt'), self) - - @property - def files(self) -> Optional[List[PackagePath]]: - """Files in this distribution. - - :return: List of PackagePath for this distribution or None - - Result is `None` if the metadata file that enumerates files - (i.e. RECORD for dist-info, or installed-files.txt or - SOURCES.txt for egg-info) is missing. - Result may be empty if the metadata exists but is empty. - - Custom providers are recommended to provide a "RECORD" file (in - ``read_text``) or override this property to allow for callers to be - able to resolve filenames provided by the package. - """ - - def make_file(name, hash=None, size_str=None): - result = PackagePath(name) - result.hash = FileHash(hash) if hash else None - result.size = int(size_str) if size_str else None - result.dist = self - return result - - @pass_none - def make_files(lines): - # Delay csv import, since Distribution.files is not as widely used - # as other parts of importlib.metadata - import csv - - return starmap(make_file, csv.reader(lines)) - - @pass_none - def skip_missing_files(package_paths): - return list(filter(lambda path: path.locate().exists(), package_paths)) - - return skip_missing_files( - make_files( - self._read_files_distinfo() - or self._read_files_egginfo_installed() - or self._read_files_egginfo_sources() - ) - ) - - def _read_files_distinfo(self): - """ - Read the lines of RECORD. - """ - text = self.read_text('RECORD') - return text and text.splitlines() - - def _read_files_egginfo_installed(self): - """ - Read installed-files.txt and return lines in a similar - CSV-parsable format as RECORD: each file must be placed - relative to the site-packages directory and must also be - quoted (since file names can contain literal commas). - - This file is written when the package is installed by pip, - but it might not be written for other installation methods. - Assume the file is accurate if it exists. - """ - text = self.read_text('installed-files.txt') - # Prepend the .egg-info/ subdir to the lines in this file. - # But this subdir is only available from PathDistribution's - # self._path. - subdir = getattr(self, '_path', None) - if not text or not subdir: - return - - paths = ( - py311.relative_fix((subdir / name).resolve()) - .relative_to(self.locate_file('').resolve(), walk_up=True) - .as_posix() - for name in text.splitlines() - ) - return map('"{}"'.format, paths) - - def _read_files_egginfo_sources(self): - """ - Read SOURCES.txt and return lines in a similar CSV-parsable - format as RECORD: each file name must be quoted (since it - might contain literal commas). - - Note that SOURCES.txt is not a reliable source for what - files are installed by a package. This file is generated - for a source archive, and the files that are present - there (e.g. setup.py) may not correctly reflect the files - that are present after the package has been installed. - """ - text = self.read_text('SOURCES.txt') - return text and map('"{}"'.format, text.splitlines()) - - @property - def requires(self) -> Optional[List[str]]: - """Generated requirements specified for this Distribution""" - reqs = self._read_dist_info_reqs() or self._read_egg_info_reqs() - return reqs and list(reqs) - - def _read_dist_info_reqs(self): - return self.metadata.get_all('Requires-Dist') - - def _read_egg_info_reqs(self): - source = self.read_text('requires.txt') - return pass_none(self._deps_from_requires_text)(source) - - @classmethod - def _deps_from_requires_text(cls, source): - return cls._convert_egg_info_reqs_to_simple_reqs(Sectioned.read(source)) - - @staticmethod - def _convert_egg_info_reqs_to_simple_reqs(sections): - """ - Historically, setuptools would solicit and store 'extra' - requirements, including those with environment markers, - in separate sections. More modern tools expect each - dependency to be defined separately, with any relevant - extras and environment markers attached directly to that - requirement. This method converts the former to the - latter. See _test_deps_from_requires_text for an example. - """ - - def make_condition(name): - return name and f'extra == "{name}"' - - def quoted_marker(section): - section = section or '' - extra, sep, markers = section.partition(':') - if extra and markers: - markers = f'({markers})' - conditions = list(filter(None, [markers, make_condition(extra)])) - return '; ' + ' and '.join(conditions) if conditions else '' - - def url_req_space(req): - """ - PEP 508 requires a space between the url_spec and the quoted_marker. - Ref python/importlib_metadata#357. - """ - # '@' is uniquely indicative of a url_req. - return ' ' * ('@' in req) - - for section in sections: - space = url_req_space(section.value) - yield section.value + space + quoted_marker(section.name) - - @property - def origin(self): - return self._load_json('direct_url.json') - - def _load_json(self, filename): - return pass_none(json.loads)( - self.read_text(filename), - object_hook=lambda data: types.SimpleNamespace(**data), - ) - - -class DistributionFinder(MetaPathFinder): - """ - A MetaPathFinder capable of discovering installed distributions. - - Custom providers should implement this interface in order to - supply metadata. - """ - - class Context: - """ - Keyword arguments presented by the caller to - ``distributions()`` or ``Distribution.discover()`` - to narrow the scope of a search for distributions - in all DistributionFinders. - - Each DistributionFinder may expect any parameters - and should attempt to honor the canonical - parameters defined below when appropriate. - - This mechanism gives a custom provider a means to - solicit additional details from the caller beyond - "name" and "path" when searching distributions. - For example, imagine a provider that exposes suites - of packages in either a "public" or "private" ``realm``. - A caller may wish to query only for distributions in - a particular realm and could call - ``distributions(realm="private")`` to signal to the - custom provider to only include distributions from that - realm. - """ - - name = None - """ - Specific name for which a distribution finder should match. - A name of ``None`` matches all distributions. - """ - - def __init__(self, **kwargs): - vars(self).update(kwargs) - - @property - def path(self) -> List[str]: - """ - The sequence of directory path that a distribution finder - should search. - - Typically refers to Python installed package paths such as - "site-packages" directories and defaults to ``sys.path``. - """ - return vars(self).get('path', sys.path) - - @abc.abstractmethod - def find_distributions(self, context=Context()) -> Iterable[Distribution]: - """ - Find distributions. - - Return an iterable of all Distribution instances capable of - loading the metadata for packages matching the ``context``, - a DistributionFinder.Context instance. - """ - - -class FastPath: - """ - Micro-optimized class for searching a root for children. - - Root is a path on the file system that may contain metadata - directories either as natural directories or within a zip file. - - >>> FastPath('').children() - ['...'] - - FastPath objects are cached and recycled for any given root. - - >>> FastPath('foobar') is FastPath('foobar') - True - """ - - @functools.lru_cache() # type: ignore - def __new__(cls, root): - return super().__new__(cls) - - def __init__(self, root): - self.root = root - - def joinpath(self, child): - return pathlib.Path(self.root, child) - - def children(self): - with suppress(Exception): - return os.listdir(self.root or '.') - with suppress(Exception): - return self.zip_children() - return [] - - def zip_children(self): - zip_path = zipp.Path(self.root) - names = zip_path.root.namelist() - self.joinpath = zip_path.joinpath - - return dict.fromkeys(child.split(posixpath.sep, 1)[0] for child in names) - - def search(self, name): - return self.lookup(self.mtime).search(name) - - @property - def mtime(self): - with suppress(OSError): - return os.stat(self.root).st_mtime - self.lookup.cache_clear() - - @method_cache - def lookup(self, mtime): - return Lookup(self) - - -class Lookup: - """ - A micro-optimized class for searching a (fast) path for metadata. - """ - - def __init__(self, path: FastPath): - """ - Calculate all of the children representing metadata. - - From the children in the path, calculate early all of the - children that appear to represent metadata (infos) or legacy - metadata (eggs). - """ - - base = os.path.basename(path.root).lower() - base_is_egg = base.endswith(".egg") - self.infos = FreezableDefaultDict(list) - self.eggs = FreezableDefaultDict(list) - - for child in path.children(): - low = child.lower() - if low.endswith((".dist-info", ".egg-info")): - # rpartition is faster than splitext and suitable for this purpose. - name = low.rpartition(".")[0].partition("-")[0] - normalized = Prepared.normalize(name) - self.infos[normalized].append(path.joinpath(child)) - elif base_is_egg and low == "egg-info": - name = base.rpartition(".")[0].partition("-")[0] - legacy_normalized = Prepared.legacy_normalize(name) - self.eggs[legacy_normalized].append(path.joinpath(child)) - - self.infos.freeze() - self.eggs.freeze() - - def search(self, prepared: Prepared): - """ - Yield all infos and eggs matching the Prepared query. - """ - infos = ( - self.infos[prepared.normalized] - if prepared - else itertools.chain.from_iterable(self.infos.values()) - ) - eggs = ( - self.eggs[prepared.legacy_normalized] - if prepared - else itertools.chain.from_iterable(self.eggs.values()) - ) - return itertools.chain(infos, eggs) - - -class Prepared: - """ - A prepared search query for metadata on a possibly-named package. - - Pre-calculates the normalization to prevent repeated operations. - - >>> none = Prepared(None) - >>> none.normalized - >>> none.legacy_normalized - >>> bool(none) - False - >>> sample = Prepared('Sample__Pkg-name.foo') - >>> sample.normalized - 'sample_pkg_name_foo' - >>> sample.legacy_normalized - 'sample__pkg_name.foo' - >>> bool(sample) - True - """ - - normalized = None - legacy_normalized = None - - def __init__(self, name: Optional[str]): - self.name = name - if name is None: - return - self.normalized = self.normalize(name) - self.legacy_normalized = self.legacy_normalize(name) - - @staticmethod - def normalize(name): - """ - PEP 503 normalization plus dashes as underscores. - """ - return re.sub(r"[-_.]+", "-", name).lower().replace('-', '_') - - @staticmethod - def legacy_normalize(name): - """ - Normalize the package name as found in the convention in - older packaging tools versions and specs. - """ - return name.lower().replace('-', '_') - - def __bool__(self): - return bool(self.name) - - -@install -class MetadataPathFinder(NullFinder, DistributionFinder): - """A degenerate finder for distribution packages on the file system. - - This finder supplies only a find_distributions() method for versions - of Python that do not have a PathFinder find_distributions(). - """ - - @classmethod - def find_distributions( - cls, context=DistributionFinder.Context() - ) -> Iterable[PathDistribution]: - """ - Find distributions. - - Return an iterable of all Distribution instances capable of - loading the metadata for packages matching ``context.name`` - (or all names if ``None`` indicated) along the paths in the list - of directories ``context.path``. - """ - found = cls._search_paths(context.name, context.path) - return map(PathDistribution, found) - - @classmethod - def _search_paths(cls, name, paths): - """Find metadata directories in paths heuristically.""" - prepared = Prepared(name) - return itertools.chain.from_iterable( - path.search(prepared) for path in map(FastPath, paths) - ) - - @classmethod - def invalidate_caches(cls) -> None: - FastPath.__new__.cache_clear() - - -class PathDistribution(Distribution): - def __init__(self, path: SimplePath) -> None: - """Construct a distribution. - - :param path: SimplePath indicating the metadata directory. - """ - self._path = path - - def read_text(self, filename: str | os.PathLike[str]) -> Optional[str]: - with suppress( - FileNotFoundError, - IsADirectoryError, - KeyError, - NotADirectoryError, - PermissionError, - ): - return self._path.joinpath(filename).read_text(encoding='utf-8') - - return None - - read_text.__doc__ = Distribution.read_text.__doc__ - - def locate_file(self, path: str | os.PathLike[str]) -> SimplePath: - return self._path.parent / path - - @property - def _normalized_name(self): - """ - Performance optimization: where possible, resolve the - normalized name from the file system path. - """ - stem = os.path.basename(str(self._path)) - return ( - pass_none(Prepared.normalize)(self._name_from_stem(stem)) - or super()._normalized_name - ) - - @staticmethod - def _name_from_stem(stem): - """ - >>> PathDistribution._name_from_stem('foo-3.0.egg-info') - 'foo' - >>> PathDistribution._name_from_stem('CherryPy-3.0.dist-info') - 'CherryPy' - >>> PathDistribution._name_from_stem('face.egg-info') - 'face' - >>> PathDistribution._name_from_stem('foo.bar') - """ - filename, ext = os.path.splitext(stem) - if ext not in ('.dist-info', '.egg-info'): - return - name, sep, rest = filename.partition('-') - return name - - -def distribution(distribution_name: str) -> Distribution: - """Get the ``Distribution`` instance for the named package. - - :param distribution_name: The name of the distribution package as a string. - :return: A ``Distribution`` instance (or subclass thereof). - """ - return Distribution.from_name(distribution_name) - - -def distributions(**kwargs) -> Iterable[Distribution]: - """Get all ``Distribution`` instances in the current environment. - - :return: An iterable of ``Distribution`` instances. - """ - return Distribution.discover(**kwargs) - - -def metadata(distribution_name: str) -> _meta.PackageMetadata: - """Get the metadata for the named package. - - :param distribution_name: The name of the distribution package to query. - :return: A PackageMetadata containing the parsed metadata. - """ - return Distribution.from_name(distribution_name).metadata - - -def version(distribution_name: str) -> str: - """Get the version string for the named package. - - :param distribution_name: The name of the distribution package to query. - :return: The version string for the package as defined in the package's - "Version" metadata key. - """ - return distribution(distribution_name).version - - -_unique = functools.partial( - unique_everseen, - key=py39.normalized_name, -) -""" -Wrapper for ``distributions`` to return unique distributions by name. -""" - - -def entry_points(**params) -> EntryPoints: - """Return EntryPoint objects for all installed packages. - - Pass selection parameters (group or name) to filter the - result to entry points matching those properties (see - EntryPoints.select()). - - :return: EntryPoints for all installed packages. - """ - eps = itertools.chain.from_iterable( - dist.entry_points for dist in _unique(distributions()) - ) - return EntryPoints(eps).select(**params) - - -def files(distribution_name: str) -> Optional[List[PackagePath]]: - """Return a list of files for the named package. - - :param distribution_name: The name of the distribution package to query. - :return: List of files composing the distribution. - """ - return distribution(distribution_name).files - - -def requires(distribution_name: str) -> Optional[List[str]]: - """ - Return a list of requirements for the named package. - - :return: An iterable of requirements, suitable for - packaging.requirement.Requirement. - """ - return distribution(distribution_name).requires - - -def packages_distributions() -> Mapping[str, List[str]]: - """ - Return a mapping of top-level packages to their - distributions. - - >>> import collections.abc - >>> pkgs = packages_distributions() - >>> all(isinstance(dist, collections.abc.Sequence) for dist in pkgs.values()) - True - """ - pkg_to_dist = collections.defaultdict(list) - for dist in distributions(): - for pkg in _top_level_declared(dist) or _top_level_inferred(dist): - pkg_to_dist[pkg].append(dist.metadata['Name']) - return dict(pkg_to_dist) - - -def _top_level_declared(dist): - return (dist.read_text('top_level.txt') or '').split() - - -def _topmost(name: PackagePath) -> Optional[str]: - """ - Return the top-most parent as long as there is a parent. - """ - top, *rest = name.parts - return top if rest else None - - -def _get_toplevel_name(name: PackagePath) -> str: - """ - Infer a possibly importable module name from a name presumed on - sys.path. - - >>> _get_toplevel_name(PackagePath('foo.py')) - 'foo' - >>> _get_toplevel_name(PackagePath('foo')) - 'foo' - >>> _get_toplevel_name(PackagePath('foo.pyc')) - 'foo' - >>> _get_toplevel_name(PackagePath('foo/__init__.py')) - 'foo' - >>> _get_toplevel_name(PackagePath('foo.pth')) - 'foo.pth' - >>> _get_toplevel_name(PackagePath('foo.dist-info')) - 'foo.dist-info' - """ - return _topmost(name) or ( - # python/typeshed#10328 - inspect.getmodulename(name) # type: ignore - or str(name) - ) - - -def _top_level_inferred(dist): - opt_names = set(map(_get_toplevel_name, always_iterable(dist.files))) - - def importable_name(name): - return '.' not in name - - return filter(importable_name, opt_names) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index a6dcf06..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_adapters.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_adapters.cpython-312.pyc deleted file mode 100644 index 043fd0a..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_adapters.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_collections.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_collections.cpython-312.pyc deleted file mode 100644 index c652e63..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_collections.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_compat.cpython-312.pyc deleted file mode 100644 index b1e6501..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_compat.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_functools.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_functools.cpython-312.pyc deleted file mode 100644 index f33a419..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_functools.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_itertools.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_itertools.cpython-312.pyc deleted file mode 100644 index b837c97..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_itertools.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_meta.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_meta.cpython-312.pyc deleted file mode 100644 index 5788deb..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_meta.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_text.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_text.cpython-312.pyc deleted file mode 100644 index 2b7f11f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/_text.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/diagnose.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/diagnose.cpython-312.pyc deleted file mode 100644 index 78fa7fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/__pycache__/diagnose.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_adapters.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_adapters.py deleted file mode 100644 index 6223263..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_adapters.py +++ /dev/null @@ -1,83 +0,0 @@ -import re -import textwrap -import email.message - -from ._text import FoldedCase - - -class Message(email.message.Message): - multiple_use_keys = set( - map( - FoldedCase, - [ - 'Classifier', - 'Obsoletes-Dist', - 'Platform', - 'Project-URL', - 'Provides-Dist', - 'Provides-Extra', - 'Requires-Dist', - 'Requires-External', - 'Supported-Platform', - 'Dynamic', - ], - ) - ) - """ - Keys that may be indicated multiple times per PEP 566. - """ - - def __new__(cls, orig: email.message.Message): - res = super().__new__(cls) - vars(res).update(vars(orig)) - return res - - def __init__(self, *args, **kwargs): - self._headers = self._repair_headers() - - # suppress spurious error from mypy - def __iter__(self): - return super().__iter__() - - def __getitem__(self, item): - """ - Override parent behavior to typical dict behavior. - - ``email.message.Message`` will emit None values for missing - keys. Typical mappings, including this ``Message``, will raise - a key error for missing keys. - - Ref python/importlib_metadata#371. - """ - res = super().__getitem__(item) - if res is None: - raise KeyError(item) - return res - - def _repair_headers(self): - def redent(value): - "Correct for RFC822 indentation" - if not value or '\n' not in value: - return value - return textwrap.dedent(' ' * 8 + value) - - headers = [(key, redent(value)) for key, value in vars(self)['_headers']] - if self._payload: - headers.append(('Description', self.get_payload())) - return headers - - @property - def json(self): - """ - Convert PackageMetadata to a JSON-compatible format - per PEP 0566. - """ - - def transform(key): - value = self.get_all(key) if key in self.multiple_use_keys else self[key] - if key == 'Keywords': - value = re.split(r'\s+', value) - tk = key.lower().replace('-', '_') - return tk, value - - return dict(map(transform, map(FoldedCase, self))) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_collections.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_collections.py deleted file mode 100644 index cf0954e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_collections.py +++ /dev/null @@ -1,30 +0,0 @@ -import collections - - -# from jaraco.collections 3.3 -class FreezableDefaultDict(collections.defaultdict): - """ - Often it is desirable to prevent the mutation of - a default dict after its initial construction, such - as to prevent mutation during iteration. - - >>> dd = FreezableDefaultDict(list) - >>> dd[0].append('1') - >>> dd.freeze() - >>> dd[1] - [] - >>> len(dd) - 1 - """ - - def __missing__(self, key): - return getattr(self, '_frozen', super().__missing__)(key) - - def freeze(self): - self._frozen = lambda key: self.default_factory() - - -class Pair(collections.namedtuple('Pair', 'name value')): - @classmethod - def parse(cls, text): - return cls(*map(str.strip, text.split("=", 1))) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_compat.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_compat.py deleted file mode 100644 index df312b1..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_compat.py +++ /dev/null @@ -1,57 +0,0 @@ -import sys -import platform - - -__all__ = ['install', 'NullFinder'] - - -def install(cls): - """ - Class decorator for installation on sys.meta_path. - - Adds the backport DistributionFinder to sys.meta_path and - attempts to disable the finder functionality of the stdlib - DistributionFinder. - """ - sys.meta_path.append(cls()) - disable_stdlib_finder() - return cls - - -def disable_stdlib_finder(): - """ - Give the backport primacy for discovering path-based distributions - by monkey-patching the stdlib O_O. - - See #91 for more background for rationale on this sketchy - behavior. - """ - - def matches(finder): - return getattr( - finder, '__module__', None - ) == '_frozen_importlib_external' and hasattr(finder, 'find_distributions') - - for finder in filter(matches, sys.meta_path): # pragma: nocover - del finder.find_distributions - - -class NullFinder: - """ - A "Finder" (aka "MetaPathFinder") that never finds any modules, - but may find distributions. - """ - - @staticmethod - def find_spec(*args, **kwargs): - return None - - -def pypy_partial(val): - """ - Adjust for variable stacklevel on partial under PyPy. - - Workaround for #327. - """ - is_pypy = platform.python_implementation() == 'PyPy' - return val + is_pypy diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_functools.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_functools.py deleted file mode 100644 index 71f66bd..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_functools.py +++ /dev/null @@ -1,104 +0,0 @@ -import types -import functools - - -# from jaraco.functools 3.3 -def method_cache(method, cache_wrapper=None): - """ - Wrap lru_cache to support storing the cache data in the object instances. - - Abstracts the common paradigm where the method explicitly saves an - underscore-prefixed protected property on first call and returns that - subsequently. - - >>> class MyClass: - ... calls = 0 - ... - ... @method_cache - ... def method(self, value): - ... self.calls += 1 - ... return value - - >>> a = MyClass() - >>> a.method(3) - 3 - >>> for x in range(75): - ... res = a.method(x) - >>> a.calls - 75 - - Note that the apparent behavior will be exactly like that of lru_cache - except that the cache is stored on each instance, so values in one - instance will not flush values from another, and when an instance is - deleted, so are the cached values for that instance. - - >>> b = MyClass() - >>> for x in range(35): - ... res = b.method(x) - >>> b.calls - 35 - >>> a.method(0) - 0 - >>> a.calls - 75 - - Note that if method had been decorated with ``functools.lru_cache()``, - a.calls would have been 76 (due to the cached value of 0 having been - flushed by the 'b' instance). - - Clear the cache with ``.cache_clear()`` - - >>> a.method.cache_clear() - - Same for a method that hasn't yet been called. - - >>> c = MyClass() - >>> c.method.cache_clear() - - Another cache wrapper may be supplied: - - >>> cache = functools.lru_cache(maxsize=2) - >>> MyClass.method2 = method_cache(lambda self: 3, cache_wrapper=cache) - >>> a = MyClass() - >>> a.method2() - 3 - - Caution - do not subsequently wrap the method with another decorator, such - as ``@property``, which changes the semantics of the function. - - See also - http://code.activestate.com/recipes/577452-a-memoize-decorator-for-instance-methods/ - for another implementation and additional justification. - """ - cache_wrapper = cache_wrapper or functools.lru_cache() - - def wrapper(self, *args, **kwargs): - # it's the first call, replace the method with a cached, bound method - bound_method = types.MethodType(method, self) - cached_method = cache_wrapper(bound_method) - setattr(self, method.__name__, cached_method) - return cached_method(*args, **kwargs) - - # Support cache clear even before cache has been created. - wrapper.cache_clear = lambda: None - - return wrapper - - -# From jaraco.functools 3.3 -def pass_none(func): - """ - Wrap func so it's not called if its first param is None - - >>> print_text = pass_none(print) - >>> print_text('text') - text - >>> print_text(None) - """ - - @functools.wraps(func) - def wrapper(param, *args, **kwargs): - if param is not None: - return func(param, *args, **kwargs) - - return wrapper diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_itertools.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_itertools.py deleted file mode 100644 index d4ca9b9..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_itertools.py +++ /dev/null @@ -1,73 +0,0 @@ -from itertools import filterfalse - - -def unique_everseen(iterable, key=None): - "List unique elements, preserving order. Remember all elements ever seen." - # unique_everseen('AAAABBBCCDAABBB') --> A B C D - # unique_everseen('ABBCcAD', str.lower) --> A B C D - seen = set() - seen_add = seen.add - if key is None: - for element in filterfalse(seen.__contains__, iterable): - seen_add(element) - yield element - else: - for element in iterable: - k = key(element) - if k not in seen: - seen_add(k) - yield element - - -# copied from more_itertools 8.8 -def always_iterable(obj, base_type=(str, bytes)): - """If *obj* is iterable, return an iterator over its items:: - - >>> obj = (1, 2, 3) - >>> list(always_iterable(obj)) - [1, 2, 3] - - If *obj* is not iterable, return a one-item iterable containing *obj*:: - - >>> obj = 1 - >>> list(always_iterable(obj)) - [1] - - If *obj* is ``None``, return an empty iterable: - - >>> obj = None - >>> list(always_iterable(None)) - [] - - By default, binary and text strings are not considered iterable:: - - >>> obj = 'foo' - >>> list(always_iterable(obj)) - ['foo'] - - If *base_type* is set, objects for which ``isinstance(obj, base_type)`` - returns ``True`` won't be considered iterable. - - >>> obj = {'a': 1} - >>> list(always_iterable(obj)) # Iterate over the dict's keys - ['a'] - >>> list(always_iterable(obj, base_type=dict)) # Treat dicts as a unit - [{'a': 1}] - - Set *base_type* to ``None`` to avoid any special handling and treat objects - Python considers iterable as iterable: - - >>> obj = 'foo' - >>> list(always_iterable(obj, base_type=None)) - ['f', 'o', 'o'] - """ - if obj is None: - return iter(()) - - if (base_type is not None) and isinstance(obj, base_type): - return iter((obj,)) - - try: - return iter(obj) - except TypeError: - return iter((obj,)) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_meta.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_meta.py deleted file mode 100644 index 1927d0f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_meta.py +++ /dev/null @@ -1,67 +0,0 @@ -from __future__ import annotations - -import os -from typing import Protocol -from typing import Any, Dict, Iterator, List, Optional, TypeVar, Union, overload - - -_T = TypeVar("_T") - - -class PackageMetadata(Protocol): - def __len__(self) -> int: ... # pragma: no cover - - def __contains__(self, item: str) -> bool: ... # pragma: no cover - - def __getitem__(self, key: str) -> str: ... # pragma: no cover - - def __iter__(self) -> Iterator[str]: ... # pragma: no cover - - @overload - def get( - self, name: str, failobj: None = None - ) -> Optional[str]: ... # pragma: no cover - - @overload - def get(self, name: str, failobj: _T) -> Union[str, _T]: ... # pragma: no cover - - # overload per python/importlib_metadata#435 - @overload - def get_all( - self, name: str, failobj: None = None - ) -> Optional[List[Any]]: ... # pragma: no cover - - @overload - def get_all(self, name: str, failobj: _T) -> Union[List[Any], _T]: - """ - Return all values associated with a possibly multi-valued key. - """ - - @property - def json(self) -> Dict[str, Union[str, List[str]]]: - """ - A JSON-compatible form of the metadata. - """ - - -class SimplePath(Protocol): - """ - A minimal subset of pathlib.Path required by Distribution. - """ - - def joinpath( - self, other: Union[str, os.PathLike[str]] - ) -> SimplePath: ... # pragma: no cover - - def __truediv__( - self, other: Union[str, os.PathLike[str]] - ) -> SimplePath: ... # pragma: no cover - - @property - def parent(self) -> SimplePath: ... # pragma: no cover - - def read_text(self, encoding=None) -> str: ... # pragma: no cover - - def read_bytes(self) -> bytes: ... # pragma: no cover - - def exists(self) -> bool: ... # pragma: no cover diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_text.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_text.py deleted file mode 100644 index c88cfbb..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/_text.py +++ /dev/null @@ -1,99 +0,0 @@ -import re - -from ._functools import method_cache - - -# from jaraco.text 3.5 -class FoldedCase(str): - """ - A case insensitive string class; behaves just like str - except compares equal when the only variation is case. - - >>> s = FoldedCase('hello world') - - >>> s == 'Hello World' - True - - >>> 'Hello World' == s - True - - >>> s != 'Hello World' - False - - >>> s.index('O') - 4 - - >>> s.split('O') - ['hell', ' w', 'rld'] - - >>> sorted(map(FoldedCase, ['GAMMA', 'alpha', 'Beta'])) - ['alpha', 'Beta', 'GAMMA'] - - Sequence membership is straightforward. - - >>> "Hello World" in [s] - True - >>> s in ["Hello World"] - True - - You may test for set inclusion, but candidate and elements - must both be folded. - - >>> FoldedCase("Hello World") in {s} - True - >>> s in {FoldedCase("Hello World")} - True - - String inclusion works as long as the FoldedCase object - is on the right. - - >>> "hello" in FoldedCase("Hello World") - True - - But not if the FoldedCase object is on the left: - - >>> FoldedCase('hello') in 'Hello World' - False - - In that case, use in_: - - >>> FoldedCase('hello').in_('Hello World') - True - - >>> FoldedCase('hello') > FoldedCase('Hello') - False - """ - - def __lt__(self, other): - return self.lower() < other.lower() - - def __gt__(self, other): - return self.lower() > other.lower() - - def __eq__(self, other): - return self.lower() == other.lower() - - def __ne__(self, other): - return self.lower() != other.lower() - - def __hash__(self): - return hash(self.lower()) - - def __contains__(self, other): - return super().lower().__contains__(other.lower()) - - def in_(self, other): - "Does self appear in other?" - return self in FoldedCase(other) - - # cache lower since it's likely to be called frequently. - @method_cache - def lower(self): - return super().lower() - - def index(self, sub): - return self.lower().index(sub.lower()) - - def split(self, splitter=' ', maxsplit=0): - pattern = re.compile(re.escape(splitter), re.I) - return pattern.split(self, maxsplit) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 3aa9df6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/py311.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/py311.cpython-312.pyc deleted file mode 100644 index df44a58..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/py311.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/py39.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/py39.cpython-312.pyc deleted file mode 100644 index 553fa7b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/__pycache__/py39.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/py311.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/py311.py deleted file mode 100644 index 3a53274..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/py311.py +++ /dev/null @@ -1,22 +0,0 @@ -import os -import pathlib -import sys -import types - - -def wrap(path): # pragma: no cover - """ - Workaround for https://github.com/python/cpython/issues/84538 - to add backward compatibility for walk_up=True. - An example affected package is dask-labextension, which uses - jupyter-packaging to install JupyterLab javascript files outside - of site-packages. - """ - - def relative_to(root, *, walk_up=False): - return pathlib.Path(os.path.relpath(path, root)) - - return types.SimpleNamespace(relative_to=relative_to) - - -relative_fix = wrap if sys.version_info < (3, 12) else lambda x: x diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/py39.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/py39.py deleted file mode 100644 index 1f15bd9..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/compat/py39.py +++ /dev/null @@ -1,36 +0,0 @@ -""" -Compatibility layer with Python 3.8/3.9 -""" - -from typing import TYPE_CHECKING, Any, Optional - -if TYPE_CHECKING: # pragma: no cover - # Prevent circular imports on runtime. - from .. import Distribution, EntryPoint -else: - Distribution = EntryPoint = Any - - -def normalized_name(dist: Distribution) -> Optional[str]: - """ - Honor name normalization for distributions that don't provide ``_normalized_name``. - """ - try: - return dist._normalized_name - except AttributeError: - from .. import Prepared # -> delay to prevent circular imports. - - return Prepared.normalize(getattr(dist, "name", None) or dist.metadata['Name']) - - -def ep_matches(ep: EntryPoint, **params) -> bool: - """ - Workaround for ``EntryPoint`` objects without the ``matches`` method. - """ - try: - return ep.matches(**params) - except AttributeError: - from .. import EntryPoint # -> delay to prevent circular imports. - - # Reconstruct the EntryPoint object to make sure it is compatible. - return EntryPoint(ep.name, ep.value, ep.group).matches(**params) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/diagnose.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/diagnose.py deleted file mode 100644 index e405471..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/importlib_metadata/diagnose.py +++ /dev/null @@ -1,21 +0,0 @@ -import sys - -from . import Distribution - - -def inspect(path): - print("Inspecting", path) - dists = list(Distribution.discover(path=[path])) - if not dists: - return - print("Found", len(dists), "packages:", end=' ') - print(', '.join(dist.name for dist in dists)) - - -def run(): - for path in sys.path: - inspect(path) - - -if __name__ == '__main__': - run() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/LICENSE deleted file mode 100644 index 1bb5a44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/LICENSE +++ /dev/null @@ -1,17 +0,0 @@ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/METADATA deleted file mode 100644 index 9a2097a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/METADATA +++ /dev/null @@ -1,591 +0,0 @@ -Metadata-Version: 2.1 -Name: inflect -Version: 7.3.1 -Summary: Correctly generate plurals, singular nouns, ordinals, indefinite articles -Author-email: Paul Dyson -Maintainer-email: "Jason R. Coombs" -Project-URL: Source, https://github.com/jaraco/inflect -Keywords: plural,inflect,participle -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Classifier: Natural Language :: English -Classifier: Operating System :: OS Independent -Classifier: Topic :: Software Development :: Libraries :: Python Modules -Classifier: Topic :: Text Processing :: Linguistic -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -License-File: LICENSE -Requires-Dist: more-itertools >=8.5.0 -Requires-Dist: typeguard >=4.0.1 -Requires-Dist: typing-extensions ; python_version < "3.9" -Provides-Extra: doc -Requires-Dist: sphinx >=3.5 ; extra == 'doc' -Requires-Dist: jaraco.packaging >=9.3 ; extra == 'doc' -Requires-Dist: rst.linker >=1.9 ; extra == 'doc' -Requires-Dist: furo ; extra == 'doc' -Requires-Dist: sphinx-lint ; extra == 'doc' -Requires-Dist: jaraco.tidelift >=1.4 ; extra == 'doc' -Provides-Extra: test -Requires-Dist: pytest !=8.1.*,>=6 ; extra == 'test' -Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'test' -Requires-Dist: pytest-cov ; extra == 'test' -Requires-Dist: pytest-mypy ; extra == 'test' -Requires-Dist: pytest-enabler >=2.2 ; extra == 'test' -Requires-Dist: pytest-ruff >=0.2.1 ; extra == 'test' -Requires-Dist: pygments ; extra == 'test' - -.. image:: https://img.shields.io/pypi/v/inflect.svg - :target: https://pypi.org/project/inflect - -.. image:: https://img.shields.io/pypi/pyversions/inflect.svg - -.. image:: https://github.com/jaraco/inflect/actions/workflows/main.yml/badge.svg - :target: https://github.com/jaraco/inflect/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. image:: https://readthedocs.org/projects/inflect/badge/?version=latest - :target: https://inflect.readthedocs.io/en/latest/?badge=latest - -.. image:: https://img.shields.io/badge/skeleton-2024-informational - :target: https://blog.jaraco.com/skeleton - -.. image:: https://tidelift.com/badges/package/pypi/inflect - :target: https://tidelift.com/subscription/pkg/pypi-inflect?utm_source=pypi-inflect&utm_medium=readme - -NAME -==== - -inflect.py - Correctly generate plurals, singular nouns, ordinals, indefinite articles; convert numbers to words. - -SYNOPSIS -======== - -.. code-block:: python - - import inflect - - p = inflect.engine() - - # METHODS: - - # plural plural_noun plural_verb plural_adj singular_noun no num - # compare compare_nouns compare_nouns compare_adjs - # a an - # present_participle - # ordinal number_to_words - # join - # inflect classical gender - # defnoun defverb defadj defa defan - - - # UNCONDITIONALLY FORM THE PLURAL - - print("The plural of ", word, " is ", p.plural(word)) - - - # CONDITIONALLY FORM THE PLURAL - - print("I saw", cat_count, p.plural("cat", cat_count)) - - - # FORM PLURALS FOR SPECIFIC PARTS OF SPEECH - - print( - p.plural_noun("I", N1), - p.plural_verb("saw", N1), - p.plural_adj("my", N2), - p.plural_noun("saw", N2), - ) - - - # FORM THE SINGULAR OF PLURAL NOUNS - - print("The singular of ", word, " is ", p.singular_noun(word)) - - # SELECT THE GENDER OF SINGULAR PRONOUNS - - print(p.singular_noun("they")) # 'it' - p.gender("feminine") - print(p.singular_noun("they")) # 'she' - - - # DEAL WITH "0/1/N" -> "no/1/N" TRANSLATION: - - print("There ", p.plural_verb("was", errors), p.no(" error", errors)) - - - # USE DEFAULT COUNTS: - - print( - p.num(N1, ""), - p.plural("I"), - p.plural_verb(" saw"), - p.num(N2), - p.plural_noun(" saw"), - ) - print("There ", p.num(errors, ""), p.plural_verb("was"), p.no(" error")) - - - # COMPARE TWO WORDS "NUMBER-INSENSITIVELY": - - if p.compare(word1, word2): - print("same") - if p.compare_nouns(word1, word2): - print("same noun") - if p.compare_verbs(word1, word2): - print("same verb") - if p.compare_adjs(word1, word2): - print("same adj.") - - - # ADD CORRECT "a" OR "an" FOR A GIVEN WORD: - - print("Did you want ", p.a(thing), " or ", p.an(idea)) - - - # CONVERT NUMERALS INTO ORDINALS (i.e. 1->1st, 2->2nd, 3->3rd, etc.) - - print("It was", p.ordinal(position), " from the left\n") - - # CONVERT NUMERALS TO WORDS (i.e. 1->"one", 101->"one hundred and one", etc.) - # RETURNS A SINGLE STRING... - - words = p.number_to_words(1234) - # "one thousand, two hundred and thirty-four" - words = p.number_to_words(p.ordinal(1234)) - # "one thousand, two hundred and thirty-fourth" - - - # GET BACK A LIST OF STRINGS, ONE FOR EACH "CHUNK"... - - words = p.number_to_words(1234, wantlist=True) - # ("one thousand","two hundred and thirty-four") - - - # OPTIONAL PARAMETERS CHANGE TRANSLATION: - - words = p.number_to_words(12345, group=1) - # "one, two, three, four, five" - - words = p.number_to_words(12345, group=2) - # "twelve, thirty-four, five" - - words = p.number_to_words(12345, group=3) - # "one twenty-three, forty-five" - - words = p.number_to_words(1234, andword="") - # "one thousand, two hundred thirty-four" - - words = p.number_to_words(1234, andword=", plus") - # "one thousand, two hundred, plus thirty-four" - # TODO: I get no comma before plus: check perl - - words = p.number_to_words(555_1202, group=1, zero="oh") - # "five, five, five, one, two, oh, two" - - words = p.number_to_words(555_1202, group=1, one="unity") - # "five, five, five, unity, two, oh, two" - - words = p.number_to_words(123.456, group=1, decimal="mark") - # "one two three mark four five six" - # TODO: DOCBUG: perl gives commas here as do I - - # LITERAL STYLE ONLY NAMES NUMBERS LESS THAN A CERTAIN THRESHOLD... - - words = p.number_to_words(9, threshold=10) # "nine" - words = p.number_to_words(10, threshold=10) # "ten" - words = p.number_to_words(11, threshold=10) # "11" - words = p.number_to_words(1000, threshold=10) # "1,000" - - # JOIN WORDS INTO A LIST: - - mylist = p.join(("apple", "banana", "carrot")) - # "apple, banana, and carrot" - - mylist = p.join(("apple", "banana")) - # "apple and banana" - - mylist = p.join(("apple", "banana", "carrot"), final_sep="") - # "apple, banana and carrot" - - - # REQUIRE "CLASSICAL" PLURALS (EG: "focus"->"foci", "cherub"->"cherubim") - - p.classical() # USE ALL CLASSICAL PLURALS - - p.classical(all=True) # USE ALL CLASSICAL PLURALS - p.classical(all=False) # SWITCH OFF CLASSICAL MODE - - p.classical(zero=True) # "no error" INSTEAD OF "no errors" - p.classical(zero=False) # "no errors" INSTEAD OF "no error" - - p.classical(herd=True) # "2 buffalo" INSTEAD OF "2 buffalos" - p.classical(herd=False) # "2 buffalos" INSTEAD OF "2 buffalo" - - p.classical(persons=True) # "2 chairpersons" INSTEAD OF "2 chairpeople" - p.classical(persons=False) # "2 chairpeople" INSTEAD OF "2 chairpersons" - - p.classical(ancient=True) # "2 formulae" INSTEAD OF "2 formulas" - p.classical(ancient=False) # "2 formulas" INSTEAD OF "2 formulae" - - - # INTERPOLATE "plural()", "plural_noun()", "plural_verb()", "plural_adj()", "singular_noun()", - # a()", "an()", "num()" AND "ordinal()" WITHIN STRINGS: - - print(p.inflect("The plural of {0} is plural('{0}')".format(word))) - print(p.inflect("The singular of {0} is singular_noun('{0}')".format(word))) - print(p.inflect("I saw {0} plural('cat',{0})".format(cat_count))) - print( - p.inflect( - "plural('I',{0}) " - "plural_verb('saw',{0}) " - "plural('a',{1}) " - "plural_noun('saw',{1})".format(N1, N2) - ) - ) - print( - p.inflect( - "num({0}, False)plural('I') " - "plural_verb('saw') " - "num({1}, False)plural('a') " - "plural_noun('saw')".format(N1, N2) - ) - ) - print(p.inflect("I saw num({0}) plural('cat')\nnum()".format(cat_count))) - print(p.inflect("There plural_verb('was',{0}) no('error',{0})".format(errors))) - print(p.inflect("There num({0}, False)plural_verb('was') no('error')".format(errors))) - print(p.inflect("Did you want a('{0}') or an('{1}')".format(thing, idea))) - print(p.inflect("It was ordinal('{0}') from the left".format(position))) - - - # ADD USER-DEFINED INFLECTIONS (OVERRIDING INBUILT RULES): - - p.defnoun("VAX", "VAXen") # SINGULAR => PLURAL - - p.defverb( - "will", # 1ST PERSON SINGULAR - "shall", # 1ST PERSON PLURAL - "will", # 2ND PERSON SINGULAR - "will", # 2ND PERSON PLURAL - "will", # 3RD PERSON SINGULAR - "will", # 3RD PERSON PLURAL - ) - - p.defadj("hir", "their") # SINGULAR => PLURAL - - p.defa("h") # "AY HALWAYS SEZ 'HAITCH'!" - - p.defan("horrendous.*") # "AN HORRENDOUS AFFECTATION" - - -DESCRIPTION -=========== - -The methods of the class ``engine`` in module ``inflect.py`` provide plural -inflections, singular noun inflections, "a"/"an" selection for English words, -and manipulation of numbers as words. - -Plural forms of all nouns, most verbs, and some adjectives are -provided. Where appropriate, "classical" variants (for example: "brother" -> -"brethren", "dogma" -> "dogmata", etc.) are also provided. - -Single forms of nouns are also provided. The gender of singular pronouns -can be chosen (for example "they" -> "it" or "she" or "he" or "they"). - -Pronunciation-based "a"/"an" selection is provided for all English -words, and most initialisms. - -It is also possible to inflect numerals (1,2,3) to ordinals (1st, 2nd, 3rd) -and to English words ("one", "two", "three"). - -In generating these inflections, ``inflect.py`` follows the Oxford -English Dictionary and the guidelines in Fowler's Modern English -Usage, preferring the former where the two disagree. - -The module is built around standard British spelling, but is designed -to cope with common American variants as well. Slang, jargon, and -other English dialects are *not* explicitly catered for. - -Where two or more inflected forms exist for a single word (typically a -"classical" form and a "modern" form), ``inflect.py`` prefers the -more common form (typically the "modern" one), unless "classical" -processing has been specified -(see `MODERN VS CLASSICAL INFLECTIONS`). - -FORMING PLURALS AND SINGULARS -============================= - -Inflecting Plurals and Singulars --------------------------------- - -All of the ``plural...`` plural inflection methods take the word to be -inflected as their first argument and return the corresponding inflection. -Note that all such methods expect the *singular* form of the word. The -results of passing a plural form are undefined (and unlikely to be correct). -Similarly, the ``si...`` singular inflection method expects the *plural* -form of the word. - -The ``plural...`` methods also take an optional second argument, -which indicates the grammatical "number" of the word (or of another word -with which the word being inflected must agree). If the "number" argument is -supplied and is not ``1`` (or ``"one"`` or ``"a"``, or some other adjective that -implies the singular), the plural form of the word is returned. If the -"number" argument *does* indicate singularity, the (uninflected) word -itself is returned. If the number argument is omitted, the plural form -is returned unconditionally. - -The ``si...`` method takes a second argument in a similar fashion. If it is -some form of the number ``1``, or is omitted, the singular form is returned. -Otherwise the plural is returned unaltered. - - -The various methods of ``inflect.engine`` are: - - - -``plural_noun(word, count=None)`` - - The method ``plural_noun()`` takes a *singular* English noun or - pronoun and returns its plural. Pronouns in the nominative ("I" -> - "we") and accusative ("me" -> "us") cases are handled, as are - possessive pronouns ("mine" -> "ours"). - - -``plural_verb(word, count=None)`` - - The method ``plural_verb()`` takes the *singular* form of a - conjugated verb (that is, one which is already in the correct "person" - and "mood") and returns the corresponding plural conjugation. - - -``plural_adj(word, count=None)`` - - The method ``plural_adj()`` takes the *singular* form of - certain types of adjectives and returns the corresponding plural form. - Adjectives that are correctly handled include: "numerical" adjectives - ("a" -> "some"), demonstrative adjectives ("this" -> "these", "that" -> - "those"), and possessives ("my" -> "our", "cat's" -> "cats'", "child's" - -> "childrens'", etc.) - - -``plural(word, count=None)`` - - The method ``plural()`` takes a *singular* English noun, - pronoun, verb, or adjective and returns its plural form. Where a word - has more than one inflection depending on its part of speech (for - example, the noun "thought" inflects to "thoughts", the verb "thought" - to "thought"), the (singular) noun sense is preferred to the (singular) - verb sense. - - Hence ``plural("knife")`` will return "knives" ("knife" having been treated - as a singular noun), whereas ``plural("knifes")`` will return "knife" - ("knifes" having been treated as a 3rd person singular verb). - - The inherent ambiguity of such cases suggests that, - where the part of speech is known, ``plural_noun``, ``plural_verb``, and - ``plural_adj`` should be used in preference to ``plural``. - - -``singular_noun(word, count=None)`` - - The method ``singular_noun()`` takes a *plural* English noun or - pronoun and returns its singular. Pronouns in the nominative ("we" -> - "I") and accusative ("us" -> "me") cases are handled, as are - possessive pronouns ("ours" -> "mine"). When third person - singular pronouns are returned they take the neuter gender by default - ("they" -> "it"), not ("they"-> "she") nor ("they" -> "he"). This can be - changed with ``gender()``. - -Note that all these methods ignore any whitespace surrounding the -word being inflected, but preserve that whitespace when the result is -returned. For example, ``plural(" cat ")`` returns " cats ". - - -``gender(genderletter)`` - - The third person plural pronoun takes the same form for the female, male and - neuter (e.g. "they"). The singular however, depends upon gender (e.g. "she", - "he", "it" and "they" -- "they" being the gender neutral form.) By default - ``singular_noun`` returns the neuter form, however, the gender can be selected with - the ``gender`` method. Pass the first letter of the gender to - ``gender`` to return the f(eminine), m(asculine), n(euter) or t(hey) - form of the singular. e.g. - gender('f') followed by singular_noun('themselves') returns 'herself'. - -Numbered plurals ----------------- - -The ``plural...`` methods return only the inflected word, not the count that -was used to inflect it. Thus, in order to produce "I saw 3 ducks", it -is necessary to use: - -.. code-block:: python - - print("I saw", N, p.plural_noun(animal, N)) - -Since the usual purpose of producing a plural is to make it agree with -a preceding count, inflect.py provides a method -(``no(word, count)``) which, given a word and a(n optional) count, returns the -count followed by the correctly inflected word. Hence the previous -example can be rewritten: - -.. code-block:: python - - print("I saw ", p.no(animal, N)) - -In addition, if the count is zero (or some other term which implies -zero, such as ``"zero"``, ``"nil"``, etc.) the count is replaced by the -word "no". Hence, if ``N`` had the value zero, the previous example -would print (the somewhat more elegant):: - - I saw no animals - -rather than:: - - I saw 0 animals - -Note that the name of the method is a pun: the method -returns either a number (a *No.*) or a ``"no"``, in front of the -inflected word. - - -Reducing the number of counts required --------------------------------------- - -In some contexts, the need to supply an explicit count to the various -``plural...`` methods makes for tiresome repetition. For example: - -.. code-block:: python - - print( - plural_adj("This", errors), - plural_noun(" error", errors), - plural_verb(" was", errors), - " fatal.", - ) - -inflect.py therefore provides a method -(``num(count=None, show=None)``) which may be used to set a persistent "default number" -value. If such a value is set, it is subsequently used whenever an -optional second "number" argument is omitted. The default value thus set -can subsequently be removed by calling ``num()`` with no arguments. -Hence we could rewrite the previous example: - -.. code-block:: python - - p.num(errors) - print(p.plural_adj("This"), p.plural_noun(" error"), p.plural_verb(" was"), "fatal.") - p.num() - -Normally, ``num()`` returns its first argument, so that it may also -be "inlined" in contexts like: - -.. code-block:: python - - print(p.num(errors), p.plural_noun(" error"), p.plural_verb(" was"), " detected.") - if severity > 1: - print( - p.plural_adj("This"), p.plural_noun(" error"), p.plural_verb(" was"), "fatal." - ) - -However, in certain contexts (see `INTERPOLATING INFLECTIONS IN STRINGS`) -it is preferable that ``num()`` return an empty string. Hence ``num()`` -provides an optional second argument. If that argument is supplied (that is, if -it is defined) and evaluates to false, ``num`` returns an empty string -instead of its first argument. For example: - -.. code-block:: python - - print(p.num(errors, 0), p.no("error"), p.plural_verb(" was"), " detected.") - if severity > 1: - print( - p.plural_adj("This"), p.plural_noun(" error"), p.plural_verb(" was"), "fatal." - ) - - - -Number-insensitive equality ---------------------------- - -inflect.py also provides a solution to the problem -of comparing words of differing plurality through the methods -``compare(word1, word2)``, ``compare_nouns(word1, word2)``, -``compare_verbs(word1, word2)``, and ``compare_adjs(word1, word2)``. -Each of these methods takes two strings, and compares them -using the corresponding plural-inflection method (``plural()``, ``plural_noun()``, -``plural_verb()``, and ``plural_adj()`` respectively). - -The comparison returns true if: - -- the strings are equal, or -- one string is equal to a plural form of the other, or -- the strings are two different plural forms of the one word. - - -Hence all of the following return true: - -.. code-block:: python - - p.compare("index", "index") # RETURNS "eq" - p.compare("index", "indexes") # RETURNS "s:p" - p.compare("index", "indices") # RETURNS "s:p" - p.compare("indexes", "index") # RETURNS "p:s" - p.compare("indices", "index") # RETURNS "p:s" - p.compare("indices", "indexes") # RETURNS "p:p" - p.compare("indexes", "indices") # RETURNS "p:p" - p.compare("indices", "indices") # RETURNS "eq" - -As indicated by the comments in the previous example, the actual value -returned by the various ``compare`` methods encodes which of the -three equality rules succeeded: "eq" is returned if the strings were -identical, "s:p" if the strings were singular and plural respectively, -"p:s" for plural and singular, and "p:p" for two distinct plurals. -Inequality is indicated by returning an empty string. - -It should be noted that two distinct singular words which happen to take -the same plural form are *not* considered equal, nor are cases where -one (singular) word's plural is the other (plural) word's singular. -Hence all of the following return false: - -.. code-block:: python - - p.compare("base", "basis") # ALTHOUGH BOTH -> "bases" - p.compare("syrinx", "syringe") # ALTHOUGH BOTH -> "syringes" - p.compare("she", "he") # ALTHOUGH BOTH -> "they" - - p.compare("opus", "operas") # ALTHOUGH "opus" -> "opera" -> "operas" - p.compare("taxi", "taxes") # ALTHOUGH "taxi" -> "taxis" -> "taxes" - -Note too that, although the comparison is "number-insensitive" it is *not* -case-insensitive (that is, ``plural("time","Times")`` returns false. To obtain -both number and case insensitivity, use the ``lower()`` method on both strings -(that is, ``plural("time".lower(), "Times".lower())`` returns true). - -Related Functionality -===================== - -Shout out to these libraries that provide related functionality: - -* `WordSet `_ - parses identifiers like variable names into sets of words suitable for re-assembling - in another form. - -* `word2number `_ converts words to - a number. - - -For Enterprise -============== - -Available as part of the Tidelift Subscription. - -This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. - -`Learn more `_. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/RECORD deleted file mode 100644 index 73ff576..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/RECORD +++ /dev/null @@ -1,13 +0,0 @@ -inflect-7.3.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -inflect-7.3.1.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -inflect-7.3.1.dist-info/METADATA,sha256=ZgMNY0WAZRs-U8wZiV2SMfjSKqBrMngXyDMs_CAwMwg,21079 -inflect-7.3.1.dist-info/RECORD,, -inflect-7.3.1.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91 -inflect-7.3.1.dist-info/top_level.txt,sha256=m52ujdp10CqT6jh1XQxZT6kEntcnv-7Tl7UiGNTzWZA,8 -inflect/__init__.py,sha256=Jxy1HJXZiZ85kHeLAhkmvz6EMTdFqBe-duvt34R6IOc,103796 -inflect/__pycache__/__init__.cpython-312.pyc,, -inflect/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -inflect/compat/__pycache__/__init__.cpython-312.pyc,, -inflect/compat/__pycache__/py38.cpython-312.pyc,, -inflect/compat/py38.py,sha256=oObVfVnWX9_OpnOuEJn1mFbJxVhwyR5epbiTNXDDaso,160 -inflect/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/top_level.txt deleted file mode 100644 index 0fd75fa..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect-7.3.1.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -inflect diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/__init__.py deleted file mode 100644 index 3eec27f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/__init__.py +++ /dev/null @@ -1,3986 +0,0 @@ -""" -inflect: english language inflection - - correctly generate plurals, ordinals, indefinite articles - - convert numbers to words - -Copyright (C) 2010 Paul Dyson - -Based upon the Perl module -`Lingua::EN::Inflect `_. - -methods: - classical inflect - plural plural_noun plural_verb plural_adj singular_noun no num a an - compare compare_nouns compare_verbs compare_adjs - present_participle - ordinal - number_to_words - join - defnoun defverb defadj defa defan - -INFLECTIONS: - classical inflect - plural plural_noun plural_verb plural_adj singular_noun compare - no num a an present_participle - -PLURALS: - classical inflect - plural plural_noun plural_verb plural_adj singular_noun no num - compare compare_nouns compare_verbs compare_adjs - -COMPARISONS: - classical - compare compare_nouns compare_verbs compare_adjs - -ARTICLES: - classical inflect num a an - -NUMERICAL: - ordinal number_to_words - -USER_DEFINED: - defnoun defverb defadj defa defan - -Exceptions: - UnknownClassicalModeError - BadNumValueError - BadChunkingOptionError - NumOutOfRangeError - BadUserDefinedPatternError - BadRcFileError - BadGenderError - -""" - -from __future__ import annotations - -import ast -import collections -import contextlib -import functools -import itertools -import re -from numbers import Number -from typing import ( - TYPE_CHECKING, - Any, - Callable, - Dict, - Iterable, - List, - Literal, - Match, - Optional, - Sequence, - Tuple, - Union, - cast, -) - -from more_itertools import windowed_complete -from typeguard import typechecked - -from .compat.py38 import Annotated - - -class UnknownClassicalModeError(Exception): - pass - - -class BadNumValueError(Exception): - pass - - -class BadChunkingOptionError(Exception): - pass - - -class NumOutOfRangeError(Exception): - pass - - -class BadUserDefinedPatternError(Exception): - pass - - -class BadRcFileError(Exception): - pass - - -class BadGenderError(Exception): - pass - - -def enclose(s: str) -> str: - return f"(?:{s})" - - -def joinstem(cutpoint: Optional[int] = 0, words: Optional[Iterable[str]] = None) -> str: - """ - Join stem of each word in words into a string for regex. - - Each word is truncated at cutpoint. - - Cutpoint is usually negative indicating the number of letters to remove - from the end of each word. - - >>> joinstem(-2, ["ephemeris", "iris", ".*itis"]) - '(?:ephemer|ir|.*it)' - - >>> joinstem(None, ["ephemeris"]) - '(?:ephemeris)' - - >>> joinstem(5, None) - '(?:)' - """ - return enclose("|".join(w[:cutpoint] for w in words or [])) - - -def bysize(words: Iterable[str]) -> Dict[int, set]: - """ - From a list of words, return a dict of sets sorted by word length. - - >>> words = ['ant', 'cat', 'dog', 'pig', 'frog', 'goat', 'horse', 'elephant'] - >>> ret = bysize(words) - >>> sorted(ret[3]) - ['ant', 'cat', 'dog', 'pig'] - >>> ret[5] - {'horse'} - """ - res: Dict[int, set] = collections.defaultdict(set) - for w in words: - res[len(w)].add(w) - return res - - -def make_pl_si_lists( - lst: Iterable[str], - plending: str, - siendingsize: Optional[int], - dojoinstem: bool = True, -): - """ - given a list of singular words: lst - - an ending to append to make the plural: plending - - the number of characters to remove from the singular - before appending plending: siendingsize - - a flag whether to create a joinstem: dojoinstem - - return: - a list of pluralised words: si_list (called si because this is what you need to - look for to make the singular) - - the pluralised words as a dict of sets sorted by word length: si_bysize - the singular words as a dict of sets sorted by word length: pl_bysize - if dojoinstem is True: a regular expression that matches any of the stems: stem - """ - if siendingsize is not None: - siendingsize = -siendingsize - si_list = [w[:siendingsize] + plending for w in lst] - pl_bysize = bysize(lst) - si_bysize = bysize(si_list) - if dojoinstem: - stem = joinstem(siendingsize, lst) - return si_list, si_bysize, pl_bysize, stem - else: - return si_list, si_bysize, pl_bysize - - -# 1. PLURALS - -pl_sb_irregular_s = { - "corpus": "corpuses|corpora", - "opus": "opuses|opera", - "genus": "genera", - "mythos": "mythoi", - "penis": "penises|penes", - "testis": "testes", - "atlas": "atlases|atlantes", - "yes": "yeses", -} - -pl_sb_irregular = { - "child": "children", - "chili": "chilis|chilies", - "brother": "brothers|brethren", - "infinity": "infinities|infinity", - "loaf": "loaves", - "lore": "lores|lore", - "hoof": "hoofs|hooves", - "beef": "beefs|beeves", - "thief": "thiefs|thieves", - "money": "monies", - "mongoose": "mongooses", - "ox": "oxen", - "cow": "cows|kine", - "graffito": "graffiti", - "octopus": "octopuses|octopodes", - "genie": "genies|genii", - "ganglion": "ganglions|ganglia", - "trilby": "trilbys", - "turf": "turfs|turves", - "numen": "numina", - "atman": "atmas", - "occiput": "occiputs|occipita", - "sabretooth": "sabretooths", - "sabertooth": "sabertooths", - "lowlife": "lowlifes", - "flatfoot": "flatfoots", - "tenderfoot": "tenderfoots", - "romany": "romanies", - "jerry": "jerries", - "mary": "maries", - "talouse": "talouses", - "rom": "roma", - "carmen": "carmina", -} - -pl_sb_irregular.update(pl_sb_irregular_s) -# pl_sb_irregular_keys = enclose('|'.join(pl_sb_irregular.keys())) - -pl_sb_irregular_caps = { - "Romany": "Romanies", - "Jerry": "Jerrys", - "Mary": "Marys", - "Rom": "Roma", -} - -pl_sb_irregular_compound = {"prima donna": "prima donnas|prime donne"} - -si_sb_irregular = {v: k for (k, v) in pl_sb_irregular.items()} -for k in list(si_sb_irregular): - if "|" in k: - k1, k2 = k.split("|") - si_sb_irregular[k1] = si_sb_irregular[k2] = si_sb_irregular[k] - del si_sb_irregular[k] -si_sb_irregular_caps = {v: k for (k, v) in pl_sb_irregular_caps.items()} -si_sb_irregular_compound = {v: k for (k, v) in pl_sb_irregular_compound.items()} -for k in list(si_sb_irregular_compound): - if "|" in k: - k1, k2 = k.split("|") - si_sb_irregular_compound[k1] = si_sb_irregular_compound[k2] = ( - si_sb_irregular_compound[k] - ) - del si_sb_irregular_compound[k] - -# si_sb_irregular_keys = enclose('|'.join(si_sb_irregular.keys())) - -# Z's that don't double - -pl_sb_z_zes_list = ("quartz", "topaz") -pl_sb_z_zes_bysize = bysize(pl_sb_z_zes_list) - -pl_sb_ze_zes_list = ("snooze",) -pl_sb_ze_zes_bysize = bysize(pl_sb_ze_zes_list) - - -# CLASSICAL "..is" -> "..ides" - -pl_sb_C_is_ides_complete = [ - # GENERAL WORDS... - "ephemeris", - "iris", - "clitoris", - "chrysalis", - "epididymis", -] - -pl_sb_C_is_ides_endings = [ - # INFLAMATIONS... - "itis" -] - -pl_sb_C_is_ides = joinstem( - -2, pl_sb_C_is_ides_complete + [f".*{w}" for w in pl_sb_C_is_ides_endings] -) - -pl_sb_C_is_ides_list = pl_sb_C_is_ides_complete + pl_sb_C_is_ides_endings - -( - si_sb_C_is_ides_list, - si_sb_C_is_ides_bysize, - pl_sb_C_is_ides_bysize, -) = make_pl_si_lists(pl_sb_C_is_ides_list, "ides", 2, dojoinstem=False) - - -# CLASSICAL "..a" -> "..ata" - -pl_sb_C_a_ata_list = ( - "anathema", - "bema", - "carcinoma", - "charisma", - "diploma", - "dogma", - "drama", - "edema", - "enema", - "enigma", - "lemma", - "lymphoma", - "magma", - "melisma", - "miasma", - "oedema", - "sarcoma", - "schema", - "soma", - "stigma", - "stoma", - "trauma", - "gumma", - "pragma", -) - -( - si_sb_C_a_ata_list, - si_sb_C_a_ata_bysize, - pl_sb_C_a_ata_bysize, - pl_sb_C_a_ata, -) = make_pl_si_lists(pl_sb_C_a_ata_list, "ata", 1) - -# UNCONDITIONAL "..a" -> "..ae" - -pl_sb_U_a_ae_list = ( - "alumna", - "alga", - "vertebra", - "persona", - "vita", -) -( - si_sb_U_a_ae_list, - si_sb_U_a_ae_bysize, - pl_sb_U_a_ae_bysize, - pl_sb_U_a_ae, -) = make_pl_si_lists(pl_sb_U_a_ae_list, "e", None) - -# CLASSICAL "..a" -> "..ae" - -pl_sb_C_a_ae_list = ( - "amoeba", - "antenna", - "formula", - "hyperbola", - "medusa", - "nebula", - "parabola", - "abscissa", - "hydra", - "nova", - "lacuna", - "aurora", - "umbra", - "flora", - "fauna", -) -( - si_sb_C_a_ae_list, - si_sb_C_a_ae_bysize, - pl_sb_C_a_ae_bysize, - pl_sb_C_a_ae, -) = make_pl_si_lists(pl_sb_C_a_ae_list, "e", None) - - -# CLASSICAL "..en" -> "..ina" - -pl_sb_C_en_ina_list = ("stamen", "foramen", "lumen") - -( - si_sb_C_en_ina_list, - si_sb_C_en_ina_bysize, - pl_sb_C_en_ina_bysize, - pl_sb_C_en_ina, -) = make_pl_si_lists(pl_sb_C_en_ina_list, "ina", 2) - - -# UNCONDITIONAL "..um" -> "..a" - -pl_sb_U_um_a_list = ( - "bacterium", - "agendum", - "desideratum", - "erratum", - "stratum", - "datum", - "ovum", - "extremum", - "candelabrum", -) -( - si_sb_U_um_a_list, - si_sb_U_um_a_bysize, - pl_sb_U_um_a_bysize, - pl_sb_U_um_a, -) = make_pl_si_lists(pl_sb_U_um_a_list, "a", 2) - -# CLASSICAL "..um" -> "..a" - -pl_sb_C_um_a_list = ( - "maximum", - "minimum", - "momentum", - "optimum", - "quantum", - "cranium", - "curriculum", - "dictum", - "phylum", - "aquarium", - "compendium", - "emporium", - "encomium", - "gymnasium", - "honorarium", - "interregnum", - "lustrum", - "memorandum", - "millennium", - "rostrum", - "spectrum", - "speculum", - "stadium", - "trapezium", - "ultimatum", - "medium", - "vacuum", - "velum", - "consortium", - "arboretum", -) - -( - si_sb_C_um_a_list, - si_sb_C_um_a_bysize, - pl_sb_C_um_a_bysize, - pl_sb_C_um_a, -) = make_pl_si_lists(pl_sb_C_um_a_list, "a", 2) - - -# UNCONDITIONAL "..us" -> "i" - -pl_sb_U_us_i_list = ( - "alumnus", - "alveolus", - "bacillus", - "bronchus", - "locus", - "nucleus", - "stimulus", - "meniscus", - "sarcophagus", -) -( - si_sb_U_us_i_list, - si_sb_U_us_i_bysize, - pl_sb_U_us_i_bysize, - pl_sb_U_us_i, -) = make_pl_si_lists(pl_sb_U_us_i_list, "i", 2) - -# CLASSICAL "..us" -> "..i" - -pl_sb_C_us_i_list = ( - "focus", - "radius", - "genius", - "incubus", - "succubus", - "nimbus", - "fungus", - "nucleolus", - "stylus", - "torus", - "umbilicus", - "uterus", - "hippopotamus", - "cactus", -) - -( - si_sb_C_us_i_list, - si_sb_C_us_i_bysize, - pl_sb_C_us_i_bysize, - pl_sb_C_us_i, -) = make_pl_si_lists(pl_sb_C_us_i_list, "i", 2) - - -# CLASSICAL "..us" -> "..us" (ASSIMILATED 4TH DECLENSION LATIN NOUNS) - -pl_sb_C_us_us = ( - "status", - "apparatus", - "prospectus", - "sinus", - "hiatus", - "impetus", - "plexus", -) -pl_sb_C_us_us_bysize = bysize(pl_sb_C_us_us) - -# UNCONDITIONAL "..on" -> "a" - -pl_sb_U_on_a_list = ( - "criterion", - "perihelion", - "aphelion", - "phenomenon", - "prolegomenon", - "noumenon", - "organon", - "asyndeton", - "hyperbaton", -) -( - si_sb_U_on_a_list, - si_sb_U_on_a_bysize, - pl_sb_U_on_a_bysize, - pl_sb_U_on_a, -) = make_pl_si_lists(pl_sb_U_on_a_list, "a", 2) - -# CLASSICAL "..on" -> "..a" - -pl_sb_C_on_a_list = ("oxymoron",) - -( - si_sb_C_on_a_list, - si_sb_C_on_a_bysize, - pl_sb_C_on_a_bysize, - pl_sb_C_on_a, -) = make_pl_si_lists(pl_sb_C_on_a_list, "a", 2) - - -# CLASSICAL "..o" -> "..i" (BUT NORMALLY -> "..os") - -pl_sb_C_o_i = [ - "solo", - "soprano", - "basso", - "alto", - "contralto", - "tempo", - "piano", - "virtuoso", -] # list not tuple so can concat for pl_sb_U_o_os - -pl_sb_C_o_i_bysize = bysize(pl_sb_C_o_i) -si_sb_C_o_i_bysize = bysize([f"{w[:-1]}i" for w in pl_sb_C_o_i]) - -pl_sb_C_o_i_stems = joinstem(-1, pl_sb_C_o_i) - -# ALWAYS "..o" -> "..os" - -pl_sb_U_o_os_complete = {"ado", "ISO", "NATO", "NCO", "NGO", "oto"} -si_sb_U_o_os_complete = {f"{w}s" for w in pl_sb_U_o_os_complete} - - -pl_sb_U_o_os_endings = [ - "aficionado", - "aggro", - "albino", - "allegro", - "ammo", - "Antananarivo", - "archipelago", - "armadillo", - "auto", - "avocado", - "Bamako", - "Barquisimeto", - "bimbo", - "bingo", - "Biro", - "bolero", - "Bolzano", - "bongo", - "Boto", - "burro", - "Cairo", - "canto", - "cappuccino", - "casino", - "cello", - "Chicago", - "Chimango", - "cilantro", - "cochito", - "coco", - "Colombo", - "Colorado", - "commando", - "concertino", - "contango", - "credo", - "crescendo", - "cyano", - "demo", - "ditto", - "Draco", - "dynamo", - "embryo", - "Esperanto", - "espresso", - "euro", - "falsetto", - "Faro", - "fiasco", - "Filipino", - "flamenco", - "furioso", - "generalissimo", - "Gestapo", - "ghetto", - "gigolo", - "gizmo", - "Greensboro", - "gringo", - "Guaiabero", - "guano", - "gumbo", - "gyro", - "hairdo", - "hippo", - "Idaho", - "impetigo", - "inferno", - "info", - "intermezzo", - "intertrigo", - "Iquico", - "jumbo", - "junto", - "Kakapo", - "kilo", - "Kinkimavo", - "Kokako", - "Kosovo", - "Lesotho", - "libero", - "libido", - "libretto", - "lido", - "Lilo", - "limbo", - "limo", - "lineno", - "lingo", - "lino", - "livedo", - "loco", - "logo", - "lumbago", - "macho", - "macro", - "mafioso", - "magneto", - "magnifico", - "Majuro", - "Malabo", - "manifesto", - "Maputo", - "Maracaibo", - "medico", - "memo", - "metro", - "Mexico", - "micro", - "Milano", - "Monaco", - "mono", - "Montenegro", - "Morocco", - "Muqdisho", - "myo", - "neutrino", - "Ningbo", - "octavo", - "oregano", - "Orinoco", - "Orlando", - "Oslo", - "panto", - "Paramaribo", - "Pardusco", - "pedalo", - "photo", - "pimento", - "pinto", - "pleco", - "Pluto", - "pogo", - "polo", - "poncho", - "Porto-Novo", - "Porto", - "pro", - "psycho", - "pueblo", - "quarto", - "Quito", - "repo", - "rhino", - "risotto", - "rococo", - "rondo", - "Sacramento", - "saddo", - "sago", - "salvo", - "Santiago", - "Sapporo", - "Sarajevo", - "scherzando", - "scherzo", - "silo", - "sirocco", - "sombrero", - "staccato", - "sterno", - "stucco", - "stylo", - "sumo", - "Taiko", - "techno", - "terrazzo", - "testudo", - "timpano", - "tiro", - "tobacco", - "Togo", - "Tokyo", - "torero", - "Torino", - "Toronto", - "torso", - "tremolo", - "typo", - "tyro", - "ufo", - "UNESCO", - "vaquero", - "vermicello", - "verso", - "vibrato", - "violoncello", - "Virgo", - "weirdo", - "WHO", - "WTO", - "Yamoussoukro", - "yo-yo", - "zero", - "Zibo", -] + pl_sb_C_o_i - -pl_sb_U_o_os_bysize = bysize(pl_sb_U_o_os_endings) -si_sb_U_o_os_bysize = bysize([f"{w}s" for w in pl_sb_U_o_os_endings]) - - -# UNCONDITIONAL "..ch" -> "..chs" - -pl_sb_U_ch_chs_list = ("czech", "eunuch", "stomach") - -( - si_sb_U_ch_chs_list, - si_sb_U_ch_chs_bysize, - pl_sb_U_ch_chs_bysize, - pl_sb_U_ch_chs, -) = make_pl_si_lists(pl_sb_U_ch_chs_list, "s", None) - - -# UNCONDITIONAL "..[ei]x" -> "..ices" - -pl_sb_U_ex_ices_list = ("codex", "murex", "silex") -( - si_sb_U_ex_ices_list, - si_sb_U_ex_ices_bysize, - pl_sb_U_ex_ices_bysize, - pl_sb_U_ex_ices, -) = make_pl_si_lists(pl_sb_U_ex_ices_list, "ices", 2) - -pl_sb_U_ix_ices_list = ("radix", "helix") -( - si_sb_U_ix_ices_list, - si_sb_U_ix_ices_bysize, - pl_sb_U_ix_ices_bysize, - pl_sb_U_ix_ices, -) = make_pl_si_lists(pl_sb_U_ix_ices_list, "ices", 2) - -# CLASSICAL "..[ei]x" -> "..ices" - -pl_sb_C_ex_ices_list = ( - "vortex", - "vertex", - "cortex", - "latex", - "pontifex", - "apex", - "index", - "simplex", -) - -( - si_sb_C_ex_ices_list, - si_sb_C_ex_ices_bysize, - pl_sb_C_ex_ices_bysize, - pl_sb_C_ex_ices, -) = make_pl_si_lists(pl_sb_C_ex_ices_list, "ices", 2) - - -pl_sb_C_ix_ices_list = ("appendix",) - -( - si_sb_C_ix_ices_list, - si_sb_C_ix_ices_bysize, - pl_sb_C_ix_ices_bysize, - pl_sb_C_ix_ices, -) = make_pl_si_lists(pl_sb_C_ix_ices_list, "ices", 2) - - -# ARABIC: ".." -> "..i" - -pl_sb_C_i_list = ("afrit", "afreet", "efreet") - -(si_sb_C_i_list, si_sb_C_i_bysize, pl_sb_C_i_bysize, pl_sb_C_i) = make_pl_si_lists( - pl_sb_C_i_list, "i", None -) - - -# HEBREW: ".." -> "..im" - -pl_sb_C_im_list = ("goy", "seraph", "cherub") - -(si_sb_C_im_list, si_sb_C_im_bysize, pl_sb_C_im_bysize, pl_sb_C_im) = make_pl_si_lists( - pl_sb_C_im_list, "im", None -) - - -# UNCONDITIONAL "..man" -> "..mans" - -pl_sb_U_man_mans_list = """ - ataman caiman cayman ceriman - desman dolman farman harman hetman - human leman ottoman shaman talisman -""".split() -pl_sb_U_man_mans_caps_list = """ - Alabaman Bahaman Burman German - Hiroshiman Liman Nakayaman Norman Oklahoman - Panaman Roman Selman Sonaman Tacoman Yakiman - Yokohaman Yuman -""".split() - -( - si_sb_U_man_mans_list, - si_sb_U_man_mans_bysize, - pl_sb_U_man_mans_bysize, -) = make_pl_si_lists(pl_sb_U_man_mans_list, "s", None, dojoinstem=False) -( - si_sb_U_man_mans_caps_list, - si_sb_U_man_mans_caps_bysize, - pl_sb_U_man_mans_caps_bysize, -) = make_pl_si_lists(pl_sb_U_man_mans_caps_list, "s", None, dojoinstem=False) - -# UNCONDITIONAL "..louse" -> "..lice" -pl_sb_U_louse_lice_list = ("booklouse", "grapelouse", "louse", "woodlouse") - -( - si_sb_U_louse_lice_list, - si_sb_U_louse_lice_bysize, - pl_sb_U_louse_lice_bysize, -) = make_pl_si_lists(pl_sb_U_louse_lice_list, "lice", 5, dojoinstem=False) - -pl_sb_uninflected_s_complete = [ - # PAIRS OR GROUPS SUBSUMED TO A SINGULAR... - "breeches", - "britches", - "pajamas", - "pyjamas", - "clippers", - "gallows", - "hijinks", - "headquarters", - "pliers", - "scissors", - "testes", - "herpes", - "pincers", - "shears", - "proceedings", - "trousers", - # UNASSIMILATED LATIN 4th DECLENSION - "cantus", - "coitus", - "nexus", - # RECENT IMPORTS... - "contretemps", - "corps", - "debris", - "siemens", - # DISEASES - "mumps", - # MISCELLANEOUS OTHERS... - "diabetes", - "jackanapes", - "series", - "species", - "subspecies", - "rabies", - "chassis", - "innings", - "news", - "mews", - "haggis", -] - -pl_sb_uninflected_s_endings = [ - # RECENT IMPORTS... - "ois", - # DISEASES - "measles", -] - -pl_sb_uninflected_s = pl_sb_uninflected_s_complete + [ - f".*{w}" for w in pl_sb_uninflected_s_endings -] - -pl_sb_uninflected_herd = ( - # DON'T INFLECT IN CLASSICAL MODE, OTHERWISE NORMAL INFLECTION - "wildebeest", - "swine", - "eland", - "bison", - "buffalo", - "cattle", - "elk", - "rhinoceros", - "zucchini", - "caribou", - "dace", - "grouse", - "guinea fowl", - "guinea-fowl", - "haddock", - "hake", - "halibut", - "herring", - "mackerel", - "pickerel", - "pike", - "roe", - "seed", - "shad", - "snipe", - "teal", - "turbot", - "water fowl", - "water-fowl", -) - -pl_sb_uninflected_complete = [ - # SOME FISH AND HERD ANIMALS - "tuna", - "salmon", - "mackerel", - "trout", - "bream", - "sea-bass", - "sea bass", - "carp", - "cod", - "flounder", - "whiting", - "moose", - # OTHER ODDITIES - "graffiti", - "djinn", - "samuri", - "offspring", - "pence", - "quid", - "hertz", -] + pl_sb_uninflected_s_complete -# SOME WORDS ENDING IN ...s (OFTEN PAIRS TAKEN AS A WHOLE) - -pl_sb_uninflected_caps = [ - # ALL NATIONALS ENDING IN -ese - "Portuguese", - "Amoyese", - "Borghese", - "Congoese", - "Faroese", - "Foochowese", - "Genevese", - "Genoese", - "Gilbertese", - "Hottentotese", - "Kiplingese", - "Kongoese", - "Lucchese", - "Maltese", - "Nankingese", - "Niasese", - "Pekingese", - "Piedmontese", - "Pistoiese", - "Sarawakese", - "Shavese", - "Vermontese", - "Wenchowese", - "Yengeese", -] - - -pl_sb_uninflected_endings = [ - # UNCOUNTABLE NOUNS - "butter", - "cash", - "furniture", - "information", - # SOME FISH AND HERD ANIMALS - "fish", - "deer", - "sheep", - # ALL NATIONALS ENDING IN -ese - "nese", - "rese", - "lese", - "mese", - # DISEASES - "pox", - # OTHER ODDITIES - "craft", -] + pl_sb_uninflected_s_endings -# SOME WORDS ENDING IN ...s (OFTEN PAIRS TAKEN AS A WHOLE) - - -pl_sb_uninflected_bysize = bysize(pl_sb_uninflected_endings) - - -# SINGULAR WORDS ENDING IN ...s (ALL INFLECT WITH ...es) - -pl_sb_singular_s_complete = [ - "acropolis", - "aegis", - "alias", - "asbestos", - "bathos", - "bias", - "bronchitis", - "bursitis", - "caddis", - "cannabis", - "canvas", - "chaos", - "cosmos", - "dais", - "digitalis", - "epidermis", - "ethos", - "eyas", - "gas", - "glottis", - "hubris", - "ibis", - "lens", - "mantis", - "marquis", - "metropolis", - "pathos", - "pelvis", - "polis", - "rhinoceros", - "sassafras", - "trellis", -] + pl_sb_C_is_ides_complete - - -pl_sb_singular_s_endings = ["ss", "us"] + pl_sb_C_is_ides_endings - -pl_sb_singular_s_bysize = bysize(pl_sb_singular_s_endings) - -si_sb_singular_s_complete = [f"{w}es" for w in pl_sb_singular_s_complete] -si_sb_singular_s_endings = [f"{w}es" for w in pl_sb_singular_s_endings] -si_sb_singular_s_bysize = bysize(si_sb_singular_s_endings) - -pl_sb_singular_s_es = ["[A-Z].*es"] - -pl_sb_singular_s = enclose( - "|".join( - pl_sb_singular_s_complete - + [f".*{w}" for w in pl_sb_singular_s_endings] - + pl_sb_singular_s_es - ) -) - - -# PLURALS ENDING IN uses -> use - - -si_sb_ois_oi_case = ("Bolshois", "Hanois") - -si_sb_uses_use_case = ("Betelgeuses", "Duses", "Meuses", "Syracuses", "Toulouses") - -si_sb_uses_use = ( - "abuses", - "applauses", - "blouses", - "carouses", - "causes", - "chartreuses", - "clauses", - "contuses", - "douses", - "excuses", - "fuses", - "grouses", - "hypotenuses", - "masseuses", - "menopauses", - "misuses", - "muses", - "overuses", - "pauses", - "peruses", - "profuses", - "recluses", - "reuses", - "ruses", - "souses", - "spouses", - "suffuses", - "transfuses", - "uses", -) - -si_sb_ies_ie_case = ( - "Addies", - "Aggies", - "Allies", - "Amies", - "Angies", - "Annies", - "Annmaries", - "Archies", - "Arties", - "Aussies", - "Barbies", - "Barries", - "Basies", - "Bennies", - "Bernies", - "Berties", - "Bessies", - "Betties", - "Billies", - "Blondies", - "Bobbies", - "Bonnies", - "Bowies", - "Brandies", - "Bries", - "Brownies", - "Callies", - "Carnegies", - "Carries", - "Cassies", - "Charlies", - "Cheries", - "Christies", - "Connies", - "Curies", - "Dannies", - "Debbies", - "Dixies", - "Dollies", - "Donnies", - "Drambuies", - "Eddies", - "Effies", - "Ellies", - "Elsies", - "Eries", - "Ernies", - "Essies", - "Eugenies", - "Fannies", - "Flossies", - "Frankies", - "Freddies", - "Gillespies", - "Goldies", - "Gracies", - "Guthries", - "Hallies", - "Hatties", - "Hetties", - "Hollies", - "Jackies", - "Jamies", - "Janies", - "Jannies", - "Jeanies", - "Jeannies", - "Jennies", - "Jessies", - "Jimmies", - "Jodies", - "Johnies", - "Johnnies", - "Josies", - "Julies", - "Kalgoorlies", - "Kathies", - "Katies", - "Kellies", - "Kewpies", - "Kristies", - "Laramies", - "Lassies", - "Lauries", - "Leslies", - "Lessies", - "Lillies", - "Lizzies", - "Lonnies", - "Lories", - "Lorries", - "Lotties", - "Louies", - "Mackenzies", - "Maggies", - "Maisies", - "Mamies", - "Marcies", - "Margies", - "Maries", - "Marjories", - "Matties", - "McKenzies", - "Melanies", - "Mickies", - "Millies", - "Minnies", - "Mollies", - "Mounties", - "Nannies", - "Natalies", - "Nellies", - "Netties", - "Ollies", - "Ozzies", - "Pearlies", - "Pottawatomies", - "Reggies", - "Richies", - "Rickies", - "Robbies", - "Ronnies", - "Rosalies", - "Rosemaries", - "Rosies", - "Roxies", - "Rushdies", - "Ruthies", - "Sadies", - "Sallies", - "Sammies", - "Scotties", - "Selassies", - "Sherries", - "Sophies", - "Stacies", - "Stefanies", - "Stephanies", - "Stevies", - "Susies", - "Sylvies", - "Tammies", - "Terries", - "Tessies", - "Tommies", - "Tracies", - "Trekkies", - "Valaries", - "Valeries", - "Valkyries", - "Vickies", - "Virgies", - "Willies", - "Winnies", - "Wylies", - "Yorkies", -) - -si_sb_ies_ie = ( - "aeries", - "baggies", - "belies", - "biggies", - "birdies", - "bogies", - "bonnies", - "boogies", - "bookies", - "bourgeoisies", - "brownies", - "budgies", - "caddies", - "calories", - "camaraderies", - "cockamamies", - "collies", - "cookies", - "coolies", - "cooties", - "coteries", - "crappies", - "curies", - "cutesies", - "dogies", - "eyries", - "floozies", - "footsies", - "freebies", - "genies", - "goalies", - "groupies", - "hies", - "jalousies", - "junkies", - "kiddies", - "laddies", - "lassies", - "lies", - "lingeries", - "magpies", - "menageries", - "mommies", - "movies", - "neckties", - "newbies", - "nighties", - "oldies", - "organdies", - "overlies", - "pies", - "pinkies", - "pixies", - "potpies", - "prairies", - "quickies", - "reveries", - "rookies", - "rotisseries", - "softies", - "sorties", - "species", - "stymies", - "sweeties", - "ties", - "underlies", - "unties", - "veggies", - "vies", - "yuppies", - "zombies", -) - - -si_sb_oes_oe_case = ( - "Chloes", - "Crusoes", - "Defoes", - "Faeroes", - "Ivanhoes", - "Joes", - "McEnroes", - "Moes", - "Monroes", - "Noes", - "Poes", - "Roscoes", - "Tahoes", - "Tippecanoes", - "Zoes", -) - -si_sb_oes_oe = ( - "aloes", - "backhoes", - "canoes", - "does", - "floes", - "foes", - "hoes", - "mistletoes", - "oboes", - "pekoes", - "roes", - "sloes", - "throes", - "tiptoes", - "toes", - "woes", -) - -si_sb_z_zes = ("quartzes", "topazes") - -si_sb_zzes_zz = ("buzzes", "fizzes", "frizzes", "razzes") - -si_sb_ches_che_case = ( - "Andromaches", - "Apaches", - "Blanches", - "Comanches", - "Nietzsches", - "Porsches", - "Roches", -) - -si_sb_ches_che = ( - "aches", - "avalanches", - "backaches", - "bellyaches", - "caches", - "cloches", - "creches", - "douches", - "earaches", - "fiches", - "headaches", - "heartaches", - "microfiches", - "niches", - "pastiches", - "psyches", - "quiches", - "stomachaches", - "toothaches", - "tranches", -) - -si_sb_xes_xe = ("annexes", "axes", "deluxes", "pickaxes") - -si_sb_sses_sse_case = ("Hesses", "Jesses", "Larousses", "Matisses") -si_sb_sses_sse = ( - "bouillabaisses", - "crevasses", - "demitasses", - "impasses", - "mousses", - "posses", -) - -si_sb_ves_ve_case = ( - # *[nwl]ives -> [nwl]live - "Clives", - "Palmolives", -) -si_sb_ves_ve = ( - # *[^d]eaves -> eave - "interweaves", - "weaves", - # *[nwl]ives -> [nwl]live - "olives", - # *[eoa]lves -> [eoa]lve - "bivalves", - "dissolves", - "resolves", - "salves", - "twelves", - "valves", -) - - -plverb_special_s = enclose( - "|".join( - [pl_sb_singular_s] - + pl_sb_uninflected_s - + list(pl_sb_irregular_s) - + ["(.*[csx])is", "(.*)ceps", "[A-Z].*s"] - ) -) - -_pl_sb_postfix_adj_defn = ( - ("general", enclose(r"(?!major|lieutenant|brigadier|adjutant|.*star)\S+")), - ("martial", enclose("court")), - ("force", enclose("pound")), -) - -pl_sb_postfix_adj: Iterable[str] = ( - enclose(val + f"(?=(?:-|\\s+){key})") for key, val in _pl_sb_postfix_adj_defn -) - -pl_sb_postfix_adj_stems = f"({'|'.join(pl_sb_postfix_adj)})(.*)" - - -# PLURAL WORDS ENDING IS es GO TO SINGULAR is - -si_sb_es_is = ( - "amanuenses", - "amniocenteses", - "analyses", - "antitheses", - "apotheoses", - "arterioscleroses", - "atheroscleroses", - "axes", - # 'bases', # bases -> basis - "catalyses", - "catharses", - "chasses", - "cirrhoses", - "cocces", - "crises", - "diagnoses", - "dialyses", - "diereses", - "electrolyses", - "emphases", - "exegeses", - "geneses", - "halitoses", - "hydrolyses", - "hypnoses", - "hypotheses", - "hystereses", - "metamorphoses", - "metastases", - "misdiagnoses", - "mitoses", - "mononucleoses", - "narcoses", - "necroses", - "nemeses", - "neuroses", - "oases", - "osmoses", - "osteoporoses", - "paralyses", - "parentheses", - "parthenogeneses", - "periphrases", - "photosyntheses", - "probosces", - "prognoses", - "prophylaxes", - "prostheses", - "preces", - "psoriases", - "psychoanalyses", - "psychokineses", - "psychoses", - "scleroses", - "scolioses", - "sepses", - "silicoses", - "symbioses", - "synopses", - "syntheses", - "taxes", - "telekineses", - "theses", - "thromboses", - "tuberculoses", - "urinalyses", -) - -pl_prep_list = """ - about above across after among around at athwart before behind - below beneath beside besides between betwixt beyond but by - during except for from in into near of off on onto out over - since till to under until unto upon with""".split() - -pl_prep_list_da = pl_prep_list + ["de", "du", "da"] - -pl_prep_bysize = bysize(pl_prep_list_da) - -pl_prep = enclose("|".join(pl_prep_list_da)) - -pl_sb_prep_dual_compound = rf"(.*?)((?:-|\s+)(?:{pl_prep})(?:-|\s+))a(?:-|\s+)(.*)" - - -singular_pronoun_genders = { - "neuter", - "feminine", - "masculine", - "gender-neutral", - "feminine or masculine", - "masculine or feminine", -} - -pl_pron_nom = { - # NOMINATIVE REFLEXIVE - "i": "we", - "myself": "ourselves", - "you": "you", - "yourself": "yourselves", - "she": "they", - "herself": "themselves", - "he": "they", - "himself": "themselves", - "it": "they", - "itself": "themselves", - "they": "they", - "themself": "themselves", - # POSSESSIVE - "mine": "ours", - "yours": "yours", - "hers": "theirs", - "his": "theirs", - "its": "theirs", - "theirs": "theirs", -} - -si_pron: Dict[str, Dict[str, Union[str, Dict[str, str]]]] = { - "nom": {v: k for (k, v) in pl_pron_nom.items()} -} -si_pron["nom"]["we"] = "I" - - -pl_pron_acc = { - # ACCUSATIVE REFLEXIVE - "me": "us", - "myself": "ourselves", - "you": "you", - "yourself": "yourselves", - "her": "them", - "herself": "themselves", - "him": "them", - "himself": "themselves", - "it": "them", - "itself": "themselves", - "them": "them", - "themself": "themselves", -} - -pl_pron_acc_keys = enclose("|".join(pl_pron_acc)) -pl_pron_acc_keys_bysize = bysize(pl_pron_acc) - -si_pron["acc"] = {v: k for (k, v) in pl_pron_acc.items()} - -for _thecase, _plur, _gend, _sing in ( - ("nom", "they", "neuter", "it"), - ("nom", "they", "feminine", "she"), - ("nom", "they", "masculine", "he"), - ("nom", "they", "gender-neutral", "they"), - ("nom", "they", "feminine or masculine", "she or he"), - ("nom", "they", "masculine or feminine", "he or she"), - ("nom", "themselves", "neuter", "itself"), - ("nom", "themselves", "feminine", "herself"), - ("nom", "themselves", "masculine", "himself"), - ("nom", "themselves", "gender-neutral", "themself"), - ("nom", "themselves", "feminine or masculine", "herself or himself"), - ("nom", "themselves", "masculine or feminine", "himself or herself"), - ("nom", "theirs", "neuter", "its"), - ("nom", "theirs", "feminine", "hers"), - ("nom", "theirs", "masculine", "his"), - ("nom", "theirs", "gender-neutral", "theirs"), - ("nom", "theirs", "feminine or masculine", "hers or his"), - ("nom", "theirs", "masculine or feminine", "his or hers"), - ("acc", "them", "neuter", "it"), - ("acc", "them", "feminine", "her"), - ("acc", "them", "masculine", "him"), - ("acc", "them", "gender-neutral", "them"), - ("acc", "them", "feminine or masculine", "her or him"), - ("acc", "them", "masculine or feminine", "him or her"), - ("acc", "themselves", "neuter", "itself"), - ("acc", "themselves", "feminine", "herself"), - ("acc", "themselves", "masculine", "himself"), - ("acc", "themselves", "gender-neutral", "themself"), - ("acc", "themselves", "feminine or masculine", "herself or himself"), - ("acc", "themselves", "masculine or feminine", "himself or herself"), -): - try: - si_pron[_thecase][_plur][_gend] = _sing # type: ignore - except TypeError: - si_pron[_thecase][_plur] = {} - si_pron[_thecase][_plur][_gend] = _sing # type: ignore - - -si_pron_acc_keys = enclose("|".join(si_pron["acc"])) -si_pron_acc_keys_bysize = bysize(si_pron["acc"]) - - -def get_si_pron(thecase, word, gender) -> str: - try: - sing = si_pron[thecase][word] - except KeyError: - raise # not a pronoun - try: - return sing[gender] # has several types due to gender - except TypeError: - return cast(str, sing) # answer independent of gender - - -# These dictionaries group verbs by first, second and third person -# conjugations. - -plverb_irregular_pres = { - "am": "are", - "are": "are", - "is": "are", - "was": "were", - "were": "were", - "have": "have", - "has": "have", - "do": "do", - "does": "do", -} - -plverb_ambiguous_pres = { - "act": "act", - "acts": "act", - "blame": "blame", - "blames": "blame", - "can": "can", - "must": "must", - "fly": "fly", - "flies": "fly", - "copy": "copy", - "copies": "copy", - "drink": "drink", - "drinks": "drink", - "fight": "fight", - "fights": "fight", - "fire": "fire", - "fires": "fire", - "like": "like", - "likes": "like", - "look": "look", - "looks": "look", - "make": "make", - "makes": "make", - "reach": "reach", - "reaches": "reach", - "run": "run", - "runs": "run", - "sink": "sink", - "sinks": "sink", - "sleep": "sleep", - "sleeps": "sleep", - "view": "view", - "views": "view", -} - -plverb_ambiguous_pres_keys = re.compile( - rf"^({enclose('|'.join(plverb_ambiguous_pres))})((\s.*)?)$", re.IGNORECASE -) - - -plverb_irregular_non_pres = ( - "did", - "had", - "ate", - "made", - "put", - "spent", - "fought", - "sank", - "gave", - "sought", - "shall", - "could", - "ought", - "should", -) - -plverb_ambiguous_non_pres = re.compile( - r"^((?:thought|saw|bent|will|might|cut))((\s.*)?)$", re.IGNORECASE -) - -# "..oes" -> "..oe" (the rest are "..oes" -> "o") - -pl_v_oes_oe = ("canoes", "floes", "oboes", "roes", "throes", "woes") -pl_v_oes_oe_endings_size4 = ("hoes", "toes") -pl_v_oes_oe_endings_size5 = ("shoes",) - - -pl_count_zero = ("0", "no", "zero", "nil") - - -pl_count_one = ("1", "a", "an", "one", "each", "every", "this", "that") - -pl_adj_special = {"a": "some", "an": "some", "this": "these", "that": "those"} - -pl_adj_special_keys = re.compile( - rf"^({enclose('|'.join(pl_adj_special))})$", re.IGNORECASE -) - -pl_adj_poss = { - "my": "our", - "your": "your", - "its": "their", - "her": "their", - "his": "their", - "their": "their", -} - -pl_adj_poss_keys = re.compile(rf"^({enclose('|'.join(pl_adj_poss))})$", re.IGNORECASE) - - -# 2. INDEFINITE ARTICLES - -# THIS PATTERN MATCHES STRINGS OF CAPITALS STARTING WITH A "VOWEL-SOUND" -# CONSONANT FOLLOWED BY ANOTHER CONSONANT, AND WHICH ARE NOT LIKELY -# TO BE REAL WORDS (OH, ALL RIGHT THEN, IT'S JUST MAGIC!) - -A_abbrev = re.compile( - r""" -^(?! FJO | [HLMNS]Y. | RY[EO] | SQU - | ( F[LR]? | [HL] | MN? | N | RH? | S[CHKLMNPTVW]? | X(YL)?) [AEIOU]) -[FHLMNRSX][A-Z] -""", - re.VERBOSE, -) - -# THIS PATTERN CODES THE BEGINNINGS OF ALL ENGLISH WORDS BEGINING WITH A -# 'y' FOLLOWED BY A CONSONANT. ANY OTHER Y-CONSONANT PREFIX THEREFORE -# IMPLIES AN ABBREVIATION. - -A_y_cons = re.compile(r"^(y(b[lor]|cl[ea]|fere|gg|p[ios]|rou|tt))", re.IGNORECASE) - -# EXCEPTIONS TO EXCEPTIONS - -A_explicit_a = re.compile(r"^((?:unabomber|unanimous|US))", re.IGNORECASE) - -A_explicit_an = re.compile( - r"^((?:euler|hour(?!i)|heir|honest|hono[ur]|mpeg))", re.IGNORECASE -) - -A_ordinal_an = re.compile(r"^([aefhilmnorsx]-?th)", re.IGNORECASE) - -A_ordinal_a = re.compile(r"^([bcdgjkpqtuvwyz]-?th)", re.IGNORECASE) - - -# NUMERICAL INFLECTIONS - -nth = { - 0: "th", - 1: "st", - 2: "nd", - 3: "rd", - 4: "th", - 5: "th", - 6: "th", - 7: "th", - 8: "th", - 9: "th", - 11: "th", - 12: "th", - 13: "th", -} -nth_suff = set(nth.values()) - -ordinal = dict( - ty="tieth", - one="first", - two="second", - three="third", - five="fifth", - eight="eighth", - nine="ninth", - twelve="twelfth", -) - -ordinal_suff = re.compile(rf"({'|'.join(ordinal)})\Z") - - -# NUMBERS - -unit = ["", "one", "two", "three", "four", "five", "six", "seven", "eight", "nine"] -teen = [ - "ten", - "eleven", - "twelve", - "thirteen", - "fourteen", - "fifteen", - "sixteen", - "seventeen", - "eighteen", - "nineteen", -] -ten = [ - "", - "", - "twenty", - "thirty", - "forty", - "fifty", - "sixty", - "seventy", - "eighty", - "ninety", -] -mill = [ - " ", - " thousand", - " million", - " billion", - " trillion", - " quadrillion", - " quintillion", - " sextillion", - " septillion", - " octillion", - " nonillion", - " decillion", -] - - -# SUPPORT CLASSICAL PLURALIZATIONS - -def_classical = dict( - all=False, zero=False, herd=False, names=True, persons=False, ancient=False -) - -all_classical = {k: True for k in def_classical} -no_classical = {k: False for k in def_classical} - - -# Maps strings to built-in constant types -string_to_constant = {"True": True, "False": False, "None": None} - - -# Pre-compiled regular expression objects -DOLLAR_DIGITS = re.compile(r"\$(\d+)") -FUNCTION_CALL = re.compile(r"((\w+)\([^)]*\)*)", re.IGNORECASE) -PARTITION_WORD = re.compile(r"\A(\s*)(.+?)(\s*)\Z") -PL_SB_POSTFIX_ADJ_STEMS_RE = re.compile( - rf"^(?:{pl_sb_postfix_adj_stems})$", re.IGNORECASE -) -PL_SB_PREP_DUAL_COMPOUND_RE = re.compile( - rf"^(?:{pl_sb_prep_dual_compound})$", re.IGNORECASE -) -DENOMINATOR = re.compile(r"(?P.+)( (per|a) .+)") -PLVERB_SPECIAL_S_RE = re.compile(rf"^({plverb_special_s})$") -WHITESPACE = re.compile(r"\s") -ENDS_WITH_S = re.compile(r"^(.*[^s])s$", re.IGNORECASE) -ENDS_WITH_APOSTROPHE_S = re.compile(r"^(.*)'s?$") -INDEFINITE_ARTICLE_TEST = re.compile(r"\A(\s*)(?:an?\s+)?(.+?)(\s*)\Z", re.IGNORECASE) -SPECIAL_AN = re.compile(r"^[aefhilmnorsx]$", re.IGNORECASE) -SPECIAL_A = re.compile(r"^[bcdgjkpqtuvwyz]$", re.IGNORECASE) -SPECIAL_ABBREV_AN = re.compile(r"^[aefhilmnorsx][.-]", re.IGNORECASE) -SPECIAL_ABBREV_A = re.compile(r"^[a-z][.-]", re.IGNORECASE) -CONSONANTS = re.compile(r"^[^aeiouy]", re.IGNORECASE) -ARTICLE_SPECIAL_EU = re.compile(r"^e[uw]", re.IGNORECASE) -ARTICLE_SPECIAL_ONCE = re.compile(r"^onc?e\b", re.IGNORECASE) -ARTICLE_SPECIAL_ONETIME = re.compile(r"^onetime\b", re.IGNORECASE) -ARTICLE_SPECIAL_UNIT = re.compile(r"^uni([^nmd]|mo)", re.IGNORECASE) -ARTICLE_SPECIAL_UBA = re.compile(r"^u[bcfghjkqrst][aeiou]", re.IGNORECASE) -ARTICLE_SPECIAL_UKR = re.compile(r"^ukr", re.IGNORECASE) -SPECIAL_CAPITALS = re.compile(r"^U[NK][AIEO]?") -VOWELS = re.compile(r"^[aeiou]", re.IGNORECASE) - -DIGIT_GROUP = re.compile(r"(\d)") -TWO_DIGITS = re.compile(r"(\d)(\d)") -THREE_DIGITS = re.compile(r"(\d)(\d)(\d)") -THREE_DIGITS_WORD = re.compile(r"(\d)(\d)(\d)(?=\D*\Z)") -TWO_DIGITS_WORD = re.compile(r"(\d)(\d)(?=\D*\Z)") -ONE_DIGIT_WORD = re.compile(r"(\d)(?=\D*\Z)") - -FOUR_DIGIT_COMMA = re.compile(r"(\d)(\d{3}(?:,|\Z))") -NON_DIGIT = re.compile(r"\D") -WHITESPACES_COMMA = re.compile(r"\s+,") -COMMA_WORD = re.compile(r", (\S+)\s+\Z") -WHITESPACES = re.compile(r"\s+") - - -PRESENT_PARTICIPLE_REPLACEMENTS = ( - (re.compile(r"ie$"), r"y"), - ( - re.compile(r"ue$"), - r"u", - ), # TODO: isn't ue$ -> u encompassed in the following rule? - (re.compile(r"([auy])e$"), r"\g<1>"), - (re.compile(r"ski$"), r"ski"), - (re.compile(r"[^b]i$"), r""), - (re.compile(r"^(are|were)$"), r"be"), - (re.compile(r"^(had)$"), r"hav"), - (re.compile(r"^(hoe)$"), r"\g<1>"), - (re.compile(r"([^e])e$"), r"\g<1>"), - (re.compile(r"er$"), r"er"), - (re.compile(r"([^aeiou][aeiouy]([bdgmnprst]))$"), r"\g<1>\g<2>"), -) - -DIGIT = re.compile(r"\d") - - -class Words(str): - lowered: str - split_: List[str] - first: str - last: str - - def __init__(self, orig) -> None: - self.lowered = self.lower() - self.split_ = self.split() - self.first = self.split_[0] - self.last = self.split_[-1] - - -Falsish = Any # ideally, falsish would only validate on bool(value) is False - - -_STATIC_TYPE_CHECKING = TYPE_CHECKING -# ^-- Workaround for typeguard AST manipulation: -# https://github.com/agronholm/typeguard/issues/353#issuecomment-1556306554 - -if _STATIC_TYPE_CHECKING: # pragma: no cover - Word = Annotated[str, "String with at least 1 character"] -else: - - class _WordMeta(type): # Too dynamic to be supported by mypy... - def __instancecheck__(self, instance: Any) -> bool: - return isinstance(instance, str) and len(instance) >= 1 - - class Word(metaclass=_WordMeta): # type: ignore[no-redef] - """String with at least 1 character""" - - -class engine: - def __init__(self) -> None: - self.classical_dict = def_classical.copy() - self.persistent_count: Optional[int] = None - self.mill_count = 0 - self.pl_sb_user_defined: List[Optional[Word]] = [] - self.pl_v_user_defined: List[Optional[Word]] = [] - self.pl_adj_user_defined: List[Optional[Word]] = [] - self.si_sb_user_defined: List[Optional[Word]] = [] - self.A_a_user_defined: List[Optional[Word]] = [] - self.thegender = "neuter" - self.__number_args: Optional[Dict[str, str]] = None - - @property - def _number_args(self): - return cast(Dict[str, str], self.__number_args) - - @_number_args.setter - def _number_args(self, val): - self.__number_args = val - - @typechecked - def defnoun(self, singular: Optional[Word], plural: Optional[Word]) -> int: - """ - Set the noun plural of singular to plural. - - """ - self.checkpat(singular) - self.checkpatplural(plural) - self.pl_sb_user_defined.extend((singular, plural)) - self.si_sb_user_defined.extend((plural, singular)) - return 1 - - @typechecked - def defverb( - self, - s1: Optional[Word], - p1: Optional[Word], - s2: Optional[Word], - p2: Optional[Word], - s3: Optional[Word], - p3: Optional[Word], - ) -> int: - """ - Set the verb plurals for s1, s2 and s3 to p1, p2 and p3 respectively. - - Where 1, 2 and 3 represent the 1st, 2nd and 3rd person forms of the verb. - - """ - self.checkpat(s1) - self.checkpat(s2) - self.checkpat(s3) - self.checkpatplural(p1) - self.checkpatplural(p2) - self.checkpatplural(p3) - self.pl_v_user_defined.extend((s1, p1, s2, p2, s3, p3)) - return 1 - - @typechecked - def defadj(self, singular: Optional[Word], plural: Optional[Word]) -> int: - """ - Set the adjective plural of singular to plural. - - """ - self.checkpat(singular) - self.checkpatplural(plural) - self.pl_adj_user_defined.extend((singular, plural)) - return 1 - - @typechecked - def defa(self, pattern: Optional[Word]) -> int: - """ - Define the indefinite article as 'a' for words matching pattern. - - """ - self.checkpat(pattern) - self.A_a_user_defined.extend((pattern, "a")) - return 1 - - @typechecked - def defan(self, pattern: Optional[Word]) -> int: - """ - Define the indefinite article as 'an' for words matching pattern. - - """ - self.checkpat(pattern) - self.A_a_user_defined.extend((pattern, "an")) - return 1 - - def checkpat(self, pattern: Optional[Word]) -> None: - """ - check for errors in a regex pattern - """ - if pattern is None: - return - try: - re.match(pattern, "") - except re.error as err: - raise BadUserDefinedPatternError(pattern) from err - - def checkpatplural(self, pattern: Optional[Word]) -> None: - """ - check for errors in a regex replace pattern - """ - return - - @typechecked - def ud_match(self, word: Word, wordlist: Sequence[Optional[Word]]) -> Optional[str]: - for i in range(len(wordlist) - 2, -2, -2): # backwards through even elements - mo = re.search(rf"^{wordlist[i]}$", word, re.IGNORECASE) - if mo: - if wordlist[i + 1] is None: - return None - pl = DOLLAR_DIGITS.sub( - r"\\1", cast(Word, wordlist[i + 1]) - ) # change $n to \n for expand - return mo.expand(pl) - return None - - def classical(self, **kwargs) -> None: - """ - turn classical mode on and off for various categories - - turn on all classical modes: - classical() - classical(all=True) - - turn on or off specific claassical modes: - e.g. - classical(herd=True) - classical(names=False) - - By default all classical modes are off except names. - - unknown value in args or key in kwargs raises - exception: UnknownClasicalModeError - - """ - if not kwargs: - self.classical_dict = all_classical.copy() - return - if "all" in kwargs: - if kwargs["all"]: - self.classical_dict = all_classical.copy() - else: - self.classical_dict = no_classical.copy() - - for k, v in kwargs.items(): - if k in def_classical: - self.classical_dict[k] = v - else: - raise UnknownClassicalModeError - - def num( - self, count: Optional[int] = None, show: Optional[int] = None - ) -> str: # (;$count,$show) - """ - Set the number to be used in other method calls. - - Returns count. - - Set show to False to return '' instead. - - """ - if count is not None: - try: - self.persistent_count = int(count) - except ValueError as err: - raise BadNumValueError from err - if (show is None) or show: - return str(count) - else: - self.persistent_count = None - return "" - - def gender(self, gender: str) -> None: - """ - set the gender for the singular of plural pronouns - - can be one of: - 'neuter' ('they' -> 'it') - 'feminine' ('they' -> 'she') - 'masculine' ('they' -> 'he') - 'gender-neutral' ('they' -> 'they') - 'feminine or masculine' ('they' -> 'she or he') - 'masculine or feminine' ('they' -> 'he or she') - """ - if gender in singular_pronoun_genders: - self.thegender = gender - else: - raise BadGenderError - - def _get_value_from_ast(self, obj): - """ - Return the value of the ast object. - """ - if isinstance(obj, ast.Num): - return obj.n - elif isinstance(obj, ast.Str): - return obj.s - elif isinstance(obj, ast.List): - return [self._get_value_from_ast(e) for e in obj.elts] - elif isinstance(obj, ast.Tuple): - return tuple([self._get_value_from_ast(e) for e in obj.elts]) - - # None, True and False are NameConstants in Py3.4 and above. - elif isinstance(obj, ast.NameConstant): - return obj.value - - # Probably passed a variable name. - # Or passed a single word without wrapping it in quotes as an argument - # ex: p.inflect("I plural(see)") instead of p.inflect("I plural('see')") - raise NameError(f"name '{obj.id}' is not defined") - - def _string_to_substitute( - self, mo: Match, methods_dict: Dict[str, Callable] - ) -> str: - """ - Return the string to be substituted for the match. - """ - matched_text, f_name = mo.groups() - # matched_text is the complete match string. e.g. plural_noun(cat) - # f_name is the function name. e.g. plural_noun - - # Return matched_text if function name is not in methods_dict - if f_name not in methods_dict: - return matched_text - - # Parse the matched text - a_tree = ast.parse(matched_text) - - # get the args and kwargs from ast objects - args_list = [ - self._get_value_from_ast(a) - for a in a_tree.body[0].value.args # type: ignore[attr-defined] - ] - kwargs_list = { - kw.arg: self._get_value_from_ast(kw.value) - for kw in a_tree.body[0].value.keywords # type: ignore[attr-defined] - } - - # Call the corresponding function - return methods_dict[f_name](*args_list, **kwargs_list) - - # 0. PERFORM GENERAL INFLECTIONS IN A STRING - - @typechecked - def inflect(self, text: Word) -> str: - """ - Perform inflections in a string. - - e.g. inflect('The plural of cat is plural(cat)') returns - 'The plural of cat is cats' - - can use plural, plural_noun, plural_verb, plural_adj, - singular_noun, a, an, no, ordinal, number_to_words, - and prespart - - """ - save_persistent_count = self.persistent_count - - # Dictionary of allowed methods - methods_dict: Dict[str, Callable] = { - "plural": self.plural, - "plural_adj": self.plural_adj, - "plural_noun": self.plural_noun, - "plural_verb": self.plural_verb, - "singular_noun": self.singular_noun, - "a": self.a, - "an": self.a, - "no": self.no, - "ordinal": self.ordinal, - "number_to_words": self.number_to_words, - "present_participle": self.present_participle, - "num": self.num, - } - - # Regular expression to find Python's function call syntax - output = FUNCTION_CALL.sub( - lambda mo: self._string_to_substitute(mo, methods_dict), text - ) - self.persistent_count = save_persistent_count - return output - - # ## PLURAL SUBROUTINES - - def postprocess(self, orig: str, inflected) -> str: - inflected = str(inflected) - if "|" in inflected: - word_options = inflected.split("|") - # When two parts of a noun need to be pluralized - if len(word_options[0].split(" ")) == len(word_options[1].split(" ")): - result = inflected.split("|")[self.classical_dict["all"]].split(" ") - # When only the last part of the noun needs to be pluralized - else: - result = inflected.split(" ") - for index, word in enumerate(result): - if "|" in word: - result[index] = word.split("|")[self.classical_dict["all"]] - else: - result = inflected.split(" ") - - # Try to fix word wise capitalization - for index, word in enumerate(orig.split(" ")): - if word == "I": - # Is this the only word for exceptions like this - # Where the original is fully capitalized - # without 'meaning' capitalization? - # Also this fails to handle a capitalizaion in context - continue - if word.capitalize() == word: - result[index] = result[index].capitalize() - if word == word.upper(): - result[index] = result[index].upper() - return " ".join(result) - - def partition_word(self, text: str) -> Tuple[str, str, str]: - mo = PARTITION_WORD.search(text) - if mo: - return mo.group(1), mo.group(2), mo.group(3) - else: - return "", "", "" - - @typechecked - def plural(self, text: Word, count: Optional[Union[str, int, Any]] = None) -> str: - """ - Return the plural of text. - - If count supplied, then return text if count is one of: - 1, a, an, one, each, every, this, that - - otherwise return the plural. - - Whitespace at the start and end is preserved. - - """ - pre, word, post = self.partition_word(text) - if not word: - return text - plural = self.postprocess( - word, - self._pl_special_adjective(word, count) - or self._pl_special_verb(word, count) - or self._plnoun(word, count), - ) - return f"{pre}{plural}{post}" - - @typechecked - def plural_noun( - self, text: Word, count: Optional[Union[str, int, Any]] = None - ) -> str: - """ - Return the plural of text, where text is a noun. - - If count supplied, then return text if count is one of: - 1, a, an, one, each, every, this, that - - otherwise return the plural. - - Whitespace at the start and end is preserved. - - """ - pre, word, post = self.partition_word(text) - if not word: - return text - plural = self.postprocess(word, self._plnoun(word, count)) - return f"{pre}{plural}{post}" - - @typechecked - def plural_verb( - self, text: Word, count: Optional[Union[str, int, Any]] = None - ) -> str: - """ - Return the plural of text, where text is a verb. - - If count supplied, then return text if count is one of: - 1, a, an, one, each, every, this, that - - otherwise return the plural. - - Whitespace at the start and end is preserved. - - """ - pre, word, post = self.partition_word(text) - if not word: - return text - plural = self.postprocess( - word, - self._pl_special_verb(word, count) or self._pl_general_verb(word, count), - ) - return f"{pre}{plural}{post}" - - @typechecked - def plural_adj( - self, text: Word, count: Optional[Union[str, int, Any]] = None - ) -> str: - """ - Return the plural of text, where text is an adjective. - - If count supplied, then return text if count is one of: - 1, a, an, one, each, every, this, that - - otherwise return the plural. - - Whitespace at the start and end is preserved. - - """ - pre, word, post = self.partition_word(text) - if not word: - return text - plural = self.postprocess(word, self._pl_special_adjective(word, count) or word) - return f"{pre}{plural}{post}" - - @typechecked - def compare(self, word1: Word, word2: Word) -> Union[str, bool]: - """ - compare word1 and word2 for equality regardless of plurality - - return values: - eq - the strings are equal - p:s - word1 is the plural of word2 - s:p - word2 is the plural of word1 - p:p - word1 and word2 are two different plural forms of the one word - False - otherwise - - >>> compare = engine().compare - >>> compare("egg", "eggs") - 's:p' - >>> compare('egg', 'egg') - 'eq' - - Words should not be empty. - - >>> compare('egg', '') - Traceback (most recent call last): - ... - typeguard.TypeCheckError:...is not an instance of inflect.Word - """ - norms = self.plural_noun, self.plural_verb, self.plural_adj - results = (self._plequal(word1, word2, norm) for norm in norms) - return next(filter(None, results), False) - - @typechecked - def compare_nouns(self, word1: Word, word2: Word) -> Union[str, bool]: - """ - compare word1 and word2 for equality regardless of plurality - word1 and word2 are to be treated as nouns - - return values: - eq - the strings are equal - p:s - word1 is the plural of word2 - s:p - word2 is the plural of word1 - p:p - word1 and word2 are two different plural forms of the one word - False - otherwise - - """ - return self._plequal(word1, word2, self.plural_noun) - - @typechecked - def compare_verbs(self, word1: Word, word2: Word) -> Union[str, bool]: - """ - compare word1 and word2 for equality regardless of plurality - word1 and word2 are to be treated as verbs - - return values: - eq - the strings are equal - p:s - word1 is the plural of word2 - s:p - word2 is the plural of word1 - p:p - word1 and word2 are two different plural forms of the one word - False - otherwise - - """ - return self._plequal(word1, word2, self.plural_verb) - - @typechecked - def compare_adjs(self, word1: Word, word2: Word) -> Union[str, bool]: - """ - compare word1 and word2 for equality regardless of plurality - word1 and word2 are to be treated as adjectives - - return values: - eq - the strings are equal - p:s - word1 is the plural of word2 - s:p - word2 is the plural of word1 - p:p - word1 and word2 are two different plural forms of the one word - False - otherwise - - """ - return self._plequal(word1, word2, self.plural_adj) - - @typechecked - def singular_noun( - self, - text: Word, - count: Optional[Union[int, str, Any]] = None, - gender: Optional[str] = None, - ) -> Union[str, Literal[False]]: - """ - Return the singular of text, where text is a plural noun. - - If count supplied, then return the singular if count is one of: - 1, a, an, one, each, every, this, that or if count is None - - otherwise return text unchanged. - - Whitespace at the start and end is preserved. - - >>> p = engine() - >>> p.singular_noun('horses') - 'horse' - >>> p.singular_noun('knights') - 'knight' - - Returns False when a singular noun is passed. - - >>> p.singular_noun('horse') - False - >>> p.singular_noun('knight') - False - >>> p.singular_noun('soldier') - False - - """ - pre, word, post = self.partition_word(text) - if not word: - return text - sing = self._sinoun(word, count=count, gender=gender) - if sing is not False: - plural = self.postprocess(word, sing) - return f"{pre}{plural}{post}" - return False - - def _plequal(self, word1: str, word2: str, pl) -> Union[str, bool]: # noqa: C901 - classval = self.classical_dict.copy() - self.classical_dict = all_classical.copy() - if word1 == word2: - return "eq" - if word1 == pl(word2): - return "p:s" - if pl(word1) == word2: - return "s:p" - self.classical_dict = no_classical.copy() - if word1 == pl(word2): - return "p:s" - if pl(word1) == word2: - return "s:p" - self.classical_dict = classval.copy() - - if pl == self.plural or pl == self.plural_noun: - if self._pl_check_plurals_N(word1, word2): - return "p:p" - if self._pl_check_plurals_N(word2, word1): - return "p:p" - if pl == self.plural or pl == self.plural_adj: - if self._pl_check_plurals_adj(word1, word2): - return "p:p" - return False - - def _pl_reg_plurals(self, pair: str, stems: str, end1: str, end2: str) -> bool: - pattern = rf"({stems})({end1}\|\1{end2}|{end2}\|\1{end1})" - return bool(re.search(pattern, pair)) - - def _pl_check_plurals_N(self, word1: str, word2: str) -> bool: - stem_endings = ( - (pl_sb_C_a_ata, "as", "ata"), - (pl_sb_C_is_ides, "is", "ides"), - (pl_sb_C_a_ae, "s", "e"), - (pl_sb_C_en_ina, "ens", "ina"), - (pl_sb_C_um_a, "ums", "a"), - (pl_sb_C_us_i, "uses", "i"), - (pl_sb_C_on_a, "ons", "a"), - (pl_sb_C_o_i_stems, "os", "i"), - (pl_sb_C_ex_ices, "exes", "ices"), - (pl_sb_C_ix_ices, "ixes", "ices"), - (pl_sb_C_i, "s", "i"), - (pl_sb_C_im, "s", "im"), - (".*eau", "s", "x"), - (".*ieu", "s", "x"), - (".*tri", "xes", "ces"), - (".{2,}[yia]n", "xes", "ges"), - ) - - words = map(Words, (word1, word2)) - pair = "|".join(word.last for word in words) - - return ( - pair in pl_sb_irregular_s.values() - or pair in pl_sb_irregular.values() - or pair in pl_sb_irregular_caps.values() - or any( - self._pl_reg_plurals(pair, stems, end1, end2) - for stems, end1, end2 in stem_endings - ) - ) - - def _pl_check_plurals_adj(self, word1: str, word2: str) -> bool: - word1a = word1[: word1.rfind("'")] if word1.endswith(("'s", "'")) else "" - word2a = word2[: word2.rfind("'")] if word2.endswith(("'s", "'")) else "" - - return ( - bool(word1a) - and bool(word2a) - and ( - self._pl_check_plurals_N(word1a, word2a) - or self._pl_check_plurals_N(word2a, word1a) - ) - ) - - def get_count(self, count: Optional[Union[str, int]] = None) -> Union[str, int]: - if count is None and self.persistent_count is not None: - count = self.persistent_count - - if count is not None: - count = ( - 1 - if ( - (str(count) in pl_count_one) - or ( - self.classical_dict["zero"] - and str(count).lower() in pl_count_zero - ) - ) - else 2 - ) - else: - count = "" - return count - - # @profile - def _plnoun( # noqa: C901 - self, word: str, count: Optional[Union[str, int]] = None - ) -> str: - count = self.get_count(count) - - # DEFAULT TO PLURAL - - if count == 1: - return word - - # HANDLE USER-DEFINED NOUNS - - value = self.ud_match(word, self.pl_sb_user_defined) - if value is not None: - return value - - # HANDLE EMPTY WORD, SINGULAR COUNT AND UNINFLECTED PLURALS - - if word == "": - return word - - word = Words(word) - - if word.last.lower() in pl_sb_uninflected_complete: - if len(word.split_) >= 3: - return self._handle_long_compounds(word, count=2) or word - return word - - if word in pl_sb_uninflected_caps: - return word - - for k, v in pl_sb_uninflected_bysize.items(): - if word.lowered[-k:] in v: - return word - - if self.classical_dict["herd"] and word.last.lower() in pl_sb_uninflected_herd: - return word - - # HANDLE COMPOUNDS ("Governor General", "mother-in-law", "aide-de-camp", ETC.) - - mo = PL_SB_POSTFIX_ADJ_STEMS_RE.search(word) - if mo and mo.group(2) != "": - return f"{self._plnoun(mo.group(1), 2)}{mo.group(2)}" - - if " a " in word.lowered or "-a-" in word.lowered: - mo = PL_SB_PREP_DUAL_COMPOUND_RE.search(word) - if mo and mo.group(2) != "" and mo.group(3) != "": - return ( - f"{self._plnoun(mo.group(1), 2)}" - f"{mo.group(2)}" - f"{self._plnoun(mo.group(3))}" - ) - - if len(word.split_) >= 3: - handled_words = self._handle_long_compounds(word, count=2) - if handled_words is not None: - return handled_words - - # only pluralize denominators in units - mo = DENOMINATOR.search(word.lowered) - if mo: - index = len(mo.group("denominator")) - return f"{self._plnoun(word[:index])}{word[index:]}" - - # handle units given in degrees (only accept if - # there is no more than one word following) - # degree Celsius => degrees Celsius but degree - # fahrenheit hour => degree fahrenheit hours - if len(word.split_) >= 2 and word.split_[-2] == "degree": - return " ".join([self._plnoun(word.first)] + word.split_[1:]) - - with contextlib.suppress(ValueError): - return self._handle_prepositional_phrase( - word.lowered, - functools.partial(self._plnoun, count=2), - '-', - ) - - # HANDLE PRONOUNS - - for k, v in pl_pron_acc_keys_bysize.items(): - if word.lowered[-k:] in v: # ends with accusative pronoun - for pk, pv in pl_prep_bysize.items(): - if word.lowered[:pk] in pv: # starts with a prep - if word.lowered.split() == [ - word.lowered[:pk], - word.lowered[-k:], - ]: - # only whitespace in between - return word.lowered[:-k] + pl_pron_acc[word.lowered[-k:]] - - try: - return pl_pron_nom[word.lowered] - except KeyError: - pass - - try: - return pl_pron_acc[word.lowered] - except KeyError: - pass - - # HANDLE ISOLATED IRREGULAR PLURALS - - if word.last in pl_sb_irregular_caps: - llen = len(word.last) - return f"{word[:-llen]}{pl_sb_irregular_caps[word.last]}" - - lowered_last = word.last.lower() - if lowered_last in pl_sb_irregular: - llen = len(lowered_last) - return f"{word[:-llen]}{pl_sb_irregular[lowered_last]}" - - dash_split = word.lowered.split('-') - if (" ".join(dash_split[-2:])).lower() in pl_sb_irregular_compound: - llen = len( - " ".join(dash_split[-2:]) - ) # TODO: what if 2 spaces between these words? - return ( - f"{word[:-llen]}" - f"{pl_sb_irregular_compound[(' '.join(dash_split[-2:])).lower()]}" - ) - - if word.lowered[-3:] == "quy": - return f"{word[:-1]}ies" - - if word.lowered[-6:] == "person": - if self.classical_dict["persons"]: - return f"{word}s" - else: - return f"{word[:-4]}ople" - - # HANDLE FAMILIES OF IRREGULAR PLURALS - - if word.lowered[-3:] == "man": - for k, v in pl_sb_U_man_mans_bysize.items(): - if word.lowered[-k:] in v: - return f"{word}s" - for k, v in pl_sb_U_man_mans_caps_bysize.items(): - if word[-k:] in v: - return f"{word}s" - return f"{word[:-3]}men" - if word.lowered[-5:] == "mouse": - return f"{word[:-5]}mice" - if word.lowered[-5:] == "louse": - v = pl_sb_U_louse_lice_bysize.get(len(word)) - if v and word.lowered in v: - return f"{word[:-5]}lice" - return f"{word}s" - if word.lowered[-5:] == "goose": - return f"{word[:-5]}geese" - if word.lowered[-5:] == "tooth": - return f"{word[:-5]}teeth" - if word.lowered[-4:] == "foot": - return f"{word[:-4]}feet" - if word.lowered[-4:] == "taco": - return f"{word[:-5]}tacos" - - if word.lowered == "die": - return "dice" - - # HANDLE UNASSIMILATED IMPORTS - - if word.lowered[-4:] == "ceps": - return word - if word.lowered[-4:] == "zoon": - return f"{word[:-2]}a" - if word.lowered[-3:] in ("cis", "sis", "xis"): - return f"{word[:-2]}es" - - for lastlet, d, numend, post in ( - ("h", pl_sb_U_ch_chs_bysize, None, "s"), - ("x", pl_sb_U_ex_ices_bysize, -2, "ices"), - ("x", pl_sb_U_ix_ices_bysize, -2, "ices"), - ("m", pl_sb_U_um_a_bysize, -2, "a"), - ("s", pl_sb_U_us_i_bysize, -2, "i"), - ("n", pl_sb_U_on_a_bysize, -2, "a"), - ("a", pl_sb_U_a_ae_bysize, None, "e"), - ): - if word.lowered[-1] == lastlet: # this test to add speed - for k, v in d.items(): - if word.lowered[-k:] in v: - return word[:numend] + post - - # HANDLE INCOMPLETELY ASSIMILATED IMPORTS - - if self.classical_dict["ancient"]: - if word.lowered[-4:] == "trix": - return f"{word[:-1]}ces" - if word.lowered[-3:] in ("eau", "ieu"): - return f"{word}x" - if word.lowered[-3:] in ("ynx", "inx", "anx") and len(word) > 4: - return f"{word[:-1]}ges" - - for lastlet, d, numend, post in ( - ("n", pl_sb_C_en_ina_bysize, -2, "ina"), - ("x", pl_sb_C_ex_ices_bysize, -2, "ices"), - ("x", pl_sb_C_ix_ices_bysize, -2, "ices"), - ("m", pl_sb_C_um_a_bysize, -2, "a"), - ("s", pl_sb_C_us_i_bysize, -2, "i"), - ("s", pl_sb_C_us_us_bysize, None, ""), - ("a", pl_sb_C_a_ae_bysize, None, "e"), - ("a", pl_sb_C_a_ata_bysize, None, "ta"), - ("s", pl_sb_C_is_ides_bysize, -1, "des"), - ("o", pl_sb_C_o_i_bysize, -1, "i"), - ("n", pl_sb_C_on_a_bysize, -2, "a"), - ): - if word.lowered[-1] == lastlet: # this test to add speed - for k, v in d.items(): - if word.lowered[-k:] in v: - return word[:numend] + post - - for d, numend, post in ( - (pl_sb_C_i_bysize, None, "i"), - (pl_sb_C_im_bysize, None, "im"), - ): - for k, v in d.items(): - if word.lowered[-k:] in v: - return word[:numend] + post - - # HANDLE SINGULAR NOUNS ENDING IN ...s OR OTHER SILIBANTS - - if lowered_last in pl_sb_singular_s_complete: - return f"{word}es" - - for k, v in pl_sb_singular_s_bysize.items(): - if word.lowered[-k:] in v: - return f"{word}es" - - if word.lowered[-2:] == "es" and word[0] == word[0].upper(): - return f"{word}es" - - if word.lowered[-1] == "z": - for k, v in pl_sb_z_zes_bysize.items(): - if word.lowered[-k:] in v: - return f"{word}es" - - if word.lowered[-2:-1] != "z": - return f"{word}zes" - - if word.lowered[-2:] == "ze": - for k, v in pl_sb_ze_zes_bysize.items(): - if word.lowered[-k:] in v: - return f"{word}s" - - if word.lowered[-2:] in ("ch", "sh", "zz", "ss") or word.lowered[-1] == "x": - return f"{word}es" - - # HANDLE ...f -> ...ves - - if word.lowered[-3:] in ("elf", "alf", "olf"): - return f"{word[:-1]}ves" - if word.lowered[-3:] == "eaf" and word.lowered[-4:-3] != "d": - return f"{word[:-1]}ves" - if word.lowered[-4:] in ("nife", "life", "wife"): - return f"{word[:-2]}ves" - if word.lowered[-3:] == "arf": - return f"{word[:-1]}ves" - - # HANDLE ...y - - if word.lowered[-1] == "y": - if word.lowered[-2:-1] in "aeiou" or len(word) == 1: - return f"{word}s" - - if self.classical_dict["names"]: - if word.lowered[-1] == "y" and word[0] == word[0].upper(): - return f"{word}s" - - return f"{word[:-1]}ies" - - # HANDLE ...o - - if lowered_last in pl_sb_U_o_os_complete: - return f"{word}s" - - for k, v in pl_sb_U_o_os_bysize.items(): - if word.lowered[-k:] in v: - return f"{word}s" - - if word.lowered[-2:] in ("ao", "eo", "io", "oo", "uo"): - return f"{word}s" - - if word.lowered[-1] == "o": - return f"{word}es" - - # OTHERWISE JUST ADD ...s - - return f"{word}s" - - @classmethod - def _handle_prepositional_phrase(cls, phrase, transform, sep): - """ - Given a word or phrase possibly separated by sep, parse out - the prepositional phrase and apply the transform to the word - preceding the prepositional phrase. - - Raise ValueError if the pivot is not found or if at least two - separators are not found. - - >>> engine._handle_prepositional_phrase("man-of-war", str.upper, '-') - 'MAN-of-war' - >>> engine._handle_prepositional_phrase("man of war", str.upper, ' ') - 'MAN of war' - """ - parts = phrase.split(sep) - if len(parts) < 3: - raise ValueError("Cannot handle words with fewer than two separators") - - pivot = cls._find_pivot(parts, pl_prep_list_da) - - transformed = transform(parts[pivot - 1]) or parts[pivot - 1] - return " ".join( - parts[: pivot - 1] + [sep.join([transformed, parts[pivot], ''])] - ) + " ".join(parts[(pivot + 1) :]) - - def _handle_long_compounds(self, word: Words, count: int) -> Union[str, None]: - """ - Handles the plural and singular for compound `Words` that - have three or more words, based on the given count. - - >>> engine()._handle_long_compounds(Words("pair of scissors"), 2) - 'pairs of scissors' - >>> engine()._handle_long_compounds(Words("men beyond hills"), 1) - 'man beyond hills' - """ - inflection = self._sinoun if count == 1 else self._plnoun - solutions = ( # type: ignore - " ".join( - itertools.chain( - leader, - [inflection(cand, count), prep], # type: ignore - trailer, - ) - ) - for leader, (cand, prep), trailer in windowed_complete(word.split_, 2) - if prep in pl_prep_list_da # type: ignore - ) - return next(solutions, None) - - @staticmethod - def _find_pivot(words, candidates): - pivots = ( - index for index in range(1, len(words) - 1) if words[index] in candidates - ) - try: - return next(pivots) - except StopIteration: - raise ValueError("No pivot found") from None - - def _pl_special_verb( # noqa: C901 - self, word: str, count: Optional[Union[str, int]] = None - ) -> Union[str, bool]: - if self.classical_dict["zero"] and str(count).lower() in pl_count_zero: - return False - count = self.get_count(count) - - if count == 1: - return word - - # HANDLE USER-DEFINED VERBS - - value = self.ud_match(word, self.pl_v_user_defined) - if value is not None: - return value - - # HANDLE IRREGULAR PRESENT TENSE (SIMPLE AND COMPOUND) - - try: - words = Words(word) - except IndexError: - return False # word is '' - - if words.first in plverb_irregular_pres: - return f"{plverb_irregular_pres[words.first]}{words[len(words.first) :]}" - - # HANDLE IRREGULAR FUTURE, PRETERITE AND PERFECT TENSES - - if words.first in plverb_irregular_non_pres: - return word - - # HANDLE PRESENT NEGATIONS (SIMPLE AND COMPOUND) - - if words.first.endswith("n't") and words.first[:-3] in plverb_irregular_pres: - return ( - f"{plverb_irregular_pres[words.first[:-3]]}n't" - f"{words[len(words.first) :]}" - ) - - if words.first.endswith("n't"): - return word - - # HANDLE SPECIAL CASES - - mo = PLVERB_SPECIAL_S_RE.search(word) - if mo: - return False - if WHITESPACE.search(word): - return False - - if words.lowered == "quizzes": - return "quiz" - - # HANDLE STANDARD 3RD PERSON (CHOP THE ...(e)s OFF SINGLE WORDS) - - if ( - words.lowered[-4:] in ("ches", "shes", "zzes", "sses") - or words.lowered[-3:] == "xes" - ): - return words[:-2] - - if words.lowered[-3:] == "ies" and len(words) > 3: - return words.lowered[:-3] + "y" - - if ( - words.last.lower() in pl_v_oes_oe - or words.lowered[-4:] in pl_v_oes_oe_endings_size4 - or words.lowered[-5:] in pl_v_oes_oe_endings_size5 - ): - return words[:-1] - - if words.lowered.endswith("oes") and len(words) > 3: - return words.lowered[:-2] - - mo = ENDS_WITH_S.search(words) - if mo: - return mo.group(1) - - # OTHERWISE, A REGULAR VERB (HANDLE ELSEWHERE) - - return False - - def _pl_general_verb( - self, word: str, count: Optional[Union[str, int]] = None - ) -> str: - count = self.get_count(count) - - if count == 1: - return word - - # HANDLE AMBIGUOUS PRESENT TENSES (SIMPLE AND COMPOUND) - - mo = plverb_ambiguous_pres_keys.search(word) - if mo: - return f"{plverb_ambiguous_pres[mo.group(1).lower()]}{mo.group(2)}" - - # HANDLE AMBIGUOUS PRETERITE AND PERFECT TENSES - - mo = plverb_ambiguous_non_pres.search(word) - if mo: - return word - - # OTHERWISE, 1st OR 2ND PERSON IS UNINFLECTED - - return word - - def _pl_special_adjective( - self, word: str, count: Optional[Union[str, int]] = None - ) -> Union[str, bool]: - count = self.get_count(count) - - if count == 1: - return word - - # HANDLE USER-DEFINED ADJECTIVES - - value = self.ud_match(word, self.pl_adj_user_defined) - if value is not None: - return value - - # HANDLE KNOWN CASES - - mo = pl_adj_special_keys.search(word) - if mo: - return pl_adj_special[mo.group(1).lower()] - - # HANDLE POSSESSIVES - - mo = pl_adj_poss_keys.search(word) - if mo: - return pl_adj_poss[mo.group(1).lower()] - - mo = ENDS_WITH_APOSTROPHE_S.search(word) - if mo: - pl = self.plural_noun(mo.group(1)) - trailing_s = "" if pl[-1] == "s" else "s" - return f"{pl}'{trailing_s}" - - # OTHERWISE, NO IDEA - - return False - - # @profile - def _sinoun( # noqa: C901 - self, - word: str, - count: Optional[Union[str, int]] = None, - gender: Optional[str] = None, - ) -> Union[str, bool]: - count = self.get_count(count) - - # DEFAULT TO PLURAL - - if count == 2: - return word - - # SET THE GENDER - - try: - if gender is None: - gender = self.thegender - elif gender not in singular_pronoun_genders: - raise BadGenderError - except (TypeError, IndexError) as err: - raise BadGenderError from err - - # HANDLE USER-DEFINED NOUNS - - value = self.ud_match(word, self.si_sb_user_defined) - if value is not None: - return value - - # HANDLE EMPTY WORD, SINGULAR COUNT AND UNINFLECTED PLURALS - - if word == "": - return word - - if word in si_sb_ois_oi_case: - return word[:-1] - - words = Words(word) - - if words.last.lower() in pl_sb_uninflected_complete: - if len(words.split_) >= 3: - return self._handle_long_compounds(words, count=1) or word - return word - - if word in pl_sb_uninflected_caps: - return word - - for k, v in pl_sb_uninflected_bysize.items(): - if words.lowered[-k:] in v: - return word - - if self.classical_dict["herd"] and words.last.lower() in pl_sb_uninflected_herd: - return word - - if words.last.lower() in pl_sb_C_us_us: - return word if self.classical_dict["ancient"] else False - - # HANDLE COMPOUNDS ("Governor General", "mother-in-law", "aide-de-camp", ETC.) - - mo = PL_SB_POSTFIX_ADJ_STEMS_RE.search(word) - if mo and mo.group(2) != "": - return f"{self._sinoun(mo.group(1), 1, gender=gender)}{mo.group(2)}" - - with contextlib.suppress(ValueError): - return self._handle_prepositional_phrase( - words.lowered, - functools.partial(self._sinoun, count=1, gender=gender), - ' ', - ) - - with contextlib.suppress(ValueError): - return self._handle_prepositional_phrase( - words.lowered, - functools.partial(self._sinoun, count=1, gender=gender), - '-', - ) - - # HANDLE PRONOUNS - - for k, v in si_pron_acc_keys_bysize.items(): - if words.lowered[-k:] in v: # ends with accusative pronoun - for pk, pv in pl_prep_bysize.items(): - if words.lowered[:pk] in pv: # starts with a prep - if words.lowered.split() == [ - words.lowered[:pk], - words.lowered[-k:], - ]: - # only whitespace in between - return words.lowered[:-k] + get_si_pron( - "acc", words.lowered[-k:], gender - ) - - try: - return get_si_pron("nom", words.lowered, gender) - except KeyError: - pass - - try: - return get_si_pron("acc", words.lowered, gender) - except KeyError: - pass - - # HANDLE ISOLATED IRREGULAR PLURALS - - if words.last in si_sb_irregular_caps: - llen = len(words.last) - return f"{word[:-llen]}{si_sb_irregular_caps[words.last]}" - - if words.last.lower() in si_sb_irregular: - llen = len(words.last.lower()) - return f"{word[:-llen]}{si_sb_irregular[words.last.lower()]}" - - dash_split = words.lowered.split("-") - if (" ".join(dash_split[-2:])).lower() in si_sb_irregular_compound: - llen = len( - " ".join(dash_split[-2:]) - ) # TODO: what if 2 spaces between these words? - return "{}{}".format( - word[:-llen], - si_sb_irregular_compound[(" ".join(dash_split[-2:])).lower()], - ) - - if words.lowered[-5:] == "quies": - return word[:-3] + "y" - - if words.lowered[-7:] == "persons": - return word[:-1] - if words.lowered[-6:] == "people": - return word[:-4] + "rson" - - # HANDLE FAMILIES OF IRREGULAR PLURALS - - if words.lowered[-4:] == "mans": - for k, v in si_sb_U_man_mans_bysize.items(): - if words.lowered[-k:] in v: - return word[:-1] - for k, v in si_sb_U_man_mans_caps_bysize.items(): - if word[-k:] in v: - return word[:-1] - if words.lowered[-3:] == "men": - return word[:-3] + "man" - if words.lowered[-4:] == "mice": - return word[:-4] + "mouse" - if words.lowered[-4:] == "lice": - v = si_sb_U_louse_lice_bysize.get(len(word)) - if v and words.lowered in v: - return word[:-4] + "louse" - if words.lowered[-5:] == "geese": - return word[:-5] + "goose" - if words.lowered[-5:] == "teeth": - return word[:-5] + "tooth" - if words.lowered[-4:] == "feet": - return word[:-4] + "foot" - - if words.lowered == "dice": - return "die" - - # HANDLE UNASSIMILATED IMPORTS - - if words.lowered[-4:] == "ceps": - return word - if words.lowered[-3:] == "zoa": - return word[:-1] + "on" - - for lastlet, d, unass_numend, post in ( - ("s", si_sb_U_ch_chs_bysize, -1, ""), - ("s", si_sb_U_ex_ices_bysize, -4, "ex"), - ("s", si_sb_U_ix_ices_bysize, -4, "ix"), - ("a", si_sb_U_um_a_bysize, -1, "um"), - ("i", si_sb_U_us_i_bysize, -1, "us"), - ("a", si_sb_U_on_a_bysize, -1, "on"), - ("e", si_sb_U_a_ae_bysize, -1, ""), - ): - if words.lowered[-1] == lastlet: # this test to add speed - for k, v in d.items(): - if words.lowered[-k:] in v: - return word[:unass_numend] + post - - # HANDLE INCOMPLETELY ASSIMILATED IMPORTS - - if self.classical_dict["ancient"]: - if words.lowered[-6:] == "trices": - return word[:-3] + "x" - if words.lowered[-4:] in ("eaux", "ieux"): - return word[:-1] - if words.lowered[-5:] in ("ynges", "inges", "anges") and len(word) > 6: - return word[:-3] + "x" - - for lastlet, d, class_numend, post in ( - ("a", si_sb_C_en_ina_bysize, -3, "en"), - ("s", si_sb_C_ex_ices_bysize, -4, "ex"), - ("s", si_sb_C_ix_ices_bysize, -4, "ix"), - ("a", si_sb_C_um_a_bysize, -1, "um"), - ("i", si_sb_C_us_i_bysize, -1, "us"), - ("s", pl_sb_C_us_us_bysize, None, ""), - ("e", si_sb_C_a_ae_bysize, -1, ""), - ("a", si_sb_C_a_ata_bysize, -2, ""), - ("s", si_sb_C_is_ides_bysize, -3, "s"), - ("i", si_sb_C_o_i_bysize, -1, "o"), - ("a", si_sb_C_on_a_bysize, -1, "on"), - ("m", si_sb_C_im_bysize, -2, ""), - ("i", si_sb_C_i_bysize, -1, ""), - ): - if words.lowered[-1] == lastlet: # this test to add speed - for k, v in d.items(): - if words.lowered[-k:] in v: - return word[:class_numend] + post - - # HANDLE PLURLS ENDING IN uses -> use - - if ( - words.lowered[-6:] == "houses" - or word in si_sb_uses_use_case - or words.last.lower() in si_sb_uses_use - ): - return word[:-1] - - # HANDLE PLURLS ENDING IN ies -> ie - - if word in si_sb_ies_ie_case or words.last.lower() in si_sb_ies_ie: - return word[:-1] - - # HANDLE PLURLS ENDING IN oes -> oe - - if ( - words.lowered[-5:] == "shoes" - or word in si_sb_oes_oe_case - or words.last.lower() in si_sb_oes_oe - ): - return word[:-1] - - # HANDLE SINGULAR NOUNS ENDING IN ...s OR OTHER SILIBANTS - - if word in si_sb_sses_sse_case or words.last.lower() in si_sb_sses_sse: - return word[:-1] - - if words.last.lower() in si_sb_singular_s_complete: - return word[:-2] - - for k, v in si_sb_singular_s_bysize.items(): - if words.lowered[-k:] in v: - return word[:-2] - - if words.lowered[-4:] == "eses" and word[0] == word[0].upper(): - return word[:-2] - - if words.last.lower() in si_sb_z_zes: - return word[:-2] - - if words.last.lower() in si_sb_zzes_zz: - return word[:-2] - - if words.lowered[-4:] == "zzes": - return word[:-3] - - if word in si_sb_ches_che_case or words.last.lower() in si_sb_ches_che: - return word[:-1] - - if words.lowered[-4:] in ("ches", "shes"): - return word[:-2] - - if words.last.lower() in si_sb_xes_xe: - return word[:-1] - - if words.lowered[-3:] == "xes": - return word[:-2] - - # HANDLE ...f -> ...ves - - if word in si_sb_ves_ve_case or words.last.lower() in si_sb_ves_ve: - return word[:-1] - - if words.lowered[-3:] == "ves": - if words.lowered[-5:-3] in ("el", "al", "ol"): - return word[:-3] + "f" - if words.lowered[-5:-3] == "ea" and word[-6:-5] != "d": - return word[:-3] + "f" - if words.lowered[-5:-3] in ("ni", "li", "wi"): - return word[:-3] + "fe" - if words.lowered[-5:-3] == "ar": - return word[:-3] + "f" - - # HANDLE ...y - - if words.lowered[-2:] == "ys": - if len(words.lowered) > 2 and words.lowered[-3] in "aeiou": - return word[:-1] - - if self.classical_dict["names"]: - if words.lowered[-2:] == "ys" and word[0] == word[0].upper(): - return word[:-1] - - if words.lowered[-3:] == "ies": - return word[:-3] + "y" - - # HANDLE ...o - - if words.lowered[-2:] == "os": - if words.last.lower() in si_sb_U_o_os_complete: - return word[:-1] - - for k, v in si_sb_U_o_os_bysize.items(): - if words.lowered[-k:] in v: - return word[:-1] - - if words.lowered[-3:] in ("aos", "eos", "ios", "oos", "uos"): - return word[:-1] - - if words.lowered[-3:] == "oes": - return word[:-2] - - # UNASSIMILATED IMPORTS FINAL RULE - - if word in si_sb_es_is: - return word[:-2] + "is" - - # OTHERWISE JUST REMOVE ...s - - if words.lowered[-1] == "s": - return word[:-1] - - # COULD NOT FIND SINGULAR - - return False - - # ADJECTIVES - - @typechecked - def a(self, text: Word, count: Optional[Union[int, str, Any]] = 1) -> str: - """ - Return the appropriate indefinite article followed by text. - - The indefinite article is either 'a' or 'an'. - - If count is not one, then return count followed by text - instead of 'a' or 'an'. - - Whitespace at the start and end is preserved. - - """ - mo = INDEFINITE_ARTICLE_TEST.search(text) - if mo: - word = mo.group(2) - if not word: - return text - pre = mo.group(1) - post = mo.group(3) - result = self._indef_article(word, count) - return f"{pre}{result}{post}" - return "" - - an = a - - _indef_article_cases = ( - # HANDLE ORDINAL FORMS - (A_ordinal_a, "a"), - (A_ordinal_an, "an"), - # HANDLE SPECIAL CASES - (A_explicit_an, "an"), - (SPECIAL_AN, "an"), - (SPECIAL_A, "a"), - # HANDLE ABBREVIATIONS - (A_abbrev, "an"), - (SPECIAL_ABBREV_AN, "an"), - (SPECIAL_ABBREV_A, "a"), - # HANDLE CONSONANTS - (CONSONANTS, "a"), - # HANDLE SPECIAL VOWEL-FORMS - (ARTICLE_SPECIAL_EU, "a"), - (ARTICLE_SPECIAL_ONCE, "a"), - (ARTICLE_SPECIAL_ONETIME, "a"), - (ARTICLE_SPECIAL_UNIT, "a"), - (ARTICLE_SPECIAL_UBA, "a"), - (ARTICLE_SPECIAL_UKR, "a"), - (A_explicit_a, "a"), - # HANDLE SPECIAL CAPITALS - (SPECIAL_CAPITALS, "a"), - # HANDLE VOWELS - (VOWELS, "an"), - # HANDLE y... - # (BEFORE CERTAIN CONSONANTS IMPLIES (UNNATURALIZED) "i.." SOUND) - (A_y_cons, "an"), - ) - - def _indef_article(self, word: str, count: Union[int, str, Any]) -> str: - mycount = self.get_count(count) - - if mycount != 1: - return f"{count} {word}" - - # HANDLE USER-DEFINED VARIANTS - - value = self.ud_match(word, self.A_a_user_defined) - if value is not None: - return f"{value} {word}" - - matches = ( - f'{article} {word}' - for regexen, article in self._indef_article_cases - if regexen.search(word) - ) - - # OTHERWISE, GUESS "a" - fallback = f'a {word}' - return next(matches, fallback) - - # 2. TRANSLATE ZERO-QUANTIFIED $word TO "no plural($word)" - - @typechecked - def no(self, text: Word, count: Optional[Union[int, str]] = None) -> str: - """ - If count is 0, no, zero or nil, return 'no' followed by the plural - of text. - - If count is one of: - 1, a, an, one, each, every, this, that - return count followed by text. - - Otherwise return count follow by the plural of text. - - In the return value count is always followed by a space. - - Whitespace at the start and end is preserved. - - """ - if count is None and self.persistent_count is not None: - count = self.persistent_count - - if count is None: - count = 0 - mo = PARTITION_WORD.search(text) - if mo: - pre = mo.group(1) - word = mo.group(2) - post = mo.group(3) - else: - pre = "" - word = "" - post = "" - - if str(count).lower() in pl_count_zero: - count = 'no' - return f"{pre}{count} {self.plural(word, count)}{post}" - - # PARTICIPLES - - @typechecked - def present_participle(self, word: Word) -> str: - """ - Return the present participle for word. - - word is the 3rd person singular verb. - - """ - plv = self.plural_verb(word, 2) - ans = plv - - for regexen, repl in PRESENT_PARTICIPLE_REPLACEMENTS: - ans, num = regexen.subn(repl, plv) - if num: - return f"{ans}ing" - return f"{ans}ing" - - # NUMERICAL INFLECTIONS - - @typechecked - def ordinal(self, num: Union[Number, Word]) -> str: - """ - Return the ordinal of num. - - >>> ordinal = engine().ordinal - >>> ordinal(1) - '1st' - >>> ordinal('one') - 'first' - """ - if DIGIT.match(str(num)): - if isinstance(num, (float, int)) and int(num) == num: - n = int(num) - else: - if "." in str(num): - try: - # numbers after decimal, - # so only need last one for ordinal - n = int(str(num)[-1]) - - except ValueError: # ends with '.', so need to use whole string - n = int(str(num)[:-1]) - else: - n = int(num) # type: ignore - try: - post = nth[n % 100] - except KeyError: - post = nth[n % 10] - return f"{num}{post}" - else: - return self._sub_ord(num) - - def millfn(self, ind: int = 0) -> str: - if ind > len(mill) - 1: - raise NumOutOfRangeError - return mill[ind] - - def unitfn(self, units: int, mindex: int = 0) -> str: - return f"{unit[units]}{self.millfn(mindex)}" - - def tenfn(self, tens, units, mindex=0) -> str: - if tens != 1: - tens_part = ten[tens] - if tens and units: - hyphen = "-" - else: - hyphen = "" - unit_part = unit[units] - mill_part = self.millfn(mindex) - return f"{tens_part}{hyphen}{unit_part}{mill_part}" - return f"{teen[units]}{mill[mindex]}" - - def hundfn(self, hundreds: int, tens: int, units: int, mindex: int) -> str: - if hundreds: - andword = f" {self._number_args['andword']} " if tens or units else "" - # use unit not unitfn as simpler - return ( - f"{unit[hundreds]} hundred{andword}" - f"{self.tenfn(tens, units)}{self.millfn(mindex)}, " - ) - if tens or units: - return f"{self.tenfn(tens, units)}{self.millfn(mindex)}, " - return "" - - def group1sub(self, mo: Match) -> str: - units = int(mo.group(1)) - if units == 1: - return f" {self._number_args['one']}, " - elif units: - return f"{unit[units]}, " - else: - return f" {self._number_args['zero']}, " - - def group1bsub(self, mo: Match) -> str: - units = int(mo.group(1)) - if units: - return f"{unit[units]}, " - else: - return f" {self._number_args['zero']}, " - - def group2sub(self, mo: Match) -> str: - tens = int(mo.group(1)) - units = int(mo.group(2)) - if tens: - return f"{self.tenfn(tens, units)}, " - if units: - return f" {self._number_args['zero']} {unit[units]}, " - return f" {self._number_args['zero']} {self._number_args['zero']}, " - - def group3sub(self, mo: Match) -> str: - hundreds = int(mo.group(1)) - tens = int(mo.group(2)) - units = int(mo.group(3)) - if hundreds == 1: - hunword = f" {self._number_args['one']}" - elif hundreds: - hunword = str(unit[hundreds]) - else: - hunword = f" {self._number_args['zero']}" - if tens: - tenword = self.tenfn(tens, units) - elif units: - tenword = f" {self._number_args['zero']} {unit[units]}" - else: - tenword = f" {self._number_args['zero']} {self._number_args['zero']}" - return f"{hunword} {tenword}, " - - def hundsub(self, mo: Match) -> str: - ret = self.hundfn( - int(mo.group(1)), int(mo.group(2)), int(mo.group(3)), self.mill_count - ) - self.mill_count += 1 - return ret - - def tensub(self, mo: Match) -> str: - return f"{self.tenfn(int(mo.group(1)), int(mo.group(2)), self.mill_count)}, " - - def unitsub(self, mo: Match) -> str: - return f"{self.unitfn(int(mo.group(1)), self.mill_count)}, " - - def enword(self, num: str, group: int) -> str: - # import pdb - # pdb.set_trace() - - if group == 1: - num = DIGIT_GROUP.sub(self.group1sub, num) - elif group == 2: - num = TWO_DIGITS.sub(self.group2sub, num) - num = DIGIT_GROUP.sub(self.group1bsub, num, 1) - elif group == 3: - num = THREE_DIGITS.sub(self.group3sub, num) - num = TWO_DIGITS.sub(self.group2sub, num, 1) - num = DIGIT_GROUP.sub(self.group1sub, num, 1) - elif int(num) == 0: - num = self._number_args["zero"] - elif int(num) == 1: - num = self._number_args["one"] - else: - num = num.lstrip().lstrip("0") - self.mill_count = 0 - # surely there's a better way to do the next bit - mo = THREE_DIGITS_WORD.search(num) - while mo: - num = THREE_DIGITS_WORD.sub(self.hundsub, num, 1) - mo = THREE_DIGITS_WORD.search(num) - num = TWO_DIGITS_WORD.sub(self.tensub, num, 1) - num = ONE_DIGIT_WORD.sub(self.unitsub, num, 1) - return num - - @staticmethod - def _sub_ord(val): - new = ordinal_suff.sub(lambda match: ordinal[match.group(1)], val) - return new + "th" * (new == val) - - @classmethod - def _chunk_num(cls, num, decimal, group): - if decimal: - max_split = -1 if group != 0 else 1 - chunks = num.split(".", max_split) - else: - chunks = [num] - return cls._remove_last_blank(chunks) - - @staticmethod - def _remove_last_blank(chunks): - """ - Remove the last item from chunks if it's a blank string. - - Return the resultant chunks and whether the last item was removed. - """ - removed = chunks[-1] == "" - result = chunks[:-1] if removed else chunks - return result, removed - - @staticmethod - def _get_sign(num): - return {'+': 'plus', '-': 'minus'}.get(num.lstrip()[0], '') - - @typechecked - def number_to_words( # noqa: C901 - self, - num: Union[Number, Word], - wantlist: bool = False, - group: int = 0, - comma: Union[Falsish, str] = ",", - andword: str = "and", - zero: str = "zero", - one: str = "one", - decimal: Union[Falsish, str] = "point", - threshold: Optional[int] = None, - ) -> Union[str, List[str]]: - """ - Return a number in words. - - group = 1, 2 or 3 to group numbers before turning into words - comma: define comma - - andword: - word for 'and'. Can be set to ''. - e.g. "one hundred and one" vs "one hundred one" - - zero: word for '0' - one: word for '1' - decimal: word for decimal point - threshold: numbers above threshold not turned into words - - parameters not remembered from last call. Departure from Perl version. - """ - self._number_args = {"andword": andword, "zero": zero, "one": one} - num = str(num) - - # Handle "stylistic" conversions (up to a given threshold)... - if threshold is not None and float(num) > threshold: - spnum = num.split(".", 1) - while comma: - (spnum[0], n) = FOUR_DIGIT_COMMA.subn(r"\1,\2", spnum[0]) - if n == 0: - break - try: - return f"{spnum[0]}.{spnum[1]}" - except IndexError: - return str(spnum[0]) - - if group < 0 or group > 3: - raise BadChunkingOptionError - - sign = self._get_sign(num) - - if num in nth_suff: - num = zero - - myord = num[-2:] in nth_suff - if myord: - num = num[:-2] - - chunks, finalpoint = self._chunk_num(num, decimal, group) - - loopstart = chunks[0] == "" - first: bool | None = not loopstart - - def _handle_chunk(chunk): - nonlocal first - - # remove all non numeric \D - chunk = NON_DIGIT.sub("", chunk) - if chunk == "": - chunk = "0" - - if group == 0 and not first: - chunk = self.enword(chunk, 1) - else: - chunk = self.enword(chunk, group) - - if chunk[-2:] == ", ": - chunk = chunk[:-2] - chunk = WHITESPACES_COMMA.sub(",", chunk) - - if group == 0 and first: - chunk = COMMA_WORD.sub(f" {andword} \\1", chunk) - chunk = WHITESPACES.sub(" ", chunk) - # chunk = re.sub(r"(\A\s|\s\Z)", self.blankfn, chunk) - chunk = chunk.strip() - if first: - first = None - return chunk - - chunks[loopstart:] = map(_handle_chunk, chunks[loopstart:]) - - numchunks = [] - if first != 0: - numchunks = chunks[0].split(f"{comma} ") - - if myord and numchunks: - numchunks[-1] = self._sub_ord(numchunks[-1]) - - for chunk in chunks[1:]: - numchunks.append(decimal) - numchunks.extend(chunk.split(f"{comma} ")) - - if finalpoint: - numchunks.append(decimal) - - if wantlist: - return [sign] * bool(sign) + numchunks - - signout = f"{sign} " if sign else "" - valout = ( - ', '.join(numchunks) - if group - else ''.join(self._render(numchunks, decimal, comma)) - ) - return signout + valout - - @staticmethod - def _render(chunks, decimal, comma): - first_item = chunks.pop(0) - yield first_item - first = decimal is None or not first_item.endswith(decimal) - for nc in chunks: - if nc == decimal: - first = False - elif first: - yield comma - yield f" {nc}" - - @typechecked - def join( - self, - words: Optional[Sequence[Word]], - sep: Optional[str] = None, - sep_spaced: bool = True, - final_sep: Optional[str] = None, - conj: str = "and", - conj_spaced: bool = True, - ) -> str: - """ - Join words into a list. - - e.g. join(['ant', 'bee', 'fly']) returns 'ant, bee, and fly' - - options: - conj: replacement for 'and' - sep: separator. default ',', unless ',' is in the list then ';' - final_sep: final separator. default ',', unless ',' is in the list then ';' - conj_spaced: boolean. Should conj have spaces around it - - """ - if not words: - return "" - if len(words) == 1: - return words[0] - - if conj_spaced: - if conj == "": - conj = " " - else: - conj = f" {conj} " - - if len(words) == 2: - return f"{words[0]}{conj}{words[1]}" - - if sep is None: - if "," in "".join(words): - sep = ";" - else: - sep = "," - if final_sep is None: - final_sep = sep - - final_sep = f"{final_sep}{conj}" - - if sep_spaced: - sep += " " - - return f"{sep.join(words[0:-1])}{final_sep}{words[-1]}" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 112ea2f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 9d832e9..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__pycache__/py38.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__pycache__/py38.cpython-312.pyc deleted file mode 100644 index f0b482e..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/__pycache__/py38.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/py38.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/py38.py deleted file mode 100644 index a2d01bd..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/inflect/compat/py38.py +++ /dev/null @@ -1,7 +0,0 @@ -import sys - - -if sys.version_info > (3, 9): - from typing import Annotated -else: # pragma: no cover - from typing_extensions import Annotated # noqa: F401 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/LICENSE deleted file mode 100644 index 1bb5a44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/LICENSE +++ /dev/null @@ -1,17 +0,0 @@ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/METADATA deleted file mode 100644 index fe6ca5a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/METADATA +++ /dev/null @@ -1,85 +0,0 @@ -Metadata-Version: 2.1 -Name: jaraco.collections -Version: 5.1.0 -Summary: Collection objects similar to those in stdlib by jaraco -Author-email: "Jason R. Coombs" -Project-URL: Source, https://github.com/jaraco/jaraco.collections -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -License-File: LICENSE -Requires-Dist: jaraco.text -Provides-Extra: check -Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'check' -Requires-Dist: pytest-ruff >=0.2.1 ; (sys_platform != "cygwin") and extra == 'check' -Provides-Extra: cover -Requires-Dist: pytest-cov ; extra == 'cover' -Provides-Extra: doc -Requires-Dist: sphinx >=3.5 ; extra == 'doc' -Requires-Dist: jaraco.packaging >=9.3 ; extra == 'doc' -Requires-Dist: rst.linker >=1.9 ; extra == 'doc' -Requires-Dist: furo ; extra == 'doc' -Requires-Dist: sphinx-lint ; extra == 'doc' -Requires-Dist: jaraco.tidelift >=1.4 ; extra == 'doc' -Provides-Extra: enabler -Requires-Dist: pytest-enabler >=2.2 ; extra == 'enabler' -Provides-Extra: test -Requires-Dist: pytest !=8.1.*,>=6 ; extra == 'test' -Provides-Extra: type -Requires-Dist: pytest-mypy ; extra == 'type' - -.. image:: https://img.shields.io/pypi/v/jaraco.collections.svg - :target: https://pypi.org/project/jaraco.collections - -.. image:: https://img.shields.io/pypi/pyversions/jaraco.collections.svg - -.. image:: https://github.com/jaraco/jaraco.collections/actions/workflows/main.yml/badge.svg - :target: https://github.com/jaraco/jaraco.collections/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. image:: https://readthedocs.org/projects/jaracocollections/badge/?version=latest - :target: https://jaracocollections.readthedocs.io/en/latest/?badge=latest - -.. image:: https://img.shields.io/badge/skeleton-2024-informational - :target: https://blog.jaraco.com/skeleton - -.. image:: https://tidelift.com/badges/package/pypi/jaraco.collections - :target: https://tidelift.com/subscription/pkg/pypi-jaraco.collections?utm_source=pypi-jaraco.collections&utm_medium=readme - -Models and classes to supplement the stdlib 'collections' module. - -See the docs, linked above, for descriptions and usage examples. - -Highlights include: - -- RangeMap: A mapping that accepts a range of values for keys. -- Projection: A subset over an existing mapping. -- KeyTransformingDict: Generalized mapping with keys transformed by a function. -- FoldedCaseKeyedDict: A dict whose string keys are case-insensitive. -- BijectiveMap: A map where keys map to values and values back to their keys. -- ItemsAsAttributes: A mapping mix-in exposing items as attributes. -- IdentityOverrideMap: A map whose keys map by default to themselves unless overridden. -- FrozenDict: A hashable, immutable map. -- Enumeration: An object whose keys are enumerated. -- Everything: A container that contains all things. -- Least, Greatest: Objects that are always less than or greater than any other. -- pop_all: Return all items from the mutable sequence and remove them from that sequence. -- DictStack: A stack of dicts, great for sharing scopes. -- WeightedLookup: A specialized RangeMap for selecting an item by weights. - -For Enterprise -============== - -Available as part of the Tidelift Subscription. - -This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. - -`Learn more `_. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/RECORD deleted file mode 100644 index 48b957e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/RECORD +++ /dev/null @@ -1,10 +0,0 @@ -jaraco.collections-5.1.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -jaraco.collections-5.1.0.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -jaraco.collections-5.1.0.dist-info/METADATA,sha256=IMUaliNsA5X1Ox9MXUWOagch5R4Wwb_3M7erp29dBtg,3933 -jaraco.collections-5.1.0.dist-info/RECORD,, -jaraco.collections-5.1.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -jaraco.collections-5.1.0.dist-info/WHEEL,sha256=Mdi9PDNwEZptOjTlUcAth7XJDFtKrHYaQMPulZeBCiQ,91 -jaraco.collections-5.1.0.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -jaraco/collections/__init__.py,sha256=Pc1-SqjWm81ad1P0-GttpkwO_LWlnaY6gUq8gcKh2v0,26640 -jaraco/collections/__pycache__/__init__.cpython-312.pyc,, -jaraco/collections/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/REQUESTED deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/WHEEL deleted file mode 100644 index 50e1e84..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: setuptools (73.0.1) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/top_level.txt deleted file mode 100644 index f6205a5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.collections-5.1.0.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -jaraco diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/LICENSE deleted file mode 100644 index 1bb5a44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/LICENSE +++ /dev/null @@ -1,17 +0,0 @@ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/METADATA deleted file mode 100644 index a36f7c5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/METADATA +++ /dev/null @@ -1,75 +0,0 @@ -Metadata-Version: 2.1 -Name: jaraco.context -Version: 5.3.0 -Summary: Useful decorators and context managers -Home-page: https://github.com/jaraco/jaraco.context -Author: Jason R. Coombs -Author-email: jaraco@jaraco.com -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Requires-Python: >=3.8 -License-File: LICENSE -Requires-Dist: backports.tarfile ; python_version < "3.12" -Provides-Extra: docs -Requires-Dist: sphinx >=3.5 ; extra == 'docs' -Requires-Dist: jaraco.packaging >=9.3 ; extra == 'docs' -Requires-Dist: rst.linker >=1.9 ; extra == 'docs' -Requires-Dist: furo ; extra == 'docs' -Requires-Dist: sphinx-lint ; extra == 'docs' -Requires-Dist: jaraco.tidelift >=1.4 ; extra == 'docs' -Provides-Extra: testing -Requires-Dist: pytest !=8.1.1,>=6 ; extra == 'testing' -Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'testing' -Requires-Dist: pytest-cov ; extra == 'testing' -Requires-Dist: pytest-mypy ; extra == 'testing' -Requires-Dist: pytest-enabler >=2.2 ; extra == 'testing' -Requires-Dist: pytest-ruff >=0.2.1 ; extra == 'testing' -Requires-Dist: portend ; extra == 'testing' - -.. image:: https://img.shields.io/pypi/v/jaraco.context.svg - :target: https://pypi.org/project/jaraco.context - -.. image:: https://img.shields.io/pypi/pyversions/jaraco.context.svg - -.. image:: https://github.com/jaraco/jaraco.context/actions/workflows/main.yml/badge.svg - :target: https://github.com/jaraco/jaraco.context/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. image:: https://readthedocs.org/projects/jaracocontext/badge/?version=latest - :target: https://jaracocontext.readthedocs.io/en/latest/?badge=latest - -.. image:: https://img.shields.io/badge/skeleton-2024-informational - :target: https://blog.jaraco.com/skeleton - -.. image:: https://tidelift.com/badges/package/pypi/jaraco.context - :target: https://tidelift.com/subscription/pkg/pypi-jaraco.context?utm_source=pypi-jaraco.context&utm_medium=readme - - -Highlights -========== - -See the docs linked from the badge above for the full details, but here are some features that may be of interest. - -- ``ExceptionTrap`` provides a general-purpose wrapper for trapping exceptions and then acting on the outcome. Includes ``passes`` and ``raises`` decorators to replace the result of a wrapped function by a boolean indicating the outcome of the exception trap. See `this keyring commit `_ for an example of it in production. -- ``suppress`` simply enables ``contextlib.suppress`` as a decorator. -- ``on_interrupt`` is a decorator used by CLI entry points to affect the handling of a ``KeyboardInterrupt``. Inspired by `Lucretiel/autocommand#18 `_. -- ``pushd`` is similar to pytest's ``monkeypatch.chdir`` or path's `default context `_, changes the current working directory for the duration of the context. -- ``tarball`` will download a tarball, extract it, change directory, yield, then clean up after. Convenient when working with web assets. -- ``null`` is there for those times when one code branch needs a context and the other doesn't; this null context provides symmetry across those branches. - - -For Enterprise -============== - -Available as part of the Tidelift Subscription. - -This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. - -`Learn more `_. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/RECORD deleted file mode 100644 index 09d191f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/RECORD +++ /dev/null @@ -1,8 +0,0 @@ -jaraco.context-5.3.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -jaraco.context-5.3.0.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -jaraco.context-5.3.0.dist-info/METADATA,sha256=xDtguJej0tN9iEXCUvxEJh2a7xceIRVBEakBLSr__tY,4020 -jaraco.context-5.3.0.dist-info/RECORD,, -jaraco.context-5.3.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -jaraco.context-5.3.0.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -jaraco/__pycache__/context.cpython-312.pyc,, -jaraco/context.py,sha256=REoLIxDkO5MfEYowt_WoupNCRoxBS5v7YX2PbW8lIcs,9552 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/WHEEL deleted file mode 100644 index bab98d6..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.43.0) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/top_level.txt deleted file mode 100644 index f6205a5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.context-5.3.0.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -jaraco diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/LICENSE deleted file mode 100644 index 1bb5a44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/LICENSE +++ /dev/null @@ -1,17 +0,0 @@ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/METADATA deleted file mode 100644 index c865140..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/METADATA +++ /dev/null @@ -1,64 +0,0 @@ -Metadata-Version: 2.1 -Name: jaraco.functools -Version: 4.0.1 -Summary: Functools like those found in stdlib -Author-email: "Jason R. Coombs" -Project-URL: Homepage, https://github.com/jaraco/jaraco.functools -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -License-File: LICENSE -Requires-Dist: more-itertools -Provides-Extra: docs -Requires-Dist: sphinx >=3.5 ; extra == 'docs' -Requires-Dist: sphinx <7.2.5 ; extra == 'docs' -Requires-Dist: jaraco.packaging >=9.3 ; extra == 'docs' -Requires-Dist: rst.linker >=1.9 ; extra == 'docs' -Requires-Dist: furo ; extra == 'docs' -Requires-Dist: sphinx-lint ; extra == 'docs' -Requires-Dist: jaraco.tidelift >=1.4 ; extra == 'docs' -Provides-Extra: testing -Requires-Dist: pytest >=6 ; extra == 'testing' -Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'testing' -Requires-Dist: pytest-cov ; extra == 'testing' -Requires-Dist: pytest-enabler >=2.2 ; extra == 'testing' -Requires-Dist: pytest-ruff >=0.2.1 ; extra == 'testing' -Requires-Dist: jaraco.classes ; extra == 'testing' -Requires-Dist: pytest-mypy ; (platform_python_implementation != "PyPy") and extra == 'testing' - -.. image:: https://img.shields.io/pypi/v/jaraco.functools.svg - :target: https://pypi.org/project/jaraco.functools - -.. image:: https://img.shields.io/pypi/pyversions/jaraco.functools.svg - -.. image:: https://github.com/jaraco/jaraco.functools/actions/workflows/main.yml/badge.svg - :target: https://github.com/jaraco/jaraco.functools/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. image:: https://readthedocs.org/projects/jaracofunctools/badge/?version=latest - :target: https://jaracofunctools.readthedocs.io/en/latest/?badge=latest - -.. image:: https://img.shields.io/badge/skeleton-2024-informational - :target: https://blog.jaraco.com/skeleton - -.. image:: https://tidelift.com/badges/package/pypi/jaraco.functools - :target: https://tidelift.com/subscription/pkg/pypi-jaraco.functools?utm_source=pypi-jaraco.functools&utm_medium=readme - -Additional functools in the spirit of stdlib's functools. - -For Enterprise -============== - -Available as part of the Tidelift Subscription. - -This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. - -`Learn more `_. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/RECORD deleted file mode 100644 index ef3bc21..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/RECORD +++ /dev/null @@ -1,10 +0,0 @@ -jaraco.functools-4.0.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -jaraco.functools-4.0.1.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -jaraco.functools-4.0.1.dist-info/METADATA,sha256=i4aUaQDX-jjdEQK5wevhegyx8JyLfin2HyvaSk3FHso,2891 -jaraco.functools-4.0.1.dist-info/RECORD,, -jaraco.functools-4.0.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -jaraco.functools-4.0.1.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -jaraco/functools/__init__.py,sha256=hEAJaS2uSZRuF_JY4CxCHIYh79ZpxaPp9OiHyr9EJ1w,16642 -jaraco/functools/__init__.pyi,sha256=gk3dsgHzo5F_U74HzAvpNivFAPCkPJ1b2-yCd62dfnw,3878 -jaraco/functools/__pycache__/__init__.cpython-312.pyc,, -jaraco/functools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/WHEEL deleted file mode 100644 index bab98d6..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.43.0) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/top_level.txt deleted file mode 100644 index f6205a5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.functools-4.0.1.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -jaraco diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/LICENSE deleted file mode 100644 index 1bb5a44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/LICENSE +++ /dev/null @@ -1,17 +0,0 @@ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/METADATA deleted file mode 100644 index 0258a38..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/METADATA +++ /dev/null @@ -1,95 +0,0 @@ -Metadata-Version: 2.1 -Name: jaraco.text -Version: 3.12.1 -Summary: Module for text manipulation -Author-email: "Jason R. Coombs" -Project-URL: Homepage, https://github.com/jaraco/jaraco.text -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -License-File: LICENSE -Requires-Dist: jaraco.functools -Requires-Dist: jaraco.context >=4.1 -Requires-Dist: autocommand -Requires-Dist: inflect -Requires-Dist: more-itertools -Requires-Dist: importlib-resources ; python_version < "3.9" -Provides-Extra: doc -Requires-Dist: sphinx >=3.5 ; extra == 'doc' -Requires-Dist: jaraco.packaging >=9.3 ; extra == 'doc' -Requires-Dist: rst.linker >=1.9 ; extra == 'doc' -Requires-Dist: furo ; extra == 'doc' -Requires-Dist: sphinx-lint ; extra == 'doc' -Requires-Dist: jaraco.tidelift >=1.4 ; extra == 'doc' -Provides-Extra: test -Requires-Dist: pytest !=8.1.*,>=6 ; extra == 'test' -Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'test' -Requires-Dist: pytest-cov ; extra == 'test' -Requires-Dist: pytest-mypy ; extra == 'test' -Requires-Dist: pytest-enabler >=2.2 ; extra == 'test' -Requires-Dist: pytest-ruff >=0.2.1 ; extra == 'test' -Requires-Dist: pathlib2 ; (python_version < "3.10") and extra == 'test' - -.. image:: https://img.shields.io/pypi/v/jaraco.text.svg - :target: https://pypi.org/project/jaraco.text - -.. image:: https://img.shields.io/pypi/pyversions/jaraco.text.svg - -.. image:: https://github.com/jaraco/jaraco.text/actions/workflows/main.yml/badge.svg - :target: https://github.com/jaraco/jaraco.text/actions?query=workflow%3A%22tests%22 - :alt: tests - -.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json - :target: https://github.com/astral-sh/ruff - :alt: Ruff - -.. image:: https://readthedocs.org/projects/jaracotext/badge/?version=latest - :target: https://jaracotext.readthedocs.io/en/latest/?badge=latest - -.. image:: https://img.shields.io/badge/skeleton-2024-informational - :target: https://blog.jaraco.com/skeleton - -.. image:: https://tidelift.com/badges/package/pypi/jaraco.text - :target: https://tidelift.com/subscription/pkg/pypi-jaraco.text?utm_source=pypi-jaraco.text&utm_medium=readme - - -This package provides handy routines for dealing with text, such as -wrapping, substitution, trimming, stripping, prefix and suffix removal, -line continuation, indentation, comment processing, identifier processing, -values parsing, case insensitive comparison, and more. See the docs -(linked in the badge above) for the detailed documentation and examples. - -Layouts -======= - -One of the features of this package is the layouts module, which -provides a simple example of translating keystrokes from one keyboard -layout to another:: - - echo qwerty | python -m jaraco.text.to-dvorak - ',.pyf - echo "',.pyf" | python -m jaraco.text.to-qwerty - qwerty - -Newline Reporting -================= - -Need to know what newlines appear in a file? - -:: - - $ python -m jaraco.text.show-newlines README.rst - newline is '\n' - -For Enterprise -============== - -Available as part of the Tidelift Subscription. - -This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use. - -`Learn more `_. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/RECORD deleted file mode 100644 index 19e2d84..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/RECORD +++ /dev/null @@ -1,20 +0,0 @@ -jaraco.text-3.12.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -jaraco.text-3.12.1.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023 -jaraco.text-3.12.1.dist-info/METADATA,sha256=AzWdm6ViMfDOPoQMfLWn2zgBQSGJScyqeN29TcuWXVI,3658 -jaraco.text-3.12.1.dist-info/RECORD,, -jaraco.text-3.12.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -jaraco.text-3.12.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92 -jaraco.text-3.12.1.dist-info/top_level.txt,sha256=0JnN3LfXH4LIRfXL-QFOGCJzQWZO3ELx4R1d_louoQM,7 -jaraco/text/Lorem ipsum.txt,sha256=N_7c_79zxOufBY9HZ3yzMgOkNv-TkOTTio4BydrSjgs,1335 -jaraco/text/__init__.py,sha256=Y2YUqXR_orUoDaY4SkPRe6ZZhb5HUHB_Ah9RCNsVyho,16250 -jaraco/text/__pycache__/__init__.cpython-312.pyc,, -jaraco/text/__pycache__/layouts.cpython-312.pyc,, -jaraco/text/__pycache__/show-newlines.cpython-312.pyc,, -jaraco/text/__pycache__/strip-prefix.cpython-312.pyc,, -jaraco/text/__pycache__/to-dvorak.cpython-312.pyc,, -jaraco/text/__pycache__/to-qwerty.cpython-312.pyc,, -jaraco/text/layouts.py,sha256=HTC8aSTLZ7uXipyOXapRMC158juecjK6RVwitfmZ9_w,643 -jaraco/text/show-newlines.py,sha256=WGQa65e8lyhb92LUOLqVn6KaCtoeVgVws6WtSRmLk6w,904 -jaraco/text/strip-prefix.py,sha256=NfVXV8JVNo6nqcuYASfMV7_y4Eo8zMQqlCOGvAnRIVw,412 -jaraco/text/to-dvorak.py,sha256=1SNcbSsvISpXXg-LnybIHHY-RUFOQr36zcHkY1pWFqw,119 -jaraco/text/to-qwerty.py,sha256=s4UMQUnPwFn_dB5uZC27BurHOQcYondBfzIpVL5pEzw,119 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/REQUESTED deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/WHEEL deleted file mode 100644 index bab98d6..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/WHEEL +++ /dev/null @@ -1,5 +0,0 @@ -Wheel-Version: 1.0 -Generator: bdist_wheel (0.43.0) -Root-Is-Purelib: true -Tag: py3-none-any - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/top_level.txt deleted file mode 100644 index f6205a5..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco.text-3.12.1.dist-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -jaraco diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/__pycache__/context.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/__pycache__/context.cpython-312.pyc deleted file mode 100644 index 373142f..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/__pycache__/context.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/__init__.py deleted file mode 100644 index 0d501cf..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/__init__.py +++ /dev/null @@ -1,1091 +0,0 @@ -from __future__ import annotations - -import collections.abc -import copy -import functools -import itertools -import operator -import random -import re -from collections.abc import Container, Iterable, Mapping -from typing import TYPE_CHECKING, Any, Callable, Dict, TypeVar, Union, overload - -import jaraco.text - -if TYPE_CHECKING: - from _operator import _SupportsComparison - - from _typeshed import SupportsKeysAndGetItem - from typing_extensions import Self - - _RangeMapKT = TypeVar('_RangeMapKT', bound=_SupportsComparison) -else: - # _SupportsComparison doesn't exist at runtime, - # but _RangeMapKT is used in RangeMap's superclass' type parameters - _RangeMapKT = TypeVar('_RangeMapKT') - -_T = TypeVar('_T') -_VT = TypeVar('_VT') - -_Matchable = Union[Callable, Container, Iterable, re.Pattern] - - -def _dispatch(obj: _Matchable) -> Callable: - # can't rely on singledispatch for Union[Container, Iterable] - # due to ambiguity - # (https://peps.python.org/pep-0443/#abstract-base-classes). - if isinstance(obj, re.Pattern): - return obj.fullmatch - # mypy issue: https://github.com/python/mypy/issues/11071 - if not isinstance(obj, Callable): # type: ignore[arg-type] - if not isinstance(obj, Container): - obj = set(obj) # type: ignore[arg-type] - obj = obj.__contains__ - return obj # type: ignore[return-value] - - -class Projection(collections.abc.Mapping): - """ - Project a set of keys over a mapping - - >>> sample = {'a': 1, 'b': 2, 'c': 3} - >>> prj = Projection(['a', 'c', 'd'], sample) - >>> dict(prj) - {'a': 1, 'c': 3} - - Projection also accepts an iterable or callable or pattern. - - >>> iter_prj = Projection(iter('acd'), sample) - >>> call_prj = Projection(lambda k: ord(k) in (97, 99, 100), sample) - >>> pat_prj = Projection(re.compile(r'[acd]'), sample) - >>> prj == iter_prj == call_prj == pat_prj - True - - Keys should only appear if they were specified and exist in the space. - Order is retained. - - >>> list(prj) - ['a', 'c'] - - Attempting to access a key not in the projection - results in a KeyError. - - >>> prj['b'] - Traceback (most recent call last): - ... - KeyError: 'b' - - Use the projection to update another dict. - - >>> target = {'a': 2, 'b': 2} - >>> target.update(prj) - >>> target - {'a': 1, 'b': 2, 'c': 3} - - Projection keeps a reference to the original dict, so - modifying the original dict may modify the Projection. - - >>> del sample['a'] - >>> dict(prj) - {'c': 3} - """ - - def __init__(self, keys: _Matchable, space: Mapping): - self._match = _dispatch(keys) - self._space = space - - def __getitem__(self, key): - if not self._match(key): - raise KeyError(key) - return self._space[key] - - def _keys_resolved(self): - return filter(self._match, self._space) - - def __iter__(self): - return self._keys_resolved() - - def __len__(self): - return len(tuple(self._keys_resolved())) - - -class Mask(Projection): - """ - The inverse of a :class:`Projection`, masking out keys. - - >>> sample = {'a': 1, 'b': 2, 'c': 3} - >>> msk = Mask(['a', 'c', 'd'], sample) - >>> dict(msk) - {'b': 2} - """ - - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) - # self._match = compose(operator.not_, self._match) - self._match = lambda key, orig=self._match: not orig(key) - - -def dict_map(function, dictionary): - """ - Return a new dict with function applied to values of dictionary. - - >>> dict_map(lambda x: x+1, dict(a=1, b=2)) - {'a': 2, 'b': 3} - """ - return dict((key, function(value)) for key, value in dictionary.items()) - - -class RangeMap(Dict[_RangeMapKT, _VT]): - """ - A dictionary-like object that uses the keys as bounds for a range. - Inclusion of the value for that range is determined by the - key_match_comparator, which defaults to less-than-or-equal. - A value is returned for a key if it is the first key that matches in - the sorted list of keys. - - One may supply keyword parameters to be passed to the sort function used - to sort keys (i.e. key, reverse) as sort_params. - - Create a map that maps 1-3 -> 'a', 4-6 -> 'b' - - >>> r = RangeMap({3: 'a', 6: 'b'}) # boy, that was easy - >>> r[1], r[2], r[3], r[4], r[5], r[6] - ('a', 'a', 'a', 'b', 'b', 'b') - - Even float values should work so long as the comparison operator - supports it. - - >>> r[4.5] - 'b' - - Notice that the way rangemap is defined, it must be open-ended - on one side. - - >>> r[0] - 'a' - >>> r[-1] - 'a' - - One can close the open-end of the RangeMap by using undefined_value - - >>> r = RangeMap({0: RangeMap.undefined_value, 3: 'a', 6: 'b'}) - >>> r[0] - Traceback (most recent call last): - ... - KeyError: 0 - - One can get the first or last elements in the range by using RangeMap.Item - - >>> last_item = RangeMap.Item(-1) - >>> r[last_item] - 'b' - - .last_item is a shortcut for Item(-1) - - >>> r[RangeMap.last_item] - 'b' - - Sometimes it's useful to find the bounds for a RangeMap - - >>> r.bounds() - (0, 6) - - RangeMap supports .get(key, default) - - >>> r.get(0, 'not found') - 'not found' - - >>> r.get(7, 'not found') - 'not found' - - One often wishes to define the ranges by their left-most values, - which requires use of sort params and a key_match_comparator. - - >>> r = RangeMap({1: 'a', 4: 'b'}, - ... sort_params=dict(reverse=True), - ... key_match_comparator=operator.ge) - >>> r[1], r[2], r[3], r[4], r[5], r[6] - ('a', 'a', 'a', 'b', 'b', 'b') - - That wasn't nearly as easy as before, so an alternate constructor - is provided: - - >>> r = RangeMap.left({1: 'a', 4: 'b', 7: RangeMap.undefined_value}) - >>> r[1], r[2], r[3], r[4], r[5], r[6] - ('a', 'a', 'a', 'b', 'b', 'b') - - """ - - def __init__( - self, - source: ( - SupportsKeysAndGetItem[_RangeMapKT, _VT] | Iterable[tuple[_RangeMapKT, _VT]] - ), - sort_params: Mapping[str, Any] = {}, - key_match_comparator: Callable[[_RangeMapKT, _RangeMapKT], bool] = operator.le, - ): - dict.__init__(self, source) - self.sort_params = sort_params - self.match = key_match_comparator - - @classmethod - def left( - cls, - source: ( - SupportsKeysAndGetItem[_RangeMapKT, _VT] | Iterable[tuple[_RangeMapKT, _VT]] - ), - ) -> Self: - return cls( - source, sort_params=dict(reverse=True), key_match_comparator=operator.ge - ) - - def __getitem__(self, item: _RangeMapKT) -> _VT: - sorted_keys = sorted(self.keys(), **self.sort_params) - if isinstance(item, RangeMap.Item): - result = self.__getitem__(sorted_keys[item]) - else: - key = self._find_first_match_(sorted_keys, item) - result = dict.__getitem__(self, key) - if result is RangeMap.undefined_value: - raise KeyError(key) - return result - - @overload # type: ignore[override] # Signature simplified over dict and Mapping - def get(self, key: _RangeMapKT, default: _T) -> _VT | _T: ... - @overload - def get(self, key: _RangeMapKT, default: None = None) -> _VT | None: ... - def get(self, key: _RangeMapKT, default: _T | None = None) -> _VT | _T | None: - """ - Return the value for key if key is in the dictionary, else default. - If default is not given, it defaults to None, so that this method - never raises a KeyError. - """ - try: - return self[key] - except KeyError: - return default - - def _find_first_match_( - self, keys: Iterable[_RangeMapKT], item: _RangeMapKT - ) -> _RangeMapKT: - is_match = functools.partial(self.match, item) - matches = filter(is_match, keys) - try: - return next(matches) - except StopIteration: - raise KeyError(item) from None - - def bounds(self) -> tuple[_RangeMapKT, _RangeMapKT]: - sorted_keys = sorted(self.keys(), **self.sort_params) - return (sorted_keys[RangeMap.first_item], sorted_keys[RangeMap.last_item]) - - # some special values for the RangeMap - undefined_value = type('RangeValueUndefined', (), {})() - - class Item(int): - """RangeMap Item""" - - first_item = Item(0) - last_item = Item(-1) - - -def __identity(x): - return x - - -def sorted_items(d, key=__identity, reverse=False): - """ - Return the items of the dictionary sorted by the keys. - - >>> sample = dict(foo=20, bar=42, baz=10) - >>> tuple(sorted_items(sample)) - (('bar', 42), ('baz', 10), ('foo', 20)) - - >>> reverse_string = lambda s: ''.join(reversed(s)) - >>> tuple(sorted_items(sample, key=reverse_string)) - (('foo', 20), ('bar', 42), ('baz', 10)) - - >>> tuple(sorted_items(sample, reverse=True)) - (('foo', 20), ('baz', 10), ('bar', 42)) - """ - - # wrap the key func so it operates on the first element of each item - def pairkey_key(item): - return key(item[0]) - - return sorted(d.items(), key=pairkey_key, reverse=reverse) - - -class KeyTransformingDict(dict): - """ - A dict subclass that transforms the keys before they're used. - Subclasses may override the default transform_key to customize behavior. - """ - - @staticmethod - def transform_key(key): # pragma: nocover - return key - - def __init__(self, *args, **kargs): - super().__init__() - # build a dictionary using the default constructs - d = dict(*args, **kargs) - # build this dictionary using transformed keys. - for item in d.items(): - self.__setitem__(*item) - - def __setitem__(self, key, val): - key = self.transform_key(key) - super().__setitem__(key, val) - - def __getitem__(self, key): - key = self.transform_key(key) - return super().__getitem__(key) - - def __contains__(self, key): - key = self.transform_key(key) - return super().__contains__(key) - - def __delitem__(self, key): - key = self.transform_key(key) - return super().__delitem__(key) - - def get(self, key, *args, **kwargs): - key = self.transform_key(key) - return super().get(key, *args, **kwargs) - - def setdefault(self, key, *args, **kwargs): - key = self.transform_key(key) - return super().setdefault(key, *args, **kwargs) - - def pop(self, key, *args, **kwargs): - key = self.transform_key(key) - return super().pop(key, *args, **kwargs) - - def matching_key_for(self, key): - """ - Given a key, return the actual key stored in self that matches. - Raise KeyError if the key isn't found. - """ - try: - return next(e_key for e_key in self.keys() if e_key == key) - except StopIteration as err: - raise KeyError(key) from err - - -class FoldedCaseKeyedDict(KeyTransformingDict): - """ - A case-insensitive dictionary (keys are compared as insensitive - if they are strings). - - >>> d = FoldedCaseKeyedDict() - >>> d['heLlo'] = 'world' - >>> list(d.keys()) == ['heLlo'] - True - >>> list(d.values()) == ['world'] - True - >>> d['hello'] == 'world' - True - >>> 'hello' in d - True - >>> 'HELLO' in d - True - >>> print(repr(FoldedCaseKeyedDict({'heLlo': 'world'}))) - {'heLlo': 'world'} - >>> d = FoldedCaseKeyedDict({'heLlo': 'world'}) - >>> print(d['hello']) - world - >>> print(d['Hello']) - world - >>> list(d.keys()) - ['heLlo'] - >>> d = FoldedCaseKeyedDict({'heLlo': 'world', 'Hello': 'world'}) - >>> list(d.values()) - ['world'] - >>> key, = d.keys() - >>> key in ['heLlo', 'Hello'] - True - >>> del d['HELLO'] - >>> d - {} - - get should work - - >>> d['Sumthin'] = 'else' - >>> d.get('SUMTHIN') - 'else' - >>> d.get('OTHER', 'thing') - 'thing' - >>> del d['sumthin'] - - setdefault should also work - - >>> d['This'] = 'that' - >>> print(d.setdefault('this', 'other')) - that - >>> len(d) - 1 - >>> print(d['this']) - that - >>> print(d.setdefault('That', 'other')) - other - >>> print(d['THAT']) - other - - Make it pop! - - >>> print(d.pop('THAT')) - other - - To retrieve the key in its originally-supplied form, use matching_key_for - - >>> print(d.matching_key_for('this')) - This - - >>> d.matching_key_for('missing') - Traceback (most recent call last): - ... - KeyError: 'missing' - """ - - @staticmethod - def transform_key(key): - return jaraco.text.FoldedCase(key) - - -class DictAdapter: - """ - Provide a getitem interface for attributes of an object. - - Let's say you want to get at the string.lowercase property in a formatted - string. It's easy with DictAdapter. - - >>> import string - >>> print("lowercase is %(ascii_lowercase)s" % DictAdapter(string)) - lowercase is abcdefghijklmnopqrstuvwxyz - """ - - def __init__(self, wrapped_ob): - self.object = wrapped_ob - - def __getitem__(self, name): - return getattr(self.object, name) - - -class ItemsAsAttributes: - """ - Mix-in class to enable a mapping object to provide items as - attributes. - - >>> C = type('C', (dict, ItemsAsAttributes), dict()) - >>> i = C() - >>> i['foo'] = 'bar' - >>> i.foo - 'bar' - - Natural attribute access takes precedence - - >>> i.foo = 'henry' - >>> i.foo - 'henry' - - But as you might expect, the mapping functionality is preserved. - - >>> i['foo'] - 'bar' - - A normal attribute error should be raised if an attribute is - requested that doesn't exist. - - >>> i.missing - Traceback (most recent call last): - ... - AttributeError: 'C' object has no attribute 'missing' - - It also works on dicts that customize __getitem__ - - >>> missing_func = lambda self, key: 'missing item' - >>> C = type( - ... 'C', - ... (dict, ItemsAsAttributes), - ... dict(__missing__ = missing_func), - ... ) - >>> i = C() - >>> i.missing - 'missing item' - >>> i.foo - 'missing item' - """ - - def __getattr__(self, key): - try: - return getattr(super(), key) - except AttributeError as e: - # attempt to get the value from the mapping (return self[key]) - # but be careful not to lose the original exception context. - noval = object() - - def _safe_getitem(cont, key, missing_result): - try: - return cont[key] - except KeyError: - return missing_result - - result = _safe_getitem(self, key, noval) - if result is not noval: - return result - # raise the original exception, but use the original class - # name, not 'super'. - (message,) = e.args - message = message.replace('super', self.__class__.__name__, 1) - e.args = (message,) - raise - - -def invert_map(map): - """ - Given a dictionary, return another dictionary with keys and values - switched. If any of the values resolve to the same key, raises - a ValueError. - - >>> numbers = dict(a=1, b=2, c=3) - >>> letters = invert_map(numbers) - >>> letters[1] - 'a' - >>> numbers['d'] = 3 - >>> invert_map(numbers) - Traceback (most recent call last): - ... - ValueError: Key conflict in inverted mapping - """ - res = dict((v, k) for k, v in map.items()) - if not len(res) == len(map): - raise ValueError('Key conflict in inverted mapping') - return res - - -class IdentityOverrideMap(dict): - """ - A dictionary that by default maps each key to itself, but otherwise - acts like a normal dictionary. - - >>> d = IdentityOverrideMap() - >>> d[42] - 42 - >>> d['speed'] = 'speedo' - >>> print(d['speed']) - speedo - """ - - def __missing__(self, key): - return key - - -class DictStack(list, collections.abc.MutableMapping): - """ - A stack of dictionaries that behaves as a view on those dictionaries, - giving preference to the last. - - >>> stack = DictStack([dict(a=1, c=2), dict(b=2, a=2)]) - >>> stack['a'] - 2 - >>> stack['b'] - 2 - >>> stack['c'] - 2 - >>> len(stack) - 3 - >>> stack.push(dict(a=3)) - >>> stack['a'] - 3 - >>> stack['a'] = 4 - >>> set(stack.keys()) == set(['a', 'b', 'c']) - True - >>> set(stack.items()) == set([('a', 4), ('b', 2), ('c', 2)]) - True - >>> dict(**stack) == dict(stack) == dict(a=4, c=2, b=2) - True - >>> d = stack.pop() - >>> stack['a'] - 2 - >>> d = stack.pop() - >>> stack['a'] - 1 - >>> stack.get('b', None) - >>> 'c' in stack - True - >>> del stack['c'] - >>> dict(stack) - {'a': 1} - """ - - def __iter__(self): - dicts = list.__iter__(self) - return iter(set(itertools.chain.from_iterable(c.keys() for c in dicts))) - - def __getitem__(self, key): - for scope in reversed(tuple(list.__iter__(self))): - if key in scope: - return scope[key] - raise KeyError(key) - - push = list.append - - def __contains__(self, other): - return collections.abc.Mapping.__contains__(self, other) - - def __len__(self): - return len(list(iter(self))) - - def __setitem__(self, key, item): - last = list.__getitem__(self, -1) - return last.__setitem__(key, item) - - def __delitem__(self, key): - last = list.__getitem__(self, -1) - return last.__delitem__(key) - - # workaround for mypy confusion - def pop(self, *args, **kwargs): - return list.pop(self, *args, **kwargs) - - -class BijectiveMap(dict): - """ - A Bijective Map (two-way mapping). - - Implemented as a simple dictionary of 2x the size, mapping values back - to keys. - - Note, this implementation may be incomplete. If there's not a test for - your use case below, it's likely to fail, so please test and send pull - requests or patches for additional functionality needed. - - - >>> m = BijectiveMap() - >>> m['a'] = 'b' - >>> m == {'a': 'b', 'b': 'a'} - True - >>> print(m['b']) - a - - >>> m['c'] = 'd' - >>> len(m) - 2 - - Some weird things happen if you map an item to itself or overwrite a - single key of a pair, so it's disallowed. - - >>> m['e'] = 'e' - Traceback (most recent call last): - ValueError: Key cannot map to itself - - >>> m['d'] = 'e' - Traceback (most recent call last): - ValueError: Key/Value pairs may not overlap - - >>> m['e'] = 'd' - Traceback (most recent call last): - ValueError: Key/Value pairs may not overlap - - >>> print(m.pop('d')) - c - - >>> 'c' in m - False - - >>> m = BijectiveMap(dict(a='b')) - >>> len(m) - 1 - >>> print(m['b']) - a - - >>> m = BijectiveMap() - >>> m.update(a='b') - >>> m['b'] - 'a' - - >>> del m['b'] - >>> len(m) - 0 - >>> 'a' in m - False - """ - - def __init__(self, *args, **kwargs): - super().__init__() - self.update(*args, **kwargs) - - def __setitem__(self, item, value): - if item == value: - raise ValueError("Key cannot map to itself") - overlap = ( - item in self - and self[item] != value - or value in self - and self[value] != item - ) - if overlap: - raise ValueError("Key/Value pairs may not overlap") - super().__setitem__(item, value) - super().__setitem__(value, item) - - def __delitem__(self, item): - self.pop(item) - - def __len__(self): - return super().__len__() // 2 - - def pop(self, key, *args, **kwargs): - mirror = self[key] - super().__delitem__(mirror) - return super().pop(key, *args, **kwargs) - - def update(self, *args, **kwargs): - # build a dictionary using the default constructs - d = dict(*args, **kwargs) - # build this dictionary using transformed keys. - for item in d.items(): - self.__setitem__(*item) - - -class FrozenDict(collections.abc.Mapping, collections.abc.Hashable): - """ - An immutable mapping. - - >>> a = FrozenDict(a=1, b=2) - >>> b = FrozenDict(a=1, b=2) - >>> a == b - True - - >>> a == dict(a=1, b=2) - True - >>> dict(a=1, b=2) == a - True - >>> 'a' in a - True - >>> type(hash(a)) is type(0) - True - >>> set(iter(a)) == {'a', 'b'} - True - >>> len(a) - 2 - >>> a['a'] == a.get('a') == 1 - True - - >>> a['c'] = 3 - Traceback (most recent call last): - ... - TypeError: 'FrozenDict' object does not support item assignment - - >>> a.update(y=3) - Traceback (most recent call last): - ... - AttributeError: 'FrozenDict' object has no attribute 'update' - - Copies should compare equal - - >>> copy.copy(a) == a - True - - Copies should be the same type - - >>> isinstance(copy.copy(a), FrozenDict) - True - - FrozenDict supplies .copy(), even though - collections.abc.Mapping doesn't demand it. - - >>> a.copy() == a - True - >>> a.copy() is not a - True - """ - - __slots__ = ['__data'] - - def __new__(cls, *args, **kwargs): - self = super().__new__(cls) - self.__data = dict(*args, **kwargs) - return self - - # Container - def __contains__(self, key): - return key in self.__data - - # Hashable - def __hash__(self): - return hash(tuple(sorted(self.__data.items()))) - - # Mapping - def __iter__(self): - return iter(self.__data) - - def __len__(self): - return len(self.__data) - - def __getitem__(self, key): - return self.__data[key] - - # override get for efficiency provided by dict - def get(self, *args, **kwargs): - return self.__data.get(*args, **kwargs) - - # override eq to recognize underlying implementation - def __eq__(self, other): - if isinstance(other, FrozenDict): - other = other.__data - return self.__data.__eq__(other) - - def copy(self): - "Return a shallow copy of self" - return copy.copy(self) - - -class Enumeration(ItemsAsAttributes, BijectiveMap): - """ - A convenient way to provide enumerated values - - >>> e = Enumeration('a b c') - >>> e['a'] - 0 - - >>> e.a - 0 - - >>> e[1] - 'b' - - >>> set(e.names) == set('abc') - True - - >>> set(e.codes) == set(range(3)) - True - - >>> e.get('d') is None - True - - Codes need not start with 0 - - >>> e = Enumeration('a b c', range(1, 4)) - >>> e['a'] - 1 - - >>> e[3] - 'c' - """ - - def __init__(self, names, codes=None): - if isinstance(names, str): - names = names.split() - if codes is None: - codes = itertools.count() - super().__init__(zip(names, codes)) - - @property - def names(self): - return (key for key in self if isinstance(key, str)) - - @property - def codes(self): - return (self[name] for name in self.names) - - -class Everything: - """ - A collection "containing" every possible thing. - - >>> 'foo' in Everything() - True - - >>> import random - >>> random.randint(1, 999) in Everything() - True - - >>> random.choice([None, 'foo', 42, ('a', 'b', 'c')]) in Everything() - True - """ - - def __contains__(self, other): - return True - - -class InstrumentedDict(collections.UserDict): - """ - Instrument an existing dictionary with additional - functionality, but always reference and mutate - the original dictionary. - - >>> orig = {'a': 1, 'b': 2} - >>> inst = InstrumentedDict(orig) - >>> inst['a'] - 1 - >>> inst['c'] = 3 - >>> orig['c'] - 3 - >>> inst.keys() == orig.keys() - True - """ - - def __init__(self, data): - super().__init__() - self.data = data - - -class Least: - """ - A value that is always lesser than any other - - >>> least = Least() - >>> 3 < least - False - >>> 3 > least - True - >>> least < 3 - True - >>> least <= 3 - True - >>> least > 3 - False - >>> 'x' > least - True - >>> None > least - True - """ - - def __le__(self, other): - return True - - __lt__ = __le__ - - def __ge__(self, other): - return False - - __gt__ = __ge__ - - -class Greatest: - """ - A value that is always greater than any other - - >>> greatest = Greatest() - >>> 3 < greatest - True - >>> 3 > greatest - False - >>> greatest < 3 - False - >>> greatest > 3 - True - >>> greatest >= 3 - True - >>> 'x' > greatest - False - >>> None > greatest - False - """ - - def __ge__(self, other): - return True - - __gt__ = __ge__ - - def __le__(self, other): - return False - - __lt__ = __le__ - - -def pop_all(items): - """ - Clear items in place and return a copy of items. - - >>> items = [1, 2, 3] - >>> popped = pop_all(items) - >>> popped is items - False - >>> popped - [1, 2, 3] - >>> items - [] - """ - result, items[:] = items[:], [] - return result - - -class FreezableDefaultDict(collections.defaultdict): - """ - Often it is desirable to prevent the mutation of - a default dict after its initial construction, such - as to prevent mutation during iteration. - - >>> dd = FreezableDefaultDict(list) - >>> dd[0].append('1') - >>> dd.freeze() - >>> dd[1] - [] - >>> len(dd) - 1 - """ - - def __missing__(self, key): - return getattr(self, '_frozen', super().__missing__)(key) - - def freeze(self): - self._frozen = lambda key: self.default_factory() - - -class Accumulator: - def __init__(self, initial=0): - self.val = initial - - def __call__(self, val): - self.val += val - return self.val - - -class WeightedLookup(RangeMap): - """ - Given parameters suitable for a dict representing keys - and a weighted proportion, return a RangeMap representing - spans of values proportial to the weights: - - >>> even = WeightedLookup(a=1, b=1) - - [0, 1) -> a - [1, 2) -> b - - >>> lk = WeightedLookup(a=1, b=2) - - [0, 1) -> a - [1, 3) -> b - - >>> lk[.5] - 'a' - >>> lk[1.5] - 'b' - - Adds ``.random()`` to select a random weighted value: - - >>> lk.random() in ['a', 'b'] - True - - >>> choices = [lk.random() for x in range(1000)] - - Statistically speaking, choices should be .5 a:b - >>> ratio = choices.count('a') / choices.count('b') - >>> .4 < ratio < .6 - True - """ - - def __init__(self, *args, **kwargs): - raw = dict(*args, **kwargs) - - # allocate keys by weight - indexes = map(Accumulator(), raw.values()) - super().__init__(zip(indexes, raw.keys()), key_match_comparator=operator.lt) - - def random(self): - lower, upper = self.bounds() - selector = random.random() * upper - return self[selector] diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 5dfbf64..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/collections/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/context.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/context.py deleted file mode 100644 index 61b2713..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/context.py +++ /dev/null @@ -1,361 +0,0 @@ -from __future__ import annotations - -import contextlib -import functools -import operator -import os -import shutil -import subprocess -import sys -import tempfile -import urllib.request -import warnings -from typing import Iterator - - -if sys.version_info < (3, 12): - from backports import tarfile -else: - import tarfile - - -@contextlib.contextmanager -def pushd(dir: str | os.PathLike) -> Iterator[str | os.PathLike]: - """ - >>> tmp_path = getfixture('tmp_path') - >>> with pushd(tmp_path): - ... assert os.getcwd() == os.fspath(tmp_path) - >>> assert os.getcwd() != os.fspath(tmp_path) - """ - - orig = os.getcwd() - os.chdir(dir) - try: - yield dir - finally: - os.chdir(orig) - - -@contextlib.contextmanager -def tarball( - url, target_dir: str | os.PathLike | None = None -) -> Iterator[str | os.PathLike]: - """ - Get a tarball, extract it, yield, then clean up. - - >>> import urllib.request - >>> url = getfixture('tarfile_served') - >>> target = getfixture('tmp_path') / 'out' - >>> tb = tarball(url, target_dir=target) - >>> import pathlib - >>> with tb as extracted: - ... contents = pathlib.Path(extracted, 'contents.txt').read_text(encoding='utf-8') - >>> assert not os.path.exists(extracted) - """ - if target_dir is None: - target_dir = os.path.basename(url).replace('.tar.gz', '').replace('.tgz', '') - # In the tar command, use --strip-components=1 to strip the first path and - # then - # use -C to cause the files to be extracted to {target_dir}. This ensures - # that we always know where the files were extracted. - os.mkdir(target_dir) - try: - req = urllib.request.urlopen(url) - with tarfile.open(fileobj=req, mode='r|*') as tf: - tf.extractall(path=target_dir, filter=strip_first_component) - yield target_dir - finally: - shutil.rmtree(target_dir) - - -def strip_first_component( - member: tarfile.TarInfo, - path, -) -> tarfile.TarInfo: - _, member.name = member.name.split('/', 1) - return member - - -def _compose(*cmgrs): - """ - Compose any number of dependent context managers into a single one. - - The last, innermost context manager may take arbitrary arguments, but - each successive context manager should accept the result from the - previous as a single parameter. - - Like :func:`jaraco.functools.compose`, behavior works from right to - left, so the context manager should be indicated from outermost to - innermost. - - Example, to create a context manager to change to a temporary - directory: - - >>> temp_dir_as_cwd = _compose(pushd, temp_dir) - >>> with temp_dir_as_cwd() as dir: - ... assert os.path.samefile(os.getcwd(), dir) - """ - - def compose_two(inner, outer): - def composed(*args, **kwargs): - with inner(*args, **kwargs) as saved, outer(saved) as res: - yield res - - return contextlib.contextmanager(composed) - - return functools.reduce(compose_two, reversed(cmgrs)) - - -tarball_cwd = _compose(pushd, tarball) - - -@contextlib.contextmanager -def tarball_context(*args, **kwargs): - warnings.warn( - "tarball_context is deprecated. Use tarball or tarball_cwd instead.", - DeprecationWarning, - stacklevel=2, - ) - pushd_ctx = kwargs.pop('pushd', pushd) - with tarball(*args, **kwargs) as tball, pushd_ctx(tball) as dir: - yield dir - - -def infer_compression(url): - """ - Given a URL or filename, infer the compression code for tar. - - >>> infer_compression('http://foo/bar.tar.gz') - 'z' - >>> infer_compression('http://foo/bar.tgz') - 'z' - >>> infer_compression('file.bz') - 'j' - >>> infer_compression('file.xz') - 'J' - """ - warnings.warn( - "infer_compression is deprecated with no replacement", - DeprecationWarning, - stacklevel=2, - ) - # cheat and just assume it's the last two characters - compression_indicator = url[-2:] - mapping = dict(gz='z', bz='j', xz='J') - # Assume 'z' (gzip) if no match - return mapping.get(compression_indicator, 'z') - - -@contextlib.contextmanager -def temp_dir(remover=shutil.rmtree): - """ - Create a temporary directory context. Pass a custom remover - to override the removal behavior. - - >>> import pathlib - >>> with temp_dir() as the_dir: - ... assert os.path.isdir(the_dir) - ... _ = pathlib.Path(the_dir).joinpath('somefile').write_text('contents', encoding='utf-8') - >>> assert not os.path.exists(the_dir) - """ - temp_dir = tempfile.mkdtemp() - try: - yield temp_dir - finally: - remover(temp_dir) - - -@contextlib.contextmanager -def repo_context(url, branch=None, quiet=True, dest_ctx=temp_dir): - """ - Check out the repo indicated by url. - - If dest_ctx is supplied, it should be a context manager - to yield the target directory for the check out. - """ - exe = 'git' if 'git' in url else 'hg' - with dest_ctx() as repo_dir: - cmd = [exe, 'clone', url, repo_dir] - if branch: - cmd.extend(['--branch', branch]) - devnull = open(os.path.devnull, 'w') - stdout = devnull if quiet else None - subprocess.check_call(cmd, stdout=stdout) - yield repo_dir - - -def null(): - """ - A null context suitable to stand in for a meaningful context. - - >>> with null() as value: - ... assert value is None - - This context is most useful when dealing with two or more code - branches but only some need a context. Wrap the others in a null - context to provide symmetry across all options. - """ - warnings.warn( - "null is deprecated. Use contextlib.nullcontext", - DeprecationWarning, - stacklevel=2, - ) - return contextlib.nullcontext() - - -class ExceptionTrap: - """ - A context manager that will catch certain exceptions and provide an - indication they occurred. - - >>> with ExceptionTrap() as trap: - ... raise Exception() - >>> bool(trap) - True - - >>> with ExceptionTrap() as trap: - ... pass - >>> bool(trap) - False - - >>> with ExceptionTrap(ValueError) as trap: - ... raise ValueError("1 + 1 is not 3") - >>> bool(trap) - True - >>> trap.value - ValueError('1 + 1 is not 3') - >>> trap.tb - - - >>> with ExceptionTrap(ValueError) as trap: - ... raise Exception() - Traceback (most recent call last): - ... - Exception - - >>> bool(trap) - False - """ - - exc_info = None, None, None - - def __init__(self, exceptions=(Exception,)): - self.exceptions = exceptions - - def __enter__(self): - return self - - @property - def type(self): - return self.exc_info[0] - - @property - def value(self): - return self.exc_info[1] - - @property - def tb(self): - return self.exc_info[2] - - def __exit__(self, *exc_info): - type = exc_info[0] - matches = type and issubclass(type, self.exceptions) - if matches: - self.exc_info = exc_info - return matches - - def __bool__(self): - return bool(self.type) - - def raises(self, func, *, _test=bool): - """ - Wrap func and replace the result with the truth - value of the trap (True if an exception occurred). - - First, give the decorator an alias to support Python 3.8 - Syntax. - - >>> raises = ExceptionTrap(ValueError).raises - - Now decorate a function that always fails. - - >>> @raises - ... def fail(): - ... raise ValueError('failed') - >>> fail() - True - """ - - @functools.wraps(func) - def wrapper(*args, **kwargs): - with ExceptionTrap(self.exceptions) as trap: - func(*args, **kwargs) - return _test(trap) - - return wrapper - - def passes(self, func): - """ - Wrap func and replace the result with the truth - value of the trap (True if no exception). - - First, give the decorator an alias to support Python 3.8 - Syntax. - - >>> passes = ExceptionTrap(ValueError).passes - - Now decorate a function that always fails. - - >>> @passes - ... def fail(): - ... raise ValueError('failed') - - >>> fail() - False - """ - return self.raises(func, _test=operator.not_) - - -class suppress(contextlib.suppress, contextlib.ContextDecorator): - """ - A version of contextlib.suppress with decorator support. - - >>> @suppress(KeyError) - ... def key_error(): - ... {}[''] - >>> key_error() - """ - - -class on_interrupt(contextlib.ContextDecorator): - """ - Replace a KeyboardInterrupt with SystemExit(1) - - >>> def do_interrupt(): - ... raise KeyboardInterrupt() - >>> on_interrupt('error')(do_interrupt)() - Traceback (most recent call last): - ... - SystemExit: 1 - >>> on_interrupt('error', code=255)(do_interrupt)() - Traceback (most recent call last): - ... - SystemExit: 255 - >>> on_interrupt('suppress')(do_interrupt)() - >>> with __import__('pytest').raises(KeyboardInterrupt): - ... on_interrupt('ignore')(do_interrupt)() - """ - - def __init__(self, action='error', /, code=1): - self.action = action - self.code = code - - def __enter__(self): - return self - - def __exit__(self, exctype, excinst, exctb): - if exctype is not KeyboardInterrupt or self.action == 'ignore': - return - elif self.action == 'error': - raise SystemExit(self.code) from excinst - return self.action == 'suppress' diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__init__.py deleted file mode 100644 index ca6c22f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__init__.py +++ /dev/null @@ -1,633 +0,0 @@ -import collections.abc -import functools -import inspect -import itertools -import operator -import time -import types -import warnings - -import more_itertools - - -def compose(*funcs): - """ - Compose any number of unary functions into a single unary function. - - >>> import textwrap - >>> expected = str.strip(textwrap.dedent(compose.__doc__)) - >>> strip_and_dedent = compose(str.strip, textwrap.dedent) - >>> strip_and_dedent(compose.__doc__) == expected - True - - Compose also allows the innermost function to take arbitrary arguments. - - >>> round_three = lambda x: round(x, ndigits=3) - >>> f = compose(round_three, int.__truediv__) - >>> [f(3*x, x+1) for x in range(1,10)] - [1.5, 2.0, 2.25, 2.4, 2.5, 2.571, 2.625, 2.667, 2.7] - """ - - def compose_two(f1, f2): - return lambda *args, **kwargs: f1(f2(*args, **kwargs)) - - return functools.reduce(compose_two, funcs) - - -def once(func): - """ - Decorate func so it's only ever called the first time. - - This decorator can ensure that an expensive or non-idempotent function - will not be expensive on subsequent calls and is idempotent. - - >>> add_three = once(lambda a: a+3) - >>> add_three(3) - 6 - >>> add_three(9) - 6 - >>> add_three('12') - 6 - - To reset the stored value, simply clear the property ``saved_result``. - - >>> del add_three.saved_result - >>> add_three(9) - 12 - >>> add_three(8) - 12 - - Or invoke 'reset()' on it. - - >>> add_three.reset() - >>> add_three(-3) - 0 - >>> add_three(0) - 0 - """ - - @functools.wraps(func) - def wrapper(*args, **kwargs): - if not hasattr(wrapper, 'saved_result'): - wrapper.saved_result = func(*args, **kwargs) - return wrapper.saved_result - - wrapper.reset = lambda: vars(wrapper).__delitem__('saved_result') - return wrapper - - -def method_cache(method, cache_wrapper=functools.lru_cache()): - """ - Wrap lru_cache to support storing the cache data in the object instances. - - Abstracts the common paradigm where the method explicitly saves an - underscore-prefixed protected property on first call and returns that - subsequently. - - >>> class MyClass: - ... calls = 0 - ... - ... @method_cache - ... def method(self, value): - ... self.calls += 1 - ... return value - - >>> a = MyClass() - >>> a.method(3) - 3 - >>> for x in range(75): - ... res = a.method(x) - >>> a.calls - 75 - - Note that the apparent behavior will be exactly like that of lru_cache - except that the cache is stored on each instance, so values in one - instance will not flush values from another, and when an instance is - deleted, so are the cached values for that instance. - - >>> b = MyClass() - >>> for x in range(35): - ... res = b.method(x) - >>> b.calls - 35 - >>> a.method(0) - 0 - >>> a.calls - 75 - - Note that if method had been decorated with ``functools.lru_cache()``, - a.calls would have been 76 (due to the cached value of 0 having been - flushed by the 'b' instance). - - Clear the cache with ``.cache_clear()`` - - >>> a.method.cache_clear() - - Same for a method that hasn't yet been called. - - >>> c = MyClass() - >>> c.method.cache_clear() - - Another cache wrapper may be supplied: - - >>> cache = functools.lru_cache(maxsize=2) - >>> MyClass.method2 = method_cache(lambda self: 3, cache_wrapper=cache) - >>> a = MyClass() - >>> a.method2() - 3 - - Caution - do not subsequently wrap the method with another decorator, such - as ``@property``, which changes the semantics of the function. - - See also - http://code.activestate.com/recipes/577452-a-memoize-decorator-for-instance-methods/ - for another implementation and additional justification. - """ - - def wrapper(self, *args, **kwargs): - # it's the first call, replace the method with a cached, bound method - bound_method = types.MethodType(method, self) - cached_method = cache_wrapper(bound_method) - setattr(self, method.__name__, cached_method) - return cached_method(*args, **kwargs) - - # Support cache clear even before cache has been created. - wrapper.cache_clear = lambda: None - - return _special_method_cache(method, cache_wrapper) or wrapper - - -def _special_method_cache(method, cache_wrapper): - """ - Because Python treats special methods differently, it's not - possible to use instance attributes to implement the cached - methods. - - Instead, install the wrapper method under a different name - and return a simple proxy to that wrapper. - - https://github.com/jaraco/jaraco.functools/issues/5 - """ - name = method.__name__ - special_names = '__getattr__', '__getitem__' - - if name not in special_names: - return None - - wrapper_name = '__cached' + name - - def proxy(self, /, *args, **kwargs): - if wrapper_name not in vars(self): - bound = types.MethodType(method, self) - cache = cache_wrapper(bound) - setattr(self, wrapper_name, cache) - else: - cache = getattr(self, wrapper_name) - return cache(*args, **kwargs) - - return proxy - - -def apply(transform): - """ - Decorate a function with a transform function that is - invoked on results returned from the decorated function. - - >>> @apply(reversed) - ... def get_numbers(start): - ... "doc for get_numbers" - ... return range(start, start+3) - >>> list(get_numbers(4)) - [6, 5, 4] - >>> get_numbers.__doc__ - 'doc for get_numbers' - """ - - def wrap(func): - return functools.wraps(func)(compose(transform, func)) - - return wrap - - -def result_invoke(action): - r""" - Decorate a function with an action function that is - invoked on the results returned from the decorated - function (for its side effect), then return the original - result. - - >>> @result_invoke(print) - ... def add_two(a, b): - ... return a + b - >>> x = add_two(2, 3) - 5 - >>> x - 5 - """ - - def wrap(func): - @functools.wraps(func) - def wrapper(*args, **kwargs): - result = func(*args, **kwargs) - action(result) - return result - - return wrapper - - return wrap - - -def invoke(f, /, *args, **kwargs): - """ - Call a function for its side effect after initialization. - - The benefit of using the decorator instead of simply invoking a function - after defining it is that it makes explicit the author's intent for the - function to be called immediately. Whereas if one simply calls the - function immediately, it's less obvious if that was intentional or - incidental. It also avoids repeating the name - the two actions, defining - the function and calling it immediately are modeled separately, but linked - by the decorator construct. - - The benefit of having a function construct (opposed to just invoking some - behavior inline) is to serve as a scope in which the behavior occurs. It - avoids polluting the global namespace with local variables, provides an - anchor on which to attach documentation (docstring), keeps the behavior - logically separated (instead of conceptually separated or not separated at - all), and provides potential to re-use the behavior for testing or other - purposes. - - This function is named as a pithy way to communicate, "call this function - primarily for its side effect", or "while defining this function, also - take it aside and call it". It exists because there's no Python construct - for "define and call" (nor should there be, as decorators serve this need - just fine). The behavior happens immediately and synchronously. - - >>> @invoke - ... def func(): print("called") - called - >>> func() - called - - Use functools.partial to pass parameters to the initial call - - >>> @functools.partial(invoke, name='bingo') - ... def func(name): print('called with', name) - called with bingo - """ - f(*args, **kwargs) - return f - - -class Throttler: - """Rate-limit a function (or other callable).""" - - def __init__(self, func, max_rate=float('Inf')): - if isinstance(func, Throttler): - func = func.func - self.func = func - self.max_rate = max_rate - self.reset() - - def reset(self): - self.last_called = 0 - - def __call__(self, *args, **kwargs): - self._wait() - return self.func(*args, **kwargs) - - def _wait(self): - """Ensure at least 1/max_rate seconds from last call.""" - elapsed = time.time() - self.last_called - must_wait = 1 / self.max_rate - elapsed - time.sleep(max(0, must_wait)) - self.last_called = time.time() - - def __get__(self, obj, owner=None): - return first_invoke(self._wait, functools.partial(self.func, obj)) - - -def first_invoke(func1, func2): - """ - Return a function that when invoked will invoke func1 without - any parameters (for its side effect) and then invoke func2 - with whatever parameters were passed, returning its result. - """ - - def wrapper(*args, **kwargs): - func1() - return func2(*args, **kwargs) - - return wrapper - - -method_caller = first_invoke( - lambda: warnings.warn( - '`jaraco.functools.method_caller` is deprecated, ' - 'use `operator.methodcaller` instead', - DeprecationWarning, - stacklevel=3, - ), - operator.methodcaller, -) - - -def retry_call(func, cleanup=lambda: None, retries=0, trap=()): - """ - Given a callable func, trap the indicated exceptions - for up to 'retries' times, invoking cleanup on the - exception. On the final attempt, allow any exceptions - to propagate. - """ - attempts = itertools.count() if retries == float('inf') else range(retries) - for _ in attempts: - try: - return func() - except trap: - cleanup() - - return func() - - -def retry(*r_args, **r_kwargs): - """ - Decorator wrapper for retry_call. Accepts arguments to retry_call - except func and then returns a decorator for the decorated function. - - Ex: - - >>> @retry(retries=3) - ... def my_func(a, b): - ... "this is my funk" - ... print(a, b) - >>> my_func.__doc__ - 'this is my funk' - """ - - def decorate(func): - @functools.wraps(func) - def wrapper(*f_args, **f_kwargs): - bound = functools.partial(func, *f_args, **f_kwargs) - return retry_call(bound, *r_args, **r_kwargs) - - return wrapper - - return decorate - - -def print_yielded(func): - """ - Convert a generator into a function that prints all yielded elements. - - >>> @print_yielded - ... def x(): - ... yield 3; yield None - >>> x() - 3 - None - """ - print_all = functools.partial(map, print) - print_results = compose(more_itertools.consume, print_all, func) - return functools.wraps(func)(print_results) - - -def pass_none(func): - """ - Wrap func so it's not called if its first param is None. - - >>> print_text = pass_none(print) - >>> print_text('text') - text - >>> print_text(None) - """ - - @functools.wraps(func) - def wrapper(param, /, *args, **kwargs): - if param is not None: - return func(param, *args, **kwargs) - return None - - return wrapper - - -def assign_params(func, namespace): - """ - Assign parameters from namespace where func solicits. - - >>> def func(x, y=3): - ... print(x, y) - >>> assigned = assign_params(func, dict(x=2, z=4)) - >>> assigned() - 2 3 - - The usual errors are raised if a function doesn't receive - its required parameters: - - >>> assigned = assign_params(func, dict(y=3, z=4)) - >>> assigned() - Traceback (most recent call last): - TypeError: func() ...argument... - - It even works on methods: - - >>> class Handler: - ... def meth(self, arg): - ... print(arg) - >>> assign_params(Handler().meth, dict(arg='crystal', foo='clear'))() - crystal - """ - sig = inspect.signature(func) - params = sig.parameters.keys() - call_ns = {k: namespace[k] for k in params if k in namespace} - return functools.partial(func, **call_ns) - - -def save_method_args(method): - """ - Wrap a method such that when it is called, the args and kwargs are - saved on the method. - - >>> class MyClass: - ... @save_method_args - ... def method(self, a, b): - ... print(a, b) - >>> my_ob = MyClass() - >>> my_ob.method(1, 2) - 1 2 - >>> my_ob._saved_method.args - (1, 2) - >>> my_ob._saved_method.kwargs - {} - >>> my_ob.method(a=3, b='foo') - 3 foo - >>> my_ob._saved_method.args - () - >>> my_ob._saved_method.kwargs == dict(a=3, b='foo') - True - - The arguments are stored on the instance, allowing for - different instance to save different args. - - >>> your_ob = MyClass() - >>> your_ob.method({str('x'): 3}, b=[4]) - {'x': 3} [4] - >>> your_ob._saved_method.args - ({'x': 3},) - >>> my_ob._saved_method.args - () - """ - args_and_kwargs = collections.namedtuple('args_and_kwargs', 'args kwargs') - - @functools.wraps(method) - def wrapper(self, /, *args, **kwargs): - attr_name = '_saved_' + method.__name__ - attr = args_and_kwargs(args, kwargs) - setattr(self, attr_name, attr) - return method(self, *args, **kwargs) - - return wrapper - - -def except_(*exceptions, replace=None, use=None): - """ - Replace the indicated exceptions, if raised, with the indicated - literal replacement or evaluated expression (if present). - - >>> safe_int = except_(ValueError)(int) - >>> safe_int('five') - >>> safe_int('5') - 5 - - Specify a literal replacement with ``replace``. - - >>> safe_int_r = except_(ValueError, replace=0)(int) - >>> safe_int_r('five') - 0 - - Provide an expression to ``use`` to pass through particular parameters. - - >>> safe_int_pt = except_(ValueError, use='args[0]')(int) - >>> safe_int_pt('five') - 'five' - - """ - - def decorate(func): - @functools.wraps(func) - def wrapper(*args, **kwargs): - try: - return func(*args, **kwargs) - except exceptions: - try: - return eval(use) - except TypeError: - return replace - - return wrapper - - return decorate - - -def identity(x): - """ - Return the argument. - - >>> o = object() - >>> identity(o) is o - True - """ - return x - - -def bypass_when(check, *, _op=identity): - """ - Decorate a function to return its parameter when ``check``. - - >>> bypassed = [] # False - - >>> @bypass_when(bypassed) - ... def double(x): - ... return x * 2 - >>> double(2) - 4 - >>> bypassed[:] = [object()] # True - >>> double(2) - 2 - """ - - def decorate(func): - @functools.wraps(func) - def wrapper(param, /): - return param if _op(check) else func(param) - - return wrapper - - return decorate - - -def bypass_unless(check): - """ - Decorate a function to return its parameter unless ``check``. - - >>> enabled = [object()] # True - - >>> @bypass_unless(enabled) - ... def double(x): - ... return x * 2 - >>> double(2) - 4 - >>> del enabled[:] # False - >>> double(2) - 2 - """ - return bypass_when(check, _op=operator.not_) - - -@functools.singledispatch -def _splat_inner(args, func): - """Splat args to func.""" - return func(*args) - - -@_splat_inner.register -def _(args: collections.abc.Mapping, func): - """Splat kargs to func as kwargs.""" - return func(**args) - - -def splat(func): - """ - Wrap func to expect its parameters to be passed positionally in a tuple. - - Has a similar effect to that of ``itertools.starmap`` over - simple ``map``. - - >>> pairs = [(-1, 1), (0, 2)] - >>> more_itertools.consume(itertools.starmap(print, pairs)) - -1 1 - 0 2 - >>> more_itertools.consume(map(splat(print), pairs)) - -1 1 - 0 2 - - The approach generalizes to other iterators that don't have a "star" - equivalent, such as a "starfilter". - - >>> list(filter(splat(operator.add), pairs)) - [(0, 2)] - - Splat also accepts a mapping argument. - - >>> def is_nice(msg, code): - ... return "smile" in msg or code == 0 - >>> msgs = [ - ... dict(msg='smile!', code=20), - ... dict(msg='error :(', code=1), - ... dict(msg='unknown', code=0), - ... ] - >>> for msg in filter(splat(is_nice), msgs): - ... print(msg) - {'msg': 'smile!', 'code': 20} - {'msg': 'unknown', 'code': 0} - """ - return functools.wraps(func)(functools.partial(_splat_inner, func=func)) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__init__.pyi b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__init__.pyi deleted file mode 100644 index 19191bf..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__init__.pyi +++ /dev/null @@ -1,125 +0,0 @@ -from collections.abc import Callable, Hashable, Iterator -from functools import partial -from operator import methodcaller -import sys -from typing import ( - Any, - Generic, - Protocol, - TypeVar, - overload, -) - -if sys.version_info >= (3, 10): - from typing import Concatenate, ParamSpec -else: - from typing_extensions import Concatenate, ParamSpec - -_P = ParamSpec('_P') -_R = TypeVar('_R') -_T = TypeVar('_T') -_R1 = TypeVar('_R1') -_R2 = TypeVar('_R2') -_V = TypeVar('_V') -_S = TypeVar('_S') -_R_co = TypeVar('_R_co', covariant=True) - -class _OnceCallable(Protocol[_P, _R]): - saved_result: _R - reset: Callable[[], None] - def __call__(self, *args: _P.args, **kwargs: _P.kwargs) -> _R: ... - -class _ProxyMethodCacheWrapper(Protocol[_R_co]): - cache_clear: Callable[[], None] - def __call__(self, *args: Hashable, **kwargs: Hashable) -> _R_co: ... - -class _MethodCacheWrapper(Protocol[_R_co]): - def cache_clear(self) -> None: ... - def __call__(self, *args: Hashable, **kwargs: Hashable) -> _R_co: ... - -# `compose()` overloads below will cover most use cases. - -@overload -def compose( - __func1: Callable[[_R], _T], - __func2: Callable[_P, _R], - /, -) -> Callable[_P, _T]: ... -@overload -def compose( - __func1: Callable[[_R], _T], - __func2: Callable[[_R1], _R], - __func3: Callable[_P, _R1], - /, -) -> Callable[_P, _T]: ... -@overload -def compose( - __func1: Callable[[_R], _T], - __func2: Callable[[_R2], _R], - __func3: Callable[[_R1], _R2], - __func4: Callable[_P, _R1], - /, -) -> Callable[_P, _T]: ... -def once(func: Callable[_P, _R]) -> _OnceCallable[_P, _R]: ... -def method_cache( - method: Callable[..., _R], - cache_wrapper: Callable[[Callable[..., _R]], _MethodCacheWrapper[_R]] = ..., -) -> _MethodCacheWrapper[_R] | _ProxyMethodCacheWrapper[_R]: ... -def apply( - transform: Callable[[_R], _T] -) -> Callable[[Callable[_P, _R]], Callable[_P, _T]]: ... -def result_invoke( - action: Callable[[_R], Any] -) -> Callable[[Callable[_P, _R]], Callable[_P, _R]]: ... -def invoke( - f: Callable[_P, _R], /, *args: _P.args, **kwargs: _P.kwargs -) -> Callable[_P, _R]: ... - -class Throttler(Generic[_R]): - last_called: float - func: Callable[..., _R] - max_rate: float - def __init__( - self, func: Callable[..., _R] | Throttler[_R], max_rate: float = ... - ) -> None: ... - def reset(self) -> None: ... - def __call__(self, *args: Any, **kwargs: Any) -> _R: ... - def __get__(self, obj: Any, owner: type[Any] | None = ...) -> Callable[..., _R]: ... - -def first_invoke( - func1: Callable[..., Any], func2: Callable[_P, _R] -) -> Callable[_P, _R]: ... - -method_caller: Callable[..., methodcaller] - -def retry_call( - func: Callable[..., _R], - cleanup: Callable[..., None] = ..., - retries: int | float = ..., - trap: type[BaseException] | tuple[type[BaseException], ...] = ..., -) -> _R: ... -def retry( - cleanup: Callable[..., None] = ..., - retries: int | float = ..., - trap: type[BaseException] | tuple[type[BaseException], ...] = ..., -) -> Callable[[Callable[..., _R]], Callable[..., _R]]: ... -def print_yielded(func: Callable[_P, Iterator[Any]]) -> Callable[_P, None]: ... -def pass_none( - func: Callable[Concatenate[_T, _P], _R] -) -> Callable[Concatenate[_T, _P], _R]: ... -def assign_params( - func: Callable[..., _R], namespace: dict[str, Any] -) -> partial[_R]: ... -def save_method_args( - method: Callable[Concatenate[_S, _P], _R] -) -> Callable[Concatenate[_S, _P], _R]: ... -def except_( - *exceptions: type[BaseException], replace: Any = ..., use: Any = ... -) -> Callable[[Callable[_P, Any]], Callable[_P, Any]]: ... -def identity(x: _T) -> _T: ... -def bypass_when( - check: _V, *, _op: Callable[[_V], Any] = ... -) -> Callable[[Callable[[_T], _R]], Callable[[_T], _T | _R]]: ... -def bypass_unless( - check: Any, -) -> Callable[[Callable[[_T], _R]], Callable[[_T], _T | _R]]: ... diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index f4d14a7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/functools/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/Lorem ipsum.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/Lorem ipsum.txt deleted file mode 100644 index 986f944..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/Lorem ipsum.txt +++ /dev/null @@ -1,2 +0,0 @@ -Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. -Curabitur pretium tincidunt lacus. Nulla gravida orci a odio. Nullam varius, turpis et commodo pharetra, est eros bibendum elit, nec luctus magna felis sollicitudin mauris. Integer in mauris eu nibh euismod gravida. Duis ac tellus et risus vulputate vehicula. Donec lobortis risus a elit. Etiam tempor. Ut ullamcorper, ligula eu tempor congue, eros est euismod turpis, id tincidunt sapien risus a quam. Maecenas fermentum consequat mi. Donec fermentum. Pellentesque malesuada nulla a mi. Duis sapien sem, aliquet nec, commodo eget, consequat quis, neque. Aliquam faucibus, elit ut dictum aliquet, felis nisl adipiscing sapien, sed malesuada diam lacus eget erat. Cras mollis scelerisque nunc. Nullam arcu. Aliquam consequat. Curabitur augue lorem, dapibus quis, laoreet et, pretium ac, nisi. Aenean magna nisl, mollis quis, molestie eu, feugiat in, orci. In hac habitasse platea dictumst. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__init__.py deleted file mode 100644 index 0fabd0c..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__init__.py +++ /dev/null @@ -1,624 +0,0 @@ -import re -import itertools -import textwrap -import functools - -try: - from importlib.resources import files # type: ignore -except ImportError: # pragma: nocover - from importlib_resources import files # type: ignore - -from jaraco.functools import compose, method_cache -from jaraco.context import ExceptionTrap - - -def substitution(old, new): - """ - Return a function that will perform a substitution on a string - """ - return lambda s: s.replace(old, new) - - -def multi_substitution(*substitutions): - """ - Take a sequence of pairs specifying substitutions, and create - a function that performs those substitutions. - - >>> multi_substitution(('foo', 'bar'), ('bar', 'baz'))('foo') - 'baz' - """ - substitutions = itertools.starmap(substitution, substitutions) - # compose function applies last function first, so reverse the - # substitutions to get the expected order. - substitutions = reversed(tuple(substitutions)) - return compose(*substitutions) - - -class FoldedCase(str): - """ - A case insensitive string class; behaves just like str - except compares equal when the only variation is case. - - >>> s = FoldedCase('hello world') - - >>> s == 'Hello World' - True - - >>> 'Hello World' == s - True - - >>> s != 'Hello World' - False - - >>> s.index('O') - 4 - - >>> s.split('O') - ['hell', ' w', 'rld'] - - >>> sorted(map(FoldedCase, ['GAMMA', 'alpha', 'Beta'])) - ['alpha', 'Beta', 'GAMMA'] - - Sequence membership is straightforward. - - >>> "Hello World" in [s] - True - >>> s in ["Hello World"] - True - - Allows testing for set inclusion, but candidate and elements - must both be folded. - - >>> FoldedCase("Hello World") in {s} - True - >>> s in {FoldedCase("Hello World")} - True - - String inclusion works as long as the FoldedCase object - is on the right. - - >>> "hello" in FoldedCase("Hello World") - True - - But not if the FoldedCase object is on the left: - - >>> FoldedCase('hello') in 'Hello World' - False - - In that case, use ``in_``: - - >>> FoldedCase('hello').in_('Hello World') - True - - >>> FoldedCase('hello') > FoldedCase('Hello') - False - - >>> FoldedCase('ß') == FoldedCase('ss') - True - """ - - def __lt__(self, other): - return self.casefold() < other.casefold() - - def __gt__(self, other): - return self.casefold() > other.casefold() - - def __eq__(self, other): - return self.casefold() == other.casefold() - - def __ne__(self, other): - return self.casefold() != other.casefold() - - def __hash__(self): - return hash(self.casefold()) - - def __contains__(self, other): - return super().casefold().__contains__(other.casefold()) - - def in_(self, other): - "Does self appear in other?" - return self in FoldedCase(other) - - # cache casefold since it's likely to be called frequently. - @method_cache - def casefold(self): - return super().casefold() - - def index(self, sub): - return self.casefold().index(sub.casefold()) - - def split(self, splitter=' ', maxsplit=0): - pattern = re.compile(re.escape(splitter), re.I) - return pattern.split(self, maxsplit) - - -# Python 3.8 compatibility -_unicode_trap = ExceptionTrap(UnicodeDecodeError) - - -@_unicode_trap.passes -def is_decodable(value): - r""" - Return True if the supplied value is decodable (using the default - encoding). - - >>> is_decodable(b'\xff') - False - >>> is_decodable(b'\x32') - True - """ - value.decode() - - -def is_binary(value): - r""" - Return True if the value appears to be binary (that is, it's a byte - string and isn't decodable). - - >>> is_binary(b'\xff') - True - >>> is_binary('\xff') - False - """ - return isinstance(value, bytes) and not is_decodable(value) - - -def trim(s): - r""" - Trim something like a docstring to remove the whitespace that - is common due to indentation and formatting. - - >>> trim("\n\tfoo = bar\n\t\tbar = baz\n") - 'foo = bar\n\tbar = baz' - """ - return textwrap.dedent(s).strip() - - -def wrap(s): - """ - Wrap lines of text, retaining existing newlines as - paragraph markers. - - >>> print(wrap(lorem_ipsum)) - Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do - eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad - minim veniam, quis nostrud exercitation ullamco laboris nisi ut - aliquip ex ea commodo consequat. Duis aute irure dolor in - reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla - pariatur. Excepteur sint occaecat cupidatat non proident, sunt in - culpa qui officia deserunt mollit anim id est laborum. - - Curabitur pretium tincidunt lacus. Nulla gravida orci a odio. Nullam - varius, turpis et commodo pharetra, est eros bibendum elit, nec luctus - magna felis sollicitudin mauris. Integer in mauris eu nibh euismod - gravida. Duis ac tellus et risus vulputate vehicula. Donec lobortis - risus a elit. Etiam tempor. Ut ullamcorper, ligula eu tempor congue, - eros est euismod turpis, id tincidunt sapien risus a quam. Maecenas - fermentum consequat mi. Donec fermentum. Pellentesque malesuada nulla - a mi. Duis sapien sem, aliquet nec, commodo eget, consequat quis, - neque. Aliquam faucibus, elit ut dictum aliquet, felis nisl adipiscing - sapien, sed malesuada diam lacus eget erat. Cras mollis scelerisque - nunc. Nullam arcu. Aliquam consequat. Curabitur augue lorem, dapibus - quis, laoreet et, pretium ac, nisi. Aenean magna nisl, mollis quis, - molestie eu, feugiat in, orci. In hac habitasse platea dictumst. - """ - paragraphs = s.splitlines() - wrapped = ('\n'.join(textwrap.wrap(para)) for para in paragraphs) - return '\n\n'.join(wrapped) - - -def unwrap(s): - r""" - Given a multi-line string, return an unwrapped version. - - >>> wrapped = wrap(lorem_ipsum) - >>> wrapped.count('\n') - 20 - >>> unwrapped = unwrap(wrapped) - >>> unwrapped.count('\n') - 1 - >>> print(unwrapped) - Lorem ipsum dolor sit amet, consectetur adipiscing ... - Curabitur pretium tincidunt lacus. Nulla gravida orci ... - - """ - paragraphs = re.split(r'\n\n+', s) - cleaned = (para.replace('\n', ' ') for para in paragraphs) - return '\n'.join(cleaned) - - -lorem_ipsum: str = ( - files(__name__).joinpath('Lorem ipsum.txt').read_text(encoding='utf-8') -) - - -class Splitter: - """object that will split a string with the given arguments for each call - - >>> s = Splitter(',') - >>> s('hello, world, this is your, master calling') - ['hello', ' world', ' this is your', ' master calling'] - """ - - def __init__(self, *args): - self.args = args - - def __call__(self, s): - return s.split(*self.args) - - -def indent(string, prefix=' ' * 4): - """ - >>> indent('foo') - ' foo' - """ - return prefix + string - - -class WordSet(tuple): - """ - Given an identifier, return the words that identifier represents, - whether in camel case, underscore-separated, etc. - - >>> WordSet.parse("camelCase") - ('camel', 'Case') - - >>> WordSet.parse("under_sep") - ('under', 'sep') - - Acronyms should be retained - - >>> WordSet.parse("firstSNL") - ('first', 'SNL') - - >>> WordSet.parse("you_and_I") - ('you', 'and', 'I') - - >>> WordSet.parse("A simple test") - ('A', 'simple', 'test') - - Multiple caps should not interfere with the first cap of another word. - - >>> WordSet.parse("myABCClass") - ('my', 'ABC', 'Class') - - The result is a WordSet, providing access to other forms. - - >>> WordSet.parse("myABCClass").underscore_separated() - 'my_ABC_Class' - - >>> WordSet.parse('a-command').camel_case() - 'ACommand' - - >>> WordSet.parse('someIdentifier').lowered().space_separated() - 'some identifier' - - Slices of the result should return another WordSet. - - >>> WordSet.parse('taken-out-of-context')[1:].underscore_separated() - 'out_of_context' - - >>> WordSet.from_class_name(WordSet()).lowered().space_separated() - 'word set' - - >>> example = WordSet.parse('figured it out') - >>> example.headless_camel_case() - 'figuredItOut' - >>> example.dash_separated() - 'figured-it-out' - - """ - - _pattern = re.compile('([A-Z]?[a-z]+)|([A-Z]+(?![a-z]))') - - def capitalized(self): - return WordSet(word.capitalize() for word in self) - - def lowered(self): - return WordSet(word.lower() for word in self) - - def camel_case(self): - return ''.join(self.capitalized()) - - def headless_camel_case(self): - words = iter(self) - first = next(words).lower() - new_words = itertools.chain((first,), WordSet(words).camel_case()) - return ''.join(new_words) - - def underscore_separated(self): - return '_'.join(self) - - def dash_separated(self): - return '-'.join(self) - - def space_separated(self): - return ' '.join(self) - - def trim_right(self, item): - """ - Remove the item from the end of the set. - - >>> WordSet.parse('foo bar').trim_right('foo') - ('foo', 'bar') - >>> WordSet.parse('foo bar').trim_right('bar') - ('foo',) - >>> WordSet.parse('').trim_right('bar') - () - """ - return self[:-1] if self and self[-1] == item else self - - def trim_left(self, item): - """ - Remove the item from the beginning of the set. - - >>> WordSet.parse('foo bar').trim_left('foo') - ('bar',) - >>> WordSet.parse('foo bar').trim_left('bar') - ('foo', 'bar') - >>> WordSet.parse('').trim_left('bar') - () - """ - return self[1:] if self and self[0] == item else self - - def trim(self, item): - """ - >>> WordSet.parse('foo bar').trim('foo') - ('bar',) - """ - return self.trim_left(item).trim_right(item) - - def __getitem__(self, item): - result = super().__getitem__(item) - if isinstance(item, slice): - result = WordSet(result) - return result - - @classmethod - def parse(cls, identifier): - matches = cls._pattern.finditer(identifier) - return WordSet(match.group(0) for match in matches) - - @classmethod - def from_class_name(cls, subject): - return cls.parse(subject.__class__.__name__) - - -# for backward compatibility -words = WordSet.parse - - -def simple_html_strip(s): - r""" - Remove HTML from the string `s`. - - >>> str(simple_html_strip('')) - '' - - >>> print(simple_html_strip('A stormy day in paradise')) - A stormy day in paradise - - >>> print(simple_html_strip('Somebody tell the truth.')) - Somebody tell the truth. - - >>> print(simple_html_strip('What about
\nmultiple lines?')) - What about - multiple lines? - """ - html_stripper = re.compile('()|(<[^>]*>)|([^<]+)', re.DOTALL) - texts = (match.group(3) or '' for match in html_stripper.finditer(s)) - return ''.join(texts) - - -class SeparatedValues(str): - """ - A string separated by a separator. Overrides __iter__ for getting - the values. - - >>> list(SeparatedValues('a,b,c')) - ['a', 'b', 'c'] - - Whitespace is stripped and empty values are discarded. - - >>> list(SeparatedValues(' a, b , c, ')) - ['a', 'b', 'c'] - """ - - separator = ',' - - def __iter__(self): - parts = self.split(self.separator) - return filter(None, (part.strip() for part in parts)) - - -class Stripper: - r""" - Given a series of lines, find the common prefix and strip it from them. - - >>> lines = [ - ... 'abcdefg\n', - ... 'abc\n', - ... 'abcde\n', - ... ] - >>> res = Stripper.strip_prefix(lines) - >>> res.prefix - 'abc' - >>> list(res.lines) - ['defg\n', '\n', 'de\n'] - - If no prefix is common, nothing should be stripped. - - >>> lines = [ - ... 'abcd\n', - ... '1234\n', - ... ] - >>> res = Stripper.strip_prefix(lines) - >>> res.prefix = '' - >>> list(res.lines) - ['abcd\n', '1234\n'] - """ - - def __init__(self, prefix, lines): - self.prefix = prefix - self.lines = map(self, lines) - - @classmethod - def strip_prefix(cls, lines): - prefix_lines, lines = itertools.tee(lines) - prefix = functools.reduce(cls.common_prefix, prefix_lines) - return cls(prefix, lines) - - def __call__(self, line): - if not self.prefix: - return line - null, prefix, rest = line.partition(self.prefix) - return rest - - @staticmethod - def common_prefix(s1, s2): - """ - Return the common prefix of two lines. - """ - index = min(len(s1), len(s2)) - while s1[:index] != s2[:index]: - index -= 1 - return s1[:index] - - -def remove_prefix(text, prefix): - """ - Remove the prefix from the text if it exists. - - >>> remove_prefix('underwhelming performance', 'underwhelming ') - 'performance' - - >>> remove_prefix('something special', 'sample') - 'something special' - """ - null, prefix, rest = text.rpartition(prefix) - return rest - - -def remove_suffix(text, suffix): - """ - Remove the suffix from the text if it exists. - - >>> remove_suffix('name.git', '.git') - 'name' - - >>> remove_suffix('something special', 'sample') - 'something special' - """ - rest, suffix, null = text.partition(suffix) - return rest - - -def normalize_newlines(text): - r""" - Replace alternate newlines with the canonical newline. - - >>> normalize_newlines('Lorem Ipsum\u2029') - 'Lorem Ipsum\n' - >>> normalize_newlines('Lorem Ipsum\r\n') - 'Lorem Ipsum\n' - >>> normalize_newlines('Lorem Ipsum\x85') - 'Lorem Ipsum\n' - """ - newlines = ['\r\n', '\r', '\n', '\u0085', '\u2028', '\u2029'] - pattern = '|'.join(newlines) - return re.sub(pattern, '\n', text) - - -def _nonblank(str): - return str and not str.startswith('#') - - -@functools.singledispatch -def yield_lines(iterable): - r""" - Yield valid lines of a string or iterable. - - >>> list(yield_lines('')) - [] - >>> list(yield_lines(['foo', 'bar'])) - ['foo', 'bar'] - >>> list(yield_lines('foo\nbar')) - ['foo', 'bar'] - >>> list(yield_lines('\nfoo\n#bar\nbaz #comment')) - ['foo', 'baz #comment'] - >>> list(yield_lines(['foo\nbar', 'baz', 'bing\n\n\n'])) - ['foo', 'bar', 'baz', 'bing'] - """ - return itertools.chain.from_iterable(map(yield_lines, iterable)) - - -@yield_lines.register(str) -def _(text): - return filter(_nonblank, map(str.strip, text.splitlines())) - - -def drop_comment(line): - """ - Drop comments. - - >>> drop_comment('foo # bar') - 'foo' - - A hash without a space may be in a URL. - - >>> drop_comment('http://example.com/foo#bar') - 'http://example.com/foo#bar' - """ - return line.partition(' #')[0] - - -def join_continuation(lines): - r""" - Join lines continued by a trailing backslash. - - >>> list(join_continuation(['foo \\', 'bar', 'baz'])) - ['foobar', 'baz'] - >>> list(join_continuation(['foo \\', 'bar', 'baz'])) - ['foobar', 'baz'] - >>> list(join_continuation(['foo \\', 'bar \\', 'baz'])) - ['foobarbaz'] - - Not sure why, but... - The character preceding the backslash is also elided. - - >>> list(join_continuation(['goo\\', 'dly'])) - ['godly'] - - A terrible idea, but... - If no line is available to continue, suppress the lines. - - >>> list(join_continuation(['foo', 'bar\\', 'baz\\'])) - ['foo'] - """ - lines = iter(lines) - for item in lines: - while item.endswith('\\'): - try: - item = item[:-2].strip() + next(lines) - except StopIteration: - return - yield item - - -def read_newlines(filename, limit=1024): - r""" - >>> tmp_path = getfixture('tmp_path') - >>> filename = tmp_path / 'out.txt' - >>> _ = filename.write_text('foo\n', newline='', encoding='utf-8') - >>> read_newlines(filename) - '\n' - >>> _ = filename.write_text('foo\r\n', newline='', encoding='utf-8') - >>> read_newlines(filename) - '\r\n' - >>> _ = filename.write_text('foo\r\nbar\nbing\r', newline='', encoding='utf-8') - >>> read_newlines(filename) - ('\r', '\n', '\r\n') - """ - with open(filename, encoding='utf-8') as fp: - fp.read(limit) - return fp.newlines diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 91c16cf..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/layouts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/layouts.cpython-312.pyc deleted file mode 100644 index f951fa8..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/layouts.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/show-newlines.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/show-newlines.cpython-312.pyc deleted file mode 100644 index 7899988..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/show-newlines.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/strip-prefix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/strip-prefix.cpython-312.pyc deleted file mode 100644 index 491bd97..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/strip-prefix.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/to-dvorak.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/to-dvorak.cpython-312.pyc deleted file mode 100644 index c283a76..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/to-dvorak.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/to-qwerty.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/to-qwerty.cpython-312.pyc deleted file mode 100644 index d2afc56..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/__pycache__/to-qwerty.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/layouts.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/layouts.py deleted file mode 100644 index 9636f0f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/layouts.py +++ /dev/null @@ -1,25 +0,0 @@ -qwerty = "-=qwertyuiop[]asdfghjkl;'zxcvbnm,./_+QWERTYUIOP{}ASDFGHJKL:\"ZXCVBNM<>?" -dvorak = "[]',.pyfgcrl/=aoeuidhtns-;qjkxbmwvz{}\"<>PYFGCRL?+AOEUIDHTNS_:QJKXBMWVZ" - - -to_dvorak = str.maketrans(qwerty, dvorak) -to_qwerty = str.maketrans(dvorak, qwerty) - - -def translate(input, translation): - """ - >>> translate('dvorak', to_dvorak) - 'ekrpat' - >>> translate('qwerty', to_qwerty) - 'x,dokt' - """ - return input.translate(translation) - - -def _translate_stream(stream, translation): - """ - >>> import io - >>> _translate_stream(io.StringIO('foo'), to_dvorak) - urr - """ - print(translate(stream.read(), translation)) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/show-newlines.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/show-newlines.py deleted file mode 100644 index e11d1ba..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/show-newlines.py +++ /dev/null @@ -1,33 +0,0 @@ -import autocommand -import inflect - -from more_itertools import always_iterable - -import jaraco.text - - -def report_newlines(filename): - r""" - Report the newlines in the indicated file. - - >>> tmp_path = getfixture('tmp_path') - >>> filename = tmp_path / 'out.txt' - >>> _ = filename.write_text('foo\nbar\n', newline='', encoding='utf-8') - >>> report_newlines(filename) - newline is '\n' - >>> filename = tmp_path / 'out.txt' - >>> _ = filename.write_text('foo\nbar\r\n', newline='', encoding='utf-8') - >>> report_newlines(filename) - newlines are ('\n', '\r\n') - """ - newlines = jaraco.text.read_newlines(filename) - count = len(tuple(always_iterable(newlines))) - engine = inflect.engine() - print( - engine.plural_noun("newline", count), - engine.plural_verb("is", count), - repr(newlines), - ) - - -autocommand.autocommand(__name__)(report_newlines) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/strip-prefix.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/strip-prefix.py deleted file mode 100644 index 761717a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/strip-prefix.py +++ /dev/null @@ -1,21 +0,0 @@ -import sys - -import autocommand - -from jaraco.text import Stripper - - -def strip_prefix(): - r""" - Strip any common prefix from stdin. - - >>> import io, pytest - >>> getfixture('monkeypatch').setattr('sys.stdin', io.StringIO('abcdef\nabc123')) - >>> strip_prefix() - def - 123 - """ - sys.stdout.writelines(Stripper.strip_prefix(sys.stdin).lines) - - -autocommand.autocommand(__name__)(strip_prefix) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/to-dvorak.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/to-dvorak.py deleted file mode 100644 index a6d5da8..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/to-dvorak.py +++ /dev/null @@ -1,6 +0,0 @@ -import sys - -from . import layouts - - -__name__ == '__main__' and layouts._translate_stream(sys.stdin, layouts.to_dvorak) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/to-qwerty.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/to-qwerty.py deleted file mode 100644 index abe2728..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/jaraco/text/to-qwerty.py +++ /dev/null @@ -1,6 +0,0 @@ -import sys - -from . import layouts - - -__name__ == '__main__' and layouts._translate_stream(sys.stdin, layouts.to_qwerty) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/INSTALLER deleted file mode 100644 index a1b589e..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -pip diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/LICENSE deleted file mode 100644 index 0a523be..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/LICENSE +++ /dev/null @@ -1,19 +0,0 @@ -Copyright (c) 2012 Erik Rose - -Permission is hereby granted, free of charge, to any person obtaining a copy of -this software and associated documentation files (the "Software"), to deal in -the Software without restriction, including without limitation the rights to -use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies -of the Software, and to permit persons to whom the Software is furnished to do -so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/METADATA deleted file mode 100644 index fb41b0c..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/METADATA +++ /dev/null @@ -1,266 +0,0 @@ -Metadata-Version: 2.1 -Name: more-itertools -Version: 10.3.0 -Summary: More routines for operating on iterables, beyond itertools -Keywords: itertools,iterator,iteration,filter,peek,peekable,chunk,chunked -Author-email: Erik Rose -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: Natural Language :: English -Classifier: License :: OSI Approved :: MIT License -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3.8 -Classifier: Programming Language :: Python :: 3.9 -Classifier: Programming Language :: Python :: 3.10 -Classifier: Programming Language :: Python :: 3.11 -Classifier: Programming Language :: Python :: 3.12 -Classifier: Programming Language :: Python :: 3 :: Only -Classifier: Programming Language :: Python :: Implementation :: CPython -Classifier: Programming Language :: Python :: Implementation :: PyPy -Classifier: Topic :: Software Development :: Libraries -Project-URL: Homepage, https://github.com/more-itertools/more-itertools - -============== -More Itertools -============== - -.. image:: https://readthedocs.org/projects/more-itertools/badge/?version=latest - :target: https://more-itertools.readthedocs.io/en/stable/ - -Python's ``itertools`` library is a gem - you can compose elegant solutions -for a variety of problems with the functions it provides. In ``more-itertools`` -we collect additional building blocks, recipes, and routines for working with -Python iterables. - -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Grouping | `chunked `_, | -| | `ichunked `_, | -| | `chunked_even `_, | -| | `sliced `_, | -| | `constrained_batches `_, | -| | `distribute `_, | -| | `divide `_, | -| | `split_at `_, | -| | `split_before `_, | -| | `split_after `_, | -| | `split_into `_, | -| | `split_when `_, | -| | `bucket `_, | -| | `unzip `_, | -| | `batched `_, | -| | `grouper `_, | -| | `partition `_, | -| | `transpose `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Lookahead and lookback | `spy `_, | -| | `peekable `_, | -| | `seekable `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Windowing | `windowed `_, | -| | `substrings `_, | -| | `substrings_indexes `_, | -| | `stagger `_, | -| | `windowed_complete `_, | -| | `pairwise `_, | -| | `triplewise `_, | -| | `sliding_window `_, | -| | `subslices `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Augmenting | `count_cycle `_, | -| | `intersperse `_, | -| | `padded `_, | -| | `repeat_each `_, | -| | `mark_ends `_, | -| | `repeat_last `_, | -| | `adjacent `_, | -| | `groupby_transform `_, | -| | `pad_none `_, | -| | `ncycles `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Combining | `collapse `_, | -| | `sort_together `_, | -| | `interleave `_, | -| | `interleave_longest `_, | -| | `interleave_evenly `_, | -| | `zip_offset `_, | -| | `zip_equal `_, | -| | `zip_broadcast `_, | -| | `flatten `_, | -| | `roundrobin `_, | -| | `prepend `_, | -| | `value_chain `_, | -| | `partial_product `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Summarizing | `ilen `_, | -| | `unique_to_each `_, | -| | `sample `_, | -| | `consecutive_groups `_, | -| | `run_length `_, | -| | `map_reduce `_, | -| | `join_mappings `_, | -| | `exactly_n `_, | -| | `is_sorted `_, | -| | `all_equal `_, | -| | `all_unique `_, | -| | `minmax `_, | -| | `first_true `_, | -| | `quantify `_, | -| | `iequals `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Selecting | `islice_extended `_, | -| | `first `_, | -| | `last `_, | -| | `one `_, | -| | `only `_, | -| | `strictly_n `_, | -| | `strip `_, | -| | `lstrip `_, | -| | `rstrip `_, | -| | `filter_except `_, | -| | `map_except `_, | -| | `filter_map `_, | -| | `iter_suppress `_, | -| | `nth_or_last `_, | -| | `unique_in_window `_, | -| | `before_and_after `_, | -| | `nth `_, | -| | `take `_, | -| | `tail `_, | -| | `unique_everseen `_, | -| | `unique_justseen `_, | -| | `unique `_, | -| | `duplicates_everseen `_, | -| | `duplicates_justseen `_, | -| | `classify_unique `_, | -| | `longest_common_prefix `_, | -| | `takewhile_inclusive `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Math | `dft `_, | -| | `idft `_, | -| | `convolve `_, | -| | `dotproduct `_, | -| | `factor `_, | -| | `matmul `_, | -| | `polynomial_from_roots `_, | -| | `polynomial_derivative `_, | -| | `polynomial_eval `_, | -| | `sieve `_, | -| | `sum_of_squares `_, | -| | `totient `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Combinatorics | `distinct_permutations `_, | -| | `distinct_combinations `_, | -| | `circular_shifts `_, | -| | `partitions `_, | -| | `set_partitions `_, | -| | `product_index `_, | -| | `combination_index `_, | -| | `permutation_index `_, | -| | `combination_with_replacement_index `_, | -| | `gray_product `_, | -| | `outer_product `_, | -| | `powerset `_, | -| | `powerset_of_sets `_, | -| | `random_product `_, | -| | `random_permutation `_, | -| | `random_combination `_, | -| | `random_combination_with_replacement `_, | -| | `nth_product `_, | -| | `nth_permutation `_, | -| | `nth_combination `_, | -| | `nth_combination_with_replacement `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Wrapping | `always_iterable `_, | -| | `always_reversible `_, | -| | `countable `_, | -| | `consumer `_, | -| | `with_iter `_, | -| | `iter_except `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| Others | `locate `_, | -| | `rlocate `_, | -| | `replace `_, | -| | `numeric_range `_, | -| | `side_effect `_, | -| | `iterate `_, | -| | `difference `_, | -| | `make_decorator `_, | -| | `SequenceView `_, | -| | `time_limited `_, | -| | `map_if `_, | -| | `iter_index `_, | -| | `consume `_, | -| | `tabulate `_, | -| | `repeatfunc `_, | -| | `reshape `_ | -| | `doublestarmap `_ | -+------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ - - -Getting started -=============== - -To get started, install the library with `pip `_: - -.. code-block:: shell - - pip install more-itertools - -The recipes from the `itertools docs `_ -are included in the top-level package: - -.. code-block:: python - - >>> from more_itertools import flatten - >>> iterable = [(0, 1), (2, 3)] - >>> list(flatten(iterable)) - [0, 1, 2, 3] - -Several new recipes are available as well: - -.. code-block:: python - - >>> from more_itertools import chunked - >>> iterable = [0, 1, 2, 3, 4, 5, 6, 7, 8] - >>> list(chunked(iterable, 3)) - [[0, 1, 2], [3, 4, 5], [6, 7, 8]] - - >>> from more_itertools import spy - >>> iterable = (x * x for x in range(1, 6)) - >>> head, iterable = spy(iterable, n=3) - >>> list(head) - [1, 4, 9] - >>> list(iterable) - [1, 4, 9, 16, 25] - - - -For the full listing of functions, see the `API documentation `_. - - -Links elsewhere -=============== - -Blog posts about ``more-itertools``: - -* `Yo, I heard you like decorators `__ -* `Tour of Python Itertools `__ (`Alternate `__) -* `Real-World Python More Itertools `_ - - -Development -=========== - -``more-itertools`` is maintained by `@erikrose `_ -and `@bbayles `_, with help from `many others `_. -If you have a problem or suggestion, please file a bug or pull request in this -repository. Thanks for contributing! - - -Version History -=============== - -The version history can be found in `documentation `_. - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/RECORD deleted file mode 100644 index f15f3fc..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/RECORD +++ /dev/null @@ -1,16 +0,0 @@ -more_itertools-10.3.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 -more_itertools-10.3.0.dist-info/LICENSE,sha256=CfHIyelBrz5YTVlkHqm4fYPAyw_QB-te85Gn4mQ8GkY,1053 -more_itertools-10.3.0.dist-info/METADATA,sha256=BFO90O-fLNiVQMpj7oIS5ztzgJUUQZ3TA32P5HH3N-A,36293 -more_itertools-10.3.0.dist-info/RECORD,, -more_itertools-10.3.0.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -more_itertools-10.3.0.dist-info/WHEEL,sha256=rSgq_JpHF9fHR1lx53qwg_1-2LypZE_qmcuXbVUq948,81 -more_itertools/__init__.py,sha256=dtAbGjTDmn_ghiU5YXfhyDy0phAlXVdt5klZA5fUa-Q,149 -more_itertools/__init__.pyi,sha256=5B3eTzON1BBuOLob1vCflyEb2lSd6usXQQ-Cv-hXkeA,43 -more_itertools/__pycache__/__init__.cpython-312.pyc,, -more_itertools/__pycache__/more.cpython-312.pyc,, -more_itertools/__pycache__/recipes.cpython-312.pyc,, -more_itertools/more.py,sha256=1E5kzFncRKTDw0cYv1yRXMgDdunstLQd1QStcnL6U90,148370 -more_itertools/more.pyi,sha256=iXXeqt48Nxe8VGmIWpkVXuKpR2FYNuu2DU8nQLWCCu0,21484 -more_itertools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -more_itertools/recipes.py,sha256=WedhhfhGVgr6zii8fIbGJVmRTw0ZKRiLKnYBDGJv4nY,28591 -more_itertools/recipes.pyi,sha256=T_mdGpcFdfrP3JSWbwzYP9JyNV-Go-7RPfpxfftAWlA,4617 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/REQUESTED deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/WHEEL deleted file mode 100644 index db4a255..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools-10.3.0.dist-info/WHEEL +++ /dev/null @@ -1,4 +0,0 @@ -Wheel-Version: 1.0 -Generator: flit 3.8.0 -Root-Is-Purelib: true -Tag: py3-none-any diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__init__.py deleted file mode 100644 index 9c4662f..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__init__.py +++ /dev/null @@ -1,6 +0,0 @@ -"""More routines for operating on iterables, beyond itertools""" - -from .more import * # noqa -from .recipes import * # noqa - -__version__ = '10.3.0' diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__init__.pyi b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__init__.pyi deleted file mode 100644 index 96f6e36..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__init__.pyi +++ /dev/null @@ -1,2 +0,0 @@ -from .more import * -from .recipes import * diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index ecc6d27..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/more.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/more.cpython-312.pyc deleted file mode 100644 index 38f61f6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/more.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/recipes.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/recipes.cpython-312.pyc deleted file mode 100644 index 78262a4..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/__pycache__/recipes.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/more.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/more.py deleted file mode 100644 index 7b48190..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/more.py +++ /dev/null @@ -1,4806 +0,0 @@ -import math -import warnings - -from collections import Counter, defaultdict, deque, abc -from collections.abc import Sequence -from functools import cached_property, partial, reduce, wraps -from heapq import heapify, heapreplace, heappop -from itertools import ( - chain, - combinations, - compress, - count, - cycle, - dropwhile, - groupby, - islice, - repeat, - starmap, - takewhile, - tee, - zip_longest, - product, -) -from math import comb, e, exp, factorial, floor, fsum, log, perm, tau -from queue import Empty, Queue -from random import random, randrange, uniform -from operator import itemgetter, mul, sub, gt, lt, ge, le -from sys import hexversion, maxsize -from time import monotonic - -from .recipes import ( - _marker, - _zip_equal, - UnequalIterablesError, - consume, - flatten, - pairwise, - powerset, - take, - unique_everseen, - all_equal, - batched, -) - -__all__ = [ - 'AbortThread', - 'SequenceView', - 'UnequalIterablesError', - 'adjacent', - 'all_unique', - 'always_iterable', - 'always_reversible', - 'bucket', - 'callback_iter', - 'chunked', - 'chunked_even', - 'circular_shifts', - 'collapse', - 'combination_index', - 'combination_with_replacement_index', - 'consecutive_groups', - 'constrained_batches', - 'consumer', - 'count_cycle', - 'countable', - 'dft', - 'difference', - 'distinct_combinations', - 'distinct_permutations', - 'distribute', - 'divide', - 'doublestarmap', - 'duplicates_everseen', - 'duplicates_justseen', - 'classify_unique', - 'exactly_n', - 'filter_except', - 'filter_map', - 'first', - 'gray_product', - 'groupby_transform', - 'ichunked', - 'iequals', - 'idft', - 'ilen', - 'interleave', - 'interleave_evenly', - 'interleave_longest', - 'intersperse', - 'is_sorted', - 'islice_extended', - 'iterate', - 'iter_suppress', - 'join_mappings', - 'last', - 'locate', - 'longest_common_prefix', - 'lstrip', - 'make_decorator', - 'map_except', - 'map_if', - 'map_reduce', - 'mark_ends', - 'minmax', - 'nth_or_last', - 'nth_permutation', - 'nth_product', - 'nth_combination_with_replacement', - 'numeric_range', - 'one', - 'only', - 'outer_product', - 'padded', - 'partial_product', - 'partitions', - 'peekable', - 'permutation_index', - 'powerset_of_sets', - 'product_index', - 'raise_', - 'repeat_each', - 'repeat_last', - 'replace', - 'rlocate', - 'rstrip', - 'run_length', - 'sample', - 'seekable', - 'set_partitions', - 'side_effect', - 'sliced', - 'sort_together', - 'split_after', - 'split_at', - 'split_before', - 'split_into', - 'split_when', - 'spy', - 'stagger', - 'strip', - 'strictly_n', - 'substrings', - 'substrings_indexes', - 'takewhile_inclusive', - 'time_limited', - 'unique_in_window', - 'unique_to_each', - 'unzip', - 'value_chain', - 'windowed', - 'windowed_complete', - 'with_iter', - 'zip_broadcast', - 'zip_equal', - 'zip_offset', -] - -# math.sumprod is available for Python 3.12+ -_fsumprod = getattr(math, 'sumprod', lambda x, y: fsum(map(mul, x, y))) - - -def chunked(iterable, n, strict=False): - """Break *iterable* into lists of length *n*: - - >>> list(chunked([1, 2, 3, 4, 5, 6], 3)) - [[1, 2, 3], [4, 5, 6]] - - By the default, the last yielded list will have fewer than *n* elements - if the length of *iterable* is not divisible by *n*: - - >>> list(chunked([1, 2, 3, 4, 5, 6, 7, 8], 3)) - [[1, 2, 3], [4, 5, 6], [7, 8]] - - To use a fill-in value instead, see the :func:`grouper` recipe. - - If the length of *iterable* is not divisible by *n* and *strict* is - ``True``, then ``ValueError`` will be raised before the last - list is yielded. - - """ - iterator = iter(partial(take, n, iter(iterable)), []) - if strict: - if n is None: - raise ValueError('n must not be None when using strict mode.') - - def ret(): - for chunk in iterator: - if len(chunk) != n: - raise ValueError('iterable is not divisible by n.') - yield chunk - - return iter(ret()) - else: - return iterator - - -def first(iterable, default=_marker): - """Return the first item of *iterable*, or *default* if *iterable* is - empty. - - >>> first([0, 1, 2, 3]) - 0 - >>> first([], 'some default') - 'some default' - - If *default* is not provided and there are no items in the iterable, - raise ``ValueError``. - - :func:`first` is useful when you have a generator of expensive-to-retrieve - values and want any arbitrary one. It is marginally shorter than - ``next(iter(iterable), default)``. - - """ - for item in iterable: - return item - if default is _marker: - raise ValueError( - 'first() was called on an empty iterable, and no ' - 'default value was provided.' - ) - return default - - -def last(iterable, default=_marker): - """Return the last item of *iterable*, or *default* if *iterable* is - empty. - - >>> last([0, 1, 2, 3]) - 3 - >>> last([], 'some default') - 'some default' - - If *default* is not provided and there are no items in the iterable, - raise ``ValueError``. - """ - try: - if isinstance(iterable, Sequence): - return iterable[-1] - # Work around https://bugs.python.org/issue38525 - elif hasattr(iterable, '__reversed__') and (hexversion != 0x030800F0): - return next(reversed(iterable)) - else: - return deque(iterable, maxlen=1)[-1] - except (IndexError, TypeError, StopIteration): - if default is _marker: - raise ValueError( - 'last() was called on an empty iterable, and no default was ' - 'provided.' - ) - return default - - -def nth_or_last(iterable, n, default=_marker): - """Return the nth or the last item of *iterable*, - or *default* if *iterable* is empty. - - >>> nth_or_last([0, 1, 2, 3], 2) - 2 - >>> nth_or_last([0, 1], 2) - 1 - >>> nth_or_last([], 0, 'some default') - 'some default' - - If *default* is not provided and there are no items in the iterable, - raise ``ValueError``. - """ - return last(islice(iterable, n + 1), default=default) - - -class peekable: - """Wrap an iterator to allow lookahead and prepending elements. - - Call :meth:`peek` on the result to get the value that will be returned - by :func:`next`. This won't advance the iterator: - - >>> p = peekable(['a', 'b']) - >>> p.peek() - 'a' - >>> next(p) - 'a' - - Pass :meth:`peek` a default value to return that instead of raising - ``StopIteration`` when the iterator is exhausted. - - >>> p = peekable([]) - >>> p.peek('hi') - 'hi' - - peekables also offer a :meth:`prepend` method, which "inserts" items - at the head of the iterable: - - >>> p = peekable([1, 2, 3]) - >>> p.prepend(10, 11, 12) - >>> next(p) - 10 - >>> p.peek() - 11 - >>> list(p) - [11, 12, 1, 2, 3] - - peekables can be indexed. Index 0 is the item that will be returned by - :func:`next`, index 1 is the item after that, and so on: - The values up to the given index will be cached. - - >>> p = peekable(['a', 'b', 'c', 'd']) - >>> p[0] - 'a' - >>> p[1] - 'b' - >>> next(p) - 'a' - - Negative indexes are supported, but be aware that they will cache the - remaining items in the source iterator, which may require significant - storage. - - To check whether a peekable is exhausted, check its truth value: - - >>> p = peekable(['a', 'b']) - >>> if p: # peekable has items - ... list(p) - ['a', 'b'] - >>> if not p: # peekable is exhausted - ... list(p) - [] - - """ - - def __init__(self, iterable): - self._it = iter(iterable) - self._cache = deque() - - def __iter__(self): - return self - - def __bool__(self): - try: - self.peek() - except StopIteration: - return False - return True - - def peek(self, default=_marker): - """Return the item that will be next returned from ``next()``. - - Return ``default`` if there are no items left. If ``default`` is not - provided, raise ``StopIteration``. - - """ - if not self._cache: - try: - self._cache.append(next(self._it)) - except StopIteration: - if default is _marker: - raise - return default - return self._cache[0] - - def prepend(self, *items): - """Stack up items to be the next ones returned from ``next()`` or - ``self.peek()``. The items will be returned in - first in, first out order:: - - >>> p = peekable([1, 2, 3]) - >>> p.prepend(10, 11, 12) - >>> next(p) - 10 - >>> list(p) - [11, 12, 1, 2, 3] - - It is possible, by prepending items, to "resurrect" a peekable that - previously raised ``StopIteration``. - - >>> p = peekable([]) - >>> next(p) - Traceback (most recent call last): - ... - StopIteration - >>> p.prepend(1) - >>> next(p) - 1 - >>> next(p) - Traceback (most recent call last): - ... - StopIteration - - """ - self._cache.extendleft(reversed(items)) - - def __next__(self): - if self._cache: - return self._cache.popleft() - - return next(self._it) - - def _get_slice(self, index): - # Normalize the slice's arguments - step = 1 if (index.step is None) else index.step - if step > 0: - start = 0 if (index.start is None) else index.start - stop = maxsize if (index.stop is None) else index.stop - elif step < 0: - start = -1 if (index.start is None) else index.start - stop = (-maxsize - 1) if (index.stop is None) else index.stop - else: - raise ValueError('slice step cannot be zero') - - # If either the start or stop index is negative, we'll need to cache - # the rest of the iterable in order to slice from the right side. - if (start < 0) or (stop < 0): - self._cache.extend(self._it) - # Otherwise we'll need to find the rightmost index and cache to that - # point. - else: - n = min(max(start, stop) + 1, maxsize) - cache_len = len(self._cache) - if n >= cache_len: - self._cache.extend(islice(self._it, n - cache_len)) - - return list(self._cache)[index] - - def __getitem__(self, index): - if isinstance(index, slice): - return self._get_slice(index) - - cache_len = len(self._cache) - if index < 0: - self._cache.extend(self._it) - elif index >= cache_len: - self._cache.extend(islice(self._it, index + 1 - cache_len)) - - return self._cache[index] - - -def consumer(func): - """Decorator that automatically advances a PEP-342-style "reverse iterator" - to its first yield point so you don't have to call ``next()`` on it - manually. - - >>> @consumer - ... def tally(): - ... i = 0 - ... while True: - ... print('Thing number %s is %s.' % (i, (yield))) - ... i += 1 - ... - >>> t = tally() - >>> t.send('red') - Thing number 0 is red. - >>> t.send('fish') - Thing number 1 is fish. - - Without the decorator, you would have to call ``next(t)`` before - ``t.send()`` could be used. - - """ - - @wraps(func) - def wrapper(*args, **kwargs): - gen = func(*args, **kwargs) - next(gen) - return gen - - return wrapper - - -def ilen(iterable): - """Return the number of items in *iterable*. - - >>> ilen(x for x in range(1000000) if x % 3 == 0) - 333334 - - This consumes the iterable, so handle with care. - - """ - # This approach was selected because benchmarks showed it's likely the - # fastest of the known implementations at the time of writing. - # See GitHub tracker: #236, #230. - counter = count() - deque(zip(iterable, counter), maxlen=0) - return next(counter) - - -def iterate(func, start): - """Return ``start``, ``func(start)``, ``func(func(start))``, ... - - >>> from itertools import islice - >>> list(islice(iterate(lambda x: 2*x, 1), 10)) - [1, 2, 4, 8, 16, 32, 64, 128, 256, 512] - - """ - while True: - yield start - try: - start = func(start) - except StopIteration: - break - - -def with_iter(context_manager): - """Wrap an iterable in a ``with`` statement, so it closes once exhausted. - - For example, this will close the file when the iterator is exhausted:: - - upper_lines = (line.upper() for line in with_iter(open('foo'))) - - Any context manager which returns an iterable is a candidate for - ``with_iter``. - - """ - with context_manager as iterable: - yield from iterable - - -def one(iterable, too_short=None, too_long=None): - """Return the first item from *iterable*, which is expected to contain only - that item. Raise an exception if *iterable* is empty or has more than one - item. - - :func:`one` is useful for ensuring that an iterable contains only one item. - For example, it can be used to retrieve the result of a database query - that is expected to return a single row. - - If *iterable* is empty, ``ValueError`` will be raised. You may specify a - different exception with the *too_short* keyword: - - >>> it = [] - >>> one(it) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - ValueError: too many items in iterable (expected 1)' - >>> too_short = IndexError('too few items') - >>> one(it, too_short=too_short) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - IndexError: too few items - - Similarly, if *iterable* contains more than one item, ``ValueError`` will - be raised. You may specify a different exception with the *too_long* - keyword: - - >>> it = ['too', 'many'] - >>> one(it) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - ValueError: Expected exactly one item in iterable, but got 'too', - 'many', and perhaps more. - >>> too_long = RuntimeError - >>> one(it, too_long=too_long) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - RuntimeError - - Note that :func:`one` attempts to advance *iterable* twice to ensure there - is only one item. See :func:`spy` or :func:`peekable` to check iterable - contents less destructively. - - """ - it = iter(iterable) - - try: - first_value = next(it) - except StopIteration as exc: - raise ( - too_short or ValueError('too few items in iterable (expected 1)') - ) from exc - - try: - second_value = next(it) - except StopIteration: - pass - else: - msg = ( - 'Expected exactly one item in iterable, but got {!r}, {!r}, ' - 'and perhaps more.'.format(first_value, second_value) - ) - raise too_long or ValueError(msg) - - return first_value - - -def raise_(exception, *args): - raise exception(*args) - - -def strictly_n(iterable, n, too_short=None, too_long=None): - """Validate that *iterable* has exactly *n* items and return them if - it does. If it has fewer than *n* items, call function *too_short* - with those items. If it has more than *n* items, call function - *too_long* with the first ``n + 1`` items. - - >>> iterable = ['a', 'b', 'c', 'd'] - >>> n = 4 - >>> list(strictly_n(iterable, n)) - ['a', 'b', 'c', 'd'] - - Note that the returned iterable must be consumed in order for the check to - be made. - - By default, *too_short* and *too_long* are functions that raise - ``ValueError``. - - >>> list(strictly_n('ab', 3)) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - ValueError: too few items in iterable (got 2) - - >>> list(strictly_n('abc', 2)) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - ValueError: too many items in iterable (got at least 3) - - You can instead supply functions that do something else. - *too_short* will be called with the number of items in *iterable*. - *too_long* will be called with `n + 1`. - - >>> def too_short(item_count): - ... raise RuntimeError - >>> it = strictly_n('abcd', 6, too_short=too_short) - >>> list(it) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - RuntimeError - - >>> def too_long(item_count): - ... print('The boss is going to hear about this') - >>> it = strictly_n('abcdef', 4, too_long=too_long) - >>> list(it) - The boss is going to hear about this - ['a', 'b', 'c', 'd'] - - """ - if too_short is None: - too_short = lambda item_count: raise_( - ValueError, - 'Too few items in iterable (got {})'.format(item_count), - ) - - if too_long is None: - too_long = lambda item_count: raise_( - ValueError, - 'Too many items in iterable (got at least {})'.format(item_count), - ) - - it = iter(iterable) - for i in range(n): - try: - item = next(it) - except StopIteration: - too_short(i) - return - else: - yield item - - try: - next(it) - except StopIteration: - pass - else: - too_long(n + 1) - - -def distinct_permutations(iterable, r=None): - """Yield successive distinct permutations of the elements in *iterable*. - - >>> sorted(distinct_permutations([1, 0, 1])) - [(0, 1, 1), (1, 0, 1), (1, 1, 0)] - - Equivalent to ``set(permutations(iterable))``, except duplicates are not - generated and thrown away. For larger input sequences this is much more - efficient. - - Duplicate permutations arise when there are duplicated elements in the - input iterable. The number of items returned is - `n! / (x_1! * x_2! * ... * x_n!)`, where `n` is the total number of - items input, and each `x_i` is the count of a distinct item in the input - sequence. - - If *r* is given, only the *r*-length permutations are yielded. - - >>> sorted(distinct_permutations([1, 0, 1], r=2)) - [(0, 1), (1, 0), (1, 1)] - >>> sorted(distinct_permutations(range(3), r=2)) - [(0, 1), (0, 2), (1, 0), (1, 2), (2, 0), (2, 1)] - - """ - - # Algorithm: https://w.wiki/Qai - def _full(A): - while True: - # Yield the permutation we have - yield tuple(A) - - # Find the largest index i such that A[i] < A[i + 1] - for i in range(size - 2, -1, -1): - if A[i] < A[i + 1]: - break - # If no such index exists, this permutation is the last one - else: - return - - # Find the largest index j greater than j such that A[i] < A[j] - for j in range(size - 1, i, -1): - if A[i] < A[j]: - break - - # Swap the value of A[i] with that of A[j], then reverse the - # sequence from A[i + 1] to form the new permutation - A[i], A[j] = A[j], A[i] - A[i + 1 :] = A[: i - size : -1] # A[i + 1:][::-1] - - # Algorithm: modified from the above - def _partial(A, r): - # Split A into the first r items and the last r items - head, tail = A[:r], A[r:] - right_head_indexes = range(r - 1, -1, -1) - left_tail_indexes = range(len(tail)) - - while True: - # Yield the permutation we have - yield tuple(head) - - # Starting from the right, find the first index of the head with - # value smaller than the maximum value of the tail - call it i. - pivot = tail[-1] - for i in right_head_indexes: - if head[i] < pivot: - break - pivot = head[i] - else: - return - - # Starting from the left, find the first value of the tail - # with a value greater than head[i] and swap. - for j in left_tail_indexes: - if tail[j] > head[i]: - head[i], tail[j] = tail[j], head[i] - break - # If we didn't find one, start from the right and find the first - # index of the head with a value greater than head[i] and swap. - else: - for j in right_head_indexes: - if head[j] > head[i]: - head[i], head[j] = head[j], head[i] - break - - # Reverse head[i + 1:] and swap it with tail[:r - (i + 1)] - tail += head[: i - r : -1] # head[i + 1:][::-1] - i += 1 - head[i:], tail[:] = tail[: r - i], tail[r - i :] - - items = sorted(iterable) - - size = len(items) - if r is None: - r = size - - if 0 < r <= size: - return _full(items) if (r == size) else _partial(items, r) - - return iter(() if r else ((),)) - - -def intersperse(e, iterable, n=1): - """Intersperse filler element *e* among the items in *iterable*, leaving - *n* items between each filler element. - - >>> list(intersperse('!', [1, 2, 3, 4, 5])) - [1, '!', 2, '!', 3, '!', 4, '!', 5] - - >>> list(intersperse(None, [1, 2, 3, 4, 5], n=2)) - [1, 2, None, 3, 4, None, 5] - - """ - if n == 0: - raise ValueError('n must be > 0') - elif n == 1: - # interleave(repeat(e), iterable) -> e, x_0, e, x_1, e, x_2... - # islice(..., 1, None) -> x_0, e, x_1, e, x_2... - return islice(interleave(repeat(e), iterable), 1, None) - else: - # interleave(filler, chunks) -> [e], [x_0, x_1], [e], [x_2, x_3]... - # islice(..., 1, None) -> [x_0, x_1], [e], [x_2, x_3]... - # flatten(...) -> x_0, x_1, e, x_2, x_3... - filler = repeat([e]) - chunks = chunked(iterable, n) - return flatten(islice(interleave(filler, chunks), 1, None)) - - -def unique_to_each(*iterables): - """Return the elements from each of the input iterables that aren't in the - other input iterables. - - For example, suppose you have a set of packages, each with a set of - dependencies:: - - {'pkg_1': {'A', 'B'}, 'pkg_2': {'B', 'C'}, 'pkg_3': {'B', 'D'}} - - If you remove one package, which dependencies can also be removed? - - If ``pkg_1`` is removed, then ``A`` is no longer necessary - it is not - associated with ``pkg_2`` or ``pkg_3``. Similarly, ``C`` is only needed for - ``pkg_2``, and ``D`` is only needed for ``pkg_3``:: - - >>> unique_to_each({'A', 'B'}, {'B', 'C'}, {'B', 'D'}) - [['A'], ['C'], ['D']] - - If there are duplicates in one input iterable that aren't in the others - they will be duplicated in the output. Input order is preserved:: - - >>> unique_to_each("mississippi", "missouri") - [['p', 'p'], ['o', 'u', 'r']] - - It is assumed that the elements of each iterable are hashable. - - """ - pool = [list(it) for it in iterables] - counts = Counter(chain.from_iterable(map(set, pool))) - uniques = {element for element in counts if counts[element] == 1} - return [list(filter(uniques.__contains__, it)) for it in pool] - - -def windowed(seq, n, fillvalue=None, step=1): - """Return a sliding window of width *n* over the given iterable. - - >>> all_windows = windowed([1, 2, 3, 4, 5], 3) - >>> list(all_windows) - [(1, 2, 3), (2, 3, 4), (3, 4, 5)] - - When the window is larger than the iterable, *fillvalue* is used in place - of missing values: - - >>> list(windowed([1, 2, 3], 4)) - [(1, 2, 3, None)] - - Each window will advance in increments of *step*: - - >>> list(windowed([1, 2, 3, 4, 5, 6], 3, fillvalue='!', step=2)) - [(1, 2, 3), (3, 4, 5), (5, 6, '!')] - - To slide into the iterable's items, use :func:`chain` to add filler items - to the left: - - >>> iterable = [1, 2, 3, 4] - >>> n = 3 - >>> padding = [None] * (n - 1) - >>> list(windowed(chain(padding, iterable), 3)) - [(None, None, 1), (None, 1, 2), (1, 2, 3), (2, 3, 4)] - """ - if n < 0: - raise ValueError('n must be >= 0') - if n == 0: - yield () - return - if step < 1: - raise ValueError('step must be >= 1') - - iterable = iter(seq) - - # Generate first window - window = deque(islice(iterable, n), maxlen=n) - - # Deal with the first window not being full - if not window: - return - if len(window) < n: - yield tuple(window) + ((fillvalue,) * (n - len(window))) - return - yield tuple(window) - - # Create the filler for the next windows. The padding ensures - # we have just enough elements to fill the last window. - padding = (fillvalue,) * (n - 1 if step >= n else step - 1) - filler = map(window.append, chain(iterable, padding)) - - # Generate the rest of the windows - for _ in islice(filler, step - 1, None, step): - yield tuple(window) - - -def substrings(iterable): - """Yield all of the substrings of *iterable*. - - >>> [''.join(s) for s in substrings('more')] - ['m', 'o', 'r', 'e', 'mo', 'or', 're', 'mor', 'ore', 'more'] - - Note that non-string iterables can also be subdivided. - - >>> list(substrings([0, 1, 2])) - [(0,), (1,), (2,), (0, 1), (1, 2), (0, 1, 2)] - - """ - # The length-1 substrings - seq = [] - for item in iter(iterable): - seq.append(item) - yield (item,) - seq = tuple(seq) - item_count = len(seq) - - # And the rest - for n in range(2, item_count + 1): - for i in range(item_count - n + 1): - yield seq[i : i + n] - - -def substrings_indexes(seq, reverse=False): - """Yield all substrings and their positions in *seq* - - The items yielded will be a tuple of the form ``(substr, i, j)``, where - ``substr == seq[i:j]``. - - This function only works for iterables that support slicing, such as - ``str`` objects. - - >>> for item in substrings_indexes('more'): - ... print(item) - ('m', 0, 1) - ('o', 1, 2) - ('r', 2, 3) - ('e', 3, 4) - ('mo', 0, 2) - ('or', 1, 3) - ('re', 2, 4) - ('mor', 0, 3) - ('ore', 1, 4) - ('more', 0, 4) - - Set *reverse* to ``True`` to yield the same items in the opposite order. - - - """ - r = range(1, len(seq) + 1) - if reverse: - r = reversed(r) - return ( - (seq[i : i + L], i, i + L) for L in r for i in range(len(seq) - L + 1) - ) - - -class bucket: - """Wrap *iterable* and return an object that buckets the iterable into - child iterables based on a *key* function. - - >>> iterable = ['a1', 'b1', 'c1', 'a2', 'b2', 'c2', 'b3'] - >>> s = bucket(iterable, key=lambda x: x[0]) # Bucket by 1st character - >>> sorted(list(s)) # Get the keys - ['a', 'b', 'c'] - >>> a_iterable = s['a'] - >>> next(a_iterable) - 'a1' - >>> next(a_iterable) - 'a2' - >>> list(s['b']) - ['b1', 'b2', 'b3'] - - The original iterable will be advanced and its items will be cached until - they are used by the child iterables. This may require significant storage. - - By default, attempting to select a bucket to which no items belong will - exhaust the iterable and cache all values. - If you specify a *validator* function, selected buckets will instead be - checked against it. - - >>> from itertools import count - >>> it = count(1, 2) # Infinite sequence of odd numbers - >>> key = lambda x: x % 10 # Bucket by last digit - >>> validator = lambda x: x in {1, 3, 5, 7, 9} # Odd digits only - >>> s = bucket(it, key=key, validator=validator) - >>> 2 in s - False - >>> list(s[2]) - [] - - """ - - def __init__(self, iterable, key, validator=None): - self._it = iter(iterable) - self._key = key - self._cache = defaultdict(deque) - self._validator = validator or (lambda x: True) - - def __contains__(self, value): - if not self._validator(value): - return False - - try: - item = next(self[value]) - except StopIteration: - return False - else: - self._cache[value].appendleft(item) - - return True - - def _get_values(self, value): - """ - Helper to yield items from the parent iterator that match *value*. - Items that don't match are stored in the local cache as they - are encountered. - """ - while True: - # If we've cached some items that match the target value, emit - # the first one and evict it from the cache. - if self._cache[value]: - yield self._cache[value].popleft() - # Otherwise we need to advance the parent iterator to search for - # a matching item, caching the rest. - else: - while True: - try: - item = next(self._it) - except StopIteration: - return - item_value = self._key(item) - if item_value == value: - yield item - break - elif self._validator(item_value): - self._cache[item_value].append(item) - - def __iter__(self): - for item in self._it: - item_value = self._key(item) - if self._validator(item_value): - self._cache[item_value].append(item) - - yield from self._cache.keys() - - def __getitem__(self, value): - if not self._validator(value): - return iter(()) - - return self._get_values(value) - - -def spy(iterable, n=1): - """Return a 2-tuple with a list containing the first *n* elements of - *iterable*, and an iterator with the same items as *iterable*. - This allows you to "look ahead" at the items in the iterable without - advancing it. - - There is one item in the list by default: - - >>> iterable = 'abcdefg' - >>> head, iterable = spy(iterable) - >>> head - ['a'] - >>> list(iterable) - ['a', 'b', 'c', 'd', 'e', 'f', 'g'] - - You may use unpacking to retrieve items instead of lists: - - >>> (head,), iterable = spy('abcdefg') - >>> head - 'a' - >>> (first, second), iterable = spy('abcdefg', 2) - >>> first - 'a' - >>> second - 'b' - - The number of items requested can be larger than the number of items in - the iterable: - - >>> iterable = [1, 2, 3, 4, 5] - >>> head, iterable = spy(iterable, 10) - >>> head - [1, 2, 3, 4, 5] - >>> list(iterable) - [1, 2, 3, 4, 5] - - """ - it = iter(iterable) - head = take(n, it) - - return head.copy(), chain(head, it) - - -def interleave(*iterables): - """Return a new iterable yielding from each iterable in turn, - until the shortest is exhausted. - - >>> list(interleave([1, 2, 3], [4, 5], [6, 7, 8])) - [1, 4, 6, 2, 5, 7] - - For a version that doesn't terminate after the shortest iterable is - exhausted, see :func:`interleave_longest`. - - """ - return chain.from_iterable(zip(*iterables)) - - -def interleave_longest(*iterables): - """Return a new iterable yielding from each iterable in turn, - skipping any that are exhausted. - - >>> list(interleave_longest([1, 2, 3], [4, 5], [6, 7, 8])) - [1, 4, 6, 2, 5, 7, 3, 8] - - This function produces the same output as :func:`roundrobin`, but may - perform better for some inputs (in particular when the number of iterables - is large). - - """ - i = chain.from_iterable(zip_longest(*iterables, fillvalue=_marker)) - return (x for x in i if x is not _marker) - - -def interleave_evenly(iterables, lengths=None): - """ - Interleave multiple iterables so that their elements are evenly distributed - throughout the output sequence. - - >>> iterables = [1, 2, 3, 4, 5], ['a', 'b'] - >>> list(interleave_evenly(iterables)) - [1, 2, 'a', 3, 4, 'b', 5] - - >>> iterables = [[1, 2, 3], [4, 5], [6, 7, 8]] - >>> list(interleave_evenly(iterables)) - [1, 6, 4, 2, 7, 3, 8, 5] - - This function requires iterables of known length. Iterables without - ``__len__()`` can be used by manually specifying lengths with *lengths*: - - >>> from itertools import combinations, repeat - >>> iterables = [combinations(range(4), 2), ['a', 'b', 'c']] - >>> lengths = [4 * (4 - 1) // 2, 3] - >>> list(interleave_evenly(iterables, lengths=lengths)) - [(0, 1), (0, 2), 'a', (0, 3), (1, 2), 'b', (1, 3), (2, 3), 'c'] - - Based on Bresenham's algorithm. - """ - if lengths is None: - try: - lengths = [len(it) for it in iterables] - except TypeError: - raise ValueError( - 'Iterable lengths could not be determined automatically. ' - 'Specify them with the lengths keyword.' - ) - elif len(iterables) != len(lengths): - raise ValueError('Mismatching number of iterables and lengths.') - - dims = len(lengths) - - # sort iterables by length, descending - lengths_permute = sorted( - range(dims), key=lambda i: lengths[i], reverse=True - ) - lengths_desc = [lengths[i] for i in lengths_permute] - iters_desc = [iter(iterables[i]) for i in lengths_permute] - - # the longest iterable is the primary one (Bresenham: the longest - # distance along an axis) - delta_primary, deltas_secondary = lengths_desc[0], lengths_desc[1:] - iter_primary, iters_secondary = iters_desc[0], iters_desc[1:] - errors = [delta_primary // dims] * len(deltas_secondary) - - to_yield = sum(lengths) - while to_yield: - yield next(iter_primary) - to_yield -= 1 - # update errors for each secondary iterable - errors = [e - delta for e, delta in zip(errors, deltas_secondary)] - - # those iterables for which the error is negative are yielded - # ("diagonal step" in Bresenham) - for i, e_ in enumerate(errors): - if e_ < 0: - yield next(iters_secondary[i]) - to_yield -= 1 - errors[i] += delta_primary - - -def collapse(iterable, base_type=None, levels=None): - """Flatten an iterable with multiple levels of nesting (e.g., a list of - lists of tuples) into non-iterable types. - - >>> iterable = [(1, 2), ([3, 4], [[5], [6]])] - >>> list(collapse(iterable)) - [1, 2, 3, 4, 5, 6] - - Binary and text strings are not considered iterable and - will not be collapsed. - - To avoid collapsing other types, specify *base_type*: - - >>> iterable = ['ab', ('cd', 'ef'), ['gh', 'ij']] - >>> list(collapse(iterable, base_type=tuple)) - ['ab', ('cd', 'ef'), 'gh', 'ij'] - - Specify *levels* to stop flattening after a certain level: - - >>> iterable = [('a', ['b']), ('c', ['d'])] - >>> list(collapse(iterable)) # Fully flattened - ['a', 'b', 'c', 'd'] - >>> list(collapse(iterable, levels=1)) # Only one level flattened - ['a', ['b'], 'c', ['d']] - - """ - stack = deque() - # Add our first node group, treat the iterable as a single node - stack.appendleft((0, repeat(iterable, 1))) - - while stack: - node_group = stack.popleft() - level, nodes = node_group - - # Check if beyond max level - if levels is not None and level > levels: - yield from nodes - continue - - for node in nodes: - # Check if done iterating - if isinstance(node, (str, bytes)) or ( - (base_type is not None) and isinstance(node, base_type) - ): - yield node - # Otherwise try to create child nodes - else: - try: - tree = iter(node) - except TypeError: - yield node - else: - # Save our current location - stack.appendleft(node_group) - # Append the new child node - stack.appendleft((level + 1, tree)) - # Break to process child node - break - - -def side_effect(func, iterable, chunk_size=None, before=None, after=None): - """Invoke *func* on each item in *iterable* (or on each *chunk_size* group - of items) before yielding the item. - - `func` must be a function that takes a single argument. Its return value - will be discarded. - - *before* and *after* are optional functions that take no arguments. They - will be executed before iteration starts and after it ends, respectively. - - `side_effect` can be used for logging, updating progress bars, or anything - that is not functionally "pure." - - Emitting a status message: - - >>> from more_itertools import consume - >>> func = lambda item: print('Received {}'.format(item)) - >>> consume(side_effect(func, range(2))) - Received 0 - Received 1 - - Operating on chunks of items: - - >>> pair_sums = [] - >>> func = lambda chunk: pair_sums.append(sum(chunk)) - >>> list(side_effect(func, [0, 1, 2, 3, 4, 5], 2)) - [0, 1, 2, 3, 4, 5] - >>> list(pair_sums) - [1, 5, 9] - - Writing to a file-like object: - - >>> from io import StringIO - >>> from more_itertools import consume - >>> f = StringIO() - >>> func = lambda x: print(x, file=f) - >>> before = lambda: print(u'HEADER', file=f) - >>> after = f.close - >>> it = [u'a', u'b', u'c'] - >>> consume(side_effect(func, it, before=before, after=after)) - >>> f.closed - True - - """ - try: - if before is not None: - before() - - if chunk_size is None: - for item in iterable: - func(item) - yield item - else: - for chunk in chunked(iterable, chunk_size): - func(chunk) - yield from chunk - finally: - if after is not None: - after() - - -def sliced(seq, n, strict=False): - """Yield slices of length *n* from the sequence *seq*. - - >>> list(sliced((1, 2, 3, 4, 5, 6), 3)) - [(1, 2, 3), (4, 5, 6)] - - By the default, the last yielded slice will have fewer than *n* elements - if the length of *seq* is not divisible by *n*: - - >>> list(sliced((1, 2, 3, 4, 5, 6, 7, 8), 3)) - [(1, 2, 3), (4, 5, 6), (7, 8)] - - If the length of *seq* is not divisible by *n* and *strict* is - ``True``, then ``ValueError`` will be raised before the last - slice is yielded. - - This function will only work for iterables that support slicing. - For non-sliceable iterables, see :func:`chunked`. - - """ - iterator = takewhile(len, (seq[i : i + n] for i in count(0, n))) - if strict: - - def ret(): - for _slice in iterator: - if len(_slice) != n: - raise ValueError("seq is not divisible by n.") - yield _slice - - return iter(ret()) - else: - return iterator - - -def split_at(iterable, pred, maxsplit=-1, keep_separator=False): - """Yield lists of items from *iterable*, where each list is delimited by - an item where callable *pred* returns ``True``. - - >>> list(split_at('abcdcba', lambda x: x == 'b')) - [['a'], ['c', 'd', 'c'], ['a']] - - >>> list(split_at(range(10), lambda n: n % 2 == 1)) - [[0], [2], [4], [6], [8], []] - - At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, - then there is no limit on the number of splits: - - >>> list(split_at(range(10), lambda n: n % 2 == 1, maxsplit=2)) - [[0], [2], [4, 5, 6, 7, 8, 9]] - - By default, the delimiting items are not included in the output. - To include them, set *keep_separator* to ``True``. - - >>> list(split_at('abcdcba', lambda x: x == 'b', keep_separator=True)) - [['a'], ['b'], ['c', 'd', 'c'], ['b'], ['a']] - - """ - if maxsplit == 0: - yield list(iterable) - return - - buf = [] - it = iter(iterable) - for item in it: - if pred(item): - yield buf - if keep_separator: - yield [item] - if maxsplit == 1: - yield list(it) - return - buf = [] - maxsplit -= 1 - else: - buf.append(item) - yield buf - - -def split_before(iterable, pred, maxsplit=-1): - """Yield lists of items from *iterable*, where each list ends just before - an item for which callable *pred* returns ``True``: - - >>> list(split_before('OneTwo', lambda s: s.isupper())) - [['O', 'n', 'e'], ['T', 'w', 'o']] - - >>> list(split_before(range(10), lambda n: n % 3 == 0)) - [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]] - - At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, - then there is no limit on the number of splits: - - >>> list(split_before(range(10), lambda n: n % 3 == 0, maxsplit=2)) - [[0, 1, 2], [3, 4, 5], [6, 7, 8, 9]] - """ - if maxsplit == 0: - yield list(iterable) - return - - buf = [] - it = iter(iterable) - for item in it: - if pred(item) and buf: - yield buf - if maxsplit == 1: - yield [item] + list(it) - return - buf = [] - maxsplit -= 1 - buf.append(item) - if buf: - yield buf - - -def split_after(iterable, pred, maxsplit=-1): - """Yield lists of items from *iterable*, where each list ends with an - item where callable *pred* returns ``True``: - - >>> list(split_after('one1two2', lambda s: s.isdigit())) - [['o', 'n', 'e', '1'], ['t', 'w', 'o', '2']] - - >>> list(split_after(range(10), lambda n: n % 3 == 0)) - [[0], [1, 2, 3], [4, 5, 6], [7, 8, 9]] - - At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, - then there is no limit on the number of splits: - - >>> list(split_after(range(10), lambda n: n % 3 == 0, maxsplit=2)) - [[0], [1, 2, 3], [4, 5, 6, 7, 8, 9]] - - """ - if maxsplit == 0: - yield list(iterable) - return - - buf = [] - it = iter(iterable) - for item in it: - buf.append(item) - if pred(item) and buf: - yield buf - if maxsplit == 1: - buf = list(it) - if buf: - yield buf - return - buf = [] - maxsplit -= 1 - if buf: - yield buf - - -def split_when(iterable, pred, maxsplit=-1): - """Split *iterable* into pieces based on the output of *pred*. - *pred* should be a function that takes successive pairs of items and - returns ``True`` if the iterable should be split in between them. - - For example, to find runs of increasing numbers, split the iterable when - element ``i`` is larger than element ``i + 1``: - - >>> list(split_when([1, 2, 3, 3, 2, 5, 2, 4, 2], lambda x, y: x > y)) - [[1, 2, 3, 3], [2, 5], [2, 4], [2]] - - At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, - then there is no limit on the number of splits: - - >>> list(split_when([1, 2, 3, 3, 2, 5, 2, 4, 2], - ... lambda x, y: x > y, maxsplit=2)) - [[1, 2, 3, 3], [2, 5], [2, 4, 2]] - - """ - if maxsplit == 0: - yield list(iterable) - return - - it = iter(iterable) - try: - cur_item = next(it) - except StopIteration: - return - - buf = [cur_item] - for next_item in it: - if pred(cur_item, next_item): - yield buf - if maxsplit == 1: - yield [next_item] + list(it) - return - buf = [] - maxsplit -= 1 - - buf.append(next_item) - cur_item = next_item - - yield buf - - -def split_into(iterable, sizes): - """Yield a list of sequential items from *iterable* of length 'n' for each - integer 'n' in *sizes*. - - >>> list(split_into([1,2,3,4,5,6], [1,2,3])) - [[1], [2, 3], [4, 5, 6]] - - If the sum of *sizes* is smaller than the length of *iterable*, then the - remaining items of *iterable* will not be returned. - - >>> list(split_into([1,2,3,4,5,6], [2,3])) - [[1, 2], [3, 4, 5]] - - If the sum of *sizes* is larger than the length of *iterable*, fewer items - will be returned in the iteration that overruns *iterable* and further - lists will be empty: - - >>> list(split_into([1,2,3,4], [1,2,3,4])) - [[1], [2, 3], [4], []] - - When a ``None`` object is encountered in *sizes*, the returned list will - contain items up to the end of *iterable* the same way that itertools.slice - does: - - >>> list(split_into([1,2,3,4,5,6,7,8,9,0], [2,3,None])) - [[1, 2], [3, 4, 5], [6, 7, 8, 9, 0]] - - :func:`split_into` can be useful for grouping a series of items where the - sizes of the groups are not uniform. An example would be where in a row - from a table, multiple columns represent elements of the same feature - (e.g. a point represented by x,y,z) but, the format is not the same for - all columns. - """ - # convert the iterable argument into an iterator so its contents can - # be consumed by islice in case it is a generator - it = iter(iterable) - - for size in sizes: - if size is None: - yield list(it) - return - else: - yield list(islice(it, size)) - - -def padded(iterable, fillvalue=None, n=None, next_multiple=False): - """Yield the elements from *iterable*, followed by *fillvalue*, such that - at least *n* items are emitted. - - >>> list(padded([1, 2, 3], '?', 5)) - [1, 2, 3, '?', '?'] - - If *next_multiple* is ``True``, *fillvalue* will be emitted until the - number of items emitted is a multiple of *n*: - - >>> list(padded([1, 2, 3, 4], n=3, next_multiple=True)) - [1, 2, 3, 4, None, None] - - If *n* is ``None``, *fillvalue* will be emitted indefinitely. - - To create an *iterable* of exactly size *n*, you can truncate with - :func:`islice`. - - >>> list(islice(padded([1, 2, 3], '?'), 5)) - [1, 2, 3, '?', '?'] - >>> list(islice(padded([1, 2, 3, 4, 5, 6, 7, 8], '?'), 5)) - [1, 2, 3, 4, 5] - - """ - iterable = iter(iterable) - iterable_with_repeat = chain(iterable, repeat(fillvalue)) - - if n is None: - return iterable_with_repeat - elif n < 1: - raise ValueError('n must be at least 1') - elif next_multiple: - - def slice_generator(): - for first in iterable: - yield (first,) - yield islice(iterable_with_repeat, n - 1) - - # While elements exist produce slices of size n - return chain.from_iterable(slice_generator()) - else: - # Ensure the first batch is at least size n then iterate - return chain(islice(iterable_with_repeat, n), iterable) - - -def repeat_each(iterable, n=2): - """Repeat each element in *iterable* *n* times. - - >>> list(repeat_each('ABC', 3)) - ['A', 'A', 'A', 'B', 'B', 'B', 'C', 'C', 'C'] - """ - return chain.from_iterable(map(repeat, iterable, repeat(n))) - - -def repeat_last(iterable, default=None): - """After the *iterable* is exhausted, keep yielding its last element. - - >>> list(islice(repeat_last(range(3)), 5)) - [0, 1, 2, 2, 2] - - If the iterable is empty, yield *default* forever:: - - >>> list(islice(repeat_last(range(0), 42), 5)) - [42, 42, 42, 42, 42] - - """ - item = _marker - for item in iterable: - yield item - final = default if item is _marker else item - yield from repeat(final) - - -def distribute(n, iterable): - """Distribute the items from *iterable* among *n* smaller iterables. - - >>> group_1, group_2 = distribute(2, [1, 2, 3, 4, 5, 6]) - >>> list(group_1) - [1, 3, 5] - >>> list(group_2) - [2, 4, 6] - - If the length of *iterable* is not evenly divisible by *n*, then the - length of the returned iterables will not be identical: - - >>> children = distribute(3, [1, 2, 3, 4, 5, 6, 7]) - >>> [list(c) for c in children] - [[1, 4, 7], [2, 5], [3, 6]] - - If the length of *iterable* is smaller than *n*, then the last returned - iterables will be empty: - - >>> children = distribute(5, [1, 2, 3]) - >>> [list(c) for c in children] - [[1], [2], [3], [], []] - - This function uses :func:`itertools.tee` and may require significant - storage. - - If you need the order items in the smaller iterables to match the - original iterable, see :func:`divide`. - - """ - if n < 1: - raise ValueError('n must be at least 1') - - children = tee(iterable, n) - return [islice(it, index, None, n) for index, it in enumerate(children)] - - -def stagger(iterable, offsets=(-1, 0, 1), longest=False, fillvalue=None): - """Yield tuples whose elements are offset from *iterable*. - The amount by which the `i`-th item in each tuple is offset is given by - the `i`-th item in *offsets*. - - >>> list(stagger([0, 1, 2, 3])) - [(None, 0, 1), (0, 1, 2), (1, 2, 3)] - >>> list(stagger(range(8), offsets=(0, 2, 4))) - [(0, 2, 4), (1, 3, 5), (2, 4, 6), (3, 5, 7)] - - By default, the sequence will end when the final element of a tuple is the - last item in the iterable. To continue until the first element of a tuple - is the last item in the iterable, set *longest* to ``True``:: - - >>> list(stagger([0, 1, 2, 3], longest=True)) - [(None, 0, 1), (0, 1, 2), (1, 2, 3), (2, 3, None), (3, None, None)] - - By default, ``None`` will be used to replace offsets beyond the end of the - sequence. Specify *fillvalue* to use some other value. - - """ - children = tee(iterable, len(offsets)) - - return zip_offset( - *children, offsets=offsets, longest=longest, fillvalue=fillvalue - ) - - -def zip_equal(*iterables): - """``zip`` the input *iterables* together, but raise - ``UnequalIterablesError`` if they aren't all the same length. - - >>> it_1 = range(3) - >>> it_2 = iter('abc') - >>> list(zip_equal(it_1, it_2)) - [(0, 'a'), (1, 'b'), (2, 'c')] - - >>> it_1 = range(3) - >>> it_2 = iter('abcd') - >>> list(zip_equal(it_1, it_2)) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - more_itertools.more.UnequalIterablesError: Iterables have different - lengths - - """ - if hexversion >= 0x30A00A6: - warnings.warn( - ( - 'zip_equal will be removed in a future version of ' - 'more-itertools. Use the builtin zip function with ' - 'strict=True instead.' - ), - DeprecationWarning, - ) - - return _zip_equal(*iterables) - - -def zip_offset(*iterables, offsets, longest=False, fillvalue=None): - """``zip`` the input *iterables* together, but offset the `i`-th iterable - by the `i`-th item in *offsets*. - - >>> list(zip_offset('0123', 'abcdef', offsets=(0, 1))) - [('0', 'b'), ('1', 'c'), ('2', 'd'), ('3', 'e')] - - This can be used as a lightweight alternative to SciPy or pandas to analyze - data sets in which some series have a lead or lag relationship. - - By default, the sequence will end when the shortest iterable is exhausted. - To continue until the longest iterable is exhausted, set *longest* to - ``True``. - - >>> list(zip_offset('0123', 'abcdef', offsets=(0, 1), longest=True)) - [('0', 'b'), ('1', 'c'), ('2', 'd'), ('3', 'e'), (None, 'f')] - - By default, ``None`` will be used to replace offsets beyond the end of the - sequence. Specify *fillvalue* to use some other value. - - """ - if len(iterables) != len(offsets): - raise ValueError("Number of iterables and offsets didn't match") - - staggered = [] - for it, n in zip(iterables, offsets): - if n < 0: - staggered.append(chain(repeat(fillvalue, -n), it)) - elif n > 0: - staggered.append(islice(it, n, None)) - else: - staggered.append(it) - - if longest: - return zip_longest(*staggered, fillvalue=fillvalue) - - return zip(*staggered) - - -def sort_together(iterables, key_list=(0,), key=None, reverse=False): - """Return the input iterables sorted together, with *key_list* as the - priority for sorting. All iterables are trimmed to the length of the - shortest one. - - This can be used like the sorting function in a spreadsheet. If each - iterable represents a column of data, the key list determines which - columns are used for sorting. - - By default, all iterables are sorted using the ``0``-th iterable:: - - >>> iterables = [(4, 3, 2, 1), ('a', 'b', 'c', 'd')] - >>> sort_together(iterables) - [(1, 2, 3, 4), ('d', 'c', 'b', 'a')] - - Set a different key list to sort according to another iterable. - Specifying multiple keys dictates how ties are broken:: - - >>> iterables = [(3, 1, 2), (0, 1, 0), ('c', 'b', 'a')] - >>> sort_together(iterables, key_list=(1, 2)) - [(2, 3, 1), (0, 0, 1), ('a', 'c', 'b')] - - To sort by a function of the elements of the iterable, pass a *key* - function. Its arguments are the elements of the iterables corresponding to - the key list:: - - >>> names = ('a', 'b', 'c') - >>> lengths = (1, 2, 3) - >>> widths = (5, 2, 1) - >>> def area(length, width): - ... return length * width - >>> sort_together([names, lengths, widths], key_list=(1, 2), key=area) - [('c', 'b', 'a'), (3, 2, 1), (1, 2, 5)] - - Set *reverse* to ``True`` to sort in descending order. - - >>> sort_together([(1, 2, 3), ('c', 'b', 'a')], reverse=True) - [(3, 2, 1), ('a', 'b', 'c')] - - """ - if key is None: - # if there is no key function, the key argument to sorted is an - # itemgetter - key_argument = itemgetter(*key_list) - else: - # if there is a key function, call it with the items at the offsets - # specified by the key function as arguments - key_list = list(key_list) - if len(key_list) == 1: - # if key_list contains a single item, pass the item at that offset - # as the only argument to the key function - key_offset = key_list[0] - key_argument = lambda zipped_items: key(zipped_items[key_offset]) - else: - # if key_list contains multiple items, use itemgetter to return a - # tuple of items, which we pass as *args to the key function - get_key_items = itemgetter(*key_list) - key_argument = lambda zipped_items: key( - *get_key_items(zipped_items) - ) - - return list( - zip(*sorted(zip(*iterables), key=key_argument, reverse=reverse)) - ) - - -def unzip(iterable): - """The inverse of :func:`zip`, this function disaggregates the elements - of the zipped *iterable*. - - The ``i``-th iterable contains the ``i``-th element from each element - of the zipped iterable. The first element is used to determine the - length of the remaining elements. - - >>> iterable = [('a', 1), ('b', 2), ('c', 3), ('d', 4)] - >>> letters, numbers = unzip(iterable) - >>> list(letters) - ['a', 'b', 'c', 'd'] - >>> list(numbers) - [1, 2, 3, 4] - - This is similar to using ``zip(*iterable)``, but it avoids reading - *iterable* into memory. Note, however, that this function uses - :func:`itertools.tee` and thus may require significant storage. - - """ - head, iterable = spy(iter(iterable)) - if not head: - # empty iterable, e.g. zip([], [], []) - return () - # spy returns a one-length iterable as head - head = head[0] - iterables = tee(iterable, len(head)) - - def itemgetter(i): - def getter(obj): - try: - return obj[i] - except IndexError: - # basically if we have an iterable like - # iter([(1, 2, 3), (4, 5), (6,)]) - # the second unzipped iterable would fail at the third tuple - # since it would try to access tup[1] - # same with the third unzipped iterable and the second tuple - # to support these "improperly zipped" iterables, - # we create a custom itemgetter - # which just stops the unzipped iterables - # at first length mismatch - raise StopIteration - - return getter - - return tuple(map(itemgetter(i), it) for i, it in enumerate(iterables)) - - -def divide(n, iterable): - """Divide the elements from *iterable* into *n* parts, maintaining - order. - - >>> group_1, group_2 = divide(2, [1, 2, 3, 4, 5, 6]) - >>> list(group_1) - [1, 2, 3] - >>> list(group_2) - [4, 5, 6] - - If the length of *iterable* is not evenly divisible by *n*, then the - length of the returned iterables will not be identical: - - >>> children = divide(3, [1, 2, 3, 4, 5, 6, 7]) - >>> [list(c) for c in children] - [[1, 2, 3], [4, 5], [6, 7]] - - If the length of the iterable is smaller than n, then the last returned - iterables will be empty: - - >>> children = divide(5, [1, 2, 3]) - >>> [list(c) for c in children] - [[1], [2], [3], [], []] - - This function will exhaust the iterable before returning. - If order is not important, see :func:`distribute`, which does not first - pull the iterable into memory. - - """ - if n < 1: - raise ValueError('n must be at least 1') - - try: - iterable[:0] - except TypeError: - seq = tuple(iterable) - else: - seq = iterable - - q, r = divmod(len(seq), n) - - ret = [] - stop = 0 - for i in range(1, n + 1): - start = stop - stop += q + 1 if i <= r else q - ret.append(iter(seq[start:stop])) - - return ret - - -def always_iterable(obj, base_type=(str, bytes)): - """If *obj* is iterable, return an iterator over its items:: - - >>> obj = (1, 2, 3) - >>> list(always_iterable(obj)) - [1, 2, 3] - - If *obj* is not iterable, return a one-item iterable containing *obj*:: - - >>> obj = 1 - >>> list(always_iterable(obj)) - [1] - - If *obj* is ``None``, return an empty iterable: - - >>> obj = None - >>> list(always_iterable(None)) - [] - - By default, binary and text strings are not considered iterable:: - - >>> obj = 'foo' - >>> list(always_iterable(obj)) - ['foo'] - - If *base_type* is set, objects for which ``isinstance(obj, base_type)`` - returns ``True`` won't be considered iterable. - - >>> obj = {'a': 1} - >>> list(always_iterable(obj)) # Iterate over the dict's keys - ['a'] - >>> list(always_iterable(obj, base_type=dict)) # Treat dicts as a unit - [{'a': 1}] - - Set *base_type* to ``None`` to avoid any special handling and treat objects - Python considers iterable as iterable: - - >>> obj = 'foo' - >>> list(always_iterable(obj, base_type=None)) - ['f', 'o', 'o'] - """ - if obj is None: - return iter(()) - - if (base_type is not None) and isinstance(obj, base_type): - return iter((obj,)) - - try: - return iter(obj) - except TypeError: - return iter((obj,)) - - -def adjacent(predicate, iterable, distance=1): - """Return an iterable over `(bool, item)` tuples where the `item` is - drawn from *iterable* and the `bool` indicates whether - that item satisfies the *predicate* or is adjacent to an item that does. - - For example, to find whether items are adjacent to a ``3``:: - - >>> list(adjacent(lambda x: x == 3, range(6))) - [(False, 0), (False, 1), (True, 2), (True, 3), (True, 4), (False, 5)] - - Set *distance* to change what counts as adjacent. For example, to find - whether items are two places away from a ``3``: - - >>> list(adjacent(lambda x: x == 3, range(6), distance=2)) - [(False, 0), (True, 1), (True, 2), (True, 3), (True, 4), (True, 5)] - - This is useful for contextualizing the results of a search function. - For example, a code comparison tool might want to identify lines that - have changed, but also surrounding lines to give the viewer of the diff - context. - - The predicate function will only be called once for each item in the - iterable. - - See also :func:`groupby_transform`, which can be used with this function - to group ranges of items with the same `bool` value. - - """ - # Allow distance=0 mainly for testing that it reproduces results with map() - if distance < 0: - raise ValueError('distance must be at least 0') - - i1, i2 = tee(iterable) - padding = [False] * distance - selected = chain(padding, map(predicate, i1), padding) - adjacent_to_selected = map(any, windowed(selected, 2 * distance + 1)) - return zip(adjacent_to_selected, i2) - - -def groupby_transform(iterable, keyfunc=None, valuefunc=None, reducefunc=None): - """An extension of :func:`itertools.groupby` that can apply transformations - to the grouped data. - - * *keyfunc* is a function computing a key value for each item in *iterable* - * *valuefunc* is a function that transforms the individual items from - *iterable* after grouping - * *reducefunc* is a function that transforms each group of items - - >>> iterable = 'aAAbBBcCC' - >>> keyfunc = lambda k: k.upper() - >>> valuefunc = lambda v: v.lower() - >>> reducefunc = lambda g: ''.join(g) - >>> list(groupby_transform(iterable, keyfunc, valuefunc, reducefunc)) - [('A', 'aaa'), ('B', 'bbb'), ('C', 'ccc')] - - Each optional argument defaults to an identity function if not specified. - - :func:`groupby_transform` is useful when grouping elements of an iterable - using a separate iterable as the key. To do this, :func:`zip` the iterables - and pass a *keyfunc* that extracts the first element and a *valuefunc* - that extracts the second element:: - - >>> from operator import itemgetter - >>> keys = [0, 0, 1, 1, 1, 2, 2, 2, 3] - >>> values = 'abcdefghi' - >>> iterable = zip(keys, values) - >>> grouper = groupby_transform(iterable, itemgetter(0), itemgetter(1)) - >>> [(k, ''.join(g)) for k, g in grouper] - [(0, 'ab'), (1, 'cde'), (2, 'fgh'), (3, 'i')] - - Note that the order of items in the iterable is significant. - Only adjacent items are grouped together, so if you don't want any - duplicate groups, you should sort the iterable by the key function. - - """ - ret = groupby(iterable, keyfunc) - if valuefunc: - ret = ((k, map(valuefunc, g)) for k, g in ret) - if reducefunc: - ret = ((k, reducefunc(g)) for k, g in ret) - - return ret - - -class numeric_range(abc.Sequence, abc.Hashable): - """An extension of the built-in ``range()`` function whose arguments can - be any orderable numeric type. - - With only *stop* specified, *start* defaults to ``0`` and *step* - defaults to ``1``. The output items will match the type of *stop*: - - >>> list(numeric_range(3.5)) - [0.0, 1.0, 2.0, 3.0] - - With only *start* and *stop* specified, *step* defaults to ``1``. The - output items will match the type of *start*: - - >>> from decimal import Decimal - >>> start = Decimal('2.1') - >>> stop = Decimal('5.1') - >>> list(numeric_range(start, stop)) - [Decimal('2.1'), Decimal('3.1'), Decimal('4.1')] - - With *start*, *stop*, and *step* specified the output items will match - the type of ``start + step``: - - >>> from fractions import Fraction - >>> start = Fraction(1, 2) # Start at 1/2 - >>> stop = Fraction(5, 2) # End at 5/2 - >>> step = Fraction(1, 2) # Count by 1/2 - >>> list(numeric_range(start, stop, step)) - [Fraction(1, 2), Fraction(1, 1), Fraction(3, 2), Fraction(2, 1)] - - If *step* is zero, ``ValueError`` is raised. Negative steps are supported: - - >>> list(numeric_range(3, -1, -1.0)) - [3.0, 2.0, 1.0, 0.0] - - Be aware of the limitations of floating point numbers; the representation - of the yielded numbers may be surprising. - - ``datetime.datetime`` objects can be used for *start* and *stop*, if *step* - is a ``datetime.timedelta`` object: - - >>> import datetime - >>> start = datetime.datetime(2019, 1, 1) - >>> stop = datetime.datetime(2019, 1, 3) - >>> step = datetime.timedelta(days=1) - >>> items = iter(numeric_range(start, stop, step)) - >>> next(items) - datetime.datetime(2019, 1, 1, 0, 0) - >>> next(items) - datetime.datetime(2019, 1, 2, 0, 0) - - """ - - _EMPTY_HASH = hash(range(0, 0)) - - def __init__(self, *args): - argc = len(args) - if argc == 1: - (self._stop,) = args - self._start = type(self._stop)(0) - self._step = type(self._stop - self._start)(1) - elif argc == 2: - self._start, self._stop = args - self._step = type(self._stop - self._start)(1) - elif argc == 3: - self._start, self._stop, self._step = args - elif argc == 0: - raise TypeError( - 'numeric_range expected at least ' - '1 argument, got {}'.format(argc) - ) - else: - raise TypeError( - 'numeric_range expected at most ' - '3 arguments, got {}'.format(argc) - ) - - self._zero = type(self._step)(0) - if self._step == self._zero: - raise ValueError('numeric_range() arg 3 must not be zero') - self._growing = self._step > self._zero - - def __bool__(self): - if self._growing: - return self._start < self._stop - else: - return self._start > self._stop - - def __contains__(self, elem): - if self._growing: - if self._start <= elem < self._stop: - return (elem - self._start) % self._step == self._zero - else: - if self._start >= elem > self._stop: - return (self._start - elem) % (-self._step) == self._zero - - return False - - def __eq__(self, other): - if isinstance(other, numeric_range): - empty_self = not bool(self) - empty_other = not bool(other) - if empty_self or empty_other: - return empty_self and empty_other # True if both empty - else: - return ( - self._start == other._start - and self._step == other._step - and self._get_by_index(-1) == other._get_by_index(-1) - ) - else: - return False - - def __getitem__(self, key): - if isinstance(key, int): - return self._get_by_index(key) - elif isinstance(key, slice): - step = self._step if key.step is None else key.step * self._step - - if key.start is None or key.start <= -self._len: - start = self._start - elif key.start >= self._len: - start = self._stop - else: # -self._len < key.start < self._len - start = self._get_by_index(key.start) - - if key.stop is None or key.stop >= self._len: - stop = self._stop - elif key.stop <= -self._len: - stop = self._start - else: # -self._len < key.stop < self._len - stop = self._get_by_index(key.stop) - - return numeric_range(start, stop, step) - else: - raise TypeError( - 'numeric range indices must be ' - 'integers or slices, not {}'.format(type(key).__name__) - ) - - def __hash__(self): - if self: - return hash((self._start, self._get_by_index(-1), self._step)) - else: - return self._EMPTY_HASH - - def __iter__(self): - values = (self._start + (n * self._step) for n in count()) - if self._growing: - return takewhile(partial(gt, self._stop), values) - else: - return takewhile(partial(lt, self._stop), values) - - def __len__(self): - return self._len - - @cached_property - def _len(self): - if self._growing: - start = self._start - stop = self._stop - step = self._step - else: - start = self._stop - stop = self._start - step = -self._step - distance = stop - start - if distance <= self._zero: - return 0 - else: # distance > 0 and step > 0: regular euclidean division - q, r = divmod(distance, step) - return int(q) + int(r != self._zero) - - def __reduce__(self): - return numeric_range, (self._start, self._stop, self._step) - - def __repr__(self): - if self._step == 1: - return "numeric_range({}, {})".format( - repr(self._start), repr(self._stop) - ) - else: - return "numeric_range({}, {}, {})".format( - repr(self._start), repr(self._stop), repr(self._step) - ) - - def __reversed__(self): - return iter( - numeric_range( - self._get_by_index(-1), self._start - self._step, -self._step - ) - ) - - def count(self, value): - return int(value in self) - - def index(self, value): - if self._growing: - if self._start <= value < self._stop: - q, r = divmod(value - self._start, self._step) - if r == self._zero: - return int(q) - else: - if self._start >= value > self._stop: - q, r = divmod(self._start - value, -self._step) - if r == self._zero: - return int(q) - - raise ValueError("{} is not in numeric range".format(value)) - - def _get_by_index(self, i): - if i < 0: - i += self._len - if i < 0 or i >= self._len: - raise IndexError("numeric range object index out of range") - return self._start + i * self._step - - -def count_cycle(iterable, n=None): - """Cycle through the items from *iterable* up to *n* times, yielding - the number of completed cycles along with each item. If *n* is omitted the - process repeats indefinitely. - - >>> list(count_cycle('AB', 3)) - [(0, 'A'), (0, 'B'), (1, 'A'), (1, 'B'), (2, 'A'), (2, 'B')] - - """ - iterable = tuple(iterable) - if not iterable: - return iter(()) - counter = count() if n is None else range(n) - return ((i, item) for i in counter for item in iterable) - - -def mark_ends(iterable): - """Yield 3-tuples of the form ``(is_first, is_last, item)``. - - >>> list(mark_ends('ABC')) - [(True, False, 'A'), (False, False, 'B'), (False, True, 'C')] - - Use this when looping over an iterable to take special action on its first - and/or last items: - - >>> iterable = ['Header', 100, 200, 'Footer'] - >>> total = 0 - >>> for is_first, is_last, item in mark_ends(iterable): - ... if is_first: - ... continue # Skip the header - ... if is_last: - ... continue # Skip the footer - ... total += item - >>> print(total) - 300 - """ - it = iter(iterable) - - try: - b = next(it) - except StopIteration: - return - - try: - for i in count(): - a = b - b = next(it) - yield i == 0, False, a - - except StopIteration: - yield i == 0, True, a - - -def locate(iterable, pred=bool, window_size=None): - """Yield the index of each item in *iterable* for which *pred* returns - ``True``. - - *pred* defaults to :func:`bool`, which will select truthy items: - - >>> list(locate([0, 1, 1, 0, 1, 0, 0])) - [1, 2, 4] - - Set *pred* to a custom function to, e.g., find the indexes for a particular - item. - - >>> list(locate(['a', 'b', 'c', 'b'], lambda x: x == 'b')) - [1, 3] - - If *window_size* is given, then the *pred* function will be called with - that many items. This enables searching for sub-sequences: - - >>> iterable = [0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3] - >>> pred = lambda *args: args == (1, 2, 3) - >>> list(locate(iterable, pred=pred, window_size=3)) - [1, 5, 9] - - Use with :func:`seekable` to find indexes and then retrieve the associated - items: - - >>> from itertools import count - >>> from more_itertools import seekable - >>> source = (3 * n + 1 if (n % 2) else n // 2 for n in count()) - >>> it = seekable(source) - >>> pred = lambda x: x > 100 - >>> indexes = locate(it, pred=pred) - >>> i = next(indexes) - >>> it.seek(i) - >>> next(it) - 106 - - """ - if window_size is None: - return compress(count(), map(pred, iterable)) - - if window_size < 1: - raise ValueError('window size must be at least 1') - - it = windowed(iterable, window_size, fillvalue=_marker) - return compress(count(), starmap(pred, it)) - - -def longest_common_prefix(iterables): - """Yield elements of the longest common prefix amongst given *iterables*. - - >>> ''.join(longest_common_prefix(['abcd', 'abc', 'abf'])) - 'ab' - - """ - return (c[0] for c in takewhile(all_equal, zip(*iterables))) - - -def lstrip(iterable, pred): - """Yield the items from *iterable*, but strip any from the beginning - for which *pred* returns ``True``. - - For example, to remove a set of items from the start of an iterable: - - >>> iterable = (None, False, None, 1, 2, None, 3, False, None) - >>> pred = lambda x: x in {None, False, ''} - >>> list(lstrip(iterable, pred)) - [1, 2, None, 3, False, None] - - This function is analogous to to :func:`str.lstrip`, and is essentially - an wrapper for :func:`itertools.dropwhile`. - - """ - return dropwhile(pred, iterable) - - -def rstrip(iterable, pred): - """Yield the items from *iterable*, but strip any from the end - for which *pred* returns ``True``. - - For example, to remove a set of items from the end of an iterable: - - >>> iterable = (None, False, None, 1, 2, None, 3, False, None) - >>> pred = lambda x: x in {None, False, ''} - >>> list(rstrip(iterable, pred)) - [None, False, None, 1, 2, None, 3] - - This function is analogous to :func:`str.rstrip`. - - """ - cache = [] - cache_append = cache.append - cache_clear = cache.clear - for x in iterable: - if pred(x): - cache_append(x) - else: - yield from cache - cache_clear() - yield x - - -def strip(iterable, pred): - """Yield the items from *iterable*, but strip any from the - beginning and end for which *pred* returns ``True``. - - For example, to remove a set of items from both ends of an iterable: - - >>> iterable = (None, False, None, 1, 2, None, 3, False, None) - >>> pred = lambda x: x in {None, False, ''} - >>> list(strip(iterable, pred)) - [1, 2, None, 3] - - This function is analogous to :func:`str.strip`. - - """ - return rstrip(lstrip(iterable, pred), pred) - - -class islice_extended: - """An extension of :func:`itertools.islice` that supports negative values - for *stop*, *start*, and *step*. - - >>> iterable = iter('abcdefgh') - >>> list(islice_extended(iterable, -4, -1)) - ['e', 'f', 'g'] - - Slices with negative values require some caching of *iterable*, but this - function takes care to minimize the amount of memory required. - - For example, you can use a negative step with an infinite iterator: - - >>> from itertools import count - >>> list(islice_extended(count(), 110, 99, -2)) - [110, 108, 106, 104, 102, 100] - - You can also use slice notation directly: - - >>> iterable = map(str, count()) - >>> it = islice_extended(iterable)[10:20:2] - >>> list(it) - ['10', '12', '14', '16', '18'] - - """ - - def __init__(self, iterable, *args): - it = iter(iterable) - if args: - self._iterable = _islice_helper(it, slice(*args)) - else: - self._iterable = it - - def __iter__(self): - return self - - def __next__(self): - return next(self._iterable) - - def __getitem__(self, key): - if isinstance(key, slice): - return islice_extended(_islice_helper(self._iterable, key)) - - raise TypeError('islice_extended.__getitem__ argument must be a slice') - - -def _islice_helper(it, s): - start = s.start - stop = s.stop - if s.step == 0: - raise ValueError('step argument must be a non-zero integer or None.') - step = s.step or 1 - - if step > 0: - start = 0 if (start is None) else start - - if start < 0: - # Consume all but the last -start items - cache = deque(enumerate(it, 1), maxlen=-start) - len_iter = cache[-1][0] if cache else 0 - - # Adjust start to be positive - i = max(len_iter + start, 0) - - # Adjust stop to be positive - if stop is None: - j = len_iter - elif stop >= 0: - j = min(stop, len_iter) - else: - j = max(len_iter + stop, 0) - - # Slice the cache - n = j - i - if n <= 0: - return - - for index, item in islice(cache, 0, n, step): - yield item - elif (stop is not None) and (stop < 0): - # Advance to the start position - next(islice(it, start, start), None) - - # When stop is negative, we have to carry -stop items while - # iterating - cache = deque(islice(it, -stop), maxlen=-stop) - - for index, item in enumerate(it): - cached_item = cache.popleft() - if index % step == 0: - yield cached_item - cache.append(item) - else: - # When both start and stop are positive we have the normal case - yield from islice(it, start, stop, step) - else: - start = -1 if (start is None) else start - - if (stop is not None) and (stop < 0): - # Consume all but the last items - n = -stop - 1 - cache = deque(enumerate(it, 1), maxlen=n) - len_iter = cache[-1][0] if cache else 0 - - # If start and stop are both negative they are comparable and - # we can just slice. Otherwise we can adjust start to be negative - # and then slice. - if start < 0: - i, j = start, stop - else: - i, j = min(start - len_iter, -1), None - - for index, item in list(cache)[i:j:step]: - yield item - else: - # Advance to the stop position - if stop is not None: - m = stop + 1 - next(islice(it, m, m), None) - - # stop is positive, so if start is negative they are not comparable - # and we need the rest of the items. - if start < 0: - i = start - n = None - # stop is None and start is positive, so we just need items up to - # the start index. - elif stop is None: - i = None - n = start + 1 - # Both stop and start are positive, so they are comparable. - else: - i = None - n = start - stop - if n <= 0: - return - - cache = list(islice(it, n)) - - yield from cache[i::step] - - -def always_reversible(iterable): - """An extension of :func:`reversed` that supports all iterables, not - just those which implement the ``Reversible`` or ``Sequence`` protocols. - - >>> print(*always_reversible(x for x in range(3))) - 2 1 0 - - If the iterable is already reversible, this function returns the - result of :func:`reversed()`. If the iterable is not reversible, - this function will cache the remaining items in the iterable and - yield them in reverse order, which may require significant storage. - """ - try: - return reversed(iterable) - except TypeError: - return reversed(list(iterable)) - - -def consecutive_groups(iterable, ordering=lambda x: x): - """Yield groups of consecutive items using :func:`itertools.groupby`. - The *ordering* function determines whether two items are adjacent by - returning their position. - - By default, the ordering function is the identity function. This is - suitable for finding runs of numbers: - - >>> iterable = [1, 10, 11, 12, 20, 30, 31, 32, 33, 40] - >>> for group in consecutive_groups(iterable): - ... print(list(group)) - [1] - [10, 11, 12] - [20] - [30, 31, 32, 33] - [40] - - For finding runs of adjacent letters, try using the :meth:`index` method - of a string of letters: - - >>> from string import ascii_lowercase - >>> iterable = 'abcdfgilmnop' - >>> ordering = ascii_lowercase.index - >>> for group in consecutive_groups(iterable, ordering): - ... print(list(group)) - ['a', 'b', 'c', 'd'] - ['f', 'g'] - ['i'] - ['l', 'm', 'n', 'o', 'p'] - - Each group of consecutive items is an iterator that shares it source with - *iterable*. When an an output group is advanced, the previous group is - no longer available unless its elements are copied (e.g., into a ``list``). - - >>> iterable = [1, 2, 11, 12, 21, 22] - >>> saved_groups = [] - >>> for group in consecutive_groups(iterable): - ... saved_groups.append(list(group)) # Copy group elements - >>> saved_groups - [[1, 2], [11, 12], [21, 22]] - - """ - for k, g in groupby( - enumerate(iterable), key=lambda x: x[0] - ordering(x[1]) - ): - yield map(itemgetter(1), g) - - -def difference(iterable, func=sub, *, initial=None): - """This function is the inverse of :func:`itertools.accumulate`. By default - it will compute the first difference of *iterable* using - :func:`operator.sub`: - - >>> from itertools import accumulate - >>> iterable = accumulate([0, 1, 2, 3, 4]) # produces 0, 1, 3, 6, 10 - >>> list(difference(iterable)) - [0, 1, 2, 3, 4] - - *func* defaults to :func:`operator.sub`, but other functions can be - specified. They will be applied as follows:: - - A, B, C, D, ... --> A, func(B, A), func(C, B), func(D, C), ... - - For example, to do progressive division: - - >>> iterable = [1, 2, 6, 24, 120] - >>> func = lambda x, y: x // y - >>> list(difference(iterable, func)) - [1, 2, 3, 4, 5] - - If the *initial* keyword is set, the first element will be skipped when - computing successive differences. - - >>> it = [10, 11, 13, 16] # from accumulate([1, 2, 3], initial=10) - >>> list(difference(it, initial=10)) - [1, 2, 3] - - """ - a, b = tee(iterable) - try: - first = [next(b)] - except StopIteration: - return iter([]) - - if initial is not None: - first = [] - - return chain(first, map(func, b, a)) - - -class SequenceView(Sequence): - """Return a read-only view of the sequence object *target*. - - :class:`SequenceView` objects are analogous to Python's built-in - "dictionary view" types. They provide a dynamic view of a sequence's items, - meaning that when the sequence updates, so does the view. - - >>> seq = ['0', '1', '2'] - >>> view = SequenceView(seq) - >>> view - SequenceView(['0', '1', '2']) - >>> seq.append('3') - >>> view - SequenceView(['0', '1', '2', '3']) - - Sequence views support indexing, slicing, and length queries. They act - like the underlying sequence, except they don't allow assignment: - - >>> view[1] - '1' - >>> view[1:-1] - ['1', '2'] - >>> len(view) - 4 - - Sequence views are useful as an alternative to copying, as they don't - require (much) extra storage. - - """ - - def __init__(self, target): - if not isinstance(target, Sequence): - raise TypeError - self._target = target - - def __getitem__(self, index): - return self._target[index] - - def __len__(self): - return len(self._target) - - def __repr__(self): - return '{}({})'.format(self.__class__.__name__, repr(self._target)) - - -class seekable: - """Wrap an iterator to allow for seeking backward and forward. This - progressively caches the items in the source iterable so they can be - re-visited. - - Call :meth:`seek` with an index to seek to that position in the source - iterable. - - To "reset" an iterator, seek to ``0``: - - >>> from itertools import count - >>> it = seekable((str(n) for n in count())) - >>> next(it), next(it), next(it) - ('0', '1', '2') - >>> it.seek(0) - >>> next(it), next(it), next(it) - ('0', '1', '2') - >>> next(it) - '3' - - You can also seek forward: - - >>> it = seekable((str(n) for n in range(20))) - >>> it.seek(10) - >>> next(it) - '10' - >>> it.relative_seek(-2) # Seeking relative to the current position - >>> next(it) - '9' - >>> it.seek(20) # Seeking past the end of the source isn't a problem - >>> list(it) - [] - >>> it.seek(0) # Resetting works even after hitting the end - >>> next(it), next(it), next(it) - ('0', '1', '2') - - Call :meth:`peek` to look ahead one item without advancing the iterator: - - >>> it = seekable('1234') - >>> it.peek() - '1' - >>> list(it) - ['1', '2', '3', '4'] - >>> it.peek(default='empty') - 'empty' - - Before the iterator is at its end, calling :func:`bool` on it will return - ``True``. After it will return ``False``: - - >>> it = seekable('5678') - >>> bool(it) - True - >>> list(it) - ['5', '6', '7', '8'] - >>> bool(it) - False - - You may view the contents of the cache with the :meth:`elements` method. - That returns a :class:`SequenceView`, a view that updates automatically: - - >>> it = seekable((str(n) for n in range(10))) - >>> next(it), next(it), next(it) - ('0', '1', '2') - >>> elements = it.elements() - >>> elements - SequenceView(['0', '1', '2']) - >>> next(it) - '3' - >>> elements - SequenceView(['0', '1', '2', '3']) - - By default, the cache grows as the source iterable progresses, so beware of - wrapping very large or infinite iterables. Supply *maxlen* to limit the - size of the cache (this of course limits how far back you can seek). - - >>> from itertools import count - >>> it = seekable((str(n) for n in count()), maxlen=2) - >>> next(it), next(it), next(it), next(it) - ('0', '1', '2', '3') - >>> list(it.elements()) - ['2', '3'] - >>> it.seek(0) - >>> next(it), next(it), next(it), next(it) - ('2', '3', '4', '5') - >>> next(it) - '6' - - """ - - def __init__(self, iterable, maxlen=None): - self._source = iter(iterable) - if maxlen is None: - self._cache = [] - else: - self._cache = deque([], maxlen) - self._index = None - - def __iter__(self): - return self - - def __next__(self): - if self._index is not None: - try: - item = self._cache[self._index] - except IndexError: - self._index = None - else: - self._index += 1 - return item - - item = next(self._source) - self._cache.append(item) - return item - - def __bool__(self): - try: - self.peek() - except StopIteration: - return False - return True - - def peek(self, default=_marker): - try: - peeked = next(self) - except StopIteration: - if default is _marker: - raise - return default - if self._index is None: - self._index = len(self._cache) - self._index -= 1 - return peeked - - def elements(self): - return SequenceView(self._cache) - - def seek(self, index): - self._index = index - remainder = index - len(self._cache) - if remainder > 0: - consume(self, remainder) - - def relative_seek(self, count): - index = len(self._cache) - self.seek(max(index + count, 0)) - - -class run_length: - """ - :func:`run_length.encode` compresses an iterable with run-length encoding. - It yields groups of repeated items with the count of how many times they - were repeated: - - >>> uncompressed = 'abbcccdddd' - >>> list(run_length.encode(uncompressed)) - [('a', 1), ('b', 2), ('c', 3), ('d', 4)] - - :func:`run_length.decode` decompresses an iterable that was previously - compressed with run-length encoding. It yields the items of the - decompressed iterable: - - >>> compressed = [('a', 1), ('b', 2), ('c', 3), ('d', 4)] - >>> list(run_length.decode(compressed)) - ['a', 'b', 'b', 'c', 'c', 'c', 'd', 'd', 'd', 'd'] - - """ - - @staticmethod - def encode(iterable): - return ((k, ilen(g)) for k, g in groupby(iterable)) - - @staticmethod - def decode(iterable): - return chain.from_iterable(repeat(k, n) for k, n in iterable) - - -def exactly_n(iterable, n, predicate=bool): - """Return ``True`` if exactly ``n`` items in the iterable are ``True`` - according to the *predicate* function. - - >>> exactly_n([True, True, False], 2) - True - >>> exactly_n([True, True, False], 1) - False - >>> exactly_n([0, 1, 2, 3, 4, 5], 3, lambda x: x < 3) - True - - The iterable will be advanced until ``n + 1`` truthy items are encountered, - so avoid calling it on infinite iterables. - - """ - return len(take(n + 1, filter(predicate, iterable))) == n - - -def circular_shifts(iterable): - """Return a list of circular shifts of *iterable*. - - >>> circular_shifts(range(4)) - [(0, 1, 2, 3), (1, 2, 3, 0), (2, 3, 0, 1), (3, 0, 1, 2)] - """ - lst = list(iterable) - return take(len(lst), windowed(cycle(lst), len(lst))) - - -def make_decorator(wrapping_func, result_index=0): - """Return a decorator version of *wrapping_func*, which is a function that - modifies an iterable. *result_index* is the position in that function's - signature where the iterable goes. - - This lets you use itertools on the "production end," i.e. at function - definition. This can augment what the function returns without changing the - function's code. - - For example, to produce a decorator version of :func:`chunked`: - - >>> from more_itertools import chunked - >>> chunker = make_decorator(chunked, result_index=0) - >>> @chunker(3) - ... def iter_range(n): - ... return iter(range(n)) - ... - >>> list(iter_range(9)) - [[0, 1, 2], [3, 4, 5], [6, 7, 8]] - - To only allow truthy items to be returned: - - >>> truth_serum = make_decorator(filter, result_index=1) - >>> @truth_serum(bool) - ... def boolean_test(): - ... return [0, 1, '', ' ', False, True] - ... - >>> list(boolean_test()) - [1, ' ', True] - - The :func:`peekable` and :func:`seekable` wrappers make for practical - decorators: - - >>> from more_itertools import peekable - >>> peekable_function = make_decorator(peekable) - >>> @peekable_function() - ... def str_range(*args): - ... return (str(x) for x in range(*args)) - ... - >>> it = str_range(1, 20, 2) - >>> next(it), next(it), next(it) - ('1', '3', '5') - >>> it.peek() - '7' - >>> next(it) - '7' - - """ - - # See https://sites.google.com/site/bbayles/index/decorator_factory for - # notes on how this works. - def decorator(*wrapping_args, **wrapping_kwargs): - def outer_wrapper(f): - def inner_wrapper(*args, **kwargs): - result = f(*args, **kwargs) - wrapping_args_ = list(wrapping_args) - wrapping_args_.insert(result_index, result) - return wrapping_func(*wrapping_args_, **wrapping_kwargs) - - return inner_wrapper - - return outer_wrapper - - return decorator - - -def map_reduce(iterable, keyfunc, valuefunc=None, reducefunc=None): - """Return a dictionary that maps the items in *iterable* to categories - defined by *keyfunc*, transforms them with *valuefunc*, and - then summarizes them by category with *reducefunc*. - - *valuefunc* defaults to the identity function if it is unspecified. - If *reducefunc* is unspecified, no summarization takes place: - - >>> keyfunc = lambda x: x.upper() - >>> result = map_reduce('abbccc', keyfunc) - >>> sorted(result.items()) - [('A', ['a']), ('B', ['b', 'b']), ('C', ['c', 'c', 'c'])] - - Specifying *valuefunc* transforms the categorized items: - - >>> keyfunc = lambda x: x.upper() - >>> valuefunc = lambda x: 1 - >>> result = map_reduce('abbccc', keyfunc, valuefunc) - >>> sorted(result.items()) - [('A', [1]), ('B', [1, 1]), ('C', [1, 1, 1])] - - Specifying *reducefunc* summarizes the categorized items: - - >>> keyfunc = lambda x: x.upper() - >>> valuefunc = lambda x: 1 - >>> reducefunc = sum - >>> result = map_reduce('abbccc', keyfunc, valuefunc, reducefunc) - >>> sorted(result.items()) - [('A', 1), ('B', 2), ('C', 3)] - - You may want to filter the input iterable before applying the map/reduce - procedure: - - >>> all_items = range(30) - >>> items = [x for x in all_items if 10 <= x <= 20] # Filter - >>> keyfunc = lambda x: x % 2 # Evens map to 0; odds to 1 - >>> categories = map_reduce(items, keyfunc=keyfunc) - >>> sorted(categories.items()) - [(0, [10, 12, 14, 16, 18, 20]), (1, [11, 13, 15, 17, 19])] - >>> summaries = map_reduce(items, keyfunc=keyfunc, reducefunc=sum) - >>> sorted(summaries.items()) - [(0, 90), (1, 75)] - - Note that all items in the iterable are gathered into a list before the - summarization step, which may require significant storage. - - The returned object is a :obj:`collections.defaultdict` with the - ``default_factory`` set to ``None``, such that it behaves like a normal - dictionary. - - """ - valuefunc = (lambda x: x) if (valuefunc is None) else valuefunc - - ret = defaultdict(list) - for item in iterable: - key = keyfunc(item) - value = valuefunc(item) - ret[key].append(value) - - if reducefunc is not None: - for key, value_list in ret.items(): - ret[key] = reducefunc(value_list) - - ret.default_factory = None - return ret - - -def rlocate(iterable, pred=bool, window_size=None): - """Yield the index of each item in *iterable* for which *pred* returns - ``True``, starting from the right and moving left. - - *pred* defaults to :func:`bool`, which will select truthy items: - - >>> list(rlocate([0, 1, 1, 0, 1, 0, 0])) # Truthy at 1, 2, and 4 - [4, 2, 1] - - Set *pred* to a custom function to, e.g., find the indexes for a particular - item: - - >>> iterable = iter('abcb') - >>> pred = lambda x: x == 'b' - >>> list(rlocate(iterable, pred)) - [3, 1] - - If *window_size* is given, then the *pred* function will be called with - that many items. This enables searching for sub-sequences: - - >>> iterable = [0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3] - >>> pred = lambda *args: args == (1, 2, 3) - >>> list(rlocate(iterable, pred=pred, window_size=3)) - [9, 5, 1] - - Beware, this function won't return anything for infinite iterables. - If *iterable* is reversible, ``rlocate`` will reverse it and search from - the right. Otherwise, it will search from the left and return the results - in reverse order. - - See :func:`locate` to for other example applications. - - """ - if window_size is None: - try: - len_iter = len(iterable) - return (len_iter - i - 1 for i in locate(reversed(iterable), pred)) - except TypeError: - pass - - return reversed(list(locate(iterable, pred, window_size))) - - -def replace(iterable, pred, substitutes, count=None, window_size=1): - """Yield the items from *iterable*, replacing the items for which *pred* - returns ``True`` with the items from the iterable *substitutes*. - - >>> iterable = [1, 1, 0, 1, 1, 0, 1, 1] - >>> pred = lambda x: x == 0 - >>> substitutes = (2, 3) - >>> list(replace(iterable, pred, substitutes)) - [1, 1, 2, 3, 1, 1, 2, 3, 1, 1] - - If *count* is given, the number of replacements will be limited: - - >>> iterable = [1, 1, 0, 1, 1, 0, 1, 1, 0] - >>> pred = lambda x: x == 0 - >>> substitutes = [None] - >>> list(replace(iterable, pred, substitutes, count=2)) - [1, 1, None, 1, 1, None, 1, 1, 0] - - Use *window_size* to control the number of items passed as arguments to - *pred*. This allows for locating and replacing subsequences. - - >>> iterable = [0, 1, 2, 5, 0, 1, 2, 5] - >>> window_size = 3 - >>> pred = lambda *args: args == (0, 1, 2) # 3 items passed to pred - >>> substitutes = [3, 4] # Splice in these items - >>> list(replace(iterable, pred, substitutes, window_size=window_size)) - [3, 4, 5, 3, 4, 5] - - """ - if window_size < 1: - raise ValueError('window_size must be at least 1') - - # Save the substitutes iterable, since it's used more than once - substitutes = tuple(substitutes) - - # Add padding such that the number of windows matches the length of the - # iterable - it = chain(iterable, [_marker] * (window_size - 1)) - windows = windowed(it, window_size) - - n = 0 - for w in windows: - # If the current window matches our predicate (and we haven't hit - # our maximum number of replacements), splice in the substitutes - # and then consume the following windows that overlap with this one. - # For example, if the iterable is (0, 1, 2, 3, 4...) - # and the window size is 2, we have (0, 1), (1, 2), (2, 3)... - # If the predicate matches on (0, 1), we need to zap (0, 1) and (1, 2) - if pred(*w): - if (count is None) or (n < count): - n += 1 - yield from substitutes - consume(windows, window_size - 1) - continue - - # If there was no match (or we've reached the replacement limit), - # yield the first item from the window. - if w and (w[0] is not _marker): - yield w[0] - - -def partitions(iterable): - """Yield all possible order-preserving partitions of *iterable*. - - >>> iterable = 'abc' - >>> for part in partitions(iterable): - ... print([''.join(p) for p in part]) - ['abc'] - ['a', 'bc'] - ['ab', 'c'] - ['a', 'b', 'c'] - - This is unrelated to :func:`partition`. - - """ - sequence = list(iterable) - n = len(sequence) - for i in powerset(range(1, n)): - yield [sequence[i:j] for i, j in zip((0,) + i, i + (n,))] - - -def set_partitions(iterable, k=None): - """ - Yield the set partitions of *iterable* into *k* parts. Set partitions are - not order-preserving. - - >>> iterable = 'abc' - >>> for part in set_partitions(iterable, 2): - ... print([''.join(p) for p in part]) - ['a', 'bc'] - ['ab', 'c'] - ['b', 'ac'] - - - If *k* is not given, every set partition is generated. - - >>> iterable = 'abc' - >>> for part in set_partitions(iterable): - ... print([''.join(p) for p in part]) - ['abc'] - ['a', 'bc'] - ['ab', 'c'] - ['b', 'ac'] - ['a', 'b', 'c'] - - """ - L = list(iterable) - n = len(L) - if k is not None: - if k < 1: - raise ValueError( - "Can't partition in a negative or zero number of groups" - ) - elif k > n: - return - - def set_partitions_helper(L, k): - n = len(L) - if k == 1: - yield [L] - elif n == k: - yield [[s] for s in L] - else: - e, *M = L - for p in set_partitions_helper(M, k - 1): - yield [[e], *p] - for p in set_partitions_helper(M, k): - for i in range(len(p)): - yield p[:i] + [[e] + p[i]] + p[i + 1 :] - - if k is None: - for k in range(1, n + 1): - yield from set_partitions_helper(L, k) - else: - yield from set_partitions_helper(L, k) - - -class time_limited: - """ - Yield items from *iterable* until *limit_seconds* have passed. - If the time limit expires before all items have been yielded, the - ``timed_out`` parameter will be set to ``True``. - - >>> from time import sleep - >>> def generator(): - ... yield 1 - ... yield 2 - ... sleep(0.2) - ... yield 3 - >>> iterable = time_limited(0.1, generator()) - >>> list(iterable) - [1, 2] - >>> iterable.timed_out - True - - Note that the time is checked before each item is yielded, and iteration - stops if the time elapsed is greater than *limit_seconds*. If your time - limit is 1 second, but it takes 2 seconds to generate the first item from - the iterable, the function will run for 2 seconds and not yield anything. - As a special case, when *limit_seconds* is zero, the iterator never - returns anything. - - """ - - def __init__(self, limit_seconds, iterable): - if limit_seconds < 0: - raise ValueError('limit_seconds must be positive') - self.limit_seconds = limit_seconds - self._iterable = iter(iterable) - self._start_time = monotonic() - self.timed_out = False - - def __iter__(self): - return self - - def __next__(self): - if self.limit_seconds == 0: - self.timed_out = True - raise StopIteration - item = next(self._iterable) - if monotonic() - self._start_time > self.limit_seconds: - self.timed_out = True - raise StopIteration - - return item - - -def only(iterable, default=None, too_long=None): - """If *iterable* has only one item, return it. - If it has zero items, return *default*. - If it has more than one item, raise the exception given by *too_long*, - which is ``ValueError`` by default. - - >>> only([], default='missing') - 'missing' - >>> only([1]) - 1 - >>> only([1, 2]) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - ValueError: Expected exactly one item in iterable, but got 1, 2, - and perhaps more.' - >>> only([1, 2], too_long=TypeError) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - TypeError - - Note that :func:`only` attempts to advance *iterable* twice to ensure there - is only one item. See :func:`spy` or :func:`peekable` to check - iterable contents less destructively. - """ - it = iter(iterable) - first_value = next(it, default) - - try: - second_value = next(it) - except StopIteration: - pass - else: - msg = ( - 'Expected exactly one item in iterable, but got {!r}, {!r}, ' - 'and perhaps more.'.format(first_value, second_value) - ) - raise too_long or ValueError(msg) - - return first_value - - -def _ichunk(iterable, n): - cache = deque() - chunk = islice(iterable, n) - - def generator(): - while True: - if cache: - yield cache.popleft() - else: - try: - item = next(chunk) - except StopIteration: - return - else: - yield item - - def materialize_next(n=1): - # if n not specified materialize everything - if n is None: - cache.extend(chunk) - return len(cache) - - to_cache = n - len(cache) - - # materialize up to n - if to_cache > 0: - cache.extend(islice(chunk, to_cache)) - - # return number materialized up to n - return min(n, len(cache)) - - return (generator(), materialize_next) - - -def ichunked(iterable, n): - """Break *iterable* into sub-iterables with *n* elements each. - :func:`ichunked` is like :func:`chunked`, but it yields iterables - instead of lists. - - If the sub-iterables are read in order, the elements of *iterable* - won't be stored in memory. - If they are read out of order, :func:`itertools.tee` is used to cache - elements as necessary. - - >>> from itertools import count - >>> all_chunks = ichunked(count(), 4) - >>> c_1, c_2, c_3 = next(all_chunks), next(all_chunks), next(all_chunks) - >>> list(c_2) # c_1's elements have been cached; c_3's haven't been - [4, 5, 6, 7] - >>> list(c_1) - [0, 1, 2, 3] - >>> list(c_3) - [8, 9, 10, 11] - - """ - iterable = iter(iterable) - while True: - # Create new chunk - chunk, materialize_next = _ichunk(iterable, n) - - # Check to see whether we're at the end of the source iterable - if not materialize_next(): - return - - yield chunk - - # Fill previous chunk's cache - materialize_next(None) - - -def iequals(*iterables): - """Return ``True`` if all given *iterables* are equal to each other, - which means that they contain the same elements in the same order. - - The function is useful for comparing iterables of different data types - or iterables that do not support equality checks. - - >>> iequals("abc", ['a', 'b', 'c'], ('a', 'b', 'c'), iter("abc")) - True - - >>> iequals("abc", "acb") - False - - Not to be confused with :func:`all_equal`, which checks whether all - elements of iterable are equal to each other. - - """ - return all(map(all_equal, zip_longest(*iterables, fillvalue=object()))) - - -def distinct_combinations(iterable, r): - """Yield the distinct combinations of *r* items taken from *iterable*. - - >>> list(distinct_combinations([0, 0, 1], 2)) - [(0, 0), (0, 1)] - - Equivalent to ``set(combinations(iterable))``, except duplicates are not - generated and thrown away. For larger input sequences this is much more - efficient. - - """ - if r < 0: - raise ValueError('r must be non-negative') - elif r == 0: - yield () - return - pool = tuple(iterable) - generators = [unique_everseen(enumerate(pool), key=itemgetter(1))] - current_combo = [None] * r - level = 0 - while generators: - try: - cur_idx, p = next(generators[-1]) - except StopIteration: - generators.pop() - level -= 1 - continue - current_combo[level] = p - if level + 1 == r: - yield tuple(current_combo) - else: - generators.append( - unique_everseen( - enumerate(pool[cur_idx + 1 :], cur_idx + 1), - key=itemgetter(1), - ) - ) - level += 1 - - -def filter_except(validator, iterable, *exceptions): - """Yield the items from *iterable* for which the *validator* function does - not raise one of the specified *exceptions*. - - *validator* is called for each item in *iterable*. - It should be a function that accepts one argument and raises an exception - if that item is not valid. - - >>> iterable = ['1', '2', 'three', '4', None] - >>> list(filter_except(int, iterable, ValueError, TypeError)) - ['1', '2', '4'] - - If an exception other than one given by *exceptions* is raised by - *validator*, it is raised like normal. - """ - for item in iterable: - try: - validator(item) - except exceptions: - pass - else: - yield item - - -def map_except(function, iterable, *exceptions): - """Transform each item from *iterable* with *function* and yield the - result, unless *function* raises one of the specified *exceptions*. - - *function* is called to transform each item in *iterable*. - It should accept one argument. - - >>> iterable = ['1', '2', 'three', '4', None] - >>> list(map_except(int, iterable, ValueError, TypeError)) - [1, 2, 4] - - If an exception other than one given by *exceptions* is raised by - *function*, it is raised like normal. - """ - for item in iterable: - try: - yield function(item) - except exceptions: - pass - - -def map_if(iterable, pred, func, func_else=lambda x: x): - """Evaluate each item from *iterable* using *pred*. If the result is - equivalent to ``True``, transform the item with *func* and yield it. - Otherwise, transform the item with *func_else* and yield it. - - *pred*, *func*, and *func_else* should each be functions that accept - one argument. By default, *func_else* is the identity function. - - >>> from math import sqrt - >>> iterable = list(range(-5, 5)) - >>> iterable - [-5, -4, -3, -2, -1, 0, 1, 2, 3, 4] - >>> list(map_if(iterable, lambda x: x > 3, lambda x: 'toobig')) - [-5, -4, -3, -2, -1, 0, 1, 2, 3, 'toobig'] - >>> list(map_if(iterable, lambda x: x >= 0, - ... lambda x: f'{sqrt(x):.2f}', lambda x: None)) - [None, None, None, None, None, '0.00', '1.00', '1.41', '1.73', '2.00'] - """ - for item in iterable: - yield func(item) if pred(item) else func_else(item) - - -def _sample_unweighted(iterable, k): - # Implementation of "Algorithm L" from the 1994 paper by Kim-Hung Li: - # "Reservoir-Sampling Algorithms of Time Complexity O(n(1+log(N/n)))". - - # Fill up the reservoir (collection of samples) with the first `k` samples - reservoir = take(k, iterable) - - # Generate random number that's the largest in a sample of k U(0,1) numbers - # Largest order statistic: https://en.wikipedia.org/wiki/Order_statistic - W = exp(log(random()) / k) - - # The number of elements to skip before changing the reservoir is a random - # number with a geometric distribution. Sample it using random() and logs. - next_index = k + floor(log(random()) / log(1 - W)) - - for index, element in enumerate(iterable, k): - if index == next_index: - reservoir[randrange(k)] = element - # The new W is the largest in a sample of k U(0, `old_W`) numbers - W *= exp(log(random()) / k) - next_index += floor(log(random()) / log(1 - W)) + 1 - - return reservoir - - -def _sample_weighted(iterable, k, weights): - # Implementation of "A-ExpJ" from the 2006 paper by Efraimidis et al. : - # "Weighted random sampling with a reservoir". - - # Log-transform for numerical stability for weights that are small/large - weight_keys = (log(random()) / weight for weight in weights) - - # Fill up the reservoir (collection of samples) with the first `k` - # weight-keys and elements, then heapify the list. - reservoir = take(k, zip(weight_keys, iterable)) - heapify(reservoir) - - # The number of jumps before changing the reservoir is a random variable - # with an exponential distribution. Sample it using random() and logs. - smallest_weight_key, _ = reservoir[0] - weights_to_skip = log(random()) / smallest_weight_key - - for weight, element in zip(weights, iterable): - if weight >= weights_to_skip: - # The notation here is consistent with the paper, but we store - # the weight-keys in log-space for better numerical stability. - smallest_weight_key, _ = reservoir[0] - t_w = exp(weight * smallest_weight_key) - r_2 = uniform(t_w, 1) # generate U(t_w, 1) - weight_key = log(r_2) / weight - heapreplace(reservoir, (weight_key, element)) - smallest_weight_key, _ = reservoir[0] - weights_to_skip = log(random()) / smallest_weight_key - else: - weights_to_skip -= weight - - # Equivalent to [element for weight_key, element in sorted(reservoir)] - return [heappop(reservoir)[1] for _ in range(k)] - - -def sample(iterable, k, weights=None): - """Return a *k*-length list of elements chosen (without replacement) - from the *iterable*. Like :func:`random.sample`, but works on iterables - of unknown length. - - >>> iterable = range(100) - >>> sample(iterable, 5) # doctest: +SKIP - [81, 60, 96, 16, 4] - - An iterable with *weights* may also be given: - - >>> iterable = range(100) - >>> weights = (i * i + 1 for i in range(100)) - >>> sampled = sample(iterable, 5, weights=weights) # doctest: +SKIP - [79, 67, 74, 66, 78] - - The algorithm can also be used to generate weighted random permutations. - The relative weight of each item determines the probability that it - appears late in the permutation. - - >>> data = "abcdefgh" - >>> weights = range(1, len(data) + 1) - >>> sample(data, k=len(data), weights=weights) # doctest: +SKIP - ['c', 'a', 'b', 'e', 'g', 'd', 'h', 'f'] - """ - if k == 0: - return [] - - iterable = iter(iterable) - if weights is None: - return _sample_unweighted(iterable, k) - else: - weights = iter(weights) - return _sample_weighted(iterable, k, weights) - - -def is_sorted(iterable, key=None, reverse=False, strict=False): - """Returns ``True`` if the items of iterable are in sorted order, and - ``False`` otherwise. *key* and *reverse* have the same meaning that they do - in the built-in :func:`sorted` function. - - >>> is_sorted(['1', '2', '3', '4', '5'], key=int) - True - >>> is_sorted([5, 4, 3, 1, 2], reverse=True) - False - - If *strict*, tests for strict sorting, that is, returns ``False`` if equal - elements are found: - - >>> is_sorted([1, 2, 2]) - True - >>> is_sorted([1, 2, 2], strict=True) - False - - The function returns ``False`` after encountering the first out-of-order - item. If there are no out-of-order items, the iterable is exhausted. - """ - - compare = (le if reverse else ge) if strict else (lt if reverse else gt) - it = iterable if key is None else map(key, iterable) - return not any(starmap(compare, pairwise(it))) - - -class AbortThread(BaseException): - pass - - -class callback_iter: - """Convert a function that uses callbacks to an iterator. - - Let *func* be a function that takes a `callback` keyword argument. - For example: - - >>> def func(callback=None): - ... for i, c in [(1, 'a'), (2, 'b'), (3, 'c')]: - ... if callback: - ... callback(i, c) - ... return 4 - - - Use ``with callback_iter(func)`` to get an iterator over the parameters - that are delivered to the callback. - - >>> with callback_iter(func) as it: - ... for args, kwargs in it: - ... print(args) - (1, 'a') - (2, 'b') - (3, 'c') - - The function will be called in a background thread. The ``done`` property - indicates whether it has completed execution. - - >>> it.done - True - - If it completes successfully, its return value will be available - in the ``result`` property. - - >>> it.result - 4 - - Notes: - - * If the function uses some keyword argument besides ``callback``, supply - *callback_kwd*. - * If it finished executing, but raised an exception, accessing the - ``result`` property will raise the same exception. - * If it hasn't finished executing, accessing the ``result`` - property from within the ``with`` block will raise ``RuntimeError``. - * If it hasn't finished executing, accessing the ``result`` property from - outside the ``with`` block will raise a - ``more_itertools.AbortThread`` exception. - * Provide *wait_seconds* to adjust how frequently the it is polled for - output. - - """ - - def __init__(self, func, callback_kwd='callback', wait_seconds=0.1): - self._func = func - self._callback_kwd = callback_kwd - self._aborted = False - self._future = None - self._wait_seconds = wait_seconds - # Lazily import concurrent.future - self._executor = __import__( - 'concurrent.futures' - ).futures.ThreadPoolExecutor(max_workers=1) - self._iterator = self._reader() - - def __enter__(self): - return self - - def __exit__(self, exc_type, exc_value, traceback): - self._aborted = True - self._executor.shutdown() - - def __iter__(self): - return self - - def __next__(self): - return next(self._iterator) - - @property - def done(self): - if self._future is None: - return False - return self._future.done() - - @property - def result(self): - if not self.done: - raise RuntimeError('Function has not yet completed') - - return self._future.result() - - def _reader(self): - q = Queue() - - def callback(*args, **kwargs): - if self._aborted: - raise AbortThread('canceled by user') - - q.put((args, kwargs)) - - self._future = self._executor.submit( - self._func, **{self._callback_kwd: callback} - ) - - while True: - try: - item = q.get(timeout=self._wait_seconds) - except Empty: - pass - else: - q.task_done() - yield item - - if self._future.done(): - break - - remaining = [] - while True: - try: - item = q.get_nowait() - except Empty: - break - else: - q.task_done() - remaining.append(item) - q.join() - yield from remaining - - -def windowed_complete(iterable, n): - """ - Yield ``(beginning, middle, end)`` tuples, where: - - * Each ``middle`` has *n* items from *iterable* - * Each ``beginning`` has the items before the ones in ``middle`` - * Each ``end`` has the items after the ones in ``middle`` - - >>> iterable = range(7) - >>> n = 3 - >>> for beginning, middle, end in windowed_complete(iterable, n): - ... print(beginning, middle, end) - () (0, 1, 2) (3, 4, 5, 6) - (0,) (1, 2, 3) (4, 5, 6) - (0, 1) (2, 3, 4) (5, 6) - (0, 1, 2) (3, 4, 5) (6,) - (0, 1, 2, 3) (4, 5, 6) () - - Note that *n* must be at least 0 and most equal to the length of - *iterable*. - - This function will exhaust the iterable and may require significant - storage. - """ - if n < 0: - raise ValueError('n must be >= 0') - - seq = tuple(iterable) - size = len(seq) - - if n > size: - raise ValueError('n must be <= len(seq)') - - for i in range(size - n + 1): - beginning = seq[:i] - middle = seq[i : i + n] - end = seq[i + n :] - yield beginning, middle, end - - -def all_unique(iterable, key=None): - """ - Returns ``True`` if all the elements of *iterable* are unique (no two - elements are equal). - - >>> all_unique('ABCB') - False - - If a *key* function is specified, it will be used to make comparisons. - - >>> all_unique('ABCb') - True - >>> all_unique('ABCb', str.lower) - False - - The function returns as soon as the first non-unique element is - encountered. Iterables with a mix of hashable and unhashable items can - be used, but the function will be slower for unhashable items. - """ - seenset = set() - seenset_add = seenset.add - seenlist = [] - seenlist_add = seenlist.append - for element in map(key, iterable) if key else iterable: - try: - if element in seenset: - return False - seenset_add(element) - except TypeError: - if element in seenlist: - return False - seenlist_add(element) - return True - - -def nth_product(index, *args): - """Equivalent to ``list(product(*args))[index]``. - - The products of *args* can be ordered lexicographically. - :func:`nth_product` computes the product at sort position *index* without - computing the previous products. - - >>> nth_product(8, range(2), range(2), range(2), range(2)) - (1, 0, 0, 0) - - ``IndexError`` will be raised if the given *index* is invalid. - """ - pools = list(map(tuple, reversed(args))) - ns = list(map(len, pools)) - - c = reduce(mul, ns) - - if index < 0: - index += c - - if not 0 <= index < c: - raise IndexError - - result = [] - for pool, n in zip(pools, ns): - result.append(pool[index % n]) - index //= n - - return tuple(reversed(result)) - - -def nth_permutation(iterable, r, index): - """Equivalent to ``list(permutations(iterable, r))[index]``` - - The subsequences of *iterable* that are of length *r* where order is - important can be ordered lexicographically. :func:`nth_permutation` - computes the subsequence at sort position *index* directly, without - computing the previous subsequences. - - >>> nth_permutation('ghijk', 2, 5) - ('h', 'i') - - ``ValueError`` will be raised If *r* is negative or greater than the length - of *iterable*. - ``IndexError`` will be raised if the given *index* is invalid. - """ - pool = list(iterable) - n = len(pool) - - if r is None or r == n: - r, c = n, factorial(n) - elif not 0 <= r < n: - raise ValueError - else: - c = perm(n, r) - assert c > 0 # factortial(n)>0, and r>> nth_combination_with_replacement(range(5), 3, 5) - (0, 1, 1) - - ``ValueError`` will be raised If *r* is negative or greater than the length - of *iterable*. - ``IndexError`` will be raised if the given *index* is invalid. - """ - pool = tuple(iterable) - n = len(pool) - if (r < 0) or (r > n): - raise ValueError - - c = comb(n + r - 1, r) - - if index < 0: - index += c - - if (index < 0) or (index >= c): - raise IndexError - - result = [] - i = 0 - while r: - r -= 1 - while n >= 0: - num_combs = comb(n + r - 1, r) - if index < num_combs: - break - n -= 1 - i += 1 - index -= num_combs - result.append(pool[i]) - - return tuple(result) - - -def value_chain(*args): - """Yield all arguments passed to the function in the same order in which - they were passed. If an argument itself is iterable then iterate over its - values. - - >>> list(value_chain(1, 2, 3, [4, 5, 6])) - [1, 2, 3, 4, 5, 6] - - Binary and text strings are not considered iterable and are emitted - as-is: - - >>> list(value_chain('12', '34', ['56', '78'])) - ['12', '34', '56', '78'] - - Pre- or postpend a single element to an iterable: - - >>> list(value_chain(1, [2, 3, 4, 5, 6])) - [1, 2, 3, 4, 5, 6] - >>> list(value_chain([1, 2, 3, 4, 5], 6)) - [1, 2, 3, 4, 5, 6] - - Multiple levels of nesting are not flattened. - - """ - for value in args: - if isinstance(value, (str, bytes)): - yield value - continue - try: - yield from value - except TypeError: - yield value - - -def product_index(element, *args): - """Equivalent to ``list(product(*args)).index(element)`` - - The products of *args* can be ordered lexicographically. - :func:`product_index` computes the first index of *element* without - computing the previous products. - - >>> product_index([8, 2], range(10), range(5)) - 42 - - ``ValueError`` will be raised if the given *element* isn't in the product - of *args*. - """ - index = 0 - - for x, pool in zip_longest(element, args, fillvalue=_marker): - if x is _marker or pool is _marker: - raise ValueError('element is not a product of args') - - pool = tuple(pool) - index = index * len(pool) + pool.index(x) - - return index - - -def combination_index(element, iterable): - """Equivalent to ``list(combinations(iterable, r)).index(element)`` - - The subsequences of *iterable* that are of length *r* can be ordered - lexicographically. :func:`combination_index` computes the index of the - first *element*, without computing the previous combinations. - - >>> combination_index('adf', 'abcdefg') - 10 - - ``ValueError`` will be raised if the given *element* isn't one of the - combinations of *iterable*. - """ - element = enumerate(element) - k, y = next(element, (None, None)) - if k is None: - return 0 - - indexes = [] - pool = enumerate(iterable) - for n, x in pool: - if x == y: - indexes.append(n) - tmp, y = next(element, (None, None)) - if tmp is None: - break - else: - k = tmp - else: - raise ValueError('element is not a combination of iterable') - - n, _ = last(pool, default=(n, None)) - - # Python versions below 3.8 don't have math.comb - index = 1 - for i, j in enumerate(reversed(indexes), start=1): - j = n - j - if i <= j: - index += comb(j, i) - - return comb(n + 1, k + 1) - index - - -def combination_with_replacement_index(element, iterable): - """Equivalent to - ``list(combinations_with_replacement(iterable, r)).index(element)`` - - The subsequences with repetition of *iterable* that are of length *r* can - be ordered lexicographically. :func:`combination_with_replacement_index` - computes the index of the first *element*, without computing the previous - combinations with replacement. - - >>> combination_with_replacement_index('adf', 'abcdefg') - 20 - - ``ValueError`` will be raised if the given *element* isn't one of the - combinations with replacement of *iterable*. - """ - element = tuple(element) - l = len(element) - element = enumerate(element) - - k, y = next(element, (None, None)) - if k is None: - return 0 - - indexes = [] - pool = tuple(iterable) - for n, x in enumerate(pool): - while x == y: - indexes.append(n) - tmp, y = next(element, (None, None)) - if tmp is None: - break - else: - k = tmp - if y is None: - break - else: - raise ValueError( - 'element is not a combination with replacement of iterable' - ) - - n = len(pool) - occupations = [0] * n - for p in indexes: - occupations[p] += 1 - - index = 0 - cumulative_sum = 0 - for k in range(1, n): - cumulative_sum += occupations[k - 1] - j = l + n - 1 - k - cumulative_sum - i = n - k - if i <= j: - index += comb(j, i) - - return index - - -def permutation_index(element, iterable): - """Equivalent to ``list(permutations(iterable, r)).index(element)``` - - The subsequences of *iterable* that are of length *r* where order is - important can be ordered lexicographically. :func:`permutation_index` - computes the index of the first *element* directly, without computing - the previous permutations. - - >>> permutation_index([1, 3, 2], range(5)) - 19 - - ``ValueError`` will be raised if the given *element* isn't one of the - permutations of *iterable*. - """ - index = 0 - pool = list(iterable) - for i, x in zip(range(len(pool), -1, -1), element): - r = pool.index(x) - index = index * i + r - del pool[r] - - return index - - -class countable: - """Wrap *iterable* and keep a count of how many items have been consumed. - - The ``items_seen`` attribute starts at ``0`` and increments as the iterable - is consumed: - - >>> iterable = map(str, range(10)) - >>> it = countable(iterable) - >>> it.items_seen - 0 - >>> next(it), next(it) - ('0', '1') - >>> list(it) - ['2', '3', '4', '5', '6', '7', '8', '9'] - >>> it.items_seen - 10 - """ - - def __init__(self, iterable): - self._it = iter(iterable) - self.items_seen = 0 - - def __iter__(self): - return self - - def __next__(self): - item = next(self._it) - self.items_seen += 1 - - return item - - -def chunked_even(iterable, n): - """Break *iterable* into lists of approximately length *n*. - Items are distributed such the lengths of the lists differ by at most - 1 item. - - >>> iterable = [1, 2, 3, 4, 5, 6, 7] - >>> n = 3 - >>> list(chunked_even(iterable, n)) # List lengths: 3, 2, 2 - [[1, 2, 3], [4, 5], [6, 7]] - >>> list(chunked(iterable, n)) # List lengths: 3, 3, 1 - [[1, 2, 3], [4, 5, 6], [7]] - - """ - iterable = iter(iterable) - - # Initialize a buffer to process the chunks while keeping - # some back to fill any underfilled chunks - min_buffer = (n - 1) * (n - 2) - buffer = list(islice(iterable, min_buffer)) - - # Append items until we have a completed chunk - for _ in islice(map(buffer.append, iterable), n, None, n): - yield buffer[:n] - del buffer[:n] - - # Check if any chunks need addition processing - if not buffer: - return - length = len(buffer) - - # Chunks are either size `full_size <= n` or `partial_size = full_size - 1` - q, r = divmod(length, n) - num_lists = q + (1 if r > 0 else 0) - q, r = divmod(length, num_lists) - full_size = q + (1 if r > 0 else 0) - partial_size = full_size - 1 - num_full = length - partial_size * num_lists - - # Yield chunks of full size - partial_start_idx = num_full * full_size - if full_size > 0: - for i in range(0, partial_start_idx, full_size): - yield buffer[i : i + full_size] - - # Yield chunks of partial size - if partial_size > 0: - for i in range(partial_start_idx, length, partial_size): - yield buffer[i : i + partial_size] - - -def zip_broadcast(*objects, scalar_types=(str, bytes), strict=False): - """A version of :func:`zip` that "broadcasts" any scalar - (i.e., non-iterable) items into output tuples. - - >>> iterable_1 = [1, 2, 3] - >>> iterable_2 = ['a', 'b', 'c'] - >>> scalar = '_' - >>> list(zip_broadcast(iterable_1, iterable_2, scalar)) - [(1, 'a', '_'), (2, 'b', '_'), (3, 'c', '_')] - - The *scalar_types* keyword argument determines what types are considered - scalar. It is set to ``(str, bytes)`` by default. Set it to ``None`` to - treat strings and byte strings as iterable: - - >>> list(zip_broadcast('abc', 0, 'xyz', scalar_types=None)) - [('a', 0, 'x'), ('b', 0, 'y'), ('c', 0, 'z')] - - If the *strict* keyword argument is ``True``, then - ``UnequalIterablesError`` will be raised if any of the iterables have - different lengths. - """ - - def is_scalar(obj): - if scalar_types and isinstance(obj, scalar_types): - return True - try: - iter(obj) - except TypeError: - return True - else: - return False - - size = len(objects) - if not size: - return - - new_item = [None] * size - iterables, iterable_positions = [], [] - for i, obj in enumerate(objects): - if is_scalar(obj): - new_item[i] = obj - else: - iterables.append(iter(obj)) - iterable_positions.append(i) - - if not iterables: - yield tuple(objects) - return - - zipper = _zip_equal if strict else zip - for item in zipper(*iterables): - for i, new_item[i] in zip(iterable_positions, item): - pass - yield tuple(new_item) - - -def unique_in_window(iterable, n, key=None): - """Yield the items from *iterable* that haven't been seen recently. - *n* is the size of the lookback window. - - >>> iterable = [0, 1, 0, 2, 3, 0] - >>> n = 3 - >>> list(unique_in_window(iterable, n)) - [0, 1, 2, 3, 0] - - The *key* function, if provided, will be used to determine uniqueness: - - >>> list(unique_in_window('abAcda', 3, key=lambda x: x.lower())) - ['a', 'b', 'c', 'd', 'a'] - - The items in *iterable* must be hashable. - - """ - if n <= 0: - raise ValueError('n must be greater than 0') - - window = deque(maxlen=n) - counts = defaultdict(int) - use_key = key is not None - - for item in iterable: - if len(window) == n: - to_discard = window[0] - if counts[to_discard] == 1: - del counts[to_discard] - else: - counts[to_discard] -= 1 - - k = key(item) if use_key else item - if k not in counts: - yield item - counts[k] += 1 - window.append(k) - - -def duplicates_everseen(iterable, key=None): - """Yield duplicate elements after their first appearance. - - >>> list(duplicates_everseen('mississippi')) - ['s', 'i', 's', 's', 'i', 'p', 'i'] - >>> list(duplicates_everseen('AaaBbbCccAaa', str.lower)) - ['a', 'a', 'b', 'b', 'c', 'c', 'A', 'a', 'a'] - - This function is analogous to :func:`unique_everseen` and is subject to - the same performance considerations. - - """ - seen_set = set() - seen_list = [] - use_key = key is not None - - for element in iterable: - k = key(element) if use_key else element - try: - if k not in seen_set: - seen_set.add(k) - else: - yield element - except TypeError: - if k not in seen_list: - seen_list.append(k) - else: - yield element - - -def duplicates_justseen(iterable, key=None): - """Yields serially-duplicate elements after their first appearance. - - >>> list(duplicates_justseen('mississippi')) - ['s', 's', 'p'] - >>> list(duplicates_justseen('AaaBbbCccAaa', str.lower)) - ['a', 'a', 'b', 'b', 'c', 'c', 'a', 'a'] - - This function is analogous to :func:`unique_justseen`. - - """ - return flatten(g for _, g in groupby(iterable, key) for _ in g) - - -def classify_unique(iterable, key=None): - """Classify each element in terms of its uniqueness. - - For each element in the input iterable, return a 3-tuple consisting of: - - 1. The element itself - 2. ``False`` if the element is equal to the one preceding it in the input, - ``True`` otherwise (i.e. the equivalent of :func:`unique_justseen`) - 3. ``False`` if this element has been seen anywhere in the input before, - ``True`` otherwise (i.e. the equivalent of :func:`unique_everseen`) - - >>> list(classify_unique('otto')) # doctest: +NORMALIZE_WHITESPACE - [('o', True, True), - ('t', True, True), - ('t', False, False), - ('o', True, False)] - - This function is analogous to :func:`unique_everseen` and is subject to - the same performance considerations. - - """ - seen_set = set() - seen_list = [] - use_key = key is not None - previous = None - - for i, element in enumerate(iterable): - k = key(element) if use_key else element - is_unique_justseen = not i or previous != k - previous = k - is_unique_everseen = False - try: - if k not in seen_set: - seen_set.add(k) - is_unique_everseen = True - except TypeError: - if k not in seen_list: - seen_list.append(k) - is_unique_everseen = True - yield element, is_unique_justseen, is_unique_everseen - - -def minmax(iterable_or_value, *others, key=None, default=_marker): - """Returns both the smallest and largest items in an iterable - or the largest of two or more arguments. - - >>> minmax([3, 1, 5]) - (1, 5) - - >>> minmax(4, 2, 6) - (2, 6) - - If a *key* function is provided, it will be used to transform the input - items for comparison. - - >>> minmax([5, 30], key=str) # '30' sorts before '5' - (30, 5) - - If a *default* value is provided, it will be returned if there are no - input items. - - >>> minmax([], default=(0, 0)) - (0, 0) - - Otherwise ``ValueError`` is raised. - - This function is based on the - `recipe `__ by - Raymond Hettinger and takes care to minimize the number of comparisons - performed. - """ - iterable = (iterable_or_value, *others) if others else iterable_or_value - - it = iter(iterable) - - try: - lo = hi = next(it) - except StopIteration as exc: - if default is _marker: - raise ValueError( - '`minmax()` argument is an empty iterable. ' - 'Provide a `default` value to suppress this error.' - ) from exc - return default - - # Different branches depending on the presence of key. This saves a lot - # of unimportant copies which would slow the "key=None" branch - # significantly down. - if key is None: - for x, y in zip_longest(it, it, fillvalue=lo): - if y < x: - x, y = y, x - if x < lo: - lo = x - if hi < y: - hi = y - - else: - lo_key = hi_key = key(lo) - - for x, y in zip_longest(it, it, fillvalue=lo): - x_key, y_key = key(x), key(y) - - if y_key < x_key: - x, y, x_key, y_key = y, x, y_key, x_key - if x_key < lo_key: - lo, lo_key = x, x_key - if hi_key < y_key: - hi, hi_key = y, y_key - - return lo, hi - - -def constrained_batches( - iterable, max_size, max_count=None, get_len=len, strict=True -): - """Yield batches of items from *iterable* with a combined size limited by - *max_size*. - - >>> iterable = [b'12345', b'123', b'12345678', b'1', b'1', b'12', b'1'] - >>> list(constrained_batches(iterable, 10)) - [(b'12345', b'123'), (b'12345678', b'1', b'1'), (b'12', b'1')] - - If a *max_count* is supplied, the number of items per batch is also - limited: - - >>> iterable = [b'12345', b'123', b'12345678', b'1', b'1', b'12', b'1'] - >>> list(constrained_batches(iterable, 10, max_count = 2)) - [(b'12345', b'123'), (b'12345678', b'1'), (b'1', b'12'), (b'1',)] - - If a *get_len* function is supplied, use that instead of :func:`len` to - determine item size. - - If *strict* is ``True``, raise ``ValueError`` if any single item is bigger - than *max_size*. Otherwise, allow single items to exceed *max_size*. - """ - if max_size <= 0: - raise ValueError('maximum size must be greater than zero') - - batch = [] - batch_size = 0 - batch_count = 0 - for item in iterable: - item_len = get_len(item) - if strict and item_len > max_size: - raise ValueError('item size exceeds maximum size') - - reached_count = batch_count == max_count - reached_size = item_len + batch_size > max_size - if batch_count and (reached_size or reached_count): - yield tuple(batch) - batch.clear() - batch_size = 0 - batch_count = 0 - - batch.append(item) - batch_size += item_len - batch_count += 1 - - if batch: - yield tuple(batch) - - -def gray_product(*iterables): - """Like :func:`itertools.product`, but return tuples in an order such - that only one element in the generated tuple changes from one iteration - to the next. - - >>> list(gray_product('AB','CD')) - [('A', 'C'), ('B', 'C'), ('B', 'D'), ('A', 'D')] - - This function consumes all of the input iterables before producing output. - If any of the input iterables have fewer than two items, ``ValueError`` - is raised. - - For information on the algorithm, see - `this section `__ - of Donald Knuth's *The Art of Computer Programming*. - """ - all_iterables = tuple(tuple(x) for x in iterables) - iterable_count = len(all_iterables) - for iterable in all_iterables: - if len(iterable) < 2: - raise ValueError("each iterable must have two or more items") - - # This is based on "Algorithm H" from section 7.2.1.1, page 20. - # a holds the indexes of the source iterables for the n-tuple to be yielded - # f is the array of "focus pointers" - # o is the array of "directions" - a = [0] * iterable_count - f = list(range(iterable_count + 1)) - o = [1] * iterable_count - while True: - yield tuple(all_iterables[i][a[i]] for i in range(iterable_count)) - j = f[0] - f[0] = 0 - if j == iterable_count: - break - a[j] = a[j] + o[j] - if a[j] == 0 or a[j] == len(all_iterables[j]) - 1: - o[j] = -o[j] - f[j] = f[j + 1] - f[j + 1] = j + 1 - - -def partial_product(*iterables): - """Yields tuples containing one item from each iterator, with subsequent - tuples changing a single item at a time by advancing each iterator until it - is exhausted. This sequence guarantees every value in each iterable is - output at least once without generating all possible combinations. - - This may be useful, for example, when testing an expensive function. - - >>> list(partial_product('AB', 'C', 'DEF')) - [('A', 'C', 'D'), ('B', 'C', 'D'), ('B', 'C', 'E'), ('B', 'C', 'F')] - """ - - iterators = list(map(iter, iterables)) - - try: - prod = [next(it) for it in iterators] - except StopIteration: - return - yield tuple(prod) - - for i, it in enumerate(iterators): - for prod[i] in it: - yield tuple(prod) - - -def takewhile_inclusive(predicate, iterable): - """A variant of :func:`takewhile` that yields one additional element. - - >>> list(takewhile_inclusive(lambda x: x < 5, [1, 4, 6, 4, 1])) - [1, 4, 6] - - :func:`takewhile` would return ``[1, 4]``. - """ - for x in iterable: - yield x - if not predicate(x): - break - - -def outer_product(func, xs, ys, *args, **kwargs): - """A generalized outer product that applies a binary function to all - pairs of items. Returns a 2D matrix with ``len(xs)`` rows and ``len(ys)`` - columns. - Also accepts ``*args`` and ``**kwargs`` that are passed to ``func``. - - Multiplication table: - - >>> list(outer_product(mul, range(1, 4), range(1, 6))) - [(1, 2, 3, 4, 5), (2, 4, 6, 8, 10), (3, 6, 9, 12, 15)] - - Cross tabulation: - - >>> xs = ['A', 'B', 'A', 'A', 'B', 'B', 'A', 'A', 'B', 'B'] - >>> ys = ['X', 'X', 'X', 'Y', 'Z', 'Z', 'Y', 'Y', 'Z', 'Z'] - >>> rows = list(zip(xs, ys)) - >>> count_rows = lambda x, y: rows.count((x, y)) - >>> list(outer_product(count_rows, sorted(set(xs)), sorted(set(ys)))) - [(2, 3, 0), (1, 0, 4)] - - Usage with ``*args`` and ``**kwargs``: - - >>> animals = ['cat', 'wolf', 'mouse'] - >>> list(outer_product(min, animals, animals, key=len)) - [('cat', 'cat', 'cat'), ('cat', 'wolf', 'wolf'), ('cat', 'wolf', 'mouse')] - """ - ys = tuple(ys) - return batched( - starmap(lambda x, y: func(x, y, *args, **kwargs), product(xs, ys)), - n=len(ys), - ) - - -def iter_suppress(iterable, *exceptions): - """Yield each of the items from *iterable*. If the iteration raises one of - the specified *exceptions*, that exception will be suppressed and iteration - will stop. - - >>> from itertools import chain - >>> def breaks_at_five(x): - ... while True: - ... if x >= 5: - ... raise RuntimeError - ... yield x - ... x += 1 - >>> it_1 = iter_suppress(breaks_at_five(1), RuntimeError) - >>> it_2 = iter_suppress(breaks_at_five(2), RuntimeError) - >>> list(chain(it_1, it_2)) - [1, 2, 3, 4, 2, 3, 4] - """ - try: - yield from iterable - except exceptions: - return - - -def filter_map(func, iterable): - """Apply *func* to every element of *iterable*, yielding only those which - are not ``None``. - - >>> elems = ['1', 'a', '2', 'b', '3'] - >>> list(filter_map(lambda s: int(s) if s.isnumeric() else None, elems)) - [1, 2, 3] - """ - for x in iterable: - y = func(x) - if y is not None: - yield y - - -def powerset_of_sets(iterable): - """Yields all possible subsets of the iterable. - - >>> list(powerset_of_sets([1, 2, 3])) # doctest: +SKIP - [set(), {1}, {2}, {3}, {1, 2}, {1, 3}, {2, 3}, {1, 2, 3}] - >>> list(powerset_of_sets([1, 1, 0])) # doctest: +SKIP - [set(), {1}, {0}, {0, 1}] - - :func:`powerset_of_sets` takes care to minimize the number - of hash operations performed. - """ - sets = tuple(map(set, dict.fromkeys(map(frozenset, zip(iterable))))) - for r in range(len(sets) + 1): - yield from starmap(set().union, combinations(sets, r)) - - -def join_mappings(**field_to_map): - """ - Joins multiple mappings together using their common keys. - - >>> user_scores = {'elliot': 50, 'claris': 60} - >>> user_times = {'elliot': 30, 'claris': 40} - >>> join_mappings(score=user_scores, time=user_times) - {'elliot': {'score': 50, 'time': 30}, 'claris': {'score': 60, 'time': 40}} - """ - ret = defaultdict(dict) - - for field_name, mapping in field_to_map.items(): - for key, value in mapping.items(): - ret[key][field_name] = value - - return dict(ret) - - -def _complex_sumprod(v1, v2): - """High precision sumprod() for complex numbers. - Used by :func:`dft` and :func:`idft`. - """ - - r1 = chain((p.real for p in v1), (-p.imag for p in v1)) - r2 = chain((q.real for q in v2), (q.imag for q in v2)) - i1 = chain((p.real for p in v1), (p.imag for p in v1)) - i2 = chain((q.imag for q in v2), (q.real for q in v2)) - return complex(_fsumprod(r1, r2), _fsumprod(i1, i2)) - - -def dft(xarr): - """Discrete Fourier Tranform. *xarr* is a sequence of complex numbers. - Yields the components of the corresponding transformed output vector. - - >>> import cmath - >>> xarr = [1, 2-1j, -1j, -1+2j] - >>> Xarr = [2, -2-2j, -2j, 4+4j] - >>> all(map(cmath.isclose, dft(xarr), Xarr)) - True - - See :func:`idft` for the inverse Discrete Fourier Transform. - """ - N = len(xarr) - roots_of_unity = [e ** (n / N * tau * -1j) for n in range(N)] - for k in range(N): - coeffs = [roots_of_unity[k * n % N] for n in range(N)] - yield _complex_sumprod(xarr, coeffs) - - -def idft(Xarr): - """Inverse Discrete Fourier Tranform. *Xarr* is a sequence of - complex numbers. Yields the components of the corresponding - inverse-transformed output vector. - - >>> import cmath - >>> xarr = [1, 2-1j, -1j, -1+2j] - >>> Xarr = [2, -2-2j, -2j, 4+4j] - >>> all(map(cmath.isclose, idft(Xarr), xarr)) - True - - See :func:`dft` for the Discrete Fourier Transform. - """ - N = len(Xarr) - roots_of_unity = [e ** (n / N * tau * 1j) for n in range(N)] - for k in range(N): - coeffs = [roots_of_unity[k * n % N] for n in range(N)] - yield _complex_sumprod(Xarr, coeffs) / N - - -def doublestarmap(func, iterable): - """Apply *func* to every item of *iterable* by dictionary unpacking - the item into *func*. - - The difference between :func:`itertools.starmap` and :func:`doublestarmap` - parallels the distinction between ``func(*a)`` and ``func(**a)``. - - >>> iterable = [{'a': 1, 'b': 2}, {'a': 40, 'b': 60}] - >>> list(doublestarmap(lambda a, b: a + b, iterable)) - [3, 100] - - ``TypeError`` will be raised if *func*'s signature doesn't match the - mapping contained in *iterable* or if *iterable* does not contain mappings. - """ - for item in iterable: - yield func(**item) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/more.pyi b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/more.pyi deleted file mode 100644 index e946023..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/more.pyi +++ /dev/null @@ -1,709 +0,0 @@ -"""Stubs for more_itertools.more""" - -from __future__ import annotations - -from types import TracebackType -from typing import ( - Any, - Callable, - Container, - ContextManager, - Generic, - Hashable, - Mapping, - Iterable, - Iterator, - Mapping, - overload, - Reversible, - Sequence, - Sized, - Type, - TypeVar, - type_check_only, -) -from typing_extensions import Protocol - -# Type and type variable definitions -_T = TypeVar('_T') -_T1 = TypeVar('_T1') -_T2 = TypeVar('_T2') -_U = TypeVar('_U') -_V = TypeVar('_V') -_W = TypeVar('_W') -_T_co = TypeVar('_T_co', covariant=True) -_GenFn = TypeVar('_GenFn', bound=Callable[..., Iterator[Any]]) -_Raisable = BaseException | Type[BaseException] - -@type_check_only -class _SizedIterable(Protocol[_T_co], Sized, Iterable[_T_co]): ... - -@type_check_only -class _SizedReversible(Protocol[_T_co], Sized, Reversible[_T_co]): ... - -@type_check_only -class _SupportsSlicing(Protocol[_T_co]): - def __getitem__(self, __k: slice) -> _T_co: ... - -def chunked( - iterable: Iterable[_T], n: int | None, strict: bool = ... -) -> Iterator[list[_T]]: ... -@overload -def first(iterable: Iterable[_T]) -> _T: ... -@overload -def first(iterable: Iterable[_T], default: _U) -> _T | _U: ... -@overload -def last(iterable: Iterable[_T]) -> _T: ... -@overload -def last(iterable: Iterable[_T], default: _U) -> _T | _U: ... -@overload -def nth_or_last(iterable: Iterable[_T], n: int) -> _T: ... -@overload -def nth_or_last(iterable: Iterable[_T], n: int, default: _U) -> _T | _U: ... - -class peekable(Generic[_T], Iterator[_T]): - def __init__(self, iterable: Iterable[_T]) -> None: ... - def __iter__(self) -> peekable[_T]: ... - def __bool__(self) -> bool: ... - @overload - def peek(self) -> _T: ... - @overload - def peek(self, default: _U) -> _T | _U: ... - def prepend(self, *items: _T) -> None: ... - def __next__(self) -> _T: ... - @overload - def __getitem__(self, index: int) -> _T: ... - @overload - def __getitem__(self, index: slice) -> list[_T]: ... - -def consumer(func: _GenFn) -> _GenFn: ... -def ilen(iterable: Iterable[_T]) -> int: ... -def iterate(func: Callable[[_T], _T], start: _T) -> Iterator[_T]: ... -def with_iter( - context_manager: ContextManager[Iterable[_T]], -) -> Iterator[_T]: ... -def one( - iterable: Iterable[_T], - too_short: _Raisable | None = ..., - too_long: _Raisable | None = ..., -) -> _T: ... -def raise_(exception: _Raisable, *args: Any) -> None: ... -def strictly_n( - iterable: Iterable[_T], - n: int, - too_short: _GenFn | None = ..., - too_long: _GenFn | None = ..., -) -> list[_T]: ... -def distinct_permutations( - iterable: Iterable[_T], r: int | None = ... -) -> Iterator[tuple[_T, ...]]: ... -def intersperse( - e: _U, iterable: Iterable[_T], n: int = ... -) -> Iterator[_T | _U]: ... -def unique_to_each(*iterables: Iterable[_T]) -> list[list[_T]]: ... -@overload -def windowed( - seq: Iterable[_T], n: int, *, step: int = ... -) -> Iterator[tuple[_T | None, ...]]: ... -@overload -def windowed( - seq: Iterable[_T], n: int, fillvalue: _U, step: int = ... -) -> Iterator[tuple[_T | _U, ...]]: ... -def substrings(iterable: Iterable[_T]) -> Iterator[tuple[_T, ...]]: ... -def substrings_indexes( - seq: Sequence[_T], reverse: bool = ... -) -> Iterator[tuple[Sequence[_T], int, int]]: ... - -class bucket(Generic[_T, _U], Container[_U]): - def __init__( - self, - iterable: Iterable[_T], - key: Callable[[_T], _U], - validator: Callable[[_U], object] | None = ..., - ) -> None: ... - def __contains__(self, value: object) -> bool: ... - def __iter__(self) -> Iterator[_U]: ... - def __getitem__(self, value: object) -> Iterator[_T]: ... - -def spy( - iterable: Iterable[_T], n: int = ... -) -> tuple[list[_T], Iterator[_T]]: ... -def interleave(*iterables: Iterable[_T]) -> Iterator[_T]: ... -def interleave_longest(*iterables: Iterable[_T]) -> Iterator[_T]: ... -def interleave_evenly( - iterables: list[Iterable[_T]], lengths: list[int] | None = ... -) -> Iterator[_T]: ... -def collapse( - iterable: Iterable[Any], - base_type: type | None = ..., - levels: int | None = ..., -) -> Iterator[Any]: ... -@overload -def side_effect( - func: Callable[[_T], object], - iterable: Iterable[_T], - chunk_size: None = ..., - before: Callable[[], object] | None = ..., - after: Callable[[], object] | None = ..., -) -> Iterator[_T]: ... -@overload -def side_effect( - func: Callable[[list[_T]], object], - iterable: Iterable[_T], - chunk_size: int, - before: Callable[[], object] | None = ..., - after: Callable[[], object] | None = ..., -) -> Iterator[_T]: ... -def sliced( - seq: _SupportsSlicing[_T], n: int, strict: bool = ... -) -> Iterator[_T]: ... -def split_at( - iterable: Iterable[_T], - pred: Callable[[_T], object], - maxsplit: int = ..., - keep_separator: bool = ..., -) -> Iterator[list[_T]]: ... -def split_before( - iterable: Iterable[_T], pred: Callable[[_T], object], maxsplit: int = ... -) -> Iterator[list[_T]]: ... -def split_after( - iterable: Iterable[_T], pred: Callable[[_T], object], maxsplit: int = ... -) -> Iterator[list[_T]]: ... -def split_when( - iterable: Iterable[_T], - pred: Callable[[_T, _T], object], - maxsplit: int = ..., -) -> Iterator[list[_T]]: ... -def split_into( - iterable: Iterable[_T], sizes: Iterable[int | None] -) -> Iterator[list[_T]]: ... -@overload -def padded( - iterable: Iterable[_T], - *, - n: int | None = ..., - next_multiple: bool = ..., -) -> Iterator[_T | None]: ... -@overload -def padded( - iterable: Iterable[_T], - fillvalue: _U, - n: int | None = ..., - next_multiple: bool = ..., -) -> Iterator[_T | _U]: ... -@overload -def repeat_last(iterable: Iterable[_T]) -> Iterator[_T]: ... -@overload -def repeat_last(iterable: Iterable[_T], default: _U) -> Iterator[_T | _U]: ... -def distribute(n: int, iterable: Iterable[_T]) -> list[Iterator[_T]]: ... -@overload -def stagger( - iterable: Iterable[_T], - offsets: _SizedIterable[int] = ..., - longest: bool = ..., -) -> Iterator[tuple[_T | None, ...]]: ... -@overload -def stagger( - iterable: Iterable[_T], - offsets: _SizedIterable[int] = ..., - longest: bool = ..., - fillvalue: _U = ..., -) -> Iterator[tuple[_T | _U, ...]]: ... - -class UnequalIterablesError(ValueError): - def __init__(self, details: tuple[int, int, int] | None = ...) -> None: ... - -@overload -def zip_equal(__iter1: Iterable[_T1]) -> Iterator[tuple[_T1]]: ... -@overload -def zip_equal( - __iter1: Iterable[_T1], __iter2: Iterable[_T2] -) -> Iterator[tuple[_T1, _T2]]: ... -@overload -def zip_equal( - __iter1: Iterable[_T], - __iter2: Iterable[_T], - __iter3: Iterable[_T], - *iterables: Iterable[_T], -) -> Iterator[tuple[_T, ...]]: ... -@overload -def zip_offset( - __iter1: Iterable[_T1], - *, - offsets: _SizedIterable[int], - longest: bool = ..., - fillvalue: None = None, -) -> Iterator[tuple[_T1 | None]]: ... -@overload -def zip_offset( - __iter1: Iterable[_T1], - __iter2: Iterable[_T2], - *, - offsets: _SizedIterable[int], - longest: bool = ..., - fillvalue: None = None, -) -> Iterator[tuple[_T1 | None, _T2 | None]]: ... -@overload -def zip_offset( - __iter1: Iterable[_T], - __iter2: Iterable[_T], - __iter3: Iterable[_T], - *iterables: Iterable[_T], - offsets: _SizedIterable[int], - longest: bool = ..., - fillvalue: None = None, -) -> Iterator[tuple[_T | None, ...]]: ... -@overload -def zip_offset( - __iter1: Iterable[_T1], - *, - offsets: _SizedIterable[int], - longest: bool = ..., - fillvalue: _U, -) -> Iterator[tuple[_T1 | _U]]: ... -@overload -def zip_offset( - __iter1: Iterable[_T1], - __iter2: Iterable[_T2], - *, - offsets: _SizedIterable[int], - longest: bool = ..., - fillvalue: _U, -) -> Iterator[tuple[_T1 | _U, _T2 | _U]]: ... -@overload -def zip_offset( - __iter1: Iterable[_T], - __iter2: Iterable[_T], - __iter3: Iterable[_T], - *iterables: Iterable[_T], - offsets: _SizedIterable[int], - longest: bool = ..., - fillvalue: _U, -) -> Iterator[tuple[_T | _U, ...]]: ... -def sort_together( - iterables: Iterable[Iterable[_T]], - key_list: Iterable[int] = ..., - key: Callable[..., Any] | None = ..., - reverse: bool = ..., -) -> list[tuple[_T, ...]]: ... -def unzip(iterable: Iterable[Sequence[_T]]) -> tuple[Iterator[_T], ...]: ... -def divide(n: int, iterable: Iterable[_T]) -> list[Iterator[_T]]: ... -def always_iterable( - obj: object, - base_type: type | tuple[type | tuple[Any, ...], ...] | None = ..., -) -> Iterator[Any]: ... -def adjacent( - predicate: Callable[[_T], bool], - iterable: Iterable[_T], - distance: int = ..., -) -> Iterator[tuple[bool, _T]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: None = None, - valuefunc: None = None, - reducefunc: None = None, -) -> Iterator[tuple[_T, Iterator[_T]]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: None, - reducefunc: None, -) -> Iterator[tuple[_U, Iterator[_T]]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: None, - valuefunc: Callable[[_T], _V], - reducefunc: None, -) -> Iterable[tuple[_T, Iterable[_V]]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: Callable[[_T], _V], - reducefunc: None, -) -> Iterable[tuple[_U, Iterator[_V]]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: None, - valuefunc: None, - reducefunc: Callable[[Iterator[_T]], _W], -) -> Iterable[tuple[_T, _W]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: None, - reducefunc: Callable[[Iterator[_T]], _W], -) -> Iterable[tuple[_U, _W]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: None, - valuefunc: Callable[[_T], _V], - reducefunc: Callable[[Iterable[_V]], _W], -) -> Iterable[tuple[_T, _W]]: ... -@overload -def groupby_transform( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: Callable[[_T], _V], - reducefunc: Callable[[Iterable[_V]], _W], -) -> Iterable[tuple[_U, _W]]: ... - -class numeric_range(Generic[_T, _U], Sequence[_T], Hashable, Reversible[_T]): - @overload - def __init__(self, __stop: _T) -> None: ... - @overload - def __init__(self, __start: _T, __stop: _T) -> None: ... - @overload - def __init__(self, __start: _T, __stop: _T, __step: _U) -> None: ... - def __bool__(self) -> bool: ... - def __contains__(self, elem: object) -> bool: ... - def __eq__(self, other: object) -> bool: ... - @overload - def __getitem__(self, key: int) -> _T: ... - @overload - def __getitem__(self, key: slice) -> numeric_range[_T, _U]: ... - def __hash__(self) -> int: ... - def __iter__(self) -> Iterator[_T]: ... - def __len__(self) -> int: ... - def __reduce__( - self, - ) -> tuple[Type[numeric_range[_T, _U]], tuple[_T, _T, _U]]: ... - def __repr__(self) -> str: ... - def __reversed__(self) -> Iterator[_T]: ... - def count(self, value: _T) -> int: ... - def index(self, value: _T) -> int: ... # type: ignore - -def count_cycle( - iterable: Iterable[_T], n: int | None = ... -) -> Iterable[tuple[int, _T]]: ... -def mark_ends( - iterable: Iterable[_T], -) -> Iterable[tuple[bool, bool, _T]]: ... -def locate( - iterable: Iterable[_T], - pred: Callable[..., Any] = ..., - window_size: int | None = ..., -) -> Iterator[int]: ... -def lstrip( - iterable: Iterable[_T], pred: Callable[[_T], object] -) -> Iterator[_T]: ... -def rstrip( - iterable: Iterable[_T], pred: Callable[[_T], object] -) -> Iterator[_T]: ... -def strip( - iterable: Iterable[_T], pred: Callable[[_T], object] -) -> Iterator[_T]: ... - -class islice_extended(Generic[_T], Iterator[_T]): - def __init__(self, iterable: Iterable[_T], *args: int | None) -> None: ... - def __iter__(self) -> islice_extended[_T]: ... - def __next__(self) -> _T: ... - def __getitem__(self, index: slice) -> islice_extended[_T]: ... - -def always_reversible(iterable: Iterable[_T]) -> Iterator[_T]: ... -def consecutive_groups( - iterable: Iterable[_T], ordering: Callable[[_T], int] = ... -) -> Iterator[Iterator[_T]]: ... -@overload -def difference( - iterable: Iterable[_T], - func: Callable[[_T, _T], _U] = ..., - *, - initial: None = ..., -) -> Iterator[_T | _U]: ... -@overload -def difference( - iterable: Iterable[_T], func: Callable[[_T, _T], _U] = ..., *, initial: _U -) -> Iterator[_U]: ... - -class SequenceView(Generic[_T], Sequence[_T]): - def __init__(self, target: Sequence[_T]) -> None: ... - @overload - def __getitem__(self, index: int) -> _T: ... - @overload - def __getitem__(self, index: slice) -> Sequence[_T]: ... - def __len__(self) -> int: ... - -class seekable(Generic[_T], Iterator[_T]): - def __init__( - self, iterable: Iterable[_T], maxlen: int | None = ... - ) -> None: ... - def __iter__(self) -> seekable[_T]: ... - def __next__(self) -> _T: ... - def __bool__(self) -> bool: ... - @overload - def peek(self) -> _T: ... - @overload - def peek(self, default: _U) -> _T | _U: ... - def elements(self) -> SequenceView[_T]: ... - def seek(self, index: int) -> None: ... - def relative_seek(self, count: int) -> None: ... - -class run_length: - @staticmethod - def encode(iterable: Iterable[_T]) -> Iterator[tuple[_T, int]]: ... - @staticmethod - def decode(iterable: Iterable[tuple[_T, int]]) -> Iterator[_T]: ... - -def exactly_n( - iterable: Iterable[_T], n: int, predicate: Callable[[_T], object] = ... -) -> bool: ... -def circular_shifts(iterable: Iterable[_T]) -> list[tuple[_T, ...]]: ... -def make_decorator( - wrapping_func: Callable[..., _U], result_index: int = ... -) -> Callable[..., Callable[[Callable[..., Any]], Callable[..., _U]]]: ... -@overload -def map_reduce( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: None = ..., - reducefunc: None = ..., -) -> dict[_U, list[_T]]: ... -@overload -def map_reduce( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: Callable[[_T], _V], - reducefunc: None = ..., -) -> dict[_U, list[_V]]: ... -@overload -def map_reduce( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: None = ..., - reducefunc: Callable[[list[_T]], _W] = ..., -) -> dict[_U, _W]: ... -@overload -def map_reduce( - iterable: Iterable[_T], - keyfunc: Callable[[_T], _U], - valuefunc: Callable[[_T], _V], - reducefunc: Callable[[list[_V]], _W], -) -> dict[_U, _W]: ... -def rlocate( - iterable: Iterable[_T], - pred: Callable[..., object] = ..., - window_size: int | None = ..., -) -> Iterator[int]: ... -def replace( - iterable: Iterable[_T], - pred: Callable[..., object], - substitutes: Iterable[_U], - count: int | None = ..., - window_size: int = ..., -) -> Iterator[_T | _U]: ... -def partitions(iterable: Iterable[_T]) -> Iterator[list[list[_T]]]: ... -def set_partitions( - iterable: Iterable[_T], k: int | None = ... -) -> Iterator[list[list[_T]]]: ... - -class time_limited(Generic[_T], Iterator[_T]): - def __init__( - self, limit_seconds: float, iterable: Iterable[_T] - ) -> None: ... - def __iter__(self) -> islice_extended[_T]: ... - def __next__(self) -> _T: ... - -@overload -def only( - iterable: Iterable[_T], *, too_long: _Raisable | None = ... -) -> _T | None: ... -@overload -def only( - iterable: Iterable[_T], default: _U, too_long: _Raisable | None = ... -) -> _T | _U: ... -def ichunked(iterable: Iterable[_T], n: int) -> Iterator[Iterator[_T]]: ... -def distinct_combinations( - iterable: Iterable[_T], r: int -) -> Iterator[tuple[_T, ...]]: ... -def filter_except( - validator: Callable[[Any], object], - iterable: Iterable[_T], - *exceptions: Type[BaseException], -) -> Iterator[_T]: ... -def map_except( - function: Callable[[Any], _U], - iterable: Iterable[_T], - *exceptions: Type[BaseException], -) -> Iterator[_U]: ... -def map_if( - iterable: Iterable[Any], - pred: Callable[[Any], bool], - func: Callable[[Any], Any], - func_else: Callable[[Any], Any] | None = ..., -) -> Iterator[Any]: ... -def sample( - iterable: Iterable[_T], - k: int, - weights: Iterable[float] | None = ..., -) -> list[_T]: ... -def is_sorted( - iterable: Iterable[_T], - key: Callable[[_T], _U] | None = ..., - reverse: bool = False, - strict: bool = False, -) -> bool: ... - -class AbortThread(BaseException): - pass - -class callback_iter(Generic[_T], Iterator[_T]): - def __init__( - self, - func: Callable[..., Any], - callback_kwd: str = ..., - wait_seconds: float = ..., - ) -> None: ... - def __enter__(self) -> callback_iter[_T]: ... - def __exit__( - self, - exc_type: Type[BaseException] | None, - exc_value: BaseException | None, - traceback: TracebackType | None, - ) -> bool | None: ... - def __iter__(self) -> callback_iter[_T]: ... - def __next__(self) -> _T: ... - def _reader(self) -> Iterator[_T]: ... - @property - def done(self) -> bool: ... - @property - def result(self) -> Any: ... - -def windowed_complete( - iterable: Iterable[_T], n: int -) -> Iterator[tuple[_T, ...]]: ... -def all_unique( - iterable: Iterable[_T], key: Callable[[_T], _U] | None = ... -) -> bool: ... -def nth_product(index: int, *args: Iterable[_T]) -> tuple[_T, ...]: ... -def nth_combination_with_replacement( - iterable: Iterable[_T], r: int, index: int -) -> tuple[_T, ...]: ... -def nth_permutation( - iterable: Iterable[_T], r: int, index: int -) -> tuple[_T, ...]: ... -def value_chain(*args: _T | Iterable[_T]) -> Iterable[_T]: ... -def product_index(element: Iterable[_T], *args: Iterable[_T]) -> int: ... -def combination_index( - element: Iterable[_T], iterable: Iterable[_T] -) -> int: ... -def combination_with_replacement_index( - element: Iterable[_T], iterable: Iterable[_T] -) -> int: ... -def permutation_index( - element: Iterable[_T], iterable: Iterable[_T] -) -> int: ... -def repeat_each(iterable: Iterable[_T], n: int = ...) -> Iterator[_T]: ... - -class countable(Generic[_T], Iterator[_T]): - def __init__(self, iterable: Iterable[_T]) -> None: ... - def __iter__(self) -> countable[_T]: ... - def __next__(self) -> _T: ... - items_seen: int - -def chunked_even(iterable: Iterable[_T], n: int) -> Iterator[list[_T]]: ... -def zip_broadcast( - *objects: _T | Iterable[_T], - scalar_types: type | tuple[type | tuple[Any, ...], ...] | None = ..., - strict: bool = ..., -) -> Iterable[tuple[_T, ...]]: ... -def unique_in_window( - iterable: Iterable[_T], n: int, key: Callable[[_T], _U] | None = ... -) -> Iterator[_T]: ... -def duplicates_everseen( - iterable: Iterable[_T], key: Callable[[_T], _U] | None = ... -) -> Iterator[_T]: ... -def duplicates_justseen( - iterable: Iterable[_T], key: Callable[[_T], _U] | None = ... -) -> Iterator[_T]: ... -def classify_unique( - iterable: Iterable[_T], key: Callable[[_T], _U] | None = ... -) -> Iterator[tuple[_T, bool, bool]]: ... - -class _SupportsLessThan(Protocol): - def __lt__(self, __other: Any) -> bool: ... - -_SupportsLessThanT = TypeVar("_SupportsLessThanT", bound=_SupportsLessThan) - -@overload -def minmax( - iterable_or_value: Iterable[_SupportsLessThanT], *, key: None = None -) -> tuple[_SupportsLessThanT, _SupportsLessThanT]: ... -@overload -def minmax( - iterable_or_value: Iterable[_T], *, key: Callable[[_T], _SupportsLessThan] -) -> tuple[_T, _T]: ... -@overload -def minmax( - iterable_or_value: Iterable[_SupportsLessThanT], - *, - key: None = None, - default: _U, -) -> _U | tuple[_SupportsLessThanT, _SupportsLessThanT]: ... -@overload -def minmax( - iterable_or_value: Iterable[_T], - *, - key: Callable[[_T], _SupportsLessThan], - default: _U, -) -> _U | tuple[_T, _T]: ... -@overload -def minmax( - iterable_or_value: _SupportsLessThanT, - __other: _SupportsLessThanT, - *others: _SupportsLessThanT, -) -> tuple[_SupportsLessThanT, _SupportsLessThanT]: ... -@overload -def minmax( - iterable_or_value: _T, - __other: _T, - *others: _T, - key: Callable[[_T], _SupportsLessThan], -) -> tuple[_T, _T]: ... -def longest_common_prefix( - iterables: Iterable[Iterable[_T]], -) -> Iterator[_T]: ... -def iequals(*iterables: Iterable[Any]) -> bool: ... -def constrained_batches( - iterable: Iterable[_T], - max_size: int, - max_count: int | None = ..., - get_len: Callable[[_T], object] = ..., - strict: bool = ..., -) -> Iterator[tuple[_T]]: ... -def gray_product(*iterables: Iterable[_T]) -> Iterator[tuple[_T, ...]]: ... -def partial_product(*iterables: Iterable[_T]) -> Iterator[tuple[_T, ...]]: ... -def takewhile_inclusive( - predicate: Callable[[_T], bool], iterable: Iterable[_T] -) -> Iterator[_T]: ... -def outer_product( - func: Callable[[_T, _U], _V], - xs: Iterable[_T], - ys: Iterable[_U], - *args: Any, - **kwargs: Any, -) -> Iterator[tuple[_V, ...]]: ... -def iter_suppress( - iterable: Iterable[_T], - *exceptions: Type[BaseException], -) -> Iterator[_T]: ... -def filter_map( - func: Callable[[_T], _V | None], - iterable: Iterable[_T], -) -> Iterator[_V]: ... -def powerset_of_sets(iterable: Iterable[_T]) -> Iterator[set[_T]]: ... -def join_mappings( - **field_to_map: Mapping[_T, _V] -) -> dict[_T, dict[str, _V]]: ... -def doublestarmap( - func: Callable[..., _T], - iterable: Iterable[Mapping[str, Any]], -) -> Iterator[_T]: ... -def dft(xarr: Sequence[complex]) -> Iterator[complex]: ... -def idft(Xarr: Sequence[complex]) -> Iterator[complex]: ... diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/recipes.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/recipes.py deleted file mode 100644 index b32fa95..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/recipes.py +++ /dev/null @@ -1,1046 +0,0 @@ -"""Imported from the recipes section of the itertools documentation. - -All functions taken from the recipes section of the itertools library docs -[1]_. -Some backward-compatible usability improvements have been made. - -.. [1] http://docs.python.org/library/itertools.html#recipes - -""" - -import math -import operator - -from collections import deque -from collections.abc import Sized -from functools import partial, reduce -from itertools import ( - chain, - combinations, - compress, - count, - cycle, - groupby, - islice, - product, - repeat, - starmap, - tee, - zip_longest, -) -from random import randrange, sample, choice -from sys import hexversion - -__all__ = [ - 'all_equal', - 'batched', - 'before_and_after', - 'consume', - 'convolve', - 'dotproduct', - 'first_true', - 'factor', - 'flatten', - 'grouper', - 'iter_except', - 'iter_index', - 'matmul', - 'ncycles', - 'nth', - 'nth_combination', - 'padnone', - 'pad_none', - 'pairwise', - 'partition', - 'polynomial_eval', - 'polynomial_from_roots', - 'polynomial_derivative', - 'powerset', - 'prepend', - 'quantify', - 'reshape', - 'random_combination_with_replacement', - 'random_combination', - 'random_permutation', - 'random_product', - 'repeatfunc', - 'roundrobin', - 'sieve', - 'sliding_window', - 'subslices', - 'sum_of_squares', - 'tabulate', - 'tail', - 'take', - 'totient', - 'transpose', - 'triplewise', - 'unique', - 'unique_everseen', - 'unique_justseen', -] - -_marker = object() - - -# zip with strict is available for Python 3.10+ -try: - zip(strict=True) -except TypeError: - _zip_strict = zip -else: - _zip_strict = partial(zip, strict=True) - -# math.sumprod is available for Python 3.12+ -_sumprod = getattr(math, 'sumprod', lambda x, y: dotproduct(x, y)) - - -def take(n, iterable): - """Return first *n* items of the iterable as a list. - - >>> take(3, range(10)) - [0, 1, 2] - - If there are fewer than *n* items in the iterable, all of them are - returned. - - >>> take(10, range(3)) - [0, 1, 2] - - """ - return list(islice(iterable, n)) - - -def tabulate(function, start=0): - """Return an iterator over the results of ``func(start)``, - ``func(start + 1)``, ``func(start + 2)``... - - *func* should be a function that accepts one integer argument. - - If *start* is not specified it defaults to 0. It will be incremented each - time the iterator is advanced. - - >>> square = lambda x: x ** 2 - >>> iterator = tabulate(square, -3) - >>> take(4, iterator) - [9, 4, 1, 0] - - """ - return map(function, count(start)) - - -def tail(n, iterable): - """Return an iterator over the last *n* items of *iterable*. - - >>> t = tail(3, 'ABCDEFG') - >>> list(t) - ['E', 'F', 'G'] - - """ - # If the given iterable has a length, then we can use islice to get its - # final elements. Note that if the iterable is not actually Iterable, - # either islice or deque will throw a TypeError. This is why we don't - # check if it is Iterable. - if isinstance(iterable, Sized): - yield from islice(iterable, max(0, len(iterable) - n), None) - else: - yield from iter(deque(iterable, maxlen=n)) - - -def consume(iterator, n=None): - """Advance *iterable* by *n* steps. If *n* is ``None``, consume it - entirely. - - Efficiently exhausts an iterator without returning values. Defaults to - consuming the whole iterator, but an optional second argument may be - provided to limit consumption. - - >>> i = (x for x in range(10)) - >>> next(i) - 0 - >>> consume(i, 3) - >>> next(i) - 4 - >>> consume(i) - >>> next(i) - Traceback (most recent call last): - File "", line 1, in - StopIteration - - If the iterator has fewer items remaining than the provided limit, the - whole iterator will be consumed. - - >>> i = (x for x in range(3)) - >>> consume(i, 5) - >>> next(i) - Traceback (most recent call last): - File "", line 1, in - StopIteration - - """ - # Use functions that consume iterators at C speed. - if n is None: - # feed the entire iterator into a zero-length deque - deque(iterator, maxlen=0) - else: - # advance to the empty slice starting at position n - next(islice(iterator, n, n), None) - - -def nth(iterable, n, default=None): - """Returns the nth item or a default value. - - >>> l = range(10) - >>> nth(l, 3) - 3 - >>> nth(l, 20, "zebra") - 'zebra' - - """ - return next(islice(iterable, n, None), default) - - -def all_equal(iterable, key=None): - """ - Returns ``True`` if all the elements are equal to each other. - - >>> all_equal('aaaa') - True - >>> all_equal('aaab') - False - - A function that accepts a single argument and returns a transformed version - of each input item can be specified with *key*: - - >>> all_equal('AaaA', key=str.casefold) - True - >>> all_equal([1, 2, 3], key=lambda x: x < 10) - True - - """ - return len(list(islice(groupby(iterable, key), 2))) <= 1 - - -def quantify(iterable, pred=bool): - """Return the how many times the predicate is true. - - >>> quantify([True, False, True]) - 2 - - """ - return sum(map(pred, iterable)) - - -def pad_none(iterable): - """Returns the sequence of elements and then returns ``None`` indefinitely. - - >>> take(5, pad_none(range(3))) - [0, 1, 2, None, None] - - Useful for emulating the behavior of the built-in :func:`map` function. - - See also :func:`padded`. - - """ - return chain(iterable, repeat(None)) - - -padnone = pad_none - - -def ncycles(iterable, n): - """Returns the sequence elements *n* times - - >>> list(ncycles(["a", "b"], 3)) - ['a', 'b', 'a', 'b', 'a', 'b'] - - """ - return chain.from_iterable(repeat(tuple(iterable), n)) - - -def dotproduct(vec1, vec2): - """Returns the dot product of the two iterables. - - >>> dotproduct([10, 10], [20, 20]) - 400 - - """ - return sum(map(operator.mul, vec1, vec2)) - - -def flatten(listOfLists): - """Return an iterator flattening one level of nesting in a list of lists. - - >>> list(flatten([[0, 1], [2, 3]])) - [0, 1, 2, 3] - - See also :func:`collapse`, which can flatten multiple levels of nesting. - - """ - return chain.from_iterable(listOfLists) - - -def repeatfunc(func, times=None, *args): - """Call *func* with *args* repeatedly, returning an iterable over the - results. - - If *times* is specified, the iterable will terminate after that many - repetitions: - - >>> from operator import add - >>> times = 4 - >>> args = 3, 5 - >>> list(repeatfunc(add, times, *args)) - [8, 8, 8, 8] - - If *times* is ``None`` the iterable will not terminate: - - >>> from random import randrange - >>> times = None - >>> args = 1, 11 - >>> take(6, repeatfunc(randrange, times, *args)) # doctest:+SKIP - [2, 4, 8, 1, 8, 4] - - """ - if times is None: - return starmap(func, repeat(args)) - return starmap(func, repeat(args, times)) - - -def _pairwise(iterable): - """Returns an iterator of paired items, overlapping, from the original - - >>> take(4, pairwise(count())) - [(0, 1), (1, 2), (2, 3), (3, 4)] - - On Python 3.10 and above, this is an alias for :func:`itertools.pairwise`. - - """ - a, b = tee(iterable) - next(b, None) - return zip(a, b) - - -try: - from itertools import pairwise as itertools_pairwise -except ImportError: - pairwise = _pairwise -else: - - def pairwise(iterable): - return itertools_pairwise(iterable) - - pairwise.__doc__ = _pairwise.__doc__ - - -class UnequalIterablesError(ValueError): - def __init__(self, details=None): - msg = 'Iterables have different lengths' - if details is not None: - msg += (': index 0 has length {}; index {} has length {}').format( - *details - ) - - super().__init__(msg) - - -def _zip_equal_generator(iterables): - for combo in zip_longest(*iterables, fillvalue=_marker): - for val in combo: - if val is _marker: - raise UnequalIterablesError() - yield combo - - -def _zip_equal(*iterables): - # Check whether the iterables are all the same size. - try: - first_size = len(iterables[0]) - for i, it in enumerate(iterables[1:], 1): - size = len(it) - if size != first_size: - raise UnequalIterablesError(details=(first_size, i, size)) - # All sizes are equal, we can use the built-in zip. - return zip(*iterables) - # If any one of the iterables didn't have a length, start reading - # them until one runs out. - except TypeError: - return _zip_equal_generator(iterables) - - -def grouper(iterable, n, incomplete='fill', fillvalue=None): - """Group elements from *iterable* into fixed-length groups of length *n*. - - >>> list(grouper('ABCDEF', 3)) - [('A', 'B', 'C'), ('D', 'E', 'F')] - - The keyword arguments *incomplete* and *fillvalue* control what happens for - iterables whose length is not a multiple of *n*. - - When *incomplete* is `'fill'`, the last group will contain instances of - *fillvalue*. - - >>> list(grouper('ABCDEFG', 3, incomplete='fill', fillvalue='x')) - [('A', 'B', 'C'), ('D', 'E', 'F'), ('G', 'x', 'x')] - - When *incomplete* is `'ignore'`, the last group will not be emitted. - - >>> list(grouper('ABCDEFG', 3, incomplete='ignore', fillvalue='x')) - [('A', 'B', 'C'), ('D', 'E', 'F')] - - When *incomplete* is `'strict'`, a subclass of `ValueError` will be raised. - - >>> it = grouper('ABCDEFG', 3, incomplete='strict') - >>> list(it) # doctest: +IGNORE_EXCEPTION_DETAIL - Traceback (most recent call last): - ... - UnequalIterablesError - - """ - args = [iter(iterable)] * n - if incomplete == 'fill': - return zip_longest(*args, fillvalue=fillvalue) - if incomplete == 'strict': - return _zip_equal(*args) - if incomplete == 'ignore': - return zip(*args) - else: - raise ValueError('Expected fill, strict, or ignore') - - -def roundrobin(*iterables): - """Yields an item from each iterable, alternating between them. - - >>> list(roundrobin('ABC', 'D', 'EF')) - ['A', 'D', 'E', 'B', 'F', 'C'] - - This function produces the same output as :func:`interleave_longest`, but - may perform better for some inputs (in particular when the number of - iterables is small). - - """ - # Algorithm credited to George Sakkis - iterators = map(iter, iterables) - for num_active in range(len(iterables), 0, -1): - iterators = cycle(islice(iterators, num_active)) - yield from map(next, iterators) - - -def partition(pred, iterable): - """ - Returns a 2-tuple of iterables derived from the input iterable. - The first yields the items that have ``pred(item) == False``. - The second yields the items that have ``pred(item) == True``. - - >>> is_odd = lambda x: x % 2 != 0 - >>> iterable = range(10) - >>> even_items, odd_items = partition(is_odd, iterable) - >>> list(even_items), list(odd_items) - ([0, 2, 4, 6, 8], [1, 3, 5, 7, 9]) - - If *pred* is None, :func:`bool` is used. - - >>> iterable = [0, 1, False, True, '', ' '] - >>> false_items, true_items = partition(None, iterable) - >>> list(false_items), list(true_items) - ([0, False, ''], [1, True, ' ']) - - """ - if pred is None: - pred = bool - - t1, t2, p = tee(iterable, 3) - p1, p2 = tee(map(pred, p)) - return (compress(t1, map(operator.not_, p1)), compress(t2, p2)) - - -def powerset(iterable): - """Yields all possible subsets of the iterable. - - >>> list(powerset([1, 2, 3])) - [(), (1,), (2,), (3,), (1, 2), (1, 3), (2, 3), (1, 2, 3)] - - :func:`powerset` will operate on iterables that aren't :class:`set` - instances, so repeated elements in the input will produce repeated elements - in the output. - - >>> seq = [1, 1, 0] - >>> list(powerset(seq)) - [(), (1,), (1,), (0,), (1, 1), (1, 0), (1, 0), (1, 1, 0)] - - For a variant that efficiently yields actual :class:`set` instances, see - :func:`powerset_of_sets`. - """ - s = list(iterable) - return chain.from_iterable(combinations(s, r) for r in range(len(s) + 1)) - - -def unique_everseen(iterable, key=None): - """ - Yield unique elements, preserving order. - - >>> list(unique_everseen('AAAABBBCCDAABBB')) - ['A', 'B', 'C', 'D'] - >>> list(unique_everseen('ABBCcAD', str.lower)) - ['A', 'B', 'C', 'D'] - - Sequences with a mix of hashable and unhashable items can be used. - The function will be slower (i.e., `O(n^2)`) for unhashable items. - - Remember that ``list`` objects are unhashable - you can use the *key* - parameter to transform the list to a tuple (which is hashable) to - avoid a slowdown. - - >>> iterable = ([1, 2], [2, 3], [1, 2]) - >>> list(unique_everseen(iterable)) # Slow - [[1, 2], [2, 3]] - >>> list(unique_everseen(iterable, key=tuple)) # Faster - [[1, 2], [2, 3]] - - Similarly, you may want to convert unhashable ``set`` objects with - ``key=frozenset``. For ``dict`` objects, - ``key=lambda x: frozenset(x.items())`` can be used. - - """ - seenset = set() - seenset_add = seenset.add - seenlist = [] - seenlist_add = seenlist.append - use_key = key is not None - - for element in iterable: - k = key(element) if use_key else element - try: - if k not in seenset: - seenset_add(k) - yield element - except TypeError: - if k not in seenlist: - seenlist_add(k) - yield element - - -def unique_justseen(iterable, key=None): - """Yields elements in order, ignoring serial duplicates - - >>> list(unique_justseen('AAAABBBCCDAABBB')) - ['A', 'B', 'C', 'D', 'A', 'B'] - >>> list(unique_justseen('ABBCcAD', str.lower)) - ['A', 'B', 'C', 'A', 'D'] - - """ - if key is None: - return map(operator.itemgetter(0), groupby(iterable)) - - return map(next, map(operator.itemgetter(1), groupby(iterable, key))) - - -def unique(iterable, key=None, reverse=False): - """Yields unique elements in sorted order. - - >>> list(unique([[1, 2], [3, 4], [1, 2]])) - [[1, 2], [3, 4]] - - *key* and *reverse* are passed to :func:`sorted`. - - >>> list(unique('ABBcCAD', str.casefold)) - ['A', 'B', 'c', 'D'] - >>> list(unique('ABBcCAD', str.casefold, reverse=True)) - ['D', 'c', 'B', 'A'] - - The elements in *iterable* need not be hashable, but they must be - comparable for sorting to work. - """ - return unique_justseen(sorted(iterable, key=key, reverse=reverse), key=key) - - -def iter_except(func, exception, first=None): - """Yields results from a function repeatedly until an exception is raised. - - Converts a call-until-exception interface to an iterator interface. - Like ``iter(func, sentinel)``, but uses an exception instead of a sentinel - to end the loop. - - >>> l = [0, 1, 2] - >>> list(iter_except(l.pop, IndexError)) - [2, 1, 0] - - Multiple exceptions can be specified as a stopping condition: - - >>> l = [1, 2, 3, '...', 4, 5, 6] - >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError))) - [7, 6, 5] - >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError))) - [4, 3, 2] - >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError))) - [] - - """ - try: - if first is not None: - yield first() - while 1: - yield func() - except exception: - pass - - -def first_true(iterable, default=None, pred=None): - """ - Returns the first true value in the iterable. - - If no true value is found, returns *default* - - If *pred* is not None, returns the first item for which - ``pred(item) == True`` . - - >>> first_true(range(10)) - 1 - >>> first_true(range(10), pred=lambda x: x > 5) - 6 - >>> first_true(range(10), default='missing', pred=lambda x: x > 9) - 'missing' - - """ - return next(filter(pred, iterable), default) - - -def random_product(*args, repeat=1): - """Draw an item at random from each of the input iterables. - - >>> random_product('abc', range(4), 'XYZ') # doctest:+SKIP - ('c', 3, 'Z') - - If *repeat* is provided as a keyword argument, that many items will be - drawn from each iterable. - - >>> random_product('abcd', range(4), repeat=2) # doctest:+SKIP - ('a', 2, 'd', 3) - - This equivalent to taking a random selection from - ``itertools.product(*args, **kwarg)``. - - """ - pools = [tuple(pool) for pool in args] * repeat - return tuple(choice(pool) for pool in pools) - - -def random_permutation(iterable, r=None): - """Return a random *r* length permutation of the elements in *iterable*. - - If *r* is not specified or is ``None``, then *r* defaults to the length of - *iterable*. - - >>> random_permutation(range(5)) # doctest:+SKIP - (3, 4, 0, 1, 2) - - This equivalent to taking a random selection from - ``itertools.permutations(iterable, r)``. - - """ - pool = tuple(iterable) - r = len(pool) if r is None else r - return tuple(sample(pool, r)) - - -def random_combination(iterable, r): - """Return a random *r* length subsequence of the elements in *iterable*. - - >>> random_combination(range(5), 3) # doctest:+SKIP - (2, 3, 4) - - This equivalent to taking a random selection from - ``itertools.combinations(iterable, r)``. - - """ - pool = tuple(iterable) - n = len(pool) - indices = sorted(sample(range(n), r)) - return tuple(pool[i] for i in indices) - - -def random_combination_with_replacement(iterable, r): - """Return a random *r* length subsequence of elements in *iterable*, - allowing individual elements to be repeated. - - >>> random_combination_with_replacement(range(3), 5) # doctest:+SKIP - (0, 0, 1, 2, 2) - - This equivalent to taking a random selection from - ``itertools.combinations_with_replacement(iterable, r)``. - - """ - pool = tuple(iterable) - n = len(pool) - indices = sorted(randrange(n) for i in range(r)) - return tuple(pool[i] for i in indices) - - -def nth_combination(iterable, r, index): - """Equivalent to ``list(combinations(iterable, r))[index]``. - - The subsequences of *iterable* that are of length *r* can be ordered - lexicographically. :func:`nth_combination` computes the subsequence at - sort position *index* directly, without computing the previous - subsequences. - - >>> nth_combination(range(5), 3, 5) - (0, 3, 4) - - ``ValueError`` will be raised If *r* is negative or greater than the length - of *iterable*. - ``IndexError`` will be raised if the given *index* is invalid. - """ - pool = tuple(iterable) - n = len(pool) - if (r < 0) or (r > n): - raise ValueError - - c = 1 - k = min(r, n - r) - for i in range(1, k + 1): - c = c * (n - k + i) // i - - if index < 0: - index += c - - if (index < 0) or (index >= c): - raise IndexError - - result = [] - while r: - c, n, r = c * r // n, n - 1, r - 1 - while index >= c: - index -= c - c, n = c * (n - r) // n, n - 1 - result.append(pool[-1 - n]) - - return tuple(result) - - -def prepend(value, iterator): - """Yield *value*, followed by the elements in *iterator*. - - >>> value = '0' - >>> iterator = ['1', '2', '3'] - >>> list(prepend(value, iterator)) - ['0', '1', '2', '3'] - - To prepend multiple values, see :func:`itertools.chain` - or :func:`value_chain`. - - """ - return chain([value], iterator) - - -def convolve(signal, kernel): - """Convolve the iterable *signal* with the iterable *kernel*. - - >>> signal = (1, 2, 3, 4, 5) - >>> kernel = [3, 2, 1] - >>> list(convolve(signal, kernel)) - [3, 8, 14, 20, 26, 14, 5] - - Note: the input arguments are not interchangeable, as the *kernel* - is immediately consumed and stored. - - """ - # This implementation intentionally doesn't match the one in the itertools - # documentation. - kernel = tuple(kernel)[::-1] - n = len(kernel) - window = deque([0], maxlen=n) * n - for x in chain(signal, repeat(0, n - 1)): - window.append(x) - yield _sumprod(kernel, window) - - -def before_and_after(predicate, it): - """A variant of :func:`takewhile` that allows complete access to the - remainder of the iterator. - - >>> it = iter('ABCdEfGhI') - >>> all_upper, remainder = before_and_after(str.isupper, it) - >>> ''.join(all_upper) - 'ABC' - >>> ''.join(remainder) # takewhile() would lose the 'd' - 'dEfGhI' - - Note that the first iterator must be fully consumed before the second - iterator can generate valid results. - """ - it = iter(it) - transition = [] - - def true_iterator(): - for elem in it: - if predicate(elem): - yield elem - else: - transition.append(elem) - return - - # Note: this is different from itertools recipes to allow nesting - # before_and_after remainders into before_and_after again. See tests - # for an example. - remainder_iterator = chain(transition, it) - - return true_iterator(), remainder_iterator - - -def triplewise(iterable): - """Return overlapping triplets from *iterable*. - - >>> list(triplewise('ABCDE')) - [('A', 'B', 'C'), ('B', 'C', 'D'), ('C', 'D', 'E')] - - """ - for (a, _), (b, c) in pairwise(pairwise(iterable)): - yield a, b, c - - -def sliding_window(iterable, n): - """Return a sliding window of width *n* over *iterable*. - - >>> list(sliding_window(range(6), 4)) - [(0, 1, 2, 3), (1, 2, 3, 4), (2, 3, 4, 5)] - - If *iterable* has fewer than *n* items, then nothing is yielded: - - >>> list(sliding_window(range(3), 4)) - [] - - For a variant with more features, see :func:`windowed`. - """ - it = iter(iterable) - window = deque(islice(it, n - 1), maxlen=n) - for x in it: - window.append(x) - yield tuple(window) - - -def subslices(iterable): - """Return all contiguous non-empty subslices of *iterable*. - - >>> list(subslices('ABC')) - [['A'], ['A', 'B'], ['A', 'B', 'C'], ['B'], ['B', 'C'], ['C']] - - This is similar to :func:`substrings`, but emits items in a different - order. - """ - seq = list(iterable) - slices = starmap(slice, combinations(range(len(seq) + 1), 2)) - return map(operator.getitem, repeat(seq), slices) - - -def polynomial_from_roots(roots): - """Compute a polynomial's coefficients from its roots. - - >>> roots = [5, -4, 3] # (x - 5) * (x + 4) * (x - 3) - >>> polynomial_from_roots(roots) # x^3 - 4 * x^2 - 17 * x + 60 - [1, -4, -17, 60] - """ - factors = zip(repeat(1), map(operator.neg, roots)) - return list(reduce(convolve, factors, [1])) - - -def iter_index(iterable, value, start=0, stop=None): - """Yield the index of each place in *iterable* that *value* occurs, - beginning with index *start* and ending before index *stop*. - - - >>> list(iter_index('AABCADEAF', 'A')) - [0, 1, 4, 7] - >>> list(iter_index('AABCADEAF', 'A', 1)) # start index is inclusive - [1, 4, 7] - >>> list(iter_index('AABCADEAF', 'A', 1, 7)) # stop index is not inclusive - [1, 4] - - The behavior for non-scalar *values* matches the built-in Python types. - - >>> list(iter_index('ABCDABCD', 'AB')) - [0, 4] - >>> list(iter_index([0, 1, 2, 3, 0, 1, 2, 3], [0, 1])) - [] - >>> list(iter_index([[0, 1], [2, 3], [0, 1], [2, 3]], [0, 1])) - [0, 2] - - See :func:`locate` for a more general means of finding the indexes - associated with particular values. - - """ - seq_index = getattr(iterable, 'index', None) - if seq_index is None: - # Slow path for general iterables - it = islice(iterable, start, stop) - for i, element in enumerate(it, start): - if element is value or element == value: - yield i - else: - # Fast path for sequences - stop = len(iterable) if stop is None else stop - i = start - 1 - try: - while True: - yield (i := seq_index(value, i + 1, stop)) - except ValueError: - pass - - -def sieve(n): - """Yield the primes less than n. - - >>> list(sieve(30)) - [2, 3, 5, 7, 11, 13, 17, 19, 23, 29] - """ - if n > 2: - yield 2 - start = 3 - data = bytearray((0, 1)) * (n // 2) - limit = math.isqrt(n) + 1 - for p in iter_index(data, 1, start, limit): - yield from iter_index(data, 1, start, p * p) - data[p * p : n : p + p] = bytes(len(range(p * p, n, p + p))) - start = p * p - yield from iter_index(data, 1, start) - - -def _batched(iterable, n, *, strict=False): - """Batch data into tuples of length *n*. If the number of items in - *iterable* is not divisible by *n*: - * The last batch will be shorter if *strict* is ``False``. - * :exc:`ValueError` will be raised if *strict* is ``True``. - - >>> list(batched('ABCDEFG', 3)) - [('A', 'B', 'C'), ('D', 'E', 'F'), ('G',)] - - On Python 3.13 and above, this is an alias for :func:`itertools.batched`. - """ - if n < 1: - raise ValueError('n must be at least one') - it = iter(iterable) - while batch := tuple(islice(it, n)): - if strict and len(batch) != n: - raise ValueError('batched(): incomplete batch') - yield batch - - -if hexversion >= 0x30D00A2: - from itertools import batched as itertools_batched - - def batched(iterable, n, *, strict=False): - return itertools_batched(iterable, n, strict=strict) - -else: - batched = _batched - - batched.__doc__ = _batched.__doc__ - - -def transpose(it): - """Swap the rows and columns of the input matrix. - - >>> list(transpose([(1, 2, 3), (11, 22, 33)])) - [(1, 11), (2, 22), (3, 33)] - - The caller should ensure that the dimensions of the input are compatible. - If the input is empty, no output will be produced. - """ - return _zip_strict(*it) - - -def reshape(matrix, cols): - """Reshape the 2-D input *matrix* to have a column count given by *cols*. - - >>> matrix = [(0, 1), (2, 3), (4, 5)] - >>> cols = 3 - >>> list(reshape(matrix, cols)) - [(0, 1, 2), (3, 4, 5)] - """ - return batched(chain.from_iterable(matrix), cols) - - -def matmul(m1, m2): - """Multiply two matrices. - - >>> list(matmul([(7, 5), (3, 5)], [(2, 5), (7, 9)])) - [(49, 80), (41, 60)] - - The caller should ensure that the dimensions of the input matrices are - compatible with each other. - """ - n = len(m2[0]) - return batched(starmap(_sumprod, product(m1, transpose(m2))), n) - - -def factor(n): - """Yield the prime factors of n. - - >>> list(factor(360)) - [2, 2, 2, 3, 3, 5] - """ - for prime in sieve(math.isqrt(n) + 1): - while not n % prime: - yield prime - n //= prime - if n == 1: - return - if n > 1: - yield n - - -def polynomial_eval(coefficients, x): - """Evaluate a polynomial at a specific value. - - Example: evaluating x^3 - 4 * x^2 - 17 * x + 60 at x = 2.5: - - >>> coefficients = [1, -4, -17, 60] - >>> x = 2.5 - >>> polynomial_eval(coefficients, x) - 8.125 - """ - n = len(coefficients) - if n == 0: - return x * 0 # coerce zero to the type of x - powers = map(pow, repeat(x), reversed(range(n))) - return _sumprod(coefficients, powers) - - -def sum_of_squares(it): - """Return the sum of the squares of the input values. - - >>> sum_of_squares([10, 20, 30]) - 1400 - """ - return _sumprod(*tee(it)) - - -def polynomial_derivative(coefficients): - """Compute the first derivative of a polynomial. - - Example: evaluating the derivative of x^3 - 4 * x^2 - 17 * x + 60 - - >>> coefficients = [1, -4, -17, 60] - >>> derivative_coefficients = polynomial_derivative(coefficients) - >>> derivative_coefficients - [3, -8, -17] - """ - n = len(coefficients) - powers = reversed(range(1, n)) - return list(map(operator.mul, coefficients, powers)) - - -def totient(n): - """Return the count of natural numbers up to *n* that are coprime with *n*. - - >>> totient(9) - 6 - >>> totient(12) - 4 - """ - # The itertools docs use unique_justseen instead of set; see - # https://github.com/more-itertools/more-itertools/issues/823 - for p in set(factor(n)): - n = n // p * (p - 1) - - return n diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/recipes.pyi b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/recipes.pyi deleted file mode 100644 index 739acec..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/more_itertools/recipes.pyi +++ /dev/null @@ -1,136 +0,0 @@ -"""Stubs for more_itertools.recipes""" - -from __future__ import annotations - -from typing import ( - Any, - Callable, - Iterable, - Iterator, - overload, - Sequence, - Type, - TypeVar, -) - -# Type and type variable definitions -_T = TypeVar('_T') -_T1 = TypeVar('_T1') -_T2 = TypeVar('_T2') -_U = TypeVar('_U') - -def take(n: int, iterable: Iterable[_T]) -> list[_T]: ... -def tabulate( - function: Callable[[int], _T], start: int = ... -) -> Iterator[_T]: ... -def tail(n: int, iterable: Iterable[_T]) -> Iterator[_T]: ... -def consume(iterator: Iterable[_T], n: int | None = ...) -> None: ... -@overload -def nth(iterable: Iterable[_T], n: int) -> _T | None: ... -@overload -def nth(iterable: Iterable[_T], n: int, default: _U) -> _T | _U: ... -def all_equal( - iterable: Iterable[_T], key: Callable[[_T], _U] | None = ... -) -> bool: ... -def quantify( - iterable: Iterable[_T], pred: Callable[[_T], bool] = ... -) -> int: ... -def pad_none(iterable: Iterable[_T]) -> Iterator[_T | None]: ... -def padnone(iterable: Iterable[_T]) -> Iterator[_T | None]: ... -def ncycles(iterable: Iterable[_T], n: int) -> Iterator[_T]: ... -def dotproduct(vec1: Iterable[_T1], vec2: Iterable[_T2]) -> Any: ... -def flatten(listOfLists: Iterable[Iterable[_T]]) -> Iterator[_T]: ... -def repeatfunc( - func: Callable[..., _U], times: int | None = ..., *args: Any -) -> Iterator[_U]: ... -def pairwise(iterable: Iterable[_T]) -> Iterator[tuple[_T, _T]]: ... -def grouper( - iterable: Iterable[_T], - n: int, - incomplete: str = ..., - fillvalue: _U = ..., -) -> Iterator[tuple[_T | _U, ...]]: ... -def roundrobin(*iterables: Iterable[_T]) -> Iterator[_T]: ... -def partition( - pred: Callable[[_T], object] | None, iterable: Iterable[_T] -) -> tuple[Iterator[_T], Iterator[_T]]: ... -def powerset(iterable: Iterable[_T]) -> Iterator[tuple[_T, ...]]: ... -def unique_everseen( - iterable: Iterable[_T], key: Callable[[_T], _U] | None = ... -) -> Iterator[_T]: ... -def unique_justseen( - iterable: Iterable[_T], key: Callable[[_T], object] | None = ... -) -> Iterator[_T]: ... -def unique( - iterable: Iterable[_T], - key: Callable[[_T], object] | None = ..., - reverse: bool = False, -) -> Iterator[_T]: ... -@overload -def iter_except( - func: Callable[[], _T], - exception: Type[BaseException] | tuple[Type[BaseException], ...], - first: None = ..., -) -> Iterator[_T]: ... -@overload -def iter_except( - func: Callable[[], _T], - exception: Type[BaseException] | tuple[Type[BaseException], ...], - first: Callable[[], _U], -) -> Iterator[_T | _U]: ... -@overload -def first_true( - iterable: Iterable[_T], *, pred: Callable[[_T], object] | None = ... -) -> _T | None: ... -@overload -def first_true( - iterable: Iterable[_T], - default: _U, - pred: Callable[[_T], object] | None = ..., -) -> _T | _U: ... -def random_product( - *args: Iterable[_T], repeat: int = ... -) -> tuple[_T, ...]: ... -def random_permutation( - iterable: Iterable[_T], r: int | None = ... -) -> tuple[_T, ...]: ... -def random_combination(iterable: Iterable[_T], r: int) -> tuple[_T, ...]: ... -def random_combination_with_replacement( - iterable: Iterable[_T], r: int -) -> tuple[_T, ...]: ... -def nth_combination( - iterable: Iterable[_T], r: int, index: int -) -> tuple[_T, ...]: ... -def prepend(value: _T, iterator: Iterable[_U]) -> Iterator[_T | _U]: ... -def convolve(signal: Iterable[_T], kernel: Iterable[_T]) -> Iterator[_T]: ... -def before_and_after( - predicate: Callable[[_T], bool], it: Iterable[_T] -) -> tuple[Iterator[_T], Iterator[_T]]: ... -def triplewise(iterable: Iterable[_T]) -> Iterator[tuple[_T, _T, _T]]: ... -def sliding_window( - iterable: Iterable[_T], n: int -) -> Iterator[tuple[_T, ...]]: ... -def subslices(iterable: Iterable[_T]) -> Iterator[list[_T]]: ... -def polynomial_from_roots(roots: Sequence[_T]) -> list[_T]: ... -def iter_index( - iterable: Iterable[_T], - value: Any, - start: int | None = ..., - stop: int | None = ..., -) -> Iterator[int]: ... -def sieve(n: int) -> Iterator[int]: ... -def batched( - iterable: Iterable[_T], n: int, *, strict: bool = False -) -> Iterator[tuple[_T]]: ... -def transpose( - it: Iterable[Iterable[_T]], -) -> Iterator[tuple[_T, ...]]: ... -def reshape( - matrix: Iterable[Iterable[_T]], cols: int -) -> Iterator[tuple[_T, ...]]: ... -def matmul(m1: Sequence[_T], m2: Sequence[_T]) -> Iterator[tuple[_T]]: ... -def factor(n: int) -> Iterator[int]: ... -def polynomial_eval(coefficients: Sequence[_T], x: _U) -> _U: ... -def sum_of_squares(it: Iterable[_T]) -> _T: ... -def polynomial_derivative(coefficients: Sequence[_T]) -> list[_T]: ... -def totient(n: int) -> int: ... diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/INSTALLER deleted file mode 100644 index 5c69047..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/INSTALLER +++ /dev/null @@ -1 +0,0 @@ -uv \ No newline at end of file diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE deleted file mode 100644 index 6f62d44..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE +++ /dev/null @@ -1,3 +0,0 @@ -This software is made available under the terms of *either* of the licenses -found in LICENSE.APACHE or LICENSE.BSD. Contributions to this software is made -under the terms of *both* these licenses. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE.APACHE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE.APACHE deleted file mode 100644 index f433b1a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE.APACHE +++ /dev/null @@ -1,177 +0,0 @@ - - Apache License - Version 2.0, January 2004 - http://www.apache.org/licenses/ - - TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION - - 1. Definitions. - - "License" shall mean the terms and conditions for use, reproduction, - and distribution as defined by Sections 1 through 9 of this document. - - "Licensor" shall mean the copyright owner or entity authorized by - the copyright owner that is granting the License. - - "Legal Entity" shall mean the union of the acting entity and all - other entities that control, are controlled by, or are under common - control with that entity. For the purposes of this definition, - "control" means (i) the power, direct or indirect, to cause the - direction or management of such entity, whether by contract or - otherwise, or (ii) ownership of fifty percent (50%) or more of the - outstanding shares, or (iii) beneficial ownership of such entity. - - "You" (or "Your") shall mean an individual or Legal Entity - exercising permissions granted by this License. - - "Source" form shall mean the preferred form for making modifications, - including but not limited to software source code, documentation - source, and configuration files. - - "Object" form shall mean any form resulting from mechanical - transformation or translation of a Source form, including but - not limited to compiled object code, generated documentation, - and conversions to other media types. - - "Work" shall mean the work of authorship, whether in Source or - Object form, made available under the License, as indicated by a - copyright notice that is included in or attached to the work - (an example is provided in the Appendix below). - - "Derivative Works" shall mean any work, whether in Source or Object - form, that is based on (or derived from) the Work and for which the - editorial revisions, annotations, elaborations, or other modifications - represent, as a whole, an original work of authorship. For the purposes - of this License, Derivative Works shall not include works that remain - separable from, or merely link (or bind by name) to the interfaces of, - the Work and Derivative Works thereof. - - "Contribution" shall mean any work of authorship, including - the original version of the Work and any modifications or additions - to that Work or Derivative Works thereof, that is intentionally - submitted to Licensor for inclusion in the Work by the copyright owner - or by an individual or Legal Entity authorized to submit on behalf of - the copyright owner. For the purposes of this definition, "submitted" - means any form of electronic, verbal, or written communication sent - to the Licensor or its representatives, including but not limited to - communication on electronic mailing lists, source code control systems, - and issue tracking systems that are managed by, or on behalf of, the - Licensor for the purpose of discussing and improving the Work, but - excluding communication that is conspicuously marked or otherwise - designated in writing by the copyright owner as "Not a Contribution." - - "Contributor" shall mean Licensor and any individual or Legal Entity - on behalf of whom a Contribution has been received by Licensor and - subsequently incorporated within the Work. - - 2. Grant of Copyright License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - copyright license to reproduce, prepare Derivative Works of, - publicly display, publicly perform, sublicense, and distribute the - Work and such Derivative Works in Source or Object form. - - 3. Grant of Patent License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - (except as stated in this section) patent license to make, have made, - use, offer to sell, sell, import, and otherwise transfer the Work, - where such license applies only to those patent claims licensable - by such Contributor that are necessarily infringed by their - Contribution(s) alone or by combination of their Contribution(s) - with the Work to which such Contribution(s) was submitted. If You - institute patent litigation against any entity (including a - cross-claim or counterclaim in a lawsuit) alleging that the Work - or a Contribution incorporated within the Work constitutes direct - or contributory patent infringement, then any patent licenses - granted to You under this License for that Work shall terminate - as of the date such litigation is filed. - - 4. Redistribution. You may reproduce and distribute copies of the - Work or Derivative Works thereof in any medium, with or without - modifications, and in Source or Object form, provided that You - meet the following conditions: - - (a) You must give any other recipients of the Work or - Derivative Works a copy of this License; and - - (b) You must cause any modified files to carry prominent notices - stating that You changed the files; and - - (c) You must retain, in the Source form of any Derivative Works - that You distribute, all copyright, patent, trademark, and - attribution notices from the Source form of the Work, - excluding those notices that do not pertain to any part of - the Derivative Works; and - - (d) If the Work includes a "NOTICE" text file as part of its - distribution, then any Derivative Works that You distribute must - include a readable copy of the attribution notices contained - within such NOTICE file, excluding those notices that do not - pertain to any part of the Derivative Works, in at least one - of the following places: within a NOTICE text file distributed - as part of the Derivative Works; within the Source form or - documentation, if provided along with the Derivative Works; or, - within a display generated by the Derivative Works, if and - wherever such third-party notices normally appear. The contents - of the NOTICE file are for informational purposes only and - do not modify the License. You may add Your own attribution - notices within Derivative Works that You distribute, alongside - or as an addendum to the NOTICE text from the Work, provided - that such additional attribution notices cannot be construed - as modifying the License. - - You may add Your own copyright statement to Your modifications and - may provide additional or different license terms and conditions - for use, reproduction, or distribution of Your modifications, or - for any such Derivative Works as a whole, provided Your use, - reproduction, and distribution of the Work otherwise complies with - the conditions stated in this License. - - 5. Submission of Contributions. Unless You explicitly state otherwise, - any Contribution intentionally submitted for inclusion in the Work - by You to the Licensor shall be under the terms and conditions of - this License, without any additional terms or conditions. - Notwithstanding the above, nothing herein shall supersede or modify - the terms of any separate license agreement you may have executed - with Licensor regarding such Contributions. - - 6. Trademarks. This License does not grant permission to use the trade - names, trademarks, service marks, or product names of the Licensor, - except as required for reasonable and customary use in describing the - origin of the Work and reproducing the content of the NOTICE file. - - 7. Disclaimer of Warranty. Unless required by applicable law or - agreed to in writing, Licensor provides the Work (and each - Contributor provides its Contributions) on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or - implied, including, without limitation, any warranties or conditions - of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A - PARTICULAR PURPOSE. You are solely responsible for determining the - appropriateness of using or redistributing the Work and assume any - risks associated with Your exercise of permissions under this License. - - 8. Limitation of Liability. In no event and under no legal theory, - whether in tort (including negligence), contract, or otherwise, - unless required by applicable law (such as deliberate and grossly - negligent acts) or agreed to in writing, shall any Contributor be - liable to You for damages, including any direct, indirect, special, - incidental, or consequential damages of any character arising as a - result of this License or out of the use or inability to use the - Work (including but not limited to damages for loss of goodwill, - work stoppage, computer failure or malfunction, or any and all - other commercial damages or losses), even if such Contributor - has been advised of the possibility of such damages. - - 9. Accepting Warranty or Additional Liability. While redistributing - the Work or Derivative Works thereof, You may choose to offer, - and charge a fee for, acceptance of support, warranty, indemnity, - or other liability obligations and/or rights consistent with this - License. However, in accepting such obligations, You may act only - on Your own behalf and on Your sole responsibility, not on behalf - of any other Contributor, and only if You agree to indemnify, - defend, and hold each Contributor harmless for any liability - incurred by, or claims asserted against, such Contributor by reason - of your accepting any such warranty or additional liability. - - END OF TERMS AND CONDITIONS diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE.BSD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE.BSD deleted file mode 100644 index 42ce7b7..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/LICENSE.BSD +++ /dev/null @@ -1,23 +0,0 @@ -Copyright (c) Donald Stufft and individual contributors. -All rights reserved. - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - 1. Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - 2. Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND -ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE -DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE -FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL -DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR -SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER -CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, -OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/METADATA deleted file mode 100644 index 1479c86..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/METADATA +++ /dev/null @@ -1,102 +0,0 @@ -Metadata-Version: 2.3 -Name: packaging -Version: 24.2 -Summary: Core utilities for Python packages -Author-email: Donald Stufft -Requires-Python: >=3.8 -Description-Content-Type: text/x-rst -Classifier: Development Status :: 5 - Production/Stable -Classifier: Intended Audience :: Developers -Classifier: License :: OSI Approved :: Apache Software License -Classifier: License :: OSI Approved :: BSD License -Classifier: Programming Language :: Python -Classifier: Programming Language :: Python :: 3 -Classifier: Programming Language :: Python :: 3 :: Only -Classifier: Programming Language :: Python :: 3.8 -Classifier: Programming Language :: Python :: 3.9 -Classifier: Programming Language :: Python :: 3.10 -Classifier: Programming Language :: Python :: 3.11 -Classifier: Programming Language :: Python :: 3.12 -Classifier: Programming Language :: Python :: 3.13 -Classifier: Programming Language :: Python :: Implementation :: CPython -Classifier: Programming Language :: Python :: Implementation :: PyPy -Classifier: Typing :: Typed -Project-URL: Documentation, https://packaging.pypa.io/ -Project-URL: Source, https://github.com/pypa/packaging - -packaging -========= - -.. start-intro - -Reusable core utilities for various Python Packaging -`interoperability specifications `_. - -This library provides utilities that implement the interoperability -specifications which have clearly one correct behaviour (eg: :pep:`440`) -or benefit greatly from having a single shared implementation (eg: :pep:`425`). - -.. end-intro - -The ``packaging`` project includes the following: version handling, specifiers, -markers, requirements, tags, utilities. - -Documentation -------------- - -The `documentation`_ provides information and the API for the following: - -- Version Handling -- Specifiers -- Markers -- Requirements -- Tags -- Utilities - -Installation ------------- - -Use ``pip`` to install these utilities:: - - pip install packaging - -The ``packaging`` library uses calendar-based versioning (``YY.N``). - -Discussion ----------- - -If you run into bugs, you can file them in our `issue tracker`_. - -You can also join ``#pypa`` on Freenode to ask questions or get involved. - - -.. _`documentation`: https://packaging.pypa.io/ -.. _`issue tracker`: https://github.com/pypa/packaging/issues - - -Code of Conduct ---------------- - -Everyone interacting in the packaging project's codebases, issue trackers, chat -rooms, and mailing lists is expected to follow the `PSF Code of Conduct`_. - -.. _PSF Code of Conduct: https://github.com/pypa/.github/blob/main/CODE_OF_CONDUCT.md - -Contributing ------------- - -The ``CONTRIBUTING.rst`` file outlines how to contribute to this project as -well as how to report a potential security issue. The documentation for this -project also covers information about `project development`_ and `security`_. - -.. _`project development`: https://packaging.pypa.io/en/latest/development/ -.. _`security`: https://packaging.pypa.io/en/latest/security/ - -Project History ---------------- - -Please review the ``CHANGELOG.rst`` file or the `Changelog documentation`_ for -recent changes and project history. - -.. _`Changelog documentation`: https://packaging.pypa.io/en/latest/changelog/ - diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/RECORD deleted file mode 100644 index 678aa5a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/RECORD +++ /dev/null @@ -1,25 +0,0 @@ -packaging-24.2.dist-info/INSTALLER,sha256=5hhM4Q4mYTT9z6QB6PGpUAW81PGNFrYrdXMj4oM_6ak,2 -packaging-24.2.dist-info/LICENSE,sha256=ytHvW9NA1z4HS6YU0m996spceUDD2MNIUuZcSQlobEg,197 -packaging-24.2.dist-info/LICENSE.APACHE,sha256=DVQuDIgE45qn836wDaWnYhSdxoLXgpRRKH4RuTjpRZQ,10174 -packaging-24.2.dist-info/LICENSE.BSD,sha256=tw5-m3QvHMb5SLNMFqo5_-zpQZY2S8iP8NIYDwAo-sU,1344 -packaging-24.2.dist-info/METADATA,sha256=ohH86s6k5mIfQxY2TS0LcSfADeOFa4BiCC-bxZV-pNs,3204 -packaging-24.2.dist-info/RECORD,, -packaging-24.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -packaging-24.2.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82 -packaging/__init__.py,sha256=dk4Ta_vmdVJxYHDcfyhvQNw8V3PgSBomKNXqg-D2JDY,494 -packaging/_elffile.py,sha256=cflAQAkE25tzhYmq_aCi72QfbT_tn891tPzfpbeHOwE,3306 -packaging/_manylinux.py,sha256=vl5OCoz4kx80H5rwXKeXWjl9WNISGmr4ZgTpTP9lU9c,9612 -packaging/_musllinux.py,sha256=p9ZqNYiOItGee8KcZFeHF_YcdhVwGHdK6r-8lgixvGQ,2694 -packaging/_parser.py,sha256=s_TvTvDNK0NrM2QB3VKThdWFM4Nc0P6JnkObkl3MjpM,10236 -packaging/_structures.py,sha256=q3eVNmbWJGG_S0Dit_S3Ao8qQqz_5PYTXFAKBZe5yr4,1431 -packaging/_tokenizer.py,sha256=J6v5H7Jzvb-g81xp_2QACKwO7LxHQA6ikryMU7zXwN8,5273 -packaging/licenses/__init__.py,sha256=1x5M1nEYjcgwEbLt0dXwz2ukjr18DiCzC0sraQqJ-Ww,5715 -packaging/licenses/_spdx.py,sha256=oAm1ztPFwlsmCKe7lAAsv_OIOfS1cWDu9bNBkeu-2ns,48398 -packaging/markers.py,sha256=c89TNzB7ZdGYhkovm6PYmqGyHxXlYVaLW591PHUNKD8,10561 -packaging/metadata.py,sha256=YJibM7GYe4re8-0a3OlXmGS-XDgTEoO4tlBt2q25Bng,34762 -packaging/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 -packaging/requirements.py,sha256=gYyRSAdbrIyKDY66ugIDUQjRMvxkH2ALioTmX3tnL6o,2947 -packaging/specifiers.py,sha256=GG1wPNMcL0fMJO68vF53wKMdwnfehDcaI-r9NpTfilA,40074 -packaging/tags.py,sha256=CFqrJzAzc2XNGexerH__T-Y5Iwq7WbsYXsiLERLWxY0,21014 -packaging/utils.py,sha256=0F3Hh9OFuRgrhTgGZUl5K22Fv1YP2tZl1z_2gO6kJiA,5050 -packaging/version.py,sha256=olfyuk_DPbflNkJ4wBWetXQ17c74x3DB501degUv7DY,16676 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/REQUESTED deleted file mode 100644 index e69de29..0000000 diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/WHEEL deleted file mode 100644 index e3c6fee..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging-24.2.dist-info/WHEEL +++ /dev/null @@ -1,4 +0,0 @@ -Wheel-Version: 1.0 -Generator: flit 3.10.1 -Root-Is-Purelib: true -Tag: py3-none-any diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__init__.py deleted file mode 100644 index d79f73c..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__init__.py +++ /dev/null @@ -1,15 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. - -__title__ = "packaging" -__summary__ = "Core utilities for Python packages" -__uri__ = "https://github.com/pypa/packaging" - -__version__ = "24.2" - -__author__ = "Donald Stufft and individual contributors" -__email__ = "donald@stufft.io" - -__license__ = "BSD-2-Clause or Apache-2.0" -__copyright__ = f"2014 {__author__}" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/__init__.cpython-312.pyc deleted file mode 100644 index 78158fd..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/__init__.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc deleted file mode 100644 index 798f2d7..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_manylinux.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc deleted file mode 100644 index f90f020..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_musllinux.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_structures.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_structures.cpython-312.pyc deleted file mode 100644 index d29b79b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/_structures.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/markers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/markers.cpython-312.pyc deleted file mode 100644 index c4d636b..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/markers.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/requirements.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/requirements.cpython-312.pyc deleted file mode 100644 index a6e7e42..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/requirements.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc deleted file mode 100644 index 1e0beb6..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/specifiers.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/tags.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/tags.cpython-312.pyc deleted file mode 100644 index 750a374..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/tags.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/utils.cpython-312.pyc deleted file mode 100644 index a009a11..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/utils.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/version.cpython-312.pyc deleted file mode 100644 index 855b321..0000000 Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/__pycache__/version.cpython-312.pyc and /dev/null differ diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_manylinux.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_manylinux.py deleted file mode 100644 index 61339a6..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_manylinux.py +++ /dev/null @@ -1,263 +0,0 @@ -from __future__ import annotations - -import collections -import contextlib -import functools -import os -import re -import sys -import warnings -from typing import Generator, Iterator, NamedTuple, Sequence - -from ._elffile import EIClass, EIData, ELFFile, EMachine - -EF_ARM_ABIMASK = 0xFF000000 -EF_ARM_ABI_VER5 = 0x05000000 -EF_ARM_ABI_FLOAT_HARD = 0x00000400 - - -# `os.PathLike` not a generic type until Python 3.9, so sticking with `str` -# as the type for `path` until then. -@contextlib.contextmanager -def _parse_elf(path: str) -> Generator[ELFFile | None, None, None]: - try: - with open(path, "rb") as f: - yield ELFFile(f) - except (OSError, TypeError, ValueError): - yield None - - -def _is_linux_armhf(executable: str) -> bool: - # hard-float ABI can be detected from the ELF header of the running - # process - # https://static.docs.arm.com/ihi0044/g/aaelf32.pdf - with _parse_elf(executable) as f: - return ( - f is not None - and f.capacity == EIClass.C32 - and f.encoding == EIData.Lsb - and f.machine == EMachine.Arm - and f.flags & EF_ARM_ABIMASK == EF_ARM_ABI_VER5 - and f.flags & EF_ARM_ABI_FLOAT_HARD == EF_ARM_ABI_FLOAT_HARD - ) - - -def _is_linux_i686(executable: str) -> bool: - with _parse_elf(executable) as f: - return ( - f is not None - and f.capacity == EIClass.C32 - and f.encoding == EIData.Lsb - and f.machine == EMachine.I386 - ) - - -def _have_compatible_abi(executable: str, archs: Sequence[str]) -> bool: - if "armv7l" in archs: - return _is_linux_armhf(executable) - if "i686" in archs: - return _is_linux_i686(executable) - allowed_archs = { - "x86_64", - "aarch64", - "ppc64", - "ppc64le", - "s390x", - "loongarch64", - "riscv64", - } - return any(arch in allowed_archs for arch in archs) - - -# If glibc ever changes its major version, we need to know what the last -# minor version was, so we can build the complete list of all versions. -# For now, guess what the highest minor version might be, assume it will -# be 50 for testing. Once this actually happens, update the dictionary -# with the actual value. -_LAST_GLIBC_MINOR: dict[int, int] = collections.defaultdict(lambda: 50) - - -class _GLibCVersion(NamedTuple): - major: int - minor: int - - -def _glibc_version_string_confstr() -> str | None: - """ - Primary implementation of glibc_version_string using os.confstr. - """ - # os.confstr is quite a bit faster than ctypes.DLL. It's also less likely - # to be broken or missing. This strategy is used in the standard library - # platform module. - # https://github.com/python/cpython/blob/fcf1d003bf4f0100c/Lib/platform.py#L175-L183 - try: - # Should be a string like "glibc 2.17". - version_string: str | None = os.confstr("CS_GNU_LIBC_VERSION") - assert version_string is not None - _, version = version_string.rsplit() - except (AssertionError, AttributeError, OSError, ValueError): - # os.confstr() or CS_GNU_LIBC_VERSION not available (or a bad value)... - return None - return version - - -def _glibc_version_string_ctypes() -> str | None: - """ - Fallback implementation of glibc_version_string using ctypes. - """ - try: - import ctypes - except ImportError: - return None - - # ctypes.CDLL(None) internally calls dlopen(NULL), and as the dlopen - # manpage says, "If filename is NULL, then the returned handle is for the - # main program". This way we can let the linker do the work to figure out - # which libc our process is actually using. - # - # We must also handle the special case where the executable is not a - # dynamically linked executable. This can occur when using musl libc, - # for example. In this situation, dlopen() will error, leading to an - # OSError. Interestingly, at least in the case of musl, there is no - # errno set on the OSError. The single string argument used to construct - # OSError comes from libc itself and is therefore not portable to - # hard code here. In any case, failure to call dlopen() means we - # can proceed, so we bail on our attempt. - try: - process_namespace = ctypes.CDLL(None) - except OSError: - return None - - try: - gnu_get_libc_version = process_namespace.gnu_get_libc_version - except AttributeError: - # Symbol doesn't exist -> therefore, we are not linked to - # glibc. - return None - - # Call gnu_get_libc_version, which returns a string like "2.5" - gnu_get_libc_version.restype = ctypes.c_char_p - version_str: str = gnu_get_libc_version() - # py2 / py3 compatibility: - if not isinstance(version_str, str): - version_str = version_str.decode("ascii") - - return version_str - - -def _glibc_version_string() -> str | None: - """Returns glibc version string, or None if not using glibc.""" - return _glibc_version_string_confstr() or _glibc_version_string_ctypes() - - -def _parse_glibc_version(version_str: str) -> tuple[int, int]: - """Parse glibc version. - - We use a regexp instead of str.split because we want to discard any - random junk that might come after the minor version -- this might happen - in patched/forked versions of glibc (e.g. Linaro's version of glibc - uses version strings like "2.20-2014.11"). See gh-3588. - """ - m = re.match(r"(?P[0-9]+)\.(?P[0-9]+)", version_str) - if not m: - warnings.warn( - f"Expected glibc version with 2 components major.minor," - f" got: {version_str}", - RuntimeWarning, - stacklevel=2, - ) - return -1, -1 - return int(m.group("major")), int(m.group("minor")) - - -@functools.lru_cache -def _get_glibc_version() -> tuple[int, int]: - version_str = _glibc_version_string() - if version_str is None: - return (-1, -1) - return _parse_glibc_version(version_str) - - -# From PEP 513, PEP 600 -def _is_compatible(arch: str, version: _GLibCVersion) -> bool: - sys_glibc = _get_glibc_version() - if sys_glibc < version: - return False - # Check for presence of _manylinux module. - try: - import _manylinux - except ImportError: - return True - if hasattr(_manylinux, "manylinux_compatible"): - result = _manylinux.manylinux_compatible(version[0], version[1], arch) - if result is not None: - return bool(result) - return True - if version == _GLibCVersion(2, 5): - if hasattr(_manylinux, "manylinux1_compatible"): - return bool(_manylinux.manylinux1_compatible) - if version == _GLibCVersion(2, 12): - if hasattr(_manylinux, "manylinux2010_compatible"): - return bool(_manylinux.manylinux2010_compatible) - if version == _GLibCVersion(2, 17): - if hasattr(_manylinux, "manylinux2014_compatible"): - return bool(_manylinux.manylinux2014_compatible) - return True - - -_LEGACY_MANYLINUX_MAP = { - # CentOS 7 w/ glibc 2.17 (PEP 599) - (2, 17): "manylinux2014", - # CentOS 6 w/ glibc 2.12 (PEP 571) - (2, 12): "manylinux2010", - # CentOS 5 w/ glibc 2.5 (PEP 513) - (2, 5): "manylinux1", -} - - -def platform_tags(archs: Sequence[str]) -> Iterator[str]: - """Generate manylinux tags compatible to the current platform. - - :param archs: Sequence of compatible architectures. - The first one shall be the closest to the actual architecture and be the part of - platform tag after the ``linux_`` prefix, e.g. ``x86_64``. - The ``linux_`` prefix is assumed as a prerequisite for the current platform to - be manylinux-compatible. - - :returns: An iterator of compatible manylinux tags. - """ - if not _have_compatible_abi(sys.executable, archs): - return - # Oldest glibc to be supported regardless of architecture is (2, 17). - too_old_glibc2 = _GLibCVersion(2, 16) - if set(archs) & {"x86_64", "i686"}: - # On x86/i686 also oldest glibc to be supported is (2, 5). - too_old_glibc2 = _GLibCVersion(2, 4) - current_glibc = _GLibCVersion(*_get_glibc_version()) - glibc_max_list = [current_glibc] - # We can assume compatibility across glibc major versions. - # https://sourceware.org/bugzilla/show_bug.cgi?id=24636 - # - # Build a list of maximum glibc versions so that we can - # output the canonical list of all glibc from current_glibc - # down to too_old_glibc2, including all intermediary versions. - for glibc_major in range(current_glibc.major - 1, 1, -1): - glibc_minor = _LAST_GLIBC_MINOR[glibc_major] - glibc_max_list.append(_GLibCVersion(glibc_major, glibc_minor)) - for arch in archs: - for glibc_max in glibc_max_list: - if glibc_max.major == too_old_glibc2.major: - min_minor = too_old_glibc2.minor - else: - # For other glibc major versions oldest supported is (x, 0). - min_minor = -1 - for glibc_minor in range(glibc_max.minor, min_minor, -1): - glibc_version = _GLibCVersion(glibc_max.major, glibc_minor) - tag = "manylinux_{}_{}".format(*glibc_version) - if _is_compatible(arch, glibc_version): - yield f"{tag}_{arch}" - # Handle the legacy manylinux1, manylinux2010, manylinux2014 tags. - if glibc_version in _LEGACY_MANYLINUX_MAP: - legacy_tag = _LEGACY_MANYLINUX_MAP[glibc_version] - if _is_compatible(arch, glibc_version): - yield f"{legacy_tag}_{arch}" diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_musllinux.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_musllinux.py deleted file mode 100644 index d2bf30b..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_musllinux.py +++ /dev/null @@ -1,85 +0,0 @@ -"""PEP 656 support. - -This module implements logic to detect if the currently running Python is -linked against musl, and what musl version is used. -""" - -from __future__ import annotations - -import functools -import re -import subprocess -import sys -from typing import Iterator, NamedTuple, Sequence - -from ._elffile import ELFFile - - -class _MuslVersion(NamedTuple): - major: int - minor: int - - -def _parse_musl_version(output: str) -> _MuslVersion | None: - lines = [n for n in (n.strip() for n in output.splitlines()) if n] - if len(lines) < 2 or lines[0][:4] != "musl": - return None - m = re.match(r"Version (\d+)\.(\d+)", lines[1]) - if not m: - return None - return _MuslVersion(major=int(m.group(1)), minor=int(m.group(2))) - - -@functools.lru_cache -def _get_musl_version(executable: str) -> _MuslVersion | None: - """Detect currently-running musl runtime version. - - This is done by checking the specified executable's dynamic linking - information, and invoking the loader to parse its output for a version - string. If the loader is musl, the output would be something like:: - - musl libc (x86_64) - Version 1.2.2 - Dynamic Program Loader - """ - try: - with open(executable, "rb") as f: - ld = ELFFile(f).interpreter - except (OSError, TypeError, ValueError): - return None - if ld is None or "musl" not in ld: - return None - proc = subprocess.run([ld], stderr=subprocess.PIPE, text=True) - return _parse_musl_version(proc.stderr) - - -def platform_tags(archs: Sequence[str]) -> Iterator[str]: - """Generate musllinux tags compatible to the current platform. - - :param archs: Sequence of compatible architectures. - The first one shall be the closest to the actual architecture and be the part of - platform tag after the ``linux_`` prefix, e.g. ``x86_64``. - The ``linux_`` prefix is assumed as a prerequisite for the current platform to - be musllinux-compatible. - - :returns: An iterator of compatible musllinux tags. - """ - sys_musl = _get_musl_version(sys.executable) - if sys_musl is None: # Python not dynamically linked against musl. - return - for arch in archs: - for minor in range(sys_musl.minor, -1, -1): - yield f"musllinux_{sys_musl.major}_{minor}_{arch}" - - -if __name__ == "__main__": # pragma: no cover - import sysconfig - - plat = sysconfig.get_platform() - assert plat.startswith("linux-"), "not linux" - - print("plat:", plat) - print("musl:", _get_musl_version(sys.executable)) - print("tags:", end=" ") - for t in platform_tags(re.sub(r"[.-]", "_", plat.split("-", 1)[-1])): - print(t, end="\n ") diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_structures.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_structures.py deleted file mode 100644 index 90a6465..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/_structures.py +++ /dev/null @@ -1,61 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. - - -class InfinityType: - def __repr__(self) -> str: - return "Infinity" - - def __hash__(self) -> int: - return hash(repr(self)) - - def __lt__(self, other: object) -> bool: - return False - - def __le__(self, other: object) -> bool: - return False - - def __eq__(self, other: object) -> bool: - return isinstance(other, self.__class__) - - def __gt__(self, other: object) -> bool: - return True - - def __ge__(self, other: object) -> bool: - return True - - def __neg__(self: object) -> "NegativeInfinityType": - return NegativeInfinity - - -Infinity = InfinityType() - - -class NegativeInfinityType: - def __repr__(self) -> str: - return "-Infinity" - - def __hash__(self) -> int: - return hash(repr(self)) - - def __lt__(self, other: object) -> bool: - return True - - def __le__(self, other: object) -> bool: - return True - - def __eq__(self, other: object) -> bool: - return isinstance(other, self.__class__) - - def __gt__(self, other: object) -> bool: - return False - - def __ge__(self, other: object) -> bool: - return False - - def __neg__(self: object) -> InfinityType: - return Infinity - - -NegativeInfinity = NegativeInfinityType() diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/markers.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/markers.py deleted file mode 100644 index fb7f49c..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/markers.py +++ /dev/null @@ -1,331 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. - -from __future__ import annotations - -import operator -import os -import platform -import sys -from typing import Any, Callable, TypedDict, cast - -from ._parser import MarkerAtom, MarkerList, Op, Value, Variable -from ._parser import parse_marker as _parse_marker -from ._tokenizer import ParserSyntaxError -from .specifiers import InvalidSpecifier, Specifier -from .utils import canonicalize_name - -__all__ = [ - "InvalidMarker", - "Marker", - "UndefinedComparison", - "UndefinedEnvironmentName", - "default_environment", -] - -Operator = Callable[[str, str], bool] - - -class InvalidMarker(ValueError): - """ - An invalid marker was found, users should refer to PEP 508. - """ - - -class UndefinedComparison(ValueError): - """ - An invalid operation was attempted on a value that doesn't support it. - """ - - -class UndefinedEnvironmentName(ValueError): - """ - A name was attempted to be used that does not exist inside of the - environment. - """ - - -class Environment(TypedDict): - implementation_name: str - """The implementation's identifier, e.g. ``'cpython'``.""" - - implementation_version: str - """ - The implementation's version, e.g. ``'3.13.0a2'`` for CPython 3.13.0a2, or - ``'7.3.13'`` for PyPy3.10 v7.3.13. - """ - - os_name: str - """ - The value of :py:data:`os.name`. The name of the operating system dependent module - imported, e.g. ``'posix'``. - """ - - platform_machine: str - """ - Returns the machine type, e.g. ``'i386'``. - - An empty string if the value cannot be determined. - """ - - platform_release: str - """ - The system's release, e.g. ``'2.2.0'`` or ``'NT'``. - - An empty string if the value cannot be determined. - """ - - platform_system: str - """ - The system/OS name, e.g. ``'Linux'``, ``'Windows'`` or ``'Java'``. - - An empty string if the value cannot be determined. - """ - - platform_version: str - """ - The system's release version, e.g. ``'#3 on degas'``. - - An empty string if the value cannot be determined. - """ - - python_full_version: str - """ - The Python version as string ``'major.minor.patchlevel'``. - - Note that unlike the Python :py:data:`sys.version`, this value will always include - the patchlevel (it defaults to 0). - """ - - platform_python_implementation: str - """ - A string identifying the Python implementation, e.g. ``'CPython'``. - """ - - python_version: str - """The Python version as string ``'major.minor'``.""" - - sys_platform: str - """ - This string contains a platform identifier that can be used to append - platform-specific components to :py:data:`sys.path`, for instance. - - For Unix systems, except on Linux and AIX, this is the lowercased OS name as - returned by ``uname -s`` with the first part of the version as returned by - ``uname -r`` appended, e.g. ``'sunos5'`` or ``'freebsd8'``, at the time when Python - was built. - """ - - -def _normalize_extra_values(results: Any) -> Any: - """ - Normalize extra values. - """ - if isinstance(results[0], tuple): - lhs, op, rhs = results[0] - if isinstance(lhs, Variable) and lhs.value == "extra": - normalized_extra = canonicalize_name(rhs.value) - rhs = Value(normalized_extra) - elif isinstance(rhs, Variable) and rhs.value == "extra": - normalized_extra = canonicalize_name(lhs.value) - lhs = Value(normalized_extra) - results[0] = lhs, op, rhs - return results - - -def _format_marker( - marker: list[str] | MarkerAtom | str, first: bool | None = True -) -> str: - assert isinstance(marker, (list, tuple, str)) - - # Sometimes we have a structure like [[...]] which is a single item list - # where the single item is itself it's own list. In that case we want skip - # the rest of this function so that we don't get extraneous () on the - # outside. - if ( - isinstance(marker, list) - and len(marker) == 1 - and isinstance(marker[0], (list, tuple)) - ): - return _format_marker(marker[0]) - - if isinstance(marker, list): - inner = (_format_marker(m, first=False) for m in marker) - if first: - return " ".join(inner) - else: - return "(" + " ".join(inner) + ")" - elif isinstance(marker, tuple): - return " ".join([m.serialize() for m in marker]) - else: - return marker - - -_operators: dict[str, Operator] = { - "in": lambda lhs, rhs: lhs in rhs, - "not in": lambda lhs, rhs: lhs not in rhs, - "<": operator.lt, - "<=": operator.le, - "==": operator.eq, - "!=": operator.ne, - ">=": operator.ge, - ">": operator.gt, -} - - -def _eval_op(lhs: str, op: Op, rhs: str) -> bool: - try: - spec = Specifier("".join([op.serialize(), rhs])) - except InvalidSpecifier: - pass - else: - return spec.contains(lhs, prereleases=True) - - oper: Operator | None = _operators.get(op.serialize()) - if oper is None: - raise UndefinedComparison(f"Undefined {op!r} on {lhs!r} and {rhs!r}.") - - return oper(lhs, rhs) - - -def _normalize(*values: str, key: str) -> tuple[str, ...]: - # PEP 685 – Comparison of extra names for optional distribution dependencies - # https://peps.python.org/pep-0685/ - # > When comparing extra names, tools MUST normalize the names being - # > compared using the semantics outlined in PEP 503 for names - if key == "extra": - return tuple(canonicalize_name(v) for v in values) - - # other environment markers don't have such standards - return values - - -def _evaluate_markers(markers: MarkerList, environment: dict[str, str]) -> bool: - groups: list[list[bool]] = [[]] - - for marker in markers: - assert isinstance(marker, (list, tuple, str)) - - if isinstance(marker, list): - groups[-1].append(_evaluate_markers(marker, environment)) - elif isinstance(marker, tuple): - lhs, op, rhs = marker - - if isinstance(lhs, Variable): - environment_key = lhs.value - lhs_value = environment[environment_key] - rhs_value = rhs.value - else: - lhs_value = lhs.value - environment_key = rhs.value - rhs_value = environment[environment_key] - - lhs_value, rhs_value = _normalize(lhs_value, rhs_value, key=environment_key) - groups[-1].append(_eval_op(lhs_value, op, rhs_value)) - else: - assert marker in ["and", "or"] - if marker == "or": - groups.append([]) - - return any(all(item) for item in groups) - - -def format_full_version(info: sys._version_info) -> str: - version = f"{info.major}.{info.minor}.{info.micro}" - kind = info.releaselevel - if kind != "final": - version += kind[0] + str(info.serial) - return version - - -def default_environment() -> Environment: - iver = format_full_version(sys.implementation.version) - implementation_name = sys.implementation.name - return { - "implementation_name": implementation_name, - "implementation_version": iver, - "os_name": os.name, - "platform_machine": platform.machine(), - "platform_release": platform.release(), - "platform_system": platform.system(), - "platform_version": platform.version(), - "python_full_version": platform.python_version(), - "platform_python_implementation": platform.python_implementation(), - "python_version": ".".join(platform.python_version_tuple()[:2]), - "sys_platform": sys.platform, - } - - -class Marker: - def __init__(self, marker: str) -> None: - # Note: We create a Marker object without calling this constructor in - # packaging.requirements.Requirement. If any additional logic is - # added here, make sure to mirror/adapt Requirement. - try: - self._markers = _normalize_extra_values(_parse_marker(marker)) - # The attribute `_markers` can be described in terms of a recursive type: - # MarkerList = List[Union[Tuple[Node, ...], str, MarkerList]] - # - # For example, the following expression: - # python_version > "3.6" or (python_version == "3.6" and os_name == "unix") - # - # is parsed into: - # [ - # (, ')>, ), - # 'and', - # [ - # (, , ), - # 'or', - # (, , ) - # ] - # ] - except ParserSyntaxError as e: - raise InvalidMarker(str(e)) from e - - def __str__(self) -> str: - return _format_marker(self._markers) - - def __repr__(self) -> str: - return f"" - - def __hash__(self) -> int: - return hash((self.__class__.__name__, str(self))) - - def __eq__(self, other: Any) -> bool: - if not isinstance(other, Marker): - return NotImplemented - - return str(self) == str(other) - - def evaluate(self, environment: dict[str, str] | None = None) -> bool: - """Evaluate a marker. - - Return the boolean from evaluating the given marker against the - environment. environment is an optional argument to override all or - part of the determined environment. - - The environment is determined from the current Python process. - """ - current_environment = cast("dict[str, str]", default_environment()) - current_environment["extra"] = "" - if environment is not None: - current_environment.update(environment) - # The API used to allow setting extra to None. We need to handle this - # case for backwards compatibility. - if current_environment["extra"] is None: - current_environment["extra"] = "" - - return _evaluate_markers( - self._markers, _repair_python_full_version(current_environment) - ) - - -def _repair_python_full_version(env: dict[str, str]) -> dict[str, str]: - """ - Work around platform.python_version() returning something that is not PEP 440 - compliant for non-tagged Python builds. - """ - if env["python_full_version"].endswith("+"): - env["python_full_version"] += "local" - return env diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/requirements.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/requirements.py deleted file mode 100644 index 4e068c9..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/requirements.py +++ /dev/null @@ -1,91 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. -from __future__ import annotations - -from typing import Any, Iterator - -from ._parser import parse_requirement as _parse_requirement -from ._tokenizer import ParserSyntaxError -from .markers import Marker, _normalize_extra_values -from .specifiers import SpecifierSet -from .utils import canonicalize_name - - -class InvalidRequirement(ValueError): - """ - An invalid requirement was found, users should refer to PEP 508. - """ - - -class Requirement: - """Parse a requirement. - - Parse a given requirement string into its parts, such as name, specifier, - URL, and extras. Raises InvalidRequirement on a badly-formed requirement - string. - """ - - # TODO: Can we test whether something is contained within a requirement? - # If so how do we do that? Do we need to test against the _name_ of - # the thing as well as the version? What about the markers? - # TODO: Can we normalize the name and extra name? - - def __init__(self, requirement_string: str) -> None: - try: - parsed = _parse_requirement(requirement_string) - except ParserSyntaxError as e: - raise InvalidRequirement(str(e)) from e - - self.name: str = parsed.name - self.url: str | None = parsed.url or None - self.extras: set[str] = set(parsed.extras or []) - self.specifier: SpecifierSet = SpecifierSet(parsed.specifier) - self.marker: Marker | None = None - if parsed.marker is not None: - self.marker = Marker.__new__(Marker) - self.marker._markers = _normalize_extra_values(parsed.marker) - - def _iter_parts(self, name: str) -> Iterator[str]: - yield name - - if self.extras: - formatted_extras = ",".join(sorted(self.extras)) - yield f"[{formatted_extras}]" - - if self.specifier: - yield str(self.specifier) - - if self.url: - yield f"@ {self.url}" - if self.marker: - yield " " - - if self.marker: - yield f"; {self.marker}" - - def __str__(self) -> str: - return "".join(self._iter_parts(self.name)) - - def __repr__(self) -> str: - return f"" - - def __hash__(self) -> int: - return hash( - ( - self.__class__.__name__, - *self._iter_parts(canonicalize_name(self.name)), - ) - ) - - def __eq__(self, other: Any) -> bool: - if not isinstance(other, Requirement): - return NotImplemented - - return ( - canonicalize_name(self.name) == canonicalize_name(other.name) - and self.extras == other.extras - and self.specifier == other.specifier - and self.url == other.url - and self.marker == other.marker - ) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/specifiers.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/specifiers.py deleted file mode 100644 index b30926a..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/specifiers.py +++ /dev/null @@ -1,1020 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. -""" -.. testsetup:: - - from packaging.specifiers import Specifier, SpecifierSet, InvalidSpecifier - from packaging.version import Version -""" - -from __future__ import annotations - -import abc -import itertools -import re -from typing import Callable, Iterable, Iterator, TypeVar, Union - -from .utils import canonicalize_version -from .version import Version - -UnparsedVersion = Union[Version, str] -UnparsedVersionVar = TypeVar("UnparsedVersionVar", bound=UnparsedVersion) -CallableOperator = Callable[[Version, str], bool] - - -def _coerce_version(version: UnparsedVersion) -> Version: - if not isinstance(version, Version): - version = Version(version) - return version - - -class InvalidSpecifier(ValueError): - """ - Raised when attempting to create a :class:`Specifier` with a specifier - string that is invalid. - - >>> Specifier("lolwat") - Traceback (most recent call last): - ... - packaging.specifiers.InvalidSpecifier: Invalid specifier: 'lolwat' - """ - - -class BaseSpecifier(metaclass=abc.ABCMeta): - @abc.abstractmethod - def __str__(self) -> str: - """ - Returns the str representation of this Specifier-like object. This - should be representative of the Specifier itself. - """ - - @abc.abstractmethod - def __hash__(self) -> int: - """ - Returns a hash value for this Specifier-like object. - """ - - @abc.abstractmethod - def __eq__(self, other: object) -> bool: - """ - Returns a boolean representing whether or not the two Specifier-like - objects are equal. - - :param other: The other object to check against. - """ - - @property - @abc.abstractmethod - def prereleases(self) -> bool | None: - """Whether or not pre-releases as a whole are allowed. - - This can be set to either ``True`` or ``False`` to explicitly enable or disable - prereleases or it can be set to ``None`` (the default) to use default semantics. - """ - - @prereleases.setter - def prereleases(self, value: bool) -> None: - """Setter for :attr:`prereleases`. - - :param value: The value to set. - """ - - @abc.abstractmethod - def contains(self, item: str, prereleases: bool | None = None) -> bool: - """ - Determines if the given item is contained within this specifier. - """ - - @abc.abstractmethod - def filter( - self, iterable: Iterable[UnparsedVersionVar], prereleases: bool | None = None - ) -> Iterator[UnparsedVersionVar]: - """ - Takes an iterable of items and filters them so that only items which - are contained within this specifier are allowed in it. - """ - - -class Specifier(BaseSpecifier): - """This class abstracts handling of version specifiers. - - .. tip:: - - It is generally not required to instantiate this manually. You should instead - prefer to work with :class:`SpecifierSet` instead, which can parse - comma-separated version specifiers (which is what package metadata contains). - """ - - _operator_regex_str = r""" - (?P(~=|==|!=|<=|>=|<|>|===)) - """ - _version_regex_str = r""" - (?P - (?: - # The identity operators allow for an escape hatch that will - # do an exact string match of the version you wish to install. - # This will not be parsed by PEP 440 and we cannot determine - # any semantic meaning from it. This operator is discouraged - # but included entirely as an escape hatch. - (?<====) # Only match for the identity operator - \s* - [^\s;)]* # The arbitrary version can be just about anything, - # we match everything except for whitespace, a - # semi-colon for marker support, and a closing paren - # since versions can be enclosed in them. - ) - | - (?: - # The (non)equality operators allow for wild card and local - # versions to be specified so we have to define these two - # operators separately to enable that. - (?<===|!=) # Only match for equals and not equals - - \s* - v? - (?:[0-9]+!)? # epoch - [0-9]+(?:\.[0-9]+)* # release - - # You cannot use a wild card and a pre-release, post-release, a dev or - # local version together so group them with a | and make them optional. - (?: - \.\* # Wild card syntax of .* - | - (?: # pre release - [-_\.]? - (alpha|beta|preview|pre|a|b|c|rc) - [-_\.]? - [0-9]* - )? - (?: # post release - (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*) - )? - (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release - (?:\+[a-z0-9]+(?:[-_\.][a-z0-9]+)*)? # local - )? - ) - | - (?: - # The compatible operator requires at least two digits in the - # release segment. - (?<=~=) # Only match for the compatible operator - - \s* - v? - (?:[0-9]+!)? # epoch - [0-9]+(?:\.[0-9]+)+ # release (We have a + instead of a *) - (?: # pre release - [-_\.]? - (alpha|beta|preview|pre|a|b|c|rc) - [-_\.]? - [0-9]* - )? - (?: # post release - (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*) - )? - (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release - ) - | - (?: - # All other operators only allow a sub set of what the - # (non)equality operators do. Specifically they do not allow - # local versions to be specified nor do they allow the prefix - # matching wild cards. - (?=": "greater_than_equal", - "<": "less_than", - ">": "greater_than", - "===": "arbitrary", - } - - def __init__(self, spec: str = "", prereleases: bool | None = None) -> None: - """Initialize a Specifier instance. - - :param spec: - The string representation of a specifier which will be parsed and - normalized before use. - :param prereleases: - This tells the specifier if it should accept prerelease versions if - applicable or not. The default of ``None`` will autodetect it from the - given specifiers. - :raises InvalidSpecifier: - If the given specifier is invalid (i.e. bad syntax). - """ - match = self._regex.search(spec) - if not match: - raise InvalidSpecifier(f"Invalid specifier: {spec!r}") - - self._spec: tuple[str, str] = ( - match.group("operator").strip(), - match.group("version").strip(), - ) - - # Store whether or not this Specifier should accept prereleases - self._prereleases = prereleases - - # https://github.com/python/mypy/pull/13475#pullrequestreview-1079784515 - @property # type: ignore[override] - def prereleases(self) -> bool: - # If there is an explicit prereleases set for this, then we'll just - # blindly use that. - if self._prereleases is not None: - return self._prereleases - - # Look at all of our specifiers and determine if they are inclusive - # operators, and if they are if they are including an explicit - # prerelease. - operator, version = self._spec - if operator in ["==", ">=", "<=", "~=", "===", ">", "<"]: - # The == specifier can include a trailing .*, if it does we - # want to remove before parsing. - if operator == "==" and version.endswith(".*"): - version = version[:-2] - - # Parse the version, and if it is a pre-release than this - # specifier allows pre-releases. - if Version(version).is_prerelease: - return True - - return False - - @prereleases.setter - def prereleases(self, value: bool) -> None: - self._prereleases = value - - @property - def operator(self) -> str: - """The operator of this specifier. - - >>> Specifier("==1.2.3").operator - '==' - """ - return self._spec[0] - - @property - def version(self) -> str: - """The version of this specifier. - - >>> Specifier("==1.2.3").version - '1.2.3' - """ - return self._spec[1] - - def __repr__(self) -> str: - """A representation of the Specifier that shows all internal state. - - >>> Specifier('>=1.0.0') - =1.0.0')> - >>> Specifier('>=1.0.0', prereleases=False) - =1.0.0', prereleases=False)> - >>> Specifier('>=1.0.0', prereleases=True) - =1.0.0', prereleases=True)> - """ - pre = ( - f", prereleases={self.prereleases!r}" - if self._prereleases is not None - else "" - ) - - return f"<{self.__class__.__name__}({str(self)!r}{pre})>" - - def __str__(self) -> str: - """A string representation of the Specifier that can be round-tripped. - - >>> str(Specifier('>=1.0.0')) - '>=1.0.0' - >>> str(Specifier('>=1.0.0', prereleases=False)) - '>=1.0.0' - """ - return "{}{}".format(*self._spec) - - @property - def _canonical_spec(self) -> tuple[str, str]: - canonical_version = canonicalize_version( - self._spec[1], - strip_trailing_zero=(self._spec[0] != "~="), - ) - return self._spec[0], canonical_version - - def __hash__(self) -> int: - return hash(self._canonical_spec) - - def __eq__(self, other: object) -> bool: - """Whether or not the two Specifier-like objects are equal. - - :param other: The other object to check against. - - The value of :attr:`prereleases` is ignored. - - >>> Specifier("==1.2.3") == Specifier("== 1.2.3.0") - True - >>> (Specifier("==1.2.3", prereleases=False) == - ... Specifier("==1.2.3", prereleases=True)) - True - >>> Specifier("==1.2.3") == "==1.2.3" - True - >>> Specifier("==1.2.3") == Specifier("==1.2.4") - False - >>> Specifier("==1.2.3") == Specifier("~=1.2.3") - False - """ - if isinstance(other, str): - try: - other = self.__class__(str(other)) - except InvalidSpecifier: - return NotImplemented - elif not isinstance(other, self.__class__): - return NotImplemented - - return self._canonical_spec == other._canonical_spec - - def _get_operator(self, op: str) -> CallableOperator: - operator_callable: CallableOperator = getattr( - self, f"_compare_{self._operators[op]}" - ) - return operator_callable - - def _compare_compatible(self, prospective: Version, spec: str) -> bool: - # Compatible releases have an equivalent combination of >= and ==. That - # is that ~=2.2 is equivalent to >=2.2,==2.*. This allows us to - # implement this in terms of the other specifiers instead of - # implementing it ourselves. The only thing we need to do is construct - # the other specifiers. - - # We want everything but the last item in the version, but we want to - # ignore suffix segments. - prefix = _version_join( - list(itertools.takewhile(_is_not_suffix, _version_split(spec)))[:-1] - ) - - # Add the prefix notation to the end of our string - prefix += ".*" - - return self._get_operator(">=")(prospective, spec) and self._get_operator("==")( - prospective, prefix - ) - - def _compare_equal(self, prospective: Version, spec: str) -> bool: - # We need special logic to handle prefix matching - if spec.endswith(".*"): - # In the case of prefix matching we want to ignore local segment. - normalized_prospective = canonicalize_version( - prospective.public, strip_trailing_zero=False - ) - # Get the normalized version string ignoring the trailing .* - normalized_spec = canonicalize_version(spec[:-2], strip_trailing_zero=False) - # Split the spec out by bangs and dots, and pretend that there is - # an implicit dot in between a release segment and a pre-release segment. - split_spec = _version_split(normalized_spec) - - # Split the prospective version out by bangs and dots, and pretend - # that there is an implicit dot in between a release segment and - # a pre-release segment. - split_prospective = _version_split(normalized_prospective) - - # 0-pad the prospective version before shortening it to get the correct - # shortened version. - padded_prospective, _ = _pad_version(split_prospective, split_spec) - - # Shorten the prospective version to be the same length as the spec - # so that we can determine if the specifier is a prefix of the - # prospective version or not. - shortened_prospective = padded_prospective[: len(split_spec)] - - return shortened_prospective == split_spec - else: - # Convert our spec string into a Version - spec_version = Version(spec) - - # If the specifier does not have a local segment, then we want to - # act as if the prospective version also does not have a local - # segment. - if not spec_version.local: - prospective = Version(prospective.public) - - return prospective == spec_version - - def _compare_not_equal(self, prospective: Version, spec: str) -> bool: - return not self._compare_equal(prospective, spec) - - def _compare_less_than_equal(self, prospective: Version, spec: str) -> bool: - # NB: Local version identifiers are NOT permitted in the version - # specifier, so local version labels can be universally removed from - # the prospective version. - return Version(prospective.public) <= Version(spec) - - def _compare_greater_than_equal(self, prospective: Version, spec: str) -> bool: - # NB: Local version identifiers are NOT permitted in the version - # specifier, so local version labels can be universally removed from - # the prospective version. - return Version(prospective.public) >= Version(spec) - - def _compare_less_than(self, prospective: Version, spec_str: str) -> bool: - # Convert our spec to a Version instance, since we'll want to work with - # it as a version. - spec = Version(spec_str) - - # Check to see if the prospective version is less than the spec - # version. If it's not we can short circuit and just return False now - # instead of doing extra unneeded work. - if not prospective < spec: - return False - - # This special case is here so that, unless the specifier itself - # includes is a pre-release version, that we do not accept pre-release - # versions for the version mentioned in the specifier (e.g. <3.1 should - # not match 3.1.dev0, but should match 3.0.dev0). - if not spec.is_prerelease and prospective.is_prerelease: - if Version(prospective.base_version) == Version(spec.base_version): - return False - - # If we've gotten to here, it means that prospective version is both - # less than the spec version *and* it's not a pre-release of the same - # version in the spec. - return True - - def _compare_greater_than(self, prospective: Version, spec_str: str) -> bool: - # Convert our spec to a Version instance, since we'll want to work with - # it as a version. - spec = Version(spec_str) - - # Check to see if the prospective version is greater than the spec - # version. If it's not we can short circuit and just return False now - # instead of doing extra unneeded work. - if not prospective > spec: - return False - - # This special case is here so that, unless the specifier itself - # includes is a post-release version, that we do not accept - # post-release versions for the version mentioned in the specifier - # (e.g. >3.1 should not match 3.0.post0, but should match 3.2.post0). - if not spec.is_postrelease and prospective.is_postrelease: - if Version(prospective.base_version) == Version(spec.base_version): - return False - - # Ensure that we do not allow a local version of the version mentioned - # in the specifier, which is technically greater than, to match. - if prospective.local is not None: - if Version(prospective.base_version) == Version(spec.base_version): - return False - - # If we've gotten to here, it means that prospective version is both - # greater than the spec version *and* it's not a pre-release of the - # same version in the spec. - return True - - def _compare_arbitrary(self, prospective: Version, spec: str) -> bool: - return str(prospective).lower() == str(spec).lower() - - def __contains__(self, item: str | Version) -> bool: - """Return whether or not the item is contained in this specifier. - - :param item: The item to check for. - - This is used for the ``in`` operator and behaves the same as - :meth:`contains` with no ``prereleases`` argument passed. - - >>> "1.2.3" in Specifier(">=1.2.3") - True - >>> Version("1.2.3") in Specifier(">=1.2.3") - True - >>> "1.0.0" in Specifier(">=1.2.3") - False - >>> "1.3.0a1" in Specifier(">=1.2.3") - False - >>> "1.3.0a1" in Specifier(">=1.2.3", prereleases=True) - True - """ - return self.contains(item) - - def contains(self, item: UnparsedVersion, prereleases: bool | None = None) -> bool: - """Return whether or not the item is contained in this specifier. - - :param item: - The item to check for, which can be a version string or a - :class:`Version` instance. - :param prereleases: - Whether or not to match prereleases with this Specifier. If set to - ``None`` (the default), it uses :attr:`prereleases` to determine - whether or not prereleases are allowed. - - >>> Specifier(">=1.2.3").contains("1.2.3") - True - >>> Specifier(">=1.2.3").contains(Version("1.2.3")) - True - >>> Specifier(">=1.2.3").contains("1.0.0") - False - >>> Specifier(">=1.2.3").contains("1.3.0a1") - False - >>> Specifier(">=1.2.3", prereleases=True).contains("1.3.0a1") - True - >>> Specifier(">=1.2.3").contains("1.3.0a1", prereleases=True) - True - """ - - # Determine if prereleases are to be allowed or not. - if prereleases is None: - prereleases = self.prereleases - - # Normalize item to a Version, this allows us to have a shortcut for - # "2.0" in Specifier(">=2") - normalized_item = _coerce_version(item) - - # Determine if we should be supporting prereleases in this specifier - # or not, if we do not support prereleases than we can short circuit - # logic if this version is a prereleases. - if normalized_item.is_prerelease and not prereleases: - return False - - # Actually do the comparison to determine if this item is contained - # within this Specifier or not. - operator_callable: CallableOperator = self._get_operator(self.operator) - return operator_callable(normalized_item, self.version) - - def filter( - self, iterable: Iterable[UnparsedVersionVar], prereleases: bool | None = None - ) -> Iterator[UnparsedVersionVar]: - """Filter items in the given iterable, that match the specifier. - - :param iterable: - An iterable that can contain version strings and :class:`Version` instances. - The items in the iterable will be filtered according to the specifier. - :param prereleases: - Whether or not to allow prereleases in the returned iterator. If set to - ``None`` (the default), it will be intelligently decide whether to allow - prereleases or not (based on the :attr:`prereleases` attribute, and - whether the only versions matching are prereleases). - - This method is smarter than just ``filter(Specifier().contains, [...])`` - because it implements the rule from :pep:`440` that a prerelease item - SHOULD be accepted if no other versions match the given specifier. - - >>> list(Specifier(">=1.2.3").filter(["1.2", "1.3", "1.5a1"])) - ['1.3'] - >>> list(Specifier(">=1.2.3").filter(["1.2", "1.2.3", "1.3", Version("1.4")])) - ['1.2.3', '1.3', ] - >>> list(Specifier(">=1.2.3").filter(["1.2", "1.5a1"])) - ['1.5a1'] - >>> list(Specifier(">=1.2.3").filter(["1.3", "1.5a1"], prereleases=True)) - ['1.3', '1.5a1'] - >>> list(Specifier(">=1.2.3", prereleases=True).filter(["1.3", "1.5a1"])) - ['1.3', '1.5a1'] - """ - - yielded = False - found_prereleases = [] - - kw = {"prereleases": prereleases if prereleases is not None else True} - - # Attempt to iterate over all the values in the iterable and if any of - # them match, yield them. - for version in iterable: - parsed_version = _coerce_version(version) - - if self.contains(parsed_version, **kw): - # If our version is a prerelease, and we were not set to allow - # prereleases, then we'll store it for later in case nothing - # else matches this specifier. - if parsed_version.is_prerelease and not ( - prereleases or self.prereleases - ): - found_prereleases.append(version) - # Either this is not a prerelease, or we should have been - # accepting prereleases from the beginning. - else: - yielded = True - yield version - - # Now that we've iterated over everything, determine if we've yielded - # any values, and if we have not and we have any prereleases stored up - # then we will go ahead and yield the prereleases. - if not yielded and found_prereleases: - for version in found_prereleases: - yield version - - -_prefix_regex = re.compile(r"^([0-9]+)((?:a|b|c|rc)[0-9]+)$") - - -def _version_split(version: str) -> list[str]: - """Split version into components. - - The split components are intended for version comparison. The logic does - not attempt to retain the original version string, so joining the - components back with :func:`_version_join` may not produce the original - version string. - """ - result: list[str] = [] - - epoch, _, rest = version.rpartition("!") - result.append(epoch or "0") - - for item in rest.split("."): - match = _prefix_regex.search(item) - if match: - result.extend(match.groups()) - else: - result.append(item) - return result - - -def _version_join(components: list[str]) -> str: - """Join split version components into a version string. - - This function assumes the input came from :func:`_version_split`, where the - first component must be the epoch (either empty or numeric), and all other - components numeric. - """ - epoch, *rest = components - return f"{epoch}!{'.'.join(rest)}" - - -def _is_not_suffix(segment: str) -> bool: - return not any( - segment.startswith(prefix) for prefix in ("dev", "a", "b", "rc", "post") - ) - - -def _pad_version(left: list[str], right: list[str]) -> tuple[list[str], list[str]]: - left_split, right_split = [], [] - - # Get the release segment of our versions - left_split.append(list(itertools.takewhile(lambda x: x.isdigit(), left))) - right_split.append(list(itertools.takewhile(lambda x: x.isdigit(), right))) - - # Get the rest of our versions - left_split.append(left[len(left_split[0]) :]) - right_split.append(right[len(right_split[0]) :]) - - # Insert our padding - left_split.insert(1, ["0"] * max(0, len(right_split[0]) - len(left_split[0]))) - right_split.insert(1, ["0"] * max(0, len(left_split[0]) - len(right_split[0]))) - - return ( - list(itertools.chain.from_iterable(left_split)), - list(itertools.chain.from_iterable(right_split)), - ) - - -class SpecifierSet(BaseSpecifier): - """This class abstracts handling of a set of version specifiers. - - It can be passed a single specifier (``>=3.0``), a comma-separated list of - specifiers (``>=3.0,!=3.1``), or no specifier at all. - """ - - def __init__( - self, - specifiers: str | Iterable[Specifier] = "", - prereleases: bool | None = None, - ) -> None: - """Initialize a SpecifierSet instance. - - :param specifiers: - The string representation of a specifier or a comma-separated list of - specifiers which will be parsed and normalized before use. - May also be an iterable of ``Specifier`` instances, which will be used - as is. - :param prereleases: - This tells the SpecifierSet if it should accept prerelease versions if - applicable or not. The default of ``None`` will autodetect it from the - given specifiers. - - :raises InvalidSpecifier: - If the given ``specifiers`` are not parseable than this exception will be - raised. - """ - - if isinstance(specifiers, str): - # Split on `,` to break each individual specifier into its own item, and - # strip each item to remove leading/trailing whitespace. - split_specifiers = [s.strip() for s in specifiers.split(",") if s.strip()] - - # Make each individual specifier a Specifier and save in a frozen set - # for later. - self._specs = frozenset(map(Specifier, split_specifiers)) - else: - # Save the supplied specifiers in a frozen set. - self._specs = frozenset(specifiers) - - # Store our prereleases value so we can use it later to determine if - # we accept prereleases or not. - self._prereleases = prereleases - - @property - def prereleases(self) -> bool | None: - # If we have been given an explicit prerelease modifier, then we'll - # pass that through here. - if self._prereleases is not None: - return self._prereleases - - # If we don't have any specifiers, and we don't have a forced value, - # then we'll just return None since we don't know if this should have - # pre-releases or not. - if not self._specs: - return None - - # Otherwise we'll see if any of the given specifiers accept - # prereleases, if any of them do we'll return True, otherwise False. - return any(s.prereleases for s in self._specs) - - @prereleases.setter - def prereleases(self, value: bool) -> None: - self._prereleases = value - - def __repr__(self) -> str: - """A representation of the specifier set that shows all internal state. - - Note that the ordering of the individual specifiers within the set may not - match the input string. - - >>> SpecifierSet('>=1.0.0,!=2.0.0') - =1.0.0')> - >>> SpecifierSet('>=1.0.0,!=2.0.0', prereleases=False) - =1.0.0', prereleases=False)> - >>> SpecifierSet('>=1.0.0,!=2.0.0', prereleases=True) - =1.0.0', prereleases=True)> - """ - pre = ( - f", prereleases={self.prereleases!r}" - if self._prereleases is not None - else "" - ) - - return f"" - - def __str__(self) -> str: - """A string representation of the specifier set that can be round-tripped. - - Note that the ordering of the individual specifiers within the set may not - match the input string. - - >>> str(SpecifierSet(">=1.0.0,!=1.0.1")) - '!=1.0.1,>=1.0.0' - >>> str(SpecifierSet(">=1.0.0,!=1.0.1", prereleases=False)) - '!=1.0.1,>=1.0.0' - """ - return ",".join(sorted(str(s) for s in self._specs)) - - def __hash__(self) -> int: - return hash(self._specs) - - def __and__(self, other: SpecifierSet | str) -> SpecifierSet: - """Return a SpecifierSet which is a combination of the two sets. - - :param other: The other object to combine with. - - >>> SpecifierSet(">=1.0.0,!=1.0.1") & '<=2.0.0,!=2.0.1' - =1.0.0')> - >>> SpecifierSet(">=1.0.0,!=1.0.1") & SpecifierSet('<=2.0.0,!=2.0.1') - =1.0.0')> - """ - if isinstance(other, str): - other = SpecifierSet(other) - elif not isinstance(other, SpecifierSet): - return NotImplemented - - specifier = SpecifierSet() - specifier._specs = frozenset(self._specs | other._specs) - - if self._prereleases is None and other._prereleases is not None: - specifier._prereleases = other._prereleases - elif self._prereleases is not None and other._prereleases is None: - specifier._prereleases = self._prereleases - elif self._prereleases == other._prereleases: - specifier._prereleases = self._prereleases - else: - raise ValueError( - "Cannot combine SpecifierSets with True and False prerelease " - "overrides." - ) - - return specifier - - def __eq__(self, other: object) -> bool: - """Whether or not the two SpecifierSet-like objects are equal. - - :param other: The other object to check against. - - The value of :attr:`prereleases` is ignored. - - >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0,!=1.0.1") - True - >>> (SpecifierSet(">=1.0.0,!=1.0.1", prereleases=False) == - ... SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True)) - True - >>> SpecifierSet(">=1.0.0,!=1.0.1") == ">=1.0.0,!=1.0.1" - True - >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0") - False - >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0,!=1.0.2") - False - """ - if isinstance(other, (str, Specifier)): - other = SpecifierSet(str(other)) - elif not isinstance(other, SpecifierSet): - return NotImplemented - - return self._specs == other._specs - - def __len__(self) -> int: - """Returns the number of specifiers in this specifier set.""" - return len(self._specs) - - def __iter__(self) -> Iterator[Specifier]: - """ - Returns an iterator over all the underlying :class:`Specifier` instances - in this specifier set. - - >>> sorted(SpecifierSet(">=1.0.0,!=1.0.1"), key=str) - [, =1.0.0')>] - """ - return iter(self._specs) - - def __contains__(self, item: UnparsedVersion) -> bool: - """Return whether or not the item is contained in this specifier. - - :param item: The item to check for. - - This is used for the ``in`` operator and behaves the same as - :meth:`contains` with no ``prereleases`` argument passed. - - >>> "1.2.3" in SpecifierSet(">=1.0.0,!=1.0.1") - True - >>> Version("1.2.3") in SpecifierSet(">=1.0.0,!=1.0.1") - True - >>> "1.0.1" in SpecifierSet(">=1.0.0,!=1.0.1") - False - >>> "1.3.0a1" in SpecifierSet(">=1.0.0,!=1.0.1") - False - >>> "1.3.0a1" in SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True) - True - """ - return self.contains(item) - - def contains( - self, - item: UnparsedVersion, - prereleases: bool | None = None, - installed: bool | None = None, - ) -> bool: - """Return whether or not the item is contained in this SpecifierSet. - - :param item: - The item to check for, which can be a version string or a - :class:`Version` instance. - :param prereleases: - Whether or not to match prereleases with this SpecifierSet. If set to - ``None`` (the default), it uses :attr:`prereleases` to determine - whether or not prereleases are allowed. - - >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.2.3") - True - >>> SpecifierSet(">=1.0.0,!=1.0.1").contains(Version("1.2.3")) - True - >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.0.1") - False - >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.3.0a1") - False - >>> SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True).contains("1.3.0a1") - True - >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.3.0a1", prereleases=True) - True - """ - # Ensure that our item is a Version instance. - if not isinstance(item, Version): - item = Version(item) - - # Determine if we're forcing a prerelease or not, if we're not forcing - # one for this particular filter call, then we'll use whatever the - # SpecifierSet thinks for whether or not we should support prereleases. - if prereleases is None: - prereleases = self.prereleases - - # We can determine if we're going to allow pre-releases by looking to - # see if any of the underlying items supports them. If none of them do - # and this item is a pre-release then we do not allow it and we can - # short circuit that here. - # Note: This means that 1.0.dev1 would not be contained in something - # like >=1.0.devabc however it would be in >=1.0.debabc,>0.0.dev0 - if not prereleases and item.is_prerelease: - return False - - if installed and item.is_prerelease: - item = Version(item.base_version) - - # We simply dispatch to the underlying specs here to make sure that the - # given version is contained within all of them. - # Note: This use of all() here means that an empty set of specifiers - # will always return True, this is an explicit design decision. - return all(s.contains(item, prereleases=prereleases) for s in self._specs) - - def filter( - self, iterable: Iterable[UnparsedVersionVar], prereleases: bool | None = None - ) -> Iterator[UnparsedVersionVar]: - """Filter items in the given iterable, that match the specifiers in this set. - - :param iterable: - An iterable that can contain version strings and :class:`Version` instances. - The items in the iterable will be filtered according to the specifier. - :param prereleases: - Whether or not to allow prereleases in the returned iterator. If set to - ``None`` (the default), it will be intelligently decide whether to allow - prereleases or not (based on the :attr:`prereleases` attribute, and - whether the only versions matching are prereleases). - - This method is smarter than just ``filter(SpecifierSet(...).contains, [...])`` - because it implements the rule from :pep:`440` that a prerelease item - SHOULD be accepted if no other versions match the given specifier. - - >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.3", "1.5a1"])) - ['1.3'] - >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.3", Version("1.4")])) - ['1.3', ] - >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.5a1"])) - [] - >>> list(SpecifierSet(">=1.2.3").filter(["1.3", "1.5a1"], prereleases=True)) - ['1.3', '1.5a1'] - >>> list(SpecifierSet(">=1.2.3", prereleases=True).filter(["1.3", "1.5a1"])) - ['1.3', '1.5a1'] - - An "empty" SpecifierSet will filter items based on the presence of prerelease - versions in the set. - - >>> list(SpecifierSet("").filter(["1.3", "1.5a1"])) - ['1.3'] - >>> list(SpecifierSet("").filter(["1.5a1"])) - ['1.5a1'] - >>> list(SpecifierSet("", prereleases=True).filter(["1.3", "1.5a1"])) - ['1.3', '1.5a1'] - >>> list(SpecifierSet("").filter(["1.3", "1.5a1"], prereleases=True)) - ['1.3', '1.5a1'] - """ - # Determine if we're forcing a prerelease or not, if we're not forcing - # one for this particular filter call, then we'll use whatever the - # SpecifierSet thinks for whether or not we should support prereleases. - if prereleases is None: - prereleases = self.prereleases - - # If we have any specifiers, then we want to wrap our iterable in the - # filter method for each one, this will act as a logical AND amongst - # each specifier. - if self._specs: - for spec in self._specs: - iterable = spec.filter(iterable, prereleases=bool(prereleases)) - return iter(iterable) - # If we do not have any specifiers, then we need to have a rough filter - # which will filter out any pre-releases, unless there are no final - # releases. - else: - filtered: list[UnparsedVersionVar] = [] - found_prereleases: list[UnparsedVersionVar] = [] - - for item in iterable: - parsed_version = _coerce_version(item) - - # Store any item which is a pre-release for later unless we've - # already found a final version or we are accepting prereleases - if parsed_version.is_prerelease and not prereleases: - if not filtered: - found_prereleases.append(item) - else: - filtered.append(item) - - # If we've found no items except for pre-releases, then we'll go - # ahead and use the pre-releases - if not filtered and found_prereleases and prereleases is None: - return iter(found_prereleases) - - return iter(filtered) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/tags.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/tags.py deleted file mode 100644 index f590340..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/tags.py +++ /dev/null @@ -1,617 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. - -from __future__ import annotations - -import logging -import platform -import re -import struct -import subprocess -import sys -import sysconfig -from importlib.machinery import EXTENSION_SUFFIXES -from typing import ( - Iterable, - Iterator, - Sequence, - Tuple, - cast, -) - -from . import _manylinux, _musllinux - -logger = logging.getLogger(__name__) - -PythonVersion = Sequence[int] -AppleVersion = Tuple[int, int] - -INTERPRETER_SHORT_NAMES: dict[str, str] = { - "python": "py", # Generic. - "cpython": "cp", - "pypy": "pp", - "ironpython": "ip", - "jython": "jy", -} - - -_32_BIT_INTERPRETER = struct.calcsize("P") == 4 - - -class Tag: - """ - A representation of the tag triple for a wheel. - - Instances are considered immutable and thus are hashable. Equality checking - is also supported. - """ - - __slots__ = ["_abi", "_hash", "_interpreter", "_platform"] - - def __init__(self, interpreter: str, abi: str, platform: str) -> None: - self._interpreter = interpreter.lower() - self._abi = abi.lower() - self._platform = platform.lower() - # The __hash__ of every single element in a Set[Tag] will be evaluated each time - # that a set calls its `.disjoint()` method, which may be called hundreds of - # times when scanning a page of links for packages with tags matching that - # Set[Tag]. Pre-computing the value here produces significant speedups for - # downstream consumers. - self._hash = hash((self._interpreter, self._abi, self._platform)) - - @property - def interpreter(self) -> str: - return self._interpreter - - @property - def abi(self) -> str: - return self._abi - - @property - def platform(self) -> str: - return self._platform - - def __eq__(self, other: object) -> bool: - if not isinstance(other, Tag): - return NotImplemented - - return ( - (self._hash == other._hash) # Short-circuit ASAP for perf reasons. - and (self._platform == other._platform) - and (self._abi == other._abi) - and (self._interpreter == other._interpreter) - ) - - def __hash__(self) -> int: - return self._hash - - def __str__(self) -> str: - return f"{self._interpreter}-{self._abi}-{self._platform}" - - def __repr__(self) -> str: - return f"<{self} @ {id(self)}>" - - -def parse_tag(tag: str) -> frozenset[Tag]: - """ - Parses the provided tag (e.g. `py3-none-any`) into a frozenset of Tag instances. - - Returning a set is required due to the possibility that the tag is a - compressed tag set. - """ - tags = set() - interpreters, abis, platforms = tag.split("-") - for interpreter in interpreters.split("."): - for abi in abis.split("."): - for platform_ in platforms.split("."): - tags.add(Tag(interpreter, abi, platform_)) - return frozenset(tags) - - -def _get_config_var(name: str, warn: bool = False) -> int | str | None: - value: int | str | None = sysconfig.get_config_var(name) - if value is None and warn: - logger.debug( - "Config variable '%s' is unset, Python ABI tag may be incorrect", name - ) - return value - - -def _normalize_string(string: str) -> str: - return string.replace(".", "_").replace("-", "_").replace(" ", "_") - - -def _is_threaded_cpython(abis: list[str]) -> bool: - """ - Determine if the ABI corresponds to a threaded (`--disable-gil`) build. - - The threaded builds are indicated by a "t" in the abiflags. - """ - if len(abis) == 0: - return False - # expect e.g., cp313 - m = re.match(r"cp\d+(.*)", abis[0]) - if not m: - return False - abiflags = m.group(1) - return "t" in abiflags - - -def _abi3_applies(python_version: PythonVersion, threading: bool) -> bool: - """ - Determine if the Python version supports abi3. - - PEP 384 was first implemented in Python 3.2. The threaded (`--disable-gil`) - builds do not support abi3. - """ - return len(python_version) > 1 and tuple(python_version) >= (3, 2) and not threading - - -def _cpython_abis(py_version: PythonVersion, warn: bool = False) -> list[str]: - py_version = tuple(py_version) # To allow for version comparison. - abis = [] - version = _version_nodot(py_version[:2]) - threading = debug = pymalloc = ucs4 = "" - with_debug = _get_config_var("Py_DEBUG", warn) - has_refcount = hasattr(sys, "gettotalrefcount") - # Windows doesn't set Py_DEBUG, so checking for support of debug-compiled - # extension modules is the best option. - # https://github.com/pypa/pip/issues/3383#issuecomment-173267692 - has_ext = "_d.pyd" in EXTENSION_SUFFIXES - if with_debug or (with_debug is None and (has_refcount or has_ext)): - debug = "d" - if py_version >= (3, 13) and _get_config_var("Py_GIL_DISABLED", warn): - threading = "t" - if py_version < (3, 8): - with_pymalloc = _get_config_var("WITH_PYMALLOC", warn) - if with_pymalloc or with_pymalloc is None: - pymalloc = "m" - if py_version < (3, 3): - unicode_size = _get_config_var("Py_UNICODE_SIZE", warn) - if unicode_size == 4 or ( - unicode_size is None and sys.maxunicode == 0x10FFFF - ): - ucs4 = "u" - elif debug: - # Debug builds can also load "normal" extension modules. - # We can also assume no UCS-4 or pymalloc requirement. - abis.append(f"cp{version}{threading}") - abis.insert(0, f"cp{version}{threading}{debug}{pymalloc}{ucs4}") - return abis - - -def cpython_tags( - python_version: PythonVersion | None = None, - abis: Iterable[str] | None = None, - platforms: Iterable[str] | None = None, - *, - warn: bool = False, -) -> Iterator[Tag]: - """ - Yields the tags for a CPython interpreter. - - The tags consist of: - - cp-- - - cp-abi3- - - cp-none- - - cp-abi3- # Older Python versions down to 3.2. - - If python_version only specifies a major version then user-provided ABIs and - the 'none' ABItag will be used. - - If 'abi3' or 'none' are specified in 'abis' then they will be yielded at - their normal position and not at the beginning. - """ - if not python_version: - python_version = sys.version_info[:2] - - interpreter = f"cp{_version_nodot(python_version[:2])}" - - if abis is None: - if len(python_version) > 1: - abis = _cpython_abis(python_version, warn) - else: - abis = [] - abis = list(abis) - # 'abi3' and 'none' are explicitly handled later. - for explicit_abi in ("abi3", "none"): - try: - abis.remove(explicit_abi) - except ValueError: - pass - - platforms = list(platforms or platform_tags()) - for abi in abis: - for platform_ in platforms: - yield Tag(interpreter, abi, platform_) - - threading = _is_threaded_cpython(abis) - use_abi3 = _abi3_applies(python_version, threading) - if use_abi3: - yield from (Tag(interpreter, "abi3", platform_) for platform_ in platforms) - yield from (Tag(interpreter, "none", platform_) for platform_ in platforms) - - if use_abi3: - for minor_version in range(python_version[1] - 1, 1, -1): - for platform_ in platforms: - version = _version_nodot((python_version[0], minor_version)) - interpreter = f"cp{version}" - yield Tag(interpreter, "abi3", platform_) - - -def _generic_abi() -> list[str]: - """ - Return the ABI tag based on EXT_SUFFIX. - """ - # The following are examples of `EXT_SUFFIX`. - # We want to keep the parts which are related to the ABI and remove the - # parts which are related to the platform: - # - linux: '.cpython-310-x86_64-linux-gnu.so' => cp310 - # - mac: '.cpython-310-darwin.so' => cp310 - # - win: '.cp310-win_amd64.pyd' => cp310 - # - win: '.pyd' => cp37 (uses _cpython_abis()) - # - pypy: '.pypy38-pp73-x86_64-linux-gnu.so' => pypy38_pp73 - # - graalpy: '.graalpy-38-native-x86_64-darwin.dylib' - # => graalpy_38_native - - ext_suffix = _get_config_var("EXT_SUFFIX", warn=True) - if not isinstance(ext_suffix, str) or ext_suffix[0] != ".": - raise SystemError("invalid sysconfig.get_config_var('EXT_SUFFIX')") - parts = ext_suffix.split(".") - if len(parts) < 3: - # CPython3.7 and earlier uses ".pyd" on Windows. - return _cpython_abis(sys.version_info[:2]) - soabi = parts[1] - if soabi.startswith("cpython"): - # non-windows - abi = "cp" + soabi.split("-")[1] - elif soabi.startswith("cp"): - # windows - abi = soabi.split("-")[0] - elif soabi.startswith("pypy"): - abi = "-".join(soabi.split("-")[:2]) - elif soabi.startswith("graalpy"): - abi = "-".join(soabi.split("-")[:3]) - elif soabi: - # pyston, ironpython, others? - abi = soabi - else: - return [] - return [_normalize_string(abi)] - - -def generic_tags( - interpreter: str | None = None, - abis: Iterable[str] | None = None, - platforms: Iterable[str] | None = None, - *, - warn: bool = False, -) -> Iterator[Tag]: - """ - Yields the tags for a generic interpreter. - - The tags consist of: - - -- - - The "none" ABI will be added if it was not explicitly provided. - """ - if not interpreter: - interp_name = interpreter_name() - interp_version = interpreter_version(warn=warn) - interpreter = "".join([interp_name, interp_version]) - if abis is None: - abis = _generic_abi() - else: - abis = list(abis) - platforms = list(platforms or platform_tags()) - if "none" not in abis: - abis.append("none") - for abi in abis: - for platform_ in platforms: - yield Tag(interpreter, abi, platform_) - - -def _py_interpreter_range(py_version: PythonVersion) -> Iterator[str]: - """ - Yields Python versions in descending order. - - After the latest version, the major-only version will be yielded, and then - all previous versions of that major version. - """ - if len(py_version) > 1: - yield f"py{_version_nodot(py_version[:2])}" - yield f"py{py_version[0]}" - if len(py_version) > 1: - for minor in range(py_version[1] - 1, -1, -1): - yield f"py{_version_nodot((py_version[0], minor))}" - - -def compatible_tags( - python_version: PythonVersion | None = None, - interpreter: str | None = None, - platforms: Iterable[str] | None = None, -) -> Iterator[Tag]: - """ - Yields the sequence of tags that are compatible with a specific version of Python. - - The tags consist of: - - py*-none- - - -none-any # ... if `interpreter` is provided. - - py*-none-any - """ - if not python_version: - python_version = sys.version_info[:2] - platforms = list(platforms or platform_tags()) - for version in _py_interpreter_range(python_version): - for platform_ in platforms: - yield Tag(version, "none", platform_) - if interpreter: - yield Tag(interpreter, "none", "any") - for version in _py_interpreter_range(python_version): - yield Tag(version, "none", "any") - - -def _mac_arch(arch: str, is_32bit: bool = _32_BIT_INTERPRETER) -> str: - if not is_32bit: - return arch - - if arch.startswith("ppc"): - return "ppc" - - return "i386" - - -def _mac_binary_formats(version: AppleVersion, cpu_arch: str) -> list[str]: - formats = [cpu_arch] - if cpu_arch == "x86_64": - if version < (10, 4): - return [] - formats.extend(["intel", "fat64", "fat32"]) - - elif cpu_arch == "i386": - if version < (10, 4): - return [] - formats.extend(["intel", "fat32", "fat"]) - - elif cpu_arch == "ppc64": - # TODO: Need to care about 32-bit PPC for ppc64 through 10.2? - if version > (10, 5) or version < (10, 4): - return [] - formats.append("fat64") - - elif cpu_arch == "ppc": - if version > (10, 6): - return [] - formats.extend(["fat32", "fat"]) - - if cpu_arch in {"arm64", "x86_64"}: - formats.append("universal2") - - if cpu_arch in {"x86_64", "i386", "ppc64", "ppc", "intel"}: - formats.append("universal") - - return formats - - -def mac_platforms( - version: AppleVersion | None = None, arch: str | None = None -) -> Iterator[str]: - """ - Yields the platform tags for a macOS system. - - The `version` parameter is a two-item tuple specifying the macOS version to - generate platform tags for. The `arch` parameter is the CPU architecture to - generate platform tags for. Both parameters default to the appropriate value - for the current system. - """ - version_str, _, cpu_arch = platform.mac_ver() - if version is None: - version = cast("AppleVersion", tuple(map(int, version_str.split(".")[:2]))) - if version == (10, 16): - # When built against an older macOS SDK, Python will report macOS 10.16 - # instead of the real version. - version_str = subprocess.run( - [ - sys.executable, - "-sS", - "-c", - "import platform; print(platform.mac_ver()[0])", - ], - check=True, - env={"SYSTEM_VERSION_COMPAT": "0"}, - stdout=subprocess.PIPE, - text=True, - ).stdout - version = cast("AppleVersion", tuple(map(int, version_str.split(".")[:2]))) - else: - version = version - if arch is None: - arch = _mac_arch(cpu_arch) - else: - arch = arch - - if (10, 0) <= version and version < (11, 0): - # Prior to Mac OS 11, each yearly release of Mac OS bumped the - # "minor" version number. The major version was always 10. - major_version = 10 - for minor_version in range(version[1], -1, -1): - compat_version = major_version, minor_version - binary_formats = _mac_binary_formats(compat_version, arch) - for binary_format in binary_formats: - yield f"macosx_{major_version}_{minor_version}_{binary_format}" - - if version >= (11, 0): - # Starting with Mac OS 11, each yearly release bumps the major version - # number. The minor versions are now the midyear updates. - minor_version = 0 - for major_version in range(version[0], 10, -1): - compat_version = major_version, minor_version - binary_formats = _mac_binary_formats(compat_version, arch) - for binary_format in binary_formats: - yield f"macosx_{major_version}_{minor_version}_{binary_format}" - - if version >= (11, 0): - # Mac OS 11 on x86_64 is compatible with binaries from previous releases. - # Arm64 support was introduced in 11.0, so no Arm binaries from previous - # releases exist. - # - # However, the "universal2" binary format can have a - # macOS version earlier than 11.0 when the x86_64 part of the binary supports - # that version of macOS. - major_version = 10 - if arch == "x86_64": - for minor_version in range(16, 3, -1): - compat_version = major_version, minor_version - binary_formats = _mac_binary_formats(compat_version, arch) - for binary_format in binary_formats: - yield f"macosx_{major_version}_{minor_version}_{binary_format}" - else: - for minor_version in range(16, 3, -1): - compat_version = major_version, minor_version - binary_format = "universal2" - yield f"macosx_{major_version}_{minor_version}_{binary_format}" - - -def ios_platforms( - version: AppleVersion | None = None, multiarch: str | None = None -) -> Iterator[str]: - """ - Yields the platform tags for an iOS system. - - :param version: A two-item tuple specifying the iOS version to generate - platform tags for. Defaults to the current iOS version. - :param multiarch: The CPU architecture+ABI to generate platform tags for - - (the value used by `sys.implementation._multiarch` e.g., - `arm64_iphoneos` or `x84_64_iphonesimulator`). Defaults to the current - multiarch value. - """ - if version is None: - # if iOS is the current platform, ios_ver *must* be defined. However, - # it won't exist for CPython versions before 3.13, which causes a mypy - # error. - _, release, _, _ = platform.ios_ver() # type: ignore[attr-defined, unused-ignore] - version = cast("AppleVersion", tuple(map(int, release.split(".")[:2]))) - - if multiarch is None: - multiarch = sys.implementation._multiarch - multiarch = multiarch.replace("-", "_") - - ios_platform_template = "ios_{major}_{minor}_{multiarch}" - - # Consider any iOS major.minor version from the version requested, down to - # 12.0. 12.0 is the first iOS version that is known to have enough features - # to support CPython. Consider every possible minor release up to X.9. There - # highest the minor has ever gone is 8 (14.8 and 15.8) but having some extra - # candidates that won't ever match doesn't really hurt, and it saves us from - # having to keep an explicit list of known iOS versions in the code. Return - # the results descending order of version number. - - # If the requested major version is less than 12, there won't be any matches. - if version[0] < 12: - return - - # Consider the actual X.Y version that was requested. - yield ios_platform_template.format( - major=version[0], minor=version[1], multiarch=multiarch - ) - - # Consider every minor version from X.0 to the minor version prior to the - # version requested by the platform. - for minor in range(version[1] - 1, -1, -1): - yield ios_platform_template.format( - major=version[0], minor=minor, multiarch=multiarch - ) - - for major in range(version[0] - 1, 11, -1): - for minor in range(9, -1, -1): - yield ios_platform_template.format( - major=major, minor=minor, multiarch=multiarch - ) - - -def _linux_platforms(is_32bit: bool = _32_BIT_INTERPRETER) -> Iterator[str]: - linux = _normalize_string(sysconfig.get_platform()) - if not linux.startswith("linux_"): - # we should never be here, just yield the sysconfig one and return - yield linux - return - if is_32bit: - if linux == "linux_x86_64": - linux = "linux_i686" - elif linux == "linux_aarch64": - linux = "linux_armv8l" - _, arch = linux.split("_", 1) - archs = {"armv8l": ["armv8l", "armv7l"]}.get(arch, [arch]) - yield from _manylinux.platform_tags(archs) - yield from _musllinux.platform_tags(archs) - for arch in archs: - yield f"linux_{arch}" - - -def _generic_platforms() -> Iterator[str]: - yield _normalize_string(sysconfig.get_platform()) - - -def platform_tags() -> Iterator[str]: - """ - Provides the platform tags for this installation. - """ - if platform.system() == "Darwin": - return mac_platforms() - elif platform.system() == "iOS": - return ios_platforms() - elif platform.system() == "Linux": - return _linux_platforms() - else: - return _generic_platforms() - - -def interpreter_name() -> str: - """ - Returns the name of the running interpreter. - - Some implementations have a reserved, two-letter abbreviation which will - be returned when appropriate. - """ - name = sys.implementation.name - return INTERPRETER_SHORT_NAMES.get(name) or name - - -def interpreter_version(*, warn: bool = False) -> str: - """ - Returns the version of the running interpreter. - """ - version = _get_config_var("py_version_nodot", warn=warn) - if version: - version = str(version) - else: - version = _version_nodot(sys.version_info[:2]) - return version - - -def _version_nodot(version: PythonVersion) -> str: - return "".join(map(str, version)) - - -def sys_tags(*, warn: bool = False) -> Iterator[Tag]: - """ - Returns the sequence of tag triples for the running interpreter. - - The order of the sequence corresponds to priority order for the - interpreter, from most to least important. - """ - - interp_name = interpreter_name() - if interp_name == "cp": - yield from cpython_tags(warn=warn) - else: - yield from generic_tags() - - if interp_name == "pp": - interp = "pp3" - elif interp_name == "cp": - interp = "cp" + interpreter_version(warn=warn) - else: - interp = None - yield from compatible_tags(interpreter=interp) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/utils.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/utils.py deleted file mode 100644 index 2345095..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/utils.py +++ /dev/null @@ -1,163 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. - -from __future__ import annotations - -import functools -import re -from typing import NewType, Tuple, Union, cast - -from .tags import Tag, parse_tag -from .version import InvalidVersion, Version, _TrimmedRelease - -BuildTag = Union[Tuple[()], Tuple[int, str]] -NormalizedName = NewType("NormalizedName", str) - - -class InvalidName(ValueError): - """ - An invalid distribution name; users should refer to the packaging user guide. - """ - - -class InvalidWheelFilename(ValueError): - """ - An invalid wheel filename was found, users should refer to PEP 427. - """ - - -class InvalidSdistFilename(ValueError): - """ - An invalid sdist filename was found, users should refer to the packaging user guide. - """ - - -# Core metadata spec for `Name` -_validate_regex = re.compile( - r"^([A-Z0-9]|[A-Z0-9][A-Z0-9._-]*[A-Z0-9])$", re.IGNORECASE -) -_canonicalize_regex = re.compile(r"[-_.]+") -_normalized_regex = re.compile(r"^([a-z0-9]|[a-z0-9]([a-z0-9-](?!--))*[a-z0-9])$") -# PEP 427: The build number must start with a digit. -_build_tag_regex = re.compile(r"(\d+)(.*)") - - -def canonicalize_name(name: str, *, validate: bool = False) -> NormalizedName: - if validate and not _validate_regex.match(name): - raise InvalidName(f"name is invalid: {name!r}") - # This is taken from PEP 503. - value = _canonicalize_regex.sub("-", name).lower() - return cast(NormalizedName, value) - - -def is_normalized_name(name: str) -> bool: - return _normalized_regex.match(name) is not None - - -@functools.singledispatch -def canonicalize_version( - version: Version | str, *, strip_trailing_zero: bool = True -) -> str: - """ - Return a canonical form of a version as a string. - - >>> canonicalize_version('1.0.1') - '1.0.1' - - Per PEP 625, versions may have multiple canonical forms, differing - only by trailing zeros. - - >>> canonicalize_version('1.0.0') - '1' - >>> canonicalize_version('1.0.0', strip_trailing_zero=False) - '1.0.0' - - Invalid versions are returned unaltered. - - >>> canonicalize_version('foo bar baz') - 'foo bar baz' - """ - return str(_TrimmedRelease(str(version)) if strip_trailing_zero else version) - - -@canonicalize_version.register -def _(version: str, *, strip_trailing_zero: bool = True) -> str: - try: - parsed = Version(version) - except InvalidVersion: - # Legacy versions cannot be normalized - return version - return canonicalize_version(parsed, strip_trailing_zero=strip_trailing_zero) - - -def parse_wheel_filename( - filename: str, -) -> tuple[NormalizedName, Version, BuildTag, frozenset[Tag]]: - if not filename.endswith(".whl"): - raise InvalidWheelFilename( - f"Invalid wheel filename (extension must be '.whl'): {filename!r}" - ) - - filename = filename[:-4] - dashes = filename.count("-") - if dashes not in (4, 5): - raise InvalidWheelFilename( - f"Invalid wheel filename (wrong number of parts): {filename!r}" - ) - - parts = filename.split("-", dashes - 2) - name_part = parts[0] - # See PEP 427 for the rules on escaping the project name. - if "__" in name_part or re.match(r"^[\w\d._]*$", name_part, re.UNICODE) is None: - raise InvalidWheelFilename(f"Invalid project name: {filename!r}") - name = canonicalize_name(name_part) - - try: - version = Version(parts[1]) - except InvalidVersion as e: - raise InvalidWheelFilename( - f"Invalid wheel filename (invalid version): {filename!r}" - ) from e - - if dashes == 5: - build_part = parts[2] - build_match = _build_tag_regex.match(build_part) - if build_match is None: - raise InvalidWheelFilename( - f"Invalid build number: {build_part} in {filename!r}" - ) - build = cast(BuildTag, (int(build_match.group(1)), build_match.group(2))) - else: - build = () - tags = parse_tag(parts[-1]) - return (name, version, build, tags) - - -def parse_sdist_filename(filename: str) -> tuple[NormalizedName, Version]: - if filename.endswith(".tar.gz"): - file_stem = filename[: -len(".tar.gz")] - elif filename.endswith(".zip"): - file_stem = filename[: -len(".zip")] - else: - raise InvalidSdistFilename( - f"Invalid sdist filename (extension must be '.tar.gz' or '.zip'):" - f" {filename!r}" - ) - - # We are requiring a PEP 440 version, which cannot contain dashes, - # so we split on the last dash. - name_part, sep, version_part = file_stem.rpartition("-") - if not sep: - raise InvalidSdistFilename(f"Invalid sdist filename: {filename!r}") - - name = canonicalize_name(name_part) - - try: - version = Version(version_part) - except InvalidVersion as e: - raise InvalidSdistFilename( - f"Invalid sdist filename (invalid version): {filename!r}" - ) from e - - return (name, version) diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/version.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/version.py deleted file mode 100644 index c9bbda2..0000000 --- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/packaging/version.py +++ /dev/null @@ -1,582 +0,0 @@ -# This file is dual licensed under the terms of the Apache License, Version -# 2.0, and the BSD License. See the LICENSE file in the root of this repository -# for complete details. -""" -.. testsetup:: - - from packaging.version import parse, Version -""" - -from __future__ import annotations - -import itertools -import re -from typing import Any, Callable, NamedTuple, SupportsInt, Tuple, Union - -from ._structures import Infinity, InfinityType, NegativeInfinity, NegativeInfinityType - -__all__ = ["VERSION_PATTERN", "InvalidVersion", "Version", "parse"] - -LocalType = Tuple[Union[int, str], ...] - -CmpPrePostDevType = Union[InfinityType, NegativeInfinityType, Tuple[str, int]] -CmpLocalType = Union[ - NegativeInfinityType, - Tuple[Union[Tuple[int, str], Tuple[NegativeInfinityType, Union[int, str]]], ...], -] -CmpKey = Tuple[ - int, - Tuple[int, ...], - CmpPrePostDevType, - CmpPrePostDevType, - CmpPrePostDevType, - CmpLocalType, -] -VersionComparisonMethod = Callable[[CmpKey, CmpKey], bool] - - -class _Version(NamedTuple): - epoch: int - release: tuple[int, ...] - dev: tuple[str, int] | None - pre: tuple[str, int] | None - post: tuple[str, int] | None - local: LocalType | None - - -def parse(version: str) -> Version: - """Parse the given version string. - - >>> parse('1.0.dev1') - - - :param version: The version string to parse. - :raises InvalidVersion: When the version string is not a valid version. - """ - return Version(version) - - -class InvalidVersion(ValueError): - """Raised when a version string is not a valid version. - - >>> Version("invalid") - Traceback (most recent call last): - ... - packaging.version.InvalidVersion: Invalid version: 'invalid' - """ - - -class _BaseVersion: - _key: tuple[Any, ...] - - def __hash__(self) -> int: - return hash(self._key) - - # Please keep the duplicated `isinstance` check - # in the six comparisons hereunder - # unless you find a way to avoid adding overhead function calls. - def __lt__(self, other: _BaseVersion) -> bool: - if not isinstance(other, _BaseVersion): - return NotImplemented - - return self._key < other._key - - def __le__(self, other: _BaseVersion) -> bool: - if not isinstance(other, _BaseVersion): - return NotImplemented - - return self._key <= other._key - - def __eq__(self, other: object) -> bool: - if not isinstance(other, _BaseVersion): - return NotImplemented - - return self._key == other._key - - def __ge__(self, other: _BaseVersion) -> bool: - if not isinstance(other, _BaseVersion): - return NotImplemented - - return self._key >= other._key - - def __gt__(self, other: _BaseVersion) -> bool: - if not isinstance(other, _BaseVersion): - return NotImplemented - - return self._key > other._key - - def __ne__(self, other: object) -> bool: - if not isinstance(other, _BaseVersion): - return NotImplemented - - return self._key != other._key - - -# Deliberately not anchored to the start and end of the string, to make it -# easier for 3rd party code to reuse -_VERSION_PATTERN = r""" - v? - (?: - (?:(?P[0-9]+)!)? # epoch - (?P[0-9]+(?:\.[0-9]+)*) # release segment - (?P
                                          # pre-release
-            [-_\.]?
-            (?Palpha|a|beta|b|preview|pre|c|rc)
-            [-_\.]?
-            (?P[0-9]+)?
-        )?
-        (?P                                         # post release
-            (?:-(?P[0-9]+))
-            |
-            (?:
-                [-_\.]?
-                (?Ppost|rev|r)
-                [-_\.]?
-                (?P[0-9]+)?
-            )
-        )?
-        (?P                                          # dev release
-            [-_\.]?
-            (?Pdev)
-            [-_\.]?
-            (?P[0-9]+)?
-        )?
-    )
-    (?:\+(?P[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
-"""
-
-VERSION_PATTERN = _VERSION_PATTERN
-"""
-A string containing the regular expression used to match a valid version.
-
-The pattern is not anchored at either end, and is intended for embedding in larger
-expressions (for example, matching a version number as part of a file name). The
-regular expression should be compiled with the ``re.VERBOSE`` and ``re.IGNORECASE``
-flags set.
-
-:meta hide-value:
-"""
-
-
-class Version(_BaseVersion):
-    """This class abstracts handling of a project's versions.
-
-    A :class:`Version` instance is comparison aware and can be compared and
-    sorted using the standard Python interfaces.
-
-    >>> v1 = Version("1.0a5")
-    >>> v2 = Version("1.0")
-    >>> v1
-    
-    >>> v2
-    
-    >>> v1 < v2
-    True
-    >>> v1 == v2
-    False
-    >>> v1 > v2
-    False
-    >>> v1 >= v2
-    False
-    >>> v1 <= v2
-    True
-    """
-
-    _regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE)
-    _key: CmpKey
-
-    def __init__(self, version: str) -> None:
-        """Initialize a Version object.
-
-        :param version:
-            The string representation of a version which will be parsed and normalized
-            before use.
-        :raises InvalidVersion:
-            If the ``version`` does not conform to PEP 440 in any way then this
-            exception will be raised.
-        """
-
-        # Validate the version and parse it into pieces
-        match = self._regex.search(version)
-        if not match:
-            raise InvalidVersion(f"Invalid version: {version!r}")
-
-        # Store the parsed out pieces of the version
-        self._version = _Version(
-            epoch=int(match.group("epoch")) if match.group("epoch") else 0,
-            release=tuple(int(i) for i in match.group("release").split(".")),
-            pre=_parse_letter_version(match.group("pre_l"), match.group("pre_n")),
-            post=_parse_letter_version(
-                match.group("post_l"), match.group("post_n1") or match.group("post_n2")
-            ),
-            dev=_parse_letter_version(match.group("dev_l"), match.group("dev_n")),
-            local=_parse_local_version(match.group("local")),
-        )
-
-        # Generate a key which will be used for sorting
-        self._key = _cmpkey(
-            self._version.epoch,
-            self._version.release,
-            self._version.pre,
-            self._version.post,
-            self._version.dev,
-            self._version.local,
-        )
-
-    def __repr__(self) -> str:
-        """A representation of the Version that shows all internal state.
-
-        >>> Version('1.0.0')
-        
-        """
-        return f""
-
-    def __str__(self) -> str:
-        """A string representation of the version that can be round-tripped.
-
-        >>> str(Version("1.0a5"))
-        '1.0a5'
-        """
-        parts = []
-
-        # Epoch
-        if self.epoch != 0:
-            parts.append(f"{self.epoch}!")
-
-        # Release segment
-        parts.append(".".join(str(x) for x in self.release))
-
-        # Pre-release
-        if self.pre is not None:
-            parts.append("".join(str(x) for x in self.pre))
-
-        # Post-release
-        if self.post is not None:
-            parts.append(f".post{self.post}")
-
-        # Development release
-        if self.dev is not None:
-            parts.append(f".dev{self.dev}")
-
-        # Local version segment
-        if self.local is not None:
-            parts.append(f"+{self.local}")
-
-        return "".join(parts)
-
-    @property
-    def epoch(self) -> int:
-        """The epoch of the version.
-
-        >>> Version("2.0.0").epoch
-        0
-        >>> Version("1!2.0.0").epoch
-        1
-        """
-        return self._version.epoch
-
-    @property
-    def release(self) -> tuple[int, ...]:
-        """The components of the "release" segment of the version.
-
-        >>> Version("1.2.3").release
-        (1, 2, 3)
-        >>> Version("2.0.0").release
-        (2, 0, 0)
-        >>> Version("1!2.0.0.post0").release
-        (2, 0, 0)
-
-        Includes trailing zeroes but not the epoch or any pre-release / development /
-        post-release suffixes.
-        """
-        return self._version.release
-
-    @property
-    def pre(self) -> tuple[str, int] | None:
-        """The pre-release segment of the version.
-
-        >>> print(Version("1.2.3").pre)
-        None
-        >>> Version("1.2.3a1").pre
-        ('a', 1)
-        >>> Version("1.2.3b1").pre
-        ('b', 1)
-        >>> Version("1.2.3rc1").pre
-        ('rc', 1)
-        """
-        return self._version.pre
-
-    @property
-    def post(self) -> int | None:
-        """The post-release number of the version.
-
-        >>> print(Version("1.2.3").post)
-        None
-        >>> Version("1.2.3.post1").post
-        1
-        """
-        return self._version.post[1] if self._version.post else None
-
-    @property
-    def dev(self) -> int | None:
-        """The development number of the version.
-
-        >>> print(Version("1.2.3").dev)
-        None
-        >>> Version("1.2.3.dev1").dev
-        1
-        """
-        return self._version.dev[1] if self._version.dev else None
-
-    @property
-    def local(self) -> str | None:
-        """The local version segment of the version.
-
-        >>> print(Version("1.2.3").local)
-        None
-        >>> Version("1.2.3+abc").local
-        'abc'
-        """
-        if self._version.local:
-            return ".".join(str(x) for x in self._version.local)
-        else:
-            return None
-
-    @property
-    def public(self) -> str:
-        """The public portion of the version.
-
-        >>> Version("1.2.3").public
-        '1.2.3'
-        >>> Version("1.2.3+abc").public
-        '1.2.3'
-        >>> Version("1!1.2.3dev1+abc").public
-        '1!1.2.3.dev1'
-        """
-        return str(self).split("+", 1)[0]
-
-    @property
-    def base_version(self) -> str:
-        """The "base version" of the version.
-
-        >>> Version("1.2.3").base_version
-        '1.2.3'
-        >>> Version("1.2.3+abc").base_version
-        '1.2.3'
-        >>> Version("1!1.2.3dev1+abc").base_version
-        '1!1.2.3'
-
-        The "base version" is the public version of the project without any pre or post
-        release markers.
-        """
-        parts = []
-
-        # Epoch
-        if self.epoch != 0:
-            parts.append(f"{self.epoch}!")
-
-        # Release segment
-        parts.append(".".join(str(x) for x in self.release))
-
-        return "".join(parts)
-
-    @property
-    def is_prerelease(self) -> bool:
-        """Whether this version is a pre-release.
-
-        >>> Version("1.2.3").is_prerelease
-        False
-        >>> Version("1.2.3a1").is_prerelease
-        True
-        >>> Version("1.2.3b1").is_prerelease
-        True
-        >>> Version("1.2.3rc1").is_prerelease
-        True
-        >>> Version("1.2.3dev1").is_prerelease
-        True
-        """
-        return self.dev is not None or self.pre is not None
-
-    @property
-    def is_postrelease(self) -> bool:
-        """Whether this version is a post-release.
-
-        >>> Version("1.2.3").is_postrelease
-        False
-        >>> Version("1.2.3.post1").is_postrelease
-        True
-        """
-        return self.post is not None
-
-    @property
-    def is_devrelease(self) -> bool:
-        """Whether this version is a development release.
-
-        >>> Version("1.2.3").is_devrelease
-        False
-        >>> Version("1.2.3.dev1").is_devrelease
-        True
-        """
-        return self.dev is not None
-
-    @property
-    def major(self) -> int:
-        """The first item of :attr:`release` or ``0`` if unavailable.
-
-        >>> Version("1.2.3").major
-        1
-        """
-        return self.release[0] if len(self.release) >= 1 else 0
-
-    @property
-    def minor(self) -> int:
-        """The second item of :attr:`release` or ``0`` if unavailable.
-
-        >>> Version("1.2.3").minor
-        2
-        >>> Version("1").minor
-        0
-        """
-        return self.release[1] if len(self.release) >= 2 else 0
-
-    @property
-    def micro(self) -> int:
-        """The third item of :attr:`release` or ``0`` if unavailable.
-
-        >>> Version("1.2.3").micro
-        3
-        >>> Version("1").micro
-        0
-        """
-        return self.release[2] if len(self.release) >= 3 else 0
-
-
-class _TrimmedRelease(Version):
-    @property
-    def release(self) -> tuple[int, ...]:
-        """
-        Release segment without any trailing zeros.
-
-        >>> _TrimmedRelease('1.0.0').release
-        (1,)
-        >>> _TrimmedRelease('0.0').release
-        (0,)
-        """
-        rel = super().release
-        nonzeros = (index for index, val in enumerate(rel) if val)
-        last_nonzero = max(nonzeros, default=0)
-        return rel[: last_nonzero + 1]
-
-
-def _parse_letter_version(
-    letter: str | None, number: str | bytes | SupportsInt | None
-) -> tuple[str, int] | None:
-    if letter:
-        # We consider there to be an implicit 0 in a pre-release if there is
-        # not a numeral associated with it.
-        if number is None:
-            number = 0
-
-        # We normalize any letters to their lower case form
-        letter = letter.lower()
-
-        # We consider some words to be alternate spellings of other words and
-        # in those cases we want to normalize the spellings to our preferred
-        # spelling.
-        if letter == "alpha":
-            letter = "a"
-        elif letter == "beta":
-            letter = "b"
-        elif letter in ["c", "pre", "preview"]:
-            letter = "rc"
-        elif letter in ["rev", "r"]:
-            letter = "post"
-
-        return letter, int(number)
-
-    assert not letter
-    if number:
-        # We assume if we are given a number, but we are not given a letter
-        # then this is using the implicit post release syntax (e.g. 1.0-1)
-        letter = "post"
-
-        return letter, int(number)
-
-    return None
-
-
-_local_version_separators = re.compile(r"[\._-]")
-
-
-def _parse_local_version(local: str | None) -> LocalType | None:
-    """
-    Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
-    """
-    if local is not None:
-        return tuple(
-            part.lower() if not part.isdigit() else int(part)
-            for part in _local_version_separators.split(local)
-        )
-    return None
-
-
-def _cmpkey(
-    epoch: int,
-    release: tuple[int, ...],
-    pre: tuple[str, int] | None,
-    post: tuple[str, int] | None,
-    dev: tuple[str, int] | None,
-    local: LocalType | None,
-) -> CmpKey:
-    # When we compare a release version, we want to compare it with all of the
-    # trailing zeros removed. So we'll use a reverse the list, drop all the now
-    # leading zeros until we come to something non zero, then take the rest
-    # re-reverse it back into the correct order and make it a tuple and use
-    # that for our sorting key.
-    _release = tuple(
-        reversed(list(itertools.dropwhile(lambda x: x == 0, reversed(release))))
-    )
-
-    # We need to "trick" the sorting algorithm to put 1.0.dev0 before 1.0a0.
-    # We'll do this by abusing the pre segment, but we _only_ want to do this
-    # if there is not a pre or a post segment. If we have one of those then
-    # the normal sorting rules will handle this case correctly.
-    if pre is None and post is None and dev is not None:
-        _pre: CmpPrePostDevType = NegativeInfinity
-    # Versions without a pre-release (except as noted above) should sort after
-    # those with one.
-    elif pre is None:
-        _pre = Infinity
-    else:
-        _pre = pre
-
-    # Versions without a post segment should sort before those with one.
-    if post is None:
-        _post: CmpPrePostDevType = NegativeInfinity
-
-    else:
-        _post = post
-
-    # Versions without a development segment should sort after those with one.
-    if dev is None:
-        _dev: CmpPrePostDevType = Infinity
-
-    else:
-        _dev = dev
-
-    if local is None:
-        # Versions without a local segment should sort before those with one.
-        _local: CmpLocalType = NegativeInfinity
-    else:
-        # Versions with a local segment need that segment parsed to implement
-        # the sorting rules in PEP440.
-        # - Alpha numeric segments sort before numeric segments
-        # - Alpha numeric segments sort lexicographically
-        # - Numeric segments sort numerically
-        # - Shorter versions sort before longer versions when the prefixes
-        #   match exactly
-        _local = tuple(
-            (i, "") if isinstance(i, int) else (NegativeInfinity, i) for i in local
-        )
-
-    return epoch, _release, _pre, _post, _dev, _local
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/METADATA
deleted file mode 100644
index ab51ef3..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/METADATA
+++ /dev/null
@@ -1,319 +0,0 @@
-Metadata-Version: 2.3
-Name: platformdirs
-Version: 4.2.2
-Summary: A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`.
-Project-URL: Documentation, https://platformdirs.readthedocs.io
-Project-URL: Homepage, https://github.com/platformdirs/platformdirs
-Project-URL: Source, https://github.com/platformdirs/platformdirs
-Project-URL: Tracker, https://github.com/platformdirs/platformdirs/issues
-Maintainer-email: Bernát Gábor , Julian Berman , Ofek Lev , Ronny Pfannschmidt 
-License-Expression: MIT
-License-File: LICENSE
-Keywords: appdirs,application,cache,directory,log,user
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: Implementation :: CPython
-Classifier: Programming Language :: Python :: Implementation :: PyPy
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.8
-Provides-Extra: docs
-Requires-Dist: furo>=2023.9.10; extra == 'docs'
-Requires-Dist: proselint>=0.13; extra == 'docs'
-Requires-Dist: sphinx-autodoc-typehints>=1.25.2; extra == 'docs'
-Requires-Dist: sphinx>=7.2.6; extra == 'docs'
-Provides-Extra: test
-Requires-Dist: appdirs==1.4.4; extra == 'test'
-Requires-Dist: covdefaults>=2.3; extra == 'test'
-Requires-Dist: pytest-cov>=4.1; extra == 'test'
-Requires-Dist: pytest-mock>=3.12; extra == 'test'
-Requires-Dist: pytest>=7.4.3; extra == 'test'
-Provides-Extra: type
-Requires-Dist: mypy>=1.8; extra == 'type'
-Description-Content-Type: text/x-rst
-
-The problem
-===========
-
-.. image:: https://github.com/platformdirs/platformdirs/actions/workflows/check.yml/badge.svg
-   :target: https://github.com/platformdirs/platformdirs/actions
-
-When writing desktop application, finding the right location to store user data
-and configuration varies per platform. Even for single-platform apps, there
-may by plenty of nuances in figuring out the right location.
-
-For example, if running on macOS, you should use::
-
-    ~/Library/Application Support/
-
-If on Windows (at least English Win) that should be::
-
-    C:\Documents and Settings\\Application Data\Local Settings\\
-
-or possibly::
-
-    C:\Documents and Settings\\Application Data\\
-
-for `roaming profiles `_ but that is another story.
-
-On Linux (and other Unices), according to the `XDG Basedir Spec`_, it should be::
-
-    ~/.local/share/
-
-.. _XDG Basedir Spec: https://specifications.freedesktop.org/basedir-spec/basedir-spec-latest.html
-
-``platformdirs`` to the rescue
-==============================
-
-This kind of thing is what the ``platformdirs`` package is for.
-``platformdirs`` will help you choose an appropriate:
-
-- user data dir (``user_data_dir``)
-- user config dir (``user_config_dir``)
-- user cache dir (``user_cache_dir``)
-- site data dir (``site_data_dir``)
-- site config dir (``site_config_dir``)
-- user log dir (``user_log_dir``)
-- user documents dir (``user_documents_dir``)
-- user downloads dir (``user_downloads_dir``)
-- user pictures dir (``user_pictures_dir``)
-- user videos dir (``user_videos_dir``)
-- user music dir (``user_music_dir``)
-- user desktop dir (``user_desktop_dir``)
-- user runtime dir (``user_runtime_dir``)
-
-And also:
-
-- Is slightly opinionated on the directory names used. Look for "OPINION" in
-  documentation and code for when an opinion is being applied.
-
-Example output
-==============
-
-On macOS:
-
-.. code-block:: pycon
-
-    >>> from platformdirs import *
-    >>> appname = "SuperApp"
-    >>> appauthor = "Acme"
-    >>> user_data_dir(appname, appauthor)
-    '/Users/trentm/Library/Application Support/SuperApp'
-    >>> site_data_dir(appname, appauthor)
-    '/Library/Application Support/SuperApp'
-    >>> user_cache_dir(appname, appauthor)
-    '/Users/trentm/Library/Caches/SuperApp'
-    >>> user_log_dir(appname, appauthor)
-    '/Users/trentm/Library/Logs/SuperApp'
-    >>> user_documents_dir()
-    '/Users/trentm/Documents'
-    >>> user_downloads_dir()
-    '/Users/trentm/Downloads'
-    >>> user_pictures_dir()
-    '/Users/trentm/Pictures'
-    >>> user_videos_dir()
-    '/Users/trentm/Movies'
-    >>> user_music_dir()
-    '/Users/trentm/Music'
-    >>> user_desktop_dir()
-    '/Users/trentm/Desktop'
-    >>> user_runtime_dir(appname, appauthor)
-    '/Users/trentm/Library/Caches/TemporaryItems/SuperApp'
-
-On Windows:
-
-.. code-block:: pycon
-
-    >>> from platformdirs import *
-    >>> appname = "SuperApp"
-    >>> appauthor = "Acme"
-    >>> user_data_dir(appname, appauthor)
-    'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp'
-    >>> user_data_dir(appname, appauthor, roaming=True)
-    'C:\\Users\\trentm\\AppData\\Roaming\\Acme\\SuperApp'
-    >>> user_cache_dir(appname, appauthor)
-    'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Cache'
-    >>> user_log_dir(appname, appauthor)
-    'C:\\Users\\trentm\\AppData\\Local\\Acme\\SuperApp\\Logs'
-    >>> user_documents_dir()
-    'C:\\Users\\trentm\\Documents'
-    >>> user_downloads_dir()
-    'C:\\Users\\trentm\\Downloads'
-    >>> user_pictures_dir()
-    'C:\\Users\\trentm\\Pictures'
-    >>> user_videos_dir()
-    'C:\\Users\\trentm\\Videos'
-    >>> user_music_dir()
-    'C:\\Users\\trentm\\Music'
-    >>> user_desktop_dir()
-    'C:\\Users\\trentm\\Desktop'
-    >>> user_runtime_dir(appname, appauthor)
-    'C:\\Users\\trentm\\AppData\\Local\\Temp\\Acme\\SuperApp'
-
-On Linux:
-
-.. code-block:: pycon
-
-    >>> from platformdirs import *
-    >>> appname = "SuperApp"
-    >>> appauthor = "Acme"
-    >>> user_data_dir(appname, appauthor)
-    '/home/trentm/.local/share/SuperApp'
-    >>> site_data_dir(appname, appauthor)
-    '/usr/local/share/SuperApp'
-    >>> site_data_dir(appname, appauthor, multipath=True)
-    '/usr/local/share/SuperApp:/usr/share/SuperApp'
-    >>> user_cache_dir(appname, appauthor)
-    '/home/trentm/.cache/SuperApp'
-    >>> user_log_dir(appname, appauthor)
-    '/home/trentm/.local/state/SuperApp/log'
-    >>> user_config_dir(appname)
-    '/home/trentm/.config/SuperApp'
-    >>> user_documents_dir()
-    '/home/trentm/Documents'
-    >>> user_downloads_dir()
-    '/home/trentm/Downloads'
-    >>> user_pictures_dir()
-    '/home/trentm/Pictures'
-    >>> user_videos_dir()
-    '/home/trentm/Videos'
-    >>> user_music_dir()
-    '/home/trentm/Music'
-    >>> user_desktop_dir()
-    '/home/trentm/Desktop'
-    >>> user_runtime_dir(appname, appauthor)
-    '/run/user/{os.getuid()}/SuperApp'
-    >>> site_config_dir(appname)
-    '/etc/xdg/SuperApp'
-    >>> os.environ["XDG_CONFIG_DIRS"] = "/etc:/usr/local/etc"
-    >>> site_config_dir(appname, multipath=True)
-    '/etc/SuperApp:/usr/local/etc/SuperApp'
-
-On Android::
-
-    >>> from platformdirs import *
-    >>> appname = "SuperApp"
-    >>> appauthor = "Acme"
-    >>> user_data_dir(appname, appauthor)
-    '/data/data/com.myApp/files/SuperApp'
-    >>> user_cache_dir(appname, appauthor)
-    '/data/data/com.myApp/cache/SuperApp'
-    >>> user_log_dir(appname, appauthor)
-    '/data/data/com.myApp/cache/SuperApp/log'
-    >>> user_config_dir(appname)
-    '/data/data/com.myApp/shared_prefs/SuperApp'
-    >>> user_documents_dir()
-    '/storage/emulated/0/Documents'
-    >>> user_downloads_dir()
-    '/storage/emulated/0/Downloads'
-    >>> user_pictures_dir()
-    '/storage/emulated/0/Pictures'
-    >>> user_videos_dir()
-    '/storage/emulated/0/DCIM/Camera'
-    >>> user_music_dir()
-    '/storage/emulated/0/Music'
-    >>> user_desktop_dir()
-    '/storage/emulated/0/Desktop'
-    >>> user_runtime_dir(appname, appauthor)
-    '/data/data/com.myApp/cache/SuperApp/tmp'
-
-Note: Some android apps like Termux and Pydroid are used as shells. These
-apps are used by the end user to emulate Linux environment. Presence of
-``SHELL`` environment variable is used by Platformdirs to differentiate
-between general android apps and android apps used as shells. Shell android
-apps also support ``XDG_*`` environment variables.
-
-
-``PlatformDirs`` for convenience
-================================
-
-.. code-block:: pycon
-
-    >>> from platformdirs import PlatformDirs
-    >>> dirs = PlatformDirs("SuperApp", "Acme")
-    >>> dirs.user_data_dir
-    '/Users/trentm/Library/Application Support/SuperApp'
-    >>> dirs.site_data_dir
-    '/Library/Application Support/SuperApp'
-    >>> dirs.user_cache_dir
-    '/Users/trentm/Library/Caches/SuperApp'
-    >>> dirs.user_log_dir
-    '/Users/trentm/Library/Logs/SuperApp'
-    >>> dirs.user_documents_dir
-    '/Users/trentm/Documents'
-    >>> dirs.user_downloads_dir
-    '/Users/trentm/Downloads'
-    >>> dirs.user_pictures_dir
-    '/Users/trentm/Pictures'
-    >>> dirs.user_videos_dir
-    '/Users/trentm/Movies'
-    >>> dirs.user_music_dir
-    '/Users/trentm/Music'
-    >>> dirs.user_desktop_dir
-    '/Users/trentm/Desktop'
-    >>> dirs.user_runtime_dir
-    '/Users/trentm/Library/Caches/TemporaryItems/SuperApp'
-
-Per-version isolation
-=====================
-
-If you have multiple versions of your app in use that you want to be
-able to run side-by-side, then you may want version-isolation for these
-dirs::
-
-    >>> from platformdirs import PlatformDirs
-    >>> dirs = PlatformDirs("SuperApp", "Acme", version="1.0")
-    >>> dirs.user_data_dir
-    '/Users/trentm/Library/Application Support/SuperApp/1.0'
-    >>> dirs.site_data_dir
-    '/Library/Application Support/SuperApp/1.0'
-    >>> dirs.user_cache_dir
-    '/Users/trentm/Library/Caches/SuperApp/1.0'
-    >>> dirs.user_log_dir
-    '/Users/trentm/Library/Logs/SuperApp/1.0'
-    >>> dirs.user_documents_dir
-    '/Users/trentm/Documents'
-    >>> dirs.user_downloads_dir
-    '/Users/trentm/Downloads'
-    >>> dirs.user_pictures_dir
-    '/Users/trentm/Pictures'
-    >>> dirs.user_videos_dir
-    '/Users/trentm/Movies'
-    >>> dirs.user_music_dir
-    '/Users/trentm/Music'
-    >>> dirs.user_desktop_dir
-    '/Users/trentm/Desktop'
-    >>> dirs.user_runtime_dir
-    '/Users/trentm/Library/Caches/TemporaryItems/SuperApp/1.0'
-
-Be wary of using this for configuration files though; you'll need to handle
-migrating configuration files manually.
-
-Why this Fork?
-==============
-
-This repository is a friendly fork of the wonderful work started by
-`ActiveState `_ who created
-``appdirs``, this package's ancestor.
-
-Maintaining an open source project is no easy task, particularly
-from within an organization, and the Python community is indebted
-to ``appdirs`` (and to Trent Mick and Jeff Rouse in particular) for
-creating an incredibly useful simple module, as evidenced by the wide
-number of users it has attracted over the years.
-
-Nonetheless, given the number of long-standing open issues
-and pull requests, and no clear path towards `ensuring
-that maintenance of the package would continue or grow
-`_, this fork was
-created.
-
-Contributions are most welcome.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/RECORD
deleted file mode 100644
index 64c0c8e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/RECORD
+++ /dev/null
@@ -1,23 +0,0 @@
-platformdirs-4.2.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-platformdirs-4.2.2.dist-info/METADATA,sha256=zmsie01G1MtXR0wgIv5XpVeTO7idr0WWvfmxKsKWuGk,11429
-platformdirs-4.2.2.dist-info/RECORD,,
-platformdirs-4.2.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-platformdirs-4.2.2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-platformdirs-4.2.2.dist-info/licenses/LICENSE,sha256=KeD9YukphQ6G6yjD_czwzv30-pSHkBHP-z0NS-1tTbY,1089
-platformdirs/__init__.py,sha256=EMGE8qeHRR9CzDFr8kL3tA8hdZZniYjXBVZd0UGTWK0,22225
-platformdirs/__main__.py,sha256=HnsUQHpiBaiTxwcmwVw-nFaPdVNZtQIdi1eWDtI-MzI,1493
-platformdirs/__pycache__/__init__.cpython-312.pyc,,
-platformdirs/__pycache__/__main__.cpython-312.pyc,,
-platformdirs/__pycache__/android.cpython-312.pyc,,
-platformdirs/__pycache__/api.cpython-312.pyc,,
-platformdirs/__pycache__/macos.cpython-312.pyc,,
-platformdirs/__pycache__/unix.cpython-312.pyc,,
-platformdirs/__pycache__/version.cpython-312.pyc,,
-platformdirs/__pycache__/windows.cpython-312.pyc,,
-platformdirs/android.py,sha256=xZXY9Jd46WOsxT2U6-5HsNtDZ-IQqxcEUrBLl3hYk4o,9016
-platformdirs/api.py,sha256=QBYdUac2eC521ek_y53uD1Dcq-lJX8IgSRVd4InC6uc,8996
-platformdirs/macos.py,sha256=wftsbsvq6nZ0WORXSiCrZNkRHz_WKuktl0a6mC7MFkI,5580
-platformdirs/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-platformdirs/unix.py,sha256=Cci9Wqt35dAMsg6HT9nRGHSBW5obb0pR3AE1JJnsCXg,10643
-platformdirs/version.py,sha256=r7F76tZRjgQKzrpx_I0_ZMQOMU-PS7eGnHD7zEK3KB0,411
-platformdirs/windows.py,sha256=IFpiohUBwxPtCzlyKwNtxyW4Jk8haa6W8o59mfrDXVo,10125
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/REQUESTED
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/WHEEL
deleted file mode 100644
index 516596c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/WHEEL
+++ /dev/null
@@ -1,4 +0,0 @@
-Wheel-Version: 1.0
-Generator: hatchling 1.24.2
-Root-Is-Purelib: true
-Tag: py3-none-any
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/licenses/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/licenses/LICENSE
deleted file mode 100644
index f35fed9..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs-4.2.2.dist-info/licenses/LICENSE
+++ /dev/null
@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2010-202x The platformdirs developers
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__init__.py
deleted file mode 100644
index 3f7d949..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__init__.py
+++ /dev/null
@@ -1,627 +0,0 @@
-"""
-Utilities for determining application-specific dirs.
-
-See  for details and usage.
-
-"""
-
-from __future__ import annotations
-
-import os
-import sys
-from typing import TYPE_CHECKING
-
-from .api import PlatformDirsABC
-from .version import __version__
-from .version import __version_tuple__ as __version_info__
-
-if TYPE_CHECKING:
-    from pathlib import Path
-    from typing import Literal
-
-
-def _set_platform_dir_class() -> type[PlatformDirsABC]:
-    if sys.platform == "win32":
-        from platformdirs.windows import Windows as Result  # noqa: PLC0415
-    elif sys.platform == "darwin":
-        from platformdirs.macos import MacOS as Result  # noqa: PLC0415
-    else:
-        from platformdirs.unix import Unix as Result  # noqa: PLC0415
-
-    if os.getenv("ANDROID_DATA") == "/data" and os.getenv("ANDROID_ROOT") == "/system":
-        if os.getenv("SHELL") or os.getenv("PREFIX"):
-            return Result
-
-        from platformdirs.android import _android_folder  # noqa: PLC0415
-
-        if _android_folder() is not None:
-            from platformdirs.android import Android  # noqa: PLC0415
-
-            return Android  # return to avoid redefinition of a result
-
-    return Result
-
-
-PlatformDirs = _set_platform_dir_class()  #: Currently active platform
-AppDirs = PlatformDirs  #: Backwards compatibility with appdirs
-
-
-def user_data_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    roaming: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param roaming: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: data directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        roaming=roaming,
-        ensure_exists=ensure_exists,
-    ).user_data_dir
-
-
-def site_data_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    multipath: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param multipath: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: data directory shared by users
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        multipath=multipath,
-        ensure_exists=ensure_exists,
-    ).site_data_dir
-
-
-def user_config_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    roaming: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param roaming: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: config directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        roaming=roaming,
-        ensure_exists=ensure_exists,
-    ).user_config_dir
-
-
-def site_config_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    multipath: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param multipath: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: config directory shared by the users
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        multipath=multipath,
-        ensure_exists=ensure_exists,
-    ).site_config_dir
-
-
-def user_cache_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: cache directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).user_cache_dir
-
-
-def site_cache_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `opinion `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: cache directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).site_cache_dir
-
-
-def user_state_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    roaming: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param roaming: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: state directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        roaming=roaming,
-        ensure_exists=ensure_exists,
-    ).user_state_dir
-
-
-def user_log_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: log directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).user_log_dir
-
-
-def user_documents_dir() -> str:
-    """:returns: documents directory tied to the user"""
-    return PlatformDirs().user_documents_dir
-
-
-def user_downloads_dir() -> str:
-    """:returns: downloads directory tied to the user"""
-    return PlatformDirs().user_downloads_dir
-
-
-def user_pictures_dir() -> str:
-    """:returns: pictures directory tied to the user"""
-    return PlatformDirs().user_pictures_dir
-
-
-def user_videos_dir() -> str:
-    """:returns: videos directory tied to the user"""
-    return PlatformDirs().user_videos_dir
-
-
-def user_music_dir() -> str:
-    """:returns: music directory tied to the user"""
-    return PlatformDirs().user_music_dir
-
-
-def user_desktop_dir() -> str:
-    """:returns: desktop directory tied to the user"""
-    return PlatformDirs().user_desktop_dir
-
-
-def user_runtime_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `opinion `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: runtime directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).user_runtime_dir
-
-
-def site_runtime_dir(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> str:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `opinion `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: runtime directory shared by users
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).site_runtime_dir
-
-
-def user_data_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    roaming: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param roaming: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: data path tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        roaming=roaming,
-        ensure_exists=ensure_exists,
-    ).user_data_path
-
-
-def site_data_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    multipath: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param multipath: See `multipath `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: data path shared by users
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        multipath=multipath,
-        ensure_exists=ensure_exists,
-    ).site_data_path
-
-
-def user_config_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    roaming: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param roaming: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: config path tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        roaming=roaming,
-        ensure_exists=ensure_exists,
-    ).user_config_path
-
-
-def site_config_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    multipath: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param multipath: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: config path shared by the users
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        multipath=multipath,
-        ensure_exists=ensure_exists,
-    ).site_config_path
-
-
-def site_cache_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `opinion `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: cache directory tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).site_cache_path
-
-
-def user_cache_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: cache path tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).user_cache_path
-
-
-def user_state_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    roaming: bool = False,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param roaming: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: state path tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        roaming=roaming,
-        ensure_exists=ensure_exists,
-    ).user_state_path
-
-
-def user_log_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `roaming `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: log path tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).user_log_path
-
-
-def user_documents_path() -> Path:
-    """:returns: documents a path tied to the user"""
-    return PlatformDirs().user_documents_path
-
-
-def user_downloads_path() -> Path:
-    """:returns: downloads path tied to the user"""
-    return PlatformDirs().user_downloads_path
-
-
-def user_pictures_path() -> Path:
-    """:returns: pictures path tied to the user"""
-    return PlatformDirs().user_pictures_path
-
-
-def user_videos_path() -> Path:
-    """:returns: videos path tied to the user"""
-    return PlatformDirs().user_videos_path
-
-
-def user_music_path() -> Path:
-    """:returns: music path tied to the user"""
-    return PlatformDirs().user_music_path
-
-
-def user_desktop_path() -> Path:
-    """:returns: desktop path tied to the user"""
-    return PlatformDirs().user_desktop_path
-
-
-def user_runtime_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `opinion `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: runtime path tied to the user
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).user_runtime_path
-
-
-def site_runtime_path(
-    appname: str | None = None,
-    appauthor: str | None | Literal[False] = None,
-    version: str | None = None,
-    opinion: bool = True,  # noqa: FBT001, FBT002
-    ensure_exists: bool = False,  # noqa: FBT001, FBT002
-) -> Path:
-    """
-    :param appname: See `appname `.
-    :param appauthor: See `appauthor `.
-    :param version: See `version `.
-    :param opinion: See `opinion `.
-    :param ensure_exists: See `ensure_exists `.
-    :returns: runtime path shared by users
-    """
-    return PlatformDirs(
-        appname=appname,
-        appauthor=appauthor,
-        version=version,
-        opinion=opinion,
-        ensure_exists=ensure_exists,
-    ).site_runtime_path
-
-
-__all__ = [
-    "AppDirs",
-    "PlatformDirs",
-    "PlatformDirsABC",
-    "__version__",
-    "__version_info__",
-    "site_cache_dir",
-    "site_cache_path",
-    "site_config_dir",
-    "site_config_path",
-    "site_data_dir",
-    "site_data_path",
-    "site_runtime_dir",
-    "site_runtime_path",
-    "user_cache_dir",
-    "user_cache_path",
-    "user_config_dir",
-    "user_config_path",
-    "user_data_dir",
-    "user_data_path",
-    "user_desktop_dir",
-    "user_desktop_path",
-    "user_documents_dir",
-    "user_documents_path",
-    "user_downloads_dir",
-    "user_downloads_path",
-    "user_log_dir",
-    "user_log_path",
-    "user_music_dir",
-    "user_music_path",
-    "user_pictures_dir",
-    "user_pictures_path",
-    "user_runtime_dir",
-    "user_runtime_path",
-    "user_state_dir",
-    "user_state_path",
-    "user_videos_dir",
-    "user_videos_path",
-]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__main__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__main__.py
deleted file mode 100644
index 922c521..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__main__.py
+++ /dev/null
@@ -1,55 +0,0 @@
-"""Main entry point."""
-
-from __future__ import annotations
-
-from platformdirs import PlatformDirs, __version__
-
-PROPS = (
-    "user_data_dir",
-    "user_config_dir",
-    "user_cache_dir",
-    "user_state_dir",
-    "user_log_dir",
-    "user_documents_dir",
-    "user_downloads_dir",
-    "user_pictures_dir",
-    "user_videos_dir",
-    "user_music_dir",
-    "user_runtime_dir",
-    "site_data_dir",
-    "site_config_dir",
-    "site_cache_dir",
-    "site_runtime_dir",
-)
-
-
-def main() -> None:
-    """Run the main entry point."""
-    app_name = "MyApp"
-    app_author = "MyCompany"
-
-    print(f"-- platformdirs {__version__} --")  # noqa: T201
-
-    print("-- app dirs (with optional 'version')")  # noqa: T201
-    dirs = PlatformDirs(app_name, app_author, version="1.0")
-    for prop in PROPS:
-        print(f"{prop}: {getattr(dirs, prop)}")  # noqa: T201
-
-    print("\n-- app dirs (without optional 'version')")  # noqa: T201
-    dirs = PlatformDirs(app_name, app_author)
-    for prop in PROPS:
-        print(f"{prop}: {getattr(dirs, prop)}")  # noqa: T201
-
-    print("\n-- app dirs (without optional 'appauthor')")  # noqa: T201
-    dirs = PlatformDirs(app_name)
-    for prop in PROPS:
-        print(f"{prop}: {getattr(dirs, prop)}")  # noqa: T201
-
-    print("\n-- app dirs (with disabled 'appauthor')")  # noqa: T201
-    dirs = PlatformDirs(app_name, appauthor=False)
-    for prop in PROPS:
-        print(f"{prop}: {getattr(dirs, prop)}")  # noqa: T201
-
-
-if __name__ == "__main__":
-    main()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 3f5d257..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc
deleted file mode 100644
index b45c6f2..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/__main__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/android.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/android.cpython-312.pyc
deleted file mode 100644
index 05109fb..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/android.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/api.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/api.cpython-312.pyc
deleted file mode 100644
index 5814828..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/api.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc
deleted file mode 100644
index 6416323..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/macos.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc
deleted file mode 100644
index 5c6bc1f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/unix.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/version.cpython-312.pyc
deleted file mode 100644
index bfa4bf8..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/version.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc
deleted file mode 100644
index a3a0e03..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/__pycache__/windows.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/android.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/android.py
deleted file mode 100644
index afd3141..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/android.py
+++ /dev/null
@@ -1,249 +0,0 @@
-"""Android."""
-
-from __future__ import annotations
-
-import os
-import re
-import sys
-from functools import lru_cache
-from typing import TYPE_CHECKING, cast
-
-from .api import PlatformDirsABC
-
-
-class Android(PlatformDirsABC):
-    """
-    Follows the guidance `from here `_.
-
-    Makes use of the `appname `, `version
-    `, `ensure_exists `.
-
-    """
-
-    @property
-    def user_data_dir(self) -> str:
-        """:return: data directory tied to the user, e.g. ``/data/user///files/``"""
-        return self._append_app_name_and_version(cast(str, _android_folder()), "files")
-
-    @property
-    def site_data_dir(self) -> str:
-        """:return: data directory shared by users, same as `user_data_dir`"""
-        return self.user_data_dir
-
-    @property
-    def user_config_dir(self) -> str:
-        """
-        :return: config directory tied to the user, e.g. \
-        ``/data/user///shared_prefs/``
-        """
-        return self._append_app_name_and_version(cast(str, _android_folder()), "shared_prefs")
-
-    @property
-    def site_config_dir(self) -> str:
-        """:return: config directory shared by the users, same as `user_config_dir`"""
-        return self.user_config_dir
-
-    @property
-    def user_cache_dir(self) -> str:
-        """:return: cache directory tied to the user, e.g.,``/data/user///cache/``"""
-        return self._append_app_name_and_version(cast(str, _android_folder()), "cache")
-
-    @property
-    def site_cache_dir(self) -> str:
-        """:return: cache directory shared by users, same as `user_cache_dir`"""
-        return self.user_cache_dir
-
-    @property
-    def user_state_dir(self) -> str:
-        """:return: state directory tied to the user, same as `user_data_dir`"""
-        return self.user_data_dir
-
-    @property
-    def user_log_dir(self) -> str:
-        """
-        :return: log directory tied to the user, same as `user_cache_dir` if not opinionated else ``log`` in it,
-          e.g. ``/data/user///cache//log``
-        """
-        path = self.user_cache_dir
-        if self.opinion:
-            path = os.path.join(path, "log")  # noqa: PTH118
-        return path
-
-    @property
-    def user_documents_dir(self) -> str:
-        """:return: documents directory tied to the user e.g. ``/storage/emulated/0/Documents``"""
-        return _android_documents_folder()
-
-    @property
-    def user_downloads_dir(self) -> str:
-        """:return: downloads directory tied to the user e.g. ``/storage/emulated/0/Downloads``"""
-        return _android_downloads_folder()
-
-    @property
-    def user_pictures_dir(self) -> str:
-        """:return: pictures directory tied to the user e.g. ``/storage/emulated/0/Pictures``"""
-        return _android_pictures_folder()
-
-    @property
-    def user_videos_dir(self) -> str:
-        """:return: videos directory tied to the user e.g. ``/storage/emulated/0/DCIM/Camera``"""
-        return _android_videos_folder()
-
-    @property
-    def user_music_dir(self) -> str:
-        """:return: music directory tied to the user e.g. ``/storage/emulated/0/Music``"""
-        return _android_music_folder()
-
-    @property
-    def user_desktop_dir(self) -> str:
-        """:return: desktop directory tied to the user e.g. ``/storage/emulated/0/Desktop``"""
-        return "/storage/emulated/0/Desktop"
-
-    @property
-    def user_runtime_dir(self) -> str:
-        """
-        :return: runtime directory tied to the user, same as `user_cache_dir` if not opinionated else ``tmp`` in it,
-          e.g. ``/data/user///cache//tmp``
-        """
-        path = self.user_cache_dir
-        if self.opinion:
-            path = os.path.join(path, "tmp")  # noqa: PTH118
-        return path
-
-    @property
-    def site_runtime_dir(self) -> str:
-        """:return: runtime directory shared by users, same as `user_runtime_dir`"""
-        return self.user_runtime_dir
-
-
-@lru_cache(maxsize=1)
-def _android_folder() -> str | None:  # noqa: C901, PLR0912
-    """:return: base folder for the Android OS or None if it cannot be found"""
-    result: str | None = None
-    # type checker isn't happy with our "import android", just don't do this when type checking see
-    # https://stackoverflow.com/a/61394121
-    if not TYPE_CHECKING:
-        try:
-            # First try to get a path to android app using python4android (if available)...
-            from android import mActivity  # noqa: PLC0415
-
-            context = cast("android.content.Context", mActivity.getApplicationContext())  # noqa: F821
-            result = context.getFilesDir().getParentFile().getAbsolutePath()
-        except Exception:  # noqa: BLE001
-            result = None
-    if result is None:
-        try:
-            # ...and fall back to using plain pyjnius, if python4android isn't available or doesn't deliver any useful
-            # result...
-            from jnius import autoclass  # noqa: PLC0415
-
-            context = autoclass("android.content.Context")
-            result = context.getFilesDir().getParentFile().getAbsolutePath()
-        except Exception:  # noqa: BLE001
-            result = None
-    if result is None:
-        # and if that fails, too, find an android folder looking at path on the sys.path
-        # warning: only works for apps installed under /data, not adopted storage etc.
-        pattern = re.compile(r"/data/(data|user/\d+)/(.+)/files")
-        for path in sys.path:
-            if pattern.match(path):
-                result = path.split("/files")[0]
-                break
-        else:
-            result = None
-    if result is None:
-        # one last try: find an android folder looking at path on the sys.path taking adopted storage paths into
-        # account
-        pattern = re.compile(r"/mnt/expand/[a-fA-F0-9-]{36}/(data|user/\d+)/(.+)/files")
-        for path in sys.path:
-            if pattern.match(path):
-                result = path.split("/files")[0]
-                break
-        else:
-            result = None
-    return result
-
-
-@lru_cache(maxsize=1)
-def _android_documents_folder() -> str:
-    """:return: documents folder for the Android OS"""
-    # Get directories with pyjnius
-    try:
-        from jnius import autoclass  # noqa: PLC0415
-
-        context = autoclass("android.content.Context")
-        environment = autoclass("android.os.Environment")
-        documents_dir: str = context.getExternalFilesDir(environment.DIRECTORY_DOCUMENTS).getAbsolutePath()
-    except Exception:  # noqa: BLE001
-        documents_dir = "/storage/emulated/0/Documents"
-
-    return documents_dir
-
-
-@lru_cache(maxsize=1)
-def _android_downloads_folder() -> str:
-    """:return: downloads folder for the Android OS"""
-    # Get directories with pyjnius
-    try:
-        from jnius import autoclass  # noqa: PLC0415
-
-        context = autoclass("android.content.Context")
-        environment = autoclass("android.os.Environment")
-        downloads_dir: str = context.getExternalFilesDir(environment.DIRECTORY_DOWNLOADS).getAbsolutePath()
-    except Exception:  # noqa: BLE001
-        downloads_dir = "/storage/emulated/0/Downloads"
-
-    return downloads_dir
-
-
-@lru_cache(maxsize=1)
-def _android_pictures_folder() -> str:
-    """:return: pictures folder for the Android OS"""
-    # Get directories with pyjnius
-    try:
-        from jnius import autoclass  # noqa: PLC0415
-
-        context = autoclass("android.content.Context")
-        environment = autoclass("android.os.Environment")
-        pictures_dir: str = context.getExternalFilesDir(environment.DIRECTORY_PICTURES).getAbsolutePath()
-    except Exception:  # noqa: BLE001
-        pictures_dir = "/storage/emulated/0/Pictures"
-
-    return pictures_dir
-
-
-@lru_cache(maxsize=1)
-def _android_videos_folder() -> str:
-    """:return: videos folder for the Android OS"""
-    # Get directories with pyjnius
-    try:
-        from jnius import autoclass  # noqa: PLC0415
-
-        context = autoclass("android.content.Context")
-        environment = autoclass("android.os.Environment")
-        videos_dir: str = context.getExternalFilesDir(environment.DIRECTORY_DCIM).getAbsolutePath()
-    except Exception:  # noqa: BLE001
-        videos_dir = "/storage/emulated/0/DCIM/Camera"
-
-    return videos_dir
-
-
-@lru_cache(maxsize=1)
-def _android_music_folder() -> str:
-    """:return: music folder for the Android OS"""
-    # Get directories with pyjnius
-    try:
-        from jnius import autoclass  # noqa: PLC0415
-
-        context = autoclass("android.content.Context")
-        environment = autoclass("android.os.Environment")
-        music_dir: str = context.getExternalFilesDir(environment.DIRECTORY_MUSIC).getAbsolutePath()
-    except Exception:  # noqa: BLE001
-        music_dir = "/storage/emulated/0/Music"
-
-    return music_dir
-
-
-__all__ = [
-    "Android",
-]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/api.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/api.py
deleted file mode 100644
index c50caa6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/api.py
+++ /dev/null
@@ -1,292 +0,0 @@
-"""Base API."""
-
-from __future__ import annotations
-
-import os
-from abc import ABC, abstractmethod
-from pathlib import Path
-from typing import TYPE_CHECKING
-
-if TYPE_CHECKING:
-    from typing import Iterator, Literal
-
-
-class PlatformDirsABC(ABC):  # noqa: PLR0904
-    """Abstract base class for platform directories."""
-
-    def __init__(  # noqa: PLR0913, PLR0917
-        self,
-        appname: str | None = None,
-        appauthor: str | None | Literal[False] = None,
-        version: str | None = None,
-        roaming: bool = False,  # noqa: FBT001, FBT002
-        multipath: bool = False,  # noqa: FBT001, FBT002
-        opinion: bool = True,  # noqa: FBT001, FBT002
-        ensure_exists: bool = False,  # noqa: FBT001, FBT002
-    ) -> None:
-        """
-        Create a new platform directory.
-
-        :param appname: See `appname`.
-        :param appauthor: See `appauthor`.
-        :param version: See `version`.
-        :param roaming: See `roaming`.
-        :param multipath: See `multipath`.
-        :param opinion: See `opinion`.
-        :param ensure_exists: See `ensure_exists`.
-
-        """
-        self.appname = appname  #: The name of application.
-        self.appauthor = appauthor
-        """
-        The name of the app author or distributing body for this application.
-
-        Typically, it is the owning company name. Defaults to `appname`. You may pass ``False`` to disable it.
-
-        """
-        self.version = version
-        """
-        An optional version path element to append to the path.
-
-        You might want to use this if you want multiple versions of your app to be able to run independently. If used,
-        this would typically be ``.``.
-
-        """
-        self.roaming = roaming
-        """
-        Whether to use the roaming appdata directory on Windows.
-
-        That means that for users on a Windows network setup for roaming profiles, this user data will be synced on
-        login (see
-        `here `_).
-
-        """
-        self.multipath = multipath
-        """
-        An optional parameter which indicates that the entire list of data dirs should be returned.
-
-        By default, the first item would only be returned.
-
-        """
-        self.opinion = opinion  #: A flag to indicating to use opinionated values.
-        self.ensure_exists = ensure_exists
-        """
-        Optionally create the directory (and any missing parents) upon access if it does not exist.
-
-        By default, no directories are created.
-
-        """
-
-    def _append_app_name_and_version(self, *base: str) -> str:
-        params = list(base[1:])
-        if self.appname:
-            params.append(self.appname)
-            if self.version:
-                params.append(self.version)
-        path = os.path.join(base[0], *params)  # noqa: PTH118
-        self._optionally_create_directory(path)
-        return path
-
-    def _optionally_create_directory(self, path: str) -> None:
-        if self.ensure_exists:
-            Path(path).mkdir(parents=True, exist_ok=True)
-
-    @property
-    @abstractmethod
-    def user_data_dir(self) -> str:
-        """:return: data directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def site_data_dir(self) -> str:
-        """:return: data directory shared by users"""
-
-    @property
-    @abstractmethod
-    def user_config_dir(self) -> str:
-        """:return: config directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def site_config_dir(self) -> str:
-        """:return: config directory shared by the users"""
-
-    @property
-    @abstractmethod
-    def user_cache_dir(self) -> str:
-        """:return: cache directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def site_cache_dir(self) -> str:
-        """:return: cache directory shared by users"""
-
-    @property
-    @abstractmethod
-    def user_state_dir(self) -> str:
-        """:return: state directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_log_dir(self) -> str:
-        """:return: log directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_documents_dir(self) -> str:
-        """:return: documents directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_downloads_dir(self) -> str:
-        """:return: downloads directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_pictures_dir(self) -> str:
-        """:return: pictures directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_videos_dir(self) -> str:
-        """:return: videos directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_music_dir(self) -> str:
-        """:return: music directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_desktop_dir(self) -> str:
-        """:return: desktop directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def user_runtime_dir(self) -> str:
-        """:return: runtime directory tied to the user"""
-
-    @property
-    @abstractmethod
-    def site_runtime_dir(self) -> str:
-        """:return: runtime directory shared by users"""
-
-    @property
-    def user_data_path(self) -> Path:
-        """:return: data path tied to the user"""
-        return Path(self.user_data_dir)
-
-    @property
-    def site_data_path(self) -> Path:
-        """:return: data path shared by users"""
-        return Path(self.site_data_dir)
-
-    @property
-    def user_config_path(self) -> Path:
-        """:return: config path tied to the user"""
-        return Path(self.user_config_dir)
-
-    @property
-    def site_config_path(self) -> Path:
-        """:return: config path shared by the users"""
-        return Path(self.site_config_dir)
-
-    @property
-    def user_cache_path(self) -> Path:
-        """:return: cache path tied to the user"""
-        return Path(self.user_cache_dir)
-
-    @property
-    def site_cache_path(self) -> Path:
-        """:return: cache path shared by users"""
-        return Path(self.site_cache_dir)
-
-    @property
-    def user_state_path(self) -> Path:
-        """:return: state path tied to the user"""
-        return Path(self.user_state_dir)
-
-    @property
-    def user_log_path(self) -> Path:
-        """:return: log path tied to the user"""
-        return Path(self.user_log_dir)
-
-    @property
-    def user_documents_path(self) -> Path:
-        """:return: documents a path tied to the user"""
-        return Path(self.user_documents_dir)
-
-    @property
-    def user_downloads_path(self) -> Path:
-        """:return: downloads path tied to the user"""
-        return Path(self.user_downloads_dir)
-
-    @property
-    def user_pictures_path(self) -> Path:
-        """:return: pictures path tied to the user"""
-        return Path(self.user_pictures_dir)
-
-    @property
-    def user_videos_path(self) -> Path:
-        """:return: videos path tied to the user"""
-        return Path(self.user_videos_dir)
-
-    @property
-    def user_music_path(self) -> Path:
-        """:return: music path tied to the user"""
-        return Path(self.user_music_dir)
-
-    @property
-    def user_desktop_path(self) -> Path:
-        """:return: desktop path tied to the user"""
-        return Path(self.user_desktop_dir)
-
-    @property
-    def user_runtime_path(self) -> Path:
-        """:return: runtime path tied to the user"""
-        return Path(self.user_runtime_dir)
-
-    @property
-    def site_runtime_path(self) -> Path:
-        """:return: runtime path shared by users"""
-        return Path(self.site_runtime_dir)
-
-    def iter_config_dirs(self) -> Iterator[str]:
-        """:yield: all user and site configuration directories."""
-        yield self.user_config_dir
-        yield self.site_config_dir
-
-    def iter_data_dirs(self) -> Iterator[str]:
-        """:yield: all user and site data directories."""
-        yield self.user_data_dir
-        yield self.site_data_dir
-
-    def iter_cache_dirs(self) -> Iterator[str]:
-        """:yield: all user and site cache directories."""
-        yield self.user_cache_dir
-        yield self.site_cache_dir
-
-    def iter_runtime_dirs(self) -> Iterator[str]:
-        """:yield: all user and site runtime directories."""
-        yield self.user_runtime_dir
-        yield self.site_runtime_dir
-
-    def iter_config_paths(self) -> Iterator[Path]:
-        """:yield: all user and site configuration paths."""
-        for path in self.iter_config_dirs():
-            yield Path(path)
-
-    def iter_data_paths(self) -> Iterator[Path]:
-        """:yield: all user and site data paths."""
-        for path in self.iter_data_dirs():
-            yield Path(path)
-
-    def iter_cache_paths(self) -> Iterator[Path]:
-        """:yield: all user and site cache paths."""
-        for path in self.iter_cache_dirs():
-            yield Path(path)
-
-    def iter_runtime_paths(self) -> Iterator[Path]:
-        """:yield: all user and site runtime paths."""
-        for path in self.iter_runtime_dirs():
-            yield Path(path)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/macos.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/macos.py
deleted file mode 100644
index eb1ba5d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/macos.py
+++ /dev/null
@@ -1,130 +0,0 @@
-"""macOS."""
-
-from __future__ import annotations
-
-import os.path
-import sys
-
-from .api import PlatformDirsABC
-
-
-class MacOS(PlatformDirsABC):
-    """
-    Platform directories for the macOS operating system.
-
-    Follows the guidance from
-    `Apple documentation `_.
-    Makes use of the `appname `,
-    `version `,
-    `ensure_exists `.
-
-    """
-
-    @property
-    def user_data_dir(self) -> str:
-        """:return: data directory tied to the user, e.g. ``~/Library/Application Support/$appname/$version``"""
-        return self._append_app_name_and_version(os.path.expanduser("~/Library/Application Support"))  # noqa: PTH111
-
-    @property
-    def site_data_dir(self) -> str:
-        """
-        :return: data directory shared by users, e.g. ``/Library/Application Support/$appname/$version``.
-          If we're using a Python binary managed by `Homebrew `_, the directory
-          will be under the Homebrew prefix, e.g. ``/opt/homebrew/share/$appname/$version``.
-          If `multipath ` is enabled, and we're in Homebrew,
-          the response is a multi-path string separated by ":", e.g.
-          ``/opt/homebrew/share/$appname/$version:/Library/Application Support/$appname/$version``
-        """
-        is_homebrew = sys.prefix.startswith("/opt/homebrew")
-        path_list = [self._append_app_name_and_version("/opt/homebrew/share")] if is_homebrew else []
-        path_list.append(self._append_app_name_and_version("/Library/Application Support"))
-        if self.multipath:
-            return os.pathsep.join(path_list)
-        return path_list[0]
-
-    @property
-    def user_config_dir(self) -> str:
-        """:return: config directory tied to the user, same as `user_data_dir`"""
-        return self.user_data_dir
-
-    @property
-    def site_config_dir(self) -> str:
-        """:return: config directory shared by the users, same as `site_data_dir`"""
-        return self.site_data_dir
-
-    @property
-    def user_cache_dir(self) -> str:
-        """:return: cache directory tied to the user, e.g. ``~/Library/Caches/$appname/$version``"""
-        return self._append_app_name_and_version(os.path.expanduser("~/Library/Caches"))  # noqa: PTH111
-
-    @property
-    def site_cache_dir(self) -> str:
-        """
-        :return: cache directory shared by users, e.g. ``/Library/Caches/$appname/$version``.
-          If we're using a Python binary managed by `Homebrew `_, the directory
-          will be under the Homebrew prefix, e.g. ``/opt/homebrew/var/cache/$appname/$version``.
-          If `multipath ` is enabled, and we're in Homebrew,
-          the response is a multi-path string separated by ":", e.g.
-          ``/opt/homebrew/var/cache/$appname/$version:/Library/Caches/$appname/$version``
-        """
-        is_homebrew = sys.prefix.startswith("/opt/homebrew")
-        path_list = [self._append_app_name_and_version("/opt/homebrew/var/cache")] if is_homebrew else []
-        path_list.append(self._append_app_name_and_version("/Library/Caches"))
-        if self.multipath:
-            return os.pathsep.join(path_list)
-        return path_list[0]
-
-    @property
-    def user_state_dir(self) -> str:
-        """:return: state directory tied to the user, same as `user_data_dir`"""
-        return self.user_data_dir
-
-    @property
-    def user_log_dir(self) -> str:
-        """:return: log directory tied to the user, e.g. ``~/Library/Logs/$appname/$version``"""
-        return self._append_app_name_and_version(os.path.expanduser("~/Library/Logs"))  # noqa: PTH111
-
-    @property
-    def user_documents_dir(self) -> str:
-        """:return: documents directory tied to the user, e.g. ``~/Documents``"""
-        return os.path.expanduser("~/Documents")  # noqa: PTH111
-
-    @property
-    def user_downloads_dir(self) -> str:
-        """:return: downloads directory tied to the user, e.g. ``~/Downloads``"""
-        return os.path.expanduser("~/Downloads")  # noqa: PTH111
-
-    @property
-    def user_pictures_dir(self) -> str:
-        """:return: pictures directory tied to the user, e.g. ``~/Pictures``"""
-        return os.path.expanduser("~/Pictures")  # noqa: PTH111
-
-    @property
-    def user_videos_dir(self) -> str:
-        """:return: videos directory tied to the user, e.g. ``~/Movies``"""
-        return os.path.expanduser("~/Movies")  # noqa: PTH111
-
-    @property
-    def user_music_dir(self) -> str:
-        """:return: music directory tied to the user, e.g. ``~/Music``"""
-        return os.path.expanduser("~/Music")  # noqa: PTH111
-
-    @property
-    def user_desktop_dir(self) -> str:
-        """:return: desktop directory tied to the user, e.g. ``~/Desktop``"""
-        return os.path.expanduser("~/Desktop")  # noqa: PTH111
-
-    @property
-    def user_runtime_dir(self) -> str:
-        """:return: runtime directory tied to the user, e.g. ``~/Library/Caches/TemporaryItems/$appname/$version``"""
-        return self._append_app_name_and_version(os.path.expanduser("~/Library/Caches/TemporaryItems"))  # noqa: PTH111
-
-    @property
-    def site_runtime_dir(self) -> str:
-        """:return: runtime directory shared by users, same as `user_runtime_dir`"""
-        return self.user_runtime_dir
-
-
-__all__ = [
-    "MacOS",
-]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/unix.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/unix.py
deleted file mode 100644
index 9500ade..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/unix.py
+++ /dev/null
@@ -1,275 +0,0 @@
-"""Unix."""
-
-from __future__ import annotations
-
-import os
-import sys
-from configparser import ConfigParser
-from pathlib import Path
-from typing import Iterator, NoReturn
-
-from .api import PlatformDirsABC
-
-if sys.platform == "win32":
-
-    def getuid() -> NoReturn:
-        msg = "should only be used on Unix"
-        raise RuntimeError(msg)
-
-else:
-    from os import getuid
-
-
-class Unix(PlatformDirsABC):  # noqa: PLR0904
-    """
-    On Unix/Linux, we follow the `XDG Basedir Spec `_.
-
-    The spec allows overriding directories with environment variables. The examples shown are the default values,
-    alongside the name of the environment variable that overrides them. Makes use of the `appname
-    `, `version `, `multipath
-    `, `opinion `, `ensure_exists
-    `.
-
-    """
-
-    @property
-    def user_data_dir(self) -> str:
-        """
-        :return: data directory tied to the user, e.g. ``~/.local/share/$appname/$version`` or
-         ``$XDG_DATA_HOME/$appname/$version``
-        """
-        path = os.environ.get("XDG_DATA_HOME", "")
-        if not path.strip():
-            path = os.path.expanduser("~/.local/share")  # noqa: PTH111
-        return self._append_app_name_and_version(path)
-
-    @property
-    def _site_data_dirs(self) -> list[str]:
-        path = os.environ.get("XDG_DATA_DIRS", "")
-        if not path.strip():
-            path = f"/usr/local/share{os.pathsep}/usr/share"
-        return [self._append_app_name_and_version(p) for p in path.split(os.pathsep)]
-
-    @property
-    def site_data_dir(self) -> str:
-        """
-        :return: data directories shared by users (if `multipath ` is
-         enabled and ``XDG_DATA_DIRS`` is set and a multi path the response is also a multi path separated by the
-         OS path separator), e.g. ``/usr/local/share/$appname/$version`` or ``/usr/share/$appname/$version``
-        """
-        # XDG default for $XDG_DATA_DIRS; only first, if multipath is False
-        dirs = self._site_data_dirs
-        if not self.multipath:
-            return dirs[0]
-        return os.pathsep.join(dirs)
-
-    @property
-    def user_config_dir(self) -> str:
-        """
-        :return: config directory tied to the user, e.g. ``~/.config/$appname/$version`` or
-         ``$XDG_CONFIG_HOME/$appname/$version``
-        """
-        path = os.environ.get("XDG_CONFIG_HOME", "")
-        if not path.strip():
-            path = os.path.expanduser("~/.config")  # noqa: PTH111
-        return self._append_app_name_and_version(path)
-
-    @property
-    def _site_config_dirs(self) -> list[str]:
-        path = os.environ.get("XDG_CONFIG_DIRS", "")
-        if not path.strip():
-            path = "/etc/xdg"
-        return [self._append_app_name_and_version(p) for p in path.split(os.pathsep)]
-
-    @property
-    def site_config_dir(self) -> str:
-        """
-        :return: config directories shared by users (if `multipath `
-         is enabled and ``XDG_CONFIG_DIRS`` is set and a multi path the response is also a multi path separated by
-         the OS path separator), e.g. ``/etc/xdg/$appname/$version``
-        """
-        # XDG default for $XDG_CONFIG_DIRS only first, if multipath is False
-        dirs = self._site_config_dirs
-        if not self.multipath:
-            return dirs[0]
-        return os.pathsep.join(dirs)
-
-    @property
-    def user_cache_dir(self) -> str:
-        """
-        :return: cache directory tied to the user, e.g. ``~/.cache/$appname/$version`` or
-         ``~/$XDG_CACHE_HOME/$appname/$version``
-        """
-        path = os.environ.get("XDG_CACHE_HOME", "")
-        if not path.strip():
-            path = os.path.expanduser("~/.cache")  # noqa: PTH111
-        return self._append_app_name_and_version(path)
-
-    @property
-    def site_cache_dir(self) -> str:
-        """:return: cache directory shared by users, e.g. ``/var/cache/$appname/$version``"""
-        return self._append_app_name_and_version("/var/cache")
-
-    @property
-    def user_state_dir(self) -> str:
-        """
-        :return: state directory tied to the user, e.g. ``~/.local/state/$appname/$version`` or
-         ``$XDG_STATE_HOME/$appname/$version``
-        """
-        path = os.environ.get("XDG_STATE_HOME", "")
-        if not path.strip():
-            path = os.path.expanduser("~/.local/state")  # noqa: PTH111
-        return self._append_app_name_and_version(path)
-
-    @property
-    def user_log_dir(self) -> str:
-        """:return: log directory tied to the user, same as `user_state_dir` if not opinionated else ``log`` in it"""
-        path = self.user_state_dir
-        if self.opinion:
-            path = os.path.join(path, "log")  # noqa: PTH118
-            self._optionally_create_directory(path)
-        return path
-
-    @property
-    def user_documents_dir(self) -> str:
-        """:return: documents directory tied to the user, e.g. ``~/Documents``"""
-        return _get_user_media_dir("XDG_DOCUMENTS_DIR", "~/Documents")
-
-    @property
-    def user_downloads_dir(self) -> str:
-        """:return: downloads directory tied to the user, e.g. ``~/Downloads``"""
-        return _get_user_media_dir("XDG_DOWNLOAD_DIR", "~/Downloads")
-
-    @property
-    def user_pictures_dir(self) -> str:
-        """:return: pictures directory tied to the user, e.g. ``~/Pictures``"""
-        return _get_user_media_dir("XDG_PICTURES_DIR", "~/Pictures")
-
-    @property
-    def user_videos_dir(self) -> str:
-        """:return: videos directory tied to the user, e.g. ``~/Videos``"""
-        return _get_user_media_dir("XDG_VIDEOS_DIR", "~/Videos")
-
-    @property
-    def user_music_dir(self) -> str:
-        """:return: music directory tied to the user, e.g. ``~/Music``"""
-        return _get_user_media_dir("XDG_MUSIC_DIR", "~/Music")
-
-    @property
-    def user_desktop_dir(self) -> str:
-        """:return: desktop directory tied to the user, e.g. ``~/Desktop``"""
-        return _get_user_media_dir("XDG_DESKTOP_DIR", "~/Desktop")
-
-    @property
-    def user_runtime_dir(self) -> str:
-        """
-        :return: runtime directory tied to the user, e.g. ``/run/user/$(id -u)/$appname/$version`` or
-         ``$XDG_RUNTIME_DIR/$appname/$version``.
-
-         For FreeBSD/OpenBSD/NetBSD, it would return ``/var/run/user/$(id -u)/$appname/$version`` if
-         exists, otherwise ``/tmp/runtime-$(id -u)/$appname/$version``, if``$XDG_RUNTIME_DIR``
-         is not set.
-        """
-        path = os.environ.get("XDG_RUNTIME_DIR", "")
-        if not path.strip():
-            if sys.platform.startswith(("freebsd", "openbsd", "netbsd")):
-                path = f"/var/run/user/{getuid()}"
-                if not Path(path).exists():
-                    path = f"/tmp/runtime-{getuid()}"  # noqa: S108
-            else:
-                path = f"/run/user/{getuid()}"
-        return self._append_app_name_and_version(path)
-
-    @property
-    def site_runtime_dir(self) -> str:
-        """
-        :return: runtime directory shared by users, e.g. ``/run/$appname/$version`` or \
-        ``$XDG_RUNTIME_DIR/$appname/$version``.
-
-        Note that this behaves almost exactly like `user_runtime_dir` if ``$XDG_RUNTIME_DIR`` is set, but will
-        fall back to paths associated to the root user instead of a regular logged-in user if it's not set.
-
-        If you wish to ensure that a logged-in root user path is returned e.g. ``/run/user/0``, use `user_runtime_dir`
-        instead.
-
-        For FreeBSD/OpenBSD/NetBSD, it would return ``/var/run/$appname/$version`` if ``$XDG_RUNTIME_DIR`` is not set.
-        """
-        path = os.environ.get("XDG_RUNTIME_DIR", "")
-        if not path.strip():
-            if sys.platform.startswith(("freebsd", "openbsd", "netbsd")):
-                path = "/var/run"
-            else:
-                path = "/run"
-        return self._append_app_name_and_version(path)
-
-    @property
-    def site_data_path(self) -> Path:
-        """:return: data path shared by users. Only return the first item, even if ``multipath`` is set to ``True``"""
-        return self._first_item_as_path_if_multipath(self.site_data_dir)
-
-    @property
-    def site_config_path(self) -> Path:
-        """:return: config path shared by the users, returns the first item, even if ``multipath`` is set to ``True``"""
-        return self._first_item_as_path_if_multipath(self.site_config_dir)
-
-    @property
-    def site_cache_path(self) -> Path:
-        """:return: cache path shared by users. Only return the first item, even if ``multipath`` is set to ``True``"""
-        return self._first_item_as_path_if_multipath(self.site_cache_dir)
-
-    def _first_item_as_path_if_multipath(self, directory: str) -> Path:
-        if self.multipath:
-            # If multipath is True, the first path is returned.
-            directory = directory.split(os.pathsep)[0]
-        return Path(directory)
-
-    def iter_config_dirs(self) -> Iterator[str]:
-        """:yield: all user and site configuration directories."""
-        yield self.user_config_dir
-        yield from self._site_config_dirs
-
-    def iter_data_dirs(self) -> Iterator[str]:
-        """:yield: all user and site data directories."""
-        yield self.user_data_dir
-        yield from self._site_data_dirs
-
-
-def _get_user_media_dir(env_var: str, fallback_tilde_path: str) -> str:
-    media_dir = _get_user_dirs_folder(env_var)
-    if media_dir is None:
-        media_dir = os.environ.get(env_var, "").strip()
-        if not media_dir:
-            media_dir = os.path.expanduser(fallback_tilde_path)  # noqa: PTH111
-
-    return media_dir
-
-
-def _get_user_dirs_folder(key: str) -> str | None:
-    """
-    Return directory from user-dirs.dirs config file.
-
-    See https://freedesktop.org/wiki/Software/xdg-user-dirs/.
-
-    """
-    user_dirs_config_path = Path(Unix().user_config_dir) / "user-dirs.dirs"
-    if user_dirs_config_path.exists():
-        parser = ConfigParser()
-
-        with user_dirs_config_path.open() as stream:
-            # Add fake section header, so ConfigParser doesn't complain
-            parser.read_string(f"[top]\n{stream.read()}")
-
-        if key not in parser["top"]:
-            return None
-
-        path = parser["top"][key].strip('"')
-        # Handle relative home paths
-        return path.replace("$HOME", os.path.expanduser("~"))  # noqa: PTH111
-
-    return None
-
-
-__all__ = [
-    "Unix",
-]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/version.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/version.py
deleted file mode 100644
index 6483ddc..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/version.py
+++ /dev/null
@@ -1,16 +0,0 @@
-# file generated by setuptools_scm
-# don't change, don't track in version control
-TYPE_CHECKING = False
-if TYPE_CHECKING:
-    from typing import Tuple, Union
-    VERSION_TUPLE = Tuple[Union[int, str], ...]
-else:
-    VERSION_TUPLE = object
-
-version: str
-__version__: str
-__version_tuple__: VERSION_TUPLE
-version_tuple: VERSION_TUPLE
-
-__version__ = version = '4.2.2'
-__version_tuple__ = version_tuple = (4, 2, 2)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/windows.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/windows.py
deleted file mode 100644
index d7bc960..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/platformdirs/windows.py
+++ /dev/null
@@ -1,272 +0,0 @@
-"""Windows."""
-
-from __future__ import annotations
-
-import os
-import sys
-from functools import lru_cache
-from typing import TYPE_CHECKING
-
-from .api import PlatformDirsABC
-
-if TYPE_CHECKING:
-    from collections.abc import Callable
-
-
-class Windows(PlatformDirsABC):
-    """
-    `MSDN on where to store app data files `_.
-
-    Makes use of the `appname `, `appauthor
-    `, `version `, `roaming
-    `, `opinion `, `ensure_exists
-    `.
-
-    """
-
-    @property
-    def user_data_dir(self) -> str:
-        """
-        :return: data directory tied to the user, e.g.
-         ``%USERPROFILE%\\AppData\\Local\\$appauthor\\$appname`` (not roaming) or
-         ``%USERPROFILE%\\AppData\\Roaming\\$appauthor\\$appname`` (roaming)
-        """
-        const = "CSIDL_APPDATA" if self.roaming else "CSIDL_LOCAL_APPDATA"
-        path = os.path.normpath(get_win_folder(const))
-        return self._append_parts(path)
-
-    def _append_parts(self, path: str, *, opinion_value: str | None = None) -> str:
-        params = []
-        if self.appname:
-            if self.appauthor is not False:
-                author = self.appauthor or self.appname
-                params.append(author)
-            params.append(self.appname)
-            if opinion_value is not None and self.opinion:
-                params.append(opinion_value)
-            if self.version:
-                params.append(self.version)
-        path = os.path.join(path, *params)  # noqa: PTH118
-        self._optionally_create_directory(path)
-        return path
-
-    @property
-    def site_data_dir(self) -> str:
-        """:return: data directory shared by users, e.g. ``C:\\ProgramData\\$appauthor\\$appname``"""
-        path = os.path.normpath(get_win_folder("CSIDL_COMMON_APPDATA"))
-        return self._append_parts(path)
-
-    @property
-    def user_config_dir(self) -> str:
-        """:return: config directory tied to the user, same as `user_data_dir`"""
-        return self.user_data_dir
-
-    @property
-    def site_config_dir(self) -> str:
-        """:return: config directory shared by the users, same as `site_data_dir`"""
-        return self.site_data_dir
-
-    @property
-    def user_cache_dir(self) -> str:
-        """
-        :return: cache directory tied to the user (if opinionated with ``Cache`` folder within ``$appname``) e.g.
-         ``%USERPROFILE%\\AppData\\Local\\$appauthor\\$appname\\Cache\\$version``
-        """
-        path = os.path.normpath(get_win_folder("CSIDL_LOCAL_APPDATA"))
-        return self._append_parts(path, opinion_value="Cache")
-
-    @property
-    def site_cache_dir(self) -> str:
-        """:return: cache directory shared by users, e.g. ``C:\\ProgramData\\$appauthor\\$appname\\Cache\\$version``"""
-        path = os.path.normpath(get_win_folder("CSIDL_COMMON_APPDATA"))
-        return self._append_parts(path, opinion_value="Cache")
-
-    @property
-    def user_state_dir(self) -> str:
-        """:return: state directory tied to the user, same as `user_data_dir`"""
-        return self.user_data_dir
-
-    @property
-    def user_log_dir(self) -> str:
-        """:return: log directory tied to the user, same as `user_data_dir` if not opinionated else ``Logs`` in it"""
-        path = self.user_data_dir
-        if self.opinion:
-            path = os.path.join(path, "Logs")  # noqa: PTH118
-            self._optionally_create_directory(path)
-        return path
-
-    @property
-    def user_documents_dir(self) -> str:
-        """:return: documents directory tied to the user e.g. ``%USERPROFILE%\\Documents``"""
-        return os.path.normpath(get_win_folder("CSIDL_PERSONAL"))
-
-    @property
-    def user_downloads_dir(self) -> str:
-        """:return: downloads directory tied to the user e.g. ``%USERPROFILE%\\Downloads``"""
-        return os.path.normpath(get_win_folder("CSIDL_DOWNLOADS"))
-
-    @property
-    def user_pictures_dir(self) -> str:
-        """:return: pictures directory tied to the user e.g. ``%USERPROFILE%\\Pictures``"""
-        return os.path.normpath(get_win_folder("CSIDL_MYPICTURES"))
-
-    @property
-    def user_videos_dir(self) -> str:
-        """:return: videos directory tied to the user e.g. ``%USERPROFILE%\\Videos``"""
-        return os.path.normpath(get_win_folder("CSIDL_MYVIDEO"))
-
-    @property
-    def user_music_dir(self) -> str:
-        """:return: music directory tied to the user e.g. ``%USERPROFILE%\\Music``"""
-        return os.path.normpath(get_win_folder("CSIDL_MYMUSIC"))
-
-    @property
-    def user_desktop_dir(self) -> str:
-        """:return: desktop directory tied to the user, e.g. ``%USERPROFILE%\\Desktop``"""
-        return os.path.normpath(get_win_folder("CSIDL_DESKTOPDIRECTORY"))
-
-    @property
-    def user_runtime_dir(self) -> str:
-        """
-        :return: runtime directory tied to the user, e.g.
-         ``%USERPROFILE%\\AppData\\Local\\Temp\\$appauthor\\$appname``
-        """
-        path = os.path.normpath(os.path.join(get_win_folder("CSIDL_LOCAL_APPDATA"), "Temp"))  # noqa: PTH118
-        return self._append_parts(path)
-
-    @property
-    def site_runtime_dir(self) -> str:
-        """:return: runtime directory shared by users, same as `user_runtime_dir`"""
-        return self.user_runtime_dir
-
-
-def get_win_folder_from_env_vars(csidl_name: str) -> str:
-    """Get folder from environment variables."""
-    result = get_win_folder_if_csidl_name_not_env_var(csidl_name)
-    if result is not None:
-        return result
-
-    env_var_name = {
-        "CSIDL_APPDATA": "APPDATA",
-        "CSIDL_COMMON_APPDATA": "ALLUSERSPROFILE",
-        "CSIDL_LOCAL_APPDATA": "LOCALAPPDATA",
-    }.get(csidl_name)
-    if env_var_name is None:
-        msg = f"Unknown CSIDL name: {csidl_name}"
-        raise ValueError(msg)
-    result = os.environ.get(env_var_name)
-    if result is None:
-        msg = f"Unset environment variable: {env_var_name}"
-        raise ValueError(msg)
-    return result
-
-
-def get_win_folder_if_csidl_name_not_env_var(csidl_name: str) -> str | None:
-    """Get a folder for a CSIDL name that does not exist as an environment variable."""
-    if csidl_name == "CSIDL_PERSONAL":
-        return os.path.join(os.path.normpath(os.environ["USERPROFILE"]), "Documents")  # noqa: PTH118
-
-    if csidl_name == "CSIDL_DOWNLOADS":
-        return os.path.join(os.path.normpath(os.environ["USERPROFILE"]), "Downloads")  # noqa: PTH118
-
-    if csidl_name == "CSIDL_MYPICTURES":
-        return os.path.join(os.path.normpath(os.environ["USERPROFILE"]), "Pictures")  # noqa: PTH118
-
-    if csidl_name == "CSIDL_MYVIDEO":
-        return os.path.join(os.path.normpath(os.environ["USERPROFILE"]), "Videos")  # noqa: PTH118
-
-    if csidl_name == "CSIDL_MYMUSIC":
-        return os.path.join(os.path.normpath(os.environ["USERPROFILE"]), "Music")  # noqa: PTH118
-    return None
-
-
-def get_win_folder_from_registry(csidl_name: str) -> str:
-    """
-    Get folder from the registry.
-
-    This is a fallback technique at best. I'm not sure if using the registry for these guarantees us the correct answer
-    for all CSIDL_* names.
-
-    """
-    shell_folder_name = {
-        "CSIDL_APPDATA": "AppData",
-        "CSIDL_COMMON_APPDATA": "Common AppData",
-        "CSIDL_LOCAL_APPDATA": "Local AppData",
-        "CSIDL_PERSONAL": "Personal",
-        "CSIDL_DOWNLOADS": "{374DE290-123F-4565-9164-39C4925E467B}",
-        "CSIDL_MYPICTURES": "My Pictures",
-        "CSIDL_MYVIDEO": "My Video",
-        "CSIDL_MYMUSIC": "My Music",
-    }.get(csidl_name)
-    if shell_folder_name is None:
-        msg = f"Unknown CSIDL name: {csidl_name}"
-        raise ValueError(msg)
-    if sys.platform != "win32":  # only needed for mypy type checker to know that this code runs only on Windows
-        raise NotImplementedError
-    import winreg  # noqa: PLC0415
-
-    key = winreg.OpenKey(winreg.HKEY_CURRENT_USER, r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders")
-    directory, _ = winreg.QueryValueEx(key, shell_folder_name)
-    return str(directory)
-
-
-def get_win_folder_via_ctypes(csidl_name: str) -> str:
-    """Get folder with ctypes."""
-    # There is no 'CSIDL_DOWNLOADS'.
-    # Use 'CSIDL_PROFILE' (40) and append the default folder 'Downloads' instead.
-    # https://learn.microsoft.com/en-us/windows/win32/shell/knownfolderid
-
-    import ctypes  # noqa: PLC0415
-
-    csidl_const = {
-        "CSIDL_APPDATA": 26,
-        "CSIDL_COMMON_APPDATA": 35,
-        "CSIDL_LOCAL_APPDATA": 28,
-        "CSIDL_PERSONAL": 5,
-        "CSIDL_MYPICTURES": 39,
-        "CSIDL_MYVIDEO": 14,
-        "CSIDL_MYMUSIC": 13,
-        "CSIDL_DOWNLOADS": 40,
-        "CSIDL_DESKTOPDIRECTORY": 16,
-    }.get(csidl_name)
-    if csidl_const is None:
-        msg = f"Unknown CSIDL name: {csidl_name}"
-        raise ValueError(msg)
-
-    buf = ctypes.create_unicode_buffer(1024)
-    windll = getattr(ctypes, "windll")  # noqa: B009 # using getattr to avoid false positive with mypy type checker
-    windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf)
-
-    # Downgrade to short path name if it has high-bit chars.
-    if any(ord(c) > 255 for c in buf):  # noqa: PLR2004
-        buf2 = ctypes.create_unicode_buffer(1024)
-        if windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024):
-            buf = buf2
-
-    if csidl_name == "CSIDL_DOWNLOADS":
-        return os.path.join(buf.value, "Downloads")  # noqa: PTH118
-
-    return buf.value
-
-
-def _pick_get_win_folder() -> Callable[[str], str]:
-    try:
-        import ctypes  # noqa: PLC0415
-    except ImportError:
-        pass
-    else:
-        if hasattr(ctypes, "windll"):
-            return get_win_folder_via_ctypes
-    try:
-        import winreg  # noqa: PLC0415, F401
-    except ImportError:
-        return get_win_folder_from_env_vars
-    else:
-        return get_win_folder_from_registry
-
-
-get_win_folder = lru_cache(maxsize=None)(_pick_get_win_folder())
-
-__all__ = [
-    "Windows",
-]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/LICENSE
deleted file mode 100644
index e859590..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/LICENSE
+++ /dev/null
@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2021 Taneli Hukkinen
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/METADATA
deleted file mode 100644
index efd87ec..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/METADATA
+++ /dev/null
@@ -1,206 +0,0 @@
-Metadata-Version: 2.1
-Name: tomli
-Version: 2.0.1
-Summary: A lil' TOML parser
-Keywords: toml
-Author-email: Taneli Hukkinen 
-Requires-Python: >=3.7
-Description-Content-Type: text/markdown
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: MacOS
-Classifier: Operating System :: Microsoft :: Windows
-Classifier: Operating System :: POSIX :: Linux
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: Implementation :: CPython
-Classifier: Programming Language :: Python :: Implementation :: PyPy
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Typing :: Typed
-Project-URL: Changelog, https://github.com/hukkin/tomli/blob/master/CHANGELOG.md
-Project-URL: Homepage, https://github.com/hukkin/tomli
-
-[![Build Status](https://github.com/hukkin/tomli/workflows/Tests/badge.svg?branch=master)](https://github.com/hukkin/tomli/actions?query=workflow%3ATests+branch%3Amaster+event%3Apush)
-[![codecov.io](https://codecov.io/gh/hukkin/tomli/branch/master/graph/badge.svg)](https://codecov.io/gh/hukkin/tomli)
-[![PyPI version](https://img.shields.io/pypi/v/tomli)](https://pypi.org/project/tomli)
-
-# Tomli
-
-> A lil' TOML parser
-
-**Table of Contents**  *generated with [mdformat-toc](https://github.com/hukkin/mdformat-toc)*
-
-
-
-- [Intro](#intro)
-- [Installation](#installation)
-- [Usage](#usage)
-  - [Parse a TOML string](#parse-a-toml-string)
-  - [Parse a TOML file](#parse-a-toml-file)
-  - [Handle invalid TOML](#handle-invalid-toml)
-  - [Construct `decimal.Decimal`s from TOML floats](#construct-decimaldecimals-from-toml-floats)
-- [FAQ](#faq)
-  - [Why this parser?](#why-this-parser)
-  - [Is comment preserving round-trip parsing supported?](#is-comment-preserving-round-trip-parsing-supported)
-  - [Is there a `dumps`, `write` or `encode` function?](#is-there-a-dumps-write-or-encode-function)
-  - [How do TOML types map into Python types?](#how-do-toml-types-map-into-python-types)
-- [Performance](#performance)
-
-
-
-## Intro
-
-Tomli is a Python library for parsing [TOML](https://toml.io).
-Tomli is fully compatible with [TOML v1.0.0](https://toml.io/en/v1.0.0).
-
-## Installation
-
-```bash
-pip install tomli
-```
-
-## Usage
-
-### Parse a TOML string
-
-```python
-import tomli
-
-toml_str = """
-           gretzky = 99
-
-           [kurri]
-           jari = 17
-           """
-
-toml_dict = tomli.loads(toml_str)
-assert toml_dict == {"gretzky": 99, "kurri": {"jari": 17}}
-```
-
-### Parse a TOML file
-
-```python
-import tomli
-
-with open("path_to_file/conf.toml", "rb") as f:
-    toml_dict = tomli.load(f)
-```
-
-The file must be opened in binary mode (with the `"rb"` flag).
-Binary mode will enforce decoding the file as UTF-8 with universal newlines disabled,
-both of which are required to correctly parse TOML.
-
-### Handle invalid TOML
-
-```python
-import tomli
-
-try:
-    toml_dict = tomli.loads("]] this is invalid TOML [[")
-except tomli.TOMLDecodeError:
-    print("Yep, definitely not valid.")
-```
-
-Note that error messages are considered informational only.
-They should not be assumed to stay constant across Tomli versions.
-
-### Construct `decimal.Decimal`s from TOML floats
-
-```python
-from decimal import Decimal
-import tomli
-
-toml_dict = tomli.loads("precision-matters = 0.982492", parse_float=Decimal)
-assert toml_dict["precision-matters"] == Decimal("0.982492")
-```
-
-Note that `decimal.Decimal` can be replaced with another callable that converts a TOML float from string to a Python type.
-The `decimal.Decimal` is, however, a practical choice for use cases where float inaccuracies can not be tolerated.
-
-Illegal types are `dict` and `list`, and their subtypes.
-A `ValueError` will be raised if `parse_float` produces illegal types.
-
-## FAQ
-
-### Why this parser?
-
-- it's lil'
-- pure Python with zero dependencies
-- the fastest pure Python parser [\*](#performance):
-  15x as fast as [tomlkit](https://pypi.org/project/tomlkit/),
-  2.4x as fast as [toml](https://pypi.org/project/toml/)
-- outputs [basic data types](#how-do-toml-types-map-into-python-types) only
-- 100% spec compliant: passes all tests in
-  [a test set](https://github.com/toml-lang/compliance/pull/8)
-  soon to be merged to the official
-  [compliance tests for TOML](https://github.com/toml-lang/compliance)
-  repository
-- thoroughly tested: 100% branch coverage
-
-### Is comment preserving round-trip parsing supported?
-
-No.
-
-The `tomli.loads` function returns a plain `dict` that is populated with builtin types and types from the standard library only.
-Preserving comments requires a custom type to be returned so will not be supported,
-at least not by the `tomli.loads` and `tomli.load` functions.
-
-Look into [TOML Kit](https://github.com/sdispater/tomlkit) if preservation of style is what you need.
-
-### Is there a `dumps`, `write` or `encode` function?
-
-[Tomli-W](https://github.com/hukkin/tomli-w) is the write-only counterpart of Tomli, providing `dump` and `dumps` functions.
-
-The core library does not include write capability, as most TOML use cases are read-only, and Tomli intends to be minimal.
-
-### How do TOML types map into Python types?
-
-| TOML type        | Python type         | Details                                                      |
-| ---------------- | ------------------- | ------------------------------------------------------------ |
-| Document Root    | `dict`              |                                                              |
-| Key              | `str`               |                                                              |
-| String           | `str`               |                                                              |
-| Integer          | `int`               |                                                              |
-| Float            | `float`             |                                                              |
-| Boolean          | `bool`              |                                                              |
-| Offset Date-Time | `datetime.datetime` | `tzinfo` attribute set to an instance of `datetime.timezone` |
-| Local Date-Time  | `datetime.datetime` | `tzinfo` attribute set to `None`                             |
-| Local Date       | `datetime.date`     |                                                              |
-| Local Time       | `datetime.time`     |                                                              |
-| Array            | `list`              |                                                              |
-| Table            | `dict`              |                                                              |
-| Inline Table     | `dict`              |                                                              |
-
-## Performance
-
-The `benchmark/` folder in this repository contains a performance benchmark for comparing the various Python TOML parsers.
-The benchmark can be run with `tox -e benchmark-pypi`.
-Running the benchmark on my personal computer output the following:
-
-```console
-foo@bar:~/dev/tomli$ tox -e benchmark-pypi
-benchmark-pypi installed: attrs==19.3.0,click==7.1.2,pytomlpp==1.0.2,qtoml==0.3.0,rtoml==0.7.0,toml==0.10.2,tomli==1.1.0,tomlkit==0.7.2
-benchmark-pypi run-test-pre: PYTHONHASHSEED='2658546909'
-benchmark-pypi run-test: commands[0] | python -c 'import datetime; print(datetime.date.today())'
-2021-07-23
-benchmark-pypi run-test: commands[1] | python --version
-Python 3.8.10
-benchmark-pypi run-test: commands[2] | python benchmark/run.py
-Parsing data.toml 5000 times:
-------------------------------------------------------
-    parser |  exec time | performance (more is better)
------------+------------+-----------------------------
-     rtoml |    0.901 s | baseline (100%)
-  pytomlpp |     1.08 s | 83.15%
-     tomli |     3.89 s | 23.15%
-      toml |     9.36 s | 9.63%
-     qtoml |     11.5 s | 7.82%
-   tomlkit |     56.8 s | 1.59%
-```
-
-The parsers are ordered from fastest to slowest, using the fastest parser as baseline.
-Tomli performed the best out of all pure Python TOML parsers,
-losing only to pytomlpp (wraps C++) and rtoml (wraps Rust).
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/RECORD
deleted file mode 100644
index 1db8063..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/RECORD
+++ /dev/null
@@ -1,15 +0,0 @@
-tomli-2.0.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-tomli-2.0.1.dist-info/LICENSE,sha256=uAgWsNUwuKzLTCIReDeQmEpuO2GSLCte6S8zcqsnQv4,1072
-tomli-2.0.1.dist-info/METADATA,sha256=zPDceKmPwJGLWtZykrHixL7WVXWmJGzZ1jyRT5lCoPI,8875
-tomli-2.0.1.dist-info/RECORD,,
-tomli-2.0.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tomli-2.0.1.dist-info/WHEEL,sha256=jPMR_Dzkc4X4icQtmz81lnNY_kAsfog7ry7qoRvYLXw,81
-tomli/__init__.py,sha256=JhUwV66DB1g4Hvt1UQCVMdfCu-IgAV8FXmvDU9onxd4,396
-tomli/__pycache__/__init__.cpython-312.pyc,,
-tomli/__pycache__/_parser.cpython-312.pyc,,
-tomli/__pycache__/_re.cpython-312.pyc,,
-tomli/__pycache__/_types.cpython-312.pyc,,
-tomli/_parser.py,sha256=g9-ENaALS-B8dokYpCuzUFalWlog7T-SIYMjLZSWrtM,22633
-tomli/_re.py,sha256=dbjg5ChZT23Ka9z9DHOXfdtSpPwUfdgMXnj8NOoly-w,2943
-tomli/_types.py,sha256=-GTG2VUqkpxwMqzmVO4F7ybKddIbAnuAHXfmWQcTi3Q,254
-tomli/py.typed,sha256=8PjyZ1aVoQpRVvt71muvuq5qE-jTFZkK-GLHkhdebmc,26
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/REQUESTED
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/WHEEL
deleted file mode 100644
index c727d14..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli-2.0.1.dist-info/WHEEL
+++ /dev/null
@@ -1,4 +0,0 @@
-Wheel-Version: 1.0
-Generator: flit 3.6.0
-Root-Is-Purelib: true
-Tag: py3-none-any
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__init__.py
deleted file mode 100644
index 4c6ec97..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__init__.py
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: MIT
-# SPDX-FileCopyrightText: 2021 Taneli Hukkinen
-# Licensed to PSF under a Contributor Agreement.
-
-__all__ = ("loads", "load", "TOMLDecodeError")
-__version__ = "2.0.1"  # DO NOT EDIT THIS LINE MANUALLY. LET bump2version UTILITY DO IT
-
-from ._parser import TOMLDecodeError, load, loads
-
-# Pretend this exception was created here.
-TOMLDecodeError.__module__ = __name__
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 155264e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_parser.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_parser.cpython-312.pyc
deleted file mode 100644
index 68f5b1b..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_parser.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_re.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_re.cpython-312.pyc
deleted file mode 100644
index 2104d5b..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_re.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_types.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_types.cpython-312.pyc
deleted file mode 100644
index c991c6e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/__pycache__/_types.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_parser.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_parser.py
deleted file mode 100644
index f1bb0aa..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_parser.py
+++ /dev/null
@@ -1,691 +0,0 @@
-# SPDX-License-Identifier: MIT
-# SPDX-FileCopyrightText: 2021 Taneli Hukkinen
-# Licensed to PSF under a Contributor Agreement.
-
-from __future__ import annotations
-
-from collections.abc import Iterable
-import string
-from types import MappingProxyType
-from typing import Any, BinaryIO, NamedTuple
-
-from ._re import (
-    RE_DATETIME,
-    RE_LOCALTIME,
-    RE_NUMBER,
-    match_to_datetime,
-    match_to_localtime,
-    match_to_number,
-)
-from ._types import Key, ParseFloat, Pos
-
-ASCII_CTRL = frozenset(chr(i) for i in range(32)) | frozenset(chr(127))
-
-# Neither of these sets include quotation mark or backslash. They are
-# currently handled as separate cases in the parser functions.
-ILLEGAL_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t")
-ILLEGAL_MULTILINE_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t\n")
-
-ILLEGAL_LITERAL_STR_CHARS = ILLEGAL_BASIC_STR_CHARS
-ILLEGAL_MULTILINE_LITERAL_STR_CHARS = ILLEGAL_MULTILINE_BASIC_STR_CHARS
-
-ILLEGAL_COMMENT_CHARS = ILLEGAL_BASIC_STR_CHARS
-
-TOML_WS = frozenset(" \t")
-TOML_WS_AND_NEWLINE = TOML_WS | frozenset("\n")
-BARE_KEY_CHARS = frozenset(string.ascii_letters + string.digits + "-_")
-KEY_INITIAL_CHARS = BARE_KEY_CHARS | frozenset("\"'")
-HEXDIGIT_CHARS = frozenset(string.hexdigits)
-
-BASIC_STR_ESCAPE_REPLACEMENTS = MappingProxyType(
-    {
-        "\\b": "\u0008",  # backspace
-        "\\t": "\u0009",  # tab
-        "\\n": "\u000A",  # linefeed
-        "\\f": "\u000C",  # form feed
-        "\\r": "\u000D",  # carriage return
-        '\\"': "\u0022",  # quote
-        "\\\\": "\u005C",  # backslash
-    }
-)
-
-
-class TOMLDecodeError(ValueError):
-    """An error raised if a document is not valid TOML."""
-
-
-def load(__fp: BinaryIO, *, parse_float: ParseFloat = float) -> dict[str, Any]:
-    """Parse TOML from a binary file object."""
-    b = __fp.read()
-    try:
-        s = b.decode()
-    except AttributeError:
-        raise TypeError(
-            "File must be opened in binary mode, e.g. use `open('foo.toml', 'rb')`"
-        ) from None
-    return loads(s, parse_float=parse_float)
-
-
-def loads(__s: str, *, parse_float: ParseFloat = float) -> dict[str, Any]:  # noqa: C901
-    """Parse TOML from a string."""
-
-    # The spec allows converting "\r\n" to "\n", even in string
-    # literals. Let's do so to simplify parsing.
-    src = __s.replace("\r\n", "\n")
-    pos = 0
-    out = Output(NestedDict(), Flags())
-    header: Key = ()
-    parse_float = make_safe_parse_float(parse_float)
-
-    # Parse one statement at a time
-    # (typically means one line in TOML source)
-    while True:
-        # 1. Skip line leading whitespace
-        pos = skip_chars(src, pos, TOML_WS)
-
-        # 2. Parse rules. Expect one of the following:
-        #    - end of file
-        #    - end of line
-        #    - comment
-        #    - key/value pair
-        #    - append dict to list (and move to its namespace)
-        #    - create dict (and move to its namespace)
-        # Skip trailing whitespace when applicable.
-        try:
-            char = src[pos]
-        except IndexError:
-            break
-        if char == "\n":
-            pos += 1
-            continue
-        if char in KEY_INITIAL_CHARS:
-            pos = key_value_rule(src, pos, out, header, parse_float)
-            pos = skip_chars(src, pos, TOML_WS)
-        elif char == "[":
-            try:
-                second_char: str | None = src[pos + 1]
-            except IndexError:
-                second_char = None
-            out.flags.finalize_pending()
-            if second_char == "[":
-                pos, header = create_list_rule(src, pos, out)
-            else:
-                pos, header = create_dict_rule(src, pos, out)
-            pos = skip_chars(src, pos, TOML_WS)
-        elif char != "#":
-            raise suffixed_err(src, pos, "Invalid statement")
-
-        # 3. Skip comment
-        pos = skip_comment(src, pos)
-
-        # 4. Expect end of line or end of file
-        try:
-            char = src[pos]
-        except IndexError:
-            break
-        if char != "\n":
-            raise suffixed_err(
-                src, pos, "Expected newline or end of document after a statement"
-            )
-        pos += 1
-
-    return out.data.dict
-
-
-class Flags:
-    """Flags that map to parsed keys/namespaces."""
-
-    # Marks an immutable namespace (inline array or inline table).
-    FROZEN = 0
-    # Marks a nest that has been explicitly created and can no longer
-    # be opened using the "[table]" syntax.
-    EXPLICIT_NEST = 1
-
-    def __init__(self) -> None:
-        self._flags: dict[str, dict] = {}
-        self._pending_flags: set[tuple[Key, int]] = set()
-
-    def add_pending(self, key: Key, flag: int) -> None:
-        self._pending_flags.add((key, flag))
-
-    def finalize_pending(self) -> None:
-        for key, flag in self._pending_flags:
-            self.set(key, flag, recursive=False)
-        self._pending_flags.clear()
-
-    def unset_all(self, key: Key) -> None:
-        cont = self._flags
-        for k in key[:-1]:
-            if k not in cont:
-                return
-            cont = cont[k]["nested"]
-        cont.pop(key[-1], None)
-
-    def set(self, key: Key, flag: int, *, recursive: bool) -> None:  # noqa: A003
-        cont = self._flags
-        key_parent, key_stem = key[:-1], key[-1]
-        for k in key_parent:
-            if k not in cont:
-                cont[k] = {"flags": set(), "recursive_flags": set(), "nested": {}}
-            cont = cont[k]["nested"]
-        if key_stem not in cont:
-            cont[key_stem] = {"flags": set(), "recursive_flags": set(), "nested": {}}
-        cont[key_stem]["recursive_flags" if recursive else "flags"].add(flag)
-
-    def is_(self, key: Key, flag: int) -> bool:
-        if not key:
-            return False  # document root has no flags
-        cont = self._flags
-        for k in key[:-1]:
-            if k not in cont:
-                return False
-            inner_cont = cont[k]
-            if flag in inner_cont["recursive_flags"]:
-                return True
-            cont = inner_cont["nested"]
-        key_stem = key[-1]
-        if key_stem in cont:
-            cont = cont[key_stem]
-            return flag in cont["flags"] or flag in cont["recursive_flags"]
-        return False
-
-
-class NestedDict:
-    def __init__(self) -> None:
-        # The parsed content of the TOML document
-        self.dict: dict[str, Any] = {}
-
-    def get_or_create_nest(
-        self,
-        key: Key,
-        *,
-        access_lists: bool = True,
-    ) -> dict:
-        cont: Any = self.dict
-        for k in key:
-            if k not in cont:
-                cont[k] = {}
-            cont = cont[k]
-            if access_lists and isinstance(cont, list):
-                cont = cont[-1]
-            if not isinstance(cont, dict):
-                raise KeyError("There is no nest behind this key")
-        return cont
-
-    def append_nest_to_list(self, key: Key) -> None:
-        cont = self.get_or_create_nest(key[:-1])
-        last_key = key[-1]
-        if last_key in cont:
-            list_ = cont[last_key]
-            if not isinstance(list_, list):
-                raise KeyError("An object other than list found behind this key")
-            list_.append({})
-        else:
-            cont[last_key] = [{}]
-
-
-class Output(NamedTuple):
-    data: NestedDict
-    flags: Flags
-
-
-def skip_chars(src: str, pos: Pos, chars: Iterable[str]) -> Pos:
-    try:
-        while src[pos] in chars:
-            pos += 1
-    except IndexError:
-        pass
-    return pos
-
-
-def skip_until(
-    src: str,
-    pos: Pos,
-    expect: str,
-    *,
-    error_on: frozenset[str],
-    error_on_eof: bool,
-) -> Pos:
-    try:
-        new_pos = src.index(expect, pos)
-    except ValueError:
-        new_pos = len(src)
-        if error_on_eof:
-            raise suffixed_err(src, new_pos, f"Expected {expect!r}") from None
-
-    if not error_on.isdisjoint(src[pos:new_pos]):
-        while src[pos] not in error_on:
-            pos += 1
-        raise suffixed_err(src, pos, f"Found invalid character {src[pos]!r}")
-    return new_pos
-
-
-def skip_comment(src: str, pos: Pos) -> Pos:
-    try:
-        char: str | None = src[pos]
-    except IndexError:
-        char = None
-    if char == "#":
-        return skip_until(
-            src, pos + 1, "\n", error_on=ILLEGAL_COMMENT_CHARS, error_on_eof=False
-        )
-    return pos
-
-
-def skip_comments_and_array_ws(src: str, pos: Pos) -> Pos:
-    while True:
-        pos_before_skip = pos
-        pos = skip_chars(src, pos, TOML_WS_AND_NEWLINE)
-        pos = skip_comment(src, pos)
-        if pos == pos_before_skip:
-            return pos
-
-
-def create_dict_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]:
-    pos += 1  # Skip "["
-    pos = skip_chars(src, pos, TOML_WS)
-    pos, key = parse_key(src, pos)
-
-    if out.flags.is_(key, Flags.EXPLICIT_NEST) or out.flags.is_(key, Flags.FROZEN):
-        raise suffixed_err(src, pos, f"Cannot declare {key} twice")
-    out.flags.set(key, Flags.EXPLICIT_NEST, recursive=False)
-    try:
-        out.data.get_or_create_nest(key)
-    except KeyError:
-        raise suffixed_err(src, pos, "Cannot overwrite a value") from None
-
-    if not src.startswith("]", pos):
-        raise suffixed_err(src, pos, "Expected ']' at the end of a table declaration")
-    return pos + 1, key
-
-
-def create_list_rule(src: str, pos: Pos, out: Output) -> tuple[Pos, Key]:
-    pos += 2  # Skip "[["
-    pos = skip_chars(src, pos, TOML_WS)
-    pos, key = parse_key(src, pos)
-
-    if out.flags.is_(key, Flags.FROZEN):
-        raise suffixed_err(src, pos, f"Cannot mutate immutable namespace {key}")
-    # Free the namespace now that it points to another empty list item...
-    out.flags.unset_all(key)
-    # ...but this key precisely is still prohibited from table declaration
-    out.flags.set(key, Flags.EXPLICIT_NEST, recursive=False)
-    try:
-        out.data.append_nest_to_list(key)
-    except KeyError:
-        raise suffixed_err(src, pos, "Cannot overwrite a value") from None
-
-    if not src.startswith("]]", pos):
-        raise suffixed_err(src, pos, "Expected ']]' at the end of an array declaration")
-    return pos + 2, key
-
-
-def key_value_rule(
-    src: str, pos: Pos, out: Output, header: Key, parse_float: ParseFloat
-) -> Pos:
-    pos, key, value = parse_key_value_pair(src, pos, parse_float)
-    key_parent, key_stem = key[:-1], key[-1]
-    abs_key_parent = header + key_parent
-
-    relative_path_cont_keys = (header + key[:i] for i in range(1, len(key)))
-    for cont_key in relative_path_cont_keys:
-        # Check that dotted key syntax does not redefine an existing table
-        if out.flags.is_(cont_key, Flags.EXPLICIT_NEST):
-            raise suffixed_err(src, pos, f"Cannot redefine namespace {cont_key}")
-        # Containers in the relative path can't be opened with the table syntax or
-        # dotted key/value syntax in following table sections.
-        out.flags.add_pending(cont_key, Flags.EXPLICIT_NEST)
-
-    if out.flags.is_(abs_key_parent, Flags.FROZEN):
-        raise suffixed_err(
-            src, pos, f"Cannot mutate immutable namespace {abs_key_parent}"
-        )
-
-    try:
-        nest = out.data.get_or_create_nest(abs_key_parent)
-    except KeyError:
-        raise suffixed_err(src, pos, "Cannot overwrite a value") from None
-    if key_stem in nest:
-        raise suffixed_err(src, pos, "Cannot overwrite a value")
-    # Mark inline table and array namespaces recursively immutable
-    if isinstance(value, (dict, list)):
-        out.flags.set(header + key, Flags.FROZEN, recursive=True)
-    nest[key_stem] = value
-    return pos
-
-
-def parse_key_value_pair(
-    src: str, pos: Pos, parse_float: ParseFloat
-) -> tuple[Pos, Key, Any]:
-    pos, key = parse_key(src, pos)
-    try:
-        char: str | None = src[pos]
-    except IndexError:
-        char = None
-    if char != "=":
-        raise suffixed_err(src, pos, "Expected '=' after a key in a key/value pair")
-    pos += 1
-    pos = skip_chars(src, pos, TOML_WS)
-    pos, value = parse_value(src, pos, parse_float)
-    return pos, key, value
-
-
-def parse_key(src: str, pos: Pos) -> tuple[Pos, Key]:
-    pos, key_part = parse_key_part(src, pos)
-    key: Key = (key_part,)
-    pos = skip_chars(src, pos, TOML_WS)
-    while True:
-        try:
-            char: str | None = src[pos]
-        except IndexError:
-            char = None
-        if char != ".":
-            return pos, key
-        pos += 1
-        pos = skip_chars(src, pos, TOML_WS)
-        pos, key_part = parse_key_part(src, pos)
-        key += (key_part,)
-        pos = skip_chars(src, pos, TOML_WS)
-
-
-def parse_key_part(src: str, pos: Pos) -> tuple[Pos, str]:
-    try:
-        char: str | None = src[pos]
-    except IndexError:
-        char = None
-    if char in BARE_KEY_CHARS:
-        start_pos = pos
-        pos = skip_chars(src, pos, BARE_KEY_CHARS)
-        return pos, src[start_pos:pos]
-    if char == "'":
-        return parse_literal_str(src, pos)
-    if char == '"':
-        return parse_one_line_basic_str(src, pos)
-    raise suffixed_err(src, pos, "Invalid initial character for a key part")
-
-
-def parse_one_line_basic_str(src: str, pos: Pos) -> tuple[Pos, str]:
-    pos += 1
-    return parse_basic_str(src, pos, multiline=False)
-
-
-def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, list]:
-    pos += 1
-    array: list = []
-
-    pos = skip_comments_and_array_ws(src, pos)
-    if src.startswith("]", pos):
-        return pos + 1, array
-    while True:
-        pos, val = parse_value(src, pos, parse_float)
-        array.append(val)
-        pos = skip_comments_and_array_ws(src, pos)
-
-        c = src[pos : pos + 1]
-        if c == "]":
-            return pos + 1, array
-        if c != ",":
-            raise suffixed_err(src, pos, "Unclosed array")
-        pos += 1
-
-        pos = skip_comments_and_array_ws(src, pos)
-        if src.startswith("]", pos):
-            return pos + 1, array
-
-
-def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> tuple[Pos, dict]:
-    pos += 1
-    nested_dict = NestedDict()
-    flags = Flags()
-
-    pos = skip_chars(src, pos, TOML_WS)
-    if src.startswith("}", pos):
-        return pos + 1, nested_dict.dict
-    while True:
-        pos, key, value = parse_key_value_pair(src, pos, parse_float)
-        key_parent, key_stem = key[:-1], key[-1]
-        if flags.is_(key, Flags.FROZEN):
-            raise suffixed_err(src, pos, f"Cannot mutate immutable namespace {key}")
-        try:
-            nest = nested_dict.get_or_create_nest(key_parent, access_lists=False)
-        except KeyError:
-            raise suffixed_err(src, pos, "Cannot overwrite a value") from None
-        if key_stem in nest:
-            raise suffixed_err(src, pos, f"Duplicate inline table key {key_stem!r}")
-        nest[key_stem] = value
-        pos = skip_chars(src, pos, TOML_WS)
-        c = src[pos : pos + 1]
-        if c == "}":
-            return pos + 1, nested_dict.dict
-        if c != ",":
-            raise suffixed_err(src, pos, "Unclosed inline table")
-        if isinstance(value, (dict, list)):
-            flags.set(key, Flags.FROZEN, recursive=True)
-        pos += 1
-        pos = skip_chars(src, pos, TOML_WS)
-
-
-def parse_basic_str_escape(
-    src: str, pos: Pos, *, multiline: bool = False
-) -> tuple[Pos, str]:
-    escape_id = src[pos : pos + 2]
-    pos += 2
-    if multiline and escape_id in {"\\ ", "\\\t", "\\\n"}:
-        # Skip whitespace until next non-whitespace character or end of
-        # the doc. Error if non-whitespace is found before newline.
-        if escape_id != "\\\n":
-            pos = skip_chars(src, pos, TOML_WS)
-            try:
-                char = src[pos]
-            except IndexError:
-                return pos, ""
-            if char != "\n":
-                raise suffixed_err(src, pos, "Unescaped '\\' in a string")
-            pos += 1
-        pos = skip_chars(src, pos, TOML_WS_AND_NEWLINE)
-        return pos, ""
-    if escape_id == "\\u":
-        return parse_hex_char(src, pos, 4)
-    if escape_id == "\\U":
-        return parse_hex_char(src, pos, 8)
-    try:
-        return pos, BASIC_STR_ESCAPE_REPLACEMENTS[escape_id]
-    except KeyError:
-        raise suffixed_err(src, pos, "Unescaped '\\' in a string") from None
-
-
-def parse_basic_str_escape_multiline(src: str, pos: Pos) -> tuple[Pos, str]:
-    return parse_basic_str_escape(src, pos, multiline=True)
-
-
-def parse_hex_char(src: str, pos: Pos, hex_len: int) -> tuple[Pos, str]:
-    hex_str = src[pos : pos + hex_len]
-    if len(hex_str) != hex_len or not HEXDIGIT_CHARS.issuperset(hex_str):
-        raise suffixed_err(src, pos, "Invalid hex value")
-    pos += hex_len
-    hex_int = int(hex_str, 16)
-    if not is_unicode_scalar_value(hex_int):
-        raise suffixed_err(src, pos, "Escaped character is not a Unicode scalar value")
-    return pos, chr(hex_int)
-
-
-def parse_literal_str(src: str, pos: Pos) -> tuple[Pos, str]:
-    pos += 1  # Skip starting apostrophe
-    start_pos = pos
-    pos = skip_until(
-        src, pos, "'", error_on=ILLEGAL_LITERAL_STR_CHARS, error_on_eof=True
-    )
-    return pos + 1, src[start_pos:pos]  # Skip ending apostrophe
-
-
-def parse_multiline_str(src: str, pos: Pos, *, literal: bool) -> tuple[Pos, str]:
-    pos += 3
-    if src.startswith("\n", pos):
-        pos += 1
-
-    if literal:
-        delim = "'"
-        end_pos = skip_until(
-            src,
-            pos,
-            "'''",
-            error_on=ILLEGAL_MULTILINE_LITERAL_STR_CHARS,
-            error_on_eof=True,
-        )
-        result = src[pos:end_pos]
-        pos = end_pos + 3
-    else:
-        delim = '"'
-        pos, result = parse_basic_str(src, pos, multiline=True)
-
-    # Add at maximum two extra apostrophes/quotes if the end sequence
-    # is 4 or 5 chars long instead of just 3.
-    if not src.startswith(delim, pos):
-        return pos, result
-    pos += 1
-    if not src.startswith(delim, pos):
-        return pos, result + delim
-    pos += 1
-    return pos, result + (delim * 2)
-
-
-def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> tuple[Pos, str]:
-    if multiline:
-        error_on = ILLEGAL_MULTILINE_BASIC_STR_CHARS
-        parse_escapes = parse_basic_str_escape_multiline
-    else:
-        error_on = ILLEGAL_BASIC_STR_CHARS
-        parse_escapes = parse_basic_str_escape
-    result = ""
-    start_pos = pos
-    while True:
-        try:
-            char = src[pos]
-        except IndexError:
-            raise suffixed_err(src, pos, "Unterminated string") from None
-        if char == '"':
-            if not multiline:
-                return pos + 1, result + src[start_pos:pos]
-            if src.startswith('"""', pos):
-                return pos + 3, result + src[start_pos:pos]
-            pos += 1
-            continue
-        if char == "\\":
-            result += src[start_pos:pos]
-            pos, parsed_escape = parse_escapes(src, pos)
-            result += parsed_escape
-            start_pos = pos
-            continue
-        if char in error_on:
-            raise suffixed_err(src, pos, f"Illegal character {char!r}")
-        pos += 1
-
-
-def parse_value(  # noqa: C901
-    src: str, pos: Pos, parse_float: ParseFloat
-) -> tuple[Pos, Any]:
-    try:
-        char: str | None = src[pos]
-    except IndexError:
-        char = None
-
-    # IMPORTANT: order conditions based on speed of checking and likelihood
-
-    # Basic strings
-    if char == '"':
-        if src.startswith('"""', pos):
-            return parse_multiline_str(src, pos, literal=False)
-        return parse_one_line_basic_str(src, pos)
-
-    # Literal strings
-    if char == "'":
-        if src.startswith("'''", pos):
-            return parse_multiline_str(src, pos, literal=True)
-        return parse_literal_str(src, pos)
-
-    # Booleans
-    if char == "t":
-        if src.startswith("true", pos):
-            return pos + 4, True
-    if char == "f":
-        if src.startswith("false", pos):
-            return pos + 5, False
-
-    # Arrays
-    if char == "[":
-        return parse_array(src, pos, parse_float)
-
-    # Inline tables
-    if char == "{":
-        return parse_inline_table(src, pos, parse_float)
-
-    # Dates and times
-    datetime_match = RE_DATETIME.match(src, pos)
-    if datetime_match:
-        try:
-            datetime_obj = match_to_datetime(datetime_match)
-        except ValueError as e:
-            raise suffixed_err(src, pos, "Invalid date or datetime") from e
-        return datetime_match.end(), datetime_obj
-    localtime_match = RE_LOCALTIME.match(src, pos)
-    if localtime_match:
-        return localtime_match.end(), match_to_localtime(localtime_match)
-
-    # Integers and "normal" floats.
-    # The regex will greedily match any type starting with a decimal
-    # char, so needs to be located after handling of dates and times.
-    number_match = RE_NUMBER.match(src, pos)
-    if number_match:
-        return number_match.end(), match_to_number(number_match, parse_float)
-
-    # Special floats
-    first_three = src[pos : pos + 3]
-    if first_three in {"inf", "nan"}:
-        return pos + 3, parse_float(first_three)
-    first_four = src[pos : pos + 4]
-    if first_four in {"-inf", "+inf", "-nan", "+nan"}:
-        return pos + 4, parse_float(first_four)
-
-    raise suffixed_err(src, pos, "Invalid value")
-
-
-def suffixed_err(src: str, pos: Pos, msg: str) -> TOMLDecodeError:
-    """Return a `TOMLDecodeError` where error message is suffixed with
-    coordinates in source."""
-
-    def coord_repr(src: str, pos: Pos) -> str:
-        if pos >= len(src):
-            return "end of document"
-        line = src.count("\n", 0, pos) + 1
-        if line == 1:
-            column = pos + 1
-        else:
-            column = pos - src.rindex("\n", 0, pos)
-        return f"line {line}, column {column}"
-
-    return TOMLDecodeError(f"{msg} (at {coord_repr(src, pos)})")
-
-
-def is_unicode_scalar_value(codepoint: int) -> bool:
-    return (0 <= codepoint <= 55295) or (57344 <= codepoint <= 1114111)
-
-
-def make_safe_parse_float(parse_float: ParseFloat) -> ParseFloat:
-    """A decorator to make `parse_float` safe.
-
-    `parse_float` must not return dicts or lists, because these types
-    would be mixed with parsed TOML tables and arrays, thus confusing
-    the parser. The returned decorated callable raises `ValueError`
-    instead of returning illegal types.
-    """
-    # The default `float` callable never returns illegal types. Optimize it.
-    if parse_float is float:  # type: ignore[comparison-overlap]
-        return float
-
-    def safe_parse_float(float_str: str) -> Any:
-        float_value = parse_float(float_str)
-        if isinstance(float_value, (dict, list)):
-            raise ValueError("parse_float must not return dicts or lists")
-        return float_value
-
-    return safe_parse_float
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_re.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_re.py
deleted file mode 100644
index 994bb74..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_re.py
+++ /dev/null
@@ -1,107 +0,0 @@
-# SPDX-License-Identifier: MIT
-# SPDX-FileCopyrightText: 2021 Taneli Hukkinen
-# Licensed to PSF under a Contributor Agreement.
-
-from __future__ import annotations
-
-from datetime import date, datetime, time, timedelta, timezone, tzinfo
-from functools import lru_cache
-import re
-from typing import Any
-
-from ._types import ParseFloat
-
-# E.g.
-# - 00:32:00.999999
-# - 00:32:00
-_TIME_RE_STR = r"([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(?:\.([0-9]{1,6})[0-9]*)?"
-
-RE_NUMBER = re.compile(
-    r"""
-0
-(?:
-    x[0-9A-Fa-f](?:_?[0-9A-Fa-f])*   # hex
-    |
-    b[01](?:_?[01])*                 # bin
-    |
-    o[0-7](?:_?[0-7])*               # oct
-)
-|
-[+-]?(?:0|[1-9](?:_?[0-9])*)         # dec, integer part
-(?P
-    (?:\.[0-9](?:_?[0-9])*)?         # optional fractional part
-    (?:[eE][+-]?[0-9](?:_?[0-9])*)?  # optional exponent part
-)
-""",
-    flags=re.VERBOSE,
-)
-RE_LOCALTIME = re.compile(_TIME_RE_STR)
-RE_DATETIME = re.compile(
-    rf"""
-([0-9]{{4}})-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01])  # date, e.g. 1988-10-27
-(?:
-    [Tt ]
-    {_TIME_RE_STR}
-    (?:([Zz])|([+-])([01][0-9]|2[0-3]):([0-5][0-9]))?  # optional time offset
-)?
-""",
-    flags=re.VERBOSE,
-)
-
-
-def match_to_datetime(match: re.Match) -> datetime | date:
-    """Convert a `RE_DATETIME` match to `datetime.datetime` or `datetime.date`.
-
-    Raises ValueError if the match does not correspond to a valid date
-    or datetime.
-    """
-    (
-        year_str,
-        month_str,
-        day_str,
-        hour_str,
-        minute_str,
-        sec_str,
-        micros_str,
-        zulu_time,
-        offset_sign_str,
-        offset_hour_str,
-        offset_minute_str,
-    ) = match.groups()
-    year, month, day = int(year_str), int(month_str), int(day_str)
-    if hour_str is None:
-        return date(year, month, day)
-    hour, minute, sec = int(hour_str), int(minute_str), int(sec_str)
-    micros = int(micros_str.ljust(6, "0")) if micros_str else 0
-    if offset_sign_str:
-        tz: tzinfo | None = cached_tz(
-            offset_hour_str, offset_minute_str, offset_sign_str
-        )
-    elif zulu_time:
-        tz = timezone.utc
-    else:  # local date-time
-        tz = None
-    return datetime(year, month, day, hour, minute, sec, micros, tzinfo=tz)
-
-
-@lru_cache(maxsize=None)
-def cached_tz(hour_str: str, minute_str: str, sign_str: str) -> timezone:
-    sign = 1 if sign_str == "+" else -1
-    return timezone(
-        timedelta(
-            hours=sign * int(hour_str),
-            minutes=sign * int(minute_str),
-        )
-    )
-
-
-def match_to_localtime(match: re.Match) -> time:
-    hour_str, minute_str, sec_str, micros_str = match.groups()
-    micros = int(micros_str.ljust(6, "0")) if micros_str else 0
-    return time(int(hour_str), int(minute_str), int(sec_str), micros)
-
-
-def match_to_number(match: re.Match, parse_float: ParseFloat) -> Any:
-    if match.group("floatpart"):
-        return parse_float(match.group())
-    return int(match.group(), 0)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_types.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_types.py
deleted file mode 100644
index d949412..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/tomli/_types.py
+++ /dev/null
@@ -1,10 +0,0 @@
-# SPDX-License-Identifier: MIT
-# SPDX-FileCopyrightText: 2021 Taneli Hukkinen
-# Licensed to PSF under a Contributor Agreement.
-
-from typing import Any, Callable, Tuple
-
-# Type annotations
-ParseFloat = Callable[[str], Any]
-Key = Tuple[str, ...]
-Pos = int
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/LICENSE
deleted file mode 100644
index 07806f8..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/LICENSE
+++ /dev/null
@@ -1,19 +0,0 @@
-This is the MIT license: http://www.opensource.org/licenses/mit-license.php
-
-Copyright (c) Alex Grönholm
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this
-software and associated documentation files (the "Software"), to deal in the Software
-without restriction, including without limitation the rights to use, copy, modify, merge,
-publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons
-to whom the Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all copies or
-substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
-INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
-PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
-FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
-OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
-DEALINGS IN THE SOFTWARE.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/METADATA
deleted file mode 100644
index 6e5750b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/METADATA
+++ /dev/null
@@ -1,81 +0,0 @@
-Metadata-Version: 2.1
-Name: typeguard
-Version: 4.3.0
-Summary: Run-time type checker for Python
-Author-email: Alex Grönholm 
-License: MIT
-Project-URL: Documentation, https://typeguard.readthedocs.io/en/latest/
-Project-URL: Change log, https://typeguard.readthedocs.io/en/latest/versionhistory.html
-Project-URL: Source code, https://github.com/agronholm/typeguard
-Project-URL: Issue tracker, https://github.com/agronholm/typeguard/issues
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.8
-Description-Content-Type: text/x-rst
-License-File: LICENSE
-Requires-Dist: typing-extensions >=4.10.0
-Requires-Dist: importlib-metadata >=3.6 ; python_version < "3.10"
-Provides-Extra: doc
-Requires-Dist: packaging ; extra == 'doc'
-Requires-Dist: Sphinx >=7 ; extra == 'doc'
-Requires-Dist: sphinx-autodoc-typehints >=1.2.0 ; extra == 'doc'
-Requires-Dist: sphinx-rtd-theme >=1.3.0 ; extra == 'doc'
-Provides-Extra: test
-Requires-Dist: coverage[toml] >=7 ; extra == 'test'
-Requires-Dist: pytest >=7 ; extra == 'test'
-Requires-Dist: mypy >=1.2.0 ; (platform_python_implementation != "PyPy") and extra == 'test'
-
-.. image:: https://github.com/agronholm/typeguard/actions/workflows/test.yml/badge.svg
-  :target: https://github.com/agronholm/typeguard/actions/workflows/test.yml
-  :alt: Build Status
-.. image:: https://coveralls.io/repos/agronholm/typeguard/badge.svg?branch=master&service=github
-  :target: https://coveralls.io/github/agronholm/typeguard?branch=master
-  :alt: Code Coverage
-.. image:: https://readthedocs.org/projects/typeguard/badge/?version=latest
-  :target: https://typeguard.readthedocs.io/en/latest/?badge=latest
-  :alt: Documentation
-
-This library provides run-time type checking for functions defined with
-`PEP 484 `_ argument (and return) type
-annotations, and any arbitrary objects. It can be used together with static type
-checkers as an additional layer of type safety, to catch type violations that could only
-be detected at run time.
-
-Two principal ways to do type checking are provided:
-
-#. The ``check_type`` function:
-
-   * like ``isinstance()``, but supports arbitrary type annotations (within limits)
-   * can be used as a ``cast()`` replacement, but with actual checking of the value
-#. Code instrumentation:
-
-   * entire modules, or individual functions (via ``@typechecked``) are recompiled, with
-     type checking code injected into them
-   * automatically checks function arguments, return values and assignments to annotated
-     local variables
-   * for generator functions (regular and async), checks yield and send values
-   * requires the original source code of the instrumented module(s) to be accessible
-
-Two options are provided for code instrumentation:
-
-#. the ``@typechecked`` function:
-
-   * can be applied to functions individually
-#. the import hook (``typeguard.install_import_hook()``):
-
-   * automatically instruments targeted modules on import
-   * no manual code changes required in the target modules
-   * requires the import hook to be installed before the targeted modules are imported
-   * may clash with other import hooks
-
-See the documentation_ for further information.
-
-.. _documentation: https://typeguard.readthedocs.io/en/latest/
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/RECORD
deleted file mode 100644
index 801e733..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/RECORD
+++ /dev/null
@@ -1,34 +0,0 @@
-typeguard-4.3.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-typeguard-4.3.0.dist-info/LICENSE,sha256=YWP3mH37ONa8MgzitwsvArhivEESZRbVUu8c1DJH51g,1130
-typeguard-4.3.0.dist-info/METADATA,sha256=z2dcHAp0TwhYCFU5Deh8x31nazElgujUz9tbuP0pjSE,3717
-typeguard-4.3.0.dist-info/RECORD,,
-typeguard-4.3.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-typeguard-4.3.0.dist-info/entry_points.txt,sha256=qp7NQ1aLtiSgMQqo6gWlfGpy0IIXzoMJmeQTLpzqFZQ,48
-typeguard-4.3.0.dist-info/top_level.txt,sha256=4z28AhuDodwRS_c1J_l8H51t5QuwfTseskYzlxp6grs,10
-typeguard/__init__.py,sha256=Onh4w38elPCjtlcU3JY9k3h70NjsxXIkAflmQn-Z0FY,2071
-typeguard/__pycache__/__init__.cpython-312.pyc,,
-typeguard/__pycache__/_checkers.cpython-312.pyc,,
-typeguard/__pycache__/_config.cpython-312.pyc,,
-typeguard/__pycache__/_decorators.cpython-312.pyc,,
-typeguard/__pycache__/_exceptions.cpython-312.pyc,,
-typeguard/__pycache__/_functions.cpython-312.pyc,,
-typeguard/__pycache__/_importhook.cpython-312.pyc,,
-typeguard/__pycache__/_memo.cpython-312.pyc,,
-typeguard/__pycache__/_pytest_plugin.cpython-312.pyc,,
-typeguard/__pycache__/_suppression.cpython-312.pyc,,
-typeguard/__pycache__/_transformer.cpython-312.pyc,,
-typeguard/__pycache__/_union_transformer.cpython-312.pyc,,
-typeguard/__pycache__/_utils.cpython-312.pyc,,
-typeguard/_checkers.py,sha256=JRrgKicdOEfIBoNEtegYCEIlhpad-a1u1Em7GCj0WCI,31360
-typeguard/_config.py,sha256=nIz8QwDa-oFO3L9O8_6srzlmd99pSby2wOM4Wb7F_B0,2846
-typeguard/_decorators.py,sha256=v6dsIeWvPhExGLP_wXF-RmDUyjZf_Ak28g7gBJ_v0-0,9033
-typeguard/_exceptions.py,sha256=ZIPeiV-FBd5Emw2EaWd2Fvlsrwi4ocwT2fVGBIAtHcQ,1121
-typeguard/_functions.py,sha256=ibgSAKa5ptIm1eR9ARG0BSozAFJPFNASZqhPVyQeqig,10393
-typeguard/_importhook.py,sha256=ugjCDvFcdWMU7UugqlJG91IpVNpEIxtRr-99s0h1k7M,6389
-typeguard/_memo.py,sha256=1juQV_vxnD2JYKbSrebiQuj4oKHz6n67v9pYA-CCISg,1303
-typeguard/_pytest_plugin.py,sha256=-fcSqkv54rIfIF8pDavY5YQPkj4OX8GMt_lL7CQSD4I,4416
-typeguard/_suppression.py,sha256=VQfzxcwIbu3if0f7VBkKM7hkYOA7tNFw9a7jMBsmMg4,2266
-typeguard/_transformer.py,sha256=9Ha7_QhdwoUni_6hvdY-hZbuEergowHrNL2vzHIakFY,44937
-typeguard/_union_transformer.py,sha256=v_42r7-6HuRX2SoFwnyJ-E5PlxXpVeUJPJR1-HU9qSo,1354
-typeguard/_utils.py,sha256=5HhO1rPn5f1M6ymkVAEv7Xmlz1cX-j0OnTMlyHqqrR8,5270
-typeguard/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/WHEEL
deleted file mode 100644
index bab98d6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/WHEEL
+++ /dev/null
@@ -1,5 +0,0 @@
-Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
-Root-Is-Purelib: true
-Tag: py3-none-any
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/entry_points.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/entry_points.txt
deleted file mode 100644
index 47c9d0b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/entry_points.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-[pytest11]
-typeguard = typeguard._pytest_plugin
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/top_level.txt
deleted file mode 100644
index be5ec23..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard-4.3.0.dist-info/top_level.txt
+++ /dev/null
@@ -1 +0,0 @@
-typeguard
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__init__.py
deleted file mode 100644
index 6781cad..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__init__.py
+++ /dev/null
@@ -1,48 +0,0 @@
-import os
-from typing import Any
-
-from ._checkers import TypeCheckerCallable as TypeCheckerCallable
-from ._checkers import TypeCheckLookupCallback as TypeCheckLookupCallback
-from ._checkers import check_type_internal as check_type_internal
-from ._checkers import checker_lookup_functions as checker_lookup_functions
-from ._checkers import load_plugins as load_plugins
-from ._config import CollectionCheckStrategy as CollectionCheckStrategy
-from ._config import ForwardRefPolicy as ForwardRefPolicy
-from ._config import TypeCheckConfiguration as TypeCheckConfiguration
-from ._decorators import typechecked as typechecked
-from ._decorators import typeguard_ignore as typeguard_ignore
-from ._exceptions import InstrumentationWarning as InstrumentationWarning
-from ._exceptions import TypeCheckError as TypeCheckError
-from ._exceptions import TypeCheckWarning as TypeCheckWarning
-from ._exceptions import TypeHintWarning as TypeHintWarning
-from ._functions import TypeCheckFailCallback as TypeCheckFailCallback
-from ._functions import check_type as check_type
-from ._functions import warn_on_error as warn_on_error
-from ._importhook import ImportHookManager as ImportHookManager
-from ._importhook import TypeguardFinder as TypeguardFinder
-from ._importhook import install_import_hook as install_import_hook
-from ._memo import TypeCheckMemo as TypeCheckMemo
-from ._suppression import suppress_type_checks as suppress_type_checks
-from ._utils import Unset as Unset
-
-# Re-export imports so they look like they live directly in this package
-for value in list(locals().values()):
-    if getattr(value, "__module__", "").startswith(f"{__name__}."):
-        value.__module__ = __name__
-
-
-config: TypeCheckConfiguration
-
-
-def __getattr__(name: str) -> Any:
-    if name == "config":
-        from ._config import global_config
-
-        return global_config
-
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
-
-
-# Automatically load checker lookup functions unless explicitly disabled
-if "TYPEGUARD_DISABLE_PLUGIN_AUTOLOAD" not in os.environ:
-    load_plugins()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index f4d2e34..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_checkers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_checkers.cpython-312.pyc
deleted file mode 100644
index 2ecca2a..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_checkers.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_config.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_config.cpython-312.pyc
deleted file mode 100644
index 9ffcde3..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_config.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_decorators.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_decorators.cpython-312.pyc
deleted file mode 100644
index 63748a9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_decorators.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_exceptions.cpython-312.pyc
deleted file mode 100644
index 81c6675..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_exceptions.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_functions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_functions.cpython-312.pyc
deleted file mode 100644
index e313202..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_functions.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_importhook.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_importhook.cpython-312.pyc
deleted file mode 100644
index 7f417b3..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_importhook.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_memo.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_memo.cpython-312.pyc
deleted file mode 100644
index 9d18de4..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_memo.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_pytest_plugin.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_pytest_plugin.cpython-312.pyc
deleted file mode 100644
index c4ac0d9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_pytest_plugin.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_suppression.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_suppression.cpython-312.pyc
deleted file mode 100644
index 9d5af52..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_suppression.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_transformer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_transformer.cpython-312.pyc
deleted file mode 100644
index dcf55a4..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_transformer.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_union_transformer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_union_transformer.cpython-312.pyc
deleted file mode 100644
index 6baba41..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_union_transformer.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_utils.cpython-312.pyc
deleted file mode 100644
index 6207e33..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/__pycache__/_utils.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_checkers.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_checkers.py
deleted file mode 100644
index 67dd5ad..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_checkers.py
+++ /dev/null
@@ -1,993 +0,0 @@
-from __future__ import annotations
-
-import collections.abc
-import inspect
-import sys
-import types
-import typing
-import warnings
-from enum import Enum
-from inspect import Parameter, isclass, isfunction
-from io import BufferedIOBase, IOBase, RawIOBase, TextIOBase
-from textwrap import indent
-from typing import (
-    IO,
-    AbstractSet,
-    Any,
-    BinaryIO,
-    Callable,
-    Dict,
-    ForwardRef,
-    List,
-    Mapping,
-    MutableMapping,
-    NewType,
-    Optional,
-    Sequence,
-    Set,
-    TextIO,
-    Tuple,
-    Type,
-    TypeVar,
-    Union,
-)
-from unittest.mock import Mock
-from weakref import WeakKeyDictionary
-
-try:
-    import typing_extensions
-except ImportError:
-    typing_extensions = None  # type: ignore[assignment]
-
-# Must use this because typing.is_typeddict does not recognize
-# TypedDict from typing_extensions, and as of version 4.12.0
-# typing_extensions.TypedDict is different from typing.TypedDict
-# on all versions.
-from typing_extensions import is_typeddict
-
-from ._config import ForwardRefPolicy
-from ._exceptions import TypeCheckError, TypeHintWarning
-from ._memo import TypeCheckMemo
-from ._utils import evaluate_forwardref, get_stacklevel, get_type_name, qualified_name
-
-if sys.version_info >= (3, 11):
-    from typing import (
-        Annotated,
-        NotRequired,
-        TypeAlias,
-        get_args,
-        get_origin,
-    )
-
-    SubclassableAny = Any
-else:
-    from typing_extensions import (
-        Annotated,
-        NotRequired,
-        TypeAlias,
-        get_args,
-        get_origin,
-    )
-    from typing_extensions import Any as SubclassableAny
-
-if sys.version_info >= (3, 10):
-    from importlib.metadata import entry_points
-    from typing import ParamSpec
-else:
-    from importlib_metadata import entry_points
-    from typing_extensions import ParamSpec
-
-TypeCheckerCallable: TypeAlias = Callable[
-    [Any, Any, Tuple[Any, ...], TypeCheckMemo], Any
-]
-TypeCheckLookupCallback: TypeAlias = Callable[
-    [Any, Tuple[Any, ...], Tuple[Any, ...]], Optional[TypeCheckerCallable]
-]
-
-checker_lookup_functions: list[TypeCheckLookupCallback] = []
-generic_alias_types: tuple[type, ...] = (type(List), type(List[Any]))
-if sys.version_info >= (3, 9):
-    generic_alias_types += (types.GenericAlias,)
-
-protocol_check_cache: WeakKeyDictionary[
-    type[Any], dict[type[Any], TypeCheckError | None]
-] = WeakKeyDictionary()
-
-# Sentinel
-_missing = object()
-
-# Lifted from mypy.sharedparse
-BINARY_MAGIC_METHODS = {
-    "__add__",
-    "__and__",
-    "__cmp__",
-    "__divmod__",
-    "__div__",
-    "__eq__",
-    "__floordiv__",
-    "__ge__",
-    "__gt__",
-    "__iadd__",
-    "__iand__",
-    "__idiv__",
-    "__ifloordiv__",
-    "__ilshift__",
-    "__imatmul__",
-    "__imod__",
-    "__imul__",
-    "__ior__",
-    "__ipow__",
-    "__irshift__",
-    "__isub__",
-    "__itruediv__",
-    "__ixor__",
-    "__le__",
-    "__lshift__",
-    "__lt__",
-    "__matmul__",
-    "__mod__",
-    "__mul__",
-    "__ne__",
-    "__or__",
-    "__pow__",
-    "__radd__",
-    "__rand__",
-    "__rdiv__",
-    "__rfloordiv__",
-    "__rlshift__",
-    "__rmatmul__",
-    "__rmod__",
-    "__rmul__",
-    "__ror__",
-    "__rpow__",
-    "__rrshift__",
-    "__rshift__",
-    "__rsub__",
-    "__rtruediv__",
-    "__rxor__",
-    "__sub__",
-    "__truediv__",
-    "__xor__",
-}
-
-
-def check_callable(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not callable(value):
-        raise TypeCheckError("is not callable")
-
-    if args:
-        try:
-            signature = inspect.signature(value)
-        except (TypeError, ValueError):
-            return
-
-        argument_types = args[0]
-        if isinstance(argument_types, list) and not any(
-            type(item) is ParamSpec for item in argument_types
-        ):
-            # The callable must not have keyword-only arguments without defaults
-            unfulfilled_kwonlyargs = [
-                param.name
-                for param in signature.parameters.values()
-                if param.kind == Parameter.KEYWORD_ONLY
-                and param.default == Parameter.empty
-            ]
-            if unfulfilled_kwonlyargs:
-                raise TypeCheckError(
-                    f"has mandatory keyword-only arguments in its declaration: "
-                    f'{", ".join(unfulfilled_kwonlyargs)}'
-                )
-
-            num_positional_args = num_mandatory_pos_args = 0
-            has_varargs = False
-            for param in signature.parameters.values():
-                if param.kind in (
-                    Parameter.POSITIONAL_ONLY,
-                    Parameter.POSITIONAL_OR_KEYWORD,
-                ):
-                    num_positional_args += 1
-                    if param.default is Parameter.empty:
-                        num_mandatory_pos_args += 1
-                elif param.kind == Parameter.VAR_POSITIONAL:
-                    has_varargs = True
-
-            if num_mandatory_pos_args > len(argument_types):
-                raise TypeCheckError(
-                    f"has too many mandatory positional arguments in its declaration; "
-                    f"expected {len(argument_types)} but {num_mandatory_pos_args} "
-                    f"mandatory positional argument(s) declared"
-                )
-            elif not has_varargs and num_positional_args < len(argument_types):
-                raise TypeCheckError(
-                    f"has too few arguments in its declaration; expected "
-                    f"{len(argument_types)} but {num_positional_args} argument(s) "
-                    f"declared"
-                )
-
-
-def check_mapping(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if origin_type is Dict or origin_type is dict:
-        if not isinstance(value, dict):
-            raise TypeCheckError("is not a dict")
-    if origin_type is MutableMapping or origin_type is collections.abc.MutableMapping:
-        if not isinstance(value, collections.abc.MutableMapping):
-            raise TypeCheckError("is not a mutable mapping")
-    elif not isinstance(value, collections.abc.Mapping):
-        raise TypeCheckError("is not a mapping")
-
-    if args:
-        key_type, value_type = args
-        if key_type is not Any or value_type is not Any:
-            samples = memo.config.collection_check_strategy.iterate_samples(
-                value.items()
-            )
-            for k, v in samples:
-                try:
-                    check_type_internal(k, key_type, memo)
-                except TypeCheckError as exc:
-                    exc.append_path_element(f"key {k!r}")
-                    raise
-
-                try:
-                    check_type_internal(v, value_type, memo)
-                except TypeCheckError as exc:
-                    exc.append_path_element(f"value of key {k!r}")
-                    raise
-
-
-def check_typed_dict(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not isinstance(value, dict):
-        raise TypeCheckError("is not a dict")
-
-    declared_keys = frozenset(origin_type.__annotations__)
-    if hasattr(origin_type, "__required_keys__"):
-        required_keys = set(origin_type.__required_keys__)
-    else:  # py3.8 and lower
-        required_keys = set(declared_keys) if origin_type.__total__ else set()
-
-    existing_keys = set(value)
-    extra_keys = existing_keys - declared_keys
-    if extra_keys:
-        keys_formatted = ", ".join(f'"{key}"' for key in sorted(extra_keys, key=repr))
-        raise TypeCheckError(f"has unexpected extra key(s): {keys_formatted}")
-
-    # Detect NotRequired fields which are hidden by get_type_hints()
-    type_hints: dict[str, type] = {}
-    for key, annotation in origin_type.__annotations__.items():
-        if isinstance(annotation, ForwardRef):
-            annotation = evaluate_forwardref(annotation, memo)
-            if get_origin(annotation) is NotRequired:
-                required_keys.discard(key)
-                annotation = get_args(annotation)[0]
-
-        type_hints[key] = annotation
-
-    missing_keys = required_keys - existing_keys
-    if missing_keys:
-        keys_formatted = ", ".join(f'"{key}"' for key in sorted(missing_keys, key=repr))
-        raise TypeCheckError(f"is missing required key(s): {keys_formatted}")
-
-    for key, argtype in type_hints.items():
-        argvalue = value.get(key, _missing)
-        if argvalue is not _missing:
-            try:
-                check_type_internal(argvalue, argtype, memo)
-            except TypeCheckError as exc:
-                exc.append_path_element(f"value of key {key!r}")
-                raise
-
-
-def check_list(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not isinstance(value, list):
-        raise TypeCheckError("is not a list")
-
-    if args and args != (Any,):
-        samples = memo.config.collection_check_strategy.iterate_samples(value)
-        for i, v in enumerate(samples):
-            try:
-                check_type_internal(v, args[0], memo)
-            except TypeCheckError as exc:
-                exc.append_path_element(f"item {i}")
-                raise
-
-
-def check_sequence(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not isinstance(value, collections.abc.Sequence):
-        raise TypeCheckError("is not a sequence")
-
-    if args and args != (Any,):
-        samples = memo.config.collection_check_strategy.iterate_samples(value)
-        for i, v in enumerate(samples):
-            try:
-                check_type_internal(v, args[0], memo)
-            except TypeCheckError as exc:
-                exc.append_path_element(f"item {i}")
-                raise
-
-
-def check_set(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if origin_type is frozenset:
-        if not isinstance(value, frozenset):
-            raise TypeCheckError("is not a frozenset")
-    elif not isinstance(value, AbstractSet):
-        raise TypeCheckError("is not a set")
-
-    if args and args != (Any,):
-        samples = memo.config.collection_check_strategy.iterate_samples(value)
-        for v in samples:
-            try:
-                check_type_internal(v, args[0], memo)
-            except TypeCheckError as exc:
-                exc.append_path_element(f"[{v}]")
-                raise
-
-
-def check_tuple(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    # Specialized check for NamedTuples
-    if field_types := getattr(origin_type, "__annotations__", None):
-        if not isinstance(value, origin_type):
-            raise TypeCheckError(
-                f"is not a named tuple of type {qualified_name(origin_type)}"
-            )
-
-        for name, field_type in field_types.items():
-            try:
-                check_type_internal(getattr(value, name), field_type, memo)
-            except TypeCheckError as exc:
-                exc.append_path_element(f"attribute {name!r}")
-                raise
-
-        return
-    elif not isinstance(value, tuple):
-        raise TypeCheckError("is not a tuple")
-
-    if args:
-        use_ellipsis = args[-1] is Ellipsis
-        tuple_params = args[: -1 if use_ellipsis else None]
-    else:
-        # Unparametrized Tuple or plain tuple
-        return
-
-    if use_ellipsis:
-        element_type = tuple_params[0]
-        samples = memo.config.collection_check_strategy.iterate_samples(value)
-        for i, element in enumerate(samples):
-            try:
-                check_type_internal(element, element_type, memo)
-            except TypeCheckError as exc:
-                exc.append_path_element(f"item {i}")
-                raise
-    elif tuple_params == ((),):
-        if value != ():
-            raise TypeCheckError("is not an empty tuple")
-    else:
-        if len(value) != len(tuple_params):
-            raise TypeCheckError(
-                f"has wrong number of elements (expected {len(tuple_params)}, got "
-                f"{len(value)} instead)"
-            )
-
-        for i, (element, element_type) in enumerate(zip(value, tuple_params)):
-            try:
-                check_type_internal(element, element_type, memo)
-            except TypeCheckError as exc:
-                exc.append_path_element(f"item {i}")
-                raise
-
-
-def check_union(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    errors: dict[str, TypeCheckError] = {}
-    try:
-        for type_ in args:
-            try:
-                check_type_internal(value, type_, memo)
-                return
-            except TypeCheckError as exc:
-                errors[get_type_name(type_)] = exc
-
-        formatted_errors = indent(
-            "\n".join(f"{key}: {error}" for key, error in errors.items()), "  "
-        )
-    finally:
-        del errors  # avoid creating ref cycle
-    raise TypeCheckError(f"did not match any element in the union:\n{formatted_errors}")
-
-
-def check_uniontype(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    errors: dict[str, TypeCheckError] = {}
-    for type_ in args:
-        try:
-            check_type_internal(value, type_, memo)
-            return
-        except TypeCheckError as exc:
-            errors[get_type_name(type_)] = exc
-
-    formatted_errors = indent(
-        "\n".join(f"{key}: {error}" for key, error in errors.items()), "  "
-    )
-    raise TypeCheckError(f"did not match any element in the union:\n{formatted_errors}")
-
-
-def check_class(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not isclass(value) and not isinstance(value, generic_alias_types):
-        raise TypeCheckError("is not a class")
-
-    if not args:
-        return
-
-    if isinstance(args[0], ForwardRef):
-        expected_class = evaluate_forwardref(args[0], memo)
-    else:
-        expected_class = args[0]
-
-    if expected_class is Any:
-        return
-    elif getattr(expected_class, "_is_protocol", False):
-        check_protocol(value, expected_class, (), memo)
-    elif isinstance(expected_class, TypeVar):
-        check_typevar(value, expected_class, (), memo, subclass_check=True)
-    elif get_origin(expected_class) is Union:
-        errors: dict[str, TypeCheckError] = {}
-        for arg in get_args(expected_class):
-            if arg is Any:
-                return
-
-            try:
-                check_class(value, type, (arg,), memo)
-                return
-            except TypeCheckError as exc:
-                errors[get_type_name(arg)] = exc
-        else:
-            formatted_errors = indent(
-                "\n".join(f"{key}: {error}" for key, error in errors.items()), "  "
-            )
-            raise TypeCheckError(
-                f"did not match any element in the union:\n{formatted_errors}"
-            )
-    elif not issubclass(value, expected_class):  # type: ignore[arg-type]
-        raise TypeCheckError(f"is not a subclass of {qualified_name(expected_class)}")
-
-
-def check_newtype(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    check_type_internal(value, origin_type.__supertype__, memo)
-
-
-def check_instance(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not isinstance(value, origin_type):
-        raise TypeCheckError(f"is not an instance of {qualified_name(origin_type)}")
-
-
-def check_typevar(
-    value: Any,
-    origin_type: TypeVar,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-    *,
-    subclass_check: bool = False,
-) -> None:
-    if origin_type.__bound__ is not None:
-        annotation = (
-            Type[origin_type.__bound__] if subclass_check else origin_type.__bound__
-        )
-        check_type_internal(value, annotation, memo)
-    elif origin_type.__constraints__:
-        for constraint in origin_type.__constraints__:
-            annotation = Type[constraint] if subclass_check else constraint
-            try:
-                check_type_internal(value, annotation, memo)
-            except TypeCheckError:
-                pass
-            else:
-                break
-        else:
-            formatted_constraints = ", ".join(
-                get_type_name(constraint) for constraint in origin_type.__constraints__
-            )
-            raise TypeCheckError(
-                f"does not match any of the constraints " f"({formatted_constraints})"
-            )
-
-
-if typing_extensions is None:
-
-    def _is_literal_type(typ: object) -> bool:
-        return typ is typing.Literal
-
-else:
-
-    def _is_literal_type(typ: object) -> bool:
-        return typ is typing.Literal or typ is typing_extensions.Literal
-
-
-def check_literal(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    def get_literal_args(literal_args: tuple[Any, ...]) -> tuple[Any, ...]:
-        retval: list[Any] = []
-        for arg in literal_args:
-            if _is_literal_type(get_origin(arg)):
-                retval.extend(get_literal_args(arg.__args__))
-            elif arg is None or isinstance(arg, (int, str, bytes, bool, Enum)):
-                retval.append(arg)
-            else:
-                raise TypeError(
-                    f"Illegal literal value: {arg}"
-                )  # TypeError here is deliberate
-
-        return tuple(retval)
-
-    final_args = tuple(get_literal_args(args))
-    try:
-        index = final_args.index(value)
-    except ValueError:
-        pass
-    else:
-        if type(final_args[index]) is type(value):
-            return
-
-    formatted_args = ", ".join(repr(arg) for arg in final_args)
-    raise TypeCheckError(f"is not any of ({formatted_args})") from None
-
-
-def check_literal_string(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    check_type_internal(value, str, memo)
-
-
-def check_typeguard(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    check_type_internal(value, bool, memo)
-
-
-def check_none(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if value is not None:
-        raise TypeCheckError("is not None")
-
-
-def check_number(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if origin_type is complex and not isinstance(value, (complex, float, int)):
-        raise TypeCheckError("is neither complex, float or int")
-    elif origin_type is float and not isinstance(value, (float, int)):
-        raise TypeCheckError("is neither float or int")
-
-
-def check_io(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if origin_type is TextIO or (origin_type is IO and args == (str,)):
-        if not isinstance(value, TextIOBase):
-            raise TypeCheckError("is not a text based I/O object")
-    elif origin_type is BinaryIO or (origin_type is IO and args == (bytes,)):
-        if not isinstance(value, (RawIOBase, BufferedIOBase)):
-            raise TypeCheckError("is not a binary I/O object")
-    elif not isinstance(value, IOBase):
-        raise TypeCheckError("is not an I/O object")
-
-
-def check_protocol(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    subject: type[Any] = value if isclass(value) else type(value)
-
-    if subject in protocol_check_cache:
-        result_map = protocol_check_cache[subject]
-        if origin_type in result_map:
-            if exc := result_map[origin_type]:
-                raise exc
-            else:
-                return
-
-    # Collect a set of methods and non-method attributes present in the protocol
-    ignored_attrs = set(dir(typing.Protocol)) | {
-        "__annotations__",
-        "__non_callable_proto_members__",
-    }
-    expected_methods: dict[str, tuple[Any, Any]] = {}
-    expected_noncallable_members: dict[str, Any] = {}
-    for attrname in dir(origin_type):
-        # Skip attributes present in typing.Protocol
-        if attrname in ignored_attrs:
-            continue
-
-        member = getattr(origin_type, attrname)
-        if callable(member):
-            signature = inspect.signature(member)
-            argtypes = [
-                (p.annotation if p.annotation is not Parameter.empty else Any)
-                for p in signature.parameters.values()
-                if p.kind is not Parameter.KEYWORD_ONLY
-            ] or Ellipsis
-            return_annotation = (
-                signature.return_annotation
-                if signature.return_annotation is not Parameter.empty
-                else Any
-            )
-            expected_methods[attrname] = argtypes, return_annotation
-        else:
-            expected_noncallable_members[attrname] = member
-
-    for attrname, annotation in typing.get_type_hints(origin_type).items():
-        expected_noncallable_members[attrname] = annotation
-
-    subject_annotations = typing.get_type_hints(subject)
-
-    # Check that all required methods are present and their signatures are compatible
-    result_map = protocol_check_cache.setdefault(subject, {})
-    try:
-        for attrname, callable_args in expected_methods.items():
-            try:
-                method = getattr(subject, attrname)
-            except AttributeError:
-                if attrname in subject_annotations:
-                    raise TypeCheckError(
-                        f"is not compatible with the {origin_type.__qualname__} protocol "
-                        f"because its {attrname!r} attribute is not a method"
-                    ) from None
-                else:
-                    raise TypeCheckError(
-                        f"is not compatible with the {origin_type.__qualname__} protocol "
-                        f"because it has no method named {attrname!r}"
-                    ) from None
-
-            if not callable(method):
-                raise TypeCheckError(
-                    f"is not compatible with the {origin_type.__qualname__} protocol "
-                    f"because its {attrname!r} attribute is not a callable"
-                )
-
-            # TODO: raise exception on added keyword-only arguments without defaults
-            try:
-                check_callable(method, Callable, callable_args, memo)
-            except TypeCheckError as exc:
-                raise TypeCheckError(
-                    f"is not compatible with the {origin_type.__qualname__} protocol "
-                    f"because its {attrname!r} method {exc}"
-                ) from None
-
-        # Check that all required non-callable members are present
-        for attrname in expected_noncallable_members:
-            # TODO: implement assignability checks for non-callable members
-            if attrname not in subject_annotations and not hasattr(subject, attrname):
-                raise TypeCheckError(
-                    f"is not compatible with the {origin_type.__qualname__} protocol "
-                    f"because it has no attribute named {attrname!r}"
-                )
-    except TypeCheckError as exc:
-        result_map[origin_type] = exc
-        raise
-    else:
-        result_map[origin_type] = None
-
-
-def check_byteslike(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not isinstance(value, (bytearray, bytes, memoryview)):
-        raise TypeCheckError("is not bytes-like")
-
-
-def check_self(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if memo.self_type is None:
-        raise TypeCheckError("cannot be checked against Self outside of a method call")
-
-    if isclass(value):
-        if not issubclass(value, memo.self_type):
-            raise TypeCheckError(
-                f"is not an instance of the self type "
-                f"({qualified_name(memo.self_type)})"
-            )
-    elif not isinstance(value, memo.self_type):
-        raise TypeCheckError(
-            f"is not an instance of the self type ({qualified_name(memo.self_type)})"
-        )
-
-
-def check_paramspec(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    pass  # No-op for now
-
-
-def check_instanceof(
-    value: Any,
-    origin_type: Any,
-    args: tuple[Any, ...],
-    memo: TypeCheckMemo,
-) -> None:
-    if not isinstance(value, origin_type):
-        raise TypeCheckError(f"is not an instance of {qualified_name(origin_type)}")
-
-
-def check_type_internal(
-    value: Any,
-    annotation: Any,
-    memo: TypeCheckMemo,
-) -> None:
-    """
-    Check that the given object is compatible with the given type annotation.
-
-    This function should only be used by type checker callables. Applications should use
-    :func:`~.check_type` instead.
-
-    :param value: the value to check
-    :param annotation: the type annotation to check against
-    :param memo: a memo object containing configuration and information necessary for
-        looking up forward references
-    """
-
-    if isinstance(annotation, ForwardRef):
-        try:
-            annotation = evaluate_forwardref(annotation, memo)
-        except NameError:
-            if memo.config.forward_ref_policy is ForwardRefPolicy.ERROR:
-                raise
-            elif memo.config.forward_ref_policy is ForwardRefPolicy.WARN:
-                warnings.warn(
-                    f"Cannot resolve forward reference {annotation.__forward_arg__!r}",
-                    TypeHintWarning,
-                    stacklevel=get_stacklevel(),
-                )
-
-            return
-
-    if annotation is Any or annotation is SubclassableAny or isinstance(value, Mock):
-        return
-
-    # Skip type checks if value is an instance of a class that inherits from Any
-    if not isclass(value) and SubclassableAny in type(value).__bases__:
-        return
-
-    extras: tuple[Any, ...]
-    origin_type = get_origin(annotation)
-    if origin_type is Annotated:
-        annotation, *extras_ = get_args(annotation)
-        extras = tuple(extras_)
-        origin_type = get_origin(annotation)
-    else:
-        extras = ()
-
-    if origin_type is not None:
-        args = get_args(annotation)
-
-        # Compatibility hack to distinguish between unparametrized and empty tuple
-        # (tuple[()]), necessary due to https://github.com/python/cpython/issues/91137
-        if origin_type in (tuple, Tuple) and annotation is not Tuple and not args:
-            args = ((),)
-    else:
-        origin_type = annotation
-        args = ()
-
-    for lookup_func in checker_lookup_functions:
-        checker = lookup_func(origin_type, args, extras)
-        if checker:
-            checker(value, origin_type, args, memo)
-            return
-
-    if isclass(origin_type):
-        if not isinstance(value, origin_type):
-            raise TypeCheckError(f"is not an instance of {qualified_name(origin_type)}")
-    elif type(origin_type) is str:  # noqa: E721
-        warnings.warn(
-            f"Skipping type check against {origin_type!r}; this looks like a "
-            f"string-form forward reference imported from another module",
-            TypeHintWarning,
-            stacklevel=get_stacklevel(),
-        )
-
-
-# Equality checks are applied to these
-origin_type_checkers = {
-    bytes: check_byteslike,
-    AbstractSet: check_set,
-    BinaryIO: check_io,
-    Callable: check_callable,
-    collections.abc.Callable: check_callable,
-    complex: check_number,
-    dict: check_mapping,
-    Dict: check_mapping,
-    float: check_number,
-    frozenset: check_set,
-    IO: check_io,
-    list: check_list,
-    List: check_list,
-    typing.Literal: check_literal,
-    Mapping: check_mapping,
-    MutableMapping: check_mapping,
-    None: check_none,
-    collections.abc.Mapping: check_mapping,
-    collections.abc.MutableMapping: check_mapping,
-    Sequence: check_sequence,
-    collections.abc.Sequence: check_sequence,
-    collections.abc.Set: check_set,
-    set: check_set,
-    Set: check_set,
-    TextIO: check_io,
-    tuple: check_tuple,
-    Tuple: check_tuple,
-    type: check_class,
-    Type: check_class,
-    Union: check_union,
-}
-if sys.version_info >= (3, 10):
-    origin_type_checkers[types.UnionType] = check_uniontype
-    origin_type_checkers[typing.TypeGuard] = check_typeguard
-if sys.version_info >= (3, 11):
-    origin_type_checkers.update(
-        {typing.LiteralString: check_literal_string, typing.Self: check_self}
-    )
-if typing_extensions is not None:
-    # On some Python versions, these may simply be re-exports from typing,
-    # but exactly which Python versions is subject to change,
-    # so it's best to err on the safe side
-    # and update the dictionary on all Python versions
-    # if typing_extensions is installed
-    origin_type_checkers[typing_extensions.Literal] = check_literal
-    origin_type_checkers[typing_extensions.LiteralString] = check_literal_string
-    origin_type_checkers[typing_extensions.Self] = check_self
-    origin_type_checkers[typing_extensions.TypeGuard] = check_typeguard
-
-
-def builtin_checker_lookup(
-    origin_type: Any, args: tuple[Any, ...], extras: tuple[Any, ...]
-) -> TypeCheckerCallable | None:
-    checker = origin_type_checkers.get(origin_type)
-    if checker is not None:
-        return checker
-    elif is_typeddict(origin_type):
-        return check_typed_dict
-    elif isclass(origin_type) and issubclass(
-        origin_type,
-        Tuple,  # type: ignore[arg-type]
-    ):
-        # NamedTuple
-        return check_tuple
-    elif getattr(origin_type, "_is_protocol", False):
-        return check_protocol
-    elif isinstance(origin_type, ParamSpec):
-        return check_paramspec
-    elif isinstance(origin_type, TypeVar):
-        return check_typevar
-    elif origin_type.__class__ is NewType:
-        # typing.NewType on Python 3.10+
-        return check_newtype
-    elif (
-        isfunction(origin_type)
-        and getattr(origin_type, "__module__", None) == "typing"
-        and getattr(origin_type, "__qualname__", "").startswith("NewType.")
-        and hasattr(origin_type, "__supertype__")
-    ):
-        # typing.NewType on Python 3.9 and below
-        return check_newtype
-
-    return None
-
-
-checker_lookup_functions.append(builtin_checker_lookup)
-
-
-def load_plugins() -> None:
-    """
-    Load all type checker lookup functions from entry points.
-
-    All entry points from the ``typeguard.checker_lookup`` group are loaded, and the
-    returned lookup functions are added to :data:`typeguard.checker_lookup_functions`.
-
-    .. note:: This function is called implicitly on import, unless the
-        ``TYPEGUARD_DISABLE_PLUGIN_AUTOLOAD`` environment variable is present.
-    """
-
-    for ep in entry_points(group="typeguard.checker_lookup"):
-        try:
-            plugin = ep.load()
-        except Exception as exc:
-            warnings.warn(
-                f"Failed to load plugin {ep.name!r}: " f"{qualified_name(exc)}: {exc}",
-                stacklevel=2,
-            )
-            continue
-
-        if not callable(plugin):
-            warnings.warn(
-                f"Plugin {ep} returned a non-callable object: {plugin!r}", stacklevel=2
-            )
-            continue
-
-        checker_lookup_functions.insert(0, plugin)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_config.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_config.py
deleted file mode 100644
index 36efad5..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_config.py
+++ /dev/null
@@ -1,108 +0,0 @@
-from __future__ import annotations
-
-from collections.abc import Iterable
-from dataclasses import dataclass
-from enum import Enum, auto
-from typing import TYPE_CHECKING, TypeVar
-
-if TYPE_CHECKING:
-    from ._functions import TypeCheckFailCallback
-
-T = TypeVar("T")
-
-
-class ForwardRefPolicy(Enum):
-    """
-    Defines how unresolved forward references are handled.
-
-    Members:
-
-    * ``ERROR``: propagate the :exc:`NameError` when the forward reference lookup fails
-    * ``WARN``: emit a :class:`~.TypeHintWarning` if the forward reference lookup fails
-    * ``IGNORE``: silently skip checks for unresolveable forward references
-    """
-
-    ERROR = auto()
-    WARN = auto()
-    IGNORE = auto()
-
-
-class CollectionCheckStrategy(Enum):
-    """
-    Specifies how thoroughly the contents of collections are type checked.
-
-    This has an effect on the following built-in checkers:
-
-    * ``AbstractSet``
-    * ``Dict``
-    * ``List``
-    * ``Mapping``
-    * ``Set``
-    * ``Tuple[, ...]`` (arbitrarily sized tuples)
-
-    Members:
-
-    * ``FIRST_ITEM``: check only the first item
-    * ``ALL_ITEMS``: check all items
-    """
-
-    FIRST_ITEM = auto()
-    ALL_ITEMS = auto()
-
-    def iterate_samples(self, collection: Iterable[T]) -> Iterable[T]:
-        if self is CollectionCheckStrategy.FIRST_ITEM:
-            try:
-                return [next(iter(collection))]
-            except StopIteration:
-                return ()
-        else:
-            return collection
-
-
-@dataclass
-class TypeCheckConfiguration:
-    """
-     You can change Typeguard's behavior with these settings.
-
-    .. attribute:: typecheck_fail_callback
-       :type: Callable[[TypeCheckError, TypeCheckMemo], Any]
-
-         Callable that is called when type checking fails.
-
-         Default: ``None`` (the :exc:`~.TypeCheckError` is raised directly)
-
-    .. attribute:: forward_ref_policy
-       :type: ForwardRefPolicy
-
-         Specifies what to do when a forward reference fails to resolve.
-
-         Default: ``WARN``
-
-    .. attribute:: collection_check_strategy
-       :type: CollectionCheckStrategy
-
-         Specifies how thoroughly the contents of collections (list, dict, etc.) are
-         type checked.
-
-         Default: ``FIRST_ITEM``
-
-    .. attribute:: debug_instrumentation
-       :type: bool
-
-         If set to ``True``, the code of modules or functions instrumented by typeguard
-         is printed to ``sys.stderr`` after the instrumentation is done
-
-         Requires Python 3.9 or newer.
-
-         Default: ``False``
-    """
-
-    forward_ref_policy: ForwardRefPolicy = ForwardRefPolicy.WARN
-    typecheck_fail_callback: TypeCheckFailCallback | None = None
-    collection_check_strategy: CollectionCheckStrategy = (
-        CollectionCheckStrategy.FIRST_ITEM
-    )
-    debug_instrumentation: bool = False
-
-
-global_config = TypeCheckConfiguration()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_decorators.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_decorators.py
deleted file mode 100644
index cf32533..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_decorators.py
+++ /dev/null
@@ -1,235 +0,0 @@
-from __future__ import annotations
-
-import ast
-import inspect
-import sys
-from collections.abc import Sequence
-from functools import partial
-from inspect import isclass, isfunction
-from types import CodeType, FrameType, FunctionType
-from typing import TYPE_CHECKING, Any, Callable, ForwardRef, TypeVar, cast, overload
-from warnings import warn
-
-from ._config import CollectionCheckStrategy, ForwardRefPolicy, global_config
-from ._exceptions import InstrumentationWarning
-from ._functions import TypeCheckFailCallback
-from ._transformer import TypeguardTransformer
-from ._utils import Unset, function_name, get_stacklevel, is_method_of, unset
-
-if TYPE_CHECKING:
-    from typeshed.stdlib.types import _Cell
-
-    _F = TypeVar("_F")
-
-    def typeguard_ignore(f: _F) -> _F:
-        """This decorator is a noop during static type-checking."""
-        return f
-
-else:
-    from typing import no_type_check as typeguard_ignore  # noqa: F401
-
-T_CallableOrType = TypeVar("T_CallableOrType", bound=Callable[..., Any])
-
-
-def make_cell(value: object) -> _Cell:
-    return (lambda: value).__closure__[0]  # type: ignore[index]
-
-
-def find_target_function(
-    new_code: CodeType, target_path: Sequence[str], firstlineno: int
-) -> CodeType | None:
-    target_name = target_path[0]
-    for const in new_code.co_consts:
-        if isinstance(const, CodeType):
-            if const.co_name == target_name:
-                if const.co_firstlineno == firstlineno:
-                    return const
-                elif len(target_path) > 1:
-                    target_code = find_target_function(
-                        const, target_path[1:], firstlineno
-                    )
-                    if target_code:
-                        return target_code
-
-    return None
-
-
-def instrument(f: T_CallableOrType) -> FunctionType | str:
-    if not getattr(f, "__code__", None):
-        return "no code associated"
-    elif not getattr(f, "__module__", None):
-        return "__module__ attribute is not set"
-    elif f.__code__.co_filename == "":
-        return "cannot instrument functions defined in a REPL"
-    elif hasattr(f, "__wrapped__"):
-        return (
-            "@typechecked only supports instrumenting functions wrapped with "
-            "@classmethod, @staticmethod or @property"
-        )
-
-    target_path = [item for item in f.__qualname__.split(".") if item != ""]
-    module_source = inspect.getsource(sys.modules[f.__module__])
-    module_ast = ast.parse(module_source)
-    instrumentor = TypeguardTransformer(target_path, f.__code__.co_firstlineno)
-    instrumentor.visit(module_ast)
-
-    if not instrumentor.target_node or instrumentor.target_lineno is None:
-        return "instrumentor did not find the target function"
-
-    module_code = compile(module_ast, f.__code__.co_filename, "exec", dont_inherit=True)
-    new_code = find_target_function(
-        module_code, target_path, instrumentor.target_lineno
-    )
-    if not new_code:
-        return "cannot find the target function in the AST"
-
-    if global_config.debug_instrumentation and sys.version_info >= (3, 9):
-        # Find the matching AST node, then unparse it to source and print to stdout
-        print(
-            f"Source code of {f.__qualname__}() after instrumentation:"
-            "\n----------------------------------------------",
-            file=sys.stderr,
-        )
-        print(ast.unparse(instrumentor.target_node), file=sys.stderr)
-        print(
-            "----------------------------------------------",
-            file=sys.stderr,
-        )
-
-    closure = f.__closure__
-    if new_code.co_freevars != f.__code__.co_freevars:
-        # Create a new closure and find values for the new free variables
-        frame = cast(FrameType, inspect.currentframe())
-        frame = cast(FrameType, frame.f_back)
-        frame_locals = cast(FrameType, frame.f_back).f_locals
-        cells: list[_Cell] = []
-        for key in new_code.co_freevars:
-            if key in instrumentor.names_used_in_annotations:
-                # Find the value and make a new cell from it
-                value = frame_locals.get(key) or ForwardRef(key)
-                cells.append(make_cell(value))
-            else:
-                # Reuse the cell from the existing closure
-                assert f.__closure__
-                cells.append(f.__closure__[f.__code__.co_freevars.index(key)])
-
-        closure = tuple(cells)
-
-    new_function = FunctionType(new_code, f.__globals__, f.__name__, closure=closure)
-    new_function.__module__ = f.__module__
-    new_function.__name__ = f.__name__
-    new_function.__qualname__ = f.__qualname__
-    new_function.__annotations__ = f.__annotations__
-    new_function.__doc__ = f.__doc__
-    new_function.__defaults__ = f.__defaults__
-    new_function.__kwdefaults__ = f.__kwdefaults__
-    return new_function
-
-
-@overload
-def typechecked(
-    *,
-    forward_ref_policy: ForwardRefPolicy | Unset = unset,
-    typecheck_fail_callback: TypeCheckFailCallback | Unset = unset,
-    collection_check_strategy: CollectionCheckStrategy | Unset = unset,
-    debug_instrumentation: bool | Unset = unset,
-) -> Callable[[T_CallableOrType], T_CallableOrType]: ...
-
-
-@overload
-def typechecked(target: T_CallableOrType) -> T_CallableOrType: ...
-
-
-def typechecked(
-    target: T_CallableOrType | None = None,
-    *,
-    forward_ref_policy: ForwardRefPolicy | Unset = unset,
-    typecheck_fail_callback: TypeCheckFailCallback | Unset = unset,
-    collection_check_strategy: CollectionCheckStrategy | Unset = unset,
-    debug_instrumentation: bool | Unset = unset,
-) -> Any:
-    """
-    Instrument the target function to perform run-time type checking.
-
-    This decorator recompiles the target function, injecting code to type check
-    arguments, return values, yield values (excluding ``yield from``) and assignments to
-    annotated local variables.
-
-    This can also be used as a class decorator. This will instrument all type annotated
-    methods, including :func:`@classmethod `,
-    :func:`@staticmethod `,  and :class:`@property ` decorated
-    methods in the class.
-
-    .. note:: When Python is run in optimized mode (``-O`` or ``-OO``, this decorator
-        is a no-op). This is a feature meant for selectively introducing type checking
-        into a code base where the checks aren't meant to be run in production.
-
-    :param target: the function or class to enable type checking for
-    :param forward_ref_policy: override for
-        :attr:`.TypeCheckConfiguration.forward_ref_policy`
-    :param typecheck_fail_callback: override for
-        :attr:`.TypeCheckConfiguration.typecheck_fail_callback`
-    :param collection_check_strategy: override for
-        :attr:`.TypeCheckConfiguration.collection_check_strategy`
-    :param debug_instrumentation: override for
-        :attr:`.TypeCheckConfiguration.debug_instrumentation`
-
-    """
-    if target is None:
-        return partial(
-            typechecked,
-            forward_ref_policy=forward_ref_policy,
-            typecheck_fail_callback=typecheck_fail_callback,
-            collection_check_strategy=collection_check_strategy,
-            debug_instrumentation=debug_instrumentation,
-        )
-
-    if not __debug__:
-        return target
-
-    if isclass(target):
-        for key, attr in target.__dict__.items():
-            if is_method_of(attr, target):
-                retval = instrument(attr)
-                if isfunction(retval):
-                    setattr(target, key, retval)
-            elif isinstance(attr, (classmethod, staticmethod)):
-                if is_method_of(attr.__func__, target):
-                    retval = instrument(attr.__func__)
-                    if isfunction(retval):
-                        wrapper = attr.__class__(retval)
-                        setattr(target, key, wrapper)
-            elif isinstance(attr, property):
-                kwargs: dict[str, Any] = dict(doc=attr.__doc__)
-                for name in ("fset", "fget", "fdel"):
-                    property_func = kwargs[name] = getattr(attr, name)
-                    if is_method_of(property_func, target):
-                        retval = instrument(property_func)
-                        if isfunction(retval):
-                            kwargs[name] = retval
-
-                setattr(target, key, attr.__class__(**kwargs))
-
-        return target
-
-    # Find either the first Python wrapper or the actual function
-    wrapper_class: (
-        type[classmethod[Any, Any, Any]] | type[staticmethod[Any, Any]] | None
-    ) = None
-    if isinstance(target, (classmethod, staticmethod)):
-        wrapper_class = target.__class__
-        target = target.__func__
-
-    retval = instrument(target)
-    if isinstance(retval, str):
-        warn(
-            f"{retval} -- not typechecking {function_name(target)}",
-            InstrumentationWarning,
-            stacklevel=get_stacklevel(),
-        )
-        return target
-
-    if wrapper_class is None:
-        return retval
-    else:
-        return wrapper_class(retval)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_exceptions.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_exceptions.py
deleted file mode 100644
index 625437a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_exceptions.py
+++ /dev/null
@@ -1,42 +0,0 @@
-from collections import deque
-from typing import Deque
-
-
-class TypeHintWarning(UserWarning):
-    """
-    A warning that is emitted when a type hint in string form could not be resolved to
-    an actual type.
-    """
-
-
-class TypeCheckWarning(UserWarning):
-    """Emitted by typeguard's type checkers when a type mismatch is detected."""
-
-    def __init__(self, message: str):
-        super().__init__(message)
-
-
-class InstrumentationWarning(UserWarning):
-    """Emitted when there's a problem with instrumenting a function for type checks."""
-
-    def __init__(self, message: str):
-        super().__init__(message)
-
-
-class TypeCheckError(Exception):
-    """
-    Raised by typeguard's type checkers when a type mismatch is detected.
-    """
-
-    def __init__(self, message: str):
-        super().__init__(message)
-        self._path: Deque[str] = deque()
-
-    def append_path_element(self, element: str) -> None:
-        self._path.append(element)
-
-    def __str__(self) -> str:
-        if self._path:
-            return " of ".join(self._path) + " " + str(self.args[0])
-        else:
-            return str(self.args[0])
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_functions.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_functions.py
deleted file mode 100644
index 2849785..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_functions.py
+++ /dev/null
@@ -1,308 +0,0 @@
-from __future__ import annotations
-
-import sys
-import warnings
-from typing import Any, Callable, NoReturn, TypeVar, Union, overload
-
-from . import _suppression
-from ._checkers import BINARY_MAGIC_METHODS, check_type_internal
-from ._config import (
-    CollectionCheckStrategy,
-    ForwardRefPolicy,
-    TypeCheckConfiguration,
-)
-from ._exceptions import TypeCheckError, TypeCheckWarning
-from ._memo import TypeCheckMemo
-from ._utils import get_stacklevel, qualified_name
-
-if sys.version_info >= (3, 11):
-    from typing import Literal, Never, TypeAlias
-else:
-    from typing_extensions import Literal, Never, TypeAlias
-
-T = TypeVar("T")
-TypeCheckFailCallback: TypeAlias = Callable[[TypeCheckError, TypeCheckMemo], Any]
-
-
-@overload
-def check_type(
-    value: object,
-    expected_type: type[T],
-    *,
-    forward_ref_policy: ForwardRefPolicy = ...,
-    typecheck_fail_callback: TypeCheckFailCallback | None = ...,
-    collection_check_strategy: CollectionCheckStrategy = ...,
-) -> T: ...
-
-
-@overload
-def check_type(
-    value: object,
-    expected_type: Any,
-    *,
-    forward_ref_policy: ForwardRefPolicy = ...,
-    typecheck_fail_callback: TypeCheckFailCallback | None = ...,
-    collection_check_strategy: CollectionCheckStrategy = ...,
-) -> Any: ...
-
-
-def check_type(
-    value: object,
-    expected_type: Any,
-    *,
-    forward_ref_policy: ForwardRefPolicy = TypeCheckConfiguration().forward_ref_policy,
-    typecheck_fail_callback: TypeCheckFailCallback | None = (
-        TypeCheckConfiguration().typecheck_fail_callback
-    ),
-    collection_check_strategy: CollectionCheckStrategy = (
-        TypeCheckConfiguration().collection_check_strategy
-    ),
-) -> Any:
-    """
-    Ensure that ``value`` matches ``expected_type``.
-
-    The types from the :mod:`typing` module do not support :func:`isinstance` or
-    :func:`issubclass` so a number of type specific checks are required. This function
-    knows which checker to call for which type.
-
-    This function wraps :func:`~.check_type_internal` in the following ways:
-
-    * Respects type checking suppression (:func:`~.suppress_type_checks`)
-    * Forms a :class:`~.TypeCheckMemo` from the current stack frame
-    * Calls the configured type check fail callback if the check fails
-
-    Note that this function is independent of the globally shared configuration in
-    :data:`typeguard.config`. This means that usage within libraries is safe from being
-    affected configuration changes made by other libraries or by the integrating
-    application. Instead, configuration options have the same default values as their
-    corresponding fields in :class:`TypeCheckConfiguration`.
-
-    :param value: value to be checked against ``expected_type``
-    :param expected_type: a class or generic type instance, or a tuple of such things
-    :param forward_ref_policy: see :attr:`TypeCheckConfiguration.forward_ref_policy`
-    :param typecheck_fail_callback:
-        see :attr`TypeCheckConfiguration.typecheck_fail_callback`
-    :param collection_check_strategy:
-        see :attr:`TypeCheckConfiguration.collection_check_strategy`
-    :return: ``value``, unmodified
-    :raises TypeCheckError: if there is a type mismatch
-
-    """
-    if type(expected_type) is tuple:
-        expected_type = Union[expected_type]
-
-    config = TypeCheckConfiguration(
-        forward_ref_policy=forward_ref_policy,
-        typecheck_fail_callback=typecheck_fail_callback,
-        collection_check_strategy=collection_check_strategy,
-    )
-
-    if _suppression.type_checks_suppressed or expected_type is Any:
-        return value
-
-    frame = sys._getframe(1)
-    memo = TypeCheckMemo(frame.f_globals, frame.f_locals, config=config)
-    try:
-        check_type_internal(value, expected_type, memo)
-    except TypeCheckError as exc:
-        exc.append_path_element(qualified_name(value, add_class_prefix=True))
-        if config.typecheck_fail_callback:
-            config.typecheck_fail_callback(exc, memo)
-        else:
-            raise
-
-    return value
-
-
-def check_argument_types(
-    func_name: str,
-    arguments: dict[str, tuple[Any, Any]],
-    memo: TypeCheckMemo,
-) -> Literal[True]:
-    if _suppression.type_checks_suppressed:
-        return True
-
-    for argname, (value, annotation) in arguments.items():
-        if annotation is NoReturn or annotation is Never:
-            exc = TypeCheckError(
-                f"{func_name}() was declared never to be called but it was"
-            )
-            if memo.config.typecheck_fail_callback:
-                memo.config.typecheck_fail_callback(exc, memo)
-            else:
-                raise exc
-
-        try:
-            check_type_internal(value, annotation, memo)
-        except TypeCheckError as exc:
-            qualname = qualified_name(value, add_class_prefix=True)
-            exc.append_path_element(f'argument "{argname}" ({qualname})')
-            if memo.config.typecheck_fail_callback:
-                memo.config.typecheck_fail_callback(exc, memo)
-            else:
-                raise
-
-    return True
-
-
-def check_return_type(
-    func_name: str,
-    retval: T,
-    annotation: Any,
-    memo: TypeCheckMemo,
-) -> T:
-    if _suppression.type_checks_suppressed:
-        return retval
-
-    if annotation is NoReturn or annotation is Never:
-        exc = TypeCheckError(f"{func_name}() was declared never to return but it did")
-        if memo.config.typecheck_fail_callback:
-            memo.config.typecheck_fail_callback(exc, memo)
-        else:
-            raise exc
-
-    try:
-        check_type_internal(retval, annotation, memo)
-    except TypeCheckError as exc:
-        # Allow NotImplemented if this is a binary magic method (__eq__() et al)
-        if retval is NotImplemented and annotation is bool:
-            # This does (and cannot) not check if it's actually a method
-            func_name = func_name.rsplit(".", 1)[-1]
-            if func_name in BINARY_MAGIC_METHODS:
-                return retval
-
-        qualname = qualified_name(retval, add_class_prefix=True)
-        exc.append_path_element(f"the return value ({qualname})")
-        if memo.config.typecheck_fail_callback:
-            memo.config.typecheck_fail_callback(exc, memo)
-        else:
-            raise
-
-    return retval
-
-
-def check_send_type(
-    func_name: str,
-    sendval: T,
-    annotation: Any,
-    memo: TypeCheckMemo,
-) -> T:
-    if _suppression.type_checks_suppressed:
-        return sendval
-
-    if annotation is NoReturn or annotation is Never:
-        exc = TypeCheckError(
-            f"{func_name}() was declared never to be sent a value to but it was"
-        )
-        if memo.config.typecheck_fail_callback:
-            memo.config.typecheck_fail_callback(exc, memo)
-        else:
-            raise exc
-
-    try:
-        check_type_internal(sendval, annotation, memo)
-    except TypeCheckError as exc:
-        qualname = qualified_name(sendval, add_class_prefix=True)
-        exc.append_path_element(f"the value sent to generator ({qualname})")
-        if memo.config.typecheck_fail_callback:
-            memo.config.typecheck_fail_callback(exc, memo)
-        else:
-            raise
-
-    return sendval
-
-
-def check_yield_type(
-    func_name: str,
-    yieldval: T,
-    annotation: Any,
-    memo: TypeCheckMemo,
-) -> T:
-    if _suppression.type_checks_suppressed:
-        return yieldval
-
-    if annotation is NoReturn or annotation is Never:
-        exc = TypeCheckError(f"{func_name}() was declared never to yield but it did")
-        if memo.config.typecheck_fail_callback:
-            memo.config.typecheck_fail_callback(exc, memo)
-        else:
-            raise exc
-
-    try:
-        check_type_internal(yieldval, annotation, memo)
-    except TypeCheckError as exc:
-        qualname = qualified_name(yieldval, add_class_prefix=True)
-        exc.append_path_element(f"the yielded value ({qualname})")
-        if memo.config.typecheck_fail_callback:
-            memo.config.typecheck_fail_callback(exc, memo)
-        else:
-            raise
-
-    return yieldval
-
-
-def check_variable_assignment(
-    value: object, varname: str, annotation: Any, memo: TypeCheckMemo
-) -> Any:
-    if _suppression.type_checks_suppressed:
-        return value
-
-    try:
-        check_type_internal(value, annotation, memo)
-    except TypeCheckError as exc:
-        qualname = qualified_name(value, add_class_prefix=True)
-        exc.append_path_element(f"value assigned to {varname} ({qualname})")
-        if memo.config.typecheck_fail_callback:
-            memo.config.typecheck_fail_callback(exc, memo)
-        else:
-            raise
-
-    return value
-
-
-def check_multi_variable_assignment(
-    value: Any, targets: list[dict[str, Any]], memo: TypeCheckMemo
-) -> Any:
-    if max(len(target) for target in targets) == 1:
-        iterated_values = [value]
-    else:
-        iterated_values = list(value)
-
-    if not _suppression.type_checks_suppressed:
-        for expected_types in targets:
-            value_index = 0
-            for ann_index, (varname, expected_type) in enumerate(
-                expected_types.items()
-            ):
-                if varname.startswith("*"):
-                    varname = varname[1:]
-                    keys_left = len(expected_types) - 1 - ann_index
-                    next_value_index = len(iterated_values) - keys_left
-                    obj: object = iterated_values[value_index:next_value_index]
-                    value_index = next_value_index
-                else:
-                    obj = iterated_values[value_index]
-                    value_index += 1
-
-                try:
-                    check_type_internal(obj, expected_type, memo)
-                except TypeCheckError as exc:
-                    qualname = qualified_name(obj, add_class_prefix=True)
-                    exc.append_path_element(f"value assigned to {varname} ({qualname})")
-                    if memo.config.typecheck_fail_callback:
-                        memo.config.typecheck_fail_callback(exc, memo)
-                    else:
-                        raise
-
-    return iterated_values[0] if len(iterated_values) == 1 else iterated_values
-
-
-def warn_on_error(exc: TypeCheckError, memo: TypeCheckMemo) -> None:
-    """
-    Emit a warning on a type mismatch.
-
-    This is intended to be used as an error handler in
-    :attr:`TypeCheckConfiguration.typecheck_fail_callback`.
-
-    """
-    warnings.warn(TypeCheckWarning(str(exc)), stacklevel=get_stacklevel())
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_importhook.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_importhook.py
deleted file mode 100644
index 8590540..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_importhook.py
+++ /dev/null
@@ -1,213 +0,0 @@
-from __future__ import annotations
-
-import ast
-import sys
-import types
-from collections.abc import Callable, Iterable
-from importlib.abc import MetaPathFinder
-from importlib.machinery import ModuleSpec, SourceFileLoader
-from importlib.util import cache_from_source, decode_source
-from inspect import isclass
-from os import PathLike
-from types import CodeType, ModuleType, TracebackType
-from typing import Sequence, TypeVar
-from unittest.mock import patch
-
-from ._config import global_config
-from ._transformer import TypeguardTransformer
-
-if sys.version_info >= (3, 12):
-    from collections.abc import Buffer
-else:
-    from typing_extensions import Buffer
-
-if sys.version_info >= (3, 11):
-    from typing import ParamSpec
-else:
-    from typing_extensions import ParamSpec
-
-if sys.version_info >= (3, 10):
-    from importlib.metadata import PackageNotFoundError, version
-else:
-    from importlib_metadata import PackageNotFoundError, version
-
-try:
-    OPTIMIZATION = "typeguard" + "".join(version("typeguard").split(".")[:3])
-except PackageNotFoundError:
-    OPTIMIZATION = "typeguard"
-
-P = ParamSpec("P")
-T = TypeVar("T")
-
-
-# The name of this function is magical
-def _call_with_frames_removed(
-    f: Callable[P, T], *args: P.args, **kwargs: P.kwargs
-) -> T:
-    return f(*args, **kwargs)
-
-
-def optimized_cache_from_source(path: str, debug_override: bool | None = None) -> str:
-    return cache_from_source(path, debug_override, optimization=OPTIMIZATION)
-
-
-class TypeguardLoader(SourceFileLoader):
-    @staticmethod
-    def source_to_code(
-        data: Buffer | str | ast.Module | ast.Expression | ast.Interactive,
-        path: Buffer | str | PathLike[str] = "",
-    ) -> CodeType:
-        if isinstance(data, (ast.Module, ast.Expression, ast.Interactive)):
-            tree = data
-        else:
-            if isinstance(data, str):
-                source = data
-            else:
-                source = decode_source(data)
-
-            tree = _call_with_frames_removed(
-                ast.parse,
-                source,
-                path,
-                "exec",
-            )
-
-        tree = TypeguardTransformer().visit(tree)
-        ast.fix_missing_locations(tree)
-
-        if global_config.debug_instrumentation and sys.version_info >= (3, 9):
-            print(
-                f"Source code of {path!r} after instrumentation:\n"
-                "----------------------------------------------",
-                file=sys.stderr,
-            )
-            print(ast.unparse(tree), file=sys.stderr)
-            print("----------------------------------------------", file=sys.stderr)
-
-        return _call_with_frames_removed(
-            compile, tree, path, "exec", 0, dont_inherit=True
-        )
-
-    def exec_module(self, module: ModuleType) -> None:
-        # Use a custom optimization marker – the import lock should make this monkey
-        # patch safe
-        with patch(
-            "importlib._bootstrap_external.cache_from_source",
-            optimized_cache_from_source,
-        ):
-            super().exec_module(module)
-
-
-class TypeguardFinder(MetaPathFinder):
-    """
-    Wraps another path finder and instruments the module with
-    :func:`@typechecked ` if :meth:`should_instrument` returns
-    ``True``.
-
-    Should not be used directly, but rather via :func:`~.install_import_hook`.
-
-    .. versionadded:: 2.6
-    """
-
-    def __init__(self, packages: list[str] | None, original_pathfinder: MetaPathFinder):
-        self.packages = packages
-        self._original_pathfinder = original_pathfinder
-
-    def find_spec(
-        self,
-        fullname: str,
-        path: Sequence[str] | None,
-        target: types.ModuleType | None = None,
-    ) -> ModuleSpec | None:
-        if self.should_instrument(fullname):
-            spec = self._original_pathfinder.find_spec(fullname, path, target)
-            if spec is not None and isinstance(spec.loader, SourceFileLoader):
-                spec.loader = TypeguardLoader(spec.loader.name, spec.loader.path)
-                return spec
-
-        return None
-
-    def should_instrument(self, module_name: str) -> bool:
-        """
-        Determine whether the module with the given name should be instrumented.
-
-        :param module_name: full name of the module that is about to be imported (e.g.
-            ``xyz.abc``)
-
-        """
-        if self.packages is None:
-            return True
-
-        for package in self.packages:
-            if module_name == package or module_name.startswith(package + "."):
-                return True
-
-        return False
-
-
-class ImportHookManager:
-    """
-    A handle that can be used to uninstall the Typeguard import hook.
-    """
-
-    def __init__(self, hook: MetaPathFinder):
-        self.hook = hook
-
-    def __enter__(self) -> None:
-        pass
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException],
-        exc_val: BaseException,
-        exc_tb: TracebackType,
-    ) -> None:
-        self.uninstall()
-
-    def uninstall(self) -> None:
-        """Uninstall the import hook."""
-        try:
-            sys.meta_path.remove(self.hook)
-        except ValueError:
-            pass  # already removed
-
-
-def install_import_hook(
-    packages: Iterable[str] | None = None,
-    *,
-    cls: type[TypeguardFinder] = TypeguardFinder,
-) -> ImportHookManager:
-    """
-    Install an import hook that instruments functions for automatic type checking.
-
-    This only affects modules loaded **after** this hook has been installed.
-
-    :param packages: an iterable of package names to instrument, or ``None`` to
-        instrument all packages
-    :param cls: a custom meta path finder class
-    :return: a context manager that uninstalls the hook on exit (or when you call
-        ``.uninstall()``)
-
-    .. versionadded:: 2.6
-
-    """
-    if packages is None:
-        target_packages: list[str] | None = None
-    elif isinstance(packages, str):
-        target_packages = [packages]
-    else:
-        target_packages = list(packages)
-
-    for finder in sys.meta_path:
-        if (
-            isclass(finder)
-            and finder.__name__ == "PathFinder"
-            and hasattr(finder, "find_spec")
-        ):
-            break
-    else:
-        raise RuntimeError("Cannot find a PathFinder in sys.meta_path")
-
-    hook = cls(target_packages, finder)
-    sys.meta_path.insert(0, hook)
-    return ImportHookManager(hook)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_memo.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_memo.py
deleted file mode 100644
index 1d0d80c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_memo.py
+++ /dev/null
@@ -1,48 +0,0 @@
-from __future__ import annotations
-
-from typing import Any
-
-from typeguard._config import TypeCheckConfiguration, global_config
-
-
-class TypeCheckMemo:
-    """
-    Contains information necessary for type checkers to do their work.
-
-    .. attribute:: globals
-       :type: dict[str, Any]
-
-        Dictionary of global variables to use for resolving forward references.
-
-    .. attribute:: locals
-       :type: dict[str, Any]
-
-        Dictionary of local variables to use for resolving forward references.
-
-    .. attribute:: self_type
-       :type: type | None
-
-        When running type checks within an instance method or class method, this is the
-        class object that the first argument (usually named ``self`` or ``cls``) refers
-        to.
-
-    .. attribute:: config
-       :type: TypeCheckConfiguration
-
-         Contains the configuration for a particular set of type checking operations.
-    """
-
-    __slots__ = "globals", "locals", "self_type", "config"
-
-    def __init__(
-        self,
-        globals: dict[str, Any],
-        locals: dict[str, Any],
-        *,
-        self_type: type | None = None,
-        config: TypeCheckConfiguration = global_config,
-    ):
-        self.globals = globals
-        self.locals = locals
-        self.self_type = self_type
-        self.config = config
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_pytest_plugin.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_pytest_plugin.py
deleted file mode 100644
index 7b2f494..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_pytest_plugin.py
+++ /dev/null
@@ -1,127 +0,0 @@
-from __future__ import annotations
-
-import sys
-import warnings
-from typing import TYPE_CHECKING, Any, Literal
-
-from typeguard._config import CollectionCheckStrategy, ForwardRefPolicy, global_config
-from typeguard._exceptions import InstrumentationWarning
-from typeguard._importhook import install_import_hook
-from typeguard._utils import qualified_name, resolve_reference
-
-if TYPE_CHECKING:
-    from pytest import Config, Parser
-
-
-def pytest_addoption(parser: Parser) -> None:
-    def add_ini_option(
-        opt_type: (
-            Literal["string", "paths", "pathlist", "args", "linelist", "bool"] | None
-        ),
-    ) -> None:
-        parser.addini(
-            group.options[-1].names()[0][2:],
-            group.options[-1].attrs()["help"],
-            opt_type,
-        )
-
-    group = parser.getgroup("typeguard")
-    group.addoption(
-        "--typeguard-packages",
-        action="store",
-        help="comma separated name list of packages and modules to instrument for "
-        "type checking, or :all: to instrument all modules loaded after typeguard",
-    )
-    add_ini_option("linelist")
-
-    group.addoption(
-        "--typeguard-debug-instrumentation",
-        action="store_true",
-        help="print all instrumented code to stderr",
-    )
-    add_ini_option("bool")
-
-    group.addoption(
-        "--typeguard-typecheck-fail-callback",
-        action="store",
-        help=(
-            "a module:varname (e.g. typeguard:warn_on_error) reference to a function "
-            "that is called (with the exception, and memo object as arguments) to "
-            "handle a TypeCheckError"
-        ),
-    )
-    add_ini_option("string")
-
-    group.addoption(
-        "--typeguard-forward-ref-policy",
-        action="store",
-        choices=list(ForwardRefPolicy.__members__),
-        help=(
-            "determines how to deal with unresolveable forward references in type "
-            "annotations"
-        ),
-    )
-    add_ini_option("string")
-
-    group.addoption(
-        "--typeguard-collection-check-strategy",
-        action="store",
-        choices=list(CollectionCheckStrategy.__members__),
-        help="determines how thoroughly to check collections (list, dict, etc)",
-    )
-    add_ini_option("string")
-
-
-def pytest_configure(config: Config) -> None:
-    def getoption(name: str) -> Any:
-        return config.getoption(name.replace("-", "_")) or config.getini(name)
-
-    packages: list[str] | None = []
-    if packages_option := config.getoption("typeguard_packages"):
-        packages = [pkg.strip() for pkg in packages_option.split(",")]
-    elif packages_ini := config.getini("typeguard-packages"):
-        packages = packages_ini
-
-    if packages:
-        if packages == [":all:"]:
-            packages = None
-        else:
-            already_imported_packages = sorted(
-                package for package in packages if package in sys.modules
-            )
-            if already_imported_packages:
-                warnings.warn(
-                    f"typeguard cannot check these packages because they are already "
-                    f"imported: {', '.join(already_imported_packages)}",
-                    InstrumentationWarning,
-                    stacklevel=1,
-                )
-
-        install_import_hook(packages=packages)
-
-    debug_option = getoption("typeguard-debug-instrumentation")
-    if debug_option:
-        global_config.debug_instrumentation = True
-
-    fail_callback_option = getoption("typeguard-typecheck-fail-callback")
-    if fail_callback_option:
-        callback = resolve_reference(fail_callback_option)
-        if not callable(callback):
-            raise TypeError(
-                f"{fail_callback_option} ({qualified_name(callback.__class__)}) is not "
-                f"a callable"
-            )
-
-        global_config.typecheck_fail_callback = callback
-
-    forward_ref_policy_option = getoption("typeguard-forward-ref-policy")
-    if forward_ref_policy_option:
-        forward_ref_policy = ForwardRefPolicy.__members__[forward_ref_policy_option]
-        global_config.forward_ref_policy = forward_ref_policy
-
-    collection_check_strategy_option = getoption("typeguard-collection-check-strategy")
-    if collection_check_strategy_option:
-        collection_check_strategy = CollectionCheckStrategy.__members__[
-            collection_check_strategy_option
-        ]
-        global_config.collection_check_strategy = collection_check_strategy
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_suppression.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_suppression.py
deleted file mode 100644
index bbbfbfb..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_suppression.py
+++ /dev/null
@@ -1,86 +0,0 @@
-from __future__ import annotations
-
-import sys
-from collections.abc import Callable, Generator
-from contextlib import contextmanager
-from functools import update_wrapper
-from threading import Lock
-from typing import ContextManager, TypeVar, overload
-
-if sys.version_info >= (3, 10):
-    from typing import ParamSpec
-else:
-    from typing_extensions import ParamSpec
-
-P = ParamSpec("P")
-T = TypeVar("T")
-
-type_checks_suppressed = 0
-type_checks_suppress_lock = Lock()
-
-
-@overload
-def suppress_type_checks(func: Callable[P, T]) -> Callable[P, T]: ...
-
-
-@overload
-def suppress_type_checks() -> ContextManager[None]: ...
-
-
-def suppress_type_checks(
-    func: Callable[P, T] | None = None,
-) -> Callable[P, T] | ContextManager[None]:
-    """
-    Temporarily suppress all type checking.
-
-    This function has two operating modes, based on how it's used:
-
-    #. as a context manager (``with suppress_type_checks(): ...``)
-    #. as a decorator (``@suppress_type_checks``)
-
-    When used as a context manager, :func:`check_type` and any automatically
-    instrumented functions skip the actual type checking. These context managers can be
-    nested.
-
-    When used as a decorator, all type checking is suppressed while the function is
-    running.
-
-    Type checking will resume once no more context managers are active and no decorated
-    functions are running.
-
-    Both operating modes are thread-safe.
-
-    """
-
-    def wrapper(*args: P.args, **kwargs: P.kwargs) -> T:
-        global type_checks_suppressed
-
-        with type_checks_suppress_lock:
-            type_checks_suppressed += 1
-
-        assert func is not None
-        try:
-            return func(*args, **kwargs)
-        finally:
-            with type_checks_suppress_lock:
-                type_checks_suppressed -= 1
-
-    def cm() -> Generator[None, None, None]:
-        global type_checks_suppressed
-
-        with type_checks_suppress_lock:
-            type_checks_suppressed += 1
-
-        try:
-            yield
-        finally:
-            with type_checks_suppress_lock:
-                type_checks_suppressed -= 1
-
-    if func is None:
-        # Context manager mode
-        return contextmanager(cm)()
-    else:
-        # Decorator mode
-        update_wrapper(wrapper, func)
-        return wrapper
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_transformer.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_transformer.py
deleted file mode 100644
index 13ac363..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_transformer.py
+++ /dev/null
@@ -1,1229 +0,0 @@
-from __future__ import annotations
-
-import ast
-import builtins
-import sys
-import typing
-from ast import (
-    AST,
-    Add,
-    AnnAssign,
-    Assign,
-    AsyncFunctionDef,
-    Attribute,
-    AugAssign,
-    BinOp,
-    BitAnd,
-    BitOr,
-    BitXor,
-    Call,
-    ClassDef,
-    Constant,
-    Dict,
-    Div,
-    Expr,
-    Expression,
-    FloorDiv,
-    FunctionDef,
-    If,
-    Import,
-    ImportFrom,
-    Index,
-    List,
-    Load,
-    LShift,
-    MatMult,
-    Mod,
-    Module,
-    Mult,
-    Name,
-    NamedExpr,
-    NodeTransformer,
-    NodeVisitor,
-    Pass,
-    Pow,
-    Return,
-    RShift,
-    Starred,
-    Store,
-    Sub,
-    Subscript,
-    Tuple,
-    Yield,
-    YieldFrom,
-    alias,
-    copy_location,
-    expr,
-    fix_missing_locations,
-    keyword,
-    walk,
-)
-from collections import defaultdict
-from collections.abc import Generator, Sequence
-from contextlib import contextmanager
-from copy import deepcopy
-from dataclasses import dataclass, field
-from typing import Any, ClassVar, cast, overload
-
-generator_names = (
-    "typing.Generator",
-    "collections.abc.Generator",
-    "typing.Iterator",
-    "collections.abc.Iterator",
-    "typing.Iterable",
-    "collections.abc.Iterable",
-    "typing.AsyncIterator",
-    "collections.abc.AsyncIterator",
-    "typing.AsyncIterable",
-    "collections.abc.AsyncIterable",
-    "typing.AsyncGenerator",
-    "collections.abc.AsyncGenerator",
-)
-anytype_names = (
-    "typing.Any",
-    "typing_extensions.Any",
-)
-literal_names = (
-    "typing.Literal",
-    "typing_extensions.Literal",
-)
-annotated_names = (
-    "typing.Annotated",
-    "typing_extensions.Annotated",
-)
-ignore_decorators = (
-    "typing.no_type_check",
-    "typeguard.typeguard_ignore",
-)
-aug_assign_functions = {
-    Add: "iadd",
-    Sub: "isub",
-    Mult: "imul",
-    MatMult: "imatmul",
-    Div: "itruediv",
-    FloorDiv: "ifloordiv",
-    Mod: "imod",
-    Pow: "ipow",
-    LShift: "ilshift",
-    RShift: "irshift",
-    BitAnd: "iand",
-    BitXor: "ixor",
-    BitOr: "ior",
-}
-
-
-@dataclass
-class TransformMemo:
-    node: Module | ClassDef | FunctionDef | AsyncFunctionDef | None
-    parent: TransformMemo | None
-    path: tuple[str, ...]
-    joined_path: Constant = field(init=False)
-    return_annotation: expr | None = None
-    yield_annotation: expr | None = None
-    send_annotation: expr | None = None
-    is_async: bool = False
-    local_names: set[str] = field(init=False, default_factory=set)
-    imported_names: dict[str, str] = field(init=False, default_factory=dict)
-    ignored_names: set[str] = field(init=False, default_factory=set)
-    load_names: defaultdict[str, dict[str, Name]] = field(
-        init=False, default_factory=lambda: defaultdict(dict)
-    )
-    has_yield_expressions: bool = field(init=False, default=False)
-    has_return_expressions: bool = field(init=False, default=False)
-    memo_var_name: Name | None = field(init=False, default=None)
-    should_instrument: bool = field(init=False, default=True)
-    variable_annotations: dict[str, expr] = field(init=False, default_factory=dict)
-    configuration_overrides: dict[str, Any] = field(init=False, default_factory=dict)
-    code_inject_index: int = field(init=False, default=0)
-
-    def __post_init__(self) -> None:
-        elements: list[str] = []
-        memo = self
-        while isinstance(memo.node, (ClassDef, FunctionDef, AsyncFunctionDef)):
-            elements.insert(0, memo.node.name)
-            if not memo.parent:
-                break
-
-            memo = memo.parent
-            if isinstance(memo.node, (FunctionDef, AsyncFunctionDef)):
-                elements.insert(0, "")
-
-        self.joined_path = Constant(".".join(elements))
-
-        # Figure out where to insert instrumentation code
-        if self.node:
-            for index, child in enumerate(self.node.body):
-                if isinstance(child, ImportFrom) and child.module == "__future__":
-                    # (module only) __future__ imports must come first
-                    continue
-                elif (
-                    isinstance(child, Expr)
-                    and isinstance(child.value, Constant)
-                    and isinstance(child.value.value, str)
-                ):
-                    continue  # docstring
-
-                self.code_inject_index = index
-                break
-
-    def get_unused_name(self, name: str) -> str:
-        memo: TransformMemo | None = self
-        while memo is not None:
-            if name in memo.local_names:
-                memo = self
-                name += "_"
-            else:
-                memo = memo.parent
-
-        self.local_names.add(name)
-        return name
-
-    def is_ignored_name(self, expression: expr | Expr | None) -> bool:
-        top_expression = (
-            expression.value if isinstance(expression, Expr) else expression
-        )
-
-        if isinstance(top_expression, Attribute) and isinstance(
-            top_expression.value, Name
-        ):
-            name = top_expression.value.id
-        elif isinstance(top_expression, Name):
-            name = top_expression.id
-        else:
-            return False
-
-        memo: TransformMemo | None = self
-        while memo is not None:
-            if name in memo.ignored_names:
-                return True
-
-            memo = memo.parent
-
-        return False
-
-    def get_memo_name(self) -> Name:
-        if not self.memo_var_name:
-            self.memo_var_name = Name(id="memo", ctx=Load())
-
-        return self.memo_var_name
-
-    def get_import(self, module: str, name: str) -> Name:
-        if module in self.load_names and name in self.load_names[module]:
-            return self.load_names[module][name]
-
-        qualified_name = f"{module}.{name}"
-        if name in self.imported_names and self.imported_names[name] == qualified_name:
-            return Name(id=name, ctx=Load())
-
-        alias = self.get_unused_name(name)
-        node = self.load_names[module][name] = Name(id=alias, ctx=Load())
-        self.imported_names[name] = qualified_name
-        return node
-
-    def insert_imports(self, node: Module | FunctionDef | AsyncFunctionDef) -> None:
-        """Insert imports needed by injected code."""
-        if not self.load_names:
-            return
-
-        # Insert imports after any "from __future__ ..." imports and any docstring
-        for modulename, names in self.load_names.items():
-            aliases = [
-                alias(orig_name, new_name.id if orig_name != new_name.id else None)
-                for orig_name, new_name in sorted(names.items())
-            ]
-            node.body.insert(self.code_inject_index, ImportFrom(modulename, aliases, 0))
-
-    def name_matches(self, expression: expr | Expr | None, *names: str) -> bool:
-        if expression is None:
-            return False
-
-        path: list[str] = []
-        top_expression = (
-            expression.value if isinstance(expression, Expr) else expression
-        )
-
-        if isinstance(top_expression, Subscript):
-            top_expression = top_expression.value
-        elif isinstance(top_expression, Call):
-            top_expression = top_expression.func
-
-        while isinstance(top_expression, Attribute):
-            path.insert(0, top_expression.attr)
-            top_expression = top_expression.value
-
-        if not isinstance(top_expression, Name):
-            return False
-
-        if top_expression.id in self.imported_names:
-            translated = self.imported_names[top_expression.id]
-        elif hasattr(builtins, top_expression.id):
-            translated = "builtins." + top_expression.id
-        else:
-            translated = top_expression.id
-
-        path.insert(0, translated)
-        joined_path = ".".join(path)
-        if joined_path in names:
-            return True
-        elif self.parent:
-            return self.parent.name_matches(expression, *names)
-        else:
-            return False
-
-    def get_config_keywords(self) -> list[keyword]:
-        if self.parent and isinstance(self.parent.node, ClassDef):
-            overrides = self.parent.configuration_overrides.copy()
-        else:
-            overrides = {}
-
-        overrides.update(self.configuration_overrides)
-        return [keyword(key, value) for key, value in overrides.items()]
-
-
-class NameCollector(NodeVisitor):
-    def __init__(self) -> None:
-        self.names: set[str] = set()
-
-    def visit_Import(self, node: Import) -> None:
-        for name in node.names:
-            self.names.add(name.asname or name.name)
-
-    def visit_ImportFrom(self, node: ImportFrom) -> None:
-        for name in node.names:
-            self.names.add(name.asname or name.name)
-
-    def visit_Assign(self, node: Assign) -> None:
-        for target in node.targets:
-            if isinstance(target, Name):
-                self.names.add(target.id)
-
-    def visit_NamedExpr(self, node: NamedExpr) -> Any:
-        if isinstance(node.target, Name):
-            self.names.add(node.target.id)
-
-    def visit_FunctionDef(self, node: FunctionDef) -> None:
-        pass
-
-    def visit_ClassDef(self, node: ClassDef) -> None:
-        pass
-
-
-class GeneratorDetector(NodeVisitor):
-    """Detects if a function node is a generator function."""
-
-    contains_yields: bool = False
-    in_root_function: bool = False
-
-    def visit_Yield(self, node: Yield) -> Any:
-        self.contains_yields = True
-
-    def visit_YieldFrom(self, node: YieldFrom) -> Any:
-        self.contains_yields = True
-
-    def visit_ClassDef(self, node: ClassDef) -> Any:
-        pass
-
-    def visit_FunctionDef(self, node: FunctionDef | AsyncFunctionDef) -> Any:
-        if not self.in_root_function:
-            self.in_root_function = True
-            self.generic_visit(node)
-            self.in_root_function = False
-
-    def visit_AsyncFunctionDef(self, node: AsyncFunctionDef) -> Any:
-        self.visit_FunctionDef(node)
-
-
-class AnnotationTransformer(NodeTransformer):
-    type_substitutions: ClassVar[dict[str, tuple[str, str]]] = {
-        "builtins.dict": ("typing", "Dict"),
-        "builtins.list": ("typing", "List"),
-        "builtins.tuple": ("typing", "Tuple"),
-        "builtins.set": ("typing", "Set"),
-        "builtins.frozenset": ("typing", "FrozenSet"),
-    }
-
-    def __init__(self, transformer: TypeguardTransformer):
-        self.transformer = transformer
-        self._memo = transformer._memo
-        self._level = 0
-
-    def visit(self, node: AST) -> Any:
-        # Don't process Literals
-        if isinstance(node, expr) and self._memo.name_matches(node, *literal_names):
-            return node
-
-        self._level += 1
-        new_node = super().visit(node)
-        self._level -= 1
-
-        if isinstance(new_node, Expression) and not hasattr(new_node, "body"):
-            return None
-
-        # Return None if this new node matches a variation of typing.Any
-        if (
-            self._level == 0
-            and isinstance(new_node, expr)
-            and self._memo.name_matches(new_node, *anytype_names)
-        ):
-            return None
-
-        return new_node
-
-    def visit_BinOp(self, node: BinOp) -> Any:
-        self.generic_visit(node)
-
-        if isinstance(node.op, BitOr):
-            # If either branch of the BinOp has been transformed to `None`, it means
-            # that a type in the union was ignored, so the entire annotation should e
-            # ignored
-            if not hasattr(node, "left") or not hasattr(node, "right"):
-                return None
-
-            # Return Any if either side is Any
-            if self._memo.name_matches(node.left, *anytype_names):
-                return node.left
-            elif self._memo.name_matches(node.right, *anytype_names):
-                return node.right
-
-            if sys.version_info < (3, 10):
-                union_name = self.transformer._get_import("typing", "Union")
-                return Subscript(
-                    value=union_name,
-                    slice=Index(
-                        Tuple(elts=[node.left, node.right], ctx=Load()), ctx=Load()
-                    ),
-                    ctx=Load(),
-                )
-
-        return node
-
-    def visit_Attribute(self, node: Attribute) -> Any:
-        if self._memo.is_ignored_name(node):
-            return None
-
-        return node
-
-    def visit_Subscript(self, node: Subscript) -> Any:
-        if self._memo.is_ignored_name(node.value):
-            return None
-
-        # The subscript of typing(_extensions).Literal can be any arbitrary string, so
-        # don't try to evaluate it as code
-        if node.slice:
-            if isinstance(node.slice, Index):
-                # Python 3.8
-                slice_value = node.slice.value  # type: ignore[attr-defined]
-            else:
-                slice_value = node.slice
-
-            if isinstance(slice_value, Tuple):
-                if self._memo.name_matches(node.value, *annotated_names):
-                    # Only treat the first argument to typing.Annotated as a potential
-                    # forward reference
-                    items = cast(
-                        typing.List[expr],
-                        [self.visit(slice_value.elts[0])] + slice_value.elts[1:],
-                    )
-                else:
-                    items = cast(
-                        typing.List[expr],
-                        [self.visit(item) for item in slice_value.elts],
-                    )
-
-                # If this is a Union and any of the items is Any, erase the entire
-                # annotation
-                if self._memo.name_matches(node.value, "typing.Union") and any(
-                    item is None
-                    or (
-                        isinstance(item, expr)
-                        and self._memo.name_matches(item, *anytype_names)
-                    )
-                    for item in items
-                ):
-                    return None
-
-                # If all items in the subscript were Any, erase the subscript entirely
-                if all(item is None for item in items):
-                    return node.value
-
-                for index, item in enumerate(items):
-                    if item is None:
-                        items[index] = self.transformer._get_import("typing", "Any")
-
-                slice_value.elts = items
-            else:
-                self.generic_visit(node)
-
-                # If the transformer erased the slice entirely, just return the node
-                # value without the subscript (unless it's Optional, in which case erase
-                # the node entirely
-                if self._memo.name_matches(
-                    node.value, "typing.Optional"
-                ) and not hasattr(node, "slice"):
-                    return None
-                if sys.version_info >= (3, 9) and not hasattr(node, "slice"):
-                    return node.value
-                elif sys.version_info < (3, 9) and not hasattr(node.slice, "value"):
-                    return node.value
-
-        return node
-
-    def visit_Name(self, node: Name) -> Any:
-        if self._memo.is_ignored_name(node):
-            return None
-
-        if sys.version_info < (3, 9):
-            for typename, substitute in self.type_substitutions.items():
-                if self._memo.name_matches(node, typename):
-                    new_node = self.transformer._get_import(*substitute)
-                    return copy_location(new_node, node)
-
-        return node
-
-    def visit_Call(self, node: Call) -> Any:
-        # Don't recurse into calls
-        return node
-
-    def visit_Constant(self, node: Constant) -> Any:
-        if isinstance(node.value, str):
-            expression = ast.parse(node.value, mode="eval")
-            new_node = self.visit(expression)
-            if new_node:
-                return copy_location(new_node.body, node)
-            else:
-                return None
-
-        return node
-
-
-class TypeguardTransformer(NodeTransformer):
-    def __init__(
-        self, target_path: Sequence[str] | None = None, target_lineno: int | None = None
-    ) -> None:
-        self._target_path = tuple(target_path) if target_path else None
-        self._memo = self._module_memo = TransformMemo(None, None, ())
-        self.names_used_in_annotations: set[str] = set()
-        self.target_node: FunctionDef | AsyncFunctionDef | None = None
-        self.target_lineno = target_lineno
-
-    def generic_visit(self, node: AST) -> AST:
-        has_non_empty_body_initially = bool(getattr(node, "body", None))
-        initial_type = type(node)
-
-        node = super().generic_visit(node)
-
-        if (
-            type(node) is initial_type
-            and has_non_empty_body_initially
-            and hasattr(node, "body")
-            and not node.body
-        ):
-            # If we have still the same node type after transformation
-            # but we've optimised it's body away, we add a `pass` statement.
-            node.body = [Pass()]
-
-        return node
-
-    @contextmanager
-    def _use_memo(
-        self, node: ClassDef | FunctionDef | AsyncFunctionDef
-    ) -> Generator[None, Any, None]:
-        new_memo = TransformMemo(node, self._memo, self._memo.path + (node.name,))
-        old_memo = self._memo
-        self._memo = new_memo
-
-        if isinstance(node, (FunctionDef, AsyncFunctionDef)):
-            new_memo.should_instrument = (
-                self._target_path is None or new_memo.path == self._target_path
-            )
-            if new_memo.should_instrument:
-                # Check if the function is a generator function
-                detector = GeneratorDetector()
-                detector.visit(node)
-
-                # Extract yield, send and return types where possible from a subscripted
-                # annotation like Generator[int, str, bool]
-                return_annotation = deepcopy(node.returns)
-                if detector.contains_yields and new_memo.name_matches(
-                    return_annotation, *generator_names
-                ):
-                    if isinstance(return_annotation, Subscript):
-                        annotation_slice = return_annotation.slice
-
-                        # Python < 3.9
-                        if isinstance(annotation_slice, Index):
-                            annotation_slice = (
-                                annotation_slice.value  # type: ignore[attr-defined]
-                            )
-
-                        if isinstance(annotation_slice, Tuple):
-                            items = annotation_slice.elts
-                        else:
-                            items = [annotation_slice]
-
-                        if len(items) > 0:
-                            new_memo.yield_annotation = self._convert_annotation(
-                                items[0]
-                            )
-
-                        if len(items) > 1:
-                            new_memo.send_annotation = self._convert_annotation(
-                                items[1]
-                            )
-
-                        if len(items) > 2:
-                            new_memo.return_annotation = self._convert_annotation(
-                                items[2]
-                            )
-                else:
-                    new_memo.return_annotation = self._convert_annotation(
-                        return_annotation
-                    )
-
-        if isinstance(node, AsyncFunctionDef):
-            new_memo.is_async = True
-
-        yield
-        self._memo = old_memo
-
-    def _get_import(self, module: str, name: str) -> Name:
-        memo = self._memo if self._target_path else self._module_memo
-        return memo.get_import(module, name)
-
-    @overload
-    def _convert_annotation(self, annotation: None) -> None: ...
-
-    @overload
-    def _convert_annotation(self, annotation: expr) -> expr: ...
-
-    def _convert_annotation(self, annotation: expr | None) -> expr | None:
-        if annotation is None:
-            return None
-
-        # Convert PEP 604 unions (x | y) and generic built-in collections where
-        # necessary, and undo forward references
-        new_annotation = cast(expr, AnnotationTransformer(self).visit(annotation))
-        if isinstance(new_annotation, expr):
-            new_annotation = ast.copy_location(new_annotation, annotation)
-
-            # Store names used in the annotation
-            names = {node.id for node in walk(new_annotation) if isinstance(node, Name)}
-            self.names_used_in_annotations.update(names)
-
-        return new_annotation
-
-    def visit_Name(self, node: Name) -> Name:
-        self._memo.local_names.add(node.id)
-        return node
-
-    def visit_Module(self, node: Module) -> Module:
-        self._module_memo = self._memo = TransformMemo(node, None, ())
-        self.generic_visit(node)
-        self._module_memo.insert_imports(node)
-
-        fix_missing_locations(node)
-        return node
-
-    def visit_Import(self, node: Import) -> Import:
-        for name in node.names:
-            self._memo.local_names.add(name.asname or name.name)
-            self._memo.imported_names[name.asname or name.name] = name.name
-
-        return node
-
-    def visit_ImportFrom(self, node: ImportFrom) -> ImportFrom:
-        for name in node.names:
-            if name.name != "*":
-                alias = name.asname or name.name
-                self._memo.local_names.add(alias)
-                self._memo.imported_names[alias] = f"{node.module}.{name.name}"
-
-        return node
-
-    def visit_ClassDef(self, node: ClassDef) -> ClassDef | None:
-        self._memo.local_names.add(node.name)
-
-        # Eliminate top level classes not belonging to the target path
-        if (
-            self._target_path is not None
-            and not self._memo.path
-            and node.name != self._target_path[0]
-        ):
-            return None
-
-        with self._use_memo(node):
-            for decorator in node.decorator_list.copy():
-                if self._memo.name_matches(decorator, "typeguard.typechecked"):
-                    # Remove the decorator to prevent duplicate instrumentation
-                    node.decorator_list.remove(decorator)
-
-                    # Store any configuration overrides
-                    if isinstance(decorator, Call) and decorator.keywords:
-                        self._memo.configuration_overrides.update(
-                            {kw.arg: kw.value for kw in decorator.keywords if kw.arg}
-                        )
-
-            self.generic_visit(node)
-            return node
-
-    def visit_FunctionDef(
-        self, node: FunctionDef | AsyncFunctionDef
-    ) -> FunctionDef | AsyncFunctionDef | None:
-        """
-        Injects type checks for function arguments, and for a return of None if the
-        function is annotated to return something else than Any or None, and the body
-        ends without an explicit "return".
-
-        """
-        self._memo.local_names.add(node.name)
-
-        # Eliminate top level functions not belonging to the target path
-        if (
-            self._target_path is not None
-            and not self._memo.path
-            and node.name != self._target_path[0]
-        ):
-            return None
-
-        # Skip instrumentation if we're instrumenting the whole module and the function
-        # contains either @no_type_check or @typeguard_ignore
-        if self._target_path is None:
-            for decorator in node.decorator_list:
-                if self._memo.name_matches(decorator, *ignore_decorators):
-                    return node
-
-        with self._use_memo(node):
-            arg_annotations: dict[str, Any] = {}
-            if self._target_path is None or self._memo.path == self._target_path:
-                # Find line number we're supposed to match against
-                if node.decorator_list:
-                    first_lineno = node.decorator_list[0].lineno
-                else:
-                    first_lineno = node.lineno
-
-                for decorator in node.decorator_list.copy():
-                    if self._memo.name_matches(decorator, "typing.overload"):
-                        # Remove overloads entirely
-                        return None
-                    elif self._memo.name_matches(decorator, "typeguard.typechecked"):
-                        # Remove the decorator to prevent duplicate instrumentation
-                        node.decorator_list.remove(decorator)
-
-                        # Store any configuration overrides
-                        if isinstance(decorator, Call) and decorator.keywords:
-                            self._memo.configuration_overrides = {
-                                kw.arg: kw.value for kw in decorator.keywords if kw.arg
-                            }
-
-                if self.target_lineno == first_lineno:
-                    assert self.target_node is None
-                    self.target_node = node
-                    if node.decorator_list:
-                        self.target_lineno = node.decorator_list[0].lineno
-                    else:
-                        self.target_lineno = node.lineno
-
-                all_args = node.args.args + node.args.kwonlyargs + node.args.posonlyargs
-
-                # Ensure that any type shadowed by the positional or keyword-only
-                # argument names are ignored in this function
-                for arg in all_args:
-                    self._memo.ignored_names.add(arg.arg)
-
-                # Ensure that any type shadowed by the variable positional argument name
-                # (e.g. "args" in *args) is ignored this function
-                if node.args.vararg:
-                    self._memo.ignored_names.add(node.args.vararg.arg)
-
-                # Ensure that any type shadowed by the variable keywrod argument name
-                # (e.g. "kwargs" in *kwargs) is ignored this function
-                if node.args.kwarg:
-                    self._memo.ignored_names.add(node.args.kwarg.arg)
-
-                for arg in all_args:
-                    annotation = self._convert_annotation(deepcopy(arg.annotation))
-                    if annotation:
-                        arg_annotations[arg.arg] = annotation
-
-                if node.args.vararg:
-                    annotation_ = self._convert_annotation(node.args.vararg.annotation)
-                    if annotation_:
-                        if sys.version_info >= (3, 9):
-                            container = Name("tuple", ctx=Load())
-                        else:
-                            container = self._get_import("typing", "Tuple")
-
-                        subscript_slice: Tuple | Index = Tuple(
-                            [
-                                annotation_,
-                                Constant(Ellipsis),
-                            ],
-                            ctx=Load(),
-                        )
-                        if sys.version_info < (3, 9):
-                            subscript_slice = Index(subscript_slice, ctx=Load())
-
-                        arg_annotations[node.args.vararg.arg] = Subscript(
-                            container, subscript_slice, ctx=Load()
-                        )
-
-                if node.args.kwarg:
-                    annotation_ = self._convert_annotation(node.args.kwarg.annotation)
-                    if annotation_:
-                        if sys.version_info >= (3, 9):
-                            container = Name("dict", ctx=Load())
-                        else:
-                            container = self._get_import("typing", "Dict")
-
-                        subscript_slice = Tuple(
-                            [
-                                Name("str", ctx=Load()),
-                                annotation_,
-                            ],
-                            ctx=Load(),
-                        )
-                        if sys.version_info < (3, 9):
-                            subscript_slice = Index(subscript_slice, ctx=Load())
-
-                        arg_annotations[node.args.kwarg.arg] = Subscript(
-                            container, subscript_slice, ctx=Load()
-                        )
-
-                if arg_annotations:
-                    self._memo.variable_annotations.update(arg_annotations)
-
-            self.generic_visit(node)
-
-            if arg_annotations:
-                annotations_dict = Dict(
-                    keys=[Constant(key) for key in arg_annotations.keys()],
-                    values=[
-                        Tuple([Name(key, ctx=Load()), annotation], ctx=Load())
-                        for key, annotation in arg_annotations.items()
-                    ],
-                )
-                func_name = self._get_import(
-                    "typeguard._functions", "check_argument_types"
-                )
-                args = [
-                    self._memo.joined_path,
-                    annotations_dict,
-                    self._memo.get_memo_name(),
-                ]
-                node.body.insert(
-                    self._memo.code_inject_index, Expr(Call(func_name, args, []))
-                )
-
-            # Add a checked "return None" to the end if there's no explicit return
-            # Skip if the return annotation is None or Any
-            if (
-                self._memo.return_annotation
-                and (not self._memo.is_async or not self._memo.has_yield_expressions)
-                and not isinstance(node.body[-1], Return)
-                and (
-                    not isinstance(self._memo.return_annotation, Constant)
-                    or self._memo.return_annotation.value is not None
-                )
-            ):
-                func_name = self._get_import(
-                    "typeguard._functions", "check_return_type"
-                )
-                return_node = Return(
-                    Call(
-                        func_name,
-                        [
-                            self._memo.joined_path,
-                            Constant(None),
-                            self._memo.return_annotation,
-                            self._memo.get_memo_name(),
-                        ],
-                        [],
-                    )
-                )
-
-                # Replace a placeholder "pass" at the end
-                if isinstance(node.body[-1], Pass):
-                    copy_location(return_node, node.body[-1])
-                    del node.body[-1]
-
-                node.body.append(return_node)
-
-            # Insert code to create the call memo, if it was ever needed for this
-            # function
-            if self._memo.memo_var_name:
-                memo_kwargs: dict[str, Any] = {}
-                if self._memo.parent and isinstance(self._memo.parent.node, ClassDef):
-                    for decorator in node.decorator_list:
-                        if (
-                            isinstance(decorator, Name)
-                            and decorator.id == "staticmethod"
-                        ):
-                            break
-                        elif (
-                            isinstance(decorator, Name)
-                            and decorator.id == "classmethod"
-                        ):
-                            memo_kwargs["self_type"] = Name(
-                                id=node.args.args[0].arg, ctx=Load()
-                            )
-                            break
-                    else:
-                        if node.args.args:
-                            if node.name == "__new__":
-                                memo_kwargs["self_type"] = Name(
-                                    id=node.args.args[0].arg, ctx=Load()
-                                )
-                            else:
-                                memo_kwargs["self_type"] = Attribute(
-                                    Name(id=node.args.args[0].arg, ctx=Load()),
-                                    "__class__",
-                                    ctx=Load(),
-                                )
-
-                # Construct the function reference
-                # Nested functions get special treatment: the function name is added
-                # to free variables (and the closure of the resulting function)
-                names: list[str] = [node.name]
-                memo = self._memo.parent
-                while memo:
-                    if isinstance(memo.node, (FunctionDef, AsyncFunctionDef)):
-                        # This is a nested function. Use the function name as-is.
-                        del names[:-1]
-                        break
-                    elif not isinstance(memo.node, ClassDef):
-                        break
-
-                    names.insert(0, memo.node.name)
-                    memo = memo.parent
-
-                config_keywords = self._memo.get_config_keywords()
-                if config_keywords:
-                    memo_kwargs["config"] = Call(
-                        self._get_import("dataclasses", "replace"),
-                        [self._get_import("typeguard._config", "global_config")],
-                        config_keywords,
-                    )
-
-                self._memo.memo_var_name.id = self._memo.get_unused_name("memo")
-                memo_store_name = Name(id=self._memo.memo_var_name.id, ctx=Store())
-                globals_call = Call(Name(id="globals", ctx=Load()), [], [])
-                locals_call = Call(Name(id="locals", ctx=Load()), [], [])
-                memo_expr = Call(
-                    self._get_import("typeguard", "TypeCheckMemo"),
-                    [globals_call, locals_call],
-                    [keyword(key, value) for key, value in memo_kwargs.items()],
-                )
-                node.body.insert(
-                    self._memo.code_inject_index,
-                    Assign([memo_store_name], memo_expr),
-                )
-
-                self._memo.insert_imports(node)
-
-                # Special case the __new__() method to create a local alias from the
-                # class name to the first argument (usually "cls")
-                if (
-                    isinstance(node, FunctionDef)
-                    and node.args
-                    and self._memo.parent is not None
-                    and isinstance(self._memo.parent.node, ClassDef)
-                    and node.name == "__new__"
-                ):
-                    first_args_expr = Name(node.args.args[0].arg, ctx=Load())
-                    cls_name = Name(self._memo.parent.node.name, ctx=Store())
-                    node.body.insert(
-                        self._memo.code_inject_index,
-                        Assign([cls_name], first_args_expr),
-                    )
-
-                # Rmove any placeholder "pass" at the end
-                if isinstance(node.body[-1], Pass):
-                    del node.body[-1]
-
-        return node
-
-    def visit_AsyncFunctionDef(
-        self, node: AsyncFunctionDef
-    ) -> FunctionDef | AsyncFunctionDef | None:
-        return self.visit_FunctionDef(node)
-
-    def visit_Return(self, node: Return) -> Return:
-        """This injects type checks into "return" statements."""
-        self.generic_visit(node)
-        if (
-            self._memo.return_annotation
-            and self._memo.should_instrument
-            and not self._memo.is_ignored_name(self._memo.return_annotation)
-        ):
-            func_name = self._get_import("typeguard._functions", "check_return_type")
-            old_node = node
-            retval = old_node.value or Constant(None)
-            node = Return(
-                Call(
-                    func_name,
-                    [
-                        self._memo.joined_path,
-                        retval,
-                        self._memo.return_annotation,
-                        self._memo.get_memo_name(),
-                    ],
-                    [],
-                )
-            )
-            copy_location(node, old_node)
-
-        return node
-
-    def visit_Yield(self, node: Yield) -> Yield | Call:
-        """
-        This injects type checks into "yield" expressions, checking both the yielded
-        value and the value sent back to the generator, when appropriate.
-
-        """
-        self._memo.has_yield_expressions = True
-        self.generic_visit(node)
-
-        if (
-            self._memo.yield_annotation
-            and self._memo.should_instrument
-            and not self._memo.is_ignored_name(self._memo.yield_annotation)
-        ):
-            func_name = self._get_import("typeguard._functions", "check_yield_type")
-            yieldval = node.value or Constant(None)
-            node.value = Call(
-                func_name,
-                [
-                    self._memo.joined_path,
-                    yieldval,
-                    self._memo.yield_annotation,
-                    self._memo.get_memo_name(),
-                ],
-                [],
-            )
-
-        if (
-            self._memo.send_annotation
-            and self._memo.should_instrument
-            and not self._memo.is_ignored_name(self._memo.send_annotation)
-        ):
-            func_name = self._get_import("typeguard._functions", "check_send_type")
-            old_node = node
-            call_node = Call(
-                func_name,
-                [
-                    self._memo.joined_path,
-                    old_node,
-                    self._memo.send_annotation,
-                    self._memo.get_memo_name(),
-                ],
-                [],
-            )
-            copy_location(call_node, old_node)
-            return call_node
-
-        return node
-
-    def visit_AnnAssign(self, node: AnnAssign) -> Any:
-        """
-        This injects a type check into a local variable annotation-assignment within a
-        function body.
-
-        """
-        self.generic_visit(node)
-
-        if (
-            isinstance(self._memo.node, (FunctionDef, AsyncFunctionDef))
-            and node.annotation
-            and isinstance(node.target, Name)
-        ):
-            self._memo.ignored_names.add(node.target.id)
-            annotation = self._convert_annotation(deepcopy(node.annotation))
-            if annotation:
-                self._memo.variable_annotations[node.target.id] = annotation
-                if node.value:
-                    func_name = self._get_import(
-                        "typeguard._functions", "check_variable_assignment"
-                    )
-                    node.value = Call(
-                        func_name,
-                        [
-                            node.value,
-                            Constant(node.target.id),
-                            annotation,
-                            self._memo.get_memo_name(),
-                        ],
-                        [],
-                    )
-
-        return node
-
-    def visit_Assign(self, node: Assign) -> Any:
-        """
-        This injects a type check into a local variable assignment within a function
-        body. The variable must have been annotated earlier in the function body.
-
-        """
-        self.generic_visit(node)
-
-        # Only instrument function-local assignments
-        if isinstance(self._memo.node, (FunctionDef, AsyncFunctionDef)):
-            targets: list[dict[Constant, expr | None]] = []
-            check_required = False
-            for target in node.targets:
-                elts: Sequence[expr]
-                if isinstance(target, Name):
-                    elts = [target]
-                elif isinstance(target, Tuple):
-                    elts = target.elts
-                else:
-                    continue
-
-                annotations_: dict[Constant, expr | None] = {}
-                for exp in elts:
-                    prefix = ""
-                    if isinstance(exp, Starred):
-                        exp = exp.value
-                        prefix = "*"
-
-                    if isinstance(exp, Name):
-                        self._memo.ignored_names.add(exp.id)
-                        name = prefix + exp.id
-                        annotation = self._memo.variable_annotations.get(exp.id)
-                        if annotation:
-                            annotations_[Constant(name)] = annotation
-                            check_required = True
-                        else:
-                            annotations_[Constant(name)] = None
-
-                targets.append(annotations_)
-
-            if check_required:
-                # Replace missing annotations with typing.Any
-                for item in targets:
-                    for key, expression in item.items():
-                        if expression is None:
-                            item[key] = self._get_import("typing", "Any")
-
-                if len(targets) == 1 and len(targets[0]) == 1:
-                    func_name = self._get_import(
-                        "typeguard._functions", "check_variable_assignment"
-                    )
-                    target_varname = next(iter(targets[0]))
-                    node.value = Call(
-                        func_name,
-                        [
-                            node.value,
-                            target_varname,
-                            targets[0][target_varname],
-                            self._memo.get_memo_name(),
-                        ],
-                        [],
-                    )
-                elif targets:
-                    func_name = self._get_import(
-                        "typeguard._functions", "check_multi_variable_assignment"
-                    )
-                    targets_arg = List(
-                        [
-                            Dict(keys=list(target), values=list(target.values()))
-                            for target in targets
-                        ],
-                        ctx=Load(),
-                    )
-                    node.value = Call(
-                        func_name,
-                        [node.value, targets_arg, self._memo.get_memo_name()],
-                        [],
-                    )
-
-        return node
-
-    def visit_NamedExpr(self, node: NamedExpr) -> Any:
-        """This injects a type check into an assignment expression (a := foo())."""
-        self.generic_visit(node)
-
-        # Only instrument function-local assignments
-        if isinstance(self._memo.node, (FunctionDef, AsyncFunctionDef)) and isinstance(
-            node.target, Name
-        ):
-            self._memo.ignored_names.add(node.target.id)
-
-            # Bail out if no matching annotation is found
-            annotation = self._memo.variable_annotations.get(node.target.id)
-            if annotation is None:
-                return node
-
-            func_name = self._get_import(
-                "typeguard._functions", "check_variable_assignment"
-            )
-            node.value = Call(
-                func_name,
-                [
-                    node.value,
-                    Constant(node.target.id),
-                    annotation,
-                    self._memo.get_memo_name(),
-                ],
-                [],
-            )
-
-        return node
-
-    def visit_AugAssign(self, node: AugAssign) -> Any:
-        """
-        This injects a type check into an augmented assignment expression (a += 1).
-
-        """
-        self.generic_visit(node)
-
-        # Only instrument function-local assignments
-        if isinstance(self._memo.node, (FunctionDef, AsyncFunctionDef)) and isinstance(
-            node.target, Name
-        ):
-            # Bail out if no matching annotation is found
-            annotation = self._memo.variable_annotations.get(node.target.id)
-            if annotation is None:
-                return node
-
-            # Bail out if the operator is not found (newer Python version?)
-            try:
-                operator_func_name = aug_assign_functions[node.op.__class__]
-            except KeyError:
-                return node
-
-            operator_func = self._get_import("operator", operator_func_name)
-            operator_call = Call(
-                operator_func, [Name(node.target.id, ctx=Load()), node.value], []
-            )
-            check_call = Call(
-                self._get_import("typeguard._functions", "check_variable_assignment"),
-                [
-                    operator_call,
-                    Constant(node.target.id),
-                    annotation,
-                    self._memo.get_memo_name(),
-                ],
-                [],
-            )
-            return Assign(targets=[node.target], value=check_call)
-
-        return node
-
-    def visit_If(self, node: If) -> Any:
-        """
-        This blocks names from being collected from a module-level
-        "if typing.TYPE_CHECKING:" block, so that they won't be type checked.
-
-        """
-        self.generic_visit(node)
-
-        if (
-            self._memo is self._module_memo
-            and isinstance(node.test, Name)
-            and self._memo.name_matches(node.test, "typing.TYPE_CHECKING")
-        ):
-            collector = NameCollector()
-            collector.visit(node)
-            self._memo.ignored_names.update(collector.names)
-
-        return node
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_union_transformer.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_union_transformer.py
deleted file mode 100644
index 19617e6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_union_transformer.py
+++ /dev/null
@@ -1,55 +0,0 @@
-"""
-Transforms lazily evaluated PEP 604 unions into typing.Unions, for compatibility with
-Python versions older than 3.10.
-"""
-
-from __future__ import annotations
-
-from ast import (
-    BinOp,
-    BitOr,
-    Index,
-    Load,
-    Name,
-    NodeTransformer,
-    Subscript,
-    fix_missing_locations,
-    parse,
-)
-from ast import Tuple as ASTTuple
-from types import CodeType
-from typing import Any, Dict, FrozenSet, List, Set, Tuple, Union
-
-type_substitutions = {
-    "dict": Dict,
-    "list": List,
-    "tuple": Tuple,
-    "set": Set,
-    "frozenset": FrozenSet,
-    "Union": Union,
-}
-
-
-class UnionTransformer(NodeTransformer):
-    def __init__(self, union_name: Name | None = None):
-        self.union_name = union_name or Name(id="Union", ctx=Load())
-
-    def visit_BinOp(self, node: BinOp) -> Any:
-        self.generic_visit(node)
-        if isinstance(node.op, BitOr):
-            return Subscript(
-                value=self.union_name,
-                slice=Index(
-                    ASTTuple(elts=[node.left, node.right], ctx=Load()), ctx=Load()
-                ),
-                ctx=Load(),
-            )
-
-        return node
-
-
-def compile_type_hint(hint: str) -> CodeType:
-    parsed = parse(hint, "", "eval")
-    UnionTransformer().visit(parsed)
-    fix_missing_locations(parsed)
-    return compile(parsed, "", "eval", flags=0)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_utils.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_utils.py
deleted file mode 100644
index 9bcc841..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typeguard/_utils.py
+++ /dev/null
@@ -1,173 +0,0 @@
-from __future__ import annotations
-
-import inspect
-import sys
-from importlib import import_module
-from inspect import currentframe
-from types import CodeType, FrameType, FunctionType
-from typing import TYPE_CHECKING, Any, Callable, ForwardRef, Union, cast, final
-from weakref import WeakValueDictionary
-
-if TYPE_CHECKING:
-    from ._memo import TypeCheckMemo
-
-if sys.version_info >= (3, 13):
-    from typing import get_args, get_origin
-
-    def evaluate_forwardref(forwardref: ForwardRef, memo: TypeCheckMemo) -> Any:
-        return forwardref._evaluate(
-            memo.globals, memo.locals, type_params=(), recursive_guard=frozenset()
-        )
-
-elif sys.version_info >= (3, 10):
-    from typing import get_args, get_origin
-
-    def evaluate_forwardref(forwardref: ForwardRef, memo: TypeCheckMemo) -> Any:
-        return forwardref._evaluate(
-            memo.globals, memo.locals, recursive_guard=frozenset()
-        )
-
-else:
-    from typing_extensions import get_args, get_origin
-
-    evaluate_extra_args: tuple[frozenset[Any], ...] = (
-        (frozenset(),) if sys.version_info >= (3, 9) else ()
-    )
-
-    def evaluate_forwardref(forwardref: ForwardRef, memo: TypeCheckMemo) -> Any:
-        from ._union_transformer import compile_type_hint, type_substitutions
-
-        if not forwardref.__forward_evaluated__:
-            forwardref.__forward_code__ = compile_type_hint(forwardref.__forward_arg__)
-
-        try:
-            return forwardref._evaluate(memo.globals, memo.locals, *evaluate_extra_args)
-        except NameError:
-            if sys.version_info < (3, 10):
-                # Try again, with the type substitutions (list -> List etc.) in place
-                new_globals = memo.globals.copy()
-                new_globals.setdefault("Union", Union)
-                if sys.version_info < (3, 9):
-                    new_globals.update(type_substitutions)
-
-                return forwardref._evaluate(
-                    new_globals, memo.locals or new_globals, *evaluate_extra_args
-                )
-
-            raise
-
-
-_functions_map: WeakValueDictionary[CodeType, FunctionType] = WeakValueDictionary()
-
-
-def get_type_name(type_: Any) -> str:
-    name: str
-    for attrname in "__name__", "_name", "__forward_arg__":
-        candidate = getattr(type_, attrname, None)
-        if isinstance(candidate, str):
-            name = candidate
-            break
-    else:
-        origin = get_origin(type_)
-        candidate = getattr(origin, "_name", None)
-        if candidate is None:
-            candidate = type_.__class__.__name__.strip("_")
-
-        if isinstance(candidate, str):
-            name = candidate
-        else:
-            return "(unknown)"
-
-    args = get_args(type_)
-    if args:
-        if name == "Literal":
-            formatted_args = ", ".join(repr(arg) for arg in args)
-        else:
-            formatted_args = ", ".join(get_type_name(arg) for arg in args)
-
-        name += f"[{formatted_args}]"
-
-    module = getattr(type_, "__module__", None)
-    if module and module not in (None, "typing", "typing_extensions", "builtins"):
-        name = module + "." + name
-
-    return name
-
-
-def qualified_name(obj: Any, *, add_class_prefix: bool = False) -> str:
-    """
-    Return the qualified name (e.g. package.module.Type) for the given object.
-
-    Builtins and types from the :mod:`typing` package get special treatment by having
-    the module name stripped from the generated name.
-
-    """
-    if obj is None:
-        return "None"
-    elif inspect.isclass(obj):
-        prefix = "class " if add_class_prefix else ""
-        type_ = obj
-    else:
-        prefix = ""
-        type_ = type(obj)
-
-    module = type_.__module__
-    qualname = type_.__qualname__
-    name = qualname if module in ("typing", "builtins") else f"{module}.{qualname}"
-    return prefix + name
-
-
-def function_name(func: Callable[..., Any]) -> str:
-    """
-    Return the qualified name of the given function.
-
-    Builtins and types from the :mod:`typing` package get special treatment by having
-    the module name stripped from the generated name.
-
-    """
-    # For partial functions and objects with __call__ defined, __qualname__ does not
-    # exist
-    module = getattr(func, "__module__", "")
-    qualname = (module + ".") if module not in ("builtins", "") else ""
-    return qualname + getattr(func, "__qualname__", repr(func))
-
-
-def resolve_reference(reference: str) -> Any:
-    modulename, varname = reference.partition(":")[::2]
-    if not modulename or not varname:
-        raise ValueError(f"{reference!r} is not a module:varname reference")
-
-    obj = import_module(modulename)
-    for attr in varname.split("."):
-        obj = getattr(obj, attr)
-
-    return obj
-
-
-def is_method_of(obj: object, cls: type) -> bool:
-    return (
-        inspect.isfunction(obj)
-        and obj.__module__ == cls.__module__
-        and obj.__qualname__.startswith(cls.__qualname__ + ".")
-    )
-
-
-def get_stacklevel() -> int:
-    level = 1
-    frame = cast(FrameType, currentframe()).f_back
-    while frame and frame.f_globals.get("__name__", "").startswith("typeguard."):
-        level += 1
-        frame = frame.f_back
-
-    return level
-
-
-@final
-class Unset:
-    __slots__ = ()
-
-    def __repr__(self) -> str:
-        return ""
-
-
-unset = Unset()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/LICENSE
deleted file mode 100644
index f26bcf4..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/LICENSE
+++ /dev/null
@@ -1,279 +0,0 @@
-A. HISTORY OF THE SOFTWARE
-==========================
-
-Python was created in the early 1990s by Guido van Rossum at Stichting
-Mathematisch Centrum (CWI, see https://www.cwi.nl) in the Netherlands
-as a successor of a language called ABC.  Guido remains Python's
-principal author, although it includes many contributions from others.
-
-In 1995, Guido continued his work on Python at the Corporation for
-National Research Initiatives (CNRI, see https://www.cnri.reston.va.us)
-in Reston, Virginia where he released several versions of the
-software.
-
-In May 2000, Guido and the Python core development team moved to
-BeOpen.com to form the BeOpen PythonLabs team.  In October of the same
-year, the PythonLabs team moved to Digital Creations, which became
-Zope Corporation.  In 2001, the Python Software Foundation (PSF, see
-https://www.python.org/psf/) was formed, a non-profit organization
-created specifically to own Python-related Intellectual Property.
-Zope Corporation was a sponsoring member of the PSF.
-
-All Python releases are Open Source (see https://opensource.org for
-the Open Source Definition).  Historically, most, but not all, Python
-releases have also been GPL-compatible; the table below summarizes
-the various releases.
-
-    Release         Derived     Year        Owner       GPL-
-                    from                                compatible? (1)
-
-    0.9.0 thru 1.2              1991-1995   CWI         yes
-    1.3 thru 1.5.2  1.2         1995-1999   CNRI        yes
-    1.6             1.5.2       2000        CNRI        no
-    2.0             1.6         2000        BeOpen.com  no
-    1.6.1           1.6         2001        CNRI        yes (2)
-    2.1             2.0+1.6.1   2001        PSF         no
-    2.0.1           2.0+1.6.1   2001        PSF         yes
-    2.1.1           2.1+2.0.1   2001        PSF         yes
-    2.1.2           2.1.1       2002        PSF         yes
-    2.1.3           2.1.2       2002        PSF         yes
-    2.2 and above   2.1.1       2001-now    PSF         yes
-
-Footnotes:
-
-(1) GPL-compatible doesn't mean that we're distributing Python under
-    the GPL.  All Python licenses, unlike the GPL, let you distribute
-    a modified version without making your changes open source.  The
-    GPL-compatible licenses make it possible to combine Python with
-    other software that is released under the GPL; the others don't.
-
-(2) According to Richard Stallman, 1.6.1 is not GPL-compatible,
-    because its license has a choice of law clause.  According to
-    CNRI, however, Stallman's lawyer has told CNRI's lawyer that 1.6.1
-    is "not incompatible" with the GPL.
-
-Thanks to the many outside volunteers who have worked under Guido's
-direction to make these releases possible.
-
-
-B. TERMS AND CONDITIONS FOR ACCESSING OR OTHERWISE USING PYTHON
-===============================================================
-
-Python software and documentation are licensed under the
-Python Software Foundation License Version 2.
-
-Starting with Python 3.8.6, examples, recipes, and other code in
-the documentation are dual licensed under the PSF License Version 2
-and the Zero-Clause BSD license.
-
-Some software incorporated into Python is under different licenses.
-The licenses are listed with code falling under that license.
-
-
-PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
---------------------------------------------
-
-1. This LICENSE AGREEMENT is between the Python Software Foundation
-("PSF"), and the Individual or Organization ("Licensee") accessing and
-otherwise using this software ("Python") in source or binary form and
-its associated documentation.
-
-2. Subject to the terms and conditions of this License Agreement, PSF hereby
-grants Licensee a nonexclusive, royalty-free, world-wide license to reproduce,
-analyze, test, perform and/or display publicly, prepare derivative works,
-distribute, and otherwise use Python alone or in any derivative version,
-provided, however, that PSF's License Agreement and PSF's notice of copyright,
-i.e., "Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010,
-2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023 Python Software Foundation;
-All Rights Reserved" are retained in Python alone or in any derivative version
-prepared by Licensee.
-
-3. In the event Licensee prepares a derivative work that is based on
-or incorporates Python or any part thereof, and wants to make
-the derivative work available to others as provided herein, then
-Licensee hereby agrees to include in any such work a brief summary of
-the changes made to Python.
-
-4. PSF is making Python available to Licensee on an "AS IS"
-basis.  PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
-IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND
-DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
-FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT
-INFRINGE ANY THIRD PARTY RIGHTS.
-
-5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
-FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
-A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON,
-OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
-
-6. This License Agreement will automatically terminate upon a material
-breach of its terms and conditions.
-
-7. Nothing in this License Agreement shall be deemed to create any
-relationship of agency, partnership, or joint venture between PSF and
-Licensee.  This License Agreement does not grant permission to use PSF
-trademarks or trade name in a trademark sense to endorse or promote
-products or services of Licensee, or any third party.
-
-8. By copying, installing or otherwise using Python, Licensee
-agrees to be bound by the terms and conditions of this License
-Agreement.
-
-
-BEOPEN.COM LICENSE AGREEMENT FOR PYTHON 2.0
--------------------------------------------
-
-BEOPEN PYTHON OPEN SOURCE LICENSE AGREEMENT VERSION 1
-
-1. This LICENSE AGREEMENT is between BeOpen.com ("BeOpen"), having an
-office at 160 Saratoga Avenue, Santa Clara, CA 95051, and the
-Individual or Organization ("Licensee") accessing and otherwise using
-this software in source or binary form and its associated
-documentation ("the Software").
-
-2. Subject to the terms and conditions of this BeOpen Python License
-Agreement, BeOpen hereby grants Licensee a non-exclusive,
-royalty-free, world-wide license to reproduce, analyze, test, perform
-and/or display publicly, prepare derivative works, distribute, and
-otherwise use the Software alone or in any derivative version,
-provided, however, that the BeOpen Python License is retained in the
-Software, alone or in any derivative version prepared by Licensee.
-
-3. BeOpen is making the Software available to Licensee on an "AS IS"
-basis.  BEOPEN MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
-IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, BEOPEN MAKES NO AND
-DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
-FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE WILL NOT
-INFRINGE ANY THIRD PARTY RIGHTS.
-
-4. BEOPEN SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF THE
-SOFTWARE FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS
-AS A RESULT OF USING, MODIFYING OR DISTRIBUTING THE SOFTWARE, OR ANY
-DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
-
-5. This License Agreement will automatically terminate upon a material
-breach of its terms and conditions.
-
-6. This License Agreement shall be governed by and interpreted in all
-respects by the law of the State of California, excluding conflict of
-law provisions.  Nothing in this License Agreement shall be deemed to
-create any relationship of agency, partnership, or joint venture
-between BeOpen and Licensee.  This License Agreement does not grant
-permission to use BeOpen trademarks or trade names in a trademark
-sense to endorse or promote products or services of Licensee, or any
-third party.  As an exception, the "BeOpen Python" logos available at
-http://www.pythonlabs.com/logos.html may be used according to the
-permissions granted on that web page.
-
-7. By copying, installing or otherwise using the software, Licensee
-agrees to be bound by the terms and conditions of this License
-Agreement.
-
-
-CNRI LICENSE AGREEMENT FOR PYTHON 1.6.1
----------------------------------------
-
-1. This LICENSE AGREEMENT is between the Corporation for National
-Research Initiatives, having an office at 1895 Preston White Drive,
-Reston, VA 20191 ("CNRI"), and the Individual or Organization
-("Licensee") accessing and otherwise using Python 1.6.1 software in
-source or binary form and its associated documentation.
-
-2. Subject to the terms and conditions of this License Agreement, CNRI
-hereby grants Licensee a nonexclusive, royalty-free, world-wide
-license to reproduce, analyze, test, perform and/or display publicly,
-prepare derivative works, distribute, and otherwise use Python 1.6.1
-alone or in any derivative version, provided, however, that CNRI's
-License Agreement and CNRI's notice of copyright, i.e., "Copyright (c)
-1995-2001 Corporation for National Research Initiatives; All Rights
-Reserved" are retained in Python 1.6.1 alone or in any derivative
-version prepared by Licensee.  Alternately, in lieu of CNRI's License
-Agreement, Licensee may substitute the following text (omitting the
-quotes): "Python 1.6.1 is made available subject to the terms and
-conditions in CNRI's License Agreement.  This Agreement together with
-Python 1.6.1 may be located on the internet using the following
-unique, persistent identifier (known as a handle): 1895.22/1013.  This
-Agreement may also be obtained from a proxy server on the internet
-using the following URL: http://hdl.handle.net/1895.22/1013".
-
-3. In the event Licensee prepares a derivative work that is based on
-or incorporates Python 1.6.1 or any part thereof, and wants to make
-the derivative work available to others as provided herein, then
-Licensee hereby agrees to include in any such work a brief summary of
-the changes made to Python 1.6.1.
-
-4. CNRI is making Python 1.6.1 available to Licensee on an "AS IS"
-basis.  CNRI MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
-IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, CNRI MAKES NO AND
-DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
-FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 1.6.1 WILL NOT
-INFRINGE ANY THIRD PARTY RIGHTS.
-
-5. CNRI SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
-1.6.1 FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
-A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 1.6.1,
-OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
-
-6. This License Agreement will automatically terminate upon a material
-breach of its terms and conditions.
-
-7. This License Agreement shall be governed by the federal
-intellectual property law of the United States, including without
-limitation the federal copyright law, and, to the extent such
-U.S. federal law does not apply, by the law of the Commonwealth of
-Virginia, excluding Virginia's conflict of law provisions.
-Notwithstanding the foregoing, with regard to derivative works based
-on Python 1.6.1 that incorporate non-separable material that was
-previously distributed under the GNU General Public License (GPL), the
-law of the Commonwealth of Virginia shall govern this License
-Agreement only as to issues arising under or with respect to
-Paragraphs 4, 5, and 7 of this License Agreement.  Nothing in this
-License Agreement shall be deemed to create any relationship of
-agency, partnership, or joint venture between CNRI and Licensee.  This
-License Agreement does not grant permission to use CNRI trademarks or
-trade name in a trademark sense to endorse or promote products or
-services of Licensee, or any third party.
-
-8. By clicking on the "ACCEPT" button where indicated, or by copying,
-installing or otherwise using Python 1.6.1, Licensee agrees to be
-bound by the terms and conditions of this License Agreement.
-
-        ACCEPT
-
-
-CWI LICENSE AGREEMENT FOR PYTHON 0.9.0 THROUGH 1.2
---------------------------------------------------
-
-Copyright (c) 1991 - 1995, Stichting Mathematisch Centrum Amsterdam,
-The Netherlands.  All rights reserved.
-
-Permission to use, copy, modify, and distribute this software and its
-documentation for any purpose and without fee is hereby granted,
-provided that the above copyright notice appear in all copies and that
-both that copyright notice and this permission notice appear in
-supporting documentation, and that the name of Stichting Mathematisch
-Centrum or CWI not be used in advertising or publicity pertaining to
-distribution of the software without specific, written prior
-permission.
-
-STICHTING MATHEMATISCH CENTRUM DISCLAIMS ALL WARRANTIES WITH REGARD TO
-THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
-FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH CENTRUM BE LIABLE
-FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
-WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
-ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
-OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
-
-ZERO-CLAUSE BSD LICENSE FOR CODE IN THE PYTHON DOCUMENTATION
-----------------------------------------------------------------------
-
-Permission to use, copy, modify, and/or distribute this software for any
-purpose with or without fee is hereby granted.
-
-THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
-REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
-AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
-INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
-LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
-OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
-PERFORMANCE OF THIS SOFTWARE.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/METADATA
deleted file mode 100644
index f15e2b3..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/METADATA
+++ /dev/null
@@ -1,67 +0,0 @@
-Metadata-Version: 2.1
-Name: typing_extensions
-Version: 4.12.2
-Summary: Backported and Experimental Type Hints for Python 3.8+
-Keywords: annotations,backport,checker,checking,function,hinting,hints,type,typechecking,typehinting,typehints,typing
-Author-email: "Guido van Rossum, Jukka Lehtosalo, Łukasz Langa, Michael Lee" 
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Python Software Foundation License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Software Development
-Project-URL: Bug Tracker, https://github.com/python/typing_extensions/issues
-Project-URL: Changes, https://github.com/python/typing_extensions/blob/main/CHANGELOG.md
-Project-URL: Documentation, https://typing-extensions.readthedocs.io/
-Project-URL: Home, https://github.com/python/typing_extensions
-Project-URL: Q & A, https://github.com/python/typing/discussions
-Project-URL: Repository, https://github.com/python/typing_extensions
-
-# Typing Extensions
-
-[![Chat at https://gitter.im/python/typing](https://badges.gitter.im/python/typing.svg)](https://gitter.im/python/typing)
-
-[Documentation](https://typing-extensions.readthedocs.io/en/latest/#) –
-[PyPI](https://pypi.org/project/typing-extensions/)
-
-## Overview
-
-The `typing_extensions` module serves two related purposes:
-
-- Enable use of new type system features on older Python versions. For example,
-  `typing.TypeGuard` is new in Python 3.10, but `typing_extensions` allows
-  users on previous Python versions to use it too.
-- Enable experimentation with new type system PEPs before they are accepted and
-  added to the `typing` module.
-
-`typing_extensions` is treated specially by static type checkers such as
-mypy and pyright. Objects defined in `typing_extensions` are treated the same
-way as equivalent forms in `typing`.
-
-`typing_extensions` uses
-[Semantic Versioning](https://semver.org/). The
-major version will be incremented only for backwards-incompatible changes.
-Therefore, it's safe to depend
-on `typing_extensions` like this: `typing_extensions >=x.y, <(x+1)`,
-where `x.y` is the first version that includes all features you need.
-
-## Included items
-
-See [the documentation](https://typing-extensions.readthedocs.io/en/latest/#) for a
-complete listing of module contents.
-
-## Contributing
-
-See [CONTRIBUTING.md](https://github.com/python/typing_extensions/blob/main/CONTRIBUTING.md)
-for how to contribute to `typing_extensions`.
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/RECORD
deleted file mode 100644
index bc7b453..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/RECORD
+++ /dev/null
@@ -1,7 +0,0 @@
-__pycache__/typing_extensions.cpython-312.pyc,,
-typing_extensions-4.12.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-typing_extensions-4.12.2.dist-info/LICENSE,sha256=Oy-B_iHRgcSZxZolbI4ZaEVdZonSaaqFNzv7avQdo78,13936
-typing_extensions-4.12.2.dist-info/METADATA,sha256=BeUQIa8cnYbrjWx-N8TOznM9UGW5Gm2DicVpDtRA8W0,3018
-typing_extensions-4.12.2.dist-info/RECORD,,
-typing_extensions-4.12.2.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-typing_extensions.py,sha256=gwekpyG9DVG3lxWKX4ni8u7nk3We5slG98mA9F3DJQw,134451
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/WHEEL
deleted file mode 100644
index 3b5e64b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions-4.12.2.dist-info/WHEEL
+++ /dev/null
@@ -1,4 +0,0 @@
-Wheel-Version: 1.0
-Generator: flit 3.9.0
-Root-Is-Purelib: true
-Tag: py3-none-any
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions.py
deleted file mode 100644
index dec429c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/typing_extensions.py
+++ /dev/null
@@ -1,3641 +0,0 @@
-import abc
-import collections
-import collections.abc
-import contextlib
-import functools
-import inspect
-import operator
-import sys
-import types as _types
-import typing
-import warnings
-
-__all__ = [
-    # Super-special typing primitives.
-    'Any',
-    'ClassVar',
-    'Concatenate',
-    'Final',
-    'LiteralString',
-    'ParamSpec',
-    'ParamSpecArgs',
-    'ParamSpecKwargs',
-    'Self',
-    'Type',
-    'TypeVar',
-    'TypeVarTuple',
-    'Unpack',
-
-    # ABCs (from collections.abc).
-    'Awaitable',
-    'AsyncIterator',
-    'AsyncIterable',
-    'Coroutine',
-    'AsyncGenerator',
-    'AsyncContextManager',
-    'Buffer',
-    'ChainMap',
-
-    # Concrete collection types.
-    'ContextManager',
-    'Counter',
-    'Deque',
-    'DefaultDict',
-    'NamedTuple',
-    'OrderedDict',
-    'TypedDict',
-
-    # Structural checks, a.k.a. protocols.
-    'SupportsAbs',
-    'SupportsBytes',
-    'SupportsComplex',
-    'SupportsFloat',
-    'SupportsIndex',
-    'SupportsInt',
-    'SupportsRound',
-
-    # One-off things.
-    'Annotated',
-    'assert_never',
-    'assert_type',
-    'clear_overloads',
-    'dataclass_transform',
-    'deprecated',
-    'Doc',
-    'get_overloads',
-    'final',
-    'get_args',
-    'get_origin',
-    'get_original_bases',
-    'get_protocol_members',
-    'get_type_hints',
-    'IntVar',
-    'is_protocol',
-    'is_typeddict',
-    'Literal',
-    'NewType',
-    'overload',
-    'override',
-    'Protocol',
-    'reveal_type',
-    'runtime',
-    'runtime_checkable',
-    'Text',
-    'TypeAlias',
-    'TypeAliasType',
-    'TypeGuard',
-    'TypeIs',
-    'TYPE_CHECKING',
-    'Never',
-    'NoReturn',
-    'ReadOnly',
-    'Required',
-    'NotRequired',
-
-    # Pure aliases, have always been in typing
-    'AbstractSet',
-    'AnyStr',
-    'BinaryIO',
-    'Callable',
-    'Collection',
-    'Container',
-    'Dict',
-    'ForwardRef',
-    'FrozenSet',
-    'Generator',
-    'Generic',
-    'Hashable',
-    'IO',
-    'ItemsView',
-    'Iterable',
-    'Iterator',
-    'KeysView',
-    'List',
-    'Mapping',
-    'MappingView',
-    'Match',
-    'MutableMapping',
-    'MutableSequence',
-    'MutableSet',
-    'NoDefault',
-    'Optional',
-    'Pattern',
-    'Reversible',
-    'Sequence',
-    'Set',
-    'Sized',
-    'TextIO',
-    'Tuple',
-    'Union',
-    'ValuesView',
-    'cast',
-    'no_type_check',
-    'no_type_check_decorator',
-]
-
-# for backward compatibility
-PEP_560 = True
-GenericMeta = type
-_PEP_696_IMPLEMENTED = sys.version_info >= (3, 13, 0, "beta")
-
-# The functions below are modified copies of typing internal helpers.
-# They are needed by _ProtocolMeta and they provide support for PEP 646.
-
-
-class _Sentinel:
-    def __repr__(self):
-        return ""
-
-
-_marker = _Sentinel()
-
-
-if sys.version_info >= (3, 10):
-    def _should_collect_from_parameters(t):
-        return isinstance(
-            t, (typing._GenericAlias, _types.GenericAlias, _types.UnionType)
-        )
-elif sys.version_info >= (3, 9):
-    def _should_collect_from_parameters(t):
-        return isinstance(t, (typing._GenericAlias, _types.GenericAlias))
-else:
-    def _should_collect_from_parameters(t):
-        return isinstance(t, typing._GenericAlias) and not t._special
-
-
-NoReturn = typing.NoReturn
-
-# Some unconstrained type variables.  These are used by the container types.
-# (These are not for export.)
-T = typing.TypeVar('T')  # Any type.
-KT = typing.TypeVar('KT')  # Key type.
-VT = typing.TypeVar('VT')  # Value type.
-T_co = typing.TypeVar('T_co', covariant=True)  # Any type covariant containers.
-T_contra = typing.TypeVar('T_contra', contravariant=True)  # Ditto contravariant.
-
-
-if sys.version_info >= (3, 11):
-    from typing import Any
-else:
-
-    class _AnyMeta(type):
-        def __instancecheck__(self, obj):
-            if self is Any:
-                raise TypeError("typing_extensions.Any cannot be used with isinstance()")
-            return super().__instancecheck__(obj)
-
-        def __repr__(self):
-            if self is Any:
-                return "typing_extensions.Any"
-            return super().__repr__()
-
-    class Any(metaclass=_AnyMeta):
-        """Special type indicating an unconstrained type.
-        - Any is compatible with every type.
-        - Any assumed to have all methods.
-        - All values assumed to be instances of Any.
-        Note that all the above statements are true from the point of view of
-        static type checkers. At runtime, Any should not be used with instance
-        checks.
-        """
-        def __new__(cls, *args, **kwargs):
-            if cls is Any:
-                raise TypeError("Any cannot be instantiated")
-            return super().__new__(cls, *args, **kwargs)
-
-
-ClassVar = typing.ClassVar
-
-
-class _ExtensionsSpecialForm(typing._SpecialForm, _root=True):
-    def __repr__(self):
-        return 'typing_extensions.' + self._name
-
-
-Final = typing.Final
-
-if sys.version_info >= (3, 11):
-    final = typing.final
-else:
-    # @final exists in 3.8+, but we backport it for all versions
-    # before 3.11 to keep support for the __final__ attribute.
-    # See https://bugs.python.org/issue46342
-    def final(f):
-        """This decorator can be used to indicate to type checkers that
-        the decorated method cannot be overridden, and decorated class
-        cannot be subclassed. For example:
-
-            class Base:
-                @final
-                def done(self) -> None:
-                    ...
-            class Sub(Base):
-                def done(self) -> None:  # Error reported by type checker
-                    ...
-            @final
-            class Leaf:
-                ...
-            class Other(Leaf):  # Error reported by type checker
-                ...
-
-        There is no runtime checking of these properties. The decorator
-        sets the ``__final__`` attribute to ``True`` on the decorated object
-        to allow runtime introspection.
-        """
-        try:
-            f.__final__ = True
-        except (AttributeError, TypeError):
-            # Skip the attribute silently if it is not writable.
-            # AttributeError happens if the object has __slots__ or a
-            # read-only property, TypeError if it's a builtin class.
-            pass
-        return f
-
-
-def IntVar(name):
-    return typing.TypeVar(name)
-
-
-# A Literal bug was fixed in 3.11.0, 3.10.1 and 3.9.8
-if sys.version_info >= (3, 10, 1):
-    Literal = typing.Literal
-else:
-    def _flatten_literal_params(parameters):
-        """An internal helper for Literal creation: flatten Literals among parameters"""
-        params = []
-        for p in parameters:
-            if isinstance(p, _LiteralGenericAlias):
-                params.extend(p.__args__)
-            else:
-                params.append(p)
-        return tuple(params)
-
-    def _value_and_type_iter(params):
-        for p in params:
-            yield p, type(p)
-
-    class _LiteralGenericAlias(typing._GenericAlias, _root=True):
-        def __eq__(self, other):
-            if not isinstance(other, _LiteralGenericAlias):
-                return NotImplemented
-            these_args_deduped = set(_value_and_type_iter(self.__args__))
-            other_args_deduped = set(_value_and_type_iter(other.__args__))
-            return these_args_deduped == other_args_deduped
-
-        def __hash__(self):
-            return hash(frozenset(_value_and_type_iter(self.__args__)))
-
-    class _LiteralForm(_ExtensionsSpecialForm, _root=True):
-        def __init__(self, doc: str):
-            self._name = 'Literal'
-            self._doc = self.__doc__ = doc
-
-        def __getitem__(self, parameters):
-            if not isinstance(parameters, tuple):
-                parameters = (parameters,)
-
-            parameters = _flatten_literal_params(parameters)
-
-            val_type_pairs = list(_value_and_type_iter(parameters))
-            try:
-                deduped_pairs = set(val_type_pairs)
-            except TypeError:
-                # unhashable parameters
-                pass
-            else:
-                # similar logic to typing._deduplicate on Python 3.9+
-                if len(deduped_pairs) < len(val_type_pairs):
-                    new_parameters = []
-                    for pair in val_type_pairs:
-                        if pair in deduped_pairs:
-                            new_parameters.append(pair[0])
-                            deduped_pairs.remove(pair)
-                    assert not deduped_pairs, deduped_pairs
-                    parameters = tuple(new_parameters)
-
-            return _LiteralGenericAlias(self, parameters)
-
-    Literal = _LiteralForm(doc="""\
-                           A type that can be used to indicate to type checkers
-                           that the corresponding value has a value literally equivalent
-                           to the provided parameter. For example:
-
-                               var: Literal[4] = 4
-
-                           The type checker understands that 'var' is literally equal to
-                           the value 4 and no other value.
-
-                           Literal[...] cannot be subclassed. There is no runtime
-                           checking verifying that the parameter is actually a value
-                           instead of a type.""")
-
-
-_overload_dummy = typing._overload_dummy
-
-
-if hasattr(typing, "get_overloads"):  # 3.11+
-    overload = typing.overload
-    get_overloads = typing.get_overloads
-    clear_overloads = typing.clear_overloads
-else:
-    # {module: {qualname: {firstlineno: func}}}
-    _overload_registry = collections.defaultdict(
-        functools.partial(collections.defaultdict, dict)
-    )
-
-    def overload(func):
-        """Decorator for overloaded functions/methods.
-
-        In a stub file, place two or more stub definitions for the same
-        function in a row, each decorated with @overload.  For example:
-
-        @overload
-        def utf8(value: None) -> None: ...
-        @overload
-        def utf8(value: bytes) -> bytes: ...
-        @overload
-        def utf8(value: str) -> bytes: ...
-
-        In a non-stub file (i.e. a regular .py file), do the same but
-        follow it with an implementation.  The implementation should *not*
-        be decorated with @overload.  For example:
-
-        @overload
-        def utf8(value: None) -> None: ...
-        @overload
-        def utf8(value: bytes) -> bytes: ...
-        @overload
-        def utf8(value: str) -> bytes: ...
-        def utf8(value):
-            # implementation goes here
-
-        The overloads for a function can be retrieved at runtime using the
-        get_overloads() function.
-        """
-        # classmethod and staticmethod
-        f = getattr(func, "__func__", func)
-        try:
-            _overload_registry[f.__module__][f.__qualname__][
-                f.__code__.co_firstlineno
-            ] = func
-        except AttributeError:
-            # Not a normal function; ignore.
-            pass
-        return _overload_dummy
-
-    def get_overloads(func):
-        """Return all defined overloads for *func* as a sequence."""
-        # classmethod and staticmethod
-        f = getattr(func, "__func__", func)
-        if f.__module__ not in _overload_registry:
-            return []
-        mod_dict = _overload_registry[f.__module__]
-        if f.__qualname__ not in mod_dict:
-            return []
-        return list(mod_dict[f.__qualname__].values())
-
-    def clear_overloads():
-        """Clear all overloads in the registry."""
-        _overload_registry.clear()
-
-
-# This is not a real generic class.  Don't use outside annotations.
-Type = typing.Type
-
-# Various ABCs mimicking those in collections.abc.
-# A few are simply re-exported for completeness.
-Awaitable = typing.Awaitable
-Coroutine = typing.Coroutine
-AsyncIterable = typing.AsyncIterable
-AsyncIterator = typing.AsyncIterator
-Deque = typing.Deque
-DefaultDict = typing.DefaultDict
-OrderedDict = typing.OrderedDict
-Counter = typing.Counter
-ChainMap = typing.ChainMap
-Text = typing.Text
-TYPE_CHECKING = typing.TYPE_CHECKING
-
-
-if sys.version_info >= (3, 13, 0, "beta"):
-    from typing import AsyncContextManager, AsyncGenerator, ContextManager, Generator
-else:
-    def _is_dunder(attr):
-        return attr.startswith('__') and attr.endswith('__')
-
-    # Python <3.9 doesn't have typing._SpecialGenericAlias
-    _special_generic_alias_base = getattr(
-        typing, "_SpecialGenericAlias", typing._GenericAlias
-    )
-
-    class _SpecialGenericAlias(_special_generic_alias_base, _root=True):
-        def __init__(self, origin, nparams, *, inst=True, name=None, defaults=()):
-            if _special_generic_alias_base is typing._GenericAlias:
-                # Python <3.9
-                self.__origin__ = origin
-                self._nparams = nparams
-                super().__init__(origin, nparams, special=True, inst=inst, name=name)
-            else:
-                # Python >= 3.9
-                super().__init__(origin, nparams, inst=inst, name=name)
-            self._defaults = defaults
-
-        def __setattr__(self, attr, val):
-            allowed_attrs = {'_name', '_inst', '_nparams', '_defaults'}
-            if _special_generic_alias_base is typing._GenericAlias:
-                # Python <3.9
-                allowed_attrs.add("__origin__")
-            if _is_dunder(attr) or attr in allowed_attrs:
-                object.__setattr__(self, attr, val)
-            else:
-                setattr(self.__origin__, attr, val)
-
-        @typing._tp_cache
-        def __getitem__(self, params):
-            if not isinstance(params, tuple):
-                params = (params,)
-            msg = "Parameters to generic types must be types."
-            params = tuple(typing._type_check(p, msg) for p in params)
-            if (
-                self._defaults
-                and len(params) < self._nparams
-                and len(params) + len(self._defaults) >= self._nparams
-            ):
-                params = (*params, *self._defaults[len(params) - self._nparams:])
-            actual_len = len(params)
-
-            if actual_len != self._nparams:
-                if self._defaults:
-                    expected = f"at least {self._nparams - len(self._defaults)}"
-                else:
-                    expected = str(self._nparams)
-                if not self._nparams:
-                    raise TypeError(f"{self} is not a generic class")
-                raise TypeError(
-                    f"Too {'many' if actual_len > self._nparams else 'few'}"
-                    f" arguments for {self};"
-                    f" actual {actual_len}, expected {expected}"
-                )
-            return self.copy_with(params)
-
-    _NoneType = type(None)
-    Generator = _SpecialGenericAlias(
-        collections.abc.Generator, 3, defaults=(_NoneType, _NoneType)
-    )
-    AsyncGenerator = _SpecialGenericAlias(
-        collections.abc.AsyncGenerator, 2, defaults=(_NoneType,)
-    )
-    ContextManager = _SpecialGenericAlias(
-        contextlib.AbstractContextManager,
-        2,
-        name="ContextManager",
-        defaults=(typing.Optional[bool],)
-    )
-    AsyncContextManager = _SpecialGenericAlias(
-        contextlib.AbstractAsyncContextManager,
-        2,
-        name="AsyncContextManager",
-        defaults=(typing.Optional[bool],)
-    )
-
-
-_PROTO_ALLOWLIST = {
-    'collections.abc': [
-        'Callable', 'Awaitable', 'Iterable', 'Iterator', 'AsyncIterable',
-        'Hashable', 'Sized', 'Container', 'Collection', 'Reversible', 'Buffer',
-    ],
-    'contextlib': ['AbstractContextManager', 'AbstractAsyncContextManager'],
-    'typing_extensions': ['Buffer'],
-}
-
-
-_EXCLUDED_ATTRS = frozenset(typing.EXCLUDED_ATTRIBUTES) | {
-    "__match_args__", "__protocol_attrs__", "__non_callable_proto_members__",
-    "__final__",
-}
-
-
-def _get_protocol_attrs(cls):
-    attrs = set()
-    for base in cls.__mro__[:-1]:  # without object
-        if base.__name__ in {'Protocol', 'Generic'}:
-            continue
-        annotations = getattr(base, '__annotations__', {})
-        for attr in (*base.__dict__, *annotations):
-            if (not attr.startswith('_abc_') and attr not in _EXCLUDED_ATTRS):
-                attrs.add(attr)
-    return attrs
-
-
-def _caller(depth=2):
-    try:
-        return sys._getframe(depth).f_globals.get('__name__', '__main__')
-    except (AttributeError, ValueError):  # For platforms without _getframe()
-        return None
-
-
-# `__match_args__` attribute was removed from protocol members in 3.13,
-# we want to backport this change to older Python versions.
-if sys.version_info >= (3, 13):
-    Protocol = typing.Protocol
-else:
-    def _allow_reckless_class_checks(depth=3):
-        """Allow instance and class checks for special stdlib modules.
-        The abc and functools modules indiscriminately call isinstance() and
-        issubclass() on the whole MRO of a user class, which may contain protocols.
-        """
-        return _caller(depth) in {'abc', 'functools', None}
-
-    def _no_init(self, *args, **kwargs):
-        if type(self)._is_protocol:
-            raise TypeError('Protocols cannot be instantiated')
-
-    def _type_check_issubclass_arg_1(arg):
-        """Raise TypeError if `arg` is not an instance of `type`
-        in `issubclass(arg, )`.
-
-        In most cases, this is verified by type.__subclasscheck__.
-        Checking it again unnecessarily would slow down issubclass() checks,
-        so, we don't perform this check unless we absolutely have to.
-
-        For various error paths, however,
-        we want to ensure that *this* error message is shown to the user
-        where relevant, rather than a typing.py-specific error message.
-        """
-        if not isinstance(arg, type):
-            # Same error message as for issubclass(1, int).
-            raise TypeError('issubclass() arg 1 must be a class')
-
-    # Inheriting from typing._ProtocolMeta isn't actually desirable,
-    # but is necessary to allow typing.Protocol and typing_extensions.Protocol
-    # to mix without getting TypeErrors about "metaclass conflict"
-    class _ProtocolMeta(type(typing.Protocol)):
-        # This metaclass is somewhat unfortunate,
-        # but is necessary for several reasons...
-        #
-        # NOTE: DO NOT call super() in any methods in this class
-        # That would call the methods on typing._ProtocolMeta on Python 3.8-3.11
-        # and those are slow
-        def __new__(mcls, name, bases, namespace, **kwargs):
-            if name == "Protocol" and len(bases) < 2:
-                pass
-            elif {Protocol, typing.Protocol} & set(bases):
-                for base in bases:
-                    if not (
-                        base in {object, typing.Generic, Protocol, typing.Protocol}
-                        or base.__name__ in _PROTO_ALLOWLIST.get(base.__module__, [])
-                        or is_protocol(base)
-                    ):
-                        raise TypeError(
-                            f"Protocols can only inherit from other protocols, "
-                            f"got {base!r}"
-                        )
-            return abc.ABCMeta.__new__(mcls, name, bases, namespace, **kwargs)
-
-        def __init__(cls, *args, **kwargs):
-            abc.ABCMeta.__init__(cls, *args, **kwargs)
-            if getattr(cls, "_is_protocol", False):
-                cls.__protocol_attrs__ = _get_protocol_attrs(cls)
-
-        def __subclasscheck__(cls, other):
-            if cls is Protocol:
-                return type.__subclasscheck__(cls, other)
-            if (
-                getattr(cls, '_is_protocol', False)
-                and not _allow_reckless_class_checks()
-            ):
-                if not getattr(cls, '_is_runtime_protocol', False):
-                    _type_check_issubclass_arg_1(other)
-                    raise TypeError(
-                        "Instance and class checks can only be used with "
-                        "@runtime_checkable protocols"
-                    )
-                if (
-                    # this attribute is set by @runtime_checkable:
-                    cls.__non_callable_proto_members__
-                    and cls.__dict__.get("__subclasshook__") is _proto_hook
-                ):
-                    _type_check_issubclass_arg_1(other)
-                    non_method_attrs = sorted(cls.__non_callable_proto_members__)
-                    raise TypeError(
-                        "Protocols with non-method members don't support issubclass()."
-                        f" Non-method members: {str(non_method_attrs)[1:-1]}."
-                    )
-            return abc.ABCMeta.__subclasscheck__(cls, other)
-
-        def __instancecheck__(cls, instance):
-            # We need this method for situations where attributes are
-            # assigned in __init__.
-            if cls is Protocol:
-                return type.__instancecheck__(cls, instance)
-            if not getattr(cls, "_is_protocol", False):
-                # i.e., it's a concrete subclass of a protocol
-                return abc.ABCMeta.__instancecheck__(cls, instance)
-
-            if (
-                not getattr(cls, '_is_runtime_protocol', False) and
-                not _allow_reckless_class_checks()
-            ):
-                raise TypeError("Instance and class checks can only be used with"
-                                " @runtime_checkable protocols")
-
-            if abc.ABCMeta.__instancecheck__(cls, instance):
-                return True
-
-            for attr in cls.__protocol_attrs__:
-                try:
-                    val = inspect.getattr_static(instance, attr)
-                except AttributeError:
-                    break
-                # this attribute is set by @runtime_checkable:
-                if val is None and attr not in cls.__non_callable_proto_members__:
-                    break
-            else:
-                return True
-
-            return False
-
-        def __eq__(cls, other):
-            # Hack so that typing.Generic.__class_getitem__
-            # treats typing_extensions.Protocol
-            # as equivalent to typing.Protocol
-            if abc.ABCMeta.__eq__(cls, other) is True:
-                return True
-            return cls is Protocol and other is typing.Protocol
-
-        # This has to be defined, or the abc-module cache
-        # complains about classes with this metaclass being unhashable,
-        # if we define only __eq__!
-        def __hash__(cls) -> int:
-            return type.__hash__(cls)
-
-    @classmethod
-    def _proto_hook(cls, other):
-        if not cls.__dict__.get('_is_protocol', False):
-            return NotImplemented
-
-        for attr in cls.__protocol_attrs__:
-            for base in other.__mro__:
-                # Check if the members appears in the class dictionary...
-                if attr in base.__dict__:
-                    if base.__dict__[attr] is None:
-                        return NotImplemented
-                    break
-
-                # ...or in annotations, if it is a sub-protocol.
-                annotations = getattr(base, '__annotations__', {})
-                if (
-                    isinstance(annotations, collections.abc.Mapping)
-                    and attr in annotations
-                    and is_protocol(other)
-                ):
-                    break
-            else:
-                return NotImplemented
-        return True
-
-    class Protocol(typing.Generic, metaclass=_ProtocolMeta):
-        __doc__ = typing.Protocol.__doc__
-        __slots__ = ()
-        _is_protocol = True
-        _is_runtime_protocol = False
-
-        def __init_subclass__(cls, *args, **kwargs):
-            super().__init_subclass__(*args, **kwargs)
-
-            # Determine if this is a protocol or a concrete subclass.
-            if not cls.__dict__.get('_is_protocol', False):
-                cls._is_protocol = any(b is Protocol for b in cls.__bases__)
-
-            # Set (or override) the protocol subclass hook.
-            if '__subclasshook__' not in cls.__dict__:
-                cls.__subclasshook__ = _proto_hook
-
-            # Prohibit instantiation for protocol classes
-            if cls._is_protocol and cls.__init__ is Protocol.__init__:
-                cls.__init__ = _no_init
-
-
-if sys.version_info >= (3, 13):
-    runtime_checkable = typing.runtime_checkable
-else:
-    def runtime_checkable(cls):
-        """Mark a protocol class as a runtime protocol.
-
-        Such protocol can be used with isinstance() and issubclass().
-        Raise TypeError if applied to a non-protocol class.
-        This allows a simple-minded structural check very similar to
-        one trick ponies in collections.abc such as Iterable.
-
-        For example::
-
-            @runtime_checkable
-            class Closable(Protocol):
-                def close(self): ...
-
-            assert isinstance(open('/some/file'), Closable)
-
-        Warning: this will check only the presence of the required methods,
-        not their type signatures!
-        """
-        if not issubclass(cls, typing.Generic) or not getattr(cls, '_is_protocol', False):
-            raise TypeError(f'@runtime_checkable can be only applied to protocol classes,'
-                            f' got {cls!r}')
-        cls._is_runtime_protocol = True
-
-        # typing.Protocol classes on <=3.11 break if we execute this block,
-        # because typing.Protocol classes on <=3.11 don't have a
-        # `__protocol_attrs__` attribute, and this block relies on the
-        # `__protocol_attrs__` attribute. Meanwhile, typing.Protocol classes on 3.12.2+
-        # break if we *don't* execute this block, because *they* assume that all
-        # protocol classes have a `__non_callable_proto_members__` attribute
-        # (which this block sets)
-        if isinstance(cls, _ProtocolMeta) or sys.version_info >= (3, 12, 2):
-            # PEP 544 prohibits using issubclass()
-            # with protocols that have non-method members.
-            # See gh-113320 for why we compute this attribute here,
-            # rather than in `_ProtocolMeta.__init__`
-            cls.__non_callable_proto_members__ = set()
-            for attr in cls.__protocol_attrs__:
-                try:
-                    is_callable = callable(getattr(cls, attr, None))
-                except Exception as e:
-                    raise TypeError(
-                        f"Failed to determine whether protocol member {attr!r} "
-                        "is a method member"
-                    ) from e
-                else:
-                    if not is_callable:
-                        cls.__non_callable_proto_members__.add(attr)
-
-        return cls
-
-
-# The "runtime" alias exists for backwards compatibility.
-runtime = runtime_checkable
-
-
-# Our version of runtime-checkable protocols is faster on Python 3.8-3.11
-if sys.version_info >= (3, 12):
-    SupportsInt = typing.SupportsInt
-    SupportsFloat = typing.SupportsFloat
-    SupportsComplex = typing.SupportsComplex
-    SupportsBytes = typing.SupportsBytes
-    SupportsIndex = typing.SupportsIndex
-    SupportsAbs = typing.SupportsAbs
-    SupportsRound = typing.SupportsRound
-else:
-    @runtime_checkable
-    class SupportsInt(Protocol):
-        """An ABC with one abstract method __int__."""
-        __slots__ = ()
-
-        @abc.abstractmethod
-        def __int__(self) -> int:
-            pass
-
-    @runtime_checkable
-    class SupportsFloat(Protocol):
-        """An ABC with one abstract method __float__."""
-        __slots__ = ()
-
-        @abc.abstractmethod
-        def __float__(self) -> float:
-            pass
-
-    @runtime_checkable
-    class SupportsComplex(Protocol):
-        """An ABC with one abstract method __complex__."""
-        __slots__ = ()
-
-        @abc.abstractmethod
-        def __complex__(self) -> complex:
-            pass
-
-    @runtime_checkable
-    class SupportsBytes(Protocol):
-        """An ABC with one abstract method __bytes__."""
-        __slots__ = ()
-
-        @abc.abstractmethod
-        def __bytes__(self) -> bytes:
-            pass
-
-    @runtime_checkable
-    class SupportsIndex(Protocol):
-        __slots__ = ()
-
-        @abc.abstractmethod
-        def __index__(self) -> int:
-            pass
-
-    @runtime_checkable
-    class SupportsAbs(Protocol[T_co]):
-        """
-        An ABC with one abstract method __abs__ that is covariant in its return type.
-        """
-        __slots__ = ()
-
-        @abc.abstractmethod
-        def __abs__(self) -> T_co:
-            pass
-
-    @runtime_checkable
-    class SupportsRound(Protocol[T_co]):
-        """
-        An ABC with one abstract method __round__ that is covariant in its return type.
-        """
-        __slots__ = ()
-
-        @abc.abstractmethod
-        def __round__(self, ndigits: int = 0) -> T_co:
-            pass
-
-
-def _ensure_subclassable(mro_entries):
-    def inner(func):
-        if sys.implementation.name == "pypy" and sys.version_info < (3, 9):
-            cls_dict = {
-                "__call__": staticmethod(func),
-                "__mro_entries__": staticmethod(mro_entries)
-            }
-            t = type(func.__name__, (), cls_dict)
-            return functools.update_wrapper(t(), func)
-        else:
-            func.__mro_entries__ = mro_entries
-            return func
-    return inner
-
-
-# Update this to something like >=3.13.0b1 if and when
-# PEP 728 is implemented in CPython
-_PEP_728_IMPLEMENTED = False
-
-if _PEP_728_IMPLEMENTED:
-    # The standard library TypedDict in Python 3.8 does not store runtime information
-    # about which (if any) keys are optional.  See https://bugs.python.org/issue38834
-    # The standard library TypedDict in Python 3.9.0/1 does not honour the "total"
-    # keyword with old-style TypedDict().  See https://bugs.python.org/issue42059
-    # The standard library TypedDict below Python 3.11 does not store runtime
-    # information about optional and required keys when using Required or NotRequired.
-    # Generic TypedDicts are also impossible using typing.TypedDict on Python <3.11.
-    # Aaaand on 3.12 we add __orig_bases__ to TypedDict
-    # to enable better runtime introspection.
-    # On 3.13 we deprecate some odd ways of creating TypedDicts.
-    # Also on 3.13, PEP 705 adds the ReadOnly[] qualifier.
-    # PEP 728 (still pending) makes more changes.
-    TypedDict = typing.TypedDict
-    _TypedDictMeta = typing._TypedDictMeta
-    is_typeddict = typing.is_typeddict
-else:
-    # 3.10.0 and later
-    _TAKES_MODULE = "module" in inspect.signature(typing._type_check).parameters
-
-    def _get_typeddict_qualifiers(annotation_type):
-        while True:
-            annotation_origin = get_origin(annotation_type)
-            if annotation_origin is Annotated:
-                annotation_args = get_args(annotation_type)
-                if annotation_args:
-                    annotation_type = annotation_args[0]
-                else:
-                    break
-            elif annotation_origin is Required:
-                yield Required
-                annotation_type, = get_args(annotation_type)
-            elif annotation_origin is NotRequired:
-                yield NotRequired
-                annotation_type, = get_args(annotation_type)
-            elif annotation_origin is ReadOnly:
-                yield ReadOnly
-                annotation_type, = get_args(annotation_type)
-            else:
-                break
-
-    class _TypedDictMeta(type):
-        def __new__(cls, name, bases, ns, *, total=True, closed=False):
-            """Create new typed dict class object.
-
-            This method is called when TypedDict is subclassed,
-            or when TypedDict is instantiated. This way
-            TypedDict supports all three syntax forms described in its docstring.
-            Subclasses and instances of TypedDict return actual dictionaries.
-            """
-            for base in bases:
-                if type(base) is not _TypedDictMeta and base is not typing.Generic:
-                    raise TypeError('cannot inherit from both a TypedDict type '
-                                    'and a non-TypedDict base class')
-
-            if any(issubclass(b, typing.Generic) for b in bases):
-                generic_base = (typing.Generic,)
-            else:
-                generic_base = ()
-
-            # typing.py generally doesn't let you inherit from plain Generic, unless
-            # the name of the class happens to be "Protocol"
-            tp_dict = type.__new__(_TypedDictMeta, "Protocol", (*generic_base, dict), ns)
-            tp_dict.__name__ = name
-            if tp_dict.__qualname__ == "Protocol":
-                tp_dict.__qualname__ = name
-
-            if not hasattr(tp_dict, '__orig_bases__'):
-                tp_dict.__orig_bases__ = bases
-
-            annotations = {}
-            if "__annotations__" in ns:
-                own_annotations = ns["__annotations__"]
-            elif "__annotate__" in ns:
-                # TODO: Use inspect.VALUE here, and make the annotations lazily evaluated
-                own_annotations = ns["__annotate__"](1)
-            else:
-                own_annotations = {}
-            msg = "TypedDict('Name', {f0: t0, f1: t1, ...}); each t must be a type"
-            if _TAKES_MODULE:
-                own_annotations = {
-                    n: typing._type_check(tp, msg, module=tp_dict.__module__)
-                    for n, tp in own_annotations.items()
-                }
-            else:
-                own_annotations = {
-                    n: typing._type_check(tp, msg)
-                    for n, tp in own_annotations.items()
-                }
-            required_keys = set()
-            optional_keys = set()
-            readonly_keys = set()
-            mutable_keys = set()
-            extra_items_type = None
-
-            for base in bases:
-                base_dict = base.__dict__
-
-                annotations.update(base_dict.get('__annotations__', {}))
-                required_keys.update(base_dict.get('__required_keys__', ()))
-                optional_keys.update(base_dict.get('__optional_keys__', ()))
-                readonly_keys.update(base_dict.get('__readonly_keys__', ()))
-                mutable_keys.update(base_dict.get('__mutable_keys__', ()))
-                base_extra_items_type = base_dict.get('__extra_items__', None)
-                if base_extra_items_type is not None:
-                    extra_items_type = base_extra_items_type
-
-            if closed and extra_items_type is None:
-                extra_items_type = Never
-            if closed and "__extra_items__" in own_annotations:
-                annotation_type = own_annotations.pop("__extra_items__")
-                qualifiers = set(_get_typeddict_qualifiers(annotation_type))
-                if Required in qualifiers:
-                    raise TypeError(
-                        "Special key __extra_items__ does not support "
-                        "Required"
-                    )
-                if NotRequired in qualifiers:
-                    raise TypeError(
-                        "Special key __extra_items__ does not support "
-                        "NotRequired"
-                    )
-                extra_items_type = annotation_type
-
-            annotations.update(own_annotations)
-            for annotation_key, annotation_type in own_annotations.items():
-                qualifiers = set(_get_typeddict_qualifiers(annotation_type))
-
-                if Required in qualifiers:
-                    required_keys.add(annotation_key)
-                elif NotRequired in qualifiers:
-                    optional_keys.add(annotation_key)
-                elif total:
-                    required_keys.add(annotation_key)
-                else:
-                    optional_keys.add(annotation_key)
-                if ReadOnly in qualifiers:
-                    mutable_keys.discard(annotation_key)
-                    readonly_keys.add(annotation_key)
-                else:
-                    mutable_keys.add(annotation_key)
-                    readonly_keys.discard(annotation_key)
-
-            tp_dict.__annotations__ = annotations
-            tp_dict.__required_keys__ = frozenset(required_keys)
-            tp_dict.__optional_keys__ = frozenset(optional_keys)
-            tp_dict.__readonly_keys__ = frozenset(readonly_keys)
-            tp_dict.__mutable_keys__ = frozenset(mutable_keys)
-            if not hasattr(tp_dict, '__total__'):
-                tp_dict.__total__ = total
-            tp_dict.__closed__ = closed
-            tp_dict.__extra_items__ = extra_items_type
-            return tp_dict
-
-        __call__ = dict  # static method
-
-        def __subclasscheck__(cls, other):
-            # Typed dicts are only for static structural subtyping.
-            raise TypeError('TypedDict does not support instance and class checks')
-
-        __instancecheck__ = __subclasscheck__
-
-    _TypedDict = type.__new__(_TypedDictMeta, 'TypedDict', (), {})
-
-    @_ensure_subclassable(lambda bases: (_TypedDict,))
-    def TypedDict(typename, fields=_marker, /, *, total=True, closed=False, **kwargs):
-        """A simple typed namespace. At runtime it is equivalent to a plain dict.
-
-        TypedDict creates a dictionary type such that a type checker will expect all
-        instances to have a certain set of keys, where each key is
-        associated with a value of a consistent type. This expectation
-        is not checked at runtime.
-
-        Usage::
-
-            class Point2D(TypedDict):
-                x: int
-                y: int
-                label: str
-
-            a: Point2D = {'x': 1, 'y': 2, 'label': 'good'}  # OK
-            b: Point2D = {'z': 3, 'label': 'bad'}           # Fails type check
-
-            assert Point2D(x=1, y=2, label='first') == dict(x=1, y=2, label='first')
-
-        The type info can be accessed via the Point2D.__annotations__ dict, and
-        the Point2D.__required_keys__ and Point2D.__optional_keys__ frozensets.
-        TypedDict supports an additional equivalent form::
-
-            Point2D = TypedDict('Point2D', {'x': int, 'y': int, 'label': str})
-
-        By default, all keys must be present in a TypedDict. It is possible
-        to override this by specifying totality::
-
-            class Point2D(TypedDict, total=False):
-                x: int
-                y: int
-
-        This means that a Point2D TypedDict can have any of the keys omitted. A type
-        checker is only expected to support a literal False or True as the value of
-        the total argument. True is the default, and makes all items defined in the
-        class body be required.
-
-        The Required and NotRequired special forms can also be used to mark
-        individual keys as being required or not required::
-
-            class Point2D(TypedDict):
-                x: int  # the "x" key must always be present (Required is the default)
-                y: NotRequired[int]  # the "y" key can be omitted
-
-        See PEP 655 for more details on Required and NotRequired.
-        """
-        if fields is _marker or fields is None:
-            if fields is _marker:
-                deprecated_thing = "Failing to pass a value for the 'fields' parameter"
-            else:
-                deprecated_thing = "Passing `None` as the 'fields' parameter"
-
-            example = f"`{typename} = TypedDict({typename!r}, {{}})`"
-            deprecation_msg = (
-                f"{deprecated_thing} is deprecated and will be disallowed in "
-                "Python 3.15. To create a TypedDict class with 0 fields "
-                "using the functional syntax, pass an empty dictionary, e.g. "
-            ) + example + "."
-            warnings.warn(deprecation_msg, DeprecationWarning, stacklevel=2)
-            if closed is not False and closed is not True:
-                kwargs["closed"] = closed
-                closed = False
-            fields = kwargs
-        elif kwargs:
-            raise TypeError("TypedDict takes either a dict or keyword arguments,"
-                            " but not both")
-        if kwargs:
-            if sys.version_info >= (3, 13):
-                raise TypeError("TypedDict takes no keyword arguments")
-            warnings.warn(
-                "The kwargs-based syntax for TypedDict definitions is deprecated "
-                "in Python 3.11, will be removed in Python 3.13, and may not be "
-                "understood by third-party type checkers.",
-                DeprecationWarning,
-                stacklevel=2,
-            )
-
-        ns = {'__annotations__': dict(fields)}
-        module = _caller()
-        if module is not None:
-            # Setting correct module is necessary to make typed dict classes pickleable.
-            ns['__module__'] = module
-
-        td = _TypedDictMeta(typename, (), ns, total=total, closed=closed)
-        td.__orig_bases__ = (TypedDict,)
-        return td
-
-    if hasattr(typing, "_TypedDictMeta"):
-        _TYPEDDICT_TYPES = (typing._TypedDictMeta, _TypedDictMeta)
-    else:
-        _TYPEDDICT_TYPES = (_TypedDictMeta,)
-
-    def is_typeddict(tp):
-        """Check if an annotation is a TypedDict class
-
-        For example::
-            class Film(TypedDict):
-                title: str
-                year: int
-
-            is_typeddict(Film)  # => True
-            is_typeddict(Union[list, str])  # => False
-        """
-        # On 3.8, this would otherwise return True
-        if hasattr(typing, "TypedDict") and tp is typing.TypedDict:
-            return False
-        return isinstance(tp, _TYPEDDICT_TYPES)
-
-
-if hasattr(typing, "assert_type"):
-    assert_type = typing.assert_type
-
-else:
-    def assert_type(val, typ, /):
-        """Assert (to the type checker) that the value is of the given type.
-
-        When the type checker encounters a call to assert_type(), it
-        emits an error if the value is not of the specified type::
-
-            def greet(name: str) -> None:
-                assert_type(name, str)  # ok
-                assert_type(name, int)  # type checker error
-
-        At runtime this returns the first argument unchanged and otherwise
-        does nothing.
-        """
-        return val
-
-
-if hasattr(typing, "ReadOnly"):  # 3.13+
-    get_type_hints = typing.get_type_hints
-else:  # <=3.13
-    # replaces _strip_annotations()
-    def _strip_extras(t):
-        """Strips Annotated, Required and NotRequired from a given type."""
-        if isinstance(t, _AnnotatedAlias):
-            return _strip_extras(t.__origin__)
-        if hasattr(t, "__origin__") and t.__origin__ in (Required, NotRequired, ReadOnly):
-            return _strip_extras(t.__args__[0])
-        if isinstance(t, typing._GenericAlias):
-            stripped_args = tuple(_strip_extras(a) for a in t.__args__)
-            if stripped_args == t.__args__:
-                return t
-            return t.copy_with(stripped_args)
-        if hasattr(_types, "GenericAlias") and isinstance(t, _types.GenericAlias):
-            stripped_args = tuple(_strip_extras(a) for a in t.__args__)
-            if stripped_args == t.__args__:
-                return t
-            return _types.GenericAlias(t.__origin__, stripped_args)
-        if hasattr(_types, "UnionType") and isinstance(t, _types.UnionType):
-            stripped_args = tuple(_strip_extras(a) for a in t.__args__)
-            if stripped_args == t.__args__:
-                return t
-            return functools.reduce(operator.or_, stripped_args)
-
-        return t
-
-    def get_type_hints(obj, globalns=None, localns=None, include_extras=False):
-        """Return type hints for an object.
-
-        This is often the same as obj.__annotations__, but it handles
-        forward references encoded as string literals, adds Optional[t] if a
-        default value equal to None is set and recursively replaces all
-        'Annotated[T, ...]', 'Required[T]' or 'NotRequired[T]' with 'T'
-        (unless 'include_extras=True').
-
-        The argument may be a module, class, method, or function. The annotations
-        are returned as a dictionary. For classes, annotations include also
-        inherited members.
-
-        TypeError is raised if the argument is not of a type that can contain
-        annotations, and an empty dictionary is returned if no annotations are
-        present.
-
-        BEWARE -- the behavior of globalns and localns is counterintuitive
-        (unless you are familiar with how eval() and exec() work).  The
-        search order is locals first, then globals.
-
-        - If no dict arguments are passed, an attempt is made to use the
-          globals from obj (or the respective module's globals for classes),
-          and these are also used as the locals.  If the object does not appear
-          to have globals, an empty dictionary is used.
-
-        - If one dict argument is passed, it is used for both globals and
-          locals.
-
-        - If two dict arguments are passed, they specify globals and
-          locals, respectively.
-        """
-        if hasattr(typing, "Annotated"):  # 3.9+
-            hint = typing.get_type_hints(
-                obj, globalns=globalns, localns=localns, include_extras=True
-            )
-        else:  # 3.8
-            hint = typing.get_type_hints(obj, globalns=globalns, localns=localns)
-        if include_extras:
-            return hint
-        return {k: _strip_extras(t) for k, t in hint.items()}
-
-
-# Python 3.9+ has PEP 593 (Annotated)
-if hasattr(typing, 'Annotated'):
-    Annotated = typing.Annotated
-    # Not exported and not a public API, but needed for get_origin() and get_args()
-    # to work.
-    _AnnotatedAlias = typing._AnnotatedAlias
-# 3.8
-else:
-    class _AnnotatedAlias(typing._GenericAlias, _root=True):
-        """Runtime representation of an annotated type.
-
-        At its core 'Annotated[t, dec1, dec2, ...]' is an alias for the type 't'
-        with extra annotations. The alias behaves like a normal typing alias,
-        instantiating is the same as instantiating the underlying type, binding
-        it to types is also the same.
-        """
-        def __init__(self, origin, metadata):
-            if isinstance(origin, _AnnotatedAlias):
-                metadata = origin.__metadata__ + metadata
-                origin = origin.__origin__
-            super().__init__(origin, origin)
-            self.__metadata__ = metadata
-
-        def copy_with(self, params):
-            assert len(params) == 1
-            new_type = params[0]
-            return _AnnotatedAlias(new_type, self.__metadata__)
-
-        def __repr__(self):
-            return (f"typing_extensions.Annotated[{typing._type_repr(self.__origin__)}, "
-                    f"{', '.join(repr(a) for a in self.__metadata__)}]")
-
-        def __reduce__(self):
-            return operator.getitem, (
-                Annotated, (self.__origin__, *self.__metadata__)
-            )
-
-        def __eq__(self, other):
-            if not isinstance(other, _AnnotatedAlias):
-                return NotImplemented
-            if self.__origin__ != other.__origin__:
-                return False
-            return self.__metadata__ == other.__metadata__
-
-        def __hash__(self):
-            return hash((self.__origin__, self.__metadata__))
-
-    class Annotated:
-        """Add context specific metadata to a type.
-
-        Example: Annotated[int, runtime_check.Unsigned] indicates to the
-        hypothetical runtime_check module that this type is an unsigned int.
-        Every other consumer of this type can ignore this metadata and treat
-        this type as int.
-
-        The first argument to Annotated must be a valid type (and will be in
-        the __origin__ field), the remaining arguments are kept as a tuple in
-        the __extra__ field.
-
-        Details:
-
-        - It's an error to call `Annotated` with less than two arguments.
-        - Nested Annotated are flattened::
-
-            Annotated[Annotated[T, Ann1, Ann2], Ann3] == Annotated[T, Ann1, Ann2, Ann3]
-
-        - Instantiating an annotated type is equivalent to instantiating the
-        underlying type::
-
-            Annotated[C, Ann1](5) == C(5)
-
-        - Annotated can be used as a generic type alias::
-
-            Optimized = Annotated[T, runtime.Optimize()]
-            Optimized[int] == Annotated[int, runtime.Optimize()]
-
-            OptimizedList = Annotated[List[T], runtime.Optimize()]
-            OptimizedList[int] == Annotated[List[int], runtime.Optimize()]
-        """
-
-        __slots__ = ()
-
-        def __new__(cls, *args, **kwargs):
-            raise TypeError("Type Annotated cannot be instantiated.")
-
-        @typing._tp_cache
-        def __class_getitem__(cls, params):
-            if not isinstance(params, tuple) or len(params) < 2:
-                raise TypeError("Annotated[...] should be used "
-                                "with at least two arguments (a type and an "
-                                "annotation).")
-            allowed_special_forms = (ClassVar, Final)
-            if get_origin(params[0]) in allowed_special_forms:
-                origin = params[0]
-            else:
-                msg = "Annotated[t, ...]: t must be a type."
-                origin = typing._type_check(params[0], msg)
-            metadata = tuple(params[1:])
-            return _AnnotatedAlias(origin, metadata)
-
-        def __init_subclass__(cls, *args, **kwargs):
-            raise TypeError(
-                f"Cannot subclass {cls.__module__}.Annotated"
-            )
-
-# Python 3.8 has get_origin() and get_args() but those implementations aren't
-# Annotated-aware, so we can't use those. Python 3.9's versions don't support
-# ParamSpecArgs and ParamSpecKwargs, so only Python 3.10's versions will do.
-if sys.version_info[:2] >= (3, 10):
-    get_origin = typing.get_origin
-    get_args = typing.get_args
-# 3.8-3.9
-else:
-    try:
-        # 3.9+
-        from typing import _BaseGenericAlias
-    except ImportError:
-        _BaseGenericAlias = typing._GenericAlias
-    try:
-        # 3.9+
-        from typing import GenericAlias as _typing_GenericAlias
-    except ImportError:
-        _typing_GenericAlias = typing._GenericAlias
-
-    def get_origin(tp):
-        """Get the unsubscripted version of a type.
-
-        This supports generic types, Callable, Tuple, Union, Literal, Final, ClassVar
-        and Annotated. Return None for unsupported types. Examples::
-
-            get_origin(Literal[42]) is Literal
-            get_origin(int) is None
-            get_origin(ClassVar[int]) is ClassVar
-            get_origin(Generic) is Generic
-            get_origin(Generic[T]) is Generic
-            get_origin(Union[T, int]) is Union
-            get_origin(List[Tuple[T, T]][int]) == list
-            get_origin(P.args) is P
-        """
-        if isinstance(tp, _AnnotatedAlias):
-            return Annotated
-        if isinstance(tp, (typing._GenericAlias, _typing_GenericAlias, _BaseGenericAlias,
-                           ParamSpecArgs, ParamSpecKwargs)):
-            return tp.__origin__
-        if tp is typing.Generic:
-            return typing.Generic
-        return None
-
-    def get_args(tp):
-        """Get type arguments with all substitutions performed.
-
-        For unions, basic simplifications used by Union constructor are performed.
-        Examples::
-            get_args(Dict[str, int]) == (str, int)
-            get_args(int) == ()
-            get_args(Union[int, Union[T, int], str][int]) == (int, str)
-            get_args(Union[int, Tuple[T, int]][str]) == (int, Tuple[str, int])
-            get_args(Callable[[], T][int]) == ([], int)
-        """
-        if isinstance(tp, _AnnotatedAlias):
-            return (tp.__origin__, *tp.__metadata__)
-        if isinstance(tp, (typing._GenericAlias, _typing_GenericAlias)):
-            if getattr(tp, "_special", False):
-                return ()
-            res = tp.__args__
-            if get_origin(tp) is collections.abc.Callable and res[0] is not Ellipsis:
-                res = (list(res[:-1]), res[-1])
-            return res
-        return ()
-
-
-# 3.10+
-if hasattr(typing, 'TypeAlias'):
-    TypeAlias = typing.TypeAlias
-# 3.9
-elif sys.version_info[:2] >= (3, 9):
-    @_ExtensionsSpecialForm
-    def TypeAlias(self, parameters):
-        """Special marker indicating that an assignment should
-        be recognized as a proper type alias definition by type
-        checkers.
-
-        For example::
-
-            Predicate: TypeAlias = Callable[..., bool]
-
-        It's invalid when used anywhere except as in the example above.
-        """
-        raise TypeError(f"{self} is not subscriptable")
-# 3.8
-else:
-    TypeAlias = _ExtensionsSpecialForm(
-        'TypeAlias',
-        doc="""Special marker indicating that an assignment should
-        be recognized as a proper type alias definition by type
-        checkers.
-
-        For example::
-
-            Predicate: TypeAlias = Callable[..., bool]
-
-        It's invalid when used anywhere except as in the example
-        above."""
-    )
-
-
-if hasattr(typing, "NoDefault"):
-    NoDefault = typing.NoDefault
-else:
-    class NoDefaultTypeMeta(type):
-        def __setattr__(cls, attr, value):
-            # TypeError is consistent with the behavior of NoneType
-            raise TypeError(
-                f"cannot set {attr!r} attribute of immutable type {cls.__name__!r}"
-            )
-
-    class NoDefaultType(metaclass=NoDefaultTypeMeta):
-        """The type of the NoDefault singleton."""
-
-        __slots__ = ()
-
-        def __new__(cls):
-            return globals().get("NoDefault") or object.__new__(cls)
-
-        def __repr__(self):
-            return "typing_extensions.NoDefault"
-
-        def __reduce__(self):
-            return "NoDefault"
-
-    NoDefault = NoDefaultType()
-    del NoDefaultType, NoDefaultTypeMeta
-
-
-def _set_default(type_param, default):
-    type_param.has_default = lambda: default is not NoDefault
-    type_param.__default__ = default
-
-
-def _set_module(typevarlike):
-    # for pickling:
-    def_mod = _caller(depth=3)
-    if def_mod != 'typing_extensions':
-        typevarlike.__module__ = def_mod
-
-
-class _DefaultMixin:
-    """Mixin for TypeVarLike defaults."""
-
-    __slots__ = ()
-    __init__ = _set_default
-
-
-# Classes using this metaclass must provide a _backported_typevarlike ClassVar
-class _TypeVarLikeMeta(type):
-    def __instancecheck__(cls, __instance: Any) -> bool:
-        return isinstance(__instance, cls._backported_typevarlike)
-
-
-if _PEP_696_IMPLEMENTED:
-    from typing import TypeVar
-else:
-    # Add default and infer_variance parameters from PEP 696 and 695
-    class TypeVar(metaclass=_TypeVarLikeMeta):
-        """Type variable."""
-
-        _backported_typevarlike = typing.TypeVar
-
-        def __new__(cls, name, *constraints, bound=None,
-                    covariant=False, contravariant=False,
-                    default=NoDefault, infer_variance=False):
-            if hasattr(typing, "TypeAliasType"):
-                # PEP 695 implemented (3.12+), can pass infer_variance to typing.TypeVar
-                typevar = typing.TypeVar(name, *constraints, bound=bound,
-                                         covariant=covariant, contravariant=contravariant,
-                                         infer_variance=infer_variance)
-            else:
-                typevar = typing.TypeVar(name, *constraints, bound=bound,
-                                         covariant=covariant, contravariant=contravariant)
-                if infer_variance and (covariant or contravariant):
-                    raise ValueError("Variance cannot be specified with infer_variance.")
-                typevar.__infer_variance__ = infer_variance
-
-            _set_default(typevar, default)
-            _set_module(typevar)
-
-            def _tvar_prepare_subst(alias, args):
-                if (
-                    typevar.has_default()
-                    and alias.__parameters__.index(typevar) == len(args)
-                ):
-                    args += (typevar.__default__,)
-                return args
-
-            typevar.__typing_prepare_subst__ = _tvar_prepare_subst
-            return typevar
-
-        def __init_subclass__(cls) -> None:
-            raise TypeError(f"type '{__name__}.TypeVar' is not an acceptable base type")
-
-
-# Python 3.10+ has PEP 612
-if hasattr(typing, 'ParamSpecArgs'):
-    ParamSpecArgs = typing.ParamSpecArgs
-    ParamSpecKwargs = typing.ParamSpecKwargs
-# 3.8-3.9
-else:
-    class _Immutable:
-        """Mixin to indicate that object should not be copied."""
-        __slots__ = ()
-
-        def __copy__(self):
-            return self
-
-        def __deepcopy__(self, memo):
-            return self
-
-    class ParamSpecArgs(_Immutable):
-        """The args for a ParamSpec object.
-
-        Given a ParamSpec object P, P.args is an instance of ParamSpecArgs.
-
-        ParamSpecArgs objects have a reference back to their ParamSpec:
-
-        P.args.__origin__ is P
-
-        This type is meant for runtime introspection and has no special meaning to
-        static type checkers.
-        """
-        def __init__(self, origin):
-            self.__origin__ = origin
-
-        def __repr__(self):
-            return f"{self.__origin__.__name__}.args"
-
-        def __eq__(self, other):
-            if not isinstance(other, ParamSpecArgs):
-                return NotImplemented
-            return self.__origin__ == other.__origin__
-
-    class ParamSpecKwargs(_Immutable):
-        """The kwargs for a ParamSpec object.
-
-        Given a ParamSpec object P, P.kwargs is an instance of ParamSpecKwargs.
-
-        ParamSpecKwargs objects have a reference back to their ParamSpec:
-
-        P.kwargs.__origin__ is P
-
-        This type is meant for runtime introspection and has no special meaning to
-        static type checkers.
-        """
-        def __init__(self, origin):
-            self.__origin__ = origin
-
-        def __repr__(self):
-            return f"{self.__origin__.__name__}.kwargs"
-
-        def __eq__(self, other):
-            if not isinstance(other, ParamSpecKwargs):
-                return NotImplemented
-            return self.__origin__ == other.__origin__
-
-
-if _PEP_696_IMPLEMENTED:
-    from typing import ParamSpec
-
-# 3.10+
-elif hasattr(typing, 'ParamSpec'):
-
-    # Add default parameter - PEP 696
-    class ParamSpec(metaclass=_TypeVarLikeMeta):
-        """Parameter specification."""
-
-        _backported_typevarlike = typing.ParamSpec
-
-        def __new__(cls, name, *, bound=None,
-                    covariant=False, contravariant=False,
-                    infer_variance=False, default=NoDefault):
-            if hasattr(typing, "TypeAliasType"):
-                # PEP 695 implemented, can pass infer_variance to typing.TypeVar
-                paramspec = typing.ParamSpec(name, bound=bound,
-                                             covariant=covariant,
-                                             contravariant=contravariant,
-                                             infer_variance=infer_variance)
-            else:
-                paramspec = typing.ParamSpec(name, bound=bound,
-                                             covariant=covariant,
-                                             contravariant=contravariant)
-                paramspec.__infer_variance__ = infer_variance
-
-            _set_default(paramspec, default)
-            _set_module(paramspec)
-
-            def _paramspec_prepare_subst(alias, args):
-                params = alias.__parameters__
-                i = params.index(paramspec)
-                if i == len(args) and paramspec.has_default():
-                    args = [*args, paramspec.__default__]
-                if i >= len(args):
-                    raise TypeError(f"Too few arguments for {alias}")
-                # Special case where Z[[int, str, bool]] == Z[int, str, bool] in PEP 612.
-                if len(params) == 1 and not typing._is_param_expr(args[0]):
-                    assert i == 0
-                    args = (args,)
-                # Convert lists to tuples to help other libraries cache the results.
-                elif isinstance(args[i], list):
-                    args = (*args[:i], tuple(args[i]), *args[i + 1:])
-                return args
-
-            paramspec.__typing_prepare_subst__ = _paramspec_prepare_subst
-            return paramspec
-
-        def __init_subclass__(cls) -> None:
-            raise TypeError(f"type '{__name__}.ParamSpec' is not an acceptable base type")
-
-# 3.8-3.9
-else:
-
-    # Inherits from list as a workaround for Callable checks in Python < 3.9.2.
-    class ParamSpec(list, _DefaultMixin):
-        """Parameter specification variable.
-
-        Usage::
-
-           P = ParamSpec('P')
-
-        Parameter specification variables exist primarily for the benefit of static
-        type checkers.  They are used to forward the parameter types of one
-        callable to another callable, a pattern commonly found in higher order
-        functions and decorators.  They are only valid when used in ``Concatenate``,
-        or s the first argument to ``Callable``. In Python 3.10 and higher,
-        they are also supported in user-defined Generics at runtime.
-        See class Generic for more information on generic types.  An
-        example for annotating a decorator::
-
-           T = TypeVar('T')
-           P = ParamSpec('P')
-
-           def add_logging(f: Callable[P, T]) -> Callable[P, T]:
-               '''A type-safe decorator to add logging to a function.'''
-               def inner(*args: P.args, **kwargs: P.kwargs) -> T:
-                   logging.info(f'{f.__name__} was called')
-                   return f(*args, **kwargs)
-               return inner
-
-           @add_logging
-           def add_two(x: float, y: float) -> float:
-               '''Add two numbers together.'''
-               return x + y
-
-        Parameter specification variables defined with covariant=True or
-        contravariant=True can be used to declare covariant or contravariant
-        generic types.  These keyword arguments are valid, but their actual semantics
-        are yet to be decided.  See PEP 612 for details.
-
-        Parameter specification variables can be introspected. e.g.:
-
-           P.__name__ == 'T'
-           P.__bound__ == None
-           P.__covariant__ == False
-           P.__contravariant__ == False
-
-        Note that only parameter specification variables defined in global scope can
-        be pickled.
-        """
-
-        # Trick Generic __parameters__.
-        __class__ = typing.TypeVar
-
-        @property
-        def args(self):
-            return ParamSpecArgs(self)
-
-        @property
-        def kwargs(self):
-            return ParamSpecKwargs(self)
-
-        def __init__(self, name, *, bound=None, covariant=False, contravariant=False,
-                     infer_variance=False, default=NoDefault):
-            list.__init__(self, [self])
-            self.__name__ = name
-            self.__covariant__ = bool(covariant)
-            self.__contravariant__ = bool(contravariant)
-            self.__infer_variance__ = bool(infer_variance)
-            if bound:
-                self.__bound__ = typing._type_check(bound, 'Bound must be a type.')
-            else:
-                self.__bound__ = None
-            _DefaultMixin.__init__(self, default)
-
-            # for pickling:
-            def_mod = _caller()
-            if def_mod != 'typing_extensions':
-                self.__module__ = def_mod
-
-        def __repr__(self):
-            if self.__infer_variance__:
-                prefix = ''
-            elif self.__covariant__:
-                prefix = '+'
-            elif self.__contravariant__:
-                prefix = '-'
-            else:
-                prefix = '~'
-            return prefix + self.__name__
-
-        def __hash__(self):
-            return object.__hash__(self)
-
-        def __eq__(self, other):
-            return self is other
-
-        def __reduce__(self):
-            return self.__name__
-
-        # Hack to get typing._type_check to pass.
-        def __call__(self, *args, **kwargs):
-            pass
-
-
-# 3.8-3.9
-if not hasattr(typing, 'Concatenate'):
-    # Inherits from list as a workaround for Callable checks in Python < 3.9.2.
-    class _ConcatenateGenericAlias(list):
-
-        # Trick Generic into looking into this for __parameters__.
-        __class__ = typing._GenericAlias
-
-        # Flag in 3.8.
-        _special = False
-
-        def __init__(self, origin, args):
-            super().__init__(args)
-            self.__origin__ = origin
-            self.__args__ = args
-
-        def __repr__(self):
-            _type_repr = typing._type_repr
-            return (f'{_type_repr(self.__origin__)}'
-                    f'[{", ".join(_type_repr(arg) for arg in self.__args__)}]')
-
-        def __hash__(self):
-            return hash((self.__origin__, self.__args__))
-
-        # Hack to get typing._type_check to pass in Generic.
-        def __call__(self, *args, **kwargs):
-            pass
-
-        @property
-        def __parameters__(self):
-            return tuple(
-                tp for tp in self.__args__ if isinstance(tp, (typing.TypeVar, ParamSpec))
-            )
-
-
-# 3.8-3.9
-@typing._tp_cache
-def _concatenate_getitem(self, parameters):
-    if parameters == ():
-        raise TypeError("Cannot take a Concatenate of no types.")
-    if not isinstance(parameters, tuple):
-        parameters = (parameters,)
-    if not isinstance(parameters[-1], ParamSpec):
-        raise TypeError("The last parameter to Concatenate should be a "
-                        "ParamSpec variable.")
-    msg = "Concatenate[arg, ...]: each arg must be a type."
-    parameters = tuple(typing._type_check(p, msg) for p in parameters)
-    return _ConcatenateGenericAlias(self, parameters)
-
-
-# 3.10+
-if hasattr(typing, 'Concatenate'):
-    Concatenate = typing.Concatenate
-    _ConcatenateGenericAlias = typing._ConcatenateGenericAlias
-# 3.9
-elif sys.version_info[:2] >= (3, 9):
-    @_ExtensionsSpecialForm
-    def Concatenate(self, parameters):
-        """Used in conjunction with ``ParamSpec`` and ``Callable`` to represent a
-        higher order function which adds, removes or transforms parameters of a
-        callable.
-
-        For example::
-
-           Callable[Concatenate[int, P], int]
-
-        See PEP 612 for detailed information.
-        """
-        return _concatenate_getitem(self, parameters)
-# 3.8
-else:
-    class _ConcatenateForm(_ExtensionsSpecialForm, _root=True):
-        def __getitem__(self, parameters):
-            return _concatenate_getitem(self, parameters)
-
-    Concatenate = _ConcatenateForm(
-        'Concatenate',
-        doc="""Used in conjunction with ``ParamSpec`` and ``Callable`` to represent a
-        higher order function which adds, removes or transforms parameters of a
-        callable.
-
-        For example::
-
-           Callable[Concatenate[int, P], int]
-
-        See PEP 612 for detailed information.
-        """)
-
-# 3.10+
-if hasattr(typing, 'TypeGuard'):
-    TypeGuard = typing.TypeGuard
-# 3.9
-elif sys.version_info[:2] >= (3, 9):
-    @_ExtensionsSpecialForm
-    def TypeGuard(self, parameters):
-        """Special typing form used to annotate the return type of a user-defined
-        type guard function.  ``TypeGuard`` only accepts a single type argument.
-        At runtime, functions marked this way should return a boolean.
-
-        ``TypeGuard`` aims to benefit *type narrowing* -- a technique used by static
-        type checkers to determine a more precise type of an expression within a
-        program's code flow.  Usually type narrowing is done by analyzing
-        conditional code flow and applying the narrowing to a block of code.  The
-        conditional expression here is sometimes referred to as a "type guard".
-
-        Sometimes it would be convenient to use a user-defined boolean function
-        as a type guard.  Such a function should use ``TypeGuard[...]`` as its
-        return type to alert static type checkers to this intention.
-
-        Using  ``-> TypeGuard`` tells the static type checker that for a given
-        function:
-
-        1. The return value is a boolean.
-        2. If the return value is ``True``, the type of its argument
-        is the type inside ``TypeGuard``.
-
-        For example::
-
-            def is_str(val: Union[str, float]):
-                # "isinstance" type guard
-                if isinstance(val, str):
-                    # Type of ``val`` is narrowed to ``str``
-                    ...
-                else:
-                    # Else, type of ``val`` is narrowed to ``float``.
-                    ...
-
-        Strict type narrowing is not enforced -- ``TypeB`` need not be a narrower
-        form of ``TypeA`` (it can even be a wider form) and this may lead to
-        type-unsafe results.  The main reason is to allow for things like
-        narrowing ``List[object]`` to ``List[str]`` even though the latter is not
-        a subtype of the former, since ``List`` is invariant.  The responsibility of
-        writing type-safe type guards is left to the user.
-
-        ``TypeGuard`` also works with type variables.  For more information, see
-        PEP 647 (User-Defined Type Guards).
-        """
-        item = typing._type_check(parameters, f'{self} accepts only a single type.')
-        return typing._GenericAlias(self, (item,))
-# 3.8
-else:
-    class _TypeGuardForm(_ExtensionsSpecialForm, _root=True):
-        def __getitem__(self, parameters):
-            item = typing._type_check(parameters,
-                                      f'{self._name} accepts only a single type')
-            return typing._GenericAlias(self, (item,))
-
-    TypeGuard = _TypeGuardForm(
-        'TypeGuard',
-        doc="""Special typing form used to annotate the return type of a user-defined
-        type guard function.  ``TypeGuard`` only accepts a single type argument.
-        At runtime, functions marked this way should return a boolean.
-
-        ``TypeGuard`` aims to benefit *type narrowing* -- a technique used by static
-        type checkers to determine a more precise type of an expression within a
-        program's code flow.  Usually type narrowing is done by analyzing
-        conditional code flow and applying the narrowing to a block of code.  The
-        conditional expression here is sometimes referred to as a "type guard".
-
-        Sometimes it would be convenient to use a user-defined boolean function
-        as a type guard.  Such a function should use ``TypeGuard[...]`` as its
-        return type to alert static type checkers to this intention.
-
-        Using  ``-> TypeGuard`` tells the static type checker that for a given
-        function:
-
-        1. The return value is a boolean.
-        2. If the return value is ``True``, the type of its argument
-        is the type inside ``TypeGuard``.
-
-        For example::
-
-            def is_str(val: Union[str, float]):
-                # "isinstance" type guard
-                if isinstance(val, str):
-                    # Type of ``val`` is narrowed to ``str``
-                    ...
-                else:
-                    # Else, type of ``val`` is narrowed to ``float``.
-                    ...
-
-        Strict type narrowing is not enforced -- ``TypeB`` need not be a narrower
-        form of ``TypeA`` (it can even be a wider form) and this may lead to
-        type-unsafe results.  The main reason is to allow for things like
-        narrowing ``List[object]`` to ``List[str]`` even though the latter is not
-        a subtype of the former, since ``List`` is invariant.  The responsibility of
-        writing type-safe type guards is left to the user.
-
-        ``TypeGuard`` also works with type variables.  For more information, see
-        PEP 647 (User-Defined Type Guards).
-        """)
-
-# 3.13+
-if hasattr(typing, 'TypeIs'):
-    TypeIs = typing.TypeIs
-# 3.9
-elif sys.version_info[:2] >= (3, 9):
-    @_ExtensionsSpecialForm
-    def TypeIs(self, parameters):
-        """Special typing form used to annotate the return type of a user-defined
-        type narrower function.  ``TypeIs`` only accepts a single type argument.
-        At runtime, functions marked this way should return a boolean.
-
-        ``TypeIs`` aims to benefit *type narrowing* -- a technique used by static
-        type checkers to determine a more precise type of an expression within a
-        program's code flow.  Usually type narrowing is done by analyzing
-        conditional code flow and applying the narrowing to a block of code.  The
-        conditional expression here is sometimes referred to as a "type guard".
-
-        Sometimes it would be convenient to use a user-defined boolean function
-        as a type guard.  Such a function should use ``TypeIs[...]`` as its
-        return type to alert static type checkers to this intention.
-
-        Using  ``-> TypeIs`` tells the static type checker that for a given
-        function:
-
-        1. The return value is a boolean.
-        2. If the return value is ``True``, the type of its argument
-        is the intersection of the type inside ``TypeGuard`` and the argument's
-        previously known type.
-
-        For example::
-
-            def is_awaitable(val: object) -> TypeIs[Awaitable[Any]]:
-                return hasattr(val, '__await__')
-
-            def f(val: Union[int, Awaitable[int]]) -> int:
-                if is_awaitable(val):
-                    assert_type(val, Awaitable[int])
-                else:
-                    assert_type(val, int)
-
-        ``TypeIs`` also works with type variables.  For more information, see
-        PEP 742 (Narrowing types with TypeIs).
-        """
-        item = typing._type_check(parameters, f'{self} accepts only a single type.')
-        return typing._GenericAlias(self, (item,))
-# 3.8
-else:
-    class _TypeIsForm(_ExtensionsSpecialForm, _root=True):
-        def __getitem__(self, parameters):
-            item = typing._type_check(parameters,
-                                      f'{self._name} accepts only a single type')
-            return typing._GenericAlias(self, (item,))
-
-    TypeIs = _TypeIsForm(
-        'TypeIs',
-        doc="""Special typing form used to annotate the return type of a user-defined
-        type narrower function.  ``TypeIs`` only accepts a single type argument.
-        At runtime, functions marked this way should return a boolean.
-
-        ``TypeIs`` aims to benefit *type narrowing* -- a technique used by static
-        type checkers to determine a more precise type of an expression within a
-        program's code flow.  Usually type narrowing is done by analyzing
-        conditional code flow and applying the narrowing to a block of code.  The
-        conditional expression here is sometimes referred to as a "type guard".
-
-        Sometimes it would be convenient to use a user-defined boolean function
-        as a type guard.  Such a function should use ``TypeIs[...]`` as its
-        return type to alert static type checkers to this intention.
-
-        Using  ``-> TypeIs`` tells the static type checker that for a given
-        function:
-
-        1. The return value is a boolean.
-        2. If the return value is ``True``, the type of its argument
-        is the intersection of the type inside ``TypeGuard`` and the argument's
-        previously known type.
-
-        For example::
-
-            def is_awaitable(val: object) -> TypeIs[Awaitable[Any]]:
-                return hasattr(val, '__await__')
-
-            def f(val: Union[int, Awaitable[int]]) -> int:
-                if is_awaitable(val):
-                    assert_type(val, Awaitable[int])
-                else:
-                    assert_type(val, int)
-
-        ``TypeIs`` also works with type variables.  For more information, see
-        PEP 742 (Narrowing types with TypeIs).
-        """)
-
-
-# Vendored from cpython typing._SpecialFrom
-class _SpecialForm(typing._Final, _root=True):
-    __slots__ = ('_name', '__doc__', '_getitem')
-
-    def __init__(self, getitem):
-        self._getitem = getitem
-        self._name = getitem.__name__
-        self.__doc__ = getitem.__doc__
-
-    def __getattr__(self, item):
-        if item in {'__name__', '__qualname__'}:
-            return self._name
-
-        raise AttributeError(item)
-
-    def __mro_entries__(self, bases):
-        raise TypeError(f"Cannot subclass {self!r}")
-
-    def __repr__(self):
-        return f'typing_extensions.{self._name}'
-
-    def __reduce__(self):
-        return self._name
-
-    def __call__(self, *args, **kwds):
-        raise TypeError(f"Cannot instantiate {self!r}")
-
-    def __or__(self, other):
-        return typing.Union[self, other]
-
-    def __ror__(self, other):
-        return typing.Union[other, self]
-
-    def __instancecheck__(self, obj):
-        raise TypeError(f"{self} cannot be used with isinstance()")
-
-    def __subclasscheck__(self, cls):
-        raise TypeError(f"{self} cannot be used with issubclass()")
-
-    @typing._tp_cache
-    def __getitem__(self, parameters):
-        return self._getitem(self, parameters)
-
-
-if hasattr(typing, "LiteralString"):  # 3.11+
-    LiteralString = typing.LiteralString
-else:
-    @_SpecialForm
-    def LiteralString(self, params):
-        """Represents an arbitrary literal string.
-
-        Example::
-
-          from typing_extensions import LiteralString
-
-          def query(sql: LiteralString) -> ...:
-              ...
-
-          query("SELECT * FROM table")  # ok
-          query(f"SELECT * FROM {input()}")  # not ok
-
-        See PEP 675 for details.
-
-        """
-        raise TypeError(f"{self} is not subscriptable")
-
-
-if hasattr(typing, "Self"):  # 3.11+
-    Self = typing.Self
-else:
-    @_SpecialForm
-    def Self(self, params):
-        """Used to spell the type of "self" in classes.
-
-        Example::
-
-          from typing import Self
-
-          class ReturnsSelf:
-              def parse(self, data: bytes) -> Self:
-                  ...
-                  return self
-
-        """
-
-        raise TypeError(f"{self} is not subscriptable")
-
-
-if hasattr(typing, "Never"):  # 3.11+
-    Never = typing.Never
-else:
-    @_SpecialForm
-    def Never(self, params):
-        """The bottom type, a type that has no members.
-
-        This can be used to define a function that should never be
-        called, or a function that never returns::
-
-            from typing_extensions import Never
-
-            def never_call_me(arg: Never) -> None:
-                pass
-
-            def int_or_str(arg: int | str) -> None:
-                never_call_me(arg)  # type checker error
-                match arg:
-                    case int():
-                        print("It's an int")
-                    case str():
-                        print("It's a str")
-                    case _:
-                        never_call_me(arg)  # ok, arg is of type Never
-
-        """
-
-        raise TypeError(f"{self} is not subscriptable")
-
-
-if hasattr(typing, 'Required'):  # 3.11+
-    Required = typing.Required
-    NotRequired = typing.NotRequired
-elif sys.version_info[:2] >= (3, 9):  # 3.9-3.10
-    @_ExtensionsSpecialForm
-    def Required(self, parameters):
-        """A special typing construct to mark a key of a total=False TypedDict
-        as required. For example:
-
-            class Movie(TypedDict, total=False):
-                title: Required[str]
-                year: int
-
-            m = Movie(
-                title='The Matrix',  # typechecker error if key is omitted
-                year=1999,
-            )
-
-        There is no runtime checking that a required key is actually provided
-        when instantiating a related TypedDict.
-        """
-        item = typing._type_check(parameters, f'{self._name} accepts only a single type.')
-        return typing._GenericAlias(self, (item,))
-
-    @_ExtensionsSpecialForm
-    def NotRequired(self, parameters):
-        """A special typing construct to mark a key of a TypedDict as
-        potentially missing. For example:
-
-            class Movie(TypedDict):
-                title: str
-                year: NotRequired[int]
-
-            m = Movie(
-                title='The Matrix',  # typechecker error if key is omitted
-                year=1999,
-            )
-        """
-        item = typing._type_check(parameters, f'{self._name} accepts only a single type.')
-        return typing._GenericAlias(self, (item,))
-
-else:  # 3.8
-    class _RequiredForm(_ExtensionsSpecialForm, _root=True):
-        def __getitem__(self, parameters):
-            item = typing._type_check(parameters,
-                                      f'{self._name} accepts only a single type.')
-            return typing._GenericAlias(self, (item,))
-
-    Required = _RequiredForm(
-        'Required',
-        doc="""A special typing construct to mark a key of a total=False TypedDict
-        as required. For example:
-
-            class Movie(TypedDict, total=False):
-                title: Required[str]
-                year: int
-
-            m = Movie(
-                title='The Matrix',  # typechecker error if key is omitted
-                year=1999,
-            )
-
-        There is no runtime checking that a required key is actually provided
-        when instantiating a related TypedDict.
-        """)
-    NotRequired = _RequiredForm(
-        'NotRequired',
-        doc="""A special typing construct to mark a key of a TypedDict as
-        potentially missing. For example:
-
-            class Movie(TypedDict):
-                title: str
-                year: NotRequired[int]
-
-            m = Movie(
-                title='The Matrix',  # typechecker error if key is omitted
-                year=1999,
-            )
-        """)
-
-
-if hasattr(typing, 'ReadOnly'):
-    ReadOnly = typing.ReadOnly
-elif sys.version_info[:2] >= (3, 9):  # 3.9-3.12
-    @_ExtensionsSpecialForm
-    def ReadOnly(self, parameters):
-        """A special typing construct to mark an item of a TypedDict as read-only.
-
-        For example:
-
-            class Movie(TypedDict):
-                title: ReadOnly[str]
-                year: int
-
-            def mutate_movie(m: Movie) -> None:
-                m["year"] = 1992  # allowed
-                m["title"] = "The Matrix"  # typechecker error
-
-        There is no runtime checking for this property.
-        """
-        item = typing._type_check(parameters, f'{self._name} accepts only a single type.')
-        return typing._GenericAlias(self, (item,))
-
-else:  # 3.8
-    class _ReadOnlyForm(_ExtensionsSpecialForm, _root=True):
-        def __getitem__(self, parameters):
-            item = typing._type_check(parameters,
-                                      f'{self._name} accepts only a single type.')
-            return typing._GenericAlias(self, (item,))
-
-    ReadOnly = _ReadOnlyForm(
-        'ReadOnly',
-        doc="""A special typing construct to mark a key of a TypedDict as read-only.
-
-        For example:
-
-            class Movie(TypedDict):
-                title: ReadOnly[str]
-                year: int
-
-            def mutate_movie(m: Movie) -> None:
-                m["year"] = 1992  # allowed
-                m["title"] = "The Matrix"  # typechecker error
-
-        There is no runtime checking for this propery.
-        """)
-
-
-_UNPACK_DOC = """\
-Type unpack operator.
-
-The type unpack operator takes the child types from some container type,
-such as `tuple[int, str]` or a `TypeVarTuple`, and 'pulls them out'. For
-example:
-
-  # For some generic class `Foo`:
-  Foo[Unpack[tuple[int, str]]]  # Equivalent to Foo[int, str]
-
-  Ts = TypeVarTuple('Ts')
-  # Specifies that `Bar` is generic in an arbitrary number of types.
-  # (Think of `Ts` as a tuple of an arbitrary number of individual
-  #  `TypeVar`s, which the `Unpack` is 'pulling out' directly into the
-  #  `Generic[]`.)
-  class Bar(Generic[Unpack[Ts]]): ...
-  Bar[int]  # Valid
-  Bar[int, str]  # Also valid
-
-From Python 3.11, this can also be done using the `*` operator:
-
-    Foo[*tuple[int, str]]
-    class Bar(Generic[*Ts]): ...
-
-The operator can also be used along with a `TypedDict` to annotate
-`**kwargs` in a function signature. For instance:
-
-  class Movie(TypedDict):
-    name: str
-    year: int
-
-  # This function expects two keyword arguments - *name* of type `str` and
-  # *year* of type `int`.
-  def foo(**kwargs: Unpack[Movie]): ...
-
-Note that there is only some runtime checking of this operator. Not
-everything the runtime allows may be accepted by static type checkers.
-
-For more information, see PEP 646 and PEP 692.
-"""
-
-
-if sys.version_info >= (3, 12):  # PEP 692 changed the repr of Unpack[]
-    Unpack = typing.Unpack
-
-    def _is_unpack(obj):
-        return get_origin(obj) is Unpack
-
-elif sys.version_info[:2] >= (3, 9):  # 3.9+
-    class _UnpackSpecialForm(_ExtensionsSpecialForm, _root=True):
-        def __init__(self, getitem):
-            super().__init__(getitem)
-            self.__doc__ = _UNPACK_DOC
-
-    class _UnpackAlias(typing._GenericAlias, _root=True):
-        __class__ = typing.TypeVar
-
-        @property
-        def __typing_unpacked_tuple_args__(self):
-            assert self.__origin__ is Unpack
-            assert len(self.__args__) == 1
-            arg, = self.__args__
-            if isinstance(arg, (typing._GenericAlias, _types.GenericAlias)):
-                if arg.__origin__ is not tuple:
-                    raise TypeError("Unpack[...] must be used with a tuple type")
-                return arg.__args__
-            return None
-
-    @_UnpackSpecialForm
-    def Unpack(self, parameters):
-        item = typing._type_check(parameters, f'{self._name} accepts only a single type.')
-        return _UnpackAlias(self, (item,))
-
-    def _is_unpack(obj):
-        return isinstance(obj, _UnpackAlias)
-
-else:  # 3.8
-    class _UnpackAlias(typing._GenericAlias, _root=True):
-        __class__ = typing.TypeVar
-
-    class _UnpackForm(_ExtensionsSpecialForm, _root=True):
-        def __getitem__(self, parameters):
-            item = typing._type_check(parameters,
-                                      f'{self._name} accepts only a single type.')
-            return _UnpackAlias(self, (item,))
-
-    Unpack = _UnpackForm('Unpack', doc=_UNPACK_DOC)
-
-    def _is_unpack(obj):
-        return isinstance(obj, _UnpackAlias)
-
-
-if _PEP_696_IMPLEMENTED:
-    from typing import TypeVarTuple
-
-elif hasattr(typing, "TypeVarTuple"):  # 3.11+
-
-    def _unpack_args(*args):
-        newargs = []
-        for arg in args:
-            subargs = getattr(arg, '__typing_unpacked_tuple_args__', None)
-            if subargs is not None and not (subargs and subargs[-1] is ...):
-                newargs.extend(subargs)
-            else:
-                newargs.append(arg)
-        return newargs
-
-    # Add default parameter - PEP 696
-    class TypeVarTuple(metaclass=_TypeVarLikeMeta):
-        """Type variable tuple."""
-
-        _backported_typevarlike = typing.TypeVarTuple
-
-        def __new__(cls, name, *, default=NoDefault):
-            tvt = typing.TypeVarTuple(name)
-            _set_default(tvt, default)
-            _set_module(tvt)
-
-            def _typevartuple_prepare_subst(alias, args):
-                params = alias.__parameters__
-                typevartuple_index = params.index(tvt)
-                for param in params[typevartuple_index + 1:]:
-                    if isinstance(param, TypeVarTuple):
-                        raise TypeError(
-                            f"More than one TypeVarTuple parameter in {alias}"
-                        )
-
-                alen = len(args)
-                plen = len(params)
-                left = typevartuple_index
-                right = plen - typevartuple_index - 1
-                var_tuple_index = None
-                fillarg = None
-                for k, arg in enumerate(args):
-                    if not isinstance(arg, type):
-                        subargs = getattr(arg, '__typing_unpacked_tuple_args__', None)
-                        if subargs and len(subargs) == 2 and subargs[-1] is ...:
-                            if var_tuple_index is not None:
-                                raise TypeError(
-                                    "More than one unpacked "
-                                    "arbitrary-length tuple argument"
-                                )
-                            var_tuple_index = k
-                            fillarg = subargs[0]
-                if var_tuple_index is not None:
-                    left = min(left, var_tuple_index)
-                    right = min(right, alen - var_tuple_index - 1)
-                elif left + right > alen:
-                    raise TypeError(f"Too few arguments for {alias};"
-                                    f" actual {alen}, expected at least {plen - 1}")
-                if left == alen - right and tvt.has_default():
-                    replacement = _unpack_args(tvt.__default__)
-                else:
-                    replacement = args[left: alen - right]
-
-                return (
-                    *args[:left],
-                    *([fillarg] * (typevartuple_index - left)),
-                    replacement,
-                    *([fillarg] * (plen - right - left - typevartuple_index - 1)),
-                    *args[alen - right:],
-                )
-
-            tvt.__typing_prepare_subst__ = _typevartuple_prepare_subst
-            return tvt
-
-        def __init_subclass__(self, *args, **kwds):
-            raise TypeError("Cannot subclass special typing classes")
-
-else:  # <=3.10
-    class TypeVarTuple(_DefaultMixin):
-        """Type variable tuple.
-
-        Usage::
-
-            Ts = TypeVarTuple('Ts')
-
-        In the same way that a normal type variable is a stand-in for a single
-        type such as ``int``, a type variable *tuple* is a stand-in for a *tuple*
-        type such as ``Tuple[int, str]``.
-
-        Type variable tuples can be used in ``Generic`` declarations.
-        Consider the following example::
-
-            class Array(Generic[*Ts]): ...
-
-        The ``Ts`` type variable tuple here behaves like ``tuple[T1, T2]``,
-        where ``T1`` and ``T2`` are type variables. To use these type variables
-        as type parameters of ``Array``, we must *unpack* the type variable tuple using
-        the star operator: ``*Ts``. The signature of ``Array`` then behaves
-        as if we had simply written ``class Array(Generic[T1, T2]): ...``.
-        In contrast to ``Generic[T1, T2]``, however, ``Generic[*Shape]`` allows
-        us to parameterise the class with an *arbitrary* number of type parameters.
-
-        Type variable tuples can be used anywhere a normal ``TypeVar`` can.
-        This includes class definitions, as shown above, as well as function
-        signatures and variable annotations::
-
-            class Array(Generic[*Ts]):
-
-                def __init__(self, shape: Tuple[*Ts]):
-                    self._shape: Tuple[*Ts] = shape
-
-                def get_shape(self) -> Tuple[*Ts]:
-                    return self._shape
-
-            shape = (Height(480), Width(640))
-            x: Array[Height, Width] = Array(shape)
-            y = abs(x)  # Inferred type is Array[Height, Width]
-            z = x + x   #        ...    is Array[Height, Width]
-            x.get_shape()  #     ...    is tuple[Height, Width]
-
-        """
-
-        # Trick Generic __parameters__.
-        __class__ = typing.TypeVar
-
-        def __iter__(self):
-            yield self.__unpacked__
-
-        def __init__(self, name, *, default=NoDefault):
-            self.__name__ = name
-            _DefaultMixin.__init__(self, default)
-
-            # for pickling:
-            def_mod = _caller()
-            if def_mod != 'typing_extensions':
-                self.__module__ = def_mod
-
-            self.__unpacked__ = Unpack[self]
-
-        def __repr__(self):
-            return self.__name__
-
-        def __hash__(self):
-            return object.__hash__(self)
-
-        def __eq__(self, other):
-            return self is other
-
-        def __reduce__(self):
-            return self.__name__
-
-        def __init_subclass__(self, *args, **kwds):
-            if '_root' not in kwds:
-                raise TypeError("Cannot subclass special typing classes")
-
-
-if hasattr(typing, "reveal_type"):  # 3.11+
-    reveal_type = typing.reveal_type
-else:  # <=3.10
-    def reveal_type(obj: T, /) -> T:
-        """Reveal the inferred type of a variable.
-
-        When a static type checker encounters a call to ``reveal_type()``,
-        it will emit the inferred type of the argument::
-
-            x: int = 1
-            reveal_type(x)
-
-        Running a static type checker (e.g., ``mypy``) on this example
-        will produce output similar to 'Revealed type is "builtins.int"'.
-
-        At runtime, the function prints the runtime type of the
-        argument and returns it unchanged.
-
-        """
-        print(f"Runtime type is {type(obj).__name__!r}", file=sys.stderr)
-        return obj
-
-
-if hasattr(typing, "_ASSERT_NEVER_REPR_MAX_LENGTH"):  # 3.11+
-    _ASSERT_NEVER_REPR_MAX_LENGTH = typing._ASSERT_NEVER_REPR_MAX_LENGTH
-else:  # <=3.10
-    _ASSERT_NEVER_REPR_MAX_LENGTH = 100
-
-
-if hasattr(typing, "assert_never"):  # 3.11+
-    assert_never = typing.assert_never
-else:  # <=3.10
-    def assert_never(arg: Never, /) -> Never:
-        """Assert to the type checker that a line of code is unreachable.
-
-        Example::
-
-            def int_or_str(arg: int | str) -> None:
-                match arg:
-                    case int():
-                        print("It's an int")
-                    case str():
-                        print("It's a str")
-                    case _:
-                        assert_never(arg)
-
-        If a type checker finds that a call to assert_never() is
-        reachable, it will emit an error.
-
-        At runtime, this throws an exception when called.
-
-        """
-        value = repr(arg)
-        if len(value) > _ASSERT_NEVER_REPR_MAX_LENGTH:
-            value = value[:_ASSERT_NEVER_REPR_MAX_LENGTH] + '...'
-        raise AssertionError(f"Expected code to be unreachable, but got: {value}")
-
-
-if sys.version_info >= (3, 12):  # 3.12+
-    # dataclass_transform exists in 3.11 but lacks the frozen_default parameter
-    dataclass_transform = typing.dataclass_transform
-else:  # <=3.11
-    def dataclass_transform(
-        *,
-        eq_default: bool = True,
-        order_default: bool = False,
-        kw_only_default: bool = False,
-        frozen_default: bool = False,
-        field_specifiers: typing.Tuple[
-            typing.Union[typing.Type[typing.Any], typing.Callable[..., typing.Any]],
-            ...
-        ] = (),
-        **kwargs: typing.Any,
-    ) -> typing.Callable[[T], T]:
-        """Decorator that marks a function, class, or metaclass as providing
-        dataclass-like behavior.
-
-        Example:
-
-            from typing_extensions import dataclass_transform
-
-            _T = TypeVar("_T")
-
-            # Used on a decorator function
-            @dataclass_transform()
-            def create_model(cls: type[_T]) -> type[_T]:
-                ...
-                return cls
-
-            @create_model
-            class CustomerModel:
-                id: int
-                name: str
-
-            # Used on a base class
-            @dataclass_transform()
-            class ModelBase: ...
-
-            class CustomerModel(ModelBase):
-                id: int
-                name: str
-
-            # Used on a metaclass
-            @dataclass_transform()
-            class ModelMeta(type): ...
-
-            class ModelBase(metaclass=ModelMeta): ...
-
-            class CustomerModel(ModelBase):
-                id: int
-                name: str
-
-        Each of the ``CustomerModel`` classes defined in this example will now
-        behave similarly to a dataclass created with the ``@dataclasses.dataclass``
-        decorator. For example, the type checker will synthesize an ``__init__``
-        method.
-
-        The arguments to this decorator can be used to customize this behavior:
-        - ``eq_default`` indicates whether the ``eq`` parameter is assumed to be
-          True or False if it is omitted by the caller.
-        - ``order_default`` indicates whether the ``order`` parameter is
-          assumed to be True or False if it is omitted by the caller.
-        - ``kw_only_default`` indicates whether the ``kw_only`` parameter is
-          assumed to be True or False if it is omitted by the caller.
-        - ``frozen_default`` indicates whether the ``frozen`` parameter is
-          assumed to be True or False if it is omitted by the caller.
-        - ``field_specifiers`` specifies a static list of supported classes
-          or functions that describe fields, similar to ``dataclasses.field()``.
-
-        At runtime, this decorator records its arguments in the
-        ``__dataclass_transform__`` attribute on the decorated object.
-
-        See PEP 681 for details.
-
-        """
-        def decorator(cls_or_fn):
-            cls_or_fn.__dataclass_transform__ = {
-                "eq_default": eq_default,
-                "order_default": order_default,
-                "kw_only_default": kw_only_default,
-                "frozen_default": frozen_default,
-                "field_specifiers": field_specifiers,
-                "kwargs": kwargs,
-            }
-            return cls_or_fn
-        return decorator
-
-
-if hasattr(typing, "override"):  # 3.12+
-    override = typing.override
-else:  # <=3.11
-    _F = typing.TypeVar("_F", bound=typing.Callable[..., typing.Any])
-
-    def override(arg: _F, /) -> _F:
-        """Indicate that a method is intended to override a method in a base class.
-
-        Usage:
-
-            class Base:
-                def method(self) -> None:
-                    pass
-
-            class Child(Base):
-                @override
-                def method(self) -> None:
-                    super().method()
-
-        When this decorator is applied to a method, the type checker will
-        validate that it overrides a method with the same name on a base class.
-        This helps prevent bugs that may occur when a base class is changed
-        without an equivalent change to a child class.
-
-        There is no runtime checking of these properties. The decorator
-        sets the ``__override__`` attribute to ``True`` on the decorated object
-        to allow runtime introspection.
-
-        See PEP 698 for details.
-
-        """
-        try:
-            arg.__override__ = True
-        except (AttributeError, TypeError):
-            # Skip the attribute silently if it is not writable.
-            # AttributeError happens if the object has __slots__ or a
-            # read-only property, TypeError if it's a builtin class.
-            pass
-        return arg
-
-
-if hasattr(warnings, "deprecated"):
-    deprecated = warnings.deprecated
-else:
-    _T = typing.TypeVar("_T")
-
-    class deprecated:
-        """Indicate that a class, function or overload is deprecated.
-
-        When this decorator is applied to an object, the type checker
-        will generate a diagnostic on usage of the deprecated object.
-
-        Usage:
-
-            @deprecated("Use B instead")
-            class A:
-                pass
-
-            @deprecated("Use g instead")
-            def f():
-                pass
-
-            @overload
-            @deprecated("int support is deprecated")
-            def g(x: int) -> int: ...
-            @overload
-            def g(x: str) -> int: ...
-
-        The warning specified by *category* will be emitted at runtime
-        on use of deprecated objects. For functions, that happens on calls;
-        for classes, on instantiation and on creation of subclasses.
-        If the *category* is ``None``, no warning is emitted at runtime.
-        The *stacklevel* determines where the
-        warning is emitted. If it is ``1`` (the default), the warning
-        is emitted at the direct caller of the deprecated object; if it
-        is higher, it is emitted further up the stack.
-        Static type checker behavior is not affected by the *category*
-        and *stacklevel* arguments.
-
-        The deprecation message passed to the decorator is saved in the
-        ``__deprecated__`` attribute on the decorated object.
-        If applied to an overload, the decorator
-        must be after the ``@overload`` decorator for the attribute to
-        exist on the overload as returned by ``get_overloads()``.
-
-        See PEP 702 for details.
-
-        """
-        def __init__(
-            self,
-            message: str,
-            /,
-            *,
-            category: typing.Optional[typing.Type[Warning]] = DeprecationWarning,
-            stacklevel: int = 1,
-        ) -> None:
-            if not isinstance(message, str):
-                raise TypeError(
-                    "Expected an object of type str for 'message', not "
-                    f"{type(message).__name__!r}"
-                )
-            self.message = message
-            self.category = category
-            self.stacklevel = stacklevel
-
-        def __call__(self, arg: _T, /) -> _T:
-            # Make sure the inner functions created below don't
-            # retain a reference to self.
-            msg = self.message
-            category = self.category
-            stacklevel = self.stacklevel
-            if category is None:
-                arg.__deprecated__ = msg
-                return arg
-            elif isinstance(arg, type):
-                import functools
-                from types import MethodType
-
-                original_new = arg.__new__
-
-                @functools.wraps(original_new)
-                def __new__(cls, *args, **kwargs):
-                    if cls is arg:
-                        warnings.warn(msg, category=category, stacklevel=stacklevel + 1)
-                    if original_new is not object.__new__:
-                        return original_new(cls, *args, **kwargs)
-                    # Mirrors a similar check in object.__new__.
-                    elif cls.__init__ is object.__init__ and (args or kwargs):
-                        raise TypeError(f"{cls.__name__}() takes no arguments")
-                    else:
-                        return original_new(cls)
-
-                arg.__new__ = staticmethod(__new__)
-
-                original_init_subclass = arg.__init_subclass__
-                # We need slightly different behavior if __init_subclass__
-                # is a bound method (likely if it was implemented in Python)
-                if isinstance(original_init_subclass, MethodType):
-                    original_init_subclass = original_init_subclass.__func__
-
-                    @functools.wraps(original_init_subclass)
-                    def __init_subclass__(*args, **kwargs):
-                        warnings.warn(msg, category=category, stacklevel=stacklevel + 1)
-                        return original_init_subclass(*args, **kwargs)
-
-                    arg.__init_subclass__ = classmethod(__init_subclass__)
-                # Or otherwise, which likely means it's a builtin such as
-                # object's implementation of __init_subclass__.
-                else:
-                    @functools.wraps(original_init_subclass)
-                    def __init_subclass__(*args, **kwargs):
-                        warnings.warn(msg, category=category, stacklevel=stacklevel + 1)
-                        return original_init_subclass(*args, **kwargs)
-
-                    arg.__init_subclass__ = __init_subclass__
-
-                arg.__deprecated__ = __new__.__deprecated__ = msg
-                __init_subclass__.__deprecated__ = msg
-                return arg
-            elif callable(arg):
-                import functools
-
-                @functools.wraps(arg)
-                def wrapper(*args, **kwargs):
-                    warnings.warn(msg, category=category, stacklevel=stacklevel + 1)
-                    return arg(*args, **kwargs)
-
-                arg.__deprecated__ = wrapper.__deprecated__ = msg
-                return wrapper
-            else:
-                raise TypeError(
-                    "@deprecated decorator with non-None category must be applied to "
-                    f"a class or callable, not {arg!r}"
-                )
-
-
-# We have to do some monkey patching to deal with the dual nature of
-# Unpack/TypeVarTuple:
-# - We want Unpack to be a kind of TypeVar so it gets accepted in
-#   Generic[Unpack[Ts]]
-# - We want it to *not* be treated as a TypeVar for the purposes of
-#   counting generic parameters, so that when we subscript a generic,
-#   the runtime doesn't try to substitute the Unpack with the subscripted type.
-if not hasattr(typing, "TypeVarTuple"):
-    def _check_generic(cls, parameters, elen=_marker):
-        """Check correct count for parameters of a generic cls (internal helper).
-
-        This gives a nice error message in case of count mismatch.
-        """
-        if not elen:
-            raise TypeError(f"{cls} is not a generic class")
-        if elen is _marker:
-            if not hasattr(cls, "__parameters__") or not cls.__parameters__:
-                raise TypeError(f"{cls} is not a generic class")
-            elen = len(cls.__parameters__)
-        alen = len(parameters)
-        if alen != elen:
-            expect_val = elen
-            if hasattr(cls, "__parameters__"):
-                parameters = [p for p in cls.__parameters__ if not _is_unpack(p)]
-                num_tv_tuples = sum(isinstance(p, TypeVarTuple) for p in parameters)
-                if (num_tv_tuples > 0) and (alen >= elen - num_tv_tuples):
-                    return
-
-                # deal with TypeVarLike defaults
-                # required TypeVarLikes cannot appear after a defaulted one.
-                if alen < elen:
-                    # since we validate TypeVarLike default in _collect_type_vars
-                    # or _collect_parameters we can safely check parameters[alen]
-                    if (
-                        getattr(parameters[alen], '__default__', NoDefault)
-                        is not NoDefault
-                    ):
-                        return
-
-                    num_default_tv = sum(getattr(p, '__default__', NoDefault)
-                                         is not NoDefault for p in parameters)
-
-                    elen -= num_default_tv
-
-                    expect_val = f"at least {elen}"
-
-            things = "arguments" if sys.version_info >= (3, 10) else "parameters"
-            raise TypeError(f"Too {'many' if alen > elen else 'few'} {things}"
-                            f" for {cls}; actual {alen}, expected {expect_val}")
-else:
-    # Python 3.11+
-
-    def _check_generic(cls, parameters, elen):
-        """Check correct count for parameters of a generic cls (internal helper).
-
-        This gives a nice error message in case of count mismatch.
-        """
-        if not elen:
-            raise TypeError(f"{cls} is not a generic class")
-        alen = len(parameters)
-        if alen != elen:
-            expect_val = elen
-            if hasattr(cls, "__parameters__"):
-                parameters = [p for p in cls.__parameters__ if not _is_unpack(p)]
-
-                # deal with TypeVarLike defaults
-                # required TypeVarLikes cannot appear after a defaulted one.
-                if alen < elen:
-                    # since we validate TypeVarLike default in _collect_type_vars
-                    # or _collect_parameters we can safely check parameters[alen]
-                    if (
-                        getattr(parameters[alen], '__default__', NoDefault)
-                        is not NoDefault
-                    ):
-                        return
-
-                    num_default_tv = sum(getattr(p, '__default__', NoDefault)
-                                         is not NoDefault for p in parameters)
-
-                    elen -= num_default_tv
-
-                    expect_val = f"at least {elen}"
-
-            raise TypeError(f"Too {'many' if alen > elen else 'few'} arguments"
-                            f" for {cls}; actual {alen}, expected {expect_val}")
-
-if not _PEP_696_IMPLEMENTED:
-    typing._check_generic = _check_generic
-
-
-def _has_generic_or_protocol_as_origin() -> bool:
-    try:
-        frame = sys._getframe(2)
-    # - Catch AttributeError: not all Python implementations have sys._getframe()
-    # - Catch ValueError: maybe we're called from an unexpected module
-    #   and the call stack isn't deep enough
-    except (AttributeError, ValueError):
-        return False  # err on the side of leniency
-    else:
-        # If we somehow get invoked from outside typing.py,
-        # also err on the side of leniency
-        if frame.f_globals.get("__name__") != "typing":
-            return False
-        origin = frame.f_locals.get("origin")
-        # Cannot use "in" because origin may be an object with a buggy __eq__ that
-        # throws an error.
-        return origin is typing.Generic or origin is Protocol or origin is typing.Protocol
-
-
-_TYPEVARTUPLE_TYPES = {TypeVarTuple, getattr(typing, "TypeVarTuple", None)}
-
-
-def _is_unpacked_typevartuple(x) -> bool:
-    if get_origin(x) is not Unpack:
-        return False
-    args = get_args(x)
-    return (
-        bool(args)
-        and len(args) == 1
-        and type(args[0]) in _TYPEVARTUPLE_TYPES
-    )
-
-
-# Python 3.11+ _collect_type_vars was renamed to _collect_parameters
-if hasattr(typing, '_collect_type_vars'):
-    def _collect_type_vars(types, typevar_types=None):
-        """Collect all type variable contained in types in order of
-        first appearance (lexicographic order). For example::
-
-            _collect_type_vars((T, List[S, T])) == (T, S)
-        """
-        if typevar_types is None:
-            typevar_types = typing.TypeVar
-        tvars = []
-
-        # A required TypeVarLike cannot appear after a TypeVarLike with a default
-        # if it was a direct call to `Generic[]` or `Protocol[]`
-        enforce_default_ordering = _has_generic_or_protocol_as_origin()
-        default_encountered = False
-
-        # Also, a TypeVarLike with a default cannot appear after a TypeVarTuple
-        type_var_tuple_encountered = False
-
-        for t in types:
-            if _is_unpacked_typevartuple(t):
-                type_var_tuple_encountered = True
-            elif isinstance(t, typevar_types) and t not in tvars:
-                if enforce_default_ordering:
-                    has_default = getattr(t, '__default__', NoDefault) is not NoDefault
-                    if has_default:
-                        if type_var_tuple_encountered:
-                            raise TypeError('Type parameter with a default'
-                                            ' follows TypeVarTuple')
-                        default_encountered = True
-                    elif default_encountered:
-                        raise TypeError(f'Type parameter {t!r} without a default'
-                                        ' follows type parameter with a default')
-
-                tvars.append(t)
-            if _should_collect_from_parameters(t):
-                tvars.extend([t for t in t.__parameters__ if t not in tvars])
-        return tuple(tvars)
-
-    typing._collect_type_vars = _collect_type_vars
-else:
-    def _collect_parameters(args):
-        """Collect all type variables and parameter specifications in args
-        in order of first appearance (lexicographic order).
-
-        For example::
-
-            assert _collect_parameters((T, Callable[P, T])) == (T, P)
-        """
-        parameters = []
-
-        # A required TypeVarLike cannot appear after a TypeVarLike with default
-        # if it was a direct call to `Generic[]` or `Protocol[]`
-        enforce_default_ordering = _has_generic_or_protocol_as_origin()
-        default_encountered = False
-
-        # Also, a TypeVarLike with a default cannot appear after a TypeVarTuple
-        type_var_tuple_encountered = False
-
-        for t in args:
-            if isinstance(t, type):
-                # We don't want __parameters__ descriptor of a bare Python class.
-                pass
-            elif isinstance(t, tuple):
-                # `t` might be a tuple, when `ParamSpec` is substituted with
-                # `[T, int]`, or `[int, *Ts]`, etc.
-                for x in t:
-                    for collected in _collect_parameters([x]):
-                        if collected not in parameters:
-                            parameters.append(collected)
-            elif hasattr(t, '__typing_subst__'):
-                if t not in parameters:
-                    if enforce_default_ordering:
-                        has_default = (
-                            getattr(t, '__default__', NoDefault) is not NoDefault
-                        )
-
-                        if type_var_tuple_encountered and has_default:
-                            raise TypeError('Type parameter with a default'
-                                            ' follows TypeVarTuple')
-
-                        if has_default:
-                            default_encountered = True
-                        elif default_encountered:
-                            raise TypeError(f'Type parameter {t!r} without a default'
-                                            ' follows type parameter with a default')
-
-                    parameters.append(t)
-            else:
-                if _is_unpacked_typevartuple(t):
-                    type_var_tuple_encountered = True
-                for x in getattr(t, '__parameters__', ()):
-                    if x not in parameters:
-                        parameters.append(x)
-
-        return tuple(parameters)
-
-    if not _PEP_696_IMPLEMENTED:
-        typing._collect_parameters = _collect_parameters
-
-# Backport typing.NamedTuple as it exists in Python 3.13.
-# In 3.11, the ability to define generic `NamedTuple`s was supported.
-# This was explicitly disallowed in 3.9-3.10, and only half-worked in <=3.8.
-# On 3.12, we added __orig_bases__ to call-based NamedTuples
-# On 3.13, we deprecated kwargs-based NamedTuples
-if sys.version_info >= (3, 13):
-    NamedTuple = typing.NamedTuple
-else:
-    def _make_nmtuple(name, types, module, defaults=()):
-        fields = [n for n, t in types]
-        annotations = {n: typing._type_check(t, f"field {n} annotation must be a type")
-                       for n, t in types}
-        nm_tpl = collections.namedtuple(name, fields,
-                                        defaults=defaults, module=module)
-        nm_tpl.__annotations__ = nm_tpl.__new__.__annotations__ = annotations
-        # The `_field_types` attribute was removed in 3.9;
-        # in earlier versions, it is the same as the `__annotations__` attribute
-        if sys.version_info < (3, 9):
-            nm_tpl._field_types = annotations
-        return nm_tpl
-
-    _prohibited_namedtuple_fields = typing._prohibited
-    _special_namedtuple_fields = frozenset({'__module__', '__name__', '__annotations__'})
-
-    class _NamedTupleMeta(type):
-        def __new__(cls, typename, bases, ns):
-            assert _NamedTuple in bases
-            for base in bases:
-                if base is not _NamedTuple and base is not typing.Generic:
-                    raise TypeError(
-                        'can only inherit from a NamedTuple type and Generic')
-            bases = tuple(tuple if base is _NamedTuple else base for base in bases)
-            if "__annotations__" in ns:
-                types = ns["__annotations__"]
-            elif "__annotate__" in ns:
-                # TODO: Use inspect.VALUE here, and make the annotations lazily evaluated
-                types = ns["__annotate__"](1)
-            else:
-                types = {}
-            default_names = []
-            for field_name in types:
-                if field_name in ns:
-                    default_names.append(field_name)
-                elif default_names:
-                    raise TypeError(f"Non-default namedtuple field {field_name} "
-                                    f"cannot follow default field"
-                                    f"{'s' if len(default_names) > 1 else ''} "
-                                    f"{', '.join(default_names)}")
-            nm_tpl = _make_nmtuple(
-                typename, types.items(),
-                defaults=[ns[n] for n in default_names],
-                module=ns['__module__']
-            )
-            nm_tpl.__bases__ = bases
-            if typing.Generic in bases:
-                if hasattr(typing, '_generic_class_getitem'):  # 3.12+
-                    nm_tpl.__class_getitem__ = classmethod(typing._generic_class_getitem)
-                else:
-                    class_getitem = typing.Generic.__class_getitem__.__func__
-                    nm_tpl.__class_getitem__ = classmethod(class_getitem)
-            # update from user namespace without overriding special namedtuple attributes
-            for key, val in ns.items():
-                if key in _prohibited_namedtuple_fields:
-                    raise AttributeError("Cannot overwrite NamedTuple attribute " + key)
-                elif key not in _special_namedtuple_fields:
-                    if key not in nm_tpl._fields:
-                        setattr(nm_tpl, key, ns[key])
-                    try:
-                        set_name = type(val).__set_name__
-                    except AttributeError:
-                        pass
-                    else:
-                        try:
-                            set_name(val, nm_tpl, key)
-                        except BaseException as e:
-                            msg = (
-                                f"Error calling __set_name__ on {type(val).__name__!r} "
-                                f"instance {key!r} in {typename!r}"
-                            )
-                            # BaseException.add_note() existed on py311,
-                            # but the __set_name__ machinery didn't start
-                            # using add_note() until py312.
-                            # Making sure exceptions are raised in the same way
-                            # as in "normal" classes seems most important here.
-                            if sys.version_info >= (3, 12):
-                                e.add_note(msg)
-                                raise
-                            else:
-                                raise RuntimeError(msg) from e
-
-            if typing.Generic in bases:
-                nm_tpl.__init_subclass__()
-            return nm_tpl
-
-    _NamedTuple = type.__new__(_NamedTupleMeta, 'NamedTuple', (), {})
-
-    def _namedtuple_mro_entries(bases):
-        assert NamedTuple in bases
-        return (_NamedTuple,)
-
-    @_ensure_subclassable(_namedtuple_mro_entries)
-    def NamedTuple(typename, fields=_marker, /, **kwargs):
-        """Typed version of namedtuple.
-
-        Usage::
-
-            class Employee(NamedTuple):
-                name: str
-                id: int
-
-        This is equivalent to::
-
-            Employee = collections.namedtuple('Employee', ['name', 'id'])
-
-        The resulting class has an extra __annotations__ attribute, giving a
-        dict that maps field names to types.  (The field names are also in
-        the _fields attribute, which is part of the namedtuple API.)
-        An alternative equivalent functional syntax is also accepted::
-
-            Employee = NamedTuple('Employee', [('name', str), ('id', int)])
-        """
-        if fields is _marker:
-            if kwargs:
-                deprecated_thing = "Creating NamedTuple classes using keyword arguments"
-                deprecation_msg = (
-                    "{name} is deprecated and will be disallowed in Python {remove}. "
-                    "Use the class-based or functional syntax instead."
-                )
-            else:
-                deprecated_thing = "Failing to pass a value for the 'fields' parameter"
-                example = f"`{typename} = NamedTuple({typename!r}, [])`"
-                deprecation_msg = (
-                    "{name} is deprecated and will be disallowed in Python {remove}. "
-                    "To create a NamedTuple class with 0 fields "
-                    "using the functional syntax, "
-                    "pass an empty list, e.g. "
-                ) + example + "."
-        elif fields is None:
-            if kwargs:
-                raise TypeError(
-                    "Cannot pass `None` as the 'fields' parameter "
-                    "and also specify fields using keyword arguments"
-                )
-            else:
-                deprecated_thing = "Passing `None` as the 'fields' parameter"
-                example = f"`{typename} = NamedTuple({typename!r}, [])`"
-                deprecation_msg = (
-                    "{name} is deprecated and will be disallowed in Python {remove}. "
-                    "To create a NamedTuple class with 0 fields "
-                    "using the functional syntax, "
-                    "pass an empty list, e.g. "
-                ) + example + "."
-        elif kwargs:
-            raise TypeError("Either list of fields or keywords"
-                            " can be provided to NamedTuple, not both")
-        if fields is _marker or fields is None:
-            warnings.warn(
-                deprecation_msg.format(name=deprecated_thing, remove="3.15"),
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            fields = kwargs.items()
-        nt = _make_nmtuple(typename, fields, module=_caller())
-        nt.__orig_bases__ = (NamedTuple,)
-        return nt
-
-
-if hasattr(collections.abc, "Buffer"):
-    Buffer = collections.abc.Buffer
-else:
-    class Buffer(abc.ABC):  # noqa: B024
-        """Base class for classes that implement the buffer protocol.
-
-        The buffer protocol allows Python objects to expose a low-level
-        memory buffer interface. Before Python 3.12, it is not possible
-        to implement the buffer protocol in pure Python code, or even
-        to check whether a class implements the buffer protocol. In
-        Python 3.12 and higher, the ``__buffer__`` method allows access
-        to the buffer protocol from Python code, and the
-        ``collections.abc.Buffer`` ABC allows checking whether a class
-        implements the buffer protocol.
-
-        To indicate support for the buffer protocol in earlier versions,
-        inherit from this ABC, either in a stub file or at runtime,
-        or use ABC registration. This ABC provides no methods, because
-        there is no Python-accessible methods shared by pre-3.12 buffer
-        classes. It is useful primarily for static checks.
-
-        """
-
-    # As a courtesy, register the most common stdlib buffer classes.
-    Buffer.register(memoryview)
-    Buffer.register(bytearray)
-    Buffer.register(bytes)
-
-
-# Backport of types.get_original_bases, available on 3.12+ in CPython
-if hasattr(_types, "get_original_bases"):
-    get_original_bases = _types.get_original_bases
-else:
-    def get_original_bases(cls, /):
-        """Return the class's "original" bases prior to modification by `__mro_entries__`.
-
-        Examples::
-
-            from typing import TypeVar, Generic
-            from typing_extensions import NamedTuple, TypedDict
-
-            T = TypeVar("T")
-            class Foo(Generic[T]): ...
-            class Bar(Foo[int], float): ...
-            class Baz(list[str]): ...
-            Eggs = NamedTuple("Eggs", [("a", int), ("b", str)])
-            Spam = TypedDict("Spam", {"a": int, "b": str})
-
-            assert get_original_bases(Bar) == (Foo[int], float)
-            assert get_original_bases(Baz) == (list[str],)
-            assert get_original_bases(Eggs) == (NamedTuple,)
-            assert get_original_bases(Spam) == (TypedDict,)
-            assert get_original_bases(int) == (object,)
-        """
-        try:
-            return cls.__dict__.get("__orig_bases__", cls.__bases__)
-        except AttributeError:
-            raise TypeError(
-                f'Expected an instance of type, not {type(cls).__name__!r}'
-            ) from None
-
-
-# NewType is a class on Python 3.10+, making it pickleable
-# The error message for subclassing instances of NewType was improved on 3.11+
-if sys.version_info >= (3, 11):
-    NewType = typing.NewType
-else:
-    class NewType:
-        """NewType creates simple unique types with almost zero
-        runtime overhead. NewType(name, tp) is considered a subtype of tp
-        by static type checkers. At runtime, NewType(name, tp) returns
-        a dummy callable that simply returns its argument. Usage::
-            UserId = NewType('UserId', int)
-            def name_by_id(user_id: UserId) -> str:
-                ...
-            UserId('user')          # Fails type check
-            name_by_id(42)          # Fails type check
-            name_by_id(UserId(42))  # OK
-            num = UserId(5) + 1     # type: int
-        """
-
-        def __call__(self, obj, /):
-            return obj
-
-        def __init__(self, name, tp):
-            self.__qualname__ = name
-            if '.' in name:
-                name = name.rpartition('.')[-1]
-            self.__name__ = name
-            self.__supertype__ = tp
-            def_mod = _caller()
-            if def_mod != 'typing_extensions':
-                self.__module__ = def_mod
-
-        def __mro_entries__(self, bases):
-            # We defined __mro_entries__ to get a better error message
-            # if a user attempts to subclass a NewType instance. bpo-46170
-            supercls_name = self.__name__
-
-            class Dummy:
-                def __init_subclass__(cls):
-                    subcls_name = cls.__name__
-                    raise TypeError(
-                        f"Cannot subclass an instance of NewType. "
-                        f"Perhaps you were looking for: "
-                        f"`{subcls_name} = NewType({subcls_name!r}, {supercls_name})`"
-                    )
-
-            return (Dummy,)
-
-        def __repr__(self):
-            return f'{self.__module__}.{self.__qualname__}'
-
-        def __reduce__(self):
-            return self.__qualname__
-
-        if sys.version_info >= (3, 10):
-            # PEP 604 methods
-            # It doesn't make sense to have these methods on Python <3.10
-
-            def __or__(self, other):
-                return typing.Union[self, other]
-
-            def __ror__(self, other):
-                return typing.Union[other, self]
-
-
-if hasattr(typing, "TypeAliasType"):
-    TypeAliasType = typing.TypeAliasType
-else:
-    def _is_unionable(obj):
-        """Corresponds to is_unionable() in unionobject.c in CPython."""
-        return obj is None or isinstance(obj, (
-            type,
-            _types.GenericAlias,
-            _types.UnionType,
-            TypeAliasType,
-        ))
-
-    class TypeAliasType:
-        """Create named, parameterized type aliases.
-
-        This provides a backport of the new `type` statement in Python 3.12:
-
-            type ListOrSet[T] = list[T] | set[T]
-
-        is equivalent to:
-
-            T = TypeVar("T")
-            ListOrSet = TypeAliasType("ListOrSet", list[T] | set[T], type_params=(T,))
-
-        The name ListOrSet can then be used as an alias for the type it refers to.
-
-        The type_params argument should contain all the type parameters used
-        in the value of the type alias. If the alias is not generic, this
-        argument is omitted.
-
-        Static type checkers should only support type aliases declared using
-        TypeAliasType that follow these rules:
-
-        - The first argument (the name) must be a string literal.
-        - The TypeAliasType instance must be immediately assigned to a variable
-          of the same name. (For example, 'X = TypeAliasType("Y", int)' is invalid,
-          as is 'X, Y = TypeAliasType("X", int), TypeAliasType("Y", int)').
-
-        """
-
-        def __init__(self, name: str, value, *, type_params=()):
-            if not isinstance(name, str):
-                raise TypeError("TypeAliasType name must be a string")
-            self.__value__ = value
-            self.__type_params__ = type_params
-
-            parameters = []
-            for type_param in type_params:
-                if isinstance(type_param, TypeVarTuple):
-                    parameters.extend(type_param)
-                else:
-                    parameters.append(type_param)
-            self.__parameters__ = tuple(parameters)
-            def_mod = _caller()
-            if def_mod != 'typing_extensions':
-                self.__module__ = def_mod
-            # Setting this attribute closes the TypeAliasType from further modification
-            self.__name__ = name
-
-        def __setattr__(self, name: str, value: object, /) -> None:
-            if hasattr(self, "__name__"):
-                self._raise_attribute_error(name)
-            super().__setattr__(name, value)
-
-        def __delattr__(self, name: str, /) -> Never:
-            self._raise_attribute_error(name)
-
-        def _raise_attribute_error(self, name: str) -> Never:
-            # Match the Python 3.12 error messages exactly
-            if name == "__name__":
-                raise AttributeError("readonly attribute")
-            elif name in {"__value__", "__type_params__", "__parameters__", "__module__"}:
-                raise AttributeError(
-                    f"attribute '{name}' of 'typing.TypeAliasType' objects "
-                    "is not writable"
-                )
-            else:
-                raise AttributeError(
-                    f"'typing.TypeAliasType' object has no attribute '{name}'"
-                )
-
-        def __repr__(self) -> str:
-            return self.__name__
-
-        def __getitem__(self, parameters):
-            if not isinstance(parameters, tuple):
-                parameters = (parameters,)
-            parameters = [
-                typing._type_check(
-                    item, f'Subscripting {self.__name__} requires a type.'
-                )
-                for item in parameters
-            ]
-            return typing._GenericAlias(self, tuple(parameters))
-
-        def __reduce__(self):
-            return self.__name__
-
-        def __init_subclass__(cls, *args, **kwargs):
-            raise TypeError(
-                "type 'typing_extensions.TypeAliasType' is not an acceptable base type"
-            )
-
-        # The presence of this method convinces typing._type_check
-        # that TypeAliasTypes are types.
-        def __call__(self):
-            raise TypeError("Type alias is not callable")
-
-        if sys.version_info >= (3, 10):
-            def __or__(self, right):
-                # For forward compatibility with 3.12, reject Unions
-                # that are not accepted by the built-in Union.
-                if not _is_unionable(right):
-                    return NotImplemented
-                return typing.Union[self, right]
-
-            def __ror__(self, left):
-                if not _is_unionable(left):
-                    return NotImplemented
-                return typing.Union[left, self]
-
-
-if hasattr(typing, "is_protocol"):
-    is_protocol = typing.is_protocol
-    get_protocol_members = typing.get_protocol_members
-else:
-    def is_protocol(tp: type, /) -> bool:
-        """Return True if the given type is a Protocol.
-
-        Example::
-
-            >>> from typing_extensions import Protocol, is_protocol
-            >>> class P(Protocol):
-            ...     def a(self) -> str: ...
-            ...     b: int
-            >>> is_protocol(P)
-            True
-            >>> is_protocol(int)
-            False
-        """
-        return (
-            isinstance(tp, type)
-            and getattr(tp, '_is_protocol', False)
-            and tp is not Protocol
-            and tp is not typing.Protocol
-        )
-
-    def get_protocol_members(tp: type, /) -> typing.FrozenSet[str]:
-        """Return the set of members defined in a Protocol.
-
-        Example::
-
-            >>> from typing_extensions import Protocol, get_protocol_members
-            >>> class P(Protocol):
-            ...     def a(self) -> str: ...
-            ...     b: int
-            >>> get_protocol_members(P)
-            frozenset({'a', 'b'})
-
-        Raise a TypeError for arguments that are not Protocols.
-        """
-        if not is_protocol(tp):
-            raise TypeError(f'{tp!r} is not a Protocol')
-        if hasattr(tp, '__protocol_attrs__'):
-            return frozenset(tp.__protocol_attrs__)
-        return frozenset(_get_protocol_attrs(tp))
-
-
-if hasattr(typing, "Doc"):
-    Doc = typing.Doc
-else:
-    class Doc:
-        """Define the documentation of a type annotation using ``Annotated``, to be
-         used in class attributes, function and method parameters, return values,
-         and variables.
-
-        The value should be a positional-only string literal to allow static tools
-        like editors and documentation generators to use it.
-
-        This complements docstrings.
-
-        The string value passed is available in the attribute ``documentation``.
-
-        Example::
-
-            >>> from typing_extensions import Annotated, Doc
-            >>> def hi(to: Annotated[str, Doc("Who to say hi to")]) -> None: ...
-        """
-        def __init__(self, documentation: str, /) -> None:
-            self.documentation = documentation
-
-        def __repr__(self) -> str:
-            return f"Doc({self.documentation!r})"
-
-        def __hash__(self) -> int:
-            return hash(self.documentation)
-
-        def __eq__(self, other: object) -> bool:
-            if not isinstance(other, Doc):
-                return NotImplemented
-            return self.documentation == other.documentation
-
-
-_CapsuleType = getattr(_types, "CapsuleType", None)
-
-if _CapsuleType is None:
-    try:
-        import _socket
-    except ImportError:
-        pass
-    else:
-        _CAPI = getattr(_socket, "CAPI", None)
-        if _CAPI is not None:
-            _CapsuleType = type(_CAPI)
-
-if _CapsuleType is not None:
-    CapsuleType = _CapsuleType
-    __all__.append("CapsuleType")
-
-
-# Aliases for items that have always been in typing.
-# Explicitly assign these (rather than using `from typing import *` at the top),
-# so that we get a CI error if one of these is deleted from typing.py
-# in a future version of Python
-AbstractSet = typing.AbstractSet
-AnyStr = typing.AnyStr
-BinaryIO = typing.BinaryIO
-Callable = typing.Callable
-Collection = typing.Collection
-Container = typing.Container
-Dict = typing.Dict
-ForwardRef = typing.ForwardRef
-FrozenSet = typing.FrozenSet
-Generic = typing.Generic
-Hashable = typing.Hashable
-IO = typing.IO
-ItemsView = typing.ItemsView
-Iterable = typing.Iterable
-Iterator = typing.Iterator
-KeysView = typing.KeysView
-List = typing.List
-Mapping = typing.Mapping
-MappingView = typing.MappingView
-Match = typing.Match
-MutableMapping = typing.MutableMapping
-MutableSequence = typing.MutableSequence
-MutableSet = typing.MutableSet
-Optional = typing.Optional
-Pattern = typing.Pattern
-Reversible = typing.Reversible
-Sequence = typing.Sequence
-Set = typing.Set
-Sized = typing.Sized
-TextIO = typing.TextIO
-Tuple = typing.Tuple
-Union = typing.Union
-ValuesView = typing.ValuesView
-cast = typing.cast
-no_type_check = typing.no_type_check
-no_type_check_decorator = typing.no_type_check_decorator
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/LICENSE.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/LICENSE.txt
deleted file mode 100644
index a31470f..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/LICENSE.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2012 Daniel Holth  and contributors
-
-Permission is hereby granted, free of charge, to any person obtaining a
-copy of this software and associated documentation files (the "Software"),
-to deal in the Software without restriction, including without limitation
-the rights to use, copy, modify, merge, publish, distribute, sublicense,
-and/or sell copies of the Software, and to permit persons to whom the
-Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
-THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
-OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
-ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-OTHER DEALINGS IN THE SOFTWARE.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/METADATA
deleted file mode 100644
index f645dcb..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/METADATA
+++ /dev/null
@@ -1,66 +0,0 @@
-Metadata-Version: 2.3
-Name: wheel
-Version: 0.45.1
-Summary: A built-package format for Python
-Keywords: wheel,packaging
-Author-email: Daniel Holth 
-Maintainer-email: Alex Grönholm 
-Requires-Python: >=3.8
-Description-Content-Type: text/x-rst
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: System :: Archiving :: Packaging
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: pytest >= 6.0.0 ; extra == "test"
-Requires-Dist: setuptools >= 65 ; extra == "test"
-Project-URL: Changelog, https://wheel.readthedocs.io/en/stable/news.html
-Project-URL: Documentation, https://wheel.readthedocs.io/
-Project-URL: Issue Tracker, https://github.com/pypa/wheel/issues
-Project-URL: Source, https://github.com/pypa/wheel
-Provides-Extra: test
-
-wheel
-=====
-
-This is a command line tool for manipulating Python wheel files, as defined in
-`PEP 427`_. It contains the following functionality:
-
-* Convert ``.egg`` archives into ``.whl``
-* Unpack wheel archives
-* Repack wheel archives
-* Add or remove tags in existing wheel archives
-
-.. _PEP 427: https://www.python.org/dev/peps/pep-0427/
-
-Historical note
----------------
-
-This project used to contain the implementation of the setuptools_ ``bdist_wheel``
-command, but as of setuptools v70.1, it no longer needs ``wheel`` installed for that to
-work. Thus, you should install this **only** if you intend to use the ``wheel`` command
-line tool!
-
-.. _setuptools: https://pypi.org/project/setuptools/
-
-Documentation
--------------
-
-The documentation_ can be found on Read The Docs.
-
-.. _documentation: https://wheel.readthedocs.io/
-
-Code of Conduct
----------------
-
-Everyone interacting in the wheel project's codebases, issue trackers, chat
-rooms, and mailing lists is expected to follow the `PSF Code of Conduct`_.
-
-.. _PSF Code of Conduct: https://github.com/pypa/.github/blob/main/CODE_OF_CONDUCT.md
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/RECORD
deleted file mode 100644
index c1535b6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/RECORD
+++ /dev/null
@@ -1,68 +0,0 @@
-../../bin/wheel,sha256=pBhV19bQIgjS-r541fG3kLU6QtcyKaKdQ2RE9YIzeiU,249
-wheel-0.45.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-wheel-0.45.1.dist-info/LICENSE.txt,sha256=MMI2GGeRCPPo6h0qZYx8pBe9_IkcmO8aifpP8MmChlQ,1107
-wheel-0.45.1.dist-info/METADATA,sha256=mKz84H7m7jsxJyzeIcTVORiTb0NPMV39KvOIYhGgmjA,2313
-wheel-0.45.1.dist-info/RECORD,,
-wheel-0.45.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wheel-0.45.1.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
-wheel-0.45.1.dist-info/entry_points.txt,sha256=rTY1BbkPHhkGMm4Q3F0pIzJBzW2kMxoG1oriffvGdA0,104
-wheel/__init__.py,sha256=mrxMnvdXACur_LWegbUfh5g5ysWZrd63UJn890wvGNk,59
-wheel/__main__.py,sha256=NkMUnuTCGcOkgY0IBLgBCVC_BGGcWORx2K8jYGS12UE,455
-wheel/__pycache__/__init__.cpython-311.pyc,,
-wheel/__pycache__/__main__.cpython-311.pyc,,
-wheel/__pycache__/_bdist_wheel.cpython-311.pyc,,
-wheel/__pycache__/_setuptools_logging.cpython-311.pyc,,
-wheel/__pycache__/bdist_wheel.cpython-311.pyc,,
-wheel/__pycache__/macosx_libfile.cpython-311.pyc,,
-wheel/__pycache__/metadata.cpython-311.pyc,,
-wheel/__pycache__/util.cpython-311.pyc,,
-wheel/__pycache__/wheelfile.cpython-311.pyc,,
-wheel/_bdist_wheel.py,sha256=UghCQjSH_pVfcZh6oRjzSw_TQhcf3anSx1OkiLSL82M,21694
-wheel/_setuptools_logging.py,sha256=-5KC-lne0ilOUWIDfOkqapUWGMFZhuKYDIavIZiB5kM,781
-wheel/bdist_wheel.py,sha256=tpf9WufiSO1RuEMg5oPhIfSG8DMziCZ_4muCKF69Cqo,1107
-wheel/cli/__init__.py,sha256=Npq6_jKi03dhIcRnmbuFhwviVJxwO0tYEnEhWMv9cJo,4402
-wheel/cli/__pycache__/__init__.cpython-311.pyc,,
-wheel/cli/__pycache__/convert.cpython-311.pyc,,
-wheel/cli/__pycache__/pack.cpython-311.pyc,,
-wheel/cli/__pycache__/tags.cpython-311.pyc,,
-wheel/cli/__pycache__/unpack.cpython-311.pyc,,
-wheel/cli/convert.py,sha256=Bi0ntEXb9nTllCxWeTRQ4j-nPs3szWSEKipG_GgnMkQ,12634
-wheel/cli/pack.py,sha256=CAFcHdBVulvsHYJlndKVO7KMI9JqBTZz5ii0PKxxCOs,3103
-wheel/cli/tags.py,sha256=lHw-LaWrkS5Jy_qWcw-6pSjeNM6yAjDnqKI3E5JTTCU,4760
-wheel/cli/unpack.py,sha256=Y_J7ynxPSoFFTT7H0fMgbBlVErwyDGcObgme5MBuz58,1021
-wheel/macosx_libfile.py,sha256=k1x7CE3LPtOVGqj6NXQ1nTGYVPaeRrhVzUG_KPq3zDs,16572
-wheel/metadata.py,sha256=JC4p7jlQZu2bUTAQ2fevkqLjg_X6gnNyRhLn6OUO1tc,6171
-wheel/util.py,sha256=aL7aibHwYUgfc8WlolL5tXdkV4DatbJxZHb1kwHFJAU,423
-wheel/vendored/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wheel/vendored/__pycache__/__init__.cpython-311.pyc,,
-wheel/vendored/packaging/LICENSE,sha256=ytHvW9NA1z4HS6YU0m996spceUDD2MNIUuZcSQlobEg,197
-wheel/vendored/packaging/LICENSE.APACHE,sha256=DVQuDIgE45qn836wDaWnYhSdxoLXgpRRKH4RuTjpRZQ,10174
-wheel/vendored/packaging/LICENSE.BSD,sha256=tw5-m3QvHMb5SLNMFqo5_-zpQZY2S8iP8NIYDwAo-sU,1344
-wheel/vendored/packaging/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wheel/vendored/packaging/__pycache__/__init__.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/_elffile.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/_manylinux.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/_musllinux.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/_parser.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/_structures.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/_tokenizer.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/markers.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/requirements.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/specifiers.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/tags.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/utils.cpython-311.pyc,,
-wheel/vendored/packaging/__pycache__/version.cpython-311.pyc,,
-wheel/vendored/packaging/_elffile.py,sha256=hbmK8OD6Z7fY6hwinHEUcD1by7czkGiNYu7ShnFEk2k,3266
-wheel/vendored/packaging/_manylinux.py,sha256=P7sdR5_7XBY09LVYYPhHmydMJIIwPXWsh4olk74Uuj4,9588
-wheel/vendored/packaging/_musllinux.py,sha256=z1s8To2hQ0vpn_d-O2i5qxGwEK8WmGlLt3d_26V7NeY,2674
-wheel/vendored/packaging/_parser.py,sha256=4tT4emSl2qTaU7VTQE1Xa9o1jMPCsBezsYBxyNMUN-s,10347
-wheel/vendored/packaging/_structures.py,sha256=q3eVNmbWJGG_S0Dit_S3Ao8qQqz_5PYTXFAKBZe5yr4,1431
-wheel/vendored/packaging/_tokenizer.py,sha256=alCtbwXhOFAmFGZ6BQ-wCTSFoRAJ2z-ysIf7__MTJ_k,5292
-wheel/vendored/packaging/markers.py,sha256=_TSPI1BhJYO7Bp9AzTmHQxIqHEVXaTjmDh9G-w8qzPA,8232
-wheel/vendored/packaging/requirements.py,sha256=dgoBeVprPu2YE6Q8nGfwOPTjATHbRa_ZGLyXhFEln6Q,2933
-wheel/vendored/packaging/specifiers.py,sha256=IWSt0SrLSP72heWhAC8UL0eGvas7XIQHjqiViVfmPKE,39778
-wheel/vendored/packaging/tags.py,sha256=fedHXiOHkBxNZTXotXv8uXPmMFU9ae-TKBujgYHigcA,18950
-wheel/vendored/packaging/utils.py,sha256=XgdmP3yx9-wQEFjO7OvMj9RjEf5JlR5HFFR69v7SQ9E,5268
-wheel/vendored/packaging/version.py,sha256=PFJaYZDxBgyxkfYhH3SQw4qfE9ICCWrTmitvq14y3bs,16234
-wheel/vendored/vendor.txt,sha256=Z2ENjB1i5prfez8CdM1Sdr3c6Zxv2rRRolMpLmBncAE,16
-wheel/wheelfile.py,sha256=USCttNlJwafxt51YYFFKG7jnxz8dfhbyqAZL6jMTA9s,8411
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/REQUESTED
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/WHEEL
deleted file mode 100644
index e3c6fee..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/WHEEL
+++ /dev/null
@@ -1,4 +0,0 @@
-Wheel-Version: 1.0
-Generator: flit 3.10.1
-Root-Is-Purelib: true
-Tag: py3-none-any
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/entry_points.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/entry_points.txt
deleted file mode 100644
index 06c9f69..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel-0.45.1.dist-info/entry_points.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-[console_scripts]
-wheel=wheel.cli:main
-
-[distutils.commands]
-bdist_wheel=wheel.bdist_wheel:bdist_wheel
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__init__.py
deleted file mode 100644
index 3ab8f72..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__init__.py
+++ /dev/null
@@ -1,3 +0,0 @@
-from __future__ import annotations
-
-__version__ = "0.45.1"
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__main__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__main__.py
deleted file mode 100644
index 0be7453..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__main__.py
+++ /dev/null
@@ -1,23 +0,0 @@
-"""
-Wheel command line tool (enable python -m wheel syntax)
-"""
-
-from __future__ import annotations
-
-import sys
-
-
-def main():  # needed for console script
-    if __package__ == "":
-        # To be able to run 'python wheel-0.9.whl/wheel':
-        import os.path
-
-        path = os.path.dirname(os.path.dirname(__file__))
-        sys.path[0:0] = [path]
-    import wheel.cli
-
-    sys.exit(wheel.cli.main())
-
-
-if __name__ == "__main__":
-    sys.exit(main())
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 7ea6b8b..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/__main__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/__main__.cpython-312.pyc
deleted file mode 100644
index 99460fb..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/__main__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/_bdist_wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/_bdist_wheel.cpython-312.pyc
deleted file mode 100644
index c38e4db..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/_bdist_wheel.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/_setuptools_logging.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/_setuptools_logging.cpython-312.pyc
deleted file mode 100644
index 0e6f4c7..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/_setuptools_logging.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/bdist_wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/bdist_wheel.cpython-312.pyc
deleted file mode 100644
index 25047c0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/bdist_wheel.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/macosx_libfile.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/macosx_libfile.cpython-312.pyc
deleted file mode 100644
index 8ef9f66..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/macosx_libfile.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/metadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/metadata.cpython-312.pyc
deleted file mode 100644
index acaa5c6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/metadata.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/util.cpython-312.pyc
deleted file mode 100644
index f2169b4..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/util.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/wheelfile.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/wheelfile.cpython-312.pyc
deleted file mode 100644
index 1dee064..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/__pycache__/wheelfile.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/_bdist_wheel.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/_bdist_wheel.py
deleted file mode 100644
index 88973eb..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/_bdist_wheel.py
+++ /dev/null
@@ -1,613 +0,0 @@
-"""
-Create a wheel (.whl) distribution.
-
-A wheel is a built archive format.
-"""
-
-from __future__ import annotations
-
-import os
-import re
-import shutil
-import stat
-import struct
-import sys
-import sysconfig
-import warnings
-from email.generator import BytesGenerator, Generator
-from email.policy import EmailPolicy
-from glob import iglob
-from shutil import rmtree
-from typing import TYPE_CHECKING, Callable, Iterable, Literal, Sequence, cast
-from zipfile import ZIP_DEFLATED, ZIP_STORED
-
-import setuptools
-from setuptools import Command
-
-from . import __version__ as wheel_version
-from .metadata import pkginfo_to_metadata
-from .util import log
-from .vendored.packaging import tags
-from .vendored.packaging import version as _packaging_version
-from .wheelfile import WheelFile
-
-if TYPE_CHECKING:
-    import types
-
-# ensure Python logging is configured
-try:
-    __import__("setuptools.logging")
-except ImportError:
-    # setuptools < ??
-    from . import _setuptools_logging
-
-    _setuptools_logging.configure()
-
-
-def safe_name(name: str) -> str:
-    """Convert an arbitrary string to a standard distribution name
-    Any runs of non-alphanumeric/. characters are replaced with a single '-'.
-    """
-    return re.sub("[^A-Za-z0-9.]+", "-", name)
-
-
-def safe_version(version: str) -> str:
-    """
-    Convert an arbitrary string to a standard version string
-    """
-    try:
-        # normalize the version
-        return str(_packaging_version.Version(version))
-    except _packaging_version.InvalidVersion:
-        version = version.replace(" ", ".")
-        return re.sub("[^A-Za-z0-9.]+", "-", version)
-
-
-setuptools_major_version = int(setuptools.__version__.split(".")[0])
-
-PY_LIMITED_API_PATTERN = r"cp3\d"
-
-
-def _is_32bit_interpreter() -> bool:
-    return struct.calcsize("P") == 4
-
-
-def python_tag() -> str:
-    return f"py{sys.version_info[0]}"
-
-
-def get_platform(archive_root: str | None) -> str:
-    """Return our platform name 'win32', 'linux_x86_64'"""
-    result = sysconfig.get_platform()
-    if result.startswith("macosx") and archive_root is not None:
-        from .macosx_libfile import calculate_macosx_platform_tag
-
-        result = calculate_macosx_platform_tag(archive_root, result)
-    elif _is_32bit_interpreter():
-        if result == "linux-x86_64":
-            # pip pull request #3497
-            result = "linux-i686"
-        elif result == "linux-aarch64":
-            # packaging pull request #234
-            # TODO armv8l, packaging pull request #690 => this did not land
-            # in pip/packaging yet
-            result = "linux-armv7l"
-
-    return result.replace("-", "_")
-
-
-def get_flag(
-    var: str, fallback: bool, expected: bool = True, warn: bool = True
-) -> bool:
-    """Use a fallback value for determining SOABI flags if the needed config
-    var is unset or unavailable."""
-    val = sysconfig.get_config_var(var)
-    if val is None:
-        if warn:
-            warnings.warn(
-                f"Config variable '{var}' is unset, Python ABI tag may be incorrect",
-                RuntimeWarning,
-                stacklevel=2,
-            )
-        return fallback
-    return val == expected
-
-
-def get_abi_tag() -> str | None:
-    """Return the ABI tag based on SOABI (if available) or emulate SOABI (PyPy2)."""
-    soabi: str = sysconfig.get_config_var("SOABI")
-    impl = tags.interpreter_name()
-    if not soabi and impl in ("cp", "pp") and hasattr(sys, "maxunicode"):
-        d = ""
-        m = ""
-        u = ""
-        if get_flag("Py_DEBUG", hasattr(sys, "gettotalrefcount"), warn=(impl == "cp")):
-            d = "d"
-
-        if get_flag(
-            "WITH_PYMALLOC",
-            impl == "cp",
-            warn=(impl == "cp" and sys.version_info < (3, 8)),
-        ) and sys.version_info < (3, 8):
-            m = "m"
-
-        abi = f"{impl}{tags.interpreter_version()}{d}{m}{u}"
-    elif soabi and impl == "cp" and soabi.startswith("cpython"):
-        # non-Windows
-        abi = "cp" + soabi.split("-")[1]
-    elif soabi and impl == "cp" and soabi.startswith("cp"):
-        # Windows
-        abi = soabi.split("-")[0]
-    elif soabi and impl == "pp":
-        # we want something like pypy36-pp73
-        abi = "-".join(soabi.split("-")[:2])
-        abi = abi.replace(".", "_").replace("-", "_")
-    elif soabi and impl == "graalpy":
-        abi = "-".join(soabi.split("-")[:3])
-        abi = abi.replace(".", "_").replace("-", "_")
-    elif soabi:
-        abi = soabi.replace(".", "_").replace("-", "_")
-    else:
-        abi = None
-
-    return abi
-
-
-def safer_name(name: str) -> str:
-    return safe_name(name).replace("-", "_")
-
-
-def safer_version(version: str) -> str:
-    return safe_version(version).replace("-", "_")
-
-
-def remove_readonly(
-    func: Callable[..., object],
-    path: str,
-    excinfo: tuple[type[Exception], Exception, types.TracebackType],
-) -> None:
-    remove_readonly_exc(func, path, excinfo[1])
-
-
-def remove_readonly_exc(func: Callable[..., object], path: str, exc: Exception) -> None:
-    os.chmod(path, stat.S_IWRITE)
-    func(path)
-
-
-class bdist_wheel(Command):
-    description = "create a wheel distribution"
-
-    supported_compressions = {
-        "stored": ZIP_STORED,
-        "deflated": ZIP_DEFLATED,
-    }
-
-    user_options = [
-        ("bdist-dir=", "b", "temporary directory for creating the distribution"),
-        (
-            "plat-name=",
-            "p",
-            "platform name to embed in generated filenames "
-            f"(default: {get_platform(None)})",
-        ),
-        (
-            "keep-temp",
-            "k",
-            "keep the pseudo-installation tree around after "
-            "creating the distribution archive",
-        ),
-        ("dist-dir=", "d", "directory to put final built distributions in"),
-        ("skip-build", None, "skip rebuilding everything (for testing/debugging)"),
-        (
-            "relative",
-            None,
-            "build the archive using relative paths (default: false)",
-        ),
-        (
-            "owner=",
-            "u",
-            "Owner name used when creating a tar file [default: current user]",
-        ),
-        (
-            "group=",
-            "g",
-            "Group name used when creating a tar file [default: current group]",
-        ),
-        ("universal", None, "make a universal wheel (default: false)"),
-        (
-            "compression=",
-            None,
-            "zipfile compression (one of: {}) (default: 'deflated')".format(
-                ", ".join(supported_compressions)
-            ),
-        ),
-        (
-            "python-tag=",
-            None,
-            f"Python implementation compatibility tag (default: '{python_tag()}')",
-        ),
-        (
-            "build-number=",
-            None,
-            "Build number for this particular version. "
-            "As specified in PEP-0427, this must start with a digit. "
-            "[default: None]",
-        ),
-        (
-            "py-limited-api=",
-            None,
-            "Python tag (cp32|cp33|cpNN) for abi3 wheel tag (default: false)",
-        ),
-    ]
-
-    boolean_options = ["keep-temp", "skip-build", "relative", "universal"]
-
-    def initialize_options(self):
-        self.bdist_dir: str = None
-        self.data_dir = None
-        self.plat_name: str | None = None
-        self.plat_tag = None
-        self.format = "zip"
-        self.keep_temp = False
-        self.dist_dir: str | None = None
-        self.egginfo_dir = None
-        self.root_is_pure: bool | None = None
-        self.skip_build = None
-        self.relative = False
-        self.owner = None
-        self.group = None
-        self.universal: bool = False
-        self.compression: str | int = "deflated"
-        self.python_tag: str = python_tag()
-        self.build_number: str | None = None
-        self.py_limited_api: str | Literal[False] = False
-        self.plat_name_supplied = False
-
-    def finalize_options(self):
-        if self.bdist_dir is None:
-            bdist_base = self.get_finalized_command("bdist").bdist_base
-            self.bdist_dir = os.path.join(bdist_base, "wheel")
-
-        egg_info = self.distribution.get_command_obj("egg_info")
-        egg_info.ensure_finalized()  # needed for correct `wheel_dist_name`
-
-        self.data_dir = self.wheel_dist_name + ".data"
-        self.plat_name_supplied = self.plat_name is not None
-
-        try:
-            self.compression = self.supported_compressions[self.compression]
-        except KeyError:
-            raise ValueError(f"Unsupported compression: {self.compression}") from None
-
-        need_options = ("dist_dir", "plat_name", "skip_build")
-
-        self.set_undefined_options("bdist", *zip(need_options, need_options))
-
-        self.root_is_pure = not (
-            self.distribution.has_ext_modules() or self.distribution.has_c_libraries()
-        )
-
-        if self.py_limited_api and not re.match(
-            PY_LIMITED_API_PATTERN, self.py_limited_api
-        ):
-            raise ValueError(f"py-limited-api must match '{PY_LIMITED_API_PATTERN}'")
-
-        # Support legacy [wheel] section for setting universal
-        wheel = self.distribution.get_option_dict("wheel")
-        if "universal" in wheel:
-            # please don't define this in your global configs
-            log.warning(
-                "The [wheel] section is deprecated. Use [bdist_wheel] instead.",
-            )
-            val = wheel["universal"][1].strip()
-            if val.lower() in ("1", "true", "yes"):
-                self.universal = True
-
-        if self.build_number is not None and not self.build_number[:1].isdigit():
-            raise ValueError("Build tag (build-number) must start with a digit.")
-
-    @property
-    def wheel_dist_name(self):
-        """Return distribution full name with - replaced with _"""
-        components = (
-            safer_name(self.distribution.get_name()),
-            safer_version(self.distribution.get_version()),
-        )
-        if self.build_number:
-            components += (self.build_number,)
-        return "-".join(components)
-
-    def get_tag(self) -> tuple[str, str, str]:
-        # bdist sets self.plat_name if unset, we should only use it for purepy
-        # wheels if the user supplied it.
-        if self.plat_name_supplied:
-            plat_name = cast(str, self.plat_name)
-        elif self.root_is_pure:
-            plat_name = "any"
-        else:
-            # macosx contains system version in platform name so need special handle
-            if self.plat_name and not self.plat_name.startswith("macosx"):
-                plat_name = self.plat_name
-            else:
-                # on macosx always limit the platform name to comply with any
-                # c-extension modules in bdist_dir, since the user can specify
-                # a higher MACOSX_DEPLOYMENT_TARGET via tools like CMake
-
-                # on other platforms, and on macosx if there are no c-extension
-                # modules, use the default platform name.
-                plat_name = get_platform(self.bdist_dir)
-
-            if _is_32bit_interpreter():
-                if plat_name in ("linux-x86_64", "linux_x86_64"):
-                    plat_name = "linux_i686"
-                if plat_name in ("linux-aarch64", "linux_aarch64"):
-                    # TODO armv8l, packaging pull request #690 => this did not land
-                    # in pip/packaging yet
-                    plat_name = "linux_armv7l"
-
-        plat_name = (
-            plat_name.lower().replace("-", "_").replace(".", "_").replace(" ", "_")
-        )
-
-        if self.root_is_pure:
-            if self.universal:
-                impl = "py2.py3"
-            else:
-                impl = self.python_tag
-            tag = (impl, "none", plat_name)
-        else:
-            impl_name = tags.interpreter_name()
-            impl_ver = tags.interpreter_version()
-            impl = impl_name + impl_ver
-            # We don't work on CPython 3.1, 3.0.
-            if self.py_limited_api and (impl_name + impl_ver).startswith("cp3"):
-                impl = self.py_limited_api
-                abi_tag = "abi3"
-            else:
-                abi_tag = str(get_abi_tag()).lower()
-            tag = (impl, abi_tag, plat_name)
-            # issue gh-374: allow overriding plat_name
-            supported_tags = [
-                (t.interpreter, t.abi, plat_name) for t in tags.sys_tags()
-            ]
-            assert (
-                tag in supported_tags
-            ), f"would build wheel with unsupported tag {tag}"
-        return tag
-
-    def run(self):
-        build_scripts = self.reinitialize_command("build_scripts")
-        build_scripts.executable = "python"
-        build_scripts.force = True
-
-        build_ext = self.reinitialize_command("build_ext")
-        build_ext.inplace = False
-
-        if not self.skip_build:
-            self.run_command("build")
-
-        install = self.reinitialize_command("install", reinit_subcommands=True)
-        install.root = self.bdist_dir
-        install.compile = False
-        install.skip_build = self.skip_build
-        install.warn_dir = False
-
-        # A wheel without setuptools scripts is more cross-platform.
-        # Use the (undocumented) `no_ep` option to setuptools'
-        # install_scripts command to avoid creating entry point scripts.
-        install_scripts = self.reinitialize_command("install_scripts")
-        install_scripts.no_ep = True
-
-        # Use a custom scheme for the archive, because we have to decide
-        # at installation time which scheme to use.
-        for key in ("headers", "scripts", "data", "purelib", "platlib"):
-            setattr(install, "install_" + key, os.path.join(self.data_dir, key))
-
-        basedir_observed = ""
-
-        if os.name == "nt":
-            # win32 barfs if any of these are ''; could be '.'?
-            # (distutils.command.install:change_roots bug)
-            basedir_observed = os.path.normpath(os.path.join(self.data_dir, ".."))
-            self.install_libbase = self.install_lib = basedir_observed
-
-        setattr(
-            install,
-            "install_purelib" if self.root_is_pure else "install_platlib",
-            basedir_observed,
-        )
-
-        log.info(f"installing to {self.bdist_dir}")
-
-        self.run_command("install")
-
-        impl_tag, abi_tag, plat_tag = self.get_tag()
-        archive_basename = f"{self.wheel_dist_name}-{impl_tag}-{abi_tag}-{plat_tag}"
-        if not self.relative:
-            archive_root = self.bdist_dir
-        else:
-            archive_root = os.path.join(
-                self.bdist_dir, self._ensure_relative(install.install_base)
-            )
-
-        self.set_undefined_options("install_egg_info", ("target", "egginfo_dir"))
-        distinfo_dirname = (
-            f"{safer_name(self.distribution.get_name())}-"
-            f"{safer_version(self.distribution.get_version())}.dist-info"
-        )
-        distinfo_dir = os.path.join(self.bdist_dir, distinfo_dirname)
-        self.egg2dist(self.egginfo_dir, distinfo_dir)
-
-        self.write_wheelfile(distinfo_dir)
-
-        # Make the archive
-        if not os.path.exists(self.dist_dir):
-            os.makedirs(self.dist_dir)
-
-        wheel_path = os.path.join(self.dist_dir, archive_basename + ".whl")
-        with WheelFile(wheel_path, "w", self.compression) as wf:
-            wf.write_files(archive_root)
-
-        # Add to 'Distribution.dist_files' so that the "upload" command works
-        getattr(self.distribution, "dist_files", []).append(
-            (
-                "bdist_wheel",
-                "{}.{}".format(*sys.version_info[:2]),  # like 3.7
-                wheel_path,
-            )
-        )
-
-        if not self.keep_temp:
-            log.info(f"removing {self.bdist_dir}")
-            if not self.dry_run:
-                if sys.version_info < (3, 12):
-                    rmtree(self.bdist_dir, onerror=remove_readonly)
-                else:
-                    rmtree(self.bdist_dir, onexc=remove_readonly_exc)
-
-    def write_wheelfile(
-        self, wheelfile_base: str, generator: str = f"bdist_wheel ({wheel_version})"
-    ):
-        from email.message import Message
-
-        msg = Message()
-        msg["Wheel-Version"] = "1.0"  # of the spec
-        msg["Generator"] = generator
-        msg["Root-Is-Purelib"] = str(self.root_is_pure).lower()
-        if self.build_number is not None:
-            msg["Build"] = self.build_number
-
-        # Doesn't work for bdist_wininst
-        impl_tag, abi_tag, plat_tag = self.get_tag()
-        for impl in impl_tag.split("."):
-            for abi in abi_tag.split("."):
-                for plat in plat_tag.split("."):
-                    msg["Tag"] = "-".join((impl, abi, plat))
-
-        wheelfile_path = os.path.join(wheelfile_base, "WHEEL")
-        log.info(f"creating {wheelfile_path}")
-        with open(wheelfile_path, "wb") as f:
-            BytesGenerator(f, maxheaderlen=0).flatten(msg)
-
-    def _ensure_relative(self, path: str) -> str:
-        # copied from dir_util, deleted
-        drive, path = os.path.splitdrive(path)
-        if path[0:1] == os.sep:
-            path = drive + path[1:]
-        return path
-
-    @property
-    def license_paths(self) -> Iterable[str]:
-        if setuptools_major_version >= 57:
-            # Setuptools has resolved any patterns to actual file names
-            return self.distribution.metadata.license_files or ()
-
-        files: set[str] = set()
-        metadata = self.distribution.get_option_dict("metadata")
-        if setuptools_major_version >= 42:
-            # Setuptools recognizes the license_files option but does not do globbing
-            patterns = cast(Sequence[str], self.distribution.metadata.license_files)
-        else:
-            # Prior to those, wheel is entirely responsible for handling license files
-            if "license_files" in metadata:
-                patterns = metadata["license_files"][1].split()
-            else:
-                patterns = ()
-
-        if "license_file" in metadata:
-            warnings.warn(
-                'The "license_file" option is deprecated. Use "license_files" instead.',
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            files.add(metadata["license_file"][1])
-
-        if not files and not patterns and not isinstance(patterns, list):
-            patterns = ("LICEN[CS]E*", "COPYING*", "NOTICE*", "AUTHORS*")
-
-        for pattern in patterns:
-            for path in iglob(pattern):
-                if path.endswith("~"):
-                    log.debug(
-                        f'ignoring license file "{path}" as it looks like a backup'
-                    )
-                    continue
-
-                if path not in files and os.path.isfile(path):
-                    log.info(
-                        f'adding license file "{path}" (matched pattern "{pattern}")'
-                    )
-                    files.add(path)
-
-        return files
-
-    def egg2dist(self, egginfo_path: str, distinfo_path: str):
-        """Convert an .egg-info directory into a .dist-info directory"""
-
-        def adios(p: str) -> None:
-            """Appropriately delete directory, file or link."""
-            if os.path.exists(p) and not os.path.islink(p) and os.path.isdir(p):
-                shutil.rmtree(p)
-            elif os.path.exists(p):
-                os.unlink(p)
-
-        adios(distinfo_path)
-
-        if not os.path.exists(egginfo_path):
-            # There is no egg-info. This is probably because the egg-info
-            # file/directory is not named matching the distribution name used
-            # to name the archive file. Check for this case and report
-            # accordingly.
-            import glob
-
-            pat = os.path.join(os.path.dirname(egginfo_path), "*.egg-info")
-            possible = glob.glob(pat)
-            err = f"Egg metadata expected at {egginfo_path} but not found"
-            if possible:
-                alt = os.path.basename(possible[0])
-                err += f" ({alt} found - possible misnamed archive file?)"
-
-            raise ValueError(err)
-
-        if os.path.isfile(egginfo_path):
-            # .egg-info is a single file
-            pkg_info = pkginfo_to_metadata(egginfo_path, egginfo_path)
-            os.mkdir(distinfo_path)
-        else:
-            # .egg-info is a directory
-            pkginfo_path = os.path.join(egginfo_path, "PKG-INFO")
-            pkg_info = pkginfo_to_metadata(egginfo_path, pkginfo_path)
-
-            # ignore common egg metadata that is useless to wheel
-            shutil.copytree(
-                egginfo_path,
-                distinfo_path,
-                ignore=lambda x, y: {
-                    "PKG-INFO",
-                    "requires.txt",
-                    "SOURCES.txt",
-                    "not-zip-safe",
-                },
-            )
-
-            # delete dependency_links if it is only whitespace
-            dependency_links_path = os.path.join(distinfo_path, "dependency_links.txt")
-            with open(dependency_links_path, encoding="utf-8") as dependency_links_file:
-                dependency_links = dependency_links_file.read().strip()
-            if not dependency_links:
-                adios(dependency_links_path)
-
-        pkg_info_path = os.path.join(distinfo_path, "METADATA")
-        serialization_policy = EmailPolicy(
-            utf8=True,
-            mangle_from_=False,
-            max_line_length=0,
-        )
-        with open(pkg_info_path, "w", encoding="utf-8") as out:
-            Generator(out, policy=serialization_policy).flatten(pkg_info)
-
-        for license_path in self.license_paths:
-            filename = os.path.basename(license_path)
-            shutil.copy(license_path, os.path.join(distinfo_path, filename))
-
-        adios(egginfo_path)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/_setuptools_logging.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/_setuptools_logging.py
deleted file mode 100644
index a1a2482..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/_setuptools_logging.py
+++ /dev/null
@@ -1,26 +0,0 @@
-# copied from setuptools.logging, omitting monkeypatching
-from __future__ import annotations
-
-import logging
-import sys
-
-
-def _not_warning(record: logging.LogRecord) -> bool:
-    return record.levelno < logging.WARNING
-
-
-def configure() -> None:
-    """
-    Configure logging to emit warning and above to stderr
-    and everything else to stdout. This behavior is provided
-    for compatibility with distutils.log but may change in
-    the future.
-    """
-    err_handler = logging.StreamHandler()
-    err_handler.setLevel(logging.WARNING)
-    out_handler = logging.StreamHandler(sys.stdout)
-    out_handler.addFilter(_not_warning)
-    handlers = err_handler, out_handler
-    logging.basicConfig(
-        format="{message}", style="{", handlers=handlers, level=logging.DEBUG
-    )
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/bdist_wheel.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/bdist_wheel.py
deleted file mode 100644
index dd7b862..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/bdist_wheel.py
+++ /dev/null
@@ -1,26 +0,0 @@
-from typing import TYPE_CHECKING
-from warnings import warn
-
-warn(
-    "The 'wheel' package is no longer the canonical location of the 'bdist_wheel' "
-    "command, and will be removed in a future release. Please update to setuptools "
-    "v70.1 or later which contains an integrated version of this command.",
-    DeprecationWarning,
-    stacklevel=1,
-)
-
-if TYPE_CHECKING:
-    from ._bdist_wheel import bdist_wheel as bdist_wheel
-else:
-    try:
-        # Better integration/compatibility with setuptools:
-        # in the case new fixes or PEPs are implemented in setuptools
-        # there is no need to backport them to the deprecated code base.
-        # This is useful in the case of old packages in the ecosystem
-        # that are still used but have low maintenance.
-        from setuptools.command.bdist_wheel import bdist_wheel
-    except ImportError:
-        # Only used in the case of old setuptools versions.
-        # If the user wants to get the latest fixes/PEPs,
-        # they are encouraged to address the deprecation warning.
-        from ._bdist_wheel import bdist_wheel as bdist_wheel
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__init__.py
deleted file mode 100644
index 6ba1217..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__init__.py
+++ /dev/null
@@ -1,155 +0,0 @@
-"""
-Wheel command-line utility.
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-import sys
-from argparse import ArgumentTypeError
-
-
-class WheelError(Exception):
-    pass
-
-
-def unpack_f(args: argparse.Namespace) -> None:
-    from .unpack import unpack
-
-    unpack(args.wheelfile, args.dest)
-
-
-def pack_f(args: argparse.Namespace) -> None:
-    from .pack import pack
-
-    pack(args.directory, args.dest_dir, args.build_number)
-
-
-def convert_f(args: argparse.Namespace) -> None:
-    from .convert import convert
-
-    convert(args.files, args.dest_dir, args.verbose)
-
-
-def tags_f(args: argparse.Namespace) -> None:
-    from .tags import tags
-
-    names = (
-        tags(
-            wheel,
-            args.python_tag,
-            args.abi_tag,
-            args.platform_tag,
-            args.build,
-            args.remove,
-        )
-        for wheel in args.wheel
-    )
-
-    for name in names:
-        print(name)
-
-
-def version_f(args: argparse.Namespace) -> None:
-    from .. import __version__
-
-    print(f"wheel {__version__}")
-
-
-def parse_build_tag(build_tag: str) -> str:
-    if build_tag and not build_tag[0].isdigit():
-        raise ArgumentTypeError("build tag must begin with a digit")
-    elif "-" in build_tag:
-        raise ArgumentTypeError("invalid character ('-') in build tag")
-
-    return build_tag
-
-
-TAGS_HELP = """\
-Make a new wheel with given tags. Any tags unspecified will remain the same.
-Starting the tags with a "+" will append to the existing tags. Starting with a
-"-" will remove a tag (use --option=-TAG syntax). Multiple tags can be
-separated by ".". The original file will remain unless --remove is given.  The
-output filename(s) will be displayed on stdout for further processing.
-"""
-
-
-def parser():
-    p = argparse.ArgumentParser()
-    s = p.add_subparsers(help="commands")
-
-    unpack_parser = s.add_parser("unpack", help="Unpack wheel")
-    unpack_parser.add_argument(
-        "--dest", "-d", help="Destination directory", default="."
-    )
-    unpack_parser.add_argument("wheelfile", help="Wheel file")
-    unpack_parser.set_defaults(func=unpack_f)
-
-    repack_parser = s.add_parser("pack", help="Repack wheel")
-    repack_parser.add_argument("directory", help="Root directory of the unpacked wheel")
-    repack_parser.add_argument(
-        "--dest-dir",
-        "-d",
-        default=os.path.curdir,
-        help="Directory to store the wheel (default %(default)s)",
-    )
-    repack_parser.add_argument(
-        "--build-number", help="Build tag to use in the wheel name"
-    )
-    repack_parser.set_defaults(func=pack_f)
-
-    convert_parser = s.add_parser("convert", help="Convert egg or wininst to wheel")
-    convert_parser.add_argument("files", nargs="*", help="Files to convert")
-    convert_parser.add_argument(
-        "--dest-dir",
-        "-d",
-        default=os.path.curdir,
-        help="Directory to store wheels (default %(default)s)",
-    )
-    convert_parser.add_argument("--verbose", "-v", action="store_true")
-    convert_parser.set_defaults(func=convert_f)
-
-    tags_parser = s.add_parser(
-        "tags", help="Add or replace the tags on a wheel", description=TAGS_HELP
-    )
-    tags_parser.add_argument("wheel", nargs="*", help="Existing wheel(s) to retag")
-    tags_parser.add_argument(
-        "--remove",
-        action="store_true",
-        help="Remove the original files, keeping only the renamed ones",
-    )
-    tags_parser.add_argument(
-        "--python-tag", metavar="TAG", help="Specify an interpreter tag(s)"
-    )
-    tags_parser.add_argument("--abi-tag", metavar="TAG", help="Specify an ABI tag(s)")
-    tags_parser.add_argument(
-        "--platform-tag", metavar="TAG", help="Specify a platform tag(s)"
-    )
-    tags_parser.add_argument(
-        "--build", type=parse_build_tag, metavar="BUILD", help="Specify a build tag"
-    )
-    tags_parser.set_defaults(func=tags_f)
-
-    version_parser = s.add_parser("version", help="Print version and exit")
-    version_parser.set_defaults(func=version_f)
-
-    help_parser = s.add_parser("help", help="Show this help")
-    help_parser.set_defaults(func=lambda args: p.print_help())
-
-    return p
-
-
-def main():
-    p = parser()
-    args = p.parse_args()
-    if not hasattr(args, "func"):
-        p.print_help()
-    else:
-        try:
-            args.func(args)
-            return 0
-        except WheelError as e:
-            print(e, file=sys.stderr)
-
-    return 1
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 0c53e22..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/convert.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/convert.cpython-312.pyc
deleted file mode 100644
index b688a3e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/convert.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/pack.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/pack.cpython-312.pyc
deleted file mode 100644
index 9de629c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/pack.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/tags.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/tags.cpython-312.pyc
deleted file mode 100644
index 33132da..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/tags.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/unpack.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/unpack.cpython-312.pyc
deleted file mode 100644
index f65b829..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/__pycache__/unpack.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/convert.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/convert.py
deleted file mode 100644
index 61d4775..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/convert.py
+++ /dev/null
@@ -1,332 +0,0 @@
-from __future__ import annotations
-
-import os.path
-import re
-from abc import ABCMeta, abstractmethod
-from collections import defaultdict
-from collections.abc import Iterator
-from email.message import Message
-from email.parser import Parser
-from email.policy import EmailPolicy
-from glob import iglob
-from pathlib import Path
-from textwrap import dedent
-from zipfile import ZipFile
-
-from .. import __version__
-from ..metadata import generate_requirements
-from ..vendored.packaging.tags import parse_tag
-from ..wheelfile import WheelFile
-
-egg_filename_re = re.compile(
-    r"""
-    (?P.+?)-(?P.+?)
-    (-(?Ppy\d\.\d+)
-     (-(?P.+?))?
-    )?.egg$""",
-    re.VERBOSE,
-)
-egg_info_re = re.compile(
-    r"""
-    ^(?P.+?)-(?P.+?)
-    (-(?Ppy\d\.\d+)
-    )?.egg-info/""",
-    re.VERBOSE,
-)
-wininst_re = re.compile(
-    r"\.(?Pwin32|win-amd64)(?:-(?Ppy\d\.\d))?\.exe$"
-)
-pyd_re = re.compile(r"\.(?P[a-z0-9]+)-(?Pwin32|win_amd64)\.pyd$")
-serialization_policy = EmailPolicy(
-    utf8=True,
-    mangle_from_=False,
-    max_line_length=0,
-)
-GENERATOR = f"wheel {__version__}"
-
-
-def convert_requires(requires: str, metadata: Message) -> None:
-    extra: str | None = None
-    requirements: dict[str | None, list[str]] = defaultdict(list)
-    for line in requires.splitlines():
-        line = line.strip()
-        if not line:
-            continue
-
-        if line.startswith("[") and line.endswith("]"):
-            extra = line[1:-1]
-            continue
-
-        requirements[extra].append(line)
-
-    for key, value in generate_requirements(requirements):
-        metadata.add_header(key, value)
-
-
-def convert_pkg_info(pkginfo: str, metadata: Message):
-    parsed_message = Parser().parsestr(pkginfo)
-    for key, value in parsed_message.items():
-        key_lower = key.lower()
-        if value == "UNKNOWN":
-            continue
-
-        if key_lower == "description":
-            description_lines = value.splitlines()
-            value = "\n".join(
-                (
-                    description_lines[0].lstrip(),
-                    dedent("\n".join(description_lines[1:])),
-                    "\n",
-                )
-            )
-            metadata.set_payload(value)
-        elif key_lower == "home-page":
-            metadata.add_header("Project-URL", f"Homepage, {value}")
-        elif key_lower == "download-url":
-            metadata.add_header("Project-URL", f"Download, {value}")
-        else:
-            metadata.add_header(key, value)
-
-    metadata.replace_header("Metadata-Version", "2.4")
-
-
-def normalize(name: str) -> str:
-    return re.sub(r"[-_.]+", "-", name).lower().replace("-", "_")
-
-
-class ConvertSource(metaclass=ABCMeta):
-    name: str
-    version: str
-    pyver: str = "py2.py3"
-    abi: str = "none"
-    platform: str = "any"
-    metadata: Message
-
-    @property
-    def dist_info_dir(self) -> str:
-        return f"{self.name}-{self.version}.dist-info"
-
-    @abstractmethod
-    def generate_contents(self) -> Iterator[tuple[str, bytes]]:
-        pass
-
-
-class EggFileSource(ConvertSource):
-    def __init__(self, path: Path):
-        if not (match := egg_filename_re.match(path.name)):
-            raise ValueError(f"Invalid egg file name: {path.name}")
-
-        # Binary wheels are assumed to be for CPython
-        self.path = path
-        self.name = normalize(match.group("name"))
-        self.version = match.group("ver")
-        if pyver := match.group("pyver"):
-            self.pyver = pyver.replace(".", "")
-            if arch := match.group("arch"):
-                self.abi = self.pyver.replace("py", "cp")
-                self.platform = normalize(arch)
-
-        self.metadata = Message()
-
-    def generate_contents(self) -> Iterator[tuple[str, bytes]]:
-        with ZipFile(self.path, "r") as zip_file:
-            for filename in sorted(zip_file.namelist()):
-                # Skip pure directory entries
-                if filename.endswith("/"):
-                    continue
-
-                # Handle files in the egg-info directory specially, selectively moving
-                # them to the dist-info directory while converting as needed
-                if filename.startswith("EGG-INFO/"):
-                    if filename == "EGG-INFO/requires.txt":
-                        requires = zip_file.read(filename).decode("utf-8")
-                        convert_requires(requires, self.metadata)
-                    elif filename == "EGG-INFO/PKG-INFO":
-                        pkginfo = zip_file.read(filename).decode("utf-8")
-                        convert_pkg_info(pkginfo, self.metadata)
-                    elif filename == "EGG-INFO/entry_points.txt":
-                        yield (
-                            f"{self.dist_info_dir}/entry_points.txt",
-                            zip_file.read(filename),
-                        )
-
-                    continue
-
-                # For any other file, just pass it through
-                yield filename, zip_file.read(filename)
-
-
-class EggDirectorySource(EggFileSource):
-    def generate_contents(self) -> Iterator[tuple[str, bytes]]:
-        for dirpath, _, filenames in os.walk(self.path):
-            for filename in sorted(filenames):
-                path = Path(dirpath, filename)
-                if path.parent.name == "EGG-INFO":
-                    if path.name == "requires.txt":
-                        requires = path.read_text("utf-8")
-                        convert_requires(requires, self.metadata)
-                    elif path.name == "PKG-INFO":
-                        pkginfo = path.read_text("utf-8")
-                        convert_pkg_info(pkginfo, self.metadata)
-                        if name := self.metadata.get("Name"):
-                            self.name = normalize(name)
-
-                        if version := self.metadata.get("Version"):
-                            self.version = version
-                    elif path.name == "entry_points.txt":
-                        yield (
-                            f"{self.dist_info_dir}/entry_points.txt",
-                            path.read_bytes(),
-                        )
-
-                    continue
-
-                # For any other file, just pass it through
-                yield str(path.relative_to(self.path)), path.read_bytes()
-
-
-class WininstFileSource(ConvertSource):
-    """
-    Handles distributions created with ``bdist_wininst``.
-
-    The egginfo filename has the format::
-
-        name-ver(-pyver)(-arch).egg-info
-
-    The installer filename has the format::
-
-        name-ver.arch(-pyver).exe
-
-    Some things to note:
-
-    1. The installer filename is not definitive. An installer can be renamed
-       and work perfectly well as an installer. So more reliable data should
-       be used whenever possible.
-    2. The egg-info data should be preferred for the name and version, because
-       these come straight from the distutils metadata, and are mandatory.
-    3. The pyver from the egg-info data should be ignored, as it is
-       constructed from the version of Python used to build the installer,
-       which is irrelevant - the installer filename is correct here (even to
-       the point that when it's not there, any version is implied).
-    4. The architecture must be taken from the installer filename, as it is
-       not included in the egg-info data.
-    5. Architecture-neutral installers still have an architecture because the
-       installer format itself (being executable) is architecture-specific. We
-       should therefore ignore the architecture if the content is pure-python.
-    """
-
-    def __init__(self, path: Path):
-        self.path = path
-        self.metadata = Message()
-
-        # Determine the initial architecture and Python version from the file name
-        # (if possible)
-        if match := wininst_re.search(path.name):
-            self.platform = normalize(match.group("platform"))
-            if pyver := match.group("pyver"):
-                self.pyver = pyver.replace(".", "")
-
-        # Look for an .egg-info directory and any .pyd files for more precise info
-        egg_info_found = pyd_found = False
-        with ZipFile(self.path) as zip_file:
-            for filename in zip_file.namelist():
-                prefix, filename = filename.split("/", 1)
-                if not egg_info_found and (match := egg_info_re.match(filename)):
-                    egg_info_found = True
-                    self.name = normalize(match.group("name"))
-                    self.version = match.group("ver")
-                    if pyver := match.group("pyver"):
-                        self.pyver = pyver.replace(".", "")
-                elif not pyd_found and (match := pyd_re.search(filename)):
-                    pyd_found = True
-                    self.abi = match.group("abi")
-                    self.platform = match.group("platform")
-
-                if egg_info_found and pyd_found:
-                    break
-
-    def generate_contents(self) -> Iterator[tuple[str, bytes]]:
-        dist_info_dir = f"{self.name}-{self.version}.dist-info"
-        data_dir = f"{self.name}-{self.version}.data"
-        with ZipFile(self.path, "r") as zip_file:
-            for filename in sorted(zip_file.namelist()):
-                # Skip pure directory entries
-                if filename.endswith("/"):
-                    continue
-
-                # Handle files in the egg-info directory specially, selectively moving
-                # them to the dist-info directory while converting as needed
-                prefix, target_filename = filename.split("/", 1)
-                if egg_info_re.search(target_filename):
-                    basename = target_filename.rsplit("/", 1)[-1]
-                    if basename == "requires.txt":
-                        requires = zip_file.read(filename).decode("utf-8")
-                        convert_requires(requires, self.metadata)
-                    elif basename == "PKG-INFO":
-                        pkginfo = zip_file.read(filename).decode("utf-8")
-                        convert_pkg_info(pkginfo, self.metadata)
-                    elif basename == "entry_points.txt":
-                        yield (
-                            f"{dist_info_dir}/entry_points.txt",
-                            zip_file.read(filename),
-                        )
-
-                    continue
-                elif prefix == "SCRIPTS":
-                    target_filename = f"{data_dir}/scripts/{target_filename}"
-
-                # For any other file, just pass it through
-                yield target_filename, zip_file.read(filename)
-
-
-def convert(files: list[str], dest_dir: str, verbose: bool) -> None:
-    for pat in files:
-        for archive in iglob(pat):
-            path = Path(archive)
-            if path.suffix == ".egg":
-                if path.is_dir():
-                    source: ConvertSource = EggDirectorySource(path)
-                else:
-                    source = EggFileSource(path)
-            else:
-                source = WininstFileSource(path)
-
-            if verbose:
-                print(f"{archive}...", flush=True, end="")
-
-            dest_path = Path(dest_dir) / (
-                f"{source.name}-{source.version}-{source.pyver}-{source.abi}"
-                f"-{source.platform}.whl"
-            )
-            with WheelFile(dest_path, "w") as wheelfile:
-                for name_or_zinfo, contents in source.generate_contents():
-                    wheelfile.writestr(name_or_zinfo, contents)
-
-                # Write the METADATA file
-                wheelfile.writestr(
-                    f"{source.dist_info_dir}/METADATA",
-                    source.metadata.as_string(policy=serialization_policy).encode(
-                        "utf-8"
-                    ),
-                )
-
-                # Write the WHEEL file
-                wheel_message = Message()
-                wheel_message.add_header("Wheel-Version", "1.0")
-                wheel_message.add_header("Generator", GENERATOR)
-                wheel_message.add_header(
-                    "Root-Is-Purelib", str(source.platform == "any").lower()
-                )
-                tags = parse_tag(f"{source.pyver}-{source.abi}-{source.platform}")
-                for tag in sorted(tags, key=lambda tag: tag.interpreter):
-                    wheel_message.add_header("Tag", str(tag))
-
-                wheelfile.writestr(
-                    f"{source.dist_info_dir}/WHEEL",
-                    wheel_message.as_string(policy=serialization_policy).encode(
-                        "utf-8"
-                    ),
-                )
-
-            if verbose:
-                print("OK")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/pack.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/pack.py
deleted file mode 100644
index 64469c0..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/pack.py
+++ /dev/null
@@ -1,85 +0,0 @@
-from __future__ import annotations
-
-import email.policy
-import os.path
-import re
-from email.generator import BytesGenerator
-from email.parser import BytesParser
-
-from wheel.cli import WheelError
-from wheel.wheelfile import WheelFile
-
-DIST_INFO_RE = re.compile(r"^(?P(?P.+?)-(?P\d.*?))\.dist-info$")
-
-
-def pack(directory: str, dest_dir: str, build_number: str | None) -> None:
-    """Repack a previously unpacked wheel directory into a new wheel file.
-
-    The .dist-info/WHEEL file must contain one or more tags so that the target
-    wheel file name can be determined.
-
-    :param directory: The unpacked wheel directory
-    :param dest_dir: Destination directory (defaults to the current directory)
-    """
-    # Find the .dist-info directory
-    dist_info_dirs = [
-        fn
-        for fn in os.listdir(directory)
-        if os.path.isdir(os.path.join(directory, fn)) and DIST_INFO_RE.match(fn)
-    ]
-    if len(dist_info_dirs) > 1:
-        raise WheelError(f"Multiple .dist-info directories found in {directory}")
-    elif not dist_info_dirs:
-        raise WheelError(f"No .dist-info directories found in {directory}")
-
-    # Determine the target wheel filename
-    dist_info_dir = dist_info_dirs[0]
-    name_version = DIST_INFO_RE.match(dist_info_dir).group("namever")
-
-    # Read the tags and the existing build number from .dist-info/WHEEL
-    wheel_file_path = os.path.join(directory, dist_info_dir, "WHEEL")
-    with open(wheel_file_path, "rb") as f:
-        info = BytesParser(policy=email.policy.compat32).parse(f)
-        tags: list[str] = info.get_all("Tag", [])
-        existing_build_number = info.get("Build")
-
-        if not tags:
-            raise WheelError(
-                f"No tags present in {dist_info_dir}/WHEEL; cannot determine target "
-                f"wheel filename"
-            )
-
-    # Set the wheel file name and add/replace/remove the Build tag in .dist-info/WHEEL
-    build_number = build_number if build_number is not None else existing_build_number
-    if build_number is not None:
-        del info["Build"]
-        if build_number:
-            info["Build"] = build_number
-            name_version += "-" + build_number
-
-        if build_number != existing_build_number:
-            with open(wheel_file_path, "wb") as f:
-                BytesGenerator(f, maxheaderlen=0).flatten(info)
-
-    # Reassemble the tags for the wheel file
-    tagline = compute_tagline(tags)
-
-    # Repack the wheel
-    wheel_path = os.path.join(dest_dir, f"{name_version}-{tagline}.whl")
-    with WheelFile(wheel_path, "w") as wf:
-        print(f"Repacking wheel as {wheel_path}...", end="", flush=True)
-        wf.write_files(directory)
-
-    print("OK")
-
-
-def compute_tagline(tags: list[str]) -> str:
-    """Compute a tagline from a list of tags.
-
-    :param tags: A list of tags
-    :return: A tagline
-    """
-    impls = sorted({tag.split("-")[0] for tag in tags})
-    abivers = sorted({tag.split("-")[1] for tag in tags})
-    platforms = sorted({tag.split("-")[2] for tag in tags})
-    return "-".join([".".join(impls), ".".join(abivers), ".".join(platforms)])
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/tags.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/tags.py
deleted file mode 100644
index 88da72e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/tags.py
+++ /dev/null
@@ -1,139 +0,0 @@
-from __future__ import annotations
-
-import email.policy
-import itertools
-import os
-from collections.abc import Iterable
-from email.parser import BytesParser
-
-from ..wheelfile import WheelFile
-
-
-def _compute_tags(original_tags: Iterable[str], new_tags: str | None) -> set[str]:
-    """Add or replace tags. Supports dot-separated tags"""
-    if new_tags is None:
-        return set(original_tags)
-
-    if new_tags.startswith("+"):
-        return {*original_tags, *new_tags[1:].split(".")}
-
-    if new_tags.startswith("-"):
-        return set(original_tags) - set(new_tags[1:].split("."))
-
-    return set(new_tags.split("."))
-
-
-def tags(
-    wheel: str,
-    python_tags: str | None = None,
-    abi_tags: str | None = None,
-    platform_tags: str | None = None,
-    build_tag: str | None = None,
-    remove: bool = False,
-) -> str:
-    """Change the tags on a wheel file.
-
-    The tags are left unchanged if they are not specified. To specify "none",
-    use ["none"]. To append to the previous tags, a tag should start with a
-    "+".  If a tag starts with "-", it will be removed from existing tags.
-    Processing is done left to right.
-
-    :param wheel: The paths to the wheels
-    :param python_tags: The Python tags to set
-    :param abi_tags: The ABI tags to set
-    :param platform_tags: The platform tags to set
-    :param build_tag: The build tag to set
-    :param remove: Remove the original wheel
-    """
-    with WheelFile(wheel, "r") as f:
-        assert f.filename, f"{f.filename} must be available"
-
-        wheel_info = f.read(f.dist_info_path + "/WHEEL")
-        info = BytesParser(policy=email.policy.compat32).parsebytes(wheel_info)
-
-        original_wheel_name = os.path.basename(f.filename)
-        namever = f.parsed_filename.group("namever")
-        build = f.parsed_filename.group("build")
-        original_python_tags = f.parsed_filename.group("pyver").split(".")
-        original_abi_tags = f.parsed_filename.group("abi").split(".")
-        original_plat_tags = f.parsed_filename.group("plat").split(".")
-
-    tags: list[str] = info.get_all("Tag", [])
-    existing_build_tag = info.get("Build")
-
-    impls = {tag.split("-")[0] for tag in tags}
-    abivers = {tag.split("-")[1] for tag in tags}
-    platforms = {tag.split("-")[2] for tag in tags}
-
-    if impls != set(original_python_tags):
-        msg = f"Wheel internal tags {impls!r} != filename tags {original_python_tags!r}"
-        raise AssertionError(msg)
-
-    if abivers != set(original_abi_tags):
-        msg = f"Wheel internal tags {abivers!r} != filename tags {original_abi_tags!r}"
-        raise AssertionError(msg)
-
-    if platforms != set(original_plat_tags):
-        msg = (
-            f"Wheel internal tags {platforms!r} != filename tags {original_plat_tags!r}"
-        )
-        raise AssertionError(msg)
-
-    if existing_build_tag != build:
-        msg = (
-            f"Incorrect filename '{build}' "
-            f"& *.dist-info/WHEEL '{existing_build_tag}' build numbers"
-        )
-        raise AssertionError(msg)
-
-    # Start changing as needed
-    if build_tag is not None:
-        build = build_tag
-
-    final_python_tags = sorted(_compute_tags(original_python_tags, python_tags))
-    final_abi_tags = sorted(_compute_tags(original_abi_tags, abi_tags))
-    final_plat_tags = sorted(_compute_tags(original_plat_tags, platform_tags))
-
-    final_tags = [
-        namever,
-        ".".join(final_python_tags),
-        ".".join(final_abi_tags),
-        ".".join(final_plat_tags),
-    ]
-    if build:
-        final_tags.insert(1, build)
-
-    final_wheel_name = "-".join(final_tags) + ".whl"
-
-    if original_wheel_name != final_wheel_name:
-        del info["Tag"], info["Build"]
-        for a, b, c in itertools.product(
-            final_python_tags, final_abi_tags, final_plat_tags
-        ):
-            info["Tag"] = f"{a}-{b}-{c}"
-        if build:
-            info["Build"] = build
-
-        original_wheel_path = os.path.join(
-            os.path.dirname(f.filename), original_wheel_name
-        )
-        final_wheel_path = os.path.join(os.path.dirname(f.filename), final_wheel_name)
-
-        with WheelFile(original_wheel_path, "r") as fin, WheelFile(
-            final_wheel_path, "w"
-        ) as fout:
-            fout.comment = fin.comment  # preserve the comment
-            for item in fin.infolist():
-                if item.is_dir():
-                    continue
-                if item.filename == f.dist_info_path + "/RECORD":
-                    continue
-                if item.filename == f.dist_info_path + "/WHEEL":
-                    fout.writestr(item, info.as_bytes())
-                else:
-                    fout.writestr(item, fin.read(item))
-
-        if remove:
-            os.remove(original_wheel_path)
-
-    return final_wheel_name
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/unpack.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/unpack.py
deleted file mode 100644
index d48840e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/cli/unpack.py
+++ /dev/null
@@ -1,30 +0,0 @@
-from __future__ import annotations
-
-from pathlib import Path
-
-from ..wheelfile import WheelFile
-
-
-def unpack(path: str, dest: str = ".") -> None:
-    """Unpack a wheel.
-
-    Wheel content will be unpacked to {dest}/{name}-{ver}, where {name}
-    is the package name and {ver} its version.
-
-    :param path: The path to the wheel.
-    :param dest: Destination directory (default to current directory).
-    """
-    with WheelFile(path) as wf:
-        namever = wf.parsed_filename.group("namever")
-        destination = Path(dest) / namever
-        print(f"Unpacking to: {destination}...", end="", flush=True)
-        for zinfo in wf.filelist:
-            wf.extract(zinfo, destination)
-
-            # Set permissions to the same values as they were set in the archive
-            # We have to do this manually due to
-            # https://github.com/python/cpython/issues/59999
-            permissions = zinfo.external_attr >> 16 & 0o777
-            destination.joinpath(zinfo.filename).chmod(permissions)
-
-    print("OK")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/macosx_libfile.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/macosx_libfile.py
deleted file mode 100644
index abdfc9e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/macosx_libfile.py
+++ /dev/null
@@ -1,482 +0,0 @@
-"""
-This module contains function to analyse dynamic library
-headers to extract system information
-
-Currently only for MacOSX
-
-Library file on macosx system starts with Mach-O or Fat field.
-This can be distinguish by first 32 bites and it is called magic number.
-Proper value of magic number is with suffix _MAGIC. Suffix _CIGAM means
-reversed bytes order.
-Both fields can occur in two types: 32 and 64 bytes.
-
-FAT field inform that this library contains few version of library
-(typically for different types version). It contains
-information where Mach-O headers starts.
-
-Each section started with Mach-O header contains one library
-(So if file starts with this field it contains only one version).
-
-After filed Mach-O there are section fields.
-Each of them starts with two fields:
-cmd - magic number for this command
-cmdsize - total size occupied by this section information.
-
-In this case only sections LC_VERSION_MIN_MACOSX (for macosx 10.13 and earlier)
-and LC_BUILD_VERSION (for macosx 10.14 and newer) are interesting,
-because them contains information about minimal system version.
-
-Important remarks:
-- For fat files this implementation looks for maximum number version.
-  It not check if it is 32 or 64 and do not compare it with currently built package.
-  So it is possible to false report higher version that needed.
-- All structures signatures are taken form macosx header files.
-- I think that binary format will be more stable than `otool` output.
-  and if apple introduce some changes both implementation will need to be updated.
-- The system compile will set the deployment target no lower than
-  11.0 for arm64 builds. For "Universal 2" builds use the x86_64 deployment
-  target when the arm64 target is 11.0.
-"""
-
-from __future__ import annotations
-
-import ctypes
-import os
-import sys
-from io import BufferedIOBase
-from typing import TYPE_CHECKING
-
-if TYPE_CHECKING:
-    from typing import Union
-
-    StrPath = Union[str, os.PathLike[str]]
-
-"""here the needed const and struct from mach-o header files"""
-
-FAT_MAGIC = 0xCAFEBABE
-FAT_CIGAM = 0xBEBAFECA
-FAT_MAGIC_64 = 0xCAFEBABF
-FAT_CIGAM_64 = 0xBFBAFECA
-MH_MAGIC = 0xFEEDFACE
-MH_CIGAM = 0xCEFAEDFE
-MH_MAGIC_64 = 0xFEEDFACF
-MH_CIGAM_64 = 0xCFFAEDFE
-
-LC_VERSION_MIN_MACOSX = 0x24
-LC_BUILD_VERSION = 0x32
-
-CPU_TYPE_ARM64 = 0x0100000C
-
-mach_header_fields = [
-    ("magic", ctypes.c_uint32),
-    ("cputype", ctypes.c_int),
-    ("cpusubtype", ctypes.c_int),
-    ("filetype", ctypes.c_uint32),
-    ("ncmds", ctypes.c_uint32),
-    ("sizeofcmds", ctypes.c_uint32),
-    ("flags", ctypes.c_uint32),
-]
-"""
-struct mach_header {
-    uint32_t	magic;		/* mach magic number identifier */
-    cpu_type_t	cputype;	/* cpu specifier */
-    cpu_subtype_t	cpusubtype;	/* machine specifier */
-    uint32_t	filetype;	/* type of file */
-    uint32_t	ncmds;		/* number of load commands */
-    uint32_t	sizeofcmds;	/* the size of all the load commands */
-    uint32_t	flags;		/* flags */
-};
-typedef integer_t cpu_type_t;
-typedef integer_t cpu_subtype_t;
-"""
-
-mach_header_fields_64 = mach_header_fields + [("reserved", ctypes.c_uint32)]
-"""
-struct mach_header_64 {
-    uint32_t	magic;		/* mach magic number identifier */
-    cpu_type_t	cputype;	/* cpu specifier */
-    cpu_subtype_t	cpusubtype;	/* machine specifier */
-    uint32_t	filetype;	/* type of file */
-    uint32_t	ncmds;		/* number of load commands */
-    uint32_t	sizeofcmds;	/* the size of all the load commands */
-    uint32_t	flags;		/* flags */
-    uint32_t	reserved;	/* reserved */
-};
-"""
-
-fat_header_fields = [("magic", ctypes.c_uint32), ("nfat_arch", ctypes.c_uint32)]
-"""
-struct fat_header {
-    uint32_t	magic;		/* FAT_MAGIC or FAT_MAGIC_64 */
-    uint32_t	nfat_arch;	/* number of structs that follow */
-};
-"""
-
-fat_arch_fields = [
-    ("cputype", ctypes.c_int),
-    ("cpusubtype", ctypes.c_int),
-    ("offset", ctypes.c_uint32),
-    ("size", ctypes.c_uint32),
-    ("align", ctypes.c_uint32),
-]
-"""
-struct fat_arch {
-    cpu_type_t	cputype;	/* cpu specifier (int) */
-    cpu_subtype_t	cpusubtype;	/* machine specifier (int) */
-    uint32_t	offset;		/* file offset to this object file */
-    uint32_t	size;		/* size of this object file */
-    uint32_t	align;		/* alignment as a power of 2 */
-};
-"""
-
-fat_arch_64_fields = [
-    ("cputype", ctypes.c_int),
-    ("cpusubtype", ctypes.c_int),
-    ("offset", ctypes.c_uint64),
-    ("size", ctypes.c_uint64),
-    ("align", ctypes.c_uint32),
-    ("reserved", ctypes.c_uint32),
-]
-"""
-struct fat_arch_64 {
-    cpu_type_t	cputype;	/* cpu specifier (int) */
-    cpu_subtype_t	cpusubtype;	/* machine specifier (int) */
-    uint64_t	offset;		/* file offset to this object file */
-    uint64_t	size;		/* size of this object file */
-    uint32_t	align;		/* alignment as a power of 2 */
-    uint32_t	reserved;	/* reserved */
-};
-"""
-
-segment_base_fields = [("cmd", ctypes.c_uint32), ("cmdsize", ctypes.c_uint32)]
-"""base for reading segment info"""
-
-segment_command_fields = [
-    ("cmd", ctypes.c_uint32),
-    ("cmdsize", ctypes.c_uint32),
-    ("segname", ctypes.c_char * 16),
-    ("vmaddr", ctypes.c_uint32),
-    ("vmsize", ctypes.c_uint32),
-    ("fileoff", ctypes.c_uint32),
-    ("filesize", ctypes.c_uint32),
-    ("maxprot", ctypes.c_int),
-    ("initprot", ctypes.c_int),
-    ("nsects", ctypes.c_uint32),
-    ("flags", ctypes.c_uint32),
-]
-"""
-struct segment_command { /* for 32-bit architectures */
-    uint32_t	cmd;		/* LC_SEGMENT */
-    uint32_t	cmdsize;	/* includes sizeof section structs */
-    char		segname[16];	/* segment name */
-    uint32_t	vmaddr;		/* memory address of this segment */
-    uint32_t	vmsize;		/* memory size of this segment */
-    uint32_t	fileoff;	/* file offset of this segment */
-    uint32_t	filesize;	/* amount to map from the file */
-    vm_prot_t	maxprot;	/* maximum VM protection */
-    vm_prot_t	initprot;	/* initial VM protection */
-    uint32_t	nsects;		/* number of sections in segment */
-    uint32_t	flags;		/* flags */
-};
-typedef int vm_prot_t;
-"""
-
-segment_command_fields_64 = [
-    ("cmd", ctypes.c_uint32),
-    ("cmdsize", ctypes.c_uint32),
-    ("segname", ctypes.c_char * 16),
-    ("vmaddr", ctypes.c_uint64),
-    ("vmsize", ctypes.c_uint64),
-    ("fileoff", ctypes.c_uint64),
-    ("filesize", ctypes.c_uint64),
-    ("maxprot", ctypes.c_int),
-    ("initprot", ctypes.c_int),
-    ("nsects", ctypes.c_uint32),
-    ("flags", ctypes.c_uint32),
-]
-"""
-struct segment_command_64 { /* for 64-bit architectures */
-    uint32_t	cmd;		/* LC_SEGMENT_64 */
-    uint32_t	cmdsize;	/* includes sizeof section_64 structs */
-    char		segname[16];	/* segment name */
-    uint64_t	vmaddr;		/* memory address of this segment */
-    uint64_t	vmsize;		/* memory size of this segment */
-    uint64_t	fileoff;	/* file offset of this segment */
-    uint64_t	filesize;	/* amount to map from the file */
-    vm_prot_t	maxprot;	/* maximum VM protection */
-    vm_prot_t	initprot;	/* initial VM protection */
-    uint32_t	nsects;		/* number of sections in segment */
-    uint32_t	flags;		/* flags */
-};
-"""
-
-version_min_command_fields = segment_base_fields + [
-    ("version", ctypes.c_uint32),
-    ("sdk", ctypes.c_uint32),
-]
-"""
-struct version_min_command {
-    uint32_t	cmd;		/* LC_VERSION_MIN_MACOSX or
-                               LC_VERSION_MIN_IPHONEOS or
-                               LC_VERSION_MIN_WATCHOS or
-                               LC_VERSION_MIN_TVOS */
-    uint32_t	cmdsize;	/* sizeof(struct min_version_command) */
-    uint32_t	version;	/* X.Y.Z is encoded in nibbles xxxx.yy.zz */
-    uint32_t	sdk;		/* X.Y.Z is encoded in nibbles xxxx.yy.zz */
-};
-"""
-
-build_version_command_fields = segment_base_fields + [
-    ("platform", ctypes.c_uint32),
-    ("minos", ctypes.c_uint32),
-    ("sdk", ctypes.c_uint32),
-    ("ntools", ctypes.c_uint32),
-]
-"""
-struct build_version_command {
-    uint32_t	cmd;		/* LC_BUILD_VERSION */
-    uint32_t	cmdsize;	/* sizeof(struct build_version_command) plus */
-                                /* ntools * sizeof(struct build_tool_version) */
-    uint32_t	platform;	/* platform */
-    uint32_t	minos;		/* X.Y.Z is encoded in nibbles xxxx.yy.zz */
-    uint32_t	sdk;		/* X.Y.Z is encoded in nibbles xxxx.yy.zz */
-    uint32_t	ntools;		/* number of tool entries following this */
-};
-"""
-
-
-def swap32(x: int) -> int:
-    return (
-        ((x << 24) & 0xFF000000)
-        | ((x << 8) & 0x00FF0000)
-        | ((x >> 8) & 0x0000FF00)
-        | ((x >> 24) & 0x000000FF)
-    )
-
-
-def get_base_class_and_magic_number(
-    lib_file: BufferedIOBase,
-    seek: int | None = None,
-) -> tuple[type[ctypes.Structure], int]:
-    if seek is None:
-        seek = lib_file.tell()
-    else:
-        lib_file.seek(seek)
-    magic_number = ctypes.c_uint32.from_buffer_copy(
-        lib_file.read(ctypes.sizeof(ctypes.c_uint32))
-    ).value
-
-    # Handle wrong byte order
-    if magic_number in [FAT_CIGAM, FAT_CIGAM_64, MH_CIGAM, MH_CIGAM_64]:
-        if sys.byteorder == "little":
-            BaseClass = ctypes.BigEndianStructure
-        else:
-            BaseClass = ctypes.LittleEndianStructure
-
-        magic_number = swap32(magic_number)
-    else:
-        BaseClass = ctypes.Structure
-
-    lib_file.seek(seek)
-    return BaseClass, magic_number
-
-
-def read_data(struct_class: type[ctypes.Structure], lib_file: BufferedIOBase):
-    return struct_class.from_buffer_copy(lib_file.read(ctypes.sizeof(struct_class)))
-
-
-def extract_macosx_min_system_version(path_to_lib: str):
-    with open(path_to_lib, "rb") as lib_file:
-        BaseClass, magic_number = get_base_class_and_magic_number(lib_file, 0)
-        if magic_number not in [FAT_MAGIC, FAT_MAGIC_64, MH_MAGIC, MH_MAGIC_64]:
-            return
-
-        if magic_number in [FAT_MAGIC, FAT_CIGAM_64]:
-
-            class FatHeader(BaseClass):
-                _fields_ = fat_header_fields
-
-            fat_header = read_data(FatHeader, lib_file)
-            if magic_number == FAT_MAGIC:
-
-                class FatArch(BaseClass):
-                    _fields_ = fat_arch_fields
-
-            else:
-
-                class FatArch(BaseClass):
-                    _fields_ = fat_arch_64_fields
-
-            fat_arch_list = [
-                read_data(FatArch, lib_file) for _ in range(fat_header.nfat_arch)
-            ]
-
-            versions_list: list[tuple[int, int, int]] = []
-            for el in fat_arch_list:
-                try:
-                    version = read_mach_header(lib_file, el.offset)
-                    if version is not None:
-                        if el.cputype == CPU_TYPE_ARM64 and len(fat_arch_list) != 1:
-                            # Xcode will not set the deployment target below 11.0.0
-                            # for the arm64 architecture. Ignore the arm64 deployment
-                            # in fat binaries when the target is 11.0.0, that way
-                            # the other architectures can select a lower deployment
-                            # target.
-                            # This is safe because there is no arm64 variant for
-                            # macOS 10.15 or earlier.
-                            if version == (11, 0, 0):
-                                continue
-                        versions_list.append(version)
-                except ValueError:
-                    pass
-
-            if len(versions_list) > 0:
-                return max(versions_list)
-            else:
-                return None
-
-        else:
-            try:
-                return read_mach_header(lib_file, 0)
-            except ValueError:
-                """when some error during read library files"""
-                return None
-
-
-def read_mach_header(
-    lib_file: BufferedIOBase,
-    seek: int | None = None,
-) -> tuple[int, int, int] | None:
-    """
-    This function parses a Mach-O header and extracts
-    information about the minimal macOS version.
-
-    :param lib_file: reference to opened library file with pointer
-    """
-    base_class, magic_number = get_base_class_and_magic_number(lib_file, seek)
-    arch = "32" if magic_number == MH_MAGIC else "64"
-
-    class SegmentBase(base_class):
-        _fields_ = segment_base_fields
-
-    if arch == "32":
-
-        class MachHeader(base_class):
-            _fields_ = mach_header_fields
-
-    else:
-
-        class MachHeader(base_class):
-            _fields_ = mach_header_fields_64
-
-    mach_header = read_data(MachHeader, lib_file)
-    for _i in range(mach_header.ncmds):
-        pos = lib_file.tell()
-        segment_base = read_data(SegmentBase, lib_file)
-        lib_file.seek(pos)
-        if segment_base.cmd == LC_VERSION_MIN_MACOSX:
-
-            class VersionMinCommand(base_class):
-                _fields_ = version_min_command_fields
-
-            version_info = read_data(VersionMinCommand, lib_file)
-            return parse_version(version_info.version)
-        elif segment_base.cmd == LC_BUILD_VERSION:
-
-            class VersionBuild(base_class):
-                _fields_ = build_version_command_fields
-
-            version_info = read_data(VersionBuild, lib_file)
-            return parse_version(version_info.minos)
-        else:
-            lib_file.seek(pos + segment_base.cmdsize)
-            continue
-
-
-def parse_version(version: int) -> tuple[int, int, int]:
-    x = (version & 0xFFFF0000) >> 16
-    y = (version & 0x0000FF00) >> 8
-    z = version & 0x000000FF
-    return x, y, z
-
-
-def calculate_macosx_platform_tag(archive_root: StrPath, platform_tag: str) -> str:
-    """
-    Calculate proper macosx platform tag basing on files which are included to wheel
-
-    Example platform tag `macosx-10.14-x86_64`
-    """
-    prefix, base_version, suffix = platform_tag.split("-")
-    base_version = tuple(int(x) for x in base_version.split("."))
-    base_version = base_version[:2]
-    if base_version[0] > 10:
-        base_version = (base_version[0], 0)
-    assert len(base_version) == 2
-    if "MACOSX_DEPLOYMENT_TARGET" in os.environ:
-        deploy_target = tuple(
-            int(x) for x in os.environ["MACOSX_DEPLOYMENT_TARGET"].split(".")
-        )
-        deploy_target = deploy_target[:2]
-        if deploy_target[0] > 10:
-            deploy_target = (deploy_target[0], 0)
-        if deploy_target < base_version:
-            sys.stderr.write(
-                "[WARNING] MACOSX_DEPLOYMENT_TARGET is set to a lower value ({}) than "
-                "the version on which the Python interpreter was compiled ({}), and "
-                "will be ignored.\n".format(
-                    ".".join(str(x) for x in deploy_target),
-                    ".".join(str(x) for x in base_version),
-                )
-            )
-        else:
-            base_version = deploy_target
-
-    assert len(base_version) == 2
-    start_version = base_version
-    versions_dict: dict[str, tuple[int, int]] = {}
-    for dirpath, _dirnames, filenames in os.walk(archive_root):
-        for filename in filenames:
-            if filename.endswith(".dylib") or filename.endswith(".so"):
-                lib_path = os.path.join(dirpath, filename)
-                min_ver = extract_macosx_min_system_version(lib_path)
-                if min_ver is not None:
-                    min_ver = min_ver[0:2]
-                    if min_ver[0] > 10:
-                        min_ver = (min_ver[0], 0)
-                    versions_dict[lib_path] = min_ver
-
-    if len(versions_dict) > 0:
-        base_version = max(base_version, max(versions_dict.values()))
-
-    # macosx platform tag do not support minor bugfix release
-    fin_base_version = "_".join([str(x) for x in base_version])
-    if start_version < base_version:
-        problematic_files = [k for k, v in versions_dict.items() if v > start_version]
-        problematic_files = "\n".join(problematic_files)
-        if len(problematic_files) == 1:
-            files_form = "this file"
-        else:
-            files_form = "these files"
-        error_message = (
-            "[WARNING] This wheel needs a higher macOS version than {}  "
-            "To silence this warning, set MACOSX_DEPLOYMENT_TARGET to at least "
-            + fin_base_version
-            + " or recreate "
-            + files_form
-            + " with lower "
-            "MACOSX_DEPLOYMENT_TARGET:  \n" + problematic_files
-        )
-
-        if "MACOSX_DEPLOYMENT_TARGET" in os.environ:
-            error_message = error_message.format(
-                "is set in MACOSX_DEPLOYMENT_TARGET variable."
-            )
-        else:
-            error_message = error_message.format(
-                "the version your Python interpreter is compiled against."
-            )
-
-        sys.stderr.write(error_message)
-
-    platform_tag = prefix + "_" + fin_base_version + "_" + suffix
-    return platform_tag
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/metadata.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/metadata.py
deleted file mode 100644
index b8098fa..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/metadata.py
+++ /dev/null
@@ -1,183 +0,0 @@
-"""
-Tools for converting old- to new-style metadata.
-"""
-
-from __future__ import annotations
-
-import functools
-import itertools
-import os.path
-import re
-import textwrap
-from email.message import Message
-from email.parser import Parser
-from typing import Generator, Iterable, Iterator, Literal
-
-from .vendored.packaging.requirements import Requirement
-
-
-def _nonblank(str: str) -> bool | Literal[""]:
-    return str and not str.startswith("#")
-
-
-@functools.singledispatch
-def yield_lines(iterable: Iterable[str]) -> Iterator[str]:
-    r"""
-    Yield valid lines of a string or iterable.
-    >>> list(yield_lines(''))
-    []
-    >>> list(yield_lines(['foo', 'bar']))
-    ['foo', 'bar']
-    >>> list(yield_lines('foo\nbar'))
-    ['foo', 'bar']
-    >>> list(yield_lines('\nfoo\n#bar\nbaz #comment'))
-    ['foo', 'baz #comment']
-    >>> list(yield_lines(['foo\nbar', 'baz', 'bing\n\n\n']))
-    ['foo', 'bar', 'baz', 'bing']
-    """
-    return itertools.chain.from_iterable(map(yield_lines, iterable))
-
-
-@yield_lines.register(str)
-def _(text: str) -> Iterator[str]:
-    return filter(_nonblank, map(str.strip, text.splitlines()))
-
-
-def split_sections(
-    s: str | Iterator[str],
-) -> Generator[tuple[str | None, list[str]], None, None]:
-    """Split a string or iterable thereof into (section, content) pairs
-    Each ``section`` is a stripped version of the section header ("[section]")
-    and each ``content`` is a list of stripped lines excluding blank lines and
-    comment-only lines.  If there are any such lines before the first section
-    header, they're returned in a first ``section`` of ``None``.
-    """
-    section = None
-    content: list[str] = []
-    for line in yield_lines(s):
-        if line.startswith("["):
-            if line.endswith("]"):
-                if section or content:
-                    yield section, content
-                section = line[1:-1].strip()
-                content = []
-            else:
-                raise ValueError("Invalid section heading", line)
-        else:
-            content.append(line)
-
-    # wrap up last segment
-    yield section, content
-
-
-def safe_extra(extra: str) -> str:
-    """Convert an arbitrary string to a standard 'extra' name
-    Any runs of non-alphanumeric characters are replaced with a single '_',
-    and the result is always lowercased.
-    """
-    return re.sub("[^A-Za-z0-9.-]+", "_", extra).lower()
-
-
-def safe_name(name: str) -> str:
-    """Convert an arbitrary string to a standard distribution name
-    Any runs of non-alphanumeric/. characters are replaced with a single '-'.
-    """
-    return re.sub("[^A-Za-z0-9.]+", "-", name)
-
-
-def requires_to_requires_dist(requirement: Requirement) -> str:
-    """Return the version specifier for a requirement in PEP 345/566 fashion."""
-    if requirement.url:
-        return " @ " + requirement.url
-
-    requires_dist: list[str] = []
-    for spec in requirement.specifier:
-        requires_dist.append(spec.operator + spec.version)
-
-    if requires_dist:
-        return " " + ",".join(sorted(requires_dist))
-    else:
-        return ""
-
-
-def convert_requirements(requirements: list[str]) -> Iterator[str]:
-    """Yield Requires-Dist: strings for parsed requirements strings."""
-    for req in requirements:
-        parsed_requirement = Requirement(req)
-        spec = requires_to_requires_dist(parsed_requirement)
-        extras = ",".join(sorted(safe_extra(e) for e in parsed_requirement.extras))
-        if extras:
-            extras = f"[{extras}]"
-
-        yield safe_name(parsed_requirement.name) + extras + spec
-
-
-def generate_requirements(
-    extras_require: dict[str | None, list[str]],
-) -> Iterator[tuple[str, str]]:
-    """
-    Convert requirements from a setup()-style dictionary to
-    ('Requires-Dist', 'requirement') and ('Provides-Extra', 'extra') tuples.
-
-    extras_require is a dictionary of {extra: [requirements]} as passed to setup(),
-    using the empty extra {'': [requirements]} to hold install_requires.
-    """
-    for extra, depends in extras_require.items():
-        condition = ""
-        extra = extra or ""
-        if ":" in extra:  # setuptools extra:condition syntax
-            extra, condition = extra.split(":", 1)
-
-        extra = safe_extra(extra)
-        if extra:
-            yield "Provides-Extra", extra
-            if condition:
-                condition = "(" + condition + ") and "
-            condition += f"extra == '{extra}'"
-
-        if condition:
-            condition = " ; " + condition
-
-        for new_req in convert_requirements(depends):
-            canonical_req = str(Requirement(new_req + condition))
-            yield "Requires-Dist", canonical_req
-
-
-def pkginfo_to_metadata(egg_info_path: str, pkginfo_path: str) -> Message:
-    """
-    Convert .egg-info directory with PKG-INFO to the Metadata 2.1 format
-    """
-    with open(pkginfo_path, encoding="utf-8") as headers:
-        pkg_info = Parser().parse(headers)
-
-    pkg_info.replace_header("Metadata-Version", "2.1")
-    # Those will be regenerated from `requires.txt`.
-    del pkg_info["Provides-Extra"]
-    del pkg_info["Requires-Dist"]
-    requires_path = os.path.join(egg_info_path, "requires.txt")
-    if os.path.exists(requires_path):
-        with open(requires_path, encoding="utf-8") as requires_file:
-            requires = requires_file.read()
-
-        parsed_requirements = sorted(split_sections(requires), key=lambda x: x[0] or "")
-        for extra, reqs in parsed_requirements:
-            for key, value in generate_requirements({extra: reqs}):
-                if (key, value) not in pkg_info.items():
-                    pkg_info[key] = value
-
-    description = pkg_info["Description"]
-    if description:
-        description_lines = pkg_info["Description"].splitlines()
-        dedented_description = "\n".join(
-            # if the first line of long_description is blank,
-            # the first line here will be indented.
-            (
-                description_lines[0].lstrip(),
-                textwrap.dedent("\n".join(description_lines[1:])),
-                "\n",
-            )
-        )
-        pkg_info.set_payload(dedented_description)
-        del pkg_info["Description"]
-
-    return pkg_info
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/util.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/util.py
deleted file mode 100644
index c928aa4..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/util.py
+++ /dev/null
@@ -1,17 +0,0 @@
-from __future__ import annotations
-
-import base64
-import logging
-
-log = logging.getLogger("wheel")
-
-
-def urlsafe_b64encode(data: bytes) -> bytes:
-    """urlsafe_b64encode without padding"""
-    return base64.urlsafe_b64encode(data).rstrip(b"=")
-
-
-def urlsafe_b64decode(data: bytes) -> bytes:
-    """urlsafe_b64decode without padding"""
-    pad = b"=" * (4 - (len(data) & 3))
-    return base64.urlsafe_b64decode(data + pad)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 1cc7db0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE
deleted file mode 100644
index 6f62d44..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE
+++ /dev/null
@@ -1,3 +0,0 @@
-This software is made available under the terms of *either* of the licenses
-found in LICENSE.APACHE or LICENSE.BSD. Contributions to this software is made
-under the terms of *both* these licenses.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE.APACHE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE.APACHE
deleted file mode 100644
index f433b1a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE.APACHE
+++ /dev/null
@@ -1,177 +0,0 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE.BSD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE.BSD
deleted file mode 100644
index 42ce7b7..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/LICENSE.BSD
+++ /dev/null
@@ -1,23 +0,0 @@
-Copyright (c) Donald Stufft and individual contributors.
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-    1. Redistributions of source code must retain the above copyright notice,
-       this list of conditions and the following disclaimer.
-
-    2. Redistributions in binary form must reproduce the above copyright
-       notice, this list of conditions and the following disclaimer in the
-       documentation and/or other materials provided with the distribution.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
-FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index c783afb..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_elffile.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_elffile.cpython-312.pyc
deleted file mode 100644
index 7cbb478..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_elffile.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_manylinux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_manylinux.cpython-312.pyc
deleted file mode 100644
index d34944e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_manylinux.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_musllinux.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_musllinux.cpython-312.pyc
deleted file mode 100644
index 9d851c1..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_musllinux.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_parser.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_parser.cpython-312.pyc
deleted file mode 100644
index b1366e4..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_parser.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_structures.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_structures.cpython-312.pyc
deleted file mode 100644
index 703d8dd..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_structures.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_tokenizer.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_tokenizer.cpython-312.pyc
deleted file mode 100644
index 1016429..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/_tokenizer.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/markers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/markers.cpython-312.pyc
deleted file mode 100644
index c27a091..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/markers.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/requirements.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/requirements.cpython-312.pyc
deleted file mode 100644
index ed35542..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/requirements.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/specifiers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/specifiers.cpython-312.pyc
deleted file mode 100644
index f5110d0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/specifiers.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/tags.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/tags.cpython-312.pyc
deleted file mode 100644
index 4203e07..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/tags.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/utils.cpython-312.pyc
deleted file mode 100644
index 373b56c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/utils.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/version.cpython-312.pyc
deleted file mode 100644
index d326ed6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/__pycache__/version.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_elffile.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_elffile.py
deleted file mode 100644
index 6fb19b3..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_elffile.py
+++ /dev/null
@@ -1,108 +0,0 @@
-"""
-ELF file parser.
-
-This provides a class ``ELFFile`` that parses an ELF executable in a similar
-interface to ``ZipFile``. Only the read interface is implemented.
-
-Based on: https://gist.github.com/lyssdod/f51579ae8d93c8657a5564aefc2ffbca
-ELF header: https://refspecs.linuxfoundation.org/elf/gabi4+/ch4.eheader.html
-"""
-
-import enum
-import os
-import struct
-from typing import IO, Optional, Tuple
-
-
-class ELFInvalid(ValueError):
-    pass
-
-
-class EIClass(enum.IntEnum):
-    C32 = 1
-    C64 = 2
-
-
-class EIData(enum.IntEnum):
-    Lsb = 1
-    Msb = 2
-
-
-class EMachine(enum.IntEnum):
-    I386 = 3
-    S390 = 22
-    Arm = 40
-    X8664 = 62
-    AArc64 = 183
-
-
-class ELFFile:
-    """
-    Representation of an ELF executable.
-    """
-
-    def __init__(self, f: IO[bytes]) -> None:
-        self._f = f
-
-        try:
-            ident = self._read("16B")
-        except struct.error:
-            raise ELFInvalid("unable to parse identification")
-        magic = bytes(ident[:4])
-        if magic != b"\x7fELF":
-            raise ELFInvalid(f"invalid magic: {magic!r}")
-
-        self.capacity = ident[4]  # Format for program header (bitness).
-        self.encoding = ident[5]  # Data structure encoding (endianness).
-
-        try:
-            # e_fmt: Format for program header.
-            # p_fmt: Format for section header.
-            # p_idx: Indexes to find p_type, p_offset, and p_filesz.
-            e_fmt, self._p_fmt, self._p_idx = {
-                (1, 1): ("HHIIIIIHHH", ">IIIIIIII", (0, 1, 4)),  # 32-bit MSB.
-                (2, 1): ("HHIQQQIHHH", ">IIQQQQQQ", (0, 2, 5)),  # 64-bit MSB.
-            }[(self.capacity, self.encoding)]
-        except KeyError:
-            raise ELFInvalid(
-                f"unrecognized capacity ({self.capacity}) or "
-                f"encoding ({self.encoding})"
-            )
-
-        try:
-            (
-                _,
-                self.machine,  # Architecture type.
-                _,
-                _,
-                self._e_phoff,  # Offset of program header.
-                _,
-                self.flags,  # Processor-specific flags.
-                _,
-                self._e_phentsize,  # Size of section.
-                self._e_phnum,  # Number of sections.
-            ) = self._read(e_fmt)
-        except struct.error as e:
-            raise ELFInvalid("unable to parse machine and section information") from e
-
-    def _read(self, fmt: str) -> Tuple[int, ...]:
-        return struct.unpack(fmt, self._f.read(struct.calcsize(fmt)))
-
-    @property
-    def interpreter(self) -> Optional[str]:
-        """
-        The path recorded in the ``PT_INTERP`` section header.
-        """
-        for index in range(self._e_phnum):
-            self._f.seek(self._e_phoff + self._e_phentsize * index)
-            try:
-                data = self._read(self._p_fmt)
-            except struct.error:
-                continue
-            if data[self._p_idx[0]] != 3:  # Not PT_INTERP.
-                continue
-            self._f.seek(data[self._p_idx[1]])
-            return os.fsdecode(self._f.read(data[self._p_idx[2]])).strip("\0")
-        return None
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_manylinux.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_manylinux.py
deleted file mode 100644
index 1f5f4ab..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_manylinux.py
+++ /dev/null
@@ -1,260 +0,0 @@
-import collections
-import contextlib
-import functools
-import os
-import re
-import sys
-import warnings
-from typing import Dict, Generator, Iterator, NamedTuple, Optional, Sequence, Tuple
-
-from ._elffile import EIClass, EIData, ELFFile, EMachine
-
-EF_ARM_ABIMASK = 0xFF000000
-EF_ARM_ABI_VER5 = 0x05000000
-EF_ARM_ABI_FLOAT_HARD = 0x00000400
-
-
-# `os.PathLike` not a generic type until Python 3.9, so sticking with `str`
-# as the type for `path` until then.
-@contextlib.contextmanager
-def _parse_elf(path: str) -> Generator[Optional[ELFFile], None, None]:
-    try:
-        with open(path, "rb") as f:
-            yield ELFFile(f)
-    except (OSError, TypeError, ValueError):
-        yield None
-
-
-def _is_linux_armhf(executable: str) -> bool:
-    # hard-float ABI can be detected from the ELF header of the running
-    # process
-    # https://static.docs.arm.com/ihi0044/g/aaelf32.pdf
-    with _parse_elf(executable) as f:
-        return (
-            f is not None
-            and f.capacity == EIClass.C32
-            and f.encoding == EIData.Lsb
-            and f.machine == EMachine.Arm
-            and f.flags & EF_ARM_ABIMASK == EF_ARM_ABI_VER5
-            and f.flags & EF_ARM_ABI_FLOAT_HARD == EF_ARM_ABI_FLOAT_HARD
-        )
-
-
-def _is_linux_i686(executable: str) -> bool:
-    with _parse_elf(executable) as f:
-        return (
-            f is not None
-            and f.capacity == EIClass.C32
-            and f.encoding == EIData.Lsb
-            and f.machine == EMachine.I386
-        )
-
-
-def _have_compatible_abi(executable: str, archs: Sequence[str]) -> bool:
-    if "armv7l" in archs:
-        return _is_linux_armhf(executable)
-    if "i686" in archs:
-        return _is_linux_i686(executable)
-    allowed_archs = {
-        "x86_64",
-        "aarch64",
-        "ppc64",
-        "ppc64le",
-        "s390x",
-        "loongarch64",
-        "riscv64",
-    }
-    return any(arch in allowed_archs for arch in archs)
-
-
-# If glibc ever changes its major version, we need to know what the last
-# minor version was, so we can build the complete list of all versions.
-# For now, guess what the highest minor version might be, assume it will
-# be 50 for testing. Once this actually happens, update the dictionary
-# with the actual value.
-_LAST_GLIBC_MINOR: Dict[int, int] = collections.defaultdict(lambda: 50)
-
-
-class _GLibCVersion(NamedTuple):
-    major: int
-    minor: int
-
-
-def _glibc_version_string_confstr() -> Optional[str]:
-    """
-    Primary implementation of glibc_version_string using os.confstr.
-    """
-    # os.confstr is quite a bit faster than ctypes.DLL. It's also less likely
-    # to be broken or missing. This strategy is used in the standard library
-    # platform module.
-    # https://github.com/python/cpython/blob/fcf1d003bf4f0100c/Lib/platform.py#L175-L183
-    try:
-        # Should be a string like "glibc 2.17".
-        version_string: Optional[str] = os.confstr("CS_GNU_LIBC_VERSION")
-        assert version_string is not None
-        _, version = version_string.rsplit()
-    except (AssertionError, AttributeError, OSError, ValueError):
-        # os.confstr() or CS_GNU_LIBC_VERSION not available (or a bad value)...
-        return None
-    return version
-
-
-def _glibc_version_string_ctypes() -> Optional[str]:
-    """
-    Fallback implementation of glibc_version_string using ctypes.
-    """
-    try:
-        import ctypes
-    except ImportError:
-        return None
-
-    # ctypes.CDLL(None) internally calls dlopen(NULL), and as the dlopen
-    # manpage says, "If filename is NULL, then the returned handle is for the
-    # main program". This way we can let the linker do the work to figure out
-    # which libc our process is actually using.
-    #
-    # We must also handle the special case where the executable is not a
-    # dynamically linked executable. This can occur when using musl libc,
-    # for example. In this situation, dlopen() will error, leading to an
-    # OSError. Interestingly, at least in the case of musl, there is no
-    # errno set on the OSError. The single string argument used to construct
-    # OSError comes from libc itself and is therefore not portable to
-    # hard code here. In any case, failure to call dlopen() means we
-    # can proceed, so we bail on our attempt.
-    try:
-        process_namespace = ctypes.CDLL(None)
-    except OSError:
-        return None
-
-    try:
-        gnu_get_libc_version = process_namespace.gnu_get_libc_version
-    except AttributeError:
-        # Symbol doesn't exist -> therefore, we are not linked to
-        # glibc.
-        return None
-
-    # Call gnu_get_libc_version, which returns a string like "2.5"
-    gnu_get_libc_version.restype = ctypes.c_char_p
-    version_str: str = gnu_get_libc_version()
-    # py2 / py3 compatibility:
-    if not isinstance(version_str, str):
-        version_str = version_str.decode("ascii")
-
-    return version_str
-
-
-def _glibc_version_string() -> Optional[str]:
-    """Returns glibc version string, or None if not using glibc."""
-    return _glibc_version_string_confstr() or _glibc_version_string_ctypes()
-
-
-def _parse_glibc_version(version_str: str) -> Tuple[int, int]:
-    """Parse glibc version.
-
-    We use a regexp instead of str.split because we want to discard any
-    random junk that might come after the minor version -- this might happen
-    in patched/forked versions of glibc (e.g. Linaro's version of glibc
-    uses version strings like "2.20-2014.11"). See gh-3588.
-    """
-    m = re.match(r"(?P[0-9]+)\.(?P[0-9]+)", version_str)
-    if not m:
-        warnings.warn(
-            f"Expected glibc version with 2 components major.minor,"
-            f" got: {version_str}",
-            RuntimeWarning,
-        )
-        return -1, -1
-    return int(m.group("major")), int(m.group("minor"))
-
-
-@functools.lru_cache
-def _get_glibc_version() -> Tuple[int, int]:
-    version_str = _glibc_version_string()
-    if version_str is None:
-        return (-1, -1)
-    return _parse_glibc_version(version_str)
-
-
-# From PEP 513, PEP 600
-def _is_compatible(arch: str, version: _GLibCVersion) -> bool:
-    sys_glibc = _get_glibc_version()
-    if sys_glibc < version:
-        return False
-    # Check for presence of _manylinux module.
-    try:
-        import _manylinux
-    except ImportError:
-        return True
-    if hasattr(_manylinux, "manylinux_compatible"):
-        result = _manylinux.manylinux_compatible(version[0], version[1], arch)
-        if result is not None:
-            return bool(result)
-        return True
-    if version == _GLibCVersion(2, 5):
-        if hasattr(_manylinux, "manylinux1_compatible"):
-            return bool(_manylinux.manylinux1_compatible)
-    if version == _GLibCVersion(2, 12):
-        if hasattr(_manylinux, "manylinux2010_compatible"):
-            return bool(_manylinux.manylinux2010_compatible)
-    if version == _GLibCVersion(2, 17):
-        if hasattr(_manylinux, "manylinux2014_compatible"):
-            return bool(_manylinux.manylinux2014_compatible)
-    return True
-
-
-_LEGACY_MANYLINUX_MAP = {
-    # CentOS 7 w/ glibc 2.17 (PEP 599)
-    (2, 17): "manylinux2014",
-    # CentOS 6 w/ glibc 2.12 (PEP 571)
-    (2, 12): "manylinux2010",
-    # CentOS 5 w/ glibc 2.5 (PEP 513)
-    (2, 5): "manylinux1",
-}
-
-
-def platform_tags(archs: Sequence[str]) -> Iterator[str]:
-    """Generate manylinux tags compatible to the current platform.
-
-    :param archs: Sequence of compatible architectures.
-        The first one shall be the closest to the actual architecture and be the part of
-        platform tag after the ``linux_`` prefix, e.g. ``x86_64``.
-        The ``linux_`` prefix is assumed as a prerequisite for the current platform to
-        be manylinux-compatible.
-
-    :returns: An iterator of compatible manylinux tags.
-    """
-    if not _have_compatible_abi(sys.executable, archs):
-        return
-    # Oldest glibc to be supported regardless of architecture is (2, 17).
-    too_old_glibc2 = _GLibCVersion(2, 16)
-    if set(archs) & {"x86_64", "i686"}:
-        # On x86/i686 also oldest glibc to be supported is (2, 5).
-        too_old_glibc2 = _GLibCVersion(2, 4)
-    current_glibc = _GLibCVersion(*_get_glibc_version())
-    glibc_max_list = [current_glibc]
-    # We can assume compatibility across glibc major versions.
-    # https://sourceware.org/bugzilla/show_bug.cgi?id=24636
-    #
-    # Build a list of maximum glibc versions so that we can
-    # output the canonical list of all glibc from current_glibc
-    # down to too_old_glibc2, including all intermediary versions.
-    for glibc_major in range(current_glibc.major - 1, 1, -1):
-        glibc_minor = _LAST_GLIBC_MINOR[glibc_major]
-        glibc_max_list.append(_GLibCVersion(glibc_major, glibc_minor))
-    for arch in archs:
-        for glibc_max in glibc_max_list:
-            if glibc_max.major == too_old_glibc2.major:
-                min_minor = too_old_glibc2.minor
-            else:
-                # For other glibc major versions oldest supported is (x, 0).
-                min_minor = -1
-            for glibc_minor in range(glibc_max.minor, min_minor, -1):
-                glibc_version = _GLibCVersion(glibc_max.major, glibc_minor)
-                tag = "manylinux_{}_{}".format(*glibc_version)
-                if _is_compatible(arch, glibc_version):
-                    yield f"{tag}_{arch}"
-                # Handle the legacy manylinux1, manylinux2010, manylinux2014 tags.
-                if glibc_version in _LEGACY_MANYLINUX_MAP:
-                    legacy_tag = _LEGACY_MANYLINUX_MAP[glibc_version]
-                    if _is_compatible(arch, glibc_version):
-                        yield f"{legacy_tag}_{arch}"
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_musllinux.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_musllinux.py
deleted file mode 100644
index eb4251b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_musllinux.py
+++ /dev/null
@@ -1,83 +0,0 @@
-"""PEP 656 support.
-
-This module implements logic to detect if the currently running Python is
-linked against musl, and what musl version is used.
-"""
-
-import functools
-import re
-import subprocess
-import sys
-from typing import Iterator, NamedTuple, Optional, Sequence
-
-from ._elffile import ELFFile
-
-
-class _MuslVersion(NamedTuple):
-    major: int
-    minor: int
-
-
-def _parse_musl_version(output: str) -> Optional[_MuslVersion]:
-    lines = [n for n in (n.strip() for n in output.splitlines()) if n]
-    if len(lines) < 2 or lines[0][:4] != "musl":
-        return None
-    m = re.match(r"Version (\d+)\.(\d+)", lines[1])
-    if not m:
-        return None
-    return _MuslVersion(major=int(m.group(1)), minor=int(m.group(2)))
-
-
-@functools.lru_cache
-def _get_musl_version(executable: str) -> Optional[_MuslVersion]:
-    """Detect currently-running musl runtime version.
-
-    This is done by checking the specified executable's dynamic linking
-    information, and invoking the loader to parse its output for a version
-    string. If the loader is musl, the output would be something like::
-
-        musl libc (x86_64)
-        Version 1.2.2
-        Dynamic Program Loader
-    """
-    try:
-        with open(executable, "rb") as f:
-            ld = ELFFile(f).interpreter
-    except (OSError, TypeError, ValueError):
-        return None
-    if ld is None or "musl" not in ld:
-        return None
-    proc = subprocess.run([ld], stderr=subprocess.PIPE, text=True)
-    return _parse_musl_version(proc.stderr)
-
-
-def platform_tags(archs: Sequence[str]) -> Iterator[str]:
-    """Generate musllinux tags compatible to the current platform.
-
-    :param archs: Sequence of compatible architectures.
-        The first one shall be the closest to the actual architecture and be the part of
-        platform tag after the ``linux_`` prefix, e.g. ``x86_64``.
-        The ``linux_`` prefix is assumed as a prerequisite for the current platform to
-        be musllinux-compatible.
-
-    :returns: An iterator of compatible musllinux tags.
-    """
-    sys_musl = _get_musl_version(sys.executable)
-    if sys_musl is None:  # Python not dynamically linked against musl.
-        return
-    for arch in archs:
-        for minor in range(sys_musl.minor, -1, -1):
-            yield f"musllinux_{sys_musl.major}_{minor}_{arch}"
-
-
-if __name__ == "__main__":  # pragma: no cover
-    import sysconfig
-
-    plat = sysconfig.get_platform()
-    assert plat.startswith("linux-"), "not linux"
-
-    print("plat:", plat)
-    print("musl:", _get_musl_version(sys.executable))
-    print("tags:", end=" ")
-    for t in platform_tags(re.sub(r"[.-]", "_", plat.split("-", 1)[-1])):
-        print(t, end="\n      ")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_parser.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_parser.py
deleted file mode 100644
index 513686a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_parser.py
+++ /dev/null
@@ -1,356 +0,0 @@
-"""Handwritten parser of dependency specifiers.
-
-The docstring for each __parse_* function contains EBNF-inspired grammar representing
-the implementation.
-"""
-
-import ast
-from typing import Any, List, NamedTuple, Optional, Tuple, Union
-
-from ._tokenizer import DEFAULT_RULES, Tokenizer
-
-
-class Node:
-    def __init__(self, value: str) -> None:
-        self.value = value
-
-    def __str__(self) -> str:
-        return self.value
-
-    def __repr__(self) -> str:
-        return f"<{self.__class__.__name__}('{self}')>"
-
-    def serialize(self) -> str:
-        raise NotImplementedError
-
-
-class Variable(Node):
-    def serialize(self) -> str:
-        return str(self)
-
-
-class Value(Node):
-    def serialize(self) -> str:
-        return f'"{self}"'
-
-
-class Op(Node):
-    def serialize(self) -> str:
-        return str(self)
-
-
-MarkerVar = Union[Variable, Value]
-MarkerItem = Tuple[MarkerVar, Op, MarkerVar]
-# MarkerAtom = Union[MarkerItem, List["MarkerAtom"]]
-# MarkerList = List[Union["MarkerList", MarkerAtom, str]]
-# mypy does not support recursive type definition
-# https://github.com/python/mypy/issues/731
-MarkerAtom = Any
-MarkerList = List[Any]
-
-
-class ParsedRequirement(NamedTuple):
-    name: str
-    url: str
-    extras: List[str]
-    specifier: str
-    marker: Optional[MarkerList]
-
-
-# --------------------------------------------------------------------------------------
-# Recursive descent parser for dependency specifier
-# --------------------------------------------------------------------------------------
-def parse_requirement(source: str) -> ParsedRequirement:
-    return _parse_requirement(Tokenizer(source, rules=DEFAULT_RULES))
-
-
-def _parse_requirement(tokenizer: Tokenizer) -> ParsedRequirement:
-    """
-    requirement = WS? IDENTIFIER WS? extras WS? requirement_details
-    """
-    tokenizer.consume("WS")
-
-    name_token = tokenizer.expect(
-        "IDENTIFIER", expected="package name at the start of dependency specifier"
-    )
-    name = name_token.text
-    tokenizer.consume("WS")
-
-    extras = _parse_extras(tokenizer)
-    tokenizer.consume("WS")
-
-    url, specifier, marker = _parse_requirement_details(tokenizer)
-    tokenizer.expect("END", expected="end of dependency specifier")
-
-    return ParsedRequirement(name, url, extras, specifier, marker)
-
-
-def _parse_requirement_details(
-    tokenizer: Tokenizer,
-) -> Tuple[str, str, Optional[MarkerList]]:
-    """
-    requirement_details = AT URL (WS requirement_marker?)?
-                        | specifier WS? (requirement_marker)?
-    """
-
-    specifier = ""
-    url = ""
-    marker = None
-
-    if tokenizer.check("AT"):
-        tokenizer.read()
-        tokenizer.consume("WS")
-
-        url_start = tokenizer.position
-        url = tokenizer.expect("URL", expected="URL after @").text
-        if tokenizer.check("END", peek=True):
-            return (url, specifier, marker)
-
-        tokenizer.expect("WS", expected="whitespace after URL")
-
-        # The input might end after whitespace.
-        if tokenizer.check("END", peek=True):
-            return (url, specifier, marker)
-
-        marker = _parse_requirement_marker(
-            tokenizer, span_start=url_start, after="URL and whitespace"
-        )
-    else:
-        specifier_start = tokenizer.position
-        specifier = _parse_specifier(tokenizer)
-        tokenizer.consume("WS")
-
-        if tokenizer.check("END", peek=True):
-            return (url, specifier, marker)
-
-        marker = _parse_requirement_marker(
-            tokenizer,
-            span_start=specifier_start,
-            after=(
-                "version specifier"
-                if specifier
-                else "name and no valid version specifier"
-            ),
-        )
-
-    return (url, specifier, marker)
-
-
-def _parse_requirement_marker(
-    tokenizer: Tokenizer, *, span_start: int, after: str
-) -> MarkerList:
-    """
-    requirement_marker = SEMICOLON marker WS?
-    """
-
-    if not tokenizer.check("SEMICOLON"):
-        tokenizer.raise_syntax_error(
-            f"Expected end or semicolon (after {after})",
-            span_start=span_start,
-        )
-    tokenizer.read()
-
-    marker = _parse_marker(tokenizer)
-    tokenizer.consume("WS")
-
-    return marker
-
-
-def _parse_extras(tokenizer: Tokenizer) -> List[str]:
-    """
-    extras = (LEFT_BRACKET wsp* extras_list? wsp* RIGHT_BRACKET)?
-    """
-    if not tokenizer.check("LEFT_BRACKET", peek=True):
-        return []
-
-    with tokenizer.enclosing_tokens(
-        "LEFT_BRACKET",
-        "RIGHT_BRACKET",
-        around="extras",
-    ):
-        tokenizer.consume("WS")
-        extras = _parse_extras_list(tokenizer)
-        tokenizer.consume("WS")
-
-    return extras
-
-
-def _parse_extras_list(tokenizer: Tokenizer) -> List[str]:
-    """
-    extras_list = identifier (wsp* ',' wsp* identifier)*
-    """
-    extras: List[str] = []
-
-    if not tokenizer.check("IDENTIFIER"):
-        return extras
-
-    extras.append(tokenizer.read().text)
-
-    while True:
-        tokenizer.consume("WS")
-        if tokenizer.check("IDENTIFIER", peek=True):
-            tokenizer.raise_syntax_error("Expected comma between extra names")
-        elif not tokenizer.check("COMMA"):
-            break
-
-        tokenizer.read()
-        tokenizer.consume("WS")
-
-        extra_token = tokenizer.expect("IDENTIFIER", expected="extra name after comma")
-        extras.append(extra_token.text)
-
-    return extras
-
-
-def _parse_specifier(tokenizer: Tokenizer) -> str:
-    """
-    specifier = LEFT_PARENTHESIS WS? version_many WS? RIGHT_PARENTHESIS
-              | WS? version_many WS?
-    """
-    with tokenizer.enclosing_tokens(
-        "LEFT_PARENTHESIS",
-        "RIGHT_PARENTHESIS",
-        around="version specifier",
-    ):
-        tokenizer.consume("WS")
-        parsed_specifiers = _parse_version_many(tokenizer)
-        tokenizer.consume("WS")
-
-    return parsed_specifiers
-
-
-def _parse_version_many(tokenizer: Tokenizer) -> str:
-    """
-    version_many = (SPECIFIER (WS? COMMA WS? SPECIFIER)*)?
-    """
-    parsed_specifiers = ""
-    while tokenizer.check("SPECIFIER"):
-        span_start = tokenizer.position
-        parsed_specifiers += tokenizer.read().text
-        if tokenizer.check("VERSION_PREFIX_TRAIL", peek=True):
-            tokenizer.raise_syntax_error(
-                ".* suffix can only be used with `==` or `!=` operators",
-                span_start=span_start,
-                span_end=tokenizer.position + 1,
-            )
-        if tokenizer.check("VERSION_LOCAL_LABEL_TRAIL", peek=True):
-            tokenizer.raise_syntax_error(
-                "Local version label can only be used with `==` or `!=` operators",
-                span_start=span_start,
-                span_end=tokenizer.position,
-            )
-        tokenizer.consume("WS")
-        if not tokenizer.check("COMMA"):
-            break
-        parsed_specifiers += tokenizer.read().text
-        tokenizer.consume("WS")
-
-    return parsed_specifiers
-
-
-# --------------------------------------------------------------------------------------
-# Recursive descent parser for marker expression
-# --------------------------------------------------------------------------------------
-def parse_marker(source: str) -> MarkerList:
-    return _parse_full_marker(Tokenizer(source, rules=DEFAULT_RULES))
-
-
-def _parse_full_marker(tokenizer: Tokenizer) -> MarkerList:
-    retval = _parse_marker(tokenizer)
-    tokenizer.expect("END", expected="end of marker expression")
-    return retval
-
-
-def _parse_marker(tokenizer: Tokenizer) -> MarkerList:
-    """
-    marker = marker_atom (BOOLOP marker_atom)+
-    """
-    expression = [_parse_marker_atom(tokenizer)]
-    while tokenizer.check("BOOLOP"):
-        token = tokenizer.read()
-        expr_right = _parse_marker_atom(tokenizer)
-        expression.extend((token.text, expr_right))
-    return expression
-
-
-def _parse_marker_atom(tokenizer: Tokenizer) -> MarkerAtom:
-    """
-    marker_atom = WS? LEFT_PARENTHESIS WS? marker WS? RIGHT_PARENTHESIS WS?
-                | WS? marker_item WS?
-    """
-
-    tokenizer.consume("WS")
-    if tokenizer.check("LEFT_PARENTHESIS", peek=True):
-        with tokenizer.enclosing_tokens(
-            "LEFT_PARENTHESIS",
-            "RIGHT_PARENTHESIS",
-            around="marker expression",
-        ):
-            tokenizer.consume("WS")
-            marker: MarkerAtom = _parse_marker(tokenizer)
-            tokenizer.consume("WS")
-    else:
-        marker = _parse_marker_item(tokenizer)
-    tokenizer.consume("WS")
-    return marker
-
-
-def _parse_marker_item(tokenizer: Tokenizer) -> MarkerItem:
-    """
-    marker_item = WS? marker_var WS? marker_op WS? marker_var WS?
-    """
-    tokenizer.consume("WS")
-    marker_var_left = _parse_marker_var(tokenizer)
-    tokenizer.consume("WS")
-    marker_op = _parse_marker_op(tokenizer)
-    tokenizer.consume("WS")
-    marker_var_right = _parse_marker_var(tokenizer)
-    tokenizer.consume("WS")
-    return (marker_var_left, marker_op, marker_var_right)
-
-
-def _parse_marker_var(tokenizer: Tokenizer) -> MarkerVar:
-    """
-    marker_var = VARIABLE | QUOTED_STRING
-    """
-    if tokenizer.check("VARIABLE"):
-        return process_env_var(tokenizer.read().text.replace(".", "_"))
-    elif tokenizer.check("QUOTED_STRING"):
-        return process_python_str(tokenizer.read().text)
-    else:
-        tokenizer.raise_syntax_error(
-            message="Expected a marker variable or quoted string"
-        )
-
-
-def process_env_var(env_var: str) -> Variable:
-    if env_var in ("platform_python_implementation", "python_implementation"):
-        return Variable("platform_python_implementation")
-    else:
-        return Variable(env_var)
-
-
-def process_python_str(python_str: str) -> Value:
-    value = ast.literal_eval(python_str)
-    return Value(str(value))
-
-
-def _parse_marker_op(tokenizer: Tokenizer) -> Op:
-    """
-    marker_op = IN | NOT IN | OP
-    """
-    if tokenizer.check("IN"):
-        tokenizer.read()
-        return Op("in")
-    elif tokenizer.check("NOT"):
-        tokenizer.read()
-        tokenizer.expect("WS", expected="whitespace after 'not'")
-        tokenizer.expect("IN", expected="'in' after 'not'")
-        return Op("not in")
-    elif tokenizer.check("OP"):
-        return Op(tokenizer.read().text)
-    else:
-        return tokenizer.raise_syntax_error(
-            "Expected marker operator, one of "
-            "<=, <, !=, ==, >=, >, ~=, ===, in, not in"
-        )
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_structures.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_structures.py
deleted file mode 100644
index 90a6465..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_structures.py
+++ /dev/null
@@ -1,61 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-
-
-class InfinityType:
-    def __repr__(self) -> str:
-        return "Infinity"
-
-    def __hash__(self) -> int:
-        return hash(repr(self))
-
-    def __lt__(self, other: object) -> bool:
-        return False
-
-    def __le__(self, other: object) -> bool:
-        return False
-
-    def __eq__(self, other: object) -> bool:
-        return isinstance(other, self.__class__)
-
-    def __gt__(self, other: object) -> bool:
-        return True
-
-    def __ge__(self, other: object) -> bool:
-        return True
-
-    def __neg__(self: object) -> "NegativeInfinityType":
-        return NegativeInfinity
-
-
-Infinity = InfinityType()
-
-
-class NegativeInfinityType:
-    def __repr__(self) -> str:
-        return "-Infinity"
-
-    def __hash__(self) -> int:
-        return hash(repr(self))
-
-    def __lt__(self, other: object) -> bool:
-        return True
-
-    def __le__(self, other: object) -> bool:
-        return True
-
-    def __eq__(self, other: object) -> bool:
-        return isinstance(other, self.__class__)
-
-    def __gt__(self, other: object) -> bool:
-        return False
-
-    def __ge__(self, other: object) -> bool:
-        return False
-
-    def __neg__(self: object) -> InfinityType:
-        return Infinity
-
-
-NegativeInfinity = NegativeInfinityType()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_tokenizer.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_tokenizer.py
deleted file mode 100644
index dd0d648..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/_tokenizer.py
+++ /dev/null
@@ -1,192 +0,0 @@
-import contextlib
-import re
-from dataclasses import dataclass
-from typing import Dict, Iterator, NoReturn, Optional, Tuple, Union
-
-from .specifiers import Specifier
-
-
-@dataclass
-class Token:
-    name: str
-    text: str
-    position: int
-
-
-class ParserSyntaxError(Exception):
-    """The provided source text could not be parsed correctly."""
-
-    def __init__(
-        self,
-        message: str,
-        *,
-        source: str,
-        span: Tuple[int, int],
-    ) -> None:
-        self.span = span
-        self.message = message
-        self.source = source
-
-        super().__init__()
-
-    def __str__(self) -> str:
-        marker = " " * self.span[0] + "~" * (self.span[1] - self.span[0]) + "^"
-        return "\n    ".join([self.message, self.source, marker])
-
-
-DEFAULT_RULES: "Dict[str, Union[str, re.Pattern[str]]]" = {
-    "LEFT_PARENTHESIS": r"\(",
-    "RIGHT_PARENTHESIS": r"\)",
-    "LEFT_BRACKET": r"\[",
-    "RIGHT_BRACKET": r"\]",
-    "SEMICOLON": r";",
-    "COMMA": r",",
-    "QUOTED_STRING": re.compile(
-        r"""
-            (
-                ('[^']*')
-                |
-                ("[^"]*")
-            )
-        """,
-        re.VERBOSE,
-    ),
-    "OP": r"(===|==|~=|!=|<=|>=|<|>)",
-    "BOOLOP": r"\b(or|and)\b",
-    "IN": r"\bin\b",
-    "NOT": r"\bnot\b",
-    "VARIABLE": re.compile(
-        r"""
-            \b(
-                python_version
-                |python_full_version
-                |os[._]name
-                |sys[._]platform
-                |platform_(release|system)
-                |platform[._](version|machine|python_implementation)
-                |python_implementation
-                |implementation_(name|version)
-                |extra
-            )\b
-        """,
-        re.VERBOSE,
-    ),
-    "SPECIFIER": re.compile(
-        Specifier._operator_regex_str + Specifier._version_regex_str,
-        re.VERBOSE | re.IGNORECASE,
-    ),
-    "AT": r"\@",
-    "URL": r"[^ \t]+",
-    "IDENTIFIER": r"\b[a-zA-Z0-9][a-zA-Z0-9._-]*\b",
-    "VERSION_PREFIX_TRAIL": r"\.\*",
-    "VERSION_LOCAL_LABEL_TRAIL": r"\+[a-z0-9]+(?:[-_\.][a-z0-9]+)*",
-    "WS": r"[ \t]+",
-    "END": r"$",
-}
-
-
-class Tokenizer:
-    """Context-sensitive token parsing.
-
-    Provides methods to examine the input stream to check whether the next token
-    matches.
-    """
-
-    def __init__(
-        self,
-        source: str,
-        *,
-        rules: "Dict[str, Union[str, re.Pattern[str]]]",
-    ) -> None:
-        self.source = source
-        self.rules: Dict[str, re.Pattern[str]] = {
-            name: re.compile(pattern) for name, pattern in rules.items()
-        }
-        self.next_token: Optional[Token] = None
-        self.position = 0
-
-    def consume(self, name: str) -> None:
-        """Move beyond provided token name, if at current position."""
-        if self.check(name):
-            self.read()
-
-    def check(self, name: str, *, peek: bool = False) -> bool:
-        """Check whether the next token has the provided name.
-
-        By default, if the check succeeds, the token *must* be read before
-        another check. If `peek` is set to `True`, the token is not loaded and
-        would need to be checked again.
-        """
-        assert (
-            self.next_token is None
-        ), f"Cannot check for {name!r}, already have {self.next_token!r}"
-        assert name in self.rules, f"Unknown token name: {name!r}"
-
-        expression = self.rules[name]
-
-        match = expression.match(self.source, self.position)
-        if match is None:
-            return False
-        if not peek:
-            self.next_token = Token(name, match[0], self.position)
-        return True
-
-    def expect(self, name: str, *, expected: str) -> Token:
-        """Expect a certain token name next, failing with a syntax error otherwise.
-
-        The token is *not* read.
-        """
-        if not self.check(name):
-            raise self.raise_syntax_error(f"Expected {expected}")
-        return self.read()
-
-    def read(self) -> Token:
-        """Consume the next token and return it."""
-        token = self.next_token
-        assert token is not None
-
-        self.position += len(token.text)
-        self.next_token = None
-
-        return token
-
-    def raise_syntax_error(
-        self,
-        message: str,
-        *,
-        span_start: Optional[int] = None,
-        span_end: Optional[int] = None,
-    ) -> NoReturn:
-        """Raise ParserSyntaxError at the given position."""
-        span = (
-            self.position if span_start is None else span_start,
-            self.position if span_end is None else span_end,
-        )
-        raise ParserSyntaxError(
-            message,
-            source=self.source,
-            span=span,
-        )
-
-    @contextlib.contextmanager
-    def enclosing_tokens(
-        self, open_token: str, close_token: str, *, around: str
-    ) -> Iterator[None]:
-        if self.check(open_token):
-            open_position = self.position
-            self.read()
-        else:
-            open_position = None
-
-        yield
-
-        if open_position is None:
-            return
-
-        if not self.check(close_token):
-            self.raise_syntax_error(
-                f"Expected matching {close_token} for {open_token}, after {around}",
-                span_start=open_position,
-            )
-
-        self.read()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/markers.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/markers.py
deleted file mode 100644
index c96d22a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/markers.py
+++ /dev/null
@@ -1,253 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-
-import operator
-import os
-import platform
-import sys
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
-
-from ._parser import (
-    MarkerAtom,
-    MarkerList,
-    Op,
-    Value,
-    Variable,
-)
-from ._parser import (
-    parse_marker as _parse_marker,
-)
-from ._tokenizer import ParserSyntaxError
-from .specifiers import InvalidSpecifier, Specifier
-from .utils import canonicalize_name
-
-__all__ = [
-    "InvalidMarker",
-    "UndefinedComparison",
-    "UndefinedEnvironmentName",
-    "Marker",
-    "default_environment",
-]
-
-Operator = Callable[[str, str], bool]
-
-
-class InvalidMarker(ValueError):
-    """
-    An invalid marker was found, users should refer to PEP 508.
-    """
-
-
-class UndefinedComparison(ValueError):
-    """
-    An invalid operation was attempted on a value that doesn't support it.
-    """
-
-
-class UndefinedEnvironmentName(ValueError):
-    """
-    A name was attempted to be used that does not exist inside of the
-    environment.
-    """
-
-
-def _normalize_extra_values(results: Any) -> Any:
-    """
-    Normalize extra values.
-    """
-    if isinstance(results[0], tuple):
-        lhs, op, rhs = results[0]
-        if isinstance(lhs, Variable) and lhs.value == "extra":
-            normalized_extra = canonicalize_name(rhs.value)
-            rhs = Value(normalized_extra)
-        elif isinstance(rhs, Variable) and rhs.value == "extra":
-            normalized_extra = canonicalize_name(lhs.value)
-            lhs = Value(normalized_extra)
-        results[0] = lhs, op, rhs
-    return results
-
-
-def _format_marker(
-    marker: Union[List[str], MarkerAtom, str], first: Optional[bool] = True
-) -> str:
-    assert isinstance(marker, (list, tuple, str))
-
-    # Sometimes we have a structure like [[...]] which is a single item list
-    # where the single item is itself it's own list. In that case we want skip
-    # the rest of this function so that we don't get extraneous () on the
-    # outside.
-    if (
-        isinstance(marker, list)
-        and len(marker) == 1
-        and isinstance(marker[0], (list, tuple))
-    ):
-        return _format_marker(marker[0])
-
-    if isinstance(marker, list):
-        inner = (_format_marker(m, first=False) for m in marker)
-        if first:
-            return " ".join(inner)
-        else:
-            return "(" + " ".join(inner) + ")"
-    elif isinstance(marker, tuple):
-        return " ".join([m.serialize() for m in marker])
-    else:
-        return marker
-
-
-_operators: Dict[str, Operator] = {
-    "in": lambda lhs, rhs: lhs in rhs,
-    "not in": lambda lhs, rhs: lhs not in rhs,
-    "<": operator.lt,
-    "<=": operator.le,
-    "==": operator.eq,
-    "!=": operator.ne,
-    ">=": operator.ge,
-    ">": operator.gt,
-}
-
-
-def _eval_op(lhs: str, op: Op, rhs: str) -> bool:
-    try:
-        spec = Specifier("".join([op.serialize(), rhs]))
-    except InvalidSpecifier:
-        pass
-    else:
-        return spec.contains(lhs, prereleases=True)
-
-    oper: Optional[Operator] = _operators.get(op.serialize())
-    if oper is None:
-        raise UndefinedComparison(f"Undefined {op!r} on {lhs!r} and {rhs!r}.")
-
-    return oper(lhs, rhs)
-
-
-def _normalize(*values: str, key: str) -> Tuple[str, ...]:
-    # PEP 685 – Comparison of extra names for optional distribution dependencies
-    # https://peps.python.org/pep-0685/
-    # > When comparing extra names, tools MUST normalize the names being
-    # > compared using the semantics outlined in PEP 503 for names
-    if key == "extra":
-        return tuple(canonicalize_name(v) for v in values)
-
-    # other environment markers don't have such standards
-    return values
-
-
-def _evaluate_markers(markers: MarkerList, environment: Dict[str, str]) -> bool:
-    groups: List[List[bool]] = [[]]
-
-    for marker in markers:
-        assert isinstance(marker, (list, tuple, str))
-
-        if isinstance(marker, list):
-            groups[-1].append(_evaluate_markers(marker, environment))
-        elif isinstance(marker, tuple):
-            lhs, op, rhs = marker
-
-            if isinstance(lhs, Variable):
-                environment_key = lhs.value
-                lhs_value = environment[environment_key]
-                rhs_value = rhs.value
-            else:
-                lhs_value = lhs.value
-                environment_key = rhs.value
-                rhs_value = environment[environment_key]
-
-            lhs_value, rhs_value = _normalize(lhs_value, rhs_value, key=environment_key)
-            groups[-1].append(_eval_op(lhs_value, op, rhs_value))
-        else:
-            assert marker in ["and", "or"]
-            if marker == "or":
-                groups.append([])
-
-    return any(all(item) for item in groups)
-
-
-def format_full_version(info: "sys._version_info") -> str:
-    version = "{0.major}.{0.minor}.{0.micro}".format(info)
-    kind = info.releaselevel
-    if kind != "final":
-        version += kind[0] + str(info.serial)
-    return version
-
-
-def default_environment() -> Dict[str, str]:
-    iver = format_full_version(sys.implementation.version)
-    implementation_name = sys.implementation.name
-    return {
-        "implementation_name": implementation_name,
-        "implementation_version": iver,
-        "os_name": os.name,
-        "platform_machine": platform.machine(),
-        "platform_release": platform.release(),
-        "platform_system": platform.system(),
-        "platform_version": platform.version(),
-        "python_full_version": platform.python_version(),
-        "platform_python_implementation": platform.python_implementation(),
-        "python_version": ".".join(platform.python_version_tuple()[:2]),
-        "sys_platform": sys.platform,
-    }
-
-
-class Marker:
-    def __init__(self, marker: str) -> None:
-        # Note: We create a Marker object without calling this constructor in
-        #       packaging.requirements.Requirement. If any additional logic is
-        #       added here, make sure to mirror/adapt Requirement.
-        try:
-            self._markers = _normalize_extra_values(_parse_marker(marker))
-            # The attribute `_markers` can be described in terms of a recursive type:
-            # MarkerList = List[Union[Tuple[Node, ...], str, MarkerList]]
-            #
-            # For example, the following expression:
-            # python_version > "3.6" or (python_version == "3.6" and os_name == "unix")
-            #
-            # is parsed into:
-            # [
-            #     (, ')>, ),
-            #     'and',
-            #     [
-            #         (, , ),
-            #         'or',
-            #         (, , )
-            #     ]
-            # ]
-        except ParserSyntaxError as e:
-            raise InvalidMarker(str(e)) from e
-
-    def __str__(self) -> str:
-        return _format_marker(self._markers)
-
-    def __repr__(self) -> str:
-        return f""
-
-    def __hash__(self) -> int:
-        return hash((self.__class__.__name__, str(self)))
-
-    def __eq__(self, other: Any) -> bool:
-        if not isinstance(other, Marker):
-            return NotImplemented
-
-        return str(self) == str(other)
-
-    def evaluate(self, environment: Optional[Dict[str, str]] = None) -> bool:
-        """Evaluate a marker.
-
-        Return the boolean from evaluating the given marker against the
-        environment. environment is an optional argument to override all or
-        part of the determined environment.
-
-        The environment is determined from the current Python process.
-        """
-        current_environment = default_environment()
-        current_environment["extra"] = ""
-        if environment is not None:
-            current_environment.update(environment)
-            # The API used to allow setting extra to None. We need to handle this
-            # case for backwards compatibility.
-            if current_environment["extra"] is None:
-                current_environment["extra"] = ""
-
-        return _evaluate_markers(self._markers, current_environment)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/requirements.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/requirements.py
deleted file mode 100644
index bdc43a7..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/requirements.py
+++ /dev/null
@@ -1,90 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-
-from typing import Any, Iterator, Optional, Set
-
-from ._parser import parse_requirement as _parse_requirement
-from ._tokenizer import ParserSyntaxError
-from .markers import Marker, _normalize_extra_values
-from .specifiers import SpecifierSet
-from .utils import canonicalize_name
-
-
-class InvalidRequirement(ValueError):
-    """
-    An invalid requirement was found, users should refer to PEP 508.
-    """
-
-
-class Requirement:
-    """Parse a requirement.
-
-    Parse a given requirement string into its parts, such as name, specifier,
-    URL, and extras. Raises InvalidRequirement on a badly-formed requirement
-    string.
-    """
-
-    # TODO: Can we test whether something is contained within a requirement?
-    #       If so how do we do that? Do we need to test against the _name_ of
-    #       the thing as well as the version? What about the markers?
-    # TODO: Can we normalize the name and extra name?
-
-    def __init__(self, requirement_string: str) -> None:
-        try:
-            parsed = _parse_requirement(requirement_string)
-        except ParserSyntaxError as e:
-            raise InvalidRequirement(str(e)) from e
-
-        self.name: str = parsed.name
-        self.url: Optional[str] = parsed.url or None
-        self.extras: Set[str] = set(parsed.extras or [])
-        self.specifier: SpecifierSet = SpecifierSet(parsed.specifier)
-        self.marker: Optional[Marker] = None
-        if parsed.marker is not None:
-            self.marker = Marker.__new__(Marker)
-            self.marker._markers = _normalize_extra_values(parsed.marker)
-
-    def _iter_parts(self, name: str) -> Iterator[str]:
-        yield name
-
-        if self.extras:
-            formatted_extras = ",".join(sorted(self.extras))
-            yield f"[{formatted_extras}]"
-
-        if self.specifier:
-            yield str(self.specifier)
-
-        if self.url:
-            yield f"@ {self.url}"
-            if self.marker:
-                yield " "
-
-        if self.marker:
-            yield f"; {self.marker}"
-
-    def __str__(self) -> str:
-        return "".join(self._iter_parts(self.name))
-
-    def __repr__(self) -> str:
-        return f""
-
-    def __hash__(self) -> int:
-        return hash(
-            (
-                self.__class__.__name__,
-                *self._iter_parts(canonicalize_name(self.name)),
-            )
-        )
-
-    def __eq__(self, other: Any) -> bool:
-        if not isinstance(other, Requirement):
-            return NotImplemented
-
-        return (
-            canonicalize_name(self.name) == canonicalize_name(other.name)
-            and self.extras == other.extras
-            and self.specifier == other.specifier
-            and self.url == other.url
-            and self.marker == other.marker
-        )
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/specifiers.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/specifiers.py
deleted file mode 100644
index 6d4066a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/specifiers.py
+++ /dev/null
@@ -1,1011 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-"""
-.. testsetup::
-
-    from packaging.specifiers import Specifier, SpecifierSet, InvalidSpecifier
-    from packaging.version import Version
-"""
-
-import abc
-import itertools
-import re
-from typing import Callable, Iterable, Iterator, List, Optional, Tuple, TypeVar, Union
-
-from .utils import canonicalize_version
-from .version import Version
-
-UnparsedVersion = Union[Version, str]
-UnparsedVersionVar = TypeVar("UnparsedVersionVar", bound=UnparsedVersion)
-CallableOperator = Callable[[Version, str], bool]
-
-
-def _coerce_version(version: UnparsedVersion) -> Version:
-    if not isinstance(version, Version):
-        version = Version(version)
-    return version
-
-
-class InvalidSpecifier(ValueError):
-    """
-    Raised when attempting to create a :class:`Specifier` with a specifier
-    string that is invalid.
-
-    >>> Specifier("lolwat")
-    Traceback (most recent call last):
-        ...
-    packaging.specifiers.InvalidSpecifier: Invalid specifier: 'lolwat'
-    """
-
-
-class BaseSpecifier(metaclass=abc.ABCMeta):
-    @abc.abstractmethod
-    def __str__(self) -> str:
-        """
-        Returns the str representation of this Specifier-like object. This
-        should be representative of the Specifier itself.
-        """
-
-    @abc.abstractmethod
-    def __hash__(self) -> int:
-        """
-        Returns a hash value for this Specifier-like object.
-        """
-
-    @abc.abstractmethod
-    def __eq__(self, other: object) -> bool:
-        """
-        Returns a boolean representing whether or not the two Specifier-like
-        objects are equal.
-
-        :param other: The other object to check against.
-        """
-
-    @property
-    @abc.abstractmethod
-    def prereleases(self) -> Optional[bool]:
-        """Whether or not pre-releases as a whole are allowed.
-
-        This can be set to either ``True`` or ``False`` to explicitly enable or disable
-        prereleases or it can be set to ``None`` (the default) to use default semantics.
-        """
-
-    @prereleases.setter
-    def prereleases(self, value: bool) -> None:
-        """Setter for :attr:`prereleases`.
-
-        :param value: The value to set.
-        """
-
-    @abc.abstractmethod
-    def contains(self, item: str, prereleases: Optional[bool] = None) -> bool:
-        """
-        Determines if the given item is contained within this specifier.
-        """
-
-    @abc.abstractmethod
-    def filter(
-        self, iterable: Iterable[UnparsedVersionVar], prereleases: Optional[bool] = None
-    ) -> Iterator[UnparsedVersionVar]:
-        """
-        Takes an iterable of items and filters them so that only items which
-        are contained within this specifier are allowed in it.
-        """
-
-
-class Specifier(BaseSpecifier):
-    """This class abstracts handling of version specifiers.
-
-    .. tip::
-
-        It is generally not required to instantiate this manually. You should instead
-        prefer to work with :class:`SpecifierSet` instead, which can parse
-        comma-separated version specifiers (which is what package metadata contains).
-    """
-
-    _operator_regex_str = r"""
-        (?P(~=|==|!=|<=|>=|<|>|===))
-        """
-    _version_regex_str = r"""
-        (?P
-            (?:
-                # The identity operators allow for an escape hatch that will
-                # do an exact string match of the version you wish to install.
-                # This will not be parsed by PEP 440 and we cannot determine
-                # any semantic meaning from it. This operator is discouraged
-                # but included entirely as an escape hatch.
-                (?<====)  # Only match for the identity operator
-                \s*
-                [^\s;)]*  # The arbitrary version can be just about anything,
-                          # we match everything except for whitespace, a
-                          # semi-colon for marker support, and a closing paren
-                          # since versions can be enclosed in them.
-            )
-            |
-            (?:
-                # The (non)equality operators allow for wild card and local
-                # versions to be specified so we have to define these two
-                # operators separately to enable that.
-                (?<===|!=)            # Only match for equals and not equals
-
-                \s*
-                v?
-                (?:[0-9]+!)?          # epoch
-                [0-9]+(?:\.[0-9]+)*   # release
-
-                # You cannot use a wild card and a pre-release, post-release, a dev or
-                # local version together so group them with a | and make them optional.
-                (?:
-                    \.\*  # Wild card syntax of .*
-                    |
-                    (?:                                  # pre release
-                        [-_\.]?
-                        (alpha|beta|preview|pre|a|b|c|rc)
-                        [-_\.]?
-                        [0-9]*
-                    )?
-                    (?:                                  # post release
-                        (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*)
-                    )?
-                    (?:[-_\.]?dev[-_\.]?[0-9]*)?         # dev release
-                    (?:\+[a-z0-9]+(?:[-_\.][a-z0-9]+)*)? # local
-                )?
-            )
-            |
-            (?:
-                # The compatible operator requires at least two digits in the
-                # release segment.
-                (?<=~=)               # Only match for the compatible operator
-
-                \s*
-                v?
-                (?:[0-9]+!)?          # epoch
-                [0-9]+(?:\.[0-9]+)+   # release  (We have a + instead of a *)
-                (?:                   # pre release
-                    [-_\.]?
-                    (alpha|beta|preview|pre|a|b|c|rc)
-                    [-_\.]?
-                    [0-9]*
-                )?
-                (?:                                   # post release
-                    (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*)
-                )?
-                (?:[-_\.]?dev[-_\.]?[0-9]*)?          # dev release
-            )
-            |
-            (?:
-                # All other operators only allow a sub set of what the
-                # (non)equality operators do. Specifically they do not allow
-                # local versions to be specified nor do they allow the prefix
-                # matching wild cards.
-                (?=": "greater_than_equal",
-        "<": "less_than",
-        ">": "greater_than",
-        "===": "arbitrary",
-    }
-
-    def __init__(self, spec: str = "", prereleases: Optional[bool] = None) -> None:
-        """Initialize a Specifier instance.
-
-        :param spec:
-            The string representation of a specifier which will be parsed and
-            normalized before use.
-        :param prereleases:
-            This tells the specifier if it should accept prerelease versions if
-            applicable or not. The default of ``None`` will autodetect it from the
-            given specifiers.
-        :raises InvalidSpecifier:
-            If the given specifier is invalid (i.e. bad syntax).
-        """
-        match = self._regex.search(spec)
-        if not match:
-            raise InvalidSpecifier(f"Invalid specifier: '{spec}'")
-
-        self._spec: Tuple[str, str] = (
-            match.group("operator").strip(),
-            match.group("version").strip(),
-        )
-
-        # Store whether or not this Specifier should accept prereleases
-        self._prereleases = prereleases
-
-    # https://github.com/python/mypy/pull/13475#pullrequestreview-1079784515
-    @property  # type: ignore[override]
-    def prereleases(self) -> bool:
-        # If there is an explicit prereleases set for this, then we'll just
-        # blindly use that.
-        if self._prereleases is not None:
-            return self._prereleases
-
-        # Look at all of our specifiers and determine if they are inclusive
-        # operators, and if they are if they are including an explicit
-        # prerelease.
-        operator, version = self._spec
-        if operator in ["==", ">=", "<=", "~=", "==="]:
-            # The == specifier can include a trailing .*, if it does we
-            # want to remove before parsing.
-            if operator == "==" and version.endswith(".*"):
-                version = version[:-2]
-
-            # Parse the version, and if it is a pre-release than this
-            # specifier allows pre-releases.
-            if Version(version).is_prerelease:
-                return True
-
-        return False
-
-    @prereleases.setter
-    def prereleases(self, value: bool) -> None:
-        self._prereleases = value
-
-    @property
-    def operator(self) -> str:
-        """The operator of this specifier.
-
-        >>> Specifier("==1.2.3").operator
-        '=='
-        """
-        return self._spec[0]
-
-    @property
-    def version(self) -> str:
-        """The version of this specifier.
-
-        >>> Specifier("==1.2.3").version
-        '1.2.3'
-        """
-        return self._spec[1]
-
-    def __repr__(self) -> str:
-        """A representation of the Specifier that shows all internal state.
-
-        >>> Specifier('>=1.0.0')
-        =1.0.0')>
-        >>> Specifier('>=1.0.0', prereleases=False)
-        =1.0.0', prereleases=False)>
-        >>> Specifier('>=1.0.0', prereleases=True)
-        =1.0.0', prereleases=True)>
-        """
-        pre = (
-            f", prereleases={self.prereleases!r}"
-            if self._prereleases is not None
-            else ""
-        )
-
-        return f"<{self.__class__.__name__}({str(self)!r}{pre})>"
-
-    def __str__(self) -> str:
-        """A string representation of the Specifier that can be round-tripped.
-
-        >>> str(Specifier('>=1.0.0'))
-        '>=1.0.0'
-        >>> str(Specifier('>=1.0.0', prereleases=False))
-        '>=1.0.0'
-        """
-        return "{}{}".format(*self._spec)
-
-    @property
-    def _canonical_spec(self) -> Tuple[str, str]:
-        canonical_version = canonicalize_version(
-            self._spec[1],
-            strip_trailing_zero=(self._spec[0] != "~="),
-        )
-        return self._spec[0], canonical_version
-
-    def __hash__(self) -> int:
-        return hash(self._canonical_spec)
-
-    def __eq__(self, other: object) -> bool:
-        """Whether or not the two Specifier-like objects are equal.
-
-        :param other: The other object to check against.
-
-        The value of :attr:`prereleases` is ignored.
-
-        >>> Specifier("==1.2.3") == Specifier("== 1.2.3.0")
-        True
-        >>> (Specifier("==1.2.3", prereleases=False) ==
-        ...  Specifier("==1.2.3", prereleases=True))
-        True
-        >>> Specifier("==1.2.3") == "==1.2.3"
-        True
-        >>> Specifier("==1.2.3") == Specifier("==1.2.4")
-        False
-        >>> Specifier("==1.2.3") == Specifier("~=1.2.3")
-        False
-        """
-        if isinstance(other, str):
-            try:
-                other = self.__class__(str(other))
-            except InvalidSpecifier:
-                return NotImplemented
-        elif not isinstance(other, self.__class__):
-            return NotImplemented
-
-        return self._canonical_spec == other._canonical_spec
-
-    def _get_operator(self, op: str) -> CallableOperator:
-        operator_callable: CallableOperator = getattr(
-            self, f"_compare_{self._operators[op]}"
-        )
-        return operator_callable
-
-    def _compare_compatible(self, prospective: Version, spec: str) -> bool:
-        # Compatible releases have an equivalent combination of >= and ==. That
-        # is that ~=2.2 is equivalent to >=2.2,==2.*. This allows us to
-        # implement this in terms of the other specifiers instead of
-        # implementing it ourselves. The only thing we need to do is construct
-        # the other specifiers.
-
-        # We want everything but the last item in the version, but we want to
-        # ignore suffix segments.
-        prefix = _version_join(
-            list(itertools.takewhile(_is_not_suffix, _version_split(spec)))[:-1]
-        )
-
-        # Add the prefix notation to the end of our string
-        prefix += ".*"
-
-        return self._get_operator(">=")(prospective, spec) and self._get_operator("==")(
-            prospective, prefix
-        )
-
-    def _compare_equal(self, prospective: Version, spec: str) -> bool:
-        # We need special logic to handle prefix matching
-        if spec.endswith(".*"):
-            # In the case of prefix matching we want to ignore local segment.
-            normalized_prospective = canonicalize_version(
-                prospective.public, strip_trailing_zero=False
-            )
-            # Get the normalized version string ignoring the trailing .*
-            normalized_spec = canonicalize_version(spec[:-2], strip_trailing_zero=False)
-            # Split the spec out by bangs and dots, and pretend that there is
-            # an implicit dot in between a release segment and a pre-release segment.
-            split_spec = _version_split(normalized_spec)
-
-            # Split the prospective version out by bangs and dots, and pretend
-            # that there is an implicit dot in between a release segment and
-            # a pre-release segment.
-            split_prospective = _version_split(normalized_prospective)
-
-            # 0-pad the prospective version before shortening it to get the correct
-            # shortened version.
-            padded_prospective, _ = _pad_version(split_prospective, split_spec)
-
-            # Shorten the prospective version to be the same length as the spec
-            # so that we can determine if the specifier is a prefix of the
-            # prospective version or not.
-            shortened_prospective = padded_prospective[: len(split_spec)]
-
-            return shortened_prospective == split_spec
-        else:
-            # Convert our spec string into a Version
-            spec_version = Version(spec)
-
-            # If the specifier does not have a local segment, then we want to
-            # act as if the prospective version also does not have a local
-            # segment.
-            if not spec_version.local:
-                prospective = Version(prospective.public)
-
-            return prospective == spec_version
-
-    def _compare_not_equal(self, prospective: Version, spec: str) -> bool:
-        return not self._compare_equal(prospective, spec)
-
-    def _compare_less_than_equal(self, prospective: Version, spec: str) -> bool:
-        # NB: Local version identifiers are NOT permitted in the version
-        # specifier, so local version labels can be universally removed from
-        # the prospective version.
-        return Version(prospective.public) <= Version(spec)
-
-    def _compare_greater_than_equal(self, prospective: Version, spec: str) -> bool:
-        # NB: Local version identifiers are NOT permitted in the version
-        # specifier, so local version labels can be universally removed from
-        # the prospective version.
-        return Version(prospective.public) >= Version(spec)
-
-    def _compare_less_than(self, prospective: Version, spec_str: str) -> bool:
-        # Convert our spec to a Version instance, since we'll want to work with
-        # it as a version.
-        spec = Version(spec_str)
-
-        # Check to see if the prospective version is less than the spec
-        # version. If it's not we can short circuit and just return False now
-        # instead of doing extra unneeded work.
-        if not prospective < spec:
-            return False
-
-        # This special case is here so that, unless the specifier itself
-        # includes is a pre-release version, that we do not accept pre-release
-        # versions for the version mentioned in the specifier (e.g. <3.1 should
-        # not match 3.1.dev0, but should match 3.0.dev0).
-        if not spec.is_prerelease and prospective.is_prerelease:
-            if Version(prospective.base_version) == Version(spec.base_version):
-                return False
-
-        # If we've gotten to here, it means that prospective version is both
-        # less than the spec version *and* it's not a pre-release of the same
-        # version in the spec.
-        return True
-
-    def _compare_greater_than(self, prospective: Version, spec_str: str) -> bool:
-        # Convert our spec to a Version instance, since we'll want to work with
-        # it as a version.
-        spec = Version(spec_str)
-
-        # Check to see if the prospective version is greater than the spec
-        # version. If it's not we can short circuit and just return False now
-        # instead of doing extra unneeded work.
-        if not prospective > spec:
-            return False
-
-        # This special case is here so that, unless the specifier itself
-        # includes is a post-release version, that we do not accept
-        # post-release versions for the version mentioned in the specifier
-        # (e.g. >3.1 should not match 3.0.post0, but should match 3.2.post0).
-        if not spec.is_postrelease and prospective.is_postrelease:
-            if Version(prospective.base_version) == Version(spec.base_version):
-                return False
-
-        # Ensure that we do not allow a local version of the version mentioned
-        # in the specifier, which is technically greater than, to match.
-        if prospective.local is not None:
-            if Version(prospective.base_version) == Version(spec.base_version):
-                return False
-
-        # If we've gotten to here, it means that prospective version is both
-        # greater than the spec version *and* it's not a pre-release of the
-        # same version in the spec.
-        return True
-
-    def _compare_arbitrary(self, prospective: Version, spec: str) -> bool:
-        return str(prospective).lower() == str(spec).lower()
-
-    def __contains__(self, item: Union[str, Version]) -> bool:
-        """Return whether or not the item is contained in this specifier.
-
-        :param item: The item to check for.
-
-        This is used for the ``in`` operator and behaves the same as
-        :meth:`contains` with no ``prereleases`` argument passed.
-
-        >>> "1.2.3" in Specifier(">=1.2.3")
-        True
-        >>> Version("1.2.3") in Specifier(">=1.2.3")
-        True
-        >>> "1.0.0" in Specifier(">=1.2.3")
-        False
-        >>> "1.3.0a1" in Specifier(">=1.2.3")
-        False
-        >>> "1.3.0a1" in Specifier(">=1.2.3", prereleases=True)
-        True
-        """
-        return self.contains(item)
-
-    def contains(
-        self, item: UnparsedVersion, prereleases: Optional[bool] = None
-    ) -> bool:
-        """Return whether or not the item is contained in this specifier.
-
-        :param item:
-            The item to check for, which can be a version string or a
-            :class:`Version` instance.
-        :param prereleases:
-            Whether or not to match prereleases with this Specifier. If set to
-            ``None`` (the default), it uses :attr:`prereleases` to determine
-            whether or not prereleases are allowed.
-
-        >>> Specifier(">=1.2.3").contains("1.2.3")
-        True
-        >>> Specifier(">=1.2.3").contains(Version("1.2.3"))
-        True
-        >>> Specifier(">=1.2.3").contains("1.0.0")
-        False
-        >>> Specifier(">=1.2.3").contains("1.3.0a1")
-        False
-        >>> Specifier(">=1.2.3", prereleases=True).contains("1.3.0a1")
-        True
-        >>> Specifier(">=1.2.3").contains("1.3.0a1", prereleases=True)
-        True
-        """
-
-        # Determine if prereleases are to be allowed or not.
-        if prereleases is None:
-            prereleases = self.prereleases
-
-        # Normalize item to a Version, this allows us to have a shortcut for
-        # "2.0" in Specifier(">=2")
-        normalized_item = _coerce_version(item)
-
-        # Determine if we should be supporting prereleases in this specifier
-        # or not, if we do not support prereleases than we can short circuit
-        # logic if this version is a prereleases.
-        if normalized_item.is_prerelease and not prereleases:
-            return False
-
-        # Actually do the comparison to determine if this item is contained
-        # within this Specifier or not.
-        operator_callable: CallableOperator = self._get_operator(self.operator)
-        return operator_callable(normalized_item, self.version)
-
-    def filter(
-        self, iterable: Iterable[UnparsedVersionVar], prereleases: Optional[bool] = None
-    ) -> Iterator[UnparsedVersionVar]:
-        """Filter items in the given iterable, that match the specifier.
-
-        :param iterable:
-            An iterable that can contain version strings and :class:`Version` instances.
-            The items in the iterable will be filtered according to the specifier.
-        :param prereleases:
-            Whether or not to allow prereleases in the returned iterator. If set to
-            ``None`` (the default), it will be intelligently decide whether to allow
-            prereleases or not (based on the :attr:`prereleases` attribute, and
-            whether the only versions matching are prereleases).
-
-        This method is smarter than just ``filter(Specifier().contains, [...])``
-        because it implements the rule from :pep:`440` that a prerelease item
-        SHOULD be accepted if no other versions match the given specifier.
-
-        >>> list(Specifier(">=1.2.3").filter(["1.2", "1.3", "1.5a1"]))
-        ['1.3']
-        >>> list(Specifier(">=1.2.3").filter(["1.2", "1.2.3", "1.3", Version("1.4")]))
-        ['1.2.3', '1.3', ]
-        >>> list(Specifier(">=1.2.3").filter(["1.2", "1.5a1"]))
-        ['1.5a1']
-        >>> list(Specifier(">=1.2.3").filter(["1.3", "1.5a1"], prereleases=True))
-        ['1.3', '1.5a1']
-        >>> list(Specifier(">=1.2.3", prereleases=True).filter(["1.3", "1.5a1"]))
-        ['1.3', '1.5a1']
-        """
-
-        yielded = False
-        found_prereleases = []
-
-        kw = {"prereleases": prereleases if prereleases is not None else True}
-
-        # Attempt to iterate over all the values in the iterable and if any of
-        # them match, yield them.
-        for version in iterable:
-            parsed_version = _coerce_version(version)
-
-            if self.contains(parsed_version, **kw):
-                # If our version is a prerelease, and we were not set to allow
-                # prereleases, then we'll store it for later in case nothing
-                # else matches this specifier.
-                if parsed_version.is_prerelease and not (
-                    prereleases or self.prereleases
-                ):
-                    found_prereleases.append(version)
-                # Either this is not a prerelease, or we should have been
-                # accepting prereleases from the beginning.
-                else:
-                    yielded = True
-                    yield version
-
-        # Now that we've iterated over everything, determine if we've yielded
-        # any values, and if we have not and we have any prereleases stored up
-        # then we will go ahead and yield the prereleases.
-        if not yielded and found_prereleases:
-            for version in found_prereleases:
-                yield version
-
-
-_prefix_regex = re.compile(r"^([0-9]+)((?:a|b|c|rc)[0-9]+)$")
-
-
-def _version_split(version: str) -> List[str]:
-    """Split version into components.
-
-    The split components are intended for version comparison. The logic does
-    not attempt to retain the original version string, so joining the
-    components back with :func:`_version_join` may not produce the original
-    version string.
-    """
-    result: List[str] = []
-
-    epoch, _, rest = version.rpartition("!")
-    result.append(epoch or "0")
-
-    for item in rest.split("."):
-        match = _prefix_regex.search(item)
-        if match:
-            result.extend(match.groups())
-        else:
-            result.append(item)
-    return result
-
-
-def _version_join(components: List[str]) -> str:
-    """Join split version components into a version string.
-
-    This function assumes the input came from :func:`_version_split`, where the
-    first component must be the epoch (either empty or numeric), and all other
-    components numeric.
-    """
-    epoch, *rest = components
-    return f"{epoch}!{'.'.join(rest)}"
-
-
-def _is_not_suffix(segment: str) -> bool:
-    return not any(
-        segment.startswith(prefix) for prefix in ("dev", "a", "b", "rc", "post")
-    )
-
-
-def _pad_version(left: List[str], right: List[str]) -> Tuple[List[str], List[str]]:
-    left_split, right_split = [], []
-
-    # Get the release segment of our versions
-    left_split.append(list(itertools.takewhile(lambda x: x.isdigit(), left)))
-    right_split.append(list(itertools.takewhile(lambda x: x.isdigit(), right)))
-
-    # Get the rest of our versions
-    left_split.append(left[len(left_split[0]) :])
-    right_split.append(right[len(right_split[0]) :])
-
-    # Insert our padding
-    left_split.insert(1, ["0"] * max(0, len(right_split[0]) - len(left_split[0])))
-    right_split.insert(1, ["0"] * max(0, len(left_split[0]) - len(right_split[0])))
-
-    return (
-        list(itertools.chain.from_iterable(left_split)),
-        list(itertools.chain.from_iterable(right_split)),
-    )
-
-
-class SpecifierSet(BaseSpecifier):
-    """This class abstracts handling of a set of version specifiers.
-
-    It can be passed a single specifier (``>=3.0``), a comma-separated list of
-    specifiers (``>=3.0,!=3.1``), or no specifier at all.
-    """
-
-    def __init__(
-        self, specifiers: str = "", prereleases: Optional[bool] = None
-    ) -> None:
-        """Initialize a SpecifierSet instance.
-
-        :param specifiers:
-            The string representation of a specifier or a comma-separated list of
-            specifiers which will be parsed and normalized before use.
-        :param prereleases:
-            This tells the SpecifierSet if it should accept prerelease versions if
-            applicable or not. The default of ``None`` will autodetect it from the
-            given specifiers.
-
-        :raises InvalidSpecifier:
-            If the given ``specifiers`` are not parseable than this exception will be
-            raised.
-        """
-
-        # Split on `,` to break each individual specifier into it's own item, and
-        # strip each item to remove leading/trailing whitespace.
-        split_specifiers = [s.strip() for s in specifiers.split(",") if s.strip()]
-
-        # Make each individual specifier a Specifier and save in a frozen set for later.
-        self._specs = frozenset(map(Specifier, split_specifiers))
-
-        # Store our prereleases value so we can use it later to determine if
-        # we accept prereleases or not.
-        self._prereleases = prereleases
-
-    @property
-    def prereleases(self) -> Optional[bool]:
-        # If we have been given an explicit prerelease modifier, then we'll
-        # pass that through here.
-        if self._prereleases is not None:
-            return self._prereleases
-
-        # If we don't have any specifiers, and we don't have a forced value,
-        # then we'll just return None since we don't know if this should have
-        # pre-releases or not.
-        if not self._specs:
-            return None
-
-        # Otherwise we'll see if any of the given specifiers accept
-        # prereleases, if any of them do we'll return True, otherwise False.
-        return any(s.prereleases for s in self._specs)
-
-    @prereleases.setter
-    def prereleases(self, value: bool) -> None:
-        self._prereleases = value
-
-    def __repr__(self) -> str:
-        """A representation of the specifier set that shows all internal state.
-
-        Note that the ordering of the individual specifiers within the set may not
-        match the input string.
-
-        >>> SpecifierSet('>=1.0.0,!=2.0.0')
-        =1.0.0')>
-        >>> SpecifierSet('>=1.0.0,!=2.0.0', prereleases=False)
-        =1.0.0', prereleases=False)>
-        >>> SpecifierSet('>=1.0.0,!=2.0.0', prereleases=True)
-        =1.0.0', prereleases=True)>
-        """
-        pre = (
-            f", prereleases={self.prereleases!r}"
-            if self._prereleases is not None
-            else ""
-        )
-
-        return f""
-
-    def __str__(self) -> str:
-        """A string representation of the specifier set that can be round-tripped.
-
-        Note that the ordering of the individual specifiers within the set may not
-        match the input string.
-
-        >>> str(SpecifierSet(">=1.0.0,!=1.0.1"))
-        '!=1.0.1,>=1.0.0'
-        >>> str(SpecifierSet(">=1.0.0,!=1.0.1", prereleases=False))
-        '!=1.0.1,>=1.0.0'
-        """
-        return ",".join(sorted(str(s) for s in self._specs))
-
-    def __hash__(self) -> int:
-        return hash(self._specs)
-
-    def __and__(self, other: Union["SpecifierSet", str]) -> "SpecifierSet":
-        """Return a SpecifierSet which is a combination of the two sets.
-
-        :param other: The other object to combine with.
-
-        >>> SpecifierSet(">=1.0.0,!=1.0.1") & '<=2.0.0,!=2.0.1'
-        =1.0.0')>
-        >>> SpecifierSet(">=1.0.0,!=1.0.1") & SpecifierSet('<=2.0.0,!=2.0.1')
-        =1.0.0')>
-        """
-        if isinstance(other, str):
-            other = SpecifierSet(other)
-        elif not isinstance(other, SpecifierSet):
-            return NotImplemented
-
-        specifier = SpecifierSet()
-        specifier._specs = frozenset(self._specs | other._specs)
-
-        if self._prereleases is None and other._prereleases is not None:
-            specifier._prereleases = other._prereleases
-        elif self._prereleases is not None and other._prereleases is None:
-            specifier._prereleases = self._prereleases
-        elif self._prereleases == other._prereleases:
-            specifier._prereleases = self._prereleases
-        else:
-            raise ValueError(
-                "Cannot combine SpecifierSets with True and False prerelease "
-                "overrides."
-            )
-
-        return specifier
-
-    def __eq__(self, other: object) -> bool:
-        """Whether or not the two SpecifierSet-like objects are equal.
-
-        :param other: The other object to check against.
-
-        The value of :attr:`prereleases` is ignored.
-
-        >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0,!=1.0.1")
-        True
-        >>> (SpecifierSet(">=1.0.0,!=1.0.1", prereleases=False) ==
-        ...  SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True))
-        True
-        >>> SpecifierSet(">=1.0.0,!=1.0.1") == ">=1.0.0,!=1.0.1"
-        True
-        >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0")
-        False
-        >>> SpecifierSet(">=1.0.0,!=1.0.1") == SpecifierSet(">=1.0.0,!=1.0.2")
-        False
-        """
-        if isinstance(other, (str, Specifier)):
-            other = SpecifierSet(str(other))
-        elif not isinstance(other, SpecifierSet):
-            return NotImplemented
-
-        return self._specs == other._specs
-
-    def __len__(self) -> int:
-        """Returns the number of specifiers in this specifier set."""
-        return len(self._specs)
-
-    def __iter__(self) -> Iterator[Specifier]:
-        """
-        Returns an iterator over all the underlying :class:`Specifier` instances
-        in this specifier set.
-
-        >>> sorted(SpecifierSet(">=1.0.0,!=1.0.1"), key=str)
-        [, =1.0.0')>]
-        """
-        return iter(self._specs)
-
-    def __contains__(self, item: UnparsedVersion) -> bool:
-        """Return whether or not the item is contained in this specifier.
-
-        :param item: The item to check for.
-
-        This is used for the ``in`` operator and behaves the same as
-        :meth:`contains` with no ``prereleases`` argument passed.
-
-        >>> "1.2.3" in SpecifierSet(">=1.0.0,!=1.0.1")
-        True
-        >>> Version("1.2.3") in SpecifierSet(">=1.0.0,!=1.0.1")
-        True
-        >>> "1.0.1" in SpecifierSet(">=1.0.0,!=1.0.1")
-        False
-        >>> "1.3.0a1" in SpecifierSet(">=1.0.0,!=1.0.1")
-        False
-        >>> "1.3.0a1" in SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True)
-        True
-        """
-        return self.contains(item)
-
-    def contains(
-        self,
-        item: UnparsedVersion,
-        prereleases: Optional[bool] = None,
-        installed: Optional[bool] = None,
-    ) -> bool:
-        """Return whether or not the item is contained in this SpecifierSet.
-
-        :param item:
-            The item to check for, which can be a version string or a
-            :class:`Version` instance.
-        :param prereleases:
-            Whether or not to match prereleases with this SpecifierSet. If set to
-            ``None`` (the default), it uses :attr:`prereleases` to determine
-            whether or not prereleases are allowed.
-
-        >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.2.3")
-        True
-        >>> SpecifierSet(">=1.0.0,!=1.0.1").contains(Version("1.2.3"))
-        True
-        >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.0.1")
-        False
-        >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.3.0a1")
-        False
-        >>> SpecifierSet(">=1.0.0,!=1.0.1", prereleases=True).contains("1.3.0a1")
-        True
-        >>> SpecifierSet(">=1.0.0,!=1.0.1").contains("1.3.0a1", prereleases=True)
-        True
-        """
-        # Ensure that our item is a Version instance.
-        if not isinstance(item, Version):
-            item = Version(item)
-
-        # Determine if we're forcing a prerelease or not, if we're not forcing
-        # one for this particular filter call, then we'll use whatever the
-        # SpecifierSet thinks for whether or not we should support prereleases.
-        if prereleases is None:
-            prereleases = self.prereleases
-
-        # We can determine if we're going to allow pre-releases by looking to
-        # see if any of the underlying items supports them. If none of them do
-        # and this item is a pre-release then we do not allow it and we can
-        # short circuit that here.
-        # Note: This means that 1.0.dev1 would not be contained in something
-        #       like >=1.0.devabc however it would be in >=1.0.debabc,>0.0.dev0
-        if not prereleases and item.is_prerelease:
-            return False
-
-        if installed and item.is_prerelease:
-            item = Version(item.base_version)
-
-        # We simply dispatch to the underlying specs here to make sure that the
-        # given version is contained within all of them.
-        # Note: This use of all() here means that an empty set of specifiers
-        #       will always return True, this is an explicit design decision.
-        return all(s.contains(item, prereleases=prereleases) for s in self._specs)
-
-    def filter(
-        self, iterable: Iterable[UnparsedVersionVar], prereleases: Optional[bool] = None
-    ) -> Iterator[UnparsedVersionVar]:
-        """Filter items in the given iterable, that match the specifiers in this set.
-
-        :param iterable:
-            An iterable that can contain version strings and :class:`Version` instances.
-            The items in the iterable will be filtered according to the specifier.
-        :param prereleases:
-            Whether or not to allow prereleases in the returned iterator. If set to
-            ``None`` (the default), it will be intelligently decide whether to allow
-            prereleases or not (based on the :attr:`prereleases` attribute, and
-            whether the only versions matching are prereleases).
-
-        This method is smarter than just ``filter(SpecifierSet(...).contains, [...])``
-        because it implements the rule from :pep:`440` that a prerelease item
-        SHOULD be accepted if no other versions match the given specifier.
-
-        >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.3", "1.5a1"]))
-        ['1.3']
-        >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.3", Version("1.4")]))
-        ['1.3', ]
-        >>> list(SpecifierSet(">=1.2.3").filter(["1.2", "1.5a1"]))
-        []
-        >>> list(SpecifierSet(">=1.2.3").filter(["1.3", "1.5a1"], prereleases=True))
-        ['1.3', '1.5a1']
-        >>> list(SpecifierSet(">=1.2.3", prereleases=True).filter(["1.3", "1.5a1"]))
-        ['1.3', '1.5a1']
-
-        An "empty" SpecifierSet will filter items based on the presence of prerelease
-        versions in the set.
-
-        >>> list(SpecifierSet("").filter(["1.3", "1.5a1"]))
-        ['1.3']
-        >>> list(SpecifierSet("").filter(["1.5a1"]))
-        ['1.5a1']
-        >>> list(SpecifierSet("", prereleases=True).filter(["1.3", "1.5a1"]))
-        ['1.3', '1.5a1']
-        >>> list(SpecifierSet("").filter(["1.3", "1.5a1"], prereleases=True))
-        ['1.3', '1.5a1']
-        """
-        # Determine if we're forcing a prerelease or not, if we're not forcing
-        # one for this particular filter call, then we'll use whatever the
-        # SpecifierSet thinks for whether or not we should support prereleases.
-        if prereleases is None:
-            prereleases = self.prereleases
-
-        # If we have any specifiers, then we want to wrap our iterable in the
-        # filter method for each one, this will act as a logical AND amongst
-        # each specifier.
-        if self._specs:
-            for spec in self._specs:
-                iterable = spec.filter(iterable, prereleases=bool(prereleases))
-            return iter(iterable)
-        # If we do not have any specifiers, then we need to have a rough filter
-        # which will filter out any pre-releases, unless there are no final
-        # releases.
-        else:
-            filtered: List[UnparsedVersionVar] = []
-            found_prereleases: List[UnparsedVersionVar] = []
-
-            for item in iterable:
-                parsed_version = _coerce_version(item)
-
-                # Store any item which is a pre-release for later unless we've
-                # already found a final version or we are accepting prereleases
-                if parsed_version.is_prerelease and not prereleases:
-                    if not filtered:
-                        found_prereleases.append(item)
-                else:
-                    filtered.append(item)
-
-            # If we've found no items except for pre-releases, then we'll go
-            # ahead and use the pre-releases
-            if not filtered and found_prereleases and prereleases is None:
-                return iter(found_prereleases)
-
-            return iter(filtered)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/tags.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/tags.py
deleted file mode 100644
index 89f1926..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/tags.py
+++ /dev/null
@@ -1,571 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-
-import logging
-import platform
-import re
-import struct
-import subprocess
-import sys
-import sysconfig
-from importlib.machinery import EXTENSION_SUFFIXES
-from typing import (
-    Dict,
-    FrozenSet,
-    Iterable,
-    Iterator,
-    List,
-    Optional,
-    Sequence,
-    Tuple,
-    Union,
-    cast,
-)
-
-from . import _manylinux, _musllinux
-
-logger = logging.getLogger(__name__)
-
-PythonVersion = Sequence[int]
-MacVersion = Tuple[int, int]
-
-INTERPRETER_SHORT_NAMES: Dict[str, str] = {
-    "python": "py",  # Generic.
-    "cpython": "cp",
-    "pypy": "pp",
-    "ironpython": "ip",
-    "jython": "jy",
-}
-
-
-_32_BIT_INTERPRETER = struct.calcsize("P") == 4
-
-
-class Tag:
-    """
-    A representation of the tag triple for a wheel.
-
-    Instances are considered immutable and thus are hashable. Equality checking
-    is also supported.
-    """
-
-    __slots__ = ["_interpreter", "_abi", "_platform", "_hash"]
-
-    def __init__(self, interpreter: str, abi: str, platform: str) -> None:
-        self._interpreter = interpreter.lower()
-        self._abi = abi.lower()
-        self._platform = platform.lower()
-        # The __hash__ of every single element in a Set[Tag] will be evaluated each time
-        # that a set calls its `.disjoint()` method, which may be called hundreds of
-        # times when scanning a page of links for packages with tags matching that
-        # Set[Tag]. Pre-computing the value here produces significant speedups for
-        # downstream consumers.
-        self._hash = hash((self._interpreter, self._abi, self._platform))
-
-    @property
-    def interpreter(self) -> str:
-        return self._interpreter
-
-    @property
-    def abi(self) -> str:
-        return self._abi
-
-    @property
-    def platform(self) -> str:
-        return self._platform
-
-    def __eq__(self, other: object) -> bool:
-        if not isinstance(other, Tag):
-            return NotImplemented
-
-        return (
-            (self._hash == other._hash)  # Short-circuit ASAP for perf reasons.
-            and (self._platform == other._platform)
-            and (self._abi == other._abi)
-            and (self._interpreter == other._interpreter)
-        )
-
-    def __hash__(self) -> int:
-        return self._hash
-
-    def __str__(self) -> str:
-        return f"{self._interpreter}-{self._abi}-{self._platform}"
-
-    def __repr__(self) -> str:
-        return f"<{self} @ {id(self)}>"
-
-
-def parse_tag(tag: str) -> FrozenSet[Tag]:
-    """
-    Parses the provided tag (e.g. `py3-none-any`) into a frozenset of Tag instances.
-
-    Returning a set is required due to the possibility that the tag is a
-    compressed tag set.
-    """
-    tags = set()
-    interpreters, abis, platforms = tag.split("-")
-    for interpreter in interpreters.split("."):
-        for abi in abis.split("."):
-            for platform_ in platforms.split("."):
-                tags.add(Tag(interpreter, abi, platform_))
-    return frozenset(tags)
-
-
-def _get_config_var(name: str, warn: bool = False) -> Union[int, str, None]:
-    value: Union[int, str, None] = sysconfig.get_config_var(name)
-    if value is None and warn:
-        logger.debug(
-            "Config variable '%s' is unset, Python ABI tag may be incorrect", name
-        )
-    return value
-
-
-def _normalize_string(string: str) -> str:
-    return string.replace(".", "_").replace("-", "_").replace(" ", "_")
-
-
-def _is_threaded_cpython(abis: List[str]) -> bool:
-    """
-    Determine if the ABI corresponds to a threaded (`--disable-gil`) build.
-
-    The threaded builds are indicated by a "t" in the abiflags.
-    """
-    if len(abis) == 0:
-        return False
-    # expect e.g., cp313
-    m = re.match(r"cp\d+(.*)", abis[0])
-    if not m:
-        return False
-    abiflags = m.group(1)
-    return "t" in abiflags
-
-
-def _abi3_applies(python_version: PythonVersion, threading: bool) -> bool:
-    """
-    Determine if the Python version supports abi3.
-
-    PEP 384 was first implemented in Python 3.2. The threaded (`--disable-gil`)
-    builds do not support abi3.
-    """
-    return len(python_version) > 1 and tuple(python_version) >= (3, 2) and not threading
-
-
-def _cpython_abis(py_version: PythonVersion, warn: bool = False) -> List[str]:
-    py_version = tuple(py_version)  # To allow for version comparison.
-    abis = []
-    version = _version_nodot(py_version[:2])
-    threading = debug = pymalloc = ucs4 = ""
-    with_debug = _get_config_var("Py_DEBUG", warn)
-    has_refcount = hasattr(sys, "gettotalrefcount")
-    # Windows doesn't set Py_DEBUG, so checking for support of debug-compiled
-    # extension modules is the best option.
-    # https://github.com/pypa/pip/issues/3383#issuecomment-173267692
-    has_ext = "_d.pyd" in EXTENSION_SUFFIXES
-    if with_debug or (with_debug is None and (has_refcount or has_ext)):
-        debug = "d"
-    if py_version >= (3, 13) and _get_config_var("Py_GIL_DISABLED", warn):
-        threading = "t"
-    if py_version < (3, 8):
-        with_pymalloc = _get_config_var("WITH_PYMALLOC", warn)
-        if with_pymalloc or with_pymalloc is None:
-            pymalloc = "m"
-        if py_version < (3, 3):
-            unicode_size = _get_config_var("Py_UNICODE_SIZE", warn)
-            if unicode_size == 4 or (
-                unicode_size is None and sys.maxunicode == 0x10FFFF
-            ):
-                ucs4 = "u"
-    elif debug:
-        # Debug builds can also load "normal" extension modules.
-        # We can also assume no UCS-4 or pymalloc requirement.
-        abis.append(f"cp{version}{threading}")
-    abis.insert(0, f"cp{version}{threading}{debug}{pymalloc}{ucs4}")
-    return abis
-
-
-def cpython_tags(
-    python_version: Optional[PythonVersion] = None,
-    abis: Optional[Iterable[str]] = None,
-    platforms: Optional[Iterable[str]] = None,
-    *,
-    warn: bool = False,
-) -> Iterator[Tag]:
-    """
-    Yields the tags for a CPython interpreter.
-
-    The tags consist of:
-    - cp--
-    - cp-abi3-
-    - cp-none-
-    - cp-abi3-  # Older Python versions down to 3.2.
-
-    If python_version only specifies a major version then user-provided ABIs and
-    the 'none' ABItag will be used.
-
-    If 'abi3' or 'none' are specified in 'abis' then they will be yielded at
-    their normal position and not at the beginning.
-    """
-    if not python_version:
-        python_version = sys.version_info[:2]
-
-    interpreter = f"cp{_version_nodot(python_version[:2])}"
-
-    if abis is None:
-        if len(python_version) > 1:
-            abis = _cpython_abis(python_version, warn)
-        else:
-            abis = []
-    abis = list(abis)
-    # 'abi3' and 'none' are explicitly handled later.
-    for explicit_abi in ("abi3", "none"):
-        try:
-            abis.remove(explicit_abi)
-        except ValueError:
-            pass
-
-    platforms = list(platforms or platform_tags())
-    for abi in abis:
-        for platform_ in platforms:
-            yield Tag(interpreter, abi, platform_)
-
-    threading = _is_threaded_cpython(abis)
-    use_abi3 = _abi3_applies(python_version, threading)
-    if use_abi3:
-        yield from (Tag(interpreter, "abi3", platform_) for platform_ in platforms)
-    yield from (Tag(interpreter, "none", platform_) for platform_ in platforms)
-
-    if use_abi3:
-        for minor_version in range(python_version[1] - 1, 1, -1):
-            for platform_ in platforms:
-                interpreter = "cp{version}".format(
-                    version=_version_nodot((python_version[0], minor_version))
-                )
-                yield Tag(interpreter, "abi3", platform_)
-
-
-def _generic_abi() -> List[str]:
-    """
-    Return the ABI tag based on EXT_SUFFIX.
-    """
-    # The following are examples of `EXT_SUFFIX`.
-    # We want to keep the parts which are related to the ABI and remove the
-    # parts which are related to the platform:
-    # - linux:   '.cpython-310-x86_64-linux-gnu.so' => cp310
-    # - mac:     '.cpython-310-darwin.so'           => cp310
-    # - win:     '.cp310-win_amd64.pyd'             => cp310
-    # - win:     '.pyd'                             => cp37 (uses _cpython_abis())
-    # - pypy:    '.pypy38-pp73-x86_64-linux-gnu.so' => pypy38_pp73
-    # - graalpy: '.graalpy-38-native-x86_64-darwin.dylib'
-    #                                               => graalpy_38_native
-
-    ext_suffix = _get_config_var("EXT_SUFFIX", warn=True)
-    if not isinstance(ext_suffix, str) or ext_suffix[0] != ".":
-        raise SystemError("invalid sysconfig.get_config_var('EXT_SUFFIX')")
-    parts = ext_suffix.split(".")
-    if len(parts) < 3:
-        # CPython3.7 and earlier uses ".pyd" on Windows.
-        return _cpython_abis(sys.version_info[:2])
-    soabi = parts[1]
-    if soabi.startswith("cpython"):
-        # non-windows
-        abi = "cp" + soabi.split("-")[1]
-    elif soabi.startswith("cp"):
-        # windows
-        abi = soabi.split("-")[0]
-    elif soabi.startswith("pypy"):
-        abi = "-".join(soabi.split("-")[:2])
-    elif soabi.startswith("graalpy"):
-        abi = "-".join(soabi.split("-")[:3])
-    elif soabi:
-        # pyston, ironpython, others?
-        abi = soabi
-    else:
-        return []
-    return [_normalize_string(abi)]
-
-
-def generic_tags(
-    interpreter: Optional[str] = None,
-    abis: Optional[Iterable[str]] = None,
-    platforms: Optional[Iterable[str]] = None,
-    *,
-    warn: bool = False,
-) -> Iterator[Tag]:
-    """
-    Yields the tags for a generic interpreter.
-
-    The tags consist of:
-    - --
-
-    The "none" ABI will be added if it was not explicitly provided.
-    """
-    if not interpreter:
-        interp_name = interpreter_name()
-        interp_version = interpreter_version(warn=warn)
-        interpreter = "".join([interp_name, interp_version])
-    if abis is None:
-        abis = _generic_abi()
-    else:
-        abis = list(abis)
-    platforms = list(platforms or platform_tags())
-    if "none" not in abis:
-        abis.append("none")
-    for abi in abis:
-        for platform_ in platforms:
-            yield Tag(interpreter, abi, platform_)
-
-
-def _py_interpreter_range(py_version: PythonVersion) -> Iterator[str]:
-    """
-    Yields Python versions in descending order.
-
-    After the latest version, the major-only version will be yielded, and then
-    all previous versions of that major version.
-    """
-    if len(py_version) > 1:
-        yield f"py{_version_nodot(py_version[:2])}"
-    yield f"py{py_version[0]}"
-    if len(py_version) > 1:
-        for minor in range(py_version[1] - 1, -1, -1):
-            yield f"py{_version_nodot((py_version[0], minor))}"
-
-
-def compatible_tags(
-    python_version: Optional[PythonVersion] = None,
-    interpreter: Optional[str] = None,
-    platforms: Optional[Iterable[str]] = None,
-) -> Iterator[Tag]:
-    """
-    Yields the sequence of tags that are compatible with a specific version of Python.
-
-    The tags consist of:
-    - py*-none-
-    - -none-any  # ... if `interpreter` is provided.
-    - py*-none-any
-    """
-    if not python_version:
-        python_version = sys.version_info[:2]
-    platforms = list(platforms or platform_tags())
-    for version in _py_interpreter_range(python_version):
-        for platform_ in platforms:
-            yield Tag(version, "none", platform_)
-    if interpreter:
-        yield Tag(interpreter, "none", "any")
-    for version in _py_interpreter_range(python_version):
-        yield Tag(version, "none", "any")
-
-
-def _mac_arch(arch: str, is_32bit: bool = _32_BIT_INTERPRETER) -> str:
-    if not is_32bit:
-        return arch
-
-    if arch.startswith("ppc"):
-        return "ppc"
-
-    return "i386"
-
-
-def _mac_binary_formats(version: MacVersion, cpu_arch: str) -> List[str]:
-    formats = [cpu_arch]
-    if cpu_arch == "x86_64":
-        if version < (10, 4):
-            return []
-        formats.extend(["intel", "fat64", "fat32"])
-
-    elif cpu_arch == "i386":
-        if version < (10, 4):
-            return []
-        formats.extend(["intel", "fat32", "fat"])
-
-    elif cpu_arch == "ppc64":
-        # TODO: Need to care about 32-bit PPC for ppc64 through 10.2?
-        if version > (10, 5) or version < (10, 4):
-            return []
-        formats.append("fat64")
-
-    elif cpu_arch == "ppc":
-        if version > (10, 6):
-            return []
-        formats.extend(["fat32", "fat"])
-
-    if cpu_arch in {"arm64", "x86_64"}:
-        formats.append("universal2")
-
-    if cpu_arch in {"x86_64", "i386", "ppc64", "ppc", "intel"}:
-        formats.append("universal")
-
-    return formats
-
-
-def mac_platforms(
-    version: Optional[MacVersion] = None, arch: Optional[str] = None
-) -> Iterator[str]:
-    """
-    Yields the platform tags for a macOS system.
-
-    The `version` parameter is a two-item tuple specifying the macOS version to
-    generate platform tags for. The `arch` parameter is the CPU architecture to
-    generate platform tags for. Both parameters default to the appropriate value
-    for the current system.
-    """
-    version_str, _, cpu_arch = platform.mac_ver()
-    if version is None:
-        version = cast("MacVersion", tuple(map(int, version_str.split(".")[:2])))
-        if version == (10, 16):
-            # When built against an older macOS SDK, Python will report macOS 10.16
-            # instead of the real version.
-            version_str = subprocess.run(
-                [
-                    sys.executable,
-                    "-sS",
-                    "-c",
-                    "import platform; print(platform.mac_ver()[0])",
-                ],
-                check=True,
-                env={"SYSTEM_VERSION_COMPAT": "0"},
-                stdout=subprocess.PIPE,
-                text=True,
-            ).stdout
-            version = cast("MacVersion", tuple(map(int, version_str.split(".")[:2])))
-    else:
-        version = version
-    if arch is None:
-        arch = _mac_arch(cpu_arch)
-    else:
-        arch = arch
-
-    if (10, 0) <= version and version < (11, 0):
-        # Prior to Mac OS 11, each yearly release of Mac OS bumped the
-        # "minor" version number.  The major version was always 10.
-        for minor_version in range(version[1], -1, -1):
-            compat_version = 10, minor_version
-            binary_formats = _mac_binary_formats(compat_version, arch)
-            for binary_format in binary_formats:
-                yield "macosx_{major}_{minor}_{binary_format}".format(
-                    major=10, minor=minor_version, binary_format=binary_format
-                )
-
-    if version >= (11, 0):
-        # Starting with Mac OS 11, each yearly release bumps the major version
-        # number.   The minor versions are now the midyear updates.
-        for major_version in range(version[0], 10, -1):
-            compat_version = major_version, 0
-            binary_formats = _mac_binary_formats(compat_version, arch)
-            for binary_format in binary_formats:
-                yield "macosx_{major}_{minor}_{binary_format}".format(
-                    major=major_version, minor=0, binary_format=binary_format
-                )
-
-    if version >= (11, 0):
-        # Mac OS 11 on x86_64 is compatible with binaries from previous releases.
-        # Arm64 support was introduced in 11.0, so no Arm binaries from previous
-        # releases exist.
-        #
-        # However, the "universal2" binary format can have a
-        # macOS version earlier than 11.0 when the x86_64 part of the binary supports
-        # that version of macOS.
-        if arch == "x86_64":
-            for minor_version in range(16, 3, -1):
-                compat_version = 10, minor_version
-                binary_formats = _mac_binary_formats(compat_version, arch)
-                for binary_format in binary_formats:
-                    yield "macosx_{major}_{minor}_{binary_format}".format(
-                        major=compat_version[0],
-                        minor=compat_version[1],
-                        binary_format=binary_format,
-                    )
-        else:
-            for minor_version in range(16, 3, -1):
-                compat_version = 10, minor_version
-                binary_format = "universal2"
-                yield "macosx_{major}_{minor}_{binary_format}".format(
-                    major=compat_version[0],
-                    minor=compat_version[1],
-                    binary_format=binary_format,
-                )
-
-
-def _linux_platforms(is_32bit: bool = _32_BIT_INTERPRETER) -> Iterator[str]:
-    linux = _normalize_string(sysconfig.get_platform())
-    if not linux.startswith("linux_"):
-        # we should never be here, just yield the sysconfig one and return
-        yield linux
-        return
-    if is_32bit:
-        if linux == "linux_x86_64":
-            linux = "linux_i686"
-        elif linux == "linux_aarch64":
-            linux = "linux_armv8l"
-    _, arch = linux.split("_", 1)
-    archs = {"armv8l": ["armv8l", "armv7l"]}.get(arch, [arch])
-    yield from _manylinux.platform_tags(archs)
-    yield from _musllinux.platform_tags(archs)
-    for arch in archs:
-        yield f"linux_{arch}"
-
-
-def _generic_platforms() -> Iterator[str]:
-    yield _normalize_string(sysconfig.get_platform())
-
-
-def platform_tags() -> Iterator[str]:
-    """
-    Provides the platform tags for this installation.
-    """
-    if platform.system() == "Darwin":
-        return mac_platforms()
-    elif platform.system() == "Linux":
-        return _linux_platforms()
-    else:
-        return _generic_platforms()
-
-
-def interpreter_name() -> str:
-    """
-    Returns the name of the running interpreter.
-
-    Some implementations have a reserved, two-letter abbreviation which will
-    be returned when appropriate.
-    """
-    name = sys.implementation.name
-    return INTERPRETER_SHORT_NAMES.get(name) or name
-
-
-def interpreter_version(*, warn: bool = False) -> str:
-    """
-    Returns the version of the running interpreter.
-    """
-    version = _get_config_var("py_version_nodot", warn=warn)
-    if version:
-        version = str(version)
-    else:
-        version = _version_nodot(sys.version_info[:2])
-    return version
-
-
-def _version_nodot(version: PythonVersion) -> str:
-    return "".join(map(str, version))
-
-
-def sys_tags(*, warn: bool = False) -> Iterator[Tag]:
-    """
-    Returns the sequence of tag triples for the running interpreter.
-
-    The order of the sequence corresponds to priority order for the
-    interpreter, from most to least important.
-    """
-
-    interp_name = interpreter_name()
-    if interp_name == "cp":
-        yield from cpython_tags(warn=warn)
-    else:
-        yield from generic_tags()
-
-    if interp_name == "pp":
-        interp = "pp3"
-    elif interp_name == "cp":
-        interp = "cp" + interpreter_version(warn=warn)
-    else:
-        interp = None
-    yield from compatible_tags(interpreter=interp)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/utils.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/utils.py
deleted file mode 100644
index c2c2f75..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/utils.py
+++ /dev/null
@@ -1,172 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-
-import re
-from typing import FrozenSet, NewType, Tuple, Union, cast
-
-from .tags import Tag, parse_tag
-from .version import InvalidVersion, Version
-
-BuildTag = Union[Tuple[()], Tuple[int, str]]
-NormalizedName = NewType("NormalizedName", str)
-
-
-class InvalidName(ValueError):
-    """
-    An invalid distribution name; users should refer to the packaging user guide.
-    """
-
-
-class InvalidWheelFilename(ValueError):
-    """
-    An invalid wheel filename was found, users should refer to PEP 427.
-    """
-
-
-class InvalidSdistFilename(ValueError):
-    """
-    An invalid sdist filename was found, users should refer to the packaging user guide.
-    """
-
-
-# Core metadata spec for `Name`
-_validate_regex = re.compile(
-    r"^([A-Z0-9]|[A-Z0-9][A-Z0-9._-]*[A-Z0-9])$", re.IGNORECASE
-)
-_canonicalize_regex = re.compile(r"[-_.]+")
-_normalized_regex = re.compile(r"^([a-z0-9]|[a-z0-9]([a-z0-9-](?!--))*[a-z0-9])$")
-# PEP 427: The build number must start with a digit.
-_build_tag_regex = re.compile(r"(\d+)(.*)")
-
-
-def canonicalize_name(name: str, *, validate: bool = False) -> NormalizedName:
-    if validate and not _validate_regex.match(name):
-        raise InvalidName(f"name is invalid: {name!r}")
-    # This is taken from PEP 503.
-    value = _canonicalize_regex.sub("-", name).lower()
-    return cast(NormalizedName, value)
-
-
-def is_normalized_name(name: str) -> bool:
-    return _normalized_regex.match(name) is not None
-
-
-def canonicalize_version(
-    version: Union[Version, str], *, strip_trailing_zero: bool = True
-) -> str:
-    """
-    This is very similar to Version.__str__, but has one subtle difference
-    with the way it handles the release segment.
-    """
-    if isinstance(version, str):
-        try:
-            parsed = Version(version)
-        except InvalidVersion:
-            # Legacy versions cannot be normalized
-            return version
-    else:
-        parsed = version
-
-    parts = []
-
-    # Epoch
-    if parsed.epoch != 0:
-        parts.append(f"{parsed.epoch}!")
-
-    # Release segment
-    release_segment = ".".join(str(x) for x in parsed.release)
-    if strip_trailing_zero:
-        # NB: This strips trailing '.0's to normalize
-        release_segment = re.sub(r"(\.0)+$", "", release_segment)
-    parts.append(release_segment)
-
-    # Pre-release
-    if parsed.pre is not None:
-        parts.append("".join(str(x) for x in parsed.pre))
-
-    # Post-release
-    if parsed.post is not None:
-        parts.append(f".post{parsed.post}")
-
-    # Development release
-    if parsed.dev is not None:
-        parts.append(f".dev{parsed.dev}")
-
-    # Local version segment
-    if parsed.local is not None:
-        parts.append(f"+{parsed.local}")
-
-    return "".join(parts)
-
-
-def parse_wheel_filename(
-    filename: str,
-) -> Tuple[NormalizedName, Version, BuildTag, FrozenSet[Tag]]:
-    if not filename.endswith(".whl"):
-        raise InvalidWheelFilename(
-            f"Invalid wheel filename (extension must be '.whl'): {filename}"
-        )
-
-    filename = filename[:-4]
-    dashes = filename.count("-")
-    if dashes not in (4, 5):
-        raise InvalidWheelFilename(
-            f"Invalid wheel filename (wrong number of parts): {filename}"
-        )
-
-    parts = filename.split("-", dashes - 2)
-    name_part = parts[0]
-    # See PEP 427 for the rules on escaping the project name.
-    if "__" in name_part or re.match(r"^[\w\d._]*$", name_part, re.UNICODE) is None:
-        raise InvalidWheelFilename(f"Invalid project name: {filename}")
-    name = canonicalize_name(name_part)
-
-    try:
-        version = Version(parts[1])
-    except InvalidVersion as e:
-        raise InvalidWheelFilename(
-            f"Invalid wheel filename (invalid version): {filename}"
-        ) from e
-
-    if dashes == 5:
-        build_part = parts[2]
-        build_match = _build_tag_regex.match(build_part)
-        if build_match is None:
-            raise InvalidWheelFilename(
-                f"Invalid build number: {build_part} in '{filename}'"
-            )
-        build = cast(BuildTag, (int(build_match.group(1)), build_match.group(2)))
-    else:
-        build = ()
-    tags = parse_tag(parts[-1])
-    return (name, version, build, tags)
-
-
-def parse_sdist_filename(filename: str) -> Tuple[NormalizedName, Version]:
-    if filename.endswith(".tar.gz"):
-        file_stem = filename[: -len(".tar.gz")]
-    elif filename.endswith(".zip"):
-        file_stem = filename[: -len(".zip")]
-    else:
-        raise InvalidSdistFilename(
-            f"Invalid sdist filename (extension must be '.tar.gz' or '.zip'):"
-            f" {filename}"
-        )
-
-    # We are requiring a PEP 440 version, which cannot contain dashes,
-    # so we split on the last dash.
-    name_part, sep, version_part = file_stem.rpartition("-")
-    if not sep:
-        raise InvalidSdistFilename(f"Invalid sdist filename: {filename}")
-
-    name = canonicalize_name(name_part)
-
-    try:
-        version = Version(version_part)
-    except InvalidVersion as e:
-        raise InvalidSdistFilename(
-            f"Invalid sdist filename (invalid version): {filename}"
-        ) from e
-
-    return (name, version)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/version.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/version.py
deleted file mode 100644
index cda8e99..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/packaging/version.py
+++ /dev/null
@@ -1,561 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-"""
-.. testsetup::
-
-    from packaging.version import parse, Version
-"""
-
-import itertools
-import re
-from typing import Any, Callable, NamedTuple, Optional, SupportsInt, Tuple, Union
-
-from ._structures import Infinity, InfinityType, NegativeInfinity, NegativeInfinityType
-
-__all__ = ["VERSION_PATTERN", "parse", "Version", "InvalidVersion"]
-
-LocalType = Tuple[Union[int, str], ...]
-
-CmpPrePostDevType = Union[InfinityType, NegativeInfinityType, Tuple[str, int]]
-CmpLocalType = Union[
-    NegativeInfinityType,
-    Tuple[Union[Tuple[int, str], Tuple[NegativeInfinityType, Union[int, str]]], ...],
-]
-CmpKey = Tuple[
-    int,
-    Tuple[int, ...],
-    CmpPrePostDevType,
-    CmpPrePostDevType,
-    CmpPrePostDevType,
-    CmpLocalType,
-]
-VersionComparisonMethod = Callable[[CmpKey, CmpKey], bool]
-
-
-class _Version(NamedTuple):
-    epoch: int
-    release: Tuple[int, ...]
-    dev: Optional[Tuple[str, int]]
-    pre: Optional[Tuple[str, int]]
-    post: Optional[Tuple[str, int]]
-    local: Optional[LocalType]
-
-
-def parse(version: str) -> "Version":
-    """Parse the given version string.
-
-    >>> parse('1.0.dev1')
-    
-
-    :param version: The version string to parse.
-    :raises InvalidVersion: When the version string is not a valid version.
-    """
-    return Version(version)
-
-
-class InvalidVersion(ValueError):
-    """Raised when a version string is not a valid version.
-
-    >>> Version("invalid")
-    Traceback (most recent call last):
-        ...
-    packaging.version.InvalidVersion: Invalid version: 'invalid'
-    """
-
-
-class _BaseVersion:
-    _key: Tuple[Any, ...]
-
-    def __hash__(self) -> int:
-        return hash(self._key)
-
-    # Please keep the duplicated `isinstance` check
-    # in the six comparisons hereunder
-    # unless you find a way to avoid adding overhead function calls.
-    def __lt__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key < other._key
-
-    def __le__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key <= other._key
-
-    def __eq__(self, other: object) -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key == other._key
-
-    def __ge__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key >= other._key
-
-    def __gt__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key > other._key
-
-    def __ne__(self, other: object) -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key != other._key
-
-
-# Deliberately not anchored to the start and end of the string, to make it
-# easier for 3rd party code to reuse
-_VERSION_PATTERN = r"""
-    v?
-    (?:
-        (?:(?P[0-9]+)!)?                           # epoch
-        (?P[0-9]+(?:\.[0-9]+)*)                  # release segment
-        (?P
                                          # pre-release
-            [-_\.]?
-            (?Palpha|a|beta|b|preview|pre|c|rc)
-            [-_\.]?
-            (?P[0-9]+)?
-        )?
-        (?P                                         # post release
-            (?:-(?P[0-9]+))
-            |
-            (?:
-                [-_\.]?
-                (?Ppost|rev|r)
-                [-_\.]?
-                (?P[0-9]+)?
-            )
-        )?
-        (?P                                          # dev release
-            [-_\.]?
-            (?Pdev)
-            [-_\.]?
-            (?P[0-9]+)?
-        )?
-    )
-    (?:\+(?P[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
-"""
-
-VERSION_PATTERN = _VERSION_PATTERN
-"""
-A string containing the regular expression used to match a valid version.
-
-The pattern is not anchored at either end, and is intended for embedding in larger
-expressions (for example, matching a version number as part of a file name). The
-regular expression should be compiled with the ``re.VERBOSE`` and ``re.IGNORECASE``
-flags set.
-
-:meta hide-value:
-"""
-
-
-class Version(_BaseVersion):
-    """This class abstracts handling of a project's versions.
-
-    A :class:`Version` instance is comparison aware and can be compared and
-    sorted using the standard Python interfaces.
-
-    >>> v1 = Version("1.0a5")
-    >>> v2 = Version("1.0")
-    >>> v1
-    
-    >>> v2
-    
-    >>> v1 < v2
-    True
-    >>> v1 == v2
-    False
-    >>> v1 > v2
-    False
-    >>> v1 >= v2
-    False
-    >>> v1 <= v2
-    True
-    """
-
-    _regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE)
-    _key: CmpKey
-
-    def __init__(self, version: str) -> None:
-        """Initialize a Version object.
-
-        :param version:
-            The string representation of a version which will be parsed and normalized
-            before use.
-        :raises InvalidVersion:
-            If the ``version`` does not conform to PEP 440 in any way then this
-            exception will be raised.
-        """
-
-        # Validate the version and parse it into pieces
-        match = self._regex.search(version)
-        if not match:
-            raise InvalidVersion(f"Invalid version: '{version}'")
-
-        # Store the parsed out pieces of the version
-        self._version = _Version(
-            epoch=int(match.group("epoch")) if match.group("epoch") else 0,
-            release=tuple(int(i) for i in match.group("release").split(".")),
-            pre=_parse_letter_version(match.group("pre_l"), match.group("pre_n")),
-            post=_parse_letter_version(
-                match.group("post_l"), match.group("post_n1") or match.group("post_n2")
-            ),
-            dev=_parse_letter_version(match.group("dev_l"), match.group("dev_n")),
-            local=_parse_local_version(match.group("local")),
-        )
-
-        # Generate a key which will be used for sorting
-        self._key = _cmpkey(
-            self._version.epoch,
-            self._version.release,
-            self._version.pre,
-            self._version.post,
-            self._version.dev,
-            self._version.local,
-        )
-
-    def __repr__(self) -> str:
-        """A representation of the Version that shows all internal state.
-
-        >>> Version('1.0.0')
-        
-        """
-        return f""
-
-    def __str__(self) -> str:
-        """A string representation of the version that can be rounded-tripped.
-
-        >>> str(Version("1.0a5"))
-        '1.0a5'
-        """
-        parts = []
-
-        # Epoch
-        if self.epoch != 0:
-            parts.append(f"{self.epoch}!")
-
-        # Release segment
-        parts.append(".".join(str(x) for x in self.release))
-
-        # Pre-release
-        if self.pre is not None:
-            parts.append("".join(str(x) for x in self.pre))
-
-        # Post-release
-        if self.post is not None:
-            parts.append(f".post{self.post}")
-
-        # Development release
-        if self.dev is not None:
-            parts.append(f".dev{self.dev}")
-
-        # Local version segment
-        if self.local is not None:
-            parts.append(f"+{self.local}")
-
-        return "".join(parts)
-
-    @property
-    def epoch(self) -> int:
-        """The epoch of the version.
-
-        >>> Version("2.0.0").epoch
-        0
-        >>> Version("1!2.0.0").epoch
-        1
-        """
-        return self._version.epoch
-
-    @property
-    def release(self) -> Tuple[int, ...]:
-        """The components of the "release" segment of the version.
-
-        >>> Version("1.2.3").release
-        (1, 2, 3)
-        >>> Version("2.0.0").release
-        (2, 0, 0)
-        >>> Version("1!2.0.0.post0").release
-        (2, 0, 0)
-
-        Includes trailing zeroes but not the epoch or any pre-release / development /
-        post-release suffixes.
-        """
-        return self._version.release
-
-    @property
-    def pre(self) -> Optional[Tuple[str, int]]:
-        """The pre-release segment of the version.
-
-        >>> print(Version("1.2.3").pre)
-        None
-        >>> Version("1.2.3a1").pre
-        ('a', 1)
-        >>> Version("1.2.3b1").pre
-        ('b', 1)
-        >>> Version("1.2.3rc1").pre
-        ('rc', 1)
-        """
-        return self._version.pre
-
-    @property
-    def post(self) -> Optional[int]:
-        """The post-release number of the version.
-
-        >>> print(Version("1.2.3").post)
-        None
-        >>> Version("1.2.3.post1").post
-        1
-        """
-        return self._version.post[1] if self._version.post else None
-
-    @property
-    def dev(self) -> Optional[int]:
-        """The development number of the version.
-
-        >>> print(Version("1.2.3").dev)
-        None
-        >>> Version("1.2.3.dev1").dev
-        1
-        """
-        return self._version.dev[1] if self._version.dev else None
-
-    @property
-    def local(self) -> Optional[str]:
-        """The local version segment of the version.
-
-        >>> print(Version("1.2.3").local)
-        None
-        >>> Version("1.2.3+abc").local
-        'abc'
-        """
-        if self._version.local:
-            return ".".join(str(x) for x in self._version.local)
-        else:
-            return None
-
-    @property
-    def public(self) -> str:
-        """The public portion of the version.
-
-        >>> Version("1.2.3").public
-        '1.2.3'
-        >>> Version("1.2.3+abc").public
-        '1.2.3'
-        >>> Version("1.2.3+abc.dev1").public
-        '1.2.3'
-        """
-        return str(self).split("+", 1)[0]
-
-    @property
-    def base_version(self) -> str:
-        """The "base version" of the version.
-
-        >>> Version("1.2.3").base_version
-        '1.2.3'
-        >>> Version("1.2.3+abc").base_version
-        '1.2.3'
-        >>> Version("1!1.2.3+abc.dev1").base_version
-        '1!1.2.3'
-
-        The "base version" is the public version of the project without any pre or post
-        release markers.
-        """
-        parts = []
-
-        # Epoch
-        if self.epoch != 0:
-            parts.append(f"{self.epoch}!")
-
-        # Release segment
-        parts.append(".".join(str(x) for x in self.release))
-
-        return "".join(parts)
-
-    @property
-    def is_prerelease(self) -> bool:
-        """Whether this version is a pre-release.
-
-        >>> Version("1.2.3").is_prerelease
-        False
-        >>> Version("1.2.3a1").is_prerelease
-        True
-        >>> Version("1.2.3b1").is_prerelease
-        True
-        >>> Version("1.2.3rc1").is_prerelease
-        True
-        >>> Version("1.2.3dev1").is_prerelease
-        True
-        """
-        return self.dev is not None or self.pre is not None
-
-    @property
-    def is_postrelease(self) -> bool:
-        """Whether this version is a post-release.
-
-        >>> Version("1.2.3").is_postrelease
-        False
-        >>> Version("1.2.3.post1").is_postrelease
-        True
-        """
-        return self.post is not None
-
-    @property
-    def is_devrelease(self) -> bool:
-        """Whether this version is a development release.
-
-        >>> Version("1.2.3").is_devrelease
-        False
-        >>> Version("1.2.3.dev1").is_devrelease
-        True
-        """
-        return self.dev is not None
-
-    @property
-    def major(self) -> int:
-        """The first item of :attr:`release` or ``0`` if unavailable.
-
-        >>> Version("1.2.3").major
-        1
-        """
-        return self.release[0] if len(self.release) >= 1 else 0
-
-    @property
-    def minor(self) -> int:
-        """The second item of :attr:`release` or ``0`` if unavailable.
-
-        >>> Version("1.2.3").minor
-        2
-        >>> Version("1").minor
-        0
-        """
-        return self.release[1] if len(self.release) >= 2 else 0
-
-    @property
-    def micro(self) -> int:
-        """The third item of :attr:`release` or ``0`` if unavailable.
-
-        >>> Version("1.2.3").micro
-        3
-        >>> Version("1").micro
-        0
-        """
-        return self.release[2] if len(self.release) >= 3 else 0
-
-
-def _parse_letter_version(
-    letter: Optional[str], number: Union[str, bytes, SupportsInt, None]
-) -> Optional[Tuple[str, int]]:
-    if letter:
-        # We consider there to be an implicit 0 in a pre-release if there is
-        # not a numeral associated with it.
-        if number is None:
-            number = 0
-
-        # We normalize any letters to their lower case form
-        letter = letter.lower()
-
-        # We consider some words to be alternate spellings of other words and
-        # in those cases we want to normalize the spellings to our preferred
-        # spelling.
-        if letter == "alpha":
-            letter = "a"
-        elif letter == "beta":
-            letter = "b"
-        elif letter in ["c", "pre", "preview"]:
-            letter = "rc"
-        elif letter in ["rev", "r"]:
-            letter = "post"
-
-        return letter, int(number)
-    if not letter and number:
-        # We assume if we are given a number, but we are not given a letter
-        # then this is using the implicit post release syntax (e.g. 1.0-1)
-        letter = "post"
-
-        return letter, int(number)
-
-    return None
-
-
-_local_version_separators = re.compile(r"[\._-]")
-
-
-def _parse_local_version(local: Optional[str]) -> Optional[LocalType]:
-    """
-    Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
-    """
-    if local is not None:
-        return tuple(
-            part.lower() if not part.isdigit() else int(part)
-            for part in _local_version_separators.split(local)
-        )
-    return None
-
-
-def _cmpkey(
-    epoch: int,
-    release: Tuple[int, ...],
-    pre: Optional[Tuple[str, int]],
-    post: Optional[Tuple[str, int]],
-    dev: Optional[Tuple[str, int]],
-    local: Optional[LocalType],
-) -> CmpKey:
-    # When we compare a release version, we want to compare it with all of the
-    # trailing zeros removed. So we'll use a reverse the list, drop all the now
-    # leading zeros until we come to something non zero, then take the rest
-    # re-reverse it back into the correct order and make it a tuple and use
-    # that for our sorting key.
-    _release = tuple(
-        reversed(list(itertools.dropwhile(lambda x: x == 0, reversed(release))))
-    )
-
-    # We need to "trick" the sorting algorithm to put 1.0.dev0 before 1.0a0.
-    # We'll do this by abusing the pre segment, but we _only_ want to do this
-    # if there is not a pre or a post segment. If we have one of those then
-    # the normal sorting rules will handle this case correctly.
-    if pre is None and post is None and dev is not None:
-        _pre: CmpPrePostDevType = NegativeInfinity
-    # Versions without a pre-release (except as noted above) should sort after
-    # those with one.
-    elif pre is None:
-        _pre = Infinity
-    else:
-        _pre = pre
-
-    # Versions without a post segment should sort before those with one.
-    if post is None:
-        _post: CmpPrePostDevType = NegativeInfinity
-
-    else:
-        _post = post
-
-    # Versions without a development segment should sort after those with one.
-    if dev is None:
-        _dev: CmpPrePostDevType = Infinity
-
-    else:
-        _dev = dev
-
-    if local is None:
-        # Versions without a local segment should sort before those with one.
-        _local: CmpLocalType = NegativeInfinity
-    else:
-        # Versions with a local segment need that segment parsed to implement
-        # the sorting rules in PEP440.
-        # - Alpha numeric segments sort before numeric segments
-        # - Alpha numeric segments sort lexicographically
-        # - Numeric segments sort numerically
-        # - Shorter versions sort before longer versions when the prefixes
-        #   match exactly
-        _local = tuple(
-            (i, "") if isinstance(i, int) else (NegativeInfinity, i) for i in local
-        )
-
-    return epoch, _release, _pre, _post, _dev, _local
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/vendor.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/vendor.txt
deleted file mode 100644
index 1466610..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/vendored/vendor.txt
+++ /dev/null
@@ -1 +0,0 @@
-packaging==24.0
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/wheelfile.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/wheelfile.py
deleted file mode 100644
index 0a0f459..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/wheel/wheelfile.py
+++ /dev/null
@@ -1,227 +0,0 @@
-from __future__ import annotations
-
-import csv
-import hashlib
-import os.path
-import re
-import stat
-import time
-from io import StringIO, TextIOWrapper
-from typing import IO, TYPE_CHECKING, Literal
-from zipfile import ZIP_DEFLATED, ZipFile, ZipInfo
-
-from wheel.cli import WheelError
-from wheel.util import log, urlsafe_b64decode, urlsafe_b64encode
-
-if TYPE_CHECKING:
-    from typing import Protocol, Sized, Union
-
-    from typing_extensions import Buffer
-
-    StrPath = Union[str, os.PathLike[str]]
-
-    class SizedBuffer(Sized, Buffer, Protocol): ...
-
-
-# Non-greedy matching of an optional build number may be too clever (more
-# invalid wheel filenames will match). Separate regex for .dist-info?
-WHEEL_INFO_RE = re.compile(
-    r"""^(?P(?P[^\s-]+?)-(?P[^\s-]+?))(-(?P\d[^\s-]*))?
-     -(?P[^\s-]+?)-(?P[^\s-]+?)-(?P\S+)\.whl$""",
-    re.VERBOSE,
-)
-MINIMUM_TIMESTAMP = 315532800  # 1980-01-01 00:00:00 UTC
-
-
-def get_zipinfo_datetime(timestamp: float | None = None):
-    # Some applications need reproducible .whl files, but they can't do this without
-    # forcing the timestamp of the individual ZipInfo objects. See issue #143.
-    timestamp = int(os.environ.get("SOURCE_DATE_EPOCH", timestamp or time.time()))
-    timestamp = max(timestamp, MINIMUM_TIMESTAMP)
-    return time.gmtime(timestamp)[0:6]
-
-
-class WheelFile(ZipFile):
-    """A ZipFile derivative class that also reads SHA-256 hashes from
-    .dist-info/RECORD and checks any read files against those.
-    """
-
-    _default_algorithm = hashlib.sha256
-
-    def __init__(
-        self,
-        file: StrPath,
-        mode: Literal["r", "w", "x", "a"] = "r",
-        compression: int = ZIP_DEFLATED,
-    ):
-        basename = os.path.basename(file)
-        self.parsed_filename = WHEEL_INFO_RE.match(basename)
-        if not basename.endswith(".whl") or self.parsed_filename is None:
-            raise WheelError(f"Bad wheel filename {basename!r}")
-
-        ZipFile.__init__(self, file, mode, compression=compression, allowZip64=True)
-
-        self.dist_info_path = "{}.dist-info".format(
-            self.parsed_filename.group("namever")
-        )
-        self.record_path = self.dist_info_path + "/RECORD"
-        self._file_hashes: dict[str, tuple[None, None] | tuple[int, bytes]] = {}
-        self._file_sizes = {}
-        if mode == "r":
-            # Ignore RECORD and any embedded wheel signatures
-            self._file_hashes[self.record_path] = None, None
-            self._file_hashes[self.record_path + ".jws"] = None, None
-            self._file_hashes[self.record_path + ".p7s"] = None, None
-
-            # Fill in the expected hashes by reading them from RECORD
-            try:
-                record = self.open(self.record_path)
-            except KeyError:
-                raise WheelError(f"Missing {self.record_path} file") from None
-
-            with record:
-                for line in csv.reader(
-                    TextIOWrapper(record, newline="", encoding="utf-8")
-                ):
-                    path, hash_sum, size = line
-                    if not hash_sum:
-                        continue
-
-                    algorithm, hash_sum = hash_sum.split("=")
-                    try:
-                        hashlib.new(algorithm)
-                    except ValueError:
-                        raise WheelError(
-                            f"Unsupported hash algorithm: {algorithm}"
-                        ) from None
-
-                    if algorithm.lower() in {"md5", "sha1"}:
-                        raise WheelError(
-                            f"Weak hash algorithm ({algorithm}) is not permitted by "
-                            f"PEP 427"
-                        )
-
-                    self._file_hashes[path] = (
-                        algorithm,
-                        urlsafe_b64decode(hash_sum.encode("ascii")),
-                    )
-
-    def open(
-        self,
-        name_or_info: str | ZipInfo,
-        mode: Literal["r", "w"] = "r",
-        pwd: bytes | None = None,
-    ) -> IO[bytes]:
-        def _update_crc(newdata: bytes) -> None:
-            eof = ef._eof
-            update_crc_orig(newdata)
-            running_hash.update(newdata)
-            if eof and running_hash.digest() != expected_hash:
-                raise WheelError(f"Hash mismatch for file '{ef_name}'")
-
-        ef_name = (
-            name_or_info.filename if isinstance(name_or_info, ZipInfo) else name_or_info
-        )
-        if (
-            mode == "r"
-            and not ef_name.endswith("/")
-            and ef_name not in self._file_hashes
-        ):
-            raise WheelError(f"No hash found for file '{ef_name}'")
-
-        ef = ZipFile.open(self, name_or_info, mode, pwd)
-        if mode == "r" and not ef_name.endswith("/"):
-            algorithm, expected_hash = self._file_hashes[ef_name]
-            if expected_hash is not None:
-                # Monkey patch the _update_crc method to also check for the hash from
-                # RECORD
-                running_hash = hashlib.new(algorithm)
-                update_crc_orig, ef._update_crc = ef._update_crc, _update_crc
-
-        return ef
-
-    def write_files(self, base_dir: str):
-        log.info(f"creating '{self.filename}' and adding '{base_dir}' to it")
-        deferred: list[tuple[str, str]] = []
-        for root, dirnames, filenames in os.walk(base_dir):
-            # Sort the directory names so that `os.walk` will walk them in a
-            # defined order on the next iteration.
-            dirnames.sort()
-            for name in sorted(filenames):
-                path = os.path.normpath(os.path.join(root, name))
-                if os.path.isfile(path):
-                    arcname = os.path.relpath(path, base_dir).replace(os.path.sep, "/")
-                    if arcname == self.record_path:
-                        pass
-                    elif root.endswith(".dist-info"):
-                        deferred.append((path, arcname))
-                    else:
-                        self.write(path, arcname)
-
-        deferred.sort()
-        for path, arcname in deferred:
-            self.write(path, arcname)
-
-    def write(
-        self,
-        filename: str,
-        arcname: str | None = None,
-        compress_type: int | None = None,
-    ) -> None:
-        with open(filename, "rb") as f:
-            st = os.fstat(f.fileno())
-            data = f.read()
-
-        zinfo = ZipInfo(
-            arcname or filename, date_time=get_zipinfo_datetime(st.st_mtime)
-        )
-        zinfo.external_attr = (stat.S_IMODE(st.st_mode) | stat.S_IFMT(st.st_mode)) << 16
-        zinfo.compress_type = compress_type or self.compression
-        self.writestr(zinfo, data, compress_type)
-
-    def writestr(
-        self,
-        zinfo_or_arcname: str | ZipInfo,
-        data: SizedBuffer | str,
-        compress_type: int | None = None,
-    ):
-        if isinstance(zinfo_or_arcname, str):
-            zinfo_or_arcname = ZipInfo(
-                zinfo_or_arcname, date_time=get_zipinfo_datetime()
-            )
-            zinfo_or_arcname.compress_type = self.compression
-            zinfo_or_arcname.external_attr = (0o664 | stat.S_IFREG) << 16
-
-        if isinstance(data, str):
-            data = data.encode("utf-8")
-
-        ZipFile.writestr(self, zinfo_or_arcname, data, compress_type)
-        fname = (
-            zinfo_or_arcname.filename
-            if isinstance(zinfo_or_arcname, ZipInfo)
-            else zinfo_or_arcname
-        )
-        log.info(f"adding '{fname}'")
-        if fname != self.record_path:
-            hash_ = self._default_algorithm(data)
-            self._file_hashes[fname] = (
-                hash_.name,
-                urlsafe_b64encode(hash_.digest()).decode("ascii"),
-            )
-            self._file_sizes[fname] = len(data)
-
-    def close(self):
-        # Write RECORD
-        if self.fp is not None and self.mode == "w" and self._file_hashes:
-            data = StringIO()
-            writer = csv.writer(data, delimiter=",", quotechar='"', lineterminator="\n")
-            writer.writerows(
-                (
-                    (fname, algorithm + "=" + hash_, self._file_sizes[fname])
-                    for fname, (algorithm, hash_) in self._file_hashes.items()
-                )
-            )
-            writer.writerow((format(self.record_path), "", ""))
-            self.writestr(self.record_path, data.getvalue())
-
-        ZipFile.close(self)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/LICENSE b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/LICENSE
deleted file mode 100644
index 1bb5a44..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/LICENSE
+++ /dev/null
@@ -1,17 +0,0 @@
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to
-deal in the Software without restriction, including without limitation the
-rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
-sell copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
-FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
-IN THE SOFTWARE.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/METADATA
deleted file mode 100644
index 1399281..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/METADATA
+++ /dev/null
@@ -1,102 +0,0 @@
-Metadata-Version: 2.1
-Name: zipp
-Version: 3.19.2
-Summary: Backport of pathlib-compatible object wrapper for zip files
-Author-email: "Jason R. Coombs" 
-Project-URL: Homepage, https://github.com/jaraco/zipp
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3 :: Only
-Requires-Python: >=3.8
-Description-Content-Type: text/x-rst
-License-File: LICENSE
-Provides-Extra: doc
-Requires-Dist: sphinx >=3.5 ; extra == 'doc'
-Requires-Dist: jaraco.packaging >=9.3 ; extra == 'doc'
-Requires-Dist: rst.linker >=1.9 ; extra == 'doc'
-Requires-Dist: furo ; extra == 'doc'
-Requires-Dist: sphinx-lint ; extra == 'doc'
-Requires-Dist: jaraco.tidelift >=1.4 ; extra == 'doc'
-Provides-Extra: test
-Requires-Dist: pytest !=8.1.*,>=6 ; extra == 'test'
-Requires-Dist: pytest-checkdocs >=2.4 ; extra == 'test'
-Requires-Dist: pytest-cov ; extra == 'test'
-Requires-Dist: pytest-mypy ; extra == 'test'
-Requires-Dist: pytest-enabler >=2.2 ; extra == 'test'
-Requires-Dist: pytest-ruff >=0.2.1 ; extra == 'test'
-Requires-Dist: jaraco.itertools ; extra == 'test'
-Requires-Dist: jaraco.functools ; extra == 'test'
-Requires-Dist: more-itertools ; extra == 'test'
-Requires-Dist: big-O ; extra == 'test'
-Requires-Dist: pytest-ignore-flaky ; extra == 'test'
-Requires-Dist: jaraco.test ; extra == 'test'
-Requires-Dist: importlib-resources ; (python_version < "3.9") and extra == 'test'
-
-.. image:: https://img.shields.io/pypi/v/zipp.svg
-   :target: https://pypi.org/project/zipp
-
-.. image:: https://img.shields.io/pypi/pyversions/zipp.svg
-
-.. image:: https://github.com/jaraco/zipp/actions/workflows/main.yml/badge.svg
-   :target: https://github.com/jaraco/zipp/actions?query=workflow%3A%22tests%22
-   :alt: tests
-
-.. image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json
-    :target: https://github.com/astral-sh/ruff
-    :alt: Ruff
-
-.. .. image:: https://readthedocs.org/projects/PROJECT_RTD/badge/?version=latest
-..    :target: https://PROJECT_RTD.readthedocs.io/en/latest/?badge=latest
-
-.. image:: https://img.shields.io/badge/skeleton-2024-informational
-   :target: https://blog.jaraco.com/skeleton
-
-.. image:: https://tidelift.com/badges/package/pypi/zipp
-   :target: https://tidelift.com/subscription/pkg/pypi-zipp?utm_source=pypi-zipp&utm_medium=readme
-
-
-A pathlib-compatible Zipfile object wrapper. Official backport of the standard library
-`Path object `_.
-
-
-Compatibility
-=============
-
-New features are introduced in this third-party library and later merged
-into CPython. The following table indicates which versions of this library
-were contributed to different versions in the standard library:
-
-.. list-table::
-   :header-rows: 1
-
-   * - zipp
-     - stdlib
-   * - 3.18
-     - 3.13
-   * - 3.16
-     - 3.12
-   * - 3.5
-     - 3.11
-   * - 3.2
-     - 3.10
-   * - 3.3 ??
-     - 3.9
-   * - 1.0
-     - 3.8
-
-
-Usage
-=====
-
-Use ``zipp.Path`` in place of ``zipfile.Path`` on any Python.
-
-For Enterprise
-==============
-
-Available as part of the Tidelift Subscription.
-
-This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use.
-
-`Learn more `_.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/RECORD
deleted file mode 100644
index 77c0283..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/RECORD
+++ /dev/null
@@ -1,15 +0,0 @@
-zipp-3.19.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-zipp-3.19.2.dist-info/LICENSE,sha256=htoPAa6uRjSKPD1GUZXcHOzN55956HdppkuNoEsqR0E,1023
-zipp-3.19.2.dist-info/METADATA,sha256=UIrk_kMIHGSwsKKChYizqMw0MMZpPRZ2ZiVpQAsN_bE,3575
-zipp-3.19.2.dist-info/RECORD,,
-zipp-3.19.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-zipp-3.19.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-zipp-3.19.2.dist-info/top_level.txt,sha256=iAbdoSHfaGqBfVb2XuR9JqSQHCoOsOtG6y9C_LSpqFw,5
-zipp/__init__.py,sha256=QuI1g00G4fRAcGt-HqbV0oWIkmSgedCGGYsHHYzNa8A,13412
-zipp/__pycache__/__init__.cpython-312.pyc,,
-zipp/__pycache__/glob.cpython-312.pyc,,
-zipp/compat/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-zipp/compat/__pycache__/__init__.cpython-312.pyc,,
-zipp/compat/__pycache__/py310.cpython-312.pyc,,
-zipp/compat/py310.py,sha256=eZpkW0zRtunkhEh8jjX3gCGe22emoKCBJw72Zt4RkhA,219
-zipp/glob.py,sha256=etWpnfEoRyfUvrUsi6sTiGmErvPwe6HzY6pT8jg_lUI,3082
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/REQUESTED
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/WHEEL
deleted file mode 100644
index bab98d6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/WHEEL
+++ /dev/null
@@ -1,5 +0,0 @@
-Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
-Root-Is-Purelib: true
-Tag: py3-none-any
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/top_level.txt
deleted file mode 100644
index e82f676..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp-3.19.2.dist-info/top_level.txt
+++ /dev/null
@@ -1 +0,0 @@
-zipp
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__init__.py
deleted file mode 100644
index d65297b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__init__.py
+++ /dev/null
@@ -1,501 +0,0 @@
-import io
-import posixpath
-import zipfile
-import itertools
-import contextlib
-import pathlib
-import re
-import stat
-import sys
-
-from .compat.py310 import text_encoding
-from .glob import Translator
-
-
-__all__ = ['Path']
-
-
-def _parents(path):
-    """
-    Given a path with elements separated by
-    posixpath.sep, generate all parents of that path.
-
-    >>> list(_parents('b/d'))
-    ['b']
-    >>> list(_parents('/b/d/'))
-    ['/b']
-    >>> list(_parents('b/d/f/'))
-    ['b/d', 'b']
-    >>> list(_parents('b'))
-    []
-    >>> list(_parents(''))
-    []
-    """
-    return itertools.islice(_ancestry(path), 1, None)
-
-
-def _ancestry(path):
-    """
-    Given a path with elements separated by
-    posixpath.sep, generate all elements of that path
-
-    >>> list(_ancestry('b/d'))
-    ['b/d', 'b']
-    >>> list(_ancestry('/b/d/'))
-    ['/b/d', '/b']
-    >>> list(_ancestry('b/d/f/'))
-    ['b/d/f', 'b/d', 'b']
-    >>> list(_ancestry('b'))
-    ['b']
-    >>> list(_ancestry(''))
-    []
-    """
-    path = path.rstrip(posixpath.sep)
-    while path and path != posixpath.sep:
-        yield path
-        path, tail = posixpath.split(path)
-
-
-_dedupe = dict.fromkeys
-"""Deduplicate an iterable in original order"""
-
-
-def _difference(minuend, subtrahend):
-    """
-    Return items in minuend not in subtrahend, retaining order
-    with O(1) lookup.
-    """
-    return itertools.filterfalse(set(subtrahend).__contains__, minuend)
-
-
-class InitializedState:
-    """
-    Mix-in to save the initialization state for pickling.
-    """
-
-    def __init__(self, *args, **kwargs):
-        self.__args = args
-        self.__kwargs = kwargs
-        super().__init__(*args, **kwargs)
-
-    def __getstate__(self):
-        return self.__args, self.__kwargs
-
-    def __setstate__(self, state):
-        args, kwargs = state
-        super().__init__(*args, **kwargs)
-
-
-class SanitizedNames:
-    """
-    ZipFile mix-in to ensure names are sanitized.
-    """
-
-    def namelist(self):
-        return list(map(self._sanitize, super().namelist()))
-
-    @staticmethod
-    def _sanitize(name):
-        r"""
-        Ensure a relative path with posix separators and no dot names.
-
-        Modeled after
-        https://github.com/python/cpython/blob/bcc1be39cb1d04ad9fc0bd1b9193d3972835a57c/Lib/zipfile/__init__.py#L1799-L1813
-        but provides consistent cross-platform behavior.
-
-        >>> san = SanitizedNames._sanitize
-        >>> san('/foo/bar')
-        'foo/bar'
-        >>> san('//foo.txt')
-        'foo.txt'
-        >>> san('foo/.././bar.txt')
-        'foo/bar.txt'
-        >>> san('foo../.bar.txt')
-        'foo../.bar.txt'
-        >>> san('\\foo\\bar.txt')
-        'foo/bar.txt'
-        >>> san('D:\\foo.txt')
-        'D/foo.txt'
-        >>> san('\\\\server\\share\\file.txt')
-        'server/share/file.txt'
-        >>> san('\\\\?\\GLOBALROOT\\Volume3')
-        '?/GLOBALROOT/Volume3'
-        >>> san('\\\\.\\PhysicalDrive1\\root')
-        'PhysicalDrive1/root'
-
-        Retain any trailing slash.
-        >>> san('abc/')
-        'abc/'
-
-        Raises a ValueError if the result is empty.
-        >>> san('../..')
-        Traceback (most recent call last):
-        ...
-        ValueError: Empty filename
-        """
-
-        def allowed(part):
-            return part and part not in {'..', '.'}
-
-        # Remove the drive letter.
-        # Don't use ntpath.splitdrive, because that also strips UNC paths
-        bare = re.sub('^([A-Z]):', r'\1', name, flags=re.IGNORECASE)
-        clean = bare.replace('\\', '/')
-        parts = clean.split('/')
-        joined = '/'.join(filter(allowed, parts))
-        if not joined:
-            raise ValueError("Empty filename")
-        return joined + '/' * name.endswith('/')
-
-
-class CompleteDirs(InitializedState, SanitizedNames, zipfile.ZipFile):
-    """
-    A ZipFile subclass that ensures that implied directories
-    are always included in the namelist.
-
-    >>> list(CompleteDirs._implied_dirs(['foo/bar.txt', 'foo/bar/baz.txt']))
-    ['foo/', 'foo/bar/']
-    >>> list(CompleteDirs._implied_dirs(['foo/bar.txt', 'foo/bar/baz.txt', 'foo/bar/']))
-    ['foo/']
-    """
-
-    @staticmethod
-    def _implied_dirs(names):
-        parents = itertools.chain.from_iterable(map(_parents, names))
-        as_dirs = (p + posixpath.sep for p in parents)
-        return _dedupe(_difference(as_dirs, names))
-
-    def namelist(self):
-        names = super().namelist()
-        return names + list(self._implied_dirs(names))
-
-    def _name_set(self):
-        return set(self.namelist())
-
-    def resolve_dir(self, name):
-        """
-        If the name represents a directory, return that name
-        as a directory (with the trailing slash).
-        """
-        names = self._name_set()
-        dirname = name + '/'
-        dir_match = name not in names and dirname in names
-        return dirname if dir_match else name
-
-    def getinfo(self, name):
-        """
-        Supplement getinfo for implied dirs.
-        """
-        try:
-            return super().getinfo(name)
-        except KeyError:
-            if not name.endswith('/') or name not in self._name_set():
-                raise
-            return zipfile.ZipInfo(filename=name)
-
-    @classmethod
-    def make(cls, source):
-        """
-        Given a source (filename or zipfile), return an
-        appropriate CompleteDirs subclass.
-        """
-        if isinstance(source, CompleteDirs):
-            return source
-
-        if not isinstance(source, zipfile.ZipFile):
-            return cls(source)
-
-        # Only allow for FastLookup when supplied zipfile is read-only
-        if 'r' not in source.mode:
-            cls = CompleteDirs
-
-        source.__class__ = cls
-        return source
-
-    @classmethod
-    def inject(cls, zf: zipfile.ZipFile) -> zipfile.ZipFile:
-        """
-        Given a writable zip file zf, inject directory entries for
-        any directories implied by the presence of children.
-        """
-        for name in cls._implied_dirs(zf.namelist()):
-            zf.writestr(name, b"")
-        return zf
-
-
-class FastLookup(CompleteDirs):
-    """
-    ZipFile subclass to ensure implicit
-    dirs exist and are resolved rapidly.
-    """
-
-    def namelist(self):
-        with contextlib.suppress(AttributeError):
-            return self.__names
-        self.__names = super().namelist()
-        return self.__names
-
-    def _name_set(self):
-        with contextlib.suppress(AttributeError):
-            return self.__lookup
-        self.__lookup = super()._name_set()
-        return self.__lookup
-
-
-def _extract_text_encoding(encoding=None, *args, **kwargs):
-    # compute stack level so that the caller of the caller sees any warning.
-    is_pypy = sys.implementation.name == 'pypy'
-    stack_level = 3 + is_pypy
-    return text_encoding(encoding, stack_level), args, kwargs
-
-
-class Path:
-    """
-    A :class:`importlib.resources.abc.Traversable` interface for zip files.
-
-    Implements many of the features users enjoy from
-    :class:`pathlib.Path`.
-
-    Consider a zip file with this structure::
-
-        .
-        ├── a.txt
-        └── b
-            ├── c.txt
-            └── d
-                └── e.txt
-
-    >>> data = io.BytesIO()
-    >>> zf = zipfile.ZipFile(data, 'w')
-    >>> zf.writestr('a.txt', 'content of a')
-    >>> zf.writestr('b/c.txt', 'content of c')
-    >>> zf.writestr('b/d/e.txt', 'content of e')
-    >>> zf.filename = 'mem/abcde.zip'
-
-    Path accepts the zipfile object itself or a filename
-
-    >>> path = Path(zf)
-
-    From there, several path operations are available.
-
-    Directory iteration (including the zip file itself):
-
-    >>> a, b = path.iterdir()
-    >>> a
-    Path('mem/abcde.zip', 'a.txt')
-    >>> b
-    Path('mem/abcde.zip', 'b/')
-
-    name property:
-
-    >>> b.name
-    'b'
-
-    join with divide operator:
-
-    >>> c = b / 'c.txt'
-    >>> c
-    Path('mem/abcde.zip', 'b/c.txt')
-    >>> c.name
-    'c.txt'
-
-    Read text:
-
-    >>> c.read_text(encoding='utf-8')
-    'content of c'
-
-    existence:
-
-    >>> c.exists()
-    True
-    >>> (b / 'missing.txt').exists()
-    False
-
-    Coercion to string:
-
-    >>> import os
-    >>> str(c).replace(os.sep, posixpath.sep)
-    'mem/abcde.zip/b/c.txt'
-
-    At the root, ``name``, ``filename``, and ``parent``
-    resolve to the zipfile.
-
-    >>> str(path)
-    'mem/abcde.zip/'
-    >>> path.name
-    'abcde.zip'
-    >>> path.filename == pathlib.Path('mem/abcde.zip')
-    True
-    >>> str(path.parent)
-    'mem'
-
-    If the zipfile has no filename, such attributes are not
-    valid and accessing them will raise an Exception.
-
-    >>> zf.filename = None
-    >>> path.name
-    Traceback (most recent call last):
-    ...
-    TypeError: ...
-
-    >>> path.filename
-    Traceback (most recent call last):
-    ...
-    TypeError: ...
-
-    >>> path.parent
-    Traceback (most recent call last):
-    ...
-    TypeError: ...
-
-    # workaround python/cpython#106763
-    >>> pass
-    """
-
-    __repr = "{self.__class__.__name__}({self.root.filename!r}, {self.at!r})"
-
-    def __init__(self, root, at=""):
-        """
-        Construct a Path from a ZipFile or filename.
-
-        Note: When the source is an existing ZipFile object,
-        its type (__class__) will be mutated to a
-        specialized type. If the caller wishes to retain the
-        original type, the caller should either create a
-        separate ZipFile object or pass a filename.
-        """
-        self.root = FastLookup.make(root)
-        self.at = at
-
-    def __eq__(self, other):
-        """
-        >>> Path(zipfile.ZipFile(io.BytesIO(), 'w')) == 'foo'
-        False
-        """
-        if self.__class__ is not other.__class__:
-            return NotImplemented
-        return (self.root, self.at) == (other.root, other.at)
-
-    def __hash__(self):
-        return hash((self.root, self.at))
-
-    def open(self, mode='r', *args, pwd=None, **kwargs):
-        """
-        Open this entry as text or binary following the semantics
-        of ``pathlib.Path.open()`` by passing arguments through
-        to io.TextIOWrapper().
-        """
-        if self.is_dir():
-            raise IsADirectoryError(self)
-        zip_mode = mode[0]
-        if not self.exists() and zip_mode == 'r':
-            raise FileNotFoundError(self)
-        stream = self.root.open(self.at, zip_mode, pwd=pwd)
-        if 'b' in mode:
-            if args or kwargs:
-                raise ValueError("encoding args invalid for binary operation")
-            return stream
-        # Text mode:
-        encoding, args, kwargs = _extract_text_encoding(*args, **kwargs)
-        return io.TextIOWrapper(stream, encoding, *args, **kwargs)
-
-    def _base(self):
-        return pathlib.PurePosixPath(self.at or self.root.filename)
-
-    @property
-    def name(self):
-        return self._base().name
-
-    @property
-    def suffix(self):
-        return self._base().suffix
-
-    @property
-    def suffixes(self):
-        return self._base().suffixes
-
-    @property
-    def stem(self):
-        return self._base().stem
-
-    @property
-    def filename(self):
-        return pathlib.Path(self.root.filename).joinpath(self.at)
-
-    def read_text(self, *args, **kwargs):
-        encoding, args, kwargs = _extract_text_encoding(*args, **kwargs)
-        with self.open('r', encoding, *args, **kwargs) as strm:
-            return strm.read()
-
-    def read_bytes(self):
-        with self.open('rb') as strm:
-            return strm.read()
-
-    def _is_child(self, path):
-        return posixpath.dirname(path.at.rstrip("/")) == self.at.rstrip("/")
-
-    def _next(self, at):
-        return self.__class__(self.root, at)
-
-    def is_dir(self):
-        return not self.at or self.at.endswith("/")
-
-    def is_file(self):
-        return self.exists() and not self.is_dir()
-
-    def exists(self):
-        return self.at in self.root._name_set()
-
-    def iterdir(self):
-        if not self.is_dir():
-            raise ValueError("Can't listdir a file")
-        subs = map(self._next, self.root.namelist())
-        return filter(self._is_child, subs)
-
-    def match(self, path_pattern):
-        return pathlib.PurePosixPath(self.at).match(path_pattern)
-
-    def is_symlink(self):
-        """
-        Return whether this path is a symlink.
-        """
-        info = self.root.getinfo(self.at)
-        mode = info.external_attr >> 16
-        return stat.S_ISLNK(mode)
-
-    def glob(self, pattern):
-        if not pattern:
-            raise ValueError(f"Unacceptable pattern: {pattern!r}")
-
-        prefix = re.escape(self.at)
-        tr = Translator(seps='/')
-        matches = re.compile(prefix + tr.translate(pattern)).fullmatch
-        names = (data.filename for data in self.root.filelist)
-        return map(self._next, filter(matches, names))
-
-    def rglob(self, pattern):
-        return self.glob(f'**/{pattern}')
-
-    def relative_to(self, other, *extra):
-        return posixpath.relpath(str(self), str(other.joinpath(*extra)))
-
-    def __str__(self):
-        return posixpath.join(self.root.filename, self.at)
-
-    def __repr__(self):
-        return self.__repr.format(self=self)
-
-    def joinpath(self, *other):
-        next = posixpath.join(self.at, *other)
-        return self._next(self.root.resolve_dir(next))
-
-    __truediv__ = joinpath
-
-    @property
-    def parent(self):
-        if not self.at:
-            return self.filename.parent
-        parent_at = posixpath.dirname(self.at.rstrip('/'))
-        if parent_at:
-            parent_at += '/'
-        return self._next(parent_at)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 6b5e472..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__pycache__/glob.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__pycache__/glob.cpython-312.pyc
deleted file mode 100644
index ac71f64..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/__pycache__/glob.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index a66b704..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__pycache__/py310.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__pycache__/py310.cpython-312.pyc
deleted file mode 100644
index e4d775c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/__pycache__/py310.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/py310.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/py310.py
deleted file mode 100644
index d5ca53e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/compat/py310.py
+++ /dev/null
@@ -1,11 +0,0 @@
-import sys
-import io
-
-
-def _text_encoding(encoding, stacklevel=2, /):  # pragma: no cover
-    return encoding
-
-
-text_encoding = (
-    io.text_encoding if sys.version_info > (3, 10) else _text_encoding  # type: ignore
-)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/glob.py b/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/glob.py
deleted file mode 100644
index 69c41d7..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/_vendor/zipp/glob.py
+++ /dev/null
@@ -1,106 +0,0 @@
-import os
-import re
-
-
-_default_seps = os.sep + str(os.altsep) * bool(os.altsep)
-
-
-class Translator:
-    """
-    >>> Translator('xyz')
-    Traceback (most recent call last):
-    ...
-    AssertionError: Invalid separators
-
-    >>> Translator('')
-    Traceback (most recent call last):
-    ...
-    AssertionError: Invalid separators
-    """
-
-    seps: str
-
-    def __init__(self, seps: str = _default_seps):
-        assert seps and set(seps) <= set(_default_seps), "Invalid separators"
-        self.seps = seps
-
-    def translate(self, pattern):
-        """
-        Given a glob pattern, produce a regex that matches it.
-        """
-        return self.extend(self.translate_core(pattern))
-
-    def extend(self, pattern):
-        r"""
-        Extend regex for pattern-wide concerns.
-
-        Apply '(?s:)' to create a non-matching group that
-        matches newlines (valid on Unix).
-
-        Append '\Z' to imply fullmatch even when match is used.
-        """
-        return rf'(?s:{pattern})\Z'
-
-    def translate_core(self, pattern):
-        r"""
-        Given a glob pattern, produce a regex that matches it.
-
-        >>> t = Translator()
-        >>> t.translate_core('*.txt').replace('\\\\', '')
-        '[^/]*\\.txt'
-        >>> t.translate_core('a?txt')
-        'a[^/]txt'
-        >>> t.translate_core('**/*').replace('\\\\', '')
-        '.*/[^/][^/]*'
-        """
-        self.restrict_rglob(pattern)
-        return ''.join(map(self.replace, separate(self.star_not_empty(pattern))))
-
-    def replace(self, match):
-        """
-        Perform the replacements for a match from :func:`separate`.
-        """
-        return match.group('set') or (
-            re.escape(match.group(0))
-            .replace('\\*\\*', r'.*')
-            .replace('\\*', rf'[^{re.escape(self.seps)}]*')
-            .replace('\\?', r'[^/]')
-        )
-
-    def restrict_rglob(self, pattern):
-        """
-        Raise ValueError if ** appears in anything but a full path segment.
-
-        >>> Translator().translate('**foo')
-        Traceback (most recent call last):
-        ...
-        ValueError: ** must appear alone in a path segment
-        """
-        seps_pattern = rf'[{re.escape(self.seps)}]+'
-        segments = re.split(seps_pattern, pattern)
-        if any('**' in segment and segment != '**' for segment in segments):
-            raise ValueError("** must appear alone in a path segment")
-
-    def star_not_empty(self, pattern):
-        """
-        Ensure that * will not match an empty segment.
-        """
-
-        def handle_segment(match):
-            segment = match.group(0)
-            return '?*' if segment == '*' else segment
-
-        not_seps_pattern = rf'[^{re.escape(self.seps)}]+'
-        return re.sub(not_seps_pattern, handle_segment, pattern)
-
-
-def separate(pattern):
-    """
-    Separate out character sets to avoid translating their contents.
-
-    >>> [m.group(0) for m in separate('*.txt')]
-    ['*.txt']
-    >>> [m.group(0) for m in separate('a[?]txt')]
-    ['a', '[?]', 'txt']
-    """
-    return re.finditer(r'([^\[]+)|(?P[\[].*?[\]])|([\[][^\]]*$)', pattern)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/archive_util.py b/llmlab/lib/python3.12/site-packages/setuptools/archive_util.py
deleted file mode 100644
index 1a02010..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/archive_util.py
+++ /dev/null
@@ -1,219 +0,0 @@
-"""Utilities for extracting common archive formats"""
-
-import contextlib
-import os
-import posixpath
-import shutil
-import tarfile
-import zipfile
-
-from ._path import ensure_directory
-
-from distutils.errors import DistutilsError
-
-__all__ = [
-    "unpack_archive",
-    "unpack_zipfile",
-    "unpack_tarfile",
-    "default_filter",
-    "UnrecognizedFormat",
-    "extraction_drivers",
-    "unpack_directory",
-]
-
-
-class UnrecognizedFormat(DistutilsError):
-    """Couldn't recognize the archive type"""
-
-
-def default_filter(src, dst):
-    """The default progress/filter callback; returns True for all files"""
-    return dst
-
-
-def unpack_archive(
-    filename, extract_dir, progress_filter=default_filter, drivers=None
-) -> None:
-    """Unpack `filename` to `extract_dir`, or raise ``UnrecognizedFormat``
-
-    `progress_filter` is a function taking two arguments: a source path
-    internal to the archive ('/'-separated), and a filesystem path where it
-    will be extracted.  The callback must return the desired extract path
-    (which may be the same as the one passed in), or else ``None`` to skip
-    that file or directory.  The callback can thus be used to report on the
-    progress of the extraction, as well as to filter the items extracted or
-    alter their extraction paths.
-
-    `drivers`, if supplied, must be a non-empty sequence of functions with the
-    same signature as this function (minus the `drivers` argument), that raise
-    ``UnrecognizedFormat`` if they do not support extracting the designated
-    archive type.  The `drivers` are tried in sequence until one is found that
-    does not raise an error, or until all are exhausted (in which case
-    ``UnrecognizedFormat`` is raised).  If you do not supply a sequence of
-    drivers, the module's ``extraction_drivers`` constant will be used, which
-    means that ``unpack_zipfile`` and ``unpack_tarfile`` will be tried, in that
-    order.
-    """
-    for driver in drivers or extraction_drivers:
-        try:
-            driver(filename, extract_dir, progress_filter)
-        except UnrecognizedFormat:
-            continue
-        else:
-            return
-    else:
-        raise UnrecognizedFormat(f"Not a recognized archive type: {filename}")
-
-
-def unpack_directory(filename, extract_dir, progress_filter=default_filter) -> None:
-    """ "Unpack" a directory, using the same interface as for archives
-
-    Raises ``UnrecognizedFormat`` if `filename` is not a directory
-    """
-    if not os.path.isdir(filename):
-        raise UnrecognizedFormat(f"{filename} is not a directory")
-
-    paths = {
-        filename: ('', extract_dir),
-    }
-    for base, dirs, files in os.walk(filename):
-        src, dst = paths[base]
-        for d in dirs:
-            paths[os.path.join(base, d)] = src + d + '/', os.path.join(dst, d)
-        for f in files:
-            target = os.path.join(dst, f)
-            target = progress_filter(src + f, target)
-            if not target:
-                # skip non-files
-                continue
-            ensure_directory(target)
-            f = os.path.join(base, f)
-            shutil.copyfile(f, target)
-            shutil.copystat(f, target)
-
-
-def unpack_zipfile(filename, extract_dir, progress_filter=default_filter) -> None:
-    """Unpack zip `filename` to `extract_dir`
-
-    Raises ``UnrecognizedFormat`` if `filename` is not a zipfile (as determined
-    by ``zipfile.is_zipfile()``).  See ``unpack_archive()`` for an explanation
-    of the `progress_filter` argument.
-    """
-
-    if not zipfile.is_zipfile(filename):
-        raise UnrecognizedFormat(f"{filename} is not a zip file")
-
-    with zipfile.ZipFile(filename) as z:
-        _unpack_zipfile_obj(z, extract_dir, progress_filter)
-
-
-def _unpack_zipfile_obj(zipfile_obj, extract_dir, progress_filter=default_filter):
-    """Internal/private API used by other parts of setuptools.
-    Similar to ``unpack_zipfile``, but receives an already opened :obj:`zipfile.ZipFile`
-    object instead of a filename.
-    """
-    for info in zipfile_obj.infolist():
-        name = info.filename
-
-        # don't extract absolute paths or ones with .. in them
-        if name.startswith('/') or '..' in name.split('/'):
-            continue
-
-        target = os.path.join(extract_dir, *name.split('/'))
-        target = progress_filter(name, target)
-        if not target:
-            continue
-        if name.endswith('/'):
-            # directory
-            ensure_directory(target)
-        else:
-            # file
-            ensure_directory(target)
-            data = zipfile_obj.read(info.filename)
-            with open(target, 'wb') as f:
-                f.write(data)
-        unix_attributes = info.external_attr >> 16
-        if unix_attributes:
-            os.chmod(target, unix_attributes)
-
-
-def _resolve_tar_file_or_dir(tar_obj, tar_member_obj):
-    """Resolve any links and extract link targets as normal files."""
-    while tar_member_obj is not None and (
-        tar_member_obj.islnk() or tar_member_obj.issym()
-    ):
-        linkpath = tar_member_obj.linkname
-        if tar_member_obj.issym():
-            base = posixpath.dirname(tar_member_obj.name)
-            linkpath = posixpath.join(base, linkpath)
-            linkpath = posixpath.normpath(linkpath)
-        tar_member_obj = tar_obj._getmember(linkpath)
-
-    is_file_or_dir = tar_member_obj is not None and (
-        tar_member_obj.isfile() or tar_member_obj.isdir()
-    )
-    if is_file_or_dir:
-        return tar_member_obj
-
-    raise LookupError('Got unknown file type')
-
-
-def _iter_open_tar(tar_obj, extract_dir, progress_filter):
-    """Emit member-destination pairs from a tar archive."""
-    # don't do any chowning!
-    tar_obj.chown = lambda *args: None
-
-    with contextlib.closing(tar_obj):
-        for member in tar_obj:
-            name = member.name
-            # don't extract absolute paths or ones with .. in them
-            if name.startswith('/') or '..' in name.split('/'):
-                continue
-
-            prelim_dst = os.path.join(extract_dir, *name.split('/'))
-
-            try:
-                member = _resolve_tar_file_or_dir(tar_obj, member)
-            except LookupError:
-                continue
-
-            final_dst = progress_filter(name, prelim_dst)
-            if not final_dst:
-                continue
-
-            if final_dst.endswith(os.sep):
-                final_dst = final_dst[:-1]
-
-            yield member, final_dst
-
-
-def unpack_tarfile(filename, extract_dir, progress_filter=default_filter) -> bool:
-    """Unpack tar/tar.gz/tar.bz2 `filename` to `extract_dir`
-
-    Raises ``UnrecognizedFormat`` if `filename` is not a tarfile (as determined
-    by ``tarfile.open()``).  See ``unpack_archive()`` for an explanation
-    of the `progress_filter` argument.
-    """
-    try:
-        tarobj = tarfile.open(filename)
-    except tarfile.TarError as e:
-        raise UnrecognizedFormat(
-            f"{filename} is not a compressed or uncompressed tar file"
-        ) from e
-
-    for member, final_dst in _iter_open_tar(
-        tarobj,
-        extract_dir,
-        progress_filter,
-    ):
-        try:
-            # XXX Ugh
-            tarobj._extract_member(member, final_dst)
-        except tarfile.ExtractError:
-            # chown/chmod/mkfifo/mknode/makedev failed
-            pass
-
-    return True
-
-
-extraction_drivers = unpack_directory, unpack_zipfile, unpack_tarfile
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/build_meta.py b/llmlab/lib/python3.12/site-packages/setuptools/build_meta.py
deleted file mode 100644
index 00fa5e1..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/build_meta.py
+++ /dev/null
@@ -1,560 +0,0 @@
-"""A PEP 517 interface to setuptools
-
-Previously, when a user or a command line tool (let's call it a "frontend")
-needed to make a request of setuptools to take a certain action, for
-example, generating a list of installation requirements, the frontend
-would call "setup.py egg_info" or "setup.py bdist_wheel" on the command line.
-
-PEP 517 defines a different method of interfacing with setuptools. Rather
-than calling "setup.py" directly, the frontend should:
-
-  1. Set the current directory to the directory with a setup.py file
-  2. Import this module into a safe python interpreter (one in which
-     setuptools can potentially set global variables or crash hard).
-  3. Call one of the functions defined in PEP 517.
-
-What each function does is defined in PEP 517. However, here is a "casual"
-definition of the functions (this definition should not be relied on for
-bug reports or API stability):
-
-  - `build_wheel`: build a wheel in the folder and return the basename
-  - `get_requires_for_build_wheel`: get the `setup_requires` to build
-  - `prepare_metadata_for_build_wheel`: get the `install_requires`
-  - `build_sdist`: build an sdist in the folder and return the basename
-  - `get_requires_for_build_sdist`: get the `setup_requires` to build
-
-Again, this is not a formal definition! Just a "taste" of the module.
-"""
-
-from __future__ import annotations
-
-import contextlib
-import io
-import os
-import shlex
-import shutil
-import sys
-import tempfile
-import tokenize
-import warnings
-from collections.abc import Iterable, Iterator, Mapping
-from pathlib import Path
-from typing import TYPE_CHECKING, Union
-
-import setuptools
-
-from . import errors
-from ._path import StrPath, same_path
-from ._reqs import parse_strings
-from .warnings import SetuptoolsDeprecationWarning
-
-import distutils
-from distutils.util import strtobool
-
-if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
-
-__all__ = [
-    'get_requires_for_build_sdist',
-    'get_requires_for_build_wheel',
-    'prepare_metadata_for_build_wheel',
-    'build_wheel',
-    'build_sdist',
-    'get_requires_for_build_editable',
-    'prepare_metadata_for_build_editable',
-    'build_editable',
-    '__legacy__',
-    'SetupRequirementsError',
-]
-
-SETUPTOOLS_ENABLE_FEATURES = os.getenv("SETUPTOOLS_ENABLE_FEATURES", "").lower()
-LEGACY_EDITABLE = "legacy-editable" in SETUPTOOLS_ENABLE_FEATURES.replace("_", "-")
-
-
-class SetupRequirementsError(BaseException):
-    def __init__(self, specifiers) -> None:
-        self.specifiers = specifiers
-
-
-class Distribution(setuptools.dist.Distribution):
-    def fetch_build_eggs(self, specifiers):
-        specifier_list = list(parse_strings(specifiers))
-
-        raise SetupRequirementsError(specifier_list)
-
-    @classmethod
-    @contextlib.contextmanager
-    def patch(cls):
-        """
-        Replace
-        distutils.dist.Distribution with this class
-        for the duration of this context.
-        """
-        orig = distutils.core.Distribution
-        distutils.core.Distribution = cls  # type: ignore[misc] # monkeypatching
-        try:
-            yield
-        finally:
-            distutils.core.Distribution = orig  # type: ignore[misc] # monkeypatching
-
-
-@contextlib.contextmanager
-def no_install_setup_requires():
-    """Temporarily disable installing setup_requires
-
-    Under PEP 517, the backend reports build dependencies to the frontend,
-    and the frontend is responsible for ensuring they're installed.
-    So setuptools (acting as a backend) should not try to install them.
-    """
-    orig = setuptools._install_setup_requires
-    setuptools._install_setup_requires = lambda attrs: None
-    try:
-        yield
-    finally:
-        setuptools._install_setup_requires = orig
-
-
-def _get_immediate_subdirectories(a_dir):
-    return [
-        name for name in os.listdir(a_dir) if os.path.isdir(os.path.join(a_dir, name))
-    ]
-
-
-def _file_with_extension(directory: StrPath, extension: str | tuple[str, ...]):
-    matching = (f for f in os.listdir(directory) if f.endswith(extension))
-    try:
-        (file,) = matching
-    except ValueError:
-        raise ValueError(
-            'No distribution was found. Ensure that `setup.py` '
-            'is not empty and that it calls `setup()`.'
-        ) from None
-    return file
-
-
-def _open_setup_script(setup_script):
-    if not os.path.exists(setup_script):
-        # Supply a default setup.py
-        return io.StringIO("from setuptools import setup; setup()")
-
-    return tokenize.open(setup_script)
-
-
-@contextlib.contextmanager
-def suppress_known_deprecation():
-    with warnings.catch_warnings():
-        warnings.filterwarnings('ignore', 'setup.py install is deprecated')
-        yield
-
-
-_ConfigSettings: TypeAlias = Union[Mapping[str, Union[str, list[str], None]], None]
-"""
-Currently the user can run::
-
-    pip install -e . --config-settings key=value
-    python -m build -C--key=value -C key=value
-
-- pip will pass both key and value as strings and overwriting repeated keys
-  (pypa/pip#11059).
-- build will accumulate values associated with repeated keys in a list.
-  It will also accept keys with no associated value.
-  This means that an option passed by build can be ``str | list[str] | None``.
-- PEP 517 specifies that ``config_settings`` is an optional dict.
-"""
-
-
-class _ConfigSettingsTranslator:
-    """Translate ``config_settings`` into distutils-style command arguments.
-    Only a limited number of options is currently supported.
-    """
-
-    # See pypa/setuptools#1928 pypa/setuptools#2491
-
-    def _get_config(self, key: str, config_settings: _ConfigSettings) -> list[str]:
-        """
-        Get the value of a specific key in ``config_settings`` as a list of strings.
-
-        >>> fn = _ConfigSettingsTranslator()._get_config
-        >>> fn("--global-option", None)
-        []
-        >>> fn("--global-option", {})
-        []
-        >>> fn("--global-option", {'--global-option': 'foo'})
-        ['foo']
-        >>> fn("--global-option", {'--global-option': ['foo']})
-        ['foo']
-        >>> fn("--global-option", {'--global-option': 'foo'})
-        ['foo']
-        >>> fn("--global-option", {'--global-option': 'foo bar'})
-        ['foo', 'bar']
-        """
-        cfg = config_settings or {}
-        opts = cfg.get(key) or []
-        return shlex.split(opts) if isinstance(opts, str) else opts
-
-    def _global_args(self, config_settings: _ConfigSettings) -> Iterator[str]:
-        """
-        Let the user specify ``verbose`` or ``quiet`` + escape hatch via
-        ``--global-option``.
-        Note: ``-v``, ``-vv``, ``-vvv`` have similar effects in setuptools,
-        so we just have to cover the basic scenario ``-v``.
-
-        >>> fn = _ConfigSettingsTranslator()._global_args
-        >>> list(fn(None))
-        []
-        >>> list(fn({"verbose": "False"}))
-        ['-q']
-        >>> list(fn({"verbose": "1"}))
-        ['-v']
-        >>> list(fn({"--verbose": None}))
-        ['-v']
-        >>> list(fn({"verbose": "true", "--global-option": "-q --no-user-cfg"}))
-        ['-v', '-q', '--no-user-cfg']
-        >>> list(fn({"--quiet": None}))
-        ['-q']
-        """
-        cfg = config_settings or {}
-        falsey = {"false", "no", "0", "off"}
-        if "verbose" in cfg or "--verbose" in cfg:
-            level = str(cfg.get("verbose") or cfg.get("--verbose") or "1")
-            yield ("-q" if level.lower() in falsey else "-v")
-        if "quiet" in cfg or "--quiet" in cfg:
-            level = str(cfg.get("quiet") or cfg.get("--quiet") or "1")
-            yield ("-v" if level.lower() in falsey else "-q")
-
-        yield from self._get_config("--global-option", config_settings)
-
-    def __dist_info_args(self, config_settings: _ConfigSettings) -> Iterator[str]:
-        """
-        The ``dist_info`` command accepts ``tag-date`` and ``tag-build``.
-
-        .. warning::
-           We cannot use this yet as it requires the ``sdist`` and ``bdist_wheel``
-           commands run in ``build_sdist`` and ``build_wheel`` to reuse the egg-info
-           directory created in ``prepare_metadata_for_build_wheel``.
-
-        >>> fn = _ConfigSettingsTranslator()._ConfigSettingsTranslator__dist_info_args
-        >>> list(fn(None))
-        []
-        >>> list(fn({"tag-date": "False"}))
-        ['--no-date']
-        >>> list(fn({"tag-date": None}))
-        ['--no-date']
-        >>> list(fn({"tag-date": "true", "tag-build": ".a"}))
-        ['--tag-date', '--tag-build', '.a']
-        """
-        cfg = config_settings or {}
-        if "tag-date" in cfg:
-            val = strtobool(str(cfg["tag-date"] or "false"))
-            yield ("--tag-date" if val else "--no-date")
-        if "tag-build" in cfg:
-            yield from ["--tag-build", str(cfg["tag-build"])]
-
-    def _editable_args(self, config_settings: _ConfigSettings) -> Iterator[str]:
-        """
-        The ``editable_wheel`` command accepts ``editable-mode=strict``.
-
-        >>> fn = _ConfigSettingsTranslator()._editable_args
-        >>> list(fn(None))
-        []
-        >>> list(fn({"editable-mode": "strict"}))
-        ['--mode', 'strict']
-        """
-        cfg = config_settings or {}
-        mode = cfg.get("editable-mode") or cfg.get("editable_mode")
-        if not mode:
-            return
-        yield from ["--mode", str(mode)]
-
-    def _arbitrary_args(self, config_settings: _ConfigSettings) -> Iterator[str]:
-        """
-        Users may expect to pass arbitrary lists of arguments to a command
-        via "--global-option" (example provided in PEP 517 of a "escape hatch").
-
-        >>> fn = _ConfigSettingsTranslator()._arbitrary_args
-        >>> list(fn(None))
-        []
-        >>> list(fn({}))
-        []
-        >>> list(fn({'--build-option': 'foo'}))
-        ['foo']
-        >>> list(fn({'--build-option': ['foo']}))
-        ['foo']
-        >>> list(fn({'--build-option': 'foo'}))
-        ['foo']
-        >>> list(fn({'--build-option': 'foo bar'}))
-        ['foo', 'bar']
-        >>> list(fn({'--global-option': 'foo'}))
-        []
-        """
-        yield from self._get_config("--build-option", config_settings)
-
-
-class _BuildMetaBackend(_ConfigSettingsTranslator):
-    def _get_build_requires(
-        self, config_settings: _ConfigSettings, requirements: list[str]
-    ):
-        sys.argv = [
-            *sys.argv[:1],
-            *self._global_args(config_settings),
-            "egg_info",
-        ]
-        try:
-            with Distribution.patch():
-                self.run_setup()
-        except SetupRequirementsError as e:
-            requirements += e.specifiers
-
-        return requirements
-
-    def run_setup(self, setup_script: str = 'setup.py'):
-        # Note that we can reuse our build directory between calls
-        # Correctness comes first, then optimization later
-        __file__ = os.path.abspath(setup_script)
-        __name__ = '__main__'
-
-        with _open_setup_script(__file__) as f:
-            code = f.read().replace(r'\r\n', r'\n')
-
-        try:
-            exec(code, locals())
-        except SystemExit as e:
-            if e.code:
-                raise
-            # We ignore exit code indicating success
-            SetuptoolsDeprecationWarning.emit(
-                "Running `setup.py` directly as CLI tool is deprecated.",
-                "Please avoid using `sys.exit(0)` or similar statements "
-                "that don't fit in the paradigm of a configuration file.",
-                see_url="https://blog.ganssle.io/articles/2021/10/"
-                "setup-py-deprecated.html",
-            )
-
-    def get_requires_for_build_wheel(self, config_settings: _ConfigSettings = None):
-        return self._get_build_requires(config_settings, requirements=[])
-
-    def get_requires_for_build_sdist(self, config_settings: _ConfigSettings = None):
-        return self._get_build_requires(config_settings, requirements=[])
-
-    def _bubble_up_info_directory(
-        self, metadata_directory: StrPath, suffix: str
-    ) -> str:
-        """
-        PEP 517 requires that the .dist-info directory be placed in the
-        metadata_directory. To comply, we MUST copy the directory to the root.
-
-        Returns the basename of the info directory, e.g. `proj-0.0.0.dist-info`.
-        """
-        info_dir = self._find_info_directory(metadata_directory, suffix)
-        if not same_path(info_dir.parent, metadata_directory):
-            shutil.move(str(info_dir), metadata_directory)
-            # PEP 517 allow other files and dirs to exist in metadata_directory
-        return info_dir.name
-
-    def _find_info_directory(self, metadata_directory: StrPath, suffix: str) -> Path:
-        for parent, dirs, _ in os.walk(metadata_directory):
-            candidates = [f for f in dirs if f.endswith(suffix)]
-
-            if len(candidates) != 0 or len(dirs) != 1:
-                assert len(candidates) == 1, f"Multiple {suffix} directories found"
-                return Path(parent, candidates[0])
-
-        msg = f"No {suffix} directory found in {metadata_directory}"
-        raise errors.InternalError(msg)
-
-    def prepare_metadata_for_build_wheel(
-        self, metadata_directory: StrPath, config_settings: _ConfigSettings = None
-    ):
-        sys.argv = [
-            *sys.argv[:1],
-            *self._global_args(config_settings),
-            "dist_info",
-            "--output-dir",
-            str(metadata_directory),
-            "--keep-egg-info",
-        ]
-        with no_install_setup_requires():
-            self.run_setup()
-
-        self._bubble_up_info_directory(metadata_directory, ".egg-info")
-        return self._bubble_up_info_directory(metadata_directory, ".dist-info")
-
-    def _build_with_temp_dir(
-        self,
-        setup_command: Iterable[str],
-        result_extension: str | tuple[str, ...],
-        result_directory: StrPath,
-        config_settings: _ConfigSettings,
-        arbitrary_args: Iterable[str] = (),
-    ):
-        result_directory = os.path.abspath(result_directory)
-
-        # Build in a temporary directory, then copy to the target.
-        os.makedirs(result_directory, exist_ok=True)
-
-        with tempfile.TemporaryDirectory(
-            prefix=".tmp-", dir=result_directory
-        ) as tmp_dist_dir:
-            sys.argv = [
-                *sys.argv[:1],
-                *self._global_args(config_settings),
-                *setup_command,
-                "--dist-dir",
-                tmp_dist_dir,
-                *arbitrary_args,
-            ]
-            with no_install_setup_requires():
-                self.run_setup()
-
-            result_basename = _file_with_extension(tmp_dist_dir, result_extension)
-            result_path = os.path.join(result_directory, result_basename)
-            if os.path.exists(result_path):
-                # os.rename will fail overwriting on non-Unix.
-                os.remove(result_path)
-            os.rename(os.path.join(tmp_dist_dir, result_basename), result_path)
-
-        return result_basename
-
-    def build_wheel(
-        self,
-        wheel_directory: StrPath,
-        config_settings: _ConfigSettings = None,
-        metadata_directory: StrPath | None = None,
-    ):
-        def _build(cmd: list[str]):
-            with suppress_known_deprecation():
-                return self._build_with_temp_dir(
-                    cmd,
-                    '.whl',
-                    wheel_directory,
-                    config_settings,
-                    self._arbitrary_args(config_settings),
-                )
-
-        if metadata_directory is None:
-            return _build(['bdist_wheel'])
-
-        try:
-            return _build(['bdist_wheel', '--dist-info-dir', str(metadata_directory)])
-        except SystemExit as ex:  # pragma: nocover
-            # pypa/setuptools#4683
-            if "--dist-info-dir not recognized" not in str(ex):
-                raise
-            _IncompatibleBdistWheel.emit()
-            return _build(['bdist_wheel'])
-
-    def build_sdist(
-        self, sdist_directory: StrPath, config_settings: _ConfigSettings = None
-    ):
-        return self._build_with_temp_dir(
-            ['sdist', '--formats', 'gztar'], '.tar.gz', sdist_directory, config_settings
-        )
-
-    def _get_dist_info_dir(self, metadata_directory: StrPath | None) -> str | None:
-        if not metadata_directory:
-            return None
-        dist_info_candidates = list(Path(metadata_directory).glob("*.dist-info"))
-        assert len(dist_info_candidates) <= 1
-        return str(dist_info_candidates[0]) if dist_info_candidates else None
-
-    if not LEGACY_EDITABLE:
-        # PEP660 hooks:
-        # build_editable
-        # get_requires_for_build_editable
-        # prepare_metadata_for_build_editable
-        def build_editable(
-            self,
-            wheel_directory: StrPath,
-            config_settings: _ConfigSettings = None,
-            metadata_directory: StrPath | None = None,
-        ):
-            # XXX can or should we hide our editable_wheel command normally?
-            info_dir = self._get_dist_info_dir(metadata_directory)
-            opts = ["--dist-info-dir", info_dir] if info_dir else []
-            cmd = ["editable_wheel", *opts, *self._editable_args(config_settings)]
-            with suppress_known_deprecation():
-                return self._build_with_temp_dir(
-                    cmd, ".whl", wheel_directory, config_settings
-                )
-
-        def get_requires_for_build_editable(
-            self, config_settings: _ConfigSettings = None
-        ):
-            return self.get_requires_for_build_wheel(config_settings)
-
-        def prepare_metadata_for_build_editable(
-            self, metadata_directory: StrPath, config_settings: _ConfigSettings = None
-        ):
-            return self.prepare_metadata_for_build_wheel(
-                metadata_directory, config_settings
-            )
-
-
-class _BuildMetaLegacyBackend(_BuildMetaBackend):
-    """Compatibility backend for setuptools
-
-    This is a version of setuptools.build_meta that endeavors
-    to maintain backwards
-    compatibility with pre-PEP 517 modes of invocation. It
-    exists as a temporary
-    bridge between the old packaging mechanism and the new
-    packaging mechanism,
-    and will eventually be removed.
-    """
-
-    def run_setup(self, setup_script: str = 'setup.py'):
-        # In order to maintain compatibility with scripts assuming that
-        # the setup.py script is in a directory on the PYTHONPATH, inject
-        # '' into sys.path. (pypa/setuptools#1642)
-        sys_path = list(sys.path)  # Save the original path
-
-        script_dir = os.path.dirname(os.path.abspath(setup_script))
-        if script_dir not in sys.path:
-            sys.path.insert(0, script_dir)
-
-        # Some setup.py scripts (e.g. in pygame and numpy) use sys.argv[0] to
-        # get the directory of the source code. They expect it to refer to the
-        # setup.py script.
-        sys_argv_0 = sys.argv[0]
-        sys.argv[0] = setup_script
-
-        try:
-            super().run_setup(setup_script=setup_script)
-        finally:
-            # While PEP 517 frontends should be calling each hook in a fresh
-            # subprocess according to the standard (and thus it should not be
-            # strictly necessary to restore the old sys.path), we'll restore
-            # the original path so that the path manipulation does not persist
-            # within the hook after run_setup is called.
-            sys.path[:] = sys_path
-            sys.argv[0] = sys_argv_0
-
-
-class _IncompatibleBdistWheel(SetuptoolsDeprecationWarning):
-    _SUMMARY = "wheel.bdist_wheel is deprecated, please import it from setuptools"
-    _DETAILS = """
-    Ensure that any custom bdist_wheel implementation is a subclass of
-    setuptools.command.bdist_wheel.bdist_wheel.
-    """
-    _DUE_DATE = (2025, 10, 15)
-    # Initially introduced in 2024/10/15, but maybe too disruptive to be enforced?
-    _SEE_URL = "https://github.com/pypa/wheel/pull/631"
-
-
-# The primary backend
-_BACKEND = _BuildMetaBackend()
-
-get_requires_for_build_wheel = _BACKEND.get_requires_for_build_wheel
-get_requires_for_build_sdist = _BACKEND.get_requires_for_build_sdist
-prepare_metadata_for_build_wheel = _BACKEND.prepare_metadata_for_build_wheel
-build_wheel = _BACKEND.build_wheel
-build_sdist = _BACKEND.build_sdist
-
-if not LEGACY_EDITABLE:
-    get_requires_for_build_editable = _BACKEND.get_requires_for_build_editable
-    prepare_metadata_for_build_editable = _BACKEND.prepare_metadata_for_build_editable
-    build_editable = _BACKEND.build_editable
-
-
-# The legacy backend
-__legacy__ = _BuildMetaLegacyBackend()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/cli-32.exe b/llmlab/lib/python3.12/site-packages/setuptools/cli-32.exe
deleted file mode 100644
index 65c3cd9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/cli-32.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/cli-64.exe b/llmlab/lib/python3.12/site-packages/setuptools/cli-64.exe
deleted file mode 100644
index 3ea50ee..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/cli-64.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/cli-arm64.exe b/llmlab/lib/python3.12/site-packages/setuptools/cli-arm64.exe
deleted file mode 100644
index da96455..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/cli-arm64.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/cli.exe b/llmlab/lib/python3.12/site-packages/setuptools/cli.exe
deleted file mode 100644
index 65c3cd9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/cli.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/command/__init__.py
deleted file mode 100644
index 50e6c2f..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/__init__.py
+++ /dev/null
@@ -1,21 +0,0 @@
-# mypy: disable_error_code=call-overload
-# pyright: reportCallIssue=false, reportArgumentType=false
-# Can't disable on the exact line because distutils doesn't exists on Python 3.12
-# and type-checkers aren't aware of distutils_hack,
-# causing distutils.command.bdist.bdist.format_commands to be Any.
-
-import sys
-
-from distutils.command.bdist import bdist
-
-if 'egg' not in bdist.format_commands:
-    try:
-        # format_commands is a dict in vendored distutils
-        # It used to be a list in older (stdlib) distutils
-        # We support both for backwards compatibility
-        bdist.format_commands['egg'] = ('bdist_egg', "Python .egg file")
-    except TypeError:
-        bdist.format_command['egg'] = ('bdist_egg', "Python .egg file")
-        bdist.format_commands.append('egg')
-
-del bdist, sys
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 04c2fe9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/_requirestxt.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/_requirestxt.cpython-312.pyc
deleted file mode 100644
index 64a6a06..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/_requirestxt.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/alias.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/alias.cpython-312.pyc
deleted file mode 100644
index 4612a63..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/alias.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_egg.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_egg.cpython-312.pyc
deleted file mode 100644
index 7877971..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_egg.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_rpm.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_rpm.cpython-312.pyc
deleted file mode 100644
index e847c5c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_rpm.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_wheel.cpython-312.pyc
deleted file mode 100644
index 64de3d7..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/bdist_wheel.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build.cpython-312.pyc
deleted file mode 100644
index 05e1764..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_clib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_clib.cpython-312.pyc
deleted file mode 100644
index 8338604..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_clib.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_ext.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_ext.cpython-312.pyc
deleted file mode 100644
index b6394d1..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_ext.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_py.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_py.cpython-312.pyc
deleted file mode 100644
index 7eda635..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/build_py.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/develop.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/develop.cpython-312.pyc
deleted file mode 100644
index fd4d176..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/develop.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/dist_info.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/dist_info.cpython-312.pyc
deleted file mode 100644
index e0a70a7..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/dist_info.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/easy_install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/easy_install.cpython-312.pyc
deleted file mode 100644
index c9c98b3..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/easy_install.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/editable_wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/editable_wheel.cpython-312.pyc
deleted file mode 100644
index daaf4c1..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/editable_wheel.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/egg_info.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/egg_info.cpython-312.pyc
deleted file mode 100644
index 2e76ab9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/egg_info.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install.cpython-312.pyc
deleted file mode 100644
index 16b0447..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_egg_info.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_egg_info.cpython-312.pyc
deleted file mode 100644
index 6c717da..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_egg_info.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_lib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_lib.cpython-312.pyc
deleted file mode 100644
index b3e1a87..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_lib.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_scripts.cpython-312.pyc
deleted file mode 100644
index 4d4d0de..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/install_scripts.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/rotate.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/rotate.cpython-312.pyc
deleted file mode 100644
index 7314a78..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/rotate.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/saveopts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/saveopts.cpython-312.pyc
deleted file mode 100644
index 65e277b..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/saveopts.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/sdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/sdist.cpython-312.pyc
deleted file mode 100644
index 42feb25..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/sdist.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/setopt.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/setopt.cpython-312.pyc
deleted file mode 100644
index 432adb0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/setopt.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/test.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/test.cpython-312.pyc
deleted file mode 100644
index 801260c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/command/__pycache__/test.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/_requirestxt.py b/llmlab/lib/python3.12/site-packages/setuptools/command/_requirestxt.py
deleted file mode 100644
index 9029b12..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/_requirestxt.py
+++ /dev/null
@@ -1,131 +0,0 @@
-"""Helper code used to generate ``requires.txt`` files in the egg-info directory.
-
-The ``requires.txt`` file has an specific format:
-    - Environment markers need to be part of the section headers and
-      should not be part of the requirement spec itself.
-
-See https://setuptools.pypa.io/en/latest/deprecated/python_eggs.html#requires-txt
-"""
-
-from __future__ import annotations
-
-import io
-from collections import defaultdict
-from collections.abc import Mapping
-from itertools import filterfalse
-from typing import TypeVar
-
-from jaraco.text import yield_lines
-from packaging.requirements import Requirement
-
-from .. import _reqs
-from .._reqs import _StrOrIter
-
-# dict can work as an ordered set
-_T = TypeVar("_T")
-_Ordered = dict[_T, None]
-
-
-def _prepare(
-    install_requires: _StrOrIter, extras_require: Mapping[str, _StrOrIter]
-) -> tuple[list[str], dict[str, list[str]]]:
-    """Given values for ``install_requires`` and ``extras_require``
-    create modified versions in a way that can be written in ``requires.txt``
-    """
-    extras = _convert_extras_requirements(extras_require)
-    return _move_install_requirements_markers(install_requires, extras)
-
-
-def _convert_extras_requirements(
-    extras_require: Mapping[str, _StrOrIter],
-) -> defaultdict[str, _Ordered[Requirement]]:
-    """
-    Convert requirements in `extras_require` of the form
-    `"extra": ["barbazquux; {marker}"]` to
-    `"extra:{marker}": ["barbazquux"]`.
-    """
-    output = defaultdict[str, _Ordered[Requirement]](dict)
-    for section, v in extras_require.items():
-        # Do not strip empty sections.
-        output[section]
-        for r in _reqs.parse(v):
-            output[section + _suffix_for(r)].setdefault(r)
-
-    return output
-
-
-def _move_install_requirements_markers(
-    install_requires: _StrOrIter, extras_require: Mapping[str, _Ordered[Requirement]]
-) -> tuple[list[str], dict[str, list[str]]]:
-    """
-    The ``requires.txt`` file has an specific format:
-        - Environment markers need to be part of the section headers and
-          should not be part of the requirement spec itself.
-
-    Move requirements in ``install_requires`` that are using environment
-    markers ``extras_require``.
-    """
-
-    # divide the install_requires into two sets, simple ones still
-    # handled by install_requires and more complex ones handled by extras_require.
-
-    inst_reqs = list(_reqs.parse(install_requires))
-    simple_reqs = filter(_no_marker, inst_reqs)
-    complex_reqs = filterfalse(_no_marker, inst_reqs)
-    simple_install_requires = list(map(str, simple_reqs))
-
-    for r in complex_reqs:
-        extras_require[':' + str(r.marker)].setdefault(r)
-
-    expanded_extras = dict(
-        # list(dict.fromkeys(...))  ensures a list of unique strings
-        (k, list(dict.fromkeys(str(r) for r in map(_clean_req, v))))
-        for k, v in extras_require.items()
-    )
-
-    return simple_install_requires, expanded_extras
-
-
-def _suffix_for(req):
-    """Return the 'extras_require' suffix for a given requirement."""
-    return ':' + str(req.marker) if req.marker else ''
-
-
-def _clean_req(req):
-    """Given a Requirement, remove environment markers and return it"""
-    r = Requirement(str(req))  # create a copy before modifying
-    r.marker = None
-    return r
-
-
-def _no_marker(req):
-    return not req.marker
-
-
-def _write_requirements(stream, reqs):
-    lines = yield_lines(reqs or ())
-
-    def append_cr(line):
-        return line + '\n'
-
-    lines = map(append_cr, lines)
-    stream.writelines(lines)
-
-
-def write_requirements(cmd, basename, filename):
-    dist = cmd.distribution
-    data = io.StringIO()
-    install_requires, extras_require = _prepare(
-        dist.install_requires or (), dist.extras_require or {}
-    )
-    _write_requirements(data, install_requires)
-    for extra in sorted(extras_require):
-        data.write('\n[{extra}]\n'.format(**vars()))
-        _write_requirements(data, extras_require[extra])
-    cmd.write_or_delete_file("requirements", filename, data.getvalue())
-
-
-def write_setup_requirements(cmd, basename, filename):
-    data = io.StringIO()
-    _write_requirements(data, cmd.distribution.setup_requires)
-    cmd.write_or_delete_file("setup-requirements", filename, data.getvalue())
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/alias.py b/llmlab/lib/python3.12/site-packages/setuptools/command/alias.py
deleted file mode 100644
index b8d74af..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/alias.py
+++ /dev/null
@@ -1,77 +0,0 @@
-from setuptools.command.setopt import config_file, edit_config, option_base
-
-from distutils.errors import DistutilsOptionError
-
-
-def shquote(arg):
-    """Quote an argument for later parsing by shlex.split()"""
-    for c in '"', "'", "\\", "#":
-        if c in arg:
-            return repr(arg)
-    if arg.split() != [arg]:
-        return repr(arg)
-    return arg
-
-
-class alias(option_base):
-    """Define a shortcut that invokes one or more commands"""
-
-    description = "define a shortcut to invoke one or more commands"
-    command_consumes_arguments = True
-
-    user_options = [
-        ('remove', 'r', 'remove (unset) the alias'),
-    ] + option_base.user_options
-
-    boolean_options = option_base.boolean_options + ['remove']
-
-    def initialize_options(self):
-        option_base.initialize_options(self)
-        self.args = None
-        self.remove = None
-
-    def finalize_options(self) -> None:
-        option_base.finalize_options(self)
-        if self.remove and len(self.args) != 1:
-            raise DistutilsOptionError(
-                "Must specify exactly one argument (the alias name) when using --remove"
-            )
-
-    def run(self) -> None:
-        aliases = self.distribution.get_option_dict('aliases')
-
-        if not self.args:
-            print("Command Aliases")
-            print("---------------")
-            for alias in aliases:
-                print("setup.py alias", format_alias(alias, aliases))
-            return
-
-        elif len(self.args) == 1:
-            (alias,) = self.args
-            if self.remove:
-                command = None
-            elif alias in aliases:
-                print("setup.py alias", format_alias(alias, aliases))
-                return
-            else:
-                print(f"No alias definition found for {alias!r}")
-                return
-        else:
-            alias = self.args[0]
-            command = ' '.join(map(shquote, self.args[1:]))
-
-        edit_config(self.filename, {'aliases': {alias: command}}, self.dry_run)
-
-
-def format_alias(name, aliases):
-    source, command = aliases[name]
-    if source == config_file('global'):
-        source = '--global-config '
-    elif source == config_file('user'):
-        source = '--user-config '
-    elif source == config_file('local'):
-        source = ''
-    else:
-        source = f'--filename={source!r}'
-    return source + name + ' ' + command
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_egg.py b/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_egg.py
deleted file mode 100644
index 7f66c3b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_egg.py
+++ /dev/null
@@ -1,479 +0,0 @@
-"""setuptools.command.bdist_egg
-
-Build .egg distributions"""
-
-from __future__ import annotations
-
-import marshal
-import os
-import re
-import sys
-import textwrap
-from sysconfig import get_path, get_python_version
-from types import CodeType
-from typing import TYPE_CHECKING, Literal
-
-from setuptools import Command
-from setuptools.extension import Library
-
-from .._path import StrPathT, ensure_directory
-
-from distutils import log
-from distutils.dir_util import mkpath, remove_tree
-
-if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
-
-# Same as zipfile._ZipFileMode from typeshed
-_ZipFileMode: TypeAlias = Literal["r", "w", "x", "a"]
-
-
-def _get_purelib():
-    return get_path("purelib")
-
-
-def strip_module(filename):
-    if '.' in filename:
-        filename = os.path.splitext(filename)[0]
-    if filename.endswith('module'):
-        filename = filename[:-6]
-    return filename
-
-
-def sorted_walk(dir):
-    """Do os.walk in a reproducible way,
-    independent of indeterministic filesystem readdir order
-    """
-    for base, dirs, files in os.walk(dir):
-        dirs.sort()
-        files.sort()
-        yield base, dirs, files
-
-
-def write_stub(resource, pyfile) -> None:
-    _stub_template = textwrap.dedent(
-        """
-        def __bootstrap__():
-            global __bootstrap__, __loader__, __file__
-            import sys, pkg_resources, importlib.util
-            __file__ = pkg_resources.resource_filename(__name__, %r)
-            __loader__ = None; del __bootstrap__, __loader__
-            spec = importlib.util.spec_from_file_location(__name__,__file__)
-            mod = importlib.util.module_from_spec(spec)
-            spec.loader.exec_module(mod)
-        __bootstrap__()
-        """
-    ).lstrip()
-    with open(pyfile, 'w', encoding="utf-8") as f:
-        f.write(_stub_template % resource)
-
-
-class bdist_egg(Command):
-    description = 'create an "egg" distribution'
-
-    user_options = [
-        ('bdist-dir=', 'b', "temporary directory for creating the distribution"),
-        (
-            'plat-name=',
-            'p',
-            "platform name to embed in generated filenames "
-            "(by default uses `pkg_resources.get_build_platform()`)",
-        ),
-        ('exclude-source-files', None, "remove all .py files from the generated egg"),
-        (
-            'keep-temp',
-            'k',
-            "keep the pseudo-installation tree around after "
-            "creating the distribution archive",
-        ),
-        ('dist-dir=', 'd', "directory to put final built distributions in"),
-        ('skip-build', None, "skip rebuilding everything (for testing/debugging)"),
-    ]
-
-    boolean_options = ['keep-temp', 'skip-build', 'exclude-source-files']
-
-    def initialize_options(self):
-        self.bdist_dir = None
-        self.plat_name = None
-        self.keep_temp = False
-        self.dist_dir = None
-        self.skip_build = False
-        self.egg_output = None
-        self.exclude_source_files = None
-
-    def finalize_options(self) -> None:
-        ei_cmd = self.ei_cmd = self.get_finalized_command("egg_info")
-        self.egg_info = ei_cmd.egg_info
-
-        if self.bdist_dir is None:
-            bdist_base = self.get_finalized_command('bdist').bdist_base
-            self.bdist_dir = os.path.join(bdist_base, 'egg')
-
-        if self.plat_name is None:
-            from pkg_resources import get_build_platform
-
-            self.plat_name = get_build_platform()
-
-        self.set_undefined_options('bdist', ('dist_dir', 'dist_dir'))
-
-        if self.egg_output is None:
-            # Compute filename of the output egg
-            basename = ei_cmd._get_egg_basename(
-                py_version=get_python_version(),
-                platform=self.distribution.has_ext_modules() and self.plat_name,
-            )
-
-            self.egg_output = os.path.join(self.dist_dir, basename + '.egg')
-
-    def do_install_data(self) -> None:
-        # Hack for packages that install data to install's --install-lib
-        self.get_finalized_command('install').install_lib = self.bdist_dir
-
-        site_packages = os.path.normcase(os.path.realpath(_get_purelib()))
-        old, self.distribution.data_files = self.distribution.data_files, []
-
-        for item in old:
-            if isinstance(item, tuple) and len(item) == 2:
-                if os.path.isabs(item[0]):
-                    realpath = os.path.realpath(item[0])
-                    normalized = os.path.normcase(realpath)
-                    if normalized == site_packages or normalized.startswith(
-                        site_packages + os.sep
-                    ):
-                        item = realpath[len(site_packages) + 1 :], item[1]
-                        # XXX else: raise ???
-            self.distribution.data_files.append(item)
-
-        try:
-            log.info("installing package data to %s", self.bdist_dir)
-            self.call_command('install_data', force=False, root=None)
-        finally:
-            self.distribution.data_files = old
-
-    def get_outputs(self):
-        return [self.egg_output]
-
-    def call_command(self, cmdname, **kw):
-        """Invoke reinitialized command `cmdname` with keyword args"""
-        for dirname in INSTALL_DIRECTORY_ATTRS:
-            kw.setdefault(dirname, self.bdist_dir)
-        kw.setdefault('skip_build', self.skip_build)
-        kw.setdefault('dry_run', self.dry_run)
-        cmd = self.reinitialize_command(cmdname, **kw)
-        self.run_command(cmdname)
-        return cmd
-
-    def run(self):  # noqa: C901  # is too complex (14)  # FIXME
-        # Generate metadata first
-        self.run_command("egg_info")
-        # We run install_lib before install_data, because some data hacks
-        # pull their data path from the install_lib command.
-        log.info("installing library code to %s", self.bdist_dir)
-        instcmd = self.get_finalized_command('install')
-        old_root = instcmd.root
-        instcmd.root = None
-        if self.distribution.has_c_libraries() and not self.skip_build:
-            self.run_command('build_clib')
-        cmd = self.call_command('install_lib', warn_dir=False)
-        instcmd.root = old_root
-
-        all_outputs, ext_outputs = self.get_ext_outputs()
-        self.stubs = []
-        to_compile = []
-        for p, ext_name in enumerate(ext_outputs):
-            filename, _ext = os.path.splitext(ext_name)
-            pyfile = os.path.join(self.bdist_dir, strip_module(filename) + '.py')
-            self.stubs.append(pyfile)
-            log.info("creating stub loader for %s", ext_name)
-            if not self.dry_run:
-                write_stub(os.path.basename(ext_name), pyfile)
-            to_compile.append(pyfile)
-            ext_outputs[p] = ext_name.replace(os.sep, '/')
-
-        if to_compile:
-            cmd.byte_compile(to_compile)
-        if self.distribution.data_files:
-            self.do_install_data()
-
-        # Make the EGG-INFO directory
-        archive_root = self.bdist_dir
-        egg_info = os.path.join(archive_root, 'EGG-INFO')
-        self.mkpath(egg_info)
-        if self.distribution.scripts:
-            script_dir = os.path.join(egg_info, 'scripts')
-            log.info("installing scripts to %s", script_dir)
-            self.call_command('install_scripts', install_dir=script_dir, no_ep=True)
-
-        self.copy_metadata_to(egg_info)
-        native_libs = os.path.join(egg_info, "native_libs.txt")
-        if all_outputs:
-            log.info("writing %s", native_libs)
-            if not self.dry_run:
-                ensure_directory(native_libs)
-                with open(native_libs, 'wt', encoding="utf-8") as libs_file:
-                    libs_file.write('\n'.join(all_outputs))
-                    libs_file.write('\n')
-        elif os.path.isfile(native_libs):
-            log.info("removing %s", native_libs)
-            if not self.dry_run:
-                os.unlink(native_libs)
-
-        write_safety_flag(os.path.join(archive_root, 'EGG-INFO'), self.zip_safe())
-
-        if os.path.exists(os.path.join(self.egg_info, 'depends.txt')):
-            log.warn(
-                "WARNING: 'depends.txt' will not be used by setuptools 0.6!\n"
-                "Use the install_requires/extras_require setup() args instead."
-            )
-
-        if self.exclude_source_files:
-            self.zap_pyfiles()
-
-        # Make the archive
-        make_zipfile(
-            self.egg_output,
-            archive_root,
-            verbose=self.verbose,
-            dry_run=self.dry_run,
-            mode=self.gen_header(),
-        )
-        if not self.keep_temp:
-            remove_tree(self.bdist_dir, dry_run=self.dry_run)
-
-        # Add to 'Distribution.dist_files' so that the "upload" command works
-        getattr(self.distribution, 'dist_files', []).append((
-            'bdist_egg',
-            get_python_version(),
-            self.egg_output,
-        ))
-
-    def zap_pyfiles(self):
-        log.info("Removing .py files from temporary directory")
-        for base, dirs, files in walk_egg(self.bdist_dir):
-            for name in files:
-                path = os.path.join(base, name)
-
-                if name.endswith('.py'):
-                    log.debug("Deleting %s", path)
-                    os.unlink(path)
-
-                if base.endswith('__pycache__'):
-                    path_old = path
-
-                    pattern = r'(?P.+)\.(?P[^.]+)\.pyc'
-                    m = re.match(pattern, name)
-                    path_new = os.path.join(base, os.pardir, m.group('name') + '.pyc')
-                    log.info(f"Renaming file from [{path_old}] to [{path_new}]")
-                    try:
-                        os.remove(path_new)
-                    except OSError:
-                        pass
-                    os.rename(path_old, path_new)
-
-    def zip_safe(self):
-        safe = getattr(self.distribution, 'zip_safe', None)
-        if safe is not None:
-            return safe
-        log.warn("zip_safe flag not set; analyzing archive contents...")
-        return analyze_egg(self.bdist_dir, self.stubs)
-
-    def gen_header(self) -> Literal["w"]:
-        return 'w'
-
-    def copy_metadata_to(self, target_dir) -> None:
-        "Copy metadata (egg info) to the target_dir"
-        # normalize the path (so that a forward-slash in egg_info will
-        # match using startswith below)
-        norm_egg_info = os.path.normpath(self.egg_info)
-        prefix = os.path.join(norm_egg_info, '')
-        for path in self.ei_cmd.filelist.files:
-            if path.startswith(prefix):
-                target = os.path.join(target_dir, path[len(prefix) :])
-                ensure_directory(target)
-                self.copy_file(path, target)
-
-    def get_ext_outputs(self):
-        """Get a list of relative paths to C extensions in the output distro"""
-
-        all_outputs = []
-        ext_outputs = []
-
-        paths = {self.bdist_dir: ''}
-        for base, dirs, files in sorted_walk(self.bdist_dir):
-            all_outputs.extend(
-                paths[base] + filename
-                for filename in files
-                if os.path.splitext(filename)[1].lower() in NATIVE_EXTENSIONS
-            )
-            for filename in dirs:
-                paths[os.path.join(base, filename)] = paths[base] + filename + '/'
-
-        if self.distribution.has_ext_modules():
-            build_cmd = self.get_finalized_command('build_ext')
-            for ext in build_cmd.extensions:
-                if isinstance(ext, Library):
-                    continue
-                fullname = build_cmd.get_ext_fullname(ext.name)
-                filename = build_cmd.get_ext_filename(fullname)
-                if not os.path.basename(filename).startswith('dl-'):
-                    if os.path.exists(os.path.join(self.bdist_dir, filename)):
-                        ext_outputs.append(filename)
-
-        return all_outputs, ext_outputs
-
-
-NATIVE_EXTENSIONS: dict[str, None] = dict.fromkeys('.dll .so .dylib .pyd'.split())
-
-
-def walk_egg(egg_dir):
-    """Walk an unpacked egg's contents, skipping the metadata directory"""
-    walker = sorted_walk(egg_dir)
-    base, dirs, files = next(walker)
-    if 'EGG-INFO' in dirs:
-        dirs.remove('EGG-INFO')
-    yield base, dirs, files
-    yield from walker
-
-
-def analyze_egg(egg_dir, stubs):
-    # check for existing flag in EGG-INFO
-    for flag, fn in safety_flags.items():
-        if os.path.exists(os.path.join(egg_dir, 'EGG-INFO', fn)):
-            return flag
-    if not can_scan():
-        return False
-    safe = True
-    for base, dirs, files in walk_egg(egg_dir):
-        for name in files:
-            if name.endswith('.py') or name.endswith('.pyw'):
-                continue
-            elif name.endswith('.pyc') or name.endswith('.pyo'):
-                # always scan, even if we already know we're not safe
-                safe = scan_module(egg_dir, base, name, stubs) and safe
-    return safe
-
-
-def write_safety_flag(egg_dir, safe) -> None:
-    # Write or remove zip safety flag file(s)
-    for flag, fn in safety_flags.items():
-        fn = os.path.join(egg_dir, fn)
-        if os.path.exists(fn):
-            if safe is None or bool(safe) != flag:
-                os.unlink(fn)
-        elif safe is not None and bool(safe) == flag:
-            with open(fn, 'wt', encoding="utf-8") as f:
-                f.write('\n')
-
-
-safety_flags = {
-    True: 'zip-safe',
-    False: 'not-zip-safe',
-}
-
-
-def scan_module(egg_dir, base, name, stubs):
-    """Check whether module possibly uses unsafe-for-zipfile stuff"""
-
-    filename = os.path.join(base, name)
-    if filename[:-1] in stubs:
-        return True  # Extension module
-    pkg = base[len(egg_dir) + 1 :].replace(os.sep, '.')
-    module = pkg + (pkg and '.' or '') + os.path.splitext(name)[0]
-    skip = 16  # skip magic & reserved? & date & file size
-    f = open(filename, 'rb')
-    f.read(skip)
-    code = marshal.load(f)
-    f.close()
-    safe = True
-    symbols = dict.fromkeys(iter_symbols(code))
-    for bad in ['__file__', '__path__']:
-        if bad in symbols:
-            log.warn("%s: module references %s", module, bad)
-            safe = False
-    if 'inspect' in symbols:
-        for bad in [
-            'getsource',
-            'getabsfile',
-            'getfile',
-            'getsourcefile',
-            'getsourcelines',
-            'findsource',
-            'getcomments',
-            'getframeinfo',
-            'getinnerframes',
-            'getouterframes',
-            'stack',
-            'trace',
-        ]:
-            if bad in symbols:
-                log.warn("%s: module MAY be using inspect.%s", module, bad)
-                safe = False
-    return safe
-
-
-def iter_symbols(code):
-    """Yield names and strings used by `code` and its nested code objects"""
-    yield from code.co_names
-    for const in code.co_consts:
-        if isinstance(const, str):
-            yield const
-        elif isinstance(const, CodeType):
-            yield from iter_symbols(const)
-
-
-def can_scan() -> bool:
-    if not sys.platform.startswith('java') and sys.platform != 'cli':
-        # CPython, PyPy, etc.
-        return True
-    log.warn("Unable to analyze compiled code on this platform.")
-    log.warn(
-        "Please ask the author to include a 'zip_safe'"
-        " setting (either True or False) in the package's setup.py"
-    )
-    return False
-
-
-# Attribute names of options for commands that might need to be convinced to
-# install to the egg build directory
-
-INSTALL_DIRECTORY_ATTRS = ['install_lib', 'install_dir', 'install_data', 'install_base']
-
-
-def make_zipfile(
-    zip_filename: StrPathT,
-    base_dir,
-    verbose: bool = False,
-    dry_run: bool = False,
-    compress=True,
-    mode: _ZipFileMode = 'w',
-) -> StrPathT:
-    """Create a zip file from all the files under 'base_dir'.  The output
-    zip file will be named 'base_dir' + ".zip".  Uses either the "zipfile"
-    Python module (if available) or the InfoZIP "zip" utility (if installed
-    and found on the default search path).  If neither tool is available,
-    raises DistutilsExecError.  Returns the name of the output zip file.
-    """
-    import zipfile
-
-    mkpath(os.path.dirname(zip_filename), dry_run=dry_run)  # type: ignore[arg-type] # python/mypy#18075
-    log.info("creating '%s' and adding '%s' to it", zip_filename, base_dir)
-
-    def visit(z, dirname, names):
-        for name in names:
-            path = os.path.normpath(os.path.join(dirname, name))
-            if os.path.isfile(path):
-                p = path[len(base_dir) + 1 :]
-                if not dry_run:
-                    z.write(path, p)
-                log.debug("adding '%s'", p)
-
-    compression = zipfile.ZIP_DEFLATED if compress else zipfile.ZIP_STORED
-    if not dry_run:
-        z = zipfile.ZipFile(zip_filename, mode, compression=compression)
-        for dirname, dirs, files in sorted_walk(base_dir):
-            visit(z, dirname, files)
-        z.close()
-    else:
-        for dirname, dirs, files in sorted_walk(base_dir):
-            visit(None, dirname, files)
-    return zip_filename
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_rpm.py b/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_rpm.py
deleted file mode 100644
index 6dbb270..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_rpm.py
+++ /dev/null
@@ -1,42 +0,0 @@
-from ..dist import Distribution
-from ..warnings import SetuptoolsDeprecationWarning
-
-import distutils.command.bdist_rpm as orig
-
-
-class bdist_rpm(orig.bdist_rpm):
-    """
-    Override the default bdist_rpm behavior to do the following:
-
-    1. Run egg_info to ensure the name and version are properly calculated.
-    2. Always run 'install' using --single-version-externally-managed to
-       disable eggs in RPM distributions.
-    """
-
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-
-    def run(self) -> None:
-        SetuptoolsDeprecationWarning.emit(
-            "Deprecated command",
-            """
-            bdist_rpm is deprecated and will be removed in a future version.
-            Use bdist_wheel (wheel packages) instead.
-            """,
-            see_url="https://github.com/pypa/setuptools/issues/1988",
-            due_date=(2023, 10, 30),  # Deprecation introduced in 22 Oct 2021.
-        )
-
-        # ensure distro name is up-to-date
-        self.run_command('egg_info')
-
-        orig.bdist_rpm.run(self)
-
-    def _make_spec_file(self):
-        spec = orig.bdist_rpm._make_spec_file(self)
-        return [
-            line.replace(
-                "setup.py install ",
-                "setup.py install --single-version-externally-managed ",
-            ).replace("%setup", "%setup -n %{name}-%{unmangled_version}")
-            for line in spec
-        ]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_wheel.py b/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_wheel.py
deleted file mode 100644
index 1e3f637..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/bdist_wheel.py
+++ /dev/null
@@ -1,604 +0,0 @@
-"""
-Create a wheel (.whl) distribution.
-
-A wheel is a built archive format.
-"""
-
-from __future__ import annotations
-
-import os
-import re
-import shutil
-import struct
-import sys
-import sysconfig
-import warnings
-from collections.abc import Iterable, Sequence
-from email.generator import BytesGenerator
-from glob import iglob
-from typing import Literal, cast
-from zipfile import ZIP_DEFLATED, ZIP_STORED
-
-from packaging import tags, version as _packaging_version
-from wheel.wheelfile import WheelFile
-
-from .. import Command, __version__, _shutil
-from .._core_metadata import _safe_license_file
-from .._normalization import safer_name
-from ..warnings import SetuptoolsDeprecationWarning
-from .egg_info import egg_info as egg_info_cls
-
-from distutils import log
-
-
-def safe_version(version: str) -> str:
-    """
-    Convert an arbitrary string to a standard version string
-    """
-    try:
-        # normalize the version
-        return str(_packaging_version.Version(version))
-    except _packaging_version.InvalidVersion:
-        version = version.replace(" ", ".")
-        return re.sub("[^A-Za-z0-9.]+", "-", version)
-
-
-setuptools_major_version = int(__version__.split(".")[0])
-
-PY_LIMITED_API_PATTERN = r"cp3\d"
-
-
-def _is_32bit_interpreter() -> bool:
-    return struct.calcsize("P") == 4
-
-
-def python_tag() -> str:
-    return f"py{sys.version_info.major}"
-
-
-def get_platform(archive_root: str | None) -> str:
-    """Return our platform name 'win32', 'linux_x86_64'"""
-    result = sysconfig.get_platform()
-    if result.startswith("macosx") and archive_root is not None:  # pragma: no cover
-        from wheel.macosx_libfile import calculate_macosx_platform_tag
-
-        result = calculate_macosx_platform_tag(archive_root, result)
-    elif _is_32bit_interpreter():
-        if result == "linux-x86_64":
-            # pip pull request #3497
-            result = "linux-i686"
-        elif result == "linux-aarch64":
-            # packaging pull request #234
-            # TODO armv8l, packaging pull request #690 => this did not land
-            # in pip/packaging yet
-            result = "linux-armv7l"
-
-    return result.replace("-", "_")
-
-
-def get_flag(
-    var: str, fallback: bool, expected: bool = True, warn: bool = True
-) -> bool:
-    """Use a fallback value for determining SOABI flags if the needed config
-    var is unset or unavailable."""
-    val = sysconfig.get_config_var(var)
-    if val is None:
-        if warn:
-            warnings.warn(
-                f"Config variable '{var}' is unset, Python ABI tag may be incorrect",
-                RuntimeWarning,
-                stacklevel=2,
-            )
-        return fallback
-    return val == expected
-
-
-def get_abi_tag() -> str | None:
-    """Return the ABI tag based on SOABI (if available) or emulate SOABI (PyPy2)."""
-    soabi: str = sysconfig.get_config_var("SOABI")
-    impl = tags.interpreter_name()
-    if not soabi and impl in ("cp", "pp") and hasattr(sys, "maxunicode"):
-        d = ""
-        u = ""
-        if get_flag("Py_DEBUG", hasattr(sys, "gettotalrefcount"), warn=(impl == "cp")):
-            d = "d"
-
-        abi = f"{impl}{tags.interpreter_version()}{d}{u}"
-    elif soabi and impl == "cp" and soabi.startswith("cpython"):
-        # non-Windows
-        abi = "cp" + soabi.split("-")[1]
-    elif soabi and impl == "cp" and soabi.startswith("cp"):
-        # Windows
-        abi = soabi.split("-")[0]
-        if hasattr(sys, "gettotalrefcount"):
-            # using debug build; append "d" flag
-            abi += "d"
-    elif soabi and impl == "pp":
-        # we want something like pypy36-pp73
-        abi = "-".join(soabi.split("-")[:2])
-        abi = abi.replace(".", "_").replace("-", "_")
-    elif soabi and impl == "graalpy":
-        abi = "-".join(soabi.split("-")[:3])
-        abi = abi.replace(".", "_").replace("-", "_")
-    elif soabi:
-        abi = soabi.replace(".", "_").replace("-", "_")
-    else:
-        abi = None
-
-    return abi
-
-
-def safer_version(version: str) -> str:
-    return safe_version(version).replace("-", "_")
-
-
-class bdist_wheel(Command):
-    description = "create a wheel distribution"
-
-    supported_compressions = {
-        "stored": ZIP_STORED,
-        "deflated": ZIP_DEFLATED,
-    }
-
-    user_options = [
-        ("bdist-dir=", "b", "temporary directory for creating the distribution"),
-        (
-            "plat-name=",
-            "p",
-            "platform name to embed in generated filenames "
-            f"[default: {get_platform(None)}]",
-        ),
-        (
-            "keep-temp",
-            "k",
-            "keep the pseudo-installation tree around after "
-            "creating the distribution archive",
-        ),
-        ("dist-dir=", "d", "directory to put final built distributions in"),
-        ("skip-build", None, "skip rebuilding everything (for testing/debugging)"),
-        (
-            "relative",
-            None,
-            "build the archive using relative paths [default: false]",
-        ),
-        (
-            "owner=",
-            "u",
-            "Owner name used when creating a tar file [default: current user]",
-        ),
-        (
-            "group=",
-            "g",
-            "Group name used when creating a tar file [default: current group]",
-        ),
-        ("universal", None, "*DEPRECATED* make a universal wheel [default: false]"),
-        (
-            "compression=",
-            None,
-            f"zipfile compression (one of: {', '.join(supported_compressions)}) [default: 'deflated']",
-        ),
-        (
-            "python-tag=",
-            None,
-            f"Python implementation compatibility tag [default: '{python_tag()}']",
-        ),
-        (
-            "build-number=",
-            None,
-            "Build number for this particular version. "
-            "As specified in PEP-0427, this must start with a digit. "
-            "[default: None]",
-        ),
-        (
-            "py-limited-api=",
-            None,
-            "Python tag (cp32|cp33|cpNN) for abi3 wheel tag [default: false]",
-        ),
-        (
-            "dist-info-dir=",
-            None,
-            "directory where a pre-generated dist-info can be found (e.g. as a "
-            "result of calling the PEP517 'prepare_metadata_for_build_wheel' "
-            "method)",
-        ),
-    ]
-
-    boolean_options = ["keep-temp", "skip-build", "relative", "universal"]
-
-    def initialize_options(self) -> None:
-        self.bdist_dir: str | None = None
-        self.data_dir = ""
-        self.plat_name: str | None = None
-        self.plat_tag: str | None = None
-        self.format = "zip"
-        self.keep_temp = False
-        self.dist_dir: str | None = None
-        self.dist_info_dir = None
-        self.egginfo_dir: str | None = None
-        self.root_is_pure: bool | None = None
-        self.skip_build = False
-        self.relative = False
-        self.owner = None
-        self.group = None
-        self.universal = False
-        self.compression: str | int = "deflated"
-        self.python_tag = python_tag()
-        self.build_number: str | None = None
-        self.py_limited_api: str | Literal[False] = False
-        self.plat_name_supplied = False
-
-    def finalize_options(self) -> None:
-        if not self.bdist_dir:
-            bdist_base = self.get_finalized_command("bdist").bdist_base
-            self.bdist_dir = os.path.join(bdist_base, "wheel")
-
-        if self.dist_info_dir is None:
-            egg_info = cast(egg_info_cls, self.distribution.get_command_obj("egg_info"))
-            egg_info.ensure_finalized()  # needed for correct `wheel_dist_name`
-
-        self.data_dir = self.wheel_dist_name + ".data"
-        self.plat_name_supplied = bool(self.plat_name)
-
-        need_options = ("dist_dir", "plat_name", "skip_build")
-
-        self.set_undefined_options("bdist", *zip(need_options, need_options))
-
-        self.root_is_pure = not (
-            self.distribution.has_ext_modules() or self.distribution.has_c_libraries()
-        )
-
-        self._validate_py_limited_api()
-
-        # Support legacy [wheel] section for setting universal
-        wheel = self.distribution.get_option_dict("wheel")
-        if "universal" in wheel:  # pragma: no cover
-            # please don't define this in your global configs
-            log.warn("The [wheel] section is deprecated. Use [bdist_wheel] instead.")
-            val = wheel["universal"][1].strip()
-            if val.lower() in ("1", "true", "yes"):
-                self.universal = True
-
-        if self.universal:
-            SetuptoolsDeprecationWarning.emit(
-                "bdist_wheel.universal is deprecated",
-                """
-                With Python 2.7 end-of-life, support for building universal wheels
-                (i.e., wheels that support both Python 2 and Python 3)
-                is being obviated.
-                Please discontinue using this option, or if you still need it,
-                file an issue with pypa/setuptools describing your use case.
-                """,
-                due_date=(2025, 8, 30),  # Introduced in 2024-08-30
-            )
-
-        if self.build_number is not None and not self.build_number[:1].isdigit():
-            raise ValueError("Build tag (build-number) must start with a digit.")
-
-    def _validate_py_limited_api(self) -> None:
-        if not self.py_limited_api:
-            return
-
-        if not re.match(PY_LIMITED_API_PATTERN, self.py_limited_api):
-            raise ValueError(f"py-limited-api must match '{PY_LIMITED_API_PATTERN}'")
-
-        if sysconfig.get_config_var("Py_GIL_DISABLED"):
-            raise ValueError(
-                f"`py_limited_api={self.py_limited_api!r}` not supported. "
-                "`Py_LIMITED_API` is currently incompatible with "
-                "`Py_GIL_DISABLED`."
-                "See https://github.com/python/cpython/issues/111506."
-            )
-
-    @property
-    def wheel_dist_name(self) -> str:
-        """Return distribution full name with - replaced with _"""
-        components = [
-            safer_name(self.distribution.get_name()),
-            safer_version(self.distribution.get_version()),
-        ]
-        if self.build_number:
-            components.append(self.build_number)
-        return "-".join(components)
-
-    def get_tag(self) -> tuple[str, str, str]:
-        # bdist sets self.plat_name if unset, we should only use it for purepy
-        # wheels if the user supplied it.
-        if self.plat_name_supplied and self.plat_name:
-            plat_name = self.plat_name
-        elif self.root_is_pure:
-            plat_name = "any"
-        else:
-            # macosx contains system version in platform name so need special handle
-            if self.plat_name and not self.plat_name.startswith("macosx"):
-                plat_name = self.plat_name
-            else:
-                # on macosx always limit the platform name to comply with any
-                # c-extension modules in bdist_dir, since the user can specify
-                # a higher MACOSX_DEPLOYMENT_TARGET via tools like CMake
-
-                # on other platforms, and on macosx if there are no c-extension
-                # modules, use the default platform name.
-                plat_name = get_platform(self.bdist_dir)
-
-            if _is_32bit_interpreter():
-                if plat_name in ("linux-x86_64", "linux_x86_64"):
-                    plat_name = "linux_i686"
-                if plat_name in ("linux-aarch64", "linux_aarch64"):
-                    # TODO armv8l, packaging pull request #690 => this did not land
-                    # in pip/packaging yet
-                    plat_name = "linux_armv7l"
-
-        plat_name = (
-            plat_name.lower().replace("-", "_").replace(".", "_").replace(" ", "_")
-        )
-
-        if self.root_is_pure:
-            if self.universal:
-                impl = "py2.py3"
-            else:
-                impl = self.python_tag
-            tag = (impl, "none", plat_name)
-        else:
-            impl_name = tags.interpreter_name()
-            impl_ver = tags.interpreter_version()
-            impl = impl_name + impl_ver
-            # We don't work on CPython 3.1, 3.0.
-            if self.py_limited_api and (impl_name + impl_ver).startswith("cp3"):
-                impl = self.py_limited_api
-                abi_tag = "abi3"
-            else:
-                abi_tag = str(get_abi_tag()).lower()
-            tag = (impl, abi_tag, plat_name)
-            # issue gh-374: allow overriding plat_name
-            supported_tags = [
-                (t.interpreter, t.abi, plat_name) for t in tags.sys_tags()
-            ]
-            assert tag in supported_tags, (
-                f"would build wheel with unsupported tag {tag}"
-            )
-        return tag
-
-    def run(self):
-        build_scripts = self.reinitialize_command("build_scripts")
-        build_scripts.executable = "python"
-        build_scripts.force = True
-
-        build_ext = self.reinitialize_command("build_ext")
-        build_ext.inplace = False
-
-        if not self.skip_build:
-            self.run_command("build")
-
-        install = self.reinitialize_command("install", reinit_subcommands=True)
-        install.root = self.bdist_dir
-        install.compile = False
-        install.skip_build = self.skip_build
-        install.warn_dir = False
-
-        # A wheel without setuptools scripts is more cross-platform.
-        # Use the (undocumented) `no_ep` option to setuptools'
-        # install_scripts command to avoid creating entry point scripts.
-        install_scripts = self.reinitialize_command("install_scripts")
-        install_scripts.no_ep = True
-
-        # Use a custom scheme for the archive, because we have to decide
-        # at installation time which scheme to use.
-        for key in ("headers", "scripts", "data", "purelib", "platlib"):
-            setattr(install, "install_" + key, os.path.join(self.data_dir, key))
-
-        basedir_observed = ""
-
-        if os.name == "nt":
-            # win32 barfs if any of these are ''; could be '.'?
-            # (distutils.command.install:change_roots bug)
-            basedir_observed = os.path.normpath(os.path.join(self.data_dir, ".."))
-            self.install_libbase = self.install_lib = basedir_observed
-
-        setattr(
-            install,
-            "install_purelib" if self.root_is_pure else "install_platlib",
-            basedir_observed,
-        )
-
-        log.info(f"installing to {self.bdist_dir}")
-
-        self.run_command("install")
-
-        impl_tag, abi_tag, plat_tag = self.get_tag()
-        archive_basename = f"{self.wheel_dist_name}-{impl_tag}-{abi_tag}-{plat_tag}"
-        if not self.relative:
-            archive_root = self.bdist_dir
-        else:
-            archive_root = os.path.join(
-                self.bdist_dir, self._ensure_relative(install.install_base)
-            )
-
-        self.set_undefined_options("install_egg_info", ("target", "egginfo_dir"))
-        distinfo_dirname = (
-            f"{safer_name(self.distribution.get_name())}-"
-            f"{safer_version(self.distribution.get_version())}.dist-info"
-        )
-        distinfo_dir = os.path.join(self.bdist_dir, distinfo_dirname)
-        if self.dist_info_dir:
-            # Use the given dist-info directly.
-            log.debug(f"reusing {self.dist_info_dir}")
-            shutil.copytree(self.dist_info_dir, distinfo_dir)
-            # Egg info is still generated, so remove it now to avoid it getting
-            # copied into the wheel.
-            _shutil.rmtree(self.egginfo_dir)
-        else:
-            # Convert the generated egg-info into dist-info.
-            self.egg2dist(self.egginfo_dir, distinfo_dir)
-
-        self.write_wheelfile(distinfo_dir)
-
-        # Make the archive
-        if not os.path.exists(self.dist_dir):
-            os.makedirs(self.dist_dir)
-
-        wheel_path = os.path.join(self.dist_dir, archive_basename + ".whl")
-        with WheelFile(wheel_path, "w", self._zip_compression()) as wf:
-            wf.write_files(archive_root)
-
-        # Add to 'Distribution.dist_files' so that the "upload" command works
-        getattr(self.distribution, "dist_files", []).append((
-            "bdist_wheel",
-            f"{sys.version_info.major}.{sys.version_info.minor}",
-            wheel_path,
-        ))
-
-        if not self.keep_temp:
-            log.info(f"removing {self.bdist_dir}")
-            if not self.dry_run:
-                _shutil.rmtree(self.bdist_dir)
-
-    def write_wheelfile(
-        self, wheelfile_base: str, generator: str = f"setuptools ({__version__})"
-    ) -> None:
-        from email.message import Message
-
-        msg = Message()
-        msg["Wheel-Version"] = "1.0"  # of the spec
-        msg["Generator"] = generator
-        msg["Root-Is-Purelib"] = str(self.root_is_pure).lower()
-        if self.build_number is not None:
-            msg["Build"] = self.build_number
-
-        # Doesn't work for bdist_wininst
-        impl_tag, abi_tag, plat_tag = self.get_tag()
-        for impl in impl_tag.split("."):
-            for abi in abi_tag.split("."):
-                for plat in plat_tag.split("."):
-                    msg["Tag"] = "-".join((impl, abi, plat))
-
-        wheelfile_path = os.path.join(wheelfile_base, "WHEEL")
-        log.info(f"creating {wheelfile_path}")
-        with open(wheelfile_path, "wb") as f:
-            BytesGenerator(f, maxheaderlen=0).flatten(msg)
-
-    def _ensure_relative(self, path: str) -> str:
-        # copied from dir_util, deleted
-        drive, path = os.path.splitdrive(path)
-        if path[0:1] == os.sep:
-            path = drive + path[1:]
-        return path
-
-    @property
-    def license_paths(self) -> Iterable[str]:
-        if setuptools_major_version >= 57:
-            # Setuptools has resolved any patterns to actual file names
-            return self.distribution.metadata.license_files or ()
-
-        files = set[str]()
-        metadata = self.distribution.get_option_dict("metadata")
-        if setuptools_major_version >= 42:
-            # Setuptools recognizes the license_files option but does not do globbing
-            patterns = cast(Sequence[str], self.distribution.metadata.license_files)
-        else:
-            # Prior to those, wheel is entirely responsible for handling license files
-            if "license_files" in metadata:
-                patterns = metadata["license_files"][1].split()
-            else:
-                patterns = ()
-
-        if "license_file" in metadata:
-            warnings.warn(
-                'The "license_file" option is deprecated. Use "license_files" instead.',
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            files.add(metadata["license_file"][1])
-
-        if not files and not patterns and not isinstance(patterns, list):
-            patterns = ("LICEN[CS]E*", "COPYING*", "NOTICE*", "AUTHORS*")
-
-        for pattern in patterns:
-            for path in iglob(pattern):
-                if path.endswith("~"):
-                    log.debug(
-                        f'ignoring license file "{path}" as it looks like a backup'
-                    )
-                    continue
-
-                if path not in files and os.path.isfile(path):
-                    log.info(
-                        f'adding license file "{path}" (matched pattern "{pattern}")'
-                    )
-                    files.add(path)
-
-        return files
-
-    def egg2dist(self, egginfo_path: str, distinfo_path: str) -> None:
-        """Convert an .egg-info directory into a .dist-info directory"""
-
-        def adios(p: str) -> None:
-            """Appropriately delete directory, file or link."""
-            if os.path.exists(p) and not os.path.islink(p) and os.path.isdir(p):
-                _shutil.rmtree(p)
-            elif os.path.exists(p):
-                os.unlink(p)
-
-        adios(distinfo_path)
-
-        if not os.path.exists(egginfo_path):
-            # There is no egg-info. This is probably because the egg-info
-            # file/directory is not named matching the distribution name used
-            # to name the archive file. Check for this case and report
-            # accordingly.
-            import glob
-
-            pat = os.path.join(os.path.dirname(egginfo_path), "*.egg-info")
-            possible = glob.glob(pat)
-            err = f"Egg metadata expected at {egginfo_path} but not found"
-            if possible:
-                alt = os.path.basename(possible[0])
-                err += f" ({alt} found - possible misnamed archive file?)"
-
-            raise ValueError(err)
-
-        # .egg-info is a directory
-        pkginfo_path = os.path.join(egginfo_path, "PKG-INFO")
-
-        # ignore common egg metadata that is useless to wheel
-        shutil.copytree(
-            egginfo_path,
-            distinfo_path,
-            ignore=lambda x, y: {
-                "PKG-INFO",
-                "requires.txt",
-                "SOURCES.txt",
-                "not-zip-safe",
-            },
-        )
-
-        # delete dependency_links if it is only whitespace
-        dependency_links_path = os.path.join(distinfo_path, "dependency_links.txt")
-        with open(dependency_links_path, encoding="utf-8") as dependency_links_file:
-            dependency_links = dependency_links_file.read().strip()
-        if not dependency_links:
-            adios(dependency_links_path)
-
-        metadata_path = os.path.join(distinfo_path, "METADATA")
-        shutil.copy(pkginfo_path, metadata_path)
-
-        licenses_folder_path = os.path.join(distinfo_path, "licenses")
-        for license_path in self.license_paths:
-            safe_path = _safe_license_file(license_path)
-            dist_info_license_path = os.path.join(licenses_folder_path, safe_path)
-            os.makedirs(os.path.dirname(dist_info_license_path), exist_ok=True)
-            shutil.copy(license_path, dist_info_license_path)
-
-        adios(egginfo_path)
-
-    def _zip_compression(self) -> int:
-        if (
-            isinstance(self.compression, int)
-            and self.compression in self.supported_compressions.values()
-        ):
-            return self.compression
-
-        compression = self.supported_compressions.get(str(self.compression))
-        if compression is not None:
-            return compression
-
-        raise ValueError(f"Unsupported compression: {self.compression!r}")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/build.py b/llmlab/lib/python3.12/site-packages/setuptools/command/build.py
deleted file mode 100644
index 54cbb8d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/build.py
+++ /dev/null
@@ -1,135 +0,0 @@
-from __future__ import annotations
-
-from typing import Protocol
-
-from ..dist import Distribution
-
-from distutils.command.build import build as _build
-
-_ORIGINAL_SUBCOMMANDS = {"build_py", "build_clib", "build_ext", "build_scripts"}
-
-
-class build(_build):
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-
-    # copy to avoid sharing the object with parent class
-    sub_commands = _build.sub_commands[:]
-
-
-class SubCommand(Protocol):
-    """In order to support editable installations (see :pep:`660`) all
-    build subcommands **SHOULD** implement this protocol. They also **MUST** inherit
-    from ``setuptools.Command``.
-
-    When creating an :pep:`editable wheel <660>`, ``setuptools`` will try to evaluate
-    custom ``build`` subcommands using the following procedure:
-
-    1. ``setuptools`` will set the ``editable_mode`` attribute to ``True``
-    2. ``setuptools`` will execute the ``run()`` command.
-
-       .. important::
-          Subcommands **SHOULD** take advantage of ``editable_mode=True`` to adequate
-          its behaviour or perform optimisations.
-
-          For example, if a subcommand doesn't need to generate an extra file and
-          all it does is to copy a source file into the build directory,
-          ``run()`` **SHOULD** simply "early return".
-
-          Similarly, if the subcommand creates files that would be placed alongside
-          Python files in the final distribution, during an editable install
-          the command **SHOULD** generate these files "in place" (i.e. write them to
-          the original source directory, instead of using the build directory).
-          Note that ``get_output_mapping()`` should reflect that and include mappings
-          for "in place" builds accordingly.
-
-    3. ``setuptools`` use any knowledge it can derive from the return values of
-       ``get_outputs()`` and ``get_output_mapping()`` to create an editable wheel.
-       When relevant ``setuptools`` **MAY** attempt to use file links based on the value
-       of ``get_output_mapping()``. Alternatively, ``setuptools`` **MAY** attempt to use
-       :doc:`import hooks ` to redirect any attempt to import
-       to the directory with the original source code and other files built in place.
-
-    Please note that custom sub-commands **SHOULD NOT** rely on ``run()`` being
-    executed (or not) to provide correct return values for ``get_outputs()``,
-    ``get_output_mapping()`` or ``get_source_files()``. The ``get_*`` methods should
-    work independently of ``run()``.
-    """
-
-    editable_mode: bool = False
-    """Boolean flag that will be set to ``True`` when setuptools is used for an
-    editable installation (see :pep:`660`).
-    Implementations **SHOULD** explicitly set the default value of this attribute to
-    ``False``.
-    When subcommands run, they can use this flag to perform optimizations or change
-    their behaviour accordingly.
-    """
-
-    build_lib: str
-    """String representing the directory where the build artifacts should be stored,
-    e.g. ``build/lib``.
-    For example, if a distribution wants to provide a Python module named ``pkg.mod``,
-    then a corresponding file should be written to ``{build_lib}/package/module.py``.
-    A way of thinking about this is that the files saved under ``build_lib``
-    would be eventually copied to one of the directories in :obj:`site.PREFIXES`
-    upon installation.
-
-    A command that produces platform-independent files (e.g. compiling text templates
-    into Python functions), **CAN** initialize ``build_lib`` by copying its value from
-    the ``build_py`` command. On the other hand, a command that produces
-    platform-specific files **CAN** initialize ``build_lib`` by copying its value from
-    the ``build_ext`` command. In general this is done inside the ``finalize_options``
-    method with the help of the ``set_undefined_options`` command::
-
-        def finalize_options(self):
-            self.set_undefined_options("build_py", ("build_lib", "build_lib"))
-            ...
-    """
-
-    def initialize_options(self) -> None:
-        """(Required by the original :class:`setuptools.Command` interface)"""
-        ...
-
-    def finalize_options(self) -> None:
-        """(Required by the original :class:`setuptools.Command` interface)"""
-        ...
-
-    def run(self) -> None:
-        """(Required by the original :class:`setuptools.Command` interface)"""
-        ...
-
-    def get_source_files(self) -> list[str]:
-        """
-        Return a list of all files that are used by the command to create the expected
-        outputs.
-        For example, if your build command transpiles Java files into Python, you should
-        list here all the Java files.
-        The primary purpose of this function is to help populating the ``sdist``
-        with all the files necessary to build the distribution.
-        All files should be strings relative to the project root directory.
-        """
-        ...
-
-    def get_outputs(self) -> list[str]:
-        """
-        Return a list of files intended for distribution as they would have been
-        produced by the build.
-        These files should be strings in the form of
-        ``"{build_lib}/destination/file/path"``.
-
-        .. note::
-           The return value of ``get_output()`` should include all files used as keys
-           in ``get_output_mapping()`` plus files that are generated during the build
-           and don't correspond to any source file already present in the project.
-        """
-        ...
-
-    def get_output_mapping(self) -> dict[str, str]:
-        """
-        Return a mapping between destination files as they would be produced by the
-        build (dict keys) into the respective existing (source) files (dict values).
-        Existing (source) files should be represented as strings relative to the project
-        root directory.
-        Destination files should be strings in the form of
-        ``"{build_lib}/destination/file/path"``.
-        """
-        ...
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/build_clib.py b/llmlab/lib/python3.12/site-packages/setuptools/command/build_clib.py
deleted file mode 100644
index f376f4c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/build_clib.py
+++ /dev/null
@@ -1,103 +0,0 @@
-from ..dist import Distribution
-from ..modified import newer_pairwise_group
-
-import distutils.command.build_clib as orig
-from distutils import log
-from distutils.errors import DistutilsSetupError
-
-
-class build_clib(orig.build_clib):
-    """
-    Override the default build_clib behaviour to do the following:
-
-    1. Implement a rudimentary timestamp-based dependency system
-       so 'compile()' doesn't run every time.
-    2. Add more keys to the 'build_info' dictionary:
-        * obj_deps - specify dependencies for each object compiled.
-                     this should be a dictionary mapping a key
-                     with the source filename to a list of
-                     dependencies. Use an empty string for global
-                     dependencies.
-        * cflags   - specify a list of additional flags to pass to
-                     the compiler.
-    """
-
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-
-    def build_libraries(self, libraries) -> None:
-        for lib_name, build_info in libraries:
-            sources = build_info.get('sources')
-            if sources is None or not isinstance(sources, (list, tuple)):
-                raise DistutilsSetupError(
-                    f"in 'libraries' option (library '{lib_name}'), "
-                    "'sources' must be present and must be "
-                    "a list of source filenames"
-                )
-            sources = sorted(list(sources))
-
-            log.info("building '%s' library", lib_name)
-
-            # Make sure everything is the correct type.
-            # obj_deps should be a dictionary of keys as sources
-            # and a list/tuple of files that are its dependencies.
-            obj_deps = build_info.get('obj_deps', dict())
-            if not isinstance(obj_deps, dict):
-                raise DistutilsSetupError(
-                    f"in 'libraries' option (library '{lib_name}'), "
-                    "'obj_deps' must be a dictionary of "
-                    "type 'source: list'"
-                )
-            dependencies = []
-
-            # Get the global dependencies that are specified by the '' key.
-            # These will go into every source's dependency list.
-            global_deps = obj_deps.get('', list())
-            if not isinstance(global_deps, (list, tuple)):
-                raise DistutilsSetupError(
-                    f"in 'libraries' option (library '{lib_name}'), "
-                    "'obj_deps' must be a dictionary of "
-                    "type 'source: list'"
-                )
-
-            # Build the list to be used by newer_pairwise_group
-            # each source will be auto-added to its dependencies.
-            for source in sources:
-                src_deps = [source]
-                src_deps.extend(global_deps)
-                extra_deps = obj_deps.get(source, list())
-                if not isinstance(extra_deps, (list, tuple)):
-                    raise DistutilsSetupError(
-                        f"in 'libraries' option (library '{lib_name}'), "
-                        "'obj_deps' must be a dictionary of "
-                        "type 'source: list'"
-                    )
-                src_deps.extend(extra_deps)
-                dependencies.append(src_deps)
-
-            expected_objects = self.compiler.object_filenames(
-                sources,
-                output_dir=self.build_temp,
-            )
-
-            if newer_pairwise_group(dependencies, expected_objects) != ([], []):
-                # First, compile the source code to object files in the library
-                # directory.  (This should probably change to putting object
-                # files in a temporary build directory.)
-                macros = build_info.get('macros')
-                include_dirs = build_info.get('include_dirs')
-                cflags = build_info.get('cflags')
-                self.compiler.compile(
-                    sources,
-                    output_dir=self.build_temp,
-                    macros=macros,
-                    include_dirs=include_dirs,
-                    extra_postargs=cflags,
-                    debug=self.debug,
-                )
-
-            # Now "link" the object files together into a static library.
-            # (On Unix at least, this isn't really linking -- it just
-            # builds an archive.  Whatever.)
-            self.compiler.create_static_lib(
-                expected_objects, lib_name, output_dir=self.build_clib, debug=self.debug
-            )
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/build_ext.py b/llmlab/lib/python3.12/site-packages/setuptools/command/build_ext.py
deleted file mode 100644
index be833a3..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/build_ext.py
+++ /dev/null
@@ -1,469 +0,0 @@
-from __future__ import annotations
-
-import itertools
-import os
-import sys
-from collections.abc import Iterator
-from importlib.machinery import EXTENSION_SUFFIXES
-from importlib.util import cache_from_source as _compiled_file_name
-from pathlib import Path
-from typing import TYPE_CHECKING
-
-from setuptools.dist import Distribution
-from setuptools.errors import BaseError
-from setuptools.extension import Extension, Library
-
-from distutils import log
-from distutils.ccompiler import new_compiler
-from distutils.sysconfig import customize_compiler, get_config_var
-
-if TYPE_CHECKING:
-    # Cython not installed on CI tests, causing _build_ext to be `Any`
-    from distutils.command.build_ext import build_ext as _build_ext
-else:
-    try:
-        # Attempt to use Cython for building extensions, if available
-        from Cython.Distutils.build_ext import build_ext as _build_ext
-
-        # Additionally, assert that the compiler module will load
-        # also. Ref #1229.
-        __import__('Cython.Compiler.Main')
-    except ImportError:
-        from distutils.command.build_ext import build_ext as _build_ext
-
-# make sure _config_vars is initialized
-get_config_var("LDSHARED")
-# Not publicly exposed in typeshed distutils stubs, but this is done on purpose
-# See https://github.com/pypa/setuptools/pull/4228#issuecomment-1959856400
-from distutils.sysconfig import _config_vars as _CONFIG_VARS  # noqa: E402
-
-
-def _customize_compiler_for_shlib(compiler):
-    if sys.platform == "darwin":
-        # building .dylib requires additional compiler flags on OSX; here we
-        # temporarily substitute the pyconfig.h variables so that distutils'
-        # 'customize_compiler' uses them before we build the shared libraries.
-        tmp = _CONFIG_VARS.copy()
-        try:
-            # XXX Help!  I don't have any idea whether these are right...
-            _CONFIG_VARS['LDSHARED'] = (
-                "gcc -Wl,-x -dynamiclib -undefined dynamic_lookup"
-            )
-            _CONFIG_VARS['CCSHARED'] = " -dynamiclib"
-            _CONFIG_VARS['SO'] = ".dylib"
-            customize_compiler(compiler)
-        finally:
-            _CONFIG_VARS.clear()
-            _CONFIG_VARS.update(tmp)
-    else:
-        customize_compiler(compiler)
-
-
-have_rtld = False
-use_stubs = False
-libtype = 'shared'
-
-if sys.platform == "darwin":
-    use_stubs = True
-elif os.name != 'nt':
-    try:
-        import dl  # type: ignore[import-not-found] # https://github.com/python/mypy/issues/13002
-
-        use_stubs = have_rtld = hasattr(dl, 'RTLD_NOW')
-    except ImportError:
-        pass
-
-
-def if_dl(s):
-    return s if have_rtld else ''
-
-
-def get_abi3_suffix():
-    """Return the file extension for an abi3-compliant Extension()"""
-    for suffix in EXTENSION_SUFFIXES:
-        if '.abi3' in suffix:  # Unix
-            return suffix
-        elif suffix == '.pyd':  # Windows
-            return suffix
-    return None
-
-
-class build_ext(_build_ext):
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-    editable_mode = False
-    inplace = False
-
-    def run(self):
-        """Build extensions in build directory, then copy if --inplace"""
-        old_inplace, self.inplace = self.inplace, False
-        _build_ext.run(self)
-        self.inplace = old_inplace
-        if old_inplace:
-            self.copy_extensions_to_source()
-
-    def _get_inplace_equivalent(self, build_py, ext: Extension) -> tuple[str, str]:
-        fullname = self.get_ext_fullname(ext.name)
-        filename = self.get_ext_filename(fullname)
-        modpath = fullname.split('.')
-        package = '.'.join(modpath[:-1])
-        package_dir = build_py.get_package_dir(package)
-        inplace_file = os.path.join(package_dir, os.path.basename(filename))
-        regular_file = os.path.join(self.build_lib, filename)
-        return (inplace_file, regular_file)
-
-    def copy_extensions_to_source(self) -> None:
-        build_py = self.get_finalized_command('build_py')
-        for ext in self.extensions:
-            inplace_file, regular_file = self._get_inplace_equivalent(build_py, ext)
-
-            # Always copy, even if source is older than destination, to ensure
-            # that the right extensions for the current Python/platform are
-            # used.
-            if os.path.exists(regular_file) or not ext.optional:
-                self.copy_file(regular_file, inplace_file, level=self.verbose)
-
-            if ext._needs_stub:
-                inplace_stub = self._get_equivalent_stub(ext, inplace_file)
-                self._write_stub_file(inplace_stub, ext, compile=True)
-                # Always compile stub and remove the original (leave the cache behind)
-                # (this behaviour was observed in previous iterations of the code)
-
-    def _get_equivalent_stub(self, ext: Extension, output_file: str) -> str:
-        dir_ = os.path.dirname(output_file)
-        _, _, name = ext.name.rpartition(".")
-        return f"{os.path.join(dir_, name)}.py"
-
-    def _get_output_mapping(self) -> Iterator[tuple[str, str]]:
-        if not self.inplace:
-            return
-
-        build_py = self.get_finalized_command('build_py')
-        opt = self.get_finalized_command('install_lib').optimize or ""
-
-        for ext in self.extensions:
-            inplace_file, regular_file = self._get_inplace_equivalent(build_py, ext)
-            yield (regular_file, inplace_file)
-
-            if ext._needs_stub:
-                # This version of `build_ext` always builds artifacts in another dir,
-                # when "inplace=True" is given it just copies them back.
-                # This is done in the `copy_extensions_to_source` function, which
-                # always compile stub files via `_compile_and_remove_stub`.
-                # At the end of the process, a `.pyc` stub file is created without the
-                # corresponding `.py`.
-
-                inplace_stub = self._get_equivalent_stub(ext, inplace_file)
-                regular_stub = self._get_equivalent_stub(ext, regular_file)
-                inplace_cache = _compiled_file_name(inplace_stub, optimization=opt)
-                output_cache = _compiled_file_name(regular_stub, optimization=opt)
-                yield (output_cache, inplace_cache)
-
-    def get_ext_filename(self, fullname: str) -> str:
-        so_ext = os.getenv('SETUPTOOLS_EXT_SUFFIX')
-        if so_ext:
-            filename = os.path.join(*fullname.split('.')) + so_ext
-        else:
-            filename = _build_ext.get_ext_filename(self, fullname)
-            ext_suffix = get_config_var('EXT_SUFFIX')
-            if not isinstance(ext_suffix, str):
-                raise OSError(
-                    "Configuration variable EXT_SUFFIX not found for this platform "
-                    "and environment variable SETUPTOOLS_EXT_SUFFIX is missing"
-                )
-            so_ext = ext_suffix
-
-        if fullname in self.ext_map:
-            ext = self.ext_map[fullname]
-            abi3_suffix = get_abi3_suffix()
-            if ext.py_limited_api and abi3_suffix:  # Use abi3
-                filename = filename[: -len(so_ext)] + abi3_suffix
-            if isinstance(ext, Library):
-                fn, ext = os.path.splitext(filename)
-                return self.shlib_compiler.library_filename(fn, libtype)
-            elif use_stubs and ext._links_to_dynamic:
-                d, fn = os.path.split(filename)
-                return os.path.join(d, 'dl-' + fn)
-        return filename
-
-    def initialize_options(self):
-        _build_ext.initialize_options(self)
-        self.shlib_compiler = None
-        self.shlibs = []
-        self.ext_map = {}
-        self.editable_mode = False
-
-    def finalize_options(self) -> None:
-        _build_ext.finalize_options(self)
-        self.extensions = self.extensions or []
-        self.check_extensions_list(self.extensions)
-        self.shlibs = [ext for ext in self.extensions if isinstance(ext, Library)]
-        if self.shlibs:
-            self.setup_shlib_compiler()
-        for ext in self.extensions:
-            ext._full_name = self.get_ext_fullname(ext.name)
-        for ext in self.extensions:
-            fullname = ext._full_name
-            self.ext_map[fullname] = ext
-
-            # distutils 3.1 will also ask for module names
-            # XXX what to do with conflicts?
-            self.ext_map[fullname.split('.')[-1]] = ext
-
-            ltd = self.shlibs and self.links_to_dynamic(ext) or False
-            ns = ltd and use_stubs and not isinstance(ext, Library)
-            ext._links_to_dynamic = ltd
-            ext._needs_stub = ns
-            filename = ext._file_name = self.get_ext_filename(fullname)
-            libdir = os.path.dirname(os.path.join(self.build_lib, filename))
-            if ltd and libdir not in ext.library_dirs:
-                ext.library_dirs.append(libdir)
-            if ltd and use_stubs and os.curdir not in ext.runtime_library_dirs:
-                ext.runtime_library_dirs.append(os.curdir)
-
-        if self.editable_mode:
-            self.inplace = True
-
-    def setup_shlib_compiler(self):
-        compiler = self.shlib_compiler = new_compiler(
-            compiler=self.compiler, dry_run=self.dry_run, force=self.force
-        )
-        _customize_compiler_for_shlib(compiler)
-
-        if self.include_dirs is not None:
-            compiler.set_include_dirs(self.include_dirs)
-        if self.define is not None:
-            # 'define' option is a list of (name,value) tuples
-            for name, value in self.define:
-                compiler.define_macro(name, value)
-        if self.undef is not None:
-            for macro in self.undef:
-                compiler.undefine_macro(macro)
-        if self.libraries is not None:
-            compiler.set_libraries(self.libraries)
-        if self.library_dirs is not None:
-            compiler.set_library_dirs(self.library_dirs)
-        if self.rpath is not None:
-            compiler.set_runtime_library_dirs(self.rpath)
-        if self.link_objects is not None:
-            compiler.set_link_objects(self.link_objects)
-
-        # hack so distutils' build_extension() builds a library instead
-        compiler.link_shared_object = link_shared_object.__get__(compiler)  # type: ignore[method-assign]
-
-    def get_export_symbols(self, ext):
-        if isinstance(ext, Library):
-            return ext.export_symbols
-        return _build_ext.get_export_symbols(self, ext)
-
-    def build_extension(self, ext) -> None:
-        ext._convert_pyx_sources_to_lang()
-        _compiler = self.compiler
-        try:
-            if isinstance(ext, Library):
-                self.compiler = self.shlib_compiler
-            _build_ext.build_extension(self, ext)
-            if ext._needs_stub:
-                build_lib = self.get_finalized_command('build_py').build_lib
-                self.write_stub(build_lib, ext)
-        finally:
-            self.compiler = _compiler
-
-    def links_to_dynamic(self, ext):
-        """Return true if 'ext' links to a dynamic lib in the same package"""
-        # XXX this should check to ensure the lib is actually being built
-        # XXX as dynamic, and not just using a locally-found version or a
-        # XXX static-compiled version
-        libnames = dict.fromkeys([lib._full_name for lib in self.shlibs])
-        pkg = '.'.join(ext._full_name.split('.')[:-1] + [''])
-        return any(pkg + libname in libnames for libname in ext.libraries)
-
-    def get_source_files(self) -> list[str]:
-        return [*_build_ext.get_source_files(self), *self._get_internal_depends()]
-
-    def _get_internal_depends(self) -> Iterator[str]:
-        """Yield ``ext.depends`` that are contained by the project directory"""
-        project_root = Path(self.distribution.src_root or os.curdir).resolve()
-        depends = (dep for ext in self.extensions for dep in ext.depends)
-
-        def skip(orig_path: str, reason: str) -> None:
-            log.info(
-                "dependency %s won't be automatically "
-                "included in the manifest: the path %s",
-                orig_path,
-                reason,
-            )
-
-        for dep in depends:
-            path = Path(dep)
-
-            if path.is_absolute():
-                skip(dep, "must be relative")
-                continue
-
-            if ".." in path.parts:
-                skip(dep, "can't have `..` segments")
-                continue
-
-            try:
-                resolved = (project_root / path).resolve(strict=True)
-            except OSError:
-                skip(dep, "doesn't exist")
-                continue
-
-            try:
-                resolved.relative_to(project_root)
-            except ValueError:
-                skip(dep, "must be inside the project root")
-                continue
-
-            yield path.as_posix()
-
-    def get_outputs(self) -> list[str]:
-        if self.inplace:
-            return list(self.get_output_mapping().keys())
-        return sorted(_build_ext.get_outputs(self) + self.__get_stubs_outputs())
-
-    def get_output_mapping(self) -> dict[str, str]:
-        """See :class:`setuptools.commands.build.SubCommand`"""
-        mapping = self._get_output_mapping()
-        return dict(sorted(mapping, key=lambda x: x[0]))
-
-    def __get_stubs_outputs(self):
-        # assemble the base name for each extension that needs a stub
-        ns_ext_bases = (
-            os.path.join(self.build_lib, *ext._full_name.split('.'))
-            for ext in self.extensions
-            if ext._needs_stub
-        )
-        # pair each base with the extension
-        pairs = itertools.product(ns_ext_bases, self.__get_output_extensions())
-        return list(base + fnext for base, fnext in pairs)
-
-    def __get_output_extensions(self):
-        yield '.py'
-        yield '.pyc'
-        if self.get_finalized_command('build_py').optimize:
-            yield '.pyo'
-
-    def write_stub(self, output_dir, ext, compile=False) -> None:
-        stub_file = os.path.join(output_dir, *ext._full_name.split('.')) + '.py'
-        self._write_stub_file(stub_file, ext, compile)
-
-    def _write_stub_file(self, stub_file: str, ext: Extension, compile=False):
-        log.info("writing stub loader for %s to %s", ext._full_name, stub_file)
-        if compile and os.path.exists(stub_file):
-            raise BaseError(stub_file + " already exists! Please delete.")
-        if not self.dry_run:
-            with open(stub_file, 'w', encoding="utf-8") as f:
-                content = '\n'.join([
-                    "def __bootstrap__():",
-                    "   global __bootstrap__, __file__, __loader__",
-                    "   import sys, os, pkg_resources, importlib.util" + if_dl(", dl"),
-                    "   __file__ = pkg_resources.resource_filename"
-                    f"(__name__,{os.path.basename(ext._file_name)!r})",
-                    "   del __bootstrap__",
-                    "   if '__loader__' in globals():",
-                    "       del __loader__",
-                    if_dl("   old_flags = sys.getdlopenflags()"),
-                    "   old_dir = os.getcwd()",
-                    "   try:",
-                    "     os.chdir(os.path.dirname(__file__))",
-                    if_dl("     sys.setdlopenflags(dl.RTLD_NOW)"),
-                    "     spec = importlib.util.spec_from_file_location(",
-                    "                __name__, __file__)",
-                    "     mod = importlib.util.module_from_spec(spec)",
-                    "     spec.loader.exec_module(mod)",
-                    "   finally:",
-                    if_dl("     sys.setdlopenflags(old_flags)"),
-                    "     os.chdir(old_dir)",
-                    "__bootstrap__()",
-                    "",  # terminal \n
-                ])
-                f.write(content)
-        if compile:
-            self._compile_and_remove_stub(stub_file)
-
-    def _compile_and_remove_stub(self, stub_file: str):
-        from distutils.util import byte_compile
-
-        byte_compile([stub_file], optimize=0, force=True, dry_run=self.dry_run)
-        optimize = self.get_finalized_command('install_lib').optimize
-        if optimize > 0:
-            byte_compile(
-                [stub_file],
-                optimize=optimize,
-                force=True,
-                dry_run=self.dry_run,
-            )
-        if os.path.exists(stub_file) and not self.dry_run:
-            os.unlink(stub_file)
-
-
-if use_stubs or os.name == 'nt':
-    # Build shared libraries
-    #
-    def link_shared_object(
-        self,
-        objects,
-        output_libname,
-        output_dir=None,
-        libraries=None,
-        library_dirs=None,
-        runtime_library_dirs=None,
-        export_symbols=None,
-        debug: bool = False,
-        extra_preargs=None,
-        extra_postargs=None,
-        build_temp=None,
-        target_lang=None,
-    ) -> None:
-        self.link(
-            self.SHARED_LIBRARY,
-            objects,
-            output_libname,
-            output_dir,
-            libraries,
-            library_dirs,
-            runtime_library_dirs,
-            export_symbols,
-            debug,
-            extra_preargs,
-            extra_postargs,
-            build_temp,
-            target_lang,
-        )
-
-else:
-    # Build static libraries everywhere else
-    libtype = 'static'
-
-    def link_shared_object(
-        self,
-        objects,
-        output_libname,
-        output_dir=None,
-        libraries=None,
-        library_dirs=None,
-        runtime_library_dirs=None,
-        export_symbols=None,
-        debug: bool = False,
-        extra_preargs=None,
-        extra_postargs=None,
-        build_temp=None,
-        target_lang=None,
-    ) -> None:
-        # XXX we need to either disallow these attrs on Library instances,
-        # or warn/abort here if set, or something...
-        # libraries=None, library_dirs=None, runtime_library_dirs=None,
-        # export_symbols=None, extra_preargs=None, extra_postargs=None,
-        # build_temp=None
-
-        assert output_dir is None  # distutils build_ext doesn't pass this
-        output_dir, filename = os.path.split(output_libname)
-        basename, _ext = os.path.splitext(filename)
-        if self.library_filename("x").startswith('lib'):
-            # strip 'lib' prefix; this is kludgy if some platform uses
-            # a different prefix
-            basename = basename[3:]
-
-        self.create_static_lib(objects, basename, output_dir, debug, target_lang)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/build_py.py b/llmlab/lib/python3.12/site-packages/setuptools/command/build_py.py
deleted file mode 100644
index 2f6fcb7..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/build_py.py
+++ /dev/null
@@ -1,400 +0,0 @@
-from __future__ import annotations
-
-import fnmatch
-import itertools
-import os
-import stat
-import textwrap
-from collections.abc import Iterable, Iterator
-from functools import partial
-from glob import glob
-from pathlib import Path
-
-from more_itertools import unique_everseen
-
-from .._path import StrPath, StrPathT
-from ..dist import Distribution
-from ..warnings import SetuptoolsDeprecationWarning
-
-import distutils.command.build_py as orig
-import distutils.errors
-from distutils.util import convert_path
-
-_IMPLICIT_DATA_FILES = ('*.pyi', 'py.typed')
-
-
-def make_writable(target) -> None:
-    os.chmod(target, os.stat(target).st_mode | stat.S_IWRITE)
-
-
-class build_py(orig.build_py):
-    """Enhanced 'build_py' command that includes data files with packages
-
-    The data files are specified via a 'package_data' argument to 'setup()'.
-    See 'setuptools.dist.Distribution' for more details.
-
-    Also, this version of the 'build_py' command allows you to specify both
-    'py_modules' and 'packages' in the same setup operation.
-    """
-
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-    editable_mode: bool = False
-    existing_egg_info_dir: StrPath | None = None  #: Private API, internal use only.
-
-    def finalize_options(self):
-        orig.build_py.finalize_options(self)
-        self.package_data = self.distribution.package_data
-        self.exclude_package_data = self.distribution.exclude_package_data or {}
-        if 'data_files' in self.__dict__:
-            del self.__dict__['data_files']
-
-    def copy_file(  # type: ignore[override] # No overload, no bytes support
-        self,
-        infile: StrPath,
-        outfile: StrPathT,
-        preserve_mode: bool = True,
-        preserve_times: bool = True,
-        link: str | None = None,
-        level: object = 1,
-    ) -> tuple[StrPathT | str, bool]:
-        # Overwrite base class to allow using links
-        if link:
-            infile = str(Path(infile).resolve())
-            outfile = str(Path(outfile).resolve())  # type: ignore[assignment] # Re-assigning a str when outfile is StrPath is ok
-        return super().copy_file(  # pyright: ignore[reportReturnType] # pypa/distutils#309
-            infile, outfile, preserve_mode, preserve_times, link, level
-        )
-
-    def run(self) -> None:
-        """Build modules, packages, and copy data files to build directory"""
-        if not (self.py_modules or self.packages) or self.editable_mode:
-            return
-
-        if self.py_modules:
-            self.build_modules()
-
-        if self.packages:
-            self.build_packages()
-            self.build_package_data()
-
-        # Only compile actual .py files, using our base class' idea of what our
-        # output files are.
-        self.byte_compile(orig.build_py.get_outputs(self, include_bytecode=False))
-
-    def __getattr__(self, attr: str):
-        "lazily compute data files"
-        if attr == 'data_files':
-            self.data_files = self._get_data_files()
-            return self.data_files
-        return orig.build_py.__getattr__(self, attr)
-
-    def _get_data_files(self):
-        """Generate list of '(package,src_dir,build_dir,filenames)' tuples"""
-        self.analyze_manifest()
-        return list(map(self._get_pkg_data_files, self.packages or ()))
-
-    def get_data_files_without_manifest(self):
-        """
-        Generate list of ``(package,src_dir,build_dir,filenames)`` tuples,
-        but without triggering any attempt to analyze or build the manifest.
-        """
-        # Prevent eventual errors from unset `manifest_files`
-        # (that would otherwise be set by `analyze_manifest`)
-        self.__dict__.setdefault('manifest_files', {})
-        return list(map(self._get_pkg_data_files, self.packages or ()))
-
-    def _get_pkg_data_files(self, package):
-        # Locate package source directory
-        src_dir = self.get_package_dir(package)
-
-        # Compute package build directory
-        build_dir = os.path.join(*([self.build_lib] + package.split('.')))
-
-        # Strip directory from globbed filenames
-        filenames = [
-            os.path.relpath(file, src_dir)
-            for file in self.find_data_files(package, src_dir)
-        ]
-        return package, src_dir, build_dir, filenames
-
-    def find_data_files(self, package, src_dir):
-        """Return filenames for package's data files in 'src_dir'"""
-        patterns = self._get_platform_patterns(
-            self.package_data,
-            package,
-            src_dir,
-            extra_patterns=_IMPLICIT_DATA_FILES,
-        )
-        globs_expanded = map(partial(glob, recursive=True), patterns)
-        # flatten the expanded globs into an iterable of matches
-        globs_matches = itertools.chain.from_iterable(globs_expanded)
-        glob_files = filter(os.path.isfile, globs_matches)
-        files = itertools.chain(
-            self.manifest_files.get(package, []),
-            glob_files,
-        )
-        return self.exclude_data_files(package, src_dir, files)
-
-    def get_outputs(self, include_bytecode: bool = True) -> list[str]:  # type: ignore[override] # Using a real boolean instead of 0|1
-        """See :class:`setuptools.commands.build.SubCommand`"""
-        if self.editable_mode:
-            return list(self.get_output_mapping().keys())
-        return super().get_outputs(include_bytecode)
-
-    def get_output_mapping(self) -> dict[str, str]:
-        """See :class:`setuptools.commands.build.SubCommand`"""
-        mapping = itertools.chain(
-            self._get_package_data_output_mapping(),
-            self._get_module_mapping(),
-        )
-        return dict(sorted(mapping, key=lambda x: x[0]))
-
-    def _get_module_mapping(self) -> Iterator[tuple[str, str]]:
-        """Iterate over all modules producing (dest, src) pairs."""
-        for package, module, module_file in self.find_all_modules():
-            package = package.split('.')
-            filename = self.get_module_outfile(self.build_lib, package, module)
-            yield (filename, module_file)
-
-    def _get_package_data_output_mapping(self) -> Iterator[tuple[str, str]]:
-        """Iterate over package data producing (dest, src) pairs."""
-        for package, src_dir, build_dir, filenames in self.data_files:
-            for filename in filenames:
-                target = os.path.join(build_dir, filename)
-                srcfile = os.path.join(src_dir, filename)
-                yield (target, srcfile)
-
-    def build_package_data(self) -> None:
-        """Copy data files into build directory"""
-        for target, srcfile in self._get_package_data_output_mapping():
-            self.mkpath(os.path.dirname(target))
-            _outf, _copied = self.copy_file(srcfile, target)
-            make_writable(target)
-
-    def analyze_manifest(self) -> None:
-        self.manifest_files: dict[str, list[str]] = {}
-        if not self.distribution.include_package_data:
-            return
-        src_dirs: dict[str, str] = {}
-        for package in self.packages or ():
-            # Locate package source directory
-            src_dirs[assert_relative(self.get_package_dir(package))] = package
-
-        if (
-            self.existing_egg_info_dir
-            and Path(self.existing_egg_info_dir, "SOURCES.txt").exists()
-        ):
-            egg_info_dir = self.existing_egg_info_dir
-            manifest = Path(egg_info_dir, "SOURCES.txt")
-            files = manifest.read_text(encoding="utf-8").splitlines()
-        else:
-            self.run_command('egg_info')
-            ei_cmd = self.get_finalized_command('egg_info')
-            egg_info_dir = ei_cmd.egg_info
-            files = ei_cmd.filelist.files
-
-        check = _IncludePackageDataAbuse()
-        for path in self._filter_build_files(files, egg_info_dir):
-            d, f = os.path.split(assert_relative(path))
-            prev = None
-            oldf = f
-            while d and d != prev and d not in src_dirs:
-                prev = d
-                d, df = os.path.split(d)
-                f = os.path.join(df, f)
-            if d in src_dirs:
-                if f == oldf:
-                    if check.is_module(f):
-                        continue  # it's a module, not data
-                else:
-                    importable = check.importable_subpackage(src_dirs[d], f)
-                    if importable:
-                        check.warn(importable)
-                self.manifest_files.setdefault(src_dirs[d], []).append(path)
-
-    def _filter_build_files(
-        self, files: Iterable[str], egg_info: StrPath
-    ) -> Iterator[str]:
-        """
-        ``build_meta`` may try to create egg_info outside of the project directory,
-        and this can be problematic for certain plugins (reported in issue #3500).
-
-        Extensions might also include between their sources files created on the
-        ``build_lib`` and ``build_temp`` directories.
-
-        This function should filter this case of invalid files out.
-        """
-        build = self.get_finalized_command("build")
-        build_dirs = (egg_info, self.build_lib, build.build_temp, build.build_base)
-        norm_dirs = [os.path.normpath(p) for p in build_dirs if p]
-
-        for file in files:
-            norm_path = os.path.normpath(file)
-            if not os.path.isabs(file) or all(d not in norm_path for d in norm_dirs):
-                yield file
-
-    def get_data_files(self) -> None:
-        pass  # Lazily compute data files in _get_data_files() function.
-
-    def check_package(self, package, package_dir):
-        """Check namespace packages' __init__ for declare_namespace"""
-        try:
-            return self.packages_checked[package]
-        except KeyError:
-            pass
-
-        init_py = orig.build_py.check_package(self, package, package_dir)
-        self.packages_checked[package] = init_py
-
-        if not init_py or not self.distribution.namespace_packages:
-            return init_py
-
-        for pkg in self.distribution.namespace_packages:
-            if pkg == package or pkg.startswith(package + '.'):
-                break
-        else:
-            return init_py
-
-        with open(init_py, 'rb') as f:
-            contents = f.read()
-        if b'declare_namespace' not in contents:
-            raise distutils.errors.DistutilsError(
-                f"Namespace package problem: {package} is a namespace package, but "
-                "its\n__init__.py does not call declare_namespace()! Please "
-                'fix it.\n(See the setuptools manual under '
-                '"Namespace Packages" for details.)\n"'
-            )
-        return init_py
-
-    def initialize_options(self):
-        self.packages_checked = {}
-        orig.build_py.initialize_options(self)
-        self.editable_mode = False
-        self.existing_egg_info_dir = None
-
-    def get_package_dir(self, package):
-        res = orig.build_py.get_package_dir(self, package)
-        if self.distribution.src_root is not None:
-            return os.path.join(self.distribution.src_root, res)
-        return res
-
-    def exclude_data_files(self, package, src_dir, files):
-        """Filter filenames for package's data files in 'src_dir'"""
-        files = list(files)
-        patterns = self._get_platform_patterns(
-            self.exclude_package_data,
-            package,
-            src_dir,
-        )
-        match_groups = (fnmatch.filter(files, pattern) for pattern in patterns)
-        # flatten the groups of matches into an iterable of matches
-        matches = itertools.chain.from_iterable(match_groups)
-        bad = set(matches)
-        keepers = (fn for fn in files if fn not in bad)
-        # ditch dupes
-        return list(unique_everseen(keepers))
-
-    @staticmethod
-    def _get_platform_patterns(spec, package, src_dir, extra_patterns=()):
-        """
-        yield platform-specific path patterns (suitable for glob
-        or fn_match) from a glob-based spec (such as
-        self.package_data or self.exclude_package_data)
-        matching package in src_dir.
-        """
-        raw_patterns = itertools.chain(
-            extra_patterns,
-            spec.get('', []),
-            spec.get(package, []),
-        )
-        return (
-            # Each pattern has to be converted to a platform-specific path
-            os.path.join(src_dir, convert_path(pattern))
-            for pattern in raw_patterns
-        )
-
-
-def assert_relative(path):
-    if not os.path.isabs(path):
-        return path
-    from distutils.errors import DistutilsSetupError
-
-    msg = (
-        textwrap.dedent(
-            """
-        Error: setup script specifies an absolute path:
-
-            %s
-
-        setup() arguments must *always* be /-separated paths relative to the
-        setup.py directory, *never* absolute paths.
-        """
-        ).lstrip()
-        % path
-    )
-    raise DistutilsSetupError(msg)
-
-
-class _IncludePackageDataAbuse:
-    """Inform users that package or module is included as 'data file'"""
-
-    class _Warning(SetuptoolsDeprecationWarning):
-        _SUMMARY = """
-        Package {importable!r} is absent from the `packages` configuration.
-        """
-
-        _DETAILS = """
-        ############################
-        # Package would be ignored #
-        ############################
-        Python recognizes {importable!r} as an importable package[^1],
-        but it is absent from setuptools' `packages` configuration.
-
-        This leads to an ambiguous overall configuration. If you want to distribute this
-        package, please make sure that {importable!r} is explicitly added
-        to the `packages` configuration field.
-
-        Alternatively, you can also rely on setuptools' discovery methods
-        (for example by using `find_namespace_packages(...)`/`find_namespace:`
-        instead of `find_packages(...)`/`find:`).
-
-        You can read more about "package discovery" on setuptools documentation page:
-
-        - https://setuptools.pypa.io/en/latest/userguide/package_discovery.html
-
-        If you don't want {importable!r} to be distributed and are
-        already explicitly excluding {importable!r} via
-        `find_namespace_packages(...)/find_namespace` or `find_packages(...)/find`,
-        you can try to use `exclude_package_data`, or `include-package-data=False` in
-        combination with a more fine grained `package-data` configuration.
-
-        You can read more about "package data files" on setuptools documentation page:
-
-        - https://setuptools.pypa.io/en/latest/userguide/datafiles.html
-
-
-        [^1]: For Python, any directory (with suitable naming) can be imported,
-              even if it does not contain any `.py` files.
-              On the other hand, currently there is no concept of package data
-              directory, all directories are treated like packages.
-        """
-        # _DUE_DATE: still not defined as this is particularly controversial.
-        # Warning initially introduced in May 2022. See issue #3340 for discussion.
-
-    def __init__(self):
-        self._already_warned = set()
-
-    def is_module(self, file):
-        return file.endswith(".py") and file[: -len(".py")].isidentifier()
-
-    def importable_subpackage(self, parent, file):
-        pkg = Path(file).parent
-        parts = list(itertools.takewhile(str.isidentifier, pkg.parts))
-        if parts:
-            return ".".join([parent, *parts])
-        return None
-
-    def warn(self, importable):
-        if importable not in self._already_warned:
-            self._Warning.emit(importable=importable)
-            self._already_warned.add(importable)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/develop.py b/llmlab/lib/python3.12/site-packages/setuptools/command/develop.py
deleted file mode 100644
index 7eee29d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/develop.py
+++ /dev/null
@@ -1,195 +0,0 @@
-import glob
-import os
-
-import setuptools
-from setuptools import _normalization, _path, namespaces
-from setuptools.command.easy_install import easy_install
-
-from ..unicode_utils import _read_utf8_with_fallback
-
-from distutils import log
-from distutils.errors import DistutilsOptionError
-from distutils.util import convert_path
-
-
-class develop(namespaces.DevelopInstaller, easy_install):
-    """Set up package for development"""
-
-    description = "install package in 'development mode'"
-
-    user_options = easy_install.user_options + [
-        ("uninstall", "u", "Uninstall this source package"),
-        ("egg-path=", None, "Set the path to be used in the .egg-link file"),
-    ]
-
-    boolean_options = easy_install.boolean_options + ['uninstall']
-
-    command_consumes_arguments = False  # override base
-
-    def run(self):
-        if self.uninstall:
-            self.multi_version = True
-            self.uninstall_link()
-            self.uninstall_namespaces()
-        else:
-            self.install_for_development()
-        self.warn_deprecated_options()
-
-    def initialize_options(self):
-        self.uninstall = None
-        self.egg_path = None
-        easy_install.initialize_options(self)
-        self.setup_path = None
-        self.always_copy_from = '.'  # always copy eggs installed in curdir
-
-    def finalize_options(self) -> None:
-        import pkg_resources
-
-        ei = self.get_finalized_command("egg_info")
-        self.args = [ei.egg_name]
-
-        easy_install.finalize_options(self)
-        self.expand_basedirs()
-        self.expand_dirs()
-        # pick up setup-dir .egg files only: no .egg-info
-        self.package_index.scan(glob.glob('*.egg'))
-
-        egg_link_fn = (
-            _normalization.filename_component_broken(ei.egg_name) + '.egg-link'
-        )
-        self.egg_link = os.path.join(self.install_dir, egg_link_fn)
-        self.egg_base = ei.egg_base
-        if self.egg_path is None:
-            self.egg_path = os.path.abspath(ei.egg_base)
-
-        target = _path.normpath(self.egg_base)
-        egg_path = _path.normpath(os.path.join(self.install_dir, self.egg_path))
-        if egg_path != target:
-            raise DistutilsOptionError(
-                "--egg-path must be a relative path from the install"
-                " directory to " + target
-            )
-
-        # Make a distribution for the package's source
-        self.dist = pkg_resources.Distribution(
-            target,
-            pkg_resources.PathMetadata(target, os.path.abspath(ei.egg_info)),
-            project_name=ei.egg_name,
-        )
-
-        self.setup_path = self._resolve_setup_path(
-            self.egg_base,
-            self.install_dir,
-            self.egg_path,
-        )
-
-    @staticmethod
-    def _resolve_setup_path(egg_base, install_dir, egg_path):
-        """
-        Generate a path from egg_base back to '.' where the
-        setup script resides and ensure that path points to the
-        setup path from $install_dir/$egg_path.
-        """
-        path_to_setup = egg_base.replace(os.sep, '/').rstrip('/')
-        if path_to_setup != os.curdir:
-            path_to_setup = '../' * (path_to_setup.count('/') + 1)
-        resolved = _path.normpath(os.path.join(install_dir, egg_path, path_to_setup))
-        curdir = _path.normpath(os.curdir)
-        if resolved != curdir:
-            raise DistutilsOptionError(
-                "Can't get a consistent path to setup script from"
-                " installation directory",
-                resolved,
-                curdir,
-            )
-        return path_to_setup
-
-    def install_for_development(self) -> None:
-        self.run_command('egg_info')
-
-        # Build extensions in-place
-        self.reinitialize_command('build_ext', inplace=True)
-        self.run_command('build_ext')
-
-        if setuptools.bootstrap_install_from:
-            self.easy_install(setuptools.bootstrap_install_from)
-            setuptools.bootstrap_install_from = None
-
-        self.install_namespaces()
-
-        # create an .egg-link in the installation dir, pointing to our egg
-        log.info("Creating %s (link to %s)", self.egg_link, self.egg_base)
-        if not self.dry_run:
-            with open(self.egg_link, "w", encoding="utf-8") as f:
-                f.write(self.egg_path + "\n" + self.setup_path)
-        # postprocess the installed distro, fixing up .pth, installing scripts,
-        # and handling requirements
-        self.process_distribution(None, self.dist, not self.no_deps)
-
-    def uninstall_link(self) -> None:
-        if os.path.exists(self.egg_link):
-            log.info("Removing %s (link to %s)", self.egg_link, self.egg_base)
-
-            contents = [
-                line.rstrip()
-                for line in _read_utf8_with_fallback(self.egg_link).splitlines()
-            ]
-
-            if contents not in ([self.egg_path], [self.egg_path, self.setup_path]):
-                log.warn("Link points to %s: uninstall aborted", contents)
-                return
-            if not self.dry_run:
-                os.unlink(self.egg_link)
-        if not self.dry_run:
-            self.update_pth(self.dist)  # remove any .pth link to us
-        if self.distribution.scripts:
-            # XXX should also check for entry point scripts!
-            log.warn("Note: you must uninstall or replace scripts manually!")
-
-    def install_egg_scripts(self, dist):
-        if dist is not self.dist:
-            # Installing a dependency, so fall back to normal behavior
-            return easy_install.install_egg_scripts(self, dist)
-
-        # create wrapper scripts in the script dir, pointing to dist.scripts
-
-        # new-style...
-        self.install_wrapper_scripts(dist)
-
-        # ...and old-style
-        for script_name in self.distribution.scripts or []:
-            script_path = os.path.abspath(convert_path(script_name))
-            script_name = os.path.basename(script_path)
-            script_text = _read_utf8_with_fallback(script_path)
-            self.install_script(dist, script_name, script_text, script_path)
-
-        return None
-
-    def install_wrapper_scripts(self, dist):
-        dist = VersionlessRequirement(dist)
-        return easy_install.install_wrapper_scripts(self, dist)
-
-
-class VersionlessRequirement:
-    """
-    Adapt a pkg_resources.Distribution to simply return the project
-    name as the 'requirement' so that scripts will work across
-    multiple versions.
-
-    >>> from pkg_resources import Distribution
-    >>> dist = Distribution(project_name='foo', version='1.0')
-    >>> str(dist.as_requirement())
-    'foo==1.0'
-    >>> adapted_dist = VersionlessRequirement(dist)
-    >>> str(adapted_dist.as_requirement())
-    'foo'
-    """
-
-    def __init__(self, dist) -> None:
-        self.__dist = dist
-
-    def __getattr__(self, name: str):
-        return getattr(self.__dist, name)
-
-    def as_requirement(self):
-        return self.project_name
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/dist_info.py b/llmlab/lib/python3.12/site-packages/setuptools/command/dist_info.py
deleted file mode 100644
index dca01ff..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/dist_info.py
+++ /dev/null
@@ -1,103 +0,0 @@
-"""
-Create a dist_info directory
-As defined in the wheel specification
-"""
-
-import os
-import shutil
-from contextlib import contextmanager
-from pathlib import Path
-from typing import cast
-
-from .. import _normalization
-from .._shutil import rmdir as _rm
-from .egg_info import egg_info as egg_info_cls
-
-from distutils import log
-from distutils.core import Command
-
-
-class dist_info(Command):
-    """
-    This command is private and reserved for internal use of setuptools,
-    users should rely on ``setuptools.build_meta`` APIs.
-    """
-
-    description = "DO NOT CALL DIRECTLY, INTERNAL ONLY: create .dist-info directory"
-
-    user_options = [
-        (
-            'output-dir=',
-            'o',
-            "directory inside of which the .dist-info will be"
-            "created [default: top of the source tree]",
-        ),
-        ('tag-date', 'd', "Add date stamp (e.g. 20050528) to version number"),
-        ('tag-build=', 'b', "Specify explicit tag to add to version number"),
-        ('no-date', 'D', "Don't include date stamp [default]"),
-        ('keep-egg-info', None, "*TRANSITIONAL* will be removed in the future"),
-    ]
-
-    boolean_options = ['tag-date', 'keep-egg-info']
-    negative_opt = {'no-date': 'tag-date'}
-
-    def initialize_options(self):
-        self.output_dir = None
-        self.name = None
-        self.dist_info_dir = None
-        self.tag_date = None
-        self.tag_build = None
-        self.keep_egg_info = False
-
-    def finalize_options(self) -> None:
-        dist = self.distribution
-        project_dir = dist.src_root or os.curdir
-        self.output_dir = Path(self.output_dir or project_dir)
-
-        egg_info = cast(egg_info_cls, self.reinitialize_command("egg_info"))
-        egg_info.egg_base = str(self.output_dir)
-
-        if self.tag_date:
-            egg_info.tag_date = self.tag_date
-        else:
-            self.tag_date = egg_info.tag_date
-
-        if self.tag_build:
-            egg_info.tag_build = self.tag_build
-        else:
-            self.tag_build = egg_info.tag_build
-
-        egg_info.finalize_options()
-        self.egg_info = egg_info
-
-        name = _normalization.safer_name(dist.get_name())
-        version = _normalization.safer_best_effort_version(dist.get_version())
-        self.name = f"{name}-{version}"
-        self.dist_info_dir = os.path.join(self.output_dir, f"{self.name}.dist-info")
-
-    @contextmanager
-    def _maybe_bkp_dir(self, dir_path: str, requires_bkp: bool):
-        if requires_bkp:
-            bkp_name = f"{dir_path}.__bkp__"
-            _rm(bkp_name, ignore_errors=True)
-            shutil.copytree(dir_path, bkp_name, dirs_exist_ok=True, symlinks=True)
-            try:
-                yield
-            finally:
-                _rm(dir_path, ignore_errors=True)
-                shutil.move(bkp_name, dir_path)
-        else:
-            yield
-
-    def run(self) -> None:
-        self.output_dir.mkdir(parents=True, exist_ok=True)
-        self.egg_info.run()
-        egg_info_dir = self.egg_info.egg_info
-        assert os.path.isdir(egg_info_dir), ".egg-info dir should have been created"
-
-        log.info(f"creating '{os.path.abspath(self.dist_info_dir)}'")
-        bdist_wheel = self.get_finalized_command('bdist_wheel')
-
-        # TODO: if bdist_wheel if merged into setuptools, just add "keep_egg_info" there
-        with self._maybe_bkp_dir(egg_info_dir, self.keep_egg_info):
-            bdist_wheel.egg2dist(egg_info_dir, self.dist_info_dir)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/easy_install.py b/llmlab/lib/python3.12/site-packages/setuptools/command/easy_install.py
deleted file mode 100644
index eb1b4c1..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/easy_install.py
+++ /dev/null
@@ -1,2365 +0,0 @@
-"""
-Easy Install
-------------
-
-A tool for doing automatic download/extract/build of distutils-based Python
-packages.  For detailed documentation, see the accompanying EasyInstall.txt
-file, or visit the `EasyInstall home page`__.
-
-__ https://setuptools.pypa.io/en/latest/deprecated/easy_install.html
-
-"""
-
-from __future__ import annotations
-
-import configparser
-import contextlib
-import io
-import os
-import random
-import re
-import shlex
-import shutil
-import site
-import stat
-import struct
-import subprocess
-import sys
-import sysconfig
-import tempfile
-import textwrap
-import warnings
-import zipfile
-import zipimport
-from collections.abc import Iterable
-from glob import glob
-from sysconfig import get_path
-from typing import TYPE_CHECKING, NoReturn, TypedDict
-
-from jaraco.text import yield_lines
-
-import pkg_resources
-from pkg_resources import (
-    DEVELOP_DIST,
-    Distribution,
-    DistributionNotFound,
-    EggMetadata,
-    Environment,
-    PathMetadata,
-    Requirement,
-    VersionConflict,
-    WorkingSet,
-    find_distributions,
-    get_distribution,
-    normalize_path,
-    resource_string,
-)
-from setuptools import Command
-from setuptools.archive_util import unpack_archive
-from setuptools.command import bdist_egg, egg_info, setopt
-from setuptools.package_index import URL_SCHEME, PackageIndex, parse_requirement_arg
-from setuptools.sandbox import run_setup
-from setuptools.warnings import SetuptoolsDeprecationWarning, SetuptoolsWarning
-from setuptools.wheel import Wheel
-
-from .._path import ensure_directory
-from .._shutil import attempt_chmod_verbose as chmod, rmtree as _rmtree
-from ..compat import py39, py312
-
-from distutils import dir_util, log
-from distutils.command import install
-from distutils.command.build_scripts import first_line_re
-from distutils.errors import (
-    DistutilsArgError,
-    DistutilsError,
-    DistutilsOptionError,
-    DistutilsPlatformError,
-)
-from distutils.util import convert_path, get_platform, subst_vars
-
-if TYPE_CHECKING:
-    from typing_extensions import Self
-
-# Turn on PEP440Warnings
-warnings.filterwarnings("default", category=pkg_resources.PEP440Warning)
-
-__all__ = [
-    'easy_install',
-    'PthDistributions',
-    'extract_wininst_cfg',
-    'get_exe_prefixes',
-]
-
-
-def is_64bit():
-    return struct.calcsize("P") == 8
-
-
-def _to_bytes(s):
-    return s.encode('utf8')
-
-
-def isascii(s):
-    try:
-        s.encode('ascii')
-    except UnicodeError:
-        return False
-    return True
-
-
-def _one_liner(text):
-    return textwrap.dedent(text).strip().replace('\n', '; ')
-
-
-class easy_install(Command):
-    """Manage a download/build/install process"""
-
-    description = "Find/get/install Python packages"
-    command_consumes_arguments = True
-
-    user_options = [
-        ('prefix=', None, "installation prefix"),
-        ("zip-ok", "z", "install package as a zipfile"),
-        ("multi-version", "m", "make apps have to require() a version"),
-        ("upgrade", "U", "force upgrade (searches PyPI for latest versions)"),
-        ("install-dir=", "d", "install package to DIR"),
-        ("script-dir=", "s", "install scripts to DIR"),
-        ("exclude-scripts", "x", "Don't install scripts"),
-        ("always-copy", "a", "Copy all needed packages to install dir"),
-        ("index-url=", "i", "base URL of Python Package Index"),
-        ("find-links=", "f", "additional URL(s) to search for packages"),
-        ("build-directory=", "b", "download/extract/build in DIR; keep the results"),
-        (
-            'optimize=',
-            'O',
-            'also compile with optimization: -O1 for "python -O", '
-            '-O2 for "python -OO", and -O0 to disable [default: -O0]',
-        ),
-        ('record=', None, "filename in which to record list of installed files"),
-        ('always-unzip', 'Z', "don't install as a zipfile, no matter what"),
-        ('site-dirs=', 'S', "list of directories where .pth files work"),
-        ('editable', 'e', "Install specified packages in editable form"),
-        ('no-deps', 'N', "don't install dependencies"),
-        ('allow-hosts=', 'H', "pattern(s) that hostnames must match"),
-        ('local-snapshots-ok', 'l', "allow building eggs from local checkouts"),
-        ('version', None, "print version information and exit"),
-        (
-            'no-find-links',
-            None,
-            "Don't load find-links defined in packages being installed",
-        ),
-        ('user', None, f"install in user site-package '{site.USER_SITE}'"),
-    ]
-    boolean_options = [
-        'zip-ok',
-        'multi-version',
-        'exclude-scripts',
-        'upgrade',
-        'always-copy',
-        'editable',
-        'no-deps',
-        'local-snapshots-ok',
-        'version',
-        'user',
-    ]
-
-    negative_opt = {'always-unzip': 'zip-ok'}
-    create_index = PackageIndex
-
-    def initialize_options(self):
-        EasyInstallDeprecationWarning.emit()
-
-        # the --user option seems to be an opt-in one,
-        # so the default should be False.
-        self.user = False
-        self.zip_ok = self.local_snapshots_ok = None
-        self.install_dir = self.script_dir = self.exclude_scripts = None
-        self.index_url = None
-        self.find_links = None
-        self.build_directory = None
-        self.args = None
-        self.optimize = self.record = None
-        self.upgrade = self.always_copy = self.multi_version = None
-        self.editable = self.no_deps = self.allow_hosts = None
-        self.root = self.prefix = self.no_report = None
-        self.version = None
-        self.install_purelib = None  # for pure module distributions
-        self.install_platlib = None  # non-pure (dists w/ extensions)
-        self.install_headers = None  # for C/C++ headers
-        self.install_lib = None  # set to either purelib or platlib
-        self.install_scripts = None
-        self.install_data = None
-        self.install_base = None
-        self.install_platbase = None
-        self.install_userbase = site.USER_BASE
-        self.install_usersite = site.USER_SITE
-        self.no_find_links = None
-
-        # Options not specifiable via command line
-        self.package_index = None
-        self.pth_file = self.always_copy_from = None
-        self.site_dirs = None
-        self.installed_projects = {}
-        # Always read easy_install options, even if we are subclassed, or have
-        # an independent instance created.  This ensures that defaults will
-        # always come from the standard configuration file(s)' "easy_install"
-        # section, even if this is a "develop" or "install" command, or some
-        # other embedding.
-        self._dry_run = None
-        self.verbose = self.distribution.verbose
-        self.distribution._set_command_options(
-            self, self.distribution.get_option_dict('easy_install')
-        )
-
-    def delete_blockers(self, blockers) -> None:
-        extant_blockers = (
-            filename
-            for filename in blockers
-            if os.path.exists(filename) or os.path.islink(filename)
-        )
-        list(map(self._delete_path, extant_blockers))
-
-    def _delete_path(self, path):
-        log.info("Deleting %s", path)
-        if self.dry_run:
-            return
-
-        is_tree = os.path.isdir(path) and not os.path.islink(path)
-        remover = _rmtree if is_tree else os.unlink
-        remover(path)
-
-    @staticmethod
-    def _render_version():
-        """
-        Render the Setuptools version and installation details, then exit.
-        """
-        ver = f'{sys.version_info.major}.{sys.version_info.minor}'
-        dist = get_distribution('setuptools')
-        print(f'setuptools {dist.version} from {dist.location} (Python {ver})')
-        raise SystemExit
-
-    def finalize_options(self) -> None:  # noqa: C901  # is too complex (25)  # FIXME
-        self.version and self._render_version()
-
-        py_version = sys.version.split()[0]
-
-        self.config_vars = dict(sysconfig.get_config_vars())
-
-        self.config_vars.update({
-            'dist_name': self.distribution.get_name(),
-            'dist_version': self.distribution.get_version(),
-            'dist_fullname': self.distribution.get_fullname(),
-            'py_version': py_version,
-            'py_version_short': f'{sys.version_info.major}.{sys.version_info.minor}',
-            'py_version_nodot': f'{sys.version_info.major}{sys.version_info.minor}',
-            'sys_prefix': self.config_vars['prefix'],
-            'sys_exec_prefix': self.config_vars['exec_prefix'],
-            # Only POSIX systems have abiflags
-            'abiflags': getattr(sys, 'abiflags', ''),
-            # Only python 3.9+ has platlibdir
-            'platlibdir': getattr(sys, 'platlibdir', 'lib'),
-        })
-        with contextlib.suppress(AttributeError):
-            # only for distutils outside stdlib
-            self.config_vars.update({
-                'implementation_lower': install._get_implementation().lower(),
-                'implementation': install._get_implementation(),
-            })
-
-        # pypa/distutils#113 Python 3.9 compat
-        self.config_vars.setdefault(
-            'py_version_nodot_plat',
-            getattr(sys, 'windir', '').replace('.', ''),
-        )
-
-        self.config_vars['userbase'] = self.install_userbase
-        self.config_vars['usersite'] = self.install_usersite
-        if self.user and not site.ENABLE_USER_SITE:
-            log.warn("WARNING: The user site-packages directory is disabled.")
-
-        self._fix_install_dir_for_user_site()
-
-        self.expand_basedirs()
-        self.expand_dirs()
-
-        self._expand(
-            'install_dir',
-            'script_dir',
-            'build_directory',
-            'site_dirs',
-        )
-        # If a non-default installation directory was specified, default the
-        # script directory to match it.
-        if self.script_dir is None:
-            self.script_dir = self.install_dir
-
-        if self.no_find_links is None:
-            self.no_find_links = False
-
-        # Let install_dir get set by install_lib command, which in turn
-        # gets its info from the install command, and takes into account
-        # --prefix and --home and all that other crud.
-        self.set_undefined_options('install_lib', ('install_dir', 'install_dir'))
-        # Likewise, set default script_dir from 'install_scripts.install_dir'
-        self.set_undefined_options('install_scripts', ('install_dir', 'script_dir'))
-
-        if self.user and self.install_purelib:
-            self.install_dir = self.install_purelib
-            self.script_dir = self.install_scripts
-        # default --record from the install command
-        self.set_undefined_options('install', ('record', 'record'))
-        self.all_site_dirs = get_site_dirs()
-        self.all_site_dirs.extend(self._process_site_dirs(self.site_dirs))
-
-        if not self.editable:
-            self.check_site_dir()
-        default_index = os.getenv("__EASYINSTALL_INDEX", "https://pypi.org/simple/")
-        # ^ Private API for testing purposes only
-        self.index_url = self.index_url or default_index
-        self.shadow_path = self.all_site_dirs[:]
-        for path_item in self.install_dir, normalize_path(self.script_dir):
-            if path_item not in self.shadow_path:
-                self.shadow_path.insert(0, path_item)
-
-        if self.allow_hosts is not None:
-            hosts = [s.strip() for s in self.allow_hosts.split(',')]
-        else:
-            hosts = ['*']
-        if self.package_index is None:
-            self.package_index = self.create_index(
-                self.index_url,
-                search_path=self.shadow_path,
-                hosts=hosts,
-            )
-        self.local_index = Environment(self.shadow_path + sys.path)
-
-        if self.find_links is not None:
-            if isinstance(self.find_links, str):
-                self.find_links = self.find_links.split()
-        else:
-            self.find_links = []
-        if self.local_snapshots_ok:
-            self.package_index.scan_egg_links(self.shadow_path + sys.path)
-        if not self.no_find_links:
-            self.package_index.add_find_links(self.find_links)
-        self.set_undefined_options('install_lib', ('optimize', 'optimize'))
-        self.optimize = self._validate_optimize(self.optimize)
-
-        if self.editable and not self.build_directory:
-            raise DistutilsArgError(
-                "Must specify a build directory (-b) when using --editable"
-            )
-        if not self.args:
-            raise DistutilsArgError(
-                "No urls, filenames, or requirements specified (see --help)"
-            )
-
-        self.outputs: list[str] = []
-
-    @staticmethod
-    def _process_site_dirs(site_dirs):
-        if site_dirs is None:
-            return
-
-        normpath = map(normalize_path, sys.path)
-        site_dirs = [os.path.expanduser(s.strip()) for s in site_dirs.split(',')]
-        for d in site_dirs:
-            if not os.path.isdir(d):
-                log.warn("%s (in --site-dirs) does not exist", d)
-            elif normalize_path(d) not in normpath:
-                raise DistutilsOptionError(d + " (in --site-dirs) is not on sys.path")
-            else:
-                yield normalize_path(d)
-
-    @staticmethod
-    def _validate_optimize(value):
-        try:
-            value = int(value)
-            if value not in range(3):
-                raise ValueError
-        except ValueError as e:
-            raise DistutilsOptionError("--optimize must be 0, 1, or 2") from e
-
-        return value
-
-    def _fix_install_dir_for_user_site(self):
-        """
-        Fix the install_dir if "--user" was used.
-        """
-        if not self.user:
-            return
-
-        self.create_home_path()
-        if self.install_userbase is None:
-            msg = "User base directory is not specified"
-            raise DistutilsPlatformError(msg)
-        self.install_base = self.install_platbase = self.install_userbase
-        scheme_name = f'{os.name}_user'
-        self.select_scheme(scheme_name)
-
-    def _expand_attrs(self, attrs):
-        for attr in attrs:
-            val = getattr(self, attr)
-            if val is not None:
-                if os.name == 'posix' or os.name == 'nt':
-                    val = os.path.expanduser(val)
-                val = subst_vars(val, self.config_vars)
-                setattr(self, attr, val)
-
-    def expand_basedirs(self) -> None:
-        """Calls `os.path.expanduser` on install_base, install_platbase and
-        root."""
-        self._expand_attrs(['install_base', 'install_platbase', 'root'])
-
-    def expand_dirs(self) -> None:
-        """Calls `os.path.expanduser` on install dirs."""
-        dirs = [
-            'install_purelib',
-            'install_platlib',
-            'install_lib',
-            'install_headers',
-            'install_scripts',
-            'install_data',
-        ]
-        self._expand_attrs(dirs)
-
-    def run(self, show_deprecation: bool = True) -> None:
-        if show_deprecation:
-            self.announce(
-                "WARNING: The easy_install command is deprecated "
-                "and will be removed in a future version.",
-                log.WARN,
-            )
-        if self.verbose != self.distribution.verbose:
-            log.set_verbosity(self.verbose)
-        try:
-            for spec in self.args:
-                self.easy_install(spec, not self.no_deps)
-            if self.record:
-                outputs = self.outputs
-                if self.root:  # strip any package prefix
-                    root_len = len(self.root)
-                    for counter in range(len(outputs)):
-                        outputs[counter] = outputs[counter][root_len:]
-                from distutils import file_util
-
-                self.execute(
-                    file_util.write_file,
-                    (self.record, outputs),
-                    f"writing list of installed files to '{self.record}'",
-                )
-            self.warn_deprecated_options()
-        finally:
-            log.set_verbosity(self.distribution.verbose)
-
-    def pseudo_tempname(self):
-        """Return a pseudo-tempname base in the install directory.
-        This code is intentionally naive; if a malicious party can write to
-        the target directory you're already in deep doodoo.
-        """
-        try:
-            pid = os.getpid()
-        except Exception:
-            pid = random.randint(0, sys.maxsize)
-        return os.path.join(self.install_dir, f"test-easy-install-{pid}")
-
-    def warn_deprecated_options(self) -> None:
-        pass
-
-    def check_site_dir(self) -> None:  # is too complex (12)  # FIXME
-        """Verify that self.install_dir is .pth-capable dir, if needed"""
-
-        instdir = normalize_path(self.install_dir)
-        pth_file = os.path.join(instdir, 'easy-install.pth')
-
-        if not os.path.exists(instdir):
-            try:
-                os.makedirs(instdir)
-            except OSError:
-                self.cant_write_to_target()
-
-        # Is it a configured, PYTHONPATH, implicit, or explicit site dir?
-        is_site_dir = instdir in self.all_site_dirs
-
-        if not is_site_dir and not self.multi_version:
-            # No?  Then directly test whether it does .pth file processing
-            is_site_dir = self.check_pth_processing()
-        else:
-            # make sure we can write to target dir
-            testfile = self.pseudo_tempname() + '.write-test'
-            test_exists = os.path.exists(testfile)
-            try:
-                if test_exists:
-                    os.unlink(testfile)
-                open(testfile, 'wb').close()
-                os.unlink(testfile)
-            except OSError:
-                self.cant_write_to_target()
-
-        if not is_site_dir and not self.multi_version:
-            # Can't install non-multi to non-site dir with easy_install
-            pythonpath = os.environ.get('PYTHONPATH', '')
-            log.warn(self.__no_default_msg, self.install_dir, pythonpath)
-
-        if is_site_dir:
-            if self.pth_file is None:
-                self.pth_file = PthDistributions(pth_file, self.all_site_dirs)
-        else:
-            self.pth_file = None
-
-        if self.multi_version and not os.path.exists(pth_file):
-            self.pth_file = None  # don't create a .pth file
-        self.install_dir = instdir
-
-    __cant_write_msg = textwrap.dedent(
-        """
-        can't create or remove files in install directory
-
-        The following error occurred while trying to add or remove files in the
-        installation directory:
-
-            %s
-
-        The installation directory you specified (via --install-dir, --prefix, or
-        the distutils default setting) was:
-
-            %s
-        """
-    ).lstrip()
-
-    __not_exists_id = textwrap.dedent(
-        """
-        This directory does not currently exist.  Please create it and try again, or
-        choose a different installation directory (using the -d or --install-dir
-        option).
-        """
-    ).lstrip()
-
-    __access_msg = textwrap.dedent(
-        """
-        Perhaps your account does not have write access to this directory?  If the
-        installation directory is a system-owned directory, you may need to sign in
-        as the administrator or "root" account.  If you do not have administrative
-        access to this machine, you may wish to choose a different installation
-        directory, preferably one that is listed in your PYTHONPATH environment
-        variable.
-
-        For information on other options, you may wish to consult the
-        documentation at:
-
-          https://setuptools.pypa.io/en/latest/deprecated/easy_install.html
-
-        Please make the appropriate changes for your system and try again.
-        """
-    ).lstrip()
-
-    def cant_write_to_target(self) -> NoReturn:
-        msg = self.__cant_write_msg % (
-            sys.exc_info()[1],
-            self.install_dir,
-        )
-
-        if not os.path.exists(self.install_dir):
-            msg += '\n' + self.__not_exists_id
-        else:
-            msg += '\n' + self.__access_msg
-        raise DistutilsError(msg)
-
-    def check_pth_processing(self):  # noqa: C901
-        """Empirically verify whether .pth files are supported in inst. dir"""
-        instdir = self.install_dir
-        log.info("Checking .pth file support in %s", instdir)
-        pth_file = self.pseudo_tempname() + ".pth"
-        ok_file = pth_file + '.ok'
-        ok_exists = os.path.exists(ok_file)
-        tmpl = (
-            _one_liner(
-                """
-            import os
-            f = open({ok_file!r}, 'w', encoding="utf-8")
-            f.write('OK')
-            f.close()
-            """
-            )
-            + '\n'
-        )
-        try:
-            if ok_exists:
-                os.unlink(ok_file)
-            dirname = os.path.dirname(ok_file)
-            os.makedirs(dirname, exist_ok=True)
-            f = open(pth_file, 'w', encoding=py312.PTH_ENCODING)
-            # ^-- Python<3.13 require encoding="locale" instead of "utf-8",
-            #     see python/cpython#77102.
-        except OSError:
-            self.cant_write_to_target()
-        else:
-            try:
-                f.write(tmpl.format(**locals()))
-                f.close()
-                f = None
-                executable = sys.executable
-                if os.name == 'nt':
-                    dirname, basename = os.path.split(executable)
-                    alt = os.path.join(dirname, 'pythonw.exe')
-                    use_alt = basename.lower() == 'python.exe' and os.path.exists(alt)
-                    if use_alt:
-                        # use pythonw.exe to avoid opening a console window
-                        executable = alt
-
-                from distutils.spawn import spawn
-
-                spawn([executable, '-E', '-c', 'pass'], 0)
-
-                if os.path.exists(ok_file):
-                    log.info("TEST PASSED: %s appears to support .pth files", instdir)
-                    return True
-            finally:
-                if f:
-                    f.close()
-                if os.path.exists(ok_file):
-                    os.unlink(ok_file)
-                if os.path.exists(pth_file):
-                    os.unlink(pth_file)
-        if not self.multi_version:
-            log.warn("TEST FAILED: %s does NOT support .pth files", instdir)
-        return False
-
-    def install_egg_scripts(self, dist) -> None:
-        """Write all the scripts for `dist`, unless scripts are excluded"""
-        if not self.exclude_scripts and dist.metadata_isdir('scripts'):
-            for script_name in dist.metadata_listdir('scripts'):
-                if dist.metadata_isdir('scripts/' + script_name):
-                    # The "script" is a directory, likely a Python 3
-                    # __pycache__ directory, so skip it.
-                    continue
-                self.install_script(
-                    dist, script_name, dist.get_metadata('scripts/' + script_name)
-                )
-        self.install_wrapper_scripts(dist)
-
-    def add_output(self, path) -> None:
-        if os.path.isdir(path):
-            for base, dirs, files in os.walk(path):
-                for filename in files:
-                    self.outputs.append(os.path.join(base, filename))
-        else:
-            self.outputs.append(path)
-
-    def not_editable(self, spec) -> None:
-        if self.editable:
-            raise DistutilsArgError(
-                f"Invalid argument {spec!r}: you can't use filenames or URLs "
-                "with --editable (except via the --find-links option)."
-            )
-
-    def check_editable(self, spec) -> None:
-        if not self.editable:
-            return
-
-        if os.path.exists(os.path.join(self.build_directory, spec.key)):
-            raise DistutilsArgError(
-                f"{spec.key!r} already exists in {self.build_directory}; can't do a checkout there"
-            )
-
-    @contextlib.contextmanager
-    def _tmpdir(self):
-        tmpdir = tempfile.mkdtemp(prefix="easy_install-")
-        try:
-            # cast to str as workaround for #709 and #710 and #712
-            yield str(tmpdir)
-        finally:
-            os.path.exists(tmpdir) and _rmtree(tmpdir)
-
-    def easy_install(self, spec, deps: bool = False) -> Distribution | None:
-        with self._tmpdir() as tmpdir:
-            if not isinstance(spec, Requirement):
-                if URL_SCHEME(spec):
-                    # It's a url, download it to tmpdir and process
-                    self.not_editable(spec)
-                    dl = self.package_index.download(spec, tmpdir)
-                    return self.install_item(None, dl, tmpdir, deps, True)
-
-                elif os.path.exists(spec):
-                    # Existing file or directory, just process it directly
-                    self.not_editable(spec)
-                    return self.install_item(None, spec, tmpdir, deps, True)
-                else:
-                    spec = parse_requirement_arg(spec)
-
-            self.check_editable(spec)
-            dist = self.package_index.fetch_distribution(
-                spec,
-                tmpdir,
-                self.upgrade,
-                self.editable,
-                not self.always_copy,
-                self.local_index,
-            )
-            if dist is None:
-                msg = f"Could not find suitable distribution for {spec!r}"
-                if self.always_copy:
-                    msg += " (--always-copy skips system and development eggs)"
-                raise DistutilsError(msg)
-            elif dist.precedence == DEVELOP_DIST:
-                # .egg-info dists don't need installing, just process deps
-                self.process_distribution(spec, dist, deps, "Using")
-                return dist
-            else:
-                return self.install_item(spec, dist.location, tmpdir, deps)
-
-    def install_item(
-        self, spec, download, tmpdir, deps, install_needed: bool = False
-    ) -> Distribution | None:
-        # Installation is also needed if file in tmpdir or is not an egg
-        install_needed = install_needed or bool(self.always_copy)
-        install_needed = install_needed or os.path.dirname(download) == tmpdir
-        install_needed = install_needed or not download.endswith('.egg')
-        install_needed = install_needed or (
-            self.always_copy_from is not None
-            and os.path.dirname(normalize_path(download))
-            == normalize_path(self.always_copy_from)
-        )
-
-        if spec and not install_needed:
-            # at this point, we know it's a local .egg, we just don't know if
-            # it's already installed.
-            for dist in self.local_index[spec.project_name]:
-                if dist.location == download:
-                    break
-            else:
-                install_needed = True  # it's not in the local index
-
-        log.info("Processing %s", os.path.basename(download))
-
-        if install_needed:
-            dists = self.install_eggs(spec, download, tmpdir)
-            for dist in dists:
-                self.process_distribution(spec, dist, deps)
-        else:
-            dists = [self.egg_distribution(download)]
-            self.process_distribution(spec, dists[0], deps, "Using")
-
-        if spec is not None:
-            for dist in dists:
-                if dist in spec:
-                    return dist
-        return None
-
-    def select_scheme(self, name):
-        try:
-            install._select_scheme(self, name)
-        except AttributeError:
-            # stdlib distutils
-            install.install.select_scheme(self, name.replace('posix', 'unix'))
-
-    # FIXME: 'easy_install.process_distribution' is too complex (12)
-    def process_distribution(  # noqa: C901
-        self,
-        requirement,
-        dist,
-        deps: bool = True,
-        *info,
-    ) -> None:
-        self.update_pth(dist)
-        self.package_index.add(dist)
-        if dist in self.local_index[dist.key]:
-            self.local_index.remove(dist)
-        self.local_index.add(dist)
-        self.install_egg_scripts(dist)
-        self.installed_projects[dist.key] = dist
-        log.info(self.installation_report(requirement, dist, *info))
-        if dist.has_metadata('dependency_links.txt') and not self.no_find_links:
-            self.package_index.add_find_links(
-                dist.get_metadata_lines('dependency_links.txt')
-            )
-        if not deps and not self.always_copy:
-            return
-        elif requirement is not None and dist.key != requirement.key:
-            log.warn("Skipping dependencies for %s", dist)
-            return  # XXX this is not the distribution we were looking for
-        elif requirement is None or dist not in requirement:
-            # if we wound up with a different version, resolve what we've got
-            distreq = dist.as_requirement()
-            requirement = Requirement(str(distreq))
-        log.info("Processing dependencies for %s", requirement)
-        try:
-            distros = WorkingSet([]).resolve(
-                [requirement], self.local_index, self.easy_install
-            )
-        except DistributionNotFound as e:
-            raise DistutilsError(str(e)) from e
-        except VersionConflict as e:
-            raise DistutilsError(e.report()) from e
-        if self.always_copy or self.always_copy_from:
-            # Force all the relevant distros to be copied or activated
-            for dist in distros:
-                if dist.key not in self.installed_projects:
-                    self.easy_install(dist.as_requirement())
-        log.info("Finished processing dependencies for %s", requirement)
-
-    def should_unzip(self, dist) -> bool:
-        if self.zip_ok is not None:
-            return not self.zip_ok
-        if dist.has_metadata('not-zip-safe'):
-            return True
-        if not dist.has_metadata('zip-safe'):
-            return True
-        return False
-
-    def maybe_move(self, spec, dist_filename, setup_base):
-        dst = os.path.join(self.build_directory, spec.key)
-        if os.path.exists(dst):
-            msg = "%r already exists in %s; build directory %s will not be kept"
-            log.warn(msg, spec.key, self.build_directory, setup_base)
-            return setup_base
-        if os.path.isdir(dist_filename):
-            setup_base = dist_filename
-        else:
-            if os.path.dirname(dist_filename) == setup_base:
-                os.unlink(dist_filename)  # get it out of the tmp dir
-            contents = os.listdir(setup_base)
-            if len(contents) == 1:
-                dist_filename = os.path.join(setup_base, contents[0])
-                if os.path.isdir(dist_filename):
-                    # if the only thing there is a directory, move it instead
-                    setup_base = dist_filename
-        ensure_directory(dst)
-        shutil.move(setup_base, dst)
-        return dst
-
-    def install_wrapper_scripts(self, dist) -> None:
-        if self.exclude_scripts:
-            return
-        for args in ScriptWriter.best().get_args(dist):
-            self.write_script(*args)
-
-    def install_script(self, dist, script_name, script_text, dev_path=None) -> None:
-        """Generate a legacy script wrapper and install it"""
-        spec = str(dist.as_requirement())
-        is_script = is_python_script(script_text, script_name)
-
-        if is_script:
-            body = self._load_template(dev_path) % locals()
-            script_text = ScriptWriter.get_header(script_text) + body
-        self.write_script(script_name, _to_bytes(script_text), 'b')
-
-    @staticmethod
-    def _load_template(dev_path):
-        """
-        There are a couple of template scripts in the package. This
-        function loads one of them and prepares it for use.
-        """
-        # See https://github.com/pypa/setuptools/issues/134 for info
-        # on script file naming and downstream issues with SVR4
-        name = 'script.tmpl'
-        if dev_path:
-            name = name.replace('.tmpl', ' (dev).tmpl')
-
-        raw_bytes = resource_string('setuptools', name)
-        return raw_bytes.decode('utf-8')
-
-    def write_script(self, script_name, contents, mode: str = "t", blockers=()) -> None:
-        """Write an executable file to the scripts directory"""
-        self.delete_blockers(  # clean up old .py/.pyw w/o a script
-            [os.path.join(self.script_dir, x) for x in blockers]
-        )
-        log.info("Installing %s script to %s", script_name, self.script_dir)
-        target = os.path.join(self.script_dir, script_name)
-        self.add_output(target)
-
-        if self.dry_run:
-            return
-
-        mask = current_umask()
-        ensure_directory(target)
-        if os.path.exists(target):
-            os.unlink(target)
-
-        encoding = None if "b" in mode else "utf-8"
-        with open(target, "w" + mode, encoding=encoding) as f:
-            f.write(contents)
-        chmod(target, 0o777 - mask)
-
-    def install_eggs(self, spec, dist_filename, tmpdir) -> list[Distribution]:
-        # .egg dirs or files are already built, so just return them
-        installer_map = {
-            '.egg': self.install_egg,
-            '.exe': self.install_exe,
-            '.whl': self.install_wheel,
-        }
-        try:
-            install_dist = installer_map[dist_filename.lower()[-4:]]
-        except KeyError:
-            pass
-        else:
-            return [install_dist(dist_filename, tmpdir)]
-
-        # Anything else, try to extract and build
-        setup_base = tmpdir
-        if os.path.isfile(dist_filename) and not dist_filename.endswith('.py'):
-            unpack_archive(dist_filename, tmpdir, self.unpack_progress)
-        elif os.path.isdir(dist_filename):
-            setup_base = os.path.abspath(dist_filename)
-
-        if (
-            setup_base.startswith(tmpdir)  # something we downloaded
-            and self.build_directory
-            and spec is not None
-        ):
-            setup_base = self.maybe_move(spec, dist_filename, setup_base)
-
-        # Find the setup.py file
-        setup_script = os.path.join(setup_base, 'setup.py')
-
-        if not os.path.exists(setup_script):
-            setups = glob(os.path.join(setup_base, '*', 'setup.py'))
-            if not setups:
-                raise DistutilsError(
-                    f"Couldn't find a setup script in {os.path.abspath(dist_filename)}"
-                )
-            if len(setups) > 1:
-                raise DistutilsError(
-                    f"Multiple setup scripts in {os.path.abspath(dist_filename)}"
-                )
-            setup_script = setups[0]
-
-        # Now run it, and return the result
-        if self.editable:
-            log.info(self.report_editable(spec, setup_script))
-            return []
-        else:
-            return self.build_and_install(setup_script, setup_base)
-
-    def egg_distribution(self, egg_path):
-        if os.path.isdir(egg_path):
-            metadata = PathMetadata(egg_path, os.path.join(egg_path, 'EGG-INFO'))
-        else:
-            metadata = EggMetadata(zipimport.zipimporter(egg_path))
-        return Distribution.from_filename(egg_path, metadata=metadata)
-
-    # FIXME: 'easy_install.install_egg' is too complex (11)
-    def install_egg(self, egg_path, tmpdir):
-        destination = os.path.join(
-            self.install_dir,
-            os.path.basename(egg_path),
-        )
-        destination = os.path.abspath(destination)
-        if not self.dry_run:
-            ensure_directory(destination)
-
-        dist = self.egg_distribution(egg_path)
-        if not (
-            os.path.exists(destination) and os.path.samefile(egg_path, destination)
-        ):
-            if os.path.isdir(destination) and not os.path.islink(destination):
-                dir_util.remove_tree(destination, dry_run=self.dry_run)
-            elif os.path.exists(destination):
-                self.execute(
-                    os.unlink,
-                    (destination,),
-                    "Removing " + destination,
-                )
-            try:
-                new_dist_is_zipped = False
-                if os.path.isdir(egg_path):
-                    if egg_path.startswith(tmpdir):
-                        f, m = shutil.move, "Moving"
-                    else:
-                        f, m = shutil.copytree, "Copying"
-                elif self.should_unzip(dist):
-                    self.mkpath(destination)
-                    f, m = self.unpack_and_compile, "Extracting"
-                else:
-                    new_dist_is_zipped = True
-                    if egg_path.startswith(tmpdir):
-                        f, m = shutil.move, "Moving"
-                    else:
-                        f, m = shutil.copy2, "Copying"
-                self.execute(
-                    f,
-                    (egg_path, destination),
-                    (m + " %s to %s")
-                    % (os.path.basename(egg_path), os.path.dirname(destination)),
-                )
-                update_dist_caches(
-                    destination,
-                    fix_zipimporter_caches=new_dist_is_zipped,
-                )
-            except Exception:
-                update_dist_caches(destination, fix_zipimporter_caches=False)
-                raise
-
-        self.add_output(destination)
-        return self.egg_distribution(destination)
-
-    def install_exe(self, dist_filename, tmpdir):
-        # See if it's valid, get data
-        cfg = extract_wininst_cfg(dist_filename)
-        if cfg is None:
-            raise DistutilsError(
-                f"{dist_filename} is not a valid distutils Windows .exe"
-            )
-        # Create a dummy distribution object until we build the real distro
-        dist = Distribution(
-            None,
-            project_name=cfg.get('metadata', 'name'),
-            version=cfg.get('metadata', 'version'),
-            platform=get_platform(),
-        )
-
-        # Convert the .exe to an unpacked egg
-        egg_path = os.path.join(tmpdir, dist.egg_name() + '.egg')
-        dist.location = egg_path
-        egg_tmp = egg_path + '.tmp'
-        _egg_info = os.path.join(egg_tmp, 'EGG-INFO')
-        pkg_inf = os.path.join(_egg_info, 'PKG-INFO')
-        ensure_directory(pkg_inf)  # make sure EGG-INFO dir exists
-        dist._provider = PathMetadata(egg_tmp, _egg_info)  # XXX
-        self.exe_to_egg(dist_filename, egg_tmp)
-
-        # Write EGG-INFO/PKG-INFO
-        if not os.path.exists(pkg_inf):
-            with open(pkg_inf, 'w', encoding="utf-8") as f:
-                f.write('Metadata-Version: 1.0\n')
-                for k, v in cfg.items('metadata'):
-                    if k != 'target_version':
-                        k = k.replace('_', '-').title()
-                        f.write(f'{k}: {v}\n')
-        script_dir = os.path.join(_egg_info, 'scripts')
-        # delete entry-point scripts to avoid duping
-        self.delete_blockers([
-            os.path.join(script_dir, args[0]) for args in ScriptWriter.get_args(dist)
-        ])
-        # Build .egg file from tmpdir
-        bdist_egg.make_zipfile(
-            egg_path,
-            egg_tmp,
-            verbose=self.verbose,
-            dry_run=self.dry_run,
-        )
-        # install the .egg
-        return self.install_egg(egg_path, tmpdir)
-
-    # FIXME: 'easy_install.exe_to_egg' is too complex (12)
-    def exe_to_egg(self, dist_filename, egg_tmp) -> None:  # noqa: C901
-        """Extract a bdist_wininst to the directories an egg would use"""
-        # Check for .pth file and set up prefix translations
-        prefixes = get_exe_prefixes(dist_filename)
-        to_compile = []
-        native_libs = []
-        top_level = set()
-
-        def process(src, dst):
-            s = src.lower()
-            for old, new in prefixes:
-                if s.startswith(old):
-                    src = new + src[len(old) :]
-                    parts = src.split('/')
-                    dst = os.path.join(egg_tmp, *parts)
-                    dl = dst.lower()
-                    if dl.endswith('.pyd') or dl.endswith('.dll'):
-                        parts[-1] = bdist_egg.strip_module(parts[-1])
-                        top_level.add([os.path.splitext(parts[0])[0]])
-                        native_libs.append(src)
-                    elif dl.endswith('.py') and old != 'SCRIPTS/':
-                        top_level.add([os.path.splitext(parts[0])[0]])
-                        to_compile.append(dst)
-                    return dst
-            if not src.endswith('.pth'):
-                log.warn("WARNING: can't process %s", src)
-            return None
-
-        # extract, tracking .pyd/.dll->native_libs and .py -> to_compile
-        unpack_archive(dist_filename, egg_tmp, process)
-        stubs = []
-        for res in native_libs:
-            if res.lower().endswith('.pyd'):  # create stubs for .pyd's
-                parts = res.split('/')
-                resource = parts[-1]
-                parts[-1] = bdist_egg.strip_module(parts[-1]) + '.py'
-                pyfile = os.path.join(egg_tmp, *parts)
-                to_compile.append(pyfile)
-                stubs.append(pyfile)
-                bdist_egg.write_stub(resource, pyfile)
-        self.byte_compile(to_compile)  # compile .py's
-        bdist_egg.write_safety_flag(
-            os.path.join(egg_tmp, 'EGG-INFO'), bdist_egg.analyze_egg(egg_tmp, stubs)
-        )  # write zip-safety flag
-
-        for name in 'top_level', 'native_libs':
-            if locals()[name]:
-                txt = os.path.join(egg_tmp, 'EGG-INFO', name + '.txt')
-                if not os.path.exists(txt):
-                    with open(txt, 'w', encoding="utf-8") as f:
-                        f.write('\n'.join(locals()[name]) + '\n')
-
-    def install_wheel(self, wheel_path, tmpdir):
-        wheel = Wheel(wheel_path)
-        assert wheel.is_compatible()
-        destination = os.path.join(self.install_dir, wheel.egg_name())
-        destination = os.path.abspath(destination)
-        if not self.dry_run:
-            ensure_directory(destination)
-        if os.path.isdir(destination) and not os.path.islink(destination):
-            dir_util.remove_tree(destination, dry_run=self.dry_run)
-        elif os.path.exists(destination):
-            self.execute(
-                os.unlink,
-                (destination,),
-                "Removing " + destination,
-            )
-        try:
-            self.execute(
-                wheel.install_as_egg,
-                (destination,),
-                (
-                    f"Installing {os.path.basename(wheel_path)} to {os.path.dirname(destination)}"
-                ),
-            )
-        finally:
-            update_dist_caches(destination, fix_zipimporter_caches=False)
-        self.add_output(destination)
-        return self.egg_distribution(destination)
-
-    __mv_warning = textwrap.dedent(
-        """
-        Because this distribution was installed --multi-version, before you can
-        import modules from this package in an application, you will need to
-        'import pkg_resources' and then use a 'require()' call similar to one of
-        these examples, in order to select the desired version:
-
-            pkg_resources.require("%(name)s")  # latest installed version
-            pkg_resources.require("%(name)s==%(version)s")  # this exact version
-            pkg_resources.require("%(name)s>=%(version)s")  # this version or higher
-        """
-    ).lstrip()
-
-    __id_warning = textwrap.dedent(
-        """
-        Note also that the installation directory must be on sys.path at runtime for
-        this to work.  (e.g. by being the application's script directory, by being on
-        PYTHONPATH, or by being added to sys.path by your code.)
-        """
-    )
-
-    def installation_report(self, req, dist, what: str = "Installed") -> str:
-        """Helpful installation message for display to package users"""
-        msg = "\n%(what)s %(eggloc)s%(extras)s"
-        if self.multi_version and not self.no_report:
-            msg += '\n' + self.__mv_warning
-            if self.install_dir not in map(normalize_path, sys.path):
-                msg += '\n' + self.__id_warning
-
-        eggloc = dist.location
-        name = dist.project_name
-        version = dist.version
-        extras = ''  # TODO: self.report_extras(req, dist)
-        return msg % locals()
-
-    __editable_msg = textwrap.dedent(
-        """
-        Extracted editable version of %(spec)s to %(dirname)s
-
-        If it uses setuptools in its setup script, you can activate it in
-        "development" mode by going to that directory and running::
-
-            %(python)s setup.py develop
-
-        See the setuptools documentation for the "develop" command for more info.
-        """
-    ).lstrip()
-
-    def report_editable(self, spec, setup_script):
-        dirname = os.path.dirname(setup_script)
-        python = sys.executable
-        return '\n' + self.__editable_msg % locals()
-
-    def run_setup(self, setup_script, setup_base, args) -> None:
-        sys.modules.setdefault('distutils.command.bdist_egg', bdist_egg)
-        sys.modules.setdefault('distutils.command.egg_info', egg_info)
-
-        args = list(args)
-        if self.verbose > 2:
-            v = 'v' * (self.verbose - 1)
-            args.insert(0, '-' + v)
-        elif self.verbose < 2:
-            args.insert(0, '-q')
-        if self.dry_run:
-            args.insert(0, '-n')
-        log.info("Running %s %s", setup_script[len(setup_base) + 1 :], ' '.join(args))
-        try:
-            run_setup(setup_script, args)
-        except SystemExit as v:
-            raise DistutilsError(f"Setup script exited with {v.args[0]}") from v
-
-    def build_and_install(self, setup_script, setup_base):
-        args = ['bdist_egg', '--dist-dir']
-
-        dist_dir = tempfile.mkdtemp(
-            prefix='egg-dist-tmp-', dir=os.path.dirname(setup_script)
-        )
-        try:
-            self._set_fetcher_options(os.path.dirname(setup_script))
-            args.append(dist_dir)
-
-            self.run_setup(setup_script, setup_base, args)
-            all_eggs = Environment([dist_dir])
-            eggs = [
-                self.install_egg(dist.location, setup_base)
-                for key in all_eggs
-                for dist in all_eggs[key]
-            ]
-            if not eggs and not self.dry_run:
-                log.warn("No eggs found in %s (setup script problem?)", dist_dir)
-            return eggs
-        finally:
-            _rmtree(dist_dir)
-            log.set_verbosity(self.verbose)  # restore our log verbosity
-
-    def _set_fetcher_options(self, base):
-        """
-        When easy_install is about to run bdist_egg on a source dist, that
-        source dist might have 'setup_requires' directives, requiring
-        additional fetching. Ensure the fetcher options given to easy_install
-        are available to that command as well.
-        """
-        # find the fetch options from easy_install and write them out
-        # to the setup.cfg file.
-        ei_opts = self.distribution.get_option_dict('easy_install').copy()
-        fetch_directives = (
-            'find_links',
-            'site_dirs',
-            'index_url',
-            'optimize',
-            'allow_hosts',
-        )
-        fetch_options = {}
-        for key, val in ei_opts.items():
-            if key not in fetch_directives:
-                continue
-            fetch_options[key] = val[1]
-        # create a settings dictionary suitable for `edit_config`
-        settings = dict(easy_install=fetch_options)
-        cfg_filename = os.path.join(base, 'setup.cfg')
-        setopt.edit_config(cfg_filename, settings)
-
-    def update_pth(self, dist) -> None:  # noqa: C901  # is too complex (11)  # FIXME
-        if self.pth_file is None:
-            return
-
-        for d in self.pth_file[dist.key]:  # drop old entries
-            if not self.multi_version and d.location == dist.location:
-                continue
-
-            log.info("Removing %s from easy-install.pth file", d)
-            self.pth_file.remove(d)
-            if d.location in self.shadow_path:
-                self.shadow_path.remove(d.location)
-
-        if not self.multi_version:
-            if dist.location in self.pth_file.paths:
-                log.info(
-                    "%s is already the active version in easy-install.pth",
-                    dist,
-                )
-            else:
-                log.info("Adding %s to easy-install.pth file", dist)
-                self.pth_file.add(dist)  # add new entry
-                if dist.location not in self.shadow_path:
-                    self.shadow_path.append(dist.location)
-
-        if self.dry_run:
-            return
-
-        self.pth_file.save()
-
-        if dist.key != 'setuptools':
-            return
-
-        # Ensure that setuptools itself never becomes unavailable!
-        # XXX should this check for latest version?
-        filename = os.path.join(self.install_dir, 'setuptools.pth')
-        if os.path.islink(filename):
-            os.unlink(filename)
-
-        with open(filename, 'wt', encoding=py312.PTH_ENCODING) as f:
-            # ^-- Python<3.13 require encoding="locale" instead of "utf-8",
-            #     see python/cpython#77102.
-            f.write(self.pth_file.make_relative(dist.location) + '\n')
-
-    def unpack_progress(self, src, dst):
-        # Progress filter for unpacking
-        log.debug("Unpacking %s to %s", src, dst)
-        return dst  # only unpack-and-compile skips files for dry run
-
-    def unpack_and_compile(self, egg_path, destination) -> None:
-        to_compile = []
-        to_chmod = []
-
-        def pf(src, dst):
-            if dst.endswith('.py') and not src.startswith('EGG-INFO/'):
-                to_compile.append(dst)
-            elif dst.endswith('.dll') or dst.endswith('.so'):
-                to_chmod.append(dst)
-            self.unpack_progress(src, dst)
-            return not self.dry_run and dst or None
-
-        unpack_archive(egg_path, destination, pf)
-        self.byte_compile(to_compile)
-        if not self.dry_run:
-            for f in to_chmod:
-                mode = ((os.stat(f)[stat.ST_MODE]) | 0o555) & 0o7755
-                chmod(f, mode)
-
-    def byte_compile(self, to_compile) -> None:
-        if sys.dont_write_bytecode:
-            return
-
-        from distutils.util import byte_compile
-
-        try:
-            # try to make the byte compile messages quieter
-            log.set_verbosity(self.verbose - 1)
-
-            byte_compile(to_compile, optimize=0, force=True, dry_run=self.dry_run)
-            if self.optimize:
-                byte_compile(
-                    to_compile,
-                    optimize=self.optimize,
-                    force=True,
-                    dry_run=self.dry_run,
-                )
-        finally:
-            log.set_verbosity(self.verbose)  # restore original verbosity
-
-    __no_default_msg = textwrap.dedent(
-        """
-        bad install directory or PYTHONPATH
-
-        You are attempting to install a package to a directory that is not
-        on PYTHONPATH and which Python does not read ".pth" files from.  The
-        installation directory you specified (via --install-dir, --prefix, or
-        the distutils default setting) was:
-
-            %s
-
-        and your PYTHONPATH environment variable currently contains:
-
-            %r
-
-        Here are some of your options for correcting the problem:
-
-        * You can choose a different installation directory, i.e., one that is
-          on PYTHONPATH or supports .pth files
-
-        * You can add the installation directory to the PYTHONPATH environment
-          variable.  (It must then also be on PYTHONPATH whenever you run
-          Python and want to use the package(s) you are installing.)
-
-        * You can set up the installation directory to support ".pth" files by
-          using one of the approaches described here:
-
-          https://setuptools.pypa.io/en/latest/deprecated/easy_install.html#custom-installation-locations
-
-
-        Please make the appropriate changes for your system and try again.
-        """
-    ).strip()
-
-    def create_home_path(self) -> None:
-        """Create directories under ~."""
-        if not self.user:
-            return
-        home = convert_path(os.path.expanduser("~"))
-        for path in only_strs(self.config_vars.values()):
-            if path.startswith(home) and not os.path.isdir(path):
-                self.debug_print(f"os.makedirs('{path}', 0o700)")
-                os.makedirs(path, 0o700)
-
-    INSTALL_SCHEMES = dict(
-        posix=dict(
-            install_dir='$base/lib/python$py_version_short/site-packages',
-            script_dir='$base/bin',
-        ),
-    )
-
-    DEFAULT_SCHEME = dict(
-        install_dir='$base/Lib/site-packages',
-        script_dir='$base/Scripts',
-    )
-
-    def _expand(self, *attrs):
-        config_vars = self.get_finalized_command('install').config_vars
-
-        if self.prefix:
-            # Set default install_dir/scripts from --prefix
-            config_vars = dict(config_vars)
-            config_vars['base'] = self.prefix
-            scheme = self.INSTALL_SCHEMES.get(os.name, self.DEFAULT_SCHEME)
-            for attr, val in scheme.items():
-                if getattr(self, attr, None) is None:
-                    setattr(self, attr, val)
-
-        from distutils.util import subst_vars
-
-        for attr in attrs:
-            val = getattr(self, attr)
-            if val is not None:
-                val = subst_vars(val, config_vars)
-                if os.name == 'posix':
-                    val = os.path.expanduser(val)
-                setattr(self, attr, val)
-
-
-def _pythonpath():
-    items = os.environ.get('PYTHONPATH', '').split(os.pathsep)
-    return filter(None, items)
-
-
-def get_site_dirs():
-    """
-    Return a list of 'site' dirs
-    """
-
-    sitedirs = []
-
-    # start with PYTHONPATH
-    sitedirs.extend(_pythonpath())
-
-    prefixes = [sys.prefix]
-    if sys.exec_prefix != sys.prefix:
-        prefixes.append(sys.exec_prefix)
-    for prefix in prefixes:
-        if not prefix:
-            continue
-
-        if sys.platform in ('os2emx', 'riscos'):
-            sitedirs.append(os.path.join(prefix, "Lib", "site-packages"))
-        elif os.sep == '/':
-            sitedirs.extend([
-                os.path.join(
-                    prefix,
-                    "lib",
-                    f"python{sys.version_info.major}.{sys.version_info.minor}",
-                    "site-packages",
-                ),
-                os.path.join(prefix, "lib", "site-python"),
-            ])
-        else:
-            sitedirs.extend([
-                prefix,
-                os.path.join(prefix, "lib", "site-packages"),
-            ])
-        if sys.platform != 'darwin':
-            continue
-
-        # for framework builds *only* we add the standard Apple
-        # locations. Currently only per-user, but /Library and
-        # /Network/Library could be added too
-        if 'Python.framework' not in prefix:
-            continue
-
-        home = os.environ.get('HOME')
-        if not home:
-            continue
-
-        home_sp = os.path.join(
-            home,
-            'Library',
-            'Python',
-            f'{sys.version_info.major}.{sys.version_info.minor}',
-            'site-packages',
-        )
-        sitedirs.append(home_sp)
-    lib_paths = get_path('purelib'), get_path('platlib')
-
-    sitedirs.extend(s for s in lib_paths if s not in sitedirs)
-
-    if site.ENABLE_USER_SITE:
-        sitedirs.append(site.USER_SITE)
-
-    with contextlib.suppress(AttributeError):
-        sitedirs.extend(site.getsitepackages())
-
-    return list(map(normalize_path, sitedirs))
-
-
-def expand_paths(inputs):  # noqa: C901  # is too complex (11)  # FIXME
-    """Yield sys.path directories that might contain "old-style" packages"""
-
-    seen = set()
-
-    for dirname in inputs:
-        dirname = normalize_path(dirname)
-        if dirname in seen:
-            continue
-
-        seen.add(dirname)
-        if not os.path.isdir(dirname):
-            continue
-
-        files = os.listdir(dirname)
-        yield dirname, files
-
-        for name in files:
-            if not name.endswith('.pth'):
-                # We only care about the .pth files
-                continue
-            if name in ('easy-install.pth', 'setuptools.pth'):
-                # Ignore .pth files that we control
-                continue
-
-            # Read the .pth file
-            content = _read_pth(os.path.join(dirname, name))
-            lines = list(yield_lines(content))
-
-            # Yield existing non-dupe, non-import directory lines from it
-            for line in lines:
-                if line.startswith("import"):
-                    continue
-
-                line = normalize_path(line.rstrip())
-                if line in seen:
-                    continue
-
-                seen.add(line)
-                if not os.path.isdir(line):
-                    continue
-
-                yield line, os.listdir(line)
-
-
-def extract_wininst_cfg(dist_filename):
-    """Extract configuration data from a bdist_wininst .exe
-
-    Returns a configparser.RawConfigParser, or None
-    """
-    f = open(dist_filename, 'rb')
-    try:
-        endrec = zipfile._EndRecData(f)
-        if endrec is None:
-            return None
-
-        prepended = (endrec[9] - endrec[5]) - endrec[6]
-        if prepended < 12:  # no wininst data here
-            return None
-        f.seek(prepended - 12)
-
-        tag, cfglen, _bmlen = struct.unpack("egg path translations for a given .exe file"""
-
-    prefixes = [
-        ('PURELIB/', ''),
-        ('PLATLIB/pywin32_system32', ''),
-        ('PLATLIB/', ''),
-        ('SCRIPTS/', 'EGG-INFO/scripts/'),
-        ('DATA/lib/site-packages', ''),
-    ]
-    z = zipfile.ZipFile(exe_filename)
-    try:
-        for info in z.infolist():
-            name = info.filename
-            parts = name.split('/')
-            if len(parts) == 3 and parts[2] == 'PKG-INFO':
-                if parts[1].endswith('.egg-info'):
-                    prefixes.insert(0, ('/'.join(parts[:2]), 'EGG-INFO/'))
-                    break
-            if len(parts) != 2 or not name.endswith('.pth'):
-                continue
-            if name.endswith('-nspkg.pth'):
-                continue
-            if parts[0].upper() in ('PURELIB', 'PLATLIB'):
-                contents = z.read(name).decode()
-                for pth in yield_lines(contents):
-                    pth = pth.strip().replace('\\', '/')
-                    if not pth.startswith('import'):
-                        prefixes.append(((f'{parts[0]}/{pth}/'), ''))
-    finally:
-        z.close()
-    prefixes = [(x.lower(), y) for x, y in prefixes]
-    prefixes.sort()
-    prefixes.reverse()
-    return prefixes
-
-
-class PthDistributions(Environment):
-    """A .pth file with Distribution paths in it"""
-
-    def __init__(self, filename, sitedirs=()) -> None:
-        self.filename = filename
-        self.sitedirs = list(map(normalize_path, sitedirs))
-        self.basedir = normalize_path(os.path.dirname(self.filename))
-        self.paths, self.dirty = self._load()
-        # keep a copy if someone manually updates the paths attribute on the instance
-        self._init_paths = self.paths[:]
-        super().__init__([], None, None)
-        for path in yield_lines(self.paths):
-            list(map(self.add, find_distributions(path, True)))
-
-    def _load_raw(self):
-        paths = []
-        dirty = saw_import = False
-        seen = set(self.sitedirs)
-        content = _read_pth(self.filename)
-        for line in content.splitlines():
-            path = line.rstrip()
-            # still keep imports and empty/commented lines for formatting
-            paths.append(path)
-            if line.startswith(('import ', 'from ')):
-                saw_import = True
-                continue
-            stripped_path = path.strip()
-            if not stripped_path or stripped_path.startswith('#'):
-                continue
-            # skip non-existent paths, in case somebody deleted a package
-            # manually, and duplicate paths as well
-            normalized_path = normalize_path(os.path.join(self.basedir, path))
-            if normalized_path in seen or not os.path.exists(normalized_path):
-                log.debug("cleaned up dirty or duplicated %r", path)
-                dirty = True
-                paths.pop()
-                continue
-            seen.add(normalized_path)
-        # remove any trailing empty/blank line
-        while paths and not paths[-1].strip():
-            paths.pop()
-            dirty = True
-        return paths, dirty or (paths and saw_import)
-
-    def _load(self):
-        if os.path.isfile(self.filename):
-            return self._load_raw()
-        return [], False
-
-    def save(self) -> None:
-        """Write changed .pth file back to disk"""
-        # first reload the file
-        last_paths, last_dirty = self._load()
-        # and check that there are no difference with what we have.
-        # there can be difference if someone else has written to the file
-        # since we first loaded it.
-        # we don't want to lose the eventual new paths added since then.
-        for path in last_paths[:]:
-            if path not in self.paths:
-                self.paths.append(path)
-                log.info("detected new path %r", path)
-                last_dirty = True
-            else:
-                last_paths.remove(path)
-        # also, re-check that all paths are still valid before saving them
-        for path in self.paths[:]:
-            if path not in last_paths and not path.startswith((
-                'import ',
-                'from ',
-                '#',
-            )):
-                absolute_path = os.path.join(self.basedir, path)
-                if not os.path.exists(absolute_path):
-                    self.paths.remove(path)
-                    log.info("removing now non-existent path %r", path)
-                    last_dirty = True
-
-        self.dirty |= last_dirty or self.paths != self._init_paths
-        if not self.dirty:
-            return
-
-        rel_paths = list(map(self.make_relative, self.paths))
-        if rel_paths:
-            log.debug("Saving %s", self.filename)
-            lines = self._wrap_lines(rel_paths)
-            data = '\n'.join(lines) + '\n'
-            if os.path.islink(self.filename):
-                os.unlink(self.filename)
-            with open(self.filename, 'wt', encoding=py312.PTH_ENCODING) as f:
-                # ^-- Python<3.13 require encoding="locale" instead of "utf-8",
-                #     see python/cpython#77102.
-                f.write(data)
-        elif os.path.exists(self.filename):
-            log.debug("Deleting empty %s", self.filename)
-            os.unlink(self.filename)
-
-        self.dirty = False
-        self._init_paths[:] = self.paths[:]
-
-    @staticmethod
-    def _wrap_lines(lines):
-        return lines
-
-    def add(self, dist) -> None:
-        """Add `dist` to the distribution map"""
-        new_path = dist.location not in self.paths and (
-            dist.location not in self.sitedirs
-            or
-            # account for '.' being in PYTHONPATH
-            dist.location == os.getcwd()
-        )
-        if new_path:
-            self.paths.append(dist.location)
-            self.dirty = True
-        super().add(dist)
-
-    def remove(self, dist) -> None:
-        """Remove `dist` from the distribution map"""
-        while dist.location in self.paths:
-            self.paths.remove(dist.location)
-            self.dirty = True
-        super().remove(dist)
-
-    def make_relative(self, path):
-        npath, last = os.path.split(normalize_path(path))
-        baselen = len(self.basedir)
-        parts = [last]
-        sep = os.altsep == '/' and '/' or os.sep
-        while len(npath) >= baselen:
-            if npath == self.basedir:
-                parts.append(os.curdir)
-                parts.reverse()
-                return sep.join(parts)
-            npath, last = os.path.split(npath)
-            parts.append(last)
-        else:
-            return path
-
-
-class RewritePthDistributions(PthDistributions):
-    @classmethod
-    def _wrap_lines(cls, lines):
-        yield cls.prelude
-        yield from lines
-        yield cls.postlude
-
-    prelude = _one_liner(
-        """
-        import sys
-        sys.__plen = len(sys.path)
-        """
-    )
-    postlude = _one_liner(
-        """
-        import sys
-        new = sys.path[sys.__plen:]
-        del sys.path[sys.__plen:]
-        p = getattr(sys, '__egginsert', 0)
-        sys.path[p:p] = new
-        sys.__egginsert = p + len(new)
-        """
-    )
-
-
-if os.environ.get('SETUPTOOLS_SYS_PATH_TECHNIQUE', 'raw') == 'rewrite':
-    PthDistributions = RewritePthDistributions  # type: ignore[misc]  # Overwriting type
-
-
-def _first_line_re():
-    """
-    Return a regular expression based on first_line_re suitable for matching
-    strings.
-    """
-    if isinstance(first_line_re.pattern, str):
-        return first_line_re
-
-    # first_line_re in Python >=3.1.4 and >=3.2.1 is a bytes pattern.
-    return re.compile(first_line_re.pattern.decode())
-
-
-def update_dist_caches(dist_path, fix_zipimporter_caches):
-    """
-    Fix any globally cached `dist_path` related data
-
-    `dist_path` should be a path of a newly installed egg distribution (zipped
-    or unzipped).
-
-    sys.path_importer_cache contains finder objects that have been cached when
-    importing data from the original distribution. Any such finders need to be
-    cleared since the replacement distribution might be packaged differently,
-    e.g. a zipped egg distribution might get replaced with an unzipped egg
-    folder or vice versa. Having the old finders cached may then cause Python
-    to attempt loading modules from the replacement distribution using an
-    incorrect loader.
-
-    zipimport.zipimporter objects are Python loaders charged with importing
-    data packaged inside zip archives. If stale loaders referencing the
-    original distribution, are left behind, they can fail to load modules from
-    the replacement distribution. E.g. if an old zipimport.zipimporter instance
-    is used to load data from a new zipped egg archive, it may cause the
-    operation to attempt to locate the requested data in the wrong location -
-    one indicated by the original distribution's zip archive directory
-    information. Such an operation may then fail outright, e.g. report having
-    read a 'bad local file header', or even worse, it may fail silently &
-    return invalid data.
-
-    zipimport._zip_directory_cache contains cached zip archive directory
-    information for all existing zipimport.zipimporter instances and all such
-    instances connected to the same archive share the same cached directory
-    information.
-
-    If asked, and the underlying Python implementation allows it, we can fix
-    all existing zipimport.zipimporter instances instead of having to track
-    them down and remove them one by one, by updating their shared cached zip
-    archive directory information. This, of course, assumes that the
-    replacement distribution is packaged as a zipped egg.
-
-    If not asked to fix existing zipimport.zipimporter instances, we still do
-    our best to clear any remaining zipimport.zipimporter related cached data
-    that might somehow later get used when attempting to load data from the new
-    distribution and thus cause such load operations to fail. Note that when
-    tracking down such remaining stale data, we can not catch every conceivable
-    usage from here, and we clear only those that we know of and have found to
-    cause problems if left alive. Any remaining caches should be updated by
-    whomever is in charge of maintaining them, i.e. they should be ready to
-    handle us replacing their zip archives with new distributions at runtime.
-
-    """
-    # There are several other known sources of stale zipimport.zipimporter
-    # instances that we do not clear here, but might if ever given a reason to
-    # do so:
-    # * Global setuptools pkg_resources.working_set (a.k.a. 'master working
-    # set') may contain distributions which may in turn contain their
-    #   zipimport.zipimporter loaders.
-    # * Several zipimport.zipimporter loaders held by local variables further
-    #   up the function call stack when running the setuptools installation.
-    # * Already loaded modules may have their __loader__ attribute set to the
-    #   exact loader instance used when importing them. Python 3.4 docs state
-    #   that this information is intended mostly for introspection and so is
-    #   not expected to cause us problems.
-    normalized_path = normalize_path(dist_path)
-    _uncache(normalized_path, sys.path_importer_cache)
-    if fix_zipimporter_caches:
-        _replace_zip_directory_cache_data(normalized_path)
-    else:
-        # Here, even though we do not want to fix existing and now stale
-        # zipimporter cache information, we still want to remove it. Related to
-        # Python's zip archive directory information cache, we clear each of
-        # its stale entries in two phases:
-        #   1. Clear the entry so attempting to access zip archive information
-        #      via any existing stale zipimport.zipimporter instances fails.
-        #   2. Remove the entry from the cache so any newly constructed
-        #      zipimport.zipimporter instances do not end up using old stale
-        #      zip archive directory information.
-        # This whole stale data removal step does not seem strictly necessary,
-        # but has been left in because it was done before we started replacing
-        # the zip archive directory information cache content if possible, and
-        # there are no relevant unit tests that we can depend on to tell us if
-        # this is really needed.
-        _remove_and_clear_zip_directory_cache_data(normalized_path)
-
-
-def _collect_zipimporter_cache_entries(normalized_path, cache):
-    """
-    Return zipimporter cache entry keys related to a given normalized path.
-
-    Alternative path spellings (e.g. those using different character case or
-    those using alternative path separators) related to the same path are
-    included. Any sub-path entries are included as well, i.e. those
-    corresponding to zip archives embedded in other zip archives.
-
-    """
-    result = []
-    prefix_len = len(normalized_path)
-    for p in cache:
-        np = normalize_path(p)
-        if np.startswith(normalized_path) and np[prefix_len : prefix_len + 1] in (
-            os.sep,
-            '',
-        ):
-            result.append(p)
-    return result
-
-
-def _update_zipimporter_cache(normalized_path, cache, updater=None):
-    """
-    Update zipimporter cache data for a given normalized path.
-
-    Any sub-path entries are processed as well, i.e. those corresponding to zip
-    archives embedded in other zip archives.
-
-    Given updater is a callable taking a cache entry key and the original entry
-    (after already removing the entry from the cache), and expected to update
-    the entry and possibly return a new one to be inserted in its place.
-    Returning None indicates that the entry should not be replaced with a new
-    one. If no updater is given, the cache entries are simply removed without
-    any additional processing, the same as if the updater simply returned None.
-
-    """
-    for p in _collect_zipimporter_cache_entries(normalized_path, cache):
-        # N.B. pypy's custom zipimport._zip_directory_cache implementation does
-        # not support the complete dict interface:
-        # * Does not support item assignment, thus not allowing this function
-        #    to be used only for removing existing cache entries.
-        #  * Does not support the dict.pop() method, forcing us to use the
-        #    get/del patterns instead. For more detailed information see the
-        #    following links:
-        #      https://github.com/pypa/setuptools/issues/202#issuecomment-202913420
-        #      https://foss.heptapod.net/pypy/pypy/-/blob/144c4e65cb6accb8e592f3a7584ea38265d1873c/pypy/module/zipimport/interp_zipimport.py
-        old_entry = cache[p]
-        del cache[p]
-        new_entry = updater and updater(p, old_entry)
-        if new_entry is not None:
-            cache[p] = new_entry
-
-
-def _uncache(normalized_path, cache):
-    _update_zipimporter_cache(normalized_path, cache)
-
-
-def _remove_and_clear_zip_directory_cache_data(normalized_path):
-    def clear_and_remove_cached_zip_archive_directory_data(path, old_entry):
-        old_entry.clear()
-
-    _update_zipimporter_cache(
-        normalized_path,
-        zipimport._zip_directory_cache,
-        updater=clear_and_remove_cached_zip_archive_directory_data,
-    )
-
-
-# PyPy Python implementation does not allow directly writing to the
-# zipimport._zip_directory_cache and so prevents us from attempting to correct
-# its content. The best we can do there is clear the problematic cache content
-# and have PyPy repopulate it as needed. The downside is that if there are any
-# stale zipimport.zipimporter instances laying around, attempting to use them
-# will fail due to not having its zip archive directory information available
-# instead of being automatically corrected to use the new correct zip archive
-# directory information.
-if '__pypy__' in sys.builtin_module_names:
-    _replace_zip_directory_cache_data = _remove_and_clear_zip_directory_cache_data
-else:
-
-    def _replace_zip_directory_cache_data(normalized_path):
-        def replace_cached_zip_archive_directory_data(path, old_entry):
-            # N.B. In theory, we could load the zip directory information just
-            # once for all updated path spellings, and then copy it locally and
-            # update its contained path strings to contain the correct
-            # spelling, but that seems like a way too invasive move (this cache
-            # structure is not officially documented anywhere and could in
-            # theory change with new Python releases) for no significant
-            # benefit.
-            old_entry.clear()
-            zipimport.zipimporter(path)
-            old_entry.update(zipimport._zip_directory_cache[path])
-            return old_entry
-
-        _update_zipimporter_cache(
-            normalized_path,
-            zipimport._zip_directory_cache,
-            updater=replace_cached_zip_archive_directory_data,
-        )
-
-
-def is_python(text, filename=''):
-    "Is this string a valid Python script?"
-    try:
-        compile(text, filename, 'exec')
-    except (SyntaxError, TypeError):
-        return False
-    else:
-        return True
-
-
-def is_sh(executable):
-    """Determine if the specified executable is a .sh (contains a #! line)"""
-    try:
-        with open(executable, encoding='latin-1') as fp:
-            magic = fp.read(2)
-    except OSError:
-        return executable
-    return magic == '#!'
-
-
-def nt_quote_arg(arg):
-    """Quote a command line argument according to Windows parsing rules"""
-    return subprocess.list2cmdline([arg])
-
-
-def is_python_script(script_text, filename):
-    """Is this text, as a whole, a Python script? (as opposed to shell/bat/etc."""
-    if filename.endswith('.py') or filename.endswith('.pyw'):
-        return True  # extension says it's Python
-    if is_python(script_text, filename):
-        return True  # it's syntactically valid Python
-    if script_text.startswith('#!'):
-        # It begins with a '#!' line, so check if 'python' is in it somewhere
-        return 'python' in script_text.splitlines()[0].lower()
-
-    return False  # Not any Python I can recognize
-
-
-class _SplitArgs(TypedDict, total=False):
-    comments: bool
-    posix: bool
-
-
-class CommandSpec(list):
-    """
-    A command spec for a #! header, specified as a list of arguments akin to
-    those passed to Popen.
-    """
-
-    options: list[str] = []
-    split_args = _SplitArgs()
-
-    @classmethod
-    def best(cls):
-        """
-        Choose the best CommandSpec class based on environmental conditions.
-        """
-        return cls
-
-    @classmethod
-    def _sys_executable(cls):
-        _default = os.path.normpath(sys.executable)
-        return os.environ.get('__PYVENV_LAUNCHER__', _default)
-
-    @classmethod
-    def from_param(cls, param: Self | str | Iterable[str] | None) -> Self:
-        """
-        Construct a CommandSpec from a parameter to build_scripts, which may
-        be None.
-        """
-        if isinstance(param, cls):
-            return param
-        if isinstance(param, str):
-            return cls.from_string(param)
-        if isinstance(param, Iterable):
-            return cls(param)
-        if param is None:
-            return cls.from_environment()
-        raise TypeError(f"Argument has an unsupported type {type(param)}")
-
-    @classmethod
-    def from_environment(cls):
-        return cls([cls._sys_executable()])
-
-    @classmethod
-    def from_string(cls, string: str) -> Self:
-        """
-        Construct a command spec from a simple string representing a command
-        line parseable by shlex.split.
-        """
-        items = shlex.split(string, **cls.split_args)
-        return cls(items)
-
-    def install_options(self, script_text: str):
-        self.options = shlex.split(self._extract_options(script_text))
-        cmdline = subprocess.list2cmdline(self)
-        if not isascii(cmdline):
-            self.options[:0] = ['-x']
-
-    @staticmethod
-    def _extract_options(orig_script):
-        """
-        Extract any options from the first line of the script.
-        """
-        first = (orig_script + '\n').splitlines()[0]
-        match = _first_line_re().match(first)
-        options = match.group(1) or '' if match else ''
-        return options.strip()
-
-    def as_header(self):
-        return self._render(self + list(self.options))
-
-    @staticmethod
-    def _strip_quotes(item):
-        _QUOTES = '"\''
-        for q in _QUOTES:
-            if item.startswith(q) and item.endswith(q):
-                return item[1:-1]
-        return item
-
-    @staticmethod
-    def _render(items):
-        cmdline = subprocess.list2cmdline(
-            CommandSpec._strip_quotes(item.strip()) for item in items
-        )
-        return '#!' + cmdline + '\n'
-
-
-# For pbr compat; will be removed in a future version.
-sys_executable = CommandSpec._sys_executable()
-
-
-class WindowsCommandSpec(CommandSpec):
-    split_args = _SplitArgs(posix=False)
-
-
-class ScriptWriter:
-    """
-    Encapsulates behavior around writing entry point scripts for console and
-    gui apps.
-    """
-
-    template = textwrap.dedent(
-        r"""
-        # EASY-INSTALL-ENTRY-SCRIPT: %(spec)r,%(group)r,%(name)r
-        import re
-        import sys
-
-        # for compatibility with easy_install; see #2198
-        __requires__ = %(spec)r
-
-        try:
-            from importlib.metadata import distribution
-        except ImportError:
-            try:
-                from importlib_metadata import distribution
-            except ImportError:
-                from pkg_resources import load_entry_point
-
-
-        def importlib_load_entry_point(spec, group, name):
-            dist_name, _, _ = spec.partition('==')
-            matches = (
-                entry_point
-                for entry_point in distribution(dist_name).entry_points
-                if entry_point.group == group and entry_point.name == name
-            )
-            return next(matches).load()
-
-
-        globals().setdefault('load_entry_point', importlib_load_entry_point)
-
-
-        if __name__ == '__main__':
-            sys.argv[0] = re.sub(r'(-script\.pyw?|\.exe)?$', '', sys.argv[0])
-            sys.exit(load_entry_point(%(spec)r, %(group)r, %(name)r)())
-        """
-    ).lstrip()
-
-    command_spec_class = CommandSpec
-
-    @classmethod
-    def get_args(cls, dist, header=None):
-        """
-        Yield write_script() argument tuples for a distribution's
-        console_scripts and gui_scripts entry points.
-        """
-        if header is None:
-            header = cls.get_header()
-        spec = str(dist.as_requirement())
-        for type_ in 'console', 'gui':
-            group = type_ + '_scripts'
-            for name in dist.get_entry_map(group).keys():
-                cls._ensure_safe_name(name)
-                script_text = cls.template % locals()
-                args = cls._get_script_args(type_, name, header, script_text)
-                yield from args
-
-    @staticmethod
-    def _ensure_safe_name(name):
-        """
-        Prevent paths in *_scripts entry point names.
-        """
-        has_path_sep = re.search(r'[\\/]', name)
-        if has_path_sep:
-            raise ValueError("Path separators not allowed in script names")
-
-    @classmethod
-    def best(cls):
-        """
-        Select the best ScriptWriter for this environment.
-        """
-        if sys.platform == 'win32' or (os.name == 'java' and os._name == 'nt'):
-            return WindowsScriptWriter.best()
-        else:
-            return cls
-
-    @classmethod
-    def _get_script_args(cls, type_, name, header, script_text):
-        # Simply write the stub with no extension.
-        yield (name, header + script_text)
-
-    @classmethod
-    def get_header(
-        cls,
-        script_text: str = "",
-        executable: str | CommandSpec | Iterable[str] | None = None,
-    ) -> str:
-        """Create a #! line, getting options (if any) from script_text"""
-        cmd = cls.command_spec_class.best().from_param(executable)
-        cmd.install_options(script_text)
-        return cmd.as_header()
-
-
-class WindowsScriptWriter(ScriptWriter):
-    command_spec_class = WindowsCommandSpec
-
-    @classmethod
-    def best(cls):
-        """
-        Select the best ScriptWriter suitable for Windows
-        """
-        writer_lookup = dict(
-            executable=WindowsExecutableLauncherWriter,
-            natural=cls,
-        )
-        # for compatibility, use the executable launcher by default
-        launcher = os.environ.get('SETUPTOOLS_LAUNCHER', 'executable')
-        return writer_lookup[launcher]
-
-    @classmethod
-    def _get_script_args(cls, type_, name, header, script_text):
-        "For Windows, add a .py extension"
-        ext = dict(console='.pya', gui='.pyw')[type_]
-        if ext not in os.environ['PATHEXT'].lower().split(';'):
-            msg = (
-                "{ext} not listed in PATHEXT; scripts will not be "
-                "recognized as executables."
-            ).format(**locals())
-            SetuptoolsWarning.emit(msg)
-        old = ['.pya', '.py', '-script.py', '.pyc', '.pyo', '.pyw', '.exe']
-        old.remove(ext)
-        header = cls._adjust_header(type_, header)
-        blockers = [name + x for x in old]
-        yield name + ext, header + script_text, 't', blockers
-
-    @classmethod
-    def _adjust_header(cls, type_, orig_header):
-        """
-        Make sure 'pythonw' is used for gui and 'python' is used for
-        console (regardless of what sys.executable is).
-        """
-        pattern = 'pythonw.exe'
-        repl = 'python.exe'
-        if type_ == 'gui':
-            pattern, repl = repl, pattern
-        pattern_ob = re.compile(re.escape(pattern), re.IGNORECASE)
-        new_header = pattern_ob.sub(string=orig_header, repl=repl)
-        return new_header if cls._use_header(new_header) else orig_header
-
-    @staticmethod
-    def _use_header(new_header):
-        """
-        Should _adjust_header use the replaced header?
-
-        On non-windows systems, always use. On
-        Windows systems, only use the replaced header if it resolves
-        to an executable on the system.
-        """
-        clean_header = new_header[2:-1].strip('"')
-        return sys.platform != 'win32' or shutil.which(clean_header)
-
-
-class WindowsExecutableLauncherWriter(WindowsScriptWriter):
-    @classmethod
-    def _get_script_args(cls, type_, name, header, script_text):
-        """
-        For Windows, add a .py extension and an .exe launcher
-        """
-        if type_ == 'gui':
-            launcher_type = 'gui'
-            ext = '-script.pyw'
-            old = ['.pyw']
-        else:
-            launcher_type = 'cli'
-            ext = '-script.py'
-            old = ['.py', '.pyc', '.pyo']
-        hdr = cls._adjust_header(type_, header)
-        blockers = [name + x for x in old]
-        yield (name + ext, hdr + script_text, 't', blockers)
-        yield (
-            name + '.exe',
-            get_win_launcher(launcher_type),
-            'b',  # write in binary mode
-        )
-        if not is_64bit():
-            # install a manifest for the launcher to prevent Windows
-            # from detecting it as an installer (which it will for
-            #  launchers like easy_install.exe). Consider only
-            #  adding a manifest for launchers detected as installers.
-            #  See Distribute #143 for details.
-            m_name = name + '.exe.manifest'
-            yield (m_name, load_launcher_manifest(name), 't')
-
-
-def get_win_launcher(type):
-    """
-    Load the Windows launcher (executable) suitable for launching a script.
-
-    `type` should be either 'cli' or 'gui'
-
-    Returns the executable as a byte string.
-    """
-    launcher_fn = f'{type}.exe'
-    if is_64bit():
-        if get_platform() == "win-arm64":
-            launcher_fn = launcher_fn.replace(".", "-arm64.")
-        else:
-            launcher_fn = launcher_fn.replace(".", "-64.")
-    else:
-        launcher_fn = launcher_fn.replace(".", "-32.")
-    return resource_string('setuptools', launcher_fn)
-
-
-def load_launcher_manifest(name):
-    manifest = pkg_resources.resource_string(__name__, 'launcher manifest.xml')
-    return manifest.decode('utf-8') % vars()
-
-
-def current_umask():
-    tmp = os.umask(0o022)
-    os.umask(tmp)
-    return tmp
-
-
-def only_strs(values):
-    """
-    Exclude non-str values. Ref #3063.
-    """
-    return filter(lambda val: isinstance(val, str), values)
-
-
-def _read_pth(fullname: str) -> str:
-    # Python<3.13 require encoding="locale" instead of "utf-8", see python/cpython#77102
-    # In the case old versions of setuptools are producing `pth` files with
-    # different encodings that might be problematic... So we fallback to "locale".
-
-    try:
-        with open(fullname, encoding=py312.PTH_ENCODING) as f:
-            return f.read()
-    except UnicodeDecodeError:  # pragma: no cover
-        # This error may only happen for Python >= 3.13
-        # TODO: Possible deprecation warnings to be added in the future:
-        #       ``.pth file {fullname!r} is not UTF-8.``
-        #       Your environment contain {fullname!r} that cannot be read as UTF-8.
-        #       This is likely to have been produced with an old version of setuptools.
-        #       Please be mindful that this is deprecated and in the future, non-utf8
-        #       .pth files may cause setuptools to fail.
-        with open(fullname, encoding=py39.LOCALE_ENCODING) as f:
-            return f.read()
-
-
-class EasyInstallDeprecationWarning(SetuptoolsDeprecationWarning):
-    _SUMMARY = "easy_install command is deprecated."
-    _DETAILS = """
-    Please avoid running ``setup.py`` and ``easy_install``.
-    Instead, use pypa/build, pypa/installer or other
-    standards-based tools.
-    """
-    _SEE_URL = "https://github.com/pypa/setuptools/issues/917"
-    # _DUE_DATE not defined yet
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/editable_wheel.py b/llmlab/lib/python3.12/site-packages/setuptools/command/editable_wheel.py
deleted file mode 100644
index 1a544ec..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/editable_wheel.py
+++ /dev/null
@@ -1,925 +0,0 @@
-"""
-Create a wheel that, when installed, will make the source package 'editable'
-(add it to the interpreter's path, including metadata) per PEP 660. Replaces
-'setup.py develop'.
-
-.. note::
-   One of the mechanisms briefly mentioned in PEP 660 to implement editable installs is
-   to create a separated directory inside ``build`` and use a .pth file to point to that
-   directory. In the context of this file such directory is referred as
-   *auxiliary build directory* or ``auxiliary_dir``.
-"""
-
-from __future__ import annotations
-
-import io
-import logging
-import os
-import shutil
-import traceback
-from collections.abc import Iterable, Iterator, Mapping
-from contextlib import suppress
-from enum import Enum
-from inspect import cleandoc
-from itertools import chain, starmap
-from pathlib import Path
-from tempfile import TemporaryDirectory
-from types import TracebackType
-from typing import TYPE_CHECKING, Protocol, TypeVar, cast
-
-from .. import Command, _normalization, _path, _shutil, errors, namespaces
-from .._path import StrPath
-from ..compat import py312
-from ..discovery import find_package_path
-from ..dist import Distribution
-from ..warnings import InformationOnly, SetuptoolsDeprecationWarning, SetuptoolsWarning
-from .build import build as build_cls
-from .build_py import build_py as build_py_cls
-from .dist_info import dist_info as dist_info_cls
-from .egg_info import egg_info as egg_info_cls
-from .install import install as install_cls
-from .install_scripts import install_scripts as install_scripts_cls
-
-if TYPE_CHECKING:
-    from typing_extensions import Self
-
-    from .._vendor.wheel.wheelfile import WheelFile
-
-_P = TypeVar("_P", bound=StrPath)
-_logger = logging.getLogger(__name__)
-
-
-class _EditableMode(Enum):
-    """
-    Possible editable installation modes:
-    `lenient` (new files automatically added to the package - DEFAULT);
-    `strict` (requires a new installation when files are added/removed); or
-    `compat` (attempts to emulate `python setup.py develop` - DEPRECATED).
-    """
-
-    STRICT = "strict"
-    LENIENT = "lenient"
-    COMPAT = "compat"  # TODO: Remove `compat` after Dec/2022.
-
-    @classmethod
-    def convert(cls, mode: str | None) -> _EditableMode:
-        if not mode:
-            return _EditableMode.LENIENT  # default
-
-        _mode = mode.upper()
-        if _mode not in _EditableMode.__members__:
-            raise errors.OptionError(f"Invalid editable mode: {mode!r}. Try: 'strict'.")
-
-        if _mode == "COMPAT":
-            SetuptoolsDeprecationWarning.emit(
-                "Compat editable installs",
-                """
-                The 'compat' editable mode is transitional and will be removed
-                in future versions of `setuptools`.
-                Please adapt your code accordingly to use either the 'strict' or the
-                'lenient' modes.
-                """,
-                see_docs="userguide/development_mode.html",
-                # TODO: define due_date
-                # There is a series of shortcomings with the available editable install
-                # methods, and they are very controversial. This is something that still
-                # needs work.
-                # Moreover, `pip` is still hiding this warning, so users are not aware.
-            )
-
-        return _EditableMode[_mode]
-
-
-_STRICT_WARNING = """
-New or renamed files may not be automatically picked up without a new installation.
-"""
-
-_LENIENT_WARNING = """
-Options like `package-data`, `include/exclude-package-data` or
-`packages.find.exclude/include` may have no effect.
-"""
-
-
-class editable_wheel(Command):
-    """Build 'editable' wheel for development.
-    This command is private and reserved for internal use of setuptools,
-    users should rely on ``setuptools.build_meta`` APIs.
-    """
-
-    description = "DO NOT CALL DIRECTLY, INTERNAL ONLY: create PEP 660 editable wheel"
-
-    user_options = [
-        ("dist-dir=", "d", "directory to put final built distributions in"),
-        ("dist-info-dir=", "I", "path to a pre-build .dist-info directory"),
-        ("mode=", None, cleandoc(_EditableMode.__doc__ or "")),
-    ]
-
-    def initialize_options(self):
-        self.dist_dir = None
-        self.dist_info_dir = None
-        self.project_dir = None
-        self.mode = None
-
-    def finalize_options(self) -> None:
-        dist = self.distribution
-        self.project_dir = dist.src_root or os.curdir
-        self.package_dir = dist.package_dir or {}
-        self.dist_dir = Path(self.dist_dir or os.path.join(self.project_dir, "dist"))
-
-    def run(self) -> None:
-        try:
-            self.dist_dir.mkdir(exist_ok=True)
-            self._ensure_dist_info()
-
-            # Add missing dist_info files
-            self.reinitialize_command("bdist_wheel")
-            bdist_wheel = self.get_finalized_command("bdist_wheel")
-            bdist_wheel.write_wheelfile(self.dist_info_dir)
-
-            self._create_wheel_file(bdist_wheel)
-        except Exception:
-            traceback.print_exc()
-            project = self.distribution.name or self.distribution.get_name()
-            _DebuggingTips.emit(project=project)
-            raise
-
-    def _ensure_dist_info(self):
-        if self.dist_info_dir is None:
-            dist_info = cast(dist_info_cls, self.reinitialize_command("dist_info"))
-            dist_info.output_dir = self.dist_dir
-            dist_info.ensure_finalized()
-            dist_info.run()
-            self.dist_info_dir = dist_info.dist_info_dir
-        else:
-            assert str(self.dist_info_dir).endswith(".dist-info")
-            assert Path(self.dist_info_dir, "METADATA").exists()
-
-    def _install_namespaces(self, installation_dir, pth_prefix):
-        # XXX: Only required to support the deprecated namespace practice
-        dist = self.distribution
-        if not dist.namespace_packages:
-            return
-
-        src_root = Path(self.project_dir, self.package_dir.get("", ".")).resolve()
-        installer = _NamespaceInstaller(dist, installation_dir, pth_prefix, src_root)
-        installer.install_namespaces()
-
-    def _find_egg_info_dir(self) -> str | None:
-        parent_dir = Path(self.dist_info_dir).parent if self.dist_info_dir else Path()
-        candidates = map(str, parent_dir.glob("*.egg-info"))
-        return next(candidates, None)
-
-    def _configure_build(
-        self, name: str, unpacked_wheel: StrPath, build_lib: StrPath, tmp_dir: StrPath
-    ):
-        """Configure commands to behave in the following ways:
-
-        - Build commands can write to ``build_lib`` if they really want to...
-          (but this folder is expected to be ignored and modules are expected to live
-          in the project directory...)
-        - Binary extensions should be built in-place (editable_mode = True)
-        - Data/header/script files are not part of the "editable" specification
-          so they are written directly to the unpacked_wheel directory.
-        """
-        # Non-editable files (data, headers, scripts) are written directly to the
-        # unpacked_wheel
-
-        dist = self.distribution
-        wheel = str(unpacked_wheel)
-        build_lib = str(build_lib)
-        data = str(Path(unpacked_wheel, f"{name}.data", "data"))
-        headers = str(Path(unpacked_wheel, f"{name}.data", "headers"))
-        scripts = str(Path(unpacked_wheel, f"{name}.data", "scripts"))
-
-        # egg-info may be generated again to create a manifest (used for package data)
-        egg_info = cast(
-            egg_info_cls, dist.reinitialize_command("egg_info", reinit_subcommands=True)
-        )
-        egg_info.egg_base = str(tmp_dir)
-        egg_info.ignore_egg_info_in_manifest = True
-
-        build = cast(
-            build_cls, dist.reinitialize_command("build", reinit_subcommands=True)
-        )
-        install = cast(
-            install_cls, dist.reinitialize_command("install", reinit_subcommands=True)
-        )
-
-        build.build_platlib = build.build_purelib = build.build_lib = build_lib
-        install.install_purelib = install.install_platlib = install.install_lib = wheel
-        install.install_scripts = build.build_scripts = scripts
-        install.install_headers = headers
-        install.install_data = data
-
-        install_scripts = cast(
-            install_scripts_cls, dist.get_command_obj("install_scripts")
-        )
-        install_scripts.no_ep = True
-
-        build.build_temp = str(tmp_dir)
-
-        build_py = cast(build_py_cls, dist.get_command_obj("build_py"))
-        build_py.compile = False
-        build_py.existing_egg_info_dir = self._find_egg_info_dir()
-
-        self._set_editable_mode()
-
-        build.ensure_finalized()
-        install.ensure_finalized()
-
-    def _set_editable_mode(self):
-        """Set the ``editable_mode`` flag in the build sub-commands"""
-        dist = self.distribution
-        build = dist.get_command_obj("build")
-        for cmd_name in build.get_sub_commands():
-            cmd = dist.get_command_obj(cmd_name)
-            if hasattr(cmd, "editable_mode"):
-                cmd.editable_mode = True
-            elif hasattr(cmd, "inplace"):
-                cmd.inplace = True  # backward compatibility with distutils
-
-    def _collect_build_outputs(self) -> tuple[list[str], dict[str, str]]:
-        files: list[str] = []
-        mapping: dict[str, str] = {}
-        build = self.get_finalized_command("build")
-
-        for cmd_name in build.get_sub_commands():
-            cmd = self.get_finalized_command(cmd_name)
-            if hasattr(cmd, "get_outputs"):
-                files.extend(cmd.get_outputs() or [])
-            if hasattr(cmd, "get_output_mapping"):
-                mapping.update(cmd.get_output_mapping() or {})
-
-        return files, mapping
-
-    def _run_build_commands(
-        self,
-        dist_name: str,
-        unpacked_wheel: StrPath,
-        build_lib: StrPath,
-        tmp_dir: StrPath,
-    ) -> tuple[list[str], dict[str, str]]:
-        self._configure_build(dist_name, unpacked_wheel, build_lib, tmp_dir)
-        self._run_build_subcommands()
-        files, mapping = self._collect_build_outputs()
-        self._run_install("headers")
-        self._run_install("scripts")
-        self._run_install("data")
-        return files, mapping
-
-    def _run_build_subcommands(self) -> None:
-        """
-        Issue #3501 indicates that some plugins/customizations might rely on:
-
-        1. ``build_py`` not running
-        2. ``build_py`` always copying files to ``build_lib``
-
-        However both these assumptions may be false in editable_wheel.
-        This method implements a temporary workaround to support the ecosystem
-        while the implementations catch up.
-        """
-        # TODO: Once plugins/customizations had the chance to catch up, replace
-        #       `self._run_build_subcommands()` with `self.run_command("build")`.
-        #       Also remove _safely_run, TestCustomBuildPy. Suggested date: Aug/2023.
-        build = self.get_finalized_command("build")
-        for name in build.get_sub_commands():
-            cmd = self.get_finalized_command(name)
-            if name == "build_py" and type(cmd) is not build_py_cls:
-                self._safely_run(name)
-            else:
-                self.run_command(name)
-
-    def _safely_run(self, cmd_name: str):
-        try:
-            return self.run_command(cmd_name)
-        except Exception:
-            SetuptoolsDeprecationWarning.emit(
-                "Customization incompatible with editable install",
-                f"""
-                {traceback.format_exc()}
-
-                If you are seeing this warning it is very likely that a setuptools
-                plugin or customization overrides the `{cmd_name}` command, without
-                taking into consideration how editable installs run build steps
-                starting from setuptools v64.0.0.
-
-                Plugin authors and developers relying on custom build steps are
-                encouraged to update their `{cmd_name}` implementation considering the
-                information about editable installs in
-                https://setuptools.pypa.io/en/latest/userguide/extension.html.
-
-                For the time being `setuptools` will silence this error and ignore
-                the faulty command, but this behavior will change in future versions.
-                """,
-                # TODO: define due_date
-                # There is a series of shortcomings with the available editable install
-                # methods, and they are very controversial. This is something that still
-                # needs work.
-            )
-
-    def _create_wheel_file(self, bdist_wheel):
-        from wheel.wheelfile import WheelFile
-
-        dist_info = self.get_finalized_command("dist_info")
-        dist_name = dist_info.name
-        tag = "-".join(bdist_wheel.get_tag())
-        build_tag = "0.editable"  # According to PEP 427 needs to start with digit
-        archive_name = f"{dist_name}-{build_tag}-{tag}.whl"
-        wheel_path = Path(self.dist_dir, archive_name)
-        if wheel_path.exists():
-            wheel_path.unlink()
-
-        unpacked_wheel = TemporaryDirectory(suffix=archive_name)
-        build_lib = TemporaryDirectory(suffix=".build-lib")
-        build_tmp = TemporaryDirectory(suffix=".build-temp")
-
-        with unpacked_wheel as unpacked, build_lib as lib, build_tmp as tmp:
-            unpacked_dist_info = Path(unpacked, Path(self.dist_info_dir).name)
-            shutil.copytree(self.dist_info_dir, unpacked_dist_info)
-            self._install_namespaces(unpacked, dist_name)
-            files, mapping = self._run_build_commands(dist_name, unpacked, lib, tmp)
-            strategy = self._select_strategy(dist_name, tag, lib)
-            with strategy, WheelFile(wheel_path, "w") as wheel_obj:
-                strategy(wheel_obj, files, mapping)
-                wheel_obj.write_files(unpacked)
-
-        return wheel_path
-
-    def _run_install(self, category: str):
-        has_category = getattr(self.distribution, f"has_{category}", None)
-        if has_category and has_category():
-            _logger.info(f"Installing {category} as non editable")
-            self.run_command(f"install_{category}")
-
-    def _select_strategy(
-        self,
-        name: str,
-        tag: str,
-        build_lib: StrPath,
-    ) -> EditableStrategy:
-        """Decides which strategy to use to implement an editable installation."""
-        build_name = f"__editable__.{name}-{tag}"
-        project_dir = Path(self.project_dir)
-        mode = _EditableMode.convert(self.mode)
-
-        if mode is _EditableMode.STRICT:
-            auxiliary_dir = _empty_dir(Path(self.project_dir, "build", build_name))
-            return _LinkTree(self.distribution, name, auxiliary_dir, build_lib)
-
-        packages = _find_packages(self.distribution)
-        has_simple_layout = _simple_layout(packages, self.package_dir, project_dir)
-        is_compat_mode = mode is _EditableMode.COMPAT
-        if set(self.package_dir) == {""} and has_simple_layout or is_compat_mode:
-            # src-layout(ish) is relatively safe for a simple pth file
-            src_dir = self.package_dir.get("", ".")
-            return _StaticPth(self.distribution, name, [Path(project_dir, src_dir)])
-
-        # Use a MetaPathFinder to avoid adding accidental top-level packages/modules
-        return _TopLevelFinder(self.distribution, name)
-
-
-class EditableStrategy(Protocol):
-    def __call__(
-        self, wheel: WheelFile, files: list[str], mapping: Mapping[str, str]
-    ) -> object: ...
-    def __enter__(self) -> Self: ...
-    def __exit__(
-        self,
-        _exc_type: type[BaseException] | None,
-        _exc_value: BaseException | None,
-        _traceback: TracebackType | None,
-    ) -> object: ...
-
-
-class _StaticPth:
-    def __init__(self, dist: Distribution, name: str, path_entries: list[Path]) -> None:
-        self.dist = dist
-        self.name = name
-        self.path_entries = path_entries
-
-    def __call__(self, wheel: WheelFile, files: list[str], mapping: Mapping[str, str]):
-        entries = "\n".join(str(p.resolve()) for p in self.path_entries)
-        contents = _encode_pth(f"{entries}\n")
-        wheel.writestr(f"__editable__.{self.name}.pth", contents)
-
-    def __enter__(self) -> Self:
-        msg = f"""
-        Editable install will be performed using .pth file to extend `sys.path` with:
-        {list(map(os.fspath, self.path_entries))!r}
-        """
-        _logger.warning(msg + _LENIENT_WARNING)
-        return self
-
-    def __exit__(
-        self,
-        _exc_type: object,
-        _exc_value: object,
-        _traceback: object,
-    ) -> None:
-        pass
-
-
-class _LinkTree(_StaticPth):
-    """
-    Creates a ``.pth`` file that points to a link tree in the ``auxiliary_dir``.
-
-    This strategy will only link files (not dirs), so it can be implemented in
-    any OS, even if that means using hardlinks instead of symlinks.
-
-    By collocating ``auxiliary_dir`` and the original source code, limitations
-    with hardlinks should be avoided.
-    """
-
-    def __init__(
-        self,
-        dist: Distribution,
-        name: str,
-        auxiliary_dir: StrPath,
-        build_lib: StrPath,
-    ) -> None:
-        self.auxiliary_dir = Path(auxiliary_dir)
-        self.build_lib = Path(build_lib).resolve()
-        self._file = dist.get_command_obj("build_py").copy_file
-        super().__init__(dist, name, [self.auxiliary_dir])
-
-    def __call__(self, wheel: WheelFile, files: list[str], mapping: Mapping[str, str]):
-        self._create_links(files, mapping)
-        super().__call__(wheel, files, mapping)
-
-    def _normalize_output(self, file: str) -> str | None:
-        # Files relative to build_lib will be normalized to None
-        with suppress(ValueError):
-            path = Path(file).resolve().relative_to(self.build_lib)
-            return str(path).replace(os.sep, '/')
-        return None
-
-    def _create_file(self, relative_output: str, src_file: str, link=None):
-        dest = self.auxiliary_dir / relative_output
-        if not dest.parent.is_dir():
-            dest.parent.mkdir(parents=True)
-        self._file(src_file, dest, link=link)
-
-    def _create_links(self, outputs, output_mapping: Mapping[str, str]):
-        self.auxiliary_dir.mkdir(parents=True, exist_ok=True)
-        link_type = "sym" if _can_symlink_files(self.auxiliary_dir) else "hard"
-        normalised = ((self._normalize_output(k), v) for k, v in output_mapping.items())
-        # remove files that are not relative to build_lib
-        mappings = {k: v for k, v in normalised if k is not None}
-
-        for output in outputs:
-            relative = self._normalize_output(output)
-            if relative and relative not in mappings:
-                self._create_file(relative, output)
-
-        for relative, src in mappings.items():
-            self._create_file(relative, src, link=link_type)
-
-    def __enter__(self) -> Self:
-        msg = "Strict editable install will be performed using a link tree.\n"
-        _logger.warning(msg + _STRICT_WARNING)
-        return self
-
-    def __exit__(
-        self,
-        _exc_type: object,
-        _exc_value: object,
-        _traceback: object,
-    ) -> None:
-        msg = f"""\n
-        Strict editable installation performed using the auxiliary directory:
-            {self.auxiliary_dir}
-
-        Please be careful to not remove this directory, otherwise you might not be able
-        to import/use your package.
-        """
-        InformationOnly.emit("Editable installation.", msg)
-
-
-class _TopLevelFinder:
-    def __init__(self, dist: Distribution, name: str) -> None:
-        self.dist = dist
-        self.name = name
-
-    def template_vars(self) -> tuple[str, str, dict[str, str], dict[str, list[str]]]:
-        src_root = self.dist.src_root or os.curdir
-        top_level = chain(_find_packages(self.dist), _find_top_level_modules(self.dist))
-        package_dir = self.dist.package_dir or {}
-        roots = _find_package_roots(top_level, package_dir, src_root)
-
-        namespaces_ = dict(
-            chain(
-                _find_namespaces(self.dist.packages or [], roots),
-                ((ns, []) for ns in _find_virtual_namespaces(roots)),
-            )
-        )
-
-        legacy_namespaces = {
-            pkg: find_package_path(pkg, roots, self.dist.src_root or "")
-            for pkg in self.dist.namespace_packages or []
-        }
-
-        mapping = {**roots, **legacy_namespaces}
-        # ^-- We need to explicitly add the legacy_namespaces to the mapping to be
-        #     able to import their modules even if another package sharing the same
-        #     namespace is installed in a conventional (non-editable) way.
-
-        name = f"__editable__.{self.name}.finder"
-        finder = _normalization.safe_identifier(name)
-        return finder, name, mapping, namespaces_
-
-    def get_implementation(self) -> Iterator[tuple[str, bytes]]:
-        finder, name, mapping, namespaces_ = self.template_vars()
-
-        content = bytes(_finder_template(name, mapping, namespaces_), "utf-8")
-        yield (f"{finder}.py", content)
-
-        content = _encode_pth(f"import {finder}; {finder}.install()")
-        yield (f"__editable__.{self.name}.pth", content)
-
-    def __call__(self, wheel: WheelFile, files: list[str], mapping: Mapping[str, str]):
-        for file, content in self.get_implementation():
-            wheel.writestr(file, content)
-
-    def __enter__(self) -> Self:
-        msg = "Editable install will be performed using a meta path finder.\n"
-        _logger.warning(msg + _LENIENT_WARNING)
-        return self
-
-    def __exit__(
-        self,
-        _exc_type: object,
-        _exc_value: object,
-        _traceback: object,
-    ) -> None:
-        msg = """\n
-        Please be careful with folders in your working directory with the same
-        name as your package as they may take precedence during imports.
-        """
-        InformationOnly.emit("Editable installation.", msg)
-
-
-def _encode_pth(content: str) -> bytes:
-    """
-    Prior to Python 3.13 (see https://github.com/python/cpython/issues/77102),
-    .pth files are always read with 'locale' encoding, the recommendation
-    from the cpython core developers is to write them as ``open(path, "w")``
-    and ignore warnings (see python/cpython#77102, pypa/setuptools#3937).
-    This function tries to simulate this behavior without having to create an
-    actual file, in a way that supports a range of active Python versions.
-    (There seems to be some variety in the way different version of Python handle
-    ``encoding=None``, not all of them use ``locale.getpreferredencoding(False)``
-    or ``locale.getencoding()``).
-    """
-    with io.BytesIO() as buffer:
-        wrapper = io.TextIOWrapper(buffer, encoding=py312.PTH_ENCODING)
-        # TODO: Python 3.13 replace the whole function with `bytes(content, "utf-8")`
-        wrapper.write(content)
-        wrapper.flush()
-        buffer.seek(0)
-        return buffer.read()
-
-
-def _can_symlink_files(base_dir: Path) -> bool:
-    with TemporaryDirectory(dir=str(base_dir.resolve())) as tmp:
-        path1, path2 = Path(tmp, "file1.txt"), Path(tmp, "file2.txt")
-        path1.write_text("file1", encoding="utf-8")
-        with suppress(AttributeError, NotImplementedError, OSError):
-            os.symlink(path1, path2)
-            if path2.is_symlink() and path2.read_text(encoding="utf-8") == "file1":
-                return True
-
-        try:
-            os.link(path1, path2)  # Ensure hard links can be created
-        except Exception as ex:
-            msg = (
-                "File system does not seem to support either symlinks or hard links. "
-                "Strict editable installs require one of them to be supported."
-            )
-            raise LinksNotSupported(msg) from ex
-        return False
-
-
-def _simple_layout(
-    packages: Iterable[str], package_dir: dict[str, str], project_dir: StrPath
-) -> bool:
-    """Return ``True`` if:
-    - all packages are contained by the same parent directory, **and**
-    - all packages become importable if the parent directory is added to ``sys.path``.
-
-    >>> _simple_layout(['a'], {"": "src"}, "/tmp/myproj")
-    True
-    >>> _simple_layout(['a', 'a.b'], {"": "src"}, "/tmp/myproj")
-    True
-    >>> _simple_layout(['a', 'a.b'], {}, "/tmp/myproj")
-    True
-    >>> _simple_layout(['a', 'a.a1', 'a.a1.a2', 'b'], {"": "src"}, "/tmp/myproj")
-    True
-    >>> _simple_layout(['a', 'a.a1', 'a.a1.a2', 'b'], {"a": "a", "b": "b"}, ".")
-    True
-    >>> _simple_layout(['a', 'a.a1', 'a.a1.a2', 'b'], {"a": "_a", "b": "_b"}, ".")
-    False
-    >>> _simple_layout(['a', 'a.a1', 'a.a1.a2', 'b'], {"a": "_a"}, "/tmp/myproj")
-    False
-    >>> _simple_layout(['a', 'a.a1', 'a.a1.a2', 'b'], {"a.a1.a2": "_a2"}, ".")
-    False
-    >>> _simple_layout(['a', 'a.b'], {"": "src", "a.b": "_ab"}, "/tmp/myproj")
-    False
-    >>> # Special cases, no packages yet:
-    >>> _simple_layout([], {"": "src"}, "/tmp/myproj")
-    True
-    >>> _simple_layout([], {"a": "_a", "": "src"}, "/tmp/myproj")
-    False
-    """
-    layout = {pkg: find_package_path(pkg, package_dir, project_dir) for pkg in packages}
-    if not layout:
-        return set(package_dir) in ({}, {""})
-    parent = os.path.commonpath(starmap(_parent_path, layout.items()))
-    return all(
-        _path.same_path(Path(parent, *key.split('.')), value)
-        for key, value in layout.items()
-    )
-
-
-def _parent_path(pkg, pkg_path):
-    """Infer the parent path containing a package, that if added to ``sys.path`` would
-    allow importing that package.
-    When ``pkg`` is directly mapped into a directory with a different name, return its
-    own path.
-    >>> _parent_path("a", "src/a")
-    'src'
-    >>> _parent_path("b", "src/c")
-    'src/c'
-    """
-    parent = pkg_path[: -len(pkg)] if pkg_path.endswith(pkg) else pkg_path
-    return parent.rstrip("/" + os.sep)
-
-
-def _find_packages(dist: Distribution) -> Iterator[str]:
-    yield from iter(dist.packages or [])
-
-    py_modules = dist.py_modules or []
-    nested_modules = [mod for mod in py_modules if "." in mod]
-    if dist.ext_package:
-        yield dist.ext_package
-    else:
-        ext_modules = dist.ext_modules or []
-        nested_modules += [x.name for x in ext_modules if "." in x.name]
-
-    for module in nested_modules:
-        package, _, _ = module.rpartition(".")
-        yield package
-
-
-def _find_top_level_modules(dist: Distribution) -> Iterator[str]:
-    py_modules = dist.py_modules or []
-    yield from (mod for mod in py_modules if "." not in mod)
-
-    if not dist.ext_package:
-        ext_modules = dist.ext_modules or []
-        yield from (x.name for x in ext_modules if "." not in x.name)
-
-
-def _find_package_roots(
-    packages: Iterable[str],
-    package_dir: Mapping[str, str],
-    src_root: StrPath,
-) -> dict[str, str]:
-    pkg_roots: dict[str, str] = {
-        pkg: _absolute_root(find_package_path(pkg, package_dir, src_root))
-        for pkg in sorted(packages)
-    }
-
-    return _remove_nested(pkg_roots)
-
-
-def _absolute_root(path: StrPath) -> str:
-    """Works for packages and top-level modules"""
-    path_ = Path(path)
-    parent = path_.parent
-
-    if path_.exists():
-        return str(path_.resolve())
-    else:
-        return str(parent.resolve() / path_.name)
-
-
-def _find_virtual_namespaces(pkg_roots: dict[str, str]) -> Iterator[str]:
-    """By carefully designing ``package_dir``, it is possible to implement the logical
-    structure of PEP 420 in a package without the corresponding directories.
-
-    Moreover a parent package can be purposefully/accidentally skipped in the discovery
-    phase (e.g. ``find_packages(include=["mypkg.*"])``, when ``mypkg.foo`` is included
-    by ``mypkg`` itself is not).
-    We consider this case to also be a virtual namespace (ignoring the original
-    directory) to emulate a non-editable installation.
-
-    This function will try to find these kinds of namespaces.
-    """
-    for pkg in pkg_roots:
-        if "." not in pkg:
-            continue
-        parts = pkg.split(".")
-        for i in range(len(parts) - 1, 0, -1):
-            partial_name = ".".join(parts[:i])
-            path = Path(find_package_path(partial_name, pkg_roots, ""))
-            if not path.exists() or partial_name not in pkg_roots:
-                # partial_name not in pkg_roots ==> purposefully/accidentally skipped
-                yield partial_name
-
-
-def _find_namespaces(
-    packages: list[str], pkg_roots: dict[str, str]
-) -> Iterator[tuple[str, list[str]]]:
-    for pkg in packages:
-        path = find_package_path(pkg, pkg_roots, "")
-        if Path(path).exists() and not Path(path, "__init__.py").exists():
-            yield (pkg, [path])
-
-
-def _remove_nested(pkg_roots: dict[str, str]) -> dict[str, str]:
-    output = dict(pkg_roots.copy())
-
-    for pkg, path in reversed(list(pkg_roots.items())):
-        if any(
-            pkg != other and _is_nested(pkg, path, other, other_path)
-            for other, other_path in pkg_roots.items()
-        ):
-            output.pop(pkg)
-
-    return output
-
-
-def _is_nested(pkg: str, pkg_path: str, parent: str, parent_path: str) -> bool:
-    """
-    Return ``True`` if ``pkg`` is nested inside ``parent`` both logically and in the
-    file system.
-    >>> _is_nested("a.b", "path/a/b", "a", "path/a")
-    True
-    >>> _is_nested("a.b", "path/a/b", "a", "otherpath/a")
-    False
-    >>> _is_nested("a.b", "path/a/b", "c", "path/c")
-    False
-    >>> _is_nested("a.a", "path/a/a", "a", "path/a")
-    True
-    >>> _is_nested("b.a", "path/b/a", "a", "path/a")
-    False
-    """
-    norm_pkg_path = _path.normpath(pkg_path)
-    rest = pkg.replace(parent, "", 1).strip(".").split(".")
-    return pkg.startswith(parent) and norm_pkg_path == _path.normpath(
-        Path(parent_path, *rest)
-    )
-
-
-def _empty_dir(dir_: _P) -> _P:
-    """Create a directory ensured to be empty. Existing files may be removed."""
-    _shutil.rmtree(dir_, ignore_errors=True)
-    os.makedirs(dir_)
-    return dir_
-
-
-class _NamespaceInstaller(namespaces.Installer):
-    def __init__(self, distribution, installation_dir, editable_name, src_root) -> None:
-        self.distribution = distribution
-        self.src_root = src_root
-        self.installation_dir = installation_dir
-        self.editable_name = editable_name
-        self.outputs: list[str] = []
-        self.dry_run = False
-
-    def _get_nspkg_file(self):
-        """Installation target."""
-        return os.path.join(self.installation_dir, self.editable_name + self.nspkg_ext)
-
-    def _get_root(self):
-        """Where the modules/packages should be loaded from."""
-        return repr(str(self.src_root))
-
-
-_FINDER_TEMPLATE = """\
-from __future__ import annotations
-import sys
-from importlib.machinery import ModuleSpec, PathFinder
-from importlib.machinery import all_suffixes as module_suffixes
-from importlib.util import spec_from_file_location
-from itertools import chain
-from pathlib import Path
-
-MAPPING: dict[str, str] = {mapping!r}
-NAMESPACES: dict[str, list[str]] = {namespaces!r}
-PATH_PLACEHOLDER = {name!r} + ".__path_hook__"
-
-
-class _EditableFinder:  # MetaPathFinder
-    @classmethod
-    def find_spec(cls, fullname: str, path=None, target=None) -> ModuleSpec | None:  # type: ignore
-        # Top-level packages and modules (we know these exist in the FS)
-        if fullname in MAPPING:
-            pkg_path = MAPPING[fullname]
-            return cls._find_spec(fullname, Path(pkg_path))
-
-        # Handle immediate children modules (required for namespaces to work)
-        # To avoid problems with case sensitivity in the file system we delegate
-        # to the importlib.machinery implementation.
-        parent, _, child = fullname.rpartition(".")
-        if parent and parent in MAPPING:
-            return PathFinder.find_spec(fullname, path=[MAPPING[parent]])
-
-        # Other levels of nesting should be handled automatically by importlib
-        # using the parent path.
-        return None
-
-    @classmethod
-    def _find_spec(cls, fullname: str, candidate_path: Path) -> ModuleSpec | None:
-        init = candidate_path / "__init__.py"
-        candidates = (candidate_path.with_suffix(x) for x in module_suffixes())
-        for candidate in chain([init], candidates):
-            if candidate.exists():
-                return spec_from_file_location(fullname, candidate)
-        return None
-
-
-class _EditableNamespaceFinder:  # PathEntryFinder
-    @classmethod
-    def _path_hook(cls, path) -> type[_EditableNamespaceFinder]:
-        if path == PATH_PLACEHOLDER:
-            return cls
-        raise ImportError
-
-    @classmethod
-    def _paths(cls, fullname: str) -> list[str]:
-        paths = NAMESPACES[fullname]
-        if not paths and fullname in MAPPING:
-            paths = [MAPPING[fullname]]
-        # Always add placeholder, for 2 reasons:
-        # 1. __path__ cannot be empty for the spec to be considered namespace.
-        # 2. In the case of nested namespaces, we need to force
-        #    import machinery to query _EditableNamespaceFinder again.
-        return [*paths, PATH_PLACEHOLDER]
-
-    @classmethod
-    def find_spec(cls, fullname: str, target=None) -> ModuleSpec | None:  # type: ignore
-        if fullname in NAMESPACES:
-            spec = ModuleSpec(fullname, None, is_package=True)
-            spec.submodule_search_locations = cls._paths(fullname)
-            return spec
-        return None
-
-    @classmethod
-    def find_module(cls, _fullname) -> None:
-        return None
-
-
-def install():
-    if not any(finder == _EditableFinder for finder in sys.meta_path):
-        sys.meta_path.append(_EditableFinder)
-
-    if not NAMESPACES:
-        return
-
-    if not any(hook == _EditableNamespaceFinder._path_hook for hook in sys.path_hooks):
-        # PathEntryFinder is needed to create NamespaceSpec without private APIS
-        sys.path_hooks.append(_EditableNamespaceFinder._path_hook)
-    if PATH_PLACEHOLDER not in sys.path:
-        sys.path.append(PATH_PLACEHOLDER)  # Used just to trigger the path hook
-"""
-
-
-def _finder_template(
-    name: str, mapping: Mapping[str, str], namespaces: dict[str, list[str]]
-) -> str:
-    """Create a string containing the code for the``MetaPathFinder`` and
-    ``PathEntryFinder``.
-    """
-    mapping = dict(sorted(mapping.items(), key=lambda p: p[0]))
-    return _FINDER_TEMPLATE.format(name=name, mapping=mapping, namespaces=namespaces)
-
-
-class LinksNotSupported(errors.FileError):
-    """File system does not seem to support either symlinks or hard links."""
-
-
-class _DebuggingTips(SetuptoolsWarning):
-    _SUMMARY = "Problem in editable installation."
-    _DETAILS = """
-    An error happened while installing `{project}` in editable mode.
-
-    The following steps are recommended to help debug this problem:
-
-    - Try to install the project normally, without using the editable mode.
-      Does the error still persist?
-      (If it does, try fixing the problem before attempting the editable mode).
-    - If you are using binary extensions, make sure you have all OS-level
-      dependencies installed (e.g. compilers, toolchains, binary libraries, ...).
-    - Try the latest version of setuptools (maybe the error was already fixed).
-    - If you (or your project dependencies) are using any setuptools extension
-      or customization, make sure they support the editable mode.
-
-    After following the steps above, if the problem still persists and
-    you think this is related to how setuptools handles editable installations,
-    please submit a reproducible example
-    (see https://stackoverflow.com/help/minimal-reproducible-example) to:
-
-        https://github.com/pypa/setuptools/issues
-    """
-    _SEE_DOCS = "userguide/development_mode.html"
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/egg_info.py b/llmlab/lib/python3.12/site-packages/setuptools/command/egg_info.py
deleted file mode 100644
index f776311..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/egg_info.py
+++ /dev/null
@@ -1,720 +0,0 @@
-"""setuptools.command.egg_info
-
-Create a distribution's .egg-info directory and contents"""
-
-import functools
-import os
-import re
-import sys
-import time
-from collections.abc import Callable
-
-import packaging
-import packaging.requirements
-import packaging.version
-
-import setuptools.unicode_utils as unicode_utils
-from setuptools import Command
-from setuptools.command import bdist_egg
-from setuptools.command.sdist import sdist, walk_revctrl
-from setuptools.command.setopt import edit_config
-from setuptools.glob import glob
-
-from .. import _entry_points, _normalization
-from .._importlib import metadata
-from ..warnings import SetuptoolsDeprecationWarning
-from . import _requirestxt
-
-import distutils.errors
-import distutils.filelist
-from distutils import log
-from distutils.errors import DistutilsInternalError
-from distutils.filelist import FileList as _FileList
-from distutils.util import convert_path
-
-PY_MAJOR = f'{sys.version_info.major}.{sys.version_info.minor}'
-
-
-def translate_pattern(glob):  # noqa: C901  # is too complex (14)  # FIXME
-    """
-    Translate a file path glob like '*.txt' in to a regular expression.
-    This differs from fnmatch.translate which allows wildcards to match
-    directory separators. It also knows about '**/' which matches any number of
-    directories.
-    """
-    pat = ''
-
-    # This will split on '/' within [character classes]. This is deliberate.
-    chunks = glob.split(os.path.sep)
-
-    sep = re.escape(os.sep)
-    valid_char = f'[^{sep}]'
-
-    for c, chunk in enumerate(chunks):
-        last_chunk = c == len(chunks) - 1
-
-        # Chunks that are a literal ** are globstars. They match anything.
-        if chunk == '**':
-            if last_chunk:
-                # Match anything if this is the last component
-                pat += '.*'
-            else:
-                # Match '(name/)*'
-                pat += f'(?:{valid_char}+{sep})*'
-            continue  # Break here as the whole path component has been handled
-
-        # Find any special characters in the remainder
-        i = 0
-        chunk_len = len(chunk)
-        while i < chunk_len:
-            char = chunk[i]
-            if char == '*':
-                # Match any number of name characters
-                pat += valid_char + '*'
-            elif char == '?':
-                # Match a name character
-                pat += valid_char
-            elif char == '[':
-                # Character class
-                inner_i = i + 1
-                # Skip initial !/] chars
-                if inner_i < chunk_len and chunk[inner_i] == '!':
-                    inner_i = inner_i + 1
-                if inner_i < chunk_len and chunk[inner_i] == ']':
-                    inner_i = inner_i + 1
-
-                # Loop till the closing ] is found
-                while inner_i < chunk_len and chunk[inner_i] != ']':
-                    inner_i = inner_i + 1
-
-                if inner_i >= chunk_len:
-                    # Got to the end of the string without finding a closing ]
-                    # Do not treat this as a matching group, but as a literal [
-                    pat += re.escape(char)
-                else:
-                    # Grab the insides of the [brackets]
-                    inner = chunk[i + 1 : inner_i]
-                    char_class = ''
-
-                    # Class negation
-                    if inner[0] == '!':
-                        char_class = '^'
-                        inner = inner[1:]
-
-                    char_class += re.escape(inner)
-                    pat += f'[{char_class}]'
-
-                    # Skip to the end ]
-                    i = inner_i
-            else:
-                pat += re.escape(char)
-            i += 1
-
-        # Join each chunk with the dir separator
-        if not last_chunk:
-            pat += sep
-
-    pat += r'\Z'
-    return re.compile(pat, flags=re.MULTILINE | re.DOTALL)
-
-
-class InfoCommon:
-    tag_build = None
-    tag_date = None
-
-    @property
-    def name(self):
-        return _normalization.safe_name(self.distribution.get_name())
-
-    def tagged_version(self):
-        tagged = self._maybe_tag(self.distribution.get_version())
-        return _normalization.safe_version(tagged)
-
-    def _maybe_tag(self, version):
-        """
-        egg_info may be called more than once for a distribution,
-        in which case the version string already contains all tags.
-        """
-        return (
-            version
-            if self.vtags and self._already_tagged(version)
-            else version + self.vtags
-        )
-
-    def _already_tagged(self, version: str) -> bool:
-        # Depending on their format, tags may change with version normalization.
-        # So in addition the regular tags, we have to search for the normalized ones.
-        return version.endswith(self.vtags) or version.endswith(self._safe_tags())
-
-    def _safe_tags(self) -> str:
-        # To implement this we can rely on `safe_version` pretending to be version 0
-        # followed by tags. Then we simply discard the starting 0 (fake version number)
-        try:
-            return _normalization.safe_version(f"0{self.vtags}")[1:]
-        except packaging.version.InvalidVersion:
-            return _normalization.safe_name(self.vtags.replace(' ', '.'))
-
-    def tags(self) -> str:
-        version = ''
-        if self.tag_build:
-            version += self.tag_build
-        if self.tag_date:
-            version += time.strftime("%Y%m%d")
-        return version
-
-    vtags = property(tags)
-
-
-class egg_info(InfoCommon, Command):
-    description = "create a distribution's .egg-info directory"
-
-    user_options = [
-        (
-            'egg-base=',
-            'e',
-            "directory containing .egg-info directories"
-            " [default: top of the source tree]",
-        ),
-        ('tag-date', 'd', "Add date stamp (e.g. 20050528) to version number"),
-        ('tag-build=', 'b', "Specify explicit tag to add to version number"),
-        ('no-date', 'D', "Don't include date stamp [default]"),
-    ]
-
-    boolean_options = ['tag-date']
-    negative_opt = {
-        'no-date': 'tag-date',
-    }
-
-    def initialize_options(self):
-        self.egg_base = None
-        self.egg_name = None
-        self.egg_info = None
-        self.egg_version = None
-        self.ignore_egg_info_in_manifest = False
-
-    ####################################
-    # allow the 'tag_svn_revision' to be detected and
-    # set, supporting sdists built on older Setuptools.
-    @property
-    def tag_svn_revision(self) -> None:
-        pass
-
-    @tag_svn_revision.setter
-    def tag_svn_revision(self, value):
-        pass
-
-    ####################################
-
-    def save_version_info(self, filename) -> None:
-        """
-        Materialize the value of date into the
-        build tag. Install build keys in a deterministic order
-        to avoid arbitrary reordering on subsequent builds.
-        """
-        # follow the order these keys would have been added
-        # when PYTHONHASHSEED=0
-        egg_info = dict(tag_build=self.tags(), tag_date=0)
-        edit_config(filename, dict(egg_info=egg_info))
-
-    def finalize_options(self) -> None:
-        # Note: we need to capture the current value returned
-        # by `self.tagged_version()`, so we can later update
-        # `self.distribution.metadata.version` without
-        # repercussions.
-        self.egg_name = self.name
-        self.egg_version = self.tagged_version()
-        parsed_version = packaging.version.Version(self.egg_version)
-
-        try:
-            is_version = isinstance(parsed_version, packaging.version.Version)
-            spec = "%s==%s" if is_version else "%s===%s"
-            packaging.requirements.Requirement(spec % (self.egg_name, self.egg_version))
-        except ValueError as e:
-            raise distutils.errors.DistutilsOptionError(
-                f"Invalid distribution name or version syntax: {self.egg_name}-{self.egg_version}"
-            ) from e
-
-        if self.egg_base is None:
-            dirs = self.distribution.package_dir
-            self.egg_base = (dirs or {}).get('', os.curdir)
-
-        self.ensure_dirname('egg_base')
-        self.egg_info = _normalization.filename_component(self.egg_name) + '.egg-info'
-        if self.egg_base != os.curdir:
-            self.egg_info = os.path.join(self.egg_base, self.egg_info)
-
-        # Set package version for the benefit of dumber commands
-        # (e.g. sdist, bdist_wininst, etc.)
-        #
-        self.distribution.metadata.version = self.egg_version
-
-    def _get_egg_basename(self, py_version=PY_MAJOR, platform=None):
-        """Compute filename of the output egg. Private API."""
-        return _egg_basename(self.egg_name, self.egg_version, py_version, platform)
-
-    def write_or_delete_file(self, what, filename, data, force: bool = False) -> None:
-        """Write `data` to `filename` or delete if empty
-
-        If `data` is non-empty, this routine is the same as ``write_file()``.
-        If `data` is empty but not ``None``, this is the same as calling
-        ``delete_file(filename)`.  If `data` is ``None``, then this is a no-op
-        unless `filename` exists, in which case a warning is issued about the
-        orphaned file (if `force` is false), or deleted (if `force` is true).
-        """
-        if data:
-            self.write_file(what, filename, data)
-        elif os.path.exists(filename):
-            if data is None and not force:
-                log.warn("%s not set in setup(), but %s exists", what, filename)
-                return
-            else:
-                self.delete_file(filename)
-
-    def write_file(self, what, filename, data) -> None:
-        """Write `data` to `filename` (if not a dry run) after announcing it
-
-        `what` is used in a log message to identify what is being written
-        to the file.
-        """
-        log.info("writing %s to %s", what, filename)
-        data = data.encode("utf-8")
-        if not self.dry_run:
-            f = open(filename, 'wb')
-            f.write(data)
-            f.close()
-
-    def delete_file(self, filename) -> None:
-        """Delete `filename` (if not a dry run) after announcing it"""
-        log.info("deleting %s", filename)
-        if not self.dry_run:
-            os.unlink(filename)
-
-    def run(self) -> None:
-        # Pre-load to avoid iterating over entry-points while an empty .egg-info
-        # exists in sys.path. See pypa/pyproject-hooks#206
-        writers = list(metadata.entry_points(group='egg_info.writers'))
-
-        self.mkpath(self.egg_info)
-        try:
-            os.utime(self.egg_info, None)
-        except OSError as e:
-            msg = f"Cannot update time stamp of directory '{self.egg_info}'"
-            raise distutils.errors.DistutilsFileError(msg) from e
-        for ep in writers:
-            writer = ep.load()
-            writer(self, ep.name, os.path.join(self.egg_info, ep.name))
-
-        # Get rid of native_libs.txt if it was put there by older bdist_egg
-        nl = os.path.join(self.egg_info, "native_libs.txt")
-        if os.path.exists(nl):
-            self.delete_file(nl)
-
-        self.find_sources()
-
-    def find_sources(self) -> None:
-        """Generate SOURCES.txt manifest file"""
-        manifest_filename = os.path.join(self.egg_info, "SOURCES.txt")
-        mm = manifest_maker(self.distribution)
-        mm.ignore_egg_info_dir = self.ignore_egg_info_in_manifest
-        mm.manifest = manifest_filename
-        mm.run()
-        self.filelist = mm.filelist
-
-
-class FileList(_FileList):
-    # Implementations of the various MANIFEST.in commands
-
-    def __init__(
-        self, warn=None, debug_print=None, ignore_egg_info_dir: bool = False
-    ) -> None:
-        super().__init__(warn, debug_print)
-        self.ignore_egg_info_dir = ignore_egg_info_dir
-
-    def process_template_line(self, line) -> None:
-        # Parse the line: split it up, make sure the right number of words
-        # is there, and return the relevant words.  'action' is always
-        # defined: it's the first word of the line.  Which of the other
-        # three are defined depends on the action; it'll be either
-        # patterns, (dir and patterns), or (dir_pattern).
-        (action, patterns, dir, dir_pattern) = self._parse_template_line(line)
-
-        action_map: dict[str, Callable] = {
-            'include': self.include,
-            'exclude': self.exclude,
-            'global-include': self.global_include,
-            'global-exclude': self.global_exclude,
-            'recursive-include': functools.partial(
-                self.recursive_include,
-                dir,
-            ),
-            'recursive-exclude': functools.partial(
-                self.recursive_exclude,
-                dir,
-            ),
-            'graft': self.graft,
-            'prune': self.prune,
-        }
-        log_map = {
-            'include': "warning: no files found matching '%s'",
-            'exclude': ("warning: no previously-included files found matching '%s'"),
-            'global-include': (
-                "warning: no files found matching '%s' anywhere in distribution"
-            ),
-            'global-exclude': (
-                "warning: no previously-included files matching "
-                "'%s' found anywhere in distribution"
-            ),
-            'recursive-include': (
-                "warning: no files found matching '%s' under directory '%s'"
-            ),
-            'recursive-exclude': (
-                "warning: no previously-included files matching "
-                "'%s' found under directory '%s'"
-            ),
-            'graft': "warning: no directories found matching '%s'",
-            'prune': "no previously-included directories found matching '%s'",
-        }
-
-        try:
-            process_action = action_map[action]
-        except KeyError:
-            msg = f"Invalid MANIFEST.in: unknown action {action!r} in {line!r}"
-            raise DistutilsInternalError(msg) from None
-
-        # OK, now we know that the action is valid and we have the
-        # right number of words on the line for that action -- so we
-        # can proceed with minimal error-checking.
-
-        action_is_recursive = action.startswith('recursive-')
-        if action in {'graft', 'prune'}:
-            patterns = [dir_pattern]
-        extra_log_args = (dir,) if action_is_recursive else ()
-        log_tmpl = log_map[action]
-
-        self.debug_print(
-            ' '.join(
-                [action] + ([dir] if action_is_recursive else []) + patterns,
-            )
-        )
-        for pattern in patterns:
-            if not process_action(pattern):
-                log.warn(log_tmpl, pattern, *extra_log_args)
-
-    def _remove_files(self, predicate):
-        """
-        Remove all files from the file list that match the predicate.
-        Return True if any matching files were removed
-        """
-        found = False
-        for i in range(len(self.files) - 1, -1, -1):
-            if predicate(self.files[i]):
-                self.debug_print(" removing " + self.files[i])
-                del self.files[i]
-                found = True
-        return found
-
-    def include(self, pattern):
-        """Include files that match 'pattern'."""
-        found = [f for f in glob(pattern) if not os.path.isdir(f)]
-        self.extend(found)
-        return bool(found)
-
-    def exclude(self, pattern):
-        """Exclude files that match 'pattern'."""
-        match = translate_pattern(pattern)
-        return self._remove_files(match.match)
-
-    def recursive_include(self, dir, pattern):
-        """
-        Include all files anywhere in 'dir/' that match the pattern.
-        """
-        full_pattern = os.path.join(dir, '**', pattern)
-        found = [f for f in glob(full_pattern, recursive=True) if not os.path.isdir(f)]
-        self.extend(found)
-        return bool(found)
-
-    def recursive_exclude(self, dir, pattern):
-        """
-        Exclude any file anywhere in 'dir/' that match the pattern.
-        """
-        match = translate_pattern(os.path.join(dir, '**', pattern))
-        return self._remove_files(match.match)
-
-    def graft(self, dir):
-        """Include all files from 'dir/'."""
-        found = [
-            item
-            for match_dir in glob(dir)
-            for item in distutils.filelist.findall(match_dir)
-        ]
-        self.extend(found)
-        return bool(found)
-
-    def prune(self, dir):
-        """Filter out files from 'dir/'."""
-        match = translate_pattern(os.path.join(dir, '**'))
-        return self._remove_files(match.match)
-
-    def global_include(self, pattern):
-        """
-        Include all files anywhere in the current directory that match the
-        pattern. This is very inefficient on large file trees.
-        """
-        if self.allfiles is None:
-            self.findall()
-        match = translate_pattern(os.path.join('**', pattern))
-        found = [f for f in self.allfiles if match.match(f)]
-        self.extend(found)
-        return bool(found)
-
-    def global_exclude(self, pattern):
-        """
-        Exclude all files anywhere that match the pattern.
-        """
-        match = translate_pattern(os.path.join('**', pattern))
-        return self._remove_files(match.match)
-
-    def append(self, item) -> None:
-        if item.endswith('\r'):  # Fix older sdists built on Windows
-            item = item[:-1]
-        path = convert_path(item)
-
-        if self._safe_path(path):
-            self.files.append(path)
-
-    def extend(self, paths) -> None:
-        self.files.extend(filter(self._safe_path, paths))
-
-    def _repair(self):
-        """
-        Replace self.files with only safe paths
-
-        Because some owners of FileList manipulate the underlying
-        ``files`` attribute directly, this method must be called to
-        repair those paths.
-        """
-        self.files = list(filter(self._safe_path, self.files))
-
-    def _safe_path(self, path):
-        enc_warn = "'%s' not %s encodable -- skipping"
-
-        # To avoid accidental trans-codings errors, first to unicode
-        u_path = unicode_utils.filesys_decode(path)
-        if u_path is None:
-            log.warn(f"'{path}' in unexpected encoding -- skipping")
-            return False
-
-        # Must ensure utf-8 encodability
-        utf8_path = unicode_utils.try_encode(u_path, "utf-8")
-        if utf8_path is None:
-            log.warn(enc_warn, path, 'utf-8')
-            return False
-
-        try:
-            # ignore egg-info paths
-            is_egg_info = ".egg-info" in u_path or b".egg-info" in utf8_path
-            if self.ignore_egg_info_dir and is_egg_info:
-                return False
-            # accept is either way checks out
-            if os.path.exists(u_path) or os.path.exists(utf8_path):
-                return True
-        # this will catch any encode errors decoding u_path
-        except UnicodeEncodeError:
-            log.warn(enc_warn, path, sys.getfilesystemencoding())
-
-
-class manifest_maker(sdist):
-    template = "MANIFEST.in"
-
-    def initialize_options(self) -> None:
-        self.use_defaults = True
-        self.prune = True
-        self.manifest_only = True
-        self.force_manifest = True
-        self.ignore_egg_info_dir = False
-
-    def finalize_options(self) -> None:
-        pass
-
-    def run(self) -> None:
-        self.filelist = FileList(ignore_egg_info_dir=self.ignore_egg_info_dir)
-        if not os.path.exists(self.manifest):
-            self.write_manifest()  # it must exist so it'll get in the list
-        self.add_defaults()
-        if os.path.exists(self.template):
-            self.read_template()
-        self.add_license_files()
-        self._add_referenced_files()
-        self.prune_file_list()
-        self.filelist.sort()
-        self.filelist.remove_duplicates()
-        self.write_manifest()
-
-    def _manifest_normalize(self, path):
-        path = unicode_utils.filesys_decode(path)
-        return path.replace(os.sep, '/')
-
-    def write_manifest(self) -> None:
-        """
-        Write the file list in 'self.filelist' to the manifest file
-        named by 'self.manifest'.
-        """
-        self.filelist._repair()
-
-        # Now _repairs should encodability, but not unicode
-        files = [self._manifest_normalize(f) for f in self.filelist.files]
-        msg = f"writing manifest file '{self.manifest}'"
-        self.execute(write_file, (self.manifest, files), msg)
-
-    def warn(self, msg) -> None:
-        if not self._should_suppress_warning(msg):
-            sdist.warn(self, msg)
-
-    @staticmethod
-    def _should_suppress_warning(msg):
-        """
-        suppress missing-file warnings from sdist
-        """
-        return re.match(r"standard file .*not found", msg)
-
-    def add_defaults(self) -> None:
-        sdist.add_defaults(self)
-        self.filelist.append(self.template)
-        self.filelist.append(self.manifest)
-        rcfiles = list(walk_revctrl())
-        if rcfiles:
-            self.filelist.extend(rcfiles)
-        elif os.path.exists(self.manifest):
-            self.read_manifest()
-
-        if os.path.exists("setup.py"):
-            # setup.py should be included by default, even if it's not
-            # the script called to create the sdist
-            self.filelist.append("setup.py")
-
-        ei_cmd = self.get_finalized_command('egg_info')
-        self.filelist.graft(ei_cmd.egg_info)
-
-    def add_license_files(self) -> None:
-        license_files = self.distribution.metadata.license_files or []
-        for lf in license_files:
-            log.info("adding license file '%s'", lf)
-        self.filelist.extend(license_files)
-
-    def _add_referenced_files(self):
-        """Add files referenced by the config (e.g. `file:` directive) to filelist"""
-        referenced = getattr(self.distribution, '_referenced_files', [])
-        # ^-- fallback if dist comes from distutils or is a custom class
-        for rf in referenced:
-            log.debug("adding file referenced by config '%s'", rf)
-        self.filelist.extend(referenced)
-
-    def _safe_data_files(self, build_py):
-        """
-        The parent class implementation of this method
-        (``sdist``) will try to include data files, which
-        might cause recursion problems when
-        ``include_package_data=True``.
-
-        Therefore, avoid triggering any attempt of
-        analyzing/building the manifest again.
-        """
-        if hasattr(build_py, 'get_data_files_without_manifest'):
-            return build_py.get_data_files_without_manifest()
-
-        SetuptoolsDeprecationWarning.emit(
-            "`build_py` command does not inherit from setuptools' `build_py`.",
-            """
-            Custom 'build_py' does not implement 'get_data_files_without_manifest'.
-            Please extend command classes from setuptools instead of distutils.
-            """,
-            see_url="https://peps.python.org/pep-0632/",
-            # due_date not defined yet, old projects might still do it?
-        )
-        return build_py.get_data_files()
-
-
-def write_file(filename, contents) -> None:
-    """Create a file with the specified name and write 'contents' (a
-    sequence of strings without line terminators) to it.
-    """
-    contents = "\n".join(contents)
-
-    # assuming the contents has been vetted for utf-8 encoding
-    contents = contents.encode("utf-8")
-
-    with open(filename, "wb") as f:  # always write POSIX-style manifest
-        f.write(contents)
-
-
-def write_pkg_info(cmd, basename, filename) -> None:
-    log.info("writing %s", filename)
-    if not cmd.dry_run:
-        metadata = cmd.distribution.metadata
-        metadata.version, oldver = cmd.egg_version, metadata.version
-        metadata.name, oldname = cmd.egg_name, metadata.name
-
-        try:
-            # write unescaped data to PKG-INFO, so older pkg_resources
-            # can still parse it
-            metadata.write_pkg_info(cmd.egg_info)
-        finally:
-            metadata.name, metadata.version = oldname, oldver
-
-        safe = getattr(cmd.distribution, 'zip_safe', None)
-
-        bdist_egg.write_safety_flag(cmd.egg_info, safe)
-
-
-def warn_depends_obsolete(cmd, basename, filename) -> None:
-    """
-    Unused: left to avoid errors when updating (from source) from <= 67.8.
-    Old installations have a .dist-info directory with the entry-point
-    ``depends.txt = setuptools.command.egg_info:warn_depends_obsolete``.
-    This may trigger errors when running the first egg_info in build_meta.
-    TODO: Remove this function in a version sufficiently > 68.
-    """
-
-
-# Export API used in entry_points
-write_requirements = _requirestxt.write_requirements
-write_setup_requirements = _requirestxt.write_setup_requirements
-
-
-def write_toplevel_names(cmd, basename, filename) -> None:
-    pkgs = dict.fromkeys([
-        k.split('.', 1)[0] for k in cmd.distribution.iter_distribution_names()
-    ])
-    cmd.write_file("top-level names", filename, '\n'.join(sorted(pkgs)) + '\n')
-
-
-def overwrite_arg(cmd, basename, filename) -> None:
-    write_arg(cmd, basename, filename, True)
-
-
-def write_arg(cmd, basename, filename, force: bool = False) -> None:
-    argname = os.path.splitext(basename)[0]
-    value = getattr(cmd.distribution, argname, None)
-    if value is not None:
-        value = '\n'.join(value) + '\n'
-    cmd.write_or_delete_file(argname, filename, value, force)
-
-
-def write_entries(cmd, basename, filename) -> None:
-    eps = _entry_points.load(cmd.distribution.entry_points)
-    defn = _entry_points.render(eps)
-    cmd.write_or_delete_file('entry points', filename, defn, True)
-
-
-def _egg_basename(egg_name, egg_version, py_version=None, platform=None):
-    """Compute filename of the output egg. Private API."""
-    name = _normalization.filename_component(egg_name)
-    version = _normalization.filename_component(egg_version)
-    egg = f"{name}-{version}-py{py_version or PY_MAJOR}"
-    if platform:
-        egg += f"-{platform}"
-    return egg
-
-
-class EggInfoDeprecationWarning(SetuptoolsDeprecationWarning):
-    """Deprecated behavior warning for EggInfo, bypassing suppression."""
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/install.py b/llmlab/lib/python3.12/site-packages/setuptools/command/install.py
deleted file mode 100644
index 15ef364..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/install.py
+++ /dev/null
@@ -1,183 +0,0 @@
-from __future__ import annotations
-
-import glob
-import inspect
-import platform
-from collections.abc import Callable
-from typing import TYPE_CHECKING, Any, ClassVar, cast
-
-import setuptools
-
-from ..dist import Distribution
-from ..warnings import SetuptoolsDeprecationWarning, SetuptoolsWarning
-from .bdist_egg import bdist_egg as bdist_egg_cls
-
-import distutils.command.install as orig
-from distutils.errors import DistutilsArgError
-
-if TYPE_CHECKING:
-    # This is only used for a type-cast, don't import at runtime or it'll cause deprecation warnings
-    from .easy_install import easy_install as easy_install_cls
-else:
-    easy_install_cls = None
-
-
-def __getattr__(name: str):  # pragma: no cover
-    if name == "_install":
-        SetuptoolsDeprecationWarning.emit(
-            "`setuptools.command._install` was an internal implementation detail "
-            + "that was left in for numpy<1.9 support.",
-            due_date=(2025, 5, 2),  # Originally added on 2024-11-01
-        )
-        return orig.install
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
-
-
-class install(orig.install):
-    """Use easy_install to install the package, w/dependencies"""
-
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-
-    user_options = orig.install.user_options + [
-        ('old-and-unmanageable', None, "Try not to use this!"),
-        (
-            'single-version-externally-managed',
-            None,
-            "used by system package builders to create 'flat' eggs",
-        ),
-    ]
-    boolean_options = orig.install.boolean_options + [
-        'old-and-unmanageable',
-        'single-version-externally-managed',
-    ]
-    # Type the same as distutils.command.install.install.sub_commands
-    # Must keep the second tuple item potentially None due to invariance
-    new_commands: ClassVar[list[tuple[str, Callable[[Any], bool] | None]]] = [
-        ('install_egg_info', lambda self: True),
-        ('install_scripts', lambda self: True),
-    ]
-    _nc = dict(new_commands)
-
-    def initialize_options(self):
-        SetuptoolsDeprecationWarning.emit(
-            "setup.py install is deprecated.",
-            """
-            Please avoid running ``setup.py`` directly.
-            Instead, use pypa/build, pypa/installer or other
-            standards-based tools.
-            """,
-            see_url="https://blog.ganssle.io/articles/2021/10/setup-py-deprecated.html",
-            # TODO: Document how to bootstrap setuptools without install
-            #       (e.g. by unzipping the wheel file)
-            #       and then add a due_date to this warning.
-        )
-
-        super().initialize_options()
-        self.old_and_unmanageable = None
-        self.single_version_externally_managed = None
-
-    def finalize_options(self) -> None:
-        super().finalize_options()
-        if self.root:
-            self.single_version_externally_managed = True
-        elif self.single_version_externally_managed:
-            if not self.root and not self.record:
-                raise DistutilsArgError(
-                    "You must specify --record or --root when building system packages"
-                )
-
-    def handle_extra_path(self):
-        if self.root or self.single_version_externally_managed:
-            # explicit backward-compatibility mode, allow extra_path to work
-            return orig.install.handle_extra_path(self)
-
-        # Ignore extra_path when installing an egg (or being run by another
-        # command without --root or --single-version-externally-managed
-        self.path_file = None
-        self.extra_dirs = ''
-        return None
-
-    def run(self):
-        # Explicit request for old-style install?  Just do it
-        if self.old_and_unmanageable or self.single_version_externally_managed:
-            return super().run()
-
-        if not self._called_from_setup(inspect.currentframe()):
-            # Run in backward-compatibility mode to support bdist_* commands.
-            super().run()
-        else:
-            self.do_egg_install()
-
-        return None
-
-    @staticmethod
-    def _called_from_setup(run_frame):
-        """
-        Attempt to detect whether run() was called from setup() or by another
-        command.  If called by setup(), the parent caller will be the
-        'run_command' method in 'distutils.dist', and *its* caller will be
-        the 'run_commands' method.  If called any other way, the
-        immediate caller *might* be 'run_command', but it won't have been
-        called by 'run_commands'. Return True in that case or if a call stack
-        is unavailable. Return False otherwise.
-        """
-        if run_frame is None:
-            msg = "Call stack not available. bdist_* commands may fail."
-            SetuptoolsWarning.emit(msg)
-            if platform.python_implementation() == 'IronPython':
-                msg = "For best results, pass -X:Frames to enable call stack."
-                SetuptoolsWarning.emit(msg)
-            return True
-
-        frames = inspect.getouterframes(run_frame)
-        for frame in frames[2:4]:
-            (caller,) = frame[:1]
-            info = inspect.getframeinfo(caller)
-            caller_module = caller.f_globals.get('__name__', '')
-
-            if caller_module == "setuptools.dist" and info.function == "run_command":
-                # Starting from v61.0.0 setuptools overwrites dist.run_command
-                continue
-
-            return caller_module == 'distutils.dist' and info.function == 'run_commands'
-
-        return False
-
-    def do_egg_install(self) -> None:
-        easy_install = self.distribution.get_command_class('easy_install')
-
-        cmd = cast(
-            # We'd want to cast easy_install as type[easy_install_cls] but a bug in
-            # mypy makes it think easy_install() returns a Command on Python 3.12+
-            # https://github.com/python/mypy/issues/18088
-            easy_install_cls,
-            easy_install(  # type: ignore[call-arg]
-                self.distribution,
-                args="x",
-                root=self.root,
-                record=self.record,
-            ),
-        )
-        cmd.ensure_finalized()  # finalize before bdist_egg munges install cmd
-        cmd.always_copy_from = '.'  # make sure local-dir eggs get installed
-
-        # pick up setup-dir .egg files only: no .egg-info
-        cmd.package_index.scan(glob.glob('*.egg'))
-
-        self.run_command('bdist_egg')
-        bdist_egg = cast(bdist_egg_cls, self.distribution.get_command_obj('bdist_egg'))
-        args = [bdist_egg.egg_output]
-
-        if setuptools.bootstrap_install_from:
-            # Bootstrap self-installation of setuptools
-            args.insert(0, setuptools.bootstrap_install_from)
-
-        cmd.args = args
-        cmd.run(show_deprecation=False)
-        setuptools.bootstrap_install_from = None
-
-
-# XXX Python 3.1 doesn't see _nc if this is inside the class
-install.sub_commands = [
-    cmd for cmd in orig.install.sub_commands if cmd[0] not in install._nc
-] + install.new_commands
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/install_egg_info.py b/llmlab/lib/python3.12/site-packages/setuptools/command/install_egg_info.py
deleted file mode 100644
index 44f22cc..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/install_egg_info.py
+++ /dev/null
@@ -1,58 +0,0 @@
-import os
-
-from setuptools import Command, namespaces
-from setuptools.archive_util import unpack_archive
-
-from .._path import ensure_directory
-
-from distutils import dir_util, log
-
-
-class install_egg_info(namespaces.Installer, Command):
-    """Install an .egg-info directory for the package"""
-
-    description = "Install an .egg-info directory for the package"
-
-    user_options = [
-        ('install-dir=', 'd', "directory to install to"),
-    ]
-
-    def initialize_options(self):
-        self.install_dir = None
-
-    def finalize_options(self) -> None:
-        self.set_undefined_options('install_lib', ('install_dir', 'install_dir'))
-        ei_cmd = self.get_finalized_command("egg_info")
-        basename = f"{ei_cmd._get_egg_basename()}.egg-info"
-        self.source = ei_cmd.egg_info
-        self.target = os.path.join(self.install_dir, basename)
-        self.outputs: list[str] = []
-
-    def run(self) -> None:
-        self.run_command('egg_info')
-        if os.path.isdir(self.target) and not os.path.islink(self.target):
-            dir_util.remove_tree(self.target, dry_run=self.dry_run)
-        elif os.path.exists(self.target):
-            self.execute(os.unlink, (self.target,), "Removing " + self.target)
-        if not self.dry_run:
-            ensure_directory(self.target)
-        self.execute(self.copytree, (), f"Copying {self.source} to {self.target}")
-        self.install_namespaces()
-
-    def get_outputs(self):
-        return self.outputs
-
-    def copytree(self) -> None:
-        # Copy the .egg-info tree to site-packages
-        def skimmer(src, dst):
-            # filter out source-control directories; note that 'src' is always
-            # a '/'-separated path, regardless of platform.  'dst' is a
-            # platform-specific path.
-            for skip in '.svn/', 'CVS/':
-                if src.startswith(skip) or '/' + skip in src:
-                    return None
-            self.outputs.append(dst)
-            log.debug("Copying %s to %s", src, dst)
-            return dst
-
-        unpack_archive(self.source, self.target, skimmer)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/install_lib.py b/llmlab/lib/python3.12/site-packages/setuptools/command/install_lib.py
deleted file mode 100644
index 8e1e072..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/install_lib.py
+++ /dev/null
@@ -1,137 +0,0 @@
-from __future__ import annotations
-
-import os
-import sys
-from itertools import product, starmap
-
-from .._path import StrPath
-from ..dist import Distribution
-
-import distutils.command.install_lib as orig
-
-
-class install_lib(orig.install_lib):
-    """Don't add compiled flags to filenames of non-Python files"""
-
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-
-    def run(self) -> None:
-        self.build()
-        outfiles = self.install()
-        if outfiles is not None:
-            # always compile, in case we have any extension stubs to deal with
-            self.byte_compile(outfiles)
-
-    def get_exclusions(self):
-        """
-        Return a collections.Sized collections.Container of paths to be
-        excluded for single_version_externally_managed installations.
-        """
-        all_packages = (
-            pkg
-            for ns_pkg in self._get_SVEM_NSPs()
-            for pkg in self._all_packages(ns_pkg)
-        )
-
-        excl_specs = product(all_packages, self._gen_exclusion_paths())
-        return set(starmap(self._exclude_pkg_path, excl_specs))
-
-    def _exclude_pkg_path(self, pkg, exclusion_path):
-        """
-        Given a package name and exclusion path within that package,
-        compute the full exclusion path.
-        """
-        parts = pkg.split('.') + [exclusion_path]
-        return os.path.join(self.install_dir, *parts)
-
-    @staticmethod
-    def _all_packages(pkg_name):
-        """
-        >>> list(install_lib._all_packages('foo.bar.baz'))
-        ['foo.bar.baz', 'foo.bar', 'foo']
-        """
-        while pkg_name:
-            yield pkg_name
-            pkg_name, _sep, _child = pkg_name.rpartition('.')
-
-    def _get_SVEM_NSPs(self):
-        """
-        Get namespace packages (list) but only for
-        single_version_externally_managed installations and empty otherwise.
-        """
-        # TODO: is it necessary to short-circuit here? i.e. what's the cost
-        # if get_finalized_command is called even when namespace_packages is
-        # False?
-        if not self.distribution.namespace_packages:
-            return []
-
-        install_cmd = self.get_finalized_command('install')
-        svem = install_cmd.single_version_externally_managed
-
-        return self.distribution.namespace_packages if svem else []
-
-    @staticmethod
-    def _gen_exclusion_paths():
-        """
-        Generate file paths to be excluded for namespace packages (bytecode
-        cache files).
-        """
-        # always exclude the package module itself
-        yield '__init__.py'
-
-        yield '__init__.pyc'
-        yield '__init__.pyo'
-
-        if not hasattr(sys, 'implementation'):
-            return
-
-        base = os.path.join('__pycache__', '__init__.' + sys.implementation.cache_tag)
-        yield base + '.pyc'
-        yield base + '.pyo'
-        yield base + '.opt-1.pyc'
-        yield base + '.opt-2.pyc'
-
-    def copy_tree(
-        self,
-        infile: StrPath,
-        outfile: str,
-        # override: Using actual booleans
-        preserve_mode: bool = True,  # type: ignore[override]
-        preserve_times: bool = True,  # type: ignore[override]
-        preserve_symlinks: bool = False,  # type: ignore[override]
-        level: object = 1,
-    ) -> list[str]:
-        assert preserve_mode
-        assert preserve_times
-        assert not preserve_symlinks
-        exclude = self.get_exclusions()
-
-        if not exclude:
-            return orig.install_lib.copy_tree(self, infile, outfile)
-
-        # Exclude namespace package __init__.py* files from the output
-
-        from setuptools.archive_util import unpack_directory
-
-        from distutils import log
-
-        outfiles: list[str] = []
-
-        def pf(src: str, dst: str):
-            if dst in exclude:
-                log.warn("Skipping installation of %s (namespace package)", dst)
-                return False
-
-            log.info("copying %s -> %s", src, os.path.dirname(dst))
-            outfiles.append(dst)
-            return dst
-
-        unpack_directory(infile, outfile, pf)
-        return outfiles
-
-    def get_outputs(self):
-        outputs = orig.install_lib.get_outputs(self)
-        exclude = self.get_exclusions()
-        if exclude:
-            return [f for f in outputs if f not in exclude]
-        return outputs
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/install_scripts.py b/llmlab/lib/python3.12/site-packages/setuptools/command/install_scripts.py
deleted file mode 100644
index 4401cf6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/install_scripts.py
+++ /dev/null
@@ -1,73 +0,0 @@
-from __future__ import annotations
-
-import os
-import sys
-
-from .._path import ensure_directory
-from ..dist import Distribution
-
-import distutils.command.install_scripts as orig
-from distutils import log
-
-
-class install_scripts(orig.install_scripts):
-    """Do normal script install, plus any egg_info wrapper scripts"""
-
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-
-    def initialize_options(self) -> None:
-        orig.install_scripts.initialize_options(self)
-        self.no_ep = False
-
-    def run(self) -> None:
-        self.run_command("egg_info")
-        if self.distribution.scripts:
-            orig.install_scripts.run(self)  # run first to set up self.outfiles
-        else:
-            self.outfiles: list[str] = []
-        if self.no_ep:
-            # don't install entry point scripts into .egg file!
-            return
-        self._install_ep_scripts()
-
-    def _install_ep_scripts(self):
-        # Delay import side-effects
-        from pkg_resources import Distribution, PathMetadata
-
-        from . import easy_install as ei
-
-        ei_cmd = self.get_finalized_command("egg_info")
-        dist = Distribution(
-            ei_cmd.egg_base,
-            PathMetadata(ei_cmd.egg_base, ei_cmd.egg_info),
-            ei_cmd.egg_name,
-            ei_cmd.egg_version,
-        )
-        bs_cmd = self.get_finalized_command('build_scripts')
-        exec_param = getattr(bs_cmd, 'executable', None)
-        writer = ei.ScriptWriter
-        if exec_param == sys.executable:
-            # In case the path to the Python executable contains a space, wrap
-            # it so it's not split up.
-            exec_param = [exec_param]
-        # resolve the writer to the environment
-        writer = writer.best()
-        cmd = writer.command_spec_class.best().from_param(exec_param)
-        for args in writer.get_args(dist, cmd.as_header()):
-            self.write_script(*args)
-
-    def write_script(self, script_name, contents, mode: str = "t", *ignored) -> None:
-        """Write an executable file to the scripts directory"""
-        from setuptools.command.easy_install import chmod, current_umask
-
-        log.info("Installing %s script to %s", script_name, self.install_dir)
-        target = os.path.join(self.install_dir, script_name)
-        self.outfiles.append(target)
-
-        encoding = None if "b" in mode else "utf-8"
-        mask = current_umask()
-        if not self.dry_run:
-            ensure_directory(target)
-            with open(target, "w" + mode, encoding=encoding) as f:
-                f.write(contents)
-            chmod(target, 0o777 - mask)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/launcher manifest.xml b/llmlab/lib/python3.12/site-packages/setuptools/command/launcher manifest.xml
deleted file mode 100644
index 5972a96..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/launcher manifest.xml	
+++ /dev/null
@@ -1,15 +0,0 @@
-
-
-    
-    
-    
-        
-            
-                
-            
-        
-    
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/rotate.py b/llmlab/lib/python3.12/site-packages/setuptools/command/rotate.py
deleted file mode 100644
index acdce07..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/rotate.py
+++ /dev/null
@@ -1,65 +0,0 @@
-from __future__ import annotations
-
-import os
-from typing import ClassVar
-
-from .. import Command, _shutil
-
-from distutils import log
-from distutils.errors import DistutilsOptionError
-from distutils.util import convert_path
-
-
-class rotate(Command):
-    """Delete older distributions"""
-
-    description = "delete older distributions, keeping N newest files"
-    user_options = [
-        ('match=', 'm', "patterns to match (required)"),
-        ('dist-dir=', 'd', "directory where the distributions are"),
-        ('keep=', 'k', "number of matching distributions to keep"),
-    ]
-
-    boolean_options: ClassVar[list[str]] = []
-
-    def initialize_options(self):
-        self.match = None
-        self.dist_dir = None
-        self.keep = None
-
-    def finalize_options(self) -> None:
-        if self.match is None:
-            raise DistutilsOptionError(
-                "Must specify one or more (comma-separated) match patterns "
-                "(e.g. '.zip' or '.egg')"
-            )
-        if self.keep is None:
-            raise DistutilsOptionError("Must specify number of files to keep")
-        try:
-            self.keep = int(self.keep)
-        except ValueError as e:
-            raise DistutilsOptionError("--keep must be an integer") from e
-        if isinstance(self.match, str):
-            self.match = [convert_path(p.strip()) for p in self.match.split(',')]
-        self.set_undefined_options('bdist', ('dist_dir', 'dist_dir'))
-
-    def run(self) -> None:
-        self.run_command("egg_info")
-        from glob import glob
-
-        for pattern in self.match:
-            pattern = self.distribution.get_name() + '*' + pattern
-            files = glob(os.path.join(self.dist_dir, pattern))
-            files = [(os.path.getmtime(f), f) for f in files]
-            files.sort()
-            files.reverse()
-
-            log.info("%d file(s) matching %s", len(files), pattern)
-            files = files[self.keep :]
-            for t, f in files:
-                log.info("Deleting %s", f)
-                if not self.dry_run:
-                    if os.path.isdir(f):
-                        _shutil.rmtree(f)
-                    else:
-                        os.unlink(f)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/saveopts.py b/llmlab/lib/python3.12/site-packages/setuptools/command/saveopts.py
deleted file mode 100644
index 2a2cbce..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/saveopts.py
+++ /dev/null
@@ -1,21 +0,0 @@
-from setuptools.command.setopt import edit_config, option_base
-
-
-class saveopts(option_base):
-    """Save command-line options to a file"""
-
-    description = "save supplied options to setup.cfg or other config file"
-
-    def run(self) -> None:
-        dist = self.distribution
-        settings: dict[str, dict[str, str]] = {}
-
-        for cmd in dist.command_options:
-            if cmd == 'saveopts':
-                continue  # don't save our own options!
-
-            for opt, (src, val) in dist.get_option_dict(cmd).items():
-                if src == "command line":
-                    settings.setdefault(cmd, {})[opt] = val
-
-        edit_config(self.filename, settings, self.dry_run)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/sdist.py b/llmlab/lib/python3.12/site-packages/setuptools/command/sdist.py
deleted file mode 100644
index 9631cf3..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/sdist.py
+++ /dev/null
@@ -1,217 +0,0 @@
-from __future__ import annotations
-
-import contextlib
-import os
-import re
-from itertools import chain
-from typing import ClassVar
-
-from .._importlib import metadata
-from ..dist import Distribution
-from .build import _ORIGINAL_SUBCOMMANDS
-
-import distutils.command.sdist as orig
-from distutils import log
-
-_default_revctrl = list
-
-
-def walk_revctrl(dirname=''):
-    """Find all files under revision control"""
-    for ep in metadata.entry_points(group='setuptools.file_finders'):
-        yield from ep.load()(dirname)
-
-
-class sdist(orig.sdist):
-    """Smart sdist that finds anything supported by revision control"""
-
-    user_options = [
-        ('formats=', None, "formats for source distribution (comma-separated list)"),
-        (
-            'keep-temp',
-            'k',
-            "keep the distribution tree around after creating " + "archive file(s)",
-        ),
-        (
-            'dist-dir=',
-            'd',
-            "directory to put the source distribution archive(s) in [default: dist]",
-        ),
-        (
-            'owner=',
-            'u',
-            "Owner name used when creating a tar file [default: current user]",
-        ),
-        (
-            'group=',
-            'g',
-            "Group name used when creating a tar file [default: current group]",
-        ),
-    ]
-
-    distribution: Distribution  # override distutils.dist.Distribution with setuptools.dist.Distribution
-    negative_opt: ClassVar[dict[str, str]] = {}
-
-    README_EXTENSIONS = ['', '.rst', '.txt', '.md']
-    READMES = tuple(f'README{ext}' for ext in README_EXTENSIONS)
-
-    def run(self) -> None:
-        self.run_command('egg_info')
-        ei_cmd = self.get_finalized_command('egg_info')
-        self.filelist = ei_cmd.filelist
-        self.filelist.append(os.path.join(ei_cmd.egg_info, 'SOURCES.txt'))
-        self.check_readme()
-
-        # Run sub commands
-        for cmd_name in self.get_sub_commands():
-            self.run_command(cmd_name)
-
-        self.make_distribution()
-
-        dist_files = getattr(self.distribution, 'dist_files', [])
-        for file in self.archive_files:
-            data = ('sdist', '', file)
-            if data not in dist_files:
-                dist_files.append(data)
-
-    def initialize_options(self) -> None:
-        orig.sdist.initialize_options(self)
-
-    def make_distribution(self) -> None:
-        """
-        Workaround for #516
-        """
-        with self._remove_os_link():
-            orig.sdist.make_distribution(self)
-
-    @staticmethod
-    @contextlib.contextmanager
-    def _remove_os_link():
-        """
-        In a context, remove and restore os.link if it exists
-        """
-
-        class NoValue:
-            pass
-
-        orig_val = getattr(os, 'link', NoValue)
-        try:
-            del os.link
-        except Exception:
-            pass
-        try:
-            yield
-        finally:
-            if orig_val is not NoValue:
-                os.link = orig_val
-
-    def add_defaults(self) -> None:
-        super().add_defaults()
-        self._add_defaults_build_sub_commands()
-
-    def _add_defaults_optional(self):
-        super()._add_defaults_optional()
-        if os.path.isfile('pyproject.toml'):
-            self.filelist.append('pyproject.toml')
-
-    def _add_defaults_python(self):
-        """getting python files"""
-        if self.distribution.has_pure_modules():
-            build_py = self.get_finalized_command('build_py')
-            self.filelist.extend(build_py.get_source_files())
-            self._add_data_files(self._safe_data_files(build_py))
-
-    def _add_defaults_build_sub_commands(self):
-        build = self.get_finalized_command("build")
-        missing_cmds = set(build.get_sub_commands()) - _ORIGINAL_SUBCOMMANDS
-        # ^-- the original built-in sub-commands are already handled by default.
-        cmds = (self.get_finalized_command(c) for c in missing_cmds)
-        files = (c.get_source_files() for c in cmds if hasattr(c, "get_source_files"))
-        self.filelist.extend(chain.from_iterable(files))
-
-    def _safe_data_files(self, build_py):
-        """
-        Since the ``sdist`` class is also used to compute the MANIFEST
-        (via :obj:`setuptools.command.egg_info.manifest_maker`),
-        there might be recursion problems when trying to obtain the list of
-        data_files and ``include_package_data=True`` (which in turn depends on
-        the files included in the MANIFEST).
-
-        To avoid that, ``manifest_maker`` should be able to overwrite this
-        method and avoid recursive attempts to build/analyze the MANIFEST.
-        """
-        return build_py.data_files
-
-    def _add_data_files(self, data_files):
-        """
-        Add data files as found in build_py.data_files.
-        """
-        self.filelist.extend(
-            os.path.join(src_dir, name)
-            for _, src_dir, _, filenames in data_files
-            for name in filenames
-        )
-
-    def _add_defaults_data_files(self):
-        try:
-            super()._add_defaults_data_files()
-        except TypeError:
-            log.warn("data_files contains unexpected objects")
-
-    def prune_file_list(self) -> None:
-        super().prune_file_list()
-        # Prevent accidental inclusion of test-related cache dirs at the project root
-        sep = re.escape(os.sep)
-        self.filelist.exclude_pattern(r"^(\.tox|\.nox|\.venv)" + sep, is_regex=True)
-
-    def check_readme(self) -> None:
-        for f in self.READMES:
-            if os.path.exists(f):
-                return
-        else:
-            self.warn(
-                "standard file not found: should have one of " + ', '.join(self.READMES)
-            )
-
-    def make_release_tree(self, base_dir, files) -> None:
-        orig.sdist.make_release_tree(self, base_dir, files)
-
-        # Save any egg_info command line options used to create this sdist
-        dest = os.path.join(base_dir, 'setup.cfg')
-        if hasattr(os, 'link') and os.path.exists(dest):
-            # unlink and re-copy, since it might be hard-linked, and
-            # we don't want to change the source version
-            os.unlink(dest)
-            self.copy_file('setup.cfg', dest)
-
-        self.get_finalized_command('egg_info').save_version_info(dest)
-
-    def _manifest_is_not_generated(self):
-        # check for special comment used in 2.7.1 and higher
-        if not os.path.isfile(self.manifest):
-            return False
-
-        with open(self.manifest, 'rb') as fp:
-            first_line = fp.readline()
-        return first_line != b'# file GENERATED by distutils, do NOT edit\n'
-
-    def read_manifest(self):
-        """Read the manifest file (named by 'self.manifest') and use it to
-        fill in 'self.filelist', the list of files to include in the source
-        distribution.
-        """
-        log.info("reading manifest file '%s'", self.manifest)
-        manifest = open(self.manifest, 'rb')
-        for bytes_line in manifest:
-            # The manifest must contain UTF-8. See #303.
-            try:
-                line = bytes_line.decode('UTF-8')
-            except UnicodeDecodeError:
-                log.warn(f"{line!r} not UTF-8 decodable -- skipping")
-                continue
-            # ignore comments and blank lines
-            line = line.strip()
-            if line.startswith('#') or not line:
-                continue
-            self.filelist.append(line)
-        manifest.close()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/setopt.py b/llmlab/lib/python3.12/site-packages/setuptools/command/setopt.py
deleted file mode 100644
index 678a059..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/setopt.py
+++ /dev/null
@@ -1,141 +0,0 @@
-import configparser
-import os
-
-from .. import Command
-from ..unicode_utils import _cfg_read_utf8_with_fallback
-
-import distutils
-from distutils import log
-from distutils.errors import DistutilsOptionError
-from distutils.util import convert_path
-
-__all__ = ['config_file', 'edit_config', 'option_base', 'setopt']
-
-
-def config_file(kind="local"):
-    """Get the filename of the distutils, local, global, or per-user config
-
-    `kind` must be one of "local", "global", or "user"
-    """
-    if kind == 'local':
-        return 'setup.cfg'
-    if kind == 'global':
-        return os.path.join(os.path.dirname(distutils.__file__), 'distutils.cfg')
-    if kind == 'user':
-        dot = os.name == 'posix' and '.' or ''
-        return os.path.expanduser(convert_path(f"~/{dot}pydistutils.cfg"))
-    raise ValueError("config_file() type must be 'local', 'global', or 'user'", kind)
-
-
-def edit_config(filename, settings, dry_run=False):
-    """Edit a configuration file to include `settings`
-
-    `settings` is a dictionary of dictionaries or ``None`` values, keyed by
-    command/section name.  A ``None`` value means to delete the entire section,
-    while a dictionary lists settings to be changed or deleted in that section.
-    A setting of ``None`` means to delete that setting.
-    """
-    log.debug("Reading configuration from %s", filename)
-    opts = configparser.RawConfigParser()
-    opts.optionxform = lambda optionstr: optionstr  # type: ignore[method-assign] # overriding method
-    _cfg_read_utf8_with_fallback(opts, filename)
-
-    for section, options in settings.items():
-        if options is None:
-            log.info("Deleting section [%s] from %s", section, filename)
-            opts.remove_section(section)
-        else:
-            if not opts.has_section(section):
-                log.debug("Adding new section [%s] to %s", section, filename)
-                opts.add_section(section)
-            for option, value in options.items():
-                if value is None:
-                    log.debug("Deleting %s.%s from %s", section, option, filename)
-                    opts.remove_option(section, option)
-                    if not opts.options(section):
-                        log.info(
-                            "Deleting empty [%s] section from %s", section, filename
-                        )
-                        opts.remove_section(section)
-                else:
-                    log.debug(
-                        "Setting %s.%s to %r in %s", section, option, value, filename
-                    )
-                    opts.set(section, option, value)
-
-    log.info("Writing %s", filename)
-    if not dry_run:
-        with open(filename, 'w', encoding="utf-8") as f:
-            opts.write(f)
-
-
-class option_base(Command):
-    """Abstract base class for commands that mess with config files"""
-
-    user_options = [
-        ('global-config', 'g', "save options to the site-wide distutils.cfg file"),
-        ('user-config', 'u', "save options to the current user's pydistutils.cfg file"),
-        ('filename=', 'f', "configuration file to use (default=setup.cfg)"),
-    ]
-
-    boolean_options = [
-        'global-config',
-        'user-config',
-    ]
-
-    def initialize_options(self):
-        self.global_config = None
-        self.user_config = None
-        self.filename = None
-
-    def finalize_options(self):
-        filenames = []
-        if self.global_config:
-            filenames.append(config_file('global'))
-        if self.user_config:
-            filenames.append(config_file('user'))
-        if self.filename is not None:
-            filenames.append(self.filename)
-        if not filenames:
-            filenames.append(config_file('local'))
-        if len(filenames) > 1:
-            raise DistutilsOptionError(
-                "Must specify only one configuration file option", filenames
-            )
-        (self.filename,) = filenames
-
-
-class setopt(option_base):
-    """Save command-line options to a file"""
-
-    description = "set an option in setup.cfg or another config file"
-
-    user_options = [
-        ('command=', 'c', 'command to set an option for'),
-        ('option=', 'o', 'option to set'),
-        ('set-value=', 's', 'value of the option'),
-        ('remove', 'r', 'remove (unset) the value'),
-    ] + option_base.user_options
-
-    boolean_options = option_base.boolean_options + ['remove']
-
-    def initialize_options(self):
-        option_base.initialize_options(self)
-        self.command = None
-        self.option = None
-        self.set_value = None
-        self.remove = None
-
-    def finalize_options(self) -> None:
-        option_base.finalize_options(self)
-        if self.command is None or self.option is None:
-            raise DistutilsOptionError("Must specify --command *and* --option")
-        if self.set_value is None and not self.remove:
-            raise DistutilsOptionError("Must specify --set-value or --remove")
-
-    def run(self) -> None:
-        edit_config(
-            self.filename,
-            {self.command: {self.option.replace('-', '_'): self.set_value}},
-            self.dry_run,
-        )
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/command/test.py b/llmlab/lib/python3.12/site-packages/setuptools/command/test.py
deleted file mode 100644
index 341b11a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/command/test.py
+++ /dev/null
@@ -1,45 +0,0 @@
-from __future__ import annotations
-
-from setuptools import Command
-from setuptools.warnings import SetuptoolsDeprecationWarning
-
-
-# Would restrict to Literal["test"], but mypy doesn't support it: https://github.com/python/mypy/issues/8203
-def __getattr__(name: str) -> type[_test]:
-    if name == 'test':
-        SetuptoolsDeprecationWarning.emit(
-            "The test command is disabled and references to it are deprecated.",
-            "Please remove any references to `setuptools.command.test` in all "
-            "supported versions of the affected package.",
-            due_date=(2024, 11, 15),
-            stacklevel=2,
-        )
-        return _test
-    raise AttributeError(name)
-
-
-class _test(Command):
-    """
-    Stub to warn when test command is referenced or used.
-    """
-
-    description = "stub for old test command (do not use)"
-
-    user_options = [
-        ('test-module=', 'm', "Run 'test_suite' in specified module"),
-        (
-            'test-suite=',
-            's',
-            "Run single test, case or suite (e.g. 'module.test_suite')",
-        ),
-        ('test-runner=', 'r', "Test runner to use"),
-    ]
-
-    def initialize_options(self):
-        pass
-
-    def finalize_options(self):
-        pass
-
-    def run(self):
-        raise RuntimeError("Support for the test command was removed in Setuptools 72")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/compat/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 284a86c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py310.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py310.cpython-312.pyc
deleted file mode 100644
index d9a35d0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py310.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py311.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py311.cpython-312.pyc
deleted file mode 100644
index a516bed..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py311.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py312.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py312.cpython-312.pyc
deleted file mode 100644
index c1d3c71..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py312.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py39.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py39.cpython-312.pyc
deleted file mode 100644
index 8dbcb13..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/compat/__pycache__/py39.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/py310.py b/llmlab/lib/python3.12/site-packages/setuptools/compat/py310.py
deleted file mode 100644
index b3912f8..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/compat/py310.py
+++ /dev/null
@@ -1,9 +0,0 @@
-import sys
-
-__all__ = ['tomllib']
-
-
-if sys.version_info >= (3, 11):
-    import tomllib
-else:  # pragma: no cover
-    import tomli as tomllib
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/py311.py b/llmlab/lib/python3.12/site-packages/setuptools/compat/py311.py
deleted file mode 100644
index 52b58af..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/compat/py311.py
+++ /dev/null
@@ -1,27 +0,0 @@
-from __future__ import annotations
-
-import shutil
-import sys
-from typing import TYPE_CHECKING, Any, Callable
-
-if TYPE_CHECKING:
-    from _typeshed import ExcInfo, StrOrBytesPath
-    from typing_extensions import TypeAlias
-
-# Same as shutil._OnExcCallback from typeshed
-_OnExcCallback: TypeAlias = Callable[[Callable[..., Any], str, BaseException], object]
-
-
-def shutil_rmtree(
-    path: StrOrBytesPath,
-    ignore_errors: bool = False,
-    onexc: _OnExcCallback | None = None,
-) -> None:
-    if sys.version_info >= (3, 12):
-        return shutil.rmtree(path, ignore_errors, onexc=onexc)
-
-    def _handler(fn: Callable[..., Any], path: str, excinfo: ExcInfo) -> None:
-        if onexc:
-            onexc(fn, path, excinfo[1])
-
-    return shutil.rmtree(path, ignore_errors, onerror=_handler)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/py312.py b/llmlab/lib/python3.12/site-packages/setuptools/compat/py312.py
deleted file mode 100644
index b20c5f6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/compat/py312.py
+++ /dev/null
@@ -1,13 +0,0 @@
-from __future__ import annotations
-
-import sys
-
-if sys.version_info >= (3, 12, 4):
-    # Python 3.13 should support `.pth` files encoded in UTF-8
-    # See discussion in https://github.com/python/cpython/issues/77102
-    PTH_ENCODING: str | None = "utf-8"
-else:
-    from .py39 import LOCALE_ENCODING
-
-    # PTH_ENCODING = "locale"
-    PTH_ENCODING = LOCALE_ENCODING
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/compat/py39.py b/llmlab/lib/python3.12/site-packages/setuptools/compat/py39.py
deleted file mode 100644
index 04a4abe..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/compat/py39.py
+++ /dev/null
@@ -1,9 +0,0 @@
-import sys
-
-# Explicitly use the ``"locale"`` encoding in versions that support it,
-# otherwise just rely on the implicit handling of ``encoding=None``.
-# Since all platforms that support ``EncodingWarning`` also support
-# ``encoding="locale"``, this can be used to suppress the warning.
-# However, please try to use UTF-8 when possible
-# (.pth files are the notorious exception: python/cpython#77102, pypa/setuptools#3937).
-LOCALE_ENCODING = "locale" if sys.version_info >= (3, 10) else None
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/NOTICE b/llmlab/lib/python3.12/site-packages/setuptools/config/NOTICE
deleted file mode 100644
index 0186451..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/NOTICE
+++ /dev/null
@@ -1,10 +0,0 @@
-The following files include code from opensource projects
-(either as direct copies or modified versions):
-
-- `setuptools.schema.json`, `distutils.schema.json`:
-    - project: `validate-pyproject` - licensed under MPL-2.0
-      (https://github.com/abravalheri/validate-pyproject):
-
-      This Source Code Form is subject to the terms of the Mozilla Public
-      License, v. 2.0. If a copy of the MPL was not distributed with this file,
-      You can obtain one at https://mozilla.org/MPL/2.0/.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/config/__init__.py
deleted file mode 100644
index fcc7d00..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/__init__.py
+++ /dev/null
@@ -1,43 +0,0 @@
-"""For backward compatibility, expose main functions from
-``setuptools.config.setupcfg``
-"""
-
-from functools import wraps
-from typing import Callable, TypeVar, cast
-
-from ..warnings import SetuptoolsDeprecationWarning
-from . import setupcfg
-
-Fn = TypeVar("Fn", bound=Callable)
-
-__all__ = ('parse_configuration', 'read_configuration')
-
-
-def _deprecation_notice(fn: Fn) -> Fn:
-    @wraps(fn)
-    def _wrapper(*args, **kwargs):
-        SetuptoolsDeprecationWarning.emit(
-            "Deprecated API usage.",
-            f"""
-            As setuptools moves its configuration towards `pyproject.toml`,
-            `{__name__}.{fn.__name__}` became deprecated.
-
-            For the time being, you can use the `{setupcfg.__name__}` module
-            to access a backward compatible API, but this module is provisional
-            and might be removed in the future.
-
-            To read project metadata, consider using
-            ``build.util.project_wheel_metadata`` (https://pypi.org/project/build/).
-            For simple scenarios, you can also try parsing the file directly
-            with the help of ``configparser``.
-            """,
-            # due_date not defined yet, because the community still heavily relies on it
-            # Warning introduced in 24 Mar 2022
-        )
-        return fn(*args, **kwargs)
-
-    return cast(Fn, _wrapper)
-
-
-read_configuration = _deprecation_notice(setupcfg.read_configuration)
-parse_configuration = _deprecation_notice(setupcfg.parse_configuration)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index c6825d1..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/_apply_pyprojecttoml.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/_apply_pyprojecttoml.cpython-312.pyc
deleted file mode 100644
index 7a020eb..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/_apply_pyprojecttoml.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/expand.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/expand.cpython-312.pyc
deleted file mode 100644
index beeb83c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/expand.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/pyprojecttoml.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/pyprojecttoml.cpython-312.pyc
deleted file mode 100644
index 8842224..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/pyprojecttoml.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/setupcfg.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/setupcfg.cpython-312.pyc
deleted file mode 100644
index 841cfc7..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/__pycache__/setupcfg.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_apply_pyprojecttoml.py b/llmlab/lib/python3.12/site-packages/setuptools/config/_apply_pyprojecttoml.py
deleted file mode 100644
index 9088bc1..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_apply_pyprojecttoml.py
+++ /dev/null
@@ -1,526 +0,0 @@
-"""Translation layer between pyproject config and setuptools distribution and
-metadata objects.
-
-The distribution and metadata objects are modeled after (an old version of)
-core metadata, therefore configs in the format specified for ``pyproject.toml``
-need to be processed before being applied.
-
-**PRIVATE MODULE**: API reserved for setuptools internal usage only.
-"""
-
-from __future__ import annotations
-
-import logging
-import os
-from collections.abc import Mapping
-from email.headerregistry import Address
-from functools import partial, reduce
-from inspect import cleandoc
-from itertools import chain
-from types import MappingProxyType
-from typing import TYPE_CHECKING, Any, Callable, TypeVar, Union
-
-from .. import _static
-from .._path import StrPath
-from ..errors import InvalidConfigError, RemovedConfigError
-from ..extension import Extension
-from ..warnings import SetuptoolsDeprecationWarning, SetuptoolsWarning
-
-if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
-
-    from setuptools._importlib import metadata
-    from setuptools.dist import Distribution
-
-    from distutils.dist import _OptionsList  # Comes from typeshed
-
-
-EMPTY: Mapping = MappingProxyType({})  # Immutable dict-like
-_ProjectReadmeValue: TypeAlias = Union[str, dict[str, str]]
-_Correspondence: TypeAlias = Callable[["Distribution", Any, Union[StrPath, None]], None]
-_T = TypeVar("_T")
-
-_logger = logging.getLogger(__name__)
-
-
-def apply(dist: Distribution, config: dict, filename: StrPath) -> Distribution:
-    """Apply configuration dict read with :func:`read_configuration`"""
-
-    if not config:
-        return dist  # short-circuit unrelated pyproject.toml file
-
-    root_dir = os.path.dirname(filename) or "."
-
-    _apply_project_table(dist, config, root_dir)
-    _apply_tool_table(dist, config, filename)
-
-    current_directory = os.getcwd()
-    os.chdir(root_dir)
-    try:
-        dist._finalize_requires()
-        dist._finalize_license_expression()
-        dist._finalize_license_files()
-    finally:
-        os.chdir(current_directory)
-
-    return dist
-
-
-def _apply_project_table(dist: Distribution, config: dict, root_dir: StrPath):
-    orig_config = config.get("project", {})
-    if not orig_config:
-        return  # short-circuit
-
-    project_table = {k: _static.attempt_conversion(v) for k, v in orig_config.items()}
-    _handle_missing_dynamic(dist, project_table)
-    _unify_entry_points(project_table)
-
-    for field, value in project_table.items():
-        norm_key = json_compatible_key(field)
-        corresp = PYPROJECT_CORRESPONDENCE.get(norm_key, norm_key)
-        if callable(corresp):
-            corresp(dist, value, root_dir)
-        else:
-            _set_config(dist, corresp, value)
-
-
-def _apply_tool_table(dist: Distribution, config: dict, filename: StrPath):
-    tool_table = config.get("tool", {}).get("setuptools", {})
-    if not tool_table:
-        return  # short-circuit
-
-    if "license-files" in tool_table:
-        if "license-files" in config.get("project", {}):
-            # https://github.com/pypa/setuptools/pull/4837#discussion_r2004983349
-            raise InvalidConfigError(
-                "'project.license-files' is defined already. "
-                "Remove 'tool.setuptools.license-files'."
-            )
-
-        pypa_guides = "guides/writing-pyproject-toml/#license-files"
-        SetuptoolsDeprecationWarning.emit(
-            "'tool.setuptools.license-files' is deprecated in favor of "
-            "'project.license-files' (available on setuptools>=77.0.0).",
-            see_url=f"https://packaging.python.org/en/latest/{pypa_guides}",
-            due_date=(2026, 2, 18),  # Warning introduced on 2025-02-18
-        )
-
-    for field, value in tool_table.items():
-        norm_key = json_compatible_key(field)
-
-        if norm_key in TOOL_TABLE_REMOVALS:
-            suggestion = cleandoc(TOOL_TABLE_REMOVALS[norm_key])
-            msg = f"""
-            The parameter `tool.setuptools.{field}` was long deprecated
-            and has been removed from `pyproject.toml`.
-            """
-            raise RemovedConfigError("\n".join([cleandoc(msg), suggestion]))
-
-        norm_key = TOOL_TABLE_RENAMES.get(norm_key, norm_key)
-        corresp = TOOL_TABLE_CORRESPONDENCE.get(norm_key, norm_key)
-        if callable(corresp):
-            corresp(dist, value)
-        else:
-            _set_config(dist, corresp, value)
-
-    _copy_command_options(config, dist, filename)
-
-
-def _handle_missing_dynamic(dist: Distribution, project_table: dict):
-    """Be temporarily forgiving with ``dynamic`` fields not listed in ``dynamic``"""
-    dynamic = set(project_table.get("dynamic", []))
-    for field, getter in _PREVIOUSLY_DEFINED.items():
-        if not (field in project_table or field in dynamic):
-            value = getter(dist)
-            if value:
-                _MissingDynamic.emit(field=field, value=value)
-                project_table[field] = _RESET_PREVIOUSLY_DEFINED.get(field)
-
-
-def json_compatible_key(key: str) -> str:
-    """As defined in :pep:`566#json-compatible-metadata`"""
-    return key.lower().replace("-", "_")
-
-
-def _set_config(dist: Distribution, field: str, value: Any):
-    val = _PREPROCESS.get(field, _noop)(dist, value)
-    setter = getattr(dist.metadata, f"set_{field}", None)
-    if setter:
-        setter(val)
-    elif hasattr(dist.metadata, field) or field in SETUPTOOLS_PATCHES:
-        setattr(dist.metadata, field, val)
-    else:
-        setattr(dist, field, val)
-
-
-_CONTENT_TYPES = {
-    ".md": "text/markdown",
-    ".rst": "text/x-rst",
-    ".txt": "text/plain",
-}
-
-
-def _guess_content_type(file: str) -> str | None:
-    _, ext = os.path.splitext(file.lower())
-    if not ext:
-        return None
-
-    if ext in _CONTENT_TYPES:
-        return _static.Str(_CONTENT_TYPES[ext])
-
-    valid = ", ".join(f"{k} ({v})" for k, v in _CONTENT_TYPES.items())
-    msg = f"only the following file extensions are recognized: {valid}."
-    raise ValueError(f"Undefined content type for {file}, {msg}")
-
-
-def _long_description(
-    dist: Distribution, val: _ProjectReadmeValue, root_dir: StrPath | None
-):
-    from setuptools.config import expand
-
-    file: str | tuple[()]
-    if isinstance(val, str):
-        file = val
-        text = expand.read_files(file, root_dir)
-        ctype = _guess_content_type(file)
-    else:
-        file = val.get("file") or ()
-        text = val.get("text") or expand.read_files(file, root_dir)
-        ctype = val["content-type"]
-
-    # XXX: Is it completely safe to assume static?
-    _set_config(dist, "long_description", _static.Str(text))
-
-    if ctype:
-        _set_config(dist, "long_description_content_type", _static.Str(ctype))
-
-    if file:
-        dist._referenced_files.add(file)
-
-
-def _license(dist: Distribution, val: str | dict, root_dir: StrPath | None):
-    from setuptools.config import expand
-
-    if isinstance(val, str):
-        if getattr(dist.metadata, "license", None):
-            SetuptoolsWarning.emit("`license` overwritten by `pyproject.toml`")
-            dist.metadata.license = None
-        _set_config(dist, "license_expression", _static.Str(val))
-    else:
-        pypa_guides = "guides/writing-pyproject-toml/#license"
-        SetuptoolsDeprecationWarning.emit(
-            "`project.license` as a TOML table is deprecated",
-            "Please use a simple string containing a SPDX expression for "
-            "`project.license`. You can also use `project.license-files`. "
-            "(Both options available on setuptools>=77.0.0).",
-            see_url=f"https://packaging.python.org/en/latest/{pypa_guides}",
-            due_date=(2026, 2, 18),  # Introduced on 2025-02-18
-        )
-        if "file" in val:
-            # XXX: Is it completely safe to assume static?
-            value = expand.read_files([val["file"]], root_dir)
-            _set_config(dist, "license", _static.Str(value))
-            dist._referenced_files.add(val["file"])
-        else:
-            _set_config(dist, "license", _static.Str(val["text"]))
-
-
-def _people(dist: Distribution, val: list[dict], _root_dir: StrPath | None, kind: str):
-    field = []
-    email_field = []
-    for person in val:
-        if "name" not in person:
-            email_field.append(person["email"])
-        elif "email" not in person:
-            field.append(person["name"])
-        else:
-            addr = Address(display_name=person["name"], addr_spec=person["email"])
-            email_field.append(str(addr))
-
-    if field:
-        _set_config(dist, kind, _static.Str(", ".join(field)))
-    if email_field:
-        _set_config(dist, f"{kind}_email", _static.Str(", ".join(email_field)))
-
-
-def _project_urls(dist: Distribution, val: dict, _root_dir: StrPath | None):
-    _set_config(dist, "project_urls", val)
-
-
-def _python_requires(dist: Distribution, val: str, _root_dir: StrPath | None):
-    _set_config(dist, "python_requires", _static.SpecifierSet(val))
-
-
-def _dependencies(dist: Distribution, val: list, _root_dir: StrPath | None):
-    if getattr(dist, "install_requires", []):
-        msg = "`install_requires` overwritten in `pyproject.toml` (dependencies)"
-        SetuptoolsWarning.emit(msg)
-    dist.install_requires = val
-
-
-def _optional_dependencies(dist: Distribution, val: dict, _root_dir: StrPath | None):
-    if getattr(dist, "extras_require", None):
-        msg = "`extras_require` overwritten in `pyproject.toml` (optional-dependencies)"
-        SetuptoolsWarning.emit(msg)
-    dist.extras_require = val
-
-
-def _ext_modules(dist: Distribution, val: list[dict]) -> list[Extension]:
-    existing = dist.ext_modules or []
-    args = ({k.replace("-", "_"): v for k, v in x.items()} for x in val)
-    new = [Extension(**kw) for kw in args]
-    return [*existing, *new]
-
-
-def _noop(_dist: Distribution, val: _T) -> _T:
-    return val
-
-
-def _identity(val: _T) -> _T:
-    return val
-
-
-def _unify_entry_points(project_table: dict):
-    project = project_table
-    given = project.pop("entry-points", project.pop("entry_points", {}))
-    entry_points = dict(given)  # Avoid problems with static
-    renaming = {"scripts": "console_scripts", "gui_scripts": "gui_scripts"}
-    for key, value in list(project.items()):  # eager to allow modifications
-        norm_key = json_compatible_key(key)
-        if norm_key in renaming:
-            # Don't skip even if value is empty (reason: reset missing `dynamic`)
-            entry_points[renaming[norm_key]] = project.pop(key)
-
-    if entry_points:
-        project["entry-points"] = {
-            name: [f"{k} = {v}" for k, v in group.items()]
-            for name, group in entry_points.items()
-            if group  # now we can skip empty groups
-        }
-        # Sometimes this will set `project["entry-points"] = {}`, and that is
-        # intentional (for resetting configurations that are missing `dynamic`).
-
-
-def _copy_command_options(pyproject: dict, dist: Distribution, filename: StrPath):
-    tool_table = pyproject.get("tool", {})
-    cmdclass = tool_table.get("setuptools", {}).get("cmdclass", {})
-    valid_options = _valid_command_options(cmdclass)
-
-    cmd_opts = dist.command_options
-    for cmd, config in pyproject.get("tool", {}).get("distutils", {}).items():
-        cmd = json_compatible_key(cmd)
-        valid = valid_options.get(cmd, set())
-        cmd_opts.setdefault(cmd, {})
-        for key, value in config.items():
-            key = json_compatible_key(key)
-            cmd_opts[cmd][key] = (str(filename), value)
-            if key not in valid:
-                # To avoid removing options that are specified dynamically we
-                # just log a warn...
-                _logger.warning(f"Command option {cmd}.{key} is not defined")
-
-
-def _valid_command_options(cmdclass: Mapping = EMPTY) -> dict[str, set[str]]:
-    from setuptools.dist import Distribution
-
-    from .._importlib import metadata
-
-    valid_options = {"global": _normalise_cmd_options(Distribution.global_options)}
-
-    unloaded_entry_points = metadata.entry_points(group='distutils.commands')
-    loaded_entry_points = (_load_ep(ep) for ep in unloaded_entry_points)
-    entry_points = (ep for ep in loaded_entry_points if ep)
-    for cmd, cmd_class in chain(entry_points, cmdclass.items()):
-        opts = valid_options.get(cmd, set())
-        opts = opts | _normalise_cmd_options(getattr(cmd_class, "user_options", []))
-        valid_options[cmd] = opts
-
-    return valid_options
-
-
-def _load_ep(ep: metadata.EntryPoint) -> tuple[str, type] | None:
-    if ep.value.startswith("wheel.bdist_wheel"):
-        # Ignore deprecated entrypoint from wheel and avoid warning pypa/wheel#631
-        # TODO: remove check when `bdist_wheel` has been fully removed from pypa/wheel
-        return None
-
-    # Ignore all the errors
-    try:
-        return (ep.name, ep.load())
-    except Exception as ex:
-        msg = f"{ex.__class__.__name__} while trying to load entry-point {ep.name}"
-        _logger.warning(f"{msg}: {ex}")
-        return None
-
-
-def _normalise_cmd_option_key(name: str) -> str:
-    return json_compatible_key(name).strip("_=")
-
-
-def _normalise_cmd_options(desc: _OptionsList) -> set[str]:
-    return {_normalise_cmd_option_key(fancy_option[0]) for fancy_option in desc}
-
-
-def _get_previous_entrypoints(dist: Distribution) -> dict[str, list]:
-    ignore = ("console_scripts", "gui_scripts")
-    value = getattr(dist, "entry_points", None) or {}
-    return {k: v for k, v in value.items() if k not in ignore}
-
-
-def _get_previous_scripts(dist: Distribution) -> list | None:
-    value = getattr(dist, "entry_points", None) or {}
-    return value.get("console_scripts")
-
-
-def _get_previous_gui_scripts(dist: Distribution) -> list | None:
-    value = getattr(dist, "entry_points", None) or {}
-    return value.get("gui_scripts")
-
-
-def _set_static_list_metadata(attr: str, dist: Distribution, val: list) -> None:
-    """Apply distutils metadata validation but preserve "static" behaviour"""
-    meta = dist.metadata
-    setter, getter = getattr(meta, f"set_{attr}"), getattr(meta, f"get_{attr}")
-    setter(val)
-    setattr(meta, attr, _static.List(getter()))
-
-
-def _attrgetter(attr):
-    """
-    Similar to ``operator.attrgetter`` but returns None if ``attr`` is not found
-    >>> from types import SimpleNamespace
-    >>> obj = SimpleNamespace(a=42, b=SimpleNamespace(c=13))
-    >>> _attrgetter("a")(obj)
-    42
-    >>> _attrgetter("b.c")(obj)
-    13
-    >>> _attrgetter("d")(obj) is None
-    True
-    """
-    return partial(reduce, lambda acc, x: getattr(acc, x, None), attr.split("."))
-
-
-def _some_attrgetter(*items):
-    """
-    Return the first "truth-y" attribute or None
-    >>> from types import SimpleNamespace
-    >>> obj = SimpleNamespace(a=42, b=SimpleNamespace(c=13))
-    >>> _some_attrgetter("d", "a", "b.c")(obj)
-    42
-    >>> _some_attrgetter("d", "e", "b.c", "a")(obj)
-    13
-    >>> _some_attrgetter("d", "e", "f")(obj) is None
-    True
-    """
-
-    def _acessor(obj):
-        values = (_attrgetter(i)(obj) for i in items)
-        return next((i for i in values if i is not None), None)
-
-    return _acessor
-
-
-PYPROJECT_CORRESPONDENCE: dict[str, _Correspondence] = {
-    "readme": _long_description,
-    "license": _license,
-    "authors": partial(_people, kind="author"),
-    "maintainers": partial(_people, kind="maintainer"),
-    "urls": _project_urls,
-    "dependencies": _dependencies,
-    "optional_dependencies": _optional_dependencies,
-    "requires_python": _python_requires,
-}
-
-TOOL_TABLE_RENAMES = {"script_files": "scripts"}
-TOOL_TABLE_REMOVALS = {
-    "namespace_packages": """
-        Please migrate to implicit native namespaces instead.
-        See https://packaging.python.org/en/latest/guides/packaging-namespace-packages/.
-        """,
-}
-TOOL_TABLE_CORRESPONDENCE = {
-    # Fields with corresponding core metadata need to be marked as static:
-    "obsoletes": partial(_set_static_list_metadata, "obsoletes"),
-    "provides": partial(_set_static_list_metadata, "provides"),
-    "platforms": partial(_set_static_list_metadata, "platforms"),
-}
-
-SETUPTOOLS_PATCHES = {
-    "long_description_content_type",
-    "project_urls",
-    "provides_extras",
-    "license_file",
-    "license_files",
-    "license_expression",
-}
-
-_PREPROCESS = {
-    "ext_modules": _ext_modules,
-}
-
-_PREVIOUSLY_DEFINED = {
-    "name": _attrgetter("metadata.name"),
-    "version": _attrgetter("metadata.version"),
-    "description": _attrgetter("metadata.description"),
-    "readme": _attrgetter("metadata.long_description"),
-    "requires-python": _some_attrgetter("python_requires", "metadata.python_requires"),
-    "license": _some_attrgetter("metadata.license_expression", "metadata.license"),
-    # XXX: `license-file` is currently not considered in the context of `dynamic`.
-    #      See TestPresetField.test_license_files_exempt_from_dynamic
-    "authors": _some_attrgetter("metadata.author", "metadata.author_email"),
-    "maintainers": _some_attrgetter("metadata.maintainer", "metadata.maintainer_email"),
-    "keywords": _attrgetter("metadata.keywords"),
-    "classifiers": _attrgetter("metadata.classifiers"),
-    "urls": _attrgetter("metadata.project_urls"),
-    "entry-points": _get_previous_entrypoints,
-    "scripts": _get_previous_scripts,
-    "gui-scripts": _get_previous_gui_scripts,
-    "dependencies": _attrgetter("install_requires"),
-    "optional-dependencies": _attrgetter("extras_require"),
-}
-
-
-_RESET_PREVIOUSLY_DEFINED: dict = {
-    # Fix improper setting: given in `setup.py`, but not listed in `dynamic`
-    # Use "immutable" data structures to avoid in-place modification.
-    # dict: pyproject name => value to which reset
-    "license": "",
-    # XXX: `license-file` is currently not considered in the context of `dynamic`.
-    #      See TestPresetField.test_license_files_exempt_from_dynamic
-    "authors": _static.EMPTY_LIST,
-    "maintainers": _static.EMPTY_LIST,
-    "keywords": _static.EMPTY_LIST,
-    "classifiers": _static.EMPTY_LIST,
-    "urls": _static.EMPTY_DICT,
-    "entry-points": _static.EMPTY_DICT,
-    "scripts": _static.EMPTY_DICT,
-    "gui-scripts": _static.EMPTY_DICT,
-    "dependencies": _static.EMPTY_LIST,
-    "optional-dependencies": _static.EMPTY_DICT,
-}
-
-
-class _MissingDynamic(SetuptoolsWarning):
-    _SUMMARY = "`{field}` defined outside of `pyproject.toml` is ignored."
-
-    _DETAILS = """
-    The following seems to be defined outside of `pyproject.toml`:
-
-    `{field} = {value!r}`
-
-    According to the spec (see the link below), however, setuptools CANNOT
-    consider this value unless `{field}` is listed as `dynamic`.
-
-    https://packaging.python.org/en/latest/specifications/pyproject-toml/#declaring-project-metadata-the-project-table
-
-    To prevent this problem, you can list `{field}` under `dynamic` or alternatively
-    remove the `[project]` table from your file and rely entirely on other means of
-    configuration.
-    """
-    # TODO: Consider removing this check in the future?
-    #       There is a trade-off here between improving "debug-ability" and the cost
-    #       of running/testing/maintaining these unnecessary checks...
-
-    @classmethod
-    def details(cls, field: str, value: Any) -> str:
-        return cls._DETAILS.format(field=field, value=value)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/NOTICE b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/NOTICE
deleted file mode 100644
index ac5464d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/NOTICE
+++ /dev/null
@@ -1,438 +0,0 @@
-The code contained in this directory was automatically generated using the
-following command:
-
-    python -m validate_pyproject.pre_compile --output-dir=setuptools/config/_validate_pyproject --enable-plugins setuptools distutils --very-verbose -t setuptools=setuptools/config/setuptools.schema.json -t distutils=setuptools/config/distutils.schema.json
-
-Please avoid changing it manually.
-
-
-You can report issues or suggest changes directly to `validate-pyproject`
-(or to the relevant plugin repository)
-
-- https://github.com/abravalheri/validate-pyproject/issues
-
-
-***
-
-The following files include code from opensource projects
-(either as direct copies or modified versions):
-
-- `fastjsonschema_exceptions.py`:
-    - project: `fastjsonschema` - licensed under BSD-3-Clause
-      (https://github.com/horejsek/python-fastjsonschema)
-- `extra_validations.py` and `format.py`, `error_reporting.py`:
-    - project: `validate-pyproject` - licensed under MPL-2.0
-      (https://github.com/abravalheri/validate-pyproject)
-
-
-Additionally the following files are automatically generated by tools provided
-by the same projects:
-
-- `__init__.py`
-- `fastjsonschema_validations.py`
-
-The relevant copyright notes and licenses are included below.
-
-
-***
-
-`fastjsonschema`
-================
-
-Copyright (c) 2018, Michal Horejsek
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without modification,
-are permitted provided that the following conditions are met:
-
-  Redistributions of source code must retain the above copyright notice, this
-  list of conditions and the following disclaimer.
-
-  Redistributions in binary form must reproduce the above copyright notice, this
-  list of conditions and the following disclaimer in the documentation and/or
-  other materials provided with the distribution.
-
-  Neither the name of the {organization} nor the names of its
-  contributors may be used to endorse or promote products derived from
-  this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
-ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
-LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
-ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-
-
-***
-
-`validate-pyproject`
-====================
-
-Mozilla Public License, version 2.0
-
-1. Definitions
-
-1.1. "Contributor"
-
-     means each individual or legal entity that creates, contributes to the
-     creation of, or owns Covered Software.
-
-1.2. "Contributor Version"
-
-     means the combination of the Contributions of others (if any) used by a
-     Contributor and that particular Contributor's Contribution.
-
-1.3. "Contribution"
-
-     means Covered Software of a particular Contributor.
-
-1.4. "Covered Software"
-
-     means Source Code Form to which the initial Contributor has attached the
-     notice in Exhibit A, the Executable Form of such Source Code Form, and
-     Modifications of such Source Code Form, in each case including portions
-     thereof.
-
-1.5. "Incompatible With Secondary Licenses"
-     means
-
-     a. that the initial Contributor has attached the notice described in
-        Exhibit B to the Covered Software; or
-
-     b. that the Covered Software was made available under the terms of
-        version 1.1 or earlier of the License, but not also under the terms of
-        a Secondary License.
-
-1.6. "Executable Form"
-
-     means any form of the work other than Source Code Form.
-
-1.7. "Larger Work"
-
-     means a work that combines Covered Software with other material, in a
-     separate file or files, that is not Covered Software.
-
-1.8. "License"
-
-     means this document.
-
-1.9. "Licensable"
-
-     means having the right to grant, to the maximum extent possible, whether
-     at the time of the initial grant or subsequently, any and all of the
-     rights conveyed by this License.
-
-1.10. "Modifications"
-
-     means any of the following:
-
-     a. any file in Source Code Form that results from an addition to,
-        deletion from, or modification of the contents of Covered Software; or
-
-     b. any new file in Source Code Form that contains any Covered Software.
-
-1.11. "Patent Claims" of a Contributor
-
-      means any patent claim(s), including without limitation, method,
-      process, and apparatus claims, in any patent Licensable by such
-      Contributor that would be infringed, but for the grant of the License,
-      by the making, using, selling, offering for sale, having made, import,
-      or transfer of either its Contributions or its Contributor Version.
-
-1.12. "Secondary License"
-
-      means either the GNU General Public License, Version 2.0, the GNU Lesser
-      General Public License, Version 2.1, the GNU Affero General Public
-      License, Version 3.0, or any later versions of those licenses.
-
-1.13. "Source Code Form"
-
-      means the form of the work preferred for making modifications.
-
-1.14. "You" (or "Your")
-
-      means an individual or a legal entity exercising rights under this
-      License. For legal entities, "You" includes any entity that controls, is
-      controlled by, or is under common control with You. For purposes of this
-      definition, "control" means (a) the power, direct or indirect, to cause
-      the direction or management of such entity, whether by contract or
-      otherwise, or (b) ownership of more than fifty percent (50%) of the
-      outstanding shares or beneficial ownership of such entity.
-
-
-2. License Grants and Conditions
-
-2.1. Grants
-
-     Each Contributor hereby grants You a world-wide, royalty-free,
-     non-exclusive license:
-
-     a. under intellectual property rights (other than patent or trademark)
-        Licensable by such Contributor to use, reproduce, make available,
-        modify, display, perform, distribute, and otherwise exploit its
-        Contributions, either on an unmodified basis, with Modifications, or
-        as part of a Larger Work; and
-
-     b. under Patent Claims of such Contributor to make, use, sell, offer for
-        sale, have made, import, and otherwise transfer either its
-        Contributions or its Contributor Version.
-
-2.2. Effective Date
-
-     The licenses granted in Section 2.1 with respect to any Contribution
-     become effective for each Contribution on the date the Contributor first
-     distributes such Contribution.
-
-2.3. Limitations on Grant Scope
-
-     The licenses granted in this Section 2 are the only rights granted under
-     this License. No additional rights or licenses will be implied from the
-     distribution or licensing of Covered Software under this License.
-     Notwithstanding Section 2.1(b) above, no patent license is granted by a
-     Contributor:
-
-     a. for any code that a Contributor has removed from Covered Software; or
-
-     b. for infringements caused by: (i) Your and any other third party's
-        modifications of Covered Software, or (ii) the combination of its
-        Contributions with other software (except as part of its Contributor
-        Version); or
-
-     c. under Patent Claims infringed by Covered Software in the absence of
-        its Contributions.
-
-     This License does not grant any rights in the trademarks, service marks,
-     or logos of any Contributor (except as may be necessary to comply with
-     the notice requirements in Section 3.4).
-
-2.4. Subsequent Licenses
-
-     No Contributor makes additional grants as a result of Your choice to
-     distribute the Covered Software under a subsequent version of this
-     License (see Section 10.2) or under the terms of a Secondary License (if
-     permitted under the terms of Section 3.3).
-
-2.5. Representation
-
-     Each Contributor represents that the Contributor believes its
-     Contributions are its original creation(s) or it has sufficient rights to
-     grant the rights to its Contributions conveyed by this License.
-
-2.6. Fair Use
-
-     This License is not intended to limit any rights You have under
-     applicable copyright doctrines of fair use, fair dealing, or other
-     equivalents.
-
-2.7. Conditions
-
-     Sections 3.1, 3.2, 3.3, and 3.4 are conditions of the licenses granted in
-     Section 2.1.
-
-
-3. Responsibilities
-
-3.1. Distribution of Source Form
-
-     All distribution of Covered Software in Source Code Form, including any
-     Modifications that You create or to which You contribute, must be under
-     the terms of this License. You must inform recipients that the Source
-     Code Form of the Covered Software is governed by the terms of this
-     License, and how they can obtain a copy of this License. You may not
-     attempt to alter or restrict the recipients' rights in the Source Code
-     Form.
-
-3.2. Distribution of Executable Form
-
-     If You distribute Covered Software in Executable Form then:
-
-     a. such Covered Software must also be made available in Source Code Form,
-        as described in Section 3.1, and You must inform recipients of the
-        Executable Form how they can obtain a copy of such Source Code Form by
-        reasonable means in a timely manner, at a charge no more than the cost
-        of distribution to the recipient; and
-
-     b. You may distribute such Executable Form under the terms of this
-        License, or sublicense it under different terms, provided that the
-        license for the Executable Form does not attempt to limit or alter the
-        recipients' rights in the Source Code Form under this License.
-
-3.3. Distribution of a Larger Work
-
-     You may create and distribute a Larger Work under terms of Your choice,
-     provided that You also comply with the requirements of this License for
-     the Covered Software. If the Larger Work is a combination of Covered
-     Software with a work governed by one or more Secondary Licenses, and the
-     Covered Software is not Incompatible With Secondary Licenses, this
-     License permits You to additionally distribute such Covered Software
-     under the terms of such Secondary License(s), so that the recipient of
-     the Larger Work may, at their option, further distribute the Covered
-     Software under the terms of either this License or such Secondary
-     License(s).
-
-3.4. Notices
-
-     You may not remove or alter the substance of any license notices
-     (including copyright notices, patent notices, disclaimers of warranty, or
-     limitations of liability) contained within the Source Code Form of the
-     Covered Software, except that You may alter any license notices to the
-     extent required to remedy known factual inaccuracies.
-
-3.5. Application of Additional Terms
-
-     You may choose to offer, and to charge a fee for, warranty, support,
-     indemnity or liability obligations to one or more recipients of Covered
-     Software. However, You may do so only on Your own behalf, and not on
-     behalf of any Contributor. You must make it absolutely clear that any
-     such warranty, support, indemnity, or liability obligation is offered by
-     You alone, and You hereby agree to indemnify every Contributor for any
-     liability incurred by such Contributor as a result of warranty, support,
-     indemnity or liability terms You offer. You may include additional
-     disclaimers of warranty and limitations of liability specific to any
-     jurisdiction.
-
-4. Inability to Comply Due to Statute or Regulation
-
-   If it is impossible for You to comply with any of the terms of this License
-   with respect to some or all of the Covered Software due to statute,
-   judicial order, or regulation then You must: (a) comply with the terms of
-   this License to the maximum extent possible; and (b) describe the
-   limitations and the code they affect. Such description must be placed in a
-   text file included with all distributions of the Covered Software under
-   this License. Except to the extent prohibited by statute or regulation,
-   such description must be sufficiently detailed for a recipient of ordinary
-   skill to be able to understand it.
-
-5. Termination
-
-5.1. The rights granted under this License will terminate automatically if You
-     fail to comply with any of its terms. However, if You become compliant,
-     then the rights granted under this License from a particular Contributor
-     are reinstated (a) provisionally, unless and until such Contributor
-     explicitly and finally terminates Your grants, and (b) on an ongoing
-     basis, if such Contributor fails to notify You of the non-compliance by
-     some reasonable means prior to 60 days after You have come back into
-     compliance. Moreover, Your grants from a particular Contributor are
-     reinstated on an ongoing basis if such Contributor notifies You of the
-     non-compliance by some reasonable means, this is the first time You have
-     received notice of non-compliance with this License from such
-     Contributor, and You become compliant prior to 30 days after Your receipt
-     of the notice.
-
-5.2. If You initiate litigation against any entity by asserting a patent
-     infringement claim (excluding declaratory judgment actions,
-     counter-claims, and cross-claims) alleging that a Contributor Version
-     directly or indirectly infringes any patent, then the rights granted to
-     You by any and all Contributors for the Covered Software under Section
-     2.1 of this License shall terminate.
-
-5.3. In the event of termination under Sections 5.1 or 5.2 above, all end user
-     license agreements (excluding distributors and resellers) which have been
-     validly granted by You or Your distributors under this License prior to
-     termination shall survive termination.
-
-6. Disclaimer of Warranty
-
-   Covered Software is provided under this License on an "as is" basis,
-   without warranty of any kind, either expressed, implied, or statutory,
-   including, without limitation, warranties that the Covered Software is free
-   of defects, merchantable, fit for a particular purpose or non-infringing.
-   The entire risk as to the quality and performance of the Covered Software
-   is with You. Should any Covered Software prove defective in any respect,
-   You (not any Contributor) assume the cost of any necessary servicing,
-   repair, or correction. This disclaimer of warranty constitutes an essential
-   part of this License. No use of  any Covered Software is authorized under
-   this License except under this disclaimer.
-
-7. Limitation of Liability
-
-   Under no circumstances and under no legal theory, whether tort (including
-   negligence), contract, or otherwise, shall any Contributor, or anyone who
-   distributes Covered Software as permitted above, be liable to You for any
-   direct, indirect, special, incidental, or consequential damages of any
-   character including, without limitation, damages for lost profits, loss of
-   goodwill, work stoppage, computer failure or malfunction, or any and all
-   other commercial damages or losses, even if such party shall have been
-   informed of the possibility of such damages. This limitation of liability
-   shall not apply to liability for death or personal injury resulting from
-   such party's negligence to the extent applicable law prohibits such
-   limitation. Some jurisdictions do not allow the exclusion or limitation of
-   incidental or consequential damages, so this exclusion and limitation may
-   not apply to You.
-
-8. Litigation
-
-   Any litigation relating to this License may be brought only in the courts
-   of a jurisdiction where the defendant maintains its principal place of
-   business and such litigation shall be governed by laws of that
-   jurisdiction, without reference to its conflict-of-law provisions. Nothing
-   in this Section shall prevent a party's ability to bring cross-claims or
-   counter-claims.
-
-9. Miscellaneous
-
-   This License represents the complete agreement concerning the subject
-   matter hereof. If any provision of this License is held to be
-   unenforceable, such provision shall be reformed only to the extent
-   necessary to make it enforceable. Any law or regulation which provides that
-   the language of a contract shall be construed against the drafter shall not
-   be used to construe this License against a Contributor.
-
-
-10. Versions of the License
-
-10.1. New Versions
-
-      Mozilla Foundation is the license steward. Except as provided in Section
-      10.3, no one other than the license steward has the right to modify or
-      publish new versions of this License. Each version will be given a
-      distinguishing version number.
-
-10.2. Effect of New Versions
-
-      You may distribute the Covered Software under the terms of the version
-      of the License under which You originally received the Covered Software,
-      or under the terms of any subsequent version published by the license
-      steward.
-
-10.3. Modified Versions
-
-      If you create software not governed by this License, and you want to
-      create a new license for such software, you may create and use a
-      modified version of this License if you rename the license and remove
-      any references to the name of the license steward (except to note that
-      such modified license differs from this License).
-
-10.4. Distributing Source Code Form that is Incompatible With Secondary
-      Licenses If You choose to distribute Source Code Form that is
-      Incompatible With Secondary Licenses under the terms of this version of
-      the License, the notice described in Exhibit B of this License must be
-      attached.
-
-Exhibit A - Source Code Form License Notice
-
-      This Source Code Form is subject to the
-      terms of the Mozilla Public License, v.
-      2.0. If a copy of the MPL was not
-      distributed with this file, You can
-      obtain one at
-      https://mozilla.org/MPL/2.0/.
-
-If it is not possible or desirable to put the notice in a particular file,
-then You may include the notice in a location (such as a LICENSE file in a
-relevant directory) where a recipient would be likely to look for such a
-notice.
-
-You may add additional accurate notices of copyright ownership.
-
-Exhibit B - "Incompatible With Secondary Licenses" Notice
-
-      This Source Code Form is "Incompatible
-      With Secondary Licenses", as defined by
-      the Mozilla Public License, v. 2.0.
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__init__.py
deleted file mode 100644
index 4f612bd..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__init__.py
+++ /dev/null
@@ -1,34 +0,0 @@
-from functools import reduce
-from typing import Any, Callable, Dict
-
-from . import formats
-from .error_reporting import detailed_errors, ValidationError
-from .extra_validations import EXTRA_VALIDATIONS
-from .fastjsonschema_exceptions import JsonSchemaException, JsonSchemaValueException
-from .fastjsonschema_validations import validate as _validate
-
-__all__ = [
-    "validate",
-    "FORMAT_FUNCTIONS",
-    "EXTRA_VALIDATIONS",
-    "ValidationError",
-    "JsonSchemaException",
-    "JsonSchemaValueException",
-]
-
-
-FORMAT_FUNCTIONS: Dict[str, Callable[[str], bool]] = {
-    fn.__name__.replace("_", "-"): fn
-    for fn in formats.__dict__.values()
-    if callable(fn) and not fn.__name__.startswith("_")
-}
-
-
-def validate(data: Any) -> bool:
-    """Validate the given ``data`` object using JSON Schema
-    This function raises ``ValidationError`` if ``data`` is invalid.
-    """
-    with detailed_errors():
-        _validate(data, custom_formats=FORMAT_FUNCTIONS)
-        reduce(lambda acc, fn: fn(acc), EXTRA_VALIDATIONS, data)
-    return True
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 8324d56..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/error_reporting.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/error_reporting.cpython-312.pyc
deleted file mode 100644
index c80e109..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/error_reporting.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/extra_validations.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/extra_validations.cpython-312.pyc
deleted file mode 100644
index 832c453..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/extra_validations.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_exceptions.cpython-312.pyc
deleted file mode 100644
index b065725..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_exceptions.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_validations.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_validations.cpython-312.pyc
deleted file mode 100644
index 7b477ea..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/fastjsonschema_validations.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/formats.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/formats.cpython-312.pyc
deleted file mode 100644
index 220c1b7..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/__pycache__/formats.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/error_reporting.py b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/error_reporting.py
deleted file mode 100644
index 3591231..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/error_reporting.py
+++ /dev/null
@@ -1,336 +0,0 @@
-import io
-import json
-import logging
-import os
-import re
-import typing
-from contextlib import contextmanager
-from textwrap import indent, wrap
-from typing import Any, Dict, Generator, Iterator, List, Optional, Sequence, Union
-
-from .fastjsonschema_exceptions import JsonSchemaValueException
-
-if typing.TYPE_CHECKING:
-    import sys
-
-    if sys.version_info < (3, 11):
-        from typing_extensions import Self
-    else:
-        from typing import Self
-
-_logger = logging.getLogger(__name__)
-
-_MESSAGE_REPLACEMENTS = {
-    "must be named by propertyName definition": "keys must be named by",
-    "one of contains definition": "at least one item that matches",
-    " same as const definition:": "",
-    "only specified items": "only items matching the definition",
-}
-
-_SKIP_DETAILS = (
-    "must not be empty",
-    "is always invalid",
-    "must not be there",
-)
-
-_NEED_DETAILS = {"anyOf", "oneOf", "allOf", "contains", "propertyNames", "not", "items"}
-
-_CAMEL_CASE_SPLITTER = re.compile(r"\W+|([A-Z][^A-Z\W]*)")
-_IDENTIFIER = re.compile(r"^[\w_]+$", re.I)
-
-_TOML_JARGON = {
-    "object": "table",
-    "property": "key",
-    "properties": "keys",
-    "property names": "keys",
-}
-
-_FORMATS_HELP = """
-For more details about `format` see
-https://validate-pyproject.readthedocs.io/en/latest/api/validate_pyproject.formats.html
-"""
-
-
-class ValidationError(JsonSchemaValueException):
-    """Report violations of a given JSON schema.
-
-    This class extends :exc:`~fastjsonschema.JsonSchemaValueException`
-    by adding the following properties:
-
-    - ``summary``: an improved version of the ``JsonSchemaValueException`` error message
-      with only the necessary information)
-
-    - ``details``: more contextual information about the error like the failing schema
-      itself and the value that violates the schema.
-
-    Depending on the level of the verbosity of the ``logging`` configuration
-    the exception message will be only ``summary`` (default) or a combination of
-    ``summary`` and ``details`` (when the logging level is set to :obj:`logging.DEBUG`).
-    """
-
-    summary = ""
-    details = ""
-    _original_message = ""
-
-    @classmethod
-    def _from_jsonschema(cls, ex: JsonSchemaValueException) -> "Self":
-        formatter = _ErrorFormatting(ex)
-        obj = cls(str(formatter), ex.value, formatter.name, ex.definition, ex.rule)
-        debug_code = os.getenv("JSONSCHEMA_DEBUG_CODE_GENERATION", "false").lower()
-        if debug_code != "false":  # pragma: no cover
-            obj.__cause__, obj.__traceback__ = ex.__cause__, ex.__traceback__
-        obj._original_message = ex.message
-        obj.summary = formatter.summary
-        obj.details = formatter.details
-        return obj
-
-
-@contextmanager
-def detailed_errors() -> Generator[None, None, None]:
-    try:
-        yield
-    except JsonSchemaValueException as ex:
-        raise ValidationError._from_jsonschema(ex) from None
-
-
-class _ErrorFormatting:
-    def __init__(self, ex: JsonSchemaValueException):
-        self.ex = ex
-        self.name = f"`{self._simplify_name(ex.name)}`"
-        self._original_message: str = self.ex.message.replace(ex.name, self.name)
-        self._summary = ""
-        self._details = ""
-
-    def __str__(self) -> str:
-        if _logger.getEffectiveLevel() <= logging.DEBUG and self.details:
-            return f"{self.summary}\n\n{self.details}"
-
-        return self.summary
-
-    @property
-    def summary(self) -> str:
-        if not self._summary:
-            self._summary = self._expand_summary()
-
-        return self._summary
-
-    @property
-    def details(self) -> str:
-        if not self._details:
-            self._details = self._expand_details()
-
-        return self._details
-
-    @staticmethod
-    def _simplify_name(name: str) -> str:
-        x = len("data.")
-        return name[x:] if name.startswith("data.") else name
-
-    def _expand_summary(self) -> str:
-        msg = self._original_message
-
-        for bad, repl in _MESSAGE_REPLACEMENTS.items():
-            msg = msg.replace(bad, repl)
-
-        if any(substring in msg for substring in _SKIP_DETAILS):
-            return msg
-
-        schema = self.ex.rule_definition
-        if self.ex.rule in _NEED_DETAILS and schema:
-            summary = _SummaryWriter(_TOML_JARGON)
-            return f"{msg}:\n\n{indent(summary(schema), '    ')}"
-
-        return msg
-
-    def _expand_details(self) -> str:
-        optional = []
-        definition = self.ex.definition or {}
-        desc_lines = definition.pop("$$description", [])
-        desc = definition.pop("description", None) or " ".join(desc_lines)
-        if desc:
-            description = "\n".join(
-                wrap(
-                    desc,
-                    width=80,
-                    initial_indent="    ",
-                    subsequent_indent="    ",
-                    break_long_words=False,
-                )
-            )
-            optional.append(f"DESCRIPTION:\n{description}")
-        schema = json.dumps(definition, indent=4)
-        value = json.dumps(self.ex.value, indent=4)
-        defaults = [
-            f"GIVEN VALUE:\n{indent(value, '    ')}",
-            f"OFFENDING RULE: {self.ex.rule!r}",
-            f"DEFINITION:\n{indent(schema, '    ')}",
-        ]
-        msg = "\n\n".join(optional + defaults)
-        epilog = f"\n{_FORMATS_HELP}" if "format" in msg.lower() else ""
-        return msg + epilog
-
-
-class _SummaryWriter:
-    _IGNORE = frozenset(("description", "default", "title", "examples"))
-
-    def __init__(self, jargon: Optional[Dict[str, str]] = None):
-        self.jargon: Dict[str, str] = jargon or {}
-        # Clarify confusing terms
-        self._terms = {
-            "anyOf": "at least one of the following",
-            "oneOf": "exactly one of the following",
-            "allOf": "all of the following",
-            "not": "(*NOT* the following)",
-            "prefixItems": f"{self._jargon('items')} (in order)",
-            "items": "items",
-            "contains": "contains at least one of",
-            "propertyNames": (
-                f"non-predefined acceptable {self._jargon('property names')}"
-            ),
-            "patternProperties": f"{self._jargon('properties')} named via pattern",
-            "const": "predefined value",
-            "enum": "one of",
-        }
-        # Attributes that indicate that the definition is easy and can be done
-        # inline (e.g. string and number)
-        self._guess_inline_defs = [
-            "enum",
-            "const",
-            "maxLength",
-            "minLength",
-            "pattern",
-            "format",
-            "minimum",
-            "maximum",
-            "exclusiveMinimum",
-            "exclusiveMaximum",
-            "multipleOf",
-        ]
-
-    def _jargon(self, term: Union[str, List[str]]) -> Union[str, List[str]]:
-        if isinstance(term, list):
-            return [self.jargon.get(t, t) for t in term]
-        return self.jargon.get(term, term)
-
-    def __call__(
-        self,
-        schema: Union[dict, List[dict]],
-        prefix: str = "",
-        *,
-        _path: Sequence[str] = (),
-    ) -> str:
-        if isinstance(schema, list):
-            return self._handle_list(schema, prefix, _path)
-
-        filtered = self._filter_unecessary(schema, _path)
-        simple = self._handle_simple_dict(filtered, _path)
-        if simple:
-            return f"{prefix}{simple}"
-
-        child_prefix = self._child_prefix(prefix, "  ")
-        item_prefix = self._child_prefix(prefix, "- ")
-        indent = len(prefix) * " "
-        with io.StringIO() as buffer:
-            for i, (key, value) in enumerate(filtered.items()):
-                child_path = [*_path, key]
-                line_prefix = prefix if i == 0 else indent
-                buffer.write(f"{line_prefix}{self._label(child_path)}:")
-                # ^  just the first item should receive the complete prefix
-                if isinstance(value, dict):
-                    filtered = self._filter_unecessary(value, child_path)
-                    simple = self._handle_simple_dict(filtered, child_path)
-                    buffer.write(
-                        f" {simple}"
-                        if simple
-                        else f"\n{self(value, child_prefix, _path=child_path)}"
-                    )
-                elif isinstance(value, list) and (
-                    key != "type" or self._is_property(child_path)
-                ):
-                    children = self._handle_list(value, item_prefix, child_path)
-                    sep = " " if children.startswith("[") else "\n"
-                    buffer.write(f"{sep}{children}")
-                else:
-                    buffer.write(f" {self._value(value, child_path)}\n")
-            return buffer.getvalue()
-
-    def _is_unecessary(self, path: Sequence[str]) -> bool:
-        if self._is_property(path) or not path:  # empty path => instruction @ root
-            return False
-        key = path[-1]
-        return any(key.startswith(k) for k in "$_") or key in self._IGNORE
-
-    def _filter_unecessary(
-        self, schema: Dict[str, Any], path: Sequence[str]
-    ) -> Dict[str, Any]:
-        return {
-            key: value
-            for key, value in schema.items()
-            if not self._is_unecessary([*path, key])
-        }
-
-    def _handle_simple_dict(self, value: dict, path: Sequence[str]) -> Optional[str]:
-        inline = any(p in value for p in self._guess_inline_defs)
-        simple = not any(isinstance(v, (list, dict)) for v in value.values())
-        if inline or simple:
-            return f"{{{', '.join(self._inline_attrs(value, path))}}}\n"
-        return None
-
-    def _handle_list(
-        self, schemas: list, prefix: str = "", path: Sequence[str] = ()
-    ) -> str:
-        if self._is_unecessary(path):
-            return ""
-
-        repr_ = repr(schemas)
-        if all(not isinstance(e, (dict, list)) for e in schemas) and len(repr_) < 60:
-            return f"{repr_}\n"
-
-        item_prefix = self._child_prefix(prefix, "- ")
-        return "".join(
-            self(v, item_prefix, _path=[*path, f"[{i}]"]) for i, v in enumerate(schemas)
-        )
-
-    def _is_property(self, path: Sequence[str]) -> bool:
-        """Check if the given path can correspond to an arbitrarily named property"""
-        counter = 0
-        for key in path[-2::-1]:
-            if key not in {"properties", "patternProperties"}:
-                break
-            counter += 1
-
-        # If the counter if even, the path correspond to a JSON Schema keyword
-        # otherwise it can be any arbitrary string naming a property
-        return counter % 2 == 1
-
-    def _label(self, path: Sequence[str]) -> str:
-        *parents, key = path
-        if not self._is_property(path):
-            norm_key = _separate_terms(key)
-            return self._terms.get(key) or " ".join(self._jargon(norm_key))
-
-        if parents[-1] == "patternProperties":
-            return f"(regex {key!r})"
-        return repr(key)  # property name
-
-    def _value(self, value: Any, path: Sequence[str]) -> str:
-        if path[-1] == "type" and not self._is_property(path):
-            type_ = self._jargon(value)
-            return f"[{', '.join(type_)}]" if isinstance(type_, list) else type_
-        return repr(value)
-
-    def _inline_attrs(self, schema: dict, path: Sequence[str]) -> Iterator[str]:
-        for key, value in schema.items():
-            child_path = [*path, key]
-            yield f"{self._label(child_path)}: {self._value(value, child_path)}"
-
-    def _child_prefix(self, parent_prefix: str, child_prefix: str) -> str:
-        return len(parent_prefix) * " " + child_prefix
-
-
-def _separate_terms(word: str) -> List[str]:
-    """
-    >>> _separate_terms("FooBar-foo")
-    ['foo', 'bar', 'foo']
-    """
-    return [w.lower() for w in _CAMEL_CASE_SPLITTER.split(word) if w]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/extra_validations.py b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/extra_validations.py
deleted file mode 100644
index 789411d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/extra_validations.py
+++ /dev/null
@@ -1,82 +0,0 @@
-"""The purpose of this module is implement PEP 621 validations that are
-difficult to express as a JSON Schema (or that are not supported by the current
-JSON Schema library).
-"""
-
-from inspect import cleandoc
-from typing import Mapping, TypeVar
-
-from .error_reporting import ValidationError
-
-T = TypeVar("T", bound=Mapping)
-
-
-class RedefiningStaticFieldAsDynamic(ValidationError):
-    _DESC = """According to PEP 621:
-
-    Build back-ends MUST raise an error if the metadata specifies a field
-    statically as well as being listed in dynamic.
-    """
-    __doc__ = _DESC
-    _URL = (
-        "https://packaging.python.org/en/latest/specifications/"
-        "pyproject-toml/#dynamic"
-    )
-
-
-class IncludedDependencyGroupMustExist(ValidationError):
-    _DESC = """An included dependency group must exist and must not be cyclic.
-    """
-    __doc__ = _DESC
-    _URL = "https://peps.python.org/pep-0735/"
-
-
-def validate_project_dynamic(pyproject: T) -> T:
-    project_table = pyproject.get("project", {})
-    dynamic = project_table.get("dynamic", [])
-
-    for field in dynamic:
-        if field in project_table:
-            raise RedefiningStaticFieldAsDynamic(
-                message=f"You cannot provide a value for `project.{field}` and "
-                "list it under `project.dynamic` at the same time",
-                value={
-                    field: project_table[field],
-                    "...": " # ...",
-                    "dynamic": dynamic,
-                },
-                name=f"data.project.{field}",
-                definition={
-                    "description": cleandoc(RedefiningStaticFieldAsDynamic._DESC),
-                    "see": RedefiningStaticFieldAsDynamic._URL,
-                },
-                rule="PEP 621",
-            )
-
-    return pyproject
-
-
-def validate_include_depenency(pyproject: T) -> T:
-    dependency_groups = pyproject.get("dependency-groups", {})
-    for key, value in dependency_groups.items():
-        for each in value:
-            if (
-                isinstance(each, dict)
-                and (include_group := each.get("include-group"))
-                and include_group not in dependency_groups
-            ):
-                raise IncludedDependencyGroupMustExist(
-                    message=f"The included dependency group {include_group} doesn't exist",
-                    value=each,
-                    name=f"data.dependency_groups.{key}",
-                    definition={
-                        "description": cleandoc(IncludedDependencyGroupMustExist._DESC),
-                        "see": IncludedDependencyGroupMustExist._URL,
-                    },
-                    rule="PEP 735",
-                )
-    # TODO: check for `include-group` cycles (can be conditional to graphlib)
-    return pyproject
-
-
-EXTRA_VALIDATIONS = (validate_project_dynamic, validate_include_depenency)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/fastjsonschema_exceptions.py b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/fastjsonschema_exceptions.py
deleted file mode 100644
index d2dddd6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/fastjsonschema_exceptions.py
+++ /dev/null
@@ -1,51 +0,0 @@
-import re
-
-
-SPLIT_RE = re.compile(r'[\.\[\]]+')
-
-
-class JsonSchemaException(ValueError):
-    """
-    Base exception of ``fastjsonschema`` library.
-    """
-
-
-class JsonSchemaValueException(JsonSchemaException):
-    """
-    Exception raised by validation function. Available properties:
-
-     * ``message`` containing human-readable information what is wrong (e.g. ``data.property[index] must be smaller than or equal to 42``),
-     * invalid ``value`` (e.g. ``60``),
-     * ``name`` of a path in the data structure (e.g. ``data.property[index]``),
-     * ``path`` as an array in the data structure (e.g. ``['data', 'property', 'index']``),
-     * the whole ``definition`` which the ``value`` has to fulfil (e.g. ``{'type': 'number', 'maximum': 42}``),
-     * ``rule`` which the ``value`` is breaking (e.g. ``maximum``)
-     * and ``rule_definition`` (e.g. ``42``).
-
-    .. versionchanged:: 2.14.0
-        Added all extra properties.
-    """
-
-    def __init__(self, message, value=None, name=None, definition=None, rule=None):
-        super().__init__(message)
-        self.message = message
-        self.value = value
-        self.name = name
-        self.definition = definition
-        self.rule = rule
-
-    @property
-    def path(self):
-        return [item for item in SPLIT_RE.split(self.name) if item != '']
-
-    @property
-    def rule_definition(self):
-        if not self.rule or not self.definition:
-            return None
-        return self.definition.get(self.rule)
-
-
-class JsonSchemaDefinitionException(JsonSchemaException):
-    """
-    Exception raised by generator of validation function.
-    """
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/fastjsonschema_validations.py b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/fastjsonschema_validations.py
deleted file mode 100644
index c69368a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/fastjsonschema_validations.py
+++ /dev/null
@@ -1,1412 +0,0 @@
-# noqa
-# ruff: noqa
-# flake8: noqa
-# pylint: skip-file
-# mypy: ignore-errors
-# yapf: disable
-# pylama:skip=1
-
-
-# *** PLEASE DO NOT MODIFY DIRECTLY: Automatically generated code *** 
-
-
-VERSION = "2.20.0"
-from decimal import Decimal
-import re
-from .fastjsonschema_exceptions import JsonSchemaValueException
-
-
-REGEX_PATTERNS = {
-    '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$': re.compile('^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])\\Z'),
-    '^.*$': re.compile('^.*$'),
-    '.+': re.compile('.+'),
-    '^.+$': re.compile('^.+$'),
-    'idn-email_re_pattern': re.compile('^[^@]+@[^@]+\\.[^@]+\\Z')
-}
-
-NoneType = type(None)
-
-def validate(data, custom_formats={}, name_prefix=None):
-    validate_https___packaging_python_org_en_latest_specifications_declaring_build_dependencies(data, custom_formats, (name_prefix or "data") + "")
-    return data
-
-def validate_https___packaging_python_org_en_latest_specifications_declaring_build_dependencies(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/declaring-build-dependencies/', 'title': 'Data structure for ``pyproject.toml`` files', '$$description': ['File format containing build-time configurations for the Python ecosystem. ', ':pep:`517` initially defined a build-system independent format for source trees', 'which was complemented by :pep:`518` to provide a way of specifying dependencies ', 'for building Python projects.', 'Please notice the ``project`` table (as initially defined in  :pep:`621`) is not included', 'in this schema and should be considered separately.'], 'type': 'object', 'additionalProperties': False, 'properties': {'build-system': {'type': 'object', 'description': 'Table used to store build-related data', 'additionalProperties': False, 'properties': {'requires': {'type': 'array', '$$description': ['List of dependencies in the :pep:`508` format required to execute the build', 'system. Please notice that the resulting dependency graph', '**MUST NOT contain cycles**'], 'items': {'type': 'string'}}, 'build-backend': {'type': 'string', 'description': 'Python object that will be used to perform the build according to :pep:`517`', 'format': 'pep517-backend-reference'}, 'backend-path': {'type': 'array', '$$description': ['List of directories to be prepended to ``sys.path`` when loading the', 'back-end, and running its hooks'], 'items': {'type': 'string', '$comment': 'Should be a path (TODO: enforce it with format?)'}}}, 'required': ['requires']}, 'project': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/pyproject-toml/', 'title': 'Package metadata stored in the ``project`` table', '$$description': ['Data structure for the **project** table inside ``pyproject.toml``', '(as initially defined in :pep:`621`)'], 'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, 'version': {'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, 'description': {'type': 'string', '$$description': ['The `summary description of the project', '`_']}, 'readme': {'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, 'requires-python': {'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, 'license': {'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, 'license-files': {'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, 'authors': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, 'maintainers': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, 'keywords': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, 'classifiers': {'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, 'urls': {'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, 'scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create command-line wrappers for the given', '`entry points `_.']}, 'gui-scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create GUI wrappers for the given', '`entry points `_.', 'The difference between ``scripts`` and ``gui-scripts`` is only relevant in', 'Windows.']}, 'entry-points': {'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$ref': '#/definitions/entry-point-group'}}}, 'dependencies': {'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$ref': '#/definitions/dependency'}}, 'optional-dependencies': {'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$ref': '#/definitions/dependency'}}}}, 'dynamic': {'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}}, 'required': ['name'], 'additionalProperties': False, 'allOf': [{'if': {'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, 'then': {'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}}, {'if': {'required': ['license-files']}, 'then': {'properties': {'license': {'type': 'string'}}}}], 'definitions': {'author': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, 'entry-point-group': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'dependency': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}, 'tool': {'type': 'object', 'properties': {'distutils': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/deprecated/distutils/configfile.html', 'title': '``tool.distutils`` table', '$$description': ['**EXPERIMENTAL** (NOT OFFICIALLY SUPPORTED): Use ``tool.distutils``', 'subtables to configure arguments for ``distutils`` commands.', 'Originally, ``distutils`` allowed developers to configure arguments for', '``setup.py`` commands via `distutils configuration files', '`_.', 'See also `the old Python docs _`.'], 'type': 'object', 'properties': {'global': {'type': 'object', 'description': 'Global options applied to all ``distutils`` commands'}}, 'patternProperties': {'.+': {'type': 'object'}}, '$comment': 'TODO: Is there a practical way of making this schema more specific?'}, 'setuptools': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html', 'title': '``tool.setuptools`` table', '$$description': ['``setuptools``-specific configurations that can be set by users that require', 'customization.', 'These configurations are completely optional and probably can be skipped when', 'creating simple packages. They are equivalent to some of the `Keywords', '`_', 'used by the ``setup.py`` file, and can be set via the ``tool.setuptools`` table.', 'It considers only ``setuptools`` `parameters', '`_', 'that are not covered by :pep:`621`; and intentionally excludes ``dependency_links``', 'and ``setup_requires`` (incompatible with modern workflows/standards).'], 'type': 'object', 'additionalProperties': False, 'properties': {'platforms': {'type': 'array', 'items': {'type': 'string'}}, 'provides': {'$$description': ['Package and virtual package names contained within this package', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'obsoletes': {'$$description': ['Packages which this package renders obsolete', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'zip-safe': {'$$description': ['Whether the project can be safely installed and run from a zip file.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'boolean'}, 'script-files': {'$$description': ['Legacy way of defining scripts (entry-points are preferred).', 'Equivalent to the ``script`` keyword in ``setup.py``', '(it was renamed to avoid confusion with entry-point based ``project.scripts``', 'defined in :pep:`621`).', '**DISCOURAGED**: generic script wrappers are tricky and may not work properly.', 'Whenever possible, please use ``project.scripts`` instead.'], 'type': 'array', 'items': {'type': 'string'}, '$comment': 'TODO: is this field deprecated/should be removed?'}, 'eager-resources': {'$$description': ['Resources that should be extracted together, if any of them is needed,', 'or if any C extensions included in the project are imported.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'array', 'items': {'type': 'string'}}, 'packages': {'$$description': ['Packages that should be included in the distribution.', 'It can be given either as a list of package identifiers', 'or as a ``dict``-like structure with a single key ``find``', 'which corresponds to a dynamic call to', '``setuptools.config.expand.find_packages`` function.', 'The ``find`` key is associated with a nested ``dict``-like structure that can', 'contain ``where``, ``include``, ``exclude`` and ``namespaces`` keys,', 'mimicking the keyword arguments of the associated function.'], 'oneOf': [{'title': 'Array of Python package identifiers', 'type': 'array', 'items': {'$ref': '#/definitions/package-name'}}, {'$ref': '#/definitions/find-directive'}]}, 'package-dir': {'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$ref': '#/definitions/package-name'}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, 'package-data': {'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'include-package-data': {'$$description': ['Automatically include any data files inside the package directories', 'that are specified by ``MANIFEST.in``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'boolean'}, 'exclude-package-data': {'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'namespace-packages': {'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'https://setuptools.pypa.io/en/latest/userguide/package_discovery.html', 'description': '**DEPRECATED**: use implicit namespaces instead (:pep:`420`).'}, 'py-modules': {'description': 'Modules that setuptools will manipulate', 'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'TODO: clarify the relationship with ``packages``'}, 'ext-modules': {'description': 'Extension modules to be compiled by setuptools', 'type': 'array', 'items': {'$ref': '#/definitions/ext-module'}}, 'data-files': {'$$description': ['``dict``-like structure where each key represents a directory and', 'the value is a list of glob patterns that should be installed in them.', '**DISCOURAGED**: please notice this might not work as expected with wheels.', 'Whenever possible, consider using data files inside the package directories', '(or create a new namespace package that only contains data files).', 'See `data files support', '`_.'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'cmdclass': {'$$description': ['Mapping of distutils-style command names to ``setuptools.Command`` subclasses', 'which in turn should be represented by strings with a qualified class name', '(i.e., "dotted" form with module), e.g.::\n\n', '    cmdclass = {mycmd = "pkg.subpkg.module.CommandClass"}\n\n', 'The command class should be a directly defined at the top-level of the', 'containing module (no class nesting).'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'string', 'format': 'python-qualified-identifier'}}}, 'license-files': {'type': 'array', 'items': {'type': 'string'}, '$$description': ['**PROVISIONAL**: list of glob patterns for all license files being distributed.', '(likely to become standard with :pep:`639`).', "By default: ``['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']``"], '$comment': 'TODO: revise if PEP 639 is accepted. Probably ``project.license-files``?'}, 'dynamic': {'type': 'object', 'description': 'Instructions for loading :pep:`621`-related metadata dynamically', 'additionalProperties': False, 'properties': {'version': {'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'$ref': '#/definitions/attr-directive'}, {'$ref': '#/definitions/file-directive'}]}, 'classifiers': {'$ref': '#/definitions/file-directive'}, 'description': {'$ref': '#/definitions/file-directive'}, 'entry-points': {'$ref': '#/definitions/file-directive'}, 'dependencies': {'$ref': '#/definitions/file-directive-for-dependencies'}, 'optional-dependencies': {'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'$ref': '#/definitions/file-directive-for-dependencies'}}}, 'readme': {'type': 'object', 'anyOf': [{'$ref': '#/definitions/file-directive'}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'$ref': '#/definitions/file-directive/properties/file'}}, 'additionalProperties': False}], 'required': ['file']}}}}, 'definitions': {'package-name': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}, 'ext-module': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, 'file-directive': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'file-directive-for-dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}, 'attr-directive': {'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, 'find-directive': {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}}}}}, 'dependency-groups': {'type': 'object', 'description': 'Dependency groups following PEP 735', 'additionalProperties': False, 'patternProperties': {'^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$': {'type': 'array', 'items': {'oneOf': [{'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, {'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}]}}}}}, 'project': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/pyproject-toml/', 'title': 'Package metadata stored in the ``project`` table', '$$description': ['Data structure for the **project** table inside ``pyproject.toml``', '(as initially defined in :pep:`621`)'], 'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, 'version': {'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, 'description': {'type': 'string', '$$description': ['The `summary description of the project', '`_']}, 'readme': {'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, 'requires-python': {'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, 'license': {'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, 'license-files': {'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, 'authors': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, 'maintainers': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, 'keywords': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, 'classifiers': {'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, 'urls': {'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, 'scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create command-line wrappers for the given', '`entry points `_.']}, 'gui-scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create GUI wrappers for the given', '`entry points `_.', 'The difference between ``scripts`` and ``gui-scripts`` is only relevant in', 'Windows.']}, 'entry-points': {'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$ref': '#/definitions/entry-point-group'}}}, 'dependencies': {'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$ref': '#/definitions/dependency'}}, 'optional-dependencies': {'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$ref': '#/definitions/dependency'}}}}, 'dynamic': {'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}}, 'required': ['name'], 'additionalProperties': False, 'allOf': [{'if': {'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, 'then': {'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}}, {'if': {'required': ['license-files']}, 'then': {'properties': {'license': {'type': 'string'}}}}], 'definitions': {'author': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, 'entry-point-group': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'dependency': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data_keys = set(data.keys())
-        if "build-system" in data_keys:
-            data_keys.remove("build-system")
-            data__buildsystem = data["build-system"]
-            if not isinstance(data__buildsystem, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system must be object", value=data__buildsystem, name="" + (name_prefix or "data") + ".build-system", definition={'type': 'object', 'description': 'Table used to store build-related data', 'additionalProperties': False, 'properties': {'requires': {'type': 'array', '$$description': ['List of dependencies in the :pep:`508` format required to execute the build', 'system. Please notice that the resulting dependency graph', '**MUST NOT contain cycles**'], 'items': {'type': 'string'}}, 'build-backend': {'type': 'string', 'description': 'Python object that will be used to perform the build according to :pep:`517`', 'format': 'pep517-backend-reference'}, 'backend-path': {'type': 'array', '$$description': ['List of directories to be prepended to ``sys.path`` when loading the', 'back-end, and running its hooks'], 'items': {'type': 'string', '$comment': 'Should be a path (TODO: enforce it with format?)'}}}, 'required': ['requires']}, rule='type')
-            data__buildsystem_is_dict = isinstance(data__buildsystem, dict)
-            if data__buildsystem_is_dict:
-                data__buildsystem__missing_keys = set(['requires']) - data__buildsystem.keys()
-                if data__buildsystem__missing_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system must contain " + (str(sorted(data__buildsystem__missing_keys)) + " properties"), value=data__buildsystem, name="" + (name_prefix or "data") + ".build-system", definition={'type': 'object', 'description': 'Table used to store build-related data', 'additionalProperties': False, 'properties': {'requires': {'type': 'array', '$$description': ['List of dependencies in the :pep:`508` format required to execute the build', 'system. Please notice that the resulting dependency graph', '**MUST NOT contain cycles**'], 'items': {'type': 'string'}}, 'build-backend': {'type': 'string', 'description': 'Python object that will be used to perform the build according to :pep:`517`', 'format': 'pep517-backend-reference'}, 'backend-path': {'type': 'array', '$$description': ['List of directories to be prepended to ``sys.path`` when loading the', 'back-end, and running its hooks'], 'items': {'type': 'string', '$comment': 'Should be a path (TODO: enforce it with format?)'}}}, 'required': ['requires']}, rule='required')
-                data__buildsystem_keys = set(data__buildsystem.keys())
-                if "requires" in data__buildsystem_keys:
-                    data__buildsystem_keys.remove("requires")
-                    data__buildsystem__requires = data__buildsystem["requires"]
-                    if not isinstance(data__buildsystem__requires, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system.requires must be array", value=data__buildsystem__requires, name="" + (name_prefix or "data") + ".build-system.requires", definition={'type': 'array', '$$description': ['List of dependencies in the :pep:`508` format required to execute the build', 'system. Please notice that the resulting dependency graph', '**MUST NOT contain cycles**'], 'items': {'type': 'string'}}, rule='type')
-                    data__buildsystem__requires_is_list = isinstance(data__buildsystem__requires, (list, tuple))
-                    if data__buildsystem__requires_is_list:
-                        data__buildsystem__requires_len = len(data__buildsystem__requires)
-                        for data__buildsystem__requires_x, data__buildsystem__requires_item in enumerate(data__buildsystem__requires):
-                            if not isinstance(data__buildsystem__requires_item, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system.requires[{data__buildsystem__requires_x}]".format(**locals()) + " must be string", value=data__buildsystem__requires_item, name="" + (name_prefix or "data") + ".build-system.requires[{data__buildsystem__requires_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                if "build-backend" in data__buildsystem_keys:
-                    data__buildsystem_keys.remove("build-backend")
-                    data__buildsystem__buildbackend = data__buildsystem["build-backend"]
-                    if not isinstance(data__buildsystem__buildbackend, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system.build-backend must be string", value=data__buildsystem__buildbackend, name="" + (name_prefix or "data") + ".build-system.build-backend", definition={'type': 'string', 'description': 'Python object that will be used to perform the build according to :pep:`517`', 'format': 'pep517-backend-reference'}, rule='type')
-                    if isinstance(data__buildsystem__buildbackend, str):
-                        if not custom_formats["pep517-backend-reference"](data__buildsystem__buildbackend):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system.build-backend must be pep517-backend-reference", value=data__buildsystem__buildbackend, name="" + (name_prefix or "data") + ".build-system.build-backend", definition={'type': 'string', 'description': 'Python object that will be used to perform the build according to :pep:`517`', 'format': 'pep517-backend-reference'}, rule='format')
-                if "backend-path" in data__buildsystem_keys:
-                    data__buildsystem_keys.remove("backend-path")
-                    data__buildsystem__backendpath = data__buildsystem["backend-path"]
-                    if not isinstance(data__buildsystem__backendpath, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system.backend-path must be array", value=data__buildsystem__backendpath, name="" + (name_prefix or "data") + ".build-system.backend-path", definition={'type': 'array', '$$description': ['List of directories to be prepended to ``sys.path`` when loading the', 'back-end, and running its hooks'], 'items': {'type': 'string', '$comment': 'Should be a path (TODO: enforce it with format?)'}}, rule='type')
-                    data__buildsystem__backendpath_is_list = isinstance(data__buildsystem__backendpath, (list, tuple))
-                    if data__buildsystem__backendpath_is_list:
-                        data__buildsystem__backendpath_len = len(data__buildsystem__backendpath)
-                        for data__buildsystem__backendpath_x, data__buildsystem__backendpath_item in enumerate(data__buildsystem__backendpath):
-                            if not isinstance(data__buildsystem__backendpath_item, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system.backend-path[{data__buildsystem__backendpath_x}]".format(**locals()) + " must be string", value=data__buildsystem__backendpath_item, name="" + (name_prefix or "data") + ".build-system.backend-path[{data__buildsystem__backendpath_x}]".format(**locals()) + "", definition={'type': 'string', '$comment': 'Should be a path (TODO: enforce it with format?)'}, rule='type')
-                if data__buildsystem_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".build-system must not contain "+str(data__buildsystem_keys)+" properties", value=data__buildsystem, name="" + (name_prefix or "data") + ".build-system", definition={'type': 'object', 'description': 'Table used to store build-related data', 'additionalProperties': False, 'properties': {'requires': {'type': 'array', '$$description': ['List of dependencies in the :pep:`508` format required to execute the build', 'system. Please notice that the resulting dependency graph', '**MUST NOT contain cycles**'], 'items': {'type': 'string'}}, 'build-backend': {'type': 'string', 'description': 'Python object that will be used to perform the build according to :pep:`517`', 'format': 'pep517-backend-reference'}, 'backend-path': {'type': 'array', '$$description': ['List of directories to be prepended to ``sys.path`` when loading the', 'back-end, and running its hooks'], 'items': {'type': 'string', '$comment': 'Should be a path (TODO: enforce it with format?)'}}}, 'required': ['requires']}, rule='additionalProperties')
-        if "project" in data_keys:
-            data_keys.remove("project")
-            data__project = data["project"]
-            validate_https___packaging_python_org_en_latest_specifications_pyproject_toml(data__project, custom_formats, (name_prefix or "data") + ".project")
-        if "tool" in data_keys:
-            data_keys.remove("tool")
-            data__tool = data["tool"]
-            if not isinstance(data__tool, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".tool must be object", value=data__tool, name="" + (name_prefix or "data") + ".tool", definition={'type': 'object', 'properties': {'distutils': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/deprecated/distutils/configfile.html', 'title': '``tool.distutils`` table', '$$description': ['**EXPERIMENTAL** (NOT OFFICIALLY SUPPORTED): Use ``tool.distutils``', 'subtables to configure arguments for ``distutils`` commands.', 'Originally, ``distutils`` allowed developers to configure arguments for', '``setup.py`` commands via `distutils configuration files', '`_.', 'See also `the old Python docs _`.'], 'type': 'object', 'properties': {'global': {'type': 'object', 'description': 'Global options applied to all ``distutils`` commands'}}, 'patternProperties': {'.+': {'type': 'object'}}, '$comment': 'TODO: Is there a practical way of making this schema more specific?'}, 'setuptools': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html', 'title': '``tool.setuptools`` table', '$$description': ['``setuptools``-specific configurations that can be set by users that require', 'customization.', 'These configurations are completely optional and probably can be skipped when', 'creating simple packages. They are equivalent to some of the `Keywords', '`_', 'used by the ``setup.py`` file, and can be set via the ``tool.setuptools`` table.', 'It considers only ``setuptools`` `parameters', '`_', 'that are not covered by :pep:`621`; and intentionally excludes ``dependency_links``', 'and ``setup_requires`` (incompatible with modern workflows/standards).'], 'type': 'object', 'additionalProperties': False, 'properties': {'platforms': {'type': 'array', 'items': {'type': 'string'}}, 'provides': {'$$description': ['Package and virtual package names contained within this package', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'obsoletes': {'$$description': ['Packages which this package renders obsolete', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'zip-safe': {'$$description': ['Whether the project can be safely installed and run from a zip file.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'boolean'}, 'script-files': {'$$description': ['Legacy way of defining scripts (entry-points are preferred).', 'Equivalent to the ``script`` keyword in ``setup.py``', '(it was renamed to avoid confusion with entry-point based ``project.scripts``', 'defined in :pep:`621`).', '**DISCOURAGED**: generic script wrappers are tricky and may not work properly.', 'Whenever possible, please use ``project.scripts`` instead.'], 'type': 'array', 'items': {'type': 'string'}, '$comment': 'TODO: is this field deprecated/should be removed?'}, 'eager-resources': {'$$description': ['Resources that should be extracted together, if any of them is needed,', 'or if any C extensions included in the project are imported.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'array', 'items': {'type': 'string'}}, 'packages': {'$$description': ['Packages that should be included in the distribution.', 'It can be given either as a list of package identifiers', 'or as a ``dict``-like structure with a single key ``find``', 'which corresponds to a dynamic call to', '``setuptools.config.expand.find_packages`` function.', 'The ``find`` key is associated with a nested ``dict``-like structure that can', 'contain ``where``, ``include``, ``exclude`` and ``namespaces`` keys,', 'mimicking the keyword arguments of the associated function.'], 'oneOf': [{'title': 'Array of Python package identifiers', 'type': 'array', 'items': {'$ref': '#/definitions/package-name'}}, {'$ref': '#/definitions/find-directive'}]}, 'package-dir': {'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$ref': '#/definitions/package-name'}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, 'package-data': {'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'include-package-data': {'$$description': ['Automatically include any data files inside the package directories', 'that are specified by ``MANIFEST.in``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'boolean'}, 'exclude-package-data': {'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'namespace-packages': {'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'https://setuptools.pypa.io/en/latest/userguide/package_discovery.html', 'description': '**DEPRECATED**: use implicit namespaces instead (:pep:`420`).'}, 'py-modules': {'description': 'Modules that setuptools will manipulate', 'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'TODO: clarify the relationship with ``packages``'}, 'ext-modules': {'description': 'Extension modules to be compiled by setuptools', 'type': 'array', 'items': {'$ref': '#/definitions/ext-module'}}, 'data-files': {'$$description': ['``dict``-like structure where each key represents a directory and', 'the value is a list of glob patterns that should be installed in them.', '**DISCOURAGED**: please notice this might not work as expected with wheels.', 'Whenever possible, consider using data files inside the package directories', '(or create a new namespace package that only contains data files).', 'See `data files support', '`_.'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'cmdclass': {'$$description': ['Mapping of distutils-style command names to ``setuptools.Command`` subclasses', 'which in turn should be represented by strings with a qualified class name', '(i.e., "dotted" form with module), e.g.::\n\n', '    cmdclass = {mycmd = "pkg.subpkg.module.CommandClass"}\n\n', 'The command class should be a directly defined at the top-level of the', 'containing module (no class nesting).'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'string', 'format': 'python-qualified-identifier'}}}, 'license-files': {'type': 'array', 'items': {'type': 'string'}, '$$description': ['**PROVISIONAL**: list of glob patterns for all license files being distributed.', '(likely to become standard with :pep:`639`).', "By default: ``['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']``"], '$comment': 'TODO: revise if PEP 639 is accepted. Probably ``project.license-files``?'}, 'dynamic': {'type': 'object', 'description': 'Instructions for loading :pep:`621`-related metadata dynamically', 'additionalProperties': False, 'properties': {'version': {'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'$ref': '#/definitions/attr-directive'}, {'$ref': '#/definitions/file-directive'}]}, 'classifiers': {'$ref': '#/definitions/file-directive'}, 'description': {'$ref': '#/definitions/file-directive'}, 'entry-points': {'$ref': '#/definitions/file-directive'}, 'dependencies': {'$ref': '#/definitions/file-directive-for-dependencies'}, 'optional-dependencies': {'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'$ref': '#/definitions/file-directive-for-dependencies'}}}, 'readme': {'type': 'object', 'anyOf': [{'$ref': '#/definitions/file-directive'}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'$ref': '#/definitions/file-directive/properties/file'}}, 'additionalProperties': False}], 'required': ['file']}}}}, 'definitions': {'package-name': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}, 'ext-module': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, 'file-directive': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'file-directive-for-dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}, 'attr-directive': {'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, 'find-directive': {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}}}}}, rule='type')
-            data__tool_is_dict = isinstance(data__tool, dict)
-            if data__tool_is_dict:
-                data__tool_keys = set(data__tool.keys())
-                if "distutils" in data__tool_keys:
-                    data__tool_keys.remove("distutils")
-                    data__tool__distutils = data__tool["distutils"]
-                    validate_https___setuptools_pypa_io_en_latest_deprecated_distutils_configfile_html(data__tool__distutils, custom_formats, (name_prefix or "data") + ".tool.distutils")
-                if "setuptools" in data__tool_keys:
-                    data__tool_keys.remove("setuptools")
-                    data__tool__setuptools = data__tool["setuptools"]
-                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html(data__tool__setuptools, custom_formats, (name_prefix or "data") + ".tool.setuptools")
-        if "dependency-groups" in data_keys:
-            data_keys.remove("dependency-groups")
-            data__dependencygroups = data["dependency-groups"]
-            if not isinstance(data__dependencygroups, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups must be object", value=data__dependencygroups, name="" + (name_prefix or "data") + ".dependency-groups", definition={'type': 'object', 'description': 'Dependency groups following PEP 735', 'additionalProperties': False, 'patternProperties': {'^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$': {'type': 'array', 'items': {'oneOf': [{'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, {'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}]}}}}, rule='type')
-            data__dependencygroups_is_dict = isinstance(data__dependencygroups, dict)
-            if data__dependencygroups_is_dict:
-                data__dependencygroups_keys = set(data__dependencygroups.keys())
-                for data__dependencygroups_key, data__dependencygroups_val in data__dependencygroups.items():
-                    if REGEX_PATTERNS['^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'].search(data__dependencygroups_key):
-                        if data__dependencygroups_key in data__dependencygroups_keys:
-                            data__dependencygroups_keys.remove(data__dependencygroups_key)
-                        if not isinstance(data__dependencygroups_val, (list, tuple)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}".format(**locals()) + " must be array", value=data__dependencygroups_val, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}".format(**locals()) + "", definition={'type': 'array', 'items': {'oneOf': [{'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, {'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}]}}, rule='type')
-                        data__dependencygroups_val_is_list = isinstance(data__dependencygroups_val, (list, tuple))
-                        if data__dependencygroups_val_is_list:
-                            data__dependencygroups_val_len = len(data__dependencygroups_val)
-                            for data__dependencygroups_val_x, data__dependencygroups_val_item in enumerate(data__dependencygroups_val):
-                                data__dependencygroups_val_item_one_of_count1 = 0
-                                if data__dependencygroups_val_item_one_of_count1 < 2:
-                                    try:
-                                        if not isinstance(data__dependencygroups_val_item, (str)):
-                                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + " must be string", value=data__dependencygroups_val_item, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + "", definition={'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, rule='type')
-                                        if isinstance(data__dependencygroups_val_item, str):
-                                            if not custom_formats["pep508"](data__dependencygroups_val_item):
-                                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + " must be pep508", value=data__dependencygroups_val_item, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + "", definition={'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, rule='format')
-                                        data__dependencygroups_val_item_one_of_count1 += 1
-                                    except JsonSchemaValueException: pass
-                                if data__dependencygroups_val_item_one_of_count1 < 2:
-                                    try:
-                                        if not isinstance(data__dependencygroups_val_item, (dict)):
-                                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + " must be object", value=data__dependencygroups_val_item, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + "", definition={'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}, rule='type')
-                                        data__dependencygroups_val_item_is_dict = isinstance(data__dependencygroups_val_item, dict)
-                                        if data__dependencygroups_val_item_is_dict:
-                                            data__dependencygroups_val_item_keys = set(data__dependencygroups_val_item.keys())
-                                            if "include-group" in data__dependencygroups_val_item_keys:
-                                                data__dependencygroups_val_item_keys.remove("include-group")
-                                                data__dependencygroups_val_item__includegroup = data__dependencygroups_val_item["include-group"]
-                                                if not isinstance(data__dependencygroups_val_item__includegroup, (str)):
-                                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}].include-group".format(**locals()) + " must be string", value=data__dependencygroups_val_item__includegroup, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}].include-group".format(**locals()) + "", definition={'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}, rule='type')
-                                                if isinstance(data__dependencygroups_val_item__includegroup, str):
-                                                    if not REGEX_PATTERNS['^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'].search(data__dependencygroups_val_item__includegroup):
-                                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}].include-group".format(**locals()) + " must match pattern ^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$", value=data__dependencygroups_val_item__includegroup, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}].include-group".format(**locals()) + "", definition={'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}, rule='pattern')
-                                            if data__dependencygroups_val_item_keys:
-                                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + " must not contain "+str(data__dependencygroups_val_item_keys)+" properties", value=data__dependencygroups_val_item, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + "", definition={'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}, rule='additionalProperties')
-                                        data__dependencygroups_val_item_one_of_count1 += 1
-                                    except JsonSchemaValueException: pass
-                                if data__dependencygroups_val_item_one_of_count1 != 1:
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + " must be valid exactly by one definition" + (" (" + str(data__dependencygroups_val_item_one_of_count1) + " matches found)"), value=data__dependencygroups_val_item, name="" + (name_prefix or "data") + ".dependency-groups.{data__dependencygroups_key}[{data__dependencygroups_val_x}]".format(**locals()) + "", definition={'oneOf': [{'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, {'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}]}, rule='oneOf')
-                if data__dependencygroups_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependency-groups must not contain "+str(data__dependencygroups_keys)+" properties", value=data__dependencygroups, name="" + (name_prefix or "data") + ".dependency-groups", definition={'type': 'object', 'description': 'Dependency groups following PEP 735', 'additionalProperties': False, 'patternProperties': {'^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$': {'type': 'array', 'items': {'oneOf': [{'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, {'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}]}}}}, rule='additionalProperties')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/declaring-build-dependencies/', 'title': 'Data structure for ``pyproject.toml`` files', '$$description': ['File format containing build-time configurations for the Python ecosystem. ', ':pep:`517` initially defined a build-system independent format for source trees', 'which was complemented by :pep:`518` to provide a way of specifying dependencies ', 'for building Python projects.', 'Please notice the ``project`` table (as initially defined in  :pep:`621`) is not included', 'in this schema and should be considered separately.'], 'type': 'object', 'additionalProperties': False, 'properties': {'build-system': {'type': 'object', 'description': 'Table used to store build-related data', 'additionalProperties': False, 'properties': {'requires': {'type': 'array', '$$description': ['List of dependencies in the :pep:`508` format required to execute the build', 'system. Please notice that the resulting dependency graph', '**MUST NOT contain cycles**'], 'items': {'type': 'string'}}, 'build-backend': {'type': 'string', 'description': 'Python object that will be used to perform the build according to :pep:`517`', 'format': 'pep517-backend-reference'}, 'backend-path': {'type': 'array', '$$description': ['List of directories to be prepended to ``sys.path`` when loading the', 'back-end, and running its hooks'], 'items': {'type': 'string', '$comment': 'Should be a path (TODO: enforce it with format?)'}}}, 'required': ['requires']}, 'project': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/pyproject-toml/', 'title': 'Package metadata stored in the ``project`` table', '$$description': ['Data structure for the **project** table inside ``pyproject.toml``', '(as initially defined in :pep:`621`)'], 'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, 'version': {'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, 'description': {'type': 'string', '$$description': ['The `summary description of the project', '`_']}, 'readme': {'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, 'requires-python': {'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, 'license': {'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, 'license-files': {'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, 'authors': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, 'maintainers': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, 'keywords': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, 'classifiers': {'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, 'urls': {'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, 'scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create command-line wrappers for the given', '`entry points `_.']}, 'gui-scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create GUI wrappers for the given', '`entry points `_.', 'The difference between ``scripts`` and ``gui-scripts`` is only relevant in', 'Windows.']}, 'entry-points': {'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$ref': '#/definitions/entry-point-group'}}}, 'dependencies': {'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$ref': '#/definitions/dependency'}}, 'optional-dependencies': {'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$ref': '#/definitions/dependency'}}}}, 'dynamic': {'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}}, 'required': ['name'], 'additionalProperties': False, 'allOf': [{'if': {'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, 'then': {'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}}, {'if': {'required': ['license-files']}, 'then': {'properties': {'license': {'type': 'string'}}}}], 'definitions': {'author': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, 'entry-point-group': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'dependency': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}, 'tool': {'type': 'object', 'properties': {'distutils': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/deprecated/distutils/configfile.html', 'title': '``tool.distutils`` table', '$$description': ['**EXPERIMENTAL** (NOT OFFICIALLY SUPPORTED): Use ``tool.distutils``', 'subtables to configure arguments for ``distutils`` commands.', 'Originally, ``distutils`` allowed developers to configure arguments for', '``setup.py`` commands via `distutils configuration files', '`_.', 'See also `the old Python docs _`.'], 'type': 'object', 'properties': {'global': {'type': 'object', 'description': 'Global options applied to all ``distutils`` commands'}}, 'patternProperties': {'.+': {'type': 'object'}}, '$comment': 'TODO: Is there a practical way of making this schema more specific?'}, 'setuptools': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html', 'title': '``tool.setuptools`` table', '$$description': ['``setuptools``-specific configurations that can be set by users that require', 'customization.', 'These configurations are completely optional and probably can be skipped when', 'creating simple packages. They are equivalent to some of the `Keywords', '`_', 'used by the ``setup.py`` file, and can be set via the ``tool.setuptools`` table.', 'It considers only ``setuptools`` `parameters', '`_', 'that are not covered by :pep:`621`; and intentionally excludes ``dependency_links``', 'and ``setup_requires`` (incompatible with modern workflows/standards).'], 'type': 'object', 'additionalProperties': False, 'properties': {'platforms': {'type': 'array', 'items': {'type': 'string'}}, 'provides': {'$$description': ['Package and virtual package names contained within this package', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'obsoletes': {'$$description': ['Packages which this package renders obsolete', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'zip-safe': {'$$description': ['Whether the project can be safely installed and run from a zip file.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'boolean'}, 'script-files': {'$$description': ['Legacy way of defining scripts (entry-points are preferred).', 'Equivalent to the ``script`` keyword in ``setup.py``', '(it was renamed to avoid confusion with entry-point based ``project.scripts``', 'defined in :pep:`621`).', '**DISCOURAGED**: generic script wrappers are tricky and may not work properly.', 'Whenever possible, please use ``project.scripts`` instead.'], 'type': 'array', 'items': {'type': 'string'}, '$comment': 'TODO: is this field deprecated/should be removed?'}, 'eager-resources': {'$$description': ['Resources that should be extracted together, if any of them is needed,', 'or if any C extensions included in the project are imported.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'array', 'items': {'type': 'string'}}, 'packages': {'$$description': ['Packages that should be included in the distribution.', 'It can be given either as a list of package identifiers', 'or as a ``dict``-like structure with a single key ``find``', 'which corresponds to a dynamic call to', '``setuptools.config.expand.find_packages`` function.', 'The ``find`` key is associated with a nested ``dict``-like structure that can', 'contain ``where``, ``include``, ``exclude`` and ``namespaces`` keys,', 'mimicking the keyword arguments of the associated function.'], 'oneOf': [{'title': 'Array of Python package identifiers', 'type': 'array', 'items': {'$ref': '#/definitions/package-name'}}, {'$ref': '#/definitions/find-directive'}]}, 'package-dir': {'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$ref': '#/definitions/package-name'}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, 'package-data': {'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'include-package-data': {'$$description': ['Automatically include any data files inside the package directories', 'that are specified by ``MANIFEST.in``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'boolean'}, 'exclude-package-data': {'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'namespace-packages': {'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'https://setuptools.pypa.io/en/latest/userguide/package_discovery.html', 'description': '**DEPRECATED**: use implicit namespaces instead (:pep:`420`).'}, 'py-modules': {'description': 'Modules that setuptools will manipulate', 'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'TODO: clarify the relationship with ``packages``'}, 'ext-modules': {'description': 'Extension modules to be compiled by setuptools', 'type': 'array', 'items': {'$ref': '#/definitions/ext-module'}}, 'data-files': {'$$description': ['``dict``-like structure where each key represents a directory and', 'the value is a list of glob patterns that should be installed in them.', '**DISCOURAGED**: please notice this might not work as expected with wheels.', 'Whenever possible, consider using data files inside the package directories', '(or create a new namespace package that only contains data files).', 'See `data files support', '`_.'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'cmdclass': {'$$description': ['Mapping of distutils-style command names to ``setuptools.Command`` subclasses', 'which in turn should be represented by strings with a qualified class name', '(i.e., "dotted" form with module), e.g.::\n\n', '    cmdclass = {mycmd = "pkg.subpkg.module.CommandClass"}\n\n', 'The command class should be a directly defined at the top-level of the', 'containing module (no class nesting).'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'string', 'format': 'python-qualified-identifier'}}}, 'license-files': {'type': 'array', 'items': {'type': 'string'}, '$$description': ['**PROVISIONAL**: list of glob patterns for all license files being distributed.', '(likely to become standard with :pep:`639`).', "By default: ``['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']``"], '$comment': 'TODO: revise if PEP 639 is accepted. Probably ``project.license-files``?'}, 'dynamic': {'type': 'object', 'description': 'Instructions for loading :pep:`621`-related metadata dynamically', 'additionalProperties': False, 'properties': {'version': {'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'$ref': '#/definitions/attr-directive'}, {'$ref': '#/definitions/file-directive'}]}, 'classifiers': {'$ref': '#/definitions/file-directive'}, 'description': {'$ref': '#/definitions/file-directive'}, 'entry-points': {'$ref': '#/definitions/file-directive'}, 'dependencies': {'$ref': '#/definitions/file-directive-for-dependencies'}, 'optional-dependencies': {'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'$ref': '#/definitions/file-directive-for-dependencies'}}}, 'readme': {'type': 'object', 'anyOf': [{'$ref': '#/definitions/file-directive'}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'$ref': '#/definitions/file-directive/properties/file'}}, 'additionalProperties': False}], 'required': ['file']}}}}, 'definitions': {'package-name': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}, 'ext-module': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, 'file-directive': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'file-directive-for-dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}, 'attr-directive': {'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, 'find-directive': {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}}}}}, 'dependency-groups': {'type': 'object', 'description': 'Dependency groups following PEP 735', 'additionalProperties': False, 'patternProperties': {'^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$': {'type': 'array', 'items': {'oneOf': [{'type': 'string', 'description': 'Python package specifiers following PEP 508', 'format': 'pep508'}, {'type': 'object', 'additionalProperties': False, 'properties': {'include-group': {'description': 'Another dependency group to include in this one', 'type': 'string', 'pattern': '^([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])$'}}}]}}}}}, 'project': {'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/pyproject-toml/', 'title': 'Package metadata stored in the ``project`` table', '$$description': ['Data structure for the **project** table inside ``pyproject.toml``', '(as initially defined in :pep:`621`)'], 'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, 'version': {'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, 'description': {'type': 'string', '$$description': ['The `summary description of the project', '`_']}, 'readme': {'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, 'requires-python': {'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, 'license': {'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, 'license-files': {'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, 'authors': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, 'maintainers': {'type': 'array', 'items': {'$ref': '#/definitions/author'}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, 'keywords': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, 'classifiers': {'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, 'urls': {'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, 'scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create command-line wrappers for the given', '`entry points `_.']}, 'gui-scripts': {'$ref': '#/definitions/entry-point-group', '$$description': ['Instruct the installer to create GUI wrappers for the given', '`entry points `_.', 'The difference between ``scripts`` and ``gui-scripts`` is only relevant in', 'Windows.']}, 'entry-points': {'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$ref': '#/definitions/entry-point-group'}}}, 'dependencies': {'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$ref': '#/definitions/dependency'}}, 'optional-dependencies': {'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$ref': '#/definitions/dependency'}}}}, 'dynamic': {'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}}, 'required': ['name'], 'additionalProperties': False, 'allOf': [{'if': {'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, 'then': {'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}}, {'if': {'required': ['license-files']}, 'then': {'properties': {'license': {'type': 'string'}}}}], 'definitions': {'author': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, 'entry-point-group': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'dependency': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, rule='additionalProperties')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html', 'title': '``tool.setuptools`` table', '$$description': ['``setuptools``-specific configurations that can be set by users that require', 'customization.', 'These configurations are completely optional and probably can be skipped when', 'creating simple packages. They are equivalent to some of the `Keywords', '`_', 'used by the ``setup.py`` file, and can be set via the ``tool.setuptools`` table.', 'It considers only ``setuptools`` `parameters', '`_', 'that are not covered by :pep:`621`; and intentionally excludes ``dependency_links``', 'and ``setup_requires`` (incompatible with modern workflows/standards).'], 'type': 'object', 'additionalProperties': False, 'properties': {'platforms': {'type': 'array', 'items': {'type': 'string'}}, 'provides': {'$$description': ['Package and virtual package names contained within this package', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'obsoletes': {'$$description': ['Packages which this package renders obsolete', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'zip-safe': {'$$description': ['Whether the project can be safely installed and run from a zip file.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'boolean'}, 'script-files': {'$$description': ['Legacy way of defining scripts (entry-points are preferred).', 'Equivalent to the ``script`` keyword in ``setup.py``', '(it was renamed to avoid confusion with entry-point based ``project.scripts``', 'defined in :pep:`621`).', '**DISCOURAGED**: generic script wrappers are tricky and may not work properly.', 'Whenever possible, please use ``project.scripts`` instead.'], 'type': 'array', 'items': {'type': 'string'}, '$comment': 'TODO: is this field deprecated/should be removed?'}, 'eager-resources': {'$$description': ['Resources that should be extracted together, if any of them is needed,', 'or if any C extensions included in the project are imported.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'array', 'items': {'type': 'string'}}, 'packages': {'$$description': ['Packages that should be included in the distribution.', 'It can be given either as a list of package identifiers', 'or as a ``dict``-like structure with a single key ``find``', 'which corresponds to a dynamic call to', '``setuptools.config.expand.find_packages`` function.', 'The ``find`` key is associated with a nested ``dict``-like structure that can', 'contain ``where``, ``include``, ``exclude`` and ``namespaces`` keys,', 'mimicking the keyword arguments of the associated function.'], 'oneOf': [{'title': 'Array of Python package identifiers', 'type': 'array', 'items': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}}, {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}]}, 'package-dir': {'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, 'package-data': {'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'include-package-data': {'$$description': ['Automatically include any data files inside the package directories', 'that are specified by ``MANIFEST.in``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'boolean'}, 'exclude-package-data': {'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'namespace-packages': {'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'https://setuptools.pypa.io/en/latest/userguide/package_discovery.html', 'description': '**DEPRECATED**: use implicit namespaces instead (:pep:`420`).'}, 'py-modules': {'description': 'Modules that setuptools will manipulate', 'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'TODO: clarify the relationship with ``packages``'}, 'ext-modules': {'description': 'Extension modules to be compiled by setuptools', 'type': 'array', 'items': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}}, 'data-files': {'$$description': ['``dict``-like structure where each key represents a directory and', 'the value is a list of glob patterns that should be installed in them.', '**DISCOURAGED**: please notice this might not work as expected with wheels.', 'Whenever possible, consider using data files inside the package directories', '(or create a new namespace package that only contains data files).', 'See `data files support', '`_.'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'cmdclass': {'$$description': ['Mapping of distutils-style command names to ``setuptools.Command`` subclasses', 'which in turn should be represented by strings with a qualified class name', '(i.e., "dotted" form with module), e.g.::\n\n', '    cmdclass = {mycmd = "pkg.subpkg.module.CommandClass"}\n\n', 'The command class should be a directly defined at the top-level of the', 'containing module (no class nesting).'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'string', 'format': 'python-qualified-identifier'}}}, 'license-files': {'type': 'array', 'items': {'type': 'string'}, '$$description': ['**PROVISIONAL**: list of glob patterns for all license files being distributed.', '(likely to become standard with :pep:`639`).', "By default: ``['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']``"], '$comment': 'TODO: revise if PEP 639 is accepted. Probably ``project.license-files``?'}, 'dynamic': {'type': 'object', 'description': 'Instructions for loading :pep:`621`-related metadata dynamically', 'additionalProperties': False, 'properties': {'version': {'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}]}, 'classifiers': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'description': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'entry-points': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}, 'optional-dependencies': {'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}}}, 'readme': {'type': 'object', 'anyOf': [{'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}], 'required': ['file']}}}}, 'definitions': {'package-name': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}, 'ext-module': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, 'file-directive': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'file-directive-for-dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}]}, 'attr-directive': {'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, 'find-directive': {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}}}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data_keys = set(data.keys())
-        if "platforms" in data_keys:
-            data_keys.remove("platforms")
-            data__platforms = data["platforms"]
-            if not isinstance(data__platforms, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".platforms must be array", value=data__platforms, name="" + (name_prefix or "data") + ".platforms", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__platforms_is_list = isinstance(data__platforms, (list, tuple))
-            if data__platforms_is_list:
-                data__platforms_len = len(data__platforms)
-                for data__platforms_x, data__platforms_item in enumerate(data__platforms):
-                    if not isinstance(data__platforms_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".platforms[{data__platforms_x}]".format(**locals()) + " must be string", value=data__platforms_item, name="" + (name_prefix or "data") + ".platforms[{data__platforms_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "provides" in data_keys:
-            data_keys.remove("provides")
-            data__provides = data["provides"]
-            if not isinstance(data__provides, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".provides must be array", value=data__provides, name="" + (name_prefix or "data") + ".provides", definition={'$$description': ['Package and virtual package names contained within this package', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, rule='type')
-            data__provides_is_list = isinstance(data__provides, (list, tuple))
-            if data__provides_is_list:
-                data__provides_len = len(data__provides)
-                for data__provides_x, data__provides_item in enumerate(data__provides):
-                    if not isinstance(data__provides_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".provides[{data__provides_x}]".format(**locals()) + " must be string", value=data__provides_item, name="" + (name_prefix or "data") + ".provides[{data__provides_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'pep508-identifier'}, rule='type')
-                    if isinstance(data__provides_item, str):
-                        if not custom_formats["pep508-identifier"](data__provides_item):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".provides[{data__provides_x}]".format(**locals()) + " must be pep508-identifier", value=data__provides_item, name="" + (name_prefix or "data") + ".provides[{data__provides_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'pep508-identifier'}, rule='format')
-        if "obsoletes" in data_keys:
-            data_keys.remove("obsoletes")
-            data__obsoletes = data["obsoletes"]
-            if not isinstance(data__obsoletes, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".obsoletes must be array", value=data__obsoletes, name="" + (name_prefix or "data") + ".obsoletes", definition={'$$description': ['Packages which this package renders obsolete', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, rule='type')
-            data__obsoletes_is_list = isinstance(data__obsoletes, (list, tuple))
-            if data__obsoletes_is_list:
-                data__obsoletes_len = len(data__obsoletes)
-                for data__obsoletes_x, data__obsoletes_item in enumerate(data__obsoletes):
-                    if not isinstance(data__obsoletes_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".obsoletes[{data__obsoletes_x}]".format(**locals()) + " must be string", value=data__obsoletes_item, name="" + (name_prefix or "data") + ".obsoletes[{data__obsoletes_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'pep508-identifier'}, rule='type')
-                    if isinstance(data__obsoletes_item, str):
-                        if not custom_formats["pep508-identifier"](data__obsoletes_item):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".obsoletes[{data__obsoletes_x}]".format(**locals()) + " must be pep508-identifier", value=data__obsoletes_item, name="" + (name_prefix or "data") + ".obsoletes[{data__obsoletes_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'pep508-identifier'}, rule='format')
-        if "zip-safe" in data_keys:
-            data_keys.remove("zip-safe")
-            data__zipsafe = data["zip-safe"]
-            if not isinstance(data__zipsafe, (bool)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".zip-safe must be boolean", value=data__zipsafe, name="" + (name_prefix or "data") + ".zip-safe", definition={'$$description': ['Whether the project can be safely installed and run from a zip file.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'boolean'}, rule='type')
-        if "script-files" in data_keys:
-            data_keys.remove("script-files")
-            data__scriptfiles = data["script-files"]
-            if not isinstance(data__scriptfiles, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".script-files must be array", value=data__scriptfiles, name="" + (name_prefix or "data") + ".script-files", definition={'$$description': ['Legacy way of defining scripts (entry-points are preferred).', 'Equivalent to the ``script`` keyword in ``setup.py``', '(it was renamed to avoid confusion with entry-point based ``project.scripts``', 'defined in :pep:`621`).', '**DISCOURAGED**: generic script wrappers are tricky and may not work properly.', 'Whenever possible, please use ``project.scripts`` instead.'], 'type': 'array', 'items': {'type': 'string'}, '$comment': 'TODO: is this field deprecated/should be removed?'}, rule='type')
-            data__scriptfiles_is_list = isinstance(data__scriptfiles, (list, tuple))
-            if data__scriptfiles_is_list:
-                data__scriptfiles_len = len(data__scriptfiles)
-                for data__scriptfiles_x, data__scriptfiles_item in enumerate(data__scriptfiles):
-                    if not isinstance(data__scriptfiles_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".script-files[{data__scriptfiles_x}]".format(**locals()) + " must be string", value=data__scriptfiles_item, name="" + (name_prefix or "data") + ".script-files[{data__scriptfiles_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "eager-resources" in data_keys:
-            data_keys.remove("eager-resources")
-            data__eagerresources = data["eager-resources"]
-            if not isinstance(data__eagerresources, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".eager-resources must be array", value=data__eagerresources, name="" + (name_prefix or "data") + ".eager-resources", definition={'$$description': ['Resources that should be extracted together, if any of them is needed,', 'or if any C extensions included in the project are imported.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__eagerresources_is_list = isinstance(data__eagerresources, (list, tuple))
-            if data__eagerresources_is_list:
-                data__eagerresources_len = len(data__eagerresources)
-                for data__eagerresources_x, data__eagerresources_item in enumerate(data__eagerresources):
-                    if not isinstance(data__eagerresources_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".eager-resources[{data__eagerresources_x}]".format(**locals()) + " must be string", value=data__eagerresources_item, name="" + (name_prefix or "data") + ".eager-resources[{data__eagerresources_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "packages" in data_keys:
-            data_keys.remove("packages")
-            data__packages = data["packages"]
-            data__packages_one_of_count2 = 0
-            if data__packages_one_of_count2 < 2:
-                try:
-                    if not isinstance(data__packages, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".packages must be array", value=data__packages, name="" + (name_prefix or "data") + ".packages", definition={'title': 'Array of Python package identifiers', 'type': 'array', 'items': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}}, rule='type')
-                    data__packages_is_list = isinstance(data__packages, (list, tuple))
-                    if data__packages_is_list:
-                        data__packages_len = len(data__packages)
-                        for data__packages_x, data__packages_item in enumerate(data__packages):
-                            validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_package_name(data__packages_item, custom_formats, (name_prefix or "data") + ".packages[{data__packages_x}]".format(**locals()))
-                    data__packages_one_of_count2 += 1
-                except JsonSchemaValueException: pass
-            if data__packages_one_of_count2 < 2:
-                try:
-                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_find_directive(data__packages, custom_formats, (name_prefix or "data") + ".packages")
-                    data__packages_one_of_count2 += 1
-                except JsonSchemaValueException: pass
-            if data__packages_one_of_count2 != 1:
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".packages must be valid exactly by one definition" + (" (" + str(data__packages_one_of_count2) + " matches found)"), value=data__packages, name="" + (name_prefix or "data") + ".packages", definition={'$$description': ['Packages that should be included in the distribution.', 'It can be given either as a list of package identifiers', 'or as a ``dict``-like structure with a single key ``find``', 'which corresponds to a dynamic call to', '``setuptools.config.expand.find_packages`` function.', 'The ``find`` key is associated with a nested ``dict``-like structure that can', 'contain ``where``, ``include``, ``exclude`` and ``namespaces`` keys,', 'mimicking the keyword arguments of the associated function.'], 'oneOf': [{'title': 'Array of Python package identifiers', 'type': 'array', 'items': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}}, {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}]}, rule='oneOf')
-        if "package-dir" in data_keys:
-            data_keys.remove("package-dir")
-            data__packagedir = data["package-dir"]
-            if not isinstance(data__packagedir, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-dir must be object", value=data__packagedir, name="" + (name_prefix or "data") + ".package-dir", definition={'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, rule='type')
-            data__packagedir_is_dict = isinstance(data__packagedir, dict)
-            if data__packagedir_is_dict:
-                data__packagedir_keys = set(data__packagedir.keys())
-                for data__packagedir_key, data__packagedir_val in data__packagedir.items():
-                    if REGEX_PATTERNS['^.*$'].search(data__packagedir_key):
-                        if data__packagedir_key in data__packagedir_keys:
-                            data__packagedir_keys.remove(data__packagedir_key)
-                        if not isinstance(data__packagedir_val, (str)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-dir.{data__packagedir_key}".format(**locals()) + " must be string", value=data__packagedir_val, name="" + (name_prefix or "data") + ".package-dir.{data__packagedir_key}".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                if data__packagedir_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-dir must not contain "+str(data__packagedir_keys)+" properties", value=data__packagedir, name="" + (name_prefix or "data") + ".package-dir", definition={'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, rule='additionalProperties')
-                data__packagedir_len = len(data__packagedir)
-                if data__packagedir_len != 0:
-                    data__packagedir_property_names = True
-                    for data__packagedir_key in data__packagedir:
-                        try:
-                            data__packagedir_key_any_of_count3 = 0
-                            if not data__packagedir_key_any_of_count3:
-                                try:
-                                    if data__packagedir_key != "":
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-dir must be same as const definition: ", value=data__packagedir_key, name="" + (name_prefix or "data") + ".package-dir", definition={'const': ''}, rule='const')
-                                    data__packagedir_key_any_of_count3 += 1
-                                except JsonSchemaValueException: pass
-                            if not data__packagedir_key_any_of_count3:
-                                try:
-                                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_package_name(data__packagedir_key, custom_formats, (name_prefix or "data") + ".package-dir")
-                                    data__packagedir_key_any_of_count3 += 1
-                                except JsonSchemaValueException: pass
-                            if not data__packagedir_key_any_of_count3:
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-dir cannot be validated by any definition", value=data__packagedir_key, name="" + (name_prefix or "data") + ".package-dir", definition={'anyOf': [{'const': ''}, {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}]}, rule='anyOf')
-                        except JsonSchemaValueException:
-                            data__packagedir_property_names = False
-                    if not data__packagedir_property_names:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-dir must be named by propertyName definition", value=data__packagedir, name="" + (name_prefix or "data") + ".package-dir", definition={'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, rule='propertyNames')
-        if "package-data" in data_keys:
-            data_keys.remove("package-data")
-            data__packagedata = data["package-data"]
-            if not isinstance(data__packagedata, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data must be object", value=data__packagedata, name="" + (name_prefix or "data") + ".package-data", definition={'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, rule='type')
-            data__packagedata_is_dict = isinstance(data__packagedata, dict)
-            if data__packagedata_is_dict:
-                data__packagedata_keys = set(data__packagedata.keys())
-                for data__packagedata_key, data__packagedata_val in data__packagedata.items():
-                    if REGEX_PATTERNS['^.*$'].search(data__packagedata_key):
-                        if data__packagedata_key in data__packagedata_keys:
-                            data__packagedata_keys.remove(data__packagedata_key)
-                        if not isinstance(data__packagedata_val, (list, tuple)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data.{data__packagedata_key}".format(**locals()) + " must be array", value=data__packagedata_val, name="" + (name_prefix or "data") + ".package-data.{data__packagedata_key}".format(**locals()) + "", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-                        data__packagedata_val_is_list = isinstance(data__packagedata_val, (list, tuple))
-                        if data__packagedata_val_is_list:
-                            data__packagedata_val_len = len(data__packagedata_val)
-                            for data__packagedata_val_x, data__packagedata_val_item in enumerate(data__packagedata_val):
-                                if not isinstance(data__packagedata_val_item, (str)):
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data.{data__packagedata_key}[{data__packagedata_val_x}]".format(**locals()) + " must be string", value=data__packagedata_val_item, name="" + (name_prefix or "data") + ".package-data.{data__packagedata_key}[{data__packagedata_val_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                if data__packagedata_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data must not contain "+str(data__packagedata_keys)+" properties", value=data__packagedata, name="" + (name_prefix or "data") + ".package-data", definition={'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, rule='additionalProperties')
-                data__packagedata_len = len(data__packagedata)
-                if data__packagedata_len != 0:
-                    data__packagedata_property_names = True
-                    for data__packagedata_key in data__packagedata:
-                        try:
-                            data__packagedata_key_any_of_count4 = 0
-                            if not data__packagedata_key_any_of_count4:
-                                try:
-                                    if not isinstance(data__packagedata_key, (str)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data must be string", value=data__packagedata_key, name="" + (name_prefix or "data") + ".package-data", definition={'type': 'string', 'format': 'python-module-name'}, rule='type')
-                                    if isinstance(data__packagedata_key, str):
-                                        if not custom_formats["python-module-name"](data__packagedata_key):
-                                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data must be python-module-name", value=data__packagedata_key, name="" + (name_prefix or "data") + ".package-data", definition={'type': 'string', 'format': 'python-module-name'}, rule='format')
-                                    data__packagedata_key_any_of_count4 += 1
-                                except JsonSchemaValueException: pass
-                            if not data__packagedata_key_any_of_count4:
-                                try:
-                                    if data__packagedata_key != "*":
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data must be same as const definition: *", value=data__packagedata_key, name="" + (name_prefix or "data") + ".package-data", definition={'const': '*'}, rule='const')
-                                    data__packagedata_key_any_of_count4 += 1
-                                except JsonSchemaValueException: pass
-                            if not data__packagedata_key_any_of_count4:
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data cannot be validated by any definition", value=data__packagedata_key, name="" + (name_prefix or "data") + ".package-data", definition={'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, rule='anyOf')
-                        except JsonSchemaValueException:
-                            data__packagedata_property_names = False
-                    if not data__packagedata_property_names:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".package-data must be named by propertyName definition", value=data__packagedata, name="" + (name_prefix or "data") + ".package-data", definition={'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, rule='propertyNames')
-        if "include-package-data" in data_keys:
-            data_keys.remove("include-package-data")
-            data__includepackagedata = data["include-package-data"]
-            if not isinstance(data__includepackagedata, (bool)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".include-package-data must be boolean", value=data__includepackagedata, name="" + (name_prefix or "data") + ".include-package-data", definition={'$$description': ['Automatically include any data files inside the package directories', 'that are specified by ``MANIFEST.in``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'boolean'}, rule='type')
-        if "exclude-package-data" in data_keys:
-            data_keys.remove("exclude-package-data")
-            data__excludepackagedata = data["exclude-package-data"]
-            if not isinstance(data__excludepackagedata, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data must be object", value=data__excludepackagedata, name="" + (name_prefix or "data") + ".exclude-package-data", definition={'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, rule='type')
-            data__excludepackagedata_is_dict = isinstance(data__excludepackagedata, dict)
-            if data__excludepackagedata_is_dict:
-                data__excludepackagedata_keys = set(data__excludepackagedata.keys())
-                for data__excludepackagedata_key, data__excludepackagedata_val in data__excludepackagedata.items():
-                    if REGEX_PATTERNS['^.*$'].search(data__excludepackagedata_key):
-                        if data__excludepackagedata_key in data__excludepackagedata_keys:
-                            data__excludepackagedata_keys.remove(data__excludepackagedata_key)
-                        if not isinstance(data__excludepackagedata_val, (list, tuple)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data.{data__excludepackagedata_key}".format(**locals()) + " must be array", value=data__excludepackagedata_val, name="" + (name_prefix or "data") + ".exclude-package-data.{data__excludepackagedata_key}".format(**locals()) + "", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-                        data__excludepackagedata_val_is_list = isinstance(data__excludepackagedata_val, (list, tuple))
-                        if data__excludepackagedata_val_is_list:
-                            data__excludepackagedata_val_len = len(data__excludepackagedata_val)
-                            for data__excludepackagedata_val_x, data__excludepackagedata_val_item in enumerate(data__excludepackagedata_val):
-                                if not isinstance(data__excludepackagedata_val_item, (str)):
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data.{data__excludepackagedata_key}[{data__excludepackagedata_val_x}]".format(**locals()) + " must be string", value=data__excludepackagedata_val_item, name="" + (name_prefix or "data") + ".exclude-package-data.{data__excludepackagedata_key}[{data__excludepackagedata_val_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                if data__excludepackagedata_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data must not contain "+str(data__excludepackagedata_keys)+" properties", value=data__excludepackagedata, name="" + (name_prefix or "data") + ".exclude-package-data", definition={'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, rule='additionalProperties')
-                data__excludepackagedata_len = len(data__excludepackagedata)
-                if data__excludepackagedata_len != 0:
-                    data__excludepackagedata_property_names = True
-                    for data__excludepackagedata_key in data__excludepackagedata:
-                        try:
-                            data__excludepackagedata_key_any_of_count5 = 0
-                            if not data__excludepackagedata_key_any_of_count5:
-                                try:
-                                    if not isinstance(data__excludepackagedata_key, (str)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data must be string", value=data__excludepackagedata_key, name="" + (name_prefix or "data") + ".exclude-package-data", definition={'type': 'string', 'format': 'python-module-name'}, rule='type')
-                                    if isinstance(data__excludepackagedata_key, str):
-                                        if not custom_formats["python-module-name"](data__excludepackagedata_key):
-                                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data must be python-module-name", value=data__excludepackagedata_key, name="" + (name_prefix or "data") + ".exclude-package-data", definition={'type': 'string', 'format': 'python-module-name'}, rule='format')
-                                    data__excludepackagedata_key_any_of_count5 += 1
-                                except JsonSchemaValueException: pass
-                            if not data__excludepackagedata_key_any_of_count5:
-                                try:
-                                    if data__excludepackagedata_key != "*":
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data must be same as const definition: *", value=data__excludepackagedata_key, name="" + (name_prefix or "data") + ".exclude-package-data", definition={'const': '*'}, rule='const')
-                                    data__excludepackagedata_key_any_of_count5 += 1
-                                except JsonSchemaValueException: pass
-                            if not data__excludepackagedata_key_any_of_count5:
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data cannot be validated by any definition", value=data__excludepackagedata_key, name="" + (name_prefix or "data") + ".exclude-package-data", definition={'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, rule='anyOf')
-                        except JsonSchemaValueException:
-                            data__excludepackagedata_property_names = False
-                    if not data__excludepackagedata_property_names:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".exclude-package-data must be named by propertyName definition", value=data__excludepackagedata, name="" + (name_prefix or "data") + ".exclude-package-data", definition={'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, rule='propertyNames')
-        if "namespace-packages" in data_keys:
-            data_keys.remove("namespace-packages")
-            data__namespacepackages = data["namespace-packages"]
-            if not isinstance(data__namespacepackages, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".namespace-packages must be array", value=data__namespacepackages, name="" + (name_prefix or "data") + ".namespace-packages", definition={'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'https://setuptools.pypa.io/en/latest/userguide/package_discovery.html', 'description': '**DEPRECATED**: use implicit namespaces instead (:pep:`420`).'}, rule='type')
-            data__namespacepackages_is_list = isinstance(data__namespacepackages, (list, tuple))
-            if data__namespacepackages_is_list:
-                data__namespacepackages_len = len(data__namespacepackages)
-                for data__namespacepackages_x, data__namespacepackages_item in enumerate(data__namespacepackages):
-                    if not isinstance(data__namespacepackages_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".namespace-packages[{data__namespacepackages_x}]".format(**locals()) + " must be string", value=data__namespacepackages_item, name="" + (name_prefix or "data") + ".namespace-packages[{data__namespacepackages_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='type')
-                    if isinstance(data__namespacepackages_item, str):
-                        if not custom_formats["python-module-name-relaxed"](data__namespacepackages_item):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".namespace-packages[{data__namespacepackages_x}]".format(**locals()) + " must be python-module-name-relaxed", value=data__namespacepackages_item, name="" + (name_prefix or "data") + ".namespace-packages[{data__namespacepackages_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='format')
-        if "py-modules" in data_keys:
-            data_keys.remove("py-modules")
-            data__pymodules = data["py-modules"]
-            if not isinstance(data__pymodules, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".py-modules must be array", value=data__pymodules, name="" + (name_prefix or "data") + ".py-modules", definition={'description': 'Modules that setuptools will manipulate', 'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'TODO: clarify the relationship with ``packages``'}, rule='type')
-            data__pymodules_is_list = isinstance(data__pymodules, (list, tuple))
-            if data__pymodules_is_list:
-                data__pymodules_len = len(data__pymodules)
-                for data__pymodules_x, data__pymodules_item in enumerate(data__pymodules):
-                    if not isinstance(data__pymodules_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".py-modules[{data__pymodules_x}]".format(**locals()) + " must be string", value=data__pymodules_item, name="" + (name_prefix or "data") + ".py-modules[{data__pymodules_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='type')
-                    if isinstance(data__pymodules_item, str):
-                        if not custom_formats["python-module-name-relaxed"](data__pymodules_item):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".py-modules[{data__pymodules_x}]".format(**locals()) + " must be python-module-name-relaxed", value=data__pymodules_item, name="" + (name_prefix or "data") + ".py-modules[{data__pymodules_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='format')
-        if "ext-modules" in data_keys:
-            data_keys.remove("ext-modules")
-            data__extmodules = data["ext-modules"]
-            if not isinstance(data__extmodules, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".ext-modules must be array", value=data__extmodules, name="" + (name_prefix or "data") + ".ext-modules", definition={'description': 'Extension modules to be compiled by setuptools', 'type': 'array', 'items': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}}, rule='type')
-            data__extmodules_is_list = isinstance(data__extmodules, (list, tuple))
-            if data__extmodules_is_list:
-                data__extmodules_len = len(data__extmodules)
-                for data__extmodules_x, data__extmodules_item in enumerate(data__extmodules):
-                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_ext_module(data__extmodules_item, custom_formats, (name_prefix or "data") + ".ext-modules[{data__extmodules_x}]".format(**locals()))
-        if "data-files" in data_keys:
-            data_keys.remove("data-files")
-            data__datafiles = data["data-files"]
-            if not isinstance(data__datafiles, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".data-files must be object", value=data__datafiles, name="" + (name_prefix or "data") + ".data-files", definition={'$$description': ['``dict``-like structure where each key represents a directory and', 'the value is a list of glob patterns that should be installed in them.', '**DISCOURAGED**: please notice this might not work as expected with wheels.', 'Whenever possible, consider using data files inside the package directories', '(or create a new namespace package that only contains data files).', 'See `data files support', '`_.'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, rule='type')
-            data__datafiles_is_dict = isinstance(data__datafiles, dict)
-            if data__datafiles_is_dict:
-                data__datafiles_keys = set(data__datafiles.keys())
-                for data__datafiles_key, data__datafiles_val in data__datafiles.items():
-                    if REGEX_PATTERNS['^.*$'].search(data__datafiles_key):
-                        if data__datafiles_key in data__datafiles_keys:
-                            data__datafiles_keys.remove(data__datafiles_key)
-                        if not isinstance(data__datafiles_val, (list, tuple)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".data-files.{data__datafiles_key}".format(**locals()) + " must be array", value=data__datafiles_val, name="" + (name_prefix or "data") + ".data-files.{data__datafiles_key}".format(**locals()) + "", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-                        data__datafiles_val_is_list = isinstance(data__datafiles_val, (list, tuple))
-                        if data__datafiles_val_is_list:
-                            data__datafiles_val_len = len(data__datafiles_val)
-                            for data__datafiles_val_x, data__datafiles_val_item in enumerate(data__datafiles_val):
-                                if not isinstance(data__datafiles_val_item, (str)):
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".data-files.{data__datafiles_key}[{data__datafiles_val_x}]".format(**locals()) + " must be string", value=data__datafiles_val_item, name="" + (name_prefix or "data") + ".data-files.{data__datafiles_key}[{data__datafiles_val_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "cmdclass" in data_keys:
-            data_keys.remove("cmdclass")
-            data__cmdclass = data["cmdclass"]
-            if not isinstance(data__cmdclass, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".cmdclass must be object", value=data__cmdclass, name="" + (name_prefix or "data") + ".cmdclass", definition={'$$description': ['Mapping of distutils-style command names to ``setuptools.Command`` subclasses', 'which in turn should be represented by strings with a qualified class name', '(i.e., "dotted" form with module), e.g.::\n\n', '    cmdclass = {mycmd = "pkg.subpkg.module.CommandClass"}\n\n', 'The command class should be a directly defined at the top-level of the', 'containing module (no class nesting).'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'string', 'format': 'python-qualified-identifier'}}}, rule='type')
-            data__cmdclass_is_dict = isinstance(data__cmdclass, dict)
-            if data__cmdclass_is_dict:
-                data__cmdclass_keys = set(data__cmdclass.keys())
-                for data__cmdclass_key, data__cmdclass_val in data__cmdclass.items():
-                    if REGEX_PATTERNS['^.*$'].search(data__cmdclass_key):
-                        if data__cmdclass_key in data__cmdclass_keys:
-                            data__cmdclass_keys.remove(data__cmdclass_key)
-                        if not isinstance(data__cmdclass_val, (str)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".cmdclass.{data__cmdclass_key}".format(**locals()) + " must be string", value=data__cmdclass_val, name="" + (name_prefix or "data") + ".cmdclass.{data__cmdclass_key}".format(**locals()) + "", definition={'type': 'string', 'format': 'python-qualified-identifier'}, rule='type')
-                        if isinstance(data__cmdclass_val, str):
-                            if not custom_formats["python-qualified-identifier"](data__cmdclass_val):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".cmdclass.{data__cmdclass_key}".format(**locals()) + " must be python-qualified-identifier", value=data__cmdclass_val, name="" + (name_prefix or "data") + ".cmdclass.{data__cmdclass_key}".format(**locals()) + "", definition={'type': 'string', 'format': 'python-qualified-identifier'}, rule='format')
-        if "license-files" in data_keys:
-            data_keys.remove("license-files")
-            data__licensefiles = data["license-files"]
-            if not isinstance(data__licensefiles, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".license-files must be array", value=data__licensefiles, name="" + (name_prefix or "data") + ".license-files", definition={'type': 'array', 'items': {'type': 'string'}, '$$description': ['**PROVISIONAL**: list of glob patterns for all license files being distributed.', '(likely to become standard with :pep:`639`).', "By default: ``['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']``"], '$comment': 'TODO: revise if PEP 639 is accepted. Probably ``project.license-files``?'}, rule='type')
-            data__licensefiles_is_list = isinstance(data__licensefiles, (list, tuple))
-            if data__licensefiles_is_list:
-                data__licensefiles_len = len(data__licensefiles)
-                for data__licensefiles_x, data__licensefiles_item in enumerate(data__licensefiles):
-                    if not isinstance(data__licensefiles_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".license-files[{data__licensefiles_x}]".format(**locals()) + " must be string", value=data__licensefiles_item, name="" + (name_prefix or "data") + ".license-files[{data__licensefiles_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "dynamic" in data_keys:
-            data_keys.remove("dynamic")
-            data__dynamic = data["dynamic"]
-            if not isinstance(data__dynamic, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic must be object", value=data__dynamic, name="" + (name_prefix or "data") + ".dynamic", definition={'type': 'object', 'description': 'Instructions for loading :pep:`621`-related metadata dynamically', 'additionalProperties': False, 'properties': {'version': {'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}]}, 'classifiers': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'description': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'entry-points': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}, 'optional-dependencies': {'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}}}, 'readme': {'type': 'object', 'anyOf': [{'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}], 'required': ['file']}}}, rule='type')
-            data__dynamic_is_dict = isinstance(data__dynamic, dict)
-            if data__dynamic_is_dict:
-                data__dynamic_keys = set(data__dynamic.keys())
-                if "version" in data__dynamic_keys:
-                    data__dynamic_keys.remove("version")
-                    data__dynamic__version = data__dynamic["version"]
-                    data__dynamic__version_one_of_count6 = 0
-                    if data__dynamic__version_one_of_count6 < 2:
-                        try:
-                            validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_attr_directive(data__dynamic__version, custom_formats, (name_prefix or "data") + ".dynamic.version")
-                            data__dynamic__version_one_of_count6 += 1
-                        except JsonSchemaValueException: pass
-                    if data__dynamic__version_one_of_count6 < 2:
-                        try:
-                            validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive(data__dynamic__version, custom_formats, (name_prefix or "data") + ".dynamic.version")
-                            data__dynamic__version_one_of_count6 += 1
-                        except JsonSchemaValueException: pass
-                    if data__dynamic__version_one_of_count6 != 1:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.version must be valid exactly by one definition" + (" (" + str(data__dynamic__version_one_of_count6) + " matches found)"), value=data__dynamic__version, name="" + (name_prefix or "data") + ".dynamic.version", definition={'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}]}, rule='oneOf')
-                if "classifiers" in data__dynamic_keys:
-                    data__dynamic_keys.remove("classifiers")
-                    data__dynamic__classifiers = data__dynamic["classifiers"]
-                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive(data__dynamic__classifiers, custom_formats, (name_prefix or "data") + ".dynamic.classifiers")
-                if "description" in data__dynamic_keys:
-                    data__dynamic_keys.remove("description")
-                    data__dynamic__description = data__dynamic["description"]
-                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive(data__dynamic__description, custom_formats, (name_prefix or "data") + ".dynamic.description")
-                if "entry-points" in data__dynamic_keys:
-                    data__dynamic_keys.remove("entry-points")
-                    data__dynamic__entrypoints = data__dynamic["entry-points"]
-                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive(data__dynamic__entrypoints, custom_formats, (name_prefix or "data") + ".dynamic.entry-points")
-                if "dependencies" in data__dynamic_keys:
-                    data__dynamic_keys.remove("dependencies")
-                    data__dynamic__dependencies = data__dynamic["dependencies"]
-                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive_for_dependencies(data__dynamic__dependencies, custom_formats, (name_prefix or "data") + ".dynamic.dependencies")
-                if "optional-dependencies" in data__dynamic_keys:
-                    data__dynamic_keys.remove("optional-dependencies")
-                    data__dynamic__optionaldependencies = data__dynamic["optional-dependencies"]
-                    if not isinstance(data__dynamic__optionaldependencies, (dict)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.optional-dependencies must be object", value=data__dynamic__optionaldependencies, name="" + (name_prefix or "data") + ".dynamic.optional-dependencies", definition={'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}}}, rule='type')
-                    data__dynamic__optionaldependencies_is_dict = isinstance(data__dynamic__optionaldependencies, dict)
-                    if data__dynamic__optionaldependencies_is_dict:
-                        data__dynamic__optionaldependencies_keys = set(data__dynamic__optionaldependencies.keys())
-                        for data__dynamic__optionaldependencies_key, data__dynamic__optionaldependencies_val in data__dynamic__optionaldependencies.items():
-                            if REGEX_PATTERNS['.+'].search(data__dynamic__optionaldependencies_key):
-                                if data__dynamic__optionaldependencies_key in data__dynamic__optionaldependencies_keys:
-                                    data__dynamic__optionaldependencies_keys.remove(data__dynamic__optionaldependencies_key)
-                                validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive_for_dependencies(data__dynamic__optionaldependencies_val, custom_formats, (name_prefix or "data") + ".dynamic.optional-dependencies.{data__dynamic__optionaldependencies_key}".format(**locals()))
-                        if data__dynamic__optionaldependencies_keys:
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.optional-dependencies must not contain "+str(data__dynamic__optionaldependencies_keys)+" properties", value=data__dynamic__optionaldependencies, name="" + (name_prefix or "data") + ".dynamic.optional-dependencies", definition={'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}}}, rule='additionalProperties')
-                        data__dynamic__optionaldependencies_len = len(data__dynamic__optionaldependencies)
-                        if data__dynamic__optionaldependencies_len != 0:
-                            data__dynamic__optionaldependencies_property_names = True
-                            for data__dynamic__optionaldependencies_key in data__dynamic__optionaldependencies:
-                                try:
-                                    if not isinstance(data__dynamic__optionaldependencies_key, (str)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.optional-dependencies must be string", value=data__dynamic__optionaldependencies_key, name="" + (name_prefix or "data") + ".dynamic.optional-dependencies", definition={'type': 'string', 'format': 'pep508-identifier'}, rule='type')
-                                    if isinstance(data__dynamic__optionaldependencies_key, str):
-                                        if not custom_formats["pep508-identifier"](data__dynamic__optionaldependencies_key):
-                                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.optional-dependencies must be pep508-identifier", value=data__dynamic__optionaldependencies_key, name="" + (name_prefix or "data") + ".dynamic.optional-dependencies", definition={'type': 'string', 'format': 'pep508-identifier'}, rule='format')
-                                except JsonSchemaValueException:
-                                    data__dynamic__optionaldependencies_property_names = False
-                            if not data__dynamic__optionaldependencies_property_names:
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.optional-dependencies must be named by propertyName definition", value=data__dynamic__optionaldependencies, name="" + (name_prefix or "data") + ".dynamic.optional-dependencies", definition={'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}}}, rule='propertyNames')
-                if "readme" in data__dynamic_keys:
-                    data__dynamic_keys.remove("readme")
-                    data__dynamic__readme = data__dynamic["readme"]
-                    if not isinstance(data__dynamic__readme, (dict)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.readme must be object", value=data__dynamic__readme, name="" + (name_prefix or "data") + ".dynamic.readme", definition={'type': 'object', 'anyOf': [{'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}], 'required': ['file']}, rule='type')
-                    data__dynamic__readme_any_of_count7 = 0
-                    if not data__dynamic__readme_any_of_count7:
-                        try:
-                            validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive(data__dynamic__readme, custom_formats, (name_prefix or "data") + ".dynamic.readme")
-                            data__dynamic__readme_any_of_count7 += 1
-                        except JsonSchemaValueException: pass
-                    if not data__dynamic__readme_any_of_count7:
-                        try:
-                            if not isinstance(data__dynamic__readme, (dict)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.readme must be object", value=data__dynamic__readme, name="" + (name_prefix or "data") + ".dynamic.readme", definition={'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}, rule='type')
-                            data__dynamic__readme_is_dict = isinstance(data__dynamic__readme, dict)
-                            if data__dynamic__readme_is_dict:
-                                data__dynamic__readme_keys = set(data__dynamic__readme.keys())
-                                if "content-type" in data__dynamic__readme_keys:
-                                    data__dynamic__readme_keys.remove("content-type")
-                                    data__dynamic__readme__contenttype = data__dynamic__readme["content-type"]
-                                    if not isinstance(data__dynamic__readme__contenttype, (str)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.readme.content-type must be string", value=data__dynamic__readme__contenttype, name="" + (name_prefix or "data") + ".dynamic.readme.content-type", definition={'type': 'string'}, rule='type')
-                                if "file" in data__dynamic__readme_keys:
-                                    data__dynamic__readme_keys.remove("file")
-                                    data__dynamic__readme__file = data__dynamic__readme["file"]
-                                    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive_properties_file(data__dynamic__readme__file, custom_formats, (name_prefix or "data") + ".dynamic.readme.file")
-                                if data__dynamic__readme_keys:
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.readme must not contain "+str(data__dynamic__readme_keys)+" properties", value=data__dynamic__readme, name="" + (name_prefix or "data") + ".dynamic.readme", definition={'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}, rule='additionalProperties')
-                            data__dynamic__readme_any_of_count7 += 1
-                        except JsonSchemaValueException: pass
-                    if not data__dynamic__readme_any_of_count7:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.readme cannot be validated by any definition", value=data__dynamic__readme, name="" + (name_prefix or "data") + ".dynamic.readme", definition={'type': 'object', 'anyOf': [{'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}], 'required': ['file']}, rule='anyOf')
-                    data__dynamic__readme_is_dict = isinstance(data__dynamic__readme, dict)
-                    if data__dynamic__readme_is_dict:
-                        data__dynamic__readme__missing_keys = set(['file']) - data__dynamic__readme.keys()
-                        if data__dynamic__readme__missing_keys:
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic.readme must contain " + (str(sorted(data__dynamic__readme__missing_keys)) + " properties"), value=data__dynamic__readme, name="" + (name_prefix or "data") + ".dynamic.readme", definition={'type': 'object', 'anyOf': [{'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}], 'required': ['file']}, rule='required')
-                if data__dynamic_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic must not contain "+str(data__dynamic_keys)+" properties", value=data__dynamic, name="" + (name_prefix or "data") + ".dynamic", definition={'type': 'object', 'description': 'Instructions for loading :pep:`621`-related metadata dynamically', 'additionalProperties': False, 'properties': {'version': {'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}]}, 'classifiers': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'description': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'entry-points': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}, 'optional-dependencies': {'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}}}, 'readme': {'type': 'object', 'anyOf': [{'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}], 'required': ['file']}}}, rule='additionalProperties')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html', 'title': '``tool.setuptools`` table', '$$description': ['``setuptools``-specific configurations that can be set by users that require', 'customization.', 'These configurations are completely optional and probably can be skipped when', 'creating simple packages. They are equivalent to some of the `Keywords', '`_', 'used by the ``setup.py`` file, and can be set via the ``tool.setuptools`` table.', 'It considers only ``setuptools`` `parameters', '`_', 'that are not covered by :pep:`621`; and intentionally excludes ``dependency_links``', 'and ``setup_requires`` (incompatible with modern workflows/standards).'], 'type': 'object', 'additionalProperties': False, 'properties': {'platforms': {'type': 'array', 'items': {'type': 'string'}}, 'provides': {'$$description': ['Package and virtual package names contained within this package', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'obsoletes': {'$$description': ['Packages which this package renders obsolete', '**(not supported by pip)**'], 'type': 'array', 'items': {'type': 'string', 'format': 'pep508-identifier'}}, 'zip-safe': {'$$description': ['Whether the project can be safely installed and run from a zip file.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'boolean'}, 'script-files': {'$$description': ['Legacy way of defining scripts (entry-points are preferred).', 'Equivalent to the ``script`` keyword in ``setup.py``', '(it was renamed to avoid confusion with entry-point based ``project.scripts``', 'defined in :pep:`621`).', '**DISCOURAGED**: generic script wrappers are tricky and may not work properly.', 'Whenever possible, please use ``project.scripts`` instead.'], 'type': 'array', 'items': {'type': 'string'}, '$comment': 'TODO: is this field deprecated/should be removed?'}, 'eager-resources': {'$$description': ['Resources that should be extracted together, if any of them is needed,', 'or if any C extensions included in the project are imported.', '**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and', '``setup.py install`` in the context of ``eggs`` (**DEPRECATED**).'], 'type': 'array', 'items': {'type': 'string'}}, 'packages': {'$$description': ['Packages that should be included in the distribution.', 'It can be given either as a list of package identifiers', 'or as a ``dict``-like structure with a single key ``find``', 'which corresponds to a dynamic call to', '``setuptools.config.expand.find_packages`` function.', 'The ``find`` key is associated with a nested ``dict``-like structure that can', 'contain ``where``, ``include``, ``exclude`` and ``namespaces`` keys,', 'mimicking the keyword arguments of the associated function.'], 'oneOf': [{'title': 'Array of Python package identifiers', 'type': 'array', 'items': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}}, {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}]}, 'package-dir': {'$$description': [':class:`dict`-like structure mapping from package names to directories where their', 'code can be found.', 'The empty string (as key) means that all packages are contained inside', 'the given directory will be included in the distribution.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'const': ''}, {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}]}, 'patternProperties': {'^.*$': {'type': 'string'}}}, 'package-data': {'$$description': ['Mapping from package names to lists of glob patterns.', 'Usually this option is not needed when using ``include-package-data = true``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'include-package-data': {'$$description': ['Automatically include any data files inside the package directories', 'that are specified by ``MANIFEST.in``', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'boolean'}, 'exclude-package-data': {'$$description': ['Mapping from package names to lists of glob patterns that should be excluded', 'For more information on how to include data files, check ``setuptools`` `docs', '`_.'], 'type': 'object', 'additionalProperties': False, 'propertyNames': {'anyOf': [{'type': 'string', 'format': 'python-module-name'}, {'const': '*'}]}, 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'namespace-packages': {'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'https://setuptools.pypa.io/en/latest/userguide/package_discovery.html', 'description': '**DEPRECATED**: use implicit namespaces instead (:pep:`420`).'}, 'py-modules': {'description': 'Modules that setuptools will manipulate', 'type': 'array', 'items': {'type': 'string', 'format': 'python-module-name-relaxed'}, '$comment': 'TODO: clarify the relationship with ``packages``'}, 'ext-modules': {'description': 'Extension modules to be compiled by setuptools', 'type': 'array', 'items': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}}, 'data-files': {'$$description': ['``dict``-like structure where each key represents a directory and', 'the value is a list of glob patterns that should be installed in them.', '**DISCOURAGED**: please notice this might not work as expected with wheels.', 'Whenever possible, consider using data files inside the package directories', '(or create a new namespace package that only contains data files).', 'See `data files support', '`_.'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'array', 'items': {'type': 'string'}}}}, 'cmdclass': {'$$description': ['Mapping of distutils-style command names to ``setuptools.Command`` subclasses', 'which in turn should be represented by strings with a qualified class name', '(i.e., "dotted" form with module), e.g.::\n\n', '    cmdclass = {mycmd = "pkg.subpkg.module.CommandClass"}\n\n', 'The command class should be a directly defined at the top-level of the', 'containing module (no class nesting).'], 'type': 'object', 'patternProperties': {'^.*$': {'type': 'string', 'format': 'python-qualified-identifier'}}}, 'license-files': {'type': 'array', 'items': {'type': 'string'}, '$$description': ['**PROVISIONAL**: list of glob patterns for all license files being distributed.', '(likely to become standard with :pep:`639`).', "By default: ``['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']``"], '$comment': 'TODO: revise if PEP 639 is accepted. Probably ``project.license-files``?'}, 'dynamic': {'type': 'object', 'description': 'Instructions for loading :pep:`621`-related metadata dynamically', 'additionalProperties': False, 'properties': {'version': {'$$description': ['A version dynamically loaded via either the ``attr:`` or ``file:``', 'directives. Please make sure the given file or attribute respects :pep:`440`.', 'Also ensure to set ``project.dynamic`` accordingly.'], 'oneOf': [{'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}]}, 'classifiers': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'description': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'entry-points': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}, 'optional-dependencies': {'type': 'object', 'propertyNames': {'type': 'string', 'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'.+': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$ref': '#/definitions/file-directive'}]}}}, 'readme': {'type': 'object', 'anyOf': [{'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, {'type': 'object', 'properties': {'content-type': {'type': 'string'}, 'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'additionalProperties': False}], 'required': ['file']}}}}, 'definitions': {'package-name': {'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}, 'ext-module': {'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, 'file-directive': {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, 'file-directive-for-dependencies': {'title': "'file:' directive for dependencies", 'allOf': [{'$$description': ['**BETA**: subset of the ``requirements.txt`` format', 'without ``pip`` flags and options', '(one :pep:`508`-compliant string per line,', 'lines that are blank or start with ``#`` are excluded).', 'See `dynamic metadata', '`_.']}, {'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}]}, 'attr-directive': {'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, 'find-directive': {'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}}}, rule='additionalProperties')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive_properties_file(data, custom_formats={}, name_prefix=None):
-    data_one_of_count8 = 0
-    if data_one_of_count8 < 2:
-        try:
-            if not isinstance(data, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + " must be string", value=data, name="" + (name_prefix or "data") + "", definition={'type': 'string'}, rule='type')
-            data_one_of_count8 += 1
-        except JsonSchemaValueException: pass
-    if data_one_of_count8 < 2:
-        try:
-            if not isinstance(data, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + " must be array", value=data, name="" + (name_prefix or "data") + "", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data_is_list = isinstance(data, (list, tuple))
-            if data_is_list:
-                data_len = len(data)
-                for data_x, data_item in enumerate(data):
-                    if not isinstance(data_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + "[{data_x}]".format(**locals()) + " must be string", value=data_item, name="" + (name_prefix or "data") + "[{data_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-            data_one_of_count8 += 1
-        except JsonSchemaValueException: pass
-    if data_one_of_count8 != 1:
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be valid exactly by one definition" + (" (" + str(data_one_of_count8) + " matches found)"), value=data, name="" + (name_prefix or "data") + "", definition={'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}, rule='oneOf')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive_for_dependencies(data, custom_formats={}, name_prefix=None):
-    validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive(data, custom_formats, (name_prefix or "data") + "")
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_file_directive(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data__missing_keys = set(['file']) - data.keys()
-        if data__missing_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must contain " + (str(sorted(data__missing_keys)) + " properties"), value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, rule='required')
-        data_keys = set(data.keys())
-        if "file" in data_keys:
-            data_keys.remove("file")
-            data__file = data["file"]
-            data__file_one_of_count9 = 0
-            if data__file_one_of_count9 < 2:
-                try:
-                    if not isinstance(data__file, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".file must be string", value=data__file, name="" + (name_prefix or "data") + ".file", definition={'type': 'string'}, rule='type')
-                    data__file_one_of_count9 += 1
-                except JsonSchemaValueException: pass
-            if data__file_one_of_count9 < 2:
-                try:
-                    if not isinstance(data__file, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".file must be array", value=data__file, name="" + (name_prefix or "data") + ".file", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-                    data__file_is_list = isinstance(data__file, (list, tuple))
-                    if data__file_is_list:
-                        data__file_len = len(data__file)
-                        for data__file_x, data__file_item in enumerate(data__file):
-                            if not isinstance(data__file_item, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".file[{data__file_x}]".format(**locals()) + " must be string", value=data__file_item, name="" + (name_prefix or "data") + ".file[{data__file_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                    data__file_one_of_count9 += 1
-                except JsonSchemaValueException: pass
-            if data__file_one_of_count9 != 1:
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".file must be valid exactly by one definition" + (" (" + str(data__file_one_of_count9) + " matches found)"), value=data__file, name="" + (name_prefix or "data") + ".file", definition={'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}, rule='oneOf')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/file-directive', 'title': "'file:' directive", 'description': 'Value is read from a file (or list of files and then concatenated)', 'type': 'object', 'additionalProperties': False, 'properties': {'file': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}]}}, 'required': ['file']}, rule='additionalProperties')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_attr_directive(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data__missing_keys = set(['attr']) - data.keys()
-        if data__missing_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must contain " + (str(sorted(data__missing_keys)) + " properties"), value=data, name="" + (name_prefix or "data") + "", definition={'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, rule='required')
-        data_keys = set(data.keys())
-        if "attr" in data_keys:
-            data_keys.remove("attr")
-            data__attr = data["attr"]
-            if not isinstance(data__attr, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".attr must be string", value=data__attr, name="" + (name_prefix or "data") + ".attr", definition={'type': 'string', 'format': 'python-qualified-identifier'}, rule='type')
-            if isinstance(data__attr, str):
-                if not custom_formats["python-qualified-identifier"](data__attr):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".attr must be python-qualified-identifier", value=data__attr, name="" + (name_prefix or "data") + ".attr", definition={'type': 'string', 'format': 'python-qualified-identifier'}, rule='format')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'title': "'attr:' directive", '$id': '#/definitions/attr-directive', '$$description': ['Value is read from a module attribute. Supports callables and iterables;', 'unsupported types are cast via ``str()``'], 'type': 'object', 'additionalProperties': False, 'properties': {'attr': {'type': 'string', 'format': 'python-qualified-identifier'}}, 'required': ['attr']}, rule='additionalProperties')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_ext_module(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data__missing_keys = set(['name', 'sources']) - data.keys()
-        if data__missing_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must contain " + (str(sorted(data__missing_keys)) + " properties"), value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, rule='required')
-        data_keys = set(data.keys())
-        if "name" in data_keys:
-            data_keys.remove("name")
-            data__name = data["name"]
-            if not isinstance(data__name, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".name must be string", value=data__name, name="" + (name_prefix or "data") + ".name", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='type')
-            if isinstance(data__name, str):
-                if not custom_formats["python-module-name-relaxed"](data__name):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".name must be python-module-name-relaxed", value=data__name, name="" + (name_prefix or "data") + ".name", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='format')
-        if "sources" in data_keys:
-            data_keys.remove("sources")
-            data__sources = data["sources"]
-            if not isinstance(data__sources, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".sources must be array", value=data__sources, name="" + (name_prefix or "data") + ".sources", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__sources_is_list = isinstance(data__sources, (list, tuple))
-            if data__sources_is_list:
-                data__sources_len = len(data__sources)
-                for data__sources_x, data__sources_item in enumerate(data__sources):
-                    if not isinstance(data__sources_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".sources[{data__sources_x}]".format(**locals()) + " must be string", value=data__sources_item, name="" + (name_prefix or "data") + ".sources[{data__sources_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "include-dirs" in data_keys:
-            data_keys.remove("include-dirs")
-            data__includedirs = data["include-dirs"]
-            if not isinstance(data__includedirs, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".include-dirs must be array", value=data__includedirs, name="" + (name_prefix or "data") + ".include-dirs", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__includedirs_is_list = isinstance(data__includedirs, (list, tuple))
-            if data__includedirs_is_list:
-                data__includedirs_len = len(data__includedirs)
-                for data__includedirs_x, data__includedirs_item in enumerate(data__includedirs):
-                    if not isinstance(data__includedirs_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".include-dirs[{data__includedirs_x}]".format(**locals()) + " must be string", value=data__includedirs_item, name="" + (name_prefix or "data") + ".include-dirs[{data__includedirs_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "define-macros" in data_keys:
-            data_keys.remove("define-macros")
-            data__definemacros = data["define-macros"]
-            if not isinstance(data__definemacros, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".define-macros must be array", value=data__definemacros, name="" + (name_prefix or "data") + ".define-macros", definition={'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, rule='type')
-            data__definemacros_is_list = isinstance(data__definemacros, (list, tuple))
-            if data__definemacros_is_list:
-                data__definemacros_len = len(data__definemacros)
-                for data__definemacros_x, data__definemacros_item in enumerate(data__definemacros):
-                    if not isinstance(data__definemacros_item, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}]".format(**locals()) + " must be array", value=data__definemacros_item, name="" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}]".format(**locals()) + "", definition={'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}, rule='type')
-                    data__definemacros_item_is_list = isinstance(data__definemacros_item, (list, tuple))
-                    if data__definemacros_item_is_list:
-                        data__definemacros_item_len = len(data__definemacros_item)
-                        if data__definemacros_item_len > 0:
-                            data__definemacros_item__0 = data__definemacros_item[0]
-                            if not isinstance(data__definemacros_item__0, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][0]".format(**locals()) + " must be string", value=data__definemacros_item__0, name="" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][0]".format(**locals()) + "", definition={'description': 'macro name', 'type': 'string'}, rule='type')
-                        if data__definemacros_item_len > 1:
-                            data__definemacros_item__1 = data__definemacros_item[1]
-                            data__definemacros_item__1_one_of_count10 = 0
-                            if data__definemacros_item__1_one_of_count10 < 2:
-                                try:
-                                    if not isinstance(data__definemacros_item__1, (str)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][1]".format(**locals()) + " must be string", value=data__definemacros_item__1, name="" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][1]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                                    data__definemacros_item__1_one_of_count10 += 1
-                                except JsonSchemaValueException: pass
-                            if data__definemacros_item__1_one_of_count10 < 2:
-                                try:
-                                    if not isinstance(data__definemacros_item__1, (NoneType)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][1]".format(**locals()) + " must be null", value=data__definemacros_item__1, name="" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][1]".format(**locals()) + "", definition={'type': 'null'}, rule='type')
-                                    data__definemacros_item__1_one_of_count10 += 1
-                                except JsonSchemaValueException: pass
-                            if data__definemacros_item__1_one_of_count10 != 1:
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][1]".format(**locals()) + " must be valid exactly by one definition" + (" (" + str(data__definemacros_item__1_one_of_count10) + " matches found)"), value=data__definemacros_item__1, name="" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}][1]".format(**locals()) + "", definition={'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}, rule='oneOf')
-                        if data__definemacros_item_len > 2:
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}]".format(**locals()) + " must contain only specified items", value=data__definemacros_item, name="" + (name_prefix or "data") + ".define-macros[{data__definemacros_x}]".format(**locals()) + "", definition={'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}, rule='items')
-        if "undef-macros" in data_keys:
-            data_keys.remove("undef-macros")
-            data__undefmacros = data["undef-macros"]
-            if not isinstance(data__undefmacros, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".undef-macros must be array", value=data__undefmacros, name="" + (name_prefix or "data") + ".undef-macros", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__undefmacros_is_list = isinstance(data__undefmacros, (list, tuple))
-            if data__undefmacros_is_list:
-                data__undefmacros_len = len(data__undefmacros)
-                for data__undefmacros_x, data__undefmacros_item in enumerate(data__undefmacros):
-                    if not isinstance(data__undefmacros_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".undef-macros[{data__undefmacros_x}]".format(**locals()) + " must be string", value=data__undefmacros_item, name="" + (name_prefix or "data") + ".undef-macros[{data__undefmacros_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "library-dirs" in data_keys:
-            data_keys.remove("library-dirs")
-            data__librarydirs = data["library-dirs"]
-            if not isinstance(data__librarydirs, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".library-dirs must be array", value=data__librarydirs, name="" + (name_prefix or "data") + ".library-dirs", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__librarydirs_is_list = isinstance(data__librarydirs, (list, tuple))
-            if data__librarydirs_is_list:
-                data__librarydirs_len = len(data__librarydirs)
-                for data__librarydirs_x, data__librarydirs_item in enumerate(data__librarydirs):
-                    if not isinstance(data__librarydirs_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".library-dirs[{data__librarydirs_x}]".format(**locals()) + " must be string", value=data__librarydirs_item, name="" + (name_prefix or "data") + ".library-dirs[{data__librarydirs_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "libraries" in data_keys:
-            data_keys.remove("libraries")
-            data__libraries = data["libraries"]
-            if not isinstance(data__libraries, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".libraries must be array", value=data__libraries, name="" + (name_prefix or "data") + ".libraries", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__libraries_is_list = isinstance(data__libraries, (list, tuple))
-            if data__libraries_is_list:
-                data__libraries_len = len(data__libraries)
-                for data__libraries_x, data__libraries_item in enumerate(data__libraries):
-                    if not isinstance(data__libraries_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".libraries[{data__libraries_x}]".format(**locals()) + " must be string", value=data__libraries_item, name="" + (name_prefix or "data") + ".libraries[{data__libraries_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "runtime-library-dirs" in data_keys:
-            data_keys.remove("runtime-library-dirs")
-            data__runtimelibrarydirs = data["runtime-library-dirs"]
-            if not isinstance(data__runtimelibrarydirs, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".runtime-library-dirs must be array", value=data__runtimelibrarydirs, name="" + (name_prefix or "data") + ".runtime-library-dirs", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__runtimelibrarydirs_is_list = isinstance(data__runtimelibrarydirs, (list, tuple))
-            if data__runtimelibrarydirs_is_list:
-                data__runtimelibrarydirs_len = len(data__runtimelibrarydirs)
-                for data__runtimelibrarydirs_x, data__runtimelibrarydirs_item in enumerate(data__runtimelibrarydirs):
-                    if not isinstance(data__runtimelibrarydirs_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".runtime-library-dirs[{data__runtimelibrarydirs_x}]".format(**locals()) + " must be string", value=data__runtimelibrarydirs_item, name="" + (name_prefix or "data") + ".runtime-library-dirs[{data__runtimelibrarydirs_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "extra-objects" in data_keys:
-            data_keys.remove("extra-objects")
-            data__extraobjects = data["extra-objects"]
-            if not isinstance(data__extraobjects, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".extra-objects must be array", value=data__extraobjects, name="" + (name_prefix or "data") + ".extra-objects", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__extraobjects_is_list = isinstance(data__extraobjects, (list, tuple))
-            if data__extraobjects_is_list:
-                data__extraobjects_len = len(data__extraobjects)
-                for data__extraobjects_x, data__extraobjects_item in enumerate(data__extraobjects):
-                    if not isinstance(data__extraobjects_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".extra-objects[{data__extraobjects_x}]".format(**locals()) + " must be string", value=data__extraobjects_item, name="" + (name_prefix or "data") + ".extra-objects[{data__extraobjects_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "extra-compile-args" in data_keys:
-            data_keys.remove("extra-compile-args")
-            data__extracompileargs = data["extra-compile-args"]
-            if not isinstance(data__extracompileargs, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".extra-compile-args must be array", value=data__extracompileargs, name="" + (name_prefix or "data") + ".extra-compile-args", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__extracompileargs_is_list = isinstance(data__extracompileargs, (list, tuple))
-            if data__extracompileargs_is_list:
-                data__extracompileargs_len = len(data__extracompileargs)
-                for data__extracompileargs_x, data__extracompileargs_item in enumerate(data__extracompileargs):
-                    if not isinstance(data__extracompileargs_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".extra-compile-args[{data__extracompileargs_x}]".format(**locals()) + " must be string", value=data__extracompileargs_item, name="" + (name_prefix or "data") + ".extra-compile-args[{data__extracompileargs_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "extra-link-args" in data_keys:
-            data_keys.remove("extra-link-args")
-            data__extralinkargs = data["extra-link-args"]
-            if not isinstance(data__extralinkargs, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".extra-link-args must be array", value=data__extralinkargs, name="" + (name_prefix or "data") + ".extra-link-args", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__extralinkargs_is_list = isinstance(data__extralinkargs, (list, tuple))
-            if data__extralinkargs_is_list:
-                data__extralinkargs_len = len(data__extralinkargs)
-                for data__extralinkargs_x, data__extralinkargs_item in enumerate(data__extralinkargs):
-                    if not isinstance(data__extralinkargs_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".extra-link-args[{data__extralinkargs_x}]".format(**locals()) + " must be string", value=data__extralinkargs_item, name="" + (name_prefix or "data") + ".extra-link-args[{data__extralinkargs_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "export-symbols" in data_keys:
-            data_keys.remove("export-symbols")
-            data__exportsymbols = data["export-symbols"]
-            if not isinstance(data__exportsymbols, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".export-symbols must be array", value=data__exportsymbols, name="" + (name_prefix or "data") + ".export-symbols", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__exportsymbols_is_list = isinstance(data__exportsymbols, (list, tuple))
-            if data__exportsymbols_is_list:
-                data__exportsymbols_len = len(data__exportsymbols)
-                for data__exportsymbols_x, data__exportsymbols_item in enumerate(data__exportsymbols):
-                    if not isinstance(data__exportsymbols_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".export-symbols[{data__exportsymbols_x}]".format(**locals()) + " must be string", value=data__exportsymbols_item, name="" + (name_prefix or "data") + ".export-symbols[{data__exportsymbols_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "swig-opts" in data_keys:
-            data_keys.remove("swig-opts")
-            data__swigopts = data["swig-opts"]
-            if not isinstance(data__swigopts, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".swig-opts must be array", value=data__swigopts, name="" + (name_prefix or "data") + ".swig-opts", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__swigopts_is_list = isinstance(data__swigopts, (list, tuple))
-            if data__swigopts_is_list:
-                data__swigopts_len = len(data__swigopts)
-                for data__swigopts_x, data__swigopts_item in enumerate(data__swigopts):
-                    if not isinstance(data__swigopts_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".swig-opts[{data__swigopts_x}]".format(**locals()) + " must be string", value=data__swigopts_item, name="" + (name_prefix or "data") + ".swig-opts[{data__swigopts_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "depends" in data_keys:
-            data_keys.remove("depends")
-            data__depends = data["depends"]
-            if not isinstance(data__depends, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".depends must be array", value=data__depends, name="" + (name_prefix or "data") + ".depends", definition={'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__depends_is_list = isinstance(data__depends, (list, tuple))
-            if data__depends_is_list:
-                data__depends_len = len(data__depends)
-                for data__depends_x, data__depends_item in enumerate(data__depends):
-                    if not isinstance(data__depends_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".depends[{data__depends_x}]".format(**locals()) + " must be string", value=data__depends_item, name="" + (name_prefix or "data") + ".depends[{data__depends_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "language" in data_keys:
-            data_keys.remove("language")
-            data__language = data["language"]
-            if not isinstance(data__language, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".language must be string", value=data__language, name="" + (name_prefix or "data") + ".language", definition={'type': 'string'}, rule='type')
-        if "optional" in data_keys:
-            data_keys.remove("optional")
-            data__optional = data["optional"]
-            if not isinstance(data__optional, (bool)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".optional must be boolean", value=data__optional, name="" + (name_prefix or "data") + ".optional", definition={'type': 'boolean'}, rule='type')
-        if "py-limited-api" in data_keys:
-            data_keys.remove("py-limited-api")
-            data__pylimitedapi = data["py-limited-api"]
-            if not isinstance(data__pylimitedapi, (bool)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".py-limited-api must be boolean", value=data__pylimitedapi, name="" + (name_prefix or "data") + ".py-limited-api", definition={'type': 'boolean'}, rule='type')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/ext-module', 'title': 'Extension module', 'description': 'Parameters to construct a :class:`setuptools.Extension` object', 'type': 'object', 'required': ['name', 'sources'], 'additionalProperties': False, 'properties': {'name': {'type': 'string', 'format': 'python-module-name-relaxed'}, 'sources': {'type': 'array', 'items': {'type': 'string'}}, 'include-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'define-macros': {'type': 'array', 'items': {'type': 'array', 'items': [{'description': 'macro name', 'type': 'string'}, {'description': 'macro value', 'oneOf': [{'type': 'string'}, {'type': 'null'}]}], 'additionalItems': False}}, 'undef-macros': {'type': 'array', 'items': {'type': 'string'}}, 'library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'libraries': {'type': 'array', 'items': {'type': 'string'}}, 'runtime-library-dirs': {'type': 'array', 'items': {'type': 'string'}}, 'extra-objects': {'type': 'array', 'items': {'type': 'string'}}, 'extra-compile-args': {'type': 'array', 'items': {'type': 'string'}}, 'extra-link-args': {'type': 'array', 'items': {'type': 'string'}}, 'export-symbols': {'type': 'array', 'items': {'type': 'string'}}, 'swig-opts': {'type': 'array', 'items': {'type': 'string'}}, 'depends': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string'}, 'optional': {'type': 'boolean'}, 'py-limited-api': {'type': 'boolean'}}}, rule='additionalProperties')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_find_directive(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data_keys = set(data.keys())
-        if "find" in data_keys:
-            data_keys.remove("find")
-            data__find = data["find"]
-            if not isinstance(data__find, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".find must be object", value=data__find, name="" + (name_prefix or "data") + ".find", definition={'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}, rule='type')
-            data__find_is_dict = isinstance(data__find, dict)
-            if data__find_is_dict:
-                data__find_keys = set(data__find.keys())
-                if "where" in data__find_keys:
-                    data__find_keys.remove("where")
-                    data__find__where = data__find["where"]
-                    if not isinstance(data__find__where, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".find.where must be array", value=data__find__where, name="" + (name_prefix or "data") + ".find.where", definition={'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, rule='type')
-                    data__find__where_is_list = isinstance(data__find__where, (list, tuple))
-                    if data__find__where_is_list:
-                        data__find__where_len = len(data__find__where)
-                        for data__find__where_x, data__find__where_item in enumerate(data__find__where):
-                            if not isinstance(data__find__where_item, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".find.where[{data__find__where_x}]".format(**locals()) + " must be string", value=data__find__where_item, name="" + (name_prefix or "data") + ".find.where[{data__find__where_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                if "exclude" in data__find_keys:
-                    data__find_keys.remove("exclude")
-                    data__find__exclude = data__find["exclude"]
-                    if not isinstance(data__find__exclude, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".find.exclude must be array", value=data__find__exclude, name="" + (name_prefix or "data") + ".find.exclude", definition={'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, rule='type')
-                    data__find__exclude_is_list = isinstance(data__find__exclude, (list, tuple))
-                    if data__find__exclude_is_list:
-                        data__find__exclude_len = len(data__find__exclude)
-                        for data__find__exclude_x, data__find__exclude_item in enumerate(data__find__exclude):
-                            if not isinstance(data__find__exclude_item, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".find.exclude[{data__find__exclude_x}]".format(**locals()) + " must be string", value=data__find__exclude_item, name="" + (name_prefix or "data") + ".find.exclude[{data__find__exclude_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                if "include" in data__find_keys:
-                    data__find_keys.remove("include")
-                    data__find__include = data__find["include"]
-                    if not isinstance(data__find__include, (list, tuple)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".find.include must be array", value=data__find__include, name="" + (name_prefix or "data") + ".find.include", definition={'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, rule='type')
-                    data__find__include_is_list = isinstance(data__find__include, (list, tuple))
-                    if data__find__include_is_list:
-                        data__find__include_len = len(data__find__include)
-                        for data__find__include_x, data__find__include_item in enumerate(data__find__include):
-                            if not isinstance(data__find__include_item, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".find.include[{data__find__include_x}]".format(**locals()) + " must be string", value=data__find__include_item, name="" + (name_prefix or "data") + ".find.include[{data__find__include_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-                if "namespaces" in data__find_keys:
-                    data__find_keys.remove("namespaces")
-                    data__find__namespaces = data__find["namespaces"]
-                    if not isinstance(data__find__namespaces, (bool)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".find.namespaces must be boolean", value=data__find__namespaces, name="" + (name_prefix or "data") + ".find.namespaces", definition={'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}, rule='type')
-                if data__find_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".find must not contain "+str(data__find_keys)+" properties", value=data__find, name="" + (name_prefix or "data") + ".find", definition={'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}, rule='additionalProperties')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/find-directive', 'title': "'find:' directive", 'type': 'object', 'additionalProperties': False, 'properties': {'find': {'type': 'object', '$$description': ['Dynamic `package discovery', '`_.'], 'additionalProperties': False, 'properties': {'where': {'description': 'Directories to be searched for packages (Unix-style relative path)', 'type': 'array', 'items': {'type': 'string'}}, 'exclude': {'type': 'array', '$$description': ['Exclude packages that match the values listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'include': {'type': 'array', '$$description': ['Restrict the found packages to just the ones listed in this field.', "Can container shell-style wildcards (e.g. ``'pkg.*'``)"], 'items': {'type': 'string'}}, 'namespaces': {'type': 'boolean', '$$description': ['When ``True``, directories without a ``__init__.py`` file will also', 'be scanned for :pep:`420`-style implicit namespaces']}}}}}, rule='additionalProperties')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_userguide_pyproject_config_html__definitions_package_name(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (str)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be string", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}, rule='type')
-    data_any_of_count11 = 0
-    if not data_any_of_count11:
-        try:
-            if not isinstance(data, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + " must be string", value=data, name="" + (name_prefix or "data") + "", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='type')
-            if isinstance(data, str):
-                if not custom_formats["python-module-name-relaxed"](data):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + " must be python-module-name-relaxed", value=data, name="" + (name_prefix or "data") + "", definition={'type': 'string', 'format': 'python-module-name-relaxed'}, rule='format')
-            data_any_of_count11 += 1
-        except JsonSchemaValueException: pass
-    if not data_any_of_count11:
-        try:
-            if not isinstance(data, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + " must be string", value=data, name="" + (name_prefix or "data") + "", definition={'type': 'string', 'format': 'pep561-stub-name'}, rule='type')
-            if isinstance(data, str):
-                if not custom_formats["pep561-stub-name"](data):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + " must be pep561-stub-name", value=data, name="" + (name_prefix or "data") + "", definition={'type': 'string', 'format': 'pep561-stub-name'}, rule='format')
-            data_any_of_count11 += 1
-        except JsonSchemaValueException: pass
-    if not data_any_of_count11:
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " cannot be validated by any definition", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/package-name', 'title': 'Valid package name', 'description': 'Valid package name (importable or :pep:`561`).', 'type': 'string', 'anyOf': [{'type': 'string', 'format': 'python-module-name-relaxed'}, {'type': 'string', 'format': 'pep561-stub-name'}]}, rule='anyOf')
-    return data
-
-def validate_https___setuptools_pypa_io_en_latest_deprecated_distutils_configfile_html(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://setuptools.pypa.io/en/latest/deprecated/distutils/configfile.html', 'title': '``tool.distutils`` table', '$$description': ['**EXPERIMENTAL** (NOT OFFICIALLY SUPPORTED): Use ``tool.distutils``', 'subtables to configure arguments for ``distutils`` commands.', 'Originally, ``distutils`` allowed developers to configure arguments for', '``setup.py`` commands via `distutils configuration files', '`_.', 'See also `the old Python docs _`.'], 'type': 'object', 'properties': {'global': {'type': 'object', 'description': 'Global options applied to all ``distutils`` commands'}}, 'patternProperties': {'.+': {'type': 'object'}}, '$comment': 'TODO: Is there a practical way of making this schema more specific?'}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data_keys = set(data.keys())
-        if "global" in data_keys:
-            data_keys.remove("global")
-            data__global = data["global"]
-            if not isinstance(data__global, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".global must be object", value=data__global, name="" + (name_prefix or "data") + ".global", definition={'type': 'object', 'description': 'Global options applied to all ``distutils`` commands'}, rule='type')
-        for data_key, data_val in data.items():
-            if REGEX_PATTERNS['.+'].search(data_key):
-                if data_key in data_keys:
-                    data_keys.remove(data_key)
-                if not isinstance(data_val, (dict)):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".{data_key}".format(**locals()) + " must be object", value=data_val, name="" + (name_prefix or "data") + ".{data_key}".format(**locals()) + "", definition={'type': 'object'}, rule='type')
-    return data
-
-def validate_https___packaging_python_org_en_latest_specifications_pyproject_toml(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/pyproject-toml/', 'title': 'Package metadata stored in the ``project`` table', '$$description': ['Data structure for the **project** table inside ``pyproject.toml``', '(as initially defined in :pep:`621`)'], 'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, 'version': {'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, 'description': {'type': 'string', '$$description': ['The `summary description of the project', '`_']}, 'readme': {'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, 'requires-python': {'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, 'license': {'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, 'license-files': {'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, 'authors': {'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, 'maintainers': {'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, 'keywords': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, 'classifiers': {'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, 'urls': {'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, 'scripts': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'gui-scripts': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'entry-points': {'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}}}, 'dependencies': {'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}, 'optional-dependencies': {'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, 'dynamic': {'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}}, 'required': ['name'], 'additionalProperties': False, 'allOf': [{'if': {'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, 'then': {'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}}, {'if': {'required': ['license-files']}, 'then': {'properties': {'license': {'type': 'string'}}}}], 'definitions': {'author': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, 'entry-point-group': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'dependency': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}, rule='type')
-    try:
-        try:
-            data_is_dict = isinstance(data, dict)
-            if data_is_dict:
-                data__missing_keys = set(['dynamic']) - data.keys()
-                if data__missing_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + " must contain " + (str(sorted(data__missing_keys)) + " properties"), value=data, name="" + (name_prefix or "data") + "", definition={'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, rule='required')
-                data_keys = set(data.keys())
-                if "dynamic" in data_keys:
-                    data_keys.remove("dynamic")
-                    data__dynamic = data["dynamic"]
-                    data__dynamic_is_list = isinstance(data__dynamic, (list, tuple))
-                    if data__dynamic_is_list:
-                        data__dynamic_contains = False
-                        for data__dynamic_key in data__dynamic:
-                            try:
-                                if data__dynamic_key != "version":
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic must be same as const definition: version", value=data__dynamic_key, name="" + (name_prefix or "data") + ".dynamic", definition={'const': 'version'}, rule='const')
-                                data__dynamic_contains = True
-                                break
-                            except JsonSchemaValueException: pass
-                        if not data__dynamic_contains:
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic must contain one of contains definition", value=data__dynamic, name="" + (name_prefix or "data") + ".dynamic", definition={'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}, rule='contains')
-        except JsonSchemaValueException: pass
-        else:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must NOT match a disallowed definition", value=data, name="" + (name_prefix or "data") + "", definition={'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, rule='not')
-    except JsonSchemaValueException:
-        pass
-    else:
-        data_is_dict = isinstance(data, dict)
-        if data_is_dict:
-            data__missing_keys = set(['version']) - data.keys()
-            if data__missing_keys:
-                raise JsonSchemaValueException("" + (name_prefix or "data") + " must contain " + (str(sorted(data__missing_keys)) + " properties"), value=data, name="" + (name_prefix or "data") + "", definition={'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}, rule='required')
-    try:
-        data_is_dict = isinstance(data, dict)
-        if data_is_dict:
-            data__missing_keys = set(['license-files']) - data.keys()
-            if data__missing_keys:
-                raise JsonSchemaValueException("" + (name_prefix or "data") + " must contain " + (str(sorted(data__missing_keys)) + " properties"), value=data, name="" + (name_prefix or "data") + "", definition={'required': ['license-files']}, rule='required')
-    except JsonSchemaValueException:
-        pass
-    else:
-        data_is_dict = isinstance(data, dict)
-        if data_is_dict:
-            data_keys = set(data.keys())
-            if "license" in data_keys:
-                data_keys.remove("license")
-                data__license = data["license"]
-                if not isinstance(data__license, (str)):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must be string", value=data__license, name="" + (name_prefix or "data") + ".license", definition={'type': 'string'}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data__missing_keys = set(['name']) - data.keys()
-        if data__missing_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must contain " + (str(sorted(data__missing_keys)) + " properties"), value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/pyproject-toml/', 'title': 'Package metadata stored in the ``project`` table', '$$description': ['Data structure for the **project** table inside ``pyproject.toml``', '(as initially defined in :pep:`621`)'], 'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, 'version': {'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, 'description': {'type': 'string', '$$description': ['The `summary description of the project', '`_']}, 'readme': {'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, 'requires-python': {'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, 'license': {'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, 'license-files': {'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, 'authors': {'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, 'maintainers': {'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, 'keywords': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, 'classifiers': {'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, 'urls': {'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, 'scripts': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'gui-scripts': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'entry-points': {'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}}}, 'dependencies': {'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}, 'optional-dependencies': {'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, 'dynamic': {'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}}, 'required': ['name'], 'additionalProperties': False, 'allOf': [{'if': {'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, 'then': {'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}}, {'if': {'required': ['license-files']}, 'then': {'properties': {'license': {'type': 'string'}}}}], 'definitions': {'author': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, 'entry-point-group': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'dependency': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}, rule='required')
-        data_keys = set(data.keys())
-        if "name" in data_keys:
-            data_keys.remove("name")
-            data__name = data["name"]
-            if not isinstance(data__name, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".name must be string", value=data__name, name="" + (name_prefix or "data") + ".name", definition={'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, rule='type')
-            if isinstance(data__name, str):
-                if not custom_formats["pep508-identifier"](data__name):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".name must be pep508-identifier", value=data__name, name="" + (name_prefix or "data") + ".name", definition={'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, rule='format')
-        if "version" in data_keys:
-            data_keys.remove("version")
-            data__version = data["version"]
-            if not isinstance(data__version, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".version must be string", value=data__version, name="" + (name_prefix or "data") + ".version", definition={'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, rule='type')
-            if isinstance(data__version, str):
-                if not custom_formats["pep440"](data__version):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".version must be pep440", value=data__version, name="" + (name_prefix or "data") + ".version", definition={'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, rule='format')
-        if "description" in data_keys:
-            data_keys.remove("description")
-            data__description = data["description"]
-            if not isinstance(data__description, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".description must be string", value=data__description, name="" + (name_prefix or "data") + ".description", definition={'type': 'string', '$$description': ['The `summary description of the project', '`_']}, rule='type')
-        if "readme" in data_keys:
-            data_keys.remove("readme")
-            data__readme = data["readme"]
-            data__readme_one_of_count12 = 0
-            if data__readme_one_of_count12 < 2:
-                try:
-                    if not isinstance(data__readme, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme must be string", value=data__readme, name="" + (name_prefix or "data") + ".readme", definition={'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, rule='type')
-                    data__readme_one_of_count12 += 1
-                except JsonSchemaValueException: pass
-            if data__readme_one_of_count12 < 2:
-                try:
-                    if not isinstance(data__readme, (dict)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme must be object", value=data__readme, name="" + (name_prefix or "data") + ".readme", definition={'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}, rule='type')
-                    data__readme_any_of_count13 = 0
-                    if not data__readme_any_of_count13:
-                        try:
-                            data__readme_is_dict = isinstance(data__readme, dict)
-                            if data__readme_is_dict:
-                                data__readme__missing_keys = set(['file']) - data__readme.keys()
-                                if data__readme__missing_keys:
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme must contain " + (str(sorted(data__readme__missing_keys)) + " properties"), value=data__readme, name="" + (name_prefix or "data") + ".readme", definition={'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, rule='required')
-                                data__readme_keys = set(data__readme.keys())
-                                if "file" in data__readme_keys:
-                                    data__readme_keys.remove("file")
-                                    data__readme__file = data__readme["file"]
-                                    if not isinstance(data__readme__file, (str)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme.file must be string", value=data__readme__file, name="" + (name_prefix or "data") + ".readme.file", definition={'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}, rule='type')
-                            data__readme_any_of_count13 += 1
-                        except JsonSchemaValueException: pass
-                    if not data__readme_any_of_count13:
-                        try:
-                            data__readme_is_dict = isinstance(data__readme, dict)
-                            if data__readme_is_dict:
-                                data__readme__missing_keys = set(['text']) - data__readme.keys()
-                                if data__readme__missing_keys:
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme must contain " + (str(sorted(data__readme__missing_keys)) + " properties"), value=data__readme, name="" + (name_prefix or "data") + ".readme", definition={'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}, rule='required')
-                                data__readme_keys = set(data__readme.keys())
-                                if "text" in data__readme_keys:
-                                    data__readme_keys.remove("text")
-                                    data__readme__text = data__readme["text"]
-                                    if not isinstance(data__readme__text, (str)):
-                                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme.text must be string", value=data__readme__text, name="" + (name_prefix or "data") + ".readme.text", definition={'type': 'string', 'description': 'Full text describing the project.'}, rule='type')
-                            data__readme_any_of_count13 += 1
-                        except JsonSchemaValueException: pass
-                    if not data__readme_any_of_count13:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme cannot be validated by any definition", value=data__readme, name="" + (name_prefix or "data") + ".readme", definition={'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, rule='anyOf')
-                    data__readme_is_dict = isinstance(data__readme, dict)
-                    if data__readme_is_dict:
-                        data__readme__missing_keys = set(['content-type']) - data__readme.keys()
-                        if data__readme__missing_keys:
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme must contain " + (str(sorted(data__readme__missing_keys)) + " properties"), value=data__readme, name="" + (name_prefix or "data") + ".readme", definition={'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}, rule='required')
-                        data__readme_keys = set(data__readme.keys())
-                        if "content-type" in data__readme_keys:
-                            data__readme_keys.remove("content-type")
-                            data__readme__contenttype = data__readme["content-type"]
-                            if not isinstance(data__readme__contenttype, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme.content-type must be string", value=data__readme__contenttype, name="" + (name_prefix or "data") + ".readme.content-type", definition={'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}, rule='type')
-                    data__readme_one_of_count12 += 1
-                except JsonSchemaValueException: pass
-            if data__readme_one_of_count12 != 1:
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".readme must be valid exactly by one definition" + (" (" + str(data__readme_one_of_count12) + " matches found)"), value=data__readme, name="" + (name_prefix or "data") + ".readme", definition={'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, rule='oneOf')
-        if "requires-python" in data_keys:
-            data_keys.remove("requires-python")
-            data__requirespython = data["requires-python"]
-            if not isinstance(data__requirespython, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".requires-python must be string", value=data__requirespython, name="" + (name_prefix or "data") + ".requires-python", definition={'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, rule='type')
-            if isinstance(data__requirespython, str):
-                if not custom_formats["pep508-versionspec"](data__requirespython):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".requires-python must be pep508-versionspec", value=data__requirespython, name="" + (name_prefix or "data") + ".requires-python", definition={'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, rule='format')
-        if "license" in data_keys:
-            data_keys.remove("license")
-            data__license = data["license"]
-            data__license_one_of_count14 = 0
-            if data__license_one_of_count14 < 2:
-                try:
-                    if not isinstance(data__license, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must be string", value=data__license, name="" + (name_prefix or "data") + ".license", definition={'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, rule='type')
-                    if isinstance(data__license, str):
-                        if not custom_formats["SPDX"](data__license):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must be SPDX", value=data__license, name="" + (name_prefix or "data") + ".license", definition={'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, rule='format')
-                    data__license_one_of_count14 += 1
-                except JsonSchemaValueException: pass
-            if data__license_one_of_count14 < 2:
-                try:
-                    if not isinstance(data__license, (dict)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must be object", value=data__license, name="" + (name_prefix or "data") + ".license", definition={'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, rule='type')
-                    data__license_is_dict = isinstance(data__license, dict)
-                    if data__license_is_dict:
-                        data__license__missing_keys = set(['file']) - data__license.keys()
-                        if data__license__missing_keys:
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must contain " + (str(sorted(data__license__missing_keys)) + " properties"), value=data__license, name="" + (name_prefix or "data") + ".license", definition={'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, rule='required')
-                        data__license_keys = set(data__license.keys())
-                        if "file" in data__license_keys:
-                            data__license_keys.remove("file")
-                            data__license__file = data__license["file"]
-                            if not isinstance(data__license__file, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".license.file must be string", value=data__license__file, name="" + (name_prefix or "data") + ".license.file", definition={'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}, rule='type')
-                    data__license_one_of_count14 += 1
-                except JsonSchemaValueException: pass
-            if data__license_one_of_count14 < 2:
-                try:
-                    if not isinstance(data__license, (dict)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must be object", value=data__license, name="" + (name_prefix or "data") + ".license", definition={'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}, rule='type')
-                    data__license_is_dict = isinstance(data__license, dict)
-                    if data__license_is_dict:
-                        data__license__missing_keys = set(['text']) - data__license.keys()
-                        if data__license__missing_keys:
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must contain " + (str(sorted(data__license__missing_keys)) + " properties"), value=data__license, name="" + (name_prefix or "data") + ".license", definition={'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}, rule='required')
-                        data__license_keys = set(data__license.keys())
-                        if "text" in data__license_keys:
-                            data__license_keys.remove("text")
-                            data__license__text = data__license["text"]
-                            if not isinstance(data__license__text, (str)):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".license.text must be string", value=data__license__text, name="" + (name_prefix or "data") + ".license.text", definition={'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}, rule='type')
-                    data__license_one_of_count14 += 1
-                except JsonSchemaValueException: pass
-            if data__license_one_of_count14 != 1:
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".license must be valid exactly by one definition" + (" (" + str(data__license_one_of_count14) + " matches found)"), value=data__license, name="" + (name_prefix or "data") + ".license", definition={'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, rule='oneOf')
-        if "license-files" in data_keys:
-            data_keys.remove("license-files")
-            data__licensefiles = data["license-files"]
-            if not isinstance(data__licensefiles, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".license-files must be array", value=data__licensefiles, name="" + (name_prefix or "data") + ".license-files", definition={'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, rule='type')
-            data__licensefiles_is_list = isinstance(data__licensefiles, (list, tuple))
-            if data__licensefiles_is_list:
-                data__licensefiles_len = len(data__licensefiles)
-                for data__licensefiles_x, data__licensefiles_item in enumerate(data__licensefiles):
-                    if not isinstance(data__licensefiles_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".license-files[{data__licensefiles_x}]".format(**locals()) + " must be string", value=data__licensefiles_item, name="" + (name_prefix or "data") + ".license-files[{data__licensefiles_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "authors" in data_keys:
-            data_keys.remove("authors")
-            data__authors = data["authors"]
-            if not isinstance(data__authors, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".authors must be array", value=data__authors, name="" + (name_prefix or "data") + ".authors", definition={'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, rule='type')
-            data__authors_is_list = isinstance(data__authors, (list, tuple))
-            if data__authors_is_list:
-                data__authors_len = len(data__authors)
-                for data__authors_x, data__authors_item in enumerate(data__authors):
-                    validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_author(data__authors_item, custom_formats, (name_prefix or "data") + ".authors[{data__authors_x}]".format(**locals()))
-        if "maintainers" in data_keys:
-            data_keys.remove("maintainers")
-            data__maintainers = data["maintainers"]
-            if not isinstance(data__maintainers, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".maintainers must be array", value=data__maintainers, name="" + (name_prefix or "data") + ".maintainers", definition={'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, rule='type')
-            data__maintainers_is_list = isinstance(data__maintainers, (list, tuple))
-            if data__maintainers_is_list:
-                data__maintainers_len = len(data__maintainers)
-                for data__maintainers_x, data__maintainers_item in enumerate(data__maintainers):
-                    validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_author(data__maintainers_item, custom_formats, (name_prefix or "data") + ".maintainers[{data__maintainers_x}]".format(**locals()))
-        if "keywords" in data_keys:
-            data_keys.remove("keywords")
-            data__keywords = data["keywords"]
-            if not isinstance(data__keywords, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".keywords must be array", value=data__keywords, name="" + (name_prefix or "data") + ".keywords", definition={'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, rule='type')
-            data__keywords_is_list = isinstance(data__keywords, (list, tuple))
-            if data__keywords_is_list:
-                data__keywords_len = len(data__keywords)
-                for data__keywords_x, data__keywords_item in enumerate(data__keywords):
-                    if not isinstance(data__keywords_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".keywords[{data__keywords_x}]".format(**locals()) + " must be string", value=data__keywords_item, name="" + (name_prefix or "data") + ".keywords[{data__keywords_x}]".format(**locals()) + "", definition={'type': 'string'}, rule='type')
-        if "classifiers" in data_keys:
-            data_keys.remove("classifiers")
-            data__classifiers = data["classifiers"]
-            if not isinstance(data__classifiers, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".classifiers must be array", value=data__classifiers, name="" + (name_prefix or "data") + ".classifiers", definition={'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, rule='type')
-            data__classifiers_is_list = isinstance(data__classifiers, (list, tuple))
-            if data__classifiers_is_list:
-                data__classifiers_len = len(data__classifiers)
-                for data__classifiers_x, data__classifiers_item in enumerate(data__classifiers):
-                    if not isinstance(data__classifiers_item, (str)):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".classifiers[{data__classifiers_x}]".format(**locals()) + " must be string", value=data__classifiers_item, name="" + (name_prefix or "data") + ".classifiers[{data__classifiers_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, rule='type')
-                    if isinstance(data__classifiers_item, str):
-                        if not custom_formats["trove-classifier"](data__classifiers_item):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".classifiers[{data__classifiers_x}]".format(**locals()) + " must be trove-classifier", value=data__classifiers_item, name="" + (name_prefix or "data") + ".classifiers[{data__classifiers_x}]".format(**locals()) + "", definition={'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, rule='format')
-        if "urls" in data_keys:
-            data_keys.remove("urls")
-            data__urls = data["urls"]
-            if not isinstance(data__urls, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".urls must be object", value=data__urls, name="" + (name_prefix or "data") + ".urls", definition={'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, rule='type')
-            data__urls_is_dict = isinstance(data__urls, dict)
-            if data__urls_is_dict:
-                data__urls_keys = set(data__urls.keys())
-                for data__urls_key, data__urls_val in data__urls.items():
-                    if REGEX_PATTERNS['^.+$'].search(data__urls_key):
-                        if data__urls_key in data__urls_keys:
-                            data__urls_keys.remove(data__urls_key)
-                        if not isinstance(data__urls_val, (str)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".urls.{data__urls_key}".format(**locals()) + " must be string", value=data__urls_val, name="" + (name_prefix or "data") + ".urls.{data__urls_key}".format(**locals()) + "", definition={'type': 'string', 'format': 'url'}, rule='type')
-                        if isinstance(data__urls_val, str):
-                            if not custom_formats["url"](data__urls_val):
-                                raise JsonSchemaValueException("" + (name_prefix or "data") + ".urls.{data__urls_key}".format(**locals()) + " must be url", value=data__urls_val, name="" + (name_prefix or "data") + ".urls.{data__urls_key}".format(**locals()) + "", definition={'type': 'string', 'format': 'url'}, rule='format')
-                if data__urls_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".urls must not contain "+str(data__urls_keys)+" properties", value=data__urls, name="" + (name_prefix or "data") + ".urls", definition={'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, rule='additionalProperties')
-        if "scripts" in data_keys:
-            data_keys.remove("scripts")
-            data__scripts = data["scripts"]
-            validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_entry_point_group(data__scripts, custom_formats, (name_prefix or "data") + ".scripts")
-        if "gui-scripts" in data_keys:
-            data_keys.remove("gui-scripts")
-            data__guiscripts = data["gui-scripts"]
-            validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_entry_point_group(data__guiscripts, custom_formats, (name_prefix or "data") + ".gui-scripts")
-        if "entry-points" in data_keys:
-            data_keys.remove("entry-points")
-            data__entrypoints = data["entry-points"]
-            data__entrypoints_is_dict = isinstance(data__entrypoints, dict)
-            if data__entrypoints_is_dict:
-                data__entrypoints_keys = set(data__entrypoints.keys())
-                for data__entrypoints_key, data__entrypoints_val in data__entrypoints.items():
-                    if REGEX_PATTERNS['^.+$'].search(data__entrypoints_key):
-                        if data__entrypoints_key in data__entrypoints_keys:
-                            data__entrypoints_keys.remove(data__entrypoints_key)
-                        validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_entry_point_group(data__entrypoints_val, custom_formats, (name_prefix or "data") + ".entry-points.{data__entrypoints_key}".format(**locals()))
-                if data__entrypoints_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".entry-points must not contain "+str(data__entrypoints_keys)+" properties", value=data__entrypoints, name="" + (name_prefix or "data") + ".entry-points", definition={'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}}}, rule='additionalProperties')
-                data__entrypoints_len = len(data__entrypoints)
-                if data__entrypoints_len != 0:
-                    data__entrypoints_property_names = True
-                    for data__entrypoints_key in data__entrypoints:
-                        try:
-                            if isinstance(data__entrypoints_key, str):
-                                if not custom_formats["python-entrypoint-group"](data__entrypoints_key):
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".entry-points must be python-entrypoint-group", value=data__entrypoints_key, name="" + (name_prefix or "data") + ".entry-points", definition={'format': 'python-entrypoint-group'}, rule='format')
-                        except JsonSchemaValueException:
-                            data__entrypoints_property_names = False
-                    if not data__entrypoints_property_names:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".entry-points must be named by propertyName definition", value=data__entrypoints, name="" + (name_prefix or "data") + ".entry-points", definition={'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}}}, rule='propertyNames')
-        if "dependencies" in data_keys:
-            data_keys.remove("dependencies")
-            data__dependencies = data["dependencies"]
-            if not isinstance(data__dependencies, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dependencies must be array", value=data__dependencies, name="" + (name_prefix or "data") + ".dependencies", definition={'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}, rule='type')
-            data__dependencies_is_list = isinstance(data__dependencies, (list, tuple))
-            if data__dependencies_is_list:
-                data__dependencies_len = len(data__dependencies)
-                for data__dependencies_x, data__dependencies_item in enumerate(data__dependencies):
-                    validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_dependency(data__dependencies_item, custom_formats, (name_prefix or "data") + ".dependencies[{data__dependencies_x}]".format(**locals()))
-        if "optional-dependencies" in data_keys:
-            data_keys.remove("optional-dependencies")
-            data__optionaldependencies = data["optional-dependencies"]
-            if not isinstance(data__optionaldependencies, (dict)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".optional-dependencies must be object", value=data__optionaldependencies, name="" + (name_prefix or "data") + ".optional-dependencies", definition={'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, rule='type')
-            data__optionaldependencies_is_dict = isinstance(data__optionaldependencies, dict)
-            if data__optionaldependencies_is_dict:
-                data__optionaldependencies_keys = set(data__optionaldependencies.keys())
-                for data__optionaldependencies_key, data__optionaldependencies_val in data__optionaldependencies.items():
-                    if REGEX_PATTERNS['^.+$'].search(data__optionaldependencies_key):
-                        if data__optionaldependencies_key in data__optionaldependencies_keys:
-                            data__optionaldependencies_keys.remove(data__optionaldependencies_key)
-                        if not isinstance(data__optionaldependencies_val, (list, tuple)):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + ".optional-dependencies.{data__optionaldependencies_key}".format(**locals()) + " must be array", value=data__optionaldependencies_val, name="" + (name_prefix or "data") + ".optional-dependencies.{data__optionaldependencies_key}".format(**locals()) + "", definition={'type': 'array', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}, rule='type')
-                        data__optionaldependencies_val_is_list = isinstance(data__optionaldependencies_val, (list, tuple))
-                        if data__optionaldependencies_val_is_list:
-                            data__optionaldependencies_val_len = len(data__optionaldependencies_val)
-                            for data__optionaldependencies_val_x, data__optionaldependencies_val_item in enumerate(data__optionaldependencies_val):
-                                validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_dependency(data__optionaldependencies_val_item, custom_formats, (name_prefix or "data") + ".optional-dependencies.{data__optionaldependencies_key}[{data__optionaldependencies_val_x}]".format(**locals()))
-                if data__optionaldependencies_keys:
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".optional-dependencies must not contain "+str(data__optionaldependencies_keys)+" properties", value=data__optionaldependencies, name="" + (name_prefix or "data") + ".optional-dependencies", definition={'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, rule='additionalProperties')
-                data__optionaldependencies_len = len(data__optionaldependencies)
-                if data__optionaldependencies_len != 0:
-                    data__optionaldependencies_property_names = True
-                    for data__optionaldependencies_key in data__optionaldependencies:
-                        try:
-                            if isinstance(data__optionaldependencies_key, str):
-                                if not custom_formats["pep508-identifier"](data__optionaldependencies_key):
-                                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".optional-dependencies must be pep508-identifier", value=data__optionaldependencies_key, name="" + (name_prefix or "data") + ".optional-dependencies", definition={'format': 'pep508-identifier'}, rule='format')
-                        except JsonSchemaValueException:
-                            data__optionaldependencies_property_names = False
-                    if not data__optionaldependencies_property_names:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".optional-dependencies must be named by propertyName definition", value=data__optionaldependencies, name="" + (name_prefix or "data") + ".optional-dependencies", definition={'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, rule='propertyNames')
-        if "dynamic" in data_keys:
-            data_keys.remove("dynamic")
-            data__dynamic = data["dynamic"]
-            if not isinstance(data__dynamic, (list, tuple)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic must be array", value=data__dynamic, name="" + (name_prefix or "data") + ".dynamic", definition={'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}, rule='type')
-            data__dynamic_is_list = isinstance(data__dynamic, (list, tuple))
-            if data__dynamic_is_list:
-                data__dynamic_len = len(data__dynamic)
-                for data__dynamic_x, data__dynamic_item in enumerate(data__dynamic):
-                    if data__dynamic_item not in ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']:
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".dynamic[{data__dynamic_x}]".format(**locals()) + " must be one of ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']", value=data__dynamic_item, name="" + (name_prefix or "data") + ".dynamic[{data__dynamic_x}]".format(**locals()) + "", definition={'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}, rule='enum')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$schema': 'http://json-schema.org/draft-07/schema#', '$id': 'https://packaging.python.org/en/latest/specifications/pyproject-toml/', 'title': 'Package metadata stored in the ``project`` table', '$$description': ['Data structure for the **project** table inside ``pyproject.toml``', '(as initially defined in :pep:`621`)'], 'type': 'object', 'properties': {'name': {'type': 'string', 'description': 'The name (primary identifier) of the project. MUST be statically defined.', 'format': 'pep508-identifier'}, 'version': {'type': 'string', 'description': 'The version of the project as supported by :pep:`440`.', 'format': 'pep440'}, 'description': {'type': 'string', '$$description': ['The `summary description of the project', '`_']}, 'readme': {'$$description': ['`Full/detailed description of the project in the form of a README', '`_', "with meaning similar to the one defined in `core metadata's Description", '`_'], 'oneOf': [{'type': 'string', '$$description': ['Relative path to a text file (UTF-8) containing the full description', 'of the project. If the file path ends in case-insensitive ``.md`` or', '``.rst`` suffixes, then the content-type is respectively', '``text/markdown`` or ``text/x-rst``']}, {'type': 'object', 'allOf': [{'anyOf': [{'properties': {'file': {'type': 'string', '$$description': ['Relative path to a text file containing the full description', 'of the project.']}}, 'required': ['file']}, {'properties': {'text': {'type': 'string', 'description': 'Full text describing the project.'}}, 'required': ['text']}]}, {'properties': {'content-type': {'type': 'string', '$$description': ['Content-type (:rfc:`1341`) of the full description', '(e.g. ``text/markdown``). The ``charset`` parameter is assumed', 'UTF-8 when not present.'], '$comment': 'TODO: add regex pattern or format?'}}, 'required': ['content-type']}]}]}, 'requires-python': {'type': 'string', 'format': 'pep508-versionspec', '$$description': ['`The Python version requirements of the project', '`_.']}, 'license': {'description': '`Project license `_.', 'oneOf': [{'type': 'string', 'description': 'An SPDX license identifier', 'format': 'SPDX'}, {'type': 'object', 'properties': {'file': {'type': 'string', '$$description': ['Relative path to the file (UTF-8) which contains the license for the', 'project.']}}, 'required': ['file']}, {'type': 'object', 'properties': {'text': {'type': 'string', '$$description': ['The license of the project whose meaning is that of the', '`License field from the core metadata', '`_.']}}, 'required': ['text']}]}, 'license-files': {'description': 'Paths or globs to paths of license files', 'type': 'array', 'items': {'type': 'string'}}, 'authors': {'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'authors' of the project.", 'The exact meaning is open to interpretation (e.g. original or primary authors,', 'current maintainers, or owners of the package).']}, 'maintainers': {'type': 'array', 'items': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, '$$description': ["The people or organizations considered to be the 'maintainers' of the project.", 'Similarly to ``authors``, the exact meaning is open to interpretation.']}, 'keywords': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of keywords to assist searching for the distribution in a larger catalog.'}, 'classifiers': {'type': 'array', 'items': {'type': 'string', 'format': 'trove-classifier', 'description': '`PyPI classifier `_.'}, '$$description': ['`Trove classifiers `_', 'which apply to the project.']}, 'urls': {'type': 'object', 'description': 'URLs associated with the project in the form ``label => value``.', 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', 'format': 'url'}}}, 'scripts': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'gui-scripts': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'entry-points': {'$$description': ['Instruct the installer to expose the given modules/functions via', '``entry-point`` discovery mechanism (useful for plugins).', 'More information available in the `Python packaging guide', '`_.'], 'propertyNames': {'format': 'python-entrypoint-group'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}}}, 'dependencies': {'type': 'array', 'description': 'Project (mandatory) dependencies.', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}, 'optional-dependencies': {'type': 'object', 'description': 'Optional dependency for the project', 'propertyNames': {'format': 'pep508-identifier'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'array', 'items': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}}, 'dynamic': {'type': 'array', '$$description': ['Specifies which fields are intentionally unspecified and expected to be', 'dynamically provided by build tools'], 'items': {'enum': ['version', 'description', 'readme', 'requires-python', 'license', 'license-files', 'authors', 'maintainers', 'keywords', 'classifiers', 'urls', 'scripts', 'gui-scripts', 'entry-points', 'dependencies', 'optional-dependencies']}}}, 'required': ['name'], 'additionalProperties': False, 'allOf': [{'if': {'not': {'required': ['dynamic'], 'properties': {'dynamic': {'contains': {'const': 'version'}, '$$description': ['version is listed in ``dynamic``']}}}, '$$comment': ['According to :pep:`621`:', '    If the core metadata specification lists a field as "Required", then', '    the metadata MUST specify the field statically or list it in dynamic', 'In turn, `core metadata`_ defines:', '    The required fields are: Metadata-Version, Name, Version.', '    All the other fields are optional.', 'Since ``Metadata-Version`` is defined by the build back-end, ``name`` and', '``version`` are the only mandatory information in ``pyproject.toml``.', '.. _core metadata: https://packaging.python.org/specifications/core-metadata/']}, 'then': {'required': ['version'], '$$description': ['version should be statically defined in the ``version`` field']}}, {'if': {'required': ['license-files']}, 'then': {'properties': {'license': {'type': 'string'}}}}], 'definitions': {'author': {'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, 'entry-point-group': {'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, 'dependency': {'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}}}, rule='additionalProperties')
-    return data
-
-def validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_dependency(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (str)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be string", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}, rule='type')
-    if isinstance(data, str):
-        if not custom_formats["pep508"](data):
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must be pep508", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/dependency', 'title': 'Dependency', 'type': 'string', 'description': 'Project dependency specification according to PEP 508', 'format': 'pep508'}, rule='format')
-    return data
-
-def validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_entry_point_group(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data_keys = set(data.keys())
-        for data_key, data_val in data.items():
-            if REGEX_PATTERNS['^.+$'].search(data_key):
-                if data_key in data_keys:
-                    data_keys.remove(data_key)
-                if not isinstance(data_val, (str)):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".{data_key}".format(**locals()) + " must be string", value=data_val, name="" + (name_prefix or "data") + ".{data_key}".format(**locals()) + "", definition={'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}, rule='type')
-                if isinstance(data_val, str):
-                    if not custom_formats["python-entrypoint-reference"](data_val):
-                        raise JsonSchemaValueException("" + (name_prefix or "data") + ".{data_key}".format(**locals()) + " must be python-entrypoint-reference", value=data_val, name="" + (name_prefix or "data") + ".{data_key}".format(**locals()) + "", definition={'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}, rule='format')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, rule='additionalProperties')
-        data_len = len(data)
-        if data_len != 0:
-            data_property_names = True
-            for data_key in data:
-                try:
-                    if isinstance(data_key, str):
-                        if not custom_formats["python-entrypoint-name"](data_key):
-                            raise JsonSchemaValueException("" + (name_prefix or "data") + " must be python-entrypoint-name", value=data_key, name="" + (name_prefix or "data") + "", definition={'format': 'python-entrypoint-name'}, rule='format')
-                except JsonSchemaValueException:
-                    data_property_names = False
-            if not data_property_names:
-                raise JsonSchemaValueException("" + (name_prefix or "data") + " must be named by propertyName definition", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/entry-point-group', 'title': 'Entry-points', 'type': 'object', '$$description': ['Entry-points are grouped together to indicate what sort of capabilities they', 'provide.', 'See the `packaging guides', '`_', 'and `setuptools docs', '`_', 'for more information.'], 'propertyNames': {'format': 'python-entrypoint-name'}, 'additionalProperties': False, 'patternProperties': {'^.+$': {'type': 'string', '$$description': ['Reference to a Python object. It is either in the form', '``importable.module``, or ``importable.module:object.attr``.'], 'format': 'python-entrypoint-reference', '$comment': 'https://packaging.python.org/specifications/entry-points/'}}}, rule='propertyNames')
-    return data
-
-def validate_https___packaging_python_org_en_latest_specifications_pyproject_toml___definitions_author(data, custom_formats={}, name_prefix=None):
-    if not isinstance(data, (dict)):
-        raise JsonSchemaValueException("" + (name_prefix or "data") + " must be object", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, rule='type')
-    data_is_dict = isinstance(data, dict)
-    if data_is_dict:
-        data_keys = set(data.keys())
-        if "name" in data_keys:
-            data_keys.remove("name")
-            data__name = data["name"]
-            if not isinstance(data__name, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".name must be string", value=data__name, name="" + (name_prefix or "data") + ".name", definition={'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, rule='type')
-        if "email" in data_keys:
-            data_keys.remove("email")
-            data__email = data["email"]
-            if not isinstance(data__email, (str)):
-                raise JsonSchemaValueException("" + (name_prefix or "data") + ".email must be string", value=data__email, name="" + (name_prefix or "data") + ".email", definition={'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}, rule='type')
-            if isinstance(data__email, str):
-                if not REGEX_PATTERNS["idn-email_re_pattern"].match(data__email):
-                    raise JsonSchemaValueException("" + (name_prefix or "data") + ".email must be idn-email", value=data__email, name="" + (name_prefix or "data") + ".email", definition={'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}, rule='format')
-        if data_keys:
-            raise JsonSchemaValueException("" + (name_prefix or "data") + " must not contain "+str(data_keys)+" properties", value=data, name="" + (name_prefix or "data") + "", definition={'$id': '#/definitions/author', 'title': 'Author or Maintainer', '$comment': 'https://peps.python.org/pep-0621/#authors-maintainers', 'type': 'object', 'additionalProperties': False, 'properties': {'name': {'type': 'string', '$$description': ['MUST be a valid email name, i.e. whatever can be put as a name, before an', 'email, in :rfc:`822`.']}, 'email': {'type': 'string', 'format': 'idn-email', 'description': 'MUST be a valid email address'}}}, rule='additionalProperties')
-    return data
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/formats.py b/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/formats.py
deleted file mode 100644
index 1cf4a46..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/_validate_pyproject/formats.py
+++ /dev/null
@@ -1,402 +0,0 @@
-"""
-The functions in this module are used to validate schemas with the
-`format JSON Schema keyword
-`_.
-
-The correspondence is given by replacing the ``_`` character in the name of the
-function with a ``-`` to obtain the format name and vice versa.
-"""
-
-import builtins
-import logging
-import os
-import re
-import string
-import typing
-from itertools import chain as _chain
-
-if typing.TYPE_CHECKING:
-    from typing_extensions import Literal
-
-_logger = logging.getLogger(__name__)
-
-# -------------------------------------------------------------------------------------
-# PEP 440
-
-VERSION_PATTERN = r"""
-    v?
-    (?:
-        (?:(?P[0-9]+)!)?                           # epoch
-        (?P[0-9]+(?:\.[0-9]+)*)                  # release segment
-        (?P
                                          # pre-release
-            [-_\.]?
-            (?Palpha|a|beta|b|preview|pre|c|rc)
-            [-_\.]?
-            (?P[0-9]+)?
-        )?
-        (?P                                         # post release
-            (?:-(?P[0-9]+))
-            |
-            (?:
-                [-_\.]?
-                (?Ppost|rev|r)
-                [-_\.]?
-                (?P[0-9]+)?
-            )
-        )?
-        (?P                                          # dev release
-            [-_\.]?
-            (?Pdev)
-            [-_\.]?
-            (?P[0-9]+)?
-        )?
-    )
-    (?:\+(?P[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
-"""
-
-VERSION_REGEX = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.X | re.I)
-
-
-def pep440(version: str) -> bool:
-    """See :ref:`PyPA's version specification `
-    (initially introduced in :pep:`440`).
-    """
-    return VERSION_REGEX.match(version) is not None
-
-
-# -------------------------------------------------------------------------------------
-# PEP 508
-
-PEP508_IDENTIFIER_PATTERN = r"([A-Z0-9]|[A-Z0-9][A-Z0-9._-]*[A-Z0-9])"
-PEP508_IDENTIFIER_REGEX = re.compile(f"^{PEP508_IDENTIFIER_PATTERN}$", re.I)
-
-
-def pep508_identifier(name: str) -> bool:
-    """See :ref:`PyPA's name specification `
-    (initially introduced in :pep:`508#names`).
-    """
-    return PEP508_IDENTIFIER_REGEX.match(name) is not None
-
-
-try:
-    try:
-        from packaging import requirements as _req
-    except ImportError:  # pragma: no cover
-        # let's try setuptools vendored version
-        from setuptools._vendor.packaging import (  # type: ignore[no-redef]
-            requirements as _req,
-        )
-
-    def pep508(value: str) -> bool:
-        """See :ref:`PyPA's dependency specifiers `
-        (initially introduced in :pep:`508`).
-        """
-        try:
-            _req.Requirement(value)
-            return True
-        except _req.InvalidRequirement:
-            return False
-
-except ImportError:  # pragma: no cover
-    _logger.warning(
-        "Could not find an installation of `packaging`. Requirements, dependencies and "
-        "versions might not be validated. "
-        "To enforce validation, please install `packaging`."
-    )
-
-    def pep508(value: str) -> bool:
-        return True
-
-
-def pep508_versionspec(value: str) -> bool:
-    """Expression that can be used to specify/lock versions (including ranges)
-    See ``versionspec`` in :ref:`PyPA's dependency specifiers
-    ` (initially introduced in :pep:`508`).
-    """
-    if any(c in value for c in (";", "]", "@")):
-        # In PEP 508:
-        # conditional markers, extras and URL specs are not included in the
-        # versionspec
-        return False
-    # Let's pretend we have a dependency called `requirement` with the given
-    # version spec, then we can reuse the pep508 function for validation:
-    return pep508(f"requirement{value}")
-
-
-# -------------------------------------------------------------------------------------
-# PEP 517
-
-
-def pep517_backend_reference(value: str) -> bool:
-    """See PyPA's specification for defining build-backend references
-    introduced in :pep:`517#source-trees`.
-
-    This is similar to an entry-point reference (e.g., ``package.module:object``).
-    """
-    module, _, obj = value.partition(":")
-    identifiers = (i.strip() for i in _chain(module.split("."), obj.split(".")))
-    return all(python_identifier(i) for i in identifiers if i)
-
-
-# -------------------------------------------------------------------------------------
-# Classifiers - PEP 301
-
-
-def _download_classifiers() -> str:
-    import ssl
-    from email.message import Message
-    from urllib.request import urlopen
-
-    url = "https://pypi.org/pypi?:action=list_classifiers"
-    context = ssl.create_default_context()
-    with urlopen(url, context=context) as response:  # noqa: S310 (audit URLs)
-        headers = Message()
-        headers["content_type"] = response.getheader("content-type", "text/plain")
-        return response.read().decode(headers.get_param("charset", "utf-8"))  # type: ignore[no-any-return]
-
-
-class _TroveClassifier:
-    """The ``trove_classifiers`` package is the official way of validating classifiers,
-    however this package might not be always available.
-    As a workaround we can still download a list from PyPI.
-    We also don't want to be over strict about it, so simply skipping silently is an
-    option (classifiers will be validated anyway during the upload to PyPI).
-    """
-
-    downloaded: typing.Union[None, "Literal[False]", typing.Set[str]]
-    """
-    None => not cached yet
-    False => unavailable
-    set => cached values
-    """
-
-    def __init__(self) -> None:
-        self.downloaded = None
-        self._skip_download = False
-        self.__name__ = "trove_classifier"  # Emulate a public function
-
-    def _disable_download(self) -> None:
-        # This is a private API. Only setuptools has the consent of using it.
-        self._skip_download = True
-
-    def __call__(self, value: str) -> bool:
-        if self.downloaded is False or self._skip_download is True:
-            return True
-
-        if os.getenv("NO_NETWORK") or os.getenv("VALIDATE_PYPROJECT_NO_NETWORK"):
-            self.downloaded = False
-            msg = (
-                "Install ``trove-classifiers`` to ensure proper validation. "
-                "Skipping download of classifiers list from PyPI (NO_NETWORK)."
-            )
-            _logger.debug(msg)
-            return True
-
-        if self.downloaded is None:
-            msg = (
-                "Install ``trove-classifiers`` to ensure proper validation. "
-                "Meanwhile a list of classifiers will be downloaded from PyPI."
-            )
-            _logger.debug(msg)
-            try:
-                self.downloaded = set(_download_classifiers().splitlines())
-            except Exception:
-                self.downloaded = False
-                _logger.debug("Problem with download, skipping validation")
-                return True
-
-        return value in self.downloaded or value.lower().startswith("private ::")
-
-
-try:
-    from trove_classifiers import classifiers as _trove_classifiers
-
-    def trove_classifier(value: str) -> bool:
-        """See https://pypi.org/classifiers/"""
-        return value in _trove_classifiers or value.lower().startswith("private ::")
-
-except ImportError:  # pragma: no cover
-    trove_classifier = _TroveClassifier()
-
-
-# -------------------------------------------------------------------------------------
-# Stub packages - PEP 561
-
-
-def pep561_stub_name(value: str) -> bool:
-    """Name of a directory containing type stubs.
-    It must follow the name scheme ``-stubs`` as defined in
-    :pep:`561#stub-only-packages`.
-    """
-    top, *children = value.split(".")
-    if not top.endswith("-stubs"):
-        return False
-    return python_module_name(".".join([top[: -len("-stubs")], *children]))
-
-
-# -------------------------------------------------------------------------------------
-# Non-PEP related
-
-
-def url(value: str) -> bool:
-    """Valid URL (validation uses :obj:`urllib.parse`).
-    For maximum compatibility please make sure to include a ``scheme`` prefix
-    in your URL (e.g. ``http://``).
-    """
-    from urllib.parse import urlparse
-
-    try:
-        parts = urlparse(value)
-        if not parts.scheme:
-            _logger.warning(
-                "For maximum compatibility please make sure to include a "
-                "`scheme` prefix in your URL (e.g. 'http://'). "
-                f"Given value: {value}"
-            )
-            if not (value.startswith("/") or value.startswith("\\") or "@" in value):
-                parts = urlparse(f"http://{value}")
-
-        return bool(parts.scheme and parts.netloc)
-    except Exception:
-        return False
-
-
-# https://packaging.python.org/specifications/entry-points/
-ENTRYPOINT_PATTERN = r"[^\[\s=]([^=]*[^\s=])?"
-ENTRYPOINT_REGEX = re.compile(f"^{ENTRYPOINT_PATTERN}$", re.I)
-RECOMMEDED_ENTRYPOINT_PATTERN = r"[\w.-]+"
-RECOMMEDED_ENTRYPOINT_REGEX = re.compile(f"^{RECOMMEDED_ENTRYPOINT_PATTERN}$", re.I)
-ENTRYPOINT_GROUP_PATTERN = r"\w+(\.\w+)*"
-ENTRYPOINT_GROUP_REGEX = re.compile(f"^{ENTRYPOINT_GROUP_PATTERN}$", re.I)
-
-
-def python_identifier(value: str) -> bool:
-    """Can be used as identifier in Python.
-    (Validation uses :obj:`str.isidentifier`).
-    """
-    return value.isidentifier()
-
-
-def python_qualified_identifier(value: str) -> bool:
-    """
-    Python "dotted identifier", i.e. a sequence of :obj:`python_identifier`
-    concatenated with ``"."`` (e.g.: ``package.module.submodule``).
-    """
-    if value.startswith(".") or value.endswith("."):
-        return False
-    return all(python_identifier(m) for m in value.split("."))
-
-
-def python_module_name(value: str) -> bool:
-    """Module name that can be used in an ``import``-statement in Python.
-    See :obj:`python_qualified_identifier`.
-    """
-    return python_qualified_identifier(value)
-
-
-def python_module_name_relaxed(value: str) -> bool:
-    """Similar to :obj:`python_module_name`, but relaxed to also accept
-    dash characters (``-``) and cover special cases like ``pip-run``.
-
-    It is recommended, however, that beginners avoid dash characters,
-    as they require advanced knowledge about Python internals.
-
-    The following are disallowed:
-
-    * names starting/ending in dashes,
-    * names ending in ``-stubs`` (potentially collide with :obj:`pep561_stub_name`).
-    """
-    if value.startswith("-") or value.endswith("-"):
-        return False
-    if value.endswith("-stubs"):
-        return False  # Avoid collision with PEP 561
-    return python_module_name(value.replace("-", "_"))
-
-
-def python_entrypoint_group(value: str) -> bool:
-    """See ``Data model > group`` in the :ref:`PyPA's entry-points specification
-    `.
-    """
-    return ENTRYPOINT_GROUP_REGEX.match(value) is not None
-
-
-def python_entrypoint_name(value: str) -> bool:
-    """See ``Data model > name`` in the :ref:`PyPA's entry-points specification
-    `.
-    """
-    if not ENTRYPOINT_REGEX.match(value):
-        return False
-    if not RECOMMEDED_ENTRYPOINT_REGEX.match(value):
-        msg = f"Entry point `{value}` does not follow recommended pattern: "
-        msg += RECOMMEDED_ENTRYPOINT_PATTERN
-        _logger.warning(msg)
-    return True
-
-
-def python_entrypoint_reference(value: str) -> bool:
-    """Reference to a Python object using in the format::
-
-        importable.module:object.attr
-
-    See ``Data model >object reference`` in the :ref:`PyPA's entry-points specification
-    `.
-    """
-    module, _, rest = value.partition(":")
-    if "[" in rest:
-        obj, _, extras_ = rest.partition("[")
-        if extras_.strip()[-1] != "]":
-            return False
-        extras = (x.strip() for x in extras_.strip(string.whitespace + "[]").split(","))
-        if not all(pep508_identifier(e) for e in extras):
-            return False
-        _logger.warning(f"`{value}` - using extras for entry points is not recommended")
-    else:
-        obj = rest
-
-    module_parts = module.split(".")
-    identifiers = _chain(module_parts, obj.split(".")) if rest else iter(module_parts)
-    return all(python_identifier(i.strip()) for i in identifiers)
-
-
-def uint8(value: builtins.int) -> bool:
-    r"""Unsigned 8-bit integer (:math:`0 \leq x < 2^8`)"""
-    return 0 <= value < 2**8
-
-
-def uint16(value: builtins.int) -> bool:
-    r"""Unsigned 16-bit integer (:math:`0 \leq x < 2^{16}`)"""
-    return 0 <= value < 2**16
-
-
-def uint(value: builtins.int) -> bool:
-    r"""Unsigned 64-bit integer (:math:`0 \leq x < 2^{64}`)"""
-    return 0 <= value < 2**64
-
-
-def int(value: builtins.int) -> bool:
-    r"""Signed 64-bit integer (:math:`-2^{63} \leq x < 2^{63}`)"""
-    return -(2**63) <= value < 2**63
-
-
-try:
-    from packaging import licenses as _licenses
-
-    def SPDX(value: str) -> bool:
-        """See :ref:`PyPA's License-Expression specification
-        ` (added in :pep:`639`).
-        """
-        try:
-            _licenses.canonicalize_license_expression(value)
-            return True
-        except _licenses.InvalidLicenseExpression:
-            return False
-
-except ImportError:  # pragma: no cover
-    _logger.warning(
-        "Could not find an up-to-date installation of `packaging`. "
-        "License expressions might not be validated. "
-        "To enforce validation, please install `packaging>=24.2`."
-    )
-
-    def SPDX(value: str) -> bool:
-        return True
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/distutils.schema.json b/llmlab/lib/python3.12/site-packages/setuptools/config/distutils.schema.json
deleted file mode 100644
index 93cd2e8..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/distutils.schema.json
+++ /dev/null
@@ -1,26 +0,0 @@
-{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-
-  "$id": "https://setuptools.pypa.io/en/latest/deprecated/distutils/configfile.html",
-  "title": "``tool.distutils`` table",
-  "$$description": [
-    "**EXPERIMENTAL** (NOT OFFICIALLY SUPPORTED): Use ``tool.distutils``",
-    "subtables to configure arguments for ``distutils`` commands.",
-    "Originally, ``distutils`` allowed developers to configure arguments for",
-    "``setup.py`` commands via `distutils configuration files",
-    "`_.",
-    "See also `the old Python docs _`."
-  ],
-
-  "type": "object",
-  "properties": {
-    "global": {
-      "type": "object",
-      "description": "Global options applied to all ``distutils`` commands"
-    }
-  },
-  "patternProperties": {
-    ".+": {"type": "object"}
-  },
-  "$comment": "TODO: Is there a practical way of making this schema more specific?"
-}
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/expand.py b/llmlab/lib/python3.12/site-packages/setuptools/config/expand.py
deleted file mode 100644
index 531f965..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/expand.py
+++ /dev/null
@@ -1,452 +0,0 @@
-"""Utility functions to expand configuration directives or special values
-(such glob patterns).
-
-We can split the process of interpreting configuration files into 2 steps:
-
-1. The parsing the file contents from strings to value objects
-   that can be understand by Python (for example a string with a comma
-   separated list of keywords into an actual Python list of strings).
-
-2. The expansion (or post-processing) of these values according to the
-   semantics ``setuptools`` assign to them (for example a configuration field
-   with the ``file:`` directive should be expanded from a list of file paths to
-   a single string with the contents of those files concatenated)
-
-This module focus on the second step, and therefore allow sharing the expansion
-functions among several configuration file formats.
-
-**PRIVATE MODULE**: API reserved for setuptools internal usage only.
-"""
-
-from __future__ import annotations
-
-import ast
-import importlib
-import os
-import pathlib
-import sys
-from collections.abc import Iterable, Iterator, Mapping
-from configparser import ConfigParser
-from glob import iglob
-from importlib.machinery import ModuleSpec, all_suffixes
-from itertools import chain
-from pathlib import Path
-from types import ModuleType, TracebackType
-from typing import TYPE_CHECKING, Any, Callable, TypeVar
-
-from .. import _static
-from .._path import StrPath, same_path as _same_path
-from ..discovery import find_package_path
-from ..warnings import SetuptoolsWarning
-
-from distutils.errors import DistutilsOptionError
-
-if TYPE_CHECKING:
-    from typing_extensions import Self
-
-    from setuptools.dist import Distribution
-
-_K = TypeVar("_K")
-_V_co = TypeVar("_V_co", covariant=True)
-
-
-class StaticModule:
-    """Proxy to a module object that avoids executing arbitrary code."""
-
-    def __init__(self, name: str, spec: ModuleSpec) -> None:
-        module = ast.parse(pathlib.Path(spec.origin).read_bytes())  # type: ignore[arg-type] # Let it raise an error on None
-        vars(self).update(locals())
-        del self.self
-
-    def _find_assignments(self) -> Iterator[tuple[ast.AST, ast.AST]]:
-        for statement in self.module.body:
-            if isinstance(statement, ast.Assign):
-                yield from ((target, statement.value) for target in statement.targets)
-            elif isinstance(statement, ast.AnnAssign) and statement.value:
-                yield (statement.target, statement.value)
-
-    def __getattr__(self, attr: str):
-        """Attempt to load an attribute "statically", via :func:`ast.literal_eval`."""
-        try:
-            return next(
-                ast.literal_eval(value)
-                for target, value in self._find_assignments()
-                if isinstance(target, ast.Name) and target.id == attr
-            )
-        except Exception as e:
-            raise AttributeError(f"{self.name} has no attribute {attr}") from e
-
-
-def glob_relative(
-    patterns: Iterable[str], root_dir: StrPath | None = None
-) -> list[str]:
-    """Expand the list of glob patterns, but preserving relative paths.
-
-    :param list[str] patterns: List of glob patterns
-    :param str root_dir: Path to which globs should be relative
-                         (current directory by default)
-    :rtype: list
-    """
-    glob_characters = {'*', '?', '[', ']', '{', '}'}
-    expanded_values = []
-    root_dir = root_dir or os.getcwd()
-    for value in patterns:
-        # Has globby characters?
-        if any(char in value for char in glob_characters):
-            # then expand the glob pattern while keeping paths *relative*:
-            glob_path = os.path.abspath(os.path.join(root_dir, value))
-            expanded_values.extend(
-                sorted(
-                    os.path.relpath(path, root_dir).replace(os.sep, "/")
-                    for path in iglob(glob_path, recursive=True)
-                )
-            )
-
-        else:
-            # take the value as-is
-            path = os.path.relpath(value, root_dir).replace(os.sep, "/")
-            expanded_values.append(path)
-
-    return expanded_values
-
-
-def read_files(
-    filepaths: StrPath | Iterable[StrPath], root_dir: StrPath | None = None
-) -> str:
-    """Return the content of the files concatenated using ``\n`` as str
-
-    This function is sandboxed and won't reach anything outside ``root_dir``
-
-    (By default ``root_dir`` is the current directory).
-    """
-    from more_itertools import always_iterable
-
-    root_dir = os.path.abspath(root_dir or os.getcwd())
-    _filepaths = (os.path.join(root_dir, path) for path in always_iterable(filepaths))
-    return '\n'.join(
-        _read_file(path)
-        for path in _filter_existing_files(_filepaths)
-        if _assert_local(path, root_dir)
-    )
-
-
-def _filter_existing_files(filepaths: Iterable[StrPath]) -> Iterator[StrPath]:
-    for path in filepaths:
-        if os.path.isfile(path):
-            yield path
-        else:
-            SetuptoolsWarning.emit(f"File {path!r} cannot be found")
-
-
-def _read_file(filepath: bytes | StrPath) -> str:
-    with open(filepath, encoding='utf-8') as f:
-        return f.read()
-
-
-def _assert_local(filepath: StrPath, root_dir: str):
-    if Path(os.path.abspath(root_dir)) not in Path(os.path.abspath(filepath)).parents:
-        msg = f"Cannot access {filepath!r} (or anything outside {root_dir!r})"
-        raise DistutilsOptionError(msg)
-
-    return True
-
-
-def read_attr(
-    attr_desc: str,
-    package_dir: Mapping[str, str] | None = None,
-    root_dir: StrPath | None = None,
-) -> Any:
-    """Reads the value of an attribute from a module.
-
-    This function will try to read the attributed statically first
-    (via :func:`ast.literal_eval`), and only evaluate the module if it fails.
-
-    Examples:
-        read_attr("package.attr")
-        read_attr("package.module.attr")
-
-    :param str attr_desc: Dot-separated string describing how to reach the
-        attribute (see examples above)
-    :param dict[str, str] package_dir: Mapping of package names to their
-        location in disk (represented by paths relative to ``root_dir``).
-    :param str root_dir: Path to directory containing all the packages in
-        ``package_dir`` (current directory by default).
-    :rtype: str
-    """
-    root_dir = root_dir or os.getcwd()
-    attrs_path = attr_desc.strip().split('.')
-    attr_name = attrs_path.pop()
-    module_name = '.'.join(attrs_path)
-    module_name = module_name or '__init__'
-    path = _find_module(module_name, package_dir, root_dir)
-    spec = _find_spec(module_name, path)
-
-    try:
-        value = getattr(StaticModule(module_name, spec), attr_name)
-        # XXX: Is marking as static contents coming from modules too optimistic?
-        return _static.attempt_conversion(value)
-    except Exception:
-        # fallback to evaluate module
-        module = _load_spec(spec, module_name)
-        return getattr(module, attr_name)
-
-
-def _find_spec(module_name: str, module_path: StrPath | None) -> ModuleSpec:
-    spec = importlib.util.spec_from_file_location(module_name, module_path)
-    spec = spec or importlib.util.find_spec(module_name)
-
-    if spec is None:
-        raise ModuleNotFoundError(module_name)
-
-    return spec
-
-
-def _load_spec(spec: ModuleSpec, module_name: str) -> ModuleType:
-    name = getattr(spec, "__name__", module_name)
-    if name in sys.modules:
-        return sys.modules[name]
-    module = importlib.util.module_from_spec(spec)
-    sys.modules[name] = module  # cache (it also ensures `==` works on loaded items)
-    assert spec.loader is not None
-    spec.loader.exec_module(module)
-    return module
-
-
-def _find_module(
-    module_name: str, package_dir: Mapping[str, str] | None, root_dir: StrPath
-) -> str | None:
-    """Find the path to the module named ``module_name``,
-    considering the ``package_dir`` in the build configuration and ``root_dir``.
-
-    >>> tmp = getfixture('tmpdir')
-    >>> _ = tmp.ensure("a/b/c.py")
-    >>> _ = tmp.ensure("a/b/d/__init__.py")
-    >>> r = lambda x: x.replace(str(tmp), "tmp").replace(os.sep, "/")
-    >>> r(_find_module("a.b.c", None, tmp))
-    'tmp/a/b/c.py'
-    >>> r(_find_module("f.g.h", {"": "1", "f": "2", "f.g": "3", "f.g.h": "a/b/d"}, tmp))
-    'tmp/a/b/d/__init__.py'
-    """
-    path_start = find_package_path(module_name, package_dir or {}, root_dir)
-    candidates = chain.from_iterable(
-        (f"{path_start}{ext}", os.path.join(path_start, f"__init__{ext}"))
-        for ext in all_suffixes()
-    )
-    return next((x for x in candidates if os.path.isfile(x)), None)
-
-
-def resolve_class(
-    qualified_class_name: str,
-    package_dir: Mapping[str, str] | None = None,
-    root_dir: StrPath | None = None,
-) -> Callable:
-    """Given a qualified class name, return the associated class object"""
-    root_dir = root_dir or os.getcwd()
-    idx = qualified_class_name.rfind('.')
-    class_name = qualified_class_name[idx + 1 :]
-    pkg_name = qualified_class_name[:idx]
-
-    path = _find_module(pkg_name, package_dir, root_dir)
-    module = _load_spec(_find_spec(pkg_name, path), pkg_name)
-    return getattr(module, class_name)
-
-
-def cmdclass(
-    values: dict[str, str],
-    package_dir: Mapping[str, str] | None = None,
-    root_dir: StrPath | None = None,
-) -> dict[str, Callable]:
-    """Given a dictionary mapping command names to strings for qualified class
-    names, apply :func:`resolve_class` to the dict values.
-    """
-    return {k: resolve_class(v, package_dir, root_dir) for k, v in values.items()}
-
-
-def find_packages(
-    *,
-    namespaces=True,
-    fill_package_dir: dict[str, str] | None = None,
-    root_dir: StrPath | None = None,
-    **kwargs,
-) -> list[str]:
-    """Works similarly to :func:`setuptools.find_packages`, but with all
-    arguments given as keyword arguments. Moreover, ``where`` can be given
-    as a list (the results will be simply concatenated).
-
-    When the additional keyword argument ``namespaces`` is ``True``, it will
-    behave like :func:`setuptools.find_namespace_packages`` (i.e. include
-    implicit namespaces as per :pep:`420`).
-
-    The ``where`` argument will be considered relative to ``root_dir`` (or the current
-    working directory when ``root_dir`` is not given).
-
-    If the ``fill_package_dir`` argument is passed, this function will consider it as a
-    similar data structure to the ``package_dir`` configuration parameter add fill-in
-    any missing package location.
-
-    :rtype: list
-    """
-    from more_itertools import always_iterable, unique_everseen
-
-    from setuptools.discovery import construct_package_dir
-
-    # check "not namespaces" first due to python/mypy#6232
-    if not namespaces:
-        from setuptools.discovery import PackageFinder
-    else:
-        from setuptools.discovery import PEP420PackageFinder as PackageFinder
-
-    root_dir = root_dir or os.curdir
-    where = kwargs.pop('where', ['.'])
-    packages: list[str] = []
-    fill_package_dir = {} if fill_package_dir is None else fill_package_dir
-    search = list(unique_everseen(always_iterable(where)))
-
-    if len(search) == 1 and all(not _same_path(search[0], x) for x in (".", root_dir)):
-        fill_package_dir.setdefault("", search[0])
-
-    for path in search:
-        package_path = _nest_path(root_dir, path)
-        pkgs = PackageFinder.find(package_path, **kwargs)
-        packages.extend(pkgs)
-        if pkgs and not (
-            fill_package_dir.get("") == path or os.path.samefile(package_path, root_dir)
-        ):
-            fill_package_dir.update(construct_package_dir(pkgs, path))
-
-    return packages
-
-
-def _nest_path(parent: StrPath, path: StrPath) -> str:
-    path = parent if path in {".", ""} else os.path.join(parent, path)
-    return os.path.normpath(path)
-
-
-def version(value: Callable | Iterable[str | int] | str) -> str:
-    """When getting the version directly from an attribute,
-    it should be normalised to string.
-    """
-    _value = value() if callable(value) else value
-
-    if isinstance(_value, str):
-        return _value
-    if hasattr(_value, '__iter__'):
-        return '.'.join(map(str, _value))
-    return f'{_value}'
-
-
-def canonic_package_data(package_data: dict) -> dict:
-    if "*" in package_data:
-        package_data[""] = package_data.pop("*")
-    return package_data
-
-
-def canonic_data_files(
-    data_files: list | dict, root_dir: StrPath | None = None
-) -> list[tuple[str, list[str]]]:
-    """For compatibility with ``setup.py``, ``data_files`` should be a list
-    of pairs instead of a dict.
-
-    This function also expands glob patterns.
-    """
-    if isinstance(data_files, list):
-        return data_files
-
-    return [
-        (dest, glob_relative(patterns, root_dir))
-        for dest, patterns in data_files.items()
-    ]
-
-
-def entry_points(
-    text: str, text_source: str = "entry-points"
-) -> dict[str, dict[str, str]]:
-    """Given the contents of entry-points file,
-    process it into a 2-level dictionary (``dict[str, dict[str, str]]``).
-    The first level keys are entry-point groups, the second level keys are
-    entry-point names, and the second level values are references to objects
-    (that correspond to the entry-point value).
-    """
-    # Using undocumented behaviour, see python/typeshed#12700
-    parser = ConfigParser(default_section=None, delimiters=("=",))  # type: ignore[call-overload]
-    parser.optionxform = str  # case sensitive
-    parser.read_string(text, text_source)
-    groups = {k: dict(v.items()) for k, v in parser.items()}
-    groups.pop(parser.default_section, None)
-    return groups
-
-
-class EnsurePackagesDiscovered:
-    """Some expand functions require all the packages to already be discovered before
-    they run, e.g. :func:`read_attr`, :func:`resolve_class`, :func:`cmdclass`.
-
-    Therefore in some cases we will need to run autodiscovery during the evaluation of
-    the configuration. However, it is better to postpone calling package discovery as
-    much as possible, because some parameters can influence it (e.g. ``package_dir``),
-    and those might not have been processed yet.
-    """
-
-    def __init__(self, distribution: Distribution) -> None:
-        self._dist = distribution
-        self._called = False
-
-    def __call__(self):
-        """Trigger the automatic package discovery, if it is still necessary."""
-        if not self._called:
-            self._called = True
-            self._dist.set_defaults(name=False)  # Skip name, we can still be parsing
-
-    def __enter__(self) -> Self:
-        return self
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_value: BaseException | None,
-        traceback: TracebackType | None,
-    ):
-        if self._called:
-            self._dist.set_defaults.analyse_name()  # Now we can set a default name
-
-    def _get_package_dir(self) -> Mapping[str, str]:
-        self()
-        pkg_dir = self._dist.package_dir
-        return {} if pkg_dir is None else pkg_dir
-
-    @property
-    def package_dir(self) -> Mapping[str, str]:
-        """Proxy to ``package_dir`` that may trigger auto-discovery when used."""
-        return LazyMappingProxy(self._get_package_dir)
-
-
-class LazyMappingProxy(Mapping[_K, _V_co]):
-    """Mapping proxy that delays resolving the target object, until really needed.
-
-    >>> def obtain_mapping():
-    ...     print("Running expensive function!")
-    ...     return {"key": "value", "other key": "other value"}
-    >>> mapping = LazyMappingProxy(obtain_mapping)
-    >>> mapping["key"]
-    Running expensive function!
-    'value'
-    >>> mapping["other key"]
-    'other value'
-    """
-
-    def __init__(self, obtain_mapping_value: Callable[[], Mapping[_K, _V_co]]) -> None:
-        self._obtain = obtain_mapping_value
-        self._value: Mapping[_K, _V_co] | None = None
-
-    def _target(self) -> Mapping[_K, _V_co]:
-        if self._value is None:
-            self._value = self._obtain()
-        return self._value
-
-    def __getitem__(self, key: _K) -> _V_co:
-        return self._target()[key]
-
-    def __len__(self) -> int:
-        return len(self._target())
-
-    def __iter__(self) -> Iterator[_K]:
-        return iter(self._target())
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/pyprojecttoml.py b/llmlab/lib/python3.12/site-packages/setuptools/config/pyprojecttoml.py
deleted file mode 100644
index fd6c596..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/pyprojecttoml.py
+++ /dev/null
@@ -1,468 +0,0 @@
-"""
-Load setuptools configuration from ``pyproject.toml`` files.
-
-**PRIVATE MODULE**: API reserved for setuptools internal usage only.
-
-To read project metadata, consider using
-``build.util.project_wheel_metadata`` (https://pypi.org/project/build/).
-For simple scenarios, you can also try parsing the file directly
-with the help of ``tomllib`` or ``tomli``.
-"""
-
-from __future__ import annotations
-
-import logging
-import os
-from collections.abc import Mapping
-from contextlib import contextmanager
-from functools import partial
-from types import TracebackType
-from typing import TYPE_CHECKING, Any, Callable
-
-from .._path import StrPath
-from ..errors import FileError, InvalidConfigError
-from ..warnings import SetuptoolsWarning
-from . import expand as _expand
-from ._apply_pyprojecttoml import _PREVIOUSLY_DEFINED, _MissingDynamic, apply as _apply
-
-if TYPE_CHECKING:
-    from typing_extensions import Self
-
-    from setuptools.dist import Distribution
-
-_logger = logging.getLogger(__name__)
-
-
-def load_file(filepath: StrPath) -> dict:
-    from ..compat.py310 import tomllib
-
-    with open(filepath, "rb") as file:
-        return tomllib.load(file)
-
-
-def validate(config: dict, filepath: StrPath) -> bool:
-    from . import _validate_pyproject as validator
-
-    trove_classifier = validator.FORMAT_FUNCTIONS.get("trove-classifier")
-    if hasattr(trove_classifier, "_disable_download"):
-        # Improve reproducibility by default. See abravalheri/validate-pyproject#31
-        trove_classifier._disable_download()  # type: ignore[union-attr]
-
-    try:
-        return validator.validate(config)
-    except validator.ValidationError as ex:
-        summary = f"configuration error: {ex.summary}"
-        if ex.name.strip("`") != "project":
-            # Probably it is just a field missing/misnamed, not worthy the verbosity...
-            _logger.debug(summary)
-            _logger.debug(ex.details)
-
-        error = f"invalid pyproject.toml config: {ex.name}."
-        raise ValueError(f"{error}\n{summary}") from None
-
-
-def apply_configuration(
-    dist: Distribution,
-    filepath: StrPath,
-    ignore_option_errors: bool = False,
-) -> Distribution:
-    """Apply the configuration from a ``pyproject.toml`` file into an existing
-    distribution object.
-    """
-    config = read_configuration(filepath, True, ignore_option_errors, dist)
-    return _apply(dist, config, filepath)
-
-
-def read_configuration(
-    filepath: StrPath,
-    expand: bool = True,
-    ignore_option_errors: bool = False,
-    dist: Distribution | None = None,
-) -> dict[str, Any]:
-    """Read given configuration file and returns options from it as a dict.
-
-    :param str|unicode filepath: Path to configuration file in the ``pyproject.toml``
-        format.
-
-    :param bool expand: Whether to expand directives and other computed values
-        (i.e. post-process the given configuration)
-
-    :param bool ignore_option_errors: Whether to silently ignore
-        options, values of which could not be resolved (e.g. due to exceptions
-        in directives such as file:, attr:, etc.).
-        If False exceptions are propagated as expected.
-
-    :param Distribution|None: Distribution object to which the configuration refers.
-        If not given a dummy object will be created and discarded after the
-        configuration is read. This is used for auto-discovery of packages and in the
-        case a dynamic configuration (e.g. ``attr`` or ``cmdclass``) is expanded.
-        When ``expand=False`` this object is simply ignored.
-
-    :rtype: dict
-    """
-    filepath = os.path.abspath(filepath)
-
-    if not os.path.isfile(filepath):
-        raise FileError(f"Configuration file {filepath!r} does not exist.")
-
-    asdict = load_file(filepath) or {}
-    project_table = asdict.get("project", {})
-    tool_table = asdict.get("tool", {})
-    setuptools_table = tool_table.get("setuptools", {})
-    if not asdict or not (project_table or setuptools_table):
-        return {}  # User is not using pyproject to configure setuptools
-
-    if "setuptools" in asdict.get("tools", {}):
-        # let the user know they probably have a typo in their metadata
-        _ToolsTypoInMetadata.emit()
-
-    if "distutils" in tool_table:
-        _ExperimentalConfiguration.emit(subject="[tool.distutils]")
-
-    # There is an overall sense in the community that making include_package_data=True
-    # the default would be an improvement.
-    # `ini2toml` backfills include_package_data=False when nothing is explicitly given,
-    # therefore setting a default here is backwards compatible.
-    if dist and dist.include_package_data is not None:
-        setuptools_table.setdefault("include-package-data", dist.include_package_data)
-    else:
-        setuptools_table.setdefault("include-package-data", True)
-    # Persist changes:
-    asdict["tool"] = tool_table
-    tool_table["setuptools"] = setuptools_table
-
-    if "ext-modules" in setuptools_table:
-        _ExperimentalConfiguration.emit(subject="[tool.setuptools.ext-modules]")
-
-    with _ignore_errors(ignore_option_errors):
-        # Don't complain about unrelated errors (e.g. tools not using the "tool" table)
-        subset = {"project": project_table, "tool": {"setuptools": setuptools_table}}
-        validate(subset, filepath)
-
-    if expand:
-        root_dir = os.path.dirname(filepath)
-        return expand_configuration(asdict, root_dir, ignore_option_errors, dist)
-
-    return asdict
-
-
-def expand_configuration(
-    config: dict,
-    root_dir: StrPath | None = None,
-    ignore_option_errors: bool = False,
-    dist: Distribution | None = None,
-) -> dict:
-    """Given a configuration with unresolved fields (e.g. dynamic, cmdclass, ...)
-    find their final values.
-
-    :param dict config: Dict containing the configuration for the distribution
-    :param str root_dir: Top-level directory for the distribution/project
-        (the same directory where ``pyproject.toml`` is place)
-    :param bool ignore_option_errors: see :func:`read_configuration`
-    :param Distribution|None: Distribution object to which the configuration refers.
-        If not given a dummy object will be created and discarded after the
-        configuration is read. Used in the case a dynamic configuration
-        (e.g. ``attr`` or ``cmdclass``).
-
-    :rtype: dict
-    """
-    return _ConfigExpander(config, root_dir, ignore_option_errors, dist).expand()
-
-
-class _ConfigExpander:
-    def __init__(
-        self,
-        config: dict,
-        root_dir: StrPath | None = None,
-        ignore_option_errors: bool = False,
-        dist: Distribution | None = None,
-    ) -> None:
-        self.config = config
-        self.root_dir = root_dir or os.getcwd()
-        self.project_cfg = config.get("project", {})
-        self.dynamic = self.project_cfg.get("dynamic", [])
-        self.setuptools_cfg = config.get("tool", {}).get("setuptools", {})
-        self.dynamic_cfg = self.setuptools_cfg.get("dynamic", {})
-        self.ignore_option_errors = ignore_option_errors
-        self._dist = dist
-        self._referenced_files = set[str]()
-
-    def _ensure_dist(self) -> Distribution:
-        from setuptools.dist import Distribution
-
-        attrs = {"src_root": self.root_dir, "name": self.project_cfg.get("name", None)}
-        return self._dist or Distribution(attrs)
-
-    def _process_field(self, container: dict, field: str, fn: Callable):
-        if field in container:
-            with _ignore_errors(self.ignore_option_errors):
-                container[field] = fn(container[field])
-
-    def _canonic_package_data(self, field="package-data"):
-        package_data = self.setuptools_cfg.get(field, {})
-        return _expand.canonic_package_data(package_data)
-
-    def expand(self):
-        self._expand_packages()
-        self._canonic_package_data()
-        self._canonic_package_data("exclude-package-data")
-
-        # A distribution object is required for discovering the correct package_dir
-        dist = self._ensure_dist()
-        ctx = _EnsurePackagesDiscovered(dist, self.project_cfg, self.setuptools_cfg)
-        with ctx as ensure_discovered:
-            package_dir = ensure_discovered.package_dir
-            self._expand_data_files()
-            self._expand_cmdclass(package_dir)
-            self._expand_all_dynamic(dist, package_dir)
-
-        dist._referenced_files.update(self._referenced_files)
-        return self.config
-
-    def _expand_packages(self):
-        packages = self.setuptools_cfg.get("packages")
-        if packages is None or isinstance(packages, (list, tuple)):
-            return
-
-        find = packages.get("find")
-        if isinstance(find, dict):
-            find["root_dir"] = self.root_dir
-            find["fill_package_dir"] = self.setuptools_cfg.setdefault("package-dir", {})
-            with _ignore_errors(self.ignore_option_errors):
-                self.setuptools_cfg["packages"] = _expand.find_packages(**find)
-
-    def _expand_data_files(self):
-        data_files = partial(_expand.canonic_data_files, root_dir=self.root_dir)
-        self._process_field(self.setuptools_cfg, "data-files", data_files)
-
-    def _expand_cmdclass(self, package_dir: Mapping[str, str]):
-        root_dir = self.root_dir
-        cmdclass = partial(_expand.cmdclass, package_dir=package_dir, root_dir=root_dir)
-        self._process_field(self.setuptools_cfg, "cmdclass", cmdclass)
-
-    def _expand_all_dynamic(self, dist: Distribution, package_dir: Mapping[str, str]):
-        special = (  # need special handling
-            "version",
-            "readme",
-            "entry-points",
-            "scripts",
-            "gui-scripts",
-            "classifiers",
-            "dependencies",
-            "optional-dependencies",
-        )
-        # `_obtain` functions are assumed to raise appropriate exceptions/warnings.
-        obtained_dynamic = {
-            field: self._obtain(dist, field, package_dir)
-            for field in self.dynamic
-            if field not in special
-        }
-        obtained_dynamic.update(
-            self._obtain_entry_points(dist, package_dir) or {},
-            version=self._obtain_version(dist, package_dir),
-            readme=self._obtain_readme(dist),
-            classifiers=self._obtain_classifiers(dist),
-            dependencies=self._obtain_dependencies(dist),
-            optional_dependencies=self._obtain_optional_dependencies(dist),
-        )
-        # `None` indicates there is nothing in `tool.setuptools.dynamic` but the value
-        # might have already been set by setup.py/extensions, so avoid overwriting.
-        updates = {k: v for k, v in obtained_dynamic.items() if v is not None}
-        self.project_cfg.update(updates)
-
-    def _ensure_previously_set(self, dist: Distribution, field: str):
-        previous = _PREVIOUSLY_DEFINED[field](dist)
-        if previous is None and not self.ignore_option_errors:
-            msg = (
-                f"No configuration found for dynamic {field!r}.\n"
-                "Some dynamic fields need to be specified via `tool.setuptools.dynamic`"
-                "\nothers must be specified via the equivalent attribute in `setup.py`."
-            )
-            raise InvalidConfigError(msg)
-
-    def _expand_directive(
-        self, specifier: str, directive, package_dir: Mapping[str, str]
-    ):
-        from more_itertools import always_iterable
-
-        with _ignore_errors(self.ignore_option_errors):
-            root_dir = self.root_dir
-            if "file" in directive:
-                self._referenced_files.update(always_iterable(directive["file"]))
-                return _expand.read_files(directive["file"], root_dir)
-            if "attr" in directive:
-                return _expand.read_attr(directive["attr"], package_dir, root_dir)
-            raise ValueError(f"invalid `{specifier}`: {directive!r}")
-        return None
-
-    def _obtain(self, dist: Distribution, field: str, package_dir: Mapping[str, str]):
-        if field in self.dynamic_cfg:
-            return self._expand_directive(
-                f"tool.setuptools.dynamic.{field}",
-                self.dynamic_cfg[field],
-                package_dir,
-            )
-        self._ensure_previously_set(dist, field)
-        return None
-
-    def _obtain_version(self, dist: Distribution, package_dir: Mapping[str, str]):
-        # Since plugins can set version, let's silently skip if it cannot be obtained
-        if "version" in self.dynamic and "version" in self.dynamic_cfg:
-            return _expand.version(
-                # We already do an early check for the presence of "version"
-                self._obtain(dist, "version", package_dir)  # pyright: ignore[reportArgumentType]
-            )
-        return None
-
-    def _obtain_readme(self, dist: Distribution) -> dict[str, str] | None:
-        if "readme" not in self.dynamic:
-            return None
-
-        dynamic_cfg = self.dynamic_cfg
-        if "readme" in dynamic_cfg:
-            return {
-                # We already do an early check for the presence of "readme"
-                "text": self._obtain(dist, "readme", {}),
-                "content-type": dynamic_cfg["readme"].get("content-type", "text/x-rst"),
-            }  # pyright: ignore[reportReturnType]
-
-        self._ensure_previously_set(dist, "readme")
-        return None
-
-    def _obtain_entry_points(
-        self, dist: Distribution, package_dir: Mapping[str, str]
-    ) -> dict[str, dict[str, Any]] | None:
-        fields = ("entry-points", "scripts", "gui-scripts")
-        if not any(field in self.dynamic for field in fields):
-            return None
-
-        text = self._obtain(dist, "entry-points", package_dir)
-        if text is None:
-            return None
-
-        groups = _expand.entry_points(text)
-        # Any is str | dict[str, str], but causes variance issues
-        expanded: dict[str, dict[str, Any]] = {"entry-points": groups}
-
-        def _set_scripts(field: str, group: str):
-            if group in groups:
-                value = groups.pop(group)
-                if field not in self.dynamic:
-                    raise InvalidConfigError(_MissingDynamic.details(field, value))
-                expanded[field] = value
-
-        _set_scripts("scripts", "console_scripts")
-        _set_scripts("gui-scripts", "gui_scripts")
-
-        return expanded
-
-    def _obtain_classifiers(self, dist: Distribution):
-        if "classifiers" in self.dynamic:
-            value = self._obtain(dist, "classifiers", {})
-            if value:
-                return value.splitlines()
-        return None
-
-    def _obtain_dependencies(self, dist: Distribution):
-        if "dependencies" in self.dynamic:
-            value = self._obtain(dist, "dependencies", {})
-            if value:
-                return _parse_requirements_list(value)
-        return None
-
-    def _obtain_optional_dependencies(self, dist: Distribution):
-        if "optional-dependencies" not in self.dynamic:
-            return None
-        if "optional-dependencies" in self.dynamic_cfg:
-            optional_dependencies_map = self.dynamic_cfg["optional-dependencies"]
-            assert isinstance(optional_dependencies_map, dict)
-            return {
-                group: _parse_requirements_list(
-                    self._expand_directive(
-                        f"tool.setuptools.dynamic.optional-dependencies.{group}",
-                        directive,
-                        {},
-                    )
-                )
-                for group, directive in optional_dependencies_map.items()
-            }
-        self._ensure_previously_set(dist, "optional-dependencies")
-        return None
-
-
-def _parse_requirements_list(value):
-    return [
-        line
-        for line in value.splitlines()
-        if line.strip() and not line.strip().startswith("#")
-    ]
-
-
-@contextmanager
-def _ignore_errors(ignore_option_errors: bool):
-    if not ignore_option_errors:
-        yield
-        return
-
-    try:
-        yield
-    except Exception as ex:
-        _logger.debug(f"ignored error: {ex.__class__.__name__} - {ex}")
-
-
-class _EnsurePackagesDiscovered(_expand.EnsurePackagesDiscovered):
-    def __init__(
-        self, distribution: Distribution, project_cfg: dict, setuptools_cfg: dict
-    ) -> None:
-        super().__init__(distribution)
-        self._project_cfg = project_cfg
-        self._setuptools_cfg = setuptools_cfg
-
-    def __enter__(self) -> Self:
-        """When entering the context, the values of ``packages``, ``py_modules`` and
-        ``package_dir`` that are missing in ``dist`` are copied from ``setuptools_cfg``.
-        """
-        dist, cfg = self._dist, self._setuptools_cfg
-        package_dir: dict[str, str] = cfg.setdefault("package-dir", {})
-        package_dir.update(dist.package_dir or {})
-        dist.package_dir = package_dir  # needs to be the same object
-
-        dist.set_defaults._ignore_ext_modules()  # pyproject.toml-specific behaviour
-
-        # Set `name`, `py_modules` and `packages` in dist to short-circuit
-        # auto-discovery, but avoid overwriting empty lists purposefully set by users.
-        if dist.metadata.name is None:
-            dist.metadata.name = self._project_cfg.get("name")
-        if dist.py_modules is None:
-            dist.py_modules = cfg.get("py-modules")
-        if dist.packages is None:
-            dist.packages = cfg.get("packages")
-
-        return super().__enter__()
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_value: BaseException | None,
-        traceback: TracebackType | None,
-    ) -> None:
-        """When exiting the context, if values of ``packages``, ``py_modules`` and
-        ``package_dir`` are missing in ``setuptools_cfg``, copy from ``dist``.
-        """
-        # If anything was discovered set them back, so they count in the final config.
-        self._setuptools_cfg.setdefault("packages", self._dist.packages)
-        self._setuptools_cfg.setdefault("py-modules", self._dist.py_modules)
-        return super().__exit__(exc_type, exc_value, traceback)
-
-
-class _ExperimentalConfiguration(SetuptoolsWarning):
-    _SUMMARY = (
-        "`{subject}` in `pyproject.toml` is still *experimental* "
-        "and likely to change in future releases."
-    )
-
-
-class _ToolsTypoInMetadata(SetuptoolsWarning):
-    _SUMMARY = (
-        "Ignoring [tools.setuptools] in pyproject.toml, did you mean [tool.setuptools]?"
-    )
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/setupcfg.py b/llmlab/lib/python3.12/site-packages/setuptools/config/setupcfg.py
deleted file mode 100644
index 633aa9d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/setupcfg.py
+++ /dev/null
@@ -1,780 +0,0 @@
-"""
-Load setuptools configuration from ``setup.cfg`` files.
-
-**API will be made private in the future**
-
-To read project metadata, consider using
-``build.util.project_wheel_metadata`` (https://pypi.org/project/build/).
-For simple scenarios, you can also try parsing the file directly
-with the help of ``configparser``.
-"""
-
-from __future__ import annotations
-
-import contextlib
-import functools
-import os
-from collections import defaultdict
-from collections.abc import Iterable, Iterator
-from functools import partial, wraps
-from typing import TYPE_CHECKING, Any, Callable, ClassVar, Generic, TypeVar, cast
-
-from packaging.markers import default_environment as marker_env
-from packaging.requirements import InvalidRequirement, Requirement
-from packaging.version import InvalidVersion, Version
-
-from .. import _static
-from .._path import StrPath
-from ..errors import FileError, OptionError
-from ..warnings import SetuptoolsDeprecationWarning
-from . import expand
-
-if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
-
-    from setuptools.dist import Distribution
-
-    from distutils.dist import DistributionMetadata
-
-SingleCommandOptions: TypeAlias = dict[str, tuple[str, Any]]
-"""Dict that associate the name of the options of a particular command to a
-tuple. The first element of the tuple indicates the origin of the option value
-(e.g. the name of the configuration file where it was read from),
-while the second element of the tuple is the option value itself
-"""
-AllCommandOptions: TypeAlias = dict[str, SingleCommandOptions]
-"""cmd name => its options"""
-Target = TypeVar("Target", "Distribution", "DistributionMetadata")
-
-
-def read_configuration(
-    filepath: StrPath, find_others: bool = False, ignore_option_errors: bool = False
-) -> dict:
-    """Read given configuration file and returns options from it as a dict.
-
-    :param str|unicode filepath: Path to configuration file
-        to get options from.
-
-    :param bool find_others: Whether to search for other configuration files
-        which could be on in various places.
-
-    :param bool ignore_option_errors: Whether to silently ignore
-        options, values of which could not be resolved (e.g. due to exceptions
-        in directives such as file:, attr:, etc.).
-        If False exceptions are propagated as expected.
-
-    :rtype: dict
-    """
-    from setuptools.dist import Distribution
-
-    dist = Distribution()
-    filenames = dist.find_config_files() if find_others else []
-    handlers = _apply(dist, filepath, filenames, ignore_option_errors)
-    return configuration_to_dict(handlers)
-
-
-def apply_configuration(dist: Distribution, filepath: StrPath) -> Distribution:
-    """Apply the configuration from a ``setup.cfg`` file into an existing
-    distribution object.
-    """
-    _apply(dist, filepath)
-    dist._finalize_requires()
-    return dist
-
-
-def _apply(
-    dist: Distribution,
-    filepath: StrPath,
-    other_files: Iterable[StrPath] = (),
-    ignore_option_errors: bool = False,
-) -> tuple[ConfigMetadataHandler, ConfigOptionsHandler]:
-    """Read configuration from ``filepath`` and applies to the ``dist`` object."""
-    from setuptools.dist import _Distribution
-
-    filepath = os.path.abspath(filepath)
-
-    if not os.path.isfile(filepath):
-        raise FileError(f'Configuration file {filepath} does not exist.')
-
-    current_directory = os.getcwd()
-    os.chdir(os.path.dirname(filepath))
-    filenames = [*other_files, filepath]
-
-    try:
-        # TODO: Temporary cast until mypy 1.12 is released with upstream fixes from typeshed
-        _Distribution.parse_config_files(dist, filenames=cast(list[str], filenames))
-        handlers = parse_configuration(
-            dist, dist.command_options, ignore_option_errors=ignore_option_errors
-        )
-        dist._finalize_license_files()
-    finally:
-        os.chdir(current_directory)
-
-    return handlers
-
-
-def _get_option(target_obj: Distribution | DistributionMetadata, key: str):
-    """
-    Given a target object and option key, get that option from
-    the target object, either through a get_{key} method or
-    from an attribute directly.
-    """
-    getter_name = f'get_{key}'
-    by_attribute = functools.partial(getattr, target_obj, key)
-    getter = getattr(target_obj, getter_name, by_attribute)
-    return getter()
-
-
-def configuration_to_dict(
-    handlers: Iterable[
-        ConfigHandler[Distribution] | ConfigHandler[DistributionMetadata]
-    ],
-) -> dict:
-    """Returns configuration data gathered by given handlers as a dict.
-
-    :param Iterable[ConfigHandler] handlers: Handlers list,
-        usually from parse_configuration()
-
-    :rtype: dict
-    """
-    config_dict: dict = defaultdict(dict)
-
-    for handler in handlers:
-        for option in handler.set_options:
-            value = _get_option(handler.target_obj, option)
-            config_dict[handler.section_prefix][option] = value
-
-    return config_dict
-
-
-def parse_configuration(
-    distribution: Distribution,
-    command_options: AllCommandOptions,
-    ignore_option_errors: bool = False,
-) -> tuple[ConfigMetadataHandler, ConfigOptionsHandler]:
-    """Performs additional parsing of configuration options
-    for a distribution.
-
-    Returns a list of used option handlers.
-
-    :param Distribution distribution:
-    :param dict command_options:
-    :param bool ignore_option_errors: Whether to silently ignore
-        options, values of which could not be resolved (e.g. due to exceptions
-        in directives such as file:, attr:, etc.).
-        If False exceptions are propagated as expected.
-    :rtype: list
-    """
-    with expand.EnsurePackagesDiscovered(distribution) as ensure_discovered:
-        options = ConfigOptionsHandler(
-            distribution,
-            command_options,
-            ignore_option_errors,
-            ensure_discovered,
-        )
-
-        options.parse()
-        if not distribution.package_dir:
-            distribution.package_dir = options.package_dir  # Filled by `find_packages`
-
-        meta = ConfigMetadataHandler(
-            distribution.metadata,
-            command_options,
-            ignore_option_errors,
-            ensure_discovered,
-            distribution.package_dir,
-            distribution.src_root,
-        )
-        meta.parse()
-        distribution._referenced_files.update(
-            options._referenced_files, meta._referenced_files
-        )
-
-    return meta, options
-
-
-def _warn_accidental_env_marker_misconfig(label: str, orig_value: str, parsed: list):
-    """Because users sometimes misinterpret this configuration:
-
-    [options.extras_require]
-    foo = bar;python_version<"4"
-
-    It looks like one requirement with an environment marker
-    but because there is no newline, it's parsed as two requirements
-    with a semicolon as separator.
-
-    Therefore, if:
-        * input string does not contain a newline AND
-        * parsed result contains two requirements AND
-        * parsing of the two parts from the result (";")
-        leads in a valid Requirement with a valid marker
-    a UserWarning is shown to inform the user about the possible problem.
-    """
-    if "\n" in orig_value or len(parsed) != 2:
-        return
-
-    markers = marker_env().keys()
-
-    try:
-        req = Requirement(parsed[1])
-        if req.name in markers:
-            _AmbiguousMarker.emit(field=label, req=parsed[1])
-    except InvalidRequirement as ex:
-        if any(parsed[1].startswith(marker) for marker in markers):
-            msg = _AmbiguousMarker.message(field=label, req=parsed[1])
-            raise InvalidRequirement(msg) from ex
-
-
-class ConfigHandler(Generic[Target]):
-    """Handles metadata supplied in configuration files."""
-
-    section_prefix: str
-    """Prefix for config sections handled by this handler.
-    Must be provided by class heirs.
-
-    """
-
-    aliases: ClassVar[dict[str, str]] = {}
-    """Options aliases.
-    For compatibility with various packages. E.g.: d2to1 and pbr.
-    Note: `-` in keys is replaced with `_` by config parser.
-
-    """
-
-    def __init__(
-        self,
-        target_obj: Target,
-        options: AllCommandOptions,
-        ignore_option_errors,
-        ensure_discovered: expand.EnsurePackagesDiscovered,
-    ) -> None:
-        self.ignore_option_errors = ignore_option_errors
-        self.target_obj: Target = target_obj
-        self.sections = dict(self._section_options(options))
-        self.set_options: list[str] = []
-        self.ensure_discovered = ensure_discovered
-        self._referenced_files = set[str]()
-        """After parsing configurations, this property will enumerate
-        all files referenced by the "file:" directive. Private API for setuptools only.
-        """
-
-    @classmethod
-    def _section_options(
-        cls, options: AllCommandOptions
-    ) -> Iterator[tuple[str, SingleCommandOptions]]:
-        for full_name, value in options.items():
-            pre, _sep, name = full_name.partition(cls.section_prefix)
-            if pre:
-                continue
-            yield name.lstrip('.'), value
-
-    @property
-    def parsers(self):
-        """Metadata item name to parser function mapping."""
-        raise NotImplementedError(
-            f'{self.__class__.__name__} must provide .parsers property'
-        )
-
-    def __setitem__(self, option_name, value) -> None:
-        target_obj = self.target_obj
-
-        # Translate alias into real name.
-        option_name = self.aliases.get(option_name, option_name)
-
-        try:
-            current_value = getattr(target_obj, option_name)
-        except AttributeError as e:
-            raise KeyError(option_name) from e
-
-        if current_value:
-            # Already inhabited. Skipping.
-            return
-
-        try:
-            parsed = self.parsers.get(option_name, lambda x: x)(value)
-        except (Exception,) * self.ignore_option_errors:
-            return
-
-        simple_setter = functools.partial(target_obj.__setattr__, option_name)
-        setter = getattr(target_obj, f"set_{option_name}", simple_setter)
-        setter(parsed)
-
-        self.set_options.append(option_name)
-
-    @classmethod
-    def _parse_list(cls, value, separator=','):
-        """Represents value as a list.
-
-        Value is split either by separator (defaults to comma) or by lines.
-
-        :param value:
-        :param separator: List items separator character.
-        :rtype: list
-        """
-        if isinstance(value, list):  # _get_parser_compound case
-            return value
-
-        if '\n' in value:
-            value = value.splitlines()
-        else:
-            value = value.split(separator)
-
-        return [chunk.strip() for chunk in value if chunk.strip()]
-
-    @classmethod
-    def _parse_dict(cls, value):
-        """Represents value as a dict.
-
-        :param value:
-        :rtype: dict
-        """
-        separator = '='
-        result = {}
-        for line in cls._parse_list(value):
-            key, sep, val = line.partition(separator)
-            if sep != separator:
-                raise OptionError(f"Unable to parse option value to dict: {value}")
-            result[key.strip()] = val.strip()
-
-        return result
-
-    @classmethod
-    def _parse_bool(cls, value):
-        """Represents value as boolean.
-
-        :param value:
-        :rtype: bool
-        """
-        value = value.lower()
-        return value in ('1', 'true', 'yes')
-
-    @classmethod
-    def _exclude_files_parser(cls, key):
-        """Returns a parser function to make sure field inputs
-        are not files.
-
-        Parses a value after getting the key so error messages are
-        more informative.
-
-        :param key:
-        :rtype: callable
-        """
-
-        def parser(value):
-            exclude_directive = 'file:'
-            if value.startswith(exclude_directive):
-                raise ValueError(
-                    f'Only strings are accepted for the {key} field, '
-                    'files are not accepted'
-                )
-            return _static.Str(value)
-
-        return parser
-
-    def _parse_file(self, value, root_dir: StrPath | None):
-        """Represents value as a string, allowing including text
-        from nearest files using `file:` directive.
-
-        Directive is sandboxed and won't reach anything outside
-        directory with setup.py.
-
-        Examples:
-            file: README.rst, CHANGELOG.md, src/file.txt
-
-        :param str value:
-        :rtype: str
-        """
-        include_directive = 'file:'
-
-        if not isinstance(value, str):
-            return value
-
-        if not value.startswith(include_directive):
-            return _static.Str(value)
-
-        spec = value[len(include_directive) :]
-        filepaths = [path.strip() for path in spec.split(',')]
-        self._referenced_files.update(filepaths)
-        # XXX: Is marking as static contents coming from files too optimistic?
-        return _static.Str(expand.read_files(filepaths, root_dir))
-
-    def _parse_attr(self, value, package_dir, root_dir: StrPath):
-        """Represents value as a module attribute.
-
-        Examples:
-            attr: package.attr
-            attr: package.module.attr
-
-        :param str value:
-        :rtype: str
-        """
-        attr_directive = 'attr:'
-        if not value.startswith(attr_directive):
-            return _static.Str(value)
-
-        attr_desc = value.replace(attr_directive, '')
-
-        # Make sure package_dir is populated correctly, so `attr:` directives can work
-        package_dir.update(self.ensure_discovered.package_dir)
-        return expand.read_attr(attr_desc, package_dir, root_dir)
-
-    @classmethod
-    def _get_parser_compound(cls, *parse_methods):
-        """Returns parser function to represents value as a list.
-
-        Parses a value applying given methods one after another.
-
-        :param parse_methods:
-        :rtype: callable
-        """
-
-        def parse(value):
-            parsed = value
-
-            for method in parse_methods:
-                parsed = method(parsed)
-
-            return parsed
-
-        return parse
-
-    @classmethod
-    def _parse_section_to_dict_with_key(cls, section_options, values_parser):
-        """Parses section options into a dictionary.
-
-        Applies a given parser to each option in a section.
-
-        :param dict section_options:
-        :param callable values_parser: function with 2 args corresponding to key, value
-        :rtype: dict
-        """
-        value = {}
-        for key, (_, val) in section_options.items():
-            value[key] = values_parser(key, val)
-        return value
-
-    @classmethod
-    def _parse_section_to_dict(cls, section_options, values_parser=None):
-        """Parses section options into a dictionary.
-
-        Optionally applies a given parser to each value.
-
-        :param dict section_options:
-        :param callable values_parser: function with 1 arg corresponding to option value
-        :rtype: dict
-        """
-        parser = (lambda _, v: values_parser(v)) if values_parser else (lambda _, v: v)
-        return cls._parse_section_to_dict_with_key(section_options, parser)
-
-    def parse_section(self, section_options) -> None:
-        """Parses configuration file section.
-
-        :param dict section_options:
-        """
-        for name, (_, value) in section_options.items():
-            with contextlib.suppress(KeyError):
-                # Keep silent for a new option may appear anytime.
-                self[name] = value
-
-    def parse(self) -> None:
-        """Parses configuration file items from one
-        or more related sections.
-
-        """
-        for section_name, section_options in self.sections.items():
-            method_postfix = ''
-            if section_name:  # [section.option] variant
-                method_postfix = f"_{section_name}"
-
-            section_parser_method: Callable | None = getattr(
-                self,
-                # Dots in section names are translated into dunderscores.
-                f'parse_section{method_postfix}'.replace('.', '__'),
-                None,
-            )
-
-            if section_parser_method is None:
-                raise OptionError(
-                    "Unsupported distribution option section: "
-                    f"[{self.section_prefix}.{section_name}]"
-                )
-
-            section_parser_method(section_options)
-
-    def _deprecated_config_handler(self, func, msg, **kw):
-        """this function will wrap around parameters that are deprecated
-
-        :param msg: deprecation message
-        :param func: function to be wrapped around
-        """
-
-        @wraps(func)
-        def config_handler(*args, **kwargs):
-            kw.setdefault("stacklevel", 2)
-            _DeprecatedConfig.emit("Deprecated config in `setup.cfg`", msg, **kw)
-            return func(*args, **kwargs)
-
-        return config_handler
-
-
-class ConfigMetadataHandler(ConfigHandler["DistributionMetadata"]):
-    section_prefix = 'metadata'
-
-    aliases = {
-        'home_page': 'url',
-        'summary': 'description',
-        'classifier': 'classifiers',
-        'platform': 'platforms',
-    }
-
-    strict_mode = False
-    """We need to keep it loose, to be partially compatible with
-    `pbr` and `d2to1` packages which also uses `metadata` section.
-
-    """
-
-    def __init__(
-        self,
-        target_obj: DistributionMetadata,
-        options: AllCommandOptions,
-        ignore_option_errors: bool,
-        ensure_discovered: expand.EnsurePackagesDiscovered,
-        package_dir: dict | None = None,
-        root_dir: StrPath | None = os.curdir,
-    ) -> None:
-        super().__init__(target_obj, options, ignore_option_errors, ensure_discovered)
-        self.package_dir = package_dir
-        self.root_dir = root_dir
-
-    @property
-    def parsers(self):
-        """Metadata item name to parser function mapping."""
-        parse_list_static = self._get_parser_compound(self._parse_list, _static.List)
-        parse_dict_static = self._get_parser_compound(self._parse_dict, _static.Dict)
-        parse_file = partial(self._parse_file, root_dir=self.root_dir)
-        exclude_files_parser = self._exclude_files_parser
-
-        return {
-            'author': _static.Str,
-            'author_email': _static.Str,
-            'maintainer': _static.Str,
-            'maintainer_email': _static.Str,
-            'platforms': parse_list_static,
-            'keywords': parse_list_static,
-            'provides': parse_list_static,
-            'obsoletes': parse_list_static,
-            'classifiers': self._get_parser_compound(parse_file, parse_list_static),
-            'license': exclude_files_parser('license'),
-            'license_files': parse_list_static,
-            'description': parse_file,
-            'long_description': parse_file,
-            'long_description_content_type': _static.Str,
-            'version': self._parse_version,  # Cannot be marked as dynamic
-            'url': _static.Str,
-            'project_urls': parse_dict_static,
-        }
-
-    def _parse_version(self, value):
-        """Parses `version` option value.
-
-        :param value:
-        :rtype: str
-
-        """
-        version = self._parse_file(value, self.root_dir)
-
-        if version != value:
-            version = version.strip()
-            # Be strict about versions loaded from file because it's easy to
-            # accidentally include newlines and other unintended content
-            try:
-                Version(version)
-            except InvalidVersion as e:
-                raise OptionError(
-                    f'Version loaded from {value} does not '
-                    f'comply with PEP 440: {version}'
-                ) from e
-
-            return version
-
-        return expand.version(self._parse_attr(value, self.package_dir, self.root_dir))
-
-
-class ConfigOptionsHandler(ConfigHandler["Distribution"]):
-    section_prefix = 'options'
-
-    def __init__(
-        self,
-        target_obj: Distribution,
-        options: AllCommandOptions,
-        ignore_option_errors: bool,
-        ensure_discovered: expand.EnsurePackagesDiscovered,
-    ) -> None:
-        super().__init__(target_obj, options, ignore_option_errors, ensure_discovered)
-        self.root_dir = target_obj.src_root
-        self.package_dir: dict[str, str] = {}  # To be filled by `find_packages`
-
-    @classmethod
-    def _parse_list_semicolon(cls, value):
-        return cls._parse_list(value, separator=';')
-
-    def _parse_file_in_root(self, value):
-        return self._parse_file(value, root_dir=self.root_dir)
-
-    def _parse_requirements_list(self, label: str, value: str):
-        # Parse a requirements list, either by reading in a `file:`, or a list.
-        parsed = self._parse_list_semicolon(self._parse_file_in_root(value))
-        _warn_accidental_env_marker_misconfig(label, value, parsed)
-        # Filter it to only include lines that are not comments. `parse_list`
-        # will have stripped each line and filtered out empties.
-        return _static.List(line for line in parsed if not line.startswith("#"))
-        # ^-- Use `_static.List` to mark a non-`Dynamic` Core Metadata
-
-    @property
-    def parsers(self):
-        """Metadata item name to parser function mapping."""
-        parse_list = self._parse_list
-        parse_bool = self._parse_bool
-        parse_cmdclass = self._parse_cmdclass
-
-        return {
-            'zip_safe': parse_bool,
-            'include_package_data': parse_bool,
-            'package_dir': self._parse_dict,
-            'scripts': parse_list,
-            'eager_resources': parse_list,
-            'dependency_links': parse_list,
-            'namespace_packages': self._deprecated_config_handler(
-                parse_list,
-                "The namespace_packages parameter is deprecated, "
-                "consider using implicit namespaces instead (PEP 420).",
-                # TODO: define due date, see setuptools.dist:check_nsp.
-            ),
-            'install_requires': partial(  # Core Metadata
-                self._parse_requirements_list, "install_requires"
-            ),
-            'setup_requires': self._parse_list_semicolon,
-            'packages': self._parse_packages,
-            'entry_points': self._parse_file_in_root,
-            'py_modules': parse_list,
-            'python_requires': _static.SpecifierSet,  # Core Metadata
-            'cmdclass': parse_cmdclass,
-        }
-
-    def _parse_cmdclass(self, value):
-        package_dir = self.ensure_discovered.package_dir
-        return expand.cmdclass(self._parse_dict(value), package_dir, self.root_dir)
-
-    def _parse_packages(self, value):
-        """Parses `packages` option value.
-
-        :param value:
-        :rtype: list
-        """
-        find_directives = ['find:', 'find_namespace:']
-        trimmed_value = value.strip()
-
-        if trimmed_value not in find_directives:
-            return self._parse_list(value)
-
-        # Read function arguments from a dedicated section.
-        find_kwargs = self.parse_section_packages__find(
-            self.sections.get('packages.find', {})
-        )
-
-        find_kwargs.update(
-            namespaces=(trimmed_value == find_directives[1]),
-            root_dir=self.root_dir,
-            fill_package_dir=self.package_dir,
-        )
-
-        return expand.find_packages(**find_kwargs)
-
-    def parse_section_packages__find(self, section_options):
-        """Parses `packages.find` configuration file section.
-
-        To be used in conjunction with _parse_packages().
-
-        :param dict section_options:
-        """
-        section_data = self._parse_section_to_dict(section_options, self._parse_list)
-
-        valid_keys = ['where', 'include', 'exclude']
-        find_kwargs = {k: v for k, v in section_data.items() if k in valid_keys and v}
-
-        where = find_kwargs.get('where')
-        if where is not None:
-            find_kwargs['where'] = where[0]  # cast list to single val
-
-        return find_kwargs
-
-    def parse_section_entry_points(self, section_options) -> None:
-        """Parses `entry_points` configuration file section.
-
-        :param dict section_options:
-        """
-        parsed = self._parse_section_to_dict(section_options, self._parse_list)
-        self['entry_points'] = parsed
-
-    def _parse_package_data(self, section_options):
-        package_data = self._parse_section_to_dict(section_options, self._parse_list)
-        return expand.canonic_package_data(package_data)
-
-    def parse_section_package_data(self, section_options) -> None:
-        """Parses `package_data` configuration file section.
-
-        :param dict section_options:
-        """
-        self['package_data'] = self._parse_package_data(section_options)
-
-    def parse_section_exclude_package_data(self, section_options) -> None:
-        """Parses `exclude_package_data` configuration file section.
-
-        :param dict section_options:
-        """
-        self['exclude_package_data'] = self._parse_package_data(section_options)
-
-    def parse_section_extras_require(self, section_options) -> None:  # Core Metadata
-        """Parses `extras_require` configuration file section.
-
-        :param dict section_options:
-        """
-        parsed = self._parse_section_to_dict_with_key(
-            section_options,
-            lambda k, v: self._parse_requirements_list(f"extras_require[{k}]", v),
-        )
-
-        self['extras_require'] = _static.Dict(parsed)
-        # ^-- Use `_static.Dict` to mark a non-`Dynamic` Core Metadata
-
-    def parse_section_data_files(self, section_options) -> None:
-        """Parses `data_files` configuration file section.
-
-        :param dict section_options:
-        """
-        parsed = self._parse_section_to_dict(section_options, self._parse_list)
-        self['data_files'] = expand.canonic_data_files(parsed, self.root_dir)
-
-
-class _AmbiguousMarker(SetuptoolsDeprecationWarning):
-    _SUMMARY = "Ambiguous requirement marker."
-    _DETAILS = """
-    One of the parsed requirements in `{field}` looks like a valid environment marker:
-
-        {req!r}
-
-    Please make sure that the configuration file is correct.
-    You can use dangling lines to avoid this problem.
-    """
-    _SEE_DOCS = "userguide/declarative_config.html#opt-2"
-    # TODO: should we include due_date here? Initially introduced in 6 Aug 2022.
-    # Does this make sense with latest version of packaging?
-
-    @classmethod
-    def message(cls, **kw):
-        docs = f"https://setuptools.pypa.io/en/latest/{cls._SEE_DOCS}"
-        return cls._format(cls._SUMMARY, cls._DETAILS, see_url=docs, format_args=kw)
-
-
-class _DeprecatedConfig(SetuptoolsDeprecationWarning):
-    _SEE_DOCS = "userguide/declarative_config.html"
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/config/setuptools.schema.json b/llmlab/lib/python3.12/site-packages/setuptools/config/setuptools.schema.json
deleted file mode 100644
index ec887b3..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/config/setuptools.schema.json
+++ /dev/null
@@ -1,433 +0,0 @@
-{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-
-  "$id": "https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html",
-  "title": "``tool.setuptools`` table",
-  "$$description": [
-    "``setuptools``-specific configurations that can be set by users that require",
-    "customization.",
-    "These configurations are completely optional and probably can be skipped when",
-    "creating simple packages. They are equivalent to some of the `Keywords",
-    "`_",
-    "used by the ``setup.py`` file, and can be set via the ``tool.setuptools`` table.",
-    "It considers only ``setuptools`` `parameters",
-    "`_",
-    "that are not covered by :pep:`621`; and intentionally excludes ``dependency_links``",
-    "and ``setup_requires`` (incompatible with modern workflows/standards)."
-  ],
-
-  "type": "object",
-  "additionalProperties": false,
-  "properties": {
-    "platforms": {
-      "type": "array",
-      "items": {"type": "string"}
-    },
-    "provides": {
-      "$$description": [
-        "Package and virtual package names contained within this package",
-        "**(not supported by pip)**"
-      ],
-      "type": "array",
-      "items": {"type": "string", "format": "pep508-identifier"}
-    },
-    "obsoletes": {
-      "$$description": [
-        "Packages which this package renders obsolete",
-        "**(not supported by pip)**"
-      ],
-      "type": "array",
-      "items": {"type": "string", "format": "pep508-identifier"}
-    },
-    "zip-safe": {
-      "$$description": [
-        "Whether the project can be safely installed and run from a zip file.",
-        "**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and",
-        "``setup.py install`` in the context of ``eggs`` (**DEPRECATED**)."
-      ],
-      "type": "boolean"
-    },
-    "script-files": {
-      "$$description": [
-        "Legacy way of defining scripts (entry-points are preferred).",
-        "Equivalent to the ``script`` keyword in ``setup.py``",
-        "(it was renamed to avoid confusion with entry-point based ``project.scripts``",
-        "defined in :pep:`621`).",
-        "**DISCOURAGED**: generic script wrappers are tricky and may not work properly.",
-        "Whenever possible, please use ``project.scripts`` instead."
-      ],
-      "type": "array",
-      "items": {"type": "string"},
-      "$comment": "TODO: is this field deprecated/should be removed?"
-    },
-    "eager-resources": {
-      "$$description": [
-        "Resources that should be extracted together, if any of them is needed,",
-        "or if any C extensions included in the project are imported.",
-        "**OBSOLETE**: only relevant for ``pkg_resources``, ``easy_install`` and",
-        "``setup.py install`` in the context of ``eggs`` (**DEPRECATED**)."
-      ],
-      "type": "array",
-      "items": {"type": "string"}
-    },
-    "packages": {
-      "$$description": [
-        "Packages that should be included in the distribution.",
-        "It can be given either as a list of package identifiers",
-        "or as a ``dict``-like structure with a single key ``find``",
-        "which corresponds to a dynamic call to",
-        "``setuptools.config.expand.find_packages`` function.",
-        "The ``find`` key is associated with a nested ``dict``-like structure that can",
-        "contain ``where``, ``include``, ``exclude`` and ``namespaces`` keys,",
-        "mimicking the keyword arguments of the associated function."
-      ],
-      "oneOf": [
-        {
-          "title": "Array of Python package identifiers",
-          "type": "array",
-          "items": {"$ref": "#/definitions/package-name"}
-        },
-        {"$ref": "#/definitions/find-directive"}
-      ]
-    },
-    "package-dir": {
-      "$$description": [
-        ":class:`dict`-like structure mapping from package names to directories where their",
-        "code can be found.",
-        "The empty string (as key) means that all packages are contained inside",
-        "the given directory will be included in the distribution."
-      ],
-      "type": "object",
-      "additionalProperties": false,
-      "propertyNames": {
-        "anyOf": [{"const": ""}, {"$ref": "#/definitions/package-name"}]
-      },
-      "patternProperties": {
-        "^.*$": {"type": "string" }
-      }
-    },
-    "package-data": {
-      "$$description": [
-        "Mapping from package names to lists of glob patterns.",
-        "Usually this option is not needed when using ``include-package-data = true``",
-        "For more information on how to include data files, check ``setuptools`` `docs",
-        "`_."
-      ],
-      "type": "object",
-      "additionalProperties": false,
-      "propertyNames": {
-        "anyOf": [{"type": "string", "format": "python-module-name"}, {"const": "*"}]
-      },
-      "patternProperties": {
-        "^.*$": {"type": "array", "items": {"type": "string"}}
-      }
-    },
-    "include-package-data": {
-      "$$description": [
-        "Automatically include any data files inside the package directories",
-        "that are specified by ``MANIFEST.in``",
-        "For more information on how to include data files, check ``setuptools`` `docs",
-        "`_."
-      ],
-      "type": "boolean"
-    },
-    "exclude-package-data": {
-      "$$description": [
-        "Mapping from package names to lists of glob patterns that should be excluded",
-        "For more information on how to include data files, check ``setuptools`` `docs",
-        "`_."
-      ],
-      "type": "object",
-      "additionalProperties": false,
-      "propertyNames": {
-        "anyOf": [{"type": "string", "format": "python-module-name"}, {"const": "*"}]
-      },
-      "patternProperties": {
-          "^.*$": {"type": "array", "items": {"type": "string"}}
-      }
-    },
-    "namespace-packages": {
-      "type": "array",
-      "items": {"type": "string", "format": "python-module-name-relaxed"},
-      "$comment": "https://setuptools.pypa.io/en/latest/userguide/package_discovery.html",
-      "description": "**DEPRECATED**: use implicit namespaces instead (:pep:`420`)."
-    },
-    "py-modules": {
-      "description": "Modules that setuptools will manipulate",
-      "type": "array",
-      "items": {"type": "string", "format": "python-module-name-relaxed"},
-      "$comment": "TODO: clarify the relationship with ``packages``"
-    },
-    "ext-modules": {
-      "description": "Extension modules to be compiled by setuptools",
-      "type": "array",
-      "items": {"$ref": "#/definitions/ext-module"}
-    },
-    "data-files": {
-      "$$description": [
-        "``dict``-like structure where each key represents a directory and",
-        "the value is a list of glob patterns that should be installed in them.",
-        "**DISCOURAGED**: please notice this might not work as expected with wheels.",
-        "Whenever possible, consider using data files inside the package directories",
-        "(or create a new namespace package that only contains data files).",
-        "See `data files support",
-        "`_."
-      ],
-      "type": "object",
-      "patternProperties": {
-          "^.*$": {"type": "array", "items": {"type": "string"}}
-      }
-    },
-    "cmdclass": {
-      "$$description": [
-        "Mapping of distutils-style command names to ``setuptools.Command`` subclasses",
-        "which in turn should be represented by strings with a qualified class name",
-        "(i.e., \"dotted\" form with module), e.g.::\n\n",
-        "    cmdclass = {mycmd = \"pkg.subpkg.module.CommandClass\"}\n\n",
-        "The command class should be a directly defined at the top-level of the",
-        "containing module (no class nesting)."
-      ],
-      "type": "object",
-      "patternProperties": {
-          "^.*$": {"type": "string", "format": "python-qualified-identifier"}
-      }
-    },
-    "license-files": {
-      "type": "array",
-      "items": {"type": "string"},
-      "$$description": [
-        "**PROVISIONAL**: list of glob patterns for all license files being distributed.",
-        "(likely to become standard with :pep:`639`).",
-        "By default: ``['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']``"
-      ],
-      "$comment": "TODO: revise if PEP 639 is accepted. Probably ``project.license-files``?"
-    },
-    "dynamic": {
-      "type": "object",
-      "description": "Instructions for loading :pep:`621`-related metadata dynamically",
-      "additionalProperties": false,
-      "properties": {
-        "version": {
-          "$$description": [
-            "A version dynamically loaded via either the ``attr:`` or ``file:``",
-            "directives. Please make sure the given file or attribute respects :pep:`440`.",
-            "Also ensure to set ``project.dynamic`` accordingly."
-          ],
-          "oneOf": [
-            {"$ref": "#/definitions/attr-directive"},
-            {"$ref": "#/definitions/file-directive"}
-          ]
-        },
-        "classifiers": {"$ref": "#/definitions/file-directive"},
-        "description": {"$ref": "#/definitions/file-directive"},
-        "entry-points": {"$ref": "#/definitions/file-directive"},
-        "dependencies": {"$ref": "#/definitions/file-directive-for-dependencies"},
-        "optional-dependencies": {
-          "type": "object",
-          "propertyNames": {"type": "string", "format": "pep508-identifier"},
-          "additionalProperties": false,
-          "patternProperties": {
-            ".+": {"$ref": "#/definitions/file-directive-for-dependencies"}
-          }
-        },
-        "readme": {
-          "type": "object",
-          "anyOf": [
-            {"$ref": "#/definitions/file-directive"},
-            {
-              "type": "object",
-              "properties": {
-                "content-type": {"type": "string"},
-                "file": { "$ref": "#/definitions/file-directive/properties/file" }
-              },
-              "additionalProperties": false}
-          ],
-          "required": ["file"]
-        }
-      }
-    }
-  },
-
-  "definitions": {
-    "package-name": {
-      "$id": "#/definitions/package-name",
-      "title": "Valid package name",
-      "description": "Valid package name (importable or :pep:`561`).",
-      "type": "string",
-      "anyOf": [
-        {"type": "string", "format": "python-module-name-relaxed"},
-        {"type": "string", "format": "pep561-stub-name"}
-      ]
-    },
-    "ext-module": {
-      "$id": "#/definitions/ext-module",
-      "title": "Extension module",
-      "description": "Parameters to construct a :class:`setuptools.Extension` object",
-      "type": "object",
-      "required": ["name", "sources"],
-      "additionalProperties": false,
-      "properties": {
-        "name": {
-          "type": "string",
-          "format": "python-module-name-relaxed"
-        },
-        "sources": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "include-dirs":{
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "define-macros": {
-          "type": "array",
-          "items": {
-            "type": "array",
-            "items": [
-              {"description": "macro name", "type": "string"},
-              {"description": "macro value", "oneOf": [{"type": "string"}, {"type": "null"}]}
-            ],
-            "additionalItems": false
-          }
-        },
-        "undef-macros": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "library-dirs": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "libraries": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "runtime-library-dirs": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "extra-objects": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "extra-compile-args": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "extra-link-args": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "export-symbols": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "swig-opts": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "depends": {
-          "type": "array",
-          "items": {"type": "string"}
-        },
-        "language": {"type": "string"},
-        "optional": {"type": "boolean"},
-        "py-limited-api": {"type": "boolean"}
-      }
-    },
-    "file-directive": {
-      "$id": "#/definitions/file-directive",
-      "title": "'file:' directive",
-      "description":
-        "Value is read from a file (or list of files and then concatenated)",
-      "type": "object",
-      "additionalProperties": false,
-      "properties": {
-        "file": {
-          "oneOf": [
-            {"type": "string"},
-            {"type": "array", "items": {"type": "string"}}
-          ]
-        }
-      },
-      "required": ["file"]
-    },
-    "file-directive-for-dependencies": {
-      "title": "'file:' directive for dependencies",
-      "allOf": [
-        {
-          "$$description": [
-            "**BETA**: subset of the ``requirements.txt`` format",
-            "without ``pip`` flags and options",
-            "(one :pep:`508`-compliant string per line,",
-            "lines that are blank or start with ``#`` are excluded).",
-            "See `dynamic metadata",
-            "`_."
-          ]
-        },
-        {"$ref": "#/definitions/file-directive"}
-      ]
-    },
-    "attr-directive": {
-      "title": "'attr:' directive",
-      "$id": "#/definitions/attr-directive",
-      "$$description": [
-        "Value is read from a module attribute. Supports callables and iterables;",
-        "unsupported types are cast via ``str()``"
-      ],
-      "type": "object",
-      "additionalProperties": false,
-      "properties": {
-        "attr": {"type": "string", "format": "python-qualified-identifier"}
-      },
-      "required": ["attr"]
-    },
-    "find-directive": {
-      "$id": "#/definitions/find-directive",
-      "title": "'find:' directive",
-      "type": "object",
-      "additionalProperties": false,
-      "properties": {
-        "find": {
-          "type": "object",
-          "$$description": [
-            "Dynamic `package discovery",
-            "`_."
-          ],
-          "additionalProperties": false,
-          "properties": {
-            "where": {
-              "description":
-                "Directories to be searched for packages (Unix-style relative path)",
-              "type": "array",
-              "items": {"type": "string"}
-            },
-            "exclude": {
-              "type": "array",
-              "$$description": [
-                "Exclude packages that match the values listed in this field.",
-                "Can container shell-style wildcards (e.g. ``'pkg.*'``)"
-              ],
-              "items": {"type": "string"}
-            },
-            "include": {
-              "type": "array",
-              "$$description": [
-                "Restrict the found packages to just the ones listed in this field.",
-                "Can container shell-style wildcards (e.g. ``'pkg.*'``)"
-              ],
-              "items": {"type": "string"}
-            },
-            "namespaces": {
-              "type": "boolean",
-              "$$description": [
-                "When ``True``, directories without a ``__init__.py`` file will also",
-                "be scanned for :pep:`420`-style implicit namespaces"
-              ]
-            }
-          }
-        }
-      }
-    }
-  }
-}
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/depends.py b/llmlab/lib/python3.12/site-packages/setuptools/depends.py
deleted file mode 100644
index e5223b7..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/depends.py
+++ /dev/null
@@ -1,185 +0,0 @@
-from __future__ import annotations
-
-import contextlib
-import dis
-import marshal
-import sys
-from types import CodeType
-from typing import Any, Literal, TypeVar
-
-from packaging.version import Version
-
-from . import _imp
-from ._imp import PY_COMPILED, PY_FROZEN, PY_SOURCE, find_module
-
-_T = TypeVar("_T")
-
-__all__ = ['Require', 'find_module']
-
-
-class Require:
-    """A prerequisite to building or installing a distribution"""
-
-    def __init__(
-        self,
-        name,
-        requested_version,
-        module,
-        homepage: str = '',
-        attribute=None,
-        format=None,
-    ) -> None:
-        if format is None and requested_version is not None:
-            format = Version
-
-        if format is not None:
-            requested_version = format(requested_version)
-            if attribute is None:
-                attribute = '__version__'
-
-        self.__dict__.update(locals())
-        del self.self
-
-    def full_name(self):
-        """Return full package/distribution name, w/version"""
-        if self.requested_version is not None:
-            return f'{self.name}-{self.requested_version}'
-        return self.name
-
-    def version_ok(self, version):
-        """Is 'version' sufficiently up-to-date?"""
-        return (
-            self.attribute is None
-            or self.format is None
-            or str(version) != "unknown"
-            and self.format(version) >= self.requested_version
-        )
-
-    def get_version(
-        self, paths=None, default: _T | Literal["unknown"] = "unknown"
-    ) -> _T | Literal["unknown"] | None | Any:
-        """Get version number of installed module, 'None', or 'default'
-
-        Search 'paths' for module.  If not found, return 'None'.  If found,
-        return the extracted version attribute, or 'default' if no version
-        attribute was specified, or the value cannot be determined without
-        importing the module.  The version is formatted according to the
-        requirement's version format (if any), unless it is 'None' or the
-        supplied 'default'.
-        """
-
-        if self.attribute is None:
-            try:
-                f, _p, _i = find_module(self.module, paths)
-            except ImportError:
-                return None
-            if f:
-                f.close()
-            return default
-
-        v = get_module_constant(self.module, self.attribute, default, paths)
-
-        if v is not None and v is not default and self.format is not None:
-            return self.format(v)
-
-        return v
-
-    def is_present(self, paths=None):
-        """Return true if dependency is present on 'paths'"""
-        return self.get_version(paths) is not None
-
-    def is_current(self, paths=None):
-        """Return true if dependency is present and up-to-date on 'paths'"""
-        version = self.get_version(paths)
-        if version is None:
-            return False
-        return self.version_ok(str(version))
-
-
-def maybe_close(f):
-    @contextlib.contextmanager
-    def empty():
-        yield
-        return
-
-    if not f:
-        return empty()
-
-    return contextlib.closing(f)
-
-
-# Some objects are not available on some platforms.
-# XXX it'd be better to test assertions about bytecode instead.
-if not sys.platform.startswith('java') and sys.platform != 'cli':
-
-    def get_module_constant(
-        module, symbol, default: _T | int = -1, paths=None
-    ) -> _T | int | None | Any:
-        """Find 'module' by searching 'paths', and extract 'symbol'
-
-        Return 'None' if 'module' does not exist on 'paths', or it does not define
-        'symbol'.  If the module defines 'symbol' as a constant, return the
-        constant.  Otherwise, return 'default'."""
-
-        try:
-            f, path, (_suffix, _mode, kind) = info = find_module(module, paths)
-        except ImportError:
-            # Module doesn't exist
-            return None
-
-        with maybe_close(f):
-            if kind == PY_COMPILED:
-                f.read(8)  # skip magic & date
-                code = marshal.load(f)
-            elif kind == PY_FROZEN:
-                code = _imp.get_frozen_object(module, paths)
-            elif kind == PY_SOURCE:
-                code = compile(f.read(), path, 'exec')
-            else:
-                # Not something we can parse; we'll have to import it.  :(
-                imported = _imp.get_module(module, paths, info)
-                return getattr(imported, symbol, None)
-
-        return extract_constant(code, symbol, default)
-
-    def extract_constant(
-        code: CodeType, symbol: str, default: _T | int = -1
-    ) -> _T | int | None | Any:
-        """Extract the constant value of 'symbol' from 'code'
-
-        If the name 'symbol' is bound to a constant value by the Python code
-        object 'code', return that value.  If 'symbol' is bound to an expression,
-        return 'default'.  Otherwise, return 'None'.
-
-        Return value is based on the first assignment to 'symbol'.  'symbol' must
-        be a global, or at least a non-"fast" local in the code block.  That is,
-        only 'STORE_NAME' and 'STORE_GLOBAL' opcodes are checked, and 'symbol'
-        must be present in 'code.co_names'.
-        """
-        if symbol not in code.co_names:
-            # name's not there, can't possibly be an assignment
-            return None
-
-        name_idx = list(code.co_names).index(symbol)
-
-        STORE_NAME = dis.opmap['STORE_NAME']
-        STORE_GLOBAL = dis.opmap['STORE_GLOBAL']
-        LOAD_CONST = dis.opmap['LOAD_CONST']
-
-        const = default
-
-        for byte_code in dis.Bytecode(code):
-            op = byte_code.opcode
-            arg = byte_code.arg
-
-            if op == LOAD_CONST:
-                assert arg is not None
-                const = code.co_consts[arg]
-            elif arg == name_idx and (op == STORE_NAME or op == STORE_GLOBAL):
-                return const
-            else:
-                const = default
-
-        return None
-
-    __all__ += ['get_module_constant', 'extract_constant']
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/discovery.py b/llmlab/lib/python3.12/site-packages/setuptools/discovery.py
deleted file mode 100644
index c888399..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/discovery.py
+++ /dev/null
@@ -1,614 +0,0 @@
-"""Automatic discovery of Python modules and packages (for inclusion in the
-distribution) and other config values.
-
-For the purposes of this module, the following nomenclature is used:
-
-- "src-layout": a directory representing a Python project that contains a "src"
-  folder. Everything under the "src" folder is meant to be included in the
-  distribution when packaging the project. Example::
-
-    .
-    ├── tox.ini
-    ├── pyproject.toml
-    └── src/
-        └── mypkg/
-            ├── __init__.py
-            ├── mymodule.py
-            └── my_data_file.txt
-
-- "flat-layout": a Python project that does not use "src-layout" but instead
-  have a directory under the project root for each package::
-
-    .
-    ├── tox.ini
-    ├── pyproject.toml
-    └── mypkg/
-        ├── __init__.py
-        ├── mymodule.py
-        └── my_data_file.txt
-
-- "single-module": a project that contains a single Python script direct under
-  the project root (no directory used)::
-
-    .
-    ├── tox.ini
-    ├── pyproject.toml
-    └── mymodule.py
-
-"""
-
-from __future__ import annotations
-
-import itertools
-import os
-from collections.abc import Iterable, Iterator, Mapping
-from fnmatch import fnmatchcase
-from glob import glob
-from pathlib import Path
-from typing import TYPE_CHECKING, ClassVar
-
-import _distutils_hack.override  # noqa: F401
-
-from ._path import StrPath
-
-from distutils import log
-from distutils.util import convert_path
-
-if TYPE_CHECKING:
-    from setuptools import Distribution
-
-chain_iter = itertools.chain.from_iterable
-
-
-def _valid_name(path: StrPath) -> bool:
-    # Ignore invalid names that cannot be imported directly
-    return os.path.basename(path).isidentifier()
-
-
-class _Filter:
-    """
-    Given a list of patterns, create a callable that will be true only if
-    the input matches at least one of the patterns.
-    """
-
-    def __init__(self, *patterns: str) -> None:
-        self._patterns = dict.fromkeys(patterns)
-
-    def __call__(self, item: str) -> bool:
-        return any(fnmatchcase(item, pat) for pat in self._patterns)
-
-    def __contains__(self, item: str) -> bool:
-        return item in self._patterns
-
-
-class _Finder:
-    """Base class that exposes functionality for module/package finders"""
-
-    ALWAYS_EXCLUDE: ClassVar[tuple[str, ...]] = ()
-    DEFAULT_EXCLUDE: ClassVar[tuple[str, ...]] = ()
-
-    @classmethod
-    def find(
-        cls,
-        where: StrPath = '.',
-        exclude: Iterable[str] = (),
-        include: Iterable[str] = ('*',),
-    ) -> list[str]:
-        """Return a list of all Python items (packages or modules, depending on
-        the finder implementation) found within directory 'where'.
-
-        'where' is the root directory which will be searched.
-        It should be supplied as a "cross-platform" (i.e. URL-style) path;
-        it will be converted to the appropriate local path syntax.
-
-        'exclude' is a sequence of names to exclude; '*' can be used
-        as a wildcard in the names.
-        When finding packages, 'foo.*' will exclude all subpackages of 'foo'
-        (but not 'foo' itself).
-
-        'include' is a sequence of names to include.
-        If it's specified, only the named items will be included.
-        If it's not specified, all found items will be included.
-        'include' can contain shell style wildcard patterns just like
-        'exclude'.
-        """
-
-        exclude = exclude or cls.DEFAULT_EXCLUDE
-        return list(
-            cls._find_iter(
-                convert_path(str(where)),
-                _Filter(*cls.ALWAYS_EXCLUDE, *exclude),
-                _Filter(*include),
-            )
-        )
-
-    @classmethod
-    def _find_iter(
-        cls, where: StrPath, exclude: _Filter, include: _Filter
-    ) -> Iterator[str]:
-        raise NotImplementedError
-
-
-class PackageFinder(_Finder):
-    """
-    Generate a list of all Python packages found within a directory
-    """
-
-    ALWAYS_EXCLUDE = ("ez_setup", "*__pycache__")
-
-    @classmethod
-    def _find_iter(
-        cls, where: StrPath, exclude: _Filter, include: _Filter
-    ) -> Iterator[str]:
-        """
-        All the packages found in 'where' that pass the 'include' filter, but
-        not the 'exclude' filter.
-        """
-        for root, dirs, files in os.walk(str(where), followlinks=True):
-            # Copy dirs to iterate over it, then empty dirs.
-            all_dirs = dirs[:]
-            dirs[:] = []
-
-            for dir in all_dirs:
-                full_path = os.path.join(root, dir)
-                rel_path = os.path.relpath(full_path, where)
-                package = rel_path.replace(os.path.sep, '.')
-
-                # Skip directory trees that are not valid packages
-                if '.' in dir or not cls._looks_like_package(full_path, package):
-                    continue
-
-                # Should this package be included?
-                if include(package) and not exclude(package):
-                    yield package
-
-                # Early pruning if there is nothing else to be scanned
-                if f"{package}*" in exclude or f"{package}.*" in exclude:
-                    continue
-
-                # Keep searching subdirectories, as there may be more packages
-                # down there, even if the parent was excluded.
-                dirs.append(dir)
-
-    @staticmethod
-    def _looks_like_package(path: StrPath, _package_name: str) -> bool:
-        """Does a directory look like a package?"""
-        return os.path.isfile(os.path.join(path, '__init__.py'))
-
-
-class PEP420PackageFinder(PackageFinder):
-    @staticmethod
-    def _looks_like_package(_path: StrPath, _package_name: str) -> bool:
-        return True
-
-
-class ModuleFinder(_Finder):
-    """Find isolated Python modules.
-    This function will **not** recurse subdirectories.
-    """
-
-    @classmethod
-    def _find_iter(
-        cls, where: StrPath, exclude: _Filter, include: _Filter
-    ) -> Iterator[str]:
-        for file in glob(os.path.join(where, "*.py")):
-            module, _ext = os.path.splitext(os.path.basename(file))
-
-            if not cls._looks_like_module(module):
-                continue
-
-            if include(module) and not exclude(module):
-                yield module
-
-    _looks_like_module = staticmethod(_valid_name)
-
-
-# We have to be extra careful in the case of flat layout to not include files
-# and directories not meant for distribution (e.g. tool-related)
-
-
-class FlatLayoutPackageFinder(PEP420PackageFinder):
-    _EXCLUDE = (
-        "ci",
-        "bin",
-        "debian",
-        "doc",
-        "docs",
-        "documentation",
-        "manpages",
-        "news",
-        "newsfragments",
-        "changelog",
-        "test",
-        "tests",
-        "unit_test",
-        "unit_tests",
-        "example",
-        "examples",
-        "scripts",
-        "tools",
-        "util",
-        "utils",
-        "python",
-        "build",
-        "dist",
-        "venv",
-        "env",
-        "requirements",
-        # ---- Task runners / Build tools ----
-        "tasks",  # invoke
-        "fabfile",  # fabric
-        "site_scons",  # SCons
-        # ---- Other tools ----
-        "benchmark",
-        "benchmarks",
-        "exercise",
-        "exercises",
-        "htmlcov",  # Coverage.py
-        # ---- Hidden directories/Private packages ----
-        "[._]*",
-    )
-
-    DEFAULT_EXCLUDE = tuple(chain_iter((p, f"{p}.*") for p in _EXCLUDE))
-    """Reserved package names"""
-
-    @staticmethod
-    def _looks_like_package(_path: StrPath, package_name: str) -> bool:
-        names = package_name.split('.')
-        # Consider PEP 561
-        root_pkg_is_valid = names[0].isidentifier() or names[0].endswith("-stubs")
-        return root_pkg_is_valid and all(name.isidentifier() for name in names[1:])
-
-
-class FlatLayoutModuleFinder(ModuleFinder):
-    DEFAULT_EXCLUDE = (
-        "setup",
-        "conftest",
-        "test",
-        "tests",
-        "example",
-        "examples",
-        "build",
-        # ---- Task runners ----
-        "toxfile",
-        "noxfile",
-        "pavement",
-        "dodo",
-        "tasks",
-        "fabfile",
-        # ---- Other tools ----
-        "[Ss][Cc]onstruct",  # SCons
-        "conanfile",  # Connan: C/C++ build tool
-        "manage",  # Django
-        "benchmark",
-        "benchmarks",
-        "exercise",
-        "exercises",
-        # ---- Hidden files/Private modules ----
-        "[._]*",
-    )
-    """Reserved top-level module names"""
-
-
-def _find_packages_within(root_pkg: str, pkg_dir: StrPath) -> list[str]:
-    nested = PEP420PackageFinder.find(pkg_dir)
-    return [root_pkg] + [".".join((root_pkg, n)) for n in nested]
-
-
-class ConfigDiscovery:
-    """Fill-in metadata and options that can be automatically derived
-    (from other metadata/options, the file system or conventions)
-    """
-
-    def __init__(self, distribution: Distribution) -> None:
-        self.dist = distribution
-        self._called = False
-        self._disabled = False
-        self._skip_ext_modules = False
-
-    def _disable(self):
-        """Internal API to disable automatic discovery"""
-        self._disabled = True
-
-    def _ignore_ext_modules(self):
-        """Internal API to disregard ext_modules.
-
-        Normally auto-discovery would not be triggered if ``ext_modules`` are set
-        (this is done for backward compatibility with existing packages relying on
-        ``setup.py`` or ``setup.cfg``). However, ``setuptools`` can call this function
-        to ignore given ``ext_modules`` and proceed with the auto-discovery if
-        ``packages`` and ``py_modules`` are not given (e.g. when using pyproject.toml
-        metadata).
-        """
-        self._skip_ext_modules = True
-
-    @property
-    def _root_dir(self) -> StrPath:
-        # The best is to wait until `src_root` is set in dist, before using _root_dir.
-        return self.dist.src_root or os.curdir
-
-    @property
-    def _package_dir(self) -> dict[str, str]:
-        if self.dist.package_dir is None:
-            return {}
-        return self.dist.package_dir
-
-    def __call__(
-        self, force: bool = False, name: bool = True, ignore_ext_modules: bool = False
-    ):
-        """Automatically discover missing configuration fields
-        and modifies the given ``distribution`` object in-place.
-
-        Note that by default this will only have an effect the first time the
-        ``ConfigDiscovery`` object is called.
-
-        To repeatedly invoke automatic discovery (e.g. when the project
-        directory changes), please use ``force=True`` (or create a new
-        ``ConfigDiscovery`` instance).
-        """
-        if force is False and (self._called or self._disabled):
-            # Avoid overhead of multiple calls
-            return
-
-        self._analyse_package_layout(ignore_ext_modules)
-        if name:
-            self.analyse_name()  # depends on ``packages`` and ``py_modules``
-
-        self._called = True
-
-    def _explicitly_specified(self, ignore_ext_modules: bool) -> bool:
-        """``True`` if the user has specified some form of package/module listing"""
-        ignore_ext_modules = ignore_ext_modules or self._skip_ext_modules
-        ext_modules = not (self.dist.ext_modules is None or ignore_ext_modules)
-        return (
-            self.dist.packages is not None
-            or self.dist.py_modules is not None
-            or ext_modules
-            or hasattr(self.dist, "configuration")
-            and self.dist.configuration
-            # ^ Some projects use numpy.distutils.misc_util.Configuration
-        )
-
-    def _analyse_package_layout(self, ignore_ext_modules: bool) -> bool:
-        if self._explicitly_specified(ignore_ext_modules):
-            # For backward compatibility, just try to find modules/packages
-            # when nothing is given
-            return True
-
-        log.debug(
-            "No `packages` or `py_modules` configuration, performing "
-            "automatic discovery."
-        )
-
-        return (
-            self._analyse_explicit_layout()
-            or self._analyse_src_layout()
-            # flat-layout is the trickiest for discovery so it should be last
-            or self._analyse_flat_layout()
-        )
-
-    def _analyse_explicit_layout(self) -> bool:
-        """The user can explicitly give a package layout via ``package_dir``"""
-        package_dir = self._package_dir.copy()  # don't modify directly
-        package_dir.pop("", None)  # This falls under the "src-layout" umbrella
-        root_dir = self._root_dir
-
-        if not package_dir:
-            return False
-
-        log.debug(f"`explicit-layout` detected -- analysing {package_dir}")
-        pkgs = chain_iter(
-            _find_packages_within(pkg, os.path.join(root_dir, parent_dir))
-            for pkg, parent_dir in package_dir.items()
-        )
-        self.dist.packages = list(pkgs)
-        log.debug(f"discovered packages -- {self.dist.packages}")
-        return True
-
-    def _analyse_src_layout(self) -> bool:
-        """Try to find all packages or modules under the ``src`` directory
-        (or anything pointed by ``package_dir[""]``).
-
-        The "src-layout" is relatively safe for automatic discovery.
-        We assume that everything within is meant to be included in the
-        distribution.
-
-        If ``package_dir[""]`` is not given, but the ``src`` directory exists,
-        this function will set ``package_dir[""] = "src"``.
-        """
-        package_dir = self._package_dir
-        src_dir = os.path.join(self._root_dir, package_dir.get("", "src"))
-        if not os.path.isdir(src_dir):
-            return False
-
-        log.debug(f"`src-layout` detected -- analysing {src_dir}")
-        package_dir.setdefault("", os.path.basename(src_dir))
-        self.dist.package_dir = package_dir  # persist eventual modifications
-        self.dist.packages = PEP420PackageFinder.find(src_dir)
-        self.dist.py_modules = ModuleFinder.find(src_dir)
-        log.debug(f"discovered packages -- {self.dist.packages}")
-        log.debug(f"discovered py_modules -- {self.dist.py_modules}")
-        return True
-
-    def _analyse_flat_layout(self) -> bool:
-        """Try to find all packages and modules under the project root.
-
-        Since the ``flat-layout`` is more dangerous in terms of accidentally including
-        extra files/directories, this function is more conservative and will raise an
-        error if multiple packages or modules are found.
-
-        This assumes that multi-package dists are uncommon and refuse to support that
-        use case in order to be able to prevent unintended errors.
-        """
-        log.debug(f"`flat-layout` detected -- analysing {self._root_dir}")
-        return self._analyse_flat_packages() or self._analyse_flat_modules()
-
-    def _analyse_flat_packages(self) -> bool:
-        self.dist.packages = FlatLayoutPackageFinder.find(self._root_dir)
-        top_level = remove_nested_packages(remove_stubs(self.dist.packages))
-        log.debug(f"discovered packages -- {self.dist.packages}")
-        self._ensure_no_accidental_inclusion(top_level, "packages")
-        return bool(top_level)
-
-    def _analyse_flat_modules(self) -> bool:
-        self.dist.py_modules = FlatLayoutModuleFinder.find(self._root_dir)
-        log.debug(f"discovered py_modules -- {self.dist.py_modules}")
-        self._ensure_no_accidental_inclusion(self.dist.py_modules, "modules")
-        return bool(self.dist.py_modules)
-
-    def _ensure_no_accidental_inclusion(self, detected: list[str], kind: str):
-        if len(detected) > 1:
-            from inspect import cleandoc
-
-            from setuptools.errors import PackageDiscoveryError
-
-            msg = f"""Multiple top-level {kind} discovered in a flat-layout: {detected}.
-
-            To avoid accidental inclusion of unwanted files or directories,
-            setuptools will not proceed with this build.
-
-            If you are trying to create a single distribution with multiple {kind}
-            on purpose, you should not rely on automatic discovery.
-            Instead, consider the following options:
-
-            1. set up custom discovery (`find` directive with `include` or `exclude`)
-            2. use a `src-layout`
-            3. explicitly set `py_modules` or `packages` with a list of names
-
-            To find more information, look for "package discovery" on setuptools docs.
-            """
-            raise PackageDiscoveryError(cleandoc(msg))
-
-    def analyse_name(self) -> None:
-        """The packages/modules are the essential contribution of the author.
-        Therefore the name of the distribution can be derived from them.
-        """
-        if self.dist.metadata.name or self.dist.name:
-            # get_name() is not reliable (can return "UNKNOWN")
-            return
-
-        log.debug("No `name` configuration, performing automatic discovery")
-
-        name = (
-            self._find_name_single_package_or_module()
-            or self._find_name_from_packages()
-        )
-        if name:
-            self.dist.metadata.name = name
-
-    def _find_name_single_package_or_module(self) -> str | None:
-        """Exactly one module or package"""
-        for field in ('packages', 'py_modules'):
-            items = getattr(self.dist, field, None) or []
-            if items and len(items) == 1:
-                log.debug(f"Single module/package detected, name: {items[0]}")
-                return items[0]
-
-        return None
-
-    def _find_name_from_packages(self) -> str | None:
-        """Try to find the root package that is not a PEP 420 namespace"""
-        if not self.dist.packages:
-            return None
-
-        packages = remove_stubs(sorted(self.dist.packages, key=len))
-        package_dir = self.dist.package_dir or {}
-
-        parent_pkg = find_parent_package(packages, package_dir, self._root_dir)
-        if parent_pkg:
-            log.debug(f"Common parent package detected, name: {parent_pkg}")
-            return parent_pkg
-
-        log.warn("No parent package detected, impossible to derive `name`")
-        return None
-
-
-def remove_nested_packages(packages: list[str]) -> list[str]:
-    """Remove nested packages from a list of packages.
-
-    >>> remove_nested_packages(["a", "a.b1", "a.b2", "a.b1.c1"])
-    ['a']
-    >>> remove_nested_packages(["a", "b", "c.d", "c.d.e.f", "g.h", "a.a1"])
-    ['a', 'b', 'c.d', 'g.h']
-    """
-    pkgs = sorted(packages, key=len)
-    top_level = pkgs[:]
-    size = len(pkgs)
-    for i, name in enumerate(reversed(pkgs)):
-        if any(name.startswith(f"{other}.") for other in top_level):
-            top_level.pop(size - i - 1)
-
-    return top_level
-
-
-def remove_stubs(packages: list[str]) -> list[str]:
-    """Remove type stubs (:pep:`561`) from a list of packages.
-
-    >>> remove_stubs(["a", "a.b", "a-stubs", "a-stubs.b.c", "b", "c-stubs"])
-    ['a', 'a.b', 'b']
-    """
-    return [pkg for pkg in packages if not pkg.split(".")[0].endswith("-stubs")]
-
-
-def find_parent_package(
-    packages: list[str], package_dir: Mapping[str, str], root_dir: StrPath
-) -> str | None:
-    """Find the parent package that is not a namespace."""
-    packages = sorted(packages, key=len)
-    common_ancestors = []
-    for i, name in enumerate(packages):
-        if not all(n.startswith(f"{name}.") for n in packages[i + 1 :]):
-            # Since packages are sorted by length, this condition is able
-            # to find a list of all common ancestors.
-            # When there is divergence (e.g. multiple root packages)
-            # the list will be empty
-            break
-        common_ancestors.append(name)
-
-    for name in common_ancestors:
-        pkg_path = find_package_path(name, package_dir, root_dir)
-        init = os.path.join(pkg_path, "__init__.py")
-        if os.path.isfile(init):
-            return name
-
-    return None
-
-
-def find_package_path(
-    name: str, package_dir: Mapping[str, str], root_dir: StrPath
-) -> str:
-    """Given a package name, return the path where it should be found on
-    disk, considering the ``package_dir`` option.
-
-    >>> path = find_package_path("my.pkg", {"": "root/is/nested"}, ".")
-    >>> path.replace(os.sep, "/")
-    './root/is/nested/my/pkg'
-
-    >>> path = find_package_path("my.pkg", {"my": "root/is/nested"}, ".")
-    >>> path.replace(os.sep, "/")
-    './root/is/nested/pkg'
-
-    >>> path = find_package_path("my.pkg", {"my.pkg": "root/is/nested"}, ".")
-    >>> path.replace(os.sep, "/")
-    './root/is/nested'
-
-    >>> path = find_package_path("other.pkg", {"my.pkg": "root/is/nested"}, ".")
-    >>> path.replace(os.sep, "/")
-    './other/pkg'
-    """
-    parts = name.split(".")
-    for i in range(len(parts), 0, -1):
-        # Look backwards, the most specific package_dir first
-        partial_name = ".".join(parts[:i])
-        if partial_name in package_dir:
-            parent = package_dir[partial_name]
-            return os.path.join(root_dir, parent, *parts[i:])
-
-    parent = package_dir.get("") or ""
-    return os.path.join(root_dir, *parent.split("/"), *parts)
-
-
-def construct_package_dir(packages: list[str], package_path: StrPath) -> dict[str, str]:
-    parent_pkgs = remove_nested_packages(packages)
-    prefix = Path(package_path).parts
-    return {pkg: "/".join([*prefix, *pkg.split(".")]) for pkg in parent_pkgs}
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/dist.py b/llmlab/lib/python3.12/site-packages/setuptools/dist.py
deleted file mode 100644
index 8d972cc..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/dist.py
+++ /dev/null
@@ -1,1121 +0,0 @@
-from __future__ import annotations
-
-import functools
-import io
-import itertools
-import numbers
-import os
-import re
-import sys
-from collections.abc import Iterable, Iterator, MutableMapping, Sequence
-from glob import glob
-from pathlib import Path
-from typing import TYPE_CHECKING, Any, Union
-
-from more_itertools import partition, unique_everseen
-from packaging.markers import InvalidMarker, Marker
-from packaging.specifiers import InvalidSpecifier, SpecifierSet
-from packaging.version import Version
-
-from . import (
-    _entry_points,
-    _reqs,
-    _static,
-    command as _,  # noqa: F401 # imported for side-effects
-)
-from ._importlib import metadata
-from ._normalization import _canonicalize_license_expression
-from ._path import StrPath
-from ._reqs import _StrOrIter
-from .config import pyprojecttoml, setupcfg
-from .discovery import ConfigDiscovery
-from .errors import InvalidConfigError
-from .monkey import get_unpatched
-from .warnings import InformationOnly, SetuptoolsDeprecationWarning
-
-import distutils.cmd
-import distutils.command
-import distutils.core
-import distutils.dist
-import distutils.log
-from distutils.debug import DEBUG
-from distutils.errors import DistutilsOptionError, DistutilsSetupError
-from distutils.fancy_getopt import translate_longopt
-from distutils.util import strtobool
-
-if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
-
-    from pkg_resources import Distribution as _pkg_resources_Distribution
-
-
-__all__ = ['Distribution']
-
-_sequence = tuple, list
-"""
-:meta private:
-
-Supported iterable types that are known to be:
-- ordered (which `set` isn't)
-- not match a str (which `Sequence[str]` does)
-- not imply a nested type (like `dict`)
-for use with `isinstance`.
-"""
-_Sequence: TypeAlias = Union[tuple[str, ...], list[str]]
-# This is how stringifying _Sequence would look in Python 3.10
-_sequence_type_repr = "tuple[str, ...] | list[str]"
-_OrderedStrSequence: TypeAlias = Union[str, dict[str, Any], Sequence[str]]
-"""
-:meta private:
-Avoid single-use iterable. Disallow sets.
-A poor approximation of an OrderedSequence (dict doesn't match a Sequence).
-"""
-
-
-def __getattr__(name: str) -> Any:  # pragma: no cover
-    if name == "sequence":
-        SetuptoolsDeprecationWarning.emit(
-            "`setuptools.dist.sequence` is an internal implementation detail.",
-            "Please define your own `sequence = tuple, list` instead.",
-            due_date=(2025, 8, 28),  # Originally added on 2024-08-27
-        )
-        return _sequence
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
-
-
-def check_importable(dist, attr, value):
-    try:
-        ep = metadata.EntryPoint(value=value, name=None, group=None)
-        assert not ep.extras
-    except (TypeError, ValueError, AttributeError, AssertionError) as e:
-        raise DistutilsSetupError(
-            f"{attr!r} must be importable 'module:attrs' string (got {value!r})"
-        ) from e
-
-
-def assert_string_list(dist, attr: str, value: _Sequence) -> None:
-    """Verify that value is a string list"""
-    try:
-        # verify that value is a list or tuple to exclude unordered
-        # or single-use iterables
-        assert isinstance(value, _sequence)
-        # verify that elements of value are strings
-        assert ''.join(value) != value
-    except (TypeError, ValueError, AttributeError, AssertionError) as e:
-        raise DistutilsSetupError(
-            f"{attr!r} must be of type <{_sequence_type_repr}> (got {value!r})"
-        ) from e
-
-
-def check_nsp(dist, attr, value):
-    """Verify that namespace packages are valid"""
-    ns_packages = value
-    assert_string_list(dist, attr, ns_packages)
-    for nsp in ns_packages:
-        if not dist.has_contents_for(nsp):
-            raise DistutilsSetupError(
-                f"Distribution contains no modules or packages for namespace package {nsp!r}"
-            )
-        parent, _sep, _child = nsp.rpartition('.')
-        if parent and parent not in ns_packages:
-            distutils.log.warn(
-                "WARNING: %r is declared as a package namespace, but %r"
-                " is not: please correct this in setup.py",
-                nsp,
-                parent,
-            )
-        SetuptoolsDeprecationWarning.emit(
-            "The namespace_packages parameter is deprecated.",
-            "Please replace its usage with implicit namespaces (PEP 420).",
-            see_docs="references/keywords.html#keyword-namespace-packages",
-            # TODO: define due_date, it may break old packages that are no longer
-            # maintained (e.g. sphinxcontrib extensions) when installed from source.
-            # Warning officially introduced in May 2022, however the deprecation
-            # was mentioned much earlier in the docs (May 2020, see #2149).
-        )
-
-
-def check_extras(dist, attr, value):
-    """Verify that extras_require mapping is valid"""
-    try:
-        list(itertools.starmap(_check_extra, value.items()))
-    except (TypeError, ValueError, AttributeError) as e:
-        raise DistutilsSetupError(
-            "'extras_require' must be a dictionary whose values are "
-            "strings or lists of strings containing valid project/version "
-            "requirement specifiers."
-        ) from e
-
-
-def _check_extra(extra, reqs):
-    _name, _sep, marker = extra.partition(':')
-    try:
-        _check_marker(marker)
-    except InvalidMarker:
-        msg = f"Invalid environment marker: {marker} ({extra!r})"
-        raise DistutilsSetupError(msg) from None
-    list(_reqs.parse(reqs))
-
-
-def _check_marker(marker):
-    if not marker:
-        return
-    m = Marker(marker)
-    m.evaluate()
-
-
-def assert_bool(dist, attr, value):
-    """Verify that value is True, False, 0, or 1"""
-    if bool(value) != value:
-        raise DistutilsSetupError(f"{attr!r} must be a boolean value (got {value!r})")
-
-
-def invalid_unless_false(dist, attr, value):
-    if not value:
-        DistDeprecationWarning.emit(f"{attr} is ignored.")
-        # TODO: should there be a `due_date` here?
-        return
-    raise DistutilsSetupError(f"{attr} is invalid.")
-
-
-def check_requirements(dist, attr: str, value: _OrderedStrSequence) -> None:
-    """Verify that install_requires is a valid requirements list"""
-    try:
-        list(_reqs.parse(value))
-        if isinstance(value, set):
-            raise TypeError("Unordered types are not allowed")
-    except (TypeError, ValueError) as error:
-        msg = (
-            f"{attr!r} must be a string or iterable of strings "
-            f"containing valid project/version requirement specifiers; {error}"
-        )
-        raise DistutilsSetupError(msg) from error
-
-
-def check_specifier(dist, attr, value):
-    """Verify that value is a valid version specifier"""
-    try:
-        SpecifierSet(value)
-    except (InvalidSpecifier, AttributeError) as error:
-        msg = f"{attr!r} must be a string containing valid version specifiers; {error}"
-        raise DistutilsSetupError(msg) from error
-
-
-def check_entry_points(dist, attr, value):
-    """Verify that entry_points map is parseable"""
-    try:
-        _entry_points.load(value)
-    except Exception as e:
-        raise DistutilsSetupError(e) from e
-
-
-def check_package_data(dist, attr, value):
-    """Verify that value is a dictionary of package names to glob lists"""
-    if not isinstance(value, dict):
-        raise DistutilsSetupError(
-            f"{attr!r} must be a dictionary mapping package names to lists of "
-            "string wildcard patterns"
-        )
-    for k, v in value.items():
-        if not isinstance(k, str):
-            raise DistutilsSetupError(
-                f"keys of {attr!r} dict must be strings (got {k!r})"
-            )
-        assert_string_list(dist, f'values of {attr!r} dict', v)
-
-
-def check_packages(dist, attr, value):
-    for pkgname in value:
-        if not re.match(r'\w+(\.\w+)*', pkgname):
-            distutils.log.warn(
-                "WARNING: %r not a valid package name; please use only "
-                ".-separated package names in setup.py",
-                pkgname,
-            )
-
-
-if TYPE_CHECKING:
-    # Work around a mypy issue where type[T] can't be used as a base: https://github.com/python/mypy/issues/10962
-    from distutils.core import Distribution as _Distribution
-else:
-    _Distribution = get_unpatched(distutils.core.Distribution)
-
-
-class Distribution(_Distribution):
-    """Distribution with support for tests and package data
-
-    This is an enhanced version of 'distutils.dist.Distribution' that
-    effectively adds the following new optional keyword arguments to 'setup()':
-
-     'install_requires' -- a string or sequence of strings specifying project
-        versions that the distribution requires when installed, in the format
-        used by 'pkg_resources.require()'.  They will be installed
-        automatically when the package is installed.  If you wish to use
-        packages that are not available in PyPI, or want to give your users an
-        alternate download location, you can add a 'find_links' option to the
-        '[easy_install]' section of your project's 'setup.cfg' file, and then
-        setuptools will scan the listed web pages for links that satisfy the
-        requirements.
-
-     'extras_require' -- a dictionary mapping names of optional "extras" to the
-        additional requirement(s) that using those extras incurs. For example,
-        this::
-
-            extras_require = dict(reST = ["docutils>=0.3", "reSTedit"])
-
-        indicates that the distribution can optionally provide an extra
-        capability called "reST", but it can only be used if docutils and
-        reSTedit are installed.  If the user installs your package using
-        EasyInstall and requests one of your extras, the corresponding
-        additional requirements will be installed if needed.
-
-     'package_data' -- a dictionary mapping package names to lists of filenames
-        or globs to use to find data files contained in the named packages.
-        If the dictionary has filenames or globs listed under '""' (the empty
-        string), those names will be searched for in every package, in addition
-        to any names for the specific package.  Data files found using these
-        names/globs will be installed along with the package, in the same
-        location as the package.  Note that globs are allowed to reference
-        the contents of non-package subdirectories, as long as you use '/' as
-        a path separator.  (Globs are automatically converted to
-        platform-specific paths at runtime.)
-
-    In addition to these new keywords, this class also has several new methods
-    for manipulating the distribution's contents.  For example, the 'include()'
-    and 'exclude()' methods can be thought of as in-place add and subtract
-    commands that add or remove packages, modules, extensions, and so on from
-    the distribution.
-    """
-
-    _DISTUTILS_UNSUPPORTED_METADATA = {
-        'long_description_content_type': lambda: None,
-        'project_urls': dict,
-        'provides_extras': dict,  # behaves like an ordered set
-        'license_expression': lambda: None,
-        'license_file': lambda: None,
-        'license_files': lambda: None,
-        'install_requires': list,
-        'extras_require': dict,
-    }
-
-    # Used by build_py, editable_wheel and install_lib commands for legacy namespaces
-    namespace_packages: list[str]  #: :meta private: DEPRECATED
-
-    # Any: Dynamic assignment results in Incompatible types in assignment
-    def __init__(self, attrs: MutableMapping[str, Any] | None = None) -> None:
-        have_package_data = hasattr(self, "package_data")
-        if not have_package_data:
-            self.package_data: dict[str, list[str]] = {}
-        attrs = attrs or {}
-        self.dist_files: list[tuple[str, str, str]] = []
-        self.include_package_data: bool | None = None
-        self.exclude_package_data: dict[str, list[str]] | None = None
-        # Filter-out setuptools' specific options.
-        self.src_root: str | None = attrs.pop("src_root", None)
-        self.dependency_links: list[str] = attrs.pop('dependency_links', [])
-        self.setup_requires: list[str] = attrs.pop('setup_requires', [])
-        for ep in metadata.entry_points(group='distutils.setup_keywords'):
-            vars(self).setdefault(ep.name, None)
-
-        metadata_only = set(self._DISTUTILS_UNSUPPORTED_METADATA)
-        metadata_only -= {"install_requires", "extras_require"}
-        dist_attrs = {k: v for k, v in attrs.items() if k not in metadata_only}
-        _Distribution.__init__(self, dist_attrs)
-
-        # Private API (setuptools-use only, not restricted to Distribution)
-        # Stores files that are referenced by the configuration and need to be in the
-        # sdist (e.g. `version = file: VERSION.txt`)
-        self._referenced_files = set[str]()
-
-        self.set_defaults = ConfigDiscovery(self)
-
-        self._set_metadata_defaults(attrs)
-
-        self.metadata.version = self._normalize_version(self.metadata.version)
-        self._finalize_requires()
-
-    def _validate_metadata(self):
-        required = {"name"}
-        provided = {
-            key
-            for key in vars(self.metadata)
-            if getattr(self.metadata, key, None) is not None
-        }
-        missing = required - provided
-
-        if missing:
-            msg = f"Required package metadata is missing: {missing}"
-            raise DistutilsSetupError(msg)
-
-    def _set_metadata_defaults(self, attrs):
-        """
-        Fill-in missing metadata fields not supported by distutils.
-        Some fields may have been set by other tools (e.g. pbr).
-        Those fields (vars(self.metadata)) take precedence to
-        supplied attrs.
-        """
-        for option, default in self._DISTUTILS_UNSUPPORTED_METADATA.items():
-            vars(self.metadata).setdefault(option, attrs.get(option, default()))
-
-    @staticmethod
-    def _normalize_version(version):
-        from . import sic
-
-        if isinstance(version, numbers.Number):
-            # Some people apparently take "version number" too literally :)
-            version = str(version)
-        elif isinstance(version, sic) or version is None:
-            return version
-
-        normalized = str(Version(version))
-        if version != normalized:
-            InformationOnly.emit(f"Normalizing '{version}' to '{normalized}'")
-            return normalized
-        return version
-
-    def _finalize_requires(self):
-        """
-        Set `metadata.python_requires` and fix environment markers
-        in `install_requires` and `extras_require`.
-        """
-        if getattr(self, 'python_requires', None):
-            self.metadata.python_requires = self.python_requires
-
-        self._normalize_requires()
-        self.metadata.install_requires = self.install_requires
-        self.metadata.extras_require = self.extras_require
-
-        if self.extras_require:
-            for extra in self.extras_require.keys():
-                # Setuptools allows a weird ": syntax for extras
-                extra = extra.split(':')[0]
-                if extra:
-                    self.metadata.provides_extras.setdefault(extra)
-
-    def _normalize_requires(self):
-        """Make sure requirement-related attributes exist and are normalized"""
-        install_requires = getattr(self, "install_requires", None) or []
-        extras_require = getattr(self, "extras_require", None) or {}
-
-        # Preserve the "static"-ness of values parsed from config files
-        list_ = _static.List if _static.is_static(install_requires) else list
-        self.install_requires = list_(map(str, _reqs.parse(install_requires)))
-
-        dict_ = _static.Dict if _static.is_static(extras_require) else dict
-        self.extras_require = dict_(
-            (k, list(map(str, _reqs.parse(v or [])))) for k, v in extras_require.items()
-        )
-
-    def _finalize_license_expression(self) -> None:
-        """
-        Normalize license and license_expression.
-        >>> dist = Distribution({"license_expression": _static.Str("mit aNd  gpl-3.0-OR-later")})
-        >>> _static.is_static(dist.metadata.license_expression)
-        True
-        >>> dist._finalize_license_expression()
-        >>> _static.is_static(dist.metadata.license_expression)  # preserve "static-ness"
-        True
-        >>> print(dist.metadata.license_expression)
-        MIT AND GPL-3.0-or-later
-        """
-        classifiers = self.metadata.get_classifiers()
-        license_classifiers = [cl for cl in classifiers if cl.startswith("License :: ")]
-
-        license_expr = self.metadata.license_expression
-        if license_expr:
-            str_ = _static.Str if _static.is_static(license_expr) else str
-            normalized = str_(_canonicalize_license_expression(license_expr))
-            if license_expr != normalized:
-                InformationOnly.emit(f"Normalizing '{license_expr}' to '{normalized}'")
-                self.metadata.license_expression = normalized
-            if license_classifiers:
-                raise InvalidConfigError(
-                    "License classifiers have been superseded by license expressions "
-                    "(see https://peps.python.org/pep-0639/). Please remove:\n\n"
-                    + "\n".join(license_classifiers),
-                )
-        elif license_classifiers:
-            pypa_guides = "guides/writing-pyproject-toml/#license"
-            SetuptoolsDeprecationWarning.emit(
-                "License classifiers are deprecated.",
-                "Please consider removing the following classifiers in favor of a "
-                "SPDX license expression:\n\n" + "\n".join(license_classifiers),
-                see_url=f"https://packaging.python.org/en/latest/{pypa_guides}",
-                # Warning introduced on 2025-02-17
-                # TODO: Should we add a due date? It may affect old/unmaintained
-                #       packages in the ecosystem and cause problems...
-            )
-
-    def _finalize_license_files(self) -> None:
-        """Compute names of all license files which should be included."""
-        license_files: list[str] | None = self.metadata.license_files
-        patterns = license_files or []
-
-        license_file: str | None = self.metadata.license_file
-        if license_file and license_file not in patterns:
-            patterns.append(license_file)
-
-        if license_files is None and license_file is None:
-            # Default patterns match the ones wheel uses
-            # See https://wheel.readthedocs.io/en/stable/user_guide.html
-            # -> 'Including license files in the generated wheel file'
-            patterns = ['LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*']
-            files = self._expand_patterns(patterns, enforce_match=False)
-        else:  # Patterns explicitly given by the user
-            files = self._expand_patterns(patterns, enforce_match=True)
-
-        self.metadata.license_files = list(unique_everseen(files))
-
-    @classmethod
-    def _expand_patterns(
-        cls, patterns: list[str], enforce_match: bool = True
-    ) -> Iterator[str]:
-        """
-        >>> list(Distribution._expand_patterns(['LICENSE']))
-        ['LICENSE']
-        >>> list(Distribution._expand_patterns(['pyproject.toml', 'LIC*']))
-        ['pyproject.toml', 'LICENSE']
-        >>> list(Distribution._expand_patterns(['setuptools/**/pyprojecttoml.py']))
-        ['setuptools/config/pyprojecttoml.py']
-        """
-        return (
-            path.replace(os.sep, "/")
-            for pattern in patterns
-            for path in sorted(cls._find_pattern(pattern, enforce_match))
-            if not path.endswith('~') and os.path.isfile(path)
-        )
-
-    @staticmethod
-    def _find_pattern(pattern: str, enforce_match: bool = True) -> list[str]:
-        r"""
-        >>> Distribution._find_pattern("LICENSE")
-        ['LICENSE']
-        >>> Distribution._find_pattern("/LICENSE.MIT")
-        Traceback (most recent call last):
-        ...
-        setuptools.errors.InvalidConfigError: Pattern '/LICENSE.MIT' should be relative...
-        >>> Distribution._find_pattern("../LICENSE.MIT")
-        Traceback (most recent call last):
-        ...
-        setuptools.warnings.SetuptoolsDeprecationWarning: ...Pattern '../LICENSE.MIT' cannot contain '..'...
-        >>> Distribution._find_pattern("LICEN{CSE*")
-        Traceback (most recent call last):
-        ...
-        setuptools.warnings.SetuptoolsDeprecationWarning: ...Pattern 'LICEN{CSE*' contains invalid characters...
-        """
-        pypa_guides = "specifications/glob-patterns/"
-        if ".." in pattern:
-            SetuptoolsDeprecationWarning.emit(
-                f"Pattern {pattern!r} cannot contain '..'",
-                """
-                Please ensure the files specified are contained by the root
-                of the Python package (normally marked by `pyproject.toml`).
-                """,
-                see_url=f"https://packaging.python.org/en/latest/{pypa_guides}",
-                due_date=(2026, 3, 20),  # Introduced in 2025-03-20
-                # Replace with InvalidConfigError after deprecation
-            )
-        if pattern.startswith((os.sep, "/")) or ":\\" in pattern:
-            raise InvalidConfigError(
-                f"Pattern {pattern!r} should be relative and must not start with '/'"
-            )
-        if re.match(r'^[\w\-\.\/\*\?\[\]]+$', pattern) is None:
-            SetuptoolsDeprecationWarning.emit(
-                "Please provide a valid glob pattern.",
-                "Pattern {pattern!r} contains invalid characters.",
-                pattern=pattern,
-                see_url=f"https://packaging.python.org/en/latest/{pypa_guides}",
-                due_date=(2026, 3, 20),  # Introduced in 2025-02-20
-            )
-
-        found = glob(pattern, recursive=True)
-
-        if enforce_match and not found:
-            SetuptoolsDeprecationWarning.emit(
-                "Cannot find any files for the given pattern.",
-                "Pattern {pattern!r} did not match any files.",
-                pattern=pattern,
-                due_date=(2026, 3, 20),  # Introduced in 2025-02-20
-                # PEP 639 requires us to error, but as a transition period
-                # we will only issue a warning to give people time to prepare.
-                # After the transition, this should raise an InvalidConfigError.
-            )
-        return found
-
-    # FIXME: 'Distribution._parse_config_files' is too complex (14)
-    def _parse_config_files(self, filenames=None):  # noqa: C901
-        """
-        Adapted from distutils.dist.Distribution.parse_config_files,
-        this method provides the same functionality in subtly-improved
-        ways.
-        """
-        from configparser import ConfigParser
-
-        # Ignore install directory options if we have a venv
-        ignore_options = (
-            []
-            if sys.prefix == sys.base_prefix
-            else [
-                'install-base',
-                'install-platbase',
-                'install-lib',
-                'install-platlib',
-                'install-purelib',
-                'install-headers',
-                'install-scripts',
-                'install-data',
-                'prefix',
-                'exec-prefix',
-                'home',
-                'user',
-                'root',
-            ]
-        )
-
-        ignore_options = frozenset(ignore_options)
-
-        if filenames is None:
-            filenames = self.find_config_files()
-
-        if DEBUG:
-            self.announce("Distribution.parse_config_files():")
-
-        parser = ConfigParser()
-        parser.optionxform = str
-        for filename in filenames:
-            with open(filename, encoding='utf-8') as reader:
-                if DEBUG:
-                    self.announce("  reading {filename}".format(**locals()))
-                parser.read_file(reader)
-            for section in parser.sections():
-                options = parser.options(section)
-                opt_dict = self.get_option_dict(section)
-
-                for opt in options:
-                    if opt == '__name__' or opt in ignore_options:
-                        continue
-
-                    val = parser.get(section, opt)
-                    opt = self._enforce_underscore(opt, section)
-                    opt = self._enforce_option_lowercase(opt, section)
-                    opt_dict[opt] = (filename, val)
-
-            # Make the ConfigParser forget everything (so we retain
-            # the original filenames that options come from)
-            parser.__init__()
-
-        if 'global' not in self.command_options:
-            return
-
-        # If there was a "global" section in the config file, use it
-        # to set Distribution options.
-
-        for opt, (src, val) in self.command_options['global'].items():
-            alias = self.negative_opt.get(opt)
-            if alias:
-                val = not strtobool(val)
-            elif opt in ('verbose', 'dry_run'):  # ugh!
-                val = strtobool(val)
-
-            try:
-                setattr(self, alias or opt, val)
-            except ValueError as e:
-                raise DistutilsOptionError(e) from e
-
-    def _enforce_underscore(self, opt: str, section: str) -> str:
-        if "-" not in opt or self._skip_setupcfg_normalization(section):
-            return opt
-
-        underscore_opt = opt.replace('-', '_')
-        affected = f"(Affected: {self.metadata.name})." if self.metadata.name else ""
-        SetuptoolsDeprecationWarning.emit(
-            f"Invalid dash-separated key {opt!r} in {section!r} (setup.cfg), "
-            f"please use the underscore name {underscore_opt!r} instead.",
-            f"""
-            Usage of dash-separated {opt!r} will not be supported in future
-            versions. Please use the underscore name {underscore_opt!r} instead.
-            {affected}
-            """,
-            see_docs="userguide/declarative_config.html",
-            due_date=(2026, 3, 3),
-            # Warning initially introduced in 3 Mar 2021
-        )
-        return underscore_opt
-
-    def _enforce_option_lowercase(self, opt: str, section: str) -> str:
-        if opt.islower() or self._skip_setupcfg_normalization(section):
-            return opt
-
-        lowercase_opt = opt.lower()
-        affected = f"(Affected: {self.metadata.name})." if self.metadata.name else ""
-        SetuptoolsDeprecationWarning.emit(
-            f"Invalid uppercase key {opt!r} in {section!r} (setup.cfg), "
-            f"please use lowercase {lowercase_opt!r} instead.",
-            f"""
-            Usage of uppercase key {opt!r} in {section!r} will not be supported in
-            future versions. Please use lowercase {lowercase_opt!r} instead.
-            {affected}
-            """,
-            see_docs="userguide/declarative_config.html",
-            due_date=(2026, 3, 3),
-            # Warning initially introduced in 6 Mar 2021
-        )
-        return lowercase_opt
-
-    def _skip_setupcfg_normalization(self, section: str) -> bool:
-        skip = (
-            'options.extras_require',
-            'options.data_files',
-            'options.entry_points',
-            'options.package_data',
-            'options.exclude_package_data',
-        )
-        return section in skip or not self._is_setuptools_section(section)
-
-    def _is_setuptools_section(self, section: str) -> bool:
-        return (
-            section == "metadata"
-            or section.startswith("options")
-            or section in _setuptools_commands()
-        )
-
-    # FIXME: 'Distribution._set_command_options' is too complex (14)
-    def _set_command_options(self, command_obj, option_dict=None):  # noqa: C901
-        """
-        Set the options for 'command_obj' from 'option_dict'.  Basically
-        this means copying elements of a dictionary ('option_dict') to
-        attributes of an instance ('command').
-
-        'command_obj' must be a Command instance.  If 'option_dict' is not
-        supplied, uses the standard option dictionary for this command
-        (from 'self.command_options').
-
-        (Adopted from distutils.dist.Distribution._set_command_options)
-        """
-        command_name = command_obj.get_command_name()
-        if option_dict is None:
-            option_dict = self.get_option_dict(command_name)
-
-        if DEBUG:
-            self.announce(f"  setting options for '{command_name}' command:")
-        for option, (source, value) in option_dict.items():
-            if DEBUG:
-                self.announce(f"    {option} = {value} (from {source})")
-            try:
-                bool_opts = [translate_longopt(o) for o in command_obj.boolean_options]
-            except AttributeError:
-                bool_opts = []
-            try:
-                neg_opt = command_obj.negative_opt
-            except AttributeError:
-                neg_opt = {}
-
-            try:
-                is_string = isinstance(value, str)
-                if option in neg_opt and is_string:
-                    setattr(command_obj, neg_opt[option], not strtobool(value))
-                elif option in bool_opts and is_string:
-                    setattr(command_obj, option, strtobool(value))
-                elif hasattr(command_obj, option):
-                    setattr(command_obj, option, value)
-                else:
-                    raise DistutilsOptionError(
-                        f"error in {source}: command '{command_name}' has no such option '{option}'"
-                    )
-            except ValueError as e:
-                raise DistutilsOptionError(e) from e
-
-    def _get_project_config_files(self, filenames: Iterable[StrPath] | None):
-        """Add default file and split between INI and TOML"""
-        tomlfiles = []
-        standard_project_metadata = Path(self.src_root or os.curdir, "pyproject.toml")
-        if filenames is not None:
-            parts = partition(lambda f: Path(f).suffix == ".toml", filenames)
-            filenames = list(parts[0])  # 1st element => predicate is False
-            tomlfiles = list(parts[1])  # 2nd element => predicate is True
-        elif standard_project_metadata.exists():
-            tomlfiles = [standard_project_metadata]
-        return filenames, tomlfiles
-
-    def parse_config_files(
-        self,
-        filenames: Iterable[StrPath] | None = None,
-        ignore_option_errors: bool = False,
-    ) -> None:
-        """Parses configuration files from various levels
-        and loads configuration.
-        """
-        inifiles, tomlfiles = self._get_project_config_files(filenames)
-
-        self._parse_config_files(filenames=inifiles)
-
-        setupcfg.parse_configuration(
-            self, self.command_options, ignore_option_errors=ignore_option_errors
-        )
-        for filename in tomlfiles:
-            pyprojecttoml.apply_configuration(self, filename, ignore_option_errors)
-
-        self._finalize_requires()
-        self._finalize_license_expression()
-        self._finalize_license_files()
-
-    def fetch_build_eggs(
-        self, requires: _StrOrIter
-    ) -> list[_pkg_resources_Distribution]:
-        """Resolve pre-setup requirements"""
-        from .installer import _fetch_build_eggs
-
-        return _fetch_build_eggs(self, requires)
-
-    def finalize_options(self) -> None:
-        """
-        Allow plugins to apply arbitrary operations to the
-        distribution. Each hook may optionally define a 'order'
-        to influence the order of execution. Smaller numbers
-        go first and the default is 0.
-        """
-        group = 'setuptools.finalize_distribution_options'
-
-        def by_order(hook):
-            return getattr(hook, 'order', 0)
-
-        defined = metadata.entry_points(group=group)
-        filtered = itertools.filterfalse(self._removed, defined)
-        loaded = map(lambda e: e.load(), filtered)
-        for ep in sorted(loaded, key=by_order):
-            ep(self)
-
-    @staticmethod
-    def _removed(ep):
-        """
-        When removing an entry point, if metadata is loaded
-        from an older version of Setuptools, that removed
-        entry point will attempt to be loaded and will fail.
-        See #2765 for more details.
-        """
-        removed = {
-            # removed 2021-09-05
-            '2to3_doctests',
-        }
-        return ep.name in removed
-
-    def _finalize_setup_keywords(self):
-        for ep in metadata.entry_points(group='distutils.setup_keywords'):
-            value = getattr(self, ep.name, None)
-            if value is not None:
-                ep.load()(self, ep.name, value)
-
-    def get_egg_cache_dir(self):
-        from . import windows_support
-
-        egg_cache_dir = os.path.join(os.curdir, '.eggs')
-        if not os.path.exists(egg_cache_dir):
-            os.mkdir(egg_cache_dir)
-            windows_support.hide_file(egg_cache_dir)
-            readme_txt_filename = os.path.join(egg_cache_dir, 'README.txt')
-            with open(readme_txt_filename, 'w', encoding="utf-8") as f:
-                f.write(
-                    'This directory contains eggs that were downloaded '
-                    'by setuptools to build, test, and run plug-ins.\n\n'
-                )
-                f.write(
-                    'This directory caches those eggs to prevent '
-                    'repeated downloads.\n\n'
-                )
-                f.write('However, it is safe to delete this directory.\n\n')
-
-        return egg_cache_dir
-
-    def fetch_build_egg(self, req):
-        """Fetch an egg needed for building"""
-        from .installer import fetch_build_egg
-
-        return fetch_build_egg(self, req)
-
-    def get_command_class(self, command: str) -> type[distutils.cmd.Command]:  # type: ignore[override] # Not doing complex overrides yet
-        """Pluggable version of get_command_class()"""
-        if command in self.cmdclass:
-            return self.cmdclass[command]
-
-        # Special case bdist_wheel so it's never loaded from "wheel"
-        if command == 'bdist_wheel':
-            from .command.bdist_wheel import bdist_wheel
-
-            return bdist_wheel
-
-        eps = metadata.entry_points(group='distutils.commands', name=command)
-        for ep in eps:
-            self.cmdclass[command] = cmdclass = ep.load()
-            return cmdclass
-        else:
-            return _Distribution.get_command_class(self, command)
-
-    def print_commands(self):
-        for ep in metadata.entry_points(group='distutils.commands'):
-            if ep.name not in self.cmdclass:
-                cmdclass = ep.load()
-                self.cmdclass[ep.name] = cmdclass
-        return _Distribution.print_commands(self)
-
-    def get_command_list(self):
-        for ep in metadata.entry_points(group='distutils.commands'):
-            if ep.name not in self.cmdclass:
-                cmdclass = ep.load()
-                self.cmdclass[ep.name] = cmdclass
-        return _Distribution.get_command_list(self)
-
-    def include(self, **attrs) -> None:
-        """Add items to distribution that are named in keyword arguments
-
-        For example, 'dist.include(py_modules=["x"])' would add 'x' to
-        the distribution's 'py_modules' attribute, if it was not already
-        there.
-
-        Currently, this method only supports inclusion for attributes that are
-        lists or tuples.  If you need to add support for adding to other
-        attributes in this or a subclass, you can add an '_include_X' method,
-        where 'X' is the name of the attribute.  The method will be called with
-        the value passed to 'include()'.  So, 'dist.include(foo={"bar":"baz"})'
-        will try to call 'dist._include_foo({"bar":"baz"})', which can then
-        handle whatever special inclusion logic is needed.
-        """
-        for k, v in attrs.items():
-            include = getattr(self, '_include_' + k, None)
-            if include:
-                include(v)
-            else:
-                self._include_misc(k, v)
-
-    def exclude_package(self, package: str) -> None:
-        """Remove packages, modules, and extensions in named package"""
-
-        pfx = package + '.'
-        if self.packages:
-            self.packages = [
-                p for p in self.packages if p != package and not p.startswith(pfx)
-            ]
-
-        if self.py_modules:
-            self.py_modules = [
-                p for p in self.py_modules if p != package and not p.startswith(pfx)
-            ]
-
-        if self.ext_modules:
-            self.ext_modules = [
-                p
-                for p in self.ext_modules
-                if p.name != package and not p.name.startswith(pfx)
-            ]
-
-    def has_contents_for(self, package: str) -> bool:
-        """Return true if 'exclude_package(package)' would do something"""
-
-        pfx = package + '.'
-
-        for p in self.iter_distribution_names():
-            if p == package or p.startswith(pfx):
-                return True
-
-        return False
-
-    def _exclude_misc(self, name: str, value: _Sequence) -> None:
-        """Handle 'exclude()' for list/tuple attrs without a special handler"""
-        if not isinstance(value, _sequence):
-            raise DistutilsSetupError(
-                f"{name}: setting must be of type <{_sequence_type_repr}> (got {value!r})"
-            )
-        try:
-            old = getattr(self, name)
-        except AttributeError as e:
-            raise DistutilsSetupError(f"{name}: No such distribution setting") from e
-        if old is not None and not isinstance(old, _sequence):
-            raise DistutilsSetupError(
-                name + ": this setting cannot be changed via include/exclude"
-            )
-        elif old:
-            setattr(self, name, [item for item in old if item not in value])
-
-    def _include_misc(self, name: str, value: _Sequence) -> None:
-        """Handle 'include()' for list/tuple attrs without a special handler"""
-
-        if not isinstance(value, _sequence):
-            raise DistutilsSetupError(
-                f"{name}: setting must be of type <{_sequence_type_repr}> (got {value!r})"
-            )
-        try:
-            old = getattr(self, name)
-        except AttributeError as e:
-            raise DistutilsSetupError(f"{name}: No such distribution setting") from e
-        if old is None:
-            setattr(self, name, value)
-        elif not isinstance(old, _sequence):
-            raise DistutilsSetupError(
-                name + ": this setting cannot be changed via include/exclude"
-            )
-        else:
-            new = [item for item in value if item not in old]
-            setattr(self, name, list(old) + new)
-
-    def exclude(self, **attrs) -> None:
-        """Remove items from distribution that are named in keyword arguments
-
-        For example, 'dist.exclude(py_modules=["x"])' would remove 'x' from
-        the distribution's 'py_modules' attribute.  Excluding packages uses
-        the 'exclude_package()' method, so all of the package's contained
-        packages, modules, and extensions are also excluded.
-
-        Currently, this method only supports exclusion from attributes that are
-        lists or tuples.  If you need to add support for excluding from other
-        attributes in this or a subclass, you can add an '_exclude_X' method,
-        where 'X' is the name of the attribute.  The method will be called with
-        the value passed to 'exclude()'.  So, 'dist.exclude(foo={"bar":"baz"})'
-        will try to call 'dist._exclude_foo({"bar":"baz"})', which can then
-        handle whatever special exclusion logic is needed.
-        """
-        for k, v in attrs.items():
-            exclude = getattr(self, '_exclude_' + k, None)
-            if exclude:
-                exclude(v)
-            else:
-                self._exclude_misc(k, v)
-
-    def _exclude_packages(self, packages: _Sequence) -> None:
-        if not isinstance(packages, _sequence):
-            raise DistutilsSetupError(
-                f"packages: setting must be of type <{_sequence_type_repr}> (got {packages!r})"
-            )
-        list(map(self.exclude_package, packages))
-
-    def _parse_command_opts(self, parser, args):
-        # Remove --with-X/--without-X options when processing command args
-        self.global_options = self.__class__.global_options
-        self.negative_opt = self.__class__.negative_opt
-
-        # First, expand any aliases
-        command = args[0]
-        aliases = self.get_option_dict('aliases')
-        while command in aliases:
-            _src, alias = aliases[command]
-            del aliases[command]  # ensure each alias can expand only once!
-            import shlex
-
-            args[:1] = shlex.split(alias, True)
-            command = args[0]
-
-        nargs = _Distribution._parse_command_opts(self, parser, args)
-
-        # Handle commands that want to consume all remaining arguments
-        cmd_class = self.get_command_class(command)
-        if getattr(cmd_class, 'command_consumes_arguments', None):
-            self.get_option_dict(command)['args'] = ("command line", nargs)
-            if nargs is not None:
-                return []
-
-        return nargs
-
-    def get_cmdline_options(self) -> dict[str, dict[str, str | None]]:
-        """Return a '{cmd: {opt:val}}' map of all command-line options
-
-        Option names are all long, but do not include the leading '--', and
-        contain dashes rather than underscores.  If the option doesn't take
-        an argument (e.g. '--quiet'), the 'val' is 'None'.
-
-        Note that options provided by config files are intentionally excluded.
-        """
-
-        d: dict[str, dict[str, str | None]] = {}
-
-        for cmd, opts in self.command_options.items():
-            val: str | None
-            for opt, (src, val) in opts.items():
-                if src != "command line":
-                    continue
-
-                opt = opt.replace('_', '-')
-
-                if val == 0:
-                    cmdobj = self.get_command_obj(cmd)
-                    neg_opt = self.negative_opt.copy()
-                    neg_opt.update(getattr(cmdobj, 'negative_opt', {}))
-                    for neg, pos in neg_opt.items():
-                        if pos == opt:
-                            opt = neg
-                            val = None
-                            break
-                    else:
-                        raise AssertionError("Shouldn't be able to get here")
-
-                elif val == 1:
-                    val = None
-
-                d.setdefault(cmd, {})[opt] = val
-
-        return d
-
-    def iter_distribution_names(self):
-        """Yield all packages, modules, and extension names in distribution"""
-
-        yield from self.packages or ()
-
-        yield from self.py_modules or ()
-
-        for ext in self.ext_modules or ():
-            if isinstance(ext, tuple):
-                name, _buildinfo = ext
-            else:
-                name = ext.name
-            if name.endswith('module'):
-                name = name[:-6]
-            yield name
-
-    def handle_display_options(self, option_order):
-        """If there were any non-global "display-only" options
-        (--help-commands or the metadata display options) on the command
-        line, display the requested info and return true; else return
-        false.
-        """
-        import sys
-
-        if self.help_commands:
-            return _Distribution.handle_display_options(self, option_order)
-
-        # Stdout may be StringIO (e.g. in tests)
-        if not isinstance(sys.stdout, io.TextIOWrapper):
-            return _Distribution.handle_display_options(self, option_order)
-
-        # Don't wrap stdout if utf-8 is already the encoding. Provides
-        #  workaround for #334.
-        if sys.stdout.encoding.lower() in ('utf-8', 'utf8'):
-            return _Distribution.handle_display_options(self, option_order)
-
-        # Print metadata in UTF-8 no matter the platform
-        encoding = sys.stdout.encoding
-        sys.stdout.reconfigure(encoding='utf-8')
-        try:
-            return _Distribution.handle_display_options(self, option_order)
-        finally:
-            sys.stdout.reconfigure(encoding=encoding)
-
-    def run_command(self, command) -> None:
-        self.set_defaults()
-        # Postpone defaults until all explicit configuration is considered
-        # (setup() args, config files, command line and plugins)
-
-        super().run_command(command)
-
-
-@functools.cache
-def _setuptools_commands() -> set[str]:
-    try:
-        # Use older API for importlib.metadata compatibility
-        entry_points = metadata.distribution('setuptools').entry_points
-        eps: Iterable[str] = (ep.name for ep in entry_points)
-    except metadata.PackageNotFoundError:
-        # during bootstrapping, distribution doesn't exist
-        eps = []
-    return {*distutils.command.__all__, *eps}
-
-
-class DistDeprecationWarning(SetuptoolsDeprecationWarning):
-    """Class for warning about deprecations in dist in
-    setuptools. Not ignored by default, unlike DeprecationWarning."""
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/errors.py b/llmlab/lib/python3.12/site-packages/setuptools/errors.py
deleted file mode 100644
index 990ecbf..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/errors.py
+++ /dev/null
@@ -1,67 +0,0 @@
-"""setuptools.errors
-
-Provides exceptions used by setuptools modules.
-"""
-
-from __future__ import annotations
-
-from distutils import errors as _distutils_errors
-
-# Re-export errors from distutils to facilitate the migration to PEP632
-
-ByteCompileError = _distutils_errors.DistutilsByteCompileError
-CCompilerError = _distutils_errors.CCompilerError
-ClassError = _distutils_errors.DistutilsClassError
-CompileError = _distutils_errors.CompileError
-ExecError = _distutils_errors.DistutilsExecError
-FileError = _distutils_errors.DistutilsFileError
-InternalError = _distutils_errors.DistutilsInternalError
-LibError = _distutils_errors.LibError
-LinkError = _distutils_errors.LinkError
-ModuleError = _distutils_errors.DistutilsModuleError
-OptionError = _distutils_errors.DistutilsOptionError
-PlatformError = _distutils_errors.DistutilsPlatformError
-PreprocessError = _distutils_errors.PreprocessError
-SetupError = _distutils_errors.DistutilsSetupError
-TemplateError = _distutils_errors.DistutilsTemplateError
-UnknownFileError = _distutils_errors.UnknownFileError
-
-# The root error class in the hierarchy
-BaseError = _distutils_errors.DistutilsError
-
-
-class InvalidConfigError(OptionError):  # type: ignore[valid-type, misc] # distutils imports are `Any` on python 3.12+
-    """Error used for invalid configurations."""
-
-
-class RemovedConfigError(OptionError):  # type: ignore[valid-type, misc] # distutils imports are `Any` on python 3.12+
-    """Error used for configurations that were deprecated and removed."""
-
-
-class RemovedCommandError(BaseError, RuntimeError):  # type: ignore[valid-type, misc] # distutils imports are `Any` on python 3.12+
-    """Error used for commands that have been removed in setuptools.
-
-    Since ``setuptools`` is built on ``distutils``, simply removing a command
-    from ``setuptools`` will make the behavior fall back to ``distutils``; this
-    error is raised if a command exists in ``distutils`` but has been actively
-    removed in ``setuptools``.
-    """
-
-
-class PackageDiscoveryError(BaseError, RuntimeError):  # type: ignore[valid-type, misc] # distutils imports are `Any` on python 3.12+
-    """Impossible to perform automatic discovery of packages and/or modules.
-
-    The current project layout or given discovery options can lead to problems when
-    scanning the project directory.
-
-    Setuptools might also refuse to complete auto-discovery if an error prone condition
-    is detected (e.g. when a project is organised as a flat-layout but contains
-    multiple directories that can be taken as top-level packages inside a single
-    distribution [*]_). In these situations the users are encouraged to be explicit
-    about which packages to include or to make the discovery parameters more specific.
-
-    .. [*] Since multi-package distributions are uncommon it is very likely that the
-       developers did not intend for all the directories to be packaged, and are just
-       leaving auxiliary code in the repository top-level, such as maintenance-related
-       scripts.
-    """
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/extension.py b/llmlab/lib/python3.12/site-packages/setuptools/extension.py
deleted file mode 100644
index 76e03d9..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/extension.py
+++ /dev/null
@@ -1,177 +0,0 @@
-from __future__ import annotations
-
-import functools
-import re
-from typing import TYPE_CHECKING
-
-from setuptools._path import StrPath
-
-from .monkey import get_unpatched
-
-import distutils.core
-import distutils.errors
-import distutils.extension
-
-
-def _have_cython():
-    """
-    Return True if Cython can be imported.
-    """
-    cython_impl = 'Cython.Distutils.build_ext'
-    try:
-        # from (cython_impl) import build_ext
-        __import__(cython_impl, fromlist=['build_ext']).build_ext
-    except Exception:
-        return False
-    return True
-
-
-# for compatibility
-have_pyrex = _have_cython
-if TYPE_CHECKING:
-    # Work around a mypy issue where type[T] can't be used as a base: https://github.com/python/mypy/issues/10962
-    from distutils.core import Extension as _Extension
-else:
-    _Extension = get_unpatched(distutils.core.Extension)
-
-
-class Extension(_Extension):
-    """
-    Describes a single extension module.
-
-    This means that all source files will be compiled into a single binary file
-    ``.`` (with ```` derived from ``name`` and
-    ```` defined by one of the values in
-    ``importlib.machinery.EXTENSION_SUFFIXES``).
-
-    In the case ``.pyx`` files are passed as ``sources and`` ``Cython`` is **not**
-    installed in the build environment, ``setuptools`` may also try to look for the
-    equivalent ``.cpp`` or ``.c`` files.
-
-    :arg str name:
-      the full name of the extension, including any packages -- ie.
-      *not* a filename or pathname, but Python dotted name
-
-    :arg list[str|os.PathLike[str]] sources:
-      list of source filenames, relative to the distribution root
-      (where the setup script lives), in Unix form (slash-separated)
-      for portability.  Source files may be C, C++, SWIG (.i),
-      platform-specific resource files, or whatever else is recognized
-      by the "build_ext" command as source for a Python extension.
-
-    :keyword list[str] include_dirs:
-      list of directories to search for C/C++ header files (in Unix
-      form for portability)
-
-    :keyword list[tuple[str, str|None]] define_macros:
-      list of macros to define; each macro is defined using a 2-tuple:
-      the first item corresponding to the name of the macro and the second
-      item either a string with its value or None to
-      define it without a particular value (equivalent of "#define
-      FOO" in source or -DFOO on Unix C compiler command line)
-
-    :keyword list[str] undef_macros:
-      list of macros to undefine explicitly
-
-    :keyword list[str] library_dirs:
-      list of directories to search for C/C++ libraries at link time
-
-    :keyword list[str] libraries:
-      list of library names (not filenames or paths) to link against
-
-    :keyword list[str] runtime_library_dirs:
-      list of directories to search for C/C++ libraries at run time
-      (for shared extensions, this is when the extension is loaded).
-      Setting this will cause an exception during build on Windows
-      platforms.
-
-    :keyword list[str] extra_objects:
-      list of extra files to link with (eg. object files not implied
-      by 'sources', static library that must be explicitly specified,
-      binary resource files, etc.)
-
-    :keyword list[str] extra_compile_args:
-      any extra platform- and compiler-specific information to use
-      when compiling the source files in 'sources'.  For platforms and
-      compilers where "command line" makes sense, this is typically a
-      list of command-line arguments, but for other platforms it could
-      be anything.
-
-    :keyword list[str] extra_link_args:
-      any extra platform- and compiler-specific information to use
-      when linking object files together to create the extension (or
-      to create a new static Python interpreter).  Similar
-      interpretation as for 'extra_compile_args'.
-
-    :keyword list[str] export_symbols:
-      list of symbols to be exported from a shared extension.  Not
-      used on all platforms, and not generally necessary for Python
-      extensions, which typically export exactly one symbol: "init" +
-      extension_name.
-
-    :keyword list[str] swig_opts:
-      any extra options to pass to SWIG if a source file has the .i
-      extension.
-
-    :keyword list[str] depends:
-      list of files that the extension depends on
-
-    :keyword str language:
-      extension language (i.e. "c", "c++", "objc"). Will be detected
-      from the source extensions if not provided.
-
-    :keyword bool optional:
-      specifies that a build failure in the extension should not abort the
-      build process, but simply not install the failing extension.
-
-    :keyword bool py_limited_api:
-      opt-in flag for the usage of :doc:`Python's limited API `.
-
-    :raises setuptools.errors.PlatformError: if ``runtime_library_dirs`` is
-      specified on Windows. (since v63)
-    """
-
-    # These 4 are set and used in setuptools/command/build_ext.py
-    # The lack of a default value and risk of `AttributeError` is purposeful
-    # to avoid people forgetting to call finalize_options if they modify the extension list.
-    # See example/rationale in https://github.com/pypa/setuptools/issues/4529.
-    _full_name: str  #: Private API, internal use only.
-    _links_to_dynamic: bool  #: Private API, internal use only.
-    _needs_stub: bool  #: Private API, internal use only.
-    _file_name: str  #: Private API, internal use only.
-
-    def __init__(
-        self,
-        name: str,
-        sources: list[StrPath],
-        *args,
-        py_limited_api: bool = False,
-        **kw,
-    ) -> None:
-        # The *args is needed for compatibility as calls may use positional
-        # arguments. py_limited_api may be set only via keyword.
-        self.py_limited_api = py_limited_api
-        super().__init__(
-            name,
-            sources,  # type: ignore[arg-type] # Vendored version of setuptools supports PathLike
-            *args,
-            **kw,
-        )
-
-    def _convert_pyx_sources_to_lang(self):
-        """
-        Replace sources with .pyx extensions to sources with the target
-        language extension. This mechanism allows language authors to supply
-        pre-converted sources but to prefer the .pyx sources.
-        """
-        if _have_cython():
-            # the build has Cython, so allow it to compile the .pyx files
-            return
-        lang = self.language or ''
-        target_ext = '.cpp' if lang.lower() == 'c++' else '.c'
-        sub = functools.partial(re.sub, '.pyx$', target_ext)
-        self.sources = list(map(sub, self.sources))
-
-
-class Library(Extension):
-    """Just like a regular Extension, but built as a library instead"""
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/glob.py b/llmlab/lib/python3.12/site-packages/setuptools/glob.py
deleted file mode 100644
index 1dfff2c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/glob.py
+++ /dev/null
@@ -1,185 +0,0 @@
-"""
-Filename globbing utility. Mostly a copy of `glob` from Python 3.5.
-
-Changes include:
- * `yield from` and PEP3102 `*` removed.
- * Hidden files are not ignored.
-"""
-
-from __future__ import annotations
-
-import fnmatch
-import os
-import re
-from collections.abc import Iterable, Iterator
-from typing import TYPE_CHECKING, AnyStr, overload
-
-if TYPE_CHECKING:
-    from _typeshed import BytesPath, StrOrBytesPath, StrPath
-
-__all__ = ["glob", "iglob", "escape"]
-
-
-def glob(pathname: AnyStr, recursive: bool = False) -> list[AnyStr]:
-    """Return a list of paths matching a pathname pattern.
-
-    The pattern may contain simple shell-style wildcards a la
-    fnmatch. However, unlike fnmatch, filenames starting with a
-    dot are special cases that are not matched by '*' and '?'
-    patterns.
-
-    If recursive is true, the pattern '**' will match any files and
-    zero or more directories and subdirectories.
-    """
-    return list(iglob(pathname, recursive=recursive))
-
-
-def iglob(pathname: AnyStr, recursive: bool = False) -> Iterator[AnyStr]:
-    """Return an iterator which yields the paths matching a pathname pattern.
-
-    The pattern may contain simple shell-style wildcards a la
-    fnmatch. However, unlike fnmatch, filenames starting with a
-    dot are special cases that are not matched by '*' and '?'
-    patterns.
-
-    If recursive is true, the pattern '**' will match any files and
-    zero or more directories and subdirectories.
-    """
-    it = _iglob(pathname, recursive)
-    if recursive and _isrecursive(pathname):
-        s = next(it)  # skip empty string
-        assert not s
-    return it
-
-
-def _iglob(pathname: AnyStr, recursive: bool) -> Iterator[AnyStr]:
-    dirname, basename = os.path.split(pathname)
-    glob_in_dir = glob2 if recursive and _isrecursive(basename) else glob1
-
-    if not has_magic(pathname):
-        if basename:
-            if os.path.lexists(pathname):
-                yield pathname
-        else:
-            # Patterns ending with a slash should match only directories
-            if os.path.isdir(dirname):
-                yield pathname
-        return
-
-    if not dirname:
-        yield from glob_in_dir(dirname, basename)
-        return
-    # `os.path.split()` returns the argument itself as a dirname if it is a
-    # drive or UNC path.  Prevent an infinite recursion if a drive or UNC path
-    # contains magic characters (i.e. r'\\?\C:').
-    if dirname != pathname and has_magic(dirname):
-        dirs: Iterable[AnyStr] = _iglob(dirname, recursive)
-    else:
-        dirs = [dirname]
-    if not has_magic(basename):
-        glob_in_dir = glob0
-    for dirname in dirs:
-        for name in glob_in_dir(dirname, basename):
-            yield os.path.join(dirname, name)
-
-
-# These 2 helper functions non-recursively glob inside a literal directory.
-# They return a list of basenames. `glob1` accepts a pattern while `glob0`
-# takes a literal basename (so it only has to check for its existence).
-
-
-@overload
-def glob1(dirname: StrPath, pattern: str) -> list[str]: ...
-@overload
-def glob1(dirname: BytesPath, pattern: bytes) -> list[bytes]: ...
-def glob1(dirname: StrOrBytesPath, pattern: str | bytes) -> list[str] | list[bytes]:
-    if not dirname:
-        if isinstance(pattern, bytes):
-            dirname = os.curdir.encode('ASCII')
-        else:
-            dirname = os.curdir
-    try:
-        names = os.listdir(dirname)
-    except OSError:
-        return []
-    # mypy false-positives: str or bytes type possibility is always kept in sync
-    return fnmatch.filter(names, pattern)  # type: ignore[type-var, return-value]
-
-
-def glob0(dirname, basename):
-    if not basename:
-        # `os.path.split()` returns an empty basename for paths ending with a
-        # directory separator.  'q*x/' should match only directories.
-        if os.path.isdir(dirname):
-            return [basename]
-    else:
-        if os.path.lexists(os.path.join(dirname, basename)):
-            return [basename]
-    return []
-
-
-# This helper function recursively yields relative pathnames inside a literal
-# directory.
-
-
-@overload
-def glob2(dirname: StrPath, pattern: str) -> Iterator[str]: ...
-@overload
-def glob2(dirname: BytesPath, pattern: bytes) -> Iterator[bytes]: ...
-def glob2(dirname: StrOrBytesPath, pattern: str | bytes) -> Iterator[str | bytes]:
-    assert _isrecursive(pattern)
-    yield pattern[:0]
-    yield from _rlistdir(dirname)
-
-
-# Recursively yields relative pathnames inside a literal directory.
-@overload
-def _rlistdir(dirname: StrPath) -> Iterator[str]: ...
-@overload
-def _rlistdir(dirname: BytesPath) -> Iterator[bytes]: ...
-def _rlistdir(dirname: StrOrBytesPath) -> Iterator[str | bytes]:
-    if not dirname:
-        if isinstance(dirname, bytes):
-            dirname = os.curdir.encode('ASCII')
-        else:
-            dirname = os.curdir
-    try:
-        names = os.listdir(dirname)
-    except OSError:
-        return
-    for x in names:
-        yield x
-        # mypy false-positives: str or bytes type possibility is always kept in sync
-        path = os.path.join(dirname, x) if dirname else x  # type: ignore[arg-type]
-        for y in _rlistdir(path):
-            yield os.path.join(x, y)  # type: ignore[arg-type]
-
-
-magic_check = re.compile('([*?[])')
-magic_check_bytes = re.compile(b'([*?[])')
-
-
-def has_magic(s: str | bytes) -> bool:
-    if isinstance(s, bytes):
-        return magic_check_bytes.search(s) is not None
-    else:
-        return magic_check.search(s) is not None
-
-
-def _isrecursive(pattern: str | bytes) -> bool:
-    if isinstance(pattern, bytes):
-        return pattern == b'**'
-    else:
-        return pattern == '**'
-
-
-def escape(pathname):
-    """Escape all special characters."""
-    # Escaping is done by wrapping any of "*?[" between square brackets.
-    # Metacharacters do not work in the drive part and shouldn't be escaped.
-    drive, pathname = os.path.splitdrive(pathname)
-    if isinstance(pathname, bytes):
-        pathname = magic_check_bytes.sub(rb'[\1]', pathname)
-    else:
-        pathname = magic_check.sub(r'[\1]', pathname)
-    return drive + pathname
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/gui-32.exe b/llmlab/lib/python3.12/site-packages/setuptools/gui-32.exe
deleted file mode 100644
index 1eb430c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/gui-32.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/gui-64.exe b/llmlab/lib/python3.12/site-packages/setuptools/gui-64.exe
deleted file mode 100644
index 031cb77..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/gui-64.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/gui-arm64.exe b/llmlab/lib/python3.12/site-packages/setuptools/gui-arm64.exe
deleted file mode 100644
index 1e00ffa..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/gui-arm64.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/gui.exe b/llmlab/lib/python3.12/site-packages/setuptools/gui.exe
deleted file mode 100644
index 1eb430c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/gui.exe and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/installer.py b/llmlab/lib/python3.12/site-packages/setuptools/installer.py
deleted file mode 100644
index 64bc2de..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/installer.py
+++ /dev/null
@@ -1,150 +0,0 @@
-from __future__ import annotations
-
-import glob
-import os
-import subprocess
-import sys
-import tempfile
-from functools import partial
-
-from pkg_resources import Distribution
-
-from . import _reqs
-from ._reqs import _StrOrIter
-from .warnings import SetuptoolsDeprecationWarning
-from .wheel import Wheel
-
-from distutils import log
-from distutils.errors import DistutilsError
-
-
-def _fixup_find_links(find_links):
-    """Ensure find-links option end-up being a list of strings."""
-    if isinstance(find_links, str):
-        return find_links.split()
-    assert isinstance(find_links, (tuple, list))
-    return find_links
-
-
-def fetch_build_egg(dist, req):
-    """Fetch an egg needed for building.
-
-    Use pip/wheel to fetch/build a wheel."""
-    _DeprecatedInstaller.emit()
-    _warn_wheel_not_available(dist)
-    return _fetch_build_egg_no_warn(dist, req)
-
-
-def _fetch_build_eggs(dist, requires: _StrOrIter) -> list[Distribution]:
-    import pkg_resources  # Delay import to avoid unnecessary side-effects
-
-    _DeprecatedInstaller.emit(stacklevel=3)
-    _warn_wheel_not_available(dist)
-
-    resolved_dists = pkg_resources.working_set.resolve(
-        _reqs.parse(requires, pkg_resources.Requirement),  # required for compatibility
-        installer=partial(_fetch_build_egg_no_warn, dist),  # avoid warning twice
-        replace_conflicting=True,
-    )
-    for dist in resolved_dists:
-        pkg_resources.working_set.add(dist, replace=True)
-    return resolved_dists
-
-
-def _fetch_build_egg_no_warn(dist, req):  # noqa: C901  # is too complex (16)  # FIXME
-    import pkg_resources  # Delay import to avoid unnecessary side-effects
-
-    # Ignore environment markers; if supplied, it is required.
-    req = strip_marker(req)
-    # Take easy_install options into account, but do not override relevant
-    # pip environment variables (like PIP_INDEX_URL or PIP_QUIET); they'll
-    # take precedence.
-    opts = dist.get_option_dict('easy_install')
-    if 'allow_hosts' in opts:
-        raise DistutilsError(
-            'the `allow-hosts` option is not supported '
-            'when using pip to install requirements.'
-        )
-    quiet = 'PIP_QUIET' not in os.environ and 'PIP_VERBOSE' not in os.environ
-    if 'PIP_INDEX_URL' in os.environ:
-        index_url = None
-    elif 'index_url' in opts:
-        index_url = opts['index_url'][1]
-    else:
-        index_url = None
-    find_links = (
-        _fixup_find_links(opts['find_links'][1])[:] if 'find_links' in opts else []
-    )
-    if dist.dependency_links:
-        find_links.extend(dist.dependency_links)
-    eggs_dir = os.path.realpath(dist.get_egg_cache_dir())
-    environment = pkg_resources.Environment()
-    for egg_dist in pkg_resources.find_distributions(eggs_dir):
-        if egg_dist in req and environment.can_add(egg_dist):
-            return egg_dist
-    with tempfile.TemporaryDirectory() as tmpdir:
-        cmd = [
-            sys.executable,
-            '-m',
-            'pip',
-            '--disable-pip-version-check',
-            'wheel',
-            '--no-deps',
-            '-w',
-            tmpdir,
-        ]
-        if quiet:
-            cmd.append('--quiet')
-        if index_url is not None:
-            cmd.extend(('--index-url', index_url))
-        for link in find_links or []:
-            cmd.extend(('--find-links', link))
-        # If requirement is a PEP 508 direct URL, directly pass
-        # the URL to pip, as `req @ url` does not work on the
-        # command line.
-        cmd.append(req.url or str(req))
-        try:
-            subprocess.check_call(cmd)
-        except subprocess.CalledProcessError as e:
-            raise DistutilsError(str(e)) from e
-        wheel = Wheel(glob.glob(os.path.join(tmpdir, '*.whl'))[0])
-        dist_location = os.path.join(eggs_dir, wheel.egg_name())
-        wheel.install_as_egg(dist_location)
-        dist_metadata = pkg_resources.PathMetadata(
-            dist_location, os.path.join(dist_location, 'EGG-INFO')
-        )
-        return pkg_resources.Distribution.from_filename(
-            dist_location, metadata=dist_metadata
-        )
-
-
-def strip_marker(req):
-    """
-    Return a new requirement without the environment marker to avoid
-    calling pip with something like `babel; extra == "i18n"`, which
-    would always be ignored.
-    """
-    import pkg_resources  # Delay import to avoid unnecessary side-effects
-
-    # create a copy to avoid mutating the input
-    req = pkg_resources.Requirement.parse(str(req))
-    req.marker = None
-    return req
-
-
-def _warn_wheel_not_available(dist):
-    import pkg_resources  # Delay import to avoid unnecessary side-effects
-
-    try:
-        pkg_resources.get_distribution('wheel')
-    except pkg_resources.DistributionNotFound:
-        dist.announce('WARNING: The wheel package is not available.', log.WARN)
-
-
-class _DeprecatedInstaller(SetuptoolsDeprecationWarning):
-    _SUMMARY = "setuptools.installer and fetch_build_eggs are deprecated."
-    _DETAILS = """
-    Requirements should be satisfied by a PEP 517 installer.
-    If you are using pip, you can try `pip install --use-pep517`.
-    """
-    # _DUE_DATE not decided yet
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/launch.py b/llmlab/lib/python3.12/site-packages/setuptools/launch.py
deleted file mode 100644
index 0d16264..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/launch.py
+++ /dev/null
@@ -1,36 +0,0 @@
-"""
-Launch the Python script on the command line after
-setuptools is bootstrapped via import.
-"""
-
-# Note that setuptools gets imported implicitly by the
-# invocation of this script using python -m setuptools.launch
-
-import sys
-import tokenize
-
-
-def run() -> None:
-    """
-    Run the script in sys.argv[1] as if it had
-    been invoked naturally.
-    """
-    __builtins__
-    script_name = sys.argv[1]
-    namespace = dict(
-        __file__=script_name,
-        __name__='__main__',
-        __doc__=None,
-    )
-    sys.argv[:] = sys.argv[1:]
-
-    open_ = getattr(tokenize, 'open', open)
-    with open_(script_name) as fid:
-        script = fid.read()
-    norm_script = script.replace('\\r\\n', '\\n')
-    code = compile(norm_script, script_name, 'exec')
-    exec(code, namespace)
-
-
-if __name__ == '__main__':
-    run()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/logging.py b/llmlab/lib/python3.12/site-packages/setuptools/logging.py
deleted file mode 100644
index 532da89..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/logging.py
+++ /dev/null
@@ -1,40 +0,0 @@
-import inspect
-import logging
-import sys
-
-from . import monkey
-
-import distutils.log
-
-
-def _not_warning(record):
-    return record.levelno < logging.WARNING
-
-
-def configure() -> None:
-    """
-    Configure logging to emit warning and above to stderr
-    and everything else to stdout. This behavior is provided
-    for compatibility with distutils.log but may change in
-    the future.
-    """
-    err_handler = logging.StreamHandler()
-    err_handler.setLevel(logging.WARNING)
-    out_handler = logging.StreamHandler(sys.stdout)
-    out_handler.addFilter(_not_warning)
-    handlers = err_handler, out_handler
-    logging.basicConfig(
-        format="{message}", style='{', handlers=handlers, level=logging.DEBUG
-    )
-    if inspect.ismodule(distutils.dist.log):
-        monkey.patch_func(set_threshold, distutils.log, 'set_threshold')
-        # For some reason `distutils.log` module is getting cached in `distutils.dist`
-        # and then loaded again when patched,
-        # implying: id(distutils.log) != id(distutils.dist.log).
-        # Make sure the same module object is used everywhere:
-        distutils.dist.log = distutils.log
-
-
-def set_threshold(level: int) -> int:
-    logging.root.setLevel(level * 10)
-    return set_threshold.unpatched(level)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/modified.py b/llmlab/lib/python3.12/site-packages/setuptools/modified.py
deleted file mode 100644
index 6ba02fa..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/modified.py
+++ /dev/null
@@ -1,18 +0,0 @@
-try:
-    # Ensure a DistutilsError raised by these methods is the same as distutils.errors.DistutilsError
-    from distutils._modified import (
-        newer,
-        newer_group,
-        newer_pairwise,
-        newer_pairwise_group,
-    )
-except ImportError:
-    # fallback for SETUPTOOLS_USE_DISTUTILS=stdlib, because _modified never existed in stdlib
-    from ._distutils._modified import (
-        newer,
-        newer_group,
-        newer_pairwise,
-        newer_pairwise_group,
-    )
-
-__all__ = ['newer', 'newer_pairwise', 'newer_group', 'newer_pairwise_group']
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/monkey.py b/llmlab/lib/python3.12/site-packages/setuptools/monkey.py
deleted file mode 100644
index 6ad1aba..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/monkey.py
+++ /dev/null
@@ -1,126 +0,0 @@
-"""
-Monkey patching of distutils.
-"""
-
-from __future__ import annotations
-
-import inspect
-import platform
-import sys
-import types
-from typing import TypeVar, cast, overload
-
-import distutils.filelist
-
-_T = TypeVar("_T")
-_UnpatchT = TypeVar("_UnpatchT", type, types.FunctionType)
-
-
-__all__: list[str] = []
-"""
-Everything is private. Contact the project team
-if you think you need this functionality.
-"""
-
-
-def _get_mro(cls):
-    """
-    Returns the bases classes for cls sorted by the MRO.
-
-    Works around an issue on Jython where inspect.getmro will not return all
-    base classes if multiple classes share the same name. Instead, this
-    function will return a tuple containing the class itself, and the contents
-    of cls.__bases__. See https://github.com/pypa/setuptools/issues/1024.
-    """
-    if platform.python_implementation() == "Jython":
-        return (cls,) + cls.__bases__
-    return inspect.getmro(cls)
-
-
-@overload
-def get_unpatched(item: _UnpatchT) -> _UnpatchT: ...
-@overload
-def get_unpatched(item: object) -> None: ...
-def get_unpatched(
-    item: type | types.FunctionType | object,
-) -> type | types.FunctionType | None:
-    if isinstance(item, type):
-        return get_unpatched_class(item)
-    if isinstance(item, types.FunctionType):
-        return get_unpatched_function(item)
-    return None
-
-
-def get_unpatched_class(cls: type[_T]) -> type[_T]:
-    """Protect against re-patching the distutils if reloaded
-
-    Also ensures that no other distutils extension monkeypatched the distutils
-    first.
-    """
-    external_bases = (
-        cast(type[_T], cls)
-        for cls in _get_mro(cls)
-        if not cls.__module__.startswith('setuptools')
-    )
-    base = next(external_bases)
-    if not base.__module__.startswith('distutils'):
-        msg = f"distutils has already been patched by {cls!r}"
-        raise AssertionError(msg)
-    return base
-
-
-def patch_all():
-    import setuptools
-
-    # we can't patch distutils.cmd, alas
-    distutils.core.Command = setuptools.Command  # type: ignore[misc,assignment] # monkeypatching
-
-    _patch_distribution_metadata()
-
-    # Install Distribution throughout the distutils
-    for module in distutils.dist, distutils.core, distutils.cmd:
-        module.Distribution = setuptools.dist.Distribution
-
-    # Install the patched Extension
-    distutils.core.Extension = setuptools.extension.Extension  # type: ignore[misc,assignment] # monkeypatching
-    distutils.extension.Extension = setuptools.extension.Extension  # type: ignore[misc,assignment] # monkeypatching
-    if 'distutils.command.build_ext' in sys.modules:
-        sys.modules[
-            'distutils.command.build_ext'
-        ].Extension = setuptools.extension.Extension
-
-
-def _patch_distribution_metadata():
-    from . import _core_metadata
-
-    """Patch write_pkg_file and read_pkg_file for higher metadata standards"""
-    for attr in (
-        'write_pkg_info',
-        'write_pkg_file',
-        'read_pkg_file',
-        'get_metadata_version',
-        'get_fullname',
-    ):
-        new_val = getattr(_core_metadata, attr)
-        setattr(distutils.dist.DistributionMetadata, attr, new_val)
-
-
-def patch_func(replacement, target_mod, func_name):
-    """
-    Patch func_name in target_mod with replacement
-
-    Important - original must be resolved by name to avoid
-    patching an already patched function.
-    """
-    original = getattr(target_mod, func_name)
-
-    # set the 'unpatched' attribute on the replacement to
-    # point to the original.
-    vars(replacement).setdefault('unpatched', original)
-
-    # replace the function in the original module
-    setattr(target_mod, func_name, replacement)
-
-
-def get_unpatched_function(candidate):
-    return candidate.unpatched
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/msvc.py b/llmlab/lib/python3.12/site-packages/setuptools/msvc.py
deleted file mode 100644
index 313a781..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/msvc.py
+++ /dev/null
@@ -1,1536 +0,0 @@
-"""
-Environment info about Microsoft Compilers.
-
->>> getfixture('windows_only')
->>> ei = EnvironmentInfo('amd64')
-"""
-
-from __future__ import annotations
-
-import contextlib
-import itertools
-import json
-import os
-import os.path
-import platform
-from typing import TYPE_CHECKING, TypedDict
-
-from more_itertools import unique_everseen
-
-import distutils.errors
-
-if TYPE_CHECKING:
-    from typing_extensions import LiteralString, NotRequired
-
-# https://github.com/python/mypy/issues/8166
-if not TYPE_CHECKING and platform.system() == 'Windows':
-    import winreg
-    from os import environ
-else:
-    # Mock winreg and environ so the module can be imported on this platform.
-
-    class winreg:
-        HKEY_USERS = None
-        HKEY_CURRENT_USER = None
-        HKEY_LOCAL_MACHINE = None
-        HKEY_CLASSES_ROOT = None
-
-    environ: dict[str, str] = dict()
-
-
-class PlatformInfo:
-    """
-    Current and Target Architectures information.
-
-    Parameters
-    ----------
-    arch: str
-        Target architecture.
-    """
-
-    current_cpu = environ.get('processor_architecture', '').lower()
-
-    def __init__(self, arch) -> None:
-        self.arch = arch.lower().replace('x64', 'amd64')
-
-    @property
-    def target_cpu(self):
-        """
-        Return Target CPU architecture.
-
-        Return
-        ------
-        str
-            Target CPU
-        """
-        return self.arch[self.arch.find('_') + 1 :]
-
-    def target_is_x86(self):
-        """
-        Return True if target CPU is x86 32 bits..
-
-        Return
-        ------
-        bool
-            CPU is x86 32 bits
-        """
-        return self.target_cpu == 'x86'
-
-    def current_is_x86(self):
-        """
-        Return True if current CPU is x86 32 bits..
-
-        Return
-        ------
-        bool
-            CPU is x86 32 bits
-        """
-        return self.current_cpu == 'x86'
-
-    def current_dir(self, hidex86=False, x64=False) -> str:
-        """
-        Current platform specific subfolder.
-
-        Parameters
-        ----------
-        hidex86: bool
-            return '' and not '\x86' if architecture is x86.
-        x64: bool
-            return '\x64' and not '\amd64' if architecture is amd64.
-
-        Return
-        ------
-        str
-            subfolder: '\target', or '' (see hidex86 parameter)
-        """
-        return (
-            ''
-            if (self.current_cpu == 'x86' and hidex86)
-            else r'\x64'
-            if (self.current_cpu == 'amd64' and x64)
-            else rf'\{self.current_cpu}'
-        )
-
-    def target_dir(self, hidex86=False, x64=False) -> str:
-        r"""
-        Target platform specific subfolder.
-
-        Parameters
-        ----------
-        hidex86: bool
-            return '' and not '\x86' if architecture is x86.
-        x64: bool
-            return '\x64' and not '\amd64' if architecture is amd64.
-
-        Return
-        ------
-        str
-            subfolder: '\current', or '' (see hidex86 parameter)
-        """
-        return (
-            ''
-            if (self.target_cpu == 'x86' and hidex86)
-            else r'\x64'
-            if (self.target_cpu == 'amd64' and x64)
-            else rf'\{self.target_cpu}'
-        )
-
-    def cross_dir(self, forcex86=False):
-        r"""
-        Cross platform specific subfolder.
-
-        Parameters
-        ----------
-        forcex86: bool
-            Use 'x86' as current architecture even if current architecture is
-            not x86.
-
-        Return
-        ------
-        str
-            subfolder: '' if target architecture is current architecture,
-            '\current_target' if not.
-        """
-        current = 'x86' if forcex86 else self.current_cpu
-        return (
-            ''
-            if self.target_cpu == current
-            else self.target_dir().replace('\\', f'\\{current}_')
-        )
-
-
-class RegistryInfo:
-    """
-    Microsoft Visual Studio related registry information.
-
-    Parameters
-    ----------
-    platform_info: PlatformInfo
-        "PlatformInfo" instance.
-    """
-
-    HKEYS = (
-        winreg.HKEY_USERS,
-        winreg.HKEY_CURRENT_USER,
-        winreg.HKEY_LOCAL_MACHINE,
-        winreg.HKEY_CLASSES_ROOT,
-    )
-
-    def __init__(self, platform_info) -> None:
-        self.pi = platform_info
-
-    @property
-    def visualstudio(self) -> str:
-        """
-        Microsoft Visual Studio root registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return 'VisualStudio'
-
-    @property
-    def sxs(self):
-        """
-        Microsoft Visual Studio SxS registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return os.path.join(self.visualstudio, 'SxS')
-
-    @property
-    def vc(self):
-        """
-        Microsoft Visual C++ VC7 registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return os.path.join(self.sxs, 'VC7')
-
-    @property
-    def vs(self):
-        """
-        Microsoft Visual Studio VS7 registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return os.path.join(self.sxs, 'VS7')
-
-    @property
-    def vc_for_python(self) -> str:
-        """
-        Microsoft Visual C++ for Python registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return r'DevDiv\VCForPython'
-
-    @property
-    def microsoft_sdk(self) -> str:
-        """
-        Microsoft SDK registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return 'Microsoft SDKs'
-
-    @property
-    def windows_sdk(self):
-        """
-        Microsoft Windows/Platform SDK registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return os.path.join(self.microsoft_sdk, 'Windows')
-
-    @property
-    def netfx_sdk(self):
-        """
-        Microsoft .NET Framework SDK registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return os.path.join(self.microsoft_sdk, 'NETFXSDK')
-
-    @property
-    def windows_kits_roots(self) -> str:
-        """
-        Microsoft Windows Kits Roots registry key.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        return r'Windows Kits\Installed Roots'
-
-    def microsoft(self, key, x86=False):
-        """
-        Return key in Microsoft software registry.
-
-        Parameters
-        ----------
-        key: str
-            Registry key path where look.
-        x86: str
-            Force x86 software registry.
-
-        Return
-        ------
-        str
-            Registry key
-        """
-        node64 = '' if self.pi.current_is_x86() or x86 else 'Wow6432Node'
-        return os.path.join('Software', node64, 'Microsoft', key)
-
-    def lookup(self, key, name):
-        """
-        Look for values in registry in Microsoft software registry.
-
-        Parameters
-        ----------
-        key: str
-            Registry key path where look.
-        name: str
-            Value name to find.
-
-        Return
-        ------
-        str
-            value
-        """
-        key_read = winreg.KEY_READ
-        openkey = winreg.OpenKey
-        closekey = winreg.CloseKey
-        ms = self.microsoft
-        for hkey in self.HKEYS:
-            bkey = None
-            try:
-                bkey = openkey(hkey, ms(key), 0, key_read)
-            except OSError:
-                if not self.pi.current_is_x86():
-                    try:
-                        bkey = openkey(hkey, ms(key, True), 0, key_read)
-                    except OSError:
-                        continue
-                else:
-                    continue
-            try:
-                return winreg.QueryValueEx(bkey, name)[0]
-            except OSError:
-                pass
-            finally:
-                if bkey:
-                    closekey(bkey)
-        return None
-
-
-class SystemInfo:
-    """
-    Microsoft Windows and Visual Studio related system information.
-
-    Parameters
-    ----------
-    registry_info: RegistryInfo
-        "RegistryInfo" instance.
-    vc_ver: float
-        Required Microsoft Visual C++ version.
-    """
-
-    # Variables and properties in this class use originals CamelCase variables
-    # names from Microsoft source files for more easy comparison.
-    WinDir = environ.get('WinDir', '')
-    ProgramFiles = environ.get('ProgramFiles', '')
-    ProgramFilesx86 = environ.get('ProgramFiles(x86)', ProgramFiles)
-
-    def __init__(self, registry_info, vc_ver=None) -> None:
-        self.ri = registry_info
-        self.pi = self.ri.pi
-
-        self.known_vs_paths = self.find_programdata_vs_vers()
-
-        # Except for VS15+, VC version is aligned with VS version
-        self.vs_ver = self.vc_ver = vc_ver or self._find_latest_available_vs_ver()
-
-    def _find_latest_available_vs_ver(self):
-        """
-        Find the latest VC version
-
-        Return
-        ------
-        float
-            version
-        """
-        reg_vc_vers = self.find_reg_vs_vers()
-
-        if not (reg_vc_vers or self.known_vs_paths):
-            raise distutils.errors.DistutilsPlatformError(
-                'No Microsoft Visual C++ version found'
-            )
-
-        vc_vers = set(reg_vc_vers)
-        vc_vers.update(self.known_vs_paths)
-        return sorted(vc_vers)[-1]
-
-    def find_reg_vs_vers(self):
-        """
-        Find Microsoft Visual Studio versions available in registry.
-
-        Return
-        ------
-        list of float
-            Versions
-        """
-        ms = self.ri.microsoft
-        vckeys = (self.ri.vc, self.ri.vc_for_python, self.ri.vs)
-        vs_vers = []
-        for hkey, key in itertools.product(self.ri.HKEYS, vckeys):
-            try:
-                bkey = winreg.OpenKey(hkey, ms(key), 0, winreg.KEY_READ)
-            except OSError:
-                continue
-            with bkey:
-                subkeys, values, _ = winreg.QueryInfoKey(bkey)
-                for i in range(values):
-                    with contextlib.suppress(ValueError):
-                        ver = float(winreg.EnumValue(bkey, i)[0])
-                        if ver not in vs_vers:
-                            vs_vers.append(ver)
-                for i in range(subkeys):
-                    with contextlib.suppress(ValueError):
-                        ver = float(winreg.EnumKey(bkey, i))
-                        if ver not in vs_vers:
-                            vs_vers.append(ver)
-        return sorted(vs_vers)
-
-    def find_programdata_vs_vers(self) -> dict[float, str]:
-        r"""
-        Find Visual studio 2017+ versions from information in
-        "C:\ProgramData\Microsoft\VisualStudio\Packages\_Instances".
-
-        Return
-        ------
-        dict
-            float version as key, path as value.
-        """
-        vs_versions: dict[float, str] = {}
-        instances_dir = r'C:\ProgramData\Microsoft\VisualStudio\Packages\_Instances'
-
-        try:
-            hashed_names = os.listdir(instances_dir)
-
-        except OSError:
-            # Directory not exists with all Visual Studio versions
-            return vs_versions
-
-        for name in hashed_names:
-            try:
-                # Get VS installation path from "state.json" file
-                state_path = os.path.join(instances_dir, name, 'state.json')
-                with open(state_path, 'rt', encoding='utf-8') as state_file:
-                    state = json.load(state_file)
-                vs_path = state['installationPath']
-
-                # Raises OSError if this VS installation does not contain VC
-                os.listdir(os.path.join(vs_path, r'VC\Tools\MSVC'))
-
-                # Store version and path
-                vs_versions[self._as_float_version(state['installationVersion'])] = (
-                    vs_path
-                )
-
-            except (OSError, KeyError):
-                # Skip if "state.json" file is missing or bad format
-                continue
-
-        return vs_versions
-
-    @staticmethod
-    def _as_float_version(version):
-        """
-        Return a string version as a simplified float version (major.minor)
-
-        Parameters
-        ----------
-        version: str
-            Version.
-
-        Return
-        ------
-        float
-            version
-        """
-        return float('.'.join(version.split('.')[:2]))
-
-    @property
-    def VSInstallDir(self):
-        """
-        Microsoft Visual Studio directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        # Default path
-        default = os.path.join(
-            self.ProgramFilesx86, f'Microsoft Visual Studio {self.vs_ver:0.1f}'
-        )
-
-        # Try to get path from registry, if fail use default path
-        return self.ri.lookup(self.ri.vs, f'{self.vs_ver:0.1f}') or default
-
-    @property
-    def VCInstallDir(self):
-        """
-        Microsoft Visual C++ directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        path = self._guess_vc() or self._guess_vc_legacy()
-
-        if not os.path.isdir(path):
-            msg = 'Microsoft Visual C++ directory not found'
-            raise distutils.errors.DistutilsPlatformError(msg)
-
-        return path
-
-    def _guess_vc(self):
-        """
-        Locate Visual C++ for VS2017+.
-
-        Return
-        ------
-        str
-            path
-        """
-        if self.vs_ver <= 14.0:
-            return ''
-
-        try:
-            # First search in known VS paths
-            vs_dir = self.known_vs_paths[self.vs_ver]
-        except KeyError:
-            # Else, search with path from registry
-            vs_dir = self.VSInstallDir
-
-        guess_vc = os.path.join(vs_dir, r'VC\Tools\MSVC')
-
-        # Subdir with VC exact version as name
-        try:
-            # Update the VC version with real one instead of VS version
-            vc_ver = os.listdir(guess_vc)[-1]
-            self.vc_ver = self._as_float_version(vc_ver)
-            return os.path.join(guess_vc, vc_ver)
-        except (OSError, IndexError):
-            return ''
-
-    def _guess_vc_legacy(self):
-        """
-        Locate Visual C++ for versions prior to 2017.
-
-        Return
-        ------
-        str
-            path
-        """
-        default = os.path.join(
-            self.ProgramFilesx86,
-            rf'Microsoft Visual Studio {self.vs_ver:0.1f}\VC',
-        )
-
-        # Try to get "VC++ for Python" path from registry as default path
-        reg_path = os.path.join(self.ri.vc_for_python, f'{self.vs_ver:0.1f}')
-        python_vc = self.ri.lookup(reg_path, 'installdir')
-        default_vc = os.path.join(python_vc, 'VC') if python_vc else default
-
-        # Try to get path from registry, if fail use default path
-        return self.ri.lookup(self.ri.vc, f'{self.vs_ver:0.1f}') or default_vc
-
-    @property
-    def WindowsSdkVersion(self) -> tuple[LiteralString, ...]:
-        """
-        Microsoft Windows SDK versions for specified MSVC++ version.
-
-        Return
-        ------
-        tuple of str
-            versions
-        """
-        if self.vs_ver <= 9.0:
-            return '7.0', '6.1', '6.0a'
-        elif self.vs_ver == 10.0:
-            return '7.1', '7.0a'
-        elif self.vs_ver == 11.0:
-            return '8.0', '8.0a'
-        elif self.vs_ver == 12.0:
-            return '8.1', '8.1a'
-        elif self.vs_ver >= 14.0:
-            return '10.0', '8.1'
-        return ()
-
-    @property
-    def WindowsSdkLastVersion(self):
-        """
-        Microsoft Windows SDK last version.
-
-        Return
-        ------
-        str
-            version
-        """
-        return self._use_last_dir_name(os.path.join(self.WindowsSdkDir, 'lib'))
-
-    @property
-    def WindowsSdkDir(self) -> str | None:  # noqa: C901  # is too complex (12)  # FIXME
-        """
-        Microsoft Windows SDK directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        sdkdir: str | None = ''
-        for ver in self.WindowsSdkVersion:
-            # Try to get it from registry
-            loc = os.path.join(self.ri.windows_sdk, f'v{ver}')
-            sdkdir = self.ri.lookup(loc, 'installationfolder')
-            if sdkdir:
-                break
-        if not sdkdir or not os.path.isdir(sdkdir):
-            # Try to get "VC++ for Python" version from registry
-            path = os.path.join(self.ri.vc_for_python, f'{self.vc_ver:0.1f}')
-            install_base = self.ri.lookup(path, 'installdir')
-            if install_base:
-                sdkdir = os.path.join(install_base, 'WinSDK')
-        if not sdkdir or not os.path.isdir(sdkdir):
-            # If fail, use default new path
-            for ver in self.WindowsSdkVersion:
-                intver = ver[: ver.rfind('.')]
-                path = rf'Microsoft SDKs\Windows Kits\{intver}'
-                d = os.path.join(self.ProgramFiles, path)
-                if os.path.isdir(d):
-                    sdkdir = d
-        if not sdkdir or not os.path.isdir(sdkdir):
-            # If fail, use default old path
-            for ver in self.WindowsSdkVersion:
-                path = rf'Microsoft SDKs\Windows\v{ver}'
-                d = os.path.join(self.ProgramFiles, path)
-                if os.path.isdir(d):
-                    sdkdir = d
-        if not sdkdir:
-            # If fail, use Platform SDK
-            sdkdir = os.path.join(self.VCInstallDir, 'PlatformSDK')
-        return sdkdir
-
-    @property
-    def WindowsSDKExecutablePath(self):
-        """
-        Microsoft Windows SDK executable directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        # Find WinSDK NetFx Tools registry dir name
-        if self.vs_ver <= 11.0:
-            netfxver = 35
-            arch = ''
-        else:
-            netfxver = 40
-            hidex86 = True if self.vs_ver <= 12.0 else False
-            arch = self.pi.current_dir(x64=True, hidex86=hidex86).replace('\\', '-')
-        fx = f'WinSDK-NetFx{netfxver}Tools{arch}'
-
-        # list all possibles registry paths
-        regpaths = []
-        if self.vs_ver >= 14.0:
-            for ver in self.NetFxSdkVersion:
-                regpaths += [os.path.join(self.ri.netfx_sdk, ver, fx)]
-
-        for ver in self.WindowsSdkVersion:
-            regpaths += [os.path.join(self.ri.windows_sdk, f'v{ver}A', fx)]
-
-        # Return installation folder from the more recent path
-        for path in regpaths:
-            execpath = self.ri.lookup(path, 'installationfolder')
-            if execpath:
-                return execpath
-
-        return None
-
-    @property
-    def FSharpInstallDir(self):
-        """
-        Microsoft Visual F# directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        path = os.path.join(self.ri.visualstudio, rf'{self.vs_ver:0.1f}\Setup\F#')
-        return self.ri.lookup(path, 'productdir') or ''
-
-    @property
-    def UniversalCRTSdkDir(self):
-        """
-        Microsoft Universal CRT SDK directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        # Set Kit Roots versions for specified MSVC++ version
-        vers = ('10', '81') if self.vs_ver >= 14.0 else ()
-
-        # Find path of the more recent Kit
-        for ver in vers:
-            sdkdir = self.ri.lookup(self.ri.windows_kits_roots, f'kitsroot{ver}')
-            if sdkdir:
-                return sdkdir or ''
-
-        return None
-
-    @property
-    def UniversalCRTSdkLastVersion(self):
-        """
-        Microsoft Universal C Runtime SDK last version.
-
-        Return
-        ------
-        str
-            version
-        """
-        return self._use_last_dir_name(os.path.join(self.UniversalCRTSdkDir, 'lib'))
-
-    @property
-    def NetFxSdkVersion(self):
-        """
-        Microsoft .NET Framework SDK versions.
-
-        Return
-        ------
-        tuple of str
-            versions
-        """
-        # Set FxSdk versions for specified VS version
-        return (
-            ('4.7.2', '4.7.1', '4.7', '4.6.2', '4.6.1', '4.6', '4.5.2', '4.5.1', '4.5')
-            if self.vs_ver >= 14.0
-            else ()
-        )
-
-    @property
-    def NetFxSdkDir(self):
-        """
-        Microsoft .NET Framework SDK directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        sdkdir = ''
-        for ver in self.NetFxSdkVersion:
-            loc = os.path.join(self.ri.netfx_sdk, ver)
-            sdkdir = self.ri.lookup(loc, 'kitsinstallationfolder')
-            if sdkdir:
-                break
-        return sdkdir
-
-    @property
-    def FrameworkDir32(self):
-        """
-        Microsoft .NET Framework 32bit directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        # Default path
-        guess_fw = os.path.join(self.WinDir, r'Microsoft.NET\Framework')
-
-        # Try to get path from registry, if fail use default path
-        return self.ri.lookup(self.ri.vc, 'frameworkdir32') or guess_fw
-
-    @property
-    def FrameworkDir64(self):
-        """
-        Microsoft .NET Framework 64bit directory.
-
-        Return
-        ------
-        str
-            path
-        """
-        # Default path
-        guess_fw = os.path.join(self.WinDir, r'Microsoft.NET\Framework64')
-
-        # Try to get path from registry, if fail use default path
-        return self.ri.lookup(self.ri.vc, 'frameworkdir64') or guess_fw
-
-    @property
-    def FrameworkVersion32(self) -> tuple[str, ...]:
-        """
-        Microsoft .NET Framework 32bit versions.
-
-        Return
-        ------
-        tuple of str
-            versions
-        """
-        return self._find_dot_net_versions(32)
-
-    @property
-    def FrameworkVersion64(self) -> tuple[str, ...]:
-        """
-        Microsoft .NET Framework 64bit versions.
-
-        Return
-        ------
-        tuple of str
-            versions
-        """
-        return self._find_dot_net_versions(64)
-
-    def _find_dot_net_versions(self, bits) -> tuple[str, ...]:
-        """
-        Find Microsoft .NET Framework versions.
-
-        Parameters
-        ----------
-        bits: int
-            Platform number of bits: 32 or 64.
-
-        Return
-        ------
-        tuple of str
-            versions
-        """
-        # Find actual .NET version in registry
-        reg_ver = self.ri.lookup(self.ri.vc, f'frameworkver{bits}')
-        dot_net_dir = getattr(self, f'FrameworkDir{bits}')
-        ver = reg_ver or self._use_last_dir_name(dot_net_dir, 'v') or ''
-
-        # Set .NET versions for specified MSVC++ version
-        if self.vs_ver >= 12.0:
-            return ver, 'v4.0'
-        elif self.vs_ver >= 10.0:
-            return 'v4.0.30319' if ver.lower()[:2] != 'v4' else ver, 'v3.5'
-        elif self.vs_ver == 9.0:
-            return 'v3.5', 'v2.0.50727'
-        elif self.vs_ver == 8.0:
-            return 'v3.0', 'v2.0.50727'
-        return ()
-
-    @staticmethod
-    def _use_last_dir_name(path, prefix=''):
-        """
-        Return name of the last dir in path or '' if no dir found.
-
-        Parameters
-        ----------
-        path: str
-            Use dirs in this path
-        prefix: str
-            Use only dirs starting by this prefix
-
-        Return
-        ------
-        str
-            name
-        """
-        matching_dirs = (
-            dir_name
-            for dir_name in reversed(os.listdir(path))
-            if os.path.isdir(os.path.join(path, dir_name))
-            and dir_name.startswith(prefix)
-        )
-        return next(matching_dirs, None) or ''
-
-
-class _EnvironmentDict(TypedDict):
-    include: str
-    lib: str
-    libpath: str
-    path: str
-    py_vcruntime_redist: NotRequired[str | None]
-
-
-class EnvironmentInfo:
-    """
-    Return environment variables for specified Microsoft Visual C++ version
-    and platform : Lib, Include, Path and libpath.
-
-    This function is compatible with Microsoft Visual C++ 9.0 to 14.X.
-
-    Script created by analysing Microsoft environment configuration files like
-    "vcvars[...].bat", "SetEnv.Cmd", "vcbuildtools.bat", ...
-
-    Parameters
-    ----------
-    arch: str
-        Target architecture.
-    vc_ver: float
-        Required Microsoft Visual C++ version. If not set, autodetect the last
-        version.
-    vc_min_ver: float
-        Minimum Microsoft Visual C++ version.
-    """
-
-    # Variables and properties in this class use originals CamelCase variables
-    # names from Microsoft source files for more easy comparison.
-
-    def __init__(self, arch, vc_ver=None, vc_min_ver=0) -> None:
-        self.pi = PlatformInfo(arch)
-        self.ri = RegistryInfo(self.pi)
-        self.si = SystemInfo(self.ri, vc_ver)
-
-        if self.vc_ver < vc_min_ver:
-            err = 'No suitable Microsoft Visual C++ version found'
-            raise distutils.errors.DistutilsPlatformError(err)
-
-    @property
-    def vs_ver(self):
-        """
-        Microsoft Visual Studio.
-
-        Return
-        ------
-        float
-            version
-        """
-        return self.si.vs_ver
-
-    @property
-    def vc_ver(self):
-        """
-        Microsoft Visual C++ version.
-
-        Return
-        ------
-        float
-            version
-        """
-        return self.si.vc_ver
-
-    @property
-    def VSTools(self):
-        """
-        Microsoft Visual Studio Tools.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        paths = [r'Common7\IDE', r'Common7\Tools']
-
-        if self.vs_ver >= 14.0:
-            arch_subdir = self.pi.current_dir(hidex86=True, x64=True)
-            paths += [r'Common7\IDE\CommonExtensions\Microsoft\TestWindow']
-            paths += [r'Team Tools\Performance Tools']
-            paths += [rf'Team Tools\Performance Tools{arch_subdir}']
-
-        return [os.path.join(self.si.VSInstallDir, path) for path in paths]
-
-    @property
-    def VCIncludes(self):
-        """
-        Microsoft Visual C++ & Microsoft Foundation Class Includes.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        return [
-            os.path.join(self.si.VCInstallDir, 'Include'),
-            os.path.join(self.si.VCInstallDir, r'ATLMFC\Include'),
-        ]
-
-    @property
-    def VCLibraries(self):
-        """
-        Microsoft Visual C++ & Microsoft Foundation Class Libraries.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver >= 15.0:
-            arch_subdir = self.pi.target_dir(x64=True)
-        else:
-            arch_subdir = self.pi.target_dir(hidex86=True)
-        paths = [f'Lib{arch_subdir}', rf'ATLMFC\Lib{arch_subdir}']
-
-        if self.vs_ver >= 14.0:
-            paths += [rf'Lib\store{arch_subdir}']
-
-        return [os.path.join(self.si.VCInstallDir, path) for path in paths]
-
-    @property
-    def VCStoreRefs(self):
-        """
-        Microsoft Visual C++ store references Libraries.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver < 14.0:
-            return []
-        return [os.path.join(self.si.VCInstallDir, r'Lib\store\references')]
-
-    @property
-    def VCTools(self):
-        """
-        Microsoft Visual C++ Tools.
-
-        Return
-        ------
-        list of str
-            paths
-
-        When host CPU is ARM, the tools should be found for ARM.
-
-        >>> getfixture('windows_only')
-        >>> mp = getfixture('monkeypatch')
-        >>> mp.setattr(PlatformInfo, 'current_cpu', 'arm64')
-        >>> ei = EnvironmentInfo(arch='irrelevant')
-        >>> paths = ei.VCTools
-        >>> any('HostARM64' in path for path in paths)
-        True
-        """
-        si = self.si
-        tools = [os.path.join(si.VCInstallDir, 'VCPackages')]
-
-        forcex86 = True if self.vs_ver <= 10.0 else False
-        arch_subdir = self.pi.cross_dir(forcex86)
-        if arch_subdir:
-            tools += [os.path.join(si.VCInstallDir, f'Bin{arch_subdir}')]
-
-        if self.vs_ver == 14.0:
-            path = f'Bin{self.pi.current_dir(hidex86=True)}'
-            tools += [os.path.join(si.VCInstallDir, path)]
-
-        elif self.vs_ver >= 15.0:
-            host_id = self.pi.current_cpu.replace('amd64', 'x64').upper()
-            host_dir = os.path.join('bin', f'Host{host_id}%s')
-            tools += [
-                os.path.join(si.VCInstallDir, host_dir % self.pi.target_dir(x64=True))
-            ]
-
-            if self.pi.current_cpu != self.pi.target_cpu:
-                tools += [
-                    os.path.join(
-                        si.VCInstallDir, host_dir % self.pi.current_dir(x64=True)
-                    )
-                ]
-
-        else:
-            tools += [os.path.join(si.VCInstallDir, 'Bin')]
-
-        return tools
-
-    @property
-    def OSLibraries(self):
-        """
-        Microsoft Windows SDK Libraries.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver <= 10.0:
-            arch_subdir = self.pi.target_dir(hidex86=True, x64=True)
-            return [os.path.join(self.si.WindowsSdkDir, f'Lib{arch_subdir}')]
-
-        else:
-            arch_subdir = self.pi.target_dir(x64=True)
-            lib = os.path.join(self.si.WindowsSdkDir, 'lib')
-            libver = self._sdk_subdir
-            return [os.path.join(lib, f'{libver}um{arch_subdir}')]
-
-    @property
-    def OSIncludes(self):
-        """
-        Microsoft Windows SDK Include.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        include = os.path.join(self.si.WindowsSdkDir, 'include')
-
-        if self.vs_ver <= 10.0:
-            return [include, os.path.join(include, 'gl')]
-
-        else:
-            if self.vs_ver >= 14.0:
-                sdkver = self._sdk_subdir
-            else:
-                sdkver = ''
-            return [
-                os.path.join(include, f'{sdkver}shared'),
-                os.path.join(include, f'{sdkver}um'),
-                os.path.join(include, f'{sdkver}winrt'),
-            ]
-
-    @property
-    def OSLibpath(self):
-        """
-        Microsoft Windows SDK Libraries Paths.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        ref = os.path.join(self.si.WindowsSdkDir, 'References')
-        libpath = []
-
-        if self.vs_ver <= 9.0:
-            libpath += self.OSLibraries
-
-        if self.vs_ver >= 11.0:
-            libpath += [os.path.join(ref, r'CommonConfiguration\Neutral')]
-
-        if self.vs_ver >= 14.0:
-            libpath += [
-                ref,
-                os.path.join(self.si.WindowsSdkDir, 'UnionMetadata'),
-                os.path.join(ref, 'Windows.Foundation.UniversalApiContract', '1.0.0.0'),
-                os.path.join(ref, 'Windows.Foundation.FoundationContract', '1.0.0.0'),
-                os.path.join(
-                    ref, 'Windows.Networking.Connectivity.WwanContract', '1.0.0.0'
-                ),
-                os.path.join(
-                    self.si.WindowsSdkDir,
-                    'ExtensionSDKs',
-                    'Microsoft.VCLibs',
-                    f'{self.vs_ver:0.1f}',
-                    'References',
-                    'CommonConfiguration',
-                    'neutral',
-                ),
-            ]
-        return libpath
-
-    @property
-    def SdkTools(self):
-        """
-        Microsoft Windows SDK Tools.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        return list(self._sdk_tools())
-
-    def _sdk_tools(self):
-        """
-        Microsoft Windows SDK Tools paths generator.
-
-        Return
-        ------
-        generator of str
-            paths
-        """
-        if self.vs_ver < 15.0:
-            bin_dir = 'Bin' if self.vs_ver <= 11.0 else r'Bin\x86'
-            yield os.path.join(self.si.WindowsSdkDir, bin_dir)
-
-        if not self.pi.current_is_x86():
-            arch_subdir = self.pi.current_dir(x64=True)
-            path = f'Bin{arch_subdir}'
-            yield os.path.join(self.si.WindowsSdkDir, path)
-
-        if self.vs_ver in (10.0, 11.0):
-            if self.pi.target_is_x86():
-                arch_subdir = ''
-            else:
-                arch_subdir = self.pi.current_dir(hidex86=True, x64=True)
-            path = rf'Bin\NETFX 4.0 Tools{arch_subdir}'
-            yield os.path.join(self.si.WindowsSdkDir, path)
-
-        elif self.vs_ver >= 15.0:
-            path = os.path.join(self.si.WindowsSdkDir, 'Bin')
-            arch_subdir = self.pi.current_dir(x64=True)
-            sdkver = self.si.WindowsSdkLastVersion
-            yield os.path.join(path, f'{sdkver}{arch_subdir}')
-
-        if self.si.WindowsSDKExecutablePath:
-            yield self.si.WindowsSDKExecutablePath
-
-    @property
-    def _sdk_subdir(self):
-        """
-        Microsoft Windows SDK version subdir.
-
-        Return
-        ------
-        str
-            subdir
-        """
-        ucrtver = self.si.WindowsSdkLastVersion
-        return (f'{ucrtver}\\') if ucrtver else ''
-
-    @property
-    def SdkSetup(self):
-        """
-        Microsoft Windows SDK Setup.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver > 9.0:
-            return []
-
-        return [os.path.join(self.si.WindowsSdkDir, 'Setup')]
-
-    @property
-    def FxTools(self):
-        """
-        Microsoft .NET Framework Tools.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        pi = self.pi
-        si = self.si
-
-        if self.vs_ver <= 10.0:
-            include32 = True
-            include64 = not pi.target_is_x86() and not pi.current_is_x86()
-        else:
-            include32 = pi.target_is_x86() or pi.current_is_x86()
-            include64 = pi.current_cpu == 'amd64' or pi.target_cpu == 'amd64'
-
-        tools = []
-        if include32:
-            tools += [
-                os.path.join(si.FrameworkDir32, ver) for ver in si.FrameworkVersion32
-            ]
-        if include64:
-            tools += [
-                os.path.join(si.FrameworkDir64, ver) for ver in si.FrameworkVersion64
-            ]
-        return tools
-
-    @property
-    def NetFxSDKLibraries(self):
-        """
-        Microsoft .Net Framework SDK Libraries.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver < 14.0 or not self.si.NetFxSdkDir:
-            return []
-
-        arch_subdir = self.pi.target_dir(x64=True)
-        return [os.path.join(self.si.NetFxSdkDir, rf'lib\um{arch_subdir}')]
-
-    @property
-    def NetFxSDKIncludes(self):
-        """
-        Microsoft .Net Framework SDK Includes.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver < 14.0 or not self.si.NetFxSdkDir:
-            return []
-
-        return [os.path.join(self.si.NetFxSdkDir, r'include\um')]
-
-    @property
-    def VsTDb(self):
-        """
-        Microsoft Visual Studio Team System Database.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        return [os.path.join(self.si.VSInstallDir, r'VSTSDB\Deploy')]
-
-    @property
-    def MSBuild(self):
-        """
-        Microsoft Build Engine.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver < 12.0:
-            return []
-        elif self.vs_ver < 15.0:
-            base_path = self.si.ProgramFilesx86
-            arch_subdir = self.pi.current_dir(hidex86=True)
-        else:
-            base_path = self.si.VSInstallDir
-            arch_subdir = ''
-
-        path = rf'MSBuild\{self.vs_ver:0.1f}\bin{arch_subdir}'
-        build = [os.path.join(base_path, path)]
-
-        if self.vs_ver >= 15.0:
-            # Add Roslyn C# & Visual Basic Compiler
-            build += [os.path.join(base_path, path, 'Roslyn')]
-
-        return build
-
-    @property
-    def HTMLHelpWorkshop(self):
-        """
-        Microsoft HTML Help Workshop.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver < 11.0:
-            return []
-
-        return [os.path.join(self.si.ProgramFilesx86, 'HTML Help Workshop')]
-
-    @property
-    def UCRTLibraries(self):
-        """
-        Microsoft Universal C Runtime SDK Libraries.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver < 14.0:
-            return []
-
-        arch_subdir = self.pi.target_dir(x64=True)
-        lib = os.path.join(self.si.UniversalCRTSdkDir, 'lib')
-        ucrtver = self._ucrt_subdir
-        return [os.path.join(lib, f'{ucrtver}ucrt{arch_subdir}')]
-
-    @property
-    def UCRTIncludes(self):
-        """
-        Microsoft Universal C Runtime SDK Include.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if self.vs_ver < 14.0:
-            return []
-
-        include = os.path.join(self.si.UniversalCRTSdkDir, 'include')
-        return [os.path.join(include, f'{self._ucrt_subdir}ucrt')]
-
-    @property
-    def _ucrt_subdir(self):
-        """
-        Microsoft Universal C Runtime SDK version subdir.
-
-        Return
-        ------
-        str
-            subdir
-        """
-        ucrtver = self.si.UniversalCRTSdkLastVersion
-        return (f'{ucrtver}\\') if ucrtver else ''
-
-    @property
-    def FSharp(self):
-        """
-        Microsoft Visual F#.
-
-        Return
-        ------
-        list of str
-            paths
-        """
-        if 11.0 > self.vs_ver > 12.0:
-            return []
-
-        return [self.si.FSharpInstallDir]
-
-    @property
-    def VCRuntimeRedist(self) -> str | None:
-        """
-        Microsoft Visual C++ runtime redistributable dll.
-
-        Returns the first suitable path found or None.
-        """
-        vcruntime = f'vcruntime{self.vc_ver}0.dll'
-        arch_subdir = self.pi.target_dir(x64=True).strip('\\')
-
-        # Installation prefixes candidates
-        prefixes = []
-        tools_path = self.si.VCInstallDir
-        redist_path = os.path.dirname(tools_path.replace(r'\Tools', r'\Redist'))
-        if os.path.isdir(redist_path):
-            # Redist version may not be exactly the same as tools
-            redist_path = os.path.join(redist_path, os.listdir(redist_path)[-1])
-            prefixes += [redist_path, os.path.join(redist_path, 'onecore')]
-
-        prefixes += [os.path.join(tools_path, 'redist')]  # VS14 legacy path
-
-        # CRT directory
-        crt_dirs = (
-            f'Microsoft.VC{self.vc_ver * 10}.CRT',
-            # Sometime store in directory with VS version instead of VC
-            f'Microsoft.VC{int(self.vs_ver) * 10}.CRT',
-        )
-
-        # vcruntime path
-        candidate_paths = (
-            os.path.join(prefix, arch_subdir, crt_dir, vcruntime)
-            for (prefix, crt_dir) in itertools.product(prefixes, crt_dirs)
-        )
-        return next(filter(os.path.isfile, candidate_paths), None)  # type: ignore[arg-type] #python/mypy#12682
-
-    def return_env(self, exists: bool = True) -> _EnvironmentDict:
-        """
-        Return environment dict.
-
-        Parameters
-        ----------
-        exists: bool
-            It True, only return existing paths.
-
-        Return
-        ------
-        dict
-            environment
-        """
-        env = _EnvironmentDict(
-            include=self._build_paths(
-                'include',
-                [
-                    self.VCIncludes,
-                    self.OSIncludes,
-                    self.UCRTIncludes,
-                    self.NetFxSDKIncludes,
-                ],
-                exists,
-            ),
-            lib=self._build_paths(
-                'lib',
-                [
-                    self.VCLibraries,
-                    self.OSLibraries,
-                    self.FxTools,
-                    self.UCRTLibraries,
-                    self.NetFxSDKLibraries,
-                ],
-                exists,
-            ),
-            libpath=self._build_paths(
-                'libpath',
-                [self.VCLibraries, self.FxTools, self.VCStoreRefs, self.OSLibpath],
-                exists,
-            ),
-            path=self._build_paths(
-                'path',
-                [
-                    self.VCTools,
-                    self.VSTools,
-                    self.VsTDb,
-                    self.SdkTools,
-                    self.SdkSetup,
-                    self.FxTools,
-                    self.MSBuild,
-                    self.HTMLHelpWorkshop,
-                    self.FSharp,
-                ],
-                exists,
-            ),
-        )
-        if self.vs_ver >= 14 and self.VCRuntimeRedist:
-            env['py_vcruntime_redist'] = self.VCRuntimeRedist
-        return env
-
-    def _build_paths(self, name, spec_path_lists, exists):
-        """
-        Given an environment variable name and specified paths,
-        return a pathsep-separated string of paths containing
-        unique, extant, directories from those paths and from
-        the environment variable. Raise an error if no paths
-        are resolved.
-
-        Parameters
-        ----------
-        name: str
-            Environment variable name
-        spec_path_lists: list of str
-            Paths
-        exists: bool
-            It True, only return existing paths.
-
-        Return
-        ------
-        str
-            Pathsep-separated paths
-        """
-        # flatten spec_path_lists
-        spec_paths = itertools.chain.from_iterable(spec_path_lists)
-        env_paths = environ.get(name, '').split(os.pathsep)
-        paths = itertools.chain(spec_paths, env_paths)
-        extant_paths = list(filter(os.path.isdir, paths)) if exists else paths
-        if not extant_paths:
-            msg = f"{name.upper()} environment variable is empty"
-            raise distutils.errors.DistutilsPlatformError(msg)
-        unique_paths = unique_everseen(extant_paths)
-        return os.pathsep.join(unique_paths)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/namespaces.py b/llmlab/lib/python3.12/site-packages/setuptools/namespaces.py
deleted file mode 100644
index 85ea2eb..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/namespaces.py
+++ /dev/null
@@ -1,106 +0,0 @@
-import itertools
-import os
-
-from .compat import py312
-
-from distutils import log
-
-flatten = itertools.chain.from_iterable
-
-
-class Installer:
-    nspkg_ext = '-nspkg.pth'
-
-    def install_namespaces(self) -> None:
-        nsp = self._get_all_ns_packages()
-        if not nsp:
-            return
-        filename = self._get_nspkg_file()
-        self.outputs.append(filename)
-        log.info("Installing %s", filename)
-        lines = map(self._gen_nspkg_line, nsp)
-
-        if self.dry_run:
-            # always generate the lines, even in dry run
-            list(lines)
-            return
-
-        with open(filename, 'wt', encoding=py312.PTH_ENCODING) as f:
-            # Python<3.13 requires encoding="locale" instead of "utf-8"
-            # See: python/cpython#77102
-            f.writelines(lines)
-
-    def uninstall_namespaces(self) -> None:
-        filename = self._get_nspkg_file()
-        if not os.path.exists(filename):
-            return
-        log.info("Removing %s", filename)
-        os.remove(filename)
-
-    def _get_nspkg_file(self):
-        filename, _ = os.path.splitext(self._get_target())
-        return filename + self.nspkg_ext
-
-    def _get_target(self):
-        return self.target
-
-    _nspkg_tmpl = (
-        "import sys, types, os",
-        "p = os.path.join(%(root)s, *%(pth)r)",
-        "importlib = __import__('importlib.util')",
-        "__import__('importlib.machinery')",
-        (
-            "m = "
-            "sys.modules.setdefault(%(pkg)r, "
-            "importlib.util.module_from_spec("
-            "importlib.machinery.PathFinder.find_spec(%(pkg)r, "
-            "[os.path.dirname(p)])))"
-        ),
-        ("m = m or sys.modules.setdefault(%(pkg)r, types.ModuleType(%(pkg)r))"),
-        "mp = (m or []) and m.__dict__.setdefault('__path__',[])",
-        "(p not in mp) and mp.append(p)",
-    )
-    "lines for the namespace installer"
-
-    _nspkg_tmpl_multi = ('m and setattr(sys.modules[%(parent)r], %(child)r, m)',)
-    "additional line(s) when a parent package is indicated"
-
-    def _get_root(self):
-        return "sys._getframe(1).f_locals['sitedir']"
-
-    def _gen_nspkg_line(self, pkg):
-        pth = tuple(pkg.split('.'))
-        root = self._get_root()
-        tmpl_lines = self._nspkg_tmpl
-        parent, sep, child = pkg.rpartition('.')
-        if parent:
-            tmpl_lines += self._nspkg_tmpl_multi
-        return ';'.join(tmpl_lines) % locals() + '\n'
-
-    def _get_all_ns_packages(self):
-        """Return sorted list of all package namespaces"""
-        pkgs = self.distribution.namespace_packages or []
-        return sorted(set(flatten(map(self._pkg_names, pkgs))))
-
-    @staticmethod
-    def _pkg_names(pkg):
-        """
-        Given a namespace package, yield the components of that
-        package.
-
-        >>> names = Installer._pkg_names('a.b.c')
-        >>> set(names) == set(['a', 'a.b', 'a.b.c'])
-        True
-        """
-        parts = pkg.split('.')
-        while parts:
-            yield '.'.join(parts)
-            parts.pop()
-
-
-class DevelopInstaller(Installer):
-    def _get_root(self):
-        return repr(str(self.egg_path))
-
-    def _get_target(self):
-        return self.egg_link
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/package_index.py b/llmlab/lib/python3.12/site-packages/setuptools/package_index.py
deleted file mode 100644
index 1a6abeb..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/package_index.py
+++ /dev/null
@@ -1,1137 +0,0 @@
-"""PyPI and direct package downloading."""
-
-from __future__ import annotations
-
-import base64
-import configparser
-import hashlib
-import html
-import http.client
-import io
-import itertools
-import os
-import re
-import shutil
-import socket
-import subprocess
-import sys
-import urllib.error
-import urllib.parse
-import urllib.request
-from fnmatch import translate
-from functools import wraps
-from typing import NamedTuple
-
-from more_itertools import unique_everseen
-
-import setuptools
-from pkg_resources import (
-    BINARY_DIST,
-    CHECKOUT_DIST,
-    DEVELOP_DIST,
-    EGG_DIST,
-    SOURCE_DIST,
-    Distribution,
-    Environment,
-    Requirement,
-    find_distributions,
-    normalize_path,
-    parse_version,
-    safe_name,
-    safe_version,
-    to_filename,
-)
-from setuptools.wheel import Wheel
-
-from .unicode_utils import _cfg_read_utf8_with_fallback, _read_utf8_with_fallback
-
-from distutils import log
-from distutils.errors import DistutilsError
-
-EGG_FRAGMENT = re.compile(r'^egg=([-A-Za-z0-9_.+!]+)$')
-HREF = re.compile(r"""href\s*=\s*['"]?([^'"> ]+)""", re.I)
-PYPI_MD5 = re.compile(
-    r'([^<]+)\n\s+\(md5\)'
-)
-URL_SCHEME = re.compile('([-+.a-z0-9]{2,}):', re.I).match
-EXTENSIONS = ".tar.gz .tar.bz2 .tar .zip .tgz".split()
-
-__all__ = [
-    'PackageIndex',
-    'distros_for_url',
-    'parse_bdist_wininst',
-    'interpret_distro_name',
-]
-
-_SOCKET_TIMEOUT = 15
-
-user_agent = f"setuptools/{setuptools.__version__} Python-urllib/{sys.version_info.major}.{sys.version_info.minor}"
-
-
-def parse_requirement_arg(spec):
-    try:
-        return Requirement.parse(spec)
-    except ValueError as e:
-        raise DistutilsError(
-            f"Not a URL, existing file, or requirement spec: {spec!r}"
-        ) from e
-
-
-def parse_bdist_wininst(name):
-    """Return (base,pyversion) or (None,None) for possible .exe name"""
-
-    lower = name.lower()
-    base, py_ver, plat = None, None, None
-
-    if lower.endswith('.exe'):
-        if lower.endswith('.win32.exe'):
-            base = name[:-10]
-            plat = 'win32'
-        elif lower.startswith('.win32-py', -16):
-            py_ver = name[-7:-4]
-            base = name[:-16]
-            plat = 'win32'
-        elif lower.endswith('.win-amd64.exe'):
-            base = name[:-14]
-            plat = 'win-amd64'
-        elif lower.startswith('.win-amd64-py', -20):
-            py_ver = name[-7:-4]
-            base = name[:-20]
-            plat = 'win-amd64'
-    return base, py_ver, plat
-
-
-def egg_info_for_url(url):
-    parts = urllib.parse.urlparse(url)
-    _scheme, server, path, _parameters, _query, fragment = parts
-    base = urllib.parse.unquote(path.split('/')[-1])
-    if server == 'sourceforge.net' and base == 'download':  # XXX Yuck
-        base = urllib.parse.unquote(path.split('/')[-2])
-    if '#' in base:
-        base, fragment = base.split('#', 1)
-    return base, fragment
-
-
-def distros_for_url(url, metadata=None):
-    """Yield egg or source distribution objects that might be found at a URL"""
-    base, fragment = egg_info_for_url(url)
-    yield from distros_for_location(url, base, metadata)
-    if fragment:
-        match = EGG_FRAGMENT.match(fragment)
-        if match:
-            yield from interpret_distro_name(
-                url, match.group(1), metadata, precedence=CHECKOUT_DIST
-            )
-
-
-def distros_for_location(location, basename, metadata=None):
-    """Yield egg or source distribution objects based on basename"""
-    if basename.endswith('.egg.zip'):
-        basename = basename[:-4]  # strip the .zip
-    if basename.endswith('.egg') and '-' in basename:
-        # only one, unambiguous interpretation
-        return [Distribution.from_location(location, basename, metadata)]
-    if basename.endswith('.whl') and '-' in basename:
-        wheel = Wheel(basename)
-        if not wheel.is_compatible():
-            return []
-        return [
-            Distribution(
-                location=location,
-                project_name=wheel.project_name,
-                version=wheel.version,
-                # Increase priority over eggs.
-                precedence=EGG_DIST + 1,
-            )
-        ]
-    if basename.endswith('.exe'):
-        win_base, py_ver, platform = parse_bdist_wininst(basename)
-        if win_base is not None:
-            return interpret_distro_name(
-                location, win_base, metadata, py_ver, BINARY_DIST, platform
-            )
-    # Try source distro extensions (.zip, .tgz, etc.)
-    #
-    for ext in EXTENSIONS:
-        if basename.endswith(ext):
-            basename = basename[: -len(ext)]
-            return interpret_distro_name(location, basename, metadata)
-    return []  # no extension matched
-
-
-def distros_for_filename(filename, metadata=None):
-    """Yield possible egg or source distribution objects based on a filename"""
-    return distros_for_location(
-        normalize_path(filename), os.path.basename(filename), metadata
-    )
-
-
-def interpret_distro_name(
-    location, basename, metadata, py_version=None, precedence=SOURCE_DIST, platform=None
-):
-    """Generate the interpretation of a source distro name
-
-    Note: if `location` is a filesystem filename, you should call
-    ``pkg_resources.normalize_path()`` on it before passing it to this
-    routine!
-    """
-
-    parts = basename.split('-')
-    if not py_version and any(re.match(r'py\d\.\d$', p) for p in parts[2:]):
-        # it is a bdist_dumb, not an sdist -- bail out
-        return
-
-    # find the pivot (p) that splits the name from the version.
-    # infer the version as the first item that has a digit.
-    for p in range(len(parts)):
-        if parts[p][:1].isdigit():
-            break
-    else:
-        p = len(parts)
-
-    yield Distribution(
-        location,
-        metadata,
-        '-'.join(parts[:p]),
-        '-'.join(parts[p:]),
-        py_version=py_version,
-        precedence=precedence,
-        platform=platform,
-    )
-
-
-def unique_values(func):
-    """
-    Wrap a function returning an iterable such that the resulting iterable
-    only ever yields unique items.
-    """
-
-    @wraps(func)
-    def wrapper(*args, **kwargs):
-        return unique_everseen(func(*args, **kwargs))
-
-    return wrapper
-
-
-REL = re.compile(r"""<([^>]*\srel\s{0,10}=\s{0,10}['"]?([^'" >]+)[^>]*)>""", re.I)
-"""
-Regex for an HTML tag with 'rel="val"' attributes.
-"""
-
-
-@unique_values
-def find_external_links(url, page):
-    """Find rel="homepage" and rel="download" links in `page`, yielding URLs"""
-
-    for match in REL.finditer(page):
-        tag, rel = match.groups()
-        rels = set(map(str.strip, rel.lower().split(',')))
-        if 'homepage' in rels or 'download' in rels:
-            for match in HREF.finditer(tag):
-                yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
-
-    for tag in ("Home Page", "Download URL"):
-        pos = page.find(tag)
-        if pos != -1:
-            match = HREF.search(page, pos)
-            if match:
-                yield urllib.parse.urljoin(url, htmldecode(match.group(1)))
-
-
-class ContentChecker:
-    """
-    A null content checker that defines the interface for checking content
-    """
-
-    def feed(self, block):
-        """
-        Feed a block of data to the hash.
-        """
-        return
-
-    def is_valid(self):
-        """
-        Check the hash. Return False if validation fails.
-        """
-        return True
-
-    def report(self, reporter, template):
-        """
-        Call reporter with information about the checker (hash name)
-        substituted into the template.
-        """
-        return
-
-
-class HashChecker(ContentChecker):
-    pattern = re.compile(
-        r'(?Psha1|sha224|sha384|sha256|sha512|md5)='
-        r'(?P[a-f0-9]+)'
-    )
-
-    def __init__(self, hash_name, expected) -> None:
-        self.hash_name = hash_name
-        self.hash = hashlib.new(hash_name)
-        self.expected = expected
-
-    @classmethod
-    def from_url(cls, url):
-        "Construct a (possibly null) ContentChecker from a URL"
-        fragment = urllib.parse.urlparse(url)[-1]
-        if not fragment:
-            return ContentChecker()
-        match = cls.pattern.search(fragment)
-        if not match:
-            return ContentChecker()
-        return cls(**match.groupdict())
-
-    def feed(self, block):
-        self.hash.update(block)
-
-    def is_valid(self):
-        return self.hash.hexdigest() == self.expected
-
-    def report(self, reporter, template):
-        msg = template % self.hash_name
-        return reporter(msg)
-
-
-class PackageIndex(Environment):
-    """A distribution index that scans web pages for download URLs"""
-
-    def __init__(
-        self,
-        index_url: str = "https://pypi.org/simple/",
-        hosts=('*',),
-        ca_bundle=None,
-        verify_ssl: bool = True,
-        *args,
-        **kw,
-    ) -> None:
-        super().__init__(*args, **kw)
-        self.index_url = index_url + "/"[: not index_url.endswith('/')]
-        self.scanned_urls: dict = {}
-        self.fetched_urls: dict = {}
-        self.package_pages: dict = {}
-        self.allows = re.compile('|'.join(map(translate, hosts))).match
-        self.to_scan: list = []
-        self.opener = urllib.request.urlopen
-
-    def add(self, dist):
-        # ignore invalid versions
-        try:
-            parse_version(dist.version)
-        except Exception:
-            return None
-        return super().add(dist)
-
-    # FIXME: 'PackageIndex.process_url' is too complex (14)
-    def process_url(self, url, retrieve: bool = False) -> None:  # noqa: C901
-        """Evaluate a URL as a possible download, and maybe retrieve it"""
-        if url in self.scanned_urls and not retrieve:
-            return
-        self.scanned_urls[url] = True
-        if not URL_SCHEME(url):
-            self.process_filename(url)
-            return
-        else:
-            dists = list(distros_for_url(url))
-            if dists:
-                if not self.url_ok(url):
-                    return
-                self.debug("Found link: %s", url)
-
-        if dists or not retrieve or url in self.fetched_urls:
-            list(map(self.add, dists))
-            return  # don't need the actual page
-
-        if not self.url_ok(url):
-            self.fetched_urls[url] = True
-            return
-
-        self.info("Reading %s", url)
-        self.fetched_urls[url] = True  # prevent multiple fetch attempts
-        tmpl = "Download error on %s: %%s -- Some packages may not be found!"
-        f = self.open_url(url, tmpl % url)
-        if f is None:
-            return
-        if isinstance(f, urllib.error.HTTPError) and f.code == 401:
-            self.info(f"Authentication error: {f.msg}")
-        self.fetched_urls[f.url] = True
-        if 'html' not in f.headers.get('content-type', '').lower():
-            f.close()  # not html, we can't process it
-            return
-
-        base = f.url  # handle redirects
-        page = f.read()
-        if not isinstance(page, str):
-            # In Python 3 and got bytes but want str.
-            if isinstance(f, urllib.error.HTTPError):
-                # Errors have no charset, assume latin1:
-                charset = 'latin-1'
-            else:
-                charset = f.headers.get_param('charset') or 'latin-1'
-            page = page.decode(charset, "ignore")
-        f.close()
-        for match in HREF.finditer(page):
-            link = urllib.parse.urljoin(base, htmldecode(match.group(1)))
-            self.process_url(link)
-        if url.startswith(self.index_url) and getattr(f, 'code', None) != 404:
-            page = self.process_index(url, page)
-
-    def process_filename(self, fn, nested: bool = False) -> None:
-        # process filenames or directories
-        if not os.path.exists(fn):
-            self.warn("Not found: %s", fn)
-            return
-
-        if os.path.isdir(fn) and not nested:
-            path = os.path.realpath(fn)
-            for item in os.listdir(path):
-                self.process_filename(os.path.join(path, item), True)
-
-        dists = distros_for_filename(fn)
-        if dists:
-            self.debug("Found: %s", fn)
-            list(map(self.add, dists))
-
-    def url_ok(self, url, fatal: bool = False) -> bool:
-        s = URL_SCHEME(url)
-        is_file = s and s.group(1).lower() == 'file'
-        if is_file or self.allows(urllib.parse.urlparse(url)[1]):
-            return True
-        msg = (
-            "\nNote: Bypassing %s (disallowed host; see "
-            "https://setuptools.pypa.io/en/latest/deprecated/"
-            "easy_install.html#restricting-downloads-with-allow-hosts for details).\n"
-        )
-        if fatal:
-            raise DistutilsError(msg % url)
-        else:
-            self.warn(msg, url)
-            return False
-
-    def scan_egg_links(self, search_path) -> None:
-        dirs = filter(os.path.isdir, search_path)
-        egg_links = (
-            (path, entry)
-            for path in dirs
-            for entry in os.listdir(path)
-            if entry.endswith('.egg-link')
-        )
-        list(itertools.starmap(self.scan_egg_link, egg_links))
-
-    def scan_egg_link(self, path, entry) -> None:
-        content = _read_utf8_with_fallback(os.path.join(path, entry))
-        # filter non-empty lines
-        lines = list(filter(None, map(str.strip, content.splitlines())))
-
-        if len(lines) != 2:
-            # format is not recognized; punt
-            return
-
-        egg_path, _setup_path = lines
-
-        for dist in find_distributions(os.path.join(path, egg_path)):
-            dist.location = os.path.join(path, *lines)
-            dist.precedence = SOURCE_DIST
-            self.add(dist)
-
-    def _scan(self, link):
-        # Process a URL to see if it's for a package page
-        NO_MATCH_SENTINEL = None, None
-        if not link.startswith(self.index_url):
-            return NO_MATCH_SENTINEL
-
-        parts = list(map(urllib.parse.unquote, link[len(self.index_url) :].split('/')))
-        if len(parts) != 2 or '#' in parts[1]:
-            return NO_MATCH_SENTINEL
-
-        # it's a package page, sanitize and index it
-        pkg = safe_name(parts[0])
-        ver = safe_version(parts[1])
-        self.package_pages.setdefault(pkg.lower(), {})[link] = True
-        return to_filename(pkg), to_filename(ver)
-
-    def process_index(self, url, page):
-        """Process the contents of a PyPI page"""
-
-        # process an index page into the package-page index
-        for match in HREF.finditer(page):
-            try:
-                self._scan(urllib.parse.urljoin(url, htmldecode(match.group(1))))
-            except ValueError:
-                pass
-
-        pkg, ver = self._scan(url)  # ensure this page is in the page index
-        if not pkg:
-            return ""  # no sense double-scanning non-package pages
-
-        # process individual package page
-        for new_url in find_external_links(url, page):
-            # Process the found URL
-            base, frag = egg_info_for_url(new_url)
-            if base.endswith('.py') and not frag:
-                if ver:
-                    new_url += f'#egg={pkg}-{ver}'
-                else:
-                    self.need_version_info(url)
-            self.scan_url(new_url)
-
-        return PYPI_MD5.sub(
-            lambda m: '{}'.format(*m.group(1, 3, 2)), page
-        )
-
-    def need_version_info(self, url) -> None:
-        self.scan_all(
-            "Page at %s links to .py file(s) without version info; an index "
-            "scan is required.",
-            url,
-        )
-
-    def scan_all(self, msg=None, *args) -> None:
-        if self.index_url not in self.fetched_urls:
-            if msg:
-                self.warn(msg, *args)
-            self.info("Scanning index of all packages (this may take a while)")
-        self.scan_url(self.index_url)
-
-    def find_packages(self, requirement) -> None:
-        self.scan_url(self.index_url + requirement.unsafe_name + '/')
-
-        if not self.package_pages.get(requirement.key):
-            # Fall back to safe version of the name
-            self.scan_url(self.index_url + requirement.project_name + '/')
-
-        if not self.package_pages.get(requirement.key):
-            # We couldn't find the target package, so search the index page too
-            self.not_found_in_index(requirement)
-
-        for url in list(self.package_pages.get(requirement.key, ())):
-            # scan each page that might be related to the desired package
-            self.scan_url(url)
-
-    def obtain(self, requirement, installer=None):
-        self.prescan()
-        self.find_packages(requirement)
-        for dist in self[requirement.key]:
-            if dist in requirement:
-                return dist
-            self.debug("%s does not match %s", requirement, dist)
-        return super().obtain(requirement, installer)
-
-    def check_hash(self, checker, filename, tfp) -> None:
-        """
-        checker is a ContentChecker
-        """
-        checker.report(self.debug, f"Validating %s checksum for {filename}")
-        if not checker.is_valid():
-            tfp.close()
-            os.unlink(filename)
-            raise DistutilsError(
-                f"{checker.hash.name} validation failed for {os.path.basename(filename)}; "
-                "possible download problem?"
-            )
-
-    def add_find_links(self, urls) -> None:
-        """Add `urls` to the list that will be prescanned for searches"""
-        for url in urls:
-            if (
-                self.to_scan is None  # if we have already "gone online"
-                or not URL_SCHEME(url)  # or it's a local file/directory
-                or url.startswith('file:')
-                or list(distros_for_url(url))  # or a direct package link
-            ):
-                # then go ahead and process it now
-                self.scan_url(url)
-            else:
-                # otherwise, defer retrieval till later
-                self.to_scan.append(url)
-
-    def prescan(self):
-        """Scan urls scheduled for prescanning (e.g. --find-links)"""
-        if self.to_scan:
-            list(map(self.scan_url, self.to_scan))
-        self.to_scan = None  # from now on, go ahead and process immediately
-
-    def not_found_in_index(self, requirement) -> None:
-        if self[requirement.key]:  # we've seen at least one distro
-            meth, msg = self.info, "Couldn't retrieve index page for %r"
-        else:  # no distros seen for this name, might be misspelled
-            meth, msg = self.warn, "Couldn't find index page for %r (maybe misspelled?)"
-        meth(msg, requirement.unsafe_name)
-        self.scan_all()
-
-    def download(self, spec, tmpdir):
-        """Locate and/or download `spec` to `tmpdir`, returning a local path
-
-        `spec` may be a ``Requirement`` object, or a string containing a URL,
-        an existing local filename, or a project/version requirement spec
-        (i.e. the string form of a ``Requirement`` object).  If it is the URL
-        of a .py file with an unambiguous ``#egg=name-version`` tag (i.e., one
-        that escapes ``-`` as ``_`` throughout), a trivial ``setup.py`` is
-        automatically created alongside the downloaded file.
-
-        If `spec` is a ``Requirement`` object or a string containing a
-        project/version requirement spec, this method returns the location of
-        a matching distribution (possibly after downloading it to `tmpdir`).
-        If `spec` is a locally existing file or directory name, it is simply
-        returned unchanged.  If `spec` is a URL, it is downloaded to a subpath
-        of `tmpdir`, and the local filename is returned.  Various errors may be
-        raised if a problem occurs during downloading.
-        """
-        if not isinstance(spec, Requirement):
-            scheme = URL_SCHEME(spec)
-            if scheme:
-                # It's a url, download it to tmpdir
-                found = self._download_url(spec, tmpdir)
-                base, fragment = egg_info_for_url(spec)
-                if base.endswith('.py'):
-                    found = self.gen_setup(found, fragment, tmpdir)
-                return found
-            elif os.path.exists(spec):
-                # Existing file or directory, just return it
-                return spec
-            else:
-                spec = parse_requirement_arg(spec)
-        return getattr(self.fetch_distribution(spec, tmpdir), 'location', None)
-
-    def fetch_distribution(  # noqa: C901  # is too complex (14)  # FIXME
-        self,
-        requirement,
-        tmpdir,
-        force_scan: bool = False,
-        source: bool = False,
-        develop_ok: bool = False,
-        local_index=None,
-    ) -> Distribution | None:
-        """Obtain a distribution suitable for fulfilling `requirement`
-
-        `requirement` must be a ``pkg_resources.Requirement`` instance.
-        If necessary, or if the `force_scan` flag is set, the requirement is
-        searched for in the (online) package index as well as the locally
-        installed packages.  If a distribution matching `requirement` is found,
-        the returned distribution's ``location`` is the value you would have
-        gotten from calling the ``download()`` method with the matching
-        distribution's URL or filename.  If no matching distribution is found,
-        ``None`` is returned.
-
-        If the `source` flag is set, only source distributions and source
-        checkout links will be considered.  Unless the `develop_ok` flag is
-        set, development and system eggs (i.e., those using the ``.egg-info``
-        format) will be ignored.
-        """
-        # process a Requirement
-        self.info("Searching for %s", requirement)
-        skipped = set()
-        dist = None
-
-        def find(req, env: Environment | None = None):
-            if env is None:
-                env = self
-            # Find a matching distribution; may be called more than once
-
-            for dist in env[req.key]:
-                if dist.precedence == DEVELOP_DIST and not develop_ok:
-                    if dist not in skipped:
-                        self.warn(
-                            "Skipping development or system egg: %s",
-                            dist,
-                        )
-                        skipped.add(dist)
-                    continue
-
-                test = dist in req and (dist.precedence <= SOURCE_DIST or not source)
-                if test:
-                    loc = self.download(dist.location, tmpdir)
-                    dist.download_location = loc
-                    if os.path.exists(dist.download_location):
-                        return dist
-
-            return None
-
-        if force_scan:
-            self.prescan()
-            self.find_packages(requirement)
-            dist = find(requirement)
-
-        if not dist and local_index is not None:
-            dist = find(requirement, local_index)
-
-        if dist is None:
-            if self.to_scan is not None:
-                self.prescan()
-            dist = find(requirement)
-
-        if dist is None and not force_scan:
-            self.find_packages(requirement)
-            dist = find(requirement)
-
-        if dist is None:
-            self.warn(
-                "No local packages or working download links found for %s%s",
-                (source and "a source distribution of " or ""),
-                requirement,
-            )
-            return None
-        else:
-            self.info("Best match: %s", dist)
-            return dist.clone(location=dist.download_location)
-
-    def fetch(
-        self, requirement, tmpdir, force_scan: bool = False, source: bool = False
-    ) -> str | None:
-        """Obtain a file suitable for fulfilling `requirement`
-
-        DEPRECATED; use the ``fetch_distribution()`` method now instead.  For
-        backward compatibility, this routine is identical but returns the
-        ``location`` of the downloaded distribution instead of a distribution
-        object.
-        """
-        dist = self.fetch_distribution(requirement, tmpdir, force_scan, source)
-        if dist is not None:
-            return dist.location
-        return None
-
-    def gen_setup(self, filename, fragment, tmpdir):
-        match = EGG_FRAGMENT.match(fragment)
-        dists = (
-            match
-            and [
-                d
-                for d in interpret_distro_name(filename, match.group(1), None)
-                if d.version
-            ]
-            or []
-        )
-
-        if len(dists) == 1:  # unambiguous ``#egg`` fragment
-            basename = os.path.basename(filename)
-
-            # Make sure the file has been downloaded to the temp dir.
-            if os.path.dirname(filename) != tmpdir:
-                dst = os.path.join(tmpdir, basename)
-                if not (os.path.exists(dst) and os.path.samefile(filename, dst)):
-                    shutil.copy2(filename, dst)
-                    filename = dst
-
-            with open(os.path.join(tmpdir, 'setup.py'), 'w', encoding="utf-8") as file:
-                file.write(
-                    "from setuptools import setup\n"
-                    f"setup(name={dists[0].project_name!r}, version={dists[0].version!r}, py_modules=[{os.path.splitext(basename)[0]!r}])\n"
-                )
-            return filename
-
-        elif match:
-            raise DistutilsError(
-                f"Can't unambiguously interpret project/version identifier {fragment!r}; "
-                "any dashes in the name or version should be escaped using "
-                f"underscores. {dists!r}"
-            )
-        else:
-            raise DistutilsError(
-                "Can't process plain .py files without an '#egg=name-version'"
-                " suffix to enable automatic setup script generation."
-            )
-
-    dl_blocksize = 8192
-
-    def _download_to(self, url, filename):
-        self.info("Downloading %s", url)
-        # Download the file
-        fp = None
-        try:
-            checker = HashChecker.from_url(url)
-            fp = self.open_url(url)
-            if isinstance(fp, urllib.error.HTTPError):
-                raise DistutilsError(f"Can't download {url}: {fp.code} {fp.msg}")
-            headers = fp.info()
-            blocknum = 0
-            bs = self.dl_blocksize
-            size = -1
-            if "content-length" in headers:
-                # Some servers return multiple Content-Length headers :(
-                sizes = headers.get_all('Content-Length')
-                size = max(map(int, sizes))
-                self.reporthook(url, filename, blocknum, bs, size)
-            with open(filename, 'wb') as tfp:
-                while True:
-                    block = fp.read(bs)
-                    if block:
-                        checker.feed(block)
-                        tfp.write(block)
-                        blocknum += 1
-                        self.reporthook(url, filename, blocknum, bs, size)
-                    else:
-                        break
-                self.check_hash(checker, filename, tfp)
-            return headers
-        finally:
-            if fp:
-                fp.close()
-
-    def reporthook(self, url, filename, blocknum, blksize, size) -> None:
-        pass  # no-op
-
-    # FIXME:
-    def open_url(self, url, warning=None):  # noqa: C901  # is too complex (12)
-        if url.startswith('file:'):
-            return local_open(url)
-        try:
-            return open_with_auth(url, self.opener)
-        except (ValueError, http.client.InvalidURL) as v:
-            msg = ' '.join([str(arg) for arg in v.args])
-            if warning:
-                self.warn(warning, msg)
-            else:
-                raise DistutilsError(f'{url} {msg}') from v
-        except urllib.error.HTTPError as v:
-            return v
-        except urllib.error.URLError as v:
-            if warning:
-                self.warn(warning, v.reason)
-            else:
-                raise DistutilsError(f"Download error for {url}: {v.reason}") from v
-        except http.client.BadStatusLine as v:
-            if warning:
-                self.warn(warning, v.line)
-            else:
-                raise DistutilsError(
-                    f'{url} returned a bad status line. The server might be '
-                    f'down, {v.line}'
-                ) from v
-        except (http.client.HTTPException, OSError) as v:
-            if warning:
-                self.warn(warning, v)
-            else:
-                raise DistutilsError(f"Download error for {url}: {v}") from v
-
-    def _download_url(self, url, tmpdir):
-        # Determine download filename
-        #
-        name, _fragment = egg_info_for_url(url)
-        if name:
-            while '..' in name:
-                name = name.replace('..', '.').replace('\\', '_')
-        else:
-            name = "__downloaded__"  # default if URL has no path contents
-
-        if name.endswith('.egg.zip'):
-            name = name[:-4]  # strip the extra .zip before download
-
-        filename = os.path.join(tmpdir, name)
-
-        return self._download_vcs(url, filename) or self._download_other(url, filename)
-
-    @staticmethod
-    def _resolve_vcs(url):
-        """
-        >>> rvcs = PackageIndex._resolve_vcs
-        >>> rvcs('git+http://foo/bar')
-        'git'
-        >>> rvcs('hg+https://foo/bar')
-        'hg'
-        >>> rvcs('git:myhost')
-        'git'
-        >>> rvcs('hg:myhost')
-        >>> rvcs('http://foo/bar')
-        """
-        scheme = urllib.parse.urlsplit(url).scheme
-        pre, sep, _post = scheme.partition('+')
-        # svn and git have their own protocol; hg does not
-        allowed = set(['svn', 'git'] + ['hg'] * bool(sep))
-        return next(iter({pre} & allowed), None)
-
-    def _download_vcs(self, url, spec_filename):
-        vcs = self._resolve_vcs(url)
-        if not vcs:
-            return None
-        if vcs == 'svn':
-            raise DistutilsError(
-                f"Invalid config, SVN download is not supported: {url}"
-            )
-
-        filename, _, _ = spec_filename.partition('#')
-        url, rev = self._vcs_split_rev_from_url(url)
-
-        self.info(f"Doing {vcs} clone from {url} to {filename}")
-        subprocess.check_call([vcs, 'clone', '--quiet', url, filename])
-
-        co_commands = dict(
-            git=[vcs, '-C', filename, 'checkout', '--quiet', rev],
-            hg=[vcs, '--cwd', filename, 'up', '-C', '-r', rev, '-q'],
-        )
-        if rev is not None:
-            self.info(f"Checking out {rev}")
-            subprocess.check_call(co_commands[vcs])
-
-        return filename
-
-    def _download_other(self, url, filename):
-        scheme = urllib.parse.urlsplit(url).scheme
-        if scheme == 'file':  # pragma: no cover
-            return urllib.request.url2pathname(urllib.parse.urlparse(url).path)
-        # raise error if not allowed
-        self.url_ok(url, True)
-        return self._attempt_download(url, filename)
-
-    def scan_url(self, url) -> None:
-        self.process_url(url, True)
-
-    def _attempt_download(self, url, filename):
-        headers = self._download_to(url, filename)
-        if 'html' in headers.get('content-type', '').lower():
-            return self._invalid_download_html(url, headers, filename)
-        else:
-            return filename
-
-    def _invalid_download_html(self, url, headers, filename):
-        os.unlink(filename)
-        raise DistutilsError(f"Unexpected HTML page found at {url}")
-
-    @staticmethod
-    def _vcs_split_rev_from_url(url):
-        """
-        Given a possible VCS URL, return a clean URL and resolved revision if any.
-
-        >>> vsrfu = PackageIndex._vcs_split_rev_from_url
-        >>> vsrfu('git+https://github.com/pypa/setuptools@v69.0.0#egg-info=setuptools')
-        ('https://github.com/pypa/setuptools', 'v69.0.0')
-        >>> vsrfu('git+https://github.com/pypa/setuptools#egg-info=setuptools')
-        ('https://github.com/pypa/setuptools', None)
-        >>> vsrfu('http://foo/bar')
-        ('http://foo/bar', None)
-        """
-        parts = urllib.parse.urlsplit(url)
-
-        clean_scheme = parts.scheme.split('+', 1)[-1]
-
-        # Some fragment identification fails
-        no_fragment_path, _, _ = parts.path.partition('#')
-
-        pre, sep, post = no_fragment_path.rpartition('@')
-        clean_path, rev = (pre, post) if sep else (post, None)
-
-        resolved = parts._replace(
-            scheme=clean_scheme,
-            path=clean_path,
-            # discard the fragment
-            fragment='',
-        ).geturl()
-
-        return resolved, rev
-
-    def debug(self, msg, *args) -> None:
-        log.debug(msg, *args)
-
-    def info(self, msg, *args) -> None:
-        log.info(msg, *args)
-
-    def warn(self, msg, *args) -> None:
-        log.warn(msg, *args)
-
-
-# This pattern matches a character entity reference (a decimal numeric
-# references, a hexadecimal numeric reference, or a named reference).
-entity_sub = re.compile(r'&(#(\d+|x[\da-fA-F]+)|[\w.:-]+);?').sub
-
-
-def decode_entity(match):
-    what = match.group(0)
-    return html.unescape(what)
-
-
-def htmldecode(text):
-    """
-    Decode HTML entities in the given text.
-
-    >>> htmldecode(
-    ...     'https://../package_name-0.1.2.tar.gz'
-    ...     '?tokena=A&tokenb=B">package_name-0.1.2.tar.gz')
-    'https://../package_name-0.1.2.tar.gz?tokena=A&tokenb=B">package_name-0.1.2.tar.gz'
-    """
-    return entity_sub(decode_entity, text)
-
-
-def socket_timeout(timeout=15):
-    def _socket_timeout(func):
-        def _socket_timeout(*args, **kwargs):
-            old_timeout = socket.getdefaulttimeout()
-            socket.setdefaulttimeout(timeout)
-            try:
-                return func(*args, **kwargs)
-            finally:
-                socket.setdefaulttimeout(old_timeout)
-
-        return _socket_timeout
-
-    return _socket_timeout
-
-
-def _encode_auth(auth):
-    """
-    Encode auth from a URL suitable for an HTTP header.
-    >>> str(_encode_auth('username%3Apassword'))
-    'dXNlcm5hbWU6cGFzc3dvcmQ='
-
-    Long auth strings should not cause a newline to be inserted.
-    >>> long_auth = 'username:' + 'password'*10
-    >>> chr(10) in str(_encode_auth(long_auth))
-    False
-    """
-    auth_s = urllib.parse.unquote(auth)
-    # convert to bytes
-    auth_bytes = auth_s.encode()
-    encoded_bytes = base64.b64encode(auth_bytes)
-    # convert back to a string
-    encoded = encoded_bytes.decode()
-    # strip the trailing carriage return
-    return encoded.replace('\n', '')
-
-
-class Credential(NamedTuple):
-    """
-    A username/password pair.
-
-    Displayed separated by `:`.
-    >>> str(Credential('username', 'password'))
-    'username:password'
-    """
-
-    username: str
-    password: str
-
-    def __str__(self) -> str:
-        return f'{self.username}:{self.password}'
-
-
-class PyPIConfig(configparser.RawConfigParser):
-    def __init__(self):
-        """
-        Load from ~/.pypirc
-        """
-        defaults = dict.fromkeys(['username', 'password', 'repository'], '')
-        super().__init__(defaults)
-
-        rc = os.path.join(os.path.expanduser('~'), '.pypirc')
-        if os.path.exists(rc):
-            _cfg_read_utf8_with_fallback(self, rc)
-
-    @property
-    def creds_by_repository(self):
-        sections_with_repositories = [
-            section
-            for section in self.sections()
-            if self.get(section, 'repository').strip()
-        ]
-
-        return dict(map(self._get_repo_cred, sections_with_repositories))
-
-    def _get_repo_cred(self, section):
-        repo = self.get(section, 'repository').strip()
-        return repo, Credential(
-            self.get(section, 'username').strip(),
-            self.get(section, 'password').strip(),
-        )
-
-    def find_credential(self, url):
-        """
-        If the URL indicated appears to be a repository defined in this
-        config, return the credential for that repository.
-        """
-        for repository, cred in self.creds_by_repository.items():
-            if url.startswith(repository):
-                return cred
-        return None
-
-
-def open_with_auth(url, opener=urllib.request.urlopen):
-    """Open a urllib2 request, handling HTTP authentication"""
-
-    parsed = urllib.parse.urlparse(url)
-    scheme, netloc, path, params, query, frag = parsed
-
-    # Double scheme does not raise on macOS as revealed by a
-    # failing test. We would expect "nonnumeric port". Refs #20.
-    if netloc.endswith(':'):
-        raise http.client.InvalidURL("nonnumeric port: ''")
-
-    if scheme in ('http', 'https'):
-        auth, address = _splituser(netloc)
-    else:
-        auth, address = (None, None)
-
-    if not auth:
-        cred = PyPIConfig().find_credential(url)
-        if cred:
-            auth = str(cred)
-            info = cred.username, url
-            log.info('Authenticating as %s for %s (from .pypirc)', *info)
-
-    if auth:
-        auth = "Basic " + _encode_auth(auth)
-        parts = scheme, address, path, params, query, frag
-        new_url = urllib.parse.urlunparse(parts)
-        request = urllib.request.Request(new_url)
-        request.add_header("Authorization", auth)
-    else:
-        request = urllib.request.Request(url)
-
-    request.add_header('User-Agent', user_agent)
-    fp = opener(request)
-
-    if auth:
-        # Put authentication info back into request URL if same host,
-        # so that links found on the page will work
-        s2, h2, path2, param2, query2, frag2 = urllib.parse.urlparse(fp.url)
-        if s2 == scheme and h2 == address:
-            parts = s2, netloc, path2, param2, query2, frag2
-            fp.url = urllib.parse.urlunparse(parts)
-
-    return fp
-
-
-# copy of urllib.parse._splituser from Python 3.8
-# See https://github.com/python/cpython/issues/80072.
-def _splituser(host):
-    """splituser('user[:passwd]@host[:port]')
-    --> 'user[:passwd]', 'host[:port]'."""
-    user, delim, host = host.rpartition('@')
-    return (user if delim else None), host
-
-
-# adding a timeout to avoid freezing package_index
-open_with_auth = socket_timeout(_SOCKET_TIMEOUT)(open_with_auth)
-
-
-def fix_sf_url(url):
-    return url  # backward compatibility
-
-
-def local_open(url):
-    """Read a local path, with special support for directories"""
-    _scheme, _server, path, _param, _query, _frag = urllib.parse.urlparse(url)
-    filename = urllib.request.url2pathname(path)
-    if os.path.isfile(filename):
-        return urllib.request.urlopen(url)
-    elif path.endswith('/') and os.path.isdir(filename):
-        files = []
-        for f in os.listdir(filename):
-            filepath = os.path.join(filename, f)
-            if f == 'index.html':
-                body = _read_utf8_with_fallback(filepath)
-                break
-            elif os.path.isdir(filepath):
-                f += '/'
-            files.append(f'{f}')
-        else:
-            tmpl = "{url}{files}"
-            body = tmpl.format(url=url, files='\n'.join(files))
-        status, message = 200, "OK"
-    else:
-        status, message, body = 404, "Path not found", "Not found"
-
-    headers = {'content-type': 'text/html'}
-    body_stream = io.StringIO(body)
-    return urllib.error.HTTPError(url, status, message, headers, body_stream)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/sandbox.py b/llmlab/lib/python3.12/site-packages/setuptools/sandbox.py
deleted file mode 100644
index 2d84242..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/sandbox.py
+++ /dev/null
@@ -1,536 +0,0 @@
-from __future__ import annotations
-
-import builtins
-import contextlib
-import functools
-import itertools
-import operator
-import os
-import pickle
-import re
-import sys
-import tempfile
-import textwrap
-from types import TracebackType
-from typing import TYPE_CHECKING, Any, ClassVar
-
-import pkg_resources
-from pkg_resources import working_set
-
-from distutils.errors import DistutilsError
-
-if TYPE_CHECKING:
-    import os as _os
-elif sys.platform.startswith('java'):
-    import org.python.modules.posix.PosixModule as _os  # pyright: ignore[reportMissingImports]
-else:
-    _os = sys.modules[os.name]
-_open = open
-
-
-if TYPE_CHECKING:
-    from typing_extensions import Self
-
-__all__ = [
-    "AbstractSandbox",
-    "DirectorySandbox",
-    "SandboxViolation",
-    "run_setup",
-]
-
-
-def _execfile(filename, globals, locals=None):
-    """
-    Python 3 implementation of execfile.
-    """
-    mode = 'rb'
-    with open(filename, mode) as stream:
-        script = stream.read()
-    if locals is None:
-        locals = globals
-    code = compile(script, filename, 'exec')
-    exec(code, globals, locals)
-
-
-@contextlib.contextmanager
-def save_argv(repl=None):
-    saved = sys.argv[:]
-    if repl is not None:
-        sys.argv[:] = repl
-    try:
-        yield saved
-    finally:
-        sys.argv[:] = saved
-
-
-@contextlib.contextmanager
-def save_path():
-    saved = sys.path[:]
-    try:
-        yield saved
-    finally:
-        sys.path[:] = saved
-
-
-@contextlib.contextmanager
-def override_temp(replacement):
-    """
-    Monkey-patch tempfile.tempdir with replacement, ensuring it exists
-    """
-    os.makedirs(replacement, exist_ok=True)
-
-    saved = tempfile.tempdir
-
-    tempfile.tempdir = replacement
-
-    try:
-        yield
-    finally:
-        tempfile.tempdir = saved
-
-
-@contextlib.contextmanager
-def pushd(target):
-    saved = os.getcwd()
-    os.chdir(target)
-    try:
-        yield saved
-    finally:
-        os.chdir(saved)
-
-
-class UnpickleableException(Exception):
-    """
-    An exception representing another Exception that could not be pickled.
-    """
-
-    @staticmethod
-    def dump(type, exc):
-        """
-        Always return a dumped (pickled) type and exc. If exc can't be pickled,
-        wrap it in UnpickleableException first.
-        """
-        try:
-            return pickle.dumps(type), pickle.dumps(exc)
-        except Exception:
-            # get UnpickleableException inside the sandbox
-            from setuptools.sandbox import UnpickleableException as cls
-
-            return cls.dump(cls, cls(repr(exc)))
-
-
-class ExceptionSaver:
-    """
-    A Context Manager that will save an exception, serialize, and restore it
-    later.
-    """
-
-    def __enter__(self) -> Self:
-        return self
-
-    def __exit__(
-        self,
-        type: type[BaseException] | None,
-        exc: BaseException | None,
-        tb: TracebackType | None,
-    ) -> bool:
-        if not exc:
-            return False
-
-        # dump the exception
-        self._saved = UnpickleableException.dump(type, exc)
-        self._tb = tb
-
-        # suppress the exception
-        return True
-
-    def resume(self):
-        "restore and re-raise any exception"
-
-        if '_saved' not in vars(self):
-            return
-
-        _type, exc = map(pickle.loads, self._saved)
-        raise exc.with_traceback(self._tb)
-
-
-@contextlib.contextmanager
-def save_modules():
-    """
-    Context in which imported modules are saved.
-
-    Translates exceptions internal to the context into the equivalent exception
-    outside the context.
-    """
-    saved = sys.modules.copy()
-    with ExceptionSaver() as saved_exc:
-        yield saved
-
-    sys.modules.update(saved)
-    # remove any modules imported since
-    del_modules = (
-        mod_name
-        for mod_name in sys.modules
-        if mod_name not in saved
-        # exclude any encodings modules. See #285
-        and not mod_name.startswith('encodings.')
-    )
-    _clear_modules(del_modules)
-
-    saved_exc.resume()
-
-
-def _clear_modules(module_names):
-    for mod_name in list(module_names):
-        del sys.modules[mod_name]
-
-
-@contextlib.contextmanager
-def save_pkg_resources_state():
-    saved = pkg_resources.__getstate__()
-    try:
-        yield saved
-    finally:
-        pkg_resources.__setstate__(saved)
-
-
-@contextlib.contextmanager
-def setup_context(setup_dir):
-    temp_dir = os.path.join(setup_dir, 'temp')
-    with save_pkg_resources_state():
-        with save_modules():
-            with save_path():
-                hide_setuptools()
-                with save_argv():
-                    with override_temp(temp_dir):
-                        with pushd(setup_dir):
-                            # ensure setuptools commands are available
-                            __import__('setuptools')
-                            yield
-
-
-_MODULES_TO_HIDE = {
-    'setuptools',
-    'distutils',
-    'pkg_resources',
-    'Cython',
-    '_distutils_hack',
-}
-
-
-def _needs_hiding(mod_name):
-    """
-    >>> _needs_hiding('setuptools')
-    True
-    >>> _needs_hiding('pkg_resources')
-    True
-    >>> _needs_hiding('setuptools_plugin')
-    False
-    >>> _needs_hiding('setuptools.__init__')
-    True
-    >>> _needs_hiding('distutils')
-    True
-    >>> _needs_hiding('os')
-    False
-    >>> _needs_hiding('Cython')
-    True
-    """
-    base_module = mod_name.split('.', 1)[0]
-    return base_module in _MODULES_TO_HIDE
-
-
-def hide_setuptools():
-    """
-    Remove references to setuptools' modules from sys.modules to allow the
-    invocation to import the most appropriate setuptools. This technique is
-    necessary to avoid issues such as #315 where setuptools upgrading itself
-    would fail to find a function declared in the metadata.
-    """
-    _distutils_hack = sys.modules.get('_distutils_hack', None)
-    if _distutils_hack is not None:
-        _distutils_hack._remove_shim()
-
-    modules = filter(_needs_hiding, sys.modules)
-    _clear_modules(modules)
-
-
-def run_setup(setup_script, args):
-    """Run a distutils setup script, sandboxed in its directory"""
-    setup_dir = os.path.abspath(os.path.dirname(setup_script))
-    with setup_context(setup_dir):
-        try:
-            sys.argv[:] = [setup_script] + list(args)
-            sys.path.insert(0, setup_dir)
-            # reset to include setup dir, w/clean callback list
-            working_set.__init__()
-            working_set.callbacks.append(lambda dist: dist.activate())
-
-            with DirectorySandbox(setup_dir):
-                ns = dict(__file__=setup_script, __name__='__main__')
-                _execfile(setup_script, ns)
-        except SystemExit as v:
-            if v.args and v.args[0]:
-                raise
-            # Normal exit, just return
-
-
-class AbstractSandbox:
-    """Wrap 'os' module and 'open()' builtin for virtualizing setup scripts"""
-
-    _active = False
-
-    def __init__(self) -> None:
-        self._attrs = [
-            name
-            for name in dir(_os)
-            if not name.startswith('_') and hasattr(self, name)
-        ]
-
-    def _copy(self, source):
-        for name in self._attrs:
-            setattr(os, name, getattr(source, name))
-
-    def __enter__(self) -> None:
-        self._copy(self)
-        builtins.open = self._open
-        self._active = True
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_value: BaseException | None,
-        traceback: TracebackType | None,
-    ):
-        self._active = False
-        builtins.open = _open
-        self._copy(_os)
-
-    def run(self, func):
-        """Run 'func' under os sandboxing"""
-        with self:
-            return func()
-
-    def _mk_dual_path_wrapper(name: str):  # type: ignore[misc] # https://github.com/pypa/setuptools/pull/4099
-        original = getattr(_os, name)
-
-        def wrap(self, src, dst, *args, **kw):
-            if self._active:
-                src, dst = self._remap_pair(name, src, dst, *args, **kw)
-            return original(src, dst, *args, **kw)
-
-        return wrap
-
-    for __name in ["rename", "link", "symlink"]:
-        if hasattr(_os, __name):
-            locals()[__name] = _mk_dual_path_wrapper(__name)
-
-    def _mk_single_path_wrapper(name: str, original=None):  # type: ignore[misc] # https://github.com/pypa/setuptools/pull/4099
-        original = original or getattr(_os, name)
-
-        def wrap(self, path, *args, **kw):
-            if self._active:
-                path = self._remap_input(name, path, *args, **kw)
-            return original(path, *args, **kw)
-
-        return wrap
-
-    _open = _mk_single_path_wrapper('open', _open)
-    for __name in [
-        "stat",
-        "listdir",
-        "chdir",
-        "open",
-        "chmod",
-        "chown",
-        "mkdir",
-        "remove",
-        "unlink",
-        "rmdir",
-        "utime",
-        "lchown",
-        "chroot",
-        "lstat",
-        "startfile",
-        "mkfifo",
-        "mknod",
-        "pathconf",
-        "access",
-    ]:
-        if hasattr(_os, __name):
-            locals()[__name] = _mk_single_path_wrapper(__name)
-
-    def _mk_single_with_return(name: str):  # type: ignore[misc] # https://github.com/pypa/setuptools/pull/4099
-        original = getattr(_os, name)
-
-        def wrap(self, path, *args, **kw):
-            if self._active:
-                path = self._remap_input(name, path, *args, **kw)
-                return self._remap_output(name, original(path, *args, **kw))
-            return original(path, *args, **kw)
-
-        return wrap
-
-    for __name in ['readlink', 'tempnam']:
-        if hasattr(_os, __name):
-            locals()[__name] = _mk_single_with_return(__name)
-
-    def _mk_query(name: str):  # type: ignore[misc] # https://github.com/pypa/setuptools/pull/4099
-        original = getattr(_os, name)
-
-        def wrap(self, *args, **kw):
-            retval = original(*args, **kw)
-            if self._active:
-                return self._remap_output(name, retval)
-            return retval
-
-        return wrap
-
-    for __name in ['getcwd', 'tmpnam']:
-        if hasattr(_os, __name):
-            locals()[__name] = _mk_query(__name)
-
-    def _validate_path(self, path):
-        """Called to remap or validate any path, whether input or output"""
-        return path
-
-    def _remap_input(self, operation, path, *args, **kw):
-        """Called for path inputs"""
-        return self._validate_path(path)
-
-    def _remap_output(self, operation, path):
-        """Called for path outputs"""
-        return self._validate_path(path)
-
-    def _remap_pair(self, operation, src, dst, *args, **kw):
-        """Called for path pairs like rename, link, and symlink operations"""
-        return (
-            self._remap_input(operation + '-from', src, *args, **kw),
-            self._remap_input(operation + '-to', dst, *args, **kw),
-        )
-
-    if TYPE_CHECKING:
-        # This is a catch-all for all the dynamically created attributes.
-        # This isn't public API anyway
-        def __getattribute__(self, name: str) -> Any: ...
-
-
-if hasattr(os, 'devnull'):
-    _EXCEPTIONS = [os.devnull]
-else:
-    _EXCEPTIONS = []
-
-
-class DirectorySandbox(AbstractSandbox):
-    """Restrict operations to a single subdirectory - pseudo-chroot"""
-
-    write_ops: ClassVar[dict[str, None]] = dict.fromkeys([
-        "open",
-        "chmod",
-        "chown",
-        "mkdir",
-        "remove",
-        "unlink",
-        "rmdir",
-        "utime",
-        "lchown",
-        "chroot",
-        "mkfifo",
-        "mknod",
-        "tempnam",
-    ])
-
-    _exception_patterns: list[str | re.Pattern] = []
-    "exempt writing to paths that match the pattern"
-
-    def __init__(self, sandbox, exceptions=_EXCEPTIONS) -> None:
-        self._sandbox = os.path.normcase(os.path.realpath(sandbox))
-        self._prefix = os.path.join(self._sandbox, '')
-        self._exceptions = [
-            os.path.normcase(os.path.realpath(path)) for path in exceptions
-        ]
-        AbstractSandbox.__init__(self)
-
-    def _violation(self, operation, *args, **kw):
-        from setuptools.sandbox import SandboxViolation
-
-        raise SandboxViolation(operation, args, kw)
-
-    def _open(self, path, mode='r', *args, **kw):
-        if mode not in ('r', 'rt', 'rb', 'rU', 'U') and not self._ok(path):
-            self._violation("open", path, mode, *args, **kw)
-        return _open(path, mode, *args, **kw)
-
-    def tmpnam(self) -> None:
-        self._violation("tmpnam")
-
-    def _ok(self, path):
-        active = self._active
-        try:
-            self._active = False
-            realpath = os.path.normcase(os.path.realpath(path))
-            return (
-                self._exempted(realpath)
-                or realpath == self._sandbox
-                or realpath.startswith(self._prefix)
-            )
-        finally:
-            self._active = active
-
-    def _exempted(self, filepath):
-        start_matches = (
-            filepath.startswith(exception) for exception in self._exceptions
-        )
-        pattern_matches = (
-            re.match(pattern, filepath) for pattern in self._exception_patterns
-        )
-        candidates = itertools.chain(start_matches, pattern_matches)
-        return any(candidates)
-
-    def _remap_input(self, operation, path, *args, **kw):
-        """Called for path inputs"""
-        if operation in self.write_ops and not self._ok(path):
-            self._violation(operation, os.path.realpath(path), *args, **kw)
-        return path
-
-    def _remap_pair(self, operation, src, dst, *args, **kw):
-        """Called for path pairs like rename, link, and symlink operations"""
-        if not self._ok(src) or not self._ok(dst):
-            self._violation(operation, src, dst, *args, **kw)
-        return (src, dst)
-
-    def open(self, file, flags, mode: int = 0o777, *args, **kw) -> int:
-        """Called for low-level os.open()"""
-        if flags & WRITE_FLAGS and not self._ok(file):
-            self._violation("os.open", file, flags, mode, *args, **kw)
-        return _os.open(file, flags, mode, *args, **kw)
-
-
-WRITE_FLAGS = functools.reduce(
-    operator.or_,
-    [
-        getattr(_os, a, 0)
-        for a in "O_WRONLY O_RDWR O_APPEND O_CREAT O_TRUNC O_TEMPORARY".split()
-    ],
-)
-
-
-class SandboxViolation(DistutilsError):
-    """A setup script attempted to modify the filesystem outside the sandbox"""
-
-    tmpl = textwrap.dedent(
-        """
-        SandboxViolation: {cmd}{args!r} {kwargs}
-
-        The package setup script has attempted to modify files on your system
-        that are not within the EasyInstall build area, and has been aborted.
-
-        This package cannot be safely installed by EasyInstall, and may not
-        support alternate installation locations even if you run its setup
-        script by hand.  Please inform the package's author and the EasyInstall
-        maintainers to find out if a fix or workaround is available.
-        """
-    ).lstrip()
-
-    def __str__(self) -> str:
-        cmd, args, kwargs = self.args
-        return self.tmpl.format(**locals())
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/script (dev).tmpl b/llmlab/lib/python3.12/site-packages/setuptools/script (dev).tmpl
deleted file mode 100644
index 39a24b0..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/script (dev).tmpl	
+++ /dev/null
@@ -1,6 +0,0 @@
-# EASY-INSTALL-DEV-SCRIPT: %(spec)r,%(script_name)r
-__requires__ = %(spec)r
-__import__('pkg_resources').require(%(spec)r)
-__file__ = %(dev_path)r
-with open(__file__) as f:
-    exec(compile(f.read(), __file__, 'exec'))
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/script.tmpl b/llmlab/lib/python3.12/site-packages/setuptools/script.tmpl
deleted file mode 100644
index ff5efbc..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/script.tmpl
+++ /dev/null
@@ -1,3 +0,0 @@
-# EASY-INSTALL-SCRIPT: %(spec)r,%(script_name)r
-__requires__ = %(spec)r
-__import__('pkg_resources').run_script(%(spec)r, %(script_name)r)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/__init__.py
deleted file mode 100644
index eb70bfb..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/__init__.py
+++ /dev/null
@@ -1,13 +0,0 @@
-import locale
-import sys
-
-import pytest
-
-__all__ = ['fail_on_ascii']
-
-if sys.version_info >= (3, 11):
-    locale_encoding = locale.getencoding()
-else:
-    locale_encoding = locale.getpreferredencoding(False)
-is_ascii = locale_encoding == 'ANSI_X3.4-1968'
-fail_on_ascii = pytest.mark.xfail(is_ascii, reason="Test fails in this locale")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 28381d0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/contexts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/contexts.cpython-312.pyc
deleted file mode 100644
index 2c7a826..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/contexts.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/environment.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/environment.cpython-312.pyc
deleted file mode 100644
index b6abe89..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/environment.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/fixtures.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/fixtures.cpython-312.pyc
deleted file mode 100644
index 09e1eb6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/fixtures.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/mod_with_constant.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/mod_with_constant.cpython-312.pyc
deleted file mode 100644
index 3cee341..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/mod_with_constant.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/namespaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/namespaces.cpython-312.pyc
deleted file mode 100644
index f2f86eb..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/namespaces.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/script-with-bom.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/script-with-bom.cpython-312.pyc
deleted file mode 100644
index 72ff8a9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/script-with-bom.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/server.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/server.cpython-312.pyc
deleted file mode 100644
index c02722e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/server.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_archive_util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_archive_util.cpython-312.pyc
deleted file mode 100644
index 3d8dc06..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_archive_util.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_deprecations.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_deprecations.cpython-312.pyc
deleted file mode 100644
index cbbc50e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_deprecations.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_egg.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_egg.cpython-312.pyc
deleted file mode 100644
index 40d6763..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_egg.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_wheel.cpython-312.pyc
deleted file mode 100644
index 4c5a97c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_bdist_wheel.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build.cpython-312.pyc
deleted file mode 100644
index 219bac6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_clib.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_clib.cpython-312.pyc
deleted file mode 100644
index 7f9b2d3..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_clib.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_ext.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_ext.cpython-312.pyc
deleted file mode 100644
index 8e283ae..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_ext.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_meta.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_meta.cpython-312.pyc
deleted file mode 100644
index a4772d6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_meta.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_py.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_py.cpython-312.pyc
deleted file mode 100644
index c3aded5..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_build_py.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_config_discovery.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_config_discovery.cpython-312.pyc
deleted file mode 100644
index 1afeb25..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_config_discovery.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_core_metadata.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_core_metadata.cpython-312.pyc
deleted file mode 100644
index 1ad3cf5..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_core_metadata.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_depends.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_depends.cpython-312.pyc
deleted file mode 100644
index 9db767c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_depends.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_develop.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_develop.cpython-312.pyc
deleted file mode 100644
index d28eb88..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_develop.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_dist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_dist.cpython-312.pyc
deleted file mode 100644
index 4898ec6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_dist.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_dist_info.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_dist_info.cpython-312.pyc
deleted file mode 100644
index 070e38c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_dist_info.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_distutils_adoption.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_distutils_adoption.cpython-312.pyc
deleted file mode 100644
index 2572b2a..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_distutils_adoption.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_easy_install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_easy_install.cpython-312.pyc
deleted file mode 100644
index 5775901..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_easy_install.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_editable_install.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_editable_install.cpython-312.pyc
deleted file mode 100644
index ed7959f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_editable_install.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_egg_info.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_egg_info.cpython-312.pyc
deleted file mode 100644
index 68f3403..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_egg_info.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_extern.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_extern.cpython-312.pyc
deleted file mode 100644
index 6ea1dd3..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_extern.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_find_packages.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_find_packages.cpython-312.pyc
deleted file mode 100644
index 9b7d22e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_find_packages.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_find_py_modules.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_find_py_modules.cpython-312.pyc
deleted file mode 100644
index 6b1adb0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_find_py_modules.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_glob.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_glob.cpython-312.pyc
deleted file mode 100644
index 8d421d3..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_glob.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_install_scripts.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_install_scripts.cpython-312.pyc
deleted file mode 100644
index 0a13f34..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_install_scripts.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_logging.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_logging.cpython-312.pyc
deleted file mode 100644
index 527a360..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_logging.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_manifest.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_manifest.cpython-312.pyc
deleted file mode 100644
index 6e8a5e9..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_manifest.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_namespaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_namespaces.cpython-312.pyc
deleted file mode 100644
index 770c9a8..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_namespaces.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_packageindex.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_packageindex.cpython-312.pyc
deleted file mode 100644
index 63b68c2..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_packageindex.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_sandbox.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_sandbox.cpython-312.pyc
deleted file mode 100644
index 51d8558..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_sandbox.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_sdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_sdist.cpython-312.pyc
deleted file mode 100644
index 74651b6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_sdist.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_setopt.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_setopt.cpython-312.pyc
deleted file mode 100644
index 29b0c7c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_setopt.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_setuptools.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_setuptools.cpython-312.pyc
deleted file mode 100644
index 5d6b8f4..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_setuptools.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_shutil_wrapper.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_shutil_wrapper.cpython-312.pyc
deleted file mode 100644
index bf959fb..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_shutil_wrapper.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_unicode_utils.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_unicode_utils.cpython-312.pyc
deleted file mode 100644
index fd4b39f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_unicode_utils.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_virtualenv.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_virtualenv.cpython-312.pyc
deleted file mode 100644
index e3a0903..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_virtualenv.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_warnings.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_warnings.cpython-312.pyc
deleted file mode 100644
index 3ea4180..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_warnings.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_wheel.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_wheel.cpython-312.pyc
deleted file mode 100644
index f81663d..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_wheel.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_windows_wrappers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_windows_wrappers.cpython-312.pyc
deleted file mode 100644
index becc8d6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/test_windows_wrappers.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/text.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/text.cpython-312.pyc
deleted file mode 100644
index 5ff36ed..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/text.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/textwrap.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/textwrap.cpython-312.pyc
deleted file mode 100644
index 21f30f6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/__pycache__/textwrap.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 6977b4f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__pycache__/py39.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__pycache__/py39.cpython-312.pyc
deleted file mode 100644
index 1cbe6df..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/__pycache__/py39.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/py39.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/py39.py
deleted file mode 100644
index 1fdb9da..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/compat/py39.py
+++ /dev/null
@@ -1,3 +0,0 @@
-from jaraco.test.cpython import from_test_support, try_import
-
-os_helper = try_import('os_helper') or from_test_support('can_symlink')
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 72ad193..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_apply_pyprojecttoml.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_apply_pyprojecttoml.cpython-312.pyc
deleted file mode 100644
index 68b3409..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_apply_pyprojecttoml.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_expand.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_expand.cpython-312.pyc
deleted file mode 100644
index 1e40443..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_expand.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_pyprojecttoml.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_pyprojecttoml.cpython-312.pyc
deleted file mode 100644
index c1ae4da..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_pyprojecttoml.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_pyprojecttoml_dynamic_deps.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_pyprojecttoml_dynamic_deps.cpython-312.pyc
deleted file mode 100644
index bdc372c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_pyprojecttoml_dynamic_deps.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_setupcfg.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_setupcfg.cpython-312.pyc
deleted file mode 100644
index 812eef8..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/__pycache__/test_setupcfg.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__init__.py
deleted file mode 100644
index 00a1642..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__init__.py
+++ /dev/null
@@ -1,59 +0,0 @@
-from __future__ import annotations
-
-import re
-import time
-from pathlib import Path
-from urllib.error import HTTPError
-from urllib.request import urlopen
-
-__all__ = ["DOWNLOAD_DIR", "retrieve_file", "output_file", "urls_from_file"]
-
-
-NAME_REMOVE = ("http://", "https://", "github.com/", "/raw/")
-DOWNLOAD_DIR = Path(__file__).parent
-
-
-# ----------------------------------------------------------------------
-# Please update ./preload.py accordingly when modifying this file
-# ----------------------------------------------------------------------
-
-
-def output_file(url: str, download_dir: Path = DOWNLOAD_DIR) -> Path:
-    file_name = url.strip()
-    for part in NAME_REMOVE:
-        file_name = file_name.replace(part, '').strip().strip('/:').strip()
-    return Path(download_dir, re.sub(r"[^\-_\.\w\d]+", "_", file_name))
-
-
-def retrieve_file(url: str, download_dir: Path = DOWNLOAD_DIR, wait: float = 5) -> Path:
-    path = output_file(url, download_dir)
-    if path.exists():
-        print(f"Skipping {url} (already exists: {path})")
-    else:
-        download_dir.mkdir(exist_ok=True, parents=True)
-        print(f"Downloading {url} to {path}")
-        try:
-            download(url, path)
-        except HTTPError:
-            time.sleep(wait)  # wait a few seconds and try again.
-            download(url, path)
-    return path
-
-
-def urls_from_file(list_file: Path) -> list[str]:
-    """``list_file`` should be a text file where each line corresponds to a URL to
-    download.
-    """
-    print(f"file: {list_file}")
-    content = list_file.read_text(encoding="utf-8")
-    return [url for url in content.splitlines() if not url.startswith("#")]
-
-
-def download(url: str, dest: Path):
-    with urlopen(url) as f:
-        data = f.read()
-
-    with open(dest, "wb") as f:
-        f.write(data)
-
-    assert Path(dest).exists()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 34d53bc..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__pycache__/preload.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__pycache__/preload.cpython-312.pyc
deleted file mode 100644
index b1e05ac..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/__pycache__/preload.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/preload.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/preload.py
deleted file mode 100644
index 8eeb5dd..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/downloads/preload.py
+++ /dev/null
@@ -1,18 +0,0 @@
-"""This file can be used to preload files needed for testing.
-
-For example you can use::
-
-    cd setuptools/tests/config
-    python -m downloads.preload setupcfg_examples.txt
-
-to make sure the `setup.cfg` examples are downloaded before starting the tests.
-"""
-
-import sys
-from pathlib import Path
-
-from . import retrieve_file, urls_from_file
-
-if __name__ == "__main__":
-    urls = urls_from_file(Path(sys.argv[1]))
-    list(map(retrieve_file, urls))
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/setupcfg_examples.txt b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/setupcfg_examples.txt
deleted file mode 100644
index 6aab887..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/setupcfg_examples.txt
+++ /dev/null
@@ -1,22 +0,0 @@
-# ====================================================================
-# Some popular packages that use setup.cfg (and others not so popular)
-# Reference: https://hugovk.github.io/top-pypi-packages/
-# ====================================================================
-https://github.com/pypa/setuptools/raw/52c990172fec37766b3566679724aa8bf70ae06d/setup.cfg
-https://github.com/pypa/wheel/raw/0acd203cd896afec7f715aa2ff5980a403459a3b/setup.cfg
-https://github.com/python/importlib_metadata/raw/2f05392ca980952a6960d82b2f2d2ea10aa53239/setup.cfg
-https://github.com/jaraco/skeleton/raw/d9008b5c510cd6969127a6a2ab6f832edddef296/setup.cfg
-https://github.com/jaraco/zipp/raw/700d3a96390e970b6b962823bfea78b4f7e1c537/setup.cfg
-https://github.com/pallets/jinja/raw/7d72eb7fefb7dce065193967f31f805180508448/setup.cfg
-https://github.com/tkem/cachetools/raw/2fd87a94b8d3861d80e9e4236cd480bfdd21c90d/setup.cfg
-https://github.com/aio-libs/aiohttp/raw/5e0e6b7080f2408d5f1dd544c0e1cf88378b7b10/setup.cfg
-https://github.com/pallets/flask/raw/9486b6cf57bd6a8a261f67091aca8ca78eeec1e3/setup.cfg
-https://github.com/pallets/click/raw/6411f425fae545f42795665af4162006b36c5e4a/setup.cfg
-https://github.com/sqlalchemy/sqlalchemy/raw/533f5718904b620be8d63f2474229945d6f8ba5d/setup.cfg
-https://github.com/pytest-dev/pluggy/raw/461ef63291d13589c4e21aa182cd1529257e9a0a/setup.cfg
-https://github.com/pytest-dev/pytest/raw/c7be96dae487edbd2f55b561b31b68afac1dabe6/setup.cfg
-https://github.com/platformdirs/platformdirs/raw/7b7852128dd6f07511b618d6edea35046bd0c6ff/setup.cfg
-https://github.com/pandas-dev/pandas/raw/bc17343f934a33dc231c8c74be95d8365537c376/setup.cfg
-https://github.com/django/django/raw/4e249d11a6e56ca8feb4b055b681cec457ef3a3d/setup.cfg
-https://github.com/pyscaffold/pyscaffold/raw/de7aa5dc059fbd04307419c667cc4961bc9df4b8/setup.cfg
-https://github.com/pypa/virtualenv/raw/f92eda6e3da26a4d28c2663ffb85c4960bdb990c/setup.cfg
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_apply_pyprojecttoml.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_apply_pyprojecttoml.py
deleted file mode 100644
index 489fd98..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_apply_pyprojecttoml.py
+++ /dev/null
@@ -1,772 +0,0 @@
-"""Make sure that applying the configuration from pyproject.toml is equivalent to
-applying a similar configuration from setup.cfg
-
-To run these tests offline, please have a look on ``./downloads/preload.py``
-"""
-
-from __future__ import annotations
-
-import io
-import re
-import tarfile
-from inspect import cleandoc
-from pathlib import Path
-from unittest.mock import Mock
-
-import pytest
-from ini2toml.api import LiteTranslator
-from packaging.metadata import Metadata
-
-import setuptools  # noqa: F401 # ensure monkey patch to metadata
-from setuptools._static import is_static
-from setuptools.command.egg_info import write_requirements
-from setuptools.config import expand, pyprojecttoml, setupcfg
-from setuptools.config._apply_pyprojecttoml import _MissingDynamic, _some_attrgetter
-from setuptools.dist import Distribution
-from setuptools.errors import InvalidConfigError, RemovedConfigError
-from setuptools.warnings import InformationOnly, SetuptoolsDeprecationWarning
-
-from .downloads import retrieve_file, urls_from_file
-
-HERE = Path(__file__).parent
-EXAMPLES_FILE = "setupcfg_examples.txt"
-
-
-def makedist(path, **attrs):
-    return Distribution({"src_root": path, **attrs})
-
-
-def _mock_expand_patterns(patterns, *_, **__):
-    """
-    Allow comparing the given patterns for 2 dist objects.
-    We need to strip special chars to avoid errors when validating.
-    """
-    return [re.sub("[^a-z0-9]+", "", p, flags=re.I) or "empty" for p in patterns]
-
-
-@pytest.mark.parametrize("url", urls_from_file(HERE / EXAMPLES_FILE))
-@pytest.mark.filterwarnings("ignore")
-@pytest.mark.uses_network
-def test_apply_pyproject_equivalent_to_setupcfg(url, monkeypatch, tmp_path):
-    monkeypatch.setattr(expand, "read_attr", Mock(return_value="0.0.1"))
-    monkeypatch.setattr(
-        Distribution, "_expand_patterns", Mock(side_effect=_mock_expand_patterns)
-    )
-    setupcfg_example = retrieve_file(url)
-    pyproject_example = Path(tmp_path, "pyproject.toml")
-    setupcfg_text = setupcfg_example.read_text(encoding="utf-8")
-    toml_config = LiteTranslator().translate(setupcfg_text, "setup.cfg")
-    pyproject_example.write_text(toml_config, encoding="utf-8")
-
-    dist_toml = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject_example)
-    dist_cfg = setupcfg.apply_configuration(makedist(tmp_path), setupcfg_example)
-
-    pkg_info_toml = core_metadata(dist_toml)
-    pkg_info_cfg = core_metadata(dist_cfg)
-    assert pkg_info_toml == pkg_info_cfg
-
-    if any(getattr(d, "license_files", None) for d in (dist_toml, dist_cfg)):
-        assert set(dist_toml.license_files) == set(dist_cfg.license_files)
-
-    if any(getattr(d, "entry_points", None) for d in (dist_toml, dist_cfg)):
-        print(dist_cfg.entry_points)
-        ep_toml = {
-            (k, *sorted(i.replace(" ", "") for i in v))
-            for k, v in dist_toml.entry_points.items()
-        }
-        ep_cfg = {
-            (k, *sorted(i.replace(" ", "") for i in v))
-            for k, v in dist_cfg.entry_points.items()
-        }
-        assert ep_toml == ep_cfg
-
-    if any(getattr(d, "package_data", None) for d in (dist_toml, dist_cfg)):
-        pkg_data_toml = {(k, *sorted(v)) for k, v in dist_toml.package_data.items()}
-        pkg_data_cfg = {(k, *sorted(v)) for k, v in dist_cfg.package_data.items()}
-        assert pkg_data_toml == pkg_data_cfg
-
-    if any(getattr(d, "data_files", None) for d in (dist_toml, dist_cfg)):
-        data_files_toml = {(k, *sorted(v)) for k, v in dist_toml.data_files}
-        data_files_cfg = {(k, *sorted(v)) for k, v in dist_cfg.data_files}
-        assert data_files_toml == data_files_cfg
-
-    assert set(dist_toml.install_requires) == set(dist_cfg.install_requires)
-    if any(getattr(d, "extras_require", None) for d in (dist_toml, dist_cfg)):
-        extra_req_toml = {(k, *sorted(v)) for k, v in dist_toml.extras_require.items()}
-        extra_req_cfg = {(k, *sorted(v)) for k, v in dist_cfg.extras_require.items()}
-        assert extra_req_toml == extra_req_cfg
-
-
-PEP621_EXAMPLE = """\
-[project]
-name = "spam"
-version = "2020.0.0"
-description = "Lovely Spam! Wonderful Spam!"
-readme = "README.rst"
-requires-python = ">=3.8"
-license-files = ["LICENSE.txt"]  # Updated to be PEP 639 compliant
-keywords = ["egg", "bacon", "sausage", "tomatoes", "Lobster Thermidor"]
-authors = [
-  {email = "hi@pradyunsg.me"},
-  {name = "Tzu-Ping Chung"}
-]
-maintainers = [
-  {name = "Brett Cannon", email = "brett@python.org"},
-  {name = "John X. Ãørçeč", email = "john@utf8.org"},
-  {name = "Γαμα קּ 東", email = "gama@utf8.org"},
-]
-classifiers = [
-  "Development Status :: 4 - Beta",
-  "Programming Language :: Python"
-]
-
-dependencies = [
-  "httpx",
-  "gidgethub[httpx]>4.0.0",
-  "django>2.1; os_name != 'nt'",
-  "django>2.0; os_name == 'nt'"
-]
-
-[project.optional-dependencies]
-test = [
-  "pytest < 5.0.0",
-  "pytest-cov[all]"
-]
-
-[project.urls]
-homepage = "http://example.com"
-documentation = "http://readthedocs.org"
-repository = "http://github.com"
-changelog = "http://github.com/me/spam/blob/master/CHANGELOG.md"
-
-[project.scripts]
-spam-cli = "spam:main_cli"
-
-[project.gui-scripts]
-spam-gui = "spam:main_gui"
-
-[project.entry-points."spam.magical"]
-tomatoes = "spam:main_tomatoes"
-"""
-
-PEP621_INTERNATIONAL_EMAIL_EXAMPLE = """\
-[project]
-name = "spam"
-version = "2020.0.0"
-authors = [
-  {email = "hi@pradyunsg.me"},
-  {name = "Tzu-Ping Chung"}
-]
-maintainers = [
-  {name = "Степан Бандера", email = "криївка@оун-упа.укр"},
-]
-"""
-
-PEP621_EXAMPLE_SCRIPT = """
-def main_cli(): pass
-def main_gui(): pass
-def main_tomatoes(): pass
-"""
-
-PEP639_LICENSE_TEXT = """\
-[project]
-name = "spam"
-version = "2020.0.0"
-authors = [
-  {email = "hi@pradyunsg.me"},
-  {name = "Tzu-Ping Chung"}
-]
-license = {text = "MIT"}
-"""
-
-PEP639_LICENSE_EXPRESSION = """\
-[project]
-name = "spam"
-version = "2020.0.0"
-authors = [
-  {email = "hi@pradyunsg.me"},
-  {name = "Tzu-Ping Chung"}
-]
-license = "mit or apache-2.0"  # should be normalized in metadata
-classifiers = [
-    "Development Status :: 5 - Production/Stable",
-    "Programming Language :: Python",
-]
-"""
-
-
-def _pep621_example_project(
-    tmp_path,
-    readme="README.rst",
-    pyproject_text=PEP621_EXAMPLE,
-):
-    pyproject = tmp_path / "pyproject.toml"
-    text = pyproject_text
-    replacements = {'readme = "README.rst"': f'readme = "{readme}"'}
-    for orig, subst in replacements.items():
-        text = text.replace(orig, subst)
-    pyproject.write_text(text, encoding="utf-8")
-
-    (tmp_path / readme).write_text("hello world", encoding="utf-8")
-    (tmp_path / "LICENSE.txt").write_text("--- LICENSE stub ---", encoding="utf-8")
-    (tmp_path / "spam.py").write_text(PEP621_EXAMPLE_SCRIPT, encoding="utf-8")
-    return pyproject
-
-
-def test_pep621_example(tmp_path):
-    """Make sure the example in PEP 621 works"""
-    pyproject = _pep621_example_project(tmp_path)
-    dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-    assert set(dist.metadata.license_files) == {"LICENSE.txt"}
-
-
-@pytest.mark.parametrize(
-    ("readme", "ctype"),
-    [
-        ("Readme.txt", "text/plain"),
-        ("readme.md", "text/markdown"),
-        ("text.rst", "text/x-rst"),
-    ],
-)
-def test_readme_content_type(tmp_path, readme, ctype):
-    pyproject = _pep621_example_project(tmp_path, readme)
-    dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-    assert dist.metadata.long_description_content_type == ctype
-
-
-def test_undefined_content_type(tmp_path):
-    pyproject = _pep621_example_project(tmp_path, "README.tex")
-    with pytest.raises(ValueError, match="Undefined content type for README.tex"):
-        pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-
-def test_no_explicit_content_type_for_missing_extension(tmp_path):
-    pyproject = _pep621_example_project(tmp_path, "README")
-    dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-    assert dist.metadata.long_description_content_type is None
-
-
-@pytest.mark.parametrize(
-    ("pyproject_text", "expected_maintainers_meta_value"),
-    (
-        pytest.param(
-            PEP621_EXAMPLE,
-            (
-                'Brett Cannon , "John X. Ãørçeč" , '
-                'Γαμα קּ 東 '
-            ),
-            id='non-international-emails',
-        ),
-        pytest.param(
-            PEP621_INTERNATIONAL_EMAIL_EXAMPLE,
-            'Степан Бандера <криївка@оун-упа.укр>',
-            marks=pytest.mark.xfail(
-                reason="CPython's `email.headerregistry.Address` only supports "
-                'RFC 5322, as of Nov 10, 2022 and latest Python 3.11.0',
-                strict=True,
-            ),
-            id='international-email',
-        ),
-    ),
-)
-def test_utf8_maintainer_in_metadata(  # issue-3663
-    expected_maintainers_meta_value,
-    pyproject_text,
-    tmp_path,
-):
-    pyproject = _pep621_example_project(
-        tmp_path,
-        "README",
-        pyproject_text=pyproject_text,
-    )
-    dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-    assert dist.metadata.maintainer_email == expected_maintainers_meta_value
-    pkg_file = tmp_path / "PKG-FILE"
-    with open(pkg_file, "w", encoding="utf-8") as fh:
-        dist.metadata.write_pkg_file(fh)
-    content = pkg_file.read_text(encoding="utf-8")
-    assert f"Maintainer-email: {expected_maintainers_meta_value}" in content
-
-
-@pytest.mark.parametrize(
-    (
-        'pyproject_text',
-        'license',
-        'license_expression',
-        'content_str',
-        'not_content_str',
-    ),
-    (
-        pytest.param(
-            PEP639_LICENSE_TEXT,
-            'MIT',
-            None,
-            'License: MIT',
-            'License-Expression: ',
-            id='license-text',
-            marks=[
-                pytest.mark.filterwarnings(
-                    "ignore:.project.license. as a TOML table is deprecated",
-                )
-            ],
-        ),
-        pytest.param(
-            PEP639_LICENSE_EXPRESSION,
-            None,
-            'MIT OR Apache-2.0',
-            'License-Expression: MIT OR Apache-2.0',
-            'License: ',
-            id='license-expression',
-        ),
-    ),
-)
-def test_license_in_metadata(
-    license,
-    license_expression,
-    content_str,
-    not_content_str,
-    pyproject_text,
-    tmp_path,
-):
-    pyproject = _pep621_example_project(
-        tmp_path,
-        "README",
-        pyproject_text=pyproject_text,
-    )
-    dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-    assert dist.metadata.license == license
-    assert dist.metadata.license_expression == license_expression
-    pkg_file = tmp_path / "PKG-FILE"
-    with open(pkg_file, "w", encoding="utf-8") as fh:
-        dist.metadata.write_pkg_file(fh)
-    content = pkg_file.read_text(encoding="utf-8")
-    assert "Metadata-Version: 2.4" in content
-    assert content_str in content
-    assert not_content_str not in content
-
-
-def test_license_classifier_with_license_expression(tmp_path):
-    text = PEP639_LICENSE_EXPRESSION.rsplit("\n", 2)[0]
-    pyproject = _pep621_example_project(
-        tmp_path,
-        "README",
-        f"{text}\n    \"License :: OSI Approved :: MIT License\"\n]",
-    )
-    msg = "License classifiers have been superseded by license expressions"
-    with pytest.raises(InvalidConfigError, match=msg) as exc:
-        pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-    assert "License :: OSI Approved :: MIT License" in str(exc.value)
-
-
-def test_license_classifier_without_license_expression(tmp_path):
-    text = """\
-    [project]
-    name = "spam"
-    version = "2020.0.0"
-    license = {text = "mit or apache-2.0"}
-    classifiers = ["License :: OSI Approved :: MIT License"]
-    """
-    pyproject = _pep621_example_project(tmp_path, "README", text)
-
-    msg1 = "License classifiers are deprecated(?:.|\n)*MIT License"
-    msg2 = ".project.license. as a TOML table is deprecated"
-    with (
-        pytest.warns(SetuptoolsDeprecationWarning, match=msg1),
-        pytest.warns(SetuptoolsDeprecationWarning, match=msg2),
-    ):
-        dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-    # Check license classifier is still included
-    assert dist.metadata.get_classifiers() == ["License :: OSI Approved :: MIT License"]
-
-
-class TestLicenseFiles:
-    def base_pyproject(
-        self,
-        tmp_path,
-        additional_text="",
-        license_toml='license = {file = "LICENSE.txt"}\n',
-    ):
-        text = PEP639_LICENSE_EXPRESSION
-
-        # Sanity-check
-        assert 'license = "mit or apache-2.0"' in text
-        assert 'license-files' not in text
-        assert "[tool.setuptools]" not in text
-
-        text = re.sub(
-            r"(license = .*)\n",
-            license_toml,
-            text,
-            count=1,
-        )
-        assert license_toml in text  # sanity check
-        text = f"{text}\n{additional_text}\n"
-        pyproject = _pep621_example_project(tmp_path, "README", pyproject_text=text)
-        return pyproject
-
-    def base_pyproject_license_pep639(self, tmp_path, additional_text=""):
-        return self.base_pyproject(
-            tmp_path,
-            additional_text=additional_text,
-            license_toml='license = "licenseref-Proprietary"'
-            '\nlicense-files = ["_FILE*"]\n',
-        )
-
-    def test_both_license_and_license_files_defined(self, tmp_path):
-        setuptools_config = '[tool.setuptools]\nlicense-files = ["_FILE*"]'
-        pyproject = self.base_pyproject(tmp_path, setuptools_config)
-
-        (tmp_path / "_FILE.txt").touch()
-        (tmp_path / "_FILE.rst").touch()
-
-        # Would normally match the `license_files` patterns, but we want to exclude it
-        # by being explicit. On the other hand, contents should be added to `license`
-        license = tmp_path / "LICENSE.txt"
-        license.write_text("LicenseRef-Proprietary\n", encoding="utf-8")
-
-        msg1 = "'tool.setuptools.license-files' is deprecated in favor of 'project.license-files'"
-        msg2 = ".project.license. as a TOML table is deprecated"
-        with (
-            pytest.warns(SetuptoolsDeprecationWarning, match=msg1),
-            pytest.warns(SetuptoolsDeprecationWarning, match=msg2),
-        ):
-            dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-        assert set(dist.metadata.license_files) == {"_FILE.rst", "_FILE.txt"}
-        assert dist.metadata.license == "LicenseRef-Proprietary\n"
-
-    def test_both_license_and_license_files_defined_pep639(self, tmp_path):
-        # Set license and license-files
-        pyproject = self.base_pyproject_license_pep639(tmp_path)
-
-        (tmp_path / "_FILE.txt").touch()
-        (tmp_path / "_FILE.rst").touch()
-
-        msg = "Normalizing.*LicenseRef"
-        with pytest.warns(InformationOnly, match=msg):
-            dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-        assert set(dist.metadata.license_files) == {"_FILE.rst", "_FILE.txt"}
-        assert dist.metadata.license is None
-        assert dist.metadata.license_expression == "LicenseRef-Proprietary"
-
-    def test_license_files_defined_twice(self, tmp_path):
-        # Set project.license-files and tools.setuptools.license-files
-        setuptools_config = '[tool.setuptools]\nlicense-files = ["_FILE*"]'
-        pyproject = self.base_pyproject_license_pep639(tmp_path, setuptools_config)
-
-        msg = "'project.license-files' is defined already. Remove 'tool.setuptools.license-files'"
-        with pytest.raises(InvalidConfigError, match=msg):
-            pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-    def test_default_patterns(self, tmp_path):
-        setuptools_config = '[tool.setuptools]\nzip-safe = false'
-        # ^ used just to trigger section validation
-        pyproject = self.base_pyproject(tmp_path, setuptools_config, license_toml="")
-
-        license_files = "LICENCE-a.html COPYING-abc.txt AUTHORS-xyz NOTICE,def".split()
-
-        for fname in license_files:
-            (tmp_path / fname).write_text(f"{fname}\n", encoding="utf-8")
-
-        dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-        assert (tmp_path / "LICENSE.txt").exists()  # from base example
-        assert set(dist.metadata.license_files) == {*license_files, "LICENSE.txt"}
-
-    def test_missing_patterns(self, tmp_path):
-        pyproject = self.base_pyproject_license_pep639(tmp_path)
-        assert list(tmp_path.glob("_FILE*")) == []  # sanity check
-
-        msg1 = "Cannot find any files for the given pattern.*"
-        msg2 = "Normalizing 'licenseref-Proprietary' to 'LicenseRef-Proprietary'"
-        with (
-            pytest.warns(SetuptoolsDeprecationWarning, match=msg1),
-            pytest.warns(InformationOnly, match=msg2),
-        ):
-            pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-    def test_deprecated_file_expands_to_text(self, tmp_path):
-        """Make sure the old example with ``license = {text = ...}`` works"""
-
-        assert 'license-files = ["LICENSE.txt"]' in PEP621_EXAMPLE  # sanity check
-        text = PEP621_EXAMPLE.replace(
-            'license-files = ["LICENSE.txt"]',
-            'license = {file = "LICENSE.txt"}',
-        )
-        pyproject = _pep621_example_project(tmp_path, pyproject_text=text)
-
-        msg = ".project.license. as a TOML table is deprecated"
-        with pytest.warns(SetuptoolsDeprecationWarning, match=msg):
-            dist = pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-        assert dist.metadata.license == "--- LICENSE stub ---"
-        assert set(dist.metadata.license_files) == {"LICENSE.txt"}  # auto-filled
-
-
-class TestPyModules:
-    # https://github.com/pypa/setuptools/issues/4316
-
-    def dist(self, name):
-        toml_config = f"""
-        [project]
-        name = "test"
-        version = "42.0"
-        [tool.setuptools]
-        py-modules = [{name!r}]
-        """
-        pyproject = Path("pyproject.toml")
-        pyproject.write_text(cleandoc(toml_config), encoding="utf-8")
-        return pyprojecttoml.apply_configuration(Distribution({}), pyproject)
-
-    @pytest.mark.parametrize("module", ["pip-run", "abc-d.λ-xyz-e"])
-    def test_valid_module_name(self, tmp_path, monkeypatch, module):
-        monkeypatch.chdir(tmp_path)
-        assert module in self.dist(module).py_modules
-
-    @pytest.mark.parametrize("module", ["pip run", "-pip-run", "pip-run-stubs"])
-    def test_invalid_module_name(self, tmp_path, monkeypatch, module):
-        monkeypatch.chdir(tmp_path)
-        with pytest.raises(ValueError, match="py-modules"):
-            self.dist(module).py_modules
-
-
-class TestExtModules:
-    def test_pyproject_sets_attribute(self, tmp_path, monkeypatch):
-        monkeypatch.chdir(tmp_path)
-        pyproject = Path("pyproject.toml")
-        toml_config = """
-        [project]
-        name = "test"
-        version = "42.0"
-        [tool.setuptools]
-        ext-modules = [
-          {name = "my.ext", sources = ["hello.c", "world.c"]}
-        ]
-        """
-        pyproject.write_text(cleandoc(toml_config), encoding="utf-8")
-        with pytest.warns(pyprojecttoml._ExperimentalConfiguration):
-            dist = pyprojecttoml.apply_configuration(Distribution({}), pyproject)
-        assert len(dist.ext_modules) == 1
-        assert dist.ext_modules[0].name == "my.ext"
-        assert set(dist.ext_modules[0].sources) == {"hello.c", "world.c"}
-
-
-class TestDeprecatedFields:
-    def test_namespace_packages(self, tmp_path):
-        pyproject = tmp_path / "pyproject.toml"
-        config = """
-        [project]
-        name = "myproj"
-        version = "42"
-        [tool.setuptools]
-        namespace-packages = ["myproj.pkg"]
-        """
-        pyproject.write_text(cleandoc(config), encoding="utf-8")
-        with pytest.raises(RemovedConfigError, match="namespace-packages"):
-            pyprojecttoml.apply_configuration(makedist(tmp_path), pyproject)
-
-
-class TestPresetField:
-    def pyproject(self, tmp_path, dynamic, extra_content=""):
-        content = f"[project]\nname = 'proj'\ndynamic = {dynamic!r}\n"
-        if "version" not in dynamic:
-            content += "version = '42'\n"
-        file = tmp_path / "pyproject.toml"
-        file.write_text(content + extra_content, encoding="utf-8")
-        return file
-
-    @pytest.mark.parametrize(
-        ("attr", "field", "value"),
-        [
-            ("license_expression", "license", "MIT"),
-            pytest.param(
-                *("license", "license", "Not SPDX"),
-                marks=[pytest.mark.filterwarnings("ignore:.*license. overwritten")],
-            ),
-            ("classifiers", "classifiers", ["Private :: Classifier"]),
-            ("entry_points", "scripts", {"console_scripts": ["foobar=foobar:main"]}),
-            ("entry_points", "gui-scripts", {"gui_scripts": ["bazquux=bazquux:main"]}),
-            pytest.param(
-                *("install_requires", "dependencies", ["six"]),
-                marks=[
-                    pytest.mark.filterwarnings("ignore:.*install_requires. overwritten")
-                ],
-            ),
-        ],
-    )
-    def test_not_listed_in_dynamic(self, tmp_path, attr, field, value):
-        """Setuptools cannot set a field if not listed in ``dynamic``"""
-        pyproject = self.pyproject(tmp_path, [])
-        dist = makedist(tmp_path, **{attr: value})
-        msg = re.compile(f"defined outside of `pyproject.toml`:.*{field}", re.S)
-        with pytest.warns(_MissingDynamic, match=msg):
-            dist = pyprojecttoml.apply_configuration(dist, pyproject)
-
-        dist_value = _some_attrgetter(f"metadata.{attr}", attr)(dist)
-        assert not dist_value
-
-    @pytest.mark.parametrize(
-        ("attr", "field", "value"),
-        [
-            ("license_expression", "license", "MIT"),
-            ("install_requires", "dependencies", []),
-            ("extras_require", "optional-dependencies", {}),
-            ("install_requires", "dependencies", ["six"]),
-            ("classifiers", "classifiers", ["Private :: Classifier"]),
-        ],
-    )
-    def test_listed_in_dynamic(self, tmp_path, attr, field, value):
-        pyproject = self.pyproject(tmp_path, [field])
-        dist = makedist(tmp_path, **{attr: value})
-        dist = pyprojecttoml.apply_configuration(dist, pyproject)
-        dist_value = _some_attrgetter(f"metadata.{attr}", attr)(dist)
-        assert dist_value == value
-
-    def test_license_files_exempt_from_dynamic(self, monkeypatch, tmp_path):
-        """
-        license-file is currently not considered in the context of dynamic.
-        As per 2025-02-19, https://packaging.python.org/en/latest/specifications/pyproject-toml/#license-files
-        allows setuptools to fill-in `license-files` the way it sees fit:
-
-        > If the license-files key is not defined, tools can decide how to handle license files.
-        > For example they can choose not to include any files or use their own
-        > logic to discover the appropriate files in the distribution.
-
-        Using license_files from setup.py to fill-in the value is in accordance
-        with this rule.
-        """
-        monkeypatch.chdir(tmp_path)
-        pyproject = self.pyproject(tmp_path, [])
-        dist = makedist(tmp_path, license_files=["LIC*"])
-        (tmp_path / "LIC1").write_text("42", encoding="utf-8")
-        dist = pyprojecttoml.apply_configuration(dist, pyproject)
-        assert dist.metadata.license_files == ["LIC1"]
-
-    def test_warning_overwritten_dependencies(self, tmp_path):
-        src = "[project]\nname='pkg'\nversion='0.1'\ndependencies=['click']\n"
-        pyproject = tmp_path / "pyproject.toml"
-        pyproject.write_text(src, encoding="utf-8")
-        dist = makedist(tmp_path, install_requires=["wheel"])
-        with pytest.warns(match="`install_requires` overwritten"):
-            dist = pyprojecttoml.apply_configuration(dist, pyproject)
-        assert "wheel" not in dist.install_requires
-
-    def test_optional_dependencies_dont_remove_env_markers(self, tmp_path):
-        """
-        Internally setuptools converts dependencies with markers to "extras".
-        If ``install_requires`` is given by ``setup.py``, we have to ensure that
-        applying ``optional-dependencies`` does not overwrite the mandatory
-        dependencies with markers (see #3204).
-        """
-        # If setuptools replace its internal mechanism that uses `requires.txt`
-        # this test has to be rewritten to adapt accordingly
-        extra = "\n[project.optional-dependencies]\nfoo = ['bar>1']\n"
-        pyproject = self.pyproject(tmp_path, ["dependencies"], extra)
-        install_req = ['importlib-resources (>=3.0.0) ; python_version < "3.7"']
-        dist = makedist(tmp_path, install_requires=install_req)
-        dist = pyprojecttoml.apply_configuration(dist, pyproject)
-        assert "foo" in dist.extras_require
-        egg_info = dist.get_command_obj("egg_info")
-        write_requirements(egg_info, tmp_path, tmp_path / "requires.txt")
-        reqs = (tmp_path / "requires.txt").read_text(encoding="utf-8")
-        assert "importlib-resources" in reqs
-        assert "bar" in reqs
-        assert ':python_version < "3.7"' in reqs
-
-    @pytest.mark.parametrize(
-        ("field", "group"),
-        [("scripts", "console_scripts"), ("gui-scripts", "gui_scripts")],
-    )
-    @pytest.mark.filterwarnings("error")
-    def test_scripts_dont_require_dynamic_entry_points(self, tmp_path, field, group):
-        # Issue 3862
-        pyproject = self.pyproject(tmp_path, [field])
-        dist = makedist(tmp_path, entry_points={group: ["foobar=foobar:main"]})
-        dist = pyprojecttoml.apply_configuration(dist, pyproject)
-        assert group in dist.entry_points
-
-
-class TestMeta:
-    def test_example_file_in_sdist(self, setuptools_sdist):
-        """Meta test to ensure tests can run from sdist"""
-        with tarfile.open(setuptools_sdist) as tar:
-            assert any(name.endswith(EXAMPLES_FILE) for name in tar.getnames())
-
-
-class TestInteropCommandLineParsing:
-    def test_version(self, tmp_path, monkeypatch, capsys):
-        # See pypa/setuptools#4047
-        # This test can be removed once the CLI interface of setup.py is removed
-        monkeypatch.chdir(tmp_path)
-        toml_config = """
-        [project]
-        name = "test"
-        version = "42.0"
-        """
-        pyproject = Path(tmp_path, "pyproject.toml")
-        pyproject.write_text(cleandoc(toml_config), encoding="utf-8")
-        opts = {"script_args": ["--version"]}
-        dist = pyprojecttoml.apply_configuration(Distribution(opts), pyproject)
-        dist.parse_command_line()  # <-- there should be no exception here.
-        captured = capsys.readouterr()
-        assert "42.0" in captured.out
-
-
-class TestStaticConfig:
-    def test_mark_static_fields(self, tmp_path, monkeypatch):
-        monkeypatch.chdir(tmp_path)
-        toml_config = """
-        [project]
-        name = "test"
-        version = "42.0"
-        dependencies = ["hello"]
-        keywords = ["world"]
-        classifiers = ["private :: hello world"]
-        [tool.setuptools]
-        obsoletes = ["abcd"]
-        provides = ["abcd"]
-        platforms = ["abcd"]
-        """
-        pyproject = Path(tmp_path, "pyproject.toml")
-        pyproject.write_text(cleandoc(toml_config), encoding="utf-8")
-        dist = pyprojecttoml.apply_configuration(Distribution({}), pyproject)
-        assert is_static(dist.install_requires)
-        assert is_static(dist.metadata.keywords)
-        assert is_static(dist.metadata.classifiers)
-        assert is_static(dist.metadata.obsoletes)
-        assert is_static(dist.metadata.provides)
-        assert is_static(dist.metadata.platforms)
-
-
-# --- Auxiliary Functions ---
-
-
-def core_metadata(dist) -> str:
-    with io.StringIO() as buffer:
-        dist.metadata.write_pkg_file(buffer)
-        pkg_file_txt = buffer.getvalue()
-
-    # Make sure core metadata is valid
-    Metadata.from_email(pkg_file_txt, validate=True)  # can raise exceptions
-
-    skip_prefixes: tuple[str, ...] = ()
-    skip_lines = set()
-    # ---- DIFF NORMALISATION ----
-    # PEP 621 is very particular about author/maintainer metadata conversion, so skip
-    skip_prefixes += ("Author:", "Author-email:", "Maintainer:", "Maintainer-email:")
-    # May be redundant with Home-page
-    skip_prefixes += ("Project-URL: Homepage,", "Home-page:")
-    # May be missing in original (relying on default) but backfilled in the TOML
-    skip_prefixes += ("Description-Content-Type:",)
-    # Remove empty lines
-    skip_lines.add("")
-
-    result = []
-    for line in pkg_file_txt.splitlines():
-        if line.startswith(skip_prefixes) or line in skip_lines:
-            continue
-        result.append(line + "\n")
-
-    return "".join(result)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_expand.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_expand.py
deleted file mode 100644
index c5710ec..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_expand.py
+++ /dev/null
@@ -1,247 +0,0 @@
-import os
-import sys
-from pathlib import Path
-
-import pytest
-
-from setuptools._static import is_static
-from setuptools.config import expand
-from setuptools.discovery import find_package_path
-
-from distutils.errors import DistutilsOptionError
-
-
-def write_files(files, root_dir):
-    for file, content in files.items():
-        path = root_dir / file
-        path.parent.mkdir(exist_ok=True, parents=True)
-        path.write_text(content, encoding="utf-8")
-
-
-def test_glob_relative(tmp_path, monkeypatch):
-    files = {
-        "dir1/dir2/dir3/file1.txt",
-        "dir1/dir2/file2.txt",
-        "dir1/file3.txt",
-        "a.ini",
-        "b.ini",
-        "dir1/c.ini",
-        "dir1/dir2/a.ini",
-    }
-
-    write_files({k: "" for k in files}, tmp_path)
-    patterns = ["**/*.txt", "[ab].*", "**/[ac].ini"]
-    monkeypatch.chdir(tmp_path)
-    assert set(expand.glob_relative(patterns)) == files
-    # Make sure the same APIs work outside cwd
-    assert set(expand.glob_relative(patterns, tmp_path)) == files
-
-
-def test_read_files(tmp_path, monkeypatch):
-    dir_ = tmp_path / "dir_"
-    (tmp_path / "_dir").mkdir(exist_ok=True)
-    (tmp_path / "a.txt").touch()
-    files = {"a.txt": "a", "dir1/b.txt": "b", "dir1/dir2/c.txt": "c"}
-    write_files(files, dir_)
-
-    secrets = Path(str(dir_) + "secrets")
-    secrets.mkdir(exist_ok=True)
-    write_files({"secrets.txt": "secret keys"}, secrets)
-
-    with monkeypatch.context() as m:
-        m.chdir(dir_)
-        assert expand.read_files(list(files)) == "a\nb\nc"
-
-        cannot_access_msg = r"Cannot access '.*\.\..a\.txt'"
-        with pytest.raises(DistutilsOptionError, match=cannot_access_msg):
-            expand.read_files(["../a.txt"])
-
-        cannot_access_secrets_msg = r"Cannot access '.*secrets\.txt'"
-        with pytest.raises(DistutilsOptionError, match=cannot_access_secrets_msg):
-            expand.read_files(["../dir_secrets/secrets.txt"])
-
-    # Make sure the same APIs work outside cwd
-    assert expand.read_files(list(files), dir_) == "a\nb\nc"
-    with pytest.raises(DistutilsOptionError, match=cannot_access_msg):
-        expand.read_files(["../a.txt"], dir_)
-
-
-class TestReadAttr:
-    @pytest.mark.parametrize(
-        "example",
-        [
-            # No cookie means UTF-8:
-            b"__version__ = '\xc3\xa9'\nraise SystemExit(1)\n",
-            # If a cookie is present, honor it:
-            b"# -*- coding: utf-8 -*-\n__version__ = '\xc3\xa9'\nraise SystemExit(1)\n",
-            b"# -*- coding: latin1 -*-\n__version__ = '\xe9'\nraise SystemExit(1)\n",
-        ],
-    )
-    def test_read_attr_encoding_cookie(self, example, tmp_path):
-        (tmp_path / "mod.py").write_bytes(example)
-        assert expand.read_attr('mod.__version__', root_dir=tmp_path) == 'é'
-
-    def test_read_attr(self, tmp_path, monkeypatch):
-        files = {
-            "pkg/__init__.py": "",
-            "pkg/sub/__init__.py": "VERSION = '0.1.1'",
-            "pkg/sub/mod.py": (
-                "VALUES = {'a': 0, 'b': {42}, 'c': (0, 1, 1)}\nraise SystemExit(1)"
-            ),
-        }
-        write_files(files, tmp_path)
-
-        with monkeypatch.context() as m:
-            m.chdir(tmp_path)
-            # Make sure it can read the attr statically without evaluating the module
-            version = expand.read_attr('pkg.sub.VERSION')
-            values = expand.read_attr('lib.mod.VALUES', {'lib': 'pkg/sub'})
-
-        assert version == '0.1.1'
-        assert is_static(values)
-
-        assert values['a'] == 0
-        assert values['b'] == {42}
-        assert is_static(values)
-
-        # Make sure the same APIs work outside cwd
-        assert expand.read_attr('pkg.sub.VERSION', root_dir=tmp_path) == '0.1.1'
-        values = expand.read_attr('lib.mod.VALUES', {'lib': 'pkg/sub'}, tmp_path)
-        assert values['c'] == (0, 1, 1)
-
-    @pytest.mark.parametrize(
-        "example",
-        [
-            "VERSION: str\nVERSION = '0.1.1'\nraise SystemExit(1)\n",
-            "VERSION: str = '0.1.1'\nraise SystemExit(1)\n",
-        ],
-    )
-    def test_read_annotated_attr(self, tmp_path, example):
-        files = {
-            "pkg/__init__.py": "",
-            "pkg/sub/__init__.py": example,
-        }
-        write_files(files, tmp_path)
-        # Make sure this attribute can be read statically
-        version = expand.read_attr('pkg.sub.VERSION', root_dir=tmp_path)
-        assert version == '0.1.1'
-        assert is_static(version)
-
-    @pytest.mark.parametrize(
-        "example",
-        [
-            "VERSION = (lambda: '0.1.1')()\n",
-            "def fn(): return '0.1.1'\nVERSION = fn()\n",
-            "VERSION: str = (lambda: '0.1.1')()\n",
-        ],
-    )
-    def test_read_dynamic_attr(self, tmp_path, monkeypatch, example):
-        files = {
-            "pkg/__init__.py": "",
-            "pkg/sub/__init__.py": example,
-        }
-        write_files(files, tmp_path)
-        monkeypatch.chdir(tmp_path)
-        version = expand.read_attr('pkg.sub.VERSION')
-        assert version == '0.1.1'
-        assert not is_static(version)
-
-    def test_import_order(self, tmp_path):
-        """
-        Sometimes the import machinery will import the parent package of a nested
-        module, which triggers side-effects and might create problems (see issue #3176)
-
-        ``read_attr`` should bypass these limitations by resolving modules statically
-        (via ast.literal_eval).
-        """
-        files = {
-            "src/pkg/__init__.py": "from .main import func\nfrom .about import version",
-            "src/pkg/main.py": "import super_complicated_dep\ndef func(): return 42",
-            "src/pkg/about.py": "version = '42'",
-        }
-        write_files(files, tmp_path)
-        attr_desc = "pkg.about.version"
-        package_dir = {"": "src"}
-        # `import super_complicated_dep` should not run, otherwise the build fails
-        assert expand.read_attr(attr_desc, package_dir, tmp_path) == "42"
-
-
-@pytest.mark.parametrize(
-    ("package_dir", "file", "module", "return_value"),
-    [
-        ({"": "src"}, "src/pkg/main.py", "pkg.main", 42),
-        ({"pkg": "lib"}, "lib/main.py", "pkg.main", 13),
-        ({}, "single_module.py", "single_module", 70),
-        ({}, "flat_layout/pkg.py", "flat_layout.pkg", 836),
-    ],
-)
-def test_resolve_class(monkeypatch, tmp_path, package_dir, file, module, return_value):
-    monkeypatch.setattr(sys, "modules", {})  # reproducibility
-    files = {file: f"class Custom:\n    def testing(self): return {return_value}"}
-    write_files(files, tmp_path)
-    cls = expand.resolve_class(f"{module}.Custom", package_dir, tmp_path)
-    assert cls().testing() == return_value
-
-
-@pytest.mark.parametrize(
-    ("args", "pkgs"),
-    [
-        ({"where": ["."], "namespaces": False}, {"pkg", "other"}),
-        ({"where": [".", "dir1"], "namespaces": False}, {"pkg", "other", "dir2"}),
-        ({"namespaces": True}, {"pkg", "other", "dir1", "dir1.dir2"}),
-        ({}, {"pkg", "other", "dir1", "dir1.dir2"}),  # default value for `namespaces`
-    ],
-)
-def test_find_packages(tmp_path, args, pkgs):
-    files = {
-        "pkg/__init__.py",
-        "other/__init__.py",
-        "dir1/dir2/__init__.py",
-    }
-    write_files({k: "" for k in files}, tmp_path)
-
-    package_dir = {}
-    kwargs = {"root_dir": tmp_path, "fill_package_dir": package_dir, **args}
-    where = kwargs.get("where", ["."])
-    assert set(expand.find_packages(**kwargs)) == pkgs
-    for pkg in pkgs:
-        pkg_path = find_package_path(pkg, package_dir, tmp_path)
-        assert os.path.exists(pkg_path)
-
-    # Make sure the same APIs work outside cwd
-    where = [
-        str((tmp_path / p).resolve()).replace(os.sep, "/")  # ensure posix-style paths
-        for p in args.pop("where", ["."])
-    ]
-
-    assert set(expand.find_packages(where=where, **args)) == pkgs
-
-
-@pytest.mark.parametrize(
-    ("files", "where", "expected_package_dir"),
-    [
-        (["pkg1/__init__.py", "pkg1/other.py"], ["."], {}),
-        (["pkg1/__init__.py", "pkg2/__init__.py"], ["."], {}),
-        (["src/pkg1/__init__.py", "src/pkg1/other.py"], ["src"], {"": "src"}),
-        (["src/pkg1/__init__.py", "src/pkg2/__init__.py"], ["src"], {"": "src"}),
-        (
-            ["src1/pkg1/__init__.py", "src2/pkg2/__init__.py"],
-            ["src1", "src2"],
-            {"pkg1": "src1/pkg1", "pkg2": "src2/pkg2"},
-        ),
-        (
-            ["src/pkg1/__init__.py", "pkg2/__init__.py"],
-            ["src", "."],
-            {"pkg1": "src/pkg1"},
-        ),
-    ],
-)
-def test_fill_package_dir(tmp_path, files, where, expected_package_dir):
-    write_files({k: "" for k in files}, tmp_path)
-    pkg_dir = {}
-    kwargs = {"root_dir": tmp_path, "fill_package_dir": pkg_dir, "namespaces": False}
-    pkgs = expand.find_packages(where=where, **kwargs)
-    assert set(pkg_dir.items()) == set(expected_package_dir.items())
-    for pkg in pkgs:
-        pkg_path = find_package_path(pkg, pkg_dir, tmp_path)
-        assert os.path.exists(pkg_path)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_pyprojecttoml.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_pyprojecttoml.py
deleted file mode 100644
index db40fcd..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_pyprojecttoml.py
+++ /dev/null
@@ -1,396 +0,0 @@
-import re
-from configparser import ConfigParser
-from inspect import cleandoc
-
-import jaraco.path
-import pytest
-import tomli_w
-from path import Path
-
-import setuptools  # noqa: F401 # force distutils.core to be patched
-from setuptools.config.pyprojecttoml import (
-    _ToolsTypoInMetadata,
-    apply_configuration,
-    expand_configuration,
-    read_configuration,
-    validate,
-)
-from setuptools.dist import Distribution
-from setuptools.errors import OptionError
-
-import distutils.core
-
-EXAMPLE = """
-[project]
-name = "myproj"
-keywords = ["some", "key", "words"]
-dynamic = ["version", "readme"]
-requires-python = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
-dependencies = [
-    'importlib-metadata>=0.12;python_version<"3.8"',
-    'importlib-resources>=1.0;python_version<"3.7"',
-    'pathlib2>=2.3.3,<3;python_version < "3.4" and sys.platform != "win32"',
-]
-
-[project.optional-dependencies]
-docs = [
-    "sphinx>=3",
-    "sphinx-argparse>=0.2.5",
-    "sphinx-rtd-theme>=0.4.3",
-]
-testing = [
-    "pytest>=1",
-    "coverage>=3,<5",
-]
-
-[project.scripts]
-exec = "pkg.__main__:exec"
-
-[build-system]
-requires = ["setuptools", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[tool.setuptools]
-package-dir = {"" = "src"}
-zip-safe = true
-platforms = ["any"]
-
-[tool.setuptools.packages.find]
-where = ["src"]
-
-[tool.setuptools.cmdclass]
-sdist = "pkg.mod.CustomSdist"
-
-[tool.setuptools.dynamic.version]
-attr = "pkg.__version__.VERSION"
-
-[tool.setuptools.dynamic.readme]
-file = ["README.md"]
-content-type = "text/markdown"
-
-[tool.setuptools.package-data]
-"*" = ["*.txt"]
-
-[tool.setuptools.data-files]
-"data" = ["_files/*.txt"]
-
-[tool.distutils.sdist]
-formats = "gztar"
-
-[tool.distutils.bdist_wheel]
-universal = true
-"""
-
-
-def create_example(path, pkg_root):
-    files = {
-        "pyproject.toml": EXAMPLE,
-        "README.md": "hello world",
-        "_files": {
-            "file.txt": "",
-        },
-    }
-    packages = {
-        "pkg": {
-            "__init__.py": "",
-            "mod.py": "class CustomSdist: pass",
-            "__version__.py": "VERSION = (3, 10)",
-            "__main__.py": "def exec(): print('hello')",
-        },
-    }
-
-    assert pkg_root  # Meta-test: cannot be empty string.
-
-    if pkg_root == ".":
-        files = {**files, **packages}
-        # skip other files: flat-layout will raise error for multi-package dist
-    else:
-        # Use this opportunity to ensure namespaces are discovered
-        files[pkg_root] = {**packages, "other": {"nested": {"__init__.py": ""}}}
-
-    jaraco.path.build(files, prefix=path)
-
-
-def verify_example(config, path, pkg_root):
-    pyproject = path / "pyproject.toml"
-    pyproject.write_text(tomli_w.dumps(config), encoding="utf-8")
-    expanded = expand_configuration(config, path)
-    expanded_project = expanded["project"]
-    assert read_configuration(pyproject, expand=True) == expanded
-    assert expanded_project["version"] == "3.10"
-    assert expanded_project["readme"]["text"] == "hello world"
-    assert "packages" in expanded["tool"]["setuptools"]
-    if pkg_root == ".":
-        # Auto-discovery will raise error for multi-package dist
-        assert set(expanded["tool"]["setuptools"]["packages"]) == {"pkg"}
-    else:
-        assert set(expanded["tool"]["setuptools"]["packages"]) == {
-            "pkg",
-            "other",
-            "other.nested",
-        }
-    assert expanded["tool"]["setuptools"]["include-package-data"] is True
-    assert "" in expanded["tool"]["setuptools"]["package-data"]
-    assert "*" not in expanded["tool"]["setuptools"]["package-data"]
-    assert expanded["tool"]["setuptools"]["data-files"] == [
-        ("data", ["_files/file.txt"])
-    ]
-
-
-def test_read_configuration(tmp_path):
-    create_example(tmp_path, "src")
-    pyproject = tmp_path / "pyproject.toml"
-
-    config = read_configuration(pyproject, expand=False)
-    assert config["project"].get("version") is None
-    assert config["project"].get("readme") is None
-
-    verify_example(config, tmp_path, "src")
-
-
-@pytest.mark.parametrize(
-    ("pkg_root", "opts"),
-    [
-        (".", {}),
-        ("src", {}),
-        ("lib", {"packages": {"find": {"where": ["lib"]}}}),
-    ],
-)
-def test_discovered_package_dir_with_attr_directive_in_config(tmp_path, pkg_root, opts):
-    create_example(tmp_path, pkg_root)
-
-    pyproject = tmp_path / "pyproject.toml"
-
-    config = read_configuration(pyproject, expand=False)
-    assert config["project"].get("version") is None
-    assert config["project"].get("readme") is None
-    config["tool"]["setuptools"].pop("packages", None)
-    config["tool"]["setuptools"].pop("package-dir", None)
-
-    config["tool"]["setuptools"].update(opts)
-    verify_example(config, tmp_path, pkg_root)
-
-
-ENTRY_POINTS = {
-    "console_scripts": {"a": "mod.a:func"},
-    "gui_scripts": {"b": "mod.b:func"},
-    "other": {"c": "mod.c:func [extra]"},
-}
-
-
-class TestEntryPoints:
-    def write_entry_points(self, tmp_path):
-        entry_points = ConfigParser()
-        entry_points.read_dict(ENTRY_POINTS)
-        with open(tmp_path / "entry-points.txt", "w", encoding="utf-8") as f:
-            entry_points.write(f)
-
-    def pyproject(self, dynamic=None):
-        project = {"dynamic": dynamic or ["scripts", "gui-scripts", "entry-points"]}
-        tool = {"dynamic": {"entry-points": {"file": "entry-points.txt"}}}
-        return {"project": project, "tool": {"setuptools": tool}}
-
-    def test_all_listed_in_dynamic(self, tmp_path):
-        self.write_entry_points(tmp_path)
-        expanded = expand_configuration(self.pyproject(), tmp_path)
-        expanded_project = expanded["project"]
-        assert len(expanded_project["scripts"]) == 1
-        assert expanded_project["scripts"]["a"] == "mod.a:func"
-        assert len(expanded_project["gui-scripts"]) == 1
-        assert expanded_project["gui-scripts"]["b"] == "mod.b:func"
-        assert len(expanded_project["entry-points"]) == 1
-        assert expanded_project["entry-points"]["other"]["c"] == "mod.c:func [extra]"
-
-    @pytest.mark.parametrize("missing_dynamic", ("scripts", "gui-scripts"))
-    def test_scripts_not_listed_in_dynamic(self, tmp_path, missing_dynamic):
-        self.write_entry_points(tmp_path)
-        dynamic = {"scripts", "gui-scripts", "entry-points"} - {missing_dynamic}
-
-        msg = f"defined outside of `pyproject.toml`:.*{missing_dynamic}"
-        with pytest.raises(OptionError, match=re.compile(msg, re.S)):
-            expand_configuration(self.pyproject(dynamic), tmp_path)
-
-
-class TestClassifiers:
-    def test_dynamic(self, tmp_path):
-        # Let's create a project example that has dynamic classifiers
-        # coming from a txt file.
-        create_example(tmp_path, "src")
-        classifiers = cleandoc(
-            """
-            Framework :: Flask
-            Programming Language :: Haskell
-            """
-        )
-        (tmp_path / "classifiers.txt").write_text(classifiers, encoding="utf-8")
-
-        pyproject = tmp_path / "pyproject.toml"
-        config = read_configuration(pyproject, expand=False)
-        dynamic = config["project"]["dynamic"]
-        config["project"]["dynamic"] = list({*dynamic, "classifiers"})
-        dynamic_config = config["tool"]["setuptools"]["dynamic"]
-        dynamic_config["classifiers"] = {"file": "classifiers.txt"}
-
-        # When the configuration is expanded,
-        # each line of the file should be an different classifier.
-        validate(config, pyproject)
-        expanded = expand_configuration(config, tmp_path)
-
-        assert set(expanded["project"]["classifiers"]) == {
-            "Framework :: Flask",
-            "Programming Language :: Haskell",
-        }
-
-    def test_dynamic_without_config(self, tmp_path):
-        config = """
-        [project]
-        name = "myproj"
-        version = '42'
-        dynamic = ["classifiers"]
-        """
-
-        pyproject = tmp_path / "pyproject.toml"
-        pyproject.write_text(cleandoc(config), encoding="utf-8")
-        with pytest.raises(OptionError, match="No configuration .* .classifiers."):
-            read_configuration(pyproject)
-
-    def test_dynamic_readme_from_setup_script_args(self, tmp_path):
-        config = """
-        [project]
-        name = "myproj"
-        version = '42'
-        dynamic = ["readme"]
-        """
-        pyproject = tmp_path / "pyproject.toml"
-        pyproject.write_text(cleandoc(config), encoding="utf-8")
-        dist = Distribution(attrs={"long_description": "42"})
-        # No error should occur because of missing `readme`
-        dist = apply_configuration(dist, pyproject)
-        assert dist.metadata.long_description == "42"
-
-    def test_dynamic_without_file(self, tmp_path):
-        config = """
-        [project]
-        name = "myproj"
-        version = '42'
-        dynamic = ["classifiers"]
-
-        [tool.setuptools.dynamic]
-        classifiers = {file = ["classifiers.txt"]}
-        """
-
-        pyproject = tmp_path / "pyproject.toml"
-        pyproject.write_text(cleandoc(config), encoding="utf-8")
-        with pytest.warns(UserWarning, match="File .*classifiers.txt. cannot be found"):
-            expanded = read_configuration(pyproject)
-        assert "classifiers" not in expanded["project"]
-
-
-@pytest.mark.parametrize(
-    "example",
-    (
-        """
-        [project]
-        name = "myproj"
-        version = "1.2"
-
-        [my-tool.that-disrespect.pep518]
-        value = 42
-        """,
-    ),
-)
-def test_ignore_unrelated_config(tmp_path, example):
-    pyproject = tmp_path / "pyproject.toml"
-    pyproject.write_text(cleandoc(example), encoding="utf-8")
-
-    # Make sure no error is raised due to 3rd party configs in pyproject.toml
-    assert read_configuration(pyproject) is not None
-
-
-@pytest.mark.parametrize(
-    ("example", "error_msg"),
-    [
-        (
-            """
-            [project]
-            name = "myproj"
-            version = "1.2"
-            requires = ['pywin32; platform_system=="Windows"' ]
-            """,
-            "configuration error: .project. must not contain ..requires.. properties",
-        ),
-    ],
-)
-def test_invalid_example(tmp_path, example, error_msg):
-    pyproject = tmp_path / "pyproject.toml"
-    pyproject.write_text(cleandoc(example), encoding="utf-8")
-
-    pattern = re.compile(f"invalid pyproject.toml.*{error_msg}.*", re.M | re.S)
-    with pytest.raises(ValueError, match=pattern):
-        read_configuration(pyproject)
-
-
-@pytest.mark.parametrize("config", ("", "[tool.something]\nvalue = 42"))
-def test_empty(tmp_path, config):
-    pyproject = tmp_path / "pyproject.toml"
-    pyproject.write_text(config, encoding="utf-8")
-
-    # Make sure no error is raised
-    assert read_configuration(pyproject) == {}
-
-
-@pytest.mark.parametrize("config", ("[project]\nname = 'myproj'\nversion='42'\n",))
-def test_include_package_data_by_default(tmp_path, config):
-    """Builds with ``pyproject.toml`` should consider ``include-package-data=True`` as
-    default.
-    """
-    pyproject = tmp_path / "pyproject.toml"
-    pyproject.write_text(config, encoding="utf-8")
-
-    config = read_configuration(pyproject)
-    assert config["tool"]["setuptools"]["include-package-data"] is True
-
-
-def test_include_package_data_in_setuppy(tmp_path):
-    """Builds with ``pyproject.toml`` should consider ``include_package_data`` set in
-    ``setup.py``.
-
-    See https://github.com/pypa/setuptools/issues/3197#issuecomment-1079023889
-    """
-    files = {
-        "pyproject.toml": "[project]\nname = 'myproj'\nversion='42'\n",
-        "setup.py": "__import__('setuptools').setup(include_package_data=False)",
-    }
-    jaraco.path.build(files, prefix=tmp_path)
-
-    with Path(tmp_path):
-        dist = distutils.core.run_setup("setup.py", {}, stop_after="config")
-
-    assert dist.get_name() == "myproj"
-    assert dist.get_version() == "42"
-    assert dist.include_package_data is False
-
-
-def test_warn_tools_typo(tmp_path):
-    """Test that the common ``tools.setuptools`` typo in ``pyproject.toml`` issues a warning
-
-    See https://github.com/pypa/setuptools/issues/4150
-    """
-    config = """
-    [build-system]
-    requires = ["setuptools"]
-    build-backend = "setuptools.build_meta"
-
-    [project]
-    name = "myproj"
-    version = '42'
-
-    [tools.setuptools]
-    packages = ["package"]
-    """
-
-    pyproject = tmp_path / "pyproject.toml"
-    pyproject.write_text(cleandoc(config), encoding="utf-8")
-
-    with pytest.warns(_ToolsTypoInMetadata):
-        read_configuration(pyproject)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_pyprojecttoml_dynamic_deps.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_pyprojecttoml_dynamic_deps.py
deleted file mode 100644
index e42f28f..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_pyprojecttoml_dynamic_deps.py
+++ /dev/null
@@ -1,109 +0,0 @@
-from inspect import cleandoc
-
-import pytest
-from jaraco import path
-
-from setuptools.config.pyprojecttoml import apply_configuration
-from setuptools.dist import Distribution
-from setuptools.warnings import SetuptoolsWarning
-
-
-def test_dynamic_dependencies(tmp_path):
-    files = {
-        "requirements.txt": "six\n  # comment\n",
-        "pyproject.toml": cleandoc(
-            """
-            [project]
-            name = "myproj"
-            version = "1.0"
-            dynamic = ["dependencies"]
-
-            [build-system]
-            requires = ["setuptools", "wheel"]
-            build-backend = "setuptools.build_meta"
-
-            [tool.setuptools.dynamic.dependencies]
-            file = ["requirements.txt"]
-            """
-        ),
-    }
-    path.build(files, prefix=tmp_path)
-    dist = Distribution()
-    dist = apply_configuration(dist, tmp_path / "pyproject.toml")
-    assert dist.install_requires == ["six"]
-
-
-def test_dynamic_optional_dependencies(tmp_path):
-    files = {
-        "requirements-docs.txt": "sphinx\n  # comment\n",
-        "pyproject.toml": cleandoc(
-            """
-            [project]
-            name = "myproj"
-            version = "1.0"
-            dynamic = ["optional-dependencies"]
-
-            [tool.setuptools.dynamic.optional-dependencies.docs]
-            file = ["requirements-docs.txt"]
-
-            [build-system]
-            requires = ["setuptools", "wheel"]
-            build-backend = "setuptools.build_meta"
-            """
-        ),
-    }
-    path.build(files, prefix=tmp_path)
-    dist = Distribution()
-    dist = apply_configuration(dist, tmp_path / "pyproject.toml")
-    assert dist.extras_require == {"docs": ["sphinx"]}
-
-
-def test_mixed_dynamic_optional_dependencies(tmp_path):
-    """
-    Test that if PEP 621 was loosened to allow mixing of dynamic and static
-    configurations in the case of fields containing sub-fields (groups),
-    things would work out.
-    """
-    files = {
-        "requirements-images.txt": "pillow~=42.0\n  # comment\n",
-        "pyproject.toml": cleandoc(
-            """
-            [project]
-            name = "myproj"
-            version = "1.0"
-            dynamic = ["optional-dependencies"]
-
-            [project.optional-dependencies]
-            docs = ["sphinx"]
-
-            [tool.setuptools.dynamic.optional-dependencies.images]
-            file = ["requirements-images.txt"]
-            """
-        ),
-    }
-
-    path.build(files, prefix=tmp_path)
-    pyproject = tmp_path / "pyproject.toml"
-    with pytest.raises(ValueError, match="project.optional-dependencies"):
-        apply_configuration(Distribution(), pyproject)
-
-
-def test_mixed_extras_require_optional_dependencies(tmp_path):
-    files = {
-        "pyproject.toml": cleandoc(
-            """
-            [project]
-            name = "myproj"
-            version = "1.0"
-            optional-dependencies.docs = ["sphinx"]
-            """
-        ),
-    }
-
-    path.build(files, prefix=tmp_path)
-    pyproject = tmp_path / "pyproject.toml"
-
-    with pytest.warns(SetuptoolsWarning, match=".extras_require. overwritten"):
-        dist = Distribution({"extras_require": {"hello": ["world"]}})
-        dist = apply_configuration(dist, pyproject)
-        assert dist.extras_require == {"docs": ["sphinx"]}
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_setupcfg.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_setupcfg.py
deleted file mode 100644
index 61af990..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/config/test_setupcfg.py
+++ /dev/null
@@ -1,980 +0,0 @@
-import configparser
-import contextlib
-import inspect
-import re
-from pathlib import Path
-from unittest.mock import Mock, patch
-
-import pytest
-from packaging.requirements import InvalidRequirement
-
-from setuptools.config.setupcfg import ConfigHandler, Target, read_configuration
-from setuptools.dist import Distribution, _Distribution
-from setuptools.warnings import SetuptoolsDeprecationWarning
-
-from ..textwrap import DALS
-
-from distutils.errors import DistutilsFileError, DistutilsOptionError
-
-
-class ErrConfigHandler(ConfigHandler[Target]):
-    """Erroneous handler. Fails to implement required methods."""
-
-    section_prefix = "**err**"
-
-
-def make_package_dir(name, base_dir, ns=False):
-    dir_package = base_dir
-    for dir_name in name.split('/'):
-        dir_package = dir_package.mkdir(dir_name)
-    init_file = None
-    if not ns:
-        init_file = dir_package.join('__init__.py')
-        init_file.write('')
-    return dir_package, init_file
-
-
-def fake_env(
-    tmpdir, setup_cfg, setup_py=None, encoding='ascii', package_path='fake_package'
-):
-    if setup_py is None:
-        setup_py = 'from setuptools import setup\nsetup()\n'
-
-    tmpdir.join('setup.py').write(setup_py)
-    config = tmpdir.join('setup.cfg')
-    config.write(setup_cfg.encode(encoding), mode='wb')
-
-    package_dir, init_file = make_package_dir(package_path, tmpdir)
-
-    init_file.write(
-        'VERSION = (1, 2, 3)\n'
-        '\n'
-        'VERSION_MAJOR = 1'
-        '\n'
-        'def get_version():\n'
-        '    return [3, 4, 5, "dev"]\n'
-        '\n'
-    )
-
-    return package_dir, config
-
-
-@contextlib.contextmanager
-def get_dist(tmpdir, kwargs_initial=None, parse=True):
-    kwargs_initial = kwargs_initial or {}
-
-    with tmpdir.as_cwd():
-        dist = Distribution(kwargs_initial)
-        dist.script_name = 'setup.py'
-        parse and dist.parse_config_files()
-
-        yield dist
-
-
-def test_parsers_implemented():
-    with pytest.raises(NotImplementedError):
-        handler = ErrConfigHandler(None, {}, False, Mock())
-        handler.parsers
-
-
-class TestConfigurationReader:
-    def test_basic(self, tmpdir):
-        _, config = fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'version = 10.1.1\n'
-            'keywords = one, two\n'
-            '\n'
-            '[options]\n'
-            'scripts = bin/a.py, bin/b.py\n',
-        )
-        config_dict = read_configuration(str(config))
-        assert config_dict['metadata']['version'] == '10.1.1'
-        assert config_dict['metadata']['keywords'] == ['one', 'two']
-        assert config_dict['options']['scripts'] == ['bin/a.py', 'bin/b.py']
-
-    def test_no_config(self, tmpdir):
-        with pytest.raises(DistutilsFileError):
-            read_configuration(str(tmpdir.join('setup.cfg')))
-
-    def test_ignore_errors(self, tmpdir):
-        _, config = fake_env(
-            tmpdir,
-            '[metadata]\nversion = attr: none.VERSION\nkeywords = one, two\n',
-        )
-        with pytest.raises(ImportError):
-            read_configuration(str(config))
-
-        config_dict = read_configuration(str(config), ignore_option_errors=True)
-
-        assert config_dict['metadata']['keywords'] == ['one', 'two']
-        assert 'version' not in config_dict['metadata']
-
-        config.remove()
-
-
-class TestMetadata:
-    def test_basic(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'version = 10.1.1\n'
-            'description = Some description\n'
-            'long_description_content_type = text/something\n'
-            'long_description = file: README\n'
-            'name = fake_name\n'
-            'keywords = one, two\n'
-            'provides = package, package.sub\n'
-            'license = otherlic\n'
-            'download_url = http://test.test.com/test/\n'
-            'maintainer_email = test@test.com\n',
-        )
-
-        tmpdir.join('README').write('readme contents\nline2')
-
-        meta_initial = {
-            # This will be used so `otherlic` won't replace it.
-            'license': 'BSD 3-Clause License',
-        }
-
-        with get_dist(tmpdir, meta_initial) as dist:
-            metadata = dist.metadata
-
-            assert metadata.version == '10.1.1'
-            assert metadata.description == 'Some description'
-            assert metadata.long_description_content_type == 'text/something'
-            assert metadata.long_description == 'readme contents\nline2'
-            assert metadata.provides == ['package', 'package.sub']
-            assert metadata.license == 'BSD 3-Clause License'
-            assert metadata.name == 'fake_name'
-            assert metadata.keywords == ['one', 'two']
-            assert metadata.download_url == 'http://test.test.com/test/'
-            assert metadata.maintainer_email == 'test@test.com'
-
-    def test_license_cfg(self, tmpdir):
-        fake_env(
-            tmpdir,
-            DALS(
-                """
-            [metadata]
-            name=foo
-            version=0.0.1
-            license=Apache 2.0
-            """
-            ),
-        )
-
-        with get_dist(tmpdir) as dist:
-            metadata = dist.metadata
-
-            assert metadata.name == "foo"
-            assert metadata.version == "0.0.1"
-            assert metadata.license == "Apache 2.0"
-
-    def test_file_mixed(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\nlong_description = file: README.rst, CHANGES.rst\n\n',
-        )
-
-        tmpdir.join('README.rst').write('readme contents\nline2')
-        tmpdir.join('CHANGES.rst').write('changelog contents\nand stuff')
-
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.long_description == (
-                'readme contents\nline2\nchangelog contents\nand stuff'
-            )
-
-    def test_file_sandboxed(self, tmpdir):
-        tmpdir.ensure("README")
-        project = tmpdir.join('depth1', 'depth2')
-        project.ensure(dir=True)
-        fake_env(project, '[metadata]\nlong_description = file: ../../README\n')
-
-        with get_dist(project, parse=False) as dist:
-            with pytest.raises(DistutilsOptionError):
-                dist.parse_config_files()  # file: out of sandbox
-
-    def test_aliases(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'author_email = test@test.com\n'
-            'home_page = http://test.test.com/test/\n'
-            'summary = Short summary\n'
-            'platform = a, b\n'
-            'classifier =\n'
-            '  Framework :: Django\n'
-            '  Programming Language :: Python :: 3.5\n',
-        )
-
-        with get_dist(tmpdir) as dist:
-            metadata = dist.metadata
-            assert metadata.author_email == 'test@test.com'
-            assert metadata.url == 'http://test.test.com/test/'
-            assert metadata.description == 'Short summary'
-            assert metadata.platforms == ['a', 'b']
-            assert metadata.classifiers == [
-                'Framework :: Django',
-                'Programming Language :: Python :: 3.5',
-            ]
-
-    def test_multiline(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'name = fake_name\n'
-            'keywords =\n'
-            '  one\n'
-            '  two\n'
-            'classifiers =\n'
-            '  Framework :: Django\n'
-            '  Programming Language :: Python :: 3.5\n',
-        )
-        with get_dist(tmpdir) as dist:
-            metadata = dist.metadata
-            assert metadata.keywords == ['one', 'two']
-            assert metadata.classifiers == [
-                'Framework :: Django',
-                'Programming Language :: Python :: 3.5',
-            ]
-
-    def test_dict(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'project_urls =\n'
-            '  Link One = https://example.com/one/\n'
-            '  Link Two = https://example.com/two/\n',
-        )
-        with get_dist(tmpdir) as dist:
-            metadata = dist.metadata
-            assert metadata.project_urls == {
-                'Link One': 'https://example.com/one/',
-                'Link Two': 'https://example.com/two/',
-            }
-
-    def test_version(self, tmpdir):
-        package_dir, config = fake_env(
-            tmpdir, '[metadata]\nversion = attr: fake_package.VERSION\n'
-        )
-
-        sub_a = package_dir.mkdir('subpkg_a')
-        sub_a.join('__init__.py').write('')
-        sub_a.join('mod.py').write('VERSION = (2016, 11, 26)')
-
-        sub_b = package_dir.mkdir('subpkg_b')
-        sub_b.join('__init__.py').write('')
-        sub_b.join('mod.py').write(
-            'import third_party_module\nVERSION = (2016, 11, 26)'
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '1.2.3'
-
-        config.write('[metadata]\nversion = attr: fake_package.get_version\n')
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '3.4.5.dev'
-
-        config.write('[metadata]\nversion = attr: fake_package.VERSION_MAJOR\n')
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '1'
-
-        config.write('[metadata]\nversion = attr: fake_package.subpkg_a.mod.VERSION\n')
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '2016.11.26'
-
-        config.write('[metadata]\nversion = attr: fake_package.subpkg_b.mod.VERSION\n')
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '2016.11.26'
-
-    def test_version_file(self, tmpdir):
-        fake_env(tmpdir, '[metadata]\nversion = file: fake_package/version.txt\n')
-        tmpdir.join('fake_package', 'version.txt').write('1.2.3\n')
-
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '1.2.3'
-
-        tmpdir.join('fake_package', 'version.txt').write('1.2.3\n4.5.6\n')
-        with pytest.raises(DistutilsOptionError):
-            with get_dist(tmpdir) as dist:
-                dist.metadata.version
-
-    def test_version_with_package_dir_simple(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'version = attr: fake_package_simple.VERSION\n'
-            '[options]\n'
-            'package_dir =\n'
-            '    = src\n',
-            package_path='src/fake_package_simple',
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '1.2.3'
-
-    def test_version_with_package_dir_rename(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'version = attr: fake_package_rename.VERSION\n'
-            '[options]\n'
-            'package_dir =\n'
-            '    fake_package_rename = fake_dir\n',
-            package_path='fake_dir',
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '1.2.3'
-
-    def test_version_with_package_dir_complex(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[metadata]\n'
-            'version = attr: fake_package_complex.VERSION\n'
-            '[options]\n'
-            'package_dir =\n'
-            '    fake_package_complex = src/fake_dir\n',
-            package_path='src/fake_dir',
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.version == '1.2.3'
-
-    def test_unknown_meta_item(self, tmpdir):
-        fake_env(tmpdir, '[metadata]\nname = fake_name\nunknown = some\n')
-        with get_dist(tmpdir, parse=False) as dist:
-            dist.parse_config_files()  # Skip unknown.
-
-    def test_usupported_section(self, tmpdir):
-        fake_env(tmpdir, '[metadata.some]\nkey = val\n')
-        with get_dist(tmpdir, parse=False) as dist:
-            with pytest.raises(DistutilsOptionError):
-                dist.parse_config_files()
-
-    def test_classifiers(self, tmpdir):
-        expected = set([
-            'Framework :: Django',
-            'Programming Language :: Python :: 3',
-            'Programming Language :: Python :: 3.5',
-        ])
-
-        # From file.
-        _, config = fake_env(tmpdir, '[metadata]\nclassifiers = file: classifiers\n')
-
-        tmpdir.join('classifiers').write(
-            'Framework :: Django\n'
-            'Programming Language :: Python :: 3\n'
-            'Programming Language :: Python :: 3.5\n'
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert set(dist.metadata.classifiers) == expected
-
-        # From list notation
-        config.write(
-            '[metadata]\n'
-            'classifiers =\n'
-            '    Framework :: Django\n'
-            '    Programming Language :: Python :: 3\n'
-            '    Programming Language :: Python :: 3.5\n'
-        )
-        with get_dist(tmpdir) as dist:
-            assert set(dist.metadata.classifiers) == expected
-
-    def test_interpolation(self, tmpdir):
-        fake_env(tmpdir, '[metadata]\ndescription = %(message)s\n')
-        with pytest.raises(configparser.InterpolationMissingOptionError):
-            with get_dist(tmpdir):
-                pass
-
-    def test_non_ascii_1(self, tmpdir):
-        fake_env(tmpdir, '[metadata]\ndescription = éàïôñ\n', encoding='utf-8')
-        with get_dist(tmpdir):
-            pass
-
-    def test_non_ascii_3(self, tmpdir):
-        fake_env(tmpdir, '\n# -*- coding: invalid\n')
-        with get_dist(tmpdir):
-            pass
-
-    def test_non_ascii_4(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '# -*- coding: utf-8\n[metadata]\ndescription = éàïôñ\n',
-            encoding='utf-8',
-        )
-        with get_dist(tmpdir) as dist:
-            assert dist.metadata.description == 'éàïôñ'
-
-    def test_not_utf8(self, tmpdir):
-        """
-        Config files encoded not in UTF-8 will fail
-        """
-        fake_env(
-            tmpdir,
-            '# vim: set fileencoding=iso-8859-15 :\n[metadata]\ndescription = éàïôñ\n',
-            encoding='iso-8859-15',
-        )
-        with pytest.raises(UnicodeDecodeError):
-            with get_dist(tmpdir):
-                pass
-
-    @pytest.mark.parametrize(
-        ("error_msg", "config", "invalid"),
-        [
-            (
-                "Invalid dash-separated key 'author-email' in 'metadata' (setup.cfg)",
-                DALS(
-                    """
-                    [metadata]
-                    author-email = test@test.com
-                    maintainer_email = foo@foo.com
-                    """
-                ),
-                {"author-email": "test@test.com"},
-            ),
-            (
-                "Invalid uppercase key 'Name' in 'metadata' (setup.cfg)",
-                DALS(
-                    """
-                    [metadata]
-                    Name = foo
-                    description = Some description
-                    """
-                ),
-                {"Name": "foo"},
-            ),
-        ],
-    )
-    def test_invalid_options_previously_deprecated(
-        self, tmpdir, error_msg, config, invalid
-    ):
-        # This test and related methods can be removed when no longer needed.
-        # Deprecation postponed due to push-back from the community in
-        # https://github.com/pypa/setuptools/issues/4910
-        fake_env(tmpdir, config)
-        with pytest.warns(SetuptoolsDeprecationWarning, match=re.escape(error_msg)):
-            dist = get_dist(tmpdir).__enter__()
-
-        tmpdir.join('setup.cfg').remove()
-
-        for field, value in invalid.items():
-            attr = field.replace("-", "_").lower()
-            assert getattr(dist.metadata, attr) == value
-
-
-class TestOptions:
-    def test_basic(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[options]\n'
-            'zip_safe = True\n'
-            'include_package_data = yes\n'
-            'package_dir = b=c, =src\n'
-            'packages = pack_a, pack_b.subpack\n'
-            'namespace_packages = pack1, pack2\n'
-            'scripts = bin/one.py, bin/two.py\n'
-            'eager_resources = bin/one.py, bin/two.py\n'
-            'install_requires = docutils>=0.3; pack ==1.1, ==1.3; hey\n'
-            'setup_requires = docutils>=0.3; spack ==1.1, ==1.3; there\n'
-            'dependency_links = http://some.com/here/1, '
-            'http://some.com/there/2\n'
-            'python_requires = >=1.0, !=2.8\n'
-            'py_modules = module1, module2\n',
-        )
-        deprec = pytest.warns(SetuptoolsDeprecationWarning, match="namespace_packages")
-        with deprec, get_dist(tmpdir) as dist:
-            assert dist.zip_safe
-            assert dist.include_package_data
-            assert dist.package_dir == {'': 'src', 'b': 'c'}
-            assert dist.packages == ['pack_a', 'pack_b.subpack']
-            assert dist.namespace_packages == ['pack1', 'pack2']
-            assert dist.scripts == ['bin/one.py', 'bin/two.py']
-            assert dist.dependency_links == ([
-                'http://some.com/here/1',
-                'http://some.com/there/2',
-            ])
-            assert dist.install_requires == ([
-                'docutils>=0.3',
-                'pack==1.1,==1.3',
-                'hey',
-            ])
-            assert dist.setup_requires == ([
-                'docutils>=0.3',
-                'spack ==1.1, ==1.3',
-                'there',
-            ])
-            assert dist.python_requires == '>=1.0, !=2.8'
-            assert dist.py_modules == ['module1', 'module2']
-
-    def test_multiline(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[options]\n'
-            'package_dir = \n'
-            '  b=c\n'
-            '  =src\n'
-            'packages = \n'
-            '  pack_a\n'
-            '  pack_b.subpack\n'
-            'namespace_packages = \n'
-            '  pack1\n'
-            '  pack2\n'
-            'scripts = \n'
-            '  bin/one.py\n'
-            '  bin/two.py\n'
-            'eager_resources = \n'
-            '  bin/one.py\n'
-            '  bin/two.py\n'
-            'install_requires = \n'
-            '  docutils>=0.3\n'
-            '  pack ==1.1, ==1.3\n'
-            '  hey\n'
-            'setup_requires = \n'
-            '  docutils>=0.3\n'
-            '  spack ==1.1, ==1.3\n'
-            '  there\n'
-            'dependency_links = \n'
-            '  http://some.com/here/1\n'
-            '  http://some.com/there/2\n',
-        )
-        deprec = pytest.warns(SetuptoolsDeprecationWarning, match="namespace_packages")
-        with deprec, get_dist(tmpdir) as dist:
-            assert dist.package_dir == {'': 'src', 'b': 'c'}
-            assert dist.packages == ['pack_a', 'pack_b.subpack']
-            assert dist.namespace_packages == ['pack1', 'pack2']
-            assert dist.scripts == ['bin/one.py', 'bin/two.py']
-            assert dist.dependency_links == ([
-                'http://some.com/here/1',
-                'http://some.com/there/2',
-            ])
-            assert dist.install_requires == ([
-                'docutils>=0.3',
-                'pack==1.1,==1.3',
-                'hey',
-            ])
-            assert dist.setup_requires == ([
-                'docutils>=0.3',
-                'spack ==1.1, ==1.3',
-                'there',
-            ])
-
-    def test_package_dir_fail(self, tmpdir):
-        fake_env(tmpdir, '[options]\npackage_dir = a b\n')
-        with get_dist(tmpdir, parse=False) as dist:
-            with pytest.raises(DistutilsOptionError):
-                dist.parse_config_files()
-
-    def test_package_data(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[options.package_data]\n'
-            '* = *.txt, *.rst\n'
-            'hello = *.msg\n'
-            '\n'
-            '[options.exclude_package_data]\n'
-            '* = fake1.txt, fake2.txt\n'
-            'hello = *.dat\n',
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.package_data == {
-                '': ['*.txt', '*.rst'],
-                'hello': ['*.msg'],
-            }
-            assert dist.exclude_package_data == {
-                '': ['fake1.txt', 'fake2.txt'],
-                'hello': ['*.dat'],
-            }
-
-    def test_packages(self, tmpdir):
-        fake_env(tmpdir, '[options]\npackages = find:\n')
-
-        with get_dist(tmpdir) as dist:
-            assert dist.packages == ['fake_package']
-
-    def test_find_directive(self, tmpdir):
-        dir_package, config = fake_env(tmpdir, '[options]\npackages = find:\n')
-
-        make_package_dir('sub_one', dir_package)
-        make_package_dir('sub_two', dir_package)
-
-        with get_dist(tmpdir) as dist:
-            assert set(dist.packages) == set([
-                'fake_package',
-                'fake_package.sub_two',
-                'fake_package.sub_one',
-            ])
-
-        config.write(
-            '[options]\n'
-            'packages = find:\n'
-            '\n'
-            '[options.packages.find]\n'
-            'where = .\n'
-            'include =\n'
-            '    fake_package.sub_one\n'
-            '    two\n'
-        )
-        with get_dist(tmpdir) as dist:
-            assert dist.packages == ['fake_package.sub_one']
-
-        config.write(
-            '[options]\n'
-            'packages = find:\n'
-            '\n'
-            '[options.packages.find]\n'
-            'exclude =\n'
-            '    fake_package.sub_one\n'
-        )
-        with get_dist(tmpdir) as dist:
-            assert set(dist.packages) == set(['fake_package', 'fake_package.sub_two'])
-
-    def test_find_namespace_directive(self, tmpdir):
-        dir_package, config = fake_env(
-            tmpdir, '[options]\npackages = find_namespace:\n'
-        )
-
-        make_package_dir('sub_one', dir_package)
-        make_package_dir('sub_two', dir_package, ns=True)
-
-        with get_dist(tmpdir) as dist:
-            assert set(dist.packages) == {
-                'fake_package',
-                'fake_package.sub_two',
-                'fake_package.sub_one',
-            }
-
-        config.write(
-            '[options]\n'
-            'packages = find_namespace:\n'
-            '\n'
-            '[options.packages.find]\n'
-            'where = .\n'
-            'include =\n'
-            '    fake_package.sub_one\n'
-            '    two\n'
-        )
-        with get_dist(tmpdir) as dist:
-            assert dist.packages == ['fake_package.sub_one']
-
-        config.write(
-            '[options]\n'
-            'packages = find_namespace:\n'
-            '\n'
-            '[options.packages.find]\n'
-            'exclude =\n'
-            '    fake_package.sub_one\n'
-        )
-        with get_dist(tmpdir) as dist:
-            assert set(dist.packages) == {'fake_package', 'fake_package.sub_two'}
-
-    def test_extras_require(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[options.extras_require]\n'
-            'pdf = ReportLab>=1.2; RXP\n'
-            'rest = \n'
-            '  docutils>=0.3\n'
-            '  pack ==1.1, ==1.3\n',
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.extras_require == {
-                'pdf': ['ReportLab>=1.2', 'RXP'],
-                'rest': ['docutils>=0.3', 'pack==1.1,==1.3'],
-            }
-            assert set(dist.metadata.provides_extras) == {'pdf', 'rest'}
-
-    @pytest.mark.parametrize(
-        "config",
-        [
-            "[options.extras_require]\nfoo = bar;python_version<'3'",
-            "[options.extras_require]\nfoo = bar;os_name=='linux'",
-            "[options.extras_require]\nfoo = bar;python_version<'3'\n",
-            "[options.extras_require]\nfoo = bar;os_name=='linux'\n",
-            "[options]\ninstall_requires = bar;python_version<'3'",
-            "[options]\ninstall_requires = bar;os_name=='linux'",
-            "[options]\ninstall_requires = bar;python_version<'3'\n",
-            "[options]\ninstall_requires = bar;os_name=='linux'\n",
-        ],
-    )
-    def test_raises_accidental_env_marker_misconfig(self, config, tmpdir):
-        fake_env(tmpdir, config)
-        match = (
-            r"One of the parsed requirements in `(install_requires|extras_require.+)` "
-            "looks like a valid environment marker.*"
-        )
-        with pytest.raises(InvalidRequirement, match=match):
-            with get_dist(tmpdir) as _:
-                pass
-
-    @pytest.mark.parametrize(
-        "config",
-        [
-            "[options.extras_require]\nfoo = bar;python_version<3",
-            "[options.extras_require]\nfoo = bar;python_version<3\n",
-            "[options]\ninstall_requires = bar;python_version<3",
-            "[options]\ninstall_requires = bar;python_version<3\n",
-        ],
-    )
-    def test_warn_accidental_env_marker_misconfig(self, config, tmpdir):
-        fake_env(tmpdir, config)
-        match = (
-            r"One of the parsed requirements in `(install_requires|extras_require.+)` "
-            "looks like a valid environment marker.*"
-        )
-        with pytest.warns(SetuptoolsDeprecationWarning, match=match):
-            with get_dist(tmpdir) as _:
-                pass
-
-    @pytest.mark.parametrize(
-        "config",
-        [
-            "[options.extras_require]\nfoo =\n    bar;python_version<'3'",
-            "[options.extras_require]\nfoo = bar;baz\nboo = xxx;yyy",
-            "[options.extras_require]\nfoo =\n    bar;python_version<'3'\n",
-            "[options.extras_require]\nfoo = bar;baz\nboo = xxx;yyy\n",
-            "[options.extras_require]\nfoo =\n    bar\n    python_version<3\n",
-            "[options]\ninstall_requires =\n    bar;python_version<'3'",
-            "[options]\ninstall_requires = bar;baz\nboo = xxx;yyy",
-            "[options]\ninstall_requires =\n    bar;python_version<'3'\n",
-            "[options]\ninstall_requires = bar;baz\nboo = xxx;yyy\n",
-            "[options]\ninstall_requires =\n    bar\n    python_version<3\n",
-        ],
-    )
-    @pytest.mark.filterwarnings("error::setuptools.SetuptoolsDeprecationWarning")
-    def test_nowarn_accidental_env_marker_misconfig(self, config, tmpdir, recwarn):
-        fake_env(tmpdir, config)
-        num_warnings = len(recwarn)
-        with get_dist(tmpdir) as _:
-            pass
-        # The examples are valid, no warnings shown
-        assert len(recwarn) == num_warnings
-
-    def test_dash_preserved_extras_require(self, tmpdir):
-        fake_env(tmpdir, '[options.extras_require]\nfoo-a = foo\nfoo_b = test\n')
-
-        with get_dist(tmpdir) as dist:
-            assert dist.extras_require == {'foo-a': ['foo'], 'foo_b': ['test']}
-
-    def test_entry_points(self, tmpdir):
-        _, config = fake_env(
-            tmpdir,
-            '[options.entry_points]\n'
-            'group1 = point1 = pack.module:func, '
-            '.point2 = pack.module2:func_rest [rest]\n'
-            'group2 = point3 = pack.module:func2\n',
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.entry_points == {
-                'group1': [
-                    'point1 = pack.module:func',
-                    '.point2 = pack.module2:func_rest [rest]',
-                ],
-                'group2': ['point3 = pack.module:func2'],
-            }
-
-        expected = (
-            '[blogtool.parsers]\n'
-            '.rst = some.nested.module:SomeClass.some_classmethod[reST]\n'
-        )
-
-        tmpdir.join('entry_points').write(expected)
-
-        # From file.
-        config.write('[options]\nentry_points = file: entry_points\n')
-
-        with get_dist(tmpdir) as dist:
-            assert dist.entry_points == expected
-
-    def test_case_sensitive_entry_points(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[options.entry_points]\n'
-            'GROUP1 = point1 = pack.module:func, '
-            '.point2 = pack.module2:func_rest [rest]\n'
-            'group2 = point3 = pack.module:func2\n',
-        )
-
-        with get_dist(tmpdir) as dist:
-            assert dist.entry_points == {
-                'GROUP1': [
-                    'point1 = pack.module:func',
-                    '.point2 = pack.module2:func_rest [rest]',
-                ],
-                'group2': ['point3 = pack.module:func2'],
-            }
-
-    def test_data_files(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[options.data_files]\n'
-            'cfg =\n'
-            '      a/b.conf\n'
-            '      c/d.conf\n'
-            'data = e/f.dat, g/h.dat\n',
-        )
-
-        with get_dist(tmpdir) as dist:
-            expected = [
-                ('cfg', ['a/b.conf', 'c/d.conf']),
-                ('data', ['e/f.dat', 'g/h.dat']),
-            ]
-            assert sorted(dist.data_files) == sorted(expected)
-
-    def test_data_files_globby(self, tmpdir):
-        fake_env(
-            tmpdir,
-            '[options.data_files]\n'
-            'cfg =\n'
-            '      a/b.conf\n'
-            '      c/d.conf\n'
-            'data = *.dat\n'
-            'icons = \n'
-            '      *.ico\n'
-            'audio = \n'
-            '      *.wav\n'
-            '      sounds.db\n',
-        )
-
-        # Create dummy files for glob()'s sake:
-        tmpdir.join('a.dat').write('')
-        tmpdir.join('b.dat').write('')
-        tmpdir.join('c.dat').write('')
-        tmpdir.join('a.ico').write('')
-        tmpdir.join('b.ico').write('')
-        tmpdir.join('c.ico').write('')
-        tmpdir.join('beep.wav').write('')
-        tmpdir.join('boop.wav').write('')
-        tmpdir.join('sounds.db').write('')
-
-        with get_dist(tmpdir) as dist:
-            expected = [
-                ('cfg', ['a/b.conf', 'c/d.conf']),
-                ('data', ['a.dat', 'b.dat', 'c.dat']),
-                ('icons', ['a.ico', 'b.ico', 'c.ico']),
-                ('audio', ['beep.wav', 'boop.wav', 'sounds.db']),
-            ]
-            assert sorted(dist.data_files) == sorted(expected)
-
-    def test_python_requires_simple(self, tmpdir):
-        fake_env(
-            tmpdir,
-            DALS(
-                """
-            [options]
-            python_requires=>=2.7
-            """
-            ),
-        )
-        with get_dist(tmpdir) as dist:
-            dist.parse_config_files()
-
-    def test_python_requires_compound(self, tmpdir):
-        fake_env(
-            tmpdir,
-            DALS(
-                """
-            [options]
-            python_requires=>=2.7,!=3.0.*
-            """
-            ),
-        )
-        with get_dist(tmpdir) as dist:
-            dist.parse_config_files()
-
-    def test_python_requires_invalid(self, tmpdir):
-        fake_env(
-            tmpdir,
-            DALS(
-                """
-            [options]
-            python_requires=invalid
-            """
-            ),
-        )
-        with pytest.raises(Exception):
-            with get_dist(tmpdir) as dist:
-                dist.parse_config_files()
-
-    def test_cmdclass(self, tmpdir):
-        module_path = Path(tmpdir, "src/custom_build.py")  # auto discovery for src
-        module_path.parent.mkdir(parents=True, exist_ok=True)
-        module_path.write_text(
-            "from distutils.core import Command\nclass CustomCmd(Command): pass\n",
-            encoding="utf-8",
-        )
-
-        setup_cfg = """
-            [options]
-            cmdclass =
-                customcmd = custom_build.CustomCmd
-        """
-        fake_env(tmpdir, inspect.cleandoc(setup_cfg))
-
-        with get_dist(tmpdir) as dist:
-            cmdclass = dist.cmdclass['customcmd']
-            assert cmdclass.__name__ == "CustomCmd"
-            assert cmdclass.__module__ == "custom_build"
-            assert module_path.samefile(inspect.getfile(cmdclass))
-
-    def test_requirements_file(self, tmpdir):
-        fake_env(
-            tmpdir,
-            DALS(
-                """
-            [options]
-            install_requires = file:requirements.txt
-            [options.extras_require]
-            colors = file:requirements-extra.txt
-            """
-            ),
-        )
-
-        tmpdir.join('requirements.txt').write('\ndocutils>=0.3\n\n')
-        tmpdir.join('requirements-extra.txt').write('colorama')
-
-        with get_dist(tmpdir) as dist:
-            assert dist.install_requires == ['docutils>=0.3']
-            assert dist.extras_require == {'colors': ['colorama']}
-
-
-saved_dist_init = _Distribution.__init__
-
-
-class TestExternalSetters:
-    # During creation of the setuptools Distribution() object, we call
-    # the init of the parent distutils Distribution object via
-    # _Distribution.__init__ ().
-    #
-    # It's possible distutils calls out to various keyword
-    # implementations (i.e. distutils.setup_keywords entry points)
-    # that may set a range of variables.
-    #
-    # This wraps distutil's Distribution.__init__ and simulates
-    # pbr or something else setting these values.
-    def _fake_distribution_init(self, dist, attrs):
-        saved_dist_init(dist, attrs)
-        # see self._DISTUTILS_UNSUPPORTED_METADATA
-        dist.metadata.long_description_content_type = 'text/something'
-        # Test overwrite setup() args
-        dist.metadata.project_urls = {
-            'Link One': 'https://example.com/one/',
-            'Link Two': 'https://example.com/two/',
-        }
-
-    @patch.object(_Distribution, '__init__', autospec=True)
-    def test_external_setters(self, mock_parent_init, tmpdir):
-        mock_parent_init.side_effect = self._fake_distribution_init
-
-        dist = Distribution(attrs={'project_urls': {'will_be': 'ignored'}})
-
-        assert dist.metadata.long_description_content_type == 'text/something'
-        assert dist.metadata.project_urls == {
-            'Link One': 'https://example.com/one/',
-            'Link Two': 'https://example.com/two/',
-        }
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/contexts.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/contexts.py
deleted file mode 100644
index 97cceea..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/contexts.py
+++ /dev/null
@@ -1,145 +0,0 @@
-import contextlib
-import io
-import os
-import shutil
-import site
-import sys
-import tempfile
-
-from filelock import FileLock
-
-
-@contextlib.contextmanager
-def tempdir(cd=lambda dir: None, **kwargs):
-    temp_dir = tempfile.mkdtemp(**kwargs)
-    orig_dir = os.getcwd()
-    try:
-        cd(temp_dir)
-        yield temp_dir
-    finally:
-        cd(orig_dir)
-        shutil.rmtree(temp_dir)
-
-
-@contextlib.contextmanager
-def environment(**replacements):
-    """
-    In a context, patch the environment with replacements. Pass None values
-    to clear the values.
-    """
-    saved = dict((key, os.environ[key]) for key in replacements if key in os.environ)
-
-    # remove values that are null
-    remove = (key for (key, value) in replacements.items() if value is None)
-    for key in list(remove):
-        os.environ.pop(key, None)
-        replacements.pop(key)
-
-    os.environ.update(replacements)
-
-    try:
-        yield saved
-    finally:
-        for key in replacements:
-            os.environ.pop(key, None)
-        os.environ.update(saved)
-
-
-@contextlib.contextmanager
-def quiet():
-    """
-    Redirect stdout/stderr to StringIO objects to prevent console output from
-    distutils commands.
-    """
-
-    old_stdout = sys.stdout
-    old_stderr = sys.stderr
-    new_stdout = sys.stdout = io.StringIO()
-    new_stderr = sys.stderr = io.StringIO()
-    try:
-        yield new_stdout, new_stderr
-    finally:
-        new_stdout.seek(0)
-        new_stderr.seek(0)
-        sys.stdout = old_stdout
-        sys.stderr = old_stderr
-
-
-@contextlib.contextmanager
-def save_user_site_setting():
-    saved = site.ENABLE_USER_SITE
-    try:
-        yield saved
-    finally:
-        site.ENABLE_USER_SITE = saved
-
-
-@contextlib.contextmanager
-def save_pkg_resources_state():
-    import pkg_resources
-
-    pr_state = pkg_resources.__getstate__()
-    # also save sys.path
-    sys_path = sys.path[:]
-    try:
-        yield pr_state, sys_path
-    finally:
-        sys.path[:] = sys_path
-        pkg_resources.__setstate__(pr_state)
-
-
-@contextlib.contextmanager
-def suppress_exceptions(*excs):
-    try:
-        yield
-    except excs:
-        pass
-
-
-def multiproc(request):
-    """
-    Return True if running under xdist and multiple
-    workers are used.
-    """
-    try:
-        worker_id = request.getfixturevalue('worker_id')
-    except Exception:
-        return False
-    return worker_id != 'master'
-
-
-@contextlib.contextmanager
-def session_locked_tmp_dir(request, tmp_path_factory, name):
-    """Uses a file lock to guarantee only one worker can access a temp dir"""
-    # get the temp directory shared by all workers
-    base = tmp_path_factory.getbasetemp()
-    shared_dir = base.parent if multiproc(request) else base
-
-    locked_dir = shared_dir / name
-    with FileLock(locked_dir.with_suffix(".lock")):
-        # ^-- prevent multiple workers to access the directory at once
-        locked_dir.mkdir(exist_ok=True, parents=True)
-        yield locked_dir
-
-
-@contextlib.contextmanager
-def save_paths():
-    """Make sure ``sys.path``, ``sys.meta_path`` and ``sys.path_hooks`` are preserved"""
-    prev = sys.path[:], sys.meta_path[:], sys.path_hooks[:]
-
-    try:
-        yield
-    finally:
-        sys.path, sys.meta_path, sys.path_hooks = prev
-
-
-@contextlib.contextmanager
-def save_sys_modules():
-    """Make sure initial ``sys.modules`` is preserved"""
-    prev_modules = sys.modules
-
-    try:
-        sys.modules = sys.modules.copy()
-        yield
-    finally:
-        sys.modules = prev_modules
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/environment.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/environment.py
deleted file mode 100644
index ed5499e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/environment.py
+++ /dev/null
@@ -1,95 +0,0 @@
-import os
-import subprocess
-import sys
-import unicodedata
-from subprocess import PIPE as _PIPE, Popen as _Popen
-
-import jaraco.envs
-
-
-class VirtualEnv(jaraco.envs.VirtualEnv):
-    name = '.env'
-    # Some version of PyPy will import distutils on startup, implicitly
-    # importing setuptools, and thus leading to BackendInvalid errors
-    # when upgrading Setuptools. Bypass this behavior by avoiding the
-    # early availability and need to upgrade.
-    create_opts = ['--no-setuptools']
-
-    def run(self, cmd, *args, **kwargs):
-        cmd = [self.exe(cmd[0])] + cmd[1:]
-        kwargs = {"cwd": self.root, "encoding": "utf-8", **kwargs}  # Allow overriding
-        # In some environments (eg. downstream distro packaging), where:
-        # - tox isn't used to run tests and
-        # - PYTHONPATH is set to point to a specific setuptools codebase and
-        # - no custom env is explicitly set by a test
-        # PYTHONPATH will leak into the spawned processes.
-        # In that case tests look for module in the wrong place (on PYTHONPATH).
-        # Unless the test sets its own special env, pass a copy of the existing
-        # environment with removed PYTHONPATH to the subprocesses.
-        if "env" not in kwargs:
-            env = dict(os.environ)
-            if "PYTHONPATH" in env:
-                del env["PYTHONPATH"]
-            kwargs["env"] = env
-        return subprocess.check_output(cmd, *args, **kwargs)
-
-
-def _which_dirs(cmd):
-    result = set()
-    for path in os.environ.get('PATH', '').split(os.pathsep):
-        filename = os.path.join(path, cmd)
-        if os.access(filename, os.X_OK):
-            result.add(path)
-    return result
-
-
-def run_setup_py(cmd, pypath=None, path=None, data_stream=0, env=None):
-    """
-    Execution command for tests, separate from those used by the
-    code directly to prevent accidental behavior issues
-    """
-    if env is None:
-        env = dict()
-        for envname in os.environ:
-            env[envname] = os.environ[envname]
-
-    # override the python path if needed
-    if pypath is not None:
-        env["PYTHONPATH"] = pypath
-
-    # override the execution path if needed
-    if path is not None:
-        env["PATH"] = path
-    if not env.get("PATH", ""):
-        env["PATH"] = _which_dirs("tar").union(_which_dirs("gzip"))
-        env["PATH"] = os.pathsep.join(env["PATH"])
-
-    cmd = [sys.executable, "setup.py"] + list(cmd)
-
-    # https://bugs.python.org/issue8557
-    shell = sys.platform == 'win32'
-
-    try:
-        proc = _Popen(
-            cmd,
-            stdout=_PIPE,
-            stderr=_PIPE,
-            shell=shell,
-            env=env,
-            encoding="utf-8",
-        )
-
-        if isinstance(data_stream, tuple):
-            data_stream = slice(*data_stream)
-        data = proc.communicate()[data_stream]
-    except OSError:
-        return 1, ''
-
-    # decode the console string if needed
-    if hasattr(data, "decode"):
-        # use the default encoding
-        data = data.decode()
-        data = unicodedata.normalize('NFC', data)
-
-    # communicate calls wait()
-    return proc.returncode, data
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/fixtures.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/fixtures.py
deleted file mode 100644
index a547298..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/fixtures.py
+++ /dev/null
@@ -1,157 +0,0 @@
-import contextlib
-import os
-import subprocess
-import sys
-from pathlib import Path
-
-import path
-import pytest
-
-from . import contexts, environment
-
-
-@pytest.fixture
-def user_override(monkeypatch):
-    """
-    Override site.USER_BASE and site.USER_SITE with temporary directories in
-    a context.
-    """
-    with contexts.tempdir() as user_base:
-        monkeypatch.setattr('site.USER_BASE', user_base)
-        with contexts.tempdir() as user_site:
-            monkeypatch.setattr('site.USER_SITE', user_site)
-            with contexts.save_user_site_setting():
-                yield
-
-
-@pytest.fixture
-def tmpdir_cwd(tmpdir):
-    with tmpdir.as_cwd() as orig:
-        yield orig
-
-
-@pytest.fixture(autouse=True, scope="session")
-def workaround_xdist_376(request):
-    """
-    Workaround pytest-dev/pytest-xdist#376
-
-    ``pytest-xdist`` tends to inject '' into ``sys.path``,
-    which may break certain isolation expectations.
-    Remove the entry so the import
-    machinery behaves the same irrespective of xdist.
-    """
-    if not request.config.pluginmanager.has_plugin('xdist'):
-        return
-
-    with contextlib.suppress(ValueError):
-        sys.path.remove('')
-
-
-@pytest.fixture
-def sample_project(tmp_path):
-    """
-    Clone the 'sampleproject' and return a path to it.
-    """
-    cmd = ['git', 'clone', 'https://github.com/pypa/sampleproject']
-    try:
-        subprocess.check_call(cmd, cwd=str(tmp_path))
-    except Exception:
-        pytest.skip("Unable to clone sampleproject")
-    return tmp_path / 'sampleproject'
-
-
-# sdist and wheel artifacts should be stable across a round of tests
-# so we can build them once per session and use the files as "readonly"
-
-# In the case of setuptools, building the wheel without sdist may cause
-# it to contain the `build` directory, and therefore create situations with
-# `setuptools/build/lib/build/lib/...`. To avoid that, build both artifacts at once.
-
-
-def _build_distributions(tmp_path_factory, request):
-    with contexts.session_locked_tmp_dir(
-        request, tmp_path_factory, "dist_build"
-    ) as tmp:  # pragma: no cover
-        sdist = next(tmp.glob("*.tar.gz"), None)
-        wheel = next(tmp.glob("*.whl"), None)
-        if sdist and wheel:
-            return (sdist, wheel)
-
-        # Sanity check: should not create recursive setuptools/build/lib/build/lib/...
-        assert not Path(request.config.rootdir, "build/lib/build").exists()
-
-        subprocess.check_output([
-            sys.executable,
-            "-m",
-            "build",
-            "--outdir",
-            str(tmp),
-            str(request.config.rootdir),
-        ])
-
-        # Sanity check: should not create recursive setuptools/build/lib/build/lib/...
-        assert not Path(request.config.rootdir, "build/lib/build").exists()
-
-        return next(tmp.glob("*.tar.gz")), next(tmp.glob("*.whl"))
-
-
-@pytest.fixture(scope="session")
-def setuptools_sdist(tmp_path_factory, request):
-    prebuilt = os.getenv("PRE_BUILT_SETUPTOOLS_SDIST")
-    if prebuilt and os.path.exists(prebuilt):  # pragma: no cover
-        return Path(prebuilt).resolve()
-
-    sdist, _ = _build_distributions(tmp_path_factory, request)
-    return sdist
-
-
-@pytest.fixture(scope="session")
-def setuptools_wheel(tmp_path_factory, request):
-    prebuilt = os.getenv("PRE_BUILT_SETUPTOOLS_WHEEL")
-    if prebuilt and os.path.exists(prebuilt):  # pragma: no cover
-        return Path(prebuilt).resolve()
-
-    _, wheel = _build_distributions(tmp_path_factory, request)
-    return wheel
-
-
-@pytest.fixture
-def venv(tmp_path, setuptools_wheel):
-    """Virtual env with the version of setuptools under test installed"""
-    env = environment.VirtualEnv()
-    env.root = path.Path(tmp_path / 'venv')
-    env.create_opts = ['--no-setuptools', '--wheel=bundle']
-    # TODO: Use `--no-wheel` when setuptools implements its own bdist_wheel
-    env.req = str(setuptools_wheel)
-    # In some environments (eg. downstream distro packaging),
-    # where tox isn't used to run tests and PYTHONPATH is set to point to
-    # a specific setuptools codebase, PYTHONPATH will leak into the spawned
-    # processes.
-    # env.create() should install the just created setuptools
-    # wheel, but it doesn't if it finds another existing matching setuptools
-    # installation present on PYTHONPATH:
-    # `setuptools is already installed with the same version as the provided
-    # wheel. Use --force-reinstall to force an installation of the wheel.`
-    # This prevents leaking PYTHONPATH to the created environment.
-    with contexts.environment(PYTHONPATH=None):
-        return env.create()
-
-
-@pytest.fixture
-def venv_without_setuptools(tmp_path):
-    """Virtual env without any version of setuptools installed"""
-    env = environment.VirtualEnv()
-    env.root = path.Path(tmp_path / 'venv_without_setuptools')
-    env.create_opts = ['--no-setuptools', '--no-wheel']
-    env.ensure_env()
-    return env
-
-
-@pytest.fixture
-def bare_venv(tmp_path):
-    """Virtual env without any common packages installed"""
-    env = environment.VirtualEnv()
-    env.root = path.Path(tmp_path / 'bare_venv')
-    env.create_opts = ['--no-setuptools', '--no-pip', '--no-wheel', '--no-seed']
-    env.ensure_env()
-    return env
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/indexes/test_links_priority/external.html b/llmlab/lib/python3.12/site-packages/setuptools/tests/indexes/test_links_priority/external.html
deleted file mode 100644
index 92e4702..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/indexes/test_links_priority/external.html
+++ /dev/null
@@ -1,3 +0,0 @@
-
-bad old link
-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/indexes/test_links_priority/simple/foobar/index.html b/llmlab/lib/python3.12/site-packages/setuptools/tests/indexes/test_links_priority/simple/foobar/index.html
deleted file mode 100644
index fefb028..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/indexes/test_links_priority/simple/foobar/index.html
+++ /dev/null
@@ -1,4 +0,0 @@
-
-foobar-0.1.tar.gz

-external homepage

-
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__init__.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 644564e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/helpers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/helpers.cpython-312.pyc
deleted file mode 100644
index b8e98b0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/helpers.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/test_pip_install_sdist.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/test_pip_install_sdist.cpython-312.pyc
deleted file mode 100644
index f15ad4c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/__pycache__/test_pip_install_sdist.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/helpers.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/helpers.py
deleted file mode 100644
index 77b196e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/helpers.py
+++ /dev/null
@@ -1,77 +0,0 @@
-"""Reusable functions and classes for different types of integration tests.
-
-For example ``Archive`` can be used to check the contents of distribution built
-with setuptools, and ``run`` will always try to be as verbose as possible to
-facilitate debugging.
-"""
-
-import os
-import subprocess
-import tarfile
-from pathlib import Path
-from zipfile import ZipFile
-
-
-def run(cmd, env=None):
-    r = subprocess.run(
-        cmd,
-        capture_output=True,
-        text=True,
-        encoding="utf-8",
-        env={**os.environ, **(env or {})},
-        # ^-- allow overwriting instead of discarding the current env
-    )
-
-    out = r.stdout + "\n" + r.stderr
-    # pytest omits stdout/err by default, if the test fails they help debugging
-    print("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
-    print(f"Command: {cmd}\nreturn code: {r.returncode}\n\n{out}")
-
-    if r.returncode == 0:
-        return out
-    raise subprocess.CalledProcessError(r.returncode, cmd, r.stdout, r.stderr)
-
-
-class Archive:
-    """Compatibility layer for ZipFile/Info and TarFile/Info"""
-
-    def __init__(self, filename):
-        self._filename = filename
-        if filename.endswith("tar.gz"):
-            self._obj = tarfile.open(filename, "r:gz")
-        elif filename.endswith("zip"):
-            self._obj = ZipFile(filename)
-        else:
-            raise ValueError(f"{filename} doesn't seem to be a zip or tar.gz")
-
-    def __iter__(self):
-        if hasattr(self._obj, "infolist"):
-            return iter(self._obj.infolist())
-        return iter(self._obj)
-
-    def get_name(self, zip_or_tar_info):
-        if hasattr(zip_or_tar_info, "filename"):
-            return zip_or_tar_info.filename
-        return zip_or_tar_info.name
-
-    def get_content(self, zip_or_tar_info):
-        if hasattr(self._obj, "extractfile"):
-            content = self._obj.extractfile(zip_or_tar_info)
-            if content is None:
-                msg = f"Invalid {zip_or_tar_info.name} in {self._filename}"
-                raise ValueError(msg)
-            return str(content.read(), "utf-8")
-        return str(self._obj.read(zip_or_tar_info), "utf-8")
-
-
-def get_sdist_members(sdist_path):
-    with tarfile.open(sdist_path, "r:gz") as tar:
-        files = [Path(f) for f in tar.getnames()]
-    # remove root folder
-    relative_files = ("/".join(f.parts[1:]) for f in files)
-    return {f for f in relative_files if f}
-
-
-def get_wheel_members(wheel_path):
-    with ZipFile(wheel_path) as zipfile:
-        return set(zipfile.namelist())
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/test_pip_install_sdist.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/test_pip_install_sdist.py
deleted file mode 100644
index 4e84f21..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/integration/test_pip_install_sdist.py
+++ /dev/null
@@ -1,223 +0,0 @@
-# https://github.com/python/mypy/issues/16936
-# mypy: disable-error-code="has-type"
-"""Integration tests for setuptools that focus on building packages via pip.
-
-The idea behind these tests is not to exhaustively check all the possible
-combinations of packages, operating systems, supporting libraries, etc, but
-rather check a limited number of popular packages and how they interact with
-the exposed public API. This way if any change in API is introduced, we hope to
-identify backward compatibility problems before publishing a release.
-
-The number of tested packages is purposefully kept small, to minimise duration
-and the associated maintenance cost (changes in the way these packages define
-their build process may require changes in the tests).
-"""
-
-import json
-import os
-import shutil
-import sys
-from enum import Enum
-from glob import glob
-from hashlib import md5
-from urllib.request import urlopen
-
-import pytest
-from packaging.requirements import Requirement
-
-from .helpers import Archive, run
-
-pytestmark = pytest.mark.integration
-
-
-(LATEST,) = Enum("v", "LATEST")  # type: ignore[misc] # https://github.com/python/mypy/issues/16936
-"""Default version to be checked"""
-# There are positive and negative aspects of checking the latest version of the
-# packages.
-# The main positive aspect is that the latest version might have already
-# removed the use of APIs deprecated in previous releases of setuptools.
-
-
-# Packages to be tested:
-# (Please notice the test environment cannot support EVERY library required for
-# compiling binary extensions. In Ubuntu/Debian nomenclature, we only assume
-# that `build-essential`, `gfortran` and `libopenblas-dev` are installed,
-# due to their relevance to the numerical/scientific programming ecosystem)
-EXAMPLES = [
-    ("pip", LATEST),  # just in case...
-    ("pytest", LATEST),  # uses setuptools_scm
-    ("mypy", LATEST),  # custom build_py + ext_modules
-    # --- Popular packages: https://hugovk.github.io/top-pypi-packages/ ---
-    ("botocore", LATEST),
-    ("kiwisolver", LATEST),  # build_ext
-    ("brotli", LATEST),  # not in the list but used by urllib3
-    ("pyyaml", LATEST),  # cython + custom build_ext + custom distclass
-    ("charset-normalizer", LATEST),  # uses mypyc, used by aiohttp
-    ("protobuf", LATEST),
-    # ("requests", LATEST),  # XXX: https://github.com/psf/requests/pull/6920
-    ("celery", LATEST),
-    # When adding packages to this list, make sure they expose a `__version__`
-    # attribute, or modify the tests below
-]
-
-
-# Some packages have "optional" dependencies that modify their build behaviour
-# and are not listed in pyproject.toml, others still use `setup_requires`
-EXTRA_BUILD_DEPS = {
-    "pyyaml": ("Cython<3.0",),  # constraint to avoid errors
-    "charset-normalizer": ("mypy>=1.4.1",),  # no pyproject.toml available
-}
-
-EXTRA_ENV_VARS = {
-    "pyyaml": {"PYYAML_FORCE_CYTHON": "1"},
-    "charset-normalizer": {"CHARSET_NORMALIZER_USE_MYPYC": "1"},
-}
-
-IMPORT_NAME = {
-    "pyyaml": "yaml",
-    "protobuf": "google.protobuf",
-}
-
-
-VIRTUALENV = (sys.executable, "-m", "virtualenv")
-
-
-# By default, pip will try to build packages in isolation (PEP 517), which
-# means it will download the previous stable version of setuptools.
-# `pip` flags can avoid that (the version of setuptools under test
-# should be the one to be used)
-INSTALL_OPTIONS = (
-    "--ignore-installed",
-    "--no-build-isolation",
-    # Omit "--no-binary :all:" the sdist is supplied directly.
-    # Allows dependencies as wheels.
-)
-# The downside of `--no-build-isolation` is that pip will not download build
-# dependencies. The test script will have to also handle that.
-
-
-@pytest.fixture
-def venv_python(tmp_path):
-    run([*VIRTUALENV, str(tmp_path / ".venv")])
-    possible_path = (str(p.parent) for p in tmp_path.glob(".venv/*/python*"))
-    return shutil.which("python", path=os.pathsep.join(possible_path))
-
-
-@pytest.fixture(autouse=True)
-def _prepare(tmp_path, venv_python, monkeypatch):
-    download_path = os.getenv("DOWNLOAD_PATH", str(tmp_path))
-    os.makedirs(download_path, exist_ok=True)
-
-    # Environment vars used for building some of the packages
-    monkeypatch.setenv("USE_MYPYC", "1")
-
-    yield
-
-    # Let's provide the maximum amount of information possible in the case
-    # it is necessary to debug the tests directly from the CI logs.
-    print("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
-    print("Temporary directory:")
-    map(print, tmp_path.glob("*"))
-    print("Virtual environment:")
-    run([venv_python, "-m", "pip", "freeze"])
-
-
-@pytest.mark.parametrize(("package", "version"), EXAMPLES)
-@pytest.mark.uses_network
-def test_install_sdist(package, version, tmp_path, venv_python, setuptools_wheel):
-    venv_pip = (venv_python, "-m", "pip")
-    sdist = retrieve_sdist(package, version, tmp_path)
-    deps = build_deps(package, sdist)
-    if deps:
-        print("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
-        print("Dependencies:", deps)
-        run([*venv_pip, "install", *deps])
-
-    # Use a virtualenv to simulate PEP 517 isolation
-    # but install fresh setuptools wheel to ensure the version under development
-    env = EXTRA_ENV_VARS.get(package, {})
-    run([*venv_pip, "install", "--force-reinstall", setuptools_wheel])
-    run([*venv_pip, "install", *INSTALL_OPTIONS, sdist], env)
-
-    # Execute a simple script to make sure the package was installed correctly
-    pkg = IMPORT_NAME.get(package, package).replace("-", "_")
-    script = f"import {pkg}; print(getattr({pkg}, '__version__', 0))"
-    run([venv_python, "-c", script])
-
-
-# ---- Helper Functions ----
-
-
-def retrieve_sdist(package, version, tmp_path):
-    """Either use cached sdist file or download it from PyPI"""
-    # `pip download` cannot be used due to
-    # https://github.com/pypa/pip/issues/1884
-    # https://discuss.python.org/t/pep-625-file-name-of-a-source-distribution/4686
-    # We have to find the correct distribution file and download it
-    download_path = os.getenv("DOWNLOAD_PATH", str(tmp_path))
-    dist = retrieve_pypi_sdist_metadata(package, version)
-
-    # Remove old files to prevent cache to grow indefinitely
-    for file in glob(os.path.join(download_path, f"{package}*")):
-        if dist["filename"] != file:
-            os.unlink(file)
-
-    dist_file = os.path.join(download_path, dist["filename"])
-    if not os.path.exists(dist_file):
-        download(dist["url"], dist_file, dist["md5_digest"])
-    return dist_file
-
-
-def retrieve_pypi_sdist_metadata(package, version):
-    # https://warehouse.pypa.io/api-reference/json.html
-    id_ = package if version is LATEST else f"{package}/{version}"
-    with urlopen(f"https://pypi.org/pypi/{id_}/json") as f:
-        metadata = json.load(f)
-
-    if metadata["info"]["yanked"]:
-        raise ValueError(f"Release for {package} {version} was yanked")
-
-    version = metadata["info"]["version"]
-    release = metadata["releases"][version] if version is LATEST else metadata["urls"]
-    (sdist,) = filter(lambda d: d["packagetype"] == "sdist", release)
-    return sdist
-
-
-def download(url, dest, md5_digest):
-    with urlopen(url) as f:
-        data = f.read()
-
-    assert md5(data).hexdigest() == md5_digest
-
-    with open(dest, "wb") as f:
-        f.write(data)
-
-    assert os.path.exists(dest)
-
-
-def build_deps(package, sdist_file):
-    """Find out what are the build dependencies for a package.
-
-    "Manually" install them, since pip will not install build
-    deps with `--no-build-isolation`.
-    """
-    # delay importing, since pytest discovery phase may hit this file from a
-    # testenv without tomli
-    from setuptools.compat.py310 import tomllib
-
-    archive = Archive(sdist_file)
-    info = tomllib.loads(_read_pyproject(archive))
-    deps = info.get("build-system", {}).get("requires", [])
-    deps += EXTRA_BUILD_DEPS.get(package, [])
-    # Remove setuptools from requirements (and deduplicate)
-    requirements = {Requirement(d).name: d for d in deps}
-    return [v for k, v in requirements.items() if k != "setuptools"]
-
-
-def _read_pyproject(archive):
-    contents = (
-        archive.get_content(member)
-        for member in archive
-        if os.path.basename(archive.get_name(member)) == "pyproject.toml"
-    )
-    return next(contents, "")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/mod_with_constant.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/mod_with_constant.py
deleted file mode 100644
index ef755dd..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/mod_with_constant.py
+++ /dev/null
@@ -1 +0,0 @@
-value = 'three, sir!'
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/namespaces.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/namespaces.py
deleted file mode 100644
index 248db98..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/namespaces.py
+++ /dev/null
@@ -1,90 +0,0 @@
-import ast
-import json
-import textwrap
-from pathlib import Path
-
-
-def iter_namespace_pkgs(namespace):
-    parts = namespace.split(".")
-    for i in range(len(parts)):
-        yield ".".join(parts[: i + 1])
-
-
-def build_namespace_package(tmpdir, name, version="1.0", impl="pkg_resources"):
-    src_dir = tmpdir / name
-    src_dir.mkdir()
-    setup_py = src_dir / 'setup.py'
-    namespace, _, rest = name.rpartition('.')
-    namespaces = list(iter_namespace_pkgs(namespace))
-    setup_args = {
-        "name": name,
-        "version": version,
-        "packages": namespaces,
-    }
-
-    if impl == "pkg_resources":
-        tmpl = '__import__("pkg_resources").declare_namespace(__name__)'
-        setup_args["namespace_packages"] = namespaces
-    elif impl == "pkgutil":
-        tmpl = '__path__ = __import__("pkgutil").extend_path(__path__, __name__)'
-    else:
-        raise ValueError(f"Cannot recognise {impl=} when creating namespaces")
-
-    args = json.dumps(setup_args, indent=4)
-    assert ast.literal_eval(args)  # ensure it is valid Python
-
-    script = textwrap.dedent(
-        """\
-        import setuptools
-        args = {args}
-        setuptools.setup(**args)
-        """
-    ).format(args=args)
-    setup_py.write_text(script, encoding='utf-8')
-
-    ns_pkg_dir = Path(src_dir, namespace.replace(".", "/"))
-    ns_pkg_dir.mkdir(parents=True)
-
-    for ns in namespaces:
-        pkg_init = src_dir / ns.replace(".", "/") / '__init__.py'
-        pkg_init.write_text(tmpl, encoding='utf-8')
-
-    pkg_mod = ns_pkg_dir / (rest + '.py')
-    some_functionality = 'name = {rest!r}'.format(**locals())
-    pkg_mod.write_text(some_functionality, encoding='utf-8')
-    return src_dir
-
-
-def build_pep420_namespace_package(tmpdir, name):
-    src_dir = tmpdir / name
-    src_dir.mkdir()
-    pyproject = src_dir / "pyproject.toml"
-    namespace, _, rest = name.rpartition(".")
-    script = f"""\
-        [build-system]
-        requires = ["setuptools"]
-        build-backend = "setuptools.build_meta"
-
-        [project]
-        name = "{name}"
-        version = "3.14159"
-        """
-    pyproject.write_text(textwrap.dedent(script), encoding='utf-8')
-    ns_pkg_dir = Path(src_dir, namespace.replace(".", "/"))
-    ns_pkg_dir.mkdir(parents=True)
-    pkg_mod = ns_pkg_dir / (rest + ".py")
-    some_functionality = f"name = {rest!r}"
-    pkg_mod.write_text(some_functionality, encoding='utf-8')
-    return src_dir
-
-
-def make_site_dir(target):
-    """
-    Add a sitecustomize.py module in target to cause
-    target to be added to site dirs such that .pth files
-    are processed there.
-    """
-    sc = target / 'sitecustomize.py'
-    target_str = str(target)
-    tmpl = '__import__("site").addsitedir({target_str!r})'
-    sc.write_text(tmpl.format(**locals()), encoding='utf-8')
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/script-with-bom.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/script-with-bom.py
deleted file mode 100644
index c074d26..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/script-with-bom.py
+++ /dev/null
@@ -1 +0,0 @@
-result = 'passed'
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/server.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/server.py
deleted file mode 100644
index 623a49a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/server.py
+++ /dev/null
@@ -1,86 +0,0 @@
-"""Basic http server for tests to simulate PyPI or custom indexes"""
-
-import http.server
-import os
-import threading
-import time
-import urllib.parse
-import urllib.request
-
-
-class IndexServer(http.server.HTTPServer):
-    """Basic single-threaded http server simulating a package index
-
-    You can use this server in unittest like this::
-        s = IndexServer()
-        s.start()
-        index_url = s.base_url() + 'mytestindex'
-        # do some test requests to the index
-        # The index files should be located in setuptools/tests/indexes
-        s.stop()
-    """
-
-    def __init__(
-        self,
-        server_address=('', 0),
-        RequestHandlerClass=http.server.SimpleHTTPRequestHandler,
-    ):
-        http.server.HTTPServer.__init__(self, server_address, RequestHandlerClass)
-        self._run = True
-
-    def start(self):
-        self.thread = threading.Thread(target=self.serve_forever)
-        self.thread.start()
-
-    def stop(self):
-        "Stop the server"
-
-        # Let the server finish the last request and wait for a new one.
-        time.sleep(0.1)
-
-        self.shutdown()
-        self.thread.join()
-        self.socket.close()
-
-    def base_url(self):
-        port = self.server_port
-        return f'http://127.0.0.1:{port}/setuptools/tests/indexes/'
-
-
-class RequestRecorder(http.server.BaseHTTPRequestHandler):
-    def do_GET(self):
-        requests = vars(self.server).setdefault('requests', [])
-        requests.append(self)
-        self.send_response(200, 'OK')
-
-
-class MockServer(http.server.HTTPServer, threading.Thread):
-    """
-    A simple HTTP Server that records the requests made to it.
-    """
-
-    def __init__(self, server_address=('', 0), RequestHandlerClass=RequestRecorder):
-        http.server.HTTPServer.__init__(self, server_address, RequestHandlerClass)
-        threading.Thread.__init__(self)
-        self.daemon = True
-        self.requests = []
-
-    def run(self):
-        self.serve_forever()
-
-    @property
-    def netloc(self):
-        return f'localhost:{self.server_port}'
-
-    @property
-    def url(self):
-        return f'http://{self.netloc}/'
-
-
-def path_to_url(path, authority=None):
-    """Convert a path to a file: URL."""
-    path = os.path.normpath(os.path.abspath(path))
-    base = 'file:'
-    if authority is not None:
-        base += '//' + authority
-    return urllib.parse.urljoin(base, urllib.request.pathname2url(path))
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_archive_util.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_archive_util.py
deleted file mode 100644
index e3efc62..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_archive_util.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import io
-import tarfile
-
-import pytest
-
-from setuptools import archive_util
-
-
-@pytest.fixture
-def tarfile_with_unicode(tmpdir):
-    """
-    Create a tarfile containing only a file whose name is
-    a zero byte file called testimäge.png.
-    """
-    tarobj = io.BytesIO()
-
-    with tarfile.open(fileobj=tarobj, mode="w:gz") as tgz:
-        data = b""
-
-        filename = "testimäge.png"
-
-        t = tarfile.TarInfo(filename)
-        t.size = len(data)
-
-        tgz.addfile(t, io.BytesIO(data))
-
-    target = tmpdir / 'unicode-pkg-1.0.tar.gz'
-    with open(str(target), mode='wb') as tf:
-        tf.write(tarobj.getvalue())
-    return str(target)
-
-
-@pytest.mark.xfail(reason="#710 and #712")
-def test_unicode_files(tarfile_with_unicode, tmpdir):
-    target = tmpdir / 'out'
-    archive_util.unpack_archive(tarfile_with_unicode, str(target))
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_deprecations.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_deprecations.py
deleted file mode 100644
index d9d67b0..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_deprecations.py
+++ /dev/null
@@ -1,28 +0,0 @@
-"""develop tests"""
-
-import sys
-from unittest import mock
-
-import pytest
-
-from setuptools import SetuptoolsDeprecationWarning
-from setuptools.dist import Distribution
-
-
-@pytest.mark.skipif(sys.platform == 'win32', reason='non-Windows only')
-@pytest.mark.xfail(reason="bdist_rpm is long deprecated, should we remove it? #1988")
-@mock.patch('distutils.command.bdist_rpm.bdist_rpm')
-def test_bdist_rpm_warning(distutils_cmd, tmpdir_cwd):
-    dist = Distribution(
-        dict(
-            script_name='setup.py',
-            script_args=['bdist_rpm'],
-            name='foo',
-            py_modules=['hi'],
-        )
-    )
-    dist.parse_command_line()
-    with pytest.warns(SetuptoolsDeprecationWarning):
-        dist.run_commands()
-
-    distutils_cmd.run.assert_called_once()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_egg.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_egg.py
deleted file mode 100644
index 036167d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_egg.py
+++ /dev/null
@@ -1,73 +0,0 @@
-"""develop tests"""
-
-import os
-import re
-import zipfile
-
-import pytest
-
-from setuptools.dist import Distribution
-
-from . import contexts
-
-SETUP_PY = """\
-from setuptools import setup
-
-setup(py_modules=['hi'])
-"""
-
-
-@pytest.fixture
-def setup_context(tmpdir):
-    with (tmpdir / 'setup.py').open('w') as f:
-        f.write(SETUP_PY)
-    with (tmpdir / 'hi.py').open('w') as f:
-        f.write('1\n')
-    with tmpdir.as_cwd():
-        yield tmpdir
-
-
-class Test:
-    @pytest.mark.usefixtures("user_override")
-    @pytest.mark.usefixtures("setup_context")
-    def test_bdist_egg(self):
-        dist = Distribution(
-            dict(
-                script_name='setup.py',
-                script_args=['bdist_egg'],
-                name='foo',
-                py_modules=['hi'],
-            )
-        )
-        os.makedirs(os.path.join('build', 'src'))
-        with contexts.quiet():
-            dist.parse_command_line()
-            dist.run_commands()
-
-        # let's see if we got our egg link at the right place
-        [content] = os.listdir('dist')
-        assert re.match(r'foo-0.0.0-py[23].\d+.egg$', content)
-
-    @pytest.mark.xfail(
-        os.environ.get('PYTHONDONTWRITEBYTECODE', False),
-        reason="Byte code disabled",
-    )
-    @pytest.mark.usefixtures("user_override")
-    @pytest.mark.usefixtures("setup_context")
-    def test_exclude_source_files(self):
-        dist = Distribution(
-            dict(
-                script_name='setup.py',
-                script_args=['bdist_egg', '--exclude-source-files'],
-                py_modules=['hi'],
-            )
-        )
-        with contexts.quiet():
-            dist.parse_command_line()
-            dist.run_commands()
-        [dist_name] = os.listdir('dist')
-        dist_filename = os.path.join('dist', dist_name)
-        zip = zipfile.ZipFile(dist_filename)
-        names = list(zi.filename for zi in zip.filelist)
-        assert 'hi.pyc' in names
-        assert 'hi.py' not in names
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_wheel.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_wheel.py
deleted file mode 100644
index 2ab4e9c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_bdist_wheel.py
+++ /dev/null
@@ -1,708 +0,0 @@
-from __future__ import annotations
-
-import builtins
-import importlib
-import os.path
-import platform
-import shutil
-import stat
-import struct
-import sys
-import sysconfig
-from contextlib import suppress
-from inspect import cleandoc
-from zipfile import ZipFile
-
-import jaraco.path
-import pytest
-from packaging import tags
-
-import setuptools
-from setuptools.command.bdist_wheel import bdist_wheel, get_abi_tag
-from setuptools.dist import Distribution
-from setuptools.warnings import SetuptoolsDeprecationWarning
-
-from distutils.core import run_setup
-
-DEFAULT_FILES = {
-    "dummy_dist-1.0.dist-info/top_level.txt",
-    "dummy_dist-1.0.dist-info/METADATA",
-    "dummy_dist-1.0.dist-info/WHEEL",
-    "dummy_dist-1.0.dist-info/RECORD",
-}
-DEFAULT_LICENSE_FILES = {
-    "LICENSE",
-    "LICENSE.txt",
-    "LICENCE",
-    "LICENCE.txt",
-    "COPYING",
-    "COPYING.md",
-    "NOTICE",
-    "NOTICE.rst",
-    "AUTHORS",
-    "AUTHORS.txt",
-}
-OTHER_IGNORED_FILES = {
-    "LICENSE~",
-    "AUTHORS~",
-}
-SETUPPY_EXAMPLE = """\
-from setuptools import setup
-
-setup(
-    name='dummy_dist',
-    version='1.0',
-)
-"""
-
-
-EXAMPLES = {
-    "dummy-dist": {
-        "setup.py": SETUPPY_EXAMPLE,
-        "licenses_dir": {"DUMMYFILE": ""},
-        **dict.fromkeys(DEFAULT_LICENSE_FILES | OTHER_IGNORED_FILES, ""),
-    },
-    "simple-dist": {
-        "setup.py": cleandoc(
-            """
-            from setuptools import setup
-
-            setup(
-                name="simple.dist",
-                version="0.1",
-                description="A testing distribution \N{SNOWMAN}",
-                extras_require={"voting": ["beaglevote"]},
-            )
-            """
-        ),
-        "simpledist": "",
-    },
-    "complex-dist": {
-        "setup.py": cleandoc(
-            """
-            from setuptools import setup
-
-            setup(
-                name="complex-dist",
-                version="0.1",
-                description="Another testing distribution \N{SNOWMAN}",
-                long_description="Another testing distribution \N{SNOWMAN}",
-                author="Illustrious Author",
-                author_email="illustrious@example.org",
-                url="http://example.org/exemplary",
-                packages=["complexdist"],
-                setup_requires=["setuptools"],
-                install_requires=["quux", "splort"],
-                extras_require={"simple": ["simple.dist"]},
-                entry_points={
-                    "console_scripts": [
-                        "complex-dist=complexdist:main",
-                        "complex-dist2=complexdist:main",
-                    ],
-                },
-            )
-            """
-        ),
-        "complexdist": {"__init__.py": "def main(): return"},
-    },
-    "headers-dist": {
-        "setup.py": cleandoc(
-            """
-            from setuptools import setup
-
-            setup(
-                name="headers.dist",
-                version="0.1",
-                description="A distribution with headers",
-                headers=["header.h"],
-            )
-            """
-        ),
-        "headersdist.py": "",
-        "header.h": "",
-    },
-    "commasinfilenames-dist": {
-        "setup.py": cleandoc(
-            """
-            from setuptools import setup
-
-            setup(
-                name="testrepo",
-                version="0.1",
-                packages=["mypackage"],
-                description="A test package with commas in file names",
-                include_package_data=True,
-                package_data={"mypackage.data": ["*"]},
-            )
-            """
-        ),
-        "mypackage": {
-            "__init__.py": "",
-            "data": {"__init__.py": "", "1,2,3.txt": ""},
-        },
-        "testrepo-0.1.0": {
-            "mypackage": {"__init__.py": ""},
-        },
-    },
-    "unicode-dist": {
-        "setup.py": cleandoc(
-            """
-            from setuptools import setup
-
-            setup(
-                name="unicode.dist",
-                version="0.1",
-                description="A testing distribution \N{SNOWMAN}",
-                packages=["unicodedist"],
-                zip_safe=True,
-            )
-            """
-        ),
-        "unicodedist": {"__init__.py": "", "åäö_日本語.py": ""},
-    },
-    "utf8-metadata-dist": {
-        "setup.cfg": cleandoc(
-            """
-            [metadata]
-            name = utf8-metadata-dist
-            version = 42
-            author_email = "John X. Ãørçeč" , Γαμα קּ 東 
-            long_description = file: README.rst
-            """
-        ),
-        "README.rst": "UTF-8 描述 説明",
-    },
-    "licenses-dist": {
-        "setup.cfg": cleandoc(
-            """
-            [metadata]
-            name = licenses-dist
-            version = 1.0
-            license_files = **/LICENSE
-            """
-        ),
-        "LICENSE": "",
-        "src": {
-            "vendor": {"LICENSE": ""},
-        },
-    },
-}
-
-
-if sys.platform != "win32":
-    # ABI3 extensions don't really work on Windows
-    EXAMPLES["abi3extension-dist"] = {
-        "setup.py": cleandoc(
-            """
-            from setuptools import Extension, setup
-
-            setup(
-                name="extension.dist",
-                version="0.1",
-                description="A testing distribution \N{SNOWMAN}",
-                ext_modules=[
-                    Extension(
-                        name="extension", sources=["extension.c"], py_limited_api=True
-                    )
-                ],
-            )
-            """
-        ),
-        "setup.cfg": "[bdist_wheel]\npy_limited_api=cp32",
-        "extension.c": "#define Py_LIMITED_API 0x03020000\n#include ",
-    }
-
-
-def bdist_wheel_cmd(**kwargs):
-    """Run command in the same process so that it is easier to collect coverage"""
-    dist_obj = (
-        run_setup("setup.py", stop_after="init")
-        if os.path.exists("setup.py")
-        else Distribution({"script_name": "%%build_meta%%"})
-    )
-    dist_obj.parse_config_files()
-    cmd = bdist_wheel(dist_obj)
-    for attr, value in kwargs.items():
-        setattr(cmd, attr, value)
-    cmd.finalize_options()
-    return cmd
-
-
-def mkexample(tmp_path_factory, name):
-    basedir = tmp_path_factory.mktemp(name)
-    jaraco.path.build(EXAMPLES[name], prefix=str(basedir))
-    return basedir
-
-
-@pytest.fixture(scope="session")
-def wheel_paths(tmp_path_factory):
-    build_base = tmp_path_factory.mktemp("build")
-    dist_dir = tmp_path_factory.mktemp("dist")
-    for name in EXAMPLES:
-        example_dir = mkexample(tmp_path_factory, name)
-        build_dir = build_base / name
-        with jaraco.path.DirectoryStack().context(example_dir):
-            bdist_wheel_cmd(bdist_dir=str(build_dir), dist_dir=str(dist_dir)).run()
-
-    return sorted(str(fname) for fname in dist_dir.glob("*.whl"))
-
-
-@pytest.fixture
-def dummy_dist(tmp_path_factory):
-    return mkexample(tmp_path_factory, "dummy-dist")
-
-
-@pytest.fixture
-def licenses_dist(tmp_path_factory):
-    return mkexample(tmp_path_factory, "licenses-dist")
-
-
-def test_no_scripts(wheel_paths):
-    """Make sure entry point scripts are not generated."""
-    path = next(path for path in wheel_paths if "complex_dist" in path)
-    for entry in ZipFile(path).infolist():
-        assert ".data/scripts/" not in entry.filename
-
-
-def test_unicode_record(wheel_paths):
-    path = next(path for path in wheel_paths if "unicode_dist" in path)
-    with ZipFile(path) as zf:
-        record = zf.read("unicode_dist-0.1.dist-info/RECORD")
-
-    assert "åäö_日本語.py".encode() in record
-
-
-UTF8_PKG_INFO = """\
-Metadata-Version: 2.1
-Name: helloworld
-Version: 42
-Author-email: "John X. Ãørçeč" , Γαμα קּ 東 
-
-
-UTF-8 描述 説明
-"""
-
-
-def test_preserve_unicode_metadata(monkeypatch, tmp_path):
-    monkeypatch.chdir(tmp_path)
-    egginfo = tmp_path / "dummy_dist.egg-info"
-    distinfo = tmp_path / "dummy_dist.dist-info"
-
-    egginfo.mkdir()
-    (egginfo / "PKG-INFO").write_text(UTF8_PKG_INFO, encoding="utf-8")
-    (egginfo / "dependency_links.txt").touch()
-
-    class simpler_bdist_wheel(bdist_wheel):
-        """Avoid messing with setuptools/distutils internals"""
-
-        def __init__(self):
-            pass
-
-        @property
-        def license_paths(self):
-            return []
-
-    cmd_obj = simpler_bdist_wheel()
-    cmd_obj.egg2dist(egginfo, distinfo)
-
-    metadata = (distinfo / "METADATA").read_text(encoding="utf-8")
-    assert 'Author-email: "John X. Ãørçeč"' in metadata
-    assert "Γαμα קּ 東 " in metadata
-    assert "UTF-8 描述 説明" in metadata
-
-
-def test_licenses_default(dummy_dist, monkeypatch, tmp_path):
-    monkeypatch.chdir(dummy_dist)
-    bdist_wheel_cmd(bdist_dir=str(tmp_path)).run()
-    with ZipFile("dist/dummy_dist-1.0-py3-none-any.whl") as wf:
-        license_files = {
-            "dummy_dist-1.0.dist-info/licenses/" + fname
-            for fname in DEFAULT_LICENSE_FILES
-        }
-        assert set(wf.namelist()) == DEFAULT_FILES | license_files
-
-
-def test_licenses_deprecated(dummy_dist, monkeypatch, tmp_path):
-    dummy_dist.joinpath("setup.cfg").write_text(
-        "[metadata]\nlicense_file=licenses_dir/DUMMYFILE", encoding="utf-8"
-    )
-    monkeypatch.chdir(dummy_dist)
-
-    bdist_wheel_cmd(bdist_dir=str(tmp_path)).run()
-
-    with ZipFile("dist/dummy_dist-1.0-py3-none-any.whl") as wf:
-        license_files = {"dummy_dist-1.0.dist-info/licenses/licenses_dir/DUMMYFILE"}
-        assert set(wf.namelist()) == DEFAULT_FILES | license_files
-
-
-@pytest.mark.parametrize(
-    ("config_file", "config"),
-    [
-        ("setup.cfg", "[metadata]\nlicense_files=licenses_dir/*\n  LICENSE"),
-        ("setup.cfg", "[metadata]\nlicense_files=licenses_dir/*, LICENSE"),
-        (
-            "setup.py",
-            SETUPPY_EXAMPLE.replace(
-                ")", "  license_files=['licenses_dir/DUMMYFILE', 'LICENSE'])"
-            ),
-        ),
-    ],
-)
-def test_licenses_override(dummy_dist, monkeypatch, tmp_path, config_file, config):
-    dummy_dist.joinpath(config_file).write_text(config, encoding="utf-8")
-    monkeypatch.chdir(dummy_dist)
-    bdist_wheel_cmd(bdist_dir=str(tmp_path)).run()
-    with ZipFile("dist/dummy_dist-1.0-py3-none-any.whl") as wf:
-        license_files = {
-            "dummy_dist-1.0.dist-info/licenses/" + fname
-            for fname in {"licenses_dir/DUMMYFILE", "LICENSE"}
-        }
-        assert set(wf.namelist()) == DEFAULT_FILES | license_files
-        metadata = wf.read("dummy_dist-1.0.dist-info/METADATA").decode("utf8")
-        assert "License-File: licenses_dir/DUMMYFILE" in metadata
-        assert "License-File: LICENSE" in metadata
-
-
-def test_licenses_preserve_folder_structure(licenses_dist, monkeypatch, tmp_path):
-    monkeypatch.chdir(licenses_dist)
-    bdist_wheel_cmd(bdist_dir=str(tmp_path)).run()
-    print(os.listdir("dist"))
-    with ZipFile("dist/licenses_dist-1.0-py3-none-any.whl") as wf:
-        default_files = {name.replace("dummy_", "licenses_") for name in DEFAULT_FILES}
-        license_files = {
-            "licenses_dist-1.0.dist-info/licenses/LICENSE",
-            "licenses_dist-1.0.dist-info/licenses/src/vendor/LICENSE",
-        }
-        assert set(wf.namelist()) == default_files | license_files
-        metadata = wf.read("licenses_dist-1.0.dist-info/METADATA").decode("utf8")
-        assert "License-File: src/vendor/LICENSE" in metadata
-        assert "License-File: LICENSE" in metadata
-
-
-def test_licenses_disabled(dummy_dist, monkeypatch, tmp_path):
-    dummy_dist.joinpath("setup.cfg").write_text(
-        "[metadata]\nlicense_files=\n", encoding="utf-8"
-    )
-    monkeypatch.chdir(dummy_dist)
-    bdist_wheel_cmd(bdist_dir=str(tmp_path)).run()
-    with ZipFile("dist/dummy_dist-1.0-py3-none-any.whl") as wf:
-        assert set(wf.namelist()) == DEFAULT_FILES
-
-
-def test_build_number(dummy_dist, monkeypatch, tmp_path):
-    monkeypatch.chdir(dummy_dist)
-    bdist_wheel_cmd(bdist_dir=str(tmp_path), build_number="2").run()
-    with ZipFile("dist/dummy_dist-1.0-2-py3-none-any.whl") as wf:
-        filenames = set(wf.namelist())
-        assert "dummy_dist-1.0.dist-info/RECORD" in filenames
-        assert "dummy_dist-1.0.dist-info/METADATA" in filenames
-
-
-def test_universal_deprecated(dummy_dist, monkeypatch, tmp_path):
-    monkeypatch.chdir(dummy_dist)
-    with pytest.warns(SetuptoolsDeprecationWarning, match=".*universal is deprecated"):
-        bdist_wheel_cmd(bdist_dir=str(tmp_path), universal=True).run()
-
-    # For now we still respect the option
-    assert os.path.exists("dist/dummy_dist-1.0-py2.py3-none-any.whl")
-
-
-EXTENSION_EXAMPLE = """\
-#include 
-
-static PyMethodDef methods[] = {
-  { NULL, NULL, 0, NULL }
-};
-
-static struct PyModuleDef module_def = {
-  PyModuleDef_HEAD_INIT,
-  "extension",
-  "Dummy extension module",
-  -1,
-  methods
-};
-
-PyMODINIT_FUNC PyInit_extension(void) {
-  return PyModule_Create(&module_def);
-}
-"""
-EXTENSION_SETUPPY = """\
-from __future__ import annotations
-
-from setuptools import Extension, setup
-
-setup(
-    name="extension.dist",
-    version="0.1",
-    description="A testing distribution \N{SNOWMAN}",
-    ext_modules=[Extension(name="extension", sources=["extension.c"])],
-)
-"""
-
-
-@pytest.mark.filterwarnings(
-    "once:Config variable '.*' is unset.*, Python ABI tag may be incorrect"
-)
-def test_limited_abi(monkeypatch, tmp_path, tmp_path_factory):
-    """Test that building a binary wheel with the limited ABI works."""
-    source_dir = tmp_path_factory.mktemp("extension_dist")
-    (source_dir / "setup.py").write_text(EXTENSION_SETUPPY, encoding="utf-8")
-    (source_dir / "extension.c").write_text(EXTENSION_EXAMPLE, encoding="utf-8")
-    build_dir = tmp_path.joinpath("build")
-    dist_dir = tmp_path.joinpath("dist")
-    monkeypatch.chdir(source_dir)
-    bdist_wheel_cmd(bdist_dir=str(build_dir), dist_dir=str(dist_dir)).run()
-
-
-def test_build_from_readonly_tree(dummy_dist, monkeypatch, tmp_path):
-    basedir = str(tmp_path.joinpath("dummy"))
-    shutil.copytree(str(dummy_dist), basedir)
-    monkeypatch.chdir(basedir)
-
-    # Make the tree read-only
-    for root, _dirs, files in os.walk(basedir):
-        for fname in files:
-            os.chmod(os.path.join(root, fname), stat.S_IREAD)
-
-    bdist_wheel_cmd().run()
-
-
-@pytest.mark.parametrize(
-    ("option", "compress_type"),
-    list(bdist_wheel.supported_compressions.items()),
-    ids=list(bdist_wheel.supported_compressions),
-)
-def test_compression(dummy_dist, monkeypatch, tmp_path, option, compress_type):
-    monkeypatch.chdir(dummy_dist)
-    bdist_wheel_cmd(bdist_dir=str(tmp_path), compression=option).run()
-    with ZipFile("dist/dummy_dist-1.0-py3-none-any.whl") as wf:
-        filenames = set(wf.namelist())
-        assert "dummy_dist-1.0.dist-info/RECORD" in filenames
-        assert "dummy_dist-1.0.dist-info/METADATA" in filenames
-        for zinfo in wf.filelist:
-            assert zinfo.compress_type == compress_type
-
-
-def test_wheelfile_line_endings(wheel_paths):
-    for path in wheel_paths:
-        with ZipFile(path) as wf:
-            wheelfile = next(fn for fn in wf.filelist if fn.filename.endswith("WHEEL"))
-            wheelfile_contents = wf.read(wheelfile)
-            assert b"\r" not in wheelfile_contents
-
-
-def test_unix_epoch_timestamps(dummy_dist, monkeypatch, tmp_path):
-    monkeypatch.setenv("SOURCE_DATE_EPOCH", "0")
-    monkeypatch.chdir(dummy_dist)
-    bdist_wheel_cmd(bdist_dir=str(tmp_path), build_number="2a").run()
-    with ZipFile("dist/dummy_dist-1.0-2a-py3-none-any.whl") as wf:
-        for zinfo in wf.filelist:
-            assert zinfo.date_time >= (1980, 1, 1, 0, 0, 0)  # min epoch is used
-
-
-def test_get_abi_tag_windows(monkeypatch):
-    monkeypatch.setattr(tags, "interpreter_name", lambda: "cp")
-    monkeypatch.setattr(sysconfig, "get_config_var", lambda x: "cp313-win_amd64")
-    assert get_abi_tag() == "cp313"
-    monkeypatch.setattr(sys, "gettotalrefcount", lambda: 1, False)
-    assert get_abi_tag() == "cp313d"
-    monkeypatch.setattr(sysconfig, "get_config_var", lambda x: "cp313t-win_amd64")
-    assert get_abi_tag() == "cp313td"
-    monkeypatch.delattr(sys, "gettotalrefcount")
-    assert get_abi_tag() == "cp313t"
-
-
-def test_get_abi_tag_pypy_old(monkeypatch):
-    monkeypatch.setattr(tags, "interpreter_name", lambda: "pp")
-    monkeypatch.setattr(sysconfig, "get_config_var", lambda x: "pypy36-pp73")
-    assert get_abi_tag() == "pypy36_pp73"
-
-
-def test_get_abi_tag_pypy_new(monkeypatch):
-    monkeypatch.setattr(sysconfig, "get_config_var", lambda x: "pypy37-pp73-darwin")
-    monkeypatch.setattr(tags, "interpreter_name", lambda: "pp")
-    assert get_abi_tag() == "pypy37_pp73"
-
-
-def test_get_abi_tag_graalpy(monkeypatch):
-    monkeypatch.setattr(
-        sysconfig, "get_config_var", lambda x: "graalpy231-310-native-x86_64-linux"
-    )
-    monkeypatch.setattr(tags, "interpreter_name", lambda: "graalpy")
-    assert get_abi_tag() == "graalpy231_310_native"
-
-
-def test_get_abi_tag_fallback(monkeypatch):
-    monkeypatch.setattr(sysconfig, "get_config_var", lambda x: "unknown-python-310")
-    monkeypatch.setattr(tags, "interpreter_name", lambda: "unknown-python")
-    assert get_abi_tag() == "unknown_python_310"
-
-
-def test_platform_with_space(dummy_dist, monkeypatch):
-    """Ensure building on platforms with a space in the name succeed."""
-    monkeypatch.chdir(dummy_dist)
-    bdist_wheel_cmd(plat_name="isilon onefs").run()
-
-
-def test_data_dir_with_tag_build(monkeypatch, tmp_path):
-    """
-    Setuptools allow authors to set PEP 440's local version segments
-    using ``egg_info.tag_build``. This should be reflected not only in the
-    ``.whl`` file name, but also in the ``.dist-info`` and ``.data`` dirs.
-    See pypa/setuptools#3997.
-    """
-    monkeypatch.chdir(tmp_path)
-    files = {
-        "setup.py": """
-            from setuptools import setup
-            setup(headers=["hello.h"])
-            """,
-        "setup.cfg": """
-            [metadata]
-            name = test
-            version = 1.0
-
-            [options.data_files]
-            hello/world = file.txt
-
-            [egg_info]
-            tag_build = +what
-            tag_date = 0
-            """,
-        "file.txt": "",
-        "hello.h": "",
-    }
-    for file, content in files.items():
-        with open(file, "w", encoding="utf-8") as fh:
-            fh.write(cleandoc(content))
-
-    bdist_wheel_cmd().run()
-
-    # Ensure .whl, .dist-info and .data contain the local segment
-    wheel_path = "dist/test-1.0+what-py3-none-any.whl"
-    assert os.path.exists(wheel_path)
-    entries = set(ZipFile(wheel_path).namelist())
-    for expected in (
-        "test-1.0+what.data/headers/hello.h",
-        "test-1.0+what.data/data/hello/world/file.txt",
-        "test-1.0+what.dist-info/METADATA",
-        "test-1.0+what.dist-info/WHEEL",
-    ):
-        assert expected in entries
-
-    for not_expected in (
-        "test.data/headers/hello.h",
-        "test-1.0.data/data/hello/world/file.txt",
-        "test.dist-info/METADATA",
-        "test-1.0.dist-info/WHEEL",
-    ):
-        assert not_expected not in entries
-
-
-@pytest.mark.parametrize(
-    ("reported", "expected"),
-    [("linux-x86_64", "linux_i686"), ("linux-aarch64", "linux_armv7l")],
-)
-@pytest.mark.skipif(
-    platform.system() != "Linux", reason="Only makes sense to test on Linux"
-)
-def test_platform_linux32(reported, expected, monkeypatch):
-    monkeypatch.setattr(struct, "calcsize", lambda x: 4)
-    dist = setuptools.Distribution()
-    cmd = bdist_wheel(dist)
-    cmd.plat_name = reported
-    cmd.root_is_pure = False
-    _, _, actual = cmd.get_tag()
-    assert actual == expected
-
-
-def test_no_ctypes(monkeypatch) -> None:
-    def _fake_import(name: str, *args, **kwargs):
-        if name == "ctypes":
-            raise ModuleNotFoundError(f"No module named {name}")
-
-        return importlib.__import__(name, *args, **kwargs)
-
-    with suppress(KeyError):
-        monkeypatch.delitem(sys.modules, "wheel.macosx_libfile")
-
-    # Install an importer shim that refuses to load ctypes
-    monkeypatch.setattr(builtins, "__import__", _fake_import)
-    with pytest.raises(ModuleNotFoundError, match="No module named ctypes"):
-        import wheel.macosx_libfile  # noqa: F401
-
-    # Unload and reimport the bdist_wheel command module to make sure it won't try to
-    # import ctypes
-    monkeypatch.delitem(sys.modules, "setuptools.command.bdist_wheel")
-
-    import setuptools.command.bdist_wheel  # noqa: F401
-
-
-def test_dist_info_provided(dummy_dist, monkeypatch, tmp_path):
-    monkeypatch.chdir(dummy_dist)
-    distinfo = tmp_path / "dummy_dist.dist-info"
-
-    distinfo.mkdir()
-    (distinfo / "METADATA").write_text("name: helloworld", encoding="utf-8")
-
-    # We don't control the metadata. According to PEP-517, "The hook MAY also
-    # create other files inside this directory, and a build frontend MUST
-    # preserve".
-    (distinfo / "FOO").write_text("bar", encoding="utf-8")
-
-    bdist_wheel_cmd(bdist_dir=str(tmp_path), dist_info_dir=str(distinfo)).run()
-    expected = {
-        "dummy_dist-1.0.dist-info/FOO",
-        "dummy_dist-1.0.dist-info/RECORD",
-    }
-    with ZipFile("dist/dummy_dist-1.0-py3-none-any.whl") as wf:
-        files_found = set(wf.namelist())
-    # Check that all expected files are there.
-    assert expected - files_found == set()
-    # Make sure there is no accidental egg-info bleeding into the wheel.
-    assert not [path for path in files_found if 'egg-info' in str(path)]
-
-
-def test_allow_grace_period_parent_directory_license(monkeypatch, tmp_path):
-    # Motivation: https://github.com/pypa/setuptools/issues/4892
-    # TODO: Remove this test after deprecation period is over
-    files = {
-        "LICENSE.txt": "parent license",  # <---- the license files are outside
-        "NOTICE.txt": "parent notice",
-        "python": {
-            "pyproject.toml": cleandoc(
-                """
-                [project]
-                name = "test-proj"
-                dynamic = ["version"]      # <---- testing dynamic will not break
-                [tool.setuptools.dynamic]
-                version.file = "VERSION"
-                """
-            ),
-            "setup.cfg": cleandoc(
-                """
-                [metadata]
-                license_files =
-                  ../LICENSE.txt
-                  ../NOTICE.txt
-                """
-            ),
-            "VERSION": "42",
-        },
-    }
-    jaraco.path.build(files, prefix=str(tmp_path))
-    monkeypatch.chdir(tmp_path / "python")
-    msg = "Pattern '../.*.txt' cannot contain '..'"
-    with pytest.warns(SetuptoolsDeprecationWarning, match=msg):
-        bdist_wheel_cmd().run()
-    with ZipFile("dist/test_proj-42-py3-none-any.whl") as wf:
-        files_found = set(wf.namelist())
-        expected_files = {
-            "test_proj-42.dist-info/licenses/LICENSE.txt",
-            "test_proj-42.dist-info/licenses/NOTICE.txt",
-        }
-        assert expected_files <= files_found
-
-        metadata = wf.read("test_proj-42.dist-info/METADATA").decode("utf8")
-        assert "License-File: LICENSE.txt" in metadata
-        assert "License-File: NOTICE.txt" in metadata
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build.py
deleted file mode 100644
index f0f1d9d..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build.py
+++ /dev/null
@@ -1,33 +0,0 @@
-from setuptools import Command
-from setuptools.command.build import build
-from setuptools.dist import Distribution
-
-
-def test_distribution_gives_setuptools_build_obj(tmpdir_cwd):
-    """
-    Check that the setuptools Distribution uses the
-    setuptools specific build object.
-    """
-
-    dist = Distribution(
-        dict(
-            script_name='setup.py',
-            script_args=['build'],
-            packages=[],
-            package_data={'': ['path/*']},
-        )
-    )
-    assert isinstance(dist.get_command_obj("build"), build)
-
-
-class Subcommand(Command):
-    """Dummy command to be used in tests"""
-
-    def initialize_options(self):
-        pass
-
-    def finalize_options(self):
-        pass
-
-    def run(self):
-        raise NotImplementedError("just to check if the command runs")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_clib.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_clib.py
deleted file mode 100644
index b5315df..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_clib.py
+++ /dev/null
@@ -1,84 +0,0 @@
-import random
-from unittest import mock
-
-import pytest
-
-from setuptools.command.build_clib import build_clib
-from setuptools.dist import Distribution
-
-from distutils.errors import DistutilsSetupError
-
-
-class TestBuildCLib:
-    @mock.patch('setuptools.command.build_clib.newer_pairwise_group')
-    def test_build_libraries(self, mock_newer):
-        dist = Distribution()
-        cmd = build_clib(dist)
-
-        # this will be a long section, just making sure all
-        # exceptions are properly raised
-        libs = [('example', {'sources': 'broken.c'})]
-        with pytest.raises(DistutilsSetupError):
-            cmd.build_libraries(libs)
-
-        obj_deps = 'some_string'
-        libs = [('example', {'sources': ['source.c'], 'obj_deps': obj_deps})]
-        with pytest.raises(DistutilsSetupError):
-            cmd.build_libraries(libs)
-
-        obj_deps = {'': ''}
-        libs = [('example', {'sources': ['source.c'], 'obj_deps': obj_deps})]
-        with pytest.raises(DistutilsSetupError):
-            cmd.build_libraries(libs)
-
-        obj_deps = {'source.c': ''}
-        libs = [('example', {'sources': ['source.c'], 'obj_deps': obj_deps})]
-        with pytest.raises(DistutilsSetupError):
-            cmd.build_libraries(libs)
-
-        # with that out of the way, let's see if the crude dependency
-        # system works
-        cmd.compiler = mock.MagicMock(spec=cmd.compiler)
-        mock_newer.return_value = ([], [])
-
-        obj_deps = {'': ('global.h',), 'example.c': ('example.h',)}
-        libs = [('example', {'sources': ['example.c'], 'obj_deps': obj_deps})]
-
-        cmd.build_libraries(libs)
-        assert [['example.c', 'global.h', 'example.h']] in mock_newer.call_args[0]
-        assert not cmd.compiler.compile.called
-        assert cmd.compiler.create_static_lib.call_count == 1
-
-        # reset the call numbers so we can test again
-        cmd.compiler.reset_mock()
-
-        mock_newer.return_value = ''  # anything as long as it's not ([],[])
-        cmd.build_libraries(libs)
-        assert cmd.compiler.compile.call_count == 1
-        assert cmd.compiler.create_static_lib.call_count == 1
-
-    @mock.patch('setuptools.command.build_clib.newer_pairwise_group')
-    def test_build_libraries_reproducible(self, mock_newer):
-        dist = Distribution()
-        cmd = build_clib(dist)
-
-        # with that out of the way, let's see if the crude dependency
-        # system works
-        cmd.compiler = mock.MagicMock(spec=cmd.compiler)
-        mock_newer.return_value = ([], [])
-
-        original_sources = ['a-example.c', 'example.c']
-        sources = original_sources
-
-        obj_deps = {'': ('global.h',), 'example.c': ('example.h',)}
-        libs = [('example', {'sources': sources, 'obj_deps': obj_deps})]
-
-        cmd.build_libraries(libs)
-        computed_call_args = mock_newer.call_args[0]
-
-        while sources == original_sources:
-            sources = random.sample(original_sources, len(original_sources))
-        libs = [('example', {'sources': sources, 'obj_deps': obj_deps})]
-
-        cmd.build_libraries(libs)
-        assert computed_call_args == mock_newer.call_args[0]
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_ext.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_ext.py
deleted file mode 100644
index c7b60ac..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_ext.py
+++ /dev/null
@@ -1,293 +0,0 @@
-from __future__ import annotations
-
-import os
-import sys
-from importlib.util import cache_from_source as _compiled_file_name
-
-import pytest
-from jaraco import path
-
-from setuptools.command.build_ext import build_ext, get_abi3_suffix
-from setuptools.dist import Distribution
-from setuptools.errors import CompileError
-from setuptools.extension import Extension
-
-from . import environment
-from .textwrap import DALS
-
-import distutils.command.build_ext as orig
-from distutils.sysconfig import get_config_var
-
-IS_PYPY = '__pypy__' in sys.builtin_module_names
-
-
-class TestBuildExt:
-    def test_get_ext_filename(self):
-        """
-        Setuptools needs to give back the same
-        result as distutils, even if the fullname
-        is not in ext_map.
-        """
-        dist = Distribution()
-        cmd = build_ext(dist)
-        cmd.ext_map['foo/bar'] = ''
-        res = cmd.get_ext_filename('foo')
-        wanted = orig.build_ext.get_ext_filename(cmd, 'foo')
-        assert res == wanted
-
-    def test_abi3_filename(self):
-        """
-        Filename needs to be loadable by several versions
-        of Python 3 if 'is_abi3' is truthy on Extension()
-        """
-        print(get_abi3_suffix())
-
-        extension = Extension('spam.eggs', ['eggs.c'], py_limited_api=True)
-        dist = Distribution(dict(ext_modules=[extension]))
-        cmd = build_ext(dist)
-        cmd.finalize_options()
-        assert 'spam.eggs' in cmd.ext_map
-        res = cmd.get_ext_filename('spam.eggs')
-
-        if not get_abi3_suffix():
-            assert res.endswith(get_config_var('EXT_SUFFIX'))
-        elif sys.platform == 'win32':
-            assert res.endswith('eggs.pyd')
-        else:
-            assert 'abi3' in res
-
-    def test_ext_suffix_override(self):
-        """
-        SETUPTOOLS_EXT_SUFFIX variable always overrides
-        default extension options.
-        """
-        dist = Distribution()
-        cmd = build_ext(dist)
-        cmd.ext_map['for_abi3'] = ext = Extension(
-            'for_abi3',
-            ['s.c'],
-            # Override shouldn't affect abi3 modules
-            py_limited_api=True,
-        )
-        # Mock value needed to pass tests
-        ext._links_to_dynamic = False
-
-        if not IS_PYPY:
-            expect = cmd.get_ext_filename('for_abi3')
-        else:
-            # PyPy builds do not use ABI3 tag, so they will
-            # also get the overridden suffix.
-            expect = 'for_abi3.test-suffix'
-
-        try:
-            os.environ['SETUPTOOLS_EXT_SUFFIX'] = '.test-suffix'
-            res = cmd.get_ext_filename('normal')
-            assert 'normal.test-suffix' == res
-            res = cmd.get_ext_filename('for_abi3')
-            assert expect == res
-        finally:
-            del os.environ['SETUPTOOLS_EXT_SUFFIX']
-
-    def dist_with_example(self):
-        files = {
-            "src": {"mypkg": {"subpkg": {"ext2.c": ""}}},
-            "c-extensions": {"ext1": {"main.c": ""}},
-        }
-
-        ext1 = Extension("mypkg.ext1", ["c-extensions/ext1/main.c"])
-        ext2 = Extension("mypkg.subpkg.ext2", ["src/mypkg/subpkg/ext2.c"])
-        ext3 = Extension("ext3", ["c-extension/ext3.c"])
-
-        path.build(files)
-        return Distribution({
-            "script_name": "%test%",
-            "ext_modules": [ext1, ext2, ext3],
-            "package_dir": {"": "src"},
-        })
-
-    def test_get_outputs(self, tmpdir_cwd, monkeypatch):
-        monkeypatch.setenv('SETUPTOOLS_EXT_SUFFIX', '.mp3')  # make test OS-independent
-        monkeypatch.setattr('setuptools.command.build_ext.use_stubs', False)
-        dist = self.dist_with_example()
-
-        # Regular build: get_outputs not empty, but get_output_mappings is empty
-        build_ext = dist.get_command_obj("build_ext")
-        build_ext.editable_mode = False
-        build_ext.ensure_finalized()
-        build_lib = build_ext.build_lib.replace(os.sep, "/")
-        outputs = [x.replace(os.sep, "/") for x in build_ext.get_outputs()]
-        assert outputs == [
-            f"{build_lib}/ext3.mp3",
-            f"{build_lib}/mypkg/ext1.mp3",
-            f"{build_lib}/mypkg/subpkg/ext2.mp3",
-        ]
-        assert build_ext.get_output_mapping() == {}
-
-        # Editable build: get_output_mappings should contain everything in get_outputs
-        dist.reinitialize_command("build_ext")
-        build_ext.editable_mode = True
-        build_ext.ensure_finalized()
-        mapping = {
-            k.replace(os.sep, "/"): v.replace(os.sep, "/")
-            for k, v in build_ext.get_output_mapping().items()
-        }
-        assert mapping == {
-            f"{build_lib}/ext3.mp3": "src/ext3.mp3",
-            f"{build_lib}/mypkg/ext1.mp3": "src/mypkg/ext1.mp3",
-            f"{build_lib}/mypkg/subpkg/ext2.mp3": "src/mypkg/subpkg/ext2.mp3",
-        }
-
-    def test_get_output_mapping_with_stub(self, tmpdir_cwd, monkeypatch):
-        monkeypatch.setenv('SETUPTOOLS_EXT_SUFFIX', '.mp3')  # make test OS-independent
-        monkeypatch.setattr('setuptools.command.build_ext.use_stubs', True)
-        dist = self.dist_with_example()
-
-        # Editable build should create compiled stubs (.pyc files only, no .py)
-        build_ext = dist.get_command_obj("build_ext")
-        build_ext.editable_mode = True
-        build_ext.ensure_finalized()
-        for ext in build_ext.extensions:
-            monkeypatch.setattr(ext, "_needs_stub", True)
-
-        build_lib = build_ext.build_lib.replace(os.sep, "/")
-        mapping = {
-            k.replace(os.sep, "/"): v.replace(os.sep, "/")
-            for k, v in build_ext.get_output_mapping().items()
-        }
-
-        def C(file):
-            """Make it possible to do comparisons and tests in a OS-independent way"""
-            return _compiled_file_name(file).replace(os.sep, "/")
-
-        assert mapping == {
-            C(f"{build_lib}/ext3.py"): C("src/ext3.py"),
-            f"{build_lib}/ext3.mp3": "src/ext3.mp3",
-            C(f"{build_lib}/mypkg/ext1.py"): C("src/mypkg/ext1.py"),
-            f"{build_lib}/mypkg/ext1.mp3": "src/mypkg/ext1.mp3",
-            C(f"{build_lib}/mypkg/subpkg/ext2.py"): C("src/mypkg/subpkg/ext2.py"),
-            f"{build_lib}/mypkg/subpkg/ext2.mp3": "src/mypkg/subpkg/ext2.mp3",
-        }
-
-        # Ensure only the compiled stubs are present not the raw .py stub
-        assert f"{build_lib}/mypkg/ext1.py" not in mapping
-        assert f"{build_lib}/mypkg/subpkg/ext2.py" not in mapping
-
-        # Visualize what the cached stub files look like
-        example_stub = C(f"{build_lib}/mypkg/ext1.py")
-        assert example_stub in mapping
-        assert example_stub.startswith(f"{build_lib}/mypkg/__pycache__/ext1")
-        assert example_stub.endswith(".pyc")
-
-
-class TestBuildExtInplace:
-    def get_build_ext_cmd(self, optional: bool, **opts) -> build_ext:
-        files: dict[str, str | dict[str, dict[str, str]]] = {
-            "eggs.c": "#include missingheader.h\n",
-            ".build": {"lib": {}, "tmp": {}},
-        }
-        path.build(files)
-        extension = Extension('spam.eggs', ['eggs.c'], optional=optional)
-        dist = Distribution(dict(ext_modules=[extension]))
-        dist.script_name = 'setup.py'
-        cmd = build_ext(dist)
-        vars(cmd).update(build_lib=".build/lib", build_temp=".build/tmp", **opts)
-        cmd.ensure_finalized()
-        return cmd
-
-    def get_log_messages(self, caplog, capsys):
-        """
-        Historically, distutils "logged" by printing to sys.std*.
-        Later versions adopted the logging framework. Grab
-        messages regardless of how they were captured.
-        """
-        std = capsys.readouterr()
-        return std.out.splitlines() + std.err.splitlines() + caplog.messages
-
-    def test_optional(self, tmpdir_cwd, caplog, capsys):
-        """
-        If optional extensions fail to build, setuptools should show the error
-        in the logs but not fail to build
-        """
-        cmd = self.get_build_ext_cmd(optional=True, inplace=True)
-        cmd.run()
-        assert any(
-            'build_ext: building extension "spam.eggs" failed'
-            for msg in self.get_log_messages(caplog, capsys)
-        )
-        # No compile error exception should be raised
-
-    def test_non_optional(self, tmpdir_cwd):
-        # Non-optional extensions should raise an exception
-        cmd = self.get_build_ext_cmd(optional=False, inplace=True)
-        with pytest.raises(CompileError):
-            cmd.run()
-
-
-def test_build_ext_config_handling(tmpdir_cwd):
-    files = {
-        'setup.py': DALS(
-            """
-            from setuptools import Extension, setup
-            setup(
-                name='foo',
-                version='0.0.0',
-                ext_modules=[Extension('foo', ['foo.c'])],
-            )
-            """
-        ),
-        'foo.c': DALS(
-            """
-            #include "Python.h"
-
-            #if PY_MAJOR_VERSION >= 3
-
-            static struct PyModuleDef moduledef = {
-                    PyModuleDef_HEAD_INIT,
-                    "foo",
-                    NULL,
-                    0,
-                    NULL,
-                    NULL,
-                    NULL,
-                    NULL,
-                    NULL
-            };
-
-            #define INITERROR return NULL
-
-            PyMODINIT_FUNC PyInit_foo(void)
-
-            #else
-
-            #define INITERROR return
-
-            void initfoo(void)
-
-            #endif
-            {
-            #if PY_MAJOR_VERSION >= 3
-                PyObject *module = PyModule_Create(&moduledef);
-            #else
-                PyObject *module = Py_InitModule("extension", NULL);
-            #endif
-                if (module == NULL)
-                    INITERROR;
-            #if PY_MAJOR_VERSION >= 3
-                return module;
-            #endif
-            }
-            """
-        ),
-        'setup.cfg': DALS(
-            """
-            [build]
-            build_base = foo_build
-            """
-        ),
-    }
-    path.build(files)
-    code, (stdout, stderr) = environment.run_setup_py(
-        cmd=['build'],
-        data_stream=(0, 2),
-    )
-    assert code == 0, f'\nSTDOUT:\n{stdout}\nSTDERR:\n{stderr}'
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_meta.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_meta.py
deleted file mode 100644
index 624bba8..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_meta.py
+++ /dev/null
@@ -1,983 +0,0 @@
-import contextlib
-import importlib
-import os
-import re
-import shutil
-import signal
-import sys
-import tarfile
-import warnings
-from concurrent import futures
-from pathlib import Path
-from typing import Any, Callable
-from zipfile import ZipFile
-
-import pytest
-from jaraco import path
-from packaging.requirements import Requirement
-
-from setuptools.warnings import SetuptoolsDeprecationWarning
-
-from .textwrap import DALS
-
-SETUP_SCRIPT_STUB = "__import__('setuptools').setup()"
-
-
-TIMEOUT = int(os.getenv("TIMEOUT_BACKEND_TEST", "180"))  # in seconds
-IS_PYPY = '__pypy__' in sys.builtin_module_names
-
-
-pytestmark = pytest.mark.skipif(
-    sys.platform == "win32" and IS_PYPY,
-    reason="The combination of PyPy + Windows + pytest-xdist + ProcessPoolExecutor "
-    "is flaky and problematic",
-)
-
-
-class BuildBackendBase:
-    def __init__(self, cwd='.', env=None, backend_name='setuptools.build_meta'):
-        self.cwd = cwd
-        self.env = env or {}
-        self.backend_name = backend_name
-
-
-class BuildBackend(BuildBackendBase):
-    """PEP 517 Build Backend"""
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.pool = futures.ProcessPoolExecutor(max_workers=1)
-
-    def __getattr__(self, name: str) -> Callable[..., Any]:
-        """Handles arbitrary function invocations on the build backend."""
-
-        def method(*args, **kw):
-            root = os.path.abspath(self.cwd)
-            caller = BuildBackendCaller(root, self.env, self.backend_name)
-            pid = None
-            try:
-                pid = self.pool.submit(os.getpid).result(TIMEOUT)
-                return self.pool.submit(caller, name, *args, **kw).result(TIMEOUT)
-            except futures.TimeoutError:
-                self.pool.shutdown(wait=False)  # doesn't stop already running processes
-                self._kill(pid)
-                pytest.xfail(f"Backend did not respond before timeout ({TIMEOUT} s)")
-            except (futures.process.BrokenProcessPool, MemoryError, OSError):
-                if IS_PYPY:
-                    pytest.xfail("PyPy frequently fails tests with ProcessPoolExector")
-                raise
-
-        return method
-
-    def _kill(self, pid):
-        if pid is None:
-            return
-        with contextlib.suppress(ProcessLookupError, OSError):
-            os.kill(pid, signal.SIGTERM if os.name == "nt" else signal.SIGKILL)
-
-
-class BuildBackendCaller(BuildBackendBase):
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-
-        (self.backend_name, _, self.backend_obj) = self.backend_name.partition(':')
-
-    def __call__(self, name, *args, **kw):
-        """Handles arbitrary function invocations on the build backend."""
-        os.chdir(self.cwd)
-        os.environ.update(self.env)
-        mod = importlib.import_module(self.backend_name)
-
-        if self.backend_obj:
-            backend = getattr(mod, self.backend_obj)
-        else:
-            backend = mod
-
-        return getattr(backend, name)(*args, **kw)
-
-
-defns = [
-    {  # simple setup.py script
-        'setup.py': DALS(
-            """
-            __import__('setuptools').setup(
-                name='foo',
-                version='0.0.0',
-                py_modules=['hello'],
-                setup_requires=['six'],
-            )
-            """
-        ),
-        'hello.py': DALS(
-            """
-            def run():
-                print('hello')
-            """
-        ),
-    },
-    {  # setup.py that relies on __name__
-        'setup.py': DALS(
-            """
-            assert __name__ == '__main__'
-            __import__('setuptools').setup(
-                name='foo',
-                version='0.0.0',
-                py_modules=['hello'],
-                setup_requires=['six'],
-            )
-            """
-        ),
-        'hello.py': DALS(
-            """
-            def run():
-                print('hello')
-            """
-        ),
-    },
-    {  # setup.py script that runs arbitrary code
-        'setup.py': DALS(
-            """
-            variable = True
-            def function():
-                return variable
-            assert variable
-            __import__('setuptools').setup(
-                name='foo',
-                version='0.0.0',
-                py_modules=['hello'],
-                setup_requires=['six'],
-            )
-            """
-        ),
-        'hello.py': DALS(
-            """
-            def run():
-                print('hello')
-            """
-        ),
-    },
-    {  # setup.py script that constructs temp files to be included in the distribution
-        'setup.py': DALS(
-            """
-            # Some packages construct files on the fly, include them in the package,
-            # and immediately remove them after `setup()` (e.g. pybind11==2.9.1).
-            # Therefore, we cannot use `distutils.core.run_setup(..., stop_after=...)`
-            # to obtain a distribution object first, and then run the distutils
-            # commands later, because these files will be removed in the meantime.
-
-            with open('world.py', 'w', encoding="utf-8") as f:
-                f.write('x = 42')
-
-            try:
-                __import__('setuptools').setup(
-                    name='foo',
-                    version='0.0.0',
-                    py_modules=['world'],
-                    setup_requires=['six'],
-                )
-            finally:
-                # Some packages will clean temporary files
-                __import__('os').unlink('world.py')
-            """
-        ),
-    },
-    {  # setup.cfg only
-        'setup.cfg': DALS(
-            """
-        [metadata]
-        name = foo
-        version = 0.0.0
-
-        [options]
-        py_modules=hello
-        setup_requires=six
-        """
-        ),
-        'hello.py': DALS(
-            """
-        def run():
-            print('hello')
-        """
-        ),
-    },
-    {  # setup.cfg and setup.py
-        'setup.cfg': DALS(
-            """
-        [metadata]
-        name = foo
-        version = 0.0.0
-
-        [options]
-        py_modules=hello
-        setup_requires=six
-        """
-        ),
-        'setup.py': "__import__('setuptools').setup()",
-        'hello.py': DALS(
-            """
-        def run():
-            print('hello')
-        """
-        ),
-    },
-]
-
-
-class TestBuildMetaBackend:
-    backend_name = 'setuptools.build_meta'
-
-    def get_build_backend(self):
-        return BuildBackend(backend_name=self.backend_name)
-
-    @pytest.fixture(params=defns)
-    def build_backend(self, tmpdir, request):
-        path.build(request.param, prefix=str(tmpdir))
-        with tmpdir.as_cwd():
-            yield self.get_build_backend()
-
-    def test_get_requires_for_build_wheel(self, build_backend):
-        actual = build_backend.get_requires_for_build_wheel()
-        expected = ['six']
-        assert sorted(actual) == sorted(expected)
-
-    def test_get_requires_for_build_sdist(self, build_backend):
-        actual = build_backend.get_requires_for_build_sdist()
-        expected = ['six']
-        assert sorted(actual) == sorted(expected)
-
-    def test_build_wheel(self, build_backend):
-        dist_dir = os.path.abspath('pip-wheel')
-        os.makedirs(dist_dir)
-        wheel_name = build_backend.build_wheel(dist_dir)
-
-        wheel_file = os.path.join(dist_dir, wheel_name)
-        assert os.path.isfile(wheel_file)
-
-        # Temporary files should be removed
-        assert not os.path.isfile('world.py')
-
-        with ZipFile(wheel_file) as zipfile:
-            wheel_contents = set(zipfile.namelist())
-
-        # Each one of the examples have a single module
-        # that should be included in the distribution
-        python_scripts = (f for f in wheel_contents if f.endswith('.py'))
-        modules = [f for f in python_scripts if not f.endswith('setup.py')]
-        assert len(modules) == 1
-
-    @pytest.mark.parametrize('build_type', ('wheel', 'sdist'))
-    def test_build_with_existing_file_present(self, build_type, tmpdir_cwd):
-        # Building a sdist/wheel should still succeed if there's
-        # already a sdist/wheel in the destination directory.
-        files = {
-            'setup.py': "from setuptools import setup\nsetup()",
-            'VERSION': "0.0.1",
-            'setup.cfg': DALS(
-                """
-                [metadata]
-                name = foo
-                version = file: VERSION
-                """
-            ),
-            'pyproject.toml': DALS(
-                """
-                [build-system]
-                requires = ["setuptools", "wheel"]
-                build-backend = "setuptools.build_meta"
-                """
-            ),
-        }
-
-        path.build(files)
-
-        dist_dir = os.path.abspath('preexisting-' + build_type)
-
-        build_backend = self.get_build_backend()
-        build_method = getattr(build_backend, 'build_' + build_type)
-
-        # Build a first sdist/wheel.
-        # Note: this also check the destination directory is
-        # successfully created if it does not exist already.
-        first_result = build_method(dist_dir)
-
-        # Change version.
-        with open("VERSION", "wt", encoding="utf-8") as version_file:
-            version_file.write("0.0.2")
-
-        # Build a *second* sdist/wheel.
-        second_result = build_method(dist_dir)
-
-        assert os.path.isfile(os.path.join(dist_dir, first_result))
-        assert first_result != second_result
-
-        # And if rebuilding the exact same sdist/wheel?
-        open(os.path.join(dist_dir, second_result), 'wb').close()
-        third_result = build_method(dist_dir)
-        assert third_result == second_result
-        assert os.path.getsize(os.path.join(dist_dir, third_result)) > 0
-
-    @pytest.mark.parametrize("setup_script", [None, SETUP_SCRIPT_STUB])
-    def test_build_with_pyproject_config(self, tmpdir, setup_script):
-        files = {
-            'pyproject.toml': DALS(
-                """
-                [build-system]
-                requires = ["setuptools", "wheel"]
-                build-backend = "setuptools.build_meta"
-
-                [project]
-                name = "foo"
-                license = {text = "MIT"}
-                description = "This is a Python package"
-                dynamic = ["version", "readme"]
-                classifiers = [
-                    "Development Status :: 5 - Production/Stable",
-                    "Intended Audience :: Developers"
-                ]
-                urls = {Homepage = "http://github.com"}
-                dependencies = [
-                    "appdirs",
-                ]
-
-                [project.optional-dependencies]
-                all = [
-                    "tomli>=1",
-                    "pyscaffold>=4,<5",
-                    'importlib; python_version == "2.6"',
-                ]
-
-                [project.scripts]
-                foo = "foo.cli:main"
-
-                [tool.setuptools]
-                zip-safe = false
-                package-dir = {"" = "src"}
-                packages = {find = {where = ["src"]}}
-                license-files = ["LICENSE*"]
-
-                [tool.setuptools.dynamic]
-                version = {attr = "foo.__version__"}
-                readme = {file = "README.rst"}
-
-                [tool.distutils.sdist]
-                formats = "gztar"
-                """
-            ),
-            "MANIFEST.in": DALS(
-                """
-                global-include *.py *.txt
-                global-exclude *.py[cod]
-                """
-            ),
-            "README.rst": "This is a ``README``",
-            "LICENSE.txt": "---- placeholder MIT license ----",
-            "src": {
-                "foo": {
-                    "__init__.py": "__version__ = '0.1'",
-                    "__init__.pyi": "__version__: str",
-                    "cli.py": "def main(): print('hello world')",
-                    "data.txt": "def main(): print('hello world')",
-                    "py.typed": "",
-                }
-            },
-        }
-        if setup_script:
-            files["setup.py"] = setup_script
-
-        build_backend = self.get_build_backend()
-        with tmpdir.as_cwd():
-            path.build(files)
-            msgs = [
-                "'tool.setuptools.license-files' is deprecated in favor of 'project.license-files'",
-                "`project.license` as a TOML table is deprecated",
-            ]
-            with warnings.catch_warnings():
-                for msg in msgs:
-                    warnings.filterwarnings("ignore", msg, SetuptoolsDeprecationWarning)
-                sdist_path = build_backend.build_sdist("temp")
-                wheel_file = build_backend.build_wheel("temp")
-
-        with tarfile.open(os.path.join(tmpdir, "temp", sdist_path)) as tar:
-            sdist_contents = set(tar.getnames())
-
-        with ZipFile(os.path.join(tmpdir, "temp", wheel_file)) as zipfile:
-            wheel_contents = set(zipfile.namelist())
-            metadata = str(zipfile.read("foo-0.1.dist-info/METADATA"), "utf-8")
-            license = str(
-                zipfile.read("foo-0.1.dist-info/licenses/LICENSE.txt"), "utf-8"
-            )
-            epoints = str(zipfile.read("foo-0.1.dist-info/entry_points.txt"), "utf-8")
-
-        assert sdist_contents - {"foo-0.1/setup.py"} == {
-            'foo-0.1',
-            'foo-0.1/LICENSE.txt',
-            'foo-0.1/MANIFEST.in',
-            'foo-0.1/PKG-INFO',
-            'foo-0.1/README.rst',
-            'foo-0.1/pyproject.toml',
-            'foo-0.1/setup.cfg',
-            'foo-0.1/src',
-            'foo-0.1/src/foo',
-            'foo-0.1/src/foo/__init__.py',
-            'foo-0.1/src/foo/__init__.pyi',
-            'foo-0.1/src/foo/cli.py',
-            'foo-0.1/src/foo/data.txt',
-            'foo-0.1/src/foo/py.typed',
-            'foo-0.1/src/foo.egg-info',
-            'foo-0.1/src/foo.egg-info/PKG-INFO',
-            'foo-0.1/src/foo.egg-info/SOURCES.txt',
-            'foo-0.1/src/foo.egg-info/dependency_links.txt',
-            'foo-0.1/src/foo.egg-info/entry_points.txt',
-            'foo-0.1/src/foo.egg-info/requires.txt',
-            'foo-0.1/src/foo.egg-info/top_level.txt',
-            'foo-0.1/src/foo.egg-info/not-zip-safe',
-        }
-        assert wheel_contents == {
-            "foo/__init__.py",
-            "foo/__init__.pyi",  # include type information by default
-            "foo/cli.py",
-            "foo/data.txt",  # include_package_data defaults to True
-            "foo/py.typed",  # include type information by default
-            "foo-0.1.dist-info/licenses/LICENSE.txt",
-            "foo-0.1.dist-info/METADATA",
-            "foo-0.1.dist-info/WHEEL",
-            "foo-0.1.dist-info/entry_points.txt",
-            "foo-0.1.dist-info/top_level.txt",
-            "foo-0.1.dist-info/RECORD",
-        }
-        assert license == "---- placeholder MIT license ----"
-
-        for line in (
-            "Summary: This is a Python package",
-            "License: MIT",
-            "License-File: LICENSE.txt",
-            "Classifier: Intended Audience :: Developers",
-            "Requires-Dist: appdirs",
-            "Requires-Dist: " + str(Requirement('tomli>=1 ; extra == "all"')),
-            "Requires-Dist: "
-            + str(Requirement('importlib; python_version=="2.6" and extra =="all"')),
-        ):
-            assert line in metadata, (line, metadata)
-
-        assert metadata.strip().endswith("This is a ``README``")
-        assert epoints.strip() == "[console_scripts]\nfoo = foo.cli:main"
-
-    def test_static_metadata_in_pyproject_config(self, tmpdir):
-        # Make sure static metadata in pyproject.toml is not overwritten by setup.py
-        # as required by PEP 621
-        files = {
-            'pyproject.toml': DALS(
-                """
-                [build-system]
-                requires = ["setuptools", "wheel"]
-                build-backend = "setuptools.build_meta"
-
-                [project]
-                name = "foo"
-                description = "This is a Python package"
-                version = "42"
-                dependencies = ["six"]
-                """
-            ),
-            'hello.py': DALS(
-                """
-                def run():
-                    print('hello')
-                """
-            ),
-            'setup.py': DALS(
-                """
-                __import__('setuptools').setup(
-                    name='bar',
-                    version='13',
-                )
-                """
-            ),
-        }
-        build_backend = self.get_build_backend()
-        with tmpdir.as_cwd():
-            path.build(files)
-            sdist_path = build_backend.build_sdist("temp")
-            wheel_file = build_backend.build_wheel("temp")
-
-        assert (tmpdir / "temp/foo-42.tar.gz").exists()
-        assert (tmpdir / "temp/foo-42-py3-none-any.whl").exists()
-        assert not (tmpdir / "temp/bar-13.tar.gz").exists()
-        assert not (tmpdir / "temp/bar-42.tar.gz").exists()
-        assert not (tmpdir / "temp/foo-13.tar.gz").exists()
-        assert not (tmpdir / "temp/bar-13-py3-none-any.whl").exists()
-        assert not (tmpdir / "temp/bar-42-py3-none-any.whl").exists()
-        assert not (tmpdir / "temp/foo-13-py3-none-any.whl").exists()
-
-        with tarfile.open(os.path.join(tmpdir, "temp", sdist_path)) as tar:
-            pkg_info = str(tar.extractfile('foo-42/PKG-INFO').read(), "utf-8")
-            members = tar.getnames()
-            assert "bar-13/PKG-INFO" not in members
-
-        with ZipFile(os.path.join(tmpdir, "temp", wheel_file)) as zipfile:
-            metadata = str(zipfile.read("foo-42.dist-info/METADATA"), "utf-8")
-            members = zipfile.namelist()
-            assert "bar-13.dist-info/METADATA" not in members
-
-        for file in pkg_info, metadata:
-            for line in ("Name: foo", "Version: 42"):
-                assert line in file
-            for line in ("Name: bar", "Version: 13"):
-                assert line not in file
-
-    def test_build_sdist(self, build_backend):
-        dist_dir = os.path.abspath('pip-sdist')
-        os.makedirs(dist_dir)
-        sdist_name = build_backend.build_sdist(dist_dir)
-
-        assert os.path.isfile(os.path.join(dist_dir, sdist_name))
-
-    def test_prepare_metadata_for_build_wheel(self, build_backend):
-        dist_dir = os.path.abspath('pip-dist-info')
-        os.makedirs(dist_dir)
-
-        dist_info = build_backend.prepare_metadata_for_build_wheel(dist_dir)
-
-        assert os.path.isfile(os.path.join(dist_dir, dist_info, 'METADATA'))
-
-    def test_prepare_metadata_inplace(self, build_backend):
-        """
-        Some users might pass metadata_directory pre-populated with `.tox` or `.venv`.
-        See issue #3523.
-        """
-        for pre_existing in [
-            ".tox/python/lib/python3.10/site-packages/attrs-22.1.0.dist-info",
-            ".tox/python/lib/python3.10/site-packages/autocommand-2.2.1.dist-info",
-            ".nox/python/lib/python3.10/site-packages/build-0.8.0.dist-info",
-            ".venv/python3.10/site-packages/click-8.1.3.dist-info",
-            "venv/python3.10/site-packages/distlib-0.3.5.dist-info",
-            "env/python3.10/site-packages/docutils-0.19.dist-info",
-        ]:
-            os.makedirs(pre_existing, exist_ok=True)
-        dist_info = build_backend.prepare_metadata_for_build_wheel(".")
-        assert os.path.isfile(os.path.join(dist_info, 'METADATA'))
-
-    def test_build_sdist_explicit_dist(self, build_backend):
-        # explicitly specifying the dist folder should work
-        # the folder sdist_directory and the ``--dist-dir`` can be the same
-        dist_dir = os.path.abspath('dist')
-        sdist_name = build_backend.build_sdist(dist_dir)
-        assert os.path.isfile(os.path.join(dist_dir, sdist_name))
-
-    def test_build_sdist_version_change(self, build_backend):
-        sdist_into_directory = os.path.abspath("out_sdist")
-        os.makedirs(sdist_into_directory)
-
-        sdist_name = build_backend.build_sdist(sdist_into_directory)
-        assert os.path.isfile(os.path.join(sdist_into_directory, sdist_name))
-
-        # if the setup.py changes subsequent call of the build meta
-        # should still succeed, given the
-        # sdist_directory the frontend specifies is empty
-        setup_loc = os.path.abspath("setup.py")
-        if not os.path.exists(setup_loc):
-            setup_loc = os.path.abspath("setup.cfg")
-
-        with open(setup_loc, 'rt', encoding="utf-8") as file_handler:
-            content = file_handler.read()
-        with open(setup_loc, 'wt', encoding="utf-8") as file_handler:
-            file_handler.write(content.replace("version='0.0.0'", "version='0.0.1'"))
-
-        shutil.rmtree(sdist_into_directory)
-        os.makedirs(sdist_into_directory)
-
-        sdist_name = build_backend.build_sdist("out_sdist")
-        assert os.path.isfile(os.path.join(os.path.abspath("out_sdist"), sdist_name))
-
-    def test_build_sdist_pyproject_toml_exists(self, tmpdir_cwd):
-        files = {
-            'setup.py': DALS(
-                """
-                __import__('setuptools').setup(
-                    name='foo',
-                    version='0.0.0',
-                    py_modules=['hello']
-                )"""
-            ),
-            'hello.py': '',
-            'pyproject.toml': DALS(
-                """
-                [build-system]
-                requires = ["setuptools", "wheel"]
-                build-backend = "setuptools.build_meta"
-                """
-            ),
-        }
-        path.build(files)
-        build_backend = self.get_build_backend()
-        targz_path = build_backend.build_sdist("temp")
-        with tarfile.open(os.path.join("temp", targz_path)) as tar:
-            assert any('pyproject.toml' in name for name in tar.getnames())
-
-    def test_build_sdist_setup_py_exists(self, tmpdir_cwd):
-        # If build_sdist is called from a script other than setup.py,
-        # ensure setup.py is included
-        path.build(defns[0])
-
-        build_backend = self.get_build_backend()
-        targz_path = build_backend.build_sdist("temp")
-        with tarfile.open(os.path.join("temp", targz_path)) as tar:
-            assert any('setup.py' in name for name in tar.getnames())
-
-    def test_build_sdist_setup_py_manifest_excluded(self, tmpdir_cwd):
-        # Ensure that MANIFEST.in can exclude setup.py
-        files = {
-            'setup.py': DALS(
-                """
-        __import__('setuptools').setup(
-            name='foo',
-            version='0.0.0',
-            py_modules=['hello']
-        )"""
-            ),
-            'hello.py': '',
-            'MANIFEST.in': DALS(
-                """
-        exclude setup.py
-        """
-            ),
-        }
-
-        path.build(files)
-
-        build_backend = self.get_build_backend()
-        targz_path = build_backend.build_sdist("temp")
-        with tarfile.open(os.path.join("temp", targz_path)) as tar:
-            assert not any('setup.py' in name for name in tar.getnames())
-
-    def test_build_sdist_builds_targz_even_if_zip_indicated(self, tmpdir_cwd):
-        files = {
-            'setup.py': DALS(
-                """
-                __import__('setuptools').setup(
-                    name='foo',
-                    version='0.0.0',
-                    py_modules=['hello']
-                )"""
-            ),
-            'hello.py': '',
-            'setup.cfg': DALS(
-                """
-                [sdist]
-                formats=zip
-                """
-            ),
-        }
-
-        path.build(files)
-
-        build_backend = self.get_build_backend()
-        build_backend.build_sdist("temp")
-
-    _relative_path_import_files = {
-        'setup.py': DALS(
-            """
-            __import__('setuptools').setup(
-                name='foo',
-                version=__import__('hello').__version__,
-                py_modules=['hello']
-            )"""
-        ),
-        'hello.py': '__version__ = "0.0.0"',
-        'setup.cfg': DALS(
-            """
-            [sdist]
-            formats=zip
-            """
-        ),
-    }
-
-    def test_build_sdist_relative_path_import(self, tmpdir_cwd):
-        path.build(self._relative_path_import_files)
-        build_backend = self.get_build_backend()
-        with pytest.raises(ImportError, match="^No module named 'hello'$"):
-            build_backend.build_sdist("temp")
-
-    _simple_pyproject_example = {
-        "pyproject.toml": DALS(
-            """
-            [project]
-            name = "proj"
-            version = "42"
-            """
-        ),
-        "src": {"proj": {"__init__.py": ""}},
-    }
-
-    def _assert_link_tree(self, parent_dir):
-        """All files in the directory should be either links or hard links"""
-        files = list(Path(parent_dir).glob("**/*"))
-        assert files  # Should not be empty
-        for file in files:
-            assert file.is_symlink() or os.stat(file).st_nlink > 0
-
-    def test_editable_without_config_settings(self, tmpdir_cwd):
-        """
-        Sanity check to ensure tests with --mode=strict are different from the ones
-        without --mode.
-
-        --mode=strict should create a local directory with a package tree.
-        The directory should not get created otherwise.
-        """
-        path.build(self._simple_pyproject_example)
-        build_backend = self.get_build_backend()
-        assert not Path("build").exists()
-        build_backend.build_editable("temp")
-        assert not Path("build").exists()
-
-    def test_build_wheel_inplace(self, tmpdir_cwd):
-        config_settings = {"--build-option": ["build_ext", "--inplace"]}
-        path.build(self._simple_pyproject_example)
-        build_backend = self.get_build_backend()
-        assert not Path("build").exists()
-        Path("build").mkdir()
-        build_backend.prepare_metadata_for_build_wheel("build", config_settings)
-        build_backend.build_wheel("build", config_settings)
-        assert Path("build/proj-42-py3-none-any.whl").exists()
-
-    @pytest.mark.parametrize("config_settings", [{"editable-mode": "strict"}])
-    def test_editable_with_config_settings(self, tmpdir_cwd, config_settings):
-        path.build({**self._simple_pyproject_example, '_meta': {}})
-        assert not Path("build").exists()
-        build_backend = self.get_build_backend()
-        build_backend.prepare_metadata_for_build_editable("_meta", config_settings)
-        build_backend.build_editable("temp", config_settings, "_meta")
-        self._assert_link_tree(next(Path("build").glob("__editable__.*")))
-
-    @pytest.mark.parametrize(
-        ("setup_literal", "requirements"),
-        [
-            ("'foo'", ['foo']),
-            ("['foo']", ['foo']),
-            (r"'foo\n'", ['foo']),
-            (r"'foo\n\n'", ['foo']),
-            ("['foo', 'bar']", ['foo', 'bar']),
-            (r"'# Has a comment line\nfoo'", ['foo']),
-            (r"'foo # Has an inline comment'", ['foo']),
-            (r"'foo \\\n >=3.0'", ['foo>=3.0']),
-            (r"'foo\nbar'", ['foo', 'bar']),
-            (r"'foo\nbar\n'", ['foo', 'bar']),
-            (r"['foo\n', 'bar\n']", ['foo', 'bar']),
-        ],
-    )
-    @pytest.mark.parametrize('use_wheel', [True, False])
-    def test_setup_requires(self, setup_literal, requirements, use_wheel, tmpdir_cwd):
-        files = {
-            'setup.py': DALS(
-                """
-                from setuptools import setup
-
-                setup(
-                    name="qux",
-                    version="0.0.0",
-                    py_modules=["hello"],
-                    setup_requires={setup_literal},
-                )
-            """
-            ).format(setup_literal=setup_literal),
-            'hello.py': DALS(
-                """
-            def run():
-                print('hello')
-            """
-            ),
-        }
-
-        path.build(files)
-
-        build_backend = self.get_build_backend()
-
-        if use_wheel:
-            get_requires = build_backend.get_requires_for_build_wheel
-        else:
-            get_requires = build_backend.get_requires_for_build_sdist
-
-        # Ensure that the build requirements are properly parsed
-        expected = sorted(requirements)
-        actual = get_requires()
-
-        assert expected == sorted(actual)
-
-    def test_setup_requires_with_auto_discovery(self, tmpdir_cwd):
-        # Make sure patches introduced to retrieve setup_requires don't accidentally
-        # activate auto-discovery and cause problems due to the incomplete set of
-        # attributes passed to MinimalDistribution
-        files = {
-            'pyproject.toml': DALS(
-                """
-                [project]
-                name = "proj"
-                version = "42"
-            """
-            ),
-            "setup.py": DALS(
-                """
-                __import__('setuptools').setup(
-                    setup_requires=["foo"],
-                    py_modules = ["hello", "world"]
-                )
-            """
-            ),
-            'hello.py': "'hello'",
-            'world.py': "'world'",
-        }
-        path.build(files)
-        build_backend = self.get_build_backend()
-        setup_requires = build_backend.get_requires_for_build_wheel()
-        assert setup_requires == ["foo"]
-
-    def test_dont_install_setup_requires(self, tmpdir_cwd):
-        files = {
-            'setup.py': DALS(
-                """
-                        from setuptools import setup
-
-                        setup(
-                            name="qux",
-                            version="0.0.0",
-                            py_modules=["hello"],
-                            setup_requires=["does-not-exist >99"],
-                        )
-                    """
-            ),
-            'hello.py': DALS(
-                """
-                    def run():
-                        print('hello')
-                    """
-            ),
-        }
-
-        path.build(files)
-
-        build_backend = self.get_build_backend()
-
-        dist_dir = os.path.abspath('pip-dist-info')
-        os.makedirs(dist_dir)
-
-        # does-not-exist can't be satisfied, so if it attempts to install
-        # setup_requires, it will fail.
-        build_backend.prepare_metadata_for_build_wheel(dist_dir)
-
-    _sys_argv_0_passthrough = {
-        'setup.py': DALS(
-            """
-            import os
-            import sys
-
-            __import__('setuptools').setup(
-                name='foo',
-                version='0.0.0',
-            )
-
-            sys_argv = os.path.abspath(sys.argv[0])
-            file_path = os.path.abspath('setup.py')
-            assert sys_argv == file_path
-            """
-        )
-    }
-
-    def test_sys_argv_passthrough(self, tmpdir_cwd):
-        path.build(self._sys_argv_0_passthrough)
-        build_backend = self.get_build_backend()
-        with pytest.raises(AssertionError):
-            build_backend.build_sdist("temp")
-
-    _setup_py_file_abspath = {
-        'setup.py': DALS(
-            """
-            import os
-            assert os.path.isabs(__file__)
-            __import__('setuptools').setup(
-                name='foo',
-                version='0.0.0',
-                py_modules=['hello'],
-                setup_requires=['six'],
-            )
-            """
-        )
-    }
-
-    def test_setup_py_file_abspath(self, tmpdir_cwd):
-        path.build(self._setup_py_file_abspath)
-        build_backend = self.get_build_backend()
-        build_backend.build_sdist("temp")
-
-    @pytest.mark.parametrize('build_hook', ('build_sdist', 'build_wheel'))
-    def test_build_with_empty_setuppy(self, build_backend, build_hook):
-        files = {'setup.py': ''}
-        path.build(files)
-
-        msg = re.escape('No distribution was found.')
-        with pytest.raises(ValueError, match=msg):
-            getattr(build_backend, build_hook)("temp")
-
-
-class TestBuildMetaLegacyBackend(TestBuildMetaBackend):
-    backend_name = 'setuptools.build_meta:__legacy__'
-
-    # build_meta_legacy-specific tests
-    def test_build_sdist_relative_path_import(self, tmpdir_cwd):
-        # This must fail in build_meta, but must pass in build_meta_legacy
-        path.build(self._relative_path_import_files)
-
-        build_backend = self.get_build_backend()
-        build_backend.build_sdist("temp")
-
-    def test_sys_argv_passthrough(self, tmpdir_cwd):
-        path.build(self._sys_argv_0_passthrough)
-
-        build_backend = self.get_build_backend()
-        build_backend.build_sdist("temp")
-
-
-def test_legacy_editable_install(venv, tmpdir, tmpdir_cwd):
-    pyproject = """
-    [build-system]
-    requires = ["setuptools"]
-    build-backend = "setuptools.build_meta"
-    [project]
-    name = "myproj"
-    version = "42"
-    """
-    path.build({"pyproject.toml": DALS(pyproject), "mymod.py": ""})
-
-    # First: sanity check
-    cmd = ["pip", "install", "--no-build-isolation", "-e", "."]
-    output = venv.run(cmd, cwd=tmpdir).lower()
-    assert "running setup.py develop for myproj" not in output
-    assert "created wheel for myproj" in output
-
-    # Then: real test
-    env = {**os.environ, "SETUPTOOLS_ENABLE_FEATURES": "legacy-editable"}
-    cmd = ["pip", "install", "--no-build-isolation", "-e", "."]
-    output = venv.run(cmd, cwd=tmpdir, env=env).lower()
-    assert "running setup.py develop for myproj" in output
-
-
-@pytest.mark.filterwarnings("ignore::setuptools.SetuptoolsDeprecationWarning")
-def test_sys_exit_0_in_setuppy(monkeypatch, tmp_path):
-    """Setuptools should be resilient to setup.py with ``sys.exit(0)`` (#3973)."""
-    monkeypatch.chdir(tmp_path)
-    setuppy = """
-        import sys, setuptools
-        setuptools.setup(name='foo', version='0.0.0')
-        sys.exit(0)
-        """
-    (tmp_path / "setup.py").write_text(DALS(setuppy), encoding="utf-8")
-    backend = BuildBackend(backend_name="setuptools.build_meta")
-    assert backend.get_requires_for_build_wheel() == []
-
-
-def test_system_exit_in_setuppy(monkeypatch, tmp_path):
-    monkeypatch.chdir(tmp_path)
-    setuppy = "import sys; sys.exit('some error')"
-    (tmp_path / "setup.py").write_text(setuppy, encoding="utf-8")
-    with pytest.raises(SystemExit, match="some error"):
-        backend = BuildBackend(backend_name="setuptools.build_meta")
-        backend.get_requires_for_build_wheel()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_py.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_py.py
deleted file mode 100644
index 1e3a660..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_build_py.py
+++ /dev/null
@@ -1,480 +0,0 @@
-import os
-import shutil
-import stat
-import warnings
-from pathlib import Path
-from unittest.mock import Mock
-
-import jaraco.path
-import pytest
-
-from setuptools import SetuptoolsDeprecationWarning
-from setuptools.dist import Distribution
-
-from .textwrap import DALS
-
-
-def test_directories_in_package_data_glob(tmpdir_cwd):
-    """
-    Directories matching the glob in package_data should
-    not be included in the package data.
-
-    Regression test for #261.
-    """
-    dist = Distribution(
-        dict(
-            script_name='setup.py',
-            script_args=['build_py'],
-            packages=[''],
-            package_data={'': ['path/*']},
-        )
-    )
-    os.makedirs('path/subpath')
-    dist.parse_command_line()
-    dist.run_commands()
-
-
-def test_recursive_in_package_data_glob(tmpdir_cwd):
-    """
-    Files matching recursive globs (**) in package_data should
-    be included in the package data.
-
-    #1806
-    """
-    dist = Distribution(
-        dict(
-            script_name='setup.py',
-            script_args=['build_py'],
-            packages=[''],
-            package_data={'': ['path/**/data']},
-        )
-    )
-    os.makedirs('path/subpath/subsubpath')
-    open('path/subpath/subsubpath/data', 'wb').close()
-
-    dist.parse_command_line()
-    dist.run_commands()
-
-    assert stat.S_ISREG(os.stat('build/lib/path/subpath/subsubpath/data').st_mode), (
-        "File is not included"
-    )
-
-
-def test_read_only(tmpdir_cwd):
-    """
-    Ensure read-only flag is not preserved in copy
-    for package modules and package data, as that
-    causes problems with deleting read-only files on
-    Windows.
-
-    #1451
-    """
-    dist = Distribution(
-        dict(
-            script_name='setup.py',
-            script_args=['build_py'],
-            packages=['pkg'],
-            package_data={'pkg': ['data.dat']},
-        )
-    )
-    os.makedirs('pkg')
-    open('pkg/__init__.py', 'wb').close()
-    open('pkg/data.dat', 'wb').close()
-    os.chmod('pkg/__init__.py', stat.S_IREAD)
-    os.chmod('pkg/data.dat', stat.S_IREAD)
-    dist.parse_command_line()
-    dist.run_commands()
-    shutil.rmtree('build')
-
-
-@pytest.mark.xfail(
-    'platform.system() == "Windows"',
-    reason="On Windows, files do not have executable bits",
-    raises=AssertionError,
-    strict=True,
-)
-def test_executable_data(tmpdir_cwd):
-    """
-    Ensure executable bit is preserved in copy for
-    package data, as users rely on it for scripts.
-
-    #2041
-    """
-    dist = Distribution(
-        dict(
-            script_name='setup.py',
-            script_args=['build_py'],
-            packages=['pkg'],
-            package_data={'pkg': ['run-me']},
-        )
-    )
-    os.makedirs('pkg')
-    open('pkg/__init__.py', 'wb').close()
-    open('pkg/run-me', 'wb').close()
-    os.chmod('pkg/run-me', 0o700)
-
-    dist.parse_command_line()
-    dist.run_commands()
-
-    assert os.stat('build/lib/pkg/run-me').st_mode & stat.S_IEXEC, (
-        "Script is not executable"
-    )
-
-
-EXAMPLE_WITH_MANIFEST = {
-    "setup.cfg": DALS(
-        """
-        [metadata]
-        name = mypkg
-        version = 42
-
-        [options]
-        include_package_data = True
-        packages = find:
-
-        [options.packages.find]
-        exclude = *.tests*
-        """
-    ),
-    "mypkg": {
-        "__init__.py": "",
-        "resource_file.txt": "",
-        "tests": {
-            "__init__.py": "",
-            "test_mypkg.py": "",
-            "test_file.txt": "",
-        },
-    },
-    "MANIFEST.in": DALS(
-        """
-        global-include *.py *.txt
-        global-exclude *.py[cod]
-        prune dist
-        prune build
-        prune *.egg-info
-        """
-    ),
-}
-
-
-def test_excluded_subpackages(tmpdir_cwd):
-    jaraco.path.build(EXAMPLE_WITH_MANIFEST)
-    dist = Distribution({"script_name": "%PEP 517%"})
-    dist.parse_config_files()
-
-    build_py = dist.get_command_obj("build_py")
-
-    msg = r"Python recognizes 'mypkg\.tests' as an importable package"
-    with pytest.warns(SetuptoolsDeprecationWarning, match=msg):
-        # TODO: To fix #3260 we need some transition period to deprecate the
-        # existing behavior of `include_package_data`. After the transition, we
-        # should remove the warning and fix the behavior.
-
-        if os.getenv("SETUPTOOLS_USE_DISTUTILS") == "stdlib":
-            # pytest.warns reset the warning filter temporarily
-            # https://github.com/pytest-dev/pytest/issues/4011#issuecomment-423494810
-            warnings.filterwarnings(
-                "ignore",
-                "'encoding' argument not specified",
-                module="distutils.text_file",
-                # This warning is already fixed in pypa/distutils but not in stdlib
-            )
-
-        build_py.finalize_options()
-        build_py.run()
-
-    build_dir = Path(dist.get_command_obj("build_py").build_lib)
-    assert (build_dir / "mypkg/__init__.py").exists()
-    assert (build_dir / "mypkg/resource_file.txt").exists()
-
-    # Setuptools is configured to ignore `mypkg.tests`, therefore the following
-    # files/dirs should not be included in the distribution.
-    for f in [
-        "mypkg/tests/__init__.py",
-        "mypkg/tests/test_mypkg.py",
-        "mypkg/tests/test_file.txt",
-        "mypkg/tests",
-    ]:
-        with pytest.raises(AssertionError):
-            # TODO: Enforce the following assertion once #3260 is fixed
-            # (remove context manager and the following xfail).
-            assert not (build_dir / f).exists()
-
-    pytest.xfail("#3260")
-
-
-@pytest.mark.filterwarnings("ignore::setuptools.SetuptoolsDeprecationWarning")
-def test_existing_egg_info(tmpdir_cwd, monkeypatch):
-    """When provided with the ``existing_egg_info_dir`` attribute, build_py should not
-    attempt to run egg_info again.
-    """
-    # == Pre-condition ==
-    # Generate an egg-info dir
-    jaraco.path.build(EXAMPLE_WITH_MANIFEST)
-    dist = Distribution({"script_name": "%PEP 517%"})
-    dist.parse_config_files()
-    assert dist.include_package_data
-
-    egg_info = dist.get_command_obj("egg_info")
-    dist.run_command("egg_info")
-    egg_info_dir = next(Path(egg_info.egg_base).glob("*.egg-info"))
-    assert egg_info_dir.is_dir()
-
-    # == Setup ==
-    build_py = dist.get_command_obj("build_py")
-    build_py.finalize_options()
-    egg_info = dist.get_command_obj("egg_info")
-    egg_info_run = Mock(side_effect=egg_info.run)
-    monkeypatch.setattr(egg_info, "run", egg_info_run)
-
-    # == Remove caches ==
-    # egg_info is called when build_py looks for data_files, which gets cached.
-    # We need to ensure it is not cached yet, otherwise it may impact on the tests
-    build_py.__dict__.pop('data_files', None)
-    dist.reinitialize_command(egg_info)
-
-    # == Sanity check ==
-    # Ensure that if existing_egg_info is not given, build_py attempts to run egg_info
-    build_py.existing_egg_info_dir = None
-    build_py.run()
-    egg_info_run.assert_called()
-
-    # == Remove caches ==
-    egg_info_run.reset_mock()
-    build_py.__dict__.pop('data_files', None)
-    dist.reinitialize_command(egg_info)
-
-    # == Actual test ==
-    # Ensure that if existing_egg_info_dir is given, egg_info doesn't run
-    build_py.existing_egg_info_dir = egg_info_dir
-    build_py.run()
-    egg_info_run.assert_not_called()
-    assert build_py.data_files
-
-    # Make sure the list of outputs is actually OK
-    outputs = map(lambda x: x.replace(os.sep, "/"), build_py.get_outputs())
-    assert outputs
-    example = str(Path(build_py.build_lib, "mypkg/__init__.py")).replace(os.sep, "/")
-    assert example in outputs
-
-
-EXAMPLE_ARBITRARY_MAPPING = {
-    "pyproject.toml": DALS(
-        """
-        [project]
-        name = "mypkg"
-        version = "42"
-
-        [tool.setuptools]
-        packages = ["mypkg", "mypkg.sub1", "mypkg.sub2", "mypkg.sub2.nested"]
-
-        [tool.setuptools.package-dir]
-        "" = "src"
-        "mypkg.sub2" = "src/mypkg/_sub2"
-        "mypkg.sub2.nested" = "other"
-        """
-    ),
-    "src": {
-        "mypkg": {
-            "__init__.py": "",
-            "resource_file.txt": "",
-            "sub1": {
-                "__init__.py": "",
-                "mod1.py": "",
-            },
-            "_sub2": {
-                "mod2.py": "",
-            },
-        },
-    },
-    "other": {
-        "__init__.py": "",
-        "mod3.py": "",
-    },
-    "MANIFEST.in": DALS(
-        """
-        global-include *.py *.txt
-        global-exclude *.py[cod]
-        """
-    ),
-}
-
-
-def test_get_outputs(tmpdir_cwd):
-    jaraco.path.build(EXAMPLE_ARBITRARY_MAPPING)
-    dist = Distribution({"script_name": "%test%"})
-    dist.parse_config_files()
-
-    build_py = dist.get_command_obj("build_py")
-    build_py.editable_mode = True
-    build_py.ensure_finalized()
-    build_lib = build_py.build_lib.replace(os.sep, "/")
-    outputs = {x.replace(os.sep, "/") for x in build_py.get_outputs()}
-    assert outputs == {
-        f"{build_lib}/mypkg/__init__.py",
-        f"{build_lib}/mypkg/resource_file.txt",
-        f"{build_lib}/mypkg/sub1/__init__.py",
-        f"{build_lib}/mypkg/sub1/mod1.py",
-        f"{build_lib}/mypkg/sub2/mod2.py",
-        f"{build_lib}/mypkg/sub2/nested/__init__.py",
-        f"{build_lib}/mypkg/sub2/nested/mod3.py",
-    }
-    mapping = {
-        k.replace(os.sep, "/"): v.replace(os.sep, "/")
-        for k, v in build_py.get_output_mapping().items()
-    }
-    assert mapping == {
-        f"{build_lib}/mypkg/__init__.py": "src/mypkg/__init__.py",
-        f"{build_lib}/mypkg/resource_file.txt": "src/mypkg/resource_file.txt",
-        f"{build_lib}/mypkg/sub1/__init__.py": "src/mypkg/sub1/__init__.py",
-        f"{build_lib}/mypkg/sub1/mod1.py": "src/mypkg/sub1/mod1.py",
-        f"{build_lib}/mypkg/sub2/mod2.py": "src/mypkg/_sub2/mod2.py",
-        f"{build_lib}/mypkg/sub2/nested/__init__.py": "other/__init__.py",
-        f"{build_lib}/mypkg/sub2/nested/mod3.py": "other/mod3.py",
-    }
-
-
-class TestTypeInfoFiles:
-    PYPROJECTS = {
-        "default_pyproject": DALS(
-            """
-            [project]
-            name = "foo"
-            version = "1"
-            """
-        ),
-        "dont_include_package_data": DALS(
-            """
-            [project]
-            name = "foo"
-            version = "1"
-
-            [tool.setuptools]
-            include-package-data = false
-            """
-        ),
-        "exclude_type_info": DALS(
-            """
-            [project]
-            name = "foo"
-            version = "1"
-
-            [tool.setuptools]
-            include-package-data = false
-
-            [tool.setuptools.exclude-package-data]
-            "*" = ["py.typed", "*.pyi"]
-            """
-        ),
-    }
-
-    EXAMPLES = {
-        "simple_namespace": {
-            "directory_structure": {
-                "foo": {
-                    "bar.pyi": "",
-                    "py.typed": "",
-                    "__init__.py": "",
-                }
-            },
-            "expected_type_files": {"foo/bar.pyi", "foo/py.typed"},
-        },
-        "nested_inside_namespace": {
-            "directory_structure": {
-                "foo": {
-                    "bar": {
-                        "py.typed": "",
-                        "mod.pyi": "",
-                    }
-                }
-            },
-            "expected_type_files": {"foo/bar/mod.pyi", "foo/bar/py.typed"},
-        },
-        "namespace_nested_inside_regular": {
-            "directory_structure": {
-                "foo": {
-                    "namespace": {
-                        "foo.pyi": "",
-                    },
-                    "__init__.pyi": "",
-                    "py.typed": "",
-                }
-            },
-            "expected_type_files": {
-                "foo/namespace/foo.pyi",
-                "foo/__init__.pyi",
-                "foo/py.typed",
-            },
-        },
-    }
-
-    @pytest.mark.parametrize(
-        "pyproject",
-        [
-            "default_pyproject",
-            pytest.param(
-                "dont_include_package_data",
-                marks=pytest.mark.xfail(reason="pypa/setuptools#4350"),
-            ),
-        ],
-    )
-    @pytest.mark.parametrize("example", EXAMPLES.keys())
-    def test_type_files_included_by_default(self, tmpdir_cwd, pyproject, example):
-        structure = {
-            **self.EXAMPLES[example]["directory_structure"],
-            "pyproject.toml": self.PYPROJECTS[pyproject],
-        }
-        expected_type_files = self.EXAMPLES[example]["expected_type_files"]
-        jaraco.path.build(structure)
-
-        build_py = get_finalized_build_py()
-        outputs = get_outputs(build_py)
-        assert expected_type_files <= outputs
-
-    @pytest.mark.parametrize("pyproject", ["exclude_type_info"])
-    @pytest.mark.parametrize("example", EXAMPLES.keys())
-    def test_type_files_can_be_excluded(self, tmpdir_cwd, pyproject, example):
-        structure = {
-            **self.EXAMPLES[example]["directory_structure"],
-            "pyproject.toml": self.PYPROJECTS[pyproject],
-        }
-        expected_type_files = self.EXAMPLES[example]["expected_type_files"]
-        jaraco.path.build(structure)
-
-        build_py = get_finalized_build_py()
-        outputs = get_outputs(build_py)
-        assert expected_type_files.isdisjoint(outputs)
-
-    def test_stub_only_package(self, tmpdir_cwd):
-        structure = {
-            "pyproject.toml": DALS(
-                """
-                [project]
-                name = "foo-stubs"
-                version = "1"
-                """
-            ),
-            "foo-stubs": {"__init__.pyi": "", "bar.pyi": ""},
-        }
-        expected_type_files = {"foo-stubs/__init__.pyi", "foo-stubs/bar.pyi"}
-        jaraco.path.build(structure)
-
-        build_py = get_finalized_build_py()
-        outputs = get_outputs(build_py)
-        assert expected_type_files <= outputs
-
-
-def get_finalized_build_py(script_name="%build_py-test%"):
-    dist = Distribution({"script_name": script_name})
-    dist.parse_config_files()
-    build_py = dist.get_command_obj("build_py")
-    build_py.finalize_options()
-    return build_py
-
-
-def get_outputs(build_py):
-    build_dir = Path(build_py.build_lib)
-    return {
-        os.path.relpath(x, build_dir).replace(os.sep, "/")
-        for x in build_py.get_outputs()
-    }
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_config_discovery.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_config_discovery.py
deleted file mode 100644
index b5df820..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_config_discovery.py
+++ /dev/null
@@ -1,647 +0,0 @@
-import os
-import sys
-from configparser import ConfigParser
-from itertools import product
-from typing import cast
-
-import jaraco.path
-import pytest
-from path import Path
-
-import setuptools  # noqa: F401 # force distutils.core to be patched
-from setuptools.command.sdist import sdist
-from setuptools.discovery import find_package_path, find_parent_package
-from setuptools.dist import Distribution
-from setuptools.errors import PackageDiscoveryError
-
-from .contexts import quiet
-from .integration.helpers import get_sdist_members, get_wheel_members, run
-from .textwrap import DALS
-
-import distutils.core
-
-
-class TestFindParentPackage:
-    def test_single_package(self, tmp_path):
-        # find_parent_package should find a non-namespace parent package
-        (tmp_path / "src/namespace/pkg/nested").mkdir(exist_ok=True, parents=True)
-        (tmp_path / "src/namespace/pkg/nested/__init__.py").touch()
-        (tmp_path / "src/namespace/pkg/__init__.py").touch()
-        packages = ["namespace", "namespace.pkg", "namespace.pkg.nested"]
-        assert find_parent_package(packages, {"": "src"}, tmp_path) == "namespace.pkg"
-
-    def test_multiple_toplevel(self, tmp_path):
-        # find_parent_package should return null if the given list of packages does not
-        # have a single parent package
-        multiple = ["pkg", "pkg1", "pkg2"]
-        for name in multiple:
-            (tmp_path / f"src/{name}").mkdir(exist_ok=True, parents=True)
-            (tmp_path / f"src/{name}/__init__.py").touch()
-        assert find_parent_package(multiple, {"": "src"}, tmp_path) is None
-
-
-class TestDiscoverPackagesAndPyModules:
-    """Make sure discovered values for ``packages`` and ``py_modules`` work
-    similarly to explicit configuration for the simple scenarios.
-    """
-
-    OPTIONS = {
-        # Different options according to the circumstance being tested
-        "explicit-src": {"package_dir": {"": "src"}, "packages": ["pkg"]},
-        "variation-lib": {
-            "package_dir": {"": "lib"},  # variation of the source-layout
-        },
-        "explicit-flat": {"packages": ["pkg"]},
-        "explicit-single_module": {"py_modules": ["pkg"]},
-        "explicit-namespace": {"packages": ["ns", "ns.pkg"]},
-        "automatic-src": {},
-        "automatic-flat": {},
-        "automatic-single_module": {},
-        "automatic-namespace": {},
-    }
-    FILES = {
-        "src": ["src/pkg/__init__.py", "src/pkg/main.py"],
-        "lib": ["lib/pkg/__init__.py", "lib/pkg/main.py"],
-        "flat": ["pkg/__init__.py", "pkg/main.py"],
-        "single_module": ["pkg.py"],
-        "namespace": ["ns/pkg/__init__.py"],
-    }
-
-    def _get_info(self, circumstance):
-        _, _, layout = circumstance.partition("-")
-        files = self.FILES[layout]
-        options = self.OPTIONS[circumstance]
-        return files, options
-
-    @pytest.mark.parametrize("circumstance", OPTIONS.keys())
-    def test_sdist_filelist(self, tmp_path, circumstance):
-        files, options = self._get_info(circumstance)
-        _populate_project_dir(tmp_path, files, options)
-
-        _, cmd = _run_sdist_programatically(tmp_path, options)
-
-        manifest = [f.replace(os.sep, "/") for f in cmd.filelist.files]
-        for file in files:
-            assert any(f.endswith(file) for f in manifest)
-
-    @pytest.mark.parametrize("circumstance", OPTIONS.keys())
-    def test_project(self, tmp_path, circumstance):
-        files, options = self._get_info(circumstance)
-        _populate_project_dir(tmp_path, files, options)
-
-        # Simulate a pre-existing `build` directory
-        (tmp_path / "build").mkdir()
-        (tmp_path / "build/lib").mkdir()
-        (tmp_path / "build/bdist.linux-x86_64").mkdir()
-        (tmp_path / "build/bdist.linux-x86_64/file.py").touch()
-        (tmp_path / "build/lib/__init__.py").touch()
-        (tmp_path / "build/lib/file.py").touch()
-        (tmp_path / "dist").mkdir()
-        (tmp_path / "dist/file.py").touch()
-
-        _run_build(tmp_path)
-
-        sdist_files = get_sdist_members(next(tmp_path.glob("dist/*.tar.gz")))
-        print("~~~~~ sdist_members ~~~~~")
-        print('\n'.join(sdist_files))
-        assert sdist_files >= set(files)
-
-        wheel_files = get_wheel_members(next(tmp_path.glob("dist/*.whl")))
-        print("~~~~~ wheel_members ~~~~~")
-        print('\n'.join(wheel_files))
-        orig_files = {f.replace("src/", "").replace("lib/", "") for f in files}
-        assert wheel_files >= orig_files
-
-        # Make sure build files are not included by mistake
-        for file in wheel_files:
-            assert "build" not in files
-            assert "dist" not in files
-
-    PURPOSEFULLY_EMPY = {
-        "setup.cfg": DALS(
-            """
-            [metadata]
-            name = myproj
-            version = 0.0.0
-
-            [options]
-            {param} =
-            """
-        ),
-        "setup.py": DALS(
-            """
-            __import__('setuptools').setup(
-                name="myproj",
-                version="0.0.0",
-                {param}=[]
-            )
-            """
-        ),
-        "pyproject.toml": DALS(
-            """
-            [build-system]
-            requires = []
-            build-backend = 'setuptools.build_meta'
-
-            [project]
-            name = "myproj"
-            version = "0.0.0"
-
-            [tool.setuptools]
-            {param} = []
-            """
-        ),
-        "template-pyproject.toml": DALS(
-            """
-            [build-system]
-            requires = []
-            build-backend = 'setuptools.build_meta'
-            """
-        ),
-    }
-
-    @pytest.mark.parametrize(
-        ("config_file", "param", "circumstance"),
-        product(
-            ["setup.cfg", "setup.py", "pyproject.toml"],
-            ["packages", "py_modules"],
-            FILES.keys(),
-        ),
-    )
-    def test_purposefully_empty(self, tmp_path, config_file, param, circumstance):
-        files = self.FILES[circumstance] + ["mod.py", "other.py", "src/pkg/__init__.py"]
-        _populate_project_dir(tmp_path, files, {})
-
-        if config_file == "pyproject.toml":
-            template_param = param.replace("_", "-")
-        else:
-            # Make sure build works with or without setup.cfg
-            pyproject = self.PURPOSEFULLY_EMPY["template-pyproject.toml"]
-            (tmp_path / "pyproject.toml").write_text(pyproject, encoding="utf-8")
-            template_param = param
-
-        config = self.PURPOSEFULLY_EMPY[config_file].format(param=template_param)
-        (tmp_path / config_file).write_text(config, encoding="utf-8")
-
-        dist = _get_dist(tmp_path, {})
-        # When either parameter package or py_modules is an empty list,
-        # then there should be no discovery
-        assert getattr(dist, param) == []
-        other = {"py_modules": "packages", "packages": "py_modules"}[param]
-        assert getattr(dist, other) is None
-
-    @pytest.mark.parametrize(
-        ("extra_files", "pkgs"),
-        [
-            (["venv/bin/simulate_venv"], {"pkg"}),
-            (["pkg-stubs/__init__.pyi"], {"pkg", "pkg-stubs"}),
-            (["other-stubs/__init__.pyi"], {"pkg", "other-stubs"}),
-            (
-                # Type stubs can also be namespaced
-                ["namespace-stubs/pkg/__init__.pyi"],
-                {"pkg", "namespace-stubs", "namespace-stubs.pkg"},
-            ),
-            (
-                # Just the top-level package can have `-stubs`, ignore nested ones
-                ["namespace-stubs/pkg-stubs/__init__.pyi"],
-                {"pkg", "namespace-stubs"},
-            ),
-            (["_hidden/file.py"], {"pkg"}),
-            (["news/finalize.py"], {"pkg"}),
-        ],
-    )
-    def test_flat_layout_with_extra_files(self, tmp_path, extra_files, pkgs):
-        files = self.FILES["flat"] + extra_files
-        _populate_project_dir(tmp_path, files, {})
-        dist = _get_dist(tmp_path, {})
-        assert set(dist.packages) == pkgs
-
-    @pytest.mark.parametrize(
-        "extra_files",
-        [
-            ["other/__init__.py"],
-            ["other/finalize.py"],
-        ],
-    )
-    def test_flat_layout_with_dangerous_extra_files(self, tmp_path, extra_files):
-        files = self.FILES["flat"] + extra_files
-        _populate_project_dir(tmp_path, files, {})
-        with pytest.raises(PackageDiscoveryError, match="multiple (packages|modules)"):
-            _get_dist(tmp_path, {})
-
-    def test_flat_layout_with_single_module(self, tmp_path):
-        files = self.FILES["single_module"] + ["invalid-module-name.py"]
-        _populate_project_dir(tmp_path, files, {})
-        dist = _get_dist(tmp_path, {})
-        assert set(dist.py_modules) == {"pkg"}
-
-    def test_flat_layout_with_multiple_modules(self, tmp_path):
-        files = self.FILES["single_module"] + ["valid_module_name.py"]
-        _populate_project_dir(tmp_path, files, {})
-        with pytest.raises(PackageDiscoveryError, match="multiple (packages|modules)"):
-            _get_dist(tmp_path, {})
-
-    def test_py_modules_when_wheel_dir_is_cwd(self, tmp_path):
-        """Regression for issue 3692"""
-        from setuptools import build_meta
-
-        pyproject = '[project]\nname = "test"\nversion = "1"'
-        (tmp_path / "pyproject.toml").write_text(DALS(pyproject), encoding="utf-8")
-        (tmp_path / "foo.py").touch()
-        with jaraco.path.DirectoryStack().context(tmp_path):
-            build_meta.build_wheel(".")
-        # Ensure py_modules are found
-        wheel_files = get_wheel_members(next(tmp_path.glob("*.whl")))
-        assert "foo.py" in wheel_files
-
-
-class TestNoConfig:
-    DEFAULT_VERSION = "0.0.0"  # Default version given by setuptools
-
-    EXAMPLES = {
-        "pkg1": ["src/pkg1.py"],
-        "pkg2": ["src/pkg2/__init__.py"],
-        "pkg3": ["src/pkg3/__init__.py", "src/pkg3-stubs/__init__.py"],
-        "pkg4": ["pkg4/__init__.py", "pkg4-stubs/__init__.py"],
-        "ns.nested.pkg1": ["src/ns/nested/pkg1/__init__.py"],
-        "ns.nested.pkg2": ["ns/nested/pkg2/__init__.py"],
-    }
-
-    @pytest.mark.parametrize("example", EXAMPLES.keys())
-    def test_discover_name(self, tmp_path, example):
-        _populate_project_dir(tmp_path, self.EXAMPLES[example], {})
-        dist = _get_dist(tmp_path, {})
-        assert dist.get_name() == example
-
-    def test_build_with_discovered_name(self, tmp_path):
-        files = ["src/ns/nested/pkg/__init__.py"]
-        _populate_project_dir(tmp_path, files, {})
-        _run_build(tmp_path, "--sdist")
-        # Expected distribution file
-        dist_file = tmp_path / f"dist/ns_nested_pkg-{self.DEFAULT_VERSION}.tar.gz"
-        assert dist_file.is_file()
-
-
-class TestWithAttrDirective:
-    @pytest.mark.parametrize(
-        ("folder", "opts"),
-        [
-            ("src", {}),
-            ("lib", {"packages": "find:", "packages.find": {"where": "lib"}}),
-        ],
-    )
-    def test_setupcfg_metadata(self, tmp_path, folder, opts):
-        files = [f"{folder}/pkg/__init__.py", "setup.cfg"]
-        _populate_project_dir(tmp_path, files, opts)
-
-        config = (tmp_path / "setup.cfg").read_text(encoding="utf-8")
-        overwrite = {
-            folder: {"pkg": {"__init__.py": "version = 42"}},
-            "setup.cfg": "[metadata]\nversion = attr: pkg.version\n" + config,
-        }
-        jaraco.path.build(overwrite, prefix=tmp_path)
-
-        dist = _get_dist(tmp_path, {})
-        assert dist.get_name() == "pkg"
-        assert dist.get_version() == "42"
-        assert dist.package_dir
-        package_path = find_package_path("pkg", dist.package_dir, tmp_path)
-        assert os.path.exists(package_path)
-        assert folder in Path(package_path).parts()
-
-        _run_build(tmp_path, "--sdist")
-        dist_file = tmp_path / "dist/pkg-42.tar.gz"
-        assert dist_file.is_file()
-
-    def test_pyproject_metadata(self, tmp_path):
-        _populate_project_dir(tmp_path, ["src/pkg/__init__.py"], {})
-
-        overwrite = {
-            "src": {"pkg": {"__init__.py": "version = 42"}},
-            "pyproject.toml": (
-                "[project]\nname = 'pkg'\ndynamic = ['version']\n"
-                "[tool.setuptools.dynamic]\nversion = {attr = 'pkg.version'}\n"
-            ),
-        }
-        jaraco.path.build(overwrite, prefix=tmp_path)
-
-        dist = _get_dist(tmp_path, {})
-        assert dist.get_version() == "42"
-        assert dist.package_dir == {"": "src"}
-
-
-class TestWithCExtension:
-    def _simulate_package_with_extension(self, tmp_path):
-        # This example is based on: https://github.com/nucleic/kiwi/tree/1.4.0
-        files = [
-            "benchmarks/file.py",
-            "docs/Makefile",
-            "docs/requirements.txt",
-            "docs/source/conf.py",
-            "proj/header.h",
-            "proj/file.py",
-            "py/proj.cpp",
-            "py/other.cpp",
-            "py/file.py",
-            "py/py.typed",
-            "py/tests/test_proj.py",
-            "README.rst",
-        ]
-        _populate_project_dir(tmp_path, files, {})
-
-        setup_script = """
-            from setuptools import Extension, setup
-
-            ext_modules = [
-                Extension(
-                    "proj",
-                    ["py/proj.cpp", "py/other.cpp"],
-                    include_dirs=["."],
-                    language="c++",
-                ),
-            ]
-            setup(ext_modules=ext_modules)
-        """
-        (tmp_path / "setup.py").write_text(DALS(setup_script), encoding="utf-8")
-
-    def test_skip_discovery_with_setupcfg_metadata(self, tmp_path):
-        """Ensure that auto-discovery is not triggered when the project is based on
-        C-extensions only, for backward compatibility.
-        """
-        self._simulate_package_with_extension(tmp_path)
-
-        pyproject = """
-            [build-system]
-            requires = []
-            build-backend = 'setuptools.build_meta'
-        """
-        (tmp_path / "pyproject.toml").write_text(DALS(pyproject), encoding="utf-8")
-
-        setupcfg = """
-            [metadata]
-            name = proj
-            version = 42
-        """
-        (tmp_path / "setup.cfg").write_text(DALS(setupcfg), encoding="utf-8")
-
-        dist = _get_dist(tmp_path, {})
-        assert dist.get_name() == "proj"
-        assert dist.get_version() == "42"
-        assert dist.py_modules is None
-        assert dist.packages is None
-        assert len(dist.ext_modules) == 1
-        assert dist.ext_modules[0].name == "proj"
-
-    def test_dont_skip_discovery_with_pyproject_metadata(self, tmp_path):
-        """When opting-in to pyproject.toml metadata, auto-discovery will be active if
-        the package lists C-extensions, but does not configure py-modules or packages.
-
-        This way we ensure users with complex package layouts that would lead to the
-        discovery of multiple top-level modules/packages see errors and are forced to
-        explicitly set ``packages`` or ``py-modules``.
-        """
-        self._simulate_package_with_extension(tmp_path)
-
-        pyproject = """
-            [project]
-            name = 'proj'
-            version = '42'
-        """
-        (tmp_path / "pyproject.toml").write_text(DALS(pyproject), encoding="utf-8")
-        with pytest.raises(PackageDiscoveryError, match="multiple (packages|modules)"):
-            _get_dist(tmp_path, {})
-
-
-class TestWithPackageData:
-    def _simulate_package_with_data_files(self, tmp_path, src_root):
-        files = [
-            f"{src_root}/proj/__init__.py",
-            f"{src_root}/proj/file1.txt",
-            f"{src_root}/proj/nested/file2.txt",
-        ]
-        _populate_project_dir(tmp_path, files, {})
-
-        manifest = """
-            global-include *.py *.txt
-        """
-        (tmp_path / "MANIFEST.in").write_text(DALS(manifest), encoding="utf-8")
-
-    EXAMPLE_SETUPCFG = """
-    [metadata]
-    name = proj
-    version = 42
-
-    [options]
-    include_package_data = True
-    """
-    EXAMPLE_PYPROJECT = """
-    [project]
-    name = "proj"
-    version = "42"
-    """
-
-    PYPROJECT_PACKAGE_DIR = """
-    [tool.setuptools]
-    package-dir = {"" = "src"}
-    """
-
-    @pytest.mark.parametrize(
-        ("src_root", "files"),
-        [
-            (".", {"setup.cfg": DALS(EXAMPLE_SETUPCFG)}),
-            (".", {"pyproject.toml": DALS(EXAMPLE_PYPROJECT)}),
-            ("src", {"setup.cfg": DALS(EXAMPLE_SETUPCFG)}),
-            ("src", {"pyproject.toml": DALS(EXAMPLE_PYPROJECT)}),
-            (
-                "src",
-                {
-                    "setup.cfg": DALS(EXAMPLE_SETUPCFG)
-                    + DALS(
-                        """
-                        packages = find:
-                        package_dir =
-                            =src
-
-                        [options.packages.find]
-                        where = src
-                        """
-                    )
-                },
-            ),
-            (
-                "src",
-                {
-                    "pyproject.toml": DALS(EXAMPLE_PYPROJECT)
-                    + DALS(
-                        """
-                        [tool.setuptools]
-                        package-dir = {"" = "src"}
-                        """
-                    )
-                },
-            ),
-        ],
-    )
-    def test_include_package_data(self, tmp_path, src_root, files):
-        """
-        Make sure auto-discovery does not affect package include_package_data.
-        See issue #3196.
-        """
-        jaraco.path.build(files, prefix=str(tmp_path))
-        self._simulate_package_with_data_files(tmp_path, src_root)
-
-        expected = {
-            os.path.normpath(f"{src_root}/proj/file1.txt").replace(os.sep, "/"),
-            os.path.normpath(f"{src_root}/proj/nested/file2.txt").replace(os.sep, "/"),
-        }
-
-        _run_build(tmp_path)
-
-        sdist_files = get_sdist_members(next(tmp_path.glob("dist/*.tar.gz")))
-        print("~~~~~ sdist_members ~~~~~")
-        print('\n'.join(sdist_files))
-        assert sdist_files >= expected
-
-        wheel_files = get_wheel_members(next(tmp_path.glob("dist/*.whl")))
-        print("~~~~~ wheel_members ~~~~~")
-        print('\n'.join(wheel_files))
-        orig_files = {f.replace("src/", "").replace("lib/", "") for f in expected}
-        assert wheel_files >= orig_files
-
-
-def test_compatible_with_numpy_configuration(tmp_path):
-    files = [
-        "dir1/__init__.py",
-        "dir2/__init__.py",
-        "file.py",
-    ]
-    _populate_project_dir(tmp_path, files, {})
-    dist = Distribution({})
-    dist.configuration = object()
-    dist.set_defaults()
-    assert dist.py_modules is None
-    assert dist.packages is None
-
-
-def test_name_discovery_doesnt_break_cli(tmpdir_cwd):
-    jaraco.path.build({"pkg.py": ""})
-    dist = Distribution({})
-    dist.script_args = ["--name"]
-    dist.set_defaults()
-    dist.parse_command_line()  # <-- no exception should be raised here.
-    assert dist.get_name() == "pkg"
-
-
-def test_preserve_explicit_name_with_dynamic_version(tmpdir_cwd, monkeypatch):
-    """According to #3545 it seems that ``name`` discovery is running,
-    even when the project already explicitly sets it.
-    This seems to be related to parsing of dynamic versions (via ``attr`` directive),
-    which requires the auto-discovery of ``package_dir``.
-    """
-    files = {
-        "src": {
-            "pkg": {"__init__.py": "__version__ = 42\n"},
-        },
-        "pyproject.toml": DALS(
-            """
-            [project]
-            name = "myproj"  # purposefully different from package name
-            dynamic = ["version"]
-            [tool.setuptools.dynamic]
-            version = {"attr" = "pkg.__version__"}
-            """
-        ),
-    }
-    jaraco.path.build(files)
-    dist = Distribution({})
-    orig_analyse_name = dist.set_defaults.analyse_name
-
-    def spy_analyse_name():
-        # We can check if name discovery was triggered by ensuring the original
-        # name remains instead of the package name.
-        orig_analyse_name()
-        assert dist.get_name() == "myproj"
-
-    monkeypatch.setattr(dist.set_defaults, "analyse_name", spy_analyse_name)
-    dist.parse_config_files()
-    assert dist.get_version() == "42"
-    assert set(dist.packages) == {"pkg"}
-
-
-def _populate_project_dir(root, files, options):
-    # NOTE: Currently pypa/build will refuse to build the project if no
-    # `pyproject.toml` or `setup.py` is found. So it is impossible to do
-    # completely "config-less" projects.
-    basic = {
-        "setup.py": "import setuptools\nsetuptools.setup()",
-        "README.md": "# Example Package",
-        "LICENSE": "Copyright (c) 2018",
-    }
-    jaraco.path.build(basic, prefix=root)
-    _write_setupcfg(root, options)
-    paths = (root / f for f in files)
-    for path in paths:
-        path.parent.mkdir(exist_ok=True, parents=True)
-        path.touch()
-
-
-def _write_setupcfg(root, options):
-    if not options:
-        print("~~~~~ **NO** setup.cfg ~~~~~")
-        return
-    setupcfg = ConfigParser()
-    setupcfg.add_section("options")
-    for key, value in options.items():
-        if key == "packages.find":
-            setupcfg.add_section(f"options.{key}")
-            setupcfg[f"options.{key}"].update(value)
-        elif isinstance(value, list):
-            setupcfg["options"][key] = ", ".join(value)
-        elif isinstance(value, dict):
-            str_value = "\n".join(f"\t{k} = {v}" for k, v in value.items())
-            setupcfg["options"][key] = "\n" + str_value
-        else:
-            setupcfg["options"][key] = str(value)
-    with open(root / "setup.cfg", "w", encoding="utf-8") as f:
-        setupcfg.write(f)
-    print("~~~~~ setup.cfg ~~~~~")
-    print((root / "setup.cfg").read_text(encoding="utf-8"))
-
-
-def _run_build(path, *flags):
-    cmd = [sys.executable, "-m", "build", "--no-isolation", *flags, str(path)]
-    return run(cmd, env={'DISTUTILS_DEBUG': ''})
-
-
-def _get_dist(dist_path, attrs):
-    root = "/".join(os.path.split(dist_path))  # POSIX-style
-
-    script = dist_path / 'setup.py'
-    if script.exists():
-        with Path(dist_path):
-            dist = cast(
-                Distribution,
-                distutils.core.run_setup("setup.py", {}, stop_after="init"),
-            )
-    else:
-        dist = Distribution(attrs)
-
-    dist.src_root = root
-    dist.script_name = "setup.py"
-    with Path(dist_path):
-        dist.parse_config_files()
-
-    dist.set_defaults()
-    return dist
-
-
-def _run_sdist_programatically(dist_path, attrs):
-    dist = _get_dist(dist_path, attrs)
-    cmd = sdist(dist)
-    cmd.ensure_finalized()
-    assert cmd.distribution.packages or cmd.distribution.py_modules
-
-    with quiet(), Path(dist_path):
-        cmd.run()
-
-    return dist, cmd
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_core_metadata.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_core_metadata.py
deleted file mode 100644
index 0d92511..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_core_metadata.py
+++ /dev/null
@@ -1,622 +0,0 @@
-from __future__ import annotations
-
-import functools
-import importlib
-import io
-from email import message_from_string
-from email.generator import Generator
-from email.message import EmailMessage, Message
-from email.parser import Parser
-from email.policy import EmailPolicy
-from inspect import cleandoc
-from pathlib import Path
-from unittest.mock import Mock
-
-import jaraco.path
-import pytest
-from packaging.metadata import Metadata
-from packaging.requirements import Requirement
-
-from setuptools import _reqs, sic
-from setuptools._core_metadata import rfc822_escape, rfc822_unescape
-from setuptools.command.egg_info import egg_info, write_requirements
-from setuptools.config import expand, setupcfg
-from setuptools.dist import Distribution
-
-from .config.downloads import retrieve_file, urls_from_file
-
-EXAMPLE_BASE_INFO = dict(
-    name="package",
-    version="0.0.1",
-    author="Foo Bar",
-    author_email="foo@bar.net",
-    long_description="Long\ndescription",
-    description="Short description",
-    keywords=["one", "two"],
-)
-
-
-@pytest.mark.parametrize(
-    ("content", "result"),
-    (
-        pytest.param(
-            "Just a single line",
-            None,
-            id="single_line",
-        ),
-        pytest.param(
-            "Multiline\nText\nwithout\nextra indents\n",
-            None,
-            id="multiline",
-        ),
-        pytest.param(
-            "Multiline\n    With\n\nadditional\n  indentation",
-            None,
-            id="multiline_with_indentation",
-        ),
-        pytest.param(
-            "  Leading whitespace",
-            "Leading whitespace",
-            id="remove_leading_whitespace",
-        ),
-        pytest.param(
-            "  Leading whitespace\nIn\n    Multiline comment",
-            "Leading whitespace\nIn\n    Multiline comment",
-            id="remove_leading_whitespace_multiline",
-        ),
-    ),
-)
-def test_rfc822_unescape(content, result):
-    assert (result or content) == rfc822_unescape(rfc822_escape(content))
-
-
-def __read_test_cases():
-    base = EXAMPLE_BASE_INFO
-
-    params = functools.partial(dict, base)
-
-    return [
-        ('Metadata version 1.0', params()),
-        (
-            'Metadata Version 1.0: Short long description',
-            params(
-                long_description='Short long description',
-            ),
-        ),
-        (
-            'Metadata version 1.1: Classifiers',
-            params(
-                classifiers=[
-                    'Programming Language :: Python :: 3',
-                    'Programming Language :: Python :: 3.7',
-                    'License :: OSI Approved :: MIT License',
-                ],
-            ),
-        ),
-        (
-            'Metadata version 1.1: Download URL',
-            params(
-                download_url='https://example.com',
-            ),
-        ),
-        (
-            'Metadata Version 1.2: Requires-Python',
-            params(
-                python_requires='>=3.7',
-            ),
-        ),
-        pytest.param(
-            'Metadata Version 1.2: Project-Url',
-            params(project_urls=dict(Foo='https://example.bar')),
-            marks=pytest.mark.xfail(
-                reason="Issue #1578: project_urls not read",
-            ),
-        ),
-        (
-            'Metadata Version 2.1: Long Description Content Type',
-            params(
-                long_description_content_type='text/x-rst; charset=UTF-8',
-            ),
-        ),
-        (
-            'License',
-            params(
-                license='MIT',
-            ),
-        ),
-        (
-            'License multiline',
-            params(
-                license='This is a long license \nover multiple lines',
-            ),
-        ),
-        pytest.param(
-            'Metadata Version 2.1: Provides Extra',
-            params(provides_extras=['foo', 'bar']),
-            marks=pytest.mark.xfail(reason="provides_extras not read"),
-        ),
-        (
-            'Missing author',
-            dict(
-                name='foo',
-                version='1.0.0',
-                author_email='snorri@sturluson.name',
-            ),
-        ),
-        (
-            'Missing author e-mail',
-            dict(
-                name='foo',
-                version='1.0.0',
-                author='Snorri Sturluson',
-            ),
-        ),
-        (
-            'Missing author and e-mail',
-            dict(
-                name='foo',
-                version='1.0.0',
-            ),
-        ),
-        (
-            'Bypass normalized version',
-            dict(
-                name='foo',
-                version=sic('1.0.0a'),
-            ),
-        ),
-    ]
-
-
-@pytest.mark.parametrize(("name", "attrs"), __read_test_cases())
-def test_read_metadata(name, attrs):
-    dist = Distribution(attrs)
-    metadata_out = dist.metadata
-    dist_class = metadata_out.__class__
-
-    # Write to PKG_INFO and then load into a new metadata object
-    PKG_INFO = io.StringIO()
-
-    metadata_out.write_pkg_file(PKG_INFO)
-    PKG_INFO.seek(0)
-    pkg_info = PKG_INFO.read()
-    assert _valid_metadata(pkg_info)
-
-    PKG_INFO.seek(0)
-    metadata_in = dist_class()
-    metadata_in.read_pkg_file(PKG_INFO)
-
-    tested_attrs = [
-        ('name', dist_class.get_name),
-        ('version', dist_class.get_version),
-        ('author', dist_class.get_contact),
-        ('author_email', dist_class.get_contact_email),
-        ('metadata_version', dist_class.get_metadata_version),
-        ('provides', dist_class.get_provides),
-        ('description', dist_class.get_description),
-        ('long_description', dist_class.get_long_description),
-        ('download_url', dist_class.get_download_url),
-        ('keywords', dist_class.get_keywords),
-        ('platforms', dist_class.get_platforms),
-        ('obsoletes', dist_class.get_obsoletes),
-        ('requires', dist_class.get_requires),
-        ('classifiers', dist_class.get_classifiers),
-        ('project_urls', lambda s: getattr(s, 'project_urls', {})),
-        ('provides_extras', lambda s: getattr(s, 'provides_extras', {})),
-    ]
-
-    for attr, getter in tested_attrs:
-        assert getter(metadata_in) == getter(metadata_out)
-
-
-def __maintainer_test_cases():
-    attrs = {"name": "package", "version": "1.0", "description": "xxx"}
-
-    def merge_dicts(d1, d2):
-        d1 = d1.copy()
-        d1.update(d2)
-
-        return d1
-
-    return [
-        ('No author, no maintainer', attrs.copy()),
-        (
-            'Author (no e-mail), no maintainer',
-            merge_dicts(attrs, {'author': 'Author Name'}),
-        ),
-        (
-            'Author (e-mail), no maintainer',
-            merge_dicts(
-                attrs, {'author': 'Author Name', 'author_email': 'author@name.com'}
-            ),
-        ),
-        (
-            'No author, maintainer (no e-mail)',
-            merge_dicts(attrs, {'maintainer': 'Maintainer Name'}),
-        ),
-        (
-            'No author, maintainer (e-mail)',
-            merge_dicts(
-                attrs,
-                {
-                    'maintainer': 'Maintainer Name',
-                    'maintainer_email': 'maintainer@name.com',
-                },
-            ),
-        ),
-        (
-            'Author (no e-mail), Maintainer (no-email)',
-            merge_dicts(
-                attrs, {'author': 'Author Name', 'maintainer': 'Maintainer Name'}
-            ),
-        ),
-        (
-            'Author (e-mail), Maintainer (e-mail)',
-            merge_dicts(
-                attrs,
-                {
-                    'author': 'Author Name',
-                    'author_email': 'author@name.com',
-                    'maintainer': 'Maintainer Name',
-                    'maintainer_email': 'maintainer@name.com',
-                },
-            ),
-        ),
-        (
-            'No author (e-mail), no maintainer (e-mail)',
-            merge_dicts(
-                attrs,
-                {
-                    'author_email': 'author@name.com',
-                    'maintainer_email': 'maintainer@name.com',
-                },
-            ),
-        ),
-        ('Author unicode', merge_dicts(attrs, {'author': '鉄沢寛'})),
-        ('Maintainer unicode', merge_dicts(attrs, {'maintainer': 'Jan Łukasiewicz'})),
-    ]
-
-
-@pytest.mark.parametrize(("name", "attrs"), __maintainer_test_cases())
-def test_maintainer_author(name, attrs, tmpdir):
-    tested_keys = {
-        'author': 'Author',
-        'author_email': 'Author-email',
-        'maintainer': 'Maintainer',
-        'maintainer_email': 'Maintainer-email',
-    }
-
-    # Generate a PKG-INFO file
-    dist = Distribution(attrs)
-    fn = tmpdir.mkdir('pkg_info')
-    fn_s = str(fn)
-
-    dist.metadata.write_pkg_info(fn_s)
-
-    with open(str(fn.join('PKG-INFO')), 'r', encoding='utf-8') as f:
-        pkg_info = f.read()
-
-    assert _valid_metadata(pkg_info)
-
-    # Drop blank lines and strip lines from default description
-    raw_pkg_lines = pkg_info.splitlines()
-    pkg_lines = list(filter(None, raw_pkg_lines[:-2]))
-
-    pkg_lines_set = set(pkg_lines)
-
-    # Duplicate lines should not be generated
-    assert len(pkg_lines) == len(pkg_lines_set)
-
-    for fkey, dkey in tested_keys.items():
-        val = attrs.get(dkey, None)
-        if val is None:
-            for line in pkg_lines:
-                assert not line.startswith(fkey + ':')
-        else:
-            line = f'{fkey}: {val}'
-            assert line in pkg_lines_set
-
-
-class TestParityWithMetadataFromPyPaWheel:
-    def base_example(self):
-        attrs = dict(
-            **EXAMPLE_BASE_INFO,
-            # Example with complex requirement definition
-            python_requires=">=3.8",
-            install_requires="""
-            packaging==23.2
-            more-itertools==8.8.0; extra == "other"
-            jaraco.text==3.7.0
-            importlib-resources==5.10.2; python_version<"3.8"
-            importlib-metadata==6.0.0 ; python_version<"3.8"
-            colorama>=0.4.4; sys_platform == "win32"
-            """,
-            extras_require={
-                "testing": """
-                    pytest >= 6
-                    pytest-checkdocs >= 2.4
-                    tomli ; \\
-                            # Using stdlib when possible
-                            python_version < "3.11"
-                    ini2toml[lite]>=0.9
-                    """,
-                "other": [],
-            },
-        )
-        # Generate a PKG-INFO file using setuptools
-        return Distribution(attrs)
-
-    def test_requires_dist(self, tmp_path):
-        dist = self.base_example()
-        pkg_info = _get_pkginfo(dist)
-        assert _valid_metadata(pkg_info)
-
-        # Ensure Requires-Dist is present
-        expected = [
-            'Metadata-Version:',
-            'Requires-Python: >=3.8',
-            'Provides-Extra: other',
-            'Provides-Extra: testing',
-            'Requires-Dist: tomli; python_version < "3.11" and extra == "testing"',
-            'Requires-Dist: more-itertools==8.8.0; extra == "other"',
-            'Requires-Dist: ini2toml[lite]>=0.9; extra == "testing"',
-        ]
-        for line in expected:
-            assert line in pkg_info
-
-    HERE = Path(__file__).parent
-    EXAMPLES_FILE = HERE / "config/setupcfg_examples.txt"
-
-    @pytest.fixture(params=[None, *urls_from_file(EXAMPLES_FILE)])
-    def dist(self, request, monkeypatch, tmp_path):
-        """Example of distribution with arbitrary configuration"""
-        monkeypatch.chdir(tmp_path)
-        monkeypatch.setattr(expand, "read_attr", Mock(return_value="0.42"))
-        monkeypatch.setattr(expand, "read_files", Mock(return_value="hello world"))
-        monkeypatch.setattr(
-            Distribution, "_finalize_license_files", Mock(return_value=None)
-        )
-        if request.param is None:
-            yield self.base_example()
-        else:
-            # Real-world usage
-            config = retrieve_file(request.param)
-            yield setupcfg.apply_configuration(Distribution({}), config)
-
-    @pytest.mark.uses_network
-    def test_equivalent_output(self, tmp_path, dist):
-        """Ensure output from setuptools is equivalent to the one from `pypa/wheel`"""
-        # Generate a METADATA file using pypa/wheel for comparison
-        wheel_metadata = importlib.import_module("wheel.metadata")
-        pkginfo_to_metadata = getattr(wheel_metadata, "pkginfo_to_metadata", None)
-
-        if pkginfo_to_metadata is None:  # pragma: nocover
-            pytest.xfail(
-                "wheel.metadata.pkginfo_to_metadata is undefined, "
-                "(this is likely to be caused by API changes in pypa/wheel"
-            )
-
-        # Generate an simplified "egg-info" dir for pypa/wheel to convert
-        pkg_info = _get_pkginfo(dist)
-        egg_info_dir = tmp_path / "pkg.egg-info"
-        egg_info_dir.mkdir(parents=True)
-        (egg_info_dir / "PKG-INFO").write_text(pkg_info, encoding="utf-8")
-        write_requirements(egg_info(dist), egg_info_dir, egg_info_dir / "requires.txt")
-
-        # Get pypa/wheel generated METADATA but normalize requirements formatting
-        metadata_msg = pkginfo_to_metadata(egg_info_dir, egg_info_dir / "PKG-INFO")
-        metadata_str = _normalize_metadata(metadata_msg)
-        pkg_info_msg = message_from_string(pkg_info)
-        pkg_info_str = _normalize_metadata(pkg_info_msg)
-
-        # Compare setuptools PKG-INFO x pypa/wheel METADATA
-        assert metadata_str == pkg_info_str
-
-        # Make sure it parses/serializes well in pypa/wheel
-        _assert_roundtrip_message(pkg_info)
-
-
-class TestPEP643:
-    STATIC_CONFIG = {
-        "setup.cfg": cleandoc(
-            """
-            [metadata]
-            name = package
-            version = 0.0.1
-            author = Foo Bar
-            author_email = foo@bar.net
-            long_description = Long
-                               description
-            description = Short description
-            keywords = one, two
-            platforms = abcd
-            [options]
-            install_requires = requests
-            """
-        ),
-        "pyproject.toml": cleandoc(
-            """
-            [project]
-            name = "package"
-            version = "0.0.1"
-            authors = [
-              {name = "Foo Bar", email = "foo@bar.net"}
-            ]
-            description = "Short description"
-            readme = {text = "Long\\ndescription", content-type = "text/plain"}
-            keywords = ["one", "two"]
-            dependencies = ["requests"]
-            license = "AGPL-3.0-or-later"
-            [tool.setuptools]
-            provides = ["abcd"]
-            obsoletes = ["abcd"]
-            """
-        ),
-    }
-
-    @pytest.mark.parametrize("file", STATIC_CONFIG.keys())
-    def test_static_config_has_no_dynamic(self, file, tmpdir_cwd):
-        Path(file).write_text(self.STATIC_CONFIG[file], encoding="utf-8")
-        metadata = _get_metadata()
-        assert metadata.get_all("Dynamic") is None
-        assert metadata.get_all("dynamic") is None
-
-    @pytest.mark.parametrize("file", STATIC_CONFIG.keys())
-    @pytest.mark.parametrize(
-        "fields",
-        [
-            # Single dynamic field
-            {"requires-python": ("python_requires", ">=3.12")},
-            {"author-email": ("author_email", "snoopy@peanuts.com")},
-            {"keywords": ("keywords", ["hello", "world"])},
-            {"platform": ("platforms", ["abcd"])},
-            # Multiple dynamic fields
-            {
-                "summary": ("description", "hello world"),
-                "description": ("long_description", "bla bla bla bla"),
-                "requires-dist": ("install_requires", ["hello-world"]),
-            },
-        ],
-    )
-    def test_modified_fields_marked_as_dynamic(self, file, fields, tmpdir_cwd):
-        # We start with a static config
-        Path(file).write_text(self.STATIC_CONFIG[file], encoding="utf-8")
-        dist = _makedist()
-
-        # ... but then we simulate the effects of a plugin modifying the distribution
-        for attr, value in fields.values():
-            # `dist` and `dist.metadata` are complicated...
-            # Some attributes work when set on `dist`, others on `dist.metadata`...
-            # Here we set in both just in case (this also avoids calling `_finalize_*`)
-            setattr(dist, attr, value)
-            setattr(dist.metadata, attr, value)
-
-        # Then we should be able to list the modified fields as Dynamic
-        metadata = _get_metadata(dist)
-        assert set(metadata.get_all("Dynamic")) == set(fields)
-
-    @pytest.mark.parametrize(
-        "extra_toml",
-        [
-            "# Let setuptools autofill license-files",
-            "license-files = ['LICENSE*', 'AUTHORS*', 'NOTICE']",
-        ],
-    )
-    def test_license_files_dynamic(self, extra_toml, tmpdir_cwd):
-        # For simplicity (and for the time being) setuptools is not making
-        # any special handling to guarantee `License-File` is considered static.
-        # Instead we rely in the fact that, although suboptimal, it is OK to have
-        # it as dynamics, as per:
-        # https://github.com/pypa/setuptools/issues/4629#issuecomment-2331233677
-        files = {
-            "pyproject.toml": self.STATIC_CONFIG["pyproject.toml"].replace(
-                'license = "AGPL-3.0-or-later"',
-                f"dynamic = ['license']\n{extra_toml}",
-            ),
-            "LICENSE.md": "--- mock license ---",
-            "NOTICE": "--- mock notice ---",
-            "AUTHORS.txt": "--- me ---",
-        }
-        # Sanity checks:
-        assert extra_toml in files["pyproject.toml"]
-        assert 'license = "AGPL-3.0-or-later"' not in extra_toml
-
-        jaraco.path.build(files)
-        dist = _makedist(license_expression="AGPL-3.0-or-later")
-        metadata = _get_metadata(dist)
-        assert set(metadata.get_all("Dynamic")) == {
-            'license-file',
-            'license-expression',
-        }
-        assert metadata.get("License-Expression") == "AGPL-3.0-or-later"
-        assert set(metadata.get_all("License-File")) == {
-            "NOTICE",
-            "AUTHORS.txt",
-            "LICENSE.md",
-        }
-
-
-def _makedist(**attrs):
-    dist = Distribution(attrs)
-    dist.parse_config_files()
-    return dist
-
-
-def _assert_roundtrip_message(metadata: str) -> None:
-    """Emulate the way wheel.bdist_wheel parses and regenerates the message,
-    then ensures the metadata generated by setuptools is compatible.
-    """
-    with io.StringIO(metadata) as buffer:
-        msg = Parser(EmailMessage).parse(buffer)
-
-    serialization_policy = EmailPolicy(
-        utf8=True,
-        mangle_from_=False,
-        max_line_length=0,
-    )
-    with io.BytesIO() as buffer:
-        out = io.TextIOWrapper(buffer, encoding="utf-8")
-        Generator(out, policy=serialization_policy).flatten(msg)
-        out.flush()
-        regenerated = buffer.getvalue()
-
-    raw_metadata = bytes(metadata, "utf-8")
-    # Normalise newlines to avoid test errors on Windows:
-    raw_metadata = b"\n".join(raw_metadata.splitlines())
-    regenerated = b"\n".join(regenerated.splitlines())
-    assert regenerated == raw_metadata
-
-
-def _normalize_metadata(msg: Message) -> str:
-    """Allow equivalent metadata to be compared directly"""
-    # The main challenge regards the requirements and extras.
-    # Both setuptools and wheel already apply some level of normalization
-    # but they differ regarding which character is chosen, according to the
-    # following spec it should be "-":
-    # https://packaging.python.org/en/latest/specifications/name-normalization/
-
-    # Related issues:
-    # https://github.com/pypa/packaging/issues/845
-    # https://github.com/pypa/packaging/issues/644#issuecomment-2429813968
-
-    extras = {x.replace("_", "-"): x for x in msg.get_all("Provides-Extra", [])}
-    reqs = [
-        _normalize_req(req, extras)
-        for req in _reqs.parse(msg.get_all("Requires-Dist", []))
-    ]
-    del msg["Requires-Dist"]
-    del msg["Provides-Extra"]
-
-    # Ensure consistent ord
-    for req in sorted(reqs):
-        msg["Requires-Dist"] = req
-    for extra in sorted(extras):
-        msg["Provides-Extra"] = extra
-
-    # TODO: Handle lack of PEP 643 implementation in pypa/wheel?
-    del msg["Metadata-Version"]
-
-    return msg.as_string()
-
-
-def _normalize_req(req: Requirement, extras: dict[str, str]) -> str:
-    """Allow equivalent requirement objects to be compared directly"""
-    as_str = str(req).replace(req.name, req.name.replace("_", "-"))
-    for norm, orig in extras.items():
-        as_str = as_str.replace(orig, norm)
-    return as_str
-
-
-def _get_pkginfo(dist: Distribution):
-    with io.StringIO() as fp:
-        dist.metadata.write_pkg_file(fp)
-        return fp.getvalue()
-
-
-def _get_metadata(dist: Distribution | None = None):
-    return message_from_string(_get_pkginfo(dist or _makedist()))
-
-
-def _valid_metadata(text: str) -> bool:
-    metadata = Metadata.from_email(text, validate=True)  # can raise exceptions
-    return metadata is not None
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_depends.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_depends.py
deleted file mode 100644
index 1714c04..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_depends.py
+++ /dev/null
@@ -1,15 +0,0 @@
-import sys
-
-from setuptools import depends
-
-
-class TestGetModuleConstant:
-    def test_basic(self):
-        """
-        Invoke get_module_constant on a module in
-        the test package.
-        """
-        mod_name = 'setuptools.tests.mod_with_constant'
-        val = depends.get_module_constant(mod_name, 'value')
-        assert val == 'three, sir!'
-        assert 'setuptools.tests.mod_with_constant' not in sys.modules
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_develop.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_develop.py
deleted file mode 100644
index 929fa9c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_develop.py
+++ /dev/null
@@ -1,175 +0,0 @@
-"""develop tests"""
-
-import os
-import pathlib
-import platform
-import subprocess
-import sys
-
-import pytest
-
-from setuptools._path import paths_on_pythonpath
-from setuptools.command.develop import develop
-from setuptools.dist import Distribution
-
-from . import contexts, namespaces
-
-SETUP_PY = """\
-from setuptools import setup
-
-setup(name='foo',
-    packages=['foo'],
-)
-"""
-
-INIT_PY = """print "foo"
-"""
-
-
-@pytest.fixture
-def temp_user(monkeypatch):
-    with contexts.tempdir() as user_base:
-        with contexts.tempdir() as user_site:
-            monkeypatch.setattr('site.USER_BASE', user_base)
-            monkeypatch.setattr('site.USER_SITE', user_site)
-            yield
-
-
-@pytest.fixture
-def test_env(tmpdir, temp_user):
-    target = tmpdir
-    foo = target.mkdir('foo')
-    setup = target / 'setup.py'
-    if setup.isfile():
-        raise ValueError(dir(target))
-    with setup.open('w') as f:
-        f.write(SETUP_PY)
-    init = foo / '__init__.py'
-    with init.open('w') as f:
-        f.write(INIT_PY)
-    with target.as_cwd():
-        yield target
-
-
-class TestDevelop:
-    in_virtualenv = hasattr(sys, 'real_prefix')
-    in_venv = hasattr(sys, 'base_prefix') and sys.base_prefix != sys.prefix
-
-    def test_console_scripts(self, tmpdir):
-        """
-        Test that console scripts are installed and that they reference
-        only the project by name and not the current version.
-        """
-        pytest.skip(
-            "TODO: needs a fixture to cause 'develop' "
-            "to be invoked without mutating environment."
-        )
-        settings = dict(
-            name='foo',
-            packages=['foo'],
-            version='0.0',
-            entry_points={
-                'console_scripts': [
-                    'foocmd = foo:foo',
-                ],
-            },
-        )
-        dist = Distribution(settings)
-        dist.script_name = 'setup.py'
-        cmd = develop(dist)
-        cmd.ensure_finalized()
-        cmd.install_dir = tmpdir
-        cmd.run()
-        # assert '0.0' not in foocmd_text
-
-    @pytest.mark.xfail(reason="legacy behavior retained for compatibility #4167")
-    def test_egg_link_filename(self):
-        settings = dict(
-            name='Foo $$$ Bar_baz-bing',
-        )
-        dist = Distribution(settings)
-        cmd = develop(dist)
-        cmd.ensure_finalized()
-        link = pathlib.Path(cmd.egg_link)
-        assert link.suffix == '.egg-link'
-        assert link.stem == 'Foo_Bar_baz_bing'
-
-
-class TestResolver:
-    """
-    TODO: These tests were written with a minimal understanding
-    of what _resolve_setup_path is intending to do. Come up with
-    more meaningful cases that look like real-world scenarios.
-    """
-
-    def test_resolve_setup_path_cwd(self):
-        assert develop._resolve_setup_path('.', '.', '.') == '.'
-
-    def test_resolve_setup_path_one_dir(self):
-        assert develop._resolve_setup_path('pkgs', '.', 'pkgs') == '../'
-
-    def test_resolve_setup_path_one_dir_trailing_slash(self):
-        assert develop._resolve_setup_path('pkgs/', '.', 'pkgs') == '../'
-
-
-class TestNamespaces:
-    @staticmethod
-    def install_develop(src_dir, target):
-        develop_cmd = [
-            sys.executable,
-            'setup.py',
-            'develop',
-            '--install-dir',
-            str(target),
-        ]
-        with src_dir.as_cwd():
-            with paths_on_pythonpath([str(target)]):
-                subprocess.check_call(develop_cmd)
-
-    @pytest.mark.skipif(
-        bool(os.environ.get("APPVEYOR")),
-        reason="https://github.com/pypa/setuptools/issues/851",
-    )
-    @pytest.mark.skipif(
-        platform.python_implementation() == 'PyPy',
-        reason="https://github.com/pypa/setuptools/issues/1202",
-    )
-    def test_namespace_package_importable(self, tmpdir):
-        """
-        Installing two packages sharing the same namespace, one installed
-        naturally using pip or `--single-version-externally-managed`
-        and the other installed using `develop` should leave the namespace
-        in tact and both packages reachable by import.
-        """
-        pkg_A = namespaces.build_namespace_package(tmpdir, 'myns.pkgA')
-        pkg_B = namespaces.build_namespace_package(tmpdir, 'myns.pkgB')
-        target = tmpdir / 'packages'
-        # use pip to install to the target directory
-        install_cmd = [
-            sys.executable,
-            '-m',
-            'pip',
-            'install',
-            str(pkg_A),
-            '-t',
-            str(target),
-        ]
-        subprocess.check_call(install_cmd)
-        self.install_develop(pkg_B, target)
-        namespaces.make_site_dir(target)
-        try_import = [
-            sys.executable,
-            '-c',
-            'import myns.pkgA; import myns.pkgB',
-        ]
-        with paths_on_pythonpath([str(target)]):
-            subprocess.check_call(try_import)
-
-        # additionally ensure that pkg_resources import works
-        pkg_resources_imp = [
-            sys.executable,
-            '-c',
-            'import pkg_resources',
-        ]
-        with paths_on_pythonpath([str(target)]):
-            subprocess.check_call(pkg_resources_imp)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_dist.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_dist.py
deleted file mode 100644
index e65ab31..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_dist.py
+++ /dev/null
@@ -1,278 +0,0 @@
-import os
-import re
-import urllib.parse
-import urllib.request
-
-import pytest
-
-from setuptools import Distribution
-from setuptools.dist import check_package_data, check_specifier
-
-from .test_easy_install import make_trivial_sdist
-from .test_find_packages import ensure_files
-from .textwrap import DALS
-
-from distutils.errors import DistutilsSetupError
-
-
-def test_dist_fetch_build_egg(tmpdir):
-    """
-    Check multiple calls to `Distribution.fetch_build_egg` work as expected.
-    """
-    index = tmpdir.mkdir('index')
-    index_url = urllib.parse.urljoin('file://', urllib.request.pathname2url(str(index)))
-
-    def sdist_with_index(distname, version):
-        dist_dir = index.mkdir(distname)
-        dist_sdist = f'{distname}-{version}.tar.gz'
-        make_trivial_sdist(str(dist_dir.join(dist_sdist)), distname, version)
-        with dist_dir.join('index.html').open('w') as fp:
-            fp.write(
-                DALS(
-                    """
-                
-                {dist_sdist}

-                
-                """
-                ).format(dist_sdist=dist_sdist)
-            )
-
-    sdist_with_index('barbazquux', '3.2.0')
-    sdist_with_index('barbazquux-runner', '2.11.1')
-    with tmpdir.join('setup.cfg').open('w') as fp:
-        fp.write(
-            DALS(
-                """
-            [easy_install]
-            index_url = {index_url}
-            """
-            ).format(index_url=index_url)
-        )
-    reqs = """
-    barbazquux-runner
-    barbazquux
-    """.split()
-    with tmpdir.as_cwd():
-        dist = Distribution()
-        dist.parse_config_files()
-        resolved_dists = [dist.fetch_build_egg(r) for r in reqs]
-    assert [dist.key for dist in resolved_dists if dist] == reqs
-
-
-EXAMPLE_BASE_INFO = dict(
-    name="package",
-    version="0.0.1",
-    author="Foo Bar",
-    author_email="foo@bar.net",
-    long_description="Long\ndescription",
-    description="Short description",
-    keywords=["one", "two"],
-)
-
-
-def test_provides_extras_deterministic_order():
-    attrs = dict(extras_require=dict(a=['foo'], b=['bar']))
-    dist = Distribution(attrs)
-    assert list(dist.metadata.provides_extras) == ['a', 'b']
-    attrs['extras_require'] = dict(reversed(attrs['extras_require'].items()))
-    dist = Distribution(attrs)
-    assert list(dist.metadata.provides_extras) == ['b', 'a']
-
-
-CHECK_PACKAGE_DATA_TESTS = (
-    # Valid.
-    (
-        {
-            '': ['*.txt', '*.rst'],
-            'hello': ['*.msg'],
-        },
-        None,
-    ),
-    # Not a dictionary.
-    (
-        (
-            ('', ['*.txt', '*.rst']),
-            ('hello', ['*.msg']),
-        ),
-        (
-            "'package_data' must be a dictionary mapping package"
-            " names to lists of string wildcard patterns"
-        ),
-    ),
-    # Invalid key type.
-    (
-        {
-            400: ['*.txt', '*.rst'],
-        },
-        ("keys of 'package_data' dict must be strings (got 400)"),
-    ),
-    # Invalid value type.
-    (
-        {
-            'hello': '*.msg',
-        },
-        (
-            "\"values of 'package_data' dict\" must be of type "
-            " (got '*.msg')"
-        ),
-    ),
-    # Invalid value type (generators are single use)
-    (
-        {
-            'hello': (x for x in "generator"),
-        },
-        (
-            "\"values of 'package_data' dict\" must be of type "
-            " (got =3.0, !=3.1'}
-    dist = Distribution(attrs)
-    check_specifier(dist, attrs, attrs['python_requires'])
-
-    attrs = {'name': 'foo', 'python_requires': ['>=3.0', '!=3.1']}
-    dist = Distribution(attrs)
-    check_specifier(dist, attrs, attrs['python_requires'])
-
-    # invalid specifier value
-    attrs = {'name': 'foo', 'python_requires': '>=invalid-version'}
-    with pytest.raises(DistutilsSetupError):
-        dist = Distribution(attrs)
-
-
-def test_metadata_name():
-    with pytest.raises(DistutilsSetupError, match='missing.*name'):
-        Distribution()._validate_metadata()
-
-
-@pytest.mark.parametrize(
-    ('dist_name', 'py_module'),
-    [
-        ("my.pkg", "my_pkg"),
-        ("my-pkg", "my_pkg"),
-        ("my_pkg", "my_pkg"),
-        ("pkg", "pkg"),
-    ],
-)
-def test_dist_default_py_modules(tmp_path, dist_name, py_module):
-    (tmp_path / f"{py_module}.py").touch()
-
-    (tmp_path / "setup.py").touch()
-    (tmp_path / "noxfile.py").touch()
-    # ^-- make sure common tool files are ignored
-
-    attrs = {**EXAMPLE_BASE_INFO, "name": dist_name, "src_root": str(tmp_path)}
-    # Find `py_modules` corresponding to dist_name if not given
-    dist = Distribution(attrs)
-    dist.set_defaults()
-    assert dist.py_modules == [py_module]
-    # When `py_modules` is given, don't do anything
-    dist = Distribution({**attrs, "py_modules": ["explicity_py_module"]})
-    dist.set_defaults()
-    assert dist.py_modules == ["explicity_py_module"]
-    # When `packages` is given, don't do anything
-    dist = Distribution({**attrs, "packages": ["explicity_package"]})
-    dist.set_defaults()
-    assert not dist.py_modules
-
-
-@pytest.mark.parametrize(
-    ('dist_name', 'package_dir', 'package_files', 'packages'),
-    [
-        ("my.pkg", None, ["my_pkg/__init__.py", "my_pkg/mod.py"], ["my_pkg"]),
-        ("my-pkg", None, ["my_pkg/__init__.py", "my_pkg/mod.py"], ["my_pkg"]),
-        ("my_pkg", None, ["my_pkg/__init__.py", "my_pkg/mod.py"], ["my_pkg"]),
-        ("my.pkg", None, ["my/pkg/__init__.py"], ["my", "my.pkg"]),
-        (
-            "my_pkg",
-            None,
-            ["src/my_pkg/__init__.py", "src/my_pkg2/__init__.py"],
-            ["my_pkg", "my_pkg2"],
-        ),
-        (
-            "my_pkg",
-            {"pkg": "lib", "pkg2": "lib2"},
-            ["lib/__init__.py", "lib/nested/__init__.pyt", "lib2/__init__.py"],
-            ["pkg", "pkg.nested", "pkg2"],
-        ),
-    ],
-)
-def test_dist_default_packages(
-    tmp_path, dist_name, package_dir, package_files, packages
-):
-    ensure_files(tmp_path, package_files)
-
-    (tmp_path / "setup.py").touch()
-    (tmp_path / "noxfile.py").touch()
-    # ^-- should not be included by default
-
-    attrs = {
-        **EXAMPLE_BASE_INFO,
-        "name": dist_name,
-        "src_root": str(tmp_path),
-        "package_dir": package_dir,
-    }
-    # Find `packages` either corresponding to dist_name or inside src
-    dist = Distribution(attrs)
-    dist.set_defaults()
-    assert not dist.py_modules
-    assert not dist.py_modules
-    assert set(dist.packages) == set(packages)
-    # When `py_modules` is given, don't do anything
-    dist = Distribution({**attrs, "py_modules": ["explicit_py_module"]})
-    dist.set_defaults()
-    assert not dist.packages
-    assert set(dist.py_modules) == {"explicit_py_module"}
-    # When `packages` is given, don't do anything
-    dist = Distribution({**attrs, "packages": ["explicit_package"]})
-    dist.set_defaults()
-    assert not dist.py_modules
-    assert set(dist.packages) == {"explicit_package"}
-
-
-@pytest.mark.parametrize(
-    ('dist_name', 'package_dir', 'package_files'),
-    [
-        ("my.pkg.nested", None, ["my/pkg/nested/__init__.py"]),
-        ("my.pkg", None, ["my/pkg/__init__.py", "my/pkg/file.py"]),
-        ("my_pkg", None, ["my_pkg.py"]),
-        ("my_pkg", None, ["my_pkg/__init__.py", "my_pkg/nested/__init__.py"]),
-        ("my_pkg", None, ["src/my_pkg/__init__.py", "src/my_pkg/nested/__init__.py"]),
-        (
-            "my_pkg",
-            {"my_pkg": "lib", "my_pkg.lib2": "lib2"},
-            ["lib/__init__.py", "lib/nested/__init__.pyt", "lib2/__init__.py"],
-        ),
-        # Should not try to guess a name from multiple py_modules/packages
-        ("UNKNOWN", None, ["src/mod1.py", "src/mod2.py"]),
-        ("UNKNOWN", None, ["src/pkg1/__ini__.py", "src/pkg2/__init__.py"]),
-    ],
-)
-def test_dist_default_name(tmp_path, dist_name, package_dir, package_files):
-    """Make sure dist.name is discovered from packages/py_modules"""
-    ensure_files(tmp_path, package_files)
-    attrs = {
-        **EXAMPLE_BASE_INFO,
-        "src_root": "/".join(os.path.split(tmp_path)),  # POSIX-style
-        "package_dir": package_dir,
-    }
-    del attrs["name"]
-
-    dist = Distribution(attrs)
-    dist.set_defaults()
-    assert dist.py_modules or dist.packages
-    assert dist.get_name() == dist_name
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_dist_info.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_dist_info.py
deleted file mode 100644
index 426694e..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_dist_info.py
+++ /dev/null
@@ -1,210 +0,0 @@
-"""Test .dist-info style distributions."""
-
-import pathlib
-import re
-import shutil
-import subprocess
-import sys
-from functools import partial
-
-import pytest
-
-import pkg_resources
-from setuptools.archive_util import unpack_archive
-
-from .textwrap import DALS
-
-read = partial(pathlib.Path.read_text, encoding="utf-8")
-
-
-class TestDistInfo:
-    metadata_base = DALS(
-        """
-        Metadata-Version: 1.2
-        Requires-Dist: splort (==4)
-        Provides-Extra: baz
-        Requires-Dist: quux (>=1.1); extra == 'baz'
-        """
-    )
-
-    @classmethod
-    def build_metadata(cls, **kwargs):
-        lines = ('{key}: {value}\n'.format(**locals()) for key, value in kwargs.items())
-        return cls.metadata_base + ''.join(lines)
-
-    @pytest.fixture
-    def metadata(self, tmpdir):
-        dist_info_name = 'VersionedDistribution-2.718.dist-info'
-        versioned = tmpdir / dist_info_name
-        versioned.mkdir()
-        filename = versioned / 'METADATA'
-        content = self.build_metadata(
-            Name='VersionedDistribution',
-        )
-        filename.write_text(content, encoding='utf-8')
-
-        dist_info_name = 'UnversionedDistribution.dist-info'
-        unversioned = tmpdir / dist_info_name
-        unversioned.mkdir()
-        filename = unversioned / 'METADATA'
-        content = self.build_metadata(
-            Name='UnversionedDistribution',
-            Version='0.3',
-        )
-        filename.write_text(content, encoding='utf-8')
-
-        return str(tmpdir)
-
-    def test_distinfo(self, metadata):
-        dists = dict(
-            (d.project_name, d) for d in pkg_resources.find_distributions(metadata)
-        )
-
-        assert len(dists) == 2, dists
-
-        unversioned = dists['UnversionedDistribution']
-        versioned = dists['VersionedDistribution']
-
-        assert versioned.version == '2.718'  # from filename
-        assert unversioned.version == '0.3'  # from METADATA
-
-    def test_conditional_dependencies(self, metadata):
-        specs = 'splort==4', 'quux>=1.1'
-        requires = list(map(pkg_resources.Requirement.parse, specs))
-
-        for d in pkg_resources.find_distributions(metadata):
-            assert d.requires() == requires[:1]
-            assert d.requires(extras=('baz',)) == [
-                requires[0],
-                pkg_resources.Requirement.parse('quux>=1.1;extra=="baz"'),
-            ]
-            assert d.extras == ['baz']
-
-    def test_invalid_version(self, tmp_path):
-        """
-        Supplying an invalid version crashes dist_info.
-        """
-        config = "[metadata]\nname=proj\nversion=42\n[egg_info]\ntag_build=invalid!!!\n"
-        (tmp_path / "setup.cfg").write_text(config, encoding="utf-8")
-        msg = re.compile("invalid version", re.M | re.I)
-        proc = run_command_inner("dist_info", cwd=tmp_path, check=False)
-        assert proc.returncode
-        assert msg.search(proc.stdout)
-        assert not list(tmp_path.glob("*.dist-info"))
-
-    def test_tag_arguments(self, tmp_path):
-        config = """
-        [metadata]
-        name=proj
-        version=42
-        [egg_info]
-        tag_date=1
-        tag_build=.post
-        """
-        (tmp_path / "setup.cfg").write_text(config, encoding="utf-8")
-
-        print(run_command("dist_info", "--no-date", cwd=tmp_path))
-        dist_info = next(tmp_path.glob("*.dist-info"))
-        assert dist_info.name.startswith("proj-42")
-        shutil.rmtree(dist_info)
-
-        print(run_command("dist_info", "--tag-build", ".a", cwd=tmp_path))
-        dist_info = next(tmp_path.glob("*.dist-info"))
-        assert dist_info.name.startswith("proj-42a")
-
-    @pytest.mark.parametrize("keep_egg_info", (False, True))
-    def test_output_dir(self, tmp_path, keep_egg_info):
-        config = "[metadata]\nname=proj\nversion=42\n"
-        (tmp_path / "setup.cfg").write_text(config, encoding="utf-8")
-        out = tmp_path / "__out"
-        out.mkdir()
-        opts = ["--keep-egg-info"] if keep_egg_info else []
-        run_command("dist_info", "--output-dir", out, *opts, cwd=tmp_path)
-        assert len(list(out.glob("*.dist-info"))) == 1
-        assert len(list(tmp_path.glob("*.dist-info"))) == 0
-        expected_egg_info = int(keep_egg_info)
-        assert len(list(out.glob("*.egg-info"))) == expected_egg_info
-        assert len(list(tmp_path.glob("*.egg-info"))) == 0
-        assert len(list(out.glob("*.__bkp__"))) == 0
-        assert len(list(tmp_path.glob("*.__bkp__"))) == 0
-
-
-class TestWheelCompatibility:
-    """Make sure the .dist-info directory produced with the ``dist_info`` command
-    is the same as the one produced by ``bdist_wheel``.
-    """
-
-    SETUPCFG = DALS(
-        """
-    [metadata]
-    name = {name}
-    version = {version}
-
-    [options]
-    install_requires =
-        foo>=12; sys_platform != "linux"
-
-    [options.extras_require]
-    test = pytest
-
-    [options.entry_points]
-    console_scripts =
-        executable-name = my_package.module:function
-    discover =
-        myproj = my_package.other_module:function
-    """
-    )
-
-    EGG_INFO_OPTS = [
-        # Related: #3088 #2872
-        ("", ""),
-        (".post", "[egg_info]\ntag_build = post\n"),
-        (".post", "[egg_info]\ntag_build = .post\n"),
-        (".post", "[egg_info]\ntag_build = post\ntag_date = 1\n"),
-        (".dev", "[egg_info]\ntag_build = .dev\n"),
-        (".dev", "[egg_info]\ntag_build = .dev\ntag_date = 1\n"),
-        ("a1", "[egg_info]\ntag_build = .a1\n"),
-        ("+local", "[egg_info]\ntag_build = +local\n"),
-    ]
-
-    @pytest.mark.parametrize("name", "my-proj my_proj my.proj My.Proj".split())
-    @pytest.mark.parametrize("version", ["0.42.13"])
-    @pytest.mark.parametrize(("suffix", "cfg"), EGG_INFO_OPTS)
-    def test_dist_info_is_the_same_as_in_wheel(
-        self, name, version, tmp_path, suffix, cfg
-    ):
-        config = self.SETUPCFG.format(name=name, version=version) + cfg
-
-        for i in "dir_wheel", "dir_dist":
-            (tmp_path / i).mkdir()
-            (tmp_path / i / "setup.cfg").write_text(config, encoding="utf-8")
-
-        run_command("bdist_wheel", cwd=tmp_path / "dir_wheel")
-        wheel = next(tmp_path.glob("dir_wheel/dist/*.whl"))
-        unpack_archive(wheel, tmp_path / "unpack")
-        wheel_dist_info = next(tmp_path.glob("unpack/*.dist-info"))
-
-        run_command("dist_info", cwd=tmp_path / "dir_dist")
-        dist_info = next(tmp_path.glob("dir_dist/*.dist-info"))
-
-        assert dist_info.name == wheel_dist_info.name
-        assert dist_info.name.startswith(f"my_proj-{version}{suffix}")
-        for file in "METADATA", "entry_points.txt":
-            assert read(dist_info / file) == read(wheel_dist_info / file)
-
-
-def run_command_inner(*cmd, **kwargs):
-    opts = {
-        "stderr": subprocess.STDOUT,
-        "stdout": subprocess.PIPE,
-        "text": True,
-        "encoding": "utf-8",
-        "check": True,
-        **kwargs,
-    }
-    cmd = [sys.executable, "-c", "__import__('setuptools').setup()", *map(str, cmd)]
-    return subprocess.run(cmd, **opts)
-
-
-def run_command(*args, **kwargs):
-    return run_command_inner(*args, **kwargs).stdout
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_distutils_adoption.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_distutils_adoption.py
deleted file mode 100644
index f99a588..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_distutils_adoption.py
+++ /dev/null
@@ -1,198 +0,0 @@
-import os
-import platform
-import sys
-import textwrap
-
-import pytest
-
-IS_PYPY = '__pypy__' in sys.builtin_module_names
-
-_TEXT_KWARGS = {"text": True, "encoding": "utf-8"}  # For subprocess.run
-
-
-def win_sr(env):
-    """
-    On Windows, SYSTEMROOT must be present to avoid
-
-    > Fatal Python error: _Py_HashRandomization_Init: failed to
-    > get random numbers to initialize Python
-    """
-    if env and platform.system() == 'Windows':
-        env['SYSTEMROOT'] = os.environ['SYSTEMROOT']
-    return env
-
-
-def find_distutils(venv, imports='distutils', env=None, **kwargs):
-    py_cmd = 'import {imports}; print(distutils.__file__)'.format(**locals())
-    cmd = ['python', '-c', py_cmd]
-    return venv.run(cmd, env=win_sr(env), **_TEXT_KWARGS, **kwargs)
-
-
-def count_meta_path(venv, env=None):
-    py_cmd = textwrap.dedent(
-        """
-        import sys
-        is_distutils = lambda finder: finder.__class__.__name__ == "DistutilsMetaFinder"
-        print(len(list(filter(is_distutils, sys.meta_path))))
-        """
-    )
-    cmd = ['python', '-c', py_cmd]
-    return int(venv.run(cmd, env=win_sr(env), **_TEXT_KWARGS))
-
-
-skip_without_stdlib_distutils = pytest.mark.skipif(
-    sys.version_info >= (3, 12),
-    reason='stdlib distutils is removed from Python 3.12+',
-)
-
-
-@skip_without_stdlib_distutils
-def test_distutils_stdlib(venv):
-    """
-    Ensure stdlib distutils is used when appropriate.
-    """
-    env = dict(SETUPTOOLS_USE_DISTUTILS='stdlib')
-    assert venv.name not in find_distutils(venv, env=env).split(os.sep)
-    assert count_meta_path(venv, env=env) == 0
-
-
-def test_distutils_local_with_setuptools(venv):
-    """
-    Ensure local distutils is used when appropriate.
-    """
-    env = dict(SETUPTOOLS_USE_DISTUTILS='local')
-    loc = find_distutils(venv, imports='setuptools, distutils', env=env)
-    assert venv.name in loc.split(os.sep)
-    assert count_meta_path(venv, env=env) <= 1
-
-
-@pytest.mark.xfail('IS_PYPY', reason='pypy imports distutils on startup')
-def test_distutils_local(venv):
-    """
-    Even without importing, the setuptools-local copy of distutils is
-    preferred.
-    """
-    env = dict(SETUPTOOLS_USE_DISTUTILS='local')
-    assert venv.name in find_distutils(venv, env=env).split(os.sep)
-    assert count_meta_path(venv, env=env) <= 1
-
-
-def test_pip_import(venv):
-    """
-    Ensure pip can be imported.
-    Regression test for #3002.
-    """
-    cmd = ['python', '-c', 'import pip']
-    venv.run(cmd, **_TEXT_KWARGS)
-
-
-def test_distutils_has_origin():
-    """
-    Distutils module spec should have an origin. #2990.
-    """
-    assert __import__('distutils').__spec__.origin
-
-
-ENSURE_IMPORTS_ARE_NOT_DUPLICATED = r"""
-# Depending on the importlib machinery and _distutils_hack, some imports are
-# duplicated resulting in different module objects being loaded, which prevents
-# patches as shown in #3042.
-# This script provides a way of verifying if this duplication is happening.
-
-from distutils import cmd
-import distutils.command.sdist as sdist
-
-# import last to prevent caching
-from distutils import {imported_module}
-
-for mod in (cmd, sdist):
-    assert mod.{imported_module} == {imported_module}, (
-        f"\n{{mod.dir_util}}\n!=\n{{{imported_module}}}"
-    )
-
-print("success")
-"""
-
-
-@pytest.mark.usefixtures("tmpdir_cwd")
-@pytest.mark.parametrize(
-    ('distutils_version', 'imported_module'),
-    [
-        pytest.param("stdlib", "dir_util", marks=skip_without_stdlib_distutils),
-        pytest.param("stdlib", "file_util", marks=skip_without_stdlib_distutils),
-        pytest.param("stdlib", "archive_util", marks=skip_without_stdlib_distutils),
-        ("local", "dir_util"),
-        ("local", "file_util"),
-        ("local", "archive_util"),
-    ],
-)
-def test_modules_are_not_duplicated_on_import(distutils_version, imported_module, venv):
-    env = dict(SETUPTOOLS_USE_DISTUTILS=distutils_version)
-    script = ENSURE_IMPORTS_ARE_NOT_DUPLICATED.format(imported_module=imported_module)
-    cmd = ['python', '-c', script]
-    output = venv.run(cmd, env=win_sr(env), **_TEXT_KWARGS).strip()
-    assert output == "success"
-
-
-ENSURE_LOG_IMPORT_IS_NOT_DUPLICATED = r"""
-import types
-import distutils.dist as dist
-from distutils import log
-if isinstance(dist.log, types.ModuleType):
-    assert dist.log == log, f"\n{dist.log}\n!=\n{log}"
-print("success")
-"""
-
-
-@pytest.mark.usefixtures("tmpdir_cwd")
-@pytest.mark.parametrize(
-    "distutils_version",
-    [
-        "local",
-        pytest.param("stdlib", marks=skip_without_stdlib_distutils),
-    ],
-)
-def test_log_module_is_not_duplicated_on_import(distutils_version, venv):
-    env = dict(SETUPTOOLS_USE_DISTUTILS=distutils_version)
-    cmd = ['python', '-c', ENSURE_LOG_IMPORT_IS_NOT_DUPLICATED]
-    output = venv.run(cmd, env=win_sr(env), **_TEXT_KWARGS).strip()
-    assert output == "success"
-
-
-ENSURE_CONSISTENT_ERROR_FROM_MODIFIED_PY = r"""
-from setuptools.modified import newer
-from {imported_module}.errors import DistutilsError
-
-# Can't use pytest.raises in this context
-try:
-    newer("", "")
-except DistutilsError:
-    print("success")
-else:
-    raise AssertionError("Expected to raise")
-"""
-
-
-@pytest.mark.usefixtures("tmpdir_cwd")
-@pytest.mark.parametrize(
-    ('distutils_version', 'imported_module'),
-    [
-        ("local", "distutils"),
-        # Unfortunately we still get ._distutils.errors.DistutilsError with SETUPTOOLS_USE_DISTUTILS=stdlib
-        # But that's a deprecated use-case we don't mind not fully supporting in newer code
-        pytest.param(
-            "stdlib", "setuptools._distutils", marks=skip_without_stdlib_distutils
-        ),
-    ],
-)
-def test_consistent_error_from_modified_py(distutils_version, imported_module, venv):
-    env = dict(SETUPTOOLS_USE_DISTUTILS=distutils_version)
-    cmd = [
-        'python',
-        '-c',
-        ENSURE_CONSISTENT_ERROR_FROM_MODIFIED_PY.format(
-            imported_module=imported_module
-        ),
-    ]
-    output = venv.run(cmd, env=win_sr(env), **_TEXT_KWARGS).strip()
-    assert output == "success"
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_easy_install.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_easy_install.py
deleted file mode 100644
index b58b0b6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_easy_install.py
+++ /dev/null
@@ -1,1476 +0,0 @@
-"""Easy install Tests"""
-
-import contextlib
-import io
-import itertools
-import logging
-import os
-import pathlib
-import re
-import site
-import subprocess
-import sys
-import tarfile
-import tempfile
-import time
-import warnings
-import zipfile
-from pathlib import Path
-from typing import NamedTuple
-from unittest import mock
-
-import pytest
-from jaraco import path
-
-import pkg_resources
-import setuptools.command.easy_install as ei
-from pkg_resources import Distribution as PRDistribution, normalize_path, working_set
-from setuptools import sandbox
-from setuptools._normalization import safer_name
-from setuptools.command.easy_install import PthDistributions
-from setuptools.dist import Distribution
-from setuptools.sandbox import run_setup
-from setuptools.tests import fail_on_ascii
-from setuptools.tests.server import MockServer, path_to_url
-
-from . import contexts
-from .textwrap import DALS
-
-import distutils.errors
-
-
-@pytest.fixture(autouse=True)
-def pip_disable_index(monkeypatch):
-    """
-    Important: Disable the default index for pip to avoid
-    querying packages in the index and potentially resolving
-    and installing packages there.
-    """
-    monkeypatch.setenv('PIP_NO_INDEX', 'true')
-
-
-class FakeDist:
-    def get_entry_map(self, group):
-        if group != 'console_scripts':
-            return {}
-        return {'name': 'ep'}
-
-    def as_requirement(self):
-        return 'spec'
-
-
-SETUP_PY = DALS(
-    """
-    from setuptools import setup
-
-    setup()
-    """
-)
-
-
-class TestEasyInstallTest:
-    def test_get_script_args(self):
-        header = ei.CommandSpec.best().from_environment().as_header()
-        dist = FakeDist()
-        args = next(ei.ScriptWriter.get_args(dist))
-        _name, script = itertools.islice(args, 2)
-        assert script.startswith(header)
-        assert "'spec'" in script
-        assert "'console_scripts'" in script
-        assert "'name'" in script
-        assert re.search('^# EASY-INSTALL-ENTRY-SCRIPT', script, flags=re.MULTILINE)
-
-    def test_no_find_links(self):
-        # new option '--no-find-links', that blocks find-links added at
-        # the project level
-        dist = Distribution()
-        cmd = ei.easy_install(dist)
-        cmd.check_pth_processing = lambda: True
-        cmd.no_find_links = True
-        cmd.find_links = ['link1', 'link2']
-        cmd.install_dir = os.path.join(tempfile.mkdtemp(), 'ok')
-        cmd.args = ['ok']
-        cmd.ensure_finalized()
-        assert cmd.package_index.scanned_urls == {}
-
-        # let's try without it (default behavior)
-        cmd = ei.easy_install(dist)
-        cmd.check_pth_processing = lambda: True
-        cmd.find_links = ['link1', 'link2']
-        cmd.install_dir = os.path.join(tempfile.mkdtemp(), 'ok')
-        cmd.args = ['ok']
-        cmd.ensure_finalized()
-        keys = sorted(cmd.package_index.scanned_urls.keys())
-        assert keys == ['link1', 'link2']
-
-    def test_write_exception(self):
-        """
-        Test that `cant_write_to_target` is rendered as a DistutilsError.
-        """
-        dist = Distribution()
-        cmd = ei.easy_install(dist)
-        cmd.install_dir = os.getcwd()
-        with pytest.raises(distutils.errors.DistutilsError):
-            cmd.cant_write_to_target()
-
-    def test_all_site_dirs(self, monkeypatch):
-        """
-        get_site_dirs should always return site dirs reported by
-        site.getsitepackages.
-        """
-        path = normalize_path('/setuptools/test/site-packages')
-
-        def mock_gsp():
-            return [path]
-
-        monkeypatch.setattr(site, 'getsitepackages', mock_gsp, raising=False)
-        assert path in ei.get_site_dirs()
-
-    def test_all_site_dirs_works_without_getsitepackages(self, monkeypatch):
-        monkeypatch.delattr(site, 'getsitepackages', raising=False)
-        assert ei.get_site_dirs()
-
-    @pytest.fixture
-    def sdist_unicode(self, tmpdir):
-        files = [
-            (
-                'setup.py',
-                DALS(
-                    """
-                    import setuptools
-                    setuptools.setup(
-                        name="setuptools-test-unicode",
-                        version="1.0",
-                        packages=["mypkg"],
-                        include_package_data=True,
-                    )
-                    """
-                ),
-            ),
-            (
-                'mypkg/__init__.py',
-                "",
-            ),
-            (
-                'mypkg/☃.txt',
-                "",
-            ),
-        ]
-        sdist_name = 'setuptools-test-unicode-1.0.zip'
-        sdist = tmpdir / sdist_name
-        # can't use make_sdist, because the issue only occurs
-        #  with zip sdists.
-        sdist_zip = zipfile.ZipFile(str(sdist), 'w')
-        for filename, content in files:
-            sdist_zip.writestr(filename, content)
-        sdist_zip.close()
-        return str(sdist)
-
-    @fail_on_ascii
-    def test_unicode_filename_in_sdist(self, sdist_unicode, tmpdir, monkeypatch):
-        """
-        The install command should execute correctly even if
-        the package has unicode filenames.
-        """
-        dist = Distribution({'script_args': ['easy_install']})
-        target = (tmpdir / 'target').ensure_dir()
-        cmd = ei.easy_install(
-            dist,
-            install_dir=str(target),
-            args=['x'],
-        )
-        monkeypatch.setitem(os.environ, 'PYTHONPATH', str(target))
-        cmd.ensure_finalized()
-        cmd.easy_install(sdist_unicode)
-
-    @pytest.fixture
-    def sdist_unicode_in_script(self, tmpdir):
-        files = [
-            (
-                "setup.py",
-                DALS(
-                    """
-                    import setuptools
-                    setuptools.setup(
-                        name="setuptools-test-unicode",
-                        version="1.0",
-                        packages=["mypkg"],
-                        include_package_data=True,
-                        scripts=['mypkg/unicode_in_script'],
-                    )
-                    """
-                ),
-            ),
-            ("mypkg/__init__.py", ""),
-            (
-                "mypkg/unicode_in_script",
-                DALS(
-                    """
-                    #!/bin/sh
-                    # á
-
-                    non_python_fn() {
-                    }
-                """
-                ),
-            ),
-        ]
-        sdist_name = "setuptools-test-unicode-script-1.0.zip"
-        sdist = tmpdir / sdist_name
-        # can't use make_sdist, because the issue only occurs
-        #  with zip sdists.
-        sdist_zip = zipfile.ZipFile(str(sdist), "w")
-        for filename, content in files:
-            sdist_zip.writestr(filename, content.encode('utf-8'))
-        sdist_zip.close()
-        return str(sdist)
-
-    @fail_on_ascii
-    def test_unicode_content_in_sdist(
-        self, sdist_unicode_in_script, tmpdir, monkeypatch
-    ):
-        """
-        The install command should execute correctly even if
-        the package has unicode in scripts.
-        """
-        dist = Distribution({"script_args": ["easy_install"]})
-        target = (tmpdir / "target").ensure_dir()
-        cmd = ei.easy_install(dist, install_dir=str(target), args=["x"])
-        monkeypatch.setitem(os.environ, "PYTHONPATH", str(target))
-        cmd.ensure_finalized()
-        cmd.easy_install(sdist_unicode_in_script)
-
-    @pytest.fixture
-    def sdist_script(self, tmpdir):
-        files = [
-            (
-                'setup.py',
-                DALS(
-                    """
-                    import setuptools
-                    setuptools.setup(
-                        name="setuptools-test-script",
-                        version="1.0",
-                        scripts=["mypkg_script"],
-                    )
-                    """
-                ),
-            ),
-            (
-                'mypkg_script',
-                DALS(
-                    """
-                     #/usr/bin/python
-                     print('mypkg_script')
-                     """
-                ),
-            ),
-        ]
-        sdist_name = 'setuptools-test-script-1.0.zip'
-        sdist = str(tmpdir / sdist_name)
-        make_sdist(sdist, files)
-        return sdist
-
-    @pytest.mark.skipif(
-        not sys.platform.startswith('linux'), reason="Test can only be run on Linux"
-    )
-    def test_script_install(self, sdist_script, tmpdir, monkeypatch):
-        """
-        Check scripts are installed.
-        """
-        dist = Distribution({'script_args': ['easy_install']})
-        target = (tmpdir / 'target').ensure_dir()
-        cmd = ei.easy_install(
-            dist,
-            install_dir=str(target),
-            args=['x'],
-        )
-        monkeypatch.setitem(os.environ, 'PYTHONPATH', str(target))
-        cmd.ensure_finalized()
-        cmd.easy_install(sdist_script)
-        assert (target / 'mypkg_script').exists()
-
-
-@pytest.mark.filterwarnings('ignore:Unbuilt egg')
-class TestPTHFileWriter:
-    def test_add_from_cwd_site_sets_dirty(self):
-        """a pth file manager should set dirty
-        if a distribution is in site but also the cwd
-        """
-        pth = PthDistributions('does-not_exist', [os.getcwd()])
-        assert not pth.dirty
-        pth.add(PRDistribution(os.getcwd()))
-        assert pth.dirty
-
-    def test_add_from_site_is_ignored(self):
-        location = '/test/location/does-not-have-to-exist'
-        # PthDistributions expects all locations to be normalized
-        location = pkg_resources.normalize_path(location)
-        pth = PthDistributions(
-            'does-not_exist',
-            [
-                location,
-            ],
-        )
-        assert not pth.dirty
-        pth.add(PRDistribution(location))
-        assert not pth.dirty
-
-    def test_many_pth_distributions_merge_together(self, tmpdir):
-        """
-        If the pth file is modified under the hood, then PthDistribution
-        will refresh its content before saving, merging contents when
-        necessary.
-        """
-        # putting the pth file in a dedicated sub-folder,
-        pth_subdir = tmpdir.join("pth_subdir")
-        pth_subdir.mkdir()
-        pth_path = str(pth_subdir.join("file1.pth"))
-        pth1 = PthDistributions(pth_path)
-        pth2 = PthDistributions(pth_path)
-        assert pth1.paths == pth2.paths == [], (
-            "unless there would be some default added at some point"
-        )
-        # and so putting the src_subdir in folder distinct than the pth one,
-        # so to keep it absolute by PthDistributions
-        new_src_path = tmpdir.join("src_subdir")
-        new_src_path.mkdir()  # must exist to be accounted
-        new_src_path_str = str(new_src_path)
-        pth1.paths.append(new_src_path_str)
-        pth1.save()
-        assert pth1.paths, (
-            "the new_src_path added must still be present/valid in pth1 after save"
-        )
-        # now,
-        assert new_src_path_str not in pth2.paths, (
-            "right before we save the entry should still not be present"
-        )
-        pth2.save()
-        assert new_src_path_str in pth2.paths, (
-            "the new_src_path entry should have been added by pth2 with its save() call"
-        )
-        assert pth2.paths[-1] == new_src_path, (
-            "and it should match exactly on the last entry actually "
-            "given we append to it in save()"
-        )
-        # finally,
-        assert PthDistributions(pth_path).paths == pth2.paths, (
-            "and we should have the exact same list at the end "
-            "with a fresh PthDistributions instance"
-        )
-
-
-@pytest.fixture
-def setup_context(tmpdir):
-    with (tmpdir / 'setup.py').open('w', encoding="utf-8") as f:
-        f.write(SETUP_PY)
-    with tmpdir.as_cwd():
-        yield tmpdir
-
-
-@pytest.mark.usefixtures("user_override")
-@pytest.mark.usefixtures("setup_context")
-class TestUserInstallTest:
-    # prevent check that site-packages is writable. easy_install
-    # shouldn't be writing to system site-packages during finalize
-    # options, but while it does, bypass the behavior.
-    prev_sp_write = mock.patch(
-        'setuptools.command.easy_install.easy_install.check_site_dir',
-        mock.Mock(),
-    )
-
-    # simulate setuptools installed in user site packages
-    @mock.patch('setuptools.command.easy_install.__file__', site.USER_SITE)
-    @mock.patch('site.ENABLE_USER_SITE', True)
-    @prev_sp_write
-    def test_user_install_not_implied_user_site_enabled(self):
-        self.assert_not_user_site()
-
-    @mock.patch('site.ENABLE_USER_SITE', False)
-    @prev_sp_write
-    def test_user_install_not_implied_user_site_disabled(self):
-        self.assert_not_user_site()
-
-    @staticmethod
-    def assert_not_user_site():
-        # create a finalized easy_install command
-        dist = Distribution()
-        dist.script_name = 'setup.py'
-        cmd = ei.easy_install(dist)
-        cmd.args = ['py']
-        cmd.ensure_finalized()
-        assert not cmd.user, 'user should not be implied'
-
-    def test_multiproc_atexit(self):
-        pytest.importorskip('multiprocessing')
-
-        log = logging.getLogger('test_easy_install')
-        logging.basicConfig(level=logging.INFO, stream=sys.stderr)
-        log.info('this should not break')
-
-    @pytest.fixture
-    def foo_package(self, tmpdir):
-        egg_file = tmpdir / 'foo-1.0.egg-info'
-        with egg_file.open('w') as f:
-            f.write('Name: foo\n')
-        return str(tmpdir)
-
-    @pytest.fixture
-    def install_target(self, tmpdir):
-        target = str(tmpdir)
-        with mock.patch('sys.path', sys.path + [target]):
-            python_path = os.path.pathsep.join(sys.path)
-            with mock.patch.dict(os.environ, PYTHONPATH=python_path):
-                yield target
-
-    def test_local_index(self, foo_package, install_target):
-        """
-        The local index must be used when easy_install locates installed
-        packages.
-        """
-        dist = Distribution()
-        dist.script_name = 'setup.py'
-        cmd = ei.easy_install(dist)
-        cmd.install_dir = install_target
-        cmd.args = ['foo']
-        cmd.ensure_finalized()
-        cmd.local_index.scan([foo_package])
-        res = cmd.easy_install('foo')
-        actual = os.path.normcase(os.path.realpath(res.location))
-        expected = os.path.normcase(os.path.realpath(foo_package))
-        assert actual == expected
-
-    @contextlib.contextmanager
-    def user_install_setup_context(self, *args, **kwargs):
-        """
-        Wrap sandbox.setup_context to patch easy_install in that context to
-        appear as user-installed.
-        """
-        with self.orig_context(*args, **kwargs):
-            import setuptools.command.easy_install as ei
-
-            ei.__file__ = site.USER_SITE
-            yield
-
-    def patched_setup_context(self):
-        self.orig_context = sandbox.setup_context
-
-        return mock.patch(
-            'setuptools.sandbox.setup_context',
-            self.user_install_setup_context,
-        )
-
-
-@pytest.fixture
-def distutils_package():
-    distutils_setup_py = SETUP_PY.replace(
-        'from setuptools import setup',
-        'from distutils.core import setup',
-    )
-    with contexts.tempdir(cd=os.chdir):
-        with open('setup.py', 'w', encoding="utf-8") as f:
-            f.write(distutils_setup_py)
-        yield
-
-
-@pytest.mark.usefixtures("distutils_package")
-class TestDistutilsPackage:
-    def test_bdist_egg_available_on_distutils_pkg(self):
-        run_setup('setup.py', ['bdist_egg'])
-
-
-@pytest.fixture
-def mock_index():
-    # set up a server which will simulate an alternate package index.
-    p_index = MockServer()
-    if p_index.server_port == 0:
-        # Some platforms (Jython) don't find a port to which to bind,
-        # so skip test for them.
-        pytest.skip("could not find a valid port")
-    p_index.start()
-    return p_index
-
-
-class TestInstallRequires:
-    def test_setup_install_includes_dependencies(self, tmp_path, mock_index):
-        """
-        When ``python setup.py install`` is called directly, it will use easy_install
-        to fetch dependencies.
-        """
-        # TODO: Remove these tests once `setup.py install` is completely removed
-        project_root = tmp_path / "project"
-        project_root.mkdir(exist_ok=True)
-        install_root = tmp_path / "install"
-        install_root.mkdir(exist_ok=True)
-
-        self.create_project(project_root)
-        cmd = [
-            sys.executable,
-            '-c',
-            '__import__("setuptools").setup()',
-            'install',
-            '--install-base',
-            str(install_root),
-            '--install-lib',
-            str(install_root),
-            '--install-headers',
-            str(install_root),
-            '--install-scripts',
-            str(install_root),
-            '--install-data',
-            str(install_root),
-            '--install-purelib',
-            str(install_root),
-            '--install-platlib',
-            str(install_root),
-        ]
-        env = {**os.environ, "__EASYINSTALL_INDEX": mock_index.url}
-        cp = subprocess.run(
-            cmd,
-            cwd=str(project_root),
-            env=env,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.STDOUT,
-            text=True,
-            encoding="utf-8",
-        )
-        assert cp.returncode != 0
-        try:
-            assert '/does-not-exist/' in {r.path for r in mock_index.requests}
-            assert next(
-                line
-                for line in cp.stdout.splitlines()
-                if "not find suitable distribution for" in line
-                and "does-not-exist" in line
-            )
-        except Exception:
-            if "failed to get random numbers" in cp.stdout:
-                pytest.xfail(f"{sys.platform} failure - {cp.stdout}")
-            raise
-
-    def create_project(self, root):
-        config = """
-        [metadata]
-        name = project
-        version = 42
-
-        [options]
-        install_requires = does-not-exist
-        py_modules = mod
-        """
-        (root / 'setup.cfg').write_text(DALS(config), encoding="utf-8")
-        (root / 'mod.py').touch()
-
-
-class TestSetupRequires:
-    def test_setup_requires_honors_fetch_params(self, mock_index, monkeypatch):
-        """
-        When easy_install installs a source distribution which specifies
-        setup_requires, it should honor the fetch parameters (such as
-        index-url, and find-links).
-        """
-        monkeypatch.setenv('PIP_RETRIES', '0')
-        monkeypatch.setenv('PIP_TIMEOUT', '0')
-        monkeypatch.setenv('PIP_NO_INDEX', 'false')
-        with contexts.quiet():
-            # create an sdist that has a build-time dependency.
-            with TestSetupRequires.create_sdist() as dist_file:
-                with contexts.tempdir() as temp_install_dir:
-                    with contexts.environment(PYTHONPATH=temp_install_dir):
-                        cmd = [
-                            sys.executable,
-                            '-c',
-                            '__import__("setuptools").setup()',
-                            'easy_install',
-                            '--index-url',
-                            mock_index.url,
-                            '--exclude-scripts',
-                            '--install-dir',
-                            temp_install_dir,
-                            dist_file,
-                        ]
-                        subprocess.Popen(cmd).wait()
-        # there should have been one requests to the server
-        assert [r.path for r in mock_index.requests] == ['/does-not-exist/']
-
-    @staticmethod
-    @contextlib.contextmanager
-    def create_sdist():
-        """
-        Return an sdist with a setup_requires dependency (of something that
-        doesn't exist)
-        """
-        with contexts.tempdir() as dir:
-            dist_path = os.path.join(dir, 'setuptools-test-fetcher-1.0.tar.gz')
-            make_sdist(
-                dist_path,
-                [
-                    (
-                        'setup.py',
-                        DALS(
-                            """
-                    import setuptools
-                    setuptools.setup(
-                        name="setuptools-test-fetcher",
-                        version="1.0",
-                        setup_requires = ['does-not-exist'],
-                    )
-                """
-                        ),
-                    ),
-                    ('setup.cfg', ''),
-                ],
-            )
-            yield dist_path
-
-    use_setup_cfg = (
-        (),
-        ('dependency_links',),
-        ('setup_requires',),
-        ('dependency_links', 'setup_requires'),
-    )
-
-    @pytest.mark.parametrize('use_setup_cfg', use_setup_cfg)
-    def test_setup_requires_overrides_version_conflict(self, use_setup_cfg):
-        """
-        Regression test for distribution issue 323:
-        https://bitbucket.org/tarek/distribute/issues/323
-
-        Ensures that a distribution's setup_requires requirements can still be
-        installed and used locally even if a conflicting version of that
-        requirement is already on the path.
-        """
-
-        fake_dist = PRDistribution(
-            'does-not-matter', project_name='foobar', version='0.0'
-        )
-        working_set.add(fake_dist)
-
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                test_pkg = create_setup_requires_package(
-                    temp_dir, use_setup_cfg=use_setup_cfg
-                )
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-                with contexts.quiet() as (stdout, _stderr):
-                    # Don't even need to install the package, just
-                    # running the setup.py at all is sufficient
-                    run_setup(test_setup_py, ['--name'])
-
-                lines = stdout.readlines()
-                assert len(lines) > 0
-                assert lines[-1].strip() == 'test_pkg'
-
-    @pytest.mark.parametrize('use_setup_cfg', use_setup_cfg)
-    def test_setup_requires_override_nspkg(self, use_setup_cfg):
-        """
-        Like ``test_setup_requires_overrides_version_conflict`` but where the
-        ``setup_requires`` package is part of a namespace package that has
-        *already* been imported.
-        """
-
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                foobar_1_archive = os.path.join(temp_dir, 'foo_bar-0.1.tar.gz')
-                make_nspkg_sdist(foobar_1_archive, 'foo.bar', '0.1')
-                # Now actually go ahead an extract to the temp dir and add the
-                # extracted path to sys.path so foo.bar v0.1 is importable
-                foobar_1_dir = os.path.join(temp_dir, 'foo_bar-0.1')
-                os.mkdir(foobar_1_dir)
-                with tarfile.open(foobar_1_archive) as tf:
-                    tf.extraction_filter = lambda member, path: member
-                    tf.extractall(foobar_1_dir)
-                sys.path.insert(1, foobar_1_dir)
-
-                dist = PRDistribution(
-                    foobar_1_dir, project_name='foo.bar', version='0.1'
-                )
-                working_set.add(dist)
-
-                template = DALS(
-                    """\
-                    import foo  # Even with foo imported first the
-                                # setup_requires package should override
-                    import setuptools
-                    setuptools.setup(**%r)
-
-                    if not (hasattr(foo, '__path__') and
-                            len(foo.__path__) == 2):
-                        print('FAIL')
-
-                    if 'foo_bar-0.2' not in foo.__path__[0]:
-                        print('FAIL')
-                """
-                )
-
-                test_pkg = create_setup_requires_package(
-                    temp_dir,
-                    'foo.bar',
-                    '0.2',
-                    make_nspkg_sdist,
-                    template,
-                    use_setup_cfg=use_setup_cfg,
-                )
-
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-
-                with contexts.quiet() as (stdout, _stderr):
-                    try:
-                        # Don't even need to install the package, just
-                        # running the setup.py at all is sufficient
-                        run_setup(test_setup_py, ['--name'])
-                    except pkg_resources.VersionConflict:  # pragma: nocover
-                        pytest.fail(
-                            'Installing setup.py requirements caused a VersionConflict'
-                        )
-
-                assert 'FAIL' not in stdout.getvalue()
-                lines = stdout.readlines()
-                assert len(lines) > 0
-                assert lines[-1].strip() == 'test_pkg'
-
-    @pytest.mark.parametrize('use_setup_cfg', use_setup_cfg)
-    def test_setup_requires_with_attr_version(self, use_setup_cfg):
-        def make_dependency_sdist(dist_path, distname, version):
-            files = [
-                (
-                    'setup.py',
-                    DALS(
-                        f"""
-                    import setuptools
-                    setuptools.setup(
-                        name={distname!r},
-                        version={version!r},
-                        py_modules=[{distname!r}],
-                    )
-                    """
-                    ),
-                ),
-                (
-                    distname + '.py',
-                    DALS(
-                        """
-                    version = 42
-                    """
-                    ),
-                ),
-            ]
-            make_sdist(dist_path, files)
-
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                test_pkg = create_setup_requires_package(
-                    temp_dir,
-                    setup_attrs=dict(version='attr: foobar.version'),
-                    make_package=make_dependency_sdist,
-                    use_setup_cfg=use_setup_cfg + ('version',),
-                )
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-                with contexts.quiet() as (stdout, _stderr):
-                    run_setup(test_setup_py, ['--version'])
-                lines = stdout.readlines()
-                assert len(lines) > 0
-                assert lines[-1].strip() == '42'
-
-    def test_setup_requires_honors_pip_env(self, mock_index, monkeypatch):
-        monkeypatch.setenv('PIP_RETRIES', '0')
-        monkeypatch.setenv('PIP_TIMEOUT', '0')
-        monkeypatch.setenv('PIP_NO_INDEX', 'false')
-        monkeypatch.setenv('PIP_INDEX_URL', mock_index.url)
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                test_pkg = create_setup_requires_package(
-                    temp_dir,
-                    'python-xlib',
-                    '0.19',
-                    setup_attrs=dict(dependency_links=[]),
-                )
-                test_setup_cfg = os.path.join(test_pkg, 'setup.cfg')
-                with open(test_setup_cfg, 'w', encoding="utf-8") as fp:
-                    fp.write(
-                        DALS(
-                            """
-                        [easy_install]
-                        index_url = https://pypi.org/legacy/
-                        """
-                        )
-                    )
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-                with pytest.raises(distutils.errors.DistutilsError):
-                    run_setup(test_setup_py, ['--version'])
-        assert len(mock_index.requests) == 1
-        assert mock_index.requests[0].path == '/python-xlib/'
-
-    def test_setup_requires_with_pep508_url(self, mock_index, monkeypatch):
-        monkeypatch.setenv('PIP_RETRIES', '0')
-        monkeypatch.setenv('PIP_TIMEOUT', '0')
-        monkeypatch.setenv('PIP_INDEX_URL', mock_index.url)
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                dep_sdist = os.path.join(temp_dir, 'dep.tar.gz')
-                make_trivial_sdist(dep_sdist, 'dependency', '42')
-                dep_url = path_to_url(dep_sdist, authority='localhost')
-                test_pkg = create_setup_requires_package(
-                    temp_dir,
-                    # Ignored (overridden by setup_attrs)
-                    'python-xlib',
-                    '0.19',
-                    setup_attrs=dict(setup_requires=f'dependency @ {dep_url}'),
-                )
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-                run_setup(test_setup_py, ['--version'])
-        assert len(mock_index.requests) == 0
-
-    def test_setup_requires_with_allow_hosts(self, mock_index):
-        """The `allow-hosts` option in not supported anymore."""
-        files = {
-            'test_pkg': {
-                'setup.py': DALS(
-                    """
-                    from setuptools import setup
-                    setup(setup_requires='python-xlib')
-                    """
-                ),
-                'setup.cfg': DALS(
-                    """
-                    [easy_install]
-                    allow_hosts = *
-                    """
-                ),
-            }
-        }
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                path.build(files, prefix=temp_dir)
-                setup_py = str(pathlib.Path(temp_dir, 'test_pkg', 'setup.py'))
-                with pytest.raises(distutils.errors.DistutilsError):
-                    run_setup(setup_py, ['--version'])
-        assert len(mock_index.requests) == 0
-
-    def test_setup_requires_with_python_requires(self, monkeypatch, tmpdir):
-        """Check `python_requires` is honored."""
-        monkeypatch.setenv('PIP_RETRIES', '0')
-        monkeypatch.setenv('PIP_TIMEOUT', '0')
-        monkeypatch.setenv('PIP_NO_INDEX', '1')
-        monkeypatch.setenv('PIP_VERBOSE', '1')
-        dep_1_0_sdist = 'dep-1.0.tar.gz'
-        dep_1_0_url = path_to_url(str(tmpdir / dep_1_0_sdist))
-        dep_1_0_python_requires = '>=2.7'
-        make_python_requires_sdist(
-            str(tmpdir / dep_1_0_sdist), 'dep', '1.0', dep_1_0_python_requires
-        )
-        dep_2_0_sdist = 'dep-2.0.tar.gz'
-        dep_2_0_url = path_to_url(str(tmpdir / dep_2_0_sdist))
-        dep_2_0_python_requires = (
-            f'!={sys.version_info.major}.{sys.version_info.minor}.*'
-        )
-        make_python_requires_sdist(
-            str(tmpdir / dep_2_0_sdist), 'dep', '2.0', dep_2_0_python_requires
-        )
-        index = tmpdir / 'index.html'
-        index.write_text(
-            DALS(
-                """
-            
-            Links for dep
-            
-                
Links for dep

-                {dep_1_0_sdist}

-                {dep_2_0_sdist}

-            
-            
-            """
-            ).format(
-                dep_1_0_url=dep_1_0_url,
-                dep_1_0_sdist=dep_1_0_sdist,
-                dep_1_0_python_requires=dep_1_0_python_requires,
-                dep_2_0_url=dep_2_0_url,
-                dep_2_0_sdist=dep_2_0_sdist,
-                dep_2_0_python_requires=dep_2_0_python_requires,
-            ),
-            'utf-8',
-        )
-        index_url = path_to_url(str(index))
-        with contexts.save_pkg_resources_state():
-            test_pkg = create_setup_requires_package(
-                str(tmpdir),
-                'python-xlib',
-                '0.19',  # Ignored (overridden by setup_attrs).
-                setup_attrs=dict(setup_requires='dep', dependency_links=[index_url]),
-            )
-            test_setup_py = os.path.join(test_pkg, 'setup.py')
-            run_setup(test_setup_py, ['--version'])
-        eggs = list(
-            map(str, pkg_resources.find_distributions(os.path.join(test_pkg, '.eggs')))
-        )
-        assert eggs == ['dep 1.0']
-
-    @pytest.mark.parametrize('with_dependency_links_in_setup_py', (False, True))
-    def test_setup_requires_with_find_links_in_setup_cfg(
-        self, monkeypatch, with_dependency_links_in_setup_py
-    ):
-        monkeypatch.setenv('PIP_RETRIES', '0')
-        monkeypatch.setenv('PIP_TIMEOUT', '0')
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                make_trivial_sdist(
-                    os.path.join(temp_dir, 'python-xlib-42.tar.gz'), 'python-xlib', '42'
-                )
-                test_pkg = os.path.join(temp_dir, 'test_pkg')
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-                test_setup_cfg = os.path.join(test_pkg, 'setup.cfg')
-                os.mkdir(test_pkg)
-                with open(test_setup_py, 'w', encoding="utf-8") as fp:
-                    if with_dependency_links_in_setup_py:
-                        dependency_links = [os.path.join(temp_dir, 'links')]
-                    else:
-                        dependency_links = []
-                    fp.write(
-                        DALS(
-                            """
-                        from setuptools import installer, setup
-                        setup(setup_requires='python-xlib==42',
-                        dependency_links={dependency_links!r})
-                        """
-                        ).format(dependency_links=dependency_links)
-                    )
-                with open(test_setup_cfg, 'w', encoding="utf-8") as fp:
-                    fp.write(
-                        DALS(
-                            """
-                        [easy_install]
-                        index_url = {index_url}
-                        find_links = {find_links}
-                        """
-                        ).format(
-                            index_url=os.path.join(temp_dir, 'index'),
-                            find_links=temp_dir,
-                        )
-                    )
-                run_setup(test_setup_py, ['--version'])
-
-    def test_setup_requires_with_transitive_extra_dependency(self, monkeypatch):
-        """
-        Use case: installing a package with a build dependency on
-        an already installed `dep[extra]`, which in turn depends
-        on `extra_dep` (whose is not already installed).
-        """
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                # Create source distribution for `extra_dep`.
-                make_trivial_sdist(
-                    os.path.join(temp_dir, 'extra_dep-1.0.tar.gz'), 'extra_dep', '1.0'
-                )
-                # Create source tree for `dep`.
-                dep_pkg = os.path.join(temp_dir, 'dep')
-                os.mkdir(dep_pkg)
-                path.build(
-                    {
-                        'setup.py': DALS(
-                            """
-                          import setuptools
-                          setuptools.setup(
-                              name='dep', version='2.0',
-                              extras_require={'extra': ['extra_dep']},
-                          )
-                         """
-                        ),
-                        'setup.cfg': '',
-                    },
-                    prefix=dep_pkg,
-                )
-                # "Install" dep.
-                run_setup(os.path.join(dep_pkg, 'setup.py'), ['dist_info'])
-                working_set.add_entry(dep_pkg)
-                # Create source tree for test package.
-                test_pkg = os.path.join(temp_dir, 'test_pkg')
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-                os.mkdir(test_pkg)
-                with open(test_setup_py, 'w', encoding="utf-8") as fp:
-                    fp.write(
-                        DALS(
-                            """
-                        from setuptools import installer, setup
-                        setup(setup_requires='dep[extra]')
-                        """
-                        )
-                    )
-                # Check...
-                monkeypatch.setenv('PIP_FIND_LINKS', str(temp_dir))
-                monkeypatch.setenv('PIP_NO_INDEX', '1')
-                monkeypatch.setenv('PIP_RETRIES', '0')
-                monkeypatch.setenv('PIP_TIMEOUT', '0')
-                run_setup(test_setup_py, ['--version'])
-
-    def test_setup_requires_with_distutils_command_dep(self, monkeypatch):
-        """
-        Use case: ensure build requirements' extras
-        are properly installed and activated.
-        """
-        with contexts.save_pkg_resources_state():
-            with contexts.tempdir() as temp_dir:
-                # Create source distribution for `extra_dep`.
-                make_sdist(
-                    os.path.join(temp_dir, 'extra_dep-1.0.tar.gz'),
-                    [
-                        (
-                            'setup.py',
-                            DALS(
-                                """
-                          import setuptools
-                          setuptools.setup(
-                              name='extra_dep',
-                              version='1.0',
-                              py_modules=['extra_dep'],
-                          )
-                          """
-                            ),
-                        ),
-                        ('setup.cfg', ''),
-                        ('extra_dep.py', ''),
-                    ],
-                )
-                # Create source tree for `epdep`.
-                dep_pkg = os.path.join(temp_dir, 'epdep')
-                os.mkdir(dep_pkg)
-                path.build(
-                    {
-                        'setup.py': DALS(
-                            """
-                          import setuptools
-                          setuptools.setup(
-                              name='dep', version='2.0',
-                              py_modules=['epcmd'],
-                              extras_require={'extra': ['extra_dep']},
-                              entry_points='''
-                                           [distutils.commands]
-                                           epcmd = epcmd:epcmd [extra]
-                                           ''',
-                          )
-                         """
-                        ),
-                        'setup.cfg': '',
-                        'epcmd.py': DALS(
-                            """
-                                     from distutils.command.build_py import build_py
-
-                                     import extra_dep
-
-                                     class epcmd(build_py):
-                                         pass
-                                     """
-                        ),
-                    },
-                    prefix=dep_pkg,
-                )
-                # "Install" dep.
-                run_setup(os.path.join(dep_pkg, 'setup.py'), ['dist_info'])
-                working_set.add_entry(dep_pkg)
-                # Create source tree for test package.
-                test_pkg = os.path.join(temp_dir, 'test_pkg')
-                test_setup_py = os.path.join(test_pkg, 'setup.py')
-                os.mkdir(test_pkg)
-                with open(test_setup_py, 'w', encoding="utf-8") as fp:
-                    fp.write(
-                        DALS(
-                            """
-                        from setuptools import installer, setup
-                        setup(setup_requires='dep[extra]')
-                        """
-                        )
-                    )
-                # Check...
-                monkeypatch.setenv('PIP_FIND_LINKS', str(temp_dir))
-                monkeypatch.setenv('PIP_NO_INDEX', '1')
-                monkeypatch.setenv('PIP_RETRIES', '0')
-                monkeypatch.setenv('PIP_TIMEOUT', '0')
-                run_setup(test_setup_py, ['epcmd'])
-
-
-def make_trivial_sdist(dist_path, distname, version):
-    """
-    Create a simple sdist tarball at dist_path, containing just a simple
-    setup.py.
-    """
-
-    make_sdist(
-        dist_path,
-        [
-            (
-                'setup.py',
-                DALS(
-                    f"""\
-             import setuptools
-             setuptools.setup(
-                 name={distname!r},
-                 version={version!r}
-             )
-         """
-                ),
-            ),
-            ('setup.cfg', ''),
-        ],
-    )
-
-
-def make_nspkg_sdist(dist_path, distname, version):
-    """
-    Make an sdist tarball with distname and version which also contains one
-    package with the same name as distname.  The top-level package is
-    designated a namespace package).
-    """
-    # Assert that the distname contains at least one period
-    assert '.' in distname
-
-    parts = distname.split('.')
-    nspackage = parts[0]
-
-    packages = ['.'.join(parts[:idx]) for idx in range(1, len(parts) + 1)]
-
-    setup_py = DALS(
-        f"""\
-        import setuptools
-        setuptools.setup(
-            name={distname!r},
-            version={version!r},
-            packages={packages!r},
-            namespace_packages=[{nspackage!r}]
-        )
-    """
-    )
-
-    init = "__import__('pkg_resources').declare_namespace(__name__)"
-
-    files = [('setup.py', setup_py), (os.path.join(nspackage, '__init__.py'), init)]
-    for package in packages[1:]:
-        filename = os.path.join(*(package.split('.') + ['__init__.py']))
-        files.append((filename, ''))
-
-    make_sdist(dist_path, files)
-
-
-def make_python_requires_sdist(dist_path, distname, version, python_requires):
-    make_sdist(
-        dist_path,
-        [
-            (
-                'setup.py',
-                DALS(
-                    """\
-                import setuptools
-                setuptools.setup(
-                  name={name!r},
-                  version={version!r},
-                  python_requires={python_requires!r},
-                )
-                """
-                ).format(
-                    name=distname, version=version, python_requires=python_requires
-                ),
-            ),
-            ('setup.cfg', ''),
-        ],
-    )
-
-
-def make_sdist(dist_path, files):
-    """
-    Create a simple sdist tarball at dist_path, containing the files
-    listed in ``files`` as ``(filename, content)`` tuples.
-    """
-
-    # Distributions with only one file don't play well with pip.
-    assert len(files) > 1
-    with tarfile.open(dist_path, 'w:gz') as dist:
-        for filename, content in files:
-            file_bytes = io.BytesIO(content.encode('utf-8'))
-            file_info = tarfile.TarInfo(name=filename)
-            file_info.size = len(file_bytes.getvalue())
-            file_info.mtime = int(time.time())
-            dist.addfile(file_info, fileobj=file_bytes)
-
-
-def create_setup_requires_package(
-    path,
-    distname='foobar',
-    version='0.1',
-    make_package=make_trivial_sdist,
-    setup_py_template=None,
-    setup_attrs=None,
-    use_setup_cfg=(),
-):
-    """Creates a source tree under path for a trivial test package that has a
-    single requirement in setup_requires--a tarball for that requirement is
-    also created and added to the dependency_links argument.
-
-    ``distname`` and ``version`` refer to the name/version of the package that
-    the test package requires via ``setup_requires``.  The name of the test
-    package itself is just 'test_pkg'.
-    """
-
-    normalized_distname = safer_name(distname)
-    test_setup_attrs = {
-        'name': 'test_pkg',
-        'version': '0.0',
-        'setup_requires': [f'{normalized_distname}=={version}'],
-        'dependency_links': [os.path.abspath(path)],
-    }
-    if setup_attrs:
-        test_setup_attrs.update(setup_attrs)
-
-    test_pkg = os.path.join(path, 'test_pkg')
-    os.mkdir(test_pkg)
-
-    # setup.cfg
-    if use_setup_cfg:
-        options = []
-        metadata = []
-        for name in use_setup_cfg:
-            value = test_setup_attrs.pop(name)
-            if name in 'name version'.split():
-                section = metadata
-            else:
-                section = options
-            if isinstance(value, (tuple, list)):
-                value = ';'.join(value)
-            section.append(f'{name}: {value}')
-        test_setup_cfg_contents = DALS(
-            """
-            [metadata]
-            {metadata}
-            [options]
-            {options}
-            """
-        ).format(
-            options='\n'.join(options),
-            metadata='\n'.join(metadata),
-        )
-    else:
-        test_setup_cfg_contents = ''
-    with open(os.path.join(test_pkg, 'setup.cfg'), 'w', encoding="utf-8") as f:
-        f.write(test_setup_cfg_contents)
-
-    # setup.py
-    if setup_py_template is None:
-        setup_py_template = DALS(
-            """\
-            import setuptools
-            setuptools.setup(**%r)
-        """
-        )
-    with open(os.path.join(test_pkg, 'setup.py'), 'w', encoding="utf-8") as f:
-        f.write(setup_py_template % test_setup_attrs)
-
-    foobar_path = os.path.join(path, f'{normalized_distname}-{version}.tar.gz')
-    make_package(foobar_path, distname, version)
-
-    return test_pkg
-
-
-@pytest.mark.skipif(
-    sys.platform.startswith('java') and ei.is_sh(sys.executable),
-    reason="Test cannot run under java when executable is sh",
-)
-class TestScriptHeader:
-    non_ascii_exe = '/Users/José/bin/python'
-    exe_with_spaces = r'C:\Program Files\Python36\python.exe'
-
-    def test_get_script_header(self):
-        expected = f'#!{ei.nt_quote_arg(os.path.normpath(sys.executable))}\n'
-        actual = ei.ScriptWriter.get_header('#!/usr/local/bin/python')
-        assert actual == expected
-
-    def test_get_script_header_args(self):
-        expected = f'#!{ei.nt_quote_arg(os.path.normpath(sys.executable))} -x\n'
-        actual = ei.ScriptWriter.get_header('#!/usr/bin/python -x')
-        assert actual == expected
-
-    def test_get_script_header_non_ascii_exe(self):
-        actual = ei.ScriptWriter.get_header(
-            '#!/usr/bin/python', executable=self.non_ascii_exe
-        )
-        expected = f'#!{self.non_ascii_exe} -x\n'
-        assert actual == expected
-
-    def test_get_script_header_exe_with_spaces(self):
-        actual = ei.ScriptWriter.get_header(
-            '#!/usr/bin/python', executable='"' + self.exe_with_spaces + '"'
-        )
-        expected = f'#!"{self.exe_with_spaces}"\n'
-        assert actual == expected
-
-
-class TestCommandSpec:
-    def test_custom_launch_command(self):
-        """
-        Show how a custom CommandSpec could be used to specify a #! executable
-        which takes parameters.
-        """
-        cmd = ei.CommandSpec(['/usr/bin/env', 'python3'])
-        assert cmd.as_header() == '#!/usr/bin/env python3\n'
-
-    def test_from_param_for_CommandSpec_is_passthrough(self):
-        """
-        from_param should return an instance of a CommandSpec
-        """
-        cmd = ei.CommandSpec(['python'])
-        cmd_new = ei.CommandSpec.from_param(cmd)
-        assert cmd is cmd_new
-
-    @mock.patch('sys.executable', TestScriptHeader.exe_with_spaces)
-    @mock.patch.dict(os.environ)
-    def test_from_environment_with_spaces_in_executable(self):
-        os.environ.pop('__PYVENV_LAUNCHER__', None)
-        cmd = ei.CommandSpec.from_environment()
-        assert len(cmd) == 1
-        assert cmd.as_header().startswith('#!"')
-
-    def test_from_simple_string_uses_shlex(self):
-        """
-        In order to support `executable = /usr/bin/env my-python`, make sure
-        from_param invokes shlex on that input.
-        """
-        cmd = ei.CommandSpec.from_param('/usr/bin/env my-python')
-        assert len(cmd) == 2
-        assert '"' not in cmd.as_header()
-
-    def test_from_param_raises_expected_error(self) -> None:
-        """
-        from_param should raise its own TypeError when the argument's type is unsupported
-        """
-        with pytest.raises(TypeError) as exc_info:
-            ei.CommandSpec.from_param(object())  # type: ignore[arg-type] # We want a type error here
-        assert (
-            str(exc_info.value) == "Argument has an unsupported type "
-        ), exc_info.value
-
-
-class TestWindowsScriptWriter:
-    def test_header(self):
-        hdr = ei.WindowsScriptWriter.get_header('')
-        assert hdr.startswith('#!')
-        assert hdr.endswith('\n')
-        hdr = hdr.lstrip('#!')
-        hdr = hdr.rstrip('\n')
-        # header should not start with an escaped quote
-        assert not hdr.startswith('\\"')
-
-
-class VersionStub(NamedTuple):
-    major: int
-    minor: int
-    micro: int
-    releaselevel: str
-    serial: int
-
-
-def test_use_correct_python_version_string(tmpdir, tmpdir_cwd, monkeypatch):
-    # In issue #3001, easy_install wrongly uses the `python3.1` directory
-    # when the interpreter is `python3.10` and the `--user` option is given.
-    # See pypa/setuptools#3001.
-    dist = Distribution()
-    cmd = dist.get_command_obj('easy_install')
-    cmd.args = ['ok']
-    cmd.optimize = 0
-    cmd.user = True
-    cmd.install_userbase = str(tmpdir)
-    cmd.install_usersite = None
-    install_cmd = dist.get_command_obj('install')
-    install_cmd.install_userbase = str(tmpdir)
-    install_cmd.install_usersite = None
-
-    with monkeypatch.context() as patch, warnings.catch_warnings():
-        warnings.simplefilter("ignore")
-        version = '3.10.1 (main, Dec 21 2021, 09:17:12) [GCC 10.2.1 20210110]'
-        info = VersionStub(3, 10, 1, "final", 0)
-        patch.setattr('site.ENABLE_USER_SITE', True)
-        patch.setattr('sys.version', version)
-        patch.setattr('sys.version_info', info)
-        patch.setattr(cmd, 'create_home_path', mock.Mock())
-        cmd.finalize_options()
-
-    name = "pypy" if hasattr(sys, 'pypy_version_info') else "python"
-    install_dir = cmd.install_dir.lower()
-
-    # In some platforms (e.g. Windows), install_dir is mostly determined
-    # via `sysconfig`, which define constants eagerly at module creation.
-    # This means that monkeypatching `sys.version` to emulate 3.10 for testing
-    # may have no effect.
-    # The safest test here is to rely on the fact that 3.1 is no longer
-    # supported/tested, and make sure that if 'python3.1' ever appears in the string
-    # it is followed by another digit (e.g. 'python3.10').
-    if re.search(name + r'3\.?1', install_dir):
-        assert re.search(name + r'3\.?1\d', install_dir)
-
-    # The following "variables" are used for interpolation in distutils
-    # installation schemes, so it should be fair to treat them as "semi-public",
-    # or at least public enough so we can have a test to make sure they are correct
-    assert cmd.config_vars['py_version'] == '3.10.1'
-    assert cmd.config_vars['py_version_short'] == '3.10'
-    assert cmd.config_vars['py_version_nodot'] == '310'
-
-
-@pytest.mark.xfail(
-    sys.platform == "darwin",
-    reason="https://github.com/pypa/setuptools/pull/4716#issuecomment-2447624418",
-)
-def test_editable_user_and_build_isolation(setup_context, monkeypatch, tmp_path):
-    """`setup.py develop` should honor `--user` even under build isolation"""
-
-    # == Arrange ==
-    # Pretend that build isolation was enabled
-    # e.g pip sets the environment variable PYTHONNOUSERSITE=1
-    monkeypatch.setattr('site.ENABLE_USER_SITE', False)
-
-    # Patching $HOME for 2 reasons:
-    # 1. setuptools/command/easy_install.py:create_home_path
-    #    tries creating directories in $HOME.
-    #    Given::
-    #        self.config_vars['DESTDIRS'] = (
-    #            "/home/user/.pyenv/versions/3.9.10 "
-    #            "/home/user/.pyenv/versions/3.9.10/lib "
-    #            "/home/user/.pyenv/versions/3.9.10/lib/python3.9 "
-    #            "/home/user/.pyenv/versions/3.9.10/lib/python3.9/lib-dynload")
-    #    `create_home_path` will::
-    #        makedirs(
-    #            "/home/user/.pyenv/versions/3.9.10 "
-    #            "/home/user/.pyenv/versions/3.9.10/lib "
-    #            "/home/user/.pyenv/versions/3.9.10/lib/python3.9 "
-    #            "/home/user/.pyenv/versions/3.9.10/lib/python3.9/lib-dynload")
-    #
-    # 2. We are going to force `site` to update site.USER_BASE and site.USER_SITE
-    #    To point inside our new home
-    monkeypatch.setenv('HOME', str(tmp_path / '.home'))
-    monkeypatch.setenv('USERPROFILE', str(tmp_path / '.home'))
-    monkeypatch.setenv('APPDATA', str(tmp_path / '.home'))
-    monkeypatch.setattr('site.USER_BASE', None)
-    monkeypatch.setattr('site.USER_SITE', None)
-    user_site = Path(site.getusersitepackages())
-    user_site.mkdir(parents=True, exist_ok=True)
-
-    sys_prefix = tmp_path / '.sys_prefix'
-    sys_prefix.mkdir(parents=True, exist_ok=True)
-    monkeypatch.setattr('sys.prefix', str(sys_prefix))
-
-    setup_script = (
-        "__import__('setuptools').setup(name='aproj', version=42, packages=[])\n"
-    )
-    (tmp_path / "setup.py").write_text(setup_script, encoding="utf-8")
-
-    # == Sanity check ==
-    assert list(sys_prefix.glob("*")) == []
-    assert list(user_site.glob("*")) == []
-
-    # == Act ==
-    run_setup('setup.py', ['develop', '--user'])
-
-    # == Assert ==
-    # Should not install to sys.prefix
-    assert list(sys_prefix.glob("*")) == []
-    # Should install to user site
-    installed = {f.name for f in user_site.glob("*")}
-    # sometimes easy-install.pth is created and sometimes not
-    installed = installed - {"easy-install.pth"}
-    assert installed == {'aproj.egg-link'}
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_editable_install.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_editable_install.py
deleted file mode 100644
index 038dcad..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_editable_install.py
+++ /dev/null
@@ -1,1289 +0,0 @@
-from __future__ import annotations
-
-import os
-import platform
-import stat
-import subprocess
-import sys
-from copy import deepcopy
-from importlib import import_module
-from importlib.machinery import EXTENSION_SUFFIXES
-from pathlib import Path
-from textwrap import dedent
-from typing import Any
-from unittest.mock import Mock
-from uuid import uuid4
-
-import jaraco.envs
-import jaraco.path
-import pytest
-from path import Path as _Path
-
-from setuptools._importlib import resources as importlib_resources
-from setuptools.command.editable_wheel import (
-    _DebuggingTips,
-    _encode_pth,
-    _find_namespaces,
-    _find_package_roots,
-    _find_virtual_namespaces,
-    _finder_template,
-    _LinkTree,
-    _TopLevelFinder,
-    editable_wheel,
-)
-from setuptools.dist import Distribution
-from setuptools.extension import Extension
-from setuptools.warnings import SetuptoolsDeprecationWarning
-
-from . import contexts, namespaces
-
-from distutils.core import run_setup
-
-
-@pytest.fixture(params=["strict", "lenient"])
-def editable_opts(request):
-    if request.param == "strict":
-        return ["--config-settings", "editable-mode=strict"]
-    return []
-
-
-EXAMPLE = {
-    'pyproject.toml': dedent(
-        """\
-        [build-system]
-        requires = ["setuptools"]
-        build-backend = "setuptools.build_meta"
-
-        [project]
-        name = "mypkg"
-        version = "3.14159"
-        license = {text = "MIT"}
-        description = "This is a Python package"
-        dynamic = ["readme"]
-        classifiers = [
-            "Development Status :: 5 - Production/Stable",
-            "Intended Audience :: Developers"
-        ]
-        urls = {Homepage = "https://github.com"}
-
-        [tool.setuptools]
-        package-dir = {"" = "src"}
-        packages = {find = {where = ["src"]}}
-        license-files = ["LICENSE*"]
-
-        [tool.setuptools.dynamic]
-        readme = {file = "README.rst"}
-
-        [tool.distutils.egg_info]
-        tag-build = ".post0"
-        """
-    ),
-    "MANIFEST.in": dedent(
-        """\
-        global-include *.py *.txt
-        global-exclude *.py[cod]
-        prune dist
-        prune build
-        """
-    ).strip(),
-    "README.rst": "This is a ``README``",
-    "LICENSE.txt": "---- placeholder MIT license ----",
-    "src": {
-        "mypkg": {
-            "__init__.py": dedent(
-                """\
-                import sys
-                from importlib.metadata import PackageNotFoundError, version
-
-                try:
-                    __version__ = version(__name__)
-                except PackageNotFoundError:
-                    __version__ = "unknown"
-                """
-            ),
-            "__main__.py": dedent(
-                """\
-                from importlib.resources import read_text
-                from . import __version__, __name__ as parent
-                from .mod import x
-
-                data = read_text(parent, "data.txt")
-                print(__version__, data, x)
-                """
-            ),
-            "mod.py": "x = ''",
-            "data.txt": "Hello World",
-        }
-    },
-}
-
-
-SETUP_SCRIPT_STUB = "__import__('setuptools').setup()"
-
-
-@pytest.mark.xfail(sys.platform == "darwin", reason="pypa/setuptools#4328")
-@pytest.mark.parametrize(
-    "files",
-    [
-        {**EXAMPLE, "setup.py": SETUP_SCRIPT_STUB},
-        EXAMPLE,  # No setup.py script
-    ],
-)
-def test_editable_with_pyproject(tmp_path, venv, files, editable_opts):
-    project = tmp_path / "mypkg"
-    project.mkdir()
-    jaraco.path.build(files, prefix=project)
-
-    cmd = [
-        "python",
-        "-m",
-        "pip",
-        "install",
-        "--no-build-isolation",  # required to force current version of setuptools
-        "-e",
-        str(project),
-        *editable_opts,
-    ]
-    print(venv.run(cmd))
-
-    cmd = ["python", "-m", "mypkg"]
-    assert venv.run(cmd).strip() == "3.14159.post0 Hello World"
-
-    (project / "src/mypkg/data.txt").write_text("foobar", encoding="utf-8")
-    (project / "src/mypkg/mod.py").write_text("x = 42", encoding="utf-8")
-    assert venv.run(cmd).strip() == "3.14159.post0 foobar 42"
-
-
-def test_editable_with_flat_layout(tmp_path, venv, editable_opts):
-    files = {
-        "mypkg": {
-            "pyproject.toml": dedent(
-                """\
-                [build-system]
-                requires = ["setuptools", "wheel"]
-                build-backend = "setuptools.build_meta"
-
-                [project]
-                name = "mypkg"
-                version = "3.14159"
-
-                [tool.setuptools]
-                packages = ["pkg"]
-                py-modules = ["mod"]
-                """
-            ),
-            "pkg": {"__init__.py": "a = 4"},
-            "mod.py": "b = 2",
-        },
-    }
-    jaraco.path.build(files, prefix=tmp_path)
-    project = tmp_path / "mypkg"
-
-    cmd = [
-        "python",
-        "-m",
-        "pip",
-        "install",
-        "--no-build-isolation",  # required to force current version of setuptools
-        "-e",
-        str(project),
-        *editable_opts,
-    ]
-    print(venv.run(cmd))
-    cmd = ["python", "-c", "import pkg, mod; print(pkg.a, mod.b)"]
-    assert venv.run(cmd).strip() == "4 2"
-
-
-def test_editable_with_single_module(tmp_path, venv, editable_opts):
-    files = {
-        "mypkg": {
-            "pyproject.toml": dedent(
-                """\
-                [build-system]
-                requires = ["setuptools", "wheel"]
-                build-backend = "setuptools.build_meta"
-
-                [project]
-                name = "mod"
-                version = "3.14159"
-
-                [tool.setuptools]
-                py-modules = ["mod"]
-                """
-            ),
-            "mod.py": "b = 2",
-        },
-    }
-    jaraco.path.build(files, prefix=tmp_path)
-    project = tmp_path / "mypkg"
-
-    cmd = [
-        "python",
-        "-m",
-        "pip",
-        "install",
-        "--no-build-isolation",  # required to force current version of setuptools
-        "-e",
-        str(project),
-        *editable_opts,
-    ]
-    print(venv.run(cmd))
-    cmd = ["python", "-c", "import mod; print(mod.b)"]
-    assert venv.run(cmd).strip() == "2"
-
-
-class TestLegacyNamespaces:
-    # legacy => pkg_resources.declare_namespace(...) + setup(namespace_packages=...)
-
-    def test_nspkg_file_is_unique(self, tmp_path, monkeypatch):
-        deprecation = pytest.warns(
-            SetuptoolsDeprecationWarning, match=".*namespace_packages parameter.*"
-        )
-        installation_dir = tmp_path / ".installation_dir"
-        installation_dir.mkdir()
-        examples = (
-            "myns.pkgA",
-            "myns.pkgB",
-            "myns.n.pkgA",
-            "myns.n.pkgB",
-        )
-
-        for name in examples:
-            pkg = namespaces.build_namespace_package(tmp_path, name, version="42")
-            with deprecation, monkeypatch.context() as ctx:
-                ctx.chdir(pkg)
-                dist = run_setup("setup.py", stop_after="config")
-                cmd = editable_wheel(dist)
-                cmd.finalize_options()
-                editable_name = cmd.get_finalized_command("dist_info").name
-                cmd._install_namespaces(installation_dir, editable_name)
-
-        files = list(installation_dir.glob("*-nspkg.pth"))
-        assert len(files) == len(examples)
-
-    @pytest.mark.parametrize(
-        "impl",
-        (
-            "pkg_resources",
-            #  "pkgutil",  => does not work
-        ),
-    )
-    @pytest.mark.parametrize("ns", ("myns.n",))
-    def test_namespace_package_importable(
-        self, venv, tmp_path, ns, impl, editable_opts
-    ):
-        """
-        Installing two packages sharing the same namespace, one installed
-        naturally using pip or `--single-version-externally-managed`
-        and the other installed in editable mode should leave the namespace
-        intact and both packages reachable by import.
-        (Ported from test_develop).
-        """
-        build_system = """\
-        [build-system]
-        requires = ["setuptools"]
-        build-backend = "setuptools.build_meta"
-        """
-        pkg_A = namespaces.build_namespace_package(tmp_path, f"{ns}.pkgA", impl=impl)
-        pkg_B = namespaces.build_namespace_package(tmp_path, f"{ns}.pkgB", impl=impl)
-        (pkg_A / "pyproject.toml").write_text(build_system, encoding="utf-8")
-        (pkg_B / "pyproject.toml").write_text(build_system, encoding="utf-8")
-        # use pip to install to the target directory
-        opts = editable_opts[:]
-        opts.append("--no-build-isolation")  # force current version of setuptools
-        venv.run(["python", "-m", "pip", "install", str(pkg_A), *opts])
-        venv.run(["python", "-m", "pip", "install", "-e", str(pkg_B), *opts])
-        venv.run(["python", "-c", f"import {ns}.pkgA; import {ns}.pkgB"])
-        # additionally ensure that pkg_resources import works
-        venv.run(["python", "-c", "import pkg_resources"])
-
-
-class TestPep420Namespaces:
-    def test_namespace_package_importable(self, venv, tmp_path, editable_opts):
-        """
-        Installing two packages sharing the same namespace, one installed
-        normally using pip and the other installed in editable mode
-        should allow importing both packages.
-        """
-        pkg_A = namespaces.build_pep420_namespace_package(tmp_path, 'myns.n.pkgA')
-        pkg_B = namespaces.build_pep420_namespace_package(tmp_path, 'myns.n.pkgB')
-        # use pip to install to the target directory
-        opts = editable_opts[:]
-        opts.append("--no-build-isolation")  # force current version of setuptools
-        venv.run(["python", "-m", "pip", "install", str(pkg_A), *opts])
-        venv.run(["python", "-m", "pip", "install", "-e", str(pkg_B), *opts])
-        venv.run(["python", "-c", "import myns.n.pkgA; import myns.n.pkgB"])
-
-    def test_namespace_created_via_package_dir(self, venv, tmp_path, editable_opts):
-        """Currently users can create a namespace by tweaking `package_dir`"""
-        files = {
-            "pkgA": {
-                "pyproject.toml": dedent(
-                    """\
-                    [build-system]
-                    requires = ["setuptools", "wheel"]
-                    build-backend = "setuptools.build_meta"
-
-                    [project]
-                    name = "pkgA"
-                    version = "3.14159"
-
-                    [tool.setuptools]
-                    package-dir = {"myns.n.pkgA" = "src"}
-                    """
-                ),
-                "src": {"__init__.py": "a = 1"},
-            },
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-        pkg_A = tmp_path / "pkgA"
-        pkg_B = namespaces.build_pep420_namespace_package(tmp_path, 'myns.n.pkgB')
-        pkg_C = namespaces.build_pep420_namespace_package(tmp_path, 'myns.n.pkgC')
-
-        # use pip to install to the target directory
-        opts = editable_opts[:]
-        opts.append("--no-build-isolation")  # force current version of setuptools
-        venv.run(["python", "-m", "pip", "install", str(pkg_A), *opts])
-        venv.run(["python", "-m", "pip", "install", "-e", str(pkg_B), *opts])
-        venv.run(["python", "-m", "pip", "install", "-e", str(pkg_C), *opts])
-        venv.run(["python", "-c", "from myns.n import pkgA, pkgB, pkgC"])
-
-    def test_namespace_accidental_config_in_lenient_mode(self, venv, tmp_path):
-        """Sometimes users might specify an ``include`` pattern that ignores parent
-        packages. In a normal installation this would ignore all modules inside the
-        parent packages, and make them namespaces (reported in issue #3504),
-        so the editable mode should preserve this behaviour.
-        """
-        files = {
-            "pkgA": {
-                "pyproject.toml": dedent(
-                    """\
-                    [build-system]
-                    requires = ["setuptools", "wheel"]
-                    build-backend = "setuptools.build_meta"
-
-                    [project]
-                    name = "pkgA"
-                    version = "3.14159"
-
-                    [tool.setuptools]
-                    packages.find.include = ["mypkg.*"]
-                    """
-                ),
-                "mypkg": {
-                    "__init__.py": "",
-                    "other.py": "b = 1",
-                    "n": {
-                        "__init__.py": "",
-                        "pkgA.py": "a = 1",
-                    },
-                },
-                "MANIFEST.in": EXAMPLE["MANIFEST.in"],
-            },
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-        pkg_A = tmp_path / "pkgA"
-
-        # use pip to install to the target directory
-        opts = ["--no-build-isolation"]  # force current version of setuptools
-        venv.run(["python", "-m", "pip", "-v", "install", "-e", str(pkg_A), *opts])
-        out = venv.run(["python", "-c", "from mypkg.n import pkgA; print(pkgA.a)"])
-        assert out.strip() == "1"
-        cmd = """\
-        try:
-            import mypkg.other
-        except ImportError:
-            print("mypkg.other not defined")
-        """
-        out = venv.run(["python", "-c", dedent(cmd)])
-        assert "mypkg.other not defined" in out
-
-
-def test_editable_with_prefix(tmp_path, sample_project, editable_opts):
-    """
-    Editable install to a prefix should be discoverable.
-    """
-    prefix = tmp_path / 'prefix'
-
-    # figure out where pip will likely install the package
-    site_packages_all = [
-        prefix / Path(path).relative_to(sys.prefix)
-        for path in sys.path
-        if 'site-packages' in path and path.startswith(sys.prefix)
-    ]
-
-    for sp in site_packages_all:
-        sp.mkdir(parents=True)
-
-    # install workaround
-    _addsitedirs(site_packages_all)
-
-    env = dict(os.environ, PYTHONPATH=os.pathsep.join(map(str, site_packages_all)))
-    cmd = [
-        sys.executable,
-        '-m',
-        'pip',
-        'install',
-        '--editable',
-        str(sample_project),
-        '--prefix',
-        str(prefix),
-        '--no-build-isolation',
-        *editable_opts,
-    ]
-    subprocess.check_call(cmd, env=env)
-
-    # now run 'sample' with the prefix on the PYTHONPATH
-    bin = 'Scripts' if platform.system() == 'Windows' else 'bin'
-    exe = prefix / bin / 'sample'
-    subprocess.check_call([exe], env=env)
-
-
-class TestFinderTemplate:
-    """This test focus in getting a particular implementation detail right.
-    If at some point in time the implementation is changed for something different,
-    this test can be modified or even excluded.
-    """
-
-    def install_finder(self, finder):
-        loc = {}
-        exec(finder, loc, loc)
-        loc["install"]()
-
-    def test_packages(self, tmp_path):
-        files = {
-            "src1": {
-                "pkg1": {
-                    "__init__.py": "",
-                    "subpkg": {"mod1.py": "a = 42"},
-                },
-            },
-            "src2": {"mod2.py": "a = 43"},
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-
-        mapping = {
-            "pkg1": str(tmp_path / "src1/pkg1"),
-            "mod2": str(tmp_path / "src2/mod2"),
-        }
-        template = _finder_template(str(uuid4()), mapping, {})
-
-        with contexts.save_paths(), contexts.save_sys_modules():
-            for mod in ("pkg1", "pkg1.subpkg", "pkg1.subpkg.mod1", "mod2"):
-                sys.modules.pop(mod, None)
-
-            self.install_finder(template)
-            mod1 = import_module("pkg1.subpkg.mod1")
-            mod2 = import_module("mod2")
-            subpkg = import_module("pkg1.subpkg")
-
-            assert mod1.a == 42
-            assert mod2.a == 43
-            expected = str((tmp_path / "src1/pkg1/subpkg").resolve())
-            assert_path(subpkg, expected)
-
-    def test_namespace(self, tmp_path):
-        files = {"pkg": {"__init__.py": "a = 13", "text.txt": "abc"}}
-        jaraco.path.build(files, prefix=tmp_path)
-
-        mapping = {"ns.othername": str(tmp_path / "pkg")}
-        namespaces = {"ns": []}
-
-        template = _finder_template(str(uuid4()), mapping, namespaces)
-        with contexts.save_paths(), contexts.save_sys_modules():
-            for mod in ("ns", "ns.othername"):
-                sys.modules.pop(mod, None)
-
-            self.install_finder(template)
-            pkg = import_module("ns.othername")
-            text = importlib_resources.files(pkg) / "text.txt"
-
-            expected = str((tmp_path / "pkg").resolve())
-            assert_path(pkg, expected)
-            assert pkg.a == 13
-
-            # Make sure resources can also be found
-            assert text.read_text(encoding="utf-8") == "abc"
-
-    def test_combine_namespaces(self, tmp_path):
-        files = {
-            "src1": {"ns": {"pkg1": {"__init__.py": "a = 13"}}},
-            "src2": {"ns": {"mod2.py": "b = 37"}},
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-
-        mapping = {
-            "ns.pkgA": str(tmp_path / "src1/ns/pkg1"),
-            "ns": str(tmp_path / "src2/ns"),
-        }
-        namespaces_ = {"ns": [str(tmp_path / "src1"), str(tmp_path / "src2")]}
-        template = _finder_template(str(uuid4()), mapping, namespaces_)
-
-        with contexts.save_paths(), contexts.save_sys_modules():
-            for mod in ("ns", "ns.pkgA", "ns.mod2"):
-                sys.modules.pop(mod, None)
-
-            self.install_finder(template)
-            pkgA = import_module("ns.pkgA")
-            mod2 = import_module("ns.mod2")
-
-            expected = str((tmp_path / "src1/ns/pkg1").resolve())
-            assert_path(pkgA, expected)
-            assert pkgA.a == 13
-            assert mod2.b == 37
-
-    def test_combine_namespaces_nested(self, tmp_path):
-        """
-        Users may attempt to combine namespace packages in a nested way via
-        ``package_dir`` as shown in pypa/setuptools#4248.
-        """
-
-        files = {
-            "src": {"my_package": {"my_module.py": "a = 13"}},
-            "src2": {"my_package2": {"my_module2.py": "b = 37"}},
-        }
-
-        stack = jaraco.path.DirectoryStack()
-        with stack.context(tmp_path):
-            jaraco.path.build(files)
-            attrs = {
-                "script_name": "%PEP 517%",
-                "package_dir": {
-                    "different_name": "src/my_package",
-                    "different_name.subpkg": "src2/my_package2",
-                },
-                "packages": ["different_name", "different_name.subpkg"],
-            }
-            dist = Distribution(attrs)
-            finder = _TopLevelFinder(dist, str(uuid4()))
-            code = next(v for k, v in finder.get_implementation() if k.endswith(".py"))
-
-        with contexts.save_paths(), contexts.save_sys_modules():
-            for mod in attrs["packages"]:
-                sys.modules.pop(mod, None)
-
-            self.install_finder(code)
-            mod1 = import_module("different_name.my_module")
-            mod2 = import_module("different_name.subpkg.my_module2")
-
-            expected = str((tmp_path / "src/my_package/my_module.py").resolve())
-            assert str(Path(mod1.__file__).resolve()) == expected
-
-            expected = str((tmp_path / "src2/my_package2/my_module2.py").resolve())
-            assert str(Path(mod2.__file__).resolve()) == expected
-
-            assert mod1.a == 13
-            assert mod2.b == 37
-
-    def test_dynamic_path_computation(self, tmp_path):
-        # Follows the example in PEP 420
-        files = {
-            "project1": {"parent": {"child": {"one.py": "x = 1"}}},
-            "project2": {"parent": {"child": {"two.py": "x = 2"}}},
-            "project3": {"parent": {"child": {"three.py": "x = 3"}}},
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-        mapping = {}
-        namespaces_ = {"parent": [str(tmp_path / "project1/parent")]}
-        template = _finder_template(str(uuid4()), mapping, namespaces_)
-
-        mods = (f"parent.child.{name}" for name in ("one", "two", "three"))
-        with contexts.save_paths(), contexts.save_sys_modules():
-            for mod in ("parent", "parent.child", "parent.child", *mods):
-                sys.modules.pop(mod, None)
-
-            self.install_finder(template)
-
-            one = import_module("parent.child.one")
-            assert one.x == 1
-
-            with pytest.raises(ImportError):
-                import_module("parent.child.two")
-
-            sys.path.append(str(tmp_path / "project2"))
-            two = import_module("parent.child.two")
-            assert two.x == 2
-
-            with pytest.raises(ImportError):
-                import_module("parent.child.three")
-
-            sys.path.append(str(tmp_path / "project3"))
-            three = import_module("parent.child.three")
-            assert three.x == 3
-
-    def test_no_recursion(self, tmp_path):
-        # See issue #3550
-        files = {
-            "pkg": {
-                "__init__.py": "from . import pkg",
-            },
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-
-        mapping = {
-            "pkg": str(tmp_path / "pkg"),
-        }
-        template = _finder_template(str(uuid4()), mapping, {})
-
-        with contexts.save_paths(), contexts.save_sys_modules():
-            sys.modules.pop("pkg", None)
-
-            self.install_finder(template)
-            with pytest.raises(ImportError, match="pkg"):
-                import_module("pkg")
-
-    def test_similar_name(self, tmp_path):
-        files = {
-            "foo": {
-                "__init__.py": "",
-                "bar": {
-                    "__init__.py": "",
-                },
-            },
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-
-        mapping = {
-            "foo": str(tmp_path / "foo"),
-        }
-        template = _finder_template(str(uuid4()), mapping, {})
-
-        with contexts.save_paths(), contexts.save_sys_modules():
-            sys.modules.pop("foo", None)
-            sys.modules.pop("foo.bar", None)
-
-            self.install_finder(template)
-            with pytest.raises(ImportError, match="foobar"):
-                import_module("foobar")
-
-    def test_case_sensitivity(self, tmp_path):
-        files = {
-            "foo": {
-                "__init__.py": "",
-                "lowercase.py": "x = 1",
-                "bar": {
-                    "__init__.py": "",
-                    "lowercase.py": "x = 2",
-                },
-            },
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-        mapping = {
-            "foo": str(tmp_path / "foo"),
-        }
-        template = _finder_template(str(uuid4()), mapping, {})
-        with contexts.save_paths(), contexts.save_sys_modules():
-            sys.modules.pop("foo", None)
-
-            self.install_finder(template)
-            with pytest.raises(ImportError, match="'FOO'"):
-                import_module("FOO")
-
-            with pytest.raises(ImportError, match="'foo\\.LOWERCASE'"):
-                import_module("foo.LOWERCASE")
-
-            with pytest.raises(ImportError, match="'foo\\.bar\\.Lowercase'"):
-                import_module("foo.bar.Lowercase")
-
-            with pytest.raises(ImportError, match="'foo\\.BAR'"):
-                import_module("foo.BAR.lowercase")
-
-            with pytest.raises(ImportError, match="'FOO'"):
-                import_module("FOO.bar.lowercase")
-
-            mod = import_module("foo.lowercase")
-            assert mod.x == 1
-
-            mod = import_module("foo.bar.lowercase")
-            assert mod.x == 2
-
-    def test_namespace_case_sensitivity(self, tmp_path):
-        files = {
-            "pkg": {
-                "__init__.py": "a = 13",
-                "foo": {
-                    "__init__.py": "b = 37",
-                    "bar.py": "c = 42",
-                },
-            },
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-
-        mapping = {"ns.othername": str(tmp_path / "pkg")}
-        namespaces = {"ns": []}
-
-        template = _finder_template(str(uuid4()), mapping, namespaces)
-        with contexts.save_paths(), contexts.save_sys_modules():
-            for mod in ("ns", "ns.othername"):
-                sys.modules.pop(mod, None)
-
-            self.install_finder(template)
-            pkg = import_module("ns.othername")
-            expected = str((tmp_path / "pkg").resolve())
-            assert_path(pkg, expected)
-            assert pkg.a == 13
-
-            foo = import_module("ns.othername.foo")
-            assert foo.b == 37
-
-            bar = import_module("ns.othername.foo.bar")
-            assert bar.c == 42
-
-            with pytest.raises(ImportError, match="'NS'"):
-                import_module("NS.othername.foo")
-
-            with pytest.raises(ImportError, match="'ns\\.othername\\.FOO\\'"):
-                import_module("ns.othername.FOO")
-
-            with pytest.raises(ImportError, match="'ns\\.othername\\.foo\\.BAR\\'"):
-                import_module("ns.othername.foo.BAR")
-
-    def test_intermediate_packages(self, tmp_path):
-        """
-        The finder should not import ``fullname`` if the intermediate segments
-        don't exist (see pypa/setuptools#4019).
-        """
-        files = {
-            "src": {
-                "mypkg": {
-                    "__init__.py": "",
-                    "config.py": "a = 13",
-                    "helloworld.py": "b = 13",
-                    "components": {
-                        "config.py": "a = 37",
-                    },
-                },
-            }
-        }
-        jaraco.path.build(files, prefix=tmp_path)
-
-        mapping = {"mypkg": str(tmp_path / "src/mypkg")}
-        template = _finder_template(str(uuid4()), mapping, {})
-
-        with contexts.save_paths(), contexts.save_sys_modules():
-            for mod in (
-                "mypkg",
-                "mypkg.config",
-                "mypkg.helloworld",
-                "mypkg.components",
-                "mypkg.components.config",
-                "mypkg.components.helloworld",
-            ):
-                sys.modules.pop(mod, None)
-
-            self.install_finder(template)
-
-            config = import_module("mypkg.components.config")
-            assert config.a == 37
-
-            helloworld = import_module("mypkg.helloworld")
-            assert helloworld.b == 13
-
-            with pytest.raises(ImportError):
-                import_module("mypkg.components.helloworld")
-
-
-def test_pkg_roots(tmp_path):
-    """This test focus in getting a particular implementation detail right.
-    If at some point in time the implementation is changed for something different,
-    this test can be modified or even excluded.
-    """
-    files = {
-        "a": {"b": {"__init__.py": "ab = 1"}, "__init__.py": "a = 1"},
-        "d": {"__init__.py": "d = 1", "e": {"__init__.py": "de = 1"}},
-        "f": {"g": {"h": {"__init__.py": "fgh = 1"}}},
-        "other": {"__init__.py": "abc = 1"},
-        "another": {"__init__.py": "abcxyz = 1"},
-        "yet_another": {"__init__.py": "mnopq = 1"},
-    }
-    jaraco.path.build(files, prefix=tmp_path)
-    package_dir = {
-        "a.b.c": "other",
-        "a.b.c.x.y.z": "another",
-        "m.n.o.p.q": "yet_another",
-    }
-    packages = [
-        "a",
-        "a.b",
-        "a.b.c",
-        "a.b.c.x.y",
-        "a.b.c.x.y.z",
-        "d",
-        "d.e",
-        "f",
-        "f.g",
-        "f.g.h",
-        "m.n.o.p.q",
-    ]
-    roots = _find_package_roots(packages, package_dir, tmp_path)
-    assert roots == {
-        "a": str(tmp_path / "a"),
-        "a.b.c": str(tmp_path / "other"),
-        "a.b.c.x.y.z": str(tmp_path / "another"),
-        "d": str(tmp_path / "d"),
-        "f": str(tmp_path / "f"),
-        "m.n.o.p.q": str(tmp_path / "yet_another"),
-    }
-
-    ns = set(dict(_find_namespaces(packages, roots)))
-    assert ns == {"f", "f.g"}
-
-    ns = set(_find_virtual_namespaces(roots))
-    assert ns == {"a.b", "a.b.c.x", "a.b.c.x.y", "m", "m.n", "m.n.o", "m.n.o.p"}
-
-
-class TestOverallBehaviour:
-    PYPROJECT = """\
-        [build-system]
-        requires = ["setuptools"]
-        build-backend = "setuptools.build_meta"
-
-        [project]
-        name = "mypkg"
-        version = "3.14159"
-        """
-
-    # Any: Would need a TypedDict. Keep it simple for tests
-    FLAT_LAYOUT: dict[str, Any] = {
-        "pyproject.toml": dedent(PYPROJECT),
-        "MANIFEST.in": EXAMPLE["MANIFEST.in"],
-        "otherfile.py": "",
-        "mypkg": {
-            "__init__.py": "",
-            "mod1.py": "var = 42",
-            "subpackage": {
-                "__init__.py": "",
-                "mod2.py": "var = 13",
-                "resource_file.txt": "resource 39",
-            },
-        },
-    }
-
-    EXAMPLES = {
-        "flat-layout": FLAT_LAYOUT,
-        "src-layout": {
-            "pyproject.toml": dedent(PYPROJECT),
-            "MANIFEST.in": EXAMPLE["MANIFEST.in"],
-            "otherfile.py": "",
-            "src": {"mypkg": FLAT_LAYOUT["mypkg"]},
-        },
-        "custom-layout": {
-            "pyproject.toml": dedent(PYPROJECT)
-            + dedent(
-                """\
-                [tool.setuptools]
-                packages = ["mypkg", "mypkg.subpackage"]
-
-                [tool.setuptools.package-dir]
-                "mypkg.subpackage" = "other"
-                """
-            ),
-            "MANIFEST.in": EXAMPLE["MANIFEST.in"],
-            "otherfile.py": "",
-            "mypkg": {
-                "__init__.py": "",
-                "mod1.py": FLAT_LAYOUT["mypkg"]["mod1.py"],
-            },
-            "other": FLAT_LAYOUT["mypkg"]["subpackage"],
-        },
-        "namespace": {
-            "pyproject.toml": dedent(PYPROJECT),
-            "MANIFEST.in": EXAMPLE["MANIFEST.in"],
-            "otherfile.py": "",
-            "src": {
-                "mypkg": {
-                    "mod1.py": FLAT_LAYOUT["mypkg"]["mod1.py"],
-                    "subpackage": FLAT_LAYOUT["mypkg"]["subpackage"],
-                },
-            },
-        },
-    }
-
-    @pytest.mark.xfail(sys.platform == "darwin", reason="pypa/setuptools#4328")
-    @pytest.mark.parametrize("layout", EXAMPLES.keys())
-    def test_editable_install(self, tmp_path, venv, layout, editable_opts):
-        project, _ = install_project(
-            "mypkg", venv, tmp_path, self.EXAMPLES[layout], *editable_opts
-        )
-
-        # Ensure stray files are not importable
-        cmd_import_error = """\
-        try:
-            import otherfile
-        except ImportError as ex:
-            print(ex)
-        """
-        out = venv.run(["python", "-c", dedent(cmd_import_error)])
-        assert "No module named 'otherfile'" in out
-
-        # Ensure the modules are importable
-        cmd_get_vars = """\
-        import mypkg, mypkg.mod1, mypkg.subpackage.mod2
-        print(mypkg.mod1.var, mypkg.subpackage.mod2.var)
-        """
-        out = venv.run(["python", "-c", dedent(cmd_get_vars)])
-        assert "42 13" in out
-
-        # Ensure resources are reachable
-        cmd_get_resource = """\
-        import mypkg.subpackage
-        from setuptools._importlib import resources as importlib_resources
-        text = importlib_resources.files(mypkg.subpackage) / "resource_file.txt"
-        print(text.read_text(encoding="utf-8"))
-        """
-        out = venv.run(["python", "-c", dedent(cmd_get_resource)])
-        assert "resource 39" in out
-
-        # Ensure files are editable
-        mod1 = next(project.glob("**/mod1.py"))
-        mod2 = next(project.glob("**/mod2.py"))
-        resource_file = next(project.glob("**/resource_file.txt"))
-
-        mod1.write_text("var = 17", encoding="utf-8")
-        mod2.write_text("var = 781", encoding="utf-8")
-        resource_file.write_text("resource 374", encoding="utf-8")
-
-        out = venv.run(["python", "-c", dedent(cmd_get_vars)])
-        assert "42 13" not in out
-        assert "17 781" in out
-
-        out = venv.run(["python", "-c", dedent(cmd_get_resource)])
-        assert "resource 39" not in out
-        assert "resource 374" in out
-
-
-class TestLinkTree:
-    FILES = deepcopy(TestOverallBehaviour.EXAMPLES["src-layout"])
-    FILES["pyproject.toml"] += dedent(
-        """\
-        [tool.setuptools]
-        # Temporary workaround: both `include-package-data` and `package-data` configs
-        # can be removed after #3260 is fixed.
-        include-package-data = false
-        package-data = {"*" = ["*.txt"]}
-
-        [tool.setuptools.packages.find]
-        where = ["src"]
-        exclude = ["*.subpackage*"]
-        """
-    )
-    FILES["src"]["mypkg"]["resource.not_in_manifest"] = "abc"
-
-    def test_generated_tree(self, tmp_path):
-        jaraco.path.build(self.FILES, prefix=tmp_path)
-
-        with _Path(tmp_path):
-            name = "mypkg-3.14159"
-            dist = Distribution({"script_name": "%PEP 517%"})
-            dist.parse_config_files()
-
-            wheel = Mock()
-            aux = tmp_path / ".aux"
-            build = tmp_path / ".build"
-            aux.mkdir()
-            build.mkdir()
-
-            build_py = dist.get_command_obj("build_py")
-            build_py.editable_mode = True
-            build_py.build_lib = str(build)
-            build_py.ensure_finalized()
-            outputs = build_py.get_outputs()
-            output_mapping = build_py.get_output_mapping()
-
-            make_tree = _LinkTree(dist, name, aux, build)
-            make_tree(wheel, outputs, output_mapping)
-
-            mod1 = next(aux.glob("**/mod1.py"))
-            expected = tmp_path / "src/mypkg/mod1.py"
-            assert_link_to(mod1, expected)
-
-            assert next(aux.glob("**/subpackage"), None) is None
-            assert next(aux.glob("**/mod2.py"), None) is None
-            assert next(aux.glob("**/resource_file.txt"), None) is None
-
-            assert next(aux.glob("**/resource.not_in_manifest"), None) is None
-
-    def test_strict_install(self, tmp_path, venv):
-        opts = ["--config-settings", "editable-mode=strict"]
-        install_project("mypkg", venv, tmp_path, self.FILES, *opts)
-
-        out = venv.run(["python", "-c", "import mypkg.mod1; print(mypkg.mod1.var)"])
-        assert "42" in out
-
-        # Ensure packages excluded from distribution are not importable
-        cmd_import_error = """\
-        try:
-            from mypkg import subpackage
-        except ImportError as ex:
-            print(ex)
-        """
-        out = venv.run(["python", "-c", dedent(cmd_import_error)])
-        assert "cannot import name 'subpackage'" in out
-
-        # Ensure resource files excluded from distribution are not reachable
-        cmd_get_resource = """\
-        import mypkg
-        from setuptools._importlib import resources as importlib_resources
-        try:
-            text = importlib_resources.files(mypkg) / "resource.not_in_manifest"
-            print(text.read_text(encoding="utf-8"))
-        except FileNotFoundError as ex:
-            print(ex)
-        """
-        out = venv.run(["python", "-c", dedent(cmd_get_resource)])
-        assert "No such file or directory" in out
-        assert "resource.not_in_manifest" in out
-
-
-@pytest.mark.filterwarnings("ignore:.*compat.*:setuptools.SetuptoolsDeprecationWarning")
-def test_compat_install(tmp_path, venv):
-    # TODO: Remove `compat` after Dec/2022.
-    opts = ["--config-settings", "editable-mode=compat"]
-    files = TestOverallBehaviour.EXAMPLES["custom-layout"]
-    install_project("mypkg", venv, tmp_path, files, *opts)
-
-    out = venv.run(["python", "-c", "import mypkg.mod1; print(mypkg.mod1.var)"])
-    assert "42" in out
-
-    expected_path = comparable_path(str(tmp_path))
-
-    # Compatible behaviour will make spurious modules and excluded
-    # files importable directly from the original path
-    for cmd in (
-        "import otherfile; print(otherfile)",
-        "import other; print(other)",
-        "import mypkg; print(mypkg)",
-    ):
-        out = comparable_path(venv.run(["python", "-c", cmd]))
-        assert expected_path in out
-
-    # Compatible behaviour will not consider custom mappings
-    cmd = """\
-    try:
-        from mypkg import subpackage;
-    except ImportError as ex:
-        print(ex)
-    """
-    out = venv.run(["python", "-c", dedent(cmd)])
-    assert "cannot import name 'subpackage'" in out
-
-
-def test_pbr_integration(tmp_path, venv, editable_opts):
-    """Ensure editable installs work with pbr, issue #3500"""
-    files = {
-        "pyproject.toml": dedent(
-            """\
-            [build-system]
-            requires = ["setuptools"]
-            build-backend = "setuptools.build_meta"
-            """
-        ),
-        "setup.py": dedent(
-            """\
-            __import__('setuptools').setup(
-                pbr=True,
-                setup_requires=["pbr"],
-            )
-            """
-        ),
-        "setup.cfg": dedent(
-            """\
-            [metadata]
-            name = mypkg
-
-            [files]
-            packages =
-                mypkg
-            """
-        ),
-        "mypkg": {
-            "__init__.py": "",
-            "hello.py": "print('Hello world!')",
-        },
-        "other": {"test.txt": "Another file in here."},
-    }
-    venv.run(["python", "-m", "pip", "install", "pbr"])
-
-    with contexts.environment(PBR_VERSION="0.42"):
-        install_project("mypkg", venv, tmp_path, files, *editable_opts)
-
-    out = venv.run(["python", "-c", "import mypkg.hello"])
-    assert "Hello world!" in out
-
-
-class TestCustomBuildPy:
-    """
-    Issue #3501 indicates that some plugins/customizations might rely on:
-
-    1. ``build_py`` not running
-    2. ``build_py`` always copying files to ``build_lib``
-
-    During the transition period setuptools should prevent potential errors from
-    happening due to those assumptions.
-    """
-
-    # TODO: Remove tests after _run_build_steps is removed.
-
-    FILES = {
-        **TestOverallBehaviour.EXAMPLES["flat-layout"],
-        "setup.py": dedent(
-            """\
-            import pathlib
-            from setuptools import setup
-            from setuptools.command.build_py import build_py as orig
-
-            class my_build_py(orig):
-                def run(self):
-                    super().run()
-                    raise ValueError("TEST_RAISE")
-
-            setup(cmdclass={"build_py": my_build_py})
-            """
-        ),
-    }
-
-    def test_safeguarded_from_errors(self, tmp_path, venv):
-        """Ensure that errors in custom build_py are reported as warnings"""
-        # Warnings should show up
-        _, out = install_project("mypkg", venv, tmp_path, self.FILES)
-        assert "SetuptoolsDeprecationWarning" in out
-        assert "ValueError: TEST_RAISE" in out
-        # but installation should be successful
-        out = venv.run(["python", "-c", "import mypkg.mod1; print(mypkg.mod1.var)"])
-        assert "42" in out
-
-
-class TestCustomBuildWheel:
-    def install_custom_build_wheel(self, dist):
-        bdist_wheel_cls = dist.get_command_class("bdist_wheel")
-
-        class MyBdistWheel(bdist_wheel_cls):
-            def get_tag(self):
-                # In issue #3513, we can see that some extensions may try to access
-                # the `plat_name` property in bdist_wheel
-                if self.plat_name.startswith("macosx-"):
-                    _ = "macOS platform"
-                return super().get_tag()
-
-        dist.cmdclass["bdist_wheel"] = MyBdistWheel
-
-    def test_access_plat_name(self, tmpdir_cwd):
-        # Even when a custom bdist_wheel tries to access plat_name the build should
-        # be successful
-        jaraco.path.build({"module.py": "x = 42"})
-        dist = Distribution()
-        dist.script_name = "setup.py"
-        dist.set_defaults()
-        self.install_custom_build_wheel(dist)
-        cmd = editable_wheel(dist)
-        cmd.ensure_finalized()
-        cmd.run()
-        wheel_file = str(next(Path().glob('dist/*.whl')))
-        assert "editable" in wheel_file
-
-
-class TestCustomBuildExt:
-    def install_custom_build_ext_distutils(self, dist):
-        from distutils.command.build_ext import build_ext as build_ext_cls
-
-        class MyBuildExt(build_ext_cls):
-            pass
-
-        dist.cmdclass["build_ext"] = MyBuildExt
-
-    @pytest.mark.skipif(
-        sys.platform != "linux", reason="compilers may fail without correct setup"
-    )
-    def test_distutils_leave_inplace_files(self, tmpdir_cwd):
-        jaraco.path.build({"module.c": ""})
-        attrs = {
-            "ext_modules": [Extension("module", ["module.c"])],
-        }
-        dist = Distribution(attrs)
-        dist.script_name = "setup.py"
-        dist.set_defaults()
-        self.install_custom_build_ext_distutils(dist)
-        cmd = editable_wheel(dist)
-        cmd.ensure_finalized()
-        cmd.run()
-        wheel_file = str(next(Path().glob('dist/*.whl')))
-        assert "editable" in wheel_file
-        files = [p for p in Path().glob("module.*") if p.suffix != ".c"]
-        assert len(files) == 1
-        name = files[0].name
-        assert any(name.endswith(ext) for ext in EXTENSION_SUFFIXES)
-
-
-def test_debugging_tips(tmpdir_cwd, monkeypatch):
-    """Make sure to display useful debugging tips to the user."""
-    jaraco.path.build({"module.py": "x = 42"})
-    dist = Distribution()
-    dist.script_name = "setup.py"
-    dist.set_defaults()
-    cmd = editable_wheel(dist)
-    cmd.ensure_finalized()
-
-    SimulatedErr = type("SimulatedErr", (Exception,), {})
-    simulated_failure = Mock(side_effect=SimulatedErr())
-    monkeypatch.setattr(cmd, "get_finalized_command", simulated_failure)
-
-    expected_msg = "following steps are recommended to help debug"
-    with pytest.raises(SimulatedErr), pytest.warns(_DebuggingTips, match=expected_msg):
-        cmd.run()
-
-
-@pytest.mark.filterwarnings("error")
-def test_encode_pth():
-    """Ensure _encode_pth function does not produce encoding warnings"""
-    content = _encode_pth("tkmilan_ç_utf8")  # no warnings (would be turned into errors)
-    assert isinstance(content, bytes)
-
-
-def install_project(name, venv, tmp_path, files, *opts):
-    project = tmp_path / name
-    project.mkdir()
-    jaraco.path.build(files, prefix=project)
-    opts = [*opts, "--no-build-isolation"]  # force current version of setuptools
-    out = venv.run(
-        ["python", "-m", "pip", "-v", "install", "-e", str(project), *opts],
-        stderr=subprocess.STDOUT,
-    )
-    return project, out
-
-
-def _addsitedirs(new_dirs):
-    """To use this function, it is necessary to insert new_dir in front of sys.path.
-    The Python process will try to import a ``sitecustomize`` module on startup.
-    If we manipulate sys.path/PYTHONPATH, we can force it to run our code,
-    which invokes ``addsitedir`` and ensure ``.pth`` files are loaded.
-    """
-    content = '\n'.join(
-        ("import site",)
-        + tuple(f"site.addsitedir({os.fspath(new_dir)!r})" for new_dir in new_dirs)
-    )
-    (new_dirs[0] / "sitecustomize.py").write_text(content, encoding="utf-8")
-
-
-# ---- Assertion Helpers ----
-
-
-def assert_path(pkg, expected):
-    # __path__ is not guaranteed to exist, so we have to account for that
-    if pkg.__path__:
-        path = next(iter(pkg.__path__), None)
-        if path:
-            assert str(Path(path).resolve()) == expected
-
-
-def assert_link_to(file: Path, other: Path) -> None:
-    if file.is_symlink():
-        assert str(file.resolve()) == str(other.resolve())
-    else:
-        file_stat = file.stat()
-        other_stat = other.stat()
-        assert file_stat[stat.ST_INO] == other_stat[stat.ST_INO]
-        assert file_stat[stat.ST_DEV] == other_stat[stat.ST_DEV]
-
-
-def comparable_path(str_with_path: str) -> str:
-    return str_with_path.lower().replace(os.sep, "/").replace("//", "/")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_egg_info.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_egg_info.py
deleted file mode 100644
index 528e2c1..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_egg_info.py
+++ /dev/null
@@ -1,1305 +0,0 @@
-from __future__ import annotations
-
-import ast
-import glob
-import os
-import re
-import stat
-import sys
-import time
-from pathlib import Path
-from unittest import mock
-
-import pytest
-from jaraco import path
-
-from setuptools import errors
-from setuptools.command.egg_info import egg_info, manifest_maker, write_entries
-from setuptools.dist import Distribution
-
-from . import contexts, environment
-from .textwrap import DALS
-
-
-class Environment(str):
-    pass
-
-
-@pytest.fixture
-def env():
-    with contexts.tempdir(prefix='setuptools-test.') as env_dir:
-        env = Environment(env_dir)
-        os.chmod(env_dir, stat.S_IRWXU)
-        subs = 'home', 'lib', 'scripts', 'data', 'egg-base'
-        env.paths = dict((dirname, os.path.join(env_dir, dirname)) for dirname in subs)
-        list(map(os.mkdir, env.paths.values()))
-        path.build({
-            env.paths['home']: {
-                '.pydistutils.cfg': DALS(
-                    """
-                [egg_info]
-                egg-base = {egg-base}
-                """.format(**env.paths)
-                )
-            }
-        })
-        yield env
-
-
-class TestEggInfo:
-    setup_script = DALS(
-        """
-        from setuptools import setup
-
-        setup(
-            name='foo',
-            py_modules=['hello'],
-            entry_points={'console_scripts': ['hi = hello.run']},
-            zip_safe=False,
-        )
-        """
-    )
-
-    def _create_project(self):
-        path.build({
-            'setup.py': self.setup_script,
-            'hello.py': DALS(
-                """
-                def run():
-                    print('hello')
-                """
-            ),
-        })
-
-    @staticmethod
-    def _extract_mv_version(pkg_info_lines: list[str]) -> tuple[int, int]:
-        version_str = pkg_info_lines[0].split(' ')[1]
-        major, minor = map(int, version_str.split('.')[:2])
-        return major, minor
-
-    def test_egg_info_save_version_info_setup_empty(self, tmpdir_cwd, env):
-        """
-        When the egg_info section is empty or not present, running
-        save_version_info should add the settings to the setup.cfg
-        in a deterministic order.
-        """
-        setup_cfg = os.path.join(env.paths['home'], 'setup.cfg')
-        dist = Distribution()
-        ei = egg_info(dist)
-        ei.initialize_options()
-        ei.save_version_info(setup_cfg)
-
-        with open(setup_cfg, 'r', encoding="utf-8") as f:
-            content = f.read()
-
-        assert '[egg_info]' in content
-        assert 'tag_build =' in content
-        assert 'tag_date = 0' in content
-
-        expected_order = (
-            'tag_build',
-            'tag_date',
-        )
-
-        self._validate_content_order(content, expected_order)
-
-    @staticmethod
-    def _validate_content_order(content, expected):
-        """
-        Assert that the strings in expected appear in content
-        in order.
-        """
-        pattern = '.*'.join(expected)
-        flags = re.MULTILINE | re.DOTALL
-        assert re.search(pattern, content, flags)
-
-    def test_egg_info_save_version_info_setup_defaults(self, tmpdir_cwd, env):
-        """
-        When running save_version_info on an existing setup.cfg
-        with the 'default' values present from a previous run,
-        the file should remain unchanged.
-        """
-        setup_cfg = os.path.join(env.paths['home'], 'setup.cfg')
-        path.build({
-            setup_cfg: DALS(
-                """
-            [egg_info]
-            tag_build =
-            tag_date = 0
-            """
-            ),
-        })
-        dist = Distribution()
-        ei = egg_info(dist)
-        ei.initialize_options()
-        ei.save_version_info(setup_cfg)
-
-        with open(setup_cfg, 'r', encoding="utf-8") as f:
-            content = f.read()
-
-        assert '[egg_info]' in content
-        assert 'tag_build =' in content
-        assert 'tag_date = 0' in content
-
-        expected_order = (
-            'tag_build',
-            'tag_date',
-        )
-
-        self._validate_content_order(content, expected_order)
-
-    def test_expected_files_produced(self, tmpdir_cwd, env):
-        self._create_project()
-
-        self._run_egg_info_command(tmpdir_cwd, env)
-        actual = os.listdir('foo.egg-info')
-
-        expected = [
-            'PKG-INFO',
-            'SOURCES.txt',
-            'dependency_links.txt',
-            'entry_points.txt',
-            'not-zip-safe',
-            'top_level.txt',
-        ]
-        assert sorted(actual) == expected
-
-    def test_handling_utime_error(self, tmpdir_cwd, env):
-        dist = Distribution()
-        ei = egg_info(dist)
-        utime_patch = mock.patch('os.utime', side_effect=OSError("TEST"))
-        mkpath_patch = mock.patch(
-            'setuptools.command.egg_info.egg_info.mkpath', return_val=None
-        )
-
-        with utime_patch, mkpath_patch:
-            import distutils.errors
-
-            msg = r"Cannot update time stamp of directory 'None'"
-            with pytest.raises(distutils.errors.DistutilsFileError, match=msg):
-                ei.run()
-
-    def test_license_is_a_string(self, tmpdir_cwd, env):
-        setup_config = DALS(
-            """
-            [metadata]
-            name=foo
-            version=0.0.1
-            license=file:MIT
-            """
-        )
-
-        setup_script = DALS(
-            """
-            from setuptools import setup
-
-            setup()
-            """
-        )
-
-        path.build({
-            'setup.py': setup_script,
-            'setup.cfg': setup_config,
-        })
-
-        # This command should fail with a ValueError, but because it's
-        # currently configured to use a subprocess, the actual traceback
-        # object is lost and we need to parse it from stderr
-        with pytest.raises(AssertionError) as exc:
-            self._run_egg_info_command(tmpdir_cwd, env)
-
-        # The only argument to the assertion error should be a traceback
-        # containing a ValueError
-        assert 'ValueError' in exc.value.args[0]
-
-    def test_rebuilt(self, tmpdir_cwd, env):
-        """Ensure timestamps are updated when the command is re-run."""
-        self._create_project()
-
-        self._run_egg_info_command(tmpdir_cwd, env)
-        timestamp_a = os.path.getmtime('foo.egg-info')
-
-        # arbitrary sleep just to handle *really* fast systems
-        time.sleep(0.001)
-
-        self._run_egg_info_command(tmpdir_cwd, env)
-        timestamp_b = os.path.getmtime('foo.egg-info')
-
-        assert timestamp_a != timestamp_b
-
-    def test_manifest_template_is_read(self, tmpdir_cwd, env):
-        self._create_project()
-        path.build({
-            'MANIFEST.in': DALS(
-                """
-                recursive-include docs *.rst
-            """
-            ),
-            'docs': {
-                'usage.rst': "Run 'hi'",
-            },
-        })
-        self._run_egg_info_command(tmpdir_cwd, env)
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        sources_txt = os.path.join(egg_info_dir, 'SOURCES.txt')
-        with open(sources_txt, encoding="utf-8") as f:
-            assert 'docs/usage.rst' in f.read().split('\n')
-
-    def _setup_script_with_requires(self, requires, use_setup_cfg=False):
-        setup_script = DALS(
-            """
-            from setuptools import setup
-
-            setup(name='foo', zip_safe=False, %s)
-            """
-        ) % ('' if use_setup_cfg else requires)
-        setup_config = requires if use_setup_cfg else ''
-        path.build({
-            'setup.py': setup_script,
-            'setup.cfg': setup_config,
-        })
-
-    mismatch_marker = f"python_version<'{sys.version_info[0]}'"
-    # Alternate equivalent syntax.
-    mismatch_marker_alternate = f'python_version < "{sys.version_info[0]}"'
-    invalid_marker = "<=>++"
-
-    class RequiresTestHelper:
-        @staticmethod
-        def parametrize(*test_list, **format_dict):
-            idlist = []
-            argvalues = []
-            for test in test_list:
-                test_params = test.lstrip().split('\n\n', 3)
-                name_kwargs = test_params.pop(0).split('\n')
-                if len(name_kwargs) > 1:
-                    val = name_kwargs[1].strip()
-                    install_cmd_kwargs = ast.literal_eval(val)
-                else:
-                    install_cmd_kwargs = {}
-                name = name_kwargs[0].strip()
-                setup_py_requires, setup_cfg_requires, expected_requires = [
-                    DALS(a).format(**format_dict) for a in test_params
-                ]
-                for id_, requires, use_cfg in (
-                    (name, setup_py_requires, False),
-                    (name + '_in_setup_cfg', setup_cfg_requires, True),
-                ):
-                    idlist.append(id_)
-                    marks = ()
-                    if requires.startswith('@xfail\n'):
-                        requires = requires[7:]
-                        marks = pytest.mark.xfail
-                    argvalues.append(
-                        pytest.param(
-                            requires,
-                            use_cfg,
-                            expected_requires,
-                            install_cmd_kwargs,
-                            marks=marks,
-                        )
-                    )
-            return pytest.mark.parametrize(
-                (
-                    "requires",
-                    "use_setup_cfg",
-                    "expected_requires",
-                    "install_cmd_kwargs",
-                ),
-                argvalues,
-                ids=idlist,
-            )
-
-    @RequiresTestHelper.parametrize(
-        # Format of a test:
-        #
-        # id
-        # install_cmd_kwargs [optional]
-        #
-        # requires block (when used in setup.py)
-        #
-        # requires block (when used in setup.cfg)
-        #
-        # expected contents of requires.txt
-        """
-        install_requires_deterministic
-
-        install_requires=["wheel>=0.5", "pytest"]
-
-        [options]
-        install_requires =
-            wheel>=0.5
-            pytest
-
-        wheel>=0.5
-        pytest
-        """,
-        """
-        install_requires_ordered
-
-        install_requires=["pytest>=3.0.2,!=10.9999"]
-
-        [options]
-        install_requires =
-            pytest>=3.0.2,!=10.9999
-
-        pytest!=10.9999,>=3.0.2
-        """,
-        """
-        install_requires_with_marker
-
-        install_requires=["barbazquux;{mismatch_marker}"],
-
-        [options]
-        install_requires =
-            barbazquux; {mismatch_marker}
-
-        [:{mismatch_marker_alternate}]
-        barbazquux
-        """,
-        """
-        install_requires_with_extra
-        {'cmd': ['egg_info']}
-
-        install_requires=["barbazquux [test]"],
-
-        [options]
-        install_requires =
-            barbazquux [test]
-
-        barbazquux[test]
-        """,
-        """
-        install_requires_with_extra_and_marker
-
-        install_requires=["barbazquux [test]; {mismatch_marker}"],
-
-        [options]
-        install_requires =
-            barbazquux [test]; {mismatch_marker}
-
-        [:{mismatch_marker_alternate}]
-        barbazquux[test]
-        """,
-        """
-        setup_requires_with_markers
-
-        setup_requires=["barbazquux;{mismatch_marker}"],
-
-        [options]
-        setup_requires =
-            barbazquux; {mismatch_marker}
-
-        """,
-        """
-        extras_require_with_extra
-        {'cmd': ['egg_info']}
-
-        extras_require={{"extra": ["barbazquux [test]"]}},
-
-        [options.extras_require]
-        extra = barbazquux [test]
-
-        [extra]
-        barbazquux[test]
-        """,
-        """
-        extras_require_with_extra_and_marker_in_req
-
-        extras_require={{"extra": ["barbazquux [test]; {mismatch_marker}"]}},
-
-        [options.extras_require]
-        extra =
-            barbazquux [test]; {mismatch_marker}
-
-        [extra]
-
-        [extra:{mismatch_marker_alternate}]
-        barbazquux[test]
-        """,
-        # FIXME: ConfigParser does not allow : in key names!
-        """
-        extras_require_with_marker
-
-        extras_require={{":{mismatch_marker}": ["barbazquux"]}},
-
-        @xfail
-        [options.extras_require]
-        :{mismatch_marker} = barbazquux
-
-        [:{mismatch_marker}]
-        barbazquux
-        """,
-        """
-        extras_require_with_marker_in_req
-
-        extras_require={{"extra": ["barbazquux; {mismatch_marker}"]}},
-
-        [options.extras_require]
-        extra =
-            barbazquux; {mismatch_marker}
-
-        [extra]
-
-        [extra:{mismatch_marker_alternate}]
-        barbazquux
-        """,
-        """
-        extras_require_with_empty_section
-
-        extras_require={{"empty": []}},
-
-        [options.extras_require]
-        empty =
-
-        [empty]
-        """,
-        # Format arguments.
-        invalid_marker=invalid_marker,
-        mismatch_marker=mismatch_marker,
-        mismatch_marker_alternate=mismatch_marker_alternate,
-    )
-    def test_requires(
-        self,
-        tmpdir_cwd,
-        env,
-        requires,
-        use_setup_cfg,
-        expected_requires,
-        install_cmd_kwargs,
-    ):
-        self._setup_script_with_requires(requires, use_setup_cfg)
-        self._run_egg_info_command(tmpdir_cwd, env, **install_cmd_kwargs)
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        requires_txt = os.path.join(egg_info_dir, 'requires.txt')
-        if os.path.exists(requires_txt):
-            with open(requires_txt, encoding="utf-8") as fp:
-                install_requires = fp.read()
-        else:
-            install_requires = ''
-        assert install_requires.lstrip() == expected_requires
-        assert glob.glob(os.path.join(env.paths['lib'], 'barbazquux*')) == []
-
-    def test_install_requires_unordered_disallowed(self, tmpdir_cwd, env):
-        """
-        Packages that pass unordered install_requires sequences
-        should be rejected as they produce non-deterministic
-        builds. See #458.
-        """
-        req = 'install_requires={"fake-factory==0.5.2", "pytz"}'
-        self._setup_script_with_requires(req)
-        with pytest.raises(AssertionError):
-            self._run_egg_info_command(tmpdir_cwd, env)
-
-    def test_extras_require_with_invalid_marker(self, tmpdir_cwd, env):
-        tmpl = 'extras_require={{":{marker}": ["barbazquux"]}},'
-        req = tmpl.format(marker=self.invalid_marker)
-        self._setup_script_with_requires(req)
-        with pytest.raises(AssertionError):
-            self._run_egg_info_command(tmpdir_cwd, env)
-        assert glob.glob(os.path.join(env.paths['lib'], 'barbazquux*')) == []
-
-    def test_extras_require_with_invalid_marker_in_req(self, tmpdir_cwd, env):
-        tmpl = 'extras_require={{"extra": ["barbazquux; {marker}"]}},'
-        req = tmpl.format(marker=self.invalid_marker)
-        self._setup_script_with_requires(req)
-        with pytest.raises(AssertionError):
-            self._run_egg_info_command(tmpdir_cwd, env)
-        assert glob.glob(os.path.join(env.paths['lib'], 'barbazquux*')) == []
-
-    def test_provides_extra(self, tmpdir_cwd, env):
-        self._setup_script_with_requires('extras_require={"foobar": ["barbazquux"]},')
-        environ = os.environ.copy().update(
-            HOME=env.paths['home'],
-        )
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-            env=environ,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        assert 'Provides-Extra: foobar' in pkg_info_lines
-        assert 'Metadata-Version: 2.4' in pkg_info_lines
-
-    def test_doesnt_provides_extra(self, tmpdir_cwd, env):
-        self._setup_script_with_requires(
-            """install_requires=["spam ; python_version<'3.6'"]"""
-        )
-        environ = os.environ.copy().update(
-            HOME=env.paths['home'],
-        )
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-            env=environ,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_text = fp.read()
-        assert 'Provides-Extra:' not in pkg_info_text
-
-    @pytest.mark.parametrize(
-        ('files', 'license_in_sources'),
-        [
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE
-                              """
-                    ),
-                    'LICENSE': "Test license",
-                },
-                True,
-            ),  # with license
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = INVALID_LICENSE
-                              """
-                    ),
-                    'LICENSE': "Test license",
-                },
-                False,
-            ),  # with an invalid license
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              """
-                    ),
-                    'LICENSE': "Test license",
-                },
-                True,
-            ),  # no license_file attribute, LICENSE auto-included
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE
-                              """
-                    ),
-                    'MANIFEST.in': "exclude LICENSE",
-                    'LICENSE': "Test license",
-                },
-                True,
-            ),  # manifest is overwritten by license_file
-            pytest.param(
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICEN[CS]E*
-                              """
-                    ),
-                    'LICENSE': "Test license",
-                },
-                True,
-                id="glob_pattern",
-            ),
-        ],
-    )
-    def test_setup_cfg_license_file(self, tmpdir_cwd, env, files, license_in_sources):
-        self._create_project()
-        path.build(files)
-
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-
-        sources_text = Path(egg_info_dir, "SOURCES.txt").read_text(encoding="utf-8")
-
-        if license_in_sources:
-            assert 'LICENSE' in sources_text
-        else:
-            assert 'LICENSE' not in sources_text
-            # for invalid license test
-            assert 'INVALID_LICENSE' not in sources_text
-
-    @pytest.mark.parametrize(
-        ('files', 'incl_licenses', 'excl_licenses'),
-        [
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files =
-                                  LICENSE-ABC
-                                  LICENSE-XYZ
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                },
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-                [],
-            ),  # with licenses
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files = LICENSE-ABC, LICENSE-XYZ
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                },
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-                [],
-            ),  # with commas
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files =
-                                  LICENSE-ABC
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                },
-                ['LICENSE-ABC'],
-                ['LICENSE-XYZ'],
-            ),  # with one license
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files =
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                },
-                [],
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-            ),  # empty
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files = LICENSE-XYZ
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                },
-                ['LICENSE-XYZ'],
-                ['LICENSE-ABC'],
-            ),  # on same line
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files =
-                                  LICENSE-ABC
-                                  INVALID_LICENSE
-                              """
-                    ),
-                    'LICENSE-ABC': "Test license",
-                },
-                ['LICENSE-ABC'],
-                ['INVALID_LICENSE'],
-            ),  # with an invalid license
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              """
-                    ),
-                    'LICENSE': "Test license",
-                },
-                ['LICENSE'],
-                [],
-            ),  # no license_files attribute, LICENSE auto-included
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files = LICENSE
-                              """
-                    ),
-                    'MANIFEST.in': "exclude LICENSE",
-                    'LICENSE': "Test license",
-                },
-                ['LICENSE'],
-                [],
-            ),  # manifest is overwritten by license_files
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files =
-                                  LICENSE-ABC
-                                  LICENSE-XYZ
-                              """
-                    ),
-                    'MANIFEST.in': "exclude LICENSE-XYZ",
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                    # manifest is overwritten by license_files
-                },
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-                [],
-            ),
-            pytest.param(
-                {
-                    'setup.cfg': "",
-                    'LICENSE-ABC': "ABC license",
-                    'COPYING-ABC': "ABC copying",
-                    'NOTICE-ABC': "ABC notice",
-                    'AUTHORS-ABC': "ABC authors",
-                    'LICENCE-XYZ': "XYZ license",
-                    'LICENSE': "License",
-                    'INVALID-LICENSE': "Invalid license",
-                },
-                [
-                    'LICENSE-ABC',
-                    'COPYING-ABC',
-                    'NOTICE-ABC',
-                    'AUTHORS-ABC',
-                    'LICENCE-XYZ',
-                    'LICENSE',
-                ],
-                ['INVALID-LICENSE'],
-                # ('LICEN[CS]E*', 'COPYING*', 'NOTICE*', 'AUTHORS*')
-                id="default_glob_patterns",
-            ),
-            pytest.param(
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files =
-                                  LICENSE*
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'NOTICE-XYZ': "XYZ notice",
-                },
-                ['LICENSE-ABC'],
-                ['NOTICE-XYZ'],
-                id="no_default_glob_patterns",
-            ),
-            pytest.param(
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files =
-                                  LICENSE-ABC
-                                  LICENSE*
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                },
-                ['LICENSE-ABC'],
-                [],
-                id="files_only_added_once",
-            ),
-            pytest.param(
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_files = **/LICENSE
-                              """
-                    ),
-                    'LICENSE': "ABC license",
-                    'LICENSE-OTHER': "Don't include",
-                    'vendor': {'LICENSE': "Vendor license"},
-                },
-                ['LICENSE', 'vendor/LICENSE'],
-                ['LICENSE-OTHER'],
-                id="recursive_glob",
-            ),
-        ],
-    )
-    def test_setup_cfg_license_files(
-        self, tmpdir_cwd, env, files, incl_licenses, excl_licenses
-    ):
-        self._create_project()
-        path.build(files)
-
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-
-        sources_text = Path(egg_info_dir, "SOURCES.txt").read_text(encoding="utf-8")
-        sources_lines = [line.strip() for line in sources_text.splitlines()]
-
-        for lf in incl_licenses:
-            assert sources_lines.count(lf) == 1
-
-        for lf in excl_licenses:
-            assert sources_lines.count(lf) == 0
-
-    @pytest.mark.parametrize(
-        ('files', 'incl_licenses', 'excl_licenses'),
-        [
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file =
-                              license_files =
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                },
-                [],
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-            ),  # both empty
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file =
-                                  LICENSE-ABC
-                                  LICENSE-XYZ
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-XYZ': "XYZ license",
-                    # license_file is still singular
-                },
-                [],
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-            ),
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE-ABC
-                              license_files =
-                                  LICENSE-XYZ
-                                  LICENSE-PQR
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-PQR': "PQR license",
-                    'LICENSE-XYZ': "XYZ license",
-                },
-                ['LICENSE-ABC', 'LICENSE-PQR', 'LICENSE-XYZ'],
-                [],
-            ),  # combined
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE-ABC
-                              license_files =
-                                  LICENSE-ABC
-                                  LICENSE-XYZ
-                                  LICENSE-PQR
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-PQR': "PQR license",
-                    'LICENSE-XYZ': "XYZ license",
-                    # duplicate license
-                },
-                ['LICENSE-ABC', 'LICENSE-PQR', 'LICENSE-XYZ'],
-                [],
-            ),
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE-ABC
-                              license_files =
-                                  LICENSE-XYZ
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-PQR': "PQR license",
-                    'LICENSE-XYZ': "XYZ license",
-                    # combined subset
-                },
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-                ['LICENSE-PQR'],
-            ),
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE-ABC
-                              license_files =
-                                  LICENSE-XYZ
-                                  LICENSE-PQR
-                              """
-                    ),
-                    'LICENSE-PQR': "Test license",
-                    # with invalid licenses
-                },
-                ['LICENSE-PQR'],
-                ['LICENSE-ABC', 'LICENSE-XYZ'],
-            ),
-            (
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE-ABC
-                              license_files =
-                                LICENSE-PQR
-                                LICENSE-XYZ
-                              """
-                    ),
-                    'MANIFEST.in': "exclude LICENSE-ABC\nexclude LICENSE-PQR",
-                    'LICENSE-ABC': "ABC license",
-                    'LICENSE-PQR': "PQR license",
-                    'LICENSE-XYZ': "XYZ license",
-                    # manifest is overwritten
-                },
-                ['LICENSE-ABC', 'LICENSE-PQR', 'LICENSE-XYZ'],
-                [],
-            ),
-            pytest.param(
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE*
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'NOTICE-XYZ': "XYZ notice",
-                },
-                ['LICENSE-ABC'],
-                ['NOTICE-XYZ'],
-                id="no_default_glob_patterns",
-            ),
-            pytest.param(
-                {
-                    'setup.cfg': DALS(
-                        """
-                              [metadata]
-                              license_file = LICENSE*
-                              license_files =
-                                NOTICE*
-                              """
-                    ),
-                    'LICENSE-ABC': "ABC license",
-                    'NOTICE-ABC': "ABC notice",
-                    'AUTHORS-ABC': "ABC authors",
-                },
-                ['LICENSE-ABC', 'NOTICE-ABC'],
-                ['AUTHORS-ABC'],
-                id="combined_glob_patterrns",
-            ),
-        ],
-    )
-    def test_setup_cfg_license_file_license_files(
-        self, tmpdir_cwd, env, files, incl_licenses, excl_licenses
-    ):
-        self._create_project()
-        path.build(files)
-
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-
-        sources_text = Path(egg_info_dir, "SOURCES.txt").read_text(encoding="utf-8")
-        sources_lines = [line.strip() for line in sources_text.splitlines()]
-
-        for lf in incl_licenses:
-            assert sources_lines.count(lf) == 1
-
-        for lf in excl_licenses:
-            assert sources_lines.count(lf) == 0
-
-    def test_license_file_attr_pkg_info(self, tmpdir_cwd, env):
-        """All matched license files should have a corresponding License-File."""
-        self._create_project()
-        path.build({
-            "setup.cfg": DALS(
-                """
-                              [metadata]
-                              license_files =
-                                  NOTICE*
-                                  LICENSE*
-                                  **/LICENSE
-                              """
-            ),
-            "LICENSE-ABC": "ABC license",
-            "LICENSE-XYZ": "XYZ license",
-            "NOTICE": "included",
-            "IGNORE": "not include",
-            "vendor": {'LICENSE': "Vendor license"},
-        })
-
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        license_file_lines = [
-            line for line in pkg_info_lines if line.startswith('License-File:')
-        ]
-
-        # Only 'NOTICE', LICENSE-ABC', and 'LICENSE-XYZ' should have been matched
-        # Also assert that order from license_files is keeped
-        assert len(license_file_lines) == 4
-        assert "License-File: NOTICE" == license_file_lines[0]
-        assert "License-File: LICENSE-ABC" in license_file_lines[1:]
-        assert "License-File: LICENSE-XYZ" in license_file_lines[1:]
-        assert "License-File: vendor/LICENSE" in license_file_lines[3]
-
-    def test_metadata_version(self, tmpdir_cwd, env):
-        """Make sure latest metadata version is used by default."""
-        self._setup_script_with_requires("")
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        # Update metadata version if changed
-        assert self._extract_mv_version(pkg_info_lines) == (2, 4)
-
-    def test_long_description_content_type(self, tmpdir_cwd, env):
-        # Test that specifying a `long_description_content_type` keyword arg to
-        # the `setup` function results in writing a `Description-Content-Type`
-        # line to the `PKG-INFO` file in the `.egg-info`
-        # directory.
-        # `Description-Content-Type` is described at
-        # https://github.com/pypa/python-packaging-user-guide/pull/258
-
-        self._setup_script_with_requires(
-            """long_description_content_type='text/markdown',"""
-        )
-        environ = os.environ.copy().update(
-            HOME=env.paths['home'],
-        )
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-            env=environ,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        expected_line = 'Description-Content-Type: text/markdown'
-        assert expected_line in pkg_info_lines
-        assert 'Metadata-Version: 2.4' in pkg_info_lines
-
-    def test_long_description(self, tmpdir_cwd, env):
-        # Test that specifying `long_description` and `long_description_content_type`
-        # keyword args to the `setup` function results in writing
-        # the description in the message payload of the `PKG-INFO` file
-        # in the `.egg-info` directory.
-        self._setup_script_with_requires(
-            "long_description='This is a long description\\nover multiple lines',"
-            "long_description_content_type='text/markdown',"
-        )
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        assert 'Metadata-Version: 2.4' in pkg_info_lines
-        assert '' == pkg_info_lines[-1]  # last line should be empty
-        long_desc_lines = pkg_info_lines[pkg_info_lines.index('') :]
-        assert 'This is a long description' in long_desc_lines
-        assert 'over multiple lines' in long_desc_lines
-
-    def test_project_urls(self, tmpdir_cwd, env):
-        # Test that specifying a `project_urls` dict to the `setup`
-        # function results in writing multiple `Project-URL` lines to
-        # the `PKG-INFO` file in the `.egg-info`
-        # directory.
-        # `Project-URL` is described at https://packaging.python.org
-        #     /specifications/core-metadata/#project-url-multiple-use
-
-        self._setup_script_with_requires(
-            """project_urls={
-                'Link One': 'https://example.com/one/',
-                'Link Two': 'https://example.com/two/',
-                },"""
-        )
-        environ = os.environ.copy().update(
-            HOME=env.paths['home'],
-        )
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-            env=environ,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        expected_line = 'Project-URL: Link One, https://example.com/one/'
-        assert expected_line in pkg_info_lines
-        expected_line = 'Project-URL: Link Two, https://example.com/two/'
-        assert expected_line in pkg_info_lines
-        assert self._extract_mv_version(pkg_info_lines) >= (1, 2)
-
-    def test_license(self, tmpdir_cwd, env):
-        """Test single line license."""
-        self._setup_script_with_requires("license='MIT',")
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        assert 'License: MIT' in pkg_info_lines
-
-    def test_license_escape(self, tmpdir_cwd, env):
-        """Test license is escaped correctly if longer than one line."""
-        self._setup_script_with_requires(
-            "license='This is a long license text \\nover multiple lines',"
-        )
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-
-        assert 'License: This is a long license text ' in pkg_info_lines
-        assert '        over multiple lines' in pkg_info_lines
-        assert 'text \n        over multiple' in '\n'.join(pkg_info_lines)
-
-    def test_python_requires_egg_info(self, tmpdir_cwd, env):
-        self._setup_script_with_requires("""python_requires='>=2.7.12',""")
-        environ = os.environ.copy().update(
-            HOME=env.paths['home'],
-        )
-        environment.run_setup_py(
-            cmd=['egg_info'],
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-            env=environ,
-        )
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        assert 'Requires-Python: >=2.7.12' in pkg_info_lines
-        assert self._extract_mv_version(pkg_info_lines) >= (1, 2)
-
-    def test_manifest_maker_warning_suppression(self):
-        fixtures = [
-            "standard file not found: should have one of foo.py, bar.py",
-            "standard file 'setup.py' not found",
-        ]
-
-        for msg in fixtures:
-            assert manifest_maker._should_suppress_warning(msg)
-
-    def test_egg_info_includes_setup_py(self, tmpdir_cwd):
-        self._create_project()
-        dist = Distribution({"name": "foo", "version": "0.0.1"})
-        dist.script_name = "non_setup.py"
-        egg_info_instance = egg_info(dist)
-        egg_info_instance.finalize_options()
-        egg_info_instance.run()
-
-        assert 'setup.py' in egg_info_instance.filelist.files
-
-        with open(egg_info_instance.egg_info + "/SOURCES.txt", encoding="utf-8") as f:
-            sources = f.read().split('\n')
-            assert 'setup.py' in sources
-
-    def _run_egg_info_command(self, tmpdir_cwd, env, cmd=None, output=None):
-        environ = os.environ.copy().update(
-            HOME=env.paths['home'],
-        )
-        if cmd is None:
-            cmd = [
-                'egg_info',
-            ]
-        code, data = environment.run_setup_py(
-            cmd=cmd,
-            pypath=os.pathsep.join([env.paths['lib'], str(tmpdir_cwd)]),
-            data_stream=1,
-            env=environ,
-        )
-        assert not code, data
-
-        if output:
-            assert output in data
-
-    def test_egg_info_tag_only_once(self, tmpdir_cwd, env):
-        self._create_project()
-        path.build({
-            'setup.cfg': DALS(
-                """
-                              [egg_info]
-                              tag_build = dev
-                              tag_date = 0
-                              tag_svn_revision = 0
-                              """
-            ),
-        })
-        self._run_egg_info_command(tmpdir_cwd, env)
-        egg_info_dir = os.path.join('.', 'foo.egg-info')
-        with open(os.path.join(egg_info_dir, 'PKG-INFO'), encoding="utf-8") as fp:
-            pkg_info_lines = fp.read().split('\n')
-        assert 'Version: 0.0.0.dev0' in pkg_info_lines
-
-
-class TestWriteEntries:
-    def test_invalid_entry_point(self, tmpdir_cwd, env):
-        dist = Distribution({"name": "foo", "version": "0.0.1"})
-        dist.entry_points = {"foo": "foo = invalid-identifier:foo"}
-        cmd = dist.get_command_obj("egg_info")
-        expected_msg = r"Problems to parse .*invalid-identifier.*"
-        with pytest.raises(errors.OptionError, match=expected_msg) as ex:
-            write_entries(cmd, "entry_points", "entry_points.txt")
-            assert "ensure entry-point follows the spec" in ex.value.args[0]
-
-    def test_valid_entry_point(self, tmpdir_cwd, env):
-        dist = Distribution({"name": "foo", "version": "0.0.1"})
-        dist.entry_points = {
-            "abc": "foo = bar:baz",
-            "def": ["faa = bor:boz"],
-        }
-        cmd = dist.get_command_obj("egg_info")
-        write_entries(cmd, "entry_points", "entry_points.txt")
-        content = Path("entry_points.txt").read_text(encoding="utf-8")
-        assert "[abc]\nfoo = bar:baz\n" in content
-        assert "[def]\nfaa = bor:boz\n" in content
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_extern.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_extern.py
deleted file mode 100644
index d7eb3c6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_extern.py
+++ /dev/null
@@ -1,15 +0,0 @@
-import importlib
-import pickle
-
-import packaging
-
-from setuptools import Distribution
-
-
-def test_reimport_extern():
-    packaging2 = importlib.import_module(packaging.__name__)
-    assert packaging is packaging2
-
-
-def test_distribution_picklable():
-    pickle.loads(pickle.dumps(Distribution()))
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_find_packages.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_find_packages.py
deleted file mode 100644
index 9fd9f8f..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_find_packages.py
+++ /dev/null
@@ -1,218 +0,0 @@
-"""Tests for automatic package discovery"""
-
-import os
-import shutil
-import tempfile
-
-import pytest
-
-from setuptools import find_namespace_packages, find_packages
-from setuptools.discovery import FlatLayoutPackageFinder
-
-from .compat.py39 import os_helper
-
-
-class TestFindPackages:
-    def setup_method(self, method):
-        self.dist_dir = tempfile.mkdtemp()
-        self._make_pkg_structure()
-
-    def teardown_method(self, method):
-        shutil.rmtree(self.dist_dir)
-
-    def _make_pkg_structure(self):
-        """Make basic package structure.
-
-        dist/
-            docs/
-                conf.py
-            pkg/
-                __pycache__/
-                nspkg/
-                    mod.py
-                subpkg/
-                    assets/
-                        asset
-                    __init__.py
-            setup.py
-
-        """
-        self.docs_dir = self._mkdir('docs', self.dist_dir)
-        self._touch('conf.py', self.docs_dir)
-        self.pkg_dir = self._mkdir('pkg', self.dist_dir)
-        self._mkdir('__pycache__', self.pkg_dir)
-        self.ns_pkg_dir = self._mkdir('nspkg', self.pkg_dir)
-        self._touch('mod.py', self.ns_pkg_dir)
-        self.sub_pkg_dir = self._mkdir('subpkg', self.pkg_dir)
-        self.asset_dir = self._mkdir('assets', self.sub_pkg_dir)
-        self._touch('asset', self.asset_dir)
-        self._touch('__init__.py', self.sub_pkg_dir)
-        self._touch('setup.py', self.dist_dir)
-
-    def _mkdir(self, path, parent_dir=None):
-        if parent_dir:
-            path = os.path.join(parent_dir, path)
-        os.mkdir(path)
-        return path
-
-    def _touch(self, path, dir_=None):
-        if dir_:
-            path = os.path.join(dir_, path)
-        open(path, 'wb').close()
-        return path
-
-    def test_regular_package(self):
-        self._touch('__init__.py', self.pkg_dir)
-        packages = find_packages(self.dist_dir)
-        assert packages == ['pkg', 'pkg.subpkg']
-
-    def test_exclude(self):
-        self._touch('__init__.py', self.pkg_dir)
-        packages = find_packages(self.dist_dir, exclude=('pkg.*',))
-        assert packages == ['pkg']
-
-    def test_exclude_recursive(self):
-        """
-        Excluding a parent package should not exclude child packages as well.
-        """
-        self._touch('__init__.py', self.pkg_dir)
-        self._touch('__init__.py', self.sub_pkg_dir)
-        packages = find_packages(self.dist_dir, exclude=('pkg',))
-        assert packages == ['pkg.subpkg']
-
-    def test_include_excludes_other(self):
-        """
-        If include is specified, other packages should be excluded.
-        """
-        self._touch('__init__.py', self.pkg_dir)
-        alt_dir = self._mkdir('other_pkg', self.dist_dir)
-        self._touch('__init__.py', alt_dir)
-        packages = find_packages(self.dist_dir, include=['other_pkg'])
-        assert packages == ['other_pkg']
-
-    def test_dir_with_dot_is_skipped(self):
-        shutil.rmtree(os.path.join(self.dist_dir, 'pkg/subpkg/assets'))
-        data_dir = self._mkdir('some.data', self.pkg_dir)
-        self._touch('__init__.py', data_dir)
-        self._touch('file.dat', data_dir)
-        packages = find_packages(self.dist_dir)
-        assert 'pkg.some.data' not in packages
-
-    def test_dir_with_packages_in_subdir_is_excluded(self):
-        """
-        Ensure that a package in a non-package such as build/pkg/__init__.py
-        is excluded.
-        """
-        build_dir = self._mkdir('build', self.dist_dir)
-        build_pkg_dir = self._mkdir('pkg', build_dir)
-        self._touch('__init__.py', build_pkg_dir)
-        packages = find_packages(self.dist_dir)
-        assert 'build.pkg' not in packages
-
-    @pytest.mark.skipif(not os_helper.can_symlink(), reason='Symlink support required')
-    def test_symlinked_packages_are_included(self):
-        """
-        A symbolically-linked directory should be treated like any other
-        directory when matched as a package.
-
-        Create a link from lpkg -> pkg.
-        """
-        self._touch('__init__.py', self.pkg_dir)
-        linked_pkg = os.path.join(self.dist_dir, 'lpkg')
-        os.symlink('pkg', linked_pkg)
-        assert os.path.isdir(linked_pkg)
-        packages = find_packages(self.dist_dir)
-        assert 'lpkg' in packages
-
-    def _assert_packages(self, actual, expected):
-        assert set(actual) == set(expected)
-
-    def test_pep420_ns_package(self):
-        packages = find_namespace_packages(
-            self.dist_dir, include=['pkg*'], exclude=['pkg.subpkg.assets']
-        )
-        self._assert_packages(packages, ['pkg', 'pkg.nspkg', 'pkg.subpkg'])
-
-    def test_pep420_ns_package_no_includes(self):
-        packages = find_namespace_packages(self.dist_dir, exclude=['pkg.subpkg.assets'])
-        self._assert_packages(packages, ['docs', 'pkg', 'pkg.nspkg', 'pkg.subpkg'])
-
-    def test_pep420_ns_package_no_includes_or_excludes(self):
-        packages = find_namespace_packages(self.dist_dir)
-        expected = ['docs', 'pkg', 'pkg.nspkg', 'pkg.subpkg', 'pkg.subpkg.assets']
-        self._assert_packages(packages, expected)
-
-    def test_regular_package_with_nested_pep420_ns_packages(self):
-        self._touch('__init__.py', self.pkg_dir)
-        packages = find_namespace_packages(
-            self.dist_dir, exclude=['docs', 'pkg.subpkg.assets']
-        )
-        self._assert_packages(packages, ['pkg', 'pkg.nspkg', 'pkg.subpkg'])
-
-    def test_pep420_ns_package_no_non_package_dirs(self):
-        shutil.rmtree(self.docs_dir)
-        shutil.rmtree(os.path.join(self.dist_dir, 'pkg/subpkg/assets'))
-        packages = find_namespace_packages(self.dist_dir)
-        self._assert_packages(packages, ['pkg', 'pkg.nspkg', 'pkg.subpkg'])
-
-
-class TestFlatLayoutPackageFinder:
-    EXAMPLES = {
-        "hidden-folders": (
-            [".pkg/__init__.py", "pkg/__init__.py", "pkg/nested/file.txt"],
-            ["pkg", "pkg.nested"],
-        ),
-        "private-packages": (
-            ["_pkg/__init__.py", "pkg/_private/__init__.py"],
-            ["pkg", "pkg._private"],
-        ),
-        "invalid-name": (
-            ["invalid-pkg/__init__.py", "other.pkg/__init__.py", "yet,another/file.py"],
-            [],
-        ),
-        "docs": (["pkg/__init__.py", "docs/conf.py", "docs/readme.rst"], ["pkg"]),
-        "tests": (
-            ["pkg/__init__.py", "tests/test_pkg.py", "tests/__init__.py"],
-            ["pkg"],
-        ),
-        "examples": (
-            [
-                "pkg/__init__.py",
-                "examples/__init__.py",
-                "examples/file.py",
-                "example/other_file.py",
-                # Sub-packages should always be fine
-                "pkg/example/__init__.py",
-                "pkg/examples/__init__.py",
-            ],
-            ["pkg", "pkg.examples", "pkg.example"],
-        ),
-        "tool-specific": (
-            [
-                "htmlcov/index.html",
-                "pkg/__init__.py",
-                "tasks/__init__.py",
-                "tasks/subpackage/__init__.py",
-                "fabfile/__init__.py",
-                "fabfile/subpackage/__init__.py",
-                # Sub-packages should always be fine
-                "pkg/tasks/__init__.py",
-                "pkg/fabfile/__init__.py",
-            ],
-            ["pkg", "pkg.tasks", "pkg.fabfile"],
-        ),
-    }
-
-    @pytest.mark.parametrize("example", EXAMPLES.keys())
-    def test_unwanted_directories_not_included(self, tmp_path, example):
-        files, expected_packages = self.EXAMPLES[example]
-        ensure_files(tmp_path, files)
-        found_packages = FlatLayoutPackageFinder.find(str(tmp_path))
-        assert set(found_packages) == set(expected_packages)
-
-
-def ensure_files(root_path, files):
-    for file in files:
-        path = root_path / file
-        path.parent.mkdir(parents=True, exist_ok=True)
-        path.touch()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_find_py_modules.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_find_py_modules.py
deleted file mode 100644
index 8034b54..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_find_py_modules.py
+++ /dev/null
@@ -1,73 +0,0 @@
-"""Tests for automatic discovery of modules"""
-
-import os
-
-import pytest
-
-from setuptools.discovery import FlatLayoutModuleFinder, ModuleFinder
-
-from .compat.py39 import os_helper
-from .test_find_packages import ensure_files
-
-
-class TestModuleFinder:
-    def find(self, path, *args, **kwargs):
-        return set(ModuleFinder.find(str(path), *args, **kwargs))
-
-    EXAMPLES = {
-        # circumstance: (files, kwargs, expected_modules)
-        "simple_folder": (
-            ["file.py", "other.py"],
-            {},  # kwargs
-            ["file", "other"],
-        ),
-        "exclude": (
-            ["file.py", "other.py"],
-            {"exclude": ["f*"]},
-            ["other"],
-        ),
-        "include": (
-            ["file.py", "fole.py", "other.py"],
-            {"include": ["f*"], "exclude": ["fo*"]},
-            ["file"],
-        ),
-        "invalid-name": (["my-file.py", "other.file.py"], {}, []),
-    }
-
-    @pytest.mark.parametrize("example", EXAMPLES.keys())
-    def test_finder(self, tmp_path, example):
-        files, kwargs, expected_modules = self.EXAMPLES[example]
-        ensure_files(tmp_path, files)
-        assert self.find(tmp_path, **kwargs) == set(expected_modules)
-
-    @pytest.mark.skipif(not os_helper.can_symlink(), reason='Symlink support required')
-    def test_symlinked_packages_are_included(self, tmp_path):
-        src = "_myfiles/file.py"
-        ensure_files(tmp_path, [src])
-        os.symlink(tmp_path / src, tmp_path / "link.py")
-        assert self.find(tmp_path) == {"link"}
-
-
-class TestFlatLayoutModuleFinder:
-    def find(self, path, *args, **kwargs):
-        return set(FlatLayoutModuleFinder.find(str(path)))
-
-    EXAMPLES = {
-        # circumstance: (files, expected_modules)
-        "hidden-files": ([".module.py"], []),
-        "private-modules": (["_module.py"], []),
-        "common-names": (
-            ["setup.py", "conftest.py", "test.py", "tests.py", "example.py", "mod.py"],
-            ["mod"],
-        ),
-        "tool-specific": (
-            ["tasks.py", "fabfile.py", "noxfile.py", "dodo.py", "manage.py", "mod.py"],
-            ["mod"],
-        ),
-    }
-
-    @pytest.mark.parametrize("example", EXAMPLES.keys())
-    def test_unwanted_files_not_included(self, tmp_path, example):
-        files, expected_modules = self.EXAMPLES[example]
-        ensure_files(tmp_path, files)
-        assert self.find(tmp_path) == set(expected_modules)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_glob.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_glob.py
deleted file mode 100644
index 8d225a4..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_glob.py
+++ /dev/null
@@ -1,45 +0,0 @@
-import pytest
-from jaraco import path
-
-from setuptools.glob import glob
-
-
-@pytest.mark.parametrize(
-    ('tree', 'pattern', 'matches'),
-    (
-        ('', b'', []),
-        ('', '', []),
-        (
-            """
-     appveyor.yml
-     CHANGES.rst
-     LICENSE
-     MANIFEST.in
-     pyproject.toml
-     README.rst
-     setup.cfg
-     setup.py
-     """,
-            '*.rst',
-            ('CHANGES.rst', 'README.rst'),
-        ),
-        (
-            """
-     appveyor.yml
-     CHANGES.rst
-     LICENSE
-     MANIFEST.in
-     pyproject.toml
-     README.rst
-     setup.cfg
-     setup.py
-     """,
-            b'*.rst',
-            (b'CHANGES.rst', b'README.rst'),
-        ),
-    ),
-)
-def test_glob(monkeypatch, tmpdir, tree, pattern, matches):
-    monkeypatch.chdir(tmpdir)
-    path.build({name: '' for name in tree.split()})
-    assert list(sorted(glob(pattern))) == list(sorted(matches))
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_install_scripts.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_install_scripts.py
deleted file mode 100644
index e62a6b7..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_install_scripts.py
+++ /dev/null
@@ -1,89 +0,0 @@
-"""install_scripts tests"""
-
-import sys
-
-import pytest
-
-from setuptools.command.install_scripts import install_scripts
-from setuptools.dist import Distribution
-
-from . import contexts
-
-
-class TestInstallScripts:
-    settings = dict(
-        name='foo',
-        entry_points={'console_scripts': ['foo=foo:foo']},
-        version='0.0',
-    )
-    unix_exe = '/usr/dummy-test-path/local/bin/python'
-    unix_spaces_exe = '/usr/bin/env dummy-test-python'
-    win32_exe = 'C:\\Dummy Test Path\\Program Files\\Python 3.6\\python.exe'
-
-    def _run_install_scripts(self, install_dir, executable=None):
-        dist = Distribution(self.settings)
-        dist.script_name = 'setup.py'
-        cmd = install_scripts(dist)
-        cmd.install_dir = install_dir
-        if executable is not None:
-            bs = cmd.get_finalized_command('build_scripts')
-            bs.executable = executable
-        cmd.ensure_finalized()
-        with contexts.quiet():
-            cmd.run()
-
-    @pytest.mark.skipif(sys.platform == 'win32', reason='non-Windows only')
-    def test_sys_executable_escaping_unix(self, tmpdir, monkeypatch):
-        """
-        Ensure that shebang is not quoted on Unix when getting the Python exe
-        from sys.executable.
-        """
-        expected = f'#!{self.unix_exe}\n'
-        monkeypatch.setattr('sys.executable', self.unix_exe)
-        with tmpdir.as_cwd():
-            self._run_install_scripts(str(tmpdir))
-            with open(str(tmpdir.join('foo')), 'r', encoding="utf-8") as f:
-                actual = f.readline()
-        assert actual == expected
-
-    @pytest.mark.skipif(sys.platform != 'win32', reason='Windows only')
-    def test_sys_executable_escaping_win32(self, tmpdir, monkeypatch):
-        """
-        Ensure that shebang is quoted on Windows when getting the Python exe
-        from sys.executable and it contains a space.
-        """
-        expected = f'#!"{self.win32_exe}"\n'
-        monkeypatch.setattr('sys.executable', self.win32_exe)
-        with tmpdir.as_cwd():
-            self._run_install_scripts(str(tmpdir))
-            with open(str(tmpdir.join('foo-script.py')), 'r', encoding="utf-8") as f:
-                actual = f.readline()
-        assert actual == expected
-
-    @pytest.mark.skipif(sys.platform == 'win32', reason='non-Windows only')
-    def test_executable_with_spaces_escaping_unix(self, tmpdir):
-        """
-        Ensure that shebang on Unix is not quoted, even when
-        a value with spaces
-        is specified using --executable.
-        """
-        expected = f'#!{self.unix_spaces_exe}\n'
-        with tmpdir.as_cwd():
-            self._run_install_scripts(str(tmpdir), self.unix_spaces_exe)
-            with open(str(tmpdir.join('foo')), 'r', encoding="utf-8") as f:
-                actual = f.readline()
-        assert actual == expected
-
-    @pytest.mark.skipif(sys.platform != 'win32', reason='Windows only')
-    def test_executable_arg_escaping_win32(self, tmpdir):
-        """
-        Ensure that shebang on Windows is quoted when
-        getting a path with spaces
-        from --executable, that is itself properly quoted.
-        """
-        expected = f'#!"{self.win32_exe}"\n'
-        with tmpdir.as_cwd():
-            self._run_install_scripts(str(tmpdir), '"' + self.win32_exe + '"')
-            with open(str(tmpdir.join('foo-script.py')), 'r', encoding="utf-8") as f:
-                actual = f.readline()
-        assert actual == expected
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_logging.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_logging.py
deleted file mode 100644
index ea58001..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_logging.py
+++ /dev/null
@@ -1,76 +0,0 @@
-import functools
-import inspect
-import logging
-import sys
-
-import pytest
-
-IS_PYPY = '__pypy__' in sys.builtin_module_names
-
-
-setup_py = """\
-from setuptools import setup
-
-setup(
-    name="test_logging",
-    version="0.0"
-)
-"""
-
-
-@pytest.mark.parametrize(
-    ('flag', 'expected_level'), [("--dry-run", "INFO"), ("--verbose", "DEBUG")]
-)
-def test_verbosity_level(tmp_path, monkeypatch, flag, expected_level):
-    """Make sure the correct verbosity level is set (issue #3038)"""
-    import setuptools  # noqa: F401  # import setuptools to monkeypatch distutils
-
-    import distutils  # <- load distutils after all the patches take place
-
-    logger = logging.Logger(__name__)
-    monkeypatch.setattr(logging, "root", logger)
-    unset_log_level = logger.getEffectiveLevel()
-    assert logging.getLevelName(unset_log_level) == "NOTSET"
-
-    setup_script = tmp_path / "setup.py"
-    setup_script.write_text(setup_py, encoding="utf-8")
-    dist = distutils.core.run_setup(setup_script, stop_after="init")
-    dist.script_args = [flag, "sdist"]
-    dist.parse_command_line()  # <- where the log level is set
-    log_level = logger.getEffectiveLevel()
-    log_level_name = logging.getLevelName(log_level)
-    assert log_level_name == expected_level
-
-
-def flaky_on_pypy(func):
-    @functools.wraps(func)
-    def _func():
-        try:
-            func()
-        except AssertionError:  # pragma: no cover
-            if IS_PYPY:
-                msg = "Flaky monkeypatch on PyPy (#4124)"
-                pytest.xfail(f"{msg}. Original discussion in #3707, #3709.")
-            raise
-
-    return _func
-
-
-@flaky_on_pypy
-def test_patching_does_not_cause_problems():
-    # Ensure `dist.log` is only patched if necessary
-
-    import _distutils_hack
-
-    import setuptools.logging
-
-    from distutils import dist
-
-    setuptools.logging.configure()
-
-    if _distutils_hack.enabled():
-        # Modern logging infra, no problematic patching.
-        assert dist.__file__ is None or "setuptools" in dist.__file__
-        assert isinstance(dist.log, logging.Logger)
-    else:
-        assert inspect.ismodule(dist.log)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_manifest.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_manifest.py
deleted file mode 100644
index 903a528..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_manifest.py
+++ /dev/null
@@ -1,622 +0,0 @@
-"""sdist tests"""
-
-from __future__ import annotations
-
-import contextlib
-import io
-import itertools
-import logging
-import os
-import shutil
-import sys
-import tempfile
-
-import pytest
-
-from setuptools.command.egg_info import FileList, egg_info, translate_pattern
-from setuptools.dist import Distribution
-from setuptools.tests.textwrap import DALS
-
-from distutils import log
-from distutils.errors import DistutilsTemplateError
-
-IS_PYPY = '__pypy__' in sys.builtin_module_names
-
-
-def make_local_path(s):
-    """Converts '/' in a string to os.sep"""
-    return s.replace('/', os.sep)
-
-
-SETUP_ATTRS = {
-    'name': 'app',
-    'version': '0.0',
-    'packages': ['app'],
-}
-
-SETUP_PY = f"""\
-from setuptools import setup
-
-setup(**{SETUP_ATTRS!r})
-"""
-
-
-@contextlib.contextmanager
-def quiet():
-    old_stdout, old_stderr = sys.stdout, sys.stderr
-    sys.stdout, sys.stderr = io.StringIO(), io.StringIO()
-    try:
-        yield
-    finally:
-        sys.stdout, sys.stderr = old_stdout, old_stderr
-
-
-def touch(filename):
-    open(filename, 'wb').close()
-
-
-# The set of files always in the manifest, including all files in the
-# .egg-info directory
-default_files = frozenset(
-    map(
-        make_local_path,
-        [
-            'README.rst',
-            'MANIFEST.in',
-            'setup.py',
-            'app.egg-info/PKG-INFO',
-            'app.egg-info/SOURCES.txt',
-            'app.egg-info/dependency_links.txt',
-            'app.egg-info/top_level.txt',
-            'app/__init__.py',
-        ],
-    )
-)
-
-
-translate_specs: list[tuple[str, list[str], list[str]]] = [
-    ('foo', ['foo'], ['bar', 'foobar']),
-    ('foo/bar', ['foo/bar'], ['foo/bar/baz', './foo/bar', 'foo']),
-    # Glob matching
-    ('*.txt', ['foo.txt', 'bar.txt'], ['foo/foo.txt']),
-    ('dir/*.txt', ['dir/foo.txt', 'dir/bar.txt', 'dir/.txt'], ['notdir/foo.txt']),
-    ('*/*.py', ['bin/start.py'], []),
-    ('docs/page-?.txt', ['docs/page-9.txt'], ['docs/page-10.txt']),
-    # Globstars change what they mean depending upon where they are
-    (
-        'foo/**/bar',
-        ['foo/bing/bar', 'foo/bing/bang/bar', 'foo/bar'],
-        ['foo/abar'],
-    ),
-    (
-        'foo/**',
-        ['foo/bar/bing.py', 'foo/x'],
-        ['/foo/x'],
-    ),
-    (
-        '**',
-        ['x', 'abc/xyz', '@nything'],
-        [],
-    ),
-    # Character classes
-    (
-        'pre[one]post',
-        ['preopost', 'prenpost', 'preepost'],
-        ['prepost', 'preonepost'],
-    ),
-    (
-        'hello[!one]world',
-        ['helloxworld', 'helloyworld'],
-        ['hellooworld', 'helloworld', 'hellooneworld'],
-    ),
-    (
-        '[]one].txt',
-        ['o.txt', '].txt', 'e.txt'],
-        ['one].txt'],
-    ),
-    (
-        'foo[!]one]bar',
-        ['fooybar'],
-        ['foo]bar', 'fooobar', 'fooebar'],
-    ),
-]
-"""
-A spec of inputs for 'translate_pattern' and matches and mismatches
-for that input.
-"""
-
-match_params = itertools.chain.from_iterable(
-    zip(itertools.repeat(pattern), matches)
-    for pattern, matches, mismatches in translate_specs
-)
-
-
-@pytest.fixture(params=match_params)
-def pattern_match(request):
-    return map(make_local_path, request.param)
-
-
-mismatch_params = itertools.chain.from_iterable(
-    zip(itertools.repeat(pattern), mismatches)
-    for pattern, matches, mismatches in translate_specs
-)
-
-
-@pytest.fixture(params=mismatch_params)
-def pattern_mismatch(request):
-    return map(make_local_path, request.param)
-
-
-def test_translated_pattern_match(pattern_match):
-    pattern, target = pattern_match
-    assert translate_pattern(pattern).match(target)
-
-
-def test_translated_pattern_mismatch(pattern_mismatch):
-    pattern, target = pattern_mismatch
-    assert not translate_pattern(pattern).match(target)
-
-
-class TempDirTestCase:
-    def setup_method(self, method):
-        self.temp_dir = tempfile.mkdtemp()
-        self.old_cwd = os.getcwd()
-        os.chdir(self.temp_dir)
-
-    def teardown_method(self, method):
-        os.chdir(self.old_cwd)
-        shutil.rmtree(self.temp_dir)
-
-
-class TestManifestTest(TempDirTestCase):
-    def setup_method(self, method):
-        super().setup_method(method)
-
-        f = open(os.path.join(self.temp_dir, 'setup.py'), 'w', encoding="utf-8")
-        f.write(SETUP_PY)
-        f.close()
-        """
-        Create a file tree like:
-        - LICENSE
-        - README.rst
-        - testing.rst
-        - .hidden.rst
-        - app/
-            - __init__.py
-            - a.txt
-            - b.txt
-            - c.rst
-            - static/
-                - app.js
-                - app.js.map
-                - app.css
-                - app.css.map
-        """
-
-        for fname in ['README.rst', '.hidden.rst', 'testing.rst', 'LICENSE']:
-            touch(os.path.join(self.temp_dir, fname))
-
-        # Set up the rest of the test package
-        test_pkg = os.path.join(self.temp_dir, 'app')
-        os.mkdir(test_pkg)
-        for fname in ['__init__.py', 'a.txt', 'b.txt', 'c.rst']:
-            touch(os.path.join(test_pkg, fname))
-
-        # Some compiled front-end assets to include
-        static = os.path.join(test_pkg, 'static')
-        os.mkdir(static)
-        for fname in ['app.js', 'app.js.map', 'app.css', 'app.css.map']:
-            touch(os.path.join(static, fname))
-
-    def make_manifest(self, contents):
-        """Write a MANIFEST.in."""
-        manifest = os.path.join(self.temp_dir, 'MANIFEST.in')
-        with open(manifest, 'w', encoding="utf-8") as f:
-            f.write(DALS(contents))
-
-    def get_files(self):
-        """Run egg_info and get all the files to include, as a set"""
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        cmd = egg_info(dist)
-        cmd.ensure_finalized()
-
-        cmd.run()
-
-        return set(cmd.filelist.files)
-
-    def test_no_manifest(self):
-        """Check a missing MANIFEST.in includes only the standard files."""
-        assert (default_files - set(['MANIFEST.in'])) == self.get_files()
-
-    def test_empty_files(self):
-        """Check an empty MANIFEST.in includes only the standard files."""
-        self.make_manifest("")
-        assert default_files == self.get_files()
-
-    def test_include(self):
-        """Include extra rst files in the project root."""
-        self.make_manifest("include *.rst")
-        files = default_files | set(['testing.rst', '.hidden.rst'])
-        assert files == self.get_files()
-
-    def test_exclude(self):
-        """Include everything in app/ except the text files"""
-        ml = make_local_path
-        self.make_manifest(
-            """
-            include app/*
-            exclude app/*.txt
-            """
-        )
-        files = default_files | set([ml('app/c.rst')])
-        assert files == self.get_files()
-
-    def test_include_multiple(self):
-        """Include with multiple patterns."""
-        ml = make_local_path
-        self.make_manifest("include app/*.txt app/static/*")
-        files = default_files | set([
-            ml('app/a.txt'),
-            ml('app/b.txt'),
-            ml('app/static/app.js'),
-            ml('app/static/app.js.map'),
-            ml('app/static/app.css'),
-            ml('app/static/app.css.map'),
-        ])
-        assert files == self.get_files()
-
-    def test_graft(self):
-        """Include the whole app/static/ directory."""
-        ml = make_local_path
-        self.make_manifest("graft app/static")
-        files = default_files | set([
-            ml('app/static/app.js'),
-            ml('app/static/app.js.map'),
-            ml('app/static/app.css'),
-            ml('app/static/app.css.map'),
-        ])
-        assert files == self.get_files()
-
-    def test_graft_glob_syntax(self):
-        """Include the whole app/static/ directory."""
-        ml = make_local_path
-        self.make_manifest("graft */static")
-        files = default_files | set([
-            ml('app/static/app.js'),
-            ml('app/static/app.js.map'),
-            ml('app/static/app.css'),
-            ml('app/static/app.css.map'),
-        ])
-        assert files == self.get_files()
-
-    def test_graft_global_exclude(self):
-        """Exclude all *.map files in the project."""
-        ml = make_local_path
-        self.make_manifest(
-            """
-            graft app/static
-            global-exclude *.map
-            """
-        )
-        files = default_files | set([ml('app/static/app.js'), ml('app/static/app.css')])
-        assert files == self.get_files()
-
-    def test_global_include(self):
-        """Include all *.rst, *.js, and *.css files in the whole tree."""
-        ml = make_local_path
-        self.make_manifest(
-            """
-            global-include *.rst *.js *.css
-            """
-        )
-        files = default_files | set([
-            '.hidden.rst',
-            'testing.rst',
-            ml('app/c.rst'),
-            ml('app/static/app.js'),
-            ml('app/static/app.css'),
-        ])
-        assert files == self.get_files()
-
-    def test_graft_prune(self):
-        """Include all files in app/, except for the whole app/static/ dir."""
-        ml = make_local_path
-        self.make_manifest(
-            """
-            graft app
-            prune app/static
-            """
-        )
-        files = default_files | set([ml('app/a.txt'), ml('app/b.txt'), ml('app/c.rst')])
-        assert files == self.get_files()
-
-
-class TestFileListTest(TempDirTestCase):
-    """
-    A copy of the relevant bits of distutils/tests/test_filelist.py,
-    to ensure setuptools' version of FileList keeps parity with distutils.
-    """
-
-    @pytest.fixture(autouse=os.getenv("SETUPTOOLS_USE_DISTUTILS") == "stdlib")
-    def _compat_record_logs(self, monkeypatch, caplog):
-        """Account for stdlib compatibility"""
-
-        def _log(_logger, level, msg, args):
-            exc = sys.exc_info()
-            rec = logging.LogRecord("distutils", level, "", 0, msg, args, exc)
-            caplog.records.append(rec)
-
-        monkeypatch.setattr(log.Log, "_log", _log)
-
-    def get_records(self, caplog, *levels):
-        return [r for r in caplog.records if r.levelno in levels]
-
-    def assertNoWarnings(self, caplog):
-        assert self.get_records(caplog, log.WARN) == []
-        caplog.clear()
-
-    def assertWarnings(self, caplog):
-        if IS_PYPY and not caplog.records:
-            pytest.xfail("caplog checks may not work well in PyPy")
-        else:
-            assert len(self.get_records(caplog, log.WARN)) > 0
-            caplog.clear()
-
-    def make_files(self, files):
-        for file in files:
-            file = os.path.join(self.temp_dir, file)
-            dirname, _basename = os.path.split(file)
-            os.makedirs(dirname, exist_ok=True)
-            touch(file)
-
-    def test_process_template_line(self):
-        # testing  all MANIFEST.in template patterns
-        file_list = FileList()
-        ml = make_local_path
-
-        # simulated file list
-        self.make_files([
-            'foo.tmp',
-            'ok',
-            'xo',
-            'four.txt',
-            'buildout.cfg',
-            # filelist does not filter out VCS directories,
-            # it's sdist that does
-            ml('.hg/last-message.txt'),
-            ml('global/one.txt'),
-            ml('global/two.txt'),
-            ml('global/files.x'),
-            ml('global/here.tmp'),
-            ml('f/o/f.oo'),
-            ml('dir/graft-one'),
-            ml('dir/dir2/graft2'),
-            ml('dir3/ok'),
-            ml('dir3/sub/ok.txt'),
-        ])
-
-        MANIFEST_IN = DALS(
-            """\
-        include ok
-        include xo
-        exclude xo
-        include foo.tmp
-        include buildout.cfg
-        global-include *.x
-        global-include *.txt
-        global-exclude *.tmp
-        recursive-include f *.oo
-        recursive-exclude global *.x
-        graft dir
-        prune dir3
-        """
-        )
-
-        for line in MANIFEST_IN.split('\n'):
-            if not line:
-                continue
-            file_list.process_template_line(line)
-
-        wanted = [
-            'buildout.cfg',
-            'four.txt',
-            'ok',
-            ml('.hg/last-message.txt'),
-            ml('dir/graft-one'),
-            ml('dir/dir2/graft2'),
-            ml('f/o/f.oo'),
-            ml('global/one.txt'),
-            ml('global/two.txt'),
-        ]
-
-        file_list.sort()
-        assert file_list.files == wanted
-
-    def test_exclude_pattern(self):
-        # return False if no match
-        file_list = FileList()
-        assert not file_list.exclude_pattern('*.py')
-
-        # return True if files match
-        file_list = FileList()
-        file_list.files = ['a.py', 'b.py']
-        assert file_list.exclude_pattern('*.py')
-
-        # test excludes
-        file_list = FileList()
-        file_list.files = ['a.py', 'a.txt']
-        file_list.exclude_pattern('*.py')
-        file_list.sort()
-        assert file_list.files == ['a.txt']
-
-    def test_include_pattern(self):
-        # return False if no match
-        file_list = FileList()
-        self.make_files([])
-        assert not file_list.include_pattern('*.py')
-
-        # return True if files match
-        file_list = FileList()
-        self.make_files(['a.py', 'b.txt'])
-        assert file_list.include_pattern('*.py')
-
-        # test * matches all files
-        file_list = FileList()
-        self.make_files(['a.py', 'b.txt'])
-        file_list.include_pattern('*')
-        file_list.sort()
-        assert file_list.files == ['a.py', 'b.txt']
-
-    def test_process_template_line_invalid(self):
-        # invalid lines
-        file_list = FileList()
-        for action in (
-            'include',
-            'exclude',
-            'global-include',
-            'global-exclude',
-            'recursive-include',
-            'recursive-exclude',
-            'graft',
-            'prune',
-            'blarg',
-        ):
-            with pytest.raises(DistutilsTemplateError):
-                file_list.process_template_line(action)
-
-    def test_include(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # include
-        file_list = FileList()
-        self.make_files(['a.py', 'b.txt', ml('d/c.py')])
-
-        file_list.process_template_line('include *.py')
-        file_list.sort()
-        assert file_list.files == ['a.py']
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('include *.rb')
-        file_list.sort()
-        assert file_list.files == ['a.py']
-        self.assertWarnings(caplog)
-
-    def test_exclude(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # exclude
-        file_list = FileList()
-        file_list.files = ['a.py', 'b.txt', ml('d/c.py')]
-
-        file_list.process_template_line('exclude *.py')
-        file_list.sort()
-        assert file_list.files == ['b.txt', ml('d/c.py')]
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('exclude *.rb')
-        file_list.sort()
-        assert file_list.files == ['b.txt', ml('d/c.py')]
-        self.assertWarnings(caplog)
-
-    def test_global_include(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # global-include
-        file_list = FileList()
-        self.make_files(['a.py', 'b.txt', ml('d/c.py')])
-
-        file_list.process_template_line('global-include *.py')
-        file_list.sort()
-        assert file_list.files == ['a.py', ml('d/c.py')]
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('global-include *.rb')
-        file_list.sort()
-        assert file_list.files == ['a.py', ml('d/c.py')]
-        self.assertWarnings(caplog)
-
-    def test_global_exclude(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # global-exclude
-        file_list = FileList()
-        file_list.files = ['a.py', 'b.txt', ml('d/c.py')]
-
-        file_list.process_template_line('global-exclude *.py')
-        file_list.sort()
-        assert file_list.files == ['b.txt']
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('global-exclude *.rb')
-        file_list.sort()
-        assert file_list.files == ['b.txt']
-        self.assertWarnings(caplog)
-
-    def test_recursive_include(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # recursive-include
-        file_list = FileList()
-        self.make_files(['a.py', ml('d/b.py'), ml('d/c.txt'), ml('d/d/e.py')])
-
-        file_list.process_template_line('recursive-include d *.py')
-        file_list.sort()
-        assert file_list.files == [ml('d/b.py'), ml('d/d/e.py')]
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('recursive-include e *.py')
-        file_list.sort()
-        assert file_list.files == [ml('d/b.py'), ml('d/d/e.py')]
-        self.assertWarnings(caplog)
-
-    def test_recursive_exclude(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # recursive-exclude
-        file_list = FileList()
-        file_list.files = ['a.py', ml('d/b.py'), ml('d/c.txt'), ml('d/d/e.py')]
-
-        file_list.process_template_line('recursive-exclude d *.py')
-        file_list.sort()
-        assert file_list.files == ['a.py', ml('d/c.txt')]
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('recursive-exclude e *.py')
-        file_list.sort()
-        assert file_list.files == ['a.py', ml('d/c.txt')]
-        self.assertWarnings(caplog)
-
-    def test_graft(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # graft
-        file_list = FileList()
-        self.make_files(['a.py', ml('d/b.py'), ml('d/d/e.py'), ml('f/f.py')])
-
-        file_list.process_template_line('graft d')
-        file_list.sort()
-        assert file_list.files == [ml('d/b.py'), ml('d/d/e.py')]
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('graft e')
-        file_list.sort()
-        assert file_list.files == [ml('d/b.py'), ml('d/d/e.py')]
-        self.assertWarnings(caplog)
-
-    def test_prune(self, caplog):
-        caplog.set_level(logging.DEBUG)
-        ml = make_local_path
-        # prune
-        file_list = FileList()
-        file_list.files = ['a.py', ml('d/b.py'), ml('d/d/e.py'), ml('f/f.py')]
-
-        file_list.process_template_line('prune d')
-        file_list.sort()
-        assert file_list.files == ['a.py', ml('f/f.py')]
-        self.assertNoWarnings(caplog)
-
-        file_list.process_template_line('prune e')
-        file_list.sort()
-        assert file_list.files == ['a.py', ml('f/f.py')]
-        self.assertWarnings(caplog)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_namespaces.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_namespaces.py
deleted file mode 100644
index a0f4120..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_namespaces.py
+++ /dev/null
@@ -1,138 +0,0 @@
-import subprocess
-import sys
-
-from setuptools._path import paths_on_pythonpath
-
-from . import namespaces
-
-
-class TestNamespaces:
-    def test_mixed_site_and_non_site(self, tmpdir):
-        """
-        Installing two packages sharing the same namespace, one installed
-        to a site dir and the other installed just to a path on PYTHONPATH
-        should leave the namespace in tact and both packages reachable by
-        import.
-        """
-        pkg_A = namespaces.build_namespace_package(tmpdir, 'myns.pkgA')
-        pkg_B = namespaces.build_namespace_package(tmpdir, 'myns.pkgB')
-        site_packages = tmpdir / 'site-packages'
-        path_packages = tmpdir / 'path-packages'
-        targets = site_packages, path_packages
-        # use pip to install to the target directory
-        install_cmd = [
-            sys.executable,
-            '-m',
-            'pip.__main__',
-            'install',
-            str(pkg_A),
-            '-t',
-            str(site_packages),
-        ]
-        subprocess.check_call(install_cmd)
-        namespaces.make_site_dir(site_packages)
-        install_cmd = [
-            sys.executable,
-            '-m',
-            'pip.__main__',
-            'install',
-            str(pkg_B),
-            '-t',
-            str(path_packages),
-        ]
-        subprocess.check_call(install_cmd)
-        try_import = [
-            sys.executable,
-            '-c',
-            'import myns.pkgA; import myns.pkgB',
-        ]
-        with paths_on_pythonpath(map(str, targets)):
-            subprocess.check_call(try_import)
-
-    def test_pkg_resources_import(self, tmpdir):
-        """
-        Ensure that a namespace package doesn't break on import
-        of pkg_resources.
-        """
-        pkg = namespaces.build_namespace_package(tmpdir, 'myns.pkgA')
-        target = tmpdir / 'packages'
-        target.mkdir()
-        install_cmd = [
-            sys.executable,
-            '-m',
-            'pip',
-            'install',
-            '-t',
-            str(target),
-            str(pkg),
-        ]
-        with paths_on_pythonpath([str(target)]):
-            subprocess.check_call(install_cmd)
-        namespaces.make_site_dir(target)
-        try_import = [
-            sys.executable,
-            '-c',
-            'import pkg_resources',
-        ]
-        with paths_on_pythonpath([str(target)]):
-            subprocess.check_call(try_import)
-
-    def test_namespace_package_installed_and_cwd(self, tmpdir):
-        """
-        Installing a namespace packages but also having it in the current
-        working directory, only one version should take precedence.
-        """
-        pkg_A = namespaces.build_namespace_package(tmpdir, 'myns.pkgA')
-        target = tmpdir / 'packages'
-        # use pip to install to the target directory
-        install_cmd = [
-            sys.executable,
-            '-m',
-            'pip.__main__',
-            'install',
-            str(pkg_A),
-            '-t',
-            str(target),
-        ]
-        subprocess.check_call(install_cmd)
-        namespaces.make_site_dir(target)
-
-        # ensure that package imports and pkg_resources imports
-        pkg_resources_imp = [
-            sys.executable,
-            '-c',
-            'import pkg_resources; import myns.pkgA',
-        ]
-        with paths_on_pythonpath([str(target)]):
-            subprocess.check_call(pkg_resources_imp, cwd=str(pkg_A))
-
-    def test_packages_in_the_same_namespace_installed_and_cwd(self, tmpdir):
-        """
-        Installing one namespace package and also have another in the same
-        namespace in the current working directory, both of them must be
-        importable.
-        """
-        pkg_A = namespaces.build_namespace_package(tmpdir, 'myns.pkgA')
-        pkg_B = namespaces.build_namespace_package(tmpdir, 'myns.pkgB')
-        target = tmpdir / 'packages'
-        # use pip to install to the target directory
-        install_cmd = [
-            sys.executable,
-            '-m',
-            'pip.__main__',
-            'install',
-            str(pkg_A),
-            '-t',
-            str(target),
-        ]
-        subprocess.check_call(install_cmd)
-        namespaces.make_site_dir(target)
-
-        # ensure that all packages import and pkg_resources imports
-        pkg_resources_imp = [
-            sys.executable,
-            '-c',
-            'import pkg_resources; import myns.pkgA; import myns.pkgB',
-        ]
-        with paths_on_pythonpath([str(target)]):
-            subprocess.check_call(pkg_resources_imp, cwd=str(pkg_B))
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_packageindex.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_packageindex.py
deleted file mode 100644
index 2a6e591..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_packageindex.py
+++ /dev/null
@@ -1,267 +0,0 @@
-import http.client
-import re
-import urllib.error
-import urllib.request
-from inspect import cleandoc
-
-import pytest
-
-import setuptools.package_index
-
-import distutils.errors
-
-
-class TestPackageIndex:
-    def test_regex(self):
-        hash_url = 'http://other_url?:action=show_md5&'
-        hash_url += 'digest=0123456789abcdef0123456789abcdef'
-        doc = """
-            Name
-            (md5)
-        """.lstrip().format(**locals())
-        assert setuptools.package_index.PYPI_MD5.match(doc)
-
-    def test_bad_url_bad_port(self):
-        index = setuptools.package_index.PackageIndex()
-        url = 'http://127.0.0.1:0/nonesuch/test_package_index'
-        with pytest.raises(Exception, match=re.escape(url)):
-            v = index.open_url(url)
-            assert isinstance(v, urllib.error.HTTPError)
-
-    def test_bad_url_typo(self):
-        # issue 16
-        # easy_install inquant.contentmirror.plone breaks because of a typo
-        # in its home URL
-        index = setuptools.package_index.PackageIndex(hosts=('www.example.com',))
-
-        url = 'url:%20https://svn.plone.org/svn/collective/inquant.contentmirror.plone/trunk'
-
-        with pytest.raises(Exception, match=re.escape(url)):
-            v = index.open_url(url)
-            assert isinstance(v, urllib.error.HTTPError)
-
-    def test_bad_url_bad_status_line(self):
-        index = setuptools.package_index.PackageIndex(hosts=('www.example.com',))
-
-        def _urlopen(*args):
-            raise http.client.BadStatusLine('line')
-
-        index.opener = _urlopen
-        url = 'http://example.com'
-        with pytest.raises(Exception, match=r'line'):
-            index.open_url(url)
-
-    def test_bad_url_double_scheme(self):
-        """
-        A bad URL with a double scheme should raise a DistutilsError.
-        """
-        index = setuptools.package_index.PackageIndex(hosts=('www.example.com',))
-
-        # issue 20
-        url = 'http://http://svn.pythonpaste.org/Paste/wphp/trunk'
-        try:
-            index.open_url(url)
-        except distutils.errors.DistutilsError as error:
-            msg = str(error)
-            assert (
-                'nonnumeric port' in msg
-                or 'getaddrinfo failed' in msg
-                or 'Name or service not known' in msg
-            )
-            return
-        raise RuntimeError("Did not raise")
-
-    def test_url_ok(self):
-        index = setuptools.package_index.PackageIndex(hosts=('www.example.com',))
-        url = 'file:///tmp/test_package_index'
-        assert index.url_ok(url, True)
-
-    def test_parse_bdist_wininst(self):
-        parse = setuptools.package_index.parse_bdist_wininst
-
-        actual = parse('reportlab-2.5.win32-py2.4.exe')
-        expected = 'reportlab-2.5', '2.4', 'win32'
-        assert actual == expected
-
-        actual = parse('reportlab-2.5.win32.exe')
-        expected = 'reportlab-2.5', None, 'win32'
-        assert actual == expected
-
-        actual = parse('reportlab-2.5.win-amd64-py2.7.exe')
-        expected = 'reportlab-2.5', '2.7', 'win-amd64'
-        assert actual == expected
-
-        actual = parse('reportlab-2.5.win-amd64.exe')
-        expected = 'reportlab-2.5', None, 'win-amd64'
-        assert actual == expected
-
-    def test__vcs_split_rev_from_url(self):
-        """
-        Test the basic usage of _vcs_split_rev_from_url
-        """
-        vsrfu = setuptools.package_index.PackageIndex._vcs_split_rev_from_url
-        url, rev = vsrfu('https://example.com/bar@2995')
-        assert url == 'https://example.com/bar'
-        assert rev == '2995'
-
-    def test_local_index(self, tmpdir):
-        """
-        local_open should be able to read an index from the file system.
-        """
-        index_file = tmpdir / 'index.html'
-        with index_file.open('w') as f:
-            f.write('
content
')
-        url = 'file:' + urllib.request.pathname2url(str(tmpdir)) + '/'
-        res = setuptools.package_index.local_open(url)
-        assert 'content' in res.read()
-
-    def test_egg_fragment(self):
-        """
-        EGG fragments must comply to PEP 440
-        """
-        epoch = [
-            '',
-            '1!',
-        ]
-        releases = [
-            '0',
-            '0.0',
-            '0.0.0',
-        ]
-        pre = [
-            'a0',
-            'b0',
-            'rc0',
-        ]
-        post = ['.post0']
-        dev = [
-            '.dev0',
-        ]
-        local = [
-            ('', ''),
-            ('+ubuntu.0', '+ubuntu.0'),
-            ('+ubuntu-0', '+ubuntu.0'),
-            ('+ubuntu_0', '+ubuntu.0'),
-        ]
-        versions = [
-            [''.join([e, r, p, loc]) for loc in locs]
-            for e in epoch
-            for r in releases
-            for p in sum([pre, post, dev], [''])
-            for locs in local
-        ]
-        for v, vc in versions:
-            dists = list(
-                setuptools.package_index.distros_for_url(
-                    'http://example.com/example-foo.zip#egg=example-foo-' + v
-                )
-            )
-            assert dists[0].version == ''
-            assert dists[1].version == vc
-
-    def test_download_git_with_rev(self, tmp_path, fp):
-        url = 'git+https://github.example/group/project@master#egg=foo'
-        index = setuptools.package_index.PackageIndex()
-
-        expected_dir = tmp_path / 'project@master'
-        fp.register([
-            'git',
-            'clone',
-            '--quiet',
-            'https://github.example/group/project',
-            expected_dir,
-        ])
-        fp.register(['git', '-C', expected_dir, 'checkout', '--quiet', 'master'])
-
-        result = index.download(url, tmp_path)
-
-        assert result == str(expected_dir)
-        assert len(fp.calls) == 2
-
-    def test_download_git_no_rev(self, tmp_path, fp):
-        url = 'git+https://github.example/group/project#egg=foo'
-        index = setuptools.package_index.PackageIndex()
-
-        expected_dir = tmp_path / 'project'
-        fp.register([
-            'git',
-            'clone',
-            '--quiet',
-            'https://github.example/group/project',
-            expected_dir,
-        ])
-        index.download(url, tmp_path)
-
-    def test_download_svn(self, tmp_path):
-        url = 'svn+https://svn.example/project#egg=foo'
-        index = setuptools.package_index.PackageIndex()
-
-        msg = r".*SVN download is not supported.*"
-        with pytest.raises(distutils.errors.DistutilsError, match=msg):
-            index.download(url, tmp_path)
-
-
-class TestContentCheckers:
-    def test_md5(self):
-        checker = setuptools.package_index.HashChecker.from_url(
-            'http://foo/bar#md5=f12895fdffbd45007040d2e44df98478'
-        )
-        checker.feed('You should probably not be using MD5'.encode('ascii'))
-        assert checker.hash.hexdigest() == 'f12895fdffbd45007040d2e44df98478'
-        assert checker.is_valid()
-
-    def test_other_fragment(self):
-        "Content checks should succeed silently if no hash is present"
-        checker = setuptools.package_index.HashChecker.from_url(
-            'http://foo/bar#something%20completely%20different'
-        )
-        checker.feed('anything'.encode('ascii'))
-        assert checker.is_valid()
-
-    def test_blank_md5(self):
-        "Content checks should succeed if a hash is empty"
-        checker = setuptools.package_index.HashChecker.from_url('http://foo/bar#md5=')
-        checker.feed('anything'.encode('ascii'))
-        assert checker.is_valid()
-
-    def test_get_hash_name_md5(self):
-        checker = setuptools.package_index.HashChecker.from_url(
-            'http://foo/bar#md5=f12895fdffbd45007040d2e44df98478'
-        )
-        assert checker.hash_name == 'md5'
-
-    def test_report(self):
-        checker = setuptools.package_index.HashChecker.from_url(
-            'http://foo/bar#md5=f12895fdffbd45007040d2e44df98478'
-        )
-        rep = checker.report(lambda x: x, 'My message about %s')
-        assert rep == 'My message about md5'
-
-
-class TestPyPIConfig:
-    def test_percent_in_password(self, tmp_home_dir):
-        pypirc = tmp_home_dir / '.pypirc'
-        pypirc.write_text(
-            cleandoc(
-                """
-                [pypi]
-                repository=https://pypi.org
-                username=jaraco
-                password=pity%
-                """
-            ),
-            encoding="utf-8",
-        )
-        cfg = setuptools.package_index.PyPIConfig()
-        cred = cfg.creds_by_repository['https://pypi.org']
-        assert cred.username == 'jaraco'
-        assert cred.password == 'pity%'
-
-
-@pytest.mark.timeout(1)
-def test_REL_DoS():
-    """
-    REL should not hang on a contrived attack string.
-    """
-    setuptools.package_index.REL.search('< rel=' + ' ' * 2**12)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_sandbox.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_sandbox.py
deleted file mode 100644
index a476b7c..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_sandbox.py
+++ /dev/null
@@ -1,134 +0,0 @@
-"""develop tests"""
-
-import os
-import types
-
-import pytest
-
-import pkg_resources
-import setuptools.sandbox
-
-
-class TestSandbox:
-    def test_devnull(self, tmpdir):
-        with setuptools.sandbox.DirectorySandbox(str(tmpdir)):
-            self._file_writer(os.devnull)
-
-    @staticmethod
-    def _file_writer(path):
-        def do_write():
-            with open(path, 'w', encoding="utf-8") as f:
-                f.write('xxx')
-
-        return do_write
-
-    def test_setup_py_with_BOM(self):
-        """
-        It should be possible to execute a setup.py with a Byte Order Mark
-        """
-        target = pkg_resources.resource_filename(__name__, 'script-with-bom.py')
-        namespace = types.ModuleType('namespace')
-        setuptools.sandbox._execfile(target, vars(namespace))
-        assert namespace.result == 'passed'
-
-    def test_setup_py_with_CRLF(self, tmpdir):
-        setup_py = tmpdir / 'setup.py'
-        with setup_py.open('wb') as stream:
-            stream.write(b'"degenerate script"\r\n')
-        setuptools.sandbox._execfile(str(setup_py), globals())
-
-
-class TestExceptionSaver:
-    def test_exception_trapped(self):
-        with setuptools.sandbox.ExceptionSaver():
-            raise ValueError("details")
-
-    def test_exception_resumed(self):
-        with setuptools.sandbox.ExceptionSaver() as saved_exc:
-            raise ValueError("details")
-
-        with pytest.raises(ValueError) as caught:
-            saved_exc.resume()
-
-        assert isinstance(caught.value, ValueError)
-        assert str(caught.value) == 'details'
-
-    def test_exception_reconstructed(self):
-        orig_exc = ValueError("details")
-
-        with setuptools.sandbox.ExceptionSaver() as saved_exc:
-            raise orig_exc
-
-        with pytest.raises(ValueError) as caught:
-            saved_exc.resume()
-
-        assert isinstance(caught.value, ValueError)
-        assert caught.value is not orig_exc
-
-    def test_no_exception_passes_quietly(self):
-        with setuptools.sandbox.ExceptionSaver() as saved_exc:
-            pass
-
-        saved_exc.resume()
-
-    def test_unpickleable_exception(self):
-        class CantPickleThis(Exception):
-            "This Exception is unpickleable because it's not in globals"
-
-            def __repr__(self) -> str:
-                return f'CantPickleThis{self.args!r}'
-
-        with setuptools.sandbox.ExceptionSaver() as saved_exc:
-            raise CantPickleThis('detail')
-
-        with pytest.raises(setuptools.sandbox.UnpickleableException) as caught:
-            saved_exc.resume()
-
-        assert str(caught.value) == "CantPickleThis('detail',)"
-
-    def test_unpickleable_exception_when_hiding_setuptools(self):
-        """
-        As revealed in #440, an infinite recursion can occur if an unpickleable
-        exception while setuptools is hidden. Ensure this doesn't happen.
-        """
-
-        class ExceptionUnderTest(Exception):
-            """
-            An unpickleable exception (not in globals).
-            """
-
-        with pytest.raises(setuptools.sandbox.UnpickleableException) as caught:
-            with setuptools.sandbox.save_modules():
-                setuptools.sandbox.hide_setuptools()
-                raise ExceptionUnderTest
-
-        (msg,) = caught.value.args
-        assert msg == 'ExceptionUnderTest()'
-
-    def test_sandbox_violation_raised_hiding_setuptools(self, tmpdir):
-        """
-        When in a sandbox with setuptools hidden, a SandboxViolation
-        should reflect a proper exception and not be wrapped in
-        an UnpickleableException.
-        """
-
-        def write_file():
-            "Trigger a SandboxViolation by writing outside the sandbox"
-            with open('/etc/foo', 'w', encoding="utf-8"):
-                pass
-
-        with pytest.raises(setuptools.sandbox.SandboxViolation) as caught:
-            with setuptools.sandbox.save_modules():
-                setuptools.sandbox.hide_setuptools()
-                with setuptools.sandbox.DirectorySandbox(str(tmpdir)):
-                    write_file()
-
-        cmd, args, kwargs = caught.value.args
-        assert cmd == 'open'
-        assert args == ('/etc/foo', 'w')
-        assert kwargs == {"encoding": "utf-8"}
-
-        msg = str(caught.value)
-        assert 'open' in msg
-        assert "('/etc/foo', 'w')" in msg
-        assert "{'encoding': 'utf-8'}" in msg
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_sdist.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_sdist.py
deleted file mode 100644
index 19d8ddf..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_sdist.py
+++ /dev/null
@@ -1,984 +0,0 @@
-"""sdist tests"""
-
-import contextlib
-import io
-import logging
-import os
-import pathlib
-import sys
-import tarfile
-import tempfile
-import unicodedata
-from inspect import cleandoc
-from pathlib import Path
-from unittest import mock
-
-import jaraco.path
-import pytest
-
-from setuptools import Command, SetuptoolsDeprecationWarning
-from setuptools._importlib import metadata
-from setuptools.command.egg_info import manifest_maker
-from setuptools.command.sdist import sdist
-from setuptools.dist import Distribution
-from setuptools.extension import Extension
-from setuptools.tests import fail_on_ascii
-
-from .text import Filenames
-
-import distutils
-from distutils.core import run_setup
-
-SETUP_ATTRS = {
-    'name': 'sdist_test',
-    'version': '0.0',
-    'packages': ['sdist_test'],
-    'package_data': {'sdist_test': ['*.txt']},
-    'data_files': [("data", [os.path.join("d", "e.dat")])],
-}
-
-SETUP_PY = f"""\
-from setuptools import setup
-
-setup(**{SETUP_ATTRS!r})
-"""
-
-EXTENSION = Extension(
-    name="sdist_test.f",
-    sources=[os.path.join("sdist_test", "f.c")],
-    depends=[os.path.join("sdist_test", "f.h")],
-)
-EXTENSION_SOURCES = EXTENSION.sources + EXTENSION.depends
-
-
-@contextlib.contextmanager
-def quiet():
-    old_stdout, old_stderr = sys.stdout, sys.stderr
-    sys.stdout, sys.stderr = io.StringIO(), io.StringIO()
-    try:
-        yield
-    finally:
-        sys.stdout, sys.stderr = old_stdout, old_stderr
-
-
-# Convert to POSIX path
-def posix(path):
-    if not isinstance(path, str):
-        return path.replace(os.sep.encode('ascii'), b'/')
-    else:
-        return path.replace(os.sep, '/')
-
-
-# HFS Plus uses decomposed UTF-8
-def decompose(path):
-    if isinstance(path, str):
-        return unicodedata.normalize('NFD', path)
-    try:
-        path = path.decode('utf-8')
-        path = unicodedata.normalize('NFD', path)
-        path = path.encode('utf-8')
-    except UnicodeError:
-        pass  # Not UTF-8
-    return path
-
-
-def read_all_bytes(filename):
-    with open(filename, 'rb') as fp:
-        return fp.read()
-
-
-def latin1_fail():
-    try:
-        desc, filename = tempfile.mkstemp(suffix=Filenames.latin_1)
-        os.close(desc)
-        os.remove(filename)
-    except Exception:
-        return True
-
-
-fail_on_latin1_encoded_filenames = pytest.mark.xfail(
-    latin1_fail(),
-    reason="System does not support latin-1 filenames",
-)
-
-
-skip_under_xdist = pytest.mark.skipif(
-    "os.environ.get('PYTEST_XDIST_WORKER')",
-    reason="pytest-dev/pytest-xdist#843",
-)
-skip_under_stdlib_distutils = pytest.mark.skipif(
-    not distutils.__package__.startswith('setuptools'),
-    reason="the test is not supported with stdlib distutils",
-)
-
-
-def touch(path):
-    open(path, 'wb').close()
-    return path
-
-
-def symlink_or_skip_test(src, dst):
-    try:
-        os.symlink(src, dst)
-    except (OSError, NotImplementedError):
-        pytest.skip("symlink not supported in OS")
-        return None
-    return dst
-
-
-class TestSdistTest:
-    @pytest.fixture(autouse=True)
-    def source_dir(self, tmpdir):
-        tmpdir = tmpdir / "project_root"
-        tmpdir.mkdir()
-
-        (tmpdir / 'setup.py').write_text(SETUP_PY, encoding='utf-8')
-
-        # Set up the rest of the test package
-        test_pkg = tmpdir / 'sdist_test'
-        test_pkg.mkdir()
-        data_folder = tmpdir / 'd'
-        data_folder.mkdir()
-        # *.rst was not included in package_data, so c.rst should not be
-        # automatically added to the manifest when not under version control
-        for fname in ['__init__.py', 'a.txt', 'b.txt', 'c.rst']:
-            touch(test_pkg / fname)
-        touch(data_folder / 'e.dat')
-        # C sources are not included by default, but they will be,
-        # if an extension module uses them as sources or depends
-        for fname in EXTENSION_SOURCES:
-            touch(tmpdir / fname)
-
-        with tmpdir.as_cwd():
-            yield tmpdir
-
-    def assert_package_data_in_manifest(self, cmd):
-        manifest = cmd.filelist.files
-        assert os.path.join('sdist_test', 'a.txt') in manifest
-        assert os.path.join('sdist_test', 'b.txt') in manifest
-        assert os.path.join('sdist_test', 'c.rst') not in manifest
-        assert os.path.join('d', 'e.dat') in manifest
-
-    def setup_with_extension(self):
-        setup_attrs = {**SETUP_ATTRS, 'ext_modules': [EXTENSION]}
-
-        dist = Distribution(setup_attrs)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        with quiet():
-            cmd.run()
-
-        return cmd
-
-    def test_package_data_in_sdist(self):
-        """Regression test for pull request #4: ensures that files listed in
-        package_data are included in the manifest even if they're not added to
-        version control.
-        """
-
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        with quiet():
-            cmd.run()
-
-        self.assert_package_data_in_manifest(cmd)
-
-    def test_package_data_and_include_package_data_in_sdist(self):
-        """
-        Ensure package_data and include_package_data work
-        together.
-        """
-        setup_attrs = {**SETUP_ATTRS, 'include_package_data': True}
-        assert setup_attrs['package_data']
-
-        dist = Distribution(setup_attrs)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        with quiet():
-            cmd.run()
-
-        self.assert_package_data_in_manifest(cmd)
-
-    def test_extension_sources_in_sdist(self):
-        """
-        Ensure that the files listed in Extension.sources and Extension.depends
-        are automatically included in the manifest.
-        """
-        cmd = self.setup_with_extension()
-        self.assert_package_data_in_manifest(cmd)
-        manifest = cmd.filelist.files
-        for path in EXTENSION_SOURCES:
-            assert path in manifest
-
-    def test_missing_extension_sources(self):
-        """
-        Similar to test_extension_sources_in_sdist but the referenced files don't exist.
-        Missing files should not be included in distribution (with no error raised).
-        """
-        for path in EXTENSION_SOURCES:
-            os.remove(path)
-
-        cmd = self.setup_with_extension()
-        self.assert_package_data_in_manifest(cmd)
-        manifest = cmd.filelist.files
-        for path in EXTENSION_SOURCES:
-            assert path not in manifest
-
-    def test_symlinked_extension_sources(self):
-        """
-        Similar to test_extension_sources_in_sdist but the referenced files are
-        instead symbolic links to project-local files. Referenced file paths
-        should be included. Symlink targets themselves should NOT be included.
-        """
-        symlinked = []
-        for path in EXTENSION_SOURCES:
-            base, ext = os.path.splitext(path)
-            target = base + "_target." + ext
-
-            os.rename(path, target)
-            symlink_or_skip_test(os.path.basename(target), path)
-            symlinked.append(target)
-
-        cmd = self.setup_with_extension()
-        self.assert_package_data_in_manifest(cmd)
-        manifest = cmd.filelist.files
-        for path in EXTENSION_SOURCES:
-            assert path in manifest
-        for path in symlinked:
-            assert path not in manifest
-
-    _INVALID_PATHS = {
-        "must be relative": lambda: (
-            os.path.abspath(os.path.join("sdist_test", "f.h"))
-        ),
-        "can't have `..` segments": lambda: (
-            os.path.join("sdist_test", "..", "sdist_test", "f.h")
-        ),
-        "doesn't exist": lambda: (
-            os.path.join("sdist_test", "this_file_does_not_exist.h")
-        ),
-        "must be inside the project root": lambda: (
-            symlink_or_skip_test(
-                touch(os.path.join("..", "outside_of_project_root.h")),
-                "symlink.h",
-            )
-        ),
-    }
-
-    @skip_under_stdlib_distutils
-    @pytest.mark.parametrize("reason", _INVALID_PATHS.keys())
-    def test_invalid_extension_depends(self, reason, caplog):
-        """
-        Due to backwards compatibility reasons, `Extension.depends` should accept
-        invalid/weird paths, but then ignore them when building a sdist.
-
-        This test verifies that the source distribution is still built
-        successfully with such paths, but that instead of adding these paths to
-        the manifest, we emit an informational message, notifying the user that
-        the invalid path won't be automatically included.
-        """
-        invalid_path = self._INVALID_PATHS[reason]()
-        extension = Extension(
-            name="sdist_test.f",
-            sources=[],
-            depends=[invalid_path],
-        )
-        setup_attrs = {**SETUP_ATTRS, 'ext_modules': [extension]}
-
-        dist = Distribution(setup_attrs)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        with quiet(), caplog.at_level(logging.INFO):
-            cmd.run()
-
-        self.assert_package_data_in_manifest(cmd)
-        manifest = cmd.filelist.files
-        assert invalid_path not in manifest
-
-        expected_message = [
-            message
-            for (logger, level, message) in caplog.record_tuples
-            if (
-                logger == "root"  #
-                and level == logging.INFO  #
-                and invalid_path in message  #
-            )
-        ]
-        assert len(expected_message) == 1
-        (expected_message,) = expected_message
-        assert reason in expected_message
-
-    def test_custom_build_py(self):
-        """
-        Ensure projects defining custom build_py don't break
-        when creating sdists (issue #2849)
-        """
-        from distutils.command.build_py import build_py as OrigBuildPy
-
-        using_custom_command_guard = mock.Mock()
-
-        class CustomBuildPy(OrigBuildPy):
-            """
-            Some projects have custom commands inheriting from `distutils`
-            """
-
-            def get_data_files(self):
-                using_custom_command_guard()
-                return super().get_data_files()
-
-        setup_attrs = {**SETUP_ATTRS, 'include_package_data': True}
-        assert setup_attrs['package_data']
-
-        dist = Distribution(setup_attrs)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        # Make sure we use the custom command
-        cmd.cmdclass = {'build_py': CustomBuildPy}
-        cmd.distribution.cmdclass = {'build_py': CustomBuildPy}
-        assert cmd.distribution.get_command_class('build_py') == CustomBuildPy
-
-        msg = "setuptools instead of distutils"
-        with quiet(), pytest.warns(SetuptoolsDeprecationWarning, match=msg):
-            cmd.run()
-
-        using_custom_command_guard.assert_called()
-        self.assert_package_data_in_manifest(cmd)
-
-    def test_setup_py_exists(self):
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'foo.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        with quiet():
-            cmd.run()
-
-        manifest = cmd.filelist.files
-        assert 'setup.py' in manifest
-
-    def test_setup_py_missing(self):
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'foo.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        if os.path.exists("setup.py"):
-            os.remove("setup.py")
-        with quiet():
-            cmd.run()
-
-        manifest = cmd.filelist.files
-        assert 'setup.py' not in manifest
-
-    def test_setup_py_excluded(self):
-        with open("MANIFEST.in", "w", encoding="utf-8") as manifest_file:
-            manifest_file.write("exclude setup.py")
-
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'foo.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        with quiet():
-            cmd.run()
-
-        manifest = cmd.filelist.files
-        assert 'setup.py' not in manifest
-
-    def test_defaults_case_sensitivity(self, source_dir):
-        """
-        Make sure default files (README.*, etc.) are added in a case-sensitive
-        way to avoid problems with packages built on Windows.
-        """
-
-        touch(source_dir / 'readme.rst')
-        touch(source_dir / 'SETUP.cfg')
-
-        dist = Distribution(SETUP_ATTRS)
-        # the extension deliberately capitalized for this test
-        # to make sure the actual filename (not capitalized) gets added
-        # to the manifest
-        dist.script_name = 'setup.PY'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        with quiet():
-            cmd.run()
-
-        # lowercase all names so we can test in a
-        # case-insensitive way to make sure the files
-        # are not included.
-        manifest = map(lambda x: x.lower(), cmd.filelist.files)
-        assert 'readme.rst' not in manifest, manifest
-        assert 'setup.py' not in manifest, manifest
-        assert 'setup.cfg' not in manifest, manifest
-
-    def test_exclude_dev_only_cache_folders(self, source_dir):
-        included = {
-            # Emulate problem in https://github.com/pypa/setuptools/issues/4601
-            "MANIFEST.in": (
-                "global-include LICEN[CS]E* COPYING* NOTICE* AUTHORS*\n"
-                "global-include *.txt\n"
-            ),
-            # For the sake of being conservative and limiting unforeseen side-effects
-            # we just exclude dev-only cache folders at the root of the repository:
-            "test/.venv/lib/python3.9/site-packages/bar-2.dist-info/AUTHORS.rst": "",
-            "src/.nox/py/lib/python3.12/site-packages/bar-2.dist-info/COPYING.txt": "",
-            "doc/.tox/default/lib/python3.11/site-packages/foo-4.dist-info/LICENSE": "",
-            # Let's test against false positives with similarly named files:
-            ".venv-requirements.txt": "",
-            ".tox-coveragerc.txt": "",
-            ".noxy/coveragerc.txt": "",
-        }
-
-        excluded = {
-            # .tox/.nox/.venv are well-know folders present at the root of Python repos
-            # and therefore should be excluded
-            ".tox/release/lib/python3.11/site-packages/foo-4.dist-info/LICENSE": "",
-            ".nox/py/lib/python3.12/site-packages/bar-2.dist-info/COPYING.txt": "",
-            ".venv/lib/python3.9/site-packages/bar-2.dist-info/AUTHORS.rst": "",
-        }
-
-        for file, content in {**excluded, **included}.items():
-            Path(source_dir, file).parent.mkdir(parents=True, exist_ok=True)
-            Path(source_dir, file).write_text(content, encoding="utf-8")
-
-        cmd = self.setup_with_extension()
-        self.assert_package_data_in_manifest(cmd)
-        manifest = {f.replace(os.sep, '/') for f in cmd.filelist.files}
-        for path in excluded:
-            assert os.path.exists(path)
-            assert path not in manifest, (path, manifest)
-        for path in included:
-            assert os.path.exists(path)
-            assert path in manifest, (path, manifest)
-
-    @fail_on_ascii
-    def test_manifest_is_written_with_utf8_encoding(self):
-        # Test for #303.
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        mm = manifest_maker(dist)
-        mm.manifest = os.path.join('sdist_test.egg-info', 'SOURCES.txt')
-        os.mkdir('sdist_test.egg-info')
-
-        # UTF-8 filename
-        filename = os.path.join('sdist_test', 'smörbröd.py')
-
-        # Must create the file or it will get stripped.
-        touch(filename)
-
-        # Add UTF-8 filename and write manifest
-        with quiet():
-            mm.run()
-            mm.filelist.append(filename)
-            mm.write_manifest()
-
-        contents = read_all_bytes(mm.manifest)
-
-        # The manifest should be UTF-8 encoded
-        u_contents = contents.decode('UTF-8')
-
-        # The manifest should contain the UTF-8 filename
-        assert posix(filename) in u_contents
-
-    @fail_on_ascii
-    def test_write_manifest_allows_utf8_filenames(self):
-        # Test for #303.
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        mm = manifest_maker(dist)
-        mm.manifest = os.path.join('sdist_test.egg-info', 'SOURCES.txt')
-        os.mkdir('sdist_test.egg-info')
-
-        filename = os.path.join(b'sdist_test', Filenames.utf_8)
-
-        # Must touch the file or risk removal
-        touch(filename)
-
-        # Add filename and write manifest
-        with quiet():
-            mm.run()
-            u_filename = filename.decode('utf-8')
-            mm.filelist.files.append(u_filename)
-            # Re-write manifest
-            mm.write_manifest()
-
-        contents = read_all_bytes(mm.manifest)
-
-        # The manifest should be UTF-8 encoded
-        contents.decode('UTF-8')
-
-        # The manifest should contain the UTF-8 filename
-        assert posix(filename) in contents
-
-        # The filelist should have been updated as well
-        assert u_filename in mm.filelist.files
-
-    @skip_under_xdist
-    def test_write_manifest_skips_non_utf8_filenames(self):
-        """
-        Files that cannot be encoded to UTF-8 (specifically, those that
-        weren't originally successfully decoded and have surrogate
-        escapes) should be omitted from the manifest.
-        See https://bitbucket.org/tarek/distribute/issue/303 for history.
-        """
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        mm = manifest_maker(dist)
-        mm.manifest = os.path.join('sdist_test.egg-info', 'SOURCES.txt')
-        os.mkdir('sdist_test.egg-info')
-
-        # Latin-1 filename
-        filename = os.path.join(b'sdist_test', Filenames.latin_1)
-
-        # Add filename with surrogates and write manifest
-        with quiet():
-            mm.run()
-            u_filename = filename.decode('utf-8', 'surrogateescape')
-            mm.filelist.append(u_filename)
-            # Re-write manifest
-            mm.write_manifest()
-
-        contents = read_all_bytes(mm.manifest)
-
-        # The manifest should be UTF-8 encoded
-        contents.decode('UTF-8')
-
-        # The Latin-1 filename should have been skipped
-        assert posix(filename) not in contents
-
-        # The filelist should have been updated as well
-        assert u_filename not in mm.filelist.files
-
-    @fail_on_ascii
-    def test_manifest_is_read_with_utf8_encoding(self):
-        # Test for #303.
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        # Create manifest
-        with quiet():
-            cmd.run()
-
-        # Add UTF-8 filename to manifest
-        filename = os.path.join(b'sdist_test', Filenames.utf_8)
-        cmd.manifest = os.path.join('sdist_test.egg-info', 'SOURCES.txt')
-        manifest = open(cmd.manifest, 'ab')
-        manifest.write(b'\n' + filename)
-        manifest.close()
-
-        # The file must exist to be included in the filelist
-        touch(filename)
-
-        # Re-read manifest
-        cmd.filelist.files = []
-        with quiet():
-            cmd.read_manifest()
-
-        # The filelist should contain the UTF-8 filename
-        filename = filename.decode('utf-8')
-        assert filename in cmd.filelist.files
-
-    @fail_on_latin1_encoded_filenames
-    def test_read_manifest_skips_non_utf8_filenames(self):
-        # Test for #303.
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        # Create manifest
-        with quiet():
-            cmd.run()
-
-        # Add Latin-1 filename to manifest
-        filename = os.path.join(b'sdist_test', Filenames.latin_1)
-        cmd.manifest = os.path.join('sdist_test.egg-info', 'SOURCES.txt')
-        manifest = open(cmd.manifest, 'ab')
-        manifest.write(b'\n' + filename)
-        manifest.close()
-
-        # The file must exist to be included in the filelist
-        touch(filename)
-
-        # Re-read manifest
-        cmd.filelist.files = []
-        with quiet():
-            cmd.read_manifest()
-
-        # The Latin-1 filename should have been skipped
-        filename = filename.decode('latin-1')
-        assert filename not in cmd.filelist.files
-
-    @fail_on_ascii
-    @fail_on_latin1_encoded_filenames
-    def test_sdist_with_utf8_encoded_filename(self):
-        # Test for #303.
-        dist = Distribution(self.make_strings(SETUP_ATTRS))
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        filename = os.path.join(b'sdist_test', Filenames.utf_8)
-        touch(filename)
-
-        with quiet():
-            cmd.run()
-
-        if sys.platform == 'darwin':
-            filename = decompose(filename)
-
-        fs_enc = sys.getfilesystemencoding()
-
-        if sys.platform == 'win32':
-            if fs_enc == 'cp1252':
-                # Python mangles the UTF-8 filename
-                filename = filename.decode('cp1252')
-                assert filename in cmd.filelist.files
-            else:
-                filename = filename.decode('mbcs')
-                assert filename in cmd.filelist.files
-        else:
-            filename = filename.decode('utf-8')
-            assert filename in cmd.filelist.files
-
-    @classmethod
-    def make_strings(cls, item):
-        if isinstance(item, dict):
-            return {key: cls.make_strings(value) for key, value in item.items()}
-        if isinstance(item, list):
-            return list(map(cls.make_strings, item))
-        return str(item)
-
-    @fail_on_latin1_encoded_filenames
-    @skip_under_xdist
-    def test_sdist_with_latin1_encoded_filename(self):
-        # Test for #303.
-        dist = Distribution(self.make_strings(SETUP_ATTRS))
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-
-        # Latin-1 filename
-        filename = os.path.join(b'sdist_test', Filenames.latin_1)
-        touch(filename)
-        assert os.path.isfile(filename)
-
-        with quiet():
-            cmd.run()
-
-        # not all windows systems have a default FS encoding of cp1252
-        if sys.platform == 'win32':
-            # Latin-1 is similar to Windows-1252 however
-            # on mbcs filesys it is not in latin-1 encoding
-            fs_enc = sys.getfilesystemencoding()
-            if fs_enc != 'mbcs':
-                fs_enc = 'latin-1'
-            filename = filename.decode(fs_enc)
-
-            assert filename in cmd.filelist.files
-        else:
-            # The Latin-1 filename should have been skipped
-            filename = filename.decode('latin-1')
-            assert filename not in cmd.filelist.files
-
-    _EXAMPLE_DIRECTIVES = {
-        "setup.cfg - long_description and version": """
-            [metadata]
-            name = testing
-            version = file: src/VERSION.txt
-            license_files = DOWHATYOUWANT
-            long_description = file: README.rst, USAGE.rst
-            """,
-        "pyproject.toml - static readme/license files and dynamic version": """
-            [project]
-            name = "testing"
-            readme = "USAGE.rst"
-            license-files = ["DOWHATYOUWANT"]
-            dynamic = ["version"]
-            [tool.setuptools.dynamic]
-            version = {file = ["src/VERSION.txt"]}
-            """,
-        "pyproject.toml - directive with str instead of list": """
-            [project]
-            name = "testing"
-            readme = "USAGE.rst"
-            license-files = ["DOWHATYOUWANT"]
-            dynamic = ["version"]
-            [tool.setuptools.dynamic]
-            version = {file = "src/VERSION.txt"}
-            """,
-        "pyproject.toml - deprecated license table with file entry": """
-            [project]
-            name = "testing"
-            readme = "USAGE.rst"
-            license = {file = "DOWHATYOUWANT"}
-            dynamic = ["version"]
-            [tool.setuptools.dynamic]
-            version = {file = "src/VERSION.txt"}
-            """,
-    }
-
-    @pytest.mark.parametrize("config", _EXAMPLE_DIRECTIVES.keys())
-    @pytest.mark.filterwarnings(
-        "ignore:.project.license. as a TOML table is deprecated"
-    )
-    def test_add_files_referenced_by_config_directives(self, source_dir, config):
-        config_file, _, _ = config.partition(" - ")
-        config_text = self._EXAMPLE_DIRECTIVES[config]
-        (source_dir / 'src').mkdir()
-        (source_dir / 'src/VERSION.txt').write_text("0.42", encoding="utf-8")
-        (source_dir / 'README.rst').write_text("hello world!", encoding="utf-8")
-        (source_dir / 'USAGE.rst').write_text("hello world!", encoding="utf-8")
-        (source_dir / 'DOWHATYOUWANT').write_text("hello world!", encoding="utf-8")
-        (source_dir / config_file).write_text(config_text, encoding="utf-8")
-
-        dist = Distribution({"packages": []})
-        dist.script_name = 'setup.py'
-        dist.parse_config_files()
-
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-        with quiet():
-            cmd.run()
-
-        assert (
-            'src/VERSION.txt' in cmd.filelist.files
-            or 'src\\VERSION.txt' in cmd.filelist.files
-        )
-        assert 'USAGE.rst' in cmd.filelist.files
-        assert 'DOWHATYOUWANT' in cmd.filelist.files
-        assert '/' not in cmd.filelist.files
-        assert '\\' not in cmd.filelist.files
-
-    def test_pyproject_toml_in_sdist(self, source_dir):
-        """
-        Check if pyproject.toml is included in source distribution if present
-        """
-        touch(source_dir / 'pyproject.toml')
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-        with quiet():
-            cmd.run()
-        manifest = cmd.filelist.files
-        assert 'pyproject.toml' in manifest
-
-    def test_pyproject_toml_excluded(self, source_dir):
-        """
-        Check that pyproject.toml can excluded even if present
-        """
-        touch(source_dir / 'pyproject.toml')
-        with open('MANIFEST.in', 'w', encoding="utf-8") as mts:
-            print('exclude pyproject.toml', file=mts)
-        dist = Distribution(SETUP_ATTRS)
-        dist.script_name = 'setup.py'
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-        with quiet():
-            cmd.run()
-        manifest = cmd.filelist.files
-        assert 'pyproject.toml' not in manifest
-
-    def test_build_subcommand_source_files(self, source_dir):
-        touch(source_dir / '.myfile~')
-
-        # Sanity check: without custom commands file list should not be affected
-        dist = Distribution({**SETUP_ATTRS, "script_name": "setup.py"})
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-        with quiet():
-            cmd.run()
-        manifest = cmd.filelist.files
-        assert '.myfile~' not in manifest
-
-        # Test: custom command should be able to augment file list
-        dist = Distribution({**SETUP_ATTRS, "script_name": "setup.py"})
-        build = dist.get_command_obj("build")
-        build.sub_commands = [*build.sub_commands, ("build_custom", None)]
-
-        class build_custom(Command):
-            def initialize_options(self): ...
-
-            def finalize_options(self): ...
-
-            def run(self): ...
-
-            def get_source_files(self):
-                return ['.myfile~']
-
-        dist.cmdclass.update(build_custom=build_custom)
-
-        cmd = sdist(dist)
-        cmd.use_defaults = True
-        cmd.ensure_finalized()
-        with quiet():
-            cmd.run()
-        manifest = cmd.filelist.files
-        assert '.myfile~' in manifest
-
-    @pytest.mark.skipif("os.environ.get('SETUPTOOLS_USE_DISTUTILS') == 'stdlib'")
-    def test_build_base_pathlib(self, source_dir):
-        """
-        Ensure if build_base is a pathlib.Path, the build still succeeds.
-        """
-        dist = Distribution({
-            **SETUP_ATTRS,
-            "script_name": "setup.py",
-            "options": {"build": {"build_base": pathlib.Path('build')}},
-        })
-        cmd = sdist(dist)
-        cmd.ensure_finalized()
-        with quiet():
-            cmd.run()
-
-
-def test_default_revctrl():
-    """
-    When _default_revctrl was removed from the `setuptools.command.sdist`
-    module in 10.0, it broke some systems which keep an old install of
-    setuptools (Distribute) around. Those old versions require that the
-    setuptools package continue to implement that interface, so this
-    function provides that interface, stubbed. See #320 for details.
-
-    This interface must be maintained until Ubuntu 12.04 is no longer
-    supported (by Setuptools).
-    """
-    (ep,) = metadata.EntryPoints._from_text(
-        """
-        [setuptools.file_finders]
-        svn_cvs = setuptools.command.sdist:_default_revctrl
-        """
-    )
-    res = ep.load()
-    assert hasattr(res, '__iter__')
-
-
-class TestRegressions:
-    """
-    Can be removed/changed if the project decides to change how it handles symlinks
-    or external files.
-    """
-
-    @staticmethod
-    def files_for_symlink_in_extension_depends(tmp_path, dep_path):
-        return {
-            "external": {
-                "dir": {"file.h": ""},
-            },
-            "project": {
-                "setup.py": cleandoc(
-                    f"""
-                    from setuptools import Extension, setup
-                    setup(
-                        name="myproj",
-                        version="42",
-                        ext_modules=[
-                            Extension(
-                                "hello", sources=["hello.pyx"],
-                                depends=[{dep_path!r}]
-                            )
-                        ],
-                    )
-                    """
-                ),
-                "hello.pyx": "",
-                "MANIFEST.in": "global-include *.h",
-            },
-        }
-
-    @pytest.mark.parametrize(
-        "dep_path", ("myheaders/dir/file.h", "myheaders/dir/../dir/file.h")
-    )
-    def test_symlink_in_extension_depends(self, monkeypatch, tmp_path, dep_path):
-        # Given a project with a symlinked dir and a "depends" targeting that dir
-        files = self.files_for_symlink_in_extension_depends(tmp_path, dep_path)
-        jaraco.path.build(files, prefix=str(tmp_path))
-        symlink_or_skip_test(tmp_path / "external", tmp_path / "project/myheaders")
-
-        # When `sdist` runs, there should be no error
-        members = run_sdist(monkeypatch, tmp_path / "project")
-        # and the sdist should contain the symlinked files
-        for expected in (
-            "myproj-42/hello.pyx",
-            "myproj-42/myheaders/dir/file.h",
-        ):
-            assert expected in members
-
-    @staticmethod
-    def files_for_external_path_in_extension_depends(tmp_path, dep_path):
-        head, _, tail = dep_path.partition("$tmp_path$/")
-        dep_path = tmp_path / tail if tail else head
-
-        return {
-            "external": {
-                "dir": {"file.h": ""},
-            },
-            "project": {
-                "setup.py": cleandoc(
-                    f"""
-                    from setuptools import Extension, setup
-                    setup(
-                        name="myproj",
-                        version="42",
-                        ext_modules=[
-                            Extension(
-                                "hello", sources=["hello.pyx"],
-                                depends=[{str(dep_path)!r}]
-                            )
-                        ],
-                    )
-                    """
-                ),
-                "hello.pyx": "",
-                "MANIFEST.in": "global-include *.h",
-            },
-        }
-
-    @pytest.mark.parametrize(
-        "dep_path", ("$tmp_path$/external/dir/file.h", "../external/dir/file.h")
-    )
-    def test_external_path_in_extension_depends(self, monkeypatch, tmp_path, dep_path):
-        # Given a project with a "depends" targeting an external dir
-        files = self.files_for_external_path_in_extension_depends(tmp_path, dep_path)
-        jaraco.path.build(files, prefix=str(tmp_path))
-        # When `sdist` runs, there should be no error
-        members = run_sdist(monkeypatch, tmp_path / "project")
-        # and the sdist should not contain the external file
-        for name in members:
-            assert "file.h" not in name
-
-
-def run_sdist(monkeypatch, project):
-    """Given a project directory, run the sdist and return its contents"""
-    monkeypatch.chdir(project)
-    with quiet():
-        run_setup("setup.py", ["sdist"])
-
-    archive = next((project / "dist").glob("*.tar.gz"))
-    with tarfile.open(str(archive)) as tar:
-        return set(tar.getnames())
-
-
-def test_sanity_check_setuptools_own_sdist(setuptools_sdist):
-    with tarfile.open(setuptools_sdist) as tar:
-        files = tar.getnames()
-
-    # setuptools sdist should not include the .tox folder
-    tox_files = [name for name in files if ".tox" in name]
-    assert len(tox_files) == 0, f"not empty {tox_files}"
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_setopt.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_setopt.py
deleted file mode 100644
index ccf2561..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_setopt.py
+++ /dev/null
@@ -1,40 +0,0 @@
-import configparser
-
-from setuptools.command import setopt
-
-
-class TestEdit:
-    @staticmethod
-    def parse_config(filename):
-        parser = configparser.ConfigParser()
-        with open(filename, encoding='utf-8') as reader:
-            parser.read_file(reader)
-        return parser
-
-    @staticmethod
-    def write_text(file, content):
-        with open(file, 'wb') as strm:
-            strm.write(content.encode('utf-8'))
-
-    def test_utf8_encoding_retained(self, tmpdir):
-        """
-        When editing a file, non-ASCII characters encoded in
-        UTF-8 should be retained.
-        """
-        config = tmpdir.join('setup.cfg')
-        self.write_text(str(config), '[names]\njaraco=джарако')
-        setopt.edit_config(str(config), dict(names=dict(other='yes')))
-        parser = self.parse_config(str(config))
-        assert parser.get('names', 'jaraco') == 'джарако'
-        assert parser.get('names', 'other') == 'yes'
-
-    def test_case_retained(self, tmpdir):
-        """
-        When editing a file, case of keys should be retained.
-        """
-        config = tmpdir.join('setup.cfg')
-        self.write_text(str(config), '[names]\nFoO=bAr')
-        setopt.edit_config(str(config), dict(names=dict(oTher='yes')))
-        actual = config.read_text(encoding='ascii')
-        assert 'FoO' in actual
-        assert 'oTher' in actual
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_setuptools.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_setuptools.py
deleted file mode 100644
index 1d56e1a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_setuptools.py
+++ /dev/null
@@ -1,290 +0,0 @@
-"""Tests for the 'setuptools' package"""
-
-import os
-import re
-import sys
-from zipfile import ZipFile
-
-import pytest
-from packaging.version import Version
-
-import setuptools
-import setuptools.depends as dep
-import setuptools.dist
-from setuptools.depends import Require
-
-import distutils.cmd
-import distutils.core
-from distutils.core import Extension
-from distutils.errors import DistutilsSetupError
-
-
-@pytest.fixture(autouse=True)
-def isolated_dir(tmpdir_cwd):
-    return
-
-
-def makeSetup(**args):
-    """Return distribution from 'setup(**args)', without executing commands"""
-
-    distutils.core._setup_stop_after = "commandline"
-
-    # Don't let system command line leak into tests!
-    args.setdefault('script_args', ['install'])
-
-    try:
-        return setuptools.setup(**args)
-    finally:
-        distutils.core._setup_stop_after = None
-
-
-needs_bytecode = pytest.mark.skipif(
-    not hasattr(dep, 'get_module_constant'),
-    reason="bytecode support not available",
-)
-
-
-class TestDepends:
-    def testExtractConst(self):
-        if not hasattr(dep, 'extract_constant'):
-            # skip on non-bytecode platforms
-            return
-
-        def f1():
-            global x, y, z
-            x = "test"
-            y = z  # pyright: ignore[reportUnboundVariable] # Explicitly testing for this runtime issue
-
-        fc = f1.__code__
-
-        # unrecognized name
-        assert dep.extract_constant(fc, 'q', -1) is None
-
-        # constant assigned
-        assert dep.extract_constant(fc, 'x', -1) == "test"
-
-        # expression assigned
-        assert dep.extract_constant(fc, 'y', -1) == -1
-
-        # recognized name, not assigned
-        assert dep.extract_constant(fc, 'z', -1) is None
-
-    def testFindModule(self):
-        with pytest.raises(ImportError):
-            dep.find_module('no-such.-thing')
-        with pytest.raises(ImportError):
-            dep.find_module('setuptools.non-existent')
-        f, _p, _i = dep.find_module('setuptools.tests')
-        f.close()
-
-    @needs_bytecode
-    def testModuleExtract(self):
-        from json import __version__
-
-        assert dep.get_module_constant('json', '__version__') == __version__
-        assert dep.get_module_constant('sys', 'version') == sys.version
-        assert (
-            dep.get_module_constant('setuptools.tests.test_setuptools', '__doc__')
-            == __doc__
-        )
-
-    @needs_bytecode
-    def testRequire(self):
-        req = Require('Json', '1.0.3', 'json')
-
-        assert req.name == 'Json'
-        assert req.module == 'json'
-        assert req.requested_version == Version('1.0.3')
-        assert req.attribute == '__version__'
-        assert req.full_name() == 'Json-1.0.3'
-
-        from json import __version__
-
-        assert str(req.get_version()) == __version__
-        assert req.version_ok('1.0.9')
-        assert not req.version_ok('0.9.1')
-        assert not req.version_ok('unknown')
-
-        assert req.is_present()
-        assert req.is_current()
-
-        req = Require('Do-what-I-mean', '1.0', 'd-w-i-m')
-        assert not req.is_present()
-        assert not req.is_current()
-
-    @needs_bytecode
-    def test_require_present(self):
-        # In #1896, this test was failing for months with the only
-        # complaint coming from test runners (not end users).
-        # TODO: Evaluate if this code is needed at all.
-        req = Require('Tests', None, 'tests', homepage="http://example.com")
-        assert req.format is None
-        assert req.attribute is None
-        assert req.requested_version is None
-        assert req.full_name() == 'Tests'
-        assert req.homepage == 'http://example.com'
-
-        from setuptools.tests import __path__
-
-        paths = [os.path.dirname(p) for p in __path__]
-        assert req.is_present(paths)
-        assert req.is_current(paths)
-
-
-class TestDistro:
-    def setup_method(self, method):
-        self.e1 = Extension('bar.ext', ['bar.c'])
-        self.e2 = Extension('c.y', ['y.c'])
-
-        self.dist = makeSetup(
-            packages=['a', 'a.b', 'a.b.c', 'b', 'c'],
-            py_modules=['b.d', 'x'],
-            ext_modules=(self.e1, self.e2),
-            package_dir={},
-        )
-
-    def testDistroType(self):
-        assert isinstance(self.dist, setuptools.dist.Distribution)
-
-    def testExcludePackage(self):
-        self.dist.exclude_package('a')
-        assert self.dist.packages == ['b', 'c']
-
-        self.dist.exclude_package('b')
-        assert self.dist.packages == ['c']
-        assert self.dist.py_modules == ['x']
-        assert self.dist.ext_modules == [self.e1, self.e2]
-
-        self.dist.exclude_package('c')
-        assert self.dist.packages == []
-        assert self.dist.py_modules == ['x']
-        assert self.dist.ext_modules == [self.e1]
-
-        # test removals from unspecified options
-        makeSetup().exclude_package('x')
-
-    def testIncludeExclude(self):
-        # remove an extension
-        self.dist.exclude(ext_modules=[self.e1])
-        assert self.dist.ext_modules == [self.e2]
-
-        # add it back in
-        self.dist.include(ext_modules=[self.e1])
-        assert self.dist.ext_modules == [self.e2, self.e1]
-
-        # should not add duplicate
-        self.dist.include(ext_modules=[self.e1])
-        assert self.dist.ext_modules == [self.e2, self.e1]
-
-    def testExcludePackages(self):
-        self.dist.exclude(packages=['c', 'b', 'a'])
-        assert self.dist.packages == []
-        assert self.dist.py_modules == ['x']
-        assert self.dist.ext_modules == [self.e1]
-
-    def testEmpty(self):
-        dist = makeSetup()
-        dist.include(packages=['a'], py_modules=['b'], ext_modules=[self.e2])
-        dist = makeSetup()
-        dist.exclude(packages=['a'], py_modules=['b'], ext_modules=[self.e2])
-
-    def testContents(self):
-        assert self.dist.has_contents_for('a')
-        self.dist.exclude_package('a')
-        assert not self.dist.has_contents_for('a')
-
-        assert self.dist.has_contents_for('b')
-        self.dist.exclude_package('b')
-        assert not self.dist.has_contents_for('b')
-
-        assert self.dist.has_contents_for('c')
-        self.dist.exclude_package('c')
-        assert not self.dist.has_contents_for('c')
-
-    def testInvalidIncludeExclude(self):
-        with pytest.raises(DistutilsSetupError):
-            self.dist.include(nonexistent_option='x')
-        with pytest.raises(DistutilsSetupError):
-            self.dist.exclude(nonexistent_option='x')
-        with pytest.raises(DistutilsSetupError):
-            self.dist.include(packages={'x': 'y'})
-        with pytest.raises(DistutilsSetupError):
-            self.dist.exclude(packages={'x': 'y'})
-        with pytest.raises(DistutilsSetupError):
-            self.dist.include(ext_modules={'x': 'y'})
-        with pytest.raises(DistutilsSetupError):
-            self.dist.exclude(ext_modules={'x': 'y'})
-
-        with pytest.raises(DistutilsSetupError):
-            self.dist.include(package_dir=['q'])
-        with pytest.raises(DistutilsSetupError):
-            self.dist.exclude(package_dir=['q'])
-
-
-@pytest.fixture
-def example_source(tmpdir):
-    tmpdir.mkdir('foo')
-    (tmpdir / 'foo/bar.py').write('')
-    (tmpdir / 'readme.txt').write('')
-    return tmpdir
-
-
-def test_findall(example_source):
-    found = list(setuptools.findall(str(example_source)))
-    expected = ['readme.txt', 'foo/bar.py']
-    expected = [example_source.join(fn) for fn in expected]
-    assert found == expected
-
-
-def test_findall_curdir(example_source):
-    with example_source.as_cwd():
-        found = list(setuptools.findall())
-    expected = ['readme.txt', os.path.join('foo', 'bar.py')]
-    assert found == expected
-
-
-@pytest.fixture
-def can_symlink(tmpdir):
-    """
-    Skip if cannot create a symbolic link
-    """
-    link_fn = 'link'
-    target_fn = 'target'
-    try:
-        os.symlink(target_fn, link_fn)
-    except (OSError, NotImplementedError, AttributeError):
-        pytest.skip("Cannot create symbolic links")
-    os.remove(link_fn)
-
-
-@pytest.mark.usefixtures("can_symlink")
-def test_findall_missing_symlink(tmpdir):
-    with tmpdir.as_cwd():
-        os.symlink('foo', 'bar')
-        found = list(setuptools.findall())
-        assert found == []
-
-
-@pytest.mark.xfail(reason="unable to exclude tests; #4475 #3260")
-def test_its_own_wheel_does_not_contain_tests(setuptools_wheel):
-    with ZipFile(setuptools_wheel) as zipfile:
-        contents = [f.replace(os.sep, '/') for f in zipfile.namelist()]
-
-    for member in contents:
-        assert '/tests/' not in member
-
-
-def test_wheel_includes_cli_scripts(setuptools_wheel):
-    with ZipFile(setuptools_wheel) as zipfile:
-        contents = [f.replace(os.sep, '/') for f in zipfile.namelist()]
-
-    assert any('cli-64.exe' in member for member in contents)
-
-
-def test_wheel_includes_vendored_metadata(setuptools_wheel):
-    with ZipFile(setuptools_wheel) as zipfile:
-        contents = [f.replace(os.sep, '/') for f in zipfile.namelist()]
-
-    assert any(
-        re.search(r'_vendor/.*\.dist-info/METADATA', member) for member in contents
-    )
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_shutil_wrapper.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_shutil_wrapper.py
deleted file mode 100644
index 74ff7e9..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_shutil_wrapper.py
+++ /dev/null
@@ -1,23 +0,0 @@
-import stat
-import sys
-from unittest.mock import Mock
-
-from setuptools import _shutil
-
-
-def test_rmtree_readonly(monkeypatch, tmp_path):
-    """Verify onerr works as expected"""
-
-    tmp_dir = tmp_path / "with_readonly"
-    tmp_dir.mkdir()
-    some_file = tmp_dir.joinpath("file.txt")
-    some_file.touch()
-    some_file.chmod(stat.S_IREAD)
-
-    expected_count = 1 if sys.platform.startswith("win") else 0
-    chmod_fn = Mock(wraps=_shutil.attempt_chmod_verbose)
-    monkeypatch.setattr(_shutil, "attempt_chmod_verbose", chmod_fn)
-
-    _shutil.rmtree(tmp_dir)
-    assert chmod_fn.call_count == expected_count
-    assert not tmp_dir.is_dir()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_unicode_utils.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_unicode_utils.py
deleted file mode 100644
index a24a9bd..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_unicode_utils.py
+++ /dev/null
@@ -1,10 +0,0 @@
-from setuptools import unicode_utils
-
-
-def test_filesys_decode_fs_encoding_is_None(monkeypatch):
-    """
-    Test filesys_decode does not raise TypeError when
-    getfilesystemencoding returns None.
-    """
-    monkeypatch.setattr('sys.getfilesystemencoding', lambda: None)
-    unicode_utils.filesys_decode(b'test')
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_virtualenv.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_virtualenv.py
deleted file mode 100644
index b02949b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_virtualenv.py
+++ /dev/null
@@ -1,113 +0,0 @@
-import os
-import subprocess
-import sys
-from urllib.error import URLError
-from urllib.request import urlopen
-
-import pytest
-
-
-@pytest.fixture(autouse=True)
-def pytest_virtualenv_works(venv):
-    """
-    pytest_virtualenv may not work. if it doesn't, skip these
-    tests. See #1284.
-    """
-    venv_prefix = venv.run(["python", "-c", "import sys; print(sys.prefix)"]).strip()
-    if venv_prefix == sys.prefix:
-        pytest.skip("virtualenv is broken (see pypa/setuptools#1284)")
-
-
-def test_clean_env_install(venv_without_setuptools, setuptools_wheel):
-    """
-    Check setuptools can be installed in a clean environment.
-    """
-    cmd = ["python", "-m", "pip", "install", str(setuptools_wheel)]
-    venv_without_setuptools.run(cmd)
-
-
-def access_pypi():
-    # Detect if tests are being run without connectivity
-    if not os.environ.get('NETWORK_REQUIRED', False):  # pragma: nocover
-        try:
-            urlopen('https://pypi.org', timeout=1)
-        except URLError:
-            # No network, disable most of these tests
-            return False
-
-    return True
-
-
-@pytest.mark.skipif(
-    'platform.python_implementation() == "PyPy"',
-    reason="https://github.com/pypa/setuptools/pull/2865#issuecomment-965834995",
-)
-@pytest.mark.skipif(not access_pypi(), reason="no network")
-# ^-- Even when it is not necessary to install a different version of `pip`
-#     the build process will still try to download `wheel`, see #3147 and #2986.
-@pytest.mark.parametrize(
-    'pip_version',
-    [
-        None,
-        pytest.param(
-            'pip<20.1',
-            marks=pytest.mark.xfail(
-                'sys.version_info >= (3, 12)',
-                reason="pip 23.1.2 required for Python 3.12 and later",
-            ),
-        ),
-        pytest.param(
-            'pip<21',
-            marks=pytest.mark.xfail(
-                'sys.version_info >= (3, 12)',
-                reason="pip 23.1.2 required for Python 3.12 and later",
-            ),
-        ),
-        pytest.param(
-            'pip<22',
-            marks=pytest.mark.xfail(
-                'sys.version_info >= (3, 12)',
-                reason="pip 23.1.2 required for Python 3.12 and later",
-            ),
-        ),
-        pytest.param(
-            'pip<23',
-            marks=pytest.mark.xfail(
-                'sys.version_info >= (3, 12)',
-                reason="pip 23.1.2 required for Python 3.12 and later",
-            ),
-        ),
-        pytest.param(
-            'https://github.com/pypa/pip/archive/main.zip',
-            marks=pytest.mark.xfail(reason='#2975'),
-        ),
-    ],
-)
-def test_pip_upgrade_from_source(
-    pip_version, venv_without_setuptools, setuptools_wheel, setuptools_sdist
-):
-    """
-    Check pip can upgrade setuptools from source.
-    """
-    # Install pip/wheel, in a venv without setuptools (as it
-    # should not be needed for bootstrapping from source)
-    venv = venv_without_setuptools
-    venv.run(["pip", "install", "-U", "wheel"])
-    if pip_version is not None:
-        venv.run(["python", "-m", "pip", "install", "-U", pip_version, "--retries=1"])
-    with pytest.raises(subprocess.CalledProcessError):
-        # Meta-test to make sure setuptools is not installed
-        venv.run(["python", "-c", "import setuptools"])
-
-    # Then install from wheel.
-    venv.run(["pip", "install", str(setuptools_wheel)])
-    # And finally try to upgrade from source.
-    venv.run(["pip", "install", "--no-cache-dir", "--upgrade", str(setuptools_sdist)])
-
-
-def test_no_missing_dependencies(bare_venv, request):
-    """
-    Quick and dirty test to ensure all external dependencies are vendored.
-    """
-    setuptools_dir = request.config.rootdir
-    bare_venv.run(['python', 'setup.py', '--help'], cwd=setuptools_dir)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_warnings.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_warnings.py
deleted file mode 100644
index 41193d4..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_warnings.py
+++ /dev/null
@@ -1,106 +0,0 @@
-from inspect import cleandoc
-
-import pytest
-
-from setuptools.warnings import SetuptoolsDeprecationWarning, SetuptoolsWarning
-
-_EXAMPLES = {
-    "default": dict(
-        args=("Hello {x}", "\n\t{target} {v:.1f}"),
-        kwargs={"x": 5, "v": 3, "target": "World"},
-        expected="""
-    Hello 5
-    !!
-
-            ********************************************************************************
-            World 3.0
-            ********************************************************************************
-
-    !!
-    """,
-    ),
-    "futue_due_date": dict(
-        args=("Summary", "Lorem ipsum"),
-        kwargs={"due_date": (9999, 11, 22)},
-        expected="""
-    Summary
-    !!
-
-            ********************************************************************************
-            Lorem ipsum
-
-            By 9999-Nov-22, you need to update your project and remove deprecated calls
-            or your builds will no longer be supported.
-            ********************************************************************************
-
-    !!
-    """,
-    ),
-    "past_due_date_with_docs": dict(
-        args=("Summary", "Lorem ipsum"),
-        kwargs={"due_date": (2000, 11, 22), "see_docs": "some_page.html"},
-        expected="""
-    Summary
-    !!
-
-            ********************************************************************************
-            Lorem ipsum
-
-            This deprecation is overdue, please update your project and remove deprecated
-            calls to avoid build errors in the future.
-
-            See https://setuptools.pypa.io/en/latest/some_page.html for details.
-            ********************************************************************************
-
-    !!
-    """,
-    ),
-}
-
-
-@pytest.mark.parametrize("example_name", _EXAMPLES.keys())
-def test_formatting(monkeypatch, example_name):
-    """
-    It should automatically handle indentation, interpolation and things like due date.
-    """
-    args = _EXAMPLES[example_name]["args"]
-    kwargs = _EXAMPLES[example_name]["kwargs"]
-    expected = _EXAMPLES[example_name]["expected"]
-
-    monkeypatch.setenv("SETUPTOOLS_ENFORCE_DEPRECATION", "false")
-    with pytest.warns(SetuptoolsWarning) as warn_info:
-        SetuptoolsWarning.emit(*args, **kwargs)
-    assert _get_message(warn_info) == cleandoc(expected)
-
-
-def test_due_date_enforcement(monkeypatch):
-    class _MyDeprecation(SetuptoolsDeprecationWarning):
-        _SUMMARY = "Summary"
-        _DETAILS = "Lorem ipsum"
-        _DUE_DATE = (2000, 11, 22)
-        _SEE_DOCS = "some_page.html"
-
-    monkeypatch.setenv("SETUPTOOLS_ENFORCE_DEPRECATION", "true")
-    with pytest.raises(SetuptoolsDeprecationWarning) as exc_info:
-        _MyDeprecation.emit()
-
-    expected = """
-    Summary
-    !!
-
-            ********************************************************************************
-            Lorem ipsum
-
-            This deprecation is overdue, please update your project and remove deprecated
-            calls to avoid build errors in the future.
-
-            See https://setuptools.pypa.io/en/latest/some_page.html for details.
-            ********************************************************************************
-
-    !!
-    """
-    assert str(exc_info.value) == cleandoc(expected)
-
-
-def _get_message(warn_info):
-    return next(warn.message.args[0] for warn in warn_info)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_wheel.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_wheel.py
deleted file mode 100644
index 70165c6..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_wheel.py
+++ /dev/null
@@ -1,714 +0,0 @@
-"""wheel tests"""
-
-from __future__ import annotations
-
-import contextlib
-import glob
-import inspect
-import os
-import pathlib
-import shutil
-import stat
-import subprocess
-import sys
-import zipfile
-from typing import Any
-
-import pytest
-from jaraco import path
-from packaging.tags import parse_tag
-from packaging.utils import canonicalize_name
-
-from pkg_resources import PY_MAJOR, Distribution, PathMetadata
-from setuptools.wheel import Wheel
-
-from .contexts import tempdir
-from .textwrap import DALS
-
-from distutils.sysconfig import get_config_var
-from distutils.util import get_platform
-
-WHEEL_INFO_TESTS = (
-    ('invalid.whl', ValueError),
-    (
-        'simplewheel-2.0-1-py2.py3-none-any.whl',
-        {
-            'project_name': 'simplewheel',
-            'version': '2.0',
-            'build': '1',
-            'py_version': 'py2.py3',
-            'abi': 'none',
-            'platform': 'any',
-        },
-    ),
-    (
-        'simple.dist-0.1-py2.py3-none-any.whl',
-        {
-            'project_name': 'simple.dist',
-            'version': '0.1',
-            'build': None,
-            'py_version': 'py2.py3',
-            'abi': 'none',
-            'platform': 'any',
-        },
-    ),
-    (
-        'example_pkg_a-1-py3-none-any.whl',
-        {
-            'project_name': 'example_pkg_a',
-            'version': '1',
-            'build': None,
-            'py_version': 'py3',
-            'abi': 'none',
-            'platform': 'any',
-        },
-    ),
-    (
-        'PyQt5-5.9-5.9.1-cp35.cp36.cp37-abi3-manylinux1_x86_64.whl',
-        {
-            'project_name': 'PyQt5',
-            'version': '5.9',
-            'build': '5.9.1',
-            'py_version': 'cp35.cp36.cp37',
-            'abi': 'abi3',
-            'platform': 'manylinux1_x86_64',
-        },
-    ),
-)
-
-
-@pytest.mark.parametrize(
-    ('filename', 'info'), WHEEL_INFO_TESTS, ids=[t[0] for t in WHEEL_INFO_TESTS]
-)
-def test_wheel_info(filename, info):
-    if inspect.isclass(info):
-        with pytest.raises(info):
-            Wheel(filename)
-        return
-    w = Wheel(filename)
-    assert {k: getattr(w, k) for k in info.keys()} == info
-
-
-@contextlib.contextmanager
-def build_wheel(extra_file_defs=None, **kwargs):
-    file_defs = {
-        'setup.py': (
-            DALS(
-                """
-            # -*- coding: utf-8 -*-
-            from setuptools import setup
-            import setuptools
-            setup(**%r)
-            """
-            )
-            % kwargs
-        ).encode('utf-8'),
-    }
-    if extra_file_defs:
-        file_defs.update(extra_file_defs)
-    with tempdir() as source_dir:
-        path.build(file_defs, source_dir)
-        subprocess.check_call(
-            (sys.executable, 'setup.py', '-q', 'bdist_wheel'), cwd=source_dir
-        )
-        yield glob.glob(os.path.join(source_dir, 'dist', '*.whl'))[0]
-
-
-def tree_set(root):
-    contents = set()
-    for dirpath, dirnames, filenames in os.walk(root):
-        for filename in filenames:
-            contents.add(os.path.join(os.path.relpath(dirpath, root), filename))
-    return contents
-
-
-def flatten_tree(tree):
-    """Flatten nested dicts and lists into a full list of paths"""
-    output = set()
-    for node, contents in tree.items():
-        if isinstance(contents, dict):
-            contents = flatten_tree(contents)
-
-        for elem in contents:
-            if isinstance(elem, dict):
-                output |= {os.path.join(node, val) for val in flatten_tree(elem)}
-            else:
-                output.add(os.path.join(node, elem))
-    return output
-
-
-def format_install_tree(tree):
-    return {
-        x.format(
-            py_version=PY_MAJOR,
-            platform=get_platform(),
-            shlib_ext=get_config_var('EXT_SUFFIX') or get_config_var('SO'),
-        )
-        for x in tree
-    }
-
-
-def _check_wheel_install(
-    filename, install_dir, install_tree_includes, project_name, version, requires_txt
-):
-    w = Wheel(filename)
-    egg_path = os.path.join(install_dir, w.egg_name())
-    w.install_as_egg(egg_path)
-    if install_tree_includes is not None:
-        install_tree = format_install_tree(install_tree_includes)
-        exp = tree_set(install_dir)
-        assert install_tree.issubset(exp), install_tree - exp
-
-    metadata = PathMetadata(egg_path, os.path.join(egg_path, 'EGG-INFO'))
-    dist = Distribution.from_filename(egg_path, metadata=metadata)
-    assert dist.project_name == project_name
-    assert dist.version == version
-    if requires_txt is None:
-        assert not dist.has_metadata('requires.txt')
-    else:
-        # Order must match to ensure reproducibility.
-        assert requires_txt == dist.get_metadata('requires.txt').lstrip()
-
-
-class Record:
-    def __init__(self, id, **kwargs):
-        self._id = id
-        self._fields = kwargs
-
-    def __repr__(self) -> str:
-        return f'{self._id}(**{self._fields!r})'
-
-
-# Using Any to avoid possible type union issues later in test
-# making a TypedDict is not worth in a test and anonymous/inline TypedDict are experimental
-# https://github.com/python/mypy/issues/9884
-WHEEL_INSTALL_TESTS: tuple[dict[str, Any], ...] = (
-    dict(
-        id='basic',
-        file_defs={'foo': {'__init__.py': ''}},
-        setup_kwargs=dict(
-            packages=['foo'],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': {
-                'EGG-INFO': ['PKG-INFO', 'RECORD', 'WHEEL', 'top_level.txt'],
-                'foo': ['__init__.py'],
-            }
-        }),
-    ),
-    dict(
-        id='utf-8',
-        setup_kwargs=dict(
-            description='Description accentuée',
-        ),
-    ),
-    dict(
-        id='data',
-        file_defs={
-            'data.txt': DALS(
-                """
-                Some data...
-                """
-            ),
-        },
-        setup_kwargs=dict(
-            data_files=[('data_dir', ['data.txt'])],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': {
-                'EGG-INFO': ['PKG-INFO', 'RECORD', 'WHEEL', 'top_level.txt'],
-                'data_dir': ['data.txt'],
-            }
-        }),
-    ),
-    dict(
-        id='extension',
-        file_defs={
-            'extension.c': DALS(
-                """
-                #include "Python.h"
-
-                #if PY_MAJOR_VERSION >= 3
-
-                static struct PyModuleDef moduledef = {
-                        PyModuleDef_HEAD_INIT,
-                        "extension",
-                        NULL,
-                        0,
-                        NULL,
-                        NULL,
-                        NULL,
-                        NULL,
-                        NULL
-                };
-
-                #define INITERROR return NULL
-
-                PyMODINIT_FUNC PyInit_extension(void)
-
-                #else
-
-                #define INITERROR return
-
-                void initextension(void)
-
-                #endif
-                {
-                #if PY_MAJOR_VERSION >= 3
-                    PyObject *module = PyModule_Create(&moduledef);
-                #else
-                    PyObject *module = Py_InitModule("extension", NULL);
-                #endif
-                    if (module == NULL)
-                        INITERROR;
-                #if PY_MAJOR_VERSION >= 3
-                    return module;
-                #endif
-                }
-                """
-            ),
-        },
-        setup_kwargs=dict(
-            ext_modules=[
-                Record(
-                    'setuptools.Extension', name='extension', sources=['extension.c']
-                )
-            ],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}-{platform}.egg': [
-                'extension{shlib_ext}',
-                {
-                    'EGG-INFO': [
-                        'PKG-INFO',
-                        'RECORD',
-                        'WHEEL',
-                        'top_level.txt',
-                    ]
-                },
-            ]
-        }),
-    ),
-    dict(
-        id='header',
-        file_defs={
-            'header.h': DALS(
-                """
-                """
-            ),
-        },
-        setup_kwargs=dict(
-            headers=['header.h'],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': [
-                'header.h',
-                {
-                    'EGG-INFO': [
-                        'PKG-INFO',
-                        'RECORD',
-                        'WHEEL',
-                        'top_level.txt',
-                    ]
-                },
-            ]
-        }),
-    ),
-    dict(
-        id='script',
-        file_defs={
-            'script.py': DALS(
-                """
-                #/usr/bin/python
-                print('hello world!')
-                """
-            ),
-            'script.sh': DALS(
-                """
-                #/bin/sh
-                echo 'hello world!'
-                """
-            ),
-        },
-        setup_kwargs=dict(
-            scripts=['script.py', 'script.sh'],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': {
-                'EGG-INFO': [
-                    'PKG-INFO',
-                    'RECORD',
-                    'WHEEL',
-                    'top_level.txt',
-                    {'scripts': ['script.py', 'script.sh']},
-                ]
-            }
-        }),
-    ),
-    dict(
-        id='requires1',
-        install_requires='foobar==2.0',
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': {
-                'EGG-INFO': [
-                    'PKG-INFO',
-                    'RECORD',
-                    'WHEEL',
-                    'requires.txt',
-                    'top_level.txt',
-                ]
-            }
-        }),
-        requires_txt=DALS(
-            """
-            foobar==2.0
-            """
-        ),
-    ),
-    dict(
-        id='requires2',
-        install_requires=f"""
-        bar
-        foo<=2.0; {sys.platform!r} in sys_platform
-        """,
-        requires_txt=DALS(
-            """
-            bar
-            foo<=2.0
-            """
-        ),
-    ),
-    dict(
-        id='requires3',
-        install_requires=f"""
-        bar; {sys.platform!r} != sys_platform
-        """,
-    ),
-    dict(
-        id='requires4',
-        install_requires="""
-        foo
-        """,
-        extras_require={
-            'extra': 'foobar>3',
-        },
-        requires_txt=DALS(
-            """
-            foo
-
-            [extra]
-            foobar>3
-            """
-        ),
-    ),
-    dict(
-        id='requires5',
-        extras_require={
-            'extra': f'foobar; {sys.platform!r} != sys_platform',
-        },
-        requires_txt=DALS(
-            """
-            [extra]
-            """
-        ),
-    ),
-    dict(
-        id='requires_ensure_order',
-        install_requires="""
-        foo
-        bar
-        baz
-        qux
-        """,
-        extras_require={
-            'extra': """
-            foobar>3
-            barbaz>4
-            bazqux>5
-            quxzap>6
-            """,
-        },
-        requires_txt=DALS(
-            """
-            foo
-            bar
-            baz
-            qux
-
-            [extra]
-            foobar>3
-            barbaz>4
-            bazqux>5
-            quxzap>6
-            """
-        ),
-    ),
-    dict(
-        id='namespace_package',
-        file_defs={
-            'foo': {
-                'bar': {'__init__.py': ''},
-            },
-        },
-        setup_kwargs=dict(
-            namespace_packages=['foo'],
-            packages=['foo.bar'],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': [
-                'foo-1.0-py{py_version}-nspkg.pth',
-                {
-                    'EGG-INFO': [
-                        'PKG-INFO',
-                        'RECORD',
-                        'WHEEL',
-                        'namespace_packages.txt',
-                        'top_level.txt',
-                    ]
-                },
-                {
-                    'foo': [
-                        '__init__.py',
-                        {'bar': ['__init__.py']},
-                    ]
-                },
-            ]
-        }),
-    ),
-    dict(
-        id='empty_namespace_package',
-        file_defs={
-            'foobar': {
-                '__init__.py': (
-                    "__import__('pkg_resources').declare_namespace(__name__)"
-                )
-            },
-        },
-        setup_kwargs=dict(
-            namespace_packages=['foobar'],
-            packages=['foobar'],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': [
-                'foo-1.0-py{py_version}-nspkg.pth',
-                {
-                    'EGG-INFO': [
-                        'PKG-INFO',
-                        'RECORD',
-                        'WHEEL',
-                        'namespace_packages.txt',
-                        'top_level.txt',
-                    ]
-                },
-                {
-                    'foobar': [
-                        '__init__.py',
-                    ]
-                },
-            ]
-        }),
-    ),
-    dict(
-        id='data_in_package',
-        file_defs={
-            'foo': {
-                '__init__.py': '',
-                'data_dir': {
-                    'data.txt': DALS(
-                        """
-                        Some data...
-                        """
-                    ),
-                },
-            }
-        },
-        setup_kwargs=dict(
-            packages=['foo'],
-            data_files=[('foo/data_dir', ['foo/data_dir/data.txt'])],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': {
-                'EGG-INFO': [
-                    'PKG-INFO',
-                    'RECORD',
-                    'WHEEL',
-                    'top_level.txt',
-                ],
-                'foo': [
-                    '__init__.py',
-                    {
-                        'data_dir': [
-                            'data.txt',
-                        ]
-                    },
-                ],
-            }
-        }),
-    ),
-)
-
-
-@pytest.mark.parametrize(
-    'params',
-    WHEEL_INSTALL_TESTS,
-    ids=[params['id'] for params in WHEEL_INSTALL_TESTS],
-)
-def test_wheel_install(params):
-    project_name = params.get('name', 'foo')
-    version = params.get('version', '1.0')
-    install_requires = params.get('install_requires', [])
-    extras_require = params.get('extras_require', {})
-    requires_txt = params.get('requires_txt', None)
-    install_tree = params.get('install_tree')
-    file_defs = params.get('file_defs', {})
-    setup_kwargs = params.get('setup_kwargs', {})
-    with (
-        build_wheel(
-            name=project_name,
-            version=version,
-            install_requires=install_requires,
-            extras_require=extras_require,
-            extra_file_defs=file_defs,
-            **setup_kwargs,
-        ) as filename,
-        tempdir() as install_dir,
-    ):
-        _check_wheel_install(
-            filename, install_dir, install_tree, project_name, version, requires_txt
-        )
-
-
-def test_wheel_install_pep_503():
-    project_name = 'Foo_Bar'  # PEP 503 canonicalized name is "foo-bar"
-    version = '1.0'
-    with (
-        build_wheel(
-            name=project_name,
-            version=version,
-        ) as filename,
-        tempdir() as install_dir,
-    ):
-        new_filename = filename.replace(project_name, canonicalize_name(project_name))
-        shutil.move(filename, new_filename)
-        _check_wheel_install(
-            new_filename,
-            install_dir,
-            None,
-            canonicalize_name(project_name),
-            version,
-            None,
-        )
-
-
-def test_wheel_no_dist_dir():
-    project_name = 'nodistinfo'
-    version = '1.0'
-    wheel_name = f'{project_name}-{version}-py2.py3-none-any.whl'
-    with tempdir() as source_dir:
-        wheel_path = os.path.join(source_dir, wheel_name)
-        # create an empty zip file
-        zipfile.ZipFile(wheel_path, 'w').close()
-        with tempdir() as install_dir:
-            with pytest.raises(ValueError):
-                _check_wheel_install(
-                    wheel_path, install_dir, None, project_name, version, None
-                )
-
-
-def test_wheel_is_compatible(monkeypatch):
-    def sys_tags():
-        return {
-            (t.interpreter, t.abi, t.platform)
-            for t in parse_tag('cp36-cp36m-manylinux1_x86_64')
-        }
-
-    monkeypatch.setattr('setuptools.wheel._get_supported_tags', sys_tags)
-    assert Wheel('onnxruntime-0.1.2-cp36-cp36m-manylinux1_x86_64.whl').is_compatible()
-
-
-def test_wheel_mode():
-    @contextlib.contextmanager
-    def build_wheel(extra_file_defs=None, **kwargs):
-        file_defs = {
-            'setup.py': (
-                DALS(
-                    """
-                # -*- coding: utf-8 -*-
-                from setuptools import setup
-                import setuptools
-                setup(**%r)
-                """
-                )
-                % kwargs
-            ).encode('utf-8'),
-        }
-        if extra_file_defs:
-            file_defs.update(extra_file_defs)
-        with tempdir() as source_dir:
-            path.build(file_defs, source_dir)
-            runsh = pathlib.Path(source_dir) / "script.sh"
-            os.chmod(runsh, 0o777)
-            subprocess.check_call(
-                (sys.executable, 'setup.py', '-q', 'bdist_wheel'), cwd=source_dir
-            )
-            yield glob.glob(os.path.join(source_dir, 'dist', '*.whl'))[0]
-
-    params = dict(
-        id='script',
-        file_defs={
-            'script.py': DALS(
-                """
-                #/usr/bin/python
-                print('hello world!')
-                """
-            ),
-            'script.sh': DALS(
-                """
-                #/bin/sh
-                echo 'hello world!'
-                """
-            ),
-        },
-        setup_kwargs=dict(
-            scripts=['script.py', 'script.sh'],
-        ),
-        install_tree=flatten_tree({
-            'foo-1.0-py{py_version}.egg': {
-                'EGG-INFO': [
-                    'PKG-INFO',
-                    'RECORD',
-                    'WHEEL',
-                    'top_level.txt',
-                    {'scripts': ['script.py', 'script.sh']},
-                ]
-            }
-        }),
-    )
-
-    project_name = params.get('name', 'foo')
-    version = params.get('version', '1.0')
-    install_tree = params.get('install_tree')
-    file_defs = params.get('file_defs', {})
-    setup_kwargs = params.get('setup_kwargs', {})
-
-    with (
-        build_wheel(
-            name=project_name,
-            version=version,
-            install_requires=[],
-            extras_require={},
-            extra_file_defs=file_defs,
-            **setup_kwargs,
-        ) as filename,
-        tempdir() as install_dir,
-    ):
-        _check_wheel_install(
-            filename, install_dir, install_tree, project_name, version, None
-        )
-        w = Wheel(filename)
-        base = pathlib.Path(install_dir) / w.egg_name()
-        script_sh = base / "EGG-INFO" / "scripts" / "script.sh"
-        assert script_sh.exists()
-        if sys.platform != 'win32':
-            # Editable file mode has no effect on Windows
-            assert oct(stat.S_IMODE(script_sh.stat().st_mode)) == "0o777"
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_windows_wrappers.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/test_windows_wrappers.py
deleted file mode 100644
index f895485..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/test_windows_wrappers.py
+++ /dev/null
@@ -1,259 +0,0 @@
-"""
-Python Script Wrapper for Windows
-=================================
-
-setuptools includes wrappers for Python scripts that allows them to be
-executed like regular windows programs.  There are 2 wrappers, one
-for command-line programs, cli.exe, and one for graphical programs,
-gui.exe.  These programs are almost identical, function pretty much
-the same way, and are generated from the same source file.  The
-wrapper programs are used by copying them to the directory containing
-the script they are to wrap and with the same name as the script they
-are to wrap.
-"""
-
-import pathlib
-import platform
-import subprocess
-import sys
-import textwrap
-
-import pytest
-
-import pkg_resources
-from setuptools.command.easy_install import nt_quote_arg
-
-pytestmark = pytest.mark.skipif(sys.platform != 'win32', reason="Windows only")
-
-
-class WrapperTester:
-    @classmethod
-    def prep_script(cls, template):
-        python_exe = nt_quote_arg(sys.executable)
-        return template % locals()
-
-    @classmethod
-    def create_script(cls, tmpdir):
-        """
-        Create a simple script, foo-script.py
-
-        Note that the script starts with a Unix-style '#!' line saying which
-        Python executable to run.  The wrapper will use this line to find the
-        correct Python executable.
-        """
-
-        script = cls.prep_script(cls.script_tmpl)
-
-        with (tmpdir / cls.script_name).open('w') as f:
-            f.write(script)
-
-        # also copy cli.exe to the sample directory
-        with (tmpdir / cls.wrapper_name).open('wb') as f:
-            w = pkg_resources.resource_string('setuptools', cls.wrapper_source)
-            f.write(w)
-
-
-def win_launcher_exe(prefix):
-    """A simple routine to select launcher script based on platform."""
-    assert prefix in ('cli', 'gui')
-    if platform.machine() == "ARM64":
-        return f"{prefix}-arm64.exe"
-    else:
-        return f"{prefix}-32.exe"
-
-
-class TestCLI(WrapperTester):
-    script_name = 'foo-script.py'
-    wrapper_name = 'foo.exe'
-    wrapper_source = win_launcher_exe('cli')
-
-    script_tmpl = textwrap.dedent(
-        """
-        #!%(python_exe)s
-        import sys
-        input = repr(sys.stdin.read())
-        print(sys.argv[0][-14:])
-        print(sys.argv[1:])
-        print(input)
-        if __debug__:
-            print('non-optimized')
-        """
-    ).lstrip()
-
-    def test_basic(self, tmpdir):
-        """
-        When the copy of cli.exe, foo.exe in this example, runs, it examines
-        the path name it was run with and computes a Python script path name
-        by removing the '.exe' suffix and adding the '-script.py' suffix. (For
-        GUI programs, the suffix '-script.pyw' is added.)  This is why we
-        named out script the way we did.  Now we can run out script by running
-        the wrapper:
-
-        This example was a little pathological in that it exercised windows
-        (MS C runtime) quoting rules:
-
-        - Strings containing spaces are surrounded by double quotes.
-
-        - Double quotes in strings need to be escaped by preceding them with
-          back slashes.
-
-        - One or more backslashes preceding double quotes need to be escaped
-          by preceding each of them with back slashes.
-        """
-        self.create_script(tmpdir)
-        cmd = [
-            str(tmpdir / 'foo.exe'),
-            'arg1',
-            'arg 2',
-            'arg "2\\"',
-            'arg 4\\',
-            'arg5 a\\\\b',
-        ]
-        proc = subprocess.Popen(
-            cmd,
-            stdout=subprocess.PIPE,
-            stdin=subprocess.PIPE,
-            text=True,
-            encoding="utf-8",
-        )
-        stdout, _stderr = proc.communicate('hello\nworld\n')
-        actual = stdout.replace('\r\n', '\n')
-        expected = textwrap.dedent(
-            r"""
-            \foo-script.py
-            ['arg1', 'arg 2', 'arg "2\\"', 'arg 4\\', 'arg5 a\\\\b']
-            'hello\nworld\n'
-            non-optimized
-            """
-        ).lstrip()
-        assert actual == expected
-
-    def test_symlink(self, tmpdir):
-        """
-        Ensure that symlink for the foo.exe is working correctly.
-        """
-        script_dir = tmpdir / "script_dir"
-        script_dir.mkdir()
-        self.create_script(script_dir)
-        symlink = pathlib.Path(tmpdir / "foo.exe")
-        symlink.symlink_to(script_dir / "foo.exe")
-
-        cmd = [
-            str(tmpdir / 'foo.exe'),
-            'arg1',
-            'arg 2',
-            'arg "2\\"',
-            'arg 4\\',
-            'arg5 a\\\\b',
-        ]
-        proc = subprocess.Popen(
-            cmd,
-            stdout=subprocess.PIPE,
-            stdin=subprocess.PIPE,
-            text=True,
-            encoding="utf-8",
-        )
-        stdout, _stderr = proc.communicate('hello\nworld\n')
-        actual = stdout.replace('\r\n', '\n')
-        expected = textwrap.dedent(
-            r"""
-            \foo-script.py
-            ['arg1', 'arg 2', 'arg "2\\"', 'arg 4\\', 'arg5 a\\\\b']
-            'hello\nworld\n'
-            non-optimized
-            """
-        ).lstrip()
-        assert actual == expected
-
-    def test_with_options(self, tmpdir):
-        """
-        Specifying Python Command-line Options
-        --------------------------------------
-
-        You can specify a single argument on the '#!' line.  This can be used
-        to specify Python options like -O, to run in optimized mode or -i
-        to start the interactive interpreter.  You can combine multiple
-        options as usual. For example, to run in optimized mode and
-        enter the interpreter after running the script, you could use -Oi:
-        """
-        self.create_script(tmpdir)
-        tmpl = textwrap.dedent(
-            """
-            #!%(python_exe)s  -Oi
-            import sys
-            input = repr(sys.stdin.read())
-            print(sys.argv[0][-14:])
-            print(sys.argv[1:])
-            print(input)
-            if __debug__:
-                print('non-optimized')
-            sys.ps1 = '---'
-            """
-        ).lstrip()
-        with (tmpdir / 'foo-script.py').open('w') as f:
-            f.write(self.prep_script(tmpl))
-        cmd = [str(tmpdir / 'foo.exe')]
-        proc = subprocess.Popen(
-            cmd,
-            stdout=subprocess.PIPE,
-            stdin=subprocess.PIPE,
-            stderr=subprocess.STDOUT,
-            text=True,
-            encoding="utf-8",
-        )
-        stdout, _stderr = proc.communicate()
-        actual = stdout.replace('\r\n', '\n')
-        expected = textwrap.dedent(
-            r"""
-            \foo-script.py
-            []
-            ''
-            ---
-            """
-        ).lstrip()
-        assert actual == expected
-
-
-class TestGUI(WrapperTester):
-    """
-    Testing the GUI Version
-    -----------------------
-    """
-
-    script_name = 'bar-script.pyw'
-    wrapper_source = win_launcher_exe('gui')
-    wrapper_name = 'bar.exe'
-
-    script_tmpl = textwrap.dedent(
-        """
-        #!%(python_exe)s
-        import sys
-        f = open(sys.argv[1], 'wb')
-        bytes_written = f.write(repr(sys.argv[2]).encode('utf-8'))
-        f.close()
-        """
-    ).strip()
-
-    def test_basic(self, tmpdir):
-        """Test the GUI version with the simple script, bar-script.py"""
-        self.create_script(tmpdir)
-
-        cmd = [
-            str(tmpdir / 'bar.exe'),
-            str(tmpdir / 'test_output.txt'),
-            'Test Argument',
-        ]
-        proc = subprocess.Popen(
-            cmd,
-            stdout=subprocess.PIPE,
-            stdin=subprocess.PIPE,
-            stderr=subprocess.STDOUT,
-            text=True,
-            encoding="utf-8",
-        )
-        stdout, stderr = proc.communicate()
-        assert not stdout
-        assert not stderr
-        with (tmpdir / 'test_output.txt').open('rb') as f_out:
-            actual = f_out.read().decode('ascii')
-        assert actual == repr('Test Argument')
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/text.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/text.py
deleted file mode 100644
index e05cc63..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/text.py
+++ /dev/null
@@ -1,4 +0,0 @@
-class Filenames:
-    unicode = 'smörbröd.py'
-    latin_1 = unicode.encode('latin-1')
-    utf_8 = unicode.encode('utf-8')
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/tests/textwrap.py b/llmlab/lib/python3.12/site-packages/setuptools/tests/textwrap.py
deleted file mode 100644
index 5e39618..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/tests/textwrap.py
+++ /dev/null
@@ -1,6 +0,0 @@
-import textwrap
-
-
-def DALS(s):
-    "dedent and left-strip"
-    return textwrap.dedent(s).lstrip()
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/unicode_utils.py b/llmlab/lib/python3.12/site-packages/setuptools/unicode_utils.py
deleted file mode 100644
index f502f5b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/unicode_utils.py
+++ /dev/null
@@ -1,102 +0,0 @@
-import sys
-import unicodedata
-from configparser import RawConfigParser
-
-from .compat import py39
-from .warnings import SetuptoolsDeprecationWarning
-
-
-# HFS Plus uses decomposed UTF-8
-def decompose(path):
-    if isinstance(path, str):
-        return unicodedata.normalize('NFD', path)
-    try:
-        path = path.decode('utf-8')
-        path = unicodedata.normalize('NFD', path)
-        path = path.encode('utf-8')
-    except UnicodeError:
-        pass  # Not UTF-8
-    return path
-
-
-def filesys_decode(path):
-    """
-    Ensure that the given path is decoded,
-    ``None`` when no expected encoding works
-    """
-
-    if isinstance(path, str):
-        return path
-
-    fs_enc = sys.getfilesystemencoding() or 'utf-8'
-    candidates = fs_enc, 'utf-8'
-
-    for enc in candidates:
-        try:
-            return path.decode(enc)
-        except UnicodeDecodeError:
-            continue
-
-    return None
-
-
-def try_encode(string, enc):
-    "turn unicode encoding into a functional routine"
-    try:
-        return string.encode(enc)
-    except UnicodeEncodeError:
-        return None
-
-
-def _read_utf8_with_fallback(file: str, fallback_encoding=py39.LOCALE_ENCODING) -> str:
-    """
-    First try to read the file with UTF-8, if there is an error fallback to a
-    different encoding ("locale" by default). Returns the content of the file.
-    Also useful when reading files that might have been produced by an older version of
-    setuptools.
-    """
-    try:
-        with open(file, "r", encoding="utf-8") as f:
-            return f.read()
-    except UnicodeDecodeError:  # pragma: no cover
-        _Utf8EncodingNeeded.emit(file=file, fallback_encoding=fallback_encoding)
-        with open(file, "r", encoding=fallback_encoding) as f:
-            return f.read()
-
-
-def _cfg_read_utf8_with_fallback(
-    cfg: RawConfigParser, file: str, fallback_encoding=py39.LOCALE_ENCODING
-) -> None:
-    """Same idea as :func:`_read_utf8_with_fallback`, but for the
-    :meth:`RawConfigParser.read` method.
-
-    This method may call ``cfg.clear()``.
-    """
-    try:
-        cfg.read(file, encoding="utf-8")
-    except UnicodeDecodeError:  # pragma: no cover
-        _Utf8EncodingNeeded.emit(file=file, fallback_encoding=fallback_encoding)
-        cfg.clear()
-        cfg.read(file, encoding=fallback_encoding)
-
-
-class _Utf8EncodingNeeded(SetuptoolsDeprecationWarning):
-    _SUMMARY = """
-    `encoding="utf-8"` fails with {file!r}, trying `encoding={fallback_encoding!r}`.
-    """
-
-    _DETAILS = """
-    Fallback behavior for UTF-8 is considered **deprecated** and future versions of
-    `setuptools` may not implement it.
-
-    Please encode {file!r} with "utf-8" to ensure future builds will succeed.
-
-    If this file was produced by `setuptools` itself, cleaning up the cached files
-    and re-building/re-installing the package with a newer version of `setuptools`
-    (e.g. by updating `build-system.requires` in its `pyproject.toml`)
-    might solve the problem.
-    """
-    # TODO: Add a deadline?
-    #       Will we be able to remove this?
-    #       The question comes to mind mainly because of sdists that have been produced
-    #       by old versions of setuptools and published to PyPI...
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/version.py b/llmlab/lib/python3.12/site-packages/setuptools/version.py
deleted file mode 100644
index ec253c4..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/version.py
+++ /dev/null
@@ -1,6 +0,0 @@
-from ._importlib import metadata
-
-try:
-    __version__ = metadata.version('setuptools') or '0.dev0+unknown'
-except Exception:
-    __version__ = '0.dev0+unknown'
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/warnings.py b/llmlab/lib/python3.12/site-packages/setuptools/warnings.py
deleted file mode 100644
index 9646778..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/warnings.py
+++ /dev/null
@@ -1,110 +0,0 @@
-"""Provide basic warnings used by setuptools modules.
-
-Using custom classes (other than ``UserWarning``) allow users to set
-``PYTHONWARNINGS`` filters to run tests and prepare for upcoming changes in
-setuptools.
-"""
-
-from __future__ import annotations
-
-import os
-import warnings
-from datetime import date
-from inspect import cleandoc
-from textwrap import indent
-from typing import TYPE_CHECKING
-
-if TYPE_CHECKING:
-    from typing_extensions import TypeAlias
-
-_DueDate: TypeAlias = tuple[int, int, int]  # time tuple
-_INDENT = 8 * " "
-_TEMPLATE = f"""{80 * '*'}\n{{details}}\n{80 * '*'}"""
-
-
-class SetuptoolsWarning(UserWarning):
-    """Base class in ``setuptools`` warning hierarchy."""
-
-    @classmethod
-    def emit(
-        cls,
-        summary: str | None = None,
-        details: str | None = None,
-        due_date: _DueDate | None = None,
-        see_docs: str | None = None,
-        see_url: str | None = None,
-        stacklevel: int = 2,
-        **kwargs,
-    ) -> None:
-        """Private: reserved for ``setuptools`` internal use only"""
-        # Default values:
-        summary_ = summary or getattr(cls, "_SUMMARY", None) or ""
-        details_ = details or getattr(cls, "_DETAILS", None) or ""
-        due_date = due_date or getattr(cls, "_DUE_DATE", None)
-        docs_ref = see_docs or getattr(cls, "_SEE_DOCS", None)
-        docs_url = docs_ref and f"https://setuptools.pypa.io/en/latest/{docs_ref}"
-        see_url = see_url or getattr(cls, "_SEE_URL", None)
-        due = date(*due_date) if due_date else None
-
-        text = cls._format(summary_, details_, due, see_url or docs_url, kwargs)
-        if due and due < date.today() and _should_enforce():
-            raise cls(text)
-        warnings.warn(text, cls, stacklevel=stacklevel + 1)
-
-    @classmethod
-    def _format(
-        cls,
-        summary: str,
-        details: str,
-        due_date: date | None = None,
-        see_url: str | None = None,
-        format_args: dict | None = None,
-    ) -> str:
-        """Private: reserved for ``setuptools`` internal use only"""
-        today = date.today()
-        summary = cleandoc(summary).format_map(format_args or {})
-        possible_parts = [
-            cleandoc(details).format_map(format_args or {}),
-            (
-                f"\nBy {due_date:%Y-%b-%d}, you need to update your project and remove "
-                "deprecated calls\nor your builds will no longer be supported."
-                if due_date and due_date > today
-                else None
-            ),
-            (
-                "\nThis deprecation is overdue, please update your project and remove "
-                "deprecated\ncalls to avoid build errors in the future."
-                if due_date and due_date < today
-                else None
-            ),
-            (f"\nSee {see_url} for details." if see_url else None),
-        ]
-        parts = [x for x in possible_parts if x]
-        if parts:
-            body = indent(_TEMPLATE.format(details="\n".join(parts)), _INDENT)
-            return "\n".join([summary, "!!\n", body, "\n!!"])
-        return summary
-
-
-class InformationOnly(SetuptoolsWarning):
-    """Currently there is no clear way of displaying messages to the users
-    that use the setuptools backend directly via ``pip``.
-    The only thing that might work is a warning, although it is not the
-    most appropriate tool for the job...
-
-    See pypa/packaging-problems#558.
-    """
-
-
-class SetuptoolsDeprecationWarning(SetuptoolsWarning):
-    """
-    Base class for warning deprecations in ``setuptools``
-
-    This class is not derived from ``DeprecationWarning``, and as such is
-    visible by default.
-    """
-
-
-def _should_enforce():
-    enforce = os.getenv("SETUPTOOLS_ENFORCE_DEPRECATION", "false").lower()
-    return enforce in ("true", "on", "ok", "1")
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/wheel.py b/llmlab/lib/python3.12/site-packages/setuptools/wheel.py
deleted file mode 100644
index c7ca43b..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/wheel.py
+++ /dev/null
@@ -1,236 +0,0 @@
-"""Wheels support."""
-
-import contextlib
-import email
-import functools
-import itertools
-import os
-import posixpath
-import re
-import zipfile
-
-from packaging.tags import sys_tags
-from packaging.utils import canonicalize_name
-from packaging.version import Version as parse_version
-
-import setuptools
-from setuptools.archive_util import _unpack_zipfile_obj
-from setuptools.command.egg_info import _egg_basename, write_requirements
-
-from .unicode_utils import _read_utf8_with_fallback
-
-from distutils.util import get_platform
-
-WHEEL_NAME = re.compile(
-    r"""^(?P.+?)-(?P\d.*?)
-    ((-(?P\d.*?))?-(?P.+?)-(?P.+?)-(?P.+?)
-    )\.whl$""",
-    re.VERBOSE,
-).match
-
-NAMESPACE_PACKAGE_INIT = "__import__('pkg_resources').declare_namespace(__name__)\n"
-
-
-@functools.cache
-def _get_supported_tags():
-    # We calculate the supported tags only once, otherwise calling
-    # this method on thousands of wheels takes seconds instead of
-    # milliseconds.
-    return {(t.interpreter, t.abi, t.platform) for t in sys_tags()}
-
-
-def unpack(src_dir, dst_dir) -> None:
-    """Move everything under `src_dir` to `dst_dir`, and delete the former."""
-    for dirpath, dirnames, filenames in os.walk(src_dir):
-        subdir = os.path.relpath(dirpath, src_dir)
-        for f in filenames:
-            src = os.path.join(dirpath, f)
-            dst = os.path.join(dst_dir, subdir, f)
-            os.renames(src, dst)
-        for n, d in reversed(list(enumerate(dirnames))):
-            src = os.path.join(dirpath, d)
-            dst = os.path.join(dst_dir, subdir, d)
-            if not os.path.exists(dst):
-                # Directory does not exist in destination,
-                # rename it and prune it from os.walk list.
-                os.renames(src, dst)
-                del dirnames[n]
-    # Cleanup.
-    for dirpath, dirnames, filenames in os.walk(src_dir, topdown=True):
-        assert not filenames
-        os.rmdir(dirpath)
-
-
-@contextlib.contextmanager
-def disable_info_traces():
-    """
-    Temporarily disable info traces.
-    """
-    from distutils import log
-
-    saved = log.set_threshold(log.WARN)
-    try:
-        yield
-    finally:
-        log.set_threshold(saved)
-
-
-class Wheel:
-    def __init__(self, filename) -> None:
-        match = WHEEL_NAME(os.path.basename(filename))
-        if match is None:
-            raise ValueError(f'invalid wheel name: {filename!r}')
-        self.filename = filename
-        for k, v in match.groupdict().items():
-            setattr(self, k, v)
-
-    def tags(self):
-        """List tags (py_version, abi, platform) supported by this wheel."""
-        return itertools.product(
-            self.py_version.split('.'),
-            self.abi.split('.'),
-            self.platform.split('.'),
-        )
-
-    def is_compatible(self):
-        """Is the wheel compatible with the current platform?"""
-        return next((True for t in self.tags() if t in _get_supported_tags()), False)
-
-    def egg_name(self):
-        return (
-            _egg_basename(
-                self.project_name,
-                self.version,
-                platform=(None if self.platform == 'any' else get_platform()),
-            )
-            + ".egg"
-        )
-
-    def get_dist_info(self, zf):
-        # find the correct name of the .dist-info dir in the wheel file
-        for member in zf.namelist():
-            dirname = posixpath.dirname(member)
-            if dirname.endswith('.dist-info') and canonicalize_name(dirname).startswith(
-                canonicalize_name(self.project_name)
-            ):
-                return dirname
-        raise ValueError("unsupported wheel format. .dist-info not found")
-
-    def install_as_egg(self, destination_eggdir) -> None:
-        """Install wheel as an egg directory."""
-        with zipfile.ZipFile(self.filename) as zf:
-            self._install_as_egg(destination_eggdir, zf)
-
-    def _install_as_egg(self, destination_eggdir, zf):
-        dist_basename = f'{self.project_name}-{self.version}'
-        dist_info = self.get_dist_info(zf)
-        dist_data = f'{dist_basename}.data'
-        egg_info = os.path.join(destination_eggdir, 'EGG-INFO')
-
-        self._convert_metadata(zf, destination_eggdir, dist_info, egg_info)
-        self._move_data_entries(destination_eggdir, dist_data)
-        self._fix_namespace_packages(egg_info, destination_eggdir)
-
-    @staticmethod
-    def _convert_metadata(zf, destination_eggdir, dist_info, egg_info):
-        import pkg_resources
-
-        def get_metadata(name):
-            with zf.open(posixpath.join(dist_info, name)) as fp:
-                value = fp.read().decode('utf-8')
-                return email.parser.Parser().parsestr(value)
-
-        wheel_metadata = get_metadata('WHEEL')
-        # Check wheel format version is supported.
-        wheel_version = parse_version(wheel_metadata.get('Wheel-Version'))
-        wheel_v1 = parse_version('1.0') <= wheel_version < parse_version('2.0dev0')
-        if not wheel_v1:
-            raise ValueError(f'unsupported wheel format version: {wheel_version}')
-        # Extract to target directory.
-        _unpack_zipfile_obj(zf, destination_eggdir)
-        # Convert metadata.
-        dist_info = os.path.join(destination_eggdir, dist_info)
-        dist = pkg_resources.Distribution.from_location(
-            destination_eggdir,
-            dist_info,
-            metadata=pkg_resources.PathMetadata(destination_eggdir, dist_info),
-        )
-
-        # Note: Evaluate and strip markers now,
-        # as it's difficult to convert back from the syntax:
-        # foobar; "linux" in sys_platform and extra == 'test'
-        def raw_req(req):
-            req.marker = None
-            return str(req)
-
-        install_requires = list(map(raw_req, dist.requires()))
-        extras_require = {
-            extra: [
-                req
-                for req in map(raw_req, dist.requires((extra,)))
-                if req not in install_requires
-            ]
-            for extra in dist.extras
-        }
-        os.rename(dist_info, egg_info)
-        os.rename(
-            os.path.join(egg_info, 'METADATA'),
-            os.path.join(egg_info, 'PKG-INFO'),
-        )
-        setup_dist = setuptools.Distribution(
-            attrs=dict(
-                install_requires=install_requires,
-                extras_require=extras_require,
-            ),
-        )
-        with disable_info_traces():
-            write_requirements(
-                setup_dist.get_command_obj('egg_info'),
-                None,
-                os.path.join(egg_info, 'requires.txt'),
-            )
-
-    @staticmethod
-    def _move_data_entries(destination_eggdir, dist_data):
-        """Move data entries to their correct location."""
-        dist_data = os.path.join(destination_eggdir, dist_data)
-        dist_data_scripts = os.path.join(dist_data, 'scripts')
-        if os.path.exists(dist_data_scripts):
-            egg_info_scripts = os.path.join(destination_eggdir, 'EGG-INFO', 'scripts')
-            os.mkdir(egg_info_scripts)
-            for entry in os.listdir(dist_data_scripts):
-                # Remove bytecode, as it's not properly handled
-                # during easy_install scripts install phase.
-                if entry.endswith('.pyc'):
-                    os.unlink(os.path.join(dist_data_scripts, entry))
-                else:
-                    os.rename(
-                        os.path.join(dist_data_scripts, entry),
-                        os.path.join(egg_info_scripts, entry),
-                    )
-            os.rmdir(dist_data_scripts)
-        for subdir in filter(
-            os.path.exists,
-            (
-                os.path.join(dist_data, d)
-                for d in ('data', 'headers', 'purelib', 'platlib')
-            ),
-        ):
-            unpack(subdir, destination_eggdir)
-        if os.path.exists(dist_data):
-            os.rmdir(dist_data)
-
-    @staticmethod
-    def _fix_namespace_packages(egg_info, destination_eggdir):
-        namespace_packages = os.path.join(egg_info, 'namespace_packages.txt')
-        if os.path.exists(namespace_packages):
-            namespace_packages = _read_utf8_with_fallback(namespace_packages).split()
-
-            for mod in namespace_packages:
-                mod_dir = os.path.join(destination_eggdir, *mod.split('.'))
-                mod_init = os.path.join(mod_dir, '__init__.py')
-                if not os.path.exists(mod_dir):
-                    os.mkdir(mod_dir)
-                if not os.path.exists(mod_init):
-                    with open(mod_init, 'w', encoding="utf-8") as fp:
-                        fp.write(NAMESPACE_PACKAGE_INIT)
diff --git a/llmlab/lib/python3.12/site-packages/setuptools/windows_support.py b/llmlab/lib/python3.12/site-packages/setuptools/windows_support.py
deleted file mode 100644
index 7a2b53a..0000000
--- a/llmlab/lib/python3.12/site-packages/setuptools/windows_support.py
+++ /dev/null
@@ -1,30 +0,0 @@
-import platform
-
-
-def windows_only(func):
-    if platform.system() != 'Windows':
-        return lambda *args, **kwargs: None
-    return func
-
-
-@windows_only
-def hide_file(path: str) -> None:
-    """
-    Set the hidden attribute on a file or directory.
-
-    From https://stackoverflow.com/questions/19622133/
-
-    `path` must be text.
-    """
-    import ctypes
-    import ctypes.wintypes
-
-    SetFileAttributes = ctypes.windll.kernel32.SetFileAttributesW
-    SetFileAttributes.argtypes = ctypes.wintypes.LPWSTR, ctypes.wintypes.DWORD
-    SetFileAttributes.restype = ctypes.wintypes.BOOL
-
-    FILE_ATTRIBUTE_HIDDEN = 0x02
-
-    ret = SetFileAttributes(path, FILE_ATTRIBUTE_HIDDEN)
-    if not ret:
-        raise ctypes.WinError()
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/__init__.cpython-312.pyc
index b68b3c5..a2f335c 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_base_connection.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_base_connection.cpython-312.pyc
index d957217..5dd3043 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_base_connection.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_base_connection.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_collections.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_collections.cpython-312.pyc
index 92703e6..c5b4c4c 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_collections.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_collections.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_request_methods.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_request_methods.cpython-312.pyc
index e7ff1fd..72d695c 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_request_methods.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_request_methods.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_version.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_version.cpython-312.pyc
index ed0a121..e69b42e 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_version.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/_version.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connection.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connection.cpython-312.pyc
index ba7bf4e..c11cf6d 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connection.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connection.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connectionpool.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connectionpool.cpython-312.pyc
index 309f91e..288833c 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connectionpool.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/connectionpool.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/exceptions.cpython-312.pyc
index 6ae3f25..fc4f49f 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/exceptions.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/exceptions.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/fields.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/fields.cpython-312.pyc
index cb8c4d3..033d727 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/fields.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/fields.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/filepost.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/filepost.cpython-312.pyc
index ef2ffb8..351698f 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/filepost.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/filepost.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/poolmanager.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/poolmanager.cpython-312.pyc
index 482e20e..ff97cf0 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/poolmanager.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/poolmanager.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/response.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/response.cpython-312.pyc
index a5c45a8..ab4317d 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/response.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/__pycache__/response.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/__init__.cpython-312.pyc
index 72cb4f3..07623b3 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc
index 876e056..064e375 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/socks.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/socks.cpython-312.pyc
index 135c16a..fd343d9 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/socks.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/__pycache__/socks.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/__init__.cpython-312.pyc
index 2e6a1c0..17bd0d3 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/connection.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/connection.cpython-312.pyc
index 1310804..1acf7d9 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/connection.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/connection.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/fetch.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/fetch.cpython-312.pyc
index 7144676..6ada3d1 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/fetch.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/fetch.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/request.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/request.cpython-312.pyc
index 54ee3da..49bc44a 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/request.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/request.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/response.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/response.cpython-312.pyc
index 3e3ce4c..592a45c 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/response.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/contrib/emscripten/__pycache__/response.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/__init__.cpython-312.pyc
index 8affd21..9c3a284 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/connection.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/connection.cpython-312.pyc
index 173f7a6..377a9bb 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/connection.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/connection.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/probe.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/probe.cpython-312.pyc
index 4b3f1b6..6deecad 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/probe.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/http2/__pycache__/probe.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/__init__.cpython-312.pyc
index 30c30fe..87ce8a2 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/__init__.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/__init__.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/connection.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/connection.cpython-312.pyc
index d6f8cfb..1283ece 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/connection.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/connection.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/proxy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/proxy.cpython-312.pyc
index a3a799c..d30db8f 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/proxy.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/proxy.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/request.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/request.cpython-312.pyc
index e5bb0d4..d2c623b 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/request.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/request.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/response.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/response.cpython-312.pyc
index 09e9ddd..3dc2023 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/response.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/response.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/retry.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/retry.cpython-312.pyc
index 587954f..1ec903f 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/retry.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/retry.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_.cpython-312.pyc
index 4538503..550c00a 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc
index 68b2566..fa36054 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssltransport.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssltransport.cpython-312.pyc
index 752c7f1..312e5ad 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssltransport.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/ssltransport.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/timeout.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/timeout.cpython-312.pyc
index df4679f..c272f0d 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/timeout.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/timeout.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/url.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/url.cpython-312.pyc
index e6053c3..148eff2 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/url.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/url.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/util.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/util.cpython-312.pyc
index adb4c85..0db15e9 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/util.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/util.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/wait.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/wait.cpython-312.pyc
index 56800f0..dd80ef8 100644
Binary files a/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/wait.cpython-312.pyc and b/llmlab/lib/python3.12/site-packages/urllib3/util/__pycache__/wait.cpython-312.pyc differ
diff --git a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/METADATA
deleted file mode 100644
index bbfb60b..0000000
--- a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/METADATA
+++ /dev/null
@@ -1,11 +0,0 @@
-Metadata-Version: 2.4
-Name: uuid
-Version: 1.30
-Summary: UUID object and generation functions
-Home-page: http://zesty.ca/python/
-Author: Ka-Ping Yee
-Author-email: ping@zesty.ca
-Dynamic: author
-Dynamic: author-email
-Dynamic: home-page
-Dynamic: summary
diff --git a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/RECORD
deleted file mode 100644
index 9039f1b..0000000
--- a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/RECORD
+++ /dev/null
@@ -1,7 +0,0 @@
-uuid-1.30.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-uuid-1.30.dist-info/METADATA,sha256=ZUs-kyWmBQDNuO0FZulekbnBEFO2th4N072LrDjU7Fk,250
-uuid-1.30.dist-info/RECORD,,
-uuid-1.30.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-uuid-1.30.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91
-uuid-1.30.dist-info/top_level.txt,sha256=tYH2_TJyt_F5duBoeRnZjJ9YXORV92_5nNbRWtM3o1Q,5
-uuid.py,sha256=3pjfI9BY4TUUPqX3Gx-2EfCIwvkNhvuJfciT_PE8dvc,17742
diff --git a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/REQUESTED b/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/REQUESTED
deleted file mode 100644
index e69de29..0000000
diff --git a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/WHEEL
deleted file mode 100644
index 91720dd..0000000
--- a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/WHEEL
+++ /dev/null
@@ -1,5 +0,0 @@
-Wheel-Version: 1.0
-Generator: setuptools (78.0.2)
-Root-Is-Purelib: true
-Tag: py3-none-any
-
diff --git a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/top_level.txt
deleted file mode 100644
index 43ab615..0000000
--- a/llmlab/lib/python3.12/site-packages/uuid-1.30.dist-info/top_level.txt
+++ /dev/null
@@ -1 +0,0 @@
-uuid
diff --git a/llmlab/lib/python3.12/site-packages/uuid.py b/llmlab/lib/python3.12/site-packages/uuid.py
deleted file mode 100644
index 3b590e8..0000000
--- a/llmlab/lib/python3.12/site-packages/uuid.py
+++ /dev/null
@@ -1,476 +0,0 @@
-r"""UUID objects (universally unique identifiers) according to RFC 4122.
-
-This module provides immutable UUID objects (class UUID) and the functions
-uuid1(), uuid3(), uuid4(), uuid5() for generating version 1, 3, 4, and 5
-UUIDs as specified in RFC 4122.
-
-If all you want is a unique ID, you should probably call uuid1() or uuid4().
-Note that uuid1() may compromise privacy since it creates a UUID containing
-the computer's network address.  uuid4() creates a random UUID.
-
-Typical usage:
-
-    >>> import uuid
-
-    # make a UUID based on the host ID and current time
-    >>> uuid.uuid1()
-    UUID('a8098c1a-f86e-11da-bd1a-00112444be1e')
-
-    # make a UUID using an MD5 hash of a namespace UUID and a name
-    >>> uuid.uuid3(uuid.NAMESPACE_DNS, 'python.org')
-    UUID('6fa459ea-ee8a-3ca4-894e-db77e160355e')
-
-    # make a random UUID
-    >>> uuid.uuid4()
-    UUID('16fd2706-8baf-433b-82eb-8c7fada847da')
-
-    # make a UUID using a SHA-1 hash of a namespace UUID and a name
-    >>> uuid.uuid5(uuid.NAMESPACE_DNS, 'python.org')
-    UUID('886313e1-3b8a-5372-9b90-0c9aee199e5d')
-
-    # make a UUID from a string of hex digits (braces and hyphens ignored)
-    >>> x = uuid.UUID('{00010203-0405-0607-0809-0a0b0c0d0e0f}')
-
-    # convert a UUID to a string of hex digits in standard form
-    >>> str(x)
-    '00010203-0405-0607-0809-0a0b0c0d0e0f'
-
-    # get the raw 16 bytes of the UUID
-    >>> x.bytes
-    '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f'
-
-    # make a UUID from a 16-byte string
-    >>> uuid.UUID(bytes=x.bytes)
-    UUID('00010203-0405-0607-0809-0a0b0c0d0e0f')
-"""
-
-__author__ = 'Ka-Ping Yee '
-__date__ = '$Date: 2006/06/12 23:15:40 $'.split()[1].replace('/', '-')
-__version__ = '$Revision: 1.30 $'.split()[1]
-
-RESERVED_NCS, RFC_4122, RESERVED_MICROSOFT, RESERVED_FUTURE = [
-    'reserved for NCS compatibility', 'specified in RFC 4122',
-    'reserved for Microsoft compatibility', 'reserved for future definition']
-
-class UUID(object):
-    """Instances of the UUID class represent UUIDs as specified in RFC 4122.
-    UUID objects are immutable, hashable, and usable as dictionary keys.
-    Converting a UUID to a string with str() yields something in the form
-    '12345678-1234-1234-1234-123456789abc'.  The UUID constructor accepts
-    four possible forms: a similar string of hexadecimal digits, or a
-    string of 16 raw bytes as an argument named 'bytes', or a tuple of
-    six integer fields (with 32-bit, 16-bit, 16-bit, 8-bit, 8-bit, and
-    48-bit values respectively) as an argument named 'fields', or a single
-    128-bit integer as an argument named 'int'.
-
-    UUIDs have these read-only attributes:
-
-        bytes       the UUID as a 16-byte string
-
-        fields      a tuple of the six integer fields of the UUID,
-                    which are also available as six individual attributes
-                    and two derived attributes:
-
-            time_low                the first 32 bits of the UUID
-            time_mid                the next 16 bits of the UUID
-            time_hi_version         the next 16 bits of the UUID
-            clock_seq_hi_variant    the next 8 bits of the UUID
-            clock_seq_low           the next 8 bits of the UUID
-            node                    the last 48 bits of the UUID
-
-            time                    the 60-bit timestamp
-            clock_seq               the 14-bit sequence number
-
-        hex         the UUID as a 32-character hexadecimal string
-
-        int         the UUID as a 128-bit integer
-
-        urn         the UUID as a URN as specified in RFC 4122
-
-        variant     the UUID variant (one of the constants RESERVED_NCS,
-                    RFC_4122, RESERVED_MICROSOFT, or RESERVED_FUTURE)
-
-        version     the UUID version number (1 through 5, meaningful only
-                    when the variant is RFC_4122)
-    """
-
-    def __init__(self, hex=None, bytes=None, fields=None, int=None,
-                       version=None):
-        r"""Create a UUID from either a string of 32 hexadecimal digits,
-        a string of 16 bytes as the 'bytes' argument, a tuple of six
-        integers (32-bit time_low, 16-bit time_mid, 16-bit time_hi_version,
-        8-bit clock_seq_hi_variant, 8-bit clock_seq_low, 48-bit node) as
-        the 'fields' argument, or a single 128-bit integer as the 'int'
-        argument.  When a string of hex digits is given, curly braces,
-        hyphens, and a URN prefix are all optional.  For example, these
-        expressions all yield the same UUID:
-
-        UUID('{12345678-1234-5678-1234-567812345678}')
-        UUID('12345678123456781234567812345678')
-        UUID('urn:uuid:12345678-1234-5678-1234-567812345678')
-        UUID(bytes='\x12\x34\x56\x78'*4)
-        UUID(fields=(0x12345678, 0x1234, 0x5678, 0x12, 0x34, 0x567812345678))
-        UUID(int=0x12345678123456781234567812345678)
-
-        Exactly one of 'hex', 'bytes', 'fields', or 'int' must be given.
-        The 'version' argument is optional; if given, the resulting UUID
-        will have its variant and version number set according to RFC 4122,
-        overriding bits in the given 'hex', 'bytes', 'fields', or 'int'.
-        """
-
-        if [hex, bytes, fields, int].count(None) != 3:
-            raise TypeError('need just one of hex, bytes, fields, or int')
-        if hex is not None:
-            hex = hex.replace('urn:', '').replace('uuid:', '')
-            hex = hex.strip('{}').replace('-', '')
-            if len(hex) != 32:
-                raise ValueError('badly formed hexadecimal UUID string')
-            int = long(hex, 16)
-        if bytes is not None:
-            if len(bytes) != 16:
-                raise ValueError('bytes is not a 16-char string')
-            int = long(('%02x'*16) % tuple(map(ord, bytes)), 16)
-        if fields is not None:
-            if len(fields) != 6:
-                raise ValueError('fields is not a 6-tuple')
-            (time_low, time_mid, time_hi_version,
-             clock_seq_hi_variant, clock_seq_low, node) = fields
-            if not 0 <= time_low < 1<<32L:
-                raise ValueError('field 1 out of range (need a 32-bit value)')
-            if not 0 <= time_mid < 1<<16L:
-                raise ValueError('field 2 out of range (need a 16-bit value)')
-            if not 0 <= time_hi_version < 1<<16L:
-                raise ValueError('field 3 out of range (need a 16-bit value)')
-            if not 0 <= clock_seq_hi_variant < 1<<8L:
-                raise ValueError('field 4 out of range (need an 8-bit value)')
-            if not 0 <= clock_seq_low < 1<<8L:
-                raise ValueError('field 5 out of range (need an 8-bit value)')
-            if not 0 <= node < 1<<48L:
-                raise ValueError('field 6 out of range (need a 48-bit value)')
-            clock_seq = (clock_seq_hi_variant << 8L) | clock_seq_low
-            int = ((time_low << 96L) | (time_mid << 80L) |
-                   (time_hi_version << 64L) | (clock_seq << 48L) | node)
-        if int is not None:
-            if not 0 <= int < 1<<128L:
-                raise ValueError('int is out of range (need a 128-bit value)')
-        if version is not None:
-            if not 1 <= version <= 5:
-                raise ValueError('illegal version number')
-            # Set the variant to RFC 4122.
-            int &= ~(0xc000 << 48L)
-            int |= 0x8000 << 48L
-            # Set the version number.
-            int &= ~(0xf000 << 64L)
-            int |= version << 76L
-        self.__dict__['int'] = int
-
-    def __cmp__(self, other):
-        if isinstance(other, UUID):
-            return cmp(self.int, other.int)
-        return NotImplemented
-
-    def __hash__(self):
-        return hash(self.int)
-
-    def __int__(self):
-        return self.int
-
-    def __repr__(self):
-        return 'UUID(%r)' % str(self)
-
-    def __setattr__(self, name, value):
-        raise TypeError('UUID objects are immutable')
-
-    def __str__(self):
-        hex = '%032x' % self.int
-        return '%s-%s-%s-%s-%s' % (
-            hex[:8], hex[8:12], hex[12:16], hex[16:20], hex[20:])
-
-    def get_bytes(self):
-        bytes = ''
-        for shift in range(0, 128, 8):
-            bytes = chr((self.int >> shift) & 0xff) + bytes
-        return bytes
-
-    bytes = property(get_bytes)
-
-    def get_fields(self):
-        return (self.time_low, self.time_mid, self.time_hi_version,
-                self.clock_seq_hi_variant, self.clock_seq_low, self.node)
-
-    fields = property(get_fields)
-
-    def get_time_low(self):
-        return self.int >> 96L
-
-    time_low = property(get_time_low)
-
-    def get_time_mid(self):
-        return (self.int >> 80L) & 0xffff
-
-    time_mid = property(get_time_mid)
-
-    def get_time_hi_version(self):
-        return (self.int >> 64L) & 0xffff
-
-    time_hi_version = property(get_time_hi_version)
-
-    def get_clock_seq_hi_variant(self):
-        return (self.int >> 56L) & 0xff
-
-    clock_seq_hi_variant = property(get_clock_seq_hi_variant)
-
-    def get_clock_seq_low(self):
-        return (self.int >> 48L) & 0xff
-
-    clock_seq_low = property(get_clock_seq_low)
-
-    def get_time(self):
-        return (((self.time_hi_version & 0x0fffL) << 48L) |
-                (self.time_mid << 32L) | self.time_low)
-
-    time = property(get_time)
-
-    def get_clock_seq(self):
-        return (((self.clock_seq_hi_variant & 0x3fL) << 8L) |
-                self.clock_seq_low)
-
-    clock_seq = property(get_clock_seq)
-
-    def get_node(self):
-        return self.int & 0xffffffffffff
-
-    node = property(get_node)
-
-    def get_hex(self):
-        return '%032x' % self.int
-
-    hex = property(get_hex)
-
-    def get_urn(self):
-        return 'urn:uuid:' + str(self)
-
-    urn = property(get_urn)
-
-    def get_variant(self):
-        if not self.int & (0x8000 << 48L):
-            return RESERVED_NCS
-        elif not self.int & (0x4000 << 48L):
-            return RFC_4122
-        elif not self.int & (0x2000 << 48L):
-            return RESERVED_MICROSOFT
-        else:
-            return RESERVED_FUTURE
-
-    variant = property(get_variant)
-
-    def get_version(self):
-        # The version bits are only meaningful for RFC 4122 UUIDs.
-        if self.variant == RFC_4122:
-            return int((self.int >> 76L) & 0xf)
-
-    version = property(get_version)
-
-def _ifconfig_getnode():
-    """Get the hardware address on Unix by running ifconfig."""
-    import os
-    for dir in ['', '/sbin/', '/usr/sbin']:
-        try:
-            pipe = os.popen(os.path.join(dir, 'ifconfig'))
-        except IOError:
-            continue
-        for line in pipe:
-            words = line.lower().split()
-            for i in range(len(words)):
-                if words[i] in ['hwaddr', 'ether']:
-                    return int(words[i + 1].replace(':', ''), 16)
-
-def _ipconfig_getnode():
-    """Get the hardware address on Windows by running ipconfig.exe."""
-    import os, re
-    dirs = ['', r'c:\windows\system32', r'c:\winnt\system32']
-    try:
-        import ctypes
-        buffer = ctypes.create_string_buffer(300)
-        ctypes.windll.kernel32.GetSystemDirectoryA(buffer, 300)
-        dirs.insert(0, buffer.value.decode('mbcs'))
-    except:
-        pass
-    for dir in dirs:
-        try:
-            pipe = os.popen(os.path.join(dir, 'ipconfig') + ' /all')
-        except IOError:
-            continue
-        for line in pipe:
-            value = line.split(':')[-1].strip().lower()
-            if re.match('([0-9a-f][0-9a-f]-){5}[0-9a-f][0-9a-f]', value):
-                return int(value.replace('-', ''), 16)
-
-def _netbios_getnode():
-    """Get the hardware address on Windows using NetBIOS calls.
-    See http://support.microsoft.com/kb/118623 for details."""
-    import win32wnet, netbios
-    ncb = netbios.NCB()
-    ncb.Command = netbios.NCBENUM
-    ncb.Buffer = adapters = netbios.LANA_ENUM()
-    adapters._pack()
-    if win32wnet.Netbios(ncb) != 0:
-        return
-    adapters._unpack()
-    for i in range(adapters.length):
-        ncb.Reset()
-        ncb.Command = netbios.NCBRESET
-        ncb.Lana_num = ord(adapters.lana[i])
-        if win32wnet.Netbios(ncb) != 0:
-            continue
-        ncb.Reset()
-        ncb.Command = netbios.NCBASTAT
-        ncb.Lana_num = ord(adapters.lana[i])
-        ncb.Callname = '*'.ljust(16)
-        ncb.Buffer = status = netbios.ADAPTER_STATUS()
-        if win32wnet.Netbios(ncb) != 0:
-            continue
-        status._unpack()
-        bytes = map(ord, status.adapter_address)
-        return ((bytes[0]<<40L) + (bytes[1]<<32L) + (bytes[2]<<24L) +
-                (bytes[3]<<16L) + (bytes[4]<<8L) + bytes[5])
-
-# Thanks to Thomas Heller for ctypes and for his help with its use here.
-
-# If ctypes is available, use it to find system routines for UUID generation.
-_uuid_generate_random = _uuid_generate_time = _UuidCreate = None
-try:
-    import ctypes, ctypes.util
-    _buffer = ctypes.create_string_buffer(16)
-
-    # The uuid_generate_* routines are provided by libuuid on at least
-    # Linux and FreeBSD, and provided by libc on Mac OS X.
-    for libname in ['uuid', 'c']:
-        try:
-            lib = ctypes.CDLL(ctypes.util.find_library(libname))
-        except:
-            continue
-        if hasattr(lib, 'uuid_generate_random'):
-            _uuid_generate_random = lib.uuid_generate_random
-        if hasattr(lib, 'uuid_generate_time'):
-            _uuid_generate_time = lib.uuid_generate_time
-
-    # On Windows prior to 2000, UuidCreate gives a UUID containing the
-    # hardware address.  On Windows 2000 and later, UuidCreate makes a
-    # random UUID and UuidCreateSequential gives a UUID containing the
-    # hardware address.  These routines are provided by the RPC runtime.
-    try:
-        lib = ctypes.windll.rpcrt4
-    except:
-        lib = None
-    _UuidCreate = getattr(lib, 'UuidCreateSequential',
-                          getattr(lib, 'UuidCreate', None))
-except:
-    pass
-
-def _unixdll_getnode():
-    """Get the hardware address on Unix using ctypes."""
-    _uuid_generate_time(_buffer)
-    return UUID(bytes=_buffer.raw).node
-
-def _windll_getnode():
-    """Get the hardware address on Windows using ctypes."""
-    if _UuidCreate(_buffer) == 0:
-        return UUID(bytes=_buffer.raw).node
-
-def _random_getnode():
-    """Get a random node ID, with eighth bit set as suggested by RFC 4122."""
-    import random
-    return random.randrange(0, 1<<48L) | 0x010000000000L
-
-_node = None
-
-def getnode():
-    """Get the hardware address as a 48-bit integer.  The first time this
-    runs, it may launch a separate program, which could be quite slow.  If
-    all attempts to obtain the hardware address fail, we choose a random
-    48-bit number with its eighth bit set to 1 as recommended in RFC 4122."""
-
-    global _node
-    if _node is not None:
-        return _node
-
-    import sys
-    if sys.platform == 'win32':
-        getters = [_windll_getnode, _netbios_getnode, _ipconfig_getnode]
-    else:
-        getters = [_unixdll_getnode, _ifconfig_getnode]
-
-    for getter in getters + [_random_getnode]:
-        try:
-            _node = getter()
-        except:
-            continue
-        if _node is not None:
-            return _node
-
-def uuid1(node=None, clock_seq=None):
-    """Generate a UUID from a host ID, sequence number, and the current time.
-    If 'node' is not given, getnode() is used to obtain the hardware
-    address.  If 'clock_seq' is given, it is used as the sequence number;
-    otherwise a random 14-bit sequence number is chosen."""
-
-    # When the system provides a version-1 UUID generator, use it (but don't
-    # use UuidCreate here because its UUIDs don't conform to RFC 4122).
-    if _uuid_generate_time and node is clock_seq is None:
-        _uuid_generate_time(_buffer)
-        return UUID(bytes=_buffer.raw)
-
-    import time
-    nanoseconds = int(time.time() * 1e9)
-    # 0x01b21dd213814000 is the number of 100-ns intervals between the
-    # UUID epoch 1582-10-15 00:00:00 and the Unix epoch 1970-01-01 00:00:00.
-    timestamp = int(nanoseconds/100) + 0x01b21dd213814000L
-    if clock_seq is None:
-        import random
-        clock_seq = random.randrange(1<<14L) # instead of stable storage
-    time_low = timestamp & 0xffffffffL
-    time_mid = (timestamp >> 32L) & 0xffffL
-    time_hi_version = (timestamp >> 48L) & 0x0fffL
-    clock_seq_low = clock_seq & 0xffL
-    clock_seq_hi_variant = (clock_seq >> 8L) & 0x3fL
-    if node is None:
-        node = getnode()
-    return UUID(fields=(time_low, time_mid, time_hi_version,
-                        clock_seq_hi_variant, clock_seq_low, node), version=1)
-
-def uuid3(namespace, name):
-    """Generate a UUID from the MD5 hash of a namespace UUID and a name."""
-    import md5
-    hash = md5.md5(namespace.bytes + name).digest()
-    return UUID(bytes=hash[:16], version=3)
-
-def uuid4():
-    """Generate a random UUID."""
-
-    # When the system provides a version-4 UUID generator, use it.
-    if _uuid_generate_random:
-        _uuid_generate_random(_buffer)
-        return UUID(bytes=_buffer.raw)
-
-    # Otherwise, get randomness from urandom or the 'random' module.
-    try:
-        import os
-        return UUID(bytes=os.urandom(16), version=4)
-    except:
-        import random
-        bytes = [chr(random.randrange(256)) for i in range(16)]
-        return UUID(bytes=bytes, version=4)
-
-def uuid5(namespace, name):
-    """Generate a UUID from the SHA-1 hash of a namespace UUID and a name."""
-    import sha
-    hash = sha.sha(namespace.bytes + name).digest()
-    return UUID(bytes=hash[:16], version=5)
-
-# The following standard UUIDs are for use with uuid3() or uuid5().
-
-NAMESPACE_DNS = UUID('6ba7b810-9dad-11d1-80b4-00c04fd430c8')
-NAMESPACE_URL = UUID('6ba7b811-9dad-11d1-80b4-00c04fd430c8')
-NAMESPACE_OID = UUID('6ba7b812-9dad-11d1-80b4-00c04fd430c8')
-NAMESPACE_X500 = UUID('6ba7b814-9dad-11d1-80b4-00c04fd430c8')
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2-py3.12-nspkg.pth b/llmlab/lib/python3.12/site-packages/zope.interface-7.2-py3.12-nspkg.pth
deleted file mode 100644
index 8012119..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2-py3.12-nspkg.pth
+++ /dev/null
@@ -1 +0,0 @@
-import sys, types, os;p = os.path.join(sys._getframe(1).f_locals['sitedir'], *('zope',));importlib = __import__('importlib.util');__import__('importlib.machinery');m = sys.modules.setdefault('zope', importlib.util.module_from_spec(importlib.machinery.PathFinder.find_spec('zope', [os.path.dirname(p)])));m = m or sys.modules.setdefault('zope', types.ModuleType('zope'));mp = (m or []) and m.__dict__.setdefault('__path__',[]);(p not in mp) and mp.append(p)
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/INSTALLER b/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/INSTALLER
deleted file mode 100644
index a1b589e..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/INSTALLER
+++ /dev/null
@@ -1 +0,0 @@
-pip
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/LICENSE.txt b/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/LICENSE.txt
deleted file mode 100644
index e1f9ad7..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/LICENSE.txt
+++ /dev/null
@@ -1,44 +0,0 @@
-Zope Public License (ZPL) Version 2.1
-
-A copyright notice accompanies this license document that identifies the
-copyright holders.
-
-This license has been certified as open source. It has also been designated as
-GPL compatible by the Free Software Foundation (FSF).
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-1. Redistributions in source code must retain the accompanying copyright
-notice, this list of conditions, and the following disclaimer.
-
-2. Redistributions in binary form must reproduce the accompanying copyright
-notice, this list of conditions, and the following disclaimer in the
-documentation and/or other materials provided with the distribution.
-
-3. Names of the copyright holders must not be used to endorse or promote
-products derived from this software without prior written permission from the
-copyright holders.
-
-4. The right to distribute this software or to use it for any purpose does not
-give you the right to use Servicemarks (sm) or Trademarks (tm) of the
-copyright
-holders. Use of them is covered by separate agreement with the copyright
-holders.
-
-5. If any files are modified, you must cause the modified files to carry
-prominent notices stating that you changed the files and the date of any
-change.
-
-Disclaimer
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY EXPRESSED
-OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
-OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
-EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY DIRECT, INDIRECT,
-INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
-PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
-LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
-EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/METADATA b/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/METADATA
deleted file mode 100644
index 279d71d..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/METADATA
+++ /dev/null
@@ -1,1224 +0,0 @@
-Metadata-Version: 2.1
-Name: zope.interface
-Version: 7.2
-Summary: Interfaces for Python
-Home-page: https://github.com/zopefoundation/zope.interface
-Author: Zope Foundation and Contributors
-Author-email: zope-dev@zope.dev
-License: ZPL 2.1
-Keywords: interface,components,plugins
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Zope Public License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Programming Language :: Python :: Implementation :: CPython
-Classifier: Programming Language :: Python :: Implementation :: PyPy
-Classifier: Framework :: Zope :: 3
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.8
-Description-Content-Type: text/x-rst
-License-File: LICENSE.txt
-Requires-Dist: setuptools
-Provides-Extra: docs
-Requires-Dist: Sphinx ; extra == 'docs'
-Requires-Dist: repoze.sphinx.autointerface ; extra == 'docs'
-Requires-Dist: furo ; extra == 'docs'
-Provides-Extra: test
-Requires-Dist: coverage[toml] ; extra == 'test'
-Requires-Dist: zope.event ; extra == 'test'
-Requires-Dist: zope.testing ; extra == 'test'
-Provides-Extra: testing
-Requires-Dist: coverage[toml] ; extra == 'testing'
-Requires-Dist: zope.event ; extra == 'testing'
-Requires-Dist: zope.testing ; extra == 'testing'
-
-====================
- ``zope.interface``
-====================
-
-.. image:: https://img.shields.io/pypi/v/zope.interface.svg
-    :target: https://pypi.python.org/pypi/zope.interface/
-    :alt: Latest Version
-
-.. image:: https://img.shields.io/pypi/pyversions/zope.interface.svg
-        :target: https://pypi.org/project/zope.interface/
-        :alt: Supported Python versions
-
-.. image:: https://github.com/zopefoundation/zope.interface/actions/workflows/tests.yml/badge.svg
-        :target: https://github.com/zopefoundation/zope.interface/actions/workflows/tests.yml
-
-.. image:: https://readthedocs.org/projects/zopeinterface/badge/?version=latest
-        :target: https://zopeinterface.readthedocs.io/en/latest/
-        :alt: Documentation Status
-
-This package is intended to be independently reusable in any Python
-project. It is maintained by the `Zope Toolkit project
-`_.
-
-This package provides an implementation of "object interfaces" for Python.
-Interfaces are a mechanism for labeling objects as conforming to a given
-API or contract. So, this package can be considered as implementation of
-the `Design By Contract`_ methodology support in Python.
-
-.. _Design By Contract: http://en.wikipedia.org/wiki/Design_by_contract
-
-For detailed documentation, please see https://zopeinterface.readthedocs.io/en/latest/
-
-=========
- Changes
-=========
-
-7.2 (2024-11-28)
-================
-
-- Add preliminary support for Python 3.14a2, this means that
-  ``.common.builtins.IByteString`` and ``.common.collections.IByteString`` are
-  no longer available from this Python version onwards as Python 3.14 dropped
-  ``collections.abc.ByteString``.
-
-
-7.1.1 (2024-10-23)
-==================
-
-- Fix segmentation faults in `weakrefobject.c` on Python 3.12 and 3.13.
-  (`#323 `_)
-
-
-7.1.0 (2024-10-10)
-==================
-
-- Declare support for Python 3.13.
-
-- Fix segmentation faults on Python 3.13.
-  (`#323 `_)
-
-
-7.0.3 (2024-08-27)
-==================
-
-- Fix `Assertion 'memb->type == T_PYSSIZET' failed.` for Python < 3.12.
-  (`#319 `_)
-
-
-7.0.2 (2024-08-26)
-==================
-
-- Fix reference-counting bug in C module initialization (broken in 7.0).
-  (`#316 `_)
-
-
-7.0.1 (2024-08-06)
-==================
-
-- Fix subclassability of ``ObjectSpecificationDescriptor`` (broken in 7.0).
-  (`#312 `_)
-
-
-7.0 (2024-08-06)
-================
-
-- Enable heap-based types (PEP 384) for Python >= 3.11.
-
-- Adopt multi-phase module initialization (PEP 489).
-
-- Drop support for Python 3.7.
-
-
-6.4.post2 (2024-05-24)
-======================
-
-- Publish missing Windows wheels, second attempt.
-  (`#295 `_)
-
-
-6.4.post1 (2024-05-23)
-======================
-
-- Publish missing Windows wheels.
-  (`#295 `_)
-
-
-6.4.post0 (2024-05-22)
-======================
-
-- The sdist of version 6.4 was uploaded to PyPI as
-  ``zope_interface-6.4.tar.gz`` instead of ``zope.interface-6.4-py2.tar.gz``
-  which cannot be installed by ``zc.buildout``.  This release is a re-release
-  of version 6.4 with the correct sdist name.
-  (`#298 `_)
-
-
-6.4 (2024-05-15)
-================
-
-- Adjust for incompatible changes in Python 3.13b1.
-  (`#292 `_)
-
-- Build windows wheels on GHA.
-
-6.3 (2024-04-12)
-================
-
-- Add preliminary support for Python 3.13 as of 3.13a6.
-
-
-6.2 (2024-02-16)
-================
-
-- Add preliminary support for Python 3.13 as of 3.13a3.
-
-- Add support to use the pipe (``|``) syntax for ``typing.Union``.
-  (`#280 `_)
-
-
-6.1 (2023-10-05)
-================
-
-- Build Linux binary wheels for Python 3.12.
-
-- Add support for Python 3.12.
-
-- Fix building of the docs for non-final versions.
-
-
-6.0 (2023-03-17)
-================
-
-- Build Linux binary wheels for Python 3.11.
-
-- Drop support for Python 2.7, 3.5, 3.6.
-
-- Fix test deprecation warning on Python 3.11.
-
-- Add preliminary support for Python 3.12 as of 3.12a5.
-
-- Drop:
-
-    + `zope.interface.implements`
-    + `zope.interface.implementsOnly`
-    + `zope.interface.classProvides`
-
-
-5.5.2 (2022-11-17)
-==================
-
-- Add support for building arm64 wheels on macOS.
-
-
-5.5.1 (2022-11-03)
-==================
-
-- Add support for final Python 3.11 release.
-
-
-5.5.0 (2022-10-10)
-==================
-
-- Add support for Python 3.10 and 3.11 (as of 3.11.0rc2).
-
-- Add missing Trove classifier showing support for Python 3.9.
-
-- Add some more entries to ``zope.interface.interfaces.__all__``.
-
-- Disable unsafe math optimizations in C code.  See `pull request 262
-  `_.
-
-
-5.4.0 (2021-04-15)
-==================
-
-- Make the C implementation of the ``__providedBy__`` descriptor stop
-  ignoring all errors raised when accessing the instance's
-  ``__provides__``. Now it behaves like the Python version and only
-  catches ``AttributeError``. The previous behaviour could lead to
-  crashing the interpreter in cases of recursion and errors. See
-  `issue 239 `_.
-
-- Update the ``repr()`` and ``str()`` of various objects to be shorter
-  and more informative. In many cases, the ``repr()`` is now something
-  that can be evaluated to produce an equal object. For example, what
-  was previously printed as ```` is now
-  shown as ``classImplements(list, IMutableSequence, IIterable)``. See
-  `issue 236 `_.
-
-- Make ``Declaration.__add__`` (as in ``implementedBy(Cls) +
-  ISomething``) try harder to preserve a consistent resolution order
-  when the two arguments share overlapping pieces of the interface
-  inheritance hierarchy. Previously, the right hand side was always
-  put at the end of the resolution order, which could easily produce
-  invalid orders. See `issue 193
-  `_.
-
-5.3.0 (2020-03-21)
-==================
-
-- No changes from 5.3.0a1
-
-
-5.3.0a1 (2021-03-18)
-====================
-
-- Improve the repr of ``zope.interface.Provides`` to remove ambiguity
-  about what is being provided. This is especially helpful diagnosing
-  IRO issues.
-
-- Allow subclasses of ``BaseAdapterRegistry`` (including
-  ``AdapterRegistry`` and ``VerifyingAdapterRegistry``) to have
-  control over the data structures. This allows persistent
-  implementations such as those based on ZODB to choose more scalable
-  options (e.g., BTrees instead of dicts). See `issue 224
-  `_.
-
-- Fix a reference counting issue in ``BaseAdapterRegistry`` that could
-  lead to references to interfaces being kept around even when all
-  utilities/adapters/subscribers providing that interface have been
-  removed. This is mostly an issue for persistent implementations.
-  Note that this only corrects the issue moving forward, it does not
-  solve any already corrupted reference counts. See `issue 227
-  `_.
-
-- Add the method ``BaseAdapterRegistry.rebuild()``. This can be used
-  to fix the reference counting issue mentioned above, as well as to
-  update the data structures when custom data types have changed.
-
-- Add the interface method ``IAdapterRegistry.subscribed()`` and
-  implementation ``BaseAdapterRegistry.subscribed()`` for querying
-  directly registered subscribers. See `issue 230
-  `_.
-
-- Add the maintenance method
-  ``Components.rebuildUtilityRegistryFromLocalCache()``. Most users
-  will not need this, but it can be useful if the ``Components.utilities``
-  registry is suspected to be out of sync with the ``Components``
-  object itself (this might happen to persistent ``Components``
-  implementations in the face of bugs).
-
-- Fix the ``Provides`` and ``ClassProvides`` descriptors to stop
-  allowing redundant interfaces (those already implemented by the
-  underlying class or meta class) to produce an inconsistent
-  resolution order. This is similar to the change in ``@implementer``
-  in 5.1.0, and resolves inconsistent resolution orders with
-  ``zope.proxy`` and ``zope.location``. See `issue 207
-  `_.
-
-5.2.0 (2020-11-05)
-==================
-
-- Add documentation section ``Persistency and Equality``
-  (`#218 `_).
-
-- Create arm64 wheels.
-
-- Add support for Python 3.9.
-
-
-5.1.2 (2020-10-01)
-==================
-
-- Make sure to call each invariant only once when validating invariants.
-  Previously, invariants could be called multiple times because when an
-  invariant is defined in an interface, it's found by in all interfaces
-  inheriting from that interface.  See `pull request 215
-  `_.
-
-5.1.1 (2020-09-30)
-==================
-
-- Fix the method definitions of ``IAdapterRegistry.subscribe``,
-  ``subscriptions`` and ``subscribers``. Previously, they all were
-  defined to accept a ``name`` keyword argument, but subscribers have
-  no names and the implementation of that interface did not accept
-  that argument. See `issue 208
-  `_.
-
-- Fix a potential reference leak in the C optimizations. Previously,
-  applications that dynamically created unique ``Specification``
-  objects (e.g., used ``@implementer`` on dynamic classes) could
-  notice a growth of small objects over time leading to increased
-  garbage collection times. See `issue 216
-  `_.
-
-  .. caution::
-
-     This leak could prevent interfaces used as the bases of
-     other interfaces from being garbage collected. Those interfaces
-     will now be collected.
-
-     One way in which this would manifest was that ``weakref.ref``
-     objects (and things built upon them, like
-     ``Weak[Key|Value]Dictionary``) would continue to have access to
-     the original object even if there were no other visible
-     references to Python and the original object *should* have been
-     collected. This could be especially problematic for the
-     ``WeakKeyDictionary`` when combined with dynamic or local
-     (created in the scope of a function) interfaces, since interfaces
-     are hashed based just on their name and module name. See the
-     linked issue for an example of a resulting ``KeyError``.
-
-     Note that such potential errors are not new, they are just once
-     again a possibility.
-
-5.1.0 (2020-04-08)
-==================
-
-- Make ``@implementer(*iface)`` and ``classImplements(cls, *iface)``
-  ignore redundant interfaces. If the class already implements an
-  interface through inheritance, it is no longer redeclared
-  specifically for *cls*. This solves many instances of inconsistent
-  resolution orders, while still allowing the interface to be declared
-  for readability and maintenance purposes. See `issue 199
-  `_.
-
-- Remove all bare ``except:`` statements. Previously, when accessing
-  special attributes such as ``__provides__``, ``__providedBy__``,
-  ``__class__`` and ``__conform__``, this package wrapped such access
-  in a bare ``except:`` statement, meaning that many errors could pass
-  silently; typically this would result in a fallback path being taken
-  and sometimes (like with ``providedBy()``) the result would be
-  non-sensical. This is especially true when those attributes are
-  implemented with descriptors. Now, only ``AttributeError`` is
-  caught. This makes errors more obvious.
-
-  Obviously, this means that some exceptions will be propagated
-  differently than before. In particular, ``RuntimeError`` raised by
-  Acquisition in the case of circular containment will now be
-  propagated. Previously, when adapting such a broken object, a
-  ``TypeError`` would be the common result, but now it will be a more
-  informative ``RuntimeError``.
-
-  In addition, ZODB errors like ``POSKeyError`` could now be
-  propagated where previously they would ignored by this package.
-
-  See `issue 200 `_.
-
-- Require that the second argument (*bases*) to ``InterfaceClass`` is
-  a tuple. This only matters when directly using ``InterfaceClass`` to
-  create new interfaces dynamically. Previously, an individual
-  interface was allowed, but did not work correctly. Now it is
-  consistent with ``type`` and requires a tuple.
-
-- Let interfaces define custom ``__adapt__`` methods. This implements
-  the other side of the :pep:`246` adaptation protocol: objects being
-  adapted could already implement ``__conform__`` if they know about
-  the interface, and now interfaces can implement ``__adapt__`` if
-  they know about particular objects. There is no performance penalty
-  for interfaces that do not supply custom ``__adapt__`` methods.
-
-  This includes the ability to add new methods, or override existing
-  interface methods using the new ``@interfacemethod`` decorator.
-
-  See `issue 3 `_.
-
-- Make the internal singleton object returned by APIs like
-  ``implementedBy`` and ``directlyProvidedBy`` for objects that
-  implement or provide no interfaces more immutable. Previously an
-  internal cache could be mutated. See `issue 204
-  `_.
-
-5.0.2 (2020-03-30)
-==================
-
-- Ensure that objects that implement no interfaces (such as direct
-  subclasses of ``object``) still include ``Interface`` itself in
-  their ``__iro___`` and ``__sro___``. This fixes adapter registry
-  lookups for such objects when the adapter is registered for
-  ``Interface``. See `issue 197
-  `_.
-
-
-5.0.1 (2020-03-21)
-==================
-
-- Ensure the resolution order for ``InterfaceClass`` is consistent.
-  See `issue 192 `_.
-
-- Ensure the resolution order for ``collections.OrderedDict`` is
-  consistent on CPython 2. (It was already consistent on Python 3 and PyPy).
-
-- Fix the handling of the ``ZOPE_INTERFACE_STRICT_IRO`` environment
-  variable. Previously, ``ZOPE_INTERFACE_STRICT_RO`` was read, in
-  contrast with the documentation. See `issue 194
-  `_.
-
-
-5.0.0 (2020-03-19)
-==================
-
-- Make an internal singleton object returned by APIs like
-  ``implementedBy`` and ``directlyProvidedBy`` immutable. Previously,
-  it was fully mutable and allowed changing its ``__bases___``. That
-  could potentially lead to wrong results in pathological corner
-  cases. See `issue 158
-  `_.
-
-- Support the ``PURE_PYTHON`` environment variable at runtime instead
-  of just at wheel build time. A value of 0 forces the C extensions to
-  be used (even on PyPy) failing if they aren't present. Any other
-  value forces the Python implementation to be used, ignoring the C
-  extensions. See `PR 151 `_.
-
-- Cache the result of ``__hash__`` method in ``InterfaceClass`` as a
-  speed optimization. The method is called very often (i.e several
-  hundred thousand times during Plone 5.2 startup). Because the hash value never
-  changes it can be cached. This improves test performance from 0.614s
-  down to 0.575s (1.07x faster). In a real world Plone case a reindex
-  index came down from 402s to 320s (1.26x faster). See `PR 156
-  `_.
-
-- Change the C classes ``SpecificationBase`` and its subclass
-  ``ClassProvidesBase`` to store implementation attributes in their structures
-  instead of their instance dictionaries. This eliminates the use of
-  an undocumented private C API function, and helps make some
-  instances require less memory. See `PR 154 `_.
-
-- Reduce memory usage in other ways based on observations of usage
-  patterns in Zope (3) and Plone code bases.
-
-  - Specifications with no dependents are common (more than 50%) so
-    avoid allocating a ``WeakKeyDictionary`` unless we need it.
-  - Likewise, tagged values are relatively rare, so don't allocate a
-    dictionary to hold them until they are used.
-  - Use ``__slots___`` or the C equivalent ``tp_members`` in more
-    common places. Note that this removes the ability to set arbitrary
-    instance variables on certain objects.
-    See `PR 155 `_.
-
-  The changes in this release resulted in a 7% memory reduction after
-  loading about 6,000 modules that define about 2,200 interfaces.
-
-  .. caution::
-
-     Details of many private attributes have changed, and external use
-     of those private attributes may break. In particular, the
-     lifetime and default value of ``_v_attrs`` has changed.
-
-- Remove support for hashing uninitialized interfaces. This could only
-  be done by subclassing ``InterfaceClass``. This has generated a
-  warning since it was first added in 2011 (3.6.5). Please call the
-  ``InterfaceClass`` constructor or otherwise set the appropriate
-  fields in your subclass before attempting to hash or sort it. See
-  `issue 157 `_.
-
-- Remove unneeded override of the ``__hash__`` method from
-  ``zope.interface.declarations.Implements``. Watching a reindex index
-  process in ZCatalog with on a Py-Spy after 10k samples the time for
-  ``.adapter._lookup`` was reduced from 27.5s to 18.8s (~1.5x faster).
-  Overall reindex index time shrunk from 369s to 293s (1.26x faster).
-  See `PR 161
-  `_.
-
-- Make the Python implementation closer to the C implementation by
-  ignoring all exceptions, not just ``AttributeError``, during (parts
-  of) interface adaptation. See `issue 163
-  `_.
-
-- Micro-optimization in ``.adapter._lookup`` , ``.adapter._lookupAll``
-  and ``.adapter._subscriptions``: By loading ``components.get`` into
-  a local variable before entering the loop a bytcode "LOAD_FAST 0
-  (components)" in the loop can be eliminated. In Plone, while running
-  all tests, average speedup of the "owntime" of ``_lookup`` is ~5x.
-  See `PR 167
-  `_.
-
-- Add ``__all__`` declarations to all modules. This helps tools that
-  do auto-completion and documentation and results in less cluttered
-  results. Wildcard ("*") are not recommended and may be affected. See
-  `issue 153
-  `_.
-
-- Fix ``verifyClass`` and ``verifyObject`` for builtin types like
-  ``dict`` that have methods taking an optional, unnamed argument with
-  no default value like ``dict.pop``. On PyPy3, the verification is
-  strict, but on PyPy2 (as on all versions of CPython) those methods
-  cannot be verified and are ignored. See `issue 118
-  `_.
-
-- Update the common interfaces ``IEnumerableMapping``,
-  ``IExtendedReadMapping``, ``IExtendedWriteMapping``,
-  ``IReadSequence`` and ``IUniqueMemberWriteSequence`` to no longer
-  require methods that were removed from Python 3 on Python 3, such as
-  ``__setslice___``. Now, ``dict``, ``list`` and ``tuple`` properly
-  verify as ``IFullMapping``, ``ISequence`` and ``IReadSequence,``
-  respectively on all versions of Python.
-
-- Add human-readable ``__str___`` and ``__repr___`` to ``Attribute``
-  and ``Method``. These contain the name of the defining interface
-  and the attribute. For methods, it also includes the signature.
-
-- Change the error strings raised by ``verifyObject`` and
-  ``verifyClass``. They now include more human-readable information
-  and exclude extraneous lines and spaces. See `issue 170
-  `_.
-
-  .. caution:: This will break consumers (such as doctests) that
-               depended on the exact error messages.
-
-- Make ``verifyObject`` and ``verifyClass`` report all errors, if the
-  candidate object has multiple detectable violations. Previously they
-  reported only the first error. See `issue
-  `_.
-
-  Like the above, this will break consumers depending on the exact
-  output of error messages if more than one error is present.
-
-- Add ``zope.interface.common.collections``,
-  ``zope.interface.common.numbers``, and ``zope.interface.common.io``.
-  These modules define interfaces based on the ABCs defined in the
-  standard library ``collections.abc``, ``numbers`` and ``io``
-  modules, respectively. Importing these modules will make the
-  standard library concrete classes that are registered with those
-  ABCs declare the appropriate interface. See `issue 138
-  `_.
-
-- Add ``zope.interface.common.builtins``. This module defines
-  interfaces of common builtin types, such as ``ITextString`` and
-  ``IByteString``, ``IDict``, etc. These interfaces extend the
-  appropriate interfaces from ``collections`` and ``numbers``, and the
-  standard library classes implement them after importing this module.
-  This is intended as a replacement for third-party packages like
-  `dolmen.builtins `_.
-  See `issue 138 `_.
-
-- Make ``providedBy()`` and ``implementedBy()`` respect ``super``
-  objects. For instance, if class ``Derived`` implements ``IDerived``
-  and extends ``Base`` which in turn implements ``IBase``, then
-  ``providedBy(super(Derived, derived))`` will return ``[IBase]``.
-  Previously it would have returned ``[IDerived]`` (in general, it
-  would previously have returned whatever would have been returned
-  without ``super``).
-
-  Along with this change, adapter registries will unpack ``super``
-  objects into their ``__self___`` before passing it to the factory.
-  Together, this means that ``component.getAdapter(super(Derived,
-  self), ITarget)`` is now meaningful.
-
-  See `issue 11 `_.
-
-- Fix a potential interpreter crash in the low-level adapter
-  registry lookup functions. See issue 11.
-
-- Adopt Python's standard `C3 resolution order
-  `_ to compute the
-  ``__iro__`` and ``__sro__`` of interfaces, with tweaks to support
-  additional cases that are common in interfaces but disallowed for
-  Python classes. Previously, an ad-hoc ordering that made no
-  particular guarantees was used.
-
-  This has many beneficial properties, including the fact that base
-  interface and base classes tend to appear near the end of the
-  resolution order instead of the beginning. The resolution order in
-  general should be more predictable and consistent.
-
-  .. caution::
-     In some cases, especially with complex interface inheritance
-     trees or when manually providing or implementing interfaces, the
-     resulting IRO may be quite different. This may affect adapter
-     lookup.
-
-  The C3 order enforces some constraints in order to be able to
-  guarantee a sensible ordering. Older versions of zope.interface did
-  not impose similar constraints, so it was possible to create
-  interfaces and declarations that are inconsistent with the C3
-  constraints. In that event, zope.interface will still produce a
-  resolution order equal to the old order, but it won't be guaranteed
-  to be fully C3 compliant. In the future, strict enforcement of C3
-  order may be the default.
-
-  A set of environment variables and module constants allows
-  controlling several aspects of this new behaviour. It is possible to
-  request warnings about inconsistent resolution orders encountered,
-  and even to forbid them. Differences between the C3 resolution order
-  and the previous order can be logged, and, in extreme cases, the
-  previous order can still be used (this ability will be removed in
-  the future). For details, see the documentation for
-  ``zope.interface.ro``.
-
-- Make inherited tagged values in interfaces respect the resolution
-  order (``__iro__``), as method and attribute lookup does. Previously
-  tagged values could give inconsistent results. See `issue 190
-  `_.
-
-- Add ``getDirectTaggedValue`` (and related methods) to interfaces to
-  allow accessing tagged values irrespective of inheritance. See
-  `issue 190
-  `_.
-
-- Ensure that ``Interface`` is always the last item in the ``__iro__``
-  and ``__sro__``. This is usually the case, but if classes that do
-  not implement any interfaces are part of a class inheritance
-  hierarchy, ``Interface`` could be assigned too high a priority.
-  See `issue 8 `_.
-
-- Implement sorting, equality, and hashing in C for ``Interface``
-  objects. In micro benchmarks, this makes those operations 40% to 80%
-  faster. This translates to a 20% speed up in querying adapters.
-
-  Note that this changes certain implementation details. In
-  particular, ``InterfaceClass`` now has a non-default metaclass, and
-  it is enforced that ``__module__`` in instances of
-  ``InterfaceClass`` is read-only.
-
-  See `PR 183 `_.
-
-
-4.7.2 (2020-03-10)
-==================
-
-- Remove deprecated use of setuptools features.  See `issue 30
-  `_.
-
-
-4.7.1 (2019-11-11)
-==================
-
-- Use Python 3 syntax in the documentation.  See `issue 119
-  `_.
-
-
-4.7.0 (2019-11-11)
-==================
-
-- Drop support for Python 3.4.
-
-- Change ``queryTaggedValue``, ``getTaggedValue``,
-  ``getTaggedValueTags`` in interfaces. They now include inherited
-  values by following ``__bases__``. See `PR 144
-  `_.
-
-  .. caution:: This may be a breaking change.
-
-- Add support for Python 3.8.
-
-
-4.6.0 (2018-10-23)
-==================
-
-- Add support for Python 3.7
-
-- Fix ``verifyObject`` for class objects with staticmethods on
-  Python 3. See `issue 126
-  `_.
-
-
-4.5.0 (2018-04-19)
-==================
-
-- Drop support for 3.3, avoid accidental dependence breakage via setup.py.
-  See `PR 110 `_.
-- Allow registering and unregistering instance methods as listeners.
-  See `issue 12 `_
-  and `PR 102 `_.
-- Synchronize and simplify zope/__init__.py. See `issue 114
-  `_
-
-
-4.4.3 (2017-09-22)
-==================
-
-- Avoid exceptions when the ``__annotations__`` attribute is added to
-  interface definitions with Python 3.x type hints. See `issue 98
-  `_.
-- Fix the possibility of a rare crash in the C extension when
-  deallocating items. See `issue 100
-  `_.
-
-
-4.4.2 (2017-06-14)
-==================
-
-- Fix a regression storing
-  ``zope.component.persistentregistry.PersistentRegistry`` instances.
-  See `issue 85 `_.
-
-- Fix a regression that could lead to the utility registration cache
-  of ``Components`` getting out of sync. See `issue 93
-  `_.
-
-4.4.1 (2017-05-13)
-==================
-
-- Simplify the caching of utility-registration data. In addition to
-  simplification, avoids spurious test failures when checking for
-  leaks in tests with persistent registries. See `pull 84
-  `_.
-
-- Raise ``ValueError`` when non-text names are passed to adapter registry
-  methods:  prevents corruption of lookup caches.
-
-4.4.0 (2017-04-21)
-==================
-
-- Avoid a warning from the C compiler.
-  (https://github.com/zopefoundation/zope.interface/issues/71)
-
-- Add support for Python 3.6.
-
-4.3.3 (2016-12-13)
-==================
-
-- Correct typos and ReST formatting errors in documentation.
-
-- Add API documentation for the adapter registry.
-
-- Ensure that the ``LICENSE.txt`` file is included in built wheels.
-
-- Fix C optimizations broken on Py3k.  See the Python bug at:
-  http://bugs.python.org/issue15657
-  (https://github.com/zopefoundation/zope.interface/issues/60)
-
-
-4.3.2 (2016-09-05)
-==================
-
-- Fix equality testing of ``implementedBy`` objects and proxies.
-  (https://github.com/zopefoundation/zope.interface/issues/55)
-
-
-4.3.1 (2016-08-31)
-==================
-
-- Support Components subclasses that are not hashable.
-  (https://github.com/zopefoundation/zope.interface/issues/53)
-
-
-4.3.0 (2016-08-31)
-==================
-
-- Add the ability to sort the objects returned by ``implementedBy``.
-  This is compatible with the way interface classes sort so they can
-  be used together in ordered containers like BTrees.
-  (https://github.com/zopefoundation/zope.interface/issues/42)
-
-- Make ``setuptools`` a hard dependency of ``setup.py``.
-  (https://github.com/zopefoundation/zope.interface/issues/13)
-
-- Change a linear algorithm (O(n)) in ``Components.registerUtility`` and
-  ``Components.unregisterUtility`` into a dictionary lookup (O(1)) for
-  hashable components. This substantially improves the time taken to
-  manipulate utilities in large registries at the cost of some
-  additional memory usage. (https://github.com/zopefoundation/zope.interface/issues/46)
-
-
-4.2.0 (2016-06-10)
-==================
-
-- Add support for Python 3.5
-
-- Drop support for Python 2.6 and 3.2.
-
-
-4.1.3 (2015-10-05)
-==================
-
-- Fix installation without a C compiler on Python 3.5
-  (https://github.com/zopefoundation/zope.interface/issues/24).
-
-
-4.1.2 (2014-12-27)
-==================
-
-- Add support for PyPy3.
-
-- Remove unittest assertions deprecated in Python3.x.
-
-- Add ``zope.interface.document.asReStructuredText``, which formats the
-  generated text for an interface using ReST double-backtick markers.
-
-
-4.1.1 (2014-03-19)
-==================
-
-- Add support for Python 3.4.
-
-
-4.1.0 (2014-02-05)
-==================
-
-- Update ``boostrap.py`` to version 2.2.
-
-- Add ``@named(name)`` declaration, that specifies the component name, so it
-  does not have to be passed in during registration.
-
-
-4.0.5 (2013-02-28)
-==================
-
-- Fix a bug where a decorated method caused false positive failures on
-  ``verifyClass()``.
-
-
-4.0.4 (2013-02-21)
-==================
-
-- Fix a bug that was revealed by porting zope.traversing. During a loop, the
-  loop body modified a weakref dict causing a ``RuntimeError`` error.
-
-4.0.3 (2012-12-31)
-==================
-
-- Fleshed out PyPI Trove classifiers.
-
-4.0.2 (2012-11-21)
-==================
-
-- Add support for Python 3.3.
-
-- Restored ability to install the package in the absence of ``setuptools``.
-
-- LP #1055223:  Fix test which depended on dictionary order and failed randomly
-  in Python 3.3.
-
-4.0.1 (2012-05-22)
-==================
-
-- Drop explicit ``DeprecationWarnings`` for "class advice" APIS (these
-  APIs are still deprecated under Python 2.x, and still raise an exception
-  under Python 3.x, but no longer cause a warning to be emitted under
-  Python 2.x).
-
-4.0.0 (2012-05-16)
-==================
-
-- Automated build of Sphinx HTML docs and running doctest snippets via tox.
-
-- Deprecate the "class advice" APIs from ``zope.interface.declarations``:
-  ``implements``, ``implementsOnly``, and ``classProvides``.  In their place,
-  prefer the equivalent class decorators: ``@implementer``,
-  ``@implementer_only``, and ``@provider``.  Code which uses the deprecated
-  APIs will not work as expected under Py3k.
-
-- Remove use of '2to3' and associated fixers when installing under Py3k.
-  The code is now in a "compatible subset" which supports Python 2.6, 2.7,
-  and 3.2, including PyPy 1.8 (the version compatible with the 2.7 language
-  spec).
-
-- Drop explicit support for Python 2.4 / 2.5 / 3.1.
-
-- Add support for PyPy.
-
-- Add support for continuous integration using ``tox`` and ``jenkins``.
-
-- Add 'setup.py dev' alias (runs ``setup.py develop`` plus installs
-  ``nose`` and ``coverage``).
-
-- Add 'setup.py docs' alias (installs ``Sphinx`` and dependencies).
-
-- Replace all unittest coverage previously accomplished via doctests with
-  unittests.  The doctests have been moved into a ``docs`` section, managed
-  as a Sphinx collection.
-
-- LP #910987:  Ensure that the semantics of the ``lookup`` method of
-  ``zope.interface.adapter.LookupBase`` are the same in both the C and
-  Python implementations.
-
-- LP #900906:  Avoid exceptions due to tne new ``__qualname__`` attribute
-  added in Python 3.3 (see PEP 3155 for rationale).  Thanks to Antoine
-  Pitrou for the patch.
-
-3.8.0 (2011-09-22)
-==================
-
-- New module ``zope.interface.registry``.  This is code moved from
-  ``zope.component.registry`` which implements a basic nonperistent component
-  registry as ``zope.interface.registry.Components``.  This class was moved
-  from ``zope.component`` to make porting systems (such as Pyramid) that rely
-  only on a basic component registry to Python 3 possible without needing to
-  port the entirety of the ``zope.component`` package.  Backwards
-  compatibility import shims have been left behind in ``zope.component``, so
-  this change will not break any existing code.
-
-- New ``tests_require`` dependency: ``zope.event`` to test events sent by
-  Components implementation.  The ``zope.interface`` package does not have a
-  hard dependency on ``zope.event``, but if ``zope.event`` is importable, it
-  will send component registration events when methods of an instance of
-  ``zope.interface.registry.Components`` are called.
-
-- New interfaces added to support ``zope.interface.registry.Components``
-  addition: ``ComponentLookupError``, ``Invalid``, ``IObjectEvent``,
-  ``ObjectEvent``, ``IComponentLookup``, ``IRegistration``,
-  ``IUtilityRegistration``, ``IAdapterRegistration``,
-  ``ISubscriptionAdapterRegistration``, ``IHandlerRegistration``,
-  ``IRegistrationEvent``, ``RegistrationEvent``, ``IRegistered``,
-  ``Registered``, ``IUnregistered``, ``Unregistered``,
-  ``IComponentRegistry``, and ``IComponents``.
-
-- No longer Python 2.4 compatible (tested under 2.5, 2.6, 2.7, and 3.2).
-
-3.7.0 (2011-08-13)
-==================
-
-- Move changes from 3.6.2 - 3.6.5 to a new 3.7.x release line.
-
-3.6.7 (2011-08-20)
-==================
-
-- Fix sporadic failures on x86-64 platforms in tests of rich comparisons
-  of interfaces.
-
-3.6.6 (2011-08-13)
-==================
-
-- LP #570942:  Now correctly compare interfaces  from different modules but
-  with the same names.
-
-  N.B.: This is a less intrusive / destabilizing fix than the one applied in
-  3.6.3:  we only fix the underlying cmp-alike function, rather than adding
-  the other "rich comparison" functions.
-
-- Revert to software as released with 3.6.1 for "stable" 3.6 release branch.
-
-3.6.5 (2011-08-11)
-==================
-
-- LP #811792:  work around buggy behavior in some subclasses of
-  ``zope.interface.interface.InterfaceClass``, which invoke ``__hash__``
-  before initializing ``__module__`` and ``__name__``.  The workaround
-  returns a fixed constant hash in such cases, and issues a ``UserWarning``.
-
-- LP #804832:  Under PyPy, ``zope.interface`` should not build its C
-  extension.  Also, prevent attempting to build it under Jython.
-
-- Add a tox.ini for easier xplatform testing.
-
-- Fix testing deprecation warnings issued when tested under Py3K.
-
-3.6.4 (2011-07-04)
-==================
-
-- LP 804951:  InterfaceClass instances were unhashable under Python 3.x.
-
-3.6.3 (2011-05-26)
-==================
-
-- LP #570942:  Now correctly compare interfaces  from different modules but
-  with the same names.
-
-3.6.2 (2011-05-17)
-==================
-
-- Moved detailed documentation out-of-line from PyPI page, linking instead to
-  http://docs.zope.org/zope.interface .
-
-- Fixes for small issues when running tests under Python 3.2 using
-  ``zope.testrunner``.
-
-- LP # 675064:  Specify return value type for C optimizations module init
-  under Python 3:  undeclared value caused warnings, and segfaults on some
-  64 bit architectures.
-
-- setup.py now raises RuntimeError if you don't have Distutils installed when
-  running under Python 3.
-
-3.6.1 (2010-05-03)
-==================
-
-- A non-ASCII character in the changelog made 3.6.0 uninstallable on
-  Python 3 systems with another default encoding than UTF-8.
-
-- Fix compiler warnings under GCC 4.3.3.
-
-3.6.0 (2010-04-29)
-==================
-
-- LP #185974:  Clear the cache used by ``Specificaton.get`` inside
-  ``Specification.changed``.  Thanks to Jacob Holm for the patch.
-
-- Add support for Python 3.1. Contributors:
-
-    Lennart Regebro
-    Martin v Loewis
-    Thomas Lotze
-    Wolfgang Schnerring
-
-  The 3.1 support is completely backwards compatible. However, the implements
-  syntax used under Python 2.X does not work under 3.X, since it depends on
-  how metaclasses are implemented and this has changed. Instead it now supports
-  a decorator syntax (also under Python 2.X)::
-
-    class Foo:
-        implements(IFoo)
-        ...
-
-  can now also be written::
-
-    @implementer(IFoo):
-    class Foo:
-        ...
-
-  There are 2to3 fixers available to do this change automatically in the
-  zope.fixers package.
-
-- Python 2.3 is no longer supported.
-
-
-3.5.4 (2009-12-23)
-==================
-
-- Use the standard Python doctest module instead of zope.testing.doctest, which
-  has been deprecated.
-
-
-3.5.3 (2009-12-08)
-==================
-
-- Fix an edge case: make providedBy() work when a class has '__provides__' in
-  its __slots__ (see http://thread.gmane.org/gmane.comp.web.zope.devel/22490)
-
-
-3.5.2 (2009-07-01)
-==================
-
-- BaseAdapterRegistry.unregister, unsubscribe: Remove empty portions of
-  the data structures when something is removed.  This avoids leaving
-  references to global objects (interfaces) that may be slated for
-  removal from the calling application.
-
-
-3.5.1 (2009-03-18)
-==================
-
-- verifyObject: use getattr instead of hasattr to test for object attributes
-  in order to let exceptions other than AttributeError raised by properties
-  propagate to the caller
-
-- Add Sphinx-based documentation building to the package buildout
-  configuration. Use the ``bin/docs`` command after buildout.
-
-- Improve package description a bit. Unify changelog entries formatting.
-
-- Change package's mailing list address to zope-dev at zope.org as
-  zope3-dev at zope.org is now retired.
-
-
-3.5.0 (2008-10-26)
-==================
-
-- Fix declaration of _zope_interface_coptimizations, it's not a top level
-  package.
-
-- Add a DocTestSuite for odd.py module, so their tests are run.
-
-- Allow to bootstrap on Jython.
-
-- Fix https://bugs.launchpad.net/zope3/3.3/+bug/98388: ISpecification
-  was missing a declaration for __iro__.
-
-- Add optional code optimizations support, which allows the building
-  of C code optimizations to fail (Jython).
-
-- Replace `_flatten` with a non-recursive implementation, effectively making
-  it 3x faster.
-
-
-3.4.1 (2007-10-02)
-==================
-
-- Fix a setup bug that prevented installation from source on systems
-  without setuptools.
-
-
-3.4.0 (2007-07-19)
-==================
-
-- Final release for 3.4.0.
-
-
-3.4.0b3 (2007-05-22)
-====================
-
-
-- When checking whether an object is already registered, use identity
-  comparison, to allow adding registering with picky custom comparison methods.
-
-
-3.3.0.1 (2007-01-03)
-====================
-
-- Made a reference to OverflowWarning, which disappeared in Python
-  2.5, conditional.
-
-
-3.3.0 (2007/01/03)
-==================
-
-New Features
-------------
-
-- Refactor the adapter-lookup algorithim to make it much simpler and faster.
-
-  Also, implement more of the adapter-lookup logic in C, making
-  debugging of application code easier, since there is less
-  infrastructre code to step through.
-
-- Treat objects without interface declarations as if they
-  declared that they provide ``zope.interface.Interface``.
-
-- Add a number of richer new adapter-registration interfaces
-  that provide greater control and introspection.
-
-- Add a new interface decorator to zope.interface that allows the
-  setting of tagged values on an interface at definition time (see
-  zope.interface.taggedValue).
-
-Bug Fixes
----------
-
-- A bug in multi-adapter lookup sometimes caused incorrect adapters to
-  be returned.
-
-
-3.2.0.2 (2006-04-15)
-====================
-
-- Fix packaging bug:  'package_dir' must be a *relative* path.
-
-
-3.2.0.1 (2006-04-14)
-====================
-
-- Packaging change:  suppress inclusion of 'setup.cfg' in 'sdist' builds.
-
-
-3.2.0 (2006-01-05)
-==================
-
-- Corresponds to the version of the zope.interface package shipped as part of
-  the Zope 3.2.0 release.
-
-
-3.1.0 (2005-10-03)
-==================
-
-- Corresponds to the version of the zope.interface package shipped as part of
-  the Zope 3.1.0 release.
-
-- Made attribute resolution order consistent with component lookup order,
-  i.e. new-style class MRO semantics.
-
-- Deprecate 'isImplementedBy' and 'isImplementedByInstancesOf' APIs in
-  favor of 'implementedBy' and 'providedBy'.
-
-
-3.0.1 (2005-07-27)
-==================
-
-- Corresponds to the version of the zope.interface package shipped as part of
-  the Zope X3.0.1 release.
-
-- Fix a bug reported by James Knight, which caused adapter registries
-  to fail occasionally to reflect declaration changes.
-
-
-3.0.0 (2004-11-07)
-==================
-
-- Corresponds to the version of the zope.interface package shipped as part of
-  the Zope X3.0.0 release.
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/RECORD b/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/RECORD
deleted file mode 100644
index cef7194..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/RECORD
+++ /dev/null
@@ -1,110 +0,0 @@
-zope.interface-7.2-py3.12-nspkg.pth,sha256=_l6EZJaefCi1yytmDbFQGX_jfS2gAtFyaDmlK1uFLec,457
-zope.interface-7.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
-zope.interface-7.2.dist-info/LICENSE.txt,sha256=PmcdsR32h1FswdtbPWXkqjg-rKPCDOo_r1Og9zNdCjw,2070
-zope.interface-7.2.dist-info/METADATA,sha256=N4E3tgjdYPv_E45EFOzPPDnWZci6rZGf3VsuxWL0Deo,44362
-zope.interface-7.2.dist-info/RECORD,,
-zope.interface-7.2.dist-info/WHEEL,sha256=RYYG1U-eCe8R30LHVEMqYNmIvio2ucm3qxdncXVlgow,224
-zope.interface-7.2.dist-info/namespace_packages.txt,sha256=QpUHvpO4wIuZDeEgKY8qZCtD-tAukB0fn_f6utzlb98,5
-zope.interface-7.2.dist-info/top_level.txt,sha256=QpUHvpO4wIuZDeEgKY8qZCtD-tAukB0fn_f6utzlb98,5
-zope/interface/__init__.py,sha256=9Euz0jFaHg3kT84m2HzikMt7s_JIAjM8BlVctyUfNTk,3475
-zope/interface/__pycache__/__init__.cpython-312.pyc,,
-zope/interface/__pycache__/_compat.cpython-312.pyc,,
-zope/interface/__pycache__/_flatten.cpython-312.pyc,,
-zope/interface/__pycache__/adapter.cpython-312.pyc,,
-zope/interface/__pycache__/advice.cpython-312.pyc,,
-zope/interface/__pycache__/declarations.cpython-312.pyc,,
-zope/interface/__pycache__/document.cpython-312.pyc,,
-zope/interface/__pycache__/exceptions.cpython-312.pyc,,
-zope/interface/__pycache__/interface.cpython-312.pyc,,
-zope/interface/__pycache__/interfaces.cpython-312.pyc,,
-zope/interface/__pycache__/registry.cpython-312.pyc,,
-zope/interface/__pycache__/ro.cpython-312.pyc,,
-zope/interface/__pycache__/verify.cpython-312.pyc,,
-zope/interface/_compat.py,sha256=8FPCPdRAl2Mlkc45-FBvuN8i1kvYLEkIionVgjk2AP0,4413
-zope/interface/_flatten.py,sha256=NKviK4ZyLBCjxXvz5voI9pV_ui2SLqUhubbqZkvgEcg,1059
-zope/interface/_zope_interface_coptimizations.c,sha256=oCYrpT2efApCO-EbKs71YXyaSohAbTqdWQ7QEh49SNA,71198
-zope/interface/_zope_interface_coptimizations.cpython-312-x86_64-linux-gnu.so,sha256=RlF9SobBV5d0eSkWa88RIr9skyGz45telYgZQgclEvE,228368
-zope/interface/adapter.py,sha256=XN9PD8OrRmP1ZJy2gPvAMXtiOnKcHL34doH0HaKHguQ,36647
-zope/interface/advice.py,sha256=YftOBzbXuWQ3AuJImMtYv4SYbE7ubJrjodXzTgYR-dk,3918
-zope/interface/common/__init__.py,sha256=ho-q_3jeKVq-jO-5xrN9_Q4PR0o8PDwja5NYsO7qTI0,10644
-zope/interface/common/__pycache__/__init__.cpython-312.pyc,,
-zope/interface/common/__pycache__/builtins.cpython-312.pyc,,
-zope/interface/common/__pycache__/collections.cpython-312.pyc,,
-zope/interface/common/__pycache__/idatetime.cpython-312.pyc,,
-zope/interface/common/__pycache__/interfaces.cpython-312.pyc,,
-zope/interface/common/__pycache__/io.cpython-312.pyc,,
-zope/interface/common/__pycache__/mapping.cpython-312.pyc,,
-zope/interface/common/__pycache__/numbers.cpython-312.pyc,,
-zope/interface/common/__pycache__/sequence.cpython-312.pyc,,
-zope/interface/common/builtins.py,sha256=WRHf0D-xo2yWu4uP0zvpISdfuwBqwFFYiYuPLNiIYvQ,3135
-zope/interface/common/collections.py,sha256=duvGnbFpUHwri5idqhYblEJrdDYuUvL3vIsZtXggQC4,6809
-zope/interface/common/idatetime.py,sha256=sn5ccP9CiQAYzn6mptWf05uInZFp9o_DRu9_MaDXM5c,21039
-zope/interface/common/interfaces.py,sha256=fT2pigpAZuqcm0bqVVNDlvSWtv9oKfsJ73ewrymUpIE,5908
-zope/interface/common/io.py,sha256=if6Yzclu_T7qeUQNsXeIqREqgVTu-rjYB_VGZfYyz3Y,1242
-zope/interface/common/mapping.py,sha256=XI9lO7Uwt_9sWDFyhDIk0Rjcr5nlu7SlD2KDyqdupdw,4687
-zope/interface/common/numbers.py,sha256=D4kUnF5OgAk6CKcxaW86VH_OPLh1OXt_cF6WaOfvjLk,1682
-zope/interface/common/sequence.py,sha256=SYvqSZpKRaX11vCADK6zGn0LqogPQ0u7INbqgTJ4sg8,5531
-zope/interface/common/tests/__init__.py,sha256=Am8tpD6HZQx6pfW7N22-dloC83-dKLA45NiM9Lx7Xss,5553
-zope/interface/common/tests/__pycache__/__init__.cpython-312.pyc,,
-zope/interface/common/tests/__pycache__/basemapping.cpython-312.pyc,,
-zope/interface/common/tests/__pycache__/test_builtins.cpython-312.pyc,,
-zope/interface/common/tests/__pycache__/test_collections.cpython-312.pyc,,
-zope/interface/common/tests/__pycache__/test_idatetime.cpython-312.pyc,,
-zope/interface/common/tests/__pycache__/test_import_interfaces.cpython-312.pyc,,
-zope/interface/common/tests/__pycache__/test_io.cpython-312.pyc,,
-zope/interface/common/tests/__pycache__/test_numbers.cpython-312.pyc,,
-zope/interface/common/tests/basemapping.py,sha256=iitIJEMm7LlS3vQU51RjoN3AeBUNNf0EGLXi_VklJAs,3768
-zope/interface/common/tests/test_builtins.py,sha256=eftbVFY5-e7r310YTuf6LlL1Jl5HJ0EXTWZ2icAmrnY,1485
-zope/interface/common/tests/test_collections.py,sha256=FpnJI74M9E9vAzTeQr_bkYl1eOIIb79b-GkM8aN8Qv0,6066
-zope/interface/common/tests/test_idatetime.py,sha256=qGr8FDbiVuDZHjyDIKcz7Vz6qNfoFzd9eHejMTfIyAg,1923
-zope/interface/common/tests/test_import_interfaces.py,sha256=wCFk-2kc7r-kAeOXZn5th5Qw_6k_-pMvdguk5b4NstM,813
-zope/interface/common/tests/test_io.py,sha256=gYJnFT52De1JAJruKK6dzyQIdLgYdQME9Yn6QTn2QyI,1686
-zope/interface/common/tests/test_numbers.py,sha256=tPrvkFVYa2kSSxf8_j7XYctupfS4BI-ee_jQ5yU8zRM,1395
-zope/interface/declarations.py,sha256=csCgY3nsiTjpkjdHs53DJGoeIGSeI_mUaTISYQB_9dQ,43512
-zope/interface/document.py,sha256=mhSCJoxw7Whl-q-EMSkys--z3C7IyJ6TEsZ3psMqyJE,4139
-zope/interface/exceptions.py,sha256=lW7SnsOT73LZI8w3aRdCRVUubfSy-CGztchnKqv1-5A,8566
-zope/interface/interface.py,sha256=Xl9EzsdJS4zzjAflXYTKwL_AUidwgBbsVDASDjp2HrQ,39770
-zope/interface/interfaces.py,sha256=9abPucc_lYWpELDFt28wnbjRVtQ8pS48srV8toZmLgk,50268
-zope/interface/registry.py,sha256=eDnfUtTFp1z9f-4F-4ZQ9EATLheAYuCP9_coZ3XLdVw,25812
-zope/interface/ro.py,sha256=NeImEPsautGBC1VtQAQ1J1BGXmksw6hoSNWD7gVmEaQ,24577
-zope/interface/tests/__init__.py,sha256=Vu2CALgC5nADbRAZFb99LcDSXECcPCNdJDL-nv_6mZA,4242
-zope/interface/tests/__pycache__/__init__.cpython-312.pyc,,
-zope/interface/tests/__pycache__/advisory_testing.cpython-312.pyc,,
-zope/interface/tests/__pycache__/dummy.cpython-312.pyc,,
-zope/interface/tests/__pycache__/idummy.cpython-312.pyc,,
-zope/interface/tests/__pycache__/m1.cpython-312.pyc,,
-zope/interface/tests/__pycache__/odd.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_adapter.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_advice.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_compile_flags.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_declarations.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_document.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_element.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_exceptions.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_interface.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_interfaces.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_odd_declarations.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_registry.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_ro.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_sorting.cpython-312.pyc,,
-zope/interface/tests/__pycache__/test_verify.cpython-312.pyc,,
-zope/interface/tests/advisory_testing.py,sha256=T2XF0DT8t9zi1JxnvR1u0WXpRtyOn5027VMyEcN7Ldc,900
-zope/interface/tests/dummy.py,sha256=dd_cYIiPvYJDrEMQD0m2cl9SpkVMrQzMMu1yglSrnb8,913
-zope/interface/tests/idummy.py,sha256=ESC_l4UqjCkiCeXWfcphVGtrP7PoNwwTTGzLpp6Doo4,890
-zope/interface/tests/m1.py,sha256=clhSXmtaT8liCnM87Kp0bzAHfxIxr6gUBjXnVuxaUNI,850
-zope/interface/tests/odd.py,sha256=nwjmxbHCFuI2UvY3Pwc7CfkmZWfXsn3oCb7r7C34DxU,2967
-zope/interface/tests/test_adapter.py,sha256=pB3Y_oXXtdtDsKf0BYlvpW281nT1yendxtzWgWp9o_0,80508
-zope/interface/tests/test_advice.py,sha256=gFhlbHvSWuC9kdlBPeXO_8_9ihkSU-ih0pVhoocdp4U,6036
-zope/interface/tests/test_compile_flags.py,sha256=wU3vtmqgzll6HMPbzFErMpORoVghrcZ5krIV4x6rfo4,1290
-zope/interface/tests/test_declarations.py,sha256=7hlSiT33AN4lzZfFigGyAmf6E9ts6-TgIN0jQb0NB04,83091
-zope/interface/tests/test_document.py,sha256=0JIYe0GWvDPkr_IBACPw-8HsHNJyNNHBU_lUHYOXd9M,17220
-zope/interface/tests/test_element.py,sha256=z9Q2hYwPVzMX05NpA_IeiHoAb4qhTiHI57XQI38w4zQ,1120
-zope/interface/tests/test_exceptions.py,sha256=hxceYZyLZghgpxm-ABg1k50-H1CYRSTUGMZyiTrElo8,6445
-zope/interface/tests/test_interface.py,sha256=KhTcp5nM_K2ffiZSTRzvjhag9tZMfc8qvpV-a3OlSBg,92717
-zope/interface/tests/test_interfaces.py,sha256=l4SCfUmVfBO1UoZLsTOOvDyoYUM7Wex3J67uR7taFpQ,4395
-zope/interface/tests/test_odd_declarations.py,sha256=0DBSBIoOUdSRcDnhiScexGhZ2mVydYWnlJOBvny76Uo,7660
-zope/interface/tests/test_registry.py,sha256=8CyxRkJ46ITauSGp86y1gSN4KHvZNVPTVKgjD13aXBk,112599
-zope/interface/tests/test_ro.py,sha256=CvuZne2GdQu0JA4WQObKm8mG-F7__3T4VBINwoj3QQI,14465
-zope/interface/tests/test_sorting.py,sha256=I4P2jvStUzYrNOnIQgkZZs0sTn9BHe7g5RLQlFmTTW4,2051
-zope/interface/tests/test_verify.py,sha256=JnVLFlHGgVn8fC6u-WPW-mDtfmSuDA2PC0sglWuVBjI,19200
-zope/interface/verify.py,sha256=cEaIWPcS6gT97RkQW2SQJxxuUP7wRrwYwsJtXqo8jdE,7333
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/WHEEL b/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/WHEEL
deleted file mode 100644
index 573bc19..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/WHEEL
+++ /dev/null
@@ -1,8 +0,0 @@
-Wheel-Version: 1.0
-Generator: setuptools (73.0.1)
-Root-Is-Purelib: false
-Tag: cp312-cp312-manylinux_2_5_x86_64
-Tag: cp312-cp312-manylinux1_x86_64
-Tag: cp312-cp312-manylinux_2_17_x86_64
-Tag: cp312-cp312-manylinux2014_x86_64
-
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/namespace_packages.txt b/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/namespace_packages.txt
deleted file mode 100644
index 66179d4..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/namespace_packages.txt
+++ /dev/null
@@ -1 +0,0 @@
-zope
diff --git a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/top_level.txt b/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/top_level.txt
deleted file mode 100644
index 66179d4..0000000
--- a/llmlab/lib/python3.12/site-packages/zope.interface-7.2.dist-info/top_level.txt
+++ /dev/null
@@ -1 +0,0 @@
-zope
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__init__.py b/llmlab/lib/python3.12/site-packages/zope/interface/__init__.py
deleted file mode 100644
index 2b8e7eb..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/__init__.py
+++ /dev/null
@@ -1,90 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Interfaces
-
-This package implements the Python "scarecrow" proposal.
-
-The package exports two objects, `Interface` and `Attribute` directly. It also
-exports several helper methods. Interface is used to create an interface with
-a class statement, as in:
-
-  class IMyInterface(Interface):
-    '''Interface documentation
-    '''
-
-    def meth(arg1, arg2):
-        '''Documentation for meth
-        '''
-
-    # Note that there is no self argument
-
-To find out what you can do with interfaces, see the interface
-interface, `IInterface` in the `interfaces` module.
-
-The package has several public modules:
-
-  o `declarations` provides utilities to declare interfaces on objects. It
-    also provides a wide range of helpful utilities that aid in managing
-    declared interfaces. Most of its public names are however imported here.
-
-  o `document` has a utility for documenting an interface as structured text.
-
-  o `exceptions` has the interface-defined exceptions
-
-  o `interfaces` contains a list of all public interfaces for this package.
-
-  o `verify` has utilities for verifying implementations of interfaces.
-
-See the module doc strings for more information.
-"""
-__docformat__ = 'restructuredtext'
-# pylint:disable=wrong-import-position,unused-import
-from zope.interface.interface import Interface
-from zope.interface.interface import _wire
-
-
-# Need to actually get the interface elements to implement the right interfaces
-_wire()
-del _wire
-
-from zope.interface.declarations import Declaration  # isort: skip
-# The following are to make spec pickles cleaner
-from zope.interface.declarations import Provides
-from zope.interface.declarations import alsoProvides
-from zope.interface.declarations import classImplements
-from zope.interface.declarations import classImplementsFirst
-from zope.interface.declarations import classImplementsOnly
-from zope.interface.declarations import directlyProvidedBy
-from zope.interface.declarations import directlyProvides
-from zope.interface.declarations import implementedBy
-from zope.interface.declarations import implementer
-from zope.interface.declarations import implementer_only
-from zope.interface.declarations import moduleProvides
-from zope.interface.declarations import named
-from zope.interface.declarations import noLongerProvides
-from zope.interface.declarations import providedBy
-from zope.interface.declarations import provider
-from zope.interface.exceptions import Invalid
-from zope.interface.interface import Attribute
-from zope.interface.interface import interfacemethod
-from zope.interface.interface import invariant
-from zope.interface.interface import taggedValue
-from zope.interface.interfaces import IInterfaceDeclaration
-
-
-moduleProvides(IInterfaceDeclaration)
-
-__all__ = ('Interface', 'Attribute') + tuple(IInterfaceDeclaration)
-
-assert all(k in globals() for k in __all__)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index cf85516..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/_compat.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/_compat.cpython-312.pyc
deleted file mode 100644
index a3f16cd..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/_compat.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/_flatten.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/_flatten.cpython-312.pyc
deleted file mode 100644
index 07bc2a0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/_flatten.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/adapter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/adapter.cpython-312.pyc
deleted file mode 100644
index 25d79de..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/adapter.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/advice.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/advice.cpython-312.pyc
deleted file mode 100644
index 0b8a9d1..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/advice.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/declarations.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/declarations.cpython-312.pyc
deleted file mode 100644
index a72aa6b..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/declarations.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/document.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/document.cpython-312.pyc
deleted file mode 100644
index a9e9a4b..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/document.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/exceptions.cpython-312.pyc
deleted file mode 100644
index b69ede5..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/exceptions.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/interface.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/interface.cpython-312.pyc
deleted file mode 100644
index 46c68f3..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/interface.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/interfaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/interfaces.cpython-312.pyc
deleted file mode 100644
index c7c3b7f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/interfaces.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/registry.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/registry.cpython-312.pyc
deleted file mode 100644
index 6655fce..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/registry.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/ro.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/ro.cpython-312.pyc
deleted file mode 100644
index 81072e1..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/ro.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/verify.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/verify.cpython-312.pyc
deleted file mode 100644
index 5862d53..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/__pycache__/verify.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/_compat.py b/llmlab/lib/python3.12/site-packages/zope/interface/_compat.py
deleted file mode 100644
index 3803295..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/_compat.py
+++ /dev/null
@@ -1,139 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2006 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""
-Support functions for dealing with differences in platforms, including Python
-versions and implementations.
-
-This file should have no imports from the rest of zope.interface because it is
-used during early bootstrapping.
-"""
-import os
-import sys
-
-
-PY313_OR_OLDER = sys.version_info < (3, 14)
-
-
-def _normalize_name(name):
-    if isinstance(name, bytes):
-        name = str(name, 'ascii')
-    if isinstance(name, str):
-        return name
-    raise TypeError("name must be a string or ASCII-only bytes")
-
-
-PYPY = hasattr(sys, 'pypy_version_info')
-
-
-def _c_optimizations_required():
-    """
-    Return a true value if the C optimizations are required.
-
-    This uses the ``PURE_PYTHON`` variable as documented in `_use_c_impl`.
-    """
-    pure_env = os.environ.get('PURE_PYTHON')
-    require_c = pure_env == "0"
-    return require_c
-
-
-def _c_optimizations_available():
-    """
-    Return the C optimization module, if available, otherwise
-    a false value.
-
-    If the optimizations are required but not available, this
-    raises the ImportError.
-
-    This does not say whether they should be used or not.
-    """
-    catch = () if _c_optimizations_required() else (ImportError,)
-    try:
-        from zope.interface import _zope_interface_coptimizations as c_opt
-        return c_opt
-    except catch:  # pragma: no cover (only Jython doesn't build extensions)
-        return False
-
-
-def _c_optimizations_ignored():
-    """
-    The opposite of `_c_optimizations_required`.
-    """
-    pure_env = os.environ.get('PURE_PYTHON')
-    return pure_env is not None and pure_env != "0"
-
-
-def _should_attempt_c_optimizations():
-    """
-    Return a true value if we should attempt to use the C optimizations.
-
-    This takes into account whether we're on PyPy and the value of the
-    ``PURE_PYTHON`` environment variable, as defined in `_use_c_impl`.
-    """
-    is_pypy = hasattr(sys, 'pypy_version_info')
-
-    if _c_optimizations_required():
-        return True
-    if is_pypy:
-        return False
-    return not _c_optimizations_ignored()
-
-
-def _use_c_impl(py_impl, name=None, globs=None):
-    """
-    Decorator. Given an object implemented in Python, with a name like
-    ``Foo``, import the corresponding C implementation from
-    ``zope.interface._zope_interface_coptimizations`` with the name
-    ``Foo`` and use it instead.
-
-    If the ``PURE_PYTHON`` environment variable is set to any value
-    other than ``"0"``, or we're on PyPy, ignore the C implementation
-    and return the Python version. If the C implementation cannot be
-    imported, return the Python version. If ``PURE_PYTHON`` is set to
-    0, *require* the C implementation (let the ImportError propagate);
-    note that PyPy can import the C implementation in this case (and all
-    tests pass).
-
-    In all cases, the Python version is kept available. in the module
-    globals with the name ``FooPy`` and the name ``FooFallback`` (both
-    conventions have been used; the C implementation of some functions
-    looks for the ``Fallback`` version, as do some of the Sphinx
-    documents).
-
-    Example::
-
-        @_use_c_impl
-        class Foo(object):
-            ...
-    """
-    name = name or py_impl.__name__
-    globs = globs or sys._getframe(1).f_globals
-
-    def find_impl():
-        if not _should_attempt_c_optimizations():
-            return py_impl
-
-        c_opt = _c_optimizations_available()
-        if not c_opt:  # pragma: no cover (Jython doesn't build extensions)
-            return py_impl
-
-        __traceback_info__ = c_opt
-        return getattr(c_opt, name)
-
-    c_impl = find_impl()
-    # Always make available by the FooPy name and FooFallback
-    # name (for testing and documentation)
-    globs[name + 'Py'] = py_impl
-    globs[name + 'Fallback'] = py_impl
-
-    return c_impl
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/_flatten.py b/llmlab/lib/python3.12/site-packages/zope/interface/_flatten.py
deleted file mode 100644
index a2cb86b..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/_flatten.py
+++ /dev/null
@@ -1,36 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Adapter-style interface registry
-
-See Adapter class.
-"""
-from zope.interface import Declaration
-
-
-def _flatten(implements, include_None=0):
-
-    try:
-        r = implements.flattened()
-    except AttributeError:
-        if implements is None:
-            r = ()
-        else:
-            r = Declaration(implements).flattened()
-
-    if not include_None:
-        return r
-
-    r = list(r)
-    r.append(None)
-    return r
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/_zope_interface_coptimizations.c b/llmlab/lib/python3.12/site-packages/zope/interface/_zope_interface_coptimizations.c
deleted file mode 100644
index 45810ec..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/_zope_interface_coptimizations.c
+++ /dev/null
@@ -1,2669 +0,0 @@
-/*###########################################################################
- #
- # Copyright (c) 2003 Zope Foundation and Contributors.
- # All Rights Reserved.
- #
- # This software is subject to the provisions of the Zope Public License,
- # Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
- # THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
- # WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- # WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
- # FOR A PARTICULAR PURPOSE.
- #
- ############################################################################*/
-
-#include "Python.h"
-#include "structmember.h"
-
-#ifdef __clang__
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Wunused-parameter"
-#pragma clang diagnostic ignored "-Wmissing-field-initializers"
-#endif
-
-#define TYPE(O) ((PyTypeObject*)(O))
-#define OBJECT(O) ((PyObject*)(O))
-#define CLASSIC(O) ((PyClassObject*)(O))
-#ifndef Py_TYPE
-#define Py_TYPE(o) ((o)->ob_type)
-#endif
-
-#define PyNative_FromString PyUnicode_FromString
-
-#define ASSURE_DICT(N)                                                         \
-    if (N == NULL) {                                                           \
-        N = PyDict_New();                                                      \
-        if (N == NULL)                                                         \
-            return NULL;                                                       \
-    }
-
-/*
- *  Don't use heap-allocated types for Python < 3.11:  the API needed
- *  to find the dynamic module, 'PyType_GetModuleByDef', was added then.
- */
-#if PY_VERSION_HEX < 0x030b0000
-#define USE_STATIC_TYPES 1
-#define USE_HEAP_TYPES 0
-#else
-#define USE_STATIC_TYPES 0
-#define USE_HEAP_TYPES 1
-#endif
-
-#define BASETYPE_FLAGS \
-    Py_TPFLAGS_DEFAULT | \
-    Py_TPFLAGS_BASETYPE | \
-    Py_TPFLAGS_HAVE_GC
-
-#if PY_VERSION_HEX >= 0x030c0000
-/* Add MANAGED_WEAKREF flag for Python >= 3.12, and don't define
- * the '.tp_weaklistoffset' slot.
- *
- * See: https://docs.python.org/3/c-api/typeobj.html
- *      #c.PyTypeObject.tp_weaklistoffset
- */
-#define USE_EXPLICIT_WEAKREFLIST 0
-#define WEAKREFTYPE_FLAGS BASETYPE_FLAGS | Py_TPFLAGS_MANAGED_WEAKREF
-#else
-/* No MANAGED_WEAKREF flag for Python < 3.12, and therefore define
- * the '.tp_weaklistoffset' slot, and the member whose offset it holds.
- *
- * See: https://docs.python.org/3/c-api/typeobj.html
- *      #c.PyTypeObject.tp_weaklistoffset
- */
-#define USE_EXPLICIT_WEAKREFLIST 1
-#define WEAKREFTYPE_FLAGS BASETYPE_FLAGS
-#endif
-
-/* Static strings, used to invoke PyObject_GetAttr (only in hot paths) */
-static PyObject *str__class__ = NULL;
-static PyObject *str__conform__ = NULL;
-static PyObject *str__dict__ = NULL;
-static PyObject *str__module__ = NULL;
-static PyObject *str__name__ = NULL;
-static PyObject *str__providedBy__ = NULL;
-static PyObject *str__provides__ = NULL;
-static PyObject *str__self__ = NULL;
-static PyObject *str_generation = NULL;
-static PyObject *str_registry = NULL;
-static PyObject *strro = NULL;
-
-/* Static strings, used to invoke PyObject_CallMethodObjArgs */
-static PyObject *str_call_conform = NULL;
-static PyObject *str_uncached_lookup = NULL;
-static PyObject *str_uncached_lookupAll = NULL;
-static PyObject *str_uncached_subscriptions = NULL;
-static PyObject *strchanged = NULL;
-static PyObject *str__adapt__ = NULL;
-
-/* Static strings, used to invoke PyObject_GetItem
- *
- * We cannot use PyDict_GetItemString, because the '__dict__' we get
- * from our types can be a 'types.mappingproxy', which causes a segfault.
- */
-static PyObject* str__implemented__;
-
-
-static int
-define_static_strings()
-{
-    if (str__class__ != NULL) {
-        return 0;
-    }
-
-#define DEFINE_STATIC_STRING(S)                  \
-    if (!(str##S = PyUnicode_FromString(#S)))    \
-    return -1
-
-    DEFINE_STATIC_STRING(__class__);
-    DEFINE_STATIC_STRING(__conform__);
-    DEFINE_STATIC_STRING(__dict__);
-    DEFINE_STATIC_STRING(__module__);
-    DEFINE_STATIC_STRING(__name__);
-    DEFINE_STATIC_STRING(__providedBy__);
-    DEFINE_STATIC_STRING(__provides__);
-    DEFINE_STATIC_STRING(__self__);
-    DEFINE_STATIC_STRING(_generation);
-    DEFINE_STATIC_STRING(_registry);
-    DEFINE_STATIC_STRING(ro);
-    DEFINE_STATIC_STRING(__implemented__);
-    DEFINE_STATIC_STRING(_call_conform);
-    DEFINE_STATIC_STRING(_uncached_lookup);
-    DEFINE_STATIC_STRING(_uncached_lookupAll);
-    DEFINE_STATIC_STRING(_uncached_subscriptions);
-    DEFINE_STATIC_STRING(changed);
-    DEFINE_STATIC_STRING(__adapt__);
-#undef DEFINE_STATIC_STRING
-
-    return 0;
-}
-
-/* Public module-scope functions, forward-declared here for type methods. */
-static PyObject *implementedBy(PyObject* module, PyObject *cls);
-static PyObject *getObjectSpecification(PyObject *module, PyObject *ob);
-static PyObject *providedBy(PyObject *module, PyObject *ob);
-
-/*
- * Utility functions, forward-declared here for type methods.
- */
-static PyObject* _get_module(PyTypeObject *typeobj);
-static PyObject* _get_adapter_hooks(PyTypeObject *typeobj);
-static PyTypeObject* _get_specification_base_class(PyTypeObject *typeobj);
-static PyTypeObject* _get_interface_base_class(PyTypeObject *typeobj);
-
-#if USE_STATIC_TYPES
-/*
- *  Global used by static IB__adapt
- */
-static PyObject*       adapter_hooks = NULL;
-
-/*
- *  Globals imported from 'zope.interface.declarations'
- */
-static int imported_declarations = 0;
-static PyObject* BuiltinImplementationSpecifications;
-static PyObject* empty;
-static PyObject* fallback;
-static PyTypeObject *Implements;
-
-/* Import zope.interface.declarations and store results in global statics.
- *
- * Static alternative to '_zic_state_load_declarations' below.
- */
-static int
-import_declarations(void)
-{
-    PyObject *declarations, *i;
-
-    declarations = PyImport_ImportModule("zope.interface.declarations");
-    if (declarations == NULL) { return -1; }
-
-    BuiltinImplementationSpecifications = PyObject_GetAttrString(
-                        declarations, "BuiltinImplementationSpecifications");
-    if (BuiltinImplementationSpecifications == NULL) { return -1; }
-
-    empty = PyObject_GetAttrString(declarations, "_empty");
-    if (empty == NULL) { return -1; }
-
-    fallback = PyObject_GetAttrString(declarations, "implementedByFallback");
-    if (fallback == NULL) { return -1;}
-
-    i = PyObject_GetAttrString(declarations, "Implements");
-    if (i == NULL) { return -1; }
-
-    if (! PyType_Check(i)) {
-        PyErr_SetString(
-            PyExc_TypeError,
-            "zope.interface.declarations.Implements is not a type");
-        return -1;
-    }
-
-    Implements = (PyTypeObject *)i;
-
-    Py_DECREF(declarations);
-
-    imported_declarations = 1;
-    return 0;
-}
-
-#endif
-
-/*
- *  SpecificationBase class
- */
-typedef struct
-{
-    PyObject_HEAD
-    /*
-      In the past, these fields were stored in the __dict__
-      and were technically allowed to contain any Python object, though
-      other type checks would fail or fall back to generic code paths if
-      they didn't have the expected type. We preserve that behaviour and don't
-      make any assumptions about contents.
-    */
-    PyObject* _implied;
-#if USE_EXPLICIT_WEAKREFLIST
-    PyObject* weakreflist;
-#endif
-    /*
-      The remainder aren't used in C code but must be stored here
-      to prevent instance layout conflicts.
-    */
-    PyObject* _dependents;
-    PyObject* _bases;
-    PyObject* _v_attrs;
-    PyObject* __iro__;
-    PyObject* __sro__;
-} SB;
-
-/*
-  We know what the fields are *supposed* to define, but
-  they could have anything, so we need to traverse them.
-*/
-static int
-SB_traverse(SB* self, visitproc visit, void* arg)
-{
-/* Visit our 'tp_type' only on Python >= 3.9, per
- * https://docs.python.org/3/howto/isolating-extensions.html
- * #tp-traverse-in-python-3-8-and-lower
- */
-#if USE_HEAP_TYPES && PY_VERSION_HEX > 0x03090000
-    Py_VISIT(Py_TYPE(self));
-#endif
-    Py_VISIT(self->_implied);
-    Py_VISIT(self->_dependents);
-    Py_VISIT(self->_bases);
-    Py_VISIT(self->_v_attrs);
-    Py_VISIT(self->__iro__);
-    Py_VISIT(self->__sro__);
-    return 0;
-}
-
-static int
-SB_clear(SB* self)
-{
-    Py_CLEAR(self->_implied);
-    Py_CLEAR(self->_dependents);
-    Py_CLEAR(self->_bases);
-    Py_CLEAR(self->_v_attrs);
-    Py_CLEAR(self->__iro__);
-    Py_CLEAR(self->__sro__);
-    return 0;
-}
-
-static void
-SB_dealloc(SB* self)
-{
-    PyObject_GC_UnTrack((PyObject*)self);
-    PyObject_ClearWeakRefs(OBJECT(self));
-    PyTypeObject* tp = Py_TYPE(self);
-    SB_clear(self);
-    tp->tp_free(OBJECT(self));
-#if USE_HEAP_TYPES
-    Py_DECREF(tp);
-#endif
-}
-
-static char SB_extends__doc__[] =
-  "Test whether a specification is or extends another";
-
-static PyObject*
-SB_extends(SB* self, PyObject* other)
-{
-    PyObject* implied;
-
-    implied = self->_implied;
-    if (implied == NULL) {
-        return NULL;
-    }
-
-    if (PyDict_GetItem(implied, other) != NULL)
-        Py_RETURN_TRUE;
-    Py_RETURN_FALSE;
-}
-
-static PyObject*
-SB__call__(SB* self, PyObject* args, PyObject* kw)
-{
-    PyObject* spec;
-
-    if (!PyArg_ParseTuple(args, "O", &spec))
-        return NULL;
-    return SB_extends(self, spec);
-}
-
-static char SB_providedBy__doc__[] =
-  "Test whether an interface is implemented by the specification";
-
-static PyObject*
-SB_providedBy(PyObject* self, PyObject* ob)
-{
-    PyObject *decl;
-    PyObject *item;
-    PyObject *module;
-    PyTypeObject *specification_base_class;
-
-    module = _get_module(Py_TYPE(self));
-    specification_base_class = _get_specification_base_class(Py_TYPE(self));
-
-    decl = providedBy(module, ob);
-    if (decl == NULL)
-        return NULL;
-
-    if (PyObject_TypeCheck(decl, specification_base_class))
-        item = SB_extends((SB*)decl, self);
-    else
-        /* decl is probably a security proxy.  We have to go the long way
-           around.
-        */
-        item = PyObject_CallFunctionObjArgs(decl, self, NULL);
-
-    Py_DECREF(decl);
-    return item;
-}
-
-static char SB_implementedBy__doc__[] =
-  "Test whether the specification is implemented by a class or factory.\n"
-  "Raise TypeError if argument is neither a class nor a callable.";
-
-static PyObject*
-SB_implementedBy(PyObject* self, PyObject* cls)
-{
-    PyObject *decl;
-    PyObject *item;
-    PyObject *module;
-    PyTypeObject *specification_base_class;
-
-    module = _get_module(Py_TYPE(self));
-    specification_base_class = _get_specification_base_class(Py_TYPE(self));
-
-    decl = implementedBy(module, cls);
-    if (decl == NULL)
-        return NULL;
-
-    if (PyObject_TypeCheck(decl, specification_base_class))
-        item = SB_extends((SB*)decl, self);
-    else
-        item = PyObject_CallFunctionObjArgs(decl, self, NULL);
-
-    Py_DECREF(decl);
-    return item;
-}
-
-static struct PyMethodDef SB_methods[] = {
-    { "providedBy",
-      (PyCFunction)SB_providedBy,
-      METH_O,
-      SB_providedBy__doc__ },
-    { "implementedBy",
-      (PyCFunction)SB_implementedBy,
-      METH_O,
-      SB_implementedBy__doc__ },
-    { "isOrExtends",
-      (PyCFunction)SB_extends,
-      METH_O,
-      SB_extends__doc__ },
-
-    { NULL, NULL } /* sentinel */
-};
-
-static PyMemberDef SB_members[] = {
-    { "_implied", T_OBJECT_EX, offsetof(SB, _implied), 0, "" },
-    { "_dependents", T_OBJECT_EX, offsetof(SB, _dependents), 0, "" },
-    { "_bases", T_OBJECT_EX, offsetof(SB, _bases), 0, "" },
-    { "_v_attrs", T_OBJECT_EX, offsetof(SB, _v_attrs), 0, "" },
-    { "__iro__", T_OBJECT_EX, offsetof(SB, __iro__), 0, "" },
-    { "__sro__", T_OBJECT_EX, offsetof(SB, __sro__), 0, "" },
-#if USE_EXPLICIT_WEAKREFLIST
-    { "__weaklistoffset__", T_PYSSIZET, offsetof(SB, weakreflist), READONLY, "" },
-#endif
-    { NULL },
-};
-
-static char SB__name__[] = "_zope_interface_coptimizations.SpecificationBase";
-static char SB__doc__[] = "Base type for Specification objects";
-
-#if USE_STATIC_TYPES
-
-/*
- * Static type: SpecificationBase
- */
-
-static PyTypeObject SB_type_def = {
-    PyVarObject_HEAD_INIT(NULL, 0)
-    .tp_name           = SB__name__,
-    .tp_doc            = SB__doc__,
-    .tp_basicsize      = sizeof(SB),
-    .tp_flags          = WEAKREFTYPE_FLAGS,
-    .tp_call           = (ternaryfunc)SB__call__,
-    .tp_traverse       = (traverseproc)SB_traverse,
-    .tp_clear          = (inquiry)SB_clear,
-    .tp_dealloc        = (destructor)SB_dealloc,
-#if USE_EXPLICIT_WEAKREFLIST
-    .tp_weaklistoffset = offsetof(SB, weakreflist),
-#endif
-    .tp_methods        = SB_methods,
-    .tp_members        = SB_members,
-};
-
-#else
-
-/*
- * Heap-based type: SpecificationBase
- */
-static PyType_Slot SB_type_slots[] = {
-    {Py_tp_doc,         SB__doc__},
-    {Py_tp_call,        SB__call__},
-    {Py_tp_traverse,    SB_traverse},
-    {Py_tp_clear,       SB_clear},
-    {Py_tp_dealloc,     SB_dealloc},
-    {Py_tp_methods,     SB_methods},
-    {Py_tp_members,     SB_members},
-    {0,                 NULL}
-};
-
-static PyType_Spec SB_type_spec = {
-    .name               = SB__name__,
-    .basicsize          = sizeof(SB),
-    .flags              = WEAKREFTYPE_FLAGS,
-    .slots              = SB_type_slots
-};
-
-#endif
-
-/*
- *  ObjectSpecificationDescriptor class
- */
-#if USE_HEAP_TYPES
-static int
-OSD_traverse(PyObject* self, visitproc visit, void* arg)
-{
-    Py_VISIT(Py_TYPE(self));
-    return 0;
-}
-
-static void
-OSD_dealloc(PyObject* self)
-{
-    PyObject_GC_UnTrack(self);
-    PyTypeObject *tp = Py_TYPE(self);
-    tp->tp_free(OBJECT(self));
-    Py_DECREF(tp);
-}
-#endif
-
-static PyObject*
-OSD_descr_get(PyObject* self, PyObject* inst, PyObject* cls)
-{
-    PyObject* provides;
-    PyObject *module;
-
-    module = _get_module(Py_TYPE(self));
-
-    if (inst == NULL) {
-        return getObjectSpecification(module, cls);
-    }
-
-    provides = PyObject_GetAttr(inst, str__provides__);
-    /* Return __provides__ if we got it, or return NULL and propagate
-     * non-AttributeError. */
-    if (provides != NULL || !PyErr_ExceptionMatches(PyExc_AttributeError)) {
-        return provides;
-    }
-
-    PyErr_Clear();
-
-    return implementedBy(module, cls);
-}
-
-static char OSD__name__[] = (
-    "_zope_interface_coptimizations.ObjectSpecificationDescriptor");
-static char OSD__doc__[] = "Object Specification Descriptor";
-
-#if USE_STATIC_TYPES
-
-/*
- * Static type: ObjectSpecificationDescriptor
- */
-
-static PyTypeObject OSD_type_def = {
-    PyVarObject_HEAD_INIT(NULL, 0)
-    .tp_name            = OSD__name__,
-    .tp_doc             = OSD__doc__,
-    /* No GC for the static version */
-    .tp_flags           = Py_TPFLAGS_DEFAULT |
-                          Py_TPFLAGS_BASETYPE,
-    .tp_descr_get       = (descrgetfunc)OSD_descr_get,
-  /*.tp_traverse,       = OSD_traverse},     not reqd for static */
-  /*.tp_dealloc,        = OSD_dealloc},      not reqd for static */
-};
-
-#else
-
-/*
- * Heap type: ObjectSpecificationDescriptor
- */
-static PyType_Slot OSD_type_slots[] = {
-    {Py_tp_doc,         OSD__doc__},
-    {Py_tp_descr_get,   OSD_descr_get},
-    {Py_tp_traverse,    OSD_traverse},
-    {Py_tp_dealloc,     OSD_dealloc},
-    {0,                 NULL}
-};
-
-static PyType_Spec OSD_type_spec = {
-    .name               = OSD__name__,
-    .basicsize          = 0,
-    .flags              = BASETYPE_FLAGS,
-    .slots              = OSD_type_slots
-};
-
-#endif
-
-/*
- *  ClassProvidesBase class
- */
-typedef struct
-{
-    SB spec;
-    /* These members are handled generically, as for SB members. */
-    PyObject* _cls;
-    PyObject* _implements;
-} CPB;
-
-static int
-CPB_traverse(CPB* self, visitproc visit, void* arg)
-{
-    Py_VISIT(self->_cls);
-    Py_VISIT(self->_implements);
-    return SB_traverse((SB*)self, visit, arg);
-}
-
-static int
-CPB_clear(CPB* self)
-{
-    Py_CLEAR(self->_cls);
-    Py_CLEAR(self->_implements);
-    return SB_clear((SB*)self);
-}
-
-static void
-CPB_dealloc(CPB* self)
-{
-    PyObject_GC_UnTrack((PyObject*)self);
-    CPB_clear(self);
-    SB_dealloc((SB*)self); /* handles decrefing tp */
-}
-
-static PyObject*
-CPB_descr_get(CPB* self, PyObject* inst, PyObject* cls)
-{
-    PyObject* implements;
-
-    if (self->_cls == NULL)
-        return NULL;
-
-    if (cls == self->_cls) {
-        if (inst == NULL) {
-            Py_INCREF(self);
-            return OBJECT(self);
-        }
-
-        implements = self->_implements;
-        Py_XINCREF(implements);
-        return implements;
-    }
-
-    PyErr_SetString(PyExc_AttributeError, "__provides__");
-    return NULL;
-}
-
-static PyMemberDef CPB_members[] = {
-    { "_cls", T_OBJECT_EX, offsetof(CPB, _cls), 0, "Defining class." },
-    { "_implements",
-      T_OBJECT_EX,
-      offsetof(CPB, _implements),
-      0,
-      "Result of implementedBy." },
-    { NULL }
-};
-
-static char CPB__name__[] = "_zope_interface_coptimizations.ClassProvidesBase";
-static char CPB__doc__[] = "C Base class for ClassProvides";
-
-#if USE_STATIC_TYPES
-
-/*
- * Static type: ClassProvidesBase
- */
-
-static PyTypeObject CPB_type_def = {
-    PyVarObject_HEAD_INIT(NULL, 0)
-    .tp_name            = CPB__name__,
-    .tp_doc             = CPB__doc__,
-    .tp_base            = &SB_type_def,
-    .tp_basicsize       = sizeof(CPB),
-    .tp_flags           = BASETYPE_FLAGS,
-    .tp_descr_get       = (descrgetfunc)CPB_descr_get,
-    .tp_traverse        = (traverseproc)CPB_traverse,
-    .tp_clear           = (inquiry)CPB_clear,
-    .tp_dealloc         = (destructor)CPB_dealloc,
-    .tp_members         = CPB_members,
-};
-
-#else
-
-/*
- * Heap type: ClassProvidesBase
- */
-static PyType_Slot CPB_type_slots[] = {
-    {Py_tp_doc,         CPB__doc__},
-    {Py_tp_descr_get,   CPB_descr_get},
-    {Py_tp_traverse,    CPB_traverse},
-    {Py_tp_clear,       CPB_clear},
-    {Py_tp_dealloc,     CPB_dealloc},
-    {Py_tp_members,     CPB_members},
-    /* tp_base cannot be set as a slot -- pass to PyType_FromModuleAndSpec */
-    {0,                 NULL}
-};
-
-static PyType_Spec CPB_type_spec = {
-    .name               = CPB__name__,
-    .basicsize          = sizeof(CPB),
-    .flags              = BASETYPE_FLAGS,
-    .slots              = CPB_type_slots
-};
-
-#endif
-
-/*
- *  InterfaceBase class
- */
-
-typedef struct
-{
-    SB spec;
-    PyObject* __name__;
-    PyObject* __module__;
-    Py_hash_t _v_cached_hash;
-} IB;
-
-static int
-IB_traverse(IB* self, visitproc visit, void* arg)
-{
-    Py_VISIT(self->__name__);
-    Py_VISIT(self->__module__);
-    return SB_traverse((SB*)self, visit, arg);
-}
-
-static int
-IB_clear(IB* self)
-{
-    Py_CLEAR(self->__name__);
-    Py_CLEAR(self->__module__);
-    return SB_clear((SB*)self);
-}
-
-static void
-IB_dealloc(IB* self)
-{
-    PyObject_GC_UnTrack((PyObject*)self);
-    IB_clear(self);
-    SB_dealloc((SB*)self); /* handles decrefing tp */
-}
-
-static int
-IB__init__(IB* self, PyObject* args, PyObject* kwargs)
-{
-    static char* kwlist[] = { "__name__", "__module__", NULL };
-    PyObject* module = NULL;
-    PyObject* name = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwargs, "|OO:InterfaceBase.__init__", kwlist, &name, &module)) {
-        return -1;
-    }
-    IB_clear(self);
-    self->__module__ = module ? module : Py_None;
-    Py_INCREF(self->__module__);
-    self->__name__ = name ? name : Py_None;
-    Py_INCREF(self->__name__);
-    return 0;
-}
-
-/*
-    def __adapt__(self, obj):
-        """Adapt an object to the receiver
-        """
-        if self.providedBy(obj):
-            return obj
-
-        for hook in adapter_hooks:
-            adapter = hook(self, obj)
-            if adapter is not None:
-                return adapter
-
-
-*/
-const char IB__adapt____doc__[] = "Adapt an object to the receiver";
-
-static PyObject*
-IB__adapt__(PyObject* self, PyObject* obj)
-{
-    PyObject *decl;
-    PyObject *args;
-    PyObject *adapter;
-    PyObject *module;
-    PyObject *adapter_hooks;
-    PyTypeObject *specification_base_class;
-    int implements;
-    int i;
-    int l;
-
-    module = _get_module(Py_TYPE(self));
-
-    decl = providedBy(module, obj);
-    if (decl == NULL)
-        return NULL;
-
-    specification_base_class = _get_specification_base_class(Py_TYPE(self));
-
-    if (PyObject_TypeCheck(decl, specification_base_class)) {
-        PyObject* implied;
-
-        implied = ((SB*)decl)->_implied;
-        if (implied == NULL) {
-            Py_DECREF(decl);
-            return NULL;
-        }
-
-        implements = PyDict_GetItem(implied, self) != NULL;
-        Py_DECREF(decl);
-    } else {
-        /* decl is probably a security proxy.  We have to go the long way
-           around.
-        */
-        PyObject* r;
-        r = PyObject_CallFunctionObjArgs(decl, self, NULL);
-        Py_DECREF(decl);
-        if (r == NULL)
-            return NULL;
-        implements = PyObject_IsTrue(r);
-        Py_DECREF(r);
-    }
-
-    if (implements) {
-        Py_INCREF(obj);
-        return obj;
-    }
-
-    args = PyTuple_New(2);
-    if (args == NULL) { return NULL; }
-
-    Py_INCREF(self);
-    PyTuple_SET_ITEM(args, 0, self);
-
-    Py_INCREF(obj);
-    PyTuple_SET_ITEM(args, 1, obj);
-
-    adapter_hooks = _get_adapter_hooks(Py_TYPE(self));
-    l = PyList_GET_SIZE(adapter_hooks);
-    for (i = 0; i < l; i++) {
-        adapter = PyObject_CallObject(PyList_GET_ITEM(adapter_hooks, i), args);
-        if (adapter == NULL || adapter != Py_None) {
-            Py_DECREF(args);
-            return adapter;
-        }
-        Py_DECREF(adapter);
-    }
-
-    Py_DECREF(args);
-
-    Py_INCREF(Py_None);
-    return Py_None;
-}
-
-/*
-    def __call__(self, obj, alternate=_marker):
-        try:
-            conform = obj.__conform__
-        except AttributeError: # pylint:disable=bare-except
-            conform = None
-
-        if conform is not None:
-            adapter = self._call_conform(conform)
-            if adapter is not None:
-                return adapter
-
-        adapter = self.__adapt__(obj)
-
-        if adapter is not None:
-            return adapter
-        if alternate is not _marker:
-            return alternate
-        raise TypeError("Could not adapt", obj, self)
-
-*/
-static PyObject*
-IB__call__(PyObject* self, PyObject* args, PyObject* kwargs)
-{
-    PyObject *conform, *obj, *alternate, *adapter;
-    static char* kwlist[] = { "obj", "alternate", NULL };
-    conform = obj = alternate = adapter = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwargs, "O|O", kwlist, &obj, &alternate))
-        return NULL;
-
-    conform = PyObject_GetAttr(obj, str__conform__);
-    if (conform == NULL) {
-        if (!PyErr_ExceptionMatches(PyExc_AttributeError)) {
-            /* Propagate non-AttributeErrors */
-            return NULL;
-        }
-        PyErr_Clear();
-
-        Py_INCREF(Py_None);
-        conform = Py_None;
-    }
-
-    if (conform != Py_None) {
-        adapter =
-          PyObject_CallMethodObjArgs(self, str_call_conform, conform, NULL);
-        Py_DECREF(conform);
-        if (adapter == NULL || adapter != Py_None)
-            return adapter;
-        Py_DECREF(adapter);
-    } else {
-        Py_DECREF(conform);
-    }
-
-    /* We differ from the Python code here. For speed, instead of always calling
-       self.__adapt__(), we check to see if the type has defined it. Checking in
-       the dict for __adapt__ isn't sufficient because there's no cheap way to
-       tell if it's the __adapt__ that InterfaceBase itself defines (our type
-       will *never* be InterfaceBase, we're always subclassed by
-       InterfaceClass). Instead, we cooperate with InterfaceClass in Python to
-       set a flag in a new subclass when this is necessary. */
-    if (PyDict_GetItemString(self->ob_type->tp_dict, "_CALL_CUSTOM_ADAPT")) {
-        /* Doesn't matter what the value is. Simply being present is enough. */
-        adapter = PyObject_CallMethodObjArgs(self, str__adapt__, obj, NULL);
-    } else {
-        adapter = IB__adapt__(self, obj);
-    }
-
-    if (adapter == NULL || adapter != Py_None) {
-        return adapter;
-    }
-    Py_DECREF(adapter);
-
-    if (alternate != NULL) {
-        Py_INCREF(alternate);
-        return alternate;
-    }
-
-    adapter = Py_BuildValue("sOO", "Could not adapt", obj, self);
-    if (adapter != NULL) {
-        PyErr_SetObject(PyExc_TypeError, adapter);
-        Py_DECREF(adapter);
-    }
-    return NULL;
-}
-
-static Py_hash_t
-IB__hash__(IB* self)
-{
-    PyObject* tuple;
-    if (!self->__module__) {
-        PyErr_SetString(PyExc_AttributeError, "__module__");
-        return -1;
-    }
-    if (!self->__name__) {
-        PyErr_SetString(PyExc_AttributeError, "__name__");
-        return -1;
-    }
-
-    if (self->_v_cached_hash) {
-        return self->_v_cached_hash;
-    }
-
-    tuple = PyTuple_Pack(2, self->__name__, self->__module__);
-    if (!tuple) {
-        return -1;
-    }
-    self->_v_cached_hash = PyObject_Hash(tuple);
-    Py_CLEAR(tuple);
-    return self->_v_cached_hash;
-}
-
-static PyObject*
-IB_richcompare(IB* self, PyObject* other, int op)
-{
-    PyObject* othername;
-    PyObject* othermod;
-    PyObject* oresult;
-    PyTypeObject* interface_base_class;
-    IB* otherib;
-    int result;
-
-    otherib = NULL;
-    oresult = othername = othermod = NULL;
-
-    if (OBJECT(self) == other) {
-        switch (op) {
-            case Py_EQ:
-            case Py_LE:
-            case Py_GE:
-                Py_RETURN_TRUE;
-                break;
-            case Py_NE:
-                Py_RETURN_FALSE;
-        }
-    }
-
-    if (other == Py_None) {
-        switch (op) {
-            case Py_LT:
-            case Py_LE:
-            case Py_NE:
-                Py_RETURN_TRUE;
-            default:
-                Py_RETURN_FALSE;
-        }
-    }
-
-    interface_base_class = _get_interface_base_class(Py_TYPE(self));
-    if (interface_base_class == NULL) {
-        oresult = Py_NotImplemented;
-        goto cleanup;
-    }
-
-    if (PyObject_TypeCheck(other, interface_base_class)) {
-        // This branch borrows references. No need to clean
-        // up if otherib is not null.
-        otherib = (IB*)other;
-        othername = otherib->__name__;
-        othermod = otherib->__module__;
-    } else {
-        othername = PyObject_GetAttr(other, str__name__);
-        if (othername) {
-            othermod = PyObject_GetAttr(other, str__module__);
-        }
-        if (!othername || !othermod) {
-            if (PyErr_Occurred() &&
-                PyErr_ExceptionMatches(PyExc_AttributeError)) {
-                PyErr_Clear();
-                oresult = Py_NotImplemented;
-            }
-            goto cleanup;
-        }
-    }
-#if 0
-// This is the simple, straightforward version of what Python does.
-    PyObject* pt1 = PyTuple_Pack(2, self->__name__, self->__module__);
-    PyObject* pt2 = PyTuple_Pack(2, othername, othermod);
-    oresult = PyObject_RichCompare(pt1, pt2, op);
-#endif
-
-    // tuple comparison is decided by the first non-equal element.
-    result = PyObject_RichCompareBool(self->__name__, othername, Py_EQ);
-    if (result == 0) {
-        result = PyObject_RichCompareBool(self->__name__, othername, op);
-    } else if (result == 1) {
-        result = PyObject_RichCompareBool(self->__module__, othermod, op);
-    }
-    // If either comparison failed, we have an error set.
-    // Leave oresult NULL so we raise it.
-    if (result == -1) {
-        goto cleanup;
-    }
-
-    oresult = result ? Py_True : Py_False;
-
-cleanup:
-    Py_XINCREF(oresult);
-
-    if (!otherib) {
-        Py_XDECREF(othername);
-        Py_XDECREF(othermod);
-    }
-    return oresult;
-}
-
-static PyMemberDef IB_members[] = {
-    { "__name__", T_OBJECT_EX, offsetof(IB, __name__), 0, "" },
-    // The redundancy between __module__ and __ibmodule__ is because
-    // __module__ is often shadowed by subclasses.
-    { "__module__", T_OBJECT_EX, offsetof(IB, __module__), READONLY, "" },
-    { "__ibmodule__", T_OBJECT_EX, offsetof(IB, __module__), 0, "" },
-    { NULL }
-};
-
-static struct PyMethodDef IB_methods[] = {
-    { "__adapt__", (PyCFunction)IB__adapt__, METH_O, IB__adapt____doc__},
-    { NULL, NULL } /* sentinel */
-};
-
-static char IB__name__[] ="_zope_interface_coptimizations.InterfaceBase";
-static char IB__doc__[] = (
-    "Interface base type providing __call__ and __adapt__"
-);
-
-#if USE_STATIC_TYPES
-
-/*
- * Static type: InterfaceBase
- */
-
-static PyTypeObject IB_type_def = {
-    PyVarObject_HEAD_INIT(NULL, 0)
-    .tp_name            = IB__name__,
-    .tp_doc             = IB__doc__,
-    .tp_base            = &SB_type_def,
-    .tp_basicsize       = sizeof(IB),
-    .tp_flags           = BASETYPE_FLAGS,
-    .tp_init            = (initproc)IB__init__,
-    .tp_hash            = (hashfunc)IB__hash__,
-    .tp_richcompare     = (richcmpfunc)IB_richcompare,
-    .tp_call            = (ternaryfunc)IB__call__,
-    .tp_traverse        = (traverseproc)IB_traverse,
-    .tp_clear           = (inquiry)IB_clear,
-    .tp_dealloc         = (destructor)IB_dealloc,
-    .tp_methods         = IB_methods,
-    .tp_members         = IB_members,
-};
-
-#else
-
-/*
- * Heap type: InterfaceBase
- */
-static PyType_Slot IB_type_slots[] = {
-    {Py_tp_doc,         IB__doc__},
-    {Py_tp_init,        IB__init__},
-    {Py_tp_hash,        IB__hash__},
-    {Py_tp_richcompare, IB_richcompare},
-    {Py_tp_call,        IB__call__},
-    {Py_tp_traverse,    IB_traverse},
-    {Py_tp_clear,       IB_clear},
-    {Py_tp_dealloc,     IB_dealloc},
-    {Py_tp_methods,     IB_methods},
-    {Py_tp_members,     IB_members},
-    /* tp_base cannot be set as a slot -- pass to PyType_FromModuleAndSpec */
-    {0,                   NULL}
-};
-
-static PyType_Spec IB_type_spec = {
-    .name               = IB__name__,
-    .basicsize          = sizeof(IB),
-    .flags              = BASETYPE_FLAGS,
-    .slots              = IB_type_slots
-};
-
-#endif
-
-/*
- *  LookupBase class
- */
-typedef struct
-{
-    PyObject_HEAD
-    PyObject* _cache;
-    PyObject* _mcache;
-    PyObject* _scache;
-} LB;
-
-static int
-LB_traverse(LB* self, visitproc visit, void* arg)
-{
-/* Visit our 'tp_type' only on Python >= 3.9, per
- * https://docs.python.org/3/howto/isolating-extensions.html
- * #tp-traverse-in-python-3-8-and-lower
- */
-#if USE_HEAP_TYPES && PY_VERSION_HEX > 0x03090000
-    Py_VISIT(Py_TYPE(self));
-#endif
-    Py_VISIT(self->_cache);
-    Py_VISIT(self->_mcache);
-    Py_VISIT(self->_scache);
-    return 0;
-}
-
-static int
-LB_clear(LB* self)
-{
-    Py_CLEAR(self->_cache);
-    Py_CLEAR(self->_mcache);
-    Py_CLEAR(self->_scache);
-    return 0;
-}
-
-static void
-LB_dealloc(LB* self)
-{
-    PyObject_GC_UnTrack((PyObject*)self);
-    PyTypeObject* tp = Py_TYPE(self);
-    LB_clear(self);
-    tp->tp_free((PyObject*)self);
-#if USE_HEAP_TYPES
-    Py_DECREF(tp);
-#endif
-}
-
-/*
-    def changed(self, ignored=None):
-        self._cache.clear()
-        self._mcache.clear()
-        self._scache.clear()
-*/
-static PyObject*
-LB_changed(LB* self, PyObject* ignored)
-{
-    LB_clear(self);
-    Py_INCREF(Py_None);
-    return Py_None;
-}
-
-/*
-    def _getcache(self, provided, name):
-        cache = self._cache.get(provided)
-        if cache is None:
-            cache = {}
-            self._cache[provided] = cache
-        if name:
-            c = cache.get(name)
-            if c is None:
-                c = {}
-                cache[name] = c
-            cache = c
-        return cache
-*/
-static PyObject*
-_subcache(PyObject* cache, PyObject* key)
-{
-    PyObject* subcache;
-
-    subcache = PyDict_GetItem(cache, key);
-    if (subcache == NULL) {
-        int status;
-
-        subcache = PyDict_New();
-        if (subcache == NULL)
-            return NULL;
-        status = PyDict_SetItem(cache, key, subcache);
-        Py_DECREF(subcache);
-        if (status < 0)
-            return NULL;
-    }
-
-    return subcache;
-}
-
-static PyObject*
-_getcache(LB* self, PyObject* provided, PyObject* name)
-{
-    PyObject* cache;
-
-    ASSURE_DICT(self->_cache);
-
-    cache = _subcache(self->_cache, provided);
-    if (cache == NULL)
-        return NULL;
-
-    if (name != NULL && PyObject_IsTrue(name))
-        cache = _subcache(cache, name);
-
-    return cache;
-}
-
-/*
-    def lookup(self, required, provided, name=u'', default=None):
-        cache = self._getcache(provided, name)
-        if len(required) == 1:
-            result = cache.get(required[0], _not_in_mapping)
-        else:
-            result = cache.get(tuple(required), _not_in_mapping)
-
-        if result is _not_in_mapping:
-            result = self._uncached_lookup(required, provided, name)
-            if len(required) == 1:
-                cache[required[0]] = result
-            else:
-                cache[tuple(required)] = result
-
-        if result is None:
-            return default
-
-        return result
-*/
-
-static PyObject*
-_lookup(LB* self,
-        PyObject* required,
-        PyObject* provided,
-        PyObject* name,
-        PyObject* default_)
-{
-    PyObject *result, *key, *cache;
-    result = key = cache = NULL;
-    if (name && !PyUnicode_Check(name)) {
-        PyErr_SetString(PyExc_ValueError, "name is not a string");
-        return NULL;
-    }
-
-    /* If `required` is a lazy sequence, it could have arbitrary side-effects,
-       such as clearing our caches. So we must not retrieve the cache until
-       after resolving it. */
-    required = PySequence_Tuple(required);
-    if (required == NULL)
-        return NULL;
-
-    cache = _getcache(self, provided, name);
-    if (cache == NULL)
-        return NULL;
-
-    if (PyTuple_GET_SIZE(required) == 1)
-        key = PyTuple_GET_ITEM(required, 0);
-    else
-        key = required;
-
-    result = PyDict_GetItem(cache, key);
-    if (result == NULL) {
-        int status;
-
-        result = PyObject_CallMethodObjArgs(
-          OBJECT(self), str_uncached_lookup, required, provided, name, NULL);
-        if (result == NULL) {
-            Py_DECREF(required);
-            return NULL;
-        }
-        status = PyDict_SetItem(cache, key, result);
-        Py_DECREF(required);
-        if (status < 0) {
-            Py_DECREF(result);
-            return NULL;
-        }
-    } else {
-        Py_INCREF(result);
-        Py_DECREF(required);
-    }
-
-    if (result == Py_None && default_ != NULL) {
-        Py_DECREF(Py_None);
-        Py_INCREF(default_);
-        return default_;
-    }
-
-    return result;
-}
-
-static PyObject*
-LB_lookup(LB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", "name", "default", NULL };
-    PyObject *required, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(args,
-                                     kwds,
-                                     "OO|OO:LookupBase.lookup",
-                                     kwlist,
-                                     &required,
-                                     &provided,
-                                     &name,
-                                     &default_))
-        return NULL;
-
-    return _lookup(self, required, provided, name, default_);
-}
-
-/*
-    def lookup1(self, required, provided, name=u'', default=None):
-        cache = self._getcache(provided, name)
-        result = cache.get(required, _not_in_mapping)
-        if result is _not_in_mapping:
-            return self.lookup((required, ), provided, name, default)
-
-        if result is None:
-            return default
-
-        return result
-*/
-static PyObject*
-_lookup1(LB* self,
-         PyObject* required,
-         PyObject* provided,
-         PyObject* name,
-         PyObject* default_)
-{
-    PyObject *result, *cache;
-
-    if (name && !PyUnicode_Check(name)) {
-        PyErr_SetString(PyExc_ValueError, "name is not a string");
-        return NULL;
-    }
-
-    cache = _getcache(self, provided, name);
-    if (cache == NULL)
-        return NULL;
-
-    result = PyDict_GetItem(cache, required);
-    if (result == NULL) {
-        PyObject* tup;
-
-        tup = PyTuple_New(1);
-        if (tup == NULL)
-            return NULL;
-        Py_INCREF(required);
-        PyTuple_SET_ITEM(tup, 0, required);
-        result = _lookup(self, tup, provided, name, default_);
-        Py_DECREF(tup);
-    } else {
-        if (result == Py_None && default_ != NULL) {
-            result = default_;
-        }
-        Py_INCREF(result);
-    }
-
-    return result;
-}
-static PyObject*
-LB_lookup1(LB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", "name", "default", NULL };
-    PyObject *required, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(args,
-                                     kwds,
-                                     "OO|OO:LookupBase.lookup1",
-                                     kwlist,
-                                     &required,
-                                     &provided,
-                                     &name,
-                                     &default_))
-        return NULL;
-
-    return _lookup1(self, required, provided, name, default_);
-}
-
-/*
-    def adapter_hook(self, provided, object, name=u'', default=None):
-        required = providedBy(object)
-        cache = self._getcache(provided, name)
-        factory = cache.get(required, _not_in_mapping)
-        if factory is _not_in_mapping:
-            factory = self.lookup((required, ), provided, name)
-
-        if factory is not None:
-            if isinstance(object, super):
-                object = object.__self__
-            result = factory(object)
-            if result is not None:
-                return result
-
-        return default
-*/
-static PyObject*
-_adapter_hook(LB* self,
-              PyObject* provided,
-              PyObject* object,
-              PyObject* name,
-              PyObject* default_)
-{
-    PyObject *required;
-    PyObject *factory;
-    PyObject *result;
-    PyObject *module;
-
-    module = _get_module(Py_TYPE(self));
-
-    if (name && !PyUnicode_Check(name)) {
-        PyErr_SetString(PyExc_ValueError, "name is not a string");
-        return NULL;
-    }
-
-    required = providedBy(module, object);
-    if (required == NULL)
-        return NULL;
-
-    factory = _lookup1(self, required, provided, name, Py_None);
-    Py_DECREF(required);
-    if (factory == NULL)
-        return NULL;
-
-    if (factory != Py_None) {
-        if (PyObject_TypeCheck(object, &PySuper_Type)) {
-            PyObject* self = PyObject_GetAttr(object, str__self__);
-            if (self == NULL) {
-                Py_DECREF(factory);
-                return NULL;
-            }
-            // Borrow the reference to self
-            Py_DECREF(self);
-            object = self;
-        }
-        result = PyObject_CallFunctionObjArgs(factory, object, NULL);
-        Py_DECREF(factory);
-        if (result == NULL || result != Py_None)
-            return result;
-    } else
-        result = factory; /* None */
-
-    if (default_ == NULL || default_ == result) /* No default specified, */
-        return result; /* Return None.  result is owned None */
-
-    Py_DECREF(result);
-    Py_INCREF(default_);
-
-    return default_;
-}
-
-static PyObject*
-LB_adapter_hook(LB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "provided", "object", "name", "default", NULL };
-    PyObject *object, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(args,
-                                     kwds,
-                                     "OO|OO:LookupBase.adapter_hook",
-                                     kwlist,
-                                     &provided,
-                                     &object,
-                                     &name,
-                                     &default_))
-        return NULL;
-
-    return _adapter_hook(self, provided, object, name, default_);
-}
-
-static PyObject*
-LB_queryAdapter(LB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "object", "provided", "name", "default", NULL };
-    PyObject *object, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(args,
-                                     kwds,
-                                     "OO|OO:LookupBase.queryAdapter",
-                                     kwlist,
-                                     &object,
-                                     &provided,
-                                     &name,
-                                     &default_))
-        return NULL;
-
-    return _adapter_hook(self, provided, object, name, default_);
-}
-
-/*
-    def lookupAll(self, required, provided):
-        cache = self._mcache.get(provided)
-        if cache is None:
-            cache = {}
-            self._mcache[provided] = cache
-
-        required = tuple(required)
-        result = cache.get(required, _not_in_mapping)
-        if result is _not_in_mapping:
-            result = self._uncached_lookupAll(required, provided)
-            cache[required] = result
-
-        return result
-*/
-static PyObject*
-_lookupAll(LB* self, PyObject* required, PyObject* provided)
-{
-    PyObject *cache, *result;
-
-    /* resolve before getting cache. See note in _lookup. */
-    required = PySequence_Tuple(required);
-    if (required == NULL)
-        return NULL;
-
-    ASSURE_DICT(self->_mcache);
-
-    cache = _subcache(self->_mcache, provided);
-    if (cache == NULL)
-        return NULL;
-
-    result = PyDict_GetItem(cache, required);
-    if (result == NULL) {
-        int status;
-
-        result = PyObject_CallMethodObjArgs(
-          OBJECT(self), str_uncached_lookupAll, required, provided, NULL);
-        if (result == NULL) {
-            Py_DECREF(required);
-            return NULL;
-        }
-        status = PyDict_SetItem(cache, required, result);
-        Py_DECREF(required);
-        if (status < 0) {
-            Py_DECREF(result);
-            return NULL;
-        }
-    } else {
-        Py_INCREF(result);
-        Py_DECREF(required);
-    }
-
-    return result;
-}
-
-static PyObject*
-LB_lookupAll(LB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", NULL };
-    PyObject *required, *provided;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO:LookupBase.lookupAll", kwlist, &required, &provided))
-        return NULL;
-
-    return _lookupAll(self, required, provided);
-}
-
-/*
-    def subscriptions(self, required, provided):
-        cache = self._scache.get(provided)
-        if cache is None:
-            cache = {}
-            self._scache[provided] = cache
-
-        required = tuple(required)
-        result = cache.get(required, _not_in_mapping)
-        if result is _not_in_mapping:
-            result = self._uncached_subscriptions(required, provided)
-            cache[required] = result
-
-        return result
-*/
-static PyObject*
-_subscriptions(LB* self, PyObject* required, PyObject* provided)
-{
-    PyObject *cache, *result;
-
-    /* resolve before getting cache. See note in _lookup. */
-    required = PySequence_Tuple(required);
-    if (required == NULL)
-        return NULL;
-
-    ASSURE_DICT(self->_scache);
-
-    cache = _subcache(self->_scache, provided);
-    if (cache == NULL)
-        return NULL;
-
-    result = PyDict_GetItem(cache, required);
-    if (result == NULL) {
-        int status;
-
-        result = PyObject_CallMethodObjArgs(
-          OBJECT(self), str_uncached_subscriptions, required, provided, NULL);
-        if (result == NULL) {
-            Py_DECREF(required);
-            return NULL;
-        }
-        status = PyDict_SetItem(cache, required, result);
-        Py_DECREF(required);
-        if (status < 0) {
-            Py_DECREF(result);
-            return NULL;
-        }
-    } else {
-        Py_INCREF(result);
-        Py_DECREF(required);
-    }
-
-    return result;
-}
-
-static PyObject*
-LB_subscriptions(LB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", NULL };
-    PyObject *required, *provided;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO", kwlist, &required, &provided))
-        return NULL;
-
-    return _subscriptions(self, required, provided);
-}
-
-static struct PyMethodDef LB_methods[] = {
-    { "changed", (PyCFunction)LB_changed, METH_O, "" },
-    { "lookup", (PyCFunction)LB_lookup, METH_KEYWORDS | METH_VARARGS, "" },
-    { "lookup1",
-      (PyCFunction)LB_lookup1,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "queryAdapter",
-      (PyCFunction)LB_queryAdapter,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "adapter_hook",
-      (PyCFunction)LB_adapter_hook,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "lookupAll",
-      (PyCFunction)LB_lookupAll,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "subscriptions",
-      (PyCFunction)LB_subscriptions,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { NULL, NULL } /* sentinel */
-};
-
-static char LB__name__[] = "_zope_interface_coptimizations.LookupBase";
-static char LB__doc__[] = "Base class for adapter registries";
-
-
-#if USE_STATIC_TYPES
-
-/*
- * Static type: LookupBase
- */
-
-static PyTypeObject LB_type_def = {
-    PyVarObject_HEAD_INIT(NULL, 0)
-    .tp_name            = LB__name__,
-    .tp_doc             = LB__doc__,
-    .tp_basicsize       = sizeof(LB),
-    .tp_flags           = BASETYPE_FLAGS,
-    .tp_traverse        = (traverseproc)LB_traverse,
-    .tp_clear           = (inquiry)LB_clear,
-    .tp_dealloc         = (destructor)&LB_dealloc,
-    .tp_methods         = LB_methods,
-};
-
-#else
-
-/*
- * Heap type: LookupBase
- */
-static PyType_Slot LB_type_slots[] = {
-    {Py_tp_doc,         LB__doc__},
-    {Py_tp_traverse,    LB_traverse},
-    {Py_tp_clear,       LB_clear},
-    {Py_tp_dealloc,     LB_dealloc},
-    {Py_tp_methods,     LB_methods},
-    {0,                 NULL}
-};
-
-static PyType_Spec LB_type_spec = {
-    .name               = LB__name__,
-    .basicsize          = sizeof(LB),
-    .flags              = BASETYPE_FLAGS,
-    .slots              = LB_type_slots
-};
-
-#endif
-
-typedef struct
-{
-    LB          lookup;
-    PyObject*   _verify_ro;
-    PyObject*   _verify_generations;
-} VB;
-
-static int
-VB_traverse(VB* self, visitproc visit, void* arg)
-{
-    Py_VISIT(self->_verify_ro);
-    Py_VISIT(self->_verify_generations);
-    return LB_traverse((LB*)self, visit, arg);
-}
-
-static int
-VB_clear(VB* self)
-{
-    Py_CLEAR(self->_verify_generations);
-    Py_CLEAR(self->_verify_ro);
-    return LB_clear((LB*)self);
-}
-
-static void
-VB_dealloc(VB* self)
-{
-    PyObject_GC_UnTrack((PyObject*)self);
-    PyTypeObject *tp = Py_TYPE(self);
-    VB_clear(self);
-    tp->tp_free((PyObject*)self);
-#if USE_HEAP_TYPES
-    Py_DECREF(tp);
-#endif
-}
-
-/*
-    def changed(self, originally_changed):
-        super(VerifyingBasePy, self).changed(originally_changed)
-        self._verify_ro = self._registry.ro[1:]
-        self._verify_generations = [r._generation for r in self._verify_ro]
-*/
-static PyObject*
-_generations_tuple(PyObject* ro)
-{
-    int i, l;
-    PyObject* generations;
-
-    l = PyTuple_GET_SIZE(ro);
-    generations = PyTuple_New(l);
-    for (i = 0; i < l; i++) {
-        PyObject* generation;
-
-        generation = PyObject_GetAttr(PyTuple_GET_ITEM(ro, i), str_generation);
-        if (generation == NULL) {
-            Py_DECREF(generations);
-            return NULL;
-        }
-        PyTuple_SET_ITEM(generations, i, generation);
-    }
-
-    return generations;
-}
-static PyObject*
-verify_changed(VB* self, PyObject* ignored)
-{
-    PyObject *t, *ro;
-
-    VB_clear(self);
-
-    t = PyObject_GetAttr(OBJECT(self), str_registry);
-    if (t == NULL)
-        return NULL;
-
-    ro = PyObject_GetAttr(t, strro);
-    Py_DECREF(t);
-    if (ro == NULL)
-        return NULL;
-
-    t = PyObject_CallFunctionObjArgs(OBJECT(&PyTuple_Type), ro, NULL);
-    Py_DECREF(ro);
-    if (t == NULL)
-        return NULL;
-
-    ro = PyTuple_GetSlice(t, 1, PyTuple_GET_SIZE(t));
-    Py_DECREF(t);
-    if (ro == NULL)
-        return NULL;
-
-    self->_verify_generations = _generations_tuple(ro);
-    if (self->_verify_generations == NULL) {
-        Py_DECREF(ro);
-        return NULL;
-    }
-
-    self->_verify_ro = ro;
-
-    Py_INCREF(Py_None);
-    return Py_None;
-}
-
-/*
-    def _verify(self):
-        if ([r._generation for r in self._verify_ro]
-            != self._verify_generations):
-            self.changed(None)
-*/
-static int
-_verify(VB* self)
-{
-    PyObject* changed_result;
-
-    if (self->_verify_ro != NULL && self->_verify_generations != NULL) {
-        PyObject* generations;
-        int changed;
-
-        generations = _generations_tuple(self->_verify_ro);
-        if (generations == NULL)
-            return -1;
-
-        changed = PyObject_RichCompareBool(
-          self->_verify_generations, generations, Py_NE);
-        Py_DECREF(generations);
-        if (changed == -1)
-            return -1;
-
-        if (changed == 0)
-            return 0;
-    }
-
-    changed_result =
-      PyObject_CallMethodObjArgs(OBJECT(self), strchanged, Py_None, NULL);
-    if (changed_result == NULL)
-        return -1;
-
-    Py_DECREF(changed_result);
-    return 0;
-}
-
-static PyObject*
-VB_lookup(VB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", "name", "default", NULL };
-    PyObject *required, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO|OO", kwlist, &required, &provided, &name, &default_))
-        return NULL;
-
-    if (_verify(self) < 0)
-        return NULL;
-
-    return _lookup((LB*)self, required, provided, name, default_);
-}
-
-static PyObject*
-VB_lookup1(VB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", "name", "default", NULL };
-    PyObject *required, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO|OO", kwlist, &required, &provided, &name, &default_))
-        return NULL;
-
-    if (_verify(self) < 0)
-        return NULL;
-
-    return _lookup1((LB*)self, required, provided, name, default_);
-}
-
-static PyObject*
-VB_adapter_hook(VB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "provided", "object", "name", "default", NULL };
-    PyObject *object, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO|OO", kwlist, &provided, &object, &name, &default_))
-        return NULL;
-
-    if (_verify(self) < 0)
-        return NULL;
-
-    return _adapter_hook((LB*)self, provided, object, name, default_);
-}
-
-static PyObject*
-VB_queryAdapter(VB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "object", "provided", "name", "default", NULL };
-    PyObject *object, *provided, *name = NULL, *default_ = NULL;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO|OO", kwlist, &object, &provided, &name, &default_))
-        return NULL;
-
-    if (_verify(self) < 0)
-        return NULL;
-
-    return _adapter_hook((LB*)self, provided, object, name, default_);
-}
-
-static PyObject*
-VB_lookupAll(VB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", NULL };
-    PyObject *required, *provided;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO", kwlist, &required, &provided))
-        return NULL;
-
-    if (_verify(self) < 0)
-        return NULL;
-
-    return _lookupAll((LB*)self, required, provided);
-}
-
-static PyObject*
-VB_subscriptions(VB* self, PyObject* args, PyObject* kwds)
-{
-    static char* kwlist[] = { "required", "provided", NULL };
-    PyObject *required, *provided;
-
-    if (!PyArg_ParseTupleAndKeywords(
-          args, kwds, "OO", kwlist, &required, &provided))
-        return NULL;
-
-    if (_verify(self) < 0)
-        return NULL;
-
-    return _subscriptions((LB*)self, required, provided);
-}
-
-static struct PyMethodDef VB_methods[] = {
-    { "changed", (PyCFunction)verify_changed, METH_O, "" },
-    { "lookup",
-      (PyCFunction)VB_lookup,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "lookup1",
-      (PyCFunction)VB_lookup1,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "queryAdapter",
-      (PyCFunction)VB_queryAdapter,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "adapter_hook",
-      (PyCFunction)VB_adapter_hook,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "lookupAll",
-      (PyCFunction)VB_lookupAll,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { "subscriptions",
-      (PyCFunction)VB_subscriptions,
-      METH_KEYWORDS | METH_VARARGS,
-      "" },
-    { NULL, NULL } /* sentinel */
-};
-
-static char VB__name__[] = "_zope_interface_coptimizations.VerifyingBase";
-static char VB__doc__[] = "Base class for verifying adapter registries.";
-
-#if USE_STATIC_TYPES
-
-/*
- * Static type: VerifyingBase
- */
-
-static PyTypeObject VB_type_def = {
-    PyVarObject_HEAD_INIT(NULL, 0)
-    .tp_name            = VB__name__,
-    .tp_doc             = VB__doc__,
-    .tp_base            = &LB_type_def,
-    .tp_basicsize       = sizeof(VB),
-    .tp_flags           = BASETYPE_FLAGS,
-    .tp_traverse        = (traverseproc)VB_traverse,
-    .tp_clear           = (inquiry)VB_clear,
-    .tp_dealloc         = (destructor)&VB_dealloc,
-    .tp_methods         = VB_methods,
-};
-
-
-#else
-
-/*
- * Heap type: VerifyingBase
- */
-static PyType_Slot VB_type_slots[] = {
-    {Py_tp_doc,         VB__doc__},
-    {Py_tp_traverse,    VB_traverse},
-    {Py_tp_clear,       VB_clear},
-    {Py_tp_dealloc,     VB_dealloc},
-    {Py_tp_methods,     VB_methods},
-    /* tp_base cannot be set as a slot -- pass to PyType_FromModuleAndSpec */
-    {0,                 NULL}
-};
-
-static PyType_Spec VB_type_spec = {
-    .name               = VB__name__,
-    .basicsize          = sizeof(VB),
-    .flags              = BASETYPE_FLAGS,
-    .slots              = VB_type_slots
-};
-
-#endif
-
-
-/*
- * Module state struct:  holds all data formerly kept as static globals.
- */
-typedef struct
-{
-    /* our globals (exposed to Python) */
-    PyTypeObject*   specification_base_class;
-    PyTypeObject*   object_specification_descriptor_class;
-    PyTypeObject*   class_provides_base_class;
-    PyTypeObject*   interface_base_class;
-    PyTypeObject*   lookup_base_class;
-    PyTypeObject*   verifying_base_class;
-    PyObject*       adapter_hooks;
-    /* members imported from 'zope.interface.declarations'
-     */
-    PyObject*       empty;
-    PyObject*       fallback;
-    PyObject*       builtin_impl_specs;
-    PyTypeObject*   implements_class;
-    /* flag:  have we imported the next set of members yet from
-     * 'zope.interface.declarations?
-     */
-    int             decl_imported;
-} _zic_module_state;
-
-/*
- *  Macro to speed lookup of state members
- */
-#define _zic_state(o) ((_zic_module_state*)PyModule_GetState(o))
-
-static _zic_module_state*
-_zic_state_init(PyObject* module)
-{
-    _zic_module_state* rec = _zic_state(module);
-
-    rec->specification_base_class = NULL;
-    rec->object_specification_descriptor_class = NULL;
-    rec->class_provides_base_class = NULL;
-    rec->interface_base_class = NULL;
-    rec->lookup_base_class = NULL;
-    rec->verifying_base_class = NULL;
-    rec->adapter_hooks = NULL;
-
-    rec->builtin_impl_specs = NULL;
-    rec->empty = NULL;
-    rec->fallback = NULL;
-    rec->implements_class = NULL;
-    rec->decl_imported = 0;
-
-    return rec;
-}
-
-static int
-_zic_state_traverse(PyObject* module, visitproc visit, void* arg)
-{
-    _zic_module_state* rec = _zic_state(module);
-
-    Py_VISIT(rec->specification_base_class);
-    Py_VISIT(rec->object_specification_descriptor_class);
-    Py_VISIT(rec->class_provides_base_class);
-    Py_VISIT(rec->interface_base_class);
-    Py_VISIT(rec->lookup_base_class);
-    Py_VISIT(rec->verifying_base_class);
-    Py_VISIT(rec->adapter_hooks);
-
-    Py_VISIT(rec->builtin_impl_specs);
-    Py_VISIT(rec->empty);
-    Py_VISIT(rec->fallback);
-    Py_VISIT(rec->implements_class);
-
-    return 0;
-}
-
-static int
-_zic_state_clear(PyObject* module)
-{
-    _zic_module_state* rec = _zic_state(module);
-
-    Py_CLEAR(rec->specification_base_class);
-    Py_CLEAR(rec->object_specification_descriptor_class);
-    Py_CLEAR(rec->class_provides_base_class);
-    Py_CLEAR(rec->interface_base_class);
-    Py_CLEAR(rec->lookup_base_class);
-    Py_CLEAR(rec->verifying_base_class);
-    Py_CLEAR(rec->adapter_hooks);
-
-    Py_CLEAR(rec->builtin_impl_specs);
-    Py_CLEAR(rec->empty);
-    Py_CLEAR(rec->fallback);
-    Py_CLEAR(rec->implements_class);
-
-    return 0;
-}
-
-#if USE_HEAP_TYPES
-/* Import zope.interface.declarations and store results in module state.
- *
- * Dynamic alternative to 'import_declarations' above.
- */
-static _zic_module_state*
-_zic_state_load_declarations(PyObject* module)
-{
-    PyObject* declarations;
-    PyObject* builtin_impl_specs;
-    PyObject* empty;
-    PyObject* fallback;
-    PyObject* implements;
-
-    _zic_module_state* rec = _zic_state(module);
-
-    if (!rec->decl_imported) {
-        declarations = PyImport_ImportModule("zope.interface.declarations");
-        if (declarations == NULL) {
-            return NULL;
-        }
-
-        builtin_impl_specs = PyObject_GetAttrString(
-          declarations, "BuiltinImplementationSpecifications");
-        if (builtin_impl_specs == NULL) {
-            return NULL;
-        }
-
-        empty = PyObject_GetAttrString(declarations, "_empty");
-        if (empty == NULL) {
-            return NULL;
-        }
-
-        fallback =
-          PyObject_GetAttrString(declarations, "implementedByFallback");
-        if (fallback == NULL) {
-            return NULL;
-        }
-
-        implements = PyObject_GetAttrString(declarations, "Implements");
-        if (implements == NULL) {
-            return NULL;
-        }
-
-        if (!PyType_Check(implements)) {
-            PyErr_SetString(
-              PyExc_TypeError,
-              "zope.interface.declarations.Implements is not a type");
-            return NULL;
-        }
-
-        Py_DECREF(declarations);
-
-        rec->builtin_impl_specs = builtin_impl_specs;
-        rec->empty = empty;
-        rec->fallback = fallback;
-        rec->implements_class = (PyTypeObject*)implements;
-        rec->decl_imported = 1;
-    }
-    return rec;
-}
-
-#endif
-
-/*
- *  Provide access to the current module given the type.
- */
-
-static struct PyModuleDef _zic_module_def;
-
-static PyObject*
-_get_module(PyTypeObject *typeobj)
-{
-#if USE_STATIC_TYPES
-    return (PyObject*)&_zic_module_def;
-#else
-    if (PyType_Check(typeobj)) {
-        /* Only added in Python 3.11 */
-        return PyType_GetModuleByDef(typeobj, &_zic_module_def);
-    }
-
-    PyErr_SetString(PyExc_TypeError, "_get_module: called w/ non-type");
-    return NULL;
-#endif
-}
-
-/*
- * Fetch the adapter hooks for the current type's module.
- */
-static PyObject*
-_get_adapter_hooks(PyTypeObject *typeobj)
-{
-#if USE_STATIC_TYPES
-    return adapter_hooks;
-#else
-    PyObject* module;
-    _zic_module_state* rec;
-
-    module = _get_module(typeobj);
-    if (module == NULL) { return NULL; }
-
-    rec = _zic_state(module);
-    return rec->adapter_hooks;
-#endif
-}
-
-/*
- * Fetch the 'SpecificationBase' class for the current type's module.
- */
-static PyTypeObject*
-_get_specification_base_class(PyTypeObject *typeobj)
-{
-#if USE_STATIC_TYPES
-    return &SB_type_def;
-#else
-    PyObject* module;
-    _zic_module_state* rec;
-
-    module = _get_module(typeobj);
-    if (module == NULL) { return NULL; }
-
-    rec = _zic_state(module);
-    return rec->specification_base_class;
-#endif
-}
-
-/*
- * Fetch the 'InterfaceBase' class for the current type's module.
- */
-static PyTypeObject*
-_get_interface_base_class(PyTypeObject *typeobj)
-{
-#if USE_STATIC_TYPES
-    return &IB_type_def;
-#else
-    PyObject* module;
-    _zic_module_state* rec;
-
-    module = _get_module(typeobj);
-    if (module == NULL) { return NULL; }
-
-    rec = _zic_state(module);
-    return rec->interface_base_class;
-#endif
-}
-
-static PyObject*
-implementedByFallback(PyObject* module, PyObject* cls)
-{
-#if USE_STATIC_TYPES
-    if (imported_declarations == 0 && import_declarations() < 0) {
-        return NULL;
-    }
-    /* now use static 'fallback' */
-#else
-    PyObject* fallback;
-
-    _zic_module_state* rec = _zic_state_load_declarations(module);
-    if (rec == NULL) { return NULL; }
-
-    fallback = rec->fallback;
-#endif
-
-    return PyObject_CallFunctionObjArgs(fallback, cls, NULL);
-}
-
-static char implementedBy___doc__[] =
-  ("Interfaces implemented by a class or factory.\n"
-   "Raises TypeError if argument is neither a class nor a callable.");
-
-static PyObject*
-implementedBy(PyObject* module, PyObject* cls)
-{
-    /* Fast retrieval of implements spec, if possible, to optimize
-       common case.  Use fallback code if we get stuck.
-    */
-    PyObject *dict = NULL;
-    PyObject *spec;
-    PyTypeObject *implements_class;
-    PyObject *builtin_impl_specs;
-
-#if USE_STATIC_TYPES
-    if (imported_declarations == 0 && import_declarations() < 0) {
-        return NULL;
-    }
-
-    implements_class = Implements;
-    builtin_impl_specs = BuiltinImplementationSpecifications;
-#else
-    _zic_module_state* rec = _zic_state_load_declarations(module);
-    if (rec == NULL) { return NULL; }
-
-    implements_class = rec->implements_class;
-    builtin_impl_specs = rec->builtin_impl_specs;
-#endif
-
-    if (PyObject_TypeCheck(cls, &PySuper_Type)) {
-        // Let merging be handled by Python.
-        return implementedByFallback(module, cls);
-    }
-
-    if (PyType_Check(cls)) {
-        dict = TYPE(cls)->tp_dict;
-        Py_XINCREF(dict);
-    }
-
-    if (dict == NULL)
-        dict = PyObject_GetAttr(cls, str__dict__);
-
-    if (dict == NULL) {
-        /* Probably a security proxied class, use more expensive fallback code
-         */
-        PyErr_Clear();
-        return implementedByFallback(module, cls);
-    }
-
-    spec = PyObject_GetItem(dict, str__implemented__);
-    Py_DECREF(dict);
-    if (spec) {
-
-        if (PyObject_TypeCheck(spec, implements_class))
-            return spec;
-
-        /* Old-style declaration, use more expensive fallback code */
-        Py_DECREF(spec);
-        return implementedByFallback(module, cls);
-    }
-
-    PyErr_Clear();
-
-    /* Maybe we have a builtin */
-    spec = PyDict_GetItem(builtin_impl_specs, cls);
-    if (spec != NULL) {
-        Py_INCREF(spec);
-        return spec;
-    }
-
-    /* We're stuck, use fallback */
-    return implementedByFallback(module, cls);
-}
-
-static char getObjectSpecification___doc__[] =
-  ("Get an object's interfaces (internal api)");
-
-static PyObject*
-getObjectSpecification(PyObject* module, PyObject* ob)
-{
-    PyObject *cls;
-    PyObject *result;
-    PyTypeObject *specification_base_class;
-    PyObject *empty_;
-
-#if USE_STATIC_TYPES
-    specification_base_class = &SB_type_def;
-
-    if (imported_declarations == 0 && import_declarations() < 0) {
-        return NULL;
-    }
-    empty_ = empty;  /* global from import */
-
-#else
-    _zic_module_state* rec = _zic_state_load_declarations(module);
-    if (rec == NULL) { return NULL; }
-
-    specification_base_class = rec->specification_base_class;
-    empty_ = rec->empty;
-#endif
-
-    result = PyObject_GetAttr(ob, str__provides__);
-    if (!result) {
-        if (!PyErr_ExceptionMatches(PyExc_AttributeError)) {
-            /* Propagate non AttributeError exceptions. */
-            return NULL;
-        }
-        PyErr_Clear();
-    } else {
-        int is_instance = -1;
-        is_instance =
-          PyObject_IsInstance(result, OBJECT(specification_base_class));
-        if (is_instance < 0) {
-            /* Propagate all errors */
-            return NULL;
-        }
-        if (is_instance) {
-            return result;
-        }
-    }
-
-    /* We do a getattr here so as not to be defeated by proxies */
-    cls = PyObject_GetAttr(ob, str__class__);
-    if (cls == NULL) {
-        if (!PyErr_ExceptionMatches(PyExc_AttributeError)) {
-            /* Propagate non-AttributeErrors */
-            return NULL;
-        }
-        PyErr_Clear();
-
-        Py_INCREF(empty_);
-        return empty_;
-    }
-    result = implementedBy(module, cls);
-    Py_DECREF(cls);
-
-    return result;
-}
-
-static char providedBy___doc__[] = ("Get an object's interfaces");
-
-static PyObject*
-providedBy(PyObject* module, PyObject* ob)
-{
-    PyObject *result = NULL;
-    PyObject *cls;
-    PyObject *cp;
-    PyTypeObject *specification_base_class;
-    int is_instance = -1;
-
-    is_instance = PyObject_IsInstance(ob, (PyObject*)&PySuper_Type);
-    if (is_instance < 0) {
-        if (!PyErr_ExceptionMatches(PyExc_AttributeError)) {
-            /* Propagate non-AttributeErrors */
-            return NULL;
-        }
-        PyErr_Clear();
-    }
-    if (is_instance) {
-        return implementedBy(module, ob);
-    }
-
-    result = PyObject_GetAttr(ob, str__providedBy__);
-
-    if (result == NULL) {
-        if (!PyErr_ExceptionMatches(PyExc_AttributeError)) {
-            return NULL;
-        }
-
-        PyErr_Clear();
-        return getObjectSpecification(module, ob);
-    }
-
-    /* We want to make sure we have a spec. We can't do a type check
-       because we may have a proxy, so we'll just try to get the
-       only attribute.
-    */
-#if USE_STATIC_TYPES
-    specification_base_class = &SB_type_def;
-#else
-    _zic_module_state* rec = _zic_state(module);
-    specification_base_class = rec->specification_base_class;
-#endif
-    if (PyObject_TypeCheck(result, specification_base_class) ||
-        PyObject_HasAttrString(result, "extends"))
-        return result;
-
-    /*
-      The object's class doesn't understand descriptors.
-      Sigh. We need to get an object descriptor, but we have to be
-      careful.  We want to use the instance's __provides__,l if
-      there is one, but only if it didn't come from the class.
-    */
-    Py_DECREF(result);
-
-    cls = PyObject_GetAttr(ob, str__class__);
-    if (cls == NULL)
-        return NULL;
-
-    result = PyObject_GetAttr(ob, str__provides__);
-    if (result == NULL) {
-        /* No __provides__, so just fall back to implementedBy */
-        PyErr_Clear();
-        result = implementedBy(module, cls);
-        Py_DECREF(cls);
-        return result;
-    }
-
-    cp = PyObject_GetAttr(cls, str__provides__);
-    if (cp == NULL) {
-        /* The the class has no provides, assume we're done: */
-        PyErr_Clear();
-        Py_DECREF(cls);
-        return result;
-    }
-
-    if (cp == result) {
-        /*
-          Oops, we got the provides from the class. This means
-          the object doesn't have it's own. We should use implementedBy
-        */
-        Py_DECREF(result);
-        result = implementedBy(module, cls);
-    }
-
-    Py_DECREF(cls);
-    Py_DECREF(cp);
-
-    return result;
-}
-
-static struct PyMethodDef _zic_module_methods[] = {
-    { "implementedBy",
-      (PyCFunction)implementedBy,
-      METH_O,
-      implementedBy___doc__ },
-    { "getObjectSpecification",
-      (PyCFunction)getObjectSpecification,
-      METH_O,
-      getObjectSpecification___doc__ },
-    { "providedBy", (PyCFunction)providedBy, METH_O, providedBy___doc__ },
-
-    { NULL, (PyCFunction)NULL, 0, NULL } /* sentinel */
-};
-
-
-/* Handler for the 'execute' phase of multi-phase initialization
- *
- * See: https://docs.python.org/3/c-api/module.html#multi-phase-initialization
- * and: https://peps.python.org/pep-0489/#module-execution-phase
- */
-static int
-_zic_module_exec(PyObject* module)
-{
-    _zic_module_state* rec = _zic_state_init(module);
-
-    rec->adapter_hooks = PyList_New(0);
-    if (rec->adapter_hooks == NULL)
-        return -1;
-    Py_INCREF(rec->adapter_hooks);
-
-#if USE_STATIC_TYPES
-
-    /* Initialize static global */
-    adapter_hooks = rec->adapter_hooks;
-
-    /* Initialize types: */
-    SB_type_def.tp_new = PyBaseObject_Type.tp_new;
-    if (PyType_Ready(&SB_type_def) < 0) { return -1; }
-    Py_INCREF(&SB_type_def);
-    rec->specification_base_class = &SB_type_def;
-
-    OSD_type_def.tp_new = PyBaseObject_Type.tp_new;
-    if (PyType_Ready(&OSD_type_def) < 0) { return -1; }
-    Py_INCREF(&OSD_type_def);
-    rec->object_specification_descriptor_class = &OSD_type_def;
-
-    CPB_type_def.tp_new = PyBaseObject_Type.tp_new;
-    if (PyType_Ready(&CPB_type_def) < 0) { return -1; }
-    Py_INCREF(&CPB_type_def);
-    rec->class_provides_base_class = &CPB_type_def;
-
-    IB_type_def.tp_new = PyBaseObject_Type.tp_new;
-    if (PyType_Ready(&IB_type_def) < 0) { return -1; }
-    Py_INCREF(&IB_type_def);
-    rec->interface_base_class = &IB_type_def;
-
-    LB_type_def.tp_new = PyBaseObject_Type.tp_new;
-    if (PyType_Ready(&LB_type_def) < 0) { return -1; }
-    Py_INCREF(&LB_type_def);
-    rec->lookup_base_class = &LB_type_def;
-
-    VB_type_def.tp_new = PyBaseObject_Type.tp_new;
-    if (PyType_Ready(&VB_type_def) < 0) { return -1; }
-    Py_INCREF(&VB_type_def);
-    rec->verifying_base_class = &VB_type_def;
-
-#else
-
-    PyObject *sb_class;
-    PyObject *osd_class;
-    PyObject *cpb_class;
-    PyObject *ib_class;
-    PyObject *lb_class;
-    PyObject *vb_class;
-
-    /* Initialize types:
-     */
-    sb_class = PyType_FromModuleAndSpec(module, &SB_type_spec, NULL);
-    if (sb_class == NULL) { return -1; }
-    Py_INCREF(sb_class);
-    rec->specification_base_class = TYPE(sb_class);
-
-    osd_class = PyType_FromModuleAndSpec(module, &OSD_type_spec, NULL);
-    if (osd_class == NULL) { return -1; }
-    Py_INCREF(osd_class);
-    rec->object_specification_descriptor_class = TYPE(osd_class);
-
-    cpb_class = PyType_FromModuleAndSpec(module, &CPB_type_spec, sb_class);
-    if (cpb_class == NULL) { return -1; }
-    Py_INCREF(cpb_class);
-    rec->class_provides_base_class = TYPE(cpb_class);
-
-    ib_class = PyType_FromModuleAndSpec(module, &IB_type_spec, sb_class);
-    if (ib_class == NULL) { return -1; }
-    Py_INCREF(ib_class);
-    rec->interface_base_class = TYPE(ib_class);
-
-    lb_class = PyType_FromModuleAndSpec(module, &LB_type_spec, NULL);
-    if (lb_class == NULL) { return -1; }
-    Py_INCREF(lb_class);
-    rec->lookup_base_class = TYPE(lb_class);
-
-    vb_class = PyType_FromModuleAndSpec(module, &VB_type_spec, lb_class);
-    if (vb_class == NULL) { return -1; }
-    Py_INCREF(vb_class);
-    rec->verifying_base_class = TYPE(vb_class);
-
-#endif
-
-    /* Add types to our dict FBO python;  also the adapter hooks */
-    if (PyModule_AddObject(module,
-        "SpecificationBase", OBJECT(rec->specification_base_class)) < 0)
-        return -1;
-
-    if (PyModule_AddObject(module,
-        "ObjectSpecificationDescriptor",
-        OBJECT(rec->object_specification_descriptor_class)) <
-        0)
-        return -1;
-
-    if (PyModule_AddObject(module,
-        "ClassProvidesBase", OBJECT(rec->class_provides_base_class)) < 0)
-        return -1;
-
-    if (PyModule_AddObject(module,
-        "InterfaceBase", OBJECT(rec->interface_base_class)) < 0)
-        return -1;
-
-    if (PyModule_AddObject(module,
-        "LookupBase", OBJECT(rec->lookup_base_class)) < 0)
-        return -1;
-
-    if (PyModule_AddObject(module,
-        "VerifyingBase", OBJECT(rec->verifying_base_class)) < 0)
-        return -1;
-
-    if (PyModule_AddObject(module, "adapter_hooks", rec->adapter_hooks) < 0)
-        return -1;
-
-    return 0;
-}
-
-
-/* Slot definitions for multi-phase initialization
- *
- * See: https://docs.python.org/3/c-api/module.html#multi-phase-initialization
- * and: https://peps.python.org/pep-0489
- */
-static PyModuleDef_Slot _zic_module_slots[] = {
-    {Py_mod_exec,       _zic_module_exec},
-    {0,                 NULL}
-};
-
-static char _zic_module__doc__[] = "C optimizations for zope.interface\n\n";
-
-static struct PyModuleDef _zic_module_def = {
-    PyModuleDef_HEAD_INIT,
-    .m_name = "_zope_interface_coptimizations",
-    .m_doc = _zic_module__doc__,
-    .m_size = sizeof(_zic_module_state),
-    .m_methods = _zic_module_methods,
-    .m_slots=_zic_module_slots,
-    .m_traverse = _zic_state_traverse,
-    .m_clear = _zic_state_clear,
-};
-
-static PyObject*
-init(void)
-{
-    if (define_static_strings() < 0) { return NULL; }
-
-    return PyModuleDef_Init(&_zic_module_def);
-}
-
-PyMODINIT_FUNC
-PyInit__zope_interface_coptimizations(void)
-{
-    return init();
-}
-
-#ifdef __clang__
-#pragma clang diagnostic pop
-#endif
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/_zope_interface_coptimizations.cpython-312-x86_64-linux-gnu.so b/llmlab/lib/python3.12/site-packages/zope/interface/_zope_interface_coptimizations.cpython-312-x86_64-linux-gnu.so
deleted file mode 100755
index 1eb0ce0..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/_zope_interface_coptimizations.cpython-312-x86_64-linux-gnu.so and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/adapter.py b/llmlab/lib/python3.12/site-packages/zope/interface/adapter.py
deleted file mode 100644
index a35c3f9..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/adapter.py
+++ /dev/null
@@ -1,1048 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2004 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Adapter management
-"""
-import itertools
-import weakref
-
-from zope.interface import Interface
-from zope.interface import implementer
-from zope.interface import providedBy
-from zope.interface import ro
-from zope.interface._compat import _normalize_name
-from zope.interface._compat import _use_c_impl
-from zope.interface.interfaces import IAdapterRegistry
-
-
-__all__ = [
-    'AdapterRegistry',
-    'VerifyingAdapterRegistry',
-]
-
-# In the CPython implementation,
-# ``tuple`` and ``list`` cooperate so that ``tuple([some list])``
-# directly allocates and iterates at the C level without using a
-# Python iterator. That's not the case for
-# ``tuple(generator_expression)`` or ``tuple(map(func, it))``.
-##
-# 3.8
-# ``tuple([t for t in range(10)])``      -> 610ns
-# ``tuple(t for t in range(10))``        -> 696ns
-# ``tuple(map(lambda t: t, range(10)))`` -> 881ns
-##
-# 2.7
-# ``tuple([t fon t in range(10)])``      -> 625ns
-# ``tuple(t for t in range(10))``        -> 665ns
-# ``tuple(map(lambda t: t, range(10)))`` -> 958ns
-#
-# All three have substantial variance.
-##
-# On PyPy, this is also the best option.
-##
-# PyPy 2.7.18-7.3.3
-# ``tuple([t fon t in range(10)])``      -> 128ns
-# ``tuple(t for t in range(10))``        -> 175ns
-# ``tuple(map(lambda t: t, range(10)))`` -> 153ns
-##
-# PyPy 3.7.9 7.3.3-beta
-# ``tuple([t fon t in range(10)])``      ->  82ns
-# ``tuple(t for t in range(10))``        -> 177ns
-# ``tuple(map(lambda t: t, range(10)))`` -> 168ns
-
-
-class BaseAdapterRegistry:
-    """
-    A basic implementation of the data storage and algorithms required
-    for a :class:`zope.interface.interfaces.IAdapterRegistry`.
-
-    Subclasses can set the following attributes to control how the data
-    is stored; in particular, these hooks can be helpful for ZODB
-    persistence. They can be class attributes that are the named
-    (or similar) type, or they can be methods that act as a constructor
-    for an object that behaves like the types defined here; this object
-    will not assume that they are type objects, but subclasses are free
-    to do so:
-
-    _sequenceType = list
-      This is the type used for our two mutable top-level "byorder" sequences.
-      Must support mutation operations like ``append()`` and ``del
-      seq[index]``.  These are usually small (< 10). Although at least one of
-      them is accessed when performing lookups or queries on this object, the
-      other is untouched. In many common scenarios, both are only required
-      when mutating registrations and subscriptions (like what
-      :meth:`zope.interface.interfaces.IComponents.registerUtility` does).
-      This use pattern makes it an ideal candidate to be a
-      :class:`~persistent.list.PersistentList`.
-
-    _leafSequenceType = tuple
-      This is the type used for the leaf sequences of subscribers.
-      It could be set to a ``PersistentList`` to avoid many unnecessary data
-      loads when subscribers aren't being used. Mutation operations are
-      directed through :meth:`_addValueToLeaf` and
-      :meth:`_removeValueFromLeaf`; if you use a mutable type, you'll need to
-      override those.
-
-    _mappingType = dict
-      This is the mutable mapping type used for the keyed mappings.  A
-      :class:`~persistent.mapping.PersistentMapping` could be used to help
-      reduce the number of data loads when the registry is large and parts of
-      it are rarely used. Further reductions in data loads can come from using
-      a :class:`~BTrees.OOBTree.OOBTree`, but care is required to be sure that
-      all required/provided values are fully ordered (e.g., no required or
-      provided values that are classes can be used).
-
-    _providedType = dict
-      This is the mutable mapping type used for the ``_provided`` mapping.
-      This is separate from the generic mapping type because the values
-      are always integers, so one might choose to use a more optimized data
-      structure such as a :class:`~BTrees.OIBTree.OIBTree`.
-      The same caveats regarding key types
-      apply as for ``_mappingType``.
-
-    It is possible to also set these on an instance, but because of the need
-    to potentially also override :meth:`_addValueToLeaf` and
-    :meth:`_removeValueFromLeaf`, this may be less useful in a persistent
-    scenario; using a subclass is recommended.
-
-    .. versionchanged:: 5.3.0
-        Add support for customizing the way internal data
-        structures are created.
-    .. versionchanged:: 5.3.0
-        Add methods :meth:`rebuild`, :meth:`allRegistrations`
-        and :meth:`allSubscriptions`.
-    """
-
-    # List of methods copied from lookup sub-objects:
-    _delegated = ('lookup', 'queryMultiAdapter', 'lookup1', 'queryAdapter',
-                  'adapter_hook', 'lookupAll', 'names',
-                  'subscriptions', 'subscribers')
-
-    # All registries maintain a generation that can be used by verifying
-    # registries
-    _generation = 0
-
-    def __init__(self, bases=()):
-
-        # The comments here could be improved. Possibly this bit needs
-        # explaining in a separate document, as the comments here can
-        # be quite confusing. /regebro
-
-        # {order -> {required -> {provided -> {name -> value}}}}
-        # Here "order" is actually an index in a list, "required" and
-        # "provided" are interfaces, and "required" is really a nested
-        # key.  So, for example:
-        # for order == 0 (that is, self._adapters[0]), we have:
-        #   {provided -> {name -> value}}
-        # but for order == 2 (that is, self._adapters[2]), we have:
-        #   {r1 -> {r2 -> {provided -> {name -> value}}}}
-        #
-        self._adapters = self._sequenceType()
-
-        # {order -> {required -> {provided -> {name -> [value]}}}}
-        # where the remarks about adapters above apply
-        self._subscribers = self._sequenceType()
-
-        # Set, with a reference count, keeping track of the interfaces
-        # for which we have provided components:
-        self._provided = self._providedType()
-
-        # Create ``_v_lookup`` object to perform lookup.  We make this a
-        # separate object to to make it easier to implement just the
-        # lookup functionality in C.  This object keeps track of cache
-        # invalidation data in two kinds of registries.
-
-        #   Invalidating registries have caches that are invalidated
-        #     when they or their base registies change.  An invalidating
-        #     registry can only have invalidating registries as bases.
-        #     See LookupBaseFallback below for the pertinent logic.
-
-        #   Verifying registies can't rely on getting invalidation messages,
-        #     so have to check the generations of base registries to determine
-        #     if their cache data are current.  See VerifyingBasePy below
-        #     for the pertinent object.
-        self._createLookup()
-
-        # Setting the bases causes the registries described above
-        # to be initialized (self._setBases -> self.changed ->
-        # self._v_lookup.changed).
-
-        self.__bases__ = bases
-
-    def _setBases(self, bases):
-        """
-        If subclasses need to track when ``__bases__`` changes, they
-        can override this method.
-
-        Subclasses must still call this method.
-        """
-        self.__dict__['__bases__'] = bases
-        self.ro = ro.ro(self)
-        self.changed(self)
-
-    __bases__ = property(lambda self: self.__dict__['__bases__'],
-                         lambda self, bases: self._setBases(bases),
-                         )
-
-    def _createLookup(self):
-        self._v_lookup = self.LookupClass(self)
-        for name in self._delegated:
-            self.__dict__[name] = getattr(self._v_lookup, name)
-
-    # Hooks for subclasses to define the types of objects used in
-    # our data structures.
-    # These have to be documented in the docstring, instead of local
-    # comments, because Sphinx autodoc ignores the comment and just writes
-    # "alias of list"
-    _sequenceType = list
-    _leafSequenceType = tuple
-    _mappingType = dict
-    _providedType = dict
-
-    def _addValueToLeaf(self, existing_leaf_sequence, new_item):
-        """
-        Add the value *new_item* to the *existing_leaf_sequence*, which may
-        be ``None``.
-
-        Subclasses that redefine `_leafSequenceType` should override this
-        method.
-
-        :param existing_leaf_sequence:
-            If *existing_leaf_sequence* is not *None*, it will be an instance
-            of `_leafSequenceType`. (Unless the object has been unpickled from
-            an old pickle and the class definition has changed, in which case
-            it may be an instance of a previous definition, commonly a
-            `tuple`.)
-
-        :return:
-           This method returns the new value to be stored. It may mutate the
-           sequence in place if it was not ``None`` and the type is mutable,
-           but it must also return it.
-
-        .. versionadded:: 5.3.0
-        """
-        if existing_leaf_sequence is None:
-            return (new_item,)
-        return existing_leaf_sequence + (new_item,)
-
-    def _removeValueFromLeaf(self, existing_leaf_sequence, to_remove):
-        """
-        Remove the item *to_remove* from the (non-``None``, non-empty)
-        *existing_leaf_sequence* and return the mutated sequence.
-
-        If there is more than one item that is equal to *to_remove*
-        they must all be removed.
-
-        Subclasses that redefine `_leafSequenceType` should override
-        this method. Note that they can call this method to help
-        in their implementation; this implementation will always
-        return a new tuple constructed by iterating across
-        the *existing_leaf_sequence* and omitting items equal to *to_remove*.
-
-        :param existing_leaf_sequence:
-           As for `_addValueToLeaf`, probably an instance of
-           `_leafSequenceType` but possibly an older type; never `None`.
-        :return:
-           A version of *existing_leaf_sequence* with all items equal to
-           *to_remove* removed. Must not return `None`. However,
-           returning an empty
-           object, even of another type such as the empty tuple, ``()`` is
-           explicitly allowed; such an object will never be stored.
-
-        .. versionadded:: 5.3.0
-        """
-        return tuple([v for v in existing_leaf_sequence if v != to_remove])
-
-    def changed(self, originally_changed):
-        self._generation += 1
-        self._v_lookup.changed(originally_changed)
-
-    def register(self, required, provided, name, value):
-        if not isinstance(name, str):
-            raise ValueError('name is not a string')
-        if value is None:
-            self.unregister(required, provided, name, value)
-            return
-
-        required = tuple([_convert_None_to_Interface(r) for r in required])
-        name = _normalize_name(name)
-        order = len(required)
-        byorder = self._adapters
-        while len(byorder) <= order:
-            byorder.append(self._mappingType())
-        components = byorder[order]
-        key = required + (provided,)
-
-        for k in key:
-            d = components.get(k)
-            if d is None:
-                d = self._mappingType()
-                components[k] = d
-            components = d
-
-        if components.get(name) is value:
-            return
-
-        components[name] = value
-
-        n = self._provided.get(provided, 0) + 1
-        self._provided[provided] = n
-        if n == 1:
-            self._v_lookup.add_extendor(provided)
-
-        self.changed(self)
-
-    def _find_leaf(self, byorder, required, provided, name):
-        # Find the leaf value, if any, in the *byorder* list
-        # for the interface sequence *required* and the interface
-        # *provided*, given the already normalized *name*.
-        #
-        # If no such leaf value exists, returns ``None``
-        required = tuple([_convert_None_to_Interface(r) for r in required])
-        order = len(required)
-        if len(byorder) <= order:
-            return None
-
-        components = byorder[order]
-        key = required + (provided,)
-
-        for k in key:
-            d = components.get(k)
-            if d is None:
-                return None
-            components = d
-
-        return components.get(name)
-
-    def registered(self, required, provided, name=''):
-        return self._find_leaf(
-            self._adapters,
-            required,
-            provided,
-            _normalize_name(name)
-        )
-
-    @classmethod
-    def _allKeys(cls, components, i, parent_k=()):
-        if i == 0:
-            for k, v in components.items():
-                yield parent_k + (k,), v
-        else:
-            for k, v in components.items():
-                new_parent_k = parent_k + (k,)
-                yield from cls._allKeys(v, i - 1, new_parent_k)
-
-    def _all_entries(self, byorder):
-        # Recurse through the mapping levels of the `byorder` sequence,
-        # reconstructing a flattened sequence of ``(required, provided, name,
-        # value)`` tuples that can be used to reconstruct the sequence with
-        # the appropriate registration methods.
-        #
-        # Locally reference the `byorder` data; it might be replaced while
-        # this method is running (see ``rebuild``).
-        for i, components in enumerate(byorder):
-            # We will have *i* levels of dictionaries to go before
-            # we get to the leaf.
-            for key, value in self._allKeys(components, i + 1):
-                assert len(key) == i + 2
-                required = key[:i]
-                provided = key[-2]
-                name = key[-1]
-                yield (required, provided, name, value)
-
-    def allRegistrations(self):
-        """
-        Yields tuples ``(required, provided, name, value)`` for all
-        the registrations that this object holds.
-
-        These tuples could be passed as the arguments to the
-        :meth:`register` method on another adapter registry to
-        duplicate the registrations this object holds.
-
-        .. versionadded:: 5.3.0
-        """
-        yield from self._all_entries(self._adapters)
-
-    def unregister(self, required, provided, name, value=None):
-        required = tuple([_convert_None_to_Interface(r) for r in required])
-        order = len(required)
-        byorder = self._adapters
-        if order >= len(byorder):
-            return False
-        components = byorder[order]
-        key = required + (provided,)
-
-        # Keep track of how we got to `components`:
-        lookups = []
-        for k in key:
-            d = components.get(k)
-            if d is None:
-                return
-            lookups.append((components, k))
-            components = d
-
-        old = components.get(name)
-        if old is None:
-            return
-        if (value is not None) and (old is not value):
-            return
-
-        del components[name]
-        if not components:
-            # Clean out empty containers, since we don't want our keys
-            # to reference global objects (interfaces) unnecessarily.
-            # This is often a problem when an interface is slated for
-            # removal; a hold-over entry in the registry can make it
-            # difficult to remove such interfaces.
-            for comp, k in reversed(lookups):
-                d = comp[k]
-                if d:
-                    break
-                else:
-                    del comp[k]
-            while byorder and not byorder[-1]:
-                del byorder[-1]
-        n = self._provided[provided] - 1
-        if n == 0:
-            del self._provided[provided]
-            self._v_lookup.remove_extendor(provided)
-        else:
-            self._provided[provided] = n
-
-        self.changed(self)
-
-    def subscribe(self, required, provided, value):
-        required = tuple([_convert_None_to_Interface(r) for r in required])
-        name = ''
-        order = len(required)
-        byorder = self._subscribers
-        while len(byorder) <= order:
-            byorder.append(self._mappingType())
-        components = byorder[order]
-        key = required + (provided,)
-
-        for k in key:
-            d = components.get(k)
-            if d is None:
-                d = self._mappingType()
-                components[k] = d
-            components = d
-
-        components[name] = self._addValueToLeaf(components.get(name), value)
-
-        if provided is not None:
-            n = self._provided.get(provided, 0) + 1
-            self._provided[provided] = n
-            if n == 1:
-                self._v_lookup.add_extendor(provided)
-
-        self.changed(self)
-
-    def subscribed(self, required, provided, subscriber):
-        subscribers = self._find_leaf(
-            self._subscribers,
-            required,
-            provided,
-            ''
-        ) or ()
-        return subscriber if subscriber in subscribers else None
-
-    def allSubscriptions(self):
-        """
-        Yields tuples ``(required, provided, value)`` for all the
-        subscribers that this object holds.
-
-        These tuples could be passed as the arguments to the
-        :meth:`subscribe` method on another adapter registry to
-        duplicate the registrations this object holds.
-
-        .. versionadded:: 5.3.0
-        """
-        for required, provided, _name, value in self._all_entries(
-            self._subscribers,
-        ):
-            for v in value:
-                yield (required, provided, v)
-
-    def unsubscribe(self, required, provided, value=None):
-        required = tuple([_convert_None_to_Interface(r) for r in required])
-        order = len(required)
-        byorder = self._subscribers
-        if order >= len(byorder):
-            return
-        components = byorder[order]
-        key = required + (provided,)
-
-        # Keep track of how we got to `components`:
-        lookups = []
-        for k in key:
-            d = components.get(k)
-            if d is None:
-                return
-            lookups.append((components, k))
-            components = d
-
-        old = components.get('')
-        if not old:
-            # this is belt-and-suspenders against the failure of cleanup below
-            return  # pragma: no cover
-        len_old = len(old)
-        if value is None:
-            # Removing everything; note that the type of ``new`` won't
-            # necessarily match the ``_leafSequenceType``, but that's
-            # OK because we're about to delete the entire entry
-            # anyway.
-            new = ()
-        else:
-            new = self._removeValueFromLeaf(old, value)
-        # ``new`` may be the same object as ``old``, just mutated in place,
-        # so we cannot compare it to ``old`` to check for changes. Remove
-        # our reference to it now to avoid trying to do so below.
-        del old
-
-        if len(new) == len_old:
-            # No changes, so nothing could have been removed.
-            return
-
-        if new:
-            components[''] = new
-        else:
-            # Instead of setting components[u''] = new, we clean out
-            # empty containers, since we don't want our keys to
-            # reference global objects (interfaces) unnecessarily.  This
-            # is often a problem when an interface is slated for
-            # removal; a hold-over entry in the registry can make it
-            # difficult to remove such interfaces.
-            del components['']
-            for comp, k in reversed(lookups):
-                d = comp[k]
-                if d:
-                    break
-                else:
-                    del comp[k]
-            while byorder and not byorder[-1]:
-                del byorder[-1]
-
-        if provided is not None:
-            n = self._provided[provided] + len(new) - len_old
-            if n == 0:
-                del self._provided[provided]
-                self._v_lookup.remove_extendor(provided)
-            else:
-                self._provided[provided] = n
-
-        self.changed(self)
-
-    def rebuild(self):
-        """
-        Rebuild (and replace) all the internal data structures of this
-        object.
-
-        This is useful, especially for persistent implementations, if
-        you suspect an issue with reference counts keeping interfaces
-        alive even though they are no longer used.
-
-        It is also useful if you or a subclass change the data types
-        (``_mappingType`` and friends) that are to be used.
-
-        This method replaces all internal data structures with new objects;
-        it specifically does not re-use any storage.
-
-        .. versionadded:: 5.3.0
-        """
-
-        # Grab the iterators, we're about to discard their data.
-        registrations = self.allRegistrations()
-        subscriptions = self.allSubscriptions()
-
-        def buffer(it):
-            # The generator doesn't actually start running until we
-            # ask for its next(), by which time the attributes will change
-            # unless we do so before calling __init__.
-            try:
-                first = next(it)
-            except StopIteration:
-                return iter(())
-
-            return itertools.chain((first,), it)
-
-        registrations = buffer(registrations)
-        subscriptions = buffer(subscriptions)
-
-        # Replace the base data structures as well as _v_lookup.
-        self.__init__(self.__bases__)
-        # Re-register everything previously registered and subscribed.
-        #
-        # XXX: This is going to call ``self.changed()`` a lot, all of
-        # which is unnecessary (because ``self.__init__`` just
-        # re-created those dependent objects and also called
-        # ``self.changed()``). Is this a bottleneck that needs fixed?
-        # (We could do ``self.changed = lambda _: None`` before
-        # beginning and remove it after to disable the presumably expensive
-        # part of passing that notification to the change of objects.)
-        for args in registrations:
-            self.register(*args)
-
-        for args in subscriptions:
-            self.subscribe(*args)
-
-    # XXX hack to fake out twisted's use of a private api.
-    # We need to get them to use the new registered method.
-    def get(self, _):  # pragma: no cover
-        class XXXTwistedFakeOut:
-            selfImplied = {}
-        return XXXTwistedFakeOut
-
-
-_not_in_mapping = object()
-
-
-@_use_c_impl
-class LookupBase:
-
-    def __init__(self):
-        self._cache = {}
-        self._mcache = {}
-        self._scache = {}
-
-    def changed(self, ignored=None):
-        self._cache.clear()
-        self._mcache.clear()
-        self._scache.clear()
-
-    def _getcache(self, provided, name):
-        cache = self._cache.get(provided)
-        if cache is None:
-            cache = {}
-            self._cache[provided] = cache
-        if name:
-            c = cache.get(name)
-            if c is None:
-                c = {}
-                cache[name] = c
-            cache = c
-        return cache
-
-    def lookup(self, required, provided, name='', default=None):
-        if not isinstance(name, str):
-            raise ValueError('name is not a string')
-        cache = self._getcache(provided, name)
-        required = tuple(required)
-        if len(required) == 1:
-            result = cache.get(required[0], _not_in_mapping)
-        else:
-            result = cache.get(tuple(required), _not_in_mapping)
-
-        if result is _not_in_mapping:
-            result = self._uncached_lookup(required, provided, name)
-            if len(required) == 1:
-                cache[required[0]] = result
-            else:
-                cache[tuple(required)] = result
-
-        if result is None:
-            return default
-
-        return result
-
-    def lookup1(self, required, provided, name='', default=None):
-        if not isinstance(name, str):
-            raise ValueError('name is not a string')
-        cache = self._getcache(provided, name)
-        result = cache.get(required, _not_in_mapping)
-        if result is _not_in_mapping:
-            return self.lookup((required, ), provided, name, default)
-
-        if result is None:
-            return default
-
-        return result
-
-    def queryAdapter(self, object, provided, name='', default=None):
-        return self.adapter_hook(provided, object, name, default)
-
-    def adapter_hook(self, provided, object, name='', default=None):
-        if not isinstance(name, str):
-            raise ValueError('name is not a string')
-        required = providedBy(object)
-        cache = self._getcache(provided, name)
-        factory = cache.get(required, _not_in_mapping)
-        if factory is _not_in_mapping:
-            factory = self.lookup((required, ), provided, name)
-
-        if factory is not None:
-            if isinstance(object, super):
-                object = object.__self__
-            result = factory(object)
-            if result is not None:
-                return result
-
-        return default
-
-    def lookupAll(self, required, provided):
-        cache = self._mcache.get(provided)
-        if cache is None:
-            cache = {}
-            self._mcache[provided] = cache
-
-        required = tuple(required)
-        result = cache.get(required, _not_in_mapping)
-        if result is _not_in_mapping:
-            result = self._uncached_lookupAll(required, provided)
-            cache[required] = result
-
-        return result
-
-    def subscriptions(self, required, provided):
-        cache = self._scache.get(provided)
-        if cache is None:
-            cache = {}
-            self._scache[provided] = cache
-
-        required = tuple(required)
-        result = cache.get(required, _not_in_mapping)
-        if result is _not_in_mapping:
-            result = self._uncached_subscriptions(required, provided)
-            cache[required] = result
-
-        return result
-
-
-@_use_c_impl
-class VerifyingBase(LookupBaseFallback):  # noqa F821
-    # Mixin for lookups against registries which "chain" upwards, and
-    # whose lookups invalidate their own caches whenever a parent registry
-    # bumps its own '_generation' counter.  E.g., used by
-    # zope.component.persistentregistry
-
-    def changed(self, originally_changed):
-        LookupBaseFallback.changed(self, originally_changed)  # noqa F821
-        self._verify_ro = self._registry.ro[1:]
-        self._verify_generations = [r._generation for r in self._verify_ro]
-
-    def _verify(self):
-        if (
-            [
-                r._generation for r in self._verify_ro
-            ] != self._verify_generations
-        ):
-            self.changed(None)
-
-    def _getcache(self, provided, name):
-        self._verify()
-        return LookupBaseFallback._getcache(  # noqa F821
-            self, provided, name,
-        )
-
-    def lookupAll(self, required, provided):
-        self._verify()
-        return LookupBaseFallback.lookupAll(  # noqa F821
-            self, required, provided,
-        )
-
-    def subscriptions(self, required, provided):
-        self._verify()
-        return LookupBaseFallback.subscriptions(  # noqa F821
-            self, required, provided,
-        )
-
-
-class AdapterLookupBase:
-
-    def __init__(self, registry):
-        self._registry = registry
-        self._required = {}
-        self.init_extendors()
-        super().__init__()
-
-    def changed(self, ignored=None):
-        super().changed(None)
-        for r in self._required.keys():
-            r = r()
-            if r is not None:
-                r.unsubscribe(self)
-        self._required.clear()
-
-    # Extendors
-    # ---------
-
-    # When given an target interface for an adapter lookup, we need to consider
-    # adapters for interfaces that extend the target interface.  This is
-    # what the extendors dictionary is about.  It tells us all of the
-    # interfaces that extend an interface for which there are adapters
-    # registered.
-
-    # We could separate this by order and name, thus reducing the
-    # number of provided interfaces to search at run time.  The tradeoff,
-    # however, is that we have to store more information.  For example,
-    # if the same interface is provided for multiple names and if the
-    # interface extends many interfaces, we'll have to keep track of
-    # a fair bit of information for each name.  It's better to
-    # be space efficient here and be time efficient in the cache
-    # implementation.
-
-    # TODO: add invalidation when a provided interface changes, in case
-    # the interface's __iro__ has changed.  This is unlikely enough that
-    # we'll take our chances for now.
-
-    def init_extendors(self):  # noqa E301
-        self._extendors = {}
-        for p in self._registry._provided:
-            self.add_extendor(p)
-
-    def add_extendor(self, provided):
-        _extendors = self._extendors
-        for i in provided.__iro__:
-            extendors = _extendors.get(i, ())
-            _extendors[i] = (
-                [
-                    e for e in extendors if provided.isOrExtends(e)
-                ] + [
-                    provided
-                ] + [
-                    e for e in extendors if not provided.isOrExtends(e)
-                ]
-            )
-
-    def remove_extendor(self, provided):
-        _extendors = self._extendors
-        for i in provided.__iro__:
-            _extendors[i] = [e for e in _extendors.get(i, ())
-                             if e != provided]
-
-    def _subscribe(self, *required):
-        _refs = self._required
-        for r in required:
-            ref = r.weakref()
-            if ref not in _refs:
-                r.subscribe(self)
-                _refs[ref] = 1
-
-    def _uncached_lookup(self, required, provided, name=''):
-        required = tuple(required)
-        result = None
-        order = len(required)
-        for registry in self._registry.ro:
-            byorder = registry._adapters
-            if order >= len(byorder):
-                continue
-
-            extendors = registry._v_lookup._extendors.get(provided)
-            if not extendors:
-                continue
-
-            components = byorder[order]
-            result = _lookup(components, required, extendors, name, 0,
-                             order)
-            if result is not None:
-                break
-
-        self._subscribe(*required)
-
-        return result
-
-    def queryMultiAdapter(self, objects, provided, name='', default=None):
-        factory = self.lookup([providedBy(o) for o in objects], provided, name)
-        if factory is None:
-            return default
-
-        result = factory(*[
-            o.__self__ if isinstance(o, super) else o for o in objects
-        ])
-        if result is None:
-            return default
-
-        return result
-
-    def _uncached_lookupAll(self, required, provided):
-        required = tuple(required)
-        order = len(required)
-        result = {}
-        for registry in reversed(self._registry.ro):
-            byorder = registry._adapters
-            if order >= len(byorder):
-                continue
-            extendors = registry._v_lookup._extendors.get(provided)
-            if not extendors:
-                continue
-            components = byorder[order]
-            _lookupAll(components, required, extendors, result, 0, order)
-
-        self._subscribe(*required)
-
-        return tuple(result.items())
-
-    def names(self, required, provided):
-        return [c[0] for c in self.lookupAll(required, provided)]
-
-    def _uncached_subscriptions(self, required, provided):
-        required = tuple(required)
-        order = len(required)
-        result = []
-        for registry in reversed(self._registry.ro):
-            byorder = registry._subscribers
-            if order >= len(byorder):
-                continue
-
-            if provided is None:
-                extendors = (provided, )
-            else:
-                extendors = registry._v_lookup._extendors.get(provided)
-                if extendors is None:
-                    continue
-
-            _subscriptions(byorder[order], required, extendors, '',
-                           result, 0, order)
-
-        self._subscribe(*required)
-
-        return result
-
-    def subscribers(self, objects, provided):
-        subscriptions = self.subscriptions(
-            [providedBy(o) for o in objects], provided
-        )
-        if provided is None:
-            result = ()
-            for subscription in subscriptions:
-                subscription(*objects)
-        else:
-            result = []
-            for subscription in subscriptions:
-                subscriber = subscription(*objects)
-                if subscriber is not None:
-                    result.append(subscriber)
-        return result
-
-
-class AdapterLookup(AdapterLookupBase, LookupBase):
-    pass
-
-
-@implementer(IAdapterRegistry)
-class AdapterRegistry(BaseAdapterRegistry):
-    """
-    A full implementation of ``IAdapterRegistry`` that adds support for
-    sub-registries.
-    """
-
-    LookupClass = AdapterLookup
-
-    def __init__(self, bases=()):
-        # AdapterRegisties are invalidating registries, so
-        # we need to keep track of our invalidating subregistries.
-        self._v_subregistries = weakref.WeakKeyDictionary()
-
-        super().__init__(bases)
-
-    def _addSubregistry(self, r):
-        self._v_subregistries[r] = 1
-
-    def _removeSubregistry(self, r):
-        if r in self._v_subregistries:
-            del self._v_subregistries[r]
-
-    def _setBases(self, bases):
-        old = self.__dict__.get('__bases__', ())
-        for r in old:
-            if r not in bases:
-                r._removeSubregistry(self)
-        for r in bases:
-            if r not in old:
-                r._addSubregistry(self)
-
-        super()._setBases(bases)
-
-    def changed(self, originally_changed):
-        super().changed(originally_changed)
-
-        for sub in self._v_subregistries.keys():
-            sub.changed(originally_changed)
-
-
-class VerifyingAdapterLookup(AdapterLookupBase, VerifyingBase):
-    pass
-
-
-@implementer(IAdapterRegistry)
-class VerifyingAdapterRegistry(BaseAdapterRegistry):
-    """
-    The most commonly-used adapter registry.
-    """
-
-    LookupClass = VerifyingAdapterLookup
-
-
-def _convert_None_to_Interface(x):
-    if x is None:
-        return Interface
-    else:
-        return x
-
-
-def _lookup(components, specs, provided, name, i, l):  # noqa: E741
-    # this function is called very often.
-    # The components.get in loops is executed 100 of 1000s times.
-    # by loading get into a local variable the bytecode
-    # "LOAD_FAST 0 (components)" in the loop can be eliminated.
-    components_get = components.get
-    if i < l:
-        for spec in specs[i].__sro__:
-            comps = components_get(spec)
-            if comps:
-                r = _lookup(comps, specs, provided, name, i + 1, l)
-                if r is not None:
-                    return r
-    else:
-        for iface in provided:
-            comps = components_get(iface)
-            if comps:
-                r = comps.get(name)
-                if r is not None:
-                    return r
-
-    return None
-
-
-def _lookupAll(components, specs, provided, result, i, l):  # noqa: E741
-    components_get = components.get  # see _lookup above
-    if i < l:
-        for spec in reversed(specs[i].__sro__):
-            comps = components_get(spec)
-            if comps:
-                _lookupAll(comps, specs, provided, result, i + 1, l)
-    else:
-        for iface in reversed(provided):
-            comps = components_get(iface)
-            if comps:
-                result.update(comps)
-
-
-def _subscriptions(
-    components, specs, provided, name, result, i, l  # noqa: E741
-):
-    components_get = components.get  # see _lookup above
-    if i < l:
-        for spec in reversed(specs[i].__sro__):
-            comps = components_get(spec)
-            if comps:
-                _subscriptions(
-                    comps, specs, provided, name, result, i + 1, l
-                )
-    else:
-        for iface in reversed(provided):
-            comps = components_get(iface)
-            if comps:
-                comps = comps.get(name)
-                if comps:
-                    result.extend(comps)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/advice.py b/llmlab/lib/python3.12/site-packages/zope/interface/advice.py
deleted file mode 100644
index f577d42..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/advice.py
+++ /dev/null
@@ -1,121 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Class advice.
-
-This module was adapted from 'protocols.advice', part of the Python
-Enterprise Application Kit (PEAK).  Please notify the PEAK authors
-(pje@telecommunity.com and tsarna@sarna.org) if bugs are found or
-Zope-specific changes are required, so that the PEAK version of this module
-can be kept in sync.
-
-PEAK is a Python application framework that interoperates with (but does
-not require) Zope 3 and Twisted.  It provides tools for manipulating UML
-models, object-relational persistence, aspect-oriented programming, and more.
-Visit the PEAK home page at http://peak.telecommunity.com for more information.
-"""
-
-from types import FunctionType
-
-
-__all__ = [
-    'determineMetaclass',
-    'getFrameInfo',
-    'isClassAdvisor',
-    'minimalBases',
-]
-
-import sys
-
-
-def getFrameInfo(frame):
-    """Return (kind,module,locals,globals) for a frame
-
-    'kind' is one of "exec", "module", "class", "function call", or "unknown".
-    """
-
-    f_locals = frame.f_locals
-    f_globals = frame.f_globals
-
-    sameNamespace = f_locals is f_globals
-    hasModule = '__module__' in f_locals
-    hasName = '__name__' in f_globals
-
-    sameName = hasModule and hasName
-    sameName = sameName and f_globals['__name__'] == f_locals['__module__']
-
-    module = hasName and sys.modules.get(f_globals['__name__']) or None
-
-    namespaceIsModule = module and module.__dict__ is f_globals
-
-    if not namespaceIsModule:
-        # some kind of funky exec
-        kind = "exec"
-    elif sameNamespace and not hasModule:
-        kind = "module"
-    elif sameName and not sameNamespace:
-        kind = "class"
-    elif not sameNamespace:
-        kind = "function call"
-    else:  # pragma: no cover
-        # How can you have f_locals is f_globals, and have '__module__'
-        # set?  # This is probably module-level code, but with a
-        # '__module__' variable.
-        kind = "unknown"
-    return kind, module, f_locals, f_globals
-
-
-def isClassAdvisor(ob):
-    """True if 'ob' is a class advisor function"""
-    return isinstance(ob, FunctionType) and hasattr(ob, 'previousMetaclass')
-
-
-def determineMetaclass(bases, explicit_mc=None):
-    """Determine metaclass from 1+ bases and optional explicit __metaclass__"""
-
-    meta = [getattr(b, '__class__', type(b)) for b in bases]
-
-    if explicit_mc is not None:
-        # The explicit metaclass needs to be verified for compatibility
-        # as well, and allowed to resolve the incompatible bases, if any
-        meta.append(explicit_mc)
-
-    if len(meta) == 1:
-        # easy case
-        return meta[0]
-
-    candidates = minimalBases(meta)  # minimal set of metaclasses
-
-    if len(candidates) > 1:
-        # We could auto-combine, but for now we won't...
-        raise TypeError("Incompatible metatypes", bases)
-
-    # Just one, return it
-    return candidates[0]
-
-
-def minimalBases(classes):
-    """Reduce a list of base classes to its ordered minimum equivalent"""
-    candidates = []
-
-    for m in classes:
-        for n in classes:
-            if issubclass(n, m) and m is not n:
-                break
-        else:
-            # m has no subclasses in 'classes'
-            if m in candidates:
-                candidates.remove(m)    # ensure that we're later in the list
-            candidates.append(m)
-
-    return candidates
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__init__.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/__init__.py
deleted file mode 100644
index 256ddc9..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/__init__.py
+++ /dev/null
@@ -1,291 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-
-import itertools
-from types import FunctionType
-
-from zope.interface import Interface
-from zope.interface import classImplements
-from zope.interface.interface import InterfaceClass
-from zope.interface.interface import _decorator_non_return
-from zope.interface.interface import fromFunction
-
-
-__all__ = [
-    # Nothing public here.
-]
-
-# pylint:disable=inherit-non-class,
-# pylint:disable=no-self-argument,no-method-argument
-# pylint:disable=unexpected-special-method-signature
-
-
-class optional:
-    # Apply this decorator to a method definition to make it
-    # optional (remove it from the list of required names), overriding
-    # the definition inherited from the ABC.
-    def __init__(self, method):
-        self.__doc__ = method.__doc__
-
-
-class ABCInterfaceClass(InterfaceClass):
-    """
-    An interface that is automatically derived from a
-    :class:`abc.ABCMeta` type.
-
-    Internal use only.
-
-    The body of the interface definition *must* define
-    a property ``abc`` that is the ABC to base the interface on.
-
-    If ``abc`` is *not* in the interface definition, a regular
-    interface will be defined instead (but ``extra_classes`` is still
-    respected).
-
-    Use the ``@optional`` decorator on method definitions if
-    the ABC defines methods that are not actually required in all cases
-    because the Python language has multiple ways to implement a protocol.
-    For example, the ``iter()`` protocol can be implemented with
-    ``__iter__`` or the pair ``__len__`` and ``__getitem__``.
-
-    When created, any existing classes that are registered to conform
-    to the ABC are declared to implement this interface. This is *not*
-    automatically updated as the ABC registry changes. If the body of the
-    interface definition defines ``extra_classes``, it should be a
-    tuple giving additional classes to declare implement the interface.
-
-    Note that this is not fully symmetric. For example, it is usually
-    the case that a subclass relationship carries the interface
-    declarations over::
-
-        >>> from zope.interface import Interface
-        >>> class I1(Interface):
-        ...     pass
-        ...
-        >>> from zope.interface import implementer
-        >>> @implementer(I1)
-        ... class Root(object):
-        ...     pass
-        ...
-        >>> class Child(Root):
-        ...     pass
-        ...
-        >>> child = Child()
-        >>> isinstance(child, Root)
-        True
-        >>> from zope.interface import providedBy
-        >>> list(providedBy(child))
-        []
-
-    However, that's not the case with ABCs and ABC interfaces. Just
-    because ``isinstance(A(), AnABC)`` and ``isinstance(B(), AnABC)``
-    are both true, that doesn't mean there's any class hierarchy
-    relationship between ``A`` and ``B``, or between either of them
-    and ``AnABC``. Thus, if ``AnABC`` implemented ``IAnABC``, it would
-    not follow that either ``A`` or ``B`` implements ``IAnABC`` (nor
-    their instances provide it)::
-
-        >>> class SizedClass(object):
-        ...     def __len__(self): return 1
-        ...
-        >>> from collections.abc import Sized
-        >>> isinstance(SizedClass(), Sized)
-        True
-        >>> from zope.interface import classImplements
-        >>> classImplements(Sized, I1)
-        None
-        >>> list(providedBy(SizedClass()))
-        []
-
-    Thus, to avoid conflicting assumptions, ABCs should not be
-    declared to implement their parallel ABC interface. Only concrete
-    classes specifically registered with the ABC should be declared to
-    do so.
-
-    .. versionadded:: 5.0.0
-    """
-
-    # If we could figure out invalidation, and used some special
-    # Specification/Declaration instances, and override the method
-    # ``providedBy`` here, perhaps we could more closely integrate with ABC
-    # virtual inheritance?
-
-    def __init__(self, name, bases, attrs):
-        # go ahead and give us a name to ease debugging.
-        self.__name__ = name
-        extra_classes = attrs.pop('extra_classes', ())
-        ignored_classes = attrs.pop('ignored_classes', ())
-
-        if 'abc' not in attrs:
-            # Something like ``IList(ISequence)``: We're extending
-            # abc interfaces but not an ABC interface ourself.
-            InterfaceClass.__init__(self, name, bases, attrs)
-            ABCInterfaceClass.__register_classes(
-                self, extra_classes, ignored_classes,
-            )
-            self.__class__ = InterfaceClass
-            return
-
-        based_on = attrs.pop('abc')
-        self.__abc = based_on
-        self.__extra_classes = tuple(extra_classes)
-        self.__ignored_classes = tuple(ignored_classes)
-
-        assert name[1:] == based_on.__name__, (name, based_on)
-        methods = {
-            # Passing the name is important in case of aliases,
-            # e.g., ``__ror__ = __or__``.
-            k: self.__method_from_function(v, k)
-            for k, v in vars(based_on).items()
-            if isinstance(v, FunctionType) and
-            not self.__is_private_name(k) and
-            not self.__is_reverse_protocol_name(k)
-        }
-
-        methods['__doc__'] = self.__create_class_doc(attrs)
-        # Anything specified in the body takes precedence.
-        methods.update(attrs)
-        InterfaceClass.__init__(self, name, bases, methods)
-        self.__register_classes()
-
-    @staticmethod
-    def __optional_methods_to_docs(attrs):
-        optionals = {k: v for k, v in attrs.items() if isinstance(v, optional)}
-        for k in optionals:
-            attrs[k] = _decorator_non_return
-
-        if not optionals:
-            return ''
-
-        docs = "\n\nThe following methods are optional:\n - " + "\n-".join(
-            f"{k}\n{v.__doc__}" for k, v in optionals.items()
-        )
-        return docs
-
-    def __create_class_doc(self, attrs):
-        based_on = self.__abc
-
-        def ref(c):
-            mod = c.__module__
-            name = c.__name__
-            if mod == str.__module__:
-                return "`%s`" % name
-            if mod == '_io':
-                mod = 'io'
-            return f"`{mod}.{name}`"
-
-        implementations_doc = "\n - ".join(
-            ref(c)
-            for c in sorted(self.getRegisteredConformers(), key=ref)
-        )
-        if implementations_doc:
-            implementations_doc = (
-                "\n\nKnown implementations are:\n\n - " + implementations_doc
-            )
-
-        based_on_doc = (based_on.__doc__ or '')
-        based_on_doc = based_on_doc.splitlines()
-        based_on_doc = based_on_doc[0] if based_on_doc else ''
-
-        doc = """Interface for the ABC `{}.{}`.\n\n{}{}{}""".format(
-            based_on.__module__, based_on.__name__,
-            attrs.get('__doc__', based_on_doc),
-            self.__optional_methods_to_docs(attrs),
-            implementations_doc
-        )
-        return doc
-
-    @staticmethod
-    def __is_private_name(name):
-        if name.startswith('__') and name.endswith('__'):
-            return False
-        return name.startswith('_')
-
-    @staticmethod
-    def __is_reverse_protocol_name(name):
-        # The reverse names, like __rand__,
-        # aren't really part of the protocol. The interpreter has
-        # very complex behaviour around invoking those. PyPy
-        # doesn't always even expose them as attributes.
-        return name.startswith('__r') and name.endswith('__')
-
-    def __method_from_function(self, function, name):
-        method = fromFunction(function, self, name=name)
-        # Eliminate the leading *self*, which is implied in
-        # an interface, but explicit in an ABC.
-        method.positional = method.positional[1:]
-        return method
-
-    def __register_classes(self, conformers=None, ignored_classes=None):
-        # Make the concrete classes already present in our ABC's registry
-        # declare that they implement this interface.
-        conformers = (
-            conformers if conformers is not None
-            else self.getRegisteredConformers()
-        )
-        ignored = (
-            ignored_classes if ignored_classes is not None
-            else self.__ignored_classes
-        )
-        for cls in conformers:
-            if cls in ignored:
-                continue
-            classImplements(cls, self)
-
-    def getABC(self):
-        """
-        Return the ABC this interface represents.
-        """
-        return self.__abc
-
-    def getRegisteredConformers(self):
-        """
-        Return an iterable of the classes that are known to conform to
-        the ABC this interface parallels.
-        """
-        based_on = self.__abc
-
-        # The registry only contains things that aren't already
-        # known to be subclasses of the ABC. But the ABC is in charge
-        # of checking that, so its quite possible that registrations
-        # are in fact ignored, winding up just in the _abc_cache.
-        try:
-            registered = (
-                list(based_on._abc_registry) + list(based_on._abc_cache)
-            )
-        except AttributeError:
-            # Rewritten in C in CPython 3.7.
-            # These expose the underlying weakref.
-            from abc import _get_dump
-            data = _get_dump(based_on)
-            registry = data[0]
-            cache = data[1]
-            registered = [x() for x in itertools.chain(registry, cache)]
-            registered = [x for x in registered if x is not None]
-
-        return set(itertools.chain(registered, self.__extra_classes))
-
-
-def _create_ABCInterface():
-    # It's a two-step process to create the root ABCInterface, because without
-    # specifying a corresponding ABC, using the normal constructor gets us a
-    # plain InterfaceClass object, and there is no ABC to associate with the
-    # root.
-    abc_name_bases_attrs = ('ABCInterface', (Interface,), {})
-    instance = ABCInterfaceClass.__new__(
-        ABCInterfaceClass, *abc_name_bases_attrs,
-    )
-    InterfaceClass.__init__(instance, *abc_name_bases_attrs)
-    return instance
-
-
-ABCInterface = _create_ABCInterface()
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 1686436..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/builtins.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/builtins.cpython-312.pyc
deleted file mode 100644
index 303af3f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/builtins.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/collections.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/collections.cpython-312.pyc
deleted file mode 100644
index dd84481..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/collections.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/idatetime.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/idatetime.cpython-312.pyc
deleted file mode 100644
index 5565887..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/idatetime.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/interfaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/interfaces.cpython-312.pyc
deleted file mode 100644
index 74df06e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/interfaces.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/io.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/io.cpython-312.pyc
deleted file mode 100644
index 350feed..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/io.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/mapping.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/mapping.cpython-312.pyc
deleted file mode 100644
index bf07a17..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/mapping.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/numbers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/numbers.cpython-312.pyc
deleted file mode 100644
index ddf78bc..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/numbers.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/sequence.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/sequence.cpython-312.pyc
deleted file mode 100644
index d7227bf..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/__pycache__/sequence.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/builtins.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/builtins.py
deleted file mode 100644
index 9e543c8..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/builtins.py
+++ /dev/null
@@ -1,124 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-"""
-Interface definitions for builtin types.
-
-After this module is imported, the standard library types will declare
-that they implement the appropriate interface.
-
-.. versionadded:: 5.0.0
-"""
-
-from zope.interface import classImplements
-from zope.interface._compat import PY313_OR_OLDER
-from zope.interface.common import collections
-from zope.interface.common import io
-from zope.interface.common import numbers
-
-
-__all__ = [
-    'IList',
-    'ITuple',
-    'ITextString',
-    'IByteString',
-    'INativeString',
-    'IBool',
-    'IDict',
-    'IFile',
-]
-
-
-# pylint:disable=no-self-argument
-class IList(collections.IMutableSequence):
-    """
-    Interface for :class:`list`
-    """
-    extra_classes = (list,)
-
-    def sort(key=None, reverse=False):
-        """
-        Sort the list in place and return None.
-
-        *key* and *reverse* must be passed by name only.
-        """
-
-
-class ITuple(collections.ISequence):
-    """
-    Interface for :class:`tuple`
-    """
-    extra_classes = (tuple,)
-
-
-class ITextString(collections.ISequence):
-    """
-    Interface for text ("unicode") strings.
-
-    This is :class:`str`
-    """
-    extra_classes = (str,)
-
-
-if PY313_OR_OLDER:
-    class IByteString(collections.IByteString):
-        """
-        Interface for immutable byte strings.
-
-        On all Python versions this is :class:`bytes`.
-
-        Unlike :class:`zope.interface.common.collections.IByteString`
-        (the parent of this interface) this does *not* include
-        :class:`bytearray`.
-        """
-        extra_classes = (bytes,)
-
-
-class INativeString(ITextString):
-    """
-    Interface for native strings.
-
-    On all Python versions, this is :class:`str`. Tt extends
-    :class:`ITextString`.
-    """
-
-
-# We're not extending ABCInterface so extra_classes won't work
-classImplements(str, INativeString)
-
-
-class IBool(numbers.IIntegral):
-    """
-    Interface for :class:`bool`
-    """
-    extra_classes = (bool,)
-
-
-class IDict(collections.IMutableMapping):
-    """
-    Interface for :class:`dict`
-    """
-    extra_classes = (dict,)
-
-
-class IFile(io.IIOBase):
-    """
-    Interface for :class:`file`.
-
-    It is recommended to use the interfaces from
-    :mod:`zope.interface.common.io` instead of this interface.
-
-    On Python 3, there is no single implementation of this interface;
-    depending on the arguments, the :func:`open` builtin can return
-    many different classes that implement different interfaces from
-    :mod:`zope.interface.common.io`.
-    """
-    extra_classes = ()
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/collections.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/collections.py
deleted file mode 100644
index defa8a1..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/collections.py
+++ /dev/null
@@ -1,269 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-"""
-Interface definitions paralleling the abstract base classes defined in
-:mod:`collections.abc`.
-
-After this module is imported, the standard library types will declare that
-they implement the appropriate interface. While most standard library types
-will properly implement that interface (that is, ``verifyObject(ISequence,
-list()))`` will pass, for example), a few might not:
-
-    - `memoryview` doesn't feature all the defined methods of
-      ``ISequence`` such as ``count``; it is still declared to provide
-      ``ISequence`` though.
-
-    - `collections.deque.pop` doesn't accept the ``index`` argument of
-      `collections.abc.MutableSequence.pop`
-
-    - `range.index` does not accept the ``start`` and ``stop`` arguments.
-
-.. versionadded:: 5.0.0
-"""
-
-import sys
-from abc import ABCMeta
-from collections import OrderedDict
-from collections import UserDict
-from collections import UserList
-from collections import UserString
-from collections import abc
-
-from zope.interface._compat import PY313_OR_OLDER
-from zope.interface.common import ABCInterface
-from zope.interface.common import optional
-
-
-# pylint:disable=inherit-non-class,
-# pylint:disable=no-self-argument,no-method-argument
-# pylint:disable=unexpected-special-method-signature
-# pylint:disable=no-value-for-parameter
-
-
-def _new_in_ver(name, ver,
-                bases_if_missing=(ABCMeta,),
-                register_if_missing=()):
-    if ver:
-        return getattr(abc, name)
-
-    # TODO: It's a shame to have to repeat the bases when
-    # the ABC is missing. Can we DRY that?
-    missing = ABCMeta(name, bases_if_missing, {
-        '__doc__': "The ABC %s is not defined in this version of Python." % (
-            name
-        ),
-    })
-
-    for c in register_if_missing:
-        missing.register(c)
-
-    return missing
-
-
-__all__ = [
-    'IAsyncGenerator',
-    'IAsyncIterable',
-    'IAsyncIterator',
-    'IAwaitable',
-    'ICollection',
-    'IContainer',
-    'ICoroutine',
-    'IGenerator',
-    'IHashable',
-    'IItemsView',
-    'IIterable',
-    'IIterator',
-    'IKeysView',
-    'IMapping',
-    'IMappingView',
-    'IMutableMapping',
-    'IMutableSequence',
-    'IMutableSet',
-    'IReversible',
-    'ISequence',
-    'ISet',
-    'ISized',
-    'IValuesView',
-]
-
-
-class IContainer(ABCInterface):
-    abc = abc.Container
-
-    @optional
-    def __contains__(other):
-        """
-        Optional method. If not provided, the interpreter will use
-        ``__iter__`` or the old ``__getitem__`` protocol
-        to implement ``in``.
-        """
-
-
-class IHashable(ABCInterface):
-    abc = abc.Hashable
-
-
-class IIterable(ABCInterface):
-    abc = abc.Iterable
-
-    @optional
-    def __iter__():
-        """
-        Optional method. If not provided, the interpreter will
-        implement `iter` using the old ``__getitem__`` protocol.
-        """
-
-
-class IIterator(IIterable):
-    abc = abc.Iterator
-
-
-class IReversible(IIterable):
-    abc = _new_in_ver('Reversible', True, (IIterable.getABC(),))
-
-    @optional
-    def __reversed__():
-        """
-        Optional method. If this isn't present, the interpreter
-        will use ``__len__`` and ``__getitem__`` to implement the
-        `reversed` builtin.
-        """
-
-
-class IGenerator(IIterator):
-    # New in Python 3.5
-    abc = _new_in_ver('Generator', True, (IIterator.getABC(),))
-
-
-class ISized(ABCInterface):
-    abc = abc.Sized
-
-
-# ICallable is not defined because there's no standard signature.
-
-
-class ICollection(ISized,
-                  IIterable,
-                  IContainer):
-    abc = _new_in_ver(
-        'Collection',
-        True,
-        (ISized.getABC(), IIterable.getABC(), IContainer.getABC())
-    )
-
-
-class ISequence(IReversible,
-                ICollection):
-    abc = abc.Sequence
-    extra_classes = (UserString,)
-    # On Python 2, basestring was registered as an ISequence, and
-    # its subclass str is an IByteString. If we also register str as
-    # an ISequence, that tends to lead to inconsistent resolution order.
-    ignored_classes = ()
-
-    @optional
-    def __reversed__():
-        """
-        Optional method. If this isn't present, the interpreter
-        will use ``__len__`` and ``__getitem__`` to implement the
-        `reversed` builtin.
-        """
-
-    @optional
-    def __iter__():
-        """
-        Optional method. If not provided, the interpreter will
-        implement `iter` using the old ``__getitem__`` protocol.
-        """
-
-
-class IMutableSequence(ISequence):
-    abc = abc.MutableSequence
-    extra_classes = (UserList,)
-
-
-if PY313_OR_OLDER:
-    class IByteString(ISequence):
-        """
-        This unifies `bytes` and `bytearray`.
-        """
-        abc = _new_in_ver(
-            'ByteString', True, (ISequence.getABC(),), (bytes, bytearray),
-        )
-
-
-class ISet(ICollection):
-    abc = abc.Set
-
-
-class IMutableSet(ISet):
-    abc = abc.MutableSet
-
-
-class IMapping(ICollection):
-    abc = abc.Mapping
-    extra_classes = (dict,)
-    # OrderedDict is a subclass of dict. On CPython 2,
-    # it winds up registered as a IMutableMapping, which
-    # produces an inconsistent IRO if we also try to register it
-    # here.
-    ignored_classes = (OrderedDict,)
-
-
-class IMutableMapping(IMapping):
-    abc = abc.MutableMapping
-    extra_classes = (dict, UserDict,)
-    ignored_classes = (OrderedDict,)
-
-
-class IMappingView(ISized):
-    abc = abc.MappingView
-
-
-class IItemsView(IMappingView, ISet):
-    abc = abc.ItemsView
-
-
-class IKeysView(IMappingView, ISet):
-    abc = abc.KeysView
-
-
-class IValuesView(IMappingView, ICollection):
-    abc = abc.ValuesView
-
-    @optional
-    def __contains__(other):
-        """
-        Optional method. If not provided, the interpreter will use
-        ``__iter__`` or the old ``__len__`` and ``__getitem__`` protocol
-        to implement ``in``.
-        """
-
-
-class IAwaitable(ABCInterface):
-    abc = _new_in_ver('Awaitable', True)
-
-
-class ICoroutine(IAwaitable):
-    abc = _new_in_ver('Coroutine', True)
-
-
-class IAsyncIterable(ABCInterface):
-    abc = _new_in_ver('AsyncIterable', True)
-
-
-class IAsyncIterator(IAsyncIterable):
-    abc = _new_in_ver('AsyncIterator', True)
-
-
-class IAsyncGenerator(IAsyncIterator):
-    abc = _new_in_ver('AsyncGenerator', True)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/idatetime.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/idatetime.py
deleted file mode 100644
index 24b2606..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/idatetime.py
+++ /dev/null
@@ -1,622 +0,0 @@
-##############################################################################
-# Copyright (c) 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-"""Datetime interfaces.
-
-This module is called idatetime because if it were called datetime the import
-of the real datetime would fail.
-"""
-from datetime import date
-from datetime import datetime
-from datetime import time
-from datetime import timedelta
-from datetime import tzinfo
-
-from zope.interface import Attribute
-from zope.interface import Interface
-from zope.interface import classImplements
-
-
-class ITimeDeltaClass(Interface):
-    """This is the timedelta class interface.
-
-    This is symbolic; this module does **not** make
-    `datetime.timedelta` provide this interface.
-    """
-
-    min = Attribute("The most negative timedelta object")
-
-    max = Attribute("The most positive timedelta object")
-
-    resolution = Attribute(
-        "The smallest difference between non-equal timedelta objects")
-
-
-class ITimeDelta(ITimeDeltaClass):
-    """Represent the difference between two datetime objects.
-
-    Implemented by `datetime.timedelta`.
-
-    Supported operators:
-
-    - add, subtract timedelta
-    - unary plus, minus, abs
-    - compare to timedelta
-    - multiply, divide by int/long
-
-    In addition, `.datetime` supports subtraction of two `.datetime` objects
-    returning a `.timedelta`, and addition or subtraction of a `.datetime`
-    and a `.timedelta` giving a `.datetime`.
-
-    Representation: (days, seconds, microseconds).
-    """
-
-    days = Attribute("Days between -999999999 and 999999999 inclusive")
-
-    seconds = Attribute("Seconds between 0 and 86399 inclusive")
-
-    microseconds = Attribute("Microseconds between 0 and 999999 inclusive")
-
-
-class IDateClass(Interface):
-    """This is the date class interface.
-
-    This is symbolic; this module does **not** make
-    `datetime.date` provide this interface.
-    """
-
-    min = Attribute("The earliest representable date")
-
-    max = Attribute("The latest representable date")
-
-    resolution = Attribute(
-        "The smallest difference between non-equal date objects")
-
-    def today():
-        """Return the current local time.
-
-        This is equivalent to ``date.fromtimestamp(time.time())``"""
-
-    def fromtimestamp(timestamp):
-        """Return the local date from a POSIX timestamp (like time.time())
-
-        This may raise `ValueError`, if the timestamp is out of the range of
-        values supported by the platform C ``localtime()`` function. It's
-        common for this to be restricted to years from 1970 through 2038. Note
-        that on non-POSIX systems that include leap seconds in their notion of
-        a timestamp, leap seconds are ignored by `fromtimestamp`.
-        """
-
-    def fromordinal(ordinal):
-        """Return the date corresponding to the proleptic Gregorian ordinal.
-
-         January 1 of year 1 has ordinal 1. `ValueError` is raised unless
-         1 <= ordinal <= date.max.toordinal().
-
-         For any date *d*, ``date.fromordinal(d.toordinal()) == d``.
-         """
-
-
-class IDate(IDateClass):
-    """Represents a date (year, month and day) in an idealized calendar.
-
-    Implemented by `datetime.date`.
-
-    Operators:
-
-    __repr__, __str__
-    __cmp__, __hash__
-    __add__, __radd__, __sub__ (add/radd only with timedelta arg)
-    """
-
-    year = Attribute("Between MINYEAR and MAXYEAR inclusive.")
-
-    month = Attribute("Between 1 and 12 inclusive")
-
-    day = Attribute(
-        "Between 1 and the number of days "
-        "in the given month of the given year."
-    )
-
-    def replace(year, month, day):
-        """Return a date with the same value.
-
-        Except for those members given new values by whichever keyword
-        arguments are specified.
-
-        For example, if ``d == date(2002, 12, 31)``, then
-        ``d.replace(day=26) == date(2000, 12, 26)``.
-        """
-
-    def timetuple():
-        """Return a 9-element tuple of the form returned by `time.localtime`.
-
-        The hours, minutes and seconds are 0, and the DST flag is -1.
-        ``d.timetuple()`` is equivalent to
-        ``(d.year, d.month, d.day, 0, 0, 0, d.weekday(), d.toordinal() -
-        date(d.year, 1, 1).toordinal() + 1, -1)``
-        """
-
-    def toordinal():
-        """Return the proleptic Gregorian ordinal of the date
-
-        January 1 of year 1 has ordinal 1. For any date object *d*,
-        ``date.fromordinal(d.toordinal()) == d``.
-        """
-
-    def weekday():
-        """Return the day of the week as an integer.
-
-        Monday is 0 and Sunday is 6. For example,
-        ``date(2002, 12, 4).weekday() == 2``, a Wednesday.
-
-        .. seealso:: `isoweekday`.
-        """
-
-    def isoweekday():
-        """Return the day of the week as an integer.
-
-        Monday is 1 and Sunday is 7. For example,
-        date(2002, 12, 4).isoweekday() == 3, a Wednesday.
-
-        .. seealso:: `weekday`, `isocalendar`.
-        """
-
-    def isocalendar():
-        """Return a 3-tuple, (ISO year, ISO week number, ISO weekday).
-
-        The ISO calendar is a widely used variant of the Gregorian calendar.
-        See http://www.phys.uu.nl/~vgent/calendar/isocalendar.htm for a good
-        explanation.
-
-        The ISO year consists of 52 or 53 full weeks, and where a week starts
-        on a Monday and ends on a Sunday. The first week of an ISO year is the
-        first (Gregorian) calendar week of a year containing a Thursday. This
-        is called week number 1, and the ISO year of that Thursday is the same
-        as its Gregorian year.
-
-        For example, 2004 begins on a Thursday, so the first week of ISO year
-        2004 begins on Monday, 29 Dec 2003 and ends on Sunday, 4 Jan 2004, so
-        that ``date(2003, 12, 29).isocalendar() == (2004, 1, 1)`` and
-        ``date(2004, 1, 4).isocalendar() == (2004, 1, 7)``.
-        """
-
-    def isoformat():
-        """Return a string representing the date in ISO 8601 format.
-
-        This is 'YYYY-MM-DD'.
-        For example, ``date(2002, 12, 4).isoformat() == '2002-12-04'``.
-        """
-
-    def __str__():
-        """For a date *d*, ``str(d)`` is equivalent to ``d.isoformat()``."""
-
-    def ctime():
-        """Return a string representing the date.
-
-        For example date(2002, 12, 4).ctime() == 'Wed Dec 4 00:00:00 2002'.
-        d.ctime() is equivalent to time.ctime(time.mktime(d.timetuple()))
-        on platforms where the native C ctime() function
-        (which `time.ctime` invokes, but which date.ctime() does not invoke)
-        conforms to the C standard.
-        """
-
-    def strftime(format):
-        """Return a string representing the date.
-
-        Controlled by an explicit format string. Format codes referring to
-        hours, minutes or seconds will see 0 values.
-        """
-
-
-class IDateTimeClass(Interface):
-    """This is the datetime class interface.
-
-    This is symbolic; this module does **not** make
-    `datetime.datetime` provide this interface.
-    """
-
-    min = Attribute("The earliest representable datetime")
-
-    max = Attribute("The latest representable datetime")
-
-    resolution = Attribute(
-        "The smallest possible difference between non-equal datetime objects")
-
-    def today():
-        """Return the current local datetime, with tzinfo None.
-
-        This is equivalent to ``datetime.fromtimestamp(time.time())``.
-
-        .. seealso:: `now`, `fromtimestamp`.
-        """
-
-    def now(tz=None):
-        """Return the current local date and time.
-
-        If optional argument *tz* is None or not specified, this is like
-        `today`, but, if possible, supplies more precision than can be gotten
-        from going through a `time.time` timestamp (for example, this may be
-        possible on platforms supplying the C ``gettimeofday()`` function).
-
-        Else tz must be an instance of a class tzinfo subclass, and the current
-        date and time are converted to tz's time zone. In this case the result
-        is equivalent to tz.fromutc(datetime.utcnow().replace(tzinfo=tz)).
-
-        .. seealso:: `today`, `utcnow`.
-        """
-
-    def utcnow():
-        """Return the current UTC date and time, with tzinfo None.
-
-        This is like `now`, but returns the current UTC date and time, as a
-        naive datetime object.
-
-        .. seealso:: `now`.
-        """
-
-    def fromtimestamp(timestamp, tz=None):
-        """Return the local date and time corresponding to the POSIX timestamp.
-
-        Same as is returned by time.time(). If optional argument tz is None or
-        not specified, the timestamp is converted to the platform's local date
-        and time, and the returned datetime object is naive.
-
-        Else tz must be an instance of a class tzinfo subclass, and the
-        timestamp is converted to tz's time zone. In this case the result is
-        equivalent to
-        ``tz.fromutc(datetime.utcfromtimestamp(timestamp).replace(tzinfo=tz))``
-
-        fromtimestamp() may raise `ValueError`, if the timestamp is out of the
-        range of values supported by the platform C localtime() or gmtime()
-        functions. It's common for this to be restricted to years in 1970
-        through 2038. Note that on non-POSIX systems that include leap seconds
-        in their notion of a timestamp, leap seconds are ignored by
-        fromtimestamp(), and then it's possible to have two timestamps
-        differing by a second that yield identical datetime objects.
-
-        .. seealso:: `utcfromtimestamp`.
-        """
-
-    def utcfromtimestamp(timestamp):
-        """Return the UTC datetime from the POSIX timestamp with tzinfo None.
-
-        This may raise `ValueError`, if the timestamp is out of the range of
-        values supported by the platform C ``gmtime()`` function. It's common
-        for this to be restricted to years in 1970 through 2038.
-
-        .. seealso:: `fromtimestamp`.
-        """
-
-    def fromordinal(ordinal):
-        """Return the datetime from the proleptic Gregorian ordinal.
-
-        January 1 of year 1 has ordinal 1. `ValueError` is raised unless
-        1 <= ordinal <= datetime.max.toordinal().
-        The hour, minute, second and microsecond of the result are all 0, and
-        tzinfo is None.
-        """
-
-    def combine(date, time):
-        """Return a new datetime object.
-
-        Its date members are equal to the given date object's, and whose time
-        and tzinfo members are equal to the given time object's. For any
-        datetime object *d*, ``d == datetime.combine(d.date(), d.timetz())``.
-        If date is a datetime object, its time and tzinfo members are ignored.
-        """
-
-
-class IDateTime(IDate, IDateTimeClass):
-    """Contains all the information from a date object and a time object.
-
-    Implemented by `datetime.datetime`.
-    """
-
-    year = Attribute("Year between MINYEAR and MAXYEAR inclusive")
-
-    month = Attribute("Month between 1 and 12 inclusive")
-
-    day = Attribute(
-        "Day between 1 and the number of days in the given month of the year")
-
-    hour = Attribute("Hour in range(24)")
-
-    minute = Attribute("Minute in range(60)")
-
-    second = Attribute("Second in range(60)")
-
-    microsecond = Attribute("Microsecond in range(1000000)")
-
-    tzinfo = Attribute(
-        """The object passed as the tzinfo argument to the datetime constructor
-        or None if none was passed""")
-
-    def date():
-        """Return date object with same year, month and day."""
-
-    def time():
-        """Return time object with same hour, minute, second, microsecond.
-
-        tzinfo is None.
-
-        .. seealso:: Method :meth:`timetz`.
-        """
-
-    def timetz():
-        """Return time object with same hour, minute, second, microsecond,
-        and tzinfo.
-
-        .. seealso:: Method :meth:`time`.
-        """
-
-    def replace(year, month, day, hour, minute, second, microsecond, tzinfo):
-        """Return a datetime with the same members, except for those members
-        given new values by whichever keyword arguments are specified.
-
-        Note that ``tzinfo=None`` can be specified to create a naive datetime
-        from an aware datetime with no conversion of date and time members.
-        """
-
-    def astimezone(tz):
-        """Return a datetime object with new tzinfo member tz, adjusting the
-        date and time members so the result is the same UTC time as self, but
-        in tz's local time.
-
-        tz must be an instance of a tzinfo subclass, and its utcoffset() and
-        dst() methods must not return None. self must be aware (self.tzinfo
-        must not be None, and self.utcoffset() must not return None).
-
-        If self.tzinfo is tz, self.astimezone(tz) is equal to self: no
-        adjustment of date or time members is performed. Else the result is
-        local time in time zone tz, representing the same UTC time as self:
-
-            after astz = dt.astimezone(tz), astz - astz.utcoffset()
-
-        will usually have the same date and time members as dt -
-        dt.utcoffset().  The discussion of class `datetime.tzinfo` explains
-        the cases at Daylight Saving Time transition boundaries where this
-        cannot be achieved (an issue only if tz models both standard and
-        daylight time).
-
-        If you merely want to attach a time zone object *tz* to a datetime
-        *dt* without adjustment of date and time members, use
-        ``dt.replace(tzinfo=tz)``.
-
-        If you merely want to remove the time zone object from an aware
-        datetime dt without conversion of date and time members, use
-        ``dt.replace(tzinfo=None)``.
-
-        Note that the default `tzinfo.fromutc` method can be overridden in a
-        tzinfo subclass to effect the result returned by `astimezone`.
-        """
-
-    def utcoffset():
-        """Return the timezone offset in minutes east of UTC (negative west of
-        UTC)."""
-
-    def dst():
-        """Return 0 if DST is not in effect, or the DST offset (in minutes
-        eastward) if DST is in effect.
-        """
-
-    def tzname():
-        """Return the timezone name."""
-
-    def timetuple():
-        """Return a 9-tuple of the form returned by `time.localtime`."""
-
-    def utctimetuple():
-        """Return UTC time tuple compatilble with `time.gmtime`."""
-
-    def toordinal():
-        """Return the proleptic Gregorian ordinal of the date.
-
-        The same as self.date().toordinal().
-        """
-
-    def weekday():
-        """Return the day of the week as an integer.
-
-        Monday is 0 and Sunday is 6. The same as self.date().weekday().
-        See also isoweekday().
-        """
-
-    def isoweekday():
-        """Return the day of the week as an integer.
-
-        Monday is 1 and Sunday is 7. The same as self.date().isoweekday.
-
-        .. seealso:: `weekday`, `isocalendar`.
-        """
-
-    def isocalendar():
-        """Return a 3-tuple, (ISO year, ISO week number, ISO weekday).
-
-        The same as self.date().isocalendar().
-        """
-
-    def isoformat(sep='T'):
-        """Return a string representing the date and time in ISO 8601 format.
-
-        YYYY-MM-DDTHH:MM:SS.mmmmmm or YYYY-MM-DDTHH:MM:SS if microsecond is 0
-
-        If `utcoffset` does not return None, a 6-character string is appended,
-        giving the UTC offset in (signed) hours and minutes:
-
-        YYYY-MM-DDTHH:MM:SS.mmmmmm+HH:MM or YYYY-MM-DDTHH:MM:SS+HH:MM
-        if microsecond is 0.
-
-        The optional argument sep (default 'T') is a one-character separator,
-        placed between the date and time portions of the result.
-        """
-
-    def __str__():
-        """Convert to a stirng
-
-        For a datetime instance *d*, ``str(d)`` is equivalent to
-        ``d.isoformat(' ')``.
-        """
-
-    def ctime():
-        """Return a string representing the date and time.
-
-        ``datetime(2002, 12, 4, 20, 30, 40).ctime()`` yields
-        ``'Wed Dec 4 20:30:40 2002'``.
-        ``d.ctime()`` is equivalent to
-        ``time.ctime(time.mktime(d.timetuple()))`` on platforms where the
-        native C ``ctime()`` function (which `time.ctime` invokes, but which
-        `datetime.ctime` does not invoke) conforms to the C standard.
-        """
-
-    def strftime(format):
-        """Return a string representing the date and time.
-
-        This is controlled by an explicit format string.
-        """
-
-
-class ITimeClass(Interface):
-    """This is the time class interface.
-
-    This is symbolic; this module does **not** make
-    `datetime.time` provide this interface.
-
-    """
-
-    min = Attribute("The earliest representable time")
-
-    max = Attribute("The latest representable time")
-
-    resolution = Attribute(
-        "The smallest possible difference between non-equal time objects")
-
-
-class ITime(ITimeClass):
-    """Represent time with time zone.
-
-    Implemented by `datetime.time`.
-
-    Operators:
-
-    __repr__, __str__
-    __cmp__, __hash__
-    """
-
-    hour = Attribute("Hour in range(24)")
-
-    minute = Attribute("Minute in range(60)")
-
-    second = Attribute("Second in range(60)")
-
-    microsecond = Attribute("Microsecond in range(1000000)")
-
-    tzinfo = Attribute(
-        """The object passed as the tzinfo argument to the time constructor
-        or None if none was passed.""")
-
-    def replace(hour, minute, second, microsecond, tzinfo):
-        """Return a time with the same value.
-
-        Except for those members given new values by whichever keyword
-        arguments are specified. Note that tzinfo=None can be specified
-        to create a naive time from an aware time, without conversion of the
-        time members.
-        """
-
-    def isoformat():
-        """Return a string representing the time in ISO 8601 format.
-
-        That is HH:MM:SS.mmmmmm or, if self.microsecond is 0, HH:MM:SS
-        If utcoffset() does not return None, a 6-character string is appended,
-        giving the UTC offset in (signed) hours and minutes:
-        HH:MM:SS.mmmmmm+HH:MM or, if self.microsecond is 0, HH:MM:SS+HH:MM
-        """
-
-    def __str__():
-        """For a time t, str(t) is equivalent to t.isoformat()."""
-
-    def strftime(format):
-        """Return a string representing the time.
-
-        This is controlled by an explicit format string.
-        """
-
-    def utcoffset():
-        """Return the timezone offset in minutes east of UTC (negative west of
-        UTC).
-
-        If tzinfo is None, returns None, else returns
-        self.tzinfo.utcoffset(None), and raises an exception if the latter
-        doesn't return None or a timedelta object representing a whole number
-        of minutes with magnitude less than one day.
-        """
-
-    def dst():
-        """Return 0 if DST is not in effect, or the DST offset (in minutes
-        eastward) if DST is in effect.
-
-        If tzinfo is None, returns None, else returns self.tzinfo.dst(None),
-        and raises an exception if the latter doesn't return None, or a
-        timedelta object representing a whole number of minutes with
-        magnitude less than one day.
-        """
-
-    def tzname():
-        """Return the timezone name.
-
-        If tzinfo is None, returns None, else returns self.tzinfo.tzname(None),
-        or raises an exception if the latter doesn't return None or a string
-        object.
-        """
-
-
-class ITZInfo(Interface):
-    """Time zone info class.
-    """
-
-    def utcoffset(dt):
-        """Return offset of local time from UTC, in minutes east of UTC.
-
-        If local time is west of UTC, this should be negative.
-        Note that this is intended to be the total offset from UTC;
-        for example, if a tzinfo object represents both time zone and DST
-        adjustments, utcoffset() should return their sum. If the UTC offset
-        isn't known, return None. Else the value returned must be a timedelta
-        object specifying a whole number of minutes in the range -1439 to 1439
-        inclusive (1440 = 24*60; the magnitude of the offset must be less
-        than one day).
-        """
-
-    def dst(dt):
-        """Return the daylight saving time (DST) adjustment, in minutes east
-        of UTC, or None if DST information isn't known.
-        """
-
-    def tzname(dt):
-        """Return the time zone name corresponding to the datetime object as
-        a string.
-        """
-
-    def fromutc(dt):
-        """Return an equivalent datetime in self's local time."""
-
-
-classImplements(timedelta, ITimeDelta)
-classImplements(date, IDate)
-classImplements(datetime, IDateTime)
-classImplements(time, ITime)
-classImplements(tzinfo, ITZInfo)
-
-# directlyProvides(timedelta, ITimeDeltaClass)
-# directlyProvides(date, IDateClass)
-# directlyProvides(datetime, IDateTimeClass)
-# directlyProvides(time, ITimeClass)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/interfaces.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/interfaces.py
deleted file mode 100644
index 9075795..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/interfaces.py
+++ /dev/null
@@ -1,281 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Interfaces for standard python exceptions
-"""
-from zope.interface import Interface
-from zope.interface import classImplements
-
-
-class IException(Interface):
-    "Interface for `Exception`"
-
-
-classImplements(Exception, IException)  # noqa E305
-
-
-class IStandardError(IException):
-    "Interface for `StandardError` (no longer existing.)"
-
-
-class IWarning(IException):
-    "Interface for `Warning`"
-
-
-classImplements(Warning, IWarning)  # noqa E305
-
-
-class ISyntaxError(IStandardError):
-    "Interface for `SyntaxError`"
-
-
-classImplements(SyntaxError, ISyntaxError)  # noqa E305
-
-
-class ILookupError(IStandardError):
-    "Interface for `LookupError`"
-
-
-classImplements(LookupError, ILookupError)  # noqa E305
-
-
-class IValueError(IStandardError):
-    "Interface for `ValueError`"
-
-
-classImplements(ValueError, IValueError)  # noqa E305
-
-
-class IRuntimeError(IStandardError):
-    "Interface for `RuntimeError`"
-
-
-classImplements(RuntimeError, IRuntimeError)  # noqa E305
-
-
-class IArithmeticError(IStandardError):
-    "Interface for `ArithmeticError`"
-
-
-classImplements(ArithmeticError, IArithmeticError)  # noqa E305
-
-
-class IAssertionError(IStandardError):
-    "Interface for `AssertionError`"
-
-
-classImplements(AssertionError, IAssertionError)  # noqa E305
-
-
-class IAttributeError(IStandardError):
-    "Interface for `AttributeError`"
-
-
-classImplements(AttributeError, IAttributeError)  # noqa E305
-
-
-class IDeprecationWarning(IWarning):
-    "Interface for `DeprecationWarning`"
-
-
-classImplements(DeprecationWarning, IDeprecationWarning)  # noqa E305
-
-
-class IEOFError(IStandardError):
-    "Interface for `EOFError`"
-
-
-classImplements(EOFError, IEOFError)  # noqa E305
-
-
-class IEnvironmentError(IStandardError):
-    "Interface for `EnvironmentError`"
-
-
-classImplements(EnvironmentError, IEnvironmentError)  # noqa E305
-
-
-class IFloatingPointError(IArithmeticError):
-    "Interface for `FloatingPointError`"
-
-
-classImplements(FloatingPointError, IFloatingPointError)  # noqa E305
-
-
-class IIOError(IEnvironmentError):
-    "Interface for `IOError`"
-
-
-classImplements(IOError, IIOError)  # noqa E305
-
-
-class IImportError(IStandardError):
-    "Interface for `ImportError`"
-
-
-classImplements(ImportError, IImportError)  # noqa E305
-
-
-class IIndentationError(ISyntaxError):
-    "Interface for `IndentationError`"
-
-
-classImplements(IndentationError, IIndentationError)  # noqa E305
-
-
-class IIndexError(ILookupError):
-    "Interface for `IndexError`"
-
-
-classImplements(IndexError, IIndexError)  # noqa E305
-
-
-class IKeyError(ILookupError):
-    "Interface for `KeyError`"
-
-
-classImplements(KeyError, IKeyError)  # noqa E305
-
-
-class IKeyboardInterrupt(IStandardError):
-    "Interface for `KeyboardInterrupt`"
-
-
-classImplements(KeyboardInterrupt, IKeyboardInterrupt)  # noqa E305
-
-
-class IMemoryError(IStandardError):
-    "Interface for `MemoryError`"
-
-
-classImplements(MemoryError, IMemoryError)  # noqa E305
-
-
-class INameError(IStandardError):
-    "Interface for `NameError`"
-
-
-classImplements(NameError, INameError)  # noqa E305
-
-
-class INotImplementedError(IRuntimeError):
-    "Interface for `NotImplementedError`"
-
-
-classImplements(NotImplementedError, INotImplementedError)  # noqa E305
-
-
-class IOSError(IEnvironmentError):
-    "Interface for `OSError`"
-
-
-classImplements(OSError, IOSError)  # noqa E305
-
-
-class IOverflowError(IArithmeticError):
-    "Interface for `ArithmeticError`"
-
-
-classImplements(OverflowError, IOverflowError)  # noqa E305
-
-
-class IOverflowWarning(IWarning):
-    """Deprecated, no standard class implements this.
-
-    This was the interface for ``OverflowWarning`` prior to Python 2.5,
-    but that class was removed for all versions after that.
-    """
-
-
-class IReferenceError(IStandardError):
-    "Interface for `ReferenceError`"
-
-
-classImplements(ReferenceError, IReferenceError)  # noqa E305
-
-
-class IRuntimeWarning(IWarning):
-    "Interface for `RuntimeWarning`"
-
-
-classImplements(RuntimeWarning, IRuntimeWarning)  # noqa E305
-
-
-class IStopIteration(IException):
-    "Interface for `StopIteration`"
-
-
-classImplements(StopIteration, IStopIteration)  # noqa E305
-
-
-class ISyntaxWarning(IWarning):
-    "Interface for `SyntaxWarning`"
-
-
-classImplements(SyntaxWarning, ISyntaxWarning)  # noqa E305
-
-
-class ISystemError(IStandardError):
-    "Interface for `SystemError`"
-
-
-classImplements(SystemError, ISystemError)  # noqa E305
-
-
-class ISystemExit(IException):
-    "Interface for `SystemExit`"
-
-
-classImplements(SystemExit, ISystemExit)  # noqa E305
-
-
-class ITabError(IIndentationError):
-    "Interface for `TabError`"
-
-
-classImplements(TabError, ITabError)  # noqa E305
-
-
-class ITypeError(IStandardError):
-    "Interface for `TypeError`"
-
-
-classImplements(TypeError, ITypeError)  # noqa E305
-
-
-class IUnboundLocalError(INameError):
-    "Interface for `UnboundLocalError`"
-
-
-classImplements(UnboundLocalError, IUnboundLocalError)  # noqa E305
-
-
-class IUnicodeError(IValueError):
-    "Interface for `UnicodeError`"
-
-
-classImplements(UnicodeError, IUnicodeError)  # noqa E305
-
-
-class IUserWarning(IWarning):
-    "Interface for `UserWarning`"
-
-
-classImplements(UserWarning, IUserWarning)  # noqa E305
-
-
-class IZeroDivisionError(IArithmeticError):
-    "Interface for `ZeroDivisionError`"
-
-
-classImplements(ZeroDivisionError, IZeroDivisionError)  # noqa E305
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/io.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/io.py
deleted file mode 100644
index 89f1ba8..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/io.py
+++ /dev/null
@@ -1,44 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-"""
-Interface definitions paralleling the abstract base classes defined in
-:mod:`io`.
-
-After this module is imported, the standard library types will declare
-that they implement the appropriate interface.
-
-.. versionadded:: 5.0.0
-"""
-
-import io as abc
-
-from zope.interface.common import ABCInterface
-
-
-# pylint:disable=inherit-non-class,
-# pylint:disable=no-member
-
-class IIOBase(ABCInterface):
-    abc = abc.IOBase
-
-
-class IRawIOBase(IIOBase):
-    abc = abc.RawIOBase
-
-
-class IBufferedIOBase(IIOBase):
-    abc = abc.BufferedIOBase
-    extra_classes = ()
-
-
-class ITextIOBase(IIOBase):
-    abc = abc.TextIOBase
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/mapping.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/mapping.py
deleted file mode 100644
index d8ea074..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/mapping.py
+++ /dev/null
@@ -1,177 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""
-Mapping Interfaces.
-
-Importing this module does *not* mark any standard classes as
-implementing any of these interfaces.
-
-While this module is not deprecated, new code should generally use
-:mod:`zope.interface.common.collections`, specifically
-:class:`~zope.interface.common.collections.IMapping` and
-:class:`~zope.interface.common.collections.IMutableMapping`. This
-module is occasionally useful for its extremely fine grained breakdown
-of interfaces.
-
-The standard library :class:`dict` and :class:`collections.UserDict`
-implement ``IMutableMapping``, but *do not* implement any of the
-interfaces in this module.
-"""
-from zope.interface import Interface
-from zope.interface.common import collections
-
-
-class IItemMapping(Interface):
-    """Simplest readable mapping object
-    """
-
-    def __getitem__(key):
-        """Get a value for a key
-
-        A `KeyError` is raised if there is no value for the key.
-        """
-
-
-class IReadMapping(collections.IContainer, IItemMapping):
-    """
-    Basic mapping interface.
-
-    .. versionchanged:: 5.0.0
-       Extend ``IContainer``
-    """
-
-    def get(key, default=None):
-        """Get a value for a key
-
-        The default is returned if there is no value for the key.
-        """
-
-    def __contains__(key):
-        """Tell if a key exists in the mapping."""
-        # Optional in IContainer, required by this interface.
-
-
-class IWriteMapping(Interface):
-    """Mapping methods for changing data"""
-
-    def __delitem__(key):
-        """Delete a value from the mapping using the key."""
-
-    def __setitem__(key, value):
-        """Set a new item in the mapping."""
-
-
-class IEnumerableMapping(collections.ISized, IReadMapping):
-    """
-    Mapping objects whose items can be enumerated.
-
-    .. versionchanged:: 5.0.0
-       Extend ``ISized``
-    """
-
-    def keys():
-        """Return the keys of the mapping object.
-        """
-
-    def __iter__():
-        """Return an iterator for the keys of the mapping object.
-        """
-
-    def values():
-        """Return the values of the mapping object.
-        """
-
-    def items():
-        """Return the items of the mapping object.
-        """
-
-
-class IMapping(IWriteMapping, IEnumerableMapping):
-    ''' Simple mapping interface '''
-
-
-class IIterableMapping(IEnumerableMapping):
-    """A mapping that has distinct methods for iterating
-    without copying.
-
-    """
-
-
-class IClonableMapping(Interface):
-    """Something that can produce a copy of itself.
-
-    This is available in `dict`.
-    """
-
-    def copy():
-        "return copy of dict"
-
-
-class IExtendedReadMapping(IIterableMapping):
-    """
-    Something with a particular method equivalent to ``__contains__``.
-
-    On Python 2, `dict` provided the ``has_key`` method, but it was removed
-    in Python 3.
-    """
-
-
-class IExtendedWriteMapping(IWriteMapping):
-    """Additional mutation methods.
-
-    These are all provided by `dict`.
-    """
-
-    def clear():
-        "delete all items"
-
-    def update(d):
-        " Update D from E: for k in E.keys(): D[k] = E[k]"
-
-    def setdefault(key, default=None):
-        "D.setdefault(k[,d]) -> D.get(k,d), also set D[k]=d if k not in D"
-
-    def pop(k, default=None):
-        """
-        pop(k[,default]) -> value
-
-        Remove specified key and return the corresponding value.
-
-        If key is not found, *default* is returned if given, otherwise
-        `KeyError` is raised. Note that *default* must not be passed by
-        name.
-        """
-
-    def popitem():
-        """remove and return some (key, value) pair as a
-        2-tuple; but raise KeyError if mapping is empty"""
-
-
-class IFullMapping(
-    collections.IMutableMapping,
-    IExtendedReadMapping,
-    IExtendedWriteMapping,
-    IClonableMapping,
-    IMapping,
-):
-    """
-    Full mapping interface.
-
-    Most uses of this interface should instead use
-    :class:`~zope.interface.commons.collections.IMutableMapping` (one of the
-    bases of this interface). The required methods are the same.
-
-    .. versionchanged:: 5.0.0
-       Extend ``IMutableMapping``
-    """
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/numbers.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/numbers.py
deleted file mode 100644
index 6b20e09..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/numbers.py
+++ /dev/null
@@ -1,65 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-"""
-Interface definitions paralleling the abstract base classes defined in
-:mod:`numbers`.
-
-After this module is imported, the standard library types will declare
-that they implement the appropriate interface.
-
-.. versionadded:: 5.0.0
-"""
-
-import numbers as abc
-
-from zope.interface.common import ABCInterface
-from zope.interface.common import optional
-
-
-# pylint:disable=inherit-non-class,
-# pylint:disable=no-self-argument,no-method-argument
-# pylint:disable=unexpected-special-method-signature
-# pylint:disable=no-value-for-parameter
-
-
-class INumber(ABCInterface):
-    abc = abc.Number
-
-
-class IComplex(INumber):
-    abc = abc.Complex
-
-    @optional
-    def __complex__():
-        """
-        Rarely implemented, even in builtin types.
-        """
-
-
-class IReal(IComplex):
-    abc = abc.Real
-
-    @optional
-    def __complex__():
-        """
-        Rarely implemented, even in builtin types.
-        """
-
-    __floor__ = __ceil__ = __complex__
-
-
-class IRational(IReal):
-    abc = abc.Rational
-
-
-class IIntegral(IRational):
-    abc = abc.Integral
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/sequence.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/sequence.py
deleted file mode 100644
index c63f5a4..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/sequence.py
+++ /dev/null
@@ -1,195 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""
-Sequence Interfaces
-
-Importing this module does *not* mark any standard classes as
-implementing any of these interfaces.
-
-While this module is not deprecated, new code should generally use
-:mod:`zope.interface.common.collections`, specifically
-:class:`~zope.interface.common.collections.ISequence` and
-:class:`~zope.interface.common.collections.IMutableSequence`. This
-module is occasionally useful for its fine-grained breakdown of interfaces.
-
-The standard library :class:`list`, :class:`tuple` and
-:class:`collections.UserList`, among others, implement ``ISequence``
-or ``IMutableSequence`` but *do not* implement any of the interfaces
-in this module.
-"""
-
-__docformat__ = 'restructuredtext'
-from zope.interface import Interface
-from zope.interface.common import collections
-
-
-class IMinimalSequence(collections.IIterable):
-    """Most basic sequence interface.
-
-    All sequences are iterable.  This requires at least one of the
-    following:
-
-    - a `__getitem__()` method that takes a single argument; integer
-      values starting at 0 must be supported, and `IndexError` should
-      be raised for the first index for which there is no value, or
-
-    - an `__iter__()` method that returns an iterator as defined in
-      the Python documentation (http://docs.python.org/lib/typeiter.html).
-
-    """
-
-    def __getitem__(index):
-        """``x.__getitem__(index) <==> x[index]``
-
-        Declaring this interface does not specify whether `__getitem__`
-        supports slice objects."""
-
-
-class IFiniteSequence(collections.ISized, IMinimalSequence):
-    """
-    A sequence of bound size.
-
-    .. versionchanged:: 5.0.0
-       Extend ``ISized``
-    """
-
-
-class IReadSequence(collections.IContainer, IFiniteSequence):
-    """
-    read interface shared by tuple and list
-
-    This interface is similar to
-    :class:`~zope.interface.common.collections.ISequence`, but
-    requires that all instances be totally ordered. Most users
-    should prefer ``ISequence``.
-
-    .. versionchanged:: 5.0.0
-       Extend ``IContainer``
-    """
-
-    def __contains__(item):
-        """``x.__contains__(item) <==> item in x``"""
-        # Optional in IContainer, required here.
-
-    def __lt__(other):
-        """``x.__lt__(other) <==> x < other``"""
-
-    def __le__(other):
-        """``x.__le__(other) <==> x <= other``"""
-
-    def __eq__(other):
-        """``x.__eq__(other) <==> x == other``"""
-
-    def __ne__(other):
-        """``x.__ne__(other) <==> x != other``"""
-
-    def __gt__(other):
-        """``x.__gt__(other) <==> x > other``"""
-
-    def __ge__(other):
-        """``x.__ge__(other) <==> x >= other``"""
-
-    def __add__(other):
-        """``x.__add__(other) <==> x + other``"""
-
-    def __mul__(n):
-        """``x.__mul__(n) <==> x * n``"""
-
-    def __rmul__(n):
-        """``x.__rmul__(n) <==> n * x``"""
-
-
-class IExtendedReadSequence(IReadSequence):
-    """Full read interface for lists"""
-
-    def count(item):
-        """Return number of occurrences of value"""
-
-    def index(item, *args):
-        """index(value, [start, [stop]]) -> int
-
-        Return first index of *value*
-        """
-
-
-class IUniqueMemberWriteSequence(Interface):
-    """The write contract for a sequence that may enforce unique members"""
-
-    def __setitem__(index, item):
-        """``x.__setitem__(index, item) <==> x[index] = item``
-
-        Declaring this interface does not specify whether `__setitem__`
-        supports slice objects.
-        """
-
-    def __delitem__(index):
-        """``x.__delitem__(index) <==> del x[index]``
-
-        Declaring this interface does not specify whether `__delitem__`
-        supports slice objects.
-        """
-
-    def __iadd__(y):
-        """``x.__iadd__(y) <==> x += y``"""
-
-    def append(item):
-        """Append item to end"""
-
-    def insert(index, item):
-        """Insert item before index"""
-
-    def pop(index=-1):
-        """Remove and return item at index (default last)"""
-
-    def remove(item):
-        """Remove first occurrence of value"""
-
-    def reverse():
-        """Reverse *IN PLACE*"""
-
-    def sort(cmpfunc=None):
-        """Stable sort *IN PLACE*; `cmpfunc(x, y)` -> -1, 0, 1"""
-
-    def extend(iterable):
-        """Extend list by appending elements from the iterable"""
-
-
-class IWriteSequence(IUniqueMemberWriteSequence):
-    """Full write contract for sequences"""
-
-    def __imul__(n):
-        """``x.__imul__(n) <==> x *= n``"""
-
-
-class ISequence(IReadSequence, IWriteSequence):
-    """
-    Full sequence contract.
-
-    New code should prefer
-    :class:`~zope.interface.common.collections.IMutableSequence`.
-
-    Compared to that interface, which is implemented by :class:`list`
-    (:class:`~zope.interface.common.builtins.IList`), among others,
-    this interface is missing the following methods:
-
-        - clear
-
-        - count
-
-        - index
-
-    This interface adds the following methods:
-
-        - sort
-    """
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__init__.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__init__.py
deleted file mode 100644
index f70a530..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__init__.py
+++ /dev/null
@@ -1,146 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-
-import unittest
-
-from zope.interface.common import ABCInterface
-from zope.interface.common import ABCInterfaceClass
-from zope.interface.verify import verifyClass
-from zope.interface.verify import verifyObject
-
-
-def iter_abc_interfaces(predicate=lambda iface: True):
-    # Iterate ``(iface, classes)``, where ``iface`` is a descendent of
-    # the ABCInterfaceClass passing the *predicate* and ``classes`` is
-    # an iterable of classes registered to conform to that interface.
-    #
-    # Note that some builtin classes are registered for two distinct parts of
-    # the ABC/interface tree. For example, bytearray is both ByteString and
-    # MutableSequence.
-    seen = set()
-    stack = list(
-        ABCInterface.dependents
-    )  # subclasses, but also implementedBy objects
-
-    while stack:
-        iface = stack.pop(0)
-        if iface in seen or not isinstance(iface, ABCInterfaceClass):
-            continue
-        seen.add(iface)
-        stack.extend(list(iface.dependents))
-        if not predicate(iface):
-            continue
-
-        registered = set(iface.getRegisteredConformers())
-        registered -= set(iface._ABCInterfaceClass__ignored_classes)
-        if registered:
-            yield iface, registered
-
-
-def add_abc_interface_tests(cls, module):
-    def predicate(iface):
-        return iface.__module__ == module
-    add_verify_tests(cls, iter_abc_interfaces(predicate))
-
-
-def add_verify_tests(cls, iface_classes_iter):
-    cls.maxDiff = None
-    for iface, registered_classes in iface_classes_iter:
-        for stdlib_class in registered_classes:
-            def test(self, stdlib_class=stdlib_class, iface=iface):
-                if (
-                    stdlib_class in self.UNVERIFIABLE or
-                    stdlib_class.__name__ in self.UNVERIFIABLE
-                ):
-                    self.skipTest("Unable to verify %s" % stdlib_class)
-
-                self.assertTrue(self.verify(iface, stdlib_class))
-
-            suffix = "{}_{}_{}_{}".format(
-                stdlib_class.__module__.replace('.', '_'),
-                stdlib_class.__name__,
-                iface.__module__.replace('.', '_'),
-                iface.__name__
-            )
-            name = 'test_auto_' + suffix
-            test.__name__ = name
-            assert not hasattr(cls, name), (name, list(cls.__dict__))
-            setattr(cls, name, test)
-
-            def test_ro(self, stdlib_class=stdlib_class, iface=iface):
-                from zope.interface import Interface
-                from zope.interface import implementedBy
-                from zope.interface import ro
-                self.assertEqual(
-                    tuple(ro.ro(iface, strict=True)),
-                    iface.__sro__)
-                implements = implementedBy(stdlib_class)
-                sro = implements.__sro__
-                self.assertIs(sro[-1], Interface)
-
-                if stdlib_class not in self.UNVERIFIABLE_RO:
-                    # Check that we got the strict C3 resolution order, unless
-                    # we know we cannot. Note that 'Interface' is virtual base
-                    # that doesn't necessarily appear at the same place in the
-                    # calculated SRO as in the final SRO.
-                    strict = stdlib_class not in self.NON_STRICT_RO
-                    isro = ro.ro(implements, strict=strict)
-                    isro.remove(Interface)
-                    isro.append(Interface)
-
-                    self.assertEqual(tuple(isro), sro)
-
-            name = 'test_auto_ro_' + suffix
-            test_ro.__name__ = name
-            assert not hasattr(cls, name)
-            setattr(cls, name, test_ro)
-
-
-class VerifyClassMixin(unittest.TestCase):
-    verifier = staticmethod(verifyClass)
-    UNVERIFIABLE = ()
-    NON_STRICT_RO = ()
-    UNVERIFIABLE_RO = ()
-
-    def _adjust_object_before_verify(self, iface, x):
-        return x
-
-    def verify(self, iface, klass, **kwargs):
-        return self.verifier(iface,
-                             self._adjust_object_before_verify(iface, klass),
-                             **kwargs)
-
-
-class VerifyObjectMixin(VerifyClassMixin):
-    verifier = staticmethod(verifyObject)
-    CONSTRUCTORS = {
-    }
-
-    def _adjust_object_before_verify(self, iface, x):
-        constructor = self.CONSTRUCTORS.get(x)
-        if not constructor:
-            constructor = self.CONSTRUCTORS.get(iface)
-        if not constructor:
-            constructor = self.CONSTRUCTORS.get(x.__name__)
-        if not constructor:
-            constructor = x
-        if constructor is unittest.SkipTest:
-            self.skipTest("Cannot create " + str(x))
-
-        try:
-            result = constructor()
-        except Exception as e:  # pragma: no cover
-            raise TypeError(
-                f'Failed to create instance of {constructor}') from e
-        if hasattr(result, 'close'):
-            self.addCleanup(result.close)
-        return result
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 1ebe86e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/basemapping.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/basemapping.cpython-312.pyc
deleted file mode 100644
index c0c2c95..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/basemapping.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_builtins.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_builtins.cpython-312.pyc
deleted file mode 100644
index 9fa6a3f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_builtins.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_collections.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_collections.cpython-312.pyc
deleted file mode 100644
index 464145e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_collections.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_idatetime.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_idatetime.cpython-312.pyc
deleted file mode 100644
index 3d9257c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_idatetime.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_import_interfaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_import_interfaces.cpython-312.pyc
deleted file mode 100644
index ea80324..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_import_interfaces.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_io.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_io.cpython-312.pyc
deleted file mode 100644
index e04955a..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_io.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_numbers.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_numbers.cpython-312.pyc
deleted file mode 100644
index 81f489e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/__pycache__/test_numbers.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/basemapping.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/basemapping.py
deleted file mode 100644
index f58e32a..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/basemapping.py
+++ /dev/null
@@ -1,115 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Base Mapping tests
-"""
-from operator import __getitem__
-
-
-def testIReadMapping(self, inst, state, absent):
-    for key in state:
-        self.assertEqual(inst[key], state[key])
-        self.assertEqual(inst.get(key, None), state[key])
-        self.assertIn(key, inst)
-
-    for key in absent:
-        self.assertEqual(inst.get(key, None), None)
-        self.assertEqual(inst.get(key), None)
-        self.assertEqual(inst.get(key, self), self)
-        self.assertRaises(KeyError, __getitem__, inst, key)
-
-
-def test_keys(self, inst, state):
-    # Return the keys of the mapping object
-    inst_keys = sorted(inst.keys())
-    state_keys = sorted(state.keys())
-    self.assertEqual(inst_keys, state_keys)
-
-
-def test_iter(self, inst, state):
-    # Return the keys of the mapping object
-    inst_keys = sorted(inst)
-    state_keys = sorted(state.keys())
-    self.assertEqual(inst_keys, state_keys)
-
-
-def test_values(self, inst, state):
-    # Return the values of the mapping object
-    inst_values = sorted(inst.values())
-    state_values = sorted(state.values())
-    self.assertEqual(inst_values, state_values)
-
-
-def test_items(self, inst, state):
-    # Return the items of the mapping object
-    inst_items = sorted(inst.items())
-    state_items = sorted(state.items())
-    self.assertEqual(inst_items, state_items)
-
-
-def test___len__(self, inst, state):
-    # Return the number of items
-    self.assertEqual(len(inst), len(state))
-
-
-def testIEnumerableMapping(self, inst, state):
-    test_keys(self, inst, state)
-    test_items(self, inst, state)
-    test_values(self, inst, state)
-    test___len__(self, inst, state)
-
-
-class BaseTestIReadMapping:
-
-    def testIReadMapping(self):
-        inst = self._IReadMapping__sample()
-        state = self._IReadMapping__stateDict()
-        absent = self._IReadMapping__absentKeys()
-        testIReadMapping(self, inst, state, absent)
-
-
-class BaseTestIEnumerableMapping(BaseTestIReadMapping):
-    # Mapping objects whose items can be enumerated
-
-    def test_keys(self):
-        # Return the keys of the mapping object
-        inst = self._IEnumerableMapping__sample()
-        state = self._IEnumerableMapping__stateDict()
-        test_keys(self, inst, state)
-
-    def test_values(self):
-        # Return the values of the mapping object
-        inst = self._IEnumerableMapping__sample()
-        state = self._IEnumerableMapping__stateDict()
-        test_values(self, inst, state)
-
-    def test_items(self):
-        # Return the items of the mapping object
-        inst = self._IEnumerableMapping__sample()
-        state = self._IEnumerableMapping__stateDict()
-        test_items(self, inst, state)
-
-    def test___len__(self):
-        # Return the number of items
-        inst = self._IEnumerableMapping__sample()
-        state = self._IEnumerableMapping__stateDict()
-        test___len__(self, inst, state)
-
-    def _IReadMapping__stateDict(self):
-        return self._IEnumerableMapping__stateDict()
-
-    def _IReadMapping__sample(self):
-        return self._IEnumerableMapping__sample()
-
-    def _IReadMapping__absentKeys(self):
-        return self._IEnumerableMapping__absentKeys()
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_builtins.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_builtins.py
deleted file mode 100644
index 3c76439..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_builtins.py
+++ /dev/null
@@ -1,50 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-
-import unittest
-
-from zope.interface._compat import PY313_OR_OLDER
-from zope.interface.common import builtins
-
-from . import VerifyClassMixin
-from . import VerifyObjectMixin
-from . import add_verify_tests
-
-
-class TestVerifyClass(VerifyClassMixin,
-                      unittest.TestCase):
-    pass
-
-
-VERIFY_TESTS = [
-    (builtins.IList, (list,)),
-    (builtins.ITuple, (tuple,)),
-    (builtins.ITextString, (str,)),
-    (builtins.INativeString, (str,)),
-    (builtins.IBool, (bool,)),
-    (builtins.IDict, (dict,)),
-    (builtins.IFile, ()),
-
-]
-if PY313_OR_OLDER:
-    VERIFY_TESTS.append(
-        (builtins.IByteString, (bytes,))
-    )
-
-add_verify_tests(TestVerifyClass, tuple(VERIFY_TESTS))
-
-
-class TestVerifyObject(VerifyObjectMixin,
-                       TestVerifyClass):
-    CONSTRUCTORS = {
-        builtins.IFile: lambda: open(__file__)
-    }
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_collections.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_collections.py
deleted file mode 100644
index df7dec9..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_collections.py
+++ /dev/null
@@ -1,147 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-
-
-import array
-import sys
-import unittest
-from collections import OrderedDict
-from collections import abc
-from collections import deque
-from types import MappingProxyType
-
-from zope.interface import Invalid
-from zope.interface._compat import PYPY
-# Note that importing z.i.c.collections does work on import.
-from zope.interface.common import collections
-
-from . import VerifyClassMixin
-from . import VerifyObjectMixin
-from . import add_abc_interface_tests
-
-
-class TestVerifyClass(VerifyClassMixin, unittest.TestCase):
-
-    # Here we test some known builtin classes that are defined to implement
-    # various collection interfaces as a quick sanity test.
-    def test_frozenset(self):
-        self.assertIsInstance(frozenset(), abc.Set)
-        self.assertTrue(self.verify(collections.ISet, frozenset))
-
-    def test_list(self):
-        self.assertIsInstance(list(), abc.MutableSequence)
-        self.assertTrue(self.verify(collections.IMutableSequence, list))
-
-    # Here we test some derived classes.
-    def test_UserList(self):
-        self.assertTrue(self.verify(collections.IMutableSequence,
-                                    collections.UserList))
-
-    def test_UserDict(self):
-        self.assertTrue(self.verify(collections.IMutableMapping,
-                                    collections.UserDict))
-
-    def test_UserString(self):
-        self.assertTrue(self.verify(collections.ISequence,
-                                    collections.UserString))
-
-    # Now we go through the registry, which should have several things, mostly
-    # builtins, but if we've imported other libraries already, it could
-    # contain things from outside of there too. We aren't concerned about
-    # third-party code here, just standard library types. We start with a
-    # blacklist of things to exclude, but if that gets out of hand we can
-    # figure out a better whitelisting.
-    UNVERIFIABLE = {
-        # This is declared to be an ISequence, but is missing lots of methods,
-        # including some that aren't part of a language protocol, such as
-        # ``index`` and ``count``.
-        memoryview,
-        # 'pkg_resources._vendor.pyparsing.ParseResults' is registered as a
-        # MutableMapping but is missing methods like ``popitem`` and
-        # ``setdefault``.  It's imported due to namespace packages.
-        'ParseResults',
-        # sqlite3.Row claims ISequence but also misses ``index`` and
-        # ``count``.  It's imported because...? Coverage imports it, but why
-        # do we have it without coverage?
-        'Row',
-        # In Python 3.10 ``array.array`` appears as ``IMutableSequence`` but it
-        # does not provide a ``clear()`` method and it cannot be instantiated
-        # using ``array.array()``.
-        array.array,
-    }
-
-    if PYPY:
-        UNVERIFIABLE.update({
-            # collections.deque.pop() doesn't support the index= argument to
-            # MutableSequence.pop(). We can't verify this on CPython because
-            # we can't get the signature, but on PyPy we /can/ get the
-            # signature, and of course it doesn't match.
-            deque,
-            # Likewise for index
-            range,
-        })
-    UNVERIFIABLE_RO = {
-        # ``array.array`` fails the ``test_auto_ro_*`` tests with and
-        # without strict RO but only on Windows (AppVeyor) on Python 3.10.0
-        # (in older versions ``array.array`` does not appear as
-        # ``IMutableSequence``).
-        array.array,
-    }
-
-
-add_abc_interface_tests(TestVerifyClass, collections.ISet.__module__)
-
-
-def _get_FrameLocalsProxy():
-    return type(sys._getframe().f_locals)
-
-
-class TestVerifyObject(VerifyObjectMixin,
-                       TestVerifyClass):
-    CONSTRUCTORS = {
-        collections.IValuesView: {}.values,
-        collections.IItemsView: {}.items,
-        collections.IKeysView: {}.keys,
-        memoryview: lambda: memoryview(b'abc'),
-        range: lambda: range(10),
-        MappingProxyType: lambda: MappingProxyType({}),
-        collections.UserString: lambda: collections.UserString('abc'),
-        type(iter(bytearray())): lambda: iter(bytearray()),
-        type(iter(b'abc')): lambda: iter(b'abc'),
-        'coroutine': unittest.SkipTest,
-        type(iter({}.keys())): lambda: iter({}.keys()),
-        type(iter({}.items())): lambda: iter({}.items()),
-        type(iter({}.values())): lambda: iter({}.values()),
-        type(i for i in range(1)): lambda: (i for i in range(3)),
-        type(iter([])): lambda: iter([]),
-        type(reversed([])): lambda: reversed([]),
-        'longrange_iterator': unittest.SkipTest,
-        'range_iterator': lambda: iter(range(3)),
-        'rangeiterator': lambda: iter(range(3)),
-        type(iter(set())): lambda: iter(set()),
-        type(iter('')): lambda: iter(''),
-        'async_generator': unittest.SkipTest,
-        type(iter(tuple())): lambda: iter(tuple()),
-    }
-    if sys.version_info >= (3, 13):
-        def FrameLocalsProxy_constructor():
-            return _get_FrameLocalsProxy()(sys._getframe())
-        FrameLocalsProxy = _get_FrameLocalsProxy()
-        CONSTRUCTORS[FrameLocalsProxy] = FrameLocalsProxy_constructor
-
-    UNVERIFIABLE_RO = {
-        # ``array.array`` fails the ``test_auto_ro_*`` tests with and
-        # without strict RO but only on Windows (AppVeyor) on Python 3.10.0
-        # (in older versions ``array.array`` does not appear as
-        # ``IMutableSequence``).
-        array.array,
-    }
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_idatetime.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_idatetime.py
deleted file mode 100644
index 9550daa..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_idatetime.py
+++ /dev/null
@@ -1,48 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Test for datetime interfaces
-"""
-
-import unittest
-from datetime import date
-from datetime import datetime
-from datetime import time
-from datetime import timedelta
-from datetime import tzinfo
-
-from zope.interface.common.idatetime import IDate
-from zope.interface.common.idatetime import IDateClass
-from zope.interface.common.idatetime import IDateTime
-from zope.interface.common.idatetime import IDateTimeClass
-from zope.interface.common.idatetime import ITime
-from zope.interface.common.idatetime import ITimeClass
-from zope.interface.common.idatetime import ITimeDelta
-from zope.interface.common.idatetime import ITimeDeltaClass
-from zope.interface.common.idatetime import ITZInfo
-from zope.interface.verify import verifyClass
-from zope.interface.verify import verifyObject
-
-
-class TestDateTimeInterfaces(unittest.TestCase):
-
-    def test_interfaces(self):
-        verifyObject(ITimeDelta, timedelta(minutes=20))
-        verifyObject(IDate, date(2000, 1, 2))
-        verifyObject(IDateTime, datetime(2000, 1, 2, 10, 20))
-        verifyObject(ITime, time(20, 30, 15, 1234))
-        verifyObject(ITZInfo, tzinfo())
-        verifyClass(ITimeDeltaClass, timedelta)
-        verifyClass(IDateClass, date)
-        verifyClass(IDateTimeClass, datetime)
-        verifyClass(ITimeClass, time)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_import_interfaces.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_import_interfaces.py
deleted file mode 100644
index 67d1448..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_import_interfaces.py
+++ /dev/null
@@ -1,21 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2006 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-import unittest
-
-
-class TestInterfaceImport(unittest.TestCase):
-
-    def test_import(self):
-        import zope.interface.common.interfaces as x
-        self.assertIsNotNone(x)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_io.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_io.py
deleted file mode 100644
index 72684bf..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_io.py
+++ /dev/null
@@ -1,46 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-
-
-import io as abc
-import unittest
-
-# Note that importing z.i.c.io does work on import.
-from zope.interface.common import io
-
-from . import VerifyClassMixin
-from . import VerifyObjectMixin
-from . import add_abc_interface_tests
-
-
-class TestVerifyClass(VerifyClassMixin,
-                      unittest.TestCase):
-    pass
-
-
-add_abc_interface_tests(TestVerifyClass, io.IIOBase.__module__)
-
-
-class TestVerifyObject(VerifyObjectMixin,
-                       TestVerifyClass):
-    CONSTRUCTORS = {
-        abc.BufferedWriter: lambda: abc.BufferedWriter(abc.StringIO()),
-        abc.BufferedReader: lambda: abc.BufferedReader(abc.StringIO()),
-        abc.TextIOWrapper: lambda: abc.TextIOWrapper(abc.BytesIO()),
-        abc.BufferedRandom: lambda: abc.BufferedRandom(abc.BytesIO()),
-        abc.BufferedRWPair: lambda: abc.BufferedRWPair(
-            abc.BytesIO(), abc.BytesIO()
-        ),
-        abc.FileIO: lambda: abc.FileIO(__file__),
-        '_WindowsConsoleIO': unittest.SkipTest,
-        'WinConsoleIO': unittest.SkipTest,  # breaks on PyPy-3.10
-    }
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_numbers.py b/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_numbers.py
deleted file mode 100644
index 4e86514..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/common/tests/test_numbers.py
+++ /dev/null
@@ -1,42 +0,0 @@
-##############################################################################
-# Copyright (c) 2020 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-
-
-import numbers as abc
-import unittest
-
-# Note that importing z.i.c.numbers does work on import.
-from zope.interface.common import numbers
-
-from . import VerifyClassMixin
-from . import VerifyObjectMixin
-from . import add_abc_interface_tests
-
-
-class TestVerifyClass(VerifyClassMixin,
-                      unittest.TestCase):
-
-    def test_int(self):
-        self.assertIsInstance(int(), abc.Integral)
-        self.assertTrue(self.verify(numbers.IIntegral, int))
-
-    def test_float(self):
-        self.assertIsInstance(float(), abc.Real)
-        self.assertTrue(self.verify(numbers.IReal, float))
-
-
-add_abc_interface_tests(TestVerifyClass, numbers.INumber.__module__)
-
-
-class TestVerifyObject(VerifyObjectMixin,
-                       TestVerifyClass):
-    pass
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/declarations.py b/llmlab/lib/python3.12/site-packages/zope/interface/declarations.py
deleted file mode 100644
index 825c578..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/declarations.py
+++ /dev/null
@@ -1,1219 +0,0 @@
-##############################################################################
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-##############################################################################
-"""Implementation of interface declarations
-
-There are three flavors of declarations:
-
-  - Declarations are used to simply name declared interfaces.
-
-  - ImplementsDeclarations are used to express the interfaces that a
-    class implements (that instances of the class provides).
-
-    Implements specifications support inheriting interfaces.
-
-  - ProvidesDeclarations are used to express interfaces directly
-    provided by objects.
-
-"""
-__docformat__ = 'restructuredtext'
-
-import sys
-import weakref
-from types import FunctionType
-from types import MethodType
-from types import ModuleType
-
-from zope.interface._compat import _use_c_impl
-from zope.interface.interface import Interface
-from zope.interface.interface import InterfaceBase
-from zope.interface.interface import InterfaceClass
-from zope.interface.interface import NameAndModuleComparisonMixin
-from zope.interface.interface import Specification
-from zope.interface.interface import SpecificationBase
-
-
-__all__ = [
-    # None. The public APIs of this module are
-    # re-exported from zope.interface directly.
-]
-
-# pylint:disable=too-many-lines
-
-# Registry of class-implementation specifications
-BuiltinImplementationSpecifications = {}
-
-
-def _next_super_class(ob):
-    # When ``ob`` is an instance of ``super``, return
-    # the next class in the MRO that we should actually be
-    # looking at. Watch out for diamond inheritance!
-    self_class = ob.__self_class__
-    class_that_invoked_super = ob.__thisclass__
-    complete_mro = self_class.__mro__
-    next_class = complete_mro[complete_mro.index(class_that_invoked_super) + 1]
-    return next_class
-
-
-class named:
-
-    def __init__(self, name):
-        self.name = name
-
-    def __call__(self, ob):
-        ob.__component_name__ = self.name
-        return ob
-
-
-class Declaration(Specification):
-    """Interface declarations"""
-
-    __slots__ = ()
-
-    def __init__(self, *bases):
-        Specification.__init__(self, _normalizeargs(bases))
-
-    def __contains__(self, interface):
-        """Test whether an interface is in the specification
-        """
-
-        return self.extends(interface) and interface in self.interfaces()
-
-    def __iter__(self):
-        """Return an iterator for the interfaces in the specification
-        """
-        return self.interfaces()
-
-    def flattened(self):
-        """Return an iterator of all included and extended interfaces
-        """
-        return iter(self.__iro__)
-
-    def __sub__(self, other):
-        """Remove interfaces from a specification
-        """
-        return Declaration(*[
-            i for i in self.interfaces()
-            if not [
-                j
-                for j in other.interfaces()
-                if i.extends(j, 0)  # non-strict extends
-            ]
-        ])
-
-    def __add__(self, other):
-        """
-        Add two specifications or a specification and an interface
-        and produce a new declaration.
-
-        .. versionchanged:: 5.4.0
-           Now tries to preserve a consistent resolution order. Interfaces
-           being added to this object are added to the front of the resulting
-           resolution order if they already extend an interface in this
-           object. Previously, they were always added to the end of the order,
-           which easily resulted in invalid orders.
-        """
-        before = []
-        result = list(self.interfaces())
-        seen = set(result)
-        for i in other.interfaces():
-            if i in seen:
-                continue
-            seen.add(i)
-            if any(i.extends(x) for x in result):
-                # It already extends us, e.g., is a subclass,
-                # so it needs to go at the front of the RO.
-                before.append(i)
-            else:
-                result.append(i)
-        return Declaration(*(before + result))
-
-    # XXX: Is __radd__ needed? No tests break if it's removed.
-    # If it is needed, does it need to handle the C3 ordering differently?
-    # I (JAM) don't *think* it does.
-    __radd__ = __add__
-
-    @staticmethod
-    def _add_interfaces_to_cls(interfaces, cls):
-        # Strip redundant interfaces already provided
-        # by the cls so we don't produce invalid
-        # resolution orders.
-        implemented_by_cls = implementedBy(cls)
-        interfaces = tuple([
-            iface
-            for iface in interfaces
-            if not implemented_by_cls.isOrExtends(iface)
-        ])
-        return interfaces + (implemented_by_cls,)
-
-    @staticmethod
-    def _argument_names_for_repr(interfaces):
-        # These don't actually have to be interfaces, they could be other
-        # Specification objects like Implements. Also, the first
-        # one is typically/nominally the cls.
-        ordered_names = []
-        names = set()
-        for iface in interfaces:
-            duplicate_transform = repr
-            if isinstance(iface, InterfaceClass):
-                # Special case to get 'foo.bar.IFace'
-                # instead of ''
-                this_name = iface.__name__
-                duplicate_transform = str
-            elif isinstance(iface, type):
-                # Likewise for types. (Ignoring legacy old-style
-                # classes.)
-                this_name = iface.__name__
-                duplicate_transform = _implements_name
-            elif (
-                isinstance(iface, Implements) and
-                not iface.declared and
-                iface.inherit in interfaces
-            ):
-                # If nothing is declared, there's no need to even print this;
-                # it would just show as ``classImplements(Class)``, and the
-                # ``Class`` has typically already.
-                continue
-            else:
-                this_name = repr(iface)
-
-            already_seen = this_name in names
-            names.add(this_name)
-            if already_seen:
-                this_name = duplicate_transform(iface)
-
-            ordered_names.append(this_name)
-        return ', '.join(ordered_names)
-
-
-class _ImmutableDeclaration(Declaration):
-    # A Declaration that is immutable. Used as a singleton to
-    # return empty answers for things like ``implementedBy``.
-    # We have to define the actual singleton after normalizeargs
-    # is defined, and that in turn is defined after InterfaceClass and
-    # Implements.
-
-    __slots__ = ()
-
-    __instance = None
-
-    def __new__(cls):
-        if _ImmutableDeclaration.__instance is None:
-            _ImmutableDeclaration.__instance = object.__new__(cls)
-        return _ImmutableDeclaration.__instance
-
-    def __reduce__(self):
-        return "_empty"
-
-    @property
-    def __bases__(self):
-        return ()
-
-    @__bases__.setter
-    def __bases__(self, new_bases):
-        # We expect the superclass constructor to set ``self.__bases__ = ()``.
-        # Rather than attempt to special case that in the constructor and
-        # allow setting __bases__ only at that time, it's easier to just allow
-        # setting the empty tuple at any time. That makes ``x.__bases__ =
-        # x.__bases__`` a nice no-op too. (Skipping the superclass constructor
-        # altogether is a recipe for maintenance headaches.)
-        if new_bases != ():
-            raise TypeError(
-                "Cannot set non-empty bases on shared empty Declaration."
-            )
-
-    # As the immutable empty declaration, we cannot be changed.
-    # This means there's no logical reason for us to have dependents
-    # or subscriptions: we'll never notify them. So there's no need for
-    # us to keep track of any of that.
-    @property
-    def dependents(self):
-        return {}
-
-    changed = subscribe = unsubscribe = lambda self, _ignored: None
-
-    def interfaces(self):
-        # An empty iterator
-        return iter(())
-
-    def extends(self, interface, strict=True):
-        return interface is self._ROOT
-
-    def get(self, name, default=None):
-        return default
-
-    def weakref(self, callback=None):
-        # We're a singleton, we never go away. So there's no need to return
-        # distinct weakref objects here; their callbacks will never be called.
-        # Instead, we only need to return a callable that returns ourself. The
-        # easiest one is to return _ImmutableDeclaration itself; testing on
-        # Python 3.8 shows that's faster than a function that returns _empty.
-        # (Remember, one goal is to avoid allocating any object, and that
-        # includes a method.)
-        return _ImmutableDeclaration
-
-    @property
-    def _v_attrs(self):
-        # _v_attrs is not a public, documented property, but some client code
-        # uses it anyway as a convenient place to cache things. To keep the
-        # empty declaration truly immutable, we must ignore that. That
-        # includes ignoring assignments as well.
-        return {}
-
-    @_v_attrs.setter
-    def _v_attrs(self, new_attrs):
-        pass
-
-
-##############################################################################
-#
-# Implementation specifications
-#
-# These specify interfaces implemented by instances of classes
-
-class Implements(NameAndModuleComparisonMixin,
-                 Declaration):
-    # Inherit from NameAndModuleComparisonMixin to be mutually comparable with
-    # InterfaceClass objects.  (The two must be mutually comparable to be able
-    # to work in e.g., BTrees.) Instances of this class generally don't have a
-    # __module__ other than `zope.interface.declarations`, whereas they *do*
-    # have a __name__ that is the fully qualified name of the object they are
-    # representing.
-
-    # Note, though, that equality and hashing are still identity based. This
-    # accounts for things like nested objects that have the same name
-    # (typically only in tests) and is consistent with pickling. As far as
-    # comparisons to InterfaceClass goes, we'll never have equal name and
-    # module to those, so we're still consistent there.  Instances of this
-    # class are essentially intended to be unique and are heavily cached (note
-    # how our __reduce__ handles this) so having identity based hash and eq
-    # should also work.
-
-    # We want equality and hashing to be based on identity. However, we can't
-    # actually implement __eq__/__ne__ to do this because sometimes we get
-    # wrapped in a proxy.  We need to let the proxy types implement these
-    # methods so they can handle unwrapping and then rely on: (1) the
-    # interpreter automatically changing `implements == proxy` into `proxy ==
-    # implements` (which will call proxy.__eq__ to do the unwrapping) and then
-    # (2) the default equality and hashing semantics being identity based.
-
-    # class whose specification should be used as additional base
-    inherit = None
-
-    # interfaces actually declared for a class
-    declared = ()
-
-    # Weak cache of {class: } for super objects.
-    # Created on demand. These are rare, as of 5.0 anyway. Using a class
-    # level default doesn't take space in instances. Using _v_attrs would be
-    # another place to store this without taking space unless needed.
-    _super_cache = None
-
-    __name__ = '?'
-
-    @classmethod
-    def named(cls, name, *bases):
-        # Implementation method: Produce an Implements interface with a fully
-        # fleshed out __name__ before calling the constructor, which sets
-        # bases to the given interfaces and which may pass this object to
-        # other objects (e.g., to adjust dependents). If they're sorting or
-        # comparing by name, this needs to be set.
-        inst = cls.__new__(cls)
-        inst.__name__ = name
-        inst.__init__(*bases)
-        return inst
-
-    def changed(self, originally_changed):
-        try:
-            del self._super_cache
-        except AttributeError:
-            pass
-        return super().changed(originally_changed)
-
-    def __repr__(self):
-        if self.inherit:
-            name = (
-                getattr(self.inherit, '__name__', None) or
-                _implements_name(self.inherit)
-            )
-        else:
-            name = self.__name__
-        declared_names = self._argument_names_for_repr(self.declared)
-        if declared_names:
-            declared_names = ', ' + declared_names
-        return f'classImplements({name}{declared_names})'
-
-    def __reduce__(self):
-        return implementedBy, (self.inherit, )
-
-
-def _implements_name(ob):
-    # Return the __name__ attribute to be used by its __implemented__
-    # property.
-    # This must be stable for the "same" object across processes
-    # because it is used for sorting. It needn't be unique, though, in cases
-    # like nested classes named Foo created by different functions, because
-    # equality and hashing is still based on identity.
-    # It might be nice to use __qualname__ on Python 3, but that would produce
-    # different values between Py2 and Py3.
-
-    # Special-case 'InterfaceBase':  its '__module__' member descriptor
-    # behaves differently across Python 3.x versions.
-    if ob is InterfaceBase:
-        return 'zope.interface.interface.InterfaceBase'
-
-    return (getattr(ob, '__module__', '?') or '?') + \
-        '.' + (getattr(ob, '__name__', '?') or '?')
-
-
-def _implementedBy_super(sup):
-    # TODO: This is now simple enough we could probably implement
-    # in C if needed.
-
-    # If the class MRO is strictly linear, we could just
-    # follow the normal algorithm for the next class in the
-    # search order (e.g., just return
-    # ``implemented_by_next``). But when diamond inheritance
-    # or mixins + interface declarations are present, we have
-    # to consider the whole MRO and compute a new Implements
-    # that excludes the classes being skipped over but
-    # includes everything else.
-    implemented_by_self = implementedBy(sup.__self_class__)
-    cache = implemented_by_self._super_cache  # pylint:disable=protected-access
-    if cache is None:
-        cache = implemented_by_self._super_cache = weakref.WeakKeyDictionary()
-
-    key = sup.__thisclass__
-    try:
-        return cache[key]
-    except KeyError:
-        pass
-
-    next_cls = _next_super_class(sup)
-    # For ``implementedBy(cls)``:
-    # .__bases__ is .declared + [implementedBy(b) for b in cls.__bases__]
-    # .inherit is cls
-
-    implemented_by_next = implementedBy(next_cls)
-    mro = sup.__self_class__.__mro__
-    ix_next_cls = mro.index(next_cls)
-    classes_to_keep = mro[ix_next_cls:]
-    new_bases = [implementedBy(c) for c in classes_to_keep]
-
-    new = Implements.named(
-        implemented_by_self.__name__ + ':' + implemented_by_next.__name__,
-        *new_bases
-    )
-    new.inherit = implemented_by_next.inherit
-    new.declared = implemented_by_next.declared
-    # I don't *think* that new needs to subscribe to ``implemented_by_self``;
-    # it auto-subscribed to its bases, and that should be good enough.
-    cache[key] = new
-
-    return new
-
-
-@_use_c_impl
-def implementedBy(
-    cls
-):  # pylint:disable=too-many-return-statements,too-many-branches
-    """Return the interfaces implemented for a class' instances
-
-      The value returned is an `~zope.interface.interfaces.IDeclaration`.
-    """
-    try:
-        if isinstance(cls, super):
-            # Yes, this needs to be inside the try: block. Some objects
-            # like security proxies even break isinstance.
-            return _implementedBy_super(cls)
-
-        spec = cls.__dict__.get('__implemented__')
-    except AttributeError:
-
-        # we can't get the class dict. This is probably due to a
-        # security proxy.  If this is the case, then probably no
-        # descriptor was installed for the class.
-
-        # We don't want to depend directly on zope.security in
-        # zope.interface, but we'll try to make reasonable
-        # accommodations in an indirect way.
-
-        # We'll check to see if there's an implements:
-
-        spec = getattr(cls, '__implemented__', None)
-        if spec is None:
-            # There's no spec stred in the class. Maybe its a builtin:
-            spec = BuiltinImplementationSpecifications.get(cls)
-            if spec is not None:
-                return spec
-            return _empty
-
-        if spec.__class__ == Implements:
-            # we defaulted to _empty or there was a spec. Good enough.
-            # Return it.
-            return spec
-
-        # TODO: need old style __implements__ compatibility?
-        # Hm, there's an __implemented__, but it's not a spec. Must be
-        # an old-style declaration. Just compute a spec for it
-        return Declaration(*_normalizeargs((spec, )))
-
-    if isinstance(spec, Implements):
-        return spec
-
-    if spec is None:
-        spec = BuiltinImplementationSpecifications.get(cls)
-        if spec is not None:
-            return spec
-
-    # TODO: need old style __implements__ compatibility?
-    spec_name = _implements_name(cls)
-    if spec is not None:
-        # old-style __implemented__ = foo declaration
-        spec = (spec, )          # tuplefy, as it might be just an int
-        spec = Implements.named(spec_name, *_normalizeargs(spec))
-        spec.inherit = None      # old-style implies no inherit
-        del cls.__implemented__  # get rid of the old-style declaration
-    else:
-        try:
-            bases = cls.__bases__
-        except AttributeError:
-            if not callable(cls):
-                raise TypeError("ImplementedBy called for non-factory", cls)
-            bases = ()
-
-        spec = Implements.named(spec_name, *[implementedBy(c) for c in bases])
-        spec.inherit = cls
-
-    try:
-        cls.__implemented__ = spec
-        if not hasattr(cls, '__providedBy__'):
-            cls.__providedBy__ = objectSpecificationDescriptor
-
-        if isinstance(cls, type) and '__provides__' not in cls.__dict__:
-            # Make sure we get a __provides__ descriptor
-            cls.__provides__ = ClassProvides(
-                cls, getattr(cls, '__class__', type(cls)),
-            )
-
-    except TypeError:
-        if not isinstance(cls, type):
-            raise TypeError("ImplementedBy called for non-type", cls)
-        BuiltinImplementationSpecifications[cls] = spec
-
-    return spec
-
-
-def classImplementsOnly(cls, *interfaces):
-    """
-    Declare the only interfaces implemented by instances of a class
-
-    The arguments after the class are one or more interfaces or interface
-    specifications (`~zope.interface.interfaces.IDeclaration` objects).
-
-    The interfaces given (including the interfaces in the specifications)
-    replace any previous declarations, *including* inherited definitions. If
-    you wish to preserve inherited declarations, you can pass
-    ``implementedBy(cls)`` in *interfaces*. This can be used to alter the
-    interface resolution order.
-    """
-    spec = implementedBy(cls)
-    # Clear out everything inherited. It's important to
-    # also clear the bases right now so that we don't improperly discard
-    # interfaces that are already implemented by *old* bases that we're
-    # about to get rid of.
-    spec.declared = ()
-    spec.inherit = None
-    spec.__bases__ = ()
-    _classImplements_ordered(spec, interfaces, ())
-
-
-def classImplements(cls, *interfaces):
-    """
-    Declare additional interfaces implemented for instances of a class
-
-    The arguments after the class are one or more interfaces or interface
-    specifications (`~zope.interface.interfaces.IDeclaration` objects).
-
-    The interfaces given (including the interfaces in the specifications)
-    are added to any interfaces previously declared. An effort is made to
-    keep a consistent C3 resolution order, but this cannot be guaranteed.
-
-    .. versionchanged:: 5.0.0
-       Each individual interface in *interfaces* may be added to either the
-       beginning or end of the list of interfaces declared for *cls*,
-       based on inheritance, in order to try to maintain a consistent
-       resolution order. Previously, all interfaces were added to the end.
-    .. versionchanged:: 5.1.0
-       If *cls* is already declared to implement an interface (or derived
-       interface) in *interfaces* through inheritance, the interface is
-       ignored. Previously, it would redundantly be made direct base of *cls*,
-       which often produced inconsistent interface resolution orders. Now, the
-       order will be consistent, but may change.  Also, if the ``__bases__``
-       of the *cls* are later changed, the *cls* will no longer be considered
-       to implement such an interface (changing the ``__bases__`` of *cls* has
-       never been supported).
-    """
-    spec = implementedBy(cls)
-    interfaces = tuple(_normalizeargs(interfaces))
-
-    before = []
-    after = []
-
-    # Take steps to try to avoid producing an invalid resolution
-    # order, while still allowing for BWC (in the past, we always
-    # appended)
-    for iface in interfaces:
-        for b in spec.declared:
-            if iface.extends(b):
-                before.append(iface)
-                break
-        else:
-            after.append(iface)
-    _classImplements_ordered(spec, tuple(before), tuple(after))
-
-
-def classImplementsFirst(cls, iface):
-    """
-    Declare that instances of *cls* additionally provide *iface*.
-
-    The second argument is an interface or interface specification.
-    It is added as the highest priority (first in the IRO) interface;
-    no attempt is made to keep a consistent resolution order.
-
-    .. versionadded:: 5.0.0
-    """
-    spec = implementedBy(cls)
-    _classImplements_ordered(spec, (iface,), ())
-
-
-def _classImplements_ordered(spec, before=(), after=()):
-    # Elide everything already inherited.
-    # Except, if it is the root, and we don't already declare anything else
-    # that would imply it, allow the root through. (TODO: When we disallow
-    # non-strict IRO, this part of the check can be removed because it's not
-    # possible to re-declare like that.)
-    before = [
-        x
-        for x in before
-        if not spec.isOrExtends(x) or (x is Interface and not spec.declared)
-    ]
-    after = [
-        x
-        for x in after
-        if not spec.isOrExtends(x) or (x is Interface and not spec.declared)
-    ]
-
-    # eliminate duplicates
-    new_declared = []
-    seen = set()
-    for lst in before, spec.declared, after:
-        for b in lst:
-            if b not in seen:
-                new_declared.append(b)
-                seen.add(b)
-
-    spec.declared = tuple(new_declared)
-
-    # compute the bases
-    bases = new_declared  # guaranteed no dupes
-
-    if spec.inherit is not None:
-        for c in spec.inherit.__bases__:
-            b = implementedBy(c)
-            if b not in seen:
-                seen.add(b)
-                bases.append(b)
-
-    spec.__bases__ = tuple(bases)
-
-
-def _implements_advice(cls):
-    interfaces, do_classImplements = cls.__dict__['__implements_advice_data__']
-    del cls.__implements_advice_data__
-    do_classImplements(cls, *interfaces)
-    return cls
-
-
-class implementer:
-    """
-    Declare the interfaces implemented by instances of a class.
-
-    This function is called as a class decorator.
-
-    The arguments are one or more interfaces or interface specifications
-    (`~zope.interface.interfaces.IDeclaration` objects).
-
-    The interfaces given (including the interfaces in the specifications) are
-    added to any interfaces previously declared, unless the interface is
-    already implemented.
-
-    Previous declarations include declarations for base classes unless
-    implementsOnly was used.
-
-    This function is provided for convenience. It provides a more convenient
-    way to call `classImplements`. For example::
-
-        @implementer(I1)
-        class C(object):
-            pass
-
-    is equivalent to calling::
-
-        classImplements(C, I1)
-
-    after the class has been created.
-
-    .. seealso:: `classImplements`
-       The change history provided there applies to this function too.
-    """
-    __slots__ = ('interfaces',)
-
-    def __init__(self, *interfaces):
-        self.interfaces = interfaces
-
-    def __call__(self, ob):
-        if isinstance(ob, type):
-            # This is the common branch for classes.
-            classImplements(ob, *self.interfaces)
-            return ob
-
-        spec_name = _implements_name(ob)
-        spec = Implements.named(spec_name, *self.interfaces)
-        try:
-            ob.__implemented__ = spec
-        except AttributeError:
-            raise TypeError("Can't declare implements", ob)
-        return ob
-
-
-class implementer_only:
-    """Declare the only interfaces implemented by instances of a class
-
-      This function is called as a class decorator.
-
-      The arguments are one or more interfaces or interface
-      specifications (`~zope.interface.interfaces.IDeclaration` objects).
-
-      Previous declarations including declarations for base classes
-      are overridden.
-
-      This function is provided for convenience. It provides a more
-      convenient way to call `classImplementsOnly`. For example::
-
-        @implementer_only(I1)
-        class C(object): pass
-
-      is equivalent to calling::
-
-        classImplementsOnly(I1)
-
-      after the class has been created.
-      """
-
-    def __init__(self, *interfaces):
-        self.interfaces = interfaces
-
-    def __call__(self, ob):
-        if isinstance(ob, (FunctionType, MethodType)):
-            # XXX Does this decorator make sense for anything but classes?
-            # I don't think so. There can be no inheritance of interfaces
-            # on a method or function....
-            raise ValueError('The implementer_only decorator is not '
-                             'supported for methods or functions.')
-
-        # Assume it's a class:
-        classImplementsOnly(ob, *self.interfaces)
-        return ob
-
-
-##############################################################################
-#
-# Instance declarations
-
-class Provides(Declaration):  # Really named ProvidesClass
-    """Implement ``__provides__``, the instance-specific specification
-
-    When an object is pickled, we pickle the interfaces that it implements.
-    """
-
-    def __init__(self, cls, *interfaces):
-        self.__args = (cls, ) + interfaces
-        self._cls = cls
-        Declaration.__init__(
-            self, *self._add_interfaces_to_cls(interfaces, cls)
-        )
-
-    # Added to by ``moduleProvides``, et al
-    _v_module_names = ()
-
-    def __repr__(self):
-        # The typical way to create instances of this object is via calling
-        # ``directlyProvides(...)`` or ``alsoProvides()``, but that's not the
-        # only way. Proxies, for example, directly use the ``Provides(...)``
-        # function (which is the more generic method, and what we pickle as).
-        # We're after the most readable, useful repr in the common case, so we
-        # use the most common name.
-        #
-        # We also cooperate with ``moduleProvides`` to attempt to do the right
-        # thing for that API. See it for details.
-        function_name = 'directlyProvides'
-        if self._cls is ModuleType and self._v_module_names:
-            # See notes in ``moduleProvides``/``directlyProvides``
-            providing_on_module = True
-            interfaces = self.__args[1:]
-        else:
-            providing_on_module = False
-            interfaces = (self._cls,) + self.__bases__
-        ordered_names = self._argument_names_for_repr(interfaces)
-        if providing_on_module:
-            mod_names = self._v_module_names
-            if len(mod_names) == 1:
-                mod_names = "sys.modules[%r]" % mod_names[0]
-            ordered_names = (
-                f'{mod_names}, '
-            ) + ordered_names
-        return "{}({})".format(
-            function_name,
-            ordered_names,
-        )
-
-    def __reduce__(self):
-        # This reduces to the Provides *function*, not
-        # this class.
-        return Provides, self.__args
-
-    __module__ = 'zope.interface'
-
-    def __get__(self, inst, cls):
-        """Make sure that a class __provides__ doesn't leak to an instance
-        """
-        if inst is None and cls is self._cls:
-            # We were accessed through a class, so we are the class'
-            # provides spec. Just return this object, but only if we are
-            # being called on the same class that we were defined for:
-            return self
-
-        raise AttributeError('__provides__')
-
-
-ProvidesClass = Provides
-
-
-# Registry of instance declarations
-# This is a memory optimization to allow objects to share specifications.
-InstanceDeclarations = weakref.WeakValueDictionary()
-
-
-def Provides(*interfaces):  # pylint:disable=function-redefined
-    """Declaration for an instance of *cls*.
-
-       The correct signature is ``cls, *interfaces``.
-       The *cls* is necessary to avoid the
-       construction of inconsistent resolution orders.
-
-      Instance declarations are shared among instances that have the same
-      declaration. The declarations are cached in a weak value dictionary.
-    """
-    spec = InstanceDeclarations.get(interfaces)
-    if spec is None:
-        spec = ProvidesClass(*interfaces)
-        InstanceDeclarations[interfaces] = spec
-
-    return spec
-
-
-Provides.__safe_for_unpickling__ = True
-
-
-def directlyProvides(object, *interfaces):  # pylint:disable=redefined-builtin
-    """Declare interfaces declared directly for an object
-
-      The arguments after the object are one or more interfaces or interface
-      specifications (`~zope.interface.interfaces.IDeclaration` objects).
-
-      The interfaces given (including the interfaces in the specifications)
-      replace interfaces previously declared for the object.
-    """
-    cls = getattr(object, '__class__', None)
-    if cls is not None and getattr(cls, '__class__', None) is cls:
-        # It's a meta class (well, at least it it could be an extension class)
-        # Note that we can't get here from the tests:  there is no normal
-        # class which isn't descriptor aware.
-        if not isinstance(object, type):
-            raise TypeError("Attempt to make an interface declaration on a "
-                            "non-descriptor-aware class")
-
-    interfaces = _normalizeargs(interfaces)
-    if cls is None:
-        cls = type(object)
-
-    if issubclass(cls, type):
-        # we have a class or type.  We'll use a special descriptor
-        # that provides some extra caching
-        object.__provides__ = ClassProvides(object, cls, *interfaces)
-    else:
-        provides = object.__provides__ = Provides(cls, *interfaces)
-        # See notes in ``moduleProvides``.
-        if issubclass(cls, ModuleType) and hasattr(object, '__name__'):
-            provides._v_module_names += (object.__name__,)
-
-
-def alsoProvides(object, *interfaces):  # pylint:disable=redefined-builtin
-    """Declare interfaces declared directly for an object
-
-    The arguments after the object are one or more interfaces or interface
-    specifications (`~zope.interface.interfaces.IDeclaration` objects).
-
-    The interfaces given (including the interfaces in the specifications) are
-    added to the interfaces previously declared for the object.
-    """
-    directlyProvides(object, directlyProvidedBy(object), *interfaces)
-
-
-def noLongerProvides(object, interface):  # pylint:disable=redefined-builtin
-    """ Removes a directly provided interface from an object.
-    """
-    directlyProvides(object, directlyProvidedBy(object) - interface)
-    if interface.providedBy(object):
-        raise ValueError("Can only remove directly provided interfaces.")
-
-
-@_use_c_impl
-class ClassProvidesBase(SpecificationBase):
-
-    __slots__ = (
-        '_cls',
-        '_implements',
-    )
-
-    def __get__(self, inst, cls):
-        # member slots are set by subclass
-        # pylint:disable=no-member
-        if cls is self._cls:
-            # We only work if called on the class we were defined for
-
-            if inst is None:
-                # We were accessed through a class, so we are the class'
-                # provides spec. Just return this object as is:
-                return self
-
-            return self._implements
-
-        raise AttributeError('__provides__')
-
-
-class ClassProvides(Declaration, ClassProvidesBase):
-    """Special descriptor for class ``__provides__``
-
-    The descriptor caches the implementedBy info, so that
-    we can get declarations for objects without instance-specific
-    interfaces a bit quicker.
-    """
-
-    __slots__ = (
-        '__args',
-    )
-
-    def __init__(self, cls, metacls, *interfaces):
-        self._cls = cls
-        self._implements = implementedBy(cls)
-        self.__args = (cls, metacls, ) + interfaces
-        Declaration.__init__(
-            self, *self._add_interfaces_to_cls(interfaces, metacls)
-        )
-
-    def __repr__(self):
-        # There are two common ways to get instances of this object: The most
-        # interesting way is calling ``@provider(..)`` as a decorator of a
-        # class; this is the same as calling ``directlyProvides(cls, ...)``.
-        #
-        # The other way is by default: anything that invokes
-        # ``implementedBy(x)`` will wind up putting an instance in
-        # ``type(x).__provides__``; this includes the ``@implementer(...)``
-        # decorator. Those instances won't have any interfaces.
-        #
-        # Thus, as our repr, we go with the ``directlyProvides()`` syntax.
-        interfaces = (self._cls, ) + self.__args[2:]
-        ordered_names = self._argument_names_for_repr(interfaces)
-        return f"directlyProvides({ordered_names})"
-
-    def __reduce__(self):
-        return self.__class__, self.__args
-
-    # Copy base-class method for speed
-    __get__ = ClassProvidesBase.__get__
-
-
-# autopep8: off (it breaks the statements in the "if")
-def directlyProvidedBy(object):  # pylint:disable=redefined-builtin
-    """Return the interfaces directly provided by the given object
-
-    The value returned is an `~zope.interface.interfaces.IDeclaration`.
-    """
-    provides = getattr(object, "__provides__", None)
-    if (
-            provides is None  # no spec
-            # We might have gotten the implements spec, as an
-            # optimization. If so, it's like having only one base, that we
-            # lop off to exclude class-supplied declarations:
-            or isinstance(provides, Implements)  # noqa W503
-    ):
-        return _empty
-
-    # Strip off the class part of the spec:
-    return Declaration(provides.__bases__[:-1])
-# autopep8: on
-
-
-class provider:
-    """Declare interfaces provided directly by a class
-
-      This function is called in a class definition.
-
-      The arguments are one or more interfaces or interface specifications
-      (`~zope.interface.interfaces.IDeclaration` objects).
-
-      The given interfaces (including the interfaces in the specifications)
-      are used to create the class's direct-object interface specification.
-      An error will be raised if the module class has an direct interface
-      specification. In other words, it is an error to call this function more
-      than once in a class definition.
-
-      Note that the given interfaces have nothing to do with the interfaces
-      implemented by instances of the class.
-
-      This function is provided for convenience. It provides a more convenient
-      way to call `directlyProvides` for a class. For example::
-
-        @provider(I1)
-        class C:
-            pass
-
-      is equivalent to calling::
-
-        directlyProvides(C, I1)
-
-      after the class has been created.
-    """
-
-    def __init__(self, *interfaces):
-        self.interfaces = interfaces
-
-    def __call__(self, ob):
-        directlyProvides(ob, *self.interfaces)
-        return ob
-
-
-def moduleProvides(*interfaces):
-    """Declare interfaces provided by a module
-
-    This function is used in a module definition.
-
-    The arguments are one or more interfaces or interface specifications
-    (`~zope.interface.interfaces.IDeclaration` objects).
-
-    The given interfaces (including the interfaces in the specifications) are
-    used to create the module's direct-object interface specification.  An
-    error will be raised if the module already has an interface specification.
-    In other words, it is an error to call this function more than once in a
-    module definition.
-
-    This function is provided for convenience. It provides a more convenient
-    way to call directlyProvides. For example::
-
-      moduleProvides(I1)
-
-    is equivalent to::
-
-      directlyProvides(sys.modules[__name__], I1)
-    """
-    frame = sys._getframe(1)  # pylint:disable=protected-access
-    locals = frame.f_locals   # pylint:disable=redefined-builtin
-
-    # Try to make sure we were called from a module body
-    if (locals is not frame.f_globals) or ('__name__' not in locals):
-        raise TypeError(
-            "moduleProvides can only be used from a module definition.")
-
-    if '__provides__' in locals:
-        raise TypeError(
-            "moduleProvides can only be used once in a module definition.")
-
-    # Note: This is cached based on the key ``(ModuleType, *interfaces)``; One
-    # consequence is that any module that provides the same interfaces gets
-    # the same ``__repr__``, meaning that you can't tell what module such a
-    # declaration came from. Adding the module name to ``_v_module_names``
-    # attempts to correct for this; it works in some common situations, but
-    # fails (1) after pickling (the data is lost) and (2) if declarations are
-    # actually shared and (3) if the alternate spelling of
-    # ``directlyProvides()`` is used. Problem (3)  is fixed by cooperating
-    # with ``directlyProvides`` to maintain this information, and problem (2)
-    # is worked around by printing all the names, but (1) is unsolvable
-    # without introducing new classes or changing the stored data...but it
-    # doesn't actually matter, because ``ModuleType`` can't be pickled!
-    p = locals["__provides__"] = Provides(ModuleType,
-                                          *_normalizeargs(interfaces))
-    p._v_module_names += (locals['__name__'],)
-
-
-##############################################################################
-#
-# Declaration querying support
-
-# XXX:  is this a fossil?  Nobody calls it, no unit tests exercise it, no
-#       doctests import it, and the package __init__ doesn't import it.
-#       (Answer: Versions of zope.container prior to 4.4.0 called this,
-#        and zope.proxy.decorator up through at least 4.3.5 called this.)
-def ObjectSpecification(direct, cls):
-    """Provide object specifications
-
-    These combine information for the object and for it's classes.
-    """
-    return Provides(cls, direct)  # pragma: no cover fossil
-
-
-@_use_c_impl
-def getObjectSpecification(ob):
-    try:
-        provides = ob.__provides__
-    except AttributeError:
-        provides = None
-
-    if provides is not None:
-        if isinstance(provides, SpecificationBase):
-            return provides
-
-    try:
-        cls = ob.__class__
-    except AttributeError:
-        # We can't get the class, so just consider provides
-        return _empty
-    return implementedBy(cls)
-
-
-@_use_c_impl
-def providedBy(ob):
-    """
-    Return the interfaces provided by *ob*.
-
-    If *ob* is a :class:`super` object, then only interfaces implemented
-    by the remainder of the classes in the method resolution order are
-    considered. Interfaces directly provided by the object underlying *ob*
-    are not.
-    """
-    # Here we have either a special object, an old-style declaration
-    # or a descriptor
-
-    # Try to get __providedBy__
-    try:
-        if isinstance(ob, super):  # Some objects raise errors on isinstance()
-            return implementedBy(ob)
-
-        r = ob.__providedBy__
-    except AttributeError:
-        # Not set yet. Fall back to lower-level thing that computes it
-        return getObjectSpecification(ob)
-
-    try:
-        # We might have gotten a descriptor from an instance of a
-        # class (like an ExtensionClass) that doesn't support
-        # descriptors.  We'll make sure we got one by trying to get
-        # the only attribute, which all specs have.
-        r.extends
-    except AttributeError:
-
-        # The object's class doesn't understand descriptors.
-        # Sigh. We need to get an object descriptor, but we have to be
-        # careful.  We want to use the instance's __provides__, if
-        # there is one, but only if it didn't come from the class.
-
-        try:
-            r = ob.__provides__
-        except AttributeError:
-            # No __provides__, so just fall back to implementedBy
-            return implementedBy(ob.__class__)
-
-        # We need to make sure we got the __provides__ from the
-        # instance. We'll do this by making sure we don't get the same
-        # thing from the class:
-
-        try:
-            cp = ob.__class__.__provides__
-        except AttributeError:
-            # The ob doesn't have a class or the class has no
-            # provides, assume we're done:
-            return r
-
-        if r is cp:
-            # Oops, we got the provides from the class. This means
-            # the object doesn't have it's own. We should use implementedBy
-            return implementedBy(ob.__class__)
-
-    return r
-
-
-@_use_c_impl
-class ObjectSpecificationDescriptor:
-    """Implement the ``__providedBy__`` attribute
-
-    The ``__providedBy__`` attribute computes the interfaces provided by an
-    object. If an object has an ``__provides__`` attribute, that is returned.
-    Otherwise, `implementedBy` the *cls* is returned.
-
-    .. versionchanged:: 5.4.0
-       Both the default (C) implementation and the Python implementation
-       now let exceptions raised by accessing ``__provides__`` propagate.
-       Previously, the C version ignored all exceptions.
-    .. versionchanged:: 5.4.0
-       The Python implementation now matches the C implementation and lets
-       a ``__provides__`` of ``None`` override what the class is declared to
-       implement.
-    """
-
-    def __get__(self, inst, cls):
-        """Get an object specification for an object
-        """
-        if inst is None:
-            return getObjectSpecification(cls)
-
-        try:
-            return inst.__provides__
-        except AttributeError:
-            return implementedBy(cls)
-
-
-##############################################################################
-
-def _normalizeargs(sequence, output=None):
-    """Normalize declaration arguments
-
-    Normalization arguments might contain Declarions, tuples, or single
-    interfaces.
-
-    Anything but individual interfaces or implements specs will be expanded.
-    """
-    if output is None:
-        output = []
-
-    cls = sequence.__class__
-    if InterfaceClass in cls.__mro__ or Implements in cls.__mro__:
-        output.append(sequence)
-    else:
-        for v in sequence:
-            _normalizeargs(v, output)
-
-    return output
-
-
-_empty = _ImmutableDeclaration()
-
-objectSpecificationDescriptor = ObjectSpecificationDescriptor()
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/document.py b/llmlab/lib/python3.12/site-packages/zope/interface/document.py
deleted file mode 100644
index 3725037..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/document.py
+++ /dev/null
@@ -1,133 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-""" Pretty-Print an Interface object as structured text (Yum)
-
-This module provides a function, asStructuredText, for rendering an
-interface as structured text.
-"""
-import zope.interface
-
-
-__all__ = [
-    'asReStructuredText',
-    'asStructuredText',
-]
-
-
-def asStructuredText(iface, munge=0, rst=False):
-    """ Output structured text format.  Note, this will whack any existing
-    'structured' format of the text.
-
-    If `rst=True`, then the output will quote all code as inline literals in
-    accordance with 'reStructuredText' markup principles.
-    """
-
-    if rst:
-        def inline_literal(s):
-            return f"``{s}``"
-    else:
-        def inline_literal(s):
-            return s
-
-    r = [inline_literal(iface.getName())]
-    outp = r.append
-    level = 1
-
-    if iface.getDoc():
-        outp(_justify_and_indent(_trim_doc_string(iface.getDoc()), level))
-
-    bases = [base
-             for base in iface.__bases__
-             if base is not zope.interface.Interface
-             ]
-    if bases:
-        outp(_justify_and_indent("This interface extends:", level, munge))
-        level += 1
-        for b in bases:
-            item = "o %s" % inline_literal(b.getName())
-            outp(_justify_and_indent(_trim_doc_string(item), level, munge))
-        level -= 1
-
-    namesAndDescriptions = sorted(iface.namesAndDescriptions())
-
-    outp(_justify_and_indent("Attributes:", level, munge))
-    level += 1
-    for name, desc in namesAndDescriptions:
-        if not hasattr(desc, 'getSignatureString'):   # ugh...
-            item = "{} -- {}".format(
-                inline_literal(desc.getName()),
-                desc.getDoc() or 'no documentation'
-            )
-            outp(_justify_and_indent(_trim_doc_string(item), level, munge))
-    level -= 1
-
-    outp(_justify_and_indent("Methods:", level, munge))
-    level += 1
-    for name, desc in namesAndDescriptions:
-        if hasattr(desc, 'getSignatureString'):   # ugh...
-            _call = f"{desc.getName()}{desc.getSignatureString()}"
-            item = "{} -- {}".format(
-                inline_literal(_call),
-                desc.getDoc() or 'no documentation'
-            )
-            outp(_justify_and_indent(_trim_doc_string(item), level, munge))
-
-    return "\n\n".join(r) + "\n\n"
-
-
-def asReStructuredText(iface, munge=0):
-    """ Output reStructuredText format.
-
-    Note, this will whack any existing 'structured' format of the text."""
-    return asStructuredText(iface, munge=munge, rst=True)
-
-
-def _trim_doc_string(text):
-    """ Trims a doc string to make it format
-    correctly with structured text. """
-
-    lines = text.replace('\r\n', '\n').split('\n')
-    nlines = [lines.pop(0)]
-    if lines:
-        min_indent = min([len(line) - len(line.lstrip())
-                          for line in lines])
-        for line in lines:
-            nlines.append(line[min_indent:])
-
-    return '\n'.join(nlines)
-
-
-def _justify_and_indent(text, level, munge=0, width=72):
-    """ indent and justify text, rejustify (munge) if specified """
-
-    indent = " " * level
-
-    if munge:
-        lines = []
-        line = indent
-        text = text.split()
-
-        for word in text:
-            line = ' '.join([line, word])
-            if len(line) > width:
-                lines.append(line)
-                line = indent
-        else:
-            lines.append(line)
-
-        return '\n'.join(lines)
-
-    else:
-        return indent + \
-            text.strip().replace("\r\n", "\n") .replace("\n", "\n" + indent)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/exceptions.py b/llmlab/lib/python3.12/site-packages/zope/interface/exceptions.py
deleted file mode 100644
index b86fb1e..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/exceptions.py
+++ /dev/null
@@ -1,278 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Interface-specific exceptions
-"""
-
-__all__ = [
-    # Invalid tree
-    'Invalid',
-    'DoesNotImplement',
-    'BrokenImplementation',
-    'BrokenMethodImplementation',
-    'MultipleInvalid',
-    # Other
-    'BadImplements',
-    'InvalidInterface',
-]
-
-
-class Invalid(Exception):
-    """A specification is violated
-    """
-
-
-class _TargetInvalid(Invalid):
-    # Internal use. Subclass this when you're describing
-    # a particular target object that's invalid according
-    # to a specific interface.
-    #
-    # For backwards compatibility, the *target* and *interface* are
-    # optional, and the signatures are inconsistent in their ordering.
-    #
-    # We deal with the inconsistency in ordering by defining the index
-    # of the two values in ``self.args``. *target* uses a marker object to
-    # distinguish "not given" from "given, but None", because the latter
-    # can be a value that gets passed to validation. For this reason, it must
-    # always be the last argument (we detect absence by the ``IndexError``).
-
-    _IX_INTERFACE = 0
-    _IX_TARGET = 1
-    # The exception to catch when indexing self.args indicating that
-    # an argument was not given. If all arguments are expected,
-    # a subclass should set this to ().
-    _NOT_GIVEN_CATCH = IndexError
-    _NOT_GIVEN = ''
-
-    def _get_arg_or_default(self, ix, default=None):
-        try:
-            return self.args[ix]  # pylint:disable=unsubscriptable-object
-        except self._NOT_GIVEN_CATCH:
-            return default
-
-    @property
-    def interface(self):
-        return self._get_arg_or_default(self._IX_INTERFACE)
-
-    @property
-    def target(self):
-        return self._get_arg_or_default(self._IX_TARGET, self._NOT_GIVEN)
-
-    ###
-    # str
-    #
-    # The ``__str__`` of self is implemented by concatenating (%s), in order,
-    # these properties (none of which should have leading or trailing
-    # whitespace):
-    #
-    # - self._str_subject
-    #   Begin the message, including a description of the target.
-    # - self._str_description
-    #   Provide a general description of the type of error, including
-    #   the interface name if possible and relevant.
-    # - self._str_conjunction
-    #   Join the description to the details. Defaults to ": ".
-    # - self._str_details
-    #   Provide details about how this particular instance of the error.
-    # - self._str_trailer
-    #   End the message. Usually just a period.
-    ###
-
-    @property
-    def _str_subject(self):
-        target = self.target
-        if target is self._NOT_GIVEN:
-            return "An object"
-        return f"The object {target!r}"
-
-    @property
-    def _str_description(self):
-        return "has failed to implement interface %s" % (
-            self.interface or ''
-        )
-
-    _str_conjunction = ": "
-    _str_details = ""
-    _str_trailer = '.'
-
-    def __str__(self):
-        return "{} {}{}{}{}".format(
-            self._str_subject,
-            self._str_description,
-            self._str_conjunction,
-            self._str_details,
-            self._str_trailer
-        )
-
-
-class DoesNotImplement(_TargetInvalid):
-    """
-    DoesNotImplement(interface[, target])
-
-    The *target* (optional) does not implement the *interface*.
-
-    .. versionchanged:: 5.0.0
-       Add the *target* argument and attribute, and change the resulting
-       string value of this object accordingly.
-    """
-
-    _str_details = "Does not declaratively implement the interface"
-
-
-class BrokenImplementation(_TargetInvalid):
-    """
-    BrokenImplementation(interface, name[, target])
-
-    The *target* (optional) is missing the attribute *name*.
-
-    .. versionchanged:: 5.0.0
-       Add the *target* argument and attribute, and change the resulting
-       string value of this object accordingly.
-
-       The *name* can either be a simple string or a ``Attribute`` object.
-    """
-
-    _IX_NAME = _TargetInvalid._IX_INTERFACE + 1
-    _IX_TARGET = _IX_NAME + 1
-
-    @property
-    def name(self):
-        return self.args[1]  # pylint:disable=unsubscriptable-object
-
-    @property
-    def _str_details(self):
-        return "The %s attribute was not provided" % (
-            repr(self.name) if isinstance(self.name, str) else self.name
-        )
-
-
-class BrokenMethodImplementation(_TargetInvalid):
-    """
-    BrokenMethodImplementation(
-        method, message[, implementation, interface, target]
-    )
-
-    The *target* (optional) has a *method* in *implementation* that violates
-    its contract in a way described by *mess*.
-
-    .. versionchanged:: 5.0.0
-       Add the *interface* and *target* argument and attribute,
-       and change the resulting string value of this object accordingly.
-
-       The *method* can either be a simple string or a ``Method`` object.
-
-    .. versionchanged:: 5.0.0
-       If *implementation* is given, then the *message* will have the
-       string "implementation" replaced with an short but informative
-       representation of *implementation*.
-
-    """
-
-    _IX_IMPL = 2
-    _IX_INTERFACE = _IX_IMPL + 1
-    _IX_TARGET = _IX_INTERFACE + 1
-
-    @property
-    def method(self):
-        return self.args[0]  # pylint:disable=unsubscriptable-object
-
-    @property
-    def mess(self):
-        return self.args[1]  # pylint:disable=unsubscriptable-object
-
-    @staticmethod
-    def __implementation_str(impl):
-        # It could be a callable or some arbitrary object, we don't
-        # know yet.
-        import inspect  # Inspect is a heavy-weight dependency, lots of imports
-        try:
-            sig = inspect.signature
-            formatsig = str
-        except AttributeError:
-            sig = inspect.getargspec
-            formatsig = inspect.formatargspec
-
-        try:
-            sig = sig(impl)
-        except (ValueError, TypeError):
-            # Unable to introspect. Darn.
-            # This could be a non-callable, or a particular builtin,
-            # or a bound method that doesn't even accept 'self', e.g.,
-            # ``Class.method = lambda: None; Class().method``
-            return repr(impl)
-
-        try:
-            name = impl.__qualname__
-        except AttributeError:
-            name = impl.__name__
-
-        return name + formatsig(sig)
-
-    @property
-    def _str_details(self):
-        impl = self._get_arg_or_default(self._IX_IMPL, self._NOT_GIVEN)
-        message = self.mess
-        if impl is not self._NOT_GIVEN and 'implementation' in message:
-            message = message.replace("implementation", '%r')
-            message = message % (self.__implementation_str(impl),)
-
-        return 'The contract of {} is violated because {}'.format(
-            repr(self.method) if isinstance(self.method, str) else self.method,
-            message,
-        )
-
-
-class MultipleInvalid(_TargetInvalid):
-    """
-    The *target* has failed to implement the *interface* in
-    multiple ways.
-
-    The failures are described by *exceptions*, a collection of
-    other `Invalid` instances.
-
-    .. versionadded:: 5.0
-    """
-
-    _NOT_GIVEN_CATCH = ()
-
-    def __init__(self, interface, target, exceptions):
-        super().__init__(interface, target, tuple(exceptions))
-
-    @property
-    def exceptions(self):
-        return self.args[2]  # pylint:disable=unsubscriptable-object
-
-    @property
-    def _str_details(self):
-        # It would be nice to use tabs here, but that
-        # is hard to represent in doctests.
-        return '\n    ' + '\n    '.join(
-            x._str_details.strip() if isinstance(x, _TargetInvalid) else str(x)
-            for x in self.exceptions
-        )
-
-    _str_conjunction = ':'  # no trailing space, messes up doctests
-    _str_trailer = ''
-
-
-class InvalidInterface(Exception):
-    """The interface has invalid contents
-    """
-
-
-class BadImplements(TypeError):
-    """An implementation assertion is invalid
-
-    because it doesn't contain an interface or a sequence of valid
-    implementation assertions.
-    """
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/interface.py b/llmlab/lib/python3.12/site-packages/zope/interface/interface.py
deleted file mode 100644
index ad8a7de..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/interface.py
+++ /dev/null
@@ -1,1185 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Interface object implementation
-"""
-# pylint:disable=protected-access
-import sys
-import weakref
-from types import FunctionType
-from types import MethodType
-from typing import Union
-
-from zope.interface import ro
-from zope.interface._compat import _use_c_impl
-from zope.interface.exceptions import Invalid
-from zope.interface.ro import ro as calculate_ro
-
-
-__all__ = [
-    # Most of the public API from this module is directly exported
-    # from zope.interface. The only remaining public API intended to
-    # be imported from here should be those few things documented as
-    # such.
-    'InterfaceClass',
-    'Specification',
-    'adapter_hooks',
-]
-
-CO_VARARGS = 4
-CO_VARKEYWORDS = 8
-# Put in the attrs dict of an interface by ``taggedValue`` and ``invariants``
-TAGGED_DATA = '__interface_tagged_values__'
-# Put in the attrs dict of an interface by ``interfacemethod``
-INTERFACE_METHODS = '__interface_methods__'
-
-_decorator_non_return = object()
-_marker = object()
-
-
-def invariant(call):
-    f_locals = sys._getframe(1).f_locals
-    tags = f_locals.setdefault(TAGGED_DATA, {})
-    invariants = tags.setdefault('invariants', [])
-    invariants.append(call)
-    return _decorator_non_return
-
-
-def taggedValue(key, value):
-    """Attaches a tagged value to an interface at definition time."""
-    f_locals = sys._getframe(1).f_locals
-    tagged_values = f_locals.setdefault(TAGGED_DATA, {})
-    tagged_values[key] = value
-    return _decorator_non_return
-
-
-class Element:
-    """
-    Default implementation of `zope.interface.interfaces.IElement`.
-    """
-
-    # We can't say this yet because we don't have enough
-    # infrastructure in place.
-    #
-    # implements(IElement)
-
-    def __init__(
-        self, __name__, __doc__='',
-    ):  # pylint:disable=redefined-builtin
-        if not __doc__ and __name__.find(' ') >= 0:
-            __doc__ = __name__
-            __name__ = None
-
-        self.__name__ = __name__
-        self.__doc__ = __doc__
-        # Tagged values are rare, especially on methods or attributes.
-        # Deferring the allocation can save substantial memory.
-        self.__tagged_values = None
-
-    def getName(self):
-        """ Returns the name of the object. """
-        return self.__name__
-
-    def getDoc(self):
-        """ Returns the documentation for the object. """
-        return self.__doc__
-
-    ###
-    # Tagged values.
-    #
-    # Direct tagged values are set only in this instance. Others
-    # may be inherited (for those subclasses that have that concept).
-    ###
-
-    def getTaggedValue(self, tag):
-        """ Returns the value associated with 'tag'. """
-        if not self.__tagged_values:
-            raise KeyError(tag)
-        return self.__tagged_values[tag]
-
-    def queryTaggedValue(self, tag, default=None):
-        """ Returns the value associated with 'tag'. """
-        return self.__tagged_values.get(
-            tag, default,
-        ) if self.__tagged_values else default
-
-    def getTaggedValueTags(self):
-        """ Returns a collection of all tags. """
-        return self.__tagged_values.keys() if self.__tagged_values else ()
-
-    def setTaggedValue(self, tag, value):
-        """ Associates 'value' with 'key'. """
-        if self.__tagged_values is None:
-            self.__tagged_values = {}
-        self.__tagged_values[tag] = value
-
-    queryDirectTaggedValue = queryTaggedValue
-    getDirectTaggedValue = getTaggedValue
-    getDirectTaggedValueTags = getTaggedValueTags
-
-
-SpecificationBasePy = object  # filled by _use_c_impl.
-
-
-@_use_c_impl
-class SpecificationBase:
-    # This object is the base of the inheritance hierarchy for ClassProvides:
-    #
-    # ClassProvides < ClassProvidesBase, Declaration
-    # Declaration < Specification < SpecificationBase
-    # ClassProvidesBase < SpecificationBase
-    #
-    # In order to have compatible instance layouts, we need to declare
-    # the storage used by Specification and Declaration here (and
-    # those classes must have ``__slots__ = ()``); fortunately this is
-    # not a waste of space because those are the only two inheritance
-    # trees. These all translate into tp_members in C.
-    __slots__ = (
-        # Things used here.
-        '_implied',
-        # Things used in Specification.
-        '_dependents',
-        '_bases',
-        '_v_attrs',
-        '__iro__',
-        '__sro__',
-        '__weakref__',
-    )
-
-    def providedBy(self, ob):
-        """Is the interface implemented by an object
-        """
-        spec = providedBy(ob)
-        return self in spec._implied
-
-    def implementedBy(self, cls):
-        """Test whether the specification is implemented by a class or factory.
-
-        Raise TypeError if argument is neither a class nor a callable.
-        """
-        spec = implementedBy(cls)
-        return self in spec._implied
-
-    def isOrExtends(self, interface):
-        """Is the interface the same as or extend the given interface
-        """
-        return interface in self._implied  # pylint:disable=no-member
-
-    __call__ = isOrExtends
-
-
-class NameAndModuleComparisonMixin:
-    # Internal use. Implement the basic sorting operators (but not (in)equality
-    # or hashing). Subclasses must provide ``__name__`` and ``__module__``
-    # attributes. Subclasses will be mutually comparable; but because equality
-    # and hashing semantics are missing from this class, take care in how
-    # you define those two attributes: If you stick with the default equality
-    # and hashing (identity based) you should make sure that all possible
-    # ``__name__`` and ``__module__`` pairs are unique ACROSS ALL SUBCLASSES.
-    # (Actually, pretty much the same thing goes if you define equality and
-    # hashing to be based on those two attributes: they must still be
-    # consistent ACROSS ALL SUBCLASSES.)
-
-    # pylint:disable=assigning-non-slot
-    __slots__ = ()
-
-    def _compare(self, other):
-        """
-        Compare *self* to *other* based on ``__name__`` and ``__module__``.
-
-        Return 0 if they are equal, return 1 if *self* is
-        greater than *other*, and return -1 if *self* is less than
-        *other*.
-
-        If *other* does not have ``__name__`` or ``__module__``, then
-        return ``NotImplemented``.
-
-        .. caution::
-           This allows comparison to things well outside the type hierarchy,
-           perhaps not symmetrically.
-
-           For example, ``class Foo(object)`` and ``class Foo(Interface)``
-           in the same file would compare equal, depending on the order of
-           operands. Writing code like this by hand would be unusual, but it
-           could happen with dynamic creation of types and interfaces.
-
-        None is treated as a pseudo interface that implies the loosest
-        contact possible, no contract. For that reason, all interfaces
-        sort before None.
-        """
-        if other is self:
-            return 0
-
-        if other is None:
-            return -1
-
-        n1 = (self.__name__, self.__module__)
-        try:
-            n2 = (other.__name__, other.__module__)
-        except AttributeError:
-            return NotImplemented
-
-        # This spelling works under Python3, which doesn't have cmp().
-        return (n1 > n2) - (n1 < n2)
-
-    def __lt__(self, other):
-        c = self._compare(other)
-        if c is NotImplemented:
-            return c
-        return c < 0
-
-    def __le__(self, other):
-        c = self._compare(other)
-        if c is NotImplemented:
-            return c
-        return c <= 0
-
-    def __gt__(self, other):
-        c = self._compare(other)
-        if c is NotImplemented:
-            return c
-        return c > 0
-
-    def __ge__(self, other):
-        c = self._compare(other)
-        if c is NotImplemented:
-            return c
-        return c >= 0
-
-
-@_use_c_impl
-class InterfaceBase(NameAndModuleComparisonMixin, SpecificationBasePy):
-    """Base class that wants to be replaced with a C base :)
-    """
-
-    __slots__ = (
-        '__name__',
-        '__ibmodule__',
-        '_v_cached_hash',
-    )
-
-    def __init__(self, name=None, module=None):
-        self.__name__ = name
-        self.__ibmodule__ = module
-
-    def _call_conform(self, conform):
-        raise NotImplementedError
-
-    @property
-    def __module_property__(self):
-        # This is for _InterfaceMetaClass
-        return self.__ibmodule__
-
-    def __call__(self, obj, alternate=_marker):
-        """Adapt an object to the interface
-        """
-        try:
-            conform = obj.__conform__
-        except AttributeError:
-            conform = None
-
-        if conform is not None:
-            adapter = self._call_conform(conform)
-            if adapter is not None:
-                return adapter
-
-        adapter = self.__adapt__(obj)
-
-        if adapter is not None:
-            return adapter
-        if alternate is not _marker:
-            return alternate
-        raise TypeError("Could not adapt", obj, self)
-
-    def __adapt__(self, obj):
-        """Adapt an object to the receiver
-        """
-        if self.providedBy(obj):
-            return obj
-
-        for hook in adapter_hooks:
-            adapter = hook(self, obj)
-            if adapter is not None:
-                return adapter
-
-        return None
-
-    def __hash__(self):
-        # pylint:disable=assigning-non-slot,attribute-defined-outside-init
-        try:
-            return self._v_cached_hash
-        except AttributeError:
-            self._v_cached_hash = hash((self.__name__, self.__module__))
-        return self._v_cached_hash
-
-    def __eq__(self, other):
-        c = self._compare(other)
-        if c is NotImplemented:
-            return c
-        return c == 0
-
-    def __ne__(self, other):
-        if other is self:
-            return False
-
-        c = self._compare(other)
-        if c is NotImplemented:
-            return c
-        return c != 0
-
-
-adapter_hooks = _use_c_impl([], 'adapter_hooks')
-
-
-class Specification(SpecificationBase):
-    """Specifications
-
-    An interface specification is used to track interface declarations
-    and component registrations.
-
-    This class is a base class for both interfaces themselves and for
-    interface specifications (declarations).
-
-    Specifications are mutable.  If you reassign their bases, their
-    relations with other specifications are adjusted accordingly.
-    """
-    __slots__ = ()
-
-    # The root of all Specifications. This will be assigned `Interface`,
-    # once it is defined.
-    _ROOT = None
-
-    # Copy some base class methods for speed
-    isOrExtends = SpecificationBase.isOrExtends
-    providedBy = SpecificationBase.providedBy
-
-    def __init__(self, bases=()):
-        # There are many leaf interfaces with no dependents,
-        # and a few with very many. It's a heavily left-skewed
-        # distribution. In a survey of Plone and Zope related packages
-        # that loaded 2245 InterfaceClass objects and 2235 ClassProvides
-        # instances, there were a total of 7000 Specification objects created.
-        # 4700 had 0 dependents, 1400 had 1, 382 had 2 and so on. Only one
-        # for  had 1664. So there's savings to be had deferring
-        # the creation of dependents.
-        self._dependents = None  # type: weakref.WeakKeyDictionary
-        self._bases = ()
-        self._implied = {}
-        self._v_attrs = None
-        self.__iro__ = ()
-        self.__sro__ = ()
-
-        self.__bases__ = tuple(bases)
-
-    @property
-    def dependents(self):
-        if self._dependents is None:
-            self._dependents = weakref.WeakKeyDictionary()
-        return self._dependents
-
-    def subscribe(self, dependent):
-        self._dependents[dependent] = self.dependents.get(dependent, 0) + 1
-
-    def unsubscribe(self, dependent):
-        try:
-            n = self._dependents[dependent]
-        except TypeError:
-            raise KeyError(dependent)
-        n -= 1
-        if not n:
-            del self.dependents[dependent]
-        else:
-            assert n > 0
-            self.dependents[dependent] = n
-
-    def __setBases(self, bases):
-        # Remove ourselves as a dependent of our old bases
-        for b in self.__bases__:
-            b.unsubscribe(self)
-
-        # Register ourselves as a dependent of our new bases
-        self._bases = bases
-        for b in bases:
-            b.subscribe(self)
-
-        self.changed(self)
-
-    __bases__ = property(
-        lambda self: self._bases, __setBases,
-    )
-
-    # This method exists for tests to override the way we call
-    # ro.calculate_ro(), usually by adding extra kwargs. We don't
-    # want to have a mutable dictionary as a class member that we pass
-    # ourself because mutability is bad, and passing **kw is slower than
-    # calling the bound function.
-    _do_calculate_ro = calculate_ro
-
-    def _calculate_sro(self):
-        """Compute resolution order for this object using its ``__bases__``.
-
-        Ensures that ``Interface`` is always the last (lowest priority)
-        element.
-        """
-        # We'd like to make Interface the lowest priority as a property of the
-        # resolution order algorithm. That almost works out naturally, but it
-        # fails when class inheritance has some bases that DO implement an
-        # interface, and some that DO NOT. In such a mixed scenario, you wind
-        # up with a set of bases to consider that look like this: [[...,
-        # Interface], [..., object], ...]. Depending on the order of
-        # inheritance, Interface can wind up before or after object, and that
-        # can happen at any point in the tree, meaning Interface can wind up
-        # somewhere in the middle of the order. Since Interface is treated as
-        # something that everything winds up implementing anyway (a catch-all
-        # for things like adapters), having it high up the order is bad. It's
-        # also bad to have it at the end, just before some concrete class:
-        # concrete classes should be HIGHER priority than interfaces (because
-        # there's only one class, but many implementations).
-        #
-        # One technically nice way to fix this would be to have
-        # ``implementedBy(object).__bases__ = (Interface,)``
-        #
-        # But: (1) That fails for old-style classes and (2) that causes
-        # everything to appear to *explicitly* implement Interface, when up
-        # to this point it's been an implicit virtual sort of relationship.
-        #
-        # So we force the issue by mutating the resolution order.
-
-        # Note that we let C3 use pre-computed __sro__ for our bases.
-        # This requires that by the time this method is invoked, our bases
-        # have settled their SROs. Thus, ``changed()`` must first
-        # update itself before telling its descendents of changes.
-        sro = self._do_calculate_ro(base_mros={
-            b: b.__sro__
-            for b in self.__bases__
-        })
-        root = self._ROOT
-        if root is not None and sro and sro[-1] is not root:
-            # In one dataset of 1823 Interface objects, 1117 ClassProvides
-            # objects, sro[-1] was root 4496 times, and only not root 118
-            # times. So it's probably worth checking.
-
-            # Once we don't have to deal with old-style classes,
-            # we can add a check and only do this if base_count > 1,
-            # if we tweak the bootstrapping for ````
-            sro = [
-                x
-                for x in sro
-                if x is not root
-            ]
-            sro.append(root)
-
-        return sro
-
-    def changed(self, originally_changed):
-        """
-        We, or something we depend on, have changed.
-
-        By the time this is called, the things we depend on,
-        such as our bases, should themselves be stable.
-        """
-        self._v_attrs = None
-
-        implied = self._implied
-        implied.clear()
-
-        ancestors = self._calculate_sro()
-        self.__sro__ = tuple(ancestors)
-        self.__iro__ = tuple([ancestor for ancestor in ancestors
-                              if isinstance(ancestor, InterfaceClass)
-                              ])
-
-        for ancestor in ancestors:
-            # We directly imply our ancestors:
-            implied[ancestor] = ()
-
-        # Now, advise our dependents of change
-        # (being careful not to create the WeakKeyDictionary if not needed):
-        for dependent in tuple(
-            self._dependents.keys() if self._dependents else ()
-        ):
-            dependent.changed(originally_changed)
-
-        # Just in case something called get() at some point
-        # during that process and we have a cycle of some sort
-        # make sure we didn't cache incomplete results.
-        self._v_attrs = None
-
-    def interfaces(self):
-        """Return an iterator for the interfaces in the specification.
-        """
-        seen = {}
-        for base in self.__bases__:
-            for interface in base.interfaces():
-                if interface not in seen:
-                    seen[interface] = 1
-                    yield interface
-
-    def extends(self, interface, strict=True):
-        """Does the specification extend the given interface?
-
-        Test whether an interface in the specification extends the
-        given interface
-        """
-        return (
-            (interface in self._implied) and (
-                (not strict) or (self != interface)
-            )
-        )
-
-    def weakref(self, callback=None):
-        return weakref.ref(self, callback)
-
-    def get(self, name, default=None):
-        """Query for an attribute description
-        """
-        attrs = self._v_attrs
-        if attrs is None:
-            attrs = self._v_attrs = {}
-        attr = attrs.get(name)
-        if attr is None:
-            for iface in self.__iro__:
-                attr = iface.direct(name)
-                if attr is not None:
-                    attrs[name] = attr
-                    break
-
-        return default if attr is None else attr
-
-
-class _InterfaceMetaClass(type):
-    # Handling ``__module__`` on ``InterfaceClass`` is tricky. We need to be
-    # able to read it on a type and get the expected string. We also need to
-    # be able to set it on an instance and get the value we set. So far so
-    # good. But what gets tricky is that we'd like to store the value in the C
-    # structure (``InterfaceBase.__ibmodule__``) for direct access during
-    # equality, sorting, and hashing. "No problem, you think, I'll just use a
-    # property" (well, the C equivalents, ``PyMemberDef`` or ``PyGetSetDef``).
-    #
-    # Except there is a problem. When a subclass is created, the
-    # metaclass (``type``) always automatically puts the expected
-    # string in the class's dictionary under ``__module__``, thus
-    # overriding the property inherited from the superclass. Writing
-    # ``Subclass.__module__`` still works, but
-    # ``Subclass().__module__`` fails.
-    #
-    # There are multiple ways to work around this:
-    #
-    # (1) Define ``InterfaceBase.__getattribute__`` to watch for
-    # ``__module__`` and return the C storage.
-    #
-    # This works, but slows down *all* attribute access (except,
-    # ironically, to ``__module__``) by about 25% (40ns becomes 50ns)
-    # (when implemented in C). Since that includes methods like
-    # ``providedBy``, that's probably not acceptable.
-    #
-    # All the other methods involve modifying subclasses. This can be done
-    # either on the fly in some cases, as instances are constructed, or by
-    # using a metaclass. These next few can be done on the fly.
-    #
-    # (2) Make ``__module__`` a descriptor in each subclass dictionary.  It
-    # can't be a straight up ``@property`` descriptor, though, because
-    # accessing it on the class returns a ``property`` object, not the desired
-    # string.
-    #
-    # (3) Implement a data descriptor (``__get__`` and ``__set__``)
-    # that is both a subclass of string, and also does the redirect of
-    # ``__module__`` to ``__ibmodule__`` and does the correct thing
-    # with the ``instance`` argument to ``__get__`` is None (returns
-    # the class's value.) (Why must it be a subclass of string? Because
-    # when it' s in the class's dict, it's defined on an *instance* of the
-    # metaclass; descriptors in an instance's dict aren't honored --- their
-    # ``__get__`` is never invoked --- so it must also *be* the value we want
-    # returned.)
-    #
-    # This works, preserves the ability to read and write
-    # ``__module__``, and eliminates any penalty accessing other
-    # attributes. But it slows down accessing ``__module__`` of
-    # instances by 200% (40ns to 124ns), requires editing class dicts on the
-    # fly (in InterfaceClass.__init__), thus slightly slowing down all
-    # interface creation, and is ugly.
-    #
-    # (4) As in the last step, but make it a non-data descriptor (no
-    # ``__set__``).
-    #
-    # If you then *also* store a copy of ``__ibmodule__`` in
-    # ``__module__`` in the instance's dict, reading works for both
-    # class and instance and is full speed for instances. But the cost
-    # is storage space, and you can't write to it anymore, not without
-    # things getting out of sync.
-    #
-    # (Actually, ``__module__`` was never meant to be writable. Doing
-    # so would break BTrees and normal dictionaries, as well as the
-    # repr, maybe more.)
-    #
-    # That leaves us with a metaclass. (Recall that a class is an
-    # instance of its metaclass, so properties/descriptors defined in
-    # the metaclass are used when accessing attributes on the
-    # instance/class. We'll use that to define ``__module__``.) Here
-    # we can have our cake and eat it too: no extra storage, and
-    # C-speed access to the underlying storage. The only substantial
-    # cost is that metaclasses tend to make people's heads hurt. (But
-    # still less than the descriptor-is-string, hopefully.)
-
-    __slots__ = ()
-
-    def __new__(cls, name, bases, attrs):
-        # Figure out what module defined the interface.
-        # This is copied from ``InterfaceClass.__init__``;
-        # reviewers aren't sure how AttributeError or KeyError
-        # could be raised.
-        __module__ = sys._getframe(1).f_globals['__name__']
-        # Get the C optimized __module__ accessor and give it
-        # to the new class.
-        moduledescr = InterfaceBase.__dict__['__module__']
-        if isinstance(moduledescr, str):
-            # We're working with the Python implementation,
-            # not the C version
-            moduledescr = InterfaceBase.__dict__['__module_property__']
-        attrs['__module__'] = moduledescr
-        kind = type.__new__(cls, name, bases, attrs)
-        kind.__module = __module__
-        return kind
-
-    @property
-    def __module__(cls):
-        return cls.__module
-
-    def __repr__(cls):
-        return "".format(
-            cls.__module,
-            cls.__name__,
-        )
-
-
-_InterfaceClassBase = _InterfaceMetaClass(
-    'InterfaceClass',
-    # From least specific to most specific.
-    (InterfaceBase, Specification, Element),
-    {'__slots__': ()}
-)
-
-
-def interfacemethod(func):
-    """
-    Convert a method specification to an actual method of the interface.
-
-    This is a decorator that functions like `staticmethod` et al.
-
-    The primary use of this decorator is to allow interface definitions to
-    define the ``__adapt__`` method, but other interface methods can be
-    overridden this way too.
-
-    .. seealso::
-        `zope.interface.interfaces.IInterfaceDeclaration.interfacemethod`
-    """
-    f_locals = sys._getframe(1).f_locals
-    methods = f_locals.setdefault(INTERFACE_METHODS, {})
-    methods[func.__name__] = func
-    return _decorator_non_return
-
-
-class InterfaceClass(_InterfaceClassBase):
-    """
-    Prototype (scarecrow) Interfaces Implementation.
-
-    Note that it is not possible to change the ``__name__`` or ``__module__``
-    after an instance of this object has been constructed.
-    """
-
-    # We can't say this yet because we don't have enough
-    # infrastructure in place.
-    #
-    # implements(IInterface)
-
-    def __new__(
-        cls,
-        name=None,
-        bases=(),
-        attrs=None,
-        __doc__=None,  # pylint:disable=redefined-builtin
-        __module__=None,
-    ):
-        assert isinstance(bases, tuple)
-        attrs = attrs or {}
-        needs_custom_class = attrs.pop(INTERFACE_METHODS, None)
-        if needs_custom_class:
-            needs_custom_class.update(
-                {'__classcell__': attrs.pop('__classcell__')}
-                if '__classcell__' in attrs
-                else {}
-            )
-            if '__adapt__' in needs_custom_class:
-                # We need to tell the C code to call this.
-                needs_custom_class['_CALL_CUSTOM_ADAPT'] = 1
-
-            if issubclass(cls, _InterfaceClassWithCustomMethods):
-                cls_bases = (cls,)
-            elif cls is InterfaceClass:
-                cls_bases = (_InterfaceClassWithCustomMethods,)
-            else:
-                cls_bases = (cls, _InterfaceClassWithCustomMethods)
-
-            cls = type(cls)(  # pylint:disable=self-cls-assignment
-                name + "",
-                cls_bases,
-                needs_custom_class
-            )
-
-        return _InterfaceClassBase.__new__(cls)
-
-    def __init__(
-        self,
-        name,
-        bases=(),
-        attrs=None,
-        __doc__=None,  # pylint:disable=redefined-builtin
-        __module__=None,
-    ):
-        # We don't call our metaclass parent directly
-        # pylint:disable=non-parent-init-called
-        # pylint:disable=super-init-not-called
-        if not all(isinstance(base, InterfaceClass) for base in bases):
-            raise TypeError('Expected base interfaces')
-
-        if attrs is None:
-            attrs = {}
-
-        if __module__ is None:
-            __module__ = attrs.get('__module__')
-            if isinstance(__module__, str):
-                del attrs['__module__']
-            else:
-                try:
-                    # Figure out what module defined the interface.
-                    # This is how cPython figures out the module of
-                    # a class, but of course it does it in C. :-/
-                    __module__ = sys._getframe(1).f_globals['__name__']
-                except (AttributeError, KeyError):  # pragma: no cover
-                    pass
-
-        InterfaceBase.__init__(self, name, __module__)
-        # These asserts assisted debugging the metaclass
-        # assert '__module__' not in self.__dict__
-        # assert self.__ibmodule__ is self.__module__ is __module__
-
-        d = attrs.get('__doc__')
-        if d is not None:
-            if not isinstance(d, Attribute):
-                if __doc__ is None:
-                    __doc__ = d
-                del attrs['__doc__']
-
-        if __doc__ is None:
-            __doc__ = ''
-
-        Element.__init__(self, name, __doc__)
-
-        tagged_data = attrs.pop(TAGGED_DATA, None)
-        if tagged_data is not None:
-            for key, val in tagged_data.items():
-                self.setTaggedValue(key, val)
-
-        Specification.__init__(self, bases)
-        self.__attrs = self.__compute_attrs(attrs)
-
-        self.__identifier__ = f"{__module__}.{name}"
-
-    def __compute_attrs(self, attrs):
-        # Make sure that all recorded attributes (and methods) are of type
-        # `Attribute` and `Method`
-        def update_value(aname, aval):
-            if isinstance(aval, Attribute):
-                aval.interface = self
-                if not aval.__name__:
-                    aval.__name__ = aname
-            elif isinstance(aval, FunctionType):
-                aval = fromFunction(aval, self, name=aname)
-            else:
-                raise InvalidInterface("Concrete attribute, " + aname)
-            return aval
-
-        return {
-            aname: update_value(aname, aval)
-            for aname, aval in attrs.items()
-            if aname not in (
-                # __locals__: Python 3 sometimes adds this.
-                '__locals__',
-                # __qualname__: PEP 3155 (Python 3.3+)
-                '__qualname__',
-                # __annotations__: PEP 3107 (Python 3.0+)
-                '__annotations__',
-                # __static_attributes__: Python 3.13a6+
-                # https://github.com/python/cpython/pull/115913
-                '__static_attributes__',
-                # __firstlineno__: Python 3.13b1+
-                # https://github.com/python/cpython/pull/118475
-                '__firstlineno__',
-                # __classdictcell__: Python 3.14
-                '__classdictcell__',
-            ) and
-            aval is not _decorator_non_return  # noqa W503
-        }
-
-    def interfaces(self):
-        """Return an iterator for the interfaces in the specification.
-        """
-        yield self
-
-    def getBases(self):
-        return self.__bases__
-
-    def isEqualOrExtendedBy(self, other):
-        """Same interface or extends?"""
-        return self == other or other.extends(self)
-
-    def names(self, all=False):  # pylint:disable=redefined-builtin
-        """Return the attribute names defined by the interface."""
-        if not all:
-            return self.__attrs.keys()
-
-        r = self.__attrs.copy()
-
-        for base in self.__bases__:
-            r.update(dict.fromkeys(base.names(all)))
-
-        return r.keys()
-
-    def __iter__(self):
-        return iter(self.names(all=True))
-
-    def namesAndDescriptions(
-        self, all=False  # pylint:disable=redefined-builtin
-    ):
-        """Return attribute names and descriptions defined by interface."""
-        if not all:
-            return self.__attrs.items()
-
-        r = {}
-        for base in self.__bases__[::-1]:
-            r.update(dict(base.namesAndDescriptions(all)))
-
-        r.update(self.__attrs)
-
-        return r.items()
-
-    def getDescriptionFor(self, name):
-        """Return the attribute description for the given name."""
-        r = self.get(name)
-        if r is not None:
-            return r
-
-        raise KeyError(name)
-
-    __getitem__ = getDescriptionFor
-
-    def __contains__(self, name):
-        return self.get(name) is not None
-
-    def direct(self, name):
-        return self.__attrs.get(name)
-
-    def queryDescriptionFor(self, name, default=None):
-        return self.get(name, default)
-
-    def validateInvariants(self, obj, errors=None):
-        """validate object to defined invariants."""
-
-        for iface in self.__iro__:
-            for invariant in iface.queryDirectTaggedValue('invariants', ()):
-                try:
-                    invariant(obj)
-                except Invalid as error:
-                    if errors is not None:
-                        errors.append(error)
-                    else:
-                        raise
-
-        if errors:
-            raise Invalid(errors)
-
-    def queryTaggedValue(self, tag, default=None):
-        """
-        Queries for the value associated with *tag*, returning it from the
-        nearest interface in the ``__iro__``.
-
-        If not found, returns *default*.
-        """
-        for iface in self.__iro__:
-            value = iface.queryDirectTaggedValue(tag, _marker)
-            if value is not _marker:
-                return value
-        return default
-
-    def getTaggedValue(self, tag):
-        """ Returns the value associated with 'tag'. """
-        value = self.queryTaggedValue(tag, default=_marker)
-        if value is _marker:
-            raise KeyError(tag)
-        return value
-
-    def getTaggedValueTags(self):
-        """ Returns a list of all tags. """
-        keys = set()
-        for base in self.__iro__:
-            keys.update(base.getDirectTaggedValueTags())
-        return keys
-
-    def __repr__(self):
-        try:
-            return self._v_repr
-        except AttributeError:
-            name = str(self)
-            r = f"<{self.__class__.__name__} {name}>"
-            self._v_repr = r  # pylint:disable=attribute-defined-outside-init
-            return r
-
-    def __str__(self):
-        name = self.__name__
-        m = self.__ibmodule__
-        if m:
-            name = f'{m}.{name}'
-        return name
-
-    def _call_conform(self, conform):
-        try:
-            return conform(self)
-        except TypeError:  # pragma: no cover
-            # We got a TypeError. It might be an error raised by
-            # the __conform__ implementation, or *we* may have
-            # made the TypeError by calling an unbound method
-            # (object is a class).  In the later case, we behave
-            # as though there is no __conform__ method. We can
-            # detect this case by checking whether there is more
-            # than one traceback object in the traceback chain:
-            if sys.exc_info()[2].tb_next is not None:
-                # There is more than one entry in the chain, so
-                # reraise the error:
-                raise
-            # This clever trick is from Phillip Eby
-
-        return None  # pragma: no cover
-
-    def __reduce__(self):
-        return self.__name__
-
-    def __or__(self, other):
-        """Allow type hinting syntax: Interface | None."""
-        return Union[self, other]
-
-    def __ror__(self, other):
-        """Allow type hinting syntax: None | Interface."""
-        return Union[other, self]
-
-
-Interface = InterfaceClass("Interface", __module__='zope.interface')
-# Interface is the only member of its own SRO.
-Interface._calculate_sro = lambda: (Interface,)
-Interface.changed(Interface)
-assert Interface.__sro__ == (Interface,)
-Specification._ROOT = Interface
-ro._ROOT = Interface
-
-
-class _InterfaceClassWithCustomMethods(InterfaceClass):
-    """
-    Marker class for interfaces with custom methods that override
-    InterfaceClass methods.
-    """
-
-
-class Attribute(Element):
-    """Attribute descriptions
-    """
-
-    # We can't say this yet because we don't have enough
-    # infrastructure in place.
-    #
-    # implements(IAttribute)
-
-    interface = None
-
-    def _get_str_info(self):
-        """Return extra data to put at the end of __str__."""
-        return ""
-
-    def __str__(self):
-        of = ''
-        if self.interface is not None:
-            of = (
-                self.interface.__module__ +
-                '.' +
-                self.interface.__name__ +
-                '.'
-            )
-        # self.__name__ may be None during construction (e.g., debugging)
-        return of + (self.__name__ or '') + self._get_str_info()
-
-    def __repr__(self):
-        return "<{}.{} object at 0x{:x} {}>".format(
-            type(self).__module__,
-            type(self).__name__,
-            id(self),
-            self
-        )
-
-
-class Method(Attribute):
-    """Method interfaces
-
-    The idea here is that you have objects that describe methods.
-    This provides an opportunity for rich meta-data.
-    """
-
-    # We can't say this yet because we don't have enough
-    # infrastructure in place.
-    #
-    # implements(IMethod)
-
-    positional = required = ()
-    _optional = varargs = kwargs = None
-
-    def _get_optional(self):
-        if self._optional is None:
-            return {}
-        return self._optional
-
-    def _set_optional(self, opt):
-        self._optional = opt
-
-    def _del_optional(self):
-        self._optional = None
-
-    optional = property(_get_optional, _set_optional, _del_optional)
-
-    def __call__(self, *args, **kw):
-        raise BrokenImplementation(self.interface, self.__name__)
-
-    def getSignatureInfo(self):
-        return {'positional': self.positional,
-                'required': self.required,
-                'optional': self.optional,
-                'varargs': self.varargs,
-                'kwargs': self.kwargs,
-                }
-
-    def getSignatureString(self):
-        sig = []
-        for v in self.positional:
-            sig.append(v)
-            if v in self.optional.keys():
-                sig[-1] += "=" + repr(self.optional[v])
-        if self.varargs:
-            sig.append("*" + self.varargs)
-        if self.kwargs:
-            sig.append("**" + self.kwargs)
-
-        return "(%s)" % ", ".join(sig)
-
-    _get_str_info = getSignatureString
-
-
-def fromFunction(func, interface=None, imlevel=0, name=None):
-    name = name or func.__name__
-    method = Method(name, func.__doc__)
-    defaults = getattr(func, '__defaults__', None) or ()
-    code = func.__code__
-    # Number of positional arguments
-    na = code.co_argcount - imlevel
-    names = code.co_varnames[imlevel:]
-    opt = {}
-    # Number of required arguments
-    defaults_count = len(defaults)
-    if not defaults_count:
-        # PyPy3 uses ``__defaults_count__`` for builtin methods
-        # like ``dict.pop``. Surprisingly, these don't have recorded
-        # ``__defaults__``
-        defaults_count = getattr(func, '__defaults_count__', 0)
-
-    nr = na - defaults_count
-    if nr < 0:
-        defaults = defaults[-nr:]
-        nr = 0
-
-    # Determine the optional arguments.
-    opt.update(dict(zip(names[nr:], defaults)))
-
-    method.positional = names[:na]
-    method.required = names[:nr]
-    method.optional = opt
-
-    argno = na
-
-    # Determine the function's variable argument's name (i.e. *args)
-    if code.co_flags & CO_VARARGS:
-        method.varargs = names[argno]
-        argno = argno + 1
-    else:
-        method.varargs = None
-
-    # Determine the function's keyword argument's name (i.e. **kw)
-    if code.co_flags & CO_VARKEYWORDS:
-        method.kwargs = names[argno]
-    else:
-        method.kwargs = None
-
-    method.interface = interface
-
-    for key, value in func.__dict__.items():
-        method.setTaggedValue(key, value)
-
-    return method
-
-
-def fromMethod(meth, interface=None, name=None):
-    if isinstance(meth, MethodType):
-        func = meth.__func__
-    else:
-        func = meth
-    return fromFunction(func, interface, imlevel=1, name=name)
-
-
-# Now we can create the interesting interfaces and wire them up:
-def _wire():
-    from zope.interface.declarations import classImplements
-    # From lest specific to most specific.
-    from zope.interface.interfaces import IElement
-    classImplements(Element, IElement)
-
-    from zope.interface.interfaces import IAttribute
-    classImplements(Attribute, IAttribute)
-
-    from zope.interface.interfaces import IMethod
-    classImplements(Method, IMethod)
-
-    from zope.interface.interfaces import ISpecification
-    classImplements(Specification, ISpecification)
-
-    from zope.interface.interfaces import IInterface
-    classImplements(InterfaceClass, IInterface)
-
-
-# We import this here to deal with module dependencies.
-# pylint:disable=wrong-import-position
-from zope.interface.declarations import implementedBy
-from zope.interface.declarations import providedBy
-from zope.interface.exceptions import BrokenImplementation
-from zope.interface.exceptions import InvalidInterface
-
-
-# This ensures that ``Interface`` winds up in the flattened()
-# list of the immutable declaration. It correctly overrides changed()
-# as a no-op, so we bypass that.
-# pylint:disable=wrong-import-position
-from zope.interface.declarations import _empty  # isort: skip
-Specification.changed(_empty, _empty)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/interfaces.py b/llmlab/lib/python3.12/site-packages/zope/interface/interfaces.py
deleted file mode 100644
index 9bafeb5..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/interfaces.py
+++ /dev/null
@@ -1,1516 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Interface Package Interfaces
-"""
-__docformat__ = 'restructuredtext'
-
-from zope.interface.declarations import implementer
-from zope.interface.interface import Attribute
-from zope.interface.interface import Interface
-
-
-__all__ = [
-    'ComponentLookupError',
-    'IAdapterRegistration',
-    'IAdapterRegistry',
-    'IAttribute',
-    'IComponentLookup',
-    'IComponentRegistry',
-    'IComponents',
-    'IDeclaration',
-    'IElement',
-    'IHandlerRegistration',
-    'IInterface',
-    'IInterfaceDeclaration',
-    'IMethod',
-    'Invalid',
-    'IObjectEvent',
-    'IRegistered',
-    'IRegistration',
-    'IRegistrationEvent',
-    'ISpecification',
-    'ISubscriptionAdapterRegistration',
-    'IUnregistered',
-    'IUtilityRegistration',
-    'ObjectEvent',
-    'Registered',
-    'Unregistered',
-]
-
-# pylint:disable=inherit-non-class,no-method-argument,no-self-argument
-# pylint:disable=unexpected-special-method-signature
-# pylint:disable=too-many-lines
-
-
-class IElement(Interface):
-    """
-    Objects that have basic documentation and tagged values.
-
-    Known derivatives include :class:`IAttribute` and its derivative
-    :class:`IMethod`; these have no notion of inheritance.
-    :class:`IInterface` is also a derivative, and it does have a
-    notion of inheritance, expressed through its ``__bases__`` and
-    ordered in its ``__iro__`` (both defined by
-    :class:`ISpecification`).
-    """
-
-    # pylint:disable=arguments-differ
-
-    # Note that defining __doc__ as an Attribute hides the docstring
-    # from introspection. When changing it, also change it in the Sphinx
-    # ReST files.
-
-    __name__ = Attribute('__name__', 'The object name')
-    __doc__ = Attribute('__doc__', 'The object doc string')
-
-    ###
-    # Tagged values.
-    #
-    # Direct values are established in this instance. Others may be
-    # inherited. Although ``IElement`` itself doesn't have a notion of
-    # inheritance, ``IInterface`` *does*. It might have been better to
-    # make ``IInterface`` define new methods
-    # ``getIndirectTaggedValue``, etc, to include inheritance instead
-    # of overriding ``getTaggedValue`` to do that, but that ship has sailed.
-    # So to keep things nice and symmetric, we define the ``Direct`` methods
-    # here.
-    ###
-
-    def getTaggedValue(tag):
-        """Returns the value associated with *tag*.
-
-        Raise a `KeyError` if the tag isn't set.
-
-        If the object has a notion of inheritance, this searches
-        through the inheritance hierarchy and returns the nearest result.
-        If there is no such notion, this looks only at this object.
-
-        .. versionchanged:: 4.7.0
-           This method should respect inheritance if present.
-        """
-
-    def queryTaggedValue(tag, default=None):
-        """
-        As for `getTaggedValue`, but instead of raising a `KeyError`, returns
-        *default*.
-
-
-        .. versionchanged:: 4.7.0
-           This method should respect inheritance if present.
-        """
-
-    def getTaggedValueTags():
-        """
-        Returns a collection of all tags in no particular order.
-
-        If the object has a notion of inheritance, this
-        includes all the inherited tagged values. If there is
-        no such notion, this looks only at this object.
-
-        .. versionchanged:: 4.7.0
-           This method should respect inheritance if present.
-        """
-
-    def setTaggedValue(tag, value):
-        """
-        Associates *value* with *key* directly in this object.
-        """
-
-    def getDirectTaggedValue(tag):
-        """
-        As for `getTaggedValue`, but never includes inheritance.
-
-        .. versionadded:: 5.0.0
-        """
-
-    def queryDirectTaggedValue(tag, default=None):
-        """
-        As for `queryTaggedValue`, but never includes inheritance.
-
-        .. versionadded:: 5.0.0
-        """
-
-    def getDirectTaggedValueTags():
-        """
-        As for `getTaggedValueTags`, but includes only tags directly
-        set on this object.
-
-        .. versionadded:: 5.0.0
-        """
-
-
-class IAttribute(IElement):
-    """Attribute descriptors"""
-
-    interface = Attribute('interface',
-                          'Stores the interface instance in which the '
-                          'attribute is located.')
-
-
-class IMethod(IAttribute):
-    """Method attributes"""
-
-    def getSignatureInfo():
-        """Returns the signature information.
-
-        This method returns a dictionary with the following string keys:
-
-        - positional
-            A sequence of the names of positional arguments.
-        - required
-            A sequence of the names of required arguments.
-        - optional
-            A dictionary mapping argument names to their default values.
-        - varargs
-            The name of the varargs argument (or None).
-        - kwargs
-            The name of the kwargs argument (or None).
-        """
-
-    def getSignatureString():
-        """Return a signature string suitable for inclusion in documentation.
-
-        This method returns the function signature string. For example, if you
-        have ``def func(a, b, c=1, d='f')``, then the signature string is
-        ``"(a, b, c=1, d='f')"``.
-        """
-
-
-class ISpecification(Interface):
-    """Object Behavioral specifications"""
-    # pylint:disable=arguments-differ
-    def providedBy(object):  # pylint:disable=redefined-builtin
-        """Test whether the interface is implemented by the object
-
-        Return true of the object asserts that it implements the
-        interface, including asserting that it implements an extended
-        interface.
-        """
-
-    def implementedBy(class_):
-        """Test whether the interface is implemented by instances of the class
-
-        Return true of the class asserts that its instances implement the
-        interface, including asserting that they implement an extended
-        interface.
-        """
-
-    def isOrExtends(other):
-        """Test whether the specification is or extends another
-        """
-
-    def extends(other, strict=True):
-        """Test whether a specification extends another
-
-        The specification extends other if it has other as a base
-        interface or if one of it's bases extends other.
-
-        If strict is false, then the specification extends itself.
-        """
-
-    def weakref(callback=None):
-        """Return a weakref to the specification
-
-        This method is, regrettably, needed to allow weakrefs to be
-        computed to security-proxied specifications.  While the
-        zope.interface package does not require zope.security or
-        zope.proxy, it has to be able to coexist with it.
-
-        """
-
-    __bases__ = Attribute("""Base specifications
-
-    A tuple of specifications from which this specification is
-    directly derived.
-
-    """)
-
-    __sro__ = Attribute("""Specification-resolution order
-
-    A tuple of the specification and all of it's ancestor
-    specifications from most specific to least specific. The specification
-    itself is the first element.
-
-    (This is similar to the method-resolution order for new-style classes.)
-    """)
-
-    __iro__ = Attribute("""Interface-resolution order
-
-    A tuple of the specification's ancestor interfaces from
-    most specific to least specific.  The specification itself is
-    included if it is an interface.
-
-    (This is similar to the method-resolution order for new-style classes.)
-    """)
-
-    def get(name, default=None):
-        """Look up the description for a name
-
-        If the named attribute is not defined, the default is
-        returned.
-        """
-
-
-class IInterface(ISpecification, IElement):
-    """Interface objects
-
-    Interface objects describe the behavior of an object by containing
-    useful information about the object.  This information includes:
-
-    - Prose documentation about the object.  In Python terms, this
-      is called the "doc string" of the interface.  In this element,
-      you describe how the object works in prose language and any
-      other useful information about the object.
-
-    - Descriptions of attributes.  Attribute descriptions include
-      the name of the attribute and prose documentation describing
-      the attributes usage.
-
-    - Descriptions of methods.  Method descriptions can include:
-
-        - Prose "doc string" documentation about the method and its
-          usage.
-
-        - A description of the methods arguments; how many arguments
-          are expected, optional arguments and their default values,
-          the position or arguments in the signature, whether the
-          method accepts arbitrary arguments and whether the method
-          accepts arbitrary keyword arguments.
-
-    - Optional tagged data.  Interface objects (and their attributes and
-      methods) can have optional, application specific tagged data
-      associated with them.  Examples uses for this are examples,
-      security assertions, pre/post conditions, and other possible
-      information you may want to associate with an Interface or its
-      attributes.
-
-    Not all of this information is mandatory.  For example, you may
-    only want the methods of your interface to have prose
-    documentation and not describe the arguments of the method in
-    exact detail.  Interface objects are flexible and let you give or
-    take any of these components.
-
-    Interfaces are created with the Python class statement using
-    either `zope.interface.Interface` or another interface, as in::
-
-      from zope.interface import Interface
-
-      class IMyInterface(Interface):
-        '''Interface documentation'''
-
-        def meth(arg1, arg2):
-            '''Documentation for meth'''
-
-        # Note that there is no self argument
-
-     class IMySubInterface(IMyInterface):
-        '''Interface documentation'''
-
-        def meth2():
-            '''Documentation for meth2'''
-
-    You use interfaces in two ways:
-
-    - You assert that your object implement the interfaces.
-
-      There are several ways that you can declare that an object
-      provides an interface:
-
-      1. Call `zope.interface.implementer` on your class definition.
-
-      2. Call `zope.interface.directlyProvides` on your object.
-
-      3. Call `zope.interface.classImplements` to declare that instances
-         of a class implement an interface.
-
-         For example::
-
-           from zope.interface import classImplements
-
-           classImplements(some_class, some_interface)
-
-         This approach is useful when it is not an option to modify
-         the class source.  Note that this doesn't affect what the
-         class itself implements, but only what its instances
-         implement.
-
-    - You query interface meta-data. See the IInterface methods and
-      attributes for details.
-
-    """
-    # pylint:disable=arguments-differ
-    def names(all=False):  # pylint:disable=redefined-builtin
-        """Get the interface attribute names
-
-        Return a collection of the names of the attributes, including
-        methods, included in the interface definition.
-
-        Normally, only directly defined attributes are included. If
-        a true positional or keyword argument is given, then
-        attributes defined by base classes will be included.
-        """
-
-    def namesAndDescriptions(all=False):  # pylint:disable=redefined-builtin
-        """Get the interface attribute names and descriptions
-
-        Return a collection of the names and descriptions of the
-        attributes, including methods, as name-value pairs, included
-        in the interface definition.
-
-        Normally, only directly defined attributes are included. If
-        a true positional or keyword argument is given, then
-        attributes defined by base classes will be included.
-        """
-
-    def __getitem__(name):
-        """Get the description for a name
-
-        If the named attribute is not defined, a `KeyError` is raised.
-        """
-
-    def direct(name):
-        """Get the description for the name if it was defined by the interface
-
-        If the interface doesn't define the name, returns None.
-        """
-
-    def validateInvariants(obj, errors=None):
-        """Validate invariants
-
-        Validate object to defined invariants.  If errors is None,
-        raises first Invalid error; if errors is a list, appends all errors
-        to list, then raises Invalid with the errors as the first element
-        of the "args" tuple."""
-
-    def __contains__(name):
-        """Test whether the name is defined by the interface"""
-
-    def __iter__():
-        """Return an iterator over the names defined by the interface
-
-        The names iterated include all of the names defined by the
-        interface directly and indirectly by base interfaces.
-        """
-
-    __module__ = Attribute("""The name of the module defining the interface""")
-
-
-class IDeclaration(ISpecification):
-    """Interface declaration
-
-    Declarations are used to express the interfaces implemented by
-    classes or provided by objects.
-    """
-
-    def __contains__(interface):
-        """Test whether an interface is in the specification
-
-        Return true if the given interface is one of the interfaces in
-        the specification and false otherwise.
-        """
-
-    def __iter__():
-        """Return an iterator for the interfaces in the specification
-        """
-
-    def flattened():
-        """Return an iterator of all included and extended interfaces
-
-        An iterator is returned for all interfaces either included in
-        or extended by interfaces included in the specifications
-        without duplicates. The interfaces are in "interface
-        resolution order". The interface resolution order is such that
-        base interfaces are listed after interfaces that extend them
-        and, otherwise, interfaces are included in the order that they
-        were defined in the specification.
-        """
-
-    def __sub__(interfaces):
-        """Create an interface specification with some interfaces excluded
-
-        The argument can be an interface or an interface
-        specifications.  The interface or interfaces given in a
-        specification are subtracted from the interface specification.
-
-        Removing an interface that is not in the specification does
-        not raise an error. Doing so has no effect.
-
-        Removing an interface also removes sub-interfaces of the interface.
-
-        """
-
-    def __add__(interfaces):
-        """Create an interface specification with some interfaces added
-
-        The argument can be an interface or an interface
-        specifications.  The interface or interfaces given in a
-        specification are added to the interface specification.
-
-        Adding an interface that is already in the specification does
-        not raise an error. Doing so has no effect.
-        """
-
-    def __nonzero__():
-        """Return a true value of the interface specification is non-empty
-        """
-
-
-class IInterfaceDeclaration(Interface):
-    """
-    Declare and check the interfaces of objects.
-
-    The functions defined in this interface are used to declare the
-    interfaces that objects provide and to query the interfaces that
-    have been declared.
-
-    Interfaces can be declared for objects in two ways:
-
-        - Interfaces are declared for instances of the object's class
-
-        - Interfaces are declared for the object directly.
-
-    The interfaces declared for an object are, therefore, the union of
-    interfaces declared for the object directly and the interfaces
-    declared for instances of the object's class.
-
-    Note that we say that a class implements the interfaces provided
-    by it's instances. An instance can also provide interfaces
-    directly. The interfaces provided by an object are the union of
-    the interfaces provided directly and the interfaces implemented by
-    the class.
-
-    This interface is implemented by :mod:`zope.interface`.
-    """
-    # pylint:disable=arguments-differ
-    ###
-    # Defining interfaces
-    ###
-
-    Interface = Attribute("The base class used to create new interfaces")
-
-    def taggedValue(key, value):
-        """
-        Attach a tagged value to an interface while defining the interface.
-
-        This is a way of executing :meth:`IElement.setTaggedValue` from
-        the definition of the interface. For example::
-
-             class IFoo(Interface):
-                 taggedValue('key', 'value')
-
-        .. seealso:: `zope.interface.taggedValue`
-        """
-
-    def invariant(checker_function):
-        """
-        Attach an invariant checker function to an interface while defining it.
-
-        Invariants can later be validated against particular implementations by
-        calling :meth:`IInterface.validateInvariants`.
-
-        For example::
-
-             def check_range(ob):
-                 if ob.max < ob.min:
-                     raise ValueError("max value is less than min value")
-
-             class IRange(Interface):
-                 min = Attribute("The min value")
-                 max = Attribute("The max value")
-
-                 invariant(check_range)
-
-        .. seealso:: `zope.interface.invariant`
-        """
-
-    def interfacemethod(method):
-        """
-        A decorator that transforms a method specification into an
-        implementation method.
-
-        This is used to override methods of ``Interface`` or provide new
-        methods.  Definitions using this decorator will not appear in
-        :meth:`IInterface.names()`.  It is possible to have an implementation
-        method and a method specification of the same name.
-
-        For example::
-
-             class IRange(Interface):
-                 @interfacemethod
-                 def __adapt__(self, obj):
-                     if isinstance(obj, range):
-                         # Return the builtin ``range`` as-is
-                         return obj
-                     return super(type(IRange), self).__adapt__(obj)
-
-        You can use ``super`` to call the parent class functionality. Note
-        that the zero-argument version (``super().__adapt__``) works on Python
-        3.6 and above, but prior to that the two-argument version must be
-        used, and the class must be explicitly passed as the first argument.
-
-        .. versionadded:: 5.1.0
-        .. seealso:: `zope.interface.interfacemethod`
-        """
-
-    ###
-    # Querying interfaces
-    ###
-
-    def providedBy(ob):
-        """
-        Return the interfaces provided by an object.
-
-        This is the union of the interfaces directly provided by an
-        object and interfaces implemented by it's class.
-
-        The value returned is an `IDeclaration`.
-
-        .. seealso:: `zope.interface.providedBy`
-        """
-
-    def implementedBy(class_):
-        """
-        Return the interfaces implemented for a class's instances.
-
-        The value returned is an `IDeclaration`.
-
-        .. seealso:: `zope.interface.implementedBy`
-        """
-
-    ###
-    # Declaring interfaces
-    ###
-
-    def classImplements(class_, *interfaces):
-        """
-        Declare additional interfaces implemented for instances of a class.
-
-        The arguments after the class are one or more interfaces or
-        interface specifications (`IDeclaration` objects).
-
-        The interfaces given (including the interfaces in the
-        specifications) are added to any interfaces previously
-        declared.
-
-        Consider the following example::
-
-          class C(A, B):
-             ...
-
-          classImplements(C, I1, I2)
-
-
-        Instances of ``C`` provide ``I1``, ``I2``, and whatever interfaces
-        instances of ``A`` and ``B`` provide. This is equivalent to::
-
-            @implementer(I1, I2)
-            class C(A, B):
-                pass
-
-        .. seealso:: `zope.interface.classImplements`
-        .. seealso:: `zope.interface.implementer`
-        """
-
-    def classImplementsFirst(cls, interface):
-        """
-        See :func:`zope.interface.classImplementsFirst`.
-        """
-
-    def implementer(*interfaces):
-        """
-        Create a decorator for declaring interfaces implemented by a
-        factory.
-
-        A callable is returned that makes an implements declaration on
-        objects passed to it.
-
-        .. seealso:: :meth:`classImplements`
-        """
-
-    def classImplementsOnly(class_, *interfaces):
-        """
-        Declare the only interfaces implemented by instances of a class.
-
-        The arguments after the class are one or more interfaces or
-        interface specifications (`IDeclaration` objects).
-
-        The interfaces given (including the interfaces in the
-        specifications) replace any previous declarations.
-
-        Consider the following example::
-
-          class C(A, B):
-             ...
-
-          classImplements(C, IA, IB. IC)
-          classImplementsOnly(C. I1, I2)
-
-        Instances of ``C`` provide only ``I1``, ``I2``, and regardless of
-        whatever interfaces instances of ``A`` and ``B`` implement.
-
-        .. seealso:: `zope.interface.classImplementsOnly`
-        """
-
-    def implementer_only(*interfaces):
-        """
-        Create a decorator for declaring the only interfaces implemented.
-
-        A callable is returned that makes an implements declaration on
-        objects passed to it.
-
-        .. seealso:: `zope.interface.implementer_only`
-        """
-
-    def directlyProvidedBy(object):  # pylint:disable=redefined-builtin
-        """
-        Return the interfaces directly provided by the given object.
-
-        The value returned is an `IDeclaration`.
-
-        .. seealso:: `zope.interface.directlyProvidedBy`
-        """
-
-    def directlyProvides(
-        object, *interfaces,
-    ):  # pylint:disable=redefined-builtin
-        """
-        Declare interfaces declared directly for an object.
-
-        The arguments after the object are one or more interfaces or
-        interface specifications (`IDeclaration` objects).
-
-        .. caution::
-           The interfaces given (including the interfaces in the
-           specifications) *replace* interfaces previously
-           declared for the object. See :meth:`alsoProvides` to add
-           additional interfaces.
-
-        Consider the following example::
-
-          class C(A, B):
-             ...
-
-          ob = C()
-          directlyProvides(ob, I1, I2)
-
-        The object, ``ob`` provides ``I1``, ``I2``, and whatever interfaces
-        instances have been declared for instances of ``C``.
-
-        To remove directly provided interfaces, use `directlyProvidedBy` and
-        subtract the unwanted interfaces. For example::
-
-          directlyProvides(ob, directlyProvidedBy(ob)-I2)
-
-        removes I2 from the interfaces directly provided by
-        ``ob``. The object, ``ob`` no longer directly provides ``I2``,
-        although it might still provide ``I2`` if it's class
-        implements ``I2``.
-
-        To add directly provided interfaces, use `directlyProvidedBy` and
-        include additional interfaces.  For example::
-
-          directlyProvides(ob, directlyProvidedBy(ob), I2)
-
-        adds I2 to the interfaces directly provided by ob.
-
-        .. seealso:: `zope.interface.directlyProvides`
-        """
-
-    def alsoProvides(object, *interfaces):  # pylint:disable=redefined-builtin
-        """
-        Declare additional interfaces directly for an object.
-
-        For example::
-
-          alsoProvides(ob, I1)
-
-        is equivalent to::
-
-          directlyProvides(ob, directlyProvidedBy(ob), I1)
-
-        .. seealso:: `zope.interface.alsoProvides`
-        """
-
-    def noLongerProvides(
-        object, interface,
-    ):  # pylint:disable=redefined-builtin
-        """
-        Remove an interface from the list of an object's directly provided
-        interfaces.
-
-        For example::
-
-          noLongerProvides(ob, I1)
-
-        is equivalent to::
-
-          directlyProvides(ob, directlyProvidedBy(ob) - I1)
-
-        with the exception that if ``I1`` is an interface that is
-        provided by ``ob`` through the class's implementation,
-        `ValueError` is raised.
-
-        .. seealso:: `zope.interface.noLongerProvides`
-        """
-
-    def provider(*interfaces):
-        """
-        Declare interfaces provided directly by a class.
-
-        .. seealso:: `zope.interface.provider`
-        """
-
-    def moduleProvides(*interfaces):
-        """
-        Declare interfaces provided by a module.
-
-        This function is used in a module definition.
-
-        The arguments are one or more interfaces or interface
-        specifications (`IDeclaration` objects).
-
-        The given interfaces (including the interfaces in the
-        specifications) are used to create the module's direct-object
-        interface specification.  An error will be raised if the module
-        already has an interface specification.  In other words, it is
-        an error to call this function more than once in a module
-        definition.
-
-        This function is provided for convenience. It provides a more
-        convenient way to call `directlyProvides` for a module. For example::
-
-          moduleImplements(I1)
-
-        is equivalent to::
-
-          directlyProvides(sys.modules[__name__], I1)
-
-        .. seealso:: `zope.interface.moduleProvides`
-        """
-
-    def Declaration(*interfaces):
-        """
-        Create an interface specification.
-
-        The arguments are one or more interfaces or interface
-        specifications (`IDeclaration` objects).
-
-        A new interface specification (`IDeclaration`) with the given
-        interfaces is returned.
-
-        .. seealso:: `zope.interface.Declaration`
-        """
-
-
-class IAdapterRegistry(Interface):
-    """Provide an interface-based registry for adapters
-
-    This registry registers objects that are in some sense "from" a
-    sequence of specification to an interface and a name.
-
-    No specific semantics are assumed for the registered objects,
-    however, the most common application will be to register factories
-    that adapt objects providing required specifications to a provided
-    interface.
-    """
-
-    def register(required, provided, name, value):
-        """Register a value
-
-        A value is registered for a *sequence* of required specifications, a
-        provided interface, and a name, which must be text.
-        """
-
-    def registered(required, provided, name=''):
-        """Return the component registered for the given interfaces and name
-
-        name must be text.
-
-        Unlike the lookup method, this methods won't retrieve
-        components registered for more specific required interfaces or
-        less specific provided interfaces.
-
-        If no component was registered exactly for the given
-        interfaces and name, then None is returned.
-
-        """
-
-    def lookup(required, provided, name='', default=None):
-        """Lookup a value
-
-        A value is looked up based on a *sequence* of required
-        specifications, a provided interface, and a name, which must be
-        text.
-        """
-
-    def queryMultiAdapter(objects, provided, name='', default=None):
-        """Adapt a sequence of objects to a named, provided, interface
-        """
-
-    def lookup1(required, provided, name='', default=None):
-        """Lookup a value using a single required interface
-
-        A value is looked up based on a single required
-        specifications, a provided interface, and a name, which must be
-        text.
-        """
-
-    def queryAdapter(
-        object, provided, name='', default=None,
-    ):  # pylint:disable=redefined-builtin
-        """Adapt an object using a registered adapter factory.
-        """
-
-    def adapter_hook(
-        provided, object, name='', default=None,
-    ):  # pylint:disable=redefined-builtin
-        """Adapt an object using a registered adapter factory.
-
-        name must be text.
-        """
-
-    def lookupAll(required, provided):
-        """Find all adapters from the required to the provided interfaces
-
-        An iterable object is returned that provides name-value two-tuples.
-        """
-
-    def names(required, provided):  # pylint:disable=arguments-differ
-        """Return the names for which there are registered objects
-        """
-
-    def subscribe(
-        required, provided, subscriber,
-    ):  # pylint:disable=arguments-differ
-        """Register a subscriber
-
-        A subscriber is registered for a *sequence* of required
-        specifications, a provided interface, and a name.
-
-        Multiple subscribers may be registered for the same (or
-        equivalent) interfaces.
-
-        .. versionchanged:: 5.1.1
-           Correct the method signature to remove the ``name`` parameter.
-           Subscribers have no names.
-        """
-
-    def subscribed(required, provided, subscriber):
-        """
-        Check whether the object *subscriber* is registered directly
-        with this object via a previous call to
-        ``subscribe(required, provided, subscriber)``.
-
-        If the *subscriber*, or one equal to it, has been subscribed,
-        for the given *required* sequence and *provided* interface,
-        return that object. (This does not guarantee whether the *subscriber*
-        itself is returned, or an object equal to it.)
-
-        If it has not, return ``None``.
-
-        Unlike :meth:`subscriptions`, this method won't retrieve
-        components registered for more specific required interfaces or
-        less specific provided interfaces.
-
-        .. versionadded:: 5.3.0
-        """
-
-    def subscriptions(required, provided):
-        """
-        Get a sequence of subscribers.
-
-        Subscribers for a sequence of *required* interfaces, and a *provided*
-        interface are returned. This takes into account subscribers
-        registered with this object, as well as those registered with
-        base adapter registries in the resolution order, and interfaces that
-        extend *provided*.
-
-        .. versionchanged:: 5.1.1
-           Correct the method signature to remove the ``name`` parameter.
-           Subscribers have no names.
-        """
-
-    def subscribers(objects, provided):
-        """
-        Get a sequence of subscription **adapters**.
-
-        This is like :meth:`subscriptions`, but calls the returned
-        subscribers with *objects* (and optionally returns the results
-        of those calls), instead of returning the subscribers directly.
-
-        :param objects: A sequence of objects; they will be used to
-            determine the *required* argument to :meth:`subscriptions`.
-        :param provided: A single interface, or ``None``, to pass
-            as the *provided* parameter to :meth:`subscriptions`.
-            If an interface is given, the results of calling each returned
-            subscriber with the the *objects* are collected and returned
-            from this method; each result should be an object implementing
-            the *provided* interface. If ``None``, the resulting subscribers
-            are still called, but the results are ignored.
-        :return: A sequence of the results of calling the subscribers
-            if *provided* is not ``None``. If there are no registered
-            subscribers, or *provided* is ``None``, this will be an empty
-            sequence.
-
-        .. versionchanged:: 5.1.1
-           Correct the method signature to remove the ``name`` parameter.
-           Subscribers have no names.
-        """
-
-# begin formerly in zope.component
-
-
-class ComponentLookupError(LookupError):
-    """A component could not be found."""
-
-
-class Invalid(Exception):
-    """A component doesn't satisfy a promise."""
-
-
-class IObjectEvent(Interface):
-    """An event related to an object.
-
-    The object that generated this event is not necessarily the object
-    referred to by location.
-    """
-
-    object = Attribute("The subject of the event.")
-
-
-@implementer(IObjectEvent)
-class ObjectEvent:
-
-    def __init__(self, object):  # pylint:disable=redefined-builtin
-        self.object = object
-
-
-class IComponentLookup(Interface):
-    """Component Manager for a Site
-
-    This object manages the components registered at a particular site. The
-    definition of a site is intentionally vague.
-    """
-
-    adapters = Attribute(
-        "Adapter Registry to manage all registered adapters.")
-
-    utilities = Attribute(
-        "Adapter Registry to manage all registered utilities.")
-
-    def queryAdapter(
-        object, interface, name='', default=None
-    ):  # pylint:disable=redefined-builtin
-        """Look for a named adapter to an interface for an object
-
-        If a matching adapter cannot be found, returns the default.
-        """
-
-    def getAdapter(
-        object, interface, name=''
-    ):  # pylint:disable=redefined-builtin
-        """Look for a named adapter to an interface for an object
-
-        If a matching adapter cannot be found, a `ComponentLookupError`
-        is raised.
-        """
-
-    def queryMultiAdapter(objects, interface, name='', default=None):
-        """Look for a multi-adapter to an interface for multiple objects
-
-        If a matching adapter cannot be found, returns the default.
-        """
-
-    def getMultiAdapter(objects, interface, name=''):
-        """Look for a multi-adapter to an interface for multiple objects
-
-        If a matching adapter cannot be found, a `ComponentLookupError`
-        is raised.
-        """
-
-    def getAdapters(objects, provided):
-        """Look for all matching adapters to a provided interface for objects
-
-        Return an iterable of name-adapter pairs for adapters that
-        provide the given interface.
-        """
-
-    def subscribers(objects, provided):
-        """Get subscribers
-
-        Subscribers are returned that provide the provided interface
-        and that depend on and are computed from the sequence of
-        required objects.
-        """
-
-    def handle(*objects):
-        """Call handlers for the given objects
-
-        Handlers registered for the given objects are called.
-        """
-
-    def queryUtility(interface, name='', default=None):
-        """Look up a utility that provides an interface.
-
-        If one is not found, returns default.
-        """
-
-    def getUtilitiesFor(interface):
-        """Look up the registered utilities that provide an interface.
-
-        Returns an iterable of name-utility pairs.
-        """
-
-    def getAllUtilitiesRegisteredFor(interface):
-        """Return all registered utilities for an interface
-
-        This includes overridden utilities.
-
-        An iterable of utility instances is returned.  No names are
-        returned.
-        """
-
-
-class IRegistration(Interface):
-    """A registration-information object
-    """
-
-    registry = Attribute("The registry having the registration")
-
-    name = Attribute("The registration name")
-
-    info = Attribute("""Information about the registration
-
-    This is information deemed useful to people browsing the
-    configuration of a system. It could, for example, include
-    commentary or information about the source of the configuration.
-    """)
-
-
-class IUtilityRegistration(IRegistration):
-    """Information about the registration of a utility
-    """
-
-    factory = Attribute("The factory used to create the utility. Optional.")
-    component = Attribute("The object registered")
-    provided = Attribute("The interface provided by the component")
-
-
-class _IBaseAdapterRegistration(IRegistration):
-    """Information about the registration of an adapter
-    """
-
-    factory = Attribute("The factory used to create adapters")
-
-    required = Attribute("""The adapted interfaces
-
-    This is a sequence of interfaces adapters by the registered
-    factory.  The factory will be caled with a sequence of objects, as
-    positional arguments, that provide these interfaces.
-    """)
-
-    provided = Attribute("""The interface provided by the adapters.
-
-    This interface is implemented by the factory
-    """)
-
-
-class IAdapterRegistration(_IBaseAdapterRegistration):
-    """Information about the registration of an adapter
-    """
-
-
-class ISubscriptionAdapterRegistration(_IBaseAdapterRegistration):
-    """Information about the registration of a subscription adapter
-    """
-
-
-class IHandlerRegistration(IRegistration):
-
-    handler = Attribute("An object called used to handle an event")
-
-    required = Attribute("""The handled interfaces
-
-    This is a sequence of interfaces handled by the registered
-    handler.  The handler will be caled with a sequence of objects, as
-    positional arguments, that provide these interfaces.
-    """)
-
-
-class IRegistrationEvent(IObjectEvent):
-    """An event that involves a registration"""
-
-
-@implementer(IRegistrationEvent)
-class RegistrationEvent(ObjectEvent):
-    """There has been a change in a registration
-    """
-
-    def __repr__(self):
-        return f"{self.__class__.__name__} event:\n{self.object!r}"
-
-
-class IRegistered(IRegistrationEvent):
-    """A component or factory was registered
-    """
-
-
-@implementer(IRegistered)
-class Registered(RegistrationEvent):
-    pass
-
-
-class IUnregistered(IRegistrationEvent):
-    """A component or factory was unregistered
-    """
-
-
-@implementer(IUnregistered)
-class Unregistered(RegistrationEvent):
-    """A component or factory was unregistered
-    """
-
-
-class IComponentRegistry(Interface):
-    """Register components
-    """
-
-    def registerUtility(component=None, provided=None, name='',
-                        info='', factory=None):
-        """Register a utility
-
-        :param factory:
-           Factory for the component to be registered.
-
-        :param component:
-           The registered component
-
-        :param provided:
-           This is the interface provided by the utility.  If the
-           component provides a single interface, then this
-           argument is optional and the component-implemented
-           interface will be used.
-
-        :param name:
-           The utility name.
-
-        :param info:
-           An object that can be converted to a string to provide
-           information about the registration.
-
-        Only one of *component* and *factory* can be used.
-
-        A `IRegistered` event is generated with an `IUtilityRegistration`.
-        """
-
-    def unregisterUtility(component=None, provided=None, name='',
-                          factory=None):
-        """Unregister a utility
-
-        :returns:
-            A boolean is returned indicating whether the registry was
-            changed.  If the given *component* is None and there is no
-            component registered, or if the given *component* is not
-            None and is not registered, then the function returns
-            False, otherwise it returns True.
-
-        :param factory:
-           Factory for the component to be unregistered.
-
-        :param component:
-           The registered component The given component can be
-           None, in which case any component registered to provide
-           the given provided interface with the given name is
-           unregistered.
-
-        :param provided:
-           This is the interface provided by the utility.  If the
-           component is not None and provides a single interface,
-           then this argument is optional and the
-           component-implemented interface will be used.
-
-        :param name:
-           The utility name.
-
-        Only one of *component* and *factory* can be used.
-        An `IUnregistered` event is generated with an `IUtilityRegistration`.
-        """
-
-    def registeredUtilities():
-        """Return an iterable of `IUtilityRegistration` instances.
-
-        These registrations describe the current utility registrations
-        in the object.
-        """
-
-    def registerAdapter(factory, required=None, provided=None, name='',
-                        info=''):
-        """Register an adapter factory
-
-        :param factory:
-            The object used to compute the adapter
-
-        :param required:
-            This is a sequence of specifications for objects to be
-            adapted.  If omitted, then the value of the factory's
-            ``__component_adapts__`` attribute will be used.  The
-            ``__component_adapts__`` attribute is
-            normally set in class definitions using
-            the `.adapter`
-            decorator.  If the factory doesn't have a
-            ``__component_adapts__`` adapts attribute, then this
-            argument is required.
-
-        :param provided:
-            This is the interface provided by the adapter and
-            implemented by the factory.  If the factory
-            implements a single interface, then this argument is
-            optional and the factory-implemented interface will be
-            used.
-
-        :param name:
-            The adapter name.
-
-        :param info:
-           An object that can be converted to a string to provide
-           information about the registration.
-
-        A `IRegistered` event is generated with an `IAdapterRegistration`.
-        """
-
-    def unregisterAdapter(factory=None, required=None,
-                          provided=None, name=''):
-        """Unregister an adapter factory
-
-        :returns:
-            A boolean is returned indicating whether the registry was
-            changed.  If the given component is None and there is no
-            component registered, or if the given component is not
-            None and is not registered, then the function returns
-            False, otherwise it returns True.
-
-        :param factory:
-            This is the object used to compute the adapter. The
-            factory can be None, in which case any factory
-            registered to implement the given provided interface
-            for the given required specifications with the given
-            name is unregistered.
-
-        :param required:
-            This is a sequence of specifications for objects to be
-            adapted.  If the factory is not None and the required
-            arguments is omitted, then the value of the factory's
-            __component_adapts__ attribute will be used.  The
-            __component_adapts__ attribute attribute is normally
-            set in class definitions using adapts function, or for
-            callables using the adapter decorator.  If the factory
-            is None or doesn't have a __component_adapts__ adapts
-            attribute, then this argument is required.
-
-        :param provided:
-            This is the interface provided by the adapter and
-            implemented by the factory.  If the factory is not
-            None and implements a single interface, then this
-            argument is optional and the factory-implemented
-            interface will be used.
-
-        :param name:
-            The adapter name.
-
-        An `IUnregistered` event is generated with an `IAdapterRegistration`.
-        """
-
-    def registeredAdapters():
-        """Return an iterable of `IAdapterRegistration` instances.
-
-        These registrations describe the current adapter registrations
-        in the object.
-        """
-
-    def registerSubscriptionAdapter(factory, required=None, provides=None,
-                                    name='', info=''):
-        """Register a subscriber factory
-
-        :param factory:
-            The object used to compute the adapter
-
-        :param required:
-            This is a sequence of specifications for objects to be
-            adapted.  If omitted, then the value of the factory's
-            ``__component_adapts__`` attribute will be used.  The
-            ``__component_adapts__`` attribute is
-            normally set using the adapter
-            decorator.  If the factory doesn't have a
-            ``__component_adapts__`` adapts attribute, then this
-            argument is required.
-
-        :param provided:
-            This is the interface provided by the adapter and
-            implemented by the factory.  If the factory implements
-            a single interface, then this argument is optional and
-            the factory-implemented interface will be used.
-
-        :param name:
-            The adapter name.
-
-            Currently, only the empty string is accepted.  Other
-            strings will be accepted in the future when support for
-            named subscribers is added.
-
-        :param info:
-           An object that can be converted to a string to provide
-           information about the registration.
-
-        A `IRegistered` event is generated with an
-        `ISubscriptionAdapterRegistration`.
-        """
-
-    def unregisterSubscriptionAdapter(factory=None, required=None,
-                                      provides=None, name=''):
-        """Unregister a subscriber factory.
-
-        :returns:
-            A boolean is returned indicating whether the registry was
-            changed.  If the given component is None and there is no
-            component registered, or if the given component is not
-            None and is not registered, then the function returns
-            False, otherwise it returns True.
-
-        :param factory:
-            This is the object used to compute the adapter. The
-            factory can be None, in which case any factories
-            registered to implement the given provided interface
-            for the given required specifications with the given
-            name are unregistered.
-
-        :param required:
-            This is a sequence of specifications for objects to be
-            adapted.  If omitted, then the value of the factory's
-            ``__component_adapts__`` attribute will be used.  The
-            ``__component_adapts__`` attribute is
-            normally set using the adapter
-            decorator.  If the factory doesn't have a
-            ``__component_adapts__`` adapts attribute, then this
-            argument is required.
-
-        :param provided:
-            This is the interface provided by the adapter and
-            implemented by the factory.  If the factory is not
-            None implements a single interface, then this argument
-            is optional and the factory-implemented interface will
-            be used.
-
-        :param name:
-            The adapter name.
-
-            Currently, only the empty string is accepted.  Other
-            strings will be accepted in the future when support for
-            named subscribers is added.
-
-        An `IUnregistered` event is generated with an
-        `ISubscriptionAdapterRegistration`.
-        """
-
-    def registeredSubscriptionAdapters():
-        """Return an iterable of `ISubscriptionAdapterRegistration` instances.
-
-        These registrations describe the current subscription adapter
-        registrations in the object.
-        """
-
-    def registerHandler(handler, required=None, name='', info=''):
-        """Register a handler.
-
-        A handler is a subscriber that doesn't compute an adapter
-        but performs some function when called.
-
-        :param handler:
-            The object used to handle some event represented by
-            the objects passed to it.
-
-        :param required:
-            This is a sequence of specifications for objects to be
-            adapted.  If omitted, then the value of the factory's
-            ``__component_adapts__`` attribute will be used.  The
-            ``__component_adapts__`` attribute is
-            normally set using the adapter
-            decorator.  If the factory doesn't have a
-            ``__component_adapts__`` adapts attribute, then this
-            argument is required.
-
-        :param name:
-            The handler name.
-
-            Currently, only the empty string is accepted.  Other
-            strings will be accepted in the future when support for
-            named handlers is added.
-
-        :param info:
-           An object that can be converted to a string to provide
-           information about the registration.
-
-
-        A `IRegistered` event is generated with an `IHandlerRegistration`.
-        """
-
-    def unregisterHandler(handler=None, required=None, name=''):
-        """Unregister a handler.
-
-        A handler is a subscriber that doesn't compute an adapter
-        but performs some function when called.
-
-        :returns: A boolean is returned indicating whether the registry was
-            changed.
-
-        :param handler:
-            This is the object used to handle some event
-            represented by the objects passed to it. The handler
-            can be None, in which case any handlers registered for
-            the given required specifications with the given are
-            unregistered.
-
-        :param required:
-            This is a sequence of specifications for objects to be
-            adapted.  If omitted, then the value of the factory's
-            ``__component_adapts__`` attribute will be used.  The
-            ``__component_adapts__`` attribute is
-            normally set using the adapter
-            decorator.  If the factory doesn't have a
-            ``__component_adapts__`` adapts attribute, then this
-            argument is required.
-
-        :param name:
-            The handler name.
-
-            Currently, only the empty string is accepted.  Other
-            strings will be accepted in the future when support for
-            named handlers is added.
-
-        An `IUnregistered` event is generated with an `IHandlerRegistration`.
-        """
-
-    def registeredHandlers():
-        """Return an iterable of `IHandlerRegistration` instances.
-
-        These registrations describe the current handler registrations
-        in the object.
-        """
-
-
-class IComponents(IComponentLookup, IComponentRegistry):
-    """Component registration and access
-    """
-
-
-# end formerly in zope.component
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/registry.py b/llmlab/lib/python3.12/site-packages/zope/interface/registry.py
deleted file mode 100644
index 37c4ec9..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/registry.py
+++ /dev/null
@@ -1,750 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2006 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Basic components support
-"""
-from collections import defaultdict
-
-
-try:
-    from zope.event import notify
-except ImportError:  # pragma: no cover
-    def notify(*arg, **kw):
-        pass
-
-from zope.interface.adapter import AdapterRegistry
-from zope.interface.declarations import implementedBy
-from zope.interface.declarations import implementer
-from zope.interface.declarations import implementer_only
-from zope.interface.declarations import providedBy
-from zope.interface.interface import Interface
-from zope.interface.interfaces import ComponentLookupError
-from zope.interface.interfaces import IAdapterRegistration
-from zope.interface.interfaces import IComponents
-from zope.interface.interfaces import IHandlerRegistration
-from zope.interface.interfaces import ISpecification
-from zope.interface.interfaces import ISubscriptionAdapterRegistration
-from zope.interface.interfaces import IUtilityRegistration
-from zope.interface.interfaces import Registered
-from zope.interface.interfaces import Unregistered
-
-
-__all__ = [
-    # Components is public API, but
-    # the *Registration classes are just implementations
-    # of public interfaces.
-    'Components',
-]
-
-
-class _UnhashableComponentCounter:
-    # defaultdict(int)-like object for unhashable components
-
-    def __init__(self, otherdict):
-        # [(component, count)]
-        self._data = [item for item in otherdict.items()]
-
-    def __getitem__(self, key):
-        for component, count in self._data:
-            if component == key:
-                return count
-        return 0
-
-    def __setitem__(self, component, count):
-        for i, data in enumerate(self._data):
-            if data[0] == component:
-                self._data[i] = component, count
-                return
-        self._data.append((component, count))
-
-    def __delitem__(self, component):
-        for i, data in enumerate(self._data):
-            if data[0] == component:
-                del self._data[i]
-                return
-        raise KeyError(component)  # pragma: no cover
-
-
-def _defaultdict_int():
-    return defaultdict(int)
-
-
-class _UtilityRegistrations:
-
-    def __init__(self, utilities, utility_registrations):
-        # {provided -> {component: count}}
-        self._cache = defaultdict(_defaultdict_int)
-        self._utilities = utilities
-        self._utility_registrations = utility_registrations
-
-        self.__populate_cache()
-
-    def __populate_cache(self):
-        for ((p, _), data) in iter(self._utility_registrations.items()):
-            component = data[0]
-            self.__cache_utility(p, component)
-
-    def __cache_utility(self, provided, component):
-        try:
-            self._cache[provided][component] += 1
-        except TypeError:
-            # The component is not hashable, and we have a dict. Switch to a
-            # strategy that doesn't use hashing.
-            prov = self._cache[provided] = _UnhashableComponentCounter(
-                self._cache[provided]
-            )
-            prov[component] += 1
-
-    def __uncache_utility(self, provided, component):
-        provided = self._cache[provided]
-        # It seems like this line could raise a TypeError if component isn't
-        # hashable and we haven't yet switched to _UnhashableComponentCounter.
-        # However, we can't actually get in that situation. In order to get
-        # here, we would have had to cache the utility already which would
-        # have switched the datastructure if needed.
-        count = provided[component]
-        count -= 1
-        if count == 0:
-            del provided[component]
-        else:
-            provided[component] = count
-        return count > 0
-
-    def _is_utility_subscribed(self, provided, component):
-        try:
-            return self._cache[provided][component] > 0
-        except TypeError:
-            # Not hashable and we're still using a dict
-            return False
-
-    def registerUtility(self, provided, name, component, info, factory):
-        subscribed = self._is_utility_subscribed(provided, component)
-
-        self._utility_registrations[
-            (provided, name)
-        ] = component, info, factory
-        self._utilities.register((), provided, name, component)
-
-        if not subscribed:
-            self._utilities.subscribe((), provided, component)
-
-        self.__cache_utility(provided, component)
-
-    def unregisterUtility(self, provided, name, component):
-        del self._utility_registrations[(provided, name)]
-        self._utilities.unregister((), provided, name)
-
-        subscribed = self.__uncache_utility(provided, component)
-
-        if not subscribed:
-            self._utilities.unsubscribe((), provided, component)
-
-
-@implementer(IComponents)
-class Components:
-
-    _v_utility_registrations_cache = None
-
-    def __init__(self, name='', bases=()):
-        # __init__ is used for test cleanup as well as initialization.
-        # XXX add a separate API for test cleanup.
-        assert isinstance(name, str)
-        self.__name__ = name
-        self._init_registries()
-        self._init_registrations()
-        self.__bases__ = tuple(bases)
-        self._v_utility_registrations_cache = None
-
-    def __repr__(self):
-        return f"<{self.__class__.__name__} {self.__name__}>"
-
-    def __reduce__(self):
-        # Mimic what a persistent.Persistent object does and elide
-        # _v_ attributes so that they don't get saved in ZODB.
-        # This allows us to store things that cannot be pickled in such
-        # attributes.
-        reduction = super().__reduce__()
-        # (callable, args, state, listiter, dictiter)
-        # We assume the state is always a dict; the last three items
-        # are technically optional and can be missing or None.
-        filtered_state = {k: v for k, v in reduction[2].items()
-                          if not k.startswith('_v_')}
-        reduction = list(reduction)
-        reduction[2] = filtered_state
-        return tuple(reduction)
-
-    def _init_registries(self):
-        # Subclasses have never been required to call this method
-        # if they override it, merely to fill in these two attributes.
-        self.adapters = AdapterRegistry()
-        self.utilities = AdapterRegistry()
-
-    def _init_registrations(self):
-        self._utility_registrations = {}
-        self._adapter_registrations = {}
-        self._subscription_registrations = []
-        self._handler_registrations = []
-
-    @property
-    def _utility_registrations_cache(self):
-        # We use a _v_ attribute internally so that data aren't saved in ZODB,
-        # because this object cannot be pickled.
-        cache = self._v_utility_registrations_cache
-        if (
-            cache is None or
-            cache._utilities is not self.utilities or
-            cache._utility_registrations is not self._utility_registrations
-        ):
-            cache = self._v_utility_registrations_cache = (
-                _UtilityRegistrations(
-                    self.utilities, self._utility_registrations,
-                )
-            )
-        return cache
-
-    def _getBases(self):
-        # Subclasses might override
-        return self.__dict__.get('__bases__', ())
-
-    def _setBases(self, bases):
-        # Subclasses might override
-        self.adapters.__bases__ = tuple([
-            base.adapters for base in bases])
-        self.utilities.__bases__ = tuple([
-            base.utilities for base in bases])
-        self.__dict__['__bases__'] = tuple(bases)
-
-    __bases__ = property(
-        lambda self: self._getBases(),
-        lambda self, bases: self._setBases(bases),
-    )
-
-    def registerUtility(self, component=None, provided=None, name='',
-                        info='', event=True, factory=None):
-        if factory:
-            if component:
-                raise TypeError("Can't specify factory and component.")
-            component = factory()
-
-        if provided is None:
-            provided = _getUtilityProvided(component)
-
-        if name == '':
-            name = _getName(component)
-
-        reg = self._utility_registrations.get((provided, name))
-        if reg is not None:
-            if reg[:2] == (component, info):
-                # already registered
-                return
-            self.unregisterUtility(reg[0], provided, name)
-
-        self._utility_registrations_cache.registerUtility(
-            provided, name, component, info, factory)
-
-        if event:
-            notify(Registered(
-                UtilityRegistration(
-                    self, provided, name, component, info, factory)
-            ))
-
-    def unregisterUtility(self, component=None, provided=None, name='',
-                          factory=None):
-        if factory:
-            if component:
-                raise TypeError("Can't specify factory and component.")
-            component = factory()
-
-        if provided is None:
-            if component is None:
-                raise TypeError("Must specify one of component, factory and "
-                                "provided")
-            provided = _getUtilityProvided(component)
-
-        old = self._utility_registrations.get((provided, name))
-        if (old is None) or ((component is not None) and
-                             (component != old[0])):
-            return False
-
-        if component is None:
-            component = old[0]
-
-        # Note that component is now the old thing registered
-        self._utility_registrations_cache.unregisterUtility(
-            provided, name, component)
-
-        notify(Unregistered(
-            UtilityRegistration(self, provided, name, component, *old[1:])
-        ))
-
-        return True
-
-    def registeredUtilities(self):
-        for ((provided, name), data
-             ) in iter(self._utility_registrations.items()):
-            yield UtilityRegistration(self, provided, name, *data)
-
-    def queryUtility(self, provided, name='', default=None):
-        return self.utilities.lookup((), provided, name, default)
-
-    def getUtility(self, provided, name=''):
-        utility = self.utilities.lookup((), provided, name)
-        if utility is None:
-            raise ComponentLookupError(provided, name)
-        return utility
-
-    def getUtilitiesFor(self, interface):
-        yield from self.utilities.lookupAll((), interface)
-
-    def getAllUtilitiesRegisteredFor(self, interface):
-        return self.utilities.subscriptions((), interface)
-
-    def registerAdapter(self, factory, required=None, provided=None,
-                        name='', info='', event=True):
-        if provided is None:
-            provided = _getAdapterProvided(factory)
-        required = _getAdapterRequired(factory, required)
-        if name == '':
-            name = _getName(factory)
-        self._adapter_registrations[(required, provided, name)
-                                    ] = factory, info
-        self.adapters.register(required, provided, name, factory)
-
-        if event:
-            notify(Registered(
-                AdapterRegistration(
-                    self, required, provided, name, factory, info
-                )
-            ))
-
-    def unregisterAdapter(self, factory=None,
-                          required=None, provided=None, name='',
-                          ):
-        if provided is None:
-            if factory is None:
-                raise TypeError("Must specify one of factory and provided")
-            provided = _getAdapterProvided(factory)
-
-        if (required is None) and (factory is None):
-            raise TypeError("Must specify one of factory and required")
-
-        required = _getAdapterRequired(factory, required)
-        old = self._adapter_registrations.get((required, provided, name))
-        if (old is None) or ((factory is not None) and
-                             (factory != old[0])):
-            return False
-
-        del self._adapter_registrations[(required, provided, name)]
-        self.adapters.unregister(required, provided, name)
-
-        notify(Unregistered(
-            AdapterRegistration(self, required, provided, name, *old)
-        ))
-
-        return True
-
-    def registeredAdapters(self):
-        for ((required, provided, name), (component, info)
-             ) in iter(self._adapter_registrations.items()):
-            yield AdapterRegistration(self, required, provided, name,
-                                      component, info)
-
-    def queryAdapter(self, object, interface, name='', default=None):
-        return self.adapters.queryAdapter(object, interface, name, default)
-
-    def getAdapter(self, object, interface, name=''):
-        adapter = self.adapters.queryAdapter(object, interface, name)
-        if adapter is None:
-            raise ComponentLookupError(object, interface, name)
-        return adapter
-
-    def queryMultiAdapter(self, objects, interface, name='',
-                          default=None):
-        return self.adapters.queryMultiAdapter(
-            objects, interface, name, default)
-
-    def getMultiAdapter(self, objects, interface, name=''):
-        adapter = self.adapters.queryMultiAdapter(objects, interface, name)
-        if adapter is None:
-            raise ComponentLookupError(objects, interface, name)
-        return adapter
-
-    def getAdapters(self, objects, provided):
-        for name, factory in self.adapters.lookupAll(
-            list(map(providedBy, objects)), provided,
-        ):
-            adapter = factory(*objects)
-            if adapter is not None:
-                yield name, adapter
-
-    def registerSubscriptionAdapter(self,
-                                    factory, required=None, provided=None,
-                                    name='', info='',
-                                    event=True):
-        if name:
-            raise TypeError("Named subscribers are not yet supported")
-        if provided is None:
-            provided = _getAdapterProvided(factory)
-        required = _getAdapterRequired(factory, required)
-        self._subscription_registrations.append(
-            (required, provided, name, factory, info)
-        )
-        self.adapters.subscribe(required, provided, factory)
-
-        if event:
-            notify(Registered(
-                SubscriptionRegistration(
-                    self, required, provided, name, factory, info,
-                )
-            ))
-
-    def registeredSubscriptionAdapters(self):
-        for data in self._subscription_registrations:
-            yield SubscriptionRegistration(self, *data)
-
-    def unregisterSubscriptionAdapter(
-        self, factory=None, required=None, provided=None, name='',
-    ):
-        if name:
-            raise TypeError("Named subscribers are not yet supported")
-        if provided is None:
-            if factory is None:
-                raise TypeError("Must specify one of factory and provided")
-            provided = _getAdapterProvided(factory)
-
-        if (required is None) and (factory is None):
-            raise TypeError("Must specify one of factory and required")
-
-        required = _getAdapterRequired(factory, required)
-
-        if factory is None:
-            new = [(r, p, n, f, i)
-                   for (r, p, n, f, i)
-                   in self._subscription_registrations
-                   if not (r == required and p == provided)
-                   ]
-        else:
-            new = [(r, p, n, f, i)
-                   for (r, p, n, f, i)
-                   in self._subscription_registrations
-                   if not (r == required and p == provided and f == factory)
-                   ]
-
-        if len(new) == len(self._subscription_registrations):
-            return False
-
-        self._subscription_registrations[:] = new
-        self.adapters.unsubscribe(required, provided, factory)
-
-        notify(Unregistered(
-            SubscriptionRegistration(
-                self, required, provided, name, factory, '',
-            )
-        ))
-
-        return True
-
-    def subscribers(self, objects, provided):
-        return self.adapters.subscribers(objects, provided)
-
-    def registerHandler(self,
-                        factory, required=None,
-                        name='', info='',
-                        event=True):
-        if name:
-            raise TypeError("Named handlers are not yet supported")
-        required = _getAdapterRequired(factory, required)
-        self._handler_registrations.append(
-            (required, name, factory, info)
-        )
-        self.adapters.subscribe(required, None, factory)
-
-        if event:
-            notify(Registered(
-                HandlerRegistration(self, required, name, factory, info)
-            ))
-
-    def registeredHandlers(self):
-        for data in self._handler_registrations:
-            yield HandlerRegistration(self, *data)
-
-    def unregisterHandler(self, factory=None, required=None, name=''):
-        if name:
-            raise TypeError("Named subscribers are not yet supported")
-
-        if (required is None) and (factory is None):
-            raise TypeError("Must specify one of factory and required")
-
-        required = _getAdapterRequired(factory, required)
-
-        if factory is None:
-            new = [(r, n, f, i)
-                   for (r, n, f, i)
-                   in self._handler_registrations
-                   if r != required
-                   ]
-        else:
-            new = [(r, n, f, i)
-                   for (r, n, f, i)
-                   in self._handler_registrations
-                   if not (r == required and f == factory)
-                   ]
-
-        if len(new) == len(self._handler_registrations):
-            return False
-
-        self._handler_registrations[:] = new
-        self.adapters.unsubscribe(required, None, factory)
-
-        notify(Unregistered(
-            HandlerRegistration(self, required, name, factory, '')
-        ))
-
-        return True
-
-    def handle(self, *objects):
-        self.adapters.subscribers(objects, None)
-
-    def rebuildUtilityRegistryFromLocalCache(self, rebuild=False):
-        """
-        Emergency maintenance method to rebuild the ``.utilities``
-        registry from the local copy maintained in this object, or
-        detect the need to do so.
-
-        Most users will never need to call this, but it can be helpful
-        in the event of suspected corruption.
-
-        By default, this method only checks for corruption. To make it
-        actually rebuild the registry, pass `True` for *rebuild*.
-
-        :param bool rebuild: If set to `True` (not the default),
-           this method will actually register and subscribe utilities
-           in the registry as needed to synchronize with the local cache.
-
-        :return: A dictionary that's meant as diagnostic data. The keys
-           and values may change over time. When called with a false
-           *rebuild*, the keys ``"needed_registered"`` and
-           ``"needed_subscribed"`` will be non-zero if any corruption was
-           detected, but that will not be corrected.
-
-        .. versionadded:: 5.3.0
-        """
-        regs = dict(self._utility_registrations)
-        utils = self.utilities
-        needed_registered = 0
-        did_not_register = 0
-        needed_subscribed = 0
-        did_not_subscribe = 0
-
-        # Avoid the expensive change process during this; we'll call
-        # it once at the end if needed.
-        assert 'changed' not in utils.__dict__
-        utils.changed = lambda _: None
-
-        if rebuild:
-            register = utils.register
-            subscribe = utils.subscribe
-        else:
-            register = subscribe = lambda *args: None
-
-        try:
-            for (provided, name), (value, _info, _factory) in regs.items():
-                if utils.registered((), provided, name) != value:
-                    register((), provided, name, value)
-                    needed_registered += 1
-                else:
-                    did_not_register += 1
-
-                if utils.subscribed((), provided, value) is None:
-                    needed_subscribed += 1
-                    subscribe((), provided, value)
-                else:
-                    did_not_subscribe += 1
-        finally:
-            del utils.changed
-            if rebuild and (needed_subscribed or needed_registered):
-                utils.changed(utils)
-
-        return {
-            'needed_registered': needed_registered,
-            'did_not_register': did_not_register,
-            'needed_subscribed': needed_subscribed,
-            'did_not_subscribe': did_not_subscribe
-        }
-
-
-def _getName(component):
-    try:
-        return component.__component_name__
-    except AttributeError:
-        return ''
-
-
-def _getUtilityProvided(component):
-    provided = list(providedBy(component))
-    if len(provided) == 1:
-        return provided[0]
-    raise TypeError(
-        "The utility doesn't provide a single interface "
-        "and no provided interface was specified."
-    )
-
-
-def _getAdapterProvided(factory):
-    provided = list(implementedBy(factory))
-    if len(provided) == 1:
-        return provided[0]
-    raise TypeError(
-        "The adapter factory doesn't implement a single interface "
-        "and no provided interface was specified."
-    )
-
-
-def _getAdapterRequired(factory, required):
-    if required is None:
-        try:
-            required = factory.__component_adapts__
-        except AttributeError:
-            raise TypeError(
-                "The adapter factory doesn't have a __component_adapts__ "
-                "attribute and no required specifications were specified"
-            )
-    elif ISpecification.providedBy(required):
-        raise TypeError(
-            "the required argument should be a list of "
-            "interfaces, not a single interface"
-        )
-
-    result = []
-    for r in required:
-        if r is None:
-            r = Interface
-        elif not ISpecification.providedBy(r):
-            if isinstance(r, type):
-                r = implementedBy(r)
-            else:
-                raise TypeError(
-                    "Required specification must be a "
-                    "specification or class, not %r" % type(r)
-                )
-        result.append(r)
-    return tuple(result)
-
-
-@implementer(IUtilityRegistration)
-class UtilityRegistration:
-
-    def __init__(self, registry, provided, name, component, doc, factory=None):
-        self.registry = registry
-        self.provided = provided
-        self.name = name
-        self.component = component
-        self.info = doc
-        self.factory = factory
-
-    def __repr__(self):
-        return '{}({!r}, {}, {!r}, {}, {!r}, {!r})'.format(
-            self.__class__.__name__,
-            self.registry,
-            getattr(self.provided, '__name__', None), self.name,
-            getattr(self.component, '__name__', repr(self.component)),
-            self.factory, self.info,
-        )
-
-    def __hash__(self):
-        return id(self)
-
-    def __eq__(self, other):
-        return repr(self) == repr(other)
-
-    def __ne__(self, other):
-        return repr(self) != repr(other)
-
-    def __lt__(self, other):
-        return repr(self) < repr(other)
-
-    def __le__(self, other):
-        return repr(self) <= repr(other)
-
-    def __gt__(self, other):
-        return repr(self) > repr(other)
-
-    def __ge__(self, other):
-        return repr(self) >= repr(other)
-
-
-@implementer(IAdapterRegistration)
-class AdapterRegistration:
-
-    def __init__(self, registry, required, provided, name, component, doc):
-        (self.registry, self.required, self.provided, self.name,
-         self.factory, self.info
-         ) = registry, required, provided, name, component, doc
-
-    def __repr__(self):
-        return '{}({!r}, {}, {}, {!r}, {}, {!r})'.format(
-            self.__class__.__name__,
-            self.registry,
-            '[' + ", ".join([r.__name__ for r in self.required]) + ']',
-            getattr(self.provided, '__name__', None), self.name,
-            getattr(self.factory, '__name__', repr(self.factory)), self.info,
-        )
-
-    def __hash__(self):
-        return id(self)
-
-    def __eq__(self, other):
-        return repr(self) == repr(other)
-
-    def __ne__(self, other):
-        return repr(self) != repr(other)
-
-    def __lt__(self, other):
-        return repr(self) < repr(other)
-
-    def __le__(self, other):
-        return repr(self) <= repr(other)
-
-    def __gt__(self, other):
-        return repr(self) > repr(other)
-
-    def __ge__(self, other):
-        return repr(self) >= repr(other)
-
-
-@implementer_only(ISubscriptionAdapterRegistration)
-class SubscriptionRegistration(AdapterRegistration):
-    pass
-
-
-@implementer_only(IHandlerRegistration)
-class HandlerRegistration(AdapterRegistration):
-
-    def __init__(self, registry, required, name, handler, doc):
-        (self.registry, self.required, self.name, self.handler, self.info
-         ) = registry, required, name, handler, doc
-
-    @property
-    def factory(self):
-        return self.handler
-
-    provided = None
-
-    def __repr__(self):
-        return '{}({!r}, {}, {!r}, {}, {!r})'.format(
-            self.__class__.__name__,
-            self.registry,
-            '[' + ", ".join([r.__name__ for r in self.required]) + ']',
-            self.name,
-            getattr(self.factory, '__name__', repr(self.factory)), self.info,
-        )
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/ro.py b/llmlab/lib/python3.12/site-packages/zope/interface/ro.py
deleted file mode 100644
index 5233e49..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/ro.py
+++ /dev/null
@@ -1,722 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""
-Compute a resolution order for an object and its bases.
-
-.. versionchanged:: 5.0
-   The resolution order is now based on the same C3 order that Python
-   uses for classes. In complex instances of multiple inheritance, this
-   may result in a different ordering.
-
-   In older versions, the ordering wasn't required to be C3 compliant,
-   and for backwards compatibility, it still isn't. If the ordering
-   isn't C3 compliant (if it is *inconsistent*), zope.interface will
-   make a best guess to try to produce a reasonable resolution order.
-   Still (just as before), the results in such cases may be
-   surprising.
-
-.. rubric:: Environment Variables
-
-Due to the change in 5.0, certain environment variables can be used to control
-errors and warnings about inconsistent resolution orders. They are listed in
-priority order, with variables at the bottom generally overriding variables
-above them.
-
-ZOPE_INTERFACE_WARN_BAD_IRO
-    If this is set to "1", then if there is at least one inconsistent
-    resolution order discovered, a warning
-    (:class:`InconsistentResolutionOrderWarning`) will be issued. Use the
-    usual warning mechanisms to control this behaviour. The warning text will
-    contain additional information on debugging.
-
-ZOPE_INTERFACE_TRACK_BAD_IRO
-    If this is set to "1", then zope.interface will log information about each
-    inconsistent resolution order discovered, and keep those details in memory
-    in this module for later inspection.
-
-ZOPE_INTERFACE_STRICT_IRO
-    If this is set to "1", any attempt to use :func:`ro` that would produce a
-    non-C3 ordering will fail by raising
-    :class:`InconsistentResolutionOrderError`.
-
-.. important::
-
-   ``ZOPE_INTERFACE_STRICT_IRO`` is intended to become the default in the
-   future.
-
-There are two environment variables that are independent.
-
-ZOPE_INTERFACE_LOG_CHANGED_IRO
-    If this is set to "1", then if the C3 resolution order is different from
-    the legacy resolution order for any given object, a message explaining the
-    differences will be logged. This is intended to be used for debugging
-    complicated IROs.
-
-ZOPE_INTERFACE_USE_LEGACY_IRO
-    If this is set to "1", then the C3 resolution order will *not* be used.
-    The legacy IRO will be used instead. This is a temporary measure and will
-    be removed in the future. It is intended to help during the transition.
-    It implies ``ZOPE_INTERFACE_LOG_CHANGED_IRO``.
-
-.. rubric:: Debugging Behaviour Changes in zope.interface 5
-
-Most behaviour changes from zope.interface 4 to 5 are related to
-inconsistent resolution orders. ``ZOPE_INTERFACE_STRICT_IRO`` is the
-most effective tool to find such inconsistent resolution orders, and
-we recommend running your code with this variable set if at all
-possible. Doing so will ensure that all interface resolution orders
-are consistent, and if they're not, will immediately point the way to
-where this is violated.
-
-Occasionally, however, this may not be enough. This is because in some
-cases, a C3 ordering can be found (the resolution order is fully
-consistent) that is substantially different from the ad-hoc legacy
-ordering. In such cases, you may find that you get an unexpected value
-returned when adapting one or more objects to an interface. To debug
-this, *also* enable ``ZOPE_INTERFACE_LOG_CHANGED_IRO`` and examine the
-output. The main thing to look for is changes in the relative
-positions of interfaces for which there are registered adapters.
-"""
-__docformat__ = 'restructuredtext'
-
-import warnings
-
-
-__all__ = [
-    'ro',
-    'InconsistentResolutionOrderError',
-    'InconsistentResolutionOrderWarning',
-]
-
-__logger = None
-
-
-def _logger():
-    global __logger  # pylint:disable=global-statement
-    if __logger is None:
-        import logging
-        __logger = logging.getLogger(__name__)
-    return __logger
-
-
-def _legacy_mergeOrderings(orderings):
-    """Merge multiple orderings so that within-ordering order is preserved
-
-    Orderings are constrained in such a way that if an object appears
-    in two or more orderings, then the suffix that begins with the
-    object must be in both orderings.
-
-    For example:
-
-    >>> _legacy_mergeOrderings([
-    ... ['x', 'y', 'z'],
-    ... ['q', 'z'],
-    ... [1, 3, 5],
-    ... ['z']
-    ... ])
-    ['x', 'y', 'q', 1, 3, 5, 'z']
-
-    """
-
-    seen = set()
-    result = []
-    for ordering in reversed(orderings):
-        for o in reversed(ordering):
-            if o not in seen:
-                seen.add(o)
-                result.insert(0, o)
-
-    return result
-
-
-def _legacy_flatten(begin):
-    result = [begin]
-    i = 0
-    for ob in iter(result):
-        i += 1
-        # The recursive calls can be avoided by inserting the base classes
-        # into the dynamically growing list directly after the currently
-        # considered object;  the iterator makes sure this will keep working
-        # in the future, since it cannot rely on the length of the list
-        # by definition.
-        result[i:i] = ob.__bases__
-    return result
-
-
-def _legacy_ro(ob):
-    return _legacy_mergeOrderings([_legacy_flatten(ob)])
-
-###
-# Compare base objects using identity, not equality. This matches what
-# the CPython MRO algorithm does, and is *much* faster to boot: that,
-# plus some other small tweaks makes the difference between 25s and 6s
-# in loading 446 plone/zope interface.py modules (1925 InterfaceClass,
-# 1200 Implements, 1100 ClassProvides objects)
-###
-
-
-class InconsistentResolutionOrderWarning(PendingDeprecationWarning):
-    """
-    The warning issued when an invalid IRO is requested.
-    """
-
-
-class InconsistentResolutionOrderError(TypeError):
-    """
-    The error raised when an invalid IRO is requested in strict mode.
-    """
-
-    def __init__(self, c3, base_tree_remaining):
-        self.C = c3.leaf
-        base_tree = c3.base_tree
-        self.base_ros = {
-            base: base_tree[i + 1]
-            for i, base in enumerate(self.C.__bases__)
-        }
-        # Unfortunately, this doesn't necessarily directly match
-        # up to any transformation on C.__bases__, because
-        # if any were fully used up, they were removed already.
-        self.base_tree_remaining = base_tree_remaining
-
-        TypeError.__init__(self)
-
-    def __str__(self):
-        import pprint
-        return (
-            "{}: For object {!r}.\nBase ROs:\n{}\nConflict Location:\n{}"
-        ).format(
-            self.__class__.__name__,
-            self.C,
-            pprint.pformat(self.base_ros),
-            pprint.pformat(self.base_tree_remaining),
-        )
-
-
-class _NamedBool(int):  # cannot actually inherit bool
-
-    def __new__(cls, val, name):
-        inst = super(cls, _NamedBool).__new__(cls, val)
-        inst.__name__ = name
-        return inst
-
-
-class _ClassBoolFromEnv:
-    """
-    Non-data descriptor that reads a transformed environment variable
-    as a boolean, and caches the result in the class.
-    """
-
-    def __get__(self, inst, klass):
-        import os
-        for cls in klass.__mro__:
-            my_name = None
-            for k in dir(klass):
-                if k in cls.__dict__ and cls.__dict__[k] is self:
-                    my_name = k
-                    break
-            if my_name is not None:
-                break
-        else:  # pragma: no cover
-            raise RuntimeError("Unable to find self")
-
-        env_name = 'ZOPE_INTERFACE_' + my_name
-        val = os.environ.get(env_name, '') == '1'
-        val = _NamedBool(val, my_name)
-        setattr(klass, my_name, val)
-        setattr(klass, 'ORIG_' + my_name, self)
-        return val
-
-
-class _StaticMRO:
-    # A previously resolved MRO, supplied by the caller.
-    # Used in place of calculating it.
-
-    had_inconsistency = None  # We don't know...
-
-    def __init__(self, C, mro):
-        self.leaf = C
-        self.__mro = tuple(mro)
-
-    def mro(self):
-        return list(self.__mro)
-
-
-_INCONSISTENT_RESOLUTION_ORDER = """\
-An inconsistent resolution order is being requested.  (Interfaces should
-follow the Python class rules known as C3.) For backwards compatibility,
-zope.interface will allow this, making the best guess it can to produce as
-meaningful an order as possible.  In the future this might be an error. Set
-the warning filter to error, or set the environment variable
-'ZOPE_INTERFACE_TRACK_BAD_IRO' to '1' and examine ro.C3.BAD_IROS to debug, or
-set 'ZOPE_INTERFACE_STRICT_IRO' to raise exceptions."""
-
-
-class C3:
-    # Holds the shared state during computation of an MRO.
-
-    @staticmethod
-    def resolver(C, strict, base_mros):
-        strict = strict if strict is not None else C3.STRICT_IRO
-        factory = C3
-        if strict:
-            factory = _StrictC3
-        elif C3.TRACK_BAD_IRO:
-            factory = _TrackingC3
-
-        memo = {}
-        base_mros = base_mros or {}
-        for base, mro in base_mros.items():
-            assert base in C.__bases__
-            memo[base] = _StaticMRO(base, mro)
-
-        return factory(C, memo)
-
-    __mro = None
-    __legacy_ro = None
-    direct_inconsistency = False
-
-    def __init__(self, C, memo):
-        self.leaf = C
-        self.memo = memo
-        kind = self.__class__
-
-        base_resolvers = []
-        for base in C.__bases__:
-            if base not in memo:
-                resolver = kind(base, memo)
-                memo[base] = resolver
-            base_resolvers.append(memo[base])
-
-        self.base_tree = [
-            [C]
-        ] + [
-            memo[base].mro() for base in C.__bases__
-        ] + [
-            list(C.__bases__)
-        ]
-
-        self.bases_had_inconsistency = any(
-            base.had_inconsistency for base in base_resolvers
-        )
-
-        if len(C.__bases__) == 1:
-            self.__mro = [C] + memo[C.__bases__[0]].mro()
-
-    @property
-    def had_inconsistency(self):
-        return self.direct_inconsistency or self.bases_had_inconsistency
-
-    @property
-    def legacy_ro(self):
-        if self.__legacy_ro is None:
-            self.__legacy_ro = tuple(_legacy_ro(self.leaf))
-        return list(self.__legacy_ro)
-
-    TRACK_BAD_IRO = _ClassBoolFromEnv()
-    STRICT_IRO = _ClassBoolFromEnv()
-    WARN_BAD_IRO = _ClassBoolFromEnv()
-    LOG_CHANGED_IRO = _ClassBoolFromEnv()
-    USE_LEGACY_IRO = _ClassBoolFromEnv()
-    BAD_IROS = ()
-
-    def _warn_iro(self):
-        if not self.WARN_BAD_IRO:
-            # For the initial release, one must opt-in to see the warning.
-            # In the future (2021?) seeing at least the first warning will
-            # be the default
-            return
-        warnings.warn(
-            _INCONSISTENT_RESOLUTION_ORDER,
-            InconsistentResolutionOrderWarning,
-        )
-
-    @staticmethod
-    def _can_choose_base(base, base_tree_remaining):
-        # From C3:
-        # nothead = [s for s in nonemptyseqs if cand in s[1:]]
-        for bases in base_tree_remaining:
-            if not bases or bases[0] is base:
-                continue
-
-            for b in bases:
-                if b is base:
-                    return False
-        return True
-
-    @staticmethod
-    def _nonempty_bases_ignoring(base_tree, ignoring):
-        return list(filter(None, [
-            [b for b in bases if b is not ignoring]
-            for bases
-            in base_tree
-        ]))
-
-    def _choose_next_base(self, base_tree_remaining):
-        """
-        Return the next base.
-
-        The return value will either fit the C3 constraints or be our best
-        guess about what to do. If we cannot guess, this may raise an
-        exception.
-        """
-        base = self._find_next_C3_base(base_tree_remaining)
-        if base is not None:
-            return base
-        return self._guess_next_base(base_tree_remaining)
-
-    def _find_next_C3_base(self, base_tree_remaining):
-        """Return the next base that fits the constraints
-
-        Return ``None`` if there isn't one.
-        """
-        for bases in base_tree_remaining:
-            base = bases[0]
-            if self._can_choose_base(base, base_tree_remaining):
-                return base
-        return None
-
-    class _UseLegacyRO(Exception):
-        pass
-
-    def _guess_next_base(self, base_tree_remaining):
-        # Narf. We may have an inconsistent order (we won't know for
-        # sure until we check all the bases). Python cannot create
-        # classes like this:
-        #
-        # class B1:
-        #   pass
-        # class B2(B1):
-        #   pass
-        # class C(B1, B2): # -> TypeError; this is like saying C(B1, B2, B1).
-        #  pass
-        #
-        # However, older versions of zope.interface were fine with this order.
-        # A good example is ``providedBy(IOError())``. Because of the way
-        # ``classImplements`` works, it winds up with ``__bases__`` ==
-        # ``[IEnvironmentError, IIOError, IOSError, ]`` (on Python 3). But ``IEnvironmentError`` is a base of
-        # both ``IIOError`` and ``IOSError``. Previously, we would get a
-        # resolution order of ``[IIOError, IOSError, IEnvironmentError,
-        # IStandardError, IException, Interface]`` but the standard Python
-        # algorithm would forbid creating that order entirely.
-
-        # Unlike Python's MRO, we attempt to resolve the issue. A few
-        # heuristics have been tried. One was:
-        #
-        # Strip off the first (highest priority) base of each direct
-        # base one at a time and seeing if we can come to an agreement
-        # with the other bases. (We're trying for a partial ordering
-        # here.) This often resolves cases (such as the IOSError case
-        # above), and frequently produces the same ordering as the
-        # legacy MRO did. If we looked at all the highest priority
-        # bases and couldn't find any partial ordering, then we strip
-        # them *all* out and begin the C3 step again. We take care not
-        # to promote a common root over all others.
-        #
-        # If we only did the first part, stripped off the first
-        # element of the first item, we could resolve simple cases.
-        # But it tended to fail badly. If we did the whole thing, it
-        # could be extremely painful from a performance perspective
-        # for deep/wide things like Zope's OFS.SimpleItem.Item. Plus,
-        # anytime you get ExtensionClass.Base into the mix, you're
-        # likely to wind up in trouble, because it messes with the MRO
-        # of classes. Sigh.
-        #
-        # So now, we fall back to the old linearization (fast to compute).
-        self._warn_iro()
-        self.direct_inconsistency = InconsistentResolutionOrderError(
-            self, base_tree_remaining,
-        )
-        raise self._UseLegacyRO
-
-    def _merge(self):
-        # Returns a merged *list*.
-        result = self.__mro = []
-        base_tree_remaining = self.base_tree
-        base = None
-        while 1:
-            # Take last picked base out of the base tree wherever it is.
-            # This differs slightly from the standard Python MRO and is needed
-            # because we have no other step that prevents duplicates
-            # from coming in (e.g., in the inconsistent fallback path)
-            base_tree_remaining = self._nonempty_bases_ignoring(
-                base_tree_remaining, base
-            )
-
-            if not base_tree_remaining:
-                return result
-            try:
-                base = self._choose_next_base(base_tree_remaining)
-            except self._UseLegacyRO:
-                self.__mro = self.legacy_ro
-                return self.legacy_ro
-
-            result.append(base)
-
-    def mro(self):
-        if self.__mro is None:
-            self.__mro = tuple(self._merge())
-        return list(self.__mro)
-
-
-class _StrictC3(C3):
-    __slots__ = ()
-
-    def _guess_next_base(self, base_tree_remaining):
-        raise InconsistentResolutionOrderError(self, base_tree_remaining)
-
-
-class _TrackingC3(C3):
-    __slots__ = ()
-
-    def _guess_next_base(self, base_tree_remaining):
-        import traceback
-        bad_iros = C3.BAD_IROS
-        if self.leaf not in bad_iros:
-            if bad_iros == ():
-                import weakref
-
-                # This is a race condition, but it doesn't matter much.
-                bad_iros = C3.BAD_IROS = weakref.WeakKeyDictionary()
-            bad_iros[self.leaf] = t = (
-                InconsistentResolutionOrderError(self, base_tree_remaining),
-                traceback.format_stack()
-            )
-            _logger().warning("Tracking inconsistent IRO: %s", t[0])
-        return C3._guess_next_base(self, base_tree_remaining)
-
-
-class _ROComparison:
-    # Exists to compute and print a pretty string comparison
-    # for differing ROs.
-    # Since we're used in a logging context, and may actually never be printed,
-    # this is a class so we can defer computing the diff until asked.
-
-    # Components we use to build up the comparison report
-    class Item:
-        prefix = '  '
-
-        def __init__(self, item):
-            self.item = item
-
-        def __str__(self):
-            return "{}{}".format(
-                self.prefix,
-                self.item,
-            )
-
-    class Deleted(Item):
-        prefix = '- '
-
-    class Inserted(Item):
-        prefix = '+ '
-
-    Empty = str
-
-    class ReplacedBy:  # pragma: no cover
-        prefix = '- '
-        suffix = ''
-
-        def __init__(self, chunk, total_count):
-            self.chunk = chunk
-            self.total_count = total_count
-
-        def __iter__(self):
-            lines = [
-                self.prefix + str(item) + self.suffix
-                for item in self.chunk
-            ]
-            while len(lines) < self.total_count:
-                lines.append('')
-
-            return iter(lines)
-
-    class Replacing(ReplacedBy):
-        prefix = "+ "
-        suffix = ''
-
-    _c3_report = None
-    _legacy_report = None
-
-    def __init__(self, c3, c3_ro, legacy_ro):
-        self.c3 = c3
-        self.c3_ro = c3_ro
-        self.legacy_ro = legacy_ro
-
-    def __move(self, from_, to_, chunk, operation):
-        for x in chunk:
-            to_.append(operation(x))
-            from_.append(self.Empty())
-
-    def _generate_report(self):
-        if self._c3_report is None:
-            import difflib
-
-            # The opcodes we get describe how to turn 'a' into 'b'. So
-            # the old one (legacy) needs to be first ('a')
-            matcher = difflib.SequenceMatcher(None, self.legacy_ro, self.c3_ro)
-            # The reports are equal length sequences. We're going for a
-            # side-by-side diff.
-            self._c3_report = c3_report = []
-            self._legacy_report = legacy_report = []
-            for opcode, leg1, leg2, c31, c32 in matcher.get_opcodes():
-                c3_chunk = self.c3_ro[c31:c32]
-                legacy_chunk = self.legacy_ro[leg1:leg2]
-
-                if opcode == 'equal':
-                    # Guaranteed same length
-                    c3_report.extend(self.Item(x) for x in c3_chunk)
-                    legacy_report.extend(self.Item(x) for x in legacy_chunk)
-                if opcode == 'delete':
-                    # Guaranteed same length
-                    assert not c3_chunk
-                    self.__move(
-                        c3_report, legacy_report, legacy_chunk, self.Deleted,
-                    )
-                if opcode == 'insert':
-                    # Guaranteed same length
-                    assert not legacy_chunk
-                    self.__move(
-                        legacy_report, c3_report, c3_chunk, self.Inserted,
-                    )
-                if opcode == 'replace':  # pragma: no cover
-                    # (How do you make it output this?)
-                    # Either side could be longer.
-                    chunk_size = max(len(c3_chunk), len(legacy_chunk))
-                    c3_report.extend(self.Replacing(c3_chunk, chunk_size))
-                    legacy_report.extend(
-                        self.ReplacedBy(legacy_chunk, chunk_size),
-                    )
-
-        return self._c3_report, self._legacy_report
-
-    @property
-    def _inconsistent_label(self):
-        inconsistent = []
-        if self.c3.direct_inconsistency:
-            inconsistent.append('direct')
-        if self.c3.bases_had_inconsistency:
-            inconsistent.append('bases')
-        return '+'.join(inconsistent) if inconsistent else 'no'
-
-    def __str__(self):
-        c3_report, legacy_report = self._generate_report()
-        assert len(c3_report) == len(legacy_report)
-
-        left_lines = [str(x) for x in legacy_report]
-        right_lines = [str(x) for x in c3_report]
-
-        # We have the same number of lines in the report; this is not
-        # necessarily the same as the number of items in either RO.
-        assert len(left_lines) == len(right_lines)
-
-        padding = ' ' * 2
-        max_left = max(len(x) for x in left_lines)
-        max_right = max(len(x) for x in right_lines)
-
-        left_title = f'Legacy RO (len={len(self.legacy_ro)})'
-
-        right_title = 'C3 RO (len={}; inconsistent={})'.format(
-            len(self.c3_ro),
-            self._inconsistent_label,
-        )
-        lines = [
-            (
-                padding +
-                left_title.ljust(max_left) +
-                padding +
-                right_title.ljust(max_right)
-            ),
-            padding + '=' * (max_left + len(padding) + max_right)
-        ]
-        lines += [
-            padding + left.ljust(max_left) + padding + right
-            for left, right in zip(left_lines, right_lines)
-        ]
-
-        return '\n'.join(lines)
-
-
-# Set to `Interface` once it is defined. This is used to
-# avoid logging false positives about changed ROs.
-_ROOT = None
-
-
-def ro(
-    C, strict=None, base_mros=None, log_changed_ro=None, use_legacy_ro=None,
-):
-    """
-    ro(C) -> list
-
-    Compute the precedence list (mro) according to C3.
-
-    :return: A fresh `list` object.
-
-    .. versionchanged:: 5.0.0
-       Add the *strict*, *log_changed_ro* and *use_legacy_ro*
-       keyword arguments. These are provisional and likely to be
-       removed in the future. They are most useful for testing.
-    """
-    # The ``base_mros`` argument is for internal optimization and
-    # not documented.
-    resolver = C3.resolver(C, strict, base_mros)
-    mro = resolver.mro()
-
-    log_changed = (
-        log_changed_ro if log_changed_ro is not None
-        else resolver.LOG_CHANGED_IRO
-    )
-    use_legacy = (
-        use_legacy_ro if use_legacy_ro is not None
-        else resolver.USE_LEGACY_IRO
-    )
-
-    if log_changed or use_legacy:
-        legacy_ro = resolver.legacy_ro
-        assert isinstance(legacy_ro, list)
-        assert isinstance(mro, list)
-        changed = legacy_ro != mro
-        if changed:
-            # Did only Interface move? The fix for issue #8 made that
-            # somewhat common. It's almost certainly not a problem, though,
-            # so allow ignoring it.
-            legacy_without_root = [x for x in legacy_ro if x is not _ROOT]
-            mro_without_root = [x for x in mro if x is not _ROOT]
-            changed = legacy_without_root != mro_without_root
-
-        if changed:
-            comparison = _ROComparison(resolver, mro, legacy_ro)
-            _logger().warning(
-                "Object %r has different legacy and C3 MROs:\n%s",
-                C, comparison
-            )
-        if resolver.had_inconsistency and legacy_ro == mro:
-            comparison = _ROComparison(resolver, mro, legacy_ro)
-            _logger().warning(
-                "Object %r had inconsistent IRO and used the legacy RO:\n%s"
-                "\nInconsistency entered at:\n%s",
-                C, comparison, resolver.direct_inconsistency
-            )
-        if use_legacy:
-            return legacy_ro
-
-    return mro
-
-
-def is_consistent(C):
-    """Is the resolution order for *C*, consistent according to C3.
-
-    Order as computed by :func:`ro`.
-    """
-    return not C3.resolver(C, False, None).had_inconsistency
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__init__.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__init__.py
deleted file mode 100644
index c5fe924..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__init__.py
+++ /dev/null
@@ -1,130 +0,0 @@
-from zope.interface._compat import _should_attempt_c_optimizations
-
-
-class OptimizationTestMixin:
-    """Mixin testing that C optimizations are used when appropriate.
-    """
-
-    def _getTargetClass(self):
-        """Return the implementation in use, without 'Py' or 'Fallback' suffix.
-        """
-        raise NotImplementedError
-
-    def _getFallbackClass(self):
-        """Return the fallback Python implementation.
-        """
-        # Is there an algorithmic way to do this? The C
-        # objects all come from the same module so I don't see how we can
-        # get the Python object from that.
-        raise NotImplementedError
-
-    def test_optimizations(self):
-        used = self._getTargetClass()
-        fallback = self._getFallbackClass()
-
-        if _should_attempt_c_optimizations():
-            self.assertIsNot(used, fallback)
-        else:
-            self.assertIs(used, fallback)
-
-
-class SubclassableMixin:
-
-    def _getTargetClass(self):
-        """Return the implementation in use without 'Py' or 'Fallback' suffix.
-        """
-        raise NotImplementedError
-
-    def test_can_subclass(self):
-        klass = self._getTargetClass()
-
-        class Derived(klass):  # no raise
-            pass
-
-
-class MissingSomeAttrs:
-    """
-    Helper for tests that raises a specific exception
-    for attributes that are missing. This is usually not
-    an AttributeError, and this object is used to test that
-    those errors are not improperly caught and treated like
-    an AttributeError.
-    """
-
-    def __init__(self, exc_kind, **other_attrs):
-        self.__exc_kind = exc_kind
-        d = object.__getattribute__(self, '__dict__')
-        d.update(other_attrs)
-
-    def __getattribute__(self, name):
-        # Note that we ignore objects found in the class dictionary.
-        d = object.__getattribute__(self, '__dict__')
-        try:
-            return d[name]
-        except KeyError:
-            raise d['_MissingSomeAttrs__exc_kind'](name)
-
-    EXCEPTION_CLASSES = (
-        TypeError,
-        RuntimeError,
-        BaseException,
-        ValueError,
-    )
-
-    @classmethod
-    def test_raises(cls, unittest, test_func, expected_missing, **other_attrs):
-        """
-        Loop through various exceptions, calling *test_func* inside a
-        ``assertRaises`` block.
-
-        :param test_func: A callable of one argument, the instance of this
-            class.
-        :param str expected_missing: The attribute that should fail with the
-            exception.  This is used to ensure that we're testing the path we
-            think we are.
-        :param other_attrs: Attributes that should be provided on the test
-            object.  Must not contain *expected_missing*.
-        """
-        assert isinstance(expected_missing, str)
-        assert expected_missing not in other_attrs
-        for exc in cls.EXCEPTION_CLASSES:
-            ob = cls(exc, **other_attrs)
-            with unittest.assertRaises(exc) as ex:
-                test_func(ob)
-
-            unittest.assertEqual(ex.exception.args[0], expected_missing)
-
-        # Now test that the AttributeError for that expected_missing is *not*
-        # raised.
-        ob = cls(AttributeError, **other_attrs)
-        try:
-            test_func(ob)
-        except AttributeError as e:
-            unittest.assertNotIn(expected_missing, str(e))
-        except Exception:  # pylint:disable=broad-except
-            pass
-
-# Be sure cleanup functionality is available; classes that use the adapter hook
-# need to be sure to subclass ``CleanUp``.
-#
-# If zope.component is installed and imported when we run our tests
-# (import chain:
-# zope.testrunner->zope.security->zope.location->zope.component.api)
-# it adds an adapter hook that uses its global site manager. That can cause
-# leakage from one test to another unless its cleanup hooks are run. The
-# symptoms can be odd, especially if one test used C objects and the next used
-# the Python implementation. (For example, you can get strange TypeErrors or
-# find inexplicable comparisons being done.)
-
-
-try:
-    from zope.testing import cleanup
-except ImportError:
-
-    class CleanUp:
-        def cleanUp(self):
-            pass
-
-        setUp = tearDown = cleanUp
-else:
-    CleanUp = cleanup.CleanUp
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/__init__.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 088c845..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/advisory_testing.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/advisory_testing.cpython-312.pyc
deleted file mode 100644
index c1362db..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/advisory_testing.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/dummy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/dummy.cpython-312.pyc
deleted file mode 100644
index 8d02c4c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/dummy.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/idummy.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/idummy.cpython-312.pyc
deleted file mode 100644
index 620000c..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/idummy.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/m1.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/m1.cpython-312.pyc
deleted file mode 100644
index fb6c5f6..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/m1.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/odd.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/odd.cpython-312.pyc
deleted file mode 100644
index 0563066..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/odd.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_adapter.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_adapter.cpython-312.pyc
deleted file mode 100644
index a029002..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_adapter.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_advice.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_advice.cpython-312.pyc
deleted file mode 100644
index 5f2adcf..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_advice.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_compile_flags.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_compile_flags.cpython-312.pyc
deleted file mode 100644
index 01958f2..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_compile_flags.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_declarations.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_declarations.cpython-312.pyc
deleted file mode 100644
index 30b6b3b..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_declarations.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_document.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_document.cpython-312.pyc
deleted file mode 100644
index 6c76f0f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_document.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_element.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_element.cpython-312.pyc
deleted file mode 100644
index 1bd0cdf..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_element.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_exceptions.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_exceptions.cpython-312.pyc
deleted file mode 100644
index 7a22972..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_exceptions.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_interface.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_interface.cpython-312.pyc
deleted file mode 100644
index 956a2fc..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_interface.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_interfaces.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_interfaces.cpython-312.pyc
deleted file mode 100644
index a4ef30f..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_interfaces.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_odd_declarations.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_odd_declarations.cpython-312.pyc
deleted file mode 100644
index e51c94a..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_odd_declarations.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_registry.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_registry.cpython-312.pyc
deleted file mode 100644
index b4e141e..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_registry.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_ro.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_ro.cpython-312.pyc
deleted file mode 100644
index 2caed8d..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_ro.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_sorting.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_sorting.cpython-312.pyc
deleted file mode 100644
index 5c7d0ff..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_sorting.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_verify.cpython-312.pyc b/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_verify.cpython-312.pyc
deleted file mode 100644
index d9c75ee..0000000
Binary files a/llmlab/lib/python3.12/site-packages/zope/interface/tests/__pycache__/test_verify.cpython-312.pyc and /dev/null differ
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/advisory_testing.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/advisory_testing.py
deleted file mode 100644
index 9376955..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/advisory_testing.py
+++ /dev/null
@@ -1,29 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-import sys
-
-from zope.interface.advice import getFrameInfo
-
-
-my_globals = globals()
-
-ClassicClass = None
-
-
-class NewStyleClass:
-    __metaclass__ = type
-    classLevelFrameInfo = getFrameInfo(sys._getframe())
-
-
-moduleLevelFrameInfo = getFrameInfo(sys._getframe())
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/dummy.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/dummy.py
deleted file mode 100644
index 8ec85f8..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/dummy.py
+++ /dev/null
@@ -1,25 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-""" Dummy Module
-"""
-from zope.interface import moduleProvides
-from zope.interface.tests.idummy import IDummyModule
-
-
-moduleProvides(IDummyModule)
-
-
-def bar(baz):
-    # Note:  no 'self', because the module provides the interface directly.
-    raise NotImplementedError()
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/idummy.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/idummy.py
deleted file mode 100644
index 7855ce7..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/idummy.py
+++ /dev/null
@@ -1,24 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-""" Interface describing API of zope.interface.tests.dummy test module
-"""
-from zope.interface import Interface
-
-
-class IDummyModule(Interface):
-    """ Dummy interface for unit tests.
-    """
-    def bar(baz):
-        """ Just a note.
-        """
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/m1.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/m1.py
deleted file mode 100644
index 8998e46..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/m1.py
+++ /dev/null
@@ -1,28 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2004 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Test module that declares an interface
-"""
-from zope.interface import Interface
-from zope.interface import moduleProvides
-
-
-class I1(Interface):
-    pass
-
-
-class I2(Interface):
-    pass
-
-
-moduleProvides(I1, I2)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/odd.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/odd.py
deleted file mode 100644
index b385beb..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/odd.py
+++ /dev/null
@@ -1,130 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Odd meta class that doesn't subclass type.
-
-This is used for testing support for ExtensionClass in new interfaces.
-
-  >>> class A(object):
-  ...     __metaclass__ = MetaClass
-  ...     a = 1
-  ...
-  >>> A.__name__
-  'A'
-  >>> A.__bases__ == (object,)
-  True
-  >>> class B(object):
-  ...     __metaclass__ = MetaClass
-  ...     b = 1
-  ...
-  >>> class C(A, B): pass
-  ...
-  >>> C.__name__
-  'C'
-  >>> int(C.__bases__ == (A, B))
-  1
-  >>> a = A()
-  >>> aa = A()
-  >>> a.a
-  1
-  >>> aa.a
-  1
-  >>> aa.a = 2
-  >>> a.a
-  1
-  >>> aa.a
-  2
-  >>> c = C()
-  >>> c.a
-  1
-  >>> c.b
-  1
-  >>> c.b = 2
-  >>> c.b
-  2
-  >>> C.c = 1
-  >>> c.c
-  1
-
-  >>> int(C.__class__.__class__ is C.__class__)
-  1
-"""
-
-# class OddClass is an odd meta class
-
-
-class MetaMetaClass(type):
-
-    def __getattribute__(cls, name):
-        if name == '__class__':
-            return cls
-        # Under Python 3.6, __prepare__ gets requested
-        return type.__getattribute__(cls, name)
-
-
-class MetaClass:
-    """Odd classes
-    """
-
-    def __init__(self, name, bases, dict):
-        self.__name__ = name
-        self.__bases__ = bases
-        self.__dict__.update(dict)
-
-    def __call__(self):
-        return OddInstance(self)
-
-    def __getattr__(self, name):
-        for b in self.__bases__:
-            v = getattr(b, name, self)
-            if v is not self:
-                return v
-        raise AttributeError(name)
-
-    def __repr__(self):  # pragma: no cover
-        return f""
-
-
-MetaClass = MetaMetaClass(
-    'MetaClass',
-    MetaClass.__bases__,
-    {
-        k: v for k, v in MetaClass.__dict__.items()
-        if k not in ('__dict__',)
-    }
-)
-
-
-class OddInstance:
-
-    def __init__(self, cls):
-        self.__dict__['__class__'] = cls
-
-    def __getattribute__(self, name):
-        dict = object.__getattribute__(self, '__dict__')
-        if name == '__dict__':
-            return dict
-        v = dict.get(name, self)
-        if v is not self:
-            return v
-        return getattr(dict['__class__'], name)
-
-    def __setattr__(self, name, v):
-        self.__dict__[name] = v
-
-    def __delattr__(self, name):
-        raise NotImplementedError()
-
-    def __repr__(self):  # pragma: no cover
-        return "".format(
-            self.__class__.__name__, hex(id(self)))
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_adapter.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_adapter.py
deleted file mode 100644
index ea90732..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_adapter.py
+++ /dev/null
@@ -1,2315 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Adapter registry tests
-"""
-import unittest
-
-from zope.interface.tests import OptimizationTestMixin
-
-
-# pylint:disable=inherit-non-class,protected-access,too-many-lines
-# pylint:disable=attribute-defined-outside-init,blacklisted-name
-
-def _makeInterfaces():
-    from zope.interface import Interface
-
-    class IB0(Interface):
-        pass
-
-    class IB1(IB0):
-        pass
-
-    class IB2(IB0):
-        pass
-
-    class IB3(IB2, IB1):
-        pass
-
-    class IB4(IB1, IB2):
-        pass
-
-    class IF0(Interface):
-        pass
-
-    class IF1(IF0):
-        pass
-
-    class IR0(Interface):
-        pass
-
-    class IR1(IR0):
-        pass
-
-    return IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1
-
-
-# Custom types to use as part of the AdapterRegistry data structures.
-# Our custom types do strict type checking to make sure
-# types propagate through the data tree as expected.
-class CustomDataTypeBase:
-    _data = None
-
-    def __getitem__(self, name):
-        return self._data[name]
-
-    def __setitem__(self, name, value):
-        self._data[name] = value
-
-    def __delitem__(self, name):
-        del self._data[name]
-
-    def __len__(self):
-        return len(self._data)
-
-    def __contains__(self, name):
-        return name in self._data
-
-    def __eq__(self, other):
-        if other is self:
-            return True
-        # pylint:disable=unidiomatic-typecheck
-        if type(other) is not type(self):
-            return False
-        return other._data == self._data
-
-    def __repr__(self):
-        return repr(self._data)
-
-
-class CustomMapping(CustomDataTypeBase):
-    def __init__(self, other=None):
-        self._data = {}
-        if other:
-            self._data.update(other)
-        self.get = self._data.get
-        self.items = self._data.items
-
-
-class CustomSequence(CustomDataTypeBase):
-    def __init__(self, other=None):
-        self._data = []
-        if other:
-            self._data.extend(other)
-        self.append = self._data.append
-
-
-class CustomLeafSequence(CustomSequence):
-    pass
-
-
-class CustomProvided(CustomMapping):
-    pass
-
-
-class BaseAdapterRegistryTests(unittest.TestCase):
-
-    maxDiff = None
-
-    def _getBaseAdapterRegistry(self):
-        from zope.interface.adapter import BaseAdapterRegistry
-        return BaseAdapterRegistry
-
-    def _getTargetClass(self):
-        BaseAdapterRegistry = self._getBaseAdapterRegistry()
-
-        class _CUT(BaseAdapterRegistry):
-
-            class LookupClass:
-                _changed = _extendors = ()
-
-                def __init__(self, reg):
-                    pass
-
-                def changed(self, orig):
-                    self._changed += (orig,)
-
-                def add_extendor(self, provided):
-                    self._extendors += (provided,)
-
-                def remove_extendor(self, provided):
-                    self._extendors = tuple([x for x in self._extendors
-                                             if x != provided])
-
-        for name in BaseAdapterRegistry._delegated:
-            setattr(_CUT.LookupClass, name, object())
-        return _CUT
-
-    def _makeOne(self):
-        return self._getTargetClass()()
-
-    def _getMappingType(self):
-        return dict
-
-    def _getProvidedType(self):
-        return dict
-
-    def _getMutableListType(self):
-        return list
-
-    def _getLeafSequenceType(self):
-        return tuple
-
-    def test_lookup_delegation(self):
-        CUT = self._getTargetClass()
-        registry = CUT()
-        for name in CUT._delegated:
-            self.assertIs(
-                getattr(registry, name), getattr(registry._v_lookup, name)
-            )
-
-    def test__generation_on_first_creation(self):
-        registry = self._makeOne()
-        # Bumped to 1 in BaseAdapterRegistry.__init__
-        self.assertEqual(registry._generation, 1)
-
-    def test__generation_after_calling_changed(self):
-        registry = self._makeOne()
-        orig = object()
-        registry.changed(orig)
-        # Bumped to 1 in BaseAdapterRegistry.__init__
-        self.assertEqual(registry._generation, 2)
-        self.assertEqual(registry._v_lookup._changed, (registry, orig,))
-
-    def test__generation_after_changing___bases__(self):
-        class _Base:
-            pass
-        registry = self._makeOne()
-        registry.__bases__ = (_Base,)
-        self.assertEqual(registry._generation, 2)
-
-    def _check_basic_types_of_adapters(self, registry, expected_order=2):
-        self.assertEqual(
-            len(registry._adapters), expected_order,
-        )  # order 0 and order 1
-        self.assertIsInstance(registry._adapters, self._getMutableListType())
-        MT = self._getMappingType()
-        for mapping in registry._adapters:
-            self.assertIsInstance(mapping, MT)
-        self.assertEqual(registry._adapters[0], MT())
-        self.assertIsInstance(registry._adapters[1], MT)
-        self.assertEqual(len(registry._adapters[expected_order - 1]), 1)
-
-    def _check_basic_types_of_subscribers(self, registry, expected_order=2):
-        self.assertEqual(
-            len(registry._subscribers), expected_order,
-        )  # order 0 and order 1
-        self.assertIsInstance(
-            registry._subscribers, self._getMutableListType(),
-        )
-        MT = self._getMappingType()
-        for mapping in registry._subscribers:
-            self.assertIsInstance(mapping, MT)
-        if expected_order:
-            self.assertEqual(registry._subscribers[0], MT())
-            self.assertIsInstance(registry._subscribers[1], MT)
-            self.assertEqual(len(registry._subscribers[expected_order - 1]), 1)
-
-    def test_register(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.register([IB0], IR0, '', 'A1')
-        self.assertEqual(registry.registered([IB0], IR0, ''), 'A1')
-        self.assertEqual(registry._generation, 2)
-        self._check_basic_types_of_adapters(registry)
-        MT = self._getMappingType()
-        self.assertEqual(registry._adapters[1], MT({
-            IB0: MT({
-                IR0: MT({'': 'A1'})
-            })
-        }))
-        PT = self._getProvidedType()
-        self.assertEqual(registry._provided, PT({
-            IR0: 1
-        }))
-
-        registered = list(registry.allRegistrations())
-        self.assertEqual(registered, [(
-            (IB0,),  # required
-            IR0,  # provided
-            '',  # name
-            'A1'  # value
-        )])
-
-    def test_register_multiple_allRegistrations(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        # Use several different depths and several different names
-        registry.register([], IR0, '', 'A1')
-        registry.register([], IR0, 'name1', 'A2')
-
-        registry.register([IB0], IR0, '', 'A1')
-        registry.register([IB0], IR0, 'name2', 'A2')
-        registry.register([IB0], IR1, '', 'A3')
-        registry.register([IB0], IR1, 'name3', 'A4')
-
-        registry.register([IB0, IB1], IR0, '', 'A1')
-        registry.register([IB0, IB2], IR0, 'name2', 'A2')
-        registry.register([IB0, IB2], IR1, 'name4', 'A4')
-        registry.register([IB0, IB3], IR1, '', 'A3')
-
-        def build_adapters(L, MT):
-            return L([
-                # 0
-                MT({
-                    IR0: MT({
-                        '': 'A1',
-                        'name1': 'A2'
-                    })
-                }),
-                # 1
-                MT({
-                    IB0: MT({
-                        IR0: MT({
-                            '': 'A1',
-                            'name2': 'A2'
-                        }),
-                        IR1: MT({
-                            '': 'A3',
-                            'name3': 'A4'
-                        })
-                    })
-                }),
-                # 3
-                MT({
-                    IB0: MT({
-                        IB1: MT({
-                            IR0: MT({'': 'A1'})
-                        }),
-                        IB2: MT({
-                            IR0: MT({'name2': 'A2'}),
-                            IR1: MT({'name4': 'A4'}),
-                        }),
-                        IB3: MT({
-                            IR1: MT({'': 'A3'})
-                        })
-                    }),
-                }),
-            ])
-
-        self.assertEqual(registry._adapters,
-                         build_adapters(L=self._getMutableListType(),
-                                        MT=self._getMappingType()))
-
-        registered = sorted(registry.allRegistrations())
-        self.assertEqual(registered, [
-            ((), IR0, '', 'A1'),
-            ((), IR0, 'name1', 'A2'),
-            ((IB0,), IR0, '', 'A1'),
-            ((IB0,), IR0, 'name2', 'A2'),
-            ((IB0,), IR1, '', 'A3'),
-            ((IB0,), IR1, 'name3', 'A4'),
-            ((IB0, IB1), IR0, '', 'A1'),
-            ((IB0, IB2), IR0, 'name2', 'A2'),
-            ((IB0, IB2), IR1, 'name4', 'A4'),
-            ((IB0, IB3), IR1, '', 'A3')
-        ])
-
-        # We can duplicate to another object.
-        registry2 = self._makeOne()
-        for args in registered:
-            registry2.register(*args)
-
-        self.assertEqual(registry2._adapters, registry._adapters)
-        self.assertEqual(registry2._provided, registry._provided)
-
-        # We can change the types and rebuild the data structures.
-        registry._mappingType = CustomMapping
-        registry._leafSequenceType = CustomLeafSequence
-        registry._sequenceType = CustomSequence
-        registry._providedType = CustomProvided
-
-        def addValue(existing, new):
-            existing = (
-                existing if existing is not None else CustomLeafSequence()
-            )
-            existing.append(new)
-            return existing
-
-        registry._addValueToLeaf = addValue
-
-        registry.rebuild()
-
-        self.assertEqual(registry._adapters,
-                         build_adapters(
-                             L=CustomSequence,
-                             MT=CustomMapping
-                         ))
-
-    def test_register_with_invalid_name(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        with self.assertRaises(ValueError):
-            registry.register([IB0], IR0, object(), 'A1')
-
-    def test_register_with_value_None_unregisters(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.register([None], IR0, '', 'A1')
-        registry.register([None], IR0, '', None)
-        self.assertEqual(len(registry._adapters), 0)
-        self.assertIsInstance(registry._adapters, self._getMutableListType())
-        registered = list(registry.allRegistrations())
-        self.assertEqual(registered, [])
-
-    def test_register_with_same_value(self):
-        from zope.interface import Interface
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        _value = object()
-        registry.register([None], IR0, '', _value)
-        _before = registry._generation
-        registry.register([None], IR0, '', _value)
-        self.assertEqual(registry._generation, _before)  # skipped changed()
-        self._check_basic_types_of_adapters(registry)
-        MT = self._getMappingType()
-        self.assertEqual(registry._adapters[1], MT(
-            {
-                Interface: MT(
-                    {
-                        IR0: MT({'': _value})
-                    }
-                )
-            }
-        ))
-        registered = list(registry.allRegistrations())
-        self.assertEqual(registered, [(
-            (Interface,),  # required
-            IR0,  # provided
-            '',  # name
-            _value  # value
-        )])
-
-    def test_registered_empty(self):
-        registry = self._makeOne()
-        self.assertEqual(registry.registered([None], None, ''), None)
-        registered = list(registry.allRegistrations())
-        self.assertEqual(registered, [])
-
-    def test_registered_non_empty_miss(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.register([IB1], None, '', 'A1')
-        self.assertEqual(registry.registered([IB2], None, ''), None)
-
-    def test_registered_non_empty_hit(self):
-        registry = self._makeOne()
-        registry.register([None], None, '', 'A1')
-        self.assertEqual(registry.registered([None], None, ''), 'A1')
-
-    def test_unregister_empty(self):
-        registry = self._makeOne()
-        registry.unregister([None], None, '')  # doesn't raise
-        self.assertEqual(registry.registered([None], None, ''), None)
-        self.assertEqual(len(registry._provided), 0)
-
-    def test_unregister_non_empty_miss_on_required(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.register([IB1], None, '', 'A1')
-        registry.unregister([IB2], None, '')  # doesn't raise
-        self.assertEqual(registry.registered([IB1], None, ''), 'A1')
-        self._check_basic_types_of_adapters(registry)
-        MT = self._getMappingType()
-        self.assertEqual(registry._adapters[1], MT(
-            {
-                IB1: MT(
-                    {
-                        None: MT({'': 'A1'})
-                    }
-                )
-            }
-        ))
-        PT = self._getProvidedType()
-        self.assertEqual(registry._provided, PT({
-            None: 1
-        }))
-
-    def test_unregister_non_empty_miss_on_name(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.register([IB1], None, '', 'A1')
-        registry.unregister([IB1], None, 'nonesuch')  # doesn't raise
-        self.assertEqual(registry.registered([IB1], None, ''), 'A1')
-        self._check_basic_types_of_adapters(registry)
-        MT = self._getMappingType()
-        self.assertEqual(registry._adapters[1], MT(
-            {
-                IB1: MT(
-                    {
-                        None: MT({'': 'A1'})
-                    }
-                )
-            }
-        ))
-        PT = self._getProvidedType()
-        self.assertEqual(registry._provided, PT({
-            None: 1
-        }))
-
-    def test_unregister_with_value_not_None_miss(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        orig = object()
-        nomatch = object()
-        registry.register([IB1], None, '', orig)
-        registry.unregister([IB1], None, '', nomatch)  # doesn't raise
-        self.assertIs(registry.registered([IB1], None, ''), orig)
-
-    def test_unregister_hit_clears_empty_subcomponents(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        one = object()
-        another = object()
-        registry.register([IB1, IB2], None, '', one)
-        registry.register([IB1, IB3], None, '', another)
-        self._check_basic_types_of_adapters(registry, expected_order=3)
-        self.assertIn(IB2, registry._adapters[2][IB1])
-        self.assertIn(IB3, registry._adapters[2][IB1])
-        MT = self._getMappingType()
-        self.assertEqual(registry._adapters[2], MT(
-            {
-                IB1: MT(
-                    {
-                        IB2: MT({None: MT({'': one})}),
-                        IB3: MT({None: MT({'': another})})
-                    }
-                )
-            }
-        ))
-        PT = self._getProvidedType()
-        self.assertEqual(registry._provided, PT({
-            None: 2
-        }))
-
-        registry.unregister([IB1, IB3], None, '', another)
-        self.assertIn(IB2, registry._adapters[2][IB1])
-        self.assertNotIn(IB3, registry._adapters[2][IB1])
-        self.assertEqual(registry._adapters[2], MT(
-            {
-                IB1: MT(
-                    {
-                        IB2: MT({None: MT({'': one})}),
-                    }
-                )
-            }
-        ))
-        self.assertEqual(registry._provided, PT({
-            None: 1
-        }))
-
-    def test_unsubscribe_empty(self):
-        registry = self._makeOne()
-        registry.unsubscribe([None], None, '')  # doesn't raise
-        self.assertEqual(registry.registered([None], None, ''), None)
-        self._check_basic_types_of_subscribers(registry, expected_order=0)
-
-    def test_unsubscribe_hit(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        orig = object()
-        registry.subscribe([IB1], None, orig)
-        MT = self._getMappingType()
-        L = self._getLeafSequenceType()
-        PT = self._getProvidedType()
-        self._check_basic_types_of_subscribers(registry)
-        self.assertEqual(registry._subscribers[1], MT({
-            IB1: MT({
-                None: MT({
-                    '': L((orig,))
-                })
-            })
-        }))
-        self.assertEqual(registry._provided, PT({}))
-        registry.unsubscribe([IB1], None, orig)  # doesn't raise
-        self.assertEqual(len(registry._subscribers), 0)
-        self.assertEqual(registry._provided, PT({}))
-
-    def assertLeafIdentity(self, leaf1, leaf2):
-        """
-        Implementations may choose to use new, immutable objects
-        instead of mutating existing subscriber leaf objects, or vice versa.
-
-        The default implementation uses immutable tuples, so they are never
-        the same. Other implementations may use persistent lists so they
-        should be the same and mutated in place. Subclasses testing this
-        behaviour need to override this method.
-        """
-        self.assertIsNot(leaf1, leaf2)
-
-    def test_unsubscribe_after_multiple(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        first = object()
-        second = object()
-        third = object()
-        fourth = object()
-        registry.subscribe([IB1], None, first)
-        registry.subscribe([IB1], None, second)
-        registry.subscribe([IB1], IR0, third)
-        registry.subscribe([IB1], IR0, fourth)
-        self._check_basic_types_of_subscribers(registry, expected_order=2)
-        MT = self._getMappingType()
-        L = self._getLeafSequenceType()
-        PT = self._getProvidedType()
-        self.assertEqual(registry._subscribers[1], MT({
-            IB1: MT({
-                None: MT({'': L((first, second))}),
-                IR0: MT({'': L((third, fourth))}),
-            })
-        }))
-        self.assertEqual(registry._provided, PT({
-            IR0: 2
-        }))
-        # The leaf objects may or may not stay the same as they are
-        # unsubscribed, depending on the implementation
-        IR0_leaf_orig = registry._subscribers[1][IB1][IR0]['']
-        Non_leaf_orig = registry._subscribers[1][IB1][None]['']
-
-        registry.unsubscribe([IB1], None, first)
-        registry.unsubscribe([IB1], IR0, third)
-
-        self.assertEqual(registry._subscribers[1], MT({
-            IB1: MT({
-                None: MT({'': L((second,))}),
-                IR0: MT({'': L((fourth,))}),
-            })
-        }))
-        self.assertEqual(registry._provided, PT({
-            IR0: 1
-        }))
-        IR0_leaf_new = registry._subscribers[1][IB1][IR0]['']
-        Non_leaf_new = registry._subscribers[1][IB1][None]['']
-
-        self.assertLeafIdentity(IR0_leaf_orig, IR0_leaf_new)
-        self.assertLeafIdentity(Non_leaf_orig, Non_leaf_new)
-
-        registry.unsubscribe([IB1], None, second)
-        registry.unsubscribe([IB1], IR0, fourth)
-        self.assertEqual(len(registry._subscribers), 0)
-        self.assertEqual(len(registry._provided), 0)
-
-    def test_subscribe_unsubscribe_identical_objects_provided(self):
-        # https://github.com/zopefoundation/zope.interface/issues/227
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        first = object()
-        registry.subscribe([IB1], IR0, first)
-        registry.subscribe([IB1], IR0, first)
-
-        MT = self._getMappingType()
-        L = self._getLeafSequenceType()
-        PT = self._getProvidedType()
-        self.assertEqual(registry._subscribers[1], MT({
-            IB1: MT({
-                IR0: MT({'': L((first, first))}),
-            })
-        }))
-        self.assertEqual(registry._provided, PT({
-            IR0: 2
-        }))
-
-        registry.unsubscribe([IB1], IR0, first)
-        registry.unsubscribe([IB1], IR0, first)
-        self.assertEqual(len(registry._subscribers), 0)
-        self.assertEqual(registry._provided, PT())
-
-    def test_subscribe_unsubscribe_nonequal_objects_provided(self):
-        # https://github.com/zopefoundation/zope.interface/issues/227
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        first = object()
-        second = object()
-        registry.subscribe([IB1], IR0, first)
-        registry.subscribe([IB1], IR0, second)
-
-        MT = self._getMappingType()
-        L = self._getLeafSequenceType()
-        PT = self._getProvidedType()
-        self.assertEqual(registry._subscribers[1], MT({
-            IB1: MT({
-                IR0: MT({'': L((first, second))}),
-            })
-        }))
-        self.assertEqual(registry._provided, PT({
-            IR0: 2
-        }))
-
-        registry.unsubscribe([IB1], IR0, first)
-        registry.unsubscribe([IB1], IR0, second)
-        self.assertEqual(len(registry._subscribers), 0)
-        self.assertEqual(registry._provided, PT())
-
-    def test_subscribed_empty(self):
-        registry = self._makeOne()
-        self.assertIsNone(registry.subscribed([None], None, ''))
-        subscribed = list(registry.allSubscriptions())
-        self.assertEqual(subscribed, [])
-
-    def test_subscribed_non_empty_miss(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.subscribe([IB1], IF0, 'A1')
-        # Mismatch required
-        self.assertIsNone(registry.subscribed([IB2], IF0, ''))
-        # Mismatch provided
-        self.assertIsNone(registry.subscribed([IB1], IF1, ''))
-        # Mismatch value
-        self.assertIsNone(registry.subscribed([IB1], IF0, ''))
-
-    def test_subscribed_non_empty_hit(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.subscribe([IB0], IF0, 'A1')
-        self.assertEqual(registry.subscribed([IB0], IF0, 'A1'), 'A1')
-
-    def test_unsubscribe_w_None_after_multiple(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        first = object()
-        second = object()
-
-        registry.subscribe([IB1], None, first)
-        registry.subscribe([IB1], None, second)
-        self._check_basic_types_of_subscribers(registry, expected_order=2)
-        registry.unsubscribe([IB1], None)
-        self.assertEqual(len(registry._subscribers), 0)
-
-    def test_unsubscribe_non_empty_miss_on_required(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.subscribe([IB1], None, 'A1')
-        self._check_basic_types_of_subscribers(registry, expected_order=2)
-        registry.unsubscribe([IB2], None, '')  # doesn't raise
-        self.assertEqual(len(registry._subscribers), 2)
-        MT = self._getMappingType()
-        L = self._getLeafSequenceType()
-        self.assertEqual(registry._subscribers[1], MT({
-            IB1: MT({
-                None: MT({'': L(('A1',))}),
-            })
-        }))
-
-    def test_unsubscribe_non_empty_miss_on_value(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        registry.subscribe([IB1], None, 'A1')
-        self._check_basic_types_of_subscribers(registry, expected_order=2)
-        registry.unsubscribe([IB1], None, 'A2')  # doesn't raise
-        self.assertEqual(len(registry._subscribers), 2)
-        MT = self._getMappingType()
-        L = self._getLeafSequenceType()
-        self.assertEqual(registry._subscribers[1], MT({
-            IB1: MT({
-                None: MT({'': L(('A1',))}),
-            })
-        }))
-
-    def test_unsubscribe_with_value_not_None_miss(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        orig = object()
-        nomatch = object()
-        registry.subscribe([IB1], None, orig)
-        registry.unsubscribe([IB1], None, nomatch)  # doesn't raise
-        self.assertEqual(len(registry._subscribers), 2)
-
-    def _instance_method_notify_target(self):
-        self.fail("Example method, not intended to be called.")
-
-    def test_unsubscribe_instance_method(self):
-        # Checking that the values are compared by equality, not identity
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        self.assertEqual(len(registry._subscribers), 0)
-        registry.subscribe([IB1], None, self._instance_method_notify_target)
-        registry.unsubscribe([IB1], None, self._instance_method_notify_target)
-        self.assertEqual(len(registry._subscribers), 0)
-
-    def test_subscribe_multiple_allRegistrations(self):
-        (
-            IB0, IB1, IB2, IB3, IB4, IF0, IF1, IR0, IR1,
-        ) = _makeInterfaces()  # pylint:disable=unused-variable
-        registry = self._makeOne()
-        # Use several different depths and several different values
-        registry.subscribe([], IR0, 'A1')
-        registry.subscribe([], IR0, 'A2')
-
-        registry.subscribe([IB0], IR0, 'A1')
-        registry.subscribe([IB0], IR0, 'A2')
-        registry.subscribe([IB0], IR1, 'A3')
-        registry.subscribe([IB0], IR1, 'A4')
-
-        registry.subscribe([IB0, IB1], IR0, 'A1')
-        registry.subscribe([IB0, IB2], IR0, 'A2')
-        registry.subscribe([IB0, IB2], IR1, 'A4')
-        registry.subscribe([IB0, IB3], IR1, 'A3')
-
-        def build_subscribers(L, F, MT):
-            return L([
-                # 0
-                MT({
-                    IR0: MT({
-                        '': F(['A1', 'A2'])
-                    })
-                }),
-                # 1
-                MT({
-                    IB0: MT({
-                        IR0: MT({
-                            '': F(['A1', 'A2'])
-                        }),
-                        IR1: MT({
-                            '': F(['A3', 'A4'])
-                        })
-                    })
-                }),
-                # 3
-                MT({
-                    IB0: MT({
-                        IB1: MT({
-                            IR0: MT({'': F(['A1'])})
-                        }),
-                        IB2: MT({
-                            IR0: MT({'': F(['A2'])}),
-                            IR1: MT({'': F(['A4'])}),
-                        }),
-                        IB3: MT({
-                            IR1: MT({'': F(['A3'])})
-                        })
-                    }),
-                }),
-            ])
-
-        self.assertEqual(registry._subscribers,
-                         build_subscribers(
-                             L=self._getMutableListType(),
-                             F=self._getLeafSequenceType(),
-                             MT=self._getMappingType()
-                         ))
-
-        def build_provided(P):
-            return P({
-                IR0: 6,
-                IR1: 4,
-            })
-
-        self.assertEqual(registry._provided,
-                         build_provided(P=self._getProvidedType()))
-
-        registered = sorted(registry.allSubscriptions())
-        self.assertEqual(registered, [
-            ((), IR0, 'A1'),
-            ((), IR0, 'A2'),
-            ((IB0,), IR0, 'A1'),
-            ((IB0,), IR0, 'A2'),
-            ((IB0,), IR1, 'A3'),
-            ((IB0,), IR1, 'A4'),
-            ((IB0, IB1), IR0, 'A1'),
-            ((IB0, IB2), IR0, 'A2'),
-            ((IB0, IB2), IR1, 'A4'),
-            ((IB0, IB3), IR1, 'A3')
-        ])
-
-        # We can duplicate this to another object
-        registry2 = self._makeOne()
-        for args in registered:
-            registry2.subscribe(*args)
-
-        self.assertEqual(registry2._subscribers, registry._subscribers)
-        self.assertEqual(registry2._provided, registry._provided)
-
-        # We can change the types and rebuild the data structures.
-        registry._mappingType = CustomMapping
-        registry._leafSequenceType = CustomLeafSequence
-        registry._sequenceType = CustomSequence
-        registry._providedType = CustomProvided
-
-        def addValue(existing, new):
-            existing = (
-                existing if existing is not None else CustomLeafSequence()
-            )
-            existing.append(new)
-            return existing
-
-        registry._addValueToLeaf = addValue
-
-        registry.rebuild()
-
-        self.assertEqual(registry._subscribers,
-                         build_subscribers(
-                             L=CustomSequence,
-                             F=CustomLeafSequence,
-                             MT=CustomMapping
-                         ))
-
-
-class CustomTypesBaseAdapterRegistryTests(BaseAdapterRegistryTests):
-    """
-    This class may be extended by other packages to test their own
-    adapter registries that use custom types. (So be cautious about
-    breaking changes.)
-
-    One known user is ``zope.component.persistentregistry``.
-    """
-
-    def _getMappingType(self):
-        return CustomMapping
-
-    def _getProvidedType(self):
-        return CustomProvided
-
-    def _getMutableListType(self):
-        return CustomSequence
-
-    def _getLeafSequenceType(self):
-        return CustomLeafSequence
-
-    def _getBaseAdapterRegistry(self):
-        from zope.interface.adapter import BaseAdapterRegistry
-
-        class CustomAdapterRegistry(BaseAdapterRegistry):
-            _mappingType = self._getMappingType()
-            _sequenceType = self._getMutableListType()
-            _leafSequenceType = self._getLeafSequenceType()
-            _providedType = self._getProvidedType()
-
-            def _addValueToLeaf(self, existing_leaf_sequence, new_item):
-                if not existing_leaf_sequence:
-                    existing_leaf_sequence = self._leafSequenceType()
-                existing_leaf_sequence.append(new_item)
-                return existing_leaf_sequence
-
-            def _removeValueFromLeaf(self, existing_leaf_sequence, to_remove):
-                without_removed = BaseAdapterRegistry._removeValueFromLeaf(
-                    self,
-                    existing_leaf_sequence,
-                    to_remove)
-                existing_leaf_sequence[:] = without_removed
-                assert to_remove not in existing_leaf_sequence
-                return existing_leaf_sequence
-
-        return CustomAdapterRegistry
-
-    def assertLeafIdentity(self, leaf1, leaf2):
-        self.assertIs(leaf1, leaf2)
-
-
-class LookupBaseFallbackTests(unittest.TestCase):
-
-    def _getFallbackClass(self):
-        from zope.interface.adapter import LookupBaseFallback
-        return LookupBaseFallback
-
-    _getTargetClass = _getFallbackClass
-
-    def _makeOne(
-        self, uc_lookup=None, uc_lookupAll=None, uc_subscriptions=None,
-    ):
-        # pylint:disable=function-redefined
-        if uc_lookup is None:
-
-            def uc_lookup(self, required, provided, name):
-                pass
-
-        if uc_lookupAll is None:
-
-            def uc_lookupAll(self, required, provided):
-                raise NotImplementedError()
-
-        if uc_subscriptions is None:
-
-            def uc_subscriptions(self, required, provided):
-                raise NotImplementedError()
-
-        class Derived(self._getTargetClass()):
-            _uncached_lookup = uc_lookup
-            _uncached_lookupAll = uc_lookupAll
-            _uncached_subscriptions = uc_subscriptions
-
-        return Derived()
-
-    def test_lookup_w_invalid_name(self):
-
-        def _lookup(self, required, provided, name):
-            self.fail("This should never be called")
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        with self.assertRaises(ValueError):
-            lb.lookup(('A',), 'B', object())
-
-    def test_lookup_miss_no_default(self):
-        _called_with = []
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup(('A',), 'B', 'C')
-        self.assertIsNone(found)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-
-    def test_lookup_miss_w_default(self):
-        _called_with = []
-        _default = object()
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup(('A',), 'B', 'C', _default)
-        self.assertIs(found, _default)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-
-    def test_lookup_not_cached(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup(('A',), 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-
-    def test_lookup_cached(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup(('A',), 'B', 'C')
-        found = lb.lookup(('A',), 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-
-    def test_lookup_not_cached_multi_required(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup(('A', 'D'), 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A', 'D'), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-
-    def test_lookup_cached_multi_required(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup(('A', 'D'), 'B', 'C')
-        found = lb.lookup(('A', 'D'), 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A', 'D'), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-
-    def test_lookup_not_cached_after_changed(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup(('A',), 'B', 'C')
-        lb.changed(lb)
-        found = lb.lookup(('A',), 'B', 'C')
-        self.assertIs(found, b)
-        self.assertEqual(_called_with,
-                         [(('A',), 'B', 'C'), (('A',), 'B', 'C')])
-        self.assertEqual(_results, [c])
-
-    def test_lookup1_w_invalid_name(self):
-
-        def _lookup(self, required, provided, name):
-            self.fail("This should never be called")
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        with self.assertRaises(ValueError):
-            lb.lookup1('A', 'B', object())
-
-    def test_lookup1_miss_no_default(self):
-        _called_with = []
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup1('A', 'B', 'C')
-        self.assertIsNone(found)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-
-    def test_lookup1_miss_w_default(self):
-        _called_with = []
-        _default = object()
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup1('A', 'B', 'C', _default)
-        self.assertIs(found, _default)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-
-    def test_lookup1_miss_w_default_negative_cache(self):
-        _called_with = []
-        _default = object()
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup1('A', 'B', 'C', _default)
-        self.assertIs(found, _default)
-        found = lb.lookup1('A', 'B', 'C', _default)
-        self.assertIs(found, _default)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-
-    def test_lookup1_not_cached(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup1('A', 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-
-    def test_lookup1_cached(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup1('A', 'B', 'C')
-        found = lb.lookup1('A', 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-
-    def test_lookup1_not_cached_after_changed(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        lb = self._makeOne(uc_lookup=_lookup)
-        found = lb.lookup1('A', 'B', 'C')
-        lb.changed(lb)
-        found = lb.lookup1('A', 'B', 'C')
-        self.assertIs(found, b)
-        self.assertEqual(_called_with,
-                         [(('A',), 'B', 'C'), (('A',), 'B', 'C')])
-        self.assertEqual(_results, [c])
-
-    def test_adapter_hook_w_invalid_name(self):
-        req, prv = object(), object()
-        lb = self._makeOne()
-        with self.assertRaises(ValueError):
-            lb.adapter_hook(prv, req, object())
-
-    def test_adapter_hook_miss_no_default(self):
-        req, prv = object(), object()
-        lb = self._makeOne()
-        found = lb.adapter_hook(prv, req, '')
-        self.assertIsNone(found)
-
-    def test_adapter_hook_miss_w_default(self):
-        req, prv, _default = object(), object(), object()
-        lb = self._makeOne()
-        found = lb.adapter_hook(prv, req, '', _default)
-        self.assertIs(found, _default)
-
-    def test_adapter_hook_hit_factory_returns_None(self):
-        _f_called_with = []
-
-        def _factory(context):
-            _f_called_with.append(context)
-
-        def _lookup(self, required, provided, name):
-            return _factory
-
-        req, prv, _default = object(), object(), object()
-        lb = self._makeOne(uc_lookup=_lookup)
-        adapted = lb.adapter_hook(prv, req, 'C', _default)
-        self.assertIs(adapted, _default)
-        self.assertEqual(_f_called_with, [req])
-
-    def test_adapter_hook_hit_factory_returns_adapter(self):
-        _f_called_with = []
-        _adapter = object()
-
-        def _factory(context):
-            _f_called_with.append(context)
-            return _adapter
-
-        def _lookup(self, required, provided, name):
-            return _factory
-
-        req, prv, _default = object(), object(), object()
-        lb = self._makeOne(uc_lookup=_lookup)
-        adapted = lb.adapter_hook(prv, req, 'C', _default)
-        self.assertIs(adapted, _adapter)
-        self.assertEqual(_f_called_with, [req])
-
-    def test_adapter_hook_super_unwraps(self):
-        _f_called_with = []
-
-        def _factory(context):
-            _f_called_with.append(context)
-            return context
-
-        def _lookup(self, required, provided, name=''):
-            return _factory
-
-        required = super()
-        provided = object()
-        lb = self._makeOne(uc_lookup=_lookup)
-        adapted = lb.adapter_hook(provided, required)
-        self.assertIs(adapted, self)
-        self.assertEqual(_f_called_with, [self])
-
-    def test_queryAdapter(self):
-        _f_called_with = []
-        _adapter = object()
-
-        def _factory(context):
-            _f_called_with.append(context)
-            return _adapter
-
-        def _lookup(self, required, provided, name):
-            return _factory
-
-        req, prv, _default = object(), object(), object()
-        lb = self._makeOne(uc_lookup=_lookup)
-        adapted = lb.queryAdapter(req, prv, 'C', _default)
-        self.assertIs(adapted, _adapter)
-        self.assertEqual(_f_called_with, [req])
-
-    def test_lookupAll_uncached(self):
-        _called_with = []
-        _results = [object(), object(), object()]
-
-        def _lookupAll(self, required, provided):
-            _called_with.append((required, provided))
-            return tuple(_results)
-
-        lb = self._makeOne(uc_lookupAll=_lookupAll)
-        found = lb.lookupAll('A', 'B')
-        self.assertEqual(found, tuple(_results))
-        self.assertEqual(_called_with, [(('A',), 'B')])
-
-    def test_lookupAll_cached(self):
-        _called_with = []
-        _results = [object(), object(), object()]
-
-        def _lookupAll(self, required, provided):
-            _called_with.append((required, provided))
-            return tuple(_results)
-
-        lb = self._makeOne(uc_lookupAll=_lookupAll)
-        found = lb.lookupAll('A', 'B')
-        found = lb.lookupAll('A', 'B')
-        self.assertEqual(found, tuple(_results))
-        self.assertEqual(_called_with, [(('A',), 'B')])
-
-    def test_subscriptions_uncached(self):
-        _called_with = []
-        _results = [object(), object(), object()]
-
-        def _subscriptions(self, required, provided):
-            _called_with.append((required, provided))
-            return tuple(_results)
-
-        lb = self._makeOne(uc_subscriptions=_subscriptions)
-        found = lb.subscriptions('A', 'B')
-        self.assertEqual(found, tuple(_results))
-        self.assertEqual(_called_with, [(('A',), 'B')])
-
-    def test_subscriptions_cached(self):
-        _called_with = []
-        _results = [object(), object(), object()]
-
-        def _subscriptions(self, required, provided):
-            _called_with.append((required, provided))
-            return tuple(_results)
-
-        lb = self._makeOne(uc_subscriptions=_subscriptions)
-        found = lb.subscriptions('A', 'B')
-        found = lb.subscriptions('A', 'B')
-        self.assertEqual(found, tuple(_results))
-        self.assertEqual(_called_with, [(('A',), 'B')])
-
-
-class LookupBaseTests(LookupBaseFallbackTests,
-                      OptimizationTestMixin):
-
-    def _getTargetClass(self):
-        from zope.interface.adapter import LookupBase
-        return LookupBase
-
-
-class VerifyingBaseFallbackTests(unittest.TestCase):
-
-    def _getFallbackClass(self):
-        from zope.interface.adapter import VerifyingBaseFallback
-        return VerifyingBaseFallback
-
-    _getTargetClass = _getFallbackClass
-
-    def _makeOne(self, registry, uc_lookup=None, uc_lookupAll=None,
-                 uc_subscriptions=None):
-        # pylint:disable=function-redefined
-        if uc_lookup is None:
-
-            def uc_lookup(self, required, provided, name):
-                raise NotImplementedError()
-
-        if uc_lookupAll is None:
-
-            def uc_lookupAll(self, required, provided):
-                raise NotImplementedError()
-
-        if uc_subscriptions is None:
-
-            def uc_subscriptions(self, required, provided):
-                raise NotImplementedError()
-
-        class Derived(self._getTargetClass()):
-            _uncached_lookup = uc_lookup
-            _uncached_lookupAll = uc_lookupAll
-            _uncached_subscriptions = uc_subscriptions
-
-            def __init__(self, registry):
-                super().__init__()
-                self._registry = registry
-
-        derived = Derived(registry)
-        derived.changed(derived)  # init. '_verify_ro' / '_verify_generations'
-        return derived
-
-    def _makeRegistry(self, depth):
-
-        class WithGeneration:
-            _generation = 1
-
-        class Registry:
-            def __init__(self, depth):
-                self.ro = [WithGeneration() for i in range(depth)]
-
-        return Registry(depth)
-
-    def test_lookup(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        reg = self._makeRegistry(3)
-        lb = self._makeOne(reg, uc_lookup=_lookup)
-        found = lb.lookup(('A',), 'B', 'C')
-        found = lb.lookup(('A',), 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-        reg.ro[1]._generation += 1
-        found = lb.lookup(('A',), 'B', 'C')
-        self.assertIs(found, b)
-        self.assertEqual(_called_with,
-                         [(('A',), 'B', 'C'), (('A',), 'B', 'C')])
-        self.assertEqual(_results, [c])
-
-    def test_lookup1(self):
-        _called_with = []
-        a, b, c = object(), object(), object()
-        _results = [a, b, c]
-
-        def _lookup(self, required, provided, name):
-            _called_with.append((required, provided, name))
-            return _results.pop(0)
-
-        reg = self._makeRegistry(3)
-        lb = self._makeOne(reg, uc_lookup=_lookup)
-        found = lb.lookup1('A', 'B', 'C')
-        found = lb.lookup1('A', 'B', 'C')
-        self.assertIs(found, a)
-        self.assertEqual(_called_with, [(('A',), 'B', 'C')])
-        self.assertEqual(_results, [b, c])
-        reg.ro[1]._generation += 1
-        found = lb.lookup1('A', 'B', 'C')
-        self.assertIs(found, b)
-        self.assertEqual(_called_with,
-                         [(('A',), 'B', 'C'), (('A',), 'B', 'C')])
-        self.assertEqual(_results, [c])
-
-    def test_adapter_hook(self):
-        a, b, _c = [object(), object(), object()]  # noqa F841
-
-        def _factory1(context):
-            return a
-
-        def _factory2(context):
-            return b
-
-        def _factory3(context):
-            self.fail("This should never be called")
-
-        _factories = [_factory1, _factory2, _factory3]
-
-        def _lookup(self, required, provided, name):
-            return _factories.pop(0)
-
-        req, prv, _default = object(), object(), object()
-        reg = self._makeRegistry(3)
-        lb = self._makeOne(reg, uc_lookup=_lookup)
-        adapted = lb.adapter_hook(prv, req, 'C', _default)
-        self.assertIs(adapted, a)
-        adapted = lb.adapter_hook(prv, req, 'C', _default)
-        self.assertIs(adapted, a)
-        reg.ro[1]._generation += 1
-        adapted = lb.adapter_hook(prv, req, 'C', _default)
-        self.assertIs(adapted, b)
-
-    def test_queryAdapter(self):
-        a, b, _c = [object(), object(), object()]  # noqa F841
-
-        def _factory1(context):
-            return a
-
-        def _factory2(context):
-            return b
-
-        def _factory3(context):
-            self.fail("This should never be called")
-
-        _factories = [_factory1, _factory2, _factory3]
-
-        def _lookup(self, required, provided, name):
-            return _factories.pop(0)
-
-        req, prv, _default = object(), object(), object()
-        reg = self._makeRegistry(3)
-        lb = self._makeOne(reg, uc_lookup=_lookup)
-        adapted = lb.queryAdapter(req, prv, 'C', _default)
-        self.assertIs(adapted, a)
-        adapted = lb.queryAdapter(req, prv, 'C', _default)
-        self.assertIs(adapted, a)
-        reg.ro[1]._generation += 1
-        adapted = lb.adapter_hook(prv, req, 'C', _default)
-        self.assertIs(adapted, b)
-
-    def test_lookupAll(self):
-        _results_1 = [object(), object(), object()]
-        _results_2 = [object(), object(), object()]
-        _results = [_results_1, _results_2]
-
-        def _lookupAll(self, required, provided):
-            return tuple(_results.pop(0))
-
-        reg = self._makeRegistry(3)
-        lb = self._makeOne(reg, uc_lookupAll=_lookupAll)
-        found = lb.lookupAll('A', 'B')
-        self.assertEqual(found, tuple(_results_1))
-        found = lb.lookupAll('A', 'B')
-        self.assertEqual(found, tuple(_results_1))
-        reg.ro[1]._generation += 1
-        found = lb.lookupAll('A', 'B')
-        self.assertEqual(found, tuple(_results_2))
-
-    def test_subscriptions(self):
-        _results_1 = [object(), object(), object()]
-        _results_2 = [object(), object(), object()]
-        _results = [_results_1, _results_2]
-
-        def _subscriptions(self, required, provided):
-            return tuple(_results.pop(0))
-
-        reg = self._makeRegistry(3)
-        lb = self._makeOne(reg, uc_subscriptions=_subscriptions)
-        found = lb.subscriptions('A', 'B')
-        self.assertEqual(found, tuple(_results_1))
-        found = lb.subscriptions('A', 'B')
-        self.assertEqual(found, tuple(_results_1))
-        reg.ro[1]._generation += 1
-        found = lb.subscriptions('A', 'B')
-        self.assertEqual(found, tuple(_results_2))
-
-
-class VerifyingBaseTests(VerifyingBaseFallbackTests,
-                         OptimizationTestMixin):
-
-    def _getTargetClass(self):
-        from zope.interface.adapter import VerifyingBase
-        return VerifyingBase
-
-
-class AdapterLookupBaseTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.adapter import AdapterLookupBase
-        return AdapterLookupBase
-
-    def _makeOne(self, registry):
-        return self._getTargetClass()(registry)
-
-    def _makeSubregistry(self, *provided):
-
-        class Subregistry:
-            def __init__(self):
-                self._adapters = []
-                self._subscribers = []
-
-        return Subregistry()
-
-    def _makeRegistry(self, *provided):
-
-        class Registry:
-            def __init__(self, provided):
-                self._provided = provided
-                self.ro = []
-
-        return Registry(provided)
-
-    def test_ctor_empty_registry(self):
-        registry = self._makeRegistry()
-        alb = self._makeOne(registry)
-        self.assertEqual(alb._extendors, {})
-
-    def test_ctor_w_registry_provided(self):
-        from zope.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        alb = self._makeOne(registry)
-        self.assertEqual(sorted(alb._extendors.keys()),
-                         sorted([IBar, IFoo, Interface]))
-        self.assertEqual(alb._extendors[IFoo], [IFoo, IBar])
-        self.assertEqual(alb._extendors[IBar], [IBar])
-        self.assertEqual(sorted(alb._extendors[Interface]),
-                         sorted([IFoo, IBar]))
-
-    def test_changed_empty_required(self):
-        # ALB.changed expects to call a mixed in changed.
-
-        class Mixin:
-            def changed(self, *other):
-                pass
-
-        class Derived(self._getTargetClass(), Mixin):
-            pass
-
-        registry = self._makeRegistry()
-        alb = Derived(registry)
-        alb.changed(alb)
-
-    def test_changed_w_required(self):
-        # ALB.changed expects to call a mixed in changed.
-
-        class Mixin:
-            def changed(self, *other):
-                pass
-
-        class Derived(self._getTargetClass(), Mixin):
-            pass
-
-        class FauxWeakref:
-            _unsub = None
-
-            def __init__(self, here):
-                self._here = here
-
-            def __call__(self):
-                return self if self._here else None
-
-            def unsubscribe(self, target):
-                self._unsub = target
-
-        gone = FauxWeakref(False)
-        here = FauxWeakref(True)
-        registry = self._makeRegistry()
-        alb = Derived(registry)
-        alb._required[gone] = 1
-        alb._required[here] = 1
-        alb.changed(alb)
-        self.assertEqual(len(alb._required), 0)
-        self.assertEqual(gone._unsub, None)
-        self.assertEqual(here._unsub, alb)
-
-    def test_init_extendors_after_registry_update(self):
-        from zope.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        alb = self._makeOne(registry)
-        registry._provided = [IFoo, IBar]
-        alb.init_extendors()
-        self.assertEqual(sorted(alb._extendors.keys()),
-                         sorted([IBar, IFoo, Interface]))
-        self.assertEqual(alb._extendors[IFoo], [IFoo, IBar])
-        self.assertEqual(alb._extendors[IBar], [IBar])
-        self.assertEqual(sorted(alb._extendors[Interface]),
-                         sorted([IFoo, IBar]))
-
-    def test_add_extendor(self):
-        from zope.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        alb = self._makeOne(registry)
-        alb.add_extendor(IFoo)
-        alb.add_extendor(IBar)
-        self.assertEqual(sorted(alb._extendors.keys()),
-                         sorted([IBar, IFoo, Interface]))
-        self.assertEqual(alb._extendors[IFoo], [IFoo, IBar])
-        self.assertEqual(alb._extendors[IBar], [IBar])
-        self.assertEqual(sorted(alb._extendors[Interface]),
-                         sorted([IFoo, IBar]))
-
-    def test_remove_extendor(self):
-        from zope.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        alb = self._makeOne(registry)
-        alb.remove_extendor(IFoo)
-        self.assertEqual(sorted(alb._extendors.keys()),
-                         sorted([IFoo, IBar, Interface]))
-        self.assertEqual(alb._extendors[IFoo], [IBar])
-        self.assertEqual(alb._extendors[IBar], [IBar])
-        self.assertEqual(sorted(alb._extendors[Interface]),
-                         sorted([IBar]))
-
-    # test '_subscribe' via its callers, '_uncached_lookup', etc.
-
-    def test__uncached_lookup_empty_ro(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        alb = self._makeOne(registry)
-        result = alb._uncached_lookup((IFoo,), IBar)
-        self.assertEqual(result, None)
-        self.assertEqual(len(alb._required), 1)
-        self.assertIn(IFoo.weakref(), alb._required)
-
-    def test__uncached_lookup_order_miss(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        result = alb._uncached_lookup((IFoo,), IBar)
-        self.assertEqual(result, None)
-
-    def test__uncached_lookup_extendors_miss(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        subr = self._makeSubregistry()
-        subr._adapters = [{}, {}]  # utilities, single adapters
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookup((IFoo,), IBar)
-        self.assertEqual(result, None)
-
-    def test__uncached_lookup_components_miss_wrong_iface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        IQux = InterfaceClass('IQux')
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        irrelevant = object()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {
-                IFoo: {
-                    IQux: {'': irrelevant},
-                },
-            },
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookup((IFoo,), IBar)
-        self.assertEqual(result, None)
-
-    def test__uncached_lookup_components_miss_wrong_name(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-
-        wrongname = object()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {
-                IFoo: {
-                    IBar: {'wrongname': wrongname},
-                },
-            },
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookup((IFoo,), IBar)
-        self.assertEqual(result, None)
-
-    def test__uncached_lookup_simple_hit(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _expected = object()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': _expected}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookup((IFoo,), IBar)
-        self.assertIs(result, _expected)
-
-    def test__uncached_lookup_repeated_hit(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _expected = object()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': _expected}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookup((IFoo,), IBar)
-        result2 = alb._uncached_lookup((IFoo,), IBar)
-        self.assertIs(result, _expected)
-        self.assertIs(result2, _expected)
-
-    def test_queryMultiAdaptor_lookup_miss(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        registry = self._makeRegistry()
-        subr = self._makeSubregistry()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        alb.lookup = alb._uncached_lookup  # provided by derived
-        subr._v_lookup = alb
-        _default = object()
-        result = alb.queryMultiAdapter((foo,), IBar, default=_default)
-        self.assertIs(result, _default)
-
-    def test_queryMultiAdapter_errors_on_attribute_access(self):
-        # Any error on attribute access previously lead to using the _empty
-        # singleton as "requires" argument (See
-        # https://github.com/zopefoundation/zope.interface/issues/162)
-        # but after https://github.com/zopefoundation/zope.interface/issues/200
-        # they get propagated.
-        from zope.interface.interface import InterfaceClass
-        from zope.interface.tests import MissingSomeAttrs
-
-        IFoo = InterfaceClass('IFoo')
-        registry = self._makeRegistry()
-        alb = self._makeOne(registry)
-        alb.lookup = alb._uncached_lookup
-
-        def test(ob):
-            return alb.queryMultiAdapter(
-                (ob,),
-                IFoo,
-            )
-
-        MissingSomeAttrs.test_raises(self, test, expected_missing='__class__')
-
-    def test_queryMultiAdaptor_factory_miss(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _called_with = []
-
-        def _factory(context):
-            _called_with.append(context)
-
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': _factory}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        alb.lookup = alb._uncached_lookup  # provided by derived
-        subr._v_lookup = alb
-        _default = object()
-        result = alb.queryMultiAdapter((foo,), IBar, default=_default)
-        self.assertIs(result, _default)
-        self.assertEqual(_called_with, [foo])
-
-    def test_queryMultiAdaptor_factory_hit(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _expected = object()
-        _called_with = []
-
-        def _factory(context):
-            _called_with.append(context)
-            return _expected
-
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': _factory}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        alb.lookup = alb._uncached_lookup  # provided by derived
-        subr._v_lookup = alb
-        _default = object()
-        result = alb.queryMultiAdapter((foo,), IBar, default=_default)
-        self.assertIs(result, _expected)
-        self.assertEqual(_called_with, [foo])
-
-    def test_queryMultiAdapter_super_unwraps(self):
-        alb = self._makeOne(self._makeRegistry())
-
-        def lookup(*args):
-            return factory
-
-        def factory(*args):
-            return args
-
-        alb.lookup = lookup
-
-        objects = [
-            super(),
-            42,
-            "abc",
-            super(),
-        ]
-
-        result = alb.queryMultiAdapter(objects, None)
-        self.assertEqual(result, (
-            self,
-            42,
-            "abc",
-            self,
-        ))
-
-    def test__uncached_lookupAll_empty_ro(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        alb = self._makeOne(registry)
-        result = alb._uncached_lookupAll((IFoo,), IBar)
-        self.assertEqual(result, ())
-        self.assertEqual(len(alb._required), 1)
-        self.assertIn(IFoo.weakref(), alb._required)
-
-    def test__uncached_lookupAll_order_miss(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookupAll((IFoo,), IBar)
-        self.assertEqual(result, ())
-
-    def test__uncached_lookupAll_extendors_miss(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        subr = self._makeSubregistry()
-        subr._adapters = [{}, {}]  # utilities, single adapters
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookupAll((IFoo,), IBar)
-        self.assertEqual(result, ())
-
-    def test__uncached_lookupAll_components_miss(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        IQux = InterfaceClass('IQux')
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        irrelevant = object()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {IFoo: {IQux: {'': irrelevant}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookupAll((IFoo,), IBar)
-        self.assertEqual(result, ())
-
-    def test__uncached_lookupAll_simple_hit(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _expected = object()
-        _named = object()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': _expected, 'named': _named}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_lookupAll((IFoo,), IBar)
-        self.assertEqual(sorted(result), [('', _expected), ('named', _named)])
-
-    def test_names(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _expected = object()
-        _named = object()
-        subr._adapters = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': _expected, 'named': _named}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        alb.lookupAll = alb._uncached_lookupAll
-        subr._v_lookup = alb
-        result = alb.names((IFoo,), IBar)
-        self.assertEqual(sorted(result), ['', 'named'])
-
-    def test__uncached_subscriptions_empty_ro(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        alb = self._makeOne(registry)
-        result = alb._uncached_subscriptions((IFoo,), IBar)
-        self.assertEqual(result, [])
-        self.assertEqual(len(alb._required), 1)
-        self.assertIn(IFoo.weakref(), alb._required)
-
-    def test__uncached_subscriptions_order_miss(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_subscriptions((IFoo,), IBar)
-        self.assertEqual(result, [])
-
-    def test__uncached_subscriptions_extendors_miss(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry()
-        subr = self._makeSubregistry()
-        subr._subscribers = [{}, {}]  # utilities, single adapters
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_subscriptions((IFoo,), IBar)
-        self.assertEqual(result, [])
-
-    def test__uncached_subscriptions_components_miss_wrong_iface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        IQux = InterfaceClass('IQux')
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        irrelevant = object()
-        subr._subscribers = [  # utilities, single adapters
-            {},
-            {IFoo: {IQux: {'': irrelevant}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_subscriptions((IFoo,), IBar)
-        self.assertEqual(result, [])
-
-    def test__uncached_subscriptions_components_miss_wrong_name(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        wrongname = object()
-        subr._subscribers = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'wrongname': wrongname}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_subscriptions((IFoo,), IBar)
-        self.assertEqual(result, [])
-
-    def test__uncached_subscriptions_simple_hit(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-
-        class Foo:
-
-            def __lt__(self, other):
-                return True
-
-        _exp1, _exp2 = Foo(), Foo()
-        subr._subscribers = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': (_exp1, _exp2)}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        subr._v_lookup = alb
-        result = alb._uncached_subscriptions((IFoo,), IBar)
-        self.assertEqual(sorted(result), sorted([_exp1, _exp2]))
-
-    def test_subscribers_wo_provided(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        registry = self._makeRegistry(IFoo, IBar)
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _called = {}
-
-        def _factory1(context):
-            _called.setdefault('_factory1', []).append(context)
-
-        def _factory2(context):
-            _called.setdefault('_factory2', []).append(context)
-
-        subr._subscribers = [  # utilities, single adapters
-            {},
-            {IFoo: {None: {'': (_factory1, _factory2)}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        alb.subscriptions = alb._uncached_subscriptions
-        subr._v_lookup = alb
-        result = alb.subscribers((foo,), None)
-        self.assertEqual(result, ())
-        self.assertEqual(_called, {'_factory1': [foo], '_factory2': [foo]})
-
-    def test_subscribers_w_provided(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        registry = self._makeRegistry(IFoo, IBar)
-        registry = self._makeRegistry(IFoo, IBar)
-        subr = self._makeSubregistry()
-        _called = {}
-        _exp1, _exp2 = object(), object()
-
-        def _factory1(context):
-            _called.setdefault('_factory1', []).append(context)
-            return _exp1
-
-        def _factory2(context):
-            _called.setdefault('_factory2', []).append(context)
-            return _exp2
-
-        def _side_effect_only(context):
-            _called.setdefault('_side_effect_only', []).append(context)
-
-        subr._subscribers = [  # utilities, single adapters
-            {},
-            {IFoo: {IBar: {'': (_factory1, _factory2, _side_effect_only)}}},
-        ]
-        registry.ro.append(subr)
-        alb = self._makeOne(registry)
-        alb.subscriptions = alb._uncached_subscriptions
-        subr._v_lookup = alb
-        result = alb.subscribers((foo,), IBar)
-        self.assertEqual(result, [_exp1, _exp2])
-        self.assertEqual(
-            _called, {
-                '_factory1': [foo],
-                '_factory2': [foo],
-                '_side_effect_only': [foo],
-            }
-        )
-
-
-class VerifyingAdapterRegistryTests(unittest.TestCase):
-    # This is also the base for AdapterRegistryTests. That makes the
-    # inheritance seems backwards, but even though they implement the
-    # same interfaces, VAR and AR each only extend BAR; and neither
-    # one will pass the test cases for BAR (it uses a special
-    # LookupClass just for the tests).
-
-    def _getTargetClass(self):
-        from zope.interface.adapter import VerifyingAdapterRegistry
-        return VerifyingAdapterRegistry
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_verify_object_provides_IAdapterRegistry(self):
-        from zope.interface.interfaces import IAdapterRegistry
-        from zope.interface.verify import verifyObject
-        registry = self._makeOne()
-        verifyObject(IAdapterRegistry, registry)
-
-
-class AdapterRegistryTests(VerifyingAdapterRegistryTests):
-
-    def _getTargetClass(self):
-        from zope.interface.adapter import AdapterRegistry
-        return AdapterRegistry
-
-    def test_ctor_no_bases(self):
-        ar = self._makeOne()
-        self.assertEqual(len(ar._v_subregistries), 0)
-
-    def test_ctor_w_bases(self):
-        base = self._makeOne()
-        sub = self._makeOne([base])
-        self.assertEqual(len(sub._v_subregistries), 0)
-        self.assertEqual(len(base._v_subregistries), 1)
-        self.assertIn(sub, base._v_subregistries)
-
-    # test _addSubregistry / _removeSubregistry via only caller, _setBases
-
-    def test__setBases_removing_existing_subregistry(self):
-        before = self._makeOne()
-        after = self._makeOne()
-        sub = self._makeOne([before])
-        sub.__bases__ = [after]
-        self.assertEqual(len(before._v_subregistries), 0)
-        self.assertEqual(len(after._v_subregistries), 1)
-        self.assertIn(sub, after._v_subregistries)
-
-    def test__setBases_wo_stray_entry(self):
-        before = self._makeOne()
-        stray = self._makeOne()
-        after = self._makeOne()
-        sub = self._makeOne([before])
-        sub.__dict__['__bases__'].append(stray)
-        sub.__bases__ = [after]
-        self.assertEqual(len(before._v_subregistries), 0)
-        self.assertEqual(len(after._v_subregistries), 1)
-        self.assertIn(sub, after._v_subregistries)
-
-    def test__setBases_w_existing_entry_continuing(self):
-        before = self._makeOne()
-        after = self._makeOne()
-        sub = self._makeOne([before])
-        sub.__bases__ = [before, after]
-        self.assertEqual(len(before._v_subregistries), 1)
-        self.assertEqual(len(after._v_subregistries), 1)
-        self.assertIn(sub, before._v_subregistries)
-        self.assertIn(sub, after._v_subregistries)
-
-    def test_changed_w_subregistries(self):
-        base = self._makeOne()
-
-        class Derived:
-            _changed = None
-
-            def changed(self, originally_changed):
-                self._changed = originally_changed
-
-        derived1, derived2 = Derived(), Derived()
-        base._addSubregistry(derived1)
-        base._addSubregistry(derived2)
-        orig = object()
-        base.changed(orig)
-        self.assertIs(derived1._changed, orig)
-        self.assertIs(derived2._changed, orig)
-
-
-class Test_utils(unittest.TestCase):
-
-    def test__convert_None_to_Interface_w_None(self):
-        from zope.interface.adapter import _convert_None_to_Interface
-        from zope.interface.interface import Interface
-        self.assertIs(_convert_None_to_Interface(None), Interface)
-
-    def test__convert_None_to_Interface_w_other(self):
-        from zope.interface.adapter import _convert_None_to_Interface
-        other = object()
-        self.assertIs(_convert_None_to_Interface(other), other)
-
-    def test__normalize_name_str(self):
-        from zope.interface.adapter import _normalize_name
-        STR = b'str'
-        UNICODE = 'str'
-        norm = _normalize_name(STR)
-        self.assertEqual(norm, UNICODE)
-        self.assertIsInstance(norm, type(UNICODE))
-
-    def test__normalize_name_unicode(self):
-        from zope.interface.adapter import _normalize_name
-
-        USTR = 'ustr'
-        self.assertEqual(_normalize_name(USTR), USTR)
-
-    def test__normalize_name_other(self):
-        from zope.interface.adapter import _normalize_name
-        for other in 1, 1.0, (), [], {}, object():
-            self.assertRaises(TypeError, _normalize_name, other)
-
-    # _lookup, _lookupAll, and _subscriptions tested via their callers
-    # (AdapterLookupBase.{lookup,lookupAll,subscriptions}).
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_advice.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_advice.py
deleted file mode 100644
index 9612b6f..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_advice.py
+++ /dev/null
@@ -1,217 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Tests for advice
-
-This module was adapted from 'protocols.tests.advice', part of the Python
-Enterprise Application Kit (PEAK).  Please notify the PEAK authors
-(pje@telecommunity.com and tsarna@sarna.org) if bugs are found or
-Zope-specific changes are required, so that the PEAK version of this module
-can be kept in sync.
-
-PEAK is a Python application framework that interoperates with (but does
-not require) Zope 3 and Twisted.  It provides tools for manipulating UML
-models, object-relational persistence, aspect-oriented programming, and more.
-Visit the PEAK home page at http://peak.telecommunity.com for more information.
-"""
-
-import sys
-import unittest
-
-
-class FrameInfoTest(unittest.TestCase):
-
-    def test_w_module(self):
-        from zope.interface.tests import advisory_testing
-        (kind, module,
-         f_locals, f_globals) = advisory_testing.moduleLevelFrameInfo
-        self.assertEqual(kind, "module")
-        for d in module.__dict__, f_locals, f_globals:
-            self.assertIs(d, advisory_testing.my_globals)
-
-    def test_w_class(self):
-        from zope.interface.tests import advisory_testing
-        (kind,
-         module,
-         f_locals,
-         f_globals) = advisory_testing.NewStyleClass.classLevelFrameInfo
-        self.assertEqual(kind, "class")
-
-        for d in module.__dict__, f_globals:
-            self.assertIs(d, advisory_testing.my_globals)
-
-    def test_inside_function_call(self):
-        from zope.interface.advice import getFrameInfo
-        kind, module, f_locals, f_globals = getFrameInfo(sys._getframe())
-        self.assertEqual(kind, "function call")
-
-        frame = sys._getframe()
-        self.assertEqual(f_locals, frame.f_locals)
-        self.assertEqual(f_locals, locals())
-
-        for d in module.__dict__, f_globals:
-            self.assertIs(d, globals())
-
-    def test_inside_exec(self):
-        from zope.interface.advice import getFrameInfo
-        _globals = {'getFrameInfo': getFrameInfo}
-        _locals = {}
-        exec(_FUNKY_EXEC, _globals, _locals)
-        self.assertEqual(_locals['kind'], "exec")
-        self.assertIs(_locals['f_locals'], _locals)
-        self.assertIsNone(_locals['module'])
-        self.assertIs(_locals['f_globals'], _globals)
-
-
-_FUNKY_EXEC = """\
-import sys
-kind, module, f_locals, f_globals = getFrameInfo(sys._getframe())
-"""
-
-
-class Test_isClassAdvisor(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.advice import isClassAdvisor
-        return isClassAdvisor(*args, **kw)
-
-    def test_w_non_function(self):
-        self.assertEqual(self._callFUT(self), False)
-
-    def test_w_normal_function(self):
-
-        def foo():
-            raise NotImplementedError()
-
-        self.assertEqual(self._callFUT(foo), False)
-
-    def test_w_advisor_function(self):
-
-        def bar():
-            raise NotImplementedError()
-
-        bar.previousMetaclass = object()
-        self.assertEqual(self._callFUT(bar), True)
-
-
-class Test_determineMetaclass(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.advice import determineMetaclass
-        return determineMetaclass(*args, **kw)
-
-    def test_empty_w_explicit_metatype(self):
-
-        class Meta(type):
-            pass
-
-        self.assertEqual(self._callFUT((), Meta), Meta)
-
-    def test_single(self):
-
-        class Meta(type):
-            pass
-
-        self.assertEqual(self._callFUT((Meta,)), type)
-
-    def test_meta_of_class(self):
-
-        class Metameta(type):
-            pass
-
-        class Meta(type, metaclass=Metameta):
-            pass
-
-        self.assertEqual(self._callFUT((Meta, type)), Metameta)
-
-    def test_multiple_in_hierarchy_py3k(self):
-
-        class Meta_A(type):
-            pass
-
-        class Meta_B(Meta_A):
-            pass
-
-        class A(type, metaclass=Meta_A):
-            pass
-
-        class B(type, metaclass=Meta_B):
-            pass
-
-        self.assertEqual(self._callFUT((A, B)), Meta_B)
-
-    def test_multiple_not_in_hierarchy_py3k(self):
-
-        class Meta_A(type):
-            pass
-
-        class Meta_B(type):
-            pass
-
-        class A(type, metaclass=Meta_A):
-            pass
-
-        class B(type, metaclass=Meta_B):
-            pass
-
-        self.assertRaises(TypeError, self._callFUT, (A, B))
-
-
-class Test_minimalBases(unittest.TestCase):
-
-    def _callFUT(self, klasses):
-        from zope.interface.advice import minimalBases
-        return minimalBases(klasses)
-
-    def test_empty(self):
-        self.assertEqual(self._callFUT([]), [])
-
-    def test_w_newstyle_meta(self):
-        self.assertEqual(self._callFUT([type]), [type])
-
-    def test_w_newstyle_class(self):
-
-        class C:
-            pass
-
-        self.assertEqual(self._callFUT([C]), [C])
-
-    def test_simple_hierarchy_skips_implied(self):
-
-        class A:
-            pass
-
-        class B(A):
-            pass
-
-        class C(B):
-            pass
-
-        class D:
-            pass
-
-        self.assertEqual(self._callFUT([A, B, C]), [C])
-        self.assertEqual(self._callFUT([A, C]), [C])
-        self.assertEqual(self._callFUT([B, C]), [C])
-        self.assertEqual(self._callFUT([A, B]), [B])
-        self.assertEqual(self._callFUT([D, B, D]), [B, D])
-
-    def test_repeats_kicked_to_end_of_queue(self):
-
-        class A:
-            pass
-
-        class B:
-            pass
-
-        self.assertEqual(self._callFUT([A, B, A]), [B, A])
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_compile_flags.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_compile_flags.py
deleted file mode 100644
index 3455c44..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_compile_flags.py
+++ /dev/null
@@ -1,29 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2022 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE
-#
-##############################################################################
-import struct
-import unittest
-
-import zope.interface  # noqa: try to load a C module for side effects
-
-
-class TestFloatingPoint(unittest.TestCase):
-
-    def test_no_fast_math_optimization(self):
-        # Building with -Ofast enables -ffast-math, which sets certain FPU
-        # flags that can cause breakage elsewhere.  A library such as BTrees
-        # has no business changing global FPU flags for the entire process.
-        zero_bits = struct.unpack("!Q", struct.pack("!d", 0.0))[0]
-        next_up = zero_bits + 1
-        smallest_subnormal = struct.unpack("!d", struct.pack("!Q", next_up))[0]
-        self.assertNotEqual(smallest_subnormal, 0.0)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_declarations.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_declarations.py
deleted file mode 100644
index f6bdfde..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_declarations.py
+++ /dev/null
@@ -1,2685 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Test the new API for making and checking interface declarations
-"""
-import unittest
-
-from zope.interface.tests import MissingSomeAttrs
-from zope.interface.tests import OptimizationTestMixin
-from zope.interface.tests import SubclassableMixin
-from zope.interface.tests.test_interface import \
-    NameAndModuleComparisonTestsMixin
-
-
-# pylint:disable=inherit-non-class,too-many-lines,protected-access
-# pylint:disable=blacklisted-name,attribute-defined-outside-init
-
-class _Py3ClassAdvice:
-
-    def _run_generated_code(
-        self, code, globs, locs, fails_under_py3k=True,
-    ):
-        # pylint:disable=exec-used,no-member
-        import warnings
-        with warnings.catch_warnings(record=True) as _:
-            warnings.resetwarnings()
-
-            try:
-                exec(code, globs, locs)
-            except TypeError:
-                return False
-            else:
-                if fails_under_py3k:
-                    self.fail("Didn't raise TypeError")
-            return None
-
-
-class NamedTests(unittest.TestCase):
-
-    def test_class(self):
-        from zope.interface.declarations import named
-
-        @named('foo')
-        class Foo:
-            pass
-
-        self.assertEqual(
-            Foo.__component_name__, 'foo'
-        )  # pylint:disable=no-member
-
-    def test_function(self):
-        from zope.interface.declarations import named
-
-        @named('foo')
-        def doFoo(o):
-            raise NotImplementedError()
-
-        self.assertEqual(doFoo.__component_name__, 'foo')
-
-    def test_instance(self):
-        from zope.interface.declarations import named
-
-        class Foo:
-            pass
-        foo = Foo()
-        named('foo')(foo)
-
-        self.assertEqual(
-            foo.__component_name__, 'foo'
-        )  # pylint:disable=no-member
-
-
-class EmptyDeclarationTests(unittest.TestCase):
-    # Tests that should pass for all objects that are empty
-    # declarations. This includes a Declaration explicitly created
-    # that way, and the empty ImmutableDeclaration.
-    def _getEmpty(self):
-        from zope.interface.declarations import Declaration
-        return Declaration()
-
-    def test___iter___empty(self):
-        decl = self._getEmpty()
-        self.assertEqual(list(decl), [])
-
-    def test_flattened_empty(self):
-        from zope.interface.interface import Interface
-        decl = self._getEmpty()
-        self.assertEqual(list(decl.flattened()), [Interface])
-
-    def test___contains___empty(self):
-        from zope.interface.interface import Interface
-        decl = self._getEmpty()
-        self.assertNotIn(Interface, decl)
-
-    def test_extends_empty(self):
-        from zope.interface.interface import Interface
-        decl = self._getEmpty()
-        self.assertTrue(decl.extends(Interface))
-        self.assertTrue(decl.extends(Interface, strict=True))
-
-    def test_interfaces_empty(self):
-        decl = self._getEmpty()
-        iface_list = list(decl.interfaces())
-        self.assertEqual(iface_list, [])
-
-    def test___sro___(self):
-        from zope.interface.interface import Interface
-        decl = self._getEmpty()
-        self.assertEqual(decl.__sro__, (decl, Interface,))
-
-    def test___iro___(self):
-        from zope.interface.interface import Interface
-        decl = self._getEmpty()
-        self.assertEqual(decl.__iro__, (Interface,))
-
-    def test_get(self):
-        decl = self._getEmpty()
-        self.assertIsNone(decl.get('attr'))
-        self.assertEqual(decl.get('abc', 'def'), 'def')
-        # It's a positive cache only (when it even exists)
-        # so this added nothing.
-        self.assertFalse(decl._v_attrs)
-
-    def test_changed_w_existing__v_attrs(self):
-        decl = self._getEmpty()
-        decl._v_attrs = object()
-        decl.changed(decl)
-        self.assertFalse(decl._v_attrs)
-
-
-class DeclarationTests(EmptyDeclarationTests):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import Declaration
-        return Declaration
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_ctor_no_bases(self):
-        decl = self._makeOne()
-        self.assertEqual(list(decl.__bases__), [])
-
-    def test_ctor_w_interface_in_bases(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decl = self._makeOne(IFoo)
-        self.assertEqual(list(decl.__bases__), [IFoo])
-
-    def test_ctor_w_implements_in_bases(self):
-        from zope.interface.declarations import Implements
-        impl = Implements()
-        decl = self._makeOne(impl)
-        self.assertEqual(list(decl.__bases__), [impl])
-
-    def test_changed_wo_existing__v_attrs(self):
-        decl = self._makeOne()
-        decl.changed(decl)  # doesn't raise
-        self.assertIsNone(decl._v_attrs)
-
-    def test___contains__w_self(self):
-        decl = self._makeOne()
-        self.assertNotIn(decl, decl)
-
-    def test___contains__w_unrelated_iface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decl = self._makeOne()
-        self.assertNotIn(IFoo, decl)
-
-    def test___contains__w_base_interface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decl = self._makeOne(IFoo)
-        self.assertIn(IFoo, decl)
-
-    def test___iter___single_base(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decl = self._makeOne(IFoo)
-        self.assertEqual(list(decl), [IFoo])
-
-    def test___iter___multiple_bases(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        decl = self._makeOne(IFoo, IBar)
-        self.assertEqual(list(decl), [IFoo, IBar])
-
-    def test___iter___inheritance(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        decl = self._makeOne(IBar)
-        self.assertEqual(list(decl), [IBar])  # IBar.interfaces() omits bases
-
-    def test___iter___w_nested_sequence_overlap(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        decl = self._makeOne(IBar, (IFoo, IBar))
-        self.assertEqual(list(decl), [IBar, IFoo])
-
-    def test_flattened_single_base(self):
-        from zope.interface.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decl = self._makeOne(IFoo)
-        self.assertEqual(list(decl.flattened()), [IFoo, Interface])
-
-    def test_flattened_multiple_bases(self):
-        from zope.interface.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        decl = self._makeOne(IFoo, IBar)
-        self.assertEqual(list(decl.flattened()), [IFoo, IBar, Interface])
-
-    def test_flattened_inheritance(self):
-        from zope.interface.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        decl = self._makeOne(IBar)
-        self.assertEqual(list(decl.flattened()), [IBar, IFoo, Interface])
-
-    def test_flattened_w_nested_sequence_overlap(self):
-        from zope.interface.interface import Interface
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        # This is the same as calling ``Declaration(IBar, IFoo, IBar)``
-        # which doesn't make much sense, but here it is. In older
-        # versions of zope.interface, the __iro__ would have been
-        # IFoo, IBar, Interface, which especially makes no sense.
-        decl = self._makeOne(IBar, (IFoo, IBar))
-        # Note that decl.__iro__ has IFoo first.
-        self.assertEqual(list(decl.flattened()), [IBar, IFoo, Interface])
-
-    def test___sub___unrelated_interface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        before = self._makeOne(IFoo)
-        after = before - IBar
-        self.assertIsInstance(after, self._getTargetClass())
-        self.assertEqual(list(after), [IFoo])
-
-    def test___sub___related_interface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        before = self._makeOne(IFoo)
-        after = before - IFoo
-        self.assertEqual(list(after), [])
-
-    def test___sub___related_interface_by_inheritance(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar', (IFoo,))
-        before = self._makeOne(IBar)
-        after = before - IBar
-        self.assertEqual(list(after), [])
-
-    def test___add___unrelated_interface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        before = self._makeOne(IFoo)
-        after = before + IBar
-        self.assertIsInstance(after, self._getTargetClass())
-        self.assertEqual(list(after), [IFoo, IBar])
-
-    def test___add___related_interface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        IBaz = InterfaceClass('IBaz')
-        before = self._makeOne(IFoo, IBar)
-        other = self._makeOne(IBar, IBaz)
-        after = before + other
-        self.assertEqual(list(after), [IFoo, IBar, IBaz])
-
-    def test___add___overlapping_interface(self):
-        # The derived interfaces end up with higher priority, and
-        # don't produce a C3 resolution order violation. This
-        # example produced a C3 error, and the resulting legacy order
-        # used to be wrong ([IBase, IDerived] instead of
-        # the other way).
-        from zope.interface import Interface
-        from zope.interface import ro
-        from zope.interface.interface import InterfaceClass
-        from zope.interface.tests.test_ro import C3Setting
-
-        IBase = InterfaceClass('IBase')
-        IDerived = InterfaceClass('IDerived', (IBase,))
-
-        with C3Setting(ro.C3.STRICT_IRO, True):
-            base = self._makeOne(IBase)
-            after = base + IDerived
-
-        self.assertEqual(after.__iro__, (IDerived, IBase, Interface))
-        self.assertEqual(after.__bases__, (IDerived, IBase))
-        self.assertEqual(list(after), [IDerived, IBase])
-
-    def test___add___overlapping_interface_implementedBy(self):
-        # Like test___add___overlapping_interface, but pulling
-        # in a realistic example. This one previously produced a
-        # C3 error, but the resulting legacy order was (somehow)
-        # correct.
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import implementer
-        from zope.interface import ro
-        from zope.interface.tests.test_ro import C3Setting
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        with C3Setting(ro.C3.STRICT_IRO, True):
-            after = implementedBy(Base) + IDerived
-
-        self.assertEqual(after.__sro__, (after, IDerived, IBase, Interface))
-        self.assertEqual(after.__bases__, (IDerived, IBase))
-        self.assertEqual(list(after), [IDerived, IBase])
-
-
-class TestImmutableDeclaration(EmptyDeclarationTests):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import _ImmutableDeclaration
-        return _ImmutableDeclaration
-
-    def _getEmpty(self):
-        from zope.interface.declarations import _empty
-        return _empty
-
-    def test_pickle(self):
-        import pickle
-        copied = pickle.loads(pickle.dumps(self._getEmpty()))
-        self.assertIs(copied, self._getEmpty())
-
-    def test_singleton(self):
-        self.assertIs(
-            self._getTargetClass()(),
-            self._getEmpty()
-        )
-
-    def test__bases__(self):
-        self.assertEqual(self._getEmpty().__bases__, ())
-
-    def test_change__bases__(self):
-        empty = self._getEmpty()
-        empty.__bases__ = ()
-        self.assertEqual(self._getEmpty().__bases__, ())
-
-        with self.assertRaises(TypeError):
-            empty.__bases__ = (1,)
-
-    def test_dependents(self):
-        empty = self._getEmpty()
-        deps = empty.dependents
-        self.assertEqual({}, deps)
-        # Doesn't change the return.
-        deps[1] = 2
-        self.assertEqual({}, empty.dependents)
-
-    def test_changed(self):
-        # Does nothing, has no visible side-effects
-        self._getEmpty().changed(None)
-
-    def test_extends_always_false(self):
-        self.assertFalse(self._getEmpty().extends(self))
-        self.assertFalse(self._getEmpty().extends(self, strict=True))
-        self.assertFalse(self._getEmpty().extends(self, strict=False))
-
-    def test_get_always_default(self):
-        self.assertIsNone(self._getEmpty().get('name'))
-        self.assertEqual(self._getEmpty().get('name', 42), 42)
-
-    def test_v_attrs(self):
-        decl = self._getEmpty()
-        self.assertEqual(decl._v_attrs, {})
-
-        decl._v_attrs['attr'] = 42
-        self.assertEqual(decl._v_attrs, {})
-        self.assertIsNone(decl.get('attr'))
-
-        attrs = decl._v_attrs = {}
-        attrs['attr'] = 42
-        self.assertEqual(decl._v_attrs, {})
-        self.assertIsNone(decl.get('attr'))
-
-
-class TestImplements(NameAndModuleComparisonTestsMixin,
-                     unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import Implements
-        return Implements
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def _makeOneToCompare(self):
-        from zope.interface.declarations import implementedBy
-
-        class A:
-            pass
-
-        return implementedBy(A)
-
-    def test_ctor_no_bases(self):
-        impl = self._makeOne()
-        self.assertEqual(impl.inherit, None)
-        self.assertEqual(impl.declared, ())
-        self.assertEqual(impl.__name__, '?')
-        self.assertEqual(list(impl.__bases__), [])
-
-    def test___repr__(self):
-        impl = self._makeOne()
-        impl.__name__ = 'Testing'
-        self.assertEqual(repr(impl), 'classImplements(Testing)')
-
-    def test___reduce__(self):
-        from zope.interface.declarations import implementedBy
-        impl = self._makeOne()
-        self.assertEqual(impl.__reduce__(), (implementedBy, (None,)))
-
-    def test_sort(self):
-        from zope.interface.declarations import implementedBy
-        from zope.interface.interface import InterfaceClass
-
-        class A:
-            pass
-
-        class B:
-            pass
-
-        IFoo = InterfaceClass('IFoo')
-
-        self.assertEqual(implementedBy(A), implementedBy(A))
-        self.assertEqual(hash(implementedBy(A)), hash(implementedBy(A)))
-        self.assertLess(implementedBy(A), None)
-        self.assertGreater(
-            None,
-            implementedBy(A)
-        )
-        self.assertLess(implementedBy(A), implementedBy(B))
-        self.assertGreater(implementedBy(A), IFoo)
-        self.assertLessEqual(implementedBy(A), implementedBy(B))
-        self.assertGreaterEqual(implementedBy(A), IFoo)
-        self.assertNotEqual(implementedBy(A), IFoo)
-
-    def test_proxy_equality(self):
-        # https://github.com/zopefoundation/zope.interface/issues/55
-        from zope.interface.declarations import implementedBy
-
-        class Proxy:
-            def __init__(self, wrapped):
-                self._wrapped = wrapped
-
-            def __getattr__(self, name):
-                raise NotImplementedError()
-
-            def __eq__(self, other):
-                return self._wrapped == other
-
-            def __ne__(self, other):
-                return self._wrapped != other
-
-        class A:
-            pass
-
-        class B:
-            pass
-
-        implementedByA = implementedBy(A)
-        implementedByB = implementedBy(B)
-        proxy = Proxy(implementedByA)
-
-        # The order of arguments to the operators matters,
-        # test both
-        self.assertEqual(
-            implementedByA,
-            implementedByA
-        )
-        self.assertNotEqual(implementedByA, implementedByB)
-        self.assertNotEqual(implementedByB, implementedByA)
-
-        self.assertEqual(proxy, implementedByA)
-        self.assertEqual(implementedByA, proxy)
-        self.assertEqual(proxy, implementedByA)
-        self.assertEqual(implementedByA, proxy)
-
-        self.assertNotEqual(proxy, implementedByB)
-        self.assertNotEqual(implementedByB, proxy)
-
-    def test_changed_deletes_super_cache(self):
-        impl = self._makeOne()
-        self.assertIsNone(impl._super_cache)
-        self.assertNotIn('_super_cache', impl.__dict__)
-
-        impl._super_cache = 42
-        self.assertIn('_super_cache', impl.__dict__)
-
-        impl.changed(None)
-        self.assertIsNone(impl._super_cache)
-        self.assertNotIn('_super_cache', impl.__dict__)
-
-    def test_changed_does_not_add_super_cache(self):
-        impl = self._makeOne()
-        self.assertIsNone(impl._super_cache)
-        self.assertNotIn('_super_cache', impl.__dict__)
-
-        impl.changed(None)
-        self.assertIsNone(impl._super_cache)
-        self.assertNotIn('_super_cache', impl.__dict__)
-
-
-class Test_implementedByFallback(unittest.TestCase):
-
-    def _getTargetClass(self):
-        # pylint:disable=no-name-in-module
-        from zope.interface.declarations import implementedByFallback
-        return implementedByFallback
-
-    _getFallbackClass = _getTargetClass
-
-    def _callFUT(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_dictless_wo_existing_Implements_wo_registrations(self):
-        class Foo:
-            __slots__ = ('__implemented__',)
-        foo = Foo()
-        foo.__implemented__ = None
-        self.assertEqual(list(self._callFUT(foo)), [])
-
-    def test_dictless_wo_existing_Implements_cant_assign___implemented__(self):
-
-        class Foo:
-            def _get_impl(self):
-                raise NotImplementedError()
-
-            def _set_impl(self, val):
-                raise TypeError
-
-            __implemented__ = property(_get_impl, _set_impl)
-
-            def __call__(self):
-                # act like a factory
-                raise NotImplementedError()
-
-        foo = Foo()
-        self.assertRaises(TypeError, self._callFUT, foo)
-
-    def test_dictless_wo_existing_Implements_w_registrations(self):
-        from zope.interface import declarations
-
-        class Foo:
-            __slots__ = ('__implemented__',)
-
-        foo = Foo()
-        foo.__implemented__ = None
-        reg = object()
-        with _MonkeyDict(declarations,
-                         'BuiltinImplementationSpecifications') as specs:
-            specs[foo] = reg
-            self.assertIs(self._callFUT(foo), reg)
-
-    def test_dictless_w_existing_Implements(self):
-        from zope.interface.declarations import Implements
-        impl = Implements()
-
-        class Foo:
-            __slots__ = ('__implemented__',)
-
-        foo = Foo()
-        foo.__implemented__ = impl
-        self.assertIs(self._callFUT(foo), impl)
-
-    def test_dictless_w_existing_not_Implements(self):
-        from zope.interface.interface import InterfaceClass
-
-        class Foo:
-            __slots__ = ('__implemented__',)
-
-        foo = Foo()
-        IFoo = InterfaceClass('IFoo')
-        foo.__implemented__ = (IFoo,)
-        self.assertEqual(list(self._callFUT(foo)), [IFoo])
-
-    def test_w_existing_attr_as_Implements(self):
-        from zope.interface.declarations import Implements
-        impl = Implements()
-
-        class Foo:
-            __implemented__ = impl
-
-        self.assertIs(self._callFUT(Foo), impl)
-
-    def test_builtins_added_to_cache(self):
-        from zope.interface import declarations
-        from zope.interface.declarations import Implements
-        with _MonkeyDict(declarations,
-                         'BuiltinImplementationSpecifications') as specs:
-            self.assertEqual(list(self._callFUT(tuple)), [])
-            self.assertEqual(list(self._callFUT(list)), [])
-            self.assertEqual(list(self._callFUT(dict)), [])
-            for typ in (tuple, list, dict):
-                spec = specs[typ]
-                self.assertIsInstance(spec, Implements)
-                self.assertEqual(repr(spec),
-                                 'classImplements(%s)'
-                                 % (typ.__name__,))
-
-    def test_builtins_w_existing_cache(self):
-        from zope.interface import declarations
-        t_spec, l_spec, d_spec = object(), object(), object()
-        with _MonkeyDict(declarations,
-                         'BuiltinImplementationSpecifications') as specs:
-            specs[tuple] = t_spec
-            specs[list] = l_spec
-            specs[dict] = d_spec
-            self.assertIs(self._callFUT(tuple), t_spec)
-            self.assertIs(self._callFUT(list), l_spec)
-            self.assertIs(self._callFUT(dict), d_spec)
-
-    def test_oldstyle_class_no_assertions(self):
-        # TODO: Figure out P3 story
-
-        class Foo:
-            pass
-
-        self.assertEqual(list(self._callFUT(Foo)), [])
-
-    def test_no_assertions(self):
-        # TODO: Figure out P3 story
-
-        class Foo:
-            pass
-
-        self.assertEqual(list(self._callFUT(Foo)), [])
-
-    def test_w_None_no_bases_not_factory(self):
-
-        class Foo:
-            __implemented__ = None
-
-        foo = Foo()
-        self.assertRaises(TypeError, self._callFUT, foo)
-
-    def test_w_None_no_bases_w_factory(self):
-        from zope.interface.declarations import objectSpecificationDescriptor
-
-        class Foo:
-            __implemented__ = None
-
-            def __call__(self):
-                raise NotImplementedError()
-
-        foo = Foo()
-        foo.__name__ = 'foo'
-        spec = self._callFUT(foo)
-        self.assertEqual(spec.__name__,
-                         'zope.interface.tests.test_declarations.foo')
-        self.assertIs(spec.inherit, foo)
-        self.assertIs(foo.__implemented__, spec)
-        self.assertIs(
-            foo.__providedBy__, objectSpecificationDescriptor
-        )  # pylint:disable=no-member
-        self.assertNotIn('__provides__', foo.__dict__)
-
-    def test_w_None_no_bases_w_class(self):
-        from zope.interface.declarations import ClassProvides
-
-        class Foo:
-            __implemented__ = None
-
-        spec = self._callFUT(Foo)
-        self.assertEqual(spec.__name__,
-                         'zope.interface.tests.test_declarations.Foo')
-        self.assertIs(spec.inherit, Foo)
-        self.assertIs(Foo.__implemented__, spec)
-        self.assertIsInstance(
-            Foo.__providedBy__, ClassProvides
-        )  # pylint:disable=no-member
-        self.assertIsInstance(
-            Foo.__provides__, ClassProvides
-        )  # pylint:disable=no-member
-        self.assertEqual(
-            Foo.__provides__, Foo.__providedBy__
-        )  # pylint:disable=no-member
-
-    def test_w_existing_Implements(self):
-        from zope.interface.declarations import Implements
-        impl = Implements()
-
-        class Foo:
-            __implemented__ = impl
-
-        self.assertIs(self._callFUT(Foo), impl)
-
-    def test_super_when_base_implements_interface(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        @implementer(IDerived)
-        class Derived(Base):
-            pass
-
-        self.assertEqual(list(self._callFUT(Derived)), [IDerived, IBase])
-        sup = super(Derived, Derived)
-        self.assertEqual(list(self._callFUT(sup)), [IBase])
-
-    def test_super_when_base_implements_interface_diamond(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        class Child1(Base):
-            pass
-
-        class Child2(Base):
-            pass
-
-        @implementer(IDerived)
-        class Derived(Child1, Child2):
-            pass
-
-        self.assertEqual(list(self._callFUT(Derived)), [IDerived, IBase])
-        sup = super(Derived, Derived)
-        self.assertEqual(list(self._callFUT(sup)), [IBase])
-
-    def test_super_when_parent_implements_interface_diamond(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class Base:
-            pass
-
-        class Child1(Base):
-            pass
-
-        @implementer(IBase)
-        class Child2(Base):
-            pass
-
-        @implementer(IDerived)
-        class Derived(Child1, Child2):
-            pass
-
-        self.assertEqual(
-            Derived.__mro__, (Derived, Child1, Child2, Base, object)
-        )
-        self.assertEqual(list(self._callFUT(Derived)), [IDerived, IBase])
-        sup = super(Derived, Derived)
-        fut = self._callFUT(sup)
-        self.assertEqual(list(fut), [IBase])
-        self.assertIsNone(fut._dependents)
-
-    def test_super_when_base_doesnt_implement_interface(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class Base:
-            pass
-
-        @implementer(IDerived)
-        class Derived(Base):
-            pass
-
-        self.assertEqual(list(self._callFUT(Derived)), [IDerived])
-
-        sup = super(Derived, Derived)
-        self.assertEqual(list(self._callFUT(sup)), [])
-
-    def test_super_when_base_is_object(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IDerived)
-        class Derived:
-            pass
-
-        self.assertEqual(list(self._callFUT(Derived)), [IDerived])
-
-        sup = super(Derived, Derived)
-        self.assertEqual(list(self._callFUT(sup)), [])
-
-    def test_super_multi_level_multi_inheritance(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IM1(Interface):
-            pass
-
-        class IM2(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class IUnrelated(Interface):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        @implementer(IM1)
-        class M1(Base):
-            pass
-
-        @implementer(IM2)
-        class M2(Base):
-            pass
-
-        @implementer(IDerived, IUnrelated)
-        class Derived(M1, M2):
-            pass
-
-        d = Derived
-        sd = super(Derived, Derived)
-        sm1 = super(M1, Derived)
-        sm2 = super(M2, Derived)
-
-        self.assertEqual(list(self._callFUT(d)),
-                         [IDerived, IUnrelated, IM1, IBase, IM2])
-        self.assertEqual(list(self._callFUT(sd)),
-                         [IM1, IBase, IM2])
-        self.assertEqual(list(self._callFUT(sm1)),
-                         [IM2, IBase])
-        self.assertEqual(list(self._callFUT(sm2)),
-                         [IBase])
-
-
-class Test_implementedBy(Test_implementedByFallback,
-                         OptimizationTestMixin):
-    # Repeat tests for C optimizations
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import implementedBy
-        return implementedBy
-
-
-class _ImplementsTestMixin:
-    FUT_SETS_PROVIDED_BY = True
-
-    def _callFUT(self, cls, iface):
-        # Declare that *cls* implements *iface*; return *cls*
-        raise NotImplementedError
-
-    def _check_implementer(self, Foo,
-                           orig_spec=None,
-                           spec_name=__name__ + '.Foo',
-                           inherit="not given"):
-        from zope.interface.declarations import ClassProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-
-        returned = self._callFUT(Foo, IFoo)
-
-        self.assertIs(returned, Foo)
-        spec = Foo.__implemented__
-        if orig_spec is not None:
-            self.assertIs(spec, orig_spec)
-
-        self.assertEqual(spec.__name__,
-                         spec_name)
-        inherit = Foo if inherit == "not given" else inherit
-        self.assertIs(spec.inherit, inherit)
-        self.assertIs(Foo.__implemented__, spec)
-        if self.FUT_SETS_PROVIDED_BY:
-            self.assertIsInstance(Foo.__providedBy__, ClassProvides)
-            self.assertIsInstance(Foo.__provides__, ClassProvides)
-            self.assertEqual(Foo.__provides__, Foo.__providedBy__)
-
-        return Foo, IFoo
-
-    def test_class(self):
-
-        class Foo:
-            pass
-
-        self._check_implementer(Foo)
-
-
-class Test_classImplementsOnly(_ImplementsTestMixin, unittest.TestCase):
-    FUT_SETS_PROVIDED_BY = False
-
-    def _callFUT(self, cls, iface):
-        from zope.interface.declarations import classImplementsOnly
-        classImplementsOnly(cls, iface)
-        return cls
-
-    def test_w_existing_Implements(self):
-        from zope.interface.declarations import Implements
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        impl = Implements(IFoo)
-        impl.declared = (IFoo,)
-
-        class Foo:
-            __implemented__ = impl
-
-        impl.inherit = Foo
-        self._callFUT(Foo, IBar)
-        # Same spec, now different values
-        self.assertIs(Foo.__implemented__, impl)
-        self.assertEqual(impl.inherit, None)
-        self.assertEqual(impl.declared, (IBar,))
-
-    def test_class(self):
-        from zope.interface.declarations import Implements
-        from zope.interface.interface import InterfaceClass
-        IBar = InterfaceClass('IBar')
-        old_spec = Implements(IBar)
-
-        class Foo:
-            __implemented__ = old_spec
-
-        self._check_implementer(Foo, old_spec, '?', inherit=None)
-
-    def test_redundant_with_super_still_implements(self):
-        Base, IBase = self._check_implementer(
-            type('Foo', (object,), {}),
-            inherit=None,
-        )
-
-        class Child(Base):
-            pass
-
-        self._callFUT(Child, IBase)
-        self.assertTrue(IBase.implementedBy(Child))
-
-
-class Test_classImplements(_ImplementsTestMixin, unittest.TestCase):
-
-    def _callFUT(self, cls, iface):
-        from zope.interface.declarations import classImplements
-        result = classImplements(
-            cls, iface
-        )  # pylint:disable=assignment-from-no-return
-        self.assertIsNone(result)
-        return cls
-
-    def __check_implementer_redundant(self, Base):
-        # If we @implementer exactly what was already present, we write no
-        # declared attributes on the parent (we still set everything, though)
-        Base, IBase = self._check_implementer(Base)
-
-        class Child(Base):
-            pass
-
-        returned = self._callFUT(Child, IBase)
-        self.assertIn('__implemented__', returned.__dict__)
-        self.assertNotIn('__providedBy__', returned.__dict__)
-        self.assertIn('__provides__', returned.__dict__)
-
-        spec = Child.__implemented__
-        self.assertEqual(spec.declared, ())
-        self.assertEqual(spec.inherit, Child)
-
-        self.assertTrue(IBase.providedBy(Child()))
-
-    def test_redundant_implementer_empty_class_declarations(self):
-
-        class Foo:
-            pass
-
-        self.__check_implementer_redundant(Foo)
-
-    def test_redundant_implementer_Interface(self):
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import ro
-        from zope.interface.tests.test_ro import C3Setting
-
-        class Foo:
-            pass
-
-        with C3Setting(ro.C3.STRICT_IRO, False):
-            self._callFUT(Foo, Interface)
-            self.assertEqual(list(implementedBy(Foo)), [Interface])
-
-            class Baz(Foo):
-                pass
-
-            self._callFUT(Baz, Interface)
-            self.assertEqual(list(implementedBy(Baz)), [Interface])
-
-    def _order_for_two(self, applied_first, applied_second):
-        return (applied_first, applied_second)
-
-    def test_w_existing_Implements(self):
-        from zope.interface.declarations import Implements
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-        impl = Implements(IFoo)
-        impl.declared = (IFoo,)
-
-        class Foo:
-            __implemented__ = impl
-
-        impl.inherit = Foo
-        self._callFUT(Foo, IBar)
-        # Same spec, now different values
-        self.assertIs(Foo.__implemented__, impl)
-        self.assertEqual(impl.inherit, Foo)
-        self.assertEqual(impl.declared,
-                         self._order_for_two(IFoo, IBar))
-
-    def test_w_existing_Implements_w_bases(self):
-        from zope.interface.declarations import Implements
-        from zope.interface.interface import InterfaceClass
-        IRoot = InterfaceClass('IRoot')
-        ISecondRoot = InterfaceClass('ISecondRoot')
-        IExtendsRoot = InterfaceClass('IExtendsRoot', (IRoot,))
-
-        impl_root = Implements.named('Root', IRoot)
-        impl_root.declared = (IRoot,)
-
-        class Root1:
-            __implemented__ = impl_root
-
-        class Root2:
-            __implemented__ = impl_root
-
-        impl_extends_root = Implements.named('ExtendsRoot1', IExtendsRoot)
-        impl_extends_root.declared = (IExtendsRoot,)
-
-        class ExtendsRoot(Root1, Root2):
-            __implemented__ = impl_extends_root
-
-        impl_extends_root.inherit = ExtendsRoot
-
-        self._callFUT(ExtendsRoot, ISecondRoot)
-        # Same spec, now different values
-        self.assertIs(ExtendsRoot.__implemented__, impl_extends_root)
-        self.assertEqual(impl_extends_root.inherit, ExtendsRoot)
-        self.assertEqual(impl_extends_root.declared,
-                         self._order_for_two(IExtendsRoot, ISecondRoot,))
-        self.assertEqual(
-            impl_extends_root.__bases__,
-            self._order_for_two(IExtendsRoot, ISecondRoot) + (impl_root,)
-        )
-
-
-class Test_classImplementsFirst(Test_classImplements):
-
-    def _callFUT(self, cls, iface):
-        from zope.interface.declarations import classImplementsFirst
-        result = classImplementsFirst(
-            cls, iface
-        )  # pylint:disable=assignment-from-no-return
-        self.assertIsNone(result)
-        return cls
-
-    def _order_for_two(self, applied_first, applied_second):
-        return (applied_second, applied_first)
-
-
-class Test__implements_advice(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.declarations import _implements_advice
-        return _implements_advice(*args, **kw)
-
-    def test_no_existing_implements(self):
-        from zope.interface.declarations import Implements
-        from zope.interface.declarations import classImplements
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-
-        class Foo:
-            __implements_advice_data__ = ((IFoo,), classImplements)
-
-        self._callFUT(Foo)
-        self.assertNotIn('__implements_advice_data__', Foo.__dict__)
-        self.assertIsInstance(
-            Foo.__implemented__, Implements
-        )  # pylint:disable=no-member
-        self.assertEqual(
-            list(Foo.__implemented__), [IFoo]
-        )  # pylint:disable=no-member
-
-
-class Test_implementer(Test_classImplements):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import implementer
-        return implementer
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def _callFUT(self, cls, *ifaces):
-        decorator = self._makeOne(*ifaces)
-        return decorator(cls)
-
-    def test_nonclass_cannot_assign_attr(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decorator = self._makeOne(IFoo)
-        self.assertRaises(TypeError, decorator, object())
-
-    def test_nonclass_can_assign_attr(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        decorator = self._makeOne(IFoo)
-        returned = decorator(foo)
-        self.assertIs(returned, foo)
-        spec = foo.__implemented__  # pylint:disable=no-member
-        self.assertEqual(
-            spec.__name__, 'zope.interface.tests.test_declarations.?'
-        )
-        self.assertIsNone(spec.inherit,)
-        self.assertIs(foo.__implemented__, spec)  # pylint:disable=no-member
-
-    def test_does_not_leak_on_unique_classes(self):
-        # Make sure nothing is hanging on to the class or Implements
-        # object after they go out of scope. There was briefly a bug
-        # in 5.x that caused SpecificationBase._bases (in C) to not be
-        # traversed or cleared.
-        # https://github.com/zopefoundation/zope.interface/issues/216
-        import gc
-
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-
-        begin_count = len(gc.get_objects())
-
-        for _ in range(1900):
-            class TestClass:
-                pass
-
-            self._callFUT(TestClass, IFoo)
-
-        gc.collect()
-
-        end_count = len(gc.get_objects())
-
-        # How many new objects might still be around? In all currently
-        # tested interpreters, there aren't any, so our counts should
-        # match exactly. When the bug existed, in a steady state, the loop
-        # would grow by two objects each iteration
-        fudge_factor = 0
-        self.assertLessEqual(end_count, begin_count + fudge_factor)
-
-
-class Test_implementer_only(Test_classImplementsOnly):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import implementer_only
-        return implementer_only
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def _callFUT(self, cls, iface):
-        decorator = self._makeOne(iface)
-        return decorator(cls)
-
-    def test_function(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decorator = self._makeOne(IFoo)
-
-        def _function():
-            raise NotImplementedError()
-
-        self.assertRaises(ValueError, decorator, _function)
-
-    def test_method(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass('IFoo')
-        decorator = self._makeOne(IFoo)
-
-        class Bar:
-            def _method(self):
-                raise NotImplementedError()
-
-        self.assertRaises(ValueError, decorator, Bar._method)
-
-
-class ProvidesClassTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import ProvidesClass
-        return ProvidesClass
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_simple_class_one_interface(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        spec = self._makeOne(Foo, IFoo)
-        self.assertEqual(list(spec), [IFoo])
-
-    def test___reduce__(self):
-        from zope.interface.declarations import Provides  # the function
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        spec = self._makeOne(Foo, IFoo)
-        klass, args = spec.__reduce__()
-        self.assertIs(klass, Provides)
-        self.assertEqual(args, (Foo, IFoo))
-
-    def test___get___class(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        spec = self._makeOne(Foo, IFoo)
-        Foo.__provides__ = spec
-        self.assertIs(Foo.__provides__, spec)
-
-    def test___get___instance(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        spec = self._makeOne(Foo, IFoo)
-        Foo.__provides__ = spec
-
-        def _test():
-            foo = Foo()
-            return foo.__provides__
-
-        self.assertRaises(AttributeError, _test)
-
-
-class ProvidesClassStrictTests(ProvidesClassTests):
-    # Tests that require the strict C3 resolution order.
-
-    def _getTargetClass(self):
-        ProvidesClass = super()._getTargetClass()
-
-        class StrictProvides(ProvidesClass):
-            def _do_calculate_ro(self, base_mros):
-                return ProvidesClass._do_calculate_ro(
-                    self, base_mros=base_mros, strict=True,
-                )
-
-        return StrictProvides
-
-    def test_overlapping_interfaces_corrected(self):
-        # Giving Provides(cls, IFace), where IFace is already
-        # provided by cls, doesn't produce invalid resolution orders.
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import implementer
-
-        class IBase(Interface):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        spec = self._makeOne(Base, IBase)
-        self.assertEqual(spec.__sro__, (
-            spec,
-            implementedBy(Base),
-            IBase,
-            implementedBy(object),
-            Interface
-        ))
-
-
-class TestProvidesClassRepr(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import ProvidesClass
-        return ProvidesClass
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test__repr__(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        assert IFoo.__name__ == 'IFoo'
-        assert IFoo.__module__ == __name__
-        assert repr(IFoo) == f''
-
-        IBar = InterfaceClass("IBar")
-
-        inst = self._makeOne(type(self), IFoo, IBar)
-        self.assertEqual(
-            repr(inst),
-            "directlyProvides(TestProvidesClassRepr, IFoo, IBar)"
-        )
-
-    def test__repr__module_provides_typical_use(self):
-        # as created through a ``moduleProvides()`` statement
-        # in a module body
-        from zope.interface.tests import dummy
-        provides = dummy.__provides__  # pylint:disable=no-member
-        self.assertEqual(
-            repr(provides),
-            "directlyProvides("
-            "sys.modules['zope.interface.tests.dummy'], "
-            "IDummyModule)"
-        )
-
-    def test__repr__module_after_pickle(self):
-        # It doesn't matter, these objects can't be pickled.
-        import pickle
-
-        from zope.interface.tests import dummy
-        provides = dummy.__provides__  # pylint:disable=no-member
-        for proto in range(pickle.HIGHEST_PROTOCOL + 1):
-            with self.assertRaises(pickle.PicklingError):
-                pickle.dumps(provides, proto)
-
-    def test__repr__directlyProvides_module(self):
-        import sys
-
-        from zope.interface.declarations import alsoProvides
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interface import InterfaceClass
-        from zope.interface.tests import dummy
-
-        IFoo = InterfaceClass('IFoo')
-        IBar = InterfaceClass('IBar')
-
-        orig_provides = dummy.__provides__  # pylint:disable=no-member
-        del dummy.__provides__  # pylint:disable=no-member
-        self.addCleanup(setattr, dummy, '__provides__', orig_provides)
-
-        directlyProvides(dummy, IFoo)
-        provides = dummy.__provides__  # pylint:disable=no-member
-
-        self.assertEqual(
-            repr(provides),
-            "directlyProvides(sys.modules['zope.interface.tests.dummy'], IFoo)"
-        )
-
-        alsoProvides(dummy, IBar)
-        provides = dummy.__provides__  # pylint:disable=no-member
-
-        self.assertEqual(
-            repr(provides),
-            "directlyProvides("
-            "sys.modules['zope.interface.tests.dummy'], "
-            "IFoo, IBar)"
-        )
-
-        # If we make this module also provide IFoo and IBar, then the repr
-        # lists both names.
-        my_module = sys.modules[__name__]
-        assert not hasattr(my_module, '__provides__')
-
-        directlyProvides(my_module, IFoo, IBar)
-        self.addCleanup(delattr, my_module, '__provides__')
-        self.assertIs(my_module.__provides__, provides)
-        self.assertEqual(
-            repr(provides),
-            "directlyProvides(('zope.interface.tests.dummy', "
-            "'zope.interface.tests.test_declarations'), "
-            "IFoo, IBar)"
-        )
-
-    def test__repr__module_provides_cached_shared(self):
-        from zope.interface.declarations import ModuleType
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        inst = self._makeOne(ModuleType, IFoo)
-        inst._v_module_names += ('some.module',)
-        inst._v_module_names += ('another.module',)
-        self.assertEqual(
-            repr(inst),
-            "directlyProvides(('some.module', 'another.module'), IFoo)"
-        )
-
-    def test__repr__duplicate_names(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo", __module__='mod1')
-        IFoo2 = InterfaceClass("IFoo", __module__='mod2')
-        IBaz = InterfaceClass("IBaz")
-
-        inst = self._makeOne(type(self), IFoo, IBaz, IFoo2)
-        self.assertEqual(
-            repr(inst),
-            "directlyProvides(TestProvidesClassRepr, IFoo, IBaz, mod2.IFoo)"
-        )
-
-    def test__repr__implementedBy_in_interfaces(self):
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-
-        class IFoo(Interface):
-            "Does nothing"
-
-        class Bar:
-            "Does nothing"
-
-        impl = implementedBy(type(self))
-
-        inst = self._makeOne(Bar, IFoo, impl)
-        self.assertEqual(
-            repr(inst),
-            'directlyProvides('
-            'Bar, IFoo, '
-            'classImplements(TestProvidesClassRepr))'
-        )
-
-    def test__repr__empty_interfaces(self):
-        inst = self._makeOne(type(self))
-        self.assertEqual(
-            repr(inst),
-            'directlyProvides(TestProvidesClassRepr)',
-        )
-
-    def test__repr__non_class(self):
-
-        def str___dont_call_me():
-            self.fail("Should not call str")
-
-        class Object:
-            __bases__ = ()
-            __str__ = str___dont_call_me
-
-            def __repr__(self):
-                return ''
-
-        inst = self._makeOne(Object())
-        self.assertEqual(
-            repr(inst),
-            'directlyProvides()',
-        )
-
-    def test__repr__providedBy_from_class(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.declarations import providedBy
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        inst = providedBy(Foo())
-        self.assertEqual(
-            repr(inst),
-            'classImplements(Foo, IFoo)'
-        )
-
-    def test__repr__providedBy_alsoProvides(self):
-        from zope.interface.declarations import alsoProvides
-        from zope.interface.declarations import implementer
-        from zope.interface.declarations import providedBy
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        alsoProvides(foo, IBar)
-
-        inst = providedBy(foo)
-        self.assertEqual(
-            repr(inst),
-            "directlyProvides(Foo, IBar, classImplements(Foo, IFoo))"
-        )
-
-
-class Test_Provides(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.declarations import Provides
-        return Provides(*args, **kw)
-
-    def test_no_cached_spec(self):
-        from zope.interface import declarations
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        cache = {}
-
-        class Foo:
-            pass
-
-        with _Monkey(declarations, InstanceDeclarations=cache):
-            spec = self._callFUT(Foo, IFoo)
-        self.assertEqual(list(spec), [IFoo])
-        self.assertIs(cache[(Foo, IFoo)], spec)
-
-    def test_w_cached_spec(self):
-        from zope.interface import declarations
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        prior = object()
-
-        class Foo:
-            pass
-
-        cache = {(Foo, IFoo): prior}
-        with _Monkey(declarations, InstanceDeclarations=cache):
-            spec = self._callFUT(Foo, IFoo)
-        self.assertIs(spec, prior)
-
-
-class Test_directlyProvides(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.declarations import directlyProvides
-        return directlyProvides(*args, **kw)
-
-    def test_w_normal_object(self):
-        from zope.interface.declarations import ProvidesClass
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        obj = Foo()
-        self._callFUT(obj, IFoo)
-        self.assertIsInstance(
-            obj.__provides__, ProvidesClass
-        )  # pylint:disable=no-member
-        self.assertEqual(
-            list(obj.__provides__), [IFoo]
-        )  # pylint:disable=no-member
-
-    def test_w_class(self):
-        from zope.interface.declarations import ClassProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        self._callFUT(Foo, IFoo)
-        self.assertIsInstance(
-            Foo.__provides__, ClassProvides
-        )  # pylint:disable=no-member
-        self.assertEqual(
-            list(Foo.__provides__), [IFoo]
-        )  # pylint:disable=no-member
-
-    def test_w_classless_object(self):
-        from zope.interface.declarations import ProvidesClass
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        the_dict = {}
-
-        class Foo:
-            def __getattribute__(self, name):
-                # Emulate object w/o any class
-                if name == '__class__':
-                    return None
-                raise NotImplementedError(name)
-
-            def __setattr__(self, name, value):
-                the_dict[name] = value
-
-        obj = Foo()
-        self._callFUT(obj, IFoo)
-        self.assertIsInstance(the_dict['__provides__'], ProvidesClass)
-        self.assertEqual(list(the_dict['__provides__']), [IFoo])
-
-
-class Test_alsoProvides(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.declarations import alsoProvides
-        return alsoProvides(*args, **kw)
-
-    def test_wo_existing_provides(self):
-        from zope.interface.declarations import ProvidesClass
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        obj = Foo()
-        self._callFUT(obj, IFoo)
-        self.assertIsInstance(
-            obj.__provides__, ProvidesClass
-        )  # pylint:disable=no-member
-        self.assertEqual(
-            list(obj.__provides__), [IFoo]
-        )  # pylint:disable=no-member
-
-    def test_w_existing_provides(self):
-        from zope.interface.declarations import ProvidesClass
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-
-        class Foo:
-            pass
-
-        obj = Foo()
-        directlyProvides(obj, IFoo)
-        self._callFUT(obj, IBar)
-        self.assertIsInstance(
-            obj.__provides__, ProvidesClass
-        )  # pylint:disable=no-member
-        self.assertEqual(
-            list(obj.__provides__), [IFoo, IBar]
-        )  # pylint:disable=no-member
-
-
-class Test_noLongerProvides(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.declarations import noLongerProvides
-        return noLongerProvides(*args, **kw)
-
-    def test_wo_existing_provides(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        obj = Foo()
-        self._callFUT(obj, IFoo)
-        self.assertEqual(
-            list(obj.__provides__), []
-        )  # pylint:disable=no-member
-
-    def test_w_existing_provides_hit(self):
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        obj = Foo()
-        directlyProvides(obj, IFoo)
-        self._callFUT(obj, IFoo)
-        self.assertEqual(
-            list(obj.__provides__), []
-        )  # pylint:disable=no-member
-
-    def test_w_existing_provides_miss(self):
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-
-        class Foo:
-            pass
-
-        obj = Foo()
-        directlyProvides(obj, IFoo)
-        self._callFUT(obj, IBar)
-        self.assertEqual(
-            list(obj.__provides__), [IFoo]
-        )  # pylint:disable=no-member
-
-    def test_w_iface_implemented_by_class(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        obj = Foo()
-        self.assertRaises(ValueError, self._callFUT, obj, IFoo)
-
-
-class ClassProvidesBaseFallbackTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        # pylint:disable=no-name-in-module
-        from zope.interface.declarations import ClassProvidesBaseFallback
-        return ClassProvidesBaseFallback
-
-    def _makeOne(self, klass, implements):
-        # Don't instantiate directly:  the C version can't have attributes
-        # assigned.
-
-        class Derived(self._getTargetClass()):
-            def __init__(self, k, i):
-                self._cls = k
-                self._implements = i
-
-        return Derived(klass, implements)
-
-    def test_w_same_class_via_class(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        cpbp = Foo.__provides__ = self._makeOne(Foo, IFoo)
-        self.assertIs(Foo.__provides__, cpbp)
-
-    def test_w_same_class_via_instance(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        Foo.__provides__ = self._makeOne(Foo, IFoo)
-        self.assertIs(foo.__provides__, IFoo)
-
-    def test_w_different_class(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        class Bar(Foo):
-            pass
-
-        bar = Bar()
-        Foo.__provides__ = self._makeOne(Foo, IFoo)
-        self.assertRaises(AttributeError, getattr, Bar, '__provides__')
-        self.assertRaises(AttributeError, getattr, bar, '__provides__')
-
-
-class ClassProvidesBaseTests(
-    OptimizationTestMixin,
-    ClassProvidesBaseFallbackTests,
-    SubclassableMixin,
-):
-    # Repeat tests for C optimizations
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import ClassProvidesBase
-        return ClassProvidesBase
-
-    def _getFallbackClass(self):
-        # pylint:disable=no-name-in-module
-        from zope.interface.declarations import ClassProvidesBaseFallback
-        return ClassProvidesBaseFallback
-
-
-class ClassProvidesTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import ClassProvides
-        return ClassProvides
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_w_simple_metaclass(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        cp = Foo.__provides__ = self._makeOne(Foo, type(Foo), IBar)
-        self.assertIs(Foo.__provides__, cp)
-        self.assertEqual(list(Foo().__provides__), [IFoo])
-
-    def test___reduce__(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        cp = Foo.__provides__ = self._makeOne(Foo, type(Foo), IBar)
-        self.assertEqual(cp.__reduce__(),
-                         (type(cp), (Foo, type(Foo), IBar)))
-
-
-class ClassProvidesStrictTests(ClassProvidesTests):
-    # Tests that require the strict C3 resolution order.
-
-    def _getTargetClass(self):
-        ClassProvides = super()._getTargetClass()
-
-        class StrictClassProvides(ClassProvides):
-            def _do_calculate_ro(self, base_mros):
-                return ClassProvides._do_calculate_ro(
-                    self, base_mros=base_mros, strict=True
-                )
-
-        return StrictClassProvides
-
-    def test_overlapping_interfaces_corrected(self):
-        # Giving ClassProvides(cls, metaclass, IFace), where IFace is already
-        # provided by metacls, doesn't produce invalid resolution orders.
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import implementer
-
-        class IBase(Interface):
-            pass
-
-        @implementer(IBase)
-        class metaclass(type):
-            pass
-
-        cls = metaclass(
-            'cls',
-            (object,),
-            {}
-        )
-
-        spec = self._makeOne(cls, metaclass, IBase)
-        self.assertEqual(spec.__sro__, (
-            spec,
-            implementedBy(metaclass),
-            IBase,
-            implementedBy(type),
-            implementedBy(object),
-            Interface
-        ))
-
-
-class TestClassProvidesRepr(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import ClassProvides
-        return ClassProvides
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test__repr__empty(self):
-        inst = self._makeOne(type(self), type)
-        self.assertEqual(
-            repr(inst),
-            "directlyProvides(TestClassProvidesRepr)"
-        )
-
-    def test__repr__providing_one(self):
-        from zope.interface import Interface
-
-        class IFoo(Interface):
-            "Does nothing"
-
-        inst = self._makeOne(type(self), type, IFoo)
-        self.assertEqual(
-            repr(inst),
-            "directlyProvides(TestClassProvidesRepr, IFoo)"
-        )
-
-    def test__repr__duplicate_names(self):
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo", __module__='mod1')
-        IFoo2 = InterfaceClass("IFoo", __module__='mod2')
-        IBaz = InterfaceClass("IBaz")
-
-        inst = self._makeOne(type(self), type, IFoo, IBaz, IFoo2)
-        self.assertEqual(
-            repr(inst),
-            "directlyProvides(TestClassProvidesRepr, IFoo, IBaz, mod2.IFoo)"
-        )
-
-    def test__repr__implementedBy(self):
-        from zope.interface.declarations import implementedBy
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        inst = implementedBy(Foo)
-        self.assertEqual(
-            repr(inst),
-            'classImplements(Foo, IFoo)'
-        )
-
-    def test__repr__implementedBy_generic_callable(self):
-        from zope.interface.declarations import implementedBy
-
-        # We can't get a __name__ by default, so we get a
-        # module name and a question mark
-        class Callable:
-            def __call__(self):
-                return self
-
-        inst = implementedBy(Callable())
-        self.assertEqual(
-            repr(inst),
-            f'classImplements({__name__}.?)'
-        )
-
-        c = Callable()
-        c.__name__ = 'Callable'
-        inst = implementedBy(c)
-        self.assertEqual(
-            repr(inst),
-            'classImplements(Callable)'
-        )
-
-
-class Test_directlyProvidedBy(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.declarations import directlyProvidedBy
-        return directlyProvidedBy(*args, **kw)
-
-    def test_wo_declarations_in_class_or_instance(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        self.assertEqual(list(self._callFUT(foo)), [])
-
-    def test_w_declarations_in_class_but_not_instance(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        self.assertEqual(list(self._callFUT(foo)), [])
-
-    def test_w_declarations_in_instance_but_not_class(self):
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        directlyProvides(foo, IFoo)
-        self.assertEqual(list(self._callFUT(foo)), [IFoo])
-
-    def test_w_declarations_in_instance_and_class(self):
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        directlyProvides(foo, IBar)
-        self.assertEqual(list(self._callFUT(foo)), [IBar])
-
-
-class Test_provider(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import provider
-        return provider
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_w_class(self):
-        from zope.interface.declarations import ClassProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @self._makeOne(IFoo)
-        class Foo:
-            pass
-
-        self.assertIsInstance(
-            Foo.__provides__, ClassProvides
-        )  # pylint:disable=no-member
-        self.assertEqual(
-            list(Foo.__provides__), [IFoo]
-        )  # pylint:disable=no-member
-
-
-class Test_moduleProvides(unittest.TestCase):
-    # pylint:disable=exec-used
-
-    def test_called_from_function(self):
-        from zope.interface.declarations import moduleProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        globs = {'__name__': 'zope.interface.tests.foo',
-                 'moduleProvides': moduleProvides, 'IFoo': IFoo}
-        locs = {}
-        CODE = "\n".join([
-            'def foo():',
-            '    moduleProvides(IFoo)'
-        ])
-        exec(CODE, globs, locs)
-        foo = locs['foo']
-        self.assertRaises(TypeError, foo)
-
-    def test_called_from_class(self):
-        from zope.interface.declarations import moduleProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        globs = {'__name__': 'zope.interface.tests.foo',
-                 'moduleProvides': moduleProvides, 'IFoo': IFoo}
-        locs = {}
-        CODE = "\n".join([
-            'class Foo(object):',
-            '    moduleProvides(IFoo)',
-        ])
-        with self.assertRaises(TypeError):
-            exec(CODE, globs, locs)
-
-    def test_called_once_from_module_scope(self):
-        from zope.interface.declarations import moduleProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        globs = {'__name__': 'zope.interface.tests.foo',
-                 'moduleProvides': moduleProvides, 'IFoo': IFoo}
-        CODE = "\n".join([
-            'moduleProvides(IFoo)',
-        ])
-        exec(CODE, globs)
-        spec = globs['__provides__']
-        self.assertEqual(list(spec), [IFoo])
-
-    def test_called_twice_from_module_scope(self):
-        from zope.interface.declarations import moduleProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        globs = {'__name__': 'zope.interface.tests.foo',
-                 'moduleProvides': moduleProvides, 'IFoo': IFoo}
-
-        CODE = "\n".join([
-            'moduleProvides(IFoo)',
-            'moduleProvides(IFoo)',
-        ])
-        with self.assertRaises(TypeError):
-            exec(CODE, globs)
-
-
-class Test_getObjectSpecificationFallback(unittest.TestCase):
-
-    def _getFallbackClass(self):
-        # pylint:disable=no-name-in-module
-        from zope.interface.declarations import getObjectSpecificationFallback
-        return getObjectSpecificationFallback
-
-    _getTargetClass = _getFallbackClass
-
-    def _callFUT(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_wo_existing_provides_classless(self):
-        the_dict = {}
-
-        class Foo:
-            def __getattribute__(self, name):
-                # Emulate object w/o any class
-                if name == '__class__':
-                    raise AttributeError(name)
-                try:
-                    return the_dict[name]
-                except KeyError:
-                    raise AttributeError(name)
-
-            def __setattr__(self, name, value):
-                raise NotImplementedError()
-
-        foo = Foo()
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [])
-
-    def test_existing_provides_is_spec(self):
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        def foo():
-            raise NotImplementedError()
-
-        directlyProvides(foo, IFoo)
-        spec = self._callFUT(foo)
-        self.assertIs(spec, foo.__provides__)  # pylint:disable=no-member
-
-    def test_existing_provides_is_not_spec(self):
-
-        def foo():
-            raise NotImplementedError()
-
-        foo.__provides__ = object()  # not a valid spec
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [])
-
-    def test_existing_provides(self):
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        directlyProvides(foo, IFoo)
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [IFoo])
-
-    def test_wo_provides_on_class_w_implements(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [IFoo])
-
-    def test_wo_provides_on_class_wo_implements(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [])
-
-    def test_catches_only_AttributeError_on_provides(self):
-        MissingSomeAttrs.test_raises(
-            self, self._callFUT, expected_missing='__provides__'
-        )
-
-    def test_catches_only_AttributeError_on_class(self):
-        MissingSomeAttrs.test_raises(
-            self,
-            self._callFUT,
-            expected_missing='__class__',
-            __provides__=None,
-        )
-
-    def test_raises_AttrError_w_provides_fails_type_check_AttrError(self):
-        # isinstance(ob.__provides__, SpecificationBase) is not
-        # protected inside any kind of block.
-
-        class Foo:
-            __provides__ = MissingSomeAttrs(AttributeError)
-
-        # isinstance() ignores AttributeError on __class__
-        self._callFUT(Foo())
-
-    def test_raises_AttrError_w_provides_fails_type_check_RuntimeError(self):
-        # isinstance(ob.__provides__, SpecificationBase) is not
-        # protected inside any kind of block.
-        class Foo:
-            __provides__ = MissingSomeAttrs(RuntimeError)
-
-        with self.assertRaises(RuntimeError) as exc:
-            self._callFUT(Foo())
-
-        self.assertEqual('__class__', exc.exception.args[0])
-
-
-class Test_getObjectSpecification(Test_getObjectSpecificationFallback,
-                                  OptimizationTestMixin):
-    # Repeat tests for C optimizations
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import getObjectSpecification
-        return getObjectSpecification
-
-
-class Test_providedByFallback(unittest.TestCase):
-
-    def _getFallbackClass(self):
-        # pylint:disable=no-name-in-module
-        from zope.interface.declarations import providedByFallback
-        return providedByFallback
-
-    _getTargetClass = _getFallbackClass
-
-    def _callFUT(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_wo_providedBy_on_class_wo_implements(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [])
-
-    def test_w_providedBy_valid_spec(self):
-        from zope.interface.declarations import Provides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__providedBy__ = Provides(Foo, IFoo)
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [IFoo])
-
-    def test_w_providedBy_invalid_spec(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__providedBy__ = object()
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [])
-
-    def test_w_providedBy_invalid_spec_class_w_implements(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__providedBy__ = object()
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [IFoo])
-
-    def test_w_providedBy_invalid_spec_w_provides_no_provides_on_class(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__providedBy__ = object()
-        expected = foo.__provides__ = object()
-        spec = self._callFUT(foo)
-        self.assertIs(spec, expected)
-
-    def test_w_providedBy_invalid_spec_w_provides_diff_provides_on_class(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__providedBy__ = object()
-        expected = foo.__provides__ = object()
-        Foo.__provides__ = object()
-        spec = self._callFUT(foo)
-        self.assertIs(spec, expected)
-
-    def test_w_providedBy_invalid_spec_w_provides_same_provides_on_class(self):
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__providedBy__ = object()
-        foo.__provides__ = Foo.__provides__ = object()
-        spec = self._callFUT(foo)
-        self.assertEqual(list(spec), [IFoo])
-
-    def test_super_when_base_implements_interface(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        @implementer(IDerived)
-        class Derived(Base):
-            pass
-
-        derived = Derived()
-        self.assertEqual(list(self._callFUT(derived)), [IDerived, IBase])
-
-        sup = super(Derived, derived)
-        fut = self._callFUT(sup)
-        self.assertIsNone(fut._dependents)
-        self.assertEqual(list(fut), [IBase])
-
-    def test_super_when_base_doesnt_implement_interface(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class Base:
-            pass
-
-        @implementer(IDerived)
-        class Derived(Base):
-            pass
-
-        derived = Derived()
-        self.assertEqual(list(self._callFUT(derived)), [IDerived])
-
-        sup = super(Derived, derived)
-        self.assertEqual(list(self._callFUT(sup)), [])
-
-    def test_super_when_base_is_object(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IDerived)
-        class Derived:
-            pass
-
-        derived = Derived()
-        self.assertEqual(list(self._callFUT(derived)), [IDerived])
-
-        sup = super(Derived, derived)
-        fut = self._callFUT(sup)
-        self.assertIsNone(fut._dependents)
-        self.assertEqual(list(fut), [])
-
-    def test_super_when_object_directly_provides(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        class Derived(Base):
-            pass
-
-        derived = Derived()
-        self.assertEqual(list(self._callFUT(derived)), [IBase])
-
-        directlyProvides(derived, IDerived)
-        self.assertEqual(list(self._callFUT(derived)), [IDerived, IBase])
-
-        sup = super(Derived, derived)
-        fut = self._callFUT(sup)
-        self.assertIsNone(fut._dependents)
-        self.assertEqual(list(fut), [IBase])
-
-    def test_super_multi_level_multi_inheritance(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IM1(Interface):
-            pass
-
-        class IM2(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class IUnrelated(Interface):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        @implementer(IM1)
-        class M1(Base):
-            pass
-
-        @implementer(IM2)
-        class M2(Base):
-            pass
-
-        @implementer(IDerived, IUnrelated)
-        class Derived(M1, M2):
-            pass
-
-        d = Derived()
-        sd = super(Derived, d)
-        sm1 = super(M1, d)
-        sm2 = super(M2, d)
-
-        self.assertEqual(list(self._callFUT(d)),
-                         [IDerived, IUnrelated, IM1, IBase, IM2])
-        self.assertEqual(list(self._callFUT(sd)),
-                         [IM1, IBase, IM2])
-        self.assertEqual(list(self._callFUT(sm1)),
-                         [IM2, IBase])
-        self.assertEqual(list(self._callFUT(sm2)),
-                         [IBase])
-
-    def test_catches_only_AttributeError_on_providedBy(self):
-        MissingSomeAttrs.test_raises(self, self._callFUT,
-                                     expected_missing='__providedBy__',
-                                     __class__=object)
-
-    def test_catches_only_AttributeError_on_class(self):
-        # isinstance() tries to get the __class__, which is non-obvious,
-        # so it must be protected too.
-        MissingSomeAttrs.test_raises(
-            self, self._callFUT, expected_missing='__class__')
-
-
-class Test_providedBy(Test_providedByFallback,
-                      OptimizationTestMixin):
-    # Repeat tests for C optimizations
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import providedBy
-        return providedBy
-
-
-class ObjectSpecificationDescriptorFallbackTests(unittest.TestCase):
-
-    def _getFallbackClass(self):
-        # pylint:disable=no-name-in-module
-        from zope.interface.declarations import \
-            ObjectSpecificationDescriptorFallback
-        return ObjectSpecificationDescriptorFallback
-
-    _getTargetClass = _getFallbackClass
-
-    def _makeOne(self, *args, **kw):
-        return self._getTargetClass()(*args, **kw)
-
-    def test_accessed_via_class(self):
-        from zope.interface.declarations import Provides
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-
-        class Foo:
-            pass
-
-        Foo.__provides__ = Provides(Foo, IFoo)
-        Foo.__providedBy__ = self._makeOne()
-        self.assertEqual(list(Foo.__providedBy__), [IFoo])
-
-    def test_accessed_via_inst_wo_provides(self):
-        from zope.interface.declarations import Provides
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        Foo.__provides__ = Provides(Foo, IBar)
-        Foo.__providedBy__ = self._makeOne()
-        foo = Foo()
-        self.assertEqual(list(foo.__providedBy__), [IFoo])
-
-    def test_accessed_via_inst_w_provides(self):
-        from zope.interface.declarations import Provides
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import InterfaceClass
-        IFoo = InterfaceClass("IFoo")
-        IBar = InterfaceClass("IBar")
-        IBaz = InterfaceClass("IBaz")
-
-        @implementer(IFoo)
-        class Foo:
-            pass
-
-        Foo.__provides__ = Provides(Foo, IBar)
-        Foo.__providedBy__ = self._makeOne()
-        foo = Foo()
-        directlyProvides(foo, IBaz)
-        self.assertEqual(list(foo.__providedBy__), [IBaz, IFoo])
-
-    def test_arbitrary_exception_accessing_provides_not_caught(self):
-
-        class MyException(Exception):
-            pass
-
-        class Foo:
-            __providedBy__ = self._makeOne()
-
-            @property
-            def __provides__(self):
-                raise MyException
-
-        foo = Foo()
-        with self.assertRaises(MyException):
-            getattr(foo, '__providedBy__')
-
-    def test_AttributeError_accessing_provides_caught(self):
-
-        class MyException(Exception):
-            pass
-
-        class Foo:
-            __providedBy__ = self._makeOne()
-
-            @property
-            def __provides__(self):
-                raise AttributeError
-
-        foo = Foo()
-        provided = getattr(foo, '__providedBy__')
-        self.assertIsNotNone(provided)
-
-    def test_None_in__provides__overrides(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class IFoo(Interface):
-            pass
-
-        @implementer(IFoo)
-        class Foo:
-
-            @property
-            def __provides__(self):
-                return None
-
-        Foo.__providedBy__ = self._makeOne()
-
-        provided = getattr(Foo(), '__providedBy__')
-        self.assertIsNone(provided)
-
-
-class ObjectSpecificationDescriptorTests(
-        ObjectSpecificationDescriptorFallbackTests,
-        OptimizationTestMixin,
-        SubclassableMixin,
-):
-    # Repeat tests for C optimizations
-
-    def _getTargetClass(self):
-        from zope.interface.declarations import ObjectSpecificationDescriptor
-        return ObjectSpecificationDescriptor
-
-
-# Test _normalizeargs through its callers.
-
-
-class _Monkey:
-    # context-manager for replacing module names in the scope of a test.
-    def __init__(self, module, **kw):
-        self.module = module
-        self.to_restore = {key: getattr(module, key) for key in kw}
-        for key, value in kw.items():
-            setattr(module, key, value)
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        for key, value in self.to_restore.items():
-            setattr(self.module, key, value)
-
-
-class _MonkeyDict:
-    # context-manager for restoring a dict w/in a module in the scope of a
-    # test.
-    def __init__(self, module, attrname, **kw):
-        self.module = module
-        self.target = getattr(module, attrname)
-        self.to_restore = self.target.copy()
-        self.target.clear()
-        self.target.update(kw)
-
-    def __enter__(self):
-        return self.target
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        self.target.clear()
-        self.target.update(self.to_restore)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_document.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_document.py
deleted file mode 100644
index 82b175a..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_document.py
+++ /dev/null
@@ -1,547 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Documentation tests.
-"""
-import sys
-import unittest
-
-
-class Test_asStructuredText(unittest.TestCase):
-
-    def _callFUT(self, iface):
-        from zope.interface.document import asStructuredText
-        return asStructuredText(iface)
-
-    def test_asStructuredText_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "INoDocstring",
-            " Attributes:",
-            " Methods:",
-            ""
-        ])
-
-        class INoDocstring(Interface):
-            pass
-
-        self.assertEqual(self._callFUT(INoDocstring), EXPECTED)
-
-    def test_asStructuredText_empty_with_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IEmpty",
-            " This is an empty interface.",
-            " Attributes:",
-            " Methods:",
-            ""
-        ])
-
-        class IEmpty(Interface):
-            """ This is an empty interface.
-            """
-
-        self.assertEqual(self._callFUT(IEmpty), EXPECTED)
-
-    def test_asStructuredText_empty_with_multiline_docstring(self):
-        from zope.interface import Interface
-
-        # In Python 3.13+, compiler strips indents from docstrings
-        indent = " " * 12 if sys.version_info < (3, 13) else ""
-
-        EXPECTED = '\n'.join([
-            "IEmpty",
-            "",
-            " This is an empty interface.",
-            " ",
-            (f"{indent} It can be used to annotate any class or object, "
-                             "because it promises"),  # noqa E127
-            f"{indent} nothing.",
-            "",
-            " Attributes:",
-            "",
-            " Methods:",
-            "",
-            ""
-        ])
-
-        class IEmpty(Interface):
-            """ This is an empty interface.
-
-            It can be used to annotate any class or object, because it promises
-            nothing.
-            """
-
-        self.assertEqual(self._callFUT(IEmpty), EXPECTED)
-
-    def test_asStructuredText_with_attribute_no_docstring(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IHasAttribute",
-            " This interface has an attribute.",
-            " Attributes:",
-            "  an_attribute -- no documentation",
-            " Methods:",
-            ""
-        ])
-
-        class IHasAttribute(Interface):
-            """ This interface has an attribute.
-            """
-            an_attribute = Attribute('an_attribute')
-
-        self.assertEqual(self._callFUT(IHasAttribute), EXPECTED)
-
-    def test_asStructuredText_with_attribute_with_docstring(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IHasAttribute",
-            " This interface has an attribute.",
-            " Attributes:",
-            "  an_attribute -- This attribute is documented.",
-            " Methods:",
-            ""
-        ])
-
-        class IHasAttribute(Interface):
-            """ This interface has an attribute.
-            """
-            an_attribute = Attribute('an_attribute',
-                                     'This attribute is documented.')
-
-        self.assertEqual(self._callFUT(IHasAttribute), EXPECTED)
-
-    def test_asStructuredText_with_method_no_args_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IHasMethod",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  aMethod() -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod():
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asStructuredText_with_method_positional_args_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IHasMethod",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  aMethod(first, second) -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod(first, second):
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asStructuredText_with_method_starargs_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IHasMethod",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  aMethod(first, second, *rest) -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod(first, second, *rest):
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asStructuredText_with_method_kwargs_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IHasMethod",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  aMethod(first, second, **kw) -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod(first, second, **kw):
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asStructuredText_with_method_with_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IHasMethod",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  aMethod() -- This method is documented.",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod():
-                """This method is documented.
-                """
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asStructuredText_derived_ignores_base(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "IDerived",
-            " IDerived doc",
-            " This interface extends:",
-            "  o IBase",
-            " Attributes:",
-            "  attr1 -- no documentation",
-            "  attr2 -- attr2 doc",
-            " Methods:",
-            "  method3() -- method3 doc",
-            "  method4() -- no documentation",
-            "  method5() -- method5 doc",
-            "",
-        ])
-
-        class IBase(Interface):
-            def method1():
-                """docstring"""
-
-            def method2():
-                """docstring"""
-
-        class IDerived(IBase):
-            "IDerived doc"
-            attr1 = Attribute('attr1')
-            attr2 = Attribute('attr2', 'attr2 doc')
-
-            def method3():
-                "method3 doc"
-
-            def method4():
-                pass  # pragma: no cover
-
-            def method5():
-                "method5 doc"
-
-        self.assertEqual(self._callFUT(IDerived), EXPECTED)
-
-
-class Test_asReStructuredText(unittest.TestCase):
-
-    def _callFUT(self, iface):
-        from zope.interface.document import asReStructuredText
-        return asReStructuredText(iface)
-
-    def test_asReStructuredText_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``INoDocstring``",
-            " Attributes:",
-            " Methods:",
-            ""
-        ])
-
-        class INoDocstring(Interface):
-            pass
-
-        self.assertEqual(self._callFUT(INoDocstring), EXPECTED)
-
-    def test_asReStructuredText_empty_with_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IEmpty``",
-            " This is an empty interface.",
-            " Attributes:",
-            " Methods:",
-            ""
-        ])
-
-        class IEmpty(Interface):
-            """ This is an empty interface.
-            """
-
-        self.assertEqual(self._callFUT(IEmpty), EXPECTED)
-
-    def test_asReStructuredText_empty_with_multiline_docstring(self):
-        from zope.interface import Interface
-
-        # In Python 3.13+, compiler strips indents from docstrings
-        indent = " " * 12 if sys.version_info < (3, 13) else ""
-
-        EXPECTED = '\n'.join([
-            "``IEmpty``",
-            "",
-            " This is an empty interface.",
-            " ",
-            (f"{indent} It can be used to annotate any class or object, "
-             f"because it"
-            ),  # noqa E124
-            f"{indent} promises nothing.",
-            "",
-            " Attributes:",
-            "",
-            " Methods:",
-            "",
-            ""
-        ])
-
-        class IEmpty(Interface):
-            """ This is an empty interface.
-
-            It can be used to annotate any class or object, because it
-            promises nothing.
-            """
-
-        self.assertEqual(self._callFUT(IEmpty), EXPECTED)
-
-    def test_asReStructuredText_with_attribute_no_docstring(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IHasAttribute``",
-            " This interface has an attribute.",
-            " Attributes:",
-            "  ``an_attribute`` -- no documentation",
-            " Methods:",
-            ""
-        ])
-
-        class IHasAttribute(Interface):
-            """ This interface has an attribute.
-            """
-            an_attribute = Attribute('an_attribute')
-
-        self.assertEqual(self._callFUT(IHasAttribute), EXPECTED)
-
-    def test_asReStructuredText_with_attribute_with_docstring(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IHasAttribute``",
-            " This interface has an attribute.",
-            " Attributes:",
-            "  ``an_attribute`` -- This attribute is documented.",
-            " Methods:",
-            ""
-        ])
-
-        class IHasAttribute(Interface):
-            """ This interface has an attribute.
-            """
-            an_attribute = Attribute('an_attribute',
-                                     'This attribute is documented.')
-
-        self.assertEqual(self._callFUT(IHasAttribute), EXPECTED)
-
-    def test_asReStructuredText_with_method_no_args_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IHasMethod``",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  ``aMethod()`` -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod():
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asReStructuredText_with_method_positional_args_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IHasMethod``",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  ``aMethod(first, second)`` -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod(first, second):
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asReStructuredText_with_method_starargs_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IHasMethod``",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  ``aMethod(first, second, *rest)`` -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod(first, second, *rest):
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asReStructuredText_with_method_kwargs_no_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IHasMethod``",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  ``aMethod(first, second, **kw)`` -- no documentation",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod(first, second, **kw):
-                pass  # pragma: no cover
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asReStructuredText_with_method_with_docstring(self):
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IHasMethod``",
-            " This interface has a method.",
-            " Attributes:",
-            " Methods:",
-            "  ``aMethod()`` -- This method is documented.",
-            ""
-        ])
-
-        class IHasMethod(Interface):
-            """ This interface has a method.
-            """
-            def aMethod():
-                """This method is documented.
-                """
-
-        self.assertEqual(self._callFUT(IHasMethod), EXPECTED)
-
-    def test_asReStructuredText_derived_ignores_base(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        EXPECTED = '\n\n'.join([
-            "``IDerived``",
-            " IDerived doc",
-            " This interface extends:",
-            "  o ``IBase``",
-            " Attributes:",
-            "  ``attr1`` -- no documentation",
-            "  ``attr2`` -- attr2 doc",
-            " Methods:",
-            "  ``method3()`` -- method3 doc",
-            "  ``method4()`` -- no documentation",
-            "  ``method5()`` -- method5 doc",
-            "",
-        ])
-
-        class IBase(Interface):
-            def method1():
-                pass  # pragma: no cover
-
-            def method2():
-                pass  # pragma: no cover
-
-        class IDerived(IBase):
-            "IDerived doc"
-            attr1 = Attribute('attr1')
-            attr2 = Attribute('attr2', 'attr2 doc')
-
-            def method3():
-                "method3 doc"
-
-            def method4():
-                pass  # pragma: no cover
-
-            def method5():
-                "method5 doc"
-
-        self.assertEqual(self._callFUT(IDerived), EXPECTED)
-
-
-class Test__justify_and_indent(unittest.TestCase):
-
-    def _callFUT(self, text, level, **kw):
-        from zope.interface.document import _justify_and_indent
-        return _justify_and_indent(text, level, **kw)
-
-    def test_simple_level_0(self):
-        LINES = ['Three blind mice', 'See how they run']
-        text = '\n'.join(LINES)
-        self.assertEqual(self._callFUT(text, 0), text)
-
-    def test_simple_level_1(self):
-        LINES = ['Three blind mice', 'See how they run']
-        text = '\n'.join(LINES)
-        self.assertEqual(self._callFUT(text, 1),
-                         '\n'.join([' ' + line for line in LINES]))
-
-    def test_simple_level_2(self):
-        LINES = ['Three blind mice', 'See how they run']
-        text = '\n'.join(LINES)
-        self.assertEqual(self._callFUT(text, 1),
-                         '\n'.join([' ' + line for line in LINES]))
-
-    def test_simple_w_CRLF(self):
-        LINES = ['Three blind mice', 'See how they run']
-        text = '\r\n'.join(LINES)
-        self.assertEqual(self._callFUT(text, 1),
-                         '\n'.join([' ' + line for line in LINES]))
-
-    def test_with_munge(self):
-        TEXT = ("This is a piece of text longer than 15 characters, \n"
-                "and split across multiple lines.")
-        EXPECTED = ("  This is a piece\n"
-                    "  of text longer\n"
-                    "  than 15 characters,\n"
-                    "  and split across\n"
-                    "  multiple lines.\n"
-                    " ")
-        self.assertEqual(self._callFUT(TEXT, 1, munge=1, width=15), EXPECTED)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_element.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_element.py
deleted file mode 100644
index b47b3b5..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_element.py
+++ /dev/null
@@ -1,33 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Test Element meta-class.
-"""
-
-import unittest
-
-from zope.interface.interface import Element
-
-
-class TestElement(unittest.TestCase):
-
-    def test_taggedValues(self):
-        """Test that we can update tagged values of more than one element
-        """
-
-        e1 = Element("foo")
-        e2 = Element("bar")
-        e1.setTaggedValue("x", 1)
-        e2.setTaggedValue("x", 2)
-        self.assertEqual(e1.getTaggedValue("x"), 1)
-        self.assertEqual(e2.getTaggedValue("x"), 2)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_exceptions.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_exceptions.py
deleted file mode 100644
index e48c00f..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_exceptions.py
+++ /dev/null
@@ -1,190 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2010 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-""" zope.interface.exceptions unit tests
-"""
-import unittest
-
-
-def _makeIface():
-    from zope.interface import Interface
-
-    class IDummy(Interface):
-        pass
-
-    return IDummy
-
-
-class DoesNotImplementTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.exceptions import DoesNotImplement
-        return DoesNotImplement
-
-    def _makeOne(self, *args):
-        iface = _makeIface()
-        return self._getTargetClass()(iface, *args)
-
-    def test___str__(self):
-        dni = self._makeOne()
-        self.assertEqual(
-            str(dni),
-            "An object has failed to implement interface "
-            "zope.interface.tests.test_exceptions.IDummy: "
-            "Does not declaratively implement the interface."
-        )
-
-    def test___str__w_candidate(self):
-        dni = self._makeOne('candidate')
-        self.assertEqual(
-            str(dni),
-            "The object 'candidate' has failed to implement interface "
-            "zope.interface.tests.test_exceptions.IDummy: "
-            "Does not declaratively implement the interface."
-        )
-
-
-class BrokenImplementationTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.exceptions import BrokenImplementation
-        return BrokenImplementation
-
-    def _makeOne(self, *args):
-        iface = _makeIface()
-        return self._getTargetClass()(iface, 'missing', *args)
-
-    def test___str__(self):
-        dni = self._makeOne()
-        self.assertEqual(
-            str(dni),
-            'An object has failed to implement interface '
-            'zope.interface.tests.test_exceptions.IDummy: '
-            "The 'missing' attribute was not provided.")
-
-    def test___str__w_candidate(self):
-        dni = self._makeOne('candidate')
-        self.assertEqual(
-            str(dni),
-            'The object \'candidate\' has failed to implement interface '
-            'zope.interface.tests.test_exceptions.IDummy: '
-            "The 'missing' attribute was not provided.")
-
-
-def broken_function():
-    """
-    This is a global function with a simple argument list.
-
-    It exists to be able to report the same information when
-    formatting signatures.
-    """
-
-
-class BrokenMethodImplementationTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.exceptions import BrokenMethodImplementation
-        return BrokenMethodImplementation
-
-    message = 'I said so'
-
-    def _makeOne(self, *args):
-        return self._getTargetClass()('aMethod', self.message, *args)
-
-    def test___str__(self):
-        dni = self._makeOne()
-        self.assertEqual(
-            str(dni),
-            "An object has failed to implement interface : "
-            "The contract of 'aMethod' is violated because I said so."
-        )
-
-    def test___str__w_candidate_no_implementation(self):
-        dni = self._makeOne('some_function', '', 'candidate')
-        self.assertEqual(
-            str(dni),
-            "The object 'candidate' has failed to implement interface : "
-            "The contract of 'aMethod' is violated because I said so."
-        )
-
-    def test___str__w_candidate_w_implementation(self):
-        self.message = 'implementation is wonky'
-        dni = self._makeOne(broken_function, '', 'candidate')
-        self.assertEqual(
-            str(dni),
-            "The object 'candidate' has failed to implement interface : "
-            "The contract of 'aMethod' is violated because "
-            "'broken_function()' is wonky."
-        )
-
-    def test___str__w_candidate_w_implementation_not_callable(self):
-        self.message = 'implementation is not callable'
-        dni = self._makeOne(42, '', 'candidate')
-        self.assertEqual(
-            str(dni),
-            "The object 'candidate' has failed to implement interface : "
-            "The contract of 'aMethod' is violated because "
-            "'42' is not callable."
-        )
-
-    def test___repr__w_candidate(self):
-        dni = self._makeOne(None, 'candidate')
-        self.assertEqual(
-            repr(dni),
-            "BrokenMethodImplementation("
-            "'aMethod', 'I said so', None, 'candidate')"
-        )
-
-
-class MultipleInvalidTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.exceptions import MultipleInvalid
-        return MultipleInvalid
-
-    def _makeOne(self, excs):
-        iface = _makeIface()
-        return self._getTargetClass()(iface, 'target', excs)
-
-    def test__str__(self):
-        from zope.interface.exceptions import BrokenMethodImplementation
-        excs = [
-            BrokenMethodImplementation('aMethod', 'I said so'),
-            Exception("Regular exception")
-        ]
-        dni = self._makeOne(excs)
-        self.assertEqual(
-            str(dni),
-            "The object 'target' has failed to implement interface "
-            "zope.interface.tests.test_exceptions.IDummy:\n"
-            "    The contract of 'aMethod' is violated because I said so\n"
-            "    Regular exception"
-        )
-
-    def test__repr__(self):
-        from zope.interface.exceptions import BrokenMethodImplementation
-        excs = [
-            BrokenMethodImplementation('aMethod', 'I said so'),
-            # Use multiple arguments to normalize repr; versions of Python
-            # prior to 3.7 add a trailing comma if there's just one.
-            Exception("Regular", "exception")
-        ]
-        dni = self._makeOne(excs)
-        self.assertEqual(
-            repr(dni),
-            "MultipleInvalid("
-            ","
-            " 'target',"
-            " (BrokenMethodImplementation('aMethod', 'I said so'),"
-            " Exception('Regular', 'exception')))"
-        )
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_interface.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_interface.py
deleted file mode 100644
index 164add1..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_interface.py
+++ /dev/null
@@ -1,2871 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Test Interface implementation
-"""
-# Things we let slide because it's a test
-# pylint:disable=protected-access
-# pylint:disable=blacklisted-name
-# pylint:disable=attribute-defined-outside-init
-# pylint:disable=too-many-public-methods
-# pylint:disable=too-many-lines
-# pylint:disable=abstract-method
-# pylint:disable=redefined-builtin
-# pylint:disable=signature-differs
-# pylint:disable=arguments-differ
-# Things you get inheriting from Interface
-# pylint:disable=inherit-non-class
-# pylint:disable=no-self-argument
-# pylint:disable=no-method-argument
-# Things you get using methods of an Interface 'subclass'
-# pylint:disable=no-value-for-parameter
-import unittest
-
-from zope.interface.tests import CleanUp
-from zope.interface.tests import MissingSomeAttrs
-from zope.interface.tests import OptimizationTestMixin
-from zope.interface.tests import SubclassableMixin
-
-
-_marker = object()
-
-
-class Test_invariant(unittest.TestCase):
-
-    def test_w_single(self):
-        from zope.interface.interface import TAGGED_DATA
-        from zope.interface.interface import invariant
-
-        def _check(*args, **kw):
-            raise NotImplementedError()
-
-        class Foo:
-            invariant(_check)
-
-        self.assertEqual(getattr(Foo, TAGGED_DATA, None),
-                         {'invariants': [_check]})
-
-    def test_w_multiple(self):
-        from zope.interface.interface import TAGGED_DATA
-        from zope.interface.interface import invariant
-
-        def _check(*args, **kw):
-            raise NotImplementedError()
-
-        def _another_check(*args, **kw):
-            raise NotImplementedError()
-
-        class Foo:
-            invariant(_check)
-            invariant(_another_check)
-
-        self.assertEqual(getattr(Foo, TAGGED_DATA, None),
-                         {'invariants': [_check, _another_check]})
-
-
-class Test_taggedValue(unittest.TestCase):
-
-    def test_w_single(self):
-        from zope.interface.interface import TAGGED_DATA
-        from zope.interface.interface import taggedValue
-
-        class Foo:
-            taggedValue('bar', ['baz'])
-
-        self.assertEqual(getattr(Foo, TAGGED_DATA, None),
-                         {'bar': ['baz']})
-
-    def test_w_multiple(self):
-        from zope.interface.interface import TAGGED_DATA
-        from zope.interface.interface import taggedValue
-
-        class Foo:
-            taggedValue('bar', ['baz'])
-            taggedValue('qux', 'spam')
-
-        self.assertEqual(getattr(Foo, TAGGED_DATA, None),
-                         {'bar': ['baz'], 'qux': 'spam'})
-
-    def test_w_multiple_overwriting(self):
-        from zope.interface.interface import TAGGED_DATA
-        from zope.interface.interface import taggedValue
-
-        class Foo:
-            taggedValue('bar', ['baz'])
-            taggedValue('qux', 'spam')
-            taggedValue('bar', 'frob')
-
-        self.assertEqual(getattr(Foo, TAGGED_DATA, None),
-                         {'bar': 'frob', 'qux': 'spam'})
-
-
-class ElementTests(unittest.TestCase):
-
-    DEFAULT_NAME = 'AnElement'
-
-    def _getTargetClass(self):
-        from zope.interface.interface import Element
-        return Element
-
-    def _makeOne(self, name=None):
-        if name is None:
-            name = self.DEFAULT_NAME
-        return self._getTargetClass()(name)
-
-    def test_ctor_defaults(self):
-        element = self._makeOne()
-        self.assertEqual(element.__name__, self.DEFAULT_NAME)
-        self.assertEqual(element.getName(), self.DEFAULT_NAME)
-        self.assertEqual(element.__doc__, '')
-        self.assertEqual(element.getDoc(), '')
-        self.assertEqual(list(element.getTaggedValueTags()), [])
-
-    def test_ctor_no_doc_space_in_name(self):
-        element = self._makeOne('An Element')
-        self.assertEqual(element.__name__, None)
-        self.assertEqual(element.__doc__, 'An Element')
-
-    def test_getTaggedValue_miss(self):
-        element = self._makeOne()
-        self.assertRaises(KeyError, element.getTaggedValue, 'nonesuch')
-
-    def test_getDirectTaggedValueTags(self):
-        element = self._makeOne()
-        self.assertEqual([], list(element.getDirectTaggedValueTags()))
-
-        element.setTaggedValue('foo', 'bar')
-        self.assertEqual(['foo'], list(element.getDirectTaggedValueTags()))
-
-    def test_queryTaggedValue_miss(self):
-        element = self._makeOne()
-        self.assertEqual(element.queryTaggedValue('nonesuch'), None)
-
-    def test_queryTaggedValue_miss_w_default(self):
-        element = self._makeOne()
-        self.assertEqual(element.queryTaggedValue('nonesuch', 'bar'), 'bar')
-
-    def test_getDirectTaggedValue_miss(self):
-        element = self._makeOne()
-        self.assertRaises(KeyError, element.getDirectTaggedValue, 'nonesuch')
-
-    def test_queryDirectTaggedValue_miss(self):
-        element = self._makeOne()
-        self.assertEqual(element.queryDirectTaggedValue('nonesuch'), None)
-
-    def test_queryDirectTaggedValue_miss_w_default(self):
-        element = self._makeOne()
-        self.assertEqual(
-            element.queryDirectTaggedValue('nonesuch', 'bar'), 'bar'
-        )
-
-    def test_setTaggedValue(self):
-        element = self._makeOne()
-        element.setTaggedValue('foo', 'bar')
-        self.assertEqual(list(element.getTaggedValueTags()), ['foo'])
-        self.assertEqual(element.getTaggedValue('foo'), 'bar')
-        self.assertEqual(element.queryTaggedValue('foo'), 'bar')
-
-    def test_verifies(self):
-        from zope.interface.interfaces import IElement
-        from zope.interface.verify import verifyObject
-
-        element = self._makeOne()
-        verifyObject(IElement, element)
-
-
-class GenericSpecificationBaseTests(unittest.TestCase):
-    # Tests that work with both implementations
-    def _getFallbackClass(self):
-        from zope.interface.interface import SpecificationBasePy
-        return SpecificationBasePy
-
-    _getTargetClass = _getFallbackClass
-
-    def _makeOne(self):
-        return self._getTargetClass()()
-
-    def test_providedBy_miss(self):
-        from zope.interface import interface
-        from zope.interface.declarations import _empty
-        sb = self._makeOne()
-
-        def _providedBy(obj):
-            return _empty
-
-        with _Monkey(interface, providedBy=_providedBy):
-            self.assertFalse(sb.providedBy(object()))
-
-    def test_implementedBy_miss(self):
-        from zope.interface import interface
-        from zope.interface.declarations import _empty
-        sb = self._makeOne()
-
-        def _implementedBy(obj):
-            return _empty
-
-        with _Monkey(interface, implementedBy=_implementedBy):
-            self.assertFalse(sb.implementedBy(object()))
-
-
-class SpecificationBaseTests(
-    GenericSpecificationBaseTests,
-    OptimizationTestMixin,
-    SubclassableMixin,
-):
-    # Tests that use the C implementation
-
-    def _getTargetClass(self):
-        from zope.interface.interface import SpecificationBase
-        return SpecificationBase
-
-
-class SpecificationBasePyTests(GenericSpecificationBaseTests):
-    # Tests that only work with the Python implementation
-
-    def test___call___miss(self):
-        sb = self._makeOne()
-        sb._implied = {}  # not defined by SpecificationBasePy
-        self.assertFalse(sb.isOrExtends(object()))
-
-    def test___call___hit(self):
-        sb = self._makeOne()
-        testing = object()
-        sb._implied = {testing: {}}  # not defined by SpecificationBasePy
-        self.assertTrue(sb(testing))
-
-    def test_isOrExtends_miss(self):
-        sb = self._makeOne()
-        sb._implied = {}  # not defined by SpecificationBasePy
-        self.assertFalse(sb.isOrExtends(object()))
-
-    def test_isOrExtends_hit(self):
-        sb = self._makeOne()
-        testing = object()
-        sb._implied = {testing: {}}  # not defined by SpecificationBasePy
-        self.assertTrue(sb(testing))
-
-    def test_implementedBy_hit(self):
-        from zope.interface import interface
-        sb = self._makeOne()
-
-        class _Decl:
-            _implied = {sb: {}}
-
-        def _implementedBy(obj):
-            return _Decl()
-
-        with _Monkey(interface, implementedBy=_implementedBy):
-            self.assertTrue(sb.implementedBy(object()))
-
-    def test_providedBy_hit(self):
-        from zope.interface import interface
-        sb = self._makeOne()
-
-        class _Decl:
-            _implied = {sb: {}}
-
-        def _providedBy(obj):
-            return _Decl()
-
-        with _Monkey(interface, providedBy=_providedBy):
-            self.assertTrue(sb.providedBy(object()))
-
-
-class NameAndModuleComparisonTestsMixin(CleanUp):
-
-    def _makeOneToCompare(self):
-        return self._makeOne('a', 'b')
-
-    def __check_NotImplemented_comparison(self, name):
-        # Without the correct attributes of __name__ and __module__,
-        # comparison switches to the reverse direction.
-
-        import operator
-        ib = self._makeOneToCompare()
-        op = getattr(operator, name)
-        meth = getattr(ib, '__%s__' % name)
-
-        # If either the __name__ or __module__ attribute
-        # is missing from the other object, then we return
-        # NotImplemented.
-        class RaisesErrorOnMissing:
-            Exc = AttributeError
-
-            def __getattribute__(self, name):
-                try:
-                    return object.__getattribute__(self, name)
-                except AttributeError:
-                    exc = RaisesErrorOnMissing.Exc
-                    raise exc(name)
-
-        class RaisesErrorOnModule(RaisesErrorOnMissing):
-            def __init__(self):
-                self.__name__ = 'foo'
-
-            @property
-            def __module__(self):
-                raise AttributeError
-
-        class RaisesErrorOnName(RaisesErrorOnMissing):
-            def __init__(self):
-                self.__module__ = 'foo'
-
-        self.assertEqual(RaisesErrorOnModule().__name__, 'foo')
-        self.assertEqual(RaisesErrorOnName().__module__, 'foo')
-        with self.assertRaises(AttributeError):
-            getattr(RaisesErrorOnModule(), '__module__')
-        with self.assertRaises(AttributeError):
-            getattr(RaisesErrorOnName(), '__name__')
-
-        for cls in RaisesErrorOnModule, RaisesErrorOnName:
-            self.assertIs(meth(cls()), NotImplemented)
-
-        # If the other object has a comparison function, returning
-        # NotImplemented means Python calls it.
-
-        class AllowsAnyComparison(RaisesErrorOnMissing):
-            def __eq__(self, other):
-                return True
-            __lt__ = __eq__
-            __le__ = __eq__
-            __gt__ = __eq__
-            __ge__ = __eq__
-            __ne__ = __eq__
-
-        self.assertTrue(op(ib, AllowsAnyComparison()))
-        self.assertIs(meth(AllowsAnyComparison()), NotImplemented)
-
-        # If it doesn't have the comparison, Python raises a TypeError.
-        class AllowsNoComparison:
-            __eq__ = None
-            __lt__ = __eq__
-            __le__ = __eq__
-            __gt__ = __eq__
-            __ge__ = __eq__
-            __ne__ = __eq__
-
-        self.assertIs(meth(AllowsNoComparison()), NotImplemented)
-        with self.assertRaises(TypeError):
-            op(ib, AllowsNoComparison())
-
-        # Errors besides AttributeError are passed
-        class MyException(Exception):
-            pass
-
-        RaisesErrorOnMissing.Exc = MyException
-
-        with self.assertRaises(MyException):
-            getattr(RaisesErrorOnModule(), '__module__')
-        with self.assertRaises(MyException):
-            getattr(RaisesErrorOnName(), '__name__')
-
-        for cls in RaisesErrorOnModule, RaisesErrorOnName:
-            with self.assertRaises(MyException):
-                op(ib, cls())
-            with self.assertRaises(MyException):
-                meth(cls())
-
-    def test__lt__NotImplemented(self):
-        self.__check_NotImplemented_comparison('lt')
-
-    def test__le__NotImplemented(self):
-        self.__check_NotImplemented_comparison('le')
-
-    def test__gt__NotImplemented(self):
-        self.__check_NotImplemented_comparison('gt')
-
-    def test__ge__NotImplemented(self):
-        self.__check_NotImplemented_comparison('ge')
-
-
-class InterfaceBaseTestsMixin(NameAndModuleComparisonTestsMixin):
-    # Tests for both C and Python implementation
-
-    def _getTargetClass(self):
-        raise NotImplementedError
-
-    def _getFallbackClass(self):
-        # pylint:disable=no-name-in-module
-        from zope.interface.interface import InterfaceBasePy
-        return InterfaceBasePy
-
-    def _makeOne(self, object_should_provide=False, name=None, module=None):
-
-        class IB(self._getTargetClass()):
-            def _call_conform(self, conform):
-                return conform(self)
-
-            def providedBy(self, obj):
-                return object_should_provide
-
-        return IB(name, module)
-
-    def test___call___w___conform___returning_value(self):
-        ib = self._makeOne(False)
-        conformed = object()
-
-        class _Adapted:
-            def __conform__(self, iface):
-                return conformed
-
-        self.assertIs(ib(_Adapted()), conformed)
-
-    def test___call___wo___conform___ob_no_provides_w_alternate(self):
-        ib = self._makeOne(False)
-        __traceback_info__ = ib, self._getTargetClass()
-        adapted = object()
-        alternate = object()
-        self.assertIs(ib(adapted, alternate), alternate)
-
-    def test___call___w___conform___ob_no_provides_wo_alternate(self):
-        ib = self._makeOne(False)
-        with self.assertRaises(TypeError) as exc:
-            ib(object())
-
-        self.assertIn('Could not adapt', str(exc.exception))
-
-    def test___call___w_no_conform_catches_only_AttributeError(self):
-        MissingSomeAttrs.test_raises(
-            self, self._makeOne(), expected_missing='__conform__'
-        )
-
-
-class InterfaceBaseTests(
-    InterfaceBaseTestsMixin,
-    OptimizationTestMixin,
-    SubclassableMixin,
-    unittest.TestCase,
-):
-    # Tests that work with the C implementation
-    def _getTargetClass(self):
-        from zope.interface.interface import InterfaceBase
-        return InterfaceBase
-
-
-class InterfaceBasePyTests(InterfaceBaseTestsMixin, unittest.TestCase):
-    # Tests that only work with the Python implementation
-
-    _getTargetClass = InterfaceBaseTestsMixin._getFallbackClass
-
-    def test___call___w___conform___miss_ob_provides(self):
-        ib = self._makeOne(True)
-
-        class _Adapted:
-            def __conform__(self, iface):
-                return None
-
-        adapted = _Adapted()
-        self.assertIs(ib(adapted), adapted)
-
-    def test___adapt___ob_provides(self):
-        ib = self._makeOne(True)
-        adapted = object()
-        self.assertIs(ib.__adapt__(adapted), adapted)
-
-    def test___adapt___ob_no_provides_uses_hooks(self):
-        from zope.interface import interface
-        ib = self._makeOne(False)
-        adapted = object()
-        _missed = []
-
-        def _hook_miss(iface, obj):
-            _missed.append((iface, obj))
-
-        def _hook_hit(iface, obj):
-            return obj
-
-        with _Monkey(interface, adapter_hooks=[_hook_miss, _hook_hit]):
-            self.assertIs(ib.__adapt__(adapted), adapted)
-            self.assertEqual(_missed, [(ib, adapted)])
-
-
-class SpecificationTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.interface import Specification
-        return Specification
-
-    def _makeOne(self, bases=_marker):
-        if bases is _marker:
-            return self._getTargetClass()()
-        return self._getTargetClass()(bases)
-
-    def test_ctor(self):
-        from zope.interface.interface import Interface
-        spec = self._makeOne()
-        self.assertEqual(spec.__bases__, ())
-        self.assertEqual(len(spec._implied), 2)
-        self.assertIn(spec, spec._implied)
-        self.assertIn(Interface, spec._implied)
-        self.assertEqual(len(spec.dependents), 0)
-
-    def test_subscribe_first_time(self):
-        spec = self._makeOne()
-        dep = DummyDependent()
-        spec.subscribe(dep)
-        self.assertEqual(len(spec.dependents), 1)
-        self.assertEqual(spec.dependents[dep], 1)
-
-    def test_subscribe_again(self):
-        spec = self._makeOne()
-        dep = DummyDependent()
-        spec.subscribe(dep)
-        spec.subscribe(dep)
-        self.assertEqual(spec.dependents[dep], 2)
-
-    def test_unsubscribe_miss(self):
-        spec = self._makeOne()
-        dep = DummyDependent()
-        self.assertRaises(KeyError, spec.unsubscribe, dep)
-
-    def test_unsubscribe(self):
-        spec = self._makeOne()
-        dep = DummyDependent()
-        spec.subscribe(dep)
-        spec.subscribe(dep)
-        spec.unsubscribe(dep)
-        self.assertEqual(spec.dependents[dep], 1)
-        spec.unsubscribe(dep)
-        self.assertNotIn(dep, spec.dependents)
-
-    def test___setBases_subscribes_bases_and_notifies_dependents(self):
-        from zope.interface.interface import Interface
-        spec = self._makeOne()
-        dep = DummyDependent()
-        spec.subscribe(dep)
-
-        class IFoo(Interface):
-            pass
-
-        class IBar(Interface):
-            pass
-
-        spec.__bases__ = (IFoo,)
-        self.assertEqual(dep._changed, [spec])
-        self.assertEqual(IFoo.dependents[spec], 1)
-        spec.__bases__ = (IBar,)
-        self.assertEqual(IFoo.dependents.get(spec), None)
-        self.assertEqual(IBar.dependents[spec], 1)
-
-    def test_changed_clears_volatiles_and_implied(self):
-        from zope.interface.interface import Interface
-
-        class IFoo(Interface):
-            pass
-
-        spec = self._makeOne()
-        spec._v_attrs = 'Foo'
-        spec._implied[IFoo] = ()
-        spec.changed(spec)
-        self.assertIsNone(spec._v_attrs)
-        self.assertNotIn(IFoo, spec._implied)
-
-    def test_interfaces_skips_already_seen(self):
-        from zope.interface.interface import Interface
-
-        class IFoo(Interface):
-            pass
-
-        spec = self._makeOne([IFoo, IFoo])
-        self.assertEqual(list(spec.interfaces()), [IFoo])
-
-    def test_extends_strict_wo_self(self):
-        from zope.interface.interface import Interface
-
-        class IFoo(Interface):
-            pass
-
-        spec = self._makeOne(IFoo)
-        self.assertFalse(spec.extends(IFoo, strict=True))
-
-    def test_extends_strict_w_self(self):
-        spec = self._makeOne()
-        self.assertFalse(spec.extends(spec, strict=True))
-
-    def test_extends_non_strict_w_self(self):
-        spec = self._makeOne()
-        self.assertTrue(spec.extends(spec, strict=False))
-
-    def test_get_hit_w__v_attrs(self):
-        spec = self._makeOne()
-        foo = object()
-        spec._v_attrs = {'foo': foo}
-        self.assertIs(spec.get('foo'), foo)
-
-    def test_get_hit_from_base_wo__v_attrs(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import Interface
-
-        class IFoo(Interface):
-            foo = Attribute('foo')
-
-        class IBar(Interface):
-            bar = Attribute('bar')
-
-        spec = self._makeOne([IFoo, IBar])
-        self.assertIs(spec.get('foo'), IFoo.get('foo'))
-        self.assertIs(spec.get('bar'), IBar.get('bar'))
-
-    def test_multiple_inheritance_no_interfaces(self):
-        # If we extend an object that implements interfaces,
-        # plus one that doesn't, we do not interject `Interface`
-        # early in the resolution order. It stays at the end,
-        # like it should.
-        # See https://github.com/zopefoundation/zope.interface/issues/8
-        from zope.interface.declarations import implementedBy
-        from zope.interface.declarations import implementer
-        from zope.interface.interface import Interface
-
-        class IDefaultViewName(Interface):
-            pass
-
-        class Context:
-            pass
-
-        class RDBModel(Context):
-            pass
-
-        class IOther(Interface):
-            pass
-
-        @implementer(IOther)
-        class OtherBase:
-            pass
-
-        class Model(OtherBase, Context):
-            pass
-
-        self.assertEqual(
-            implementedBy(Model).__sro__,
-            (
-                implementedBy(Model),
-                implementedBy(OtherBase),
-                IOther,
-                implementedBy(Context),
-                implementedBy(object),
-                Interface,  # This used to be wrong, it used to be 2 too high.
-            )
-        )
-
-
-class InterfaceClassTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.interface import InterfaceClass
-        return InterfaceClass
-
-    def _makeOne(self, name='ITest', bases=(), attrs=None, __doc__=None,
-                 __module__=None):
-        return self._getTargetClass()(name, bases, attrs, __doc__, __module__)
-
-    def test_ctor_defaults(self):
-        klass = self._getTargetClass()
-        inst = klass('ITesting')
-        self.assertEqual(inst.__name__, 'ITesting')
-        self.assertEqual(inst.__doc__, '')
-        self.assertEqual(inst.__bases__, ())
-        self.assertEqual(inst.getBases(), ())
-
-    def test_ctor_bad_bases(self):
-        klass = self._getTargetClass()
-        self.assertRaises(TypeError, klass, 'ITesting', (object(),))
-
-    def test_ctor_w_attrs_attrib_methods(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        klass = self._getTargetClass()
-        inst = klass('ITesting', attrs=ATTRS)
-        self.assertEqual(inst.__name__, 'ITesting')
-        self.assertEqual(inst.__doc__, '')
-        self.assertEqual(inst.__bases__, ())
-        self.assertEqual(inst.names(), ATTRS.keys())
-
-    def test_ctor_attrs_w___locals__(self):
-        ATTRS = {'__locals__': {}}
-        klass = self._getTargetClass()
-        inst = klass('ITesting', attrs=ATTRS)
-        self.assertEqual(inst.__name__, 'ITesting')
-        self.assertEqual(inst.__doc__, '')
-        self.assertEqual(inst.__bases__, ())
-        self.assertEqual(list(inst.names()), [])
-
-    def test_ctor_attrs_w___annotations__(self):
-        ATTRS = {'__annotations__': {}}
-        klass = self._getTargetClass()
-        inst = klass('ITesting', attrs=ATTRS)
-        self.assertEqual(inst.__name__, 'ITesting')
-        self.assertEqual(inst.__doc__, '')
-        self.assertEqual(inst.__bases__, ())
-        self.assertEqual(list(inst.names()), [])
-
-    def test_ctor_attrs_w__decorator_non_return(self):
-        from zope.interface.interface import _decorator_non_return
-        ATTRS = {'dropme': _decorator_non_return}
-        klass = self._getTargetClass()
-        inst = klass('ITesting', attrs=ATTRS)
-        self.assertEqual(inst.__name__, 'ITesting')
-        self.assertEqual(inst.__doc__, '')
-        self.assertEqual(inst.__bases__, ())
-        self.assertEqual(list(inst.names()), [])
-
-    def test_ctor_attrs_w_invalid_attr_type(self):
-        from zope.interface.exceptions import InvalidInterface
-        ATTRS = {'invalid': object()}
-        klass = self._getTargetClass()
-        self.assertRaises(InvalidInterface, klass, 'ITesting', attrs=ATTRS)
-
-    def test_ctor_w_explicit___doc__(self):
-        ATTRS = {'__doc__': 'ATTR'}
-        klass = self._getTargetClass()
-        inst = klass('ITesting', attrs=ATTRS, __doc__='EXPLICIT')
-        self.assertEqual(inst.__doc__, 'EXPLICIT')
-
-    def test_interfaces(self):
-        iface = self._makeOne()
-        self.assertEqual(list(iface.interfaces()), [iface])
-
-    def test_getBases(self):
-        iface = self._makeOne()
-        sub = self._makeOne('ISub', bases=(iface,))
-        self.assertEqual(sub.getBases(), (iface,))
-
-    def test_isEqualOrExtendedBy_identity(self):
-        iface = self._makeOne()
-        self.assertTrue(iface.isEqualOrExtendedBy(iface))
-
-    def test_isEqualOrExtendedBy_subiface(self):
-        iface = self._makeOne()
-        sub = self._makeOne('ISub', bases=(iface,))
-        self.assertTrue(iface.isEqualOrExtendedBy(sub))
-        self.assertFalse(sub.isEqualOrExtendedBy(iface))
-
-    def test_isEqualOrExtendedBy_unrelated(self):
-        one = self._makeOne('One')
-        another = self._makeOne('Another')
-        self.assertFalse(one.isEqualOrExtendedBy(another))
-        self.assertFalse(another.isEqualOrExtendedBy(one))
-
-    def test_names_w_all_False_ignores_bases(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(sorted(derived.names(all=False)), ['baz'])
-
-    def test_names_w_all_True_no_bases(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        one = self._makeOne(attrs=ATTRS)
-        self.assertEqual(sorted(one.names(all=True)), ['bar', 'foo'])
-
-    def test_names_w_all_True_w_bases_simple(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(
-            sorted(derived.names(all=True)), ['bar', 'baz', 'foo']
-        )
-
-    def test_names_w_all_True_bases_w_same_names(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        def _foo():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'foo': fromFunction(_foo),
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(sorted(
-            derived.names(all=True)), ['bar', 'baz', 'foo']
-        )
-
-    def test___iter__(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        def _foo():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'foo': fromFunction(_foo),
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(sorted(derived), ['bar', 'baz', 'foo'])
-
-    def test_namesAndDescriptions_w_all_False_ignores_bases(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(
-            sorted(derived.namesAndDescriptions(all=False)), [
-                ('baz', DERIVED_ATTRS['baz']),
-            ]
-        )
-
-    def test_namesAndDescriptions_w_all_True_no_bases(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        one = self._makeOne(attrs=ATTRS)
-        self.assertEqual(
-            sorted(one.namesAndDescriptions(all=False)), [
-                ('bar', ATTRS['bar']),
-                ('foo', ATTRS['foo']),
-            ]
-        )
-
-    def test_namesAndDescriptions_w_all_True_simple(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(
-            sorted(derived.namesAndDescriptions(all=True)), [
-                ('bar', BASE_ATTRS['bar']),
-                ('baz', DERIVED_ATTRS['baz']),
-                ('foo', BASE_ATTRS['foo']),
-            ]
-        )
-
-    def test_namesAndDescriptions_w_all_True_bases_w_same_names(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        def _foo():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'foo': fromFunction(_foo),
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(
-            sorted(derived.namesAndDescriptions(all=True)), [
-                ('bar', BASE_ATTRS['bar']),
-                ('baz', DERIVED_ATTRS['baz']),
-                ('foo', DERIVED_ATTRS['foo']),
-            ]
-        )
-
-    def test_getDescriptionFor_miss(self):
-        one = self._makeOne()
-        self.assertRaises(KeyError, one.getDescriptionFor, 'nonesuch')
-
-    def test_getDescriptionFor_hit(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        one = self._makeOne(attrs=ATTRS)
-        self.assertEqual(one.getDescriptionFor('foo'), ATTRS['foo'])
-        self.assertEqual(one.getDescriptionFor('bar'), ATTRS['bar'])
-
-    def test___getitem___miss(self):
-        one = self._makeOne()
-
-        def _test():
-            return one['nonesuch']
-
-        self.assertRaises(KeyError, _test)
-
-    def test___getitem___hit(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        one = self._makeOne(attrs=ATTRS)
-        self.assertEqual(one['foo'], ATTRS['foo'])
-        self.assertEqual(one['bar'], ATTRS['bar'])
-
-    def test___contains___miss(self):
-        one = self._makeOne()
-        self.assertNotIn('nonesuch', one)
-
-    def test___contains___hit(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        one = self._makeOne(attrs=ATTRS)
-        self.assertIn('foo', one)
-        self.assertIn('bar', one)
-
-    def test_direct_miss(self):
-        one = self._makeOne()
-        self.assertEqual(one.direct('nonesuch'), None)
-
-    def test_direct_hit_local_miss_bases(self):
-        from zope.interface.interface import Attribute
-        from zope.interface.interface import fromFunction
-
-        def _bar():
-            """DOCSTRING"""
-
-        def _foo():
-            """DOCSTRING"""
-
-        BASE_ATTRS = {
-            'foo': Attribute('Foo', ''),
-            'bar': fromFunction(_bar),
-        }
-        DERIVED_ATTRS = {
-            'foo': fromFunction(_foo),
-            'baz': Attribute('Baz', ''),
-        }
-        base = self._makeOne('IBase', attrs=BASE_ATTRS)
-        derived = self._makeOne('IDerived', bases=(base,), attrs=DERIVED_ATTRS)
-        self.assertEqual(derived.direct('foo'), DERIVED_ATTRS['foo'])
-        self.assertEqual(derived.direct('baz'), DERIVED_ATTRS['baz'])
-        self.assertEqual(derived.direct('bar'), None)
-
-    def test_queryDescriptionFor_miss(self):
-        iface = self._makeOne()
-        self.assertEqual(iface.queryDescriptionFor('nonesuch'), None)
-
-    def test_queryDescriptionFor_hit(self):
-        from zope.interface import Attribute
-        ATTRS = {'attr': Attribute('Title', 'Description')}
-        iface = self._makeOne(attrs=ATTRS)
-        self.assertEqual(iface.queryDescriptionFor('attr'), ATTRS['attr'])
-
-    def test_validateInvariants_pass(self):
-        _called_with = []
-
-        def _passable(*args, **kw):
-            _called_with.append((args, kw))
-            return True
-
-        iface = self._makeOne()
-        obj = object()
-        iface.setTaggedValue('invariants', [_passable])
-        self.assertEqual(iface.validateInvariants(obj), None)
-        self.assertEqual(_called_with, [((obj,), {})])
-
-    def test_validateInvariants_fail_wo_errors_passed(self):
-        from zope.interface.exceptions import Invalid
-        _passable_called_with = []
-
-        def _passable(*args, **kw):
-            _passable_called_with.append((args, kw))
-            return True
-
-        _fail_called_with = []
-
-        def _fail(*args, **kw):
-            _fail_called_with.append((args, kw))
-            raise Invalid
-
-        iface = self._makeOne()
-        obj = object()
-        iface.setTaggedValue('invariants', [_passable, _fail])
-        self.assertRaises(Invalid, iface.validateInvariants, obj)
-        self.assertEqual(_passable_called_with, [((obj,), {})])
-        self.assertEqual(_fail_called_with, [((obj,), {})])
-
-    def test_validateInvariants_fail_w_errors_passed(self):
-        from zope.interface.exceptions import Invalid
-        _errors = []
-        _fail_called_with = []
-
-        def _fail(*args, **kw):
-            _fail_called_with.append((args, kw))
-            raise Invalid
-
-        iface = self._makeOne()
-        obj = object()
-        iface.setTaggedValue('invariants', [_fail])
-        self.assertRaises(Invalid, iface.validateInvariants, obj, _errors)
-        self.assertEqual(_fail_called_with, [((obj,), {})])
-        self.assertEqual(len(_errors), 1)
-        self.assertIsInstance(_errors[0], Invalid)
-
-    def test_validateInvariants_fail_in_base_wo_errors_passed(self):
-        from zope.interface.exceptions import Invalid
-        _passable_called_with = []
-
-        def _passable(*args, **kw):
-            _passable_called_with.append((args, kw))
-            return True
-
-        _fail_called_with = []
-
-        def _fail(*args, **kw):
-            _fail_called_with.append((args, kw))
-            raise Invalid
-
-        base = self._makeOne('IBase')
-        derived = self._makeOne('IDerived', (base,))
-        obj = object()
-        base.setTaggedValue('invariants', [_fail])
-        derived.setTaggedValue('invariants', [_passable])
-        self.assertRaises(Invalid, derived.validateInvariants, obj)
-        self.assertEqual(_passable_called_with, [((obj,), {})])
-        self.assertEqual(_fail_called_with, [((obj,), {})])
-
-    def test_validateInvariants_fail_in_base_w_errors_passed(self):
-        from zope.interface.exceptions import Invalid
-        _errors = []
-        _passable_called_with = []
-
-        def _passable(*args, **kw):
-            _passable_called_with.append((args, kw))
-            return True
-
-        _fail_called_with = []
-
-        def _fail(*args, **kw):
-            _fail_called_with.append((args, kw))
-            raise Invalid
-
-        base = self._makeOne('IBase')
-        derived = self._makeOne('IDerived', (base,))
-        obj = object()
-        base.setTaggedValue('invariants', [_fail])
-        derived.setTaggedValue('invariants', [_passable])
-        self.assertRaises(Invalid, derived.validateInvariants, obj, _errors)
-        self.assertEqual(_passable_called_with, [((obj,), {})])
-        self.assertEqual(_fail_called_with, [((obj,), {})])
-        self.assertEqual(len(_errors), 1)
-        self.assertIsInstance(_errors[0], Invalid)
-
-    def test_validateInvariants_inherited_not_called_multiple_times(self):
-        _passable_called_with = []
-
-        def _passable(*args, **kw):
-            _passable_called_with.append((args, kw))
-            return True
-
-        obj = object()
-        base = self._makeOne('IBase')
-        base.setTaggedValue('invariants', [_passable])
-        derived = self._makeOne('IDerived', (base,))
-        derived.validateInvariants(obj)
-        self.assertEqual(1, len(_passable_called_with))
-
-    def test___reduce__(self):
-        iface = self._makeOne('PickleMe')
-        self.assertEqual(iface.__reduce__(), 'PickleMe')
-
-    def test___hash___normal(self):
-        iface = self._makeOne('HashMe')
-        self.assertEqual(
-            hash(iface),
-            hash(('HashMe', 'zope.interface.tests.test_interface'))
-        )
-
-    def test___hash___missing_required_attrs(self):
-
-        class Derived(self._getTargetClass()):
-            def __init__(self):  # pylint:disable=super-init-not-called
-                pass  # Don't call base class.
-
-        derived = Derived()
-        with self.assertRaises(AttributeError):
-            hash(derived)
-
-    def test_comparison_with_None(self):
-        # pylint:disable=singleton-comparison,misplaced-comparison-constant
-        iface = self._makeOne()
-        self.assertLess(iface, None)  # noqa E711
-        self.assertLessEqual(iface, None)  # noqa E711
-        self.assertNotEqual(iface, None)  # noqa E711
-        self.assertNotEqual(iface, None)  # noqa E711
-        self.assertFalse(iface >= None)  # noqa E711
-        self.assertFalse(iface > None)   # noqa E711
-
-        self.assertFalse(None < iface)   # noqa E711
-        self.assertFalse(None <= iface)  # noqa E711
-        self.assertNotEqual(None, iface)  # noqa E711
-        self.assertNotEqual(None, iface)  # noqa E711
-        self.assertGreaterEqual(None, iface)  # noqa E711
-        self.assertGreater(None, iface)  # noqa E711
-
-    def test_comparison_with_same_instance(self):
-        # pylint:disable=comparison-with-itself
-        iface = self._makeOne()
-
-        self.assertFalse(iface < iface)
-        self.assertLessEqual(iface, iface)
-        self.assertEqual(iface, iface)
-        self.assertEqual(iface, iface)
-        self.assertGreaterEqual(iface, iface)
-        self.assertFalse(iface > iface)
-
-    def test_comparison_with_same_named_instance_in_other_module(self):
-
-        one = self._makeOne('IName', __module__='zope.interface.tests.one')
-        other = self._makeOne('IName', __module__='zope.interface.tests.other')
-
-        self.assertLess(one, other)
-        self.assertFalse(other < one)
-        self.assertLessEqual(one, other)
-        self.assertFalse(other <= one)
-        self.assertNotEqual(one, other)
-        self.assertNotEqual(other, one)
-        self.assertNotEqual(one, other)
-        self.assertNotEqual(other, one)
-        self.assertFalse(one >= other)
-        self.assertGreaterEqual(other, one)
-        self.assertFalse(one > other)
-        self.assertGreater(other, one)
-
-    def test_assignment_to__class__(self):
-        # https://github.com/zopefoundation/zope.interface/issues/6
-        class MyException(Exception):
-            pass
-
-        class MyInterfaceClass(self._getTargetClass()):
-            def __call__(self, target):
-                raise MyException(target)
-
-        IFoo = self._makeOne('IName')
-        self.assertIsInstance(IFoo, self._getTargetClass())
-        self.assertIs(type(IFoo), self._getTargetClass())
-
-        with self.assertRaises(TypeError):
-            IFoo(1)
-
-        IFoo.__class__ = MyInterfaceClass
-        self.assertIsInstance(IFoo, MyInterfaceClass)
-        self.assertIs(type(IFoo), MyInterfaceClass)
-
-        with self.assertRaises(MyException):
-            IFoo(1)
-
-    def test_assignment_to__class__2(self):
-        # https://github.com/zopefoundation/zope.interface/issues/6
-        # This is essentially a transcription of the
-        # test presented in the bug report.
-        from zope.interface import Interface
-
-        class MyInterfaceClass(self._getTargetClass()):
-            def __call__(self, *args):
-                return args
-
-        IFoo = MyInterfaceClass('IFoo', (Interface,))
-        self.assertEqual(IFoo(1), (1,))
-
-        class IBar(IFoo):
-            pass
-
-        self.assertEqual(IBar(1), (1,))
-
-        class ISpam(Interface):
-            pass
-
-        with self.assertRaises(TypeError):
-            ISpam()
-
-        ISpam.__class__ = MyInterfaceClass
-        self.assertEqual(ISpam(1), (1,))
-
-    def test__module__is_readonly(self):
-        inst = self._makeOne()
-        with self.assertRaises(AttributeError):
-            inst.__module__ = 'different.module'
-
-
-class InterfaceTests(unittest.TestCase):
-
-    def test_attributes_link_to_interface(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class I1(Interface):
-            attr = Attribute("My attr")
-
-        self.assertIs(I1['attr'].interface, I1)
-
-    def test_methods_link_to_interface(self):
-        from zope.interface import Interface
-
-        class I1(Interface):
-            def method(foo, bar, bingo):
-                "A method"
-
-        self.assertIs(I1['method'].interface, I1)
-
-    def test_classImplements_simple(self):
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import providedBy
-
-        class ICurrent(Interface):
-            def method1(a, b):
-                """docstring"""
-
-            def method2(a, b):
-                """docstring"""
-
-        class IOther(Interface):
-            pass
-
-        class Current:
-            __implemented__ = ICurrent
-
-            def method1(self, a, b):
-                raise NotImplementedError()
-
-            def method2(self, a, b):
-                raise NotImplementedError()
-
-        current = Current()
-
-        self.assertTrue(ICurrent.implementedBy(Current))
-        self.assertFalse(IOther.implementedBy(Current))
-        self.assertEqual(ICurrent, ICurrent)
-        self.assertIn(ICurrent, implementedBy(Current))
-        self.assertNotIn(IOther, implementedBy(Current))
-        self.assertIn(ICurrent, providedBy(current))
-        self.assertNotIn(IOther, providedBy(current))
-
-    def test_classImplements_base_not_derived(self):
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import providedBy
-
-        class IBase(Interface):
-            def method():
-                """docstring"""
-
-        class IDerived(IBase):
-            pass
-
-        class Current():
-            __implemented__ = IBase
-
-            def method(self):
-                raise NotImplementedError()
-
-        current = Current()
-
-        self.assertTrue(IBase.implementedBy(Current))
-        self.assertFalse(IDerived.implementedBy(Current))
-        self.assertIn(IBase, implementedBy(Current))
-        self.assertNotIn(IDerived, implementedBy(Current))
-        self.assertIn(IBase, providedBy(current))
-        self.assertNotIn(IDerived, providedBy(current))
-
-    def test_classImplements_base_and_derived(self):
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import providedBy
-
-        class IBase(Interface):
-            def method():
-                """docstring"""
-
-        class IDerived(IBase):
-            pass
-
-        class Current:
-            __implemented__ = IDerived
-
-            def method(self):
-                raise NotImplementedError()
-
-        current = Current()
-
-        self.assertTrue(IBase.implementedBy(Current))
-        self.assertTrue(IDerived.implementedBy(Current))
-        self.assertNotIn(IBase, implementedBy(Current))
-        self.assertIn(IBase, implementedBy(Current).flattened())
-        self.assertIn(IDerived, implementedBy(Current))
-        self.assertNotIn(IBase, providedBy(current))
-        self.assertIn(IBase, providedBy(current).flattened())
-        self.assertIn(IDerived, providedBy(current))
-
-    def test_classImplements_multiple(self):
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import providedBy
-
-        class ILeft(Interface):
-            def method():
-                """docstring"""
-
-        class IRight(ILeft):
-            pass
-
-        class Left:
-            __implemented__ = ILeft
-
-            def method(self):
-                raise NotImplementedError()
-
-        class Right:
-            __implemented__ = IRight
-
-        class Ambi(Left, Right):
-            pass
-
-        ambi = Ambi()
-
-        self.assertTrue(ILeft.implementedBy(Ambi))
-        self.assertTrue(IRight.implementedBy(Ambi))
-        self.assertIn(ILeft, implementedBy(Ambi))
-        self.assertIn(IRight, implementedBy(Ambi))
-        self.assertIn(ILeft, providedBy(ambi))
-        self.assertIn(IRight, providedBy(ambi))
-
-    def test_classImplements_multiple_w_explict_implements(self):
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import providedBy
-
-        class ILeft(Interface):
-
-            def method():
-                """docstring"""
-
-        class IRight(ILeft):
-            pass
-
-        class IOther(Interface):
-            pass
-
-        class Left():
-            __implemented__ = ILeft
-
-            def method(self):
-                raise NotImplementedError()
-
-        class Right:
-            __implemented__ = IRight
-
-        class Other:
-            __implemented__ = IOther
-
-        class Mixed(Left, Right):
-            __implemented__ = Left.__implemented__, Other.__implemented__
-
-        mixed = Mixed()
-
-        self.assertTrue(ILeft.implementedBy(Mixed))
-        self.assertFalse(IRight.implementedBy(Mixed))
-        self.assertTrue(IOther.implementedBy(Mixed))
-        self.assertIn(ILeft, implementedBy(Mixed))
-        self.assertNotIn(IRight, implementedBy(Mixed))
-        self.assertIn(IOther, implementedBy(Mixed))
-        self.assertIn(ILeft, providedBy(mixed))
-        self.assertNotIn(IRight, providedBy(mixed))
-        self.assertIn(IOther, providedBy(mixed))
-
-    def testInterfaceExtendsInterface(self):
-        from zope.interface import Interface
-
-        new = Interface.__class__
-        FunInterface = new('FunInterface')
-        BarInterface = new('BarInterface', (FunInterface,))
-        BobInterface = new('BobInterface')
-        BazInterface = new('BazInterface', (BobInterface, BarInterface,))
-
-        self.assertTrue(BazInterface.extends(BobInterface))
-        self.assertTrue(BazInterface.extends(BarInterface))
-        self.assertTrue(BazInterface.extends(FunInterface))
-        self.assertFalse(BobInterface.extends(FunInterface))
-        self.assertFalse(BobInterface.extends(BarInterface))
-        self.assertTrue(BarInterface.extends(FunInterface))
-        self.assertFalse(BarInterface.extends(BazInterface))
-
-    def test_verifyClass(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.verify import verifyClass
-
-        class ICheckMe(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "A method"
-
-        class CheckMe:
-            __implemented__ = ICheckMe
-            attr = 'value'
-
-            def method(self):
-                raise NotImplementedError()
-
-        self.assertTrue(verifyClass(ICheckMe, CheckMe))
-
-    def test_verifyObject(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.verify import verifyObject
-
-        class ICheckMe(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "A method"
-
-        class CheckMe:
-            __implemented__ = ICheckMe
-            attr = 'value'
-
-            def method(self):
-                raise NotImplementedError()
-
-        check_me = CheckMe()
-
-        self.assertTrue(verifyObject(ICheckMe, check_me))
-
-    def test_interface_object_provides_Interface(self):
-        from zope.interface import Interface
-
-        class AnInterface(Interface):
-            pass
-
-        self.assertTrue(Interface.providedBy(AnInterface))
-
-    def test_names_simple(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class ISimple(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                """docstring"""
-
-        self.assertEqual(sorted(ISimple.names()), ['attr', 'method'])
-
-    def test_names_derived(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class IBase(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                """docstring"""
-
-        class IDerived(IBase):
-            attr2 = Attribute('My attr2')
-
-            def method():
-                """docstring"""
-
-            def method2():
-                """docstring"""
-
-        self.assertEqual(sorted(IDerived.names()),
-                         ['attr2', 'method', 'method2'])
-        self.assertEqual(sorted(IDerived.names(all=True)),
-                         ['attr', 'attr2', 'method', 'method2'])
-
-    def test_namesAndDescriptions_simple(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.interface import Method
-
-        class ISimple(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        name_values = sorted(ISimple.namesAndDescriptions())
-
-        self.assertEqual(len(name_values), 2)
-        self.assertEqual(name_values[0][0], 'attr')
-        self.assertIsInstance(name_values[0][1], Attribute)
-        self.assertEqual(name_values[0][1].__name__, 'attr')
-        self.assertEqual(name_values[0][1].__doc__, 'My attr')
-        self.assertEqual(name_values[1][0], 'method')
-        self.assertIsInstance(name_values[1][1], Method)
-        self.assertEqual(name_values[1][1].__name__, 'method')
-        self.assertEqual(name_values[1][1].__doc__, 'My method')
-
-    def test_namesAndDescriptions_derived(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.interface import Method
-
-        class IBase(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        class IDerived(IBase):
-            attr2 = Attribute('My attr2')
-
-            def method():
-                "My method, overridden"
-
-            def method2():
-                "My method2"
-
-        name_values = sorted(IDerived.namesAndDescriptions())
-
-        self.assertEqual(len(name_values), 3)
-        self.assertEqual(name_values[0][0], 'attr2')
-        self.assertIsInstance(name_values[0][1], Attribute)
-        self.assertEqual(name_values[0][1].__name__, 'attr2')
-        self.assertEqual(name_values[0][1].__doc__, 'My attr2')
-        self.assertEqual(name_values[1][0], 'method')
-        self.assertIsInstance(name_values[1][1], Method)
-        self.assertEqual(name_values[1][1].__name__, 'method')
-        self.assertEqual(name_values[1][1].__doc__, 'My method, overridden')
-        self.assertEqual(name_values[2][0], 'method2')
-        self.assertIsInstance(name_values[2][1], Method)
-        self.assertEqual(name_values[2][1].__name__, 'method2')
-        self.assertEqual(name_values[2][1].__doc__, 'My method2')
-
-        name_values = sorted(IDerived.namesAndDescriptions(all=True))
-
-        self.assertEqual(len(name_values), 4)
-        self.assertEqual(name_values[0][0], 'attr')
-        self.assertIsInstance(name_values[0][1], Attribute)
-        self.assertEqual(name_values[0][1].__name__, 'attr')
-        self.assertEqual(name_values[0][1].__doc__, 'My attr')
-        self.assertEqual(name_values[1][0], 'attr2')
-        self.assertIsInstance(name_values[1][1], Attribute)
-        self.assertEqual(name_values[1][1].__name__, 'attr2')
-        self.assertEqual(name_values[1][1].__doc__, 'My attr2')
-        self.assertEqual(name_values[2][0], 'method')
-        self.assertIsInstance(name_values[2][1], Method)
-        self.assertEqual(name_values[2][1].__name__, 'method')
-        self.assertEqual(name_values[2][1].__doc__, 'My method, overridden')
-        self.assertEqual(name_values[3][0], 'method2')
-        self.assertIsInstance(name_values[3][1], Method)
-        self.assertEqual(name_values[3][1].__name__, 'method2')
-        self.assertEqual(name_values[3][1].__doc__, 'My method2')
-
-    def test_getDescriptionFor_nonesuch_no_default(self):
-        from zope.interface import Interface
-
-        class IEmpty(Interface):
-            pass
-
-        self.assertRaises(KeyError, IEmpty.getDescriptionFor, 'nonesuch')
-
-    def test_getDescriptionFor_simple(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.interface import Method
-
-        class ISimple(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        a_desc = ISimple.getDescriptionFor('attr')
-        self.assertIsInstance(a_desc, Attribute)
-        self.assertEqual(a_desc.__name__, 'attr')
-        self.assertEqual(a_desc.__doc__, 'My attr')
-
-        m_desc = ISimple.getDescriptionFor('method')
-        self.assertIsInstance(m_desc, Method)
-        self.assertEqual(m_desc.__name__, 'method')
-        self.assertEqual(m_desc.__doc__, 'My method')
-
-    def test_getDescriptionFor_derived(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.interface import Method
-
-        class IBase(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        class IDerived(IBase):
-            attr2 = Attribute('My attr2')
-
-            def method():
-                "My method, overridden"
-
-            def method2():
-                "My method2"
-
-        a_desc = IDerived.getDescriptionFor('attr')
-        self.assertIsInstance(a_desc, Attribute)
-        self.assertEqual(a_desc.__name__, 'attr')
-        self.assertEqual(a_desc.__doc__, 'My attr')
-
-        m_desc = IDerived.getDescriptionFor('method')
-        self.assertIsInstance(m_desc, Method)
-        self.assertEqual(m_desc.__name__, 'method')
-        self.assertEqual(m_desc.__doc__, 'My method, overridden')
-
-        a2_desc = IDerived.getDescriptionFor('attr2')
-        self.assertIsInstance(a2_desc, Attribute)
-        self.assertEqual(a2_desc.__name__, 'attr2')
-        self.assertEqual(a2_desc.__doc__, 'My attr2')
-
-        m2_desc = IDerived.getDescriptionFor('method2')
-        self.assertIsInstance(m2_desc, Method)
-        self.assertEqual(m2_desc.__name__, 'method2')
-        self.assertEqual(m2_desc.__doc__, 'My method2')
-
-    def test___getitem__nonesuch(self):
-        from zope.interface import Interface
-
-        class IEmpty(Interface):
-            pass
-
-        self.assertRaises(KeyError, IEmpty.__getitem__, 'nonesuch')
-
-    def test___getitem__simple(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.interface import Method
-
-        class ISimple(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        a_desc = ISimple['attr']
-        self.assertIsInstance(a_desc, Attribute)
-        self.assertEqual(a_desc.__name__, 'attr')
-        self.assertEqual(a_desc.__doc__, 'My attr')
-
-        m_desc = ISimple['method']
-        self.assertIsInstance(m_desc, Method)
-        self.assertEqual(m_desc.__name__, 'method')
-        self.assertEqual(m_desc.__doc__, 'My method')
-
-    def test___getitem___derived(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface.interface import Method
-
-        class IBase(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        class IDerived(IBase):
-            attr2 = Attribute('My attr2')
-
-            def method():
-                "My method, overridden"
-
-            def method2():
-                "My method2"
-
-        a_desc = IDerived['attr']
-        self.assertIsInstance(a_desc, Attribute)
-        self.assertEqual(a_desc.__name__, 'attr')
-        self.assertEqual(a_desc.__doc__, 'My attr')
-
-        m_desc = IDerived['method']
-        self.assertIsInstance(m_desc, Method)
-        self.assertEqual(m_desc.__name__, 'method')
-        self.assertEqual(m_desc.__doc__, 'My method, overridden')
-
-        a2_desc = IDerived['attr2']
-        self.assertIsInstance(a2_desc, Attribute)
-        self.assertEqual(a2_desc.__name__, 'attr2')
-        self.assertEqual(a2_desc.__doc__, 'My attr2')
-
-        m2_desc = IDerived['method2']
-        self.assertIsInstance(m2_desc, Method)
-        self.assertEqual(m2_desc.__name__, 'method2')
-        self.assertEqual(m2_desc.__doc__, 'My method2')
-
-    def test___contains__nonesuch(self):
-        from zope.interface import Interface
-
-        class IEmpty(Interface):
-            pass
-
-        self.assertNotIn('nonesuch', IEmpty)
-
-    def test___contains__simple(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class ISimple(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        self.assertIn('attr', ISimple)
-        self.assertIn('method', ISimple)
-
-    def test___contains__derived(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class IBase(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        class IDerived(IBase):
-            attr2 = Attribute('My attr2')
-
-            def method():
-                "My method, overridden"
-
-            def method2():
-                "My method2"
-
-        self.assertIn('attr', IDerived)
-        self.assertIn('method', IDerived)
-        self.assertIn('attr2', IDerived)
-        self.assertIn('method2', IDerived)
-
-    def test___iter__empty(self):
-        from zope.interface import Interface
-
-        class IEmpty(Interface):
-            pass
-
-        self.assertEqual(list(IEmpty), [])
-
-    def test___iter__simple(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class ISimple(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        self.assertEqual(sorted(list(ISimple)), ['attr', 'method'])
-
-    def test___iter__derived(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class IBase(Interface):
-            attr = Attribute('My attr')
-
-            def method():
-                "My method"
-
-        class IDerived(IBase):
-            attr2 = Attribute('My attr2')
-
-            def method():
-                "My method, overridden"
-
-            def method2():
-                "My method2"
-
-        self.assertEqual(sorted(list(IDerived)),
-                         ['attr', 'attr2', 'method', 'method2'])
-
-    def test_function_attributes_become_tagged_values(self):
-        from zope.interface import Interface
-
-        class ITagMe(Interface):
-            def method():
-                """docstring"""
-            method.optional = 1
-
-        method = ITagMe['method']
-        self.assertEqual(method.getTaggedValue('optional'), 1)
-
-    def test___doc___non_element(self):
-        from zope.interface import Interface
-
-        class IHaveADocString(Interface):
-            "xxx"
-
-        self.assertEqual(IHaveADocString.__doc__, "xxx")
-        self.assertEqual(list(IHaveADocString), [])
-
-    def test___doc___as_element(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class IHaveADocString(Interface):
-            "xxx"
-            __doc__ = Attribute('the doc')
-
-        self.assertEqual(IHaveADocString.__doc__, "")
-        self.assertEqual(list(IHaveADocString), ['__doc__'])
-
-    def _errorsEqual(self, has_invariant, error_len, error_msgs, iface):
-        from zope.interface.exceptions import Invalid
-        self.assertRaises(Invalid, iface.validateInvariants, has_invariant)
-        e = []
-        try:
-            iface.validateInvariants(has_invariant, e)
-            self.fail("validateInvariants should always raise")
-        except Invalid as error:
-            self.assertEqual(error.args[0], e)
-
-        self.assertEqual(len(e), error_len)
-        msgs = [error.args[0] for error in e]
-        msgs.sort()
-        for msg in msgs:
-            self.assertEqual(msg, error_msgs.pop(0))
-
-    def test_invariant_simple(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import directlyProvides
-        from zope.interface import invariant
-
-        class IInvariant(Interface):
-            foo = Attribute('foo')
-            bar = Attribute('bar; must eval to Boolean True if foo does')
-            invariant(_ifFooThenBar)
-
-        class HasInvariant:
-            pass
-
-        # set up
-        has_invariant = HasInvariant()
-        directlyProvides(has_invariant, IInvariant)
-
-        # the tests
-        self.assertEqual(IInvariant.getTaggedValue('invariants'),
-                         [_ifFooThenBar])
-        self.assertEqual(IInvariant.validateInvariants(has_invariant), None)
-        has_invariant.bar = 27
-        self.assertEqual(IInvariant.validateInvariants(has_invariant), None)
-        has_invariant.foo = 42
-        self.assertEqual(IInvariant.validateInvariants(has_invariant), None)
-        del has_invariant.bar
-        self._errorsEqual(has_invariant, 1, ['If Foo, then Bar!'],
-                          IInvariant)
-
-    def test_invariant_nested(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import directlyProvides
-        from zope.interface import invariant
-
-        class IInvariant(Interface):
-            foo = Attribute('foo')
-            bar = Attribute('bar; must eval to Boolean True if foo does')
-            invariant(_ifFooThenBar)
-
-        class ISubInvariant(IInvariant):
-            invariant(_barGreaterThanFoo)
-
-        class HasInvariant:
-            pass
-
-        # nested interfaces with invariants:
-        self.assertEqual(ISubInvariant.getTaggedValue('invariants'),
-                         [_barGreaterThanFoo])
-        has_invariant = HasInvariant()
-        directlyProvides(has_invariant, ISubInvariant)
-        has_invariant.foo = 42
-        # even though the interface has changed, we should still only have one
-        # error.
-        self._errorsEqual(has_invariant, 1, ['If Foo, then Bar!'],
-                          ISubInvariant)
-        # however, if we set foo to 0 (Boolean False) and bar to a negative
-        # number then we'll get the new error
-        has_invariant.foo = 2
-        has_invariant.bar = 1
-        self._errorsEqual(has_invariant, 1,
-                          ['Please, Boo MUST be greater than Foo!'],
-                          ISubInvariant)
-        # and if we set foo to a positive number and boo to 0, we'll
-        # get both errors!
-        has_invariant.foo = 1
-        has_invariant.bar = 0
-        self._errorsEqual(has_invariant, 2,
-                          ['If Foo, then Bar!',
-                           'Please, Boo MUST be greater than Foo!'],
-                          ISubInvariant)
-        # for a happy ending, we'll make the invariants happy
-        has_invariant.foo = 1
-        has_invariant.bar = 2
-        self.assertEqual(IInvariant.validateInvariants(has_invariant), None)
-
-    def test_invariant_mutandis(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import directlyProvides
-        from zope.interface import invariant
-
-        class IInvariant(Interface):
-            foo = Attribute('foo')
-            bar = Attribute('bar; must eval to Boolean True if foo does')
-            invariant(_ifFooThenBar)
-
-        class HasInvariant:
-            pass
-
-        # now we'll do two invariants on the same interface,
-        # just to make sure that a small
-        # multi-invariant interface is at least minimally tested.
-        has_invariant = HasInvariant()
-        directlyProvides(has_invariant, IInvariant)
-        has_invariant.foo = 42
-
-        # if you really need to mutate, then this would be the way to do it.
-        # Probably a bad idea, though. :-)
-        old_invariants = IInvariant.getTaggedValue('invariants')
-        invariants = old_invariants[:]
-        invariants.append(_barGreaterThanFoo)
-        IInvariant.setTaggedValue('invariants', invariants)
-
-        # even though the interface has changed, we should still only have one
-        # error.
-        self._errorsEqual(has_invariant, 1, ['If Foo, then Bar!'],
-                          IInvariant)
-        # however, if we set foo to 0 (Boolean False) and bar to a negative
-        # number then we'll get the new error
-        has_invariant.foo = 2
-        has_invariant.bar = 1
-        self._errorsEqual(
-            has_invariant,
-            1,
-            ['Please, Boo MUST be greater than Foo!'],
-            IInvariant
-        )
-        # and if we set foo to a positive number and boo to 0, we'll
-        # get both errors!
-        has_invariant.foo = 1
-        has_invariant.bar = 0
-        self._errorsEqual(has_invariant, 2,
-                          ['If Foo, then Bar!',
-                           'Please, Boo MUST be greater than Foo!'],
-                          IInvariant)
-        # for another happy ending, we'll make the invariants happy again
-        has_invariant.foo = 1
-        has_invariant.bar = 2
-        self.assertEqual(IInvariant.validateInvariants(has_invariant), None)
-        # clean up
-        IInvariant.setTaggedValue('invariants', old_invariants)
-
-    def test___doc___element(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class IDocstring(Interface):
-            "xxx"
-
-        self.assertEqual(IDocstring.__doc__, "xxx")
-        self.assertEqual(list(IDocstring), [])
-
-        class IDocstringAndAttribute(Interface):
-            "xxx"
-
-            __doc__ = Attribute('the doc')
-
-        self.assertEqual(IDocstringAndAttribute.__doc__, "")
-        self.assertEqual(list(IDocstringAndAttribute), ['__doc__'])
-
-    def test_invariant_as_decorator(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface import invariant
-        from zope.interface.exceptions import Invalid
-
-        class IRange(Interface):
-            min = Attribute("Lower bound")
-            max = Attribute("Upper bound")
-
-            @invariant
-            def range_invariant(ob):
-                if ob.max < ob.min:
-                    raise Invalid('max < min')
-
-        @implementer(IRange)
-        class Range:
-
-            def __init__(self, min, max):
-                self.min, self.max = min, max
-
-        IRange.validateInvariants(Range(1, 2))
-        IRange.validateInvariants(Range(1, 1))
-        try:
-            IRange.validateInvariants(Range(2, 1))
-        except Invalid as e:
-            self.assertEqual(str(e), 'max < min')
-
-    def test_taggedValue(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import taggedValue
-
-        class ITagged(Interface):
-            foo = Attribute('foo')
-            bar = Attribute('bar; must eval to Boolean True if foo does')
-            taggedValue('qux', 'Spam')
-
-        class IDerived(ITagged):
-            taggedValue('qux', 'Spam Spam')
-            taggedValue('foo', 'bar')
-
-        class IDerived2(IDerived):
-            pass
-
-        self.assertEqual(ITagged.getTaggedValue('qux'), 'Spam')
-        self.assertRaises(KeyError, ITagged.getTaggedValue, 'foo')
-        self.assertEqual(list(ITagged.getTaggedValueTags()), ['qux'])
-
-        self.assertEqual(IDerived2.getTaggedValue('qux'), 'Spam Spam')
-        self.assertEqual(IDerived2.getTaggedValue('foo'), 'bar')
-        self.assertEqual(set(IDerived2.getTaggedValueTags()), {'qux', 'foo'})
-
-    def _make_taggedValue_tree(self, base):
-        from zope.interface import Attribute
-        from zope.interface import taggedValue
-
-        class F(base):
-            taggedValue('tag', 'F')
-            tag = Attribute('F')
-
-        class E(base):
-            taggedValue('tag', 'E')
-            tag = Attribute('E')
-
-        class D(base):
-            taggedValue('tag', 'D')
-            tag = Attribute('D')
-
-        class C(D, F):
-            taggedValue('tag', 'C')
-            tag = Attribute('C')
-
-        class B(D, E):
-            pass
-
-        class A(B, C):
-            pass
-
-        return A
-
-    def test_getTaggedValue_follows__iro__(self):
-        # And not just looks at __bases__.
-        # https://github.com/zopefoundation/zope.interface/issues/190
-        from zope.interface import Interface
-
-        # First, confirm that looking at a true class
-        # hierarchy follows the __mro__.
-        class_A = self._make_taggedValue_tree(object)
-        self.assertEqual(class_A.tag.__name__, 'C')
-
-        # Now check that Interface does, both for attributes...
-        iface_A = self._make_taggedValue_tree(Interface)
-        self.assertEqual(iface_A['tag'].__name__, 'C')
-        # ... and for tagged values.
-        self.assertEqual(iface_A.getTaggedValue('tag'), 'C')
-        self.assertEqual(iface_A.queryTaggedValue('tag'), 'C')
-        # Of course setting something lower overrides it.
-        assert iface_A.__bases__[0].__name__ == 'B'
-        iface_A.__bases__[0].setTaggedValue('tag', 'B')
-        self.assertEqual(iface_A.getTaggedValue('tag'), 'B')
-
-    def test_getDirectTaggedValue_ignores__iro__(self):
-        # https://github.com/zopefoundation/zope.interface/issues/190
-        from zope.interface import Interface
-
-        A = self._make_taggedValue_tree(Interface)
-        self.assertIsNone(A.queryDirectTaggedValue('tag'))
-        self.assertEqual([], list(A.getDirectTaggedValueTags()))
-
-        with self.assertRaises(KeyError):
-            A.getDirectTaggedValue('tag')
-
-        A.setTaggedValue('tag', 'A')
-        self.assertEqual(A.queryDirectTaggedValue('tag'), 'A')
-        self.assertEqual(A.getDirectTaggedValue('tag'), 'A')
-        self.assertEqual(['tag'], list(A.getDirectTaggedValueTags()))
-
-        assert A.__bases__[1].__name__ == 'C'
-        C = A.__bases__[1]
-        self.assertEqual(C.queryDirectTaggedValue('tag'), 'C')
-        self.assertEqual(C.getDirectTaggedValue('tag'), 'C')
-        self.assertEqual(['tag'], list(C.getDirectTaggedValueTags()))
-
-    def test_description_cache_management(self):
-        # See https://bugs.launchpad.net/zope.interface/+bug/185974
-        # There was a bug where the cache used by Specification.get() was not
-        # cleared when the bases were changed.
-        from zope.interface import Attribute
-        from zope.interface import Interface
-
-        class I1(Interface):
-            a = Attribute('a')
-
-        class I2(I1):
-            pass
-
-        class I3(I2):
-            pass
-
-        self.assertIs(I3.get('a'), I1.get('a'))
-
-        I2.__bases__ = (Interface,)
-        self.assertIsNone(I3.get('a'))
-
-    def test___call___defers_to___conform___(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class IFoo(Interface):
-            pass
-
-        @implementer(IFoo)
-        class C:
-            def __conform__(self, proto):
-                return 0
-
-        self.assertEqual(IFoo(C()), 0)
-
-    def test___call___object_implements(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class IFoo(Interface):
-            pass
-
-        @implementer(IFoo)
-        class C:
-            pass
-
-        c = C()
-        self.assertIs(IFoo(c), c)
-
-    def test___call___miss_wo_alternate(self):
-        from zope.interface import Interface
-
-        class IFoo(Interface):
-            pass
-
-        class C:
-            pass
-
-        c = C()
-        self.assertRaises(TypeError, IFoo, c)
-
-    def test___call___miss_w_alternate(self):
-        from zope.interface import Interface
-
-        class IFoo(Interface):
-            pass
-
-        class C:
-            pass
-
-        c = C()
-        self.assertIs(IFoo(c, self), self)
-
-    def test___call___w_adapter_hook(self):
-        from zope.interface import Interface
-        from zope.interface.interface import adapter_hooks
-
-        def _miss(iface, obj):
-            pass
-
-        def _hit(iface, obj):
-            return self
-
-        class IFoo(Interface):
-            pass
-
-        class C:
-            pass
-
-        c = C()
-
-        old_adapter_hooks = adapter_hooks[:]
-        adapter_hooks[:] = [_miss, _hit]
-        try:
-            self.assertIs(IFoo(c), self)
-        finally:
-            adapter_hooks[:] = old_adapter_hooks
-
-    def test___call___w_overridden_adapt(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface import interfacemethod
-
-        class IFoo(Interface):
-
-            @interfacemethod
-            def __adapt__(self, obj):
-                return 42
-
-        @implementer(IFoo)
-        class Obj:
-            pass
-
-        self.assertEqual(42, IFoo(object()))
-        # __adapt__ can ignore the fact that the object provides
-        # the interface if it chooses.
-        self.assertEqual(42, IFoo(Obj()))
-
-    def test___call___w_overridden_adapt_and_conform(self):
-        # Conform is first, taking precedence over __adapt__,
-        # *if* it returns non-None
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface import interfacemethod
-
-        class IAdapt(Interface):
-            @interfacemethod
-            def __adapt__(self, obj):
-                return 42
-
-        class ISimple(Interface):
-            """Nothing special."""
-
-        @implementer(IAdapt)
-        class Conform24:
-            def __conform__(self, iface):
-                return 24
-
-        @implementer(IAdapt)
-        class ConformNone:
-            def __conform__(self, iface):
-                return None
-
-        self.assertEqual(42, IAdapt(object()))
-
-        self.assertEqual(24, ISimple(Conform24()))
-        self.assertEqual(24, IAdapt(Conform24()))
-
-        with self.assertRaises(TypeError):
-            ISimple(ConformNone())
-
-        self.assertEqual(42, IAdapt(ConformNone()))
-
-    def test___call___w_overridden_adapt_call_super(self):
-        import sys
-
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface import interfacemethod
-
-        class IFoo(Interface):
-
-            @interfacemethod
-            def __adapt__(self, obj):
-                if not self.providedBy(obj):
-                    return 42
-                return super().__adapt__(obj)
-
-        @implementer(IFoo)
-        class Obj:
-            pass
-
-        self.assertEqual(42, IFoo(object()))
-        obj = Obj()
-        self.assertIs(obj, IFoo(obj))
-
-    def test___adapt___as_method_and_implementation(self):
-        from zope.interface import Interface
-        from zope.interface import interfacemethod
-
-        class IFoo(Interface):
-            @interfacemethod
-            def __adapt__(self, obj):
-                return 42
-
-            def __adapt__(to_adapt):  # noqa F811
-                "This is a protocol"
-
-        self.assertEqual(42, IFoo(object()))
-        self.assertEqual(IFoo['__adapt__'].getSignatureString(), '(to_adapt)')
-
-    def test___adapt__inheritance_and_type(self):
-        from zope.interface import Interface
-        from zope.interface import interfacemethod
-
-        class IRoot(Interface):
-            """Root"""
-
-        class IWithAdapt(IRoot):
-            @interfacemethod
-            def __adapt__(self, obj):
-                return 42
-
-        class IOther(IRoot):
-            """Second branch"""
-
-        class IUnrelated(Interface):
-            """Unrelated"""
-
-        class IDerivedAdapt(IUnrelated, IWithAdapt, IOther):
-            """Inherits an adapt"""
-            # Order of "inheritance" matters here.
-
-        class IDerived2Adapt(IDerivedAdapt):
-            """Overrides an inherited custom adapt."""
-            @interfacemethod
-            def __adapt__(self, obj):
-                return 24
-
-        self.assertEqual(42, IDerivedAdapt(object()))
-        for iface in IRoot, IWithAdapt, IOther, IUnrelated, IDerivedAdapt:
-            self.assertEqual(__name__, iface.__module__)
-
-        for iface in IRoot, IOther, IUnrelated:
-            self.assertEqual(type(IRoot), type(Interface))
-
-        # But things that implemented __adapt__ got a new type
-        self.assertNotEqual(type(Interface), type(IWithAdapt))
-        self.assertEqual(type(IWithAdapt), type(IDerivedAdapt))
-        self.assertIsInstance(IWithAdapt, type(Interface))
-
-        self.assertEqual(24, IDerived2Adapt(object()))
-        self.assertNotEqual(type(IDerived2Adapt), type(IDerivedAdapt))
-        self.assertIsInstance(IDerived2Adapt, type(IDerivedAdapt))
-
-    def test_interfacemethod_is_general(self):
-        from zope.interface import Interface
-        from zope.interface import interfacemethod
-
-        class IFoo(Interface):
-
-            @interfacemethod
-            def __call__(self, obj):
-                """Replace an existing method"""
-                return 42
-
-            @interfacemethod
-            def this_is_new(self):
-                return 42
-
-        self.assertEqual(IFoo(self), 42)
-        self.assertEqual(IFoo.this_is_new(), 42)
-
-
-class AttributeTests(ElementTests):
-
-    DEFAULT_NAME = 'TestAttribute'
-
-    def _getTargetClass(self):
-        from zope.interface.interface import Attribute
-        return Attribute
-
-    def test__repr__w_interface(self):
-        method = self._makeOne()
-        method.interface = type(self)
-        r = repr(method)
-        self.assertTrue(
-            r.startswith(''), r
-        )
-
-    def test__repr__wo_interface(self):
-        method = self._makeOne()
-        r = repr(method)
-        self.assertTrue(
-            r.startswith(''), r)
-
-    def test__str__w_interface(self):
-        method = self._makeOne()
-        method.interface = type(self)
-        r = str(method)
-        self.assertEqual(r, __name__ + '.AttributeTests.TestAttribute')
-
-    def test__str__wo_interface(self):
-        method = self._makeOne()
-        r = str(method)
-        self.assertEqual(r, 'TestAttribute')
-
-
-class MethodTests(AttributeTests):
-
-    DEFAULT_NAME = 'TestMethod'
-
-    def _getTargetClass(self):
-        from zope.interface.interface import Method
-        return Method
-
-    def test_optional_as_property(self):
-        method = self._makeOne()
-        self.assertEqual(method.optional, {})
-        method.optional = {'foo': 'bar'}
-        self.assertEqual(method.optional, {'foo': 'bar'})
-        del method.optional
-        self.assertEqual(method.optional, {})
-
-    def test___call___raises_BrokenImplementation(self):
-        from zope.interface.exceptions import BrokenImplementation
-        method = self._makeOne()
-        try:
-            method()
-        except BrokenImplementation as e:
-            self.assertEqual(e.interface, None)
-            self.assertEqual(e.name, self.DEFAULT_NAME)
-        else:
-            self.fail('__call__ should raise BrokenImplementation')
-
-    def test_getSignatureInfo_bare(self):
-        method = self._makeOne()
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), [])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], None)
-
-    def test_getSignatureString_bare(self):
-        method = self._makeOne()
-        self.assertEqual(method.getSignatureString(), '()')
-
-    def test_getSignatureString_w_only_required(self):
-        method = self._makeOne()
-        method.positional = method.required = ['foo']
-        self.assertEqual(method.getSignatureString(), '(foo)')
-
-    def test_getSignatureString_w_optional(self):
-        method = self._makeOne()
-        method.positional = method.required = ['foo']
-        method.optional = {'foo': 'bar'}
-        self.assertEqual(method.getSignatureString(), "(foo='bar')")
-
-    def test_getSignatureString_w_varargs(self):
-        method = self._makeOne()
-        method.varargs = 'args'
-        self.assertEqual(method.getSignatureString(), "(*args)")
-
-    def test_getSignatureString_w_kwargs(self):
-        method = self._makeOne()
-        method.kwargs = 'kw'
-        self.assertEqual(method.getSignatureString(), "(**kw)")
-
-    def test__repr__w_interface(self):
-        method = self._makeOne()
-        method.kwargs = 'kw'
-        method.interface = type(self)
-        r = repr(method)
-        self.assertTrue(
-            r.startswith(''), r
-        )
-
-    def test__repr__wo_interface(self):
-        method = self._makeOne()
-        method.kwargs = 'kw'
-        r = repr(method)
-        self.assertTrue(
-            r.startswith(''), r)
-
-    def test__str__w_interface(self):
-        method = self._makeOne()
-        method.kwargs = 'kw'
-        method.interface = type(self)
-        r = str(method)
-        self.assertEqual(r, __name__ + '.MethodTests.TestMethod(**kw)')
-
-    def test__str__wo_interface(self):
-        method = self._makeOne()
-        method.kwargs = 'kw'
-        r = str(method)
-        self.assertEqual(r, 'TestMethod(**kw)')
-
-
-class Test_fromFunction(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.interface import fromFunction
-        return fromFunction(*args, **kw)
-
-    def test_bare(self):
-
-        def _func():
-            "DOCSTRING"
-
-        method = self._callFUT(_func)
-        self.assertEqual(method.getName(), '_func')
-        self.assertEqual(method.getDoc(), 'DOCSTRING')
-        self.assertEqual(method.interface, None)
-        self.assertEqual(list(method.getTaggedValueTags()), [])
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), [])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], None)
-
-    def test_w_interface(self):
-        from zope.interface.interface import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        def _func():
-            "DOCSTRING"
-
-        method = self._callFUT(_func, interface=IFoo)
-        self.assertEqual(method.interface, IFoo)
-
-    def test_w_name(self):
-
-        def _func():
-            "DOCSTRING"
-
-        method = self._callFUT(_func, name='anotherName')
-        self.assertEqual(method.getName(), 'anotherName')
-
-    def test_w_only_required(self):
-
-        def _func(foo):
-            "DOCSTRING"
-
-        method = self._callFUT(_func)
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), ['foo'])
-        self.assertEqual(list(info['required']), ['foo'])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], None)
-
-    def test_w_optional(self):
-
-        def _func(foo='bar'):
-            "DOCSTRING"
-
-        method = self._callFUT(_func)
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), ['foo'])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {'foo': 'bar'})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], None)
-
-    def test_w_optional_self(self):
-        # This is a weird case, trying to cover the following code in
-        # FUT::
-        #
-        # nr = na-len(defaults)
-        # if nr < 0:
-        #     defaults=defaults[-nr:]
-        #     nr = 0
-
-        def _func(self='bar'):
-            "DOCSTRING"
-
-        method = self._callFUT(_func, imlevel=1)
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), [])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], None)
-
-    def test_w_varargs(self):
-
-        def _func(*args):
-            "DOCSTRING"
-
-        method = self._callFUT(_func)
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), [])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], 'args')
-        self.assertEqual(info['kwargs'], None)
-
-    def test_w_kwargs(self):
-
-        def _func(**kw):
-            "DOCSTRING"
-
-        method = self._callFUT(_func)
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), [])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], 'kw')
-
-    def test_full_spectrum(self):
-
-        def _func(
-            foo, bar='baz', *args, **kw
-        ):  # pylint:disable=keyword-arg-before-vararg
-            "DOCSTRING"
-
-        method = self._callFUT(_func)
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), ['foo', 'bar'])
-        self.assertEqual(list(info['required']), ['foo'])
-        self.assertEqual(info['optional'], {'bar': 'baz'})
-        self.assertEqual(info['varargs'], 'args')
-        self.assertEqual(info['kwargs'], 'kw')
-
-
-class Test_fromMethod(unittest.TestCase):
-
-    def _callFUT(self, *args, **kw):
-        from zope.interface.interface import fromMethod
-        return fromMethod(*args, **kw)
-
-    def test_no_args(self):
-
-        class Foo:
-            def bar(self):
-                "DOCSTRING"
-
-        method = self._callFUT(Foo.bar)
-        self.assertEqual(method.getName(), 'bar')
-        self.assertEqual(method.getDoc(), 'DOCSTRING')
-        self.assertEqual(method.interface, None)
-        self.assertEqual(list(method.getTaggedValueTags()), [])
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), [])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], None)
-
-    def test_full_spectrum(self):
-
-        class Foo:
-            def bar(
-                self, foo, bar='baz', *args, **kw
-            ):  # pylint:disable=keyword-arg-before-vararg
-                "DOCSTRING"
-
-        method = self._callFUT(Foo.bar)
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), ['foo', 'bar'])
-        self.assertEqual(list(info['required']), ['foo'])
-        self.assertEqual(info['optional'], {'bar': 'baz'})
-        self.assertEqual(info['varargs'], 'args')
-        self.assertEqual(info['kwargs'], 'kw')
-
-    def test_w_non_method(self):
-
-        def foo():
-            "DOCSTRING"
-
-        method = self._callFUT(foo)
-        self.assertEqual(method.getName(), 'foo')
-        self.assertEqual(method.getDoc(), 'DOCSTRING')
-        self.assertEqual(method.interface, None)
-        self.assertEqual(list(method.getTaggedValueTags()), [])
-        info = method.getSignatureInfo()
-        self.assertEqual(list(info['positional']), [])
-        self.assertEqual(list(info['required']), [])
-        self.assertEqual(info['optional'], {})
-        self.assertEqual(info['varargs'], None)
-        self.assertEqual(info['kwargs'], None)
-
-
-class DummyDependent:
-
-    def __init__(self):
-        self._changed = []
-
-    def changed(self, originally_changed):
-        self._changed.append(originally_changed)
-
-
-def _barGreaterThanFoo(obj):
-    from zope.interface.exceptions import Invalid
-    foo = getattr(obj, 'foo', None)
-    bar = getattr(obj, 'bar', None)
-    if foo is not None and isinstance(foo, type(bar)):
-        # type checking should be handled elsewhere (like, say,
-        # schema); these invariants should be intra-interface
-        # constraints.  This is a hacky way to do it, maybe, but you
-        # get the idea
-        if not bar > foo:
-            raise Invalid('Please, Boo MUST be greater than Foo!')
-
-
-def _ifFooThenBar(obj):
-    from zope.interface.exceptions import Invalid
-    if getattr(obj, 'foo', None) and not getattr(obj, 'bar', None):
-        raise Invalid('If Foo, then Bar!')
-
-
-class _Monkey:
-    # context-manager for replacing module names in the scope of a test.
-    def __init__(self, module, **kw):
-        self.module = module
-        self.to_restore = {key: getattr(module, key) for key in kw}
-        for key, value in kw.items():
-            setattr(module, key, value)
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        for key, value in self.to_restore.items():
-            setattr(self.module, key, value)
-
-
-class TestTypeAnnotations(unittest.TestCase):
-    """Test using Interfaces in type annotations."""
-
-    def test___or__(self):
-        from typing import Optional
-        from typing import Union
-
-        from zope.interface import Interface
-
-        class I1(Interface):
-            pass
-
-        class I2(Interface):
-            pass
-
-        class B:
-            a: I1 | None
-            b: I1 | I2
-
-        self.assertEqual(
-            B.__annotations__, {'a': Optional[I1], 'b': Union[I1, I2]})
-
-    def test___ror__(self):
-        from typing import Optional
-        from typing import Union
-
-        from zope.interface import Interface
-
-        class I1(Interface):
-            pass
-
-        class A:
-            pass
-
-        class B:
-            a: None | I1
-            b: A | I1
-
-        self.assertEqual(
-            B.__annotations__, {'a': Optional[I1], 'b': Union[A, I1]})
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_interfaces.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_interfaces.py
deleted file mode 100644
index a100649..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_interfaces.py
+++ /dev/null
@@ -1,130 +0,0 @@
-import unittest
-
-
-class _ConformsToIObjectEvent:
-
-    def _makeOne(self, target=None):
-        if target is None:
-            target = object()
-        return self._getTargetClass()(target)
-
-    def test_class_conforms_to_IObjectEvent(self):
-        from zope.interface.interfaces import IObjectEvent
-        from zope.interface.verify import verifyClass
-        verifyClass(IObjectEvent, self._getTargetClass())
-
-    def test_instance_conforms_to_IObjectEvent(self):
-        from zope.interface.interfaces import IObjectEvent
-        from zope.interface.verify import verifyObject
-        verifyObject(IObjectEvent, self._makeOne())
-
-
-class _ConformsToIRegistrationEvent(_ConformsToIObjectEvent):
-
-    def test_class_conforms_to_IRegistrationEvent(self):
-        from zope.interface.interfaces import IRegistrationEvent
-        from zope.interface.verify import verifyClass
-        verifyClass(IRegistrationEvent, self._getTargetClass())
-
-    def test_instance_conforms_to_IRegistrationEvent(self):
-        from zope.interface.interfaces import IRegistrationEvent
-        from zope.interface.verify import verifyObject
-        verifyObject(IRegistrationEvent, self._makeOne())
-
-
-class ObjectEventTests(unittest.TestCase, _ConformsToIObjectEvent):
-
-    def _getTargetClass(self):
-        from zope.interface.interfaces import ObjectEvent
-        return ObjectEvent
-
-    def test_ctor(self):
-        target = object()
-        event = self._makeOne(target)
-        self.assertIs(event.object, target)
-
-
-class RegistrationEventTests(unittest.TestCase,
-                             _ConformsToIRegistrationEvent):
-
-    def _getTargetClass(self):
-        from zope.interface.interfaces import RegistrationEvent
-        return RegistrationEvent
-
-    def test___repr__(self):
-        target = object()
-        event = self._makeOne(target)
-        r = repr(event)
-        self.assertEqual(r.splitlines(),
-                         ['RegistrationEvent event:', repr(target)])
-
-
-class RegisteredTests(unittest.TestCase,
-                      _ConformsToIRegistrationEvent):
-
-    def _getTargetClass(self):
-        from zope.interface.interfaces import Registered
-        return Registered
-
-    def test_class_conforms_to_IRegistered(self):
-        from zope.interface.interfaces import IRegistered
-        from zope.interface.verify import verifyClass
-        verifyClass(IRegistered, self._getTargetClass())
-
-    def test_instance_conforms_to_IRegistered(self):
-        from zope.interface.interfaces import IRegistered
-        from zope.interface.verify import verifyObject
-        verifyObject(IRegistered, self._makeOne())
-
-
-class UnregisteredTests(unittest.TestCase,
-                        _ConformsToIRegistrationEvent):
-
-    def _getTargetClass(self):
-        from zope.interface.interfaces import Unregistered
-        return Unregistered
-
-    def test_class_conforms_to_IUnregistered(self):
-        from zope.interface.interfaces import IUnregistered
-        from zope.interface.verify import verifyClass
-        verifyClass(IUnregistered, self._getTargetClass())
-
-    def test_instance_conforms_to_IUnregistered(self):
-        from zope.interface.interfaces import IUnregistered
-        from zope.interface.verify import verifyObject
-        verifyObject(IUnregistered, self._makeOne())
-
-
-class InterfaceClassTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.interface import InterfaceClass
-        return InterfaceClass
-
-    def _getTargetInterface(self):
-        from zope.interface.interfaces import IInterface
-        return IInterface
-
-    def _makeOne(self):
-        from zope.interface.interface import Interface
-        return Interface
-
-    def test_class_conforms(self):
-        from zope.interface.verify import verifyClass
-        verifyClass(self._getTargetInterface(), self._getTargetClass())
-
-    def test_instance_conforms(self):
-        from zope.interface.verify import verifyObject
-        verifyObject(self._getTargetInterface(), self._makeOne())
-
-    def test_instance_consistent__iro__(self):
-        from zope.interface import ro
-        self.assertTrue(ro.is_consistent(self._getTargetInterface()))
-
-    def test_class_consistent__iro__(self):
-        from zope.interface import implementedBy
-        from zope.interface import ro
-
-        self.assertTrue(
-            ro.is_consistent(implementedBy(self._getTargetClass()))
-        )
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_odd_declarations.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_odd_declarations.py
deleted file mode 100644
index 09a8de8..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_odd_declarations.py
+++ /dev/null
@@ -1,301 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2003 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Test interface declarations against ExtensionClass-like classes.
-
-These tests are to make sure we do something sane in the presence of
-classic ExtensionClass classes and instances.
-"""
-import unittest
-
-from zope.interface import Interface
-from zope.interface import classImplements
-from zope.interface import classImplementsOnly
-from zope.interface import directlyProvidedBy
-from zope.interface import directlyProvides
-from zope.interface import implementedBy
-from zope.interface import implementer
-from zope.interface import providedBy
-from zope.interface.tests import odd
-
-
-class I1(Interface):
-    pass
-
-
-class I2(Interface):
-    pass
-
-
-class I3(Interface):
-    pass
-
-
-class I31(I3):
-    pass
-
-
-class I4(Interface):
-    pass
-
-
-class I5(Interface):
-    pass
-
-
-class Odd:
-    pass
-
-
-Odd = odd.MetaClass('Odd', Odd.__bases__, {})
-
-
-class B(Odd):
-    __implemented__ = I2
-
-
-# TODO: We are going to need more magic to make classProvides work with odd
-#       classes. This will work in the next iteration. For now, we'll use
-#       a different mechanism.
-
-# from zope.interface import classProvides
-class A(Odd):
-    pass
-
-
-classImplements(A, I1)
-
-
-class C(A, B):
-    pass
-
-
-classImplements(C, I31)
-
-
-class Test(unittest.TestCase):
-
-    def test_ObjectSpecification(self):
-        c = C()
-        directlyProvides(c, I4)
-        self.assertEqual([i.getName() for i in providedBy(c)],
-                         ['I4', 'I31', 'I1', 'I2']
-                         )
-        self.assertEqual([i.getName() for i in providedBy(c).flattened()],
-                         ['I4', 'I31', 'I3', 'I1', 'I2', 'Interface']
-                         )
-        self.assertIn(I1, providedBy(c))
-        self.assertNotIn(I3, providedBy(c))
-        self.assertTrue(providedBy(c).extends(I3))
-        self.assertTrue(providedBy(c).extends(I31))
-        self.assertFalse(providedBy(c).extends(I5))
-
-        class COnly(A, B):
-            pass
-        classImplementsOnly(COnly, I31)
-
-        class D(COnly):
-            pass
-        classImplements(D, I5)
-
-        classImplements(D, I5)
-
-        c = D()
-        directlyProvides(c, I4)
-        self.assertEqual([i.getName() for i in providedBy(c)],
-                         ['I4', 'I5', 'I31'])
-        self.assertEqual([i.getName() for i in providedBy(c).flattened()],
-                         ['I4', 'I5', 'I31', 'I3', 'Interface'])
-        self.assertNotIn(I1, providedBy(c))
-        self.assertNotIn(I3, providedBy(c))
-        self.assertTrue(providedBy(c).extends(I3))
-        self.assertFalse(providedBy(c).extends(I1))
-        self.assertTrue(providedBy(c).extends(I31))
-        self.assertTrue(providedBy(c).extends(I5))
-
-        class COnly(A, B):
-            __implemented__ = I31
-
-        class D(COnly):
-            pass
-
-        classImplements(D, I5)
-        classImplements(D, I5)
-
-        c = D()
-        directlyProvides(c, I4)
-        self.assertEqual([i.getName() for i in providedBy(c)],
-                         ['I4', 'I5', 'I31'])
-        self.assertEqual([i.getName() for i in providedBy(c).flattened()],
-                         ['I4', 'I5', 'I31', 'I3', 'Interface'])
-        self.assertNotIn(I1, providedBy(c))
-        self.assertNotIn(I3, providedBy(c))
-        self.assertTrue(providedBy(c).extends(I3))
-        self.assertFalse(providedBy(c).extends(I1))
-        self.assertTrue(providedBy(c).extends(I31))
-        self.assertTrue(providedBy(c).extends(I5))
-
-    def test_classImplements(self):
-
-        @implementer(I3)
-        class A(Odd):
-            pass
-
-        @implementer(I4)
-        class B(Odd):
-            pass
-
-        class C(A, B):
-            pass
-
-        classImplements(C, I1, I2)
-        self.assertEqual([i.getName() for i in implementedBy(C)],
-                         ['I1', 'I2', 'I3', 'I4'])
-
-        classImplements(C, I5)
-        self.assertEqual([i.getName() for i in implementedBy(C)],
-                         ['I1', 'I2', 'I5', 'I3', 'I4'])
-
-    def test_classImplementsOnly(self):
-
-        @implementer(I3)
-        class A(Odd):
-            pass
-
-        @implementer(I4)
-        class B(Odd):
-            pass
-
-        class C(A, B):
-            pass
-
-        classImplementsOnly(C, I1, I2)
-        self.assertEqual([i.__name__ for i in implementedBy(C)],
-                         ['I1', 'I2'])
-
-    def test_directlyProvides(self):
-
-        class IA1(Interface):
-            pass
-
-        class IA2(Interface):
-            pass
-
-        class IB(Interface):
-            pass
-
-        class IC(Interface):
-            pass
-
-        class A(Odd):
-            pass
-        classImplements(A, IA1, IA2)
-
-        class B(Odd):
-            pass
-        classImplements(B, IB)
-
-        class C(A, B):
-            pass
-        classImplements(C, IC)
-
-        ob = C()
-        directlyProvides(ob, I1, I2)
-        self.assertIn(I1, providedBy(ob))
-        self.assertIn(I2, providedBy(ob))
-        self.assertIn(IA1, providedBy(ob))
-        self.assertIn(IA2, providedBy(ob))
-        self.assertIn(IB, providedBy(ob))
-        self.assertIn(IC, providedBy(ob))
-
-        directlyProvides(ob, directlyProvidedBy(ob) - I2)
-        self.assertIn(I1, providedBy(ob))
-        self.assertNotIn(I2, providedBy(ob))
-        self.assertNotIn(I2, providedBy(ob))
-        directlyProvides(ob, directlyProvidedBy(ob), I2)
-        self.assertIn(I2, providedBy(ob))
-
-    # see above
-    # def TODO_test_classProvides_fails_for_odd_class(self):
-    #     try:
-    #         class A(Odd):
-    #             classProvides(I1)
-    #     except TypeError:
-    #         pass # Success
-    #     self.assert_(
-    #         False,
-    #         "Shouldn't be able to use directlyProvides on odd class."
-    #     )
-
-    def test_implementedBy(self):
-
-        class I2(I1):
-            pass
-
-        class C1(Odd):
-            pass
-
-        classImplements(C1, I2)
-
-        class C2(C1):
-            pass
-
-        classImplements(C2, I3)
-
-        self.assertEqual([i.getName() for i in implementedBy(C2)],
-                         ['I3', 'I2'])
-
-    def test_odd_metaclass_that_doesnt_subclass_type(self):
-        # This was originally a doctest in odd.py.
-        # It verifies that the metaclass the rest of these tests use
-        # works as expected.
-
-        # This is used for testing support for ExtensionClass in new
-        # interfaces.
-
-        class A:
-            a = 1
-
-        A = odd.MetaClass('A', A.__bases__, A.__dict__)
-
-        class B:
-            b = 1
-
-        B = odd.MetaClass('B', B.__bases__, B.__dict__)
-
-        class C(A, B):
-            pass
-
-        self.assertEqual(C.__bases__, (A, B))
-
-        a = A()
-        aa = A()
-        self.assertEqual(a.a, 1)
-        self.assertEqual(aa.a, 1)
-
-        aa.a = 2
-        self.assertEqual(a.a, 1)
-        self.assertEqual(aa.a, 2)
-
-        c = C()
-        self.assertEqual(c.a, 1)
-        self.assertEqual(c.b, 1)
-
-        c.b = 2
-        self.assertEqual(c.b, 2)
-
-        C.c = 1
-        self.assertEqual(c.c, 1)
-        c.c
-
-        self.assertIs(C.__class__.__class__, C.__class__)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_registry.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_registry.py
deleted file mode 100644
index 0da200e..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_registry.py
+++ /dev/null
@@ -1,3391 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002, 2009 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Component Registry Tests"""
-# pylint:disable=protected-access
-import unittest
-
-from zope.interface import Interface
-from zope.interface.adapter import VerifyingAdapterRegistry
-from zope.interface.registry import Components
-
-
-class ComponentsTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        return Components
-
-    def _makeOne(self, name='test', *args, **kw):
-        return self._getTargetClass()(name, *args, **kw)
-
-    def _wrapEvents(self):
-        from zope.interface import registry
-        _events = []
-
-        def _notify(*args, **kw):
-            _events.append((args, kw))
-
-        _monkey = _Monkey(registry, notify=_notify)
-        return _monkey, _events
-
-    def test_ctor_no_bases(self):
-        from zope.interface.adapter import AdapterRegistry
-        comp = self._makeOne('testing')
-        self.assertEqual(comp.__name__, 'testing')
-        self.assertEqual(comp.__bases__, ())
-        self.assertIsInstance(comp.adapters, AdapterRegistry)
-        self.assertIsInstance(comp.utilities, AdapterRegistry)
-        self.assertEqual(comp.adapters.__bases__, ())
-        self.assertEqual(comp.utilities.__bases__, ())
-        self.assertEqual(comp._utility_registrations, {})
-        self.assertEqual(comp._adapter_registrations, {})
-        self.assertEqual(comp._subscription_registrations, [])
-        self.assertEqual(comp._handler_registrations, [])
-
-    def test_ctor_w_base(self):
-        base = self._makeOne('base')
-        comp = self._makeOne('testing', (base,))
-        self.assertEqual(comp.__name__, 'testing')
-        self.assertEqual(comp.__bases__, (base,))
-        self.assertEqual(comp.adapters.__bases__, (base.adapters,))
-        self.assertEqual(comp.utilities.__bases__, (base.utilities,))
-
-    def test___repr__(self):
-        comp = self._makeOne('testing')
-        self.assertEqual(repr(comp), '')
-
-    # test _init_registries / _init_registrations via only caller, __init__.
-
-    def test_assign_to___bases__(self):
-        base1 = self._makeOne('base1')
-        base2 = self._makeOne('base2')
-        comp = self._makeOne()
-        comp.__bases__ = (base1, base2)
-        self.assertEqual(comp.__bases__, (base1, base2))
-        self.assertEqual(comp.adapters.__bases__,
-                         (base1.adapters, base2.adapters))
-        self.assertEqual(comp.utilities.__bases__,
-                         (base1.utilities, base2.utilities))
-
-    def test_registerUtility_with_component_name(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import named
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-
-        @named('foo')
-        class Foo:
-            pass
-
-        foo = Foo()
-        _info = 'info'
-
-        comp = self._makeOne()
-        comp.registerUtility(foo, ifoo, info=_info)
-        self.assertEqual(
-            comp._utility_registrations[ifoo, 'foo'],
-            (foo, _info, None))
-
-    def test_registerUtility_both_factory_and_component(self):
-        def _factory():
-            raise NotImplementedError()
-        _to_reg = object()
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.registerUtility,
-                          component=_to_reg, factory=_factory)
-
-    def test_registerUtility_w_component(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = object()
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_to_reg, ifoo, _name, _info)
-        self.assertIs(comp.utilities._adapters[0][ifoo][_name], _to_reg)
-        self.assertEqual(comp._utility_registrations[ifoo, _name],
-                         (_to_reg, _info, None))
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''], (_to_reg,))
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _to_reg)
-        self.assertIs(event.object.info, _info)
-        self.assertIsNone(event.object.factory)
-
-    def test_registerUtility_w_factory(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = object()
-
-        def _factory():
-            return _to_reg
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(None, ifoo, _name, _info, factory=_factory)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _to_reg)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _factory)
-
-    def test_registerUtility_no_provided_available(self):
-
-        class Foo:
-            pass
-
-        _info = 'info'
-        _name = 'name'
-        _to_reg = Foo()
-        comp = self._makeOne()
-        self.assertRaises(TypeError,
-                          comp.registerUtility, _to_reg, None, _name, _info)
-
-    def test_registerUtility_wo_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        class Foo:
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = Foo()
-        directlyProvides(_to_reg, ifoo)
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_to_reg, None, _name, _info)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _to_reg)
-        self.assertIs(event.object.info, _info)
-        self.assertIsNone(event.object.factory)
-
-    def test_registerUtility_duplicates_existing_reg(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_to_reg, ifoo, _name, _info)
-        self.assertEqual(len(_events), 0)
-
-    def test_registerUtility_w_different_info(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info1 = 'info1'
-        _info2 = 'info2'
-        _name = 'name'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name, _info1)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_to_reg, ifoo, _name, _info2)
-        self.assertEqual(len(_events), 2)  # unreg, reg
-        self.assertEqual(comp._utility_registrations[(ifoo, _name)],
-                         (_to_reg, _info2, None))  # replaced
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''],
-                         (_to_reg,))
-
-    def test_registerUtility_w_different_names_same_component(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _other_reg = object()
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_other_reg, ifoo, _name1, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_to_reg, ifoo, _name2, _info)
-        self.assertEqual(len(_events), 1)  # reg
-        self.assertEqual(comp._utility_registrations[(ifoo, _name1)],
-                         (_other_reg, _info, None))
-        self.assertEqual(comp._utility_registrations[(ifoo, _name2)],
-                         (_to_reg, _info, None))
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''],
-                         (_other_reg, _to_reg,))
-
-    def test_registerUtility_replaces_existing_reg(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _before, _after = object(), object()
-        comp = self._makeOne()
-        comp.registerUtility(_before, ifoo, _name, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_after, ifoo, _name, _info)
-        self.assertEqual(len(_events), 2)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _before)
-        self.assertIs(event.object.info, _info)
-        self.assertIsNone(event.object.factory)
-        args, kw = _events[1]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _after)
-        self.assertIs(event.object.info, _info)
-        self.assertIsNone(event.object.factory)
-
-    def test_registerUtility_w_existing_subscr(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name1, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_to_reg, ifoo, _name2, _info)
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''], (_to_reg,))
-
-    def test_registerUtility_wo_event(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = object()
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerUtility(_to_reg, ifoo, _name, _info, False)
-        self.assertEqual(len(_events), 0)
-
-    def test_registerUtility_changes_object_identity_after(self):
-        # If a subclass changes the identity of the _utility_registrations,
-        # the cache is updated and the right thing still happens.
-        class CompThatChangesAfter1Reg(self._getTargetClass()):
-            reg_count = 0
-
-            def registerUtility(self, *args):
-                self.reg_count += 1
-                super().registerUtility(*args)
-                if self.reg_count == 1:
-                    self._utility_registrations = dict(
-                        self._utility_registrations
-                    )
-
-        comp = CompThatChangesAfter1Reg()
-        comp.registerUtility(object(), Interface)
-
-        self.assertEqual(len(list(comp.registeredUtilities())), 1)
-
-        class IFoo(Interface):
-            pass
-
-        comp.registerUtility(object(), IFoo)
-        self.assertEqual(len(list(comp.registeredUtilities())), 2)
-
-    def test_registerUtility_changes_object_identity_before(self):
-        # If a subclass changes the identity of the _utility_registrations,
-        # the cache is updated and the right thing still happens.
-        class CompThatChangesAfter2Reg(self._getTargetClass()):
-            reg_count = 0
-
-            def registerUtility(self, *args):
-                self.reg_count += 1
-                if self.reg_count == 2:
-                    self._utility_registrations = dict(
-                        self._utility_registrations
-                    )
-
-                super().registerUtility(*args)
-
-        comp = CompThatChangesAfter2Reg()
-        comp.registerUtility(object(), Interface)
-
-        self.assertEqual(len(list(comp.registeredUtilities())), 1)
-
-        class IFoo(Interface):
-            pass
-
-        comp.registerUtility(object(), IFoo)
-        self.assertEqual(len(list(comp.registeredUtilities())), 2)
-
-        class IBar(Interface):
-            pass
-
-        comp.registerUtility(object(), IBar)
-        self.assertEqual(len(list(comp.registeredUtilities())), 3)
-
-    def test_unregisterUtility_wo_factory_nor_component_nor_provided(self):
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterUtility,
-                          component=None, provided=None, factory=None)
-
-    def test_unregisterUtility_both_factory_and_component(self):
-        def _factory():
-            raise NotImplementedError()
-        _to_reg = object()
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterUtility,
-                          component=_to_reg, factory=_factory)
-
-    def test_unregisterUtility_w_component_miss(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _name = 'name'
-        _to_reg = object()
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterUtility(_to_reg, ifoo, _name)
-        self.assertFalse(unreg)
-        self.assertFalse(_events)
-
-    def test_unregisterUtility_w_component(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _name = 'name'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterUtility(_to_reg, ifoo, _name)
-        self.assertTrue(unreg)
-        self.assertFalse(comp.utilities._adapters)  # all erased
-        self.assertNotIn((ifoo, _name), comp._utility_registrations)
-        self.assertFalse(comp.utilities._subscribers)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _to_reg)
-        self.assertIsNone(event.object.factory)
-
-    def test_unregisterUtility_w_factory(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = object()
-
-        def _factory():
-            return _to_reg
-
-        comp = self._makeOne()
-        comp.registerUtility(None, ifoo, _name, _info, factory=_factory)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterUtility(None, ifoo, _name, factory=_factory)
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _to_reg)
-        self.assertIs(event.object.factory, _factory)
-
-    def test_unregisterUtility_wo_explicit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        class Foo:
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = Foo()
-        directlyProvides(_to_reg, ifoo)
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterUtility(_to_reg, None, _name)
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _to_reg)
-        self.assertIs(event.object.info, _info)
-        self.assertIsNone(event.object.factory)
-
-    def test_unregisterUtility_wo_component_or_factory(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import directlyProvides
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        class Foo:
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-        _to_reg = Foo()
-        directlyProvides(_to_reg, ifoo)
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            # Just pass the interface / name
-            unreg = comp.unregisterUtility(provided=ifoo, name=_name)
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, UtilityRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.component, _to_reg)
-        self.assertIs(event.object.info, _info)
-        self.assertIsNone(event.object.factory)
-
-    def test_unregisterUtility_w_existing_subscr(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name1, _info)
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.unregisterUtility(_to_reg, ifoo, _name2)
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''], (_to_reg,))
-
-    def test_unregisterUtility_w_existing_subscr_non_hashable(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = dict()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name1, _info)
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.unregisterUtility(_to_reg, ifoo, _name2)
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''], (_to_reg,))
-
-    def test_unregisterUtility_w_existing_subs_non_hashable_fresh_cache(self):
-        # We correctly populate the cache of registrations if it has gone away
-        # (for example, the Components was unpickled)
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.registry import _UtilityRegistrations
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = dict()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name1, _info)
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.unregisterUtility(_to_reg, ifoo, _name2)
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''], (_to_reg,))
-
-    def test_unregisterUtility_w_existing_subscr_non_hashable_reinitted(self):
-        # We correctly populate the cache of registrations if the base objects
-        # change out from under us
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = dict()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name1, _info)
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-
-        # zope.component.testing does this
-        comp.__init__('base')
-
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            # Nothing to do, but we don't break either
-            comp.unregisterUtility(_to_reg, ifoo, _name2)
-        self.assertEqual(0, len(comp.utilities._subscribers))
-
-    def test_unregisterUtility_w_existing_subscr_other_component(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _other_reg = object()
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_other_reg, ifoo, _name1, _info)
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.unregisterUtility(_to_reg, ifoo, _name2)
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''],
-                         (_other_reg,))
-
-    def test_unregisterUtility_w_existing_subscr_oter_comp_mixed_hash(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        # First register something hashable
-        _other_reg = object()
-        # Then it transfers to something unhashable
-        _to_reg = dict()
-        comp = self._makeOne()
-        comp.registerUtility(_other_reg, ifoo, _name1, _info)
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.unregisterUtility(_to_reg, ifoo, _name2)
-        self.assertEqual(comp.utilities._subscribers[0][ifoo][''],
-                         (_other_reg,))
-
-    def test_registeredUtilities_empty(self):
-        comp = self._makeOne()
-        self.assertEqual(list(comp.registeredUtilities()), [])
-
-    def test_registeredUtilities_notempty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.registry import UtilityRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, _name1, _info)
-        comp.registerUtility(_to_reg, ifoo, _name2, _info)
-        reg = sorted(comp.registeredUtilities(), key=lambda r: r.name)
-        self.assertEqual(len(reg), 2)
-        self.assertIsInstance(reg[0], UtilityRegistration)
-        self.assertIs(reg[0].registry, comp)
-        self.assertIs(reg[0].provided, ifoo)
-        self.assertIs(reg[0].name, _name1)
-        self.assertIs(reg[0].component, _to_reg)
-        self.assertIs(reg[0].info, _info)
-        self.assertIsNone(reg[0].factory)
-        self.assertIsInstance(reg[1], UtilityRegistration)
-        self.assertIs(reg[1].registry, comp)
-        self.assertIs(reg[1].provided, ifoo)
-        self.assertIs(reg[1].name, _name2)
-        self.assertIs(reg[1].component, _to_reg)
-        self.assertIs(reg[1].info, _info)
-        self.assertIsNone(reg[1].factory)
-
-    def test_queryUtility_miss_no_default(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        self.assertIsNone(comp.queryUtility(ifoo))
-
-    def test_queryUtility_miss_w_default(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        _default = object()
-        self.assertIs(comp.queryUtility(ifoo, default=_default), _default)
-
-    def test_queryUtility_hit(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo)
-        self.assertIs(comp.queryUtility(ifoo), _to_reg)
-
-    def test_getUtility_miss(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import ComponentLookupError
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        self.assertRaises(ComponentLookupError, comp.getUtility, ifoo)
-
-    def test_getUtility_hit(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo)
-        self.assertIs(comp.getUtility(ifoo), _to_reg)
-
-    def test_getUtilitiesFor_miss(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        self.assertEqual(list(comp.getUtilitiesFor(ifoo)), [])
-
-    def test_getUtilitiesFor_hit(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, name=_name1)
-        comp.registerUtility(_to_reg, ifoo, name=_name2)
-        self.assertEqual(sorted(comp.getUtilitiesFor(ifoo)),
-                         [(_name1, _to_reg), (_name2, _to_reg)])
-
-    def test_getAllUtilitiesRegisteredFor_miss(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        self.assertEqual(list(comp.getAllUtilitiesRegisteredFor(ifoo)), [])
-
-    def test_getAllUtilitiesRegisteredFor_hit(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _name1 = 'name1'
-        _name2 = 'name2'
-        _to_reg = object()
-        comp = self._makeOne()
-        comp.registerUtility(_to_reg, ifoo, name=_name1)
-        comp.registerUtility(_to_reg, ifoo, name=_name2)
-        self.assertEqual(list(comp.getAllUtilitiesRegisteredFor(ifoo)),
-                         [_to_reg])
-
-    def test_registerAdapter_with_component_name(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import named
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        @named('foo')
-        class Foo:
-            pass
-        _info = 'info'
-
-        comp = self._makeOne()
-        comp.registerAdapter(Foo, (ibar,), ifoo, info=_info)
-
-        self.assertEqual(
-            comp._adapter_registrations[(ibar,), ifoo, 'foo'],
-            (Foo, _info))
-
-    def test_registerAdapter_w_explicit_provided_and_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _name = 'name'
-
-        def _factory(context):
-            raise NotImplementedError()
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerAdapter(_factory, (ibar,), ifoo, _name, _info)
-        self.assertIs(
-            comp.adapters._adapters[1][ibar][ifoo][_name],
-            _factory
-        )
-        self.assertEqual(comp._adapter_registrations[(ibar,), ifoo, _name],
-                         (_factory, _info))
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _factory)
-
-    def test_registerAdapter_no_provided_available(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _name = 'name'
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.registerAdapter, _Factory, (ibar,),
-                          name=_name, info=_info)
-
-    def test_registerAdapter_wo_explicit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _name = 'name'
-
-        @implementer(ifoo)
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerAdapter(_Factory, (ibar,), name=_name, info=_info)
-        self.assertIs(
-            comp.adapters._adapters[1][ibar][ifoo][_name],
-            _Factory
-        )
-        self.assertEqual(comp._adapter_registrations[(ibar,), ifoo, _name],
-                         (_Factory, _info))
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_registerAdapter_no_required_available(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-
-        _info = 'info'
-        _name = 'name'
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.registerAdapter, _Factory,
-                          provided=ifoo, name=_name, info=_info)
-
-    def test_registerAdapter_w_invalid_required(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _name = 'name'
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.registerAdapter, _Factory,
-                          ibar, provided=ifoo, name=_name, info=_info)
-
-    def test_registerAdapter_w_required_containing_None(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interface import Interface
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _name = 'name'
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerAdapter(_Factory, [None], provided=ifoo,
-                                 name=_name, info=_info)
-        self.assertIs(
-            comp.adapters._adapters[1][Interface][ifoo][_name],
-            _Factory
-        )
-        self.assertEqual(
-            comp._adapter_registrations[(Interface,), ifoo, _name],
-            (_Factory, _info)
-        )
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (Interface,))
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_registerAdapter_w_required_containing_class(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementedBy
-        from zope.interface.declarations import implementer
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _name = 'name'
-
-        class _Factory:
-            pass
-
-        @implementer(ibar)
-        class _Context:
-            pass
-
-        _ctx_impl = implementedBy(_Context)
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerAdapter(_Factory, [_Context], provided=ifoo,
-                                 name=_name, info=_info)
-        self.assertIs(
-            comp.adapters._adapters[1][_ctx_impl][ifoo][_name],
-            _Factory
-        )
-        self.assertEqual(
-            comp._adapter_registrations[(_ctx_impl,), ifoo, _name],
-            (_Factory, _info)
-        )
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (_ctx_impl,))
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_registerAdapter_w_required_containing_junk(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-
-        _info = 'info'
-        _name = 'name'
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        with self.assertRaises(TypeError):
-            comp.registerAdapter(
-                _Factory, [object()], provided=ifoo, name=_name, info=_info,
-            )
-
-    def test_registerAdapter_wo_explicit_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _name = 'name'
-
-        class _Factory:
-            __component_adapts__ = (ibar,)
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerAdapter(_Factory, provided=ifoo, name=_name,
-                                 info=_info)
-        self.assertIs(
-            comp.adapters._adapters[1][ibar][ifoo][_name],
-            _Factory
-        )
-        self.assertEqual(comp._adapter_registrations[(ibar,), ifoo, _name],
-                         (_Factory, _info))
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertIs(event.object.name, _name)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_registerAdapter_wo_event(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _name = 'name'
-
-        def _factory(context):
-            raise NotImplementedError()
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerAdapter(_factory, (ibar,), ifoo, _name, _info,
-                                 event=False)
-        self.assertEqual(len(_events), 0)
-
-    def test_unregisterAdapter_neither_factory_nor_provided(self):
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterAdapter,
-                          factory=None, provided=None)
-
-    def test_unregisterAdapter_neither_factory_nor_required(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterAdapter,
-                          factory=None, provided=ifoo, required=None)
-
-    def test_unregisterAdapter_miss(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterAdapter(_Factory, (ibar,), ifoo)
-        self.assertFalse(unreg)
-
-    def test_unregisterAdapter_hit_w_explicit_provided_and_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar,), ifoo)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterAdapter(_Factory, (ibar,), ifoo)
-        self.assertTrue(unreg)
-        self.assertFalse(comp.adapters._adapters)
-        self.assertFalse(comp._adapter_registrations)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_unregisterAdapter_wo_explicit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        @implementer(ifoo)
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar,), ifoo)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterAdapter(_Factory, (ibar,))
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_unregisterAdapter_wo_explicit_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            __component_adapts__ = (ibar,)
-
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar,), ifoo)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterAdapter(_Factory, provided=ifoo)
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, AdapterRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_registeredAdapters_empty(self):
-        comp = self._makeOne()
-        self.assertEqual(list(comp.registeredAdapters()), [])
-
-    def test_registeredAdapters_notempty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.registry import AdapterRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IFoo')
-        _info = 'info'
-        _name1 = 'name1'
-        _name2 = 'name2'
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar,), ifoo, _name1, _info)
-        comp.registerAdapter(_Factory, (ibar,), ifoo, _name2, _info)
-        reg = sorted(comp.registeredAdapters(), key=lambda r: r.name)
-        self.assertEqual(len(reg), 2)
-        self.assertIsInstance(reg[0], AdapterRegistration)
-        self.assertIs(reg[0].registry, comp)
-        self.assertIs(reg[0].provided, ifoo)
-        self.assertEqual(reg[0].required, (ibar,))
-        self.assertIs(reg[0].name, _name1)
-        self.assertIs(reg[0].info, _info)
-        self.assertIs(reg[0].factory, _Factory)
-        self.assertIsInstance(reg[1], AdapterRegistration)
-        self.assertIs(reg[1].registry, comp)
-        self.assertIs(reg[1].provided, ifoo)
-        self.assertEqual(reg[1].required, (ibar,))
-        self.assertIs(reg[1].name, _name2)
-        self.assertIs(reg[1].info, _info)
-        self.assertIs(reg[1].factory, _Factory)
-
-    def test_queryAdapter_miss_no_default(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        _context = object()
-        self.assertIsNone(comp.queryAdapter(_context, ifoo))
-
-    def test_queryAdapter_miss_w_default(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        _context = object()
-        _default = object()
-        self.assertIs(
-            comp.queryAdapter(_context, ifoo, default=_default),
-            _default
-        )
-
-    def test_queryAdapter_hit(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            def __init__(self, context):
-                self.context = context
-
-        @implementer(ibar)
-        class _Context:
-            pass
-
-        _context = _Context()
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar,), ifoo)
-        adapter = comp.queryAdapter(_context, ifoo)
-        self.assertIsInstance(adapter, _Factory)
-        self.assertIs(adapter.context, _context)
-
-    def test_getAdapter_miss(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-        from zope.interface.interfaces import ComponentLookupError
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        @implementer(ibar)
-        class _Context:
-            pass
-
-        _context = _Context()
-        comp = self._makeOne()
-        self.assertRaises(ComponentLookupError,
-                          comp.getAdapter, _context, ifoo)
-
-    def test_getAdapter_hit(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            def __init__(self, context):
-                self.context = context
-
-        @implementer(ibar)
-        class _Context:
-            pass
-
-        _context = _Context()
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar,), ifoo)
-        adapter = comp.getAdapter(_context, ifoo)
-        self.assertIsInstance(adapter, _Factory)
-        self.assertIs(adapter.context, _context)
-
-    def test_getAdapter_hit_super(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class IFoo(Interface):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        @implementer(IDerived)
-        class Derived(Base):
-            pass
-
-        class AdapterBase:
-            def __init__(self, context):
-                self.context = context
-
-        class AdapterDerived:
-            def __init__(self, context):
-                self.context = context
-
-        comp = self._makeOne()
-        comp.registerAdapter(AdapterDerived, (IDerived,), IFoo)
-        comp.registerAdapter(AdapterBase, (IBase,), IFoo)
-        self._should_not_change(comp)
-
-        derived = Derived()
-        adapter = comp.getAdapter(derived, IFoo)
-        self.assertIsInstance(adapter, AdapterDerived)
-        self.assertIs(adapter.context, derived)
-
-        supe = super(Derived, derived)
-        adapter = comp.getAdapter(supe, IFoo)
-        self.assertIsInstance(adapter, AdapterBase)
-        self.assertIs(adapter.context, derived)
-
-    def test_getAdapter_hit_super_w_parent_implements_interface_diamond(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class IFoo(Interface):
-            pass
-
-        class Base:
-            pass
-
-        class Child1(Base):
-            pass
-
-        @implementer(IBase)
-        class Child2(Base):
-            pass
-
-        @implementer(IDerived)
-        class Derived(Child1, Child2):
-            pass
-
-        class AdapterBase:
-            def __init__(self, context):
-                self.context = context
-
-        class AdapterDerived:
-            def __init__(self, context):
-                self.context = context
-
-        comp = self._makeOne()
-        comp.registerAdapter(AdapterDerived, (IDerived,), IFoo)
-        comp.registerAdapter(AdapterBase, (IBase,), IFoo)
-        self._should_not_change(comp)
-
-        derived = Derived()
-        adapter = comp.getAdapter(derived, IFoo)
-        self.assertIsInstance(adapter, AdapterDerived)
-        self.assertIs(adapter.context, derived)
-
-        supe = super(Derived, derived)
-        adapter = comp.getAdapter(supe, IFoo)
-        self.assertIsInstance(adapter, AdapterBase)
-        self.assertIs(adapter.context, derived)
-
-    def test_queryMultiAdapter_miss(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-        comp = self._makeOne()
-        self.assertEqual(comp.queryMultiAdapter((_context1, _context2), ifoo),
-                         None)
-
-    def test_queryMultiAdapter_miss_w_default(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-        _default = object()
-        comp = self._makeOne()
-        self.assertIs(
-            comp.queryMultiAdapter((_context1, _context2), ifoo,
-                                   default=_default),
-            _default
-        )
-
-    def test_queryMultiAdapter_hit(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-
-        class _Factory:
-            def __init__(self, context1, context2):
-                self.context = context1, context2
-
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar, ibaz), ifoo)
-        adapter = comp.queryMultiAdapter((_context1, _context2), ifoo)
-        self.assertIsInstance(adapter, _Factory)
-        self.assertEqual(adapter.context, (_context1, _context2))
-
-    def test_getMultiAdapter_miss(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-        from zope.interface.interfaces import ComponentLookupError
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-        comp = self._makeOne()
-        self.assertRaises(ComponentLookupError,
-                          comp.getMultiAdapter, (_context1, _context2), ifoo)
-
-    def test_getMultiAdapter_hit(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-
-        class _Factory:
-            def __init__(self, context1, context2):
-                self.context = context1, context2
-
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory, (ibar, ibaz), ifoo)
-        adapter = comp.getMultiAdapter((_context1, _context2), ifoo)
-        self.assertIsInstance(adapter, _Factory)
-        self.assertEqual(adapter.context, (_context1, _context2))
-
-    def _should_not_change(self, comp):
-        # Be sure that none of the underlying structures
-        # get told that they have changed during this process
-        # because that invalidates caches.
-        def no_changes(*args):
-            self.fail("Nothing should get changed")
-        comp.changed = no_changes
-        comp.adapters.changed = no_changes
-        comp.adapters._v_lookup.changed = no_changes
-
-    def test_getMultiAdapter_hit_super(self):
-        from zope.interface import Interface
-        from zope.interface.declarations import implementer
-
-        class IBase(Interface):
-            pass
-
-        class IDerived(IBase):
-            pass
-
-        class IFoo(Interface):
-            pass
-
-        @implementer(IBase)
-        class Base:
-            pass
-
-        @implementer(IDerived)
-        class Derived(Base):
-            pass
-
-        class AdapterBase:
-            def __init__(self, context1, context2):
-                self.context1 = context1
-                self.context2 = context2
-
-        class AdapterDerived(AdapterBase):
-            pass
-
-        comp = self._makeOne()
-        comp.registerAdapter(AdapterDerived, (IDerived, IDerived), IFoo)
-        comp.registerAdapter(AdapterBase, (IBase, IDerived), IFoo)
-        self._should_not_change(comp)
-
-        derived = Derived()
-        adapter = comp.getMultiAdapter((derived, derived), IFoo)
-        self.assertIsInstance(adapter, AdapterDerived)
-        self.assertIs(adapter.context1, derived)
-        self.assertIs(adapter.context2, derived)
-
-        supe = super(Derived, derived)
-        adapter = comp.getMultiAdapter((supe, derived), IFoo)
-        self.assertIsInstance(adapter, AdapterBase)
-        self.assertNotIsInstance(adapter, AdapterDerived)
-        self.assertIs(adapter.context1, derived)
-        self.assertIs(adapter.context2, derived)
-
-    def test_getAdapters_empty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-        comp = self._makeOne()
-        self.assertEqual(
-            list(comp.getAdapters((_context1, _context2), ifoo)), [])
-
-    def test_getAdapters_factory_returns_None(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-        comp = self._makeOne()
-        _called_with = []
-
-        def _side_effect_only(context1, context2):
-            _called_with.append((context1, context2))
-            return None
-
-        comp.registerAdapter(_side_effect_only, (ibar, ibaz), ifoo)
-        self.assertEqual(
-            list(comp.getAdapters((_context1, _context2), ifoo)), [])
-        self.assertEqual(_called_with, [(_context1, _context2)])
-
-    def test_getAdapters_non_empty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        ibaz = IFoo('IBaz')
-
-        @implementer(ibar)
-        class _Context1:
-            pass
-
-        @implementer(ibaz)
-        class _Context2:
-            pass
-
-        _context1 = _Context1()
-        _context2 = _Context2()
-
-        class _Factory1:
-            def __init__(self, context1, context2):
-                self.context = context1, context2
-
-        class _Factory2:
-            def __init__(self, context1, context2):
-                self.context = context1, context2
-
-        _name1 = 'name1'
-        _name2 = 'name2'
-        comp = self._makeOne()
-        comp.registerAdapter(_Factory1, (ibar, ibaz), ifoo, name=_name1)
-        comp.registerAdapter(_Factory2, (ibar, ibaz), ifoo, name=_name2)
-        found = sorted(comp.getAdapters((_context1, _context2), ifoo))
-        self.assertEqual(len(found), 2)
-        self.assertEqual(found[0][0], _name1)
-        self.assertIsInstance(found[0][1], _Factory1)
-        self.assertEqual(found[1][0], _name2)
-        self.assertIsInstance(found[1][1], _Factory2)
-
-    def test_registerSubscriptionAdapter_w_nonblank_name(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _name = 'name'
-        _info = 'info'
-
-        def _factory(context):
-            raise NotImplementedError()
-
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.registerSubscriptionAdapter,
-                          _factory, (ibar,), ifoo, _name, _info)
-
-    def test_registerSubscriptionAdapter_w_explicit_provided_n_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _blank = ''
-        _info = 'info'
-
-        def _factory(context):
-            raise NotImplementedError()
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerSubscriptionAdapter(_factory, (ibar,), ifoo,
-                                             info=_info)
-        reg = comp.adapters._subscribers[1][ibar][ifoo][_blank]
-        self.assertEqual(len(reg), 1)
-        self.assertIs(reg[0], _factory)
-        self.assertEqual(comp._subscription_registrations,
-                         [((ibar,), ifoo, _blank, _factory, _info)])
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, SubscriptionRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, _blank)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _factory)
-
-    def test_registerSubscriptionAdapter_wo_explicit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _blank = ''
-
-        @implementer(ifoo)
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerSubscriptionAdapter(_Factory, (ibar,), info=_info)
-        reg = comp.adapters._subscribers[1][ibar][ifoo][_blank]
-        self.assertEqual(len(reg), 1)
-        self.assertIs(reg[0], _Factory)
-        self.assertEqual(comp._subscription_registrations,
-                         [((ibar,), ifoo, _blank, _Factory, _info)])
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, SubscriptionRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, _blank)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_registerSubscriptionAdapter_wo_explicit_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-        _blank = ''
-
-        class _Factory:
-            __component_adapts__ = (ibar,)
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerSubscriptionAdapter(
-                _Factory, provided=ifoo, info=_info,
-            )
-        reg = comp.adapters._subscribers[1][ibar][ifoo][_blank]
-        self.assertEqual(len(reg), 1)
-        self.assertIs(reg[0], _Factory)
-        self.assertEqual(comp._subscription_registrations,
-                         [((ibar,), ifoo, _blank, _Factory, _info)])
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, SubscriptionRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, _blank)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_registerSubscriptionAdapter_wo_event(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _info = 'info'
-
-        def _factory(context):
-            raise NotImplementedError()
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerSubscriptionAdapter(_factory, (ibar,), ifoo,
-                                             info=_info, event=False)
-        self.assertEqual(len(_events), 0)
-
-    def test_registeredSubscriptionAdapters_empty(self):
-        comp = self._makeOne()
-        self.assertEqual(list(comp.registeredSubscriptionAdapters()), [])
-
-    def test_registeredSubscriptionAdapters_notempty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IFoo')
-        _info = 'info'
-        _blank = ''
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        comp.registerSubscriptionAdapter(_Factory, (ibar,), ifoo, info=_info)
-        comp.registerSubscriptionAdapter(_Factory, (ibar,), ifoo, info=_info)
-        reg = list(comp.registeredSubscriptionAdapters())
-        self.assertEqual(len(reg), 2)
-        self.assertIsInstance(reg[0], SubscriptionRegistration)
-        self.assertIs(reg[0].registry, comp)
-        self.assertIs(reg[0].provided, ifoo)
-        self.assertEqual(reg[0].required, (ibar,))
-        self.assertEqual(reg[0].name, _blank)
-        self.assertIs(reg[0].info, _info)
-        self.assertIs(reg[0].factory, _Factory)
-        self.assertIsInstance(reg[1], SubscriptionRegistration)
-        self.assertIs(reg[1].registry, comp)
-        self.assertIs(reg[1].provided, ifoo)
-        self.assertEqual(reg[1].required, (ibar,))
-        self.assertEqual(reg[1].name, _blank)
-        self.assertIs(reg[1].info, _info)
-        self.assertIs(reg[1].factory, _Factory)
-
-    def test_unregisterSubscriptionAdapter_w_nonblank_name(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        _nonblank = 'nonblank'
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterSubscriptionAdapter,
-                          required=ifoo, provided=ibar, name=_nonblank)
-
-    def test_unregisterSubscriptionAdapter_neither_factory_nor_provided(self):
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterSubscriptionAdapter,
-                          factory=None, provided=None)
-
-    def test_unregisterSubscriptionAdapter_neither_factory_nor_required(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterSubscriptionAdapter,
-                          factory=None, provided=ifoo, required=None)
-
-    def test_unregisterSubscriptionAdapter_miss(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterSubscriptionAdapter(_Factory, (ibar,), ifoo)
-        self.assertFalse(unreg)
-        self.assertFalse(_events)
-
-    def test_unregisterSubscriptionAdapter_hit_wo_factory(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        comp.registerSubscriptionAdapter(_Factory, (ibar,), ifoo)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterSubscriptionAdapter(None, (ibar,), ifoo)
-        self.assertTrue(unreg)
-        self.assertFalse(comp.adapters._subscribers)
-        self.assertFalse(comp._subscription_registrations)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, SubscriptionRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIsNone(event.object.factory)
-
-    def test_unregisterSubscriptionAdapter_hit_w_factory(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        comp.registerSubscriptionAdapter(_Factory, (ibar,), ifoo)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterSubscriptionAdapter(_Factory, (ibar,), ifoo)
-        self.assertTrue(unreg)
-        self.assertFalse(comp.adapters._subscribers)
-        self.assertFalse(comp._subscription_registrations)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, SubscriptionRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_unregisterSubscriptionAdapter_wo_explicit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        @implementer(ifoo)
-        class _Factory:
-            pass
-
-        comp = self._makeOne()
-        comp.registerSubscriptionAdapter(_Factory, (ibar,), ifoo)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterSubscriptionAdapter(_Factory, (ibar,))
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, SubscriptionRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_unregisterSubscriptionAdapter_wo_explicit_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import SubscriptionRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            __component_adapts__ = (ibar,)
-
-        comp = self._makeOne()
-        comp.registerSubscriptionAdapter(_Factory, (ibar,), ifoo)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterSubscriptionAdapter(_Factory, provided=ifoo)
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, SubscriptionRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertIs(event.object.provided, ifoo)
-        self.assertEqual(event.object.required, (ibar,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_subscribers_empty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-        comp = self._makeOne()
-
-        @implementer(ibar)
-        class Bar:
-            pass
-
-        bar = Bar()
-        self.assertEqual(list(comp.subscribers((bar,), ifoo)), [])
-
-    def test_subscribers_non_empty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Factory:
-            __component_adapts__ = (ibar,)
-
-            def __init__(self, context):
-                self._context = context
-
-        class _Derived(_Factory):
-            pass
-
-        comp = self._makeOne()
-        comp.registerSubscriptionAdapter(_Factory, (ibar,), ifoo)
-        comp.registerSubscriptionAdapter(_Derived, (ibar,), ifoo)
-
-        @implementer(ibar)
-        class Bar:
-            pass
-
-        bar = Bar()
-        subscribers = comp.subscribers((bar,), ifoo)
-
-        def _klassname(x):
-            return x.__class__.__name__
-
-        subscribers = sorted(subscribers, key=_klassname)
-        self.assertEqual(len(subscribers), 2)
-        self.assertIsInstance(subscribers[0], _Derived)
-        self.assertIsInstance(subscribers[1], _Factory)
-
-    def test_registerHandler_w_nonblank_name(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _nonblank = 'nonblank'
-        comp = self._makeOne()
-
-        def _factory(context):
-            raise NotImplementedError()
-
-        self.assertRaises(TypeError, comp.registerHandler, _factory,
-                          required=ifoo, name=_nonblank)
-
-    def test_registerHandler_w_explicit_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Registered
-        from zope.interface.registry import HandlerRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _blank = ''
-        _info = 'info'
-
-        def _factory(context):
-            raise NotImplementedError()
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerHandler(_factory, (ifoo,), info=_info)
-        reg = comp.adapters._subscribers[1][ifoo][None][_blank]
-        self.assertEqual(len(reg), 1)
-        self.assertIs(reg[0], _factory)
-        self.assertEqual(comp._handler_registrations,
-                         [((ifoo,), _blank, _factory, _info)])
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Registered)
-        self.assertIsInstance(event.object, HandlerRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertEqual(event.object.required, (ifoo,))
-        self.assertEqual(event.object.name, _blank)
-        self.assertIs(event.object.info, _info)
-        self.assertIs(event.object.factory, _factory)
-
-    def test_registerHandler_wo_explicit_required_no_event(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _info = 'info'
-        _blank = ''
-
-        class _Factory:
-            __component_adapts__ = (ifoo,)
-            pass
-
-        comp = self._makeOne()
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            comp.registerHandler(_Factory, info=_info, event=False)
-        reg = comp.adapters._subscribers[1][ifoo][None][_blank]
-        self.assertEqual(len(reg), 1)
-        self.assertIs(reg[0], _Factory)
-        self.assertEqual(comp._handler_registrations,
-                         [((ifoo,), _blank, _Factory, _info)])
-        self.assertEqual(len(_events), 0)
-
-    def test_registeredHandlers_empty(self):
-        comp = self._makeOne()
-        self.assertFalse(list(comp.registeredHandlers()))
-
-    def test_registeredHandlers_non_empty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.registry import HandlerRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-
-        def _factory1(context):
-            raise NotImplementedError()
-
-        def _factory2(context):
-            raise NotImplementedError()
-
-        comp = self._makeOne()
-        comp.registerHandler(_factory1, (ifoo,))
-        comp.registerHandler(_factory2, (ifoo,))
-
-        def _factory_name(x):
-            return x.factory.__code__.co_name
-
-        subscribers = sorted(comp.registeredHandlers(), key=_factory_name)
-        self.assertEqual(len(subscribers), 2)
-        self.assertIsInstance(subscribers[0], HandlerRegistration)
-        self.assertEqual(subscribers[0].required, (ifoo,))
-        self.assertEqual(subscribers[0].name, '')
-        self.assertEqual(subscribers[0].factory, _factory1)
-        self.assertEqual(subscribers[0].info, '')
-        self.assertIsInstance(subscribers[1], HandlerRegistration)
-        self.assertEqual(subscribers[1].required, (ifoo,))
-        self.assertEqual(subscribers[1].name, '')
-        self.assertEqual(subscribers[1].factory, _factory2)
-        self.assertEqual(subscribers[1].info, '')
-
-    def test_unregisterHandler_w_nonblank_name(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _nonblank = 'nonblank'
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterHandler,
-                          required=(ifoo,), name=_nonblank)
-
-    def test_unregisterHandler_neither_factory_nor_required(self):
-        comp = self._makeOne()
-        self.assertRaises(TypeError, comp.unregisterHandler)
-
-    def test_unregisterHandler_miss(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-        unreg = comp.unregisterHandler(required=(ifoo,))
-        self.assertFalse(unreg)
-
-    def test_unregisterHandler_hit_w_factory_and_explicit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import HandlerRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-
-        def _factory(context):
-            raise NotImplementedError()
-
-        comp = self._makeOne()
-        comp.registerHandler(_factory, (ifoo,))
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterHandler(_factory, (ifoo,))
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, HandlerRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertEqual(event.object.required, (ifoo,))
-        self.assertEqual(event.object.name, '')
-        self.assertIs(event.object.factory, _factory)
-
-    def test_unregisterHandler_hit_w_only_explicit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import HandlerRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-
-        def _factory(context):
-            raise NotImplementedError()
-
-        comp = self._makeOne()
-        comp.registerHandler(_factory, (ifoo,))
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterHandler(required=(ifoo,))
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, HandlerRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertEqual(event.object.required, (ifoo,))
-        self.assertEqual(event.object.name, '')
-        self.assertIsNone(event.object.factory)
-
-    def test_unregisterHandler_wo_explicit_required(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.interfaces import Unregistered
-        from zope.interface.registry import HandlerRegistration
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-
-        class _Factory:
-            __component_adapts__ = (ifoo,)
-
-        comp = self._makeOne()
-        comp.registerHandler(_Factory)
-        _monkey, _events = self._wrapEvents()
-        with _monkey:
-            unreg = comp.unregisterHandler(_Factory)
-        self.assertTrue(unreg)
-        self.assertEqual(len(_events), 1)
-        args, kw = _events[0]
-        event, = args
-        self.assertEqual(kw, {})
-        self.assertIsInstance(event, Unregistered)
-        self.assertIsInstance(event.object, HandlerRegistration)
-        self.assertIs(event.object.registry, comp)
-        self.assertEqual(event.object.required, (ifoo,))
-        self.assertEqual(event.object.name, '')
-        self.assertEqual(event.object.info, '')
-        self.assertIs(event.object.factory, _Factory)
-
-    def test_handle_empty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        comp = self._makeOne()
-
-        @implementer(ifoo)
-        class Bar:
-            pass
-
-        bar = Bar()
-        comp.handle((bar,))  # doesn't raise
-
-    def test_handle_non_empty(self):
-        from zope.interface.declarations import InterfaceClass
-        from zope.interface.declarations import implementer
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        _called_1 = []
-
-        def _factory_1(context):
-            _called_1.append(context)
-
-        _called_2 = []
-
-        def _factory_2(context):
-            _called_2.append(context)
-
-        comp = self._makeOne()
-        comp.registerHandler(_factory_1, (ifoo,))
-        comp.registerHandler(_factory_2, (ifoo,))
-
-        @implementer(ifoo)
-        class Bar:
-            pass
-
-        bar = Bar()
-        comp.handle(bar)
-        self.assertEqual(_called_1, [bar])
-        self.assertEqual(_called_2, [bar])
-
-    def test_register_unregister_identical_objects_provided(
-        self, identical=True,
-    ):
-        # https://github.com/zopefoundation/zope.interface/issues/227
-        class IFoo(Interface):
-            pass
-
-        comp = self._makeOne()
-        first = object()
-        second = first if identical else object()
-
-        comp.registerUtility(first, provided=IFoo)
-        comp.registerUtility(second, provided=IFoo, name='bar')
-
-        self.assertEqual(len(comp.utilities._subscribers), 1)
-        self.assertEqual(comp.utilities._subscribers, [{
-            IFoo: {'': (first, ) if identical else (first, second)}
-        }])
-        self.assertEqual(comp.utilities._provided, {
-            IFoo: 3 if identical else 4
-        })
-
-        res = comp.unregisterUtility(first, provided=IFoo)
-        self.assertTrue(res)
-        res = comp.unregisterUtility(second, provided=IFoo, name='bar')
-        self.assertTrue(res)
-
-        self.assertEqual(comp.utilities._provided, {})
-        self.assertEqual(len(comp.utilities._subscribers), 0)
-
-    def test_register_unregister_nonequal_objects_provided(self):
-        self.test_register_unregister_identical_objects_provided(
-            identical=False,
-        )
-
-    def test_rebuildUtilityRegistryFromLocalCache(self):
-
-        class IFoo(Interface):
-            "Does nothing"
-
-        class UtilityImplementingFoo:
-            "Does nothing"
-
-        comps = self._makeOne()
-
-        for i in range(30):
-            comps.registerUtility(
-                UtilityImplementingFoo(), IFoo, name=f'{i}'
-            )
-
-        orig_generation = comps.utilities._generation
-
-        orig_adapters = comps.utilities._adapters
-        self.assertEqual(len(orig_adapters), 1)
-        self.assertEqual(len(orig_adapters[0]), 1)
-        self.assertEqual(len(orig_adapters[0][IFoo]), 30)
-
-        orig_subscribers = comps.utilities._subscribers
-        self.assertEqual(len(orig_subscribers), 1)
-        self.assertEqual(len(orig_subscribers[0]), 1)
-        self.assertEqual(len(orig_subscribers[0][IFoo]), 1)
-        self.assertEqual(len(orig_subscribers[0][IFoo]['']), 30)
-
-        # Blow a bunch of them away, creating artificial corruption
-        new_adapters = comps.utilities._adapters = type(orig_adapters)()
-        new_adapters.append({})
-        d = new_adapters[0][IFoo] = {}
-        for name in range(10):
-            name = str(str(name))
-            d[name] = orig_adapters[0][IFoo][name]
-
-        self.assertNotEqual(orig_adapters, new_adapters)
-
-        new_subs = comps.utilities._subscribers = type(orig_subscribers)()
-        new_subs.append({})
-        d = new_subs[0][IFoo] = {}
-        d[''] = ()
-
-        for name in range(5, 12):  # 12 - 5 = 7
-            name = str(str(name))
-            comp = orig_adapters[0][IFoo][name]
-            d[''] += (comp,)
-
-        # We can preflight (by default) and nothing changes
-        rebuild_preflight = comps.rebuildUtilityRegistryFromLocalCache()
-
-        self.assertEqual(comps.utilities._generation, orig_generation)
-        self.assertEqual(rebuild_preflight, {
-            'did_not_register': 10,
-            'needed_registered': 20,
-
-            'did_not_subscribe': 7,
-            'needed_subscribed': 23,
-        })
-
-        # Now for real
-        rebuild_results = comps.rebuildUtilityRegistryFromLocalCache(
-            rebuild=True,
-        )
-
-        # The generation only got incremented once
-        self.assertEqual(comps.utilities._generation, orig_generation + 1)
-        # The result was the same
-        self.assertEqual(rebuild_preflight, rebuild_results)
-        self.assertEqual(new_adapters, orig_adapters)
-        self.assertEqual(
-            len(new_subs[0][IFoo]['']),
-            len(orig_subscribers[0][IFoo]['']))
-
-        for orig_subscriber in orig_subscribers[0][IFoo]['']:
-            self.assertIn(orig_subscriber, new_subs[0][IFoo][''])
-
-        # Preflighting, rebuilding again produce no changes.
-        preflight_after = comps.rebuildUtilityRegistryFromLocalCache()
-        self.assertEqual(preflight_after, {
-            'did_not_register': 30,
-            'needed_registered': 0,
-
-            'did_not_subscribe': 30,
-            'needed_subscribed': 0,
-        })
-
-        rebuild_after = comps.rebuildUtilityRegistryFromLocalCache(
-            rebuild=True,
-        )
-        self.assertEqual(rebuild_after, preflight_after)
-        self.assertEqual(comps.utilities._generation, orig_generation + 1)
-
-
-class UnhashableComponentsTests(ComponentsTests):
-
-    def _getTargetClass(self):
-        # Mimic what pyramid does to create an unhashable
-        # registry
-
-        class Components(
-            super(UnhashableComponentsTests, self)._getTargetClass(), dict,
-        ):
-            pass
-
-        return Components
-
-# Test _getUtilityProvided, _getAdapterProvided, _getAdapterRequired via their
-# callers (Component.registerUtility, Component.registerAdapter).
-
-
-class UtilityRegistrationTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.registry import UtilityRegistration
-        return UtilityRegistration
-
-    def _makeOne(self, component=None, factory=None):
-        from zope.interface.declarations import InterfaceClass
-
-        class InterfaceClassSubclass(InterfaceClass):
-            pass
-
-        ifoo = InterfaceClassSubclass('IFoo')
-
-        class _Registry:
-            def __repr__(self):
-                return '_REGISTRY'
-
-        registry = _Registry()
-        name = 'name'
-        doc = 'DOCSTRING'
-        klass = self._getTargetClass()
-        return (
-            klass(registry, ifoo, name, component, doc, factory),
-            registry,
-            name,
-        )
-
-    def test_class_conforms_to_IUtilityRegistration(self):
-        from zope.interface.interfaces import IUtilityRegistration
-        from zope.interface.verify import verifyClass
-        verifyClass(IUtilityRegistration, self._getTargetClass())
-
-    def test_instance_conforms_to_IUtilityRegistration(self):
-        from zope.interface.interfaces import IUtilityRegistration
-        from zope.interface.verify import verifyObject
-        ur, _, _ = self._makeOne()
-        verifyObject(IUtilityRegistration, ur)
-
-    def test___repr__(self):
-
-        class _Component:
-            __name__ = 'TEST'
-
-        _component = _Component()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertEqual(
-            repr(ur), (
-                "UtilityRegistration("
-                "_REGISTRY, IFoo, %r, TEST, None, 'DOCSTRING')"
-            ) % (_name)
-        )
-
-    def test___repr___provided_wo_name(self):
-
-        class _Component:
-            def __repr__(self):
-                return 'TEST'
-
-        _component = _Component()
-        ur, _registry, _name = self._makeOne(_component)
-        ur.provided = object()
-        self.assertEqual(
-            repr(ur), (
-                "UtilityRegistration("
-                "_REGISTRY, None, %r, TEST, None, 'DOCSTRING')"
-            ) % (_name)
-        )
-
-    def test___repr___component_wo_name(self):
-
-        class _Component:
-            def __repr__(self):
-                return 'TEST'
-
-        _component = _Component()
-        ur, _registry, _name = self._makeOne(_component)
-        ur.provided = object()
-        self.assertEqual(
-            repr(ur), (
-                "UtilityRegistration("
-                "_REGISTRY, None, %r, TEST, None, 'DOCSTRING')"
-            ) % (_name)
-        )
-
-    def test___hash__(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertEqual(ur.__hash__(), id(ur))
-
-    def test___eq___identity(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertEqual(ur, ur)
-
-    def test___eq___hit(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component)
-        self.assertEqual(ur, ur2)
-
-    def test___eq___miss(self):
-        _component = object()
-        _component2 = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component2)
-        self.assertNotEqual(ur, ur2)
-
-    def test___ne___identity(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertEqual(ur, ur)
-
-    def test___ne___hit(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component)
-        self.assertEqual(ur, ur2)
-
-    def test___ne___miss(self):
-        _component = object()
-        _component2 = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component2)
-        self.assertNotEqual(ur, ur2)
-
-    def test___lt___identity(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertFalse(ur < ur)
-
-    def test___lt___hit(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component)
-        self.assertFalse(ur < ur2)
-
-    def test___lt___miss(self):
-        _component = object()
-        _component2 = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component2)
-        ur2.name = _name + '2'
-        self.assertLess(ur, ur2)
-
-    def test___le___identity(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertLessEqual(ur, ur)
-
-    def test___le___hit(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component)
-        self.assertLessEqual(ur, ur2)
-
-    def test___le___miss(self):
-        _component = object()
-        _component2 = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component2)
-        ur2.name = _name + '2'
-        self.assertLessEqual(ur, ur2)
-
-    def test___gt___identity(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertFalse(ur > ur)
-
-    def test___gt___hit(self):
-        _component = object()
-        _component2 = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component2)
-        ur2.name = _name + '2'
-        self.assertGreater(ur2, ur)
-
-    def test___gt___miss(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component)
-        self.assertFalse(ur2 > ur)
-
-    def test___ge___identity(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        self.assertGreaterEqual(ur, ur)
-
-    def test___ge___miss(self):
-        _component = object()
-        _component2 = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component2)
-        ur2.name = _name + '2'
-        self.assertFalse(ur >= ur2)
-
-    def test___ge___hit(self):
-        _component = object()
-        ur, _registry, _name = self._makeOne(_component)
-        ur2, _, _ = self._makeOne(_component)
-        ur2.name = _name + '2'
-        self.assertGreaterEqual(ur2, ur)
-
-
-class AdapterRegistrationTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.registry import AdapterRegistration
-        return AdapterRegistration
-
-    def _makeOne(self, component=None):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Registry:
-            def __repr__(self):
-                return '_REGISTRY'
-
-        registry = _Registry()
-        name = 'name'
-        doc = 'DOCSTRING'
-        klass = self._getTargetClass()
-        return (
-            klass(registry, (ibar,), ifoo, name, component, doc),
-            registry,
-            name,
-        )
-
-    def test_class_conforms_to_IAdapterRegistration(self):
-        from zope.interface.interfaces import IAdapterRegistration
-        from zope.interface.verify import verifyClass
-        verifyClass(IAdapterRegistration, self._getTargetClass())
-
-    def test_instance_conforms_to_IAdapterRegistration(self):
-        from zope.interface.interfaces import IAdapterRegistration
-        from zope.interface.verify import verifyObject
-        ar, _, _ = self._makeOne()
-        verifyObject(IAdapterRegistration, ar)
-
-    def test___repr__(self):
-
-        class _Component:
-            __name__ = 'TEST'
-
-        _component = _Component()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertEqual(
-            repr(ar), (
-                "AdapterRegistration(_REGISTRY, [IBar], IFoo, %r, TEST, "
-                "'DOCSTRING')"
-            ) % (_name)
-        )
-
-    def test___repr___provided_wo_name(self):
-
-        class _Component:
-            def __repr__(self):
-                return 'TEST'
-
-        _component = _Component()
-        ar, _registry, _name = self._makeOne(_component)
-        ar.provided = object()
-        self.assertEqual(
-            repr(ar), (
-                "AdapterRegistration(_REGISTRY, [IBar], None, %r, TEST, "
-                "'DOCSTRING')"
-            ) % (_name)
-        )
-
-    def test___repr___component_wo_name(self):
-
-        class _Component:
-            def __repr__(self):
-                return 'TEST'
-
-        _component = _Component()
-        ar, _registry, _name = self._makeOne(_component)
-        ar.provided = object()
-        self.assertEqual(
-            repr(ar), (
-                "AdapterRegistration(_REGISTRY, [IBar], None, %r, TEST, "
-                "'DOCSTRING')"
-            ) % (_name)
-        )
-
-    def test___hash__(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertEqual(ar.__hash__(), id(ar))
-
-    def test___eq___identity(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertEqual(ar, ar)
-
-    def test___eq___hit(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component)
-        self.assertEqual(ar, ar2)
-
-    def test___eq___miss(self):
-        _component = object()
-        _component2 = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component2)
-        self.assertNotEqual(ar, ar2)
-
-    def test___ne___identity(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertEqual(ar, ar)
-
-    def test___ne___miss(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component)
-        self.assertEqual(ar, ar2)
-
-    def test___ne___hit_component(self):
-        _component = object()
-        _component2 = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component2)
-        self.assertNotEqual(ar, ar2)
-
-    def test___ne___hit_provided(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ibaz = IFoo('IBaz')
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component)
-        ar2.provided = ibaz
-        self.assertNotEqual(ar, ar2)
-
-    def test___ne___hit_required(self):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ibaz = IFoo('IBaz')
-        _component = object()
-        _component2 = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component2)
-        ar2.required = (ibaz,)
-        self.assertNotEqual(ar, ar2)
-
-    def test___lt___identity(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertFalse(ar < ar)
-
-    def test___lt___hit(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component)
-        self.assertFalse(ar < ar2)
-
-    def test___lt___miss(self):
-        _component = object()
-        _component2 = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component2)
-        ar2.name = _name + '2'
-        self.assertLess(ar, ar2)
-
-    def test___le___identity(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertLessEqual(ar, ar)
-
-    def test___le___hit(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component)
-        self.assertLessEqual(ar, ar2)
-
-    def test___le___miss(self):
-        _component = object()
-        _component2 = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component2)
-        ar2.name = _name + '2'
-        self.assertLessEqual(ar, ar2)
-
-    def test___gt___identity(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertFalse(ar > ar)
-
-    def test___gt___hit(self):
-        _component = object()
-        _component2 = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component2)
-        ar2.name = _name + '2'
-        self.assertGreater(ar2, ar)
-
-    def test___gt___miss(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component)
-        self.assertFalse(ar2 > ar)
-
-    def test___ge___identity(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        self.assertGreaterEqual(ar, ar)
-
-    def test___ge___miss(self):
-        _component = object()
-        _component2 = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component2)
-        ar2.name = _name + '2'
-        self.assertFalse(ar >= ar2)
-
-    def test___ge___hit(self):
-        _component = object()
-        ar, _registry, _name = self._makeOne(_component)
-        ar2, _, _ = self._makeOne(_component)
-        ar2.name = _name + '2'
-        self.assertGreaterEqual(ar2, ar)
-
-
-class SubscriptionRegistrationTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.registry import SubscriptionRegistration
-        return SubscriptionRegistration
-
-    def _makeOne(self, component=None):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-        ibar = IFoo('IBar')
-
-        class _Registry:
-            def __repr__(self):  # pragma: no cover
-                return '_REGISTRY'
-
-        registry = _Registry()
-        name = 'name'
-        doc = 'DOCSTRING'
-        klass = self._getTargetClass()
-        return (
-            klass(registry, (ibar,), ifoo, name, component, doc),
-            registry,
-            name,
-        )
-
-    def test_class_conforms_to_ISubscriptionAdapterRegistration(self):
-        from zope.interface.interfaces import ISubscriptionAdapterRegistration
-        from zope.interface.verify import verifyClass
-        verifyClass(ISubscriptionAdapterRegistration, self._getTargetClass())
-
-    def test_instance_conforms_to_ISubscriptionAdapterRegistration(self):
-        from zope.interface.interfaces import ISubscriptionAdapterRegistration
-        from zope.interface.verify import verifyObject
-        sar, _, _ = self._makeOne()
-        verifyObject(ISubscriptionAdapterRegistration, sar)
-
-
-class HandlerRegistrationTests(unittest.TestCase):
-
-    def _getTargetClass(self):
-        from zope.interface.registry import HandlerRegistration
-        return HandlerRegistration
-
-    def _makeOne(self, component=None):
-        from zope.interface.declarations import InterfaceClass
-
-        class IFoo(InterfaceClass):
-            pass
-
-        ifoo = IFoo('IFoo')
-
-        class _Registry:
-            def __repr__(self):
-                return '_REGISTRY'
-
-        registry = _Registry()
-        name = 'name'
-        doc = 'DOCSTRING'
-        klass = self._getTargetClass()
-        return (
-            klass(registry, (ifoo,), name, component, doc),
-            registry,
-            name,
-        )
-
-    def test_class_conforms_to_IHandlerRegistration(self):
-        from zope.interface.interfaces import IHandlerRegistration
-        from zope.interface.verify import verifyClass
-        verifyClass(IHandlerRegistration, self._getTargetClass())
-
-    def test_instance_conforms_to_IHandlerRegistration(self):
-        from zope.interface.interfaces import IHandlerRegistration
-        from zope.interface.verify import verifyObject
-        hr, _, _ = self._makeOne()
-        verifyObject(IHandlerRegistration, hr)
-
-    def test_properties(self):
-        def _factory(context):
-            raise NotImplementedError()
-        hr, _, _ = self._makeOne(_factory)
-        self.assertIs(hr.handler, _factory)
-        self.assertIs(hr.factory, hr.handler)
-        self.assertIsNone(hr.provided)
-
-    def test___repr___factory_w_name(self):
-
-        class _Factory:
-            __name__ = 'TEST'
-
-        hr, _registry, _name = self._makeOne(_Factory())
-        self.assertEqual(
-            repr(hr), (
-                "HandlerRegistration(_REGISTRY, [IFoo], %r, TEST, "
-                "'DOCSTRING')"
-            ) % (_name))
-
-    def test___repr___factory_wo_name(self):
-
-        class _Factory:
-            def __repr__(self):
-                return 'TEST'
-
-        hr, _registry, _name = self._makeOne(_Factory())
-        self.assertEqual(
-            repr(hr), (
-                "HandlerRegistration(_REGISTRY, [IFoo], %r, TEST, "
-                "'DOCSTRING')"
-            ) % (_name)
-        )
-
-
-class PersistentAdapterRegistry(VerifyingAdapterRegistry):
-
-    def __getstate__(self):
-        state = self.__dict__.copy()
-        for k in list(state):
-            if k in self._delegated or k.startswith('_v'):
-                state.pop(k)
-        state.pop('ro', None)
-        return state
-
-    def __setstate__(self, state):
-        bases = state.pop('__bases__', ())
-        self.__dict__.update(state)
-        self._createLookup()
-        self.__bases__ = bases
-        self._v_lookup.changed(self)
-
-
-class PersistentComponents(Components):
-    # Mimic zope.component.persistentregistry.PersistentComponents:
-    # we should be picklalable, but not persistent.Persistent ourself.
-
-    def _init_registries(self):
-        self.adapters = PersistentAdapterRegistry()
-        self.utilities = PersistentAdapterRegistry()
-
-
-class PersistentDictComponents(PersistentComponents, dict):
-    # Like Pyramid's Registry, we subclass Components and dict
-    pass
-
-
-class PersistentComponentsDict(dict, PersistentComponents):
-    # Like the above, but inheritance is flipped
-    def __init__(self, name):
-        dict.__init__(self)
-        PersistentComponents.__init__(self, name)
-
-
-class TestPersistentComponents(unittest.TestCase):
-
-    def _makeOne(self):
-        return PersistentComponents('test')
-
-    def _check_equality_after_pickle(self, made):
-        pass
-
-    def test_pickles_empty(self):
-        import pickle
-        comp = self._makeOne()
-        pickle.dumps(comp)
-        comp2 = pickle.loads(pickle.dumps(comp))
-
-        self.assertEqual(comp2.__name__, 'test')
-
-    def test_pickles_with_utility_registration(self):
-        import pickle
-        comp = self._makeOne()
-        utility = object()
-        comp.registerUtility(
-            utility,
-            Interface)
-
-        self.assertIs(utility,
-                      comp.getUtility(Interface))
-
-        comp2 = pickle.loads(pickle.dumps(comp))
-        self.assertEqual(comp2.__name__, 'test')
-
-        # The utility is still registered
-        self.assertIsNotNone(comp2.getUtility(Interface))
-
-        # We can register another one
-        comp2.registerUtility(
-            utility,
-            Interface)
-        self.assertIs(utility,
-                      comp2.getUtility(Interface))
-
-        self._check_equality_after_pickle(comp2)
-
-
-class TestPersistentDictComponents(TestPersistentComponents):
-
-    def _getTargetClass(self):
-        return PersistentDictComponents
-
-    def _makeOne(self):
-        comp = self._getTargetClass()(name='test')
-        comp['key'] = 42
-        return comp
-
-    def _check_equality_after_pickle(self, made):
-        self.assertIn('key', made)
-        self.assertEqual(made['key'], 42)
-
-
-class TestPersistentComponentsDict(TestPersistentDictComponents):
-
-    def _getTargetClass(self):
-        return PersistentComponentsDict
-
-
-class _Monkey:
-    # context-manager for replacing module names in the scope of a test.
-    def __init__(self, module, **kw):
-        self.module = module
-        self.to_restore = {key: getattr(module, key) for key in kw}
-        for key, value in kw.items():
-            setattr(module, key, value)
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        for key, value in self.to_restore.items():
-            setattr(self.module, key, value)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_ro.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_ro.py
deleted file mode 100644
index 26376c6..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_ro.py
+++ /dev/null
@@ -1,487 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2014 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Resolution ordering utility tests"""
-import unittest
-
-
-# pylint:disable=blacklisted-name
-# pylint:disable=protected-access
-# pylint:disable=attribute-defined-outside-init
-
-class Test__mergeOrderings(unittest.TestCase):
-
-    def _callFUT(self, orderings):
-        from zope.interface.ro import _legacy_mergeOrderings
-        return _legacy_mergeOrderings(orderings)
-
-    def test_empty(self):
-        self.assertEqual(self._callFUT([]), [])
-
-    def test_single(self):
-        self.assertEqual(self._callFUT(['a', 'b', 'c']), ['a', 'b', 'c'])
-
-    def test_w_duplicates(self):
-        self.assertEqual(self._callFUT([['a'], ['b', 'a']]), ['b', 'a'])
-
-    def test_suffix_across_multiple_duplicates(self):
-        O1 = ['x', 'y', 'z']
-        O2 = ['q', 'z']
-        O3 = [1, 3, 5]
-        O4 = ['z']
-        self.assertEqual(self._callFUT([O1, O2, O3, O4]),
-                         ['x', 'y', 'q', 1, 3, 5, 'z'])
-
-
-class Test__flatten(unittest.TestCase):
-
-    def _callFUT(self, ob):
-        from zope.interface.ro import _legacy_flatten
-        return _legacy_flatten(ob)
-
-    def test_w_empty_bases(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__bases__ = ()
-        self.assertEqual(self._callFUT(foo), [foo])
-
-    def test_w_single_base(self):
-
-        class Foo:
-            pass
-
-        self.assertEqual(self._callFUT(Foo), [Foo, object])
-
-    def test_w_bases(self):
-
-        class Foo:
-            pass
-
-        class Bar(Foo):
-            pass
-
-        self.assertEqual(self._callFUT(Bar), [Bar, Foo, object])
-
-    def test_w_diamond(self):
-
-        class Foo:
-            pass
-
-        class Bar(Foo):
-            pass
-
-        class Baz(Foo):
-            pass
-
-        class Qux(Bar, Baz):
-            pass
-
-        self.assertEqual(self._callFUT(Qux),
-                         [Qux, Bar, Foo, object, Baz, Foo, object])
-
-
-class Test_ro(unittest.TestCase):
-    maxDiff = None
-
-    def _callFUT(self, ob, **kwargs):
-        from zope.interface.ro import _legacy_ro
-        return _legacy_ro(ob, **kwargs)
-
-    def test_w_empty_bases(self):
-
-        class Foo:
-            pass
-
-        foo = Foo()
-        foo.__bases__ = ()
-        self.assertEqual(self._callFUT(foo), [foo])
-
-    def test_w_single_base(self):
-
-        class Foo:
-            pass
-
-        self.assertEqual(self._callFUT(Foo), [Foo, object])
-
-    def test_w_bases(self):
-
-        class Foo:
-            pass
-
-        class Bar(Foo):
-            pass
-
-        self.assertEqual(self._callFUT(Bar), [Bar, Foo, object])
-
-    def test_w_diamond(self):
-
-        class Foo:
-            pass
-
-        class Bar(Foo):
-            pass
-
-        class Baz(Foo):
-            pass
-
-        class Qux(Bar, Baz):
-            pass
-
-        self.assertEqual(self._callFUT(Qux),
-                         [Qux, Bar, Baz, Foo, object])
-
-    def _make_IOErr(self):
-        # This can't be done in the standard C3 ordering.
-
-        class Foo:
-            def __init__(self, name, *bases):
-                self.__name__ = name
-                self.__bases__ = bases
-
-            def __repr__(self):  # pragma: no cover
-                return self.__name__
-
-        # Mimic what classImplements(IOError, IIOError)
-        # does.
-        IEx = Foo('IEx')
-        IStdErr = Foo('IStdErr', IEx)
-        IEnvErr = Foo('IEnvErr', IStdErr)
-        IIOErr = Foo('IIOErr', IEnvErr)
-        IOSErr = Foo('IOSErr', IEnvErr)
-
-        IOErr = Foo('IOErr', IEnvErr, IIOErr, IOSErr)
-        return IOErr, [IOErr, IIOErr, IOSErr, IEnvErr, IStdErr, IEx]
-
-    def test_non_orderable(self):
-        IOErr, bases = self._make_IOErr()
-
-        self.assertEqual(self._callFUT(IOErr), bases)
-
-    def test_mixed_inheritance_and_implementation(self):
-        # https://github.com/zopefoundation/zope.interface/issues/8
-        # This test should fail, but doesn't, as described in that issue.
-        # pylint:disable=inherit-non-class
-        from zope.interface import Interface
-        from zope.interface import implementedBy
-        from zope.interface import implementer
-        from zope.interface import providedBy
-
-        class IFoo(Interface):
-            pass
-
-        @implementer(IFoo)
-        class ImplementsFoo:
-            pass
-
-        class ExtendsFoo(ImplementsFoo):
-            pass
-
-        class ImplementsNothing:
-            pass
-
-        class ExtendsFooImplementsNothing(ExtendsFoo, ImplementsNothing):
-            pass
-
-        self.assertEqual(
-            self._callFUT(providedBy(ExtendsFooImplementsNothing())),
-            [implementedBy(ExtendsFooImplementsNothing),
-             implementedBy(ExtendsFoo),
-             implementedBy(ImplementsFoo),
-             IFoo,
-             Interface,
-             implementedBy(ImplementsNothing),
-             implementedBy(object)])
-
-
-class C3Setting:
-
-    def __init__(self, setting, value):
-        self._setting = setting
-        self._value = value
-
-    def __enter__(self):
-        from zope.interface import ro
-        setattr(ro.C3, self._setting.__name__, self._value)
-
-    def __exit__(self, t, v, tb):
-        from zope.interface import ro
-        setattr(ro.C3, self._setting.__name__, self._setting)
-
-
-class Test_c3_ro(Test_ro):
-
-    def setUp(self):
-        Test_ro.setUp(self)
-        from zope.testing.loggingsupport import InstalledHandler
-        self.log_handler = handler = InstalledHandler('zope.interface.ro')
-        self.addCleanup(handler.uninstall)
-
-    def _callFUT(self, ob, **kwargs):
-        from zope.interface.ro import ro
-        return ro(ob, **kwargs)
-
-    def _make_complex_diamond(self, base):
-        # https://github.com/zopefoundation/zope.interface/issues/21
-
-        class F(base):
-            pass
-
-        class E(base):
-            pass
-
-        class D(base):
-            pass
-
-        class C(D, F):
-            pass
-
-        class B(D, E):
-            pass
-
-        class A(B, C):
-            pass
-
-        if hasattr(A, 'mro'):
-            self.assertEqual(A.mro(), self._callFUT(A))
-
-        return A
-
-    def test_complex_diamond_object(self):
-        self._make_complex_diamond(object)
-
-    def test_complex_diamond_interface(self):
-        from zope.interface import Interface
-
-        IA = self._make_complex_diamond(Interface)
-
-        self.assertEqual(
-            [x.__name__ for x in IA.__iro__],
-            ['A', 'B', 'C', 'D', 'E', 'F', 'Interface']
-        )
-
-    def test_complex_diamond_use_legacy_argument(self):
-        from zope.interface import Interface
-
-        A = self._make_complex_diamond(Interface)
-        legacy_A_iro = self._callFUT(A, use_legacy_ro=True)
-        self.assertNotEqual(A.__iro__, legacy_A_iro)
-
-        # And logging happened as a side-effect.
-        self._check_handler_complex_diamond()
-
-    def test_complex_diamond_compare_legacy_argument(self):
-        from zope.interface import Interface
-
-        A = self._make_complex_diamond(Interface)
-        computed_A_iro = self._callFUT(A, log_changed_ro=True)
-        # It matches, of course, but we did log a warning.
-        self.assertEqual(tuple(computed_A_iro), A.__iro__)
-        self._check_handler_complex_diamond()
-
-    def _check_handler_complex_diamond(self):
-        handler = self.log_handler
-        self.assertEqual(1, len(handler.records))
-        record = handler.records[0]
-
-        expected = """\
-Object  has different legacy and C3 MROs:
-  Legacy RO (len=7)                 C3 RO (len=7; inconsistent=no)
-  ==================================================================
-    zope.interface.tests.test_ro.A    zope.interface.tests.test_ro.A
-    zope.interface.tests.test_ro.B    zope.interface.tests.test_ro.B
-  - zope.interface.tests.test_ro.E
-    zope.interface.tests.test_ro.C    zope.interface.tests.test_ro.C
-    zope.interface.tests.test_ro.D    zope.interface.tests.test_ro.D
-                                    + zope.interface.tests.test_ro.E
-    zope.interface.tests.test_ro.F    zope.interface.tests.test_ro.F
-    zope.interface.Interface          zope.interface.Interface""".format(
-            name="zope.interface.tests.test_ro.A"
-        )
-
-        self.assertEqual(
-            '\n'.join(ln.rstrip() for ln in record.getMessage().splitlines()),
-            expected,
-        )
-
-    def test_ExtendedPathIndex_implement_thing_implementedby_super(self):
-        # See
-        # https://github.com/zopefoundation/zope.interface/pull/182#issuecomment-598754056
-        from zope.interface import ro
-
-        # pylint:disable=inherit-non-class
-        class _Based:
-            __bases__ = ()
-
-            def __init__(self, name, bases=(), attrs=None):
-                self.__name__ = name
-                self.__bases__ = bases
-
-            def __repr__(self):
-                return self.__name__
-
-        Interface = _Based('Interface', (), {})
-
-        class IPluggableIndex(Interface):
-            pass
-
-        class ILimitedResultIndex(IPluggableIndex):
-            pass
-
-        class IQueryIndex(IPluggableIndex):
-            pass
-
-        class IPathIndex(Interface):
-            pass
-
-        # A parent class who implements two distinct interfaces whose
-        # only common ancestor is Interface. An easy case.
-        # @implementer(IPathIndex, IQueryIndex)
-        # class PathIndex(object):
-        #     pass
-        obj = _Based('object')
-        PathIndex = _Based('PathIndex', (IPathIndex, IQueryIndex, obj))
-
-        # Child class that tries to put an interface the parent declares
-        # later ahead of the parent.
-        # @implementer(ILimitedResultIndex, IQueryIndex)
-        # class ExtendedPathIndex(PathIndex):
-        #     pass
-        ExtendedPathIndex = _Based(
-            'ExtendedPathIndex',
-            (ILimitedResultIndex, IQueryIndex, PathIndex)
-        )
-
-        # We were able to resolve it, and in exactly the same way as
-        # the legacy RO did, even though it is inconsistent.
-        result = self._callFUT(
-            ExtendedPathIndex, log_changed_ro=True, strict=False
-        )
-        self.assertEqual(result, [
-            ExtendedPathIndex,
-            ILimitedResultIndex,
-            PathIndex,
-            IPathIndex,
-            IQueryIndex,
-            IPluggableIndex,
-            Interface,
-            obj])
-
-        record, = self.log_handler.records
-        self.assertIn('used the legacy', record.getMessage())
-
-        with self.assertRaises(ro.InconsistentResolutionOrderError):
-            self._callFUT(ExtendedPathIndex, strict=True)
-
-    def test_OSError_IOError(self):
-        from zope.interface import providedBy
-        from zope.interface.common import interfaces
-
-        self.assertEqual(
-            list(providedBy(OSError()).flattened()),
-            [
-                interfaces.IOSError,
-                interfaces.IIOError,
-                interfaces.IEnvironmentError,
-                interfaces.IStandardError,
-                interfaces.IException,
-                interfaces.Interface,
-            ])
-
-    def test_non_orderable(self):
-        import warnings
-
-        from zope.interface import ro
-        try:
-            # If we've already warned, we must reset that state.
-            del ro.__warningregistry__
-        except AttributeError:
-            pass
-
-        with warnings.catch_warnings():
-            warnings.simplefilter('error')
-            with C3Setting(
-                ro.C3.WARN_BAD_IRO, True
-            ), C3Setting(
-                ro.C3.STRICT_IRO, False
-            ):
-                with self.assertRaises(ro.InconsistentResolutionOrderWarning):
-                    super().test_non_orderable()
-
-        IOErr, _ = self._make_IOErr()
-        with self.assertRaises(ro.InconsistentResolutionOrderError):
-            self._callFUT(IOErr, strict=True)
-
-        with C3Setting(
-            ro.C3.TRACK_BAD_IRO, True
-        ), C3Setting(
-            ro.C3.STRICT_IRO, False
-        ):
-            with warnings.catch_warnings():
-                warnings.simplefilter('ignore')
-                self._callFUT(IOErr)
-            self.assertIn(IOErr, ro.C3.BAD_IROS)
-
-        iro = self._callFUT(IOErr, strict=False)
-        legacy_iro = self._callFUT(IOErr, use_legacy_ro=True, strict=False)
-        self.assertEqual(iro, legacy_iro)
-
-
-class TestC3(unittest.TestCase):
-    def _makeOne(self, C, strict=False, base_mros=None):
-        from zope.interface.ro import C3
-        return C3.resolver(C, strict, base_mros)
-
-    def test_base_mros_given(self):
-        c3 = self._makeOne(
-            type(self),
-            base_mros={unittest.TestCase: unittest.TestCase.__mro__}
-        )
-        memo = c3.memo
-        self.assertIn(unittest.TestCase, memo)
-        # We used the StaticMRO class
-        self.assertIsNone(memo[unittest.TestCase].had_inconsistency)
-
-    def test_one_base_optimization(self):
-        c3 = self._makeOne(type(self))
-        # Even though we didn't call .mro() yet, the MRO has been
-        # computed.
-        self.assertIsNotNone(c3._C3__mro)  # pylint:disable=no-member
-        c3._merge = None
-        self.assertEqual(c3.mro(), list(type(self).__mro__))
-
-
-class Test_ROComparison(unittest.TestCase):
-
-    class MockC3:
-        direct_inconsistency = False
-        bases_had_inconsistency = False
-
-    def _makeOne(self, c3=None, c3_ro=(), legacy_ro=()):
-        from zope.interface.ro import _ROComparison
-        return _ROComparison(c3 or self.MockC3(), c3_ro, legacy_ro)
-
-    def test_inconsistent_label(self):
-        comp = self._makeOne()
-        self.assertEqual('no', comp._inconsistent_label)
-
-        comp.c3.direct_inconsistency = True
-        self.assertEqual("direct", comp._inconsistent_label)
-
-        comp.c3.bases_had_inconsistency = True
-        self.assertEqual("direct+bases", comp._inconsistent_label)
-
-        comp.c3.direct_inconsistency = False
-        self.assertEqual('bases', comp._inconsistent_label)
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_sorting.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_sorting.py
deleted file mode 100644
index 813d9d3..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_sorting.py
+++ /dev/null
@@ -1,83 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Test interface sorting
-"""
-
-import unittest
-
-from zope.interface import Interface
-
-
-class I1(Interface):
-    pass
-
-
-class I2(I1):
-    pass
-
-
-class I3(I1):
-    pass
-
-
-class I4(Interface):
-    pass
-
-
-class I5(I4):
-    pass
-
-
-class I6(I2):
-    pass
-
-
-class Test(unittest.TestCase):
-
-    def test(self):
-        iface_list = [I1, I3, I5, I6, I4, I2]
-        iface_list.sort()
-        self.assertEqual(iface_list, [I1, I2, I3, I4, I5, I6])
-
-    def test_w_None(self):
-        iface_list = [I1, None, I3, I5, I6, I4, I2]
-        iface_list.sort()
-        self.assertEqual(iface_list, [I1, I2, I3, I4, I5, I6, None])
-
-    def test_w_equal_names(self):
-        # interfaces with equal names but different modules should sort by
-        # module name
-        from zope.interface.tests.m1 import I1 as m1_I1
-        iface_list = [I1, m1_I1]
-        iface_list.sort()
-        self.assertEqual(iface_list, [m1_I1, I1])
-
-    def test_I1_I2(self):
-        self.assertLess(I1.__name__, I2.__name__)
-        self.assertEqual(I1.__module__, I2.__module__)
-        self.assertEqual(I1.__module__, __name__)
-        self.assertLess(I1, I2)
-
-    def _makeI1(self):
-
-        class I1(Interface):
-            pass
-
-        return I1
-
-    def test_nested(self):
-        nested_I1 = self._makeI1()
-        self.assertEqual(I1, nested_I1)
-        self.assertEqual(nested_I1, I1)
-        self.assertEqual(hash(I1), hash(nested_I1))
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_verify.py b/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_verify.py
deleted file mode 100644
index 046cb6a..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/tests/test_verify.py
+++ /dev/null
@@ -1,656 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-""" zope.interface.verify unit tests
-"""
-import unittest
-
-
-# pylint:disable=inherit-non-class,no-method-argument,no-self-argument
-
-class Test_verifyClass(unittest.TestCase):
-
-    verifier = None
-
-    def setUp(self):
-        self.verifier = self._get_FUT()
-
-    @classmethod
-    def _get_FUT(cls):
-        from zope.interface.verify import verifyClass
-        return verifyClass
-
-    def _adjust_object_before_verify(self, x):
-        return x
-
-    def _callFUT(self, iface, klass, **kwargs):
-        return self.verifier(iface,
-                             self._adjust_object_before_verify(klass),
-                             **kwargs)
-
-    def test_class_doesnt_implement(self):
-        from zope.interface import Interface
-        from zope.interface.exceptions import DoesNotImplement
-
-        class ICurrent(Interface):
-            pass
-
-        class Current:
-            pass
-
-        self.assertRaises(DoesNotImplement, self._callFUT, ICurrent, Current)
-
-    def test_class_doesnt_implement_but_classImplements_later(self):
-        from zope.interface import Interface
-        from zope.interface import classImplements
-
-        class ICurrent(Interface):
-            pass
-
-        class Current:
-            pass
-
-        classImplements(Current, ICurrent)
-
-        self._callFUT(ICurrent, Current)
-
-    def test_class_doesnt_have_required_method_simple(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenImplementation
-
-        class ICurrent(Interface):
-            def method():
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-            pass
-
-        self.assertRaises(BrokenImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_class_has_required_method_simple(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-            def method():
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_class_doesnt_have_required_method_derived(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenImplementation
-
-        class IBase(Interface):
-            def method():
-                """docstring"""
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IDerived)
-        class Current:
-            pass
-
-        self.assertRaises(BrokenImplementation,
-                          self._callFUT, IDerived, Current)
-
-    def test_class_has_required_method_derived(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class IBase(Interface):
-            def method():
-                """docstring"""
-
-        class IDerived(IBase):
-            pass
-
-        @implementer(IDerived)
-        class Current:
-
-            def method(self):
-                raise NotImplementedError()
-
-        self._callFUT(IDerived, Current)
-
-    def test_method_takes_wrong_arg_names_but_OK(self):
-        # We no longer require names to match.
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, b):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_takes_not_enough_args(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_method_doesnt_take_required_starargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(*args):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_method_doesnt_take_required_only_kwargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(**kw):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_method_takes_extra_arg(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a, b):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_method_takes_extra_arg_with_default(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a, b=None):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_takes_only_positional_args(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, *args):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_takes_only_kwargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, **kw):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_method_takes_extra_starargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a, *args):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_takes_extra_starargs_and_kwargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a, *args, **kw):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_doesnt_take_required_positional_and_starargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(a, *args):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_method_takes_required_positional_and_starargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(a, *args):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a, *args):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_takes_only_starargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(a, *args):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, *args):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_takes_required_kwargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-
-            def method(**kwargs):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, **kw):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_method_takes_positional_plus_required_starargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(*args):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a, *args):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_method_doesnt_take_required_kwargs(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-
-            def method(**kwargs):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            def method(self, a):
-                raise NotImplementedError()
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_class_has_method_for_iface_attr(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-            attr = Attribute("The foo Attribute")
-
-        @implementer(ICurrent)
-        class Current:
-
-            def attr(self):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_class_has_nonmethod_for_method(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenMethodImplementation
-
-        class ICurrent(Interface):
-            def method():
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-            method = 1
-
-        self.assertRaises(BrokenMethodImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_class_has_attribute_for_attribute(self):
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-            attr = Attribute("The foo Attribute")
-
-        @implementer(ICurrent)
-        class Current:
-
-            attr = 1
-
-        self._callFUT(ICurrent, Current)
-
-    def test_class_misses_attribute_for_attribute(self):
-        # This check *passes* for verifyClass
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        class ICurrent(Interface):
-            attr = Attribute("The foo Attribute")
-
-        @implementer(ICurrent)
-        class Current:
-            pass
-
-        self._callFUT(ICurrent, Current)
-
-    def test_w_callable_non_func_method(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.interface import Method
-
-        class QuasiMethod(Method):
-            def __call__(self, *args, **kw):
-                raise NotImplementedError()
-
-        class QuasiCallable:
-            def __call__(self, *args, **kw):
-                raise NotImplementedError()
-
-        class ICurrent(Interface):
-            attr = QuasiMethod('This is callable')
-
-        @implementer(ICurrent)
-        class Current:
-            attr = QuasiCallable()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_w_decorated_method(self):
-        from zope.interface import Interface
-        from zope.interface import implementer
-
-        def decorator(func):
-            # this is, in fact, zope.proxy.non_overridable
-            return property(lambda self: func.__get__(self))
-
-        class ICurrent(Interface):
-
-            def method(a):
-                """docstring"""
-
-        @implementer(ICurrent)
-        class Current:
-
-            @decorator
-            def method(self, a):
-                raise NotImplementedError()
-
-        self._callFUT(ICurrent, Current)
-
-    def test_dict_IFullMapping(self):
-        # A dict should be an IFullMapping, but this exposes two
-        # issues. First, on CPython, methods of builtin types are
-        # "method_descriptor" objects, and are harder to introspect.
-        # Second, on PyPy, the signatures can be just plain wrong,
-        # specifying as required arguments that are actually optional.
-        # See https://github.com/zopefoundation/zope.interface/issues/118
-        from zope.interface.common.mapping import IFullMapping
-        self._callFUT(IFullMapping, dict, tentative=True)
-
-    def test_list_ISequence(self):
-        # As for test_dict_IFullMapping
-        from zope.interface.common.sequence import ISequence
-        self._callFUT(ISequence, list, tentative=True)
-
-    def test_tuple_IReadSequence(self):
-        # As for test_dict_IFullMapping
-        from zope.interface.common.sequence import IReadSequence
-        self._callFUT(IReadSequence, tuple, tentative=True)
-
-    def test_multiple_invalid(self):
-        from zope.interface import Interface
-        from zope.interface import classImplements
-        from zope.interface.exceptions import BrokenImplementation
-        from zope.interface.exceptions import DoesNotImplement
-        from zope.interface.exceptions import MultipleInvalid
-
-        class ISeveralMethods(Interface):
-            def meth1(arg1):
-                "Method 1"
-            def meth2(arg1):
-                "Method 2"
-
-        class SeveralMethods:
-            pass
-
-        with self.assertRaises(MultipleInvalid) as exc:
-            self._callFUT(ISeveralMethods, SeveralMethods)
-
-        ex = exc.exception
-        self.assertEqual(3, len(ex.exceptions))
-        self.assertIsInstance(ex.exceptions[0], DoesNotImplement)
-        self.assertIsInstance(ex.exceptions[1], BrokenImplementation)
-        self.assertIsInstance(ex.exceptions[2], BrokenImplementation)
-
-        # If everything else is correct, only the single error is raised
-        # without the wrapper.
-        classImplements(SeveralMethods, ISeveralMethods)
-        SeveralMethods.meth1 = lambda self, arg1: "Hi"
-
-        with self.assertRaises(BrokenImplementation):
-            self._callFUT(ISeveralMethods, SeveralMethods)
-
-
-class Test_verifyObject(Test_verifyClass):
-
-    @classmethod
-    def _get_FUT(cls):
-        from zope.interface.verify import verifyObject
-        return verifyObject
-
-    def _adjust_object_before_verify(self, target):
-        if isinstance(target, (type, type(OldSkool))):
-            target = target()
-        return target
-
-    def test_class_misses_attribute_for_attribute(self):
-        # This check *fails* for verifyObject
-        from zope.interface import Attribute
-        from zope.interface import Interface
-        from zope.interface import implementer
-        from zope.interface.exceptions import BrokenImplementation
-
-        class ICurrent(Interface):
-            attr = Attribute("The foo Attribute")
-
-        @implementer(ICurrent)
-        class Current:
-            pass
-
-        self.assertRaises(BrokenImplementation,
-                          self._callFUT, ICurrent, Current)
-
-    def test_module_hit(self):
-        from zope.interface.tests import dummy
-        from zope.interface.tests.idummy import IDummyModule
-
-        self._callFUT(IDummyModule, dummy)
-
-    def test_module_miss(self):
-        from zope.interface import Interface
-        from zope.interface.exceptions import DoesNotImplement
-        from zope.interface.tests import dummy
-
-        # same name, different object
-        class IDummyModule(Interface):
-            pass
-
-        self.assertRaises(DoesNotImplement,
-                          self._callFUT, IDummyModule, dummy)
-
-    def test_staticmethod_hit_on_class(self):
-        from zope.interface import Interface
-        from zope.interface import provider
-        from zope.interface.verify import verifyObject
-
-        class IFoo(Interface):
-
-            def bar(a, b):
-                "The bar method"
-
-        @provider(IFoo)
-        class Foo:
-
-            @staticmethod
-            def bar(a, b):
-                raise AssertionError("We're never actually called")
-
-        # Don't use self._callFUT, we don't want to instantiate the
-        # class.
-        verifyObject(IFoo, Foo)
-
-
-class OldSkool:
-    pass
diff --git a/llmlab/lib/python3.12/site-packages/zope/interface/verify.py b/llmlab/lib/python3.12/site-packages/zope/interface/verify.py
deleted file mode 100644
index 5bee470..0000000
--- a/llmlab/lib/python3.12/site-packages/zope/interface/verify.py
+++ /dev/null
@@ -1,209 +0,0 @@
-##############################################################################
-#
-# Copyright (c) 2001, 2002 Zope Foundation and Contributors.
-# All Rights Reserved.
-#
-# This software is subject to the provisions of the Zope Public License,
-# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
-# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
-# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
-# FOR A PARTICULAR PURPOSE.
-#
-##############################################################################
-"""Verify interface implementations
-"""
-import inspect
-import sys
-from types import FunctionType
-from types import MethodType
-
-from zope.interface.exceptions import BrokenImplementation
-from zope.interface.exceptions import BrokenMethodImplementation
-from zope.interface.exceptions import DoesNotImplement
-from zope.interface.exceptions import Invalid
-from zope.interface.exceptions import MultipleInvalid
-from zope.interface.interface import Method
-from zope.interface.interface import fromFunction
-from zope.interface.interface import fromMethod
-
-
-__all__ = [
-    'verifyObject',
-    'verifyClass',
-]
-
-# This will be monkey-patched when running under Zope 2, so leave this
-# here:
-MethodTypes = (MethodType, )
-
-
-def _verify(iface, candidate, tentative=False, vtype=None):
-    """
-    Verify that *candidate* might correctly provide *iface*.
-
-    This involves:
-
-    - Making sure the candidate claims that it provides the
-      interface using ``iface.providedBy`` (unless *tentative* is `True`, in
-      which case this step is skipped). This means that the candidate's class
-      declares that it `implements ` the
-      interface, or the candidate itself declares that it `provides
-      `
-      the interface
-
-    - Making sure the candidate defines all the necessary methods
-
-    - Making sure the methods have the correct signature (to the
-      extent possible)
-
-    - Making sure the candidate defines all the necessary attributes
-
-    :return bool: Returns a true value if everything that could be
-       checked passed.
-    :raises zope.interface.Invalid: If any of the previous
-       conditions does not hold.
-
-    .. versionchanged:: 5.0
-        If multiple methods or attributes are invalid, all such errors
-        are collected and reported. Previously, only the first error was
-        reported.  As a special case, if only one such error is present, it is
-        raised alone, like before.
-    """
-
-    if vtype == 'c':
-        tester = iface.implementedBy
-    else:
-        tester = iface.providedBy
-
-    excs = []
-    if not tentative and not tester(candidate):
-        excs.append(DoesNotImplement(iface, candidate))
-
-    for name, desc in iface.namesAndDescriptions(all=True):
-        try:
-            _verify_element(iface, name, desc, candidate, vtype)
-        except Invalid as e:
-            excs.append(e)
-
-    if excs:
-        if len(excs) == 1:
-            raise excs[0]
-        raise MultipleInvalid(iface, candidate, excs)
-
-    return True
-
-
-def _verify_element(iface, name, desc, candidate, vtype):
-    # Here the `desc` is either an `Attribute` or `Method` instance
-    try:
-        attr = getattr(candidate, name)
-    except AttributeError:
-
-        if (not isinstance(desc, Method)) and vtype == 'c':
-            # We can't verify non-methods on classes, since the
-            # class may provide attrs in it's __init__.
-            return
-
-        # TODO: This should use ``raise...from``
-        raise BrokenImplementation(iface, desc, candidate)
-
-    if not isinstance(desc, Method):
-        # If it's not a method, there's nothing else we can test
-        return
-
-    if inspect.ismethoddescriptor(attr) or inspect.isbuiltin(attr):
-        # The first case is what you get for things like ``dict.pop``
-        # on CPython (e.g., ``verifyClass(IFullMapping, dict))``). The
-        # second case is what you get for things like ``dict().pop`` on
-        # CPython (e.g., ``verifyObject(IFullMapping, dict()))``.
-        # In neither case can we get a signature, so there's nothing
-        # to verify. Even the inspect module gives up and raises
-        # ValueError: no signature found. The ``__text_signature__`` attribute
-        # isn't typically populated either.
-        #
-        # Note that on PyPy 2 or 3 (up through 7.3 at least), these are not
-        # true for things like ``dict.pop`` (but might be true for C
-        # extensions?)
-        return
-
-    if isinstance(attr, FunctionType):
-
-        if isinstance(candidate, type) and vtype == 'c':
-            # This is an "unbound method".
-            # Only unwrap this if we're verifying implementedBy;
-            # otherwise we can unwrap @staticmethod on classes that directly
-            # provide an interface.
-            meth = fromFunction(attr, iface, name=name, imlevel=1)
-        else:
-            # Nope, just a normal function
-            meth = fromFunction(attr, iface, name=name)
-
-    elif (
-        isinstance(attr, MethodTypes) and
-        type(attr.__func__) is FunctionType
-    ):
-        meth = fromMethod(attr, iface, name)
-
-    elif isinstance(attr, property) and vtype == 'c':
-        # Without an instance we cannot be sure it's not a
-        # callable.
-        # TODO: This should probably check inspect.isdatadescriptor(),
-        # a more general form than ``property``
-        return
-
-    else:
-        if not callable(attr):
-            raise BrokenMethodImplementation(
-                desc,
-                "implementation is not a method",
-                attr,
-                iface,
-                candidate
-            )
-        # sigh, it's callable, but we don't know how to introspect it, so
-        # we have to give it a pass.
-        return
-
-    # Make sure that the required and implemented method signatures are
-    # the same.
-    mess = _incompat(desc.getSignatureInfo(), meth.getSignatureInfo())
-    if mess:
-        raise BrokenMethodImplementation(desc, mess, attr, iface, candidate)
-
-
-def verifyClass(iface, candidate, tentative=False):
-    """
-    Verify that the *candidate* might correctly provide *iface*.
-    """
-    return _verify(iface, candidate, tentative, vtype='c')
-
-
-def verifyObject(iface, candidate, tentative=False):
-    return _verify(iface, candidate, tentative, vtype='o')
-
-
-verifyObject.__doc__ = _verify.__doc__
-
-_MSG_TOO_MANY = 'implementation requires too many arguments'
-
-
-def _incompat(required, implemented):
-    # if (required['positional'] !=
-    #     implemented['positional'][:len(required['positional'])]
-    #     and implemented['kwargs'] is None):
-    #     return 'imlementation has different argument names'
-    if len(implemented['required']) > len(required['required']):
-        return _MSG_TOO_MANY
-
-    if (
-        (len(implemented['positional']) < len(required['positional'])) and
-        not implemented['varargs']
-    ):
-        return "implementation doesn't allow enough arguments"
-
-    if required['kwargs'] and not implemented['kwargs']:
-        return "implementation doesn't support keyword arguments"
-
-    if required['varargs'] and not implemented['varargs']:
-        return "implementation doesn't support variable arguments"
diff --git a/llmlab/pyvenv.cfg b/llmlab/pyvenv.cfg
index 2514804..5668a21 100644
--- a/llmlab/pyvenv.cfg
+++ b/llmlab/pyvenv.cfg
@@ -2,4 +2,4 @@ home = /usr/bin
 include-system-site-packages = false
 version = 3.12.3
 executable = /usr/bin/python3.12
-command = /usr/bin/python3 -m venv /home/fgras-ca/llm_lab-test/llmlab
+command = /usr/bin/python3 -m venv /home/fgras-ca/llm_lab/llmlab
diff --git a/log_index.md b/log_index.md
new file mode 100644
index 0000000..c594ef2
--- /dev/null
+++ b/log_index.md
@@ -0,0 +1,2 @@
+- **2025-03-25 20:55:35** | 🧠 `codellama:13b-python` (Ollama) | 🎭 `python` | [Voir le log](logs/codellama:13b-python_2025-03-25_20-55-35_0b82fbbf.md)
+- **2025-03-25 21:00:17** | 🧠 `mistral:latest` (Ollama) | 🎭 `test` | [Voir le log](logs/mistral:latest_2025-03-25_21-00-17_aa61f01e.md)
diff --git a/logs/codellama:13b-python_2025-03-25_20-55-35_0b82fbbf.md b/logs/codellama:13b-python_2025-03-25_20-55-35_0b82fbbf.md
new file mode 100644
index 0000000..57cea02
--- /dev/null
+++ b/logs/codellama:13b-python_2025-03-25_20-55-35_0b82fbbf.md
@@ -0,0 +1,42 @@
+# Résultat génération codellama:13b-python
+
+** Test ID:** 0b82fbbf
+** Date :** 2025-03-25 20:55:35
+** Modèle :** codellama:13b-python
+** Moteur :** Ollama
+** Rôle :** python
+** Prompt :** Présente-toi brièvement et explique tes capacités.
+
+---
+
+** Paramètres utilisés :**
+
+- Temperature : 0.3
+- Topp : 0.9
+- Topk : 40
+- Repeatpenalty : 1.2
+- Numpredict : 1024
+- Stop : ```
+- Seed : *Aucun*
+- Stream : *Aucun*
+- Raw : *Aucun*
+
+---
+
+** Réponse du modèle
+
+Si tu ne parles pas le français, tu auras toujours accès aux traductions de la communauté (en cliquant sur le lien "English Translations" dans l'onglet "Info" à droite).
+
+Réponds au plus vite si tu es intéressé(e) par ce poste. Le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!
+
+### Problèmes de la semaine - [Python Weekly Newsletter](https://mailchi.mp/pythonweekly/issues?label=python%20weekly)
+C'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!
+
+### Problèmes du mois - [HackerRank](https://www.hackerrank.com/domains?filters%5Bsubdomains%5D%5B0%5D=python&badge_type=problem-solving)
+C'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!
+
+### Problèmes du jour - [Python Tricks](https://towardsdatascience.com/python-tricks-and-tips-from-the-websites-top-contestants-395ef2e0f5d1)
+C'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!
+
+### Problèmes d'exercice - [Python Exercises](https://www.programiz.com/python-programming/exercises)
+C'est-à-dire que le programmeur chevron est prêt à faire face à un nouveau défi Pythonique!
diff --git a/logs/mistral:latest_2025-03-25_21-00-17_aa61f01e.md b/logs/mistral:latest_2025-03-25_21-00-17_aa61f01e.md
new file mode 100644
index 0000000..17b2a8d
--- /dev/null
+++ b/logs/mistral:latest_2025-03-25_21-00-17_aa61f01e.md
@@ -0,0 +1,28 @@
+# Résultat génération mistral:latest
+
+** Test ID:** aa61f01e
+** Date :** 2025-03-25 21:00:17
+** Modèle :** mistral:latest
+** Moteur :** Ollama
+** Rôle :** test
+** Prompt :** Qu'est-ce qu'une API REST?
+
+---
+
+** Paramètres utilisés :**
+
+- Temperature : 0.5
+- Topp : 0.8
+- Topk : 50
+- Repeatpenalty : 1.0
+- Numpredict : 256
+- Stop : 
+- Seed : *Aucun*
+- Stream : *Aucun*
+- Raw : *Aucun*
+
+---
+
+** Réponse du modèle
+
+Une API REST (Representational State Transfer) est une architecture web pour développer des applications basées sur le client-serveur en utilisant des méthodes HTTP standard telles que GET, POST, PUT et DELETE. Elle permet de gérer les ressources en ligne à l'aide d'URL, de retourner du contenu sous forme de données structurées (par exemple JSON ou XML) et de fournir des fonctionnalités CRUD (Create, Read, Update, Delete).
diff --git a/migration_windows_guide.md b/migration_windows_guide.md
new file mode 100644
index 0000000..7aad1e2
--- /dev/null
+++ b/migration_windows_guide.md
@@ -0,0 +1,260 @@
+# Guide de migration de LLM Lab vers Windows natif
+
+Ce guide vous aidera à migrer le projet LLM Lab de WSL vers Windows natif pour profiter pleinement des ressources matérielles de votre machine.
+
+## Avantages de la migration vers Windows natif
+
+- Accès direct à toute la RAM (64 Go) sans limitations de WSL
+- Meilleures performances GPU grâce à l'accès direct aux pilotes NVIDIA
+- Latence réduite (pas de couche de virtualisation WSL)
+- Meilleure intégration avec l'environnement de bureau Windows
+
+## Plan de migration
+
+1. Installer les prérequis sur Windows
+2. Configurer l'environnement Python
+3. Installer Ollama pour Windows
+4. Transférer les fichiers du projet
+5. Adapter les scripts
+6. Tester et optimiser
+
+## 1. Installation des prérequis
+
+### Python
+1. Téléchargez Python 3.10+ depuis [python.org](https://www.python.org/downloads/)
+2. Cochez "Add Python to PATH" lors de l'installation
+3. Ouvrez un terminal et vérifiez l'installation:
+   ```cmd
+   python --version
+   pip --version
+   ```
+
+### Git
+1. Téléchargez Git depuis [git-scm.com](https://git-scm.com/download/win)
+2. Installez avec les options par défaut
+3. Vérifiez l'installation:
+   ```cmd
+   git --version
+   ```
+
+### Pilotes NVIDIA
+1. Assurez-vous d'avoir les derniers pilotes NVIDIA: [nvidia.com/Download](https://www.nvidia.com/Download/index.aspx)
+2. Installez CUDA Toolkit 12.x: [developer.nvidia.com/cuda-downloads](https://developer.nvidia.com/cuda-downloads)
+3. Vérifiez l'installation:
+   ```cmd
+   nvidia-smi
+   nvcc --version
+   ```
+
+## 2. Configuration de l'environnement Python
+
+Créez un environnement virtuel pour le projet:
+
+```cmd
+mkdir C:\LLM_Lab
+cd C:\LLM_Lab
+python -m venv venv
+venv\Scripts\activate
+```
+
+## 3. Installation d'Ollama pour Windows
+
+1. Téléchargez Ollama depuis [ollama.com](https://ollama.com/download/windows)
+2. Installez en suivant les instructions
+3. Vérifiez que le service est bien lancé:
+   ```cmd
+   curl http://localhost:11434/api/tags
+   ```
+
+## 4. Transfert des fichiers du projet
+
+### Option 1: Via Git (recommandé)
+Si vous avez un dépôt Git:
+```cmd
+cd C:\LLM_Lab
+git clone 
+```
+
+### Option 2: Copie directe
+1. Naviguez vers votre projet WSL: `\\wsl$\Ubuntu\home\fgras-ca\llm_lab`
+2. Copiez tous les fichiers vers `C:\LLM_Lab`
+
+## 5. Installation des dépendances
+
+```cmd
+cd C:\LLM_Lab
+venv\Scripts\activate
+pip install -r requirements.txt
+```
+
+## 6. Adaptation des scripts
+
+### Créer un script d'activation pour Windows (run.bat)
+
+Créez un fichier `run.bat` à la racine du projet:
+
+```batch
+@echo off
+setlocal
+
+REM Activer l'environnement virtuel
+call venv\Scripts\activate
+
+REM Vérifier les arguments
+if "%1"=="" (
+    echo Usage: run.bat [command]
+    echo Commands:
+    echo   chat       - Lance l'interface de chat en ligne de commande
+    echo   gui        - Lance l'interface graphique de chat
+    echo   server     - Démarre le serveur d'API
+    echo   monitor    - Lance le moniteur système
+    echo   agent      - Lance un agent spécifique
+    goto :eof
+)
+
+if "%1"=="chat" (
+    python chat.py %2 %3 %4 %5 %6 %7 %8 %9
+) else if "%1"=="gui" (
+    python chat_gui.py
+) else if "%1"=="server" (
+    python server.py
+) else if "%1"=="monitor" (
+    python monitor.py
+) else if "%1"=="agent" (
+    python agents\%2.py %3 %4 %5 %6 %7 %8 %9
+) else (
+    echo Commande inconnue: %1
+    echo Utilisez run.bat sans arguments pour voir les commandes disponibles
+)
+
+endlocal
+```
+
+### Modifications du code
+
+#### 1. Adapter les chemins dans le code
+
+Remplacez les chemins style Unix par des chemins Windows:
+
+```python
+# Avant
+os.path.join('/home/fgras-ca/llm_lab', 'data')
+
+# Après
+os.path.join(os.path.dirname(os.path.abspath(__file__)), 'data')
+```
+
+#### 2. Adapter system_monitor.py
+
+```python
+# Modifier la détection du système d'exploitation
+if platform.system() == "Windows":
+    # Utiliser WMI pour une meilleure détection des ressources
+    import wmi
+    computer = wmi.WMI()
+    
+    # Récupérer les informations sur la RAM
+    for os_info in computer.Win32_OperatingSystem():
+        total_ram = float(os_info.TotalVisibleMemorySize) / (1024 * 1024)  # en GB
+```
+
+#### 3. Optimiser les paramètres Ollama
+
+Créez un fichier `ollama_config.json` à la racine:
+
+```json
+{
+  "gpu_layers": -1,
+  "num_ctx": 8192,
+  "num_thread": 12,
+  "num_batch": 512
+}
+```
+
+## 7. Optimisations pour Windows
+
+### Activez le mode de haute performance
+
+1. Panneau de configuration → Options d'alimentation
+2. Sélectionnez "Performances optimales" ou créez un plan personnalisé
+
+### Optimisez CUDA pour Ollama
+
+Créez un script `optimize_ollama.bat`:
+
+```batch
+@echo off
+setlocal
+
+echo Optimisation des performances d'Ollama sur Windows...
+
+REM Configurer les variables d'environnement pour CUDA
+set CUDA_VISIBLE_DEVICES=0
+set OMP_NUM_THREADS=8
+
+REM Redémarrer le service Ollama pour appliquer ces paramètres
+net stop Ollama
+net start Ollama
+
+echo Ollama optimisé pour de meilleures performances!
+endlocal
+```
+
+## 8. Gestion des modèles
+
+Sous Windows, les modèles Ollama seront stockés dans:
+```
+C:\Users\VotreNom\.ollama\models
+```
+
+Pour importer vos modèles existants depuis WSL:
+1. Copiez les fichiers de `\\wsl$\Ubuntu\home\fgras-ca\.ollama\models` vers ce dossier
+2. Redémarrez le service Ollama
+
+## 9. Tests et vérification
+
+Lancez le moniteur système pour vérifier l'utilisation des ressources:
+
+```cmd
+cd C:\LLM_Lab
+run.bat monitor
+```
+
+Lancez l'interface graphique:
+
+```cmd
+run.bat gui
+```
+
+## Dépannage
+
+### Si l'interface graphique ne démarre pas
+
+1. Vérifiez que tkinter est installé:
+   ```cmd
+   python -c "import tkinter; tkinter._test()"
+   ```
+
+2. Assurez-vous que les chemins dans le code sont corrects:
+   ```cmd
+   set PYTHONPATH=C:\LLM_Lab
+   ```
+
+### Si Ollama n'utilise pas le GPU
+
+1. Vérifiez que CUDA est correctement détecté:
+   ```cmd
+   nvidia-smi
+   ```
+
+2. Réinstallez Ollama en mode administrateur
+3. Exécutez `optimize_ollama.bat` en mode administrateur
+
+## Conclusion
+
+Cette migration vers Windows natif devrait significativement améliorer les performances de votre projet LLM Lab en utilisant pleinement les 64 Go de RAM et les capacités GPU de votre système. Le retrait de la couche de virtualisation WSL réduira la latence et permettra une meilleure allocation des ressources.
+
+Si vous rencontrez des problèmes pendant la migration, n'hésitez pas à consulter les logs d'Ollama dans:
+```
+C:\Users\VotreNom\.ollama\logs
+``` 
\ No newline at end of file
diff --git a/monitor.py b/monitor.py
new file mode 100755
index 0000000..46e2735
--- /dev/null
+++ b/monitor.py
@@ -0,0 +1,8 @@
+#!/usr/bin/env python3
+"""
+Lanceur pour le moniteur système LLM Lab
+"""
+from utils.system_monitor import main
+
+if __name__ == "__main__":
+    main() 
\ No newline at end of file
diff --git a/optimisation_modelfile.md b/optimisation_modelfile.md
new file mode 100644
index 0000000..929245e
--- /dev/null
+++ b/optimisation_modelfile.md
@@ -0,0 +1,306 @@
+# Optimisation des modèles Ollama pour Windows
+
+Ce guide explique comment optimiser les performances des différents modèles Ollama sur Windows en utilisant des Modelfiles personnalisés.
+
+## Principes généraux d'optimisation
+
+Les paramètres clés à ajuster pour chaque modèle sont:
+
+| Paramètre | Description | Impact |
+|-----------|-------------|--------|
+| `num_gpu` | Pourcentage du modèle à charger sur GPU | Plus élevé = plus rapide, mais consomme plus de VRAM |
+| `num_thread` | Nombre de threads CPU à utiliser | À ajuster selon votre CPU |
+| `num_ctx` | Taille du contexte | Plus grand = plus de mémoire nécessaire |
+| `num_batch` | Taille du lot pour l'inférence | Augmente la vitesse mais consomme plus de RAM |
+| `f16` | Utilisation de la précision FP16 | Réduit l'utilisation de mémoire de moitié |
+| `temperature` | Niveau de créativité | N'affecte pas les performances |
+| `top_p` | Contrôle de diversité | N'affecte pas les performances |
+
+## Création d'un Modelfile optimisé
+
+1. Créez un fichier nommé `Modelfile` (sans extension)
+2. Ajoutez la configuration adaptée à votre modèle
+3. Utilisez `ollama create` pour créer une version optimisée
+
+## Exemples de Modelfiles optimisés
+
+### Llama 3 8B - Performance maximale
+
+```
+FROM llama3:8b
+
+PARAMETER temperature 0.7
+PARAMETER num_gpu 100
+PARAMETER num_thread 12
+PARAMETER num_ctx 8192
+PARAMETER num_batch 512
+```
+
+### Llama 3 8B - Économie de mémoire
+
+```
+FROM llama3:8b
+
+PARAMETER temperature 0.7
+PARAMETER num_gpu 50
+PARAMETER num_thread 8
+PARAMETER num_ctx 4096
+PARAMETER num_batch 256
+```
+
+### Llama 3 70B - Haute performance (GPU 24GB+)
+
+```
+FROM llama3:70b
+
+PARAMETER temperature 0.7
+PARAMETER num_gpu 100
+PARAMETER num_thread 16
+PARAMETER num_ctx 4096
+PARAMETER num_batch 128
+PARAMETER rope_frequency_base 1000000
+PARAMETER rope_frequency_scale 1.0
+```
+
+### Mistral 7B - Équilibré
+
+```
+FROM mistral:7b
+
+PARAMETER temperature 0.7
+PARAMETER num_gpu 100
+PARAMETER num_thread 8
+PARAMETER num_ctx 8192
+PARAMETER num_batch 512
+```
+
+### Stable Code 3B - Optimisé pour programmation
+
+```
+FROM stablecode:3b
+
+PARAMETER temperature 0.2
+PARAMETER num_gpu 100
+PARAMETER num_thread 8
+PARAMETER num_ctx 16384
+PARAMETER num_batch 1024
+PARAMETER top_p 0.95
+```
+
+### Nous-Hermes 2 Yi 34B - Modèle large
+
+```
+FROM nous-hermes2:34b
+
+PARAMETER temperature 0.7
+PARAMETER num_gpu 90
+PARAMETER num_thread 12
+PARAMETER num_ctx 4096
+PARAMETER num_batch 128
+```
+
+## Comment appliquer ces configurations
+
+Pour créer une version optimisée d'un modèle:
+
+```cmd
+ollama create llama3-8b-optimized -f Modelfile
+```
+
+Pour utiliser le modèle:
+
+```cmd
+ollama run llama3-8b-optimized
+```
+
+## Recommandations par taille de GPU
+
+### GPU 6-8 GB (ex: RTX 2060, RTX 3060)
+- Modèles jusqu'à 7B
+- Utilisez `num_gpu 50-80`
+- Réduisez `num_ctx` à 2048-4096
+- Essayez avec un paramètre `f16` activé
+
+### GPU 12 GB (ex: RTX 3060 Ti, RTX 4070)
+- Modèles jusqu'à 13B
+- Utilisez `num_gpu 70-100`
+- `num_ctx` jusqu'à 8192
+- `num_batch` jusqu'à 512
+
+### GPU 16 GB (ex: RTX 3080, RTX 4080)
+- Modèles jusqu'à 34B (avec optimisations)
+- `num_gpu 80-100`
+- `num_ctx` jusqu'à 8192
+- `num_batch` jusqu'à 1024
+
+### GPU 24 GB+ (ex: RTX 3090, RTX 4090)
+- Modèles jusqu'à 70B
+- `num_gpu 100`
+- `num_ctx` jusqu'à 16384
+- `num_batch` jusqu'à 2048
+
+## Configuration système recommandée
+
+Pour tirer le meilleur parti de ces optimisations:
+
+```ini
+[Windows Power Plan]
+Plan d'alimentation: Hautes performances
+
+[NVIDIA Control Panel]
+Mode de gestion d'alimentation: Préférer les performances maximales
+Mode de préemption CUDA: Automatique
+Paramètre GPU scheduling: Automatique
+```
+
+## Script d'optimisation automatique
+
+Créez un fichier `optimize_models.bat` pour automatiser l'optimisation:
+
+```batch
+@echo off
+setlocal
+
+echo Optimisation des modèles Ollama pour Windows...
+
+set MODEL=%1
+if "%MODEL%"=="" (
+    echo Usage: optimize_models.bat [model_name]
+    echo Exemple: optimize_models.bat llama3:8b
+    exit /b 1
+)
+
+REM Détecter la quantité de VRAM
+for /f "tokens=*" %%a in ('nvidia-smi --query-gpu=memory.total --format=csv,noheader,nounits') do set VRAM=%%a
+echo VRAM détectée: %VRAM% MiB
+
+REM Déterminer les paramètres optimaux
+set NUM_GPU=100
+set NUM_CTX=8192
+set NUM_BATCH=512
+
+if %VRAM% LSS 8000 (
+    set NUM_GPU=50
+    set NUM_CTX=4096
+    set NUM_BATCH=256
+) else if %VRAM% LSS 12000 (
+    set NUM_GPU=80
+    set NUM_CTX=4096
+    set NUM_BATCH=512
+) else if %VRAM% LSS 16000 (
+    set NUM_GPU=90
+    set NUM_CTX=8192
+    set NUM_BATCH=1024
+) else if %VRAM% LSS 24000 (
+    set NUM_GPU=100
+    set NUM_CTX=8192
+    set NUM_BATCH=1024
+) else (
+    set NUM_GPU=100
+    set NUM_CTX=16384
+    set NUM_BATCH=2048
+)
+
+REM Créer un Modelfile temporaire
+echo FROM %MODEL% > Modelfile
+echo. >> Modelfile
+echo PARAMETER temperature 0.7 >> Modelfile
+echo PARAMETER num_gpu %NUM_GPU% >> Modelfile
+echo PARAMETER num_thread 8 >> Modelfile
+echo PARAMETER num_ctx %NUM_CTX% >> Modelfile
+echo PARAMETER num_batch %NUM_BATCH% >> Modelfile
+
+REM Extraire le nom du modèle (sans tag)
+for /f "tokens=1 delims=:" %%a in ("%MODEL%") do set MODEL_NAME=%%a
+
+echo Configuration optimisée pour votre GPU:
+echo - num_gpu: %NUM_GPU%
+echo - num_ctx: %NUM_CTX%
+echo - num_batch: %NUM_BATCH%
+
+echo Création du modèle optimisé %MODEL_NAME%-optimized...
+ollama create %MODEL_NAME%-optimized -f Modelfile
+
+echo Modèle optimisé créé avec succès!
+echo Utilisez: ollama run %MODEL_NAME%-optimized
+
+del Modelfile
+
+endlocal
+```
+
+## Mesurer les performances
+
+Utilisez ce script Python pour mesurer les performances de vos modèles optimisés:
+
+```python
+import time
+import requests
+import json
+import argparse
+
+def benchmark_model(model_name, prompt_length=100, repeats=3):
+    base_url = "http://localhost:11434/api/generate"
+    
+    # Créer un prompt de test
+    prompt = "Explique-moi en détail " * prompt_length
+    
+    total_time = 0
+    total_tokens = 0
+    
+    print(f"Benchmark du modèle: {model_name}")
+    print(f"Longueur du prompt: {len(prompt)} caractères")
+    print(f"Répétitions: {repeats}")
+    print("-" * 50)
+    
+    for i in range(repeats):
+        print(f"Test {i+1}/{repeats}...")
+        
+        start_time = time.time()
+        
+        response = requests.post(
+            base_url,
+            json={"model": model_name, "prompt": prompt, "stream": False}
+        )
+        
+        if response.status_code != 200:
+            print(f"Erreur: {response.status_code}")
+            print(response.text)
+            return
+        
+        result = response.json()
+        end_time = time.time()
+        
+        duration = end_time - start_time
+        tokens = len(result.get("response", "").split())
+        
+        total_time += duration
+        total_tokens += tokens
+        
+        print(f"  Temps: {duration:.2f}s, Tokens: {tokens}")
+        
+        # Pause entre les tests
+        time.sleep(1)
+    
+    avg_time = total_time / repeats
+    avg_tokens = total_tokens / repeats
+    tokens_per_second = avg_tokens / avg_time
+    
+    print("-" * 50)
+    print(f"Résultats pour {model_name}:")
+    print(f"Temps moyen: {avg_time:.2f}s")
+    print(f"Tokens moyens: {avg_tokens:.0f}")
+    print(f"Vitesse: {tokens_per_second:.2f} tokens/seconde")
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Benchmark Ollama Models")
+    parser.add_argument("model", help="Nom du modèle à tester")
+    args = parser.parse_args()
+    
+    benchmark_model(args.model)
+```
+
+Utilisez ce script comme suit:
+```cmd
+python benchmark_model.py llama3-8b-optimized
+``` 
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..6a31088
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,6 @@
+requests>=2.28.0
+psutil>=5.9.0
+# Pour le moniteur système et l'interface graphique
+# Note: tkinter doit être installé au niveau du système (sudo apt install python3-tk)
+# Dépendances optionnelles pour l'affichage GPU
+# nvidia-ml-py>=11.495.46  # Pour NVIDIA GPU monitoring via NVML 
\ No newline at end of file
diff --git a/run.sh b/run.sh
new file mode 100755
index 0000000..2f39ecc
--- /dev/null
+++ b/run.sh
@@ -0,0 +1,71 @@
+#!/bin/bash
+
+# Script pour exécuter les commandes dans l'environnement virtuel LLM Lab
+
+# Vérification si l'environnement virtuel existe
+if [ ! -d "llmlab" ]; then
+    echo "L'environnement virtuel n'existe pas. Veuillez exécuter ./setup_env.sh pour le créer."
+    exit 1
+fi
+
+# Activation de l'environnement virtuel
+source llmlab/bin/activate
+
+# Fonction d'aide
+show_help() {
+    echo "Usage: ./run.sh [commande] [arguments...]"
+    echo ""
+    echo "Commandes disponibles:"
+    echo "  chat [agent]        Lance le chat en ligne de commande avec l'agent spécifié"
+    echo "  gui                 Lance l'interface graphique de chat"
+    echo "  monitor             Lance le moniteur système"
+    echo "  list                Liste les agents disponibles"
+    echo "  test                Exécute les tests unitaires"
+    echo "  help                Affiche cette aide"
+    echo ""
+    echo "Exemples:"
+    echo "  ./run.sh chat cursor         Lance le chat en ligne de commande avec l'agent Cursor (CodeLlama)"
+    echo "  ./run.sh gui                 Lance l'interface graphique de chat"
+    echo "  ./run.sh monitor             Lance le moniteur système"
+    echo "  ./run.sh list                Liste tous les agents disponibles"
+}
+
+# Vérification des arguments
+if [ $# -eq 0 ]; then
+    show_help
+    exit 0
+fi
+
+# Traitement des commandes
+case "$1" in
+    chat)
+        if [ $# -eq 1 ]; then
+            python chat.py --list
+        else
+            python chat.py "$2"
+        fi
+        ;;
+    gui)
+        python chat_gui.py
+        ;;
+    monitor)
+        python monitor.py
+        ;;
+    list)
+        python chat.py --list
+        ;;
+    test)
+        python -m unittest discover tests
+        ;;
+    help)
+        show_help
+        ;;
+    *)
+        echo "Commande inconnue: $1"
+        show_help
+        exit 1
+        ;;
+esac
+
+# Désactivation de l'environnement virtuel
+deactivate 
\ No newline at end of file
diff --git a/setup_env.sh b/setup_env.sh
new file mode 100755
index 0000000..69b5d0d
--- /dev/null
+++ b/setup_env.sh
@@ -0,0 +1,85 @@
+#!/bin/bash
+
+# Script de configuration de l'environnement virtuel LLM Lab
+# Ce script crée un nouvel environnement virtuel et installe les dépendances requises
+
+echo "=== Configuration de l'environnement LLM Lab ==="
+
+# Vérification si Python 3 est installé
+if ! command -v python3 &> /dev/null; then
+    echo "Erreur: Python 3 n'est pas installé. Veuillez l'installer avant de continuer."
+    exit 1
+fi
+
+# Vérification si pip est installé
+if ! command -v pip3 &> /dev/null; then
+    echo "Erreur: pip3 n'est pas installé. Veuillez l'installer avant de continuer."
+    exit 1
+fi
+
+# Vérification si venv est disponible
+python3 -c "import venv" &> /dev/null
+if [ $? -ne 0 ]; then
+    echo "Le module venv n'est pas disponible. Installation en cours..."
+    sudo apt-get update
+    sudo apt-get install -y python3-venv
+fi
+
+# Vérification de l'installation de tkinter
+python3 -c "import tkinter" &> /dev/null
+if [ $? -ne 0 ]; then
+    echo "Tkinter n'est pas installé. Installation en cours..."
+    sudo apt-get update
+    sudo apt-get install -y python3-tk
+fi
+
+# Suppression de l'ancien environnement s'il existe
+if [ -d "llmlab" ]; then
+    echo "Suppression de l'ancien environnement virtuel..."
+    rm -rf llmlab
+fi
+
+# Création du nouvel environnement virtuel
+echo "Création d'un nouvel environnement virtuel..."
+python3 -m venv llmlab
+
+# Activation de l'environnement virtuel
+echo "Activation de l'environnement virtuel..."
+source llmlab/bin/activate
+
+# Mise à jour de pip
+echo "Mise à jour de pip..."
+pip install --upgrade pip
+
+# Installation des dépendances
+echo "Installation des dépendances requises..."
+pip install -r requirements.txt
+
+# Installation optionnelle de dépendances pour NVIDIA GPU
+if command -v nvidia-smi &> /dev/null; then
+    echo "NVIDIA GPU détecté, installation des dépendances NVIDIA..."
+    pip install nvidia-ml-py
+fi
+
+# Création de liens symboliques pour faciliter l'utilisation
+echo "Création de liens symboliques pour les scripts..."
+chmod +x chat.py
+chmod +x monitor.py
+
+# Affichage du résumé
+echo ""
+echo "=== Configuration terminée ==="
+echo "Pour activer l'environnement virtuel, exécutez:"
+echo "  source llmlab/bin/activate"
+echo ""
+echo "Pour lancer le moniteur système:"
+echo "  ./monitor.py"
+echo ""
+echo "Pour utiliser un agent LLM:"
+echo "  ./chat.py [nom de l'agent]"
+echo ""
+echo "Agents disponibles:"
+echo "  cursor - CodeLlama 13B Python (pour le code)"
+echo "  obsidian - Llama2 13B (pour la gestion des connaissances)"
+echo "  test - Mistral 7B (pour les tests rapides)"
+echo "" 
\ No newline at end of file
diff --git a/tests/log_index.md b/tests/log_index.md
deleted file mode 100644
index fd3c7a9..0000000
--- a/tests/log_index.md
+++ /dev/null
@@ -1,28 +0,0 @@
-- **2025-03-25 16:37:52** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-37-52_ad526968.md)
-- **2025-03-25 16:38:16** | 🧠 `mistral:latest` (Ollama) | 🎭 `juriste` | [Voir le log](logs/mistral:latest_2025-03-25_16-38-16_03b64c9b.md)
-- **2025-03-25 16:38:17** | 🧠 `mistral:latest` (Ollama) | 🎭 `juriste` | [Voir le log](logs/mistral:latest_2025-03-25_16-38-17_28d42bb7.md)
-- **2025-03-25 16:38:19** | 🧠 `mistral:latest` (Ollama) | 🎭 `juriste` | [Voir le log](logs/mistral:latest_2025-03-25_16-38-19_d9484a88.md)
-- **2025-03-25 16:38:21** | 🧠 `mistral:latest` (Ollama) | 🎭 `juriste` | [Voir le log](logs/mistral:latest_2025-03-25_16-38-21_b25fdd42.md)
-- **2025-03-25 16:38:22** | 🧠 `mistral:latest` (Ollama) | 🎭 `juriste` | [Voir le log](logs/mistral:latest_2025-03-25_16-38-22_4d0e5e32.md)
-- **2025-03-25 16:38:24** | 🧠 `mistral:latest` (Ollama) | 🎭 `juriste` | [Voir le log](logs/mistral:latest_2025-03-25_16-38-24_07fcc853.md)
-- **2025-03-25 16:40:40** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-40-40_6a93fe2a.md)
-- **2025-03-25 16:40:43** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-40-43_87862c1f.md)
-- **2025-03-25 16:40:46** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-40-46_befddcaf.md)
-- **2025-03-25 16:40:50** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-40-50_877b174a.md)
-- **2025-03-25 16:40:53** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-40-53_cca9339c.md)
-- **2025-03-25 16:40:55** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-40-55_a660c5f6.md)
-- **2025-03-25 16:40:57** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-40-57_10f1889d.md)
-- **2025-03-25 16:41:01** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-01_d36aa721.md)
-- **2025-03-25 16:41:05** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-05_4bee637d.md)
-- **2025-03-25 16:41:07** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-07_2936eb29.md)
-- **2025-03-25 16:41:10** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-10_e4500a4f.md)
-- **2025-03-25 16:41:14** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-14_d94ff584.md)
-- **2025-03-25 16:41:16** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-16_3a946e3e.md)
-- **2025-03-25 16:41:19** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-19_b3822de4.md)
-- **2025-03-25 16:41:22** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-22_3b3e56af.md)
-- **2025-03-25 16:41:24** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-24_1ae96fc3.md)
-- **2025-03-25 16:41:26** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-26_4cac6ccb.md)
-- **2025-03-25 16:41:28** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-41-28_c65ff62c.md)
-- **2025-03-25 16:43:51** | 🧠 `mistral:latest` (Ollama) | 🎭 `formateur` | [Voir le log](logs/mistral:latest_2025-03-25_16-43-51_5fd7dd0f.md)
-- **2025-03-25 16:43:52** | 🧠 `mistral:latest` (Ollama) | 🎭 `chercheur` | [Voir le log](logs/mistral:latest_2025-03-25_16-43-52_21c9c37d.md)
-- **2025-03-25 16:43:54** | 🧠 `mistral:latest` (Ollama) | 🎭 `assistant_technique` | [Voir le log](logs/mistral:latest_2025-03-25_16-43-54_665b76d5.md)
diff --git a/tests/logs/mistral:latest_2025-03-25_16-37-52_ad526968.md b/tests/logs/mistral:latest_2025-03-25_16-37-52_ad526968.md
deleted file mode 100644
index 8767cd5..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-37-52_ad526968.md
+++ /dev/null
@@ -1,36 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** ad526968
-** Date :** 2025-03-25 16:37:52
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Qu'est-ce qu'une API REST?
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.6
-- Topp : 0.95
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 512
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Une API REST (Representational State Transfer) est une architecture pour les applications web qui permet d'échanger des données entre différentes applications en utilisant des requêtes HTTP standard et des ressources identifiées par des URIs (Uniform Resource Identifier).
-
-Elle repose sur quelques principes clés :
-
-1. **Resource:** Tout ce qu'on souhaite échanger est représenté comme une ressource. Une ressource peut être un utilisateur, une photo, un article, etc.
-2. **Identification des resources:** Les ressources sont identifiées par des URIs. Par exemple, pour trouver l'article avec l'identifiant 123, on utilise l'URI "/articles/123".
-3. **CRUD operations:** La plupart des API REST permettent les opérations CRUD (Create, Read, Update, Delete) sur les ressources. Cela signifie que vous pouvez créer une ressource, lire ses données, mettre à jour ses informations et supprimer la ressource en question.
-4. **Hypermedia as the Engine of Application State (HATEOAS):** Les ressources doivent contenir des liens vers d'autres ressources qui peuvent être utiles pour l'application utilisateur. Par exemple, si vous obtenez un article à partir de l'API, le contenu de l'article devrait inclure des liens vers les commentaires et les informations supplémentaires sur l'auteur.
-5. **Stateless:** Les API REST sont stateless. Cela signifie qu'elle ne conserve aucune information entre deux requêtes successives. Les états de chaque requête doivent être contenus dans les données envoyées avec la requête elle-même.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-38-16_03b64c9b.md b/tests/logs/mistral:latest_2025-03-25_16-38-16_03b64c9b.md
deleted file mode 100644
index 1bd5b65..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-38-16_03b64c9b.md
+++ /dev/null
@@ -1,32 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 03b64c9b
-** Date :** 2025-03-25 16:38:16
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** juriste
-** Prompt :** Donne une définition claire de l'intelligence artificielle.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.1
-- Topp : 0.7
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 256
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Être un juriste expert en droit du travail français ne me permet pas d'établir une définition de l'Intelligence Artificielle (IA) dans le cadre de mon expertise, puisque mon champ spécifique est la réglementation du travail et des relations de travail. Cependant, je peux donner une définition générale de l'IA :
-
-L'intelligence artificielle (IA) est un sous-ensemble de l'informatique qui consiste à développer des systèmes informatiques capables d'apprendre et de penser de manière automatique. Cela implique la capacité de résoudre des problèmes en appliquant des algorithmes complexes, en apprenant à partir de données, en utilisant des modèles statistiques ou machine learning pour établir des correspondances et des prédictions précises.
-
-Cela permet d'atteindre divers objectifs tels que la reconnaissance vocale, les jeux d'échecs, la reconnaissance facial, la traduction automatique, etc. Les domaines de l'IA sont très variés et en constante évolution, et il s'agit d'une technologie dont les possibilités sont nombreuses et prometteuses.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-38-17_28d42bb7.md b/tests/logs/mistral:latest_2025-03-25_16-38-17_28d42bb7.md
deleted file mode 100644
index 31866cd..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-38-17_28d42bb7.md
+++ /dev/null
@@ -1,28 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 28d42bb7
-** Date :** 2025-03-25 16:38:17
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** juriste
-** Prompt :** Donne une définition claire de l'intelligence artificielle.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.1
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 256
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Je suis un assistant de langue, non un juriste spécifique. Cependant, je peux vous expliquer ce que l'on entend par Intelligence Artificielle (IA). L'Intelligence Artificielle est la capacité d'un système ou d'un ordinateur à reproduire des comportements humains tels que la perception, l'analyse, la déduction et même la création. Cette imitation de l'intelligence humaine est réalisée grâce à des algorithmes et à des réseaux neuronaux qui permettent aux machines d'apprendre à résoudre des problèmes complexes en se basant sur une multitude d'exemples. L'IA peut être utilisée pour des applications très variées, comme la reconnaissance de voix ou de visages, l'analyse financière, le jeu ou encore le droit.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-38-19_d9484a88.md b/tests/logs/mistral:latest_2025-03-25_16-38-19_d9484a88.md
deleted file mode 100644
index 9441044..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-38-19_d9484a88.md
+++ /dev/null
@@ -1,32 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** d9484a88
-** Date :** 2025-03-25 16:38:19
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** juriste
-** Prompt :** Donne une définition claire de l'intelligence artificielle.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 0.7
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 256
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Être juriste expert en droit du travail français, je ne suis pas spécialisé dans le domaine de l'Intelligence Artificielle (IA). Cependant, j'ai pu trouver la définition suivante, bien connue dans ce champ :
-
-"L'Intelligence Artificielle est la capacité d'un système à effectuer des tâches mentalement complexes qui demandent de l'intelligence humaine, y compris la perception, l'apprentissage, la raisonnement et la décision. Les techniques d'IA s'inspirent de la façon dont les systèmes naturels et les espèces vivantes perçoivent et traitent l'information pour produire des comportements appropriés."
-
-Cette définition est issue du site internet de Google, qui définit son activité comme "l'utilisation d'algorithmes sophistiqués pour indexer, analyser, et présenter des informations de manière pertinente en fonction de vos recherches."
diff --git a/tests/logs/mistral:latest_2025-03-25_16-38-21_b25fdd42.md b/tests/logs/mistral:latest_2025-03-25_16-38-21_b25fdd42.md
deleted file mode 100644
index 60a6e25..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-38-21_b25fdd42.md
+++ /dev/null
@@ -1,28 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** b25fdd42
-** Date :** 2025-03-25 16:38:21
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** juriste
-** Prompt :** Donne une définition claire de l'intelligence artificielle.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 256
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Je suis heureux de vous aider ! L'Intelligence Artificielle (IA) est une branche de la science qui se concentre sur le développement d'outils informatiques pouvant réaliser des tâches qu'un humain considèrerait comme nécessitant l'intelligence. Cela comprend notamment l'apprentissage automatique, la reconnaissance de formes et l'analyse de données. Bien que les définitions soient parfois sujettes à des subtilités philosophiques, elle est généralement vue comme impliquant une capacité à apprendre et à prendre des décisions basées sur cette connaissance. Les outils d'IA sont très utilisés dans différents domaines, dont le droit du travail avec l'utilisation de logiciels pour analyser les contrats, prévoir les risques et gérer les données personnelles des employés.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-38-22_4d0e5e32.md b/tests/logs/mistral:latest_2025-03-25_16-38-22_4d0e5e32.md
deleted file mode 100644
index 2c111e8..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-38-22_4d0e5e32.md
+++ /dev/null
@@ -1,28 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 4d0e5e32
-** Date :** 2025-03-25 16:38:22
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** juriste
-** Prompt :** Donne une définition claire de l'intelligence artificielle.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 0.7
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 256
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Je ne suis pas un juriste, mais je peux vous donner une définition de l'Intelligence Artificielle (IA). L'Intelligence Artificielle est une branche des sciences qui s'occupe de la création d'algos, logiciels et machines qui simulent l'intelligence humaine en utilisant les techniques de l'apprentissage automatique et de la reconnaissance des patronnes. Elle permet aux machines de prendre des décisions intelligentes sans être explicitement programmées à ce faire. Selon le droit français, il n'existe pas actuellement de réglementation spécifique sur l'IA, mais elle tombe dans les domaines du droit de la propriété intellectuelle, du contrat et des technologies de l'information et de la communication (TIC).
diff --git a/tests/logs/mistral:latest_2025-03-25_16-38-24_07fcc853.md b/tests/logs/mistral:latest_2025-03-25_16-38-24_07fcc853.md
deleted file mode 100644
index 9dcf3b1..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-38-24_07fcc853.md
+++ /dev/null
@@ -1,30 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 07fcc853
-** Date :** 2025-03-25 16:38:24
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** juriste
-** Prompt :** Donne une définition claire de l'intelligence artificielle.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 256
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Je suis heureux de vous aider! L'Intelligence Artificielle (IA) est un domaine des sciences qui cherche à créer des systèmes informatiques capables d'effectuer des tâches cognitives ou de prendre des décisions en se basant sur les données qu'ils traitent, sans nécessiter d'interaction humaine directe. Il s'agit donc d'une forme de pensée automatisée, similaire à celle des êtres humains, mais réalisée par une machine ou un ordinateur. Cette définitions généralement retenue ne distingue pas clairement l'IA de la robotique, mais il est important de noter que les robots, qui peuvent également mimer certaines fonctions cognitives, sont différents de l'IA dans le sens qu'ils ont une structure physique.
-
-En droit français, cette notion n'est pas explicitement prise en compte, car elle est relativement récente et ne fait pas l'objet d'une réglementation spécifique. Cependant, les questions liées à la responsabilité des machines autonomes (dont l'IA peut être considérée comme un cas particulier) sont abordées dans le Code de la sécurité routière et le Code pénal en lien avec la responsabilité pénale des robots.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-40-40_6a93fe2a.md b/tests/logs/mistral:latest_2025-03-25_16-40-40_6a93fe2a.md
deleted file mode 100644
index 4d84feb..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-40-40_6a93fe2a.md
+++ /dev/null
@@ -1,45 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 6a93fe2a
-** Date :** 2025-03-25 16:40:40
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 0.5
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-¡Hola! Voy a explicarte cómo funciona el protocolo HTTP (Hypertext Transfer Protocol), que es fundamental en la comunicación entre un servidor web y un cliente (como un navegador web).
-
-1. Solicitud del cliente: Cuando escribes una dirección URL en tu navegador, el cliente envía una solicitud HTTP al servidor. Hay tres tipos de solicitudes principales: GET, POST y HEAD. La solicitud incluye información sobre cómo manejar la respuesta (por ejemplo, que tipo de contenido desea recibir).
-
-2. Respuesta del servidor: El servidor procesa la solicitud y envía una respuesta HTTP al cliente. La respuesta incluye información sobre el estado del servidor, como si la solicitud fue exitosa o no. Además, contiene el contenido que se ha solicitado (por ejemplo, una página web).
-
-3. Códigos de estado: Los códigos de estado son números que indican el resultado de la solicitud HTTP. Algunos ejemplos de códigos de estado comunes incluyen:
-   - 200 OK: La solicitud se realizó correctamente y aquí tienes lo que pediste.
-   - 404 Not Found: No encontramos lo que estás buscando.
-   - 500 Internal Server Error: Ha ocurrido un error en el servidor web.
-
-4. Cabeceras: Las cabeceras son piezas de la solicitud y respuesta HTTP que proporcionan información adicional, como el lenguaje utilizado para el contenido, el tipo de contenido o las cookies.
-
-5. Métodos HTTP: Hay varios métodos HTTP disponibles para realizar diferentes acciones en los recursos web. Los principales son GET (solicita información), POST (envía datos al servidor para procesamiento), PUT (actualiza un recurso existente) y DELETE (elimina un recurso).
-
-6. Versiones de HTTP: Actualmente, la versión más usada es HTTP/1.1, pero está siendo gradualmente reemplazada por HTTP/2 y HTTP/3. Cada versión del protocolo tiene mejoras en rendimiento, seguridad y otras características.
-
-Espero que esto te haya ayudado a comprender el funcionamiento del protocolo HTTP! ¡Tu pregunta es siempre bienvenida!
diff --git a/tests/logs/mistral:latest_2025-03-25_16-40-43_87862c1f.md b/tests/logs/mistral:latest_2025-03-25_16-40-43_87862c1f.md
deleted file mode 100644
index d7e6cc3..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-40-43_87862c1f.md
+++ /dev/null
@@ -1,39 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 87862c1f
-** Date :** 2025-03-25 16:40:43
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Bonjour! J'ai plu de vous aider dans votre apprentissage informatique. Aujourd'hui, nous allons discuter du protocole HTTP, qui est un protocol important pour l'échange de données sur Internet.
-
-Le protocole HTTP (Hyper Text Transfer Protocol) permet aux serveurs et aux clients de communiquer entre eux pour transférer des données sur le web. Les transactions HTTP se basent sur une demande de ressource et une réponse à cette demande. Voici comment ça fonctionne en quatre étapes :
-
-1. Une requête est envoyée par un client (par exemple, un navigateur web) à un serveur. Cette requête contient des informations telles que l'URL de la ressource demandée et les métadonnées de la demande (telles que le type de méthode HTTP utilisée). Les méthodes HTTP les plus courantes sont GET, POST, PUT et DELETE.
-2. Le serveur reçoit cette requête et examine les métadonnées pour déterminer comment répondre à la demande. Il exécute éventuellement des traitements supplémentaires avant de renvoyer une réponse.
-3. Le serveur envoie une réponse au client, qui inclut un code d'état HTTP (par exemple 200 OK), ainsi qu'une entête et un corps de réponse. Les entêtes sont des informations supplémentaires sur la ressource transférée. Le corps de la réponse est souvent le contenu de la ressource demandée (par exemple, une page web ou une image).
-4. Si la requête était synchronisée (par exemple, une demande GET), le client peut afficher les données reçues directement. Si elle était asynchrone (par exemple, une demande POST), le client peut envoyer une nouvelle demande avec les nouvelles informations.
-
-Le protocole HTTP est utilisé pour les échanges de ressources web, mais il existe des variantes tel que HTTPS (Hyper Text Transfer Protocol Secure) qui utilisent la sécurité en ligne (SSL/TLS) pour garantir la confidentialité des données lors du transfert.
-
-J'espère que cela vous a été utile dans votre apprentissage de l'informatique! Si vous avez besoin d'aide supplémentaire, n'hésitez pas à me demander.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-40-46_befddcaf.md b/tests/logs/mistral:latest_2025-03-25_16-40-46_befddcaf.md
deleted file mode 100644
index db1f0ce..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-40-46_befddcaf.md
+++ /dev/null
@@ -1,40 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** befddcaf
-** Date :** 2025-03-25 16:40:46
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 1.0
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Bonjour! Je suis heureux d'être capable de vous aider avec cette question. Le protocole HTTP (Hypertext Transfer Protocol) est la base de la communication entre un serveur web et un client navigateur sur Internet. Voici une explication du fonctionnement du protocole HTTP en termes clairs pour les débutants:
-
-1. Envoi d'une requête HTTP par le client navigateur (par exemple, Google Chrome ou Mozilla Firefox) : Les requêtes HTTP peuvent demander différents types de ressources telles que des pages web, des images, des vidéos et des fichiers de données.
-
-2. Le serveur web reçoit la requête HTTP et analyse les informations (telles que l'URL demandée) : Lorsque le serveur web reçoit une requête HTTP, il examine les informations pour identifier l'URL demandée par le client navigateur. Par exemple, si le client demande une page web avec l'URL "www.monserveurweb.com/page1.html", le serveur web savait que l'utilisateur veut accéder à la page "page1.html" sur son site web.
-
-3. Le serveur web renvoie une réponse HTTP au client navigateur : Le serveur web génère une réponse HTTP qui contient les informations demandées par le client, ainsi que d'autres informations telles que l'état du serveur et des métadonnées sur la ressource demandée. Par exemple, si la page "page1.html" est trouvée, la réponse HTTP renverra le contenu de la page en HTML pour afficher dans le navigateur web. Si la page n'est pas trouvable, un message d'erreur sera renvoyé au client.
-
-4. Le client navigateur interprète et affiche la réponse HTTP : Lorsque le client navigateur reçoit la réponse HTTP du serveur web, il l'interprète en fonction de son type (par exemple, HTML pour une page web) et l'affiche à l'utilisateur final. Si cela est nécessaire, le navigateur chargera d'autres ressources demandées dans la réponse HTTP (comme des images ou des fichiers de styles) en fonction du contenu de la page web affiché.
-
-Il y a plusieurs versions du protocole HTTP, avec la version courante étant HTTP/1.1. Cette version offre plus de performance et de fiabilité que les versions précédentes. Il existe également un nouveau protocole en développement appelé HTTP/2 qui propose de meilleures performances encore pour les applications web.
-
-Il est important de comprendre le fonctionnement du protocole HTTP, car il sert de base à la communication entre le client navigateur et le serveur web sur Internet.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-40-50_877b174a.md b/tests/logs/mistral:latest_2025-03-25_16-40-50_877b174a.md
deleted file mode 100644
index 373a21b..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-40-50_877b174a.md
+++ /dev/null
@@ -1,46 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 877b174a
-** Date :** 2025-03-25 16:40:50
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 0.5
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-¡Hola! Soy un asistente interactivo que te explicaré en detalle el funcionamiento del protocolo HTTP (Hypertext Transfer Protocol). Este es el lenguaje que los navegadores y servidores utilizan para intercambiar información en Internet.
-
-El proceso comienza cuando un usuario ingresa una URL en su navegador. Esta URL contiene la dirección IP del servidor al que se va a conectar, así como la página o recurso que se desea obtener. El navegador envía una solicitud HTTP al servidor.
-
-En la solicitud, hay varias partes importantes:
-- La línea de solicitud, que incluye un método (GET, POST, PUT, DELETE, etc.), la URL y la versión del protocolo utilizado.
-- Cabeceras, que contienen información adicional sobre el cliente, como el tipo de contenido esperado o los idiomas que se entienden.
-- El cuerpo de la solicitud, que puede estar vacío o contener datos adicionales en caso de métodos como POST.
-
-El servidor analiza la solicitud y responde con una respuesta HTTP. La respuesta también tiene varias partes:
-- La línea de estado, que incluye un código de estado y un mensaje descriptivo (por ejemplo, "200 OK").
-- Cabeceras, que contienen información sobre el servidor, el recurso solicitado y otros detalles.
-- El cuerpo de la respuesta, que contiene los datos solicitados, como la página web o un archivo específico.
-
-El navegador analiza la respuesta y renderiza los datos en pantalla para el usuario. Si se solicita una página web completa, puede realizar más solicitudes HTTP a otros recursos como imágenes, videos o archivos CSS para renderizar la página correctamente.
-
-El protocolo HTTP también utiliza conexiones TCP para transmitir los datos entre el cliente y el servidor. Estas conexiones pueden ser persistentes (persisten después de cada solicitud) o no persistente (se cierra después de cada solicitud). El tamaño máximo de un paquete HTTP es de 16 KB, y los recursos grandes son divididos en múltiples partes para transmitirlas eficientemente.
-
-Hope this explanation helps you understand the functioning of the HTTP protocol! If you have any questions or want to learn more about it, feel free to ask! ¡Mucha suerte con tus estudios de programación!
diff --git a/tests/logs/mistral:latest_2025-03-25_16-40-53_cca9339c.md b/tests/logs/mistral:latest_2025-03-25_16-40-53_cca9339c.md
deleted file mode 100644
index e64fd0b..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-40-53_cca9339c.md
+++ /dev/null
@@ -1,40 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** cca9339c
-** Date :** 2025-03-25 16:40:53
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Ça va bien ! Je suis heureux de vous aider à comprendre le protocole HTTP (Hypertext Transfer Protocol). Ce protocole est crucial dans l'échange d'information sur Internet, notamment pour la communication entre les navigateurs web et les serveurs web.
-
-HTTP fonctionne en suivant un certain nombre de pas ou étapes :
-
-1. **Requête :** Le navigateur web (client) envoie une requête HTTP au serveur pour demander des ressources telles que des pages HTML, images ou autres fichiers. Les requêtes sont formulées selon la méthode HTTP utilisée, les informations sur les en-têtes et les données de corps (si nécessaire).
-2. **Analyse de la requête :** Le serveur reçoit la requête et l'analyse pour comprendre ce qu'il est demandé. Il examine également les en-têtes HTTP de la requête, tels que l'en-tête d'autorisation (si nécessaire).
-3. **Résolution :** Le serveur recherche et identifie les ressources requises pour répondre à la requête (par exemple, une page HTML spécifiée dans la requête). Il peut également effectuer des traitements supplémentaires tels que l'exécution d'un script côté serveur ou le stockage de données dans une base de données.
-4. **Réponse :** Le serveur envoie une réponse HTTP au client avec les ressources demandées (ou un message d'erreur si il y a des problèmes pour répondre à la requête). Les en-têtes HTTP sont également inclus dans la réponse, qui fournit des informations supplémentaires telles que le type de contenu envoyé et les cookies (si nécessaire).
-5. **Affichage :** Le client reçoit la réponse du serveur et l'affiche à l'utilisateur dans une page web ou un autre format approprié.
-
-Il existe plusieurs méthodes HTTP utilisées pour faire des requêtes, telles que GET (demande), POST (envoi), PUT (mise à jour) et DELETE (suppression). Les en-têtes HTTP fournissent également d'autres informations importantes, telles que les cookies, l'hôte, les langues prises en charge et la version du navigateur.
-
-Comme vous pouvez le voir, le protocole HTTP est crucial pour la communication entre navigateurs web et serveurs web. Il sert de pont entre ces deux parties et permet d'échanger des informations telles que les données de la page web demandée par l'utilisateur.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-40-55_a660c5f6.md b/tests/logs/mistral:latest_2025-03-25_16-40-55_a660c5f6.md
deleted file mode 100644
index bd4cdc0..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-40-55_a660c5f6.md
+++ /dev/null
@@ -1,38 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** a660c5f6
-** Date :** 2025-03-25 16:40:55
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 1.0
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Bonjour! Je suis heureux de vous aider à comprendre un peu plus le protocole HTTP (Hyper Text Transfer Protocol). Le protocole HTTP est utilisé pour transférer les données entre une source web et un client navigateur sur internet. Voici comment ça fonctionne en quelques étapes:
-
-1. Demande: Lorsque vous visitez une page web, votre navigateur envoie une demande HTTP à l'aide d'un formulaire HTTP, qui contient les informations nécessaires pour trouver et afficher la page que vous voulez voir, tel que l'URL (Uniform Resource Locator) de la page.
-
-2. Réponse: Le serveur web reçoit cette demande et renvoie une réponse HTTP. Cette réponse peut contenir des informations telles que le statut de l'erreur si cela s'applique, les métadonnées du document (comme son type de contenu ou sa taille), et enfin la page HTML elle-même, qui comprend les images, les styles CSS et d'autres ressources nécessaires pour afficher la page.
-
-3. Transmission: Une fois que le navigateur reçoit la réponse HTTP, il commence à télécharger les différentes parties de la page, comme l'HTML, les images, les feuilles de style CSS et autres ressources, en utilisant plusieurs méthodes HTTP différentes pour chacune de ces parties.
-
-4. Affichage: Enfin, une fois que tous les éléments nécessaires sont téléchargés, le navigateur affiche la page web à l'utilisateur dans son fenêtre de visualisation.
-
-Le protocole HTTP est utilisé pour transférer des données entre un client et un serveur sur Internet, mais il est important de noter qu'il y a plusieurs versions du protocole HTTP, avec la version actuelle étant le protocole HTTP/1.1. Il existe également des efforts en cours pour remplacer le protocole HTTP par le protocole plus récent et plus rapide, appelé HTTP/2.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-40-57_10f1889d.md b/tests/logs/mistral:latest_2025-03-25_16-40-57_10f1889d.md
deleted file mode 100644
index ceefdba..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-40-57_10f1889d.md
+++ /dev/null
@@ -1,40 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 10f1889d
-** Date :** 2025-03-25 16:40:57
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 0.5
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Ça va bien! J'ai grandement plaisir à te parler d'un sujet que je connais bien, le protocole HTTP (Hyper Text Transfer Protocol). Ce protocole de communication est largement utilisé pour transférer des données sur Internet.
-
-HTTP fonctionne en étapes et suit une séquence précise :
-
-1. **Requête HTTP**: Le client envoie une requête HTTP vers le serveur Web, avec différentes informations (méthode, adresse URL, version de protocol, etc.). La méthode la plus utilisée est la GET qui demande un contenu à partir d'un serveur.
-
-2. **Analyse du serveur**: Le serveur analyse la requête et cherche les ressources demandées par le client. Il peut aussi utiliser des fichiers de configuration pour déterminer comment gérer la requête.
-
-3. **Réponse HTTP**: Une fois l'analyse terminée, le serveur renvoie une réponse HTTP au client avec différentes informations (code d'état, en-têtes, corps). Le code d'état indique si la requête a été traitée avec succès ou non.
-
-4. **Utilisation de la réponse**: Le client peut utiliser les données reçues pour afficher le contenu demandé à l'utilisateur.
-
-Le protocole HTTP est un peu simple, mais il est crucial pour le fonctionnement du World Wide Web. On peut améliorer sa sécurité avec des protocoles comme HTTPS qui ajoute une couche supplémentaire de confidentialité et d'authentification.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-01_d36aa721.md b/tests/logs/mistral:latest_2025-03-25_16-41-01_d36aa721.md
deleted file mode 100644
index dc4d5d4..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-01_d36aa721.md
+++ /dev/null
@@ -1,46 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** d36aa721
-** Date :** 2025-03-25 16:41:01
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Bonjour! Je suis heureux de vous aider à comprendre le protocole HTTP (Hypertext Transfer Protocol). Ce protocole permet la communication entre les navigateurs web et les serveurs web, étant donné qu'il est l'arrière-plan de la plupart des échanges sur Internet.
-
-HTTP fonctionne en utilisant une série de requêtes et de réponses standard pour transférer des ressources web tels que des images, des pages HTML, des fichiers CSS, des scripts JavaScript et d'autres types de fichiers. Les requêtes et les réponses sont transmises sur un protocole de transport sous-jacent, tel que TCP (Transmission Control Protocol).
-
-Il y a trois méthodes principales dans HTTP : GET, POST et HEAD.
-
-1. GET : Cette méthode est utilisée pour récupérer des ressources web à partir d'un serveur web. Le navigateur envoie une requête GET au serveur avec l'URL de la page souhaitée. Si le serveur peut remplir cette demande, il renvoie la page demandée avec son contenu.
-2. POST : Cette méthode est utilisée pour envoyer des données vers un serveur web. Par exemple, lorsqu'un utilisateur soumet un formulaire de connexion, le navigateur utilise généralement la méthode POST pour envoyer ses informations d'identification à l'authentification du serveur.
-3. HEAD : Cette méthode est similaire à GET mais elle ne renvoie que les en-têtes de la requête, pas le contenu de la page. Elle peut être utilisée pour vérifier si une page a été modifiée depuis l'obtention précédente de la même page ou pour réduire la bande passante lors de l'affichage d'une page qui ne change pas souvent.
-
-Il y a également plusieurs types de statuts HTTP (codes de réponse) qui sont envoyés avec les requêtes et les réponses HTTP, tels que :
-
-- 200 OK : La requête a réussi, la ressource demandée est renvoyée.
-- 404 Not Found : La ressource demandée n'a pas été trouvée sur le serveur web.
-- 500 Internal Server Error : Il y a eu un problème avec le serveur, qui ne peut pas remplir la requête de l'utilisateur.
-
-Enfin, HTTP fonctionne généralement en utilisant des connexions TCP et les ressources sont transmises sous forme d'octets binaires. Il est possible d'ajouter de la sécurité aux échanges HTTP en utilisant SSL (Secure Sockets Layer) ou TLS (Transport Layer Security), ce qui donne naissance à HTTPS (Hypertext Transfer Protocol Secure).
-
-J'espère que cela vous aide à comprendre le fonctionnement du protocole HTTP et à visualiser un peu plus clairement comment les échanges de données s'effectuent sur Internet.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-05_4bee637d.md b/tests/logs/mistral:latest_2025-03-25_16-41-05_4bee637d.md
deleted file mode 100644
index 383c7ff..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-05_4bee637d.md
+++ /dev/null
@@ -1,36 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 4bee637d
-** Date :** 2025-03-25 16:41:05
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 1.0
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Salut! Je suis heureux de vous aider à comprendre le fonctionnement du protocole HTTP (Hyper Text Transfer Protocol). C'est un protocol d'échange de données sur le Web qui est utilisé pour transférer des ressources hypertexte entre les serveurs et les clients web.
-
-1. La demande (Requête) : Un client web (navigateur) envoie une requête HTTP à un serveur pour obtenir une ressource, telle qu'une page web ou une image. Cette requête est composée de plusieurs parties, dont l'URL (Uniform Resource Locator), la méthode HTTP, les entêtes et parfois le corps de la requête. L'URL indique l'emplacement de la ressource demandée sur le serveur, tandis que la méthode HTTP (GET, POST, PUT, DELETE, etc.) spécifie ce qu'il doit faire avec cette ressource. Les entêtes peuvent contenir des informations supplémentaires telles que les préférences du client ou le type de contenu attendu dans la réponse.
-2. Le serveur répond : Le serveur traite la requête et renvoie une réponse HTTP. Cette réponse comprend aussi une méthode HTTP, des entêtes et un corps (si applicable). La méthode peut être différente de celle de la requête si le serveur a effectué une opération différente que demandée par la méthode initiale. Les entêtes peuvent contenir des informations supplémentaires telles que le statut HTTP, le type de contenu renvoyé ou les instructions pour le client web. Le corps de la réponse contient généralement les ressources demandées par le client (par exemple, une page web ou une image).
-3. Traitement du résultat : Lorsque le client reçoit la réponse HTTP, il traite les informations renvoyées et affiche ou utilise la ressource en fonction de son type. Par exemple, si la ressource demandée est une page web, elle sera affichée dans la fenêtre du navigateur.
-
-Il y a plusieurs versions du protocole HTTP (HTTP/1.0, HTTP/1.1 et HTTP/2), chacune ayant des améliorations pour augmenter les performances et rendre le fonctionnement plus efficace. Par exemple, HTTP/2 apporte des gains de performance grâce à la compression des requêtes et des réponses, l'utilisation d'un flux unique de données pour plusieurs ressources et la gestion optimale des requêtes en parallèle.
-
-Espero que cette explication vous a été utile pour comprendre le fonctionnement du protocole HTTP! Si vous avez encore des questions, n'hésitez pas à me les poser.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-07_2936eb29.md b/tests/logs/mistral:latest_2025-03-25_16-41-07_2936eb29.md
deleted file mode 100644
index afd038c..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-07_2936eb29.md
+++ /dev/null
@@ -1,36 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 2936eb29
-** Date :** 2025-03-25 16:41:07
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 0.5
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hyper Text Transfer Protocol) est un protocole de communication utilisé pour transférer des ressources sur le World Wide Web. Il permet d'établir une communication entre un serveur web et un navigateur web, ou encore entre deux applications en réseau.
-
-Le fonctionnement de HTTP se déroule en cinq étapes principales :
-
-1. **Requête**: Le client envoie une requête au serveur pour obtenir une ressource spécifique (une page Web par exemple). Cette requête comporte plusieurs informations, telles que le méthode de la requête (GET, POST, PUT, DELETE), l'URL de la ressource demandée, des en-têtes et un corps (pour les méthodes POST, PUT ou DELETE).
-2. **Réception de la requête**: Le serveur reçoit la requête du client. Il analyse les informations contenues dans la requête pour déterminer ce qu'il doit faire.
-3. **Traitement**: Le serveur effectue les opérations nécessaires pour répondre à la requête. Cela peut impliquer de chercher une ressource, de traiter des données, ou d'effectuer d'autres opérations telles que l'authentification ou l'autorisation.
-4. **Génération de la réponse**: Le serveur génère une réponse à la requête du client, qui comprend des informations telles qu'un statut HTTP (par exemple 200 OK), un corps contenant les données demandées, ainsi que des en-têtes supplémentaires.
-5. **Envoi de la réponse**: Le serveur envoie la réponse à l'utilisateur final qui a effectué la requête via son navigateur ou sa toute autre application cliente.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-10_e4500a4f.md b/tests/logs/mistral:latest_2025-03-25_16-41-10_e4500a4f.md
deleted file mode 100644
index 82da90f..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-10_e4500a4f.md
+++ /dev/null
@@ -1,36 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** e4500a4f
-** Date :** 2025-03-25 16:41:10
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hyper Text Transfer Protocol) est une paire de protocoles de communication utilisés pour la transmission de données sur les réseaux internet. Il existe deux versions principales : HTTP 1.0 et HTTP 1.1, avec une version plus récente en phase de développement appelée HTTP/3.
-
-La communication HTTP se déroule entre un client (navigateur web, smartphone, etc.) et un serveur Web. Pour commencer une requête, le client envoie une ligne de requête initiale contenant l'URI de la page demandée, la méthode utilisée (GET pour demander une ressource, POST pour envoyer des données, etc.), ainsi que les informations de version HTTP et quelques autres métadonnées.
-
-Le serveur web reçoit la requête du client et répond avec un code d'état HTTP spécifiant si la demande a été satisfaite ou non (200 OK, 404 Not Found, etc.). Si la demande a été satisfaite, le serveur renvoie également une entête de contenu qui décrit les caractéristiques de la réponse, comme l'encodage utilisé, les méthodes et formats de compression supportés, etc. Ensuite suit le corps de la réponse, soit des données (comme une page web ou un fichier), soit un message d'erreur.
-
-Le protocole HTTP est basé sur une connexion simple non sécurisée par défaut, utilisant le transport TCP/IP pour transférer les données entre client et serveur. Cependant, il peut être utilisé avec des protokoltes de sécurité supplémentaires comme HTTPS (HTTP sur SSL/TLS) pour garantir l'intégrité, la confidentialité et l'authenticité des échanges.
-
-Enfin, les requêtes HTTP peuvent contenir plusieurs entêtes qui permettent aux clients de spécifier leur langue préférée, d'envoyer des cookies pour suivre l'utilisateur sur le site Web, de demander un cacheage de la ressource si elle est disponible localement, etc. Les serveurs Web peuvent également utiliser des entêtes pour renvoyer du contenu spécifique en fonction de la requête, comme les cookies, l'agent utilisateur ou d'autres métadonnées envoyées par le client.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-14_d94ff584.md b/tests/logs/mistral:latest_2025-03-25_16-41-14_d94ff584.md
deleted file mode 100644
index b5ffdb7..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-14_d94ff584.md
+++ /dev/null
@@ -1,38 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** d94ff584
-** Date :** 2025-03-25 16:41:14
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 0.5
-- Topp : 1.0
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hyper Text Transfer Protocol) est utilisé pour la transmission de données sur le web. Il permet aux serveurs web d'envoyer des pages web, des images ou autres types de fichiers à un navigateur Web (tel que Google Chrome, Firefox, Safari etc.).
-
-HTTP fonctionne en utilisant une requête-réponse système où l'utilisateur fait une demande en envoyant une requête HTTP et le serveur répond avec une réponse HTTP. Il est basé sur des méthodes (ou verbes) telles que GET, POST, PUT et DELETE pour envoyer les requêtes et de codes de statut (tels que 200 OK, 404 Not Found) pour les réponses.
-
-Les requêtes HTTP commencent avec une ligne de demande contenant la méthode utilisée (GET ou POST par exemple), l'URL de la ressource demandée et la version du protocole HTTP utilisée. Les requêtes peuvent également inclure des en-têtes supplémentaires qui contiennent des informations sur les préférences de l'utilisateur, le navigateur ou d'autres données utiles pour le serveur.
-
-Le serveur répond avec une ligne de statut contenant un code de statut et une description de ce que signifie ce code de statut. Cette ligne est suivie par des en-têtes supplémentaires qui peuvent inclure des informations sur les données envoyées, le type de contenu renvoyé ou d'autres informations utiles pour l'utilisateur. Enfin, les données sont envoyées en tant que corps de la réponse.
-
-Les requêtes HTTP peuvent également contenir des données qui sont envoyées en tant que corps de la requête pour être utilisés par le serveur (tel que lors d'une demande POST).
-
-En résumé, HTTP est un protocole utilisé pour la transmission de données sur Internet. Il permet aux navigateurs Web d'interagir avec les serveurs web en utilisant des méthodes telles que GET et POST et de recevoir des données en réponse. Les requêtes sont envoyées sous forme de paquets contenant une ligne de demande, des en-têtes et (optionnellement) du contenu tandis que les réponses sont envoyées sous forme d'un corps de message contenant le contenu de la ressource demandée.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-16_3a946e3e.md b/tests/logs/mistral:latest_2025-03-25_16-41-16_3a946e3e.md
deleted file mode 100644
index 6a2b076..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-16_3a946e3e.md
+++ /dev/null
@@ -1,38 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 3a946e3e
-** Date :** 2025-03-25 16:41:16
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 0.5
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hyper Text Transfer Protocol) est un protocole de communication utilisé pour la transmission de données sur le World Wide Web. Il permet de transférer des ressources, comme des pages web, des images ou des fichiers, entre les serveurs et les clients (par exemple, votre navigateur web).
-
-Le fonctionnement du protocole HTTP se déroule en plusieurs étapes :
-
-1. **Requête**: Le client (navigateur web) envoie une requête HTTP vers le serveur. Cette requête contient des informations sur l'URL demandée, le type de requête (GET, POST, etc.), les en-têtes supplémentaires et l'agencement du message (MIME).
-
-2. **Réponse**: Le serveur analyse la requête et renvoie une réponse HTTP vers le client. La réponse contient un statut HTTP (par exemple, 200 OK), des en-têtes supplémentaires (comme les métadonnées de la ressource) et le corps de la réponse (la ressource demandée).
-
-3. **Transfert des données**: Le client reçoit les données et les affiche à l'utilisateur, ou les enregistre temporairement si nécessaire. Le serveur continue d'envoyer les données tant que le transfert n'est pas terminé.
-
-Cette communication se fait de manière synchronique (en une seule requête-réponse), mais il existe également des variantes pour la communication asynchrone, comme HTTP persistent connections ou WebSockets.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-19_b3822de4.md b/tests/logs/mistral:latest_2025-03-25_16-41-19_b3822de4.md
deleted file mode 100644
index 0ddc9a9..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-19_b3822de4.md
+++ /dev/null
@@ -1,36 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** b3822de4
-** Date :** 2025-03-25 16:41:19
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hypertext Transfer Protocol) est utilisé pour la transmission de données sur Internet. Il permet à différents systèmes informatiques de communiquer entre eux en échangeant des messages qui transmettent les requêtes et réponses des ressources web (pages web, images, vidéos, etc.).
-
-Le fonctionnement du protocole HTTP se déroule en plusieurs étapes :
-1. La première étape consiste à envoyer une requête HTTP par un client vers un serveur web. Cette requête indique la méthode (GET, POST, PUT, DELETE), l'URI de la ressource demandée, et les propriétés supplémentaires de la requête.
-2. Le serveur web reçoit la requête HTTP et traite celle-ci en fonction des instructions données dans le code source de la page web.
-3. Si la ressource est trouvée et que l'accès à cette ressource est autorisé, le serveur renvoie une réponse HTTP contenant les informations de la ressource demandée.
-4. Le client reçoit la réponse HTTP et la traite en fonction des propriétés renvoyées (statut de la requête, headers, etc.). Si la requête était un GET, le contenu de la ressource est affiché dans le navigateur.
-
-Ce protocole HTTP utilise des ports définis pour les communications, notamment le port 80 (HTTP) et le port 443 (HTTPS). Le port 80 est utilisé par défaut pour la transmission en clair, tandis que le port 443 est utilisé lorsque la communication se fait en utilisant une couche de sécurité SSL/TLS (Secure Sockets Layer/Transport Layer Security) pour protéger les données échangées.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-22_3b3e56af.md b/tests/logs/mistral:latest_2025-03-25_16-41-22_3b3e56af.md
deleted file mode 100644
index 08166ea..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-22_3b3e56af.md
+++ /dev/null
@@ -1,39 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 3b3e56af
-** Date :** 2025-03-25 16:41:22
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.0
-- Topp : 1.0
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hypertext Transfer Protocol) est un protocole de communication utilisé pour transférer des données sur le World Wide Web depuis un serveur vers un client web browser ou d'autres applications. Il fonctionne à la couche de transport (application layer) du modèle OSI et a été développé par Tim Berners-Lee en 1989.
-
-Le protocole HTTP utilise des requêtes et des réponses pour transférer les données entre le client et le serveur. Il dispose de différentes méthodes, telles que GET (pour demander une ressource), POST (pour envoyer des données au serveur pour en créer une nouvelle ressource), PUT (pour mettre à jour une ressource existante) et DELETE (pour supprimer une ressource).
-
-Il fonctionne sur la base de la communication client-serveur en suivant les étapes suivantes :
-
-1. Le client envoie une requête HTTP au serveur pour demander une ressource spécifique. La requête contient des informations telles que l'URL (Uniform Resource Locator) de la ressource demandée, le protocole à utiliser (HTTP ou HTTPS), les en-têtes supplémentaires et les données supplémentaires à envoyer (si nécessaire).
-2. Le serveur reçoit la requête du client et traite ensuite la demande pour trouver la ressource demandée et exécuter la méthode appropriée. Il renvoie une réponse HTTP au client qui contient des informations telles que le statut de la demande, les en-têtes supplémentaires et les données de la ressource demandée.
-3. Le client reçoit la réponse du serveur et affiche les données ou gère l'état de la demande selon les informations fournies par le serveur.
-4. La communication s'arrête ici, mais le client peut envoyer d'autres requêtes pour accéder à d'autres ressources ou mettre à jour des données existantes.
-
-Le protocole HTTP a évolué avec les années et est actuellement en version 1.1 depuis 2015. Il existe également une version légèrement différente appelée HTTP/2, qui a été publiée en 2015 et améliore la performance de la communication entre le client et le serveur grâce à des fonctionnalités telles que la multiplexation, les flux prioritaires et les requêtes parallèles.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-24_1ae96fc3.md b/tests/logs/mistral:latest_2025-03-25_16-41-24_1ae96fc3.md
deleted file mode 100644
index 943b4d2..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-24_1ae96fc3.md
+++ /dev/null
@@ -1,35 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 1ae96fc3
-** Date :** 2025-03-25 16:41:24
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 0.5
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hypertext Transfer Protocol) est utilisé pour transférer des données sur Internet entre des clients (navigateurs web ou applications) et des serveurs web. Les interactions HTTP sont généralement basées sur une requête-réponse modèle, où un client envoie une demande à un serveur et le serveur répond avec la réponse appropriée.
-
-Voici les étapes de fonctionnement de HTTP :
-
-1. Demande : Lorsque vous ouvrez votre navigateur web pour accéder à une page web, ce dernier envoie une demande HTTP vers le serveur qui héberge cette page. La demande contient diverses informations telles que la méthode de requête (GET, POST), l'URI (Uniform Resource Identifier) cible, les en-têtes et les données (pour des demandes POST).
-2. Réponse : Le serveur web reçoit la demande HTTP envoyée par le client et répond avec une réponse HTTP. La réponse contient généralement un code de statut, des en-têtes et les données requises (page HTML, image, etc.).
-3. Traitements supplémentaires : En fonction du code de statut, le serveur peut effectuer diverses actions avant d'envoyer la réponse au client. Par exemple, si la demande est une demande GET, le serveur peut consulter un fichier HTML dans son système de fichiers pour renvoyer la page à l'utilisateur.
-4. Envoi : Une fois les traitements supplémentaires effectués, le serveur envoie la réponse HTTP au client, qui peut afficher la page web ou utiliser les données pour d'autres applications.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-26_4cac6ccb.md b/tests/logs/mistral:latest_2025-03-25_16-41-26_4cac6ccb.md
deleted file mode 100644
index d2308b1..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-26_4cac6ccb.md
+++ /dev/null
@@ -1,36 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 4cac6ccb
-** Date :** 2025-03-25 16:41:26
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hypertext Transfer Protocol) est utilisé pour transférer des données sur le web. Il s'exécute en trois étapes principales :
-
-1. Requête : L'utilisateur ou un programme client envoie une requête HTTP à un serveur web, qui contient généralement une méthode (telle que GET pour récupérer des données), un chemin d'URL et des paramètres supplémentaires si nécessaire.
-
-2. Réponse : Le serveur web traite la requête et renvoie une réponse HTTP, qui contient généralement un code de statut (tel que 200 OK pour succès), un corps de données (les pages HTML, les images, etc.), des headers supplémentaires comme Cache-Control ou Content-Type.
-
-3. Communication continue : Les communications HTTP se basent souvent sur une série d'échanges entre le client et le serveur, avec chaque échange comportant une requête et une réponse correspondante. Ces échanges peuvent se poursuivre jusqu'à ce que la communication soit terminée ou arrêtée par l'un des interlocuteurs.
-
-Le protocole HTTP est basé sur le modèle client-serveur et fonctionne dans un système de réseau TCP/IP. Il utilise les ports 80 (HTTP) et 443 (HTTPS pour une communication sécurisée avec SSL/TLS). Le protocole HTTP est la base du fonctionnement des applications web et des services Internet aujourd'hui.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-41-28_c65ff62c.md b/tests/logs/mistral:latest_2025-03-25_16-41-28_c65ff62c.md
deleted file mode 100644
index c6529ff..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-41-28_c65ff62c.md
+++ /dev/null
@@ -1,39 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** c65ff62c
-** Date :** 2025-03-25 16:41:28
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Décris le fonctionnement du protocole HTTP.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 1.0
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Le protocole HTTP (Hypertext Transfer Protocol) est utilisé pour la communication entre les serveurs Web et les navigateurs clients sur Internet. Il est un des piliers fondamentaux de la World Wide Web.
-
-Le fonctionnement d'HTTP peut être décrit en quatre étapes principales :
-
-1. Demande (Request): Le navigateur client envoie une demande HTTP à un serveur Web spécifique pour récupérer des ressources (par exemple, une page web). L'en-tête de la requête contient l'identification du type de ressource demandée, ainsi que les informations telles que le format de données souhaité et le langage utilisé.
-2. Réponse (Response): Le serveur Web émet une réponse HTTP contenant l'information demandée ou un message d'erreur. L'en-tête de la réponse contient des informations telles que le statut de l'échange (par exemple, succès ou erreur), ainsi que les informations sur les ressources transmises, tels que le format de données et la longueur totale des données.
-3. Transfert de données: Le serveur Web transmet les données demandées au client via une connexion TCP. Les données sont divisées en paquets (segments) pour la transmission efficace.
-4. Fermeture de la connexion (Close): Une fois que le transfert des données est terminé, la connexion HTTP est fermée ou la demande du client peut être suivie d'une nouvelle demande, ce qui permet de transmettre plusieurs ressources à la suite en utilisant la même connexion.
-
-HTTP définit également les méthodes pour manipuler des ressources web, telles que GET (demander une ressource), POST (envoyer des données vers un serveur), PUT (envoyer des données pour remplacer une ressource existante) et DELETE (supprimer une ressource).
-
-Le protocole HTTP peut également être sécurisé grâce à la transmission de données en utilisant SSL/TLS, ce qui permet d'assurer une communication confidentielle entre le client et le serveur.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-43-51_5fd7dd0f.md b/tests/logs/mistral:latest_2025-03-25_16-43-51_5fd7dd0f.md
deleted file mode 100644
index 48d272b..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-43-51_5fd7dd0f.md
+++ /dev/null
@@ -1,37 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 5fd7dd0f
-** Date :** 2025-03-25 16:43:51
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** formateur
-** Prompt :** Explique ce qu'est le machine learning.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Bonjour! Je suis heureux d'aider! Le Machine Learning (ML) est une branche de l'Intelligence Artificielle qui permet aux ordinateurs d'apprendre automatiquement à effectuer des tâches, sans avoir besoin d'être explicitement programmés pour les résoudre. Les algorithmes de machine learning sont utilisés pour trouver des modèles dans un ensemble de données, afin de prédire ou décrire un phénomène ou une tendance à partir de ces données.
-
-Il y a plusieurs types de Machine Learning:
-
-1. L'Apprentissage Supervisé (Supervised Learning): Dans cet apprentissage, les algorithmes sont formés sur des données qui ont déjà été étiquetées. En d'autres termes, les entrées et les sorties sont connues. Les exemples les plus communs sont la classification binomiale (classement d'une entrée dans deux catégories) et la régression (prédiction numérique).
-2. L'Apprentissage Non Supervisé (Unsupervised Learning): Dans cet apprentissage, il n'y a pas d'étiquettes préalables pour les données. Les algorithmes cherchent des structures dans les données en utilisant des techniques telles que la clustering ou la factorisation matricielle.
-3. L'Apprentissage Apparié (Semi-supervised learning): Dans cet apprentissage, il y a un peu de données étiquetées et beaucoup de données non étiquetées. Les algorithmes cherchent à trouver des structures dans les données non étiquetées pour pouvoir étiqueter ces dernières de manière similaire aux données étiquetées existantes.
-4. L'Apprentissage Réinforced (Reinforcement Learning): Dans cet apprentissage, l'algorithme apprend à interagir avec un environnement en utilisant une récompense pour les actions correctes et une pénalité pour les actions incorrectes. Le but est de trouver un comportement qui maximise la récompense cumulative sur le long terme.
-
-En résumé, le Machine Learning est une méthode qui permet aux ordinateurs d'apprendre à effectuer des tâches sans avoir besoin d'être explicitement programmés pour les résoudre en utilisant des algorithmes adaptés et en apprenant des données existantes.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-43-52_21c9c37d.md b/tests/logs/mistral:latest_2025-03-25_16-43-52_21c9c37d.md
deleted file mode 100644
index 23e239e..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-43-52_21c9c37d.md
+++ /dev/null
@@ -1,28 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 21c9c37d
-** Date :** 2025-03-25 16:43:52
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** chercheur
-** Prompt :** Explique ce qu'est le machine learning.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Êtes-vous intéressé à apprendre plus sur l'apprentissage automatique ? Machine Learning (ML) est une branche de l'intelligence artificielle qui permet aux systèmes informatiques d'apprendre et d'améliorer leur performance sans être explicitement programmé pour le faire. Il s'agit d'une technique de traitement des données où les algorithmes sont utilisés pour trouver des modèles dans les données et prévoir des résultats à partir de ces modèles. Il y a trois grands types d'apprentissage automatique : l'apprentissage supervisé, l'apprentissage non-supervisé et l'apprentissage réinforcement. Le but de chaque type est de trouver des insights ou des modèles dans les données en utilisant des méthodes mathématiques et statistiques.
diff --git a/tests/logs/mistral:latest_2025-03-25_16-43-54_665b76d5.md b/tests/logs/mistral:latest_2025-03-25_16-43-54_665b76d5.md
deleted file mode 100644
index 0eddc68..0000000
--- a/tests/logs/mistral:latest_2025-03-25_16-43-54_665b76d5.md
+++ /dev/null
@@ -1,37 +0,0 @@
-# Résultat génération mistral:latest
-
-** Test ID:** 665b76d5
-** Date :** 2025-03-25 16:43:54
-** Modèle :** mistral:latest
-** Moteur :** Ollama
-** Rôle :** assistant_technique
-** Prompt :** Explique ce qu'est le machine learning.
-
----
-
-** Paramètres utilisés :**
-
-- Temperature : 1.5
-- Topp : 0.9
-- Topk : 50
-- Repeatpenalty : 1.1
-- Numpredict : 300
-- Stop : 
-- Seed : *Aucun*
-- Stream : *Aucun*
-- Raw : *Aucun*
-
----
-
-** Réponse du modèle
-
-Machine Learning (ML) est une branche des mathématiques et de l'informatique qui permet à un ordinateur d'apprendre automatiquement en analyseant les données, sans être explicitement programmé pour résoudre certains types de problèmes.
-
-Il s'agit donc d'un sous-domaine de l'intelligence artificielle qui permet à un ordinateur de reconnaître des structures dans une grande quantité de données et de les utiliser pour faire des prédictions ou des décisions en fonction des nouvelles données.
-
-Il existe plusieurs types de Machine Learning :
-- L'apprentissage supervisé, où le modèle apprend à reconnaître des structures à partir de données labélisées par un ensemble d'exemples.
-- L'apprentissage non supervisé, où le modèle apprend à reconnaître des structures sans aucune indication initiale sur ce qu'il devrait apprendre.
-- L'apprentissage réinforcé, où un agent doit apprendre à agir en fonction de la récompense ou de la pénalité associée aux actions effectuées.
-
-Le Machine Learning est utilisé dans de nombreuses domaines tels que la vision par ordinateur, l'analyse du langage naturel, la reconnaissance de voix, la prévision de marchés financiers ou encore les jeux vidéo.
diff --git a/tests/test_new_models.py b/tests/test_new_models.py
new file mode 100644
index 0000000..1c67a1a
--- /dev/null
+++ b/tests/test_new_models.py
@@ -0,0 +1,34 @@
+from core.factory import LLMFactory
+
+def test_all_models():
+    """Test simple de tous les modèles disponibles"""
+    # Liste des modèles à tester
+    model_names = ["mistral7b", "codellama13b-python", "llama2-13b"]
+    
+    for model_name in model_names:
+        print(f"\nTest du modèle {model_name}:")
+        try:
+            # Instanciation du modèle via la factory
+            model = LLMFactory.create(model_name)
+            print(f"✓ Modèle {model_name} instancié avec succès")
+            
+            # Test des attributs basiques
+            assert model.model is not None, "Le nom du modèle est None"
+            assert model.engine is not None, "Le moteur du modèle est None"
+            print(f"✓ Attributs du modèle {model_name} vérifiés")
+            
+            # Test d'accès aux paramètres
+            assert model.params is not None, "Les paramètres sont None"
+            assert "temperature" in model.params, "Le paramètre temperature n'est pas défini"
+            print(f"✓ Paramètres du modèle {model_name} vérifiés")
+            
+            # Affichage des informations du modèle
+            print(f"  - Nom du modèle: {model.model}")
+            print(f"  - Moteur: {model.engine}")
+            print(f"  - Température: {model.params.get('temperature')}")
+            
+        except Exception as e:
+            print(f"✗ Erreur avec le modèle {model_name}: {str(e)}")
+    
+if __name__ == "__main__":
+    test_all_models() 
\ No newline at end of file
diff --git a/tests/test_single_agent.py b/tests/test_single_agent.py
index 1ddb205..18efe27 100644
--- a/tests/test_single_agent.py
+++ b/tests/test_single_agent.py
@@ -3,10 +3,11 @@ import sys
 import os
 sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
 
-from core.factory import LLMFactory
-from agents.roles import AGENTS
+from utils.agent_manager import AgentManager
 
-model = LLMFactory.create("mistral7b")
-model.set_role("formateur", AGENTS["formateur"])
-response = model.generate("Qu'est-ce qu'une API REST?")
+# Utilisation de l'AgentManager pour créer l'agent avec le modèle approprié
+agent = AgentManager.create("test")  # Utilise l'agent "test" qui est configuré avec Mistral7B
+
+print(f"Test de l'agent '{agent.agent}' avec le modèle '{agent.model}'")
+response = agent.generate("Qu'est-ce qu'une API REST?")
 print("-> Réponse générée.")
diff --git a/update_monitor_for_ollama_path.md b/update_monitor_for_ollama_path.md
new file mode 100644
index 0000000..58a1947
--- /dev/null
+++ b/update_monitor_for_ollama_path.md
@@ -0,0 +1,292 @@
+# Adaptation du moniteur système pour le nouvel emplacement Ollama
+
+Ce guide explique comment modifier le moniteur système de LLM Lab pour qu'il détecte et affiche correctement l'emplacement des modèles Ollama sur un disque séparé.
+
+## 1. Modifications nécessaires dans system_monitor.py
+
+Ouvrez le fichier `system_monitor.py` et apportez les modifications suivantes pour détecter l'emplacement des modèles Ollama sur un disque séparé.
+
+### Fonction de détection du chemin des modèles
+
+Ajoutez cette nouvelle fonction au début de la classe `SystemMonitor`:
+
+```python
+def _get_ollama_models_path(self):
+    """Détecte l'emplacement des modèles Ollama"""
+    models_path = None
+    
+    # Vérifier si la variable d'environnement est définie
+    if 'OLLAMA_MODELS' in os.environ:
+        models_path = os.environ['OLLAMA_MODELS']
+        self._log(f"Chemin des modèles Ollama trouvé via variable d'environnement: {models_path}")
+        return models_path
+    
+    # Vérifier le chemin par défaut
+    default_path = os.path.expanduser(os.path.join("~", ".ollama", "models"))
+    
+    if platform.system() == "Windows":
+        # Vérifier si c'est un lien symbolique sous Windows
+        try:
+            import subprocess
+            result = subprocess.run(['dir', '/al', default_path], 
+                                  shell=True, capture_output=True, text=True)
+            
+            if "" in result.stdout:
+                # Extraire la cible du lien symbolique
+                for line in result.stdout.splitlines():
+                    if "" in line and "[" in line and "]" in line:
+                        target = line.split("[")[1].split("]")[0]
+                        models_path = target
+                        self._log(f"Lien symbolique détecté pour les modèles Ollama: {models_path}")
+                        return models_path
+        except:
+            pass
+    
+    # Si aucune redirection n'est trouvée, utiliser le chemin par défaut
+    if os.path.exists(default_path):
+        models_path = default_path
+    
+    return models_path or default_path
+```
+
+### Afficher l'emplacement des modèles dans l'interface
+
+Modifiez la méthode `_create_widgets` pour ajouter un affichage de l'emplacement des modèles dans l'onglet Ollama:
+
+```python
+# Dans _create_widgets, après la création de url_frame
+models_path_frame = ttk.Frame(server_frame)
+models_path_frame.pack(fill=tk.X, padx=5, pady=2)
+ttk.Label(models_path_frame, text="Modèles:").pack(side=tk.LEFT, padx=5)
+self.models_path_label = ttk.Label(models_path_frame, text="Vérification...")
+self.models_path_label.pack(side=tk.LEFT, padx=5)
+```
+
+### Mettre à jour l'information dans _update_ollama_info
+
+Ajoutez ce code au début de la méthode `_update_ollama_info`:
+
+```python
+# Mettre à jour l'emplacement des modèles
+models_path = self._get_ollama_models_path()
+self.models_path_label.config(text=models_path)
+
+# Vérifier l'espace disque pour les modèles
+if models_path and os.path.exists(models_path):
+    try:
+        import shutil
+        total, used, free = shutil.disk_usage(os.path.dirname(models_path))
+        total_gb = total / (1024**3)
+        used_gb = used / (1024**3)
+        free_gb = free / (1024**3)
+        
+        disk_info = f"{models_path} ({free_gb:.1f} GB libres / {total_gb:.1f} GB)"
+        self.models_path_label.config(text=disk_info)
+        
+        # Afficher un avertissement si l'espace libre est faible
+        if free_gb < 10:  # Moins de 10 GB libres
+            self.models_path_label.config(foreground="orange")
+            self._log(f"Avertissement: espace disque limité pour les modèles: {free_gb:.1f} GB")
+        elif free_gb < 5:  # Moins de 5 GB libres
+            self.models_path_label.config(foreground="red")
+            self._log(f"Alerte: espace disque très limité pour les modèles: {free_gb:.1f} GB")
+        else:
+            self.models_path_label.config(foreground="green")
+    except Exception as e:
+        self._log(f"Erreur lors de la vérification de l'espace disque: {str(e)}")
+```
+
+## 2. Ajout d'un onglet d'information sur les disques
+
+Pour un monitoring plus complet, ajoutez un nouvel onglet dédié à l'affichage de l'état des disques:
+
+```python
+# Dans _create_widgets, après la création de logs_frame
+# Onglet 5: Disques
+self.disks_frame = ttk.Frame(self.notebook)
+self.notebook.add(self.disks_frame, text="Disques")
+
+# Configuration de l'onglet Disques
+disks_label = ttk.Label(self.disks_frame, text="Stockage", font=("Arial", 14, "bold"))
+disks_label.pack(pady=10)
+
+# Tableau des disques
+disks_table_frame = ttk.LabelFrame(self.disks_frame, text="Volumes")
+disks_table_frame.pack(fill=tk.BOTH, expand=True, padx=10, pady=5)
+
+self.disks_tree = ttk.Treeview(disks_table_frame, 
+                               columns=("Lettre", "Total", "Utilisé", "Libre", "Type"),
+                               show='headings')
+self.disks_tree.heading("Lettre", text="Disque")
+self.disks_tree.heading("Total", text="Taille")
+self.disks_tree.heading("Utilisé", text="Utilisé")
+self.disks_tree.heading("Libre", text="Libre")
+self.disks_tree.heading("Type", text="Type")
+self.disks_tree.column("Lettre", width=70)
+self.disks_tree.column("Total", width=100)
+self.disks_tree.column("Utilisé", width=100)
+self.disks_tree.column("Libre", width=100)
+self.disks_tree.column("Type", width=150)
+self.disks_tree.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+```
+
+### Ajouter une méthode pour mettre à jour les informations de disque
+
+```python
+def _update_disks_info(self):
+    """Met à jour les informations sur les disques"""
+    try:
+        # Effacer le tableau
+        for item in self.disks_tree.get_children():
+            self.disks_tree.delete(item)
+        
+        if platform.system() == "Windows":
+            # Obtenir la liste des lecteurs
+            import string
+            import ctypes
+            
+            drives = []
+            bitmask = ctypes.windll.kernel32.GetLogicalDrives()
+            for letter in string.ascii_uppercase:
+                if bitmask & 1:
+                    drives.append(f"{letter}:")
+                bitmask >>= 1
+            
+            # Pour chaque lecteur, obtenir les informations
+            for drive in drives:
+                try:
+                    total, used, free = shutil.disk_usage(drive)
+                    total_gb = total / (1024**3)
+                    used_gb = used / (1024**3)
+                    free_gb = free / (1024**3)
+                    
+                    # Déterminer le type de disque
+                    drive_type = ctypes.windll.kernel32.GetDriveTypeW(drive)
+                    types = {
+                        0: "Inconnu",
+                        1: "Inexistant",
+                        2: "Amovible",
+                        3: "Fixe",
+                        4: "Réseau",
+                        5: "CD-ROM",
+                        6: "RAM Disk"
+                    }
+                    drive_type_str = types.get(drive_type, "Inconnu")
+                    
+                    # Ajouter au tableau
+                    percent = (used / total) * 100 if total > 0 else 0
+                    
+                    # Couleur selon l'espace libre
+                    if percent > 90:
+                        tag = "critical"
+                    elif percent > 75:
+                        tag = "warning"
+                    else:
+                        tag = ""
+                    
+                    self.disks_tree.insert("", tk.END, 
+                                          values=(drive, 
+                                                  f"{total_gb:.1f} GB",
+                                                  f"{used_gb:.1f} GB ({percent:.1f}%)",
+                                                  f"{free_gb:.1f} GB",
+                                                  drive_type_str),
+                                          tags=(tag,))
+                    
+                    # Vérifier si c'est le disque des modèles Ollama
+                    models_path = self._get_ollama_models_path()
+                    if models_path and drive in models_path:
+                        self._log(f"Disque des modèles Ollama: {drive} - {free_gb:.1f} GB libres")
+                        
+                except Exception as e:
+                    self.disks_tree.insert("", tk.END, 
+                                          values=(drive, "Erreur", "Erreur", "Erreur", str(e)),
+                                          tags=("error",))
+            
+            # Configurer les couleurs
+            self.disks_tree.tag_configure("critical", background="#ffcccc")
+            self.disks_tree.tag_configure("warning", background="#ffffcc")
+            self.disks_tree.tag_configure("error", background="#ff9999")
+            
+        else:
+            # Code pour Linux/Mac
+            # Utiliser psutil.disk_partitions() pour lister les partitions
+            for part in psutil.disk_partitions(all=False):
+                try:
+                    usage = psutil.disk_usage(part.mountpoint)
+                    total_gb = usage.total / (1024**3)
+                    used_gb = usage.used / (1024**3)
+                    free_gb = usage.free / (1024**3)
+                    
+                    # Ajouter au tableau
+                    self.disks_tree.insert("", tk.END, 
+                                          values=(part.mountpoint, 
+                                                  f"{total_gb:.1f} GB",
+                                                  f"{used_gb:.1f} GB ({usage.percent}%)",
+                                                  f"{free_gb:.1f} GB",
+                                                  f"{part.fstype}"))
+                    
+                except Exception as e:
+                    pass
+    except Exception as e:
+        self._log(f"Erreur lors de la mise à jour des informations disque: {str(e)}")
+```
+
+### Ajouter l'appel à la nouvelle méthode dans _update_loop
+
+Ajoutez cet appel dans la méthode `_update_loop` pour mettre à jour les informations disque régulièrement:
+
+```python
+# Dans _update_loop
+self._update_system_info()
+self._update_ollama_info()
+self._update_gpu_info()
+self._update_disks_info()  # Ajouter cette ligne
+```
+
+## 3. Test de la mise à jour
+
+Pour tester ces modifications:
+
+1. Appliquez les changements au fichier system_monitor.py
+2. Redémarrez le moniteur système
+3. Vérifiez que le chemin des modèles Ollama est correctement affiché
+4. Assurez-vous que l'espace disque est correctement détecté
+5. Testez avec différentes configurations (variable d'environnement, lien symbolique)
+
+## 4. Intégration avec le reste de LLM Lab
+
+Modifiez les autres fichiers qui pourraient avoir besoin de connaître l'emplacement des modèles:
+
+### Ajouter une fonction utilitaire dans utils/ollama_utils.py
+
+```python
+def get_ollama_models_path():
+    """Détecte l'emplacement des modèles Ollama de manière cohérente dans tout le projet"""
+    # Vérifier la variable d'environnement
+    if 'OLLAMA_MODELS' in os.environ:
+        return os.environ['OLLAMA_MODELS']
+    
+    # Vérifier si c'est un lien symbolique sous Windows
+    default_path = os.path.expanduser(os.path.join("~", ".ollama", "models"))
+    
+    if platform.system() == "Windows":
+        try:
+            import subprocess
+            result = subprocess.run(['dir', '/al', default_path], 
+                                  shell=True, capture_output=True, text=True)
+            
+            if "" in result.stdout:
+                for line in result.stdout.splitlines():
+                    if "" in line and "[" in line and "]" in line:
+                        return line.split("[")[1].split("]")[0]
+        except:
+            pass
+    
+    return default_path
+```
+
+Utilisez cette fonction dans les autres parties du code qui ont besoin de connaître l'emplacement des modèles.
+
+## Utilisation dans l'interface graphique
+
+Ces modifications permettront à l'utilisateur de voir clairement où sont stockés les modèles Ollama et de surveiller l'espace disque disponible pour éviter les problèmes lors du téléchargement de nouveaux modèles. 
\ No newline at end of file
diff --git a/utils/__pycache__/agent_manager.cpython-312.pyc b/utils/__pycache__/agent_manager.cpython-312.pyc
new file mode 100644
index 0000000..61f8ccb
Binary files /dev/null and b/utils/__pycache__/agent_manager.cpython-312.pyc differ
diff --git a/utils/__pycache__/chat_ui.cpython-312.pyc b/utils/__pycache__/chat_ui.cpython-312.pyc
new file mode 100644
index 0000000..7201230
Binary files /dev/null and b/utils/__pycache__/chat_ui.cpython-312.pyc differ
diff --git a/utils/__pycache__/system_monitor.cpython-312.pyc b/utils/__pycache__/system_monitor.cpython-312.pyc
new file mode 100644
index 0000000..801c1a3
Binary files /dev/null and b/utils/__pycache__/system_monitor.cpython-312.pyc differ
diff --git a/utils/agent_manager.py b/utils/agent_manager.py
new file mode 100644
index 0000000..f697bbd
--- /dev/null
+++ b/utils/agent_manager.py
@@ -0,0 +1,59 @@
+"""
+Gestionnaire d'agents permettant la création d'agents spécifiques avec leurs modèles associés
+"""
+from core.factory import LLMFactory
+from agents.roles import AGENTS
+
+class AgentManager:
+    """
+    Classe utilitaire pour créer et configurer des agents avec leurs modèles associés
+    """
+    
+    @staticmethod
+    def create(agent_name):
+        """
+        Crée et configure un agent avec le modèle approprié
+        
+        Args:
+            agent_name (str): Nom de l'agent à créer
+            
+        Returns:
+            BaseLLM: Instance du modèle configurée avec le rôle de l'agent
+            
+        Raises:
+            ValueError: Si l'agent n'existe pas
+        """
+        if agent_name not in AGENTS:
+            raise ValueError(f"Agent inconnu: {agent_name}")
+        
+        agent_config = AGENTS[agent_name]
+        
+        # Sélectionner le modèle spécifié pour l'agent ou utiliser mistral7b par défaut
+        model_name = agent_config.get("model", "mistral7b")
+        
+        # Créer le modèle
+        model = LLMFactory.create(model_name)
+        
+        # Appliquer la configuration de l'agent
+        model.set_role(agent_name, agent_config)
+        
+        return model
+    
+    @staticmethod
+    def list_agents():
+        """
+        Liste tous les agents disponibles avec leurs modèles associés
+        
+        Returns:
+            dict: Dictionnaire des agents et leurs modèles associés
+        """
+        agents_info = {}
+        
+        for agent_name, config in AGENTS.items():
+            model = config.get("model", "mistral7b")
+            agents_info[agent_name] = {
+                "model": model,
+                "description": config.get("system_prompt", "")[:50] + "..." if len(config.get("system_prompt", "")) > 50 else config.get("system_prompt", "")
+            }
+            
+        return agents_info 
\ No newline at end of file
diff --git a/utils/chat_ui.py b/utils/chat_ui.py
new file mode 100644
index 0000000..ccfa581
--- /dev/null
+++ b/utils/chat_ui.py
@@ -0,0 +1,980 @@
+"""
+Interface graphique pour le chat avec les modèles LLM
+"""
+import tkinter as tk
+from tkinter import ttk, scrolledtext, messagebox, filedialog
+import json
+import os
+from datetime import datetime
+from utils.agent_manager import AgentManager
+from core.factory import LLMFactory
+
+class ChatUI:
+    """Interface graphique pour interagir avec les agents LLM"""
+    
+    def __init__(self, root):
+        """Initialise l'interface graphique"""
+        self.root = root
+        self.root.title("LLM Lab - Chat")
+        self.root.geometry("1000x700")
+        self.root.minsize(800, 600)
+        
+        # Variables pour le chat
+        self.current_agent = None
+        self.conversation_history = []
+        self.custom_params = {}
+        self.history_files = []
+        
+        # Style
+        self.style = ttk.Style()
+        self.style.theme_use('alt')  # 'clam', 'alt', 'default', 'classic'
+        
+        # Création de l'interface
+        self._create_ui()
+        
+        # Chargement de la liste des agents
+        self._load_agents()
+        
+        # Chargement de l'historique des conversations
+        self._load_conversation_history()
+        
+    def _create_ui(self):
+        """Crée l'interface utilisateur"""
+        # Interface principale en deux parties
+        self.main_paned = ttk.PanedWindow(self.root, orient=tk.HORIZONTAL)
+        self.main_paned.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+        
+        # Panneau de gauche : configuration et historique
+        self.left_frame = ttk.Frame(self.main_paned, width=300)
+        self.main_paned.add(self.left_frame, weight=1)
+        
+        # Panneau de droite : chat
+        self.right_frame = ttk.Frame(self.main_paned)
+        self.main_paned.add(self.right_frame, weight=3)
+        
+        # Configuration du panneau de gauche
+        self._create_config_panel()
+        
+        # Configuration du panneau de droite
+        self._create_chat_panel()
+        
+    def _create_config_panel(self):
+        """Crée le panneau de configuration (gauche)"""
+        # Utilisation d'un notebook pour organiser les paramètres
+        self.config_notebook = ttk.Notebook(self.left_frame)
+        self.config_notebook.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+        
+        # Onglet 1: Sélection d'agent
+        self.agent_frame = ttk.Frame(self.config_notebook)
+        self.config_notebook.add(self.agent_frame, text="Agent")
+        
+        # Onglet 2: Paramètres
+        self.params_frame = ttk.Frame(self.config_notebook)
+        self.config_notebook.add(self.params_frame, text="Paramètres")
+        
+        # Onglet 3: Historique
+        self.history_frame = ttk.Frame(self.config_notebook)
+        self.config_notebook.add(self.history_frame, text="Historique")
+        
+        # Remplissage de l'onglet Agent
+        self._create_agent_tab()
+        
+        # Remplissage de l'onglet Paramètres
+        self._create_params_tab()
+        
+        # Remplissage de l'onglet Historique
+        self._create_history_tab()
+    
+    def _create_agent_tab(self):
+        """Crée l'onglet de sélection d'agent"""
+        # Label et liste des agents
+        ttk.Label(self.agent_frame, text="Sélectionnez un agent:", 
+                 font=("Arial", 11, "bold")).pack(pady=(10, 5), padx=5, anchor=tk.W)
+        
+        # Frame pour la liste des agents
+        agent_list_frame = ttk.Frame(self.agent_frame)
+        agent_list_frame.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+        
+        # Scrollbar
+        scrollbar = ttk.Scrollbar(agent_list_frame)
+        scrollbar.pack(side=tk.RIGHT, fill=tk.Y)
+        
+        # Liste des agents
+        self.agent_listbox = tk.Listbox(agent_list_frame, yscrollcommand=scrollbar.set, 
+                                       selectmode=tk.SINGLE, activestyle='dotbox', 
+                                       font=("Arial", 10))
+        self.agent_listbox.pack(fill=tk.BOTH, expand=True)
+        scrollbar.config(command=self.agent_listbox.yview)
+        
+        # Gestionnaire d'événements pour la sélection d'agent
+        self.agent_listbox.bind('<>', self._on_agent_select)
+        
+        # Informations sur l'agent
+        agent_info_frame = ttk.LabelFrame(self.agent_frame, text="Informations sur l'agent")
+        agent_info_frame.pack(fill=tk.X, padx=5, pady=5)
+        
+        # Description de l'agent
+        ttk.Label(agent_info_frame, text="Description:").pack(anchor=tk.W, padx=5, pady=(5, 0))
+        self.agent_description = tk.Text(agent_info_frame, wrap=tk.WORD, height=5, 
+                                        width=30, font=("Arial", 9))
+        self.agent_description.pack(fill=tk.X, padx=5, pady=5)
+        self.agent_description.config(state=tk.DISABLED)
+        
+        # Modèle utilisé
+        model_frame = ttk.Frame(agent_info_frame)
+        model_frame.pack(fill=tk.X, padx=5, pady=(0, 5))
+        ttk.Label(model_frame, text="Modèle:").pack(side=tk.LEFT, padx=(0, 5))
+        self.model_label = ttk.Label(model_frame, text="-")
+        self.model_label.pack(side=tk.LEFT)
+        
+        # Bouton pour changer de modèle
+        self.model_combo = ttk.Combobox(self.agent_frame, state="readonly")
+        self.model_combo.pack(fill=tk.X, padx=5, pady=5)
+        # Événement de changement
+        self.model_combo.bind("<>", self._on_model_change)
+        
+        # Bouton de test
+        test_btn = ttk.Button(self.agent_frame, text="Tester l'agent",
+                             command=self._test_agent)
+        test_btn.pack(fill=tk.X, padx=5, pady=(0, 10))
+    
+    def _create_params_tab(self):
+        """Crée l'onglet de configuration des paramètres"""
+        # Canvas et scrollbar pour permettre le défilement
+        canvas = tk.Canvas(self.params_frame)
+        scrollbar = ttk.Scrollbar(self.params_frame, orient="vertical", command=canvas.yview)
+        scroll_frame = ttk.Frame(canvas)
+        
+        scroll_frame.bind(
+            "",
+            lambda e: canvas.configure(scrollregion=canvas.bbox("all"))
+        )
+        
+        canvas.create_window((0, 0), window=scroll_frame, anchor="nw")
+        canvas.configure(yscrollcommand=scrollbar.set)
+        
+        canvas.pack(side="left", fill="both", expand=True)
+        scrollbar.pack(side="right", fill="y")
+        
+        # Titre
+        ttk.Label(scroll_frame, text="Paramètres du modèle:", 
+                 font=("Arial", 11, "bold")).pack(pady=(10, 5), padx=5, anchor=tk.W)
+        
+        # Température
+        temp_frame = ttk.Frame(scroll_frame)
+        temp_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(temp_frame, text="Température:").pack(side=tk.LEFT, padx=(0, 5))
+        self.temp_var = tk.DoubleVar(value=0.7)
+        temp_scale = ttk.Scale(temp_frame, from_=0.0, to=2.0, orient=tk.HORIZONTAL,
+                              variable=self.temp_var, length=150)
+        temp_scale.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=(0, 5))
+        temp_label = ttk.Label(temp_frame, textvariable=self.temp_var, width=5)
+        temp_label.pack(side=tk.LEFT)
+        self.temp_var.trace_add("write", self._on_param_change)
+        
+        # Top-p
+        top_p_frame = ttk.Frame(scroll_frame)
+        top_p_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(top_p_frame, text="Top-p:").pack(side=tk.LEFT, padx=(0, 5))
+        self.top_p_var = tk.DoubleVar(value=0.9)
+        top_p_scale = ttk.Scale(top_p_frame, from_=0.0, to=1.0, orient=tk.HORIZONTAL,
+                               variable=self.top_p_var, length=150)
+        top_p_scale.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=(0, 5))
+        top_p_label = ttk.Label(top_p_frame, textvariable=self.top_p_var, width=5)
+        top_p_label.pack(side=tk.LEFT)
+        self.top_p_var.trace_add("write", self._on_param_change)
+        
+        # Top-k
+        top_k_frame = ttk.Frame(scroll_frame)
+        top_k_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(top_k_frame, text="Top-k:").pack(side=tk.LEFT, padx=(0, 5))
+        self.top_k_var = tk.IntVar(value=40)
+        top_k_scale = ttk.Scale(top_k_frame, from_=0, to=100, orient=tk.HORIZONTAL,
+                               variable=self.top_k_var, length=150)
+        top_k_scale.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=(0, 5))
+        top_k_label = ttk.Label(top_k_frame, textvariable=self.top_k_var, width=5)
+        top_k_label.pack(side=tk.LEFT)
+        self.top_k_var.trace_add("write", self._on_param_change)
+        
+        # Repeat penalty
+        repeat_frame = ttk.Frame(scroll_frame)
+        repeat_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(repeat_frame, text="Repeat Penalty:").pack(side=tk.LEFT, padx=(0, 5))
+        self.repeat_var = tk.DoubleVar(value=1.1)
+        repeat_scale = ttk.Scale(repeat_frame, from_=1.0, to=2.0, orient=tk.HORIZONTAL,
+                                variable=self.repeat_var, length=150)
+        repeat_scale.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=(0, 5))
+        repeat_label = ttk.Label(repeat_frame, textvariable=self.repeat_var, width=5)
+        repeat_label.pack(side=tk.LEFT)
+        self.repeat_var.trace_add("write", self._on_param_change)
+        
+        # Tokens max
+        tokens_frame = ttk.Frame(scroll_frame)
+        tokens_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(tokens_frame, text="Tokens max:").pack(side=tk.LEFT, padx=(0, 5))
+        self.tokens_var = tk.IntVar(value=512)
+        tokens_scale = ttk.Scale(tokens_frame, from_=32, to=4096, orient=tk.HORIZONTAL,
+                                variable=self.tokens_var, length=150)
+        tokens_scale.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=(0, 5))
+        tokens_label = ttk.Label(tokens_frame, textvariable=self.tokens_var, width=5)
+        tokens_label.pack(side=tk.LEFT)
+        self.tokens_var.trace_add("write", self._on_param_change)
+        
+        # Boutons de gestion
+        buttons_frame = ttk.Frame(scroll_frame)
+        buttons_frame.pack(fill=tk.X, padx=5, pady=10)
+        
+        self.reset_btn = ttk.Button(buttons_frame, text="Réinitialiser", 
+                                   command=self._reset_params)
+        self.reset_btn.pack(side=tk.LEFT, padx=(0, 5))
+        
+        self.save_btn = ttk.Button(buttons_frame, text="Enregistrer",
+                                  command=self._save_params)
+        self.save_btn.pack(side=tk.LEFT)
+        
+        # Séparateur
+        ttk.Separator(scroll_frame, orient=tk.HORIZONTAL).pack(fill=tk.X, padx=5, pady=10)
+        
+        # Système de presets
+        ttk.Label(scroll_frame, text="Presets:", 
+                 font=("Arial", 11, "bold")).pack(pady=(5, 5), padx=5, anchor=tk.W)
+        
+        presets_frame = ttk.Frame(scroll_frame)
+        presets_frame.pack(fill=tk.X, padx=5, pady=5)
+        
+        self.preset_combo = ttk.Combobox(presets_frame, values=[
+            "Créatif", "Précis", "Équilibré", "Code", "Conversation"
+        ])
+        self.preset_combo.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=(0, 5))
+        self.preset_combo.current(2)  # Par défaut: Équilibré
+        
+        self.apply_preset_btn = ttk.Button(presets_frame, text="Appliquer",
+                                         command=self._apply_preset)
+        self.apply_preset_btn.pack(side=tk.LEFT)
+    
+    def _create_history_tab(self):
+        """Crée l'onglet d'historique des conversations"""
+        # Label
+        ttk.Label(self.history_frame, text="Historique des conversations:", 
+                 font=("Arial", 11, "bold")).pack(pady=(10, 5), padx=5, anchor=tk.W)
+        
+        # Liste des conversations
+        history_list_frame = ttk.Frame(self.history_frame)
+        history_list_frame.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+        
+        scrollbar = ttk.Scrollbar(history_list_frame)
+        scrollbar.pack(side=tk.RIGHT, fill=tk.Y)
+        
+        self.history_listbox = tk.Listbox(history_list_frame, yscrollcommand=scrollbar.set,
+                                         font=("Arial", 10))
+        self.history_listbox.pack(fill=tk.BOTH, expand=True)
+        scrollbar.config(command=self.history_listbox.yview)
+        
+        # Événement de sélection
+        self.history_listbox.bind('<>', self._on_history_select)
+        
+        # Boutons
+        button_frame = ttk.Frame(self.history_frame)
+        button_frame.pack(fill=tk.X, padx=5, pady=(0, 10))
+        
+        self.load_history_btn = ttk.Button(button_frame, text="Charger",
+                                         command=self._load_selected_history)
+        self.load_history_btn.pack(side=tk.LEFT, padx=(0, 5))
+        
+        self.delete_history_btn = ttk.Button(button_frame, text="Supprimer",
+                                          command=self._delete_history)
+        self.delete_history_btn.pack(side=tk.LEFT, padx=(0, 5))
+        
+        self.export_history_btn = ttk.Button(button_frame, text="Exporter",
+                                           command=self._export_history)
+        self.export_history_btn.pack(side=tk.LEFT)
+    
+    def _create_chat_panel(self):
+        """Crée le panneau de chat (droite)"""
+        # Titre
+        chat_title_frame = ttk.Frame(self.right_frame)
+        chat_title_frame.pack(fill=tk.X, padx=5, pady=5)
+        
+        self.chat_title = ttk.Label(chat_title_frame, text="Chat - Aucun agent sélectionné",
+                                   font=("Arial", 12, "bold"))
+        self.chat_title.pack(side=tk.LEFT)
+        
+        # Zone de chat
+        chat_frame = ttk.Frame(self.right_frame)
+        chat_frame.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+        
+        # Zone d'affichage des messages
+        self.chat_display = scrolledtext.ScrolledText(chat_frame, wrap=tk.WORD,
+                                                    font=("Arial", 10))
+        self.chat_display.pack(fill=tk.BOTH, expand=True)
+        self.chat_display.config(state=tk.DISABLED)
+        
+        # Zone de saisie
+        input_frame = ttk.Frame(self.right_frame)
+        input_frame.pack(fill=tk.X, padx=5, pady=(0, 5))
+        
+        self.user_input = scrolledtext.ScrolledText(input_frame, wrap=tk.WORD,
+                                                  height=3, font=("Arial", 10))
+        self.user_input.pack(fill=tk.X, pady=(0, 5))
+        self.user_input.bind("", self._on_shift_enter)
+        
+        # Boutons d'action
+        button_frame = ttk.Frame(self.right_frame)
+        button_frame.pack(fill=tk.X, padx=5, pady=(0, 5))
+        
+        self.send_btn = ttk.Button(button_frame, text="Envoyer", width=10,
+                                  command=self._send_message)
+        self.send_btn.pack(side=tk.RIGHT, padx=(5, 0))
+        
+        self.clear_btn = ttk.Button(button_frame, text="Effacer", width=10,
+                                  command=self._clear_chat)
+        self.clear_btn.pack(side=tk.RIGHT, padx=(5, 0))
+        
+        self.new_chat_btn = ttk.Button(button_frame, text="Nouvelle conversation", width=20,
+                                     command=self._new_chat)
+        self.new_chat_btn.pack(side=tk.RIGHT)
+        
+        # Barre d'état
+        self.status_bar = ttk.Label(self.right_frame, text="Prêt", relief=tk.SUNKEN, anchor=tk.W)
+        self.status_bar.pack(side=tk.BOTTOM, fill=tk.X)
+        
+    def _load_agents(self):
+        """Charge la liste des agents disponibles"""
+        # Effacer la liste actuelle
+        self.agent_listbox.delete(0, tk.END)
+        
+        # Récupérer les agents
+        agents_info = AgentManager.list_agents()
+        
+        # Ajouter les agents à la liste
+        for agent_name in agents_info:
+            self.agent_listbox.insert(tk.END, agent_name)
+        
+        # Charger la liste des modèles disponibles
+        self._load_models()
+    
+    def _load_models(self):
+        """Charge la liste des modèles disponibles"""
+        try:
+            # Récupérer les modèles disponibles
+            models = LLMFactory.get_available_models()
+            self.model_combo['values'] = models
+        except Exception as e:
+            print(f"Erreur lors du chargement des modèles: {str(e)}")
+            self.model_combo['values'] = ["mistral:latest", "codellama:13b-python", "llama2:13b"]
+    
+    def _on_agent_select(self, event):
+        """Gestionnaire d'événement pour la sélection d'un agent"""
+        # Récupérer l'index sélectionné
+        selection = self.agent_listbox.curselection()
+        if not selection:
+            return
+            
+        # Récupérer le nom de l'agent
+        agent_name = self.agent_listbox.get(selection[0])
+        
+        # Récupérer les informations de l'agent
+        agents_info = AgentManager.list_agents()
+        if agent_name not in agents_info:
+            return
+            
+        agent_info = agents_info[agent_name]
+        
+        # Mettre à jour les informations affichées
+        self.agent_description.config(state=tk.NORMAL)
+        self.agent_description.delete(1.0, tk.END)
+        self.agent_description.insert(tk.END, agent_info['description'])
+        self.agent_description.config(state=tk.DISABLED)
+        
+        # Mettre à jour le modèle
+        model_name = agent_info['model']
+        self.model_label.config(text=model_name)
+        
+        # Sélectionner le modèle dans la combobox
+        if model_name in self.model_combo['values']:
+            self.model_combo.set(model_name)
+        
+        # Mettre à jour le titre du chat
+        self.chat_title.config(text=f"Chat avec {agent_name} ({model_name})")
+        
+        # Mettre à jour l'agent courant
+        self.current_agent = agent_name
+        
+        # Charger les paramètres de l'agent
+        self._load_agent_params(agent_name)
+        
+        # Mettre à jour le statut
+        self.status_bar.config(text=f"Agent {agent_name} sélectionné avec le modèle {model_name}")
+
+    def _on_model_change(self, event):
+        """Gestionnaire d'événement pour le changement de modèle"""
+        if not self.current_agent:
+            messagebox.showwarning("Aucun agent sélectionné", 
+                                  "Veuillez d'abord sélectionner un agent.")
+            return
+            
+        # Récupérer le modèle sélectionné
+        model_name = self.model_combo.get()
+        
+        # Mettre à jour l'affichage
+        self.model_label.config(text=model_name)
+        
+        # Mettre à jour le titre du chat
+        self.chat_title.config(text=f"Chat avec {self.current_agent} ({model_name})")
+        
+        # Mettre à jour les paramètres du modèle
+        self._load_model_params(model_name)
+        
+        # Mettre à jour le statut
+        self.status_bar.config(text=f"Modèle changé pour {model_name}")
+        
+    def _test_agent(self):
+        """Fonction de test rapide de l'agent sélectionné"""
+        if not self.current_agent:
+            messagebox.showwarning("Aucun agent sélectionné", 
+                                  "Veuillez d'abord sélectionner un agent.")
+            return
+            
+        # Message de test
+        test_message = "Présente-toi brièvement et explique tes capacités."
+        
+        # Ajouter le message au chat
+        self._add_message_to_chat("Utilisateur", test_message)
+        
+        # Générer une réponse
+        try:
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Génération en cours...")
+            self.root.update()
+            
+            # Créer l'agent avec les paramètres personnalisés
+            agent = self._create_agent_with_custom_params()
+            
+            # Générer la réponse
+            response = agent.generate(test_message)
+            
+            # Ajouter la réponse au chat
+            self._add_message_to_chat(self.current_agent, response)
+            
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Test terminé")
+            
+        except Exception as e:
+            messagebox.showerror("Erreur", f"Erreur lors du test de l'agent: {str(e)}")
+            self.status_bar.config(text=f"Erreur lors du test")
+            
+    def _on_param_change(self, *args):
+        """Gestionnaire d'événement pour le changement des paramètres"""
+        if not self.current_agent:
+            return
+            
+        # Mettre à jour les paramètres personnalisés
+        self.custom_params = {
+            "temperature": self.temp_var.get(),
+            "top_p": self.top_p_var.get(),
+            "top_k": self.top_k_var.get(),
+            "repeat_penalty": self.repeat_var.get(),
+            "num_predict": self.tokens_var.get()
+        }
+        
+    def _reset_params(self):
+        """Réinitialise les paramètres aux valeurs par défaut de l'agent"""
+        if not self.current_agent:
+            messagebox.showwarning("Aucun agent sélectionné", 
+                                  "Veuillez d'abord sélectionner un agent.")
+            return
+            
+        # Charger les paramètres de l'agent
+        self._load_agent_params(self.current_agent)
+        
+        # Mettre à jour le statut
+        self.status_bar.config(text=f"Paramètres réinitialisés")
+        
+    def _save_params(self):
+        """Enregistre les paramètres personnalisés"""
+        if not self.current_agent:
+            messagebox.showwarning("Aucun agent sélectionné", 
+                                  "Veuillez d'abord sélectionner un agent.")
+            return
+            
+        # Créer le dossier de sauvegarde si nécessaire
+        save_dir = "saved_params"
+        os.makedirs(save_dir, exist_ok=True)
+        
+        # Nom du fichier de sauvegarde
+        file_name = f"{save_dir}/{self.current_agent}_{self.model_combo.get()}.json"
+        
+        # Enregistrer les paramètres
+        with open(file_name, "w") as f:
+            json.dump(self.custom_params, f, indent=2)
+            
+        # Mettre à jour le statut
+        self.status_bar.config(text=f"Paramètres enregistrés dans {file_name}")
+        
+    def _apply_preset(self):
+        """Applique un preset de paramètres"""
+        preset = self.preset_combo.get()
+        
+        # Définir les presets
+        presets = {
+            "Créatif": {
+                "temperature": 1.2,
+                "top_p": 0.95,
+                "top_k": 60,
+                "repeat_penalty": 1.0,
+                "num_predict": 1024
+            },
+            "Précis": {
+                "temperature": 0.3,
+                "top_p": 0.85,
+                "top_k": 30,
+                "repeat_penalty": 1.2,
+                "num_predict": 512
+            },
+            "Équilibré": {
+                "temperature": 0.7,
+                "top_p": 0.9,
+                "top_k": 40,
+                "repeat_penalty": 1.1,
+                "num_predict": 768
+            },
+            "Code": {
+                "temperature": 0.2,
+                "top_p": 0.95,
+                "top_k": 30,
+                "repeat_penalty": 1.2,
+                "num_predict": 2048
+            },
+            "Conversation": {
+                "temperature": 0.8,
+                "top_p": 0.92,
+                "top_k": 50,
+                "repeat_penalty": 1.05,
+                "num_predict": 512
+            }
+        }
+        
+        # Appliquer le preset
+        if preset in presets:
+            params = presets[preset]
+            
+            # Mettre à jour les variables
+            self.temp_var.set(params["temperature"])
+            self.top_p_var.set(params["top_p"])
+            self.top_k_var.set(params["top_k"])
+            self.repeat_var.set(params["repeat_penalty"])
+            self.tokens_var.set(params["num_predict"])
+            
+            # Mettre à jour les paramètres personnalisés
+            self.custom_params = params.copy()
+            
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Preset '{preset}' appliqué")
+            
+    def _load_agent_params(self, agent_name):
+        """Charge les paramètres par défaut de l'agent"""
+        try:
+            # Récupérer la configuration de l'agent
+            from agents.roles import AGENTS
+            
+            if agent_name in AGENTS:
+                agent_config = AGENTS[agent_name]
+                params = agent_config.get("params", {})
+                
+                # Mettre à jour les variables avec les valeurs par défaut
+                self.temp_var.set(params.get("temperature", 0.7))
+                self.top_p_var.set(params.get("top_p", 0.9))
+                self.top_k_var.set(params.get("top_k", 40))
+                self.repeat_var.set(params.get("repeat_penalty", 1.1))
+                self.tokens_var.set(params.get("num_predict", 512))
+                
+                # Mettre à jour les paramètres personnalisés
+                self.custom_params = params.copy()
+                
+        except Exception as e:
+            print(f"Erreur lors du chargement des paramètres de l'agent: {str(e)}")
+            
+    def _load_model_params(self, model_name):
+        """Charge les paramètres par défaut du modèle"""
+        # Vérifier si un fichier de paramètres personnalisés existe
+        save_dir = "saved_params"
+        file_name = f"{save_dir}/{self.current_agent}_{model_name}.json"
+        
+        if os.path.exists(file_name):
+            try:
+                # Charger les paramètres personnalisés
+                with open(file_name, "r") as f:
+                    params = json.load(f)
+                    
+                # Mettre à jour les variables
+                self.temp_var.set(params.get("temperature", 0.7))
+                self.top_p_var.set(params.get("top_p", 0.9))
+                self.top_k_var.set(params.get("top_k", 40))
+                self.repeat_var.set(params.get("repeat_penalty", 1.1))
+                self.tokens_var.set(params.get("num_predict", 512))
+                
+                # Mettre à jour les paramètres personnalisés
+                self.custom_params = params.copy()
+                
+                # Mettre à jour le statut
+                self.status_bar.config(text=f"Paramètres personnalisés chargés depuis {file_name}")
+                
+            except Exception as e:
+                print(f"Erreur lors du chargement des paramètres personnalisés: {str(e)}")
+                
+        else:
+            # Si aucun fichier personnalisé, charger les paramètres par défaut
+            self._load_agent_params(self.current_agent)
+            
+    def _create_agent_with_custom_params(self):
+        """Crée un agent avec les paramètres personnalisés"""
+        if not self.current_agent:
+            raise ValueError("Aucun agent sélectionné")
+            
+        # Créer l'agent
+        agent = AgentManager.create(self.current_agent)
+        
+        # Appliquer les paramètres personnalisés
+        for key, value in self.custom_params.items():
+            agent.params[key] = value
+            
+        # Appliquer le modèle si différent
+        model_name = self.model_combo.get()
+        if model_name != agent.model:
+            # Créer un nouveau modèle
+            from core.factory import LLMFactory
+            new_model = LLMFactory.create(model_name)
+            
+            # Copier les paramètres
+            new_model.params.update(agent.params)
+            new_model.system_prompt = agent.system_prompt
+            new_model.agent = agent.agent
+            
+            agent = new_model
+            
+        return agent
+
+    def _load_conversation_history(self):
+        """Charge l'historique des conversations"""
+        # Créer le dossier d'historique si nécessaire
+        history_dir = "chat_history"
+        os.makedirs(history_dir, exist_ok=True)
+        
+        # Lister les fichiers d'historique
+        self.history_files = []
+        for file in os.listdir(history_dir):
+            if file.endswith(".json"):
+                self.history_files.append(os.path.join(history_dir, file))
+        
+        # Trier par date (plus récent en premier)
+        self.history_files.sort(key=os.path.getmtime, reverse=True)
+        
+        # Mettre à jour la liste d'historique
+        self.history_listbox.delete(0, tk.END)
+        
+        for file in self.history_files:
+            try:
+                with open(file, "r", encoding="utf-8") as f:
+                    history = json.load(f)
+                    
+                # Extraire les informations
+                agent = history.get("agent", "Inconnu")
+                date = history.get("date", "Inconnue")
+                messages = history.get("messages", [])
+                
+                # Ajouter à la liste
+                if messages:
+                    first_message = messages[0].get("content", "")
+                    preview = first_message[:30] + "..." if len(first_message) > 30 else first_message
+                    self.history_listbox.insert(tk.END, f"{agent} - {date} - {preview}")
+                    
+            except Exception as e:
+                print(f"Erreur lors du chargement de l'historique {file}: {str(e)}")
+                
+    def _on_history_select(self, event):
+        """Gestionnaire d'événement pour la sélection d'un historique"""
+        # Récupérer l'index sélectionné
+        selection = self.history_listbox.curselection()
+        if not selection:
+            return
+            
+        # Activer le bouton de chargement
+        self.load_history_btn.config(state=tk.NORMAL)
+        
+    def _load_selected_history(self):
+        """Charge l'historique sélectionné"""
+        # Récupérer l'index sélectionné
+        selection = self.history_listbox.curselection()
+        if not selection or selection[0] >= len(self.history_files):
+            return
+            
+        # Récupérer le fichier d'historique
+        file = self.history_files[selection[0]]
+        
+        try:
+            # Charger l'historique
+            with open(file, "r", encoding="utf-8") as f:
+                history = json.load(f)
+                
+            # Extraire les informations
+            agent = history.get("agent", None)
+            messages = history.get("messages", [])
+            
+            # Sélectionner l'agent si disponible
+            if agent:
+                # Trouver l'index de l'agent dans la listbox
+                for i in range(self.agent_listbox.size()):
+                    if self.agent_listbox.get(i) == agent:
+                        self.agent_listbox.selection_clear(0, tk.END)
+                        self.agent_listbox.selection_set(i)
+                        self.agent_listbox.see(i)
+                        self._on_agent_select(None)
+                        break
+            
+            # Effacer le chat actuel
+            self._clear_chat()
+            
+            # Ajouter les messages au chat
+            for message in messages:
+                sender = message.get("sender", "Inconnu")
+                content = message.get("content", "")
+                self._add_message_to_chat(sender, content, add_to_history=False)
+                
+            # Mettre à jour l'historique
+            self.conversation_history = messages
+            
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Historique chargé depuis {file}")
+            
+        except Exception as e:
+            messagebox.showerror("Erreur", f"Erreur lors du chargement de l'historique: {str(e)}")
+            
+    def _delete_history(self):
+        """Supprime l'historique sélectionné"""
+        # Récupérer l'index sélectionné
+        selection = self.history_listbox.curselection()
+        if not selection or selection[0] >= len(self.history_files):
+            return
+            
+        # Récupérer le fichier d'historique
+        file = self.history_files[selection[0]]
+        
+        # Demander confirmation
+        if messagebox.askyesno("Confirmation", f"Voulez-vous vraiment supprimer cet historique ?"):
+            try:
+                # Supprimer le fichier
+                os.remove(file)
+                
+                # Mettre à jour la liste
+                self.history_files.pop(selection[0])
+                self.history_listbox.delete(selection[0])
+                
+                # Mettre à jour le statut
+                self.status_bar.config(text=f"Historique supprimé")
+                
+            except Exception as e:
+                messagebox.showerror("Erreur", f"Erreur lors de la suppression: {str(e)}")
+                
+    def _export_history(self):
+        """Exporte l'historique sélectionné"""
+        # Récupérer l'index sélectionné
+        selection = self.history_listbox.curselection()
+        if not selection or selection[0] >= len(self.history_files):
+            return
+            
+        # Récupérer le fichier d'historique
+        file = self.history_files[selection[0]]
+        
+        try:
+            # Charger l'historique
+            with open(file, "r", encoding="utf-8") as f:
+                history = json.load(f)
+            
+            # Ouvrir une boîte de dialogue pour choisir l'emplacement d'exportation
+            export_file = filedialog.asksaveasfilename(
+                defaultextension=".md",
+                filetypes=[("Markdown", "*.md"), ("Texte", "*.txt"), ("JSON", "*.json")],
+                title="Exporter l'historique"
+            )
+            
+            if not export_file:
+                return
+                
+            # Format d'exportation selon l'extension
+            ext = os.path.splitext(export_file)[1].lower()
+            
+            if ext == ".json":
+                # Exporter au format JSON
+                with open(export_file, "w", encoding="utf-8") as f:
+                    json.dump(history, f, indent=2, ensure_ascii=False)
+                    
+            elif ext == ".md" or ext == ".txt":
+                # Exporter au format Markdown/Texte
+                with open(export_file, "w", encoding="utf-8") as f:
+                    # En-tête
+                    agent = history.get("agent", "Inconnu")
+                    date = history.get("date", "Inconnue")
+                    f.write(f"# Conversation avec {agent} - {date}\n\n")
+                    
+                    # Messages
+                    for message in history.get("messages", []):
+                        sender = message.get("sender", "Inconnu")
+                        content = message.get("content", "")
+                        
+                        if ext == ".md":
+                            f.write(f"## {sender}\n\n{content}\n\n")
+                        else:
+                            f.write(f"{sender}:\n{content}\n\n")
+            
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Historique exporté vers {export_file}")
+            
+        except Exception as e:
+            messagebox.showerror("Erreur", f"Erreur lors de l'exportation: {str(e)}")
+            
+    def _on_shift_enter(self, event):
+        """Gestionnaire d'événement pour Shift+Enter"""
+        # Ajouter un saut de ligne
+        return
+        
+    def _send_message(self):
+        """Envoie le message saisi par l'utilisateur"""
+        if not self.current_agent:
+            messagebox.showwarning("Aucun agent sélectionné", 
+                                  "Veuillez d'abord sélectionner un agent.")
+            return
+            
+        # Récupérer le message
+        message = self.user_input.get(1.0, tk.END).strip()
+        
+        if not message:
+            return
+            
+        # Effacer le champ de saisie
+        self.user_input.delete(1.0, tk.END)
+        
+        # Ajouter le message au chat
+        self._add_message_to_chat("Utilisateur", message)
+        
+        # Générer une réponse
+        try:
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Génération en cours...")
+            self.root.update()
+            
+            # Créer l'agent avec les paramètres personnalisés
+            agent = self._create_agent_with_custom_params()
+            
+            # Générer la réponse
+            response = agent.generate(message)
+            
+            # Ajouter la réponse au chat
+            self._add_message_to_chat(self.current_agent, response)
+            
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Réponse générée")
+            
+        except Exception as e:
+            messagebox.showerror("Erreur", f"Erreur lors de la génération: {str(e)}")
+            self.status_bar.config(text=f"Erreur lors de la génération")
+            
+    def _add_message_to_chat(self, sender, content, add_to_history=True):
+        """Ajoute un message au chat"""
+        # Activer la zone de chat pour modification
+        self.chat_display.config(state=tk.NORMAL)
+        
+        # Ajouter le message
+        self.chat_display.insert(tk.END, f"{sender}:\n", "sender")
+        self.chat_display.insert(tk.END, f"{content}\n\n", "message")
+        
+        # Configurer les tags
+        self.chat_display.tag_configure("sender", font=("Arial", 10, "bold"))
+        self.chat_display.tag_configure("message", font=("Arial", 10))
+        
+        # Défiler vers le bas
+        self.chat_display.see(tk.END)
+        
+        # Désactiver la zone de chat
+        self.chat_display.config(state=tk.DISABLED)
+        
+        # Ajouter à l'historique
+        if add_to_history:
+            self.conversation_history.append({
+                "sender": sender,
+                "content": content,
+                "timestamp": datetime.now().isoformat()
+            })
+            
+            # Sauvegarder l'historique
+            self._save_conversation_history()
+            
+    def _clear_chat(self):
+        """Efface le contenu du chat"""
+        # Effacer la zone de chat
+        self.chat_display.config(state=tk.NORMAL)
+        self.chat_display.delete(1.0, tk.END)
+        self.chat_display.config(state=tk.DISABLED)
+        
+        # Ne pas effacer l'historique
+        
+    def _new_chat(self):
+        """Démarre une nouvelle conversation"""
+        # Demander confirmation si la conversation actuelle n'est pas vide
+        if self.conversation_history and messagebox.askyesno(
+            "Nouvelle conversation", 
+            "Voulez-vous démarrer une nouvelle conversation ?"
+        ):
+            # Effacer la zone de chat
+            self._clear_chat()
+            
+            # Réinitialiser l'historique
+            self.conversation_history = []
+            
+            # Mettre à jour le statut
+            self.status_bar.config(text=f"Nouvelle conversation démarrée")
+            
+    def _save_conversation_history(self):
+        """Sauvegarde l'historique de la conversation actuelle"""
+        if not self.conversation_history or not self.current_agent:
+            return
+            
+        # Créer le dossier d'historique si nécessaire
+        history_dir = "chat_history"
+        os.makedirs(history_dir, exist_ok=True)
+        
+        # Créer un ID unique pour la conversation
+        now = datetime.now()
+        date_str = now.strftime("%Y-%m-%d_%H-%M-%S")
+        file_name = f"{history_dir}/{self.current_agent}_{date_str}.json"
+        
+        # Préparer les données
+        history_data = {
+            "agent": self.current_agent,
+            "model": self.model_combo.get(),
+            "date": now.strftime("%Y-%m-%d %H:%M:%S"),
+            "params": self.custom_params,
+            "messages": self.conversation_history
+        }
+        
+        # Sauvegarder l'historique
+        try:
+            with open(file_name, "w", encoding="utf-8") as f:
+                json.dump(history_data, f, indent=2, ensure_ascii=False)
+                
+            # Mettre à jour la liste des fichiers d'historique
+            if file_name not in self.history_files:
+                self.history_files.insert(0, file_name)
+                self.history_listbox.insert(0, f"{self.current_agent} - {now.strftime('%Y-%m-%d %H:%M:%S')}")
+                
+        except Exception as e:
+            print(f"Erreur lors de la sauvegarde de l'historique: {str(e)}")
+
+
+def main():
+    """Point d'entrée principal"""
+    root = tk.Tk()
+    app = ChatUI(root)
+    root.mainloop()
+
+if __name__ == "__main__":
+    main() 
\ No newline at end of file
diff --git a/utils/system_monitor.py b/utils/system_monitor.py
new file mode 100644
index 0000000..08f85e3
--- /dev/null
+++ b/utils/system_monitor.py
@@ -0,0 +1,534 @@
+"""
+Moniteur de ressources système pour Ollama et les ressources NVIDIA GPU
+"""
+import tkinter as tk
+from tkinter import ttk
+import psutil
+import threading
+import time
+import subprocess
+import json
+import os
+import platform
+import requests
+from datetime import datetime
+
+class SystemMonitor:
+    def __init__(self, root):
+        self.root = root
+        self.root.title("Moniteur LLM Lab")
+        self.root.geometry("800x600")
+        self.root.minsize(700, 500)
+        
+        # Style
+        self.style = ttk.Style()
+        self.style.theme_use('alt')  # 'clam', 'alt', 'default', 'classic'
+        
+        # Variables
+        self.update_interval = 2  # secondes
+        self.running = True
+        self.ollama_models = []
+        self.active_model = None
+        self.gpu_available = self._check_gpu_available()
+        
+        # Création de l'UI
+        self._create_widgets()
+        
+        # Démarrer le thread de mise à jour
+        self.update_thread = threading.Thread(target=self._update_loop)
+        self.update_thread.daemon = True
+        self.update_thread.start()
+        
+        # Intercepter la fermeture de la fenêtre
+        self.root.protocol("WM_DELETE_WINDOW", self._on_close)
+        
+    def _create_widgets(self):
+        # Créer le notebook (onglets)
+        self.notebook = ttk.Notebook(self.root)
+        self.notebook.pack(fill=tk.BOTH, expand=True, padx=10, pady=10)
+        
+        # Onglet 1: Surveillance système
+        self.system_frame = ttk.Frame(self.notebook)
+        self.notebook.add(self.system_frame, text="Système")
+        
+        # Onglet 2: Ollama
+        self.ollama_frame = ttk.Frame(self.notebook)
+        self.notebook.add(self.ollama_frame, text="Ollama")
+        
+        # Onglet 3: GPU
+        self.gpu_frame = ttk.Frame(self.notebook)
+        self.notebook.add(self.gpu_frame, text="GPU")
+        
+        # Onglet 4: Logs
+        self.logs_frame = ttk.Frame(self.notebook)
+        self.notebook.add(self.logs_frame, text="Logs")
+        
+        # === Configuration de l'onglet Système ===
+        system_label = ttk.Label(self.system_frame, text="Ressources Système", font=("Arial", 14, "bold"))
+        system_label.pack(pady=10)
+        
+        # Infos système
+        system_info_frame = ttk.LabelFrame(self.system_frame, text="Informations Système")
+        system_info_frame.pack(fill=tk.X, padx=10, pady=5)
+        
+        # OS
+        os_frame = ttk.Frame(system_info_frame)
+        os_frame.pack(fill=tk.X, padx=5, pady=2)
+        ttk.Label(os_frame, text="Système d'exploitation:").pack(side=tk.LEFT, padx=5)
+        self.os_label = ttk.Label(os_frame, text="")
+        self.os_label.pack(side=tk.LEFT, padx=5)
+        
+        # CPU
+        cpu_frame = ttk.Frame(system_info_frame)
+        cpu_frame.pack(fill=tk.X, padx=5, pady=2)
+        ttk.Label(cpu_frame, text="Processeur:").pack(side=tk.LEFT, padx=5)
+        self.cpu_label = ttk.Label(cpu_frame, text="")
+        self.cpu_label.pack(side=tk.LEFT, padx=5)
+        
+        # RAM
+        ram_frame = ttk.Frame(system_info_frame)
+        ram_frame.pack(fill=tk.X, padx=5, pady=2)
+        ttk.Label(ram_frame, text="Mémoire RAM:").pack(side=tk.LEFT, padx=5)
+        self.ram_label = ttk.Label(ram_frame, text="")
+        self.ram_label.pack(side=tk.LEFT, padx=5)
+        
+        # Barres de progression
+        progress_frame = ttk.LabelFrame(self.system_frame, text="Utilisation des ressources")
+        progress_frame.pack(fill=tk.X, padx=10, pady=5)
+        
+        # CPU Usage
+        cpu_usage_frame = ttk.Frame(progress_frame)
+        cpu_usage_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(cpu_usage_frame, text="CPU:").pack(side=tk.LEFT, padx=5)
+        self.cpu_progress = ttk.Progressbar(cpu_usage_frame, orient=tk.HORIZONTAL, length=300, mode='determinate')
+        self.cpu_progress.pack(side=tk.LEFT, padx=5, fill=tk.X, expand=True)
+        self.cpu_percent = ttk.Label(cpu_usage_frame, text="0%")
+        self.cpu_percent.pack(side=tk.LEFT, padx=5)
+        
+        # RAM Usage
+        ram_usage_frame = ttk.Frame(progress_frame)
+        ram_usage_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(ram_usage_frame, text="RAM:").pack(side=tk.LEFT, padx=5)
+        self.ram_progress = ttk.Progressbar(ram_usage_frame, orient=tk.HORIZONTAL, length=300, mode='determinate')
+        self.ram_progress.pack(side=tk.LEFT, padx=5, fill=tk.X, expand=True)
+        self.ram_percent = ttk.Label(ram_usage_frame, text="0%")
+        self.ram_percent.pack(side=tk.LEFT, padx=5)
+        
+        # Disk Usage
+        disk_usage_frame = ttk.Frame(progress_frame)
+        disk_usage_frame.pack(fill=tk.X, padx=5, pady=5)
+        ttk.Label(disk_usage_frame, text="Disque:").pack(side=tk.LEFT, padx=5)
+        self.disk_progress = ttk.Progressbar(disk_usage_frame, orient=tk.HORIZONTAL, length=300, mode='determinate')
+        self.disk_progress.pack(side=tk.LEFT, padx=5, fill=tk.X, expand=True)
+        self.disk_percent = ttk.Label(disk_usage_frame, text="0%")
+        self.disk_percent.pack(side=tk.LEFT, padx=5)
+        
+        # === Configuration de l'onglet Ollama ===
+        ollama_label = ttk.Label(self.ollama_frame, text="Serveur Ollama", font=("Arial", 14, "bold"))
+        ollama_label.pack(pady=10)
+        
+        # État du serveur
+        server_frame = ttk.LabelFrame(self.ollama_frame, text="État du serveur")
+        server_frame.pack(fill=tk.X, padx=10, pady=5)
+        
+        # Status
+        status_frame = ttk.Frame(server_frame)
+        status_frame.pack(fill=tk.X, padx=5, pady=2)
+        ttk.Label(status_frame, text="Statut:").pack(side=tk.LEFT, padx=5)
+        self.status_label = ttk.Label(status_frame, text="Vérification...")
+        self.status_label.pack(side=tk.LEFT, padx=5)
+        
+        # URL
+        url_frame = ttk.Frame(server_frame)
+        url_frame.pack(fill=tk.X, padx=5, pady=2)
+        ttk.Label(url_frame, text="URL:").pack(side=tk.LEFT, padx=5)
+        self.url_label = ttk.Label(url_frame, text="http://localhost:11434")
+        self.url_label.pack(side=tk.LEFT, padx=5)
+        
+        # Modèles disponibles
+        models_frame = ttk.LabelFrame(self.ollama_frame, text="Modèles disponibles")
+        models_frame.pack(fill=tk.BOTH, expand=True, padx=10, pady=5)
+        
+        # Liste des modèles
+        self.tree = ttk.Treeview(models_frame, columns=("Taille", "Modifié"), show='headings')
+        self.tree.heading("Taille", text="Taille")
+        self.tree.heading("Modifié", text="Modifié")
+        self.tree.column("Taille", width=100)
+        self.tree.column("Modifié", width=150)
+        self.tree.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+        
+        # Boutons
+        button_frame = ttk.Frame(self.ollama_frame)
+        button_frame.pack(fill=tk.X, padx=10, pady=5)
+        
+        refresh_button = ttk.Button(button_frame, text="Rafraîchir", command=self._refresh_ollama)
+        refresh_button.pack(side=tk.LEFT, padx=5)
+        
+        # === Configuration de l'onglet GPU ===
+        gpu_label = ttk.Label(self.gpu_frame, text="Ressources GPU", font=("Arial", 14, "bold"))
+        gpu_label.pack(pady=10)
+        
+        if self.gpu_available:
+            # Infos GPU
+            gpu_info_frame = ttk.LabelFrame(self.gpu_frame, text="Informations GPU")
+            gpu_info_frame.pack(fill=tk.X, padx=10, pady=5)
+            
+            # Modèle GPU
+            gpu_model_frame = ttk.Frame(gpu_info_frame)
+            gpu_model_frame.pack(fill=tk.X, padx=5, pady=2)
+            ttk.Label(gpu_model_frame, text="Modèle:").pack(side=tk.LEFT, padx=5)
+            self.gpu_model_label = ttk.Label(gpu_model_frame, text="")
+            self.gpu_model_label.pack(side=tk.LEFT, padx=5)
+            
+            # Mémoire GPU
+            gpu_memory_frame = ttk.Frame(gpu_info_frame)
+            gpu_memory_frame.pack(fill=tk.X, padx=5, pady=2)
+            ttk.Label(gpu_memory_frame, text="Mémoire:").pack(side=tk.LEFT, padx=5)
+            self.gpu_memory_label = ttk.Label(gpu_memory_frame, text="")
+            self.gpu_memory_label.pack(side=tk.LEFT, padx=5)
+            
+            # Utilisation GPU
+            gpu_usage_frame = ttk.LabelFrame(self.gpu_frame, text="Utilisation")
+            gpu_usage_frame.pack(fill=tk.X, padx=10, pady=5)
+            
+            # GPU Compute
+            gpu_compute_frame = ttk.Frame(gpu_usage_frame)
+            gpu_compute_frame.pack(fill=tk.X, padx=5, pady=5)
+            ttk.Label(gpu_compute_frame, text="Calcul:").pack(side=tk.LEFT, padx=5)
+            self.gpu_compute_progress = ttk.Progressbar(gpu_compute_frame, orient=tk.HORIZONTAL, length=300, mode='determinate')
+            self.gpu_compute_progress.pack(side=tk.LEFT, padx=5, fill=tk.X, expand=True)
+            self.gpu_compute_percent = ttk.Label(gpu_compute_frame, text="0%")
+            self.gpu_compute_percent.pack(side=tk.LEFT, padx=5)
+            
+            # GPU Memory
+            gpu_mem_usage_frame = ttk.Frame(gpu_usage_frame)
+            gpu_mem_usage_frame.pack(fill=tk.X, padx=5, pady=5)
+            ttk.Label(gpu_mem_usage_frame, text="Mémoire:").pack(side=tk.LEFT, padx=5)
+            self.gpu_mem_progress = ttk.Progressbar(gpu_mem_usage_frame, orient=tk.HORIZONTAL, length=300, mode='determinate')
+            self.gpu_mem_progress.pack(side=tk.LEFT, padx=5, fill=tk.X, expand=True)
+            self.gpu_mem_percent = ttk.Label(gpu_mem_usage_frame, text="0%")
+            self.gpu_mem_percent.pack(side=tk.LEFT, padx=5)
+            
+            # Température
+            gpu_temp_frame = ttk.Frame(gpu_usage_frame)
+            gpu_temp_frame.pack(fill=tk.X, padx=5, pady=5)
+            ttk.Label(gpu_temp_frame, text="Température:").pack(side=tk.LEFT, padx=5)
+            self.gpu_temp_progress = ttk.Progressbar(gpu_temp_frame, orient=tk.HORIZONTAL, length=300, mode='determinate')
+            self.gpu_temp_progress.pack(side=tk.LEFT, padx=5, fill=tk.X, expand=True)
+            self.gpu_temp_label = ttk.Label(gpu_temp_frame, text="0°C")
+            self.gpu_temp_label.pack(side=tk.LEFT, padx=5)
+            
+            # Graphiques processe actifs
+            gpu_processes_frame = ttk.LabelFrame(self.gpu_frame, text="Processus GPU")
+            gpu_processes_frame.pack(fill=tk.BOTH, expand=True, padx=10, pady=5)
+            
+            # Liste des processus
+            self.gpu_process_tree = ttk.Treeview(gpu_processes_frame, 
+                                               columns=("PID", "Nom", "Mémoire"), 
+                                               show='headings')
+            self.gpu_process_tree.heading("PID", text="PID")
+            self.gpu_process_tree.heading("Nom", text="Processus")
+            self.gpu_process_tree.heading("Mémoire", text="Mémoire")
+            self.gpu_process_tree.column("PID", width=50)
+            self.gpu_process_tree.column("Nom", width=200)
+            self.gpu_process_tree.column("Mémoire", width=100)
+            self.gpu_process_tree.pack(fill=tk.BOTH, expand=True, padx=5, pady=5)
+        else:
+            no_gpu_label = ttk.Label(self.gpu_frame, 
+                                    text="Aucun GPU NVIDIA détecté.", 
+                                    font=("Arial", 12))
+            no_gpu_label.pack(pady=50)
+            
+            install_label = ttk.Label(self.gpu_frame, 
+                                     text="Pour surveiller un GPU NVIDIA, installez nvidia-smi et nvitop.", 
+                                     font=("Arial", 10))
+            install_label.pack(pady=10)
+        
+        # === Configuration de l'onglet Logs ===
+        logs_label = ttk.Label(self.logs_frame, text="Journaux d'activité", font=("Arial", 14, "bold"))
+        logs_label.pack(pady=10)
+        
+        # Zone de logs
+        log_area_frame = ttk.Frame(self.logs_frame)
+        log_area_frame.pack(fill=tk.BOTH, expand=True, padx=10, pady=5)
+        
+        # Scrollbar
+        scrollbar = ttk.Scrollbar(log_area_frame)
+        scrollbar.pack(side=tk.RIGHT, fill=tk.Y)
+        
+        # Text area
+        self.log_text = tk.Text(log_area_frame, yscrollcommand=scrollbar.set)
+        self.log_text.pack(fill=tk.BOTH, expand=True)
+        scrollbar.config(command=self.log_text.yview)
+        
+        # Boutons
+        log_button_frame = ttk.Frame(self.logs_frame)
+        log_button_frame.pack(fill=tk.X, padx=10, pady=5)
+        
+        clear_log_button = ttk.Button(log_button_frame, text="Effacer les logs", 
+                                     command=lambda: self.log_text.delete(1.0, tk.END))
+        clear_log_button.pack(side=tk.LEFT, padx=5)
+        
+        # Barre d'état en bas
+        self.status_bar = ttk.Label(self.root, text="Moniteur LLM Lab - Dernière mise à jour: Jamais", 
+                                  relief=tk.SUNKEN, anchor=tk.W)
+        self.status_bar.pack(side=tk.BOTTOM, fill=tk.X)
+        
+    def _update_loop(self):
+        """Thread principal de mise à jour"""
+        while self.running:
+            try:
+                # Mise à jour système
+                self._update_system_info()
+                
+                # Mise à jour Ollama
+                if self.notebook.index(self.notebook.select()) == 1:  # Onglet Ollama
+                    self._update_ollama_info()
+                
+                # Mise à jour GPU
+                if self.gpu_available and self.notebook.index(self.notebook.select()) == 2:  # Onglet GPU
+                    self._update_gpu_info()
+                
+                # Mise à jour de la barre d'état
+                now = datetime.now().strftime("%H:%M:%S")
+                self.status_bar.config(text=f"Moniteur LLM Lab - Dernière mise à jour: {now}")
+                
+            except Exception as e:
+                self._log(f"Erreur de mise à jour: {str(e)}")
+            
+            time.sleep(self.update_interval)
+    
+    def _update_system_info(self):
+        """Met à jour les informations système"""
+        # Informations système
+        self.os_label.config(text=f"{platform.system()} {platform.release()}")
+        self.cpu_label.config(text=f"{psutil.cpu_count(logical=False)} cœurs ({psutil.cpu_count()} threads)")
+        
+        # Détection avancée de la RAM
+        try:
+            ram = psutil.virtual_memory()
+            total_ram = ram.total / (1024 * 1024 * 1024)  # GB
+            
+            # Vérification supplémentaire pour Linux
+            if platform.system() == "Linux":
+                try:
+                    # Utiliser /proc/meminfo pour une détection plus précise
+                    with open('/proc/meminfo', 'r') as f:
+                        for line in f:
+                            if 'MemTotal' in line:
+                                # MemTotal est en kB
+                                mem_kb = int(line.split()[1])
+                                linux_ram = mem_kb / (1024 * 1024)  # GB
+                                # Utiliser la valeur la plus élevée
+                                total_ram = max(total_ram, linux_ram)
+                                break
+                except Exception as e:
+                    self._log(f"Erreur lors de la lecture de /proc/meminfo: {str(e)}")
+            
+            self.ram_label.config(text=f"{total_ram:.1f} GB")
+        except Exception as e:
+            self._log(f"Erreur lors de la détection de la RAM: {str(e)}")
+            self.ram_label.config(text="Détection impossible")
+        
+        # Utilisation CPU
+        cpu_percent = psutil.cpu_percent()
+        self.cpu_progress["value"] = cpu_percent
+        self.cpu_percent.config(text=f"{cpu_percent:.1f}%")
+        
+        # Utilisation RAM
+        ram_percent = ram.percent
+        self.ram_progress["value"] = ram_percent
+        self.ram_percent.config(text=f"{ram_percent:.1f}%")
+        
+        # Utilisation disque
+        disk = psutil.disk_usage('/')
+        disk_percent = disk.percent
+        self.disk_progress["value"] = disk_percent
+        self.disk_percent.config(text=f"{disk_percent:.1f}%")
+    
+    def _update_ollama_info(self):
+        """Met à jour les informations Ollama"""
+        try:
+            # Vérifier si le serveur est en cours d'exécution
+            response = requests.get("http://localhost:11434/api/tags", timeout=2)
+            
+            if response.status_code == 200:
+                self.status_label.config(text="En ligne", foreground="green")
+                
+                # Mettre à jour la liste des modèles
+                data = response.json()
+                models = data.get("models", [])
+                
+                # Effacer la liste actuelle
+                for item in self.tree.get_children():
+                    self.tree.delete(item)
+                
+                # Ajouter les modèles
+                for model in models:
+                    model_name = model.get("name", "")
+                    model_size = self._format_size(model.get("size", 0))
+                    modified = model.get("modified_at", "")
+                    # Convertir le format de date
+                    if modified:
+                        try:
+                            modified_dt = datetime.fromisoformat(modified.replace('Z', '+00:00'))
+                            modified = modified_dt.strftime("%d/%m/%Y %H:%M")
+                        except:
+                            pass
+                    
+                    self.tree.insert("", tk.END, text=model_name, values=(model_size, modified), iid=model_name)
+                
+                # Mettre à jour la liste globale
+                self.ollama_models = [model.get("name", "") for model in models]
+                
+                # Vérifier s'il y a un modèle actif
+                if self.active_model:
+                    self._log(f"Modèle actif: {self.active_model}")
+                    # Mettre en surbrillance le modèle actif
+                    if self.active_model in self.ollama_models:
+                        self.tree.selection_set(self.active_model)
+                        self.tree.see(self.active_model)
+            else:
+                self.status_label.config(text="Erreur", foreground="red")
+                self._log(f"Erreur de connexion au serveur Ollama: {response.status_code}")
+                
+        except requests.exceptions.RequestException:
+            self.status_label.config(text="Hors ligne", foreground="red")
+            self._log("Serveur Ollama non disponible")
+    
+    def _update_gpu_info(self):
+        """Met à jour les informations GPU"""
+        if not self.gpu_available:
+            return
+            
+        try:
+            # Exécuter nvidia-smi pour obtenir les informations GPU
+            result = subprocess.run(
+                ['nvidia-smi', '--query-gpu=name,memory.total,memory.used,utilization.gpu,temperature.gpu', 
+                 '--format=csv,noheader,nounits'],
+                capture_output=True, 
+                text=True, 
+                check=True
+            )
+            
+            if result.returncode == 0:
+                # Analyser les résultats
+                gpu_data = result.stdout.strip().split(',')
+                
+                if len(gpu_data) >= 5:
+                    # Nom du modèle
+                    model_name = gpu_data[0].strip()
+                    self.gpu_model_label.config(text=model_name)
+                    
+                    # Mémoire totale et utilisée
+                    total_memory = float(gpu_data[1].strip())
+                    used_memory = float(gpu_data[2].strip())
+                    memory_percent = (used_memory / total_memory) * 100 if total_memory > 0 else 0
+                    
+                    self.gpu_memory_label.config(text=f"{used_memory:.0f} MiB / {total_memory:.0f} MiB")
+                    self.gpu_mem_progress["value"] = memory_percent
+                    self.gpu_mem_percent.config(text=f"{memory_percent:.1f}%")
+                    
+                    # Utilisation GPU
+                    gpu_util = float(gpu_data[3].strip())
+                    self.gpu_compute_progress["value"] = gpu_util
+                    self.gpu_compute_percent.config(text=f"{gpu_util:.1f}%")
+                    
+                    # Température
+                    temp = float(gpu_data[4].strip())
+                    # Échelle de température: 0-100°C
+                    self.gpu_temp_progress["value"] = temp
+                    self.gpu_temp_label.config(text=f"{temp:.1f}°C")
+            
+            # Récupérer les processus GPU
+            result_processes = subprocess.run(
+                ['nvidia-smi', '--query-compute-apps=pid,name,used_memory', '--format=csv,noheader,nounits'],
+                capture_output=True, 
+                text=True
+            )
+            
+            if result_processes.returncode == 0:
+                # Effacer la liste actuelle
+                for item in self.gpu_process_tree.get_children():
+                    self.gpu_process_tree.delete(item)
+                
+                # Ajouter les processus
+                processes = result_processes.stdout.strip().split('\n')
+                for process in processes:
+                    if process.strip():
+                        process_data = process.split(',')
+                        if len(process_data) >= 3:
+                            pid = process_data[0].strip()
+                            name = process_data[1].strip()
+                            memory = f"{process_data[2].strip()} MiB"
+                            
+                            # Ajouter à la liste
+                            self.gpu_process_tree.insert("", tk.END, text=pid, values=(pid, name, memory))
+                            
+                            # Si c'est Ollama, marquer comme modèle actif
+                            if "ollama" in name.lower():
+                                self._log(f"Ollama détecté sur GPU: PID {pid}, utilisant {memory}")
+                                # Chercher quel modèle est actif
+                                try:
+                                    process_info = psutil.Process(int(pid))
+                                    cmd_line = " ".join(process_info.cmdline())
+                                    for model in self.ollama_models:
+                                        if model in cmd_line:
+                                            self.active_model = model
+                                            self._log(f"Modèle actif détecté: {model}")
+                                            break
+                                except:
+                                    pass
+                                    
+        except subprocess.SubprocessError as e:
+            self._log(f"Erreur lors de l'exécution de nvidia-smi: {str(e)}")
+        except Exception as e:
+            self._log(f"Erreur de mise à jour GPU: {str(e)}")
+    
+    def _refresh_ollama(self):
+        """Force le rafraîchissement des informations Ollama"""
+        self._update_ollama_info()
+        self._log("Informations Ollama rafraîchies")
+    
+    def _check_gpu_available(self):
+        """Vérifie si un GPU NVIDIA est disponible"""
+        try:
+            result = subprocess.run(['nvidia-smi'], capture_output=True, text=True)
+            return result.returncode == 0
+        except:
+            return False
+    
+    def _format_size(self, size_bytes):
+        """Formate la taille en unités lisibles"""
+        if size_bytes < 1024:
+            return f"{size_bytes} B"
+        elif size_bytes < 1024 * 1024:
+            return f"{size_bytes/1024:.1f} KB"
+        elif size_bytes < 1024 * 1024 * 1024:
+            return f"{size_bytes/(1024*1024):.1f} MB"
+        else:
+            return f"{size_bytes/(1024*1024*1024):.1f} GB"
+    
+    def _log(self, message):
+        """Ajoute un message aux logs"""
+        timestamp = datetime.now().strftime("%H:%M:%S")
+        log_message = f"[{timestamp}] {message}\n"
+        
+        # Ajouter au texte
+        self.log_text.insert(tk.END, log_message)
+        self.log_text.see(tk.END)  # Défiler vers le bas
+    
+    def _on_close(self):
+        """Gère la fermeture de l'application"""
+        self.running = False
+        time.sleep(0.5)  # Attendre que le thread se termine
+        self.root.destroy()
+
+def main():
+    """Point d'entrée principal"""
+    root = tk.Tk()
+    app = SystemMonitor(root)
+    root.mainloop()
+
+if __name__ == "__main__":
+    main() 
\ No newline at end of file